* [PATCH 3/7] drm/amdgpu: require a job to schedule an IB
2026-03-16 18:16 [PATCH 1/7] drm/amdgpu/job: use GFP_ATOMIC while in gpu reset Alex Deucher
@ 2026-03-16 18:16 ` Alex Deucher
0 siblings, 0 replies; 8+ messages in thread
From: Alex Deucher @ 2026-03-16 18:16 UTC (permalink / raw)
To: amd-gfx, christian.koenig; +Cc: Alex Deucher, Jesse Zhang
Remove the old direct submit path. This simplifies
the code.
v2: remove more local variables
Reviewed-by: Jesse Zhang <jesse.zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c | 2 +-
drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c | 113 ++++++++-------------
drivers/gpu/drm/amd/amdgpu/amdgpu_job.c | 5 +-
drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h | 3 +-
4 files changed, 45 insertions(+), 78 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
index 823b92005689a..4ec1058b7cdfa 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
@@ -685,7 +685,7 @@ 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");
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
index 80565c4a31bdf..55a9670f1dd90 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
@@ -103,8 +103,6 @@ void amdgpu_ib_free(struct amdgpu_ib *ib, struct dma_fence *f)
* amdgpu_ib_schedule - schedule an IB (Indirect Buffer) on the ring
*
* @ring: ring index the IB is associated with
- * @num_ibs: number of IBs to schedule
- * @ibs: IB objects to schedule
* @job: job to schedule
* @f: fence created during this submission
*
@@ -121,90 +119,70 @@ void amdgpu_ib_free(struct amdgpu_ib *ib, struct dma_fence *f)
* a CONST_IB), it will be put on the ring prior to the DE IB. Prior
* to SI there was just a DE IB.
*/
-int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned int 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)
{
struct amdgpu_device *adev = ring->adev;
- struct amdgpu_ib *ib = &ibs[0];
+ struct amdgpu_ib *ib;
struct dma_fence *tmp = NULL;
struct amdgpu_fence *af;
struct amdgpu_fence *vm_af;
bool need_ctx_switch;
- struct amdgpu_vm *vm;
uint64_t fence_ctx;
uint32_t status = 0, alloc_size;
unsigned int fence_flags = 0;
- bool secure, init_shadow;
- u64 shadow_va, csa_va, gds_va;
+ bool secure;
int vmid = AMDGPU_JOB_GET_VMID(job);
bool need_pipe_sync = false;
unsigned int cond_exec;
unsigned int i;
int r = 0;
- if (num_ibs == 0)
+ if (!job)
+ return -EINVAL;
+ if (job->num_ibs == 0)
return -EINVAL;
- /* ring tests don't use a job */
- if (job) {
- vm = job->vm;
- fence_ctx = job->base.s_fence ?
- job->base.s_fence->finished.context : 0;
- shadow_va = job->shadow_va;
- csa_va = job->csa_va;
- gds_va = job->gds_va;
- init_shadow = job->init_shadow;
- af = job->hw_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;
- } else {
- vm = NULL;
- fence_ctx = 0;
- shadow_va = 0;
- csa_va = 0;
- gds_va = 0;
- init_shadow = false;
- af = kzalloc(sizeof(*af), GFP_ATOMIC);
- if (!af)
- return -ENOMEM;
- }
+ ib = &job->ibs[0];
+ 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 */
+ vm_af->context = fence_ctx;
if (!ring->sched.ready) {
dev_err(adev->dev, "couldn't schedule ib on ring <%s>\n", ring->name);
- r = -EINVAL;
- goto free_fence;
+ return -EINVAL;
}
- if (vm && !job->vmid) {
+ if (job->vm && !job->vmid) {
dev_err(adev->dev, "VM IB without ID\n");
- r = -EINVAL;
- goto free_fence;
+ return -EINVAL;
}
if ((ib->flags & AMDGPU_IB_FLAGS_SECURE) &&
(!ring->funcs->secure_submission_supported)) {
dev_err(adev->dev, "secure submissions not supported on ring <%s>\n", ring->name);
- r = -EINVAL;
- goto free_fence;
+ return -EINVAL;
}
- alloc_size = ring->funcs->emit_frame_size + num_ibs *
+ alloc_size = ring->funcs->emit_frame_size + job->num_ibs *
ring->funcs->emit_ib_size;
r = amdgpu_ring_alloc(ring, alloc_size);
if (r) {
dev_err(adev->dev, "scheduling IB failed (%d).\n", r);
- goto free_fence;
+ return r;
}
need_ctx_switch = ring->current_ctx != fence_ctx;
- if (ring->funcs->emit_pipeline_sync && job &&
+ if (ring->funcs->emit_pipeline_sync &&
((tmp = amdgpu_sync_get_fence(&job->explicit_sync)) ||
need_ctx_switch || amdgpu_vm_need_pipeline_sync(ring, job))) {
@@ -216,14 +194,11 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned int num_ibs,
dma_fence_put(tmp);
}
- if (job) {
- vm_af = job->hw_vm_fence;
- /* VM sequence */
- vm_af->ib_wptr = ring->wptr;
- amdgpu_vm_flush(ring, job, need_pipe_sync);
- vm_af->ib_dw_size =
- amdgpu_ring_get_dw_distance(ring, vm_af->ib_wptr, ring->wptr);
- }
+ /* VM sequence */
+ vm_af->ib_wptr = ring->wptr;
+ amdgpu_vm_flush(ring, job, need_pipe_sync);
+ vm_af->ib_dw_size =
+ amdgpu_ring_get_dw_distance(ring, vm_af->ib_wptr, ring->wptr);
/* IB sequence */
af->ib_wptr = ring->wptr;
@@ -240,8 +215,8 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned int num_ibs,
ring->funcs->emit_wave_limit(ring, true);
if (ring->funcs->emit_gfx_shadow && adev->gfx.cp_gfx_shadow)
- amdgpu_ring_emit_gfx_shadow(ring, shadow_va, csa_va, gds_va,
- init_shadow, vmid);
+ amdgpu_ring_emit_gfx_shadow(ring, job->shadow_va, job->csa_va, job->gds_va,
+ job->init_shadow, vmid);
if (ring->funcs->init_cond_exec)
cond_exec = amdgpu_ring_init_cond_exec(ring,
@@ -255,7 +230,7 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned int num_ibs,
if (need_ctx_switch)
status |= AMDGPU_HAVE_CTX_SWITCH;
- if (job && ring->funcs->emit_cntxcntl) {
+ if (ring->funcs->emit_cntxcntl) {
status |= job->preamble_status;
status |= job->preemption_status;
amdgpu_ring_emit_cntxcntl(ring, status);
@@ -264,15 +239,15 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned int num_ibs,
/* Setup initial TMZiness and send it off.
*/
secure = false;
- if (job && ring->funcs->emit_frame_cntl) {
+ if (ring->funcs->emit_frame_cntl) {
secure = ib->flags & AMDGPU_IB_FLAGS_SECURE;
amdgpu_ring_emit_frame_cntl(ring, true, secure);
}
- for (i = 0; i < num_ibs; ++i) {
- ib = &ibs[i];
+ for (i = 0; i < job->num_ibs; ++i) {
+ ib = &job->ibs[i];
- if (job && ring->funcs->emit_frame_cntl) {
+ if (ring->funcs->emit_frame_cntl) {
if (secure != !!(ib->flags & AMDGPU_IB_FLAGS_SECURE)) {
amdgpu_ring_emit_frame_cntl(ring, false, secure);
secure = !secure;
@@ -284,7 +259,7 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned int num_ibs,
status &= ~AMDGPU_HAVE_CTX_SWITCH;
}
- if (job && ring->funcs->emit_frame_cntl)
+ if (ring->funcs->emit_frame_cntl)
amdgpu_ring_emit_frame_cntl(ring, false, secure);
amdgpu_device_invalidate_hdp(adev, ring);
@@ -296,7 +271,7 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned int num_ibs,
fence_flags |= AMDGPU_FENCE_FLAG_TC_WB_ONLY;
/* wrap the last IB with fence */
- if (job && job->uf_addr) {
+ if (job->uf_addr) {
amdgpu_ring_emit_fence(ring, job->uf_addr, job->uf_sequence,
fence_flags | AMDGPU_FENCE_FLAG_64BIT);
}
@@ -310,8 +285,7 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned int num_ibs,
amdgpu_fence_emit(ring, af, fence_flags);
*f = &af->base;
/* get a ref for the job */
- if (job)
- dma_fence_get(*f);
+ dma_fence_get(*f);
if (ring->funcs->insert_end)
ring->funcs->insert_end(ring);
@@ -319,7 +293,7 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned int num_ibs,
amdgpu_ring_patch_cond_exec(ring, cond_exec);
ring->current_ctx = fence_ctx;
- if (job && ring->funcs->emit_switch_buffer)
+ if (ring->funcs->emit_switch_buffer)
amdgpu_ring_emit_switch_buffer(ring);
if (ring->funcs->emit_wave_limit &&
@@ -333,11 +307,6 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned int num_ibs,
amdgpu_ring_commit(ring);
return 0;
-
-free_fence:
- if (!job)
- kfree(af);
- return r;
}
/**
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
index 95aa87b4406eb..cd0707737a29b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
@@ -377,7 +377,7 @@ 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;
@@ -447,8 +447,7 @@ 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,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
index ce5af137ee400..fafb876d73da1 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
@@ -575,8 +575,7 @@ 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);
--
2.53.0
^ permalink raw reply related [flat|nested] 8+ messages in thread
* [PATCH 1/7] drm/amdgpu/job: use GFP_ATOMIC while in gpu reset
@ 2026-03-18 18:35 Alex Deucher
2026-03-18 18:35 ` [PATCH 2/7] drm/amdgpu: switch all IPs to using job for IBs Alex Deucher
` (5 more replies)
0 siblings, 6 replies; 8+ messages in thread
From: Alex Deucher @ 2026-03-18 18:35 UTC (permalink / raw)
To: amd-gfx; +Cc: Alex Deucher, Jesse Zhang
If we need to allocate a job during GPU reset, use
GFP_ATOMIC rather than GFP_KERNEL.
v2: use pool type it determine alloc flags.
Reviewed-by: Jesse Zhang <jesse.zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
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(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
index 3bfd79c89df32..823b92005689a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
@@ -671,7 +671,7 @@ 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;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index 22aafa969b3dc..f75f5079be80f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -275,7 +275,7 @@ 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]) {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
index f1ed4a436f5b4..80565c4a31bdf 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
@@ -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;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
index 55172c2dcc355..95aa87b4406eb 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
@@ -188,7 +188,7 @@ 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;
@@ -196,18 +196,21 @@ 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;
@@ -246,7 +249,7 @@ 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;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.h
index 56a88e14a0448..9de2cae966fea 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.h
@@ -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,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h
index 912c9afaf9e11..8abff5fdae81d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h
@@ -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)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sa.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_sa.c
index 39070b2a4c04f..1d44b95de7e55 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sa.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sa.c
@@ -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;
--
2.53.0
^ permalink raw reply related [flat|nested] 8+ messages in thread
* [PATCH 2/7] drm/amdgpu: switch all IPs to using job for IBs
2026-03-18 18:35 [PATCH 1/7] drm/amdgpu/job: use GFP_ATOMIC while in gpu reset Alex Deucher
@ 2026-03-18 18:35 ` Alex Deucher
2026-03-18 18:36 ` [PATCH 3/7] drm/amdgpu: require a job to schedule an IB Alex Deucher
` (4 subsequent siblings)
5 siblings, 0 replies; 8+ messages in thread
From: Alex Deucher @ 2026-03-18 18:35 UTC (permalink / raw)
To: amd-gfx; +Cc: Alex Deucher, Pierre-Eric Pelloux-Prayer, Christian König
Switch to using a job structure for IBs.
v2: fix missing ib pointer setup spotted by the kernel test robot
Acked-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
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 | 139 ++++++++++++-----------
drivers/gpu/drm/amd/amdgpu/gfx_v9_4_2.c | 27 ++---
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, 502 insertions(+), 427 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vpe.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vpe.c
index fd881388d6125..9fb1946be1ba2 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vpe.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vpe.c
@@ -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);
diff --git a/drivers/gpu/drm/amd/amdgpu/cik_sdma.c b/drivers/gpu/drm/amd/amdgpu/cik_sdma.c
index 22780c09177d8..c6fccb92e656c 100644
--- a/drivers/gpu/drm/amd/amdgpu/cik_sdma.c
+++ b/drivers/gpu/drm/amd/amdgpu/cik_sdma.c
@@ -651,7 +651,8 @@ 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;
@@ -665,22 +666,27 @@ 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) {
@@ -696,7 +702,6 @@ 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);
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
index 1893ceeeb26c8..50954b60e49df 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
@@ -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);
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
index b1a1b8a10a08b..d03a4577d4ebf 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
@@ -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);
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c
index a418ae609c363..905dbd06c28f3 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c
@@ -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);
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v12_1.c b/drivers/gpu/drm/amd/amdgpu/gfx_v12_1.c
index db49582a211f7..266e890edae0f 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v12_1.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v12_1.c
@@ -306,7 +306,8 @@ 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;
@@ -318,8 +319,6 @@ 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;
@@ -328,22 +327,27 @@ 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) {
@@ -358,7 +362,6 @@ 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);
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c
index 73223d97a87f5..2f8aa99f17480 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c
@@ -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;
}
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
index 2b691452775bc..fa235b981c2e9 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
@@ -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;
}
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
index a6b4c8f41dc11..4736216cd0211 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
@@ -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;
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
index 95be105671ece..50ef4e06be569 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
@@ -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;
@@ -4670,112 +4674,114 @@ 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;
}
+ ib = &job->ibs[0];
/* 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 +4793,6 @@ 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;
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_2.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_2.c
index 8058ea91ecafd..96ec6d9ea8656 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_2.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_2.c
@@ -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;
@@ -360,14 +361,14 @@ 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;
}
+ ib = &job->ibs[0];
/* load the compute shaders */
for (i = 0; i < shader_size/sizeof(u32); i++)
@@ -408,11 +409,11 @@ 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 +494,6 @@ 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 +514,6 @@ 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 +538,6 @@ 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 +577,6 @@ 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 +608,10 @@ 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 +631,6 @@ 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 +650,6 @@ 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 +679,6 @@ 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);
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c
index ad4d442e7345e..d78b2c2ae13a3 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c
@@ -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);
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c b/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c
index 0090ace49024f..34c5acfa038d2 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c
@@ -583,7 +583,8 @@ 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;
@@ -597,26 +598,30 @@ 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) {
@@ -632,7 +637,6 @@ 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);
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
index 2526d393162ac..73bd9005dbeaa 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
@@ -857,7 +857,8 @@ 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;
@@ -871,26 +872,30 @@ 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) {
@@ -905,7 +910,6 @@ 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);
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
index 44f0f23e11484..94f1ea2d7f73a 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
@@ -1515,7 +1515,8 @@ 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;
@@ -1529,26 +1530,30 @@ 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) {
@@ -1564,7 +1569,6 @@ 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);
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c
index 78bdfed0a7fd3..0895ae39f6af0 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c
@@ -1111,7 +1111,8 @@ 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;
@@ -1125,26 +1126,30 @@ 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) {
@@ -1160,7 +1165,6 @@ 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);
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c
index 52f4e9e099cbf..e91f976f869dc 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c
@@ -1073,7 +1073,8 @@ 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;
@@ -1081,7 +1082,6 @@ 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) {
@@ -1092,27 +1092,31 @@ 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) {
@@ -1132,7 +1136,6 @@ 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);
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c
index b4fb90cc8f7d9..d626d91a188eb 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c
@@ -973,7 +973,8 @@ 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;
@@ -981,7 +982,6 @@ 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) {
@@ -992,26 +992,31 @@ 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) {
@@ -1031,7 +1036,6 @@ 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);
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c
index b005672f2f96b..b7b6e7674400e 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c
@@ -980,7 +980,8 @@ 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;
@@ -988,7 +989,6 @@ 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) {
@@ -999,26 +999,31 @@ 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) {
@@ -1038,7 +1043,6 @@ 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);
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c
index 5679a94d0815e..7013f58de9d40 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c
@@ -996,7 +996,8 @@ 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;
@@ -1004,7 +1005,6 @@ 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) {
@@ -1015,26 +1015,31 @@ 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) {
@@ -1054,7 +1059,6 @@ 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);
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v7_1.c b/drivers/gpu/drm/amd/amdgpu/sdma_v7_1.c
index f20e0fc3fc743..28237f6ae002c 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v7_1.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v7_1.c
@@ -986,7 +986,8 @@ 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;
@@ -994,7 +995,6 @@ 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) {
@@ -1005,26 +1005,31 @@ 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) {
@@ -1044,7 +1049,6 @@ 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);
diff --git a/drivers/gpu/drm/amd/amdgpu/si_dma.c b/drivers/gpu/drm/amd/amdgpu/si_dma.c
index 3e58feb2d5e4f..8362db058da2a 100644
--- a/drivers/gpu/drm/amd/amdgpu/si_dma.c
+++ b/drivers/gpu/drm/amd/amdgpu/si_dma.c
@@ -258,7 +258,8 @@ 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;
@@ -272,20 +273,25 @@ 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) {
@@ -301,7 +307,6 @@ 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);
--
2.53.0
^ permalink raw reply related [flat|nested] 8+ messages in thread
* [PATCH 3/7] drm/amdgpu: require a job to schedule an IB
2026-03-18 18:35 [PATCH 1/7] drm/amdgpu/job: use GFP_ATOMIC while in gpu reset Alex Deucher
2026-03-18 18:35 ` [PATCH 2/7] drm/amdgpu: switch all IPs to using job for IBs Alex Deucher
@ 2026-03-18 18:36 ` Alex Deucher
2026-03-18 18:36 ` [PATCH 4/7] drm/amdgpu: plumb timedout fence through to force completion Alex Deucher
` (3 subsequent siblings)
5 siblings, 0 replies; 8+ messages in thread
From: Alex Deucher @ 2026-03-18 18:36 UTC (permalink / raw)
To: amd-gfx; +Cc: Alex Deucher, Jesse Zhang
Remove the old direct submit path. This simplifies
the code.
v2: remove more local variables
Reviewed-by: Jesse Zhang <jesse.zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c | 2 +-
drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c | 113 ++++++++-------------
drivers/gpu/drm/amd/amdgpu/amdgpu_job.c | 5 +-
drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h | 3 +-
4 files changed, 45 insertions(+), 78 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
index 823b92005689a..4ec1058b7cdfa 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
@@ -685,7 +685,7 @@ 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");
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
index 80565c4a31bdf..55a9670f1dd90 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
@@ -103,8 +103,6 @@ void amdgpu_ib_free(struct amdgpu_ib *ib, struct dma_fence *f)
* amdgpu_ib_schedule - schedule an IB (Indirect Buffer) on the ring
*
* @ring: ring index the IB is associated with
- * @num_ibs: number of IBs to schedule
- * @ibs: IB objects to schedule
* @job: job to schedule
* @f: fence created during this submission
*
@@ -121,90 +119,70 @@ void amdgpu_ib_free(struct amdgpu_ib *ib, struct dma_fence *f)
* a CONST_IB), it will be put on the ring prior to the DE IB. Prior
* to SI there was just a DE IB.
*/
-int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned int 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)
{
struct amdgpu_device *adev = ring->adev;
- struct amdgpu_ib *ib = &ibs[0];
+ struct amdgpu_ib *ib;
struct dma_fence *tmp = NULL;
struct amdgpu_fence *af;
struct amdgpu_fence *vm_af;
bool need_ctx_switch;
- struct amdgpu_vm *vm;
uint64_t fence_ctx;
uint32_t status = 0, alloc_size;
unsigned int fence_flags = 0;
- bool secure, init_shadow;
- u64 shadow_va, csa_va, gds_va;
+ bool secure;
int vmid = AMDGPU_JOB_GET_VMID(job);
bool need_pipe_sync = false;
unsigned int cond_exec;
unsigned int i;
int r = 0;
- if (num_ibs == 0)
+ if (!job)
+ return -EINVAL;
+ if (job->num_ibs == 0)
return -EINVAL;
- /* ring tests don't use a job */
- if (job) {
- vm = job->vm;
- fence_ctx = job->base.s_fence ?
- job->base.s_fence->finished.context : 0;
- shadow_va = job->shadow_va;
- csa_va = job->csa_va;
- gds_va = job->gds_va;
- init_shadow = job->init_shadow;
- af = job->hw_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;
- } else {
- vm = NULL;
- fence_ctx = 0;
- shadow_va = 0;
- csa_va = 0;
- gds_va = 0;
- init_shadow = false;
- af = kzalloc(sizeof(*af), GFP_ATOMIC);
- if (!af)
- return -ENOMEM;
- }
+ ib = &job->ibs[0];
+ 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 */
+ vm_af->context = fence_ctx;
if (!ring->sched.ready) {
dev_err(adev->dev, "couldn't schedule ib on ring <%s>\n", ring->name);
- r = -EINVAL;
- goto free_fence;
+ return -EINVAL;
}
- if (vm && !job->vmid) {
+ if (job->vm && !job->vmid) {
dev_err(adev->dev, "VM IB without ID\n");
- r = -EINVAL;
- goto free_fence;
+ return -EINVAL;
}
if ((ib->flags & AMDGPU_IB_FLAGS_SECURE) &&
(!ring->funcs->secure_submission_supported)) {
dev_err(adev->dev, "secure submissions not supported on ring <%s>\n", ring->name);
- r = -EINVAL;
- goto free_fence;
+ return -EINVAL;
}
- alloc_size = ring->funcs->emit_frame_size + num_ibs *
+ alloc_size = ring->funcs->emit_frame_size + job->num_ibs *
ring->funcs->emit_ib_size;
r = amdgpu_ring_alloc(ring, alloc_size);
if (r) {
dev_err(adev->dev, "scheduling IB failed (%d).\n", r);
- goto free_fence;
+ return r;
}
need_ctx_switch = ring->current_ctx != fence_ctx;
- if (ring->funcs->emit_pipeline_sync && job &&
+ if (ring->funcs->emit_pipeline_sync &&
((tmp = amdgpu_sync_get_fence(&job->explicit_sync)) ||
need_ctx_switch || amdgpu_vm_need_pipeline_sync(ring, job))) {
@@ -216,14 +194,11 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned int num_ibs,
dma_fence_put(tmp);
}
- if (job) {
- vm_af = job->hw_vm_fence;
- /* VM sequence */
- vm_af->ib_wptr = ring->wptr;
- amdgpu_vm_flush(ring, job, need_pipe_sync);
- vm_af->ib_dw_size =
- amdgpu_ring_get_dw_distance(ring, vm_af->ib_wptr, ring->wptr);
- }
+ /* VM sequence */
+ vm_af->ib_wptr = ring->wptr;
+ amdgpu_vm_flush(ring, job, need_pipe_sync);
+ vm_af->ib_dw_size =
+ amdgpu_ring_get_dw_distance(ring, vm_af->ib_wptr, ring->wptr);
/* IB sequence */
af->ib_wptr = ring->wptr;
@@ -240,8 +215,8 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned int num_ibs,
ring->funcs->emit_wave_limit(ring, true);
if (ring->funcs->emit_gfx_shadow && adev->gfx.cp_gfx_shadow)
- amdgpu_ring_emit_gfx_shadow(ring, shadow_va, csa_va, gds_va,
- init_shadow, vmid);
+ amdgpu_ring_emit_gfx_shadow(ring, job->shadow_va, job->csa_va, job->gds_va,
+ job->init_shadow, vmid);
if (ring->funcs->init_cond_exec)
cond_exec = amdgpu_ring_init_cond_exec(ring,
@@ -255,7 +230,7 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned int num_ibs,
if (need_ctx_switch)
status |= AMDGPU_HAVE_CTX_SWITCH;
- if (job && ring->funcs->emit_cntxcntl) {
+ if (ring->funcs->emit_cntxcntl) {
status |= job->preamble_status;
status |= job->preemption_status;
amdgpu_ring_emit_cntxcntl(ring, status);
@@ -264,15 +239,15 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned int num_ibs,
/* Setup initial TMZiness and send it off.
*/
secure = false;
- if (job && ring->funcs->emit_frame_cntl) {
+ if (ring->funcs->emit_frame_cntl) {
secure = ib->flags & AMDGPU_IB_FLAGS_SECURE;
amdgpu_ring_emit_frame_cntl(ring, true, secure);
}
- for (i = 0; i < num_ibs; ++i) {
- ib = &ibs[i];
+ for (i = 0; i < job->num_ibs; ++i) {
+ ib = &job->ibs[i];
- if (job && ring->funcs->emit_frame_cntl) {
+ if (ring->funcs->emit_frame_cntl) {
if (secure != !!(ib->flags & AMDGPU_IB_FLAGS_SECURE)) {
amdgpu_ring_emit_frame_cntl(ring, false, secure);
secure = !secure;
@@ -284,7 +259,7 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned int num_ibs,
status &= ~AMDGPU_HAVE_CTX_SWITCH;
}
- if (job && ring->funcs->emit_frame_cntl)
+ if (ring->funcs->emit_frame_cntl)
amdgpu_ring_emit_frame_cntl(ring, false, secure);
amdgpu_device_invalidate_hdp(adev, ring);
@@ -296,7 +271,7 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned int num_ibs,
fence_flags |= AMDGPU_FENCE_FLAG_TC_WB_ONLY;
/* wrap the last IB with fence */
- if (job && job->uf_addr) {
+ if (job->uf_addr) {
amdgpu_ring_emit_fence(ring, job->uf_addr, job->uf_sequence,
fence_flags | AMDGPU_FENCE_FLAG_64BIT);
}
@@ -310,8 +285,7 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned int num_ibs,
amdgpu_fence_emit(ring, af, fence_flags);
*f = &af->base;
/* get a ref for the job */
- if (job)
- dma_fence_get(*f);
+ dma_fence_get(*f);
if (ring->funcs->insert_end)
ring->funcs->insert_end(ring);
@@ -319,7 +293,7 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned int num_ibs,
amdgpu_ring_patch_cond_exec(ring, cond_exec);
ring->current_ctx = fence_ctx;
- if (job && ring->funcs->emit_switch_buffer)
+ if (ring->funcs->emit_switch_buffer)
amdgpu_ring_emit_switch_buffer(ring);
if (ring->funcs->emit_wave_limit &&
@@ -333,11 +307,6 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned int num_ibs,
amdgpu_ring_commit(ring);
return 0;
-
-free_fence:
- if (!job)
- kfree(af);
- return r;
}
/**
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
index 95aa87b4406eb..cd0707737a29b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
@@ -377,7 +377,7 @@ 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;
@@ -447,8 +447,7 @@ 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,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
index ce5af137ee400..fafb876d73da1 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
@@ -575,8 +575,7 @@ 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);
--
2.53.0
^ permalink raw reply related [flat|nested] 8+ messages in thread
* [PATCH 4/7] drm/amdgpu: plumb timedout fence through to force completion
2026-03-18 18:35 [PATCH 1/7] drm/amdgpu/job: use GFP_ATOMIC while in gpu reset Alex Deucher
2026-03-18 18:35 ` [PATCH 2/7] drm/amdgpu: switch all IPs to using job for IBs Alex Deucher
2026-03-18 18:36 ` [PATCH 3/7] drm/amdgpu: require a job to schedule an IB Alex Deucher
@ 2026-03-18 18:36 ` Alex Deucher
2026-03-18 18:36 ` [PATCH 5/7] drm/amdgpu: simplify VCN reset helper Alex Deucher
` (2 subsequent siblings)
5 siblings, 0 replies; 8+ messages in thread
From: Alex Deucher @ 2026-03-18 18:36 UTC (permalink / raw)
To: amd-gfx; +Cc: Alex Deucher, Christian König
When 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
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
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 | 26 +++++++++++++++++----
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, 48 insertions(+), 20 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
index 63b702ec972bb..874ee1a1861c7 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
@@ -1937,7 +1937,7 @@ 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);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index dcae77b6c2723..f47e9d5034a75 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -5081,6 +5081,7 @@ 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);
@@ -5093,6 +5094,9 @@ 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];
@@ -5101,7 +5105,7 @@ 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);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
index d209591e3710a..0542d88f7159a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
@@ -547,7 +547,7 @@ 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 &&
@@ -662,16 +662,34 @@ 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
*
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
index fafb876d73da1..6ac66dac524ac 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
@@ -159,7 +159,8 @@ 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_ring_set_fence_errors_and_reemit(struct amdgpu_ring *ring,
struct amdgpu_fence *guilty_fence);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c
index 321310ba2c08e..fcd81242059e6 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c
@@ -600,10 +600,10 @@ 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);
}
}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
index 9d5cca7da1d9e..3a3bc0d370fa6 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
@@ -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;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
index 03d95dca93d75..46af6475c4899 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
@@ -1486,15 +1486,16 @@ 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);
@@ -1518,9 +1519,13 @@ 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
@@ -1556,7 +1561,7 @@ 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,
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c
index e78526a4e521e..a6aa72ec8fb19 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c
@@ -1669,7 +1669,7 @@ static int vcn_v4_0_3_reset_jpeg_post_helper(struct amdgpu_device *adev, int ins
for (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(
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_1.c b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_1.c
index c28c6aff17aaa..100ea1a914b4e 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_1.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_1.c
@@ -1332,7 +1332,7 @@ static int vcn_v5_0_1_reset_jpeg_post_helper(struct amdgpu_device *adev, int ins
for (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(
--
2.53.0
^ permalink raw reply related [flat|nested] 8+ messages in thread
* [PATCH 5/7] drm/amdgpu: simplify VCN reset helper
2026-03-18 18:35 [PATCH 1/7] drm/amdgpu/job: use GFP_ATOMIC while in gpu reset Alex Deucher
` (2 preceding siblings ...)
2026-03-18 18:36 ` [PATCH 4/7] drm/amdgpu: plumb timedout fence through to force completion Alex Deucher
@ 2026-03-18 18:36 ` Alex Deucher
2026-03-18 18:36 ` [PATCH 6/7] drm/amdgpu/cs: drop early return for guilty contexts Alex Deucher
2026-03-18 18:36 ` [PATCH 7/7] drm/amdgpu: Call drm_sched_increase_karma() for ring resets Alex Deucher
5 siblings, 0 replies; 8+ messages in thread
From: Alex Deucher @ 2026-03-18 18:36 UTC (permalink / raw)
To: amd-gfx; +Cc: Alex Deucher, Jesse Zhang
Remove the wrapper function.
Reviewed-by: Jesse Zhang <jesse.zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c | 41 ++++++++-----------------
1 file changed, 13 insertions(+), 28 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
index 46af6475c4899..6314a8824146e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
@@ -1485,19 +1485,27 @@ 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
@@ -1541,29 +1549,6 @@ 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)
{
--
2.53.0
^ permalink raw reply related [flat|nested] 8+ messages in thread
* [PATCH 6/7] drm/amdgpu/cs: drop early return for guilty contexts
2026-03-18 18:35 [PATCH 1/7] drm/amdgpu/job: use GFP_ATOMIC while in gpu reset Alex Deucher
` (3 preceding siblings ...)
2026-03-18 18:36 ` [PATCH 5/7] drm/amdgpu: simplify VCN reset helper Alex Deucher
@ 2026-03-18 18:36 ` Alex Deucher
2026-03-18 18:36 ` [PATCH 7/7] drm/amdgpu: Call drm_sched_increase_karma() for ring resets Alex Deucher
5 siblings, 0 replies; 8+ messages in thread
From: Alex Deucher @ 2026-03-18 18:36 UTC (permalink / raw)
To: amd-gfx; +Cc: Alex Deucher
The fences are already marked with an error and the
scheduling entities will reflect that.
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c | 5 -----
1 file changed, 5 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index f75f5079be80f..31200332312a9 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -60,11 +60,6 @@ static int amdgpu_cs_parser_init(struct amdgpu_cs_parser *p,
if (!p->ctx)
return -EINVAL;
- if (atomic_read(&p->ctx->guilty)) {
- amdgpu_ctx_put(p->ctx);
- return -ECANCELED;
- }
-
amdgpu_sync_create(&p->sync);
drm_exec_init(&p->exec, DRM_EXEC_INTERRUPTIBLE_WAIT |
DRM_EXEC_IGNORE_DUPLICATES, 0);
--
2.53.0
^ permalink raw reply related [flat|nested] 8+ messages in thread
* [PATCH 7/7] drm/amdgpu: Call drm_sched_increase_karma() for ring resets
2026-03-18 18:35 [PATCH 1/7] drm/amdgpu/job: use GFP_ATOMIC while in gpu reset Alex Deucher
` (4 preceding siblings ...)
2026-03-18 18:36 ` [PATCH 6/7] drm/amdgpu/cs: drop early return for guilty contexts Alex Deucher
@ 2026-03-18 18:36 ` Alex Deucher
5 siblings, 0 replies; 8+ messages in thread
From: Alex Deucher @ 2026-03-18 18:36 UTC (permalink / raw)
To: amd-gfx; +Cc: Alex Deucher, Jesse Zhang
Mark the entity as guilty so the ctx query IOCTL returns
the correct state. Align with adapter resets.
This only makes sense now that the CS IOCTL no longer
returns early on a guilty context. Without that patch,
this would break userspace.
Reviewed-by: Jesse Zhang <jesse.zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
drivers/gpu/drm/amd/amdgpu/amdgpu_job.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
index cd0707737a29b..dd9b649cf88e4 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
@@ -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 */
--
2.53.0
^ permalink raw reply related [flat|nested] 8+ messages in thread
end of thread, other threads:[~2026-03-18 18:36 UTC | newest]
Thread overview: 8+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2026-03-18 18:35 [PATCH 1/7] drm/amdgpu/job: use GFP_ATOMIC while in gpu reset Alex Deucher
2026-03-18 18:35 ` [PATCH 2/7] drm/amdgpu: switch all IPs to using job for IBs Alex Deucher
2026-03-18 18:36 ` [PATCH 3/7] drm/amdgpu: require a job to schedule an IB Alex Deucher
2026-03-18 18:36 ` [PATCH 4/7] drm/amdgpu: plumb timedout fence through to force completion Alex Deucher
2026-03-18 18:36 ` [PATCH 5/7] drm/amdgpu: simplify VCN reset helper Alex Deucher
2026-03-18 18:36 ` [PATCH 6/7] drm/amdgpu/cs: drop early return for guilty contexts Alex Deucher
2026-03-18 18:36 ` [PATCH 7/7] drm/amdgpu: Call drm_sched_increase_karma() for ring resets Alex Deucher
-- strict thread matches above, loose matches on Subject: below --
2026-03-16 18:16 [PATCH 1/7] drm/amdgpu/job: use GFP_ATOMIC while in gpu reset Alex Deucher
2026-03-16 18:16 ` [PATCH 3/7] drm/amdgpu: require a job to schedule an IB Alex Deucher
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox