Improvements for IB handling V8
Subsystems (3)
Alex Deucher
maintainercover Improvements for IB handling V8
This set contains a number of bug fixes and cleanups for IB handling that I worked on over the holidays. The first the three patches from V1 are already reviewed, so I didn't include them in V2 or V3. The first patches from V3 have been reviewed so I did not include them either.
Patch 1:
Fix for ring resets. In V8, return the proper job status so scheduler re-adds the job to the pending list itself.
Patches 2-4:
Removes the direct submit path for IBs and requires that all IB submissions use a job structure. This greatly simplifies the IB submission code. V2 uses GFP_ATOMIC when in reset. V3 sqaushes all of the IP changes into one patch. Not sure there is much value breaking this out per IP. V4 uses the pool type to determine the alloc flags. No changes in V8.
Patches 5-9:
Improvements for adapter resets. Properly add the bad job back to the pending list so we can stop calling drm_sched_stop/start(). Return the proper error number in the CS IOCTL when the context is guilty. Now that that is handled properly we can call drm_sched_increase_karma() for ring resets as well. Properly set the error on the the timedout fence for adapter resets. These changes also resulted in a small clean up the the VCN reset helper. In V8, patch 5 is updated to return the proper job status so the scheduler adds the job back to the pending list itself.
Patch 10-12:
Rework the backup and reemit code for per ring reset so that we can safely reemit repeatedly. This removes the current single reemit limit currently in place. V4 saves and restores the fences rather than emitting them directly and also saves and reemits the vm flush contents. V5 simplifies and further cleans things up. V6 reworks the IB schedule sequence to cleanly split the vm fence state from the IB fence state. This greatly simplifies the reemit code as the VM state is no longer intermixed with the IB state. V7 adds some minor improvements to the IB bookkeeping in the fences. No changes in V8.
Git tree available as well:
https://gitlab.freedesktop.org/agd5f/linux/-/commits/ib_improvements8?ref_type=heads
Alex Deucher (12):
drm/amdgpu: re-add the bad job to the pending list for ring resets drm/amdgpu/job: use GFP_ATOMIC while in gpu reset drm/amdgpu: switch all IPs to using job for IBs drm/amdgpu: require a job to schedule an IB
drm/amdgpu: don't call drm_sched_stop/start() in asic reset drm/amdgpu/cs: return -ETIME for guilty contexts drm/amdgpu: plumb timedout fence through to force completion drm/amdgpu: simplify VCN reset helper
drm/amdgpu: Call drm_sched_increase_karma() for ring resets drm/amdgpu: reorder IB schedule sequence
drm/amdgpu: add a helper to calculate ring distance drm/amdgpu: rework ring reset backup and reemit v8
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c | 4 +- drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c | 4 +- drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c | 2 +- drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 10 +- drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c | 124 ++++++++-------- drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c | 152 +++++++++----------- drivers/gpu/drm/amd/amdgpu/amdgpu_job.c | 27 ++-- drivers/gpu/drm/amd/amdgpu/amdgpu_job.h | 2 +- drivers/gpu/drm/amd/amdgpu/amdgpu_object.h | 2 +- drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c | 50 ++----- drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h | 44 +++--- drivers/gpu/drm/amd/amdgpu/amdgpu_sa.c | 5 +- drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c | 4 +- drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c | 2 +- drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c | 52 +++---- drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 7 + drivers/gpu/drm/amd/amdgpu/amdgpu_vpe.c | 37 ++--- drivers/gpu/drm/amd/amdgpu/cik_sdma.c | 31 ++-- drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c | 29 ++-- drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c | 29 ++-- drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c | 29 ++-- drivers/gpu/drm/amd/amdgpu/gfx_v12_1.c | 29 ++-- drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c | 24 ++-- drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c | 25 ++-- drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c | 139 +++++++++--------- drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c | 138 +++++++++--------- drivers/gpu/drm/amd/amdgpu/gfx_v9_4_2.c | 26 ++-- drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c | 29 ++-- drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c | 38 ++--- drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c | 38 ++--- drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c | 38 ++--- drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c | 38 ++--- drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c | 37 ++--- drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c | 36 ++--- drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c | 36 ++--- drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c | 36 ++--- drivers/gpu/drm/amd/amdgpu/sdma_v7_1.c | 36 ++--- drivers/gpu/drm/amd/amdgpu/si_dma.c | 29 ++-- drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c | 2 +- drivers/gpu/drm/amd/amdgpu/vcn_v5_0_1.c | 2 +- 40 files changed, 725 insertions(+), 697 deletions(-)
Signature · 1 line
2.52.0
Alex Deucher
maintainerPATCH 1/12 drm/amdgpu: re-add the bad job to the pending list for ring resets
Returning DRM_GPU_SCHED_STAT_NO_HANG causes the scheduler to add the bad job back the pending list. We've already set the errors on the fence and killed the bad job at this point so it's the correct behavior.
--- drivers/gpu/drm/amd/amdgpu/amdgpu_job.c | 9 ++++++++- drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c | 4 ---- 2 files changed, 8 insertions(+), 5 deletions(-)
drivers/gpu/drm/amd/amdgpu/amdgpu_job.c +8 -1
@@ -92,6 +92,7 @@ static enum drm_gpu_sched_stat amdgpu_job_timedout(struct drm_sched_job *s_job)struct drm_wedge_task_info *info =NULL ;struct amdgpu_task_info *ti =NULL ;struct amdgpu_device *adev = ring->adev; +enum drm_gpu_sched_stat status =DRM_GPU_SCHED_STAT_RESET ;int idx, r;if (!drm_dev_enter (adev_to_drm (adev), &idx)) {
@@ -135,13 +136,19 @@ static enum drm_gpu_sched_stat amdgpu_job_timedout(struct drm_sched_job *s_job) ring->funcs->reset) {dev_err (adev->dev,"Starting %s ring reset\n" , s_job->sched->name); +/* Stop the scheduler to prevent anybody else from touching the ring buffer. */ +drm_sched_wqueue_stop (&ring->sched); r =amdgpu_ring_reset (ring, job->vmid, job->hw_fence);if (!r) { +/* Start the scheduler again */ +drm_sched_wqueue_start (&ring->sched);atomic_inc (&ring->adev->gpu_reset_counter);dev_err (adev->dev,"Ring %s reset succeeded\n" , ring->sched.name);drm_dev_wedged_event (adev_to_drm (adev),DRM_WEDGE_RECOVERY_NONE , info); +/* This is needed to add the job back to the pending list */ + status =DRM_GPU_SCHED_STAT_NO_HANG ; goto exit; }dev_err (adev->dev,"Ring %s reset failed\n" , ring->sched.name);
@@ -177,7 +184,7 @@ static enum drm_gpu_sched_stat amdgpu_job_timedout(struct drm_sched_job *s_job) exit:amdgpu_vm_put_task_info (ti);drm_dev_exit (idx); -return DRM_GPU_SCHED_STAT_RESET ; +return status; } int amdgpu_job_alloc(struct amdgpu_device *adev, struct amdgpu_vm *vm,
drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c +0 -4
@@ -868,8 +868,6 @@ bool amdgpu_ring_sched_ready(struct amdgpu_ring *ring)void amdgpu_ring_reset_helper_begin (struct amdgpu_ring *ring,struct amdgpu_fence *guilty_fence) { -/* Stop the scheduler to prevent anybody else from touching the ring buffer. */ -drm_sched_wqueue_stop (&ring->sched);/* back up the non-guilty commands */ amdgpu_ring_backup_unprocessed_commands (ring, guilty_fence); }
@@ -895,8 +893,6 @@ int amdgpu_ring_reset_helper_end(struct amdgpu_ring *ring,amdgpu_ring_write (ring, ring->ring_backup[i]);amdgpu_ring_commit (ring); } -/* Start the scheduler again */ -drm_sched_wqueue_start (&ring->sched);return 0 ; }
Signature · 1 line
2.52.0
Re: [PATCH 01/12] drm/amdgpu: re-add the bad job to the pending list for ring resets
Le 30/01/2026 à 18:30, Alex Deucher a écrit :
Quoted 6 lines
Returning
DRM_GPU_SCHED_STAT_NO_HANGcauses the scheduler to add the bad job back the pending list. We've already set the errors on the fence and killed the bad job at this point so it's the correct behavior.Signed-off-by Alex Deucher <[email protected]>
Quoted 68 lines
--- drivers/gpu/drm/amd/amdgpu/amdgpu_job.c | 9 ++++++++- drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c | 4 ---- 2 files changed, 8 insertions(+), 5 deletions(-)drivers/gpu/drm/amd/amdgpu/amdgpu_job.c +8
-1@@ -92,6 +92,7 @@ static enum drm_gpu_sched_stat amdgpu_job_timedout(struct drm_sched_job *s_job)struct drm_wedge_task_info *info =NULL ;struct amdgpu_task_info *ti =NULL ;struct amdgpu_device *adev = ring->adev; +enum drm_gpu_sched_stat status =DRM_GPU_SCHED_STAT_RESET ;int idx, r;if (!drm_dev_enter (adev_to_drm (adev), &idx)) {@@ -135,13 +136,19 @@ static enum drm_gpu_sched_stat amdgpu_job_timedout(struct drm_sched_job *s_job) ring->funcs->reset) {dev_err (adev->dev,"Starting %s ring reset\n" , s_job->sched->name); +/* Stop the scheduler to prevent anybody else from touching the ring buffer. */ +drm_sched_wqueue_stop (&ring->sched); r =amdgpu_ring_reset (ring, job->vmid, job->hw_fence);if (!r) { +/* Start the scheduler again */ +drm_sched_wqueue_start (&ring->sched);atomic_inc (&ring->adev->gpu_reset_counter);dev_err (adev->dev,"Ring %s reset succeeded\n" , ring->sched.name);drm_dev_wedged_event (adev_to_drm (adev),DRM_WEDGE_RECOVERY_NONE , info); +/* This is needed to add the job back to the pending list */ + status =DRM_GPU_SCHED_STAT_NO_HANG ; goto exit; }dev_err (adev->dev,"Ring %s reset failed\n" , ring->sched.name);@@ -177,7 +184,7 @@ static enum drm_gpu_sched_stat amdgpu_job_timedout(struct drm_sched_job *s_job) exit:amdgpu_vm_put_task_info (ti);drm_dev_exit (idx); -return DRM_GPU_SCHED_STAT_RESET ; +return status; } int amdgpu_job_alloc(struct amdgpu_device *adev, struct amdgpu_vm *vm,drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c +0
-4@@ -868,8 +868,6 @@ bool amdgpu_ring_sched_ready(struct amdgpu_ring *ring)void amdgpu_ring_reset_helper_begin (struct amdgpu_ring *ring,struct amdgpu_fence *guilty_fence) { -/* Stop the scheduler to prevent anybody else from touching the ring buffer. */ -drm_sched_wqueue_stop (&ring->sched);/* back up the non-guilty commands */ amdgpu_ring_backup_unprocessed_commands (ring, guilty_fence); }@@ -895,8 +893,6 @@ int amdgpu_ring_reset_helper_end(struct amdgpu_ring *ring,amdgpu_ring_write (ring, ring->ring_backup[i]);amdgpu_ring_commit (ring); } -/* Start the scheduler again */ -drm_sched_wqueue_start (&ring->sched);return 0 ; }
Alex Deucher
maintainerPATCH 2/12 drm/amdgpu/job: use GFP_ATOMIC while in gpu reset
In reply to Alex DeucherIf we need to allocate a job during GPU reset, use GFP_ATOMIC rather than GFP_KERNEL.
v2: use pool type it determine alloc flags.
--- drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c | 2 +- drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c | 2 +- drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c | 2 +- drivers/gpu/drm/amd/amdgpu/amdgpu_job.c | 13 ++++++++----- drivers/gpu/drm/amd/amdgpu/amdgpu_job.h | 2 +- drivers/gpu/drm/amd/amdgpu/amdgpu_object.h | 2 +- drivers/gpu/drm/amd/amdgpu/amdgpu_sa.c | 5 +++-- 7 files changed, 16 insertions(+), 12 deletions(-)
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c +1 -1
@@ -672,7 +672,7 @@ int amdgpu_amdkfd_submit_ib(struct amdgpu_device *adev, goto err; } - ret =amdgpu_job_alloc (adev,NULL ,NULL ,NULL ,1 , &job,0 ); + ret =amdgpu_job_alloc (adev,NULL ,NULL ,NULL ,1 , &job,0 , false);if (ret) goto err;
drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c +1 -1
@@ -282,7 +282,7 @@ static int amdgpu_cs_pass1(struct amdgpu_cs_parser *p,for (i =0 ; i < p->gang_size; ++i) { ret =amdgpu_job_alloc (p->adev, vm, p->entities[i], vm, num_ibs[i], &p->jobs[i], - p->filp->client_id); + p->filp->client_id, false);if (ret) goto free_all_kdata;switch (p->adev->enforce_isolation[fpriv->xcp_id]) {
drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c +1 -1
@@ -69,7 +69,7 @@ int amdgpu_ib_get(struct amdgpu_device *adev, struct amdgpu_vm *vm,if (size) { r =amdgpu_sa_bo_new (&adev->ib_pools[pool_type], - &ib->sa_bo, size); + &ib->sa_bo, size, pool_type ==AMDGPU_IB_POOL_DIRECT );if (r) {dev_err (adev->dev,"failed to get a new IB (%d)\n" , r);return r;
drivers/gpu/drm/amd/amdgpu/amdgpu_job.c +8 -5
@@ -190,7 +190,7 @@ static enum drm_gpu_sched_stat amdgpu_job_timedout(struct drm_sched_job *s_job)int amdgpu_job_alloc (struct amdgpu_device *adev,struct amdgpu_vm *vm,struct drm_sched_entity *entity,void *owner,unsigned int num_ibs,struct amdgpu_job **job, -u64 drm_client_id) +u64 drm_client_id,bool need_atomic) {struct amdgpu_fence *af;int r;
@@ -198,18 +198,21 @@ int amdgpu_job_alloc(struct amdgpu_device *adev, struct amdgpu_vm *vm,if (num_ibs ==0 )return -EINVAL ; - *job =kzalloc (struct_size (*job, ibs, num_ibs),GFP_KERNEL ); + *job =kzalloc (struct_size (*job, ibs, num_ibs), + need_atomic ?GFP_ATOMIC :GFP_KERNEL );if (!*job)return -ENOMEM ; - af =kzalloc (sizeof (struct amdgpu_fence ),GFP_KERNEL ); + af =kzalloc (sizeof (struct amdgpu_fence ), + need_atomic ?GFP_ATOMIC :GFP_KERNEL );if (!af) { r = -ENOMEM ; goto err_job; } (*job)->hw_fence = af; - af =kzalloc (sizeof (struct amdgpu_fence ),GFP_KERNEL ); + af =kzalloc (sizeof (struct amdgpu_fence ), + need_atomic ?GFP_ATOMIC :GFP_KERNEL );if (!af) { r = -ENOMEM ; goto err_fence;
@@ -248,7 +251,7 @@ int amdgpu_job_alloc_with_ib(struct amdgpu_device *adev,int r; r =amdgpu_job_alloc (adev,NULL , entity, owner,1 , job, - k_job_id); + k_job_id, pool_type ==AMDGPU_IB_POOL_DIRECT );if (r)return r;
drivers/gpu/drm/amd/amdgpu/amdgpu_job.h +1 -1
@@ -113,7 +113,7 @@ static inline struct amdgpu_ring *amdgpu_job_ring(struct amdgpu_job *job)int amdgpu_job_alloc (struct amdgpu_device *adev,struct amdgpu_vm *vm,struct drm_sched_entity *entity,void *owner,unsigned int num_ibs,struct amdgpu_job **job, -u64 drm_client_id); +u64 drm_client_id,bool need_atomic); int amdgpu_job_alloc_with_ib(struct amdgpu_device *adev, struct drm_sched_entity *entity, void *owner, size_t size, enum amdgpu_ib_pool_type pool_type,
drivers/gpu/drm/amd/amdgpu/amdgpu_object.h +1 -1
@@ -341,7 +341,7 @@ int amdgpu_sa_bo_manager_start(struct amdgpu_device *adev, struct amdgpu_sa_manager *sa_manager);int amdgpu_sa_bo_new (struct amdgpu_sa_manager *sa_manager,struct drm_suballoc **sa_bo, -unsigned int size); +unsigned int size,bool need_atomic);void amdgpu_sa_bo_free (struct drm_suballoc **sa_bo,struct dma_fence *fence);#if defined(CONFIG_DEBUG_FS )
drivers/gpu/drm/amd/amdgpu/amdgpu_sa.c +3 -2
@@ -78,10 +78,11 @@ void amdgpu_sa_bo_manager_fini(struct amdgpu_device *adev,int amdgpu_sa_bo_new (struct amdgpu_sa_manager *sa_manager,struct drm_suballoc **sa_bo, -unsigned int size) +unsigned int size,bool need_atomic) {struct drm_suballoc *sa =drm_suballoc_new (&sa_manager->base, size, -GFP_KERNEL , false,0 ); + need_atomic ?GFP_ATOMIC :GFP_KERNEL , + false,0 );if (IS_ERR (sa)) { *sa_bo =NULL ;
Signature · 1 line
2.52.0
Alex Deucher
maintainerPATCH 3/12 drm/amdgpu: switch all IPs to using job for IBs
In reply to Alex DeucherSwitch to using a job structure for IBs.
--- drivers/gpu/drm/amd/amdgpu/amdgpu_vpe.c | 37 +++--- drivers/gpu/drm/amd/amdgpu/cik_sdma.c | 31 ++--- drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c | 29 ++--- drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c | 29 ++--- drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c | 29 ++--- drivers/gpu/drm/amd/amdgpu/gfx_v12_1.c | 29 ++--- drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c | 24 ++-- drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c | 25 ++-- drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c | 139 ++++++++++++----------- drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c | 138 +++++++++++----------- drivers/gpu/drm/amd/amdgpu/gfx_v9_4_2.c | 26 ++--- drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c | 29 ++--- drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c | 38 ++++--- drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c | 38 ++++--- drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c | 38 ++++--- drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c | 38 ++++--- drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c | 37 +++--- drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c | 36 +++--- drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c | 36 +++--- drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c | 36 +++--- drivers/gpu/drm/amd/amdgpu/sdma_v7_1.c | 36 +++--- drivers/gpu/drm/amd/amdgpu/si_dma.c | 29 +++-- 22 files changed, 500 insertions(+), 427 deletions(-)
drivers/gpu/drm/amd/amdgpu/amdgpu_vpe.c +21 -16
@@ -817,7 +817,8 @@ static int vpe_ring_test_ib(struct amdgpu_ring *ring, long timeout) {struct amdgpu_device *adev = ring->adev;const uint32_t test_pattern =0xdeadbeef ; -struct amdgpu_ib ib = {}; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ;uint32_t index;uint64_t wb_addr;
@@ -832,23 +833,28 @@ static int vpe_ring_test_ib(struct amdgpu_ring *ring, long timeout) adev->wb.wb[index] =0 ; wb_addr = adev->wb.gpu_addr + (index *4 ); - ret =amdgpu_ib_get (adev,NULL ,256 ,AMDGPU_IB_POOL_DIRECT , &ib); + ret =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,256 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_VPE_RING_TEST );if (ret) goto err0; - - ib.ptr[0 ] =VPE_CMD_HEADER (VPE_CMD_OPCODE_FENCE ,0 ); - ib.ptr[1 ] =lower_32_bits (wb_addr); - ib.ptr[2 ] =upper_32_bits (wb_addr); - ib.ptr[3 ] = test_pattern; - ib.ptr[4 ] =VPE_CMD_HEADER (VPE_CMD_OPCODE_NOP ,0 ); - ib.ptr[5 ] =VPE_CMD_HEADER (VPE_CMD_OPCODE_NOP ,0 ); - ib.ptr[6 ] =VPE_CMD_HEADER (VPE_CMD_OPCODE_NOP ,0 ); - ib.ptr[7 ] =VPE_CMD_HEADER (VPE_CMD_OPCODE_NOP ,0 ); - ib.length_dw =8 ; - - ret =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (ret) + ib = &job->ibs[0 ]; + + ib->ptr[0 ] =VPE_CMD_HEADER (VPE_CMD_OPCODE_FENCE ,0 ); + ib->ptr[1 ] =lower_32_bits (wb_addr); + ib->ptr[2 ] =upper_32_bits (wb_addr); + ib->ptr[3 ] = test_pattern; + ib->ptr[4 ] =VPE_CMD_HEADER (VPE_CMD_OPCODE_NOP ,0 ); + ib->ptr[5 ] =VPE_CMD_HEADER (VPE_CMD_OPCODE_NOP ,0 ); + ib->ptr[6 ] =VPE_CMD_HEADER (VPE_CMD_OPCODE_NOP ,0 ); + ib->ptr[7 ] =VPE_CMD_HEADER (VPE_CMD_OPCODE_NOP ,0 ); + ib->length_dw =8 ; + + ret =amdgpu_job_submit_direct (job, ring, &f); +if (ret) { +amdgpu_job_free (job); goto err1; + } ret =dma_fence_wait_timeout (f, false, timeout);if (ret <=0 ) {
@@ -859,7 +865,6 @@ static int vpe_ring_test_ib(struct amdgpu_ring *ring, long timeout) ret = (le32_to_cpu (adev->wb.wb[index]) == test_pattern) ?0 : -EINVAL ; err1: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f); err0:amdgpu_device_wb_free (adev, index);
drivers/gpu/drm/amd/amdgpu/cik_sdma.c +18 -13
@@ -652,7 +652,8 @@ static int cik_sdma_ring_test_ring(struct amdgpu_ring *ring)static int cik_sdma_ring_test_ib (struct amdgpu_ring *ring,long timeout) {struct amdgpu_device *adev = ring->adev; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ;unsigned index;u32 tmp =0 ;
@@ -666,22 +667,27 @@ static int cik_sdma_ring_test_ib(struct amdgpu_ring *ring, long timeout) gpu_addr = adev->wb.gpu_addr + (index *4 ); tmp =0xCAFEDEAD ; adev->wb.wb[index] =cpu_to_le32 (tmp); -memset (&ib,0 ,sizeof (ib)); - r =amdgpu_ib_get (adev,NULL ,256 , -AMDGPU_IB_POOL_DIRECT , &ib); + + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,256 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_SDMA_RING_TEST );if (r) goto err0; + ib = &job->ibs[0 ]; - ib.ptr[0 ] =SDMA_PACKET (SDMA_OPCODE_WRITE , + ib->ptr[0 ] =SDMA_PACKET (SDMA_OPCODE_WRITE ,SDMA_WRITE_SUB_OPCODE_LINEAR ,0 ); - ib.ptr[1 ] =lower_32_bits (gpu_addr); - ib.ptr[2 ] =upper_32_bits (gpu_addr); - ib.ptr[3 ] =1 ; - ib.ptr[4 ] =0xDEADBEEF ; - ib.length_dw =5 ; - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (r) + ib->ptr[1 ] =lower_32_bits (gpu_addr); + ib->ptr[2 ] =upper_32_bits (gpu_addr); + ib->ptr[3 ] =1 ; + ib->ptr[4 ] =0xDEADBEEF ; + ib->length_dw =5 ; + + r =amdgpu_job_submit_direct (job, ring, &f); +if (r) { +amdgpu_job_free (job); goto err1; + } r =dma_fence_wait_timeout (f, false, timeout);if (r ==0 ) {
@@ -697,7 +703,6 @@ static int cik_sdma_ring_test_ib(struct amdgpu_ring *ring, long timeout) r = -EINVAL ; err1: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f); err0:amdgpu_device_wb_free (adev, index);
drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c +16 -13
@@ -4071,15 +4071,14 @@ static int gfx_v10_0_ring_test_ring(struct amdgpu_ring *ring)static int gfx_v10_0_ring_test_ib (struct amdgpu_ring *ring,long timeout) {struct amdgpu_device *adev = ring->adev; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ;unsigned int index;uint64_t gpu_addr;uint32_t *cpu_ptr;long r; -memset (&ib,0 ,sizeof (ib)); - r =amdgpu_device_wb_get (adev, &index);if (r)return r;
@@ -4088,22 +4087,27 @@ static int gfx_v10_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) adev->wb.wb[index] =cpu_to_le32 (0xCAFEDEAD ); cpu_ptr = &adev->wb.wb[index]; - r =amdgpu_ib_get (adev,NULL ,20 ,AMDGPU_IB_POOL_DIRECT , &ib); + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,20 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_GFX_RING_TEST );if (r) {drm_err (adev_to_drm (adev),"failed to get ib (%ld).\n" , r); goto err1; } + ib = &job->ibs[0 ]; - ib.ptr[0 ] =PACKET3 (PACKET3_WRITE_DATA ,3 ); - ib.ptr[1 ] =WRITE_DATA_DST_SEL (5 ) |WR_CONFIRM ; - ib.ptr[2 ] =lower_32_bits (gpu_addr); - ib.ptr[3 ] =upper_32_bits (gpu_addr); - ib.ptr[4 ] =0xDEADBEEF ; - ib.length_dw =5 ; + ib->ptr[0 ] =PACKET3 (PACKET3_WRITE_DATA ,3 ); + ib->ptr[1 ] =WRITE_DATA_DST_SEL (5 ) |WR_CONFIRM ; + ib->ptr[2 ] =lower_32_bits (gpu_addr); + ib->ptr[3 ] =upper_32_bits (gpu_addr); + ib->ptr[4 ] =0xDEADBEEF ; + ib->length_dw =5 ; - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (r) + r =amdgpu_job_submit_direct (job, ring, &f); +if (r) { +amdgpu_job_free (job); goto err2; + } r =dma_fence_wait_timeout (f, false, timeout);if (r ==0 ) {
@@ -4118,7 +4122,6 @@ static int gfx_v10_0_ring_test_ib(struct amdgpu_ring *ring, long timeout)else r = -EINVAL ; err2: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f); err1:amdgpu_device_wb_free (adev, index);
drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c +16 -13
@@ -604,7 +604,8 @@ static int gfx_v11_0_ring_test_ring(struct amdgpu_ring *ring)static int gfx_v11_0_ring_test_ib (struct amdgpu_ring *ring,long timeout) {struct amdgpu_device *adev = ring->adev; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ;unsigned index;uint64_t gpu_addr;
@@ -616,8 +617,6 @@ static int gfx_v11_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) ring->funcs->type == AMDGPU_RING_TYPE_KIQ)return 0 ; -memset (&ib,0 ,sizeof (ib)); - r =amdgpu_device_wb_get (adev, &index);if (r)return r;
@@ -626,22 +625,27 @@ static int gfx_v11_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) adev->wb.wb[index] =cpu_to_le32 (0xCAFEDEAD ); cpu_ptr = &adev->wb.wb[index]; - r =amdgpu_ib_get (adev,NULL ,20 ,AMDGPU_IB_POOL_DIRECT , &ib); + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,20 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_GFX_RING_TEST );if (r) {drm_err (adev_to_drm (adev),"failed to get ib (%ld).\n" , r); goto err1; } + ib = &job->ibs[0 ]; - ib.ptr[0 ] =PACKET3 (PACKET3_WRITE_DATA ,3 ); - ib.ptr[1 ] =WRITE_DATA_DST_SEL (5 ) |WR_CONFIRM ; - ib.ptr[2 ] =lower_32_bits (gpu_addr); - ib.ptr[3 ] =upper_32_bits (gpu_addr); - ib.ptr[4 ] =0xDEADBEEF ; - ib.length_dw =5 ; + ib->ptr[0 ] =PACKET3 (PACKET3_WRITE_DATA ,3 ); + ib->ptr[1 ] =WRITE_DATA_DST_SEL (5 ) |WR_CONFIRM ; + ib->ptr[2 ] =lower_32_bits (gpu_addr); + ib->ptr[3 ] =upper_32_bits (gpu_addr); + ib->ptr[4 ] =0xDEADBEEF ; + ib->length_dw =5 ; - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (r) + r =amdgpu_job_submit_direct (job, ring, &f); +if (r) { +amdgpu_job_free (job); goto err2; + } r =dma_fence_wait_timeout (f, false, timeout);if (r ==0 ) {
@@ -656,7 +660,6 @@ static int gfx_v11_0_ring_test_ib(struct amdgpu_ring *ring, long timeout)else r = -EINVAL ; err2: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f); err1:amdgpu_device_wb_free (adev, index);
drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c +16 -13
@@ -493,7 +493,8 @@ static int gfx_v12_0_ring_test_ring(struct amdgpu_ring *ring)static int gfx_v12_0_ring_test_ib (struct amdgpu_ring *ring,long timeout) {struct amdgpu_device *adev = ring->adev; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ;unsigned index;uint64_t gpu_addr;
@@ -505,8 +506,6 @@ static int gfx_v12_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) ring->funcs->type == AMDGPU_RING_TYPE_KIQ)return 0 ; -memset (&ib,0 ,sizeof (ib)); - r =amdgpu_device_wb_get (adev, &index);if (r)return r;
@@ -515,22 +514,27 @@ static int gfx_v12_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) adev->wb.wb[index] =cpu_to_le32 (0xCAFEDEAD ); cpu_ptr = &adev->wb.wb[index]; - r =amdgpu_ib_get (adev,NULL ,16 ,AMDGPU_IB_POOL_DIRECT , &ib); + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,16 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_GFX_RING_TEST );if (r) {drm_err (adev_to_drm (adev),"failed to get ib (%ld).\n" , r); goto err1; } + ib = &job->ibs[0 ]; - ib.ptr[0 ] =PACKET3 (PACKET3_WRITE_DATA ,3 ); - ib.ptr[1 ] =WRITE_DATA_DST_SEL (5 ) |WR_CONFIRM ; - ib.ptr[2 ] =lower_32_bits (gpu_addr); - ib.ptr[3 ] =upper_32_bits (gpu_addr); - ib.ptr[4 ] =0xDEADBEEF ; - ib.length_dw =5 ; + ib->ptr[0 ] =PACKET3 (PACKET3_WRITE_DATA ,3 ); + ib->ptr[1 ] =WRITE_DATA_DST_SEL (5 ) |WR_CONFIRM ; + ib->ptr[2 ] =lower_32_bits (gpu_addr); + ib->ptr[3 ] =upper_32_bits (gpu_addr); + ib->ptr[4 ] =0xDEADBEEF ; + ib->length_dw =5 ; - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (r) + r =amdgpu_job_submit_direct (job, ring, &f); +if (r) { +amdgpu_job_free (job); goto err2; + } r =dma_fence_wait_timeout (f, false, timeout);if (r ==0 ) {
@@ -545,7 +549,6 @@ static int gfx_v12_0_ring_test_ib(struct amdgpu_ring *ring, long timeout)else r = -EINVAL ; err2: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f); err1:amdgpu_device_wb_free (adev, index);
drivers/gpu/drm/amd/amdgpu/gfx_v12_1.c +16 -13
@@ -307,7 +307,8 @@ static int gfx_v12_1_ring_test_ring(struct amdgpu_ring *ring)static int gfx_v12_1_ring_test_ib (struct amdgpu_ring *ring,long timeout) {struct amdgpu_device *adev = ring->adev; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ;unsigned index;uint64_t gpu_addr;
@@ -319,8 +320,6 @@ static int gfx_v12_1_ring_test_ib(struct amdgpu_ring *ring, long timeout) ring->funcs->type == AMDGPU_RING_TYPE_KIQ)return 0 ; -memset (&ib,0 ,sizeof (ib)); - r =amdgpu_device_wb_get (adev, &index);if (r)return r;
@@ -329,22 +328,27 @@ static int gfx_v12_1_ring_test_ib(struct amdgpu_ring *ring, long timeout) adev->wb.wb[index] =cpu_to_le32 (0xCAFEDEAD ); cpu_ptr = &adev->wb.wb[index]; - r =amdgpu_ib_get (adev,NULL ,16 ,AMDGPU_IB_POOL_DIRECT , &ib); + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,16 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_GFX_RING_TEST );if (r) {dev_err (adev->dev,"amdgpu: failed to get ib (%ld).\n" , r); goto err1; } + ib = &job->ibs[0 ]; - ib.ptr[0 ] =PACKET3 (PACKET3_WRITE_DATA ,3 ); - ib.ptr[1 ] =WRITE_DATA_DST_SEL (5 ) |WR_CONFIRM ; - ib.ptr[2 ] =lower_32_bits (gpu_addr); - ib.ptr[3 ] =upper_32_bits (gpu_addr); - ib.ptr[4 ] =0xDEADBEEF ; - ib.length_dw =5 ; + ib->ptr[0 ] =PACKET3 (PACKET3_WRITE_DATA ,3 ); + ib->ptr[1 ] =WRITE_DATA_DST_SEL (5 ) |WR_CONFIRM ; + ib->ptr[2 ] =lower_32_bits (gpu_addr); + ib->ptr[3 ] =upper_32_bits (gpu_addr); + ib->ptr[4 ] =0xDEADBEEF ; + ib->length_dw =5 ; - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (r) + r =amdgpu_job_submit_direct (job, ring, &f); +if (r) { +amdgpu_job_free (job); goto err2; + } r =dma_fence_wait_timeout (f, false, timeout);if (r ==0 ) {
@@ -359,7 +363,6 @@ static int gfx_v12_1_ring_test_ib(struct amdgpu_ring *ring, long timeout)else r = -EINVAL ; err2: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f); err1:amdgpu_device_wb_free (adev, index);
drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c +14 -10
@@ -1895,24 +1895,29 @@ static int gfx_v6_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) {struct amdgpu_device *adev = ring->adev;struct dma_fence *f =NULL ; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;uint32_t tmp =0 ;long r;WREG32 (mmSCRATCH_REG0,0xCAFEDEAD ); -memset (&ib,0 ,sizeof (ib)); - r =amdgpu_ib_get (adev,NULL ,256 ,AMDGPU_IB_POOL_DIRECT , &ib); + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,256 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_GFX_RING_TEST );if (r)return r; - ib.ptr[0 ] =PACKET3 (PACKET3_SET_CONFIG_REG ,1 ); - ib.ptr[1 ] = mmSCRATCH_REG0 -PACKET3_SET_CONFIG_REG_START ; - ib.ptr[2 ] =0xDEADBEEF ; - ib.length_dw =3 ; + ib = &job->ibs[0 ]; + ib->ptr[0 ] =PACKET3 (PACKET3_SET_CONFIG_REG ,1 ); + ib->ptr[1 ] = mmSCRATCH_REG0 -PACKET3_SET_CONFIG_REG_START ; + ib->ptr[2 ] =0xDEADBEEF ; + ib->length_dw =3 ; - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (r) + r =amdgpu_job_submit_direct (job, ring, &f); +if (r) { +amdgpu_job_free (job); goto error; + } r =dma_fence_wait_timeout (f, false, timeout);if (r ==0 ) {
@@ -1928,7 +1933,6 @@ static int gfx_v6_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) r = -EINVAL ; error: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f);return r; }
drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c +15 -10
@@ -2291,25 +2291,31 @@ static void gfx_v7_ring_emit_cntxcntl(struct amdgpu_ring *ring, uint32_t flags)static int gfx_v7_0_ring_test_ib (struct amdgpu_ring *ring,long timeout) {struct amdgpu_device *adev = ring->adev; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ;uint32_t tmp =0 ;long r;WREG32 (mmSCRATCH_REG0,0xCAFEDEAD ); -memset (&ib,0 ,sizeof (ib)); - r =amdgpu_ib_get (adev,NULL ,256 ,AMDGPU_IB_POOL_DIRECT , &ib); + + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,256 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_GFX_RING_TEST );if (r)return r; - ib.ptr[0 ] =PACKET3 (PACKET3_SET_UCONFIG_REG ,1 ); - ib.ptr[1 ] = mmSCRATCH_REG0 -PACKET3_SET_UCONFIG_REG_START ; - ib.ptr[2 ] =0xDEADBEEF ; - ib.length_dw =3 ; + ib = &job->ibs[0 ]; + ib->ptr[0 ] =PACKET3 (PACKET3_SET_UCONFIG_REG ,1 ); + ib->ptr[1 ] = mmSCRATCH_REG0 -PACKET3_SET_UCONFIG_REG_START ; + ib->ptr[2 ] =0xDEADBEEF ; + ib->length_dw =3 ; - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (r) + r =amdgpu_job_submit_direct (job, ring, &f); +if (r) { +amdgpu_job_free (job); goto error; + } r =dma_fence_wait_timeout (f, false, timeout);if (r ==0 ) {
@@ -2325,7 +2331,6 @@ static int gfx_v7_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) r = -EINVAL ; error: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f);return r; }
drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +72 -67
230 lines not on this page · raw message
drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +71 -67
234 lines not on this page · raw message
drivers/gpu/drm/amd/amdgpu/gfx_v9_4_2.c +8 -18
@@ -345,12 +345,13 @@ const struct soc15_reg_entry sgpr64_init_regs_aldebaran[] = {static int gfx_v9_4_2_run_shader (struct amdgpu_device *adev,struct amdgpu_ring *ring, -struct amdgpu_ib *ib,const u32 *shader_ptr,u32 shader_size,const struct soc15_reg_entry *init_regs,u32 regs_size,u32 compute_dim_x,u64 wb_gpu_addr,u32 pattern,struct dma_fence **fence_ptr) { +struct amdgpu_job *job; +struct amdgpu_ib *ib;int r, i;uint32_t total_size, shader_offset;u64 gpu_addr;
@@ -360,10 +361,9 @@ static int gfx_v9_4_2_run_shader(struct amdgpu_device *adev, shader_offset = total_size; total_size +=ALIGN (shader_size,256 ); -/* allocate an indirect buffer to put the commands in */ -memset (ib,0 ,sizeof (*ib)); - r =amdgpu_ib_get (adev,NULL , total_size, -AMDGPU_IB_POOL_DIRECT , ib); + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL , total_size, +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_RUN_SHADER );if (r) {dev_err (adev->dev,"failed to get ib (%d).\n" , r);return r;
@@ -408,11 +408,11 @@ static int gfx_v9_4_2_run_shader(struct amdgpu_device *adev, ib->ptr[ib->length_dw++] =REG_SET_FIELD (0 ,COMPUTE_DISPATCH_INITIATOR ,COMPUTE_SHADER_EN ,1 ); -/* shedule the ib on the ring */ - r =amdgpu_ib_schedule (ring,1 , ib,NULL , fence_ptr); +/* schedule the ib on the ring */ + r =amdgpu_job_submit_direct (job, ring, fence_ptr);if (r) {dev_err (adev->dev,"ib submit failed (%d).\n" , r); -amdgpu_ib_free (ib,NULL ); +amdgpu_job_free (job); }return r; }
@@ -493,7 +493,6 @@ static int gfx_v9_4_2_do_sgprs_init(struct amdgpu_device *adev)int wb_size = adev->gfx.config.max_shader_engines *CU_ID_MAX *SIMD_ID_MAX *WAVE_ID_MAX ;struct amdgpu_ib wb_ib; -struct amdgpu_ib disp_ibs[3 ];struct dma_fence *fences[3 ];u32 pattern[3 ] = {0x1 ,0x5 ,0xa };
@@ -514,7 +513,6 @@ static int gfx_v9_4_2_do_sgprs_init(struct amdgpu_device *adev) r = gfx_v9_4_2_run_shader(adev, &adev->gfx.compute_ring[0], - &disp_ibs[0], sgpr112_init_compute_shader_aldebaran, sizeof(sgpr112_init_compute_shader_aldebaran), sgpr112_init_regs_aldebaran,
@@ -539,7 +537,6 @@ static int gfx_v9_4_2_do_sgprs_init(struct amdgpu_device *adev) r = gfx_v9_4_2_run_shader(adev, &adev->gfx.compute_ring[1], - &disp_ibs[1], sgpr96_init_compute_shader_aldebaran, sizeof(sgpr96_init_compute_shader_aldebaran), sgpr96_init_regs_aldebaran,
@@ -579,7 +576,6 @@ static int gfx_v9_4_2_do_sgprs_init(struct amdgpu_device *adev)memset (wb_ib.ptr,0 , (1 + wb_size) *sizeof (uint32_t )); r = gfx_v9_4_2_run_shader(adev, &adev->gfx.compute_ring[0], - &disp_ibs[2], sgpr64_init_compute_shader_aldebaran, sizeof(sgpr64_init_compute_shader_aldebaran), sgpr64_init_regs_aldebaran,
@@ -611,13 +607,10 @@ static int gfx_v9_4_2_do_sgprs_init(struct amdgpu_device *adev) } disp2_failed: -amdgpu_ib_free (&disp_ibs[2 ],NULL );dma_fence_put (fences[2 ]); disp1_failed: -amdgpu_ib_free (&disp_ibs[1 ],NULL );dma_fence_put (fences[1 ]); disp0_failed: -amdgpu_ib_free (&disp_ibs[0 ],NULL );dma_fence_put (fences[0 ]); pro_end:amdgpu_ib_free (&wb_ib,NULL );
@@ -637,7 +630,6 @@ static int gfx_v9_4_2_do_vgprs_init(struct amdgpu_device *adev)int wb_size = adev->gfx.config.max_shader_engines *CU_ID_MAX *SIMD_ID_MAX *WAVE_ID_MAX ;struct amdgpu_ib wb_ib; -struct amdgpu_ib disp_ib;struct dma_fence *fence;u32 pattern =0xa ;
@@ -657,7 +649,6 @@ static int gfx_v9_4_2_do_vgprs_init(struct amdgpu_device *adev) r = gfx_v9_4_2_run_shader(adev, &adev->gfx.compute_ring[0], - &disp_ib, vgpr_init_compute_shader_aldebaran, sizeof(vgpr_init_compute_shader_aldebaran), vgpr_init_regs_aldebaran,
@@ -687,7 +678,6 @@ static int gfx_v9_4_2_do_vgprs_init(struct amdgpu_device *adev) } disp_failed: -amdgpu_ib_free (&disp_ib,NULL );dma_fence_put (fence); pro_end:amdgpu_ib_free (&wb_ib,NULL );
drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c +16 -13
@@ -451,9 +451,9 @@ static int gfx_v9_4_3_ring_test_ring(struct amdgpu_ring *ring)static int gfx_v9_4_3_ring_test_ib (struct amdgpu_ring *ring,long timeout) {struct amdgpu_device *adev = ring->adev; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ; -unsigned index;uint64_t gpu_addr;uint32_t tmp;
@@ -465,22 +465,26 @@ static int gfx_v9_4_3_ring_test_ib(struct amdgpu_ring *ring, long timeout) gpu_addr = adev->wb.gpu_addr + (index *4 ); adev->wb.wb[index] =cpu_to_le32 (0xCAFEDEAD ); -memset (&ib,0 ,sizeof (ib)); - r =amdgpu_ib_get (adev,NULL ,20 ,AMDGPU_IB_POOL_DIRECT , &ib); + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,20 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_GFX_RING_TEST );if (r) goto err1; - ib.ptr[0 ] =PACKET3 (PACKET3_WRITE_DATA ,3 ); - ib.ptr[1 ] =WRITE_DATA_DST_SEL (5 ) |WR_CONFIRM ; - ib.ptr[2 ] =lower_32_bits (gpu_addr); - ib.ptr[3 ] =upper_32_bits (gpu_addr); - ib.ptr[4 ] =0xDEADBEEF ; - ib.length_dw =5 ; + ib = &job->ibs[0 ]; + ib->ptr[0 ] =PACKET3 (PACKET3_WRITE_DATA ,3 ); + ib->ptr[1 ] =WRITE_DATA_DST_SEL (5 ) |WR_CONFIRM ; + ib->ptr[2 ] =lower_32_bits (gpu_addr); + ib->ptr[3 ] =upper_32_bits (gpu_addr); + ib->ptr[4 ] =0xDEADBEEF ; + ib->length_dw =5 ; - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (r) + r =amdgpu_job_submit_direct (job, ring, &f); +if (r) { +amdgpu_job_free (job); goto err2; + } r =dma_fence_wait_timeout (f, false, timeout);if (r ==0 ) {
@@ -497,7 +501,6 @@ static int gfx_v9_4_3_ring_test_ib(struct amdgpu_ring *ring, long timeout) r = -EINVAL ; err2: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f); err1:amdgpu_device_wb_free (adev, index);
drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c +21 -17
@@ -584,7 +584,8 @@ static int sdma_v2_4_ring_test_ring(struct amdgpu_ring *ring)static int sdma_v2_4_ring_test_ib (struct amdgpu_ring *ring,long timeout) {struct amdgpu_device *adev = ring->adev; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ;unsigned index;u32 tmp =0 ;
@@ -598,26 +599,30 @@ static int sdma_v2_4_ring_test_ib(struct amdgpu_ring *ring, long timeout) gpu_addr = adev->wb.gpu_addr + (index *4 ); tmp =0xCAFEDEAD ; adev->wb.wb[index] =cpu_to_le32 (tmp); -memset (&ib,0 ,sizeof (ib)); - r =amdgpu_ib_get (adev,NULL ,256 , -AMDGPU_IB_POOL_DIRECT , &ib); + + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,256 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_SDMA_RING_TEST );if (r) goto err0; - ib.ptr[0 ] =SDMA_PKT_HEADER_OP (SDMA_OP_WRITE ) | + ib = &job->ibs[0 ]; + ib->ptr[0 ] =SDMA_PKT_HEADER_OP (SDMA_OP_WRITE ) |SDMA_PKT_HEADER_SUB_OP (SDMA_SUBOP_WRITE_LINEAR ); - ib.ptr[1 ] =lower_32_bits (gpu_addr); - ib.ptr[2 ] =upper_32_bits (gpu_addr); - ib.ptr[3 ] =SDMA_PKT_WRITE_UNTILED_DW_3_COUNT (1 ); - ib.ptr[4 ] =0xDEADBEEF ; - ib.ptr[5 ] =SDMA_PKT_HEADER_OP (SDMA_OP_NOP ); - ib.ptr[6 ] =SDMA_PKT_HEADER_OP (SDMA_OP_NOP ); - ib.ptr[7 ] =SDMA_PKT_HEADER_OP (SDMA_OP_NOP ); - ib.length_dw =8 ; - - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (r) + ib->ptr[1 ] =lower_32_bits (gpu_addr); + ib->ptr[2 ] =upper_32_bits (gpu_addr); + ib->ptr[3 ] =SDMA_PKT_WRITE_UNTILED_DW_3_COUNT (1 ); + ib->ptr[4 ] =0xDEADBEEF ; + ib->ptr[5 ] =SDMA_PKT_HEADER_OP (SDMA_OP_NOP ); + ib->ptr[6 ] =SDMA_PKT_HEADER_OP (SDMA_OP_NOP ); + ib->ptr[7 ] =SDMA_PKT_HEADER_OP (SDMA_OP_NOP ); + ib->length_dw =8 ; + + r =amdgpu_job_submit_direct (job, ring, &f); +if (r) { +amdgpu_job_free (job); goto err1; + } r =dma_fence_wait_timeout (f, false, timeout);if (r ==0 ) {
@@ -633,7 +638,6 @@ static int sdma_v2_4_ring_test_ib(struct amdgpu_ring *ring, long timeout) r = -EINVAL ; err1: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f); err0:amdgpu_device_wb_free (adev, index);
drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c +21 -17
@@ -858,7 +858,8 @@ static int sdma_v3_0_ring_test_ring(struct amdgpu_ring *ring)static int sdma_v3_0_ring_test_ib (struct amdgpu_ring *ring,long timeout) {struct amdgpu_device *adev = ring->adev; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ;unsigned index;u32 tmp =0 ;
@@ -872,26 +873,30 @@ static int sdma_v3_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) gpu_addr = adev->wb.gpu_addr + (index *4 ); tmp =0xCAFEDEAD ; adev->wb.wb[index] =cpu_to_le32 (tmp); -memset (&ib,0 ,sizeof (ib)); - r =amdgpu_ib_get (adev,NULL ,256 , -AMDGPU_IB_POOL_DIRECT , &ib); + + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,256 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_SDMA_RING_TEST );if (r) goto err0; - ib.ptr[0 ] =SDMA_PKT_HEADER_OP (SDMA_OP_WRITE ) | + ib = &job->ibs[0 ]; + ib->ptr[0 ] =SDMA_PKT_HEADER_OP (SDMA_OP_WRITE ) |SDMA_PKT_HEADER_SUB_OP (SDMA_SUBOP_WRITE_LINEAR ); - ib.ptr[1 ] =lower_32_bits (gpu_addr); - ib.ptr[2 ] =upper_32_bits (gpu_addr); - ib.ptr[3 ] =SDMA_PKT_WRITE_UNTILED_DW_3_COUNT (1 ); - ib.ptr[4 ] =0xDEADBEEF ; - ib.ptr[5 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.ptr[6 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.ptr[7 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.length_dw =8 ; - - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (r) + ib->ptr[1 ] =lower_32_bits (gpu_addr); + ib->ptr[2 ] =upper_32_bits (gpu_addr); + ib->ptr[3 ] =SDMA_PKT_WRITE_UNTILED_DW_3_COUNT (1 ); + ib->ptr[4 ] =0xDEADBEEF ; + ib->ptr[5 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->ptr[6 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->ptr[7 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->length_dw =8 ; + + r =amdgpu_job_submit_direct (job, ring, &f); +if (r) { +amdgpu_job_free (job); goto err1; + } r =dma_fence_wait_timeout (f, false, timeout);if (r ==0 ) {
@@ -906,7 +911,6 @@ static int sdma_v3_0_ring_test_ib(struct amdgpu_ring *ring, long timeout)else r = -EINVAL ; err1: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f); err0:amdgpu_device_wb_free (adev, index);
drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c +21 -17
@@ -1516,7 +1516,8 @@ static int sdma_v4_0_ring_test_ring(struct amdgpu_ring *ring)static int sdma_v4_0_ring_test_ib (struct amdgpu_ring *ring,long timeout) {struct amdgpu_device *adev = ring->adev; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ;unsigned index;long r;
@@ -1530,26 +1531,30 @@ static int sdma_v4_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) gpu_addr = adev->wb.gpu_addr + (index *4 ); tmp =0xCAFEDEAD ; adev->wb.wb[index] =cpu_to_le32 (tmp); -memset (&ib,0 ,sizeof (ib)); - r =amdgpu_ib_get (adev,NULL ,256 , -AMDGPU_IB_POOL_DIRECT , &ib); + + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,256 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_SDMA_RING_TEST );if (r) goto err0; - ib.ptr[0 ] =SDMA_PKT_HEADER_OP (SDMA_OP_WRITE ) | + ib = &job->ibs[0 ]; + ib->ptr[0 ] =SDMA_PKT_HEADER_OP (SDMA_OP_WRITE ) |SDMA_PKT_HEADER_SUB_OP (SDMA_SUBOP_WRITE_LINEAR ); - ib.ptr[1 ] =lower_32_bits (gpu_addr); - ib.ptr[2 ] =upper_32_bits (gpu_addr); - ib.ptr[3 ] =SDMA_PKT_WRITE_UNTILED_DW_3_COUNT (0 ); - ib.ptr[4 ] =0xDEADBEEF ; - ib.ptr[5 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.ptr[6 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.ptr[7 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.length_dw =8 ; - - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (r) + ib->ptr[1 ] =lower_32_bits (gpu_addr); + ib->ptr[2 ] =upper_32_bits (gpu_addr); + ib->ptr[3 ] =SDMA_PKT_WRITE_UNTILED_DW_3_COUNT (0 ); + ib->ptr[4 ] =0xDEADBEEF ; + ib->ptr[5 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->ptr[6 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->ptr[7 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->length_dw =8 ; + + r =amdgpu_job_submit_direct (job, ring, &f); +if (r) { +amdgpu_job_free (job); goto err1; + } r =dma_fence_wait_timeout (f, false, timeout);if (r ==0 ) {
@@ -1565,7 +1570,6 @@ static int sdma_v4_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) r = -EINVAL ; err1: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f); err0:amdgpu_device_wb_free (adev, index);
drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c +21 -17
@@ -1112,7 +1112,8 @@ static int sdma_v4_4_2_ring_test_ring(struct amdgpu_ring *ring)static int sdma_v4_4_2_ring_test_ib (struct amdgpu_ring *ring,long timeout) {struct amdgpu_device *adev = ring->adev; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ;unsigned index;long r;
@@ -1126,26 +1127,30 @@ static int sdma_v4_4_2_ring_test_ib(struct amdgpu_ring *ring, long timeout) gpu_addr = adev->wb.gpu_addr + (index *4 ); tmp =0xCAFEDEAD ; adev->wb.wb[index] =cpu_to_le32 (tmp); -memset (&ib,0 ,sizeof (ib)); - r =amdgpu_ib_get (adev,NULL ,256 , -AMDGPU_IB_POOL_DIRECT , &ib); + + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,256 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_SDMA_RING_TEST );if (r) goto err0; - ib.ptr[0 ] =SDMA_PKT_HEADER_OP (SDMA_OP_WRITE ) | + ib = &job->ibs[0 ]; + ib->ptr[0 ] =SDMA_PKT_HEADER_OP (SDMA_OP_WRITE ) |SDMA_PKT_HEADER_SUB_OP (SDMA_SUBOP_WRITE_LINEAR ); - ib.ptr[1 ] =lower_32_bits (gpu_addr); - ib.ptr[2 ] =upper_32_bits (gpu_addr); - ib.ptr[3 ] =SDMA_PKT_WRITE_UNTILED_DW_3_COUNT (0 ); - ib.ptr[4 ] =0xDEADBEEF ; - ib.ptr[5 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.ptr[6 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.ptr[7 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.length_dw =8 ; - - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (r) + ib->ptr[1 ] =lower_32_bits (gpu_addr); + ib->ptr[2 ] =upper_32_bits (gpu_addr); + ib->ptr[3 ] =SDMA_PKT_WRITE_UNTILED_DW_3_COUNT (0 ); + ib->ptr[4 ] =0xDEADBEEF ; + ib->ptr[5 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->ptr[6 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->ptr[7 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->length_dw =8 ; + + r =amdgpu_job_submit_direct (job, ring, &f); +if (r) { +amdgpu_job_free (job); goto err1; + } r =dma_fence_wait_timeout (f, false, timeout);if (r ==0 ) {
@@ -1161,7 +1166,6 @@ static int sdma_v4_4_2_ring_test_ib(struct amdgpu_ring *ring, long timeout) r = -EINVAL ; err1: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f); err0:amdgpu_device_wb_free (adev, index);
drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c +20 -17
@@ -1074,7 +1074,8 @@ static int sdma_v5_0_ring_test_ring(struct amdgpu_ring *ring)static int sdma_v5_0_ring_test_ib (struct amdgpu_ring *ring,long timeout) {struct amdgpu_device *adev = ring->adev; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ;unsigned index;long r;
@@ -1082,7 +1083,6 @@ static int sdma_v5_0_ring_test_ib(struct amdgpu_ring *ring, long timeout)u64 gpu_addr; tmp =0xCAFEDEAD ; -memset (&ib,0 ,sizeof (ib)); r =amdgpu_device_wb_get (adev, &index);if (r) {
@@ -1093,27 +1093,31 @@ static int sdma_v5_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) gpu_addr = adev->wb.gpu_addr + (index *4 ); adev->wb.wb[index] =cpu_to_le32 (tmp); - r =amdgpu_ib_get (adev,NULL ,256 , -AMDGPU_IB_POOL_DIRECT , &ib); + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,256 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_SDMA_RING_TEST );if (r) {drm_err (adev_to_drm (adev),"failed to get ib (%ld).\n" , r); goto err0; } - ib.ptr[0 ] =SDMA_PKT_HEADER_OP (SDMA_OP_WRITE ) | + ib = &job->ibs[0 ]; + ib->ptr[0 ] =SDMA_PKT_HEADER_OP (SDMA_OP_WRITE ) |SDMA_PKT_HEADER_SUB_OP (SDMA_SUBOP_WRITE_LINEAR ); - ib.ptr[1 ] =lower_32_bits (gpu_addr); - ib.ptr[2 ] =upper_32_bits (gpu_addr); - ib.ptr[3 ] =SDMA_PKT_WRITE_UNTILED_DW_3_COUNT (0 ); - ib.ptr[4 ] =0xDEADBEEF ; - ib.ptr[5 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.ptr[6 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.ptr[7 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.length_dw =8 ; - - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (r) + ib->ptr[1 ] =lower_32_bits (gpu_addr); + ib->ptr[2 ] =upper_32_bits (gpu_addr); + ib->ptr[3 ] =SDMA_PKT_WRITE_UNTILED_DW_3_COUNT (0 ); + ib->ptr[4 ] =0xDEADBEEF ; + ib->ptr[5 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->ptr[6 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->ptr[7 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->length_dw =8 ; + + r =amdgpu_job_submit_direct (job, ring, &f); +if (r) { +amdgpu_job_free (job); goto err1; + } r =dma_fence_wait_timeout (f, false, timeout);if (r ==0 ) {
@@ -1133,7 +1137,6 @@ static int sdma_v5_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) r = -EINVAL ; err1: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f); err0:amdgpu_device_wb_free (adev, index);
drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c +20 -16
@@ -974,7 +974,8 @@ static int sdma_v5_2_ring_test_ring(struct amdgpu_ring *ring)static int sdma_v5_2_ring_test_ib (struct amdgpu_ring *ring,long timeout) {struct amdgpu_device *adev = ring->adev; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ;unsigned index;long r;
@@ -982,7 +983,6 @@ static int sdma_v5_2_ring_test_ib(struct amdgpu_ring *ring, long timeout)u64 gpu_addr; tmp =0xCAFEDEAD ; -memset (&ib,0 ,sizeof (ib)); r =amdgpu_device_wb_get (adev, &index);if (r) {
@@ -993,26 +993,31 @@ static int sdma_v5_2_ring_test_ib(struct amdgpu_ring *ring, long timeout) gpu_addr = adev->wb.gpu_addr + (index *4 ); adev->wb.wb[index] =cpu_to_le32 (tmp); - r =amdgpu_ib_get (adev,NULL ,256 ,AMDGPU_IB_POOL_DIRECT , &ib); + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,256 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_SDMA_RING_TEST );if (r) {drm_err (adev_to_drm (adev),"failed to get ib (%ld).\n" , r); goto err0; } - ib.ptr[0 ] =SDMA_PKT_HEADER_OP (SDMA_OP_WRITE ) | + ib = &job->ibs[0 ]; + ib->ptr[0 ] =SDMA_PKT_HEADER_OP (SDMA_OP_WRITE ) |SDMA_PKT_HEADER_SUB_OP (SDMA_SUBOP_WRITE_LINEAR ); - ib.ptr[1 ] =lower_32_bits (gpu_addr); - ib.ptr[2 ] =upper_32_bits (gpu_addr); - ib.ptr[3 ] =SDMA_PKT_WRITE_UNTILED_DW_3_COUNT (0 ); - ib.ptr[4 ] =0xDEADBEEF ; - ib.ptr[5 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.ptr[6 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.ptr[7 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.length_dw =8 ; - - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (r) + ib->ptr[1 ] =lower_32_bits (gpu_addr); + ib->ptr[2 ] =upper_32_bits (gpu_addr); + ib->ptr[3 ] =SDMA_PKT_WRITE_UNTILED_DW_3_COUNT (0 ); + ib->ptr[4 ] =0xDEADBEEF ; + ib->ptr[5 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->ptr[6 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->ptr[7 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->length_dw =8 ; + + r =amdgpu_job_submit_direct (job, ring, &f); +if (r) { +amdgpu_job_free (job); goto err1; + } r =dma_fence_wait_timeout (f, false, timeout);if (r ==0 ) {
@@ -1032,7 +1037,6 @@ static int sdma_v5_2_ring_test_ib(struct amdgpu_ring *ring, long timeout) r = -EINVAL ; err1: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f); err0:amdgpu_device_wb_free (adev, index);
drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c +20 -16
@@ -981,7 +981,8 @@ static int sdma_v6_0_ring_test_ring(struct amdgpu_ring *ring)static int sdma_v6_0_ring_test_ib (struct amdgpu_ring *ring,long timeout) {struct amdgpu_device *adev = ring->adev; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ;unsigned index;long r;
@@ -989,7 +990,6 @@ static int sdma_v6_0_ring_test_ib(struct amdgpu_ring *ring, long timeout)u64 gpu_addr; tmp =0xCAFEDEAD ; -memset (&ib,0 ,sizeof (ib)); r =amdgpu_device_wb_get (adev, &index);if (r) {
@@ -1000,26 +1000,31 @@ static int sdma_v6_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) gpu_addr = adev->wb.gpu_addr + (index *4 ); adev->wb.wb[index] =cpu_to_le32 (tmp); - r =amdgpu_ib_get (adev,NULL ,256 ,AMDGPU_IB_POOL_DIRECT , &ib); + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,256 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_SDMA_RING_TEST );if (r) {drm_err (adev_to_drm (adev),"failed to get ib (%ld).\n" , r); goto err0; } - ib.ptr[0 ] =SDMA_PKT_COPY_LINEAR_HEADER_OP (SDMA_OP_WRITE ) | + ib = &job->ibs[0 ]; + ib->ptr[0 ] =SDMA_PKT_COPY_LINEAR_HEADER_OP (SDMA_OP_WRITE ) |SDMA_PKT_COPY_LINEAR_HEADER_SUB_OP (SDMA_SUBOP_WRITE_LINEAR ); - ib.ptr[1 ] =lower_32_bits (gpu_addr); - ib.ptr[2 ] =upper_32_bits (gpu_addr); - ib.ptr[3 ] =SDMA_PKT_WRITE_UNTILED_DW_3_COUNT (0 ); - ib.ptr[4 ] =0xDEADBEEF ; - ib.ptr[5 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.ptr[6 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.ptr[7 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.length_dw =8 ; - - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (r) + ib->ptr[1 ] =lower_32_bits (gpu_addr); + ib->ptr[2 ] =upper_32_bits (gpu_addr); + ib->ptr[3 ] =SDMA_PKT_WRITE_UNTILED_DW_3_COUNT (0 ); + ib->ptr[4 ] =0xDEADBEEF ; + ib->ptr[5 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->ptr[6 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->ptr[7 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->length_dw =8 ; + + r =amdgpu_job_submit_direct (job, ring, &f); +if (r) { +amdgpu_job_free (job); goto err1; + } r =dma_fence_wait_timeout (f, false, timeout);if (r ==0 ) {
@@ -1039,7 +1044,6 @@ static int sdma_v6_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) r = -EINVAL ; err1: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f); err0:amdgpu_device_wb_free (adev, index);
drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c +20 -16
@@ -997,7 +997,8 @@ static int sdma_v7_0_ring_test_ring(struct amdgpu_ring *ring)static int sdma_v7_0_ring_test_ib (struct amdgpu_ring *ring,long timeout) {struct amdgpu_device *adev = ring->adev; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ;unsigned index;long r;
@@ -1005,7 +1006,6 @@ static int sdma_v7_0_ring_test_ib(struct amdgpu_ring *ring, long timeout)u64 gpu_addr; tmp =0xCAFEDEAD ; -memset (&ib,0 ,sizeof (ib)); r =amdgpu_device_wb_get (adev, &index);if (r) {
@@ -1016,26 +1016,31 @@ static int sdma_v7_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) gpu_addr = adev->wb.gpu_addr + (index *4 ); adev->wb.wb[index] =cpu_to_le32 (tmp); - r =amdgpu_ib_get (adev,NULL ,256 ,AMDGPU_IB_POOL_DIRECT , &ib); + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,256 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_SDMA_RING_TEST );if (r) {drm_err (adev_to_drm (adev),"failed to get ib (%ld).\n" , r); goto err0; } - ib.ptr[0 ] =SDMA_PKT_COPY_LINEAR_HEADER_OP (SDMA_OP_WRITE ) | + ib = &job->ibs[0 ]; + ib->ptr[0 ] =SDMA_PKT_COPY_LINEAR_HEADER_OP (SDMA_OP_WRITE ) |SDMA_PKT_COPY_LINEAR_HEADER_SUB_OP (SDMA_SUBOP_WRITE_LINEAR ); - ib.ptr[1 ] =lower_32_bits (gpu_addr); - ib.ptr[2 ] =upper_32_bits (gpu_addr); - ib.ptr[3 ] =SDMA_PKT_WRITE_UNTILED_DW_3_COUNT (0 ); - ib.ptr[4 ] =0xDEADBEEF ; - ib.ptr[5 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.ptr[6 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.ptr[7 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.length_dw =8 ; - - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (r) + ib->ptr[1 ] =lower_32_bits (gpu_addr); + ib->ptr[2 ] =upper_32_bits (gpu_addr); + ib->ptr[3 ] =SDMA_PKT_WRITE_UNTILED_DW_3_COUNT (0 ); + ib->ptr[4 ] =0xDEADBEEF ; + ib->ptr[5 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->ptr[6 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->ptr[7 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->length_dw =8 ; + + r =amdgpu_job_submit_direct (job, ring, &f); +if (r) { +amdgpu_job_free (job); goto err1; + } r =dma_fence_wait_timeout (f, false, timeout);if (r ==0 ) {
@@ -1055,7 +1060,6 @@ static int sdma_v7_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) r = -EINVAL ; err1: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f); err0:amdgpu_device_wb_free (adev, index);
drivers/gpu/drm/amd/amdgpu/sdma_v7_1.c +20 -16
@@ -987,7 +987,8 @@ static int sdma_v7_1_ring_test_ring(struct amdgpu_ring *ring)static int sdma_v7_1_ring_test_ib (struct amdgpu_ring *ring,long timeout) {struct amdgpu_device *adev = ring->adev; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ;unsigned index;long r;
@@ -995,7 +996,6 @@ static int sdma_v7_1_ring_test_ib(struct amdgpu_ring *ring, long timeout)u64 gpu_addr; tmp =0xCAFEDEAD ; -memset (&ib,0 ,sizeof (ib)); r =amdgpu_device_wb_get (adev, &index);if (r) {
@@ -1006,26 +1006,31 @@ static int sdma_v7_1_ring_test_ib(struct amdgpu_ring *ring, long timeout) gpu_addr = adev->wb.gpu_addr + (index *4 ); adev->wb.wb[index] =cpu_to_le32 (tmp); - r =amdgpu_ib_get (adev,NULL ,256 ,AMDGPU_IB_POOL_DIRECT , &ib); + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,256 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_SDMA_RING_TEST );if (r) {DRM_ERROR ("amdgpu: failed to get ib (%ld).\n" , r); goto err0; } - ib.ptr[0 ] =SDMA_PKT_COPY_LINEAR_HEADER_OP (SDMA_OP_WRITE ) | + ib = &job->ibs[0 ]; + ib->ptr[0 ] =SDMA_PKT_COPY_LINEAR_HEADER_OP (SDMA_OP_WRITE ) |SDMA_PKT_COPY_LINEAR_HEADER_SUB_OP (SDMA_SUBOP_WRITE_LINEAR ); - ib.ptr[1 ] =lower_32_bits (gpu_addr); - ib.ptr[2 ] =upper_32_bits (gpu_addr); - ib.ptr[3 ] =SDMA_PKT_WRITE_UNTILED_DW_3_COUNT (0 ); - ib.ptr[4 ] =0xDEADBEEF ; - ib.ptr[5 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.ptr[6 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.ptr[7 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.length_dw =8 ; - - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (r) + ib->ptr[1 ] =lower_32_bits (gpu_addr); + ib->ptr[2 ] =upper_32_bits (gpu_addr); + ib->ptr[3 ] =SDMA_PKT_WRITE_UNTILED_DW_3_COUNT (0 ); + ib->ptr[4 ] =0xDEADBEEF ; + ib->ptr[5 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->ptr[6 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->ptr[7 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->length_dw =8 ; + + r =amdgpu_job_submit_direct (job, ring, &f); +if (r) { +amdgpu_job_free (job); goto err1; + } r =dma_fence_wait_timeout (f, false, timeout);if (r ==0 ) {
@@ -1045,7 +1050,6 @@ static int sdma_v7_1_ring_test_ib(struct amdgpu_ring *ring, long timeout) r = -EINVAL ; err1: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f); err0:amdgpu_device_wb_free (adev, index);
drivers/gpu/drm/amd/amdgpu/si_dma.c +17 -12
@@ -259,7 +259,8 @@ static int si_dma_ring_test_ring(struct amdgpu_ring *ring)static int si_dma_ring_test_ib (struct amdgpu_ring *ring,long timeout) {struct amdgpu_device *adev = ring->adev; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ;unsigned index;u32 tmp =0 ;
@@ -273,20 +274,25 @@ static int si_dma_ring_test_ib(struct amdgpu_ring *ring, long timeout) gpu_addr = adev->wb.gpu_addr + (index *4 ); tmp =0xCAFEDEAD ; adev->wb.wb[index] =cpu_to_le32 (tmp); -memset (&ib,0 ,sizeof (ib)); - r =amdgpu_ib_get (adev,NULL ,256 , -AMDGPU_IB_POOL_DIRECT , &ib); + + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,256 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_SDMA_RING_TEST );if (r) goto err0; - ib.ptr[0 ] =DMA_PACKET (DMA_PACKET_WRITE ,0 ,0 ,0 ,1 ); - ib.ptr[1 ] =lower_32_bits (gpu_addr); - ib.ptr[2 ] =upper_32_bits (gpu_addr) &0xff ; - ib.ptr[3 ] =0xDEADBEEF ; - ib.length_dw =4 ; - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (r) + ib = &job->ibs[0 ]; + ib->ptr[0 ] =DMA_PACKET (DMA_PACKET_WRITE ,0 ,0 ,0 ,1 ); + ib->ptr[1 ] =lower_32_bits (gpu_addr); + ib->ptr[2 ] =upper_32_bits (gpu_addr) &0xff ; + ib->ptr[3 ] =0xDEADBEEF ; + ib->length_dw =4 ; + + r =amdgpu_job_submit_direct (job, ring, &f); +if (r) { +amdgpu_job_free (job); goto err1; + } r =dma_fence_wait_timeout (f, false, timeout);if (r ==0 ) {
@@ -302,7 +308,6 @@ static int si_dma_ring_test_ib(struct amdgpu_ring *ring, long timeout) r = -EINVAL ; err1: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f); err0:amdgpu_device_wb_free (adev, index);
Signature · 1 line
2.52.0
Re: [PATCH 03/12] drm/amdgpu: switch all IPs to using job for IBs
Quoted 845 lines · Alex Deucher
Switch to using a job structure for IBs.
Acked-by Christian König <[email protected]>Signed-off-by Alex Deucher <[email protected]>--- drivers/gpu/drm/amd/amdgpu/amdgpu_vpe.c | 37 +++--- drivers/gpu/drm/amd/amdgpu/cik_sdma.c | 31 ++--- drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c | 29 ++--- drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c | 29 ++--- drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c | 29 ++--- drivers/gpu/drm/amd/amdgpu/gfx_v12_1.c | 29 ++--- drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c | 24 ++-- drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c | 25 ++-- drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c | 139 ++++++++++++----------- drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c | 138 +++++++++++----------- drivers/gpu/drm/amd/amdgpu/gfx_v9_4_2.c | 26 ++--- drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c | 29 ++--- drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c | 38 ++++--- drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c | 38 ++++--- drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c | 38 ++++--- drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c | 38 ++++--- drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c | 37 +++--- drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c | 36 +++--- drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c | 36 +++--- drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c | 36 +++--- drivers/gpu/drm/amd/amdgpu/sdma_v7_1.c | 36 +++--- drivers/gpu/drm/amd/amdgpu/si_dma.c | 29 +++-- 22 files changed, 500 insertions(+), 427 deletions(-)drivers/gpu/drm/amd/amdgpu/amdgpu_vpe.c +21
-16@@ -817,7 +817,8 @@ static int vpe_ring_test_ib(struct amdgpu_ring *ring, long timeout) {struct amdgpu_device *adev = ring->adev;const uint32_t test_pattern =0xdeadbeef ; -struct amdgpu_ib ib = {}; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ;uint32_t index;uint64_t wb_addr;@@ -832,23 +833,28 @@ static int vpe_ring_test_ib(struct amdgpu_ring *ring, long timeout) adev->wb.wb[index] =0 ; wb_addr = adev->wb.gpu_addr + (index *4 ); - ret =amdgpu_ib_get (adev,NULL ,256 ,AMDGPU_IB_POOL_DIRECT , &ib); + ret =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,256 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_VPE_RING_TEST );if (ret) goto err0; - - ib.ptr[0 ] =VPE_CMD_HEADER (VPE_CMD_OPCODE_FENCE ,0 ); - ib.ptr[1 ] =lower_32_bits (wb_addr); - ib.ptr[2 ] =upper_32_bits (wb_addr); - ib.ptr[3 ] = test_pattern; - ib.ptr[4 ] =VPE_CMD_HEADER (VPE_CMD_OPCODE_NOP ,0 ); - ib.ptr[5 ] =VPE_CMD_HEADER (VPE_CMD_OPCODE_NOP ,0 ); - ib.ptr[6 ] =VPE_CMD_HEADER (VPE_CMD_OPCODE_NOP ,0 ); - ib.ptr[7 ] =VPE_CMD_HEADER (VPE_CMD_OPCODE_NOP ,0 ); - ib.length_dw =8 ; - - ret =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (ret) + ib = &job->ibs[0 ]; + + ib->ptr[0 ] =VPE_CMD_HEADER (VPE_CMD_OPCODE_FENCE ,0 ); + ib->ptr[1 ] =lower_32_bits (wb_addr); + ib->ptr[2 ] =upper_32_bits (wb_addr); + ib->ptr[3 ] = test_pattern; + ib->ptr[4 ] =VPE_CMD_HEADER (VPE_CMD_OPCODE_NOP ,0 ); + ib->ptr[5 ] =VPE_CMD_HEADER (VPE_CMD_OPCODE_NOP ,0 ); + ib->ptr[6 ] =VPE_CMD_HEADER (VPE_CMD_OPCODE_NOP ,0 ); + ib->ptr[7 ] =VPE_CMD_HEADER (VPE_CMD_OPCODE_NOP ,0 ); + ib->length_dw =8 ; + + ret =amdgpu_job_submit_direct (job, ring, &f); +if (ret) { +amdgpu_job_free (job); goto err1; + } ret =dma_fence_wait_timeout (f, false, timeout);if (ret <=0 ) {@@ -859,7 +865,6 @@ static int vpe_ring_test_ib(struct amdgpu_ring *ring, long timeout) ret = (le32_to_cpu (adev->wb.wb[index]) == test_pattern) ?0 : -EINVAL ; err1: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f); err0:amdgpu_device_wb_free (adev, index);drivers/gpu/drm/amd/amdgpu/cik_sdma.c +18
-13@@ -652,7 +652,8 @@ static int cik_sdma_ring_test_ring(struct amdgpu_ring *ring)static int cik_sdma_ring_test_ib (struct amdgpu_ring *ring,long timeout) {struct amdgpu_device *adev = ring->adev; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ;unsigned index;u32 tmp =0 ;@@ -666,22 +667,27 @@ static int cik_sdma_ring_test_ib(struct amdgpu_ring *ring, long timeout) gpu_addr = adev->wb.gpu_addr + (index *4 ); tmp =0xCAFEDEAD ; adev->wb.wb[index] =cpu_to_le32 (tmp); -memset (&ib,0 ,sizeof (ib)); - r =amdgpu_ib_get (adev,NULL ,256 , -AMDGPU_IB_POOL_DIRECT , &ib); + + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,256 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_SDMA_RING_TEST );if (r) goto err0; + ib = &job->ibs[0 ]; - ib.ptr[0 ] =SDMA_PACKET (SDMA_OPCODE_WRITE , + ib->ptr[0 ] =SDMA_PACKET (SDMA_OPCODE_WRITE ,SDMA_WRITE_SUB_OPCODE_LINEAR ,0 ); - ib.ptr[1 ] =lower_32_bits (gpu_addr); - ib.ptr[2 ] =upper_32_bits (gpu_addr); - ib.ptr[3 ] =1 ; - ib.ptr[4 ] =0xDEADBEEF ; - ib.length_dw =5 ; - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (r) + ib->ptr[1 ] =lower_32_bits (gpu_addr); + ib->ptr[2 ] =upper_32_bits (gpu_addr); + ib->ptr[3 ] =1 ; + ib->ptr[4 ] =0xDEADBEEF ; + ib->length_dw =5 ; + + r =amdgpu_job_submit_direct (job, ring, &f); +if (r) { +amdgpu_job_free (job); goto err1; + } r =dma_fence_wait_timeout (f, false, timeout);if (r ==0 ) {@@ -697,7 +703,6 @@ static int cik_sdma_ring_test_ib(struct amdgpu_ring *ring, long timeout) r = -EINVAL ; err1: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f); err0:amdgpu_device_wb_free (adev, index);drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c +16
-13@@ -4071,15 +4071,14 @@ static int gfx_v10_0_ring_test_ring(struct amdgpu_ring *ring)static int gfx_v10_0_ring_test_ib (struct amdgpu_ring *ring,long timeout) {struct amdgpu_device *adev = ring->adev; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ;unsigned int index;uint64_t gpu_addr;uint32_t *cpu_ptr;long r; -memset (&ib,0 ,sizeof (ib)); - r =amdgpu_device_wb_get (adev, &index);if (r)return r;@@ -4088,22 +4087,27 @@ static int gfx_v10_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) adev->wb.wb[index] =cpu_to_le32 (0xCAFEDEAD ); cpu_ptr = &adev->wb.wb[index]; - r =amdgpu_ib_get (adev,NULL ,20 ,AMDGPU_IB_POOL_DIRECT , &ib); + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,20 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_GFX_RING_TEST );if (r) {drm_err (adev_to_drm (adev),"failed to get ib (%ld).\n" , r); goto err1; } + ib = &job->ibs[0 ]; - ib.ptr[0 ] =PACKET3 (PACKET3_WRITE_DATA ,3 ); - ib.ptr[1 ] =WRITE_DATA_DST_SEL (5 ) |WR_CONFIRM ; - ib.ptr[2 ] =lower_32_bits (gpu_addr); - ib.ptr[3 ] =upper_32_bits (gpu_addr); - ib.ptr[4 ] =0xDEADBEEF ; - ib.length_dw =5 ; + ib->ptr[0 ] =PACKET3 (PACKET3_WRITE_DATA ,3 ); + ib->ptr[1 ] =WRITE_DATA_DST_SEL (5 ) |WR_CONFIRM ; + ib->ptr[2 ] =lower_32_bits (gpu_addr); + ib->ptr[3 ] =upper_32_bits (gpu_addr); + ib->ptr[4 ] =0xDEADBEEF ; + ib->length_dw =5 ; - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (r) + r =amdgpu_job_submit_direct (job, ring, &f); +if (r) { +amdgpu_job_free (job); goto err2; + } r =dma_fence_wait_timeout (f, false, timeout);if (r ==0 ) {@@ -4118,7 +4122,6 @@ static int gfx_v10_0_ring_test_ib(struct amdgpu_ring *ring, long timeout)else r = -EINVAL ; err2: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f); err1:amdgpu_device_wb_free (adev, index);drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c +16
-13@@ -604,7 +604,8 @@ static int gfx_v11_0_ring_test_ring(struct amdgpu_ring *ring)static int gfx_v11_0_ring_test_ib (struct amdgpu_ring *ring,long timeout) {struct amdgpu_device *adev = ring->adev; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ;unsigned index;uint64_t gpu_addr;@@ -616,8 +617,6 @@ static int gfx_v11_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) ring->funcs->type == AMDGPU_RING_TYPE_KIQ)return 0 ; -memset (&ib,0 ,sizeof (ib)); - r =amdgpu_device_wb_get (adev, &index);if (r)return r;@@ -626,22 +625,27 @@ static int gfx_v11_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) adev->wb.wb[index] =cpu_to_le32 (0xCAFEDEAD ); cpu_ptr = &adev->wb.wb[index]; - r =amdgpu_ib_get (adev,NULL ,20 ,AMDGPU_IB_POOL_DIRECT , &ib); + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,20 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_GFX_RING_TEST );if (r) {drm_err (adev_to_drm (adev),"failed to get ib (%ld).\n" , r); goto err1; } + ib = &job->ibs[0 ]; - ib.ptr[0 ] =PACKET3 (PACKET3_WRITE_DATA ,3 ); - ib.ptr[1 ] =WRITE_DATA_DST_SEL (5 ) |WR_CONFIRM ; - ib.ptr[2 ] =lower_32_bits (gpu_addr); - ib.ptr[3 ] =upper_32_bits (gpu_addr); - ib.ptr[4 ] =0xDEADBEEF ; - ib.length_dw =5 ; + ib->ptr[0 ] =PACKET3 (PACKET3_WRITE_DATA ,3 ); + ib->ptr[1 ] =WRITE_DATA_DST_SEL (5 ) |WR_CONFIRM ; + ib->ptr[2 ] =lower_32_bits (gpu_addr); + ib->ptr[3 ] =upper_32_bits (gpu_addr); + ib->ptr[4 ] =0xDEADBEEF ; + ib->length_dw =5 ; - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (r) + r =amdgpu_job_submit_direct (job, ring, &f); +if (r) { +amdgpu_job_free (job); goto err2; + } r =dma_fence_wait_timeout (f, false, timeout);if (r ==0 ) {@@ -656,7 +660,6 @@ static int gfx_v11_0_ring_test_ib(struct amdgpu_ring *ring, long timeout)else r = -EINVAL ; err2: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f); err1:amdgpu_device_wb_free (adev, index);drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c +16
-13@@ -493,7 +493,8 @@ static int gfx_v12_0_ring_test_ring(struct amdgpu_ring *ring)static int gfx_v12_0_ring_test_ib (struct amdgpu_ring *ring,long timeout) {struct amdgpu_device *adev = ring->adev; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ;unsigned index;uint64_t gpu_addr;@@ -505,8 +506,6 @@ static int gfx_v12_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) ring->funcs->type == AMDGPU_RING_TYPE_KIQ)return 0 ; -memset (&ib,0 ,sizeof (ib)); - r =amdgpu_device_wb_get (adev, &index);if (r)return r;@@ -515,22 +514,27 @@ static int gfx_v12_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) adev->wb.wb[index] =cpu_to_le32 (0xCAFEDEAD ); cpu_ptr = &adev->wb.wb[index]; - r =amdgpu_ib_get (adev,NULL ,16 ,AMDGPU_IB_POOL_DIRECT , &ib); + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,16 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_GFX_RING_TEST );if (r) {drm_err (adev_to_drm (adev),"failed to get ib (%ld).\n" , r); goto err1; } + ib = &job->ibs[0 ]; - ib.ptr[0 ] =PACKET3 (PACKET3_WRITE_DATA ,3 ); - ib.ptr[1 ] =WRITE_DATA_DST_SEL (5 ) |WR_CONFIRM ; - ib.ptr[2 ] =lower_32_bits (gpu_addr); - ib.ptr[3 ] =upper_32_bits (gpu_addr); - ib.ptr[4 ] =0xDEADBEEF ; - ib.length_dw =5 ; + ib->ptr[0 ] =PACKET3 (PACKET3_WRITE_DATA ,3 ); + ib->ptr[1 ] =WRITE_DATA_DST_SEL (5 ) |WR_CONFIRM ; + ib->ptr[2 ] =lower_32_bits (gpu_addr); + ib->ptr[3 ] =upper_32_bits (gpu_addr); + ib->ptr[4 ] =0xDEADBEEF ; + ib->length_dw =5 ; - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (r) + r =amdgpu_job_submit_direct (job, ring, &f); +if (r) { +amdgpu_job_free (job); goto err2; + } r =dma_fence_wait_timeout (f, false, timeout);if (r ==0 ) {@@ -545,7 +549,6 @@ static int gfx_v12_0_ring_test_ib(struct amdgpu_ring *ring, long timeout)else r = -EINVAL ; err2: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f); err1:amdgpu_device_wb_free (adev, index);drivers/gpu/drm/amd/amdgpu/gfx_v12_1.c +16
-13@@ -307,7 +307,8 @@ static int gfx_v12_1_ring_test_ring(struct amdgpu_ring *ring)static int gfx_v12_1_ring_test_ib (struct amdgpu_ring *ring,long timeout) {struct amdgpu_device *adev = ring->adev; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ;unsigned index;uint64_t gpu_addr;@@ -319,8 +320,6 @@ static int gfx_v12_1_ring_test_ib(struct amdgpu_ring *ring, long timeout) ring->funcs->type == AMDGPU_RING_TYPE_KIQ)return 0 ; -memset (&ib,0 ,sizeof (ib)); - r =amdgpu_device_wb_get (adev, &index);if (r)return r;@@ -329,22 +328,27 @@ static int gfx_v12_1_ring_test_ib(struct amdgpu_ring *ring, long timeout) adev->wb.wb[index] =cpu_to_le32 (0xCAFEDEAD ); cpu_ptr = &adev->wb.wb[index]; - r =amdgpu_ib_get (adev,NULL ,16 ,AMDGPU_IB_POOL_DIRECT , &ib); + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,16 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_GFX_RING_TEST );if (r) {dev_err (adev->dev,"amdgpu: failed to get ib (%ld).\n" , r); goto err1; } + ib = &job->ibs[0 ]; - ib.ptr[0 ] =PACKET3 (PACKET3_WRITE_DATA ,3 ); - ib.ptr[1 ] =WRITE_DATA_DST_SEL (5 ) |WR_CONFIRM ; - ib.ptr[2 ] =lower_32_bits (gpu_addr); - ib.ptr[3 ] =upper_32_bits (gpu_addr); - ib.ptr[4 ] =0xDEADBEEF ; - ib.length_dw =5 ; + ib->ptr[0 ] =PACKET3 (PACKET3_WRITE_DATA ,3 ); + ib->ptr[1 ] =WRITE_DATA_DST_SEL (5 ) |WR_CONFIRM ; + ib->ptr[2 ] =lower_32_bits (gpu_addr); + ib->ptr[3 ] =upper_32_bits (gpu_addr); + ib->ptr[4 ] =0xDEADBEEF ; + ib->length_dw =5 ; - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (r) + r =amdgpu_job_submit_direct (job, ring, &f); +if (r) { +amdgpu_job_free (job); goto err2; + } r =dma_fence_wait_timeout (f, false, timeout);if (r ==0 ) {@@ -359,7 +363,6 @@ static int gfx_v12_1_ring_test_ib(struct amdgpu_ring *ring, long timeout)else r = -EINVAL ; err2: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f); err1:amdgpu_device_wb_free (adev, index);drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c +14
-10@@ -1895,24 +1895,29 @@ static int gfx_v6_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) {struct amdgpu_device *adev = ring->adev;struct dma_fence *f =NULL ; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;uint32_t tmp =0 ;long r;WREG32 (mmSCRATCH_REG0,0xCAFEDEAD ); -memset (&ib,0 ,sizeof (ib)); - r =amdgpu_ib_get (adev,NULL ,256 ,AMDGPU_IB_POOL_DIRECT , &ib); + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,256 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_GFX_RING_TEST );if (r)return r; - ib.ptr[0 ] =PACKET3 (PACKET3_SET_CONFIG_REG ,1 ); - ib.ptr[1 ] = mmSCRATCH_REG0 -PACKET3_SET_CONFIG_REG_START ; - ib.ptr[2 ] =0xDEADBEEF ; - ib.length_dw =3 ; + ib = &job->ibs[0 ]; + ib->ptr[0 ] =PACKET3 (PACKET3_SET_CONFIG_REG ,1 ); + ib->ptr[1 ] = mmSCRATCH_REG0 -PACKET3_SET_CONFIG_REG_START ; + ib->ptr[2 ] =0xDEADBEEF ; + ib->length_dw =3 ; - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (r) + r =amdgpu_job_submit_direct (job, ring, &f); +if (r) { +amdgpu_job_free (job); goto error; + } r =dma_fence_wait_timeout (f, false, timeout);if (r ==0 ) {@@ -1928,7 +1933,6 @@ static int gfx_v6_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) r = -EINVAL ; error: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f);return r; }drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c +15
-10@@ -2291,25 +2291,31 @@ static void gfx_v7_ring_emit_cntxcntl(struct amdgpu_ring *ring, uint32_t flags)static int gfx_v7_0_ring_test_ib (struct amdgpu_ring *ring,long timeout) {struct amdgpu_device *adev = ring->adev; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ;uint32_t tmp =0 ;long r;WREG32 (mmSCRATCH_REG0,0xCAFEDEAD ); -memset (&ib,0 ,sizeof (ib)); - r =amdgpu_ib_get (adev,NULL ,256 ,AMDGPU_IB_POOL_DIRECT , &ib); + + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,256 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_GFX_RING_TEST );if (r)return r; - ib.ptr[0 ] =PACKET3 (PACKET3_SET_UCONFIG_REG ,1 ); - ib.ptr[1 ] = mmSCRATCH_REG0 -PACKET3_SET_UCONFIG_REG_START ; - ib.ptr[2 ] =0xDEADBEEF ; - ib.length_dw =3 ; + ib = &job->ibs[0 ]; + ib->ptr[0 ] =PACKET3 (PACKET3_SET_UCONFIG_REG ,1 ); + ib->ptr[1 ] = mmSCRATCH_REG0 -PACKET3_SET_UCONFIG_REG_START ; + ib->ptr[2 ] =0xDEADBEEF ; + ib->length_dw =3 ; - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (r) + r =amdgpu_job_submit_direct (job, ring, &f); +if (r) { +amdgpu_job_free (job); goto error; + } r =dma_fence_wait_timeout (f, false, timeout);if (r ==0 ) {@@ -2325,7 +2331,6 @@ static int gfx_v7_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) r = -EINVAL ; error: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f);return r; }drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +72
-67@@ -868,9 +868,9 @@ static int gfx_v8_0_ring_test_ring(struct amdgpu_ring *ring)static int gfx_v8_0_ring_test_ib (struct amdgpu_ring *ring,long timeout) {struct amdgpu_device *adev = ring->adev; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ; -unsigned int index;uint64_t gpu_addr;uint32_t tmp;@@ -882,22 +882,26 @@ static int gfx_v8_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) gpu_addr = adev->wb.gpu_addr + (index *4 ); adev->wb.wb[index] =cpu_to_le32 (0xCAFEDEAD ); -memset (&ib,0 ,sizeof (ib)); - r =amdgpu_ib_get (adev,NULL ,20 ,AMDGPU_IB_POOL_DIRECT , &ib); + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,20 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_GFX_RING_TEST );if (r) goto err1; - ib.ptr[0 ] =PACKET3 (PACKET3_WRITE_DATA ,3 ); - ib.ptr[1 ] =WRITE_DATA_DST_SEL (5 ) |WR_CONFIRM ; - ib.ptr[2 ] =lower_32_bits (gpu_addr); - ib.ptr[3 ] =upper_32_bits (gpu_addr); - ib.ptr[4 ] =0xDEADBEEF ; - ib.length_dw =5 ; + ib = &job->ibs[0 ]; + ib->ptr[0 ] =PACKET3 (PACKET3_WRITE_DATA ,3 ); + ib->ptr[1 ] =WRITE_DATA_DST_SEL (5 ) |WR_CONFIRM ; + ib->ptr[2 ] =lower_32_bits (gpu_addr); + ib->ptr[3 ] =upper_32_bits (gpu_addr); + ib->ptr[4 ] =0xDEADBEEF ; + ib->length_dw =5 ; - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (r) + r =amdgpu_job_submit_direct (job, ring, &f); +if (r) { +amdgpu_job_free (job); goto err2; + } r =dma_fence_wait_timeout (f, false, timeout);if (r ==0 ) {@@ -914,7 +918,6 @@ static int gfx_v8_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) r = -EINVAL ; err2: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f); err1:amdgpu_device_wb_free (adev, index);@@ -1474,7 +1477,8 @@ static const u32 sec_ded_counter_registers[] =static int gfx_v8_0_do_edc_gpr_workarounds (struct amdgpu_device *adev) {struct amdgpu_ring *ring = &adev->gfx.compute_ring[0 ]; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ;int r, i;u32 tmp;@@ -1505,106 +1509,108 @@ static int gfx_v8_0_do_edc_gpr_workarounds(struct amdgpu_device *adev) total_size +=sizeof (sgpr_init_compute_shader);/* allocate an indirect buffer to put the commands in */ -memset (&ib,0 ,sizeof (ib)); - r =amdgpu_ib_get (adev,NULL , total_size, -AMDGPU_IB_POOL_DIRECT , &ib); + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL , total_size, +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_RUN_SHADER );if (r) {drm_err (adev_to_drm (adev),"failed to get ib (%d).\n" , r);return r; } + ib = &job->ibs[0 ];/* load the compute shaders */ for (i =0 ; i <ARRAY_SIZE (vgpr_init_compute_shader); i++) - ib.ptr[i + (vgpr_offset /4 )] = vgpr_init_compute_shader[i]; + ib->ptr[i + (vgpr_offset /4 )] = vgpr_init_compute_shader[i];for (i =0 ; i <ARRAY_SIZE (sgpr_init_compute_shader); i++) - ib.ptr[i + (sgpr_offset /4 )] = sgpr_init_compute_shader[i]; + ib->ptr[i + (sgpr_offset /4 )] = sgpr_init_compute_shader[i];/* init the ib length to 0 */ - ib.length_dw =0 ; + ib->length_dw =0 ;/* VGPR */ /* write the register state for the compute dispatch */ for (i =0 ; i <ARRAY_SIZE (vgpr_init_regs); i +=2 ) { - ib.ptr[ib.length_dw++] =PACKET3 (PACKET3_SET_SH_REG ,1 ); - ib.ptr[ib.length_dw++] = vgpr_init_regs[i] -PACKET3_SET_SH_REG_START ; - ib.ptr[ib.length_dw++] = vgpr_init_regs[i +1 ]; + ib->ptr[ib->length_dw++] =PACKET3 (PACKET3_SET_SH_REG ,1 ); + ib->ptr[ib->length_dw++] = vgpr_init_regs[i] -PACKET3_SET_SH_REG_START ; + ib->ptr[ib->length_dw++] = vgpr_init_regs[i +1 ]; }/* write the shader start address: mmCOMPUTE_PGM_LO, mmCOMPUTE_PGM_HI */ - gpu_addr = (ib.gpu_addr + (u64 )vgpr_offset) >>8 ; - ib.ptr[ib.length_dw++] =PACKET3 (PACKET3_SET_SH_REG ,2 ); - ib.ptr[ib.length_dw++] = mmCOMPUTE_PGM_LO -PACKET3_SET_SH_REG_START ; - ib.ptr[ib.length_dw++] =lower_32_bits (gpu_addr); - ib.ptr[ib.length_dw++] =upper_32_bits (gpu_addr); + gpu_addr = (ib->gpu_addr + (u64 )vgpr_offset) >>8 ; + ib->ptr[ib->length_dw++] =PACKET3 (PACKET3_SET_SH_REG ,2 ); + ib->ptr[ib->length_dw++] = mmCOMPUTE_PGM_LO -PACKET3_SET_SH_REG_START ; + ib->ptr[ib->length_dw++] =lower_32_bits (gpu_addr); + ib->ptr[ib->length_dw++] =upper_32_bits (gpu_addr);/* write dispatch packet */ - ib.ptr[ib.length_dw++] =PACKET3 (PACKET3_DISPATCH_DIRECT ,3 ); - ib.ptr[ib.length_dw++] =8 ;/* x */ - ib.ptr[ib.length_dw++] =1 ;/* y */ - ib.ptr[ib.length_dw++] =1 ;/* z */ - ib.ptr[ib.length_dw++] = + ib->ptr[ib->length_dw++] =PACKET3 (PACKET3_DISPATCH_DIRECT ,3 ); + ib->ptr[ib->length_dw++] =8 ;/* x */ + ib->ptr[ib->length_dw++] =1 ;/* y */ + ib->ptr[ib->length_dw++] =1 ;/* z */ + ib->ptr[ib->length_dw++] =REG_SET_FIELD (0 ,COMPUTE_DISPATCH_INITIATOR ,COMPUTE_SHADER_EN ,1 );/* write CS partial flush packet */ - ib.ptr[ib.length_dw++] =PACKET3 (PACKET3_EVENT_WRITE ,0 ); - ib.ptr[ib.length_dw++] =EVENT_TYPE (7 ) |EVENT_INDEX (4 ); + ib->ptr[ib->length_dw++] =PACKET3 (PACKET3_EVENT_WRITE ,0 ); + ib->ptr[ib->length_dw++] =EVENT_TYPE (7 ) |EVENT_INDEX (4 );/* SGPR1 */ /* write the register state for the compute dispatch */ for (i =0 ; i <ARRAY_SIZE (sgpr1_init_regs); i +=2 ) { - ib.ptr[ib.length_dw++] =PACKET3 (PACKET3_SET_SH_REG ,1 ); - ib.ptr[ib.length_dw++] = sgpr1_init_regs[i] -PACKET3_SET_SH_REG_START ; - ib.ptr[ib.length_dw++] = sgpr1_init_regs[i +1 ]; + ib->ptr[ib->length_dw++] =PACKET3 (PACKET3_SET_SH_REG ,1 ); + ib->ptr[ib->length_dw++] = sgpr1_init_regs[i] -PACKET3_SET_SH_REG_START ; + ib->ptr[ib->length_dw++] = sgpr1_init_regs[i +1 ]; }/* write the shader start address: mmCOMPUTE_PGM_LO, mmCOMPUTE_PGM_HI */ - gpu_addr = (ib.gpu_addr + (u64 )sgpr_offset) >>8 ; - ib.ptr[ib.length_dw++] =PACKET3 (PACKET3_SET_SH_REG ,2 ); - ib.ptr[ib.length_dw++] = mmCOMPUTE_PGM_LO -PACKET3_SET_SH_REG_START ; - ib.ptr[ib.length_dw++] =lower_32_bits (gpu_addr); - ib.ptr[ib.length_dw++] =upper_32_bits (gpu_addr); + gpu_addr = (ib->gpu_addr + (u64 )sgpr_offset) >>8 ; + ib->ptr[ib->length_dw++] =PACKET3 (PACKET3_SET_SH_REG ,2 ); + ib->ptr[ib->length_dw++] = mmCOMPUTE_PGM_LO -PACKET3_SET_SH_REG_START ; + ib->ptr[ib->length_dw++] =lower_32_bits (gpu_addr); + ib->ptr[ib->length_dw++] =upper_32_bits (gpu_addr);/* write dispatch packet */ - ib.ptr[ib.length_dw++] =PACKET3 (PACKET3_DISPATCH_DIRECT ,3 ); - ib.ptr[ib.length_dw++] =8 ;/* x */ - ib.ptr[ib.length_dw++] =1 ;/* y */ - ib.ptr[ib.length_dw++] =1 ;/* z */ - ib.ptr[ib.length_dw++] = + ib->ptr[ib->length_dw++] =PACKET3 (PACKET3_DISPATCH_DIRECT ,3 ); + ib->ptr[ib->length_dw++] =8 ;/* x */ + ib->ptr[ib->length_dw++] =1 ;/* y */ + ib->ptr[ib->length_dw++] =1 ;/* z */ + ib->ptr[ib->length_dw++] =REG_SET_FIELD (0 ,COMPUTE_DISPATCH_INITIATOR ,COMPUTE_SHADER_EN ,1 );/* write CS partial flush packet */ - ib.ptr[ib.length_dw++] =PACKET3 (PACKET3_EVENT_WRITE ,0 ); - ib.ptr[ib.length_dw++] =EVENT_TYPE (7 ) |EVENT_INDEX (4 ); + ib->ptr[ib->length_dw++] =PACKET3 (PACKET3_EVENT_WRITE ,0 ); + ib->ptr[ib->length_dw++] =EVENT_TYPE (7 ) |EVENT_INDEX (4 );/* SGPR2 */ /* write the register state for the compute dispatch */ for (i =0 ; i <ARRAY_SIZE (sgpr2_init_regs); i +=2 ) { - ib.ptr[ib.length_dw++] =PACKET3 (PACKET3_SET_SH_REG ,1 ); - ib.ptr[ib.length_dw++] = sgpr2_init_regs[i] -PACKET3_SET_SH_REG_START ; - ib.ptr[ib.length_dw++] = sgpr2_init_regs[i +1 ]; + ib->ptr[ib->length_dw++] =PACKET3 (PACKET3_SET_SH_REG ,1 ); + ib->ptr[ib->length_dw++] = sgpr2_init_regs[i] -PACKET3_SET_SH_REG_START ; + ib->ptr[ib->length_dw++] = sgpr2_init_regs[i +1 ]; }/* write the shader start address: mmCOMPUTE_PGM_LO, mmCOMPUTE_PGM_HI */ - gpu_addr = (ib.gpu_addr + (u64 )sgpr_offset) >>8 ; - ib.ptr[ib.length_dw++] =PACKET3 (PACKET3_SET_SH_REG ,2 ); - ib.ptr[ib.length_dw++] = mmCOMPUTE_PGM_LO -PACKET3_SET_SH_REG_START ; - ib.ptr[ib.length_dw++] =lower_32_bits (gpu_addr); - ib.ptr[ib.length_dw++] =upper_32_bits (gpu_addr); + gpu_addr = (ib->gpu_addr + (u64 )sgpr_offset) >>8 ; + ib->ptr[ib->length_dw++] =PACKET3 (PACKET3_SET_SH_REG ,2 ); + ib->ptr[ib->length_dw++] = mmCOMPUTE_PGM_LO -PACKET3_SET_SH_REG_START ; + ib->ptr[ib->length_dw++] =lower_32_bits (gpu_addr); + ib->ptr[ib->length_dw++] =upper_32_bits (gpu_addr);/* write dispatch packet */ - ib.ptr[ib.length_dw++] =PACKET3 (PACKET3_DISPATCH_DIRECT ,3 ); - ib.ptr[ib.length_dw++] =8 ;/* x */ - ib.ptr[ib.length_dw++] =1 ;/* y */ - ib.ptr[ib.length_dw++] =1 ;/* z */ - ib.ptr[ib.length_dw++] = + ib->ptr[ib->length_dw++] =PACKET3 (PACKET3_DISPATCH_DIRECT ,3 ); + ib->ptr[ib->length_dw++] =8 ;/* x */ + ib->ptr[ib->length_dw++] =1 ;/* y */ + ib->ptr[ib->length_dw++] =1 ;/* z */ + ib->ptr[ib->length_dw++] =REG_SET_FIELD (0 ,COMPUTE_DISPATCH_INITIATOR ,COMPUTE_SHADER_EN ,1 );/* write CS partial flush packet */ - ib.ptr[ib.length_dw++] =PACKET3 (PACKET3_EVENT_WRITE ,0 ); - ib.ptr[ib.length_dw++] =EVENT_TYPE (7 ) |EVENT_INDEX (4 ); + ib->ptr[ib->length_dw++] =PACKET3 (PACKET3_EVENT_WRITE ,0 ); + ib->ptr[ib->length_dw++] =EVENT_TYPE (7 ) |EVENT_INDEX (4 );/* shedule the ib on the ring */ - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); + r =amdgpu_job_submit_direct (job, ring, &f);if (r) {drm_err (adev_to_drm (adev),"ib submit failed (%d).\n" , r); +amdgpu_job_free (job); goto fail; }@@ -1629,7 +1635,6 @@ static int gfx_v8_0_do_edc_gpr_workarounds(struct amdgpu_device *adev)RREG32 (sec_ded_counter_registers[i]); fail: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f);return r;drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +18
-14@@ -1224,9 +1224,9 @@ static int gfx_v9_0_ring_test_ring(struct amdgpu_ring *ring)static int gfx_v9_0_ring_test_ib (struct amdgpu_ring *ring,long timeout) {struct amdgpu_device *adev = ring->adev; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ; -unsigned index;uint64_t gpu_addr;uint32_t tmp;@@ -1238,22 +1238,26 @@ static int gfx_v9_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) gpu_addr = adev->wb.gpu_addr + (index *4 ); adev->wb.wb[index] =cpu_to_le32 (0xCAFEDEAD ); -memset (&ib,0 ,sizeof (ib)); - r =amdgpu_ib_get (adev,NULL ,20 ,AMDGPU_IB_POOL_DIRECT , &ib); + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,20 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_GFX_RING_TEST );if (r) goto err1; - ib.ptr[0 ] =PACKET3 (PACKET3_WRITE_DATA ,3 ); - ib.ptr[1 ] =WRITE_DATA_DST_SEL (5 ) |WR_CONFIRM ; - ib.ptr[2 ] =lower_32_bits (gpu_addr); - ib.ptr[3 ] =upper_32_bits (gpu_addr); - ib.ptr[4 ] =0xDEADBEEF ; - ib.length_dw =5 ; + ib = &job->ibs[0 ]; + ib->ptr[0 ] =PACKET3 (PACKET3_WRITE_DATA ,3 ); + ib->ptr[1 ] =WRITE_DATA_DST_SEL (5 ) |WR_CONFIRM ; + ib->ptr[2 ] =lower_32_bits (gpu_addr); + ib->ptr[3 ] =upper_32_bits (gpu_addr); + ib->ptr[4 ] =0xDEADBEEF ; + ib->length_dw =5 ; - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (r) + r =amdgpu_job_submit_direct (job, ring, &f); +if (r) { +amdgpu_job_free (job); goto err2; + } r =dma_fence_wait_timeout (f, false, timeout);if (r ==0 ) {@@ -1270,7 +1274,6 @@ static int gfx_v9_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) r = -EINVAL ; err2: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f); err1:amdgpu_device_wb_free (adev, index);@@ -4624,7 +4627,8 @@ static int gfx_v9_0_do_edc_gds_workarounds(struct amdgpu_device *adev)static int gfx_v9_0_do_edc_gpr_workarounds (struct amdgpu_device *adev) {struct amdgpu_ring *ring = &adev->gfx.compute_ring[0 ]; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ;int r, i;unsigned total_size, vgpr_offset, sgpr_offset;@@ -4670,9 +4674,9 @@ static int gfx_v9_0_do_edc_gpr_workarounds(struct amdgpu_device *adev) total_size +=sizeof (sgpr_init_compute_shader);
drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c static int gfx_v9_0_do_edc_gpr_workarounds(struct amdgpu_device *adev) · line 4682
Quoted 10 lines
drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +3
-3/* allocate an indirect buffer to put the commands in */ -memset (&ib,0 ,sizeof (ib)); - r =amdgpu_ib_get (adev,NULL , total_size, -AMDGPU_IB_POOL_DIRECT , &ib); + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL , total_size, +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_RUN_SHADER );if (r) {drm_err (adev_to_drm (adev),"failed to get ib (%d).\n" , r);return r;
Missing:
ib = &job->ibs[0];
fixed up locally.
Quoted 184 lines
drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +50
-50@@ -4680,102 +4684,103 @@ static int gfx_v9_0_do_edc_gpr_workarounds(struct amdgpu_device *adev)/* load the compute shaders */ for (i =0 ; i < vgpr_init_shader_size/sizeof (u32); i++) - ib.ptr[i + (vgpr_offset /4 )] = vgpr_init_shader_ptr[i]; + ib->ptr[i + (vgpr_offset /4 )] = vgpr_init_shader_ptr[i];for (i =0 ; i <ARRAY_SIZE (sgpr_init_compute_shader); i++) - ib.ptr[i + (sgpr_offset /4 )] = sgpr_init_compute_shader[i]; + ib->ptr[i + (sgpr_offset /4 )] = sgpr_init_compute_shader[i];/* init the ib length to 0 */ - ib.length_dw =0 ; + ib->length_dw =0 ;/* VGPR */ /* write the register state for the compute dispatch */ for (i =0 ; i < gpr_reg_size; i++) { - ib.ptr[ib.length_dw++] =PACKET3 (PACKET3_SET_SH_REG ,1 ); - ib.ptr[ib.length_dw++] =SOC15_REG_ENTRY_OFFSET (vgpr_init_regs_ptr[i]) + ib->ptr[ib->length_dw++] =PACKET3 (PACKET3_SET_SH_REG ,1 ); + ib->ptr[ib->length_dw++] =SOC15_REG_ENTRY_OFFSET (vgpr_init_regs_ptr[i]) -PACKET3_SET_SH_REG_START ; - ib.ptr[ib.length_dw++] = vgpr_init_regs_ptr[i].reg_value; + ib->ptr[ib->length_dw++] = vgpr_init_regs_ptr[i].reg_value; }/* write the shader start address: mmCOMPUTE_PGM_LO, mmCOMPUTE_PGM_HI */ - gpu_addr = (ib.gpu_addr + (u64 )vgpr_offset) >>8 ; - ib.ptr[ib.length_dw++] =PACKET3 (PACKET3_SET_SH_REG ,2 ); - ib.ptr[ib.length_dw++] =SOC15_REG_OFFSET (GC ,0 , mmCOMPUTE_PGM_LO) + gpu_addr = (ib->gpu_addr + (u64 )vgpr_offset) >>8 ; + ib->ptr[ib->length_dw++] =PACKET3 (PACKET3_SET_SH_REG ,2 ); + ib->ptr[ib->length_dw++] =SOC15_REG_OFFSET (GC ,0 , mmCOMPUTE_PGM_LO) -PACKET3_SET_SH_REG_START ; - ib.ptr[ib.length_dw++] =lower_32_bits (gpu_addr); - ib.ptr[ib.length_dw++] =upper_32_bits (gpu_addr); + ib->ptr[ib->length_dw++] =lower_32_bits (gpu_addr); + ib->ptr[ib->length_dw++] =upper_32_bits (gpu_addr);/* write dispatch packet */ - ib.ptr[ib.length_dw++] =PACKET3 (PACKET3_DISPATCH_DIRECT ,3 ); - ib.ptr[ib.length_dw++] = compute_dim_x *2 ;/* x */ - ib.ptr[ib.length_dw++] =1 ;/* y */ - ib.ptr[ib.length_dw++] =1 ;/* z */ - ib.ptr[ib.length_dw++] = + ib->ptr[ib->length_dw++] =PACKET3 (PACKET3_DISPATCH_DIRECT ,3 ); + ib->ptr[ib->length_dw++] = compute_dim_x *2 ;/* x */ + ib->ptr[ib->length_dw++] =1 ;/* y */ + ib->ptr[ib->length_dw++] =1 ;/* z */ + ib->ptr[ib->length_dw++] =REG_SET_FIELD (0 ,COMPUTE_DISPATCH_INITIATOR ,COMPUTE_SHADER_EN ,1 );/* write CS partial flush packet */ - ib.ptr[ib.length_dw++] =PACKET3 (PACKET3_EVENT_WRITE ,0 ); - ib.ptr[ib.length_dw++] =EVENT_TYPE (7 ) |EVENT_INDEX (4 ); + ib->ptr[ib->length_dw++] =PACKET3 (PACKET3_EVENT_WRITE ,0 ); + ib->ptr[ib->length_dw++] =EVENT_TYPE (7 ) |EVENT_INDEX (4 );/* SGPR1 */ /* write the register state for the compute dispatch */ for (i =0 ; i < gpr_reg_size; i++) { - ib.ptr[ib.length_dw++] =PACKET3 (PACKET3_SET_SH_REG ,1 ); - ib.ptr[ib.length_dw++] =SOC15_REG_ENTRY_OFFSET (sgpr1_init_regs[i]) + ib->ptr[ib->length_dw++] =PACKET3 (PACKET3_SET_SH_REG ,1 ); + ib->ptr[ib->length_dw++] =SOC15_REG_ENTRY_OFFSET (sgpr1_init_regs[i]) -PACKET3_SET_SH_REG_START ; - ib.ptr[ib.length_dw++] = sgpr1_init_regs[i].reg_value; + ib->ptr[ib->length_dw++] = sgpr1_init_regs[i].reg_value; }/* write the shader start address: mmCOMPUTE_PGM_LO, mmCOMPUTE_PGM_HI */ - gpu_addr = (ib.gpu_addr + (u64 )sgpr_offset) >>8 ; - ib.ptr[ib.length_dw++] =PACKET3 (PACKET3_SET_SH_REG ,2 ); - ib.ptr[ib.length_dw++] =SOC15_REG_OFFSET (GC ,0 , mmCOMPUTE_PGM_LO) + gpu_addr = (ib->gpu_addr + (u64 )sgpr_offset) >>8 ; + ib->ptr[ib->length_dw++] =PACKET3 (PACKET3_SET_SH_REG ,2 ); + ib->ptr[ib->length_dw++] =SOC15_REG_OFFSET (GC ,0 , mmCOMPUTE_PGM_LO) -PACKET3_SET_SH_REG_START ; - ib.ptr[ib.length_dw++] =lower_32_bits (gpu_addr); - ib.ptr[ib.length_dw++] =upper_32_bits (gpu_addr); + ib->ptr[ib->length_dw++] =lower_32_bits (gpu_addr); + ib->ptr[ib->length_dw++] =upper_32_bits (gpu_addr);/* write dispatch packet */ - ib.ptr[ib.length_dw++] =PACKET3 (PACKET3_DISPATCH_DIRECT ,3 ); - ib.ptr[ib.length_dw++] = compute_dim_x /2 * sgpr_work_group_size;/* x */ - ib.ptr[ib.length_dw++] =1 ;/* y */ - ib.ptr[ib.length_dw++] =1 ;/* z */ - ib.ptr[ib.length_dw++] = + ib->ptr[ib->length_dw++] =PACKET3 (PACKET3_DISPATCH_DIRECT ,3 ); + ib->ptr[ib->length_dw++] = compute_dim_x /2 * sgpr_work_group_size;/* x */ + ib->ptr[ib->length_dw++] =1 ;/* y */ + ib->ptr[ib->length_dw++] =1 ;/* z */ + ib->ptr[ib->length_dw++] =REG_SET_FIELD (0 ,COMPUTE_DISPATCH_INITIATOR ,COMPUTE_SHADER_EN ,1 );/* write CS partial flush packet */ - ib.ptr[ib.length_dw++] =PACKET3 (PACKET3_EVENT_WRITE ,0 ); - ib.ptr[ib.length_dw++] =EVENT_TYPE (7 ) |EVENT_INDEX (4 ); + ib->ptr[ib->length_dw++] =PACKET3 (PACKET3_EVENT_WRITE ,0 ); + ib->ptr[ib->length_dw++] =EVENT_TYPE (7 ) |EVENT_INDEX (4 );/* SGPR2 */ /* write the register state for the compute dispatch */ for (i =0 ; i < gpr_reg_size; i++) { - ib.ptr[ib.length_dw++] =PACKET3 (PACKET3_SET_SH_REG ,1 ); - ib.ptr[ib.length_dw++] =SOC15_REG_ENTRY_OFFSET (sgpr2_init_regs[i]) + ib->ptr[ib->length_dw++] =PACKET3 (PACKET3_SET_SH_REG ,1 ); + ib->ptr[ib->length_dw++] =SOC15_REG_ENTRY_OFFSET (sgpr2_init_regs[i]) -PACKET3_SET_SH_REG_START ; - ib.ptr[ib.length_dw++] = sgpr2_init_regs[i].reg_value; + ib->ptr[ib->length_dw++] = sgpr2_init_regs[i].reg_value; }/* write the shader start address: mmCOMPUTE_PGM_LO, mmCOMPUTE_PGM_HI */ - gpu_addr = (ib.gpu_addr + (u64 )sgpr_offset) >>8 ; - ib.ptr[ib.length_dw++] =PACKET3 (PACKET3_SET_SH_REG ,2 ); - ib.ptr[ib.length_dw++] =SOC15_REG_OFFSET (GC ,0 , mmCOMPUTE_PGM_LO) + gpu_addr = (ib->gpu_addr + (u64 )sgpr_offset) >>8 ; + ib->ptr[ib->length_dw++] =PACKET3 (PACKET3_SET_SH_REG ,2 ); + ib->ptr[ib->length_dw++] =SOC15_REG_OFFSET (GC ,0 , mmCOMPUTE_PGM_LO) -PACKET3_SET_SH_REG_START ; - ib.ptr[ib.length_dw++] =lower_32_bits (gpu_addr); - ib.ptr[ib.length_dw++] =upper_32_bits (gpu_addr); + ib->ptr[ib->length_dw++] =lower_32_bits (gpu_addr); + ib->ptr[ib->length_dw++] =upper_32_bits (gpu_addr);/* write dispatch packet */ - ib.ptr[ib.length_dw++] =PACKET3 (PACKET3_DISPATCH_DIRECT ,3 ); - ib.ptr[ib.length_dw++] = compute_dim_x /2 * sgpr_work_group_size;/* x */ - ib.ptr[ib.length_dw++] =1 ;/* y */ - ib.ptr[ib.length_dw++] =1 ;/* z */ - ib.ptr[ib.length_dw++] = + ib->ptr[ib->length_dw++] =PACKET3 (PACKET3_DISPATCH_DIRECT ,3 ); + ib->ptr[ib->length_dw++] = compute_dim_x /2 * sgpr_work_group_size;/* x */ + ib->ptr[ib->length_dw++] =1 ;/* y */ + ib->ptr[ib->length_dw++] =1 ;/* z */ + ib->ptr[ib->length_dw++] =REG_SET_FIELD (0 ,COMPUTE_DISPATCH_INITIATOR ,COMPUTE_SHADER_EN ,1 );/* write CS partial flush packet */ - ib.ptr[ib.length_dw++] =PACKET3 (PACKET3_EVENT_WRITE ,0 ); - ib.ptr[ib.length_dw++] =EVENT_TYPE (7 ) |EVENT_INDEX (4 ); + ib->ptr[ib->length_dw++] =PACKET3 (PACKET3_EVENT_WRITE ,0 ); + ib->ptr[ib->length_dw++] =EVENT_TYPE (7 ) |EVENT_INDEX (4 );/* shedule the ib on the ring */ - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); + r =amdgpu_job_submit_direct (job, ring, &f);if (r) {drm_err (adev_to_drm (adev),"ib schedule failed (%d).\n" , r); +amdgpu_job_free (job); goto fail; }@@ -4787,7 +4792,6 @@ static int gfx_v9_0_do_edc_gpr_workarounds(struct amdgpu_device *adev) } fail: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f);return r;drivers/gpu/drm/amd/amdgpu/gfx_v9_4_2.c +2
-1@@ -345,12 +345,13 @@ const struct soc15_reg_entry sgpr64_init_regs_aldebaran[] = {static int gfx_v9_4_2_run_shader (struct amdgpu_device *adev,struct amdgpu_ring *ring, -struct amdgpu_ib *ib,const u32 *shader_ptr,u32 shader_size,const struct soc15_reg_entry *init_regs,u32 regs_size,u32 compute_dim_x,u64 wb_gpu_addr,u32 pattern,struct dma_fence **fence_ptr) { +struct amdgpu_job *job; +struct amdgpu_ib *ib;int r, i;uint32_t total_size, shader_offset;u64 gpu_addr;@@ -360,10 +361,9 @@ static int gfx_v9_4_2_run_shader(struct amdgpu_device *adev, shader_offset = total_size; total_size +=ALIGN (shader_size,256 );
drivers/gpu/drm/amd/amdgpu/gfx_v9_4_2.c static int gfx_v9_4_2_run_shader(struct amdgpu_device *adev, · line 369
Quoted 10 lines
drivers/gpu/drm/amd/amdgpu/gfx_v9_4_2.c +3
-4-/* allocate an indirect buffer to put the commands in */ -memset (ib,0 ,sizeof (*ib)); - r =amdgpu_ib_get (adev,NULL , total_size, -AMDGPU_IB_POOL_DIRECT , ib); + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL , total_size, +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_RUN_SHADER );if (r) {dev_err (adev->dev,"failed to get ib (%d).\n" , r);return r;
Missing:
ib = &job->ibs[0];
fixed up locally.
Alex
Quoted 855 lines
drivers/gpu/drm/amd/amdgpu/gfx_v9_4_2.c +3
-13@@ -408,11 +408,11 @@ static int gfx_v9_4_2_run_shader(struct amdgpu_device *adev, ib->ptr[ib->length_dw++] =REG_SET_FIELD (0 ,COMPUTE_DISPATCH_INITIATOR ,COMPUTE_SHADER_EN ,1 ); -/* shedule the ib on the ring */ - r =amdgpu_ib_schedule (ring,1 , ib,NULL , fence_ptr); +/* schedule the ib on the ring */ + r =amdgpu_job_submit_direct (job, ring, fence_ptr);if (r) {dev_err (adev->dev,"ib submit failed (%d).\n" , r); -amdgpu_ib_free (ib,NULL ); +amdgpu_job_free (job); }return r; }@@ -493,7 +493,6 @@ static int gfx_v9_4_2_do_sgprs_init(struct amdgpu_device *adev)int wb_size = adev->gfx.config.max_shader_engines *CU_ID_MAX *SIMD_ID_MAX *WAVE_ID_MAX ;struct amdgpu_ib wb_ib; -struct amdgpu_ib disp_ibs[3 ];struct dma_fence *fences[3 ];u32 pattern[3 ] = {0x1 ,0x5 ,0xa };@@ -514,7 +513,6 @@ static int gfx_v9_4_2_do_sgprs_init(struct amdgpu_device *adev) r = gfx_v9_4_2_run_shader(adev, &adev->gfx.compute_ring[0], - &disp_ibs[0], sgpr112_init_compute_shader_aldebaran, sizeof(sgpr112_init_compute_shader_aldebaran), sgpr112_init_regs_aldebaran,@@ -539,7 +537,6 @@ static int gfx_v9_4_2_do_sgprs_init(struct amdgpu_device *adev) r = gfx_v9_4_2_run_shader(adev, &adev->gfx.compute_ring[1], - &disp_ibs[1], sgpr96_init_compute_shader_aldebaran, sizeof(sgpr96_init_compute_shader_aldebaran), sgpr96_init_regs_aldebaran,@@ -579,7 +576,6 @@ static int gfx_v9_4_2_do_sgprs_init(struct amdgpu_device *adev)memset (wb_ib.ptr,0 , (1 + wb_size) *sizeof (uint32_t )); r = gfx_v9_4_2_run_shader(adev, &adev->gfx.compute_ring[0], - &disp_ibs[2], sgpr64_init_compute_shader_aldebaran, sizeof(sgpr64_init_compute_shader_aldebaran), sgpr64_init_regs_aldebaran,@@ -611,13 +607,10 @@ static int gfx_v9_4_2_do_sgprs_init(struct amdgpu_device *adev) } disp2_failed: -amdgpu_ib_free (&disp_ibs[2 ],NULL );dma_fence_put (fences[2 ]); disp1_failed: -amdgpu_ib_free (&disp_ibs[1 ],NULL );dma_fence_put (fences[1 ]); disp0_failed: -amdgpu_ib_free (&disp_ibs[0 ],NULL );dma_fence_put (fences[0 ]); pro_end:amdgpu_ib_free (&wb_ib,NULL );@@ -637,7 +630,6 @@ static int gfx_v9_4_2_do_vgprs_init(struct amdgpu_device *adev)int wb_size = adev->gfx.config.max_shader_engines *CU_ID_MAX *SIMD_ID_MAX *WAVE_ID_MAX ;struct amdgpu_ib wb_ib; -struct amdgpu_ib disp_ib;struct dma_fence *fence;u32 pattern =0xa ;@@ -657,7 +649,6 @@ static int gfx_v9_4_2_do_vgprs_init(struct amdgpu_device *adev) r = gfx_v9_4_2_run_shader(adev, &adev->gfx.compute_ring[0], - &disp_ib, vgpr_init_compute_shader_aldebaran, sizeof(vgpr_init_compute_shader_aldebaran), vgpr_init_regs_aldebaran,@@ -687,7 +678,6 @@ static int gfx_v9_4_2_do_vgprs_init(struct amdgpu_device *adev) } disp_failed: -amdgpu_ib_free (&disp_ib,NULL );dma_fence_put (fence); pro_end:amdgpu_ib_free (&wb_ib,NULL );drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c +16
-13@@ -451,9 +451,9 @@ static int gfx_v9_4_3_ring_test_ring(struct amdgpu_ring *ring)static int gfx_v9_4_3_ring_test_ib (struct amdgpu_ring *ring,long timeout) {struct amdgpu_device *adev = ring->adev; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ; -unsigned index;uint64_t gpu_addr;uint32_t tmp;@@ -465,22 +465,26 @@ static int gfx_v9_4_3_ring_test_ib(struct amdgpu_ring *ring, long timeout) gpu_addr = adev->wb.gpu_addr + (index *4 ); adev->wb.wb[index] =cpu_to_le32 (0xCAFEDEAD ); -memset (&ib,0 ,sizeof (ib)); - r =amdgpu_ib_get (adev,NULL ,20 ,AMDGPU_IB_POOL_DIRECT , &ib); + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,20 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_GFX_RING_TEST );if (r) goto err1; - ib.ptr[0 ] =PACKET3 (PACKET3_WRITE_DATA ,3 ); - ib.ptr[1 ] =WRITE_DATA_DST_SEL (5 ) |WR_CONFIRM ; - ib.ptr[2 ] =lower_32_bits (gpu_addr); - ib.ptr[3 ] =upper_32_bits (gpu_addr); - ib.ptr[4 ] =0xDEADBEEF ; - ib.length_dw =5 ; + ib = &job->ibs[0 ]; + ib->ptr[0 ] =PACKET3 (PACKET3_WRITE_DATA ,3 ); + ib->ptr[1 ] =WRITE_DATA_DST_SEL (5 ) |WR_CONFIRM ; + ib->ptr[2 ] =lower_32_bits (gpu_addr); + ib->ptr[3 ] =upper_32_bits (gpu_addr); + ib->ptr[4 ] =0xDEADBEEF ; + ib->length_dw =5 ; - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (r) + r =amdgpu_job_submit_direct (job, ring, &f); +if (r) { +amdgpu_job_free (job); goto err2; + } r =dma_fence_wait_timeout (f, false, timeout);if (r ==0 ) {@@ -497,7 +501,6 @@ static int gfx_v9_4_3_ring_test_ib(struct amdgpu_ring *ring, long timeout) r = -EINVAL ; err2: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f); err1:amdgpu_device_wb_free (adev, index);drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c +21
-17@@ -584,7 +584,8 @@ static int sdma_v2_4_ring_test_ring(struct amdgpu_ring *ring)static int sdma_v2_4_ring_test_ib (struct amdgpu_ring *ring,long timeout) {struct amdgpu_device *adev = ring->adev; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ;unsigned index;u32 tmp =0 ;@@ -598,26 +599,30 @@ static int sdma_v2_4_ring_test_ib(struct amdgpu_ring *ring, long timeout) gpu_addr = adev->wb.gpu_addr + (index *4 ); tmp =0xCAFEDEAD ; adev->wb.wb[index] =cpu_to_le32 (tmp); -memset (&ib,0 ,sizeof (ib)); - r =amdgpu_ib_get (adev,NULL ,256 , -AMDGPU_IB_POOL_DIRECT , &ib); + + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,256 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_SDMA_RING_TEST );if (r) goto err0; - ib.ptr[0 ] =SDMA_PKT_HEADER_OP (SDMA_OP_WRITE ) | + ib = &job->ibs[0 ]; + ib->ptr[0 ] =SDMA_PKT_HEADER_OP (SDMA_OP_WRITE ) |SDMA_PKT_HEADER_SUB_OP (SDMA_SUBOP_WRITE_LINEAR ); - ib.ptr[1 ] =lower_32_bits (gpu_addr); - ib.ptr[2 ] =upper_32_bits (gpu_addr); - ib.ptr[3 ] =SDMA_PKT_WRITE_UNTILED_DW_3_COUNT (1 ); - ib.ptr[4 ] =0xDEADBEEF ; - ib.ptr[5 ] =SDMA_PKT_HEADER_OP (SDMA_OP_NOP ); - ib.ptr[6 ] =SDMA_PKT_HEADER_OP (SDMA_OP_NOP ); - ib.ptr[7 ] =SDMA_PKT_HEADER_OP (SDMA_OP_NOP ); - ib.length_dw =8 ; - - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (r) + ib->ptr[1 ] =lower_32_bits (gpu_addr); + ib->ptr[2 ] =upper_32_bits (gpu_addr); + ib->ptr[3 ] =SDMA_PKT_WRITE_UNTILED_DW_3_COUNT (1 ); + ib->ptr[4 ] =0xDEADBEEF ; + ib->ptr[5 ] =SDMA_PKT_HEADER_OP (SDMA_OP_NOP ); + ib->ptr[6 ] =SDMA_PKT_HEADER_OP (SDMA_OP_NOP ); + ib->ptr[7 ] =SDMA_PKT_HEADER_OP (SDMA_OP_NOP ); + ib->length_dw =8 ; + + r =amdgpu_job_submit_direct (job, ring, &f); +if (r) { +amdgpu_job_free (job); goto err1; + } r =dma_fence_wait_timeout (f, false, timeout);if (r ==0 ) {@@ -633,7 +638,6 @@ static int sdma_v2_4_ring_test_ib(struct amdgpu_ring *ring, long timeout) r = -EINVAL ; err1: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f); err0:amdgpu_device_wb_free (adev, index);drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c +21
-17@@ -858,7 +858,8 @@ static int sdma_v3_0_ring_test_ring(struct amdgpu_ring *ring)static int sdma_v3_0_ring_test_ib (struct amdgpu_ring *ring,long timeout) {struct amdgpu_device *adev = ring->adev; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ;unsigned index;u32 tmp =0 ;@@ -872,26 +873,30 @@ static int sdma_v3_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) gpu_addr = adev->wb.gpu_addr + (index *4 ); tmp =0xCAFEDEAD ; adev->wb.wb[index] =cpu_to_le32 (tmp); -memset (&ib,0 ,sizeof (ib)); - r =amdgpu_ib_get (adev,NULL ,256 , -AMDGPU_IB_POOL_DIRECT , &ib); + + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,256 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_SDMA_RING_TEST );if (r) goto err0; - ib.ptr[0 ] =SDMA_PKT_HEADER_OP (SDMA_OP_WRITE ) | + ib = &job->ibs[0 ]; + ib->ptr[0 ] =SDMA_PKT_HEADER_OP (SDMA_OP_WRITE ) |SDMA_PKT_HEADER_SUB_OP (SDMA_SUBOP_WRITE_LINEAR ); - ib.ptr[1 ] =lower_32_bits (gpu_addr); - ib.ptr[2 ] =upper_32_bits (gpu_addr); - ib.ptr[3 ] =SDMA_PKT_WRITE_UNTILED_DW_3_COUNT (1 ); - ib.ptr[4 ] =0xDEADBEEF ; - ib.ptr[5 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.ptr[6 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.ptr[7 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.length_dw =8 ; - - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (r) + ib->ptr[1 ] =lower_32_bits (gpu_addr); + ib->ptr[2 ] =upper_32_bits (gpu_addr); + ib->ptr[3 ] =SDMA_PKT_WRITE_UNTILED_DW_3_COUNT (1 ); + ib->ptr[4 ] =0xDEADBEEF ; + ib->ptr[5 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->ptr[6 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->ptr[7 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->length_dw =8 ; + + r =amdgpu_job_submit_direct (job, ring, &f); +if (r) { +amdgpu_job_free (job); goto err1; + } r =dma_fence_wait_timeout (f, false, timeout);if (r ==0 ) {@@ -906,7 +911,6 @@ static int sdma_v3_0_ring_test_ib(struct amdgpu_ring *ring, long timeout)else r = -EINVAL ; err1: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f); err0:amdgpu_device_wb_free (adev, index);drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c +21
-17@@ -1516,7 +1516,8 @@ static int sdma_v4_0_ring_test_ring(struct amdgpu_ring *ring)static int sdma_v4_0_ring_test_ib (struct amdgpu_ring *ring,long timeout) {struct amdgpu_device *adev = ring->adev; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ;unsigned index;long r;@@ -1530,26 +1531,30 @@ static int sdma_v4_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) gpu_addr = adev->wb.gpu_addr + (index *4 ); tmp =0xCAFEDEAD ; adev->wb.wb[index] =cpu_to_le32 (tmp); -memset (&ib,0 ,sizeof (ib)); - r =amdgpu_ib_get (adev,NULL ,256 , -AMDGPU_IB_POOL_DIRECT , &ib); + + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,256 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_SDMA_RING_TEST );if (r) goto err0; - ib.ptr[0 ] =SDMA_PKT_HEADER_OP (SDMA_OP_WRITE ) | + ib = &job->ibs[0 ]; + ib->ptr[0 ] =SDMA_PKT_HEADER_OP (SDMA_OP_WRITE ) |SDMA_PKT_HEADER_SUB_OP (SDMA_SUBOP_WRITE_LINEAR ); - ib.ptr[1 ] =lower_32_bits (gpu_addr); - ib.ptr[2 ] =upper_32_bits (gpu_addr); - ib.ptr[3 ] =SDMA_PKT_WRITE_UNTILED_DW_3_COUNT (0 ); - ib.ptr[4 ] =0xDEADBEEF ; - ib.ptr[5 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.ptr[6 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.ptr[7 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.length_dw =8 ; - - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (r) + ib->ptr[1 ] =lower_32_bits (gpu_addr); + ib->ptr[2 ] =upper_32_bits (gpu_addr); + ib->ptr[3 ] =SDMA_PKT_WRITE_UNTILED_DW_3_COUNT (0 ); + ib->ptr[4 ] =0xDEADBEEF ; + ib->ptr[5 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->ptr[6 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->ptr[7 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->length_dw =8 ; + + r =amdgpu_job_submit_direct (job, ring, &f); +if (r) { +amdgpu_job_free (job); goto err1; + } r =dma_fence_wait_timeout (f, false, timeout);if (r ==0 ) {@@ -1565,7 +1570,6 @@ static int sdma_v4_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) r = -EINVAL ; err1: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f); err0:amdgpu_device_wb_free (adev, index);drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c +21
-17@@ -1112,7 +1112,8 @@ static int sdma_v4_4_2_ring_test_ring(struct amdgpu_ring *ring)static int sdma_v4_4_2_ring_test_ib (struct amdgpu_ring *ring,long timeout) {struct amdgpu_device *adev = ring->adev; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ;unsigned index;long r;@@ -1126,26 +1127,30 @@ static int sdma_v4_4_2_ring_test_ib(struct amdgpu_ring *ring, long timeout) gpu_addr = adev->wb.gpu_addr + (index *4 ); tmp =0xCAFEDEAD ; adev->wb.wb[index] =cpu_to_le32 (tmp); -memset (&ib,0 ,sizeof (ib)); - r =amdgpu_ib_get (adev,NULL ,256 , -AMDGPU_IB_POOL_DIRECT , &ib); + + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,256 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_SDMA_RING_TEST );if (r) goto err0; - ib.ptr[0 ] =SDMA_PKT_HEADER_OP (SDMA_OP_WRITE ) | + ib = &job->ibs[0 ]; + ib->ptr[0 ] =SDMA_PKT_HEADER_OP (SDMA_OP_WRITE ) |SDMA_PKT_HEADER_SUB_OP (SDMA_SUBOP_WRITE_LINEAR ); - ib.ptr[1 ] =lower_32_bits (gpu_addr); - ib.ptr[2 ] =upper_32_bits (gpu_addr); - ib.ptr[3 ] =SDMA_PKT_WRITE_UNTILED_DW_3_COUNT (0 ); - ib.ptr[4 ] =0xDEADBEEF ; - ib.ptr[5 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.ptr[6 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.ptr[7 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.length_dw =8 ; - - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (r) + ib->ptr[1 ] =lower_32_bits (gpu_addr); + ib->ptr[2 ] =upper_32_bits (gpu_addr); + ib->ptr[3 ] =SDMA_PKT_WRITE_UNTILED_DW_3_COUNT (0 ); + ib->ptr[4 ] =0xDEADBEEF ; + ib->ptr[5 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->ptr[6 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->ptr[7 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->length_dw =8 ; + + r =amdgpu_job_submit_direct (job, ring, &f); +if (r) { +amdgpu_job_free (job); goto err1; + } r =dma_fence_wait_timeout (f, false, timeout);if (r ==0 ) {@@ -1161,7 +1166,6 @@ static int sdma_v4_4_2_ring_test_ib(struct amdgpu_ring *ring, long timeout) r = -EINVAL ; err1: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f); err0:amdgpu_device_wb_free (adev, index);drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c +20
-17@@ -1074,7 +1074,8 @@ static int sdma_v5_0_ring_test_ring(struct amdgpu_ring *ring)static int sdma_v5_0_ring_test_ib (struct amdgpu_ring *ring,long timeout) {struct amdgpu_device *adev = ring->adev; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ;unsigned index;long r;@@ -1082,7 +1083,6 @@ static int sdma_v5_0_ring_test_ib(struct amdgpu_ring *ring, long timeout)u64 gpu_addr; tmp =0xCAFEDEAD ; -memset (&ib,0 ,sizeof (ib)); r =amdgpu_device_wb_get (adev, &index);if (r) {@@ -1093,27 +1093,31 @@ static int sdma_v5_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) gpu_addr = adev->wb.gpu_addr + (index *4 ); adev->wb.wb[index] =cpu_to_le32 (tmp); - r =amdgpu_ib_get (adev,NULL ,256 , -AMDGPU_IB_POOL_DIRECT , &ib); + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,256 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_SDMA_RING_TEST );if (r) {drm_err (adev_to_drm (adev),"failed to get ib (%ld).\n" , r); goto err0; } - ib.ptr[0 ] =SDMA_PKT_HEADER_OP (SDMA_OP_WRITE ) | + ib = &job->ibs[0 ]; + ib->ptr[0 ] =SDMA_PKT_HEADER_OP (SDMA_OP_WRITE ) |SDMA_PKT_HEADER_SUB_OP (SDMA_SUBOP_WRITE_LINEAR ); - ib.ptr[1 ] =lower_32_bits (gpu_addr); - ib.ptr[2 ] =upper_32_bits (gpu_addr); - ib.ptr[3 ] =SDMA_PKT_WRITE_UNTILED_DW_3_COUNT (0 ); - ib.ptr[4 ] =0xDEADBEEF ; - ib.ptr[5 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.ptr[6 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.ptr[7 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.length_dw =8 ; - - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (r) + ib->ptr[1 ] =lower_32_bits (gpu_addr); + ib->ptr[2 ] =upper_32_bits (gpu_addr); + ib->ptr[3 ] =SDMA_PKT_WRITE_UNTILED_DW_3_COUNT (0 ); + ib->ptr[4 ] =0xDEADBEEF ; + ib->ptr[5 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->ptr[6 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->ptr[7 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->length_dw =8 ; + + r =amdgpu_job_submit_direct (job, ring, &f); +if (r) { +amdgpu_job_free (job); goto err1; + } r =dma_fence_wait_timeout (f, false, timeout);if (r ==0 ) {@@ -1133,7 +1137,6 @@ static int sdma_v5_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) r = -EINVAL ; err1: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f); err0:amdgpu_device_wb_free (adev, index);drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c +20
-16@@ -974,7 +974,8 @@ static int sdma_v5_2_ring_test_ring(struct amdgpu_ring *ring)static int sdma_v5_2_ring_test_ib (struct amdgpu_ring *ring,long timeout) {struct amdgpu_device *adev = ring->adev; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ;unsigned index;long r;@@ -982,7 +983,6 @@ static int sdma_v5_2_ring_test_ib(struct amdgpu_ring *ring, long timeout)u64 gpu_addr; tmp =0xCAFEDEAD ; -memset (&ib,0 ,sizeof (ib)); r =amdgpu_device_wb_get (adev, &index);if (r) {@@ -993,26 +993,31 @@ static int sdma_v5_2_ring_test_ib(struct amdgpu_ring *ring, long timeout) gpu_addr = adev->wb.gpu_addr + (index *4 ); adev->wb.wb[index] =cpu_to_le32 (tmp); - r =amdgpu_ib_get (adev,NULL ,256 ,AMDGPU_IB_POOL_DIRECT , &ib); + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,256 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_SDMA_RING_TEST );if (r) {drm_err (adev_to_drm (adev),"failed to get ib (%ld).\n" , r); goto err0; } - ib.ptr[0 ] =SDMA_PKT_HEADER_OP (SDMA_OP_WRITE ) | + ib = &job->ibs[0 ]; + ib->ptr[0 ] =SDMA_PKT_HEADER_OP (SDMA_OP_WRITE ) |SDMA_PKT_HEADER_SUB_OP (SDMA_SUBOP_WRITE_LINEAR ); - ib.ptr[1 ] =lower_32_bits (gpu_addr); - ib.ptr[2 ] =upper_32_bits (gpu_addr); - ib.ptr[3 ] =SDMA_PKT_WRITE_UNTILED_DW_3_COUNT (0 ); - ib.ptr[4 ] =0xDEADBEEF ; - ib.ptr[5 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.ptr[6 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.ptr[7 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.length_dw =8 ; - - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (r) + ib->ptr[1 ] =lower_32_bits (gpu_addr); + ib->ptr[2 ] =upper_32_bits (gpu_addr); + ib->ptr[3 ] =SDMA_PKT_WRITE_UNTILED_DW_3_COUNT (0 ); + ib->ptr[4 ] =0xDEADBEEF ; + ib->ptr[5 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->ptr[6 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->ptr[7 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->length_dw =8 ; + + r =amdgpu_job_submit_direct (job, ring, &f); +if (r) { +amdgpu_job_free (job); goto err1; + } r =dma_fence_wait_timeout (f, false, timeout);if (r ==0 ) {@@ -1032,7 +1037,6 @@ static int sdma_v5_2_ring_test_ib(struct amdgpu_ring *ring, long timeout) r = -EINVAL ; err1: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f); err0:amdgpu_device_wb_free (adev, index);drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c +20
-16@@ -981,7 +981,8 @@ static int sdma_v6_0_ring_test_ring(struct amdgpu_ring *ring)static int sdma_v6_0_ring_test_ib (struct amdgpu_ring *ring,long timeout) {struct amdgpu_device *adev = ring->adev; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ;unsigned index;long r;@@ -989,7 +990,6 @@ static int sdma_v6_0_ring_test_ib(struct amdgpu_ring *ring, long timeout)u64 gpu_addr; tmp =0xCAFEDEAD ; -memset (&ib,0 ,sizeof (ib)); r =amdgpu_device_wb_get (adev, &index);if (r) {@@ -1000,26 +1000,31 @@ static int sdma_v6_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) gpu_addr = adev->wb.gpu_addr + (index *4 ); adev->wb.wb[index] =cpu_to_le32 (tmp); - r =amdgpu_ib_get (adev,NULL ,256 ,AMDGPU_IB_POOL_DIRECT , &ib); + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,256 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_SDMA_RING_TEST );if (r) {drm_err (adev_to_drm (adev),"failed to get ib (%ld).\n" , r); goto err0; } - ib.ptr[0 ] =SDMA_PKT_COPY_LINEAR_HEADER_OP (SDMA_OP_WRITE ) | + ib = &job->ibs[0 ]; + ib->ptr[0 ] =SDMA_PKT_COPY_LINEAR_HEADER_OP (SDMA_OP_WRITE ) |SDMA_PKT_COPY_LINEAR_HEADER_SUB_OP (SDMA_SUBOP_WRITE_LINEAR ); - ib.ptr[1 ] =lower_32_bits (gpu_addr); - ib.ptr[2 ] =upper_32_bits (gpu_addr); - ib.ptr[3 ] =SDMA_PKT_WRITE_UNTILED_DW_3_COUNT (0 ); - ib.ptr[4 ] =0xDEADBEEF ; - ib.ptr[5 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.ptr[6 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.ptr[7 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.length_dw =8 ; - - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (r) + ib->ptr[1 ] =lower_32_bits (gpu_addr); + ib->ptr[2 ] =upper_32_bits (gpu_addr); + ib->ptr[3 ] =SDMA_PKT_WRITE_UNTILED_DW_3_COUNT (0 ); + ib->ptr[4 ] =0xDEADBEEF ; + ib->ptr[5 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->ptr[6 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->ptr[7 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->length_dw =8 ; + + r =amdgpu_job_submit_direct (job, ring, &f); +if (r) { +amdgpu_job_free (job); goto err1; + } r =dma_fence_wait_timeout (f, false, timeout);if (r ==0 ) {@@ -1039,7 +1044,6 @@ static int sdma_v6_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) r = -EINVAL ; err1: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f); err0:amdgpu_device_wb_free (adev, index);drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c +20
-16@@ -997,7 +997,8 @@ static int sdma_v7_0_ring_test_ring(struct amdgpu_ring *ring)static int sdma_v7_0_ring_test_ib (struct amdgpu_ring *ring,long timeout) {struct amdgpu_device *adev = ring->adev; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ;unsigned index;long r;@@ -1005,7 +1006,6 @@ static int sdma_v7_0_ring_test_ib(struct amdgpu_ring *ring, long timeout)u64 gpu_addr; tmp =0xCAFEDEAD ; -memset (&ib,0 ,sizeof (ib)); r =amdgpu_device_wb_get (adev, &index);if (r) {@@ -1016,26 +1016,31 @@ static int sdma_v7_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) gpu_addr = adev->wb.gpu_addr + (index *4 ); adev->wb.wb[index] =cpu_to_le32 (tmp); - r =amdgpu_ib_get (adev,NULL ,256 ,AMDGPU_IB_POOL_DIRECT , &ib); + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,256 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_SDMA_RING_TEST );if (r) {drm_err (adev_to_drm (adev),"failed to get ib (%ld).\n" , r); goto err0; } - ib.ptr[0 ] =SDMA_PKT_COPY_LINEAR_HEADER_OP (SDMA_OP_WRITE ) | + ib = &job->ibs[0 ]; + ib->ptr[0 ] =SDMA_PKT_COPY_LINEAR_HEADER_OP (SDMA_OP_WRITE ) |SDMA_PKT_COPY_LINEAR_HEADER_SUB_OP (SDMA_SUBOP_WRITE_LINEAR ); - ib.ptr[1 ] =lower_32_bits (gpu_addr); - ib.ptr[2 ] =upper_32_bits (gpu_addr); - ib.ptr[3 ] =SDMA_PKT_WRITE_UNTILED_DW_3_COUNT (0 ); - ib.ptr[4 ] =0xDEADBEEF ; - ib.ptr[5 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.ptr[6 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.ptr[7 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.length_dw =8 ; - - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (r) + ib->ptr[1 ] =lower_32_bits (gpu_addr); + ib->ptr[2 ] =upper_32_bits (gpu_addr); + ib->ptr[3 ] =SDMA_PKT_WRITE_UNTILED_DW_3_COUNT (0 ); + ib->ptr[4 ] =0xDEADBEEF ; + ib->ptr[5 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->ptr[6 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->ptr[7 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->length_dw =8 ; + + r =amdgpu_job_submit_direct (job, ring, &f); +if (r) { +amdgpu_job_free (job); goto err1; + } r =dma_fence_wait_timeout (f, false, timeout);if (r ==0 ) {@@ -1055,7 +1060,6 @@ static int sdma_v7_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) r = -EINVAL ; err1: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f); err0:amdgpu_device_wb_free (adev, index);drivers/gpu/drm/amd/amdgpu/sdma_v7_1.c +20
-16@@ -987,7 +987,8 @@ static int sdma_v7_1_ring_test_ring(struct amdgpu_ring *ring)static int sdma_v7_1_ring_test_ib (struct amdgpu_ring *ring,long timeout) {struct amdgpu_device *adev = ring->adev; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ;unsigned index;long r;@@ -995,7 +996,6 @@ static int sdma_v7_1_ring_test_ib(struct amdgpu_ring *ring, long timeout)u64 gpu_addr; tmp =0xCAFEDEAD ; -memset (&ib,0 ,sizeof (ib)); r =amdgpu_device_wb_get (adev, &index);if (r) {@@ -1006,26 +1006,31 @@ static int sdma_v7_1_ring_test_ib(struct amdgpu_ring *ring, long timeout) gpu_addr = adev->wb.gpu_addr + (index *4 ); adev->wb.wb[index] =cpu_to_le32 (tmp); - r =amdgpu_ib_get (adev,NULL ,256 ,AMDGPU_IB_POOL_DIRECT , &ib); + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,256 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_SDMA_RING_TEST );if (r) {DRM_ERROR ("amdgpu: failed to get ib (%ld).\n" , r); goto err0; } - ib.ptr[0 ] =SDMA_PKT_COPY_LINEAR_HEADER_OP (SDMA_OP_WRITE ) | + ib = &job->ibs[0 ]; + ib->ptr[0 ] =SDMA_PKT_COPY_LINEAR_HEADER_OP (SDMA_OP_WRITE ) |SDMA_PKT_COPY_LINEAR_HEADER_SUB_OP (SDMA_SUBOP_WRITE_LINEAR ); - ib.ptr[1 ] =lower_32_bits (gpu_addr); - ib.ptr[2 ] =upper_32_bits (gpu_addr); - ib.ptr[3 ] =SDMA_PKT_WRITE_UNTILED_DW_3_COUNT (0 ); - ib.ptr[4 ] =0xDEADBEEF ; - ib.ptr[5 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.ptr[6 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.ptr[7 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.length_dw =8 ; - - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (r) + ib->ptr[1 ] =lower_32_bits (gpu_addr); + ib->ptr[2 ] =upper_32_bits (gpu_addr); + ib->ptr[3 ] =SDMA_PKT_WRITE_UNTILED_DW_3_COUNT (0 ); + ib->ptr[4 ] =0xDEADBEEF ; + ib->ptr[5 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->ptr[6 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->ptr[7 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->length_dw =8 ; + + r =amdgpu_job_submit_direct (job, ring, &f); +if (r) { +amdgpu_job_free (job); goto err1; + } r =dma_fence_wait_timeout (f, false, timeout);if (r ==0 ) {@@ -1045,7 +1050,6 @@ static int sdma_v7_1_ring_test_ib(struct amdgpu_ring *ring, long timeout) r = -EINVAL ; err1: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f); err0:amdgpu_device_wb_free (adev, index);drivers/gpu/drm/amd/amdgpu/si_dma.c +17
-13@@ -259,7 +259,8 @@ static int si_dma_ring_test_ring(struct amdgpu_ring *ring)static int si_dma_ring_test_ib (struct amdgpu_ring *ring,long timeout) {struct amdgpu_device *adev = ring->adev; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ;unsigned index;u32 tmp =0 ;@@ -273,20 +274,25 @@ static int si_dma_ring_test_ib(struct amdgpu_ring *ring, long timeout) gpu_addr = adev->wb.gpu_addr + (index *4 ); tmp =0xCAFEDEAD ; adev->wb.wb[index] =cpu_to_le32 (tmp); -memset (&ib,0 ,sizeof (ib)); - r =amdgpu_ib_get (adev,NULL ,256 , -AMDGPU_IB_POOL_DIRECT , &ib); + + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,256 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_SDMA_RING_TEST );if (r) goto err0; - ib.ptr[0 ] =DMA_PACKET (DMA_PACKET_WRITE ,0 ,0 ,0 ,1 ); - ib.ptr[1 ] =lower_32_bits (gpu_addr); - ib.ptr[2 ] =upper_32_bits (gpu_addr) &0xff ; - ib.ptr[3 ] =0xDEADBEEF ; - ib.length_dw =4 ; - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (r) + ib = &job->ibs[0 ]; + ib->ptr[0 ] =DMA_PACKET (DMA_PACKET_WRITE ,0 ,0 ,0 ,1 ); + ib->ptr[1 ] =lower_32_bits (gpu_addr); + ib->ptr[2 ] =upper_32_bits (gpu_addr) &0xff ; + ib->ptr[3 ] =0xDEADBEEF ; + ib->length_dw =4 ; + + r =amdgpu_job_submit_direct (job, ring, &f); +if (r) { +amdgpu_job_free (job); goto err1; + } r =dma_fence_wait_timeout (f, false, timeout);if (r ==0 ) {@@ -302,7 +308,6 @@ static int si_dma_ring_test_ib(struct amdgpu_ring *ring, long timeout) r = -EINVAL ; err1: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f); err0:amdgpu_device_wb_free (adev, index); --2.52.0
Re: [PATCH 03/12] drm/amdgpu: switch all IPs to using job for IBs
In reply to Alex DeucherLe 30/01/2026 à 18:30, Alex Deucher a écrit :
Quoted 73 lines
Switch to using a job structure for IBs.
Acked-by Christian König <[email protected]>Signed-off-by Alex Deucher <[email protected]>--- drivers/gpu/drm/amd/amdgpu/amdgpu_vpe.c | 37 +++--- drivers/gpu/drm/amd/amdgpu/cik_sdma.c | 31 ++--- drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c | 29 ++--- drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c | 29 ++--- drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c | 29 ++--- drivers/gpu/drm/amd/amdgpu/gfx_v12_1.c | 29 ++--- drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c | 24 ++-- drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c | 25 ++-- drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c | 139 ++++++++++++----------- drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c | 138 +++++++++++----------- drivers/gpu/drm/amd/amdgpu/gfx_v9_4_2.c | 26 ++--- drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c | 29 ++--- drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c | 38 ++++--- drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c | 38 ++++--- drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c | 38 ++++--- drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c | 38 ++++--- drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c | 37 +++--- drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c | 36 +++--- drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c | 36 +++--- drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c | 36 +++--- drivers/gpu/drm/amd/amdgpu/sdma_v7_1.c | 36 +++--- drivers/gpu/drm/amd/amdgpu/si_dma.c | 29 +++-- 22 files changed, 500 insertions(+), 427 deletions(-)drivers/gpu/drm/amd/amdgpu/amdgpu_vpe.c +12
-15@@ -817,7 +817,8 @@ static int vpe_ring_test_ib(struct amdgpu_ring *ring, long timeout) {struct amdgpu_device *adev = ring->adev;const uint32_t test_pattern =0xdeadbeef ; -struct amdgpu_ib ib = {}; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ;uint32_t index;uint64_t wb_addr;@@ -832,23 +833,28 @@ static int vpe_ring_test_ib(struct amdgpu_ring *ring, long timeout) adev->wb.wb[index] =0 ; wb_addr = adev->wb.gpu_addr + (index *4 ); - ret =amdgpu_ib_get (adev,NULL ,256 ,AMDGPU_IB_POOL_DIRECT , &ib); + ret =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,256 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_VPE_RING_TEST );if (ret) goto err0; - - ib.ptr[0 ] =VPE_CMD_HEADER (VPE_CMD_OPCODE_FENCE ,0 ); - ib.ptr[1 ] =lower_32_bits (wb_addr); - ib.ptr[2 ] =upper_32_bits (wb_addr); - ib.ptr[3 ] = test_pattern; - ib.ptr[4 ] =VPE_CMD_HEADER (VPE_CMD_OPCODE_NOP ,0 ); - ib.ptr[5 ] =VPE_CMD_HEADER (VPE_CMD_OPCODE_NOP ,0 ); - ib.ptr[6 ] =VPE_CMD_HEADER (VPE_CMD_OPCODE_NOP ,0 ); - ib.ptr[7 ] =VPE_CMD_HEADER (VPE_CMD_OPCODE_NOP ,0 ); - ib.length_dw =8 ; - - ret =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (ret) + ib = &job->ibs[0 ]; + + ib->ptr[0 ] =VPE_CMD_HEADER (VPE_CMD_OPCODE_FENCE ,0 ); + ib->ptr[1 ] =lower_32_bits (wb_addr); + ib->ptr[2 ] =upper_32_bits (wb_addr); + ib->ptr[3 ] = test_pattern; + ib->ptr[4 ] =VPE_CMD_HEADER (VPE_CMD_OPCODE_NOP ,0 );
drivers/gpu/drm/amd/amdgpu/amdgpu_vpe.c static int vpe_ring_test_ib(struct amdgpu_ring *ring, long timeout) · line 857
Quoted 10 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_vpe.c +9
-0+ ib->ptr[5 ] =VPE_CMD_HEADER (VPE_CMD_OPCODE_NOP ,0 ); + ib->ptr[6 ] =VPE_CMD_HEADER (VPE_CMD_OPCODE_NOP ,0 ); + ib->ptr[7 ] =VPE_CMD_HEADER (VPE_CMD_OPCODE_NOP ,0 ); + ib->length_dw =8 ; + + ret =amdgpu_job_submit_direct (job, ring, &f); +if (ret) { +amdgpu_job_free (job); goto err1; + }
This is a nice cleanup. What about going one step further and provide a helper like:
u32 test_dws[] = {
VPE_CMD_HEADER(VPE_CMD_OPCODE_FENCE, 0),
lower_32_bits(wb_addr),
... };
ret = amdgpu_ring_run_dwords(ring, ARRAY_SIZE(test_dws), test_dws,
timeout);
Because that's what most _ring_test_ib function do.
Thanks,
Pierre-Eric
Quoted 1,817 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_vpe.c +0
-1ret =dma_fence_wait_timeout (f, false, timeout);if (ret <=0 ) {@@ -859,7 +865,6 @@ static int vpe_ring_test_ib(struct amdgpu_ring *ring, long timeout) ret = (le32_to_cpu (adev->wb.wb[index]) == test_pattern) ?0 : -EINVAL ; err1: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f); err0:amdgpu_device_wb_free (adev, index);drivers/gpu/drm/amd/amdgpu/cik_sdma.c +18
-13@@ -652,7 +652,8 @@ static int cik_sdma_ring_test_ring(struct amdgpu_ring *ring)static int cik_sdma_ring_test_ib (struct amdgpu_ring *ring,long timeout) {struct amdgpu_device *adev = ring->adev; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ;unsigned index;u32 tmp =0 ;@@ -666,22 +667,27 @@ static int cik_sdma_ring_test_ib(struct amdgpu_ring *ring, long timeout) gpu_addr = adev->wb.gpu_addr + (index *4 ); tmp =0xCAFEDEAD ; adev->wb.wb[index] =cpu_to_le32 (tmp); -memset (&ib,0 ,sizeof (ib)); - r =amdgpu_ib_get (adev,NULL ,256 , -AMDGPU_IB_POOL_DIRECT , &ib); + + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,256 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_SDMA_RING_TEST );if (r) goto err0; + ib = &job->ibs[0 ]; - ib.ptr[0 ] =SDMA_PACKET (SDMA_OPCODE_WRITE , + ib->ptr[0 ] =SDMA_PACKET (SDMA_OPCODE_WRITE ,SDMA_WRITE_SUB_OPCODE_LINEAR ,0 ); - ib.ptr[1 ] =lower_32_bits (gpu_addr); - ib.ptr[2 ] =upper_32_bits (gpu_addr); - ib.ptr[3 ] =1 ; - ib.ptr[4 ] =0xDEADBEEF ; - ib.length_dw =5 ; - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (r) + ib->ptr[1 ] =lower_32_bits (gpu_addr); + ib->ptr[2 ] =upper_32_bits (gpu_addr); + ib->ptr[3 ] =1 ; + ib->ptr[4 ] =0xDEADBEEF ; + ib->length_dw =5 ; + + r =amdgpu_job_submit_direct (job, ring, &f); +if (r) { +amdgpu_job_free (job); goto err1; + } r =dma_fence_wait_timeout (f, false, timeout);if (r ==0 ) {@@ -697,7 +703,6 @@ static int cik_sdma_ring_test_ib(struct amdgpu_ring *ring, long timeout) r = -EINVAL ; err1: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f); err0:amdgpu_device_wb_free (adev, index);drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c +16
-13@@ -4071,15 +4071,14 @@ static int gfx_v10_0_ring_test_ring(struct amdgpu_ring *ring)static int gfx_v10_0_ring_test_ib (struct amdgpu_ring *ring,long timeout) {struct amdgpu_device *adev = ring->adev; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ;unsigned int index;uint64_t gpu_addr;uint32_t *cpu_ptr;long r; -memset (&ib,0 ,sizeof (ib)); - r =amdgpu_device_wb_get (adev, &index);if (r)return r;@@ -4088,22 +4087,27 @@ static int gfx_v10_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) adev->wb.wb[index] =cpu_to_le32 (0xCAFEDEAD ); cpu_ptr = &adev->wb.wb[index]; - r =amdgpu_ib_get (adev,NULL ,20 ,AMDGPU_IB_POOL_DIRECT , &ib); + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,20 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_GFX_RING_TEST );if (r) {drm_err (adev_to_drm (adev),"failed to get ib (%ld).\n" , r); goto err1; } + ib = &job->ibs[0 ]; - ib.ptr[0 ] =PACKET3 (PACKET3_WRITE_DATA ,3 ); - ib.ptr[1 ] =WRITE_DATA_DST_SEL (5 ) |WR_CONFIRM ; - ib.ptr[2 ] =lower_32_bits (gpu_addr); - ib.ptr[3 ] =upper_32_bits (gpu_addr); - ib.ptr[4 ] =0xDEADBEEF ; - ib.length_dw =5 ; + ib->ptr[0 ] =PACKET3 (PACKET3_WRITE_DATA ,3 ); + ib->ptr[1 ] =WRITE_DATA_DST_SEL (5 ) |WR_CONFIRM ; + ib->ptr[2 ] =lower_32_bits (gpu_addr); + ib->ptr[3 ] =upper_32_bits (gpu_addr); + ib->ptr[4 ] =0xDEADBEEF ; + ib->length_dw =5 ; - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (r) + r =amdgpu_job_submit_direct (job, ring, &f); +if (r) { +amdgpu_job_free (job); goto err2; + } r =dma_fence_wait_timeout (f, false, timeout);if (r ==0 ) {@@ -4118,7 +4122,6 @@ static int gfx_v10_0_ring_test_ib(struct amdgpu_ring *ring, long timeout)else r = -EINVAL ; err2: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f); err1:amdgpu_device_wb_free (adev, index);drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c +16
-13@@ -604,7 +604,8 @@ static int gfx_v11_0_ring_test_ring(struct amdgpu_ring *ring)static int gfx_v11_0_ring_test_ib (struct amdgpu_ring *ring,long timeout) {struct amdgpu_device *adev = ring->adev; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ;unsigned index;uint64_t gpu_addr;@@ -616,8 +617,6 @@ static int gfx_v11_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) ring->funcs->type == AMDGPU_RING_TYPE_KIQ)return 0 ; -memset (&ib,0 ,sizeof (ib)); - r =amdgpu_device_wb_get (adev, &index);if (r)return r;@@ -626,22 +625,27 @@ static int gfx_v11_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) adev->wb.wb[index] =cpu_to_le32 (0xCAFEDEAD ); cpu_ptr = &adev->wb.wb[index]; - r =amdgpu_ib_get (adev,NULL ,20 ,AMDGPU_IB_POOL_DIRECT , &ib); + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,20 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_GFX_RING_TEST );if (r) {drm_err (adev_to_drm (adev),"failed to get ib (%ld).\n" , r); goto err1; } + ib = &job->ibs[0 ]; - ib.ptr[0 ] =PACKET3 (PACKET3_WRITE_DATA ,3 ); - ib.ptr[1 ] =WRITE_DATA_DST_SEL (5 ) |WR_CONFIRM ; - ib.ptr[2 ] =lower_32_bits (gpu_addr); - ib.ptr[3 ] =upper_32_bits (gpu_addr); - ib.ptr[4 ] =0xDEADBEEF ; - ib.length_dw =5 ; + ib->ptr[0 ] =PACKET3 (PACKET3_WRITE_DATA ,3 ); + ib->ptr[1 ] =WRITE_DATA_DST_SEL (5 ) |WR_CONFIRM ; + ib->ptr[2 ] =lower_32_bits (gpu_addr); + ib->ptr[3 ] =upper_32_bits (gpu_addr); + ib->ptr[4 ] =0xDEADBEEF ; + ib->length_dw =5 ; - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (r) + r =amdgpu_job_submit_direct (job, ring, &f); +if (r) { +amdgpu_job_free (job); goto err2; + } r =dma_fence_wait_timeout (f, false, timeout);if (r ==0 ) {@@ -656,7 +660,6 @@ static int gfx_v11_0_ring_test_ib(struct amdgpu_ring *ring, long timeout)else r = -EINVAL ; err2: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f); err1:amdgpu_device_wb_free (adev, index);drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c +16
-13@@ -493,7 +493,8 @@ static int gfx_v12_0_ring_test_ring(struct amdgpu_ring *ring)static int gfx_v12_0_ring_test_ib (struct amdgpu_ring *ring,long timeout) {struct amdgpu_device *adev = ring->adev; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ;unsigned index;uint64_t gpu_addr;@@ -505,8 +506,6 @@ static int gfx_v12_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) ring->funcs->type == AMDGPU_RING_TYPE_KIQ)return 0 ; -memset (&ib,0 ,sizeof (ib)); - r =amdgpu_device_wb_get (adev, &index);if (r)return r;@@ -515,22 +514,27 @@ static int gfx_v12_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) adev->wb.wb[index] =cpu_to_le32 (0xCAFEDEAD ); cpu_ptr = &adev->wb.wb[index]; - r =amdgpu_ib_get (adev,NULL ,16 ,AMDGPU_IB_POOL_DIRECT , &ib); + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,16 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_GFX_RING_TEST );if (r) {drm_err (adev_to_drm (adev),"failed to get ib (%ld).\n" , r); goto err1; } + ib = &job->ibs[0 ]; - ib.ptr[0 ] =PACKET3 (PACKET3_WRITE_DATA ,3 ); - ib.ptr[1 ] =WRITE_DATA_DST_SEL (5 ) |WR_CONFIRM ; - ib.ptr[2 ] =lower_32_bits (gpu_addr); - ib.ptr[3 ] =upper_32_bits (gpu_addr); - ib.ptr[4 ] =0xDEADBEEF ; - ib.length_dw =5 ; + ib->ptr[0 ] =PACKET3 (PACKET3_WRITE_DATA ,3 ); + ib->ptr[1 ] =WRITE_DATA_DST_SEL (5 ) |WR_CONFIRM ; + ib->ptr[2 ] =lower_32_bits (gpu_addr); + ib->ptr[3 ] =upper_32_bits (gpu_addr); + ib->ptr[4 ] =0xDEADBEEF ; + ib->length_dw =5 ; - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (r) + r =amdgpu_job_submit_direct (job, ring, &f); +if (r) { +amdgpu_job_free (job); goto err2; + } r =dma_fence_wait_timeout (f, false, timeout);if (r ==0 ) {@@ -545,7 +549,6 @@ static int gfx_v12_0_ring_test_ib(struct amdgpu_ring *ring, long timeout)else r = -EINVAL ; err2: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f); err1:amdgpu_device_wb_free (adev, index);drivers/gpu/drm/amd/amdgpu/gfx_v12_1.c +16
-13@@ -307,7 +307,8 @@ static int gfx_v12_1_ring_test_ring(struct amdgpu_ring *ring)static int gfx_v12_1_ring_test_ib (struct amdgpu_ring *ring,long timeout) {struct amdgpu_device *adev = ring->adev; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ;unsigned index;uint64_t gpu_addr;@@ -319,8 +320,6 @@ static int gfx_v12_1_ring_test_ib(struct amdgpu_ring *ring, long timeout) ring->funcs->type == AMDGPU_RING_TYPE_KIQ)return 0 ; -memset (&ib,0 ,sizeof (ib)); - r =amdgpu_device_wb_get (adev, &index);if (r)return r;@@ -329,22 +328,27 @@ static int gfx_v12_1_ring_test_ib(struct amdgpu_ring *ring, long timeout) adev->wb.wb[index] =cpu_to_le32 (0xCAFEDEAD ); cpu_ptr = &adev->wb.wb[index]; - r =amdgpu_ib_get (adev,NULL ,16 ,AMDGPU_IB_POOL_DIRECT , &ib); + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,16 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_GFX_RING_TEST );if (r) {dev_err (adev->dev,"amdgpu: failed to get ib (%ld).\n" , r); goto err1; } + ib = &job->ibs[0 ]; - ib.ptr[0 ] =PACKET3 (PACKET3_WRITE_DATA ,3 ); - ib.ptr[1 ] =WRITE_DATA_DST_SEL (5 ) |WR_CONFIRM ; - ib.ptr[2 ] =lower_32_bits (gpu_addr); - ib.ptr[3 ] =upper_32_bits (gpu_addr); - ib.ptr[4 ] =0xDEADBEEF ; - ib.length_dw =5 ; + ib->ptr[0 ] =PACKET3 (PACKET3_WRITE_DATA ,3 ); + ib->ptr[1 ] =WRITE_DATA_DST_SEL (5 ) |WR_CONFIRM ; + ib->ptr[2 ] =lower_32_bits (gpu_addr); + ib->ptr[3 ] =upper_32_bits (gpu_addr); + ib->ptr[4 ] =0xDEADBEEF ; + ib->length_dw =5 ; - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (r) + r =amdgpu_job_submit_direct (job, ring, &f); +if (r) { +amdgpu_job_free (job); goto err2; + } r =dma_fence_wait_timeout (f, false, timeout);if (r ==0 ) {@@ -359,7 +363,6 @@ static int gfx_v12_1_ring_test_ib(struct amdgpu_ring *ring, long timeout)else r = -EINVAL ; err2: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f); err1:amdgpu_device_wb_free (adev, index);drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c +14
-10@@ -1895,24 +1895,29 @@ static int gfx_v6_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) {struct amdgpu_device *adev = ring->adev;struct dma_fence *f =NULL ; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;uint32_t tmp =0 ;long r;WREG32 (mmSCRATCH_REG0,0xCAFEDEAD ); -memset (&ib,0 ,sizeof (ib)); - r =amdgpu_ib_get (adev,NULL ,256 ,AMDGPU_IB_POOL_DIRECT , &ib); + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,256 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_GFX_RING_TEST );if (r)return r; - ib.ptr[0 ] =PACKET3 (PACKET3_SET_CONFIG_REG ,1 ); - ib.ptr[1 ] = mmSCRATCH_REG0 -PACKET3_SET_CONFIG_REG_START ; - ib.ptr[2 ] =0xDEADBEEF ; - ib.length_dw =3 ; + ib = &job->ibs[0 ]; + ib->ptr[0 ] =PACKET3 (PACKET3_SET_CONFIG_REG ,1 ); + ib->ptr[1 ] = mmSCRATCH_REG0 -PACKET3_SET_CONFIG_REG_START ; + ib->ptr[2 ] =0xDEADBEEF ; + ib->length_dw =3 ; - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (r) + r =amdgpu_job_submit_direct (job, ring, &f); +if (r) { +amdgpu_job_free (job); goto error; + } r =dma_fence_wait_timeout (f, false, timeout);if (r ==0 ) {@@ -1928,7 +1933,6 @@ static int gfx_v6_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) r = -EINVAL ; error: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f);return r; }drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c +15
-10@@ -2291,25 +2291,31 @@ static void gfx_v7_ring_emit_cntxcntl(struct amdgpu_ring *ring, uint32_t flags)static int gfx_v7_0_ring_test_ib (struct amdgpu_ring *ring,long timeout) {struct amdgpu_device *adev = ring->adev; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ;uint32_t tmp =0 ;long r;WREG32 (mmSCRATCH_REG0,0xCAFEDEAD ); -memset (&ib,0 ,sizeof (ib)); - r =amdgpu_ib_get (adev,NULL ,256 ,AMDGPU_IB_POOL_DIRECT , &ib); + + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,256 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_GFX_RING_TEST );if (r)return r; - ib.ptr[0 ] =PACKET3 (PACKET3_SET_UCONFIG_REG ,1 ); - ib.ptr[1 ] = mmSCRATCH_REG0 -PACKET3_SET_UCONFIG_REG_START ; - ib.ptr[2 ] =0xDEADBEEF ; - ib.length_dw =3 ; + ib = &job->ibs[0 ]; + ib->ptr[0 ] =PACKET3 (PACKET3_SET_UCONFIG_REG ,1 ); + ib->ptr[1 ] = mmSCRATCH_REG0 -PACKET3_SET_UCONFIG_REG_START ; + ib->ptr[2 ] =0xDEADBEEF ; + ib->length_dw =3 ; - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (r) + r =amdgpu_job_submit_direct (job, ring, &f); +if (r) { +amdgpu_job_free (job); goto error; + } r =dma_fence_wait_timeout (f, false, timeout);if (r ==0 ) {@@ -2325,7 +2331,6 @@ static int gfx_v7_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) r = -EINVAL ; error: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f);return r; }drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +72
-67@@ -868,9 +868,9 @@ static int gfx_v8_0_ring_test_ring(struct amdgpu_ring *ring)static int gfx_v8_0_ring_test_ib (struct amdgpu_ring *ring,long timeout) {struct amdgpu_device *adev = ring->adev; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ; -unsigned int index;uint64_t gpu_addr;uint32_t tmp;@@ -882,22 +882,26 @@ static int gfx_v8_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) gpu_addr = adev->wb.gpu_addr + (index *4 ); adev->wb.wb[index] =cpu_to_le32 (0xCAFEDEAD ); -memset (&ib,0 ,sizeof (ib)); - r =amdgpu_ib_get (adev,NULL ,20 ,AMDGPU_IB_POOL_DIRECT , &ib); + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,20 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_GFX_RING_TEST );if (r) goto err1; - ib.ptr[0 ] =PACKET3 (PACKET3_WRITE_DATA ,3 ); - ib.ptr[1 ] =WRITE_DATA_DST_SEL (5 ) |WR_CONFIRM ; - ib.ptr[2 ] =lower_32_bits (gpu_addr); - ib.ptr[3 ] =upper_32_bits (gpu_addr); - ib.ptr[4 ] =0xDEADBEEF ; - ib.length_dw =5 ; + ib = &job->ibs[0 ]; + ib->ptr[0 ] =PACKET3 (PACKET3_WRITE_DATA ,3 ); + ib->ptr[1 ] =WRITE_DATA_DST_SEL (5 ) |WR_CONFIRM ; + ib->ptr[2 ] =lower_32_bits (gpu_addr); + ib->ptr[3 ] =upper_32_bits (gpu_addr); + ib->ptr[4 ] =0xDEADBEEF ; + ib->length_dw =5 ; - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (r) + r =amdgpu_job_submit_direct (job, ring, &f); +if (r) { +amdgpu_job_free (job); goto err2; + } r =dma_fence_wait_timeout (f, false, timeout);if (r ==0 ) {@@ -914,7 +918,6 @@ static int gfx_v8_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) r = -EINVAL ; err2: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f); err1:amdgpu_device_wb_free (adev, index);@@ -1474,7 +1477,8 @@ static const u32 sec_ded_counter_registers[] =static int gfx_v8_0_do_edc_gpr_workarounds (struct amdgpu_device *adev) {struct amdgpu_ring *ring = &adev->gfx.compute_ring[0 ]; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ;int r, i;u32 tmp;@@ -1505,106 +1509,108 @@ static int gfx_v8_0_do_edc_gpr_workarounds(struct amdgpu_device *adev) total_size +=sizeof (sgpr_init_compute_shader);/* allocate an indirect buffer to put the commands in */ -memset (&ib,0 ,sizeof (ib)); - r =amdgpu_ib_get (adev,NULL , total_size, -AMDGPU_IB_POOL_DIRECT , &ib); + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL , total_size, +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_RUN_SHADER );if (r) {drm_err (adev_to_drm (adev),"failed to get ib (%d).\n" , r);return r; } + ib = &job->ibs[0 ];/* load the compute shaders */ for (i =0 ; i <ARRAY_SIZE (vgpr_init_compute_shader); i++) - ib.ptr[i + (vgpr_offset /4 )] = vgpr_init_compute_shader[i]; + ib->ptr[i + (vgpr_offset /4 )] = vgpr_init_compute_shader[i];for (i =0 ; i <ARRAY_SIZE (sgpr_init_compute_shader); i++) - ib.ptr[i + (sgpr_offset /4 )] = sgpr_init_compute_shader[i]; + ib->ptr[i + (sgpr_offset /4 )] = sgpr_init_compute_shader[i];/* init the ib length to 0 */ - ib.length_dw =0 ; + ib->length_dw =0 ;/* VGPR */ /* write the register state for the compute dispatch */ for (i =0 ; i <ARRAY_SIZE (vgpr_init_regs); i +=2 ) { - ib.ptr[ib.length_dw++] =PACKET3 (PACKET3_SET_SH_REG ,1 ); - ib.ptr[ib.length_dw++] = vgpr_init_regs[i] -PACKET3_SET_SH_REG_START ; - ib.ptr[ib.length_dw++] = vgpr_init_regs[i +1 ]; + ib->ptr[ib->length_dw++] =PACKET3 (PACKET3_SET_SH_REG ,1 ); + ib->ptr[ib->length_dw++] = vgpr_init_regs[i] -PACKET3_SET_SH_REG_START ; + ib->ptr[ib->length_dw++] = vgpr_init_regs[i +1 ]; }/* write the shader start address: mmCOMPUTE_PGM_LO, mmCOMPUTE_PGM_HI */ - gpu_addr = (ib.gpu_addr + (u64 )vgpr_offset) >>8 ; - ib.ptr[ib.length_dw++] =PACKET3 (PACKET3_SET_SH_REG ,2 ); - ib.ptr[ib.length_dw++] = mmCOMPUTE_PGM_LO -PACKET3_SET_SH_REG_START ; - ib.ptr[ib.length_dw++] =lower_32_bits (gpu_addr); - ib.ptr[ib.length_dw++] =upper_32_bits (gpu_addr); + gpu_addr = (ib->gpu_addr + (u64 )vgpr_offset) >>8 ; + ib->ptr[ib->length_dw++] =PACKET3 (PACKET3_SET_SH_REG ,2 ); + ib->ptr[ib->length_dw++] = mmCOMPUTE_PGM_LO -PACKET3_SET_SH_REG_START ; + ib->ptr[ib->length_dw++] =lower_32_bits (gpu_addr); + ib->ptr[ib->length_dw++] =upper_32_bits (gpu_addr);/* write dispatch packet */ - ib.ptr[ib.length_dw++] =PACKET3 (PACKET3_DISPATCH_DIRECT ,3 ); - ib.ptr[ib.length_dw++] =8 ;/* x */ - ib.ptr[ib.length_dw++] =1 ;/* y */ - ib.ptr[ib.length_dw++] =1 ;/* z */ - ib.ptr[ib.length_dw++] = + ib->ptr[ib->length_dw++] =PACKET3 (PACKET3_DISPATCH_DIRECT ,3 ); + ib->ptr[ib->length_dw++] =8 ;/* x */ + ib->ptr[ib->length_dw++] =1 ;/* y */ + ib->ptr[ib->length_dw++] =1 ;/* z */ + ib->ptr[ib->length_dw++] =REG_SET_FIELD (0 ,COMPUTE_DISPATCH_INITIATOR ,COMPUTE_SHADER_EN ,1 );/* write CS partial flush packet */ - ib.ptr[ib.length_dw++] =PACKET3 (PACKET3_EVENT_WRITE ,0 ); - ib.ptr[ib.length_dw++] =EVENT_TYPE (7 ) |EVENT_INDEX (4 ); + ib->ptr[ib->length_dw++] =PACKET3 (PACKET3_EVENT_WRITE ,0 ); + ib->ptr[ib->length_dw++] =EVENT_TYPE (7 ) |EVENT_INDEX (4 );/* SGPR1 */ /* write the register state for the compute dispatch */ for (i =0 ; i <ARRAY_SIZE (sgpr1_init_regs); i +=2 ) { - ib.ptr[ib.length_dw++] =PACKET3 (PACKET3_SET_SH_REG ,1 ); - ib.ptr[ib.length_dw++] = sgpr1_init_regs[i] -PACKET3_SET_SH_REG_START ; - ib.ptr[ib.length_dw++] = sgpr1_init_regs[i +1 ]; + ib->ptr[ib->length_dw++] =PACKET3 (PACKET3_SET_SH_REG ,1 ); + ib->ptr[ib->length_dw++] = sgpr1_init_regs[i] -PACKET3_SET_SH_REG_START ; + ib->ptr[ib->length_dw++] = sgpr1_init_regs[i +1 ]; }/* write the shader start address: mmCOMPUTE_PGM_LO, mmCOMPUTE_PGM_HI */ - gpu_addr = (ib.gpu_addr + (u64 )sgpr_offset) >>8 ; - ib.ptr[ib.length_dw++] =PACKET3 (PACKET3_SET_SH_REG ,2 ); - ib.ptr[ib.length_dw++] = mmCOMPUTE_PGM_LO -PACKET3_SET_SH_REG_START ; - ib.ptr[ib.length_dw++] =lower_32_bits (gpu_addr); - ib.ptr[ib.length_dw++] =upper_32_bits (gpu_addr); + gpu_addr = (ib->gpu_addr + (u64 )sgpr_offset) >>8 ; + ib->ptr[ib->length_dw++] =PACKET3 (PACKET3_SET_SH_REG ,2 ); + ib->ptr[ib->length_dw++] = mmCOMPUTE_PGM_LO -PACKET3_SET_SH_REG_START ; + ib->ptr[ib->length_dw++] =lower_32_bits (gpu_addr); + ib->ptr[ib->length_dw++] =upper_32_bits (gpu_addr);/* write dispatch packet */ - ib.ptr[ib.length_dw++] =PACKET3 (PACKET3_DISPATCH_DIRECT ,3 ); - ib.ptr[ib.length_dw++] =8 ;/* x */ - ib.ptr[ib.length_dw++] =1 ;/* y */ - ib.ptr[ib.length_dw++] =1 ;/* z */ - ib.ptr[ib.length_dw++] = + ib->ptr[ib->length_dw++] =PACKET3 (PACKET3_DISPATCH_DIRECT ,3 ); + ib->ptr[ib->length_dw++] =8 ;/* x */ + ib->ptr[ib->length_dw++] =1 ;/* y */ + ib->ptr[ib->length_dw++] =1 ;/* z */ + ib->ptr[ib->length_dw++] =REG_SET_FIELD (0 ,COMPUTE_DISPATCH_INITIATOR ,COMPUTE_SHADER_EN ,1 );/* write CS partial flush packet */ - ib.ptr[ib.length_dw++] =PACKET3 (PACKET3_EVENT_WRITE ,0 ); - ib.ptr[ib.length_dw++] =EVENT_TYPE (7 ) |EVENT_INDEX (4 ); + ib->ptr[ib->length_dw++] =PACKET3 (PACKET3_EVENT_WRITE ,0 ); + ib->ptr[ib->length_dw++] =EVENT_TYPE (7 ) |EVENT_INDEX (4 );/* SGPR2 */ /* write the register state for the compute dispatch */ for (i =0 ; i <ARRAY_SIZE (sgpr2_init_regs); i +=2 ) { - ib.ptr[ib.length_dw++] =PACKET3 (PACKET3_SET_SH_REG ,1 ); - ib.ptr[ib.length_dw++] = sgpr2_init_regs[i] -PACKET3_SET_SH_REG_START ; - ib.ptr[ib.length_dw++] = sgpr2_init_regs[i +1 ]; + ib->ptr[ib->length_dw++] =PACKET3 (PACKET3_SET_SH_REG ,1 ); + ib->ptr[ib->length_dw++] = sgpr2_init_regs[i] -PACKET3_SET_SH_REG_START ; + ib->ptr[ib->length_dw++] = sgpr2_init_regs[i +1 ]; }/* write the shader start address: mmCOMPUTE_PGM_LO, mmCOMPUTE_PGM_HI */ - gpu_addr = (ib.gpu_addr + (u64 )sgpr_offset) >>8 ; - ib.ptr[ib.length_dw++] =PACKET3 (PACKET3_SET_SH_REG ,2 ); - ib.ptr[ib.length_dw++] = mmCOMPUTE_PGM_LO -PACKET3_SET_SH_REG_START ; - ib.ptr[ib.length_dw++] =lower_32_bits (gpu_addr); - ib.ptr[ib.length_dw++] =upper_32_bits (gpu_addr); + gpu_addr = (ib->gpu_addr + (u64 )sgpr_offset) >>8 ; + ib->ptr[ib->length_dw++] =PACKET3 (PACKET3_SET_SH_REG ,2 ); + ib->ptr[ib->length_dw++] = mmCOMPUTE_PGM_LO -PACKET3_SET_SH_REG_START ; + ib->ptr[ib->length_dw++] =lower_32_bits (gpu_addr); + ib->ptr[ib->length_dw++] =upper_32_bits (gpu_addr);/* write dispatch packet */ - ib.ptr[ib.length_dw++] =PACKET3 (PACKET3_DISPATCH_DIRECT ,3 ); - ib.ptr[ib.length_dw++] =8 ;/* x */ - ib.ptr[ib.length_dw++] =1 ;/* y */ - ib.ptr[ib.length_dw++] =1 ;/* z */ - ib.ptr[ib.length_dw++] = + ib->ptr[ib->length_dw++] =PACKET3 (PACKET3_DISPATCH_DIRECT ,3 ); + ib->ptr[ib->length_dw++] =8 ;/* x */ + ib->ptr[ib->length_dw++] =1 ;/* y */ + ib->ptr[ib->length_dw++] =1 ;/* z */ + ib->ptr[ib->length_dw++] =REG_SET_FIELD (0 ,COMPUTE_DISPATCH_INITIATOR ,COMPUTE_SHADER_EN ,1 );/* write CS partial flush packet */ - ib.ptr[ib.length_dw++] =PACKET3 (PACKET3_EVENT_WRITE ,0 ); - ib.ptr[ib.length_dw++] =EVENT_TYPE (7 ) |EVENT_INDEX (4 ); + ib->ptr[ib->length_dw++] =PACKET3 (PACKET3_EVENT_WRITE ,0 ); + ib->ptr[ib->length_dw++] =EVENT_TYPE (7 ) |EVENT_INDEX (4 );/* shedule the ib on the ring */ - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); + r =amdgpu_job_submit_direct (job, ring, &f);if (r) {drm_err (adev_to_drm (adev),"ib submit failed (%d).\n" , r); +amdgpu_job_free (job); goto fail; }@@ -1629,7 +1635,6 @@ static int gfx_v8_0_do_edc_gpr_workarounds(struct amdgpu_device *adev)RREG32 (sec_ded_counter_registers[i]); fail: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f);return r;drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +71
-67@@ -1224,9 +1224,9 @@ static int gfx_v9_0_ring_test_ring(struct amdgpu_ring *ring)static int gfx_v9_0_ring_test_ib (struct amdgpu_ring *ring,long timeout) {struct amdgpu_device *adev = ring->adev; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ; -unsigned index;uint64_t gpu_addr;uint32_t tmp;@@ -1238,22 +1238,26 @@ static int gfx_v9_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) gpu_addr = adev->wb.gpu_addr + (index *4 ); adev->wb.wb[index] =cpu_to_le32 (0xCAFEDEAD ); -memset (&ib,0 ,sizeof (ib)); - r =amdgpu_ib_get (adev,NULL ,20 ,AMDGPU_IB_POOL_DIRECT , &ib); + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,20 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_GFX_RING_TEST );if (r) goto err1; - ib.ptr[0 ] =PACKET3 (PACKET3_WRITE_DATA ,3 ); - ib.ptr[1 ] =WRITE_DATA_DST_SEL (5 ) |WR_CONFIRM ; - ib.ptr[2 ] =lower_32_bits (gpu_addr); - ib.ptr[3 ] =upper_32_bits (gpu_addr); - ib.ptr[4 ] =0xDEADBEEF ; - ib.length_dw =5 ; + ib = &job->ibs[0 ]; + ib->ptr[0 ] =PACKET3 (PACKET3_WRITE_DATA ,3 ); + ib->ptr[1 ] =WRITE_DATA_DST_SEL (5 ) |WR_CONFIRM ; + ib->ptr[2 ] =lower_32_bits (gpu_addr); + ib->ptr[3 ] =upper_32_bits (gpu_addr); + ib->ptr[4 ] =0xDEADBEEF ; + ib->length_dw =5 ; - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (r) + r =amdgpu_job_submit_direct (job, ring, &f); +if (r) { +amdgpu_job_free (job); goto err2; + } r =dma_fence_wait_timeout (f, false, timeout);if (r ==0 ) {@@ -1270,7 +1274,6 @@ static int gfx_v9_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) r = -EINVAL ; err2: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f); err1:amdgpu_device_wb_free (adev, index);@@ -4624,7 +4627,8 @@ static int gfx_v9_0_do_edc_gds_workarounds(struct amdgpu_device *adev)static int gfx_v9_0_do_edc_gpr_workarounds (struct amdgpu_device *adev) {struct amdgpu_ring *ring = &adev->gfx.compute_ring[0 ]; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ;int r, i;unsigned total_size, vgpr_offset, sgpr_offset;@@ -4670,9 +4674,9 @@ static int gfx_v9_0_do_edc_gpr_workarounds(struct amdgpu_device *adev) total_size +=sizeof (sgpr_init_compute_shader);/* allocate an indirect buffer to put the commands in */ -memset (&ib,0 ,sizeof (ib)); - r =amdgpu_ib_get (adev,NULL , total_size, -AMDGPU_IB_POOL_DIRECT , &ib); + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL , total_size, +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_RUN_SHADER );if (r) {drm_err (adev_to_drm (adev),"failed to get ib (%d).\n" , r);return r;@@ -4680,102 +4684,103 @@ static int gfx_v9_0_do_edc_gpr_workarounds(struct amdgpu_device *adev)/* load the compute shaders */ for (i =0 ; i < vgpr_init_shader_size/sizeof (u32); i++) - ib.ptr[i + (vgpr_offset /4 )] = vgpr_init_shader_ptr[i]; + ib->ptr[i + (vgpr_offset /4 )] = vgpr_init_shader_ptr[i];for (i =0 ; i <ARRAY_SIZE (sgpr_init_compute_shader); i++) - ib.ptr[i + (sgpr_offset /4 )] = sgpr_init_compute_shader[i]; + ib->ptr[i + (sgpr_offset /4 )] = sgpr_init_compute_shader[i];/* init the ib length to 0 */ - ib.length_dw =0 ; + ib->length_dw =0 ;/* VGPR */ /* write the register state for the compute dispatch */ for (i =0 ; i < gpr_reg_size; i++) { - ib.ptr[ib.length_dw++] =PACKET3 (PACKET3_SET_SH_REG ,1 ); - ib.ptr[ib.length_dw++] =SOC15_REG_ENTRY_OFFSET (vgpr_init_regs_ptr[i]) + ib->ptr[ib->length_dw++] =PACKET3 (PACKET3_SET_SH_REG ,1 ); + ib->ptr[ib->length_dw++] =SOC15_REG_ENTRY_OFFSET (vgpr_init_regs_ptr[i]) -PACKET3_SET_SH_REG_START ; - ib.ptr[ib.length_dw++] = vgpr_init_regs_ptr[i].reg_value; + ib->ptr[ib->length_dw++] = vgpr_init_regs_ptr[i].reg_value; }/* write the shader start address: mmCOMPUTE_PGM_LO, mmCOMPUTE_PGM_HI */ - gpu_addr = (ib.gpu_addr + (u64 )vgpr_offset) >>8 ; - ib.ptr[ib.length_dw++] =PACKET3 (PACKET3_SET_SH_REG ,2 ); - ib.ptr[ib.length_dw++] =SOC15_REG_OFFSET (GC ,0 , mmCOMPUTE_PGM_LO) + gpu_addr = (ib->gpu_addr + (u64 )vgpr_offset) >>8 ; + ib->ptr[ib->length_dw++] =PACKET3 (PACKET3_SET_SH_REG ,2 ); + ib->ptr[ib->length_dw++] =SOC15_REG_OFFSET (GC ,0 , mmCOMPUTE_PGM_LO) -PACKET3_SET_SH_REG_START ; - ib.ptr[ib.length_dw++] =lower_32_bits (gpu_addr); - ib.ptr[ib.length_dw++] =upper_32_bits (gpu_addr); + ib->ptr[ib->length_dw++] =lower_32_bits (gpu_addr); + ib->ptr[ib->length_dw++] =upper_32_bits (gpu_addr);/* write dispatch packet */ - ib.ptr[ib.length_dw++] =PACKET3 (PACKET3_DISPATCH_DIRECT ,3 ); - ib.ptr[ib.length_dw++] = compute_dim_x *2 ;/* x */ - ib.ptr[ib.length_dw++] =1 ;/* y */ - ib.ptr[ib.length_dw++] =1 ;/* z */ - ib.ptr[ib.length_dw++] = + ib->ptr[ib->length_dw++] =PACKET3 (PACKET3_DISPATCH_DIRECT ,3 ); + ib->ptr[ib->length_dw++] = compute_dim_x *2 ;/* x */ + ib->ptr[ib->length_dw++] =1 ;/* y */ + ib->ptr[ib->length_dw++] =1 ;/* z */ + ib->ptr[ib->length_dw++] =REG_SET_FIELD (0 ,COMPUTE_DISPATCH_INITIATOR ,COMPUTE_SHADER_EN ,1 );/* write CS partial flush packet */ - ib.ptr[ib.length_dw++] =PACKET3 (PACKET3_EVENT_WRITE ,0 ); - ib.ptr[ib.length_dw++] =EVENT_TYPE (7 ) |EVENT_INDEX (4 ); + ib->ptr[ib->length_dw++] =PACKET3 (PACKET3_EVENT_WRITE ,0 ); + ib->ptr[ib->length_dw++] =EVENT_TYPE (7 ) |EVENT_INDEX (4 );/* SGPR1 */ /* write the register state for the compute dispatch */ for (i =0 ; i < gpr_reg_size; i++) { - ib.ptr[ib.length_dw++] =PACKET3 (PACKET3_SET_SH_REG ,1 ); - ib.ptr[ib.length_dw++] =SOC15_REG_ENTRY_OFFSET (sgpr1_init_regs[i]) + ib->ptr[ib->length_dw++] =PACKET3 (PACKET3_SET_SH_REG ,1 ); + ib->ptr[ib->length_dw++] =SOC15_REG_ENTRY_OFFSET (sgpr1_init_regs[i]) -PACKET3_SET_SH_REG_START ; - ib.ptr[ib.length_dw++] = sgpr1_init_regs[i].reg_value; + ib->ptr[ib->length_dw++] = sgpr1_init_regs[i].reg_value; }/* write the shader start address: mmCOMPUTE_PGM_LO, mmCOMPUTE_PGM_HI */ - gpu_addr = (ib.gpu_addr + (u64 )sgpr_offset) >>8 ; - ib.ptr[ib.length_dw++] =PACKET3 (PACKET3_SET_SH_REG ,2 ); - ib.ptr[ib.length_dw++] =SOC15_REG_OFFSET (GC ,0 , mmCOMPUTE_PGM_LO) + gpu_addr = (ib->gpu_addr + (u64 )sgpr_offset) >>8 ; + ib->ptr[ib->length_dw++] =PACKET3 (PACKET3_SET_SH_REG ,2 ); + ib->ptr[ib->length_dw++] =SOC15_REG_OFFSET (GC ,0 , mmCOMPUTE_PGM_LO) -PACKET3_SET_SH_REG_START ; - ib.ptr[ib.length_dw++] =lower_32_bits (gpu_addr); - ib.ptr[ib.length_dw++] =upper_32_bits (gpu_addr); + ib->ptr[ib->length_dw++] =lower_32_bits (gpu_addr); + ib->ptr[ib->length_dw++] =upper_32_bits (gpu_addr);/* write dispatch packet */ - ib.ptr[ib.length_dw++] =PACKET3 (PACKET3_DISPATCH_DIRECT ,3 ); - ib.ptr[ib.length_dw++] = compute_dim_x /2 * sgpr_work_group_size;/* x */ - ib.ptr[ib.length_dw++] =1 ;/* y */ - ib.ptr[ib.length_dw++] =1 ;/* z */ - ib.ptr[ib.length_dw++] = + ib->ptr[ib->length_dw++] =PACKET3 (PACKET3_DISPATCH_DIRECT ,3 ); + ib->ptr[ib->length_dw++] = compute_dim_x /2 * sgpr_work_group_size;/* x */ + ib->ptr[ib->length_dw++] =1 ;/* y */ + ib->ptr[ib->length_dw++] =1 ;/* z */ + ib->ptr[ib->length_dw++] =REG_SET_FIELD (0 ,COMPUTE_DISPATCH_INITIATOR ,COMPUTE_SHADER_EN ,1 );/* write CS partial flush packet */ - ib.ptr[ib.length_dw++] =PACKET3 (PACKET3_EVENT_WRITE ,0 ); - ib.ptr[ib.length_dw++] =EVENT_TYPE (7 ) |EVENT_INDEX (4 ); + ib->ptr[ib->length_dw++] =PACKET3 (PACKET3_EVENT_WRITE ,0 ); + ib->ptr[ib->length_dw++] =EVENT_TYPE (7 ) |EVENT_INDEX (4 );/* SGPR2 */ /* write the register state for the compute dispatch */ for (i =0 ; i < gpr_reg_size; i++) { - ib.ptr[ib.length_dw++] =PACKET3 (PACKET3_SET_SH_REG ,1 ); - ib.ptr[ib.length_dw++] =SOC15_REG_ENTRY_OFFSET (sgpr2_init_regs[i]) + ib->ptr[ib->length_dw++] =PACKET3 (PACKET3_SET_SH_REG ,1 ); + ib->ptr[ib->length_dw++] =SOC15_REG_ENTRY_OFFSET (sgpr2_init_regs[i]) -PACKET3_SET_SH_REG_START ; - ib.ptr[ib.length_dw++] = sgpr2_init_regs[i].reg_value; + ib->ptr[ib->length_dw++] = sgpr2_init_regs[i].reg_value; }/* write the shader start address: mmCOMPUTE_PGM_LO, mmCOMPUTE_PGM_HI */ - gpu_addr = (ib.gpu_addr + (u64 )sgpr_offset) >>8 ; - ib.ptr[ib.length_dw++] =PACKET3 (PACKET3_SET_SH_REG ,2 ); - ib.ptr[ib.length_dw++] =SOC15_REG_OFFSET (GC ,0 , mmCOMPUTE_PGM_LO) + gpu_addr = (ib->gpu_addr + (u64 )sgpr_offset) >>8 ; + ib->ptr[ib->length_dw++] =PACKET3 (PACKET3_SET_SH_REG ,2 ); + ib->ptr[ib->length_dw++] =SOC15_REG_OFFSET (GC ,0 , mmCOMPUTE_PGM_LO) -PACKET3_SET_SH_REG_START ; - ib.ptr[ib.length_dw++] =lower_32_bits (gpu_addr); - ib.ptr[ib.length_dw++] =upper_32_bits (gpu_addr); + ib->ptr[ib->length_dw++] =lower_32_bits (gpu_addr); + ib->ptr[ib->length_dw++] =upper_32_bits (gpu_addr);/* write dispatch packet */ - ib.ptr[ib.length_dw++] =PACKET3 (PACKET3_DISPATCH_DIRECT ,3 ); - ib.ptr[ib.length_dw++] = compute_dim_x /2 * sgpr_work_group_size;/* x */ - ib.ptr[ib.length_dw++] =1 ;/* y */ - ib.ptr[ib.length_dw++] =1 ;/* z */ - ib.ptr[ib.length_dw++] = + ib->ptr[ib->length_dw++] =PACKET3 (PACKET3_DISPATCH_DIRECT ,3 ); + ib->ptr[ib->length_dw++] = compute_dim_x /2 * sgpr_work_group_size;/* x */ + ib->ptr[ib->length_dw++] =1 ;/* y */ + ib->ptr[ib->length_dw++] =1 ;/* z */ + ib->ptr[ib->length_dw++] =REG_SET_FIELD (0 ,COMPUTE_DISPATCH_INITIATOR ,COMPUTE_SHADER_EN ,1 );/* write CS partial flush packet */ - ib.ptr[ib.length_dw++] =PACKET3 (PACKET3_EVENT_WRITE ,0 ); - ib.ptr[ib.length_dw++] =EVENT_TYPE (7 ) |EVENT_INDEX (4 ); + ib->ptr[ib->length_dw++] =PACKET3 (PACKET3_EVENT_WRITE ,0 ); + ib->ptr[ib->length_dw++] =EVENT_TYPE (7 ) |EVENT_INDEX (4 );/* shedule the ib on the ring */ - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); + r =amdgpu_job_submit_direct (job, ring, &f);if (r) {drm_err (adev_to_drm (adev),"ib schedule failed (%d).\n" , r); +amdgpu_job_free (job); goto fail; }@@ -4787,7 +4792,6 @@ static int gfx_v9_0_do_edc_gpr_workarounds(struct amdgpu_device *adev) } fail: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f);return r;drivers/gpu/drm/amd/amdgpu/gfx_v9_4_2.c +8
-18@@ -345,12 +345,13 @@ const struct soc15_reg_entry sgpr64_init_regs_aldebaran[] = {static int gfx_v9_4_2_run_shader (struct amdgpu_device *adev,struct amdgpu_ring *ring, -struct amdgpu_ib *ib,const u32 *shader_ptr,u32 shader_size,const struct soc15_reg_entry *init_regs,u32 regs_size,u32 compute_dim_x,u64 wb_gpu_addr,u32 pattern,struct dma_fence **fence_ptr) { +struct amdgpu_job *job; +struct amdgpu_ib *ib;int r, i;uint32_t total_size, shader_offset;u64 gpu_addr;@@ -360,10 +361,9 @@ static int gfx_v9_4_2_run_shader(struct amdgpu_device *adev, shader_offset = total_size; total_size +=ALIGN (shader_size,256 ); -/* allocate an indirect buffer to put the commands in */ -memset (ib,0 ,sizeof (*ib)); - r =amdgpu_ib_get (adev,NULL , total_size, -AMDGPU_IB_POOL_DIRECT , ib); + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL , total_size, +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_RUN_SHADER );if (r) {dev_err (adev->dev,"failed to get ib (%d).\n" , r);return r;@@ -408,11 +408,11 @@ static int gfx_v9_4_2_run_shader(struct amdgpu_device *adev, ib->ptr[ib->length_dw++] =REG_SET_FIELD (0 ,COMPUTE_DISPATCH_INITIATOR ,COMPUTE_SHADER_EN ,1 ); -/* shedule the ib on the ring */ - r =amdgpu_ib_schedule (ring,1 , ib,NULL , fence_ptr); +/* schedule the ib on the ring */ + r =amdgpu_job_submit_direct (job, ring, fence_ptr);if (r) {dev_err (adev->dev,"ib submit failed (%d).\n" , r); -amdgpu_ib_free (ib,NULL ); +amdgpu_job_free (job); }return r; }@@ -493,7 +493,6 @@ static int gfx_v9_4_2_do_sgprs_init(struct amdgpu_device *adev)int wb_size = adev->gfx.config.max_shader_engines *CU_ID_MAX *SIMD_ID_MAX *WAVE_ID_MAX ;struct amdgpu_ib wb_ib; -struct amdgpu_ib disp_ibs[3 ];struct dma_fence *fences[3 ];u32 pattern[3 ] = {0x1 ,0x5 ,0xa };@@ -514,7 +513,6 @@ static int gfx_v9_4_2_do_sgprs_init(struct amdgpu_device *adev) r = gfx_v9_4_2_run_shader(adev, &adev->gfx.compute_ring[0], - &disp_ibs[0], sgpr112_init_compute_shader_aldebaran, sizeof(sgpr112_init_compute_shader_aldebaran), sgpr112_init_regs_aldebaran,@@ -539,7 +537,6 @@ static int gfx_v9_4_2_do_sgprs_init(struct amdgpu_device *adev) r = gfx_v9_4_2_run_shader(adev, &adev->gfx.compute_ring[1], - &disp_ibs[1], sgpr96_init_compute_shader_aldebaran, sizeof(sgpr96_init_compute_shader_aldebaran), sgpr96_init_regs_aldebaran,@@ -579,7 +576,6 @@ static int gfx_v9_4_2_do_sgprs_init(struct amdgpu_device *adev)memset (wb_ib.ptr,0 , (1 + wb_size) *sizeof (uint32_t )); r = gfx_v9_4_2_run_shader(adev, &adev->gfx.compute_ring[0], - &disp_ibs[2], sgpr64_init_compute_shader_aldebaran, sizeof(sgpr64_init_compute_shader_aldebaran), sgpr64_init_regs_aldebaran,@@ -611,13 +607,10 @@ static int gfx_v9_4_2_do_sgprs_init(struct amdgpu_device *adev) } disp2_failed: -amdgpu_ib_free (&disp_ibs[2 ],NULL );dma_fence_put (fences[2 ]); disp1_failed: -amdgpu_ib_free (&disp_ibs[1 ],NULL );dma_fence_put (fences[1 ]); disp0_failed: -amdgpu_ib_free (&disp_ibs[0 ],NULL );dma_fence_put (fences[0 ]); pro_end:amdgpu_ib_free (&wb_ib,NULL );@@ -637,7 +630,6 @@ static int gfx_v9_4_2_do_vgprs_init(struct amdgpu_device *adev)int wb_size = adev->gfx.config.max_shader_engines *CU_ID_MAX *SIMD_ID_MAX *WAVE_ID_MAX ;struct amdgpu_ib wb_ib; -struct amdgpu_ib disp_ib;struct dma_fence *fence;u32 pattern =0xa ;@@ -657,7 +649,6 @@ static int gfx_v9_4_2_do_vgprs_init(struct amdgpu_device *adev) r = gfx_v9_4_2_run_shader(adev, &adev->gfx.compute_ring[0], - &disp_ib, vgpr_init_compute_shader_aldebaran, sizeof(vgpr_init_compute_shader_aldebaran), vgpr_init_regs_aldebaran,@@ -687,7 +678,6 @@ static int gfx_v9_4_2_do_vgprs_init(struct amdgpu_device *adev) } disp_failed: -amdgpu_ib_free (&disp_ib,NULL );dma_fence_put (fence); pro_end:amdgpu_ib_free (&wb_ib,NULL );drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c +16
-13@@ -451,9 +451,9 @@ static int gfx_v9_4_3_ring_test_ring(struct amdgpu_ring *ring)static int gfx_v9_4_3_ring_test_ib (struct amdgpu_ring *ring,long timeout) {struct amdgpu_device *adev = ring->adev; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ; -unsigned index;uint64_t gpu_addr;uint32_t tmp;@@ -465,22 +465,26 @@ static int gfx_v9_4_3_ring_test_ib(struct amdgpu_ring *ring, long timeout) gpu_addr = adev->wb.gpu_addr + (index *4 ); adev->wb.wb[index] =cpu_to_le32 (0xCAFEDEAD ); -memset (&ib,0 ,sizeof (ib)); - r =amdgpu_ib_get (adev,NULL ,20 ,AMDGPU_IB_POOL_DIRECT , &ib); + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,20 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_GFX_RING_TEST );if (r) goto err1; - ib.ptr[0 ] =PACKET3 (PACKET3_WRITE_DATA ,3 ); - ib.ptr[1 ] =WRITE_DATA_DST_SEL (5 ) |WR_CONFIRM ; - ib.ptr[2 ] =lower_32_bits (gpu_addr); - ib.ptr[3 ] =upper_32_bits (gpu_addr); - ib.ptr[4 ] =0xDEADBEEF ; - ib.length_dw =5 ; + ib = &job->ibs[0 ]; + ib->ptr[0 ] =PACKET3 (PACKET3_WRITE_DATA ,3 ); + ib->ptr[1 ] =WRITE_DATA_DST_SEL (5 ) |WR_CONFIRM ; + ib->ptr[2 ] =lower_32_bits (gpu_addr); + ib->ptr[3 ] =upper_32_bits (gpu_addr); + ib->ptr[4 ] =0xDEADBEEF ; + ib->length_dw =5 ; - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (r) + r =amdgpu_job_submit_direct (job, ring, &f); +if (r) { +amdgpu_job_free (job); goto err2; + } r =dma_fence_wait_timeout (f, false, timeout);if (r ==0 ) {@@ -497,7 +501,6 @@ static int gfx_v9_4_3_ring_test_ib(struct amdgpu_ring *ring, long timeout) r = -EINVAL ; err2: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f); err1:amdgpu_device_wb_free (adev, index);drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c +21
-17@@ -584,7 +584,8 @@ static int sdma_v2_4_ring_test_ring(struct amdgpu_ring *ring)static int sdma_v2_4_ring_test_ib (struct amdgpu_ring *ring,long timeout) {struct amdgpu_device *adev = ring->adev; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ;unsigned index;u32 tmp =0 ;@@ -598,26 +599,30 @@ static int sdma_v2_4_ring_test_ib(struct amdgpu_ring *ring, long timeout) gpu_addr = adev->wb.gpu_addr + (index *4 ); tmp =0xCAFEDEAD ; adev->wb.wb[index] =cpu_to_le32 (tmp); -memset (&ib,0 ,sizeof (ib)); - r =amdgpu_ib_get (adev,NULL ,256 , -AMDGPU_IB_POOL_DIRECT , &ib); + + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,256 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_SDMA_RING_TEST );if (r) goto err0; - ib.ptr[0 ] =SDMA_PKT_HEADER_OP (SDMA_OP_WRITE ) | + ib = &job->ibs[0 ]; + ib->ptr[0 ] =SDMA_PKT_HEADER_OP (SDMA_OP_WRITE ) |SDMA_PKT_HEADER_SUB_OP (SDMA_SUBOP_WRITE_LINEAR ); - ib.ptr[1 ] =lower_32_bits (gpu_addr); - ib.ptr[2 ] =upper_32_bits (gpu_addr); - ib.ptr[3 ] =SDMA_PKT_WRITE_UNTILED_DW_3_COUNT (1 ); - ib.ptr[4 ] =0xDEADBEEF ; - ib.ptr[5 ] =SDMA_PKT_HEADER_OP (SDMA_OP_NOP ); - ib.ptr[6 ] =SDMA_PKT_HEADER_OP (SDMA_OP_NOP ); - ib.ptr[7 ] =SDMA_PKT_HEADER_OP (SDMA_OP_NOP ); - ib.length_dw =8 ; - - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (r) + ib->ptr[1 ] =lower_32_bits (gpu_addr); + ib->ptr[2 ] =upper_32_bits (gpu_addr); + ib->ptr[3 ] =SDMA_PKT_WRITE_UNTILED_DW_3_COUNT (1 ); + ib->ptr[4 ] =0xDEADBEEF ; + ib->ptr[5 ] =SDMA_PKT_HEADER_OP (SDMA_OP_NOP ); + ib->ptr[6 ] =SDMA_PKT_HEADER_OP (SDMA_OP_NOP ); + ib->ptr[7 ] =SDMA_PKT_HEADER_OP (SDMA_OP_NOP ); + ib->length_dw =8 ; + + r =amdgpu_job_submit_direct (job, ring, &f); +if (r) { +amdgpu_job_free (job); goto err1; + } r =dma_fence_wait_timeout (f, false, timeout);if (r ==0 ) {@@ -633,7 +638,6 @@ static int sdma_v2_4_ring_test_ib(struct amdgpu_ring *ring, long timeout) r = -EINVAL ; err1: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f); err0:amdgpu_device_wb_free (adev, index);drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c +21
-17@@ -858,7 +858,8 @@ static int sdma_v3_0_ring_test_ring(struct amdgpu_ring *ring)static int sdma_v3_0_ring_test_ib (struct amdgpu_ring *ring,long timeout) {struct amdgpu_device *adev = ring->adev; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ;unsigned index;u32 tmp =0 ;@@ -872,26 +873,30 @@ static int sdma_v3_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) gpu_addr = adev->wb.gpu_addr + (index *4 ); tmp =0xCAFEDEAD ; adev->wb.wb[index] =cpu_to_le32 (tmp); -memset (&ib,0 ,sizeof (ib)); - r =amdgpu_ib_get (adev,NULL ,256 , -AMDGPU_IB_POOL_DIRECT , &ib); + + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,256 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_SDMA_RING_TEST );if (r) goto err0; - ib.ptr[0 ] =SDMA_PKT_HEADER_OP (SDMA_OP_WRITE ) | + ib = &job->ibs[0 ]; + ib->ptr[0 ] =SDMA_PKT_HEADER_OP (SDMA_OP_WRITE ) |SDMA_PKT_HEADER_SUB_OP (SDMA_SUBOP_WRITE_LINEAR ); - ib.ptr[1 ] =lower_32_bits (gpu_addr); - ib.ptr[2 ] =upper_32_bits (gpu_addr); - ib.ptr[3 ] =SDMA_PKT_WRITE_UNTILED_DW_3_COUNT (1 ); - ib.ptr[4 ] =0xDEADBEEF ; - ib.ptr[5 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.ptr[6 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.ptr[7 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.length_dw =8 ; - - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (r) + ib->ptr[1 ] =lower_32_bits (gpu_addr); + ib->ptr[2 ] =upper_32_bits (gpu_addr); + ib->ptr[3 ] =SDMA_PKT_WRITE_UNTILED_DW_3_COUNT (1 ); + ib->ptr[4 ] =0xDEADBEEF ; + ib->ptr[5 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->ptr[6 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->ptr[7 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->length_dw =8 ; + + r =amdgpu_job_submit_direct (job, ring, &f); +if (r) { +amdgpu_job_free (job); goto err1; + } r =dma_fence_wait_timeout (f, false, timeout);if (r ==0 ) {@@ -906,7 +911,6 @@ static int sdma_v3_0_ring_test_ib(struct amdgpu_ring *ring, long timeout)else r = -EINVAL ; err1: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f); err0:amdgpu_device_wb_free (adev, index);drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c +21
-17@@ -1516,7 +1516,8 @@ static int sdma_v4_0_ring_test_ring(struct amdgpu_ring *ring)static int sdma_v4_0_ring_test_ib (struct amdgpu_ring *ring,long timeout) {struct amdgpu_device *adev = ring->adev; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ;unsigned index;long r;@@ -1530,26 +1531,30 @@ static int sdma_v4_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) gpu_addr = adev->wb.gpu_addr + (index *4 ); tmp =0xCAFEDEAD ; adev->wb.wb[index] =cpu_to_le32 (tmp); -memset (&ib,0 ,sizeof (ib)); - r =amdgpu_ib_get (adev,NULL ,256 , -AMDGPU_IB_POOL_DIRECT , &ib); + + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,256 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_SDMA_RING_TEST );if (r) goto err0; - ib.ptr[0 ] =SDMA_PKT_HEADER_OP (SDMA_OP_WRITE ) | + ib = &job->ibs[0 ]; + ib->ptr[0 ] =SDMA_PKT_HEADER_OP (SDMA_OP_WRITE ) |SDMA_PKT_HEADER_SUB_OP (SDMA_SUBOP_WRITE_LINEAR ); - ib.ptr[1 ] =lower_32_bits (gpu_addr); - ib.ptr[2 ] =upper_32_bits (gpu_addr); - ib.ptr[3 ] =SDMA_PKT_WRITE_UNTILED_DW_3_COUNT (0 ); - ib.ptr[4 ] =0xDEADBEEF ; - ib.ptr[5 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.ptr[6 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.ptr[7 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.length_dw =8 ; - - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (r) + ib->ptr[1 ] =lower_32_bits (gpu_addr); + ib->ptr[2 ] =upper_32_bits (gpu_addr); + ib->ptr[3 ] =SDMA_PKT_WRITE_UNTILED_DW_3_COUNT (0 ); + ib->ptr[4 ] =0xDEADBEEF ; + ib->ptr[5 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->ptr[6 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->ptr[7 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->length_dw =8 ; + + r =amdgpu_job_submit_direct (job, ring, &f); +if (r) { +amdgpu_job_free (job); goto err1; + } r =dma_fence_wait_timeout (f, false, timeout);if (r ==0 ) {@@ -1565,7 +1570,6 @@ static int sdma_v4_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) r = -EINVAL ; err1: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f); err0:amdgpu_device_wb_free (adev, index);drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c +21
-17@@ -1112,7 +1112,8 @@ static int sdma_v4_4_2_ring_test_ring(struct amdgpu_ring *ring)static int sdma_v4_4_2_ring_test_ib (struct amdgpu_ring *ring,long timeout) {struct amdgpu_device *adev = ring->adev; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ;unsigned index;long r;@@ -1126,26 +1127,30 @@ static int sdma_v4_4_2_ring_test_ib(struct amdgpu_ring *ring, long timeout) gpu_addr = adev->wb.gpu_addr + (index *4 ); tmp =0xCAFEDEAD ; adev->wb.wb[index] =cpu_to_le32 (tmp); -memset (&ib,0 ,sizeof (ib)); - r =amdgpu_ib_get (adev,NULL ,256 , -AMDGPU_IB_POOL_DIRECT , &ib); + + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,256 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_SDMA_RING_TEST );if (r) goto err0; - ib.ptr[0 ] =SDMA_PKT_HEADER_OP (SDMA_OP_WRITE ) | + ib = &job->ibs[0 ]; + ib->ptr[0 ] =SDMA_PKT_HEADER_OP (SDMA_OP_WRITE ) |SDMA_PKT_HEADER_SUB_OP (SDMA_SUBOP_WRITE_LINEAR ); - ib.ptr[1 ] =lower_32_bits (gpu_addr); - ib.ptr[2 ] =upper_32_bits (gpu_addr); - ib.ptr[3 ] =SDMA_PKT_WRITE_UNTILED_DW_3_COUNT (0 ); - ib.ptr[4 ] =0xDEADBEEF ; - ib.ptr[5 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.ptr[6 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.ptr[7 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.length_dw =8 ; - - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (r) + ib->ptr[1 ] =lower_32_bits (gpu_addr); + ib->ptr[2 ] =upper_32_bits (gpu_addr); + ib->ptr[3 ] =SDMA_PKT_WRITE_UNTILED_DW_3_COUNT (0 ); + ib->ptr[4 ] =0xDEADBEEF ; + ib->ptr[5 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->ptr[6 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->ptr[7 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->length_dw =8 ; + + r =amdgpu_job_submit_direct (job, ring, &f); +if (r) { +amdgpu_job_free (job); goto err1; + } r =dma_fence_wait_timeout (f, false, timeout);if (r ==0 ) {@@ -1161,7 +1166,6 @@ static int sdma_v4_4_2_ring_test_ib(struct amdgpu_ring *ring, long timeout) r = -EINVAL ; err1: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f); err0:amdgpu_device_wb_free (adev, index);drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c +20
-17@@ -1074,7 +1074,8 @@ static int sdma_v5_0_ring_test_ring(struct amdgpu_ring *ring)static int sdma_v5_0_ring_test_ib (struct amdgpu_ring *ring,long timeout) {struct amdgpu_device *adev = ring->adev; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ;unsigned index;long r;@@ -1082,7 +1083,6 @@ static int sdma_v5_0_ring_test_ib(struct amdgpu_ring *ring, long timeout)u64 gpu_addr; tmp =0xCAFEDEAD ; -memset (&ib,0 ,sizeof (ib)); r =amdgpu_device_wb_get (adev, &index);if (r) {@@ -1093,27 +1093,31 @@ static int sdma_v5_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) gpu_addr = adev->wb.gpu_addr + (index *4 ); adev->wb.wb[index] =cpu_to_le32 (tmp); - r =amdgpu_ib_get (adev,NULL ,256 , -AMDGPU_IB_POOL_DIRECT , &ib); + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,256 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_SDMA_RING_TEST );if (r) {drm_err (adev_to_drm (adev),"failed to get ib (%ld).\n" , r); goto err0; } - ib.ptr[0 ] =SDMA_PKT_HEADER_OP (SDMA_OP_WRITE ) | + ib = &job->ibs[0 ]; + ib->ptr[0 ] =SDMA_PKT_HEADER_OP (SDMA_OP_WRITE ) |SDMA_PKT_HEADER_SUB_OP (SDMA_SUBOP_WRITE_LINEAR ); - ib.ptr[1 ] =lower_32_bits (gpu_addr); - ib.ptr[2 ] =upper_32_bits (gpu_addr); - ib.ptr[3 ] =SDMA_PKT_WRITE_UNTILED_DW_3_COUNT (0 ); - ib.ptr[4 ] =0xDEADBEEF ; - ib.ptr[5 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.ptr[6 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.ptr[7 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.length_dw =8 ; - - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (r) + ib->ptr[1 ] =lower_32_bits (gpu_addr); + ib->ptr[2 ] =upper_32_bits (gpu_addr); + ib->ptr[3 ] =SDMA_PKT_WRITE_UNTILED_DW_3_COUNT (0 ); + ib->ptr[4 ] =0xDEADBEEF ; + ib->ptr[5 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->ptr[6 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->ptr[7 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->length_dw =8 ; + + r =amdgpu_job_submit_direct (job, ring, &f); +if (r) { +amdgpu_job_free (job); goto err1; + } r =dma_fence_wait_timeout (f, false, timeout);if (r ==0 ) {@@ -1133,7 +1137,6 @@ static int sdma_v5_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) r = -EINVAL ; err1: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f); err0:amdgpu_device_wb_free (adev, index);drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c +20
-16@@ -974,7 +974,8 @@ static int sdma_v5_2_ring_test_ring(struct amdgpu_ring *ring)static int sdma_v5_2_ring_test_ib (struct amdgpu_ring *ring,long timeout) {struct amdgpu_device *adev = ring->adev; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ;unsigned index;long r;@@ -982,7 +983,6 @@ static int sdma_v5_2_ring_test_ib(struct amdgpu_ring *ring, long timeout)u64 gpu_addr; tmp =0xCAFEDEAD ; -memset (&ib,0 ,sizeof (ib)); r =amdgpu_device_wb_get (adev, &index);if (r) {@@ -993,26 +993,31 @@ static int sdma_v5_2_ring_test_ib(struct amdgpu_ring *ring, long timeout) gpu_addr = adev->wb.gpu_addr + (index *4 ); adev->wb.wb[index] =cpu_to_le32 (tmp); - r =amdgpu_ib_get (adev,NULL ,256 ,AMDGPU_IB_POOL_DIRECT , &ib); + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,256 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_SDMA_RING_TEST );if (r) {drm_err (adev_to_drm (adev),"failed to get ib (%ld).\n" , r); goto err0; } - ib.ptr[0 ] =SDMA_PKT_HEADER_OP (SDMA_OP_WRITE ) | + ib = &job->ibs[0 ]; + ib->ptr[0 ] =SDMA_PKT_HEADER_OP (SDMA_OP_WRITE ) |SDMA_PKT_HEADER_SUB_OP (SDMA_SUBOP_WRITE_LINEAR ); - ib.ptr[1 ] =lower_32_bits (gpu_addr); - ib.ptr[2 ] =upper_32_bits (gpu_addr); - ib.ptr[3 ] =SDMA_PKT_WRITE_UNTILED_DW_3_COUNT (0 ); - ib.ptr[4 ] =0xDEADBEEF ; - ib.ptr[5 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.ptr[6 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.ptr[7 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.length_dw =8 ; - - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (r) + ib->ptr[1 ] =lower_32_bits (gpu_addr); + ib->ptr[2 ] =upper_32_bits (gpu_addr); + ib->ptr[3 ] =SDMA_PKT_WRITE_UNTILED_DW_3_COUNT (0 ); + ib->ptr[4 ] =0xDEADBEEF ; + ib->ptr[5 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->ptr[6 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->ptr[7 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->length_dw =8 ; + + r =amdgpu_job_submit_direct (job, ring, &f); +if (r) { +amdgpu_job_free (job); goto err1; + } r =dma_fence_wait_timeout (f, false, timeout);if (r ==0 ) {@@ -1032,7 +1037,6 @@ static int sdma_v5_2_ring_test_ib(struct amdgpu_ring *ring, long timeout) r = -EINVAL ; err1: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f); err0:amdgpu_device_wb_free (adev, index);drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c +20
-16@@ -981,7 +981,8 @@ static int sdma_v6_0_ring_test_ring(struct amdgpu_ring *ring)static int sdma_v6_0_ring_test_ib (struct amdgpu_ring *ring,long timeout) {struct amdgpu_device *adev = ring->adev; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ;unsigned index;long r;@@ -989,7 +990,6 @@ static int sdma_v6_0_ring_test_ib(struct amdgpu_ring *ring, long timeout)u64 gpu_addr; tmp =0xCAFEDEAD ; -memset (&ib,0 ,sizeof (ib)); r =amdgpu_device_wb_get (adev, &index);if (r) {@@ -1000,26 +1000,31 @@ static int sdma_v6_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) gpu_addr = adev->wb.gpu_addr + (index *4 ); adev->wb.wb[index] =cpu_to_le32 (tmp); - r =amdgpu_ib_get (adev,NULL ,256 ,AMDGPU_IB_POOL_DIRECT , &ib); + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,256 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_SDMA_RING_TEST );if (r) {drm_err (adev_to_drm (adev),"failed to get ib (%ld).\n" , r); goto err0; } - ib.ptr[0 ] =SDMA_PKT_COPY_LINEAR_HEADER_OP (SDMA_OP_WRITE ) | + ib = &job->ibs[0 ]; + ib->ptr[0 ] =SDMA_PKT_COPY_LINEAR_HEADER_OP (SDMA_OP_WRITE ) |SDMA_PKT_COPY_LINEAR_HEADER_SUB_OP (SDMA_SUBOP_WRITE_LINEAR ); - ib.ptr[1 ] =lower_32_bits (gpu_addr); - ib.ptr[2 ] =upper_32_bits (gpu_addr); - ib.ptr[3 ] =SDMA_PKT_WRITE_UNTILED_DW_3_COUNT (0 ); - ib.ptr[4 ] =0xDEADBEEF ; - ib.ptr[5 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.ptr[6 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.ptr[7 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.length_dw =8 ; - - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (r) + ib->ptr[1 ] =lower_32_bits (gpu_addr); + ib->ptr[2 ] =upper_32_bits (gpu_addr); + ib->ptr[3 ] =SDMA_PKT_WRITE_UNTILED_DW_3_COUNT (0 ); + ib->ptr[4 ] =0xDEADBEEF ; + ib->ptr[5 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->ptr[6 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->ptr[7 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->length_dw =8 ; + + r =amdgpu_job_submit_direct (job, ring, &f); +if (r) { +amdgpu_job_free (job); goto err1; + } r =dma_fence_wait_timeout (f, false, timeout);if (r ==0 ) {@@ -1039,7 +1044,6 @@ static int sdma_v6_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) r = -EINVAL ; err1: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f); err0:amdgpu_device_wb_free (adev, index);drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c +20
-16@@ -997,7 +997,8 @@ static int sdma_v7_0_ring_test_ring(struct amdgpu_ring *ring)static int sdma_v7_0_ring_test_ib (struct amdgpu_ring *ring,long timeout) {struct amdgpu_device *adev = ring->adev; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ;unsigned index;long r;@@ -1005,7 +1006,6 @@ static int sdma_v7_0_ring_test_ib(struct amdgpu_ring *ring, long timeout)u64 gpu_addr; tmp =0xCAFEDEAD ; -memset (&ib,0 ,sizeof (ib)); r =amdgpu_device_wb_get (adev, &index);if (r) {@@ -1016,26 +1016,31 @@ static int sdma_v7_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) gpu_addr = adev->wb.gpu_addr + (index *4 ); adev->wb.wb[index] =cpu_to_le32 (tmp); - r =amdgpu_ib_get (adev,NULL ,256 ,AMDGPU_IB_POOL_DIRECT , &ib); + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,256 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_SDMA_RING_TEST );if (r) {drm_err (adev_to_drm (adev),"failed to get ib (%ld).\n" , r); goto err0; } - ib.ptr[0 ] =SDMA_PKT_COPY_LINEAR_HEADER_OP (SDMA_OP_WRITE ) | + ib = &job->ibs[0 ]; + ib->ptr[0 ] =SDMA_PKT_COPY_LINEAR_HEADER_OP (SDMA_OP_WRITE ) |SDMA_PKT_COPY_LINEAR_HEADER_SUB_OP (SDMA_SUBOP_WRITE_LINEAR ); - ib.ptr[1 ] =lower_32_bits (gpu_addr); - ib.ptr[2 ] =upper_32_bits (gpu_addr); - ib.ptr[3 ] =SDMA_PKT_WRITE_UNTILED_DW_3_COUNT (0 ); - ib.ptr[4 ] =0xDEADBEEF ; - ib.ptr[5 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.ptr[6 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.ptr[7 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.length_dw =8 ; - - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (r) + ib->ptr[1 ] =lower_32_bits (gpu_addr); + ib->ptr[2 ] =upper_32_bits (gpu_addr); + ib->ptr[3 ] =SDMA_PKT_WRITE_UNTILED_DW_3_COUNT (0 ); + ib->ptr[4 ] =0xDEADBEEF ; + ib->ptr[5 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->ptr[6 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->ptr[7 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->length_dw =8 ; + + r =amdgpu_job_submit_direct (job, ring, &f); +if (r) { +amdgpu_job_free (job); goto err1; + } r =dma_fence_wait_timeout (f, false, timeout);if (r ==0 ) {@@ -1055,7 +1060,6 @@ static int sdma_v7_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) r = -EINVAL ; err1: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f); err0:amdgpu_device_wb_free (adev, index);drivers/gpu/drm/amd/amdgpu/sdma_v7_1.c +20
-16@@ -987,7 +987,8 @@ static int sdma_v7_1_ring_test_ring(struct amdgpu_ring *ring)static int sdma_v7_1_ring_test_ib (struct amdgpu_ring *ring,long timeout) {struct amdgpu_device *adev = ring->adev; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ;unsigned index;long r;@@ -995,7 +996,6 @@ static int sdma_v7_1_ring_test_ib(struct amdgpu_ring *ring, long timeout)u64 gpu_addr; tmp =0xCAFEDEAD ; -memset (&ib,0 ,sizeof (ib)); r =amdgpu_device_wb_get (adev, &index);if (r) {@@ -1006,26 +1006,31 @@ static int sdma_v7_1_ring_test_ib(struct amdgpu_ring *ring, long timeout) gpu_addr = adev->wb.gpu_addr + (index *4 ); adev->wb.wb[index] =cpu_to_le32 (tmp); - r =amdgpu_ib_get (adev,NULL ,256 ,AMDGPU_IB_POOL_DIRECT , &ib); + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,256 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_SDMA_RING_TEST );if (r) {DRM_ERROR ("amdgpu: failed to get ib (%ld).\n" , r); goto err0; } - ib.ptr[0 ] =SDMA_PKT_COPY_LINEAR_HEADER_OP (SDMA_OP_WRITE ) | + ib = &job->ibs[0 ]; + ib->ptr[0 ] =SDMA_PKT_COPY_LINEAR_HEADER_OP (SDMA_OP_WRITE ) |SDMA_PKT_COPY_LINEAR_HEADER_SUB_OP (SDMA_SUBOP_WRITE_LINEAR ); - ib.ptr[1 ] =lower_32_bits (gpu_addr); - ib.ptr[2 ] =upper_32_bits (gpu_addr); - ib.ptr[3 ] =SDMA_PKT_WRITE_UNTILED_DW_3_COUNT (0 ); - ib.ptr[4 ] =0xDEADBEEF ; - ib.ptr[5 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.ptr[6 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.ptr[7 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.length_dw =8 ; - - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (r) + ib->ptr[1 ] =lower_32_bits (gpu_addr); + ib->ptr[2 ] =upper_32_bits (gpu_addr); + ib->ptr[3 ] =SDMA_PKT_WRITE_UNTILED_DW_3_COUNT (0 ); + ib->ptr[4 ] =0xDEADBEEF ; + ib->ptr[5 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->ptr[6 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->ptr[7 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->length_dw =8 ; + + r =amdgpu_job_submit_direct (job, ring, &f); +if (r) { +amdgpu_job_free (job); goto err1; + } r =dma_fence_wait_timeout (f, false, timeout);if (r ==0 ) {@@ -1045,7 +1050,6 @@ static int sdma_v7_1_ring_test_ib(struct amdgpu_ring *ring, long timeout) r = -EINVAL ; err1: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f); err0:amdgpu_device_wb_free (adev, index);drivers/gpu/drm/amd/amdgpu/si_dma.c +17
-12@@ -259,7 +259,8 @@ static int si_dma_ring_test_ring(struct amdgpu_ring *ring)static int si_dma_ring_test_ib (struct amdgpu_ring *ring,long timeout) {struct amdgpu_device *adev = ring->adev; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ;unsigned index;u32 tmp =0 ;@@ -273,20 +274,25 @@ static int si_dma_ring_test_ib(struct amdgpu_ring *ring, long timeout) gpu_addr = adev->wb.gpu_addr + (index *4 ); tmp =0xCAFEDEAD ; adev->wb.wb[index] =cpu_to_le32 (tmp); -memset (&ib,0 ,sizeof (ib)); - r =amdgpu_ib_get (adev,NULL ,256 , -AMDGPU_IB_POOL_DIRECT , &ib); + + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,256 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_SDMA_RING_TEST );if (r) goto err0; - ib.ptr[0 ] =DMA_PACKET (DMA_PACKET_WRITE ,0 ,0 ,0 ,1 ); - ib.ptr[1 ] =lower_32_bits (gpu_addr); - ib.ptr[2 ] =upper_32_bits (gpu_addr) &0xff ; - ib.ptr[3 ] =0xDEADBEEF ; - ib.length_dw =4 ; - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (r) + ib = &job->ibs[0 ]; + ib->ptr[0 ] =DMA_PACKET (DMA_PACKET_WRITE ,0 ,0 ,0 ,1 ); + ib->ptr[1 ] =lower_32_bits (gpu_addr); + ib->ptr[2 ] =upper_32_bits (gpu_addr) &0xff ; + ib->ptr[3 ] =0xDEADBEEF ; + ib->length_dw =4 ; + + r =amdgpu_job_submit_direct (job, ring, &f); +if (r) { +amdgpu_job_free (job); goto err1; + } r =dma_fence_wait_timeout (f, false, timeout);if (r ==0 ) {@@ -302,7 +308,6 @@ static int si_dma_ring_test_ib(struct amdgpu_ring *ring, long timeout) r = -EINVAL ; err1: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f); err0:amdgpu_device_wb_free (adev, index);
Re: [PATCH 03/12] drm/amdgpu: switch all IPs to using job for IBs
Quoted 97 lines · Pierre-Eric Pelloux-Prayer
Quoted 73 lines · Alex Deucher
Switch to using a job structure for IBs.
Acked-by Christian König <[email protected]>Signed-off-by Alex Deucher <[email protected]>--- drivers/gpu/drm/amd/amdgpu/amdgpu_vpe.c | 37 +++--- drivers/gpu/drm/amd/amdgpu/cik_sdma.c | 31 ++--- drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c | 29 ++--- drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c | 29 ++--- drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c | 29 ++--- drivers/gpu/drm/amd/amdgpu/gfx_v12_1.c | 29 ++--- drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c | 24 ++-- drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c | 25 ++-- drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c | 139 ++++++++++++----------- drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c | 138 +++++++++++----------- drivers/gpu/drm/amd/amdgpu/gfx_v9_4_2.c | 26 ++--- drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c | 29 ++--- drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c | 38 ++++--- drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c | 38 ++++--- drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c | 38 ++++--- drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c | 38 ++++--- drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c | 37 +++--- drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c | 36 +++--- drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c | 36 +++--- drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c | 36 +++--- drivers/gpu/drm/amd/amdgpu/sdma_v7_1.c | 36 +++--- drivers/gpu/drm/amd/amdgpu/si_dma.c | 29 +++-- 22 files changed, 500 insertions(+), 427 deletions(-)drivers/gpu/drm/amd/amdgpu/amdgpu_vpe.c +12
-15@@ -817,7 +817,8 @@ static int vpe_ring_test_ib(struct amdgpu_ring *ring, long timeout) {struct amdgpu_device *adev = ring->adev;const uint32_t test_pattern =0xdeadbeef ; -struct amdgpu_ib ib = {}; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ;uint32_t index;uint64_t wb_addr;@@ -832,23 +833,28 @@ static int vpe_ring_test_ib(struct amdgpu_ring *ring, long timeout) adev->wb.wb[index] =0 ; wb_addr = adev->wb.gpu_addr + (index *4 ); - ret =amdgpu_ib_get (adev,NULL ,256 ,AMDGPU_IB_POOL_DIRECT , &ib); + ret =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,256 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_VPE_RING_TEST );if (ret) goto err0; - - ib.ptr[0 ] =VPE_CMD_HEADER (VPE_CMD_OPCODE_FENCE ,0 ); - ib.ptr[1 ] =lower_32_bits (wb_addr); - ib.ptr[2 ] =upper_32_bits (wb_addr); - ib.ptr[3 ] = test_pattern; - ib.ptr[4 ] =VPE_CMD_HEADER (VPE_CMD_OPCODE_NOP ,0 ); - ib.ptr[5 ] =VPE_CMD_HEADER (VPE_CMD_OPCODE_NOP ,0 ); - ib.ptr[6 ] =VPE_CMD_HEADER (VPE_CMD_OPCODE_NOP ,0 ); - ib.ptr[7 ] =VPE_CMD_HEADER (VPE_CMD_OPCODE_NOP ,0 ); - ib.length_dw =8 ; - - ret =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (ret) + ib = &job->ibs[0 ]; + + ib->ptr[0 ] =VPE_CMD_HEADER (VPE_CMD_OPCODE_FENCE ,0 ); + ib->ptr[1 ] =lower_32_bits (wb_addr); + ib->ptr[2 ] =upper_32_bits (wb_addr); + ib->ptr[3 ] = test_pattern; + ib->ptr[4 ] =VPE_CMD_HEADER (VPE_CMD_OPCODE_NOP ,0 );drivers/gpu/drm/amd/amdgpu/amdgpu_vpe.c static int vpe_ring_test_ib(struct amdgpu_ring *ring, long timeout) · line 857
Quoted 10 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_vpe.c +9
-0+ ib->ptr[5 ] =VPE_CMD_HEADER (VPE_CMD_OPCODE_NOP ,0 ); + ib->ptr[6 ] =VPE_CMD_HEADER (VPE_CMD_OPCODE_NOP ,0 ); + ib->ptr[7 ] =VPE_CMD_HEADER (VPE_CMD_OPCODE_NOP ,0 ); + ib->length_dw =8 ; + + ret =amdgpu_job_submit_direct (job, ring, &f); +if (ret) { +amdgpu_job_free (job); goto err1; + }This is a nice cleanup. What about going one step further and provide a helper like:
u32 test_dws[] = { VPE_CMD_HEADER(VPE_CMD_OPCODE_FENCE, 0), lower_32_bits(wb_addr), ... }; ret = amdgpu_ring_run_dwords(ring, ARRAY_SIZE(test_dws), test_dws,
Quoted 3 lines
timeout);
Because that's what most
_ring_test_ibfunction do.
I can look into that as a follow up series.
Alex
Quoted 1,820 lines
Thanks,
Pierre-EricQuoted 1,817 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_vpe.c +0
-1ret =dma_fence_wait_timeout (f, false, timeout);if (ret <=0 ) {@@ -859,7 +865,6 @@ static int vpe_ring_test_ib(struct amdgpu_ring *ring, long timeout) ret = (le32_to_cpu (adev->wb.wb[index]) == test_pattern) ?0 : -EINVAL ; err1: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f); err0:amdgpu_device_wb_free (adev, index);drivers/gpu/drm/amd/amdgpu/cik_sdma.c +18
-13@@ -652,7 +652,8 @@ static int cik_sdma_ring_test_ring(struct amdgpu_ring *ring)static int cik_sdma_ring_test_ib (struct amdgpu_ring *ring,long timeout) {struct amdgpu_device *adev = ring->adev; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ;unsigned index;u32 tmp =0 ;@@ -666,22 +667,27 @@ static int cik_sdma_ring_test_ib(struct amdgpu_ring *ring, long timeout) gpu_addr = adev->wb.gpu_addr + (index *4 ); tmp =0xCAFEDEAD ; adev->wb.wb[index] =cpu_to_le32 (tmp); -memset (&ib,0 ,sizeof (ib)); - r =amdgpu_ib_get (adev,NULL ,256 , -AMDGPU_IB_POOL_DIRECT , &ib); + + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,256 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_SDMA_RING_TEST );if (r) goto err0; + ib = &job->ibs[0 ]; - ib.ptr[0 ] =SDMA_PACKET (SDMA_OPCODE_WRITE , + ib->ptr[0 ] =SDMA_PACKET (SDMA_OPCODE_WRITE ,SDMA_WRITE_SUB_OPCODE_LINEAR ,0 ); - ib.ptr[1 ] =lower_32_bits (gpu_addr); - ib.ptr[2 ] =upper_32_bits (gpu_addr); - ib.ptr[3 ] =1 ; - ib.ptr[4 ] =0xDEADBEEF ; - ib.length_dw =5 ; - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (r) + ib->ptr[1 ] =lower_32_bits (gpu_addr); + ib->ptr[2 ] =upper_32_bits (gpu_addr); + ib->ptr[3 ] =1 ; + ib->ptr[4 ] =0xDEADBEEF ; + ib->length_dw =5 ; + + r =amdgpu_job_submit_direct (job, ring, &f); +if (r) { +amdgpu_job_free (job); goto err1; + } r =dma_fence_wait_timeout (f, false, timeout);if (r ==0 ) {@@ -697,7 +703,6 @@ static int cik_sdma_ring_test_ib(struct amdgpu_ring *ring, long timeout) r = -EINVAL ; err1: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f); err0:amdgpu_device_wb_free (adev, index);drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c +16
-13@@ -4071,15 +4071,14 @@ static int gfx_v10_0_ring_test_ring(struct amdgpu_ring *ring)static int gfx_v10_0_ring_test_ib (struct amdgpu_ring *ring,long timeout) {struct amdgpu_device *adev = ring->adev; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ;unsigned int index;uint64_t gpu_addr;uint32_t *cpu_ptr;long r; -memset (&ib,0 ,sizeof (ib)); - r =amdgpu_device_wb_get (adev, &index);if (r)return r;@@ -4088,22 +4087,27 @@ static int gfx_v10_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) adev->wb.wb[index] =cpu_to_le32 (0xCAFEDEAD ); cpu_ptr = &adev->wb.wb[index]; - r =amdgpu_ib_get (adev,NULL ,20 ,AMDGPU_IB_POOL_DIRECT , &ib); + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,20 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_GFX_RING_TEST );if (r) {drm_err (adev_to_drm (adev),"failed to get ib (%ld).\n" , r); goto err1; } + ib = &job->ibs[0 ]; - ib.ptr[0 ] =PACKET3 (PACKET3_WRITE_DATA ,3 ); - ib.ptr[1 ] =WRITE_DATA_DST_SEL (5 ) |WR_CONFIRM ; - ib.ptr[2 ] =lower_32_bits (gpu_addr); - ib.ptr[3 ] =upper_32_bits (gpu_addr); - ib.ptr[4 ] =0xDEADBEEF ; - ib.length_dw =5 ; + ib->ptr[0 ] =PACKET3 (PACKET3_WRITE_DATA ,3 ); + ib->ptr[1 ] =WRITE_DATA_DST_SEL (5 ) |WR_CONFIRM ; + ib->ptr[2 ] =lower_32_bits (gpu_addr); + ib->ptr[3 ] =upper_32_bits (gpu_addr); + ib->ptr[4 ] =0xDEADBEEF ; + ib->length_dw =5 ; - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (r) + r =amdgpu_job_submit_direct (job, ring, &f); +if (r) { +amdgpu_job_free (job); goto err2; + } r =dma_fence_wait_timeout (f, false, timeout);if (r ==0 ) {@@ -4118,7 +4122,6 @@ static int gfx_v10_0_ring_test_ib(struct amdgpu_ring *ring, long timeout)else r = -EINVAL ; err2: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f); err1:amdgpu_device_wb_free (adev, index);drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c +16
-13@@ -604,7 +604,8 @@ static int gfx_v11_0_ring_test_ring(struct amdgpu_ring *ring)static int gfx_v11_0_ring_test_ib (struct amdgpu_ring *ring,long timeout) {struct amdgpu_device *adev = ring->adev; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ;unsigned index;uint64_t gpu_addr;@@ -616,8 +617,6 @@ static int gfx_v11_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) ring->funcs->type == AMDGPU_RING_TYPE_KIQ)return 0 ; -memset (&ib,0 ,sizeof (ib)); - r =amdgpu_device_wb_get (adev, &index);if (r)return r;@@ -626,22 +625,27 @@ static int gfx_v11_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) adev->wb.wb[index] =cpu_to_le32 (0xCAFEDEAD ); cpu_ptr = &adev->wb.wb[index]; - r =amdgpu_ib_get (adev,NULL ,20 ,AMDGPU_IB_POOL_DIRECT , &ib); + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,20 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_GFX_RING_TEST );if (r) {drm_err (adev_to_drm (adev),"failed to get ib (%ld).\n" , r); goto err1; } + ib = &job->ibs[0 ]; - ib.ptr[0 ] =PACKET3 (PACKET3_WRITE_DATA ,3 ); - ib.ptr[1 ] =WRITE_DATA_DST_SEL (5 ) |WR_CONFIRM ; - ib.ptr[2 ] =lower_32_bits (gpu_addr); - ib.ptr[3 ] =upper_32_bits (gpu_addr); - ib.ptr[4 ] =0xDEADBEEF ; - ib.length_dw =5 ; + ib->ptr[0 ] =PACKET3 (PACKET3_WRITE_DATA ,3 ); + ib->ptr[1 ] =WRITE_DATA_DST_SEL (5 ) |WR_CONFIRM ; + ib->ptr[2 ] =lower_32_bits (gpu_addr); + ib->ptr[3 ] =upper_32_bits (gpu_addr); + ib->ptr[4 ] =0xDEADBEEF ; + ib->length_dw =5 ; - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (r) + r =amdgpu_job_submit_direct (job, ring, &f); +if (r) { +amdgpu_job_free (job); goto err2; + } r =dma_fence_wait_timeout (f, false, timeout);if (r ==0 ) {@@ -656,7 +660,6 @@ static int gfx_v11_0_ring_test_ib(struct amdgpu_ring *ring, long timeout)else r = -EINVAL ; err2: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f); err1:amdgpu_device_wb_free (adev, index);drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c +16
-13@@ -493,7 +493,8 @@ static int gfx_v12_0_ring_test_ring(struct amdgpu_ring *ring)static int gfx_v12_0_ring_test_ib (struct amdgpu_ring *ring,long timeout) {struct amdgpu_device *adev = ring->adev; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ;unsigned index;uint64_t gpu_addr;@@ -505,8 +506,6 @@ static int gfx_v12_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) ring->funcs->type == AMDGPU_RING_TYPE_KIQ)return 0 ; -memset (&ib,0 ,sizeof (ib)); - r =amdgpu_device_wb_get (adev, &index);if (r)return r;@@ -515,22 +514,27 @@ static int gfx_v12_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) adev->wb.wb[index] =cpu_to_le32 (0xCAFEDEAD ); cpu_ptr = &adev->wb.wb[index]; - r =amdgpu_ib_get (adev,NULL ,16 ,AMDGPU_IB_POOL_DIRECT , &ib); + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,16 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_GFX_RING_TEST );if (r) {drm_err (adev_to_drm (adev),"failed to get ib (%ld).\n" , r); goto err1; } + ib = &job->ibs[0 ]; - ib.ptr[0 ] =PACKET3 (PACKET3_WRITE_DATA ,3 ); - ib.ptr[1 ] =WRITE_DATA_DST_SEL (5 ) |WR_CONFIRM ; - ib.ptr[2 ] =lower_32_bits (gpu_addr); - ib.ptr[3 ] =upper_32_bits (gpu_addr); - ib.ptr[4 ] =0xDEADBEEF ; - ib.length_dw =5 ; + ib->ptr[0 ] =PACKET3 (PACKET3_WRITE_DATA ,3 ); + ib->ptr[1 ] =WRITE_DATA_DST_SEL (5 ) |WR_CONFIRM ; + ib->ptr[2 ] =lower_32_bits (gpu_addr); + ib->ptr[3 ] =upper_32_bits (gpu_addr); + ib->ptr[4 ] =0xDEADBEEF ; + ib->length_dw =5 ; - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (r) + r =amdgpu_job_submit_direct (job, ring, &f); +if (r) { +amdgpu_job_free (job); goto err2; + } r =dma_fence_wait_timeout (f, false, timeout);if (r ==0 ) {@@ -545,7 +549,6 @@ static int gfx_v12_0_ring_test_ib(struct amdgpu_ring *ring, long timeout)else r = -EINVAL ; err2: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f); err1:amdgpu_device_wb_free (adev, index);drivers/gpu/drm/amd/amdgpu/gfx_v12_1.c +16
-13@@ -307,7 +307,8 @@ static int gfx_v12_1_ring_test_ring(struct amdgpu_ring *ring)static int gfx_v12_1_ring_test_ib (struct amdgpu_ring *ring,long timeout) {struct amdgpu_device *adev = ring->adev; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ;unsigned index;uint64_t gpu_addr;@@ -319,8 +320,6 @@ static int gfx_v12_1_ring_test_ib(struct amdgpu_ring *ring, long timeout) ring->funcs->type == AMDGPU_RING_TYPE_KIQ)return 0 ; -memset (&ib,0 ,sizeof (ib)); - r =amdgpu_device_wb_get (adev, &index);if (r)return r;@@ -329,22 +328,27 @@ static int gfx_v12_1_ring_test_ib(struct amdgpu_ring *ring, long timeout) adev->wb.wb[index] =cpu_to_le32 (0xCAFEDEAD ); cpu_ptr = &adev->wb.wb[index]; - r =amdgpu_ib_get (adev,NULL ,16 ,AMDGPU_IB_POOL_DIRECT , &ib); + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,16 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_GFX_RING_TEST );if (r) {dev_err (adev->dev,"amdgpu: failed to get ib (%ld).\n" , r); goto err1; } + ib = &job->ibs[0 ]; - ib.ptr[0 ] =PACKET3 (PACKET3_WRITE_DATA ,3 ); - ib.ptr[1 ] =WRITE_DATA_DST_SEL (5 ) |WR_CONFIRM ; - ib.ptr[2 ] =lower_32_bits (gpu_addr); - ib.ptr[3 ] =upper_32_bits (gpu_addr); - ib.ptr[4 ] =0xDEADBEEF ; - ib.length_dw =5 ; + ib->ptr[0 ] =PACKET3 (PACKET3_WRITE_DATA ,3 ); + ib->ptr[1 ] =WRITE_DATA_DST_SEL (5 ) |WR_CONFIRM ; + ib->ptr[2 ] =lower_32_bits (gpu_addr); + ib->ptr[3 ] =upper_32_bits (gpu_addr); + ib->ptr[4 ] =0xDEADBEEF ; + ib->length_dw =5 ; - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (r) + r =amdgpu_job_submit_direct (job, ring, &f); +if (r) { +amdgpu_job_free (job); goto err2; + } r =dma_fence_wait_timeout (f, false, timeout);if (r ==0 ) {@@ -359,7 +363,6 @@ static int gfx_v12_1_ring_test_ib(struct amdgpu_ring *ring, long timeout)else r = -EINVAL ; err2: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f); err1:amdgpu_device_wb_free (adev, index);drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c +14
-10@@ -1895,24 +1895,29 @@ static int gfx_v6_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) {struct amdgpu_device *adev = ring->adev;struct dma_fence *f =NULL ; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;uint32_t tmp =0 ;long r;WREG32 (mmSCRATCH_REG0,0xCAFEDEAD ); -memset (&ib,0 ,sizeof (ib)); - r =amdgpu_ib_get (adev,NULL ,256 ,AMDGPU_IB_POOL_DIRECT , &ib); + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,256 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_GFX_RING_TEST );if (r)return r; - ib.ptr[0 ] =PACKET3 (PACKET3_SET_CONFIG_REG ,1 ); - ib.ptr[1 ] = mmSCRATCH_REG0 -PACKET3_SET_CONFIG_REG_START ; - ib.ptr[2 ] =0xDEADBEEF ; - ib.length_dw =3 ; + ib = &job->ibs[0 ]; + ib->ptr[0 ] =PACKET3 (PACKET3_SET_CONFIG_REG ,1 ); + ib->ptr[1 ] = mmSCRATCH_REG0 -PACKET3_SET_CONFIG_REG_START ; + ib->ptr[2 ] =0xDEADBEEF ; + ib->length_dw =3 ; - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (r) + r =amdgpu_job_submit_direct (job, ring, &f); +if (r) { +amdgpu_job_free (job); goto error; + } r =dma_fence_wait_timeout (f, false, timeout);if (r ==0 ) {@@ -1928,7 +1933,6 @@ static int gfx_v6_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) r = -EINVAL ; error: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f);return r; }drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c +15
-10@@ -2291,25 +2291,31 @@ static void gfx_v7_ring_emit_cntxcntl(struct amdgpu_ring *ring, uint32_t flags)static int gfx_v7_0_ring_test_ib (struct amdgpu_ring *ring,long timeout) {struct amdgpu_device *adev = ring->adev; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ;uint32_t tmp =0 ;long r;WREG32 (mmSCRATCH_REG0,0xCAFEDEAD ); -memset (&ib,0 ,sizeof (ib)); - r =amdgpu_ib_get (adev,NULL ,256 ,AMDGPU_IB_POOL_DIRECT , &ib); + + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,256 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_GFX_RING_TEST );if (r)return r; - ib.ptr[0 ] =PACKET3 (PACKET3_SET_UCONFIG_REG ,1 ); - ib.ptr[1 ] = mmSCRATCH_REG0 -PACKET3_SET_UCONFIG_REG_START ; - ib.ptr[2 ] =0xDEADBEEF ; - ib.length_dw =3 ; + ib = &job->ibs[0 ]; + ib->ptr[0 ] =PACKET3 (PACKET3_SET_UCONFIG_REG ,1 ); + ib->ptr[1 ] = mmSCRATCH_REG0 -PACKET3_SET_UCONFIG_REG_START ; + ib->ptr[2 ] =0xDEADBEEF ; + ib->length_dw =3 ; - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (r) + r =amdgpu_job_submit_direct (job, ring, &f); +if (r) { +amdgpu_job_free (job); goto error; + } r =dma_fence_wait_timeout (f, false, timeout);if (r ==0 ) {@@ -2325,7 +2331,6 @@ static int gfx_v7_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) r = -EINVAL ; error: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f);return r; }drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +72
-67@@ -868,9 +868,9 @@ static int gfx_v8_0_ring_test_ring(struct amdgpu_ring *ring)static int gfx_v8_0_ring_test_ib (struct amdgpu_ring *ring,long timeout) {struct amdgpu_device *adev = ring->adev; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ; -unsigned int index;uint64_t gpu_addr;uint32_t tmp;@@ -882,22 +882,26 @@ static int gfx_v8_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) gpu_addr = adev->wb.gpu_addr + (index *4 ); adev->wb.wb[index] =cpu_to_le32 (0xCAFEDEAD ); -memset (&ib,0 ,sizeof (ib)); - r =amdgpu_ib_get (adev,NULL ,20 ,AMDGPU_IB_POOL_DIRECT , &ib); + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,20 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_GFX_RING_TEST );if (r) goto err1; - ib.ptr[0 ] =PACKET3 (PACKET3_WRITE_DATA ,3 ); - ib.ptr[1 ] =WRITE_DATA_DST_SEL (5 ) |WR_CONFIRM ; - ib.ptr[2 ] =lower_32_bits (gpu_addr); - ib.ptr[3 ] =upper_32_bits (gpu_addr); - ib.ptr[4 ] =0xDEADBEEF ; - ib.length_dw =5 ; + ib = &job->ibs[0 ]; + ib->ptr[0 ] =PACKET3 (PACKET3_WRITE_DATA ,3 ); + ib->ptr[1 ] =WRITE_DATA_DST_SEL (5 ) |WR_CONFIRM ; + ib->ptr[2 ] =lower_32_bits (gpu_addr); + ib->ptr[3 ] =upper_32_bits (gpu_addr); + ib->ptr[4 ] =0xDEADBEEF ; + ib->length_dw =5 ; - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (r) + r =amdgpu_job_submit_direct (job, ring, &f); +if (r) { +amdgpu_job_free (job); goto err2; + } r =dma_fence_wait_timeout (f, false, timeout);if (r ==0 ) {@@ -914,7 +918,6 @@ static int gfx_v8_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) r = -EINVAL ; err2: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f); err1:amdgpu_device_wb_free (adev, index);@@ -1474,7 +1477,8 @@ static const u32 sec_ded_counter_registers[] =static int gfx_v8_0_do_edc_gpr_workarounds (struct amdgpu_device *adev) {struct amdgpu_ring *ring = &adev->gfx.compute_ring[0 ]; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ;int r, i;u32 tmp;@@ -1505,106 +1509,108 @@ static int gfx_v8_0_do_edc_gpr_workarounds(struct amdgpu_device *adev) total_size +=sizeof (sgpr_init_compute_shader);/* allocate an indirect buffer to put the commands in */ -memset (&ib,0 ,sizeof (ib)); - r =amdgpu_ib_get (adev,NULL , total_size, -AMDGPU_IB_POOL_DIRECT , &ib); + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL , total_size, +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_RUN_SHADER );if (r) {drm_err (adev_to_drm (adev),"failed to get ib (%d).\n" , r);return r; } + ib = &job->ibs[0 ];/* load the compute shaders */ for (i =0 ; i <ARRAY_SIZE (vgpr_init_compute_shader); i++) - ib.ptr[i + (vgpr_offset /4 )] = vgpr_init_compute_shader[i]; + ib->ptr[i + (vgpr_offset /4 )] = vgpr_init_compute_shader[i];for (i =0 ; i <ARRAY_SIZE (sgpr_init_compute_shader); i++) - ib.ptr[i + (sgpr_offset /4 )] = sgpr_init_compute_shader[i]; + ib->ptr[i + (sgpr_offset /4 )] = sgpr_init_compute_shader[i];/* init the ib length to 0 */ - ib.length_dw =0 ; + ib->length_dw =0 ;/* VGPR */ /* write the register state for the compute dispatch */ for (i =0 ; i <ARRAY_SIZE (vgpr_init_regs); i +=2 ) { - ib.ptr[ib.length_dw++] =PACKET3 (PACKET3_SET_SH_REG ,1 ); - ib.ptr[ib.length_dw++] = vgpr_init_regs[i] -PACKET3_SET_SH_REG_START ; - ib.ptr[ib.length_dw++] = vgpr_init_regs[i +1 ]; + ib->ptr[ib->length_dw++] =PACKET3 (PACKET3_SET_SH_REG ,1 ); + ib->ptr[ib->length_dw++] = vgpr_init_regs[i] -PACKET3_SET_SH_REG_START ; + ib->ptr[ib->length_dw++] = vgpr_init_regs[i +1 ]; }/* write the shader start address: mmCOMPUTE_PGM_LO, mmCOMPUTE_PGM_HI */ - gpu_addr = (ib.gpu_addr + (u64 )vgpr_offset) >>8 ; - ib.ptr[ib.length_dw++] =PACKET3 (PACKET3_SET_SH_REG ,2 ); - ib.ptr[ib.length_dw++] = mmCOMPUTE_PGM_LO -PACKET3_SET_SH_REG_START ; - ib.ptr[ib.length_dw++] =lower_32_bits (gpu_addr); - ib.ptr[ib.length_dw++] =upper_32_bits (gpu_addr); + gpu_addr = (ib->gpu_addr + (u64 )vgpr_offset) >>8 ; + ib->ptr[ib->length_dw++] =PACKET3 (PACKET3_SET_SH_REG ,2 ); + ib->ptr[ib->length_dw++] = mmCOMPUTE_PGM_LO -PACKET3_SET_SH_REG_START ; + ib->ptr[ib->length_dw++] =lower_32_bits (gpu_addr); + ib->ptr[ib->length_dw++] =upper_32_bits (gpu_addr);/* write dispatch packet */ - ib.ptr[ib.length_dw++] =PACKET3 (PACKET3_DISPATCH_DIRECT ,3 ); - ib.ptr[ib.length_dw++] =8 ;/* x */ - ib.ptr[ib.length_dw++] =1 ;/* y */ - ib.ptr[ib.length_dw++] =1 ;/* z */ - ib.ptr[ib.length_dw++] = + ib->ptr[ib->length_dw++] =PACKET3 (PACKET3_DISPATCH_DIRECT ,3 ); + ib->ptr[ib->length_dw++] =8 ;/* x */ + ib->ptr[ib->length_dw++] =1 ;/* y */ + ib->ptr[ib->length_dw++] =1 ;/* z */ + ib->ptr[ib->length_dw++] =REG_SET_FIELD (0 ,COMPUTE_DISPATCH_INITIATOR ,COMPUTE_SHADER_EN ,1 );/* write CS partial flush packet */ - ib.ptr[ib.length_dw++] =PACKET3 (PACKET3_EVENT_WRITE ,0 ); - ib.ptr[ib.length_dw++] =EVENT_TYPE (7 ) |EVENT_INDEX (4 ); + ib->ptr[ib->length_dw++] =PACKET3 (PACKET3_EVENT_WRITE ,0 ); + ib->ptr[ib->length_dw++] =EVENT_TYPE (7 ) |EVENT_INDEX (4 );/* SGPR1 */ /* write the register state for the compute dispatch */ for (i =0 ; i <ARRAY_SIZE (sgpr1_init_regs); i +=2 ) { - ib.ptr[ib.length_dw++] =PACKET3 (PACKET3_SET_SH_REG ,1 ); - ib.ptr[ib.length_dw++] = sgpr1_init_regs[i] -PACKET3_SET_SH_REG_START ; - ib.ptr[ib.length_dw++] = sgpr1_init_regs[i +1 ]; + ib->ptr[ib->length_dw++] =PACKET3 (PACKET3_SET_SH_REG ,1 ); + ib->ptr[ib->length_dw++] = sgpr1_init_regs[i] -PACKET3_SET_SH_REG_START ; + ib->ptr[ib->length_dw++] = sgpr1_init_regs[i +1 ]; }/* write the shader start address: mmCOMPUTE_PGM_LO, mmCOMPUTE_PGM_HI */ - gpu_addr = (ib.gpu_addr + (u64 )sgpr_offset) >>8 ; - ib.ptr[ib.length_dw++] =PACKET3 (PACKET3_SET_SH_REG ,2 ); - ib.ptr[ib.length_dw++] = mmCOMPUTE_PGM_LO -PACKET3_SET_SH_REG_START ; - ib.ptr[ib.length_dw++] =lower_32_bits (gpu_addr); - ib.ptr[ib.length_dw++] =upper_32_bits (gpu_addr); + gpu_addr = (ib->gpu_addr + (u64 )sgpr_offset) >>8 ; + ib->ptr[ib->length_dw++] =PACKET3 (PACKET3_SET_SH_REG ,2 ); + ib->ptr[ib->length_dw++] = mmCOMPUTE_PGM_LO -PACKET3_SET_SH_REG_START ; + ib->ptr[ib->length_dw++] =lower_32_bits (gpu_addr); + ib->ptr[ib->length_dw++] =upper_32_bits (gpu_addr);/* write dispatch packet */ - ib.ptr[ib.length_dw++] =PACKET3 (PACKET3_DISPATCH_DIRECT ,3 ); - ib.ptr[ib.length_dw++] =8 ;/* x */ - ib.ptr[ib.length_dw++] =1 ;/* y */ - ib.ptr[ib.length_dw++] =1 ;/* z */ - ib.ptr[ib.length_dw++] = + ib->ptr[ib->length_dw++] =PACKET3 (PACKET3_DISPATCH_DIRECT ,3 ); + ib->ptr[ib->length_dw++] =8 ;/* x */ + ib->ptr[ib->length_dw++] =1 ;/* y */ + ib->ptr[ib->length_dw++] =1 ;/* z */ + ib->ptr[ib->length_dw++] =REG_SET_FIELD (0 ,COMPUTE_DISPATCH_INITIATOR ,COMPUTE_SHADER_EN ,1 );/* write CS partial flush packet */ - ib.ptr[ib.length_dw++] =PACKET3 (PACKET3_EVENT_WRITE ,0 ); - ib.ptr[ib.length_dw++] =EVENT_TYPE (7 ) |EVENT_INDEX (4 ); + ib->ptr[ib->length_dw++] =PACKET3 (PACKET3_EVENT_WRITE ,0 ); + ib->ptr[ib->length_dw++] =EVENT_TYPE (7 ) |EVENT_INDEX (4 );/* SGPR2 */ /* write the register state for the compute dispatch */ for (i =0 ; i <ARRAY_SIZE (sgpr2_init_regs); i +=2 ) { - ib.ptr[ib.length_dw++] =PACKET3 (PACKET3_SET_SH_REG ,1 ); - ib.ptr[ib.length_dw++] = sgpr2_init_regs[i] -PACKET3_SET_SH_REG_START ; - ib.ptr[ib.length_dw++] = sgpr2_init_regs[i +1 ]; + ib->ptr[ib->length_dw++] =PACKET3 (PACKET3_SET_SH_REG ,1 ); + ib->ptr[ib->length_dw++] = sgpr2_init_regs[i] -PACKET3_SET_SH_REG_START ; + ib->ptr[ib->length_dw++] = sgpr2_init_regs[i +1 ]; }/* write the shader start address: mmCOMPUTE_PGM_LO, mmCOMPUTE_PGM_HI */ - gpu_addr = (ib.gpu_addr + (u64 )sgpr_offset) >>8 ; - ib.ptr[ib.length_dw++] =PACKET3 (PACKET3_SET_SH_REG ,2 ); - ib.ptr[ib.length_dw++] = mmCOMPUTE_PGM_LO -PACKET3_SET_SH_REG_START ; - ib.ptr[ib.length_dw++] =lower_32_bits (gpu_addr); - ib.ptr[ib.length_dw++] =upper_32_bits (gpu_addr); + gpu_addr = (ib->gpu_addr + (u64 )sgpr_offset) >>8 ; + ib->ptr[ib->length_dw++] =PACKET3 (PACKET3_SET_SH_REG ,2 ); + ib->ptr[ib->length_dw++] = mmCOMPUTE_PGM_LO -PACKET3_SET_SH_REG_START ; + ib->ptr[ib->length_dw++] =lower_32_bits (gpu_addr); + ib->ptr[ib->length_dw++] =upper_32_bits (gpu_addr);/* write dispatch packet */ - ib.ptr[ib.length_dw++] =PACKET3 (PACKET3_DISPATCH_DIRECT ,3 ); - ib.ptr[ib.length_dw++] =8 ;/* x */ - ib.ptr[ib.length_dw++] =1 ;/* y */ - ib.ptr[ib.length_dw++] =1 ;/* z */ - ib.ptr[ib.length_dw++] = + ib->ptr[ib->length_dw++] =PACKET3 (PACKET3_DISPATCH_DIRECT ,3 ); + ib->ptr[ib->length_dw++] =8 ;/* x */ + ib->ptr[ib->length_dw++] =1 ;/* y */ + ib->ptr[ib->length_dw++] =1 ;/* z */ + ib->ptr[ib->length_dw++] =REG_SET_FIELD (0 ,COMPUTE_DISPATCH_INITIATOR ,COMPUTE_SHADER_EN ,1 );/* write CS partial flush packet */ - ib.ptr[ib.length_dw++] =PACKET3 (PACKET3_EVENT_WRITE ,0 ); - ib.ptr[ib.length_dw++] =EVENT_TYPE (7 ) |EVENT_INDEX (4 ); + ib->ptr[ib->length_dw++] =PACKET3 (PACKET3_EVENT_WRITE ,0 ); + ib->ptr[ib->length_dw++] =EVENT_TYPE (7 ) |EVENT_INDEX (4 );/* shedule the ib on the ring */ - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); + r =amdgpu_job_submit_direct (job, ring, &f);if (r) {drm_err (adev_to_drm (adev),"ib submit failed (%d).\n" , r); +amdgpu_job_free (job); goto fail; }@@ -1629,7 +1635,6 @@ static int gfx_v8_0_do_edc_gpr_workarounds(struct amdgpu_device *adev)RREG32 (sec_ded_counter_registers[i]); fail: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f);return r;drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +71
-67@@ -1224,9 +1224,9 @@ static int gfx_v9_0_ring_test_ring(struct amdgpu_ring *ring)static int gfx_v9_0_ring_test_ib (struct amdgpu_ring *ring,long timeout) {struct amdgpu_device *adev = ring->adev; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ; -unsigned index;uint64_t gpu_addr;uint32_t tmp;@@ -1238,22 +1238,26 @@ static int gfx_v9_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) gpu_addr = adev->wb.gpu_addr + (index *4 ); adev->wb.wb[index] =cpu_to_le32 (0xCAFEDEAD ); -memset (&ib,0 ,sizeof (ib)); - r =amdgpu_ib_get (adev,NULL ,20 ,AMDGPU_IB_POOL_DIRECT , &ib); + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,20 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_GFX_RING_TEST );if (r) goto err1; - ib.ptr[0 ] =PACKET3 (PACKET3_WRITE_DATA ,3 ); - ib.ptr[1 ] =WRITE_DATA_DST_SEL (5 ) |WR_CONFIRM ; - ib.ptr[2 ] =lower_32_bits (gpu_addr); - ib.ptr[3 ] =upper_32_bits (gpu_addr); - ib.ptr[4 ] =0xDEADBEEF ; - ib.length_dw =5 ; + ib = &job->ibs[0 ]; + ib->ptr[0 ] =PACKET3 (PACKET3_WRITE_DATA ,3 ); + ib->ptr[1 ] =WRITE_DATA_DST_SEL (5 ) |WR_CONFIRM ; + ib->ptr[2 ] =lower_32_bits (gpu_addr); + ib->ptr[3 ] =upper_32_bits (gpu_addr); + ib->ptr[4 ] =0xDEADBEEF ; + ib->length_dw =5 ; - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (r) + r =amdgpu_job_submit_direct (job, ring, &f); +if (r) { +amdgpu_job_free (job); goto err2; + } r =dma_fence_wait_timeout (f, false, timeout);if (r ==0 ) {@@ -1270,7 +1274,6 @@ static int gfx_v9_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) r = -EINVAL ; err2: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f); err1:amdgpu_device_wb_free (adev, index);@@ -4624,7 +4627,8 @@ static int gfx_v9_0_do_edc_gds_workarounds(struct amdgpu_device *adev)static int gfx_v9_0_do_edc_gpr_workarounds (struct amdgpu_device *adev) {struct amdgpu_ring *ring = &adev->gfx.compute_ring[0 ]; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ;int r, i;unsigned total_size, vgpr_offset, sgpr_offset;@@ -4670,9 +4674,9 @@ static int gfx_v9_0_do_edc_gpr_workarounds(struct amdgpu_device *adev) total_size +=sizeof (sgpr_init_compute_shader);/* allocate an indirect buffer to put the commands in */ -memset (&ib,0 ,sizeof (ib)); - r =amdgpu_ib_get (adev,NULL , total_size, -AMDGPU_IB_POOL_DIRECT , &ib); + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL , total_size, +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_RUN_SHADER );if (r) {drm_err (adev_to_drm (adev),"failed to get ib (%d).\n" , r);return r;@@ -4680,102 +4684,103 @@ static int gfx_v9_0_do_edc_gpr_workarounds(struct amdgpu_device *adev)/* load the compute shaders */ for (i =0 ; i < vgpr_init_shader_size/sizeof (u32); i++) - ib.ptr[i + (vgpr_offset /4 )] = vgpr_init_shader_ptr[i]; + ib->ptr[i + (vgpr_offset /4 )] = vgpr_init_shader_ptr[i];for (i =0 ; i <ARRAY_SIZE (sgpr_init_compute_shader); i++) - ib.ptr[i + (sgpr_offset /4 )] = sgpr_init_compute_shader[i]; + ib->ptr[i + (sgpr_offset /4 )] = sgpr_init_compute_shader[i];/* init the ib length to 0 */ - ib.length_dw =0 ; + ib->length_dw =0 ;/* VGPR */ /* write the register state for the compute dispatch */ for (i =0 ; i < gpr_reg_size; i++) { - ib.ptr[ib.length_dw++] =PACKET3 (PACKET3_SET_SH_REG ,1 ); - ib.ptr[ib.length_dw++] =SOC15_REG_ENTRY_OFFSET (vgpr_init_regs_ptr[i]) + ib->ptr[ib->length_dw++] =PACKET3 (PACKET3_SET_SH_REG ,1 ); + ib->ptr[ib->length_dw++] =SOC15_REG_ENTRY_OFFSET (vgpr_init_regs_ptr[i]) -PACKET3_SET_SH_REG_START ; - ib.ptr[ib.length_dw++] = vgpr_init_regs_ptr[i].reg_value; + ib->ptr[ib->length_dw++] = vgpr_init_regs_ptr[i].reg_value; }/* write the shader start address: mmCOMPUTE_PGM_LO, mmCOMPUTE_PGM_HI */ - gpu_addr = (ib.gpu_addr + (u64 )vgpr_offset) >>8 ; - ib.ptr[ib.length_dw++] =PACKET3 (PACKET3_SET_SH_REG ,2 ); - ib.ptr[ib.length_dw++] =SOC15_REG_OFFSET (GC ,0 , mmCOMPUTE_PGM_LO) + gpu_addr = (ib->gpu_addr + (u64 )vgpr_offset) >>8 ; + ib->ptr[ib->length_dw++] =PACKET3 (PACKET3_SET_SH_REG ,2 ); + ib->ptr[ib->length_dw++] =SOC15_REG_OFFSET (GC ,0 , mmCOMPUTE_PGM_LO) -PACKET3_SET_SH_REG_START ; - ib.ptr[ib.length_dw++] =lower_32_bits (gpu_addr); - ib.ptr[ib.length_dw++] =upper_32_bits (gpu_addr); + ib->ptr[ib->length_dw++] =lower_32_bits (gpu_addr); + ib->ptr[ib->length_dw++] =upper_32_bits (gpu_addr);/* write dispatch packet */ - ib.ptr[ib.length_dw++] =PACKET3 (PACKET3_DISPATCH_DIRECT ,3 ); - ib.ptr[ib.length_dw++] = compute_dim_x *2 ;/* x */ - ib.ptr[ib.length_dw++] =1 ;/* y */ - ib.ptr[ib.length_dw++] =1 ;/* z */ - ib.ptr[ib.length_dw++] = + ib->ptr[ib->length_dw++] =PACKET3 (PACKET3_DISPATCH_DIRECT ,3 ); + ib->ptr[ib->length_dw++] = compute_dim_x *2 ;/* x */ + ib->ptr[ib->length_dw++] =1 ;/* y */ + ib->ptr[ib->length_dw++] =1 ;/* z */ + ib->ptr[ib->length_dw++] =REG_SET_FIELD (0 ,COMPUTE_DISPATCH_INITIATOR ,COMPUTE_SHADER_EN ,1 );/* write CS partial flush packet */ - ib.ptr[ib.length_dw++] =PACKET3 (PACKET3_EVENT_WRITE ,0 ); - ib.ptr[ib.length_dw++] =EVENT_TYPE (7 ) |EVENT_INDEX (4 ); + ib->ptr[ib->length_dw++] =PACKET3 (PACKET3_EVENT_WRITE ,0 ); + ib->ptr[ib->length_dw++] =EVENT_TYPE (7 ) |EVENT_INDEX (4 );/* SGPR1 */ /* write the register state for the compute dispatch */ for (i =0 ; i < gpr_reg_size; i++) { - ib.ptr[ib.length_dw++] =PACKET3 (PACKET3_SET_SH_REG ,1 ); - ib.ptr[ib.length_dw++] =SOC15_REG_ENTRY_OFFSET (sgpr1_init_regs[i]) + ib->ptr[ib->length_dw++] =PACKET3 (PACKET3_SET_SH_REG ,1 ); + ib->ptr[ib->length_dw++] =SOC15_REG_ENTRY_OFFSET (sgpr1_init_regs[i]) -PACKET3_SET_SH_REG_START ; - ib.ptr[ib.length_dw++] = sgpr1_init_regs[i].reg_value; + ib->ptr[ib->length_dw++] = sgpr1_init_regs[i].reg_value; }/* write the shader start address: mmCOMPUTE_PGM_LO, mmCOMPUTE_PGM_HI */ - gpu_addr = (ib.gpu_addr + (u64 )sgpr_offset) >>8 ; - ib.ptr[ib.length_dw++] =PACKET3 (PACKET3_SET_SH_REG ,2 ); - ib.ptr[ib.length_dw++] =SOC15_REG_OFFSET (GC ,0 , mmCOMPUTE_PGM_LO) + gpu_addr = (ib->gpu_addr + (u64 )sgpr_offset) >>8 ; + ib->ptr[ib->length_dw++] =PACKET3 (PACKET3_SET_SH_REG ,2 ); + ib->ptr[ib->length_dw++] =SOC15_REG_OFFSET (GC ,0 , mmCOMPUTE_PGM_LO) -PACKET3_SET_SH_REG_START ; - ib.ptr[ib.length_dw++] =lower_32_bits (gpu_addr); - ib.ptr[ib.length_dw++] =upper_32_bits (gpu_addr); + ib->ptr[ib->length_dw++] =lower_32_bits (gpu_addr); + ib->ptr[ib->length_dw++] =upper_32_bits (gpu_addr);/* write dispatch packet */ - ib.ptr[ib.length_dw++] =PACKET3 (PACKET3_DISPATCH_DIRECT ,3 ); - ib.ptr[ib.length_dw++] = compute_dim_x /2 * sgpr_work_group_size;/* x */ - ib.ptr[ib.length_dw++] =1 ;/* y */ - ib.ptr[ib.length_dw++] =1 ;/* z */ - ib.ptr[ib.length_dw++] = + ib->ptr[ib->length_dw++] =PACKET3 (PACKET3_DISPATCH_DIRECT ,3 ); + ib->ptr[ib->length_dw++] = compute_dim_x /2 * sgpr_work_group_size;/* x */ + ib->ptr[ib->length_dw++] =1 ;/* y */ + ib->ptr[ib->length_dw++] =1 ;/* z */ + ib->ptr[ib->length_dw++] =REG_SET_FIELD (0 ,COMPUTE_DISPATCH_INITIATOR ,COMPUTE_SHADER_EN ,1 );/* write CS partial flush packet */ - ib.ptr[ib.length_dw++] =PACKET3 (PACKET3_EVENT_WRITE ,0 ); - ib.ptr[ib.length_dw++] =EVENT_TYPE (7 ) |EVENT_INDEX (4 ); + ib->ptr[ib->length_dw++] =PACKET3 (PACKET3_EVENT_WRITE ,0 ); + ib->ptr[ib->length_dw++] =EVENT_TYPE (7 ) |EVENT_INDEX (4 );/* SGPR2 */ /* write the register state for the compute dispatch */ for (i =0 ; i < gpr_reg_size; i++) { - ib.ptr[ib.length_dw++] =PACKET3 (PACKET3_SET_SH_REG ,1 ); - ib.ptr[ib.length_dw++] =SOC15_REG_ENTRY_OFFSET (sgpr2_init_regs[i]) + ib->ptr[ib->length_dw++] =PACKET3 (PACKET3_SET_SH_REG ,1 ); + ib->ptr[ib->length_dw++] =SOC15_REG_ENTRY_OFFSET (sgpr2_init_regs[i]) -PACKET3_SET_SH_REG_START ; - ib.ptr[ib.length_dw++] = sgpr2_init_regs[i].reg_value; + ib->ptr[ib->length_dw++] = sgpr2_init_regs[i].reg_value; }/* write the shader start address: mmCOMPUTE_PGM_LO, mmCOMPUTE_PGM_HI */ - gpu_addr = (ib.gpu_addr + (u64 )sgpr_offset) >>8 ; - ib.ptr[ib.length_dw++] =PACKET3 (PACKET3_SET_SH_REG ,2 ); - ib.ptr[ib.length_dw++] =SOC15_REG_OFFSET (GC ,0 , mmCOMPUTE_PGM_LO) + gpu_addr = (ib->gpu_addr + (u64 )sgpr_offset) >>8 ; + ib->ptr[ib->length_dw++] =PACKET3 (PACKET3_SET_SH_REG ,2 ); + ib->ptr[ib->length_dw++] =SOC15_REG_OFFSET (GC ,0 , mmCOMPUTE_PGM_LO) -PACKET3_SET_SH_REG_START ; - ib.ptr[ib.length_dw++] =lower_32_bits (gpu_addr); - ib.ptr[ib.length_dw++] =upper_32_bits (gpu_addr); + ib->ptr[ib->length_dw++] =lower_32_bits (gpu_addr); + ib->ptr[ib->length_dw++] =upper_32_bits (gpu_addr);/* write dispatch packet */ - ib.ptr[ib.length_dw++] =PACKET3 (PACKET3_DISPATCH_DIRECT ,3 ); - ib.ptr[ib.length_dw++] = compute_dim_x /2 * sgpr_work_group_size;/* x */ - ib.ptr[ib.length_dw++] =1 ;/* y */ - ib.ptr[ib.length_dw++] =1 ;/* z */ - ib.ptr[ib.length_dw++] = + ib->ptr[ib->length_dw++] =PACKET3 (PACKET3_DISPATCH_DIRECT ,3 ); + ib->ptr[ib->length_dw++] = compute_dim_x /2 * sgpr_work_group_size;/* x */ + ib->ptr[ib->length_dw++] =1 ;/* y */ + ib->ptr[ib->length_dw++] =1 ;/* z */ + ib->ptr[ib->length_dw++] =REG_SET_FIELD (0 ,COMPUTE_DISPATCH_INITIATOR ,COMPUTE_SHADER_EN ,1 );/* write CS partial flush packet */ - ib.ptr[ib.length_dw++] =PACKET3 (PACKET3_EVENT_WRITE ,0 ); - ib.ptr[ib.length_dw++] =EVENT_TYPE (7 ) |EVENT_INDEX (4 ); + ib->ptr[ib->length_dw++] =PACKET3 (PACKET3_EVENT_WRITE ,0 ); + ib->ptr[ib->length_dw++] =EVENT_TYPE (7 ) |EVENT_INDEX (4 );/* shedule the ib on the ring */ - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); + r =amdgpu_job_submit_direct (job, ring, &f);if (r) {drm_err (adev_to_drm (adev),"ib schedule failed (%d).\n" , r); +amdgpu_job_free (job); goto fail; }@@ -4787,7 +4792,6 @@ static int gfx_v9_0_do_edc_gpr_workarounds(struct amdgpu_device *adev) } fail: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f);return r;drivers/gpu/drm/amd/amdgpu/gfx_v9_4_2.c +8
-18@@ -345,12 +345,13 @@ const struct soc15_reg_entry sgpr64_init_regs_aldebaran[] = {static int gfx_v9_4_2_run_shader (struct amdgpu_device *adev,struct amdgpu_ring *ring, -struct amdgpu_ib *ib,const u32 *shader_ptr,u32 shader_size,const struct soc15_reg_entry *init_regs,u32 regs_size,u32 compute_dim_x,u64 wb_gpu_addr,u32 pattern,struct dma_fence **fence_ptr) { +struct amdgpu_job *job; +struct amdgpu_ib *ib;int r, i;uint32_t total_size, shader_offset;u64 gpu_addr;@@ -360,10 +361,9 @@ static int gfx_v9_4_2_run_shader(struct amdgpu_device *adev, shader_offset = total_size; total_size +=ALIGN (shader_size,256 ); -/* allocate an indirect buffer to put the commands in */ -memset (ib,0 ,sizeof (*ib)); - r =amdgpu_ib_get (adev,NULL , total_size, -AMDGPU_IB_POOL_DIRECT , ib); + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL , total_size, +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_RUN_SHADER );if (r) {dev_err (adev->dev,"failed to get ib (%d).\n" , r);return r;@@ -408,11 +408,11 @@ static int gfx_v9_4_2_run_shader(struct amdgpu_device *adev, ib->ptr[ib->length_dw++] =REG_SET_FIELD (0 ,COMPUTE_DISPATCH_INITIATOR ,COMPUTE_SHADER_EN ,1 ); -/* shedule the ib on the ring */ - r =amdgpu_ib_schedule (ring,1 , ib,NULL , fence_ptr); +/* schedule the ib on the ring */ + r =amdgpu_job_submit_direct (job, ring, fence_ptr);if (r) {dev_err (adev->dev,"ib submit failed (%d).\n" , r); -amdgpu_ib_free (ib,NULL ); +amdgpu_job_free (job); }return r; }@@ -493,7 +493,6 @@ static int gfx_v9_4_2_do_sgprs_init(struct amdgpu_device *adev)int wb_size = adev->gfx.config.max_shader_engines *CU_ID_MAX *SIMD_ID_MAX *WAVE_ID_MAX ;struct amdgpu_ib wb_ib; -struct amdgpu_ib disp_ibs[3 ];struct dma_fence *fences[3 ];u32 pattern[3 ] = {0x1 ,0x5 ,0xa };@@ -514,7 +513,6 @@ static int gfx_v9_4_2_do_sgprs_init(struct amdgpu_device *adev) r = gfx_v9_4_2_run_shader(adev, &adev->gfx.compute_ring[0], - &disp_ibs[0], sgpr112_init_compute_shader_aldebaran, sizeof(sgpr112_init_compute_shader_aldebaran), sgpr112_init_regs_aldebaran,@@ -539,7 +537,6 @@ static int gfx_v9_4_2_do_sgprs_init(struct amdgpu_device *adev) r = gfx_v9_4_2_run_shader(adev, &adev->gfx.compute_ring[1], - &disp_ibs[1], sgpr96_init_compute_shader_aldebaran, sizeof(sgpr96_init_compute_shader_aldebaran), sgpr96_init_regs_aldebaran,@@ -579,7 +576,6 @@ static int gfx_v9_4_2_do_sgprs_init(struct amdgpu_device *adev)memset (wb_ib.ptr,0 , (1 + wb_size) *sizeof (uint32_t )); r = gfx_v9_4_2_run_shader(adev, &adev->gfx.compute_ring[0], - &disp_ibs[2], sgpr64_init_compute_shader_aldebaran, sizeof(sgpr64_init_compute_shader_aldebaran), sgpr64_init_regs_aldebaran,@@ -611,13 +607,10 @@ static int gfx_v9_4_2_do_sgprs_init(struct amdgpu_device *adev) } disp2_failed: -amdgpu_ib_free (&disp_ibs[2 ],NULL );dma_fence_put (fences[2 ]); disp1_failed: -amdgpu_ib_free (&disp_ibs[1 ],NULL );dma_fence_put (fences[1 ]); disp0_failed: -amdgpu_ib_free (&disp_ibs[0 ],NULL );dma_fence_put (fences[0 ]); pro_end:amdgpu_ib_free (&wb_ib,NULL );@@ -637,7 +630,6 @@ static int gfx_v9_4_2_do_vgprs_init(struct amdgpu_device *adev)int wb_size = adev->gfx.config.max_shader_engines *CU_ID_MAX *SIMD_ID_MAX *WAVE_ID_MAX ;struct amdgpu_ib wb_ib; -struct amdgpu_ib disp_ib;struct dma_fence *fence;u32 pattern =0xa ;@@ -657,7 +649,6 @@ static int gfx_v9_4_2_do_vgprs_init(struct amdgpu_device *adev) r = gfx_v9_4_2_run_shader(adev, &adev->gfx.compute_ring[0], - &disp_ib, vgpr_init_compute_shader_aldebaran, sizeof(vgpr_init_compute_shader_aldebaran), vgpr_init_regs_aldebaran,@@ -687,7 +678,6 @@ static int gfx_v9_4_2_do_vgprs_init(struct amdgpu_device *adev) } disp_failed: -amdgpu_ib_free (&disp_ib,NULL );dma_fence_put (fence); pro_end:amdgpu_ib_free (&wb_ib,NULL );drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c +16
-13@@ -451,9 +451,9 @@ static int gfx_v9_4_3_ring_test_ring(struct amdgpu_ring *ring)static int gfx_v9_4_3_ring_test_ib (struct amdgpu_ring *ring,long timeout) {struct amdgpu_device *adev = ring->adev; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ; -unsigned index;uint64_t gpu_addr;uint32_t tmp;@@ -465,22 +465,26 @@ static int gfx_v9_4_3_ring_test_ib(struct amdgpu_ring *ring, long timeout) gpu_addr = adev->wb.gpu_addr + (index *4 ); adev->wb.wb[index] =cpu_to_le32 (0xCAFEDEAD ); -memset (&ib,0 ,sizeof (ib)); - r =amdgpu_ib_get (adev,NULL ,20 ,AMDGPU_IB_POOL_DIRECT , &ib); + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,20 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_GFX_RING_TEST );if (r) goto err1; - ib.ptr[0 ] =PACKET3 (PACKET3_WRITE_DATA ,3 ); - ib.ptr[1 ] =WRITE_DATA_DST_SEL (5 ) |WR_CONFIRM ; - ib.ptr[2 ] =lower_32_bits (gpu_addr); - ib.ptr[3 ] =upper_32_bits (gpu_addr); - ib.ptr[4 ] =0xDEADBEEF ; - ib.length_dw =5 ; + ib = &job->ibs[0 ]; + ib->ptr[0 ] =PACKET3 (PACKET3_WRITE_DATA ,3 ); + ib->ptr[1 ] =WRITE_DATA_DST_SEL (5 ) |WR_CONFIRM ; + ib->ptr[2 ] =lower_32_bits (gpu_addr); + ib->ptr[3 ] =upper_32_bits (gpu_addr); + ib->ptr[4 ] =0xDEADBEEF ; + ib->length_dw =5 ; - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (r) + r =amdgpu_job_submit_direct (job, ring, &f); +if (r) { +amdgpu_job_free (job); goto err2; + } r =dma_fence_wait_timeout (f, false, timeout);if (r ==0 ) {@@ -497,7 +501,6 @@ static int gfx_v9_4_3_ring_test_ib(struct amdgpu_ring *ring, long timeout) r = -EINVAL ; err2: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f); err1:amdgpu_device_wb_free (adev, index);drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c +21
-17@@ -584,7 +584,8 @@ static int sdma_v2_4_ring_test_ring(struct amdgpu_ring *ring)static int sdma_v2_4_ring_test_ib (struct amdgpu_ring *ring,long timeout) {struct amdgpu_device *adev = ring->adev; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ;unsigned index;u32 tmp =0 ;@@ -598,26 +599,30 @@ static int sdma_v2_4_ring_test_ib(struct amdgpu_ring *ring, long timeout) gpu_addr = adev->wb.gpu_addr + (index *4 ); tmp =0xCAFEDEAD ; adev->wb.wb[index] =cpu_to_le32 (tmp); -memset (&ib,0 ,sizeof (ib)); - r =amdgpu_ib_get (adev,NULL ,256 , -AMDGPU_IB_POOL_DIRECT , &ib); + + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,256 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_SDMA_RING_TEST );if (r) goto err0; - ib.ptr[0 ] =SDMA_PKT_HEADER_OP (SDMA_OP_WRITE ) | + ib = &job->ibs[0 ]; + ib->ptr[0 ] =SDMA_PKT_HEADER_OP (SDMA_OP_WRITE ) |SDMA_PKT_HEADER_SUB_OP (SDMA_SUBOP_WRITE_LINEAR ); - ib.ptr[1 ] =lower_32_bits (gpu_addr); - ib.ptr[2 ] =upper_32_bits (gpu_addr); - ib.ptr[3 ] =SDMA_PKT_WRITE_UNTILED_DW_3_COUNT (1 ); - ib.ptr[4 ] =0xDEADBEEF ; - ib.ptr[5 ] =SDMA_PKT_HEADER_OP (SDMA_OP_NOP ); - ib.ptr[6 ] =SDMA_PKT_HEADER_OP (SDMA_OP_NOP ); - ib.ptr[7 ] =SDMA_PKT_HEADER_OP (SDMA_OP_NOP ); - ib.length_dw =8 ; - - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (r) + ib->ptr[1 ] =lower_32_bits (gpu_addr); + ib->ptr[2 ] =upper_32_bits (gpu_addr); + ib->ptr[3 ] =SDMA_PKT_WRITE_UNTILED_DW_3_COUNT (1 ); + ib->ptr[4 ] =0xDEADBEEF ; + ib->ptr[5 ] =SDMA_PKT_HEADER_OP (SDMA_OP_NOP ); + ib->ptr[6 ] =SDMA_PKT_HEADER_OP (SDMA_OP_NOP ); + ib->ptr[7 ] =SDMA_PKT_HEADER_OP (SDMA_OP_NOP ); + ib->length_dw =8 ; + + r =amdgpu_job_submit_direct (job, ring, &f); +if (r) { +amdgpu_job_free (job); goto err1; + } r =dma_fence_wait_timeout (f, false, timeout);if (r ==0 ) {@@ -633,7 +638,6 @@ static int sdma_v2_4_ring_test_ib(struct amdgpu_ring *ring, long timeout) r = -EINVAL ; err1: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f); err0:amdgpu_device_wb_free (adev, index);drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c +21
-17@@ -858,7 +858,8 @@ static int sdma_v3_0_ring_test_ring(struct amdgpu_ring *ring)static int sdma_v3_0_ring_test_ib (struct amdgpu_ring *ring,long timeout) {struct amdgpu_device *adev = ring->adev; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ;unsigned index;u32 tmp =0 ;@@ -872,26 +873,30 @@ static int sdma_v3_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) gpu_addr = adev->wb.gpu_addr + (index *4 ); tmp =0xCAFEDEAD ; adev->wb.wb[index] =cpu_to_le32 (tmp); -memset (&ib,0 ,sizeof (ib)); - r =amdgpu_ib_get (adev,NULL ,256 , -AMDGPU_IB_POOL_DIRECT , &ib); + + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,256 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_SDMA_RING_TEST );if (r) goto err0; - ib.ptr[0 ] =SDMA_PKT_HEADER_OP (SDMA_OP_WRITE ) | + ib = &job->ibs[0 ]; + ib->ptr[0 ] =SDMA_PKT_HEADER_OP (SDMA_OP_WRITE ) |SDMA_PKT_HEADER_SUB_OP (SDMA_SUBOP_WRITE_LINEAR ); - ib.ptr[1 ] =lower_32_bits (gpu_addr); - ib.ptr[2 ] =upper_32_bits (gpu_addr); - ib.ptr[3 ] =SDMA_PKT_WRITE_UNTILED_DW_3_COUNT (1 ); - ib.ptr[4 ] =0xDEADBEEF ; - ib.ptr[5 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.ptr[6 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.ptr[7 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.length_dw =8 ; - - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (r) + ib->ptr[1 ] =lower_32_bits (gpu_addr); + ib->ptr[2 ] =upper_32_bits (gpu_addr); + ib->ptr[3 ] =SDMA_PKT_WRITE_UNTILED_DW_3_COUNT (1 ); + ib->ptr[4 ] =0xDEADBEEF ; + ib->ptr[5 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->ptr[6 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->ptr[7 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->length_dw =8 ; + + r =amdgpu_job_submit_direct (job, ring, &f); +if (r) { +amdgpu_job_free (job); goto err1; + } r =dma_fence_wait_timeout (f, false, timeout);if (r ==0 ) {@@ -906,7 +911,6 @@ static int sdma_v3_0_ring_test_ib(struct amdgpu_ring *ring, long timeout)else r = -EINVAL ; err1: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f); err0:amdgpu_device_wb_free (adev, index);drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c +21
-17@@ -1516,7 +1516,8 @@ static int sdma_v4_0_ring_test_ring(struct amdgpu_ring *ring)static int sdma_v4_0_ring_test_ib (struct amdgpu_ring *ring,long timeout) {struct amdgpu_device *adev = ring->adev; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ;unsigned index;long r;@@ -1530,26 +1531,30 @@ static int sdma_v4_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) gpu_addr = adev->wb.gpu_addr + (index *4 ); tmp =0xCAFEDEAD ; adev->wb.wb[index] =cpu_to_le32 (tmp); -memset (&ib,0 ,sizeof (ib)); - r =amdgpu_ib_get (adev,NULL ,256 , -AMDGPU_IB_POOL_DIRECT , &ib); + + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,256 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_SDMA_RING_TEST );if (r) goto err0; - ib.ptr[0 ] =SDMA_PKT_HEADER_OP (SDMA_OP_WRITE ) | + ib = &job->ibs[0 ]; + ib->ptr[0 ] =SDMA_PKT_HEADER_OP (SDMA_OP_WRITE ) |SDMA_PKT_HEADER_SUB_OP (SDMA_SUBOP_WRITE_LINEAR ); - ib.ptr[1 ] =lower_32_bits (gpu_addr); - ib.ptr[2 ] =upper_32_bits (gpu_addr); - ib.ptr[3 ] =SDMA_PKT_WRITE_UNTILED_DW_3_COUNT (0 ); - ib.ptr[4 ] =0xDEADBEEF ; - ib.ptr[5 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.ptr[6 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.ptr[7 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.length_dw =8 ; - - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (r) + ib->ptr[1 ] =lower_32_bits (gpu_addr); + ib->ptr[2 ] =upper_32_bits (gpu_addr); + ib->ptr[3 ] =SDMA_PKT_WRITE_UNTILED_DW_3_COUNT (0 ); + ib->ptr[4 ] =0xDEADBEEF ; + ib->ptr[5 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->ptr[6 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->ptr[7 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->length_dw =8 ; + + r =amdgpu_job_submit_direct (job, ring, &f); +if (r) { +amdgpu_job_free (job); goto err1; + } r =dma_fence_wait_timeout (f, false, timeout);if (r ==0 ) {@@ -1565,7 +1570,6 @@ static int sdma_v4_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) r = -EINVAL ; err1: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f); err0:amdgpu_device_wb_free (adev, index);drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c +21
-17@@ -1112,7 +1112,8 @@ static int sdma_v4_4_2_ring_test_ring(struct amdgpu_ring *ring)static int sdma_v4_4_2_ring_test_ib (struct amdgpu_ring *ring,long timeout) {struct amdgpu_device *adev = ring->adev; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ;unsigned index;long r;@@ -1126,26 +1127,30 @@ static int sdma_v4_4_2_ring_test_ib(struct amdgpu_ring *ring, long timeout) gpu_addr = adev->wb.gpu_addr + (index *4 ); tmp =0xCAFEDEAD ; adev->wb.wb[index] =cpu_to_le32 (tmp); -memset (&ib,0 ,sizeof (ib)); - r =amdgpu_ib_get (adev,NULL ,256 , -AMDGPU_IB_POOL_DIRECT , &ib); + + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,256 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_SDMA_RING_TEST );if (r) goto err0; - ib.ptr[0 ] =SDMA_PKT_HEADER_OP (SDMA_OP_WRITE ) | + ib = &job->ibs[0 ]; + ib->ptr[0 ] =SDMA_PKT_HEADER_OP (SDMA_OP_WRITE ) |SDMA_PKT_HEADER_SUB_OP (SDMA_SUBOP_WRITE_LINEAR ); - ib.ptr[1 ] =lower_32_bits (gpu_addr); - ib.ptr[2 ] =upper_32_bits (gpu_addr); - ib.ptr[3 ] =SDMA_PKT_WRITE_UNTILED_DW_3_COUNT (0 ); - ib.ptr[4 ] =0xDEADBEEF ; - ib.ptr[5 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.ptr[6 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.ptr[7 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.length_dw =8 ; - - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (r) + ib->ptr[1 ] =lower_32_bits (gpu_addr); + ib->ptr[2 ] =upper_32_bits (gpu_addr); + ib->ptr[3 ] =SDMA_PKT_WRITE_UNTILED_DW_3_COUNT (0 ); + ib->ptr[4 ] =0xDEADBEEF ; + ib->ptr[5 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->ptr[6 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->ptr[7 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->length_dw =8 ; + + r =amdgpu_job_submit_direct (job, ring, &f); +if (r) { +amdgpu_job_free (job); goto err1; + } r =dma_fence_wait_timeout (f, false, timeout);if (r ==0 ) {@@ -1161,7 +1166,6 @@ static int sdma_v4_4_2_ring_test_ib(struct amdgpu_ring *ring, long timeout) r = -EINVAL ; err1: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f); err0:amdgpu_device_wb_free (adev, index);drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c +20
-17@@ -1074,7 +1074,8 @@ static int sdma_v5_0_ring_test_ring(struct amdgpu_ring *ring)static int sdma_v5_0_ring_test_ib (struct amdgpu_ring *ring,long timeout) {struct amdgpu_device *adev = ring->adev; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ;unsigned index;long r;@@ -1082,7 +1083,6 @@ static int sdma_v5_0_ring_test_ib(struct amdgpu_ring *ring, long timeout)u64 gpu_addr; tmp =0xCAFEDEAD ; -memset (&ib,0 ,sizeof (ib)); r =amdgpu_device_wb_get (adev, &index);if (r) {@@ -1093,27 +1093,31 @@ static int sdma_v5_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) gpu_addr = adev->wb.gpu_addr + (index *4 ); adev->wb.wb[index] =cpu_to_le32 (tmp); - r =amdgpu_ib_get (adev,NULL ,256 , -AMDGPU_IB_POOL_DIRECT , &ib); + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,256 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_SDMA_RING_TEST );if (r) {drm_err (adev_to_drm (adev),"failed to get ib (%ld).\n" , r); goto err0; } - ib.ptr[0 ] =SDMA_PKT_HEADER_OP (SDMA_OP_WRITE ) | + ib = &job->ibs[0 ]; + ib->ptr[0 ] =SDMA_PKT_HEADER_OP (SDMA_OP_WRITE ) |SDMA_PKT_HEADER_SUB_OP (SDMA_SUBOP_WRITE_LINEAR ); - ib.ptr[1 ] =lower_32_bits (gpu_addr); - ib.ptr[2 ] =upper_32_bits (gpu_addr); - ib.ptr[3 ] =SDMA_PKT_WRITE_UNTILED_DW_3_COUNT (0 ); - ib.ptr[4 ] =0xDEADBEEF ; - ib.ptr[5 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.ptr[6 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.ptr[7 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.length_dw =8 ; - - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (r) + ib->ptr[1 ] =lower_32_bits (gpu_addr); + ib->ptr[2 ] =upper_32_bits (gpu_addr); + ib->ptr[3 ] =SDMA_PKT_WRITE_UNTILED_DW_3_COUNT (0 ); + ib->ptr[4 ] =0xDEADBEEF ; + ib->ptr[5 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->ptr[6 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->ptr[7 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->length_dw =8 ; + + r =amdgpu_job_submit_direct (job, ring, &f); +if (r) { +amdgpu_job_free (job); goto err1; + } r =dma_fence_wait_timeout (f, false, timeout);if (r ==0 ) {@@ -1133,7 +1137,6 @@ static int sdma_v5_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) r = -EINVAL ; err1: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f); err0:amdgpu_device_wb_free (adev, index);drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c +20
-16@@ -974,7 +974,8 @@ static int sdma_v5_2_ring_test_ring(struct amdgpu_ring *ring)static int sdma_v5_2_ring_test_ib (struct amdgpu_ring *ring,long timeout) {struct amdgpu_device *adev = ring->adev; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ;unsigned index;long r;@@ -982,7 +983,6 @@ static int sdma_v5_2_ring_test_ib(struct amdgpu_ring *ring, long timeout)u64 gpu_addr; tmp =0xCAFEDEAD ; -memset (&ib,0 ,sizeof (ib)); r =amdgpu_device_wb_get (adev, &index);if (r) {@@ -993,26 +993,31 @@ static int sdma_v5_2_ring_test_ib(struct amdgpu_ring *ring, long timeout) gpu_addr = adev->wb.gpu_addr + (index *4 ); adev->wb.wb[index] =cpu_to_le32 (tmp); - r =amdgpu_ib_get (adev,NULL ,256 ,AMDGPU_IB_POOL_DIRECT , &ib); + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,256 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_SDMA_RING_TEST );if (r) {drm_err (adev_to_drm (adev),"failed to get ib (%ld).\n" , r); goto err0; } - ib.ptr[0 ] =SDMA_PKT_HEADER_OP (SDMA_OP_WRITE ) | + ib = &job->ibs[0 ]; + ib->ptr[0 ] =SDMA_PKT_HEADER_OP (SDMA_OP_WRITE ) |SDMA_PKT_HEADER_SUB_OP (SDMA_SUBOP_WRITE_LINEAR ); - ib.ptr[1 ] =lower_32_bits (gpu_addr); - ib.ptr[2 ] =upper_32_bits (gpu_addr); - ib.ptr[3 ] =SDMA_PKT_WRITE_UNTILED_DW_3_COUNT (0 ); - ib.ptr[4 ] =0xDEADBEEF ; - ib.ptr[5 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.ptr[6 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.ptr[7 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.length_dw =8 ; - - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (r) + ib->ptr[1 ] =lower_32_bits (gpu_addr); + ib->ptr[2 ] =upper_32_bits (gpu_addr); + ib->ptr[3 ] =SDMA_PKT_WRITE_UNTILED_DW_3_COUNT (0 ); + ib->ptr[4 ] =0xDEADBEEF ; + ib->ptr[5 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->ptr[6 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->ptr[7 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->length_dw =8 ; + + r =amdgpu_job_submit_direct (job, ring, &f); +if (r) { +amdgpu_job_free (job); goto err1; + } r =dma_fence_wait_timeout (f, false, timeout);if (r ==0 ) {@@ -1032,7 +1037,6 @@ static int sdma_v5_2_ring_test_ib(struct amdgpu_ring *ring, long timeout) r = -EINVAL ; err1: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f); err0:amdgpu_device_wb_free (adev, index);drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c +20
-16@@ -981,7 +981,8 @@ static int sdma_v6_0_ring_test_ring(struct amdgpu_ring *ring)static int sdma_v6_0_ring_test_ib (struct amdgpu_ring *ring,long timeout) {struct amdgpu_device *adev = ring->adev; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ;unsigned index;long r;@@ -989,7 +990,6 @@ static int sdma_v6_0_ring_test_ib(struct amdgpu_ring *ring, long timeout)u64 gpu_addr; tmp =0xCAFEDEAD ; -memset (&ib,0 ,sizeof (ib)); r =amdgpu_device_wb_get (adev, &index);if (r) {@@ -1000,26 +1000,31 @@ static int sdma_v6_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) gpu_addr = adev->wb.gpu_addr + (index *4 ); adev->wb.wb[index] =cpu_to_le32 (tmp); - r =amdgpu_ib_get (adev,NULL ,256 ,AMDGPU_IB_POOL_DIRECT , &ib); + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,256 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_SDMA_RING_TEST );if (r) {drm_err (adev_to_drm (adev),"failed to get ib (%ld).\n" , r); goto err0; } - ib.ptr[0 ] =SDMA_PKT_COPY_LINEAR_HEADER_OP (SDMA_OP_WRITE ) | + ib = &job->ibs[0 ]; + ib->ptr[0 ] =SDMA_PKT_COPY_LINEAR_HEADER_OP (SDMA_OP_WRITE ) |SDMA_PKT_COPY_LINEAR_HEADER_SUB_OP (SDMA_SUBOP_WRITE_LINEAR ); - ib.ptr[1 ] =lower_32_bits (gpu_addr); - ib.ptr[2 ] =upper_32_bits (gpu_addr); - ib.ptr[3 ] =SDMA_PKT_WRITE_UNTILED_DW_3_COUNT (0 ); - ib.ptr[4 ] =0xDEADBEEF ; - ib.ptr[5 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.ptr[6 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.ptr[7 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.length_dw =8 ; - - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (r) + ib->ptr[1 ] =lower_32_bits (gpu_addr); + ib->ptr[2 ] =upper_32_bits (gpu_addr); + ib->ptr[3 ] =SDMA_PKT_WRITE_UNTILED_DW_3_COUNT (0 ); + ib->ptr[4 ] =0xDEADBEEF ; + ib->ptr[5 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->ptr[6 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->ptr[7 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->length_dw =8 ; + + r =amdgpu_job_submit_direct (job, ring, &f); +if (r) { +amdgpu_job_free (job); goto err1; + } r =dma_fence_wait_timeout (f, false, timeout);if (r ==0 ) {@@ -1039,7 +1044,6 @@ static int sdma_v6_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) r = -EINVAL ; err1: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f); err0:amdgpu_device_wb_free (adev, index);drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c +20
-16@@ -997,7 +997,8 @@ static int sdma_v7_0_ring_test_ring(struct amdgpu_ring *ring)static int sdma_v7_0_ring_test_ib (struct amdgpu_ring *ring,long timeout) {struct amdgpu_device *adev = ring->adev; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ;unsigned index;long r;@@ -1005,7 +1006,6 @@ static int sdma_v7_0_ring_test_ib(struct amdgpu_ring *ring, long timeout)u64 gpu_addr; tmp =0xCAFEDEAD ; -memset (&ib,0 ,sizeof (ib)); r =amdgpu_device_wb_get (adev, &index);if (r) {@@ -1016,26 +1016,31 @@ static int sdma_v7_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) gpu_addr = adev->wb.gpu_addr + (index *4 ); adev->wb.wb[index] =cpu_to_le32 (tmp); - r =amdgpu_ib_get (adev,NULL ,256 ,AMDGPU_IB_POOL_DIRECT , &ib); + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,256 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_SDMA_RING_TEST );if (r) {drm_err (adev_to_drm (adev),"failed to get ib (%ld).\n" , r); goto err0; } - ib.ptr[0 ] =SDMA_PKT_COPY_LINEAR_HEADER_OP (SDMA_OP_WRITE ) | + ib = &job->ibs[0 ]; + ib->ptr[0 ] =SDMA_PKT_COPY_LINEAR_HEADER_OP (SDMA_OP_WRITE ) |SDMA_PKT_COPY_LINEAR_HEADER_SUB_OP (SDMA_SUBOP_WRITE_LINEAR ); - ib.ptr[1 ] =lower_32_bits (gpu_addr); - ib.ptr[2 ] =upper_32_bits (gpu_addr); - ib.ptr[3 ] =SDMA_PKT_WRITE_UNTILED_DW_3_COUNT (0 ); - ib.ptr[4 ] =0xDEADBEEF ; - ib.ptr[5 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.ptr[6 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.ptr[7 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.length_dw =8 ; - - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (r) + ib->ptr[1 ] =lower_32_bits (gpu_addr); + ib->ptr[2 ] =upper_32_bits (gpu_addr); + ib->ptr[3 ] =SDMA_PKT_WRITE_UNTILED_DW_3_COUNT (0 ); + ib->ptr[4 ] =0xDEADBEEF ; + ib->ptr[5 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->ptr[6 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->ptr[7 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->length_dw =8 ; + + r =amdgpu_job_submit_direct (job, ring, &f); +if (r) { +amdgpu_job_free (job); goto err1; + } r =dma_fence_wait_timeout (f, false, timeout);if (r ==0 ) {@@ -1055,7 +1060,6 @@ static int sdma_v7_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) r = -EINVAL ; err1: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f); err0:amdgpu_device_wb_free (adev, index);drivers/gpu/drm/amd/amdgpu/sdma_v7_1.c +20
-16@@ -987,7 +987,8 @@ static int sdma_v7_1_ring_test_ring(struct amdgpu_ring *ring)static int sdma_v7_1_ring_test_ib (struct amdgpu_ring *ring,long timeout) {struct amdgpu_device *adev = ring->adev; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ;unsigned index;long r;@@ -995,7 +996,6 @@ static int sdma_v7_1_ring_test_ib(struct amdgpu_ring *ring, long timeout)u64 gpu_addr; tmp =0xCAFEDEAD ; -memset (&ib,0 ,sizeof (ib)); r =amdgpu_device_wb_get (adev, &index);if (r) {@@ -1006,26 +1006,31 @@ static int sdma_v7_1_ring_test_ib(struct amdgpu_ring *ring, long timeout) gpu_addr = adev->wb.gpu_addr + (index *4 ); adev->wb.wb[index] =cpu_to_le32 (tmp); - r =amdgpu_ib_get (adev,NULL ,256 ,AMDGPU_IB_POOL_DIRECT , &ib); + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,256 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_SDMA_RING_TEST );if (r) {DRM_ERROR ("amdgpu: failed to get ib (%ld).\n" , r); goto err0; } - ib.ptr[0 ] =SDMA_PKT_COPY_LINEAR_HEADER_OP (SDMA_OP_WRITE ) | + ib = &job->ibs[0 ]; + ib->ptr[0 ] =SDMA_PKT_COPY_LINEAR_HEADER_OP (SDMA_OP_WRITE ) |SDMA_PKT_COPY_LINEAR_HEADER_SUB_OP (SDMA_SUBOP_WRITE_LINEAR ); - ib.ptr[1 ] =lower_32_bits (gpu_addr); - ib.ptr[2 ] =upper_32_bits (gpu_addr); - ib.ptr[3 ] =SDMA_PKT_WRITE_UNTILED_DW_3_COUNT (0 ); - ib.ptr[4 ] =0xDEADBEEF ; - ib.ptr[5 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.ptr[6 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.ptr[7 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.length_dw =8 ; - - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (r) + ib->ptr[1 ] =lower_32_bits (gpu_addr); + ib->ptr[2 ] =upper_32_bits (gpu_addr); + ib->ptr[3 ] =SDMA_PKT_WRITE_UNTILED_DW_3_COUNT (0 ); + ib->ptr[4 ] =0xDEADBEEF ; + ib->ptr[5 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->ptr[6 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->ptr[7 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->length_dw =8 ; + + r =amdgpu_job_submit_direct (job, ring, &f); +if (r) { +amdgpu_job_free (job); goto err1; + } r =dma_fence_wait_timeout (f, false, timeout);if (r ==0 ) {@@ -1045,7 +1050,6 @@ static int sdma_v7_1_ring_test_ib(struct amdgpu_ring *ring, long timeout) r = -EINVAL ; err1: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f); err0:amdgpu_device_wb_free (adev, index);drivers/gpu/drm/amd/amdgpu/si_dma.c +17
-12@@ -259,7 +259,8 @@ static int si_dma_ring_test_ring(struct amdgpu_ring *ring)static int si_dma_ring_test_ib (struct amdgpu_ring *ring,long timeout) {struct amdgpu_device *adev = ring->adev; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ;unsigned index;u32 tmp =0 ;@@ -273,20 +274,25 @@ static int si_dma_ring_test_ib(struct amdgpu_ring *ring, long timeout) gpu_addr = adev->wb.gpu_addr + (index *4 ); tmp =0xCAFEDEAD ; adev->wb.wb[index] =cpu_to_le32 (tmp); -memset (&ib,0 ,sizeof (ib)); - r =amdgpu_ib_get (adev,NULL ,256 , -AMDGPU_IB_POOL_DIRECT , &ib); + + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,256 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_SDMA_RING_TEST );if (r) goto err0; - ib.ptr[0 ] =DMA_PACKET (DMA_PACKET_WRITE ,0 ,0 ,0 ,1 ); - ib.ptr[1 ] =lower_32_bits (gpu_addr); - ib.ptr[2 ] =upper_32_bits (gpu_addr) &0xff ; - ib.ptr[3 ] =0xDEADBEEF ; - ib.length_dw =4 ; - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (r) + ib = &job->ibs[0 ]; + ib->ptr[0 ] =DMA_PACKET (DMA_PACKET_WRITE ,0 ,0 ,0 ,1 ); + ib->ptr[1 ] =lower_32_bits (gpu_addr); + ib->ptr[2 ] =upper_32_bits (gpu_addr) &0xff ; + ib->ptr[3 ] =0xDEADBEEF ; + ib->length_dw =4 ; + + r =amdgpu_job_submit_direct (job, ring, &f); +if (r) { +amdgpu_job_free (job); goto err1; + } r =dma_fence_wait_timeout (f, false, timeout);if (r ==0 ) {@@ -302,7 +308,6 @@ static int si_dma_ring_test_ib(struct amdgpu_ring *ring, long timeout) r = -EINVAL ; err1: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f); err0:amdgpu_device_wb_free (adev, index);
Re: [PATCH 03/12] drm/amdgpu: switch all IPs to using job for IBs
Le 05/02/2026 à 15:20, Alex Deucher a écrit :
Quoted 101 lines
Quoted 99 lines · Pierre-Eric Pelloux-Prayer
Quoted 73 lines · Alex Deucher
Switch to using a job structure for IBs.
Acked-by Christian König <[email protected]>Signed-off-by Alex Deucher <[email protected]>--- drivers/gpu/drm/amd/amdgpu/amdgpu_vpe.c | 37 +++--- drivers/gpu/drm/amd/amdgpu/cik_sdma.c | 31 ++--- drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c | 29 ++--- drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c | 29 ++--- drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c | 29 ++--- drivers/gpu/drm/amd/amdgpu/gfx_v12_1.c | 29 ++--- drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c | 24 ++-- drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c | 25 ++-- drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c | 139 ++++++++++++----------- drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c | 138 +++++++++++----------- drivers/gpu/drm/amd/amdgpu/gfx_v9_4_2.c | 26 ++--- drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c | 29 ++--- drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c | 38 ++++--- drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c | 38 ++++--- drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c | 38 ++++--- drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c | 38 ++++--- drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c | 37 +++--- drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c | 36 +++--- drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c | 36 +++--- drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c | 36 +++--- drivers/gpu/drm/amd/amdgpu/sdma_v7_1.c | 36 +++--- drivers/gpu/drm/amd/amdgpu/si_dma.c | 29 +++-- 22 files changed, 500 insertions(+), 427 deletions(-)drivers/gpu/drm/amd/amdgpu/amdgpu_vpe.c +12
-15@@ -817,7 +817,8 @@ static int vpe_ring_test_ib(struct amdgpu_ring *ring, long timeout) {struct amdgpu_device *adev = ring->adev;const uint32_t test_pattern =0xdeadbeef ; -struct amdgpu_ib ib = {}; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ;uint32_t index;uint64_t wb_addr;@@ -832,23 +833,28 @@ static int vpe_ring_test_ib(struct amdgpu_ring *ring, long timeout) adev->wb.wb[index] =0 ; wb_addr = adev->wb.gpu_addr + (index *4 ); - ret =amdgpu_ib_get (adev,NULL ,256 ,AMDGPU_IB_POOL_DIRECT , &ib); + ret =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,256 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_VPE_RING_TEST );if (ret) goto err0; - - ib.ptr[0 ] =VPE_CMD_HEADER (VPE_CMD_OPCODE_FENCE ,0 ); - ib.ptr[1 ] =lower_32_bits (wb_addr); - ib.ptr[2 ] =upper_32_bits (wb_addr); - ib.ptr[3 ] = test_pattern; - ib.ptr[4 ] =VPE_CMD_HEADER (VPE_CMD_OPCODE_NOP ,0 ); - ib.ptr[5 ] =VPE_CMD_HEADER (VPE_CMD_OPCODE_NOP ,0 ); - ib.ptr[6 ] =VPE_CMD_HEADER (VPE_CMD_OPCODE_NOP ,0 ); - ib.ptr[7 ] =VPE_CMD_HEADER (VPE_CMD_OPCODE_NOP ,0 ); - ib.length_dw =8 ; - - ret =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (ret) + ib = &job->ibs[0 ]; + + ib->ptr[0 ] =VPE_CMD_HEADER (VPE_CMD_OPCODE_FENCE ,0 ); + ib->ptr[1 ] =lower_32_bits (wb_addr); + ib->ptr[2 ] =upper_32_bits (wb_addr); + ib->ptr[3 ] = test_pattern; + ib->ptr[4 ] =VPE_CMD_HEADER (VPE_CMD_OPCODE_NOP ,0 );drivers/gpu/drm/amd/amdgpu/amdgpu_vpe.c static int vpe_ring_test_ib(struct amdgpu_ring *ring, long timeout) · line 857
Quoted 10 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_vpe.c +9
-0+ ib->ptr[5 ] =VPE_CMD_HEADER (VPE_CMD_OPCODE_NOP ,0 ); + ib->ptr[6 ] =VPE_CMD_HEADER (VPE_CMD_OPCODE_NOP ,0 ); + ib->ptr[7 ] =VPE_CMD_HEADER (VPE_CMD_OPCODE_NOP ,0 ); + ib->length_dw =8 ; + + ret =amdgpu_job_submit_direct (job, ring, &f); +if (ret) { +amdgpu_job_free (job); goto err1; + }This is a nice cleanup. What about going one step further and provide a helper like:
u32 test_dws[] = { VPE_CMD_HEADER(VPE_CMD_OPCODE_FENCE, 0), lower_32_bits(wb_addr), ... }; ret = amdgpu_ring_run_dwords(ring, ARRAY_SIZE(test_dws), test_dws,timeout);
Quoted 3 lines
Quoted 1 line
Because that's what most
_ring_test_ibfunction do.I can look into that as a follow up series.
Sure.
In any case this patch is Acked-by me.
Pierre-Eric
Quoted 1,824 lines
Alex
Quoted 1,820 lines
Thanks,
Pierre-EricQuoted 1,817 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_vpe.c +0
-1ret =dma_fence_wait_timeout (f, false, timeout);if (ret <=0 ) {@@ -859,7 +865,6 @@ static int vpe_ring_test_ib(struct amdgpu_ring *ring, long timeout) ret = (le32_to_cpu (adev->wb.wb[index]) == test_pattern) ?0 : -EINVAL ; err1: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f); err0:amdgpu_device_wb_free (adev, index);drivers/gpu/drm/amd/amdgpu/cik_sdma.c +18
-13@@ -652,7 +652,8 @@ static int cik_sdma_ring_test_ring(struct amdgpu_ring *ring)static int cik_sdma_ring_test_ib (struct amdgpu_ring *ring,long timeout) {struct amdgpu_device *adev = ring->adev; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ;unsigned index;u32 tmp =0 ;@@ -666,22 +667,27 @@ static int cik_sdma_ring_test_ib(struct amdgpu_ring *ring, long timeout) gpu_addr = adev->wb.gpu_addr + (index *4 ); tmp =0xCAFEDEAD ; adev->wb.wb[index] =cpu_to_le32 (tmp); -memset (&ib,0 ,sizeof (ib)); - r =amdgpu_ib_get (adev,NULL ,256 , -AMDGPU_IB_POOL_DIRECT , &ib); + + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,256 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_SDMA_RING_TEST );if (r) goto err0; + ib = &job->ibs[0 ]; - ib.ptr[0 ] =SDMA_PACKET (SDMA_OPCODE_WRITE , + ib->ptr[0 ] =SDMA_PACKET (SDMA_OPCODE_WRITE ,SDMA_WRITE_SUB_OPCODE_LINEAR ,0 ); - ib.ptr[1 ] =lower_32_bits (gpu_addr); - ib.ptr[2 ] =upper_32_bits (gpu_addr); - ib.ptr[3 ] =1 ; - ib.ptr[4 ] =0xDEADBEEF ; - ib.length_dw =5 ; - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (r) + ib->ptr[1 ] =lower_32_bits (gpu_addr); + ib->ptr[2 ] =upper_32_bits (gpu_addr); + ib->ptr[3 ] =1 ; + ib->ptr[4 ] =0xDEADBEEF ; + ib->length_dw =5 ; + + r =amdgpu_job_submit_direct (job, ring, &f); +if (r) { +amdgpu_job_free (job); goto err1; + } r =dma_fence_wait_timeout (f, false, timeout);if (r ==0 ) {@@ -697,7 +703,6 @@ static int cik_sdma_ring_test_ib(struct amdgpu_ring *ring, long timeout) r = -EINVAL ; err1: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f); err0:amdgpu_device_wb_free (adev, index);drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c +16
-13@@ -4071,15 +4071,14 @@ static int gfx_v10_0_ring_test_ring(struct amdgpu_ring *ring)static int gfx_v10_0_ring_test_ib (struct amdgpu_ring *ring,long timeout) {struct amdgpu_device *adev = ring->adev; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ;unsigned int index;uint64_t gpu_addr;uint32_t *cpu_ptr;long r; -memset (&ib,0 ,sizeof (ib)); - r =amdgpu_device_wb_get (adev, &index);if (r)return r;@@ -4088,22 +4087,27 @@ static int gfx_v10_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) adev->wb.wb[index] =cpu_to_le32 (0xCAFEDEAD ); cpu_ptr = &adev->wb.wb[index]; - r =amdgpu_ib_get (adev,NULL ,20 ,AMDGPU_IB_POOL_DIRECT , &ib); + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,20 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_GFX_RING_TEST );if (r) {drm_err (adev_to_drm (adev),"failed to get ib (%ld).\n" , r); goto err1; } + ib = &job->ibs[0 ]; - ib.ptr[0 ] =PACKET3 (PACKET3_WRITE_DATA ,3 ); - ib.ptr[1 ] =WRITE_DATA_DST_SEL (5 ) |WR_CONFIRM ; - ib.ptr[2 ] =lower_32_bits (gpu_addr); - ib.ptr[3 ] =upper_32_bits (gpu_addr); - ib.ptr[4 ] =0xDEADBEEF ; - ib.length_dw =5 ; + ib->ptr[0 ] =PACKET3 (PACKET3_WRITE_DATA ,3 ); + ib->ptr[1 ] =WRITE_DATA_DST_SEL (5 ) |WR_CONFIRM ; + ib->ptr[2 ] =lower_32_bits (gpu_addr); + ib->ptr[3 ] =upper_32_bits (gpu_addr); + ib->ptr[4 ] =0xDEADBEEF ; + ib->length_dw =5 ; - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (r) + r =amdgpu_job_submit_direct (job, ring, &f); +if (r) { +amdgpu_job_free (job); goto err2; + } r =dma_fence_wait_timeout (f, false, timeout);if (r ==0 ) {@@ -4118,7 +4122,6 @@ static int gfx_v10_0_ring_test_ib(struct amdgpu_ring *ring, long timeout)else r = -EINVAL ; err2: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f); err1:amdgpu_device_wb_free (adev, index);drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c +16
-13@@ -604,7 +604,8 @@ static int gfx_v11_0_ring_test_ring(struct amdgpu_ring *ring)static int gfx_v11_0_ring_test_ib (struct amdgpu_ring *ring,long timeout) {struct amdgpu_device *adev = ring->adev; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ;unsigned index;uint64_t gpu_addr;@@ -616,8 +617,6 @@ static int gfx_v11_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) ring->funcs->type == AMDGPU_RING_TYPE_KIQ)return 0 ; -memset (&ib,0 ,sizeof (ib)); - r =amdgpu_device_wb_get (adev, &index);if (r)return r;@@ -626,22 +625,27 @@ static int gfx_v11_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) adev->wb.wb[index] =cpu_to_le32 (0xCAFEDEAD ); cpu_ptr = &adev->wb.wb[index]; - r =amdgpu_ib_get (adev,NULL ,20 ,AMDGPU_IB_POOL_DIRECT , &ib); + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,20 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_GFX_RING_TEST );if (r) {drm_err (adev_to_drm (adev),"failed to get ib (%ld).\n" , r); goto err1; } + ib = &job->ibs[0 ]; - ib.ptr[0 ] =PACKET3 (PACKET3_WRITE_DATA ,3 ); - ib.ptr[1 ] =WRITE_DATA_DST_SEL (5 ) |WR_CONFIRM ; - ib.ptr[2 ] =lower_32_bits (gpu_addr); - ib.ptr[3 ] =upper_32_bits (gpu_addr); - ib.ptr[4 ] =0xDEADBEEF ; - ib.length_dw =5 ; + ib->ptr[0 ] =PACKET3 (PACKET3_WRITE_DATA ,3 ); + ib->ptr[1 ] =WRITE_DATA_DST_SEL (5 ) |WR_CONFIRM ; + ib->ptr[2 ] =lower_32_bits (gpu_addr); + ib->ptr[3 ] =upper_32_bits (gpu_addr); + ib->ptr[4 ] =0xDEADBEEF ; + ib->length_dw =5 ; - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (r) + r =amdgpu_job_submit_direct (job, ring, &f); +if (r) { +amdgpu_job_free (job); goto err2; + } r =dma_fence_wait_timeout (f, false, timeout);if (r ==0 ) {@@ -656,7 +660,6 @@ static int gfx_v11_0_ring_test_ib(struct amdgpu_ring *ring, long timeout)else r = -EINVAL ; err2: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f); err1:amdgpu_device_wb_free (adev, index);drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c +16
-13@@ -493,7 +493,8 @@ static int gfx_v12_0_ring_test_ring(struct amdgpu_ring *ring)static int gfx_v12_0_ring_test_ib (struct amdgpu_ring *ring,long timeout) {struct amdgpu_device *adev = ring->adev; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ;unsigned index;uint64_t gpu_addr;@@ -505,8 +506,6 @@ static int gfx_v12_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) ring->funcs->type == AMDGPU_RING_TYPE_KIQ)return 0 ; -memset (&ib,0 ,sizeof (ib)); - r =amdgpu_device_wb_get (adev, &index);if (r)return r;@@ -515,22 +514,27 @@ static int gfx_v12_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) adev->wb.wb[index] =cpu_to_le32 (0xCAFEDEAD ); cpu_ptr = &adev->wb.wb[index]; - r =amdgpu_ib_get (adev,NULL ,16 ,AMDGPU_IB_POOL_DIRECT , &ib); + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,16 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_GFX_RING_TEST );if (r) {drm_err (adev_to_drm (adev),"failed to get ib (%ld).\n" , r); goto err1; } + ib = &job->ibs[0 ]; - ib.ptr[0 ] =PACKET3 (PACKET3_WRITE_DATA ,3 ); - ib.ptr[1 ] =WRITE_DATA_DST_SEL (5 ) |WR_CONFIRM ; - ib.ptr[2 ] =lower_32_bits (gpu_addr); - ib.ptr[3 ] =upper_32_bits (gpu_addr); - ib.ptr[4 ] =0xDEADBEEF ; - ib.length_dw =5 ; + ib->ptr[0 ] =PACKET3 (PACKET3_WRITE_DATA ,3 ); + ib->ptr[1 ] =WRITE_DATA_DST_SEL (5 ) |WR_CONFIRM ; + ib->ptr[2 ] =lower_32_bits (gpu_addr); + ib->ptr[3 ] =upper_32_bits (gpu_addr); + ib->ptr[4 ] =0xDEADBEEF ; + ib->length_dw =5 ; - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (r) + r =amdgpu_job_submit_direct (job, ring, &f); +if (r) { +amdgpu_job_free (job); goto err2; + } r =dma_fence_wait_timeout (f, false, timeout);if (r ==0 ) {@@ -545,7 +549,6 @@ static int gfx_v12_0_ring_test_ib(struct amdgpu_ring *ring, long timeout)else r = -EINVAL ; err2: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f); err1:amdgpu_device_wb_free (adev, index);drivers/gpu/drm/amd/amdgpu/gfx_v12_1.c +16
-13@@ -307,7 +307,8 @@ static int gfx_v12_1_ring_test_ring(struct amdgpu_ring *ring)static int gfx_v12_1_ring_test_ib (struct amdgpu_ring *ring,long timeout) {struct amdgpu_device *adev = ring->adev; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ;unsigned index;uint64_t gpu_addr;@@ -319,8 +320,6 @@ static int gfx_v12_1_ring_test_ib(struct amdgpu_ring *ring, long timeout) ring->funcs->type == AMDGPU_RING_TYPE_KIQ)return 0 ; -memset (&ib,0 ,sizeof (ib)); - r =amdgpu_device_wb_get (adev, &index);if (r)return r;@@ -329,22 +328,27 @@ static int gfx_v12_1_ring_test_ib(struct amdgpu_ring *ring, long timeout) adev->wb.wb[index] =cpu_to_le32 (0xCAFEDEAD ); cpu_ptr = &adev->wb.wb[index]; - r =amdgpu_ib_get (adev,NULL ,16 ,AMDGPU_IB_POOL_DIRECT , &ib); + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,16 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_GFX_RING_TEST );if (r) {dev_err (adev->dev,"amdgpu: failed to get ib (%ld).\n" , r); goto err1; } + ib = &job->ibs[0 ]; - ib.ptr[0 ] =PACKET3 (PACKET3_WRITE_DATA ,3 ); - ib.ptr[1 ] =WRITE_DATA_DST_SEL (5 ) |WR_CONFIRM ; - ib.ptr[2 ] =lower_32_bits (gpu_addr); - ib.ptr[3 ] =upper_32_bits (gpu_addr); - ib.ptr[4 ] =0xDEADBEEF ; - ib.length_dw =5 ; + ib->ptr[0 ] =PACKET3 (PACKET3_WRITE_DATA ,3 ); + ib->ptr[1 ] =WRITE_DATA_DST_SEL (5 ) |WR_CONFIRM ; + ib->ptr[2 ] =lower_32_bits (gpu_addr); + ib->ptr[3 ] =upper_32_bits (gpu_addr); + ib->ptr[4 ] =0xDEADBEEF ; + ib->length_dw =5 ; - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (r) + r =amdgpu_job_submit_direct (job, ring, &f); +if (r) { +amdgpu_job_free (job); goto err2; + } r =dma_fence_wait_timeout (f, false, timeout);if (r ==0 ) {@@ -359,7 +363,6 @@ static int gfx_v12_1_ring_test_ib(struct amdgpu_ring *ring, long timeout)else r = -EINVAL ; err2: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f); err1:amdgpu_device_wb_free (adev, index);drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c +14
-10@@ -1895,24 +1895,29 @@ static int gfx_v6_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) {struct amdgpu_device *adev = ring->adev;struct dma_fence *f =NULL ; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;uint32_t tmp =0 ;long r;WREG32 (mmSCRATCH_REG0,0xCAFEDEAD ); -memset (&ib,0 ,sizeof (ib)); - r =amdgpu_ib_get (adev,NULL ,256 ,AMDGPU_IB_POOL_DIRECT , &ib); + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,256 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_GFX_RING_TEST );if (r)return r; - ib.ptr[0 ] =PACKET3 (PACKET3_SET_CONFIG_REG ,1 ); - ib.ptr[1 ] = mmSCRATCH_REG0 -PACKET3_SET_CONFIG_REG_START ; - ib.ptr[2 ] =0xDEADBEEF ; - ib.length_dw =3 ; + ib = &job->ibs[0 ]; + ib->ptr[0 ] =PACKET3 (PACKET3_SET_CONFIG_REG ,1 ); + ib->ptr[1 ] = mmSCRATCH_REG0 -PACKET3_SET_CONFIG_REG_START ; + ib->ptr[2 ] =0xDEADBEEF ; + ib->length_dw =3 ; - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (r) + r =amdgpu_job_submit_direct (job, ring, &f); +if (r) { +amdgpu_job_free (job); goto error; + } r =dma_fence_wait_timeout (f, false, timeout);if (r ==0 ) {@@ -1928,7 +1933,6 @@ static int gfx_v6_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) r = -EINVAL ; error: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f);return r; }drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c +15
-10@@ -2291,25 +2291,31 @@ static void gfx_v7_ring_emit_cntxcntl(struct amdgpu_ring *ring, uint32_t flags)static int gfx_v7_0_ring_test_ib (struct amdgpu_ring *ring,long timeout) {struct amdgpu_device *adev = ring->adev; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ;uint32_t tmp =0 ;long r;WREG32 (mmSCRATCH_REG0,0xCAFEDEAD ); -memset (&ib,0 ,sizeof (ib)); - r =amdgpu_ib_get (adev,NULL ,256 ,AMDGPU_IB_POOL_DIRECT , &ib); + + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,256 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_GFX_RING_TEST );if (r)return r; - ib.ptr[0 ] =PACKET3 (PACKET3_SET_UCONFIG_REG ,1 ); - ib.ptr[1 ] = mmSCRATCH_REG0 -PACKET3_SET_UCONFIG_REG_START ; - ib.ptr[2 ] =0xDEADBEEF ; - ib.length_dw =3 ; + ib = &job->ibs[0 ]; + ib->ptr[0 ] =PACKET3 (PACKET3_SET_UCONFIG_REG ,1 ); + ib->ptr[1 ] = mmSCRATCH_REG0 -PACKET3_SET_UCONFIG_REG_START ; + ib->ptr[2 ] =0xDEADBEEF ; + ib->length_dw =3 ; - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (r) + r =amdgpu_job_submit_direct (job, ring, &f); +if (r) { +amdgpu_job_free (job); goto error; + } r =dma_fence_wait_timeout (f, false, timeout);if (r ==0 ) {@@ -2325,7 +2331,6 @@ static int gfx_v7_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) r = -EINVAL ; error: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f);return r; }drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +72
-67@@ -868,9 +868,9 @@ static int gfx_v8_0_ring_test_ring(struct amdgpu_ring *ring)static int gfx_v8_0_ring_test_ib (struct amdgpu_ring *ring,long timeout) {struct amdgpu_device *adev = ring->adev; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ; -unsigned int index;uint64_t gpu_addr;uint32_t tmp;@@ -882,22 +882,26 @@ static int gfx_v8_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) gpu_addr = adev->wb.gpu_addr + (index *4 ); adev->wb.wb[index] =cpu_to_le32 (0xCAFEDEAD ); -memset (&ib,0 ,sizeof (ib)); - r =amdgpu_ib_get (adev,NULL ,20 ,AMDGPU_IB_POOL_DIRECT , &ib); + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,20 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_GFX_RING_TEST );if (r) goto err1; - ib.ptr[0 ] =PACKET3 (PACKET3_WRITE_DATA ,3 ); - ib.ptr[1 ] =WRITE_DATA_DST_SEL (5 ) |WR_CONFIRM ; - ib.ptr[2 ] =lower_32_bits (gpu_addr); - ib.ptr[3 ] =upper_32_bits (gpu_addr); - ib.ptr[4 ] =0xDEADBEEF ; - ib.length_dw =5 ; + ib = &job->ibs[0 ]; + ib->ptr[0 ] =PACKET3 (PACKET3_WRITE_DATA ,3 ); + ib->ptr[1 ] =WRITE_DATA_DST_SEL (5 ) |WR_CONFIRM ; + ib->ptr[2 ] =lower_32_bits (gpu_addr); + ib->ptr[3 ] =upper_32_bits (gpu_addr); + ib->ptr[4 ] =0xDEADBEEF ; + ib->length_dw =5 ; - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (r) + r =amdgpu_job_submit_direct (job, ring, &f); +if (r) { +amdgpu_job_free (job); goto err2; + } r =dma_fence_wait_timeout (f, false, timeout);if (r ==0 ) {@@ -914,7 +918,6 @@ static int gfx_v8_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) r = -EINVAL ; err2: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f); err1:amdgpu_device_wb_free (adev, index);@@ -1474,7 +1477,8 @@ static const u32 sec_ded_counter_registers[] =static int gfx_v8_0_do_edc_gpr_workarounds (struct amdgpu_device *adev) {struct amdgpu_ring *ring = &adev->gfx.compute_ring[0 ]; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ;int r, i;u32 tmp;@@ -1505,106 +1509,108 @@ static int gfx_v8_0_do_edc_gpr_workarounds(struct amdgpu_device *adev) total_size +=sizeof (sgpr_init_compute_shader);/* allocate an indirect buffer to put the commands in */ -memset (&ib,0 ,sizeof (ib)); - r =amdgpu_ib_get (adev,NULL , total_size, -AMDGPU_IB_POOL_DIRECT , &ib); + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL , total_size, +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_RUN_SHADER );if (r) {drm_err (adev_to_drm (adev),"failed to get ib (%d).\n" , r);return r; } + ib = &job->ibs[0 ];/* load the compute shaders */ for (i =0 ; i <ARRAY_SIZE (vgpr_init_compute_shader); i++) - ib.ptr[i + (vgpr_offset /4 )] = vgpr_init_compute_shader[i]; + ib->ptr[i + (vgpr_offset /4 )] = vgpr_init_compute_shader[i];for (i =0 ; i <ARRAY_SIZE (sgpr_init_compute_shader); i++) - ib.ptr[i + (sgpr_offset /4 )] = sgpr_init_compute_shader[i]; + ib->ptr[i + (sgpr_offset /4 )] = sgpr_init_compute_shader[i];/* init the ib length to 0 */ - ib.length_dw =0 ; + ib->length_dw =0 ;/* VGPR */ /* write the register state for the compute dispatch */ for (i =0 ; i <ARRAY_SIZE (vgpr_init_regs); i +=2 ) { - ib.ptr[ib.length_dw++] =PACKET3 (PACKET3_SET_SH_REG ,1 ); - ib.ptr[ib.length_dw++] = vgpr_init_regs[i] -PACKET3_SET_SH_REG_START ; - ib.ptr[ib.length_dw++] = vgpr_init_regs[i +1 ]; + ib->ptr[ib->length_dw++] =PACKET3 (PACKET3_SET_SH_REG ,1 ); + ib->ptr[ib->length_dw++] = vgpr_init_regs[i] -PACKET3_SET_SH_REG_START ; + ib->ptr[ib->length_dw++] = vgpr_init_regs[i +1 ]; }/* write the shader start address: mmCOMPUTE_PGM_LO, mmCOMPUTE_PGM_HI */ - gpu_addr = (ib.gpu_addr + (u64 )vgpr_offset) >>8 ; - ib.ptr[ib.length_dw++] =PACKET3 (PACKET3_SET_SH_REG ,2 ); - ib.ptr[ib.length_dw++] = mmCOMPUTE_PGM_LO -PACKET3_SET_SH_REG_START ; - ib.ptr[ib.length_dw++] =lower_32_bits (gpu_addr); - ib.ptr[ib.length_dw++] =upper_32_bits (gpu_addr); + gpu_addr = (ib->gpu_addr + (u64 )vgpr_offset) >>8 ; + ib->ptr[ib->length_dw++] =PACKET3 (PACKET3_SET_SH_REG ,2 ); + ib->ptr[ib->length_dw++] = mmCOMPUTE_PGM_LO -PACKET3_SET_SH_REG_START ; + ib->ptr[ib->length_dw++] =lower_32_bits (gpu_addr); + ib->ptr[ib->length_dw++] =upper_32_bits (gpu_addr);/* write dispatch packet */ - ib.ptr[ib.length_dw++] =PACKET3 (PACKET3_DISPATCH_DIRECT ,3 ); - ib.ptr[ib.length_dw++] =8 ;/* x */ - ib.ptr[ib.length_dw++] =1 ;/* y */ - ib.ptr[ib.length_dw++] =1 ;/* z */ - ib.ptr[ib.length_dw++] = + ib->ptr[ib->length_dw++] =PACKET3 (PACKET3_DISPATCH_DIRECT ,3 ); + ib->ptr[ib->length_dw++] =8 ;/* x */ + ib->ptr[ib->length_dw++] =1 ;/* y */ + ib->ptr[ib->length_dw++] =1 ;/* z */ + ib->ptr[ib->length_dw++] =REG_SET_FIELD (0 ,COMPUTE_DISPATCH_INITIATOR ,COMPUTE_SHADER_EN ,1 );/* write CS partial flush packet */ - ib.ptr[ib.length_dw++] =PACKET3 (PACKET3_EVENT_WRITE ,0 ); - ib.ptr[ib.length_dw++] =EVENT_TYPE (7 ) |EVENT_INDEX (4 ); + ib->ptr[ib->length_dw++] =PACKET3 (PACKET3_EVENT_WRITE ,0 ); + ib->ptr[ib->length_dw++] =EVENT_TYPE (7 ) |EVENT_INDEX (4 );/* SGPR1 */ /* write the register state for the compute dispatch */ for (i =0 ; i <ARRAY_SIZE (sgpr1_init_regs); i +=2 ) { - ib.ptr[ib.length_dw++] =PACKET3 (PACKET3_SET_SH_REG ,1 ); - ib.ptr[ib.length_dw++] = sgpr1_init_regs[i] -PACKET3_SET_SH_REG_START ; - ib.ptr[ib.length_dw++] = sgpr1_init_regs[i +1 ]; + ib->ptr[ib->length_dw++] =PACKET3 (PACKET3_SET_SH_REG ,1 ); + ib->ptr[ib->length_dw++] = sgpr1_init_regs[i] -PACKET3_SET_SH_REG_START ; + ib->ptr[ib->length_dw++] = sgpr1_init_regs[i +1 ]; }/* write the shader start address: mmCOMPUTE_PGM_LO, mmCOMPUTE_PGM_HI */ - gpu_addr = (ib.gpu_addr + (u64 )sgpr_offset) >>8 ; - ib.ptr[ib.length_dw++] =PACKET3 (PACKET3_SET_SH_REG ,2 ); - ib.ptr[ib.length_dw++] = mmCOMPUTE_PGM_LO -PACKET3_SET_SH_REG_START ; - ib.ptr[ib.length_dw++] =lower_32_bits (gpu_addr); - ib.ptr[ib.length_dw++] =upper_32_bits (gpu_addr); + gpu_addr = (ib->gpu_addr + (u64 )sgpr_offset) >>8 ; + ib->ptr[ib->length_dw++] =PACKET3 (PACKET3_SET_SH_REG ,2 ); + ib->ptr[ib->length_dw++] = mmCOMPUTE_PGM_LO -PACKET3_SET_SH_REG_START ; + ib->ptr[ib->length_dw++] =lower_32_bits (gpu_addr); + ib->ptr[ib->length_dw++] =upper_32_bits (gpu_addr);/* write dispatch packet */ - ib.ptr[ib.length_dw++] =PACKET3 (PACKET3_DISPATCH_DIRECT ,3 ); - ib.ptr[ib.length_dw++] =8 ;/* x */ - ib.ptr[ib.length_dw++] =1 ;/* y */ - ib.ptr[ib.length_dw++] =1 ;/* z */ - ib.ptr[ib.length_dw++] = + ib->ptr[ib->length_dw++] =PACKET3 (PACKET3_DISPATCH_DIRECT ,3 ); + ib->ptr[ib->length_dw++] =8 ;/* x */ + ib->ptr[ib->length_dw++] =1 ;/* y */ + ib->ptr[ib->length_dw++] =1 ;/* z */ + ib->ptr[ib->length_dw++] =REG_SET_FIELD (0 ,COMPUTE_DISPATCH_INITIATOR ,COMPUTE_SHADER_EN ,1 );/* write CS partial flush packet */ - ib.ptr[ib.length_dw++] =PACKET3 (PACKET3_EVENT_WRITE ,0 ); - ib.ptr[ib.length_dw++] =EVENT_TYPE (7 ) |EVENT_INDEX (4 ); + ib->ptr[ib->length_dw++] =PACKET3 (PACKET3_EVENT_WRITE ,0 ); + ib->ptr[ib->length_dw++] =EVENT_TYPE (7 ) |EVENT_INDEX (4 );/* SGPR2 */ /* write the register state for the compute dispatch */ for (i =0 ; i <ARRAY_SIZE (sgpr2_init_regs); i +=2 ) { - ib.ptr[ib.length_dw++] =PACKET3 (PACKET3_SET_SH_REG ,1 ); - ib.ptr[ib.length_dw++] = sgpr2_init_regs[i] -PACKET3_SET_SH_REG_START ; - ib.ptr[ib.length_dw++] = sgpr2_init_regs[i +1 ]; + ib->ptr[ib->length_dw++] =PACKET3 (PACKET3_SET_SH_REG ,1 ); + ib->ptr[ib->length_dw++] = sgpr2_init_regs[i] -PACKET3_SET_SH_REG_START ; + ib->ptr[ib->length_dw++] = sgpr2_init_regs[i +1 ]; }/* write the shader start address: mmCOMPUTE_PGM_LO, mmCOMPUTE_PGM_HI */ - gpu_addr = (ib.gpu_addr + (u64 )sgpr_offset) >>8 ; - ib.ptr[ib.length_dw++] =PACKET3 (PACKET3_SET_SH_REG ,2 ); - ib.ptr[ib.length_dw++] = mmCOMPUTE_PGM_LO -PACKET3_SET_SH_REG_START ; - ib.ptr[ib.length_dw++] =lower_32_bits (gpu_addr); - ib.ptr[ib.length_dw++] =upper_32_bits (gpu_addr); + gpu_addr = (ib->gpu_addr + (u64 )sgpr_offset) >>8 ; + ib->ptr[ib->length_dw++] =PACKET3 (PACKET3_SET_SH_REG ,2 ); + ib->ptr[ib->length_dw++] = mmCOMPUTE_PGM_LO -PACKET3_SET_SH_REG_START ; + ib->ptr[ib->length_dw++] =lower_32_bits (gpu_addr); + ib->ptr[ib->length_dw++] =upper_32_bits (gpu_addr);/* write dispatch packet */ - ib.ptr[ib.length_dw++] =PACKET3 (PACKET3_DISPATCH_DIRECT ,3 ); - ib.ptr[ib.length_dw++] =8 ;/* x */ - ib.ptr[ib.length_dw++] =1 ;/* y */ - ib.ptr[ib.length_dw++] =1 ;/* z */ - ib.ptr[ib.length_dw++] = + ib->ptr[ib->length_dw++] =PACKET3 (PACKET3_DISPATCH_DIRECT ,3 ); + ib->ptr[ib->length_dw++] =8 ;/* x */ + ib->ptr[ib->length_dw++] =1 ;/* y */ + ib->ptr[ib->length_dw++] =1 ;/* z */ + ib->ptr[ib->length_dw++] =REG_SET_FIELD (0 ,COMPUTE_DISPATCH_INITIATOR ,COMPUTE_SHADER_EN ,1 );/* write CS partial flush packet */ - ib.ptr[ib.length_dw++] =PACKET3 (PACKET3_EVENT_WRITE ,0 ); - ib.ptr[ib.length_dw++] =EVENT_TYPE (7 ) |EVENT_INDEX (4 ); + ib->ptr[ib->length_dw++] =PACKET3 (PACKET3_EVENT_WRITE ,0 ); + ib->ptr[ib->length_dw++] =EVENT_TYPE (7 ) |EVENT_INDEX (4 );/* shedule the ib on the ring */ - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); + r =amdgpu_job_submit_direct (job, ring, &f);if (r) {drm_err (adev_to_drm (adev),"ib submit failed (%d).\n" , r); +amdgpu_job_free (job); goto fail; }@@ -1629,7 +1635,6 @@ static int gfx_v8_0_do_edc_gpr_workarounds(struct amdgpu_device *adev)RREG32 (sec_ded_counter_registers[i]); fail: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f);return r;drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +71
-67@@ -1224,9 +1224,9 @@ static int gfx_v9_0_ring_test_ring(struct amdgpu_ring *ring)static int gfx_v9_0_ring_test_ib (struct amdgpu_ring *ring,long timeout) {struct amdgpu_device *adev = ring->adev; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ; -unsigned index;uint64_t gpu_addr;uint32_t tmp;@@ -1238,22 +1238,26 @@ static int gfx_v9_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) gpu_addr = adev->wb.gpu_addr + (index *4 ); adev->wb.wb[index] =cpu_to_le32 (0xCAFEDEAD ); -memset (&ib,0 ,sizeof (ib)); - r =amdgpu_ib_get (adev,NULL ,20 ,AMDGPU_IB_POOL_DIRECT , &ib); + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,20 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_GFX_RING_TEST );if (r) goto err1; - ib.ptr[0 ] =PACKET3 (PACKET3_WRITE_DATA ,3 ); - ib.ptr[1 ] =WRITE_DATA_DST_SEL (5 ) |WR_CONFIRM ; - ib.ptr[2 ] =lower_32_bits (gpu_addr); - ib.ptr[3 ] =upper_32_bits (gpu_addr); - ib.ptr[4 ] =0xDEADBEEF ; - ib.length_dw =5 ; + ib = &job->ibs[0 ]; + ib->ptr[0 ] =PACKET3 (PACKET3_WRITE_DATA ,3 ); + ib->ptr[1 ] =WRITE_DATA_DST_SEL (5 ) |WR_CONFIRM ; + ib->ptr[2 ] =lower_32_bits (gpu_addr); + ib->ptr[3 ] =upper_32_bits (gpu_addr); + ib->ptr[4 ] =0xDEADBEEF ; + ib->length_dw =5 ; - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (r) + r =amdgpu_job_submit_direct (job, ring, &f); +if (r) { +amdgpu_job_free (job); goto err2; + } r =dma_fence_wait_timeout (f, false, timeout);if (r ==0 ) {@@ -1270,7 +1274,6 @@ static int gfx_v9_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) r = -EINVAL ; err2: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f); err1:amdgpu_device_wb_free (adev, index);@@ -4624,7 +4627,8 @@ static int gfx_v9_0_do_edc_gds_workarounds(struct amdgpu_device *adev)static int gfx_v9_0_do_edc_gpr_workarounds (struct amdgpu_device *adev) {struct amdgpu_ring *ring = &adev->gfx.compute_ring[0 ]; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ;int r, i;unsigned total_size, vgpr_offset, sgpr_offset;@@ -4670,9 +4674,9 @@ static int gfx_v9_0_do_edc_gpr_workarounds(struct amdgpu_device *adev) total_size +=sizeof (sgpr_init_compute_shader);/* allocate an indirect buffer to put the commands in */ -memset (&ib,0 ,sizeof (ib)); - r =amdgpu_ib_get (adev,NULL , total_size, -AMDGPU_IB_POOL_DIRECT , &ib); + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL , total_size, +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_RUN_SHADER );if (r) {drm_err (adev_to_drm (adev),"failed to get ib (%d).\n" , r);return r;@@ -4680,102 +4684,103 @@ static int gfx_v9_0_do_edc_gpr_workarounds(struct amdgpu_device *adev)/* load the compute shaders */ for (i =0 ; i < vgpr_init_shader_size/sizeof (u32); i++) - ib.ptr[i + (vgpr_offset /4 )] = vgpr_init_shader_ptr[i]; + ib->ptr[i + (vgpr_offset /4 )] = vgpr_init_shader_ptr[i];for (i =0 ; i <ARRAY_SIZE (sgpr_init_compute_shader); i++) - ib.ptr[i + (sgpr_offset /4 )] = sgpr_init_compute_shader[i]; + ib->ptr[i + (sgpr_offset /4 )] = sgpr_init_compute_shader[i];/* init the ib length to 0 */ - ib.length_dw =0 ; + ib->length_dw =0 ;/* VGPR */ /* write the register state for the compute dispatch */ for (i =0 ; i < gpr_reg_size; i++) { - ib.ptr[ib.length_dw++] =PACKET3 (PACKET3_SET_SH_REG ,1 ); - ib.ptr[ib.length_dw++] =SOC15_REG_ENTRY_OFFSET (vgpr_init_regs_ptr[i]) + ib->ptr[ib->length_dw++] =PACKET3 (PACKET3_SET_SH_REG ,1 ); + ib->ptr[ib->length_dw++] =SOC15_REG_ENTRY_OFFSET (vgpr_init_regs_ptr[i]) -PACKET3_SET_SH_REG_START ; - ib.ptr[ib.length_dw++] = vgpr_init_regs_ptr[i].reg_value; + ib->ptr[ib->length_dw++] = vgpr_init_regs_ptr[i].reg_value; }/* write the shader start address: mmCOMPUTE_PGM_LO, mmCOMPUTE_PGM_HI */ - gpu_addr = (ib.gpu_addr + (u64 )vgpr_offset) >>8 ; - ib.ptr[ib.length_dw++] =PACKET3 (PACKET3_SET_SH_REG ,2 ); - ib.ptr[ib.length_dw++] =SOC15_REG_OFFSET (GC ,0 , mmCOMPUTE_PGM_LO) + gpu_addr = (ib->gpu_addr + (u64 )vgpr_offset) >>8 ; + ib->ptr[ib->length_dw++] =PACKET3 (PACKET3_SET_SH_REG ,2 ); + ib->ptr[ib->length_dw++] =SOC15_REG_OFFSET (GC ,0 , mmCOMPUTE_PGM_LO) -PACKET3_SET_SH_REG_START ; - ib.ptr[ib.length_dw++] =lower_32_bits (gpu_addr); - ib.ptr[ib.length_dw++] =upper_32_bits (gpu_addr); + ib->ptr[ib->length_dw++] =lower_32_bits (gpu_addr); + ib->ptr[ib->length_dw++] =upper_32_bits (gpu_addr);/* write dispatch packet */ - ib.ptr[ib.length_dw++] =PACKET3 (PACKET3_DISPATCH_DIRECT ,3 ); - ib.ptr[ib.length_dw++] = compute_dim_x *2 ;/* x */ - ib.ptr[ib.length_dw++] =1 ;/* y */ - ib.ptr[ib.length_dw++] =1 ;/* z */ - ib.ptr[ib.length_dw++] = + ib->ptr[ib->length_dw++] =PACKET3 (PACKET3_DISPATCH_DIRECT ,3 ); + ib->ptr[ib->length_dw++] = compute_dim_x *2 ;/* x */ + ib->ptr[ib->length_dw++] =1 ;/* y */ + ib->ptr[ib->length_dw++] =1 ;/* z */ + ib->ptr[ib->length_dw++] =REG_SET_FIELD (0 ,COMPUTE_DISPATCH_INITIATOR ,COMPUTE_SHADER_EN ,1 );/* write CS partial flush packet */ - ib.ptr[ib.length_dw++] =PACKET3 (PACKET3_EVENT_WRITE ,0 ); - ib.ptr[ib.length_dw++] =EVENT_TYPE (7 ) |EVENT_INDEX (4 ); + ib->ptr[ib->length_dw++] =PACKET3 (PACKET3_EVENT_WRITE ,0 ); + ib->ptr[ib->length_dw++] =EVENT_TYPE (7 ) |EVENT_INDEX (4 );/* SGPR1 */ /* write the register state for the compute dispatch */ for (i =0 ; i < gpr_reg_size; i++) { - ib.ptr[ib.length_dw++] =PACKET3 (PACKET3_SET_SH_REG ,1 ); - ib.ptr[ib.length_dw++] =SOC15_REG_ENTRY_OFFSET (sgpr1_init_regs[i]) + ib->ptr[ib->length_dw++] =PACKET3 (PACKET3_SET_SH_REG ,1 ); + ib->ptr[ib->length_dw++] =SOC15_REG_ENTRY_OFFSET (sgpr1_init_regs[i]) -PACKET3_SET_SH_REG_START ; - ib.ptr[ib.length_dw++] = sgpr1_init_regs[i].reg_value; + ib->ptr[ib->length_dw++] = sgpr1_init_regs[i].reg_value; }/* write the shader start address: mmCOMPUTE_PGM_LO, mmCOMPUTE_PGM_HI */ - gpu_addr = (ib.gpu_addr + (u64 )sgpr_offset) >>8 ; - ib.ptr[ib.length_dw++] =PACKET3 (PACKET3_SET_SH_REG ,2 ); - ib.ptr[ib.length_dw++] =SOC15_REG_OFFSET (GC ,0 , mmCOMPUTE_PGM_LO) + gpu_addr = (ib->gpu_addr + (u64 )sgpr_offset) >>8 ; + ib->ptr[ib->length_dw++] =PACKET3 (PACKET3_SET_SH_REG ,2 ); + ib->ptr[ib->length_dw++] =SOC15_REG_OFFSET (GC ,0 , mmCOMPUTE_PGM_LO) -PACKET3_SET_SH_REG_START ; - ib.ptr[ib.length_dw++] =lower_32_bits (gpu_addr); - ib.ptr[ib.length_dw++] =upper_32_bits (gpu_addr); + ib->ptr[ib->length_dw++] =lower_32_bits (gpu_addr); + ib->ptr[ib->length_dw++] =upper_32_bits (gpu_addr);/* write dispatch packet */ - ib.ptr[ib.length_dw++] =PACKET3 (PACKET3_DISPATCH_DIRECT ,3 ); - ib.ptr[ib.length_dw++] = compute_dim_x /2 * sgpr_work_group_size;/* x */ - ib.ptr[ib.length_dw++] =1 ;/* y */ - ib.ptr[ib.length_dw++] =1 ;/* z */ - ib.ptr[ib.length_dw++] = + ib->ptr[ib->length_dw++] =PACKET3 (PACKET3_DISPATCH_DIRECT ,3 ); + ib->ptr[ib->length_dw++] = compute_dim_x /2 * sgpr_work_group_size;/* x */ + ib->ptr[ib->length_dw++] =1 ;/* y */ + ib->ptr[ib->length_dw++] =1 ;/* z */ + ib->ptr[ib->length_dw++] =REG_SET_FIELD (0 ,COMPUTE_DISPATCH_INITIATOR ,COMPUTE_SHADER_EN ,1 );/* write CS partial flush packet */ - ib.ptr[ib.length_dw++] =PACKET3 (PACKET3_EVENT_WRITE ,0 ); - ib.ptr[ib.length_dw++] =EVENT_TYPE (7 ) |EVENT_INDEX (4 ); + ib->ptr[ib->length_dw++] =PACKET3 (PACKET3_EVENT_WRITE ,0 ); + ib->ptr[ib->length_dw++] =EVENT_TYPE (7 ) |EVENT_INDEX (4 );/* SGPR2 */ /* write the register state for the compute dispatch */ for (i =0 ; i < gpr_reg_size; i++) { - ib.ptr[ib.length_dw++] =PACKET3 (PACKET3_SET_SH_REG ,1 ); - ib.ptr[ib.length_dw++] =SOC15_REG_ENTRY_OFFSET (sgpr2_init_regs[i]) + ib->ptr[ib->length_dw++] =PACKET3 (PACKET3_SET_SH_REG ,1 ); + ib->ptr[ib->length_dw++] =SOC15_REG_ENTRY_OFFSET (sgpr2_init_regs[i]) -PACKET3_SET_SH_REG_START ; - ib.ptr[ib.length_dw++] = sgpr2_init_regs[i].reg_value; + ib->ptr[ib->length_dw++] = sgpr2_init_regs[i].reg_value; }/* write the shader start address: mmCOMPUTE_PGM_LO, mmCOMPUTE_PGM_HI */ - gpu_addr = (ib.gpu_addr + (u64 )sgpr_offset) >>8 ; - ib.ptr[ib.length_dw++] =PACKET3 (PACKET3_SET_SH_REG ,2 ); - ib.ptr[ib.length_dw++] =SOC15_REG_OFFSET (GC ,0 , mmCOMPUTE_PGM_LO) + gpu_addr = (ib->gpu_addr + (u64 )sgpr_offset) >>8 ; + ib->ptr[ib->length_dw++] =PACKET3 (PACKET3_SET_SH_REG ,2 ); + ib->ptr[ib->length_dw++] =SOC15_REG_OFFSET (GC ,0 , mmCOMPUTE_PGM_LO) -PACKET3_SET_SH_REG_START ; - ib.ptr[ib.length_dw++] =lower_32_bits (gpu_addr); - ib.ptr[ib.length_dw++] =upper_32_bits (gpu_addr); + ib->ptr[ib->length_dw++] =lower_32_bits (gpu_addr); + ib->ptr[ib->length_dw++] =upper_32_bits (gpu_addr);/* write dispatch packet */ - ib.ptr[ib.length_dw++] =PACKET3 (PACKET3_DISPATCH_DIRECT ,3 ); - ib.ptr[ib.length_dw++] = compute_dim_x /2 * sgpr_work_group_size;/* x */ - ib.ptr[ib.length_dw++] =1 ;/* y */ - ib.ptr[ib.length_dw++] =1 ;/* z */ - ib.ptr[ib.length_dw++] = + ib->ptr[ib->length_dw++] =PACKET3 (PACKET3_DISPATCH_DIRECT ,3 ); + ib->ptr[ib->length_dw++] = compute_dim_x /2 * sgpr_work_group_size;/* x */ + ib->ptr[ib->length_dw++] =1 ;/* y */ + ib->ptr[ib->length_dw++] =1 ;/* z */ + ib->ptr[ib->length_dw++] =REG_SET_FIELD (0 ,COMPUTE_DISPATCH_INITIATOR ,COMPUTE_SHADER_EN ,1 );/* write CS partial flush packet */ - ib.ptr[ib.length_dw++] =PACKET3 (PACKET3_EVENT_WRITE ,0 ); - ib.ptr[ib.length_dw++] =EVENT_TYPE (7 ) |EVENT_INDEX (4 ); + ib->ptr[ib->length_dw++] =PACKET3 (PACKET3_EVENT_WRITE ,0 ); + ib->ptr[ib->length_dw++] =EVENT_TYPE (7 ) |EVENT_INDEX (4 );/* shedule the ib on the ring */ - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); + r =amdgpu_job_submit_direct (job, ring, &f);if (r) {drm_err (adev_to_drm (adev),"ib schedule failed (%d).\n" , r); +amdgpu_job_free (job); goto fail; }@@ -4787,7 +4792,6 @@ static int gfx_v9_0_do_edc_gpr_workarounds(struct amdgpu_device *adev) } fail: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f);return r;drivers/gpu/drm/amd/amdgpu/gfx_v9_4_2.c +8
-18@@ -345,12 +345,13 @@ const struct soc15_reg_entry sgpr64_init_regs_aldebaran[] = {static int gfx_v9_4_2_run_shader (struct amdgpu_device *adev,struct amdgpu_ring *ring, -struct amdgpu_ib *ib,const u32 *shader_ptr,u32 shader_size,const struct soc15_reg_entry *init_regs,u32 regs_size,u32 compute_dim_x,u64 wb_gpu_addr,u32 pattern,struct dma_fence **fence_ptr) { +struct amdgpu_job *job; +struct amdgpu_ib *ib;int r, i;uint32_t total_size, shader_offset;u64 gpu_addr;@@ -360,10 +361,9 @@ static int gfx_v9_4_2_run_shader(struct amdgpu_device *adev, shader_offset = total_size; total_size +=ALIGN (shader_size,256 ); -/* allocate an indirect buffer to put the commands in */ -memset (ib,0 ,sizeof (*ib)); - r =amdgpu_ib_get (adev,NULL , total_size, -AMDGPU_IB_POOL_DIRECT , ib); + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL , total_size, +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_RUN_SHADER );if (r) {dev_err (adev->dev,"failed to get ib (%d).\n" , r);return r;@@ -408,11 +408,11 @@ static int gfx_v9_4_2_run_shader(struct amdgpu_device *adev, ib->ptr[ib->length_dw++] =REG_SET_FIELD (0 ,COMPUTE_DISPATCH_INITIATOR ,COMPUTE_SHADER_EN ,1 ); -/* shedule the ib on the ring */ - r =amdgpu_ib_schedule (ring,1 , ib,NULL , fence_ptr); +/* schedule the ib on the ring */ + r =amdgpu_job_submit_direct (job, ring, fence_ptr);if (r) {dev_err (adev->dev,"ib submit failed (%d).\n" , r); -amdgpu_ib_free (ib,NULL ); +amdgpu_job_free (job); }return r; }@@ -493,7 +493,6 @@ static int gfx_v9_4_2_do_sgprs_init(struct amdgpu_device *adev)int wb_size = adev->gfx.config.max_shader_engines *CU_ID_MAX *SIMD_ID_MAX *WAVE_ID_MAX ;struct amdgpu_ib wb_ib; -struct amdgpu_ib disp_ibs[3 ];struct dma_fence *fences[3 ];u32 pattern[3 ] = {0x1 ,0x5 ,0xa };@@ -514,7 +513,6 @@ static int gfx_v9_4_2_do_sgprs_init(struct amdgpu_device *adev) r = gfx_v9_4_2_run_shader(adev, &adev->gfx.compute_ring[0], - &disp_ibs[0], sgpr112_init_compute_shader_aldebaran, sizeof(sgpr112_init_compute_shader_aldebaran), sgpr112_init_regs_aldebaran,@@ -539,7 +537,6 @@ static int gfx_v9_4_2_do_sgprs_init(struct amdgpu_device *adev) r = gfx_v9_4_2_run_shader(adev, &adev->gfx.compute_ring[1], - &disp_ibs[1], sgpr96_init_compute_shader_aldebaran, sizeof(sgpr96_init_compute_shader_aldebaran), sgpr96_init_regs_aldebaran,@@ -579,7 +576,6 @@ static int gfx_v9_4_2_do_sgprs_init(struct amdgpu_device *adev)memset (wb_ib.ptr,0 , (1 + wb_size) *sizeof (uint32_t )); r = gfx_v9_4_2_run_shader(adev, &adev->gfx.compute_ring[0], - &disp_ibs[2], sgpr64_init_compute_shader_aldebaran, sizeof(sgpr64_init_compute_shader_aldebaran), sgpr64_init_regs_aldebaran,@@ -611,13 +607,10 @@ static int gfx_v9_4_2_do_sgprs_init(struct amdgpu_device *adev) } disp2_failed: -amdgpu_ib_free (&disp_ibs[2 ],NULL );dma_fence_put (fences[2 ]); disp1_failed: -amdgpu_ib_free (&disp_ibs[1 ],NULL );dma_fence_put (fences[1 ]); disp0_failed: -amdgpu_ib_free (&disp_ibs[0 ],NULL );dma_fence_put (fences[0 ]); pro_end:amdgpu_ib_free (&wb_ib,NULL );@@ -637,7 +630,6 @@ static int gfx_v9_4_2_do_vgprs_init(struct amdgpu_device *adev)int wb_size = adev->gfx.config.max_shader_engines *CU_ID_MAX *SIMD_ID_MAX *WAVE_ID_MAX ;struct amdgpu_ib wb_ib; -struct amdgpu_ib disp_ib;struct dma_fence *fence;u32 pattern =0xa ;@@ -657,7 +649,6 @@ static int gfx_v9_4_2_do_vgprs_init(struct amdgpu_device *adev) r = gfx_v9_4_2_run_shader(adev, &adev->gfx.compute_ring[0], - &disp_ib, vgpr_init_compute_shader_aldebaran, sizeof(vgpr_init_compute_shader_aldebaran), vgpr_init_regs_aldebaran,@@ -687,7 +678,6 @@ static int gfx_v9_4_2_do_vgprs_init(struct amdgpu_device *adev) } disp_failed: -amdgpu_ib_free (&disp_ib,NULL );dma_fence_put (fence); pro_end:amdgpu_ib_free (&wb_ib,NULL );drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c +16
-13@@ -451,9 +451,9 @@ static int gfx_v9_4_3_ring_test_ring(struct amdgpu_ring *ring)static int gfx_v9_4_3_ring_test_ib (struct amdgpu_ring *ring,long timeout) {struct amdgpu_device *adev = ring->adev; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ; -unsigned index;uint64_t gpu_addr;uint32_t tmp;@@ -465,22 +465,26 @@ static int gfx_v9_4_3_ring_test_ib(struct amdgpu_ring *ring, long timeout) gpu_addr = adev->wb.gpu_addr + (index *4 ); adev->wb.wb[index] =cpu_to_le32 (0xCAFEDEAD ); -memset (&ib,0 ,sizeof (ib)); - r =amdgpu_ib_get (adev,NULL ,20 ,AMDGPU_IB_POOL_DIRECT , &ib); + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,20 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_GFX_RING_TEST );if (r) goto err1; - ib.ptr[0 ] =PACKET3 (PACKET3_WRITE_DATA ,3 ); - ib.ptr[1 ] =WRITE_DATA_DST_SEL (5 ) |WR_CONFIRM ; - ib.ptr[2 ] =lower_32_bits (gpu_addr); - ib.ptr[3 ] =upper_32_bits (gpu_addr); - ib.ptr[4 ] =0xDEADBEEF ; - ib.length_dw =5 ; + ib = &job->ibs[0 ]; + ib->ptr[0 ] =PACKET3 (PACKET3_WRITE_DATA ,3 ); + ib->ptr[1 ] =WRITE_DATA_DST_SEL (5 ) |WR_CONFIRM ; + ib->ptr[2 ] =lower_32_bits (gpu_addr); + ib->ptr[3 ] =upper_32_bits (gpu_addr); + ib->ptr[4 ] =0xDEADBEEF ; + ib->length_dw =5 ; - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (r) + r =amdgpu_job_submit_direct (job, ring, &f); +if (r) { +amdgpu_job_free (job); goto err2; + } r =dma_fence_wait_timeout (f, false, timeout);if (r ==0 ) {@@ -497,7 +501,6 @@ static int gfx_v9_4_3_ring_test_ib(struct amdgpu_ring *ring, long timeout) r = -EINVAL ; err2: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f); err1:amdgpu_device_wb_free (adev, index);drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c +21
-17@@ -584,7 +584,8 @@ static int sdma_v2_4_ring_test_ring(struct amdgpu_ring *ring)static int sdma_v2_4_ring_test_ib (struct amdgpu_ring *ring,long timeout) {struct amdgpu_device *adev = ring->adev; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ;unsigned index;u32 tmp =0 ;@@ -598,26 +599,30 @@ static int sdma_v2_4_ring_test_ib(struct amdgpu_ring *ring, long timeout) gpu_addr = adev->wb.gpu_addr + (index *4 ); tmp =0xCAFEDEAD ; adev->wb.wb[index] =cpu_to_le32 (tmp); -memset (&ib,0 ,sizeof (ib)); - r =amdgpu_ib_get (adev,NULL ,256 , -AMDGPU_IB_POOL_DIRECT , &ib); + + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,256 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_SDMA_RING_TEST );if (r) goto err0; - ib.ptr[0 ] =SDMA_PKT_HEADER_OP (SDMA_OP_WRITE ) | + ib = &job->ibs[0 ]; + ib->ptr[0 ] =SDMA_PKT_HEADER_OP (SDMA_OP_WRITE ) |SDMA_PKT_HEADER_SUB_OP (SDMA_SUBOP_WRITE_LINEAR ); - ib.ptr[1 ] =lower_32_bits (gpu_addr); - ib.ptr[2 ] =upper_32_bits (gpu_addr); - ib.ptr[3 ] =SDMA_PKT_WRITE_UNTILED_DW_3_COUNT (1 ); - ib.ptr[4 ] =0xDEADBEEF ; - ib.ptr[5 ] =SDMA_PKT_HEADER_OP (SDMA_OP_NOP ); - ib.ptr[6 ] =SDMA_PKT_HEADER_OP (SDMA_OP_NOP ); - ib.ptr[7 ] =SDMA_PKT_HEADER_OP (SDMA_OP_NOP ); - ib.length_dw =8 ; - - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (r) + ib->ptr[1 ] =lower_32_bits (gpu_addr); + ib->ptr[2 ] =upper_32_bits (gpu_addr); + ib->ptr[3 ] =SDMA_PKT_WRITE_UNTILED_DW_3_COUNT (1 ); + ib->ptr[4 ] =0xDEADBEEF ; + ib->ptr[5 ] =SDMA_PKT_HEADER_OP (SDMA_OP_NOP ); + ib->ptr[6 ] =SDMA_PKT_HEADER_OP (SDMA_OP_NOP ); + ib->ptr[7 ] =SDMA_PKT_HEADER_OP (SDMA_OP_NOP ); + ib->length_dw =8 ; + + r =amdgpu_job_submit_direct (job, ring, &f); +if (r) { +amdgpu_job_free (job); goto err1; + } r =dma_fence_wait_timeout (f, false, timeout);if (r ==0 ) {@@ -633,7 +638,6 @@ static int sdma_v2_4_ring_test_ib(struct amdgpu_ring *ring, long timeout) r = -EINVAL ; err1: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f); err0:amdgpu_device_wb_free (adev, index);drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c +21
-17@@ -858,7 +858,8 @@ static int sdma_v3_0_ring_test_ring(struct amdgpu_ring *ring)static int sdma_v3_0_ring_test_ib (struct amdgpu_ring *ring,long timeout) {struct amdgpu_device *adev = ring->adev; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ;unsigned index;u32 tmp =0 ;@@ -872,26 +873,30 @@ static int sdma_v3_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) gpu_addr = adev->wb.gpu_addr + (index *4 ); tmp =0xCAFEDEAD ; adev->wb.wb[index] =cpu_to_le32 (tmp); -memset (&ib,0 ,sizeof (ib)); - r =amdgpu_ib_get (adev,NULL ,256 , -AMDGPU_IB_POOL_DIRECT , &ib); + + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,256 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_SDMA_RING_TEST );if (r) goto err0; - ib.ptr[0 ] =SDMA_PKT_HEADER_OP (SDMA_OP_WRITE ) | + ib = &job->ibs[0 ]; + ib->ptr[0 ] =SDMA_PKT_HEADER_OP (SDMA_OP_WRITE ) |SDMA_PKT_HEADER_SUB_OP (SDMA_SUBOP_WRITE_LINEAR ); - ib.ptr[1 ] =lower_32_bits (gpu_addr); - ib.ptr[2 ] =upper_32_bits (gpu_addr); - ib.ptr[3 ] =SDMA_PKT_WRITE_UNTILED_DW_3_COUNT (1 ); - ib.ptr[4 ] =0xDEADBEEF ; - ib.ptr[5 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.ptr[6 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.ptr[7 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.length_dw =8 ; - - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (r) + ib->ptr[1 ] =lower_32_bits (gpu_addr); + ib->ptr[2 ] =upper_32_bits (gpu_addr); + ib->ptr[3 ] =SDMA_PKT_WRITE_UNTILED_DW_3_COUNT (1 ); + ib->ptr[4 ] =0xDEADBEEF ; + ib->ptr[5 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->ptr[6 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->ptr[7 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->length_dw =8 ; + + r =amdgpu_job_submit_direct (job, ring, &f); +if (r) { +amdgpu_job_free (job); goto err1; + } r =dma_fence_wait_timeout (f, false, timeout);if (r ==0 ) {@@ -906,7 +911,6 @@ static int sdma_v3_0_ring_test_ib(struct amdgpu_ring *ring, long timeout)else r = -EINVAL ; err1: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f); err0:amdgpu_device_wb_free (adev, index);drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c +21
-17@@ -1516,7 +1516,8 @@ static int sdma_v4_0_ring_test_ring(struct amdgpu_ring *ring)static int sdma_v4_0_ring_test_ib (struct amdgpu_ring *ring,long timeout) {struct amdgpu_device *adev = ring->adev; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ;unsigned index;long r;@@ -1530,26 +1531,30 @@ static int sdma_v4_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) gpu_addr = adev->wb.gpu_addr + (index *4 ); tmp =0xCAFEDEAD ; adev->wb.wb[index] =cpu_to_le32 (tmp); -memset (&ib,0 ,sizeof (ib)); - r =amdgpu_ib_get (adev,NULL ,256 , -AMDGPU_IB_POOL_DIRECT , &ib); + + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,256 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_SDMA_RING_TEST );if (r) goto err0; - ib.ptr[0 ] =SDMA_PKT_HEADER_OP (SDMA_OP_WRITE ) | + ib = &job->ibs[0 ]; + ib->ptr[0 ] =SDMA_PKT_HEADER_OP (SDMA_OP_WRITE ) |SDMA_PKT_HEADER_SUB_OP (SDMA_SUBOP_WRITE_LINEAR ); - ib.ptr[1 ] =lower_32_bits (gpu_addr); - ib.ptr[2 ] =upper_32_bits (gpu_addr); - ib.ptr[3 ] =SDMA_PKT_WRITE_UNTILED_DW_3_COUNT (0 ); - ib.ptr[4 ] =0xDEADBEEF ; - ib.ptr[5 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.ptr[6 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.ptr[7 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.length_dw =8 ; - - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (r) + ib->ptr[1 ] =lower_32_bits (gpu_addr); + ib->ptr[2 ] =upper_32_bits (gpu_addr); + ib->ptr[3 ] =SDMA_PKT_WRITE_UNTILED_DW_3_COUNT (0 ); + ib->ptr[4 ] =0xDEADBEEF ; + ib->ptr[5 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->ptr[6 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->ptr[7 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->length_dw =8 ; + + r =amdgpu_job_submit_direct (job, ring, &f); +if (r) { +amdgpu_job_free (job); goto err1; + } r =dma_fence_wait_timeout (f, false, timeout);if (r ==0 ) {@@ -1565,7 +1570,6 @@ static int sdma_v4_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) r = -EINVAL ; err1: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f); err0:amdgpu_device_wb_free (adev, index);drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c +21
-17@@ -1112,7 +1112,8 @@ static int sdma_v4_4_2_ring_test_ring(struct amdgpu_ring *ring)static int sdma_v4_4_2_ring_test_ib (struct amdgpu_ring *ring,long timeout) {struct amdgpu_device *adev = ring->adev; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ;unsigned index;long r;@@ -1126,26 +1127,30 @@ static int sdma_v4_4_2_ring_test_ib(struct amdgpu_ring *ring, long timeout) gpu_addr = adev->wb.gpu_addr + (index *4 ); tmp =0xCAFEDEAD ; adev->wb.wb[index] =cpu_to_le32 (tmp); -memset (&ib,0 ,sizeof (ib)); - r =amdgpu_ib_get (adev,NULL ,256 , -AMDGPU_IB_POOL_DIRECT , &ib); + + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,256 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_SDMA_RING_TEST );if (r) goto err0; - ib.ptr[0 ] =SDMA_PKT_HEADER_OP (SDMA_OP_WRITE ) | + ib = &job->ibs[0 ]; + ib->ptr[0 ] =SDMA_PKT_HEADER_OP (SDMA_OP_WRITE ) |SDMA_PKT_HEADER_SUB_OP (SDMA_SUBOP_WRITE_LINEAR ); - ib.ptr[1 ] =lower_32_bits (gpu_addr); - ib.ptr[2 ] =upper_32_bits (gpu_addr); - ib.ptr[3 ] =SDMA_PKT_WRITE_UNTILED_DW_3_COUNT (0 ); - ib.ptr[4 ] =0xDEADBEEF ; - ib.ptr[5 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.ptr[6 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.ptr[7 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.length_dw =8 ; - - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (r) + ib->ptr[1 ] =lower_32_bits (gpu_addr); + ib->ptr[2 ] =upper_32_bits (gpu_addr); + ib->ptr[3 ] =SDMA_PKT_WRITE_UNTILED_DW_3_COUNT (0 ); + ib->ptr[4 ] =0xDEADBEEF ; + ib->ptr[5 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->ptr[6 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->ptr[7 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->length_dw =8 ; + + r =amdgpu_job_submit_direct (job, ring, &f); +if (r) { +amdgpu_job_free (job); goto err1; + } r =dma_fence_wait_timeout (f, false, timeout);if (r ==0 ) {@@ -1161,7 +1166,6 @@ static int sdma_v4_4_2_ring_test_ib(struct amdgpu_ring *ring, long timeout) r = -EINVAL ; err1: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f); err0:amdgpu_device_wb_free (adev, index);drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c +20
-17@@ -1074,7 +1074,8 @@ static int sdma_v5_0_ring_test_ring(struct amdgpu_ring *ring)static int sdma_v5_0_ring_test_ib (struct amdgpu_ring *ring,long timeout) {struct amdgpu_device *adev = ring->adev; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ;unsigned index;long r;@@ -1082,7 +1083,6 @@ static int sdma_v5_0_ring_test_ib(struct amdgpu_ring *ring, long timeout)u64 gpu_addr; tmp =0xCAFEDEAD ; -memset (&ib,0 ,sizeof (ib)); r =amdgpu_device_wb_get (adev, &index);if (r) {@@ -1093,27 +1093,31 @@ static int sdma_v5_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) gpu_addr = adev->wb.gpu_addr + (index *4 ); adev->wb.wb[index] =cpu_to_le32 (tmp); - r =amdgpu_ib_get (adev,NULL ,256 , -AMDGPU_IB_POOL_DIRECT , &ib); + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,256 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_SDMA_RING_TEST );if (r) {drm_err (adev_to_drm (adev),"failed to get ib (%ld).\n" , r); goto err0; } - ib.ptr[0 ] =SDMA_PKT_HEADER_OP (SDMA_OP_WRITE ) | + ib = &job->ibs[0 ]; + ib->ptr[0 ] =SDMA_PKT_HEADER_OP (SDMA_OP_WRITE ) |SDMA_PKT_HEADER_SUB_OP (SDMA_SUBOP_WRITE_LINEAR ); - ib.ptr[1 ] =lower_32_bits (gpu_addr); - ib.ptr[2 ] =upper_32_bits (gpu_addr); - ib.ptr[3 ] =SDMA_PKT_WRITE_UNTILED_DW_3_COUNT (0 ); - ib.ptr[4 ] =0xDEADBEEF ; - ib.ptr[5 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.ptr[6 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.ptr[7 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.length_dw =8 ; - - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (r) + ib->ptr[1 ] =lower_32_bits (gpu_addr); + ib->ptr[2 ] =upper_32_bits (gpu_addr); + ib->ptr[3 ] =SDMA_PKT_WRITE_UNTILED_DW_3_COUNT (0 ); + ib->ptr[4 ] =0xDEADBEEF ; + ib->ptr[5 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->ptr[6 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->ptr[7 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->length_dw =8 ; + + r =amdgpu_job_submit_direct (job, ring, &f); +if (r) { +amdgpu_job_free (job); goto err1; + } r =dma_fence_wait_timeout (f, false, timeout);if (r ==0 ) {@@ -1133,7 +1137,6 @@ static int sdma_v5_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) r = -EINVAL ; err1: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f); err0:amdgpu_device_wb_free (adev, index);drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c +20
-16@@ -974,7 +974,8 @@ static int sdma_v5_2_ring_test_ring(struct amdgpu_ring *ring)static int sdma_v5_2_ring_test_ib (struct amdgpu_ring *ring,long timeout) {struct amdgpu_device *adev = ring->adev; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ;unsigned index;long r;@@ -982,7 +983,6 @@ static int sdma_v5_2_ring_test_ib(struct amdgpu_ring *ring, long timeout)u64 gpu_addr; tmp =0xCAFEDEAD ; -memset (&ib,0 ,sizeof (ib)); r =amdgpu_device_wb_get (adev, &index);if (r) {@@ -993,26 +993,31 @@ static int sdma_v5_2_ring_test_ib(struct amdgpu_ring *ring, long timeout) gpu_addr = adev->wb.gpu_addr + (index *4 ); adev->wb.wb[index] =cpu_to_le32 (tmp); - r =amdgpu_ib_get (adev,NULL ,256 ,AMDGPU_IB_POOL_DIRECT , &ib); + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,256 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_SDMA_RING_TEST );if (r) {drm_err (adev_to_drm (adev),"failed to get ib (%ld).\n" , r); goto err0; } - ib.ptr[0 ] =SDMA_PKT_HEADER_OP (SDMA_OP_WRITE ) | + ib = &job->ibs[0 ]; + ib->ptr[0 ] =SDMA_PKT_HEADER_OP (SDMA_OP_WRITE ) |SDMA_PKT_HEADER_SUB_OP (SDMA_SUBOP_WRITE_LINEAR ); - ib.ptr[1 ] =lower_32_bits (gpu_addr); - ib.ptr[2 ] =upper_32_bits (gpu_addr); - ib.ptr[3 ] =SDMA_PKT_WRITE_UNTILED_DW_3_COUNT (0 ); - ib.ptr[4 ] =0xDEADBEEF ; - ib.ptr[5 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.ptr[6 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.ptr[7 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.length_dw =8 ; - - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (r) + ib->ptr[1 ] =lower_32_bits (gpu_addr); + ib->ptr[2 ] =upper_32_bits (gpu_addr); + ib->ptr[3 ] =SDMA_PKT_WRITE_UNTILED_DW_3_COUNT (0 ); + ib->ptr[4 ] =0xDEADBEEF ; + ib->ptr[5 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->ptr[6 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->ptr[7 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->length_dw =8 ; + + r =amdgpu_job_submit_direct (job, ring, &f); +if (r) { +amdgpu_job_free (job); goto err1; + } r =dma_fence_wait_timeout (f, false, timeout);if (r ==0 ) {@@ -1032,7 +1037,6 @@ static int sdma_v5_2_ring_test_ib(struct amdgpu_ring *ring, long timeout) r = -EINVAL ; err1: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f); err0:amdgpu_device_wb_free (adev, index);drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c +20
-16@@ -981,7 +981,8 @@ static int sdma_v6_0_ring_test_ring(struct amdgpu_ring *ring)static int sdma_v6_0_ring_test_ib (struct amdgpu_ring *ring,long timeout) {struct amdgpu_device *adev = ring->adev; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ;unsigned index;long r;@@ -989,7 +990,6 @@ static int sdma_v6_0_ring_test_ib(struct amdgpu_ring *ring, long timeout)u64 gpu_addr; tmp =0xCAFEDEAD ; -memset (&ib,0 ,sizeof (ib)); r =amdgpu_device_wb_get (adev, &index);if (r) {@@ -1000,26 +1000,31 @@ static int sdma_v6_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) gpu_addr = adev->wb.gpu_addr + (index *4 ); adev->wb.wb[index] =cpu_to_le32 (tmp); - r =amdgpu_ib_get (adev,NULL ,256 ,AMDGPU_IB_POOL_DIRECT , &ib); + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,256 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_SDMA_RING_TEST );if (r) {drm_err (adev_to_drm (adev),"failed to get ib (%ld).\n" , r); goto err0; } - ib.ptr[0 ] =SDMA_PKT_COPY_LINEAR_HEADER_OP (SDMA_OP_WRITE ) | + ib = &job->ibs[0 ]; + ib->ptr[0 ] =SDMA_PKT_COPY_LINEAR_HEADER_OP (SDMA_OP_WRITE ) |SDMA_PKT_COPY_LINEAR_HEADER_SUB_OP (SDMA_SUBOP_WRITE_LINEAR ); - ib.ptr[1 ] =lower_32_bits (gpu_addr); - ib.ptr[2 ] =upper_32_bits (gpu_addr); - ib.ptr[3 ] =SDMA_PKT_WRITE_UNTILED_DW_3_COUNT (0 ); - ib.ptr[4 ] =0xDEADBEEF ; - ib.ptr[5 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.ptr[6 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.ptr[7 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.length_dw =8 ; - - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (r) + ib->ptr[1 ] =lower_32_bits (gpu_addr); + ib->ptr[2 ] =upper_32_bits (gpu_addr); + ib->ptr[3 ] =SDMA_PKT_WRITE_UNTILED_DW_3_COUNT (0 ); + ib->ptr[4 ] =0xDEADBEEF ; + ib->ptr[5 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->ptr[6 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->ptr[7 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->length_dw =8 ; + + r =amdgpu_job_submit_direct (job, ring, &f); +if (r) { +amdgpu_job_free (job); goto err1; + } r =dma_fence_wait_timeout (f, false, timeout);if (r ==0 ) {@@ -1039,7 +1044,6 @@ static int sdma_v6_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) r = -EINVAL ; err1: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f); err0:amdgpu_device_wb_free (adev, index);drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c +20
-16@@ -997,7 +997,8 @@ static int sdma_v7_0_ring_test_ring(struct amdgpu_ring *ring)static int sdma_v7_0_ring_test_ib (struct amdgpu_ring *ring,long timeout) {struct amdgpu_device *adev = ring->adev; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ;unsigned index;long r;@@ -1005,7 +1006,6 @@ static int sdma_v7_0_ring_test_ib(struct amdgpu_ring *ring, long timeout)u64 gpu_addr; tmp =0xCAFEDEAD ; -memset (&ib,0 ,sizeof (ib)); r =amdgpu_device_wb_get (adev, &index);if (r) {@@ -1016,26 +1016,31 @@ static int sdma_v7_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) gpu_addr = adev->wb.gpu_addr + (index *4 ); adev->wb.wb[index] =cpu_to_le32 (tmp); - r =amdgpu_ib_get (adev,NULL ,256 ,AMDGPU_IB_POOL_DIRECT , &ib); + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,256 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_SDMA_RING_TEST );if (r) {drm_err (adev_to_drm (adev),"failed to get ib (%ld).\n" , r); goto err0; } - ib.ptr[0 ] =SDMA_PKT_COPY_LINEAR_HEADER_OP (SDMA_OP_WRITE ) | + ib = &job->ibs[0 ]; + ib->ptr[0 ] =SDMA_PKT_COPY_LINEAR_HEADER_OP (SDMA_OP_WRITE ) |SDMA_PKT_COPY_LINEAR_HEADER_SUB_OP (SDMA_SUBOP_WRITE_LINEAR ); - ib.ptr[1 ] =lower_32_bits (gpu_addr); - ib.ptr[2 ] =upper_32_bits (gpu_addr); - ib.ptr[3 ] =SDMA_PKT_WRITE_UNTILED_DW_3_COUNT (0 ); - ib.ptr[4 ] =0xDEADBEEF ; - ib.ptr[5 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.ptr[6 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.ptr[7 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.length_dw =8 ; - - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (r) + ib->ptr[1 ] =lower_32_bits (gpu_addr); + ib->ptr[2 ] =upper_32_bits (gpu_addr); + ib->ptr[3 ] =SDMA_PKT_WRITE_UNTILED_DW_3_COUNT (0 ); + ib->ptr[4 ] =0xDEADBEEF ; + ib->ptr[5 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->ptr[6 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->ptr[7 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->length_dw =8 ; + + r =amdgpu_job_submit_direct (job, ring, &f); +if (r) { +amdgpu_job_free (job); goto err1; + } r =dma_fence_wait_timeout (f, false, timeout);if (r ==0 ) {@@ -1055,7 +1060,6 @@ static int sdma_v7_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) r = -EINVAL ; err1: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f); err0:amdgpu_device_wb_free (adev, index);drivers/gpu/drm/amd/amdgpu/sdma_v7_1.c +20
-16@@ -987,7 +987,8 @@ static int sdma_v7_1_ring_test_ring(struct amdgpu_ring *ring)static int sdma_v7_1_ring_test_ib (struct amdgpu_ring *ring,long timeout) {struct amdgpu_device *adev = ring->adev; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ;unsigned index;long r;@@ -995,7 +996,6 @@ static int sdma_v7_1_ring_test_ib(struct amdgpu_ring *ring, long timeout)u64 gpu_addr; tmp =0xCAFEDEAD ; -memset (&ib,0 ,sizeof (ib)); r =amdgpu_device_wb_get (adev, &index);if (r) {@@ -1006,26 +1006,31 @@ static int sdma_v7_1_ring_test_ib(struct amdgpu_ring *ring, long timeout) gpu_addr = adev->wb.gpu_addr + (index *4 ); adev->wb.wb[index] =cpu_to_le32 (tmp); - r =amdgpu_ib_get (adev,NULL ,256 ,AMDGPU_IB_POOL_DIRECT , &ib); + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,256 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_SDMA_RING_TEST );if (r) {DRM_ERROR ("amdgpu: failed to get ib (%ld).\n" , r); goto err0; } - ib.ptr[0 ] =SDMA_PKT_COPY_LINEAR_HEADER_OP (SDMA_OP_WRITE ) | + ib = &job->ibs[0 ]; + ib->ptr[0 ] =SDMA_PKT_COPY_LINEAR_HEADER_OP (SDMA_OP_WRITE ) |SDMA_PKT_COPY_LINEAR_HEADER_SUB_OP (SDMA_SUBOP_WRITE_LINEAR ); - ib.ptr[1 ] =lower_32_bits (gpu_addr); - ib.ptr[2 ] =upper_32_bits (gpu_addr); - ib.ptr[3 ] =SDMA_PKT_WRITE_UNTILED_DW_3_COUNT (0 ); - ib.ptr[4 ] =0xDEADBEEF ; - ib.ptr[5 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.ptr[6 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.ptr[7 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.length_dw =8 ; - - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (r) + ib->ptr[1 ] =lower_32_bits (gpu_addr); + ib->ptr[2 ] =upper_32_bits (gpu_addr); + ib->ptr[3 ] =SDMA_PKT_WRITE_UNTILED_DW_3_COUNT (0 ); + ib->ptr[4 ] =0xDEADBEEF ; + ib->ptr[5 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->ptr[6 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->ptr[7 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->length_dw =8 ; + + r =amdgpu_job_submit_direct (job, ring, &f); +if (r) { +amdgpu_job_free (job); goto err1; + } r =dma_fence_wait_timeout (f, false, timeout);if (r ==0 ) {@@ -1045,7 +1050,6 @@ static int sdma_v7_1_ring_test_ib(struct amdgpu_ring *ring, long timeout) r = -EINVAL ; err1: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f); err0:amdgpu_device_wb_free (adev, index);drivers/gpu/drm/amd/amdgpu/si_dma.c +17
-12@@ -259,7 +259,8 @@ static int si_dma_ring_test_ring(struct amdgpu_ring *ring)static int si_dma_ring_test_ib (struct amdgpu_ring *ring,long timeout) {struct amdgpu_device *adev = ring->adev; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ;unsigned index;u32 tmp =0 ;@@ -273,20 +274,25 @@ static int si_dma_ring_test_ib(struct amdgpu_ring *ring, long timeout) gpu_addr = adev->wb.gpu_addr + (index *4 ); tmp =0xCAFEDEAD ; adev->wb.wb[index] =cpu_to_le32 (tmp); -memset (&ib,0 ,sizeof (ib)); - r =amdgpu_ib_get (adev,NULL ,256 , -AMDGPU_IB_POOL_DIRECT , &ib); + + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,256 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_SDMA_RING_TEST );if (r) goto err0; - ib.ptr[0 ] =DMA_PACKET (DMA_PACKET_WRITE ,0 ,0 ,0 ,1 ); - ib.ptr[1 ] =lower_32_bits (gpu_addr); - ib.ptr[2 ] =upper_32_bits (gpu_addr) &0xff ; - ib.ptr[3 ] =0xDEADBEEF ; - ib.length_dw =4 ; - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (r) + ib = &job->ibs[0 ]; + ib->ptr[0 ] =DMA_PACKET (DMA_PACKET_WRITE ,0 ,0 ,0 ,1 ); + ib->ptr[1 ] =lower_32_bits (gpu_addr); + ib->ptr[2 ] =upper_32_bits (gpu_addr) &0xff ; + ib->ptr[3 ] =0xDEADBEEF ; + ib->length_dw =4 ; + + r =amdgpu_job_submit_direct (job, ring, &f); +if (r) { +amdgpu_job_free (job); goto err1; + } r =dma_fence_wait_timeout (f, false, timeout);if (r ==0 ) {@@ -302,7 +308,6 @@ static int si_dma_ring_test_ib(struct amdgpu_ring *ring, long timeout) r = -EINVAL ; err1: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f); err0:amdgpu_device_wb_free (adev, index);
Re: [PATCH 03/12] drm/amdgpu: switch all IPs to using job for IBs
In reply to Alex DeucherQuoted 101 lines · Alex Deucher
Quoted 99 lines · Pierre-Eric Pelloux-Prayer
Quoted 73 lines · Alex Deucher
Switch to using a job structure for IBs.
Acked-by Christian König <[email protected]>Signed-off-by Alex Deucher <[email protected]>--- drivers/gpu/drm/amd/amdgpu/amdgpu_vpe.c | 37 +++--- drivers/gpu/drm/amd/amdgpu/cik_sdma.c | 31 ++--- drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c | 29 ++--- drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c | 29 ++--- drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c | 29 ++--- drivers/gpu/drm/amd/amdgpu/gfx_v12_1.c | 29 ++--- drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c | 24 ++-- drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c | 25 ++-- drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c | 139 ++++++++++++----------- drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c | 138 +++++++++++----------- drivers/gpu/drm/amd/amdgpu/gfx_v9_4_2.c | 26 ++--- drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c | 29 ++--- drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c | 38 ++++--- drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c | 38 ++++--- drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c | 38 ++++--- drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c | 38 ++++--- drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c | 37 +++--- drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c | 36 +++--- drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c | 36 +++--- drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c | 36 +++--- drivers/gpu/drm/amd/amdgpu/sdma_v7_1.c | 36 +++--- drivers/gpu/drm/amd/amdgpu/si_dma.c | 29 +++-- 22 files changed, 500 insertions(+), 427 deletions(-)drivers/gpu/drm/amd/amdgpu/amdgpu_vpe.c +12
-15@@ -817,7 +817,8 @@ static int vpe_ring_test_ib(struct amdgpu_ring *ring, long timeout) {struct amdgpu_device *adev = ring->adev;const uint32_t test_pattern =0xdeadbeef ; -struct amdgpu_ib ib = {}; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ;uint32_t index;uint64_t wb_addr;@@ -832,23 +833,28 @@ static int vpe_ring_test_ib(struct amdgpu_ring *ring, long timeout) adev->wb.wb[index] =0 ; wb_addr = adev->wb.gpu_addr + (index *4 ); - ret =amdgpu_ib_get (adev,NULL ,256 ,AMDGPU_IB_POOL_DIRECT , &ib); + ret =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,256 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_VPE_RING_TEST );if (ret) goto err0; - - ib.ptr[0 ] =VPE_CMD_HEADER (VPE_CMD_OPCODE_FENCE ,0 ); - ib.ptr[1 ] =lower_32_bits (wb_addr); - ib.ptr[2 ] =upper_32_bits (wb_addr); - ib.ptr[3 ] = test_pattern; - ib.ptr[4 ] =VPE_CMD_HEADER (VPE_CMD_OPCODE_NOP ,0 ); - ib.ptr[5 ] =VPE_CMD_HEADER (VPE_CMD_OPCODE_NOP ,0 ); - ib.ptr[6 ] =VPE_CMD_HEADER (VPE_CMD_OPCODE_NOP ,0 ); - ib.ptr[7 ] =VPE_CMD_HEADER (VPE_CMD_OPCODE_NOP ,0 ); - ib.length_dw =8 ; - - ret =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (ret) + ib = &job->ibs[0 ]; + + ib->ptr[0 ] =VPE_CMD_HEADER (VPE_CMD_OPCODE_FENCE ,0 ); + ib->ptr[1 ] =lower_32_bits (wb_addr); + ib->ptr[2 ] =upper_32_bits (wb_addr); + ib->ptr[3 ] = test_pattern; + ib->ptr[4 ] =VPE_CMD_HEADER (VPE_CMD_OPCODE_NOP ,0 );drivers/gpu/drm/amd/amdgpu/amdgpu_vpe.c static int vpe_ring_test_ib(struct amdgpu_ring *ring, long timeout) · line 857
Quoted 10 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_vpe.c +9
-0+ ib->ptr[5 ] =VPE_CMD_HEADER (VPE_CMD_OPCODE_NOP ,0 ); + ib->ptr[6 ] =VPE_CMD_HEADER (VPE_CMD_OPCODE_NOP ,0 ); + ib->ptr[7 ] =VPE_CMD_HEADER (VPE_CMD_OPCODE_NOP ,0 ); + ib->length_dw =8 ; + + ret =amdgpu_job_submit_direct (job, ring, &f); +if (ret) { +amdgpu_job_free (job); goto err1; + }This is a nice cleanup. What about going one step further and provide a helper like:
u32 test_dws[] = { VPE_CMD_HEADER(VPE_CMD_OPCODE_FENCE, 0), lower_32_bits(wb_addr), ... }; ret = amdgpu_ring_run_dwords(ring, ARRAY_SIZE(test_dws), test_dws,timeout);
Quoted 3 lines
Quoted 1 line
Because that's what most
_ring_test_ibfunction do.I can look into that as a follow up series.
Apologies for parachuting in.
FWIW, when you land this I might re-surface my IB emission compaction work (for example https://lore.kernel.org/amd-gfx/[email protected]/). I don't think so far I was addressing the ring test functions but I can easily add those too.
Regards,
Tvrtko
Quoted 1,816 lines
Quoted 1,816 lines
Quoted 1,816 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_vpe.c +0
-1ret =dma_fence_wait_timeout (f, false, timeout);if (ret <=0 ) {@@ -859,7 +865,6 @@ static int vpe_ring_test_ib(struct amdgpu_ring *ring, long timeout) ret = (le32_to_cpu (adev->wb.wb[index]) == test_pattern) ?0 : -EINVAL ; err1: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f); err0:amdgpu_device_wb_free (adev, index);drivers/gpu/drm/amd/amdgpu/cik_sdma.c +18
-13@@ -652,7 +652,8 @@ static int cik_sdma_ring_test_ring(struct amdgpu_ring *ring)static int cik_sdma_ring_test_ib (struct amdgpu_ring *ring,long timeout) {struct amdgpu_device *adev = ring->adev; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ;unsigned index;u32 tmp =0 ;@@ -666,22 +667,27 @@ static int cik_sdma_ring_test_ib(struct amdgpu_ring *ring, long timeout) gpu_addr = adev->wb.gpu_addr + (index *4 ); tmp =0xCAFEDEAD ; adev->wb.wb[index] =cpu_to_le32 (tmp); -memset (&ib,0 ,sizeof (ib)); - r =amdgpu_ib_get (adev,NULL ,256 , -AMDGPU_IB_POOL_DIRECT , &ib); + + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,256 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_SDMA_RING_TEST );if (r) goto err0; + ib = &job->ibs[0 ]; - ib.ptr[0 ] =SDMA_PACKET (SDMA_OPCODE_WRITE , + ib->ptr[0 ] =SDMA_PACKET (SDMA_OPCODE_WRITE ,SDMA_WRITE_SUB_OPCODE_LINEAR ,0 ); - ib.ptr[1 ] =lower_32_bits (gpu_addr); - ib.ptr[2 ] =upper_32_bits (gpu_addr); - ib.ptr[3 ] =1 ; - ib.ptr[4 ] =0xDEADBEEF ; - ib.length_dw =5 ; - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (r) + ib->ptr[1 ] =lower_32_bits (gpu_addr); + ib->ptr[2 ] =upper_32_bits (gpu_addr); + ib->ptr[3 ] =1 ; + ib->ptr[4 ] =0xDEADBEEF ; + ib->length_dw =5 ; + + r =amdgpu_job_submit_direct (job, ring, &f); +if (r) { +amdgpu_job_free (job); goto err1; + } r =dma_fence_wait_timeout (f, false, timeout);if (r ==0 ) {@@ -697,7 +703,6 @@ static int cik_sdma_ring_test_ib(struct amdgpu_ring *ring, long timeout) r = -EINVAL ; err1: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f); err0:amdgpu_device_wb_free (adev, index);drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c +16
-13@@ -4071,15 +4071,14 @@ static int gfx_v10_0_ring_test_ring(struct amdgpu_ring *ring)static int gfx_v10_0_ring_test_ib (struct amdgpu_ring *ring,long timeout) {struct amdgpu_device *adev = ring->adev; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ;unsigned int index;uint64_t gpu_addr;uint32_t *cpu_ptr;long r; -memset (&ib,0 ,sizeof (ib)); - r =amdgpu_device_wb_get (adev, &index);if (r)return r;@@ -4088,22 +4087,27 @@ static int gfx_v10_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) adev->wb.wb[index] =cpu_to_le32 (0xCAFEDEAD ); cpu_ptr = &adev->wb.wb[index]; - r =amdgpu_ib_get (adev,NULL ,20 ,AMDGPU_IB_POOL_DIRECT , &ib); + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,20 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_GFX_RING_TEST );if (r) {drm_err (adev_to_drm (adev),"failed to get ib (%ld).\n" , r); goto err1; } + ib = &job->ibs[0 ]; - ib.ptr[0 ] =PACKET3 (PACKET3_WRITE_DATA ,3 ); - ib.ptr[1 ] =WRITE_DATA_DST_SEL (5 ) |WR_CONFIRM ; - ib.ptr[2 ] =lower_32_bits (gpu_addr); - ib.ptr[3 ] =upper_32_bits (gpu_addr); - ib.ptr[4 ] =0xDEADBEEF ; - ib.length_dw =5 ; + ib->ptr[0 ] =PACKET3 (PACKET3_WRITE_DATA ,3 ); + ib->ptr[1 ] =WRITE_DATA_DST_SEL (5 ) |WR_CONFIRM ; + ib->ptr[2 ] =lower_32_bits (gpu_addr); + ib->ptr[3 ] =upper_32_bits (gpu_addr); + ib->ptr[4 ] =0xDEADBEEF ; + ib->length_dw =5 ; - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (r) + r =amdgpu_job_submit_direct (job, ring, &f); +if (r) { +amdgpu_job_free (job); goto err2; + } r =dma_fence_wait_timeout (f, false, timeout);if (r ==0 ) {@@ -4118,7 +4122,6 @@ static int gfx_v10_0_ring_test_ib(struct amdgpu_ring *ring, long timeout)else r = -EINVAL ; err2: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f); err1:amdgpu_device_wb_free (adev, index);drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c +16
-13@@ -604,7 +604,8 @@ static int gfx_v11_0_ring_test_ring(struct amdgpu_ring *ring)static int gfx_v11_0_ring_test_ib (struct amdgpu_ring *ring,long timeout) {struct amdgpu_device *adev = ring->adev; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ;unsigned index;uint64_t gpu_addr;@@ -616,8 +617,6 @@ static int gfx_v11_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) ring->funcs->type == AMDGPU_RING_TYPE_KIQ)return 0 ; -memset (&ib,0 ,sizeof (ib)); - r =amdgpu_device_wb_get (adev, &index);if (r)return r;@@ -626,22 +625,27 @@ static int gfx_v11_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) adev->wb.wb[index] =cpu_to_le32 (0xCAFEDEAD ); cpu_ptr = &adev->wb.wb[index]; - r =amdgpu_ib_get (adev,NULL ,20 ,AMDGPU_IB_POOL_DIRECT , &ib); + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,20 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_GFX_RING_TEST );if (r) {drm_err (adev_to_drm (adev),"failed to get ib (%ld).\n" , r); goto err1; } + ib = &job->ibs[0 ]; - ib.ptr[0 ] =PACKET3 (PACKET3_WRITE_DATA ,3 ); - ib.ptr[1 ] =WRITE_DATA_DST_SEL (5 ) |WR_CONFIRM ; - ib.ptr[2 ] =lower_32_bits (gpu_addr); - ib.ptr[3 ] =upper_32_bits (gpu_addr); - ib.ptr[4 ] =0xDEADBEEF ; - ib.length_dw =5 ; + ib->ptr[0 ] =PACKET3 (PACKET3_WRITE_DATA ,3 ); + ib->ptr[1 ] =WRITE_DATA_DST_SEL (5 ) |WR_CONFIRM ; + ib->ptr[2 ] =lower_32_bits (gpu_addr); + ib->ptr[3 ] =upper_32_bits (gpu_addr); + ib->ptr[4 ] =0xDEADBEEF ; + ib->length_dw =5 ; - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (r) + r =amdgpu_job_submit_direct (job, ring, &f); +if (r) { +amdgpu_job_free (job); goto err2; + } r =dma_fence_wait_timeout (f, false, timeout);if (r ==0 ) {@@ -656,7 +660,6 @@ static int gfx_v11_0_ring_test_ib(struct amdgpu_ring *ring, long timeout)else r = -EINVAL ; err2: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f); err1:amdgpu_device_wb_free (adev, index);drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c +16
-13@@ -493,7 +493,8 @@ static int gfx_v12_0_ring_test_ring(struct amdgpu_ring *ring)static int gfx_v12_0_ring_test_ib (struct amdgpu_ring *ring,long timeout) {struct amdgpu_device *adev = ring->adev; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ;unsigned index;uint64_t gpu_addr;@@ -505,8 +506,6 @@ static int gfx_v12_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) ring->funcs->type == AMDGPU_RING_TYPE_KIQ)return 0 ; -memset (&ib,0 ,sizeof (ib)); - r =amdgpu_device_wb_get (adev, &index);if (r)return r;@@ -515,22 +514,27 @@ static int gfx_v12_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) adev->wb.wb[index] =cpu_to_le32 (0xCAFEDEAD ); cpu_ptr = &adev->wb.wb[index]; - r =amdgpu_ib_get (adev,NULL ,16 ,AMDGPU_IB_POOL_DIRECT , &ib); + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,16 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_GFX_RING_TEST );if (r) {drm_err (adev_to_drm (adev),"failed to get ib (%ld).\n" , r); goto err1; } + ib = &job->ibs[0 ]; - ib.ptr[0 ] =PACKET3 (PACKET3_WRITE_DATA ,3 ); - ib.ptr[1 ] =WRITE_DATA_DST_SEL (5 ) |WR_CONFIRM ; - ib.ptr[2 ] =lower_32_bits (gpu_addr); - ib.ptr[3 ] =upper_32_bits (gpu_addr); - ib.ptr[4 ] =0xDEADBEEF ; - ib.length_dw =5 ; + ib->ptr[0 ] =PACKET3 (PACKET3_WRITE_DATA ,3 ); + ib->ptr[1 ] =WRITE_DATA_DST_SEL (5 ) |WR_CONFIRM ; + ib->ptr[2 ] =lower_32_bits (gpu_addr); + ib->ptr[3 ] =upper_32_bits (gpu_addr); + ib->ptr[4 ] =0xDEADBEEF ; + ib->length_dw =5 ; - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (r) + r =amdgpu_job_submit_direct (job, ring, &f); +if (r) { +amdgpu_job_free (job); goto err2; + } r =dma_fence_wait_timeout (f, false, timeout);if (r ==0 ) {@@ -545,7 +549,6 @@ static int gfx_v12_0_ring_test_ib(struct amdgpu_ring *ring, long timeout)else r = -EINVAL ; err2: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f); err1:amdgpu_device_wb_free (adev, index);drivers/gpu/drm/amd/amdgpu/gfx_v12_1.c +16
-13@@ -307,7 +307,8 @@ static int gfx_v12_1_ring_test_ring(struct amdgpu_ring *ring)static int gfx_v12_1_ring_test_ib (struct amdgpu_ring *ring,long timeout) {struct amdgpu_device *adev = ring->adev; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ;unsigned index;uint64_t gpu_addr;@@ -319,8 +320,6 @@ static int gfx_v12_1_ring_test_ib(struct amdgpu_ring *ring, long timeout) ring->funcs->type == AMDGPU_RING_TYPE_KIQ)return 0 ; -memset (&ib,0 ,sizeof (ib)); - r =amdgpu_device_wb_get (adev, &index);if (r)return r;@@ -329,22 +328,27 @@ static int gfx_v12_1_ring_test_ib(struct amdgpu_ring *ring, long timeout) adev->wb.wb[index] =cpu_to_le32 (0xCAFEDEAD ); cpu_ptr = &adev->wb.wb[index]; - r =amdgpu_ib_get (adev,NULL ,16 ,AMDGPU_IB_POOL_DIRECT , &ib); + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,16 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_GFX_RING_TEST );if (r) {dev_err (adev->dev,"amdgpu: failed to get ib (%ld).\n" , r); goto err1; } + ib = &job->ibs[0 ]; - ib.ptr[0 ] =PACKET3 (PACKET3_WRITE_DATA ,3 ); - ib.ptr[1 ] =WRITE_DATA_DST_SEL (5 ) |WR_CONFIRM ; - ib.ptr[2 ] =lower_32_bits (gpu_addr); - ib.ptr[3 ] =upper_32_bits (gpu_addr); - ib.ptr[4 ] =0xDEADBEEF ; - ib.length_dw =5 ; + ib->ptr[0 ] =PACKET3 (PACKET3_WRITE_DATA ,3 ); + ib->ptr[1 ] =WRITE_DATA_DST_SEL (5 ) |WR_CONFIRM ; + ib->ptr[2 ] =lower_32_bits (gpu_addr); + ib->ptr[3 ] =upper_32_bits (gpu_addr); + ib->ptr[4 ] =0xDEADBEEF ; + ib->length_dw =5 ; - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (r) + r =amdgpu_job_submit_direct (job, ring, &f); +if (r) { +amdgpu_job_free (job); goto err2; + } r =dma_fence_wait_timeout (f, false, timeout);if (r ==0 ) {@@ -359,7 +363,6 @@ static int gfx_v12_1_ring_test_ib(struct amdgpu_ring *ring, long timeout)else r = -EINVAL ; err2: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f); err1:amdgpu_device_wb_free (adev, index);drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c +14
-10@@ -1895,24 +1895,29 @@ static int gfx_v6_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) {struct amdgpu_device *adev = ring->adev;struct dma_fence *f =NULL ; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;uint32_t tmp =0 ;long r;WREG32 (mmSCRATCH_REG0,0xCAFEDEAD ); -memset (&ib,0 ,sizeof (ib)); - r =amdgpu_ib_get (adev,NULL ,256 ,AMDGPU_IB_POOL_DIRECT , &ib); + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,256 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_GFX_RING_TEST );if (r)return r; - ib.ptr[0 ] =PACKET3 (PACKET3_SET_CONFIG_REG ,1 ); - ib.ptr[1 ] = mmSCRATCH_REG0 -PACKET3_SET_CONFIG_REG_START ; - ib.ptr[2 ] =0xDEADBEEF ; - ib.length_dw =3 ; + ib = &job->ibs[0 ]; + ib->ptr[0 ] =PACKET3 (PACKET3_SET_CONFIG_REG ,1 ); + ib->ptr[1 ] = mmSCRATCH_REG0 -PACKET3_SET_CONFIG_REG_START ; + ib->ptr[2 ] =0xDEADBEEF ; + ib->length_dw =3 ; - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (r) + r =amdgpu_job_submit_direct (job, ring, &f); +if (r) { +amdgpu_job_free (job); goto error; + } r =dma_fence_wait_timeout (f, false, timeout);if (r ==0 ) {@@ -1928,7 +1933,6 @@ static int gfx_v6_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) r = -EINVAL ; error: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f);return r; }drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c +15
-10@@ -2291,25 +2291,31 @@ static void gfx_v7_ring_emit_cntxcntl(struct amdgpu_ring *ring, uint32_t flags)static int gfx_v7_0_ring_test_ib (struct amdgpu_ring *ring,long timeout) {struct amdgpu_device *adev = ring->adev; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ;uint32_t tmp =0 ;long r;WREG32 (mmSCRATCH_REG0,0xCAFEDEAD ); -memset (&ib,0 ,sizeof (ib)); - r =amdgpu_ib_get (adev,NULL ,256 ,AMDGPU_IB_POOL_DIRECT , &ib); + + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,256 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_GFX_RING_TEST );if (r)return r; - ib.ptr[0 ] =PACKET3 (PACKET3_SET_UCONFIG_REG ,1 ); - ib.ptr[1 ] = mmSCRATCH_REG0 -PACKET3_SET_UCONFIG_REG_START ; - ib.ptr[2 ] =0xDEADBEEF ; - ib.length_dw =3 ; + ib = &job->ibs[0 ]; + ib->ptr[0 ] =PACKET3 (PACKET3_SET_UCONFIG_REG ,1 ); + ib->ptr[1 ] = mmSCRATCH_REG0 -PACKET3_SET_UCONFIG_REG_START ; + ib->ptr[2 ] =0xDEADBEEF ; + ib->length_dw =3 ; - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (r) + r =amdgpu_job_submit_direct (job, ring, &f); +if (r) { +amdgpu_job_free (job); goto error; + } r =dma_fence_wait_timeout (f, false, timeout);if (r ==0 ) {@@ -2325,7 +2331,6 @@ static int gfx_v7_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) r = -EINVAL ; error: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f);return r; }drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +72
-67@@ -868,9 +868,9 @@ static int gfx_v8_0_ring_test_ring(struct amdgpu_ring *ring)static int gfx_v8_0_ring_test_ib (struct amdgpu_ring *ring,long timeout) {struct amdgpu_device *adev = ring->adev; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ; -unsigned int index;uint64_t gpu_addr;uint32_t tmp;@@ -882,22 +882,26 @@ static int gfx_v8_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) gpu_addr = adev->wb.gpu_addr + (index *4 ); adev->wb.wb[index] =cpu_to_le32 (0xCAFEDEAD ); -memset (&ib,0 ,sizeof (ib)); - r =amdgpu_ib_get (adev,NULL ,20 ,AMDGPU_IB_POOL_DIRECT , &ib); + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,20 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_GFX_RING_TEST );if (r) goto err1; - ib.ptr[0 ] =PACKET3 (PACKET3_WRITE_DATA ,3 ); - ib.ptr[1 ] =WRITE_DATA_DST_SEL (5 ) |WR_CONFIRM ; - ib.ptr[2 ] =lower_32_bits (gpu_addr); - ib.ptr[3 ] =upper_32_bits (gpu_addr); - ib.ptr[4 ] =0xDEADBEEF ; - ib.length_dw =5 ; + ib = &job->ibs[0 ]; + ib->ptr[0 ] =PACKET3 (PACKET3_WRITE_DATA ,3 ); + ib->ptr[1 ] =WRITE_DATA_DST_SEL (5 ) |WR_CONFIRM ; + ib->ptr[2 ] =lower_32_bits (gpu_addr); + ib->ptr[3 ] =upper_32_bits (gpu_addr); + ib->ptr[4 ] =0xDEADBEEF ; + ib->length_dw =5 ; - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (r) + r =amdgpu_job_submit_direct (job, ring, &f); +if (r) { +amdgpu_job_free (job); goto err2; + } r =dma_fence_wait_timeout (f, false, timeout);if (r ==0 ) {@@ -914,7 +918,6 @@ static int gfx_v8_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) r = -EINVAL ; err2: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f); err1:amdgpu_device_wb_free (adev, index);@@ -1474,7 +1477,8 @@ static const u32 sec_ded_counter_registers[] =static int gfx_v8_0_do_edc_gpr_workarounds (struct amdgpu_device *adev) {struct amdgpu_ring *ring = &adev->gfx.compute_ring[0 ]; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ;int r, i;u32 tmp;@@ -1505,106 +1509,108 @@ static int gfx_v8_0_do_edc_gpr_workarounds(struct amdgpu_device *adev) total_size +=sizeof (sgpr_init_compute_shader);/* allocate an indirect buffer to put the commands in */ -memset (&ib,0 ,sizeof (ib)); - r =amdgpu_ib_get (adev,NULL , total_size, -AMDGPU_IB_POOL_DIRECT , &ib); + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL , total_size, +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_RUN_SHADER );if (r) {drm_err (adev_to_drm (adev),"failed to get ib (%d).\n" , r);return r; } + ib = &job->ibs[0 ];/* load the compute shaders */ for (i =0 ; i <ARRAY_SIZE (vgpr_init_compute_shader); i++) - ib.ptr[i + (vgpr_offset /4 )] = vgpr_init_compute_shader[i]; + ib->ptr[i + (vgpr_offset /4 )] = vgpr_init_compute_shader[i];for (i =0 ; i <ARRAY_SIZE (sgpr_init_compute_shader); i++) - ib.ptr[i + (sgpr_offset /4 )] = sgpr_init_compute_shader[i]; + ib->ptr[i + (sgpr_offset /4 )] = sgpr_init_compute_shader[i];/* init the ib length to 0 */ - ib.length_dw =0 ; + ib->length_dw =0 ;/* VGPR */ /* write the register state for the compute dispatch */ for (i =0 ; i <ARRAY_SIZE (vgpr_init_regs); i +=2 ) { - ib.ptr[ib.length_dw++] =PACKET3 (PACKET3_SET_SH_REG ,1 ); - ib.ptr[ib.length_dw++] = vgpr_init_regs[i] -PACKET3_SET_SH_REG_START ; - ib.ptr[ib.length_dw++] = vgpr_init_regs[i +1 ]; + ib->ptr[ib->length_dw++] =PACKET3 (PACKET3_SET_SH_REG ,1 ); + ib->ptr[ib->length_dw++] = vgpr_init_regs[i] -PACKET3_SET_SH_REG_START ; + ib->ptr[ib->length_dw++] = vgpr_init_regs[i +1 ]; }/* write the shader start address: mmCOMPUTE_PGM_LO, mmCOMPUTE_PGM_HI */ - gpu_addr = (ib.gpu_addr + (u64 )vgpr_offset) >>8 ; - ib.ptr[ib.length_dw++] =PACKET3 (PACKET3_SET_SH_REG ,2 ); - ib.ptr[ib.length_dw++] = mmCOMPUTE_PGM_LO -PACKET3_SET_SH_REG_START ; - ib.ptr[ib.length_dw++] =lower_32_bits (gpu_addr); - ib.ptr[ib.length_dw++] =upper_32_bits (gpu_addr); + gpu_addr = (ib->gpu_addr + (u64 )vgpr_offset) >>8 ; + ib->ptr[ib->length_dw++] =PACKET3 (PACKET3_SET_SH_REG ,2 ); + ib->ptr[ib->length_dw++] = mmCOMPUTE_PGM_LO -PACKET3_SET_SH_REG_START ; + ib->ptr[ib->length_dw++] =lower_32_bits (gpu_addr); + ib->ptr[ib->length_dw++] =upper_32_bits (gpu_addr);/* write dispatch packet */ - ib.ptr[ib.length_dw++] =PACKET3 (PACKET3_DISPATCH_DIRECT ,3 ); - ib.ptr[ib.length_dw++] =8 ;/* x */ - ib.ptr[ib.length_dw++] =1 ;/* y */ - ib.ptr[ib.length_dw++] =1 ;/* z */ - ib.ptr[ib.length_dw++] = + ib->ptr[ib->length_dw++] =PACKET3 (PACKET3_DISPATCH_DIRECT ,3 ); + ib->ptr[ib->length_dw++] =8 ;/* x */ + ib->ptr[ib->length_dw++] =1 ;/* y */ + ib->ptr[ib->length_dw++] =1 ;/* z */ + ib->ptr[ib->length_dw++] =REG_SET_FIELD (0 ,COMPUTE_DISPATCH_INITIATOR ,COMPUTE_SHADER_EN ,1 );/* write CS partial flush packet */ - ib.ptr[ib.length_dw++] =PACKET3 (PACKET3_EVENT_WRITE ,0 ); - ib.ptr[ib.length_dw++] =EVENT_TYPE (7 ) |EVENT_INDEX (4 ); + ib->ptr[ib->length_dw++] =PACKET3 (PACKET3_EVENT_WRITE ,0 ); + ib->ptr[ib->length_dw++] =EVENT_TYPE (7 ) |EVENT_INDEX (4 );/* SGPR1 */ /* write the register state for the compute dispatch */ for (i =0 ; i <ARRAY_SIZE (sgpr1_init_regs); i +=2 ) { - ib.ptr[ib.length_dw++] =PACKET3 (PACKET3_SET_SH_REG ,1 ); - ib.ptr[ib.length_dw++] = sgpr1_init_regs[i] -PACKET3_SET_SH_REG_START ; - ib.ptr[ib.length_dw++] = sgpr1_init_regs[i +1 ]; + ib->ptr[ib->length_dw++] =PACKET3 (PACKET3_SET_SH_REG ,1 ); + ib->ptr[ib->length_dw++] = sgpr1_init_regs[i] -PACKET3_SET_SH_REG_START ; + ib->ptr[ib->length_dw++] = sgpr1_init_regs[i +1 ]; }/* write the shader start address: mmCOMPUTE_PGM_LO, mmCOMPUTE_PGM_HI */ - gpu_addr = (ib.gpu_addr + (u64 )sgpr_offset) >>8 ; - ib.ptr[ib.length_dw++] =PACKET3 (PACKET3_SET_SH_REG ,2 ); - ib.ptr[ib.length_dw++] = mmCOMPUTE_PGM_LO -PACKET3_SET_SH_REG_START ; - ib.ptr[ib.length_dw++] =lower_32_bits (gpu_addr); - ib.ptr[ib.length_dw++] =upper_32_bits (gpu_addr); + gpu_addr = (ib->gpu_addr + (u64 )sgpr_offset) >>8 ; + ib->ptr[ib->length_dw++] =PACKET3 (PACKET3_SET_SH_REG ,2 ); + ib->ptr[ib->length_dw++] = mmCOMPUTE_PGM_LO -PACKET3_SET_SH_REG_START ; + ib->ptr[ib->length_dw++] =lower_32_bits (gpu_addr); + ib->ptr[ib->length_dw++] =upper_32_bits (gpu_addr);/* write dispatch packet */ - ib.ptr[ib.length_dw++] =PACKET3 (PACKET3_DISPATCH_DIRECT ,3 ); - ib.ptr[ib.length_dw++] =8 ;/* x */ - ib.ptr[ib.length_dw++] =1 ;/* y */ - ib.ptr[ib.length_dw++] =1 ;/* z */ - ib.ptr[ib.length_dw++] = + ib->ptr[ib->length_dw++] =PACKET3 (PACKET3_DISPATCH_DIRECT ,3 ); + ib->ptr[ib->length_dw++] =8 ;/* x */ + ib->ptr[ib->length_dw++] =1 ;/* y */ + ib->ptr[ib->length_dw++] =1 ;/* z */ + ib->ptr[ib->length_dw++] =REG_SET_FIELD (0 ,COMPUTE_DISPATCH_INITIATOR ,COMPUTE_SHADER_EN ,1 );/* write CS partial flush packet */ - ib.ptr[ib.length_dw++] =PACKET3 (PACKET3_EVENT_WRITE ,0 ); - ib.ptr[ib.length_dw++] =EVENT_TYPE (7 ) |EVENT_INDEX (4 ); + ib->ptr[ib->length_dw++] =PACKET3 (PACKET3_EVENT_WRITE ,0 ); + ib->ptr[ib->length_dw++] =EVENT_TYPE (7 ) |EVENT_INDEX (4 );/* SGPR2 */ /* write the register state for the compute dispatch */ for (i =0 ; i <ARRAY_SIZE (sgpr2_init_regs); i +=2 ) { - ib.ptr[ib.length_dw++] =PACKET3 (PACKET3_SET_SH_REG ,1 ); - ib.ptr[ib.length_dw++] = sgpr2_init_regs[i] -PACKET3_SET_SH_REG_START ; - ib.ptr[ib.length_dw++] = sgpr2_init_regs[i +1 ]; + ib->ptr[ib->length_dw++] =PACKET3 (PACKET3_SET_SH_REG ,1 ); + ib->ptr[ib->length_dw++] = sgpr2_init_regs[i] -PACKET3_SET_SH_REG_START ; + ib->ptr[ib->length_dw++] = sgpr2_init_regs[i +1 ]; }/* write the shader start address: mmCOMPUTE_PGM_LO, mmCOMPUTE_PGM_HI */ - gpu_addr = (ib.gpu_addr + (u64 )sgpr_offset) >>8 ; - ib.ptr[ib.length_dw++] =PACKET3 (PACKET3_SET_SH_REG ,2 ); - ib.ptr[ib.length_dw++] = mmCOMPUTE_PGM_LO -PACKET3_SET_SH_REG_START ; - ib.ptr[ib.length_dw++] =lower_32_bits (gpu_addr); - ib.ptr[ib.length_dw++] =upper_32_bits (gpu_addr); + gpu_addr = (ib->gpu_addr + (u64 )sgpr_offset) >>8 ; + ib->ptr[ib->length_dw++] =PACKET3 (PACKET3_SET_SH_REG ,2 ); + ib->ptr[ib->length_dw++] = mmCOMPUTE_PGM_LO -PACKET3_SET_SH_REG_START ; + ib->ptr[ib->length_dw++] =lower_32_bits (gpu_addr); + ib->ptr[ib->length_dw++] =upper_32_bits (gpu_addr);/* write dispatch packet */ - ib.ptr[ib.length_dw++] =PACKET3 (PACKET3_DISPATCH_DIRECT ,3 ); - ib.ptr[ib.length_dw++] =8 ;/* x */ - ib.ptr[ib.length_dw++] =1 ;/* y */ - ib.ptr[ib.length_dw++] =1 ;/* z */ - ib.ptr[ib.length_dw++] = + ib->ptr[ib->length_dw++] =PACKET3 (PACKET3_DISPATCH_DIRECT ,3 ); + ib->ptr[ib->length_dw++] =8 ;/* x */ + ib->ptr[ib->length_dw++] =1 ;/* y */ + ib->ptr[ib->length_dw++] =1 ;/* z */ + ib->ptr[ib->length_dw++] =REG_SET_FIELD (0 ,COMPUTE_DISPATCH_INITIATOR ,COMPUTE_SHADER_EN ,1 );/* write CS partial flush packet */ - ib.ptr[ib.length_dw++] =PACKET3 (PACKET3_EVENT_WRITE ,0 ); - ib.ptr[ib.length_dw++] =EVENT_TYPE (7 ) |EVENT_INDEX (4 ); + ib->ptr[ib->length_dw++] =PACKET3 (PACKET3_EVENT_WRITE ,0 ); + ib->ptr[ib->length_dw++] =EVENT_TYPE (7 ) |EVENT_INDEX (4 );/* shedule the ib on the ring */ - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); + r =amdgpu_job_submit_direct (job, ring, &f);if (r) {drm_err (adev_to_drm (adev),"ib submit failed (%d).\n" , r); +amdgpu_job_free (job); goto fail; }@@ -1629,7 +1635,6 @@ static int gfx_v8_0_do_edc_gpr_workarounds(struct amdgpu_device *adev)RREG32 (sec_ded_counter_registers[i]); fail: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f);return r;drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +71
-67@@ -1224,9 +1224,9 @@ static int gfx_v9_0_ring_test_ring(struct amdgpu_ring *ring)static int gfx_v9_0_ring_test_ib (struct amdgpu_ring *ring,long timeout) {struct amdgpu_device *adev = ring->adev; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ; -unsigned index;uint64_t gpu_addr;uint32_t tmp;@@ -1238,22 +1238,26 @@ static int gfx_v9_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) gpu_addr = adev->wb.gpu_addr + (index *4 ); adev->wb.wb[index] =cpu_to_le32 (0xCAFEDEAD ); -memset (&ib,0 ,sizeof (ib)); - r =amdgpu_ib_get (adev,NULL ,20 ,AMDGPU_IB_POOL_DIRECT , &ib); + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,20 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_GFX_RING_TEST );if (r) goto err1; - ib.ptr[0 ] =PACKET3 (PACKET3_WRITE_DATA ,3 ); - ib.ptr[1 ] =WRITE_DATA_DST_SEL (5 ) |WR_CONFIRM ; - ib.ptr[2 ] =lower_32_bits (gpu_addr); - ib.ptr[3 ] =upper_32_bits (gpu_addr); - ib.ptr[4 ] =0xDEADBEEF ; - ib.length_dw =5 ; + ib = &job->ibs[0 ]; + ib->ptr[0 ] =PACKET3 (PACKET3_WRITE_DATA ,3 ); + ib->ptr[1 ] =WRITE_DATA_DST_SEL (5 ) |WR_CONFIRM ; + ib->ptr[2 ] =lower_32_bits (gpu_addr); + ib->ptr[3 ] =upper_32_bits (gpu_addr); + ib->ptr[4 ] =0xDEADBEEF ; + ib->length_dw =5 ; - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (r) + r =amdgpu_job_submit_direct (job, ring, &f); +if (r) { +amdgpu_job_free (job); goto err2; + } r =dma_fence_wait_timeout (f, false, timeout);if (r ==0 ) {@@ -1270,7 +1274,6 @@ static int gfx_v9_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) r = -EINVAL ; err2: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f); err1:amdgpu_device_wb_free (adev, index);@@ -4624,7 +4627,8 @@ static int gfx_v9_0_do_edc_gds_workarounds(struct amdgpu_device *adev)static int gfx_v9_0_do_edc_gpr_workarounds (struct amdgpu_device *adev) {struct amdgpu_ring *ring = &adev->gfx.compute_ring[0 ]; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ;int r, i;unsigned total_size, vgpr_offset, sgpr_offset;@@ -4670,9 +4674,9 @@ static int gfx_v9_0_do_edc_gpr_workarounds(struct amdgpu_device *adev) total_size +=sizeof (sgpr_init_compute_shader);/* allocate an indirect buffer to put the commands in */ -memset (&ib,0 ,sizeof (ib)); - r =amdgpu_ib_get (adev,NULL , total_size, -AMDGPU_IB_POOL_DIRECT , &ib); + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL , total_size, +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_RUN_SHADER );if (r) {drm_err (adev_to_drm (adev),"failed to get ib (%d).\n" , r);return r;@@ -4680,102 +4684,103 @@ static int gfx_v9_0_do_edc_gpr_workarounds(struct amdgpu_device *adev)/* load the compute shaders */ for (i =0 ; i < vgpr_init_shader_size/sizeof (u32); i++) - ib.ptr[i + (vgpr_offset /4 )] = vgpr_init_shader_ptr[i]; + ib->ptr[i + (vgpr_offset /4 )] = vgpr_init_shader_ptr[i];for (i =0 ; i <ARRAY_SIZE (sgpr_init_compute_shader); i++) - ib.ptr[i + (sgpr_offset /4 )] = sgpr_init_compute_shader[i]; + ib->ptr[i + (sgpr_offset /4 )] = sgpr_init_compute_shader[i];/* init the ib length to 0 */ - ib.length_dw =0 ; + ib->length_dw =0 ;/* VGPR */ /* write the register state for the compute dispatch */ for (i =0 ; i < gpr_reg_size; i++) { - ib.ptr[ib.length_dw++] =PACKET3 (PACKET3_SET_SH_REG ,1 ); - ib.ptr[ib.length_dw++] =SOC15_REG_ENTRY_OFFSET (vgpr_init_regs_ptr[i]) + ib->ptr[ib->length_dw++] =PACKET3 (PACKET3_SET_SH_REG ,1 ); + ib->ptr[ib->length_dw++] =SOC15_REG_ENTRY_OFFSET (vgpr_init_regs_ptr[i]) -PACKET3_SET_SH_REG_START ; - ib.ptr[ib.length_dw++] = vgpr_init_regs_ptr[i].reg_value; + ib->ptr[ib->length_dw++] = vgpr_init_regs_ptr[i].reg_value; }/* write the shader start address: mmCOMPUTE_PGM_LO, mmCOMPUTE_PGM_HI */ - gpu_addr = (ib.gpu_addr + (u64 )vgpr_offset) >>8 ; - ib.ptr[ib.length_dw++] =PACKET3 (PACKET3_SET_SH_REG ,2 ); - ib.ptr[ib.length_dw++] =SOC15_REG_OFFSET (GC ,0 , mmCOMPUTE_PGM_LO) + gpu_addr = (ib->gpu_addr + (u64 )vgpr_offset) >>8 ; + ib->ptr[ib->length_dw++] =PACKET3 (PACKET3_SET_SH_REG ,2 ); + ib->ptr[ib->length_dw++] =SOC15_REG_OFFSET (GC ,0 , mmCOMPUTE_PGM_LO) -PACKET3_SET_SH_REG_START ; - ib.ptr[ib.length_dw++] =lower_32_bits (gpu_addr); - ib.ptr[ib.length_dw++] =upper_32_bits (gpu_addr); + ib->ptr[ib->length_dw++] =lower_32_bits (gpu_addr); + ib->ptr[ib->length_dw++] =upper_32_bits (gpu_addr);/* write dispatch packet */ - ib.ptr[ib.length_dw++] =PACKET3 (PACKET3_DISPATCH_DIRECT ,3 ); - ib.ptr[ib.length_dw++] = compute_dim_x *2 ;/* x */ - ib.ptr[ib.length_dw++] =1 ;/* y */ - ib.ptr[ib.length_dw++] =1 ;/* z */ - ib.ptr[ib.length_dw++] = + ib->ptr[ib->length_dw++] =PACKET3 (PACKET3_DISPATCH_DIRECT ,3 ); + ib->ptr[ib->length_dw++] = compute_dim_x *2 ;/* x */ + ib->ptr[ib->length_dw++] =1 ;/* y */ + ib->ptr[ib->length_dw++] =1 ;/* z */ + ib->ptr[ib->length_dw++] =REG_SET_FIELD (0 ,COMPUTE_DISPATCH_INITIATOR ,COMPUTE_SHADER_EN ,1 );/* write CS partial flush packet */ - ib.ptr[ib.length_dw++] =PACKET3 (PACKET3_EVENT_WRITE ,0 ); - ib.ptr[ib.length_dw++] =EVENT_TYPE (7 ) |EVENT_INDEX (4 ); + ib->ptr[ib->length_dw++] =PACKET3 (PACKET3_EVENT_WRITE ,0 ); + ib->ptr[ib->length_dw++] =EVENT_TYPE (7 ) |EVENT_INDEX (4 );/* SGPR1 */ /* write the register state for the compute dispatch */ for (i =0 ; i < gpr_reg_size; i++) { - ib.ptr[ib.length_dw++] =PACKET3 (PACKET3_SET_SH_REG ,1 ); - ib.ptr[ib.length_dw++] =SOC15_REG_ENTRY_OFFSET (sgpr1_init_regs[i]) + ib->ptr[ib->length_dw++] =PACKET3 (PACKET3_SET_SH_REG ,1 ); + ib->ptr[ib->length_dw++] =SOC15_REG_ENTRY_OFFSET (sgpr1_init_regs[i]) -PACKET3_SET_SH_REG_START ; - ib.ptr[ib.length_dw++] = sgpr1_init_regs[i].reg_value; + ib->ptr[ib->length_dw++] = sgpr1_init_regs[i].reg_value; }/* write the shader start address: mmCOMPUTE_PGM_LO, mmCOMPUTE_PGM_HI */ - gpu_addr = (ib.gpu_addr + (u64 )sgpr_offset) >>8 ; - ib.ptr[ib.length_dw++] =PACKET3 (PACKET3_SET_SH_REG ,2 ); - ib.ptr[ib.length_dw++] =SOC15_REG_OFFSET (GC ,0 , mmCOMPUTE_PGM_LO) + gpu_addr = (ib->gpu_addr + (u64 )sgpr_offset) >>8 ; + ib->ptr[ib->length_dw++] =PACKET3 (PACKET3_SET_SH_REG ,2 ); + ib->ptr[ib->length_dw++] =SOC15_REG_OFFSET (GC ,0 , mmCOMPUTE_PGM_LO) -PACKET3_SET_SH_REG_START ; - ib.ptr[ib.length_dw++] =lower_32_bits (gpu_addr); - ib.ptr[ib.length_dw++] =upper_32_bits (gpu_addr); + ib->ptr[ib->length_dw++] =lower_32_bits (gpu_addr); + ib->ptr[ib->length_dw++] =upper_32_bits (gpu_addr);/* write dispatch packet */ - ib.ptr[ib.length_dw++] =PACKET3 (PACKET3_DISPATCH_DIRECT ,3 ); - ib.ptr[ib.length_dw++] = compute_dim_x /2 * sgpr_work_group_size;/* x */ - ib.ptr[ib.length_dw++] =1 ;/* y */ - ib.ptr[ib.length_dw++] =1 ;/* z */ - ib.ptr[ib.length_dw++] = + ib->ptr[ib->length_dw++] =PACKET3 (PACKET3_DISPATCH_DIRECT ,3 ); + ib->ptr[ib->length_dw++] = compute_dim_x /2 * sgpr_work_group_size;/* x */ + ib->ptr[ib->length_dw++] =1 ;/* y */ + ib->ptr[ib->length_dw++] =1 ;/* z */ + ib->ptr[ib->length_dw++] =REG_SET_FIELD (0 ,COMPUTE_DISPATCH_INITIATOR ,COMPUTE_SHADER_EN ,1 );/* write CS partial flush packet */ - ib.ptr[ib.length_dw++] =PACKET3 (PACKET3_EVENT_WRITE ,0 ); - ib.ptr[ib.length_dw++] =EVENT_TYPE (7 ) |EVENT_INDEX (4 ); + ib->ptr[ib->length_dw++] =PACKET3 (PACKET3_EVENT_WRITE ,0 ); + ib->ptr[ib->length_dw++] =EVENT_TYPE (7 ) |EVENT_INDEX (4 );/* SGPR2 */ /* write the register state for the compute dispatch */ for (i =0 ; i < gpr_reg_size; i++) { - ib.ptr[ib.length_dw++] =PACKET3 (PACKET3_SET_SH_REG ,1 ); - ib.ptr[ib.length_dw++] =SOC15_REG_ENTRY_OFFSET (sgpr2_init_regs[i]) + ib->ptr[ib->length_dw++] =PACKET3 (PACKET3_SET_SH_REG ,1 ); + ib->ptr[ib->length_dw++] =SOC15_REG_ENTRY_OFFSET (sgpr2_init_regs[i]) -PACKET3_SET_SH_REG_START ; - ib.ptr[ib.length_dw++] = sgpr2_init_regs[i].reg_value; + ib->ptr[ib->length_dw++] = sgpr2_init_regs[i].reg_value; }/* write the shader start address: mmCOMPUTE_PGM_LO, mmCOMPUTE_PGM_HI */ - gpu_addr = (ib.gpu_addr + (u64 )sgpr_offset) >>8 ; - ib.ptr[ib.length_dw++] =PACKET3 (PACKET3_SET_SH_REG ,2 ); - ib.ptr[ib.length_dw++] =SOC15_REG_OFFSET (GC ,0 , mmCOMPUTE_PGM_LO) + gpu_addr = (ib->gpu_addr + (u64 )sgpr_offset) >>8 ; + ib->ptr[ib->length_dw++] =PACKET3 (PACKET3_SET_SH_REG ,2 ); + ib->ptr[ib->length_dw++] =SOC15_REG_OFFSET (GC ,0 , mmCOMPUTE_PGM_LO) -PACKET3_SET_SH_REG_START ; - ib.ptr[ib.length_dw++] =lower_32_bits (gpu_addr); - ib.ptr[ib.length_dw++] =upper_32_bits (gpu_addr); + ib->ptr[ib->length_dw++] =lower_32_bits (gpu_addr); + ib->ptr[ib->length_dw++] =upper_32_bits (gpu_addr);/* write dispatch packet */ - ib.ptr[ib.length_dw++] =PACKET3 (PACKET3_DISPATCH_DIRECT ,3 ); - ib.ptr[ib.length_dw++] = compute_dim_x /2 * sgpr_work_group_size;/* x */ - ib.ptr[ib.length_dw++] =1 ;/* y */ - ib.ptr[ib.length_dw++] =1 ;/* z */ - ib.ptr[ib.length_dw++] = + ib->ptr[ib->length_dw++] =PACKET3 (PACKET3_DISPATCH_DIRECT ,3 ); + ib->ptr[ib->length_dw++] = compute_dim_x /2 * sgpr_work_group_size;/* x */ + ib->ptr[ib->length_dw++] =1 ;/* y */ + ib->ptr[ib->length_dw++] =1 ;/* z */ + ib->ptr[ib->length_dw++] =REG_SET_FIELD (0 ,COMPUTE_DISPATCH_INITIATOR ,COMPUTE_SHADER_EN ,1 );/* write CS partial flush packet */ - ib.ptr[ib.length_dw++] =PACKET3 (PACKET3_EVENT_WRITE ,0 ); - ib.ptr[ib.length_dw++] =EVENT_TYPE (7 ) |EVENT_INDEX (4 ); + ib->ptr[ib->length_dw++] =PACKET3 (PACKET3_EVENT_WRITE ,0 ); + ib->ptr[ib->length_dw++] =EVENT_TYPE (7 ) |EVENT_INDEX (4 );/* shedule the ib on the ring */ - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); + r =amdgpu_job_submit_direct (job, ring, &f);if (r) {drm_err (adev_to_drm (adev),"ib schedule failed (%d).\n" , r); +amdgpu_job_free (job); goto fail; }@@ -4787,7 +4792,6 @@ static int gfx_v9_0_do_edc_gpr_workarounds(struct amdgpu_device *adev) } fail: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f);return r;drivers/gpu/drm/amd/amdgpu/gfx_v9_4_2.c +8
-18@@ -345,12 +345,13 @@ const struct soc15_reg_entry sgpr64_init_regs_aldebaran[] = {static int gfx_v9_4_2_run_shader (struct amdgpu_device *adev,struct amdgpu_ring *ring, -struct amdgpu_ib *ib,const u32 *shader_ptr,u32 shader_size,const struct soc15_reg_entry *init_regs,u32 regs_size,u32 compute_dim_x,u64 wb_gpu_addr,u32 pattern,struct dma_fence **fence_ptr) { +struct amdgpu_job *job; +struct amdgpu_ib *ib;int r, i;uint32_t total_size, shader_offset;u64 gpu_addr;@@ -360,10 +361,9 @@ static int gfx_v9_4_2_run_shader(struct amdgpu_device *adev, shader_offset = total_size; total_size +=ALIGN (shader_size,256 ); -/* allocate an indirect buffer to put the commands in */ -memset (ib,0 ,sizeof (*ib)); - r =amdgpu_ib_get (adev,NULL , total_size, -AMDGPU_IB_POOL_DIRECT , ib); + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL , total_size, +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_RUN_SHADER );if (r) {dev_err (adev->dev,"failed to get ib (%d).\n" , r);return r;@@ -408,11 +408,11 @@ static int gfx_v9_4_2_run_shader(struct amdgpu_device *adev, ib->ptr[ib->length_dw++] =REG_SET_FIELD (0 ,COMPUTE_DISPATCH_INITIATOR ,COMPUTE_SHADER_EN ,1 ); -/* shedule the ib on the ring */ - r =amdgpu_ib_schedule (ring,1 , ib,NULL , fence_ptr); +/* schedule the ib on the ring */ + r =amdgpu_job_submit_direct (job, ring, fence_ptr);if (r) {dev_err (adev->dev,"ib submit failed (%d).\n" , r); -amdgpu_ib_free (ib,NULL ); +amdgpu_job_free (job); }return r; }@@ -493,7 +493,6 @@ static int gfx_v9_4_2_do_sgprs_init(struct amdgpu_device *adev)int wb_size = adev->gfx.config.max_shader_engines *CU_ID_MAX *SIMD_ID_MAX *WAVE_ID_MAX ;struct amdgpu_ib wb_ib; -struct amdgpu_ib disp_ibs[3 ];struct dma_fence *fences[3 ];u32 pattern[3 ] = {0x1 ,0x5 ,0xa };@@ -514,7 +513,6 @@ static int gfx_v9_4_2_do_sgprs_init(struct amdgpu_device *adev) r = gfx_v9_4_2_run_shader(adev, &adev->gfx.compute_ring[0], - &disp_ibs[0], sgpr112_init_compute_shader_aldebaran, sizeof(sgpr112_init_compute_shader_aldebaran), sgpr112_init_regs_aldebaran,@@ -539,7 +537,6 @@ static int gfx_v9_4_2_do_sgprs_init(struct amdgpu_device *adev) r = gfx_v9_4_2_run_shader(adev, &adev->gfx.compute_ring[1], - &disp_ibs[1], sgpr96_init_compute_shader_aldebaran, sizeof(sgpr96_init_compute_shader_aldebaran), sgpr96_init_regs_aldebaran,@@ -579,7 +576,6 @@ static int gfx_v9_4_2_do_sgprs_init(struct amdgpu_device *adev)memset (wb_ib.ptr,0 , (1 + wb_size) *sizeof (uint32_t )); r = gfx_v9_4_2_run_shader(adev, &adev->gfx.compute_ring[0], - &disp_ibs[2], sgpr64_init_compute_shader_aldebaran, sizeof(sgpr64_init_compute_shader_aldebaran), sgpr64_init_regs_aldebaran,@@ -611,13 +607,10 @@ static int gfx_v9_4_2_do_sgprs_init(struct amdgpu_device *adev) } disp2_failed: -amdgpu_ib_free (&disp_ibs[2 ],NULL );dma_fence_put (fences[2 ]); disp1_failed: -amdgpu_ib_free (&disp_ibs[1 ],NULL );dma_fence_put (fences[1 ]); disp0_failed: -amdgpu_ib_free (&disp_ibs[0 ],NULL );dma_fence_put (fences[0 ]); pro_end:amdgpu_ib_free (&wb_ib,NULL );@@ -637,7 +630,6 @@ static int gfx_v9_4_2_do_vgprs_init(struct amdgpu_device *adev)int wb_size = adev->gfx.config.max_shader_engines *CU_ID_MAX *SIMD_ID_MAX *WAVE_ID_MAX ;struct amdgpu_ib wb_ib; -struct amdgpu_ib disp_ib;struct dma_fence *fence;u32 pattern =0xa ;@@ -657,7 +649,6 @@ static int gfx_v9_4_2_do_vgprs_init(struct amdgpu_device *adev) r = gfx_v9_4_2_run_shader(adev, &adev->gfx.compute_ring[0], - &disp_ib, vgpr_init_compute_shader_aldebaran, sizeof(vgpr_init_compute_shader_aldebaran), vgpr_init_regs_aldebaran,@@ -687,7 +678,6 @@ static int gfx_v9_4_2_do_vgprs_init(struct amdgpu_device *adev) } disp_failed: -amdgpu_ib_free (&disp_ib,NULL );dma_fence_put (fence); pro_end:amdgpu_ib_free (&wb_ib,NULL );drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c +16
-13@@ -451,9 +451,9 @@ static int gfx_v9_4_3_ring_test_ring(struct amdgpu_ring *ring)static int gfx_v9_4_3_ring_test_ib (struct amdgpu_ring *ring,long timeout) {struct amdgpu_device *adev = ring->adev; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ; -unsigned index;uint64_t gpu_addr;uint32_t tmp;@@ -465,22 +465,26 @@ static int gfx_v9_4_3_ring_test_ib(struct amdgpu_ring *ring, long timeout) gpu_addr = adev->wb.gpu_addr + (index *4 ); adev->wb.wb[index] =cpu_to_le32 (0xCAFEDEAD ); -memset (&ib,0 ,sizeof (ib)); - r =amdgpu_ib_get (adev,NULL ,20 ,AMDGPU_IB_POOL_DIRECT , &ib); + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,20 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_GFX_RING_TEST );if (r) goto err1; - ib.ptr[0 ] =PACKET3 (PACKET3_WRITE_DATA ,3 ); - ib.ptr[1 ] =WRITE_DATA_DST_SEL (5 ) |WR_CONFIRM ; - ib.ptr[2 ] =lower_32_bits (gpu_addr); - ib.ptr[3 ] =upper_32_bits (gpu_addr); - ib.ptr[4 ] =0xDEADBEEF ; - ib.length_dw =5 ; + ib = &job->ibs[0 ]; + ib->ptr[0 ] =PACKET3 (PACKET3_WRITE_DATA ,3 ); + ib->ptr[1 ] =WRITE_DATA_DST_SEL (5 ) |WR_CONFIRM ; + ib->ptr[2 ] =lower_32_bits (gpu_addr); + ib->ptr[3 ] =upper_32_bits (gpu_addr); + ib->ptr[4 ] =0xDEADBEEF ; + ib->length_dw =5 ; - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (r) + r =amdgpu_job_submit_direct (job, ring, &f); +if (r) { +amdgpu_job_free (job); goto err2; + } r =dma_fence_wait_timeout (f, false, timeout);if (r ==0 ) {@@ -497,7 +501,6 @@ static int gfx_v9_4_3_ring_test_ib(struct amdgpu_ring *ring, long timeout) r = -EINVAL ; err2: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f); err1:amdgpu_device_wb_free (adev, index);drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c +21
-17@@ -584,7 +584,8 @@ static int sdma_v2_4_ring_test_ring(struct amdgpu_ring *ring)static int sdma_v2_4_ring_test_ib (struct amdgpu_ring *ring,long timeout) {struct amdgpu_device *adev = ring->adev; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ;unsigned index;u32 tmp =0 ;@@ -598,26 +599,30 @@ static int sdma_v2_4_ring_test_ib(struct amdgpu_ring *ring, long timeout) gpu_addr = adev->wb.gpu_addr + (index *4 ); tmp =0xCAFEDEAD ; adev->wb.wb[index] =cpu_to_le32 (tmp); -memset (&ib,0 ,sizeof (ib)); - r =amdgpu_ib_get (adev,NULL ,256 , -AMDGPU_IB_POOL_DIRECT , &ib); + + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,256 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_SDMA_RING_TEST );if (r) goto err0; - ib.ptr[0 ] =SDMA_PKT_HEADER_OP (SDMA_OP_WRITE ) | + ib = &job->ibs[0 ]; + ib->ptr[0 ] =SDMA_PKT_HEADER_OP (SDMA_OP_WRITE ) |SDMA_PKT_HEADER_SUB_OP (SDMA_SUBOP_WRITE_LINEAR ); - ib.ptr[1 ] =lower_32_bits (gpu_addr); - ib.ptr[2 ] =upper_32_bits (gpu_addr); - ib.ptr[3 ] =SDMA_PKT_WRITE_UNTILED_DW_3_COUNT (1 ); - ib.ptr[4 ] =0xDEADBEEF ; - ib.ptr[5 ] =SDMA_PKT_HEADER_OP (SDMA_OP_NOP ); - ib.ptr[6 ] =SDMA_PKT_HEADER_OP (SDMA_OP_NOP ); - ib.ptr[7 ] =SDMA_PKT_HEADER_OP (SDMA_OP_NOP ); - ib.length_dw =8 ; - - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (r) + ib->ptr[1 ] =lower_32_bits (gpu_addr); + ib->ptr[2 ] =upper_32_bits (gpu_addr); + ib->ptr[3 ] =SDMA_PKT_WRITE_UNTILED_DW_3_COUNT (1 ); + ib->ptr[4 ] =0xDEADBEEF ; + ib->ptr[5 ] =SDMA_PKT_HEADER_OP (SDMA_OP_NOP ); + ib->ptr[6 ] =SDMA_PKT_HEADER_OP (SDMA_OP_NOP ); + ib->ptr[7 ] =SDMA_PKT_HEADER_OP (SDMA_OP_NOP ); + ib->length_dw =8 ; + + r =amdgpu_job_submit_direct (job, ring, &f); +if (r) { +amdgpu_job_free (job); goto err1; + } r =dma_fence_wait_timeout (f, false, timeout);if (r ==0 ) {@@ -633,7 +638,6 @@ static int sdma_v2_4_ring_test_ib(struct amdgpu_ring *ring, long timeout) r = -EINVAL ; err1: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f); err0:amdgpu_device_wb_free (adev, index);drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c +21
-17@@ -858,7 +858,8 @@ static int sdma_v3_0_ring_test_ring(struct amdgpu_ring *ring)static int sdma_v3_0_ring_test_ib (struct amdgpu_ring *ring,long timeout) {struct amdgpu_device *adev = ring->adev; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ;unsigned index;u32 tmp =0 ;@@ -872,26 +873,30 @@ static int sdma_v3_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) gpu_addr = adev->wb.gpu_addr + (index *4 ); tmp =0xCAFEDEAD ; adev->wb.wb[index] =cpu_to_le32 (tmp); -memset (&ib,0 ,sizeof (ib)); - r =amdgpu_ib_get (adev,NULL ,256 , -AMDGPU_IB_POOL_DIRECT , &ib); + + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,256 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_SDMA_RING_TEST );if (r) goto err0; - ib.ptr[0 ] =SDMA_PKT_HEADER_OP (SDMA_OP_WRITE ) | + ib = &job->ibs[0 ]; + ib->ptr[0 ] =SDMA_PKT_HEADER_OP (SDMA_OP_WRITE ) |SDMA_PKT_HEADER_SUB_OP (SDMA_SUBOP_WRITE_LINEAR ); - ib.ptr[1 ] =lower_32_bits (gpu_addr); - ib.ptr[2 ] =upper_32_bits (gpu_addr); - ib.ptr[3 ] =SDMA_PKT_WRITE_UNTILED_DW_3_COUNT (1 ); - ib.ptr[4 ] =0xDEADBEEF ; - ib.ptr[5 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.ptr[6 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.ptr[7 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.length_dw =8 ; - - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (r) + ib->ptr[1 ] =lower_32_bits (gpu_addr); + ib->ptr[2 ] =upper_32_bits (gpu_addr); + ib->ptr[3 ] =SDMA_PKT_WRITE_UNTILED_DW_3_COUNT (1 ); + ib->ptr[4 ] =0xDEADBEEF ; + ib->ptr[5 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->ptr[6 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->ptr[7 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->length_dw =8 ; + + r =amdgpu_job_submit_direct (job, ring, &f); +if (r) { +amdgpu_job_free (job); goto err1; + } r =dma_fence_wait_timeout (f, false, timeout);if (r ==0 ) {@@ -906,7 +911,6 @@ static int sdma_v3_0_ring_test_ib(struct amdgpu_ring *ring, long timeout)else r = -EINVAL ; err1: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f); err0:amdgpu_device_wb_free (adev, index);drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c +21
-17@@ -1516,7 +1516,8 @@ static int sdma_v4_0_ring_test_ring(struct amdgpu_ring *ring)static int sdma_v4_0_ring_test_ib (struct amdgpu_ring *ring,long timeout) {struct amdgpu_device *adev = ring->adev; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ;unsigned index;long r;@@ -1530,26 +1531,30 @@ static int sdma_v4_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) gpu_addr = adev->wb.gpu_addr + (index *4 ); tmp =0xCAFEDEAD ; adev->wb.wb[index] =cpu_to_le32 (tmp); -memset (&ib,0 ,sizeof (ib)); - r =amdgpu_ib_get (adev,NULL ,256 , -AMDGPU_IB_POOL_DIRECT , &ib); + + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,256 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_SDMA_RING_TEST );if (r) goto err0; - ib.ptr[0 ] =SDMA_PKT_HEADER_OP (SDMA_OP_WRITE ) | + ib = &job->ibs[0 ]; + ib->ptr[0 ] =SDMA_PKT_HEADER_OP (SDMA_OP_WRITE ) |SDMA_PKT_HEADER_SUB_OP (SDMA_SUBOP_WRITE_LINEAR ); - ib.ptr[1 ] =lower_32_bits (gpu_addr); - ib.ptr[2 ] =upper_32_bits (gpu_addr); - ib.ptr[3 ] =SDMA_PKT_WRITE_UNTILED_DW_3_COUNT (0 ); - ib.ptr[4 ] =0xDEADBEEF ; - ib.ptr[5 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.ptr[6 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.ptr[7 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.length_dw =8 ; - - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (r) + ib->ptr[1 ] =lower_32_bits (gpu_addr); + ib->ptr[2 ] =upper_32_bits (gpu_addr); + ib->ptr[3 ] =SDMA_PKT_WRITE_UNTILED_DW_3_COUNT (0 ); + ib->ptr[4 ] =0xDEADBEEF ; + ib->ptr[5 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->ptr[6 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->ptr[7 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->length_dw =8 ; + + r =amdgpu_job_submit_direct (job, ring, &f); +if (r) { +amdgpu_job_free (job); goto err1; + } r =dma_fence_wait_timeout (f, false, timeout);if (r ==0 ) {@@ -1565,7 +1570,6 @@ static int sdma_v4_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) r = -EINVAL ; err1: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f); err0:amdgpu_device_wb_free (adev, index);drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c +21
-17@@ -1112,7 +1112,8 @@ static int sdma_v4_4_2_ring_test_ring(struct amdgpu_ring *ring)static int sdma_v4_4_2_ring_test_ib (struct amdgpu_ring *ring,long timeout) {struct amdgpu_device *adev = ring->adev; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ;unsigned index;long r;@@ -1126,26 +1127,30 @@ static int sdma_v4_4_2_ring_test_ib(struct amdgpu_ring *ring, long timeout) gpu_addr = adev->wb.gpu_addr + (index *4 ); tmp =0xCAFEDEAD ; adev->wb.wb[index] =cpu_to_le32 (tmp); -memset (&ib,0 ,sizeof (ib)); - r =amdgpu_ib_get (adev,NULL ,256 , -AMDGPU_IB_POOL_DIRECT , &ib); + + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,256 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_SDMA_RING_TEST );if (r) goto err0; - ib.ptr[0 ] =SDMA_PKT_HEADER_OP (SDMA_OP_WRITE ) | + ib = &job->ibs[0 ]; + ib->ptr[0 ] =SDMA_PKT_HEADER_OP (SDMA_OP_WRITE ) |SDMA_PKT_HEADER_SUB_OP (SDMA_SUBOP_WRITE_LINEAR ); - ib.ptr[1 ] =lower_32_bits (gpu_addr); - ib.ptr[2 ] =upper_32_bits (gpu_addr); - ib.ptr[3 ] =SDMA_PKT_WRITE_UNTILED_DW_3_COUNT (0 ); - ib.ptr[4 ] =0xDEADBEEF ; - ib.ptr[5 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.ptr[6 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.ptr[7 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.length_dw =8 ; - - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (r) + ib->ptr[1 ] =lower_32_bits (gpu_addr); + ib->ptr[2 ] =upper_32_bits (gpu_addr); + ib->ptr[3 ] =SDMA_PKT_WRITE_UNTILED_DW_3_COUNT (0 ); + ib->ptr[4 ] =0xDEADBEEF ; + ib->ptr[5 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->ptr[6 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->ptr[7 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->length_dw =8 ; + + r =amdgpu_job_submit_direct (job, ring, &f); +if (r) { +amdgpu_job_free (job); goto err1; + } r =dma_fence_wait_timeout (f, false, timeout);if (r ==0 ) {@@ -1161,7 +1166,6 @@ static int sdma_v4_4_2_ring_test_ib(struct amdgpu_ring *ring, long timeout) r = -EINVAL ; err1: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f); err0:amdgpu_device_wb_free (adev, index);drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c +20
-17@@ -1074,7 +1074,8 @@ static int sdma_v5_0_ring_test_ring(struct amdgpu_ring *ring)static int sdma_v5_0_ring_test_ib (struct amdgpu_ring *ring,long timeout) {struct amdgpu_device *adev = ring->adev; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ;unsigned index;long r;@@ -1082,7 +1083,6 @@ static int sdma_v5_0_ring_test_ib(struct amdgpu_ring *ring, long timeout)u64 gpu_addr; tmp =0xCAFEDEAD ; -memset (&ib,0 ,sizeof (ib)); r =amdgpu_device_wb_get (adev, &index);if (r) {@@ -1093,27 +1093,31 @@ static int sdma_v5_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) gpu_addr = adev->wb.gpu_addr + (index *4 ); adev->wb.wb[index] =cpu_to_le32 (tmp); - r =amdgpu_ib_get (adev,NULL ,256 , -AMDGPU_IB_POOL_DIRECT , &ib); + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,256 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_SDMA_RING_TEST );if (r) {drm_err (adev_to_drm (adev),"failed to get ib (%ld).\n" , r); goto err0; } - ib.ptr[0 ] =SDMA_PKT_HEADER_OP (SDMA_OP_WRITE ) | + ib = &job->ibs[0 ]; + ib->ptr[0 ] =SDMA_PKT_HEADER_OP (SDMA_OP_WRITE ) |SDMA_PKT_HEADER_SUB_OP (SDMA_SUBOP_WRITE_LINEAR ); - ib.ptr[1 ] =lower_32_bits (gpu_addr); - ib.ptr[2 ] =upper_32_bits (gpu_addr); - ib.ptr[3 ] =SDMA_PKT_WRITE_UNTILED_DW_3_COUNT (0 ); - ib.ptr[4 ] =0xDEADBEEF ; - ib.ptr[5 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.ptr[6 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.ptr[7 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.length_dw =8 ; - - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (r) + ib->ptr[1 ] =lower_32_bits (gpu_addr); + ib->ptr[2 ] =upper_32_bits (gpu_addr); + ib->ptr[3 ] =SDMA_PKT_WRITE_UNTILED_DW_3_COUNT (0 ); + ib->ptr[4 ] =0xDEADBEEF ; + ib->ptr[5 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->ptr[6 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->ptr[7 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->length_dw =8 ; + + r =amdgpu_job_submit_direct (job, ring, &f); +if (r) { +amdgpu_job_free (job); goto err1; + } r =dma_fence_wait_timeout (f, false, timeout);if (r ==0 ) {@@ -1133,7 +1137,6 @@ static int sdma_v5_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) r = -EINVAL ; err1: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f); err0:amdgpu_device_wb_free (adev, index);drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c +20
-16@@ -974,7 +974,8 @@ static int sdma_v5_2_ring_test_ring(struct amdgpu_ring *ring)static int sdma_v5_2_ring_test_ib (struct amdgpu_ring *ring,long timeout) {struct amdgpu_device *adev = ring->adev; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ;unsigned index;long r;@@ -982,7 +983,6 @@ static int sdma_v5_2_ring_test_ib(struct amdgpu_ring *ring, long timeout)u64 gpu_addr; tmp =0xCAFEDEAD ; -memset (&ib,0 ,sizeof (ib)); r =amdgpu_device_wb_get (adev, &index);if (r) {@@ -993,26 +993,31 @@ static int sdma_v5_2_ring_test_ib(struct amdgpu_ring *ring, long timeout) gpu_addr = adev->wb.gpu_addr + (index *4 ); adev->wb.wb[index] =cpu_to_le32 (tmp); - r =amdgpu_ib_get (adev,NULL ,256 ,AMDGPU_IB_POOL_DIRECT , &ib); + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,256 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_SDMA_RING_TEST );if (r) {drm_err (adev_to_drm (adev),"failed to get ib (%ld).\n" , r); goto err0; } - ib.ptr[0 ] =SDMA_PKT_HEADER_OP (SDMA_OP_WRITE ) | + ib = &job->ibs[0 ]; + ib->ptr[0 ] =SDMA_PKT_HEADER_OP (SDMA_OP_WRITE ) |SDMA_PKT_HEADER_SUB_OP (SDMA_SUBOP_WRITE_LINEAR ); - ib.ptr[1 ] =lower_32_bits (gpu_addr); - ib.ptr[2 ] =upper_32_bits (gpu_addr); - ib.ptr[3 ] =SDMA_PKT_WRITE_UNTILED_DW_3_COUNT (0 ); - ib.ptr[4 ] =0xDEADBEEF ; - ib.ptr[5 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.ptr[6 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.ptr[7 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.length_dw =8 ; - - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (r) + ib->ptr[1 ] =lower_32_bits (gpu_addr); + ib->ptr[2 ] =upper_32_bits (gpu_addr); + ib->ptr[3 ] =SDMA_PKT_WRITE_UNTILED_DW_3_COUNT (0 ); + ib->ptr[4 ] =0xDEADBEEF ; + ib->ptr[5 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->ptr[6 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->ptr[7 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->length_dw =8 ; + + r =amdgpu_job_submit_direct (job, ring, &f); +if (r) { +amdgpu_job_free (job); goto err1; + } r =dma_fence_wait_timeout (f, false, timeout);if (r ==0 ) {@@ -1032,7 +1037,6 @@ static int sdma_v5_2_ring_test_ib(struct amdgpu_ring *ring, long timeout) r = -EINVAL ; err1: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f); err0:amdgpu_device_wb_free (adev, index);drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c +20
-16@@ -981,7 +981,8 @@ static int sdma_v6_0_ring_test_ring(struct amdgpu_ring *ring)static int sdma_v6_0_ring_test_ib (struct amdgpu_ring *ring,long timeout) {struct amdgpu_device *adev = ring->adev; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ;unsigned index;long r;@@ -989,7 +990,6 @@ static int sdma_v6_0_ring_test_ib(struct amdgpu_ring *ring, long timeout)u64 gpu_addr; tmp =0xCAFEDEAD ; -memset (&ib,0 ,sizeof (ib)); r =amdgpu_device_wb_get (adev, &index);if (r) {@@ -1000,26 +1000,31 @@ static int sdma_v6_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) gpu_addr = adev->wb.gpu_addr + (index *4 ); adev->wb.wb[index] =cpu_to_le32 (tmp); - r =amdgpu_ib_get (adev,NULL ,256 ,AMDGPU_IB_POOL_DIRECT , &ib); + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,256 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_SDMA_RING_TEST );if (r) {drm_err (adev_to_drm (adev),"failed to get ib (%ld).\n" , r); goto err0; } - ib.ptr[0 ] =SDMA_PKT_COPY_LINEAR_HEADER_OP (SDMA_OP_WRITE ) | + ib = &job->ibs[0 ]; + ib->ptr[0 ] =SDMA_PKT_COPY_LINEAR_HEADER_OP (SDMA_OP_WRITE ) |SDMA_PKT_COPY_LINEAR_HEADER_SUB_OP (SDMA_SUBOP_WRITE_LINEAR ); - ib.ptr[1 ] =lower_32_bits (gpu_addr); - ib.ptr[2 ] =upper_32_bits (gpu_addr); - ib.ptr[3 ] =SDMA_PKT_WRITE_UNTILED_DW_3_COUNT (0 ); - ib.ptr[4 ] =0xDEADBEEF ; - ib.ptr[5 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.ptr[6 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.ptr[7 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.length_dw =8 ; - - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (r) + ib->ptr[1 ] =lower_32_bits (gpu_addr); + ib->ptr[2 ] =upper_32_bits (gpu_addr); + ib->ptr[3 ] =SDMA_PKT_WRITE_UNTILED_DW_3_COUNT (0 ); + ib->ptr[4 ] =0xDEADBEEF ; + ib->ptr[5 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->ptr[6 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->ptr[7 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->length_dw =8 ; + + r =amdgpu_job_submit_direct (job, ring, &f); +if (r) { +amdgpu_job_free (job); goto err1; + } r =dma_fence_wait_timeout (f, false, timeout);if (r ==0 ) {@@ -1039,7 +1044,6 @@ static int sdma_v6_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) r = -EINVAL ; err1: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f); err0:amdgpu_device_wb_free (adev, index);drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c +20
-16@@ -997,7 +997,8 @@ static int sdma_v7_0_ring_test_ring(struct amdgpu_ring *ring)static int sdma_v7_0_ring_test_ib (struct amdgpu_ring *ring,long timeout) {struct amdgpu_device *adev = ring->adev; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ;unsigned index;long r;@@ -1005,7 +1006,6 @@ static int sdma_v7_0_ring_test_ib(struct amdgpu_ring *ring, long timeout)u64 gpu_addr; tmp =0xCAFEDEAD ; -memset (&ib,0 ,sizeof (ib)); r =amdgpu_device_wb_get (adev, &index);if (r) {@@ -1016,26 +1016,31 @@ static int sdma_v7_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) gpu_addr = adev->wb.gpu_addr + (index *4 ); adev->wb.wb[index] =cpu_to_le32 (tmp); - r =amdgpu_ib_get (adev,NULL ,256 ,AMDGPU_IB_POOL_DIRECT , &ib); + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,256 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_SDMA_RING_TEST );if (r) {drm_err (adev_to_drm (adev),"failed to get ib (%ld).\n" , r); goto err0; } - ib.ptr[0 ] =SDMA_PKT_COPY_LINEAR_HEADER_OP (SDMA_OP_WRITE ) | + ib = &job->ibs[0 ]; + ib->ptr[0 ] =SDMA_PKT_COPY_LINEAR_HEADER_OP (SDMA_OP_WRITE ) |SDMA_PKT_COPY_LINEAR_HEADER_SUB_OP (SDMA_SUBOP_WRITE_LINEAR ); - ib.ptr[1 ] =lower_32_bits (gpu_addr); - ib.ptr[2 ] =upper_32_bits (gpu_addr); - ib.ptr[3 ] =SDMA_PKT_WRITE_UNTILED_DW_3_COUNT (0 ); - ib.ptr[4 ] =0xDEADBEEF ; - ib.ptr[5 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.ptr[6 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.ptr[7 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.length_dw =8 ; - - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (r) + ib->ptr[1 ] =lower_32_bits (gpu_addr); + ib->ptr[2 ] =upper_32_bits (gpu_addr); + ib->ptr[3 ] =SDMA_PKT_WRITE_UNTILED_DW_3_COUNT (0 ); + ib->ptr[4 ] =0xDEADBEEF ; + ib->ptr[5 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->ptr[6 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->ptr[7 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->length_dw =8 ; + + r =amdgpu_job_submit_direct (job, ring, &f); +if (r) { +amdgpu_job_free (job); goto err1; + } r =dma_fence_wait_timeout (f, false, timeout);if (r ==0 ) {@@ -1055,7 +1060,6 @@ static int sdma_v7_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) r = -EINVAL ; err1: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f); err0:amdgpu_device_wb_free (adev, index);drivers/gpu/drm/amd/amdgpu/sdma_v7_1.c +20
-16@@ -987,7 +987,8 @@ static int sdma_v7_1_ring_test_ring(struct amdgpu_ring *ring)static int sdma_v7_1_ring_test_ib (struct amdgpu_ring *ring,long timeout) {struct amdgpu_device *adev = ring->adev; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ;unsigned index;long r;@@ -995,7 +996,6 @@ static int sdma_v7_1_ring_test_ib(struct amdgpu_ring *ring, long timeout)u64 gpu_addr; tmp =0xCAFEDEAD ; -memset (&ib,0 ,sizeof (ib)); r =amdgpu_device_wb_get (adev, &index);if (r) {@@ -1006,26 +1006,31 @@ static int sdma_v7_1_ring_test_ib(struct amdgpu_ring *ring, long timeout) gpu_addr = adev->wb.gpu_addr + (index *4 ); adev->wb.wb[index] =cpu_to_le32 (tmp); - r =amdgpu_ib_get (adev,NULL ,256 ,AMDGPU_IB_POOL_DIRECT , &ib); + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,256 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_SDMA_RING_TEST );if (r) {DRM_ERROR ("amdgpu: failed to get ib (%ld).\n" , r); goto err0; } - ib.ptr[0 ] =SDMA_PKT_COPY_LINEAR_HEADER_OP (SDMA_OP_WRITE ) | + ib = &job->ibs[0 ]; + ib->ptr[0 ] =SDMA_PKT_COPY_LINEAR_HEADER_OP (SDMA_OP_WRITE ) |SDMA_PKT_COPY_LINEAR_HEADER_SUB_OP (SDMA_SUBOP_WRITE_LINEAR ); - ib.ptr[1 ] =lower_32_bits (gpu_addr); - ib.ptr[2 ] =upper_32_bits (gpu_addr); - ib.ptr[3 ] =SDMA_PKT_WRITE_UNTILED_DW_3_COUNT (0 ); - ib.ptr[4 ] =0xDEADBEEF ; - ib.ptr[5 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.ptr[6 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.ptr[7 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); - ib.length_dw =8 ; - - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (r) + ib->ptr[1 ] =lower_32_bits (gpu_addr); + ib->ptr[2 ] =upper_32_bits (gpu_addr); + ib->ptr[3 ] =SDMA_PKT_WRITE_UNTILED_DW_3_COUNT (0 ); + ib->ptr[4 ] =0xDEADBEEF ; + ib->ptr[5 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->ptr[6 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->ptr[7 ] =SDMA_PKT_NOP_HEADER_OP (SDMA_OP_NOP ); + ib->length_dw =8 ; + + r =amdgpu_job_submit_direct (job, ring, &f); +if (r) { +amdgpu_job_free (job); goto err1; + } r =dma_fence_wait_timeout (f, false, timeout);if (r ==0 ) {@@ -1045,7 +1050,6 @@ static int sdma_v7_1_ring_test_ib(struct amdgpu_ring *ring, long timeout) r = -EINVAL ; err1: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f); err0:amdgpu_device_wb_free (adev, index);drivers/gpu/drm/amd/amdgpu/si_dma.c +17
-12@@ -259,7 +259,8 @@ static int si_dma_ring_test_ring(struct amdgpu_ring *ring)static int si_dma_ring_test_ib (struct amdgpu_ring *ring,long timeout) {struct amdgpu_device *adev = ring->adev; -struct amdgpu_ib ib; +struct amdgpu_job *job; +struct amdgpu_ib *ib;struct dma_fence *f =NULL ;unsigned index;u32 tmp =0 ;@@ -273,20 +274,25 @@ static int si_dma_ring_test_ib(struct amdgpu_ring *ring, long timeout) gpu_addr = adev->wb.gpu_addr + (index *4 ); tmp =0xCAFEDEAD ; adev->wb.wb[index] =cpu_to_le32 (tmp); -memset (&ib,0 ,sizeof (ib)); - r =amdgpu_ib_get (adev,NULL ,256 , -AMDGPU_IB_POOL_DIRECT , &ib); + + r =amdgpu_job_alloc_with_ib (ring->adev,NULL ,NULL ,256 , +AMDGPU_IB_POOL_DIRECT , &job, +AMDGPU_KERNEL_JOB_ID_SDMA_RING_TEST );if (r) goto err0; - ib.ptr[0 ] =DMA_PACKET (DMA_PACKET_WRITE ,0 ,0 ,0 ,1 ); - ib.ptr[1 ] =lower_32_bits (gpu_addr); - ib.ptr[2 ] =upper_32_bits (gpu_addr) &0xff ; - ib.ptr[3 ] =0xDEADBEEF ; - ib.length_dw =4 ; - r =amdgpu_ib_schedule (ring,1 , &ib,NULL , &f); -if (r) + ib = &job->ibs[0 ]; + ib->ptr[0 ] =DMA_PACKET (DMA_PACKET_WRITE ,0 ,0 ,0 ,1 ); + ib->ptr[1 ] =lower_32_bits (gpu_addr); + ib->ptr[2 ] =upper_32_bits (gpu_addr) &0xff ; + ib->ptr[3 ] =0xDEADBEEF ; + ib->length_dw =4 ; + + r =amdgpu_job_submit_direct (job, ring, &f); +if (r) { +amdgpu_job_free (job); goto err1; + } r =dma_fence_wait_timeout (f, false, timeout);if (r ==0 ) {@@ -302,7 +308,6 @@ static int si_dma_ring_test_ib(struct amdgpu_ring *ring, long timeout) r = -EINVAL ; err1: -amdgpu_ib_free (&ib,NULL );dma_fence_put (f); err0:amdgpu_device_wb_free (adev, index);
Alex Deucher
maintainerPATCH 4/12 drm/amdgpu: require a job to schedule an IB
In reply to Alex DeucherRemove the old direct submit path. This simplifies the code.
v2: remove more local variables
--- drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c | 2 +- drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c | 111 ++++++++------------- drivers/gpu/drm/amd/amdgpu/amdgpu_job.c | 5 +- drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h | 3 +- 4 files changed, 44 insertions(+), 77 deletions(-)
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c +1 -1
@@ -686,7 +686,7 @@ int amdgpu_amdkfd_submit_ib(struct amdgpu_device *adev, job->vmid = vmid; job->num_ibs =1 ; - ret =amdgpu_ib_schedule (ring,1 , ib, job, &f); + ret =amdgpu_ib_schedule (ring, job, &f);if (ret) {drm_err (adev_to_drm (adev),"failed to schedule IB.\n" );
drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c +40 -71
221 lines not on this page · raw message
drivers/gpu/drm/amd/amdgpu/amdgpu_job.c +2 -3
@@ -379,7 +379,7 @@ int amdgpu_job_submit_direct(struct amdgpu_job *job, struct amdgpu_ring *ring,int r; job->base.sched = &ring->sched; - r =amdgpu_ib_schedule (ring, job->num_ibs, job->ibs, job, fence); + r =amdgpu_ib_schedule (ring, job, fence);if (r)return r;
@@ -449,8 +449,7 @@ static struct dma_fence *amdgpu_job_run(struct drm_sched_job *sched_job)dev_dbg (adev->dev,"Skip scheduling IBs in ring(%s)" , ring->name); }else { - r =amdgpu_ib_schedule (ring, job->num_ibs, job->ibs, job, - &fence); + r =amdgpu_ib_schedule (ring, job, &fence);if (r) dev_err(adev->dev, "Error scheduling IBs (%d) in ring(%s)", r,
drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h +1 -2
@@ -569,8 +569,7 @@ int amdgpu_ib_get(struct amdgpu_device *adev, struct amdgpu_vm *vm,enum amdgpu_ib_pool_type pool, struct amdgpu_ib *ib);void amdgpu_ib_free (struct amdgpu_ib *ib,struct dma_fence *f); -int amdgpu_ib_schedule (struct amdgpu_ring *ring,unsigned num_ibs, -struct amdgpu_ib *ibs,struct amdgpu_job *job, +int amdgpu_ib_schedule (struct amdgpu_ring *ring,struct amdgpu_job *job,struct dma_fence **f);int amdgpu_ib_pool_init (struct amdgpu_device *adev);void amdgpu_ib_pool_fini (struct amdgpu_device *adev);
Signature · 1 line
2.52.0
Alex Deucher
maintainerPATCH 5/12 drm/amdgpu: don't call drm_sched_stop/start() in asic reset
In reply to Alex DeucherWe only want to stop the work queues, not mess with the fences, etc.
v2: add the job back to the pending list.
v3: return the proper job status so scheduler adds the
job back to the pending list
--- drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 4 ++-- drivers/gpu/drm/amd/amdgpu/amdgpu_job.c | 6 ++---- 2 files changed, 4 insertions(+), 6 deletions(-)
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +2 -2
@@ -6313,7 +6313,7 @@ static void amdgpu_device_halt_activities(struct amdgpu_device *adev,if (!amdgpu_ring_sched_ready (ring))continue ; -drm_sched_stop (&ring->sched, job ? &job->base :NULL ); +drm_sched_wqueue_stop (&ring->sched);if (need_emergency_restart)amdgpu_job_stop_all_jobs_on_sched (&ring->sched);
@@ -6397,7 +6397,7 @@ static int amdgpu_device_sched_resume(struct list_head *device_list,if (!amdgpu_ring_sched_ready (ring))continue ; -drm_sched_start (&ring->sched,0 ); +drm_sched_wqueue_start (&ring->sched); }if (!drm_drv_uses_atomic_modeset (adev_to_drm (tmp_adev)) && !job_signaled)
drivers/gpu/drm/amd/amdgpu/amdgpu_job.c +2 -4
@@ -92,7 +92,6 @@ static enum drm_gpu_sched_stat amdgpu_job_timedout(struct drm_sched_job *s_job)struct drm_wedge_task_info *info =NULL ;struct amdgpu_task_info *ti =NULL ;struct amdgpu_device *adev = ring->adev; -enum drm_gpu_sched_stat status =DRM_GPU_SCHED_STAT_RESET ;int idx, r;if (!drm_dev_enter (adev_to_drm (adev), &idx)) {
@@ -147,8 +146,6 @@ static enum drm_gpu_sched_stat amdgpu_job_timedout(struct drm_sched_job *s_job) ring->sched.name);drm_dev_wedged_event (adev_to_drm (adev),DRM_WEDGE_RECOVERY_NONE , info); -/* This is needed to add the job back to the pending list */ - status =DRM_GPU_SCHED_STAT_NO_HANG ; goto exit; }dev_err (adev->dev,"Ring %s reset failed\n" , ring->sched.name);
@@ -184,7 +181,8 @@ static enum drm_gpu_sched_stat amdgpu_job_timedout(struct drm_sched_job *s_job) exit:amdgpu_vm_put_task_info (ti);drm_dev_exit (idx); -return status; +/* This is needed to add the job back to the pending list */ +return DRM_GPU_SCHED_STAT_NO_HANG ; } int amdgpu_job_alloc(struct amdgpu_device *adev, struct amdgpu_vm *vm,
Signature · 1 line
2.52.0
Re: [PATCH 05/12] drm/amdgpu: don't call drm_sched_stop/start() in asic reset
Le 30/01/2026 à 18:30, Alex Deucher a écrit :
Quoted 57 lines
We only want to stop the work queues, not mess with the fences, etc.
v2: add the job back to the pending list.
v3: return the proper job status so scheduler adds the
job back to the pending listSigned-off-by Alex Deucher <[email protected]>--- drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 4 ++-- drivers/gpu/drm/amd/amdgpu/amdgpu_job.c | 6 ++---- 2 files changed, 4 insertions(+), 6 deletions(-)drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +2
-2@@ -6313,7 +6313,7 @@ static void amdgpu_device_halt_activities(struct amdgpu_device *adev,if (!amdgpu_ring_sched_ready (ring))continue ; -drm_sched_stop (&ring->sched, job ? &job->base :NULL ); +drm_sched_wqueue_stop (&ring->sched);if (need_emergency_restart)amdgpu_job_stop_all_jobs_on_sched (&ring->sched);@@ -6397,7 +6397,7 @@ static int amdgpu_device_sched_resume(struct list_head *device_list,if (!amdgpu_ring_sched_ready (ring))continue ; -drm_sched_start (&ring->sched,0 ); +drm_sched_wqueue_start (&ring->sched); }if (!drm_drv_uses_atomic_modeset (adev_to_drm (tmp_adev)) && !job_signaled)drivers/gpu/drm/amd/amdgpu/amdgpu_job.c +0
-3@@ -92,7 +92,6 @@ static enum drm_gpu_sched_stat amdgpu_job_timedout(struct drm_sched_job *s_job)struct drm_wedge_task_info *info =NULL ;struct amdgpu_task_info *ti =NULL ;struct amdgpu_device *adev = ring->adev; -enum drm_gpu_sched_stat status =DRM_GPU_SCHED_STAT_RESET ;int idx, r;if (!drm_dev_enter (adev_to_drm (adev), &idx)) {@@ -147,8 +146,6 @@ static enum drm_gpu_sched_stat amdgpu_job_timedout(struct drm_sched_job *s_job) ring->sched.name);drm_dev_wedged_event (adev_to_drm (adev),DRM_WEDGE_RECOVERY_NONE , info); -/* This is needed to add the job back to the pending list */ - status =DRM_GPU_SCHED_STAT_NO_HANG ; goto exit; }dev_err (adev->dev,"Ring %s reset failed\n" , ring->sched.name);
drivers/gpu/drm/amd/amdgpu/amdgpu_job.c static enum drm_gpu_sched_stat amdgpu_job_timedout(struct drm_sched_job *s_job) · line 185
Quoted 6 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_job.c +2
-1@@ -184,7 +181,8 @@ static enum drm_gpu_sched_stat amdgpu_job_timedout(struct drm_sched_job *s_job) exit:amdgpu_vm_put_task_info (ti);drm_dev_exit (idx); -return status; +/* This is needed to add the job back to the pending list */ +return DRM_GPU_SCHED_STAT_NO_HANG ;
This part seems unrelated to the patch and is overwriting what was done in patch 1/12.
Pierre-Eric
Quoted 3 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_job.c +0
-0} int amdgpu_job_alloc(struct amdgpu_device *adev, struct amdgpu_vm *vm,
Re: [PATCH 05/12] drm/amdgpu: don't call drm_sched_stop/start() in asic reset
Quoted 62 lines · Pierre-Eric Pelloux-Prayer
Quoted 58 lines · Alex Deucher
We only want to stop the work queues, not mess with the fences, etc.
v2: add the job back to the pending list.
v3: return the proper job status so scheduler adds the
job back to the pending listSigned-off-by Alex Deucher <[email protected]>--- drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 4 ++-- drivers/gpu/drm/amd/amdgpu/amdgpu_job.c | 6 ++---- 2 files changed, 4 insertions(+), 6 deletions(-)drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +2
-2@@ -6313,7 +6313,7 @@ static void amdgpu_device_halt_activities(struct amdgpu_device *adev,if (!amdgpu_ring_sched_ready (ring))continue ; -drm_sched_stop (&ring->sched, job ? &job->base :NULL ); +drm_sched_wqueue_stop (&ring->sched);if (need_emergency_restart)amdgpu_job_stop_all_jobs_on_sched (&ring->sched);@@ -6397,7 +6397,7 @@ static int amdgpu_device_sched_resume(struct list_head *device_list,if (!amdgpu_ring_sched_ready (ring))continue ; -drm_sched_start (&ring->sched,0 ); +drm_sched_wqueue_start (&ring->sched); }if (!drm_drv_uses_atomic_modeset (adev_to_drm (tmp_adev)) && !job_signaled)drivers/gpu/drm/amd/amdgpu/amdgpu_job.c +0
-3@@ -92,7 +92,6 @@ static enum drm_gpu_sched_stat amdgpu_job_timedout(struct drm_sched_job *s_job)struct drm_wedge_task_info *info =NULL ;struct amdgpu_task_info *ti =NULL ;struct amdgpu_device *adev = ring->adev; -enum drm_gpu_sched_stat status =DRM_GPU_SCHED_STAT_RESET ;int idx, r;if (!drm_dev_enter (adev_to_drm (adev), &idx)) {@@ -147,8 +146,6 @@ static enum drm_gpu_sched_stat amdgpu_job_timedout(struct drm_sched_job *s_job) ring->sched.name);drm_dev_wedged_event (adev_to_drm (adev),DRM_WEDGE_RECOVERY_NONE , info); -/* This is needed to add the job back to the pending list */ - status =DRM_GPU_SCHED_STAT_NO_HANG ; goto exit; }dev_err (adev->dev,"Ring %s reset failed\n" , ring->sched.name);@@ -184,7 +181,8 @@ static enum drm_gpu_sched_stat amdgpu_job_timedout(struct drm_sched_job *s_job) exit:
Quoted 8 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_job.c static enum drm_gpu_sched_stat amdgpu_job_timedout(struct drm_sched_job *s_job) · line 185
Quoted 5 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_job.c +2
-1amdgpu_vm_put_task_info (ti);drm_dev_exit (idx); -return status; +/* This is needed to add the job back to the pending list */ +return DRM_GPU_SCHED_STAT_NO_HANG ;This part seems unrelated to the patch and is overwriting what was done in patch 1/12.
Patch 1 fixes the pending list handling for per queue resets. This patch reworks the adapter reset path to match the behavior of the per queue reset path. After this patch they match so we can safely return DRM_GPU_SCHED_STAT_NO_HANG in both cases. Previously the adapter reset path called drm_sched_wqueue_stop()/start() which handles re-adding the job to the pending list. Since it no longer does, we need to return DRM_GPU_SCHED_STAT_NO_HANG for both cases.
Alex
Quoted 7 lines
Pierre-Eric
Quoted 3 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_job.c +0
-0} int amdgpu_job_alloc(struct amdgpu_device *adev, struct amdgpu_vm *vm,
Pierre-Eric Pelloux-Prayer
Acked-byRe: [PATCH 05/12] drm/amdgpu: don't call drm_sched_stop/start() in asic reset
Le 05/02/2026 à 15:26, Alex Deucher a écrit :
Quoted 73 lines
Quoted 62 lines · Pierre-Eric Pelloux-Prayer
Quoted 58 lines · Alex Deucher
We only want to stop the work queues, not mess with the fences, etc.
v2: add the job back to the pending list.
v3: return the proper job status so scheduler adds the
job back to the pending listSigned-off-by Alex Deucher <[email protected]>--- drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 4 ++-- drivers/gpu/drm/amd/amdgpu/amdgpu_job.c | 6 ++---- 2 files changed, 4 insertions(+), 6 deletions(-)drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +2
-2@@ -6313,7 +6313,7 @@ static void amdgpu_device_halt_activities(struct amdgpu_device *adev,if (!amdgpu_ring_sched_ready (ring))continue ; -drm_sched_stop (&ring->sched, job ? &job->base :NULL ); +drm_sched_wqueue_stop (&ring->sched);if (need_emergency_restart)amdgpu_job_stop_all_jobs_on_sched (&ring->sched);@@ -6397,7 +6397,7 @@ static int amdgpu_device_sched_resume(struct list_head *device_list,if (!amdgpu_ring_sched_ready (ring))continue ; -drm_sched_start (&ring->sched,0 ); +drm_sched_wqueue_start (&ring->sched); }if (!drm_drv_uses_atomic_modeset (adev_to_drm (tmp_adev)) && !job_signaled)drivers/gpu/drm/amd/amdgpu/amdgpu_job.c +0
-3@@ -92,7 +92,6 @@ static enum drm_gpu_sched_stat amdgpu_job_timedout(struct drm_sched_job *s_job)struct drm_wedge_task_info *info =NULL ;struct amdgpu_task_info *ti =NULL ;struct amdgpu_device *adev = ring->adev; -enum drm_gpu_sched_stat status =DRM_GPU_SCHED_STAT_RESET ;int idx, r;if (!drm_dev_enter (adev_to_drm (adev), &idx)) {@@ -147,8 +146,6 @@ static enum drm_gpu_sched_stat amdgpu_job_timedout(struct drm_sched_job *s_job) ring->sched.name);drm_dev_wedged_event (adev_to_drm (adev),DRM_WEDGE_RECOVERY_NONE , info); -/* This is needed to add the job back to the pending list */ - status =DRM_GPU_SCHED_STAT_NO_HANG ; goto exit; }dev_err (adev->dev,"Ring %s reset failed\n" , ring->sched.name);@@ -184,7 +181,8 @@ static enum drm_gpu_sched_stat amdgpu_job_timedout(struct drm_sched_job *s_job) exit:Quoted 8 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_job.c static enum drm_gpu_sched_stat amdgpu_job_timedout(struct drm_sched_job *s_job) · line 185
Quoted 5 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_job.c +2
-1amdgpu_vm_put_task_info (ti);drm_dev_exit (idx); -return status; +/* This is needed to add the job back to the pending list */ +return DRM_GPU_SCHED_STAT_NO_HANG ;This part seems unrelated to the patch and is overwriting what was done in patch 1/12.
Quoted 7 lines
Patch 1 fixes the pending list handling for per queue resets. This patch reworks the adapter reset path to match the behavior of the per queue reset path. After this patch they match so we can safely return
DRM_GPU_SCHED_STAT_NO_HANGin both cases. Previously the adapter reset path called drm_sched_wqueue_stop()/start() which handles re-adding the job to the pending list. Since it no longer does, we need to returnDRM_GPU_SCHED_STAT_NO_HANGfor both cases.
I looked a bit more in the patchset adding DRM_GPU_SCHED_STAT_NO_HANG and your changes make sense. This patch is:
Alex Deucher
maintainerPATCH 6/12 drm/amdgpu/cs: return -ETIME for guilty contexts
In reply to Alex DeucherReturn -ETIME rather than -ECANCELED for guilty contexts. Userspace only considers contexts to be guilty if they return -ETIME. Returning -ECANCELED means the context was innocent.
--- drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c +1 -1
@@ -62,7 +62,7 @@ static int amdgpu_cs_parser_init(struct amdgpu_cs_parser *p,if (atomic_read (&p->ctx->guilty)) {amdgpu_ctx_put (p->ctx); -return -ECANCELED ; +return -ETIME ; }amdgpu_sync_create (&p->sync);
Signature · 1 line
2.52.0
Alex Deucher
maintainerPATCH 7/12 drm/amdgpu: plumb timedout fence through to force completion
In reply to Alex DeucherWhen we do a full adapter reset, if we know the timedout fence mark the fence with -ETIME rather than -ECANCELED so it gets properly handled by userspace.
v2: rebase
--- drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c | 2 +- drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 6 ++++- drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c | 28 +++++++++++++++++---- drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h | 3 ++- drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c | 4 +-- drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c | 2 +- drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c | 21 ++++++++++------ drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c | 2 +- drivers/gpu/drm/amd/amdgpu/vcn_v5_0_1.c | 2 +- 9 files changed, 49 insertions(+), 21 deletions(-)
drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c +1 -1
@@ -1936,7 +1936,7 @@ static int amdgpu_debugfs_ib_preempt(void *data, u64 val)/* swap out the old fences */ amdgpu_ib_preempt_fences_swap (ring, fences); -amdgpu_fence_driver_force_completion (ring); +amdgpu_fence_driver_force_completion (ring,NULL );/* resubmit unfinished jobs */ amdgpu_ib_preempt_job_recovery (&ring->sched);
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +5 -1
@@ -5795,6 +5795,7 @@ int amdgpu_device_pre_asic_reset(struct amdgpu_device *adev, {int i, r =0 ;struct amdgpu_job *job =NULL ; +struct dma_fence *fence =NULL ;struct amdgpu_device *tmp_adev = reset_context->reset_req_dev;bool need_full_reset =test_bit (AMDGPU_NEED_FULL_RESET , &reset_context->flags);
@@ -5807,6 +5808,9 @@ int amdgpu_device_pre_asic_reset(struct amdgpu_device *adev,amdgpu_fence_driver_isr_toggle (adev, true); +if (job) + fence = &job->hw_fence->base; +/* block all schedulers and reset given job's ring */ for (i =0 ; i <AMDGPU_MAX_RINGS ; ++i) {struct amdgpu_ring *ring = adev->rings[i];
@@ -5815,7 +5819,7 @@ int amdgpu_device_pre_asic_reset(struct amdgpu_device *adev,continue ;/* after all hw jobs are reset, hw fence is meaningless, so force_completion */ -amdgpu_fence_driver_force_completion (ring); +amdgpu_fence_driver_force_completion (ring, fence); }amdgpu_fence_driver_isr_toggle (adev, false);
drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c +23 -5
@@ -567,7 +567,7 @@ void amdgpu_fence_driver_hw_fini(struct amdgpu_device *adev) r = -ENODEV ;/* no need to trigger GPU reset as we are unloading */ if (r) -amdgpu_fence_driver_force_completion (ring); +amdgpu_fence_driver_force_completion (ring,NULL ); if (!drm_dev_is_unplugged(adev_to_drm(adev)) && ring->fence_drv.irq_src &&
@@ -682,16 +682,34 @@ void amdgpu_fence_driver_set_error(struct amdgpu_ring *ring, int error)* amdgpu_fence_driver_force_completion - force signal latest fence of ring * * @ring: fence of the ring to signal +* @timedout_fence: fence of the timedout job * */ -void amdgpu_fence_driver_force_completion (struct amdgpu_ring *ring) +void amdgpu_fence_driver_force_completion (struct amdgpu_ring *ring, +struct dma_fence *timedout_fence) { -amdgpu_fence_driver_set_error (ring, -ECANCELED ); +struct amdgpu_fence_driver *drv = &ring->fence_drv; +unsigned long flags; + +spin_lock_irqsave (&drv->lock, flags); +for (unsigned int i =0 ; i <= drv->num_fences_mask; ++i) { +struct dma_fence *fence; + + fence =rcu_dereference_protected (drv->fences[i], +lockdep_is_held (&drv->lock)); +if (fence && !dma_fence_is_signaled_locked (fence)) { +if (fence == timedout_fence) +dma_fence_set_error (fence, -ETIME ); +else +dma_fence_set_error (fence, -ECANCELED ); + } + } +spin_unlock_irqrestore (&drv->lock, flags); +amdgpu_fence_write (ring, ring->fence_drv.sync_seq);amdgpu_fence_process (ring); } -/* * Kernel queue reset handling *
@@ -752,7 +770,7 @@ void amdgpu_fence_driver_update_timedout_fence_state(struct amdgpu_fence *af)if (reemitted) {/* if we've already reemitted once then just cancel everything */ -amdgpu_fence_driver_force_completion (af->ring); +amdgpu_fence_driver_force_completion (af->ring, &af->base); af->ring->ring_backup_entries_to_copy =0 ; } }
drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h +2 -1
@@ -160,7 +160,8 @@ struct amdgpu_fence {extern const struct drm_sched_backend_ops amdgpu_sched_ops;void amdgpu_fence_driver_set_error (struct amdgpu_ring *ring,int error); -void amdgpu_fence_driver_force_completion (struct amdgpu_ring *ring); +void amdgpu_fence_driver_force_completion (struct amdgpu_ring *ring, +struct dma_fence *timedout_fence);void amdgpu_fence_driver_update_timedout_fence_state (struct amdgpu_fence *af);void amdgpu_fence_save_wptr (struct amdgpu_fence *af);
drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c +2 -2
@@ -597,10 +597,10 @@ int amdgpu_sdma_reset_engine(struct amdgpu_device *adev, uint32_t instance_id,* to be submitted to the queues after the reset is complete. */ if (!ret) { -amdgpu_fence_driver_force_completion (gfx_ring); +amdgpu_fence_driver_force_completion (gfx_ring,NULL );drm_sched_wqueue_start (&gfx_ring->sched);if (adev->sdma.has_page_queue) { -amdgpu_fence_driver_force_completion (page_ring); +amdgpu_fence_driver_force_completion (page_ring,NULL );drm_sched_wqueue_start (&page_ring->sched); } }
drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c +1 -1
@@ -512,7 +512,7 @@ int amdgpu_uvd_resume(struct amdgpu_device *adev) }memset_io (ptr,0 , size);/* to restore uvd fence seq */ -amdgpu_fence_driver_force_completion (&adev->uvd.inst[i].ring); +amdgpu_fence_driver_force_completion (&adev->uvd.inst[i].ring,NULL ); } }return 0 ;
drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c +13 -8
@@ -1482,15 +1482,16 @@ int vcn_set_powergating_state(struct amdgpu_ip_block *ip_block,/** * amdgpu_vcn_reset_engine - Reset a specific VCN engine -* @adev: Pointer to the AMDGPU device -* @instance_id: VCN engine instance to reset +* @ring: Pointer to the VCN ring +* @timedout_fence: fence that timed out * * Returns: 0 on success, or a negative error code on failure. */ -static int amdgpu_vcn_reset_engine (struct amdgpu_device *adev, -uint32_t instance_id) +static int amdgpu_vcn_reset_engine (struct amdgpu_ring *ring, +struct amdgpu_fence *timedout_fence) { -struct amdgpu_vcn_inst *vinst = &adev->vcn.inst[instance_id]; +struct amdgpu_device *adev = ring->adev; +struct amdgpu_vcn_inst *vinst = &adev->vcn.inst[ring->me];int r, i;mutex_lock (&vinst->engine_reset_mutex);
@@ -1514,9 +1515,13 @@ static int amdgpu_vcn_reset_engine(struct amdgpu_device *adev,if (r) goto unlock; } -amdgpu_fence_driver_force_completion (&vinst->ring_dec); +amdgpu_fence_driver_force_completion (&vinst->ring_dec, + (&vinst->ring_dec == ring) ? + &timedout_fence->base :NULL );for (i =0 ; i < vinst->num_enc_rings; i++) -amdgpu_fence_driver_force_completion (&vinst->ring_enc[i]); +amdgpu_fence_driver_force_completion (&vinst->ring_enc[i], + (&vinst->ring_enc[i] == ring) ? + &timedout_fence->base :NULL );/* Restart the scheduler's work queue for the dec and enc rings * if they were stopped by this function. This allows new tasks
@@ -1552,7 +1557,7 @@ int amdgpu_vcn_ring_reset(struct amdgpu_ring *ring,if (adev->vcn.inst[ring->me].using_unified_queue)return -EINVAL ; -return amdgpu_vcn_reset_engine (adev, ring->me); +return amdgpu_vcn_reset_engine (ring, timedout_fence); } int amdgpu_vcn_reg_dump_init(struct amdgpu_device *adev,
drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c +1 -1
@@ -1669,7 +1669,7 @@ static int vcn_v4_0_3_reset_jpeg_post_helper(struct amdgpu_device *adev, int insfor (i =0 ; i < adev->jpeg.num_jpeg_rings; ++i) { ring = &adev->jpeg.inst[inst].ring_dec[i];/* Force completion of any remaining jobs */ -amdgpu_fence_driver_force_completion (ring); +amdgpu_fence_driver_force_completion (ring,NULL );if (ring->use_doorbell) WREG32_SOC15_OFFSET(
drivers/gpu/drm/amd/amdgpu/vcn_v5_0_1.c +1 -1
@@ -1332,7 +1332,7 @@ static int vcn_v5_0_1_reset_jpeg_post_helper(struct amdgpu_device *adev, int insfor (i =0 ; i < adev->jpeg.num_jpeg_rings; ++i) { ring = &adev->jpeg.inst[inst].ring_dec[i];/* Force completion of any remaining jobs */ -amdgpu_fence_driver_force_completion (ring); +amdgpu_fence_driver_force_completion (ring,NULL );if (ring->use_doorbell) WREG32_SOC15_OFFSET(
Signature · 1 line
2.52.0
Alex Deucher
maintainerPATCH 8/12 drm/amdgpu: simplify VCN reset helper
In reply to Alex DeucherRemove the wrapper function.
--- drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c | 41 ++++++++----------------- 1 file changed, 13 insertions(+), 28 deletions(-)
drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c +13 -28
@@ -1481,19 +1481,27 @@ int vcn_set_powergating_state(struct amdgpu_ip_block *ip_block, }/** -* amdgpu_vcn_reset_engine - Reset a specific VCN engine -* @ring: Pointer to the VCN ring -* @timedout_fence: fence that timed out +* amdgpu_vcn_ring_reset - Reset a VCN ring +* @ring: ring to reset +* @vmid: vmid of guilty job +* @timedout_fence: fence of timed out job * +* This helper is for VCN blocks without unified queues because +* resetting the engine resets all queues in that case. With +* unified queues we have one queue per engine. * Returns: 0 on success, or a negative error code on failure. */ -static int amdgpu_vcn_reset_engine (struct amdgpu_ring *ring, -struct amdgpu_fence *timedout_fence) +int amdgpu_vcn_ring_reset (struct amdgpu_ring *ring, +unsigned int vmid, +struct amdgpu_fence *timedout_fence) {struct amdgpu_device *adev = ring->adev;struct amdgpu_vcn_inst *vinst = &adev->vcn.inst[ring->me];int r, i; +if (adev->vcn.inst[ring->me].using_unified_queue) +return -EINVAL ; +mutex_lock (&vinst->engine_reset_mutex);/* Stop the scheduler's work queue for the dec and enc rings if they are running. * This ensures that no new tasks are submitted to the queues while
@@ -1537,29 +1545,6 @@ static int amdgpu_vcn_reset_engine(struct amdgpu_ring *ring,return r; } -/** -* amdgpu_vcn_ring_reset - Reset a VCN ring -* @ring: ring to reset -* @vmid: vmid of guilty job -* @timedout_fence: fence of timed out job -* -* This helper is for VCN blocks without unified queues because -* resetting the engine resets all queues in that case. With -* unified queues we have one queue per engine. -* Returns: 0 on success, or a negative error code on failure. -*/ -int amdgpu_vcn_ring_reset (struct amdgpu_ring *ring, -unsigned int vmid, -struct amdgpu_fence *timedout_fence) -{ -struct amdgpu_device *adev = ring->adev; - -if (adev->vcn.inst[ring->me].using_unified_queue) -return -EINVAL ; - -return amdgpu_vcn_reset_engine (ring, timedout_fence); -} -int amdgpu_vcn_reg_dump_init (struct amdgpu_device *adev,const struct amdgpu_hwip_reg_entry *reg,u32 count) {
Signature · 1 line
2.52.0
Alex Deucher
maintainerPATCH 9/12 drm/amdgpu: Call drm_sched_increase_karma() for ring resets
In reply to Alex DeucherMark the entity as guilty. Align with adapter resets. This only makes sense now that the CS IOCTL returns -ETIME rather than -ECANCELED. Without that patch, this would break userspace.
--- drivers/gpu/drm/amd/amdgpu/amdgpu_job.c | 2 ++ 1 file changed, 2 insertions(+)
drivers/gpu/drm/amd/amdgpu/amdgpu_job.c +2 -0
@@ -137,6 +137,8 @@ static enum drm_gpu_sched_stat amdgpu_job_timedout(struct drm_sched_job *s_job) s_job->sched->name);/* Stop the scheduler to prevent anybody else from touching the ring buffer. */ drm_sched_wqueue_stop (&ring->sched); +if (job->vm) +drm_sched_increase_karma (&job->base); r =amdgpu_ring_reset (ring, job->vmid, job->hw_fence);if (!r) {/* Start the scheduler again */
Signature · 1 line
2.52.0
Alex Deucher
maintainerPATCH 10/12 drm/amdgpu: reorder IB schedule sequence
In reply to Alex DeucherThis reorders the IB schedule sequence to cleanly separate the vm operation from the IB submission. This makes the two independent so we can cleanly associate each one with its respective fence.
--- drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c | 22 +++++++++++----------- drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 7 +++++++ 2 files changed, 18 insertions(+), 11 deletions(-)
drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c +11 -11
@@ -192,16 +192,6 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, struct amdgpu_job *job,dma_fence_put (tmp); } -if ((ib->flags &AMDGPU_IB_FLAG_EMIT_MEM_SYNC ) && ring->funcs->emit_mem_sync) - ring->funcs->emit_mem_sync (ring); - -if (ring->funcs->emit_wave_limit && - ring->hw_prio ==AMDGPU_GFX_PIPE_PRIO_HIGH ) - ring->funcs->emit_wave_limit (ring, true); - -if (ring->funcs->insert_start) - ring->funcs->insert_start (ring); - r =amdgpu_vm_flush (ring, job, need_pipe_sync);if (r) {amdgpu_ring_undo (ring);
@@ -210,6 +200,16 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, struct amdgpu_job *job,amdgpu_ring_ib_begin (ring); +if (ring->funcs->insert_start) + ring->funcs->insert_start (ring); + +if ((ib->flags &AMDGPU_IB_FLAG_EMIT_MEM_SYNC ) && ring->funcs->emit_mem_sync) + ring->funcs->emit_mem_sync (ring); + +if (ring->funcs->emit_wave_limit && + ring->hw_prio ==AMDGPU_GFX_PIPE_PRIO_HIGH ) + ring->funcs->emit_wave_limit (ring, true); +if (ring->funcs->emit_gfx_shadow && adev->gfx.cp_gfx_shadow)amdgpu_ring_emit_gfx_shadow (ring, job->shadow_va, job->csa_va, job->gds_va, job->init_shadow, vmid);
@@ -297,6 +297,7 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, struct amdgpu_job *job, ring->hw_prio == AMDGPU_GFX_PIPE_PRIO_HIGH) ring->funcs->emit_wave_limit(ring, false); +amdgpu_ring_ib_end (ring);/* Save the wptr associated with this fence. * This must be last for resets to work properly * as we need to save the wptr associated with this
@@ -305,7 +306,6 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, struct amdgpu_job *job,*/ amdgpu_fence_save_wptr (af); -amdgpu_ring_ib_end (ring);amdgpu_ring_commit (ring);return 0 ;
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +7 -0
@@ -815,6 +815,10 @@ int amdgpu_vm_flush(struct amdgpu_ring *ring, struct amdgpu_job *job,return 0 ;amdgpu_ring_ib_begin (ring); + +if (ring->funcs->insert_start) + ring->funcs->insert_start (ring); +if (ring->funcs->init_cond_exec) patch =amdgpu_ring_init_cond_exec (ring, ring->cond_exe_gpu_addr);
@@ -891,6 +895,9 @@ int amdgpu_vm_flush(struct amdgpu_ring *ring, struct amdgpu_job *job,amdgpu_ring_emit_switch_buffer (ring); } +if (ring->funcs->insert_end) + ring->funcs->insert_end (ring); +amdgpu_ring_ib_end (ring);return 0 ; }
Signature · 1 line
2.52.0
Re: [PATCH 10/12] drm/amdgpu: reorder IB schedule sequence
Le 30/01/2026 à 18:30, Alex Deucher a écrit :
Quoted 6 lines
This reorders the IB schedule sequence to cleanly separate the vm operation from the IB submission. This makes the two independent so we can cleanly associate each one with its respective fence.
Signed-off-by Alex Deucher <[email protected]>
Quoted 84 lines
--- drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c | 22 +++++++++++----------- drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 7 +++++++ 2 files changed, 18 insertions(+), 11 deletions(-)drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c +11
-11@@ -192,16 +192,6 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, struct amdgpu_job *job,dma_fence_put (tmp); } -if ((ib->flags &AMDGPU_IB_FLAG_EMIT_MEM_SYNC ) && ring->funcs->emit_mem_sync) - ring->funcs->emit_mem_sync (ring); - -if (ring->funcs->emit_wave_limit && - ring->hw_prio ==AMDGPU_GFX_PIPE_PRIO_HIGH ) - ring->funcs->emit_wave_limit (ring, true); - -if (ring->funcs->insert_start) - ring->funcs->insert_start (ring); - r =amdgpu_vm_flush (ring, job, need_pipe_sync);if (r) {amdgpu_ring_undo (ring);@@ -210,6 +200,16 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, struct amdgpu_job *job,amdgpu_ring_ib_begin (ring); +if (ring->funcs->insert_start) + ring->funcs->insert_start (ring); + +if ((ib->flags &AMDGPU_IB_FLAG_EMIT_MEM_SYNC ) && ring->funcs->emit_mem_sync) + ring->funcs->emit_mem_sync (ring); + +if (ring->funcs->emit_wave_limit && + ring->hw_prio ==AMDGPU_GFX_PIPE_PRIO_HIGH ) + ring->funcs->emit_wave_limit (ring, true); +if (ring->funcs->emit_gfx_shadow && adev->gfx.cp_gfx_shadow)amdgpu_ring_emit_gfx_shadow (ring, job->shadow_va, job->csa_va, job->gds_va, job->init_shadow, vmid);@@ -297,6 +297,7 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, struct amdgpu_job *job, ring->hw_prio == AMDGPU_GFX_PIPE_PRIO_HIGH) ring->funcs->emit_wave_limit(ring, false); +amdgpu_ring_ib_end (ring);/* Save the wptr associated with this fence. * This must be last for resets to work properly * as we need to save the wptr associated with this @@ -305,7 +306,6 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, struct amdgpu_job *job,*/ amdgpu_fence_save_wptr (af); -amdgpu_ring_ib_end (ring);amdgpu_ring_commit (ring);return 0 ;drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +7
-0@@ -815,6 +815,10 @@ int amdgpu_vm_flush(struct amdgpu_ring *ring, struct amdgpu_job *job,return 0 ;amdgpu_ring_ib_begin (ring); + +if (ring->funcs->insert_start) + ring->funcs->insert_start (ring); +if (ring->funcs->init_cond_exec) patch =amdgpu_ring_init_cond_exec (ring, ring->cond_exe_gpu_addr);@@ -891,6 +895,9 @@ int amdgpu_vm_flush(struct amdgpu_ring *ring, struct amdgpu_job *job,amdgpu_ring_emit_switch_buffer (ring); } +if (ring->funcs->insert_end) + ring->funcs->insert_end (ring); +amdgpu_ring_ib_end (ring);return 0 ; }
Alex Deucher
maintainerPATCH 11/12 drm/amdgpu: add a helper to calculate ring distance
In reply to Alex DeucherAdd a helper to calculate the distance in DWs between two wptrs.
--- drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h | 18 ++++++++++++------ 1 file changed, 12 insertions(+), 6 deletions(-)
drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h +12 -6
@@ -523,6 +523,17 @@ static inline void amdgpu_ring_write_multiple(struct amdgpu_ring *ring, ring->count_dw -= count_dw; } +static inline unsigned int amdgpu_ring_get_dw_distance (struct amdgpu_ring *ring, +u64 start_wptr,u64 end_wptr) +{ +unsigned int start = start_wptr & ring->buf_mask; +unsigned int end = end_wptr & ring->buf_mask; + +if (end < start) + end += ring->ring_size >>2 ; +return end - start; +} +/** * amdgpu_ring_patch_cond_exec - patch dw count of conditional execute * @ring: amdgpu_ring structure
@@ -533,18 +544,13 @@ static inline void amdgpu_ring_write_multiple(struct amdgpu_ring *ring,static inline void amdgpu_ring_patch_cond_exec (struct amdgpu_ring *ring,unsigned int offset) { -unsigned cur; -if (!ring->funcs->init_cond_exec)return ;WARN_ON (offset > ring->buf_mask);WARN_ON (ring->ring[offset] !=0 ); - cur = (ring->wptr -1 ) & ring->buf_mask; -if (cur < offset) - cur += ring->ring_size >>2 ; - ring->ring[offset] = cur - offset; + ring->ring[offset] =amdgpu_ring_get_dw_distance (ring, offset, ring->wptr -1 ); }int amdgpu_ring_test_helper (struct amdgpu_ring *ring);
Signature · 1 line
2.52.0
Re: [PATCH 11/12] drm/amdgpu: add a helper to calculate ring distance
Le 30/01/2026 à 18:30, Alex Deucher a écrit :
Quoted 4 lines
Add a helper to calculate the distance in DWs between two wptrs.
Signed-off-by Alex Deucher <[email protected]>
Quoted 46 lines
--- drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h | 18 ++++++++++++------ 1 file changed, 12 insertions(+), 6 deletions(-)drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h +12
-6@@ -523,6 +523,17 @@ static inline void amdgpu_ring_write_multiple(struct amdgpu_ring *ring, ring->count_dw -= count_dw; } +static inline unsigned int amdgpu_ring_get_dw_distance (struct amdgpu_ring *ring, +u64 start_wptr,u64 end_wptr) +{ +unsigned int start = start_wptr & ring->buf_mask; +unsigned int end = end_wptr & ring->buf_mask; + +if (end < start) + end += ring->ring_size >>2 ; +return end - start; +} +/** * amdgpu_ring_patch_cond_exec - patch dw count of conditional execute * @ring: amdgpu_ring structure @@ -533,18 +544,13 @@ static inline void amdgpu_ring_write_multiple(struct amdgpu_ring *ring,static inline void amdgpu_ring_patch_cond_exec (struct amdgpu_ring *ring,unsigned int offset) { -unsigned cur; -if (!ring->funcs->init_cond_exec)return ;WARN_ON (offset > ring->buf_mask);WARN_ON (ring->ring[offset] !=0 ); - cur = (ring->wptr -1 ) & ring->buf_mask; -if (cur < offset) - cur += ring->ring_size >>2 ; - ring->ring[offset] = cur - offset; + ring->ring[offset] =amdgpu_ring_get_dw_distance (ring, offset, ring->wptr -1 ); }int amdgpu_ring_test_helper (struct amdgpu_ring *ring);
Alex Deucher
maintainerPATCH 12/12 drm/amdgpu: rework ring reset backup and reemit v8
In reply to Alex DeucherStore the start wptr and ib size in the IB fence. On queue reset, save the ring contents of all IBs.
For reemit, reemit the entire IB state for non-guilty contexts. For guilty contexts, replace the IB submission with nops, but reemit the rest. Split the reemit per fence and when we reemit, update the wptr with the new values from reemit. This allows us to reemit jobs repeatedly as the wptrs get properly updated each time.
v2: further simplify the logic
v3: reemit vm state, not just vm fence
v4: just nop the IB and possibly the VM portion of the submission
v5: simplify the vm fence check
v6: split the vm and ib fences
v7: fix commit message
v8: use wptr rather than count_dw to calculate offsets
--- drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c | 98 +++++++++-------------- drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c | 25 ++++-- drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c | 46 +++-------- drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h | 20 ++--- 4 files changed, 72 insertions(+), 117 deletions(-)
drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c +36 -62
@@ -89,16 +89,6 @@ static u32 amdgpu_fence_read(struct amdgpu_ring *ring)return seq; } -static void amdgpu_fence_save_fence_wptr_start (struct amdgpu_fence *af) -{ - af->fence_wptr_start = af->ring->wptr; -} - -static void amdgpu_fence_save_fence_wptr_end (struct amdgpu_fence *af) -{ - af->fence_wptr_end = af->ring->wptr; -} -/** * amdgpu_fence_emit - emit a fence on the requested ring *
@@ -126,11 +116,9 @@ int amdgpu_fence_emit(struct amdgpu_ring *ring, struct amdgpu_fence *af, &ring->fence_drv.lock, adev->fence_context + ring->idx, seq); -amdgpu_fence_save_fence_wptr_start (af);amdgpu_ring_emit_fence (ring, ring->fence_drv.gpu_addr, seq, flags |AMDGPU_FENCE_FLAG_INT ); -amdgpu_fence_save_fence_wptr_end (af); -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 ))) {
@@ -241,7 +229,6 @@ bool amdgpu_fence_process(struct amdgpu_ring *ring) do { struct dma_fence *fence, **ptr; - struct amdgpu_fence *am_fence; ++last_seq; last_seq &= drv->num_fences_mask;
@@ -254,12 +241,6 @@ bool amdgpu_fence_process(struct amdgpu_ring *ring)if (!fence)continue ; -/* Save the wptr in the fence driver so we know what the last processed -* wptr was. This is required for re-emitting the ring state for -* queues that are reset but are not guilty and thus have no guilty fence. -*/ - am_fence = container_of(fence, struct amdgpu_fence, base); - drv->signalled_wptr = am_fence->wptr;dma_fence_signal (fence);dma_fence_put (fence);pm_runtime_put_autosuspend (adev_to_drm (adev)->dev);
@@ -726,25 +707,28 @@ void amdgpu_fence_driver_force_completion(struct amdgpu_ring *ring,*/ /** -* amdgpu_fence_driver_update_timedout_fence_state - Update fence state and set errors +* amdgpu_ring_set_fence_errors_and_reemit - Set dma_fence errors and reemit * -* @af: fence of the ring to update +* @guilty_fence: fence of the ring to update * */ -void amdgpu_fence_driver_update_timedout_fence_state (struct amdgpu_fence *af) +void amdgpu_ring_set_fence_errors_and_reemit (struct amdgpu_ring *ring, +struct amdgpu_fence *guilty_fence) {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; -bool reemitted = false; +unsigned int i; +bool is_guilty_fence; +bool is_guilty_context; 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 */ + ring->reemit = true; +amdgpu_ring_alloc (ring, ring->ring_backup_entries_to_copy);spin_lock_irqsave (&ring->fence_drv.lock, flags); do { last_seq++;
@@ -756,39 +740,45 @@ void amdgpu_fence_driver_update_timedout_fence_state(struct amdgpu_fence *af)if (unprocessed && !dma_fence_is_signaled_locked (unprocessed)) { fence = container_of(unprocessed, struct amdgpu_fence, base); + is_guilty_fence = fence == guilty_fence; + is_guilty_context = fence->context == guilty_fence->context; -if (fence->reemitted >1 ) - reemitted = true; -else if (fence == af) +/* mark all fences from the guilty context with an error */ +if (is_guilty_fence)dma_fence_set_error (&fence->base, -ETIME ); -else if (fence->context == af->context) +else if (is_guilty_context)dma_fence_set_error (&fence->base, -ECANCELED ); + +/* reemit the packet stream and update wptrs */ + fence->ib_wptr = ring->wptr; +for (i =0 ; i < fence->ib_dw_size; i++) { +/* Skip the IB(s) for the guilty context. */ +if (is_guilty_context && + i >= fence->skip_ib_dw_start_offset && + i < fence->skip_ib_dw_end_offset) +amdgpu_ring_write (ring, ring->funcs->nop); +else +amdgpu_ring_write (ring, + ring->ring_backup[fence->backup_idx + i]); + } }rcu_read_unlock (); }while (last_seq != seq);spin_unlock_irqrestore (&ring->fence_drv.lock, flags); - -if (reemitted) { -/* if we've already reemitted once then just cancel everything */ -amdgpu_fence_driver_force_completion (af->ring, &af->base); - af->ring->ring_backup_entries_to_copy =0 ; - } -} - -void amdgpu_fence_save_wptr (struct amdgpu_fence *af) -{ - af->wptr = af->ring->wptr; +amdgpu_ring_commit (ring); + ring->reemit = false; }static void amdgpu_ring_backup_unprocessed_command (struct amdgpu_ring *ring, -u64 start_wptr,u64 end_wptr) +struct amdgpu_fence *af) { -unsigned int first_idx = start_wptr & ring->buf_mask; -unsigned int last_idx = end_wptr & ring->buf_mask; +unsigned int first_idx = af->ib_wptr & ring->buf_mask; +unsigned int dw_size = af->ib_dw_size;unsigned int i; + af->backup_idx = ring->ring_backup_entries_to_copy;/* Backup the contents of the ring buffer. */ -for (i = first_idx; i != last_idx; ++i, i &= ring->buf_mask) +for (i = first_idx; dw_size >0 ; ++i, i &= ring->buf_mask, --dw_size) ring->ring_backup[ring->ring_backup_entries_to_copy++] = ring->ring[i]; }
@@ -798,12 +788,10 @@ 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;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; - wptr = ring->fence_drv.signalled_wptr; ring->ring_backup_entries_to_copy =0 ; do {
@@ -817,21 +805,7 @@ void amdgpu_ring_backup_unprocessed_commands(struct amdgpu_ring *ring,if (unprocessed && !dma_fence_is_signaled (unprocessed)) { fence = container_of(unprocessed, struct amdgpu_fence, base); -/* save everything if the ring is not guilty, otherwise -* just save the content from other contexts. -*/ -if (!fence->reemitted && - (!guilty_fence || (fence->context != guilty_fence->context))) { -amdgpu_ring_backup_unprocessed_command (ring, wptr, - fence->wptr); - }else if (!fence->reemitted) { -/* always save the fence */ -amdgpu_ring_backup_unprocessed_command (ring, - fence->fence_wptr_start, - fence->fence_wptr_end); - } - wptr = fence->wptr; - fence->reemitted++; +amdgpu_ring_backup_unprocessed_command (ring, fence); }rcu_read_unlock (); }while (last_seq != seq);
drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c +17 -8
@@ -126,6 +126,7 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, struct amdgpu_job *job,struct amdgpu_ib *ib;struct dma_fence *tmp =NULL ;struct amdgpu_fence *af; +struct amdgpu_fence *vm_af;bool need_ctx_switch;uint64_t fence_ctx;uint32_t status =0 , alloc_size;
@@ -146,13 +147,14 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, struct amdgpu_job *job, fence_ctx = job->base.s_fence ? job->base.s_fence->finished.context :0 ; af = job->hw_fence; + vm_af = job->hw_vm_fence;/* Save the context of the job for reset handling. * The driver needs this so it can skip the ring * contents for guilty contexts. */ af->context = fence_ctx;/* the vm fence is also part of the job's context */ - job->hw_vm_fence->context = fence_ctx; + vm_af->context = fence_ctx;if (!ring->sched.ready) {dev_err (adev->dev,"couldn't schedule ib on ring <%s>\n" , ring->name);
@@ -192,12 +194,18 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, struct amdgpu_job *job,dma_fence_put (tmp); } +/* VM sequence */ + vm_af->ib_wptr = ring->wptr; r =amdgpu_vm_flush (ring, job, need_pipe_sync);if (r) {amdgpu_ring_undo (ring);return r; } + vm_af->ib_dw_size = +amdgpu_ring_get_dw_distance (ring, vm_af->ib_wptr, ring->wptr); +/* IB sequence */ + af->ib_wptr = ring->wptr;amdgpu_ring_ib_begin (ring);if (ring->funcs->insert_start)
@@ -218,6 +226,9 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, struct amdgpu_job *job, cond_exec =amdgpu_ring_init_cond_exec (ring, ring->cond_exe_gpu_addr); +/* Skip the IB for guilty contexts */ + af->skip_ib_dw_start_offset = +amdgpu_ring_get_dw_distance (ring, af->ib_wptr, ring->wptr);amdgpu_device_flush_hdp (adev, ring);if (need_ctx_switch)
@@ -256,6 +267,9 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, struct amdgpu_job *job,amdgpu_ring_emit_frame_cntl (ring, false, secure);amdgpu_device_invalidate_hdp (adev, ring); +/* Skip the IB for guilty contexts */ + af->skip_ib_dw_end_offset = +amdgpu_ring_get_dw_distance (ring, af->ib_wptr, ring->wptr);if (ib->flags &AMDGPU_IB_FLAG_TC_WB_NOT_INVALIDATE ) fence_flags |=AMDGPU_FENCE_FLAG_TC_WB_ONLY ;
@@ -298,13 +312,8 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, struct amdgpu_job *job, ring->funcs->emit_wave_limit (ring, false);amdgpu_ring_ib_end (ring); -/* Save the wptr associated with this fence. -* This must be last for resets to work properly -* as we need to save the wptr associated with this -* fence so we know what rings contents to backup -* after we reset the queue. -*/ -amdgpu_fence_save_wptr (af); + + af->ib_dw_size =amdgpu_ring_get_dw_distance (ring, af->ib_wptr, ring->wptr);amdgpu_ring_commit (ring);
drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c +9 -37
71 lines not on this page · raw message
drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h +10 -10
@@ -121,7 +121,6 @@ struct amdgpu_fence_driver {/* sync_seq is protected by ring emission lock */ uint32_t sync_seq;atomic_t last_seq; -u64 signalled_wptr;bool initialized;struct amdgpu_irq_src *irq_src;unsigned irq_type;
@@ -146,15 +145,15 @@ struct amdgpu_fence {struct amdgpu_ring *ring;ktime_t start_timestamp; -/* wptr for the total submission for resets */ -u64 wptr; +/* location and size of the IB */ +u64 ib_wptr; +unsigned int ib_dw_size; +unsigned int skip_ib_dw_start_offset; +unsigned int skip_ib_dw_end_offset;/* fence context for resets */ u64 context; -/* has this fence been reemitted */ -unsigned int reemitted; -/* wptr for the fence for the submission */ -u64 fence_wptr_start; -u64 fence_wptr_end; +/* idx for ring backups */ +unsigned int backup_idx; };extern const struct drm_sched_backend_ops amdgpu_sched_ops;
@@ -162,8 +161,8 @@ extern const struct drm_sched_backend_ops amdgpu_sched_ops;void amdgpu_fence_driver_set_error (struct amdgpu_ring *ring,int error);void amdgpu_fence_driver_force_completion (struct amdgpu_ring *ring,struct dma_fence *timedout_fence); -void amdgpu_fence_driver_update_timedout_fence_state (struct amdgpu_fence *af); -void amdgpu_fence_save_wptr (struct amdgpu_fence *af); +void amdgpu_ring_set_fence_errors_and_reemit (struct amdgpu_ring *ring, +struct amdgpu_fence *guilty_fence);int amdgpu_fence_driver_init_ring (struct amdgpu_ring *ring); int amdgpu_fence_driver_start_ring(struct amdgpu_ring *ring,
@@ -314,6 +313,7 @@ struct amdgpu_ring {/* backups for resets */ uint32_t *ring_backup;unsigned int ring_backup_entries_to_copy; +bool reemit;unsigned rptr_offs;u64 rptr_gpu_addr;u32 *rptr_cpu_addr;
Signature · 1 line
2.52.0