On 2023-10-11 19:58, Matthew Brost wrote:
> Add scheduler wqueue ready, stop, and start helpers to hide the
> implementation details of the scheduler from the drivers.
>
> v2:
> - s/sched_wqueue/sched_wqueue (Luben)
> - Remove the extra white line after the return-statement (Luben)
> - update drm_sched_wqueue_ready comment (Luben)
>
> Signed-off-by: Matthew Brost <matthew.brost@xxxxxxxxx>
> Cc: Luben Tuikov <luben.tuikov@xxxxxxx>
Cc comes before S-O-B, but I can fix this when applying it, so don't worry about
this patch anymore. I'll also add Link: and so on, but this is all automated for
me so don't worry about it.
Reviewed-by: Luben Tuikov <luben.tuikov@xxxxxxx>
--
Regards,
Luben
> ---
> .../drm/amd/amdgpu/amdgpu_amdkfd_arcturus.c | 2 +-
> drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c | 15 +++----
> drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 12 +++---
> drivers/gpu/drm/msm/adreno/adreno_device.c | 6 ++-
> drivers/gpu/drm/scheduler/sched_main.c | 39 ++++++++++++++++++-
> include/drm/gpu_scheduler.h | 3 ++
> 6 files changed, 59 insertions(+), 18 deletions(-)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_arcturus.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_arcturus.c
> index 625db444df1c..10d56979fe3b 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_arcturus.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_arcturus.c
> @@ -290,7 +290,7 @@ static int suspend_resume_compute_scheduler(struct amdgpu_device *adev, bool sus
> for (i = 0; i < adev->gfx.num_compute_rings; i++) {
> struct amdgpu_ring *ring = &adev->gfx.compute_ring[i];
>
> - if (!(ring && ring->sched.thread))
> + if (!(ring && drm_sched_wqueue_ready(&ring->sched)))
> continue;
>
> /* stop secheduler and drain ring. */
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
> index a4faea4fa0b5..a4c0bb358db7 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
> @@ -1659,9 +1659,9 @@ static int amdgpu_debugfs_test_ib_show(struct seq_file *m, void *unused)
> for (i = 0; i < AMDGPU_MAX_RINGS; i++) {
> struct amdgpu_ring *ring = adev->rings[i];
>
> - if (!ring || !ring->sched.thread)
> + if (!ring || !drm_sched_wqueue_ready(&ring->sched))
> continue;
> - kthread_park(ring->sched.thread);
> + drm_sched_wqueue_stop(&ring->sched);
> }
>
> seq_puts(m, "run ib test:\n");
> @@ -1675,9 +1675,9 @@ static int amdgpu_debugfs_test_ib_show(struct seq_file *m, void *unused)
> for (i = 0; i < AMDGPU_MAX_RINGS; i++) {
> struct amdgpu_ring *ring = adev->rings[i];
>
> - if (!ring || !ring->sched.thread)
> + if (!ring || !drm_sched_wqueue_ready(&ring->sched))
> continue;
> - kthread_unpark(ring->sched.thread);
> + drm_sched_wqueue_start(&ring->sched);
> }
>
> up_write(&adev->reset_domain->sem);
> @@ -1897,7 +1897,8 @@ static int amdgpu_debugfs_ib_preempt(void *data, u64 val)
>
> ring = adev->rings[val];
>
> - if (!ring || !ring->funcs->preempt_ib || !ring->sched.thread)
> + if (!ring || !ring->funcs->preempt_ib ||
> + !drm_sched_wqueue_ready(&ring->sched))
> return -EINVAL;
>
> /* the last preemption failed */
> @@ -1915,7 +1916,7 @@ static int amdgpu_debugfs_ib_preempt(void *data, u64 val)
> goto pro_end;
>
> /* stop the scheduler */
> - kthread_park(ring->sched.thread);
> + drm_sched_wqueue_stop(&ring->sched);
>
> /* preempt the IB */
> r = amdgpu_ring_preempt_ib(ring);
> @@ -1949,7 +1950,7 @@ static int amdgpu_debugfs_ib_preempt(void *data, u64 val)
>
> failure:
> /* restart the scheduler */
> - kthread_unpark(ring->sched.thread);
> + drm_sched_wqueue_start(&ring->sched);
>
> up_read(&adev->reset_domain->sem);
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
> index 2b8356699f23..b1aafe815f28 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
> @@ -4588,7 +4588,7 @@ bool amdgpu_device_has_job_running(struct amdgpu_device *adev)
> for (i = 0; i < AMDGPU_MAX_RINGS; ++i) {
> struct amdgpu_ring *ring = adev->rings[i];
>
> - if (!ring || !ring->sched.thread)
> + if (!ring || !drm_sched_wqueue_ready(&ring->sched))
> continue;
>
> spin_lock(&ring->sched.job_list_lock);
> @@ -4727,7 +4727,7 @@ int amdgpu_device_pre_asic_reset(struct amdgpu_device *adev,
> for (i = 0; i < AMDGPU_MAX_RINGS; ++i) {
> struct amdgpu_ring *ring = adev->rings[i];
>
> - if (!ring || !ring->sched.thread)
> + if (!ring || !drm_sched_wqueue_ready(&ring->sched))
> continue;
>
> /* Clear job fence from fence drv to avoid force_completion
> @@ -5266,7 +5266,7 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
> for (i = 0; i < AMDGPU_MAX_RINGS; ++i) {
> struct amdgpu_ring *ring = tmp_adev->rings[i];
>
> - if (!ring || !ring->sched.thread)
> + if (!ring || !drm_sched_wqueue_ready(&ring->sched))
> continue;
>
> drm_sched_stop(&ring->sched, job ? &job->base : NULL);
> @@ -5341,7 +5341,7 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
> for (i = 0; i < AMDGPU_MAX_RINGS; ++i) {
> struct amdgpu_ring *ring = tmp_adev->rings[i];
>
> - if (!ring || !ring->sched.thread)
> + if (!ring || !drm_sched_wqueue_ready(&ring->sched))
> continue;
>
> drm_sched_start(&ring->sched, true);
> @@ -5667,7 +5667,7 @@ pci_ers_result_t amdgpu_pci_error_detected(struct pci_dev *pdev, pci_channel_sta
> for (i = 0; i < AMDGPU_MAX_RINGS; ++i) {
> struct amdgpu_ring *ring = adev->rings[i];
>
> - if (!ring || !ring->sched.thread)
> + if (!ring || !drm_sched_wqueue_ready(&ring->sched))
> continue;
>
> drm_sched_stop(&ring->sched, NULL);
> @@ -5795,7 +5795,7 @@ void amdgpu_pci_resume(struct pci_dev *pdev)
> for (i = 0; i < AMDGPU_MAX_RINGS; ++i) {
> struct amdgpu_ring *ring = adev->rings[i];
>
> - if (!ring || !ring->sched.thread)
> + if (!ring || !drm_sched_wqueue_ready(&ring->sched))
> continue;
>
> drm_sched_start(&ring->sched, true);
> diff --git a/drivers/gpu/drm/msm/adreno/adreno_device.c b/drivers/gpu/drm/msm/adreno/adreno_device.c
> index fa527935ffd4..8fa9ce3746b6 100644
> --- a/drivers/gpu/drm/msm/adreno/adreno_device.c
> +++ b/drivers/gpu/drm/msm/adreno/adreno_device.c
> @@ -809,7 +809,8 @@ static void suspend_scheduler(struct msm_gpu *gpu)
> */
> for (i = 0; i < gpu->nr_rings; i++) {
> struct drm_gpu_scheduler *sched = &gpu->rb[i]->sched;
> - kthread_park(sched->thread);
> +
> + drm_sched_wqueue_stop(sched);
> }
> }
>
> @@ -819,7 +820,8 @@ static void resume_scheduler(struct msm_gpu *gpu)
>
> for (i = 0; i < gpu->nr_rings; i++) {
> struct drm_gpu_scheduler *sched = &gpu->rb[i]->sched;
> - kthread_unpark(sched->thread);
> +
> + drm_sched_wqueue_start(sched);
> }
> }
>
> diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c
> index 5a3a622fc672..6f2f7dd4ba0a 100644
> --- a/drivers/gpu/drm/scheduler/sched_main.c
> +++ b/drivers/gpu/drm/scheduler/sched_main.c
> @@ -439,7 +439,7 @@ void drm_sched_stop(struct drm_gpu_scheduler *sched, struct drm_sched_job *bad)
> {
> struct drm_sched_job *s_job, *tmp;
>
> - kthread_park(sched->thread);
> + drm_sched_wqueue_stop(sched);
>
> /*
> * Reinsert back the bad job here - now it's safe as
> @@ -552,7 +552,7 @@ void drm_sched_start(struct drm_gpu_scheduler *sched, bool full_recovery)
> spin_unlock(&sched->job_list_lock);
> }
>
> - kthread_unpark(sched->thread);
> + drm_sched_wqueue_start(sched);
> }
> EXPORT_SYMBOL(drm_sched_start);
>
> @@ -1206,3 +1206,38 @@ void drm_sched_increase_karma(struct drm_sched_job *bad)
> }
> }
> EXPORT_SYMBOL(drm_sched_increase_karma);
> +
> +/**
> + * drm_sched_wqueue_ready - Is the scheduler ready for submission
> + *
> + * @sched: scheduler instance
> + *
> + * Returns true if submission is ready
> + */
> +bool drm_sched_wqueue_ready(struct drm_gpu_scheduler *sched)
> +{
> + return !!sched->thread;
> +}
> +EXPORT_SYMBOL(drm_sched_wqueue_ready);
> +
> +/**
> + * drm_sched_wqueue_stop - stop scheduler submission
> + *
> + * @sched: scheduler instance
> + */
> +void drm_sched_wqueue_stop(struct drm_gpu_scheduler *sched)
> +{
> + kthread_park(sched->thread);
> +}
> +EXPORT_SYMBOL(drm_sched_wqueue_stop);
> +
> +/**
> + * drm_sched_wqueue_start - start scheduler submission
> + *
> + * @sched: scheduler instance
> + */
> +void drm_sched_wqueue_start(struct drm_gpu_scheduler *sched)
> +{
> + kthread_unpark(sched->thread);
> +}
> +EXPORT_SYMBOL(drm_sched_wqueue_start);
> diff --git a/include/drm/gpu_scheduler.h b/include/drm/gpu_scheduler.h
> index f9544d9b670d..38578fe74573 100644
> --- a/include/drm/gpu_scheduler.h
> +++ b/include/drm/gpu_scheduler.h
> @@ -550,6 +550,9 @@ void drm_sched_entity_modify_sched(struct drm_sched_entity *entity,
>
> void drm_sched_job_cleanup(struct drm_sched_job *job);
> void drm_sched_wakeup_if_can_queue(struct drm_gpu_scheduler *sched);
> +bool drm_sched_wqueue_ready(struct drm_gpu_scheduler *sched);
> +void drm_sched_wqueue_stop(struct drm_gpu_scheduler *sched);
> +void drm_sched_wqueue_start(struct drm_gpu_scheduler *sched);
> void drm_sched_stop(struct drm_gpu_scheduler *sched, struct drm_sched_job *bad);
> void drm_sched_start(struct drm_gpu_scheduler *sched, bool full_recovery);
> void drm_sched_resubmit_jobs(struct drm_gpu_scheduler *sched);
