diff options
Diffstat (limited to 'drivers/gpu/drm/amd/amdgpu')
22 files changed, 175 insertions, 188 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/ObjectID.h b/drivers/gpu/drm/amd/amdgpu/ObjectID.h index 5b393622f592..a0f0a17e224f 100644 --- a/drivers/gpu/drm/amd/amdgpu/ObjectID.h +++ b/drivers/gpu/drm/amd/amdgpu/ObjectID.h @@ -119,6 +119,7 @@ #define CONNECTOR_OBJECT_ID_eDP 0x14 #define CONNECTOR_OBJECT_ID_MXM 0x15 #define CONNECTOR_OBJECT_ID_LVDS_eDP 0x16 +#define CONNECTOR_OBJECT_ID_USBC 0x17 /* deleted */ 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_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 3987ecb24ef4..49f734137f15 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -5733,7 +5733,7 @@ void amdgpu_device_flush_hdp(struct amdgpu_device *adev, struct amdgpu_ring *ring) { #ifdef CONFIG_X86_64 - if (adev->flags & AMD_IS_APU) + if ((adev->flags & AMD_IS_APU) && !amdgpu_passthrough(adev)) return; #endif if (adev->gmc.xgmi.connected_to_cpu) @@ -5749,7 +5749,7 @@ void amdgpu_device_invalidate_hdp(struct amdgpu_device *adev, struct amdgpu_ring *ring) { #ifdef CONFIG_X86_64 - if (adev->flags & AMD_IS_APU) + if ((adev->flags & AMD_IS_APU) && !amdgpu_passthrough(adev)) return; #endif if (adev->gmc.xgmi.connected_to_cpu) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index bb1c025d9001..b03663f42cc9 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -680,7 +680,7 @@ MODULE_PARM_DESC(sched_policy, * Maximum number of processes that HWS can schedule concurrently. The maximum is the * number of VMIDs assigned to the HWS, which is also the default. */ -int hws_max_conc_proc = 8; +int hws_max_conc_proc = -1; module_param(hws_max_conc_proc, int, 0444); MODULE_PARM_DESC(hws_max_conc_proc, "Max # processes HWS can execute concurrently when sched_policy=0 (0 = no concurrency, #VMIDs for KFD = Maximum(default))"); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c index 8fe939976224..28a736c507bb 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c @@ -266,7 +266,7 @@ static int amdgpu_gfx_kiq_acquire(struct amdgpu_device *adev, * adev->gfx.mec.num_pipe_per_mec * adev->gfx.mec.num_queue_per_pipe; - while (queue_bit-- >= 0) { + while (--queue_bit >= 0) { if (test_bit(queue_bit, adev->gfx.mec.queue_bitmap)) continue; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c index ca2cfb65f976..a66a0881a934 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c @@ -561,9 +561,15 @@ void amdgpu_gmc_noretry_set(struct amdgpu_device *adev) switch (adev->ip_versions[GC_HWIP][0]) { case IP_VERSION(9, 0, 1): + case IP_VERSION(9, 3, 0): case IP_VERSION(9, 4, 0): case IP_VERSION(9, 4, 1): case IP_VERSION(9, 4, 2): + case IP_VERSION(10, 3, 3): + case IP_VERSION(10, 3, 4): + case IP_VERSION(10, 3, 5): + case IP_VERSION(10, 3, 6): + case IP_VERSION(10, 3, 7): /* * noretry = 0 will cause kfd page fault tests fail * for some ASICs, so set default to 1 for these ASICs. 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 25731719c627..dd6693fff280 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c @@ -1284,6 +1284,7 @@ void amdgpu_bo_get_memory(struct amdgpu_bo *bo, uint64_t *vram_mem, */ void amdgpu_bo_release_notify(struct ttm_buffer_object *bo) { + struct amdgpu_device *adev = amdgpu_ttm_adev(bo->bdev); struct dma_fence *fence = NULL; struct amdgpu_bo *abo; int r; @@ -1303,7 +1304,8 @@ void amdgpu_bo_release_notify(struct ttm_buffer_object *bo) amdgpu_amdkfd_remove_fence_on_pt_pd_bos(abo); if (bo->resource->mem_type != TTM_PL_VRAM || - !(abo->flags & AMDGPU_GEM_CREATE_VRAM_WIPE_ON_RELEASE)) + !(abo->flags & AMDGPU_GEM_CREATE_VRAM_WIPE_ON_RELEASE) || + adev->in_suspend || adev->shutdown) return; if (WARN_ON_ONCE(!dma_resv_trylock(bo->base.resv))) @@ -1388,6 +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_ring.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h index 5320bb0883d8..317d80209e95 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h @@ -300,8 +300,8 @@ void amdgpu_ring_generic_pad_ib(struct amdgpu_ring *ring, struct amdgpu_ib *ib); void amdgpu_ring_commit(struct amdgpu_ring *ring); void amdgpu_ring_undo(struct amdgpu_ring *ring); int amdgpu_ring_init(struct amdgpu_device *adev, struct amdgpu_ring *ring, - unsigned int ring_size, struct amdgpu_irq_src *irq_src, - unsigned int irq_type, unsigned int prio, + unsigned int max_dw, struct amdgpu_irq_src *irq_src, + unsigned int irq_type, unsigned int hw_prio, atomic_t *sched_score); void amdgpu_ring_fini(struct amdgpu_ring *ring); void amdgpu_ring_emit_reg_write_reg_wait_helper(struct amdgpu_ring *ring, 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_vcn.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h index e2fde88aaf5e..f06fb7f882e2 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h @@ -159,6 +159,7 @@ #define AMDGPU_VCN_MULTI_QUEUE_FLAG (1 << 8) #define AMDGPU_VCN_SW_RING_FLAG (1 << 9) #define AMDGPU_VCN_FW_LOGGING_FLAG (1 << 10) +#define AMDGPU_VCN_SMU_VERSION_INFO_FLAG (1 << 11) #define AMDGPU_VCN_IB_FLAG_DECODE_BUFFER 0x00000001 #define AMDGPU_VCN_CMD_FLAG_MSG_BUFFER 0x00000001 @@ -279,6 +280,11 @@ struct amdgpu_fw_shared_fw_logging { uint32_t size; }; +struct amdgpu_fw_shared_smu_interface_info { + uint8_t smu_interface_type; + uint8_t padding[3]; +}; + struct amdgpu_fw_shared { uint32_t present_flag_0; uint8_t pad[44]; @@ -287,6 +293,7 @@ struct amdgpu_fw_shared { struct amdgpu_fw_shared_multi_queue multi_queue; struct amdgpu_fw_shared_sw_ring sw_ring; struct amdgpu_fw_shared_fw_logging fw_log; + struct amdgpu_fw_shared_smu_interface_info smu_interface_info; }; struct amdgpu_vcn_fwlog { 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/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c index f4c6accd3226..9426e252d8aa 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c @@ -3293,7 +3293,7 @@ static const struct soc15_reg_golden golden_settings_gc_10_3_3[] = SOC15_REG_GOLDEN_VALUE(GC, 0, mmDB_DEBUG3, 0xffffffff, 0x00000280), SOC15_REG_GOLDEN_VALUE(GC, 0, mmDB_DEBUG4, 0xffffffff, 0x00800000), SOC15_REG_GOLDEN_VALUE(GC, 0, mmGB_ADDR_CONFIG, 0x0c1807ff, 0x00000242), - SOC15_REG_GOLDEN_VALUE(GC, 0, mmGCR_GENERAL_CNTL, 0x1ff1ffff, 0x00000500), + SOC15_REG_GOLDEN_VALUE(GC, 0, mmGCR_GENERAL_CNTL_Vangogh, 0x1ff1ffff, 0x00000500), SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL1_PIPE_STEER, 0x000000ff, 0x000000e4), SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL2_PIPE_STEER_0, 0x77777777, 0x32103210), SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL2_PIPE_STEER_1, 0x77777777, 0x32103210), @@ -3429,7 +3429,7 @@ static const struct soc15_reg_golden golden_settings_gc_10_3_6[] = SOC15_REG_GOLDEN_VALUE(GC, 0, mmDB_DEBUG3, 0xffffffff, 0x00000280), SOC15_REG_GOLDEN_VALUE(GC, 0, mmDB_DEBUG4, 0xffffffff, 0x00800000), SOC15_REG_GOLDEN_VALUE(GC, 0, mmGB_ADDR_CONFIG, 0x0c1807ff, 0x00000042), - SOC15_REG_GOLDEN_VALUE(GC, 0, mmGCR_GENERAL_CNTL, 0x1ff1ffff, 0x00000500), + SOC15_REG_GOLDEN_VALUE(GC, 0, mmGCR_GENERAL_CNTL_Vangogh, 0x1ff1ffff, 0x00000500), SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL1_PIPE_STEER, 0x000000ff, 0x00000044), SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL2_PIPE_STEER_0, 0x77777777, 0x32103210), SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL2_PIPE_STEER_1, 0x77777777, 0x32103210), @@ -3454,7 +3454,7 @@ static const struct soc15_reg_golden golden_settings_gc_10_3_7[] = { SOC15_REG_GOLDEN_VALUE(GC, 0, mmDB_DEBUG3, 0xffffffff, 0x00000280), SOC15_REG_GOLDEN_VALUE(GC, 0, mmDB_DEBUG4, 0xffffffff, 0x00800000), SOC15_REG_GOLDEN_VALUE(GC, 0, mmGB_ADDR_CONFIG, 0x0c1807ff, 0x00000041), - SOC15_REG_GOLDEN_VALUE(GC, 0, mmGCR_GENERAL_CNTL, 0x1ff1ffff, 0x00000500), + SOC15_REG_GOLDEN_VALUE(GC, 0, mmGCR_GENERAL_CNTL_Vangogh, 0x1ff1ffff, 0x00000500), SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL1_PIPE_STEER, 0x000000ff, 0x000000e4), SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL2_PIPE_STEER_0, 0x77777777, 0x32103210), SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL2_PIPE_STEER_1, 0x77777777, 0x32103210), @@ -7689,6 +7689,7 @@ static uint64_t gfx_v10_0_get_gpu_clock_counter(struct amdgpu_device *adev) switch (adev->ip_versions[GC_HWIP][0]) { case IP_VERSION(10, 3, 1): case IP_VERSION(10, 3, 3): + case IP_VERSION(10, 3, 7): preempt_disable(); clock_hi = RREG32_SOC15_NO_KIQ(SMUIO, 0, mmGOLDEN_TSC_COUNT_UPPER_Vangogh); clock_lo = RREG32_SOC15_NO_KIQ(SMUIO, 0, mmGOLDEN_TSC_COUNT_LOWER_Vangogh); diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c index 3c1d440824a7..5228421b0f72 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c @@ -814,7 +814,7 @@ static int gmc_v10_0_mc_init(struct amdgpu_device *adev) adev->gmc.aper_size = pci_resource_len(adev->pdev, 0); #ifdef CONFIG_X86_64 - if (adev->flags & AMD_IS_APU) { + if ((adev->flags & AMD_IS_APU) && !amdgpu_passthrough(adev)) { adev->gmc.aper_base = adev->gfxhub.funcs->get_mc_fb_offset(adev); adev->gmc.aper_size = adev->gmc.real_vram_size; } diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c index 344d819b4c1b..979da6f510e8 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c @@ -381,8 +381,9 @@ static int gmc_v7_0_mc_init(struct amdgpu_device *adev) adev->gmc.aper_size = pci_resource_len(adev->pdev, 0); #ifdef CONFIG_X86_64 - if (adev->flags & AMD_IS_APU && - adev->gmc.real_vram_size > adev->gmc.aper_size) { + if ((adev->flags & AMD_IS_APU) && + adev->gmc.real_vram_size > adev->gmc.aper_size && + !amdgpu_passthrough(adev)) { adev->gmc.aper_base = ((u64)RREG32(mmMC_VM_FB_OFFSET)) << 22; adev->gmc.aper_size = adev->gmc.real_vram_size; } diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c index ca9841d5669f..1932a3e4af7e 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c @@ -581,7 +581,7 @@ static int gmc_v8_0_mc_init(struct amdgpu_device *adev) adev->gmc.aper_size = pci_resource_len(adev->pdev, 0); #ifdef CONFIG_X86_64 - if (adev->flags & AMD_IS_APU) { + if ((adev->flags & AMD_IS_APU) && !amdgpu_passthrough(adev)) { adev->gmc.aper_base = ((u64)RREG32(mmMC_VM_FB_OFFSET)) << 22; adev->gmc.aper_size = adev->gmc.real_vram_size; } diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c index 431742eb7811..6009fbfdcc19 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c @@ -1456,7 +1456,7 @@ static int gmc_v9_0_mc_init(struct amdgpu_device *adev) */ /* check whether both host-gpu and gpu-gpu xgmi links exist */ - if ((adev->flags & AMD_IS_APU) || + if (((adev->flags & AMD_IS_APU) && !amdgpu_passthrough(adev)) || (adev->gmc.xgmi.supported && adev->gmc.xgmi.connected_to_cpu)) { adev->gmc.aper_base = @@ -1721,7 +1721,7 @@ static int gmc_v9_0_sw_fini(void *handle) amdgpu_gem_force_release(adev); amdgpu_vm_manager_fini(adev); amdgpu_gart_table_vram_free(adev); - amdgpu_bo_unref(&adev->gmc.pdb0_bo); + amdgpu_bo_free_kernel(&adev->gmc.pdb0_bo, NULL, &adev->gmc.ptr_pdb0); amdgpu_bo_fini(adev); return 0; diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c index dff54190b96c..f0fbcda76f5e 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c @@ -24,6 +24,7 @@ #include <linux/firmware.h> #include "amdgpu.h" +#include "amdgpu_cs.h" #include "amdgpu_vcn.h" #include "amdgpu_pm.h" #include "soc15.h" @@ -1900,6 +1901,75 @@ static const struct amd_ip_funcs vcn_v1_0_ip_funcs = { .set_powergating_state = vcn_v1_0_set_powergating_state, }; +/* + * It is a hardware issue that VCN can't handle a GTT TMZ buffer on + * CHIP_RAVEN series ASIC. Move such a GTT TMZ buffer to VRAM domain + * before command submission as a workaround. + */ +static int vcn_v1_0_validate_bo(struct amdgpu_cs_parser *parser, + struct amdgpu_job *job, + uint64_t addr) +{ + struct ttm_operation_ctx ctx = { false, false }; + struct amdgpu_fpriv *fpriv = parser->filp->driver_priv; + struct amdgpu_vm *vm = &fpriv->vm; + struct amdgpu_bo_va_mapping *mapping; + struct amdgpu_bo *bo; + int r; + + addr &= AMDGPU_GMC_HOLE_MASK; + if (addr & 0x7) { + DRM_ERROR("VCN messages must be 8 byte aligned!\n"); + return -EINVAL; + } + + mapping = amdgpu_vm_bo_lookup_mapping(vm, addr/AMDGPU_GPU_PAGE_SIZE); + if (!mapping || !mapping->bo_va || !mapping->bo_va->base.bo) + return -EINVAL; + + bo = mapping->bo_va->base.bo; + if (!(bo->flags & AMDGPU_GEM_CREATE_ENCRYPTED)) + return 0; + + amdgpu_bo_placement_from_domain(bo, AMDGPU_GEM_DOMAIN_VRAM); + r = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx); + if (r) { + DRM_ERROR("Failed to validate the VCN message BO (%d)!\n", r); + return r; + } + + return r; +} + +static int vcn_v1_0_ring_patch_cs_in_place(struct amdgpu_cs_parser *p, + struct amdgpu_job *job, + struct amdgpu_ib *ib) +{ + uint32_t msg_lo = 0, msg_hi = 0; + int i, r; + + if (!(ib->flags & AMDGPU_IB_FLAGS_SECURE)) + return 0; + + for (i = 0; i < ib->length_dw; i += 2) { + uint32_t reg = amdgpu_ib_get_value(ib, i); + uint32_t val = amdgpu_ib_get_value(ib, i + 1); + + if (reg == PACKET0(p->adev->vcn.internal.data0, 0)) { + msg_lo = val; + } else if (reg == PACKET0(p->adev->vcn.internal.data1, 0)) { + msg_hi = val; + } else if (reg == PACKET0(p->adev->vcn.internal.cmd, 0)) { + r = vcn_v1_0_validate_bo(p, job, + ((u64)msg_hi) << 32 | msg_lo); + if (r) + return r; + } + } + + return 0; +} + static const struct amdgpu_ring_funcs vcn_v1_0_dec_ring_vm_funcs = { .type = AMDGPU_RING_TYPE_VCN_DEC, .align_mask = 0xf, @@ -1910,6 +1980,7 @@ static const struct amdgpu_ring_funcs vcn_v1_0_dec_ring_vm_funcs = { .get_rptr = vcn_v1_0_dec_ring_get_rptr, .get_wptr = vcn_v1_0_dec_ring_get_wptr, .set_wptr = vcn_v1_0_dec_ring_set_wptr, + .patch_cs_in_place = vcn_v1_0_ring_patch_cs_in_place, .emit_frame_size = 6 + 6 + /* hdp invalidate / flush */ SOC15_FLUSH_GPU_TLB_NUM_WREG * 6 + diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c index c87263ed20ec..cb5f0a12333f 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c @@ -219,6 +219,11 @@ static int vcn_v3_0_sw_init(void *handle) cpu_to_le32(AMDGPU_VCN_MULTI_QUEUE_FLAG) | cpu_to_le32(AMDGPU_VCN_FW_SHARED_FLAG_0_RB); fw_shared->sw_ring.is_enabled = cpu_to_le32(DEC_SW_RING_ENABLED); + fw_shared->present_flag_0 |= AMDGPU_VCN_SMU_VERSION_INFO_FLAG; + if (adev->ip_versions[UVD_HWIP][0] == IP_VERSION(3, 1, 2)) + fw_shared->smu_interface_info.smu_interface_type = 2; + else if (adev->ip_versions[UVD_HWIP][0] == IP_VERSION(3, 1, 1)) + fw_shared->smu_interface_info.smu_interface_type = 1; if (amdgpu_vcnfw_log) amdgpu_vcn_fwlog_init(&adev->vcn.inst[i]); @@ -575,8 +580,8 @@ static void vcn_v3_0_mc_resume_dpg_mode(struct amdgpu_device *adev, int inst_idx AMDGPU_GPU_PAGE_ALIGN(sizeof(struct amdgpu_fw_shared)), 0, indirect); /* VCN global tiling registers */ - WREG32_SOC15_DPG_MODE(0, SOC15_DPG_MODE_OFFSET( - UVD, 0, mmUVD_GFX10_ADDR_CONFIG), adev->gfx.config.gb_addr_config, 0, indirect); + WREG32_SOC15_DPG_MODE(inst_idx, SOC15_DPG_MODE_OFFSET( + UVD, inst_idx, mmUVD_GFX10_ADDR_CONFIG), adev->gfx.config.gb_addr_config, 0, indirect); } static void vcn_v3_0_disable_static_power_gating(struct amdgpu_device *adev, int inst) @@ -1480,8 +1485,11 @@ static int vcn_v3_0_start_sriov(struct amdgpu_device *adev) static int vcn_v3_0_stop_dpg_mode(struct amdgpu_device *adev, int inst_idx) { + struct dpg_pause_state state = {.fw_based = VCN_DPG_STATE__UNPAUSE}; uint32_t tmp; + vcn_v3_0_pause_dpg_mode(adev, inst_idx, &state); + /* Wait for power status to be 1 */ SOC15_WAIT_ON_RREG(VCN, inst_idx, mmUVD_POWER_STATUS, 1, UVD_POWER_STATUS__UVD_POWER_STATUS_MASK); |