| Message ID | 20231026041236.1273694-4-matthew.brost@intel.com (mailing list archive) |
|---|---|
| State | Not Applicable |
| Headers | show |
| Series | None | expand |
On 2023-10-26 00:12, Matthew Brost wrote: > From: Luben Tuikov <luben.tuikov@amd.com> > > The GPU scheduler has now a variable number of run-queues, which are set up at > drm_sched_init() time. This way, each driver announces how many run-queues it > requires (supports) per each GPU scheduler it creates. Note, that run-queues > correspond to scheduler "priorities", thus if the number of run-queues is set > to 1 at drm_sched_init(), then that scheduler supports a single run-queue, > i.e. single "priority". If a driver further sets a single entity per > run-queue, then this creates a 1-to-1 correspondence between a scheduler and > a scheduled entity. > > Cc: Lucas Stach <l.stach@pengutronix.de> > Cc: Russell King <linux+etnaviv@armlinux.org.uk> > Cc: Qiang Yu <yuq825@gmail.com> > Cc: Rob Clark <robdclark@gmail.com> > Cc: Abhinav Kumar <quic_abhinavk@quicinc.com> > Cc: Dmitry Baryshkov <dmitry.baryshkov@linaro.org> > Cc: Danilo Krummrich <dakr@redhat.com> > Cc: Matthew Brost <matthew.brost@intel.com> > Cc: Boris Brezillon <boris.brezillon@collabora.com> > Cc: Alex Deucher <alexander.deucher@amd.com> > Cc: Christian König <christian.koenig@amd.com> > Cc: Emma Anholt <emma@anholt.net> > Cc: etnaviv@lists.freedesktop.org > Cc: lima@lists.freedesktop.org > Cc: linux-arm-msm@vger.kernel.org > Cc: freedreno@lists.freedesktop.org > Cc: nouveau@lists.freedesktop.org > Cc: dri-devel@lists.freedesktop.org > Signed-off-by: Luben Tuikov <luben.tuikov@amd.com> > Signed-off-by: Matthew Brost <matthew.brost@intel.com> Normally, you'd add your R-B. You should add your S-O-B tag, if you've co-authored/contributed to the commit or are the actual committer to drm-*, as "dim" requires it, but dim will tell you, so generally, I don't do that unless the tool tells me to. :-) So here, feel free to R-B the patch instead of S-O-B, on a patch post. Regards, Luben > --- > drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 1 + > drivers/gpu/drm/amd/amdgpu/amdgpu_job.c | 4 +- > drivers/gpu/drm/etnaviv/etnaviv_sched.c | 3 +- > drivers/gpu/drm/lima/lima_sched.c | 3 +- > drivers/gpu/drm/msm/msm_ringbuffer.c | 3 +- > drivers/gpu/drm/nouveau/nouveau_sched.c | 1 + > drivers/gpu/drm/panfrost/panfrost_job.c | 3 +- > drivers/gpu/drm/scheduler/sched_entity.c | 18 +++++- > drivers/gpu/drm/scheduler/sched_main.c | 75 ++++++++++++++++++---- > drivers/gpu/drm/v3d/v3d_sched.c | 14 ++-- > include/drm/gpu_scheduler.h | 9 ++- > 11 files changed, 102 insertions(+), 32 deletions(-) > > diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c > index b54c4d771104..94d073bfbd13 100644 > --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c > +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c > @@ -2280,6 +2280,7 @@ static int amdgpu_device_init_schedulers(struct amdgpu_device *adev) > } > > r = drm_sched_init(&ring->sched, &amdgpu_sched_ops, NULL, > + DRM_SCHED_PRIORITY_COUNT, > ring->num_hw_submission, 0, > timeout, adev->reset_domain->wq, > ring->sched_score, ring->name, > diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c > index 78476bc75b4e..1f357198533f 100644 > --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c > +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c > @@ -325,8 +325,8 @@ void amdgpu_job_stop_all_jobs_on_sched(struct drm_gpu_scheduler *sched) > int i; > > /* Signal all jobs not yet scheduled */ > - for (i = DRM_SCHED_PRIORITY_COUNT - 1; i >= DRM_SCHED_PRIORITY_MIN; i--) { > - struct drm_sched_rq *rq = &sched->sched_rq[i]; > + for (i = sched->num_rqs - 1; i >= DRM_SCHED_PRIORITY_MIN; i--) { > + struct drm_sched_rq *rq = sched->sched_rq[i]; > spin_lock(&rq->lock); > list_for_each_entry(s_entity, &rq->entities, list) { > while ((s_job = to_drm_sched_job(spsc_queue_pop(&s_entity->job_queue)))) { > diff --git a/drivers/gpu/drm/etnaviv/etnaviv_sched.c b/drivers/gpu/drm/etnaviv/etnaviv_sched.c > index 618a804ddc34..396334984e4d 100644 > --- a/drivers/gpu/drm/etnaviv/etnaviv_sched.c > +++ b/drivers/gpu/drm/etnaviv/etnaviv_sched.c > @@ -134,7 +134,8 @@ int etnaviv_sched_init(struct etnaviv_gpu *gpu) > { > int ret; > > - ret = drm_sched_init(&gpu->sched, &etnaviv_sched_ops, NULL, > + ret = drm_sched_init(&gpu->sched, &etnaviv_sched_ops, > + DRM_SCHED_PRIORITY_COUNT, NULL, > etnaviv_hw_jobs_limit, etnaviv_job_hang_limit, > msecs_to_jiffies(500), NULL, NULL, > dev_name(gpu->dev), gpu->dev); > diff --git a/drivers/gpu/drm/lima/lima_sched.c b/drivers/gpu/drm/lima/lima_sched.c > index 8d858aed0e56..23a6276f1332 100644 > --- a/drivers/gpu/drm/lima/lima_sched.c > +++ b/drivers/gpu/drm/lima/lima_sched.c > @@ -488,7 +488,8 @@ int lima_sched_pipe_init(struct lima_sched_pipe *pipe, const char *name) > > INIT_WORK(&pipe->recover_work, lima_sched_recover_work); > > - return drm_sched_init(&pipe->base, &lima_sched_ops, NULL, 1, > + return drm_sched_init(&pipe->base, &lima_sched_ops, > + DRM_SCHED_PRIORITY_COUNT, NULL, 1, > lima_job_hang_limit, > msecs_to_jiffies(timeout), NULL, > NULL, name, pipe->ldev->dev); > diff --git a/drivers/gpu/drm/msm/msm_ringbuffer.c b/drivers/gpu/drm/msm/msm_ringbuffer.c > index 1097f8e93d6b..935154979fc2 100644 > --- a/drivers/gpu/drm/msm/msm_ringbuffer.c > +++ b/drivers/gpu/drm/msm/msm_ringbuffer.c > @@ -94,7 +94,8 @@ struct msm_ringbuffer *msm_ringbuffer_new(struct msm_gpu *gpu, int id, > /* currently managing hangcheck ourselves: */ > sched_timeout = MAX_SCHEDULE_TIMEOUT; > > - ret = drm_sched_init(&ring->sched, &msm_sched_ops, NULL, > + ret = drm_sched_init(&ring->sched, &msm_sched_ops, > + DRM_SCHED_PRIORITY_COUNT, NULL, > num_hw_submissions, 0, sched_timeout, > NULL, NULL, to_msm_bo(ring->bo)->name, > gpu->dev->dev); > diff --git a/drivers/gpu/drm/nouveau/nouveau_sched.c b/drivers/gpu/drm/nouveau/nouveau_sched.c > index 4c959dec42b3..c4ba56b1a6dd 100644 > --- a/drivers/gpu/drm/nouveau/nouveau_sched.c > +++ b/drivers/gpu/drm/nouveau/nouveau_sched.c > @@ -436,6 +436,7 @@ int nouveau_sched_init(struct nouveau_drm *drm) > return -ENOMEM; > > return drm_sched_init(sched, &nouveau_sched_ops, NULL, > + DRM_SCHED_PRIORITY_COUNT, > NOUVEAU_SCHED_HW_SUBMISSIONS, 0, job_hang_limit, > NULL, NULL, "nouveau_sched", drm->dev->dev); > } > diff --git a/drivers/gpu/drm/panfrost/panfrost_job.c b/drivers/gpu/drm/panfrost/panfrost_job.c > index 934b7b930c76..205d62c04f96 100644 > --- a/drivers/gpu/drm/panfrost/panfrost_job.c > +++ b/drivers/gpu/drm/panfrost/panfrost_job.c > @@ -852,7 +852,8 @@ int panfrost_job_init(struct panfrost_device *pfdev) > js->queue[j].fence_context = dma_fence_context_alloc(1); > > ret = drm_sched_init(&js->queue[j].sched, > - &panfrost_sched_ops, NULL, > + &panfrost_sched_ops, > + DRM_SCHED_PRIORITY_COUNT, NULL, > nentries, 0, > msecs_to_jiffies(JOB_TIMEOUT_MS), > pfdev->reset.wq, > diff --git a/drivers/gpu/drm/scheduler/sched_entity.c b/drivers/gpu/drm/scheduler/sched_entity.c > index a42763e1429d..409e4256f6e7 100644 > --- a/drivers/gpu/drm/scheduler/sched_entity.c > +++ b/drivers/gpu/drm/scheduler/sched_entity.c > @@ -75,8 +75,20 @@ int drm_sched_entity_init(struct drm_sched_entity *entity, > RCU_INIT_POINTER(entity->last_scheduled, NULL); > RB_CLEAR_NODE(&entity->rb_tree_node); > > - if(num_sched_list) > - entity->rq = &sched_list[0]->sched_rq[entity->priority]; > + if (!sched_list[0]->sched_rq) { > + /* Warn drivers not to do this and to fix their DRM > + * calling order. > + */ > + pr_warn("%s: called with uninitialized scheduler\n", __func__); > + } else if (num_sched_list) { > + /* The "priority" of an entity cannot exceed the number > + * of run-queues of a scheduler. > + */ > + if (entity->priority >= sched_list[0]->num_rqs) > + entity->priority = max_t(u32, sched_list[0]->num_rqs, > + DRM_SCHED_PRIORITY_MIN); > + entity->rq = sched_list[0]->sched_rq[entity->priority]; > + } > > init_completion(&entity->entity_idle); > > @@ -533,7 +545,7 @@ void drm_sched_entity_select_rq(struct drm_sched_entity *entity) > > spin_lock(&entity->rq_lock); > sched = drm_sched_pick_best(entity->sched_list, entity->num_sched_list); > - rq = sched ? &sched->sched_rq[entity->priority] : NULL; > + rq = sched ? sched->sched_rq[entity->priority] : NULL; > if (rq != entity->rq) { > drm_sched_rq_remove_entity(entity->rq, entity); > entity->rq = rq; > diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c > index 3a955b8acc4e..b22157e920d4 100644 > --- a/drivers/gpu/drm/scheduler/sched_main.c > +++ b/drivers/gpu/drm/scheduler/sched_main.c > @@ -641,8 +641,14 @@ int drm_sched_job_init(struct drm_sched_job *job, > struct drm_sched_entity *entity, > void *owner) > { > - if (!entity->rq) > + if (!entity->rq) { > + /* This will most likely be followed by missing frames > + * or worse--a blank screen--leave a trail in the > + * logs, so this can be debugged easier. > + */ > + drm_err(job->sched, "%s: entity has no rq!\n", __func__); > return -ENOENT; > + } > > job->entity = entity; > job->s_fence = drm_sched_fence_alloc(entity, owner); > @@ -680,7 +686,7 @@ void drm_sched_job_arm(struct drm_sched_job *job) > sched = entity->rq->sched; > > job->sched = sched; > - job->s_priority = entity->rq - sched->sched_rq; > + job->s_priority = entity->priority; > job->id = atomic64_inc_return(&sched->job_id_count); > > drm_sched_fence_init(job->s_fence, job->entity); > @@ -897,10 +903,10 @@ drm_sched_select_entity(struct drm_gpu_scheduler *sched) > return NULL; > > /* Kernel run queue has higher priority than normal run queue*/ > - for (i = DRM_SCHED_PRIORITY_COUNT - 1; i >= DRM_SCHED_PRIORITY_MIN; i--) { > + for (i = sched->num_rqs - 1; i >= DRM_SCHED_PRIORITY_MIN; i--) { > entity = drm_sched_policy == DRM_SCHED_POLICY_FIFO ? > - drm_sched_rq_select_entity_fifo(&sched->sched_rq[i]) : > - drm_sched_rq_select_entity_rr(&sched->sched_rq[i]); > + drm_sched_rq_select_entity_fifo(sched->sched_rq[i]) : > + drm_sched_rq_select_entity_rr(sched->sched_rq[i]); > if (entity) > break; > } > @@ -1065,6 +1071,7 @@ static void drm_sched_main(struct work_struct *w) > * @ops: backend operations for this scheduler > * @submit_wq: workqueue to use for submission. If NULL, an ordered wq is > * allocated and used > + * @num_rqs: number of runqueues, one for each priority, up to DRM_SCHED_PRIORITY_COUNT > * @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 > @@ -1079,11 +1086,12 @@ static void drm_sched_main(struct work_struct *w) > int drm_sched_init(struct drm_gpu_scheduler *sched, > const struct drm_sched_backend_ops *ops, > struct workqueue_struct *submit_wq, > - unsigned hw_submission, unsigned hang_limit, > + u32 num_rqs, unsigned hw_submission, unsigned hang_limit, > long timeout, struct workqueue_struct *timeout_wq, > atomic_t *score, const char *name, struct device *dev) > { > - int i; > + int i, ret; > + > sched->ops = ops; > sched->hw_submission_limit = hw_submission; > sched->name = name; > @@ -1102,8 +1110,36 @@ int drm_sched_init(struct drm_gpu_scheduler *sched, > sched->hang_limit = hang_limit; > sched->score = score ? score : &sched->_score; > sched->dev = dev; > - for (i = DRM_SCHED_PRIORITY_MIN; i < DRM_SCHED_PRIORITY_COUNT; i++) > - drm_sched_rq_init(sched, &sched->sched_rq[i]); > + > + if (num_rqs > DRM_SCHED_PRIORITY_COUNT) { > + /* This is a gross violation--tell drivers what the problem is. > + */ > + drm_err(sched, "%s: num_rqs cannot be greater than DRM_SCHED_PRIORITY_COUNT\n", > + __func__); > + return -EINVAL; > + } else if (sched->sched_rq) { > + /* Not an error, but warn anyway so drivers can > + * fine-tune their DRM calling order, and return all > + * is good. > + */ > + drm_warn(sched, "%s: scheduler already initialized!\n", __func__); > + return 0; > + } > + > + sched->sched_rq = kmalloc_array(num_rqs, sizeof(*sched->sched_rq), > + GFP_KERNEL | __GFP_ZERO); > + if (!sched->sched_rq) { > + drm_err(sched, "%s: out of memory for sched_rq\n", __func__); > + return -ENOMEM; > + } > + sched->num_rqs = num_rqs; > + ret = -ENOMEM; > + for (i = DRM_SCHED_PRIORITY_MIN; i < sched->num_rqs; i++) { > + sched->sched_rq[i] = kzalloc(sizeof(*sched->sched_rq[i]), GFP_KERNEL); > + if (!sched->sched_rq[i]) > + goto Out_unroll; > + drm_sched_rq_init(sched, sched->sched_rq[i]); > + } > > init_waitqueue_head(&sched->job_scheduled); > INIT_LIST_HEAD(&sched->pending_list); > @@ -1117,6 +1153,14 @@ int drm_sched_init(struct drm_gpu_scheduler *sched, > > sched->ready = true; > return 0; > + > +Out_unroll: > + for (--i ; i >= DRM_SCHED_PRIORITY_MIN; i--) > + kfree(sched->sched_rq[i]); > + kfree(sched->sched_rq); > + sched->sched_rq = NULL; > + drm_err(sched, "%s: Failed to setup GPU scheduler--out of memory\n", __func__); > + return ret; > } > EXPORT_SYMBOL(drm_sched_init); > > @@ -1134,8 +1178,8 @@ void drm_sched_fini(struct drm_gpu_scheduler *sched) > > drm_sched_wqueue_stop(sched); > > - for (i = DRM_SCHED_PRIORITY_COUNT - 1; i >= DRM_SCHED_PRIORITY_MIN; i--) { > - struct drm_sched_rq *rq = &sched->sched_rq[i]; > + for (i = sched->num_rqs - 1; i >= DRM_SCHED_PRIORITY_MIN; i--) { > + struct drm_sched_rq *rq = sched->sched_rq[i]; > > spin_lock(&rq->lock); > list_for_each_entry(s_entity, &rq->entities, list) > @@ -1146,7 +1190,7 @@ void drm_sched_fini(struct drm_gpu_scheduler *sched) > */ > s_entity->stopped = true; > spin_unlock(&rq->lock); > - > + kfree(sched->sched_rq[i]); > } > > /* Wakeup everyone stuck in drm_sched_entity_flush for this scheduler */ > @@ -1158,6 +1202,8 @@ void drm_sched_fini(struct drm_gpu_scheduler *sched) > if (sched->own_submit_wq) > destroy_workqueue(sched->submit_wq); > sched->ready = false; > + kfree(sched->sched_rq); > + sched->sched_rq = NULL; > } > EXPORT_SYMBOL(drm_sched_fini); > > @@ -1184,9 +1230,10 @@ void drm_sched_increase_karma(struct drm_sched_job *bad) > if (bad->s_priority != DRM_SCHED_PRIORITY_KERNEL) { > atomic_inc(&bad->karma); > > - for (i = DRM_SCHED_PRIORITY_MIN; i < DRM_SCHED_PRIORITY_KERNEL; > + for (i = DRM_SCHED_PRIORITY_MIN; > + i < min_t(typeof(sched->num_rqs), sched->num_rqs, DRM_SCHED_PRIORITY_KERNEL); > i++) { > - struct drm_sched_rq *rq = &sched->sched_rq[i]; > + struct drm_sched_rq *rq = sched->sched_rq[i]; > > spin_lock(&rq->lock); > list_for_each_entry_safe(entity, tmp, &rq->entities, list) { > diff --git a/drivers/gpu/drm/v3d/v3d_sched.c b/drivers/gpu/drm/v3d/v3d_sched.c > index 38e092ea41e6..175c3e30647a 100644 > --- a/drivers/gpu/drm/v3d/v3d_sched.c > +++ b/drivers/gpu/drm/v3d/v3d_sched.c > @@ -388,7 +388,7 @@ v3d_sched_init(struct v3d_dev *v3d) > int ret; > > ret = drm_sched_init(&v3d->queue[V3D_BIN].sched, > - &v3d_bin_sched_ops, NULL, > + &v3d_bin_sched_ops, DRM_SCHED_PRIORITY_COUNT, NULL, > hw_jobs_limit, job_hang_limit, > msecs_to_jiffies(hang_limit_ms), NULL, > NULL, "v3d_bin", v3d->drm.dev); > @@ -396,15 +396,15 @@ v3d_sched_init(struct v3d_dev *v3d) > return ret; > > ret = drm_sched_init(&v3d->queue[V3D_RENDER].sched, > - &v3d_render_sched_ops, NULL, > - hw_jobs_limit, job_hang_limit, > + &v3d_render_sched_ops, DRM_SCHED_PRIORITY_COUNT, > + NULL, hw_jobs_limit, job_hang_limit, > msecs_to_jiffies(hang_limit_ms), NULL, > NULL, "v3d_render", v3d->drm.dev); > if (ret) > goto fail; > > ret = drm_sched_init(&v3d->queue[V3D_TFU].sched, > - &v3d_tfu_sched_ops, NULL, > + &v3d_tfu_sched_ops, DRM_SCHED_PRIORITY_COUNT, NULL, > hw_jobs_limit, job_hang_limit, > msecs_to_jiffies(hang_limit_ms), NULL, > NULL, "v3d_tfu", v3d->drm.dev); > @@ -413,7 +413,8 @@ v3d_sched_init(struct v3d_dev *v3d) > > if (v3d_has_csd(v3d)) { > ret = drm_sched_init(&v3d->queue[V3D_CSD].sched, > - &v3d_csd_sched_ops, NULL, > + &v3d_csd_sched_ops, > + DRM_SCHED_PRIORITY_COUNT, NULL, > hw_jobs_limit, job_hang_limit, > msecs_to_jiffies(hang_limit_ms), NULL, > NULL, "v3d_csd", v3d->drm.dev); > @@ -421,7 +422,8 @@ v3d_sched_init(struct v3d_dev *v3d) > goto fail; > > ret = drm_sched_init(&v3d->queue[V3D_CACHE_CLEAN].sched, > - &v3d_cache_clean_sched_ops, NULL, > + &v3d_cache_clean_sched_ops, > + DRM_SCHED_PRIORITY_COUNT, NULL, > hw_jobs_limit, job_hang_limit, > msecs_to_jiffies(hang_limit_ms), NULL, > NULL, "v3d_cache_clean", v3d->drm.dev); > diff --git a/include/drm/gpu_scheduler.h b/include/drm/gpu_scheduler.h > index 211bd3cdabdc..1d52b8bbb06c 100644 > --- a/include/drm/gpu_scheduler.h > +++ b/include/drm/gpu_scheduler.h > @@ -472,7 +472,9 @@ struct drm_sched_backend_ops { > * @hw_submission_limit: the max size of the hardware queue. > * @timeout: the time after which a job is removed from the scheduler. > * @name: name of the ring for which this scheduler is being used. > - * @sched_rq: priority wise array of run queues. > + * @num_rqs: Number of run-queues. This is at most DRM_SCHED_PRIORITY_COUNT, > + * as there's usually one run-queue per priority, but could be less. > + * @sched_rq: An allocated array of run-queues of size @num_rqs; > * @job_scheduled: once @drm_sched_entity_do_release is called the scheduler > * waits on this wait queue until all the scheduled jobs are > * finished. > @@ -502,7 +504,8 @@ struct drm_gpu_scheduler { > uint32_t hw_submission_limit; > long timeout; > const char *name; > - struct drm_sched_rq sched_rq[DRM_SCHED_PRIORITY_COUNT]; > + u32 num_rqs; > + struct drm_sched_rq **sched_rq; > wait_queue_head_t job_scheduled; > atomic_t hw_rq_count; > atomic64_t job_id_count; > @@ -525,7 +528,7 @@ struct drm_gpu_scheduler { > int drm_sched_init(struct drm_gpu_scheduler *sched, > const struct drm_sched_backend_ops *ops, > struct workqueue_struct *submit_wq, > - uint32_t hw_submission, unsigned hang_limit, > + u32 num_rqs, uint32_t hw_submission, unsigned hang_limit, > long timeout, struct workqueue_struct *timeout_wq, > atomic_t *score, const char *name, struct device *dev); >
Hi Matthew, kernel test robot noticed the following build warnings: [auto build test WARNING on 201c8a7bd1f3f415920a2df4b8a8817e973f42fe] url: https://github.com/intel-lab-lkp/linux/commits/Matthew-Brost/drm-sched-Add-drm_sched_wqueue_-helpers/20231026-121313 base: 201c8a7bd1f3f415920a2df4b8a8817e973f42fe patch link: https://lore.kernel.org/r/20231026041236.1273694-4-matthew.brost%40intel.com patch subject: [PATCH v7 3/6] drm/sched: Convert the GPU scheduler to variable number of run-queues config: m68k-allyesconfig (https://download.01.org/0day-ci/archive/20231026/202310261439.3rbAtEoB-lkp@intel.com/config) compiler: m68k-linux-gcc (GCC) 13.2.0 reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20231026/202310261439.3rbAtEoB-lkp@intel.com/reproduce) If you fix the issue in a separate patch/commit (i.e. not just a new version of the same patch/commit), kindly add following tags | Reported-by: kernel test robot <lkp@intel.com> | Closes: https://lore.kernel.org/oe-kbuild-all/202310261439.3rbAtEoB-lkp@intel.com/ All warnings (new ones prefixed by >>): drivers/gpu/drm/etnaviv/etnaviv_sched.c: In function 'etnaviv_sched_init': >> drivers/gpu/drm/etnaviv/etnaviv_sched.c:138:30: warning: passing argument 3 of 'drm_sched_init' makes pointer from integer without a cast [-Wint-conversion] 138 | DRM_SCHED_PRIORITY_COUNT, NULL, | ^~~~~~~~~~~~~~~~~~~~~~~~ | | | int In file included from drivers/gpu/drm/etnaviv/etnaviv_drv.h:20, from drivers/gpu/drm/etnaviv/etnaviv_sched.c:8: include/drm/gpu_scheduler.h:530:45: note: expected 'struct workqueue_struct *' but argument is of type 'int' 530 | struct workqueue_struct *submit_wq, | ~~~~~~~~~~~~~~~~~~~~~~~~~^~~~~~~~~ In file included from include/uapi/linux/posix_types.h:5, from include/uapi/linux/types.h:14, from include/linux/types.h:6, from include/linux/kasan-checks.h:5, from include/asm-generic/rwonce.h:26, from ./arch/m68k/include/generated/asm/rwonce.h:1, from include/linux/compiler.h:246, from include/linux/build_bug.h:5, from include/linux/init.h:5, from include/linux/moduleparam.h:5, from drivers/gpu/drm/etnaviv/etnaviv_sched.c:6: >> include/linux/stddef.h:8:14: warning: passing argument 4 of 'drm_sched_init' makes integer from pointer without a cast [-Wint-conversion] 8 | #define NULL ((void *)0) | ^~~~~~~~~~~ | | | void * drivers/gpu/drm/etnaviv/etnaviv_sched.c:138:56: note: in expansion of macro 'NULL' 138 | DRM_SCHED_PRIORITY_COUNT, NULL, | ^~~~ include/drm/gpu_scheduler.h:531:24: note: expected 'u32' {aka 'unsigned int'} but argument is of type 'void *' 531 | u32 num_rqs, uint32_t hw_submission, unsigned hang_limit, | ~~~~^~~~~~~ -- drivers/gpu/drm/lima/lima_sched.c: In function 'lima_sched_pipe_init': >> drivers/gpu/drm/lima/lima_sched.c:492:31: warning: passing argument 3 of 'drm_sched_init' makes pointer from integer without a cast [-Wint-conversion] 492 | DRM_SCHED_PRIORITY_COUNT, NULL, 1, | ^~~~~~~~~~~~~~~~~~~~~~~~ | | | int In file included from drivers/gpu/drm/lima/lima_sched.h:7, from drivers/gpu/drm/lima/lima_device.h:12, from drivers/gpu/drm/lima/lima_ctx.h:10, from drivers/gpu/drm/lima/lima_drv.h:9, from drivers/gpu/drm/lima/lima_sched.c:11: include/drm/gpu_scheduler.h:530:45: note: expected 'struct workqueue_struct *' but argument is of type 'int' 530 | struct workqueue_struct *submit_wq, | ~~~~~~~~~~~~~~~~~~~~~~~~~^~~~~~~~~ In file included from include/uapi/linux/posix_types.h:5, from include/uapi/linux/types.h:14, from include/linux/types.h:6, from include/linux/io.h:9, from include/linux/iosys-map.h:10, from drivers/gpu/drm/lima/lima_sched.c:4: >> include/linux/stddef.h:8:14: warning: passing argument 4 of 'drm_sched_init' makes integer from pointer without a cast [-Wint-conversion] 8 | #define NULL ((void *)0) | ^~~~~~~~~~~ | | | void * drivers/gpu/drm/lima/lima_sched.c:492:57: note: in expansion of macro 'NULL' 492 | DRM_SCHED_PRIORITY_COUNT, NULL, 1, | ^~~~ include/drm/gpu_scheduler.h:531:24: note: expected 'u32' {aka 'unsigned int'} but argument is of type 'void *' 531 | u32 num_rqs, uint32_t hw_submission, unsigned hang_limit, | ~~~~^~~~~~~ -- drivers/gpu/drm/v3d/v3d_sched.c: In function 'v3d_sched_init': >> drivers/gpu/drm/v3d/v3d_sched.c:391:50: warning: passing argument 3 of 'drm_sched_init' makes pointer from integer without a cast [-Wint-conversion] 391 | &v3d_bin_sched_ops, DRM_SCHED_PRIORITY_COUNT, NULL, | ^~~~~~~~~~~~~~~~~~~~~~~~ | | | int In file included from drivers/gpu/drm/v3d/v3d_drv.h:12, from drivers/gpu/drm/v3d/v3d_sched.c:23: include/drm/gpu_scheduler.h:530:45: note: expected 'struct workqueue_struct *' but argument is of type 'int' 530 | struct workqueue_struct *submit_wq, | ~~~~~~~~~~~~~~~~~~~~~~~~~^~~~~~~~~ In file included from include/uapi/linux/posix_types.h:5, from include/uapi/linux/types.h:14, from include/linux/types.h:6, from include/linux/kasan-checks.h:5, from include/asm-generic/rwonce.h:26, from ./arch/m68k/include/generated/asm/rwonce.h:1, from include/linux/compiler.h:246, from include/linux/err.h:5, from include/linux/kthread.h:5, from drivers/gpu/drm/v3d/v3d_sched.c:21: >> include/linux/stddef.h:8:14: warning: passing argument 4 of 'drm_sched_init' makes integer from pointer without a cast [-Wint-conversion] 8 | #define NULL ((void *)0) | ^~~~~~~~~~~ | | | void * drivers/gpu/drm/v3d/v3d_sched.c:391:76: note: in expansion of macro 'NULL' 391 | &v3d_bin_sched_ops, DRM_SCHED_PRIORITY_COUNT, NULL, | ^~~~ include/drm/gpu_scheduler.h:531:24: note: expected 'u32' {aka 'unsigned int'} but argument is of type 'void *' 531 | u32 num_rqs, uint32_t hw_submission, unsigned hang_limit, | ~~~~^~~~~~~ drivers/gpu/drm/v3d/v3d_sched.c:399:53: warning: passing argument 3 of 'drm_sched_init' makes pointer from integer without a cast [-Wint-conversion] 399 | &v3d_render_sched_ops, DRM_SCHED_PRIORITY_COUNT, | ^~~~~~~~~~~~~~~~~~~~~~~~ | | | int include/drm/gpu_scheduler.h:530:45: note: expected 'struct workqueue_struct *' but argument is of type 'int' 530 | struct workqueue_struct *submit_wq, | ~~~~~~~~~~~~~~~~~~~~~~~~~^~~~~~~~~ >> include/linux/stddef.h:8:14: warning: passing argument 4 of 'drm_sched_init' makes integer from pointer without a cast [-Wint-conversion] 8 | #define NULL ((void *)0) | ^~~~~~~~~~~ | | | void * drivers/gpu/drm/v3d/v3d_sched.c:400:30: note: in expansion of macro 'NULL' 400 | NULL, hw_jobs_limit, job_hang_limit, | ^~~~ include/drm/gpu_scheduler.h:531:24: note: expected 'u32' {aka 'unsigned int'} but argument is of type 'void *' 531 | u32 num_rqs, uint32_t hw_submission, unsigned hang_limit, | ~~~~^~~~~~~ drivers/gpu/drm/v3d/v3d_sched.c:407:50: warning: passing argument 3 of 'drm_sched_init' makes pointer from integer without a cast [-Wint-conversion] 407 | &v3d_tfu_sched_ops, DRM_SCHED_PRIORITY_COUNT, NULL, | ^~~~~~~~~~~~~~~~~~~~~~~~ | | | int include/drm/gpu_scheduler.h:530:45: note: expected 'struct workqueue_struct *' but argument is of type 'int' 530 | struct workqueue_struct *submit_wq, | ~~~~~~~~~~~~~~~~~~~~~~~~~^~~~~~~~~ >> include/linux/stddef.h:8:14: warning: passing argument 4 of 'drm_sched_init' makes integer from pointer without a cast [-Wint-conversion] 8 | #define NULL ((void *)0) | ^~~~~~~~~~~ | | | void * drivers/gpu/drm/v3d/v3d_sched.c:407:76: note: in expansion of macro 'NULL' 407 | &v3d_tfu_sched_ops, DRM_SCHED_PRIORITY_COUNT, NULL, | ^~~~ include/drm/gpu_scheduler.h:531:24: note: expected 'u32' {aka 'unsigned int'} but argument is of type 'void *' 531 | u32 num_rqs, uint32_t hw_submission, unsigned hang_limit, | ~~~~^~~~~~~ drivers/gpu/drm/v3d/v3d_sched.c:417:38: warning: passing argument 3 of 'drm_sched_init' makes pointer from integer without a cast [-Wint-conversion] 417 | DRM_SCHED_PRIORITY_COUNT, NULL, | ^~~~~~~~~~~~~~~~~~~~~~~~ | | | int include/drm/gpu_scheduler.h:530:45: note: expected 'struct workqueue_struct *' but argument is of type 'int' 530 | struct workqueue_struct *submit_wq, | ~~~~~~~~~~~~~~~~~~~~~~~~~^~~~~~~~~ >> include/linux/stddef.h:8:14: warning: passing argument 4 of 'drm_sched_init' makes integer from pointer without a cast [-Wint-conversion] 8 | #define NULL ((void *)0) | ^~~~~~~~~~~ | | | void * drivers/gpu/drm/v3d/v3d_sched.c:417:64: note: in expansion of macro 'NULL' 417 | DRM_SCHED_PRIORITY_COUNT, NULL, | ^~~~ include/drm/gpu_scheduler.h:531:24: note: expected 'u32' {aka 'unsigned int'} but argument is of type 'void *' 531 | u32 num_rqs, uint32_t hw_submission, unsigned hang_limit, | ~~~~^~~~~~~ drivers/gpu/drm/v3d/v3d_sched.c:426:38: warning: passing argument 3 of 'drm_sched_init' makes pointer from integer without a cast [-Wint-conversion] 426 | DRM_SCHED_PRIORITY_COUNT, NULL, | ^~~~~~~~~~~~~~~~~~~~~~~~ | | | int include/drm/gpu_scheduler.h:530:45: note: expected 'struct workqueue_struct *' but argument is of type 'int' 530 | struct workqueue_struct *submit_wq, | ~~~~~~~~~~~~~~~~~~~~~~~~~^~~~~~~~~ >> include/linux/stddef.h:8:14: warning: passing argument 4 of 'drm_sched_init' makes integer from pointer without a cast [-Wint-conversion] 8 | #define NULL ((void *)0) | ^~~~~~~~~~~ | | | void * drivers/gpu/drm/v3d/v3d_sched.c:426:64: note: in expansion of macro 'NULL' 426 | DRM_SCHED_PRIORITY_COUNT, NULL, | ^~~~ include/drm/gpu_scheduler.h:531:24: note: expected 'u32' {aka 'unsigned int'} but argument is of type 'void *' 531 | u32 num_rqs, uint32_t hw_submission, unsigned hang_limit, | ~~~~^~~~~~~ vim +/drm_sched_init +138 drivers/gpu/drm/etnaviv/etnaviv_sched.c 132 133 int etnaviv_sched_init(struct etnaviv_gpu *gpu) 134 { 135 int ret; 136 137 ret = drm_sched_init(&gpu->sched, &etnaviv_sched_ops, > 138 DRM_SCHED_PRIORITY_COUNT, NULL, 139 etnaviv_hw_jobs_limit, etnaviv_job_hang_limit, 140 msecs_to_jiffies(500), NULL, NULL, 141 dev_name(gpu->dev), gpu->dev); 142 if (ret) 143 return ret; 144 145 return 0; 146 } 147
Hi, On 2023-10-26 02:33, kernel test robot wrote: > Hi Matthew, > > kernel test robot noticed the following build warnings: > > [auto build test WARNING on 201c8a7bd1f3f415920a2df4b8a8817e973f42fe] > > url: https://github.com/intel-lab-lkp/linux/commits/Matthew-Brost/drm-sched-Add-drm_sched_wqueue_-helpers/20231026-121313 > base: 201c8a7bd1f3f415920a2df4b8a8817e973f42fe > patch link: https://lore.kernel.org/r/20231026041236.1273694-4-matthew.brost%40intel.com > patch subject: [PATCH v7 3/6] drm/sched: Convert the GPU scheduler to variable number of run-queues > config: m68k-allyesconfig (https://download.01.org/0day-ci/archive/20231026/202310261439.3rbAtEoB-lkp@intel.com/config) > compiler: m68k-linux-gcc (GCC) 13.2.0 > reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20231026/202310261439.3rbAtEoB-lkp@intel.com/reproduce) > > If you fix the issue in a separate patch/commit (i.e. not just a new version of > the same patch/commit), kindly add following tags > | Reported-by: kernel test robot <lkp@intel.com> > | Closes: https://lore.kernel.org/oe-kbuild-all/202310261439.3rbAtEoB-lkp@intel.com/ > > All warnings (new ones prefixed by >>): > > drivers/gpu/drm/etnaviv/etnaviv_sched.c: In function 'etnaviv_sched_init': >>> drivers/gpu/drm/etnaviv/etnaviv_sched.c:138:30: warning: passing argument 3 of 'drm_sched_init' makes pointer from integer without a cast [-Wint-conversion] > 138 | DRM_SCHED_PRIORITY_COUNT, NULL, > | ^~~~~~~~~~~~~~~~~~~~~~~~ > | | > | int > In file included from drivers/gpu/drm/etnaviv/etnaviv_drv.h:20, > from drivers/gpu/drm/etnaviv/etnaviv_sched.c:8: > include/drm/gpu_scheduler.h:530:45: note: expected 'struct workqueue_struct *' but argument is of type 'int' > 530 | struct workqueue_struct *submit_wq, > | ~~~~~~~~~~~~~~~~~~~~~~~~~^~~~~~~~~ > In file included from include/uapi/linux/posix_types.h:5, > from include/uapi/linux/types.h:14, > from include/linux/types.h:6, > from include/linux/kasan-checks.h:5, > from include/asm-generic/rwonce.h:26, > from ./arch/m68k/include/generated/asm/rwonce.h:1, > from include/linux/compiler.h:246, > from include/linux/build_bug.h:5, > from include/linux/init.h:5, > from include/linux/moduleparam.h:5, > from drivers/gpu/drm/etnaviv/etnaviv_sched.c:6: The reason for this compilation failure is that this patch is completely mangled and nothing like the patch I posted. My patch is: https://lore.kernel.org/all/20231023032251.164775-1-luben.tuikov@amd.com/ Save it raw to your disk from this link: https://lore.kernel.org/all/20231023032251.164775-1-luben.tuikov@amd.com/raw And apply it with "git am <file-name>" on top of your clean tree, e.g. drm-misc-next. THEN, after that, apply your patches. It should then compile without any problems. Just looking at the first hunk in my patch: > diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c > index 2b8356699f235d..251995a90bbe69 100644 > --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c > +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c > @@ -2280,6 +2280,7 @@ static int amdgpu_device_init_schedulers(struct amdgpu_device *adev) > } > > r = drm_sched_init(&ring->sched, &amdgpu_sched_ops, > + DRM_SCHED_PRIORITY_COUNT, > ring->num_hw_submission, 0, > timeout, adev->reset_domain->wq, > ring->sched_score, ring->name, While this looks like this in the version you posted of my patch: > diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c > index b54c4d771104..94d073bfbd13 100644 > --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c > +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c > @@ -2280,6 +2280,7 @@ static int amdgpu_device_init_schedulers(struct amdgpu_device *adev) > } > > r = drm_sched_init(&ring->sched, &amdgpu_sched_ops, NULL, > + DRM_SCHED_PRIORITY_COUNT, > ring->num_hw_submission, 0, > timeout, adev->reset_domain->wq, > ring->sched_score, ring->name, What's that "NULL" doing as the 3rd argument??? And the rest is similarly mangled as well. Please apply my patch AS IS, no local changes, and then apply your patches on top. That should ensure compilation is correct for all, and a more precise review can be had. FWIW, we should've had dynamic sched_rq from the outset as opposed to having to have my patch that now. So imagine that you already have a branch which has dynamic sched_rq, and then you apply your patches--should be a more straightforward and clean application. Regards, Luben >>> include/linux/stddef.h:8:14: warning: passing argument 4 of 'drm_sched_init' makes integer from pointer without a cast [-Wint-conversion] > 8 | #define NULL ((void *)0) > | ^~~~~~~~~~~ > | | > | void * > drivers/gpu/drm/etnaviv/etnaviv_sched.c:138:56: note: in expansion of macro 'NULL' > 138 | DRM_SCHED_PRIORITY_COUNT, NULL, > | ^~~~ > include/drm/gpu_scheduler.h:531:24: note: expected 'u32' {aka 'unsigned int'} but argument is of type 'void *' > 531 | u32 num_rqs, uint32_t hw_submission, unsigned hang_limit, > | ~~~~^~~~~~~ > -- > drivers/gpu/drm/lima/lima_sched.c: In function 'lima_sched_pipe_init': >>> drivers/gpu/drm/lima/lima_sched.c:492:31: warning: passing argument 3 of 'drm_sched_init' makes pointer from integer without a cast [-Wint-conversion] > 492 | DRM_SCHED_PRIORITY_COUNT, NULL, 1, > | ^~~~~~~~~~~~~~~~~~~~~~~~ > | | > | int > In file included from drivers/gpu/drm/lima/lima_sched.h:7, > from drivers/gpu/drm/lima/lima_device.h:12, > from drivers/gpu/drm/lima/lima_ctx.h:10, > from drivers/gpu/drm/lima/lima_drv.h:9, > from drivers/gpu/drm/lima/lima_sched.c:11: > include/drm/gpu_scheduler.h:530:45: note: expected 'struct workqueue_struct *' but argument is of type 'int' > 530 | struct workqueue_struct *submit_wq, > | ~~~~~~~~~~~~~~~~~~~~~~~~~^~~~~~~~~ > In file included from include/uapi/linux/posix_types.h:5, > from include/uapi/linux/types.h:14, > from include/linux/types.h:6, > from include/linux/io.h:9, > from include/linux/iosys-map.h:10, > from drivers/gpu/drm/lima/lima_sched.c:4: >>> include/linux/stddef.h:8:14: warning: passing argument 4 of 'drm_sched_init' makes integer from pointer without a cast [-Wint-conversion] > 8 | #define NULL ((void *)0) > | ^~~~~~~~~~~ > | | > | void * > drivers/gpu/drm/lima/lima_sched.c:492:57: note: in expansion of macro 'NULL' > 492 | DRM_SCHED_PRIORITY_COUNT, NULL, 1, > | ^~~~ > include/drm/gpu_scheduler.h:531:24: note: expected 'u32' {aka 'unsigned int'} but argument is of type 'void *' > 531 | u32 num_rqs, uint32_t hw_submission, unsigned hang_limit, > | ~~~~^~~~~~~ > -- > drivers/gpu/drm/v3d/v3d_sched.c: In function 'v3d_sched_init': >>> drivers/gpu/drm/v3d/v3d_sched.c:391:50: warning: passing argument 3 of 'drm_sched_init' makes pointer from integer without a cast [-Wint-conversion] > 391 | &v3d_bin_sched_ops, DRM_SCHED_PRIORITY_COUNT, NULL, > | ^~~~~~~~~~~~~~~~~~~~~~~~ > | | > | int > In file included from drivers/gpu/drm/v3d/v3d_drv.h:12, > from drivers/gpu/drm/v3d/v3d_sched.c:23: > include/drm/gpu_scheduler.h:530:45: note: expected 'struct workqueue_struct *' but argument is of type 'int' > 530 | struct workqueue_struct *submit_wq, > | ~~~~~~~~~~~~~~~~~~~~~~~~~^~~~~~~~~ > In file included from include/uapi/linux/posix_types.h:5, > from include/uapi/linux/types.h:14, > from include/linux/types.h:6, > from include/linux/kasan-checks.h:5, > from include/asm-generic/rwonce.h:26, > from ./arch/m68k/include/generated/asm/rwonce.h:1, > from include/linux/compiler.h:246, > from include/linux/err.h:5, > from include/linux/kthread.h:5, > from drivers/gpu/drm/v3d/v3d_sched.c:21: >>> include/linux/stddef.h:8:14: warning: passing argument 4 of 'drm_sched_init' makes integer from pointer without a cast [-Wint-conversion] > 8 | #define NULL ((void *)0) > | ^~~~~~~~~~~ > | | > | void * > drivers/gpu/drm/v3d/v3d_sched.c:391:76: note: in expansion of macro 'NULL' > 391 | &v3d_bin_sched_ops, DRM_SCHED_PRIORITY_COUNT, NULL, > | ^~~~ > include/drm/gpu_scheduler.h:531:24: note: expected 'u32' {aka 'unsigned int'} but argument is of type 'void *' > 531 | u32 num_rqs, uint32_t hw_submission, unsigned hang_limit, > | ~~~~^~~~~~~ > drivers/gpu/drm/v3d/v3d_sched.c:399:53: warning: passing argument 3 of 'drm_sched_init' makes pointer from integer without a cast [-Wint-conversion] > 399 | &v3d_render_sched_ops, DRM_SCHED_PRIORITY_COUNT, > | ^~~~~~~~~~~~~~~~~~~~~~~~ > | | > | int > include/drm/gpu_scheduler.h:530:45: note: expected 'struct workqueue_struct *' but argument is of type 'int' > 530 | struct workqueue_struct *submit_wq, > | ~~~~~~~~~~~~~~~~~~~~~~~~~^~~~~~~~~ >>> include/linux/stddef.h:8:14: warning: passing argument 4 of 'drm_sched_init' makes integer from pointer without a cast [-Wint-conversion] > 8 | #define NULL ((void *)0) > | ^~~~~~~~~~~ > | | > | void * > drivers/gpu/drm/v3d/v3d_sched.c:400:30: note: in expansion of macro 'NULL' > 400 | NULL, hw_jobs_limit, job_hang_limit, > | ^~~~ > include/drm/gpu_scheduler.h:531:24: note: expected 'u32' {aka 'unsigned int'} but argument is of type 'void *' > 531 | u32 num_rqs, uint32_t hw_submission, unsigned hang_limit, > | ~~~~^~~~~~~ > drivers/gpu/drm/v3d/v3d_sched.c:407:50: warning: passing argument 3 of 'drm_sched_init' makes pointer from integer without a cast [-Wint-conversion] > 407 | &v3d_tfu_sched_ops, DRM_SCHED_PRIORITY_COUNT, NULL, > | ^~~~~~~~~~~~~~~~~~~~~~~~ > | | > | int > include/drm/gpu_scheduler.h:530:45: note: expected 'struct workqueue_struct *' but argument is of type 'int' > 530 | struct workqueue_struct *submit_wq, > | ~~~~~~~~~~~~~~~~~~~~~~~~~^~~~~~~~~ >>> include/linux/stddef.h:8:14: warning: passing argument 4 of 'drm_sched_init' makes integer from pointer without a cast [-Wint-conversion] > 8 | #define NULL ((void *)0) > | ^~~~~~~~~~~ > | | > | void * > drivers/gpu/drm/v3d/v3d_sched.c:407:76: note: in expansion of macro 'NULL' > 407 | &v3d_tfu_sched_ops, DRM_SCHED_PRIORITY_COUNT, NULL, > | ^~~~ > include/drm/gpu_scheduler.h:531:24: note: expected 'u32' {aka 'unsigned int'} but argument is of type 'void *' > 531 | u32 num_rqs, uint32_t hw_submission, unsigned hang_limit, > | ~~~~^~~~~~~ > drivers/gpu/drm/v3d/v3d_sched.c:417:38: warning: passing argument 3 of 'drm_sched_init' makes pointer from integer without a cast [-Wint-conversion] > 417 | DRM_SCHED_PRIORITY_COUNT, NULL, > | ^~~~~~~~~~~~~~~~~~~~~~~~ > | | > | int > include/drm/gpu_scheduler.h:530:45: note: expected 'struct workqueue_struct *' but argument is of type 'int' > 530 | struct workqueue_struct *submit_wq, > | ~~~~~~~~~~~~~~~~~~~~~~~~~^~~~~~~~~ >>> include/linux/stddef.h:8:14: warning: passing argument 4 of 'drm_sched_init' makes integer from pointer without a cast [-Wint-conversion] > 8 | #define NULL ((void *)0) > | ^~~~~~~~~~~ > | | > | void * > drivers/gpu/drm/v3d/v3d_sched.c:417:64: note: in expansion of macro 'NULL' > 417 | DRM_SCHED_PRIORITY_COUNT, NULL, > | ^~~~ > include/drm/gpu_scheduler.h:531:24: note: expected 'u32' {aka 'unsigned int'} but argument is of type 'void *' > 531 | u32 num_rqs, uint32_t hw_submission, unsigned hang_limit, > | ~~~~^~~~~~~ > drivers/gpu/drm/v3d/v3d_sched.c:426:38: warning: passing argument 3 of 'drm_sched_init' makes pointer from integer without a cast [-Wint-conversion] > 426 | DRM_SCHED_PRIORITY_COUNT, NULL, > | ^~~~~~~~~~~~~~~~~~~~~~~~ > | | > | int > include/drm/gpu_scheduler.h:530:45: note: expected 'struct workqueue_struct *' but argument is of type 'int' > 530 | struct workqueue_struct *submit_wq, > | ~~~~~~~~~~~~~~~~~~~~~~~~~^~~~~~~~~ >>> include/linux/stddef.h:8:14: warning: passing argument 4 of 'drm_sched_init' makes integer from pointer without a cast [-Wint-conversion] > 8 | #define NULL ((void *)0) > | ^~~~~~~~~~~ > | | > | void * > drivers/gpu/drm/v3d/v3d_sched.c:426:64: note: in expansion of macro 'NULL' > 426 | DRM_SCHED_PRIORITY_COUNT, NULL, > | ^~~~ > include/drm/gpu_scheduler.h:531:24: note: expected 'u32' {aka 'unsigned int'} but argument is of type 'void *' > 531 | u32 num_rqs, uint32_t hw_submission, unsigned hang_limit, > | ~~~~^~~~~~~ > > > vim +/drm_sched_init +138 drivers/gpu/drm/etnaviv/etnaviv_sched.c > > 132 > 133 int etnaviv_sched_init(struct etnaviv_gpu *gpu) > 134 { > 135 int ret; > 136 > 137 ret = drm_sched_init(&gpu->sched, &etnaviv_sched_ops, > > 138 DRM_SCHED_PRIORITY_COUNT, NULL, > 139 etnaviv_hw_jobs_limit, etnaviv_job_hang_limit, > 140 msecs_to_jiffies(500), NULL, NULL, > 141 dev_name(gpu->dev), gpu->dev); > 142 if (ret) > 143 return ret; > 144 > 145 return 0; > 146 } > 147 >
Also note that there were no complaints from "kernel test robot <lkp@intel.com>" when I posted my patch (this patch), but there is now, which further shows that there's unwarranted changes. Just follow the steps I outlined below, and we should all be good. Thanks! Regards, Luben On 2023-10-26 05:36, Luben Tuikov wrote: > Hi, > > On 2023-10-26 02:33, kernel test robot wrote: >> Hi Matthew, >> >> kernel test robot noticed the following build warnings: >> >> [auto build test WARNING on 201c8a7bd1f3f415920a2df4b8a8817e973f42fe] >> >> url: https://github.com/intel-lab-lkp/linux/commits/Matthew-Brost/drm-sched-Add-drm_sched_wqueue_-helpers/20231026-121313 >> base: 201c8a7bd1f3f415920a2df4b8a8817e973f42fe >> patch link: https://lore.kernel.org/r/20231026041236.1273694-4-matthew.brost%40intel.com >> patch subject: [PATCH v7 3/6] drm/sched: Convert the GPU scheduler to variable number of run-queues >> config: m68k-allyesconfig (https://download.01.org/0day-ci/archive/20231026/202310261439.3rbAtEoB-lkp@intel.com/config) >> compiler: m68k-linux-gcc (GCC) 13.2.0 >> reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20231026/202310261439.3rbAtEoB-lkp@intel.com/reproduce) >> >> If you fix the issue in a separate patch/commit (i.e. not just a new version of >> the same patch/commit), kindly add following tags >> | Reported-by: kernel test robot <lkp@intel.com> >> | Closes: https://lore.kernel.org/oe-kbuild-all/202310261439.3rbAtEoB-lkp@intel.com/ >> >> All warnings (new ones prefixed by >>): >> >> drivers/gpu/drm/etnaviv/etnaviv_sched.c: In function 'etnaviv_sched_init': >>>> drivers/gpu/drm/etnaviv/etnaviv_sched.c:138:30: warning: passing argument 3 of 'drm_sched_init' makes pointer from integer without a cast [-Wint-conversion] >> 138 | DRM_SCHED_PRIORITY_COUNT, NULL, >> | ^~~~~~~~~~~~~~~~~~~~~~~~ >> | | >> | int >> In file included from drivers/gpu/drm/etnaviv/etnaviv_drv.h:20, >> from drivers/gpu/drm/etnaviv/etnaviv_sched.c:8: >> include/drm/gpu_scheduler.h:530:45: note: expected 'struct workqueue_struct *' but argument is of type 'int' >> 530 | struct workqueue_struct *submit_wq, >> | ~~~~~~~~~~~~~~~~~~~~~~~~~^~~~~~~~~ >> In file included from include/uapi/linux/posix_types.h:5, >> from include/uapi/linux/types.h:14, >> from include/linux/types.h:6, >> from include/linux/kasan-checks.h:5, >> from include/asm-generic/rwonce.h:26, >> from ./arch/m68k/include/generated/asm/rwonce.h:1, >> from include/linux/compiler.h:246, >> from include/linux/build_bug.h:5, >> from include/linux/init.h:5, >> from include/linux/moduleparam.h:5, >> from drivers/gpu/drm/etnaviv/etnaviv_sched.c:6: > > The reason for this compilation failure is that this patch is completely mangled and nothing like the patch I posted. > > My patch is: https://lore.kernel.org/all/20231023032251.164775-1-luben.tuikov@amd.com/ > > Save it raw to your disk from this link: https://lore.kernel.org/all/20231023032251.164775-1-luben.tuikov@amd.com/raw > > And apply it with "git am <file-name>" on top of your clean tree, e.g. drm-misc-next. THEN, after that, > apply your patches. > > It should then compile without any problems. > > Just looking at the first hunk in my patch: > >> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c >> index 2b8356699f235d..251995a90bbe69 100644 >> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c >> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c >> @@ -2280,6 +2280,7 @@ static int amdgpu_device_init_schedulers(struct amdgpu_device *adev) >> } >> >> r = drm_sched_init(&ring->sched, &amdgpu_sched_ops, >> + DRM_SCHED_PRIORITY_COUNT, >> ring->num_hw_submission, 0, >> timeout, adev->reset_domain->wq, >> ring->sched_score, ring->name, > > While this looks like this in the version you posted of my patch: > >> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c >> index b54c4d771104..94d073bfbd13 100644 >> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c >> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c >> @@ -2280,6 +2280,7 @@ static int amdgpu_device_init_schedulers(struct amdgpu_device *adev) >> } >> >> r = drm_sched_init(&ring->sched, &amdgpu_sched_ops, NULL, >> + DRM_SCHED_PRIORITY_COUNT, >> ring->num_hw_submission, 0, >> timeout, adev->reset_domain->wq, >> ring->sched_score, ring->name, > > What's that "NULL" doing as the 3rd argument??? > > And the rest is similarly mangled as well. > > Please apply my patch AS IS, no local changes, and then apply your patches on top. That should ensure compilation is correct for all, > and a more precise review can be had. > > FWIW, we should've had dynamic sched_rq from the outset as opposed to having to have my patch that now. So imagine that you already > have a branch which has dynamic sched_rq, and then you apply your patches--should be a more straightforward and clean application. > > Regards, > Luben > >>>> include/linux/stddef.h:8:14: warning: passing argument 4 of 'drm_sched_init' makes integer from pointer without a cast [-Wint-conversion] >> 8 | #define NULL ((void *)0) >> | ^~~~~~~~~~~ >> | | >> | void * >> drivers/gpu/drm/etnaviv/etnaviv_sched.c:138:56: note: in expansion of macro 'NULL' >> 138 | DRM_SCHED_PRIORITY_COUNT, NULL, >> | ^~~~ >> include/drm/gpu_scheduler.h:531:24: note: expected 'u32' {aka 'unsigned int'} but argument is of type 'void *' >> 531 | u32 num_rqs, uint32_t hw_submission, unsigned hang_limit, >> | ~~~~^~~~~~~ >> -- >> drivers/gpu/drm/lima/lima_sched.c: In function 'lima_sched_pipe_init': >>>> drivers/gpu/drm/lima/lima_sched.c:492:31: warning: passing argument 3 of 'drm_sched_init' makes pointer from integer without a cast [-Wint-conversion] >> 492 | DRM_SCHED_PRIORITY_COUNT, NULL, 1, >> | ^~~~~~~~~~~~~~~~~~~~~~~~ >> | | >> | int >> In file included from drivers/gpu/drm/lima/lima_sched.h:7, >> from drivers/gpu/drm/lima/lima_device.h:12, >> from drivers/gpu/drm/lima/lima_ctx.h:10, >> from drivers/gpu/drm/lima/lima_drv.h:9, >> from drivers/gpu/drm/lima/lima_sched.c:11: >> include/drm/gpu_scheduler.h:530:45: note: expected 'struct workqueue_struct *' but argument is of type 'int' >> 530 | struct workqueue_struct *submit_wq, >> | ~~~~~~~~~~~~~~~~~~~~~~~~~^~~~~~~~~ >> In file included from include/uapi/linux/posix_types.h:5, >> from include/uapi/linux/types.h:14, >> from include/linux/types.h:6, >> from include/linux/io.h:9, >> from include/linux/iosys-map.h:10, >> from drivers/gpu/drm/lima/lima_sched.c:4: >>>> include/linux/stddef.h:8:14: warning: passing argument 4 of 'drm_sched_init' makes integer from pointer without a cast [-Wint-conversion] >> 8 | #define NULL ((void *)0) >> | ^~~~~~~~~~~ >> | | >> | void * >> drivers/gpu/drm/lima/lima_sched.c:492:57: note: in expansion of macro 'NULL' >> 492 | DRM_SCHED_PRIORITY_COUNT, NULL, 1, >> | ^~~~ >> include/drm/gpu_scheduler.h:531:24: note: expected 'u32' {aka 'unsigned int'} but argument is of type 'void *' >> 531 | u32 num_rqs, uint32_t hw_submission, unsigned hang_limit, >> | ~~~~^~~~~~~ >> -- >> drivers/gpu/drm/v3d/v3d_sched.c: In function 'v3d_sched_init': >>>> drivers/gpu/drm/v3d/v3d_sched.c:391:50: warning: passing argument 3 of 'drm_sched_init' makes pointer from integer without a cast [-Wint-conversion] >> 391 | &v3d_bin_sched_ops, DRM_SCHED_PRIORITY_COUNT, NULL, >> | ^~~~~~~~~~~~~~~~~~~~~~~~ >> | | >> | int >> In file included from drivers/gpu/drm/v3d/v3d_drv.h:12, >> from drivers/gpu/drm/v3d/v3d_sched.c:23: >> include/drm/gpu_scheduler.h:530:45: note: expected 'struct workqueue_struct *' but argument is of type 'int' >> 530 | struct workqueue_struct *submit_wq, >> | ~~~~~~~~~~~~~~~~~~~~~~~~~^~~~~~~~~ >> In file included from include/uapi/linux/posix_types.h:5, >> from include/uapi/linux/types.h:14, >> from include/linux/types.h:6, >> from include/linux/kasan-checks.h:5, >> from include/asm-generic/rwonce.h:26, >> from ./arch/m68k/include/generated/asm/rwonce.h:1, >> from include/linux/compiler.h:246, >> from include/linux/err.h:5, >> from include/linux/kthread.h:5, >> from drivers/gpu/drm/v3d/v3d_sched.c:21: >>>> include/linux/stddef.h:8:14: warning: passing argument 4 of 'drm_sched_init' makes integer from pointer without a cast [-Wint-conversion] >> 8 | #define NULL ((void *)0) >> | ^~~~~~~~~~~ >> | | >> | void * >> drivers/gpu/drm/v3d/v3d_sched.c:391:76: note: in expansion of macro 'NULL' >> 391 | &v3d_bin_sched_ops, DRM_SCHED_PRIORITY_COUNT, NULL, >> | ^~~~ >> include/drm/gpu_scheduler.h:531:24: note: expected 'u32' {aka 'unsigned int'} but argument is of type 'void *' >> 531 | u32 num_rqs, uint32_t hw_submission, unsigned hang_limit, >> | ~~~~^~~~~~~ >> drivers/gpu/drm/v3d/v3d_sched.c:399:53: warning: passing argument 3 of 'drm_sched_init' makes pointer from integer without a cast [-Wint-conversion] >> 399 | &v3d_render_sched_ops, DRM_SCHED_PRIORITY_COUNT, >> | ^~~~~~~~~~~~~~~~~~~~~~~~ >> | | >> | int >> include/drm/gpu_scheduler.h:530:45: note: expected 'struct workqueue_struct *' but argument is of type 'int' >> 530 | struct workqueue_struct *submit_wq, >> | ~~~~~~~~~~~~~~~~~~~~~~~~~^~~~~~~~~ >>>> include/linux/stddef.h:8:14: warning: passing argument 4 of 'drm_sched_init' makes integer from pointer without a cast [-Wint-conversion] >> 8 | #define NULL ((void *)0) >> | ^~~~~~~~~~~ >> | | >> | void * >> drivers/gpu/drm/v3d/v3d_sched.c:400:30: note: in expansion of macro 'NULL' >> 400 | NULL, hw_jobs_limit, job_hang_limit, >> | ^~~~ >> include/drm/gpu_scheduler.h:531:24: note: expected 'u32' {aka 'unsigned int'} but argument is of type 'void *' >> 531 | u32 num_rqs, uint32_t hw_submission, unsigned hang_limit, >> | ~~~~^~~~~~~ >> drivers/gpu/drm/v3d/v3d_sched.c:407:50: warning: passing argument 3 of 'drm_sched_init' makes pointer from integer without a cast [-Wint-conversion] >> 407 | &v3d_tfu_sched_ops, DRM_SCHED_PRIORITY_COUNT, NULL, >> | ^~~~~~~~~~~~~~~~~~~~~~~~ >> | | >> | int >> include/drm/gpu_scheduler.h:530:45: note: expected 'struct workqueue_struct *' but argument is of type 'int' >> 530 | struct workqueue_struct *submit_wq, >> | ~~~~~~~~~~~~~~~~~~~~~~~~~^~~~~~~~~ >>>> include/linux/stddef.h:8:14: warning: passing argument 4 of 'drm_sched_init' makes integer from pointer without a cast [-Wint-conversion] >> 8 | #define NULL ((void *)0) >> | ^~~~~~~~~~~ >> | | >> | void * >> drivers/gpu/drm/v3d/v3d_sched.c:407:76: note: in expansion of macro 'NULL' >> 407 | &v3d_tfu_sched_ops, DRM_SCHED_PRIORITY_COUNT, NULL, >> | ^~~~ >> include/drm/gpu_scheduler.h:531:24: note: expected 'u32' {aka 'unsigned int'} but argument is of type 'void *' >> 531 | u32 num_rqs, uint32_t hw_submission, unsigned hang_limit, >> | ~~~~^~~~~~~ >> drivers/gpu/drm/v3d/v3d_sched.c:417:38: warning: passing argument 3 of 'drm_sched_init' makes pointer from integer without a cast [-Wint-conversion] >> 417 | DRM_SCHED_PRIORITY_COUNT, NULL, >> | ^~~~~~~~~~~~~~~~~~~~~~~~ >> | | >> | int >> include/drm/gpu_scheduler.h:530:45: note: expected 'struct workqueue_struct *' but argument is of type 'int' >> 530 | struct workqueue_struct *submit_wq, >> | ~~~~~~~~~~~~~~~~~~~~~~~~~^~~~~~~~~ >>>> include/linux/stddef.h:8:14: warning: passing argument 4 of 'drm_sched_init' makes integer from pointer without a cast [-Wint-conversion] >> 8 | #define NULL ((void *)0) >> | ^~~~~~~~~~~ >> | | >> | void * >> drivers/gpu/drm/v3d/v3d_sched.c:417:64: note: in expansion of macro 'NULL' >> 417 | DRM_SCHED_PRIORITY_COUNT, NULL, >> | ^~~~ >> include/drm/gpu_scheduler.h:531:24: note: expected 'u32' {aka 'unsigned int'} but argument is of type 'void *' >> 531 | u32 num_rqs, uint32_t hw_submission, unsigned hang_limit, >> | ~~~~^~~~~~~ >> drivers/gpu/drm/v3d/v3d_sched.c:426:38: warning: passing argument 3 of 'drm_sched_init' makes pointer from integer without a cast [-Wint-conversion] >> 426 | DRM_SCHED_PRIORITY_COUNT, NULL, >> | ^~~~~~~~~~~~~~~~~~~~~~~~ >> | | >> | int >> include/drm/gpu_scheduler.h:530:45: note: expected 'struct workqueue_struct *' but argument is of type 'int' >> 530 | struct workqueue_struct *submit_wq, >> | ~~~~~~~~~~~~~~~~~~~~~~~~~^~~~~~~~~ >>>> include/linux/stddef.h:8:14: warning: passing argument 4 of 'drm_sched_init' makes integer from pointer without a cast [-Wint-conversion] >> 8 | #define NULL ((void *)0) >> | ^~~~~~~~~~~ >> | | >> | void * >> drivers/gpu/drm/v3d/v3d_sched.c:426:64: note: in expansion of macro 'NULL' >> 426 | DRM_SCHED_PRIORITY_COUNT, NULL, >> | ^~~~ >> include/drm/gpu_scheduler.h:531:24: note: expected 'u32' {aka 'unsigned int'} but argument is of type 'void *' >> 531 | u32 num_rqs, uint32_t hw_submission, unsigned hang_limit, >> | ~~~~^~~~~~~ >> >> >> vim +/drm_sched_init +138 drivers/gpu/drm/etnaviv/etnaviv_sched.c >> >> 132 >> 133 int etnaviv_sched_init(struct etnaviv_gpu *gpu) >> 134 { >> 135 int ret; >> 136 >> 137 ret = drm_sched_init(&gpu->sched, &etnaviv_sched_ops, >> > 138 DRM_SCHED_PRIORITY_COUNT, NULL, >> 139 etnaviv_hw_jobs_limit, etnaviv_job_hang_limit, >> 140 msecs_to_jiffies(500), NULL, NULL, >> 141 dev_name(gpu->dev), gpu->dev); >> 142 if (ret) >> 143 return ret; >> 144 >> 145 return 0; >> 146 } >> 147 >> >
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index b54c4d771104..94d073bfbd13 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -2280,6 +2280,7 @@ static int amdgpu_device_init_schedulers(struct amdgpu_device *adev) } r = drm_sched_init(&ring->sched, &amdgpu_sched_ops, NULL, + DRM_SCHED_PRIORITY_COUNT, ring->num_hw_submission, 0, timeout, adev->reset_domain->wq, ring->sched_score, ring->name, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c index 78476bc75b4e..1f357198533f 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c @@ -325,8 +325,8 @@ void amdgpu_job_stop_all_jobs_on_sched(struct drm_gpu_scheduler *sched) int i; /* Signal all jobs not yet scheduled */ - for (i = DRM_SCHED_PRIORITY_COUNT - 1; i >= DRM_SCHED_PRIORITY_MIN; i--) { - struct drm_sched_rq *rq = &sched->sched_rq[i]; + for (i = sched->num_rqs - 1; i >= DRM_SCHED_PRIORITY_MIN; i--) { + struct drm_sched_rq *rq = sched->sched_rq[i]; spin_lock(&rq->lock); list_for_each_entry(s_entity, &rq->entities, list) { while ((s_job = to_drm_sched_job(spsc_queue_pop(&s_entity->job_queue)))) { diff --git a/drivers/gpu/drm/etnaviv/etnaviv_sched.c b/drivers/gpu/drm/etnaviv/etnaviv_sched.c index 618a804ddc34..396334984e4d 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_sched.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_sched.c @@ -134,7 +134,8 @@ int etnaviv_sched_init(struct etnaviv_gpu *gpu) { int ret; - ret = drm_sched_init(&gpu->sched, &etnaviv_sched_ops, NULL, + ret = drm_sched_init(&gpu->sched, &etnaviv_sched_ops, + DRM_SCHED_PRIORITY_COUNT, NULL, etnaviv_hw_jobs_limit, etnaviv_job_hang_limit, msecs_to_jiffies(500), NULL, NULL, dev_name(gpu->dev), gpu->dev); diff --git a/drivers/gpu/drm/lima/lima_sched.c b/drivers/gpu/drm/lima/lima_sched.c index 8d858aed0e56..23a6276f1332 100644 --- a/drivers/gpu/drm/lima/lima_sched.c +++ b/drivers/gpu/drm/lima/lima_sched.c @@ -488,7 +488,8 @@ int lima_sched_pipe_init(struct lima_sched_pipe *pipe, const char *name) INIT_WORK(&pipe->recover_work, lima_sched_recover_work); - return drm_sched_init(&pipe->base, &lima_sched_ops, NULL, 1, + return drm_sched_init(&pipe->base, &lima_sched_ops, + DRM_SCHED_PRIORITY_COUNT, NULL, 1, lima_job_hang_limit, msecs_to_jiffies(timeout), NULL, NULL, name, pipe->ldev->dev); diff --git a/drivers/gpu/drm/msm/msm_ringbuffer.c b/drivers/gpu/drm/msm/msm_ringbuffer.c index 1097f8e93d6b..935154979fc2 100644 --- a/drivers/gpu/drm/msm/msm_ringbuffer.c +++ b/drivers/gpu/drm/msm/msm_ringbuffer.c @@ -94,7 +94,8 @@ struct msm_ringbuffer *msm_ringbuffer_new(struct msm_gpu *gpu, int id, /* currently managing hangcheck ourselves: */ sched_timeout = MAX_SCHEDULE_TIMEOUT; - ret = drm_sched_init(&ring->sched, &msm_sched_ops, NULL, + ret = drm_sched_init(&ring->sched, &msm_sched_ops, + DRM_SCHED_PRIORITY_COUNT, NULL, num_hw_submissions, 0, sched_timeout, NULL, NULL, to_msm_bo(ring->bo)->name, gpu->dev->dev); diff --git a/drivers/gpu/drm/nouveau/nouveau_sched.c b/drivers/gpu/drm/nouveau/nouveau_sched.c index 4c959dec42b3..c4ba56b1a6dd 100644 --- a/drivers/gpu/drm/nouveau/nouveau_sched.c +++ b/drivers/gpu/drm/nouveau/nouveau_sched.c @@ -436,6 +436,7 @@ int nouveau_sched_init(struct nouveau_drm *drm) return -ENOMEM; return drm_sched_init(sched, &nouveau_sched_ops, NULL, + DRM_SCHED_PRIORITY_COUNT, NOUVEAU_SCHED_HW_SUBMISSIONS, 0, job_hang_limit, NULL, NULL, "nouveau_sched", drm->dev->dev); } diff --git a/drivers/gpu/drm/panfrost/panfrost_job.c b/drivers/gpu/drm/panfrost/panfrost_job.c index 934b7b930c76..205d62c04f96 100644 --- a/drivers/gpu/drm/panfrost/panfrost_job.c +++ b/drivers/gpu/drm/panfrost/panfrost_job.c @@ -852,7 +852,8 @@ int panfrost_job_init(struct panfrost_device *pfdev) js->queue[j].fence_context = dma_fence_context_alloc(1); ret = drm_sched_init(&js->queue[j].sched, - &panfrost_sched_ops, NULL, + &panfrost_sched_ops, + DRM_SCHED_PRIORITY_COUNT, NULL, nentries, 0, msecs_to_jiffies(JOB_TIMEOUT_MS), pfdev->reset.wq, diff --git a/drivers/gpu/drm/scheduler/sched_entity.c b/drivers/gpu/drm/scheduler/sched_entity.c index a42763e1429d..409e4256f6e7 100644 --- a/drivers/gpu/drm/scheduler/sched_entity.c +++ b/drivers/gpu/drm/scheduler/sched_entity.c @@ -75,8 +75,20 @@ int drm_sched_entity_init(struct drm_sched_entity *entity, RCU_INIT_POINTER(entity->last_scheduled, NULL); RB_CLEAR_NODE(&entity->rb_tree_node); - if(num_sched_list) - entity->rq = &sched_list[0]->sched_rq[entity->priority]; + if (!sched_list[0]->sched_rq) { + /* Warn drivers not to do this and to fix their DRM + * calling order. + */ + pr_warn("%s: called with uninitialized scheduler\n", __func__); + } else if (num_sched_list) { + /* The "priority" of an entity cannot exceed the number + * of run-queues of a scheduler. + */ + if (entity->priority >= sched_list[0]->num_rqs) + entity->priority = max_t(u32, sched_list[0]->num_rqs, + DRM_SCHED_PRIORITY_MIN); + entity->rq = sched_list[0]->sched_rq[entity->priority]; + } init_completion(&entity->entity_idle); @@ -533,7 +545,7 @@ void drm_sched_entity_select_rq(struct drm_sched_entity *entity) spin_lock(&entity->rq_lock); sched = drm_sched_pick_best(entity->sched_list, entity->num_sched_list); - rq = sched ? &sched->sched_rq[entity->priority] : NULL; + rq = sched ? sched->sched_rq[entity->priority] : NULL; if (rq != entity->rq) { drm_sched_rq_remove_entity(entity->rq, entity); entity->rq = rq; diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c index 3a955b8acc4e..b22157e920d4 100644 --- a/drivers/gpu/drm/scheduler/sched_main.c +++ b/drivers/gpu/drm/scheduler/sched_main.c @@ -641,8 +641,14 @@ int drm_sched_job_init(struct drm_sched_job *job, struct drm_sched_entity *entity, void *owner) { - if (!entity->rq) + if (!entity->rq) { + /* This will most likely be followed by missing frames + * or worse--a blank screen--leave a trail in the + * logs, so this can be debugged easier. + */ + drm_err(job->sched, "%s: entity has no rq!\n", __func__); return -ENOENT; + } job->entity = entity; job->s_fence = drm_sched_fence_alloc(entity, owner); @@ -680,7 +686,7 @@ void drm_sched_job_arm(struct drm_sched_job *job) sched = entity->rq->sched; job->sched = sched; - job->s_priority = entity->rq - sched->sched_rq; + job->s_priority = entity->priority; job->id = atomic64_inc_return(&sched->job_id_count); drm_sched_fence_init(job->s_fence, job->entity); @@ -897,10 +903,10 @@ drm_sched_select_entity(struct drm_gpu_scheduler *sched) return NULL; /* Kernel run queue has higher priority than normal run queue*/ - for (i = DRM_SCHED_PRIORITY_COUNT - 1; i >= DRM_SCHED_PRIORITY_MIN; i--) { + for (i = sched->num_rqs - 1; i >= DRM_SCHED_PRIORITY_MIN; i--) { entity = drm_sched_policy == DRM_SCHED_POLICY_FIFO ? - drm_sched_rq_select_entity_fifo(&sched->sched_rq[i]) : - drm_sched_rq_select_entity_rr(&sched->sched_rq[i]); + drm_sched_rq_select_entity_fifo(sched->sched_rq[i]) : + drm_sched_rq_select_entity_rr(sched->sched_rq[i]); if (entity) break; } @@ -1065,6 +1071,7 @@ static void drm_sched_main(struct work_struct *w) * @ops: backend operations for this scheduler * @submit_wq: workqueue to use for submission. If NULL, an ordered wq is * allocated and used + * @num_rqs: number of runqueues, one for each priority, up to DRM_SCHED_PRIORITY_COUNT * @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 @@ -1079,11 +1086,12 @@ static void drm_sched_main(struct work_struct *w) int drm_sched_init(struct drm_gpu_scheduler *sched, const struct drm_sched_backend_ops *ops, struct workqueue_struct *submit_wq, - unsigned hw_submission, unsigned hang_limit, + u32 num_rqs, unsigned hw_submission, unsigned hang_limit, long timeout, struct workqueue_struct *timeout_wq, atomic_t *score, const char *name, struct device *dev) { - int i; + int i, ret; + sched->ops = ops; sched->hw_submission_limit = hw_submission; sched->name = name; @@ -1102,8 +1110,36 @@ int drm_sched_init(struct drm_gpu_scheduler *sched, sched->hang_limit = hang_limit; sched->score = score ? score : &sched->_score; sched->dev = dev; - for (i = DRM_SCHED_PRIORITY_MIN; i < DRM_SCHED_PRIORITY_COUNT; i++) - drm_sched_rq_init(sched, &sched->sched_rq[i]); + + if (num_rqs > DRM_SCHED_PRIORITY_COUNT) { + /* This is a gross violation--tell drivers what the problem is. + */ + drm_err(sched, "%s: num_rqs cannot be greater than DRM_SCHED_PRIORITY_COUNT\n", + __func__); + return -EINVAL; + } else if (sched->sched_rq) { + /* Not an error, but warn anyway so drivers can + * fine-tune their DRM calling order, and return all + * is good. + */ + drm_warn(sched, "%s: scheduler already initialized!\n", __func__); + return 0; + } + + sched->sched_rq = kmalloc_array(num_rqs, sizeof(*sched->sched_rq), + GFP_KERNEL | __GFP_ZERO); + if (!sched->sched_rq) { + drm_err(sched, "%s: out of memory for sched_rq\n", __func__); + return -ENOMEM; + } + sched->num_rqs = num_rqs; + ret = -ENOMEM; + for (i = DRM_SCHED_PRIORITY_MIN; i < sched->num_rqs; i++) { + sched->sched_rq[i] = kzalloc(sizeof(*sched->sched_rq[i]), GFP_KERNEL); + if (!sched->sched_rq[i]) + goto Out_unroll; + drm_sched_rq_init(sched, sched->sched_rq[i]); + } init_waitqueue_head(&sched->job_scheduled); INIT_LIST_HEAD(&sched->pending_list); @@ -1117,6 +1153,14 @@ int drm_sched_init(struct drm_gpu_scheduler *sched, sched->ready = true; return 0; + +Out_unroll: + for (--i ; i >= DRM_SCHED_PRIORITY_MIN; i--) + kfree(sched->sched_rq[i]); + kfree(sched->sched_rq); + sched->sched_rq = NULL; + drm_err(sched, "%s: Failed to setup GPU scheduler--out of memory\n", __func__); + return ret; } EXPORT_SYMBOL(drm_sched_init); @@ -1134,8 +1178,8 @@ void drm_sched_fini(struct drm_gpu_scheduler *sched) drm_sched_wqueue_stop(sched); - for (i = DRM_SCHED_PRIORITY_COUNT - 1; i >= DRM_SCHED_PRIORITY_MIN; i--) { - struct drm_sched_rq *rq = &sched->sched_rq[i]; + for (i = sched->num_rqs - 1; i >= DRM_SCHED_PRIORITY_MIN; i--) { + struct drm_sched_rq *rq = sched->sched_rq[i]; spin_lock(&rq->lock); list_for_each_entry(s_entity, &rq->entities, list) @@ -1146,7 +1190,7 @@ void drm_sched_fini(struct drm_gpu_scheduler *sched) */ s_entity->stopped = true; spin_unlock(&rq->lock); - + kfree(sched->sched_rq[i]); } /* Wakeup everyone stuck in drm_sched_entity_flush for this scheduler */ @@ -1158,6 +1202,8 @@ void drm_sched_fini(struct drm_gpu_scheduler *sched) if (sched->own_submit_wq) destroy_workqueue(sched->submit_wq); sched->ready = false; + kfree(sched->sched_rq); + sched->sched_rq = NULL; } EXPORT_SYMBOL(drm_sched_fini); @@ -1184,9 +1230,10 @@ void drm_sched_increase_karma(struct drm_sched_job *bad) if (bad->s_priority != DRM_SCHED_PRIORITY_KERNEL) { atomic_inc(&bad->karma); - for (i = DRM_SCHED_PRIORITY_MIN; i < DRM_SCHED_PRIORITY_KERNEL; + for (i = DRM_SCHED_PRIORITY_MIN; + i < min_t(typeof(sched->num_rqs), sched->num_rqs, DRM_SCHED_PRIORITY_KERNEL); i++) { - struct drm_sched_rq *rq = &sched->sched_rq[i]; + struct drm_sched_rq *rq = sched->sched_rq[i]; spin_lock(&rq->lock); list_for_each_entry_safe(entity, tmp, &rq->entities, list) { diff --git a/drivers/gpu/drm/v3d/v3d_sched.c b/drivers/gpu/drm/v3d/v3d_sched.c index 38e092ea41e6..175c3e30647a 100644 --- a/drivers/gpu/drm/v3d/v3d_sched.c +++ b/drivers/gpu/drm/v3d/v3d_sched.c @@ -388,7 +388,7 @@ v3d_sched_init(struct v3d_dev *v3d) int ret; ret = drm_sched_init(&v3d->queue[V3D_BIN].sched, - &v3d_bin_sched_ops, NULL, + &v3d_bin_sched_ops, DRM_SCHED_PRIORITY_COUNT, NULL, hw_jobs_limit, job_hang_limit, msecs_to_jiffies(hang_limit_ms), NULL, NULL, "v3d_bin", v3d->drm.dev); @@ -396,15 +396,15 @@ v3d_sched_init(struct v3d_dev *v3d) return ret; ret = drm_sched_init(&v3d->queue[V3D_RENDER].sched, - &v3d_render_sched_ops, NULL, - hw_jobs_limit, job_hang_limit, + &v3d_render_sched_ops, DRM_SCHED_PRIORITY_COUNT, + NULL, hw_jobs_limit, job_hang_limit, msecs_to_jiffies(hang_limit_ms), NULL, NULL, "v3d_render", v3d->drm.dev); if (ret) goto fail; ret = drm_sched_init(&v3d->queue[V3D_TFU].sched, - &v3d_tfu_sched_ops, NULL, + &v3d_tfu_sched_ops, DRM_SCHED_PRIORITY_COUNT, NULL, hw_jobs_limit, job_hang_limit, msecs_to_jiffies(hang_limit_ms), NULL, NULL, "v3d_tfu", v3d->drm.dev); @@ -413,7 +413,8 @@ v3d_sched_init(struct v3d_dev *v3d) if (v3d_has_csd(v3d)) { ret = drm_sched_init(&v3d->queue[V3D_CSD].sched, - &v3d_csd_sched_ops, NULL, + &v3d_csd_sched_ops, + DRM_SCHED_PRIORITY_COUNT, NULL, hw_jobs_limit, job_hang_limit, msecs_to_jiffies(hang_limit_ms), NULL, NULL, "v3d_csd", v3d->drm.dev); @@ -421,7 +422,8 @@ v3d_sched_init(struct v3d_dev *v3d) goto fail; ret = drm_sched_init(&v3d->queue[V3D_CACHE_CLEAN].sched, - &v3d_cache_clean_sched_ops, NULL, + &v3d_cache_clean_sched_ops, + DRM_SCHED_PRIORITY_COUNT, NULL, hw_jobs_limit, job_hang_limit, msecs_to_jiffies(hang_limit_ms), NULL, NULL, "v3d_cache_clean", v3d->drm.dev); diff --git a/include/drm/gpu_scheduler.h b/include/drm/gpu_scheduler.h index 211bd3cdabdc..1d52b8bbb06c 100644 --- a/include/drm/gpu_scheduler.h +++ b/include/drm/gpu_scheduler.h @@ -472,7 +472,9 @@ struct drm_sched_backend_ops { * @hw_submission_limit: the max size of the hardware queue. * @timeout: the time after which a job is removed from the scheduler. * @name: name of the ring for which this scheduler is being used. - * @sched_rq: priority wise array of run queues. + * @num_rqs: Number of run-queues. This is at most DRM_SCHED_PRIORITY_COUNT, + * as there's usually one run-queue per priority, but could be less. + * @sched_rq: An allocated array of run-queues of size @num_rqs; * @job_scheduled: once @drm_sched_entity_do_release is called the scheduler * waits on this wait queue until all the scheduled jobs are * finished. @@ -502,7 +504,8 @@ struct drm_gpu_scheduler { uint32_t hw_submission_limit; long timeout; const char *name; - struct drm_sched_rq sched_rq[DRM_SCHED_PRIORITY_COUNT]; + u32 num_rqs; + struct drm_sched_rq **sched_rq; wait_queue_head_t job_scheduled; atomic_t hw_rq_count; atomic64_t job_id_count; @@ -525,7 +528,7 @@ struct drm_gpu_scheduler { int drm_sched_init(struct drm_gpu_scheduler *sched, const struct drm_sched_backend_ops *ops, struct workqueue_struct *submit_wq, - uint32_t hw_submission, unsigned hang_limit, + u32 num_rqs, uint32_t hw_submission, unsigned hang_limit, long timeout, struct workqueue_struct *timeout_wq, atomic_t *score, const char *name, struct device *dev);