From: Rob Clark <robdclark at chromium.org> Simplify the exec path (removing a legacy optimization) and convert to drm_exec. One drm_exec patch to allow passing in the expected # of GEM objects to avoid re-allocation. I'd be a bit happier if I could avoid the extra objects table allocation in drm_exec in the first place, but wasn't really happy with any of the things I tried to get rid of that. v2: updates in 6/7 and other nit-addressing Rob Clark (7): drm/msm/gem: Remove "valid" tracking drm/msm/gem: Remove submit_unlock_unpin_bo() drm/msm/gem: Don't queue job to sched in error cases drm/msm/gem: Split out submit_unpin_objects() helper drm/msm/gem: Cleanup submit_cleanup_bo() drm/exec: Pass in initial # of objects drm/msm/gem: Convert to drm_exec .../gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c | 8 +- drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c | 2 +- drivers/gpu/drm/amd/amdgpu/amdgpu_csa.c | 4 +- drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c | 4 +- drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c | 4 +- drivers/gpu/drm/amd/amdgpu/amdgpu_umsch_mm.c | 4 +- drivers/gpu/drm/amd/amdkfd/kfd_svm.c | 2 +- drivers/gpu/drm/drm_exec.c | 13 +- drivers/gpu/drm/msm/Kconfig | 1 + drivers/gpu/drm/msm/msm_gem.h | 13 +- drivers/gpu/drm/msm/msm_gem_submit.c | 199 +++++------------- drivers/gpu/drm/msm/msm_ringbuffer.c | 3 +- drivers/gpu/drm/nouveau/nouveau_exec.c | 2 +- drivers/gpu/drm/nouveau/nouveau_uvmm.c | 2 +- drivers/gpu/drm/tests/drm_exec_test.c | 16 +- include/drm/drm_exec.h | 2 +- 16 files changed, 92 insertions(+), 187 deletions(-) -- 2.42.0
Rob Clark
2023-Nov-21 00:38 UTC
[Nouveau] [PATCH v2 6/7] drm/exec: Pass in initial # of objects
From: Rob Clark <robdclark at chromium.org> In cases where the # is known ahead of time, it is silly to do the table resize dance. Signed-off-by: Rob Clark <robdclark at chromium.org> Reviewed-by: Christian K?nig <christian.koenig at amd.com> --- drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c | 8 ++++---- drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c | 2 +- drivers/gpu/drm/amd/amdgpu/amdgpu_csa.c | 4 ++-- drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c | 4 ++-- drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c | 4 ++-- drivers/gpu/drm/amd/amdgpu/amdgpu_umsch_mm.c | 4 ++-- drivers/gpu/drm/amd/amdkfd/kfd_svm.c | 2 +- drivers/gpu/drm/drm_exec.c | 13 ++++++++++--- drivers/gpu/drm/nouveau/nouveau_exec.c | 2 +- drivers/gpu/drm/nouveau/nouveau_uvmm.c | 2 +- drivers/gpu/drm/tests/drm_exec_test.c | 16 ++++++++-------- include/drm/drm_exec.h | 2 +- 12 files changed, 35 insertions(+), 28 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c index 41fbc4fd0fac..0bd3c4a6267a 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c @@ -1137,7 +1137,7 @@ static int reserve_bo_and_vm(struct kgd_mem *mem, ctx->n_vms = 1; ctx->sync = &mem->sync; - drm_exec_init(&ctx->exec, DRM_EXEC_INTERRUPTIBLE_WAIT); + drm_exec_init(&ctx->exec, DRM_EXEC_INTERRUPTIBLE_WAIT, 0); drm_exec_until_all_locked(&ctx->exec) { ret = amdgpu_vm_lock_pd(vm, &ctx->exec, 2); drm_exec_retry_on_contention(&ctx->exec); @@ -1176,7 +1176,7 @@ static int reserve_bo_and_cond_vms(struct kgd_mem *mem, int ret; ctx->sync = &mem->sync; - drm_exec_init(&ctx->exec, DRM_EXEC_INTERRUPTIBLE_WAIT); + drm_exec_init(&ctx->exec, DRM_EXEC_INTERRUPTIBLE_WAIT, 0); drm_exec_until_all_locked(&ctx->exec) { ctx->n_vms = 0; list_for_each_entry(entry, &mem->attachments, list) { @@ -2552,7 +2552,7 @@ static int validate_invalid_user_pages(struct amdkfd_process_info *process_info) amdgpu_sync_create(&sync); - drm_exec_init(&exec, 0); + drm_exec_init(&exec, 0, 0); /* Reserve all BOs and page tables for validation */ drm_exec_until_all_locked(&exec) { /* Reserve all the page directories */ @@ -2793,7 +2793,7 @@ int amdgpu_amdkfd_gpuvm_restore_process_bos(void *info, struct dma_fence **ef) mutex_lock(&process_info->lock); - drm_exec_init(&exec, 0); + drm_exec_init(&exec, 0, 0); drm_exec_until_all_locked(&exec) { list_for_each_entry(peer_vm, &process_info->vm_list_head, vm_list_node) { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c index df3ecfa9e13f..2464606494d4 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c @@ -66,7 +66,7 @@ static int amdgpu_cs_parser_init(struct amdgpu_cs_parser *p, amdgpu_sync_create(&p->sync); drm_exec_init(&p->exec, DRM_EXEC_INTERRUPTIBLE_WAIT | - DRM_EXEC_IGNORE_DUPLICATES); + DRM_EXEC_IGNORE_DUPLICATES, 0); return 0; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_csa.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_csa.c index 720011019741..796fa6f1420b 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_csa.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_csa.c @@ -70,7 +70,7 @@ int amdgpu_map_static_csa(struct amdgpu_device *adev, struct amdgpu_vm *vm, struct drm_exec exec; int r; - drm_exec_init(&exec, DRM_EXEC_INTERRUPTIBLE_WAIT); + drm_exec_init(&exec, DRM_EXEC_INTERRUPTIBLE_WAIT, 0); drm_exec_until_all_locked(&exec) { r = amdgpu_vm_lock_pd(vm, &exec, 0); if (likely(!r)) @@ -110,7 +110,7 @@ int amdgpu_unmap_static_csa(struct amdgpu_device *adev, struct amdgpu_vm *vm, struct drm_exec exec; int r; - drm_exec_init(&exec, DRM_EXEC_INTERRUPTIBLE_WAIT); + drm_exec_init(&exec, DRM_EXEC_INTERRUPTIBLE_WAIT, 0); drm_exec_until_all_locked(&exec) { r = amdgpu_vm_lock_pd(vm, &exec, 0); if (likely(!r)) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c index 84beeaa4d21c..49a5f1c73b3e 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c @@ -203,7 +203,7 @@ static void amdgpu_gem_object_close(struct drm_gem_object *obj, struct drm_exec exec; long r; - drm_exec_init(&exec, DRM_EXEC_IGNORE_DUPLICATES); + drm_exec_init(&exec, DRM_EXEC_IGNORE_DUPLICATES, 0); drm_exec_until_all_locked(&exec) { r = drm_exec_prepare_obj(&exec, &bo->tbo.base, 1); drm_exec_retry_on_contention(&exec); @@ -739,7 +739,7 @@ int amdgpu_gem_va_ioctl(struct drm_device *dev, void *data, } drm_exec_init(&exec, DRM_EXEC_INTERRUPTIBLE_WAIT | - DRM_EXEC_IGNORE_DUPLICATES); + DRM_EXEC_IGNORE_DUPLICATES, 0); drm_exec_until_all_locked(&exec) { if (gobj) { r = drm_exec_lock_obj(&exec, gobj); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c index 9ddbf1494326..abd0b9763904 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c @@ -1122,7 +1122,7 @@ int amdgpu_mes_ctx_map_meta_data(struct amdgpu_device *adev, amdgpu_sync_create(&sync); - drm_exec_init(&exec, 0); + drm_exec_init(&exec, 0, 0); drm_exec_until_all_locked(&exec) { r = drm_exec_lock_obj(&exec, &ctx_data->meta_data_obj->tbo.base); @@ -1193,7 +1193,7 @@ int amdgpu_mes_ctx_unmap_meta_data(struct amdgpu_device *adev, struct drm_exec exec; long r; - drm_exec_init(&exec, 0); + drm_exec_init(&exec, 0, 0); drm_exec_until_all_locked(&exec) { r = drm_exec_lock_obj(&exec, &ctx_data->meta_data_obj->tbo.base); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_umsch_mm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_umsch_mm.c index ca45ba8ac171..bfbf59326ee1 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_umsch_mm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_umsch_mm.c @@ -86,7 +86,7 @@ static int map_ring_data(struct amdgpu_device *adev, struct amdgpu_vm *vm, amdgpu_sync_create(&sync); - drm_exec_init(&exec, 0); + drm_exec_init(&exec, 0, 0); drm_exec_until_all_locked(&exec) { r = drm_exec_lock_obj(&exec, &bo->tbo.base); drm_exec_retry_on_contention(&exec); @@ -149,7 +149,7 @@ static int unmap_ring_data(struct amdgpu_device *adev, struct amdgpu_vm *vm, struct drm_exec exec; long r; - drm_exec_init(&exec, 0); + drm_exec_init(&exec, 0, 0); drm_exec_until_all_locked(&exec) { r = drm_exec_lock_obj(&exec, &bo->tbo.base); drm_exec_retry_on_contention(&exec); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c index f2f3c338fd94..76d9f14ccc7c 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c @@ -1529,7 +1529,7 @@ static int svm_range_reserve_bos(struct svm_validate_context *ctx, bool intr) uint32_t gpuidx; int r; - drm_exec_init(&ctx->exec, intr ? DRM_EXEC_INTERRUPTIBLE_WAIT: 0); + drm_exec_init(&ctx->exec, intr ? DRM_EXEC_INTERRUPTIBLE_WAIT: 0, 0); drm_exec_until_all_locked(&ctx->exec) { for_each_set_bit(gpuidx, ctx->bitmap, MAX_GPU_INSTANCE) { pdd = kfd_process_device_from_gpuidx(ctx->process, gpuidx); diff --git a/drivers/gpu/drm/drm_exec.c b/drivers/gpu/drm/drm_exec.c index 5d2809de4517..48ee851b61d9 100644 --- a/drivers/gpu/drm/drm_exec.c +++ b/drivers/gpu/drm/drm_exec.c @@ -69,16 +69,23 @@ static void drm_exec_unlock_all(struct drm_exec *exec) * drm_exec_init - initialize a drm_exec object * @exec: the drm_exec object to initialize * @flags: controls locking behavior, see DRM_EXEC_* defines + * @nr: the initial # of objects * * Initialize the object and make sure that we can track locked objects. + * + * If nr is non-zero then it is used as the initial objects table size. + * In either case, the table will grow (be re-allocated) on demand. */ -void drm_exec_init(struct drm_exec *exec, uint32_t flags) +void drm_exec_init(struct drm_exec *exec, uint32_t flags, unsigned nr) { + if (!nr) + nr = PAGE_SIZE / sizeof(void *); + exec->flags = flags; - exec->objects = kmalloc(PAGE_SIZE, GFP_KERNEL); + exec->objects = kvmalloc_array(nr, sizeof(void *), GFP_KERNEL); /* If allocation here fails, just delay that till the first use */ - exec->max_objects = exec->objects ? PAGE_SIZE / sizeof(void *) : 0; + exec->max_objects = exec->objects ? nr : 0; exec->num_objects = 0; exec->contended = DRM_EXEC_DUMMY; exec->prelocked = NULL; diff --git a/drivers/gpu/drm/nouveau/nouveau_exec.c b/drivers/gpu/drm/nouveau/nouveau_exec.c index 9a5ef574744b..769392276e4f 100644 --- a/drivers/gpu/drm/nouveau/nouveau_exec.c +++ b/drivers/gpu/drm/nouveau/nouveau_exec.c @@ -103,7 +103,7 @@ nouveau_exec_job_submit(struct nouveau_job *job) nouveau_uvmm_lock(uvmm); drm_exec_init(exec, DRM_EXEC_INTERRUPTIBLE_WAIT | - DRM_EXEC_IGNORE_DUPLICATES); + DRM_EXEC_IGNORE_DUPLICATES, 0); drm_exec_until_all_locked(exec) { struct drm_gpuva *va; diff --git a/drivers/gpu/drm/nouveau/nouveau_uvmm.c b/drivers/gpu/drm/nouveau/nouveau_uvmm.c index 5cf892c50f43..f93cfccc2c93 100644 --- a/drivers/gpu/drm/nouveau/nouveau_uvmm.c +++ b/drivers/gpu/drm/nouveau/nouveau_uvmm.c @@ -1288,7 +1288,7 @@ nouveau_uvmm_bind_job_submit(struct nouveau_job *job) } drm_exec_init(exec, DRM_EXEC_INTERRUPTIBLE_WAIT | - DRM_EXEC_IGNORE_DUPLICATES); + DRM_EXEC_IGNORE_DUPLICATES, 0); drm_exec_until_all_locked(exec) { list_for_each_op(op, &bind_job->ops) { struct drm_gpuva_op *va_op; diff --git a/drivers/gpu/drm/tests/drm_exec_test.c b/drivers/gpu/drm/tests/drm_exec_test.c index 563949d777dd..81f928a429ba 100644 --- a/drivers/gpu/drm/tests/drm_exec_test.c +++ b/drivers/gpu/drm/tests/drm_exec_test.c @@ -46,7 +46,7 @@ static void sanitycheck(struct kunit *test) { struct drm_exec exec; - drm_exec_init(&exec, DRM_EXEC_INTERRUPTIBLE_WAIT); + drm_exec_init(&exec, DRM_EXEC_INTERRUPTIBLE_WAIT, 0); drm_exec_fini(&exec); KUNIT_SUCCEED(test); } @@ -60,7 +60,7 @@ static void test_lock(struct kunit *test) drm_gem_private_object_init(priv->drm, &gobj, PAGE_SIZE); - drm_exec_init(&exec, DRM_EXEC_INTERRUPTIBLE_WAIT); + drm_exec_init(&exec, DRM_EXEC_INTERRUPTIBLE_WAIT, 0); drm_exec_until_all_locked(&exec) { ret = drm_exec_lock_obj(&exec, &gobj); drm_exec_retry_on_contention(&exec); @@ -80,7 +80,7 @@ static void test_lock_unlock(struct kunit *test) drm_gem_private_object_init(priv->drm, &gobj, PAGE_SIZE); - drm_exec_init(&exec, DRM_EXEC_INTERRUPTIBLE_WAIT); + drm_exec_init(&exec, DRM_EXEC_INTERRUPTIBLE_WAIT, 0); drm_exec_until_all_locked(&exec) { ret = drm_exec_lock_obj(&exec, &gobj); drm_exec_retry_on_contention(&exec); @@ -107,7 +107,7 @@ static void test_duplicates(struct kunit *test) drm_gem_private_object_init(priv->drm, &gobj, PAGE_SIZE); - drm_exec_init(&exec, DRM_EXEC_IGNORE_DUPLICATES); + drm_exec_init(&exec, DRM_EXEC_IGNORE_DUPLICATES, 0); drm_exec_until_all_locked(&exec) { ret = drm_exec_lock_obj(&exec, &gobj); drm_exec_retry_on_contention(&exec); @@ -134,7 +134,7 @@ static void test_prepare(struct kunit *test) drm_gem_private_object_init(priv->drm, &gobj, PAGE_SIZE); - drm_exec_init(&exec, DRM_EXEC_INTERRUPTIBLE_WAIT); + drm_exec_init(&exec, DRM_EXEC_INTERRUPTIBLE_WAIT, 0); drm_exec_until_all_locked(&exec) { ret = drm_exec_prepare_obj(&exec, &gobj, 1); drm_exec_retry_on_contention(&exec); @@ -159,7 +159,7 @@ static void test_prepare_array(struct kunit *test) drm_gem_private_object_init(priv->drm, &gobj1, PAGE_SIZE); drm_gem_private_object_init(priv->drm, &gobj2, PAGE_SIZE); - drm_exec_init(&exec, DRM_EXEC_INTERRUPTIBLE_WAIT); + drm_exec_init(&exec, DRM_EXEC_INTERRUPTIBLE_WAIT, 0); drm_exec_until_all_locked(&exec) ret = drm_exec_prepare_array(&exec, array, ARRAY_SIZE(array), 1); @@ -174,14 +174,14 @@ static void test_multiple_loops(struct kunit *test) { struct drm_exec exec; - drm_exec_init(&exec, DRM_EXEC_INTERRUPTIBLE_WAIT); + drm_exec_init(&exec, DRM_EXEC_INTERRUPTIBLE_WAIT, 0); drm_exec_until_all_locked(&exec) { break; } drm_exec_fini(&exec); - drm_exec_init(&exec, DRM_EXEC_INTERRUPTIBLE_WAIT); + drm_exec_init(&exec, DRM_EXEC_INTERRUPTIBLE_WAIT, 0); drm_exec_until_all_locked(&exec) { break; diff --git a/include/drm/drm_exec.h b/include/drm/drm_exec.h index b5bf0b6da791..f1a66c048721 100644 --- a/include/drm/drm_exec.h +++ b/include/drm/drm_exec.h @@ -135,7 +135,7 @@ static inline bool drm_exec_is_contended(struct drm_exec *exec) return !!exec->contended; } -void drm_exec_init(struct drm_exec *exec, uint32_t flags); +void drm_exec_init(struct drm_exec *exec, uint32_t flags, unsigned nr); void drm_exec_fini(struct drm_exec *exec); bool drm_exec_cleanup(struct drm_exec *exec); int drm_exec_lock_obj(struct drm_exec *exec, struct drm_gem_object *obj); -- 2.42.0