diff options
author | 2022-04-12 17:39:45 +1000 | |
---|---|---|
committer | 2022-04-12 17:44:27 +1000 | |
commit | b85ffe47c4ec172214a38b7e7087c60582c488f0 (patch) | |
tree | 128168c955a62a870f7da7cfda94e9299a076486 /drivers/gpu/drm/amd | |
parent | Linux 5.18-rc2 (diff) | |
parent | dma-buf/drivers: make reserving a shared slot mandatory v4 (diff) | |
download | linux-b85ffe47c4ec172214a38b7e7087c60582c488f0.tar.gz linux-b85ffe47c4ec172214a38b7e7087c60582c488f0.tar.bz2 linux-b85ffe47c4ec172214a38b7e7087c60582c488f0.zip |
Merge tag 'drm-misc-next-2022-04-07' of git://anongit.freedesktop.org/drm/drm-misc into drm-next
drm-misc-next for 5.19:
UAPI Changes:
Cross-subsystem Changes:
Core Changes:
- atomic: Add atomic_print_state to private objects
- edid: Constify the EDID parsing API, rework of the API
- dma-buf: Add dma_resv_replace_fences, dma_resv_get_singleton, make
dma_resv_excl_fence private
- format: Support monochrome formats
- fbdev: fixes for cfb_imageblit and sys_imageblit, pagelist
corruption fix
- selftests: several small fixes
- ttm: Rework bulk move handling
Driver Changes:
- Switch all relevant drivers to drm_mode_copy or drm_mode_duplicate
- bridge: conversions to devm_drm_of_get_bridge and panel_bridge,
autosuspend for analogix_dp, audio support for it66121, DSI to DPI
support for tc358767, PLL fixes and I2C support for icn6211
- bridge_connector: Enable HPD if supported
- etnaviv: fencing improvements
- gma500: GEM and GTT improvements, connector handling fixes
- komeda: switch to plane reset helper
- mediatek: MIPI DSI improvements
- omapdrm: GEM improvements
- panel: DT bindings fixes for st7735r, few fixes for ssd130x, new
panels: ltk035c5444t, B133UAN01, NV3052C
- qxl: Allow to run on arm64
- sysfb: Kconfig rework, support for VESA graphic mode selection
- vc4: Add a tracepoint for CL submissions, HDMI YUV output,
HDMI and clock improvements
- virtio: Remove restriction of non-zero blob_flags,
- vmwgfx: support for CursorMob and CursorBypass 4, various
improvements and small fixes
[airlied: fixup conflict with newvision panel callbacks]
Signed-off-by: Dave Airlie <airlied@redhat.com>
From: Maxime Ripard <maxime@cerno.tech>
Link: https://patchwork.freedesktop.org/patch/msgid/20220407085940.pnflvjojs4qw4b77@houat
Diffstat (limited to 'drivers/gpu/drm/amd')
-rw-r--r-- | drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c | 53 | ||||
-rw-r--r-- | drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c | 15 | ||||
-rw-r--r-- | drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c | 49 | ||||
-rw-r--r-- | drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c | 23 | ||||
-rw-r--r-- | drivers/gpu/drm/amd/amdgpu/amdgpu_object.c | 8 | ||||
-rw-r--r-- | drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 1 | ||||
-rw-r--r-- | drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 78 | ||||
-rw-r--r-- | drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h | 3 | ||||
-rw-r--r-- | drivers/gpu/drm/amd/amdkfd/kfd_svm.c | 2 |
9 files changed, 61 insertions, 171 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c index cd89d2e46852..98b1736bb221 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c @@ -253,53 +253,18 @@ void amdgpu_amdkfd_release_notify(struct amdgpu_bo *bo) static int amdgpu_amdkfd_remove_eviction_fence(struct amdgpu_bo *bo, struct amdgpu_amdkfd_fence *ef) { - struct dma_resv *resv = bo->tbo.base.resv; - struct dma_resv_list *old, *new; - unsigned int i, j, k; + struct dma_fence *replacement; if (!ef) return -EINVAL; - old = dma_resv_shared_list(resv); - if (!old) - return 0; - - new = kmalloc(struct_size(new, shared, old->shared_max), GFP_KERNEL); - if (!new) - return -ENOMEM; - - /* Go through all the shared fences in the resevation object and sort - * the interesting ones to the end of the list. + /* TODO: Instead of block before we should use the fence of the page + * table update and TLB flush here directly. */ - for (i = 0, j = old->shared_count, k = 0; i < old->shared_count; ++i) { - struct dma_fence *f; - - f = rcu_dereference_protected(old->shared[i], - dma_resv_held(resv)); - - if (f->context == ef->base.context) - RCU_INIT_POINTER(new->shared[--j], f); - else - RCU_INIT_POINTER(new->shared[k++], f); - } - new->shared_max = old->shared_max; - new->shared_count = k; - - /* Install the new fence list, seqcount provides the barriers */ - write_seqcount_begin(&resv->seq); - RCU_INIT_POINTER(resv->fence, new); - write_seqcount_end(&resv->seq); - - /* Drop the references to the removed fences or move them to ef_list */ - for (i = j; i < old->shared_count; ++i) { - struct dma_fence *f; - - f = rcu_dereference_protected(new->shared[i], - dma_resv_held(resv)); - dma_fence_put(f); - } - kfree_rcu(old, rcu); - + replacement = dma_fence_get_stub(); + dma_resv_replace_fences(bo->tbo.base.resv, ef->base.context, + replacement); + dma_fence_put(replacement); return 0; } @@ -1268,7 +1233,7 @@ static int init_kfd_vm(struct amdgpu_vm *vm, void **process_info, AMDGPU_FENCE_OWNER_KFD, false); if (ret) goto wait_pd_fail; - ret = dma_resv_reserve_shared(vm->root.bo->tbo.base.resv, 1); + ret = dma_resv_reserve_fences(vm->root.bo->tbo.base.resv, 1); if (ret) goto reserve_shared_fail; amdgpu_bo_fence(vm->root.bo, @@ -2606,7 +2571,7 @@ int amdgpu_amdkfd_add_gws_to_process(void *info, void *gws, struct kgd_mem **mem * Add process eviction fence to bo so they can * evict each other. */ - ret = dma_resv_reserve_shared(gws_bo->tbo.base.resv, 1); + ret = dma_resv_reserve_fences(gws_bo->tbo.base.resv, 1); if (ret) goto reserve_shared_fail; amdgpu_bo_fence(gws_bo, &process_info->eviction_fence->base, true); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c index 970b065e9a6b..e85e347eb670 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c @@ -1275,18 +1275,23 @@ static int amdgpu_cs_submit(struct amdgpu_cs_parser *p, amdgpu_bo_list_for_each_entry(e, p->bo_list) { struct dma_resv *resv = e->tv.bo->base.resv; struct dma_fence_chain *chain = e->chain; + struct dma_resv_iter cursor; + struct dma_fence *fence; if (!chain) continue; /* - * Work around dma_resv shortcomings by wrapping up the - * submission in a dma_fence_chain and add it as exclusive + * Temporary workaround dma_resv shortcommings by wrapping up + * the submission in a dma_fence_chain and add it as exclusive * fence. + * + * TODO: Remove together with dma_resv rework. */ - dma_fence_chain_init(chain, dma_resv_excl_fence(resv), - dma_fence_get(p->fence), 1); - + dma_resv_for_each_fence(&cursor, resv, false, fence) { + break; + } + dma_fence_chain_init(chain, fence, dma_fence_get(p->fence), 1); rcu_assign_pointer(resv->fence_excl, &chain->base); e->chain = NULL; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c index dd78402e3cb0..8c6b2284cf56 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c @@ -26,23 +26,12 @@ #include "amdgpu.h" -struct amdgpu_gtt_node { - struct ttm_buffer_object *tbo; - struct ttm_range_mgr_node base; -}; - static inline struct amdgpu_gtt_mgr * to_gtt_mgr(struct ttm_resource_manager *man) { return container_of(man, struct amdgpu_gtt_mgr, manager); } -static inline struct amdgpu_gtt_node * -to_amdgpu_gtt_node(struct ttm_resource *res) -{ - return container_of(res, struct amdgpu_gtt_node, base.base); -} - /** * DOC: mem_info_gtt_total * @@ -106,9 +95,9 @@ const struct attribute_group amdgpu_gtt_mgr_attr_group = { */ bool amdgpu_gtt_mgr_has_gart_addr(struct ttm_resource *res) { - struct amdgpu_gtt_node *node = to_amdgpu_gtt_node(res); + struct ttm_range_mgr_node *node = to_ttm_range_mgr_node(res); - return drm_mm_node_allocated(&node->base.mm_nodes[0]); + return drm_mm_node_allocated(&node->mm_nodes[0]); } /** @@ -128,15 +117,14 @@ static int amdgpu_gtt_mgr_new(struct ttm_resource_manager *man, { struct amdgpu_gtt_mgr *mgr = to_gtt_mgr(man); uint32_t num_pages = PFN_UP(tbo->base.size); - struct amdgpu_gtt_node *node; + struct ttm_range_mgr_node *node; int r; - node = kzalloc(struct_size(node, base.mm_nodes, 1), GFP_KERNEL); + node = kzalloc(struct_size(node, mm_nodes, 1), GFP_KERNEL); if (!node) return -ENOMEM; - node->tbo = tbo; - ttm_resource_init(tbo, place, &node->base.base); + ttm_resource_init(tbo, place, &node->base); if (!(place->flags & TTM_PL_FLAG_TEMPORARY) && ttm_resource_manager_usage(man) > man->size) { r = -ENOSPC; @@ -145,8 +133,7 @@ static int amdgpu_gtt_mgr_new(struct ttm_resource_manager *man, if (place->lpfn) { spin_lock(&mgr->lock); - r = drm_mm_insert_node_in_range(&mgr->mm, - &node->base.mm_nodes[0], + r = drm_mm_insert_node_in_range(&mgr->mm, &node->mm_nodes[0], num_pages, tbo->page_alignment, 0, place->fpfn, place->lpfn, DRM_MM_INSERT_BEST); @@ -154,18 +141,18 @@ static int amdgpu_gtt_mgr_new(struct ttm_resource_manager *man, if (unlikely(r)) goto err_free; - node->base.base.start = node->base.mm_nodes[0].start; + node->base.start = node->mm_nodes[0].start; } else { - node->base.mm_nodes[0].start = 0; - node->base.mm_nodes[0].size = node->base.base.num_pages; - node->base.base.start = AMDGPU_BO_INVALID_OFFSET; + node->mm_nodes[0].start = 0; + node->mm_nodes[0].size = node->base.num_pages; + node->base.start = AMDGPU_BO_INVALID_OFFSET; } - *res = &node->base.base; + *res = &node->base; return 0; err_free: - ttm_resource_fini(man, &node->base.base); + ttm_resource_fini(man, &node->base); kfree(node); return r; } @@ -181,12 +168,12 @@ err_free: static void amdgpu_gtt_mgr_del(struct ttm_resource_manager *man, struct ttm_resource *res) { - struct amdgpu_gtt_node *node = to_amdgpu_gtt_node(res); + struct ttm_range_mgr_node *node = to_ttm_range_mgr_node(res); struct amdgpu_gtt_mgr *mgr = to_gtt_mgr(man); spin_lock(&mgr->lock); - if (drm_mm_node_allocated(&node->base.mm_nodes[0])) - drm_mm_remove_node(&node->base.mm_nodes[0]); + if (drm_mm_node_allocated(&node->mm_nodes[0])) + drm_mm_remove_node(&node->mm_nodes[0]); spin_unlock(&mgr->lock); ttm_resource_fini(man, res); @@ -202,15 +189,15 @@ static void amdgpu_gtt_mgr_del(struct ttm_resource_manager *man, */ void amdgpu_gtt_mgr_recover(struct amdgpu_gtt_mgr *mgr) { - struct amdgpu_gtt_node *node; + struct ttm_range_mgr_node *node; struct drm_mm_node *mm_node; struct amdgpu_device *adev; adev = container_of(mgr, typeof(*adev), mman.gtt_mgr); spin_lock(&mgr->lock); drm_mm_for_each_node(mm_node, &mgr->mm) { - node = container_of(mm_node, typeof(*node), base.mm_nodes[0]); - amdgpu_ttm_recover_gart(node->tbo); + node = container_of(mm_node, typeof(*node), mm_nodes[0]); + amdgpu_ttm_recover_gart(node->base.bo); } spin_unlock(&mgr->lock); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c index 92a70fb57fa3..81207737c716 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c @@ -107,36 +107,19 @@ static void amdgpu_pasid_free_cb(struct dma_fence *fence, void amdgpu_pasid_free_delayed(struct dma_resv *resv, u32 pasid) { - struct dma_fence *fence, **fences; struct amdgpu_pasid_cb *cb; - unsigned count; + struct dma_fence *fence; int r; - r = dma_resv_get_fences(resv, true, &count, &fences); + r = dma_resv_get_singleton(resv, true, &fence); if (r) goto fallback; - if (count == 0) { + if (!fence) { amdgpu_pasid_free(pasid); return; } - if (count == 1) { - fence = fences[0]; - kfree(fences); - } else { - uint64_t context = dma_fence_context_alloc(1); - struct dma_fence_array *array; - - array = dma_fence_array_create(count, fences, context, - 1, false); - if (!array) { - kfree(fences); - goto fallback; - } - fence = &array->base; - } - cb = kmalloc(sizeof(*cb), GFP_KERNEL); if (!cb) { /* Last resort when we are OOM */ diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c index 940752488330..dd6693fff280 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c @@ -1390,6 +1390,14 @@ void amdgpu_bo_fence(struct amdgpu_bo *bo, struct dma_fence *fence, bool shared) { struct dma_resv *resv = bo->tbo.base.resv; + int r; + + r = dma_resv_reserve_fences(resv, 1); + if (r) { + /* As last resort on OOM we block for the fence */ + dma_fence_wait(fence, false); + return; + } if (shared) dma_resv_add_shared_fence(resv, fence); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c index 4b9ee6e27f74..f7f149588432 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c @@ -1547,7 +1547,6 @@ static struct ttm_device_funcs amdgpu_bo_driver = { .io_mem_reserve = &amdgpu_ttm_io_mem_reserve, .io_mem_pfn = amdgpu_ttm_io_mem_pfn, .access_memory = &amdgpu_ttm_access_memory, - .del_from_lru_notify = &amdgpu_vm_del_from_lru_notify }; /* diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index fc4563cf2828..b13451255e8b 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -377,7 +377,7 @@ static void amdgpu_vm_bo_base_init(struct amdgpu_vm_bo_base *base, dma_resv_assert_held(vm->root.bo->tbo.base.resv); - vm->bulk_moveable = false; + ttm_bo_set_bulk_move(&bo->tbo, &vm->lru_bulk_move); if (bo->tbo.type == ttm_bo_type_kernel && bo->parent) amdgpu_vm_bo_relocated(base); else @@ -640,36 +640,6 @@ void amdgpu_vm_get_pd_bo(struct amdgpu_vm *vm, } /** - * amdgpu_vm_del_from_lru_notify - update bulk_moveable flag - * - * @bo: BO which was removed from the LRU - * - * Make sure the bulk_moveable flag is updated when a BO is removed from the - * LRU. - */ -void amdgpu_vm_del_from_lru_notify(struct ttm_buffer_object *bo) -{ - struct amdgpu_bo *abo; - struct amdgpu_vm_bo_base *bo_base; - - if (!amdgpu_bo_is_amdgpu_bo(bo)) - return; - - if (bo->pin_count) - return; - - abo = ttm_to_amdgpu_bo(bo); - if (!abo->parent) - return; - for (bo_base = abo->vm_bo; bo_base; bo_base = bo_base->next) { - struct amdgpu_vm *vm = bo_base->vm; - - if (abo->tbo.base.resv == vm->root.bo->tbo.base.resv) - vm->bulk_moveable = false; - } - -} -/** * amdgpu_vm_move_to_lru_tail - move all BOs to the end of LRU * * @adev: amdgpu device pointer @@ -681,35 +651,9 @@ void amdgpu_vm_del_from_lru_notify(struct ttm_buffer_object *bo) void amdgpu_vm_move_to_lru_tail(struct amdgpu_device *adev, struct amdgpu_vm *vm) { - struct amdgpu_vm_bo_base *bo_base; - - if (vm->bulk_moveable) { - spin_lock(&adev->mman.bdev.lru_lock); - ttm_bo_bulk_move_lru_tail(&vm->lru_bulk_move); - spin_unlock(&adev->mman.bdev.lru_lock); - return; - } - - memset(&vm->lru_bulk_move, 0, sizeof(vm->lru_bulk_move)); - spin_lock(&adev->mman.bdev.lru_lock); - list_for_each_entry(bo_base, &vm->idle, vm_status) { - struct amdgpu_bo *bo = bo_base->bo; - struct amdgpu_bo *shadow = amdgpu_bo_shadowed(bo); - - if (!bo->parent) - continue; - - ttm_bo_move_to_lru_tail(&bo->tbo, bo->tbo.resource, - &vm->lru_bulk_move); - if (shadow) - ttm_bo_move_to_lru_tail(&shadow->tbo, - shadow->tbo.resource, - &vm->lru_bulk_move); - } + ttm_lru_bulk_move_tail(&vm->lru_bulk_move); spin_unlock(&adev->mman.bdev.lru_lock); - - vm->bulk_moveable = true; } /** @@ -732,8 +676,6 @@ int amdgpu_vm_validate_pt_bos(struct amdgpu_device *adev, struct amdgpu_vm *vm, struct amdgpu_vm_bo_base *bo_base, *tmp; int r; - vm->bulk_moveable &= list_empty(&vm->evicted); - list_for_each_entry_safe(bo_base, tmp, &vm->evicted, vm_status) { struct amdgpu_bo *bo = bo_base->bo; struct amdgpu_bo *shadow = amdgpu_bo_shadowed(bo); @@ -1057,10 +999,16 @@ static void amdgpu_vm_free_table(struct amdgpu_vm_bo_base *entry) if (!entry->bo) return; + 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); entry->bo->vm_bo = NULL; list_del(&entry->vm_status); - amdgpu_bo_unref(&shadow); amdgpu_bo_unref(&entry->bo); } @@ -1080,8 +1028,6 @@ static void amdgpu_vm_free_pts(struct amdgpu_device *adev, struct amdgpu_vm_pt_cursor cursor; struct amdgpu_vm_bo_base *entry; - vm->bulk_moveable = false; - for_each_amdgpu_vm_pt_dfs_safe(adev, vm, start, cursor, entry) amdgpu_vm_free_table(entry); @@ -2665,7 +2611,7 @@ void amdgpu_vm_bo_del(struct amdgpu_device *adev, if (bo) { dma_resv_assert_held(bo->tbo.base.resv); if (bo->tbo.base.resv == vm->root.bo->tbo.base.resv) - vm->bulk_moveable = false; + ttm_bo_set_bulk_move(&bo->tbo, NULL); for (base = &bo_va->base.bo->vm_bo; *base; base = &(*base)->next) { @@ -2980,7 +2926,7 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm) if (r) goto error_free_root; - r = dma_resv_reserve_shared(root_bo->tbo.base.resv, 1); + r = dma_resv_reserve_fences(root_bo->tbo.base.resv, 1); if (r) goto error_unreserve; @@ -3423,7 +3369,7 @@ bool amdgpu_vm_handle_fault(struct amdgpu_device *adev, u32 pasid, value = 0; } - r = dma_resv_reserve_shared(root->tbo.base.resv, 1); + r = dma_resv_reserve_fences(root->tbo.base.resv, 1); if (r) { pr_debug("failed %d to reserve fence slot\n", r); goto error_unlock; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h index a40a6a993bb0..bd7892482bbf 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h @@ -317,8 +317,6 @@ struct amdgpu_vm { /* Store positions of group of BOs */ struct ttm_lru_bulk_move lru_bulk_move; - /* mark whether can do the bulk move */ - bool bulk_moveable; /* Flag to indicate if VM is used for compute */ bool is_compute_context; }; @@ -454,7 +452,6 @@ void amdgpu_vm_set_task_info(struct amdgpu_vm *vm); void amdgpu_vm_move_to_lru_tail(struct amdgpu_device *adev, struct amdgpu_vm *vm); -void amdgpu_vm_del_from_lru_notify(struct ttm_buffer_object *bo); void amdgpu_vm_get_memory(struct amdgpu_vm *vm, uint64_t *vram_mem, uint64_t *gtt_mem, uint64_t *cpu_mem); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c index 3b8856b4cece..b3fc3e958227 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c @@ -548,7 +548,7 @@ svm_range_vram_node_new(struct amdgpu_device *adev, struct svm_range *prange, goto reserve_bo_failed; } - r = dma_resv_reserve_shared(bo->tbo.base.resv, 1); + r = dma_resv_reserve_fences(bo->tbo.base.resv, 1); if (r) { pr_debug("failed %d to reserve bo\n", r); amdgpu_bo_unreserve(bo); |