diff options
Diffstat (limited to 'drivers/gpu/drm')
98 files changed, 855 insertions, 491 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h index 12e71bbfd222..103635ab784c 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h @@ -76,7 +76,7 @@ extern int amdgpu_modeset; extern int amdgpu_vram_limit; extern int amdgpu_vis_vram_limit; -extern unsigned amdgpu_gart_size; +extern int amdgpu_gart_size; extern int amdgpu_gtt_size; extern int amdgpu_moverate; extern int amdgpu_benchmarking; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c index fb6e5dbd5a03..309f2419c6d8 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c @@ -155,7 +155,6 @@ static const struct kfd2kgd_calls kfd2kgd = { struct kfd2kgd_calls *amdgpu_amdkfd_gfx_8_0_get_functions(void) { return (struct kfd2kgd_calls *)&kfd2kgd; - return (struct kfd2kgd_calls *)&kfd2kgd; } static inline struct amdgpu_device *get_amdgpu_device(struct kgd_dev *kgd) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c index 269b835571eb..60d8bedb694d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c @@ -1079,6 +1079,9 @@ static int amdgpu_cs_process_syncobj_out_dep(struct amdgpu_cs_parser *p, GFP_KERNEL); p->num_post_dep_syncobjs = 0; + if (!p->post_dep_syncobjs) + return -ENOMEM; + for (i = 0; i < num_deps; ++i) { p->post_dep_syncobjs[i] = drm_syncobj_find(p->filp, deps[i].handle); if (!p->post_dep_syncobjs[i]) @@ -1150,7 +1153,6 @@ static int amdgpu_cs_submit(struct amdgpu_cs_parser *p, cs->out.handle = amdgpu_ctx_add_fence(p->ctx, ring, p->fence); job->uf_sequence = cs->out.handle; amdgpu_job_free_resources(job); - amdgpu_cs_parser_fini(p, 0, true); trace_amdgpu_cs_ioctl(job); amd_sched_entity_push_job(&job->base); @@ -1208,10 +1210,7 @@ int amdgpu_cs_ioctl(struct drm_device *dev, void *data, struct drm_file *filp) goto out; r = amdgpu_cs_submit(&parser, cs); - if (r) - goto out; - return 0; out: amdgpu_cs_parser_fini(&parser, r, reserved_buffers); return r; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 1a459ac63df4..e630d918fefc 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -1062,11 +1062,11 @@ static void amdgpu_check_arguments(struct amdgpu_device *adev) amdgpu_sched_jobs = roundup_pow_of_two(amdgpu_sched_jobs); } - if (amdgpu_gart_size < 32) { + if (amdgpu_gart_size != -1 && amdgpu_gart_size < 32) { /* gart size must be greater or equal to 32M */ dev_warn(adev->dev, "gart size (%d) too small\n", amdgpu_gart_size); - amdgpu_gart_size = 32; + amdgpu_gart_size = -1; } if (amdgpu_gtt_size != -1 && amdgpu_gtt_size < 32) { @@ -2622,12 +2622,6 @@ static int amdgpu_recover_vram_from_shadow(struct amdgpu_device *adev, goto err; } - r = amdgpu_ttm_bind(&bo->shadow->tbo, &bo->shadow->tbo.mem); - if (r) { - DRM_ERROR("%p bind failed\n", bo->shadow); - goto err; - } - r = amdgpu_bo_restore_from_shadow(adev, ring, bo, NULL, fence, true); if (r) { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index e39ec981b11c..0f16986ec5bc 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -76,7 +76,7 @@ int amdgpu_vram_limit = 0; int amdgpu_vis_vram_limit = 0; -unsigned amdgpu_gart_size = 256; +int amdgpu_gart_size = -1; /* auto */ int amdgpu_gtt_size = -1; /* auto */ int amdgpu_moverate = -1; /* auto */ int amdgpu_benchmarking = 0; @@ -128,7 +128,7 @@ module_param_named(vramlimit, amdgpu_vram_limit, int, 0600); MODULE_PARM_DESC(vis_vramlimit, "Restrict visible VRAM for testing, in megabytes"); module_param_named(vis_vramlimit, amdgpu_vis_vram_limit, int, 0444); -MODULE_PARM_DESC(gartsize, "Size of PCIE/IGP gart to setup in megabytes (32, 64, etc.)"); +MODULE_PARM_DESC(gartsize, "Size of GART to setup in megabytes (32, 64, etc., -1=auto)"); module_param_named(gartsize, amdgpu_gart_size, uint, 0600); MODULE_PARM_DESC(gttsize, "Size of the GTT domain in megabytes (-1 = auto)"); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c index 94c1e2e8e34c..f4370081f6e6 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c @@ -57,18 +57,6 @@ */ /** - * amdgpu_gart_set_defaults - set the default gart_size - * - * @adev: amdgpu_device pointer - * - * Set the default gart_size based on parameters and available VRAM. - */ -void amdgpu_gart_set_defaults(struct amdgpu_device *adev) -{ - adev->mc.gart_size = (uint64_t)amdgpu_gart_size << 20; -} - -/** * amdgpu_gart_table_ram_alloc - allocate system ram for gart page table * * @adev: amdgpu_device pointer diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.h index d4cce6936200..afbe803b1a13 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.h @@ -56,7 +56,6 @@ struct amdgpu_gart { const struct amdgpu_gart_funcs *gart_funcs; }; -void amdgpu_gart_set_defaults(struct amdgpu_device *adev); int amdgpu_gart_table_ram_alloc(struct amdgpu_device *adev); void amdgpu_gart_table_ram_free(struct amdgpu_device *adev); int amdgpu_gart_table_vram_alloc(struct amdgpu_device *adev); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c index 9e05e257729f..0d15eb7d31d7 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c @@ -108,10 +108,10 @@ bool amdgpu_gtt_mgr_is_allocated(struct ttm_mem_reg *mem) * * Allocate the address space for a node. */ -int amdgpu_gtt_mgr_alloc(struct ttm_mem_type_manager *man, - struct ttm_buffer_object *tbo, - const struct ttm_place *place, - struct ttm_mem_reg *mem) +static int amdgpu_gtt_mgr_alloc(struct ttm_mem_type_manager *man, + struct ttm_buffer_object *tbo, + const struct ttm_place *place, + struct ttm_mem_reg *mem) { struct amdgpu_device *adev = amdgpu_ttm_adev(man->bdev); struct amdgpu_gtt_mgr *mgr = man->priv; @@ -143,12 +143,8 @@ int amdgpu_gtt_mgr_alloc(struct ttm_mem_type_manager *man, fpfn, lpfn, mode); spin_unlock(&mgr->lock); - if (!r) { + if (!r) mem->start = node->start; - if (&tbo->mem == mem) - tbo->offset = (tbo->mem.start << PAGE_SHIFT) + - tbo->bdev->man[tbo->mem.mem_type].gpu_offset; - } return r; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c index 4bdd851f56d0..538e5f27d120 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c @@ -221,8 +221,9 @@ int amdgpu_irq_init(struct amdgpu_device *adev) spin_lock_init(&adev->irq.lock); - /* Disable vblank irqs aggressively for power-saving */ - adev->ddev->vblank_disable_immediate = true; + if (!adev->enable_virtual_display) + /* Disable vblank irqs aggressively for power-saving */ + adev->ddev->vblank_disable_immediate = true; r = drm_vblank_init(adev->ddev, adev->mode_info.num_crtc); if (r) { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c index e1cde6b80027..3b0f2ec6eec7 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c @@ -51,7 +51,7 @@ struct amdgpu_mn { /* objects protected by lock */ struct mutex lock; - struct rb_root objects; + struct rb_root_cached objects; }; struct amdgpu_mn_node { @@ -76,8 +76,8 @@ static void amdgpu_mn_destroy(struct work_struct *work) mutex_lock(&adev->mn_lock); mutex_lock(&rmn->lock); hash_del(&rmn->node); - rbtree_postorder_for_each_entry_safe(node, next_node, &rmn->objects, - it.rb) { + rbtree_postorder_for_each_entry_safe(node, next_node, + &rmn->objects.rb_root, it.rb) { list_for_each_entry_safe(bo, next_bo, &node->bos, mn_list) { bo->mn = NULL; list_del_init(&bo->mn_list); @@ -221,7 +221,7 @@ static struct amdgpu_mn *amdgpu_mn_get(struct amdgpu_device *adev) rmn->mm = mm; rmn->mn.ops = &amdgpu_mn_ops; mutex_init(&rmn->lock); - rmn->objects = RB_ROOT; + rmn->objects = RB_ROOT_CACHED; r = __mmu_notifier_register(&rmn->mn, mm); if (r) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c index e7e899190bef..9e495da0bb03 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c @@ -91,7 +91,10 @@ static void amdgpu_ttm_placement_init(struct amdgpu_device *adev, if (domain & AMDGPU_GEM_DOMAIN_GTT) { places[c].fpfn = 0; - places[c].lpfn = 0; + if (flags & AMDGPU_GEM_CREATE_SHADOW) + places[c].lpfn = adev->mc.gart_size >> PAGE_SHIFT; + else + places[c].lpfn = 0; places[c].flags = TTM_PL_FLAG_TT; if (flags & AMDGPU_GEM_CREATE_CPU_GTT_USWC) places[c].flags |= TTM_PL_FLAG_WC | @@ -446,17 +449,16 @@ static int amdgpu_bo_create_shadow(struct amdgpu_device *adev, if (bo->shadow) return 0; - bo->flags |= AMDGPU_GEM_CREATE_SHADOW; - memset(&placements, 0, - (AMDGPU_GEM_DOMAIN_MAX + 1) * sizeof(struct ttm_place)); - - amdgpu_ttm_placement_init(adev, &placement, - placements, AMDGPU_GEM_DOMAIN_GTT, - AMDGPU_GEM_CREATE_CPU_GTT_USWC); + memset(&placements, 0, sizeof(placements)); + amdgpu_ttm_placement_init(adev, &placement, placements, + AMDGPU_GEM_DOMAIN_GTT, + AMDGPU_GEM_CREATE_CPU_GTT_USWC | + AMDGPU_GEM_CREATE_SHADOW); r = amdgpu_bo_create_restricted(adev, size, byte_align, true, AMDGPU_GEM_DOMAIN_GTT, - AMDGPU_GEM_CREATE_CPU_GTT_USWC, + AMDGPU_GEM_CREATE_CPU_GTT_USWC | + AMDGPU_GEM_CREATE_SHADOW, NULL, &placement, bo->tbo.resv, 0, @@ -484,30 +486,28 @@ int amdgpu_bo_create(struct amdgpu_device *adev, { struct ttm_placement placement = {0}; struct ttm_place placements[AMDGPU_GEM_DOMAIN_MAX + 1]; + uint64_t parent_flags = flags & ~AMDGPU_GEM_CREATE_SHADOW; int r; - memset(&placements, 0, - (AMDGPU_GEM_DOMAIN_MAX + 1) * sizeof(struct ttm_place)); + memset(&placements, 0, sizeof(placements)); + amdgpu_ttm_placement_init(adev, &placement, placements, + domain, parent_flags); - amdgpu_ttm_placement_init(adev, &placement, - placements, domain, flags); - - r = amdgpu_bo_create_restricted(adev, size, byte_align, kernel, - domain, flags, sg, &placement, - resv, init_value, bo_ptr); + r = amdgpu_bo_create_restricted(adev, size, byte_align, kernel, domain, + parent_flags, sg, &placement, resv, + init_value, bo_ptr); if (r) return r; - if (amdgpu_need_backup(adev) && (flags & AMDGPU_GEM_CREATE_SHADOW)) { - if (!resv) { - r = ww_mutex_lock(&(*bo_ptr)->tbo.resv->lock, NULL); - WARN_ON(r != 0); - } + if ((flags & AMDGPU_GEM_CREATE_SHADOW) && amdgpu_need_backup(adev)) { + if (!resv) + WARN_ON(reservation_object_lock((*bo_ptr)->tbo.resv, + NULL)); r = amdgpu_bo_create_shadow(adev, size, byte_align, (*bo_ptr)); if (!resv) - ww_mutex_unlock(&(*bo_ptr)->tbo.resv->lock); + reservation_object_unlock((*bo_ptr)->tbo.resv); if (r) amdgpu_bo_unref(bo_ptr); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c index 6c5646b48d1a..5ce65280b396 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c @@ -170,6 +170,16 @@ int amdgpu_ring_init(struct amdgpu_device *adev, struct amdgpu_ring *ring, unsigned irq_type) { int r; + int sched_hw_submission = amdgpu_sched_hw_submission; + + /* Set the hw submission limit higher for KIQ because + * it's used for a number of gfx/compute tasks by both + * KFD and KGD which may have outstanding fences and + * it doesn't really use the gpu scheduler anyway; + * KIQ tasks get submitted directly to the ring. + */ + if (ring->funcs->type == AMDGPU_RING_TYPE_KIQ) + sched_hw_submission = max(sched_hw_submission, 256); if (ring->adev == NULL) { if (adev->num_rings >= AMDGPU_MAX_RINGS) @@ -178,8 +188,7 @@ int amdgpu_ring_init(struct amdgpu_device *adev, struct amdgpu_ring *ring, ring->adev = adev; ring->idx = adev->num_rings++; adev->rings[ring->idx] = ring; - r = amdgpu_fence_driver_init_ring(ring, - amdgpu_sched_hw_submission); + r = amdgpu_fence_driver_init_ring(ring, sched_hw_submission); if (r) return r; } @@ -218,8 +227,7 @@ int amdgpu_ring_init(struct amdgpu_device *adev, struct amdgpu_ring *ring, return r; } - ring->ring_size = roundup_pow_of_two(max_dw * 4 * - amdgpu_sched_hw_submission); + ring->ring_size = roundup_pow_of_two(max_dw * 4 * sched_hw_submission); ring->buf_mask = (ring->ring_size / 4) - 1; ring->ptr_mask = ring->funcs->support_64bit_ptrs ? diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c index 8b2c294f6f79..7ef6c28a34d9 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c @@ -761,35 +761,11 @@ static void amdgpu_ttm_tt_unpin_userptr(struct ttm_tt *ttm) sg_free_table(ttm->sg); } -static int amdgpu_ttm_do_bind(struct ttm_tt *ttm, struct ttm_mem_reg *mem) -{ - struct amdgpu_ttm_tt *gtt = (void *)ttm; - uint64_t flags; - int r; - - spin_lock(>t->adev->gtt_list_lock); - flags = amdgpu_ttm_tt_pte_flags(gtt->adev, ttm, mem); - gtt->offset = (u64)mem->start << PAGE_SHIFT; - r = amdgpu_gart_bind(gtt->adev, gtt->offset, ttm->num_pages, - ttm->pages, gtt->ttm.dma_address, flags); - - if (r) { - DRM_ERROR("failed to bind %lu pages at 0x%08llX\n", - ttm->num_pages, gtt->offset); - goto error_gart_bind; - } - - list_add_tail(>t->list, >t->adev->gtt_list); -error_gart_bind: - spin_unlock(>t->adev->gtt_list_lock); - return r; - -} - static int amdgpu_ttm_backend_bind(struct ttm_tt *ttm, struct ttm_mem_reg *bo_mem) { struct amdgpu_ttm_tt *gtt = (void*)ttm; + uint64_t flags; int r = 0; if (gtt->userptr) { @@ -809,9 +785,24 @@ static int amdgpu_ttm_backend_bind(struct ttm_tt *ttm, bo_mem->mem_type == AMDGPU_PL_OA) return -EINVAL; - if (amdgpu_gtt_mgr_is_allocated(bo_mem)) - r = amdgpu_ttm_do_bind(ttm, bo_mem); + if (!amdgpu_gtt_mgr_is_allocated(bo_mem)) + return 0; + spin_lock(>t->adev->gtt_list_lock); + flags = amdgpu_ttm_tt_pte_flags(gtt->adev, ttm, bo_mem); + gtt->offset = (u64)bo_mem->start << PAGE_SHIFT; + r = amdgpu_gart_bind(gtt->adev, gtt->offset, ttm->num_pages, + ttm->pages, gtt->ttm.dma_address, flags); + + if (r) { + DRM_ERROR("failed to bind %lu pages at 0x%08llX\n", + ttm->num_pages, gtt->offset); + goto error_gart_bind; + } + + list_add_tail(>t->list, >t->adev->gtt_list); +error_gart_bind: + spin_unlock(>t->adev->gtt_list_lock); return r; } @@ -824,20 +815,39 @@ bool amdgpu_ttm_is_bound(struct ttm_tt *ttm) int amdgpu_ttm_bind(struct ttm_buffer_object *bo, struct ttm_mem_reg *bo_mem) { + struct amdgpu_device *adev = amdgpu_ttm_adev(bo->bdev); struct ttm_tt *ttm = bo->ttm; + struct ttm_mem_reg tmp; + + struct ttm_placement placement; + struct ttm_place placements; int r; if (!ttm || amdgpu_ttm_is_bound(ttm)) return 0; - r = amdgpu_gtt_mgr_alloc(&bo->bdev->man[TTM_PL_TT], bo, - NULL, bo_mem); - if (r) { - DRM_ERROR("Failed to allocate GTT address space (%d)\n", r); + tmp = bo->mem; + tmp.mm_node = NULL; + placement.num_placement = 1; + placement.placement = &placements; + placement.num_busy_placement = 1; + placement.busy_placement = &placements; + placements.fpfn = 0; + placements.lpfn = adev->mc.gart_size >> PAGE_SHIFT; + placements.flags = TTM_PL_MASK_CACHING | TTM_PL_FLAG_TT; + + r = ttm_bo_mem_space(bo, &placement, &tmp, true, false); + if (unlikely(r)) return r; - } - return amdgpu_ttm_do_bind(ttm, bo_mem); + r = ttm_bo_move_ttm(bo, true, false, &tmp); + if (unlikely(r)) + ttm_bo_mem_put(bo, &tmp); + else + bo->offset = (bo->mem.start << PAGE_SHIFT) + + bo->bdev->man[bo->mem.mem_type].gpu_offset; + + return r; } int amdgpu_ttm_recover_gart(struct amdgpu_device *adev) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h index f22a4758719d..43093bffa2cf 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h @@ -62,10 +62,6 @@ extern const struct ttm_mem_type_manager_func amdgpu_gtt_mgr_func; extern const struct ttm_mem_type_manager_func amdgpu_vram_mgr_func; bool amdgpu_gtt_mgr_is_allocated(struct ttm_mem_reg *mem); -int amdgpu_gtt_mgr_alloc(struct ttm_mem_type_manager *man, - struct ttm_buffer_object *tbo, - const struct ttm_place *place, - struct ttm_mem_reg *mem); uint64_t amdgpu_gtt_mgr_usage(struct ttm_mem_type_manager *man); uint64_t amdgpu_vram_mgr_usage(struct ttm_mem_type_manager *man); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index 6b1343e5541d..bd20ff018512 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -165,14 +165,6 @@ static int amdgpu_vm_validate_level(struct amdgpu_vm_pt *parent, unsigned i; int r; - if (parent->bo->shadow) { - struct amdgpu_bo *shadow = parent->bo->shadow; - - r = amdgpu_ttm_bind(&shadow->tbo, &shadow->tbo.mem); - if (r) - return r; - } - if (use_cpu_for_update) { r = amdgpu_bo_kmap(parent->bo, NULL); if (r) @@ -1277,7 +1269,7 @@ static void amdgpu_vm_handle_huge_pages(struct amdgpu_pte_update_params *p, /* In the case of a mixed PT the PDE must point to it*/ if (p->adev->asic_type < CHIP_VEGA10 || nptes != AMDGPU_VM_PTE_COUNT(p->adev) || - p->func == amdgpu_vm_do_copy_ptes || + p->src || !(flags & AMDGPU_PTE_VALID)) { dst = amdgpu_bo_gpu_offset(entry->bo); @@ -1294,9 +1286,23 @@ static void amdgpu_vm_handle_huge_pages(struct amdgpu_pte_update_params *p, entry->addr = (dst | flags); if (use_cpu_update) { + /* In case a huge page is replaced with a system + * memory mapping, p->pages_addr != NULL and + * amdgpu_vm_cpu_set_ptes would try to translate dst + * through amdgpu_vm_map_gart. But dst is already a + * GPU address (of the page table). Disable + * amdgpu_vm_map_gart temporarily. + */ + dma_addr_t *tmp; + + tmp = p->pages_addr; + p->pages_addr = NULL; + pd_addr = (unsigned long)amdgpu_bo_kptr(parent->bo); pde = pd_addr + (entry - parent->entries) * 8; amdgpu_vm_cpu_set_ptes(p, pde, dst, 1, 0, flags); + + p->pages_addr = tmp; } else { if (parent->bo->shadow) { pd_addr = amdgpu_bo_gpu_offset(parent->bo->shadow); @@ -1610,7 +1616,6 @@ error_free: * * @adev: amdgpu_device pointer * @exclusive: fence we need to sync to - * @gtt_flags: flags as they are used for GTT * @pages_addr: DMA addresses to use for mapping * @vm: requested vm * @mapping: mapped range and flags to use for the update @@ -1624,7 +1629,6 @@ error_free: */ static int amdgpu_vm_bo_split_mapping(struct amdgpu_device *adev, struct dma_fence *exclusive, - uint64_t gtt_flags, dma_addr_t *pages_addr, struct amdgpu_vm *vm, struct amdgpu_bo_va_mapping *mapping, @@ -1679,11 +1683,7 @@ static int amdgpu_vm_bo_split_mapping(struct amdgpu_device *adev, } if (pages_addr) { - if (flags == gtt_flags) - src = adev->gart.table_addr + - (addr >> AMDGPU_GPU_PAGE_SHIFT) * 8; - else - max_entries = min(max_entries, 16ull * 1024ull); + max_entries = min(max_entries, 16ull * 1024ull); addr = 0; } else if (flags & AMDGPU_PTE_VALID) { addr += adev->vm_manager.vram_base_offset; @@ -1728,10 +1728,10 @@ int amdgpu_vm_bo_update(struct amdgpu_device *adev, struct amdgpu_vm *vm = bo_va->base.vm; struct amdgpu_bo_va_mapping *mapping; dma_addr_t *pages_addr = NULL; - uint64_t gtt_flags, flags; struct ttm_mem_reg *mem; struct drm_mm_node *nodes; struct dma_fence *exclusive; + uint64_t flags; int r; if (clear || !bo_va->base.bo) { @@ -1751,15 +1751,10 @@ int amdgpu_vm_bo_update(struct amdgpu_device *adev, exclusive = reservation_object_get_excl(bo->tbo.resv); } - if (bo) { + if (bo) flags = amdgpu_ttm_tt_pte_flags(adev, bo->tbo.ttm, mem); - gtt_flags = (amdgpu_ttm_is_bound(bo->tbo.ttm) && - adev == amdgpu_ttm_adev(bo->tbo.bdev)) ? - flags : 0; - } else { + else flags = 0x0; - gtt_flags = ~0x0; - } spin_lock(&vm->status_lock); if (!list_empty(&bo_va->base.vm_status)) @@ -1767,8 +1762,7 @@ int amdgpu_vm_bo_update(struct amdgpu_device *adev, spin_unlock(&vm->status_lock); list_for_each_entry(mapping, &bo_va->invalids, list) { - r = amdgpu_vm_bo_split_mapping(adev, exclusive, - gtt_flags, pages_addr, vm, + r = amdgpu_vm_bo_split_mapping(adev, exclusive, pages_addr, vm, mapping, flags, nodes, &bo_va->last_pt_update); if (r) @@ -2475,7 +2469,7 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm, u64 flags; uint64_t init_pde_value = 0; - vm->va = RB_ROOT; + vm->va = RB_ROOT_CACHED; vm->client_id = atomic64_inc_return(&adev->vm_manager.client_counter); for (i = 0; i < AMDGPU_MAX_VMHUBS; i++) vm->reserved_vmid[i] = NULL; @@ -2596,10 +2590,11 @@ void amdgpu_vm_fini(struct amdgpu_device *adev, struct amdgpu_vm *vm) amd_sched_entity_fini(vm->entity.sched, &vm->entity); - if (!RB_EMPTY_ROOT(&vm->va)) { + if (!RB_EMPTY_ROOT(&vm->va.rb_root)) { dev_err(adev->dev, "still active bo inside vm\n"); } - rbtree_postorder_for_each_entry_safe(mapping, tmp, &vm->va, rb) { + rbtree_postorder_for_each_entry_safe(mapping, tmp, + &vm->va.rb_root, rb) { list_del(&mapping->list); amdgpu_vm_it_remove(mapping, &vm->va); kfree(mapping); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h index ba6691b58ee7..6716355403ec 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h @@ -118,7 +118,7 @@ struct amdgpu_vm_pt { struct amdgpu_vm { /* tree of virtual addresses mapped */ - struct rb_root va; + struct rb_root_cached va; /* protecting invalidated */ spinlock_t status_lock; diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c index d228f5a99044..dbbe986f90f2 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c @@ -636,7 +636,194 @@ static void gfx_v6_0_tiling_mode_table_init(struct amdgpu_device *adev) NUM_BANKS(ADDR_SURF_2_BANK); for (reg_offset = 0; reg_offset < num_tile_mode_states; reg_offset++) WREG32(mmGB_TILE_MODE0 + reg_offset, tilemode[reg_offset]); - } else if (adev->asic_type == CHIP_OLAND || adev->asic_type == CHIP_HAINAN) { + } else if (adev->asic_type == CHIP_OLAND) { + tilemode[0] = MICRO_TILE_MODE(ADDR_SURF_DEPTH_MICRO_TILING) | + ARRAY_MODE(ARRAY_2D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P4_8x16) | + TILE_SPLIT(ADDR_SURF_TILE_SPLIT_64B) | + NUM_BANKS(ADDR_SURF_16_BANK) | + BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_4); + tilemode[1] = MICRO_TILE_MODE(ADDR_SURF_DEPTH_MICRO_TILING) | + ARRAY_MODE(ARRAY_2D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P4_8x16) | + TILE_SPLIT(ADDR_SURF_TILE_SPLIT_128B) | + NUM_BANKS(ADDR_SURF_16_BANK) | + BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_4); + tilemode[2] = MICRO_TILE_MODE(ADDR_SURF_DEPTH_MICRO_TILING) | + ARRAY_MODE(ARRAY_2D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P4_8x16) | + TILE_SPLIT(ADDR_SURF_TILE_SPLIT_256B) | + NUM_BANKS(ADDR_SURF_16_BANK) | + BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_4); + tilemode[3] = MICRO_TILE_MODE(ADDR_SURF_DEPTH_MICRO_TILING) | + ARRAY_MODE(ARRAY_2D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P4_8x16) | + TILE_SPLIT(ADDR_SURF_TILE_SPLIT_128B) | + NUM_BANKS(ADDR_SURF_16_BANK) | + BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_4); + tilemode[4] = MICRO_TILE_MODE(ADDR_SURF_DEPTH_MICRO_TILING) | + ARRAY_MODE(ARRAY_1D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P4_8x16) | + TILE_SPLIT(ADDR_SURF_TILE_SPLIT_64B) | + NUM_BANKS(ADDR_SURF_16_BANK) | + BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_2) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2); + tilemode[5] = MICRO_TILE_MODE(ADDR_SURF_DEPTH_MICRO_TILING) | + ARRAY_MODE(ARRAY_2D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P4_8x16) | + TILE_SPLIT(split_equal_to_row_size) | + NUM_BANKS(ADDR_SURF_16_BANK) | + BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_2) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2); + tilemode[6] = MICRO_TILE_MODE(ADDR_SURF_DEPTH_MICRO_TILING) | + ARRAY_MODE(ARRAY_2D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P4_8x16) | + TILE_SPLIT(split_equal_to_row_size) | + NUM_BANKS(ADDR_SURF_16_BANK) | + BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_1) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2); + tilemode[7] = MICRO_TILE_MODE(ADDR_SURF_DEPTH_MICRO_TILING) | + ARRAY_MODE(ARRAY_2D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P4_8x16) | + TILE_SPLIT(split_equal_to_row_size) | + NUM_BANKS(ADDR_SURF_16_BANK) | + BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_4); + tilemode[8] = MICRO_TILE_MODE(ADDR_SURF_DISPLAY_MICRO_TILING) | + ARRAY_MODE(ARRAY_LINEAR_ALIGNED) | + PIPE_CONFIG(ADDR_SURF_P4_8x16) | + TILE_SPLIT(ADDR_SURF_TILE_SPLIT_64B) | + NUM_BANKS(ADDR_SURF_16_BANK) | + BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_2) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2); + tilemode[9] = MICRO_TILE_MODE(ADDR_SURF_DISPLAY_MICRO_TILING) | + ARRAY_MODE(ARRAY_1D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P4_8x16) | + TILE_SPLIT(ADDR_SURF_TILE_SPLIT_64B) | + NUM_BANKS(ADDR_SURF_16_BANK) | + BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_2) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2); + tilemode[10] = MICRO_TILE_MODE(ADDR_SURF_DISPLAY_MICRO_TILING) | + ARRAY_MODE(ARRAY_2D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P4_8x16) | + TILE_SPLIT(ADDR_SURF_TILE_SPLIT_256B) | + NUM_BANKS(ADDR_SURF_16_BANK) | + BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_4); + tilemode[11] = MICRO_TILE_MODE(ADDR_SURF_DISPLAY_MICRO_TILING) | + ARRAY_MODE(ARRAY_2D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P4_8x16) | + TILE_SPLIT(ADDR_SURF_TILE_SPLIT_256B) | + NUM_BANKS(ADDR_SURF_16_BANK) | + BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_2) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2); + tilemode[12] = MICRO_TILE_MODE(ADDR_SURF_DISPLAY_MICRO_TILING) | + ARRAY_MODE(ARRAY_2D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P4_8x16) | + TILE_SPLIT(ADDR_SURF_TILE_SPLIT_512B) | + NUM_BANKS(ADDR_SURF_16_BANK) | + BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_1) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2); + tilemode[13] = MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) | + ARRAY_MODE(ARRAY_1D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P4_8x16) | + TILE_SPLIT(ADDR_SURF_TILE_SPLIT_64B) | + NUM_BANKS(ADDR_SURF_16_BANK) | + BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_2) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2); + tilemode[14] = MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) | + ARRAY_MODE(ARRAY_2D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P4_8x16) | + TILE_SPLIT(ADDR_SURF_TILE_SPLIT_256B) | + NUM_BANKS(ADDR_SURF_16_BANK) | + BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2); + tilemode[15] = MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) | + ARRAY_MODE(ARRAY_2D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P4_8x16) | + TILE_SPLIT(ADDR_SURF_TILE_SPLIT_256B) | + NUM_BANKS(ADDR_SURF_16_BANK) | + BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_2) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2); + tilemode[16] = MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) | + ARRAY_MODE(ARRAY_2D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P4_8x16) | + TILE_SPLIT(ADDR_SURF_TILE_SPLIT_512B) | + NUM_BANKS(ADDR_SURF_16_BANK) | + BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_1) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2); + tilemode[17] = MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) | + ARRAY_MODE(ARRAY_2D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P4_8x16) | + TILE_SPLIT(split_equal_to_row_size) | + NUM_BANKS(ADDR_SURF_16_BANK) | + BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_1) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2); + tilemode[21] = MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) | + ARRAY_MODE(ARRAY_2D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P8_32x32_8x16) | + TILE_SPLIT(ADDR_SURF_TILE_SPLIT_256B) | + NUM_BANKS(ADDR_SURF_16_BANK) | + BANK_WIDTH(ADDR_SURF_BANK_WIDTH_2) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2); + tilemode[22] = MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) | + ARRAY_MODE(ARRAY_2D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P8_32x32_8x16) | + TILE_SPLIT(ADDR_SURF_TILE_SPLIT_256B) | + NUM_BANKS(ADDR_SURF_16_BANK) | + BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_4); + tilemode[23] = MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) | + ARRAY_MODE(ARRAY_2D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P8_32x32_8x16) | + TILE_SPLIT(ADDR_SURF_TILE_SPLIT_256B) | + NUM_BANKS(ADDR_SURF_16_BANK) | + BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_2) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2); + tilemode[24] = MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) | + ARRAY_MODE(ARRAY_2D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P8_32x32_8x16) | + TILE_SPLIT(ADDR_SURF_TILE_SPLIT_512B) | + NUM_BANKS(ADDR_SURF_16_BANK) | + BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_1) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2); + tilemode[25] = MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) | + ARRAY_MODE(ARRAY_2D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P8_32x32_8x16) | + TILE_SPLIT(ADDR_SURF_TILE_SPLIT_1KB) | + NUM_BANKS(ADDR_SURF_8_BANK) | + BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_1) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_1); + for (reg_offset = 0; reg_offset < num_tile_mode_states; reg_offset++) + WREG32(mmGB_TILE_MODE0 + reg_offset, tilemode[reg_offset]); + } else if (adev->asic_type == CHIP_HAINAN) { tilemode[0] = MICRO_TILE_MODE(ADDR_SURF_DEPTH_MICRO_TILING) | ARRAY_MODE(ARRAY_2D_TILED_THIN1) | PIPE_CONFIG(ADDR_SURF_P2) | diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c index 832e592fcd07..fc260c13b1da 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c @@ -4579,9 +4579,9 @@ static int gfx_v8_0_mqd_init(struct amdgpu_ring *ring) mqd->compute_misc_reserved = 0x00000003; if (!(adev->flags & AMD_IS_APU)) { mqd->dynamic_cu_mask_addr_lo = lower_32_bits(ring->mqd_gpu_addr - + offsetof(struct vi_mqd_allocation, dyamic_cu_mask)); + + offsetof(struct vi_mqd_allocation, dynamic_cu_mask)); mqd->dynamic_cu_mask_addr_hi = upper_32_bits(ring->mqd_gpu_addr - + offsetof(struct vi_mqd_allocation, dyamic_cu_mask)); + + offsetof(struct vi_mqd_allocation, dynamic_cu_mask)); } eop_base_addr = ring->eop_gpu_addr >> 8; mqd->cp_hqd_eop_base_addr_lo = eop_base_addr; @@ -4768,8 +4768,8 @@ static int gfx_v8_0_kiq_init_queue(struct amdgpu_ring *ring) mutex_unlock(&adev->srbm_mutex); } else { memset((void *)mqd, 0, sizeof(struct vi_mqd_allocation)); - ((struct vi_mqd_allocation *)mqd)->dyamic_cu_mask = 0xFFFFFFFF; - ((struct vi_mqd_allocation *)mqd)->dyamic_rb_mask = 0xFFFFFFFF; + ((struct vi_mqd_allocation *)mqd)->dynamic_cu_mask = 0xFFFFFFFF; + ((struct vi_mqd_allocation *)mqd)->dynamic_rb_mask = 0xFFFFFFFF; mutex_lock(&adev->srbm_mutex); vi_srbm_select(adev, ring->me, ring->pipe, ring->queue, 0); gfx_v8_0_mqd_init(ring); @@ -4792,8 +4792,8 @@ static int gfx_v8_0_kcq_init_queue(struct amdgpu_ring *ring) if (!adev->gfx.in_reset && !adev->gfx.in_suspend) { memset((void *)mqd, 0, sizeof(struct vi_mqd_allocation)); - ((struct vi_mqd_allocation *)mqd)->dyamic_cu_mask = 0xFFFFFFFF; - ((struct vi_mqd_allocation *)mqd)->dyamic_rb_mask = 0xFFFFFFFF; + ((struct vi_mqd_allocation *)mqd)->dynamic_cu_mask = 0xFFFFFFFF; + ((struct vi_mqd_allocation *)mqd)->dynamic_rb_mask = 0xFFFFFFFF; mutex_lock(&adev->srbm_mutex); vi_srbm_select(adev, ring->me, ring->pipe, ring->queue, 0); gfx_v8_0_mqd_init(ring); diff --git a/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c b/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c index 4f2788b61a08..6c8040e616c4 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c @@ -124,7 +124,7 @@ static void gfxhub_v1_0_init_tlb_regs(struct amdgpu_device *adev) static void gfxhub_v1_0_init_cache_regs(struct amdgpu_device *adev) { - uint32_t tmp, field; + uint32_t tmp; /* Setup L2 cache */ tmp = RREG32_SOC15(GC, 0, mmVM_L2_CNTL); @@ -143,9 +143,8 @@ static void gfxhub_v1_0_init_cache_regs(struct amdgpu_device *adev) tmp = REG_SET_FIELD(tmp, VM_L2_CNTL2, INVALIDATE_L2_CACHE, 1); WREG32_SOC15(GC, 0, mmVM_L2_CNTL2, tmp); - field = adev->vm_manager.fragment_size; tmp = mmVM_L2_CNTL3_DEFAULT; - tmp = REG_SET_FIELD(tmp, VM_L2_CNTL3, BANK_SELECT, field); + tmp = REG_SET_FIELD(tmp, VM_L2_CNTL3, BANK_SELECT, 9); tmp = REG_SET_FIELD(tmp, VM_L2_CNTL3, L2_CACHE_BIGK_FRAGMENT_SIZE, 6); WREG32_SOC15(GC, 0, mmVM_L2_CNTL3, tmp); diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c index 12b0c4cd7a5a..5be9c83dfcf7 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c @@ -332,7 +332,24 @@ static int gmc_v6_0_mc_init(struct amdgpu_device *adev) adev->mc.real_vram_size = RREG32(mmCONFIG_MEMSIZE) * 1024ULL * 1024ULL; adev->mc.visible_vram_size = adev->mc.aper_size; - amdgpu_gart_set_defaults(adev); + /* set the gart size */ + if (amdgpu_gart_size == -1) { + switch (adev->asic_type) { + case CHIP_HAINAN: /* no MM engines */ + default: + adev->mc.gart_size = 256ULL << 20; + break; + case CHIP_VERDE: /* UVD, VCE do not support GPUVM */ + case CHIP_TAHITI: /* UVD, VCE do not support GPUVM */ + case CHIP_PITCAIRN: /* UVD, VCE do not support GPUVM */ + case CHIP_OLAND: /* UVD, VCE do not support GPUVM */ + adev->mc.gart_size = 1024ULL << 20; + break; + } + } else { + adev->mc.gart_size = (u64)amdgpu_gart_size << 20; + } + gmc_v6_0_vram_gtt_location(adev, &adev->mc); return 0; diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c index e42c1ad3af5e..eace9e7182c8 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c @@ -386,7 +386,27 @@ static int gmc_v7_0_mc_init(struct amdgpu_device *adev) if (adev->mc.visible_vram_size > adev->mc.real_vram_size) adev->mc.visible_vram_size = adev->mc.real_vram_size; - amdgpu_gart_set_defaults(adev); + /* set the gart size */ + if (amdgpu_gart_size == -1) { + switch (adev->asic_type) { + case CHIP_TOPAZ: /* no MM engines */ + default: + adev->mc.gart_size = 256ULL << 20; + break; +#ifdef CONFIG_DRM_AMDGPU_CIK + case CHIP_BONAIRE: /* UVD, VCE do not support GPUVM */ + case CHIP_HAWAII: /* UVD, VCE do not support GPUVM */ + case CHIP_KAVERI: /* UVD, VCE do not support GPUVM */ + case CHIP_KABINI: /* UVD, VCE do not support GPUVM */ + case CHIP_MULLINS: /* UVD, VCE do not support GPUVM */ + adev->mc.gart_size = 1024ULL << 20; + break; +#endif + } + } else { + adev->mc.gart_size = (u64)amdgpu_gart_size << 20; + } + gmc_v7_0_vram_gtt_location(adev, &adev->mc); return 0; diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c index 7ca2dae8237a..3b3326daf32b 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c @@ -562,7 +562,26 @@ static int gmc_v8_0_mc_init(struct amdgpu_device *adev) if (adev->mc.visible_vram_size > adev->mc.real_vram_size) adev->mc.visible_vram_size = adev->mc.real_vram_size; - amdgpu_gart_set_defaults(adev); + /* set the gart size */ + if (amdgpu_gart_size == -1) { + switch (adev->asic_type) { + case CHIP_POLARIS11: /* all engines support GPUVM */ + case CHIP_POLARIS10: /* all engines support GPUVM */ + case CHIP_POLARIS12: /* all engines support GPUVM */ + default: + adev->mc.gart_size = 256ULL << 20; + break; + case CHIP_TONGA: /* UVD, VCE do not support GPUVM */ + case CHIP_FIJI: /* UVD, VCE do not support GPUVM */ + case CHIP_CARRIZO: /* UVD, VCE do not support GPUVM, DCE SG support */ + case CHIP_STONEY: /* UVD does not support GPUVM, DCE SG support */ + adev->mc.gart_size = 1024ULL << 20; + break; + } + } else { + adev->mc.gart_size = (u64)amdgpu_gart_size << 20; + } + gmc_v8_0_vram_gtt_location(adev, &adev->mc); return 0; diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c index 2769c2b3b56e..d04d0b123212 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c @@ -499,7 +499,21 @@ static int gmc_v9_0_mc_init(struct amdgpu_device *adev) if (adev->mc.visible_vram_size > adev->mc.real_vram_size) adev->mc.visible_vram_size = adev->mc.real_vram_size; - amdgpu_gart_set_defaults(adev); + /* set the gart size */ + if (amdgpu_gart_size == -1) { + switch (adev->asic_type) { + case CHIP_VEGA10: /* all engines support GPUVM */ + default: + adev->mc.gart_size = 256ULL << 20; + break; + case CHIP_RAVEN: /* DCE SG support */ + adev->mc.gart_size = 1024ULL << 20; + break; + } + } else { + adev->mc.gart_size = (u64)amdgpu_gart_size << 20; + } + gmc_v9_0_vram_gtt_location(adev, &adev->mc); return 0; diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c index 4395a4f12149..74cb647da30e 100644 --- a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c +++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c @@ -138,7 +138,7 @@ static void mmhub_v1_0_init_tlb_regs(struct amdgpu_device *adev) static void mmhub_v1_0_init_cache_regs(struct amdgpu_device *adev) { - uint32_t tmp, field; + uint32_t tmp; /* Setup L2 cache */ tmp = RREG32_SOC15(MMHUB, 0, mmVM_L2_CNTL); @@ -157,9 +157,8 @@ static void mmhub_v1_0_init_cache_regs(struct amdgpu_device *adev) tmp = REG_SET_FIELD(tmp, VM_L2_CNTL2, INVALIDATE_L2_CACHE, 1); WREG32_SOC15(MMHUB, 0, mmVM_L2_CNTL2, tmp); - field = adev->vm_manager.fragment_size; tmp = mmVM_L2_CNTL3_DEFAULT; - tmp = REG_SET_FIELD(tmp, VM_L2_CNTL3, BANK_SELECT, field); + tmp = REG_SET_FIELD(tmp, VM_L2_CNTL3, BANK_SELECT, 9); tmp = REG_SET_FIELD(tmp, VM_L2_CNTL3, L2_CACHE_BIGK_FRAGMENT_SIZE, 6); WREG32_SOC15(MMHUB, 0, mmVM_L2_CNTL3, tmp); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c index e4a8c2e52cb2..660b3fbade41 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c @@ -892,6 +892,8 @@ static int kfd_ioctl_get_tile_config(struct file *filep, int err = 0; dev = kfd_device_by_id(args->gpu_id); + if (!dev) + return -EINVAL; dev->kfd2kgd->get_tile_config(dev->kgd, &config); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_events.c b/drivers/gpu/drm/amd/amdkfd/kfd_events.c index 5979158c3f7b..944abfad39c1 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_events.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_events.c @@ -292,7 +292,10 @@ static int create_signal_event(struct file *devkfd, struct kfd_event *ev) { if (p->signal_event_count == KFD_SIGNAL_EVENT_LIMIT) { - pr_warn("Signal event wasn't created because limit was reached\n"); + if (!p->signal_event_limit_reached) { + pr_warn("Signal event wasn't created because limit was reached\n"); + p->signal_event_limit_reached = true; + } return -ENOMEM; } diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c b/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c index 681b639f5133..ed71ad40e8f7 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c @@ -183,8 +183,8 @@ static void uninitialize(struct kernel_queue *kq) { if (kq->queue->properties.type == KFD_QUEUE_TYPE_HIQ) kq->mqd->destroy_mqd(kq->mqd, - NULL, - false, + kq->queue->mqd, + KFD_PREEMPT_TYPE_WAVEFRONT_RESET, QUEUE_PREEMPT_DEFAULT_TIMEOUT_MS, kq->queue->pipe, kq->queue->queue); @@ -210,6 +210,11 @@ static int acquire_packet_buffer(struct kernel_queue *kq, uint32_t wptr, rptr; unsigned int *queue_address; + /* When rptr == wptr, the buffer is empty. + * When rptr == wptr + 1, the buffer is full. + * It is always rptr that advances to the position of wptr, rather than + * the opposite. So we can only use up to queue_size_dwords - 1 dwords. + */ rptr = *kq->rptr_kernel; wptr = *kq->wptr_kernel; queue_address = (unsigned int *)kq->pq_kernel_addr; @@ -219,11 +224,10 @@ static int acquire_packet_buffer(struct kernel_queue *kq, pr_debug("wptr: %d\n", wptr); pr_debug("queue_address 0x%p\n", queue_address); - available_size = (rptr - 1 - wptr + queue_size_dwords) % + available_size = (rptr + queue_size_dwords - 1 - wptr) % queue_size_dwords; - if (packet_size_in_dwords >= queue_size_dwords || - packet_size_in_dwords >= available_size) { + if (packet_size_in_dwords > available_size) { /* * make sure calling functions know * acquire_packet_buffer() failed @@ -233,6 +237,14 @@ static int acquire_packet_buffer(struct kernel_queue *kq, } if (wptr + packet_size_in_dwords >= queue_size_dwords) { + /* make sure after rolling back to position 0, there is + * still enough space. + */ + if (packet_size_in_dwords >= rptr) { + *buffer_ptr = NULL; + return -ENOMEM; + } + /* fill nops, roll back and start at position 0 */ while (wptr > 0) { queue_address[wptr] = kq->nop_packet; wptr = (wptr + 1) % queue_size_dwords; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h index b397ec726400..b87e96cee5fa 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h +++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h @@ -521,6 +521,7 @@ struct kfd_process { struct list_head signal_event_pages; u32 next_nonsignal_event_id; size_t signal_event_count; + bool signal_event_limit_reached; }; /** diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c index 1cae95e2b13a..03bec765b03d 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c @@ -143,7 +143,6 @@ int pqm_create_queue(struct process_queue_manager *pqm, int num_queues = 0; struct queue *cur; - memset(&q_properties, 0, sizeof(struct queue_properties)); memcpy(&q_properties, properties, sizeof(struct queue_properties)); q = NULL; kq = NULL; diff --git a/drivers/gpu/drm/amd/include/vi_structs.h b/drivers/gpu/drm/amd/include/vi_structs.h index ca93b5160ba6..3e606a761d0e 100644 --- a/drivers/gpu/drm/amd/include/vi_structs.h +++ b/drivers/gpu/drm/amd/include/vi_structs.h @@ -419,8 +419,8 @@ struct vi_mqd_allocation { struct vi_mqd mqd; uint32_t wptr_poll_mem; uint32_t rptr_report_mem; - uint32_t dyamic_cu_mask; - uint32_t dyamic_rb_mask; + uint32_t dynamic_cu_mask; + uint32_t dynamic_rb_mask; }; struct cz_mqd { diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/rv_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/rv_hwmgr.c index edc5fb6412d9..2c3e6baf2524 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/rv_hwmgr.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/rv_hwmgr.c @@ -317,8 +317,8 @@ static int rv_tf_set_num_active_display(struct pp_hwmgr *hwmgr, void *input, } static const struct phm_master_table_item rv_set_power_state_list[] = { - { NULL, rv_tf_set_clock_limit }, - { NULL, rv_tf_set_num_active_display }, + { .tableFunction = rv_tf_set_clock_limit }, + { .tableFunction = rv_tf_set_num_active_display }, { } }; @@ -391,7 +391,7 @@ static int rv_tf_disable_gfx_off(struct pp_hwmgr *hwmgr, } static const struct phm_master_table_item rv_disable_dpm_list[] = { - {NULL, rv_tf_disable_gfx_off}, + { .tableFunction = rv_tf_disable_gfx_off }, { }, }; @@ -416,7 +416,7 @@ static int rv_tf_enable_gfx_off(struct pp_hwmgr *hwmgr, } static const struct phm_master_table_item rv_enable_dpm_list[] = { - {NULL, rv_tf_enable_gfx_off}, + { .tableFunction = rv_tf_enable_gfx_off }, { }, }; diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c index 9d71a259d97d..f8f02e70b8bc 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c @@ -1558,7 +1558,8 @@ static int vega10_populate_smc_link_levels(struct pp_hwmgr *hwmgr) */ static int vega10_populate_single_gfx_level(struct pp_hwmgr *hwmgr, - uint32_t gfx_clock, PllSetting_t *current_gfxclk_level) + uint32_t gfx_clock, PllSetting_t *current_gfxclk_level, + uint32_t *acg_freq) { struct phm_ppt_v2_information *table_info = (struct phm_ppt_v2_information *)(hwmgr->pptable); @@ -1609,6 +1610,8 @@ static int vega10_populate_single_gfx_level(struct pp_hwmgr *hwmgr, cpu_to_le16(dividers.usPll_ss_slew_frac); current_gfxclk_level->Did = (uint8_t)(dividers.ulDid); + *acg_freq = gfx_clock / 100; /* 100 Khz to Mhz conversion */ + return 0; } @@ -1689,7 +1692,8 @@ static int vega10_populate_all_graphic_levels(struct pp_hwmgr *hwmgr) for (i = 0; i < dpm_table->count; i++) { result = vega10_populate_single_gfx_level(hwmgr, dpm_table->dpm_levels[i].value, - &(pp_table->GfxclkLevel[i])); + &(pp_table->GfxclkLevel[i]), + &(pp_table->AcgFreqTable[i])); if (result) return result; } @@ -1698,7 +1702,8 @@ static int vega10_populate_all_graphic_levels(struct pp_hwmgr *hwmgr) while (i < NUM_GFXCLK_DPM_LEVELS) { result = vega10_populate_single_gfx_level(hwmgr, dpm_table->dpm_levels[j].value, - &(pp_table->GfxclkLevel[i])); + &(pp_table->GfxclkLevel[i]), + &(pp_table->AcgFreqTable[i])); if (result) return result; i++; diff --git a/drivers/gpu/drm/amd/powerplay/inc/smu9_driver_if.h b/drivers/gpu/drm/amd/powerplay/inc/smu9_driver_if.h index f6d6c61f796a..2818c98ff5ca 100644 --- a/drivers/gpu/drm/amd/powerplay/inc/smu9_driver_if.h +++ b/drivers/gpu/drm/amd/powerplay/inc/smu9_driver_if.h @@ -315,10 +315,12 @@ typedef struct { uint8_t AcgEnable[NUM_GFXCLK_DPM_LEVELS]; GbVdroopTable_t AcgBtcGbVdroopTable; QuadraticInt_t AcgAvfsGb; - uint32_t Reserved[4]; + + /* ACG Frequency Table, in Mhz */ + uint32_t AcgFreqTable[NUM_GFXCLK_DPM_LEVELS]; /* Padding - ignore */ - uint32_t MmHubPadding[7]; /* SMU internal use */ + uint32_t MmHubPadding[3]; /* SMU internal use */ } PPTable_t; diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/smu7_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/smu7_smumgr.c index 76347ff6d655..c49a6f22002f 100644 --- a/drivers/gpu/drm/amd/powerplay/smumgr/smu7_smumgr.c +++ b/drivers/gpu/drm/amd/powerplay/smumgr/smu7_smumgr.c @@ -380,7 +380,8 @@ static int smu7_populate_single_firmware_entry(struct pp_smumgr *smumgr, entry->num_register_entries = 0; } - if (fw_type == UCODE_ID_RLC_G) + if ((fw_type == UCODE_ID_RLC_G) + || (fw_type == UCODE_ID_CP_MEC)) entry->flags = 1; else entry->flags = 0; diff --git a/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c b/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c index 38cea6fb25a8..97c94f9683fa 100644 --- a/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c +++ b/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c @@ -205,17 +205,32 @@ void amd_sched_entity_fini(struct amd_gpu_scheduler *sched, struct amd_sched_entity *entity) { struct amd_sched_rq *rq = entity->rq; + int r; if (!amd_sched_entity_is_initialized(sched, entity)) return; - /** * The client will not queue more IBs during this fini, consume existing - * queued IBs + * queued IBs or discard them on SIGKILL */ - wait_event(sched->job_scheduled, amd_sched_entity_is_idle(entity)); - + if ((current->flags & PF_SIGNALED) && current->exit_code == SIGKILL) + r = -ERESTARTSYS; + else + r = wait_event_killable(sched->job_scheduled, + amd_sched_entity_is_idle(entity)); amd_sched_rq_remove_entity(rq, entity); + if (r) { + struct amd_sched_job *job; + + /* Park the kernel for a moment to make sure it isn't processing + * our enity. + */ + kthread_park(sched->thread); + kthread_unpark(sched->thread); + while (kfifo_out(&entity->job_queue, &job, sizeof(job))) + sched->ops->free_job(job); + + } kfifo_free(&entity->job_queue); } diff --git a/drivers/gpu/drm/drm_blend.c b/drivers/gpu/drm/drm_blend.c index db6aeec50b82..2e5e089dd912 100644 --- a/drivers/gpu/drm/drm_blend.c +++ b/drivers/gpu/drm/drm_blend.c @@ -319,7 +319,7 @@ static int drm_atomic_helper_crtc_normalize_zpos(struct drm_crtc *crtc, DRM_DEBUG_ATOMIC("[CRTC:%d:%s] calculating normalized zpos values\n", crtc->base.id, crtc->name); - states = kmalloc_array(total_planes, sizeof(*states), GFP_TEMPORARY); + states = kmalloc_array(total_planes, sizeof(*states), GFP_KERNEL); if (!states) return -ENOMEM; diff --git a/drivers/gpu/drm/drm_dp_dual_mode_helper.c b/drivers/gpu/drm/drm_dp_dual_mode_helper.c index 80e62f669321..0ef9011a1856 100644 --- a/drivers/gpu/drm/drm_dp_dual_mode_helper.c +++ b/drivers/gpu/drm/drm_dp_dual_mode_helper.c @@ -111,7 +111,7 @@ ssize_t drm_dp_dual_mode_write(struct i2c_adapter *adapter, void *data; int ret; - data = kmalloc(msg.len, GFP_TEMPORARY); + data = kmalloc(msg.len, GFP_KERNEL); if (!data) return -ENOMEM; diff --git a/drivers/gpu/drm/drm_mm.c b/drivers/gpu/drm/drm_mm.c index f794089d30ac..61a1c8ea74bc 100644 --- a/drivers/gpu/drm/drm_mm.c +++ b/drivers/gpu/drm/drm_mm.c @@ -169,7 +169,7 @@ INTERVAL_TREE_DEFINE(struct drm_mm_node, rb, struct drm_mm_node * __drm_mm_interval_first(const struct drm_mm *mm, u64 start, u64 last) { - return drm_mm_interval_tree_iter_first((struct rb_root *)&mm->interval_tree, + return drm_mm_interval_tree_iter_first((struct rb_root_cached *)&mm->interval_tree, start, last) ?: (struct drm_mm_node *)&mm->head_node; } EXPORT_SYMBOL(__drm_mm_interval_first); @@ -180,6 +180,7 @@ static void drm_mm_interval_tree_add_node(struct drm_mm_node *hole_node, struct drm_mm *mm = hole_node->mm; struct rb_node **link, *rb; struct drm_mm_node *parent; + bool leftmost = true; node->__subtree_last = LAST(node); @@ -196,9 +197,10 @@ static void drm_mm_interval_tree_add_node(struct drm_mm_node *hole_node, rb = &hole_node->rb; link = &hole_node->rb.rb_right; + leftmost = false; } else { rb = NULL; - link = &mm->interval_tree.rb_node; + link = &mm->interval_tree.rb_root.rb_node; } while (*link) { @@ -208,14 +210,15 @@ static void drm_mm_interval_tree_add_node(struct drm_mm_node *hole_node, parent->__subtree_last = node->__subtree_last; if (node->start < parent->start) link = &parent->rb.rb_left; - else + else { link = &parent->rb.rb_right; + leftmost = true; + } } rb_link_node(&node->rb, rb, link); - rb_insert_augmented(&node->rb, - &mm->interval_tree, - &drm_mm_interval_tree_augment); + rb_insert_augmented_cached(&node->rb, &mm->interval_tree, leftmost, + &drm_mm_interval_tree_augment); } #define RB_INSERT(root, member, expr) do { \ @@ -577,7 +580,7 @@ void drm_mm_replace_node(struct drm_mm_node *old, struct drm_mm_node *new) *new = *old; list_replace(&old->node_list, &new->node_list); - rb_replace_node(&old->rb, &new->rb, &old->mm->interval_tree); + rb_replace_node(&old->rb, &new->rb, &old->mm->interval_tree.rb_root); if (drm_mm_hole_follows(old)) { list_replace(&old->hole_stack, &new->hole_stack); @@ -863,7 +866,7 @@ void drm_mm_init(struct drm_mm *mm, u64 start, u64 size) mm->color_adjust = NULL; INIT_LIST_HEAD(&mm->hole_stack); - mm->interval_tree = RB_ROOT; + mm->interval_tree = RB_ROOT_CACHED; mm->holes_size = RB_ROOT; mm->holes_addr = RB_ROOT; diff --git a/drivers/gpu/drm/drm_scdc_helper.c b/drivers/gpu/drm/drm_scdc_helper.c index 7d1b0f011d33..935653eb3616 100644 --- a/drivers/gpu/drm/drm_scdc_helper.c +++ b/drivers/gpu/drm/drm_scdc_helper.c @@ -102,7 +102,7 @@ ssize_t drm_scdc_write(struct i2c_adapter *adapter, u8 offset, void *data; int err; - data = kmalloc(1 + size, GFP_TEMPORARY); + data = kmalloc(1 + size, GFP_KERNEL); if (!data) return -ENOMEM; diff --git a/drivers/gpu/drm/drm_vma_manager.c b/drivers/gpu/drm/drm_vma_manager.c index d9100b565198..28f1226576f8 100644 --- a/drivers/gpu/drm/drm_vma_manager.c +++ b/drivers/gpu/drm/drm_vma_manager.c @@ -147,7 +147,7 @@ struct drm_vma_offset_node *drm_vma_offset_lookup_locked(struct drm_vma_offset_m struct rb_node *iter; unsigned long offset; - iter = mgr->vm_addr_space_mm.interval_tree.rb_node; + iter = mgr->vm_addr_space_mm.interval_tree.rb_root.rb_node; best = NULL; while (likely(iter)) { diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gem.c b/drivers/gpu/drm/etnaviv/etnaviv_gem.c index 5a634594a6ce..57881167ccd2 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_gem.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_gem.c @@ -551,12 +551,15 @@ static const struct etnaviv_gem_ops etnaviv_gem_shmem_ops = { void etnaviv_gem_free_object(struct drm_gem_object *obj) { struct etnaviv_gem_object *etnaviv_obj = to_etnaviv_bo(obj); + struct etnaviv_drm_private *priv = obj->dev->dev_private; struct etnaviv_vram_mapping *mapping, *tmp; /* object should not be active */ WARN_ON(is_active(etnaviv_obj)); + mutex_lock(&priv->gem_lock); list_del(&etnaviv_obj->gem_node); + mutex_unlock(&priv->gem_lock); list_for_each_entry_safe(mapping, tmp, &etnaviv_obj->vram_list, obj_node) { diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c b/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c index a7ff2e4c00d2..46dfe0737f43 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c @@ -37,7 +37,7 @@ static struct etnaviv_gem_submit *submit_create(struct drm_device *dev, struct etnaviv_gem_submit *submit; size_t sz = size_vstruct(nr, sizeof(submit->bos[0]), sizeof(*submit)); - submit = kmalloc(sz, GFP_TEMPORARY | __GFP_NOWARN | __GFP_NORETRY); + submit = kmalloc(sz, GFP_KERNEL | __GFP_NOWARN | __GFP_NORETRY); if (submit) { submit->dev = dev; submit->gpu = gpu; @@ -445,8 +445,10 @@ int etnaviv_ioctl_gem_submit(struct drm_device *dev, void *data, cmdbuf->user_size = ALIGN(args->stream_size, 8); ret = etnaviv_gpu_submit(gpu, submit, cmdbuf); - if (ret == 0) - cmdbuf = NULL; + if (ret) + goto out; + + cmdbuf = NULL; if (args->flags & ETNA_SUBMIT_FENCE_FD_OUT) { /* diff --git a/drivers/gpu/drm/exynos/exynos5433_drm_decon.c b/drivers/gpu/drm/exynos/exynos5433_drm_decon.c index 730b8d9db187..6be5b53c3b27 100644 --- a/drivers/gpu/drm/exynos/exynos5433_drm_decon.c +++ b/drivers/gpu/drm/exynos/exynos5433_drm_decon.c @@ -14,6 +14,7 @@ #include <linux/clk.h> #include <linux/component.h> #include <linux/iopoll.h> +#include <linux/irq.h> #include <linux/mfd/syscon.h> #include <linux/of_device.h> #include <linux/of_gpio.h> diff --git a/drivers/gpu/drm/exynos/exynos_drm_drv.c b/drivers/gpu/drm/exynos/exynos_drm_drv.c index b1f7299600f0..e651a58c18cf 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_drv.c +++ b/drivers/gpu/drm/exynos/exynos_drm_drv.c @@ -168,23 +168,19 @@ static struct drm_driver exynos_drm_driver = { static int exynos_drm_suspend(struct device *dev) { struct drm_device *drm_dev = dev_get_drvdata(dev); - struct drm_connector *connector; - struct drm_connector_list_iter conn_iter; + struct exynos_drm_private *private = drm_dev->dev_private; if (pm_runtime_suspended(dev) || !drm_dev) return 0; - drm_connector_list_iter_begin(drm_dev, &conn_iter); - drm_for_each_connector_iter(connector, &conn_iter) { - int old_dpms = connector->dpms; - - if (connector->funcs->dpms) - connector->funcs->dpms(connector, DRM_MODE_DPMS_OFF); - - /* Set the old mode back to the connector for resume */ - connector->dpms = old_dpms; + drm_kms_helper_poll_disable(drm_dev); + exynos_drm_fbdev_suspend(drm_dev); + private->suspend_state = drm_atomic_helper_suspend(drm_dev); + if (IS_ERR(private->suspend_state)) { + exynos_drm_fbdev_resume(drm_dev); + drm_kms_helper_poll_enable(drm_dev); + return PTR_ERR(private->suspend_state); } - drm_connector_list_iter_end(&conn_iter); return 0; } @@ -192,22 +188,14 @@ static int exynos_drm_suspend(struct device *dev) static int exynos_drm_resume(struct device *dev) { struct drm_device *drm_dev = dev_get_drvdata(dev); - struct drm_connector *connector; - struct drm_connector_list_iter conn_iter; + struct exynos_drm_private *private = drm_dev->dev_private; if (pm_runtime_suspended(dev) || !drm_dev) return 0; - drm_connector_list_iter_begin(drm_dev, &conn_iter); - drm_for_each_connector_iter(connector, &conn_iter) { - if (connector->funcs->dpms) { - int dpms = connector->dpms; - - connector->dpms = DRM_MODE_DPMS_OFF; - connector->funcs->dpms(connector, dpms); - } - } - drm_connector_list_iter_end(&conn_iter); + drm_atomic_helper_resume(drm_dev, private->suspend_state); + exynos_drm_fbdev_resume(drm_dev); + drm_kms_helper_poll_enable(drm_dev); return 0; } diff --git a/drivers/gpu/drm/exynos/exynos_drm_drv.h b/drivers/gpu/drm/exynos/exynos_drm_drv.h index cf131c2aa23e..f8bae4cb4823 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_drv.h +++ b/drivers/gpu/drm/exynos/exynos_drm_drv.h @@ -202,6 +202,7 @@ struct drm_exynos_file_private { */ struct exynos_drm_private { struct drm_fb_helper *fb_helper; + struct drm_atomic_state *suspend_state; struct device *dma_dev; void *mapping; diff --git a/drivers/gpu/drm/exynos/exynos_drm_fbdev.c b/drivers/gpu/drm/exynos/exynos_drm_fbdev.c index c3a068409b48..dfb66ecf417b 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_fbdev.c +++ b/drivers/gpu/drm/exynos/exynos_drm_fbdev.c @@ -18,6 +18,8 @@ #include <drm/drm_crtc_helper.h> #include <drm/exynos_drm.h> +#include <linux/console.h> + #include "exynos_drm_drv.h" #include "exynos_drm_fb.h" #include "exynos_drm_fbdev.h" @@ -285,3 +287,21 @@ void exynos_drm_output_poll_changed(struct drm_device *dev) drm_fb_helper_hotplug_event(fb_helper); } + +void exynos_drm_fbdev_suspend(struct drm_device *dev) +{ + struct exynos_drm_private *private = dev->dev_private; + + console_lock(); + drm_fb_helper_set_suspend(private->fb_helper, 1); + console_unlock(); +} + +void exynos_drm_fbdev_resume(struct drm_device *dev) +{ + struct exynos_drm_private *private = dev->dev_private; + + console_lock(); + drm_fb_helper_set_suspend(private->fb_helper, 0); + console_unlock(); +} diff --git a/drivers/gpu/drm/exynos/exynos_drm_fbdev.h b/drivers/gpu/drm/exynos/exynos_drm_fbdev.h index 330eef87f718..645d1bb7f665 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_fbdev.h +++ b/drivers/gpu/drm/exynos/exynos_drm_fbdev.h @@ -21,6 +21,8 @@ int exynos_drm_fbdev_init(struct drm_device *dev); void exynos_drm_fbdev_fini(struct drm_device *dev); void exynos_drm_fbdev_restore_mode(struct drm_device *dev); void exynos_drm_output_poll_changed(struct drm_device *dev); +void exynos_drm_fbdev_suspend(struct drm_device *drm); +void exynos_drm_fbdev_resume(struct drm_device *drm); #else @@ -39,6 +41,14 @@ static inline void exynos_drm_fbdev_restore_mode(struct drm_device *dev) #define exynos_drm_output_poll_changed (NULL) +static inline void exynos_drm_fbdev_suspend(struct drm_device *drm) +{ +} + +static inline void exynos_drm_fbdev_resume(struct drm_device *drm) +{ +} + #endif #endif diff --git a/drivers/gpu/drm/exynos/exynos_hdmi.c b/drivers/gpu/drm/exynos/exynos_hdmi.c index 214fa5e51963..0109ff40b1db 100644 --- a/drivers/gpu/drm/exynos/exynos_hdmi.c +++ b/drivers/gpu/drm/exynos/exynos_hdmi.c @@ -944,22 +944,27 @@ static bool hdmi_mode_fixup(struct drm_encoder *encoder, struct drm_device *dev = encoder->dev; struct drm_connector *connector; struct drm_display_mode *m; + struct drm_connector_list_iter conn_iter; int mode_ok; drm_mode_set_crtcinfo(adjusted_mode, 0); - list_for_each_entry(connector, &dev->mode_config.connector_list, head) { + drm_connector_list_iter_begin(dev, &conn_iter); + drm_for_each_connector_iter(connector, &conn_iter) { if (connector->encoder == encoder) break; } + if (connector) + drm_connector_get(connector); + drm_connector_list_iter_end(&conn_iter); - if (connector->encoder != encoder) + if (!connector) return true; mode_ok = hdmi_mode_valid(connector, adjusted_mode); if (mode_ok == MODE_OK) - return true; + goto cleanup; /* * Find the most suitable mode and copy it to adjusted_mode. @@ -979,6 +984,9 @@ static bool hdmi_mode_fixup(struct drm_encoder *encoder, } } +cleanup: + drm_connector_put(connector); + return true; } diff --git a/drivers/gpu/drm/gma500/tc35876x-dsi-lvds.c b/drivers/gpu/drm/gma500/tc35876x-dsi-lvds.c index 771ff66711af..37c997e24b9e 100644 --- a/drivers/gpu/drm/gma500/tc35876x-dsi-lvds.c +++ b/drivers/gpu/drm/gma500/tc35876x-dsi-lvds.c @@ -26,7 +26,7 @@ #include "mdfld_output.h" #include "mdfld_dsi_pkg_sender.h" #include "tc35876x-dsi-lvds.h" -#include <linux/i2c/tc35876x.h> +#include <linux/platform_data/tc35876x.h> #include <linux/kernel.h> #include <linux/module.h> #include <asm/intel_scu_ipc.h> diff --git a/drivers/gpu/drm/i915/gvt/cfg_space.c b/drivers/gpu/drm/i915/gvt/cfg_space.c index 40af17ec6312..ff3154fe6588 100644 --- a/drivers/gpu/drm/i915/gvt/cfg_space.c +++ b/drivers/gpu/drm/i915/gvt/cfg_space.c @@ -197,78 +197,65 @@ static int emulate_pci_command_write(struct intel_vgpu *vgpu, static int emulate_pci_bar_write(struct intel_vgpu *vgpu, unsigned int offset, void *p_data, unsigned int bytes) { - unsigned int bar_index = - (rounddown(offset, 8) % PCI_BASE_ADDRESS_0) / 8; u32 new = *(u32 *)(p_data); bool lo = IS_ALIGNED(offset, 8); u64 size; int ret = 0; bool mmio_enabled = vgpu_cfg_space(vgpu)[PCI_COMMAND] & PCI_COMMAND_MEMORY; + struct intel_vgpu_pci_bar *bars = vgpu->cfg_space.bar; - if (WARN_ON(bar_index >= INTEL_GVT_PCI_BAR_MAX)) - return -EINVAL; - + /* + * Power-up software can determine how much address + * space the device requires by writing a value of + * all 1's to the register and then reading the value + * back. The device will return 0's in all don't-care + * address bits. + */ if (new == 0xffffffff) { - /* - * Power-up software can determine how much address - * space the device requires by writing a value of - * all 1's to the register and then reading the value - * back. The device will return 0's in all don't-care - * address bits. - */ - size = vgpu->cfg_space.bar[bar_index].size; - if (lo) { - new = rounddown(new, size); - } else { - u32 val = vgpu_cfg_space(vgpu)[rounddown(offset, 8)]; - /* for 32bit mode bar it returns all-0 in upper 32 - * bit, for 64bit mode bar it will calculate the - * size with lower 32bit and return the corresponding - * value + switch (offset) { + case PCI_BASE_ADDRESS_0: + case PCI_BASE_ADDRESS_1: + size = ~(bars[INTEL_GVT_PCI_BAR_GTTMMIO].size -1); + intel_vgpu_write_pci_bar(vgpu, offset, + size >> (lo ? 0 : 32), lo); + /* + * Untrap the BAR, since guest hasn't configured a + * valid GPA */ - if (val & PCI_BASE_ADDRESS_MEM_TYPE_64) - new &= (~(size-1)) >> 32; - else - new = 0; - } - /* - * Unmapp & untrap the BAR, since guest hasn't configured a - * valid GPA - */ - switch (bar_index) { - case INTEL_GVT_PCI_BAR_GTTMMIO: ret = trap_gttmmio(vgpu, false); break; - case INTEL_GVT_PCI_BAR_APERTURE: + case PCI_BASE_ADDRESS_2: + case PCI_BASE_ADDRESS_3: + size = ~(bars[INTEL_GVT_PCI_BAR_APERTURE].size -1); + intel_vgpu_write_pci_bar(vgpu, offset, + size >> (lo ? 0 : 32), lo); ret = map_aperture(vgpu, false); break; + default: + /* Unimplemented BARs */ + intel_vgpu_write_pci_bar(vgpu, offset, 0x0, false); } - intel_vgpu_write_pci_bar(vgpu, offset, new, lo); } else { - /* - * Unmapp & untrap the old BAR first, since guest has - * re-configured the BAR - */ - switch (bar_index) { - case INTEL_GVT_PCI_BAR_GTTMMIO: - ret = trap_gttmmio(vgpu, false); + switch (offset) { + case PCI_BASE_ADDRESS_0: + case PCI_BASE_ADDRESS_1: + /* + * Untrap the old BAR first, since guest has + * re-configured the BAR + */ + trap_gttmmio(vgpu, false); + intel_vgpu_write_pci_bar(vgpu, offset, new, lo); + ret = trap_gttmmio(vgpu, mmio_enabled); break; - case INTEL_GVT_PCI_BAR_APERTURE: - ret = map_aperture(vgpu, false); + case PCI_BASE_ADDRESS_2: + case PCI_BASE_ADDRESS_3: + map_aperture(vgpu, false); + intel_vgpu_write_pci_bar(vgpu, offset, new, lo); + ret = map_aperture(vgpu, mmio_enabled); break; - } - intel_vgpu_write_pci_bar(vgpu, offset, new, lo); - /* Track the new BAR */ - if (mmio_enabled) { - switch (bar_index) { - case INTEL_GVT_PCI_BAR_GTTMMIO: - ret = trap_gttmmio(vgpu, true); - break; - case INTEL_GVT_PCI_BAR_APERTURE: - ret = map_aperture(vgpu, true); - break; - } + default: + intel_vgpu_write_pci_bar(vgpu, offset, new, lo); } } return ret; @@ -299,10 +286,7 @@ int intel_vgpu_emulate_cfg_write(struct intel_vgpu *vgpu, unsigned int offset, } switch (rounddown(offset, 4)) { - case PCI_BASE_ADDRESS_0: - case PCI_BASE_ADDRESS_1: - case PCI_BASE_ADDRESS_2: - case PCI_BASE_ADDRESS_3: + case PCI_BASE_ADDRESS_0 ... PCI_BASE_ADDRESS_5: if (WARN_ON(!IS_ALIGNED(offset, 4))) return -EINVAL; return emulate_pci_bar_write(vgpu, offset, p_data, bytes); @@ -344,7 +328,6 @@ void intel_vgpu_init_cfg_space(struct intel_vgpu *vgpu, struct intel_gvt *gvt = vgpu->gvt; const struct intel_gvt_device_info *info = &gvt->device_info; u16 *gmch_ctl; - int i; memcpy(vgpu_cfg_space(vgpu), gvt->firmware.cfg_space, info->cfg_space_size); @@ -371,13 +354,13 @@ void intel_vgpu_init_cfg_space(struct intel_vgpu *vgpu, */ memset(vgpu_cfg_space(vgpu) + PCI_BASE_ADDRESS_1, 0, 4); memset(vgpu_cfg_space(vgpu) + PCI_BASE_ADDRESS_3, 0, 4); + memset(vgpu_cfg_space(vgpu) + PCI_BASE_ADDRESS_4, 0, 8); memset(vgpu_cfg_space(vgpu) + INTEL_GVT_PCI_OPREGION, 0, 4); - for (i = 0; i < INTEL_GVT_MAX_BAR_NUM; i++) { - vgpu->cfg_space.bar[i].size = pci_resource_len( - gvt->dev_priv->drm.pdev, i * 2); - vgpu->cfg_space.bar[i].tracked = false; - } + vgpu->cfg_space.bar[INTEL_GVT_PCI_BAR_GTTMMIO].size = + pci_resource_len(gvt->dev_priv->drm.pdev, 0); + vgpu->cfg_space.bar[INTEL_GVT_PCI_BAR_APERTURE].size = + pci_resource_len(gvt->dev_priv->drm.pdev, 2); } /** diff --git a/drivers/gpu/drm/i915/gvt/handlers.c b/drivers/gpu/drm/i915/gvt/handlers.c index 3502a59166ff..2294466dd415 100644 --- a/drivers/gpu/drm/i915/gvt/handlers.c +++ b/drivers/gpu/drm/i915/gvt/handlers.c @@ -2659,7 +2659,6 @@ static int init_skl_mmio_info(struct intel_gvt *gvt) MMIO_D(HSW_PWR_WELL_CTL_BIOS(SKL_DISP_PW_MISC_IO), D_SKL_PLUS); MMIO_DH(HSW_PWR_WELL_CTL_DRIVER(SKL_DISP_PW_MISC_IO), D_SKL_PLUS, NULL, skl_power_well_ctl_write); - MMIO_DH(GEN6_PCODE_MAILBOX, D_SKL_PLUS, NULL, mailbox_write); MMIO_D(0xa210, D_SKL_PLUS); MMIO_D(GEN9_MEDIA_PG_IDLE_HYSTERESIS, D_SKL_PLUS); diff --git a/drivers/gpu/drm/i915/i915_cmd_parser.c b/drivers/gpu/drm/i915/i915_cmd_parser.c index f0cb22cc0dd6..8ba932b22f7c 100644 --- a/drivers/gpu/drm/i915/i915_cmd_parser.c +++ b/drivers/gpu/drm/i915/i915_cmd_parser.c @@ -1073,7 +1073,7 @@ static u32 *copy_batch(struct drm_i915_gem_object *dst_obj, goto unpin_src; } - dst = i915_gem_object_pin_map(dst_obj, I915_MAP_WB); + dst = i915_gem_object_pin_map(dst_obj, I915_MAP_FORCE_WB); if (IS_ERR(dst)) goto unpin_dst; diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c index a36216bd2a84..e4d4b6b41e26 100644 --- a/drivers/gpu/drm/i915/i915_debugfs.c +++ b/drivers/gpu/drm/i915/i915_debugfs.c @@ -4308,10 +4308,10 @@ i915_drop_caches_set(void *data, u64 val) fs_reclaim_acquire(GFP_KERNEL); if (val & DROP_BOUND) - i915_gem_shrink(dev_priv, LONG_MAX, I915_SHRINK_BOUND); + i915_gem_shrink(dev_priv, LONG_MAX, NULL, I915_SHRINK_BOUND); if (val & DROP_UNBOUND) - i915_gem_shrink(dev_priv, LONG_MAX, I915_SHRINK_UNBOUND); + i915_gem_shrink(dev_priv, LONG_MAX, NULL, I915_SHRINK_UNBOUND); if (val & DROP_SHRINK_ALL) i915_gem_shrink_all(dev_priv); diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c index 43100229613c..9f45cfeae775 100644 --- a/drivers/gpu/drm/i915/i915_drv.c +++ b/drivers/gpu/drm/i915/i915_drv.c @@ -1891,9 +1891,15 @@ void i915_reset(struct drm_i915_private *i915, unsigned int flags) /* * Everything depends on having the GTT running, so we need to start - * there. Fortunately we don't need to do this unless we reset the - * chip at a PCI level. - * + * there. + */ + ret = i915_ggtt_enable_hw(i915); + if (ret) { + DRM_ERROR("Failed to re-enable GGTT following reset %d\n", ret); + goto error; + } + + /* * Next we need to restore the context, but we don't use those * yet either... * diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index 60267e375e88..18d9da53282b 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -3479,6 +3479,9 @@ void __i915_gem_object_invalidate(struct drm_i915_gem_object *obj); enum i915_map_type { I915_MAP_WB = 0, I915_MAP_WC, +#define I915_MAP_OVERRIDE BIT(31) + I915_MAP_FORCE_WB = I915_MAP_WB | I915_MAP_OVERRIDE, + I915_MAP_FORCE_WC = I915_MAP_WC | I915_MAP_OVERRIDE, }; /** @@ -3742,6 +3745,7 @@ i915_gem_object_create_internal(struct drm_i915_private *dev_priv, /* i915_gem_shrinker.c */ unsigned long i915_gem_shrink(struct drm_i915_private *dev_priv, unsigned long target, + unsigned long *nr_scanned, unsigned flags); #define I915_SHRINK_PURGEABLE 0x1 #define I915_SHRINK_UNBOUND 0x2 diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index b9e8e0d6e97b..19404c96eeb1 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -695,12 +695,11 @@ flush_write_domain(struct drm_i915_gem_object *obj, unsigned int flush_domains) switch (obj->base.write_domain) { case I915_GEM_DOMAIN_GTT: if (INTEL_GEN(dev_priv) >= 6 && !HAS_LLC(dev_priv)) { - if (intel_runtime_pm_get_if_in_use(dev_priv)) { - spin_lock_irq(&dev_priv->uncore.lock); - POSTING_READ_FW(RING_ACTHD(dev_priv->engine[RCS]->mmio_base)); - spin_unlock_irq(&dev_priv->uncore.lock); - intel_runtime_pm_put(dev_priv); - } + intel_runtime_pm_get(dev_priv); + spin_lock_irq(&dev_priv->uncore.lock); + POSTING_READ_FW(RING_ACTHD(dev_priv->engine[RCS]->mmio_base)); + spin_unlock_irq(&dev_priv->uncore.lock); + intel_runtime_pm_put(dev_priv); } intel_fb_obj_flush(obj, @@ -2213,7 +2212,7 @@ i915_gem_object_put_pages_gtt(struct drm_i915_gem_object *obj, static void __i915_gem_object_reset_page_iter(struct drm_i915_gem_object *obj) { struct radix_tree_iter iter; - void **slot; + void __rcu **slot; radix_tree_for_each_slot(slot, &obj->mm.get_page.radix, &iter, 0) radix_tree_delete(&obj->mm.get_page.radix, iter.index); @@ -2354,7 +2353,7 @@ rebuild_st: goto err_sg; } - i915_gem_shrink(dev_priv, 2 * page_count, *s++); + i915_gem_shrink(dev_priv, 2 * page_count, NULL, *s++); cond_resched(); /* We've tried hard to allocate the memory by reaping @@ -2541,7 +2540,7 @@ static void *i915_gem_object_map(const struct drm_i915_gem_object *obj, if (n_pages > ARRAY_SIZE(stack_pages)) { /* Too big for stack -- allocate temporary array instead */ - pages = kvmalloc_array(n_pages, sizeof(*pages), GFP_TEMPORARY); + pages = kvmalloc_array(n_pages, sizeof(*pages), GFP_KERNEL); if (!pages) return NULL; } @@ -2553,6 +2552,9 @@ static void *i915_gem_object_map(const struct drm_i915_gem_object *obj, GEM_BUG_ON(i != n_pages); switch (type) { + default: + MISSING_CASE(type); + /* fallthrough to use PAGE_KERNEL anyway */ case I915_MAP_WB: pgprot = PAGE_KERNEL; break; @@ -2583,7 +2585,9 @@ void *i915_gem_object_pin_map(struct drm_i915_gem_object *obj, if (ret) return ERR_PTR(ret); - pinned = true; + pinned = !(type & I915_MAP_OVERRIDE); + type &= ~I915_MAP_OVERRIDE; + if (!atomic_inc_not_zero(&obj->mm.pages_pin_count)) { if (unlikely(IS_ERR_OR_NULL(obj->mm.pages))) { ret = ____i915_gem_object_get_pages(obj); @@ -3258,7 +3262,13 @@ void i915_gem_close_object(struct drm_gem_object *gem, struct drm_file *file) vma = radix_tree_delete(&ctx->handles_vma, lut->handle); - if (!i915_vma_is_ggtt(vma)) + GEM_BUG_ON(vma->obj != obj); + + /* We allow the process to have multiple handles to the same + * vma, in the same fd namespace, by virtue of flink/open. + */ + GEM_BUG_ON(!vma->open_count); + if (!--vma->open_count && !i915_vma_is_ggtt(vma)) i915_vma_close(vma); list_del(&lut->obj_link); @@ -5015,7 +5025,7 @@ int i915_gem_freeze_late(struct drm_i915_private *dev_priv) * the objects as well, see i915_gem_freeze() */ - i915_gem_shrink(dev_priv, -1UL, I915_SHRINK_UNBOUND); + i915_gem_shrink(dev_priv, -1UL, NULL, I915_SHRINK_UNBOUND); i915_gem_drain_freed_objects(dev_priv); mutex_lock(&dev_priv->drm.struct_mutex); diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c index 4c2016237d61..92437f455b43 100644 --- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c @@ -285,7 +285,7 @@ static int eb_create(struct i915_execbuffer *eb) * direct lookup. */ do { - unsigned int flags; + gfp_t flags; /* While we can still reduce the allocation size, don't * raise a warning and allow the allocation to fail. @@ -293,7 +293,7 @@ static int eb_create(struct i915_execbuffer *eb) * as possible to perform the allocation and warn * if it fails. */ - flags = GFP_TEMPORARY; + flags = GFP_KERNEL; if (size > 1) flags |= __GFP_NORETRY | __GFP_NOWARN; @@ -720,6 +720,7 @@ static int eb_lookup_vmas(struct i915_execbuffer *eb) goto err_obj; } + vma->open_count++; list_add(&lut->obj_link, &obj->lut_list); list_add(&lut->ctx_link, &eb->ctx->handles_list); lut->ctx = eb->ctx; @@ -1070,7 +1071,9 @@ static int __reloc_gpu_alloc(struct i915_execbuffer *eb, return PTR_ERR(obj); cmd = i915_gem_object_pin_map(obj, - cache->has_llc ? I915_MAP_WB : I915_MAP_WC); + cache->has_llc ? + I915_MAP_FORCE_WB : + I915_MAP_FORCE_WC); i915_gem_object_unpin_pages(obj); if (IS_ERR(cmd)) return PTR_ERR(cmd); @@ -1512,7 +1515,7 @@ static int eb_copy_relocations(const struct i915_execbuffer *eb) urelocs = u64_to_user_ptr(eb->exec[i].relocs_ptr); size = nreloc * sizeof(*relocs); - relocs = kvmalloc_array(size, 1, GFP_TEMPORARY); + relocs = kvmalloc_array(size, 1, GFP_KERNEL); if (!relocs) { kvfree(relocs); err = -ENOMEM; @@ -1526,7 +1529,7 @@ static int eb_copy_relocations(const struct i915_execbuffer *eb) min_t(u64, BIT_ULL(31), size - copied); if (__copy_from_user((char *)relocs + copied, - (char *)urelocs + copied, + (char __user *)urelocs + copied, len)) { kvfree(relocs); err = -EFAULT; @@ -2074,7 +2077,7 @@ get_fence_array(struct drm_i915_gem_execbuffer2 *args, return ERR_PTR(-EFAULT); fences = kvmalloc_array(args->num_cliprects, sizeof(*fences), - __GFP_NOWARN | GFP_TEMPORARY); + __GFP_NOWARN | GFP_KERNEL); if (!fences) return ERR_PTR(-ENOMEM); @@ -2460,9 +2463,9 @@ i915_gem_execbuffer(struct drm_device *dev, void *data, /* Copy in the exec list from userland */ exec_list = kvmalloc_array(args->buffer_count, sizeof(*exec_list), - __GFP_NOWARN | GFP_TEMPORARY); + __GFP_NOWARN | GFP_KERNEL); exec2_list = kvmalloc_array(args->buffer_count + 1, sz, - __GFP_NOWARN | GFP_TEMPORARY); + __GFP_NOWARN | GFP_KERNEL); if (exec_list == NULL || exec2_list == NULL) { DRM_DEBUG("Failed to allocate exec list for %d buffers\n", args->buffer_count); @@ -2540,7 +2543,7 @@ i915_gem_execbuffer2(struct drm_device *dev, void *data, /* Allocate an extra slot for use by the command parser */ exec2_list = kvmalloc_array(args->buffer_count + 1, sz, - __GFP_NOWARN | GFP_TEMPORARY); + __GFP_NOWARN | GFP_KERNEL); if (exec2_list == NULL) { DRM_DEBUG("Failed to allocate exec list for %d buffers\n", args->buffer_count); diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c index d60f38adc4c4..e2410eb5d96e 100644 --- a/drivers/gpu/drm/i915/i915_gem_gtt.c +++ b/drivers/gpu/drm/i915/i915_gem_gtt.c @@ -2062,7 +2062,7 @@ int i915_gem_gtt_prepare_pages(struct drm_i915_gem_object *obj, */ GEM_BUG_ON(obj->mm.pages == pages); } while (i915_gem_shrink(to_i915(obj->base.dev), - obj->base.size >> PAGE_SHIFT, + obj->base.size >> PAGE_SHIFT, NULL, I915_SHRINK_BOUND | I915_SHRINK_UNBOUND | I915_SHRINK_ACTIVE)); @@ -2754,10 +2754,10 @@ static void cnl_setup_private_ppat(struct drm_i915_private *dev_priv) I915_WRITE(GEN10_PAT_INDEX(1), GEN8_PPAT_WC | GEN8_PPAT_LLCELLC); I915_WRITE(GEN10_PAT_INDEX(2), GEN8_PPAT_WT | GEN8_PPAT_LLCELLC); I915_WRITE(GEN10_PAT_INDEX(3), GEN8_PPAT_UC); - I915_WRITE(GEN10_PAT_INDEX(4), GEN8_PPAT_LLCELLC | GEN8_PPAT_AGE(0)); - I915_WRITE(GEN10_PAT_INDEX(5), GEN8_PPAT_LLCELLC | GEN8_PPAT_AGE(1)); - I915_WRITE(GEN10_PAT_INDEX(6), GEN8_PPAT_LLCELLC | GEN8_PPAT_AGE(2)); - I915_WRITE(GEN10_PAT_INDEX(7), GEN8_PPAT_LLCELLC | GEN8_PPAT_AGE(3)); + I915_WRITE(GEN10_PAT_INDEX(4), GEN8_PPAT_WB | GEN8_PPAT_LLCELLC | GEN8_PPAT_AGE(0)); + I915_WRITE(GEN10_PAT_INDEX(5), GEN8_PPAT_WB | GEN8_PPAT_LLCELLC | GEN8_PPAT_AGE(1)); + I915_WRITE(GEN10_PAT_INDEX(6), GEN8_PPAT_WB | GEN8_PPAT_LLCELLC | GEN8_PPAT_AGE(2)); + I915_WRITE(GEN10_PAT_INDEX(7), GEN8_PPAT_WB | GEN8_PPAT_LLCELLC | GEN8_PPAT_AGE(3)); } /* The GGTT and PPGTT need a private PPAT setup in order to handle cacheability @@ -3231,7 +3231,7 @@ intel_rotate_pages(struct intel_rotation_info *rot_info, /* Allocate a temporary list of source pages for random access. */ page_addr_list = kvmalloc_array(n_pages, sizeof(dma_addr_t), - GFP_TEMPORARY); + GFP_KERNEL); if (!page_addr_list) return ERR_PTR(ret); diff --git a/drivers/gpu/drm/i915/i915_gem_shrinker.c b/drivers/gpu/drm/i915/i915_gem_shrinker.c index 77fb39808131..74002b2d1b6f 100644 --- a/drivers/gpu/drm/i915/i915_gem_shrinker.c +++ b/drivers/gpu/drm/i915/i915_gem_shrinker.c @@ -136,6 +136,7 @@ static bool unsafe_drop_pages(struct drm_i915_gem_object *obj) * i915_gem_shrink - Shrink buffer object caches * @dev_priv: i915 device * @target: amount of memory to make available, in pages + * @nr_scanned: optional output for number of pages scanned (incremental) * @flags: control flags for selecting cache types * * This function is the main interface to the shrinker. It will try to release @@ -158,7 +159,9 @@ static bool unsafe_drop_pages(struct drm_i915_gem_object *obj) */ unsigned long i915_gem_shrink(struct drm_i915_private *dev_priv, - unsigned long target, unsigned flags) + unsigned long target, + unsigned long *nr_scanned, + unsigned flags) { const struct { struct list_head *list; @@ -169,6 +172,7 @@ i915_gem_shrink(struct drm_i915_private *dev_priv, { NULL, 0 }, }, *phase; unsigned long count = 0; + unsigned long scanned = 0; bool unlock; if (!shrinker_lock(dev_priv, &unlock)) @@ -249,6 +253,7 @@ i915_gem_shrink(struct drm_i915_private *dev_priv, count += obj->base.size >> PAGE_SHIFT; } mutex_unlock(&obj->mm.lock); + scanned += obj->base.size >> PAGE_SHIFT; } } list_splice_tail(&still_in_list, phase->list); @@ -261,6 +266,8 @@ i915_gem_shrink(struct drm_i915_private *dev_priv, shrinker_unlock(dev_priv, unlock); + if (nr_scanned) + *nr_scanned += scanned; return count; } @@ -283,7 +290,7 @@ unsigned long i915_gem_shrink_all(struct drm_i915_private *dev_priv) unsigned long freed; intel_runtime_pm_get(dev_priv); - freed = i915_gem_shrink(dev_priv, -1UL, + freed = i915_gem_shrink(dev_priv, -1UL, NULL, I915_SHRINK_BOUND | I915_SHRINK_UNBOUND | I915_SHRINK_ACTIVE); @@ -329,23 +336,28 @@ i915_gem_shrinker_scan(struct shrinker *shrinker, struct shrink_control *sc) unsigned long freed; bool unlock; + sc->nr_scanned = 0; + if (!shrinker_lock(dev_priv, &unlock)) return SHRINK_STOP; freed = i915_gem_shrink(dev_priv, sc->nr_to_scan, + &sc->nr_scanned, I915_SHRINK_BOUND | I915_SHRINK_UNBOUND | I915_SHRINK_PURGEABLE); if (freed < sc->nr_to_scan) freed += i915_gem_shrink(dev_priv, - sc->nr_to_scan - freed, + sc->nr_to_scan - sc->nr_scanned, + &sc->nr_scanned, I915_SHRINK_BOUND | I915_SHRINK_UNBOUND); if (freed < sc->nr_to_scan && current_is_kswapd()) { intel_runtime_pm_get(dev_priv); freed += i915_gem_shrink(dev_priv, - sc->nr_to_scan - freed, + sc->nr_to_scan - sc->nr_scanned, + &sc->nr_scanned, I915_SHRINK_ACTIVE | I915_SHRINK_BOUND | I915_SHRINK_UNBOUND); @@ -354,7 +366,7 @@ i915_gem_shrinker_scan(struct shrinker *shrinker, struct shrink_control *sc) shrinker_unlock(dev_priv, unlock); - return freed; + return sc->nr_scanned ? freed : SHRINK_STOP; } static bool @@ -453,7 +465,7 @@ i915_gem_shrinker_vmap(struct notifier_block *nb, unsigned long event, void *ptr goto out; intel_runtime_pm_get(dev_priv); - freed_pages += i915_gem_shrink(dev_priv, -1UL, + freed_pages += i915_gem_shrink(dev_priv, -1UL, NULL, I915_SHRINK_BOUND | I915_SHRINK_UNBOUND | I915_SHRINK_ACTIVE | diff --git a/drivers/gpu/drm/i915/i915_gem_userptr.c b/drivers/gpu/drm/i915/i915_gem_userptr.c index f152a38d7079..709efe2357ea 100644 --- a/drivers/gpu/drm/i915/i915_gem_userptr.c +++ b/drivers/gpu/drm/i915/i915_gem_userptr.c @@ -49,7 +49,7 @@ struct i915_mmu_notifier { spinlock_t lock; struct hlist_node node; struct mmu_notifier mn; - struct rb_root objects; + struct rb_root_cached objects; struct workqueue_struct *wq; }; @@ -123,7 +123,7 @@ static void i915_gem_userptr_mn_invalidate_range_start(struct mmu_notifier *_mn, struct interval_tree_node *it; LIST_HEAD(cancelled); - if (RB_EMPTY_ROOT(&mn->objects)) + if (RB_EMPTY_ROOT(&mn->objects.rb_root)) return; /* interval ranges are inclusive, but invalidate range is exclusive */ @@ -172,7 +172,7 @@ i915_mmu_notifier_create(struct mm_struct *mm) spin_lock_init(&mn->lock); mn->mn.ops = &i915_gem_userptr_notifier; - mn->objects = RB_ROOT; + mn->objects = RB_ROOT_CACHED; mn->wq = alloc_workqueue("i915-userptr-release", WQ_UNBOUND, 0); if (mn->wq == NULL) { kfree(mn); @@ -507,7 +507,7 @@ __i915_gem_userptr_get_pages_worker(struct work_struct *_work) ret = -ENOMEM; pinned = 0; - pvec = kvmalloc_array(npages, sizeof(struct page *), GFP_TEMPORARY); + pvec = kvmalloc_array(npages, sizeof(struct page *), GFP_KERNEL); if (pvec != NULL) { struct mm_struct *mm = obj->userptr.mm->mm; unsigned int flags = 0; @@ -643,7 +643,7 @@ i915_gem_userptr_get_pages(struct drm_i915_gem_object *obj) if (mm == current->mm) { pvec = kvmalloc_array(num_pages, sizeof(struct page *), - GFP_TEMPORARY | + GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN); if (pvec) /* defer to worker if malloc fails */ diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c index ed5a1eb839ad..0c779671fe2d 100644 --- a/drivers/gpu/drm/i915/i915_gpu_error.c +++ b/drivers/gpu/drm/i915/i915_gpu_error.c @@ -787,16 +787,16 @@ int i915_error_state_buf_init(struct drm_i915_error_state_buf *ebuf, */ ebuf->size = count + 1 > PAGE_SIZE ? count + 1 : PAGE_SIZE; ebuf->buf = kmalloc(ebuf->size, - GFP_TEMPORARY | __GFP_NORETRY | __GFP_NOWARN); + GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN); if (ebuf->buf == NULL) { ebuf->size = PAGE_SIZE; - ebuf->buf = kmalloc(ebuf->size, GFP_TEMPORARY); + ebuf->buf = kmalloc(ebuf->size, GFP_KERNEL); } if (ebuf->buf == NULL) { ebuf->size = 128; - ebuf->buf = kmalloc(ebuf->size, GFP_TEMPORARY); + ebuf->buf = kmalloc(ebuf->size, GFP_KERNEL); } if (ebuf->buf == NULL) diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c index e21ce9c18b6e..b63893eeca73 100644 --- a/drivers/gpu/drm/i915/i915_irq.c +++ b/drivers/gpu/drm/i915/i915_irq.c @@ -839,7 +839,6 @@ static bool i915_get_crtc_scanoutpos(struct drm_device *dev, unsigned int pipe, pipe); int position; int vbl_start, vbl_end, hsync_start, htotal, vtotal; - bool in_vbl = true; unsigned long irqflags; if (WARN_ON(!mode->crtc_clock)) { @@ -922,8 +921,6 @@ static bool i915_get_crtc_scanoutpos(struct drm_device *dev, unsigned int pipe, spin_unlock_irqrestore(&dev_priv->uncore.lock, irqflags); - in_vbl = position >= vbl_start && position < vbl_end; - /* * While in vblank, position will be negative * counting up towards 0 at vbl_end. And outside diff --git a/drivers/gpu/drm/i915/i915_trace.h b/drivers/gpu/drm/i915/i915_trace.h index b24a83d43559..6fd5c57e21f6 100644 --- a/drivers/gpu/drm/i915/i915_trace.h +++ b/drivers/gpu/drm/i915/i915_trace.h @@ -38,7 +38,7 @@ TRACE_EVENT(intel_cpu_fifo_underrun, ); TRACE_EVENT(intel_pch_fifo_underrun, - TP_PROTO(struct drm_i915_private *dev_priv, enum transcoder pch_transcoder), + TP_PROTO(struct drm_i915_private *dev_priv, enum pipe pch_transcoder), TP_ARGS(dev_priv, pch_transcoder), TP_STRUCT__entry( @@ -48,7 +48,7 @@ TRACE_EVENT(intel_pch_fifo_underrun, ), TP_fast_assign( - enum pipe pipe = (enum pipe)pch_transcoder; + enum pipe pipe = pch_transcoder; __entry->pipe = pipe; __entry->frame = dev_priv->drm.driver->get_vblank_counter(&dev_priv->drm, pipe); __entry->scanline = intel_get_crtc_scanline(intel_get_crtc_for_pipe(dev_priv, pipe)); diff --git a/drivers/gpu/drm/i915/i915_vma.h b/drivers/gpu/drm/i915/i915_vma.h index 1fd61e88cfd0..e811067c7724 100644 --- a/drivers/gpu/drm/i915/i915_vma.h +++ b/drivers/gpu/drm/i915/i915_vma.h @@ -59,6 +59,12 @@ struct i915_vma { u32 fence_size; u32 fence_alignment; + /** + * Count of the number of times this vma has been opened by different + * handles (but same file) for execbuf, i.e. the number of aliases + * that exist in the ctx->handle_vmas LUT for this vma. + */ + unsigned int open_count; unsigned int flags; /** * How many users have pinned this object in GTT space. The following diff --git a/drivers/gpu/drm/i915/intel_audio.c b/drivers/gpu/drm/i915/intel_audio.c index d805b6e6fe71..27743be5b768 100644 --- a/drivers/gpu/drm/i915/intel_audio.c +++ b/drivers/gpu/drm/i915/intel_audio.c @@ -606,11 +606,6 @@ void intel_audio_codec_enable(struct intel_encoder *intel_encoder, connector->encoder->base.id, connector->encoder->name); - /* ELD Conn_Type */ - connector->eld[5] &= ~(3 << 2); - if (intel_crtc_has_dp_encoder(crtc_state)) - connector->eld[5] |= (1 << 2); - connector->eld[6] = drm_av_sync_delay(connector, adjusted_mode) / 2; if (dev_priv->display.audio_codec_enable) diff --git a/drivers/gpu/drm/i915/intel_bios.c b/drivers/gpu/drm/i915/intel_bios.c index 183e87e8ea31..00c6aee0a9a1 100644 --- a/drivers/gpu/drm/i915/intel_bios.c +++ b/drivers/gpu/drm/i915/intel_bios.c @@ -1163,6 +1163,13 @@ static void parse_ddi_port(struct drm_i915_private *dev_priv, enum port port, is_hdmi = is_dvi && (child->common.device_type & DEVICE_TYPE_NOT_HDMI_OUTPUT) == 0; is_edp = is_dp && (child->common.device_type & DEVICE_TYPE_INTERNAL_CONNECTOR); + if (port == PORT_A && is_dvi) { + DRM_DEBUG_KMS("VBT claims port A supports DVI%s, ignoring\n", + is_hdmi ? "/HDMI" : ""); + is_dvi = false; + is_hdmi = false; + } + info->supports_dvi = is_dvi; info->supports_hdmi = is_hdmi; info->supports_dp = is_dp; diff --git a/drivers/gpu/drm/i915/intel_color.c b/drivers/gpu/drm/i915/intel_color.c index 8e4e829682b9..ff9ecd211abb 100644 --- a/drivers/gpu/drm/i915/intel_color.c +++ b/drivers/gpu/drm/i915/intel_color.c @@ -107,7 +107,7 @@ static void ctm_mult_by_limited(uint64_t *result, int64_t *input) } } -void i9xx_load_ycbcr_conversion_matrix(struct intel_crtc *intel_crtc) +static void i9xx_load_ycbcr_conversion_matrix(struct intel_crtc *intel_crtc) { int pipe = intel_crtc->pipe; struct drm_i915_private *dev_priv = to_i915(intel_crtc->base.dev); diff --git a/drivers/gpu/drm/i915/intel_csr.c b/drivers/gpu/drm/i915/intel_csr.c index 965988f79a55..92c1f8e166dc 100644 --- a/drivers/gpu/drm/i915/intel_csr.c +++ b/drivers/gpu/drm/i915/intel_csr.c @@ -216,7 +216,7 @@ static void gen9_set_dc_state_debugmask(struct drm_i915_private *dev_priv) mask = DC_STATE_DEBUG_MASK_MEMORY_UP; - if (IS_BROXTON(dev_priv)) + if (IS_GEN9_LP(dev_priv)) mask |= DC_STATE_DEBUG_MASK_CORES; /* The below bit doesn't need to be cleared ever afterwards */ diff --git a/drivers/gpu/drm/i915/intel_ddi.c b/drivers/gpu/drm/i915/intel_ddi.c index 4b4fd1f8110b..476681d5940c 100644 --- a/drivers/gpu/drm/i915/intel_ddi.c +++ b/drivers/gpu/drm/i915/intel_ddi.c @@ -1655,7 +1655,8 @@ bool intel_ddi_get_hw_state(struct intel_encoder *encoder, out: if (ret && IS_GEN9_LP(dev_priv)) { tmp = I915_READ(BXT_PHY_CTL(port)); - if ((tmp & (BXT_PHY_LANE_POWERDOWN_ACK | + if ((tmp & (BXT_PHY_CMNLANE_POWERDOWN_ACK | + BXT_PHY_LANE_POWERDOWN_ACK | BXT_PHY_LANE_ENABLED)) != BXT_PHY_LANE_ENABLED) DRM_ERROR("Port %c enabled but PHY powered down? " "(PHY_CTL %08x)\n", port_name(port), tmp); diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index 0e93ec201fe3..64f7b51ed97c 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -2288,17 +2288,13 @@ void intel_add_fb_offsets(int *x, int *y, } } -/* - * Input tile dimensions and pitch must already be - * rotated to match x and y, and in pixel units. - */ -static u32 _intel_adjust_tile_offset(int *x, int *y, - unsigned int tile_width, - unsigned int tile_height, - unsigned int tile_size, - unsigned int pitch_tiles, - u32 old_offset, - u32 new_offset) +static u32 __intel_adjust_tile_offset(int *x, int *y, + unsigned int tile_width, + unsigned int tile_height, + unsigned int tile_size, + unsigned int pitch_tiles, + u32 old_offset, + u32 new_offset) { unsigned int pitch_pixels = pitch_tiles * tile_width; unsigned int tiles; @@ -2319,18 +2315,13 @@ static u32 _intel_adjust_tile_offset(int *x, int *y, return new_offset; } -/* - * Adjust the tile offset by moving the difference into - * the x/y offsets. - */ -static u32 intel_adjust_tile_offset(int *x, int *y, - const struct intel_plane_state *state, int plane, - u32 old_offset, u32 new_offset) +static u32 _intel_adjust_tile_offset(int *x, int *y, + const struct drm_framebuffer *fb, int plane, + unsigned int rotation, + u32 old_offset, u32 new_offset) { - const struct drm_i915_private *dev_priv = to_i915(state->base.plane->dev); - const struct drm_framebuffer *fb = state->base.fb; + const struct drm_i915_private *dev_priv = to_i915(fb->dev); unsigned int cpp = fb->format->cpp[plane]; - unsigned int rotation = state->base.rotation; unsigned int pitch = intel_fb_pitch(fb, plane, rotation); WARN_ON(new_offset > old_offset); @@ -2349,9 +2340,9 @@ static u32 intel_adjust_tile_offset(int *x, int *y, pitch_tiles = pitch / (tile_width * cpp); } - _intel_adjust_tile_offset(x, y, tile_width, tile_height, - tile_size, pitch_tiles, - old_offset, new_offset); + __intel_adjust_tile_offset(x, y, tile_width, tile_height, + tile_size, pitch_tiles, + old_offset, new_offset); } else { old_offset += *y * pitch + *x * cpp; @@ -2363,6 +2354,19 @@ static u32 intel_adjust_tile_offset(int *x, int *y, } /* + * Adjust the tile offset by moving the difference into + * the x/y offsets. + */ +static u32 intel_adjust_tile_offset(int *x, int *y, + const struct intel_plane_state *state, int plane, + u32 old_offset, u32 new_offset) +{ + return _intel_adjust_tile_offset(x, y, state->base.fb, plane, + state->base.rotation, + old_offset, new_offset); +} + +/* * Computes the linear offset to the base tile and adjusts * x, y. bytes per pixel is assumed to be a power-of-two. * @@ -2413,9 +2417,9 @@ static u32 _intel_compute_tile_offset(const struct drm_i915_private *dev_priv, offset = (tile_rows * pitch_tiles + tiles) * tile_size; offset_aligned = offset & ~alignment; - _intel_adjust_tile_offset(x, y, tile_width, tile_height, - tile_size, pitch_tiles, - offset, offset_aligned); + __intel_adjust_tile_offset(x, y, tile_width, tile_height, + tile_size, pitch_tiles, + offset, offset_aligned); } else { offset = *y * pitch + *x * cpp; offset_aligned = offset & ~alignment; @@ -2447,16 +2451,24 @@ u32 intel_compute_tile_offset(int *x, int *y, rotation, alignment); } -/* Convert the fb->offset[] linear offset into x/y offsets */ -static void intel_fb_offset_to_xy(int *x, int *y, - const struct drm_framebuffer *fb, int plane) +/* Convert the fb->offset[] into x/y offsets */ +static int intel_fb_offset_to_xy(int *x, int *y, + const struct drm_framebuffer *fb, int plane) { - unsigned int cpp = fb->format->cpp[plane]; - unsigned int pitch = fb->pitches[plane]; - u32 linear_offset = fb->offsets[plane]; + struct drm_i915_private *dev_priv = to_i915(fb->dev); + + if (fb->modifier != DRM_FORMAT_MOD_LINEAR && + fb->offsets[plane] % intel_tile_size(dev_priv)) + return -EINVAL; + + *x = 0; + *y = 0; + + _intel_adjust_tile_offset(x, y, + fb, plane, DRM_MODE_ROTATE_0, + fb->offsets[plane], 0); - *y = linear_offset / pitch; - *x = linear_offset % pitch / cpp; + return 0; } static unsigned int intel_fb_modifier_to_tiling(uint64_t fb_modifier) @@ -2523,12 +2535,18 @@ intel_fill_fb_info(struct drm_i915_private *dev_priv, unsigned int cpp, size; u32 offset; int x, y; + int ret; cpp = fb->format->cpp[i]; width = drm_framebuffer_plane_width(fb->width, fb, i); height = drm_framebuffer_plane_height(fb->height, fb, i); - intel_fb_offset_to_xy(&x, &y, fb, i); + ret = intel_fb_offset_to_xy(&x, &y, fb, i); + if (ret) { + DRM_DEBUG_KMS("bad fb plane %d offset: 0x%x\n", + i, fb->offsets[i]); + return ret; + } if ((fb->modifier == I915_FORMAT_MOD_Y_TILED_CCS || fb->modifier == I915_FORMAT_MOD_Yf_TILED_CCS) && i == 1) { @@ -2539,11 +2557,13 @@ intel_fill_fb_info(struct drm_i915_private *dev_priv, int ccs_x, ccs_y; intel_tile_dims(fb, i, &tile_width, &tile_height); + tile_width *= hsub; + tile_height *= vsub; - ccs_x = (x * hsub) % (tile_width * hsub); - ccs_y = (y * vsub) % (tile_height * vsub); - main_x = intel_fb->normal[0].x % (tile_width * hsub); - main_y = intel_fb->normal[0].y % (tile_height * vsub); + ccs_x = (x * hsub) % tile_width; + ccs_y = (y * vsub) % tile_height; + main_x = intel_fb->normal[0].x % tile_width; + main_y = intel_fb->normal[0].y % tile_height; /* * CCS doesn't have its own x/y offset register, so the intra CCS tile @@ -2569,7 +2589,7 @@ intel_fill_fb_info(struct drm_i915_private *dev_priv, * fb layout agrees with the fence layout. We already check that the * fb stride matches the fence stride elsewhere. */ - if (i915_gem_object_is_tiled(intel_fb->obj) && + if (i == 0 && i915_gem_object_is_tiled(intel_fb->obj) && (x + width) * cpp > fb->pitches[i]) { DRM_DEBUG_KMS("bad fb plane %d offset: 0x%x\n", i, fb->offsets[i]); @@ -2632,10 +2652,10 @@ intel_fill_fb_info(struct drm_i915_private *dev_priv, * We only keep the x/y offsets, so push all of the * gtt offset into the x/y offsets. */ - _intel_adjust_tile_offset(&x, &y, - tile_width, tile_height, - tile_size, pitch_tiles, - gtt_offset_rotated * tile_size, 0); + __intel_adjust_tile_offset(&x, &y, + tile_width, tile_height, + tile_size, pitch_tiles, + gtt_offset_rotated * tile_size, 0); gtt_offset_rotated += rot_info->plane[i].width * rot_info->plane[i].height; @@ -12339,7 +12359,6 @@ static void intel_atomic_commit_tail(struct drm_atomic_state *state) struct drm_crtc_state *old_crtc_state, *new_crtc_state; struct drm_crtc *crtc; struct intel_crtc_state *intel_cstate; - bool hw_check = intel_state->modeset; u64 put_domains[I915_MAX_PIPES] = {}; unsigned crtc_vblank_mask = 0; int i; @@ -12356,7 +12375,6 @@ static void intel_atomic_commit_tail(struct drm_atomic_state *state) if (needs_modeset(new_crtc_state) || to_intel_crtc_state(new_crtc_state)->update_pipe) { - hw_check = true; put_domains[to_intel_crtc(crtc)->pipe] = modeset_get_crtc_power_domains(crtc, @@ -14010,7 +14028,7 @@ static int intel_framebuffer_init(struct intel_framebuffer *intel_fb, if (mode_cmd->handles[i] != mode_cmd->handles[0]) { DRM_DEBUG_KMS("bad plane %d handle\n", i); - return -EINVAL; + goto err; } stride_alignment = intel_fb_stride_alignment(fb, i); diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c index 4fd4853b2250..64134947c0aa 100644 --- a/drivers/gpu/drm/i915/intel_dp.c +++ b/drivers/gpu/drm/i915/intel_dp.c @@ -5273,7 +5273,7 @@ intel_dp_init_panel_power_sequencer(struct drm_device *dev, * seems sufficient to avoid this problem. */ if (dev_priv->quirks & QUIRK_INCREASE_T12_DELAY) { - vbt.t11_t12 = max_t(u16, vbt.t11_t12, 800 * 10); + vbt.t11_t12 = max_t(u16, vbt.t11_t12, 900 * 10); DRM_DEBUG_KMS("Increasing T12 panel delay as per the quirk to %d\n", vbt.t11_t12); } diff --git a/drivers/gpu/drm/i915/intel_dpio_phy.c b/drivers/gpu/drm/i915/intel_dpio_phy.c index 09b670929786..de38d014ed39 100644 --- a/drivers/gpu/drm/i915/intel_dpio_phy.c +++ b/drivers/gpu/drm/i915/intel_dpio_phy.c @@ -208,12 +208,6 @@ static const struct bxt_ddi_phy_info glk_ddi_phy_info[] = { }, }; -static u32 bxt_phy_port_mask(const struct bxt_ddi_phy_info *phy_info) -{ - return (phy_info->dual_channel * BIT(phy_info->channel[DPIO_CH1].port)) | - BIT(phy_info->channel[DPIO_CH0].port); -} - static const struct bxt_ddi_phy_info * bxt_get_phy_list(struct drm_i915_private *dev_priv, int *count) { @@ -313,7 +307,6 @@ bool bxt_ddi_phy_is_enabled(struct drm_i915_private *dev_priv, enum dpio_phy phy) { const struct bxt_ddi_phy_info *phy_info; - enum port port; phy_info = bxt_get_phy_info(dev_priv, phy); @@ -335,19 +328,6 @@ bool bxt_ddi_phy_is_enabled(struct drm_i915_private *dev_priv, return false; } - for_each_port_masked(port, bxt_phy_port_mask(phy_info)) { - u32 tmp = I915_READ(BXT_PHY_CTL(port)); - - if (tmp & BXT_PHY_CMNLANE_POWERDOWN_ACK) { - DRM_DEBUG_DRIVER("DDI PHY %d powered, but common lane " - "for port %c powered down " - "(PHY_CTL %08x)\n", - phy, port_name(port), tmp); - - return false; - } - } - return true; } diff --git a/drivers/gpu/drm/i915/intel_dsi.c b/drivers/gpu/drm/i915/intel_dsi.c index f0c11aec5ea5..7442891762be 100644 --- a/drivers/gpu/drm/i915/intel_dsi.c +++ b/drivers/gpu/drm/i915/intel_dsi.c @@ -892,8 +892,6 @@ static void intel_dsi_disable(struct intel_encoder *encoder, struct intel_crtc_state *old_crtc_state, struct drm_connector_state *old_conn_state) { - struct drm_device *dev = encoder->base.dev; - struct drm_i915_private *dev_priv = dev->dev_private; struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base); enum port port; @@ -903,15 +901,6 @@ static void intel_dsi_disable(struct intel_encoder *encoder, intel_panel_disable_backlight(old_conn_state); /* - * Disable Device ready before the port shutdown in order - * to avoid split screen - */ - if (IS_BROXTON(dev_priv)) { - for_each_dsi_port(port, intel_dsi->ports) - I915_WRITE(MIPI_DEVICE_READY(port), 0); - } - - /* * According to the spec we should send SHUTDOWN before * MIPI_SEQ_DISPLAY_OFF only for v3+ VBTs, but field testing * has shown that the v3 sequence works for v2 VBTs too diff --git a/drivers/gpu/drm/i915/intel_fbc.c b/drivers/gpu/drm/i915/intel_fbc.c index 3fca9fa39a8e..8c8ead2276e0 100644 --- a/drivers/gpu/drm/i915/intel_fbc.c +++ b/drivers/gpu/drm/i915/intel_fbc.c @@ -406,9 +406,7 @@ static void intel_fbc_work_fn(struct work_struct *__work) struct drm_vblank_crtc *vblank = &dev_priv->drm.vblank[crtc->pipe]; if (drm_crtc_vblank_get(&crtc->base)) { - DRM_ERROR("vblank not available for FBC on pipe %c\n", - pipe_name(crtc->pipe)); - + /* CRTC is now off, leave FBC deactivated */ mutex_lock(&fbc->lock); work->scheduled = false; mutex_unlock(&fbc->lock); diff --git a/drivers/gpu/drm/i915/intel_fifo_underrun.c b/drivers/gpu/drm/i915/intel_fifo_underrun.c index 5a7cca32c0fa..04689600e337 100644 --- a/drivers/gpu/drm/i915/intel_fifo_underrun.c +++ b/drivers/gpu/drm/i915/intel_fifo_underrun.c @@ -187,11 +187,11 @@ static void broadwell_set_fifo_underrun_reporting(struct drm_device *dev, } static void ibx_set_fifo_underrun_reporting(struct drm_device *dev, - enum transcoder pch_transcoder, + enum pipe pch_transcoder, bool enable) { struct drm_i915_private *dev_priv = to_i915(dev); - uint32_t bit = (pch_transcoder == TRANSCODER_A) ? + uint32_t bit = (pch_transcoder == PIPE_A) ? SDE_TRANSA_FIFO_UNDER : SDE_TRANSB_FIFO_UNDER; if (enable) @@ -203,7 +203,7 @@ static void ibx_set_fifo_underrun_reporting(struct drm_device *dev, static void cpt_check_pch_fifo_underruns(struct intel_crtc *crtc) { struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); - enum transcoder pch_transcoder = (enum transcoder) crtc->pipe; + enum pipe pch_transcoder = crtc->pipe; uint32_t serr_int = I915_READ(SERR_INT); lockdep_assert_held(&dev_priv->irq_lock); @@ -215,12 +215,12 @@ static void cpt_check_pch_fifo_underruns(struct intel_crtc *crtc) POSTING_READ(SERR_INT); trace_intel_pch_fifo_underrun(dev_priv, pch_transcoder); - DRM_ERROR("pch fifo underrun on pch transcoder %s\n", - transcoder_name(pch_transcoder)); + DRM_ERROR("pch fifo underrun on pch transcoder %c\n", + pipe_name(pch_transcoder)); } static void cpt_set_fifo_underrun_reporting(struct drm_device *dev, - enum transcoder pch_transcoder, + enum pipe pch_transcoder, bool enable, bool old) { struct drm_i915_private *dev_priv = to_i915(dev); @@ -238,8 +238,8 @@ static void cpt_set_fifo_underrun_reporting(struct drm_device *dev, if (old && I915_READ(SERR_INT) & SERR_INT_TRANS_FIFO_UNDERRUN(pch_transcoder)) { - DRM_ERROR("uncleared pch fifo underrun on pch transcoder %s\n", - transcoder_name(pch_transcoder)); + DRM_ERROR("uncleared pch fifo underrun on pch transcoder %c\n", + pipe_name(pch_transcoder)); } } } @@ -395,8 +395,8 @@ void intel_pch_fifo_underrun_irq_handler(struct drm_i915_private *dev_priv, if (intel_set_pch_fifo_underrun_reporting(dev_priv, pch_transcoder, false)) { trace_intel_pch_fifo_underrun(dev_priv, pch_transcoder); - DRM_ERROR("PCH transcoder %s FIFO underrun\n", - transcoder_name(pch_transcoder)); + DRM_ERROR("PCH transcoder %c FIFO underrun\n", + pipe_name(pch_transcoder)); } } diff --git a/drivers/gpu/drm/i915/intel_i2c.c b/drivers/gpu/drm/i915/intel_i2c.c index 6698826954e1..eb5827110d8f 100644 --- a/drivers/gpu/drm/i915/intel_i2c.c +++ b/drivers/gpu/drm/i915/intel_i2c.c @@ -649,7 +649,7 @@ static void gmbus_unlock_bus(struct i2c_adapter *adapter, mutex_unlock(&dev_priv->gmbus_mutex); } -const struct i2c_lock_operations gmbus_lock_ops = { +static const struct i2c_lock_operations gmbus_lock_ops = { .lock_bus = gmbus_lock_bus, .trylock_bus = gmbus_trylock_bus, .unlock_bus = gmbus_unlock_bus, diff --git a/drivers/gpu/drm/i915/intel_modes.c b/drivers/gpu/drm/i915/intel_modes.c index 951e834dd274..28a778b785ac 100644 --- a/drivers/gpu/drm/i915/intel_modes.c +++ b/drivers/gpu/drm/i915/intel_modes.c @@ -30,6 +30,21 @@ #include "intel_drv.h" #include "i915_drv.h" +static void intel_connector_update_eld_conn_type(struct drm_connector *connector) +{ + u8 conn_type; + + if (connector->connector_type == DRM_MODE_CONNECTOR_DisplayPort || + connector->connector_type == DRM_MODE_CONNECTOR_eDP) { + conn_type = DRM_ELD_CONN_TYPE_DP; + } else { + conn_type = DRM_ELD_CONN_TYPE_HDMI; + } + + connector->eld[DRM_ELD_SAD_COUNT_CONN_TYPE] &= ~DRM_ELD_CONN_TYPE_MASK; + connector->eld[DRM_ELD_SAD_COUNT_CONN_TYPE] |= conn_type; +} + /** * intel_connector_update_modes - update connector from edid * @connector: DRM connector device to use @@ -44,6 +59,8 @@ int intel_connector_update_modes(struct drm_connector *connector, ret = drm_add_edid_modes(connector, edid); drm_edid_to_eld(connector, edid); + intel_connector_update_eld_conn_type(connector); + return ret; } diff --git a/drivers/gpu/drm/i915/intel_panel.c b/drivers/gpu/drm/i915/intel_panel.c index a17b1de7d7e0..3b1c5d783ee7 100644 --- a/drivers/gpu/drm/i915/intel_panel.c +++ b/drivers/gpu/drm/i915/intel_panel.c @@ -1699,6 +1699,8 @@ bxt_setup_backlight(struct intel_connector *connector, enum pipe unused) if (!panel->backlight.max) return -ENODEV; + panel->backlight.min = get_backlight_min_vbt(connector); + val = bxt_get_backlight(connector); val = intel_panel_compute_brightness(connector, val); panel->backlight.level = clamp(val, panel->backlight.min, @@ -1735,6 +1737,8 @@ cnp_setup_backlight(struct intel_connector *connector, enum pipe unused) if (!panel->backlight.max) return -ENODEV; + panel->backlight.min = get_backlight_min_vbt(connector); + val = bxt_get_backlight(connector); val = intel_panel_compute_brightness(connector, val); panel->backlight.level = clamp(val, panel->backlight.min, diff --git a/drivers/gpu/drm/i915/intel_runtime_pm.c b/drivers/gpu/drm/i915/intel_runtime_pm.c index b66d8e136aa3..b3a087cb0860 100644 --- a/drivers/gpu/drm/i915/intel_runtime_pm.c +++ b/drivers/gpu/drm/i915/intel_runtime_pm.c @@ -2782,6 +2782,9 @@ static void cnl_display_core_init(struct drm_i915_private *dev_priv, bool resume /* 6. Enable DBUF */ gen9_dbuf_enable(dev_priv); + + if (resume && dev_priv->csr.dmc_payload) + intel_csr_load_program(dev_priv); } #undef CNL_PROCMON_IDX diff --git a/drivers/gpu/drm/i915/intel_sdvo.c b/drivers/gpu/drm/i915/intel_sdvo.c index 3dc38c2ef4c3..29a3b0f5bec7 100644 --- a/drivers/gpu/drm/i915/intel_sdvo.c +++ b/drivers/gpu/drm/i915/intel_sdvo.c @@ -2980,7 +2980,7 @@ static void proxy_unlock_bus(struct i2c_adapter *adapter, sdvo->i2c->lock_ops->unlock_bus(sdvo->i2c, flags); } -const struct i2c_lock_operations proxy_lock_ops = { +static const struct i2c_lock_operations proxy_lock_ops = { .lock_bus = proxy_lock_bus, .trylock_bus = proxy_trylock_bus, .unlock_bus = proxy_unlock_bus, diff --git a/drivers/gpu/drm/i915/selftests/i915_random.c b/drivers/gpu/drm/i915/selftests/i915_random.c index d044bf9a6feb..222c511bea49 100644 --- a/drivers/gpu/drm/i915/selftests/i915_random.c +++ b/drivers/gpu/drm/i915/selftests/i915_random.c @@ -62,7 +62,7 @@ unsigned int *i915_random_order(unsigned int count, struct rnd_state *state) { unsigned int *order, i; - order = kmalloc_array(count, sizeof(*order), GFP_TEMPORARY); + order = kmalloc_array(count, sizeof(*order), GFP_KERNEL); if (!order) return order; diff --git a/drivers/gpu/drm/i915/selftests/intel_breadcrumbs.c b/drivers/gpu/drm/i915/selftests/intel_breadcrumbs.c index 7276194c04f7..828904b7d468 100644 --- a/drivers/gpu/drm/i915/selftests/intel_breadcrumbs.c +++ b/drivers/gpu/drm/i915/selftests/intel_breadcrumbs.c @@ -117,12 +117,12 @@ static int igt_random_insert_remove(void *arg) mock_engine_reset(engine); - waiters = kvmalloc_array(count, sizeof(*waiters), GFP_TEMPORARY); + waiters = kvmalloc_array(count, sizeof(*waiters), GFP_KERNEL); if (!waiters) goto out_engines; bitmap = kcalloc(DIV_ROUND_UP(count, BITS_PER_LONG), sizeof(*bitmap), - GFP_TEMPORARY); + GFP_KERNEL); if (!bitmap) goto out_waiters; @@ -187,12 +187,12 @@ static int igt_insert_complete(void *arg) mock_engine_reset(engine); - waiters = kvmalloc_array(count, sizeof(*waiters), GFP_TEMPORARY); + waiters = kvmalloc_array(count, sizeof(*waiters), GFP_KERNEL); if (!waiters) goto out_engines; bitmap = kcalloc(DIV_ROUND_UP(count, BITS_PER_LONG), sizeof(*bitmap), - GFP_TEMPORARY); + GFP_KERNEL); if (!bitmap) goto out_waiters; @@ -368,7 +368,7 @@ static int igt_wakeup(void *arg) mock_engine_reset(engine); - waiters = kvmalloc_array(count, sizeof(*waiters), GFP_TEMPORARY); + waiters = kvmalloc_array(count, sizeof(*waiters), GFP_KERNEL); if (!waiters) goto out_engines; diff --git a/drivers/gpu/drm/i915/selftests/intel_uncore.c b/drivers/gpu/drm/i915/selftests/intel_uncore.c index 2d0fef2cfca6..3cac22eb47ce 100644 --- a/drivers/gpu/drm/i915/selftests/intel_uncore.c +++ b/drivers/gpu/drm/i915/selftests/intel_uncore.c @@ -127,7 +127,7 @@ static int intel_uncore_check_forcewake_domains(struct drm_i915_private *dev_pri return 0; valid = kzalloc(BITS_TO_LONGS(FW_RANGE) * sizeof(*valid), - GFP_TEMPORARY); + GFP_KERNEL); if (!valid) return -ENOMEM; diff --git a/drivers/gpu/drm/lib/drm_random.c b/drivers/gpu/drm/lib/drm_random.c index 7b12a68c3b54..a78c4b483e8d 100644 --- a/drivers/gpu/drm/lib/drm_random.c +++ b/drivers/gpu/drm/lib/drm_random.c @@ -28,7 +28,7 @@ unsigned int *drm_random_order(unsigned int count, struct rnd_state *state) { unsigned int *order, i; - order = kmalloc_array(count, sizeof(*order), GFP_TEMPORARY); + order = kmalloc_array(count, sizeof(*order), GFP_KERNEL); if (!order) return order; diff --git a/drivers/gpu/drm/msm/msm_gem_submit.c b/drivers/gpu/drm/msm/msm_gem_submit.c index 8a75c0bd8a78..5d0a75d4b249 100644 --- a/drivers/gpu/drm/msm/msm_gem_submit.c +++ b/drivers/gpu/drm/msm/msm_gem_submit.c @@ -40,7 +40,7 @@ static struct msm_gem_submit *submit_create(struct drm_device *dev, if (sz > SIZE_MAX) return NULL; - submit = kmalloc(sz, GFP_TEMPORARY | __GFP_NOWARN | __GFP_NORETRY); + submit = kmalloc(sz, GFP_KERNEL | __GFP_NOWARN | __GFP_NORETRY); if (!submit) return NULL; diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gpio/base.c b/drivers/gpu/drm/nouveau/nvkm/subdev/gpio/base.c index 4a57defc99b3..1399d923d446 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/gpio/base.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gpio/base.c @@ -171,7 +171,7 @@ nvkm_gpio_fini(struct nvkm_subdev *subdev, bool suspend) return 0; } -static struct dmi_system_id gpio_reset_ids[] = { +static const struct dmi_system_id gpio_reset_ids[] = { { .ident = "Apple Macbook 10,1", .matches = { diff --git a/drivers/gpu/drm/qxl/qxl_display.c b/drivers/gpu/drm/qxl/qxl_display.c index 14c5613b4388..afbf50d0c08f 100644 --- a/drivers/gpu/drm/qxl/qxl_display.c +++ b/drivers/gpu/drm/qxl/qxl_display.c @@ -509,23 +509,25 @@ static void qxl_primary_atomic_update(struct drm_plane *plane, .y2 = qfb->base.height }; - if (!old_state->fb) { - qxl_io_log(qdev, - "create primary fb: %dx%d,%d,%d\n", - bo->surf.width, bo->surf.height, - bo->surf.stride, bo->surf.format); + if (old_state->fb) { + qfb_old = to_qxl_framebuffer(old_state->fb); + bo_old = gem_to_qxl_bo(qfb_old->obj); + } else { + bo_old = NULL; + } - qxl_io_create_primary(qdev, 0, bo); - bo->is_primary = true; + if (bo == bo_old) return; - } else { - qfb_old = to_qxl_framebuffer(old_state->fb); - bo_old = gem_to_qxl_bo(qfb_old->obj); + if (bo_old && bo_old->is_primary) { + qxl_io_destroy_primary(qdev); bo_old->is_primary = false; } - bo->is_primary = true; + if (!bo->is_primary) { + qxl_io_create_primary(qdev, 0, bo); + bo->is_primary = true; + } qxl_draw_dirty_fb(qdev, qfb, bo, 0, 0, &norect, 1, 1); } @@ -534,13 +536,15 @@ static void qxl_primary_atomic_disable(struct drm_plane *plane, { struct qxl_device *qdev = plane->dev->dev_private; - if (old_state->fb) - { struct qxl_framebuffer *qfb = + if (old_state->fb) { + struct qxl_framebuffer *qfb = to_qxl_framebuffer(old_state->fb); struct qxl_bo *bo = gem_to_qxl_bo(qfb->obj); - qxl_io_destroy_primary(qdev); - bo->is_primary = false; + if (bo->is_primary) { + qxl_io_destroy_primary(qdev); + bo->is_primary = false; + } } } @@ -698,14 +702,15 @@ static void qxl_plane_cleanup_fb(struct drm_plane *plane, struct drm_gem_object *obj; struct qxl_bo *user_bo; - if (!plane->state->fb) { - /* we never executed prepare_fb, so there's nothing to + if (!old_state->fb) { + /* + * we never executed prepare_fb, so there's nothing to * unpin. */ return; } - obj = to_qxl_framebuffer(plane->state->fb)->obj; + obj = to_qxl_framebuffer(old_state->fb)->obj; user_bo = gem_to_qxl_bo(obj); qxl_bo_unpin(user_bo); } diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h index ec63bc5e9de7..8cbaeec090c9 100644 --- a/drivers/gpu/drm/radeon/radeon.h +++ b/drivers/gpu/drm/radeon/radeon.h @@ -924,7 +924,7 @@ struct radeon_vm_id { struct radeon_vm { struct mutex mutex; - struct rb_root va; + struct rb_root_cached va; /* protecting invalidated and freed */ spinlock_t status_lock; diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c index 997131d58c7f..ffc10cadcf34 100644 --- a/drivers/gpu/drm/radeon/radeon_device.c +++ b/drivers/gpu/drm/radeon/radeon_device.c @@ -1663,7 +1663,7 @@ int radeon_suspend_kms(struct drm_device *dev, bool suspend, radeon_agp_suspend(rdev); pci_save_state(dev->pdev); - if (freeze && rdev->family >= CHIP_CEDAR) { + if (freeze && rdev->family >= CHIP_CEDAR && !(rdev->flags & RADEON_IS_IGP)) { rdev->asic->asic_reset(rdev, true); pci_restore_state(dev->pdev); } else if (suspend) { diff --git a/drivers/gpu/drm/radeon/radeon_mn.c b/drivers/gpu/drm/radeon/radeon_mn.c index 896f2cf51e4e..1d62288b7ee3 100644 --- a/drivers/gpu/drm/radeon/radeon_mn.c +++ b/drivers/gpu/drm/radeon/radeon_mn.c @@ -50,7 +50,7 @@ struct radeon_mn { /* objects protected by lock */ struct mutex lock; - struct rb_root objects; + struct rb_root_cached objects; }; struct radeon_mn_node { @@ -75,8 +75,8 @@ static void radeon_mn_destroy(struct work_struct *work) mutex_lock(&rdev->mn_lock); mutex_lock(&rmn->lock); hash_del(&rmn->node); - rbtree_postorder_for_each_entry_safe(node, next_node, &rmn->objects, - it.rb) { + rbtree_postorder_for_each_entry_safe(node, next_node, + &rmn->objects.rb_root, it.rb) { interval_tree_remove(&node->it, &rmn->objects); list_for_each_entry_safe(bo, next_bo, &node->bos, mn_list) { @@ -205,7 +205,7 @@ static struct radeon_mn *radeon_mn_get(struct radeon_device *rdev) rmn->mm = mm; rmn->mn.ops = &radeon_mn_ops; mutex_init(&rmn->lock); - rmn->objects = RB_ROOT; + rmn->objects = RB_ROOT_CACHED; r = __mmu_notifier_register(&rmn->mn, mm); if (r) diff --git a/drivers/gpu/drm/radeon/radeon_vm.c b/drivers/gpu/drm/radeon/radeon_vm.c index 5e82b408d522..e5c0e635e371 100644 --- a/drivers/gpu/drm/radeon/radeon_vm.c +++ b/drivers/gpu/drm/radeon/radeon_vm.c @@ -1185,7 +1185,7 @@ int radeon_vm_init(struct radeon_device *rdev, struct radeon_vm *vm) vm->ids[i].last_id_use = NULL; } mutex_init(&vm->mutex); - vm->va = RB_ROOT; + vm->va = RB_ROOT_CACHED; spin_lock_init(&vm->status_lock); INIT_LIST_HEAD(&vm->invalidated); INIT_LIST_HEAD(&vm->freed); @@ -1232,10 +1232,11 @@ void radeon_vm_fini(struct radeon_device *rdev, struct radeon_vm *vm) struct radeon_bo_va *bo_va, *tmp; int i, r; - if (!RB_EMPTY_ROOT(&vm->va)) { + if (!RB_EMPTY_ROOT(&vm->va.rb_root)) { dev_err(rdev->dev, "still active bo inside vm\n"); } - rbtree_postorder_for_each_entry_safe(bo_va, tmp, &vm->va, it.rb) { + rbtree_postorder_for_each_entry_safe(bo_va, tmp, + &vm->va.rb_root, it.rb) { interval_tree_remove(&bo_va->it, &vm->va); r = radeon_bo_reserve(bo_va->bo, false); if (!r) { diff --git a/drivers/gpu/drm/selftests/test-drm_mm.c b/drivers/gpu/drm/selftests/test-drm_mm.c index dfdd858eda0a..86eb4c185a28 100644 --- a/drivers/gpu/drm/selftests/test-drm_mm.c +++ b/drivers/gpu/drm/selftests/test-drm_mm.c @@ -1627,7 +1627,7 @@ static int igt_topdown(void *ignored) goto err; bitmap = kzalloc(count / BITS_PER_LONG * sizeof(unsigned long), - GFP_TEMPORARY); + GFP_KERNEL); if (!bitmap) goto err_nodes; @@ -1741,7 +1741,7 @@ static int igt_bottomup(void *ignored) goto err; bitmap = kzalloc(count / BITS_PER_LONG * sizeof(unsigned long), - GFP_TEMPORARY); + GFP_KERNEL); if (!bitmap) goto err_nodes; diff --git a/drivers/gpu/drm/sun4i/Kconfig b/drivers/gpu/drm/sun4i/Kconfig index 06f05302ee75..882d85db9053 100644 --- a/drivers/gpu/drm/sun4i/Kconfig +++ b/drivers/gpu/drm/sun4i/Kconfig @@ -26,7 +26,7 @@ config DRM_SUN4I_HDMI_CEC bool "Allwinner A10 HDMI CEC Support" depends on DRM_SUN4I_HDMI select CEC_CORE - depends on CEC_PIN + select CEC_PIN help Choose this option if you have an Allwinner SoC with an HDMI controller and want to use CEC. diff --git a/drivers/gpu/drm/sun4i/sun4i_hdmi.h b/drivers/gpu/drm/sun4i/sun4i_hdmi.h index 1457750988da..a1f8cba251a2 100644 --- a/drivers/gpu/drm/sun4i/sun4i_hdmi.h +++ b/drivers/gpu/drm/sun4i/sun4i_hdmi.h @@ -15,7 +15,7 @@ #include <drm/drm_connector.h> #include <drm/drm_encoder.h> -#include <media/cec.h> +#include <media/cec-pin.h> #define SUN4I_HDMI_CTRL_REG 0x004 #define SUN4I_HDMI_CTRL_ENABLE BIT(31) diff --git a/drivers/gpu/drm/sun4i/sun4i_hdmi_enc.c b/drivers/gpu/drm/sun4i/sun4i_hdmi_enc.c index 9ea6cd5a1370..3cf1a6932fac 100644 --- a/drivers/gpu/drm/sun4i/sun4i_hdmi_enc.c +++ b/drivers/gpu/drm/sun4i/sun4i_hdmi_enc.c @@ -302,26 +302,29 @@ static int sun4i_hdmi_bind(struct device *dev, struct device *master, hdmi->mod_clk = devm_clk_get(dev, "mod"); if (IS_ERR(hdmi->mod_clk)) { dev_err(dev, "Couldn't get the HDMI mod clock\n"); - return PTR_ERR(hdmi->mod_clk); + ret = PTR_ERR(hdmi->mod_clk); + goto err_disable_bus_clk; } clk_prepare_enable(hdmi->mod_clk); hdmi->pll0_clk = devm_clk_get(dev, "pll-0"); if (IS_ERR(hdmi->pll0_clk)) { dev_err(dev, "Couldn't get the HDMI PLL 0 clock\n"); - return PTR_ERR(hdmi->pll0_clk); + ret = PTR_ERR(hdmi->pll0_clk); + goto err_disable_mod_clk; } hdmi->pll1_clk = devm_clk_get(dev, "pll-1"); if (IS_ERR(hdmi->pll1_clk)) { dev_err(dev, "Couldn't get the HDMI PLL 1 clock\n"); - return PTR_ERR(hdmi->pll1_clk); + ret = PTR_ERR(hdmi->pll1_clk); + goto err_disable_mod_clk; } ret = sun4i_tmds_create(hdmi); if (ret) { dev_err(dev, "Couldn't create the TMDS clock\n"); - return ret; + goto err_disable_mod_clk; } writel(SUN4I_HDMI_CTRL_ENABLE, hdmi->base + SUN4I_HDMI_CTRL_REG); @@ -362,7 +365,7 @@ static int sun4i_hdmi_bind(struct device *dev, struct device *master, ret = sun4i_hdmi_i2c_create(dev, hdmi); if (ret) { dev_err(dev, "Couldn't create the HDMI I2C adapter\n"); - return ret; + goto err_disable_mod_clk; } drm_encoder_helper_add(&hdmi->encoder, @@ -422,6 +425,10 @@ err_cleanup_connector: drm_encoder_cleanup(&hdmi->encoder); err_del_i2c_adapter: i2c_del_adapter(hdmi->i2c); +err_disable_mod_clk: + clk_disable_unprepare(hdmi->mod_clk); +err_disable_bus_clk: + clk_disable_unprepare(hdmi->bus_clk); return ret; } @@ -434,6 +441,8 @@ static void sun4i_hdmi_unbind(struct device *dev, struct device *master, drm_connector_cleanup(&hdmi->connector); drm_encoder_cleanup(&hdmi->encoder); i2c_del_adapter(hdmi->i2c); + clk_disable_unprepare(hdmi->mod_clk); + clk_disable_unprepare(hdmi->bus_clk); } static const struct component_ops sun4i_hdmi_ops = { diff --git a/drivers/gpu/drm/tegra/trace.h b/drivers/gpu/drm/tegra/trace.h index e9b7cdad5c4c..5a1ab4046e92 100644 --- a/drivers/gpu/drm/tegra/trace.h +++ b/drivers/gpu/drm/tegra/trace.h @@ -63,6 +63,6 @@ DEFINE_EVENT(register_access, sor_readl, /* This part must be outside protection */ #undef TRACE_INCLUDE_PATH -#define TRACE_INCLUDE_PATH . +#define TRACE_INCLUDE_PATH ../../drivers/gpu/drm/tegra #define TRACE_INCLUDE_FILE trace #include <trace/define_trace.h> diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c index cba11f13d994..180ce6296416 100644 --- a/drivers/gpu/drm/ttm/ttm_bo.c +++ b/drivers/gpu/drm/ttm/ttm_bo.c @@ -109,8 +109,8 @@ static ssize_t ttm_bo_global_show(struct kobject *kobj, struct ttm_bo_global *glob = container_of(kobj, struct ttm_bo_global, kobj); - return snprintf(buffer, PAGE_SIZE, "%lu\n", - (unsigned long) atomic_read(&glob->bo_count)); + return snprintf(buffer, PAGE_SIZE, "%d\n", + atomic_read(&glob->bo_count)); } static struct attribute *ttm_bo_global_attrs[] = { diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c b/drivers/gpu/drm/ttm/ttm_bo_util.c index d0459b392e5e..c934ad5b3903 100644 --- a/drivers/gpu/drm/ttm/ttm_bo_util.c +++ b/drivers/gpu/drm/ttm/ttm_bo_util.c @@ -469,6 +469,7 @@ static int ttm_buffer_object_transfer(struct ttm_buffer_object *bo, * TODO: Explicit member copy would probably be better here. */ + atomic_inc(&bo->glob->bo_count); INIT_LIST_HEAD(&fbo->ddestroy); INIT_LIST_HEAD(&fbo->lru); INIT_LIST_HEAD(&fbo->swap); |