From 1f8644d56e91f1c3cbeb1a36c3a998397d06b9dc Mon Sep 17 00:00:00 2001 From: Lukasz Luba Date: Thu, 21 Jan 2021 17:04:45 +0000 Subject: drm/panfrost: Add governor data with pre-defined thresholds The simple_ondemand devfreq governor uses two thresholds to decide about the frequency change: upthreshold, downdifferential. These two tunable change the behavior of the governor decision, e.g. how fast to increase the frequency or how rapidly limit the frequency. This patch adds needed governor data with thresholds values gathered experimentally in different workloads. Signed-off-by: Lukasz Luba Reviewed-by: Steven Price Signed-off-by: Steven Price Link: https://patchwork.freedesktop.org/patch/msgid/20210121170445.19761-1-lukasz.luba@arm.com --- drivers/gpu/drm/panfrost/panfrost_devfreq.c | 10 +++++++++- drivers/gpu/drm/panfrost/panfrost_devfreq.h | 2 ++ 2 files changed, 11 insertions(+), 1 deletion(-) (limited to 'drivers/gpu/drm/panfrost') diff --git a/drivers/gpu/drm/panfrost/panfrost_devfreq.c b/drivers/gpu/drm/panfrost/panfrost_devfreq.c index 56b3f5935703..7c5ffc81dce1 100644 --- a/drivers/gpu/drm/panfrost/panfrost_devfreq.c +++ b/drivers/gpu/drm/panfrost/panfrost_devfreq.c @@ -130,8 +130,16 @@ int panfrost_devfreq_init(struct panfrost_device *pfdev) panfrost_devfreq_profile.initial_freq = cur_freq; dev_pm_opp_put(opp); + /* + * Setup default thresholds for the simple_ondemand governor. + * The values are chosen based on experiments. + */ + pfdevfreq->gov_data.upthreshold = 45; + pfdevfreq->gov_data.downdifferential = 5; + devfreq = devm_devfreq_add_device(dev, &panfrost_devfreq_profile, - DEVFREQ_GOV_SIMPLE_ONDEMAND, NULL); + DEVFREQ_GOV_SIMPLE_ONDEMAND, + &pfdevfreq->gov_data); if (IS_ERR(devfreq)) { DRM_DEV_ERROR(dev, "Couldn't initialize GPU devfreq\n"); ret = PTR_ERR(devfreq); diff --git a/drivers/gpu/drm/panfrost/panfrost_devfreq.h b/drivers/gpu/drm/panfrost/panfrost_devfreq.h index db6ea48e21f9..1e2a4de941aa 100644 --- a/drivers/gpu/drm/panfrost/panfrost_devfreq.h +++ b/drivers/gpu/drm/panfrost/panfrost_devfreq.h @@ -4,6 +4,7 @@ #ifndef __PANFROST_DEVFREQ_H__ #define __PANFROST_DEVFREQ_H__ +#include #include #include @@ -17,6 +18,7 @@ struct panfrost_devfreq { struct devfreq *devfreq; struct opp_table *regulators_opp_table; struct thermal_cooling_device *cooling; + struct devfreq_simple_ondemand_data gov_data; bool opp_of_table_added; ktime_t busy_time; -- cgit v1.2.3 From a6a1f036c74e3d2a3a56b3140492c7c3ecb879f3 Mon Sep 17 00:00:00 2001 From: Luben Tuikov Date: Wed, 20 Jan 2021 15:09:59 -0500 Subject: drm/scheduler: Job timeout handler returns status (v3) MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This patch does not change current behaviour. The driver's job timeout handler now returns status indicating back to the DRM layer whether the device (GPU) is no longer available, such as after it's been unplugged, or whether all is normal, i.e. current behaviour. All drivers which make use of the drm_sched_backend_ops' .timedout_job() callback have been accordingly renamed and return the would've-been default value of DRM_GPU_SCHED_STAT_NOMINAL to restart the task's timeout timer--this is the old behaviour, and is preserved by this patch. v2: Use enum as the status of a driver's job timeout callback method. v3: Return scheduler/device information, rather than task information. Cc: Alexander Deucher Cc: Andrey Grodzovsky Cc: Christian König Cc: Daniel Vetter Cc: Lucas Stach Cc: Russell King Cc: Christian Gmeiner Cc: Qiang Yu Cc: Rob Herring Cc: Tomeu Vizoso Cc: Steven Price Cc: Alyssa Rosenzweig Cc: Eric Anholt Reported-by: kernel test robot Signed-off-by: Luben Tuikov Acked-by: Alyssa Rosenzweig Acked-by: Christian König Acked-by: Steven Price Signed-off-by: Christian König Link: https://patchwork.freedesktop.org/patch/415095/ --- drivers/gpu/drm/amd/amdgpu/amdgpu_job.c | 6 ++++-- drivers/gpu/drm/etnaviv/etnaviv_sched.c | 7 ++++++- drivers/gpu/drm/lima/lima_sched.c | 4 +++- drivers/gpu/drm/panfrost/panfrost_job.c | 9 ++++++--- drivers/gpu/drm/scheduler/sched_main.c | 4 +--- drivers/gpu/drm/v3d/v3d_sched.c | 32 +++++++++++++++++--------------- include/drm/gpu_scheduler.h | 18 +++++++++++++++--- 7 files changed, 52 insertions(+), 28 deletions(-) (limited to 'drivers/gpu/drm/panfrost') diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c index ff48101bab55..759b34799221 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c @@ -28,7 +28,7 @@ #include "amdgpu.h" #include "amdgpu_trace.h" -static void amdgpu_job_timedout(struct drm_sched_job *s_job) +static enum drm_gpu_sched_stat amdgpu_job_timedout(struct drm_sched_job *s_job) { struct amdgpu_ring *ring = to_amdgpu_ring(s_job->sched); struct amdgpu_job *job = to_amdgpu_job(s_job); @@ -41,7 +41,7 @@ static void amdgpu_job_timedout(struct drm_sched_job *s_job) amdgpu_ring_soft_recovery(ring, job->vmid, s_job->s_fence->parent)) { DRM_ERROR("ring %s timeout, but soft recovered\n", s_job->sched->name); - return; + return DRM_GPU_SCHED_STAT_NOMINAL; } amdgpu_vm_get_task_info(ring->adev, job->pasid, &ti); @@ -53,10 +53,12 @@ static void amdgpu_job_timedout(struct drm_sched_job *s_job) if (amdgpu_device_should_recover_gpu(ring->adev)) { amdgpu_device_gpu_recover(ring->adev, job); + return DRM_GPU_SCHED_STAT_NOMINAL; } else { drm_sched_suspend_timeout(&ring->sched); if (amdgpu_sriov_vf(adev)) adev->virt.tdr_debug = true; + return DRM_GPU_SCHED_STAT_NOMINAL; } } diff --git a/drivers/gpu/drm/etnaviv/etnaviv_sched.c b/drivers/gpu/drm/etnaviv/etnaviv_sched.c index cd46c882269c..2a9439cbb0fb 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_sched.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_sched.c @@ -82,7 +82,8 @@ static struct dma_fence *etnaviv_sched_run_job(struct drm_sched_job *sched_job) return fence; } -static void etnaviv_sched_timedout_job(struct drm_sched_job *sched_job) +static enum drm_gpu_sched_stat etnaviv_sched_timedout_job(struct drm_sched_job + *sched_job) { struct etnaviv_gem_submit *submit = to_etnaviv_submit(sched_job); struct etnaviv_gpu *gpu = submit->gpu; @@ -120,9 +121,13 @@ static void etnaviv_sched_timedout_job(struct drm_sched_job *sched_job) drm_sched_resubmit_jobs(&gpu->sched); + drm_sched_start(&gpu->sched, true); + return DRM_GPU_SCHED_STAT_NOMINAL; + out_no_timeout: /* restart scheduler after GPU is usable again */ drm_sched_start(&gpu->sched, true); + return DRM_GPU_SCHED_STAT_NOMINAL; } static void etnaviv_sched_free_job(struct drm_sched_job *sched_job) diff --git a/drivers/gpu/drm/lima/lima_sched.c b/drivers/gpu/drm/lima/lima_sched.c index 63b4c5643f9c..6e4273852712 100644 --- a/drivers/gpu/drm/lima/lima_sched.c +++ b/drivers/gpu/drm/lima/lima_sched.c @@ -415,7 +415,7 @@ out: mutex_unlock(&dev->error_task_list_lock); } -static void lima_sched_timedout_job(struct drm_sched_job *job) +static enum drm_gpu_sched_stat lima_sched_timedout_job(struct drm_sched_job *job) { struct lima_sched_pipe *pipe = to_lima_pipe(job->sched); struct lima_sched_task *task = to_lima_task(job); @@ -449,6 +449,8 @@ static void lima_sched_timedout_job(struct drm_sched_job *job) drm_sched_resubmit_jobs(&pipe->base); drm_sched_start(&pipe->base, true); + + return DRM_GPU_SCHED_STAT_NOMINAL; } static void lima_sched_free_job(struct drm_sched_job *job) diff --git a/drivers/gpu/drm/panfrost/panfrost_job.c b/drivers/gpu/drm/panfrost/panfrost_job.c index 04e6f6f9b742..0a83eefa49c4 100644 --- a/drivers/gpu/drm/panfrost/panfrost_job.c +++ b/drivers/gpu/drm/panfrost/panfrost_job.c @@ -432,7 +432,8 @@ static void panfrost_scheduler_start(struct panfrost_queue_state *queue) mutex_unlock(&queue->lock); } -static void panfrost_job_timedout(struct drm_sched_job *sched_job) +static enum drm_gpu_sched_stat panfrost_job_timedout(struct drm_sched_job + *sched_job) { struct panfrost_job *job = to_panfrost_job(sched_job); struct panfrost_device *pfdev = job->pfdev; @@ -443,7 +444,7 @@ static void panfrost_job_timedout(struct drm_sched_job *sched_job) * spurious. Bail out. */ if (dma_fence_is_signaled(job->done_fence)) - return; + return DRM_GPU_SCHED_STAT_NOMINAL; dev_err(pfdev->dev, "gpu sched timeout, js=%d, config=0x%x, status=0x%x, head=0x%x, tail=0x%x, sched_job=%p", js, @@ -455,11 +456,13 @@ static void panfrost_job_timedout(struct drm_sched_job *sched_job) /* Scheduler is already stopped, nothing to do. */ if (!panfrost_scheduler_stop(&pfdev->js->queue[js], sched_job)) - return; + return DRM_GPU_SCHED_STAT_NOMINAL; /* Schedule a reset if there's no reset in progress. */ if (!atomic_xchg(&pfdev->reset.pending, 1)) schedule_work(&pfdev->reset.work); + + return DRM_GPU_SCHED_STAT_NOMINAL; } static const struct drm_sched_backend_ops panfrost_sched_ops = { diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c index 92637b70c9bf..73fccc54268b 100644 --- a/drivers/gpu/drm/scheduler/sched_main.c +++ b/drivers/gpu/drm/scheduler/sched_main.c @@ -527,7 +527,7 @@ void drm_sched_start(struct drm_gpu_scheduler *sched, bool full_recovery) EXPORT_SYMBOL(drm_sched_start); /** - * drm_sched_resubmit_jobs - helper to relunch job from pending ring list + * drm_sched_resubmit_jobs - helper to relaunch jobs from the pending list * * @sched: scheduler instance * @@ -561,8 +561,6 @@ void drm_sched_resubmit_jobs(struct drm_gpu_scheduler *sched) } else { s_job->s_fence->parent = fence; } - - } } EXPORT_SYMBOL(drm_sched_resubmit_jobs); diff --git a/drivers/gpu/drm/v3d/v3d_sched.c b/drivers/gpu/drm/v3d/v3d_sched.c index 452682e2209f..ef2338a294ca 100644 --- a/drivers/gpu/drm/v3d/v3d_sched.c +++ b/drivers/gpu/drm/v3d/v3d_sched.c @@ -259,7 +259,7 @@ v3d_cache_clean_job_run(struct drm_sched_job *sched_job) return NULL; } -static void +static enum drm_gpu_sched_status v3d_gpu_reset_for_timeout(struct v3d_dev *v3d, struct drm_sched_job *sched_job) { enum v3d_queue q; @@ -285,6 +285,8 @@ 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; } /* If the current address or return address have changed, then the GPU @@ -292,7 +294,7 @@ v3d_gpu_reset_for_timeout(struct v3d_dev *v3d, struct drm_sched_job *sched_job) * could fail if the GPU got in an infinite loop in the CL, but that * is pretty unlikely outside of an i-g-t testcase. */ -static void +static enum drm_task_status v3d_cl_job_timedout(struct drm_sched_job *sched_job, enum v3d_queue q, u32 *timedout_ctca, u32 *timedout_ctra) { @@ -304,39 +306,39 @@ v3d_cl_job_timedout(struct drm_sched_job *sched_job, enum v3d_queue q, if (*timedout_ctca != ctca || *timedout_ctra != ctra) { *timedout_ctca = ctca; *timedout_ctra = ctra; - return; + return DRM_GPU_SCHED_STAT_NOMINAL; } - v3d_gpu_reset_for_timeout(v3d, sched_job); + return v3d_gpu_reset_for_timeout(v3d, sched_job); } -static void +static enum drm_task_status v3d_bin_job_timedout(struct drm_sched_job *sched_job) { struct v3d_bin_job *job = to_bin_job(sched_job); - v3d_cl_job_timedout(sched_job, V3D_BIN, - &job->timedout_ctca, &job->timedout_ctra); + return v3d_cl_job_timedout(sched_job, V3D_BIN, + &job->timedout_ctca, &job->timedout_ctra); } -static void +static enum drm_task_status v3d_render_job_timedout(struct drm_sched_job *sched_job) { struct v3d_render_job *job = to_render_job(sched_job); - v3d_cl_job_timedout(sched_job, V3D_RENDER, - &job->timedout_ctca, &job->timedout_ctra); + return v3d_cl_job_timedout(sched_job, V3D_RENDER, + &job->timedout_ctca, &job->timedout_ctra); } -static void +static enum drm_task_status v3d_generic_job_timedout(struct drm_sched_job *sched_job) { struct v3d_job *job = to_v3d_job(sched_job); - v3d_gpu_reset_for_timeout(job->v3d, sched_job); + return v3d_gpu_reset_for_timeout(job->v3d, sched_job); } -static void +static enum drm_task_status v3d_csd_job_timedout(struct drm_sched_job *sched_job) { struct v3d_csd_job *job = to_csd_job(sched_job); @@ -348,10 +350,10 @@ v3d_csd_job_timedout(struct drm_sched_job *sched_job) */ if (job->timedout_batches != batches) { job->timedout_batches = batches; - return; + return DRM_GPU_SCHED_STAT_NOMINAL; } - v3d_gpu_reset_for_timeout(v3d, sched_job); + return v3d_gpu_reset_for_timeout(v3d, sched_job); } static const struct drm_sched_backend_ops v3d_bin_sched_ops = { diff --git a/include/drm/gpu_scheduler.h b/include/drm/gpu_scheduler.h index 975e8a67947f..ce6a383ed99f 100644 --- a/include/drm/gpu_scheduler.h +++ b/include/drm/gpu_scheduler.h @@ -206,6 +206,12 @@ static inline bool drm_sched_invalidate_job(struct drm_sched_job *s_job, return s_job && atomic_inc_return(&s_job->karma) > threshold; } +enum drm_gpu_sched_stat { + DRM_GPU_SCHED_STAT_NONE, /* Reserve 0 */ + DRM_GPU_SCHED_STAT_NOMINAL, + DRM_GPU_SCHED_STAT_ENODEV, +}; + /** * struct drm_sched_backend_ops * @@ -230,10 +236,16 @@ struct drm_sched_backend_ops { struct dma_fence *(*run_job)(struct drm_sched_job *sched_job); /** - * @timedout_job: Called when a job has taken too long to execute, - * to trigger GPU recovery. + * @timedout_job: Called when a job has taken too long to execute, + * to trigger GPU recovery. + * + * Return DRM_GPU_SCHED_STAT_NOMINAL, when all is normal, + * and the underlying driver has started or completed recovery. + * + * Return DRM_GPU_SCHED_STAT_ENODEV, if the device is no longer + * available, i.e. has been unplugged. */ - void (*timedout_job)(struct drm_sched_job *sched_job); + enum drm_gpu_sched_stat (*timedout_job)(struct drm_sched_job *sched_job); /** * @free_job: Called once the job's finished fence has been signaled -- cgit v1.2.3 From f2f12eb9c32bc7a714276d8862efac2e7c41bcbe Mon Sep 17 00:00:00 2001 From: Christian König Date: Tue, 2 Feb 2021 12:40:01 +0100 Subject: drm/scheduler: provide scheduler score externally MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Allow multiple schedulers to share the load balancing score. This is useful when one engine has different hw rings. Signed-off-by: Christian König Reviewed-and-Tested-by: Leo Liu Link: https://patchwork.freedesktop.org/patch/msgid/20210204144405.2737-1-christian.koenig@amd.com --- drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c | 2 +- drivers/gpu/drm/etnaviv/etnaviv_sched.c | 2 +- drivers/gpu/drm/lima/lima_sched.c | 2 +- drivers/gpu/drm/panfrost/panfrost_job.c | 2 +- drivers/gpu/drm/scheduler/sched_entity.c | 2 +- drivers/gpu/drm/scheduler/sched_main.c | 18 +++++++++--------- drivers/gpu/drm/v3d/v3d_sched.c | 10 +++++----- include/drm/gpu_scheduler.h | 5 +++-- 8 files changed, 22 insertions(+), 21 deletions(-) (limited to 'drivers/gpu/drm/panfrost') diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c index d56f4023ebb3..8e0a5650d383 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c @@ -487,7 +487,7 @@ int amdgpu_fence_driver_init_ring(struct amdgpu_ring *ring, r = drm_sched_init(&ring->sched, &amdgpu_sched_ops, num_hw_submission, amdgpu_job_hang_limit, - timeout, ring->name); + timeout, NULL, ring->name); if (r) { DRM_ERROR("Failed to create scheduler on ring %s.\n", ring->name); diff --git a/drivers/gpu/drm/etnaviv/etnaviv_sched.c b/drivers/gpu/drm/etnaviv/etnaviv_sched.c index 2a9439cbb0fb..19826e504efc 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_sched.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_sched.c @@ -190,7 +190,7 @@ int etnaviv_sched_init(struct etnaviv_gpu *gpu) ret = drm_sched_init(&gpu->sched, &etnaviv_sched_ops, etnaviv_hw_jobs_limit, etnaviv_job_hang_limit, - msecs_to_jiffies(500), dev_name(gpu->dev)); + msecs_to_jiffies(500), NULL, dev_name(gpu->dev)); if (ret) return ret; diff --git a/drivers/gpu/drm/lima/lima_sched.c b/drivers/gpu/drm/lima/lima_sched.c index 20dafa62980f..ecf3267334ff 100644 --- a/drivers/gpu/drm/lima/lima_sched.c +++ b/drivers/gpu/drm/lima/lima_sched.c @@ -509,7 +509,7 @@ int lima_sched_pipe_init(struct lima_sched_pipe *pipe, const char *name) return drm_sched_init(&pipe->base, &lima_sched_ops, 1, lima_job_hang_limit, msecs_to_jiffies(timeout), - name); + NULL, name); } void lima_sched_pipe_fini(struct lima_sched_pipe *pipe) diff --git a/drivers/gpu/drm/panfrost/panfrost_job.c b/drivers/gpu/drm/panfrost/panfrost_job.c index 0a83eefa49c4..6003cfeb1322 100644 --- a/drivers/gpu/drm/panfrost/panfrost_job.c +++ b/drivers/gpu/drm/panfrost/panfrost_job.c @@ -627,7 +627,7 @@ int panfrost_job_init(struct panfrost_device *pfdev) ret = drm_sched_init(&js->queue[j].sched, &panfrost_sched_ops, 1, 0, msecs_to_jiffies(JOB_TIMEOUT_MS), - "pan_js"); + NULL, "pan_js"); if (ret) { dev_err(pfdev->dev, "Failed to create scheduler: %d.", ret); goto err_sched; diff --git a/drivers/gpu/drm/scheduler/sched_entity.c b/drivers/gpu/drm/scheduler/sched_entity.c index c1ac3e4003c6..92d965b629c6 100644 --- a/drivers/gpu/drm/scheduler/sched_entity.c +++ b/drivers/gpu/drm/scheduler/sched_entity.c @@ -489,7 +489,7 @@ void drm_sched_entity_push_job(struct drm_sched_job *sched_job, bool first; trace_drm_sched_job(sched_job, entity); - atomic_inc(&entity->rq->sched->score); + atomic_inc(entity->rq->sched->score); WRITE_ONCE(entity->last_user, current->group_leader); first = spsc_queue_push(&entity->job_queue, &sched_job->queue_node); diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c index 73fccc54268b..d82a7ebf6099 100644 --- a/drivers/gpu/drm/scheduler/sched_main.c +++ b/drivers/gpu/drm/scheduler/sched_main.c @@ -91,7 +91,7 @@ void drm_sched_rq_add_entity(struct drm_sched_rq *rq, if (!list_empty(&entity->list)) return; spin_lock(&rq->lock); - atomic_inc(&rq->sched->score); + atomic_inc(rq->sched->score); list_add_tail(&entity->list, &rq->entities); spin_unlock(&rq->lock); } @@ -110,7 +110,7 @@ void drm_sched_rq_remove_entity(struct drm_sched_rq *rq, if (list_empty(&entity->list)) return; spin_lock(&rq->lock); - atomic_dec(&rq->sched->score); + atomic_dec(rq->sched->score); list_del_init(&entity->list); if (rq->current_entity == entity) rq->current_entity = NULL; @@ -173,7 +173,7 @@ static void drm_sched_job_done(struct drm_sched_job *s_job) struct drm_gpu_scheduler *sched = s_fence->sched; atomic_dec(&sched->hw_rq_count); - atomic_dec(&sched->score); + atomic_dec(sched->score); trace_drm_sched_process_job(s_fence); @@ -732,7 +732,7 @@ drm_sched_pick_best(struct drm_gpu_scheduler **sched_list, continue; } - num_score = atomic_read(&sched->score); + num_score = atomic_read(sched->score); if (num_score < min_score) { min_score = num_score; picked_sched = sched; @@ -842,16 +842,15 @@ static int drm_sched_main(void *param) * @hw_submission: number of hw submissions that can be in flight * @hang_limit: number of times to allow a job to hang before dropping it * @timeout: timeout value in jiffies for the scheduler + * @score: optional score atomic shared with other schedulers * @name: name used for debugging * * Return 0 on success, otherwise error code. */ int drm_sched_init(struct drm_gpu_scheduler *sched, const struct drm_sched_backend_ops *ops, - unsigned hw_submission, - unsigned hang_limit, - long timeout, - const char *name) + unsigned hw_submission, unsigned hang_limit, long timeout, + atomic_t *score, const char *name) { int i, ret; sched->ops = ops; @@ -859,6 +858,7 @@ int drm_sched_init(struct drm_gpu_scheduler *sched, sched->name = name; sched->timeout = timeout; sched->hang_limit = hang_limit; + sched->score = score ? score : &sched->_score; for (i = DRM_SCHED_PRIORITY_MIN; i < DRM_SCHED_PRIORITY_COUNT; i++) drm_sched_rq_init(sched, &sched->sched_rq[i]); @@ -868,7 +868,7 @@ int drm_sched_init(struct drm_gpu_scheduler *sched, spin_lock_init(&sched->job_list_lock); atomic_set(&sched->hw_rq_count, 0); INIT_DELAYED_WORK(&sched->work_tdr, drm_sched_job_timedout); - atomic_set(&sched->score, 0); + atomic_set(&sched->_score, 0); atomic64_set(&sched->job_id_count, 0); /* Each scheduler will run on a seperate kernel thread */ diff --git a/drivers/gpu/drm/v3d/v3d_sched.c b/drivers/gpu/drm/v3d/v3d_sched.c index ceb33f8e4379..8992480c88fa 100644 --- a/drivers/gpu/drm/v3d/v3d_sched.c +++ b/drivers/gpu/drm/v3d/v3d_sched.c @@ -403,7 +403,7 @@ v3d_sched_init(struct v3d_dev *v3d) &v3d_bin_sched_ops, hw_jobs_limit, job_hang_limit, msecs_to_jiffies(hang_limit_ms), - "v3d_bin"); + NULL, "v3d_bin"); if (ret) { dev_err(v3d->drm.dev, "Failed to create bin scheduler: %d.", ret); return ret; @@ -413,7 +413,7 @@ v3d_sched_init(struct v3d_dev *v3d) &v3d_render_sched_ops, hw_jobs_limit, job_hang_limit, msecs_to_jiffies(hang_limit_ms), - "v3d_render"); + NULL, "v3d_render"); if (ret) { dev_err(v3d->drm.dev, "Failed to create render scheduler: %d.", ret); @@ -425,7 +425,7 @@ v3d_sched_init(struct v3d_dev *v3d) &v3d_tfu_sched_ops, hw_jobs_limit, job_hang_limit, msecs_to_jiffies(hang_limit_ms), - "v3d_tfu"); + NULL, "v3d_tfu"); if (ret) { dev_err(v3d->drm.dev, "Failed to create TFU scheduler: %d.", ret); @@ -438,7 +438,7 @@ v3d_sched_init(struct v3d_dev *v3d) &v3d_csd_sched_ops, hw_jobs_limit, job_hang_limit, msecs_to_jiffies(hang_limit_ms), - "v3d_csd"); + NULL, "v3d_csd"); if (ret) { dev_err(v3d->drm.dev, "Failed to create CSD scheduler: %d.", ret); @@ -450,7 +450,7 @@ v3d_sched_init(struct v3d_dev *v3d) &v3d_cache_clean_sched_ops, hw_jobs_limit, job_hang_limit, msecs_to_jiffies(hang_limit_ms), - "v3d_cache_clean"); + NULL, "v3d_cache_clean"); if (ret) { dev_err(v3d->drm.dev, "Failed to create CACHE_CLEAN scheduler: %d.", ret); diff --git a/include/drm/gpu_scheduler.h b/include/drm/gpu_scheduler.h index ce6a383ed99f..1c815e0a14ed 100644 --- a/include/drm/gpu_scheduler.h +++ b/include/drm/gpu_scheduler.h @@ -297,7 +297,8 @@ struct drm_gpu_scheduler { struct list_head pending_list; spinlock_t job_list_lock; int hang_limit; - atomic_t score; + atomic_t *score; + atomic_t _score; bool ready; bool free_guilty; }; @@ -305,7 +306,7 @@ struct drm_gpu_scheduler { int drm_sched_init(struct drm_gpu_scheduler *sched, const struct drm_sched_backend_ops *ops, uint32_t hw_submission, unsigned hang_limit, long timeout, - const char *name); + atomic_t *score, const char *name); void drm_sched_fini(struct drm_gpu_scheduler *sched); int drm_sched_job_init(struct drm_sched_job *job, -- cgit v1.2.3 From 3aa0a80fc692c9959c261f4c5bfe9c23ddd90562 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Fri, 5 Feb 2021 12:17:55 +0100 Subject: drm/panfrost: Clear MMU irqs before handling the fault When a fault is handled it will unblock the GPU which will continue executing its shader and might fault almost immediately on a different page. If we clear interrupts after handling the fault we might miss new faults, so clear them before. Cc: Fixes: 187d2929206e ("drm/panfrost: Add support for GPU heap allocations") Signed-off-by: Boris Brezillon Reviewed-by: Steven Price Link: https://patchwork.freedesktop.org/patch/msgid/20210205111757.585248-2-boris.brezillon@collabora.com --- drivers/gpu/drm/panfrost/panfrost_mmu.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'drivers/gpu/drm/panfrost') diff --git a/drivers/gpu/drm/panfrost/panfrost_mmu.c b/drivers/gpu/drm/panfrost/panfrost_mmu.c index 7c1b3481b785..904d63450862 100644 --- a/drivers/gpu/drm/panfrost/panfrost_mmu.c +++ b/drivers/gpu/drm/panfrost/panfrost_mmu.c @@ -593,6 +593,8 @@ static irqreturn_t panfrost_mmu_irq_handler_thread(int irq, void *data) access_type = (fault_status >> 8) & 0x3; source_id = (fault_status >> 16); + mmu_write(pfdev, MMU_INT_CLEAR, mask); + /* Page fault only */ ret = -1; if ((status & mask) == BIT(i) && (exception_type & 0xF8) == 0xC0) @@ -616,8 +618,6 @@ static irqreturn_t panfrost_mmu_irq_handler_thread(int irq, void *data) access_type, access_type_name(pfdev, fault_status), source_id); - mmu_write(pfdev, MMU_INT_CLEAR, mask); - status &= ~mask; } -- cgit v1.2.3 From f45da8204ff1707c529a8769f5467ff16f504b26 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Fri, 5 Feb 2021 12:17:56 +0100 Subject: drm/panfrost: Don't try to map pages that are already mapped We allocate 2MB chunks at a time, so it might appear that a page fault has already been handled by a previous page fault when we reach panfrost_mmu_map_fault_addr(). Bail out in that case to avoid mapping the same area twice. Cc: Fixes: 187d2929206e ("drm/panfrost: Add support for GPU heap allocations") Signed-off-by: Boris Brezillon Reviewed-by: Steven Price Link: https://patchwork.freedesktop.org/patch/msgid/20210205111757.585248-3-boris.brezillon@collabora.com --- drivers/gpu/drm/panfrost/panfrost_mmu.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'drivers/gpu/drm/panfrost') diff --git a/drivers/gpu/drm/panfrost/panfrost_mmu.c b/drivers/gpu/drm/panfrost/panfrost_mmu.c index 904d63450862..21e552d1ac71 100644 --- a/drivers/gpu/drm/panfrost/panfrost_mmu.c +++ b/drivers/gpu/drm/panfrost/panfrost_mmu.c @@ -488,8 +488,14 @@ static int panfrost_mmu_map_fault_addr(struct panfrost_device *pfdev, int as, } bo->base.pages = pages; bo->base.pages_use_count = 1; - } else + } else { pages = bo->base.pages; + if (pages[page_offset]) { + /* Pages are already mapped, bail out. */ + mutex_unlock(&bo->base.pages_lock); + goto out; + } + } mapping = bo->base.base.filp->f_mapping; mapping_set_unevictable(mapping); @@ -522,6 +528,7 @@ static int panfrost_mmu_map_fault_addr(struct panfrost_device *pfdev, int as, dev_dbg(pfdev->dev, "mapped page fault @ AS%d %llx", as, addr); +out: panfrost_gem_mapping_put(bomapping); return 0; -- cgit v1.2.3 From 0eae01bea643413758e78ca8f07be2b1ba234e36 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Fri, 5 Feb 2021 12:17:57 +0100 Subject: drm/panfrost: Stay in the threaded MMU IRQ handler until we've handled all IRQs Doing a hw-irq -> threaded-irq round-trip is counter-productive, stay in the threaded irq handler as long as we can. v2: * Rework the loop to avoid a goto Signed-off-by: Boris Brezillon Reviewed-by: Steven Price Reviewed-by: Rob Herring Link: https://patchwork.freedesktop.org/patch/msgid/20210205111757.585248-4-boris.brezillon@collabora.com --- drivers/gpu/drm/panfrost/panfrost_mmu.c | 26 ++++++++++++++------------ 1 file changed, 14 insertions(+), 12 deletions(-) (limited to 'drivers/gpu/drm/panfrost') diff --git a/drivers/gpu/drm/panfrost/panfrost_mmu.c b/drivers/gpu/drm/panfrost/panfrost_mmu.c index 21e552d1ac71..0581186ebfb3 100644 --- a/drivers/gpu/drm/panfrost/panfrost_mmu.c +++ b/drivers/gpu/drm/panfrost/panfrost_mmu.c @@ -578,22 +578,20 @@ static irqreturn_t panfrost_mmu_irq_handler_thread(int irq, void *data) { struct panfrost_device *pfdev = data; u32 status = mmu_read(pfdev, MMU_INT_RAWSTAT); - int i, ret; + int ret; - for (i = 0; status; i++) { - u32 mask = BIT(i) | BIT(i + 16); + while (status) { + u32 as = ffs(status | (status >> 16)) - 1; + u32 mask = BIT(as) | BIT(as + 16); u64 addr; u32 fault_status; u32 exception_type; u32 access_type; u32 source_id; - if (!(status & mask)) - continue; - - fault_status = mmu_read(pfdev, AS_FAULTSTATUS(i)); - addr = mmu_read(pfdev, AS_FAULTADDRESS_LO(i)); - addr |= (u64)mmu_read(pfdev, AS_FAULTADDRESS_HI(i)) << 32; + fault_status = mmu_read(pfdev, AS_FAULTSTATUS(as)); + addr = mmu_read(pfdev, AS_FAULTADDRESS_LO(as)); + addr |= (u64)mmu_read(pfdev, AS_FAULTADDRESS_HI(as)) << 32; /* decode the fault status */ exception_type = fault_status & 0xFF; @@ -604,8 +602,8 @@ static irqreturn_t panfrost_mmu_irq_handler_thread(int irq, void *data) /* Page fault only */ ret = -1; - if ((status & mask) == BIT(i) && (exception_type & 0xF8) == 0xC0) - ret = panfrost_mmu_map_fault_addr(pfdev, i, addr); + if ((status & mask) == BIT(as) && (exception_type & 0xF8) == 0xC0) + ret = panfrost_mmu_map_fault_addr(pfdev, as, addr); if (ret) /* terminal fault, print info about the fault */ @@ -617,7 +615,7 @@ static irqreturn_t panfrost_mmu_irq_handler_thread(int irq, void *data) "exception type 0x%X: %s\n" "access type 0x%X: %s\n" "source id 0x%X\n", - i, addr, + as, addr, "TODO", fault_status, (fault_status & (1 << 10) ? "DECODER FAULT" : "SLAVE FAULT"), @@ -626,6 +624,10 @@ static irqreturn_t panfrost_mmu_irq_handler_thread(int irq, void *data) source_id); status &= ~mask; + + /* If we received new MMU interrupts, process them before returning. */ + if (!status) + status = mmu_read(pfdev, MMU_INT_RAWSTAT); } mmu_write(pfdev, MMU_INT_MASK, ~0); -- cgit v1.2.3