Linaro-mm-sig October 2024

linaro-mm-sig@lists.linaro.org

7 participants
8 discussions

[PATCH AUTOSEL 6.10 66/70] drm/amdgpu: nuke the VM PD/PT shadow handling

by Sasha Levin

From: Christian König <christian.koenig(a)amd.com> [ Upstream commit 7181faaa4703705939580abffaf9cb5d6b50dbb7 ] This was only used as workaround for recovering the page tables after VRAM was lost and is no longer necessary after the function amdgpu_vm_bo_reset_state_machine() started to do the same. Compute never used shadows either, so the only proplematic case left is SVM and that is most likely not recoverable in any way when VRAM is lost. Signed-off-by: Christian König <christian.koenig(a)amd.com> Acked-by: Lijo Lazar <lijo.lazar(a)amd.com> Signed-off-by: Alex Deucher <alexander.deucher(a)amd.com> Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- drivers/gpu/drm/amd/amdgpu/amdgpu.h | 4 - drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 87 +-------------------- drivers/gpu/drm/amd/amdgpu/amdgpu_object.c | 67 +--------------- drivers/gpu/drm/amd/amdgpu/amdgpu_object.h | 21 ----- drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 17 ---- drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c | 56 +------------ drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c | 19 +---- 7 files changed, 6 insertions(+), 265 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h index f87d53e183c3d..b48e8066c01cc 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h @@ -1078,10 +1078,6 @@ struct amdgpu_device { struct amdgpu_virt virt; - /* link all shadow bo */ - struct list_head shadow_list; - struct mutex shadow_list_lock; - /* record hw reset is performed */ bool has_hw_reset; u8 reset_magic[AMDGPU_RESET_MAGIC_NUM]; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index e66546df0bc19..1df57a02a7598 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -4072,9 +4072,6 @@ int amdgpu_device_init(struct amdgpu_device *adev, spin_lock_init(&adev->mm_stats.lock); spin_lock_init(&adev->wb.lock); - INIT_LIST_HEAD(&adev->shadow_list); - mutex_init(&adev->shadow_list_lock); - INIT_LIST_HEAD(&adev->reset_list); INIT_LIST_HEAD(&adev->ras_list); @@ -4979,80 +4976,6 @@ static int amdgpu_device_ip_post_soft_reset(struct amdgpu_device *adev) return 0; } -/** - * amdgpu_device_recover_vram - Recover some VRAM contents - * - * @adev: amdgpu_device pointer - * - * Restores the contents of VRAM buffers from the shadows in GTT. Used to - * restore things like GPUVM page tables after a GPU reset where - * the contents of VRAM might be lost. - * - * Returns: - * 0 on success, negative error code on failure. - */ -static int amdgpu_device_recover_vram(struct amdgpu_device *adev) -{ - struct dma_fence *fence = NULL, *next = NULL; - struct amdgpu_bo *shadow; - struct amdgpu_bo_vm *vmbo; - long r = 1, tmo; - - if (amdgpu_sriov_runtime(adev)) - tmo = msecs_to_jiffies(8000); - else - tmo = msecs_to_jiffies(100); - - dev_info(adev->dev, "recover vram bo from shadow start\n"); - mutex_lock(&adev->shadow_list_lock); - list_for_each_entry(vmbo, &adev->shadow_list, shadow_list) { - /* If vm is compute context or adev is APU, shadow will be NULL */ - if (!vmbo->shadow) - continue; - shadow = vmbo->shadow; - - /* No need to recover an evicted BO */ - if (!shadow->tbo.resource || - shadow->tbo.resource->mem_type != TTM_PL_TT || - shadow->tbo.resource->start == AMDGPU_BO_INVALID_OFFSET || - shadow->parent->tbo.resource->mem_type != TTM_PL_VRAM) - continue; - - r = amdgpu_bo_restore_shadow(shadow, &next); - if (r) - break; - - if (fence) { - tmo = dma_fence_wait_timeout(fence, false, tmo); - dma_fence_put(fence); - fence = next; - if (tmo == 0) { - r = -ETIMEDOUT; - break; - } else if (tmo < 0) { - r = tmo; - break; - } - } else { - fence = next; - } - } - mutex_unlock(&adev->shadow_list_lock); - - if (fence) - tmo = dma_fence_wait_timeout(fence, false, tmo); - dma_fence_put(fence); - - if (r < 0 || tmo <= 0) { - dev_err(adev->dev, "recover vram bo from shadow failed, r is %ld, tmo is %ld\n", r, tmo); - return -EIO; - } - - dev_info(adev->dev, "recover vram bo from shadow done\n"); - return 0; -} - - /** * amdgpu_device_reset_sriov - reset ASIC for SR-IOV vf * @@ -5112,12 +5035,8 @@ static int amdgpu_device_reset_sriov(struct amdgpu_device *adev, if (r) return r; - if (adev->virt.gim_feature & AMDGIM_FEATURE_GIM_FLR_VRAMLOST) { + if (adev->virt.gim_feature & AMDGIM_FEATURE_GIM_FLR_VRAMLOST) amdgpu_inc_vram_lost(adev); - r = amdgpu_device_recover_vram(adev); - } - if (r) - return r; /* need to be called during full access so we can't do it later like * bare-metal does. @@ -5529,9 +5448,7 @@ int amdgpu_do_asic_reset(struct list_head *device_list_handle, } } - if (!r) - r = amdgpu_device_recover_vram(tmp_adev); - else + if (r) tmp_adev->asic_reset_res = r; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c index c556c8b653fa4..5f3b2c157824e 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c @@ -77,24 +77,6 @@ static void amdgpu_bo_user_destroy(struct ttm_buffer_object *tbo) amdgpu_bo_destroy(tbo); } -static void amdgpu_bo_vm_destroy(struct ttm_buffer_object *tbo) -{ - struct amdgpu_device *adev = amdgpu_ttm_adev(tbo->bdev); - struct amdgpu_bo *shadow_bo = ttm_to_amdgpu_bo(tbo), *bo; - struct amdgpu_bo_vm *vmbo; - - bo = shadow_bo->parent; - vmbo = to_amdgpu_bo_vm(bo); - /* in case amdgpu_device_recover_vram got NULL of bo->parent */ - if (!list_empty(&vmbo->shadow_list)) { - mutex_lock(&adev->shadow_list_lock); - list_del_init(&vmbo->shadow_list); - mutex_unlock(&adev->shadow_list_lock); - } - - amdgpu_bo_destroy(tbo); -} - /** * amdgpu_bo_is_amdgpu_bo - check if the buffer object is an &amdgpu_bo * @bo: buffer object to be checked @@ -108,8 +90,7 @@ static void amdgpu_bo_vm_destroy(struct ttm_buffer_object *tbo) bool amdgpu_bo_is_amdgpu_bo(struct ttm_buffer_object *bo) { if (bo->destroy == &amdgpu_bo_destroy || - bo->destroy == &amdgpu_bo_user_destroy || - bo->destroy == &amdgpu_bo_vm_destroy) + bo->destroy == &amdgpu_bo_user_destroy) return true; return false; @@ -722,52 +703,6 @@ int amdgpu_bo_create_vm(struct amdgpu_device *adev, return r; } -/** - * amdgpu_bo_add_to_shadow_list - add a BO to the shadow list - * - * @vmbo: BO that will be inserted into the shadow list - * - * Insert a BO to the shadow list. - */ -void amdgpu_bo_add_to_shadow_list(struct amdgpu_bo_vm *vmbo) -{ - struct amdgpu_device *adev = amdgpu_ttm_adev(vmbo->bo.tbo.bdev); - - mutex_lock(&adev->shadow_list_lock); - list_add_tail(&vmbo->shadow_list, &adev->shadow_list); - vmbo->shadow->parent = amdgpu_bo_ref(&vmbo->bo); - vmbo->shadow->tbo.destroy = &amdgpu_bo_vm_destroy; - mutex_unlock(&adev->shadow_list_lock); -} - -/** - * amdgpu_bo_restore_shadow - restore an &amdgpu_bo shadow - * - * @shadow: &amdgpu_bo shadow to be restored - * @fence: dma_fence associated with the operation - * - * Copies a buffer object's shadow content back to the object. - * This is used for recovering a buffer from its shadow in case of a gpu - * reset where vram context may be lost. - * - * Returns: - * 0 for success or a negative error code on failure. - */ -int amdgpu_bo_restore_shadow(struct amdgpu_bo *shadow, struct dma_fence **fence) - -{ - struct amdgpu_device *adev = amdgpu_ttm_adev(shadow->tbo.bdev); - struct amdgpu_ring *ring = adev->mman.buffer_funcs_ring; - uint64_t shadow_addr, parent_addr; - - shadow_addr = amdgpu_bo_gpu_offset(shadow); - parent_addr = amdgpu_bo_gpu_offset(shadow->parent); - - return amdgpu_copy_buffer(ring, shadow_addr, parent_addr, - amdgpu_bo_size(shadow), NULL, fence, - true, false, 0); -} - /** * amdgpu_bo_kmap - map an &amdgpu_bo buffer object * @bo: &amdgpu_bo buffer object to be mapped diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h index bc42ccbde659a..a4fa1f296daec 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h @@ -130,8 +130,6 @@ struct amdgpu_bo_user { struct amdgpu_bo_vm { struct amdgpu_bo bo; - struct amdgpu_bo *shadow; - struct list_head shadow_list; struct amdgpu_vm_bo_base entries[]; }; @@ -269,22 +267,6 @@ static inline bool amdgpu_bo_encrypted(struct amdgpu_bo *bo) return bo->flags & AMDGPU_GEM_CREATE_ENCRYPTED; } -/** - * amdgpu_bo_shadowed - check if the BO is shadowed - * - * @bo: BO to be tested. - * - * Returns: - * NULL if not shadowed or else return a BO pointer. - */ -static inline struct amdgpu_bo *amdgpu_bo_shadowed(struct amdgpu_bo *bo) -{ - if (bo->tbo.type == ttm_bo_type_kernel) - return to_amdgpu_bo_vm(bo)->shadow; - - return NULL; -} - bool amdgpu_bo_is_amdgpu_bo(struct ttm_buffer_object *bo); void amdgpu_bo_placement_from_domain(struct amdgpu_bo *abo, u32 domain); @@ -343,9 +325,6 @@ u64 amdgpu_bo_gpu_offset(struct amdgpu_bo *bo); u64 amdgpu_bo_gpu_offset_no_check(struct amdgpu_bo *bo); void amdgpu_bo_get_memory(struct amdgpu_bo *bo, struct amdgpu_mem_stats *stats); -void amdgpu_bo_add_to_shadow_list(struct amdgpu_bo_vm *vmbo); -int amdgpu_bo_restore_shadow(struct amdgpu_bo *shadow, - struct dma_fence **fence); uint32_t amdgpu_bo_get_preferred_domain(struct amdgpu_device *adev, uint32_t domain); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index 0f7106066480e..4820277e3c550 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -465,7 +465,6 @@ int amdgpu_vm_validate(struct amdgpu_device *adev, struct amdgpu_vm *vm, { uint64_t new_vm_generation = amdgpu_vm_generation(adev, vm); struct amdgpu_vm_bo_base *bo_base; - struct amdgpu_bo *shadow; struct amdgpu_bo *bo; int r; @@ -486,16 +485,10 @@ int amdgpu_vm_validate(struct amdgpu_device *adev, struct amdgpu_vm *vm, spin_unlock(&vm->status_lock); bo = bo_base->bo; - shadow = amdgpu_bo_shadowed(bo); r = validate(param, bo); if (r) return r; - if (shadow) { - r = validate(param, shadow); - if (r) - return r; - } if (bo->tbo.type != ttm_bo_type_kernel) { amdgpu_vm_bo_moved(bo_base); @@ -2125,10 +2118,6 @@ void amdgpu_vm_bo_invalidate(struct amdgpu_device *adev, { struct amdgpu_vm_bo_base *bo_base; - /* shadow bo doesn't have bo base, its validation needs its parent */ - if (bo->parent && (amdgpu_bo_shadowed(bo->parent) == bo)) - bo = bo->parent; - for (bo_base = bo->vm_bo; bo_base; bo_base = bo_base->next) { struct amdgpu_vm *vm = bo_base->vm; @@ -2456,7 +2445,6 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm, root_bo = amdgpu_bo_ref(&root->bo); r = amdgpu_bo_reserve(root_bo, true); if (r) { - amdgpu_bo_unref(&root->shadow); amdgpu_bo_unref(&root_bo); goto error_free_delayed; } @@ -2548,11 +2536,6 @@ int amdgpu_vm_make_compute(struct amdgpu_device *adev, struct amdgpu_vm *vm) vm->last_update = dma_fence_get_stub(); vm->is_compute_context = true; - /* Free the shadow bo for compute VM */ - amdgpu_bo_unref(&to_amdgpu_bo_vm(vm->root.bo)->shadow); - - goto unreserve_bo; - unreserve_bo: amdgpu_bo_unreserve(vm->root.bo); return r; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c index f07647a9a9d97..ad3a9e594a406 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c @@ -383,14 +383,6 @@ int amdgpu_vm_pt_clear(struct amdgpu_device *adev, struct amdgpu_vm *vm, if (r) return r; - if (vmbo->shadow) { - struct amdgpu_bo *shadow = vmbo->shadow; - - r = ttm_bo_validate(&shadow->tbo, &shadow->placement, &ctx); - if (r) - return r; - } - if (!drm_dev_enter(adev_to_drm(adev), &idx)) return -ENODEV; @@ -448,10 +440,7 @@ int amdgpu_vm_pt_create(struct amdgpu_device *adev, struct amdgpu_vm *vm, int32_t xcp_id) { struct amdgpu_bo_param bp; - struct amdgpu_bo *bo; - struct dma_resv *resv; unsigned int num_entries; - int r; memset(&bp, 0, sizeof(bp)); @@ -484,42 +473,7 @@ int amdgpu_vm_pt_create(struct amdgpu_device *adev, struct amdgpu_vm *vm, if (vm->root.bo) bp.resv = vm->root.bo->tbo.base.resv; - r = amdgpu_bo_create_vm(adev, &bp, vmbo); - if (r) - return r; - - bo = &(*vmbo)->bo; - if (vm->is_compute_context || (adev->flags & AMD_IS_APU)) { - (*vmbo)->shadow = NULL; - return 0; - } - - if (!bp.resv) - WARN_ON(dma_resv_lock(bo->tbo.base.resv, - NULL)); - resv = bp.resv; - memset(&bp, 0, sizeof(bp)); - bp.size = amdgpu_vm_pt_size(adev, level); - bp.domain = AMDGPU_GEM_DOMAIN_GTT; - bp.flags = AMDGPU_GEM_CREATE_CPU_GTT_USWC; - bp.type = ttm_bo_type_kernel; - bp.resv = bo->tbo.base.resv; - bp.bo_ptr_size = sizeof(struct amdgpu_bo); - bp.xcp_id_plus1 = xcp_id + 1; - - r = amdgpu_bo_create(adev, &bp, &(*vmbo)->shadow); - - if (!resv) - dma_resv_unlock(bo->tbo.base.resv); - - if (r) { - amdgpu_bo_unref(&bo); - return r; - } - - amdgpu_bo_add_to_shadow_list(*vmbo); - - return 0; + return amdgpu_bo_create_vm(adev, &bp, vmbo); } /** @@ -569,7 +523,6 @@ static int amdgpu_vm_pt_alloc(struct amdgpu_device *adev, return 0; error_free_pt: - amdgpu_bo_unref(&pt->shadow); amdgpu_bo_unref(&pt_bo); return r; } @@ -581,17 +534,10 @@ static int amdgpu_vm_pt_alloc(struct amdgpu_device *adev, */ static void amdgpu_vm_pt_free(struct amdgpu_vm_bo_base *entry) { - struct amdgpu_bo *shadow; - if (!entry->bo) return; entry->bo->vm_bo = NULL; - shadow = amdgpu_bo_shadowed(entry->bo); - if (shadow) { - ttm_bo_set_bulk_move(&shadow->tbo, NULL); - amdgpu_bo_unref(&shadow); - } ttm_bo_set_bulk_move(&entry->bo->tbo, NULL); spin_lock(&entry->vm->status_lock); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c index 9b748d7058b5c..390432a22ddd5 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c @@ -35,16 +35,7 @@ */ static int amdgpu_vm_sdma_map_table(struct amdgpu_bo_vm *table) { - int r; - - r = amdgpu_ttm_alloc_gart(&table->bo.tbo); - if (r) - return r; - - if (table->shadow) - r = amdgpu_ttm_alloc_gart(&table->shadow->tbo); - - return r; + return amdgpu_ttm_alloc_gart(&table->bo.tbo); } /* Allocate a new job for @count PTE updates */ @@ -273,17 +264,13 @@ static int amdgpu_vm_sdma_update(struct amdgpu_vm_update_params *p, if (!p->pages_addr) { /* set page commands needed */ - if (vmbo->shadow) - amdgpu_vm_sdma_set_ptes(p, vmbo->shadow, pe, addr, - count, incr, flags); amdgpu_vm_sdma_set_ptes(p, bo, pe, addr, count, incr, flags); return 0; } /* copy commands needed */ - ndw -= p->adev->vm_manager.vm_pte_funcs->copy_pte_num_dw * - (vmbo->shadow ? 2 : 1); + ndw -= p->adev->vm_manager.vm_pte_funcs->copy_pte_num_dw; /* for padding */ ndw -= 7; @@ -298,8 +285,6 @@ static int amdgpu_vm_sdma_update(struct amdgpu_vm_update_params *p, pte[i] |= flags; } - if (vmbo->shadow) - amdgpu_vm_sdma_copy_ptes(p, vmbo->shadow, pe, nptes); amdgpu_vm_sdma_copy_ptes(p, bo, pe, nptes); pe += nptes * 8; -- 2.43.0

6 hours, 49 minutes

[PATCH AUTOSEL 6.11 72/76] drm/amdgpu: nuke the VM PD/PT shadow handling

by Sasha Levin

From: Christian König <christian.koenig(a)amd.com> [ Upstream commit 7181faaa4703705939580abffaf9cb5d6b50dbb7 ] This was only used as workaround for recovering the page tables after VRAM was lost and is no longer necessary after the function amdgpu_vm_bo_reset_state_machine() started to do the same. Compute never used shadows either, so the only proplematic case left is SVM and that is most likely not recoverable in any way when VRAM is lost. Signed-off-by: Christian König <christian.koenig(a)amd.com> Acked-by: Lijo Lazar <lijo.lazar(a)amd.com> Signed-off-by: Alex Deucher <alexander.deucher(a)amd.com> Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- drivers/gpu/drm/amd/amdgpu/amdgpu.h | 4 - drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 87 +-------------------- drivers/gpu/drm/amd/amdgpu/amdgpu_object.c | 67 +--------------- drivers/gpu/drm/amd/amdgpu/amdgpu_object.h | 21 ----- drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 17 ---- drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c | 56 +------------ drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c | 19 +---- 7 files changed, 6 insertions(+), 265 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h index 137a88b8de453..a1b2bf3db55b8 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h @@ -1091,10 +1091,6 @@ struct amdgpu_device { struct amdgpu_virt virt; - /* link all shadow bo */ - struct list_head shadow_list; - struct mutex shadow_list_lock; - /* record hw reset is performed */ bool has_hw_reset; u8 reset_magic[AMDGPU_RESET_MAGIC_NUM]; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index bcacf2e35eba0..dfd468729d52b 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -4073,9 +4073,6 @@ int amdgpu_device_init(struct amdgpu_device *adev, spin_lock_init(&adev->mm_stats.lock); spin_lock_init(&adev->wb.lock); - INIT_LIST_HEAD(&adev->shadow_list); - mutex_init(&adev->shadow_list_lock); - INIT_LIST_HEAD(&adev->reset_list); INIT_LIST_HEAD(&adev->ras_list); @@ -4980,80 +4977,6 @@ static int amdgpu_device_ip_post_soft_reset(struct amdgpu_device *adev) return 0; } -/** - * amdgpu_device_recover_vram - Recover some VRAM contents - * - * @adev: amdgpu_device pointer - * - * Restores the contents of VRAM buffers from the shadows in GTT. Used to - * restore things like GPUVM page tables after a GPU reset where - * the contents of VRAM might be lost. - * - * Returns: - * 0 on success, negative error code on failure. - */ -static int amdgpu_device_recover_vram(struct amdgpu_device *adev) -{ - struct dma_fence *fence = NULL, *next = NULL; - struct amdgpu_bo *shadow; - struct amdgpu_bo_vm *vmbo; - long r = 1, tmo; - - if (amdgpu_sriov_runtime(adev)) - tmo = msecs_to_jiffies(8000); - else - tmo = msecs_to_jiffies(100); - - dev_info(adev->dev, "recover vram bo from shadow start\n"); - mutex_lock(&adev->shadow_list_lock); - list_for_each_entry(vmbo, &adev->shadow_list, shadow_list) { - /* If vm is compute context or adev is APU, shadow will be NULL */ - if (!vmbo->shadow) - continue; - shadow = vmbo->shadow; - - /* No need to recover an evicted BO */ - if (!shadow->tbo.resource || - shadow->tbo.resource->mem_type != TTM_PL_TT || - shadow->tbo.resource->start == AMDGPU_BO_INVALID_OFFSET || - shadow->parent->tbo.resource->mem_type != TTM_PL_VRAM) - continue; - - r = amdgpu_bo_restore_shadow(shadow, &next); - if (r) - break; - - if (fence) { - tmo = dma_fence_wait_timeout(fence, false, tmo); - dma_fence_put(fence); - fence = next; - if (tmo == 0) { - r = -ETIMEDOUT; - break; - } else if (tmo < 0) { - r = tmo; - break; - } - } else { - fence = next; - } - } - mutex_unlock(&adev->shadow_list_lock); - - if (fence) - tmo = dma_fence_wait_timeout(fence, false, tmo); - dma_fence_put(fence); - - if (r < 0 || tmo <= 0) { - dev_err(adev->dev, "recover vram bo from shadow failed, r is %ld, tmo is %ld\n", r, tmo); - return -EIO; - } - - dev_info(adev->dev, "recover vram bo from shadow done\n"); - return 0; -} - - /** * amdgpu_device_reset_sriov - reset ASIC for SR-IOV vf * @@ -5116,12 +5039,8 @@ static int amdgpu_device_reset_sriov(struct amdgpu_device *adev, if (r) return r; - if (adev->virt.gim_feature & AMDGIM_FEATURE_GIM_FLR_VRAMLOST) { + if (adev->virt.gim_feature & AMDGIM_FEATURE_GIM_FLR_VRAMLOST) amdgpu_inc_vram_lost(adev); - r = amdgpu_device_recover_vram(adev); - } - if (r) - return r; /* need to be called during full access so we can't do it later like * bare-metal does. @@ -5541,9 +5460,7 @@ int amdgpu_do_asic_reset(struct list_head *device_list_handle, } } - if (!r) - r = amdgpu_device_recover_vram(tmp_adev); - else + if (r) tmp_adev->asic_reset_res = r; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c index e32161f6b67a3..a987f671b1d53 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c @@ -77,24 +77,6 @@ static void amdgpu_bo_user_destroy(struct ttm_buffer_object *tbo) amdgpu_bo_destroy(tbo); } -static void amdgpu_bo_vm_destroy(struct ttm_buffer_object *tbo) -{ - struct amdgpu_device *adev = amdgpu_ttm_adev(tbo->bdev); - struct amdgpu_bo *shadow_bo = ttm_to_amdgpu_bo(tbo), *bo; - struct amdgpu_bo_vm *vmbo; - - bo = shadow_bo->parent; - vmbo = to_amdgpu_bo_vm(bo); - /* in case amdgpu_device_recover_vram got NULL of bo->parent */ - if (!list_empty(&vmbo->shadow_list)) { - mutex_lock(&adev->shadow_list_lock); - list_del_init(&vmbo->shadow_list); - mutex_unlock(&adev->shadow_list_lock); - } - - amdgpu_bo_destroy(tbo); -} - /** * amdgpu_bo_is_amdgpu_bo - check if the buffer object is an &amdgpu_bo * @bo: buffer object to be checked @@ -108,8 +90,7 @@ static void amdgpu_bo_vm_destroy(struct ttm_buffer_object *tbo) bool amdgpu_bo_is_amdgpu_bo(struct ttm_buffer_object *bo) { if (bo->destroy == &amdgpu_bo_destroy || - bo->destroy == &amdgpu_bo_user_destroy || - bo->destroy == &amdgpu_bo_vm_destroy) + bo->destroy == &amdgpu_bo_user_destroy) return true; return false; @@ -722,52 +703,6 @@ int amdgpu_bo_create_vm(struct amdgpu_device *adev, return r; } -/** - * amdgpu_bo_add_to_shadow_list - add a BO to the shadow list - * - * @vmbo: BO that will be inserted into the shadow list - * - * Insert a BO to the shadow list. - */ -void amdgpu_bo_add_to_shadow_list(struct amdgpu_bo_vm *vmbo) -{ - struct amdgpu_device *adev = amdgpu_ttm_adev(vmbo->bo.tbo.bdev); - - mutex_lock(&adev->shadow_list_lock); - list_add_tail(&vmbo->shadow_list, &adev->shadow_list); - vmbo->shadow->parent = amdgpu_bo_ref(&vmbo->bo); - vmbo->shadow->tbo.destroy = &amdgpu_bo_vm_destroy; - mutex_unlock(&adev->shadow_list_lock); -} - -/** - * amdgpu_bo_restore_shadow - restore an &amdgpu_bo shadow - * - * @shadow: &amdgpu_bo shadow to be restored - * @fence: dma_fence associated with the operation - * - * Copies a buffer object's shadow content back to the object. - * This is used for recovering a buffer from its shadow in case of a gpu - * reset where vram context may be lost. - * - * Returns: - * 0 for success or a negative error code on failure. - */ -int amdgpu_bo_restore_shadow(struct amdgpu_bo *shadow, struct dma_fence **fence) - -{ - struct amdgpu_device *adev = amdgpu_ttm_adev(shadow->tbo.bdev); - struct amdgpu_ring *ring = adev->mman.buffer_funcs_ring; - uint64_t shadow_addr, parent_addr; - - shadow_addr = amdgpu_bo_gpu_offset(shadow); - parent_addr = amdgpu_bo_gpu_offset(shadow->parent); - - return amdgpu_copy_buffer(ring, shadow_addr, parent_addr, - amdgpu_bo_size(shadow), NULL, fence, - true, false, 0); -} - /** * amdgpu_bo_kmap - map an &amdgpu_bo buffer object * @bo: &amdgpu_bo buffer object to be mapped diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h index bc42ccbde659a..a4fa1f296daec 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h @@ -130,8 +130,6 @@ struct amdgpu_bo_user { struct amdgpu_bo_vm { struct amdgpu_bo bo; - struct amdgpu_bo *shadow; - struct list_head shadow_list; struct amdgpu_vm_bo_base entries[]; }; @@ -269,22 +267,6 @@ static inline bool amdgpu_bo_encrypted(struct amdgpu_bo *bo) return bo->flags & AMDGPU_GEM_CREATE_ENCRYPTED; } -/** - * amdgpu_bo_shadowed - check if the BO is shadowed - * - * @bo: BO to be tested. - * - * Returns: - * NULL if not shadowed or else return a BO pointer. - */ -static inline struct amdgpu_bo *amdgpu_bo_shadowed(struct amdgpu_bo *bo) -{ - if (bo->tbo.type == ttm_bo_type_kernel) - return to_amdgpu_bo_vm(bo)->shadow; - - return NULL; -} - bool amdgpu_bo_is_amdgpu_bo(struct ttm_buffer_object *bo); void amdgpu_bo_placement_from_domain(struct amdgpu_bo *abo, u32 domain); @@ -343,9 +325,6 @@ u64 amdgpu_bo_gpu_offset(struct amdgpu_bo *bo); u64 amdgpu_bo_gpu_offset_no_check(struct amdgpu_bo *bo); void amdgpu_bo_get_memory(struct amdgpu_bo *bo, struct amdgpu_mem_stats *stats); -void amdgpu_bo_add_to_shadow_list(struct amdgpu_bo_vm *vmbo); -int amdgpu_bo_restore_shadow(struct amdgpu_bo *shadow, - struct dma_fence **fence); uint32_t amdgpu_bo_get_preferred_domain(struct amdgpu_device *adev, uint32_t domain); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index a060c28f0877c..8cda1d02dade3 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -465,7 +465,6 @@ int amdgpu_vm_validate(struct amdgpu_device *adev, struct amdgpu_vm *vm, { uint64_t new_vm_generation = amdgpu_vm_generation(adev, vm); struct amdgpu_vm_bo_base *bo_base; - struct amdgpu_bo *shadow; struct amdgpu_bo *bo; int r; @@ -486,16 +485,10 @@ int amdgpu_vm_validate(struct amdgpu_device *adev, struct amdgpu_vm *vm, spin_unlock(&vm->status_lock); bo = bo_base->bo; - shadow = amdgpu_bo_shadowed(bo); r = validate(param, bo); if (r) return r; - if (shadow) { - r = validate(param, shadow); - if (r) - return r; - } if (bo->tbo.type != ttm_bo_type_kernel) { amdgpu_vm_bo_moved(bo_base); @@ -2123,10 +2116,6 @@ void amdgpu_vm_bo_invalidate(struct amdgpu_device *adev, { struct amdgpu_vm_bo_base *bo_base; - /* shadow bo doesn't have bo base, its validation needs its parent */ - if (bo->parent && (amdgpu_bo_shadowed(bo->parent) == bo)) - bo = bo->parent; - for (bo_base = bo->vm_bo; bo_base; bo_base = bo_base->next) { struct amdgpu_vm *vm = bo_base->vm; @@ -2454,7 +2443,6 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm, root_bo = amdgpu_bo_ref(&root->bo); r = amdgpu_bo_reserve(root_bo, true); if (r) { - amdgpu_bo_unref(&root->shadow); amdgpu_bo_unref(&root_bo); goto error_free_delayed; } @@ -2546,11 +2534,6 @@ int amdgpu_vm_make_compute(struct amdgpu_device *adev, struct amdgpu_vm *vm) vm->last_update = dma_fence_get_stub(); vm->is_compute_context = true; - /* Free the shadow bo for compute VM */ - amdgpu_bo_unref(&to_amdgpu_bo_vm(vm->root.bo)->shadow); - - goto unreserve_bo; - unreserve_bo: amdgpu_bo_unreserve(vm->root.bo); return r; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c index e39d6e7643bfb..c8e0b8cfd3363 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c @@ -383,14 +383,6 @@ int amdgpu_vm_pt_clear(struct amdgpu_device *adev, struct amdgpu_vm *vm, if (r) return r; - if (vmbo->shadow) { - struct amdgpu_bo *shadow = vmbo->shadow; - - r = ttm_bo_validate(&shadow->tbo, &shadow->placement, &ctx); - if (r) - return r; - } - if (!drm_dev_enter(adev_to_drm(adev), &idx)) return -ENODEV; @@ -448,10 +440,7 @@ int amdgpu_vm_pt_create(struct amdgpu_device *adev, struct amdgpu_vm *vm, int32_t xcp_id) { struct amdgpu_bo_param bp; - struct amdgpu_bo *bo; - struct dma_resv *resv; unsigned int num_entries; - int r; memset(&bp, 0, sizeof(bp)); @@ -484,42 +473,7 @@ int amdgpu_vm_pt_create(struct amdgpu_device *adev, struct amdgpu_vm *vm, if (vm->root.bo) bp.resv = vm->root.bo->tbo.base.resv; - r = amdgpu_bo_create_vm(adev, &bp, vmbo); - if (r) - return r; - - bo = &(*vmbo)->bo; - if (vm->is_compute_context || (adev->flags & AMD_IS_APU)) { - (*vmbo)->shadow = NULL; - return 0; - } - - if (!bp.resv) - WARN_ON(dma_resv_lock(bo->tbo.base.resv, - NULL)); - resv = bp.resv; - memset(&bp, 0, sizeof(bp)); - bp.size = amdgpu_vm_pt_size(adev, level); - bp.domain = AMDGPU_GEM_DOMAIN_GTT; - bp.flags = AMDGPU_GEM_CREATE_CPU_GTT_USWC; - bp.type = ttm_bo_type_kernel; - bp.resv = bo->tbo.base.resv; - bp.bo_ptr_size = sizeof(struct amdgpu_bo); - bp.xcp_id_plus1 = xcp_id + 1; - - r = amdgpu_bo_create(adev, &bp, &(*vmbo)->shadow); - - if (!resv) - dma_resv_unlock(bo->tbo.base.resv); - - if (r) { - amdgpu_bo_unref(&bo); - return r; - } - - amdgpu_bo_add_to_shadow_list(*vmbo); - - return 0; + return amdgpu_bo_create_vm(adev, &bp, vmbo); } /** @@ -569,7 +523,6 @@ static int amdgpu_vm_pt_alloc(struct amdgpu_device *adev, return 0; error_free_pt: - amdgpu_bo_unref(&pt->shadow); amdgpu_bo_unref(&pt_bo); return r; } @@ -581,17 +534,10 @@ static int amdgpu_vm_pt_alloc(struct amdgpu_device *adev, */ static void amdgpu_vm_pt_free(struct amdgpu_vm_bo_base *entry) { - struct amdgpu_bo *shadow; - if (!entry->bo) return; entry->bo->vm_bo = NULL; - shadow = amdgpu_bo_shadowed(entry->bo); - if (shadow) { - ttm_bo_set_bulk_move(&shadow->tbo, NULL); - amdgpu_bo_unref(&shadow); - } ttm_bo_set_bulk_move(&entry->bo->tbo, NULL); spin_lock(&entry->vm->status_lock); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c index 9b748d7058b5c..390432a22ddd5 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c @@ -35,16 +35,7 @@ */ static int amdgpu_vm_sdma_map_table(struct amdgpu_bo_vm *table) { - int r; - - r = amdgpu_ttm_alloc_gart(&table->bo.tbo); - if (r) - return r; - - if (table->shadow) - r = amdgpu_ttm_alloc_gart(&table->shadow->tbo); - - return r; + return amdgpu_ttm_alloc_gart(&table->bo.tbo); } /* Allocate a new job for @count PTE updates */ @@ -273,17 +264,13 @@ static int amdgpu_vm_sdma_update(struct amdgpu_vm_update_params *p, if (!p->pages_addr) { /* set page commands needed */ - if (vmbo->shadow) - amdgpu_vm_sdma_set_ptes(p, vmbo->shadow, pe, addr, - count, incr, flags); amdgpu_vm_sdma_set_ptes(p, bo, pe, addr, count, incr, flags); return 0; } /* copy commands needed */ - ndw -= p->adev->vm_manager.vm_pte_funcs->copy_pte_num_dw * - (vmbo->shadow ? 2 : 1); + ndw -= p->adev->vm_manager.vm_pte_funcs->copy_pte_num_dw; /* for padding */ ndw -= 7; @@ -298,8 +285,6 @@ static int amdgpu_vm_sdma_update(struct amdgpu_vm_update_params *p, pte[i] |= flags; } - if (vmbo->shadow) - amdgpu_vm_sdma_copy_ptes(p, vmbo->shadow, pe, nptes); amdgpu_vm_sdma_copy_ptes(p, bo, pe, nptes); pe += nptes * 8; -- 2.43.0

6 hours, 53 minutes

Re: [PATCH 1/3] dma-buf: replace symbolic permission S_IRUGO with octal 0444

by Sumit Semwal

Hello Pintu, On Tue, 1 Oct 2024 at 23:16, Pintu Kumar <quic_pintu(a)quicinc.com> wrote: > > Symbolic permissions are not preferred, instead use the octal. > Also, fix other warnings/errors as well for cleanup. > > WARNING: Block comments use * on subsequent lines > + /* only support discovering the end of the buffer, > + but also allow SEEK_SET to maintain the idiomatic > > WARNING: Block comments use a trailing */ on a separate line > + SEEK_END(0), SEEK_CUR(0) pattern */ > > WARNING: Block comments use a trailing */ on a separate line > + * before passing the sgt back to the exporter. */ > > ERROR: "foo * bar" should be "foo *bar" > +static struct sg_table * __map_dma_buf(struct dma_buf_attachment *attach, > > WARNING: Symbolic permissions 'S_IRUGO' are not preferred. Consider using octal permissions '0444'. > + d = debugfs_create_file("bufinfo", S_IRUGO, dma_buf_debugfs_dir, > > total: 1 errors, 4 warnings, 1746 lines checked > > Signed-off-by: Pintu Kumar <quic_pintu(a)quicinc.com> Thanks for this patch - could you please also mention in the commit log how did you find this? It looks like you ran checkpatch, but it's not clear from the commit log. Since this patch does multiple things related to checkpatch warnings (change S_IRUGO to 0444, comments correction, function declaration correction), can I please ask you to change the commit title to also reflect that? > --- > drivers/dma-buf/dma-buf.c | 12 +++++++----- > 1 file changed, 7 insertions(+), 5 deletions(-) > > diff --git a/drivers/dma-buf/dma-buf.c b/drivers/dma-buf/dma-buf.c > index 8892bc701a66..2e63d50e46d3 100644 > --- a/drivers/dma-buf/dma-buf.c > +++ b/drivers/dma-buf/dma-buf.c > @@ -176,8 +176,9 @@ static loff_t dma_buf_llseek(struct file *file, loff_t offset, int whence) > dmabuf = file->private_data; > > /* only support discovering the end of the buffer, > - but also allow SEEK_SET to maintain the idiomatic > - SEEK_END(0), SEEK_CUR(0) pattern */ > + * but also allow SEEK_SET to maintain the idiomatic > + * SEEK_END(0), SEEK_CUR(0) pattern. > + */ > if (whence == SEEK_END) > base = dmabuf->size; > else if (whence == SEEK_SET) > @@ -782,13 +783,14 @@ static void mangle_sg_table(struct sg_table *sg_table) > /* To catch abuse of the underlying struct page by importers mix > * up the bits, but take care to preserve the low SG_ bits to > * not corrupt the sgt. The mixing is undone in __unmap_dma_buf > - * before passing the sgt back to the exporter. */ > + * before passing the sgt back to the exporter. > + */ > for_each_sgtable_sg(sg_table, sg, i) > sg->page_link ^= ~0xffUL; > #endif > > } > -static struct sg_table * __map_dma_buf(struct dma_buf_attachment *attach, > +static struct sg_table *__map_dma_buf(struct dma_buf_attachment *attach, > enum dma_data_direction direction) > { > struct sg_table *sg_table; > @@ -1694,7 +1696,7 @@ static int dma_buf_init_debugfs(void) > > dma_buf_debugfs_dir = d; > > - d = debugfs_create_file("bufinfo", S_IRUGO, dma_buf_debugfs_dir, > + d = debugfs_create_file("bufinfo", 0444, dma_buf_debugfs_dir, > NULL, &dma_buf_debug_fops); > if (IS_ERR(d)) { > pr_debug("dma_buf: debugfs: failed to create node bufinfo\n"); > -- > 2.17.1 > Best, Sumit.

1 day, 8 hours

Re: [PATCH v8 0/5] Support fdinfo runtime and memory stats on Panthor

by Jani Nikula

On Wed, 02 Oct 2024, Boris Brezillon <boris.brezillon(a)collabora.com> wrote: > Queued to drm-misc-next after applying the few modifications I > mentioned. Also added Steve's ack (given on IRC) on the first patch. Can we have the drm-tip rebuild conflict resolution too, please? diff --cc drivers/gpu/drm/panthor/panthor_drv.c index c520f156e2d7,f9b93f84d611..000000000000 --- a/drivers/gpu/drm/panthor/panthor_drv.c +++ b/drivers/gpu/drm/panthor/panthor_drv.c @@@ -1383,7 -1476,7 +1476,11 @@@ static const struct file_operations pan .read = drm_read, .llseek = noop_llseek, .mmap = panthor_mmap, ++<<<<<<< HEAD + .fop_flags = FOP_UNSIGNED_OFFSET, ++======= + .show_fdinfo = drm_show_fdinfo, ++>>>>>>> drm-misc/drm-misc-next }; #ifdef CONFIG_DEBUG_FS > >> >> .../testing/sysfs-driver-panthor-profiling | 10 + >> Documentation/gpu/panthor.rst | 46 +++ >> drivers/gpu/drm/panthor/panthor_devfreq.c | 18 +- >> drivers/gpu/drm/panthor/panthor_device.h | 36 ++ >> drivers/gpu/drm/panthor/panthor_drv.c | 73 ++++ >> drivers/gpu/drm/panthor/panthor_gem.c | 12 + >> drivers/gpu/drm/panthor/panthor_sched.c | 384 +++++++++++++++--- >> drivers/gpu/drm/panthor/panthor_sched.h | 2 + >> 8 files changed, 531 insertions(+), 50 deletions(-) >> create mode 100644 Documentation/ABI/testing/sysfs-driver-panthor-profiling >> create mode 100644 Documentation/gpu/panthor.rst >> > -- Jani Nikula, Intel

2 days, 15 hours

Re: [PATCH v8 1/5] drm/panthor: introduce job cycle and timestamp accounting

by Steven Price

On 02/10/2024 09:38, Boris Brezillon wrote: > On Tue, 24 Sep 2024 00:06:21 +0100 > Adrián Larumbe <adrian.larumbe(a)collabora.com> wrote: > >> +static u32 calc_profiling_ringbuf_num_slots(struct panthor_device *ptdev, >> + u32 cs_ringbuf_size) >> +{ >> + u32 min_profiled_job_instrs = U32_MAX; >> + u32 last_flag = fls(PANTHOR_DEVICE_PROFILING_ALL); >> + >> + /* >> + * We want to calculate the minimum size of a profiled job's CS, >> + * because since they need additional instructions for the sampling >> + * of performance metrics, they might take up further slots in >> + * the queue's ringbuffer. This means we might not need as many job >> + * slots for keeping track of their profiling information. What we >> + * need is the maximum number of slots we should allocate to this end, >> + * which matches the maximum number of profiled jobs we can place >> + * simultaneously in the queue's ring buffer. >> + * That has to be calculated separately for every single job profiling >> + * flag, but not in the case job profiling is disabled, since unprofiled >> + * jobs don't need to keep track of this at all. >> + */ >> + for (u32 i = 0; i < last_flag; i++) { >> + if (BIT(i) & PANTHOR_DEVICE_PROFILING_ALL) > > I'll get rid of this check when applying, as suggested by Steve. Steve, > with this modification do you want me to add your R-b? Yes, please do. Thanks, Steve > BTW, I've also fixed a bunch of checkpatch errors/warnings, so you > might want to run checkpatch --strict next time. > >> + min_profiled_job_instrs = >> + min(min_profiled_job_instrs, calc_job_credits(BIT(i))); >> + } >> + >> + return DIV_ROUND_UP(cs_ringbuf_size, min_profiled_job_instrs * sizeof(u64)); >> +}

2 days, 16 hours

Re: [PATCH 2/3] dma-buf/heaps: replace kmap_atomic with kmap_local_page

by T.J. Mercier

On Tue, Oct 1, 2024 at 7:51 PM Pintu Kumar <quic_pintu(a)quicinc.com> wrote: > > Use of kmap_atomic/kunmap_atomic is deprecated, use > kmap_local_page/kunmap_local instead. > > This is reported by checkpatch. > Also fix repeated word issue. > > WARNING: Deprecated use of 'kmap_atomic', prefer 'kmap_local_page' instead > + void *vaddr = kmap_atomic(page); > > WARNING: Deprecated use of 'kunmap_atomic', prefer 'kunmap_local' instead > + kunmap_atomic(vaddr); > > WARNING: Possible repeated word: 'by' > + * has been killed by by SIGKILL > > total: 0 errors, 3 warnings, 405 lines checked > > Signed-off-by: Pintu Kumar <quic_pintu(a)quicinc.com> Reviewed-by: T.J. Mercier <tjmercier(a)google.com> The Android kernels have been doing this for over a year, so should be pretty well tested at this point: https://r.android.com/c/kernel/common/+/2500840 > --- > drivers/dma-buf/heaps/cma_heap.c | 6 +++--- > 1 file changed, 3 insertions(+), 3 deletions(-) > > diff --git a/drivers/dma-buf/heaps/cma_heap.c b/drivers/dma-buf/heaps/cma_heap.c > index 93be88b805fe..8c55431cc16c 100644 > --- a/drivers/dma-buf/heaps/cma_heap.c > +++ b/drivers/dma-buf/heaps/cma_heap.c > @@ -309,13 +309,13 @@ static struct dma_buf *cma_heap_allocate(struct dma_heap *heap, > struct page *page = cma_pages; > > while (nr_clear_pages > 0) { > - void *vaddr = kmap_atomic(page); > + void *vaddr = kmap_local_page(page); > > memset(vaddr, 0, PAGE_SIZE); > - kunmap_atomic(vaddr); > + kunmap_local(vaddr); > /* > * Avoid wasting time zeroing memory if the process > - * has been killed by by SIGKILL > + * has been killed by SIGKILL. > */ > if (fatal_signal_pending(current)) > goto free_cma; > -- > 2.17.1 >

3 days, 3 hours

[PATCH] Documentation: dma-buf: heaps: Add heap name definitions

by Maxime Ripard

Following a recent discussion at last Plumbers, John Stultz, Sumit Sewal, TJ Mercier and I came to an agreement that we should document what the dma-buf heaps names are expected to be, and what the buffers attributes you'll get should be documented. Let's create that doc to make sure those attributes and names are guaranteed going forward. Signed-off-by: Maxime Ripard <mripard(a)kernel.org> --- To: Jonathan Corbet <corbet(a)lwn.net> To: Sumit Semwal <sumit.semwal(a)linaro.org> Cc: Benjamin Gaignard <benjamin.gaignard(a)collabora.com> Cc: Brian Starkey <Brian.Starkey(a)arm.com> Cc: John Stultz <jstultz(a)google.com> Cc: "T.J. Mercier" <tjmercier(a)google.com> Cc: "Christian König" <christian.koenig(a)amd.com> Cc: dri-devel(a)lists.freedesktop.org Cc: linaro-mm-sig(a)lists.linaro.org Cc: linux-media(a)vger.kernel.org Cc: linux-doc(a)vger.kernel.org --- Documentation/userspace-api/dma-buf-heaps.rst | 71 +++++++++++++++++++ Documentation/userspace-api/index.rst | 1 + 2 files changed, 72 insertions(+) create mode 100644 Documentation/userspace-api/dma-buf-heaps.rst diff --git a/Documentation/userspace-api/dma-buf-heaps.rst b/Documentation/userspace-api/dma-buf-heaps.rst new file mode 100644 index 000000000000..00436227b542 --- /dev/null +++ b/Documentation/userspace-api/dma-buf-heaps.rst @@ -0,0 +1,71 @@ +.. SPDX-License-Identifier: GPL-2.0 + +============================== +Allocating dma-buf using heaps +============================== + +Dma-buf Heaps are a way for userspace to allocate dma-buf objects. They are +typically used to allocate buffers from a specific allocation pool, or to share +buffers across frameworks. + +Heaps +===== + +A heap represent a specific allocator. The Linux kernel currently supports the +following heaps: + + - The ``system`` heap allocates virtually contiguous, cacheable, buffers + + - The ``reserved`` heap allocates physically contiguous, cacheable, buffers. + Depending on the platform, it might be called differently: + + - Acer Iconia Tab A500: ``linux,cma`` + - Allwinner sun4i, sun5i and sun7i families: ``default-pool`` + - Amlogic A1: ``linux,cma`` + - Amlogic G12A/G12B/SM1: ``linux,cma`` + - Amlogic GXBB/GXL: ``linux,cma`` + - ASUS EeePad Transformer TF101: ``linux,cma`` + - ASUS Google Nexus 7 (Project Bach / ME370TG) E1565: ``linux,cma`` + - ASUS Google Nexus 7 (Project Nakasi / ME370T) E1565: ``linux,cma`` + - ASUS Google Nexus 7 (Project Nakasi / ME370T) PM269: ``linux,cma`` + - Asus Transformer Infinity TF700T: ``linux,cma`` + - Asus Transformer Pad 3G TF300TG: ``linux,cma`` + - Asus Transformer Pad TF300T: ``linux,cma`` + - Asus Transformer Pad TF701T: ``linux,cma`` + - Asus Transformer Prime TF201: ``linux,cma`` + - ASUS Vivobook S 15: ``linux,cma`` + - Cadence KC705: ``linux,cma`` + - Digi International ConnectCore 6UL: ``linux,cma`` + - Freescale i.MX8DXL EVK: ``linux,cma`` + - Freescale TQMa8Xx: ``linux,cma`` + - Hisilicon Hikey: ``linux,cma`` + - Lenovo ThinkPad T14s Gen 6: ``linux,cma`` + - Lenovo ThinkPad X13s: ``linux,cma`` + - Lenovo Yoga Slim 7x: ``linux,cma`` + - LG Optimus 4X HD P880: ``linux,cma`` + - LG Optimus Vu P895: ``linux,cma`` + - Loongson 2k0500, 2k1000 and 2k2000: ``linux,cma`` + - Microsoft Romulus: ``linux,cma`` + - NXP i.MX8ULP EVK: ``linux,cma`` + - NXP i.MX93 9x9 QSB: ``linux,cma`` + - NXP i.MX93 11X11 EVK: ``linux,cma`` + - NXP i.MX93 14X14 EVK: ``linux,cma`` + - NXP i.MX95 19X19 EVK: ``linux,cma`` + - Ouya Game Console: ``linux,cma`` + - Pegatron Chagall: ``linux,cma`` + - PHYTEC phyCORE-AM62A SOM: ``linux,cma`` + - PHYTEC phyCORE-i.MX93 SOM: ``linux,cma`` + - Qualcomm SC8280XP CRD: ``linux,cma`` + - Qualcomm X1E80100 CRD: ``linux,cma`` + - Qualcomm X1E80100 QCP: ``linux,cma`` + - RaspberryPi: ``linux,cma`` + - Texas Instruments AM62x SK board family: ``linux,cma`` + - Texas Instruments AM62A7 SK: ``linux,cma`` + - Toradex Apalis iMX8: ``linux,cma`` + - TQ-Systems i.MX8MM TQMa8MxML: ``linux,cma`` + - TQ-Systems i.MX8MN TQMa8MxNL: ``linux,cma`` + - TQ-Systems i.MX8MPlus TQMa8MPxL: ``linux,cma`` + - TQ-Systems i.MX8MQ TQMa8MQ: ``linux,cma`` + - TQ-Systems i.MX93 TQMa93xxLA/TQMa93xxCA SOM: ``linux,cma`` + - TQ-Systems MBA6ULx Baseboard: ``linux,cma`` + diff --git a/Documentation/userspace-api/index.rst b/Documentation/userspace-api/index.rst index 274cc7546efc..4901ce7c6cb7 100644 --- a/Documentation/userspace-api/index.rst +++ b/Documentation/userspace-api/index.rst @@ -41,10 +41,11 @@ Devices and I/O .. toctree:: :maxdepth: 1 accelerators/ocxl + dma-buf-heaps dma-buf-alloc-exchange gpio/index iommufd media/index dcdbas -- 2.46.1

3 days, 4 hours

Re: Question about 'dma_resv_get_fences'

by Christian König

Hi, Am 30.09.24 um 21:38 schrieb Zichen Xie: > Dear Linux Developers for DMA BUFFER SHARING FRAMEWORK, > > We are curious about the function 'dma_resv_get_fences' here: > https://elixir.bootlin.com/linux/v6.11/source/drivers/dma-buf/dma-resv.c#L5…, > and the logic below: > ``` > dma_resv_for_each_fence_unlocked(&cursor, fence) { > > if (dma_resv_iter_is_restarted(&cursor)) { > struct dma_fence **new_fences; > unsigned int count; > > while (*num_fences) > dma_fence_put((*fences)[--(*num_fences)]); > > count = cursor.num_fences + 1; > > /* Eventually re-allocate the array */ > new_fences = krealloc_array(*fences, count, > sizeof(void *), > GFP_KERNEL); > if (count && !new_fences) { > kfree(*fences); > *fences = NULL; > *num_fences = 0; > dma_resv_iter_end(&cursor); > return -ENOMEM; > } > *fences = new_fences; > } > > (*fences)[(*num_fences)++] = dma_fence_get(fence); > } > ``` > The existing check 'if (count && !new_fences)' may fail if count==0, > and 'krealloc_array' with count==0 is an undefined behavior. The > realloc may fail and return a NULL pointer, leading to a NULL Pointer > Dereference in '(*fences)[(*num_fences)++] = dma_fence_get(fence);' You already answered the question yourself "count = cursor.num_fences + 1;". So count can never be 0. What could theoretically be possible is that num_fences overflows, but this value isn't userspace controllable and we would run into memory allocation failures long before that happened. But we could potentially remove this whole handling since if there are no fences in the dma_resv object we don't enter the loop in the first place. Regards, Christian. > > Please correct us if we miss some key prerequisites for this function! > Thank you very much!

3 days, 17 hours

2024

2023

2022

2021

2020

2019

2018

2017

2016

2015

2014

2013

2012

2011

Linaro-mm-sig October 2024