Among the scheduler's statuses, the only one that indicates an error is
DRM_GPU_SCHED_STAT_ENODEV. Any status other than DRM_GPU_SCHED_STAT_ENODEV
signifies that the operation succeeded and the GPU is in a nominal state.
However, to provide more information about the GPU's status, it is needed
to convey more information than just "OK".
Therefore, rename DRM_GPU_SCHED_STAT_NOMINAL to
DRM_GPU_SCHED_STAT_RESET, which better communicates the meaning of this
status. The status DRM_GPU_SCHED_STAT_RESET indicates that the GPU has
hung, but it has been successfully reset and is now in a nominal state
again.
Signed-off-by: Maíra Canal <mca...@igalia.com>
Reviewed-by: Philipp Stanner <pha...@kernel.org>
---
To: Min Ma <min...@amd.com>
To: Lizhi Hou <lizhi....@amd.com>
To: Oded Gabbay <ogab...@kernel.org>
To: Frank Binns <frank.bi...@imgtec.com>
To: Matt Coster <matt.cos...@imgtec.com>
To: Qiang Yu <yuq...@gmail.com>
To: Lyude Paul <ly...@redhat.com>
To: Alex Deucher <alexander.deuc...@amd.com>
To: Christian König <christian.koe...@amd.com>
---
drivers/accel/amdxdna/aie2_ctx.c | 2 +-
drivers/gpu/drm/amd/amdgpu/amdgpu_job.c | 2 +-
drivers/gpu/drm/etnaviv/etnaviv_sched.c | 4 ++--
drivers/gpu/drm/imagination/pvr_queue.c | 4 ++--
drivers/gpu/drm/lima/lima_sched.c | 6 +++---
drivers/gpu/drm/nouveau/nouveau_exec.c | 2 +-
drivers/gpu/drm/nouveau/nouveau_sched.c | 2 +-
drivers/gpu/drm/panfrost/panfrost_job.c | 6 +++---
drivers/gpu/drm/panthor/panthor_mmu.c | 2 +-
drivers/gpu/drm/panthor/panthor_sched.c | 2 +-
drivers/gpu/drm/scheduler/sched_main.c | 2 +-
drivers/gpu/drm/scheduler/tests/mock_scheduler.c | 2 +-
drivers/gpu/drm/v3d/v3d_sched.c | 6 +++---
drivers/gpu/drm/xe/xe_guc_submit.c | 6 +++---
include/drm/gpu_scheduler.h | 4 ++--
15 files changed, 26 insertions(+), 26 deletions(-)
diff --git a/drivers/accel/amdxdna/aie2_ctx.c b/drivers/accel/amdxdna/aie2_ctx.c
index
f20999f2d66864fd4a6b7069e866727c37befb39..2cff5419bd2facb59ff5df6388aba0512fd45d5c
100644
--- a/drivers/accel/amdxdna/aie2_ctx.c
+++ b/drivers/accel/amdxdna/aie2_ctx.c
@@ -361,7 +361,7 @@ aie2_sched_job_timedout(struct drm_sched_job *sched_job)
aie2_hwctx_restart(xdna, hwctx);
mutex_unlock(&xdna->dev_lock);
- return DRM_GPU_SCHED_STAT_NOMINAL;
+ return DRM_GPU_SCHED_STAT_RESET;
}
static const struct drm_sched_backend_ops sched_ops = {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
index
87f7040d8a2bb1af2aa46a051f10df3074974672..ec73cf3a9024121bcd3110dcfe6ffc0a37943862
100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
@@ -175,7 +175,7 @@ static enum drm_gpu_sched_stat amdgpu_job_timedout(struct
drm_sched_job *s_job)
exit:
amdgpu_vm_put_task_info(ti);
drm_dev_exit(idx);
- return DRM_GPU_SCHED_STAT_NOMINAL;
+ return DRM_GPU_SCHED_STAT_RESET;
}
int amdgpu_job_alloc(struct amdgpu_device *adev, struct amdgpu_vm *vm,
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_sched.c
b/drivers/gpu/drm/etnaviv/etnaviv_sched.c
index
76a3a3e517d8d9f654fb6b9e98e72910795cfc7a..7146069a98492f5fab2a49d96e2054f649e1fe3d
100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_sched.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_sched.c
@@ -86,11 +86,11 @@ static enum drm_gpu_sched_stat
etnaviv_sched_timedout_job(struct drm_sched_job
drm_sched_resubmit_jobs(&gpu->sched);
drm_sched_start(&gpu->sched, 0);
- return DRM_GPU_SCHED_STAT_NOMINAL;
+ return DRM_GPU_SCHED_STAT_RESET;
out_no_timeout:
list_add(&sched_job->list, &sched_job->sched->pending_list);
- return DRM_GPU_SCHED_STAT_NOMINAL;
+ return DRM_GPU_SCHED_STAT_RESET;
}
static void etnaviv_sched_free_job(struct drm_sched_job *sched_job)
diff --git a/drivers/gpu/drm/imagination/pvr_queue.c
b/drivers/gpu/drm/imagination/pvr_queue.c
index
5a41ee79fed646a86344cd16e78efdb45ff02e43..fc415dd0d7a73631bd4144c9f35b9b294c625a12
100644
--- a/drivers/gpu/drm/imagination/pvr_queue.c
+++ b/drivers/gpu/drm/imagination/pvr_queue.c
@@ -803,7 +803,7 @@ static void pvr_queue_start(struct pvr_queue *queue)
* the scheduler, and re-assign parent fences in the middle.
*
* Return:
- * * DRM_GPU_SCHED_STAT_NOMINAL.
+ * * DRM_GPU_SCHED_STAT_RESET.
*/
static enum drm_gpu_sched_stat
pvr_queue_timedout_job(struct drm_sched_job *s_job)
@@ -854,7 +854,7 @@ pvr_queue_timedout_job(struct drm_sched_job *s_job)
drm_sched_start(sched, 0);
- return DRM_GPU_SCHED_STAT_NOMINAL;
+ return DRM_GPU_SCHED_STAT_RESET;
}
/**
diff --git a/drivers/gpu/drm/lima/lima_sched.c
b/drivers/gpu/drm/lima/lima_sched.c
index
954f4325b859b2977a2cc608a99a6ebb642f1000..739e8c6c6d909aa4263bad8a12ec07f0c6607bb2
100644
--- a/drivers/gpu/drm/lima/lima_sched.c
+++ b/drivers/gpu/drm/lima/lima_sched.c
@@ -412,7 +412,7 @@ static enum drm_gpu_sched_stat
lima_sched_timedout_job(struct drm_sched_job *job
*/
if (dma_fence_is_signaled(task->fence)) {
DRM_WARN("%s spurious timeout\n", lima_ip_name(ip));
- return DRM_GPU_SCHED_STAT_NOMINAL;
+ return DRM_GPU_SCHED_STAT_RESET;
}
/*
@@ -429,7 +429,7 @@ static enum drm_gpu_sched_stat
lima_sched_timedout_job(struct drm_sched_job *job
if (dma_fence_is_signaled(task->fence)) {
DRM_WARN("%s unexpectedly high interrupt latency\n",
lima_ip_name(ip));
- return DRM_GPU_SCHED_STAT_NOMINAL;
+ return DRM_GPU_SCHED_STAT_RESET;
}
/*
@@ -467,7 +467,7 @@ static enum drm_gpu_sched_stat
lima_sched_timedout_job(struct drm_sched_job *job
drm_sched_resubmit_jobs(&pipe->base);
drm_sched_start(&pipe->base, 0);
- return DRM_GPU_SCHED_STAT_NOMINAL;
+ return DRM_GPU_SCHED_STAT_RESET;
}
static void lima_sched_free_job(struct drm_sched_job *job)
diff --git a/drivers/gpu/drm/nouveau/nouveau_exec.c
b/drivers/gpu/drm/nouveau/nouveau_exec.c
index
41b7c608c9054869ddadfe17c96100266e44c254..edbbda78bac90432c4877aa39a9587cf976705c7
100644
--- a/drivers/gpu/drm/nouveau/nouveau_exec.c
+++ b/drivers/gpu/drm/nouveau/nouveau_exec.c
@@ -189,7 +189,7 @@ nouveau_exec_job_timeout(struct nouveau_job *job)
NV_PRINTK(warn, job->cli, "job timeout, channel %d killed!\n",
chan->chid);
- return DRM_GPU_SCHED_STAT_NOMINAL;
+ return DRM_GPU_SCHED_STAT_RESET;
}
static const struct nouveau_job_ops nouveau_exec_job_ops = {
diff --git a/drivers/gpu/drm/nouveau/nouveau_sched.c
b/drivers/gpu/drm/nouveau/nouveau_sched.c
index
7d9c3418e76b6eb90ccfeea345d60e3d67118733..0cc0bc9f9952b1cfbc4015cb2c292fbf383459c9
100644
--- a/drivers/gpu/drm/nouveau/nouveau_sched.c
+++ b/drivers/gpu/drm/nouveau/nouveau_sched.c
@@ -370,7 +370,7 @@ nouveau_sched_timedout_job(struct drm_sched_job *sched_job)
{
struct drm_gpu_scheduler *sched = sched_job->sched;
struct nouveau_job *job = to_nouveau_job(sched_job);
- enum drm_gpu_sched_stat stat = DRM_GPU_SCHED_STAT_NOMINAL;
+ enum drm_gpu_sched_stat stat = DRM_GPU_SCHED_STAT_RESET;
drm_sched_stop(sched, sched_job);
diff --git a/drivers/gpu/drm/panfrost/panfrost_job.c
b/drivers/gpu/drm/panfrost/panfrost_job.c
index
5657106c2f7d0a0ca6162850767f58f3200cce13..afcffe7f8fe9e11f84e4ab7e8f5a72f7bf583690
100644
--- a/drivers/gpu/drm/panfrost/panfrost_job.c
+++ b/drivers/gpu/drm/panfrost/panfrost_job.c
@@ -755,7 +755,7 @@ static enum drm_gpu_sched_stat panfrost_job_timedout(struct
drm_sched_job
* spurious. Bail out.
*/
if (dma_fence_is_signaled(job->done_fence))
- return DRM_GPU_SCHED_STAT_NOMINAL;
+ return DRM_GPU_SCHED_STAT_RESET;
/*
* Panfrost IRQ handler may take a long time to process an interrupt
@@ -770,7 +770,7 @@ static enum drm_gpu_sched_stat panfrost_job_timedout(struct
drm_sched_job
if (dma_fence_is_signaled(job->done_fence)) {
dev_warn(pfdev->dev, "unexpectedly high interrupt latency\n");
- return DRM_GPU_SCHED_STAT_NOMINAL;
+ return DRM_GPU_SCHED_STAT_RESET;
}
dev_err(pfdev->dev, "gpu sched timeout, js=%d, config=0x%x,
status=0x%x, head=0x%x, tail=0x%x, sched_job=%p",
@@ -786,7 +786,7 @@ static enum drm_gpu_sched_stat panfrost_job_timedout(struct
drm_sched_job
atomic_set(&pfdev->reset.pending, 1);
panfrost_reset(pfdev, sched_job);
- return DRM_GPU_SCHED_STAT_NOMINAL;
+ return DRM_GPU_SCHED_STAT_RESET;
}
static void panfrost_reset_work(struct work_struct *work)
diff --git a/drivers/gpu/drm/panthor/panthor_mmu.c
b/drivers/gpu/drm/panthor/panthor_mmu.c
index
ed3712f8d6a9136b99c49d687ab84918959edd95..4140f697ba5af5769492d3bbb378e18aec8ade98
100644
--- a/drivers/gpu/drm/panthor/panthor_mmu.c
+++ b/drivers/gpu/drm/panthor/panthor_mmu.c
@@ -2259,7 +2259,7 @@ static enum drm_gpu_sched_stat
panthor_vm_bind_timedout_job(struct drm_sched_job *sched_job)
{
WARN(1, "VM_BIND ops are synchronous for now, there should be no
timeout!");
- return DRM_GPU_SCHED_STAT_NOMINAL;
+ return DRM_GPU_SCHED_STAT_RESET;
}
static const struct drm_sched_backend_ops panthor_vm_bind_ops = {
diff --git a/drivers/gpu/drm/panthor/panthor_sched.c
b/drivers/gpu/drm/panthor/panthor_sched.c
index
a2248f692a030c1c84869b9a1948ad1cb0c0b490..8f17394cc82aad9eaf01e473cd9d3dea46fa3d61
100644
--- a/drivers/gpu/drm/panthor/panthor_sched.c
+++ b/drivers/gpu/drm/panthor/panthor_sched.c
@@ -3241,7 +3241,7 @@ queue_timedout_job(struct drm_sched_job *sched_job)
queue_start(queue);
- return DRM_GPU_SCHED_STAT_NOMINAL;
+ return DRM_GPU_SCHED_STAT_RESET;
}
static void queue_free_job(struct drm_sched_job *sched_job)
diff --git a/drivers/gpu/drm/scheduler/sched_main.c
b/drivers/gpu/drm/scheduler/sched_main.c
index
d94270cf8bf5c8d7b8ddb17db12118a4c55ca43c..4f2593f0c7d98a20a5d22f05e31c6929ec1cd8f9
100644
--- a/drivers/gpu/drm/scheduler/sched_main.c
+++ b/drivers/gpu/drm/scheduler/sched_main.c
@@ -527,7 +527,7 @@ static void drm_sched_job_timedout(struct work_struct *work)
{
struct drm_gpu_scheduler *sched;
struct drm_sched_job *job;
- enum drm_gpu_sched_stat status = DRM_GPU_SCHED_STAT_NOMINAL;
+ enum drm_gpu_sched_stat status = DRM_GPU_SCHED_STAT_RESET;
sched = container_of(work, struct drm_gpu_scheduler, work_tdr.work);
diff --git a/drivers/gpu/drm/scheduler/tests/mock_scheduler.c
b/drivers/gpu/drm/scheduler/tests/mock_scheduler.c
index
0d1d57213e058b1c0db1fbf308723216ce80bef3..ad96e8db13c414cd773654397b34f83943c15d74
100644
--- a/drivers/gpu/drm/scheduler/tests/mock_scheduler.c
+++ b/drivers/gpu/drm/scheduler/tests/mock_scheduler.c
@@ -231,7 +231,7 @@ mock_sched_timedout_job(struct drm_sched_job *sched_job)
drm_sched_job_cleanup(sched_job);
/* Mock job itself is freed by the kunit framework. */
- return DRM_GPU_SCHED_STAT_NOMINAL;
+ return DRM_GPU_SCHED_STAT_RESET;
}
static void mock_sched_free_job(struct drm_sched_job *sched_job)
diff --git a/drivers/gpu/drm/v3d/v3d_sched.c b/drivers/gpu/drm/v3d/v3d_sched.c
index
35f131a46d0701cc8040d3b9654595a2bc260eab..e2b7f24d528e773968daea0f5b31c869584bb692
100644
--- a/drivers/gpu/drm/v3d/v3d_sched.c
+++ b/drivers/gpu/drm/v3d/v3d_sched.c
@@ -741,7 +741,7 @@ v3d_gpu_reset_for_timeout(struct v3d_dev *v3d, struct
drm_sched_job *sched_job)
mutex_unlock(&v3d->reset_lock);
- return DRM_GPU_SCHED_STAT_NOMINAL;
+ return DRM_GPU_SCHED_STAT_RESET;
}
static void
@@ -773,7 +773,7 @@ v3d_cl_job_timedout(struct drm_sched_job *sched_job, enum
v3d_queue q,
*timedout_ctra = ctra;
v3d_sched_skip_reset(sched_job);
- return DRM_GPU_SCHED_STAT_NOMINAL;
+ return DRM_GPU_SCHED_STAT_RESET;
}
return v3d_gpu_reset_for_timeout(v3d, sched_job);
@@ -819,7 +819,7 @@ v3d_csd_job_timedout(struct drm_sched_job *sched_job)
job->timedout_batches = batches;
v3d_sched_skip_reset(sched_job);
- return DRM_GPU_SCHED_STAT_NOMINAL;
+ return DRM_GPU_SCHED_STAT_RESET;
}
return v3d_gpu_reset_for_timeout(v3d, sched_job);
diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c
b/drivers/gpu/drm/xe/xe_guc_submit.c
index
df7a5a4eec74cc97c9934fb3ad383a2bae1d9a3d..ca2344b538c30b26542742ae9ea145836c940bbf
100644
--- a/drivers/gpu/drm/xe/xe_guc_submit.c
+++ b/drivers/gpu/drm/xe/xe_guc_submit.c
@@ -1096,7 +1096,7 @@ guc_exec_queue_timedout_job(struct drm_sched_job *drm_job)
xe_sched_add_pending_job(sched, job);
xe_sched_submission_start(sched);
- return DRM_GPU_SCHED_STAT_NOMINAL;
+ return DRM_GPU_SCHED_STAT_RESET;
}
/* Kill the run_job entry point */
@@ -1265,7 +1265,7 @@ guc_exec_queue_timedout_job(struct drm_sched_job *drm_job)
/* Start fence signaling */
xe_hw_fence_irq_start(q->fence_irq);
- return DRM_GPU_SCHED_STAT_NOMINAL;
+ return DRM_GPU_SCHED_STAT_RESET;
sched_enable:
enable_scheduling(q);
@@ -1278,7 +1278,7 @@ guc_exec_queue_timedout_job(struct drm_sched_job *drm_job)
xe_sched_add_pending_job(sched, job);
xe_sched_submission_start(sched);
- return DRM_GPU_SCHED_STAT_NOMINAL;
+ return DRM_GPU_SCHED_STAT_RESET;
}
static void __guc_exec_queue_fini_async(struct work_struct *w)
diff --git a/include/drm/gpu_scheduler.h b/include/drm/gpu_scheduler.h
index
190844370f48aee6ac9734ddfad65c8718f0a52a..ed300920996a8d830af5a4c011173ae4c25919dc
100644
--- a/include/drm/gpu_scheduler.h
+++ b/include/drm/gpu_scheduler.h
@@ -391,12 +391,12 @@ struct drm_sched_job {
* enum drm_gpu_sched_stat - the scheduler's status
*
* @DRM_GPU_SCHED_STAT_NONE: Reserved. Do not use.
- * @DRM_GPU_SCHED_STAT_NOMINAL: Operation succeeded.
+ * @DRM_GPU_SCHED_STAT_RESET: The GPU hung and successfully reset.
* @DRM_GPU_SCHED_STAT_ENODEV: Error: Device is not available anymore.
*/
enum drm_gpu_sched_stat {
DRM_GPU_SCHED_STAT_NONE,
- DRM_GPU_SCHED_STAT_NOMINAL,
+ DRM_GPU_SCHED_STAT_RESET,
DRM_GPU_SCHED_STAT_ENODEV,
};
--
2.50.0
