diff options
Diffstat (limited to 'drivers/gpu/drm')
206 files changed, 5663 insertions, 1917 deletions
diff --git a/drivers/gpu/drm/Kconfig b/drivers/gpu/drm/Kconfig index 594ac6c3a1f4..7ff89690a976 100644 --- a/drivers/gpu/drm/Kconfig +++ b/drivers/gpu/drm/Kconfig @@ -98,8 +98,8 @@ config DRM_DEBUG_DP_MST_TOPOLOGY_REFS config DRM_FBDEV_EMULATION bool "Enable legacy fbdev support for your modesetting driver" depends on DRM + depends on FB select DRM_KMS_HELPER - select FB select FB_CFB_FILLRECT select FB_CFB_COPYAREA select FB_CFB_IMAGEBLIT @@ -379,6 +379,19 @@ source "drivers/gpu/drm/xlnx/Kconfig" source "drivers/gpu/drm/gud/Kconfig" +config DRM_HYPERV + tristate "DRM Support for Hyper-V synthetic video device" + depends on DRM && PCI && MMU && HYPERV + select DRM_KMS_HELPER + select DRM_GEM_SHMEM_HELPER + help + This is a KMS driver for Hyper-V synthetic video device. Choose this + option if you would like to enable drm driver for Hyper-V virtual + machine. Unselect Hyper-V framebuffer driver (CONFIG_FB_HYPERV) so + that DRM driver is used by default. + + If M is selected the module will be called hyperv_drm. + # Keep legacy drivers last menuconfig DRM_LEGACY diff --git a/drivers/gpu/drm/Makefile b/drivers/gpu/drm/Makefile index a91cc7684904..a118692a6df7 100644 --- a/drivers/gpu/drm/Makefile +++ b/drivers/gpu/drm/Makefile @@ -126,3 +126,4 @@ obj-$(CONFIG_DRM_MCDE) += mcde/ obj-$(CONFIG_DRM_TIDSS) += tidss/ obj-y += xlnx/ obj-y += gud/ +obj-$(CONFIG_DRM_HYPERV) += hyperv/ diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c index d6cb7cf76623..fdee98fae2ba 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c @@ -247,7 +247,7 @@ static int amdgpu_amdkfd_remove_eviction_fence(struct amdgpu_bo *bo, if (!ef) return -EINVAL; - old = dma_resv_get_list(resv); + old = dma_resv_shared_list(resv); if (!old) return 0; @@ -1671,7 +1671,7 @@ int amdgpu_amdkfd_gpuvm_map_memory_to_gpu( * the next restore worker */ if (amdgpu_ttm_tt_get_usermm(bo->tbo.ttm) && - bo->tbo.mem.mem_type == TTM_PL_SYSTEM) + bo->tbo.resource->mem_type == TTM_PL_SYSTEM) is_invalid_userptr = true; ret = vm_validate_pt_pd_bos(avm); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 861dd5f79d7f..6a242ec3f7ef 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -4136,9 +4136,9 @@ static int amdgpu_device_recover_vram(struct amdgpu_device *adev) list_for_each_entry(shadow, &adev->shadow_list, shadow_list) { /* No need to recover an evicted BO */ - if (shadow->tbo.mem.mem_type != TTM_PL_TT || - shadow->tbo.mem.start == AMDGPU_BO_INVALID_OFFSET || - shadow->parent->tbo.mem.mem_type != TTM_PL_VRAM) + if (shadow->tbo.resource->mem_type != TTM_PL_TT || + shadow->tbo.resource->start == AMDGPU_BO_INVALID_OFFSET || + shadow->parent->tbo.resource->mem_type != TTM_PL_VRAM) continue; r = amdgpu_bo_restore_shadow(shadow, &next); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c index 2b978b7e7a4b..2b6a66c849d4 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c @@ -203,9 +203,8 @@ int amdgpu_display_crtc_page_flip_target(struct drm_crtc *crtc, goto unpin; } - r = dma_resv_get_fences_rcu(new_abo->tbo.base.resv, &work->excl, - &work->shared_count, - &work->shared); + r = dma_resv_get_fences(new_abo->tbo.base.resv, &work->excl, + &work->shared_count, &work->shared); if (unlikely(r != 0)) { DRM_ERROR("failed to get fences for buffer\n"); goto unpin; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c index 6ec1312b7389..c3053b83b80c 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c @@ -49,10 +49,10 @@ __dma_resv_make_exclusive(struct dma_resv *obj) unsigned int count; int r; - if (!dma_resv_get_list(obj)) /* no shared fences to convert */ + if (!dma_resv_shared_list(obj)) /* no shared fences to convert */ return 0; - r = dma_resv_get_fences_rcu(obj, NULL, &count, &fences); + r = dma_resv_get_fences(obj, NULL, &count, &fences); if (r) return r; @@ -226,12 +226,12 @@ static struct sg_table *amdgpu_dma_buf_map(struct dma_buf_attachment *attach, if (r) return ERR_PTR(r); - } else if (!(amdgpu_mem_type_to_domain(bo->tbo.mem.mem_type) & + } else if (!(amdgpu_mem_type_to_domain(bo->tbo.resource->mem_type) & AMDGPU_GEM_DOMAIN_GTT)) { return ERR_PTR(-EBUSY); } - switch (bo->tbo.mem.mem_type) { + switch (bo->tbo.resource->mem_type) { case TTM_PL_TT: sgt = drm_prime_pages_to_sg(obj->dev, bo->tbo.ttm->pages, @@ -245,8 +245,9 @@ static struct sg_table *amdgpu_dma_buf_map(struct dma_buf_attachment *attach, break; case TTM_PL_VRAM: - r = amdgpu_vram_mgr_alloc_sgt(adev, &bo->tbo.mem, 0, - bo->tbo.base.size, attach->dev, dir, &sgt); + r = amdgpu_vram_mgr_alloc_sgt(adev, bo->tbo.resource, 0, + bo->tbo.base.size, attach->dev, + dir, &sgt); if (r) return ERR_PTR(r); break; @@ -436,7 +437,7 @@ amdgpu_dma_buf_move_notify(struct dma_buf_attachment *attach) struct amdgpu_vm_bo_base *bo_base; int r; - if (bo->tbo.mem.mem_type == TTM_PL_SYSTEM) + if (bo->tbo.resource->mem_type == TTM_PL_SYSTEM) return; r = ttm_bo_validate(&bo->tbo, &placement, &ctx); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c index 88ea77b1e68a..9cf4beaf646c 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c @@ -226,7 +226,7 @@ static void amdgpu_gem_object_close(struct drm_gem_object *obj, if (!amdgpu_vm_ready(vm)) goto out_unlock; - fence = dma_resv_get_excl(bo->tbo.base.resv); + fence = dma_resv_excl_fence(bo->tbo.base.resv); if (fence) { amdgpu_bo_fence(bo, fence, true); fence = NULL; @@ -526,8 +526,7 @@ int amdgpu_gem_wait_idle_ioctl(struct drm_device *dev, void *data, return -ENOENT; } robj = gem_to_amdgpu_bo(gobj); - ret = dma_resv_wait_timeout_rcu(robj->tbo.base.resv, true, true, - timeout); + ret = dma_resv_wait_timeout(robj->tbo.base.resv, true, true, timeout); /* ret == 0 means not signaled, * ret > 0 means signaled diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c index 4fc1515381f5..0174f7817ce2 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c @@ -101,7 +101,7 @@ void amdgpu_gmc_get_pde_for_bo(struct amdgpu_bo *bo, int level, { struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev); - switch (bo->tbo.mem.mem_type) { + switch (bo->tbo.resource->mem_type) { case TTM_PL_TT: *addr = bo->tbo.ttm->dma_address[0]; break; @@ -112,7 +112,7 @@ void amdgpu_gmc_get_pde_for_bo(struct amdgpu_bo *bo, int level, *addr = 0; break; } - *flags = amdgpu_ttm_tt_pde_flags(bo->tbo.ttm, &bo->tbo.mem); + *flags = amdgpu_ttm_tt_pde_flags(bo->tbo.ttm, bo->tbo.resource); amdgpu_gmc_get_vm_pde(adev, level, addr, flags); } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c index 9ab33048923e..ec96e0b26b11 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c @@ -22,18 +22,26 @@ * Authors: Christian König */ +#include <drm/ttm/ttm_range_manager.h> + #include "amdgpu.h" +struct amdgpu_gtt_node { + struct ttm_buffer_object *tbo; + struct ttm_range_mgr_node base; +}; + static inline struct amdgpu_gtt_mgr * to_gtt_mgr(struct ttm_resource_manager *man) { return container_of(man, struct amdgpu_gtt_mgr, manager); } -struct amdgpu_gtt_node { - struct drm_mm_node node; - struct ttm_buffer_object *tbo; -}; +static inline struct amdgpu_gtt_node * +to_amdgpu_gtt_node(struct ttm_resource *res) +{ + return container_of(res, struct amdgpu_gtt_node, base.base); +} /** * DOC: mem_info_gtt_total @@ -93,13 +101,15 @@ const struct attribute_group amdgpu_gtt_mgr_attr_group = { /** * amdgpu_gtt_mgr_has_gart_addr - Check if mem has address space * - * @mem: the mem object to check + * @res: the mem object to check * * Check if a mem object has already address space allocated. */ -bool amdgpu_gtt_mgr_has_gart_addr(struct ttm_resource *mem) +bool amdgpu_gtt_mgr_has_gart_addr(struct ttm_resource *res) { - return mem->mm_node != NULL; + struct amdgpu_gtt_node *node = to_amdgpu_gtt_node(res); + + return drm_mm_node_allocated(&node->base.mm_nodes[0]); } /** @@ -115,54 +125,57 @@ bool amdgpu_gtt_mgr_has_gart_addr(struct ttm_resource *mem) static int amdgpu_gtt_mgr_new(struct ttm_resource_manager *man, struct ttm_buffer_object *tbo, const struct ttm_place *place, - struct ttm_resource *mem) + struct ttm_resource **res) { struct amdgpu_gtt_mgr *mgr = to_gtt_mgr(man); + uint32_t num_pages = PFN_UP(tbo->base.size); struct amdgpu_gtt_node *node; int r; spin_lock(&mgr->lock); - if ((&tbo->mem == mem || tbo->mem.mem_type != TTM_PL_TT) && - atomic64_read(&mgr->available) < mem->num_pages) { + if (tbo->resource && tbo->resource->mem_type != TTM_PL_TT && + atomic64_read(&mgr->available) < num_pages) { spin_unlock(&mgr->lock); return -ENOSPC; } - atomic64_sub(mem->num_pages, &mgr->available); + atomic64_sub(num_pages, &mgr->available); spin_unlock(&mgr->lock); - if (!place->lpfn) { - mem->mm_node = NULL; - mem->start = AMDGPU_BO_INVALID_OFFSET; - return 0; - } - - node = kzalloc(sizeof(*node), GFP_KERNEL); + node = kzalloc(struct_size(node, base.mm_nodes, 1), GFP_KERNEL); if (!node) { r = -ENOMEM; goto err_out; } node->tbo = tbo; + ttm_resource_init(tbo, place, &node->base.base); - spin_lock(&mgr->lock); - r = drm_mm_insert_node_in_range(&mgr->mm, &node->node, mem->num_pages, - tbo->page_alignment, 0, place->fpfn, - place->lpfn, DRM_MM_INSERT_BEST); - spin_unlock(&mgr->lock); - - if (unlikely(r)) - goto err_free; - - mem->mm_node = node; - mem->start = node->node.start; + if (place->lpfn) { + spin_lock(&mgr->lock); + r = drm_mm_insert_node_in_range(&mgr->mm, + &node->base.mm_nodes[0], + num_pages, tbo->page_alignment, + 0, place->fpfn, place->lpfn, + DRM_MM_INSERT_BEST); + spin_unlock(&mgr->lock); + if (unlikely(r)) + goto err_free; + + node->base.base.start = node->base.mm_nodes[0].start; + } else { + node->base.mm_nodes[0].start = 0; + node->base.mm_nodes[0].size = node->base.base.num_pages; + node->base.base.start = AMDGPU_BO_INVALID_OFFSET; + } + *res = &node->base.base; return 0; err_free: kfree(node); err_out: - atomic64_add(mem->num_pages, &mgr->available); + atomic64_add(num_pages, &mgr->available); return r; } @@ -176,19 +189,18 @@ err_out: * Free the allocated GTT again. */ static void amdgpu_gtt_mgr_del(struct ttm_resource_manager *man, - struct ttm_resource *mem) + struct ttm_resource *res) { + struct amdgpu_gtt_node *node = to_amdgpu_gtt_node(res); struct amdgpu_gtt_mgr *mgr = to_gtt_mgr(man); - struct amdgpu_gtt_node *node = mem->mm_node; - if (node) { - spin_lock(&mgr->lock); - drm_mm_remove_node(&node->node); - spin_unlock(&mgr->lock); - kfree(node); - } + spin_lock(&mgr->lock); + if (drm_mm_node_allocated(&node->base.mm_nodes[0])) + drm_mm_remove_node(&node->base.mm_nodes[0]); + spin_unlock(&mgr->lock); + atomic64_add(res->num_pages, &mgr->available); - atomic64_add(mem->num_pages, &mgr->available); + kfree(node); } /** @@ -224,7 +236,7 @@ int amdgpu_gtt_mgr_recover(struct ttm_resource_manager *man) adev = container_of(mgr, typeof(*adev), mman.gtt_mgr); spin_lock(&mgr->lock); drm_mm_for_each_node(mm_node, &mgr->mm) { - node = container_of(mm_node, struct amdgpu_gtt_node, node); + node = container_of(mm_node, typeof(*node), base.mm_nodes[0]); r = amdgpu_ttm_recover_gart(node->tbo); if (r) break; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c index c7f3aae23c62..b7fb72bff2c1 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c @@ -112,7 +112,7 @@ void amdgpu_pasid_free_delayed(struct dma_resv *resv, unsigned count; int r; - r = dma_resv_get_fences_rcu(resv, NULL, &count, &fences); + r = dma_resv_get_fences(resv, NULL, &count, &fences); if (r) goto fallback; @@ -156,8 +156,7 @@ fallback: /* Not enough memory for the delayed delete, as last resort * block for all the fences to complete. */ - dma_resv_wait_timeout_rcu(resv, true, false, - MAX_SCHEDULE_TIMEOUT); + dma_resv_wait_timeout(resv, true, false, MAX_SCHEDULE_TIMEOUT); amdgpu_pasid_free(pasid); } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c index 2741c28ff1b5..d6c54c7f7679 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c @@ -75,8 +75,8 @@ static bool amdgpu_mn_invalidate_gfx(struct mmu_interval_notifier *mni, mmu_interval_set_seq(mni, cur_seq); - r = dma_resv_wait_timeout_rcu(bo->tbo.base.resv, true, false, - MAX_SCHEDULE_TIMEOUT); + r = dma_resv_wait_timeout(bo->tbo.base.resv, true, false, + MAX_SCHEDULE_TIMEOUT); mutex_unlock(&adev->notifier_lock); if (r <= 0) DRM_ERROR("(%ld) failed to wait for user bo\n", r); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c index 16417802bba9..b7a2070d90af 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c @@ -364,14 +364,14 @@ int amdgpu_bo_create_kernel_at(struct amdgpu_device *adev, if (cpu_addr) amdgpu_bo_kunmap(*bo_ptr); - ttm_resource_free(&(*bo_ptr)->tbo, &(*bo_ptr)->tbo.mem); + ttm_resource_free(&(*bo_ptr)->tbo, &(*bo_ptr)->tbo.resource); for (i = 0; i < (*bo_ptr)->placement.num_placement; ++i) { (*bo_ptr)->placements[i].fpfn = offset >> PAGE_SHIFT; (*bo_ptr)->placements[i].lpfn = (offset + size) >> PAGE_SHIFT; } r = ttm_bo_mem_space(&(*bo_ptr)->tbo, &(*bo_ptr)->placement, - &(*bo_ptr)->tbo.mem, &ctx); + &(*bo_ptr)->tbo.resource, &ctx); if (r) goto error; @@ -575,15 +575,15 @@ int amdgpu_bo_create(struct amdgpu_device *adev, return r; if (!amdgpu_gmc_vram_full_visible(&adev->gmc) && - bo->tbo.mem.mem_type == TTM_PL_VRAM && - bo->tbo.mem.start < adev->gmc.visible_vram_size >> PAGE_SHIFT) + bo->tbo.resource->mem_type == TTM_PL_VRAM && + bo->tbo.resource->start < adev->gmc.visible_vram_size >> PAGE_SHIFT) amdgpu_cs_report_moved_bytes(adev, ctx.bytes_moved, ctx.bytes_moved); else amdgpu_cs_report_moved_bytes(adev, ctx.bytes_moved, 0); if (bp->flags & AMDGPU_GEM_CREATE_VRAM_CLEARED && - bo->tbo.mem.mem_type == TTM_PL_VRAM) { + bo->tbo.resource->mem_type == TTM_PL_VRAM) { struct dma_fence *fence; r = amdgpu_fill_buffer(bo, 0, bo->tbo.base.resv, &fence); @@ -777,12 +777,12 @@ int amdgpu_bo_kmap(struct amdgpu_bo *bo, void **ptr) return 0; } - r = dma_resv_wait_timeout_rcu(bo->tbo.base.resv, false, false, - MAX_SCHEDULE_TIMEOUT); + r = dma_resv_wait_timeout(bo->tbo.base.resv, false, false, + MAX_SCHEDULE_TIMEOUT); if (r < 0) return r; - r = ttm_bo_kmap(&bo->tbo, 0, bo->tbo.mem.num_pages, &bo->kmap); + r = ttm_bo_kmap(&bo->tbo, 0, bo->tbo.resource->num_pages, &bo->kmap); if (r) return r; @@ -905,8 +905,8 @@ int amdgpu_bo_pin_restricted(struct amdgpu_bo *bo, u32 domain, domain = amdgpu_bo_get_preferred_pin_domain(adev, domain); if (bo->tbo.pin_count) { - uint32_t mem_type = bo->tbo.mem.mem_type; - uint32_t mem_flags = bo->tbo.mem.placement; + uint32_t mem_type = bo->tbo.resource->mem_type; + uint32_t mem_flags = bo->tbo.resource->placement; if (!(domain & amdgpu_mem_type_to_domain(mem_type))) return -EINVAL; @@ -956,7 +956,7 @@ int amdgpu_bo_pin_restricted(struct amdgpu_bo *bo, u32 domain, ttm_bo_pin(&bo->tbo); - domain = amdgpu_mem_type_to_domain(bo->tbo.mem.mem_type); + domain = amdgpu_mem_type_to_domain(bo->tbo.resource->mem_type); if (domain == AMDGPU_GEM_DOMAIN_VRAM) { atomic64_add(amdgpu_bo_size(bo), &adev->vram_pin_size); atomic64_add(amdgpu_vram_mgr_bo_visible_size(bo), @@ -1008,11 +1008,11 @@ void amdgpu_bo_unpin(struct amdgpu_bo *bo) if (bo->tbo.base.import_attach) dma_buf_unpin(bo->tbo.base.import_attach); - if (bo->tbo.mem.mem_type == TTM_PL_VRAM) { + if (bo->tbo.resource->mem_type == TTM_PL_VRAM) { atomic64_sub(amdgpu_bo_size(bo), &adev->vram_pin_size); atomic64_sub(amdgpu_vram_mgr_bo_visible_size(bo), &adev->visible_pin_size); - } else if (bo->tbo.mem.mem_type == TTM_PL_TT) { + } else if (bo->tbo.resource->mem_type == TTM_PL_TT) { atomic64_sub(amdgpu_bo_size(bo), &adev->gart_pin_size); } } @@ -1245,7 +1245,7 @@ void amdgpu_bo_move_notify(struct ttm_buffer_object *bo, { struct amdgpu_device *adev = amdgpu_ttm_adev(bo->bdev); struct amdgpu_bo *abo; - struct ttm_resource *old_mem = &bo->mem; + struct ttm_resource *old_mem = bo->resource; if (!amdgpu_bo_is_amdgpu_bo(bo)) return; @@ -1256,7 +1256,7 @@ void amdgpu_bo_move_notify(struct ttm_buffer_object *bo, amdgpu_bo_kunmap(abo); if (abo->tbo.base.dma_buf && !abo->tbo.base.import_attach && - bo->mem.mem_type != TTM_PL_SYSTEM) + bo->resource->mem_type != TTM_PL_SYSTEM) dma_buf_move_notify(abo->tbo.base.dma_buf); /* remember the eviction */ @@ -1276,7 +1276,7 @@ void amdgpu_bo_get_memory(struct amdgpu_bo *bo, uint64_t *vram_mem, { unsigned int domain; - domain = amdgpu_mem_type_to_domain(bo->tbo.mem.mem_type); + domain = amdgpu_mem_type_to_domain(bo->tbo.resource->mem_type); switch (domain) { case AMDGPU_GEM_DOMAIN_VRAM: *vram_mem += amdgpu_bo_size(bo); @@ -1318,7 +1318,7 @@ void amdgpu_bo_release_notify(struct ttm_buffer_object *bo) if (bo->base.resv == &bo->base._resv) amdgpu_amdkfd_remove_fence_on_pt_pd_bos(abo); - if (bo->mem.mem_type != TTM_PL_VRAM || !bo->mem.mm_node || + if (bo->resource->mem_type != TTM_PL_VRAM || !(abo->flags & AMDGPU_GEM_CREATE_VRAM_WIPE_ON_RELEASE)) return; @@ -1355,10 +1355,10 @@ vm_fault_t amdgpu_bo_fault_reserve_notify(struct ttm_buffer_object *bo) /* Remember that this BO was accessed by the CPU */ abo->flags |= AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED; - if (bo->mem.mem_type != TTM_PL_VRAM) + if (bo->resource->mem_type != TTM_PL_VRAM) return 0; - offset = bo->mem.start << PAGE_SHIFT; + offset = bo->resource->start << PAGE_SHIFT; if ((offset + bo->base.size) <= adev->gmc.visible_vram_size) return 0; @@ -1381,9 +1381,9 @@ vm_fault_t amdgpu_bo_fault_reserve_notify(struct ttm_buffer_object *bo) else if (unlikely(r)) return VM_FAULT_SIGBUS; - offset = bo->mem.start << PAGE_SHIFT; + offset = bo->resource->start << PAGE_SHIFT; /* this should never happen */ - if (bo->mem.mem_type == TTM_PL_VRAM && + if (bo->resource->mem_type == TTM_PL_VRAM && (offset + bo->base.size) > adev->gmc.visible_vram_size) return VM_FAULT_SIGBUS; @@ -1468,11 +1468,11 @@ int amdgpu_bo_sync_wait(struct amdgpu_bo *bo, void *owner, bool intr) */ u64 amdgpu_bo_gpu_offset(struct amdgpu_bo *bo) { - WARN_ON_ONCE(bo->tbo.mem.mem_type == TTM_PL_SYSTEM); + WARN_ON_ONCE(bo->tbo.resource->mem_type == TTM_PL_SYSTEM); WARN_ON_ONCE(!dma_resv_is_locked(bo->tbo.base.resv) && !bo->tbo.pin_count && bo->tbo.type != ttm_bo_type_kernel); - WARN_ON_ONCE(bo->tbo.mem.start == AMDGPU_BO_INVALID_OFFSET); - WARN_ON_ONCE(bo->tbo.mem.mem_type == TTM_PL_VRAM && + WARN_ON_ONCE(bo->tbo.resource->start == AMDGPU_BO_INVALID_OFFSET); + WARN_ON_ONCE(bo->tbo.resource->mem_type == TTM_PL_VRAM && !(bo->flags & AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS)); return amdgpu_bo_gpu_offset_no_check(bo); @@ -1490,8 +1490,8 @@ u64 amdgpu_bo_gpu_offset_no_check(struct amdgpu_bo *bo) struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev); uint64_t offset; - offset = (bo->tbo.mem.start << PAGE_SHIFT) + - amdgpu_ttm_domain_start(adev, bo->tbo.mem.mem_type); + offset = (bo->tbo.resource->start << PAGE_SHIFT) + + amdgpu_ttm_domain_start(adev, bo->tbo.resource->mem_type); return amdgpu_gmc_sign_extend(offset); } @@ -1544,7 +1544,7 @@ u64 amdgpu_bo_print_info(int id, struct amdgpu_bo *bo, struct seq_file *m) unsigned int pin_count; u64 size; - domain = amdgpu_mem_type_to_domain(bo->tbo.mem.mem_type); + domain = amdgpu_mem_type_to_domain(bo->tbo.resource->mem_type); switch (domain) { case AMDGPU_GEM_DOMAIN_VRAM: placement = "VRAM"; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h index 90eab1c31027..126df03a7066 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h @@ -223,10 +223,10 @@ static inline bool amdgpu_bo_in_cpu_visible_vram(struct amdgpu_bo *bo) struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev); struct amdgpu_res_cursor cursor; - if (bo->tbo.mem.mem_type != TTM_PL_VRAM) + if (bo->tbo.resource->mem_type != TTM_PL_VRAM) return false; - amdgpu_res_first(&bo->tbo.mem, 0, amdgpu_bo_size(bo), &cursor); + amdgpu_res_first(bo->tbo.resource, 0, amdgpu_bo_size(bo), &cursor); while (cursor.remaining) { if (cursor.start < adev->gmc.visible_vram_size) return true; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_preempt_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_preempt_mgr.c index d607f314cc1b..f6aff7ce5160 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_preempt_mgr.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_preempt_mgr.c @@ -66,14 +66,18 @@ static DEVICE_ATTR_RO(mem_info_preempt_used); static int amdgpu_preempt_mgr_new(struct ttm_resource_manager *man, struct ttm_buffer_object *tbo, const struct ttm_place *place, - struct ttm_resource *mem) + struct ttm_resource **res) { struct amdgpu_preempt_mgr *mgr = to_preempt_mgr(man); - atomic64_add(mem->num_pages, &mgr->used); + *res = kzalloc(sizeof(**res), GFP_KERNEL); + if (*res) + return -ENOMEM; - mem->mm_node = NULL; - mem->start = AMDGPU_BO_INVALID_OFFSET; + ttm_resource_init(tbo, place, *res); + (*res)->start = AMDGPU_BO_INVALID_OFFSET; + + atomic64_add((*res)->num_pages, &mgr->used); return 0; } @@ -86,11 +90,12 @@ static int amdgpu_preempt_mgr_new(struct ttm_resource_manager *man, * Free the allocated GTT again. */ static void amdgpu_preempt_mgr_del(struct ttm_resource_manager *man, - struct ttm_resource *mem) + struct ttm_resource *res) { struct amdgpu_preempt_mgr *mgr = to_preempt_mgr(man); - atomic64_sub(mem->num_pages, &mgr->used); + atomic64_sub(res->num_pages, &mgr->used); + kfree(res); } /** diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_res_cursor.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_res_cursor.h index 40f2adf305bc..59e0fefb15aa 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_res_cursor.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_res_cursor.h @@ -28,6 +28,7 @@ #include <drm/drm_mm.h> #include <drm/ttm/ttm_resource.h> +#include <drm/ttm/ttm_range_manager.h> /* state back for walking over vram_mgr and gtt_mgr allocations */ struct amdgpu_res_cursor { @@ -53,7 +54,7 @@ static inline void amdgpu_res_first(struct ttm_resource *res, { struct drm_mm_node *node; - if (!res || !res->mm_node) { + if (!res) { cur->start = start; cur->size = size; cur->remaining = size; @@ -63,7 +64,7 @@ static inline void amdgpu_res_first(struct ttm_resource *res, BUG_ON(start + size > res->num_pages << PAGE_SHIFT); - node = res->mm_node; + node = to_ttm_range_mgr_node(res)->mm_nodes; while (start >= node->size << PAGE_SHIFT) start -= node++->size << PAGE_SHIFT; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c index 4e558632a5d2..1b2ceccaf5b0 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c @@ -210,10 +210,10 @@ int amdgpu_sync_resv(struct amdgpu_device *adev, struct amdgpu_sync *sync, return -EINVAL; /* always sync to the exclusive fence */ - f = dma_resv_get_excl(resv); + f = dma_resv_excl_fence(resv); r = amdgpu_sync_fence(sync, f); - flist = dma_resv_get_list(resv); + flist = dma_resv_shared_list(resv); if (!flist || r) return r; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h index 792d20261846..0527772fe1b8 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h @@ -127,8 +127,8 @@ TRACE_EVENT(amdgpu_bo_create, TP_fast_assign( __entry->bo = bo; - __entry->pages = bo->tbo.mem.num_pages; - __entry->type = bo->tbo.mem.mem_type; + __entry->pages = bo->tbo.resource->num_pages; + __entry->type = bo->tbo.resource->mem_type; __entry->prefer = bo->preferred_domains; __entry->allow = bo->allowed_domains; __entry->visible = bo->flags; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c index 118911059dc1..80dff29f2bc7 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c @@ -45,6 +45,7 @@ #include <drm/ttm/ttm_bo_api.h> #include <drm/ttm/ttm_bo_driver.h> #include <drm/ttm/ttm_placement.h> +#include <drm/ttm/ttm_range_manager.h> #include <drm/amdgpu_drm.h> @@ -125,7 +126,8 @@ static void amdgpu_evict_flags(struct ttm_buffer_object *bo, rcu_read_unlock(); return; } - switch (bo->mem.mem_type) { + + switch (bo->resource->mem_type) { case AMDGPU_PL_GDS: case AMDGPU_PL_GWS: case AMDGPU_PL_OA: @@ -460,7 +462,7 @@ static int amdgpu_bo_move(struct ttm_buffer_object *bo, bool evict, { struct amdgpu_device *adev; struct amdgpu_bo *abo; - struct ttm_resource *old_mem = &bo->mem; + struct ttm_resource *old_mem = bo->resource; int r; if (new_mem->mem_type == TTM_PL_TT || @@ -495,7 +497,7 @@ static int amdgpu_bo_move(struct ttm_buffer_object *bo, bool evict, return r; amdgpu_ttm_backend_unbind(bo->bdev, bo->ttm); - ttm_resource_free(bo, &bo->mem); + ttm_resource_free(bo, &bo->resource); ttm_bo_assign_mem(bo, new_mem); goto out; } @@ -605,7 +607,8 @@ static unsigned long amdgpu_ttm_io_mem_pfn(struct ttm_buffer_object *bo, struct amdgpu_device *adev = amdgpu_ttm_adev(bo->bdev); struct amdgpu_res_cursor cursor; - amdgpu_res_first(&bo->mem, (u64)page_offset << PAGE_SHIFT, 0, &cursor); + amdgpu_res_first(bo->resource, (u64)page_offset << PAGE_SHIFT, 0, + &cursor); return (adev->gmc.aper_base + cursor.start) >> PAGE_SHIFT; } @@ -954,50 +957,50 @@ int amdgpu_ttm_alloc_gart(struct ttm_buffer_object *bo) struct amdgpu_device *adev = amdgpu_ttm_adev(bo->bdev); struct ttm_operation_ctx ctx = { false, false }; struct amdgpu_ttm_tt *gtt = (void *)bo->ttm; - struct ttm_resource tmp; struct ttm_placement placement; struct ttm_place placements; + struct ttm_resource *tmp; uint64_t addr, flags; int r; - if (bo->mem.start != AMDGPU_BO_INVALID_OFFSET) + if (bo->resource->start != AMDGPU_BO_INVALID_OFFSET) return 0; addr = amdgpu_gmc_agp_addr(bo); if (addr != AMDGPU_BO_INVALID_OFFSET) { - bo->mem.start = addr >> PAGE_SHIFT; - } else { + bo->resource->start = addr >> PAGE_SHIFT; + return 0; + } - /* allocate GART space */ - placement.num_placement = 1; - placement.placement = &placements; - placement.num_busy_placement = 1; - placement.busy_placement = &placements; - placements.fpfn = 0; - placements.lpfn = adev->gmc.gart_size >> PAGE_SHIFT; - placements.mem_type = TTM_PL_TT; - placements.flags = bo->mem.placement; - - r = ttm_bo_mem_space(bo, &placement, &tmp, &ctx); - if (unlikely(r)) - return r; + /* allocate GART space */ + placement.num_placement = 1; + placement.placement = &placements; + placement.num_busy_placement = 1; + placement.busy_placement = &placements; + placements.fpfn = 0; + placements.lpfn = adev->gmc.gart_size >> PAGE_SHIFT; + placements.mem_type = TTM_PL_TT; + placements.flags = bo->resource->placement; - /* compute PTE flags for this buffer object */ - flags = amdgpu_ttm_tt_pte_flags(adev, bo->ttm, &tmp); + r = ttm_bo_mem_space(bo, &placement, &tmp, &ctx); + if (unlikely(r)) + return r; - /* Bind pages */ - gtt->offset = (u64)tmp.start << PAGE_SHIFT; - r = amdgpu_ttm_gart_bind(adev, bo, flags); - if (unlikely(r)) { - ttm_resource_free(bo, &tmp); - return r; - } + /* compute PTE flags for this buffer object */ + flags = amdgpu_ttm_tt_pte_flags(adev, bo->ttm, tmp); - amdgpu_gart_invalidate_tlb(adev); - ttm_resource_free(bo, &bo->mem); - bo->mem = tmp; + /* Bind pages */ + gtt->offset = (u64)tmp->start << PAGE_SHIFT; + r = amdgpu_ttm_gart_bind(adev, bo, flags); + if (unlikely(r)) { + ttm_resource_free(bo, &tmp); + return r; } + amdgpu_gart_invalidate_tlb(adev); + ttm_resource_free(bo, &bo->resource); + ttm_bo_assign_mem(bo, tmp); + return 0; } @@ -1016,7 +1019,7 @@ int amdgpu_ttm_recover_gart(struct ttm_buffer_object *tbo) if (!tbo->ttm) return 0; - flags = amdgpu_ttm_tt_pte_flags(adev, tbo->ttm, &tbo->mem); + flags = amdgpu_ttm_tt_pte_flags(adev, tbo->ttm, tbo->resource); r = amdgpu_ttm_gart_bind(adev, tbo, flags); return r; @@ -1330,12 +1333,16 @@ uint64_t amdgpu_ttm_tt_pte_flags(struct amdgpu_device *adev, struct ttm_tt *ttm, static bool amdgpu_ttm_bo_eviction_valuable(struct ttm_buffer_object *bo, const struct ttm_place *place) { - unsigned long num_pages = bo->mem.num_pages; + unsigned long num_pages = bo->resource->num_pages; struct amdgpu_res_cursor cursor; struct dma_resv_list *flist; struct dma_fence *f; int i; + /* Swapout? */ + if (bo->resource->mem_type == TTM_PL_SYSTEM) + return true; + if (bo->type == ttm_bo_type_kernel && !amdgpu_vm_evictable(ttm_to_amdgpu_bo(bo))) return false; @@ -1344,7 +1351,7 @@ static bool amdgpu_ttm_bo_eviction_valuable(struct ttm_buffer_object *bo, * If true, then return false as any KFD process needs all its BOs to * be resident to run successfully */ - flist = dma_resv_get_list(bo->base.resv); + flist = dma_resv_shared_list(bo->base.resv); if (flist) { for (i = 0; i < flist->shared_count; ++i) { f = rcu_dereference_protected(flist->shared[i], @@ -1354,7 +1361,7 @@ static bool amdgpu_ttm_bo_eviction_valuable(struct ttm_buffer_object *bo, } } - switch (bo->mem.mem_type) { + switch (bo->resource->mem_type) { case AMDGPU_PL_PREEMPT: /* Preemptible BOs don't own system resources managed by the * driver (pages, VRAM, GART space). They point to resources @@ -1372,7 +1379,7 @@ static bool amdgpu_ttm_bo_eviction_valuable(struct ttm_buffer_object *bo, case TTM_PL_VRAM: /* Check each drm MM node individually */ - amdgpu_res_first(&bo->mem, 0, (u64)num_pages << PAGE_SHIFT, + amdgpu_res_first(bo->resource, 0, (u64)num_pages << PAGE_SHIFT, &cursor); while (cursor.remaining) { if (place->fpfn < PFN_DOWN(cursor.start + cursor.size) @@ -1414,10 +1421,10 @@ static int amdgpu_ttm_access_memory(struct ttm_buffer_object *bo, uint32_t value = 0; int ret = 0; - if (bo->mem.mem_type != TTM_PL_VRAM) + if (bo->resource->mem_type != TTM_PL_VRAM) return -EIO; - amdgpu_res_first(&bo->mem, offset, len, &cursor); + amdgpu_res_first(bo->resource, offset, len, &cursor); while (cursor.remaining) { uint64_t aligned_pos = cursor.start & ~(uint64_t)3; uint64_t bytes = 4 - (cursor.start & 3); @@ -1952,21 +1959,21 @@ int amdgpu_fill_buffer(struct amdgpu_bo *bo, return -EINVAL; } - if (bo->tbo.mem.mem_type == AMDGPU_PL_PREEMPT) { + if (bo->tbo.resource->mem_type == AMDGPU_PL_PREEMPT) { DRM_ERROR("Trying to clear preemptible memory.\n"); return -EINVAL; } - if (bo->tbo.mem.mem_type == TTM_PL_TT) { + if (bo->tbo.resource->mem_type == TTM_PL_TT) { r = amdgpu_ttm_alloc_gart(&bo->tbo); if (r) return r; } - num_bytes = bo->tbo.mem.num_pages << PAGE_SHIFT; + num_bytes = bo->tbo.resource->num_pages << PAGE_SHIFT; num_loops = 0; - amdgpu_res_first(&bo->tbo.mem, 0, num_bytes, &cursor); + amdgpu_res_first(bo->tbo.resource, 0, num_bytes, &cursor); while (cursor.remaining) { num_loops += DIV_ROUND_UP_ULL(cursor.size, max_bytes); amdgpu_res_next(&cursor, cursor.size); @@ -1991,12 +1998,13 @@ int amdgpu_fill_buffer(struct amdgpu_bo *bo, } } - amdgpu_res_first(&bo->tbo.mem, 0, num_bytes, &cursor); + amdgpu_res_first(bo->tbo.resource, 0, num_bytes, &cursor); while (cursor.remaining) { uint32_t cur_size = min_t(uint64_t, cursor.size, max_bytes); uint64_t dst_addr = cursor.start; - dst_addr += amdgpu_ttm_domain_start(adev, bo->tbo.mem.mem_type); + dst_addr += amdgpu_ttm_domain_start(adev, + bo->tbo.resource->mem_type); amdgpu_emit_fill_buffer(adev, &job->ibs[0], src_data, dst_addr, cur_size); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c index ce8f80a959c6..0f576f294d8a 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c @@ -1125,9 +1125,8 @@ static int amdgpu_uvd_send_msg(struct amdgpu_ring *ring, struct amdgpu_bo *bo, ib->length_dw = 16; if (direct) { - r = dma_resv_wait_timeout_rcu(bo->tbo.base.resv, - true, false, - msecs_to_jiffies(10)); + r = dma_resv_wait_timeout(bo->tbo.base.resv, true, false, + msecs_to_jiffies(10)); if (r == 0) r = -ETIMEDOUT; if (r < 0) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index b4e46c7222f1..18246b5b6ee3 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -342,7 +342,7 @@ static void amdgpu_vm_bo_base_init(struct amdgpu_vm_bo_base *base, amdgpu_vm_bo_idle(base); if (bo->preferred_domains & - amdgpu_mem_type_to_domain(bo->tbo.mem.mem_type)) + amdgpu_mem_type_to_domain(bo->tbo.resource->mem_type)) return; /* @@ -658,10 +658,11 @@ void amdgpu_vm_move_to_lru_tail(struct amdgpu_device *adev, if (!bo->parent) continue; - ttm_bo_move_to_lru_tail(&bo->tbo, &bo->tbo.mem, + ttm_bo_move_to_lru_tail(&bo->tbo, bo->tbo.resource, &vm->lru_bulk_move); if (shadow) - ttm_bo_move_to_lru_tail(&shadow->tbo, &shadow->tbo.mem, + ttm_bo_move_to_lru_tail(&shadow->tbo, + shadow->tbo.resource, &vm->lru_bulk_move); } spin_unlock(&adev->mman.bdev.lru_lock); @@ -1859,10 +1860,10 @@ int amdgpu_vm_bo_update(struct amdgpu_device *adev, struct amdgpu_bo_va *bo_va, struct drm_gem_object *gobj = dma_buf->priv; struct amdgpu_bo *abo = gem_to_amdgpu_bo(gobj); - if (abo->tbo.mem.mem_type == TTM_PL_VRAM) + if (abo->tbo.resource->mem_type == TTM_PL_VRAM) bo = gem_to_amdgpu_bo(gobj); } - mem = &bo->tbo.mem; + mem = bo->tbo.resource; if (mem->mem_type == TTM_PL_TT || mem->mem_type == AMDGPU_PL_PREEMPT) pages_addr = bo->tbo.ttm->dma_address; @@ -1923,7 +1924,7 @@ int amdgpu_vm_bo_update(struct amdgpu_device *adev, struct amdgpu_bo_va *bo_va, * next command submission. */ if (bo && bo->tbo.base.resv == vm->root.base.bo->tbo.base.resv) { - uint32_t mem_type = bo->tbo.mem.mem_type; + uint32_t mem_type = bo->tbo.resource->mem_type; if (!(bo->preferred_domains & amdgpu_mem_type_to_domain(mem_type))) @@ -2064,13 +2065,12 @@ static void amdgpu_vm_prt_fini(struct amdgpu_device *adev, struct amdgpu_vm *vm) unsigned i, shared_count; int r; - r = dma_resv_get_fences_rcu(resv, &excl, - &shared_count, &shared); + r = dma_resv_get_fences(resv, &excl, &shared_count, &shared); if (r) { /* Not enough memory to grab the fence list, as last resort * block for all the fences to complete. */ - dma_resv_wait_timeout_rcu(resv, true, false, + dma_resv_wait_timeout(resv, true, false, MAX_SCHEDULE_TIMEOUT); return; } @@ -2682,7 +2682,7 @@ bool amdgpu_vm_evictable(struct amdgpu_bo *bo) return true; /* Don't evict VM page tables while they are busy */ - if (!dma_resv_test_signaled_rcu(bo->tbo.base.resv, true)) + if (!dma_resv_test_signaled(bo->tbo.base.resv, true)) return false; /* Try to block ongoing updates */ @@ -2862,8 +2862,8 @@ void amdgpu_vm_adjust_size(struct amdgpu_device *adev, uint32_t min_vm_size, */ long amdgpu_vm_wait_idle(struct amdgpu_vm *vm, long timeout) { - timeout = dma_resv_wait_timeout_rcu(vm->root.base.bo->tbo.base.resv, - true, true, timeout); + timeout = dma_resv_wait_timeout(vm->root.base.bo->tbo.base.resv, true, + true, timeout); if (timeout <= 0) return timeout; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c index 07e007dbff7c..436ec246a7da 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c @@ -23,6 +23,8 @@ */ #include <linux/dma-mapping.h> +#include <drm/ttm/ttm_range_manager.h> + #include "amdgpu.h" #include "amdgpu_vm.h" #include "amdgpu_res_cursor.h" @@ -217,19 +219,20 @@ static u64 amdgpu_vram_mgr_vis_size(struct amdgpu_device *adev, u64 amdgpu_vram_mgr_bo_visible_size(struct amdgpu_bo *bo) { struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev); - struct ttm_resource *mem = &bo->tbo.mem; - struct drm_mm_node *nodes = mem->mm_node; - unsigned pages = mem->num_pages; + struct ttm_resource *res = bo->tbo.resource; + unsigned pages = res->num_pages; + struct drm_mm_node *mm; u64 usage; if (amdgpu_gmc_vram_full_visible(&adev->gmc)) return amdgpu_bo_size(bo); - if (mem->start >= adev->gmc.visible_vram_size >> PAGE_SHIFT) + if (res->start >= adev->gmc.visible_vram_size >> PAGE_SHIFT) return 0; - for (usage = 0; nodes && pages; pages -= nodes->size, nodes++) - usage += amdgpu_vram_mgr_vis_size(adev, nodes); + mm = &container_of(res, struct ttm_range_mgr_node, base)->mm_nodes[0]; + for (usage = 0; pages; pages -= mm->size, mm++) + usage += amdgpu_vram_mgr_vis_size(adev, mm); return usage; } @@ -365,15 +368,15 @@ static void amdgpu_vram_mgr_virt_start(struct ttm_resource *mem, static int amdgpu_vram_mgr_new(struct ttm_resource_manager *man, struct ttm_buffer_object *tbo, const struct ttm_place *place, - struct ttm_resource *mem) + struct ttm_resource **res) { unsigned long lpfn, num_nodes, pages_per_node, pages_left, pages; struct amdgpu_vram_mgr *mgr = to_vram_mgr(man); struct amdgpu_device *adev = to_amdgpu_device(mgr); uint64_t vis_usage = 0, mem_bytes, max_bytes; + struct ttm_range_mgr_node *node; struct drm_mm *mm = &mgr->mm; enum drm_mm_insert_mode mode; - struct drm_mm_node *nodes; unsigned i; int r; @@ -386,10 +389,10 @@ static int amdgpu_vram_mgr_new(struct ttm_resource_manager *man, max_bytes -= AMDGPU_VM_RESERVED_VRAM; /* bail out quickly if there's likely not enough VRAM for this BO */ - mem_bytes = (u64)mem->num_pages << PAGE_SHIFT; + mem_bytes = tbo->base.size; if (atomic64_add_return(mem_bytes, &mgr->usage) > max_bytes) { - atomic64_sub(mem_bytes, &mgr->usage); - return -ENOSPC; + r = -ENOSPC; + goto error_sub; } if (place->flags & TTM_PL_FLAG_CONTIGUOUS) { @@ -404,22 +407,23 @@ static int amdgpu_vram_mgr_new(struct ttm_resource_manager *man, #endif pages_per_node = max_t(uint32_t, pages_per_node, tbo->page_alignment); - num_nodes = DIV_ROUND_UP(mem->num_pages, pages_per_node); + num_nodes = DIV_ROUND_UP_ULL(PFN_UP(mem_bytes), pages_per_node); } - nodes = kvmalloc_array((uint32_t)num_nodes, sizeof(*nodes), - GFP_KERNEL | __GFP_ZERO); - if (!nodes) { - atomic64_sub(mem_bytes, &mgr->usage); - return -ENOMEM; + node = kvmalloc(struct_size(node, mm_nodes, num_nodes), + GFP_KERNEL | __GFP_ZERO); + if (!node) { + r = -ENOMEM; + goto error_sub; } + ttm_resource_init(tbo, place, &node->base); + mode = DRM_MM_INSERT_BEST; if (place->flags & TTM_PL_FLAG_TOPDOWN) mode = DRM_MM_INSERT_HIGH; - mem->start = 0; - pages_left = mem->num_pages; + pages_left = node->base.num_pages; /* Limit maximum size to 2GB due to SG table limitations */ pages = min(pages_left, 2UL << (30 - PAGE_SHIFT)); @@ -432,8 +436,9 @@ static int amdgpu_vram_mgr_new(struct ttm_resource_manager *man, if (pages >= pages_per_node) alignment = pages_per_node; - r = drm_mm_insert_node_in_range(mm, &nodes[i], pages, alignment, - 0, place->fpfn, lpfn, mode); + r = drm_mm_insert_node_in_range(mm, &node->mm_nodes[i], pages, + alignment, 0, place->fpfn, + lpfn, mode); if (unlikely(r)) { if (pages > pages_per_node) { if (is_power_of_2(pages)) @@ -442,11 +447,11 @@ static int amdgpu_vram_mgr_new(struct ttm_resource_manager *man, pages = rounddown_pow_of_two(pages); continue; } - goto error; + goto error_free; } - vis_usage += amdgpu_vram_mgr_vis_size(adev, &nodes[i]); - amdgpu_vram_mgr_virt_start(mem, &nodes[i]); + vis_usage += amdgpu_vram_mgr_vis_size(adev, &node->mm_nodes[i]); + amdgpu_vram_mgr_virt_start(&node->base, &node->mm_nodes[i]); pages_left -= pages; ++i; @@ -456,19 +461,20 @@ static int amdgpu_vram_mgr_new(struct ttm_resource_manager *man, spin_unlock(&mgr->lock); if (i == 1) - mem->placement |= TTM_PL_FLAG_CONTIGUOUS; + node->base.placement |= TTM_PL_FLAG_CONTIGUOUS; atomic64_add(vis_usage, &mgr->vis_usage); - mem->mm_node = nodes; + *res = &node->base; return 0; -error: +error_free: while (i--) - drm_mm_remove_node(&nodes[i]); + drm_mm_remove_node(&node->mm_nodes[i]); spin_unlock(&mgr->lock); - atomic64_sub(mem->num_pages << PAGE_SHIFT, &mgr->usage); + kvfree(node); - kvfree(nodes); +error_sub: + atomic64_sub(mem_bytes, &mgr->usage); return r; } @@ -481,24 +487,22 @@ error: * Free the allocated VRAM again. */ static void amdgpu_vram_mgr_del(struct ttm_resource_manager *man, - struct ttm_resource *mem) + struct ttm_resource *res) { + struct ttm_range_mgr_node *node = to_ttm_range_mgr_node(res); struct amdgpu_vram_mgr *mgr = to_vram_mgr(man); struct amdgpu_device *adev = to_amdgpu_device(mgr); - struct drm_mm_node *nodes = mem->mm_node; uint64_t usage = 0, vis_usage = 0; - unsigned pages = mem->num_pages; - - if (!mem->mm_node) - return; + unsigned i, pages; spin_lock(&mgr->lock); - while (pages) { - pages -= nodes->size; - drm_mm_remove_node(nodes); - usage += nodes->size << PAGE_SHIFT; - vis_usage += amdgpu_vram_mgr_vis_size(adev, nodes); - ++nodes; + for (i = 0, pages = res->num_pages; pages; + pages -= node->mm_nodes[i].size, ++i) { + struct drm_mm_node *mm = &node->mm_nodes[i]; + + drm_mm_remove_node(mm); + usage += mm->size << PAGE_SHIFT; + vis_usage += amdgpu_vram_mgr_vis_size(adev, mm); } amdgpu_vram_mgr_do_reserve(man); spin_unlock(&mgr->lock); @@ -506,8 +510,7 @@ static void amdgpu_vram_mgr_del(struct ttm_resource_manager *man, atomic64_sub(usage, &mgr->usage); atomic64_sub(vis_usage, &mgr->vis_usage); - kvfree(mem->mm_node); - mem->mm_node = NULL; + kvfree(node); } /** @@ -524,7 +527,7 @@ static void amdgpu_vram_mgr_del(struct ttm_resource_manager *man, * Allocate and fill a sg table from a VRAM allocation. */ int amdgpu_vram_mgr_alloc_sgt(struct amdgpu_device *adev, - struct ttm_resource *mem, + struct ttm_resource *res, u64 offset, u64 length, struct device *dev, enum dma_data_direction dir, @@ -540,7 +543,7 @@ int amdgpu_vram_mgr_alloc_sgt(struct amdgpu_device *adev, return -ENOMEM; /* Determine the number of DRM_MM nodes to export */ - amdgpu_res_first(mem, offset, length, &cursor); + amdgpu_res_first(res, offset, length, &cursor); while (cursor.remaining) { num_entries++; amdgpu_res_next(&cursor, cursor.size); @@ -560,7 +563,7 @@ int amdgpu_vram_mgr_alloc_sgt(struct amdgpu_device *adev, * and the number of bytes from it. Access the following * DRM_MM node(s) if more buffer needs to exported */ - amdgpu_res_first(mem, offset, length, &cursor); + amdgpu_res_first(res, offset, length, &cursor); for_each_sgtable_sg((*sgt), sg, i) { phys_addr_t phys = cursor.start + adev->gmc.aper_base; size_t size = cursor.size; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c index fd8f544f0de2..2660f03e63a7 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c @@ -29,6 +29,7 @@ #include "amdgpu_object.h" #include "amdgpu_vm.h" #include "amdgpu_mn.h" +#include "amdgpu_res_cursor.h" #include "kfd_priv.h" #include "kfd_svm.h" #include "kfd_migrate.h" @@ -205,34 +206,6 @@ svm_migrate_copy_done(struct amdgpu_device *adev, struct dma_fence *mfence) return r; } -static uint64_t -svm_migrate_node_physical_addr(struct amdgpu_device *adev, - struct drm_mm_node **mm_node, uint64_t *offset) -{ - struct drm_mm_node *node = *mm_node; - uint64_t pos = *offset; - - if (node->start == AMDGPU_BO_INVALID_OFFSET) { - pr_debug("drm node is not validated\n"); - return 0; - } - - pr_debug("vram node start 0x%llx npages 0x%llx\n", node->start, - node->size); - - if (pos >= node->size) { - do { - pos -= node->size; - node++; - } while (pos >= node->size); - - *mm_node = node; - *offset = pos; - } - - return (node->start + pos) << PAGE_SHIFT; -} - unsigned long svm_migrate_addr_to_pfn(struct amdgpu_device *adev, unsigned long addr) { @@ -297,11 +270,9 @@ svm_migrate_copy_to_vram(struct amdgpu_device *adev, struct svm_range *prange, { uint64_t npages = migrate->cpages; struct device *dev = adev->dev; - struct drm_mm_node *node; + struct amdgpu_res_cursor cursor; dma_addr_t *src; uint64_t *dst; - uint64_t vram_addr; - uint64_t offset; uint64_t i, j; int r; @@ -317,19 +288,12 @@ svm_migrate_copy_to_vram(struct amdgpu_device *adev, struct svm_range *prange, goto out; } - node = prange->ttm_res->mm_node; - offset = prange->offset; - vram_addr = svm_migrate_node_physical_addr(adev, &node, &offset); - if (!vram_addr) { - WARN_ONCE(1, "vram node address is 0\n"); - r = -ENOMEM; - goto out; - } - + amdgpu_res_first(prange->ttm_res, prange->offset << PAGE_SHIFT, + npages << PAGE_SHIFT, &cursor); for (i = j = 0; i < npages; i++) { struct page *spage; - dst[i] = vram_addr + (j << PAGE_SHIFT); + dst[i] = cursor.start + (j << PAGE_SHIFT); migrate->dst[i] = svm_migrate_addr_to_pfn(adev, dst[i]); svm_migrate_get_vram_page(prange, migrate->dst[i]); @@ -354,18 +318,10 @@ svm_migrate_copy_to_vram(struct amdgpu_device *adev, struct svm_range *prange, mfence); if (r) goto out_free_vram_pages; - offset += j; - vram_addr = (node->start + offset) << PAGE_SHIFT; + amdgpu_res_next(&cursor, j << PAGE_SHIFT); j = 0; } else { - offset++; - vram_addr += PAGE_SIZE; - } - if (offset >= node->size) { - node++; - pr_debug("next node size 0x%llx\n", node->size); - vram_addr = node->start << PAGE_SHIFT; - offset = 0; + amdgpu_res_next(&cursor, PAGE_SIZE); } continue; } @@ -373,19 +329,15 @@ svm_migrate_copy_to_vram(struct amdgpu_device *adev, struct svm_range *prange, pr_debug("dma mapping src to 0x%llx, page_to_pfn 0x%lx\n", src[i] >> PAGE_SHIFT, page_to_pfn(spage)); - if (j + offset >= node->size - 1 && i < npages - 1) { + if (j >= (cursor.size >> PAGE_SHIFT) - 1 && i < npages - 1) { r = svm_migrate_copy_memory_gart(adev, src + i - j, dst + i - j, j + 1, FROM_RAM_TO_VRAM, mfence); if (r) goto out_free_vram_pages; - - node++; - pr_debug("next node size 0x%llx\n", node->size); - vram_addr = node->start << PAGE_SHIFT; - offset = 0; - j = 0; + amdgpu_res_next(&cursor, (j + 1) * PAGE_SIZE); + j= 0; } else { j++; } diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c index 0f18bd0dc64e..da569d417d1d 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c @@ -409,7 +409,7 @@ svm_range_validate_svm_bo(struct amdgpu_device *adev, struct svm_range *prange) pr_debug("reuse old bo svms 0x%p [0x%lx 0x%lx]\n", prange->svms, prange->start, prange->last); - prange->ttm_res = &prange->svm_bo->bo->tbo.mem; + prange->ttm_res = prange->svm_bo->bo->tbo.resource; return true; } @@ -515,7 +515,7 @@ svm_range_vram_node_new(struct amdgpu_device *adev, struct svm_range *prange, svm_bo->bo = bo; prange->svm_bo = svm_bo; - prange->ttm_res = &bo->tbo.mem; + prange->ttm_res = bo->tbo.resource; prange->offset = 0; spin_lock(&svm_bo->list_lock); diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index d08459227629..6fda0dfb78f8 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -8491,9 +8491,8 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_state *state, * deadlock during GPU reset when this fence will not signal * but we hold reservation lock for the BO. */ - r = dma_resv_wait_timeout_rcu(abo->tbo.base.resv, true, - false, - msecs_to_jiffies(5000)); + r = dma_resv_wait_timeout(abo->tbo.base.resv, true, false, + msecs_to_jiffies(5000)); if (unlikely(r <= 0)) DRM_ERROR("Waiting for fences timed out!"); diff --git a/drivers/gpu/drm/bridge/Kconfig b/drivers/gpu/drm/bridge/Kconfig index c96e4b38d1d3..85b673613687 100644 --- a/drivers/gpu/drm/bridge/Kconfig +++ b/drivers/gpu/drm/bridge/Kconfig @@ -285,6 +285,16 @@ config DRM_TI_TFP410 help Texas Instruments TFP410 DVI/HDMI Transmitter driver +config DRM_TI_SN65DSI83 + tristate "TI SN65DSI83 and SN65DSI84 DSI to LVDS bridge" + depends on OF + select DRM_KMS_HELPER + select REGMAP_I2C + select DRM_PANEL + select DRM_MIPI_DSI + help + Texas Instruments SN65DSI83 and SN65DSI84 DSI to LVDS Bridge driver + config DRM_TI_SN65DSI86 tristate "TI SN65DSI86 DSI to eDP bridge" depends on OF diff --git a/drivers/gpu/drm/bridge/Makefile b/drivers/gpu/drm/bridge/Makefile index dff2b2897529..f2c73683cfcb 100644 --- a/drivers/gpu/drm/bridge/Makefile +++ b/drivers/gpu/drm/bridge/Makefile @@ -23,6 +23,7 @@ obj-$(CONFIG_DRM_TOSHIBA_TC358767) += tc358767.o obj-$(CONFIG_DRM_TOSHIBA_TC358768) += tc358768.o obj-$(CONFIG_DRM_TOSHIBA_TC358775) += tc358775.o obj-$(CONFIG_DRM_I2C_ADV7511) += adv7511/ +obj-$(CONFIG_DRM_TI_SN65DSI83) += ti-sn65dsi83.o obj-$(CONFIG_DRM_TI_SN65DSI86) += ti-sn65dsi86.o obj-$(CONFIG_DRM_TI_TFP410) += ti-tfp410.o obj-$(CONFIG_DRM_TI_TPD12S015) += ti-tpd12s015.o diff --git a/drivers/gpu/drm/bridge/ti-sn65dsi83.c b/drivers/gpu/drm/bridge/ti-sn65dsi83.c new file mode 100644 index 000000000000..750f2172ef08 --- /dev/null +++ b/drivers/gpu/drm/bridge/ti-sn65dsi83.c @@ -0,0 +1,709 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * TI SN65DSI83,84,85 driver + * + * Currently supported: + * - SN65DSI83 + * = 1x Single-link DSI ~ 1x Single-link LVDS + * - Supported + * - Single-link LVDS mode tested + * - SN65DSI84 + * = 1x Single-link DSI ~ 2x Single-link or 1x Dual-link LVDS + * - Supported + * - Dual-link LVDS mode tested + * - 2x Single-link LVDS mode unsupported + * (should be easy to add by someone who has the HW) + * - SN65DSI85 + * = 2x Single-link or 1x Dual-link DSI ~ 2x Single-link or 1x Dual-link LVDS + * - Unsupported + * (should be easy to add by someone who has the HW) + * + * Copyright (C) 2021 Marek Vasut <marex@denx.de> + * + * Based on previous work of: + * Valentin Raevsky <valentin@compulab.co.il> + * Philippe Schenker <philippe.schenker@toradex.com> + */ + +#include <linux/bits.h> +#include <linux/clk.h> +#include <linux/gpio/consumer.h> +#include <linux/i2c.h> +#include <linux/module.h> +#include <linux/of_device.h> +#include <linux/of_graph.h> +#include <linux/regmap.h> + +#include <drm/drm_atomic_helper.h> +#include <drm/drm_bridge.h> +#include <drm/drm_mipi_dsi.h> +#include <drm/drm_of.h> +#include <drm/drm_panel.h> +#include <drm/drm_print.h> +#include <drm/drm_probe_helper.h> + +/* ID registers */ +#define REG_ID(n) (0x00 + (n)) +/* Reset and clock registers */ +#define REG_RC_RESET 0x09 +#define REG_RC_RESET_SOFT_RESET BIT(0) +#define REG_RC_LVDS_PLL 0x0a +#define REG_RC_LVDS_PLL_PLL_EN_STAT BIT(7) +#define REG_RC_LVDS_PLL_LVDS_CLK_RANGE(n) (((n) & 0x7) << 1) +#define REG_RC_LVDS_PLL_HS_CLK_SRC_DPHY BIT(0) +#define REG_RC_DSI_CLK 0x0b +#define REG_RC_DSI_CLK_DSI_CLK_DIVIDER(n) (((n) & 0x1f) << 3) +#define REG_RC_DSI_CLK_REFCLK_MULTIPLIER(n) ((n) & 0x3) +#define REG_RC_PLL_EN 0x0d +#define REG_RC_PLL_EN_PLL_EN BIT(0) +/* DSI registers */ +#define REG_DSI_LANE 0x10 +#define REG_DSI_LANE_LEFT_RIGHT_PIXELS BIT(7) /* DSI85-only */ +#define REG_DSI_LANE_DSI_CHANNEL_MODE_DUAL 0 /* DSI85-only */ +#define REG_DSI_LANE_DSI_CHANNEL_MODE_2SINGLE BIT(6) /* DSI85-only */ +#define REG_DSI_LANE_DSI_CHANNEL_MODE_SINGLE BIT(5) +#define REG_DSI_LANE_CHA_DSI_LANES(n) (((n) & 0x3) << 3) +#define REG_DSI_LANE_CHB_DSI_LANES(n) (((n) & 0x3) << 1) +#define REG_DSI_LANE_SOT_ERR_TOL_DIS BIT(0) +#define REG_DSI_EQ 0x11 +#define REG_DSI_EQ_CHA_DSI_DATA_EQ(n) (((n) & 0x3) << 6) +#define REG_DSI_EQ_CHA_DSI_CLK_EQ(n) (((n) & 0x3) << 2) +#define REG_DSI_CLK 0x12 +#define REG_DSI_CLK_CHA_DSI_CLK_RANGE(n) ((n) & 0xff) +/* LVDS registers */ +#define REG_LVDS_FMT 0x18 +#define REG_LVDS_FMT_DE_NEG_POLARITY BIT(7) +#define REG_LVDS_FMT_HS_NEG_POLARITY BIT(6) +#define REG_LVDS_FMT_VS_NEG_POLARITY BIT(5) +#define REG_LVDS_FMT_LVDS_LINK_CFG BIT(4) /* 0:AB 1:A-only */ +#define REG_LVDS_FMT_CHA_24BPP_MODE BIT(3) +#define REG_LVDS_FMT_CHB_24BPP_MODE BIT(2) +#define REG_LVDS_FMT_CHA_24BPP_FORMAT1 BIT(1) +#define REG_LVDS_FMT_CHB_24BPP_FORMAT1 BIT(0) +#define REG_LVDS_VCOM 0x19 +#define REG_LVDS_VCOM_CHA_LVDS_VOCM BIT(6) +#define REG_LVDS_VCOM_CHB_LVDS_VOCM BIT(4) +#define REG_LVDS_VCOM_CHA_LVDS_VOD_SWING(n) (((n) & 0x3) << 2) +#define REG_LVDS_VCOM_CHB_LVDS_VOD_SWING(n) ((n) & 0x3) +#define REG_LVDS_LANE 0x1a +#define REG_LVDS_LANE_EVEN_ODD_SWAP BIT(6) +#define REG_LVDS_LANE_CHA_REVERSE_LVDS BIT(5) +#define REG_LVDS_LANE_CHB_REVERSE_LVDS BIT(4) +#define REG_LVDS_LANE_CHA_LVDS_TERM BIT(1) +#define REG_LVDS_LANE_CHB_LVDS_TERM BIT(0) +#define REG_LVDS_CM 0x1b +#define REG_LVDS_CM_CHA_LVDS_CM_ADJUST(n) (((n) & 0x3) << 4) +#define REG_LVDS_CM_CHB_LVDS_CM_ADJUST(n) ((n) & 0x3) +/* Video registers */ +#define REG_VID_CHA_ACTIVE_LINE_LENGTH_LOW 0x20 +#define REG_VID_CHA_ACTIVE_LINE_LENGTH_HIGH 0x21 +#define REG_VID_CHA_VERTICAL_DISPLAY_SIZE_LOW 0x24 +#define REG_VID_CHA_VERTICAL_DISPLAY_SIZE_HIGH 0x25 +#define REG_VID_CHA_SYNC_DELAY_LOW 0x28 +#define REG_VID_CHA_SYNC_DELAY_HIGH 0x29 +#define REG_VID_CHA_HSYNC_PULSE_WIDTH_LOW 0x2c +#define REG_VID_CHA_HSYNC_PULSE_WIDTH_HIGH 0x2d +#define REG_VID_CHA_VSYNC_PULSE_WIDTH_LOW 0x30 +#define REG_VID_CHA_VSYNC_PULSE_WIDTH_HIGH 0x31 +#define REG_VID_CHA_HORIZONTAL_BACK_PORCH 0x34 +#define REG_VID_CHA_VERTICAL_BACK_PORCH 0x36 +#define REG_VID_CHA_HORIZONTAL_FRONT_PORCH 0x38 +#define REG_VID_CHA_VERTICAL_FRONT_PORCH 0x3a +#define REG_VID_CHA_TEST_PATTERN 0x3c +/* IRQ registers */ +#define REG_IRQ_GLOBAL 0xe0 +#define REG_IRQ_GLOBAL_IRQ_EN BIT(0) +#define REG_IRQ_EN 0xe1 +#define REG_IRQ_EN_CHA_SYNCH_ERR_EN BIT(7) +#define REG_IRQ_EN_CHA_CRC_ERR_EN BIT(6) +#define REG_IRQ_EN_CHA_UNC_ECC_ERR_EN BIT(5) +#define REG_IRQ_EN_CHA_COR_ECC_ERR_EN BIT(4) +#define REG_IRQ_EN_CHA_LLP_ERR_EN BIT(3) +#define REG_IRQ_EN_CHA_SOT_BIT_ERR_EN BIT(2) +#define REG_IRQ_EN_CHA_PLL_UNLOCK_EN BIT(0) +#define REG_IRQ_STAT 0xe5 +#define REG_IRQ_STAT_CHA_SYNCH_ERR BIT(7) +#define REG_IRQ_STAT_CHA_CRC_ERR BIT(6) +#define REG_IRQ_STAT_CHA_UNC_ECC_ERR BIT(5) +#define REG_IRQ_STAT_CHA_COR_ECC_ERR BIT(4) +#define REG_IRQ_STAT_CHA_LLP_ERR BIT(3) +#define REG_IRQ_STAT_CHA_SOT_BIT_ERR BIT(2) +#define REG_IRQ_STAT_CHA_PLL_UNLOCK BIT(0) + +enum sn65dsi83_model { + MODEL_SN65DSI83, + MODEL_SN65DSI84, +}; + +struct sn65dsi83 { + struct drm_bridge bridge; + struct drm_display_mode mode; + struct device *dev; + struct regmap *regmap; + struct device_node *host_node; + struct mipi_dsi_device *dsi; + struct drm_bridge *panel_bridge; + struct gpio_desc *enable_gpio; + int dsi_lanes; + bool lvds_dual_link; + bool lvds_dual_link_even_odd_swap; + bool lvds_format_24bpp; + bool lvds_format_jeida; +}; + +static const struct regmap_range sn65dsi83_readable_ranges[] = { + regmap_reg_range(REG_ID(0), REG_ID(8)), + regmap_reg_range(REG_RC_LVDS_PLL, REG_RC_DSI_CLK), + regmap_reg_range(REG_RC_PLL_EN, REG_RC_PLL_EN), + regmap_reg_range(REG_DSI_LANE, REG_DSI_CLK), + regmap_reg_range(REG_LVDS_FMT, REG_LVDS_CM), + regmap_reg_range(REG_VID_CHA_ACTIVE_LINE_LENGTH_LOW, + REG_VID_CHA_ACTIVE_LINE_LENGTH_HIGH), + regmap_reg_range(REG_VID_CHA_VERTICAL_DISPLAY_SIZE_LOW, + REG_VID_CHA_VERTICAL_DISPLAY_SIZE_HIGH), + regmap_reg_range(REG_VID_CHA_SYNC_DELAY_LOW, + REG_VID_CHA_SYNC_DELAY_HIGH), + regmap_reg_range(REG_VID_CHA_HSYNC_PULSE_WIDTH_LOW, + REG_VID_CHA_HSYNC_PULSE_WIDTH_HIGH), + regmap_reg_range(REG_VID_CHA_VSYNC_PULSE_WIDTH_LOW, + REG_VID_CHA_VSYNC_PULSE_WIDTH_HIGH), + regmap_reg_range(REG_VID_CHA_HORIZONTAL_BACK_PORCH, + REG_VID_CHA_HORIZONTAL_BACK_PORCH), + regmap_reg_range(REG_VID_CHA_VERTICAL_BACK_PORCH, + REG_VID_CHA_VERTICAL_BACK_PORCH), + regmap_reg_range(REG_VID_CHA_HORIZONTAL_FRONT_PORCH, + REG_VID_CHA_HORIZONTAL_FRONT_PORCH), + regmap_reg_range(REG_VID_CHA_VERTICAL_FRONT_PORCH, + REG_VID_CHA_VERTICAL_FRONT_PORCH), + regmap_reg_range(REG_VID_CHA_TEST_PATTERN, REG_VID_CHA_TEST_PATTERN), + regmap_reg_range(REG_IRQ_GLOBAL, REG_IRQ_EN), + regmap_reg_range(REG_IRQ_STAT, REG_IRQ_STAT), +}; + +static const struct regmap_access_table sn65dsi83_readable_table = { + .yes_ranges = sn65dsi83_readable_ranges, + .n_yes_ranges = ARRAY_SIZE(sn65dsi83_readable_ranges), +}; + +static const struct regmap_range sn65dsi83_writeable_ranges[] = { + regmap_reg_range(REG_RC_RESET, REG_RC_DSI_CLK), + regmap_reg_range(REG_RC_PLL_EN, REG_RC_PLL_EN), + regmap_reg_range(REG_DSI_LANE, REG_DSI_CLK), + regmap_reg_range(REG_LVDS_FMT, REG_LVDS_CM), + regmap_reg_range(REG_VID_CHA_ACTIVE_LINE_LENGTH_LOW, + REG_VID_CHA_ACTIVE_LINE_LENGTH_HIGH), + regmap_reg_range(REG_VID_CHA_VERTICAL_DISPLAY_SIZE_LOW, + REG_VID_CHA_VERTICAL_DISPLAY_SIZE_HIGH), + regmap_reg_range(REG_VID_CHA_SYNC_DELAY_LOW, + REG_VID_CHA_SYNC_DELAY_HIGH), + regmap_reg_range(REG_VID_CHA_HSYNC_PULSE_WIDTH_LOW, + REG_VID_CHA_HSYNC_PULSE_WIDTH_HIGH), + regmap_reg_range(REG_VID_CHA_VSYNC_PULSE_WIDTH_LOW, + REG_VID_CHA_VSYNC_PULSE_WIDTH_HIGH), + regmap_reg_range(REG_VID_CHA_HORIZONTAL_BACK_PORCH, + REG_VID_CHA_HORIZONTAL_BACK_PORCH), + regmap_reg_range(REG_VID_CHA_VERTICAL_BACK_PORCH, + REG_VID_CHA_VERTICAL_BACK_PORCH), + regmap_reg_range(REG_VID_CHA_HORIZONTAL_FRONT_PORCH, + REG_VID_CHA_HORIZONTAL_FRONT_PORCH), + regmap_reg_range(REG_VID_CHA_VERTICAL_FRONT_PORCH, + REG_VID_CHA_VERTICAL_FRONT_PORCH), + regmap_reg_range(REG_VID_CHA_TEST_PATTERN, REG_VID_CHA_TEST_PATTERN), + regmap_reg_range(REG_IRQ_GLOBAL, REG_IRQ_EN), + regmap_reg_range(REG_IRQ_STAT, REG_IRQ_STAT), +}; + +static const struct regmap_access_table sn65dsi83_writeable_table = { + .yes_ranges = sn65dsi83_writeable_ranges, + .n_yes_ranges = ARRAY_SIZE(sn65dsi83_writeable_ranges), +}; + +static const struct regmap_range sn65dsi83_volatile_ranges[] = { + regmap_reg_range(REG_RC_RESET, REG_RC_RESET), + regmap_reg_range(REG_RC_LVDS_PLL, REG_RC_LVDS_PLL), + regmap_reg_range(REG_IRQ_STAT, REG_IRQ_STAT), +}; + +static const struct regmap_access_table sn65dsi83_volatile_table = { + .yes_ranges = sn65dsi83_volatile_ranges, + .n_yes_ranges = ARRAY_SIZE(sn65dsi83_volatile_ranges), +}; + +static const struct regmap_config sn65dsi83_regmap_config = { + .reg_bits = 8, + .val_bits = 8, + .rd_table = &sn65dsi83_readable_table, + .wr_table = &sn65dsi83_writeable_table, + .volatile_table = &sn65dsi83_volatile_table, + .cache_type = REGCACHE_RBTREE, + .max_register = REG_IRQ_STAT, +}; + +static struct sn65dsi83 *bridge_to_sn65dsi83(struct drm_bridge *bridge) +{ + return container_of(bridge, struct sn65dsi83, bridge); +} + +static int sn65dsi83_attach(struct drm_bridge *bridge, + enum drm_bridge_attach_flags flags) +{ + struct sn65dsi83 *ctx = bridge_to_sn65dsi83(bridge); + struct device *dev = ctx->dev; + struct mipi_dsi_device *dsi; + struct mipi_dsi_host *host; + int ret = 0; + + const struct mipi_dsi_device_info info = { + .type = "sn65dsi83", + .channel = 0, + .node = NULL, + }; + + host = of_find_mipi_dsi_host_by_node(ctx->host_node); + if (!host) { + dev_err(dev, "failed to find dsi host\n"); + return -EPROBE_DEFER; + } + + dsi = mipi_dsi_device_register_full(host, &info); + if (IS_ERR(dsi)) { + return dev_err_probe(dev, PTR_ERR(dsi), + "failed to create dsi device\n"); + } + + ctx->dsi = dsi; + + dsi->lanes = ctx->dsi_lanes; + dsi->format = MIPI_DSI_FMT_RGB888; + dsi->mode_flags = MIPI_DSI_MODE_VIDEO | MIPI_DSI_MODE_VIDEO_BURST; + + ret = mipi_dsi_attach(dsi); + if (ret < 0) { + dev_err(dev, "failed to attach dsi to host\n"); + goto err_dsi_attach; + } + + return drm_bridge_attach(bridge->encoder, ctx->panel_bridge, + &ctx->bridge, flags); + +err_dsi_attach: + mipi_dsi_device_unregister(dsi); + return ret; +} + +static void sn65dsi83_pre_enable(struct drm_bridge *bridge) +{ + struct sn65dsi83 *ctx = bridge_to_sn65dsi83(bridge); + + /* + * Reset the chip, pull EN line low for t_reset=10ms, + * then high for t_en=1ms. + */ + regcache_mark_dirty(ctx->regmap); + gpiod_set_value(ctx->enable_gpio, 0); + usleep_range(10000, 11000); + gpiod_set_value(ctx->enable_gpio, 1); + usleep_range(1000, 1100); +} + +static u8 sn65dsi83_get_lvds_range(struct sn65dsi83 *ctx) +{ + /* + * The encoding of the LVDS_CLK_RANGE is as follows: + * 000 - 25 MHz <= LVDS_CLK < 37.5 MHz + * 001 - 37.5 MHz <= LVDS_CLK < 62.5 MHz + * 010 - 62.5 MHz <= LVDS_CLK < 87.5 MHz + * 011 - 87.5 MHz <= LVDS_CLK < 112.5 MHz + * 100 - 112.5 MHz <= LVDS_CLK < 137.5 MHz + * 101 - 137.5 MHz <= LVDS_CLK <= 154 MHz + * which is a range of 12.5MHz..162.5MHz in 50MHz steps, except that + * the ends of the ranges are clamped to the supported range. Since + * sn65dsi83_mode_valid() already filters the valid modes and limits + * the clock to 25..154 MHz, the range calculation can be simplified + * as follows: + */ + int mode_clock = ctx->mode.clock; + + if (ctx->lvds_dual_link) + mode_clock /= 2; + + return (mode_clock - 12500) / 25000; +} + +static u8 sn65dsi83_get_dsi_range(struct sn65dsi83 *ctx) +{ + /* + * The encoding of the CHA_DSI_CLK_RANGE is as follows: + * 0x00 through 0x07 - Reserved + * 0x08 - 40 <= DSI_CLK < 45 MHz + * 0x09 - 45 <= DSI_CLK < 50 MHz + * ... + * 0x63 - 495 <= DSI_CLK < 500 MHz + * 0x64 - 500 MHz + * 0x65 through 0xFF - Reserved + * which is DSI clock in 5 MHz steps, clamped to 40..500 MHz. + * The DSI clock are calculated as: + * DSI_CLK = mode clock * bpp / dsi_data_lanes / 2 + * the 2 is there because the bus is DDR. + */ + return DIV_ROUND_UP(clamp((unsigned int)ctx->mode.clock * + mipi_dsi_pixel_format_to_bpp(ctx->dsi->format) / + ctx->dsi_lanes / 2, 40000U, 500000U), 5000U); +} + +static u8 sn65dsi83_get_dsi_div(struct sn65dsi83 *ctx) +{ + /* The divider is (DSI_CLK / LVDS_CLK) - 1, which really is: */ + unsigned int dsi_div = mipi_dsi_pixel_format_to_bpp(ctx->dsi->format); + + dsi_div /= ctx->dsi_lanes; + + if (!ctx->lvds_dual_link) + dsi_div /= 2; + + return dsi_div - 1; +} + +static void sn65dsi83_enable(struct drm_bridge *bridge) +{ + struct sn65dsi83 *ctx = bridge_to_sn65dsi83(bridge); + unsigned int pval; + u16 val; + int ret; + + /* Clear reset, disable PLL */ + regmap_write(ctx->regmap, REG_RC_RESET, 0x00); + regmap_write(ctx->regmap, REG_RC_PLL_EN, 0x00); + + /* Reference clock derived from DSI link clock. */ + regmap_write(ctx->regmap, REG_RC_LVDS_PLL, + REG_RC_LVDS_PLL_LVDS_CLK_RANGE(sn65dsi83_get_lvds_range(ctx)) | + REG_RC_LVDS_PLL_HS_CLK_SRC_DPHY); + regmap_write(ctx->regmap, REG_DSI_CLK, + REG_DSI_CLK_CHA_DSI_CLK_RANGE(sn65dsi83_get_dsi_range(ctx))); + regmap_write(ctx->regmap, REG_RC_DSI_CLK, + REG_RC_DSI_CLK_DSI_CLK_DIVIDER(sn65dsi83_get_dsi_div(ctx))); + + /* Set number of DSI lanes and LVDS link config. */ + regmap_write(ctx->regmap, REG_DSI_LANE, + REG_DSI_LANE_DSI_CHANNEL_MODE_SINGLE | + REG_DSI_LANE_CHA_DSI_LANES(~(ctx->dsi_lanes - 1)) | + /* CHB is DSI85-only, set to default on DSI83/DSI84 */ + REG_DSI_LANE_CHB_DSI_LANES(3)); + /* No equalization. */ + regmap_write(ctx->regmap, REG_DSI_EQ, 0x00); + + /* Set up sync signal polarity. */ + val = (ctx->mode.flags & DRM_MODE_FLAG_NHSYNC ? + REG_LVDS_FMT_HS_NEG_POLARITY : 0) | + (ctx->mode.flags & DRM_MODE_FLAG_NVSYNC ? + REG_LVDS_FMT_VS_NEG_POLARITY : 0); + + /* Set up bits-per-pixel, 18bpp or 24bpp. */ + if (ctx->lvds_format_24bpp) { + val |= REG_LVDS_FMT_CHA_24BPP_MODE; + if (ctx->lvds_dual_link) + val |= REG_LVDS_FMT_CHB_24BPP_MODE; + } + + /* Set up LVDS format, JEIDA/Format 1 or SPWG/Format 2 */ + if (ctx->lvds_format_jeida) { + val |= REG_LVDS_FMT_CHA_24BPP_FORMAT1; + if (ctx->lvds_dual_link) + val |= REG_LVDS_FMT_CHB_24BPP_FORMAT1; + } + + /* Set up LVDS output config (DSI84,DSI85) */ + if (!ctx->lvds_dual_link) + val |= REG_LVDS_FMT_LVDS_LINK_CFG; + + regmap_write(ctx->regmap, REG_LVDS_FMT, val); + regmap_write(ctx->regmap, REG_LVDS_VCOM, 0x05); + regmap_write(ctx->regmap, REG_LVDS_LANE, + (ctx->lvds_dual_link_even_odd_swap ? + REG_LVDS_LANE_EVEN_ODD_SWAP : 0) | + REG_LVDS_LANE_CHA_LVDS_TERM | + REG_LVDS_LANE_CHB_LVDS_TERM); + regmap_write(ctx->regmap, REG_LVDS_CM, 0x00); + + val = cpu_to_le16(ctx->mode.hdisplay); + regmap_bulk_write(ctx->regmap, REG_VID_CHA_ACTIVE_LINE_LENGTH_LOW, + &val, 2); + val = cpu_to_le16(ctx->mode.vdisplay); + regmap_bulk_write(ctx->regmap, REG_VID_CHA_VERTICAL_DISPLAY_SIZE_LOW, + &val, 2); + /* 32 + 1 pixel clock to ensure proper operation */ + val = cpu_to_le16(32 + 1); + regmap_bulk_write(ctx->regmap, REG_VID_CHA_SYNC_DELAY_LOW, &val, 2); + val = cpu_to_le16(ctx->mode.hsync_end - ctx->mode.hsync_start); + regmap_bulk_write(ctx->regmap, REG_VID_CHA_HSYNC_PULSE_WIDTH_LOW, + &val, 2); + val = cpu_to_le16(ctx->mode.vsync_end - ctx->mode.vsync_start); + regmap_bulk_write(ctx->regmap, REG_VID_CHA_VSYNC_PULSE_WIDTH_LOW, + &val, 2); + regmap_write(ctx->regmap, REG_VID_CHA_HORIZONTAL_BACK_PORCH, + ctx->mode.htotal - ctx->mode.hsync_end); + regmap_write(ctx->regmap, REG_VID_CHA_VERTICAL_BACK_PORCH, + ctx->mode.vtotal - ctx->mode.vsync_end); + regmap_write(ctx->regmap, REG_VID_CHA_HORIZONTAL_FRONT_PORCH, + ctx->mode.hsync_start - ctx->mode.hdisplay); + regmap_write(ctx->regmap, REG_VID_CHA_VERTICAL_FRONT_PORCH, + ctx->mode.vsync_start - ctx->mode.vdisplay); + regmap_write(ctx->regmap, REG_VID_CHA_TEST_PATTERN, 0x00); + + /* Enable PLL */ + regmap_write(ctx->regmap, REG_RC_PLL_EN, REG_RC_PLL_EN_PLL_EN); + usleep_range(3000, 4000); + ret = regmap_read_poll_timeout(ctx->regmap, REG_RC_LVDS_PLL, pval, + pval & REG_RC_LVDS_PLL_PLL_EN_STAT, + 1000, 100000); + if (ret) { + dev_err(ctx->dev, "failed to lock PLL, ret=%i\n", ret); + /* On failure, disable PLL again and exit. */ + regmap_write(ctx->regmap, REG_RC_PLL_EN, 0x00); + return; + } + + /* Trigger reset after CSR register update. */ + regmap_write(ctx->regmap, REG_RC_RESET, REG_RC_RESET_SOFT_RESET); + + /* Clear all errors that got asserted during initialization. */ + regmap_read(ctx->regmap, REG_IRQ_STAT, &pval); + regmap_write(ctx->regmap, REG_IRQ_STAT, pval); +} + +static void sn65dsi83_disable(struct drm_bridge *bridge) +{ + struct sn65dsi83 *ctx = bridge_to_sn65dsi83(bridge); + + /* Clear reset, disable PLL */ + regmap_write(ctx->regmap, REG_RC_RESET, 0x00); + regmap_write(ctx->regmap, REG_RC_PLL_EN, 0x00); +} + +static void sn65dsi83_post_disable(struct drm_bridge *bridge) +{ + struct sn65dsi83 *ctx = bridge_to_sn65dsi83(bridge); + + /* Put the chip in reset, pull EN line low. */ + gpiod_set_value(ctx->enable_gpio, 0); +} + +static enum drm_mode_status +sn65dsi83_mode_valid(struct drm_bridge *bridge, + const struct drm_display_info *info, + const struct drm_display_mode *mode) +{ + /* LVDS output clock range 25..154 MHz */ + if (mode->clock < 25000) + return MODE_CLOCK_LOW; + if (mode->clock > 154000) + return MODE_CLOCK_HIGH; + + return MODE_OK; +} + +static void sn65dsi83_mode_set(struct drm_bridge *bridge, + const struct drm_display_mode *mode, + const struct drm_display_mode *adj) +{ + struct sn65dsi83 *ctx = bridge_to_sn65dsi83(bridge); + + ctx->mode = *adj; +} + +static bool sn65dsi83_mode_fixup(struct drm_bridge *bridge, + const struct drm_display_mode *mode, + struct drm_display_mode *adj) +{ + struct sn65dsi83 *ctx = bridge_to_sn65dsi83(bridge); + u32 input_bus_format = MEDIA_BUS_FMT_RGB888_1X24; + struct drm_encoder *encoder = bridge->encoder; + struct drm_device *ddev = encoder->dev; + struct drm_connector *connector; + + /* The DSI format is always RGB888_1X24 */ + list_for_each_entry(connector, &ddev->mode_config.connector_list, head) { + switch (connector->display_info.bus_formats[0]) { + case MEDIA_BUS_FMT_RGB666_1X7X3_SPWG: + ctx->lvds_format_24bpp = false; + ctx->lvds_format_jeida = true; + break; + case MEDIA_BUS_FMT_RGB888_1X7X4_JEIDA: + ctx->lvds_format_24bpp = true; + ctx->lvds_format_jeida = true; + break; + case MEDIA_BUS_FMT_RGB888_1X7X4_SPWG: + ctx->lvds_format_24bpp = true; + ctx->lvds_format_jeida = false; + break; + default: + /* + * Some bridges still don't set the correct + * LVDS bus pixel format, use SPWG24 default + * format until those are fixed. + */ + ctx->lvds_format_24bpp = true; + ctx->lvds_format_jeida = false; + dev_warn(ctx->dev, + "Unsupported LVDS bus format 0x%04x, please check output bridge driver. Falling back to SPWG24.\n", + connector->display_info.bus_formats[0]); + break; + } + + drm_display_info_set_bus_formats(&connector->display_info, + &input_bus_format, 1); + } + + return true; +} + +static const struct drm_bridge_funcs sn65dsi83_funcs = { + .attach = sn65dsi83_attach, + .pre_enable = sn65dsi83_pre_enable, + .enable = sn65dsi83_enable, + .disable = sn65dsi83_disable, + .post_disable = sn65dsi83_post_disable, + .mode_valid = sn65dsi83_mode_valid, + .mode_set = sn65dsi83_mode_set, + .mode_fixup = sn65dsi83_mode_fixup, +}; + +static int sn65dsi83_parse_dt(struct sn65dsi83 *ctx, enum sn65dsi83_model model) +{ + struct drm_bridge *panel_bridge; + struct device *dev = ctx->dev; + struct device_node *endpoint; + struct drm_panel *panel; + int ret; + + endpoint = of_graph_get_endpoint_by_regs(dev->of_node, 0, 0); + ctx->dsi_lanes = of_property_count_u32_elems(endpoint, "data-lanes"); + ctx->host_node = of_graph_get_remote_port_parent(endpoint); + of_node_put(endpoint); + + if (ctx->dsi_lanes < 0 || ctx->dsi_lanes > 4) + return -EINVAL; + if (!ctx->host_node) + return -ENODEV; + + ctx->lvds_dual_link = false; + ctx->lvds_dual_link_even_odd_swap = false; + if (model != MODEL_SN65DSI83) { + struct device_node *port2, *port3; + int dual_link; + + port2 = of_graph_get_port_by_id(dev->of_node, 2); + port3 = of_graph_get_port_by_id(dev->of_node, 3); + dual_link = drm_of_lvds_get_dual_link_pixel_order(port2, port3); + of_node_put(port2); + of_node_put(port3); + + if (dual_link == DRM_LVDS_DUAL_LINK_ODD_EVEN_PIXELS) { + ctx->lvds_dual_link = true; + /* Odd pixels to LVDS Channel A, even pixels to B */ + ctx->lvds_dual_link_even_odd_swap = false; + } else if (dual_link == DRM_LVDS_DUAL_LINK_EVEN_ODD_PIXELS) { + ctx->lvds_dual_link = true; + /* Even pixels to LVDS Channel A, odd pixels to B */ + ctx->lvds_dual_link_even_odd_swap = true; + } + } + + ret = drm_of_find_panel_or_bridge(dev->of_node, 2, 0, &panel, &panel_bridge); + if (ret < 0) + return ret; + if (panel) { + panel_bridge = devm_drm_panel_bridge_add(dev, panel); + if (IS_ERR(panel_bridge)) + return PTR_ERR(panel_bridge); + } + + ctx->panel_bridge = panel_bridge; + + return 0; +} + +static int sn65dsi83_probe(struct i2c_client *client, + const struct i2c_device_id *id) +{ + struct device *dev = &client->dev; + enum sn65dsi83_model model; + struct sn65dsi83 *ctx; + int ret; + + ctx = devm_kzalloc(dev, sizeof(*ctx), GFP_KERNEL); + if (!ctx) + return -ENOMEM; + + ctx->dev = dev; + + if (dev->of_node) { + model = (enum sn65dsi83_model)(uintptr_t) + of_device_get_match_data(dev); + } else { + model = id->driver_data; + } + + ctx->enable_gpio = devm_gpiod_get(ctx->dev, "enable", GPIOD_OUT_LOW); + if (IS_ERR(ctx->enable_gpio)) + return PTR_ERR(ctx->enable_gpio); + + ret = sn65dsi83_parse_dt(ctx, model); + if (ret) + return ret; + + ctx->regmap = devm_regmap_init_i2c(client, &sn65dsi83_regmap_config); + if (IS_ERR(ctx->regmap)) + return PTR_ERR(ctx->regmap); + + dev_set_drvdata(dev, ctx); + i2c_set_clientdata(client, ctx); + + ctx->bridge.funcs = &sn65dsi83_funcs; + ctx->bridge.of_node = dev->of_node; + drm_bridge_add(&ctx->bridge); + + return 0; +} + +static int sn65dsi83_remove(struct i2c_client *client) +{ + struct sn65dsi83 *ctx = i2c_get_clientdata(client); + + mipi_dsi_detach(ctx->dsi); + mipi_dsi_device_unregister(ctx->dsi); + drm_bridge_remove(&ctx->bridge); + of_node_put(ctx->host_node); + + return 0; +} + +static struct i2c_device_id sn65dsi83_id[] = { + { "ti,sn65dsi83", MODEL_SN65DSI83 }, + { "ti,sn65dsi84", MODEL_SN65DSI84 }, + {}, +}; +MODULE_DEVICE_TABLE(i2c, sn65dsi83_id); + +static const struct of_device_id sn65dsi83_match_table[] = { + { .compatible = "ti,sn65dsi83", .data = (void *)MODEL_SN65DSI83 }, + { .compatible = "ti,sn65dsi84", .data = (void *)MODEL_SN65DSI84 }, + {}, +}; +MODULE_DEVICE_TABLE(of, sn65dsi83_match_table); + +static struct i2c_driver sn65dsi83_driver = { + .probe = sn65dsi83_probe, + .remove = sn65dsi83_remove, + .id_table = sn65dsi83_id, + .driver = { + .name = "sn65dsi83", + .of_match_table = sn65dsi83_match_table, + }, +}; +module_i2c_driver(sn65dsi83_driver); + +MODULE_AUTHOR("Marek Vasut <marex@denx.de>"); +MODULE_DESCRIPTION("TI SN65DSI83 DSI to LVDS bridge driver"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/gpu/drm/drm_cache.c b/drivers/gpu/drm/drm_cache.c index 79a50ef1250f..546599f19a93 100644 --- a/drivers/gpu/drm/drm_cache.c +++ b/drivers/gpu/drm/drm_cache.c @@ -28,6 +28,7 @@ * Authors: Thomas Hellström <thomas-at-tungstengraphics-dot-com> */ +#include <linux/dma-buf-map.h> #include <linux/export.h> #include <linux/highmem.h> #include <linux/mem_encrypt.h> @@ -35,6 +36,9 @@ #include <drm/drm_cache.h> +/* A small bounce buffer that fits on the stack. */ +#define MEMCPY_BOUNCE_SIZE 128 + #if defined(CONFIG_X86) #include <asm/smp.h> @@ -209,3 +213,147 @@ bool drm_need_swiotlb(int dma_bits) return max_iomem > ((u64)1 << dma_bits); } EXPORT_SYMBOL(drm_need_swiotlb); + +static void memcpy_fallback(struct dma_buf_map *dst, + const struct dma_buf_map *src, + unsigned long len) +{ + if (!dst->is_iomem && !src->is_iomem) { + memcpy(dst->vaddr, src->vaddr, len); + } else if (!src->is_iomem) { + dma_buf_map_memcpy_to(dst, src->vaddr, len); + } else if (!dst->is_iomem) { + memcpy_fromio(dst->vaddr, src->vaddr_iomem, len); + } else { + /* + * Bounce size is not performance tuned, but using a + * bounce buffer like this is significantly faster than + * resorting to ioreadxx() + iowritexx(). + */ + char bounce[MEMCPY_BOUNCE_SIZE]; + void __iomem *_src = src->vaddr_iomem; + void __iomem *_dst = dst->vaddr_iomem; + + while (len >= MEMCPY_BOUNCE_SIZE) { + memcpy_fromio(bounce, _src, MEMCPY_BOUNCE_SIZE); + memcpy_toio(_dst, bounce, MEMCPY_BOUNCE_SIZE); + _src += MEMCPY_BOUNCE_SIZE; + _dst += MEMCPY_BOUNCE_SIZE; + len -= MEMCPY_BOUNCE_SIZE; + } + if (len) { + memcpy_fromio(bounce, _src, MEMCPY_BOUNCE_SIZE); + memcpy_toio(_dst, bounce, MEMCPY_BOUNCE_SIZE); + } + } +} + +#ifdef CONFIG_X86 + +static DEFINE_STATIC_KEY_FALSE(has_movntdqa); + +static void __memcpy_ntdqa(void *dst, const void *src, unsigned long len) +{ + kernel_fpu_begin(); + + while (len >= 4) { + asm("movntdqa (%0), %%xmm0\n" + "movntdqa 16(%0), %%xmm1\n" + "movntdqa 32(%0), %%xmm2\n" + "movntdqa 48(%0), %%xmm3\n" + "movaps %%xmm0, (%1)\n" + "movaps %%xmm1, 16(%1)\n" + "movaps %%xmm2, 32(%1)\n" + "movaps %%xmm3, 48(%1)\n" + :: "r" (src), "r" (dst) : "memory"); + src += 64; + dst += 64; + len -= 4; + } + while (len--) { + asm("movntdqa (%0), %%xmm0\n" + "movaps %%xmm0, (%1)\n" + :: "r" (src), "r" (dst) : "memory"); + src += 16; + dst += 16; + } + + kernel_fpu_end(); +} + +/* + * __drm_memcpy_from_wc copies @len bytes from @src to @dst using + * non-temporal instructions where available. Note that all arguments + * (@src, @dst) must be aligned to 16 bytes and @len must be a multiple + * of 16. + */ +static void __drm_memcpy_from_wc(void *dst, const void *src, unsigned long len) +{ + if (unlikely(((unsigned long)dst | (unsigned long)src | len) & 15)) + memcpy(dst, src, len); + else if (likely(len)) + __memcpy_ntdqa(dst, src, len >> 4); +} + +/** + * drm_memcpy_from_wc - Perform the fastest available memcpy from a source + * that may be WC. + * @dst: The destination pointer + * @src: The source pointer + * @len: The size of the area o transfer in bytes + * + * Tries an arch optimized memcpy for prefetching reading out of a WC region, + * and if no such beast is available, falls back to a normal memcpy. + */ +void drm_memcpy_from_wc(struct dma_buf_map *dst, + const struct dma_buf_map *src, + unsigned long len) +{ + if (WARN_ON(in_interrupt())) { + memcpy_fallback(dst, src, len); + return; + } + + if (static_branch_likely(&has_movntdqa)) { + __drm_memcpy_from_wc(dst->is_iomem ? + (void __force *)dst->vaddr_iomem : + dst->vaddr, + src->is_iomem ? + (void const __force *)src->vaddr_iomem : + src->vaddr, + len); + return; + } + + memcpy_fallback(dst, src, len); +} +EXPORT_SYMBOL(drm_memcpy_from_wc); + +/* + * drm_memcpy_init_early - One time initialization of the WC memcpy code + */ +void drm_memcpy_init_early(void) +{ + /* + * Some hypervisors (e.g. KVM) don't support VEX-prefix instructions + * emulation. So don't enable movntdqa in hypervisor guest. + */ + if (static_cpu_has(X86_FEATURE_XMM4_1) && + !boot_cpu_has(X86_FEATURE_HYPERVISOR)) + static_branch_enable(&has_movntdqa); +} +#else +void drm_memcpy_from_wc(struct dma_buf_map *dst, + const struct dma_buf_map *src, + unsigned long len) +{ + WARN_ON(in_interrupt()); + + memcpy_fallback(dst, src, len); +} +EXPORT_SYMBOL(drm_memcpy_from_wc); + +void drm_memcpy_init_early(void) +{ +} +#endif /* CONFIG_X86 */ diff --git a/drivers/gpu/drm/drm_drv.c b/drivers/gpu/drm/drm_drv.c index 3d8d68a98b95..8804ec7d3215 100644 --- a/drivers/gpu/drm/drm_drv.c +++ b/drivers/gpu/drm/drm_drv.c @@ -35,6 +35,7 @@ #include <linux/slab.h> #include <linux/srcu.h> +#include <drm/drm_cache.h> #include <drm/drm_client.h> #include <drm/drm_color_mgmt.h> #include <drm/drm_drv.h> @@ -1041,6 +1042,7 @@ static int __init drm_core_init(void) drm_connector_ida_init(); idr_init(&drm_minors_idr); + drm_memcpy_init_early(); ret = drm_sysfs_init(); if (ret < 0) { diff --git a/drivers/gpu/drm/drm_gem.c b/drivers/gpu/drm/drm_gem.c index 9989425e9875..d62fb1a3c916 100644 --- a/drivers/gpu/drm/drm_gem.c +++ b/drivers/gpu/drm/drm_gem.c @@ -770,8 +770,7 @@ long drm_gem_dma_resv_wait(struct drm_file *filep, u32 handle, return -EINVAL; } - ret = dma_resv_wait_timeout_rcu(obj->resv, wait_all, - true, timeout); + ret = dma_resv_wait_timeout(obj->resv, wait_all, true, timeout); if (ret == 0) ret = -ETIME; else if (ret > 0) @@ -1375,12 +1374,12 @@ int drm_gem_fence_array_add_implicit(struct xarray *fence_array, if (!write) { struct dma_fence *fence = - dma_resv_get_excl_rcu(obj->resv); + dma_resv_get_excl_unlocked(obj->resv); return drm_gem_fence_array_add(fence_array, fence); } - ret = dma_resv_get_fences_rcu(obj->resv, NULL, + ret = dma_resv_get_fences(obj->resv, NULL, &fence_count, &fences); if (ret || !fence_count) return ret; diff --git a/drivers/gpu/drm/drm_gem_atomic_helper.c b/drivers/gpu/drm/drm_gem_atomic_helper.c index a005c5a0ba46..a27135084ae5 100644 --- a/drivers/gpu/drm/drm_gem_atomic_helper.c +++ b/drivers/gpu/drm/drm_gem_atomic_helper.c @@ -147,7 +147,7 @@ int drm_gem_plane_helper_prepare_fb(struct drm_plane *plane, struct drm_plane_st return 0; obj = drm_gem_fb_get_obj(state->fb, 0); - fence = dma_resv_get_excl_rcu(obj->resv); + fence = dma_resv_get_excl_unlocked(obj->resv); drm_atomic_set_fence_for_plane(state, fence); return 0; diff --git a/drivers/gpu/drm/drm_gem_cma_helper.c b/drivers/gpu/drm/drm_gem_cma_helper.c index 4a24af2c5c43..d53388199f34 100644 --- a/drivers/gpu/drm/drm_gem_cma_helper.c +++ b/drivers/gpu/drm/drm_gem_cma_helper.c @@ -104,8 +104,7 @@ error: * @size: size of the object to allocate * * This function creates a CMA GEM object and allocates a contiguous chunk of - * memory as backing store. The backing memory has the writecombine attribute - * set. + * memory as backing store. * * Returns: * A struct drm_gem_cma_object * on success or an ERR_PTR()-encoded negative diff --git a/drivers/gpu/drm/drm_gem_ttm_helper.c b/drivers/gpu/drm/drm_gem_ttm_helper.c index b14bed8be771..ecf3d2a54a98 100644 --- a/drivers/gpu/drm/drm_gem_ttm_helper.c +++ b/drivers/gpu/drm/drm_gem_ttm_helper.c @@ -40,12 +40,12 @@ void drm_gem_ttm_print_info(struct drm_printer *p, unsigned int indent, const struct ttm_buffer_object *bo = drm_gem_ttm_of_gem(gem); drm_printf_indent(p, indent, "placement="); - drm_print_bits(p, bo->mem.placement, plname, ARRAY_SIZE(plname)); + drm_print_bits(p, bo->resource->placement, plname, ARRAY_SIZE(plname)); drm_printf(p, "\n"); - if (bo->mem.bus.is_iomem) + if (bo->resource->bus.is_iomem) drm_printf_indent(p, indent, "bus.offset=%lx\n", - (unsigned long)bo->mem.bus.offset); + (unsigned long)bo->resource->bus.offset); } EXPORT_SYMBOL(drm_gem_ttm_print_info); diff --git a/drivers/gpu/drm/drm_gem_vram_helper.c b/drivers/gpu/drm/drm_gem_vram_helper.c index 797200315854..2a1229b8364e 100644 --- a/drivers/gpu/drm/drm_gem_vram_helper.c +++ b/drivers/gpu/drm/drm_gem_vram_helper.c @@ -17,6 +17,8 @@ #include <drm/drm_prime.h> #include <drm/drm_simple_kms_helper.h> +#include <drm/ttm/ttm_range_manager.h> + static const struct drm_gem_object_funcs drm_gem_vram_object_funcs; /** @@ -248,10 +250,11 @@ EXPORT_SYMBOL(drm_gem_vram_put); static u64 drm_gem_vram_pg_offset(struct drm_gem_vram_object *gbo) { /* Keep TTM behavior for now, remove when drivers are audited */ - if (WARN_ON_ONCE(!gbo->bo.mem.mm_node)) + if (WARN_ON_ONCE(!gbo->bo.resource || + gbo->bo.resource->mem_type == TTM_PL_SYSTEM)) return 0; - return gbo->bo.mem.start; + return gbo->bo.resource->start; } /** diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gem.c b/drivers/gpu/drm/etnaviv/etnaviv_gem.c index db69f19ab5bc..b8fa6ed3dd73 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_gem.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_gem.c @@ -390,14 +390,12 @@ int etnaviv_gem_cpu_prep(struct drm_gem_object *obj, u32 op, } if (op & ETNA_PREP_NOSYNC) { - if (!dma_resv_test_signaled_rcu(obj->resv, - write)) + if (!dma_resv_test_signaled(obj->resv, write)) return -EBUSY; } else { unsigned long remain = etnaviv_timeout_to_jiffies(timeout); - ret = dma_resv_wait_timeout_rcu(obj->resv, - write, true, remain); + ret = dma_resv_wait_timeout(obj->resv, write, true, remain); if (ret <= 0) return ret == 0 ? -ETIMEDOUT : ret; } @@ -461,7 +459,7 @@ static void etnaviv_gem_describe(struct drm_gem_object *obj, struct seq_file *m) off, etnaviv_obj->vaddr, obj->size); rcu_read_lock(); - fobj = rcu_dereference(robj->fence); + fobj = dma_resv_shared_list(robj); if (fobj) { unsigned int i, shared_count = fobj->shared_count; @@ -471,7 +469,7 @@ static void etnaviv_gem_describe(struct drm_gem_object *obj, struct seq_file *m) } } - fence = rcu_dereference(robj->fence_excl); + fence = dma_resv_excl_fence(robj); if (fence) etnaviv_gem_describe_fence(fence, "Exclusive", m); rcu_read_unlock(); diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c b/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c index d05c35994579..d53856d7a747 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c @@ -189,13 +189,13 @@ static int submit_fence_sync(struct etnaviv_gem_submit *submit) continue; if (bo->flags & ETNA_SUBMIT_BO_WRITE) { - ret = dma_resv_get_fences_rcu(robj, &bo->excl, - &bo->nr_shared, - &bo->shared); + ret = dma_resv_get_fences(robj, &bo->excl, + &bo->nr_shared, + &bo->shared); if (ret) return ret; } else { - bo->excl = dma_resv_get_excl_rcu(robj); + bo->excl = dma_resv_get_excl_unlocked(robj); } } diff --git a/drivers/gpu/drm/exynos/exynos7_drm_decon.c b/drivers/gpu/drm/exynos/exynos7_drm_decon.c index 431c5d32f9a4..9b5e6f94e558 100644 --- a/drivers/gpu/drm/exynos/exynos7_drm_decon.c +++ b/drivers/gpu/drm/exynos/exynos7_drm_decon.c @@ -344,7 +344,7 @@ static void decon_win_set_colkey(struct decon_context *ctx, unsigned int win) } /** - * shadow_protect_win() - disable updating values from shadow registers at vsync + * decon_shadow_protect_win() - disable updating values from shadow registers at vsync * * @ctx: display and enhancement controller context * @win: window to protect registers for diff --git a/drivers/gpu/drm/exynos/exynos_drm_ipp.c b/drivers/gpu/drm/exynos/exynos_drm_ipp.c index 4f2b7551b251..9ae868935357 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_ipp.c +++ b/drivers/gpu/drm/exynos/exynos_drm_ipp.c @@ -88,7 +88,7 @@ void exynos_drm_ipp_unregister(struct device *dev, } /** - * exynos_drm_ipp_ioctl_get_res_ioctl - enumerate all ipp modules + * exynos_drm_ipp_get_res_ioctl - enumerate all ipp modules * @dev: DRM device * @data: ioctl data * @file_priv: DRM file info @@ -136,7 +136,7 @@ static inline struct exynos_drm_ipp *__ipp_get(uint32_t id) } /** - * exynos_drm_ipp_ioctl_get_caps - get ipp module capabilities and formats + * exynos_drm_ipp_get_caps_ioctl - get ipp module capabilities and formats * @dev: DRM device * @data: ioctl data * @file_priv: DRM file info diff --git a/drivers/gpu/drm/hyperv/Makefile b/drivers/gpu/drm/hyperv/Makefile new file mode 100644 index 000000000000..265f12f2c660 --- /dev/null +++ b/drivers/gpu/drm/hyperv/Makefile @@ -0,0 +1,8 @@ +# SPDX-License-Identifier: GPL-2.0-only + +hyperv_drm-y := \ + hyperv_drm_drv.o \ + hyperv_drm_modeset.o \ + hyperv_drm_proto.o + +obj-$(CONFIG_DRM_HYPERV) += hyperv_drm.o diff --git a/drivers/gpu/drm/hyperv/hyperv_drm.h b/drivers/gpu/drm/hyperv/hyperv_drm.h new file mode 100644 index 000000000000..886add4f9cd0 --- /dev/null +++ b/drivers/gpu/drm/hyperv/hyperv_drm.h @@ -0,0 +1,52 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright 2021 Microsoft + */ + +#ifndef _HYPERV_DRM_H_ +#define _HYPERV_DRM_H_ + +#define VMBUS_MAX_PACKET_SIZE 0x4000 + +struct hyperv_drm_device { + /* drm */ + struct drm_device dev; + struct drm_simple_display_pipe pipe; + struct drm_connector connector; + + /* mode */ + u32 screen_width_max; + u32 screen_height_max; + u32 preferred_width; + u32 preferred_height; + u32 screen_depth; + + /* hw */ + struct resource *mem; + void __iomem *vram; + unsigned long fb_base; + unsigned long fb_size; + struct completion wait; + u32 synthvid_version; + u32 mmio_megabytes; + bool dirt_needed; + + u8 init_buf[VMBUS_MAX_PACKET_SIZE]; + u8 recv_buf[VMBUS_MAX_PACKET_SIZE]; + + struct hv_device *hdev; +}; + +#define to_hv(_dev) container_of(_dev, struct hyperv_drm_device, dev) + +/* hyperv_drm_modeset */ +int hyperv_mode_config_init(struct hyperv_drm_device *hv); + +/* hyperv_drm_proto */ +int hyperv_update_vram_location(struct hv_device *hdev, phys_addr_t vram_pp); +int hyperv_update_situation(struct hv_device *hdev, u8 active, u32 bpp, + u32 w, u32 h, u32 pitch); +int hyperv_update_dirt(struct hv_device *hdev, struct drm_rect *rect); +int hyperv_connect_vsp(struct hv_device *hdev); + +#endif diff --git a/drivers/gpu/drm/hyperv/hyperv_drm_drv.c b/drivers/gpu/drm/hyperv/hyperv_drm_drv.c new file mode 100644 index 000000000000..eb06c92c4bfd --- /dev/null +++ b/drivers/gpu/drm/hyperv/hyperv_drm_drv.c @@ -0,0 +1,311 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright 2021 Microsoft + */ + +#include <linux/efi.h> +#include <linux/hyperv.h> +#include <linux/module.h> +#include <linux/pci.h> + +#include <drm/drm_aperture.h> +#include <drm/drm_atomic_helper.h> +#include <drm/drm_drv.h> +#include <drm/drm_fb_helper.h> +#include <drm/drm_gem_shmem_helper.h> +#include <drm/drm_simple_kms_helper.h> + +#include "hyperv_drm.h" + +#define DRIVER_NAME "hyperv_drm" +#define DRIVER_DESC "DRM driver for Hyper-V synthetic video device" +#define DRIVER_DATE "2020" +#define DRIVER_MAJOR 1 +#define DRIVER_MINOR 0 + +#define PCI_VENDOR_ID_MICROSOFT 0x1414 +#define PCI_DEVICE_ID_HYPERV_VIDEO 0x5353 + +DEFINE_DRM_GEM_FOPS(hv_fops); + +static struct drm_driver hyperv_driver = { + .driver_features = DRIVER_MODESET | DRIVER_GEM | DRIVER_ATOMIC, + + .name = DRIVER_NAME, + .desc = DRIVER_DESC, + .date = DRIVER_DATE, + .major = DRIVER_MAJOR, + .minor = DRIVER_MINOR, + + .fops = &hv_fops, + DRM_GEM_SHMEM_DRIVER_OPS, +}; + +static int hyperv_pci_probe(struct pci_dev *pdev, + const struct pci_device_id *ent) +{ + return 0; +} + +static void hyperv_pci_remove(struct pci_dev *pdev) +{ +} + +static const struct pci_device_id hyperv_pci_tbl[] = { + { + .vendor = PCI_VENDOR_ID_MICROSOFT, + .device = PCI_DEVICE_ID_HYPERV_VIDEO, + }, + { /* end of list */ } +}; + +/* + * PCI stub to support gen1 VM. + */ +static struct pci_driver hyperv_pci_driver = { + .name = KBUILD_MODNAME, + .id_table = hyperv_pci_tbl, + .probe = hyperv_pci_probe, + .remove = hyperv_pci_remove, +}; + +static int hyperv_setup_gen1(struct hyperv_drm_device *hv) +{ + struct drm_device *dev = &hv->dev; + struct pci_dev *pdev; + int ret; + + pdev = pci_get_device(PCI_VENDOR_ID_MICROSOFT, + PCI_DEVICE_ID_HYPERV_VIDEO, NULL); + if (!pdev) { + drm_err(dev, "Unable to find PCI Hyper-V video\n"); + return -ENODEV; + } + + ret = drm_aperture_remove_conflicting_pci_framebuffers(pdev, "hypervdrmfb"); + if (ret) { + drm_err(dev, "Not able to remove boot fb\n"); + return ret; + } + + if (pci_request_region(pdev, 0, DRIVER_NAME) != 0) + drm_warn(dev, "Cannot request framebuffer, boot fb still active?\n"); + + if ((pdev->resource[0].flags & IORESOURCE_MEM) == 0) { + drm_err(dev, "Resource at bar 0 is not IORESOURCE_MEM\n"); + ret = -ENODEV; + goto error; + } + + hv->fb_base = pci_resource_start(pdev, 0); + hv->fb_size = pci_resource_len(pdev, 0); + if (!hv->fb_base) { + drm_err(dev, "Resource not available\n"); + ret = -ENODEV; + goto error; + } + + hv->fb_size = min(hv->fb_size, + (unsigned long)(hv->mmio_megabytes * 1024 * 1024)); + hv->vram = devm_ioremap(&pdev->dev, hv->fb_base, hv->fb_size); + if (!hv->vram) { + drm_err(dev, "Failed to map vram\n"); + ret = -ENOMEM; + } + +error: + pci_dev_put(pdev); + return ret; +} + +static int hyperv_setup_gen2(struct hyperv_drm_device *hv, + struct hv_device *hdev) +{ + struct drm_device *dev = &hv->dev; + int ret; + + drm_aperture_remove_conflicting_framebuffers(screen_info.lfb_base, + screen_info.lfb_size, + false, + "hypervdrmfb"); + + hv->fb_size = (unsigned long)hv->mmio_megabytes * 1024 * 1024; + + ret = vmbus_allocate_mmio(&hv->mem, hdev, 0, -1, hv->fb_size, 0x100000, + true); + if (ret) { + drm_err(dev, "Failed to allocate mmio\n"); + return -ENOMEM; + } + + /* + * Map the VRAM cacheable for performance. This is also required for VM + * connect to display properly for ARM64 Linux VM, as the host also maps + * the VRAM cacheable. + */ + hv->vram = ioremap_cache(hv->mem->start, hv->fb_size); + if (!hv->vram) { + drm_err(dev, "Failed to map vram\n"); + ret = -ENOMEM; + goto error; + } + + hv->fb_base = hv->mem->start; + return 0; + +error: + vmbus_free_mmio(hv->mem->start, hv->fb_size); + return ret; +} + +static int hyperv_vmbus_probe(struct hv_device *hdev, + const struct hv_vmbus_device_id *dev_id) +{ + struct hyperv_drm_device *hv; + struct drm_device *dev; + int ret; + + hv = devm_drm_dev_alloc(&hdev->device, &hyperv_driver, + struct hyperv_drm_device, dev); + if (IS_ERR(hv)) + return PTR_ERR(hv); + + dev = &hv->dev; + init_completion(&hv->wait); + hv_set_drvdata(hdev, hv); + hv->hdev = hdev; + + ret = hyperv_connect_vsp(hdev); + if (ret) { + drm_err(dev, "Failed to connect to vmbus.\n"); + goto err_hv_set_drv_data; + } + + if (efi_enabled(EFI_BOOT)) + ret = hyperv_setup_gen2(hv, hdev); + else + ret = hyperv_setup_gen1(hv); + + if (ret) + goto err_vmbus_close; + + /* + * Should be done only once during init and resume. Failing to update + * vram location is not fatal. Device will update dirty area till + * preferred resolution only. + */ + ret = hyperv_update_vram_location(hdev, hv->fb_base); + if (ret) + drm_warn(dev, "Failed to update vram location.\n"); + + hv->dirt_needed = true; + + ret = hyperv_mode_config_init(hv); + if (ret) + goto err_vmbus_close; + + ret = drm_dev_register(dev, 0); + if (ret) { + drm_err(dev, "Failed to register drm driver.\n"); + goto err_vmbus_close; + } + + drm_fbdev_generic_setup(dev, 0); + + return 0; + +err_vmbus_close: + vmbus_close(hdev->channel); +err_hv_set_drv_data: + hv_set_drvdata(hdev, NULL); + return ret; +} + +static int hyperv_vmbus_remove(struct hv_device *hdev) +{ + struct drm_device *dev = hv_get_drvdata(hdev); + struct hyperv_drm_device *hv = to_hv(dev); + + drm_dev_unplug(dev); + drm_atomic_helper_shutdown(dev); + vmbus_close(hdev->channel); + hv_set_drvdata(hdev, NULL); + vmbus_free_mmio(hv->mem->start, hv->fb_size); + + return 0; +} + +static int hyperv_vmbus_suspend(struct hv_device *hdev) +{ + struct drm_device *dev = hv_get_drvdata(hdev); + int ret; + + ret = drm_mode_config_helper_suspend(dev); + if (ret) + return ret; + + vmbus_close(hdev->channel); + + return 0; +} + +static int hyperv_vmbus_resume(struct hv_device *hdev) +{ + struct drm_device *dev = hv_get_drvdata(hdev); + struct hyperv_drm_device *hv = to_hv(dev); + int ret; + + ret = hyperv_connect_vsp(hdev); + if (ret) + return ret; + + ret = hyperv_update_vram_location(hdev, hv->fb_base); + if (ret) + return ret; + + return drm_mode_config_helper_resume(dev); +} + +static const struct hv_vmbus_device_id hyperv_vmbus_tbl[] = { + /* Synthetic Video Device GUID */ + {HV_SYNTHVID_GUID}, + {} +}; + +static struct hv_driver hyperv_hv_driver = { + .name = KBUILD_MODNAME, + .id_table = hyperv_vmbus_tbl, + .probe = hyperv_vmbus_probe, + .remove = hyperv_vmbus_remove, + .suspend = hyperv_vmbus_suspend, + .resume = hyperv_vmbus_resume, + .driver = { + .probe_type = PROBE_PREFER_ASYNCHRONOUS, + }, +}; + +static int __init hyperv_init(void) +{ + int ret; + + ret = pci_register_driver(&hyperv_pci_driver); + if (ret != 0) + return ret; + + return vmbus_driver_register(&hyperv_hv_driver); +} + +static void __exit hyperv_exit(void) +{ + vmbus_driver_unregister(&hyperv_hv_driver); + pci_unregister_driver(&hyperv_pci_driver); +} + +module_init(hyperv_init); +module_exit(hyperv_exit); + +MODULE_DEVICE_TABLE(pci, hyperv_pci_tbl); +MODULE_DEVICE_TABLE(vmbus, hyperv_vmbus_tbl); +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Deepak Rawat <drawat.floss@gmail.com>"); +MODULE_DESCRIPTION("DRM driver for Hyper-V synthetic video device"); diff --git a/drivers/gpu/drm/hyperv/hyperv_drm_modeset.c b/drivers/gpu/drm/hyperv/hyperv_drm_modeset.c new file mode 100644 index 000000000000..02718e3e859e --- /dev/null +++ b/drivers/gpu/drm/hyperv/hyperv_drm_modeset.c @@ -0,0 +1,231 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright 2021 Microsoft + */ + +#include <linux/hyperv.h> + +#include <drm/drm_damage_helper.h> +#include <drm/drm_drv.h> +#include <drm/drm_fb_helper.h> +#include <drm/drm_format_helper.h> +#include <drm/drm_fourcc.h> +#include <drm/drm_gem_atomic_helper.h> +#include <drm/drm_gem_framebuffer_helper.h> +#include <drm/drm_gem_shmem_helper.h> +#include <drm/drm_probe_helper.h> +#include <drm/drm_simple_kms_helper.h> + +#include "hyperv_drm.h" + +static int hyperv_blit_to_vram_rect(struct drm_framebuffer *fb, + const struct dma_buf_map *map, + struct drm_rect *rect) +{ + struct hyperv_drm_device *hv = to_hv(fb->dev); + void *vmap = map->vaddr; /* TODO: Use mapping abstraction properly */ + int idx; + + if (!drm_dev_enter(&hv->dev, &idx)) + return -ENODEV; + + drm_fb_memcpy_dstclip(hv->vram, fb->pitches[0], vmap, fb, rect); + drm_dev_exit(idx); + + return 0; +} + +static int hyperv_blit_to_vram_fullscreen(struct drm_framebuffer *fb, const struct dma_buf_map *map) +{ + struct drm_rect fullscreen = { + .x1 = 0, + .x2 = fb->width, + .y1 = 0, + .y2 = fb->height, + }; + return hyperv_blit_to_vram_rect(fb, map, &fullscreen); +} + +static int hyperv_connector_get_modes(struct drm_connector *connector) +{ + struct hyperv_drm_device *hv = to_hv(connector->dev); + int count; + + count = drm_add_modes_noedid(connector, + connector->dev->mode_config.max_width, + connector->dev->mode_config.max_height); + drm_set_preferred_mode(connector, hv->preferred_width, + hv->preferred_height); + + return count; +} + +static const struct drm_connector_helper_funcs hyperv_connector_helper_funcs = { + .get_modes = hyperv_connector_get_modes, +}; + +static const struct drm_connector_funcs hyperv_connector_funcs = { + .fill_modes = drm_helper_probe_single_connector_modes, + .destroy = drm_connector_cleanup, + .reset = drm_atomic_helper_connector_reset, + .atomic_duplicate_state = drm_atomic_helper_connector_duplicate_state, + .atomic_destroy_state = drm_atomic_helper_connector_destroy_state, +}; + +static inline int hyperv_conn_init(struct hyperv_drm_device *hv) +{ + drm_connector_helper_add(&hv->connector, &hyperv_connector_helper_funcs); + return drm_connector_init(&hv->dev, &hv->connector, + &hyperv_connector_funcs, + DRM_MODE_CONNECTOR_VIRTUAL); +} + +static int hyperv_check_size(struct hyperv_drm_device *hv, int w, int h, + struct drm_framebuffer *fb) +{ + u32 pitch = w * (hv->screen_depth / 8); + + if (fb) + pitch = fb->pitches[0]; + + if (pitch * h > hv->fb_size) + return -EINVAL; + + return 0; +} + +static void hyperv_pipe_enable(struct drm_simple_display_pipe *pipe, + struct drm_crtc_state *crtc_state, + struct drm_plane_state *plane_state) +{ + struct hyperv_drm_device *hv = to_hv(pipe->crtc.dev); + struct drm_shadow_plane_state *shadow_plane_state = to_drm_shadow_plane_state(plane_state); + + hyperv_update_situation(hv->hdev, 1, hv->screen_depth, + crtc_state->mode.hdisplay, + crtc_state->mode.vdisplay, + plane_state->fb->pitches[0]); + hyperv_blit_to_vram_fullscreen(plane_state->fb, &shadow_plane_state->map[0]); +} + +static int hyperv_pipe_check(struct drm_simple_display_pipe *pipe, + struct drm_plane_state *plane_state, + struct drm_crtc_state *crtc_state) +{ + struct hyperv_drm_device *hv = to_hv(pipe->crtc.dev); + struct drm_framebuffer *fb = plane_state->fb; + + if (fb->format->format != DRM_FORMAT_XRGB8888) + return -EINVAL; + + if (fb->pitches[0] * fb->height > hv->fb_size) + return -EINVAL; + + return 0; +} + +static void hyperv_pipe_update(struct drm_simple_display_pipe *pipe, + struct drm_plane_state *old_state) +{ + struct hyperv_drm_device *hv = to_hv(pipe->crtc.dev); + struct drm_plane_state *state = pipe->plane.state; + struct drm_shadow_plane_state *shadow_plane_state = to_drm_shadow_plane_state(state); + struct drm_rect rect; + + if (drm_atomic_helper_damage_merged(old_state, state, &rect)) { + hyperv_blit_to_vram_rect(state->fb, &shadow_plane_state->map[0], &rect); + hyperv_update_dirt(hv->hdev, &rect); + } +} + +static const struct drm_simple_display_pipe_funcs hyperv_pipe_funcs = { + .enable = hyperv_pipe_enable, + .check = hyperv_pipe_check, + .update = hyperv_pipe_update, + DRM_GEM_SIMPLE_DISPLAY_PIPE_SHADOW_PLANE_FUNCS, +}; + +static const uint32_t hyperv_formats[] = { + DRM_FORMAT_XRGB8888, +}; + +static const uint64_t hyperv_modifiers[] = { + DRM_FORMAT_MOD_LINEAR, + DRM_FORMAT_MOD_INVALID +}; + +static inline int hyperv_pipe_init(struct hyperv_drm_device *hv) +{ + int ret; + + ret = drm_simple_display_pipe_init(&hv->dev, + &hv->pipe, + &hyperv_pipe_funcs, + hyperv_formats, + ARRAY_SIZE(hyperv_formats), + NULL, + &hv->connector); + if (ret) + return ret; + + drm_plane_enable_fb_damage_clips(&hv->pipe.plane); + + return 0; +} + +static enum drm_mode_status +hyperv_mode_valid(struct drm_device *dev, + const struct drm_display_mode *mode) +{ + struct hyperv_drm_device *hv = to_hv(dev); + + if (hyperv_check_size(hv, mode->hdisplay, mode->vdisplay, NULL)) + return MODE_BAD; + + return MODE_OK; +} + +static const struct drm_mode_config_funcs hyperv_mode_config_funcs = { + .fb_create = drm_gem_fb_create_with_dirty, + .mode_valid = hyperv_mode_valid, + .atomic_check = drm_atomic_helper_check, + .atomic_commit = drm_atomic_helper_commit, +}; + +int hyperv_mode_config_init(struct hyperv_drm_device *hv) +{ + struct drm_device *dev = &hv->dev; + int ret; + + ret = drmm_mode_config_init(dev); + if (ret) { + drm_err(dev, "Failed to initialized mode setting.\n"); + return ret; + } + + dev->mode_config.min_width = 0; + dev->mode_config.min_height = 0; + dev->mode_config.max_width = hv->screen_width_max; + dev->mode_config.max_height = hv->screen_height_max; + + dev->mode_config.preferred_depth = hv->screen_depth; + dev->mode_config.prefer_shadow = 0; + + dev->mode_config.funcs = &hyperv_mode_config_funcs; + + ret = hyperv_conn_init(hv); + if (ret) { + drm_err(dev, "Failed to initialized connector.\n"); + return ret; + } + + ret = hyperv_pipe_init(hv); + if (ret) { + drm_err(dev, "Failed to initialized pipe.\n"); + return ret; + } + + drm_mode_config_reset(dev); + + return 0; +} diff --git a/drivers/gpu/drm/hyperv/hyperv_drm_proto.c b/drivers/gpu/drm/hyperv/hyperv_drm_proto.c new file mode 100644 index 000000000000..6d4bdccfbd1a --- /dev/null +++ b/drivers/gpu/drm/hyperv/hyperv_drm_proto.c @@ -0,0 +1,485 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright 2021 Microsoft + * + * Portions of this code is derived from hyperv_fb.c + */ + +#include <linux/hyperv.h> + +#include <drm/drm_print.h> +#include <drm/drm_simple_kms_helper.h> + +#include "hyperv_drm.h" + +#define VMBUS_RING_BUFSIZE (256 * 1024) +#define VMBUS_VSP_TIMEOUT (10 * HZ) + +#define SYNTHVID_VERSION(major, minor) ((minor) << 16 | (major)) +#define SYNTHVID_VER_GET_MAJOR(ver) (ver & 0x0000ffff) +#define SYNTHVID_VER_GET_MINOR(ver) ((ver & 0xffff0000) >> 16) +#define SYNTHVID_VERSION_WIN7 SYNTHVID_VERSION(3, 0) +#define SYNTHVID_VERSION_WIN8 SYNTHVID_VERSION(3, 2) +#define SYNTHVID_VERSION_WIN10 SYNTHVID_VERSION(3, 5) + +#define SYNTHVID_DEPTH_WIN7 16 +#define SYNTHVID_DEPTH_WIN8 32 +#define SYNTHVID_FB_SIZE_WIN7 (4 * 1024 * 1024) +#define SYNTHVID_FB_SIZE_WIN8 (8 * 1024 * 1024) +#define SYNTHVID_WIDTH_MAX_WIN7 1600 +#define SYNTHVID_HEIGHT_MAX_WIN7 1200 + +enum pipe_msg_type { + PIPE_MSG_INVALID, + PIPE_MSG_DATA, + PIPE_MSG_MAX +}; + +enum synthvid_msg_type { + SYNTHVID_ERROR = 0, + SYNTHVID_VERSION_REQUEST = 1, + SYNTHVID_VERSION_RESPONSE = 2, + SYNTHVID_VRAM_LOCATION = 3, + SYNTHVID_VRAM_LOCATION_ACK = 4, + SYNTHVID_SITUATION_UPDATE = 5, + SYNTHVID_SITUATION_UPDATE_ACK = 6, + SYNTHVID_POINTER_POSITION = 7, + SYNTHVID_POINTER_SHAPE = 8, + SYNTHVID_FEATURE_CHANGE = 9, + SYNTHVID_DIRT = 10, + SYNTHVID_RESOLUTION_REQUEST = 13, + SYNTHVID_RESOLUTION_RESPONSE = 14, + + SYNTHVID_MAX = 15 +}; + +struct pipe_msg_hdr { + u32 type; + u32 size; /* size of message after this field */ +} __packed; + +struct hvd_screen_info { + u16 width; + u16 height; +} __packed; + +struct synthvid_msg_hdr { + u32 type; + u32 size; /* size of this header + payload after this field */ +} __packed; + +struct synthvid_version_req { + u32 version; +} __packed; + +struct synthvid_version_resp { + u32 version; + u8 is_accepted; + u8 max_video_outputs; +} __packed; + +struct synthvid_vram_location { + u64 user_ctx; + u8 is_vram_gpa_specified; + u64 vram_gpa; +} __packed; + +struct synthvid_vram_location_ack { + u64 user_ctx; +} __packed; + +struct video_output_situation { + u8 active; + u32 vram_offset; + u8 depth_bits; + u32 width_pixels; + u32 height_pixels; + u32 pitch_bytes; +} __packed; + +struct synthvid_situation_update { + u64 user_ctx; + u8 video_output_count; + struct video_output_situation video_output[1]; +} __packed; + +struct synthvid_situation_update_ack { + u64 user_ctx; +} __packed; + +struct synthvid_pointer_position { + u8 is_visible; + u8 video_output; + s32 image_x; + s32 image_y; +} __packed; + +#define SYNTHVID_CURSOR_MAX_X 96 +#define SYNTHVID_CURSOR_MAX_Y 96 +#define SYNTHVID_CURSOR_ARGB_PIXEL_SIZE 4 +#define SYNTHVID_CURSOR_MAX_SIZE (SYNTHVID_CURSOR_MAX_X * \ + SYNTHVID_CURSOR_MAX_Y * SYNTHVID_CURSOR_ARGB_PIXEL_SIZE) +#define SYNTHVID_CURSOR_COMPLETE (-1) + +struct synthvid_pointer_shape { + u8 part_idx; + u8 is_argb; + u32 width; /* SYNTHVID_CURSOR_MAX_X at most */ + u32 height; /* SYNTHVID_CURSOR_MAX_Y at most */ + u32 hot_x; /* hotspot relative to upper-left of pointer image */ + u32 hot_y; + u8 data[4]; +} __packed; + +struct synthvid_feature_change { + u8 is_dirt_needed; + u8 is_ptr_pos_needed; + u8 is_ptr_shape_needed; + u8 is_situ_needed; +} __packed; + +struct rect { + s32 x1, y1; /* top left corner */ + s32 x2, y2; /* bottom right corner, exclusive */ +} __packed; + +struct synthvid_dirt { + u8 video_output; + u8 dirt_count; + struct rect rect[1]; +} __packed; + +#define SYNTHVID_EDID_BLOCK_SIZE 128 +#define SYNTHVID_MAX_RESOLUTION_COUNT 64 + +struct synthvid_supported_resolution_req { + u8 maximum_resolution_count; +} __packed; + +struct synthvid_supported_resolution_resp { + u8 edid_block[SYNTHVID_EDID_BLOCK_SIZE]; + u8 resolution_count; + u8 default_resolution_index; + u8 is_standard; + struct hvd_screen_info supported_resolution[SYNTHVID_MAX_RESOLUTION_COUNT]; +} __packed; + +struct synthvid_msg { + struct pipe_msg_hdr pipe_hdr; + struct synthvid_msg_hdr vid_hdr; + union { + struct synthvid_version_req ver_req; + struct synthvid_version_resp ver_resp; + struct synthvid_vram_location vram; + struct synthvid_vram_location_ack vram_ack; + struct synthvid_situation_update situ; + struct synthvid_situation_update_ack situ_ack; + struct synthvid_pointer_position ptr_pos; + struct synthvid_pointer_shape ptr_shape; + struct synthvid_feature_change feature_chg; + struct synthvid_dirt dirt; + struct synthvid_supported_resolution_req resolution_req; + struct synthvid_supported_resolution_resp resolution_resp; + }; +} __packed; + +static inline bool hyperv_version_ge(u32 ver1, u32 ver2) +{ + if (SYNTHVID_VER_GET_MAJOR(ver1) > SYNTHVID_VER_GET_MAJOR(ver2) || + (SYNTHVID_VER_GET_MAJOR(ver1) == SYNTHVID_VER_GET_MAJOR(ver2) && + SYNTHVID_VER_GET_MINOR(ver1) >= SYNTHVID_VER_GET_MINOR(ver2))) + return true; + + return false; +} + +static inline int hyperv_sendpacket(struct hv_device *hdev, struct synthvid_msg *msg) +{ + static atomic64_t request_id = ATOMIC64_INIT(0); + struct hyperv_drm_device *hv = hv_get_drvdata(hdev); + int ret; + + msg->pipe_hdr.type = PIPE_MSG_DATA; + msg->pipe_hdr.size = msg->vid_hdr.size; + + ret = vmbus_sendpacket(hdev->channel, msg, + msg->vid_hdr.size + sizeof(struct pipe_msg_hdr), + atomic64_inc_return(&request_id), + VM_PKT_DATA_INBAND, 0); + + if (ret) + drm_err(&hv->dev, "Unable to send packet via vmbus\n"); + + return ret; +} + +static int hyperv_negotiate_version(struct hv_device *hdev, u32 ver) +{ + struct hyperv_drm_device *hv = hv_get_drvdata(hdev); + struct synthvid_msg *msg = (struct synthvid_msg *)hv->init_buf; + struct drm_device *dev = &hv->dev; + unsigned long t; + + memset(msg, 0, sizeof(struct synthvid_msg)); + msg->vid_hdr.type = SYNTHVID_VERSION_REQUEST; + msg->vid_hdr.size = sizeof(struct synthvid_msg_hdr) + + sizeof(struct synthvid_version_req); + msg->ver_req.version = ver; + hyperv_sendpacket(hdev, msg); + + t = wait_for_completion_timeout(&hv->wait, VMBUS_VSP_TIMEOUT); + if (!t) { + drm_err(dev, "Time out on waiting version response\n"); + return -ETIMEDOUT; + } + + if (!msg->ver_resp.is_accepted) { + drm_err(dev, "Version request not accepted\n"); + return -ENODEV; + } + + hv->synthvid_version = ver; + drm_info(dev, "Synthvid Version major %d, minor %d\n", + SYNTHVID_VER_GET_MAJOR(ver), SYNTHVID_VER_GET_MINOR(ver)); + + return 0; +} + +int hyperv_update_vram_location(struct hv_device *hdev, phys_addr_t vram_pp) +{ + struct hyperv_drm_device *hv = hv_get_drvdata(hdev); + struct synthvid_msg *msg = (struct synthvid_msg *)hv->init_buf; + struct drm_device *dev = &hv->dev; + unsigned long t; + + memset(msg, 0, sizeof(struct synthvid_msg)); + msg->vid_hdr.type = SYNTHVID_VRAM_LOCATION; + msg->vid_hdr.size = sizeof(struct synthvid_msg_hdr) + + sizeof(struct synthvid_vram_location); + msg->vram.user_ctx = vram_pp; + msg->vram.vram_gpa = vram_pp; + msg->vram.is_vram_gpa_specified = 1; + hyperv_sendpacket(hdev, msg); + + t = wait_for_completion_timeout(&hv->wait, VMBUS_VSP_TIMEOUT); + if (!t) { + drm_err(dev, "Time out on waiting vram location ack\n"); + return -ETIMEDOUT; + } + if (msg->vram_ack.user_ctx != vram_pp) { + drm_err(dev, "Unable to set VRAM location\n"); + return -ENODEV; + } + + return 0; +} + +int hyperv_update_situation(struct hv_device *hdev, u8 active, u32 bpp, + u32 w, u32 h, u32 pitch) +{ + struct synthvid_msg msg; + + memset(&msg, 0, sizeof(struct synthvid_msg)); + + msg.vid_hdr.type = SYNTHVID_SITUATION_UPDATE; + msg.vid_hdr.size = sizeof(struct synthvid_msg_hdr) + + sizeof(struct synthvid_situation_update); + msg.situ.user_ctx = 0; + msg.situ.video_output_count = 1; + msg.situ.video_output[0].active = active; + /* vram_offset should always be 0 */ + msg.situ.video_output[0].vram_offset = 0; + msg.situ.video_output[0].depth_bits = bpp; + msg.situ.video_output[0].width_pixels = w; + msg.situ.video_output[0].height_pixels = h; + msg.situ.video_output[0].pitch_bytes = pitch; + + hyperv_sendpacket(hdev, &msg); + + return 0; +} + +int hyperv_update_dirt(struct hv_device *hdev, struct drm_rect *rect) +{ + struct hyperv_drm_device *hv = hv_get_drvdata(hdev); + struct synthvid_msg msg; + + if (!hv->dirt_needed) + return 0; + + memset(&msg, 0, sizeof(struct synthvid_msg)); + + msg.vid_hdr.type = SYNTHVID_DIRT; + msg.vid_hdr.size = sizeof(struct synthvid_msg_hdr) + + sizeof(struct synthvid_dirt); + msg.dirt.video_output = 0; + msg.dirt.dirt_count = 1; + msg.dirt.rect[0].x1 = rect->x1; + msg.dirt.rect[0].y1 = rect->y1; + msg.dirt.rect[0].x2 = rect->x2; + msg.dirt.rect[0].y2 = rect->y2; + + hyperv_sendpacket(hdev, &msg); + + return 0; +} + +static int hyperv_get_supported_resolution(struct hv_device *hdev) +{ + struct hyperv_drm_device *hv = hv_get_drvdata(hdev); + struct synthvid_msg *msg = (struct synthvid_msg *)hv->init_buf; + struct drm_device *dev = &hv->dev; + unsigned long t; + u8 index; + int i; + + memset(msg, 0, sizeof(struct synthvid_msg)); + msg->vid_hdr.type = SYNTHVID_RESOLUTION_REQUEST; + msg->vid_hdr.size = sizeof(struct synthvid_msg_hdr) + + sizeof(struct synthvid_supported_resolution_req); + msg->resolution_req.maximum_resolution_count = + SYNTHVID_MAX_RESOLUTION_COUNT; + hyperv_sendpacket(hdev, msg); + + t = wait_for_completion_timeout(&hv->wait, VMBUS_VSP_TIMEOUT); + if (!t) { + drm_err(dev, "Time out on waiting resolution response\n"); + return -ETIMEDOUT; + } + + if (msg->resolution_resp.resolution_count == 0) { + drm_err(dev, "No supported resolutions\n"); + return -ENODEV; + } + + index = msg->resolution_resp.default_resolution_index; + if (index >= msg->resolution_resp.resolution_count) { + drm_err(dev, "Invalid resolution index: %d\n", index); + return -ENODEV; + } + + for (i = 0; i < msg->resolution_resp.resolution_count; i++) { + hv->screen_width_max = max_t(u32, hv->screen_width_max, + msg->resolution_resp.supported_resolution[i].width); + hv->screen_height_max = max_t(u32, hv->screen_height_max, + msg->resolution_resp.supported_resolution[i].height); + } + + hv->preferred_width = + msg->resolution_resp.supported_resolution[index].width; + hv->preferred_height = + msg->resolution_resp.supported_resolution[index].height; + + return 0; +} + +static void hyperv_receive_sub(struct hv_device *hdev) +{ + struct hyperv_drm_device *hv = hv_get_drvdata(hdev); + struct synthvid_msg *msg; + + if (!hv) + return; + + msg = (struct synthvid_msg *)hv->recv_buf; + + /* Complete the wait event */ + if (msg->vid_hdr.type == SYNTHVID_VERSION_RESPONSE || + msg->vid_hdr.type == SYNTHVID_RESOLUTION_RESPONSE || + msg->vid_hdr.type == SYNTHVID_VRAM_LOCATION_ACK) { + memcpy(hv->init_buf, msg, VMBUS_MAX_PACKET_SIZE); + complete(&hv->wait); + return; + } + + if (msg->vid_hdr.type == SYNTHVID_FEATURE_CHANGE) + hv->dirt_needed = msg->feature_chg.is_dirt_needed; +} + +static void hyperv_receive(void *ctx) +{ + struct hv_device *hdev = ctx; + struct hyperv_drm_device *hv = hv_get_drvdata(hdev); + struct synthvid_msg *recv_buf; + u32 bytes_recvd; + u64 req_id; + int ret; + + if (!hv) + return; + + recv_buf = (struct synthvid_msg *)hv->recv_buf; + + do { + ret = vmbus_recvpacket(hdev->channel, recv_buf, + VMBUS_MAX_PACKET_SIZE, + &bytes_recvd, &req_id); + if (bytes_recvd > 0 && + recv_buf->pipe_hdr.type == PIPE_MSG_DATA) + hyperv_receive_sub(hdev); + } while (bytes_recvd > 0 && ret == 0); +} + +int hyperv_connect_vsp(struct hv_device *hdev) +{ + struct hyperv_drm_device *hv = hv_get_drvdata(hdev); + struct drm_device *dev = &hv->dev; + int ret; + + ret = vmbus_open(hdev->channel, VMBUS_RING_BUFSIZE, VMBUS_RING_BUFSIZE, + NULL, 0, hyperv_receive, hdev); + if (ret) { + drm_err(dev, "Unable to open vmbus channel\n"); + return ret; + } + + /* Negotiate the protocol version with host */ + switch (vmbus_proto_version) { + case VERSION_WIN10: + case VERSION_WIN10_V5: + ret = hyperv_negotiate_version(hdev, SYNTHVID_VERSION_WIN10); + if (!ret) + break; + fallthrough; + case VERSION_WIN8: + case VERSION_WIN8_1: + ret = hyperv_negotiate_version(hdev, SYNTHVID_VERSION_WIN8); + if (!ret) + break; + fallthrough; + case VERSION_WS2008: + case VERSION_WIN7: + ret = hyperv_negotiate_version(hdev, SYNTHVID_VERSION_WIN7); + break; + default: + ret = hyperv_negotiate_version(hdev, SYNTHVID_VERSION_WIN10); + break; + } + + if (ret) { + drm_err(dev, "Synthetic video device version not accepted %d\n", ret); + goto error; + } + + if (hv->synthvid_version == SYNTHVID_VERSION_WIN7) + hv->screen_depth = SYNTHVID_DEPTH_WIN7; + else + hv->screen_depth = SYNTHVID_DEPTH_WIN8; + + if (hyperv_version_ge(hv->synthvid_version, SYNTHVID_VERSION_WIN10)) { + ret = hyperv_get_supported_resolution(hdev); + if (ret) + drm_err(dev, "Failed to get supported resolution from host, use default\n"); + } else { + hv->screen_width_max = SYNTHVID_WIDTH_MAX_WIN7; + hv->screen_height_max = SYNTHVID_HEIGHT_MAX_WIN7; + } + + hv->mmio_megabytes = hdev->channel->offermsg.offer.mmio_megabytes; + + return 0; + +error: + vmbus_close(hdev->channel); + return ret; +} diff --git a/drivers/gpu/drm/i915/Makefile b/drivers/gpu/drm/i915/Makefile index d0d936d9137b..6947495bf34b 100644 --- a/drivers/gpu/drm/i915/Makefile +++ b/drivers/gpu/drm/i915/Makefile @@ -201,10 +201,10 @@ i915-y += \ display/intel_combo_phy.o \ display/intel_connector.o \ display/intel_crtc.o \ - display/intel_csr.o \ display/intel_cursor.o \ display/intel_display.o \ display/intel_display_power.o \ + display/intel_dmc.o \ display/intel_dpio_phy.o \ display/intel_dpll.o \ display/intel_dpll_mgr.o \ @@ -263,6 +263,7 @@ i915-y += \ display/intel_lvds.o \ display/intel_panel.o \ display/intel_pps.o \ + display/intel_qp_tables.o \ display/intel_sdvo.o \ display/intel_tv.o \ display/intel_vdsc.o \ diff --git a/drivers/gpu/drm/i915/display/icl_dsi.c b/drivers/gpu/drm/i915/display/icl_dsi.c index ce544e20f35c..16812488c5dd 100644 --- a/drivers/gpu/drm/i915/display/icl_dsi.c +++ b/drivers/gpu/drm/i915/display/icl_dsi.c @@ -363,10 +363,19 @@ static void gen11_dsi_program_esc_clk_div(struct intel_encoder *encoder, struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder); enum port port; int afe_clk_khz; - u32 esc_clk_div_m; + int theo_word_clk, act_word_clk; + u32 esc_clk_div_m, esc_clk_div_m_phy; afe_clk_khz = afe_clk(encoder, crtc_state); - esc_clk_div_m = DIV_ROUND_UP(afe_clk_khz, DSI_MAX_ESC_CLK); + + if (IS_ALDERLAKE_S(dev_priv) || IS_ALDERLAKE_P(dev_priv)) { + theo_word_clk = DIV_ROUND_UP(afe_clk_khz, 8 * DSI_MAX_ESC_CLK); + act_word_clk = max(3, theo_word_clk + (theo_word_clk + 1) % 2); + esc_clk_div_m = act_word_clk * 8; + esc_clk_div_m_phy = (act_word_clk - 1) / 2; + } else { + esc_clk_div_m = DIV_ROUND_UP(afe_clk_khz, DSI_MAX_ESC_CLK); + } for_each_dsi_port(port, intel_dsi->ports) { intel_de_write(dev_priv, ICL_DSI_ESC_CLK_DIV(port), @@ -379,6 +388,14 @@ static void gen11_dsi_program_esc_clk_div(struct intel_encoder *encoder, esc_clk_div_m & ICL_ESC_CLK_DIV_MASK); intel_de_posting_read(dev_priv, ICL_DPHY_ESC_CLK_DIV(port)); } + + if (IS_ALDERLAKE_S(dev_priv) || IS_ALDERLAKE_P(dev_priv)) { + for_each_dsi_port(port, intel_dsi->ports) { + intel_de_write(dev_priv, ADL_MIPIO_DW(port, 8), + esc_clk_div_m_phy & TX_ESC_CLK_DIV_PHY); + intel_de_posting_read(dev_priv, ADL_MIPIO_DW(port, 8)); + } + } } static void get_dsi_io_power_domains(struct drm_i915_private *dev_priv, diff --git a/drivers/gpu/drm/i915/display/intel_atomic.c b/drivers/gpu/drm/i915/display/intel_atomic.c index 88f424020a5f..b4e7ac51aa31 100644 --- a/drivers/gpu/drm/i915/display/intel_atomic.c +++ b/drivers/gpu/drm/i915/display/intel_atomic.c @@ -187,6 +187,26 @@ intel_connector_needs_modeset(struct intel_atomic_state *state, new_conn_state->crtc))); } +/** + * intel_any_crtc_needs_modeset - check if any CRTC needs a modeset + * @state: the atomic state corresponding to this modeset + * + * Returns true if any CRTC in @state needs a modeset. + */ +bool intel_any_crtc_needs_modeset(struct intel_atomic_state *state) +{ + struct intel_crtc *crtc; + struct intel_crtc_state *crtc_state; + int i; + + for_each_new_intel_crtc_in_state(state, crtc, crtc_state, i) { + if (intel_crtc_needs_modeset(crtc_state)) + return true; + } + + return false; +} + struct intel_digital_connector_state * intel_atomic_get_digital_connector_state(struct intel_atomic_state *state, struct intel_connector *connector) diff --git a/drivers/gpu/drm/i915/display/intel_atomic.h b/drivers/gpu/drm/i915/display/intel_atomic.h index 62a3365ed5e6..d2700c74c9da 100644 --- a/drivers/gpu/drm/i915/display/intel_atomic.h +++ b/drivers/gpu/drm/i915/display/intel_atomic.h @@ -35,6 +35,7 @@ struct drm_connector_state * intel_digital_connector_duplicate_state(struct drm_connector *connector); bool intel_connector_needs_modeset(struct intel_atomic_state *state, struct drm_connector *connector); +bool intel_any_crtc_needs_modeset(struct intel_atomic_state *state); struct intel_digital_connector_state * intel_atomic_get_digital_connector_state(struct intel_atomic_state *state, struct intel_connector *connector); diff --git a/drivers/gpu/drm/i915/display/intel_bw.c b/drivers/gpu/drm/i915/display/intel_bw.c index a35435083b60..bfb398f0432e 100644 --- a/drivers/gpu/drm/i915/display/intel_bw.c +++ b/drivers/gpu/drm/i915/display/intel_bw.c @@ -162,7 +162,7 @@ static int icl_get_bw_info(struct drm_i915_private *dev_priv, const struct intel { struct intel_qgv_info qi = {}; bool is_y_tile = true; /* assume y tile may be used */ - int num_channels = dev_priv->dram_info.num_channels; + int num_channels = max_t(u8, 1, dev_priv->dram_info.num_channels); int deinterleave; int ipqdepth, ipqdepthpch; int dclk_max; @@ -267,7 +267,7 @@ void intel_bw_init_hw(struct drm_i915_private *dev_priv) if (!HAS_DISPLAY(dev_priv)) return; - if (IS_ALDERLAKE_S(dev_priv)) + if (IS_ALDERLAKE_S(dev_priv) || IS_ALDERLAKE_P(dev_priv)) icl_get_bw_info(dev_priv, &adls_sa_info); else if (IS_ROCKETLAKE(dev_priv)) icl_get_bw_info(dev_priv, &rkl_sa_info); diff --git a/drivers/gpu/drm/i915/display/intel_cdclk.c b/drivers/gpu/drm/i915/display/intel_cdclk.c index 4656a6edc3be..613ffcc68eba 100644 --- a/drivers/gpu/drm/i915/display/intel_cdclk.c +++ b/drivers/gpu/drm/i915/display/intel_cdclk.c @@ -28,6 +28,7 @@ #include "intel_cdclk.h" #include "intel_de.h" #include "intel_display_types.h" +#include "intel_psr.h" #include "intel_sideband.h" /** @@ -1547,6 +1548,35 @@ static void cnl_cdclk_pll_enable(struct drm_i915_private *dev_priv, int vco) dev_priv->cdclk.hw.vco = vco; } +static bool has_cdclk_crawl(struct drm_i915_private *i915) +{ + return INTEL_INFO(i915)->has_cdclk_crawl; +} + +static void adlp_cdclk_pll_crawl(struct drm_i915_private *dev_priv, int vco) +{ + int ratio = DIV_ROUND_CLOSEST(vco, dev_priv->cdclk.hw.ref); + u32 val; + + /* Write PLL ratio without disabling */ + val = CNL_CDCLK_PLL_RATIO(ratio) | BXT_DE_PLL_PLL_ENABLE; + intel_de_write(dev_priv, BXT_DE_PLL_ENABLE, val); + + /* Submit freq change request */ + val |= BXT_DE_PLL_FREQ_REQ; + intel_de_write(dev_priv, BXT_DE_PLL_ENABLE, val); + + /* Timeout 200us */ + if (intel_de_wait_for_set(dev_priv, BXT_DE_PLL_ENABLE, + BXT_DE_PLL_LOCK | BXT_DE_PLL_FREQ_REQ_ACK, 1)) + DRM_ERROR("timeout waiting for FREQ change request ack\n"); + + val &= ~BXT_DE_PLL_FREQ_REQ; + intel_de_write(dev_priv, BXT_DE_PLL_ENABLE, val); + + dev_priv->cdclk.hw.vco = vco; +} + static u32 bxt_cdclk_cd2x_pipe(struct drm_i915_private *dev_priv, enum pipe pipe) { if (DISPLAY_VER(dev_priv) >= 12) { @@ -1619,14 +1649,16 @@ static void bxt_set_cdclk(struct drm_i915_private *dev_priv, return; } - if (DISPLAY_VER(dev_priv) >= 11 || IS_CANNONLAKE(dev_priv)) { + if (has_cdclk_crawl(dev_priv) && dev_priv->cdclk.hw.vco > 0 && vco > 0) { + if (dev_priv->cdclk.hw.vco != vco) + adlp_cdclk_pll_crawl(dev_priv, vco); + } else if (DISPLAY_VER(dev_priv) >= 11 || IS_CANNONLAKE(dev_priv)) { if (dev_priv->cdclk.hw.vco != 0 && dev_priv->cdclk.hw.vco != vco) cnl_cdclk_pll_disable(dev_priv); if (dev_priv->cdclk.hw.vco != vco) cnl_cdclk_pll_enable(dev_priv, vco); - } else { if (dev_priv->cdclk.hw.vco != 0 && dev_priv->cdclk.hw.vco != vco) @@ -1819,6 +1851,28 @@ void intel_cdclk_uninit_hw(struct drm_i915_private *i915) skl_cdclk_uninit_hw(i915); } +static bool intel_cdclk_can_crawl(struct drm_i915_private *dev_priv, + const struct intel_cdclk_config *a, + const struct intel_cdclk_config *b) +{ + int a_div, b_div; + + if (!has_cdclk_crawl(dev_priv)) + return false; + + /* + * The vco and cd2x divider will change independently + * from each, so we disallow cd2x change when crawling. + */ + a_div = DIV_ROUND_CLOSEST(a->vco, a->cdclk); + b_div = DIV_ROUND_CLOSEST(b->vco, b->cdclk); + + return a->vco != 0 && b->vco != 0 && + a->vco != b->vco && + a_div == b_div && + a->ref == b->ref; +} + /** * intel_cdclk_needs_modeset - Determine if changong between the CDCLK * configurations requires a modeset on all pipes @@ -1908,6 +1962,12 @@ static void intel_set_cdclk(struct drm_i915_private *dev_priv, intel_dump_cdclk_config(cdclk_config, "Changing CDCLK to"); + for_each_intel_encoder_with_psr(&dev_priv->drm, encoder) { + struct intel_dp *intel_dp = enc_to_intel_dp(encoder); + + intel_psr_pause(intel_dp); + } + /* * Lock aux/gmbus while we change cdclk in case those * functions use cdclk. Not all platforms/ports do, @@ -1930,6 +1990,12 @@ static void intel_set_cdclk(struct drm_i915_private *dev_priv, } mutex_unlock(&dev_priv->gmbus_mutex); + for_each_intel_encoder_with_psr(&dev_priv->drm, encoder) { + struct intel_dp *intel_dp = enc_to_intel_dp(encoder); + + intel_psr_resume(intel_dp); + } + if (drm_WARN(&dev_priv->drm, intel_cdclk_changed(&dev_priv->cdclk.hw, cdclk_config), "cdclk state doesn't match!\n")) { @@ -2462,7 +2528,7 @@ int intel_modeset_calc_cdclk(struct intel_atomic_state *state) struct drm_i915_private *dev_priv = to_i915(state->base.dev); const struct intel_cdclk_state *old_cdclk_state; struct intel_cdclk_state *new_cdclk_state; - enum pipe pipe; + enum pipe pipe = INVALID_PIPE; int ret; new_cdclk_state = intel_atomic_get_cdclk_state(state); @@ -2514,15 +2580,18 @@ int intel_modeset_calc_cdclk(struct intel_atomic_state *state) if (drm_atomic_crtc_needs_modeset(&crtc_state->uapi)) pipe = INVALID_PIPE; - } else { - pipe = INVALID_PIPE; } - if (pipe != INVALID_PIPE) { + if (intel_cdclk_can_crawl(dev_priv, + &old_cdclk_state->actual, + &new_cdclk_state->actual)) { + drm_dbg_kms(&dev_priv->drm, + "Can change cdclk via crawl\n"); + } else if (pipe != INVALID_PIPE) { new_cdclk_state->pipe = pipe; drm_dbg_kms(&dev_priv->drm, - "Can change cdclk with pipe %c active\n", + "Can change cdclk cd2x divider with pipe %c active\n", pipe_name(pipe)); } else if (intel_cdclk_needs_modeset(&old_cdclk_state->actual, &new_cdclk_state->actual)) { @@ -2531,8 +2600,6 @@ int intel_modeset_calc_cdclk(struct intel_atomic_state *state) if (ret) return ret; - new_cdclk_state->pipe = INVALID_PIPE; - drm_dbg_kms(&dev_priv->drm, "Modeset required for cdclk change\n"); } diff --git a/drivers/gpu/drm/i915/display/intel_csr.h b/drivers/gpu/drm/i915/display/intel_csr.h deleted file mode 100644 index 03c64f8af7ab..000000000000 --- a/drivers/gpu/drm/i915/display/intel_csr.h +++ /dev/null @@ -1,21 +0,0 @@ -/* SPDX-License-Identifier: MIT */ -/* - * Copyright © 2019 Intel Corporation - */ - -#ifndef __INTEL_CSR_H__ -#define __INTEL_CSR_H__ - -struct drm_i915_private; - -#define CSR_VERSION(major, minor) ((major) << 16 | (minor)) -#define CSR_VERSION_MAJOR(version) ((version) >> 16) -#define CSR_VERSION_MINOR(version) ((version) & 0xffff) - -void intel_csr_ucode_init(struct drm_i915_private *i915); -void intel_csr_load_program(struct drm_i915_private *i915); -void intel_csr_ucode_fini(struct drm_i915_private *i915); -void intel_csr_ucode_suspend(struct drm_i915_private *i915); -void intel_csr_ucode_resume(struct drm_i915_private *i915); - -#endif /* __INTEL_CSR_H__ */ diff --git a/drivers/gpu/drm/i915/display/intel_cursor.c b/drivers/gpu/drm/i915/display/intel_cursor.c index 2ab389b38694..966e020331fb 100644 --- a/drivers/gpu/drm/i915/display/intel_cursor.c +++ b/drivers/gpu/drm/i915/display/intel_cursor.c @@ -383,6 +383,10 @@ static u32 i9xx_cursor_ctl(const struct intel_crtc_state *crtc_state, if (plane_state->hw.rotation & DRM_MODE_ROTATE_180) cntl |= MCURSOR_ROTATE_180; + /* Wa_22012358565:adlp */ + if (DISPLAY_VER(dev_priv) == 13) + cntl |= MCURSOR_ARB_SLOTS(1); + return cntl; } diff --git a/drivers/gpu/drm/i915/display/intel_ddi.c b/drivers/gpu/drm/i915/display/intel_ddi.c index eccbdd42d223..390869bd6b63 100644 --- a/drivers/gpu/drm/i915/display/intel_ddi.c +++ b/drivers/gpu/drm/i915/display/intel_ddi.c @@ -249,15 +249,48 @@ static u32 icl_pll_to_ddi_clk_sel(struct intel_encoder *encoder, } } +static u32 ddi_buf_phy_link_rate(int port_clock) +{ + switch (port_clock) { + case 162000: + return DDI_BUF_PHY_LINK_RATE(0); + case 216000: + return DDI_BUF_PHY_LINK_RATE(4); + case 243000: + return DDI_BUF_PHY_LINK_RATE(5); + case 270000: + return DDI_BUF_PHY_LINK_RATE(1); + case 324000: + return DDI_BUF_PHY_LINK_RATE(6); + case 432000: + return DDI_BUF_PHY_LINK_RATE(7); + case 540000: + return DDI_BUF_PHY_LINK_RATE(2); + case 810000: + return DDI_BUF_PHY_LINK_RATE(3); + default: + MISSING_CASE(port_clock); + return DDI_BUF_PHY_LINK_RATE(0); + } +} + static void intel_ddi_init_dp_buf_reg(struct intel_encoder *encoder, const struct intel_crtc_state *crtc_state) { + struct drm_i915_private *i915 = to_i915(encoder->base.dev); struct intel_dp *intel_dp = enc_to_intel_dp(encoder); struct intel_digital_port *dig_port = enc_to_dig_port(encoder); + enum phy phy = intel_port_to_phy(i915, encoder->port); intel_dp->DP = dig_port->saved_port_bits | DDI_BUF_CTL_ENABLE | DDI_BUF_TRANS_SELECT(0); intel_dp->DP |= DDI_PORT_WIDTH(crtc_state->lane_count); + + if (IS_ALDERLAKE_P(i915) && intel_phy_is_tc(i915, phy)) { + intel_dp->DP |= ddi_buf_phy_link_rate(crtc_state->port_clock); + if (dig_port->tc_mode != TC_PORT_TBT_ALT) + intel_dp->DP |= DDI_BUF_CTL_TC_PHY_OWNERSHIP; + } } static int icl_calc_tbt_pll_link(struct drm_i915_private *dev_priv, @@ -979,6 +1012,8 @@ static u8 intel_ddi_dp_voltage_max(struct intel_dp *intel_dp, if (DISPLAY_VER(dev_priv) >= 12) { if (intel_phy_is_combo(dev_priv, phy)) tgl_get_combo_buf_trans(encoder, crtc_state, &n_entries); + else if (IS_ALDERLAKE_P(dev_priv)) + adlp_get_dkl_buf_trans(encoder, crtc_state, &n_entries); else tgl_get_dkl_buf_trans(encoder, crtc_state, &n_entries); } else if (DISPLAY_VER(dev_priv) == 11) { @@ -1425,7 +1460,10 @@ tgl_dkl_phy_ddi_vswing_sequence(struct intel_encoder *encoder, if (enc_to_dig_port(encoder)->tc_mode == TC_PORT_TBT_ALT) return; - ddi_translations = tgl_get_dkl_buf_trans(encoder, crtc_state, &n_entries); + if (IS_ALDERLAKE_P(dev_priv)) + ddi_translations = adlp_get_dkl_buf_trans(encoder, crtc_state, &n_entries); + else + ddi_translations = tgl_get_dkl_buf_trans(encoder, crtc_state, &n_entries); if (drm_WARN_ON_ONCE(&dev_priv->drm, !ddi_translations)) return; @@ -2772,7 +2810,6 @@ static void intel_ddi_pre_enable(struct intel_atomic_state *state, conn_state); /* FIXME precompute everything properly */ - /* FIXME how do we turn infoframes off again? */ if (dig_port->lspcon.active && dig_port->dp.has_hdmi_sink) dig_port->set_infoframes(encoder, crtc_state->has_infoframe, @@ -3157,6 +3194,9 @@ static void intel_enable_ddi_hdmi(struct intel_atomic_state *state, /* In HDMI/DVI mode, the port width, and swing/emphasis values * are ignored so nothing special needs to be done besides * enabling the port. + * + * On ADL_P the PHY link rate and lane count must be programmed but + * these are both 0 for HDMI. */ intel_de_write(dev_priv, DDI_BUF_CTL(port), dig_port->saved_port_bits | DDI_BUF_CTL_ENABLE); @@ -4022,9 +4062,11 @@ static int intel_ddi_compute_config_late(struct intel_encoder *encoder, static void intel_ddi_encoder_destroy(struct drm_encoder *encoder) { + struct drm_i915_private *i915 = to_i915(encoder->dev); struct intel_digital_port *dig_port = enc_to_dig_port(to_intel_encoder(encoder)); intel_dp_encoder_flush_work(encoder); + intel_display_power_flush_work(i915); drm_encoder_cleanup(encoder); if (dig_port) @@ -4688,9 +4730,12 @@ void intel_ddi_init(struct drm_i915_private *dev_priv, enum port port) dig_port->hpd_pulse = intel_dp_hpd_pulse; - /* Splitter enable for eDP MSO is supported for pipe A only. */ - if (dig_port->dp.mso_link_count) + /* Splitter enable for eDP MSO is limited to certain pipes. */ + if (dig_port->dp.mso_link_count) { encoder->pipe_mask = BIT(PIPE_A); + if (IS_ALDERLAKE_P(dev_priv)) + encoder->pipe_mask |= BIT(PIPE_B); + } } /* In theory we don't need the encoder->type check, but leave it just in diff --git a/drivers/gpu/drm/i915/display/intel_ddi_buf_trans.c b/drivers/gpu/drm/i915/display/intel_ddi_buf_trans.c index 7bcdd5c12028..8bfd00f49f2a 100644 --- a/drivers/gpu/drm/i915/display/intel_ddi_buf_trans.c +++ b/drivers/gpu/drm/i915/display/intel_ddi_buf_trans.c @@ -735,6 +735,34 @@ static const struct cnl_ddi_buf_trans rkl_combo_phy_ddi_translations_dp_hbr2_hbr { 0x6, 0x7F, 0x3F, 0x00, 0x00 }, /* 900 900 0.0 */ }; +static const struct tgl_dkl_phy_ddi_buf_trans adlp_dkl_phy_dp_ddi_trans_hbr[] = { + /* VS pre-emp Non-trans mV Pre-emph dB */ + { 0x7, 0x0, 0x01 }, /* 0 0 400mV 0 dB */ + { 0x5, 0x0, 0x06 }, /* 0 1 400mV 3.5 dB */ + { 0x2, 0x0, 0x0B }, /* 0 2 400mV 6 dB */ + { 0x0, 0x0, 0x17 }, /* 0 3 400mV 9.5 dB */ + { 0x5, 0x0, 0x00 }, /* 1 0 600mV 0 dB */ + { 0x2, 0x0, 0x08 }, /* 1 1 600mV 3.5 dB */ + { 0x0, 0x0, 0x14 }, /* 1 2 600mV 6 dB */ + { 0x2, 0x0, 0x00 }, /* 2 0 800mV 0 dB */ + { 0x0, 0x0, 0x0B }, /* 2 1 800mV 3.5 dB */ + { 0x0, 0x0, 0x00 }, /* 3 0 1200mV 0 dB */ +}; + +static const struct tgl_dkl_phy_ddi_buf_trans adlp_dkl_phy_dp_ddi_trans_hbr2_hbr3[] = { + /* VS pre-emp Non-trans mV Pre-emph dB */ + { 0x7, 0x0, 0x00 }, /* 0 0 400mV 0 dB */ + { 0x5, 0x0, 0x04 }, /* 0 1 400mV 3.5 dB */ + { 0x2, 0x0, 0x0A }, /* 0 2 400mV 6 dB */ + { 0x0, 0x0, 0x18 }, /* 0 3 400mV 9.5 dB */ + { 0x5, 0x0, 0x00 }, /* 1 0 600mV 0 dB */ + { 0x2, 0x0, 0x06 }, /* 1 1 600mV 3.5 dB */ + { 0x0, 0x0, 0x14 }, /* 1 2 600mV 6 dB */ + { 0x2, 0x0, 0x00 }, /* 2 0 800mV 0 dB */ + { 0x0, 0x0, 0x09 }, /* 2 1 800mV 3.5 dB */ + { 0x0, 0x0, 0x00 }, /* 3 0 1200mV 0 dB */ +}; + bool is_hobl_buf_trans(const struct cnl_ddi_buf_trans *table) { return table == tgl_combo_phy_ddi_translations_edp_hbr2_hobl; @@ -1348,6 +1376,31 @@ tgl_get_dkl_buf_trans(struct intel_encoder *encoder, return tgl_get_dkl_buf_trans_dp(encoder, crtc_state, n_entries); } +static const struct tgl_dkl_phy_ddi_buf_trans * +adlp_get_dkl_buf_trans_dp(struct intel_encoder *encoder, + const struct intel_crtc_state *crtc_state, + int *n_entries) +{ + if (crtc_state->port_clock > 270000) { + *n_entries = ARRAY_SIZE(adlp_dkl_phy_dp_ddi_trans_hbr2_hbr3); + return adlp_dkl_phy_dp_ddi_trans_hbr2_hbr3; + } + + *n_entries = ARRAY_SIZE(adlp_dkl_phy_dp_ddi_trans_hbr); + return adlp_dkl_phy_dp_ddi_trans_hbr; +} + +const struct tgl_dkl_phy_ddi_buf_trans * +adlp_get_dkl_buf_trans(struct intel_encoder *encoder, + const struct intel_crtc_state *crtc_state, + int *n_entries) +{ + if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_HDMI)) + return tgl_get_dkl_buf_trans_hdmi(encoder, crtc_state, n_entries); + else + return adlp_get_dkl_buf_trans_dp(encoder, crtc_state, n_entries); +} + int intel_ddi_hdmi_num_entries(struct intel_encoder *encoder, const struct intel_crtc_state *crtc_state, int *default_entry) diff --git a/drivers/gpu/drm/i915/display/intel_ddi_buf_trans.h b/drivers/gpu/drm/i915/display/intel_ddi_buf_trans.h index f8f0ef87e977..4c2efab38642 100644 --- a/drivers/gpu/drm/i915/display/intel_ddi_buf_trans.h +++ b/drivers/gpu/drm/i915/display/intel_ddi_buf_trans.h @@ -67,6 +67,10 @@ bxt_get_buf_trans(struct intel_encoder *encoder, const struct intel_crtc_state *crtc_state, int *n_entries); +const struct tgl_dkl_phy_ddi_buf_trans * +adlp_get_dkl_buf_trans(struct intel_encoder *encoder, + const struct intel_crtc_state *crtc_state, + int *n_entries); const struct cnl_ddi_buf_trans * tgl_get_combo_buf_trans(struct intel_encoder *encoder, const struct intel_crtc_state *crtc_state, diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c index 422b59ebf6dc..362bff9beb5c 100644 --- a/drivers/gpu/drm/i915/display/intel_display.c +++ b/drivers/gpu/drm/i915/display/intel_display.c @@ -79,9 +79,9 @@ #include "intel_cdclk.h" #include "intel_color.h" #include "intel_crtc.h" -#include "intel_csr.h" #include "intel_de.h" #include "intel_display_types.h" +#include "intel_dmc.h" #include "intel_dp_link_training.h" #include "intel_fbc.h" #include "intel_fdi.h" @@ -975,6 +975,11 @@ void intel_enable_pipe(const struct intel_crtc_state *new_crtc_state) /* FIXME: assert CPU port conditions for SNB+ */ } + /* Wa_22012358565:adlp */ + if (DISPLAY_VER(dev_priv) == 13) + intel_de_rmw(dev_priv, PIPE_ARB_CTL(pipe), + 0, PIPE_ARB_USE_PROG_SLOTS); + reg = PIPECONF(cpu_transcoder); val = intel_de_read(dev_priv, reg); if (val & PIPECONF_ENABLE) { @@ -1690,7 +1695,8 @@ initial_plane_vma(struct drm_i915_private *i915, * important and we should probably use that space with FBC or other * features. */ - if (size * 2 > i915->stolen_usable_size) + if (IS_ENABLED(CONFIG_FRAMEBUFFER_CONSOLE) && + size * 2 > i915->stolen_usable_size) return NULL; obj = i915_gem_object_create_stolen_for_preallocated(i915, base, size); @@ -2208,6 +2214,21 @@ static void icl_set_pipe_chicken(struct intel_crtc *crtc) * across pipe */ tmp |= PIXEL_ROUNDING_TRUNC_FB_PASSTHRU; + + /* + * "The underrun recovery mechanism should be disabled + * when the following is enabled for this pipe: + * WiDi + * Downscaling (this includes YUV420 fullblend) + * COG + * DSC + * PSR2" + * + * FIXME: enable whenever possible... + */ + if (IS_ALDERLAKE_P(dev_priv)) + tmp |= UNDERRUN_RECOVERY_DISABLE; + intel_de_write(dev_priv, PIPE_CHICKEN(pipe), tmp); } @@ -3675,7 +3696,9 @@ bool intel_phy_is_combo(struct drm_i915_private *dev_priv, enum phy phy) bool intel_phy_is_tc(struct drm_i915_private *dev_priv, enum phy phy) { - if (IS_TIGERLAKE(dev_priv)) + if (IS_ALDERLAKE_P(dev_priv)) + return phy >= PHY_F && phy <= PHY_I; + else if (IS_TIGERLAKE(dev_priv)) return phy >= PHY_D && phy <= PHY_I; else if (IS_ICELAKE(dev_priv)) return phy >= PHY_C && phy <= PHY_F; @@ -5714,8 +5737,12 @@ static void hsw_set_pipeconf(const struct intel_crtc_state *crtc_state) static void bdw_set_pipemisc(const struct intel_crtc_state *crtc_state) { struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); + const struct intel_crtc_scaler_state *scaler_state = + &crtc_state->scaler_state; + struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); u32 val = 0; + int i; switch (crtc_state->pipe_bpp) { case 18: @@ -5754,6 +5781,23 @@ static void bdw_set_pipemisc(const struct intel_crtc_state *crtc_state) if (DISPLAY_VER(dev_priv) >= 12) val |= PIPEMISC_PIXEL_ROUNDING_TRUNC; + if (IS_ALDERLAKE_P(dev_priv)) { + bool scaler_in_use = false; + + for (i = 0; i < crtc->num_scalers; i++) { + if (!scaler_state->scalers[i].in_use) + continue; + + scaler_in_use = true; + break; + } + + intel_de_rmw(dev_priv, PIPE_MISC2(crtc->pipe), + PIPE_MISC2_UNDERRUN_BUBBLE_COUNTER_MASK, + scaler_in_use ? PIPE_MISC2_BUBBLE_COUNTER_SCALER_EN : + PIPE_MISC2_BUBBLE_COUNTER_SCALER_DIS); + } + intel_de_write(dev_priv, PIPEMISC(crtc->pipe), val); } @@ -7631,10 +7675,11 @@ static void intel_dump_pipe_config(const struct intel_crtc_state *pipe_config, intel_hdmi_infoframe_enable(DP_SDP_VSC)) intel_dump_dp_vsc_sdp(dev_priv, &pipe_config->infoframes.vsc); - drm_dbg_kms(&dev_priv->drm, "vrr: %s, vmin: %d, vmax: %d, pipeline full: %d, flipline: %d, vmin vblank: %d, vmax vblank: %d\n", + drm_dbg_kms(&dev_priv->drm, "vrr: %s, vmin: %d, vmax: %d, pipeline full: %d, guardband: %d flipline: %d, vmin vblank: %d, vmax vblank: %d\n", yesno(pipe_config->vrr.enable), pipe_config->vrr.vmin, pipe_config->vrr.vmax, - pipe_config->vrr.pipeline_full, pipe_config->vrr.flipline, + pipe_config->vrr.pipeline_full, pipe_config->vrr.guardband, + pipe_config->vrr.flipline, intel_vrr_vmin_vblank_start(pipe_config), intel_vrr_vmax_vblank_start(pipe_config)); @@ -8270,6 +8315,16 @@ intel_pipe_config_compare(const struct intel_crtc_state *current_config, } \ } while (0) +#define PIPE_CONF_CHECK_X_WITH_MASK(name, mask) do { \ + if ((current_config->name & (mask)) != (pipe_config->name & (mask))) { \ + pipe_config_mismatch(fastset, crtc, __stringify(name), \ + "(expected 0x%08x, found 0x%08x)", \ + current_config->name & (mask), \ + pipe_config->name & (mask)); \ + ret = false; \ + } \ +} while (0) + #define PIPE_CONF_CHECK_I(name) do { \ if (current_config->name != pipe_config->name) { \ pipe_config_mismatch(fastset, crtc, __stringify(name), \ @@ -8558,6 +8613,11 @@ intel_pipe_config_compare(const struct intel_crtc_state *current_config, bp_gamma = intel_color_get_gamma_bit_precision(pipe_config); if (bp_gamma) PIPE_CONF_CHECK_COLOR_LUT(gamma_mode, hw.gamma_lut, bp_gamma); + + PIPE_CONF_CHECK_BOOL(has_psr); + PIPE_CONF_CHECK_BOOL(has_psr2); + PIPE_CONF_CHECK_BOOL(enable_psr2_sel_fetch); + PIPE_CONF_CHECK_I(dc3co_exitline); } PIPE_CONF_CHECK_BOOL(double_wide); @@ -8611,7 +8671,12 @@ intel_pipe_config_compare(const struct intel_crtc_state *current_config, PIPE_CONF_CHECK_I(min_voltage_level); } - PIPE_CONF_CHECK_X(infoframes.enable); + if (fastset && (current_config->has_psr || pipe_config->has_psr)) + PIPE_CONF_CHECK_X_WITH_MASK(infoframes.enable, + ~intel_hdmi_infoframe_enable(DP_SDP_VSC)); + else + PIPE_CONF_CHECK_X(infoframes.enable); + PIPE_CONF_CHECK_X(infoframes.gcp); PIPE_CONF_CHECK_INFOFRAME(avi); PIPE_CONF_CHECK_INFOFRAME(spd); @@ -8640,11 +8705,7 @@ intel_pipe_config_compare(const struct intel_crtc_state *current_config, PIPE_CONF_CHECK_I(vrr.vmax); PIPE_CONF_CHECK_I(vrr.flipline); PIPE_CONF_CHECK_I(vrr.pipeline_full); - - PIPE_CONF_CHECK_BOOL(has_psr); - PIPE_CONF_CHECK_BOOL(has_psr2); - PIPE_CONF_CHECK_BOOL(enable_psr2_sel_fetch); - PIPE_CONF_CHECK_I(dc3co_exitline); + PIPE_CONF_CHECK_I(vrr.guardband); #undef PIPE_CONF_CHECK_X #undef PIPE_CONF_CHECK_I @@ -8750,6 +8811,38 @@ static void verify_wm_state(struct intel_crtc *crtc, hw_wm_level->lines); } + hw_wm_level = &hw->wm.planes[plane->id].sagv.wm0; + sw_wm_level = &sw_wm->planes[plane->id].sagv.wm0; + + if (HAS_HW_SAGV_WM(dev_priv) && + !skl_wm_level_equals(hw_wm_level, sw_wm_level)) { + drm_err(&dev_priv->drm, + "[PLANE:%d:%s] mismatch in SAGV WM (expected e=%d b=%u l=%u, got e=%d b=%u l=%u)\n", + plane->base.base.id, plane->base.name, + sw_wm_level->enable, + sw_wm_level->blocks, + sw_wm_level->lines, + hw_wm_level->enable, + hw_wm_level->blocks, + hw_wm_level->lines); + } + + hw_wm_level = &hw->wm.planes[plane->id].sagv.trans_wm; + sw_wm_level = &sw_wm->planes[plane->id].sagv.trans_wm; + + if (HAS_HW_SAGV_WM(dev_priv) && + !skl_wm_level_equals(hw_wm_level, sw_wm_level)) { + drm_err(&dev_priv->drm, + "[PLANE:%d:%s] mismatch in SAGV trans WM (expected e=%d b=%u l=%u, got e=%d b=%u l=%u)\n", + plane->base.base.id, plane->base.name, + sw_wm_level->enable, + sw_wm_level->blocks, + sw_wm_level->lines, + hw_wm_level->enable, + hw_wm_level->blocks, + hw_wm_level->lines); + } + /* DDB */ hw_ddb_entry = &hw->ddb_y[plane->id]; sw_ddb_entry = &new_crtc_state->wm.skl.plane_ddb_y[plane->id]; @@ -9923,6 +10016,9 @@ static int intel_atomic_check(struct drm_device *dev, if (ret) goto fail; + if (intel_any_crtc_needs_modeset(state)) + any_ms = true; + if (any_ms) { ret = intel_modeset_checks(state); if (ret) @@ -11040,7 +11136,7 @@ intel_prepare_plane_fb(struct drm_plane *_plane, if (ret < 0) goto unpin_fb; - fence = dma_resv_get_excl_rcu(obj->base.resv); + fence = dma_resv_get_excl_unlocked(obj->base.resv); if (fence) { add_rps_boost_after_vblank(new_plane_state->hw.crtc, fence); @@ -11219,7 +11315,14 @@ static void intel_setup_outputs(struct drm_i915_private *dev_priv) if (!HAS_DISPLAY(dev_priv)) return; - if (IS_ALDERLAKE_S(dev_priv)) { + if (IS_ALDERLAKE_P(dev_priv)) { + intel_ddi_init(dev_priv, PORT_A); + intel_ddi_init(dev_priv, PORT_B); + intel_ddi_init(dev_priv, PORT_TC1); + intel_ddi_init(dev_priv, PORT_TC2); + intel_ddi_init(dev_priv, PORT_TC3); + intel_ddi_init(dev_priv, PORT_TC4); + } else if (IS_ALDERLAKE_S(dev_priv)) { intel_ddi_init(dev_priv, PORT_A); intel_ddi_init(dev_priv, PORT_TC1); intel_ddi_init(dev_priv, PORT_TC2); @@ -12192,7 +12295,7 @@ int intel_modeset_init_noirq(struct drm_i915_private *i915) if (!HAS_DISPLAY(i915)) return 0; - intel_csr_ucode_init(i915); + intel_dmc_ucode_init(i915); i915->modeset_wq = alloc_ordered_workqueue("i915_modeset", 0); i915->flip_wq = alloc_workqueue("i915_flip", WQ_HIGHPRI | @@ -12200,19 +12303,21 @@ int intel_modeset_init_noirq(struct drm_i915_private *i915) i915->framestart_delay = 1; /* 1-4 */ + i915->window2_delay = 0; /* No DSB so no window2 delay */ + intel_mode_config_init(i915); ret = intel_cdclk_init(i915); if (ret) - goto cleanup_vga_client_pw_domain_csr; + goto cleanup_vga_client_pw_domain_dmc; ret = intel_dbuf_init(i915); if (ret) - goto cleanup_vga_client_pw_domain_csr; + goto cleanup_vga_client_pw_domain_dmc; ret = intel_bw_init(i915); if (ret) - goto cleanup_vga_client_pw_domain_csr; + goto cleanup_vga_client_pw_domain_dmc; init_llist_head(&i915->atomic_helper.free_list); INIT_WORK(&i915->atomic_helper.free_work, @@ -12224,8 +12329,8 @@ int intel_modeset_init_noirq(struct drm_i915_private *i915) return 0; -cleanup_vga_client_pw_domain_csr: - intel_csr_ucode_fini(i915); +cleanup_vga_client_pw_domain_dmc: + intel_dmc_ucode_fini(i915); intel_power_domains_driver_remove(i915); intel_vga_unregister(i915); cleanup_bios: @@ -13304,7 +13409,7 @@ void intel_modeset_driver_remove_noirq(struct drm_i915_private *i915) /* part #3: call after gem init */ void intel_modeset_driver_remove_nogem(struct drm_i915_private *i915) { - intel_csr_ucode_fini(i915); + intel_dmc_ucode_fini(i915); intel_power_domains_driver_remove(i915); diff --git a/drivers/gpu/drm/i915/display/intel_display_debugfs.c b/drivers/gpu/drm/i915/display/intel_display_debugfs.c index d77a0ab5cacf..88bb05d5c483 100644 --- a/drivers/gpu/drm/i915/display/intel_display_debugfs.c +++ b/drivers/gpu/drm/i915/display/intel_display_debugfs.c @@ -7,11 +7,11 @@ #include <drm/drm_fourcc.h> #include "i915_debugfs.h" -#include "intel_csr.h" #include "intel_display_debugfs.h" #include "intel_display_power.h" #include "intel_de.h" #include "intel_display_types.h" +#include "intel_dmc.h" #include "intel_dp.h" #include "intel_fbc.h" #include "intel_hdcp.h" @@ -532,24 +532,24 @@ static int i915_dmc_info(struct seq_file *m, void *unused) { struct drm_i915_private *dev_priv = node_to_i915(m->private); intel_wakeref_t wakeref; - struct intel_csr *csr; + struct intel_dmc *dmc; i915_reg_t dc5_reg, dc6_reg = {}; - if (!HAS_CSR(dev_priv)) + if (!HAS_DMC(dev_priv)) return -ENODEV; - csr = &dev_priv->csr; + dmc = &dev_priv->dmc; wakeref = intel_runtime_pm_get(&dev_priv->runtime_pm); - seq_printf(m, "fw loaded: %s\n", yesno(csr->dmc_payload != NULL)); - seq_printf(m, "path: %s\n", csr->fw_path); + seq_printf(m, "fw loaded: %s\n", yesno(intel_dmc_has_payload(dev_priv))); + seq_printf(m, "path: %s\n", dmc->fw_path); - if (!csr->dmc_payload) + if (!intel_dmc_has_payload(dev_priv)) goto out; - seq_printf(m, "version: %d.%d\n", CSR_VERSION_MAJOR(csr->version), - CSR_VERSION_MINOR(csr->version)); + seq_printf(m, "version: %d.%d\n", DMC_VERSION_MAJOR(dmc->version), + DMC_VERSION_MINOR(dmc->version)); if (DISPLAY_VER(dev_priv) >= 12) { if (IS_DGFX(dev_priv)) { @@ -568,10 +568,10 @@ static int i915_dmc_info(struct seq_file *m, void *unused) seq_printf(m, "DC3CO count: %d\n", intel_de_read(dev_priv, DMC_DEBUG3)); } else { - dc5_reg = IS_BROXTON(dev_priv) ? BXT_CSR_DC3_DC5_COUNT : - SKL_CSR_DC3_DC5_COUNT; + dc5_reg = IS_BROXTON(dev_priv) ? BXT_DMC_DC3_DC5_COUNT : + SKL_DMC_DC3_DC5_COUNT; if (!IS_GEMINILAKE(dev_priv) && !IS_BROXTON(dev_priv)) - dc6_reg = SKL_CSR_DC5_DC6_COUNT; + dc6_reg = SKL_DMC_DC5_DC6_COUNT; } seq_printf(m, "DC3 -> DC5 count: %d\n", @@ -582,10 +582,10 @@ static int i915_dmc_info(struct seq_file *m, void *unused) out: seq_printf(m, "program base: 0x%08x\n", - intel_de_read(dev_priv, CSR_PROGRAM(0))); + intel_de_read(dev_priv, DMC_PROGRAM(0))); seq_printf(m, "ssp base: 0x%08x\n", - intel_de_read(dev_priv, CSR_SSP_BASE)); - seq_printf(m, "htp: 0x%08x\n", intel_de_read(dev_priv, CSR_HTP_SKL)); + intel_de_read(dev_priv, DMC_SSP_BASE)); + seq_printf(m, "htp: 0x%08x\n", intel_de_read(dev_priv, DMC_HTP_SKL)); intel_runtime_pm_put(&dev_priv->runtime_pm, wakeref); diff --git a/drivers/gpu/drm/i915/display/intel_display_power.c b/drivers/gpu/drm/i915/display/intel_display_power.c index 54c6d65011ee..4298ae684d7d 100644 --- a/drivers/gpu/drm/i915/display/intel_display_power.c +++ b/drivers/gpu/drm/i915/display/intel_display_power.c @@ -9,10 +9,10 @@ #include "i915_irq.h" #include "intel_cdclk.h" #include "intel_combo_phy.h" -#include "intel_csr.h" #include "intel_display_power.h" #include "intel_de.h" #include "intel_display_types.h" +#include "intel_dmc.h" #include "intel_dpio_phy.h" #include "intel_hotplug.h" #include "intel_pm.h" @@ -291,8 +291,7 @@ static void hsw_power_well_pre_disable(struct drm_i915_private *dev_priv, #define ICL_TBT_AUX_PW_TO_CH(pw_idx) \ ((pw_idx) - ICL_PW_CTL_IDX_AUX_TBT1 + AUX_CH_C) -static enum aux_ch icl_tc_phy_aux_ch(struct drm_i915_private *dev_priv, - struct i915_power_well *power_well) +static enum aux_ch icl_aux_pw_to_ch(const struct i915_power_well *power_well) { int pw_idx = power_well->desc->hsw.idx; @@ -327,6 +326,15 @@ aux_ch_to_digital_port(struct drm_i915_private *dev_priv, return dig_port; } +static enum phy icl_aux_pw_to_phy(struct drm_i915_private *i915, + const struct i915_power_well *power_well) +{ + enum aux_ch aux_ch = icl_aux_pw_to_ch(power_well); + struct intel_digital_port *dig_port = aux_ch_to_digital_port(i915, aux_ch); + + return intel_port_to_phy(i915, dig_port->base.port); +} + static void hsw_wait_for_power_well_enable(struct drm_i915_private *dev_priv, struct i915_power_well *power_well, bool timeout_expected) @@ -468,15 +476,13 @@ static void hsw_power_well_disable(struct drm_i915_private *dev_priv, hsw_wait_for_power_well_disable(dev_priv, power_well); } -#define ICL_AUX_PW_TO_PHY(pw_idx) ((pw_idx) - ICL_PW_CTL_IDX_AUX_A) - static void icl_combo_phy_aux_power_well_enable(struct drm_i915_private *dev_priv, struct i915_power_well *power_well) { const struct i915_power_well_regs *regs = power_well->desc->hsw.regs; int pw_idx = power_well->desc->hsw.idx; - enum phy phy = ICL_AUX_PW_TO_PHY(pw_idx); + enum phy phy = icl_aux_pw_to_phy(dev_priv, power_well); u32 val; drm_WARN_ON(&dev_priv->drm, !IS_ICELAKE(dev_priv)); @@ -508,7 +514,7 @@ icl_combo_phy_aux_power_well_disable(struct drm_i915_private *dev_priv, { const struct i915_power_well_regs *regs = power_well->desc->hsw.regs; int pw_idx = power_well->desc->hsw.idx; - enum phy phy = ICL_AUX_PW_TO_PHY(pw_idx); + enum phy phy = icl_aux_pw_to_phy(dev_priv, power_well); u32 val; drm_WARN_ON(&dev_priv->drm, !IS_ICELAKE(dev_priv)); @@ -595,7 +601,7 @@ static void icl_tc_phy_aux_power_well_enable(struct drm_i915_private *dev_priv, struct i915_power_well *power_well) { - enum aux_ch aux_ch = icl_tc_phy_aux_ch(dev_priv, power_well); + enum aux_ch aux_ch = icl_aux_pw_to_ch(power_well); struct intel_digital_port *dig_port = aux_ch_to_digital_port(dev_priv, aux_ch); const struct i915_power_well_regs *regs = power_well->desc->hsw.regs; bool is_tbt = power_well->desc->hsw.is_tc_tbt; @@ -619,11 +625,9 @@ icl_tc_phy_aux_power_well_enable(struct drm_i915_private *dev_priv, * or need to enable AUX on a legacy TypeC port as part of the TC-cold * exit sequence. */ - timeout_expected = is_tbt; - if (DISPLAY_VER(dev_priv) == 11 && dig_port->tc_legacy_port) { + timeout_expected = is_tbt || intel_tc_cold_requires_aux_pw(dig_port); + if (DISPLAY_VER(dev_priv) == 11 && dig_port->tc_legacy_port) icl_tc_cold_exit(dev_priv); - timeout_expected = true; - } hsw_wait_for_power_well_enable(dev_priv, power_well, timeout_expected); @@ -645,7 +649,7 @@ static void icl_tc_phy_aux_power_well_disable(struct drm_i915_private *dev_priv, struct i915_power_well *power_well) { - enum aux_ch aux_ch = icl_tc_phy_aux_ch(dev_priv, power_well); + enum aux_ch aux_ch = icl_aux_pw_to_ch(power_well); struct intel_digital_port *dig_port = aux_ch_to_digital_port(dev_priv, aux_ch); icl_tc_port_assert_ref_held(dev_priv, power_well, dig_port); @@ -657,11 +661,9 @@ static void icl_aux_power_well_enable(struct drm_i915_private *dev_priv, struct i915_power_well *power_well) { - int pw_idx = power_well->desc->hsw.idx; - enum phy phy = ICL_AUX_PW_TO_PHY(pw_idx); /* non-TBT only */ - bool is_tbt = power_well->desc->hsw.is_tc_tbt; + enum phy phy = icl_aux_pw_to_phy(dev_priv, power_well); - if (is_tbt || intel_phy_is_tc(dev_priv, phy)) + if (intel_phy_is_tc(dev_priv, phy)) return icl_tc_phy_aux_power_well_enable(dev_priv, power_well); else if (IS_ICELAKE(dev_priv)) return icl_combo_phy_aux_power_well_enable(dev_priv, @@ -674,11 +676,9 @@ static void icl_aux_power_well_disable(struct drm_i915_private *dev_priv, struct i915_power_well *power_well) { - int pw_idx = power_well->desc->hsw.idx; - enum phy phy = ICL_AUX_PW_TO_PHY(pw_idx); /* non-TBT only */ - bool is_tbt = power_well->desc->hsw.is_tc_tbt; + enum phy phy = icl_aux_pw_to_phy(dev_priv, power_well); - if (is_tbt || intel_phy_is_tc(dev_priv, phy)) + if (intel_phy_is_tc(dev_priv, phy)) return icl_tc_phy_aux_power_well_disable(dev_priv, power_well); else if (IS_ICELAKE(dev_priv)) return icl_combo_phy_aux_power_well_disable(dev_priv, @@ -829,8 +829,8 @@ static void gen9_sanitize_dc_state(struct drm_i915_private *dev_priv) drm_dbg_kms(&dev_priv->drm, "Resetting DC state tracking from %02x to %02x\n", - dev_priv->csr.dc_state, val); - dev_priv->csr.dc_state = val; + dev_priv->dmc.dc_state, val); + dev_priv->dmc.dc_state = val; } /** @@ -865,8 +865,8 @@ static void gen9_set_dc_state(struct drm_i915_private *dev_priv, u32 state) return; if (drm_WARN_ON_ONCE(&dev_priv->drm, - state & ~dev_priv->csr.allowed_dc_mask)) - state &= dev_priv->csr.allowed_dc_mask; + state & ~dev_priv->dmc.allowed_dc_mask)) + state &= dev_priv->dmc.allowed_dc_mask; val = intel_de_read(dev_priv, DC_STATE_EN); mask = gen9_dc_mask(dev_priv); @@ -874,16 +874,16 @@ static void gen9_set_dc_state(struct drm_i915_private *dev_priv, u32 state) val & mask, state); /* Check if DMC is ignoring our DC state requests */ - if ((val & mask) != dev_priv->csr.dc_state) + if ((val & mask) != dev_priv->dmc.dc_state) drm_err(&dev_priv->drm, "DC state mismatch (0x%x -> 0x%x)\n", - dev_priv->csr.dc_state, val & mask); + dev_priv->dmc.dc_state, val & mask); val &= ~mask; val |= state; gen9_write_dc_state(dev_priv, val); - dev_priv->csr.dc_state = val & mask; + dev_priv->dmc.dc_state = val & mask; } static u32 @@ -902,7 +902,7 @@ sanitize_target_dc_state(struct drm_i915_private *dev_priv, if (target_dc_state != states[i]) continue; - if (dev_priv->csr.allowed_dc_mask & target_dc_state) + if (dev_priv->dmc.allowed_dc_mask & target_dc_state) break; target_dc_state = states[i + 1]; @@ -958,15 +958,15 @@ static void bxt_disable_dc9(struct drm_i915_private *dev_priv) intel_pps_unlock_regs_wa(dev_priv); } -static void assert_csr_loaded(struct drm_i915_private *dev_priv) +static void assert_dmc_loaded(struct drm_i915_private *dev_priv) { drm_WARN_ONCE(&dev_priv->drm, - !intel_de_read(dev_priv, CSR_PROGRAM(0)), - "CSR program storage start is NULL\n"); - drm_WARN_ONCE(&dev_priv->drm, !intel_de_read(dev_priv, CSR_SSP_BASE), - "CSR SSP Base Not fine\n"); - drm_WARN_ONCE(&dev_priv->drm, !intel_de_read(dev_priv, CSR_HTP_SKL), - "CSR HTP Not fine\n"); + !intel_de_read(dev_priv, DMC_PROGRAM(0)), + "DMC program storage start is NULL\n"); + drm_WARN_ONCE(&dev_priv->drm, !intel_de_read(dev_priv, DMC_SSP_BASE), + "DMC SSP Base Not fine\n"); + drm_WARN_ONCE(&dev_priv->drm, !intel_de_read(dev_priv, DMC_HTP_SKL), + "DMC HTP Not fine\n"); } static struct i915_power_well * @@ -1016,7 +1016,7 @@ void intel_display_power_set_target_dc_state(struct drm_i915_private *dev_priv, state = sanitize_target_dc_state(dev_priv, state); - if (state == dev_priv->csr.target_dc_state) + if (state == dev_priv->dmc.target_dc_state) goto unlock; dc_off_enabled = power_well->desc->ops->is_enabled(dev_priv, @@ -1028,7 +1028,7 @@ void intel_display_power_set_target_dc_state(struct drm_i915_private *dev_priv, if (!dc_off_enabled) power_well->desc->ops->enable(dev_priv, power_well); - dev_priv->csr.target_dc_state = state; + dev_priv->dmc.target_dc_state = state; if (!dc_off_enabled) power_well->desc->ops->disable(dev_priv, power_well); @@ -1057,7 +1057,7 @@ static void assert_can_enable_dc5(struct drm_i915_private *dev_priv) "DC5 already programmed to be enabled.\n"); assert_rpm_wakelock_held(&dev_priv->runtime_pm); - assert_csr_loaded(dev_priv); + assert_dmc_loaded(dev_priv); } static void gen9_enable_dc5(struct drm_i915_private *dev_priv) @@ -1084,7 +1084,7 @@ static void assert_can_enable_dc6(struct drm_i915_private *dev_priv) DC_STATE_EN_UPTO_DC6), "DC6 already programmed to be enabled.\n"); - assert_csr_loaded(dev_priv); + assert_dmc_loaded(dev_priv); } static void skl_enable_dc6(struct drm_i915_private *dev_priv) @@ -1181,7 +1181,7 @@ static void gen9_disable_dc_states(struct drm_i915_private *dev_priv) { struct intel_cdclk_config cdclk_config = {}; - if (dev_priv->csr.target_dc_state == DC_STATE_EN_DC3CO) { + if (dev_priv->dmc.target_dc_state == DC_STATE_EN_DC3CO) { tgl_disable_dc3co(dev_priv); return; } @@ -1220,10 +1220,10 @@ static void gen9_dc_off_power_well_enable(struct drm_i915_private *dev_priv, static void gen9_dc_off_power_well_disable(struct drm_i915_private *dev_priv, struct i915_power_well *power_well) { - if (!dev_priv->csr.dmc_payload) + if (!intel_dmc_has_payload(dev_priv)) return; - switch (dev_priv->csr.target_dc_state) { + switch (dev_priv->dmc.target_dc_state) { case DC_STATE_EN_DC3CO: tgl_enable_dc3co(dev_priv); break; @@ -2265,6 +2265,12 @@ intel_display_power_put_async_work(struct work_struct *work) fetch_and_zero(&power_domains->async_put_domains[1]); queue_async_put_domains_work(power_domains, fetch_and_zero(&new_work_wakeref)); + } else { + /* + * Cancel the work that got queued after this one got dequeued, + * since here we released the corresponding async-put reference. + */ + cancel_delayed_work(&power_domains->async_put_work); } out_verify: @@ -3072,7 +3078,6 @@ intel_display_power_put_mask_in_set(struct drm_i915_private *i915, BIT_ULL(POWER_DOMAIN_PORT_DDI_C_LANES) | \ BIT_ULL(POWER_DOMAIN_PORT_DDI_LANES_D_XELPD) | \ BIT_ULL(POWER_DOMAIN_PORT_DDI_LANES_E_XELPD) | \ - BIT_ULL(POWER_DOMAIN_AUX_C) | \ BIT_ULL(POWER_DOMAIN_PORT_DDI_LANES_TC1) | \ BIT_ULL(POWER_DOMAIN_PORT_DDI_LANES_TC2) | \ BIT_ULL(POWER_DOMAIN_PORT_DDI_LANES_TC3) | \ @@ -3084,6 +3089,10 @@ intel_display_power_put_mask_in_set(struct drm_i915_private *i915, BIT_ULL(POWER_DOMAIN_AUX_USBC2) | \ BIT_ULL(POWER_DOMAIN_AUX_USBC3) | \ BIT_ULL(POWER_DOMAIN_AUX_USBC4) | \ + BIT_ULL(POWER_DOMAIN_AUX_TBT1) | \ + BIT_ULL(POWER_DOMAIN_AUX_TBT2) | \ + BIT_ULL(POWER_DOMAIN_AUX_TBT3) | \ + BIT_ULL(POWER_DOMAIN_AUX_TBT4) | \ BIT_ULL(POWER_DOMAIN_INIT)) /* @@ -5090,10 +5099,10 @@ int intel_power_domains_init(struct drm_i915_private *dev_priv) dev_priv->params.disable_power_well = sanitize_disable_power_well_option(dev_priv, dev_priv->params.disable_power_well); - dev_priv->csr.allowed_dc_mask = + dev_priv->dmc.allowed_dc_mask = get_allowed_dc_mask(dev_priv, dev_priv->params.enable_dc); - dev_priv->csr.target_dc_state = + dev_priv->dmc.target_dc_state = sanitize_target_dc_state(dev_priv, DC_STATE_EN_UPTO_DC6); BUILD_BUG_ON(POWER_DOMAIN_NUM > 64); @@ -5245,6 +5254,9 @@ static void gen12_dbuf_slices_config(struct drm_i915_private *dev_priv) { enum dbuf_slice slice; + if (IS_ALDERLAKE_P(dev_priv)) + return; + for_each_dbuf_slice(dev_priv, slice) intel_de_rmw(dev_priv, DBUF_CTL_S(slice), DBUF_TRACKER_STATE_SERVICE_MASK, @@ -5256,6 +5268,9 @@ static void icl_mbus_init(struct drm_i915_private *dev_priv) unsigned long abox_regs = INTEL_INFO(dev_priv)->abox_mask; u32 mask, val, i; + if (IS_ALDERLAKE_P(dev_priv)) + return; + mask = MBUS_ABOX_BT_CREDIT_POOL1_MASK | MBUS_ABOX_BT_CREDIT_POOL2_MASK | MBUS_ABOX_B_CREDIT_MASK | @@ -5573,8 +5588,8 @@ static void skl_display_core_init(struct drm_i915_private *dev_priv, gen9_dbuf_enable(dev_priv); - if (resume && dev_priv->csr.dmc_payload) - intel_csr_load_program(dev_priv); + if (resume && intel_dmc_has_payload(dev_priv)) + intel_dmc_load_program(dev_priv); } static void skl_display_core_uninit(struct drm_i915_private *dev_priv) @@ -5640,8 +5655,8 @@ static void bxt_display_core_init(struct drm_i915_private *dev_priv, bool resume gen9_dbuf_enable(dev_priv); - if (resume && dev_priv->csr.dmc_payload) - intel_csr_load_program(dev_priv); + if (resume && intel_dmc_has_payload(dev_priv)) + intel_dmc_load_program(dev_priv); } static void bxt_display_core_uninit(struct drm_i915_private *dev_priv) @@ -5706,8 +5721,8 @@ 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); + if (resume && intel_dmc_has_payload(dev_priv)) + intel_dmc_load_program(dev_priv); } static void cnl_display_core_uninit(struct drm_i915_private *dev_priv) @@ -5863,8 +5878,8 @@ static void icl_display_core_init(struct drm_i915_private *dev_priv, if (DISPLAY_VER(dev_priv) >= 12) tgl_bw_buddy_init(dev_priv); - if (resume && dev_priv->csr.dmc_payload) - intel_csr_load_program(dev_priv); + if (resume && intel_dmc_has_payload(dev_priv)) + intel_dmc_load_program(dev_priv); /* Wa_14011508470 */ if (DISPLAY_VER(dev_priv) == 12) { @@ -6218,13 +6233,13 @@ void intel_power_domains_suspend(struct drm_i915_private *i915, /* * In case of suspend-to-idle (aka S0ix) on a DMC platform without DC9 * support don't manually deinit the power domains. This also means the - * CSR/DMC firmware will stay active, it will power down any HW + * DMC firmware will stay active, it will power down any HW * resources as required and also enable deeper system power states * that would be blocked if the firmware was inactive. */ - if (!(i915->csr.allowed_dc_mask & DC_STATE_EN_DC9) && + if (!(i915->dmc.allowed_dc_mask & DC_STATE_EN_DC9) && suspend_mode == I915_DRM_SUSPEND_IDLE && - i915->csr.dmc_payload) { + intel_dmc_has_payload(i915)) { intel_display_power_flush_work(i915); intel_power_domains_verify_state(i915); return; @@ -6414,19 +6429,19 @@ void intel_display_power_resume(struct drm_i915_private *i915) if (DISPLAY_VER(i915) >= 11) { bxt_disable_dc9(i915); icl_display_core_init(i915, true); - if (i915->csr.dmc_payload) { - if (i915->csr.allowed_dc_mask & + if (intel_dmc_has_payload(i915)) { + if (i915->dmc.allowed_dc_mask & DC_STATE_EN_UPTO_DC6) skl_enable_dc6(i915); - else if (i915->csr.allowed_dc_mask & + else if (i915->dmc.allowed_dc_mask & DC_STATE_EN_UPTO_DC5) gen9_enable_dc5(i915); } } else if (IS_GEMINILAKE(i915) || IS_BROXTON(i915)) { bxt_disable_dc9(i915); bxt_display_core_init(i915, true); - if (i915->csr.dmc_payload && - (i915->csr.allowed_dc_mask & DC_STATE_EN_UPTO_DC5)) + if (intel_dmc_has_payload(i915) && + (i915->dmc.allowed_dc_mask & DC_STATE_EN_UPTO_DC5)) gen9_enable_dc5(i915); } else if (IS_HASWELL(i915) || IS_BROADWELL(i915)) { hsw_disable_pc8(i915); diff --git a/drivers/gpu/drm/i915/display/intel_display_types.h b/drivers/gpu/drm/i915/display/intel_display_types.h index 9c0adfc60c6f..ee7cbdd7db87 100644 --- a/drivers/gpu/drm/i915/display/intel_display_types.h +++ b/drivers/gpu/drm/i915/display/intel_display_types.h @@ -1202,7 +1202,7 @@ struct intel_crtc_state { struct { bool enable; u8 pipeline_full; - u16 flipline, vmin, vmax; + u16 flipline, vmin, vmax, guardband; } vrr; /* Stream Splitter for eDP MSO */ @@ -1482,6 +1482,7 @@ struct intel_psr { bool sink_support; bool source_support; bool enabled; + bool paused; enum pipe pipe; enum transcoder transcoder; bool active; @@ -1498,7 +1499,7 @@ struct intel_psr { bool sink_not_reliable; bool irq_aux_error; u16 su_x_granularity; - bool dc3co_enabled; + u32 dc3co_exitline; u32 dc3co_exit_delay; struct delayed_work dc3co_work; struct drm_dp_vsc_sdp vsc; diff --git a/drivers/gpu/drm/i915/display/intel_csr.c b/drivers/gpu/drm/i915/display/intel_dmc.c index 26a922d34263..97308da28059 100644 --- a/drivers/gpu/drm/i915/display/intel_csr.c +++ b/drivers/gpu/drm/i915/display/intel_dmc.c @@ -26,14 +26,13 @@ #include "i915_drv.h" #include "i915_reg.h" -#include "intel_csr.h" #include "intel_de.h" +#include "intel_dmc.h" /** - * DOC: csr support for dmc + * DOC: DMC Firmware Support * - * Display Context Save and Restore (CSR) firmware support added from gen9 - * onwards to drive newly added DMC (Display microcontroller) in display + * From gen9 onwards we have newly added DMC (Display microcontroller) in display * engine to save and restore the state of display engine when it enter into * low-power state and comes back to normal. */ @@ -44,55 +43,55 @@ __stringify(major) "_" \ __stringify(minor) ".bin" -#define GEN12_CSR_MAX_FW_SIZE ICL_CSR_MAX_FW_SIZE +#define GEN12_DMC_MAX_FW_SIZE ICL_DMC_MAX_FW_SIZE -#define ADLS_CSR_PATH DMC_PATH(adls, 2, 01) -#define ADLS_CSR_VERSION_REQUIRED CSR_VERSION(2, 1) -MODULE_FIRMWARE(ADLS_CSR_PATH); +#define ADLS_DMC_PATH DMC_PATH(adls, 2, 01) +#define ADLS_DMC_VERSION_REQUIRED DMC_VERSION(2, 1) +MODULE_FIRMWARE(ADLS_DMC_PATH); -#define DG1_CSR_PATH DMC_PATH(dg1, 2, 02) -#define DG1_CSR_VERSION_REQUIRED CSR_VERSION(2, 2) -MODULE_FIRMWARE(DG1_CSR_PATH); +#define DG1_DMC_PATH DMC_PATH(dg1, 2, 02) +#define DG1_DMC_VERSION_REQUIRED DMC_VERSION(2, 2) +MODULE_FIRMWARE(DG1_DMC_PATH); -#define RKL_CSR_PATH DMC_PATH(rkl, 2, 02) -#define RKL_CSR_VERSION_REQUIRED CSR_VERSION(2, 2) -MODULE_FIRMWARE(RKL_CSR_PATH); +#define RKL_DMC_PATH DMC_PATH(rkl, 2, 02) +#define RKL_DMC_VERSION_REQUIRED DMC_VERSION(2, 2) +MODULE_FIRMWARE(RKL_DMC_PATH); -#define TGL_CSR_PATH DMC_PATH(tgl, 2, 08) -#define TGL_CSR_VERSION_REQUIRED CSR_VERSION(2, 8) -MODULE_FIRMWARE(TGL_CSR_PATH); +#define TGL_DMC_PATH DMC_PATH(tgl, 2, 08) +#define TGL_DMC_VERSION_REQUIRED DMC_VERSION(2, 8) +MODULE_FIRMWARE(TGL_DMC_PATH); -#define ICL_CSR_PATH DMC_PATH(icl, 1, 09) -#define ICL_CSR_VERSION_REQUIRED CSR_VERSION(1, 9) -#define ICL_CSR_MAX_FW_SIZE 0x6000 -MODULE_FIRMWARE(ICL_CSR_PATH); +#define ICL_DMC_PATH DMC_PATH(icl, 1, 09) +#define ICL_DMC_VERSION_REQUIRED DMC_VERSION(1, 9) +#define ICL_DMC_MAX_FW_SIZE 0x6000 +MODULE_FIRMWARE(ICL_DMC_PATH); -#define CNL_CSR_PATH DMC_PATH(cnl, 1, 07) -#define CNL_CSR_VERSION_REQUIRED CSR_VERSION(1, 7) -#define CNL_CSR_MAX_FW_SIZE GLK_CSR_MAX_FW_SIZE -MODULE_FIRMWARE(CNL_CSR_PATH); +#define CNL_DMC_PATH DMC_PATH(cnl, 1, 07) +#define CNL_DMC_VERSION_REQUIRED DMC_VERSION(1, 7) +#define CNL_DMC_MAX_FW_SIZE GLK_DMC_MAX_FW_SIZE +MODULE_FIRMWARE(CNL_DMC_PATH); -#define GLK_CSR_PATH DMC_PATH(glk, 1, 04) -#define GLK_CSR_VERSION_REQUIRED CSR_VERSION(1, 4) -#define GLK_CSR_MAX_FW_SIZE 0x4000 -MODULE_FIRMWARE(GLK_CSR_PATH); +#define GLK_DMC_PATH DMC_PATH(glk, 1, 04) +#define GLK_DMC_VERSION_REQUIRED DMC_VERSION(1, 4) +#define GLK_DMC_MAX_FW_SIZE 0x4000 +MODULE_FIRMWARE(GLK_DMC_PATH); -#define KBL_CSR_PATH DMC_PATH(kbl, 1, 04) -#define KBL_CSR_VERSION_REQUIRED CSR_VERSION(1, 4) -#define KBL_CSR_MAX_FW_SIZE BXT_CSR_MAX_FW_SIZE -MODULE_FIRMWARE(KBL_CSR_PATH); +#define KBL_DMC_PATH DMC_PATH(kbl, 1, 04) +#define KBL_DMC_VERSION_REQUIRED DMC_VERSION(1, 4) +#define KBL_DMC_MAX_FW_SIZE BXT_DMC_MAX_FW_SIZE +MODULE_FIRMWARE(KBL_DMC_PATH); -#define SKL_CSR_PATH DMC_PATH(skl, 1, 27) -#define SKL_CSR_VERSION_REQUIRED CSR_VERSION(1, 27) -#define SKL_CSR_MAX_FW_SIZE BXT_CSR_MAX_FW_SIZE -MODULE_FIRMWARE(SKL_CSR_PATH); +#define SKL_DMC_PATH DMC_PATH(skl, 1, 27) +#define SKL_DMC_VERSION_REQUIRED DMC_VERSION(1, 27) +#define SKL_DMC_MAX_FW_SIZE BXT_DMC_MAX_FW_SIZE +MODULE_FIRMWARE(SKL_DMC_PATH); -#define BXT_CSR_PATH DMC_PATH(bxt, 1, 07) -#define BXT_CSR_VERSION_REQUIRED CSR_VERSION(1, 7) -#define BXT_CSR_MAX_FW_SIZE 0x3000 -MODULE_FIRMWARE(BXT_CSR_PATH); +#define BXT_DMC_PATH DMC_PATH(bxt, 1, 07) +#define BXT_DMC_VERSION_REQUIRED DMC_VERSION(1, 7) +#define BXT_DMC_MAX_FW_SIZE 0x3000 +MODULE_FIRMWARE(BXT_DMC_PATH); -#define CSR_DEFAULT_FW_OFFSET 0xFFFFFFFF +#define DMC_DEFAULT_FW_OFFSET 0xFFFFFFFF #define PACKAGE_MAX_FW_INFO_ENTRIES 20 #define PACKAGE_V2_MAX_FW_INFO_ENTRIES 32 #define DMC_V1_MAX_MMIO_COUNT 8 @@ -238,6 +237,11 @@ struct stepping_info { char substepping; }; +bool intel_dmc_has_payload(struct drm_i915_private *i915) +{ + return i915->dmc.dmc_payload; +} + static const struct stepping_info skl_stepping_info[] = { {'A', '0'}, {'B', '0'}, {'C', '0'}, {'D', '0'}, {'E', '0'}, {'F', '0'}, @@ -303,47 +307,47 @@ static void gen9_set_dc_state_debugmask(struct drm_i915_private *dev_priv) } /** - * intel_csr_load_program() - write the firmware from memory to register. + * intel_dmc_load_program() - write the firmware from memory to register. * @dev_priv: i915 drm device. * - * CSR firmware is read from a .bin file and kept in internal memory one time. + * DMC firmware is read from a .bin file and kept in internal memory one time. * Everytime display comes back from low power state this function is called to * copy the firmware from internal memory to registers. */ -void intel_csr_load_program(struct drm_i915_private *dev_priv) +void intel_dmc_load_program(struct drm_i915_private *dev_priv) { - u32 *payload = dev_priv->csr.dmc_payload; + u32 *payload = dev_priv->dmc.dmc_payload; u32 i, fw_size; - if (!HAS_CSR(dev_priv)) { + if (!HAS_DMC(dev_priv)) { drm_err(&dev_priv->drm, - "No CSR support available for this platform\n"); + "No DMC support available for this platform\n"); return; } - if (!dev_priv->csr.dmc_payload) { + if (!intel_dmc_has_payload(dev_priv)) { drm_err(&dev_priv->drm, "Tried to program CSR with empty payload\n"); return; } - fw_size = dev_priv->csr.dmc_fw_size; + fw_size = dev_priv->dmc.dmc_fw_size; assert_rpm_wakelock_held(&dev_priv->runtime_pm); preempt_disable(); for (i = 0; i < fw_size; i++) - intel_uncore_write_fw(&dev_priv->uncore, CSR_PROGRAM(i), + intel_uncore_write_fw(&dev_priv->uncore, DMC_PROGRAM(i), payload[i]); preempt_enable(); - for (i = 0; i < dev_priv->csr.mmio_count; i++) { - intel_de_write(dev_priv, dev_priv->csr.mmioaddr[i], - dev_priv->csr.mmiodata[i]); + for (i = 0; i < dev_priv->dmc.mmio_count; i++) { + intel_de_write(dev_priv, dev_priv->dmc.mmioaddr[i], + dev_priv->dmc.mmiodata[i]); } - dev_priv->csr.dc_state = 0; + dev_priv->dmc.dc_state = 0; gen9_set_dc_state_debugmask(dev_priv); } @@ -357,7 +361,7 @@ static u32 find_dmc_fw_offset(const struct intel_fw_info *fw_info, const struct stepping_info *si, u8 package_ver) { - u32 dmc_offset = CSR_DEFAULT_FW_OFFSET; + u32 dmc_offset = DMC_DEFAULT_FW_OFFSET; unsigned int i; for (i = 0; i < num_entries; i++) { @@ -392,17 +396,18 @@ static u32 find_dmc_fw_offset(const struct intel_fw_info *fw_info, return dmc_offset; } -static u32 parse_csr_fw_dmc(struct intel_csr *csr, - const struct intel_dmc_header_base *dmc_header, - size_t rem_size) +static u32 parse_dmc_fw_header(struct intel_dmc *dmc, + const struct intel_dmc_header_base *dmc_header, + size_t rem_size) { + struct drm_i915_private *i915 = container_of(dmc, typeof(*i915), dmc); unsigned int header_len_bytes, dmc_header_size, payload_size, i; const u32 *mmioaddr, *mmiodata; u32 mmio_count, mmio_count_max; u8 *payload; - BUILD_BUG_ON(ARRAY_SIZE(csr->mmioaddr) < DMC_V3_MAX_MMIO_COUNT || - ARRAY_SIZE(csr->mmioaddr) < DMC_V1_MAX_MMIO_COUNT); + BUILD_BUG_ON(ARRAY_SIZE(dmc->mmioaddr) < DMC_V3_MAX_MMIO_COUNT || + ARRAY_SIZE(dmc->mmioaddr) < DMC_V1_MAX_MMIO_COUNT); /* * Check if we can access common fields, we will checkc again below @@ -440,34 +445,34 @@ static u32 parse_csr_fw_dmc(struct intel_csr *csr, header_len_bytes = dmc_header->header_len; dmc_header_size = sizeof(*v1); } else { - DRM_ERROR("Unknown DMC fw header version: %u\n", - dmc_header->header_ver); + drm_err(&i915->drm, "Unknown DMC fw header version: %u\n", + dmc_header->header_ver); return 0; } if (header_len_bytes != dmc_header_size) { - DRM_ERROR("DMC firmware has wrong dmc header length " - "(%u bytes)\n", header_len_bytes); + drm_err(&i915->drm, "DMC firmware has wrong dmc header length " + "(%u bytes)\n", header_len_bytes); return 0; } /* Cache the dmc header info. */ if (mmio_count > mmio_count_max) { - DRM_ERROR("DMC firmware has wrong mmio count %u\n", mmio_count); + drm_err(&i915->drm, "DMC firmware has wrong mmio count %u\n", mmio_count); return 0; } for (i = 0; i < mmio_count; i++) { - if (mmioaddr[i] < CSR_MMIO_START_RANGE || - mmioaddr[i] > CSR_MMIO_END_RANGE) { - DRM_ERROR("DMC firmware has wrong mmio address 0x%x\n", - mmioaddr[i]); + if (mmioaddr[i] < DMC_MMIO_START_RANGE || + mmioaddr[i] > DMC_MMIO_END_RANGE) { + drm_err(&i915->drm, "DMC firmware has wrong mmio address 0x%x\n", + mmioaddr[i]); return 0; } - csr->mmioaddr[i] = _MMIO(mmioaddr[i]); - csr->mmiodata[i] = mmiodata[i]; + dmc->mmioaddr[i] = _MMIO(mmioaddr[i]); + dmc->mmiodata[i] = mmiodata[i]; } - csr->mmio_count = mmio_count; + dmc->mmio_count = mmio_count; rem_size -= header_len_bytes; @@ -476,34 +481,33 @@ static u32 parse_csr_fw_dmc(struct intel_csr *csr, if (rem_size < payload_size) goto error_truncated; - if (payload_size > csr->max_fw_size) { - DRM_ERROR("DMC FW too big (%u bytes)\n", payload_size); + if (payload_size > dmc->max_fw_size) { + drm_err(&i915->drm, "DMC FW too big (%u bytes)\n", payload_size); return 0; } - csr->dmc_fw_size = dmc_header->fw_size; + dmc->dmc_fw_size = dmc_header->fw_size; - csr->dmc_payload = kmalloc(payload_size, GFP_KERNEL); - if (!csr->dmc_payload) { - DRM_ERROR("Memory allocation failed for dmc payload\n"); + dmc->dmc_payload = kmalloc(payload_size, GFP_KERNEL); + if (!dmc->dmc_payload) return 0; - } payload = (u8 *)(dmc_header) + header_len_bytes; - memcpy(csr->dmc_payload, payload, payload_size); + memcpy(dmc->dmc_payload, payload, payload_size); return header_len_bytes + payload_size; error_truncated: - DRM_ERROR("Truncated DMC firmware, refusing.\n"); + drm_err(&i915->drm, "Truncated DMC firmware, refusing.\n"); return 0; } static u32 -parse_csr_fw_package(struct intel_csr *csr, +parse_dmc_fw_package(struct intel_dmc *dmc, const struct intel_package_header *package_header, const struct stepping_info *si, size_t rem_size) { + struct drm_i915_private *i915 = container_of(dmc, typeof(*i915), dmc); u32 package_size = sizeof(struct intel_package_header); u32 num_entries, max_entries, dmc_offset; const struct intel_fw_info *fw_info; @@ -516,8 +520,8 @@ parse_csr_fw_package(struct intel_csr *csr, } else if (package_header->header_ver == 2) { max_entries = PACKAGE_V2_MAX_FW_INFO_ENTRIES; } else { - DRM_ERROR("DMC firmware has unknown header version %u\n", - package_header->header_ver); + drm_err(&i915->drm, "DMC firmware has unknown header version %u\n", + package_header->header_ver); return 0; } @@ -530,8 +534,8 @@ parse_csr_fw_package(struct intel_csr *csr, goto error_truncated; if (package_header->header_len * 4 != package_size) { - DRM_ERROR("DMC firmware has wrong package header length " - "(%u bytes)\n", package_size); + drm_err(&i915->drm, "DMC firmware has wrong package header length " + "(%u bytes)\n", package_size); return 0; } @@ -543,9 +547,9 @@ parse_csr_fw_package(struct intel_csr *csr, ((u8 *)package_header + sizeof(*package_header)); dmc_offset = find_dmc_fw_offset(fw_info, num_entries, si, package_header->header_ver); - if (dmc_offset == CSR_DEFAULT_FW_OFFSET) { - DRM_ERROR("DMC firmware not supported for %c stepping\n", - si->stepping); + if (dmc_offset == DMC_DEFAULT_FW_OFFSET) { + drm_err(&i915->drm, "DMC firmware not supported for %c stepping\n", + si->stepping); return 0; } @@ -553,51 +557,53 @@ parse_csr_fw_package(struct intel_csr *csr, return package_size + dmc_offset * 4; error_truncated: - DRM_ERROR("Truncated DMC firmware, refusing.\n"); + drm_err(&i915->drm, "Truncated DMC firmware, refusing.\n"); return 0; } /* Return number of bytes parsed or 0 on error */ -static u32 parse_csr_fw_css(struct intel_csr *csr, +static u32 parse_dmc_fw_css(struct intel_dmc *dmc, struct intel_css_header *css_header, size_t rem_size) { + struct drm_i915_private *i915 = container_of(dmc, typeof(*i915), dmc); + if (rem_size < sizeof(struct intel_css_header)) { - DRM_ERROR("Truncated DMC firmware, refusing.\n"); + drm_err(&i915->drm, "Truncated DMC firmware, refusing.\n"); return 0; } if (sizeof(struct intel_css_header) != (css_header->header_len * 4)) { - DRM_ERROR("DMC firmware has wrong CSS header length " - "(%u bytes)\n", - (css_header->header_len * 4)); + drm_err(&i915->drm, "DMC firmware has wrong CSS header length " + "(%u bytes)\n", + (css_header->header_len * 4)); return 0; } - if (csr->required_version && - css_header->version != csr->required_version) { - DRM_INFO("Refusing to load DMC firmware v%u.%u," + if (dmc->required_version && + css_header->version != dmc->required_version) { + drm_info(&i915->drm, "Refusing to load DMC firmware v%u.%u," " please use v%u.%u\n", - CSR_VERSION_MAJOR(css_header->version), - CSR_VERSION_MINOR(css_header->version), - CSR_VERSION_MAJOR(csr->required_version), - CSR_VERSION_MINOR(csr->required_version)); + DMC_VERSION_MAJOR(css_header->version), + DMC_VERSION_MINOR(css_header->version), + DMC_VERSION_MAJOR(dmc->required_version), + DMC_VERSION_MINOR(dmc->required_version)); return 0; } - csr->version = css_header->version; + dmc->version = css_header->version; return sizeof(struct intel_css_header); } -static void parse_csr_fw(struct drm_i915_private *dev_priv, +static void parse_dmc_fw(struct drm_i915_private *dev_priv, const struct firmware *fw) { struct intel_css_header *css_header; struct intel_package_header *package_header; struct intel_dmc_header_base *dmc_header; - struct intel_csr *csr = &dev_priv->csr; + struct intel_dmc *dmc = &dev_priv->dmc; const struct stepping_info *si = intel_get_stepping_info(dev_priv); u32 readcount = 0; u32 r; @@ -607,7 +613,7 @@ static void parse_csr_fw(struct drm_i915_private *dev_priv, /* Extract CSS Header information */ css_header = (struct intel_css_header *)fw->data; - r = parse_csr_fw_css(csr, css_header, fw->size); + r = parse_dmc_fw_css(dmc, css_header, fw->size); if (!r) return; @@ -615,7 +621,7 @@ static void parse_csr_fw(struct drm_i915_private *dev_priv, /* Extract Package Header information */ package_header = (struct intel_package_header *)&fw->data[readcount]; - r = parse_csr_fw_package(csr, package_header, si, fw->size - readcount); + r = parse_dmc_fw_package(dmc, package_header, si, fw->size - readcount); if (!r) return; @@ -623,49 +629,49 @@ static void parse_csr_fw(struct drm_i915_private *dev_priv, /* Extract dmc_header information */ dmc_header = (struct intel_dmc_header_base *)&fw->data[readcount]; - parse_csr_fw_dmc(csr, dmc_header, fw->size - readcount); + parse_dmc_fw_header(dmc, dmc_header, fw->size - readcount); } -static void intel_csr_runtime_pm_get(struct drm_i915_private *dev_priv) +static void intel_dmc_runtime_pm_get(struct drm_i915_private *dev_priv) { - drm_WARN_ON(&dev_priv->drm, dev_priv->csr.wakeref); - dev_priv->csr.wakeref = + drm_WARN_ON(&dev_priv->drm, dev_priv->dmc.wakeref); + dev_priv->dmc.wakeref = intel_display_power_get(dev_priv, POWER_DOMAIN_INIT); } -static void intel_csr_runtime_pm_put(struct drm_i915_private *dev_priv) +static void intel_dmc_runtime_pm_put(struct drm_i915_private *dev_priv) { intel_wakeref_t wakeref __maybe_unused = - fetch_and_zero(&dev_priv->csr.wakeref); + fetch_and_zero(&dev_priv->dmc.wakeref); intel_display_power_put(dev_priv, POWER_DOMAIN_INIT, wakeref); } -static void csr_load_work_fn(struct work_struct *work) +static void dmc_load_work_fn(struct work_struct *work) { struct drm_i915_private *dev_priv; - struct intel_csr *csr; + struct intel_dmc *dmc; const struct firmware *fw = NULL; - dev_priv = container_of(work, typeof(*dev_priv), csr.work); - csr = &dev_priv->csr; + dev_priv = container_of(work, typeof(*dev_priv), dmc.work); + dmc = &dev_priv->dmc; - request_firmware(&fw, dev_priv->csr.fw_path, dev_priv->drm.dev); - parse_csr_fw(dev_priv, fw); + request_firmware(&fw, dev_priv->dmc.fw_path, dev_priv->drm.dev); + parse_dmc_fw(dev_priv, fw); - if (dev_priv->csr.dmc_payload) { - intel_csr_load_program(dev_priv); - intel_csr_runtime_pm_put(dev_priv); + if (intel_dmc_has_payload(dev_priv)) { + intel_dmc_load_program(dev_priv); + intel_dmc_runtime_pm_put(dev_priv); drm_info(&dev_priv->drm, "Finished loading DMC firmware %s (v%u.%u)\n", - dev_priv->csr.fw_path, CSR_VERSION_MAJOR(csr->version), - CSR_VERSION_MINOR(csr->version)); + dev_priv->dmc.fw_path, DMC_VERSION_MAJOR(dmc->version), + DMC_VERSION_MINOR(dmc->version)); } else { drm_notice(&dev_priv->drm, "Failed to load DMC firmware %s." " Disabling runtime power management.\n", - csr->fw_path); + dmc->fw_path); drm_notice(&dev_priv->drm, "DMC firmware homepage: %s", INTEL_UC_FIRMWARE_URL); } @@ -674,152 +680,152 @@ static void csr_load_work_fn(struct work_struct *work) } /** - * intel_csr_ucode_init() - initialize the firmware loading. + * intel_dmc_ucode_init() - initialize the firmware loading. * @dev_priv: i915 drm device. * * This function is called at the time of loading the display driver to read * firmware from a .bin file and copied into a internal memory. */ -void intel_csr_ucode_init(struct drm_i915_private *dev_priv) +void intel_dmc_ucode_init(struct drm_i915_private *dev_priv) { - struct intel_csr *csr = &dev_priv->csr; + struct intel_dmc *dmc = &dev_priv->dmc; - INIT_WORK(&dev_priv->csr.work, csr_load_work_fn); + INIT_WORK(&dev_priv->dmc.work, dmc_load_work_fn); - if (!HAS_CSR(dev_priv)) + if (!HAS_DMC(dev_priv)) return; /* - * Obtain a runtime pm reference, until CSR is loaded, to avoid entering + * Obtain a runtime pm reference, until DMC is loaded, to avoid entering * runtime-suspend. * * On error, we return with the rpm wakeref held to prevent runtime - * suspend as runtime suspend *requires* a working CSR for whatever + * suspend as runtime suspend *requires* a working DMC for whatever * reason. */ - intel_csr_runtime_pm_get(dev_priv); + intel_dmc_runtime_pm_get(dev_priv); if (IS_ALDERLAKE_S(dev_priv)) { - csr->fw_path = ADLS_CSR_PATH; - csr->required_version = ADLS_CSR_VERSION_REQUIRED; - csr->max_fw_size = GEN12_CSR_MAX_FW_SIZE; + dmc->fw_path = ADLS_DMC_PATH; + dmc->required_version = ADLS_DMC_VERSION_REQUIRED; + dmc->max_fw_size = GEN12_DMC_MAX_FW_SIZE; } else if (IS_DG1(dev_priv)) { - csr->fw_path = DG1_CSR_PATH; - csr->required_version = DG1_CSR_VERSION_REQUIRED; - csr->max_fw_size = GEN12_CSR_MAX_FW_SIZE; + dmc->fw_path = DG1_DMC_PATH; + dmc->required_version = DG1_DMC_VERSION_REQUIRED; + dmc->max_fw_size = GEN12_DMC_MAX_FW_SIZE; } else if (IS_ROCKETLAKE(dev_priv)) { - csr->fw_path = RKL_CSR_PATH; - csr->required_version = RKL_CSR_VERSION_REQUIRED; - csr->max_fw_size = GEN12_CSR_MAX_FW_SIZE; + dmc->fw_path = RKL_DMC_PATH; + dmc->required_version = RKL_DMC_VERSION_REQUIRED; + dmc->max_fw_size = GEN12_DMC_MAX_FW_SIZE; } else if (DISPLAY_VER(dev_priv) >= 12) { - csr->fw_path = TGL_CSR_PATH; - csr->required_version = TGL_CSR_VERSION_REQUIRED; - csr->max_fw_size = GEN12_CSR_MAX_FW_SIZE; + dmc->fw_path = TGL_DMC_PATH; + dmc->required_version = TGL_DMC_VERSION_REQUIRED; + dmc->max_fw_size = GEN12_DMC_MAX_FW_SIZE; } else if (DISPLAY_VER(dev_priv) == 11) { - csr->fw_path = ICL_CSR_PATH; - csr->required_version = ICL_CSR_VERSION_REQUIRED; - csr->max_fw_size = ICL_CSR_MAX_FW_SIZE; + dmc->fw_path = ICL_DMC_PATH; + dmc->required_version = ICL_DMC_VERSION_REQUIRED; + dmc->max_fw_size = ICL_DMC_MAX_FW_SIZE; } else if (IS_CANNONLAKE(dev_priv)) { - csr->fw_path = CNL_CSR_PATH; - csr->required_version = CNL_CSR_VERSION_REQUIRED; - csr->max_fw_size = CNL_CSR_MAX_FW_SIZE; + dmc->fw_path = CNL_DMC_PATH; + dmc->required_version = CNL_DMC_VERSION_REQUIRED; + dmc->max_fw_size = CNL_DMC_MAX_FW_SIZE; } else if (IS_GEMINILAKE(dev_priv)) { - csr->fw_path = GLK_CSR_PATH; - csr->required_version = GLK_CSR_VERSION_REQUIRED; - csr->max_fw_size = GLK_CSR_MAX_FW_SIZE; + dmc->fw_path = GLK_DMC_PATH; + dmc->required_version = GLK_DMC_VERSION_REQUIRED; + dmc->max_fw_size = GLK_DMC_MAX_FW_SIZE; } else if (IS_KABYLAKE(dev_priv) || IS_COFFEELAKE(dev_priv) || IS_COMETLAKE(dev_priv)) { - csr->fw_path = KBL_CSR_PATH; - csr->required_version = KBL_CSR_VERSION_REQUIRED; - csr->max_fw_size = KBL_CSR_MAX_FW_SIZE; + dmc->fw_path = KBL_DMC_PATH; + dmc->required_version = KBL_DMC_VERSION_REQUIRED; + dmc->max_fw_size = KBL_DMC_MAX_FW_SIZE; } else if (IS_SKYLAKE(dev_priv)) { - csr->fw_path = SKL_CSR_PATH; - csr->required_version = SKL_CSR_VERSION_REQUIRED; - csr->max_fw_size = SKL_CSR_MAX_FW_SIZE; + dmc->fw_path = SKL_DMC_PATH; + dmc->required_version = SKL_DMC_VERSION_REQUIRED; + dmc->max_fw_size = SKL_DMC_MAX_FW_SIZE; } else if (IS_BROXTON(dev_priv)) { - csr->fw_path = BXT_CSR_PATH; - csr->required_version = BXT_CSR_VERSION_REQUIRED; - csr->max_fw_size = BXT_CSR_MAX_FW_SIZE; + dmc->fw_path = BXT_DMC_PATH; + dmc->required_version = BXT_DMC_VERSION_REQUIRED; + dmc->max_fw_size = BXT_DMC_MAX_FW_SIZE; } if (dev_priv->params.dmc_firmware_path) { if (strlen(dev_priv->params.dmc_firmware_path) == 0) { - csr->fw_path = NULL; + dmc->fw_path = NULL; drm_info(&dev_priv->drm, - "Disabling CSR firmware and runtime PM\n"); + "Disabling DMC firmware and runtime PM\n"); return; } - csr->fw_path = dev_priv->params.dmc_firmware_path; + dmc->fw_path = dev_priv->params.dmc_firmware_path; /* Bypass version check for firmware override. */ - csr->required_version = 0; + dmc->required_version = 0; } - if (csr->fw_path == NULL) { + if (!dmc->fw_path) { drm_dbg_kms(&dev_priv->drm, - "No known CSR firmware for platform, disabling runtime PM\n"); + "No known DMC firmware for platform, disabling runtime PM\n"); return; } - drm_dbg_kms(&dev_priv->drm, "Loading %s\n", csr->fw_path); - schedule_work(&dev_priv->csr.work); + drm_dbg_kms(&dev_priv->drm, "Loading %s\n", dmc->fw_path); + schedule_work(&dev_priv->dmc.work); } /** - * intel_csr_ucode_suspend() - prepare CSR firmware before system suspend + * intel_dmc_ucode_suspend() - prepare DMC firmware before system suspend * @dev_priv: i915 drm device * * Prepare the DMC firmware before entering system suspend. This includes * flushing pending work items and releasing any resources acquired during * init. */ -void intel_csr_ucode_suspend(struct drm_i915_private *dev_priv) +void intel_dmc_ucode_suspend(struct drm_i915_private *dev_priv) { - if (!HAS_CSR(dev_priv)) + if (!HAS_DMC(dev_priv)) return; - flush_work(&dev_priv->csr.work); + flush_work(&dev_priv->dmc.work); /* Drop the reference held in case DMC isn't loaded. */ - if (!dev_priv->csr.dmc_payload) - intel_csr_runtime_pm_put(dev_priv); + if (!intel_dmc_has_payload(dev_priv)) + intel_dmc_runtime_pm_put(dev_priv); } /** - * intel_csr_ucode_resume() - init CSR firmware during system resume + * intel_dmc_ucode_resume() - init DMC firmware during system resume * @dev_priv: i915 drm device * * Reinitialize the DMC firmware during system resume, reacquiring any - * resources released in intel_csr_ucode_suspend(). + * resources released in intel_dmc_ucode_suspend(). */ -void intel_csr_ucode_resume(struct drm_i915_private *dev_priv) +void intel_dmc_ucode_resume(struct drm_i915_private *dev_priv) { - if (!HAS_CSR(dev_priv)) + if (!HAS_DMC(dev_priv)) return; /* * Reacquire the reference to keep RPM disabled in case DMC isn't * loaded. */ - if (!dev_priv->csr.dmc_payload) - intel_csr_runtime_pm_get(dev_priv); + if (!intel_dmc_has_payload(dev_priv)) + intel_dmc_runtime_pm_get(dev_priv); } /** - * intel_csr_ucode_fini() - unload the CSR firmware. + * intel_dmc_ucode_fini() - unload the DMC firmware. * @dev_priv: i915 drm device. * * Firmmware unloading includes freeing the internal memory and reset the * firmware loading status. */ -void intel_csr_ucode_fini(struct drm_i915_private *dev_priv) +void intel_dmc_ucode_fini(struct drm_i915_private *dev_priv) { - if (!HAS_CSR(dev_priv)) + if (!HAS_DMC(dev_priv)) return; - intel_csr_ucode_suspend(dev_priv); - drm_WARN_ON(&dev_priv->drm, dev_priv->csr.wakeref); + intel_dmc_ucode_suspend(dev_priv); + drm_WARN_ON(&dev_priv->drm, dev_priv->dmc.wakeref); - kfree(dev_priv->csr.dmc_payload); + kfree(dev_priv->dmc.dmc_payload); } diff --git a/drivers/gpu/drm/i915/display/intel_dmc.h b/drivers/gpu/drm/i915/display/intel_dmc.h new file mode 100644 index 000000000000..4c22f567b61b --- /dev/null +++ b/drivers/gpu/drm/i915/display/intel_dmc.h @@ -0,0 +1,43 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright © 2019 Intel Corporation + */ + +#ifndef __INTEL_DMC_H__ +#define __INTEL_DMC_H__ + +#include "i915_reg.h" +#include "intel_wakeref.h" +#include <linux/workqueue.h> + +struct drm_i915_private; + +#define DMC_VERSION(major, minor) ((major) << 16 | (minor)) +#define DMC_VERSION_MAJOR(version) ((version) >> 16) +#define DMC_VERSION_MINOR(version) ((version) & 0xffff) + +struct intel_dmc { + struct work_struct work; + const char *fw_path; + u32 required_version; + u32 max_fw_size; /* bytes */ + u32 *dmc_payload; + u32 dmc_fw_size; /* dwords */ + u32 version; + u32 mmio_count; + i915_reg_t mmioaddr[20]; + u32 mmiodata[20]; + u32 dc_state; + u32 target_dc_state; + u32 allowed_dc_mask; + intel_wakeref_t wakeref; +}; + +void intel_dmc_ucode_init(struct drm_i915_private *i915); +void intel_dmc_load_program(struct drm_i915_private *i915); +void intel_dmc_ucode_fini(struct drm_i915_private *i915); +void intel_dmc_ucode_suspend(struct drm_i915_private *i915); +void intel_dmc_ucode_resume(struct drm_i915_private *i915); +bool intel_dmc_has_payload(struct drm_i915_private *i915); + +#endif /* __INTEL_DMC_H__ */ diff --git a/drivers/gpu/drm/i915/display/intel_dp_link_training.c b/drivers/gpu/drm/i915/display/intel_dp_link_training.c index 6bf6f1ec13ed..08bceae40aa8 100644 --- a/drivers/gpu/drm/i915/display/intel_dp_link_training.c +++ b/drivers/gpu/drm/i915/display/intel_dp_link_training.c @@ -128,49 +128,13 @@ intel_dp_set_lttpr_transparent_mode(struct intel_dp *intel_dp, bool enable) return drm_dp_dpcd_write(&intel_dp->aux, DP_PHY_REPEATER_MODE, &val, 1) == 1; } -/** - * intel_dp_init_lttpr_and_dprx_caps - detect LTTPR and DPRX caps, init the LTTPR link training mode - * @intel_dp: Intel DP struct - * - * Read the LTTPR common and DPRX capabilities and switch to non-transparent - * link training mode if any is detected and read the PHY capabilities for all - * detected LTTPRs. In case of an LTTPR detection error or if the number of - * LTTPRs is more than is supported (8), fall back to the no-LTTPR, - * transparent mode link training mode. - * - * Returns: - * >0 if LTTPRs were detected and the non-transparent LT mode was set. The - * DPRX capabilities are read out. - * 0 if no LTTPRs or more than 8 LTTPRs were detected or in case of a - * detection failure and the transparent LT mode was set. The DPRX - * capabilities are read out. - * <0 Reading out the DPRX capabilities failed. - */ -int intel_dp_init_lttpr_and_dprx_caps(struct intel_dp *intel_dp) +static int intel_dp_init_lttpr(struct intel_dp *intel_dp) { int lttpr_count; - bool ret; int i; - ret = intel_dp_read_lttpr_common_caps(intel_dp); - - /* The DPTX shall read the DPRX caps after LTTPR detection. */ - if (drm_dp_read_dpcd_caps(&intel_dp->aux, intel_dp->dpcd)) { - intel_dp_reset_lttpr_common_caps(intel_dp); - return -EIO; - } - - if (!ret) - return 0; - - /* - * The 0xF0000-0xF02FF range is only valid if the DPCD revision is - * at least 1.4. - */ - if (intel_dp->dpcd[DP_DPCD_REV] < 0x14) { - intel_dp_reset_lttpr_common_caps(intel_dp); + if (!intel_dp_read_lttpr_common_caps(intel_dp)) return 0; - } lttpr_count = drm_dp_lttpr_count(intel_dp->lttpr_common_caps); /* @@ -211,6 +175,37 @@ int intel_dp_init_lttpr_and_dprx_caps(struct intel_dp *intel_dp) return lttpr_count; } + +/** + * intel_dp_init_lttpr_and_dprx_caps - detect LTTPR and DPRX caps, init the LTTPR link training mode + * @intel_dp: Intel DP struct + * + * Read the LTTPR common and DPRX capabilities and switch to non-transparent + * link training mode if any is detected and read the PHY capabilities for all + * detected LTTPRs. In case of an LTTPR detection error or if the number of + * LTTPRs is more than is supported (8), fall back to the no-LTTPR, + * transparent mode link training mode. + * + * Returns: + * >0 if LTTPRs were detected and the non-transparent LT mode was set. The + * DPRX capabilities are read out. + * 0 if no LTTPRs or more than 8 LTTPRs were detected or in case of a + * detection failure and the transparent LT mode was set. The DPRX + * capabilities are read out. + * <0 Reading out the DPRX capabilities failed. + */ +int intel_dp_init_lttpr_and_dprx_caps(struct intel_dp *intel_dp) +{ + int lttpr_count = intel_dp_init_lttpr(intel_dp); + + /* The DPTX shall read the DPRX caps after LTTPR detection. */ + if (drm_dp_read_dpcd_caps(&intel_dp->aux, intel_dp->dpcd)) { + intel_dp_reset_lttpr_common_caps(intel_dp); + return -EIO; + } + + return lttpr_count; +} EXPORT_SYMBOL(intel_dp_init_lttpr_and_dprx_caps); static u8 dp_voltage_max(u8 preemph) diff --git a/drivers/gpu/drm/i915/display/intel_dpll_mgr.c b/drivers/gpu/drm/i915/display/intel_dpll_mgr.c index 18bfe8d09277..71ac57670043 100644 --- a/drivers/gpu/drm/i915/display/intel_dpll_mgr.c +++ b/drivers/gpu/drm/i915/display/intel_dpll_mgr.c @@ -149,6 +149,16 @@ void assert_shared_dpll(struct drm_i915_private *dev_priv, pll->info->name, onoff(state), onoff(cur_state)); } +static enum tc_port icl_pll_id_to_tc_port(enum intel_dpll_id id) +{ + return TC_PORT_1 + id - DPLL_ID_ICL_MGPLL1; +} + +enum intel_dpll_id icl_tc_port_to_pll_id(enum tc_port tc_port) +{ + return tc_port - TC_PORT_1 + DPLL_ID_ICL_MGPLL1; +} + static i915_reg_t intel_combo_pll_enable_reg(struct drm_i915_private *i915, struct intel_shared_dpll *pll) @@ -161,6 +171,19 @@ intel_combo_pll_enable_reg(struct drm_i915_private *i915, return CNL_DPLL_ENABLE(pll->info->id); } +static i915_reg_t +intel_tc_pll_enable_reg(struct drm_i915_private *i915, + struct intel_shared_dpll *pll) +{ + const enum intel_dpll_id id = pll->info->id; + enum tc_port tc_port = icl_pll_id_to_tc_port(id); + + if (IS_ALDERLAKE_P(i915)) + return ADLP_PORTTC_PLL_ENABLE(tc_port); + + return MG_PLL_ENABLE(tc_port); +} + /** * intel_prepare_shared_dpll - call a dpll's prepare hook * @crtc_state: CRTC, and its state, which has a shared dpll @@ -3120,16 +3143,6 @@ static void icl_calc_dpll_state(struct drm_i915_private *i915, pll_state->cfgcr1 |= DPLL_CFGCR1_CENTRAL_FREQ_8400; } -static enum tc_port icl_pll_id_to_tc_port(enum intel_dpll_id id) -{ - return id - DPLL_ID_ICL_MGPLL1; -} - -enum intel_dpll_id icl_tc_port_to_pll_id(enum tc_port tc_port) -{ - return tc_port + DPLL_ID_ICL_MGPLL1; -} - static bool icl_mg_pll_find_divisors(int clock_khz, bool is_dp, bool use_ssc, u32 *target_dco_khz, struct intel_dpll_hw_state *state, @@ -3728,12 +3741,14 @@ static bool mg_pll_get_hw_state(struct drm_i915_private *dev_priv, bool ret = false; u32 val; + i915_reg_t enable_reg = intel_tc_pll_enable_reg(dev_priv, pll); + wakeref = intel_display_power_get_if_enabled(dev_priv, POWER_DOMAIN_DISPLAY_CORE); if (!wakeref) return false; - val = intel_de_read(dev_priv, MG_PLL_ENABLE(tc_port)); + val = intel_de_read(dev_priv, enable_reg); if (!(val & PLL_ENABLE)) goto out; @@ -3797,7 +3812,7 @@ static bool dkl_pll_get_hw_state(struct drm_i915_private *dev_priv, if (!wakeref) return false; - val = intel_de_read(dev_priv, MG_PLL_ENABLE(tc_port)); + val = intel_de_read(dev_priv, intel_tc_pll_enable_reg(dev_priv, pll)); if (!(val & PLL_ENABLE)) goto out; @@ -4169,8 +4184,7 @@ static void tbt_pll_enable(struct drm_i915_private *dev_priv, static void mg_pll_enable(struct drm_i915_private *dev_priv, struct intel_shared_dpll *pll) { - i915_reg_t enable_reg = - MG_PLL_ENABLE(icl_pll_id_to_tc_port(pll->info->id)); + i915_reg_t enable_reg = intel_tc_pll_enable_reg(dev_priv, pll); icl_pll_power_enable(dev_priv, pll, enable_reg); @@ -4249,8 +4263,7 @@ static void tbt_pll_disable(struct drm_i915_private *dev_priv, static void mg_pll_disable(struct drm_i915_private *dev_priv, struct intel_shared_dpll *pll) { - i915_reg_t enable_reg = - MG_PLL_ENABLE(icl_pll_id_to_tc_port(pll->info->id)); + i915_reg_t enable_reg = intel_tc_pll_enable_reg(dev_priv, pll); icl_pll_disable(dev_priv, pll, enable_reg); } @@ -4416,6 +4429,26 @@ static const struct intel_dpll_mgr adls_pll_mgr = { .dump_hw_state = icl_dump_hw_state, }; +static const struct dpll_info adlp_plls[] = { + { "DPLL 0", &combo_pll_funcs, DPLL_ID_ICL_DPLL0, 0 }, + { "DPLL 1", &combo_pll_funcs, DPLL_ID_ICL_DPLL1, 0 }, + { "TBT PLL", &tbt_pll_funcs, DPLL_ID_ICL_TBTPLL, 0 }, + { "TC PLL 1", &dkl_pll_funcs, DPLL_ID_ICL_MGPLL1, 0 }, + { "TC PLL 2", &dkl_pll_funcs, DPLL_ID_ICL_MGPLL2, 0 }, + { "TC PLL 3", &dkl_pll_funcs, DPLL_ID_ICL_MGPLL3, 0 }, + { "TC PLL 4", &dkl_pll_funcs, DPLL_ID_ICL_MGPLL4, 0 }, + { }, +}; + +static const struct intel_dpll_mgr adlp_pll_mgr = { + .dpll_info = adlp_plls, + .get_dplls = icl_get_dplls, + .put_dplls = icl_put_dplls, + .update_active_dpll = icl_update_active_dpll, + .update_ref_clks = icl_update_dpll_ref_clks, + .dump_hw_state = icl_dump_hw_state, +}; + /** * intel_shared_dpll_init - Initialize shared DPLLs * @dev: drm device @@ -4429,7 +4462,9 @@ void intel_shared_dpll_init(struct drm_device *dev) const struct dpll_info *dpll_info; int i; - if (IS_ALDERLAKE_S(dev_priv)) + if (IS_ALDERLAKE_P(dev_priv)) + dpll_mgr = &adlp_pll_mgr; + else if (IS_ALDERLAKE_S(dev_priv)) dpll_mgr = &adls_pll_mgr; else if (IS_DG1(dev_priv)) dpll_mgr = &dg1_pll_mgr; diff --git a/drivers/gpu/drm/i915/display/intel_fb.c b/drivers/gpu/drm/i915/display/intel_fb.c index a005c68889e7..c60a81a81c09 100644 --- a/drivers/gpu/drm/i915/display/intel_fb.c +++ b/drivers/gpu/drm/i915/display/intel_fb.c @@ -355,8 +355,17 @@ static int intel_fb_offset_to_xy(int *x, int *y, unsigned int height; u32 alignment; - if (DISPLAY_VER(i915) >= 12 && - is_semiplanar_uv_plane(fb, color_plane)) + /* + * All DPT color planes must be 512*4k aligned (the amount mapped by a + * single DPT page). For ADL_P CCS FBs this only works by requiring + * the allocated offsets to be 2MB aligned. Once supoort to remap + * such FBs is added we can remove this requirement, as then all the + * planes can be remapped to an aligned offset. + */ + if (IS_ALDERLAKE_P(i915) && is_ccs_modifier(fb->modifier)) + alignment = 512 * 4096; + else if (DISPLAY_VER(i915) >= 12 && + is_semiplanar_uv_plane(fb, color_plane)) alignment = intel_tile_row_size(fb, color_plane); else if (fb->modifier != DRM_FORMAT_MOD_LINEAR) alignment = intel_tile_size(i915); diff --git a/drivers/gpu/drm/i915/display/intel_fifo_underrun.c b/drivers/gpu/drm/i915/display/intel_fifo_underrun.c index 3315aa1d4d5a..eb841960840d 100644 --- a/drivers/gpu/drm/i915/display/intel_fifo_underrun.c +++ b/drivers/gpu/drm/i915/display/intel_fifo_underrun.c @@ -185,15 +185,34 @@ static void ivb_set_fifo_underrun_reporting(struct drm_device *dev, } } +static u32 +icl_pipe_status_underrun_mask(struct drm_i915_private *dev_priv) +{ + u32 mask = PIPE_STATUS_UNDERRUN; + + if (DISPLAY_VER(dev_priv) >= 13) + mask |= PIPE_STATUS_SOFT_UNDERRUN_XELPD | + PIPE_STATUS_HARD_UNDERRUN_XELPD | + PIPE_STATUS_PORT_UNDERRUN_XELPD; + + return mask; +} + static void bdw_set_fifo_underrun_reporting(struct drm_device *dev, enum pipe pipe, bool enable) { struct drm_i915_private *dev_priv = to_i915(dev); + u32 mask = gen8_de_pipe_underrun_mask(dev_priv); - if (enable) - bdw_enable_pipe_irq(dev_priv, pipe, GEN8_PIPE_FIFO_UNDERRUN); - else - bdw_disable_pipe_irq(dev_priv, pipe, GEN8_PIPE_FIFO_UNDERRUN); + if (enable) { + if (DISPLAY_VER(dev_priv) >= 11) + intel_de_write(dev_priv, ICL_PIPESTATUS(pipe), + icl_pipe_status_underrun_mask(dev_priv)); + + bdw_enable_pipe_irq(dev_priv, pipe, mask); + } else { + bdw_disable_pipe_irq(dev_priv, pipe, mask); + } } static void ibx_set_fifo_underrun_reporting(struct drm_device *dev, @@ -373,6 +392,7 @@ void intel_cpu_fifo_underrun_irq_handler(struct drm_i915_private *dev_priv, enum pipe pipe) { struct intel_crtc *crtc = intel_get_crtc_for_pipe(dev_priv, pipe); + u32 underruns = 0; /* We may be called too early in init, thanks BIOS! */ if (crtc == NULL) @@ -383,10 +403,35 @@ void intel_cpu_fifo_underrun_irq_handler(struct drm_i915_private *dev_priv, crtc->cpu_fifo_underrun_disabled) return; + /* + * Starting with display version 11, the PIPE_STAT register records + * whether an underrun has happened, and on XELPD+, it will also record + * whether the underrun was soft/hard and whether it was triggered by + * the downstream port logic. We should clear these bits (which use + * write-1-to-clear logic) too. + * + * Note that although the IIR gives us the same underrun and soft/hard + * information, PIPE_STAT is the only place we can find out whether + * the underrun was caused by the downstream port. + */ + if (DISPLAY_VER(dev_priv) >= 11) { + underruns = intel_de_read(dev_priv, ICL_PIPESTATUS(pipe)) & + icl_pipe_status_underrun_mask(dev_priv); + intel_de_write(dev_priv, ICL_PIPESTATUS(pipe), underruns); + } + if (intel_set_cpu_fifo_underrun_reporting(dev_priv, pipe, false)) { trace_intel_cpu_fifo_underrun(dev_priv, pipe); - drm_err(&dev_priv->drm, "CPU pipe %c FIFO underrun\n", - pipe_name(pipe)); + + if (DISPLAY_VER(dev_priv) >= 11) + drm_err(&dev_priv->drm, "CPU pipe %c FIFO underrun: %s%s%s%s\n", + pipe_name(pipe), + underruns & PIPE_STATUS_SOFT_UNDERRUN_XELPD ? "soft," : "", + underruns & PIPE_STATUS_HARD_UNDERRUN_XELPD ? "hard," : "", + underruns & PIPE_STATUS_PORT_UNDERRUN_XELPD ? "port," : "", + underruns & PIPE_STATUS_UNDERRUN ? "transcoder," : ""); + else + drm_err(&dev_priv->drm, "CPU pipe %c FIFO underrun\n", pipe_name(pipe)); } intel_fbc_handle_fifo_underrun_irq(dev_priv); diff --git a/drivers/gpu/drm/i915/display/intel_hdmi.c b/drivers/gpu/drm/i915/display/intel_hdmi.c index 4a1b2d863b0c..7e51c98c475e 100644 --- a/drivers/gpu/drm/i915/display/intel_hdmi.c +++ b/drivers/gpu/drm/i915/display/intel_hdmi.c @@ -1865,28 +1865,69 @@ static int intel_hdmi_port_clock(int clock, int bpc) return clock * bpc / 8; } +static bool intel_hdmi_bpc_possible(struct drm_connector *connector, + int bpc, bool has_hdmi_sink, bool ycbcr420_output) +{ + struct drm_i915_private *i915 = to_i915(connector->dev); + const struct drm_display_info *info = &connector->display_info; + const struct drm_hdmi_info *hdmi = &info->hdmi; + + switch (bpc) { + case 12: + if (HAS_GMCH(i915)) + return false; + + if (!has_hdmi_sink) + return false; + + if (ycbcr420_output) + return hdmi->y420_dc_modes & DRM_EDID_YCBCR420_DC_36; + else + return info->edid_hdmi_dc_modes & DRM_EDID_HDMI_DC_36; + case 10: + if (DISPLAY_VER(i915) < 11) + return false; + + if (!has_hdmi_sink) + return false; + + if (ycbcr420_output) + return hdmi->y420_dc_modes & DRM_EDID_YCBCR420_DC_30; + else + return info->edid_hdmi_dc_modes & DRM_EDID_HDMI_DC_30; + case 8: + return true; + default: + MISSING_CASE(bpc); + return false; + } +} + static enum drm_mode_status -intel_hdmi_mode_clock_valid(struct intel_hdmi *hdmi, int clock, bool has_hdmi_sink) +intel_hdmi_mode_clock_valid(struct drm_connector *connector, int clock, + bool has_hdmi_sink, bool ycbcr420_output) { - struct drm_device *dev = intel_hdmi_to_dev(hdmi); - struct drm_i915_private *dev_priv = to_i915(dev); + struct intel_hdmi *hdmi = intel_attached_hdmi(to_intel_connector(connector)); enum drm_mode_status status; + if (ycbcr420_output) + clock /= 2; + /* check if we can do 8bpc */ status = hdmi_port_clock_valid(hdmi, intel_hdmi_port_clock(clock, 8), true, has_hdmi_sink); - if (has_hdmi_sink) { - /* if we can't do 8bpc we may still be able to do 12bpc */ - if (status != MODE_OK && !HAS_GMCH(dev_priv)) - status = hdmi_port_clock_valid(hdmi, intel_hdmi_port_clock(clock, 12), - true, has_hdmi_sink); + /* if we can't do 8bpc we may still be able to do 12bpc */ + if (status != MODE_OK && + intel_hdmi_bpc_possible(connector, 12, has_hdmi_sink, ycbcr420_output)) + status = hdmi_port_clock_valid(hdmi, intel_hdmi_port_clock(clock, 12), + true, has_hdmi_sink); - /* if we can't do 8,12bpc we may still be able to do 10bpc */ - if (status != MODE_OK && DISPLAY_VER(dev_priv) >= 11) - status = hdmi_port_clock_valid(hdmi, intel_hdmi_port_clock(clock, 10), - true, has_hdmi_sink); - } + /* if we can't do 8,12bpc we may still be able to do 10bpc */ + if (status != MODE_OK && + intel_hdmi_bpc_possible(connector, 10, has_hdmi_sink, ycbcr420_output)) + status = hdmi_port_clock_valid(hdmi, intel_hdmi_port_clock(clock, 10), + true, has_hdmi_sink); return status; } @@ -1920,18 +1961,15 @@ intel_hdmi_mode_valid(struct drm_connector *connector, } ycbcr_420_only = drm_mode_is_420_only(&connector->display_info, mode); - if (ycbcr_420_only) - clock /= 2; - status = intel_hdmi_mode_clock_valid(hdmi, clock, has_hdmi_sink); + status = intel_hdmi_mode_clock_valid(connector, clock, has_hdmi_sink, ycbcr_420_only); if (status != MODE_OK) { if (ycbcr_420_only || !connector->ycbcr_420_allowed || !drm_mode_is_420_also(&connector->display_info, mode)) return status; - clock /= 2; - status = intel_hdmi_mode_clock_valid(hdmi, clock, has_hdmi_sink); + status = intel_hdmi_mode_clock_valid(connector, clock, has_hdmi_sink, true); if (status != MODE_OK) return status; } @@ -1950,32 +1988,12 @@ bool intel_hdmi_deep_color_possible(const struct intel_crtc_state *crtc_state, if (crtc_state->pipe_bpp < bpc * 3) return false; - if (!has_hdmi_sink) - return false; - for_each_new_connector_in_state(state, connector, connector_state, i) { - const struct drm_display_info *info = &connector->display_info; - if (connector_state->crtc != crtc_state->uapi.crtc) continue; - if (ycbcr420_output) { - const struct drm_hdmi_info *hdmi = &info->hdmi; - - if (bpc == 12 && !(hdmi->y420_dc_modes & - DRM_EDID_YCBCR420_DC_36)) - return false; - else if (bpc == 10 && !(hdmi->y420_dc_modes & - DRM_EDID_YCBCR420_DC_30)) - return false; - } else { - if (bpc == 12 && !(info->edid_hdmi_dc_modes & - DRM_EDID_HDMI_DC_36)) - return false; - else if (bpc == 10 && !(info->edid_hdmi_dc_modes & - DRM_EDID_HDMI_DC_30)) - return false; - } + if (!intel_hdmi_bpc_possible(connector, bpc, has_hdmi_sink, ycbcr420_output)) + return false; } return true; @@ -1989,12 +2007,6 @@ static bool hdmi_deep_color_possible(const struct intel_crtc_state *crtc_state, const struct drm_display_mode *adjusted_mode = &crtc_state->hw.adjusted_mode; - if (HAS_GMCH(dev_priv)) - return false; - - if (bpc == 10 && DISPLAY_VER(dev_priv) < 11) - return false; - /* * HDMI deep color affects the clocks, so it's only possible * when not cloning with other encoder types. diff --git a/drivers/gpu/drm/i915/display/intel_psr.c b/drivers/gpu/drm/i915/display/intel_psr.c index acaf3d459821..77865cf6641f 100644 --- a/drivers/gpu/drm/i915/display/intel_psr.c +++ b/drivers/gpu/drm/i915/display/intel_psr.c @@ -638,7 +638,7 @@ unlock: static void tgl_disallow_dc3co_on_psr2_exit(struct intel_dp *intel_dp) { - if (!intel_dp->psr.dc3co_enabled) + if (!intel_dp->psr.dc3co_exitline) return; cancel_delayed_work(&intel_dp->psr.dc3co_work); @@ -646,12 +646,26 @@ static void tgl_disallow_dc3co_on_psr2_exit(struct intel_dp *intel_dp) tgl_psr2_disable_dc3co(intel_dp); } +static bool +dc3co_is_pipe_port_compatible(struct intel_dp *intel_dp, + struct intel_crtc_state *crtc_state) +{ + struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp); + enum pipe pipe = to_intel_crtc(crtc_state->uapi.crtc)->pipe; + struct drm_i915_private *dev_priv = dp_to_i915(intel_dp); + enum port port = dig_port->base.port; + + if (IS_ALDERLAKE_P(dev_priv)) + return pipe <= PIPE_B && port <= PORT_B; + else + return pipe == PIPE_A && port == PORT_A; +} + static void tgl_dc3co_exitline_compute_config(struct intel_dp *intel_dp, struct intel_crtc_state *crtc_state) { const u32 crtc_vdisplay = crtc_state->uapi.adjusted_mode.crtc_vdisplay; - struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp); struct drm_i915_private *dev_priv = dp_to_i915(intel_dp); u32 exit_scanlines; @@ -669,12 +683,10 @@ tgl_dc3co_exitline_compute_config(struct intel_dp *intel_dp, if (crtc_state->enable_psr2_sel_fetch) return; - if (!(dev_priv->csr.allowed_dc_mask & DC_STATE_EN_DC3CO)) + if (!(dev_priv->dmc.allowed_dc_mask & DC_STATE_EN_DC3CO)) return; - /* B.Specs:49196 DC3CO only works with pipeA and DDIA.*/ - if (to_intel_crtc(crtc_state->uapi.crtc)->pipe != PIPE_A || - dig_port->base.port != PORT_A) + if (!dc3co_is_pipe_port_compatible(intel_dp, crtc_state)) return; /* @@ -753,6 +765,15 @@ static bool intel_psr2_config_valid(struct intel_dp *intel_dp, return false; } + /* + * We are missing the implementation of some workarounds to enabled PSR2 + * in Alderlake_P, until ready PSR2 should be kept disabled. + */ + if (IS_ALDERLAKE_P(dev_priv)) { + drm_dbg_kms(&dev_priv->drm, "PSR2 is missing the implementation of workarounds\n"); + return false; + } + if (!transcoder_has_psr2(dev_priv, crtc_state->cpu_transcoder)) { drm_dbg_kms(&dev_priv->drm, "PSR2 not supported in transcoder %s\n", @@ -969,11 +990,10 @@ static void intel_psr_activate(struct intel_dp *intel_dp) intel_dp->psr.active = true; } -static void intel_psr_enable_source(struct intel_dp *intel_dp, - const struct intel_crtc_state *crtc_state) +static void intel_psr_enable_source(struct intel_dp *intel_dp) { struct drm_i915_private *dev_priv = dp_to_i915(intel_dp); - enum transcoder cpu_transcoder = crtc_state->cpu_transcoder; + enum transcoder cpu_transcoder = intel_dp->psr.transcoder; u32 mask; /* Only HSW and BDW have PSR AUX registers that need to be setup. SKL+ @@ -1010,7 +1030,7 @@ static void intel_psr_enable_source(struct intel_dp *intel_dp, psr_irq_control(intel_dp); - if (crtc_state->dc3co_exitline) { + if (intel_dp->psr.dc3co_exitline) { u32 val; /* @@ -1019,7 +1039,7 @@ static void intel_psr_enable_source(struct intel_dp *intel_dp, */ val = intel_de_read(dev_priv, EXITLINE(cpu_transcoder)); val &= ~EXITLINE_MASK; - val |= crtc_state->dc3co_exitline << EXITLINE_SHIFT; + val |= intel_dp->psr.dc3co_exitline << EXITLINE_SHIFT; val |= EXITLINE_ENABLE; intel_de_write(dev_priv, EXITLINE(cpu_transcoder), val); } @@ -1030,27 +1050,11 @@ static void intel_psr_enable_source(struct intel_dp *intel_dp, IGNORE_PSR2_HW_TRACKING : 0); } -static void intel_psr_enable_locked(struct intel_dp *intel_dp, - const struct intel_crtc_state *crtc_state, - const struct drm_connector_state *conn_state) +static bool psr_interrupt_error_check(struct intel_dp *intel_dp) { - struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp); struct drm_i915_private *dev_priv = dp_to_i915(intel_dp); - struct intel_encoder *encoder = &dig_port->base; u32 val; - drm_WARN_ON(&dev_priv->drm, intel_dp->psr.enabled); - - intel_dp->psr.psr2_enabled = crtc_state->has_psr2; - intel_dp->psr.busy_frontbuffer_bits = 0; - intel_dp->psr.pipe = to_intel_crtc(crtc_state->uapi.crtc)->pipe; - intel_dp->psr.dc3co_enabled = !!crtc_state->dc3co_exitline; - intel_dp->psr.transcoder = crtc_state->cpu_transcoder; - /* DC5/DC6 requires at least 6 idle frames */ - val = usecs_to_jiffies(intel_get_frame_time_us(crtc_state) * 6); - intel_dp->psr.dc3co_exit_delay = val; - intel_dp->psr.psr2_sel_fetch_enabled = crtc_state->enable_psr2_sel_fetch; - /* * If a PSR error happened and the driver is reloaded, the EDP_PSR_IIR * will still keep the error set even after the reset done in the @@ -1071,17 +1075,45 @@ static void intel_psr_enable_locked(struct intel_dp *intel_dp, intel_dp->psr.sink_not_reliable = true; drm_dbg_kms(&dev_priv->drm, "PSR interruption error set, not enabling PSR\n"); - return; + return false; } + return true; +} + +static void intel_psr_enable_locked(struct intel_dp *intel_dp, + const struct intel_crtc_state *crtc_state, + const struct drm_connector_state *conn_state) +{ + struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp); + struct drm_i915_private *dev_priv = dp_to_i915(intel_dp); + struct intel_encoder *encoder = &dig_port->base; + u32 val; + + drm_WARN_ON(&dev_priv->drm, intel_dp->psr.enabled); + + intel_dp->psr.psr2_enabled = crtc_state->has_psr2; + intel_dp->psr.busy_frontbuffer_bits = 0; + intel_dp->psr.pipe = to_intel_crtc(crtc_state->uapi.crtc)->pipe; + intel_dp->psr.transcoder = crtc_state->cpu_transcoder; + /* DC5/DC6 requires at least 6 idle frames */ + val = usecs_to_jiffies(intel_get_frame_time_us(crtc_state) * 6); + intel_dp->psr.dc3co_exit_delay = val; + intel_dp->psr.dc3co_exitline = crtc_state->dc3co_exitline; + intel_dp->psr.psr2_sel_fetch_enabled = crtc_state->enable_psr2_sel_fetch; + + if (!psr_interrupt_error_check(intel_dp)) + return; + drm_dbg_kms(&dev_priv->drm, "Enabling PSR%s\n", intel_dp->psr.psr2_enabled ? "2" : "1"); intel_dp_compute_psr_vsc_sdp(intel_dp, crtc_state, conn_state, &intel_dp->psr.vsc); intel_write_dp_vsc_sdp(encoder, crtc_state, &intel_dp->psr.vsc); intel_psr_enable_sink(intel_dp); - intel_psr_enable_source(intel_dp, crtc_state); + intel_psr_enable_source(intel_dp); intel_dp->psr.enabled = true; + intel_dp->psr.paused = false; intel_psr_activate(intel_dp); } @@ -1151,22 +1183,12 @@ static void intel_psr_exit(struct intel_dp *intel_dp) intel_dp->psr.active = false; } -static void intel_psr_disable_locked(struct intel_dp *intel_dp) +static void intel_psr_wait_exit_locked(struct intel_dp *intel_dp) { struct drm_i915_private *dev_priv = dp_to_i915(intel_dp); i915_reg_t psr_status; u32 psr_status_mask; - lockdep_assert_held(&intel_dp->psr.lock); - - if (!intel_dp->psr.enabled) - return; - - drm_dbg_kms(&dev_priv->drm, "Disabling PSR%s\n", - intel_dp->psr.psr2_enabled ? "2" : "1"); - - intel_psr_exit(intel_dp); - if (intel_dp->psr.psr2_enabled) { psr_status = EDP_PSR2_STATUS(intel_dp->psr.transcoder); psr_status_mask = EDP_PSR2_STATUS_STATE_MASK; @@ -1179,6 +1201,22 @@ static void intel_psr_disable_locked(struct intel_dp *intel_dp) if (intel_de_wait_for_clear(dev_priv, psr_status, psr_status_mask, 2000)) drm_err(&dev_priv->drm, "Timed out waiting PSR idle state\n"); +} + +static void intel_psr_disable_locked(struct intel_dp *intel_dp) +{ + struct drm_i915_private *dev_priv = dp_to_i915(intel_dp); + + lockdep_assert_held(&intel_dp->psr.lock); + + if (!intel_dp->psr.enabled) + return; + + drm_dbg_kms(&dev_priv->drm, "Disabling PSR%s\n", + intel_dp->psr.psr2_enabled ? "2" : "1"); + + intel_psr_exit(intel_dp); + intel_psr_wait_exit_locked(intel_dp); /* WA 1408330847 */ if (intel_dp->psr.psr2_sel_fetch_enabled && @@ -1223,6 +1261,61 @@ void intel_psr_disable(struct intel_dp *intel_dp, cancel_delayed_work_sync(&intel_dp->psr.dc3co_work); } +/** + * intel_psr_pause - Pause PSR + * @intel_dp: Intel DP + * + * This function need to be called after enabling psr. + */ +void intel_psr_pause(struct intel_dp *intel_dp) +{ + struct intel_psr *psr = &intel_dp->psr; + + if (!CAN_PSR(intel_dp)) + return; + + mutex_lock(&psr->lock); + + if (!psr->enabled) { + mutex_unlock(&psr->lock); + return; + } + + intel_psr_exit(intel_dp); + intel_psr_wait_exit_locked(intel_dp); + psr->paused = true; + + mutex_unlock(&psr->lock); + + cancel_work_sync(&psr->work); + cancel_delayed_work_sync(&psr->dc3co_work); +} + +/** + * intel_psr_resume - Resume PSR + * @intel_dp: Intel DP + * + * This function need to be called after pausing psr. + */ +void intel_psr_resume(struct intel_dp *intel_dp) +{ + struct intel_psr *psr = &intel_dp->psr; + + if (!CAN_PSR(intel_dp)) + return; + + mutex_lock(&psr->lock); + + if (!psr->paused) + goto unlock; + + psr->paused = false; + intel_psr_activate(intel_dp); + +unlock: + mutex_unlock(&psr->lock); +} + static void psr_force_hw_tracking_exit(struct intel_dp *intel_dp) { struct drm_i915_private *dev_priv = dp_to_i915(intel_dp); @@ -1818,7 +1911,7 @@ tgl_dc3co_flush(struct intel_dp *intel_dp, unsigned int frontbuffer_bits, { mutex_lock(&intel_dp->psr.lock); - if (!intel_dp->psr.dc3co_enabled) + if (!intel_dp->psr.dc3co_exitline) goto unlock; if (!intel_dp->psr.psr2_enabled || !intel_dp->psr.active) @@ -1877,6 +1970,16 @@ void intel_psr_flush(struct drm_i915_private *dev_priv, INTEL_FRONTBUFFER_ALL_MASK(intel_dp->psr.pipe); intel_dp->psr.busy_frontbuffer_bits &= ~pipe_frontbuffer_bits; + /* + * If the PSR is paused by an explicit intel_psr_paused() call, + * we have to ensure that the PSR is not activated until + * intel_psr_resume() is called. + */ + if (intel_dp->psr.paused) { + mutex_unlock(&intel_dp->psr.lock); + continue; + } + /* By definition flush = invalidate + flush */ if (pipe_frontbuffer_bits) psr_force_hw_tracking_exit(intel_dp); diff --git a/drivers/gpu/drm/i915/display/intel_psr.h b/drivers/gpu/drm/i915/display/intel_psr.h index e3db85e97f4c..641521b101c8 100644 --- a/drivers/gpu/drm/i915/display/intel_psr.h +++ b/drivers/gpu/drm/i915/display/intel_psr.h @@ -51,5 +51,7 @@ void intel_psr2_program_plane_sel_fetch(struct intel_plane *plane, const struct intel_crtc_state *crtc_state, const struct intel_plane_state *plane_state, int color_plane); +void intel_psr_pause(struct intel_dp *intel_dp); +void intel_psr_resume(struct intel_dp *intel_dp); #endif /* __INTEL_PSR_H__ */ diff --git a/drivers/gpu/drm/i915/display/intel_qp_tables.c b/drivers/gpu/drm/i915/display/intel_qp_tables.c new file mode 100644 index 000000000000..c626a24fe98f --- /dev/null +++ b/drivers/gpu/drm/i915/display/intel_qp_tables.c @@ -0,0 +1,309 @@ +// SPDX-License-Identifier: MIT +/* + * Copyright © 2021 Intel Corporation + */ + +#include <drm/drm_dsc.h> + +#include "i915_utils.h" +#include "intel_qp_tables.h" + +/* from BPP 6 to 24 in steps of 0.5 */ +#define RC_RANGE_QP444_8BPC_MAX_NUM_BPP 37 + +/* from BPP 6 to 30 in steps of 0.5 */ +#define RC_RANGE_QP444_10BPC_MAX_NUM_BPP 49 + +/* from BPP 6 to 36 in steps of 0.5 */ +#define RC_RANGE_QP444_12BPC_MAX_NUM_BPP 61 + +/* + * These qp tables are as per the C model + * and it has the rows pointing to bpps which increment + * in steps of 0.5 + * We do not support fractional bpps as of today, + * hence we would skip the fractional bpps during + * our references for qp calclulations. + */ +static const u8 rc_range_minqp444_8bpc[DSC_NUM_BUF_RANGES][RC_RANGE_QP444_8BPC_MAX_NUM_BPP] = { + { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, + 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 }, + { 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, + 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 }, + { 3, 2, 2, 2, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, + 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 }, + { 3, 3, 2, 2, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, + 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 }, + { 5, 4, 4, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 2, 1, 1, 1, 1, 1, 1, 1, 1, + 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0 }, + { 5, 4, 4, 4, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 2, 1, 1, 1, 1, 1, 1, 1, + 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0 }, + { 5, 5, 4, 4, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 2, 2, 2, 1, 1, 1, 1, 1, + 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0 }, + { 5, 5, 4, 4, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 2, 2, 2, 2, 2, 2, 2, 2, + 2, 2, 2, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0 }, + { 5, 5, 4, 4, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 2, 2, 2, 2, 2, 2, 2, 2, + 2, 2, 2, 2, 2, 1, 1, 1, 1, 1, 1, 0, 0, 0 }, + { 6, 5, 5, 4, 4, 4, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, + 3, 3, 3, 2, 2, 1, 1, 1, 1, 1, 1, 0, 0, 0 }, + { 6, 6, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 4, 4, 4, 4, 4, 4, 4, 4, 4, 3, + 3, 3, 3, 2, 2, 1, 1, 1, 1, 1, 1, 1, 1, 0 }, + { 6, 6, 6, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 4, 4, 4, 4, 4, 4, + 4, 4, 4, 3, 3, 2, 2, 2, 2, 1, 1, 1, 1, 0 }, + { 6, 6, 6, 6, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 4, + 4, 4, 4, 3, 3, 2, 2, 2, 2, 1, 1, 1, 1, 0 }, + { 9, 9, 9, 9, 8, 8, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 6, 6, 5, + 5, 5, 5, 4, 4, 3, 3, 3, 3, 2, 2, 1, 1, 1 }, + { 14, 14, 13, 13, 12, 12, 12, 12, 11, 11, 10, 10, 10, 10, 9, 9, 9, 8, 8, + 8, 7, 7, 7, 7, 6, 6, 5, 5, 5, 5, 4, 4, 4, 3, 3, 3, 3 } +}; + +static const u8 rc_range_maxqp444_8bpc[DSC_NUM_BUF_RANGES][RC_RANGE_QP444_8BPC_MAX_NUM_BPP] = { + { 4, 4, 4, 4, 4, 4, 3, 3, 3, 3, 2, 2, 2, 2, 1, 1, 1, 0, 0, 0, 0, 0, 0, + 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 }, + { 6, 6, 5, 5, 4, 4, 4, 4, 4, 4, 4, 4, 3, 3, 3, 2, 2, 1, 1, 1, 1, 1, 1, + 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0 }, + { 8, 7, 7, 6, 5, 5, 5, 5, 5, 5, 5, 5, 4, 4, 4, 3, 2, 2, 1, 1, 1, 1, 1, + 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0 }, + { 8, 8, 7, 7, 6, 6, 6, 6, 6, 6, 6, 6, 5, 5, 5, 4, 3, 3, 2, 2, 2, 2, 2, + 2, 2, 2, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0 }, + { 9, 8, 8, 7, 7, 7, 7, 7, 7, 7, 7, 7, 6, 6, 5, 4, 4, 3, 2, 2, 2, 2, 2, + 2, 2, 2, 2, 2, 1, 1, 1, 1, 1, 1, 1, 1, 0 }, + { 9, 8, 8, 8, 7, 7, 7, 7, 7, 7, 7, 7, 6, 6, 6, 5, 4, 4, 3, 3, 3, 3, 3, + 3, 3, 3, 2, 2, 2, 2, 1, 1, 1, 1, 1, 1, 1 }, + { 9, 9, 8, 8, 7, 7, 7, 7, 7, 7, 7, 7, 7, 6, 6, 5, 4, 4, 3, 3, 3, 3, 3, + 3, 3, 3, 2, 2, 2, 2, 1, 1, 1, 1, 1, 1, 1 }, + { 10, 10, 9, 9, 8, 8, 8, 8, 8, 8, 8, 8, 8, 7, 7, 6, 5, 5, 4, 4, 4, 4, 3, + 3, 3, 3, 2, 2, 2, 2, 2, 2, 1, 1, 1, 1, 1 }, + { 11, 11, 10, 10, 9, 9, 9, 9, 9, 9, 8, 8, 8, 7, 7, 6, 6, 5, 5, 5, 5, 5, + 4, 4, 4, 4, 3, 3, 2, 2, 2, 2, 2, 2, 1, 1, 1 }, + { 12, 11, 11, 10, 10, 10, 9, 9, 9, 9, 9, 9, 9, 8, 8, 7, 6, 6, 5, 5, 5, + 5, 4, 4, 4, 4, 3, 3, 2, 2, 2, 2, 2, 2, 1, 1, 1 }, + { 12, 12, 11, 11, 10, 10, 10, 10, 10, 10, 9, 9, 9, 8, 8, 7, 7, 6, 6, 6, + 5, 5, 4, 4, 4, 4, 3, 3, 2, 2, 2, 2, 2, 2, 2, 2, 1 }, + { 12, 12, 12, 11, 11, 11, 10, 10, 10, 10, 9, 9, 9, 9, 8, 8, 8, 7, 7, 7, + 6, 6, 5, 5, 5, 5, 4, 4, 3, 3, 3, 3, 2, 2, 2, 2, 1 }, + { 12, 12, 12, 12, 11, 11, 11, 11, 11, 10, 10, 9, 9, 9, 8, 8, 8, 7, 7, 7, + 6, 6, 5, 5, 5, 5, 4, 4, 3, 3, 3, 3, 2, 2, 2, 2, 1 }, + { 13, 13, 13, 13, 12, 12, 11, 11, 11, 11, 10, 10, 10, 10, 9, 9, 8, 8, 8, + 8, 7, 7, 6, 6, 6, 6, 5, 5, 4, 4, 4, 4, 3, 3, 2, 2, 2 }, + { 15, 15, 14, 14, 13, 13, 13, 13, 12, 12, 11, 11, 11, 11, 10, 10, 10, 9, + 9, 9, 8, 8, 8, 8, 7, 7, 6, 6, 6, 6, 5, 5, 5, 4, 4, 4, 4 } +}; + +static const u8 rc_range_minqp444_10bpc[DSC_NUM_BUF_RANGES][RC_RANGE_QP444_10BPC_MAX_NUM_BPP] = { + { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, + 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, + 0, 0, 0 }, + { 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 3, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 1, 1, + 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, + 0, 0, 0 }, + { 7, 6, 6, 6, 5, 5, 5, 5, 5, 5, 5, 5, 4, 4, 4, 3, 3, 3, 3, 3, 3, 2, 2, + 2, 2, 2, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, + 0, 0, 0 }, + { 7, 7, 6, 6, 5, 5, 5, 5, 5, 5, 5, 5, 4, 4, 4, 4, 4, 4, 4, 4, 4, 3, 3, + 3, 3, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, + 0, 0, 0 }, + { 9, 8, 8, 7, 7, 7, 7, 7, 7, 7, 7, 7, 6, 6, 5, 5, 5, 5, 4, 4, 4, 4, 3, + 3, 3, 3, 3, 3, 2, 2, 2, 2, 2, 2, 2, 2, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, + 0, 0, 0 }, + { 9, 8, 8, 8, 7, 7, 7, 7, 7, 7, 7, 7, 6, 6, 6, 6, 5, 5, 5, 5, 5, 5, 4, + 4, 4, 4, 3, 3, 3, 3, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 1, 1, 1, 0, 0, 0, + 0, 0, 0 }, + { 9, 9, 8, 8, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 6, 6, 6, 5, 5, 5, 5, 5, + 4, 4, 4, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 2, 2, 2, 1, 1, 1, 1, 0, 0, + 0, 0, 0 }, + { 9, 9, 8, 8, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 6, 6, 6, 6, 6, 6, 5, + 5, 5, 5, 4, 4, 4, 4, 4, 4, 3, 3, 3, 3, 3, 3, 2, 2, 2, 2, 1, 1, 1, 0, + 0, 0, 0 }, + { 9, 9, 8, 8, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 6, 6, 6, 6, 6, 5, + 5, 5, 5, 5, 5, 5, 4, 4, 4, 4, 4, 3, 3, 3, 3, 3, 3, 2, 2, 2, 1, 1, 1, + 1, 0, 0 }, + { 10, 9, 9, 8, 8, 8, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 6, 6, 6, 6, 6, + 6, 6, 6, 6, 6, 5, 5, 4, 4, 4, 4, 3, 3, 3, 3, 3, 3, 3, 2, 2, 2, 1, 1, + 1, 1, 0 }, + { 10, 10, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 8, 8, 8, 8, 7, 7, 7, 7, 7, 6, + 6, 6, 6, 6, 6, 5, 5, 5, 5, 5, 5, 5, 5, 4, 4, 4, 3, 3, 3, 2, 2, 2, 1, + 1, 1, 1 }, + { 10, 10, 10, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 8, 8, 8, 8, 8, + 7, 7, 7, 7, 7, 7, 6, 6, 6, 6, 5, 5, 5, 5, 4, 4, 4, 4, 3, 3, 3, 3, 2, + 2, 1, 1, 1 }, + { 10, 10, 10, 10, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 8, 8, + 8, 8, 8, 8, 7, 7, 6, 6, 6, 6, 5, 5, 5, 5, 4, 4, 4, 4, 3, 3, 3, 3, 2, + 2, 2, 2, 1 }, + { 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 11, 11, 11, 11, 11, 11, 11, + 11, 11, 11, 10, 10, 9, 9, 9, 9, 8, 8, 7, 7, 7, 7, 6, 6, 5, 5, 5, 5, 4, + 4, 3, 3, 3, 3, 2, 2, 2, 2, 1 }, + { 18, 18, 17, 17, 16, 16, 16, 16, 15, 15, 14, 14, 14, 14, 13, 13, 13, + 12, 12, 12, 11, 11, 11, 11, 10, 10, 9, 9, 9, 9, 9, 8, 8, 7, 7, 7, 7, + 7, 6, 6, 5, 5, 5, 5, 4, 4, 3, 3, 3 } +}; + +static const u8 rc_range_maxqp444_10bpc[DSC_NUM_BUF_RANGES][RC_RANGE_QP444_10BPC_MAX_NUM_BPP] = { + { 8, 8, 8, 8, 8, 8, 7, 7, 7, 6, 5, 5, 4, 4, 3, 3, 3, 2, 2, 2, 2, 2, 2, + 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, + 0, 0, 0 }, + { 10, 10, 9, 9, 8, 8, 8, 8, 8, 8, 7, 7, 6, 6, 6, 5, 5, 4, 4, 4, 4, 3, 3, + 3, 3, 3, 2, 2, 2, 2, 2, 2, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, + 0, 0, 0 }, + { 12, 11, 11, 10, 9, 9, 9, 9, 9, 9, 9, 9, 8, 8, 8, 7, 6, 6, 5, 5, 5, 4, + 4, 4, 4, 4, 3, 3, 3, 3, 3, 3, 2, 2, 2, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, + 0, 0, 0, 0 }, + { 12, 12, 11, 11, 10, 10, 10, 10, 10, 10, 10, 10, 9, 9, 9, 8, 7, 7, 6, + 6, 6, 5, 5, 5, 5, 5, 4, 4, 3, 3, 3, 3, 3, 3, 3, 3, 2, 2, 1, 1, 1, 1, + 1, 0, 0, 0, 0, 0, 0 }, + { 13, 12, 12, 11, 11, 11, 11, 11, 11, 11, 11, 11, 10, 10, 9, 8, 8, 7, + 6, 6, 6, 6, 5, 5, 5, 5, 5, 5, 4, 4, 4, 3, 3, 3, 3, 3, 2, 2, 2, 2, 1, + 1, 1, 1, 0, 0, 0, 0, 0 }, + { 13, 12, 12, 12, 11, 11, 11, 11, 11, 11, 11, 11, 10, 10, 10, 9, 8, 8, + 7, 7, 7, 7, 6, 6, 6, 6, 5, 5, 5, 5, 4, 3, 3, 3, 3, 3, 3, 3, 3, 3, 2, + 2, 2, 1, 1, 1, 1, 0, 0 }, + { 13, 13, 12, 12, 11, 11, 11, 11, 11, 11, 11, 11, 11, 10, 10, 9, 8, 8, + 7, 7, 7, 7, 7, 6, 6, 6, 5, 5, 5, 5, 4, 4, 4, 4, 4, 4, 4, 3, 3, 3, 2, + 2, 2, 2, 1, 1, 1, 1, 1 }, + { 14, 14, 13, 13, 12, 12, 12, 12, 12, 12, 12, 12, 12, 11, 11, 10, 9, 9, + 8, 8, 8, 8, 7, 7, 7, 7, 6, 6, 6, 5, 5, 5, 4, 4, 4, 4, 4, 4, 3, 3, 3, + 3, 2, 2, 2, 1, 1, 1, 1 }, + { 15, 15, 14, 14, 13, 13, 13, 13, 13, 13, 12, 12, 12, 11, 11, 10, 10, 9, + 9, 9, 9, 9, 8, 8, 8, 8, 7, 7, 6, 5, 5, 5, 5, 5, 4, 4, 4, 4, 4, 4, 3, + 3, 3, 2, 2, 2, 2, 1, 1 }, + { 16, 15, 15, 14, 14, 14, 13, 13, 13, 13, 13, 13, 13, 12, 12, 11, 10, + 10, 9, 9, 9, 9, 8, 8, 8, 8, 7, 7, 6, 6, 5, 5, 5, 5, 4, 4, 4, 4, 4, 4, + 4, 3, 3, 3, 2, 2, 2, 2, 1 }, + { 16, 16, 15, 15, 14, 14, 14, 14, 14, 14, 13, 13, 13, 12, 12, 11, 11, + 10, 10, 10, 9, 9, 8, 8, 8, 8, 7, 7, 6, 6, 6, 6, 6, 6, 6, 6, 5, 5, 5, + 4, 4, 4, 3, 3, 3, 2, 2, 2, 2 }, + { 16, 16, 16, 15, 15, 15, 14, 14, 14, 14, 13, 13, 13, 13, 12, 12, 12, + 11, 11, 11, 10, 10, 9, 9, 9, 9, 8, 8, 7, 7, 7, 7, 6, 6, 6, 6, 5, 5, 5, + 5, 4, 4, 4, 4, 3, 3, 2, 2, 2 }, + { 16, 16, 16, 16, 15, 15, 15, 15, 15, 14, 14, 13, 13, 13, 12, 12, 12, + 11, 11, 11, 10, 10, 9, 9, 9, 9, 8, 8, 7, 7, 7, 7, 6, 6, 6, 6, 5, 5, 5, + 5, 4, 4, 4, 4, 3, 3, 3, 3, 2 }, + { 17, 17, 17, 17, 16, 16, 15, 15, 15, 15, 14, 14, 14, 14, 13, 13, 12, + 12, 12, 12, 11, 11, 10, 10, 10, 10, 9, 9, 8, 8, 8, 8, 7, 7, 6, 6, 6, + 6, 5, 5, 4, 4, 4, 4, 3, 3, 3, 3, 2 }, + { 19, 19, 18, 18, 17, 17, 17, 17, 16, 16, 15, 15, 15, 15, 14, 14, 14, + 13, 13, 13, 12, 12, 12, 12, 11, 11, 10, 10, 10, 10, 10, 9, 9, 8, 8, 8, + 8, 8, 7, 7, 6, 6, 6, 6, 5, 5, 4, 4, 4 } +}; + +static const u8 rc_range_minqp444_12bpc[DSC_NUM_BUF_RANGES][RC_RANGE_QP444_12BPC_MAX_NUM_BPP] = { + { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, + 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, + 0, 0, 0, 0, 0, 0, 0, 0, 0 }, + { 5, 5, 5, 5, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 3, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, + 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, + 0, 0, 0, 0, 0, 0, 0, 0, 0 }, + { 11, 10, 10, 9, 8, 8, 8, 8, 8, 8, 8, 8, 7, 7, 7, 6, 5, 5, 4, 4, 4, 3, 3, 3, 3, + 3, 2, 2, 2, 2, 2, 2, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, + 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 }, + { 11, 11, 10, 10, 9, 9, 9, 9, 9, 9, 9, 9, 8, 8, 8, 7, 6, 6, 6, 6, 6, 5, 5, 5, + 5, 5, 4, 4, 3, 3, 3, 3, 3, 3, 3, 3, 2, 2, 2, 2, 2, 2, 2, 1, 1, 1, 1, 1, 1, 0, + 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 }, + { 13, 12, 12, 11, 11, 11, 11, 11, 11, 11, 11, 11, 10, 10, 9, 9, 9, 8, 7, 7, 7, + 7, 5, 5, 5, 5, 5, 5, 4, 4, 4, 3, 3, 3, 3, 3, 3, 3, 3, 3, 2, 2, 2, 2, 1, 1, + 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 }, + { 13, 12, 12, 12, 11, 11, 11, 11, 11, 11, 11, 11, 11, 11, 11, 10, 9, 9, 8, 8, + 8, 8, 6, 6, 6, 6, 5, 5, 5, 5, 5, 4, 4, 4, 4, 4, 4, 4, 4, 4, 3, 3, 3, 2, 2, 2, + 2, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0 }, + { 13, 13, 12, 12, 11, 11, 11, 11, 11, 11, 11, 11, 11, 11, 11, 10, 9, 9, 9, 9, + 9, 9, 9, 8, 8, 8, 7, 7, 7, 6, 5, 5, 5, 5, 5, 5, 5, 4, 4, 4, 4, 4, 4, 4, 3, 3, + 3, 2, 2, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0 }, + { 13, 13, 12, 12, 11, 11, 11, 11, 11, 11, 11, 11, 11, 11, 11, 11, 10, 10, 10, + 10, 10, 10, 9, 9, 9, 9, 8, 8, 8, 7, 7, 7, 6, 6, 6, 6, 6, 6, 5, 5, 5, 5, 4, 4, + 4, 3, 3, 2, 2, 2, 2, 2, 2, 1, 1, 1, 1, 0, 0, 0, 0 }, + { 13, 13, 12, 12, 11, 11, 11, 11, 11, 11, 11, 11, 11, 11, 11, 11, 11, 11, 11, + 11, 11, 11, 10, 10, 10, 10, 9, 9, 8, 7, 7, 7, 7, 7, 6, 6, 6, 6, 6, 6, 5, 5, + 5, 4, 4, 4, 4, 3, 3, 2, 2, 2, 2, 1, 1, 1, 1, 1, 1, 0, 0 }, + { 14, 13, 13, 12, 12, 12, 11, 11, 11, 11, 11, 11, 11, 11, 11, 11, 11, 11, 11, + 11, 11, 11, 10, 10, 10, 10, 9, 9, 8, 8, 8, 8, 8, 8, 7, 7, 7, 7, 7, 6, 6, 5, + 5, 5, 4, 4, 4, 4, 3, 3, 3, 3, 3, 2, 2, 2, 2, 2, 1, 1, 0 }, + { 14, 14, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 12, 12, 12, 12, + 12, 11, 11, 11, 11, 11, 11, 10, 10, 9, 9, 9, 9, 9, 9, 9, 9, 8, 8, 8, 7, 7, 7, + 6, 6, 6, 5, 5, 5, 5, 4, 4, 3, 3, 3, 2, 2, 2, 2, 1, 1, 1 }, + { 14, 14, 14, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, + 13, 12, 12, 11, 11, 11, 11, 11, 11, 10, 10, 10, 10, 9, 9, 9, 9, 8, 8, 8, 8, + 7, 7, 7, 7, 6, 6, 5, 5, 5, 4, 4, 4, 3, 3, 3, 3, 2, 2, 1, 1, 1 }, + { 14, 14, 14, 14, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, + 13, 12, 12, 12, 12, 12, 12, 11, 11, 10, 10, 10, 10, 9, 9, 9, 9, 8, 8, 8, 8, + 7, 7, 7, 7, 6, 6, 6, 6, 5, 4, 4, 4, 3, 3, 3, 3, 2, 2, 1, 1, 1 }, + { 17, 17, 17, 17, 16, 16, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, + 15, 14, 14, 13, 13, 13, 13, 12, 12, 11, 11, 11, 11, 10, 10, 9, 9, 9, 9, 8, 8, + 7, 7, 7, 7, 7, 6, 6, 6, 5, 5, 5, 5, 4, 4, 3, 3, 3, 3, 2, 2, 1 }, + { 22, 22, 21, 21, 20, 20, 20, 20, 19, 19, 18, 18, 18, 18, 17, 17, 17, 16, 16, + 16, 15, 15, 15, 15, 14, 14, 13, 13, 13, 13, 13, 12, 12, 11, 11, 11, 11, 11, + 10, 10, 9, 9, 9, 9, 9, 8, 8, 7, 7, 7, 7, 7, 6, 6, 5, 5, 5, 5, 4, 4, 3 } +}; + +static const u8 rc_range_maxqp444_12bpc[DSC_NUM_BUF_RANGES][RC_RANGE_QP444_12BPC_MAX_NUM_BPP] = { + { 12, 12, 12, 12, 12, 12, 11, 11, 11, 10, 9, 9, 6, 6, 5, 5, 5, 4, 4, 4, 4, 4, + 4, 3, 3, 3, 3, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, + 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 }, + { 14, 14, 13, 13, 12, 12, 12, 12, 12, 12, 11, 11, 9, 9, 9, 8, 8, 7, 7, 7, 7, 5, + 5, 5, 5, 5, 4, 4, 4, 3, 3, 3, 2, 2, 2, 2, 2, 2, 2, 1, 1, 1, 1, 1, 1, 1, 1, 1, + 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 }, + { 16, 15, 15, 14, 13, 13, 13, 13, 13, 13, 13, 13, 12, 12, 12, 11, 10, 10, 9, 9, + 9, 7, 7, 7, 7, 7, 6, 6, 5, 5, 5, 5, 4, 4, 4, 3, 3, 3, 3, 3, 3, 2, 2, 2, 1, 1, + 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 }, + { 16, 16, 15, 15, 14, 14, 14, 14, 14, 14, 14, 14, 13, 13, 13, 12, 11, 11, 10, + 10, 10, 8, 8, 8, 8, 8, 7, 7, 6, 5, 5, 5, 5, 5, 5, 5, 4, 4, 3, 3, 3, 3, 3, 2, + 2, 2, 2, 2, 2, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 }, + { 17, 16, 16, 15, 15, 15, 15, 15, 15, 15, 15, 15, 14, 14, 13, 12, 12, 11, 10, + 10, 10, 10, 8, 8, 8, 8, 8, 8, 7, 7, 7, 6, 6, 5, 5, 5, 4, 4, 4, 4, 3, 3, 3, 3, + 2, 2, 2, 2, 2, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0 }, + { 17, 16, 16, 16, 15, 15, 15, 15, 15, 15, 15, 15, 14, 14, 14, 13, 12, 12, 11, + 11, 11, 11, 9, 9, 9, 9, 8, 8, 8, 8, 7, 6, 6, 6, 6, 6, 5, 5, 5, 5, 4, 4, 4, 3, + 3, 3, 3, 2, 2, 2, 2, 2, 2, 1, 1, 1, 1, 1, 1, 1, 0 }, + { 17, 17, 16, 16, 15, 15, 15, 15, 15, 15, 15, 15, 15, 14, 14, 13, 12, 12, 11, + 11, 11, 11, 11, 10, 10, 10, 9, 9, 9, 8, 7, 7, 7, 7, 7, 7, 7, 6, 6, 6, 5, 5, + 5, 5, 4, 4, 4, 3, 3, 2, 2, 2, 2, 2, 2, 2, 1, 1, 1, 1, 0 }, + { 18, 18, 17, 17, 16, 16, 16, 16, 16, 16, 16, 16, 16, 15, 15, 14, 13, 13, 12, + 12, 12, 12, 11, 11, 11, 11, 10, 10, 10, 8, 8, 8, 7, 7, 7, 7, 7, 7, 6, 6, 6, + 6, 5, 5, 5, 4, 4, 3, 3, 3, 3, 3, 3, 2, 2, 2, 2, 1, 1, 1, 1 }, + { 19, 19, 18, 18, 17, 17, 17, 17, 17, 17, 16, 16, 16, 15, 15, 14, 14, 13, 13, + 13, 13, 13, 12, 12, 12, 12, 11, 11, 10, 9, 8, 8, 8, 8, 7, 7, 7, 7, 7, 7, 6, + 6, 6, 5, 5, 5, 5, 4, 4, 3, 3, 3, 3, 2, 2, 2, 2, 2, 2, 1, 1 }, + { 20, 19, 19, 18, 18, 18, 17, 17, 17, 17, 17, 17, 17, 16, 16, 15, 14, 14, 13, + 13, 13, 13, 12, 12, 12, 12, 11, 11, 10, 10, 9, 9, 9, 9, 8, 8, 8, 8, 8, 7, 7, + 6, 6, 6, 5, 5, 5, 5, 4, 4, 4, 4, 4, 3, 3, 3, 3, 3, 2, 2, 1 }, + { 20, 20, 19, 19, 18, 18, 18, 18, 18, 18, 17, 17, 17, 16, 16, 15, 15, 14, 14, + 14, 13, 13, 12, 12, 12, 12, 11, 11, 10, 10, 10, 10, 10, 10, 10, 10, 9, 9, 9, + 8, 8, 8, 7, 7, 7, 6, 6, 6, 6, 5, 5, 4, 4, 4, 3, 3, 3, 3, 2, 2, 2 }, + { 20, 20, 20, 19, 19, 19, 18, 18, 18, 18, 17, 17, 17, 17, 16, 16, 16, 15, 15, + 15, 14, 14, 13, 13, 13, 13, 12, 12, 11, 11, 11, 11, 10, 10, 10, 10, 9, 9, 9, + 9, 8, 8, 8, 8, 7, 7, 6, 6, 6, 5, 5, 5, 4, 4, 4, 4, 3, 3, 2, 2, 2 }, + { 20, 20, 20, 20, 19, 19, 19, 19, 19, 18, 18, 17, 17, 17, 16, 16, 16, 15, 15, + 15, 14, 14, 13, 13, 13, 13, 12, 12, 11, 11, 11, 11, 10, 10, 10, 10, 9, 9, 9, + 9, 8, 8, 8, 8, 7, 7, 7, 7, 6, 5, 5, 5, 4, 4, 4, 4, 3, 3, 2, 2, 2 }, + { 21, 21, 21, 21, 20, 20, 19, 19, 19, 19, 18, 18, 18, 18, 17, 17, 16, 16, 16, + 16, 15, 15, 14, 14, 14, 14, 13, 13, 12, 12, 12, 12, 11, 11, 10, 10, 10, 10, + 9, 9, 8, 8, 8, 8, 8, 7, 7, 7, 6, 6, 6, 6, 5, 5, 4, 4, 4, 4, 3, 3, 2 }, + { 23, 23, 22, 22, 21, 21, 21, 21, 20, 20, 19, 19, 19, 19, 18, 18, 18, 17, 17, + 17, 16, 16, 16, 16, 15, 15, 14, 14, 14, 14, 14, 13, 13, 12, 12, 12, 12, 12, + 11, 11, 10, 10, 10, 10, 10, 9, 9, 8, 8, 8, 8, 8, 7, 7, 6, 6, 6, 6, 5, 5, 4 } +}; + +#define PARAM_TABLE(_minmax, _bpc, _row, _col) do { \ + if (bpc == (_bpc)) \ + return rc_range_##_minmax##qp444_##_bpc##bpc[_row][_col]; \ +} while (0) + +u8 intel_lookup_range_min_qp(int bpc, int buf_i, int bpp_i) +{ + PARAM_TABLE(min, 8, buf_i, bpp_i); + PARAM_TABLE(min, 10, buf_i, bpp_i); + PARAM_TABLE(min, 12, buf_i, bpp_i); + + MISSING_CASE(bpc); + return 0; +} + +u8 intel_lookup_range_max_qp(int bpc, int buf_i, int bpp_i) +{ + PARAM_TABLE(max, 8, buf_i, bpp_i); + PARAM_TABLE(max, 10, buf_i, bpp_i); + PARAM_TABLE(max, 12, buf_i, bpp_i); + + MISSING_CASE(bpc); + return 0; +} diff --git a/drivers/gpu/drm/i915/display/intel_qp_tables.h b/drivers/gpu/drm/i915/display/intel_qp_tables.h new file mode 100644 index 000000000000..9fb3c36bd7c6 --- /dev/null +++ b/drivers/gpu/drm/i915/display/intel_qp_tables.h @@ -0,0 +1,14 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright © 2021 Intel Corporation + */ + +#ifndef _INTEL_QP_TABLES_H_ +#define _INTEL_QP_TABLES_H_ + +#include <linux/types.h> + +u8 intel_lookup_range_min_qp(int bpc, int buf_i, int bpp_i); +u8 intel_lookup_range_max_qp(int bpc, int buf_i, int bpp_i); + +#endif diff --git a/drivers/gpu/drm/i915/display/intel_tc.c b/drivers/gpu/drm/i915/display/intel_tc.c index e325463acddd..c23c210a55f5 100644 --- a/drivers/gpu/drm/i915/display/intel_tc.c +++ b/drivers/gpu/drm/i915/display/intel_tc.c @@ -26,9 +26,7 @@ static const char *tc_port_mode_name(enum tc_port_mode mode) static enum intel_display_power_domain tc_cold_get_power_domain(struct intel_digital_port *dig_port) { - struct drm_i915_private *i915 = to_i915(dig_port->base.base.dev); - - if (DISPLAY_VER(i915) == 11) + if (intel_tc_cold_requires_aux_pw(dig_port)) return intel_legacy_aux_to_power_domain(dig_port->aux_ch); else return POWER_DOMAIN_TC_COLD_OFF; @@ -205,7 +203,7 @@ static void tc_port_fixup_legacy_flag(struct intel_digital_port *dig_port, dig_port->tc_legacy_port = !dig_port->tc_legacy_port; } -static u32 tc_port_live_status_mask(struct intel_digital_port *dig_port) +static u32 icl_tc_port_live_status_mask(struct intel_digital_port *dig_port) { struct drm_i915_private *i915 = to_i915(dig_port->base.base.dev); struct intel_uncore *uncore = &i915->uncore; @@ -238,6 +236,40 @@ static u32 tc_port_live_status_mask(struct intel_digital_port *dig_port) return mask; } +static u32 adl_tc_port_live_status_mask(struct intel_digital_port *dig_port) +{ + struct drm_i915_private *i915 = to_i915(dig_port->base.base.dev); + enum tc_port tc_port = intel_port_to_tc(i915, dig_port->base.port); + u32 isr_bit = i915->hotplug.pch_hpd[dig_port->base.hpd_pin]; + struct intel_uncore *uncore = &i915->uncore; + u32 val, mask = 0; + + val = intel_uncore_read(uncore, TCSS_DDI_STATUS(tc_port)); + if (val & TCSS_DDI_STATUS_HPD_LIVE_STATUS_ALT) + mask |= BIT(TC_PORT_DP_ALT); + if (val & TCSS_DDI_STATUS_HPD_LIVE_STATUS_TBT) + mask |= BIT(TC_PORT_TBT_ALT); + + if (intel_uncore_read(uncore, SDEISR) & isr_bit) + mask |= BIT(TC_PORT_LEGACY); + + /* The sink can be connected only in a single mode. */ + if (!drm_WARN_ON(&i915->drm, hweight32(mask) > 1)) + tc_port_fixup_legacy_flag(dig_port, mask); + + return mask; +} + +static u32 tc_port_live_status_mask(struct intel_digital_port *dig_port) +{ + struct drm_i915_private *i915 = to_i915(dig_port->base.base.dev); + + if (IS_ALDERLAKE_P(i915)) + return adl_tc_port_live_status_mask(dig_port); + + return icl_tc_port_live_status_mask(dig_port); +} + static bool icl_tc_phy_status_complete(struct intel_digital_port *dig_port) { struct drm_i915_private *i915 = to_i915(dig_port->base.base.dev); @@ -256,6 +288,33 @@ static bool icl_tc_phy_status_complete(struct intel_digital_port *dig_port) return val & DP_PHY_MODE_STATUS_COMPLETED(dig_port->tc_phy_fia_idx); } +static bool adl_tc_phy_status_complete(struct intel_digital_port *dig_port) +{ + struct drm_i915_private *i915 = to_i915(dig_port->base.base.dev); + struct intel_uncore *uncore = &i915->uncore; + u32 val; + + val = intel_uncore_read(uncore, TCSS_DDI_STATUS(dig_port->tc_phy_fia_idx)); + if (val == 0xffffffff) { + drm_dbg_kms(&i915->drm, + "Port %s: PHY in TCCOLD, assuming not complete\n", + dig_port->tc_port_name); + return false; + } + + return val & TCSS_DDI_STATUS_READY; +} + +static bool tc_phy_status_complete(struct intel_digital_port *dig_port) +{ + struct drm_i915_private *i915 = to_i915(dig_port->base.base.dev); + + if (IS_ALDERLAKE_P(i915)) + return adl_tc_phy_status_complete(dig_port); + + return icl_tc_phy_status_complete(dig_port); +} + static bool icl_tc_phy_take_ownership(struct intel_digital_port *dig_port, bool take) { @@ -280,7 +339,7 @@ static bool icl_tc_phy_take_ownership(struct intel_digital_port *dig_port, intel_uncore_write(uncore, PORT_TX_DFLEXDPCSSS(dig_port->tc_phy_fia), val); - if (!take && wait_for(!icl_tc_phy_status_complete(dig_port), 10)) + if (!take && wait_for(!tc_phy_status_complete(dig_port), 10)) drm_dbg_kms(&i915->drm, "Port %s: PHY complete clear timed out\n", dig_port->tc_port_name); @@ -288,6 +347,34 @@ static bool icl_tc_phy_take_ownership(struct intel_digital_port *dig_port, return true; } +static bool adl_tc_phy_take_ownership(struct intel_digital_port *dig_port, + bool take) +{ + struct drm_i915_private *i915 = to_i915(dig_port->base.base.dev); + struct intel_uncore *uncore = &i915->uncore; + enum port port = dig_port->base.port; + u32 val; + + val = intel_uncore_read(uncore, DDI_BUF_CTL(port)); + if (take) + val |= DDI_BUF_CTL_TC_PHY_OWNERSHIP; + else + val &= ~DDI_BUF_CTL_TC_PHY_OWNERSHIP; + intel_uncore_write(uncore, DDI_BUF_CTL(port), val); + + return true; +} + +static bool tc_phy_take_ownership(struct intel_digital_port *dig_port, bool take) +{ + struct drm_i915_private *i915 = to_i915(dig_port->base.base.dev); + + if (IS_ALDERLAKE_P(i915)) + return adl_tc_phy_take_ownership(dig_port, take); + + return icl_tc_phy_take_ownership(dig_port, take); +} + static bool icl_tc_phy_is_owned(struct intel_digital_port *dig_port) { struct drm_i915_private *i915 = to_i915(dig_port->base.base.dev); @@ -306,6 +393,27 @@ static bool icl_tc_phy_is_owned(struct intel_digital_port *dig_port) return val & DP_PHY_MODE_STATUS_NOT_SAFE(dig_port->tc_phy_fia_idx); } +static bool adl_tc_phy_is_owned(struct intel_digital_port *dig_port) +{ + struct drm_i915_private *i915 = to_i915(dig_port->base.base.dev); + struct intel_uncore *uncore = &i915->uncore; + enum port port = dig_port->base.port; + u32 val; + + val = intel_uncore_read(uncore, DDI_BUF_CTL(port)); + return val & DDI_BUF_CTL_TC_PHY_OWNERSHIP; +} + +static bool tc_phy_is_owned(struct intel_digital_port *dig_port) +{ + struct drm_i915_private *i915 = to_i915(dig_port->base.base.dev); + + if (IS_ALDERLAKE_P(i915)) + return adl_tc_phy_is_owned(dig_port); + + return icl_tc_phy_is_owned(dig_port); +} + /* * This function implements the first part of the Connect Flow described by our * specification, Gen11 TypeC Programming chapter. The rest of the flow (reading @@ -323,13 +431,13 @@ static void icl_tc_phy_connect(struct intel_digital_port *dig_port, struct drm_i915_private *i915 = to_i915(dig_port->base.base.dev); int max_lanes; - if (!icl_tc_phy_status_complete(dig_port)) { + if (!tc_phy_status_complete(dig_port)) { drm_dbg_kms(&i915->drm, "Port %s: PHY not ready\n", dig_port->tc_port_name); goto out_set_tbt_alt_mode; } - if (!icl_tc_phy_take_ownership(dig_port, true) && + if (!tc_phy_take_ownership(dig_port, true) && !drm_WARN_ON(&i915->drm, dig_port->tc_legacy_port)) goto out_set_tbt_alt_mode; @@ -364,7 +472,7 @@ static void icl_tc_phy_connect(struct intel_digital_port *dig_port, return; out_release_phy: - icl_tc_phy_take_ownership(dig_port, false); + tc_phy_take_ownership(dig_port, false); out_set_tbt_alt_mode: dig_port->tc_mode = TC_PORT_TBT_ALT; } @@ -380,7 +488,7 @@ static void icl_tc_phy_disconnect(struct intel_digital_port *dig_port) /* Nothing to do, we never disconnect from legacy mode */ break; case TC_PORT_DP_ALT: - icl_tc_phy_take_ownership(dig_port, false); + tc_phy_take_ownership(dig_port, false); dig_port->tc_mode = TC_PORT_TBT_ALT; break; case TC_PORT_TBT_ALT: @@ -395,13 +503,13 @@ static bool icl_tc_phy_is_connected(struct intel_digital_port *dig_port) { struct drm_i915_private *i915 = to_i915(dig_port->base.base.dev); - if (!icl_tc_phy_status_complete(dig_port)) { + if (!tc_phy_status_complete(dig_port)) { drm_dbg_kms(&i915->drm, "Port %s: PHY status not complete\n", dig_port->tc_port_name); return dig_port->tc_mode == TC_PORT_TBT_ALT; } - if (!icl_tc_phy_is_owned(dig_port)) { + if (!tc_phy_is_owned(dig_port)) { drm_dbg_kms(&i915->drm, "Port %s: PHY not owned\n", dig_port->tc_port_name); @@ -419,8 +527,8 @@ intel_tc_port_get_current_mode(struct intel_digital_port *dig_port) u32 live_status_mask = tc_port_live_status_mask(dig_port); enum tc_port_mode mode; - if (!icl_tc_phy_is_owned(dig_port) || - drm_WARN_ON(&i915->drm, !icl_tc_phy_status_complete(dig_port))) + if (!tc_phy_is_owned(dig_port) || + drm_WARN_ON(&i915->drm, !tc_phy_status_complete(dig_port))) return TC_PORT_TBT_ALT; mode = dig_port->tc_legacy_port ? TC_PORT_LEGACY : TC_PORT_DP_ALT; @@ -442,7 +550,7 @@ intel_tc_port_get_target_mode(struct intel_digital_port *dig_port) if (live_status_mask) return fls(live_status_mask) - 1; - return icl_tc_phy_status_complete(dig_port) && + return tc_phy_status_complete(dig_port) && dig_port->tc_legacy_port ? TC_PORT_LEGACY : TC_PORT_TBT_ALT; } @@ -454,7 +562,7 @@ static void intel_tc_port_reset_mode(struct intel_digital_port *dig_port, enum tc_port_mode old_tc_mode = dig_port->tc_mode; intel_display_power_flush_work(i915); - if (DISPLAY_VER(i915) != 11 || !dig_port->tc_legacy_port) { + if (!intel_tc_cold_requires_aux_pw(dig_port)) { enum intel_display_power_domain aux_domain; bool aux_powered; @@ -624,13 +732,11 @@ tc_has_modular_fia(struct drm_i915_private *i915, struct intel_digital_port *dig if (!INTEL_INFO(i915)->display.has_modular_fia) return false; - /* TODO: check if in real HW MODULAR_FIA_MASK is set, if so remove this block */ - if (IS_ALDERLAKE_P(i915)) - return true; - + mutex_lock(&dig_port->tc_lock); wakeref = tc_cold_block(dig_port); val = intel_uncore_read(&i915->uncore, PORT_TX_DFLEXDPSP(FIA1)); tc_cold_unblock(dig_port, wakeref); + mutex_unlock(&dig_port->tc_lock); drm_WARN_ON(&i915->drm, val == 0xffffffff); @@ -673,3 +779,11 @@ void intel_tc_port_init(struct intel_digital_port *dig_port, bool is_legacy) dig_port->tc_link_refcount = 0; tc_port_load_fia_params(i915, dig_port); } + +bool intel_tc_cold_requires_aux_pw(struct intel_digital_port *dig_port) +{ + struct drm_i915_private *i915 = to_i915(dig_port->base.base.dev); + + return (DISPLAY_VER(i915) == 11 && dig_port->tc_legacy_port) || + IS_ALDERLAKE_P(i915); +} diff --git a/drivers/gpu/drm/i915/display/intel_tc.h b/drivers/gpu/drm/i915/display/intel_tc.h index b619e4736f85..0eacbd76ec15 100644 --- a/drivers/gpu/drm/i915/display/intel_tc.h +++ b/drivers/gpu/drm/i915/display/intel_tc.h @@ -29,4 +29,6 @@ bool intel_tc_port_ref_held(struct intel_digital_port *dig_port); void intel_tc_port_init(struct intel_digital_port *dig_port, bool is_legacy); +bool intel_tc_cold_requires_aux_pw(struct intel_digital_port *dig_port); + #endif /* __INTEL_TC_H__ */ diff --git a/drivers/gpu/drm/i915/display/intel_tv.c b/drivers/gpu/drm/i915/display/intel_tv.c index ce73ebdfc669..aa52af7891f0 100644 --- a/drivers/gpu/drm/i915/display/intel_tv.c +++ b/drivers/gpu/drm/i915/display/intel_tv.c @@ -1307,7 +1307,7 @@ intel_tv_compute_config(struct intel_encoder *encoder, * the active portion. Hence following this formula seems * more trouble that it's worth. * - * if (IS_GEN(dev_priv, 4)) { + * if (GRAPHICS_VER(dev_priv) == 4) { * num = cdclk * (tv_mode->oversample >> !tv_mode->progressive); * den = tv_mode->clock; * } else { diff --git a/drivers/gpu/drm/i915/display/intel_vdsc.c b/drivers/gpu/drm/i915/display/intel_vdsc.c index efc3184d8315..7121b66bf96d 100644 --- a/drivers/gpu/drm/i915/display/intel_vdsc.c +++ b/drivers/gpu/drm/i915/display/intel_vdsc.c @@ -5,12 +5,13 @@ * Author: Gaurav K Singh <gaurav.k.singh@intel.com> * Manasi Navare <manasi.d.navare@intel.com> */ - +#include <linux/limits.h> #include "i915_drv.h" #include "intel_de.h" #include "intel_display_types.h" #include "intel_dsi.h" #include "intel_vdsc.h" +#include "intel_qp_tables.h" enum ROW_INDEX_BPP { ROW_INDEX_6BPP = 0, @@ -373,12 +374,81 @@ static bool is_pipe_dsc(const struct intel_crtc_state *crtc_state) return true; } +static void +calculate_rc_params(struct rc_parameters *rc, + struct drm_dsc_config *vdsc_cfg) +{ + int bpc = vdsc_cfg->bits_per_component; + int bpp = vdsc_cfg->bits_per_pixel >> 4; + int ofs_und6[] = { 0, -2, -2, -4, -6, -6, -8, -8, -8, -10, -10, -12, -12, -12, -12 }; + int ofs_und8[] = { 2, 0, 0, -2, -4, -6, -8, -8, -8, -10, -10, -10, -12, -12, -12 }; + int ofs_und12[] = { 2, 0, 0, -2, -4, -6, -8, -8, -8, -10, -10, -10, -12, -12, -12 }; + int ofs_und15[] = { 10, 8, 6, 4, 2, 0, -2, -4, -6, -8, -10, -10, -12, -12, -12 }; + int qp_bpc_modifier = (bpc - 8) * 2; + u32 res, buf_i, bpp_i; + + if (vdsc_cfg->slice_height >= 8) + rc->first_line_bpg_offset = + 12 + DIV_ROUND_UP((9 * min(34, vdsc_cfg->slice_height - 8)), 100); + else + rc->first_line_bpg_offset = 2 * (vdsc_cfg->slice_height - 1); + + /* Our hw supports only 444 modes as of today */ + if (bpp >= 12) + rc->initial_offset = 2048; + else if (bpp >= 10) + rc->initial_offset = 5632 - DIV_ROUND_UP(((bpp - 10) * 3584), 2); + else if (bpp >= 8) + rc->initial_offset = 6144 - DIV_ROUND_UP(((bpp - 8) * 512), 2); + else + rc->initial_offset = 6144; + + /* initial_xmit_delay = rc_model_size/2/compression_bpp */ + rc->initial_xmit_delay = DIV_ROUND_UP(DSC_RC_MODEL_SIZE_CONST, 2 * bpp); + + rc->flatness_min_qp = 3 + qp_bpc_modifier; + rc->flatness_max_qp = 12 + qp_bpc_modifier; + + rc->rc_quant_incr_limit0 = 11 + qp_bpc_modifier; + rc->rc_quant_incr_limit1 = 11 + qp_bpc_modifier; + + bpp_i = (2 * (bpp - 6)); + for (buf_i = 0; buf_i < DSC_NUM_BUF_RANGES; buf_i++) { + /* Read range_minqp and range_max_qp from qp tables */ + rc->rc_range_params[buf_i].range_min_qp = + intel_lookup_range_min_qp(bpc, buf_i, bpp_i); + rc->rc_range_params[buf_i].range_max_qp = + intel_lookup_range_max_qp(bpc, buf_i, bpp_i); + + /* Calculate range_bgp_offset */ + if (bpp <= 6) { + rc->rc_range_params[buf_i].range_bpg_offset = ofs_und6[buf_i]; + } else if (bpp <= 8) { + res = DIV_ROUND_UP(((bpp - 6) * (ofs_und8[buf_i] - ofs_und6[buf_i])), 2); + rc->rc_range_params[buf_i].range_bpg_offset = + ofs_und6[buf_i] + res; + } else if (bpp <= 12) { + rc->rc_range_params[buf_i].range_bpg_offset = + ofs_und8[buf_i]; + } else if (bpp <= 15) { + res = DIV_ROUND_UP(((bpp - 12) * (ofs_und15[buf_i] - ofs_und12[buf_i])), 3); + rc->rc_range_params[buf_i].range_bpg_offset = + ofs_und12[buf_i] + res; + } else { + rc->rc_range_params[buf_i].range_bpg_offset = + ofs_und15[buf_i]; + } + } +} + int intel_dsc_compute_params(struct intel_encoder *encoder, struct intel_crtc_state *pipe_config) { + struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); struct drm_dsc_config *vdsc_cfg = &pipe_config->dsc.config; u16 compressed_bpp = pipe_config->dsc.compressed_bpp; const struct rc_parameters *rc_params; + struct rc_parameters *rc = NULL; u8 i = 0; vdsc_cfg->pic_width = pipe_config->hw.adjusted_mode.crtc_hdisplay; @@ -413,9 +483,24 @@ int intel_dsc_compute_params(struct intel_encoder *encoder, vdsc_cfg->rc_buf_thresh[13] = 0x7D; } - rc_params = get_rc_params(compressed_bpp, vdsc_cfg->bits_per_component); - if (!rc_params) - return -EINVAL; + /* + * From XE_LPD onwards we supports compression bpps in steps of 1 + * upto uncompressed bpp-1, hence add calculations for all the rc + * parameters + */ + if (DISPLAY_VER(dev_priv) >= 13) { + rc = kmalloc(sizeof(*rc), GFP_KERNEL); + if (!rc) + return -ENOMEM; + + calculate_rc_params(rc, vdsc_cfg); + rc_params = rc; + } else { + rc_params = get_rc_params(compressed_bpp, + vdsc_cfg->bits_per_component); + if (!rc_params) + return -EINVAL; + } vdsc_cfg->first_line_bpg_offset = rc_params->first_line_bpg_offset; vdsc_cfg->initial_xmit_delay = rc_params->initial_xmit_delay; @@ -441,20 +526,20 @@ int intel_dsc_compute_params(struct intel_encoder *encoder, /* * BitsPerComponent value determines mux_word_size: - * When BitsPerComponent is 12bpc, muxWordSize will be equal to 64 bits - * When BitsPerComponent is 8 or 10bpc, muxWordSize will be equal to - * 48 bits + * When BitsPerComponent is less than or 10bpc, muxWordSize will be equal to + * 48 bits otherwise 64 */ - if (vdsc_cfg->bits_per_component == 8 || - vdsc_cfg->bits_per_component == 10) + if (vdsc_cfg->bits_per_component <= 10) vdsc_cfg->mux_word_size = DSC_MUX_WORD_SIZE_8_10_BPC; - else if (vdsc_cfg->bits_per_component == 12) + else vdsc_cfg->mux_word_size = DSC_MUX_WORD_SIZE_12_BPC; /* InitialScaleValue is a 6 bit value with 3 fractional bits (U3.3) */ vdsc_cfg->initial_scale_value = (vdsc_cfg->rc_model_size << 3) / (vdsc_cfg->rc_model_size - vdsc_cfg->initial_offset); + kfree(rc); + return 0; } @@ -1076,12 +1161,12 @@ void intel_dsc_disable(const struct intel_crtc_state *old_crtc_state) struct intel_crtc *crtc = to_intel_crtc(old_crtc_state->uapi.crtc); struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); - if (!(old_crtc_state->dsc.compression_enable && - old_crtc_state->bigjoiner)) - return; - - intel_de_write(dev_priv, dss_ctl1_reg(old_crtc_state), 0); - intel_de_write(dev_priv, dss_ctl2_reg(old_crtc_state), 0); + /* Disable only if either of them is enabled */ + if (old_crtc_state->dsc.compression_enable || + old_crtc_state->bigjoiner) { + intel_de_write(dev_priv, dss_ctl1_reg(old_crtc_state), 0); + intel_de_write(dev_priv, dss_ctl2_reg(old_crtc_state), 0); + } } void intel_uncompressed_joiner_get_config(struct intel_crtc_state *crtc_state) diff --git a/drivers/gpu/drm/i915/display/intel_vrr.c b/drivers/gpu/drm/i915/display/intel_vrr.c index 046210ae1de0..c335b1dbafcf 100644 --- a/drivers/gpu/drm/i915/display/intel_vrr.c +++ b/drivers/gpu/drm/i915/display/intel_vrr.c @@ -68,7 +68,10 @@ static int intel_vrr_vblank_exit_length(const struct intel_crtc_state *crtc_stat struct drm_i915_private *i915 = to_i915(crtc->base.dev); /* The hw imposes the extra scanline before frame start */ - return crtc_state->vrr.pipeline_full + i915->framestart_delay + 1; + if (DISPLAY_VER(i915) >= 13) + return crtc_state->vrr.guardband + i915->framestart_delay + 1; + else + return crtc_state->vrr.pipeline_full + i915->framestart_delay + 1; } int intel_vrr_vmin_vblank_start(const struct intel_crtc_state *crtc_state) @@ -86,6 +89,8 @@ void intel_vrr_compute_config(struct intel_crtc_state *crtc_state, struct drm_connector_state *conn_state) { + struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); + struct drm_i915_private *i915 = to_i915(crtc->base.dev); struct intel_connector *connector = to_intel_connector(conn_state->connector); struct drm_display_mode *adjusted_mode = &crtc_state->hw.adjusted_mode; @@ -124,17 +129,26 @@ intel_vrr_compute_config(struct intel_crtc_state *crtc_state, crtc_state->vrr.flipline = crtc_state->vrr.vmin + 1; /* - * FIXME: s/4/framestart_delay+1/ to get consistent - * earliest/latest points for register latching regardless - * of the framestart_delay used? - * - * FIXME: this really needs the extra scanline to provide consistent - * behaviour for all framestart_delay values. Otherwise with - * framestart_delay==3 we will end up extending the min vblank by - * one extra line. + * For XE_LPD+, we use guardband and pipeline override + * is deprecated. */ - crtc_state->vrr.pipeline_full = - min(255, crtc_state->vrr.vmin - adjusted_mode->crtc_vdisplay - 4 - 1); + if (DISPLAY_VER(i915) >= 13) + crtc_state->vrr.guardband = + crtc_state->vrr.vmin - adjusted_mode->crtc_vdisplay - + i915->window2_delay; + else + /* + * FIXME: s/4/framestart_delay+1/ to get consistent + * earliest/latest points for register latching regardless + * of the framestart_delay used? + * + * FIXME: this really needs the extra scanline to provide consistent + * behaviour for all framestart_delay values. Otherwise with + * framestart_delay==3 we will end up extending the min vblank by + * one extra line. + */ + crtc_state->vrr.pipeline_full = + min(255, crtc_state->vrr.vmin - adjusted_mode->crtc_vdisplay - 4 - 1); crtc_state->mode_flags |= I915_MODE_FLAG_VRR; } @@ -149,10 +163,15 @@ void intel_vrr_enable(struct intel_encoder *encoder, if (!crtc_state->vrr.enable) return; - trans_vrr_ctl = VRR_CTL_VRR_ENABLE | - VRR_CTL_IGN_MAX_SHIFT | VRR_CTL_FLIP_LINE_EN | - VRR_CTL_PIPELINE_FULL(crtc_state->vrr.pipeline_full) | - VRR_CTL_PIPELINE_FULL_OVERRIDE; + if (DISPLAY_VER(dev_priv) >= 13) + trans_vrr_ctl = VRR_CTL_VRR_ENABLE | + VRR_CTL_IGN_MAX_SHIFT | VRR_CTL_FLIP_LINE_EN | + XELPD_VRR_CTL_VRR_GUARDBAND(crtc_state->vrr.guardband); + else + trans_vrr_ctl = VRR_CTL_VRR_ENABLE | + VRR_CTL_IGN_MAX_SHIFT | VRR_CTL_FLIP_LINE_EN | + VRR_CTL_PIPELINE_FULL(crtc_state->vrr.pipeline_full) | + VRR_CTL_PIPELINE_FULL_OVERRIDE; intel_de_write(dev_priv, TRANS_VRR_VMIN(cpu_transcoder), crtc_state->vrr.vmin - 1); intel_de_write(dev_priv, TRANS_VRR_VMAX(cpu_transcoder), crtc_state->vrr.vmax - 1); @@ -199,8 +218,13 @@ void intel_vrr_get_config(struct intel_crtc *crtc, if (!crtc_state->vrr.enable) return; - if (trans_vrr_ctl & VRR_CTL_PIPELINE_FULL_OVERRIDE) - crtc_state->vrr.pipeline_full = REG_FIELD_GET(VRR_CTL_PIPELINE_FULL_MASK, trans_vrr_ctl); + if (DISPLAY_VER(dev_priv) >= 13) + crtc_state->vrr.guardband = + REG_FIELD_GET(XELPD_VRR_CTL_VRR_GUARDBAND_MASK, trans_vrr_ctl); + else + if (trans_vrr_ctl & VRR_CTL_PIPELINE_FULL_OVERRIDE) + crtc_state->vrr.pipeline_full = + REG_FIELD_GET(VRR_CTL_PIPELINE_FULL_MASK, trans_vrr_ctl); if (trans_vrr_ctl & VRR_CTL_FLIP_LINE_EN) crtc_state->vrr.flipline = intel_de_read(dev_priv, TRANS_VRR_FLIPLINE(cpu_transcoder)) + 1; crtc_state->vrr.vmax = intel_de_read(dev_priv, TRANS_VRR_VMAX(cpu_transcoder)) + 1; diff --git a/drivers/gpu/drm/i915/display/skl_universal_plane.c b/drivers/gpu/drm/i915/display/skl_universal_plane.c index 59e032f3687a..92a4fd508e92 100644 --- a/drivers/gpu/drm/i915/display/skl_universal_plane.c +++ b/drivers/gpu/drm/i915/display/skl_universal_plane.c @@ -850,6 +850,29 @@ static u32 cnl_plane_ctl_flip(unsigned int reflect) return 0; } +static u32 adlp_plane_ctl_arb_slots(const struct intel_plane_state *plane_state) +{ + const struct drm_framebuffer *fb = plane_state->hw.fb; + + if (intel_format_info_is_yuv_semiplanar(fb->format, fb->modifier)) { + switch (fb->format->cpp[0]) { + case 2: + return PLANE_CTL_ARB_SLOTS(1); + default: + return PLANE_CTL_ARB_SLOTS(0); + } + } else { + switch (fb->format->cpp[0]) { + case 8: + return PLANE_CTL_ARB_SLOTS(3); + case 4: + return PLANE_CTL_ARB_SLOTS(1); + default: + return PLANE_CTL_ARB_SLOTS(0); + } + } +} + static u32 skl_plane_ctl_crtc(const struct intel_crtc_state *crtc_state) { struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev); @@ -903,6 +926,10 @@ static u32 skl_plane_ctl(const struct intel_crtc_state *crtc_state, else if (key->flags & I915_SET_COLORKEY_SOURCE) plane_ctl |= PLANE_CTL_KEY_ENABLE_SOURCE; + /* Wa_22012358565:adlp */ + if (DISPLAY_VER(dev_priv) == 13) + plane_ctl |= adlp_plane_ctl_arb_slots(plane_state); + return plane_ctl; } diff --git a/drivers/gpu/drm/i915/dma_resv_utils.c b/drivers/gpu/drm/i915/dma_resv_utils.c index 9e508e7d4629..7df91b7e4ca8 100644 --- a/drivers/gpu/drm/i915/dma_resv_utils.c +++ b/drivers/gpu/drm/i915/dma_resv_utils.c @@ -10,7 +10,7 @@ void dma_resv_prune(struct dma_resv *resv) { if (dma_resv_trylock(resv)) { - if (dma_resv_test_signaled_rcu(resv, true)) + if (dma_resv_test_signaled(resv, true)) dma_resv_add_excl_fence(resv, NULL); dma_resv_unlock(resv); } diff --git a/drivers/gpu/drm/i915/gem/i915_gem_busy.c b/drivers/gpu/drm/i915/gem/i915_gem_busy.c index 25235ef630c1..6234e17259c1 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_busy.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_busy.c @@ -105,7 +105,7 @@ i915_gem_busy_ioctl(struct drm_device *dev, void *data, * Alternatively, we can trade that extra information on read/write * activity with * args->busy = - * !dma_resv_test_signaled_rcu(obj->resv, true); + * !dma_resv_test_signaled(obj->resv, true); * to report the overall busyness. This is what the wait-ioctl does. * */ @@ -113,11 +113,10 @@ retry: seq = raw_read_seqcount(&obj->base.resv->seq); /* Translate the exclusive fence to the READ *and* WRITE engine */ - args->busy = - busy_check_writer(rcu_dereference(obj->base.resv->fence_excl)); + args->busy = busy_check_writer(dma_resv_excl_fence(obj->base.resv)); /* Translate shared fences to READ set of engines */ - list = rcu_dereference(obj->base.resv->fence); + list = dma_resv_shared_list(obj->base.resv); if (list) { unsigned int shared_count = list->shared_count, i; diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c index 297143511f99..66789111a24b 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c @@ -1481,7 +1481,7 @@ static inline bool use_reloc_gpu(struct i915_vma *vma) if (DBG_FORCE_RELOC) return false; - return !dma_resv_test_signaled_rcu(vma->resv, true); + return !dma_resv_test_signaled(vma->resv, true); } static unsigned long vma_phys_addr(struct i915_vma *vma, u32 offset) diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.h b/drivers/gpu/drm/i915/gem/i915_gem_object.h index 2ebd79537aea..7c0eb425cb3b 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_object.h +++ b/drivers/gpu/drm/i915/gem/i915_gem_object.h @@ -500,7 +500,7 @@ i915_gem_object_last_write_engine(struct drm_i915_gem_object *obj) struct dma_fence *fence; rcu_read_lock(); - fence = dma_resv_get_excl_rcu(obj->base.resv); + fence = dma_resv_get_excl_unlocked(obj->base.resv); rcu_read_unlock(); if (fence && dma_fence_is_i915(fence) && !dma_fence_is_signaled(fence)) diff --git a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c index a657b99ec760..b5cbbe659a77 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c @@ -85,8 +85,8 @@ static bool i915_gem_userptr_invalidate(struct mmu_interval_notifier *mni, return true; /* we will unbind on next submission, still have userptr pins */ - r = dma_resv_wait_timeout_rcu(obj->base.resv, true, false, - MAX_SCHEDULE_TIMEOUT); + r = dma_resv_wait_timeout(obj->base.resv, true, false, + MAX_SCHEDULE_TIMEOUT); if (r <= 0) drm_err(&i915->drm, "(%ld) failed to wait for idle\n", r); diff --git a/drivers/gpu/drm/i915/gem/i915_gem_wait.c b/drivers/gpu/drm/i915/gem/i915_gem_wait.c index 4b9856d5ba14..1e97520c62b2 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_wait.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_wait.c @@ -45,7 +45,7 @@ i915_gem_object_wait_reservation(struct dma_resv *resv, unsigned int count, i; int ret; - ret = dma_resv_get_fences_rcu(resv, &excl, &count, &shared); + ret = dma_resv_get_fences(resv, &excl, &count, &shared); if (ret) return ret; @@ -73,7 +73,7 @@ i915_gem_object_wait_reservation(struct dma_resv *resv, */ prune_fences = count && timeout >= 0; } else { - excl = dma_resv_get_excl_rcu(resv); + excl = dma_resv_get_excl_unlocked(resv); } if (excl && timeout >= 0) @@ -158,8 +158,8 @@ i915_gem_object_wait_priority(struct drm_i915_gem_object *obj, unsigned int count, i; int ret; - ret = dma_resv_get_fences_rcu(obj->base.resv, - &excl, &count, &shared); + ret = dma_resv_get_fences(obj->base.resv, &excl, &count, + &shared); if (ret) return ret; @@ -170,7 +170,7 @@ i915_gem_object_wait_priority(struct drm_i915_gem_object *obj, kfree(shared); } else { - excl = dma_resv_get_excl_rcu(obj->base.resv); + excl = dma_resv_get_excl_unlocked(obj->base.resv); } if (excl) { diff --git a/drivers/gpu/drm/i915/gt/intel_gtt.h b/drivers/gpu/drm/i915/gt/intel_gtt.h index ca00b45827b7..50a98ce39f74 100644 --- a/drivers/gpu/drm/i915/gt/intel_gtt.h +++ b/drivers/gpu/drm/i915/gt/intel_gtt.h @@ -359,6 +359,7 @@ struct i915_ppgtt { #define i915_is_ggtt(vm) ((vm)->is_ggtt) #define i915_is_dpt(vm) ((vm)->is_dpt) +#define i915_is_ggtt_or_dpt(vm) (i915_is_ggtt(vm) || i915_is_dpt(vm)) int __must_check i915_vm_lock_objects(struct i915_address_space *vm, struct i915_gem_ww_ctx *ww); @@ -393,7 +394,7 @@ static inline struct i915_ppgtt * i915_vm_to_ppgtt(struct i915_address_space *vm) { BUILD_BUG_ON(offsetof(struct i915_ppgtt, vm)); - GEM_BUG_ON(i915_is_ggtt(vm)); + GEM_BUG_ON(i915_is_ggtt_or_dpt(vm)); return container_of(vm, struct i915_ppgtt, vm); } diff --git a/drivers/gpu/drm/i915/gvt/cmd_parser.c b/drivers/gpu/drm/i915/gvt/cmd_parser.c index ca9c9e27a43d..c4118b808268 100644 --- a/drivers/gpu/drm/i915/gvt/cmd_parser.c +++ b/drivers/gpu/drm/i915/gvt/cmd_parser.c @@ -1006,7 +1006,7 @@ static int cmd_reg_handler(struct parser_exec_state *s, * update reg values in it into vregs, so LRIs in workload with * inhibit context will restore with correct values */ - if (IS_GEN(s->engine->i915, 9) && + if (GRAPHICS_VER(s->engine->i915) == 9 && intel_gvt_mmio_is_sr_in_ctx(gvt, offset) && !strncmp(cmd, "lri", 3)) { intel_gvt_hypervisor_read_gpa(s->vgpu, @@ -1390,7 +1390,7 @@ static int gen8_check_mi_display_flip(struct parser_exec_state *s, if (!info->async_flip) return 0; - if (INTEL_GEN(s->engine->i915) >= 9) { + if (GRAPHICS_VER(s->engine->i915) >= 9) { stride = vgpu_vreg_t(s->vgpu, info->stride_reg) & GENMASK(9, 0); tile = (vgpu_vreg_t(s->vgpu, info->ctrl_reg) & GENMASK(12, 10)) >> 10; @@ -1418,7 +1418,7 @@ static int gen8_update_plane_mmio_from_mi_display_flip( set_mask_bits(&vgpu_vreg_t(vgpu, info->surf_reg), GENMASK(31, 12), info->surf_val << 12); - if (INTEL_GEN(dev_priv) >= 9) { + if (GRAPHICS_VER(dev_priv) >= 9) { set_mask_bits(&vgpu_vreg_t(vgpu, info->stride_reg), GENMASK(9, 0), info->stride_val); set_mask_bits(&vgpu_vreg_t(vgpu, info->ctrl_reg), GENMASK(12, 10), @@ -1446,7 +1446,7 @@ static int decode_mi_display_flip(struct parser_exec_state *s, { if (IS_BROADWELL(s->engine->i915)) return gen8_decode_mi_display_flip(s, info); - if (INTEL_GEN(s->engine->i915) >= 9) + if (GRAPHICS_VER(s->engine->i915) >= 9) return skl_decode_mi_display_flip(s, info); return -ENODEV; diff --git a/drivers/gpu/drm/i915/gvt/dmabuf.c b/drivers/gpu/drm/i915/gvt/dmabuf.c index d4f883f35b95..8e65cd8258b9 100644 --- a/drivers/gpu/drm/i915/gvt/dmabuf.c +++ b/drivers/gpu/drm/i915/gvt/dmabuf.c @@ -223,7 +223,7 @@ static struct drm_i915_gem_object *vgpu_create_gem(struct drm_device *dev, obj->read_domains = I915_GEM_DOMAIN_GTT; obj->write_domain = 0; - if (INTEL_GEN(dev_priv) >= 9) { + if (GRAPHICS_VER(dev_priv) >= 9) { unsigned int tiling_mode = 0; unsigned int stride = 0; diff --git a/drivers/gpu/drm/i915/gvt/fb_decoder.c b/drivers/gpu/drm/i915/gvt/fb_decoder.c index 0889ad8291b0..11a8baba6822 100644 --- a/drivers/gpu/drm/i915/gvt/fb_decoder.c +++ b/drivers/gpu/drm/i915/gvt/fb_decoder.c @@ -151,7 +151,7 @@ static u32 intel_vgpu_get_stride(struct intel_vgpu *vgpu, int pipe, u32 stride_reg = vgpu_vreg_t(vgpu, DSPSTRIDE(pipe)) & stride_mask; u32 stride = stride_reg; - if (INTEL_GEN(dev_priv) >= 9) { + if (GRAPHICS_VER(dev_priv) >= 9) { switch (tiled) { case PLANE_CTL_TILED_LINEAR: stride = stride_reg * 64; @@ -215,7 +215,7 @@ int intel_vgpu_decode_primary_plane(struct intel_vgpu *vgpu, if (!plane->enabled) return -ENODEV; - if (INTEL_GEN(dev_priv) >= 9) { + if (GRAPHICS_VER(dev_priv) >= 9) { plane->tiled = val & PLANE_CTL_TILED_MASK; fmt = skl_format_to_drm( val & PLANE_CTL_FORMAT_MASK, @@ -256,9 +256,9 @@ int intel_vgpu_decode_primary_plane(struct intel_vgpu *vgpu, } plane->stride = intel_vgpu_get_stride(vgpu, pipe, plane->tiled, - (INTEL_GEN(dev_priv) >= 9) ? - (_PRI_PLANE_STRIDE_MASK >> 6) : - _PRI_PLANE_STRIDE_MASK, plane->bpp); + (GRAPHICS_VER(dev_priv) >= 9) ? + (_PRI_PLANE_STRIDE_MASK >> 6) : + _PRI_PLANE_STRIDE_MASK, plane->bpp); plane->width = (vgpu_vreg_t(vgpu, PIPESRC(pipe)) & _PIPE_H_SRCSZ_MASK) >> _PIPE_H_SRCSZ_SHIFT; diff --git a/drivers/gpu/drm/i915/gvt/gtt.c b/drivers/gpu/drm/i915/gvt/gtt.c index 9478c132d7b6..cc2c05e18206 100644 --- a/drivers/gpu/drm/i915/gvt/gtt.c +++ b/drivers/gpu/drm/i915/gvt/gtt.c @@ -1055,12 +1055,12 @@ static bool vgpu_ips_enabled(struct intel_vgpu *vgpu) { struct drm_i915_private *dev_priv = vgpu->gvt->gt->i915; - if (INTEL_GEN(dev_priv) == 9 || INTEL_GEN(dev_priv) == 10) { + if (GRAPHICS_VER(dev_priv) == 9 || GRAPHICS_VER(dev_priv) == 10) { u32 ips = vgpu_vreg_t(vgpu, GEN8_GAMW_ECO_DEV_RW_IA) & GAMW_ECO_ENABLE_64K_IPS_FIELD; return ips == GAMW_ECO_ENABLE_64K_IPS_FIELD; - } else if (INTEL_GEN(dev_priv) >= 11) { + } else if (GRAPHICS_VER(dev_priv) >= 11) { /* 64K paging only controlled by IPS bit in PTE now. */ return true; } else diff --git a/drivers/gpu/drm/i915/gvt/handlers.c b/drivers/gpu/drm/i915/gvt/handlers.c index dda320749c65..98eb48c24c46 100644 --- a/drivers/gpu/drm/i915/gvt/handlers.c +++ b/drivers/gpu/drm/i915/gvt/handlers.c @@ -220,7 +220,7 @@ static int gamw_echo_dev_rw_ia_write(struct intel_vgpu *vgpu, { u32 ips = (*(u32 *)p_data) & GAMW_ECO_ENABLE_64K_IPS_FIELD; - if (INTEL_GEN(vgpu->gvt->gt->i915) <= 10) { + if (GRAPHICS_VER(vgpu->gvt->gt->i915) <= 10) { if (ips == GAMW_ECO_ENABLE_64K_IPS_FIELD) gvt_dbg_core("vgpu%d: ips enabled\n", vgpu->id); else if (!ips) @@ -286,7 +286,7 @@ static int mul_force_wake_write(struct intel_vgpu *vgpu, old = vgpu_vreg(vgpu, offset); new = CALC_MODE_MASK_REG(old, *(u32 *)p_data); - if (INTEL_GEN(vgpu->gvt->gt->i915) >= 9) { + if (GRAPHICS_VER(vgpu->gvt->gt->i915) >= 9) { switch (offset) { case FORCEWAKE_RENDER_GEN9_REG: ack_reg_offset = FORCEWAKE_ACK_RENDER_GEN9_REG; @@ -1174,7 +1174,7 @@ static int dp_aux_ch_ctl_mmio_write(struct intel_vgpu *vgpu, write_vreg(vgpu, offset, p_data, bytes); data = vgpu_vreg(vgpu, offset); - if ((INTEL_GEN(vgpu->gvt->gt->i915) >= 9) + if ((GRAPHICS_VER(vgpu->gvt->gt->i915) >= 9) && offset != _REG_SKL_DP_AUX_CH_CTL(port_index)) { /* SKL DPB/C/D aux ctl register changed */ return 0; @@ -3342,9 +3342,9 @@ static int init_skl_mmio_info(struct intel_gvt *gvt) MMIO_D(_MMIO(_PLANE_SURF_3_A), D_SKL_PLUS); MMIO_D(_MMIO(_PLANE_SURF_3_B), D_SKL_PLUS); - MMIO_D(CSR_SSP_BASE, D_SKL_PLUS); - MMIO_D(CSR_HTP_SKL, D_SKL_PLUS); - MMIO_D(CSR_LAST_WRITE, D_SKL_PLUS); + MMIO_D(DMC_SSP_BASE, D_SKL_PLUS); + MMIO_D(DMC_HTP_SKL, D_SKL_PLUS); + MMIO_D(DMC_LAST_WRITE, D_SKL_PLUS); MMIO_DFH(BDW_SCRATCH1, D_SKL_PLUS, F_CMD_ACCESS, NULL, NULL); @@ -3655,7 +3655,7 @@ void intel_gvt_clean_mmio_info(struct intel_gvt *gvt) * otherwise, need to update cmd_reg_handler in cmd_parser.c */ static struct gvt_mmio_block mmio_blocks[] = { - {D_SKL_PLUS, _MMIO(CSR_MMIO_START_RANGE), 0x3000, NULL, NULL}, + {D_SKL_PLUS, _MMIO(DMC_MMIO_START_RANGE), 0x3000, NULL, NULL}, {D_ALL, _MMIO(MCHBAR_MIRROR_BASE_SNB), 0x40000, NULL, NULL}, {D_ALL, _MMIO(VGT_PVINFO_PAGE), VGT_PVINFO_SIZE, pvinfo_mmio_read, pvinfo_mmio_write}, diff --git a/drivers/gpu/drm/i915/gvt/interrupt.c b/drivers/gpu/drm/i915/gvt/interrupt.c index 497d28ce47df..614b951d919f 100644 --- a/drivers/gpu/drm/i915/gvt/interrupt.c +++ b/drivers/gpu/drm/i915/gvt/interrupt.c @@ -585,7 +585,7 @@ static void gen8_init_irq( SET_BIT_INFO(irq, 4, PRIMARY_C_FLIP_DONE, INTEL_GVT_IRQ_INFO_DE_PIPE_C); SET_BIT_INFO(irq, 5, SPRITE_C_FLIP_DONE, INTEL_GVT_IRQ_INFO_DE_PIPE_C); - } else if (INTEL_GEN(gvt->gt->i915) >= 9) { + } else if (GRAPHICS_VER(gvt->gt->i915) >= 9) { SET_BIT_INFO(irq, 25, AUX_CHANNEL_B, INTEL_GVT_IRQ_INFO_DE_PORT); SET_BIT_INFO(irq, 26, AUX_CHANNEL_C, INTEL_GVT_IRQ_INFO_DE_PORT); SET_BIT_INFO(irq, 27, AUX_CHANNEL_D, INTEL_GVT_IRQ_INFO_DE_PORT); diff --git a/drivers/gpu/drm/i915/gvt/mmio_context.c b/drivers/gpu/drm/i915/gvt/mmio_context.c index c9589e26af93..b8ac80765461 100644 --- a/drivers/gpu/drm/i915/gvt/mmio_context.c +++ b/drivers/gpu/drm/i915/gvt/mmio_context.c @@ -373,7 +373,7 @@ static void handle_tlb_pending_event(struct intel_vgpu *vgpu, */ fw = intel_uncore_forcewake_for_reg(uncore, reg, FW_REG_READ | FW_REG_WRITE); - if (engine->id == RCS0 && INTEL_GEN(engine->i915) >= 9) + if (engine->id == RCS0 && GRAPHICS_VER(engine->i915) >= 9) fw |= FORCEWAKE_RENDER; intel_uncore_forcewake_get(uncore, fw); @@ -409,7 +409,7 @@ static void switch_mocs(struct intel_vgpu *pre, struct intel_vgpu *next, if (drm_WARN_ON(&engine->i915->drm, engine->id >= ARRAY_SIZE(regs))) return; - if (engine->id == RCS0 && IS_GEN(engine->i915, 9)) + if (engine->id == RCS0 && GRAPHICS_VER(engine->i915) == 9) return; if (!pre && !gen9_render_mocs.initialized) @@ -474,7 +474,7 @@ static void switch_mmio(struct intel_vgpu *pre, struct engine_mmio *mmio; u32 old_v, new_v; - if (INTEL_GEN(engine->i915) >= 9) + if (GRAPHICS_VER(engine->i915) >= 9) switch_mocs(pre, next, engine); for (mmio = engine->i915->gvt->engine_mmio_list.mmio; @@ -486,7 +486,7 @@ static void switch_mmio(struct intel_vgpu *pre, * state image on gen9, it's initialized by lri command and * save or restore with context together. */ - if (IS_GEN(engine->i915, 9) && mmio->in_context) + if (GRAPHICS_VER(engine->i915) == 9 && mmio->in_context) continue; // save @@ -580,7 +580,7 @@ void intel_gvt_init_engine_mmio_context(struct intel_gvt *gvt) { struct engine_mmio *mmio; - if (INTEL_GEN(gvt->gt->i915) >= 9) { + if (GRAPHICS_VER(gvt->gt->i915) >= 9) { gvt->engine_mmio_list.mmio = gen9_engine_mmio_list; gvt->engine_mmio_list.tlb_mmio_offset_list = gen8_tlb_mmio_offset_list; gvt->engine_mmio_list.tlb_mmio_offset_list_cnt = ARRAY_SIZE(gen8_tlb_mmio_offset_list); diff --git a/drivers/gpu/drm/i915/gvt/scheduler.c b/drivers/gpu/drm/i915/gvt/scheduler.c index fc735692f21f..734c37c5e347 100644 --- a/drivers/gpu/drm/i915/gvt/scheduler.c +++ b/drivers/gpu/drm/i915/gvt/scheduler.c @@ -364,7 +364,7 @@ static int copy_workload_to_ring_buffer(struct intel_vgpu_workload *workload) u32 *cs; int err; - if (IS_GEN(req->engine->i915, 9) && is_inhibit_context(req->context)) + if (GRAPHICS_VER(req->engine->i915) == 9 && is_inhibit_context(req->context)) intel_vgpu_restore_inhibit_context(vgpu, req); /* @@ -1148,7 +1148,7 @@ static void complete_current_workload(struct intel_gvt *gvt, int ring_id) static int workload_thread(void *arg) { struct intel_engine_cs *engine = arg; - const bool need_force_wake = INTEL_GEN(engine->i915) >= 9; + const bool need_force_wake = GRAPHICS_VER(engine->i915) >= 9; struct intel_gvt *gvt = engine->i915->gvt; struct intel_gvt_workload_scheduler *scheduler = &gvt->scheduler; struct intel_vgpu_workload *workload = NULL; diff --git a/drivers/gpu/drm/i915/gvt/vgpu.c b/drivers/gpu/drm/i915/gvt/vgpu.c index 9039787f123a..fa6b92615799 100644 --- a/drivers/gpu/drm/i915/gvt/vgpu.c +++ b/drivers/gpu/drm/i915/gvt/vgpu.c @@ -149,10 +149,10 @@ int intel_gvt_init_vgpu_types(struct intel_gvt *gvt) gvt->types[i].avail_instance = min(low_avail / vgpu_types[i].low_mm, high_avail / vgpu_types[i].high_mm); - if (IS_GEN(gvt->gt->i915, 8)) + if (GRAPHICS_VER(gvt->gt->i915) == 8) sprintf(gvt->types[i].name, "GVTg_V4_%s", vgpu_types[i].name); - else if (IS_GEN(gvt->gt->i915, 9)) + else if (GRAPHICS_VER(gvt->gt->i915) == 9) sprintf(gvt->types[i].name, "GVTg_V5_%s", vgpu_types[i].name); diff --git a/drivers/gpu/drm/i915/i915_cmd_parser.c b/drivers/gpu/drm/i915/i915_cmd_parser.c index 5b4b2bd46e7c..3992c25a191d 100644 --- a/drivers/gpu/drm/i915/i915_cmd_parser.c +++ b/drivers/gpu/drm/i915/i915_cmd_parser.c @@ -946,8 +946,8 @@ int intel_engine_init_cmd_parser(struct intel_engine_cs *engine) int cmd_table_count; int ret; - if (!IS_GEN(engine->i915, 7) && !(IS_GEN(engine->i915, 9) && - engine->class == COPY_ENGINE_CLASS)) + if (GRAPHICS_VER(engine->i915) != 7 && !(GRAPHICS_VER(engine->i915) == 9 && + engine->class == COPY_ENGINE_CLASS)) return 0; switch (engine->class) { @@ -977,7 +977,7 @@ int intel_engine_init_cmd_parser(struct intel_engine_cs *engine) break; case COPY_ENGINE_CLASS: engine->get_cmd_length_mask = gen7_blt_get_cmd_length_mask; - if (IS_GEN(engine->i915, 9)) { + if (GRAPHICS_VER(engine->i915) == 9) { cmd_tables = gen9_blt_cmd_table; cmd_table_count = ARRAY_SIZE(gen9_blt_cmd_table); engine->get_cmd_length_mask = @@ -993,7 +993,7 @@ int intel_engine_init_cmd_parser(struct intel_engine_cs *engine) cmd_table_count = ARRAY_SIZE(gen7_blt_cmd_table); } - if (IS_GEN(engine->i915, 9)) { + if (GRAPHICS_VER(engine->i915) == 9) { engine->reg_tables = gen9_blt_reg_tables; engine->reg_table_count = ARRAY_SIZE(gen9_blt_reg_tables); @@ -1537,7 +1537,7 @@ int intel_engine_cmd_parser(struct intel_engine_cs *engine, if (IS_HASWELL(engine->i915)) flags = MI_BATCH_NON_SECURE_HSW; - GEM_BUG_ON(!IS_GEN_RANGE(engine->i915, 6, 7)); + GEM_BUG_ON(!IS_GRAPHICS_VER(engine->i915, 6, 7)); __gen6_emit_bb_start(batch_end, batch_addr, flags); diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c index 8dd374691102..cc745751ac53 100644 --- a/drivers/gpu/drm/i915/i915_debugfs.c +++ b/drivers/gpu/drm/i915/i915_debugfs.c @@ -124,6 +124,17 @@ stringify_page_sizes(unsigned int page_sizes, char *buf, size_t len) } } +static const char *stringify_vma_type(const struct i915_vma *vma) +{ + if (i915_vma_is_ggtt(vma)) + return "ggtt"; + + if (i915_vma_is_dpt(vma)) + return "dpt"; + + return "ppgtt"; +} + void i915_debugfs_describe_obj(struct seq_file *m, struct drm_i915_gem_object *obj) { @@ -156,11 +167,11 @@ i915_debugfs_describe_obj(struct seq_file *m, struct drm_i915_gem_object *obj) if (i915_vma_is_pinned(vma)) pin_count++; - seq_printf(m, " (%sgtt offset: %08llx, size: %08llx, pages: %s", - i915_vma_is_ggtt(vma) ? "g" : "pp", + seq_printf(m, " (%s offset: %08llx, size: %08llx, pages: %s", + stringify_vma_type(vma), vma->node.start, vma->node.size, stringify_page_sizes(vma->page_sizes.gtt, NULL, 0)); - if (i915_vma_is_ggtt(vma)) { + if (i915_vma_is_ggtt(vma) || i915_vma_is_dpt(vma)) { switch (vma->ggtt_view.type) { case I915_GGTT_VIEW_NORMAL: seq_puts(m, ", normal"); @@ -350,7 +361,7 @@ static int i915_frequency_info(struct seq_file *m, void *unused) wakeref = intel_runtime_pm_get(&dev_priv->runtime_pm); - if (IS_GEN(dev_priv, 5)) { + if (GRAPHICS_VER(dev_priv) == 5) { u16 rgvswctl = intel_uncore_read16(uncore, MEMSWCTL); u16 rgvstat = intel_uncore_read16(uncore, MEMSTAT_ILK); @@ -397,7 +408,7 @@ static int i915_frequency_info(struct seq_file *m, void *unused) seq_printf(m, "efficient (RPe) frequency: %d MHz\n", intel_gpu_freq(rps, rps->efficient_freq)); - } else if (INTEL_GEN(dev_priv) >= 6) { + } else if (GRAPHICS_VER(dev_priv) >= 6) { u32 rp_state_limits; u32 gt_perf_status; u32 rp_state_cap; @@ -421,7 +432,7 @@ static int i915_frequency_info(struct seq_file *m, void *unused) intel_uncore_forcewake_get(&dev_priv->uncore, FORCEWAKE_ALL); reqf = intel_uncore_read(&dev_priv->uncore, GEN6_RPNSWREQ); - if (INTEL_GEN(dev_priv) >= 9) + if (GRAPHICS_VER(dev_priv) >= 9) reqf >>= 23; else { reqf &= ~GEN6_TURBO_DISABLE; @@ -447,7 +458,7 @@ static int i915_frequency_info(struct seq_file *m, void *unused) intel_uncore_forcewake_put(&dev_priv->uncore, FORCEWAKE_ALL); - if (INTEL_GEN(dev_priv) >= 11) { + if (GRAPHICS_VER(dev_priv) >= 11) { pm_ier = intel_uncore_read(&dev_priv->uncore, GEN11_GPM_WGBOXPERF_INTR_ENABLE); pm_imr = intel_uncore_read(&dev_priv->uncore, GEN11_GPM_WGBOXPERF_INTR_MASK); /* @@ -456,7 +467,7 @@ static int i915_frequency_info(struct seq_file *m, void *unused) */ pm_isr = 0; pm_iir = 0; - } else if (INTEL_GEN(dev_priv) >= 8) { + } else if (GRAPHICS_VER(dev_priv) >= 8) { pm_ier = intel_uncore_read(&dev_priv->uncore, GEN8_GT_IER(2)); pm_imr = intel_uncore_read(&dev_priv->uncore, GEN8_GT_IMR(2)); pm_isr = intel_uncore_read(&dev_priv->uncore, GEN8_GT_ISR(2)); @@ -479,14 +490,14 @@ static int i915_frequency_info(struct seq_file *m, void *unused) seq_printf(m, "PM IER=0x%08x IMR=0x%08x, MASK=0x%08x\n", pm_ier, pm_imr, pm_mask); - if (INTEL_GEN(dev_priv) <= 10) + if (GRAPHICS_VER(dev_priv) <= 10) seq_printf(m, "PM ISR=0x%08x IIR=0x%08x\n", pm_isr, pm_iir); seq_printf(m, "pm_intrmsk_mbz: 0x%08x\n", rps->pm_intrmsk_mbz); seq_printf(m, "GT_PERF_STATUS: 0x%08x\n", gt_perf_status); seq_printf(m, "Render p-state ratio: %d\n", - (gt_perf_status & (INTEL_GEN(dev_priv) >= 9 ? 0x1ff00 : 0xff00)) >> 8); + (gt_perf_status & (GRAPHICS_VER(dev_priv) >= 9 ? 0x1ff00 : 0xff00)) >> 8); seq_printf(m, "Render p-state VID: %d\n", gt_perf_status & 0xff); seq_printf(m, "Render p-state limit: %d\n", @@ -527,20 +538,20 @@ static int i915_frequency_info(struct seq_file *m, void *unused) max_freq = (IS_GEN9_LP(dev_priv) ? rp_state_cap >> 0 : rp_state_cap >> 16) & 0xff; max_freq *= (IS_GEN9_BC(dev_priv) || - INTEL_GEN(dev_priv) >= 10 ? GEN9_FREQ_SCALER : 1); + GRAPHICS_VER(dev_priv) >= 10 ? GEN9_FREQ_SCALER : 1); seq_printf(m, "Lowest (RPN) frequency: %dMHz\n", intel_gpu_freq(rps, max_freq)); max_freq = (rp_state_cap & 0xff00) >> 8; max_freq *= (IS_GEN9_BC(dev_priv) || - INTEL_GEN(dev_priv) >= 10 ? GEN9_FREQ_SCALER : 1); + GRAPHICS_VER(dev_priv) >= 10 ? GEN9_FREQ_SCALER : 1); seq_printf(m, "Nominal (RP1) frequency: %dMHz\n", intel_gpu_freq(rps, max_freq)); max_freq = (IS_GEN9_LP(dev_priv) ? rp_state_cap >> 16 : rp_state_cap >> 0) & 0xff; max_freq *= (IS_GEN9_BC(dev_priv) || - INTEL_GEN(dev_priv) >= 10 ? GEN9_FREQ_SCALER : 1); + GRAPHICS_VER(dev_priv) >= 10 ? GEN9_FREQ_SCALER : 1); seq_printf(m, "Max non-overclocked (RP0) frequency: %dMHz\n", intel_gpu_freq(rps, max_freq)); seq_printf(m, "Max overclocked frequency: %dMHz\n", @@ -611,12 +622,12 @@ static int i915_swizzle_info(struct seq_file *m, void *data) seq_puts(m, "L-shaped memory detected\n"); /* On BDW+, swizzling is not used. See detect_bit_6_swizzle() */ - if (INTEL_GEN(dev_priv) >= 8 || IS_VALLEYVIEW(dev_priv)) + if (GRAPHICS_VER(dev_priv) >= 8 || IS_VALLEYVIEW(dev_priv)) return 0; wakeref = intel_runtime_pm_get(&dev_priv->runtime_pm); - if (IS_GEN_RANGE(dev_priv, 3, 4)) { + if (IS_GRAPHICS_VER(dev_priv, 3, 4)) { seq_printf(m, "DDC = 0x%08x\n", intel_uncore_read(uncore, DCC)); seq_printf(m, "DDC2 = 0x%08x\n", @@ -634,7 +645,7 @@ static int i915_swizzle_info(struct seq_file *m, void *data) intel_uncore_read(uncore, MAD_DIMM_C2)); seq_printf(m, "TILECTL = 0x%08x\n", intel_uncore_read(uncore, TILECTL)); - if (INTEL_GEN(dev_priv) >= 8) + if (GRAPHICS_VER(dev_priv) >= 8) seq_printf(m, "GAMTARBMODE = 0x%08x\n", intel_uncore_read(uncore, GAMTARBMODE)); else @@ -945,7 +956,7 @@ static int i915_forcewake_open(struct inode *inode, struct file *file) atomic_inc(>->user_wakeref); intel_gt_pm_get(gt); - if (INTEL_GEN(i915) >= 6) + if (GRAPHICS_VER(i915) >= 6) intel_uncore_forcewake_user_get(gt->uncore); return 0; @@ -956,7 +967,7 @@ static int i915_forcewake_release(struct inode *inode, struct file *file) struct drm_i915_private *i915 = inode->i_private; struct intel_gt *gt = &i915->gt; - if (INTEL_GEN(i915) >= 6) + if (GRAPHICS_VER(i915) >= 6) intel_uncore_forcewake_user_put(&i915->uncore); intel_gt_pm_put(gt); atomic_dec(>->user_wakeref); diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c index 5118dc8386b2..d5b3c5ba6bd2 100644 --- a/drivers/gpu/drm/i915/i915_drv.c +++ b/drivers/gpu/drm/i915/i915_drv.c @@ -49,7 +49,7 @@ #include "display/intel_acpi.h" #include "display/intel_bw.h" #include "display/intel_cdclk.h" -#include "display/intel_csr.h" +#include "display/intel_dmc.h" #include "display/intel_display_types.h" #include "display/intel_dp.h" #include "display/intel_fbdev.h" @@ -106,12 +106,12 @@ static int i915_get_bridge_dev(struct drm_i915_private *dev_priv) static int intel_alloc_mchbar_resource(struct drm_i915_private *dev_priv) { - int reg = INTEL_GEN(dev_priv) >= 4 ? MCHBAR_I965 : MCHBAR_I915; + int reg = GRAPHICS_VER(dev_priv) >= 4 ? MCHBAR_I965 : MCHBAR_I915; u32 temp_lo, temp_hi = 0; u64 mchbar_addr; int ret; - if (INTEL_GEN(dev_priv) >= 4) + if (GRAPHICS_VER(dev_priv) >= 4) pci_read_config_dword(dev_priv->bridge_dev, reg + 4, &temp_hi); pci_read_config_dword(dev_priv->bridge_dev, reg, &temp_lo); mchbar_addr = ((u64)temp_hi << 32) | temp_lo; @@ -138,7 +138,7 @@ intel_alloc_mchbar_resource(struct drm_i915_private *dev_priv) return ret; } - if (INTEL_GEN(dev_priv) >= 4) + if (GRAPHICS_VER(dev_priv) >= 4) pci_write_config_dword(dev_priv->bridge_dev, reg + 4, upper_32_bits(dev_priv->mch_res.start)); @@ -151,7 +151,7 @@ intel_alloc_mchbar_resource(struct drm_i915_private *dev_priv) static void intel_setup_mchbar(struct drm_i915_private *dev_priv) { - int mchbar_reg = INTEL_GEN(dev_priv) >= 4 ? MCHBAR_I965 : MCHBAR_I915; + int mchbar_reg = GRAPHICS_VER(dev_priv) >= 4 ? MCHBAR_I965 : MCHBAR_I915; u32 temp; bool enabled; @@ -190,7 +190,7 @@ intel_setup_mchbar(struct drm_i915_private *dev_priv) static void intel_teardown_mchbar(struct drm_i915_private *dev_priv) { - int mchbar_reg = INTEL_GEN(dev_priv) >= 4 ? MCHBAR_I965 : MCHBAR_I915; + int mchbar_reg = GRAPHICS_VER(dev_priv) >= 4 ? MCHBAR_I965 : MCHBAR_I915; if (dev_priv->mchbar_need_disable) { if (IS_I915G(dev_priv) || IS_I915GM(dev_priv)) { @@ -475,7 +475,7 @@ static int i915_set_dma_info(struct drm_i915_private *i915) goto mask_err; /* overlay on gen2 is broken and can't address above 1G */ - if (IS_GEN(i915, 2)) + if (GRAPHICS_VER(i915) == 2) mask_size = 30; /* @@ -601,7 +601,7 @@ static int i915_driver_hw_probe(struct drm_i915_private *dev_priv) * device. The kernel then disables that interrupt source and so * prevents the other device from working properly. */ - if (INTEL_GEN(dev_priv) >= 5) { + if (GRAPHICS_VER(dev_priv) >= 5) { if (pci_enable_msi(pdev) < 0) drm_dbg(&dev_priv->drm, "can't enable MSI"); } @@ -729,7 +729,7 @@ static void i915_welcome_messages(struct drm_i915_private *dev_priv) intel_platform_name(INTEL_INFO(dev_priv)->platform), intel_subplatform(RUNTIME_INFO(dev_priv), INTEL_INFO(dev_priv)->platform), - INTEL_GEN(dev_priv)); + GRAPHICS_VER(dev_priv)); intel_device_info_print_static(INTEL_INFO(dev_priv), &p); intel_device_info_print_runtime(RUNTIME_INFO(dev_priv), &p); @@ -803,7 +803,7 @@ int i915_driver_probe(struct pci_dev *pdev, const struct pci_device_id *ent) */ #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST) if (IS_ENABLED(CONFIG_DRM_I915_UNSTABLE_FAKE_LMEM)) { - if (INTEL_GEN(i915) >= 9 && i915_selftest.live < 0 && + if (GRAPHICS_VER(i915) >= 9 && i915_selftest.live < 0 && i915->params.fake_lmem_start) { mkwrite_device_info(i915)->memory_regions = REGION_SMEM | REGION_LMEM | REGION_STOLEN_SMEM; @@ -1043,7 +1043,7 @@ void i915_driver_shutdown(struct drm_i915_private *i915) intel_suspend_encoders(i915); intel_shutdown_encoders(i915); - intel_csr_ucode_suspend(i915); + intel_dmc_ucode_suspend(i915); /* * The only requirement is to reboot with display DC states disabled, @@ -1124,7 +1124,7 @@ static int i915_drm_suspend(struct drm_device *dev) dev_priv->suspend_count++; - intel_csr_ucode_suspend(dev_priv); + intel_dmc_ucode_suspend(dev_priv); enable_rpm_wakeref_asserts(&dev_priv->runtime_pm); @@ -1182,7 +1182,7 @@ static int i915_drm_suspend_late(struct drm_device *dev, bool hibernation) * Fujitsu FSC S7110 * Acer Aspire 1830T */ - if (!(hibernation && INTEL_GEN(dev_priv) < 6)) + if (!(hibernation && GRAPHICS_VER(dev_priv) < 6)) pci_set_power_state(pdev, PCI_D3hot); out: @@ -1226,7 +1226,7 @@ static int i915_drm_resume(struct drm_device *dev) i915_ggtt_resume(&dev_priv->ggtt); - intel_csr_ucode_resume(dev_priv); + intel_dmc_ucode_resume(dev_priv); i915_restore_display(dev_priv); intel_pps_unlock_regs_wa(dev_priv); diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index 9aee6a045590..7b7918f72c41 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -67,6 +67,7 @@ #include "display/intel_bios.h" #include "display/intel_display.h" #include "display/intel_display_power.h" +#include "display/intel_dmc.h" #include "display/intel_dpll_mgr.h" #include "display/intel_dsb.h" #include "display/intel_frontbuffer.h" @@ -328,23 +329,6 @@ struct drm_i915_display_funcs { void (*read_luts)(struct intel_crtc_state *crtc_state); }; -struct intel_csr { - struct work_struct work; - const char *fw_path; - u32 required_version; - u32 max_fw_size; /* bytes */ - u32 *dmc_payload; - u32 dmc_fw_size; /* dwords */ - u32 version; - u32 mmio_count; - i915_reg_t mmioaddr[20]; - u32 mmiodata[20]; - u32 dc_state; - u32 target_dc_state; - u32 allowed_dc_mask; - intel_wakeref_t wakeref; -}; - enum i915_cache_level { I915_CACHE_NONE = 0, I915_CACHE_LLC, /* also used for snoopable memory on non-LLC */ @@ -589,6 +573,8 @@ i915_fence_timeout(const struct drm_i915_private *i915) /* Amount of SAGV/QGV points, BSpec precisely defines this */ #define I915_NUM_QGV_POINTS 8 +#define HAS_HW_SAGV_WM(i915) (DISPLAY_VER(i915) >= 13 && !IS_DGFX(i915)) + struct ddi_vbt_port_info { /* Non-NULL if port present. */ struct intel_bios_encoder_data *devdata; @@ -824,7 +810,7 @@ struct drm_i915_private { struct intel_wopcm wopcm; - struct intel_csr csr; + struct intel_dmc dmc; struct intel_gmbus gmbus[GMBUS_NUM_PINS]; @@ -1138,6 +1124,9 @@ struct drm_i915_private { u8 framestart_delay; + /* Window2 specifies time required to program DSB (Window2) in number of scan lines */ + u8 window2_delay; + u8 pch_ssc_use; /* For i915gm/i945gm vblank irq workaround */ @@ -1558,9 +1547,9 @@ IS_SUBPLATFORM(const struct drm_i915_private *i915, (IS_ALDERLAKE_P(__i915) && \ IS_GT_STEP(__i915, since, until)) -#define IS_LP(dev_priv) (INTEL_INFO(dev_priv)->is_lp) -#define IS_GEN9_LP(dev_priv) (IS_GEN(dev_priv, 9) && IS_LP(dev_priv)) -#define IS_GEN9_BC(dev_priv) (IS_GEN(dev_priv, 9) && !IS_LP(dev_priv)) +#define IS_LP(dev_priv) (INTEL_INFO(dev_priv)->is_lp) +#define IS_GEN9_LP(dev_priv) (GRAPHICS_VER(dev_priv) == 9 && IS_LP(dev_priv)) +#define IS_GEN9_BC(dev_priv) (GRAPHICS_VER(dev_priv) == 9 && !IS_LP(dev_priv)) #define __HAS_ENGINE(engine_mask, id) ((engine_mask) & BIT(id)) #define HAS_ENGINE(gt, id) __HAS_ENGINE((gt)->info.engine_mask, id) @@ -1580,12 +1569,12 @@ IS_SUBPLATFORM(const struct drm_i915_private *i915, * The Gen7 cmdparser copies the scanned buffer to the ggtt for execution * All later gens can run the final buffer from the ppgtt */ -#define CMDPARSER_USES_GGTT(dev_priv) IS_GEN(dev_priv, 7) +#define CMDPARSER_USES_GGTT(dev_priv) (GRAPHICS_VER(dev_priv) == 7) #define HAS_LLC(dev_priv) (INTEL_INFO(dev_priv)->has_llc) #define HAS_SNOOP(dev_priv) (INTEL_INFO(dev_priv)->has_snoop) #define HAS_EDRAM(dev_priv) ((dev_priv)->edram_size_mb) -#define HAS_SECURE_BATCHES(dev_priv) (INTEL_GEN(dev_priv) < 6) +#define HAS_SECURE_BATCHES(dev_priv) (GRAPHICS_VER(dev_priv) < 6) #define HAS_WT(dev_priv) HAS_EDRAM(dev_priv) #define HWS_NEEDS_PHYSICAL(dev_priv) (INTEL_INFO(dev_priv)->hws_needs_physical) @@ -1618,7 +1607,7 @@ IS_SUBPLATFORM(const struct drm_i915_private *i915, #define HAS_BROKEN_CS_TLB(dev_priv) (IS_I830(dev_priv) || IS_I845G(dev_priv)) #define NEEDS_RC6_CTX_CORRUPTION_WA(dev_priv) \ - (IS_BROADWELL(dev_priv) || IS_GEN(dev_priv, 9)) + (IS_BROADWELL(dev_priv) || GRAPHICS_VER(dev_priv) == 9) /* WaRsDisableCoarsePowerGating:skl,cnl */ #define NEEDS_WaRsDisableCoarsePowerGating(dev_priv) \ @@ -1626,23 +1615,22 @@ IS_SUBPLATFORM(const struct drm_i915_private *i915, IS_SKL_GT3(dev_priv) || \ IS_SKL_GT4(dev_priv)) -#define HAS_GMBUS_IRQ(dev_priv) (INTEL_GEN(dev_priv) >= 4) -#define HAS_GMBUS_BURST_READ(dev_priv) (INTEL_GEN(dev_priv) >= 10 || \ +#define HAS_GMBUS_IRQ(dev_priv) (GRAPHICS_VER(dev_priv) >= 4) +#define HAS_GMBUS_BURST_READ(dev_priv) (GRAPHICS_VER(dev_priv) >= 10 || \ IS_GEMINILAKE(dev_priv) || \ IS_KABYLAKE(dev_priv)) /* With the 945 and later, Y tiling got adjusted so that it was 32 128-byte * rows, which changed the alignment requirements and fence programming. */ -#define HAS_128_BYTE_Y_TILING(dev_priv) (!IS_GEN(dev_priv, 2) && \ - !(IS_I915G(dev_priv) || \ - IS_I915GM(dev_priv))) +#define HAS_128_BYTE_Y_TILING(dev_priv) (GRAPHICS_VER(dev_priv) != 2 && \ + !(IS_I915G(dev_priv) || IS_I915GM(dev_priv))) #define SUPPORTS_TV(dev_priv) (INTEL_INFO(dev_priv)->display.supports_tv) #define I915_HAS_HOTPLUG(dev_priv) (INTEL_INFO(dev_priv)->display.has_hotplug) -#define HAS_FW_BLC(dev_priv) (INTEL_GEN(dev_priv) > 2) +#define HAS_FW_BLC(dev_priv) (GRAPHICS_VER(dev_priv) > 2) #define HAS_FBC(dev_priv) (INTEL_INFO(dev_priv)->display.has_fbc) -#define HAS_CUR_FBC(dev_priv) (!HAS_GMCH(dev_priv) && INTEL_GEN(dev_priv) >= 7) +#define HAS_CUR_FBC(dev_priv) (!HAS_GMCH(dev_priv) && GRAPHICS_VER(dev_priv) >= 7) #define HAS_IPS(dev_priv) (IS_HSW_ULT(dev_priv) || IS_BROADWELL(dev_priv)) @@ -1653,7 +1641,7 @@ IS_SUBPLATFORM(const struct drm_i915_private *i915, #define HAS_PSR(dev_priv) (INTEL_INFO(dev_priv)->display.has_psr) #define HAS_PSR_HW_TRACKING(dev_priv) \ (INTEL_INFO(dev_priv)->display.has_psr_hw_tracking) -#define HAS_PSR2_SEL_FETCH(dev_priv) (INTEL_GEN(dev_priv) >= 12) +#define HAS_PSR2_SEL_FETCH(dev_priv) (GRAPHICS_VER(dev_priv) >= 12) #define HAS_TRANSCODER(dev_priv, trans) ((INTEL_INFO(dev_priv)->cpu_transcoder_mask & BIT(trans)) != 0) #define HAS_RC6(dev_priv) (INTEL_INFO(dev_priv)->has_rc6) @@ -1662,9 +1650,9 @@ IS_SUBPLATFORM(const struct drm_i915_private *i915, #define HAS_RPS(dev_priv) (INTEL_INFO(dev_priv)->has_rps) -#define HAS_CSR(dev_priv) (INTEL_INFO(dev_priv)->display.has_csr) +#define HAS_DMC(dev_priv) (INTEL_INFO(dev_priv)->display.has_dmc) -#define HAS_MSO(i915) (INTEL_GEN(i915) >= 12) +#define HAS_MSO(i915) (GRAPHICS_VER(i915) >= 12) #define HAS_RUNTIME_PM(dev_priv) (INTEL_INFO(dev_priv)->has_runtime_pm) #define HAS_64BIT_RELOC(dev_priv) (INTEL_INFO(dev_priv)->has_64bit_reloc) @@ -1683,7 +1671,7 @@ IS_SUBPLATFORM(const struct drm_i915_private *i915, #define HAS_GMCH(dev_priv) (INTEL_INFO(dev_priv)->display.has_gmch) -#define HAS_LSPCON(dev_priv) (IS_GEN_RANGE(dev_priv, 9, 10)) +#define HAS_LSPCON(dev_priv) (IS_GRAPHICS_VER(dev_priv, 9, 10)) /* DPF == dynamic parity feature */ #define HAS_L3_DPF(dev_priv) (INTEL_INFO(dev_priv)->has_l3_dpf) @@ -1697,7 +1685,7 @@ IS_SUBPLATFORM(const struct drm_i915_private *i915, #define HAS_DISPLAY(dev_priv) (INTEL_INFO(dev_priv)->pipe_mask != 0) -#define HAS_VRR(i915) (INTEL_GEN(i915) >= 12) +#define HAS_VRR(i915) (GRAPHICS_VER(i915) >= 12) /* Only valid when HAS_DISPLAY() is true */ #define INTEL_DISPLAY_ENABLED(dev_priv) \ @@ -1724,7 +1712,7 @@ static inline bool intel_vtd_active(void) static inline bool intel_scanout_needs_vtd_wa(struct drm_i915_private *dev_priv) { - return INTEL_GEN(dev_priv) >= 6 && intel_vtd_active(); + return GRAPHICS_VER(dev_priv) >= 6 && intel_vtd_active(); } static inline bool @@ -1942,7 +1930,7 @@ int remap_io_sg(struct vm_area_struct *vma, static inline int intel_hws_csb_write_index(struct drm_i915_private *i915) { - if (INTEL_GEN(i915) >= 10) + if (GRAPHICS_VER(i915) >= 10) return CNL_HWS_CSB_WRITE_INDEX; else return I915_HWS_CSB_WRITE_INDEX; diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index cffd7f4f87dc..1aadc021d92e 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -442,7 +442,7 @@ i915_gem_pread_ioctl(struct drm_device *dev, void *data, /* PREAD is disallowed for all platforms after TGL-LP. This also * covers all platforms with local memory. */ - if (INTEL_GEN(i915) >= 12 && !IS_TIGERLAKE(i915)) + if (GRAPHICS_VER(i915) >= 12 && !IS_TIGERLAKE(i915)) return -EOPNOTSUPP; if (args->size == 0) @@ -722,7 +722,7 @@ i915_gem_pwrite_ioctl(struct drm_device *dev, void *data, /* PWRITE is disallowed for all platforms after TGL-LP. This also * covers all platforms with local memory. */ - if (INTEL_GEN(i915) >= 12 && !IS_TIGERLAKE(i915)) + if (GRAPHICS_VER(i915) >= 12 && !IS_TIGERLAKE(i915)) return -EOPNOTSUPP; if (args->size == 0) diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c index 99ca242ec13b..35c97c39f125 100644 --- a/drivers/gpu/drm/i915/i915_gpu_error.c +++ b/drivers/gpu/drm/i915/i915_gpu_error.c @@ -36,7 +36,7 @@ #include <drm/drm_print.h> -#include "display/intel_csr.h" +#include "display/intel_dmc.h" #include "display/intel_overlay.h" #include "gem/i915_gem_context.h" @@ -435,13 +435,13 @@ static void error_print_instdone(struct drm_i915_error_state_buf *m, err_printf(m, " INSTDONE: 0x%08x\n", ee->instdone.instdone); - if (ee->engine->class != RENDER_CLASS || INTEL_GEN(m->i915) <= 3) + if (ee->engine->class != RENDER_CLASS || GRAPHICS_VER(m->i915) <= 3) return; err_printf(m, " SC_INSTDONE: 0x%08x\n", ee->instdone.slice_common); - if (INTEL_GEN(m->i915) <= 6) + if (GRAPHICS_VER(m->i915) <= 6) return; for_each_instdone_slice_subslice(m->i915, sseu, slice, subslice) @@ -454,7 +454,7 @@ static void error_print_instdone(struct drm_i915_error_state_buf *m, slice, subslice, ee->instdone.row[slice][subslice]); - if (INTEL_GEN(m->i915) < 12) + if (GRAPHICS_VER(m->i915) < 12) return; err_printf(m, " SC_INSTDONE_EXTRA: 0x%08x\n", @@ -543,7 +543,7 @@ static void error_print_engine(struct drm_i915_error_state_buf *m, upper_32_bits(start), lower_32_bits(start), upper_32_bits(end), lower_32_bits(end)); } - if (INTEL_GEN(m->i915) >= 4) { + if (GRAPHICS_VER(m->i915) >= 4) { err_printf(m, " BBADDR: 0x%08x_%08x\n", (u32)(ee->bbaddr>>32), (u32)ee->bbaddr); err_printf(m, " BB_STATE: 0x%08x\n", ee->bbstate); @@ -552,14 +552,14 @@ static void error_print_engine(struct drm_i915_error_state_buf *m, err_printf(m, " INSTPM: 0x%08x\n", ee->instpm); err_printf(m, " FADDR: 0x%08x %08x\n", upper_32_bits(ee->faddr), lower_32_bits(ee->faddr)); - if (INTEL_GEN(m->i915) >= 6) { + if (GRAPHICS_VER(m->i915) >= 6) { err_printf(m, " RC PSMI: 0x%08x\n", ee->rc_psmi); err_printf(m, " FAULT_REG: 0x%08x\n", ee->fault_reg); } if (HAS_PPGTT(m->i915)) { err_printf(m, " GFX_MODE: 0x%08x\n", ee->vm_info.gfx_mode); - if (INTEL_GEN(m->i915) >= 8) { + if (GRAPHICS_VER(m->i915) >= 8) { int i; for (i = 0; i < 4; i++) err_printf(m, " PDP%d: 0x%016llx\n", @@ -706,25 +706,25 @@ static void err_print_gt(struct drm_i915_error_state_buf *m, for (i = 0; i < gt->nfence; i++) err_printf(m, " fence[%d] = %08llx\n", i, gt->fence[i]); - if (IS_GEN_RANGE(m->i915, 6, 11)) { + if (IS_GRAPHICS_VER(m->i915, 6, 11)) { err_printf(m, "ERROR: 0x%08x\n", gt->error); err_printf(m, "DONE_REG: 0x%08x\n", gt->done_reg); } - if (INTEL_GEN(m->i915) >= 8) + if (GRAPHICS_VER(m->i915) >= 8) err_printf(m, "FAULT_TLB_DATA: 0x%08x 0x%08x\n", gt->fault_data1, gt->fault_data0); - if (IS_GEN(m->i915, 7)) + if (GRAPHICS_VER(m->i915) == 7) err_printf(m, "ERR_INT: 0x%08x\n", gt->err_int); - if (IS_GEN_RANGE(m->i915, 8, 11)) + if (IS_GRAPHICS_VER(m->i915, 8, 11)) err_printf(m, "GTT_CACHE_EN: 0x%08x\n", gt->gtt_cache); - if (IS_GEN(m->i915, 12)) + if (GRAPHICS_VER(m->i915) == 12) err_printf(m, "AUX_ERR_DBG: 0x%08x\n", gt->aux_err); - if (INTEL_GEN(m->i915) >= 12) { + if (GRAPHICS_VER(m->i915) >= 12) { int i; for (i = 0; i < GEN12_SFC_DONE_MAX; i++) @@ -788,14 +788,14 @@ static void __err_print_to_sgl(struct drm_i915_error_state_buf *m, err_printf(m, "IOMMU enabled?: %d\n", error->iommu); - if (HAS_CSR(m->i915)) { - struct intel_csr *csr = &m->i915->csr; + if (HAS_DMC(m->i915)) { + struct intel_dmc *dmc = &m->i915->dmc; err_printf(m, "DMC loaded: %s\n", - yesno(csr->dmc_payload != NULL)); + yesno(intel_dmc_has_payload(m->i915) != 0)); err_printf(m, "DMC fw version: %d.%d\n", - CSR_VERSION_MAJOR(csr->version), - CSR_VERSION_MINOR(csr->version)); + DMC_VERSION_MAJOR(dmc->version), + DMC_VERSION_MINOR(dmc->version)); } err_printf(m, "RPM wakelock: %s\n", yesno(error->wakelock)); @@ -1092,12 +1092,12 @@ static void gt_record_fences(struct intel_gt_coredump *gt) struct intel_uncore *uncore = gt->_gt->uncore; int i; - if (INTEL_GEN(uncore->i915) >= 6) { + if (GRAPHICS_VER(uncore->i915) >= 6) { for (i = 0; i < ggtt->num_fences; i++) gt->fence[i] = intel_uncore_read64(uncore, FENCE_REG_GEN6_LO(i)); - } else if (INTEL_GEN(uncore->i915) >= 4) { + } else if (GRAPHICS_VER(uncore->i915) >= 4) { for (i = 0; i < ggtt->num_fences; i++) gt->fence[i] = intel_uncore_read64(uncore, @@ -1115,20 +1115,20 @@ static void engine_record_registers(struct intel_engine_coredump *ee) const struct intel_engine_cs *engine = ee->engine; struct drm_i915_private *i915 = engine->i915; - if (INTEL_GEN(i915) >= 6) { + if (GRAPHICS_VER(i915) >= 6) { ee->rc_psmi = ENGINE_READ(engine, RING_PSMI_CTL); - if (INTEL_GEN(i915) >= 12) + if (GRAPHICS_VER(i915) >= 12) ee->fault_reg = intel_uncore_read(engine->uncore, GEN12_RING_FAULT_REG); - else if (INTEL_GEN(i915) >= 8) + else if (GRAPHICS_VER(i915) >= 8) ee->fault_reg = intel_uncore_read(engine->uncore, GEN8_RING_FAULT_REG); else ee->fault_reg = GEN6_RING_FAULT_REG_READ(engine); } - if (INTEL_GEN(i915) >= 4) { + if (GRAPHICS_VER(i915) >= 4) { ee->esr = ENGINE_READ(engine, RING_ESR); ee->faddr = ENGINE_READ(engine, RING_DMA_FADD); ee->ipeir = ENGINE_READ(engine, RING_IPEIR); @@ -1136,7 +1136,7 @@ static void engine_record_registers(struct intel_engine_coredump *ee) ee->instps = ENGINE_READ(engine, RING_INSTPS); ee->bbaddr = ENGINE_READ(engine, RING_BBADDR); ee->ccid = ENGINE_READ(engine, CCID); - if (INTEL_GEN(i915) >= 8) { + if (GRAPHICS_VER(i915) >= 8) { ee->faddr |= (u64)ENGINE_READ(engine, RING_DMA_FADD_UDW) << 32; ee->bbaddr |= (u64)ENGINE_READ(engine, RING_BBADDR_UDW) << 32; } @@ -1155,13 +1155,13 @@ static void engine_record_registers(struct intel_engine_coredump *ee) ee->head = ENGINE_READ(engine, RING_HEAD); ee->tail = ENGINE_READ(engine, RING_TAIL); ee->ctl = ENGINE_READ(engine, RING_CTL); - if (INTEL_GEN(i915) > 2) + if (GRAPHICS_VER(i915) > 2) ee->mode = ENGINE_READ(engine, RING_MI_MODE); if (!HWS_NEEDS_PHYSICAL(i915)) { i915_reg_t mmio; - if (IS_GEN(i915, 7)) { + if (GRAPHICS_VER(i915) == 7) { switch (engine->id) { default: MISSING_CASE(engine->id); @@ -1179,7 +1179,7 @@ static void engine_record_registers(struct intel_engine_coredump *ee) mmio = VEBOX_HWS_PGA_GEN7; break; } - } else if (IS_GEN(engine->i915, 6)) { + } else if (GRAPHICS_VER(engine->i915) == 6) { mmio = RING_HWS_PGA_GEN6(engine->mmio_base); } else { /* XXX: gen8 returns to sanity */ @@ -1196,13 +1196,13 @@ static void engine_record_registers(struct intel_engine_coredump *ee) ee->vm_info.gfx_mode = ENGINE_READ(engine, RING_MODE_GEN7); - if (IS_GEN(i915, 6)) { + if (GRAPHICS_VER(i915) == 6) { ee->vm_info.pp_dir_base = ENGINE_READ(engine, RING_PP_DIR_BASE_READ); - } else if (IS_GEN(i915, 7)) { + } else if (GRAPHICS_VER(i915) == 7) { ee->vm_info.pp_dir_base = ENGINE_READ(engine, RING_PP_DIR_BASE); - } else if (INTEL_GEN(i915) >= 8) { + } else if (GRAPHICS_VER(i915) >= 8) { u32 base = engine->mmio_base; for (i = 0; i < 4; i++) { @@ -1534,52 +1534,52 @@ static void gt_record_regs(struct intel_gt_coredump *gt) gt->forcewake = intel_uncore_read_fw(uncore, FORCEWAKE_VLV); } - if (IS_GEN(i915, 7)) + if (GRAPHICS_VER(i915) == 7) gt->err_int = intel_uncore_read(uncore, GEN7_ERR_INT); - if (INTEL_GEN(i915) >= 12) { + if (GRAPHICS_VER(i915) >= 12) { gt->fault_data0 = intel_uncore_read(uncore, GEN12_FAULT_TLB_DATA0); gt->fault_data1 = intel_uncore_read(uncore, GEN12_FAULT_TLB_DATA1); - } else if (INTEL_GEN(i915) >= 8) { + } else if (GRAPHICS_VER(i915) >= 8) { gt->fault_data0 = intel_uncore_read(uncore, GEN8_FAULT_TLB_DATA0); gt->fault_data1 = intel_uncore_read(uncore, GEN8_FAULT_TLB_DATA1); } - if (IS_GEN(i915, 6)) { + if (GRAPHICS_VER(i915) == 6) { gt->forcewake = intel_uncore_read_fw(uncore, FORCEWAKE); gt->gab_ctl = intel_uncore_read(uncore, GAB_CTL); gt->gfx_mode = intel_uncore_read(uncore, GFX_MODE); } /* 2: Registers which belong to multiple generations */ - if (INTEL_GEN(i915) >= 7) + if (GRAPHICS_VER(i915) >= 7) gt->forcewake = intel_uncore_read_fw(uncore, FORCEWAKE_MT); - if (INTEL_GEN(i915) >= 6) { + if (GRAPHICS_VER(i915) >= 6) { gt->derrmr = intel_uncore_read(uncore, DERRMR); - if (INTEL_GEN(i915) < 12) { + if (GRAPHICS_VER(i915) < 12) { gt->error = intel_uncore_read(uncore, ERROR_GEN6); gt->done_reg = intel_uncore_read(uncore, DONE_REG); } } /* 3: Feature specific registers */ - if (IS_GEN_RANGE(i915, 6, 7)) { + if (IS_GRAPHICS_VER(i915, 6, 7)) { gt->gam_ecochk = intel_uncore_read(uncore, GAM_ECOCHK); gt->gac_eco = intel_uncore_read(uncore, GAC_ECO_BITS); } - if (IS_GEN_RANGE(i915, 8, 11)) + if (IS_GRAPHICS_VER(i915, 8, 11)) gt->gtt_cache = intel_uncore_read(uncore, HSW_GTT_CACHE_EN); - if (IS_GEN(i915, 12)) + if (GRAPHICS_VER(i915) == 12) gt->aux_err = intel_uncore_read(uncore, GEN12_AUX_ERR_DBG); - if (INTEL_GEN(i915) >= 12) { + if (GRAPHICS_VER(i915) >= 12) { for (i = 0; i < GEN12_SFC_DONE_MAX; i++) { gt->sfc_done[i] = intel_uncore_read(uncore, GEN12_SFC_DONE(i)); @@ -1589,7 +1589,7 @@ static void gt_record_regs(struct intel_gt_coredump *gt) } /* 4: Everything else */ - if (INTEL_GEN(i915) >= 11) { + if (GRAPHICS_VER(i915) >= 11) { gt->ier = intel_uncore_read(uncore, GEN8_DE_MISC_IER); gt->gtier[0] = intel_uncore_read(uncore, @@ -1608,7 +1608,7 @@ static void gt_record_regs(struct intel_gt_coredump *gt) intel_uncore_read(uncore, GEN11_GUNIT_CSME_INTR_ENABLE); gt->ngtier = 6; - } else if (INTEL_GEN(i915) >= 8) { + } else if (GRAPHICS_VER(i915) >= 8) { gt->ier = intel_uncore_read(uncore, GEN8_DE_MISC_IER); for (i = 0; i < 4; i++) gt->gtier[i] = @@ -1618,7 +1618,7 @@ static void gt_record_regs(struct intel_gt_coredump *gt) gt->ier = intel_uncore_read(uncore, DEIER); gt->gtier[0] = intel_uncore_read(uncore, GTIER); gt->ngtier = 1; - } else if (IS_GEN(i915, 2)) { + } else if (GRAPHICS_VER(i915) == 2) { gt->ier = intel_uncore_read16(uncore, GEN2_IER); } else if (!IS_VALLEYVIEW(i915)) { gt->ier = intel_uncore_read(uncore, GEN2_IER); @@ -1674,7 +1674,7 @@ static const char *error_msg(struct i915_gpu_coredump *error) len = scnprintf(error->error_msg, sizeof(error->error_msg), "GPU HANG: ecode %d:%x:%08x", - INTEL_GEN(error->i915), hung_classes, + GRAPHICS_VER(error->i915), hung_classes, generate_ecode(first)); if (first && first->context.pid) { /* Just show the first executing process, more is confusing */ diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c index 9ff511862848..a11bdb667241 100644 --- a/drivers/gpu/drm/i915/i915_irq.c +++ b/drivers/gpu/drm/i915/i915_irq.c @@ -2175,7 +2175,7 @@ static irqreturn_t ilk_irq_handler(int irq, void *arg) gt_iir = raw_reg_read(regs, GTIIR); if (gt_iir) { raw_reg_write(regs, GTIIR, gt_iir); - if (INTEL_GEN(i915) >= 6) + if (GRAPHICS_VER(i915) >= 6) gen6_gt_irq_handler(&i915->gt, gt_iir); else gen5_gt_irq_handler(&i915->gt, gt_iir); @@ -2192,7 +2192,7 @@ static irqreturn_t ilk_irq_handler(int irq, void *arg) ret = IRQ_HANDLED; } - if (INTEL_GEN(i915) >= 6) { + if (GRAPHICS_VER(i915) >= 6) { u32 pm_iir = raw_reg_read(regs, GEN6_PMIIR); if (pm_iir) { raw_reg_write(regs, GEN6_PMIIR, pm_iir); @@ -2425,6 +2425,17 @@ static u32 gen8_de_pipe_flip_done_mask(struct drm_i915_private *i915) return GEN8_PIPE_PRIMARY_FLIP_DONE; } +u32 gen8_de_pipe_underrun_mask(struct drm_i915_private *dev_priv) +{ + u32 mask = GEN8_PIPE_FIFO_UNDERRUN; + + if (DISPLAY_VER(dev_priv) >= 13) + mask |= XELPD_PIPE_SOFT_UNDERRUN | + XELPD_PIPE_HARD_UNDERRUN; + + return mask; +} + static irqreturn_t gen8_de_irq_handler(struct drm_i915_private *dev_priv, u32 master_ctl) { @@ -2536,7 +2547,7 @@ gen8_de_irq_handler(struct drm_i915_private *dev_priv, u32 master_ctl) if (iir & GEN8_PIPE_CDCLK_CRC_DONE) hsw_pipe_crc_irq_handler(dev_priv, pipe); - if (iir & GEN8_PIPE_FIFO_UNDERRUN) + if (iir & gen8_de_pipe_underrun_mask(dev_priv)) intel_cpu_fifo_underrun_irq_handler(dev_priv, pipe); fault_errors = iir & gen8_de_pipe_fault_mask(dev_priv); @@ -3028,7 +3039,7 @@ static void ilk_irq_reset(struct drm_i915_private *dev_priv) GEN3_IRQ_RESET(uncore, DE); dev_priv->irq_mask = ~0u; - if (IS_GEN(dev_priv, 7)) + if (GRAPHICS_VER(dev_priv) == 7) intel_uncore_write(uncore, GEN7_ERR_INT, 0xffffffff); if (IS_HASWELL(dev_priv)) { @@ -3173,7 +3184,8 @@ void gen8_irq_power_well_post_enable(struct drm_i915_private *dev_priv, u8 pipe_mask) { struct intel_uncore *uncore = &dev_priv->uncore; - u32 extra_ier = GEN8_PIPE_VBLANK | GEN8_PIPE_FIFO_UNDERRUN | + u32 extra_ier = GEN8_PIPE_VBLANK | + gen8_de_pipe_underrun_mask(dev_priv) | gen8_de_pipe_flip_done_mask(dev_priv); enum pipe pipe; @@ -3646,7 +3658,7 @@ static void ilk_irq_postinstall(struct drm_i915_private *dev_priv) struct intel_uncore *uncore = &dev_priv->uncore; u32 display_mask, extra_mask; - if (INTEL_GEN(dev_priv) >= 7) { + if (GRAPHICS_VER(dev_priv) >= 7) { display_mask = (DE_MASTER_IRQ_CONTROL | DE_GSE_IVB | DE_PCH_EVENT_IVB | DE_AUX_CHANNEL_A_IVB); extra_mask = (DE_PIPEC_VBLANK_IVB | DE_PIPEB_VBLANK_IVB | @@ -3757,7 +3769,8 @@ static void gen8_de_irq_postinstall(struct drm_i915_private *dev_priv) } de_pipe_enables = de_pipe_masked | - GEN8_PIPE_VBLANK | GEN8_PIPE_FIFO_UNDERRUN | + GEN8_PIPE_VBLANK | + gen8_de_pipe_underrun_mask(dev_priv) | gen8_de_pipe_flip_done_mask(dev_priv); de_port_enables = de_port_masked; @@ -4317,7 +4330,7 @@ void intel_irq_init(struct drm_i915_private *dev_priv) dev_priv->l3_parity.remap_info[i] = NULL; /* pre-gen11 the guc irqs bits are in the upper 16 bits of the pm reg */ - if (HAS_GT_UC(dev_priv) && INTEL_GEN(dev_priv) < 11) + if (HAS_GT_UC(dev_priv) && GRAPHICS_VER(dev_priv) < 11) dev_priv->gt.pm_guc_events = GUC_INTR_GUC2HOST << 16; if (!HAS_DISPLAY(dev_priv)) @@ -4388,18 +4401,18 @@ static irq_handler_t intel_irq_handler(struct drm_i915_private *dev_priv) return cherryview_irq_handler; else if (IS_VALLEYVIEW(dev_priv)) return valleyview_irq_handler; - else if (IS_GEN(dev_priv, 4)) + else if (GRAPHICS_VER(dev_priv) == 4) return i965_irq_handler; - else if (IS_GEN(dev_priv, 3)) + else if (GRAPHICS_VER(dev_priv) == 3) return i915_irq_handler; else return i8xx_irq_handler; } else { if (HAS_MASTER_UNIT_IRQ(dev_priv)) return dg1_irq_handler; - if (INTEL_GEN(dev_priv) >= 11) + if (GRAPHICS_VER(dev_priv) >= 11) return gen11_irq_handler; - else if (INTEL_GEN(dev_priv) >= 8) + else if (GRAPHICS_VER(dev_priv) >= 8) return gen8_irq_handler; else return ilk_irq_handler; @@ -4413,16 +4426,16 @@ static void intel_irq_reset(struct drm_i915_private *dev_priv) cherryview_irq_reset(dev_priv); else if (IS_VALLEYVIEW(dev_priv)) valleyview_irq_reset(dev_priv); - else if (IS_GEN(dev_priv, 4)) + else if (GRAPHICS_VER(dev_priv) == 4) i965_irq_reset(dev_priv); - else if (IS_GEN(dev_priv, 3)) + else if (GRAPHICS_VER(dev_priv) == 3) i915_irq_reset(dev_priv); else i8xx_irq_reset(dev_priv); } else { - if (INTEL_GEN(dev_priv) >= 11) + if (GRAPHICS_VER(dev_priv) >= 11) gen11_irq_reset(dev_priv); - else if (INTEL_GEN(dev_priv) >= 8) + else if (GRAPHICS_VER(dev_priv) >= 8) gen8_irq_reset(dev_priv); else ilk_irq_reset(dev_priv); @@ -4436,16 +4449,16 @@ static void intel_irq_postinstall(struct drm_i915_private *dev_priv) cherryview_irq_postinstall(dev_priv); else if (IS_VALLEYVIEW(dev_priv)) valleyview_irq_postinstall(dev_priv); - else if (IS_GEN(dev_priv, 4)) + else if (GRAPHICS_VER(dev_priv) == 4) i965_irq_postinstall(dev_priv); - else if (IS_GEN(dev_priv, 3)) + else if (GRAPHICS_VER(dev_priv) == 3) i915_irq_postinstall(dev_priv); else i8xx_irq_postinstall(dev_priv); } else { - if (INTEL_GEN(dev_priv) >= 11) + if (GRAPHICS_VER(dev_priv) >= 11) gen11_irq_postinstall(dev_priv); - else if (INTEL_GEN(dev_priv) >= 8) + else if (GRAPHICS_VER(dev_priv) >= 8) gen8_irq_postinstall(dev_priv); else ilk_irq_postinstall(dev_priv); diff --git a/drivers/gpu/drm/i915/i915_irq.h b/drivers/gpu/drm/i915/i915_irq.h index 25f25cd95818..db34d5dbe402 100644 --- a/drivers/gpu/drm/i915/i915_irq.h +++ b/drivers/gpu/drm/i915/i915_irq.h @@ -100,6 +100,7 @@ void gen8_irq_power_well_post_enable(struct drm_i915_private *dev_priv, u8 pipe_mask); void gen8_irq_power_well_pre_disable(struct drm_i915_private *dev_priv, u8 pipe_mask); +u32 gen8_de_pipe_underrun_mask(struct drm_i915_private *dev_priv); bool intel_crtc_get_vblank_timestamp(struct drm_crtc *crtc, int *max_error, ktime_t *vblank_time, bool in_vblank_irq); diff --git a/drivers/gpu/drm/i915/i915_pci.c b/drivers/gpu/drm/i915/i915_pci.c index 574881c0e339..83b500bb170c 100644 --- a/drivers/gpu/drm/i915/i915_pci.c +++ b/drivers/gpu/drm/i915/i915_pci.c @@ -643,7 +643,7 @@ static const struct intel_device_info chv_info = { GEN8_FEATURES, \ GEN(9), \ GEN9_DEFAULT_PAGE_SIZES, \ - .display.has_csr = 1, \ + .display.has_dmc = 1, \ .has_gt_uc = 1, \ .display.has_hdcp = 1, \ .display.has_ipc = 1, \ @@ -698,7 +698,7 @@ static const struct intel_device_info skl_gt4_info = { .display.has_psr = 1, \ .display.has_psr_hw_tracking = 1, \ .has_runtime_pm = 1, \ - .display.has_csr = 1, \ + .display.has_dmc = 1, \ .has_rc6 = 1, \ .has_rps = true, \ .display.has_dp_mst = 1, \ @@ -953,6 +953,7 @@ static const struct intel_device_info adl_p_info = { GEN12_FEATURES, XE_LPD_FEATURES, PLATFORM(INTEL_ALDERLAKE_P), + .has_cdclk_crawl = 1, .require_force_probe = 1, .display.has_modular_fia = 1, .platform_engine_mask = diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c index cb03e4152d2d..9f94914958c3 100644 --- a/drivers/gpu/drm/i915/i915_perf.c +++ b/drivers/gpu/drm/i915/i915_perf.c @@ -719,7 +719,7 @@ static int gen8_append_oa_reports(struct i915_perf_stream *stream, * it to userspace... */ reason = ((report32[0] >> OAREPORT_REASON_SHIFT) & - (IS_GEN(stream->perf->i915, 12) ? + (GRAPHICS_VER(stream->perf->i915) == 12 ? OAREPORT_REASON_MASK_EXTENDED : OAREPORT_REASON_MASK)); @@ -734,7 +734,7 @@ static int gen8_append_oa_reports(struct i915_perf_stream *stream, * understand that the ID has been squashed by the kernel. */ if (!(report32[0] & stream->perf->gen8_valid_ctx_bit) && - INTEL_GEN(stream->perf->i915) <= 11) + GRAPHICS_VER(stream->perf->i915) <= 11) ctx_id = report32[2] = INVALID_CTX_ID; /* @@ -801,7 +801,7 @@ static int gen8_append_oa_reports(struct i915_perf_stream *stream, if (start_offset != *offset) { i915_reg_t oaheadptr; - oaheadptr = IS_GEN(stream->perf->i915, 12) ? + oaheadptr = GRAPHICS_VER(stream->perf->i915) == 12 ? GEN12_OAG_OAHEADPTR : GEN8_OAHEADPTR; spin_lock_irqsave(&stream->oa_buffer.ptr_lock, flags); @@ -854,7 +854,7 @@ static int gen8_oa_read(struct i915_perf_stream *stream, if (drm_WARN_ON(&uncore->i915->drm, !stream->oa_buffer.vaddr)) return -EIO; - oastatus_reg = IS_GEN(stream->perf->i915, 12) ? + oastatus_reg = GRAPHICS_VER(stream->perf->i915) == 12 ? GEN12_OAG_OASTATUS : GEN8_OASTATUS; oastatus = intel_uncore_read(uncore, oastatus_reg); @@ -901,7 +901,7 @@ static int gen8_oa_read(struct i915_perf_stream *stream, intel_uncore_rmw(uncore, oastatus_reg, GEN8_OASTATUS_COUNTER_OVERFLOW | GEN8_OASTATUS_REPORT_LOST, - IS_GEN_RANGE(uncore->i915, 8, 11) ? + IS_GRAPHICS_VER(uncore->i915, 8, 11) ? (GEN8_OASTATUS_HEAD_POINTER_WRAP | GEN8_OASTATUS_TAIL_POINTER_WRAP) : 0); } @@ -1243,7 +1243,7 @@ static int oa_get_render_ctx_id(struct i915_perf_stream *stream) if (IS_ERR(ce)) return PTR_ERR(ce); - switch (INTEL_GEN(ce->engine->i915)) { + switch (GRAPHICS_VER(ce->engine->i915)) { case 7: { /* * On Haswell we don't do any post processing of the reports @@ -1297,7 +1297,7 @@ static int oa_get_render_ctx_id(struct i915_perf_stream *stream) } default: - MISSING_CASE(INTEL_GEN(ce->engine->i915)); + MISSING_CASE(GRAPHICS_VER(ce->engine->i915)); } ce->tag = stream->specific_ctx_id; @@ -1602,7 +1602,7 @@ static u32 *save_restore_register(struct i915_perf_stream *stream, u32 *cs, cmd = save ? MI_STORE_REGISTER_MEM : MI_LOAD_REGISTER_MEM; cmd |= MI_SRM_LRM_GLOBAL_GTT; - if (INTEL_GEN(stream->perf->i915) >= 8) + if (GRAPHICS_VER(stream->perf->i915) >= 8) cmd++; for (d = 0; d < dword_count; d++) { @@ -1731,7 +1731,7 @@ retry: *cs++ = i915_mmio_reg_offset(MI_PREDICATE_RESULT_1); /* Restart from the beginning if we had timestamps roll over. */ - *cs++ = (INTEL_GEN(i915) < 8 ? + *cs++ = (GRAPHICS_VER(i915) < 8 ? MI_BATCH_BUFFER_START : MI_BATCH_BUFFER_START_GEN8) | MI_BATCH_PREDICATE; @@ -1768,7 +1768,7 @@ retry: *cs++ = i915_mmio_reg_offset(MI_PREDICATE_RESULT_1); /* Predicate the jump. */ - *cs++ = (INTEL_GEN(i915) < 8 ? + *cs++ = (GRAPHICS_VER(i915) < 8 ? MI_BATCH_BUFFER_START : MI_BATCH_BUFFER_START_GEN8) | MI_BATCH_PREDICATE; @@ -1892,7 +1892,7 @@ retry: oa_config->flex_regs_len); /* Jump into the active wait. */ - *cs++ = (INTEL_GEN(stream->perf->i915) < 8 ? + *cs++ = (GRAPHICS_VER(stream->perf->i915) < 8 ? MI_BATCH_BUFFER_START : MI_BATCH_BUFFER_START_GEN8); *cs++ = i915_ggtt_offset(stream->noa_wait); @@ -2492,7 +2492,7 @@ gen8_enable_metric_set(struct i915_perf_stream *stream, * be read back from automatically triggered reports, as part of the * RPT_ID field. */ - if (IS_GEN_RANGE(stream->perf->i915, 9, 11)) { + if (IS_GRAPHICS_VER(stream->perf->i915, 9, 11)) { intel_uncore_write(uncore, GEN8_OA_DEBUG, _MASKED_BIT_ENABLE(GEN9_OA_DEBUG_DISABLE_CLK_RATIO_REPORTS | GEN9_OA_DEBUG_INCLUDE_CLK_RATIO)); @@ -2797,7 +2797,7 @@ get_default_sseu_config(struct intel_sseu *out_sseu, *out_sseu = intel_sseu_from_device_info(devinfo_sseu); - if (IS_GEN(engine->i915, 11)) { + if (GRAPHICS_VER(engine->i915) == 11) { /* * We only need subslice count so it doesn't matter which ones * we select - just turn off low bits in the amount of half of @@ -2864,7 +2864,7 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream, } if (!(props->sample_flags & SAMPLE_OA_REPORT) && - (INTEL_GEN(perf->i915) < 12 || !stream->ctx)) { + (GRAPHICS_VER(perf->i915) < 12 || !stream->ctx)) { DRM_DEBUG("Only OA report sampling supported\n"); return -EINVAL; } @@ -3006,7 +3006,7 @@ void i915_oa_init_reg_state(const struct intel_context *ce, /* perf.exclusive_stream serialised by lrc_configure_all_contexts() */ stream = READ_ONCE(engine->i915->perf.exclusive_stream); - if (stream && INTEL_GEN(stream->perf->i915) < 12) + if (stream && GRAPHICS_VER(stream->perf->i915) < 12) gen8_update_reg_state_unlocked(ce, stream); } @@ -3443,7 +3443,7 @@ i915_perf_open_ioctl_locked(struct i915_perf *perf, */ if (IS_HASWELL(perf->i915) && specific_ctx) privileged_op = false; - else if (IS_GEN(perf->i915, 12) && specific_ctx && + else if (GRAPHICS_VER(perf->i915) == 12 && specific_ctx && (props->sample_flags & SAMPLE_OA_REPORT) == 0) privileged_op = false; @@ -4119,7 +4119,7 @@ int i915_perf_add_config_ioctl(struct drm_device *dev, void *data, } oa_config->b_counter_regs = regs; - if (INTEL_GEN(perf->i915) < 8) { + if (GRAPHICS_VER(perf->i915) < 8) { if (args->n_flex_regs != 0) { err = -EINVAL; goto reg_err; @@ -4365,7 +4365,7 @@ void i915_perf_init(struct drm_i915_private *i915) */ perf->ops.read = gen8_oa_read; - if (IS_GEN_RANGE(i915, 8, 9)) { + if (IS_GRAPHICS_VER(i915, 8, 9)) { perf->ops.is_valid_b_counter_reg = gen7_is_valid_b_counter_addr; perf->ops.is_valid_mux_reg = @@ -4384,7 +4384,7 @@ void i915_perf_init(struct drm_i915_private *i915) perf->ops.disable_metric_set = gen8_disable_metric_set; perf->ops.oa_hw_tail_read = gen8_oa_hw_tail_read; - if (IS_GEN(i915, 8)) { + if (GRAPHICS_VER(i915) == 8) { perf->ctx_oactxctrl_offset = 0x120; perf->ctx_flexeu0_offset = 0x2ce; @@ -4395,7 +4395,7 @@ void i915_perf_init(struct drm_i915_private *i915) perf->gen8_valid_ctx_bit = BIT(16); } - } else if (IS_GEN_RANGE(i915, 10, 11)) { + } else if (IS_GRAPHICS_VER(i915, 10, 11)) { perf->ops.is_valid_b_counter_reg = gen7_is_valid_b_counter_addr; perf->ops.is_valid_mux_reg = @@ -4409,7 +4409,7 @@ void i915_perf_init(struct drm_i915_private *i915) perf->ops.disable_metric_set = gen10_disable_metric_set; perf->ops.oa_hw_tail_read = gen8_oa_hw_tail_read; - if (IS_GEN(i915, 10)) { + if (GRAPHICS_VER(i915) == 10) { perf->ctx_oactxctrl_offset = 0x128; perf->ctx_flexeu0_offset = 0x3de; } else { @@ -4417,7 +4417,7 @@ void i915_perf_init(struct drm_i915_private *i915) perf->ctx_flexeu0_offset = 0x78e; } perf->gen8_valid_ctx_bit = BIT(16); - } else if (IS_GEN(i915, 12)) { + } else if (GRAPHICS_VER(i915) == 12) { perf->ops.is_valid_b_counter_reg = gen12_is_valid_b_counter_addr; perf->ops.is_valid_mux_reg = diff --git a/drivers/gpu/drm/i915/i915_pmu.c b/drivers/gpu/drm/i915/i915_pmu.c index a75cd1db320b..22c4d4178766 100644 --- a/drivers/gpu/drm/i915/i915_pmu.c +++ b/drivers/gpu/drm/i915/i915_pmu.c @@ -287,7 +287,7 @@ static bool exclusive_mmio_access(const struct drm_i915_private *i915) * risk a machine hang. For a fun history lesson dig out the old * userspace intel_gpu_top and run it on Ivybridge or Haswell! */ - return IS_GEN(i915, 7); + return GRAPHICS_VER(i915) == 7; } static void engine_sample(struct intel_engine_cs *engine, unsigned int period_ns) @@ -463,7 +463,7 @@ engine_event_status(struct intel_engine_cs *engine, case I915_SAMPLE_WAIT: break; case I915_SAMPLE_SEMA: - if (INTEL_GEN(engine->i915) < 6) + if (GRAPHICS_VER(engine->i915) < 6) return -ENODEV; break; default: @@ -485,7 +485,7 @@ config_status(struct drm_i915_private *i915, u64 config) return -ENODEV; fallthrough; case I915_PMU_REQUESTED_FREQUENCY: - if (INTEL_GEN(i915) < 6) + if (GRAPHICS_VER(i915) < 6) return -ENODEV; break; case I915_PMU_INTERRUPTS: @@ -1147,7 +1147,7 @@ void i915_pmu_register(struct drm_i915_private *i915) int ret = -ENOMEM; - if (INTEL_GEN(i915) <= 2) { + if (GRAPHICS_VER(i915) <= 2) { drm_info(&i915->drm, "PMU not supported for this GPU."); return; } diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index c294e3f93bed..e915ec034c98 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -2941,6 +2941,15 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg) #define MBUS_BBOX_CTL_S1 _MMIO(0x45040) #define MBUS_BBOX_CTL_S2 _MMIO(0x45044) +#define MBUS_CTL _MMIO(0x4438C) +#define MBUS_JOIN REG_BIT(31) +#define MBUS_HASHING_MODE_MASK REG_BIT(30) +#define MBUS_HASHING_MODE_2x2 REG_FIELD_PREP(MBUS_HASHING_MODE_MASK, 0) +#define MBUS_HASHING_MODE_1x4 REG_FIELD_PREP(MBUS_HASHING_MODE_MASK, 1) +#define MBUS_JOIN_PIPE_SELECT_MASK REG_GENMASK(28, 26) +#define MBUS_JOIN_PIPE_SELECT(pipe) REG_FIELD_PREP(MBUS_JOIN_PIPE_SELECT_MASK, pipe) +#define MBUS_JOIN_PIPE_SELECT_NONE MBUS_JOIN_PIPE_SELECT(7) + #define HDPORT_STATE _MMIO(0x45050) #define HDPORT_DPLL_USED_MASK REG_GENMASK(15, 12) #define HDPORT_DDI_USED(phy) REG_BIT(2 * (phy) + 1) @@ -4382,6 +4391,8 @@ enum { #define VRR_CTL_PIPELINE_FULL_MASK REG_GENMASK(10, 3) #define VRR_CTL_PIPELINE_FULL(x) REG_FIELD_PREP(VRR_CTL_PIPELINE_FULL_MASK, (x)) #define VRR_CTL_PIPELINE_FULL_OVERRIDE REG_BIT(0) +#define XELPD_VRR_CTL_VRR_GUARDBAND_MASK REG_GENMASK(15, 0) +#define XELPD_VRR_CTL_VRR_GUARDBAND(x) REG_FIELD_PREP(XELPD_VRR_CTL_VRR_GUARDBAND_MASK, (x)) #define _TRANS_VRR_VMAX_A 0x60424 #define _TRANS_VRR_VMAX_B 0x61424 @@ -6141,6 +6152,10 @@ enum { #define _PIPEBGCMAX 0x71010 #define PIPEGCMAX(pipe, i) _MMIO_PIPE2(pipe, _PIPEAGCMAX + (i) * 4) +#define _PIPE_ARB_CTL_A 0x70028 /* icl+ */ +#define PIPE_ARB_CTL(pipe) _MMIO_PIPE2(pipe, _PIPE_ARB_CTL_A) +#define PIPE_ARB_USE_PROG_SLOTS REG_BIT(13) + #define _PIPE_MISC_A 0x70030 #define _PIPE_MISC_B 0x71030 #define PIPEMISC_YUV420_ENABLE (1 << 27) /* glk+ */ @@ -6158,12 +6173,26 @@ enum { #define PIPEMISC_DITHER_TYPE_SP (0 << 2) #define PIPEMISC(pipe) _MMIO_PIPE2(pipe, _PIPE_MISC_A) +#define _PIPE_MISC2_A 0x7002C +#define _PIPE_MISC2_B 0x7102C +#define PIPE_MISC2_BUBBLE_COUNTER_SCALER_EN (0x50 << 24) +#define PIPE_MISC2_BUBBLE_COUNTER_SCALER_DIS (0x14 << 24) +#define PIPE_MISC2_UNDERRUN_BUBBLE_COUNTER_MASK (0xff << 24) +#define PIPE_MISC2(pipe) _MMIO_PIPE2(pipe, _PIPE_MISC2_A) + /* Skylake+ pipe bottom (background) color */ #define _SKL_BOTTOM_COLOR_A 0x70034 #define SKL_BOTTOM_COLOR_GAMMA_ENABLE (1 << 31) #define SKL_BOTTOM_COLOR_CSC_ENABLE (1 << 30) #define SKL_BOTTOM_COLOR(pipe) _MMIO_PIPE2(pipe, _SKL_BOTTOM_COLOR_A) +#define _ICL_PIPE_A_STATUS 0x70058 +#define ICL_PIPESTATUS(pipe) _MMIO_PIPE2(pipe, _ICL_PIPE_A_STATUS) +#define PIPE_STATUS_UNDERRUN REG_BIT(31) +#define PIPE_STATUS_SOFT_UNDERRUN_XELPD REG_BIT(28) +#define PIPE_STATUS_HARD_UNDERRUN_XELPD REG_BIT(27) +#define PIPE_STATUS_PORT_UNDERRUN_XELPD REG_BIT(26) + #define VLV_DPFLIPSTAT _MMIO(VLV_DISPLAY_BASE + 0x70028) #define PIPEB_LINE_COMPARE_INT_EN (1 << 29) #define PIPEB_HLINE_INT_EN (1 << 28) @@ -6432,16 +6461,28 @@ enum { /* Watermark register definitions for SKL */ #define _CUR_WM_A_0 0x70140 #define _CUR_WM_B_0 0x71140 +#define _CUR_WM_SAGV_A 0x70158 +#define _CUR_WM_SAGV_B 0x71158 +#define _CUR_WM_SAGV_TRANS_A 0x7015C +#define _CUR_WM_SAGV_TRANS_B 0x7115C +#define _CUR_WM_TRANS_A 0x70168 +#define _CUR_WM_TRANS_B 0x71168 #define _PLANE_WM_1_A_0 0x70240 #define _PLANE_WM_1_B_0 0x71240 #define _PLANE_WM_2_A_0 0x70340 #define _PLANE_WM_2_B_0 0x71340 -#define _PLANE_WM_TRANS_1_A_0 0x70268 -#define _PLANE_WM_TRANS_1_B_0 0x71268 -#define _PLANE_WM_TRANS_2_A_0 0x70368 -#define _PLANE_WM_TRANS_2_B_0 0x71368 -#define _CUR_WM_TRANS_A_0 0x70168 -#define _CUR_WM_TRANS_B_0 0x71168 +#define _PLANE_WM_SAGV_1_A 0x70258 +#define _PLANE_WM_SAGV_1_B 0x71258 +#define _PLANE_WM_SAGV_2_A 0x70358 +#define _PLANE_WM_SAGV_2_B 0x71358 +#define _PLANE_WM_SAGV_TRANS_1_A 0x7025C +#define _PLANE_WM_SAGV_TRANS_1_B 0x7125C +#define _PLANE_WM_SAGV_TRANS_2_A 0x7035C +#define _PLANE_WM_SAGV_TRANS_2_B 0x7135C +#define _PLANE_WM_TRANS_1_A 0x70268 +#define _PLANE_WM_TRANS_1_B 0x71268 +#define _PLANE_WM_TRANS_2_A 0x70368 +#define _PLANE_WM_TRANS_2_B 0x71368 #define PLANE_WM_EN (1 << 31) #define PLANE_WM_IGNORE_LINES (1 << 30) #define PLANE_WM_LINES_MASK REG_GENMASK(26, 14) @@ -6449,19 +6490,32 @@ enum { #define _CUR_WM_0(pipe) _PIPE(pipe, _CUR_WM_A_0, _CUR_WM_B_0) #define CUR_WM(pipe, level) _MMIO(_CUR_WM_0(pipe) + ((4) * (level))) -#define CUR_WM_TRANS(pipe) _MMIO_PIPE(pipe, _CUR_WM_TRANS_A_0, _CUR_WM_TRANS_B_0) - +#define CUR_WM_SAGV(pipe) _MMIO_PIPE(pipe, _CUR_WM_SAGV_A, _CUR_WM_SAGV_B) +#define CUR_WM_SAGV_TRANS(pipe) _MMIO_PIPE(pipe, _CUR_WM_SAGV_TRANS_A, _CUR_WM_SAGV_TRANS_B) +#define CUR_WM_TRANS(pipe) _MMIO_PIPE(pipe, _CUR_WM_TRANS_A, _CUR_WM_TRANS_B) #define _PLANE_WM_1(pipe) _PIPE(pipe, _PLANE_WM_1_A_0, _PLANE_WM_1_B_0) #define _PLANE_WM_2(pipe) _PIPE(pipe, _PLANE_WM_2_A_0, _PLANE_WM_2_B_0) -#define _PLANE_WM_BASE(pipe, plane) \ - _PLANE(plane, _PLANE_WM_1(pipe), _PLANE_WM_2(pipe)) -#define PLANE_WM(pipe, plane, level) \ - _MMIO(_PLANE_WM_BASE(pipe, plane) + ((4) * (level))) -#define _PLANE_WM_TRANS_1(pipe) \ - _PIPE(pipe, _PLANE_WM_TRANS_1_A_0, _PLANE_WM_TRANS_1_B_0) -#define _PLANE_WM_TRANS_2(pipe) \ - _PIPE(pipe, _PLANE_WM_TRANS_2_A_0, _PLANE_WM_TRANS_2_B_0) -#define PLANE_WM_TRANS(pipe, plane) \ +#define _PLANE_WM_BASE(pipe, plane) \ + _PLANE(plane, _PLANE_WM_1(pipe), _PLANE_WM_2(pipe)) +#define PLANE_WM(pipe, plane, level) \ + _MMIO(_PLANE_WM_BASE(pipe, plane) + ((4) * (level))) +#define _PLANE_WM_SAGV_1(pipe) \ + _PIPE(pipe, _PLANE_WM_SAGV_1_A, _PLANE_WM_SAGV_1_B) +#define _PLANE_WM_SAGV_2(pipe) \ + _PIPE(pipe, _PLANE_WM_SAGV_2_A, _PLANE_WM_SAGV_2_B) +#define PLANE_WM_SAGV(pipe, plane) \ + _MMIO(_PLANE(plane, _PLANE_WM_SAGV_1(pipe), _PLANE_WM_SAGV_2(pipe))) +#define _PLANE_WM_SAGV_TRANS_1(pipe) \ + _PIPE(pipe, _PLANE_WM_SAGV_TRANS_1_A, _PLANE_WM_SAGV_TRANS_1_B) +#define _PLANE_WM_SAGV_TRANS_2(pipe) \ + _PIPE(pipe, _PLANE_WM_SAGV_TRANS_2_A, _PLANE_WM_SAGV_TRANS_2_B) +#define PLANE_WM_SAGV_TRANS(pipe, plane) \ + _MMIO(_PLANE(plane, _PLANE_WM_SAGV_TRANS_1(pipe), _PLANE_WM_SAGV_TRANS_2(pipe))) +#define _PLANE_WM_TRANS_1(pipe) \ + _PIPE(pipe, _PLANE_WM_TRANS_1_A, _PLANE_WM_TRANS_1_B) +#define _PLANE_WM_TRANS_2(pipe) \ + _PIPE(pipe, _PLANE_WM_TRANS_2_A, _PLANE_WM_TRANS_2_B) +#define PLANE_WM_TRANS(pipe, plane) \ _MMIO(_PLANE(plane, _PLANE_WM_TRANS_1(pipe), _PLANE_WM_TRANS_2(pipe))) /* define the Watermark register on Ironlake */ @@ -6566,6 +6620,8 @@ enum { #define MCURSOR_MODE_128_ARGB_AX ((1 << 5) | MCURSOR_MODE_128_32B_AX) #define MCURSOR_MODE_256_ARGB_AX ((1 << 5) | MCURSOR_MODE_256_32B_AX) #define MCURSOR_MODE_64_ARGB_AX ((1 << 5) | MCURSOR_MODE_64_32B_AX) +#define MCURSOR_ARB_SLOTS_MASK REG_GENMASK(30, 28) /* icl+ */ +#define MCURSOR_ARB_SLOTS(x) REG_FIELD_PREP(MCURSOR_ARB_SLOTS_MASK, (x)) /* icl+ */ #define MCURSOR_PIPE_SELECT_MASK (0x3 << 28) #define MCURSOR_PIPE_SELECT_SHIFT 28 #define MCURSOR_PIPE_SELECT(pipe) ((pipe) << 28) @@ -7017,6 +7073,8 @@ enum { #define _PLANE_CTL_2_A 0x70280 #define _PLANE_CTL_3_A 0x70380 #define PLANE_CTL_ENABLE (1 << 31) +#define PLANE_CTL_ARB_SLOTS_MASK REG_GENMASK(30, 28) /* icl+ */ +#define PLANE_CTL_ARB_SLOTS(x) REG_FIELD_PREP(PLANE_CTL_ARB_SLOTS_MASK, (x)) /* icl+ */ #define PLANE_CTL_PIPE_GAMMA_ENABLE (1 << 30) /* Pre-GLK */ #define PLANE_CTL_YUV_RANGE_CORRECTION_DISABLE (1 << 28) /* @@ -7280,7 +7338,7 @@ enum { #define _PLANE_BUF_CFG_1_B 0x7127c #define _PLANE_BUF_CFG_2_B 0x7137c -#define DDB_ENTRY_MASK 0x7FF /* skl+: 10 bits, icl+ 11 bits */ +#define DDB_ENTRY_MASK 0xFFF /* skl+: 10 bits, icl+ 11 bits, adlp+ 12 bits */ #define DDB_ENTRY_END_SHIFT 16 #define _PLANE_BUF_CFG_1(pipe) \ _PIPE(pipe, _PLANE_BUF_CFG_1_A, _PLANE_BUF_CFG_1_B) @@ -7692,20 +7750,20 @@ enum { #define GAMMA_MODE_MODE_SPLIT (3 << 0) /* ivb-bdw */ #define GAMMA_MODE_MODE_12BIT_MULTI_SEGMENTED (3 << 0) /* icl + */ -/* DMC/CSR */ -#define CSR_PROGRAM(i) _MMIO(0x80000 + (i) * 4) -#define CSR_SSP_BASE_ADDR_GEN9 0x00002FC0 -#define CSR_HTP_ADDR_SKL 0x00500034 -#define CSR_SSP_BASE _MMIO(0x8F074) -#define CSR_HTP_SKL _MMIO(0x8F004) -#define CSR_LAST_WRITE _MMIO(0x8F034) -#define CSR_LAST_WRITE_VALUE 0xc003b400 -/* MMIO address range for CSR program (0x80000 - 0x82FFF) */ -#define CSR_MMIO_START_RANGE 0x80000 -#define CSR_MMIO_END_RANGE 0x8FFFF -#define SKL_CSR_DC3_DC5_COUNT _MMIO(0x80030) -#define SKL_CSR_DC5_DC6_COUNT _MMIO(0x8002C) -#define BXT_CSR_DC3_DC5_COUNT _MMIO(0x80038) +/* DMC */ +#define DMC_PROGRAM(i) _MMIO(0x80000 + (i) * 4) +#define DMC_SSP_BASE_ADDR_GEN9 0x00002FC0 +#define DMC_HTP_ADDR_SKL 0x00500034 +#define DMC_SSP_BASE _MMIO(0x8F074) +#define DMC_HTP_SKL _MMIO(0x8F004) +#define DMC_LAST_WRITE _MMIO(0x8F034) +#define DMC_LAST_WRITE_VALUE 0xc003b400 +/* MMIO address range for DMC program (0x80000 - 0x82FFF) */ +#define DMC_MMIO_START_RANGE 0x80000 +#define DMC_MMIO_END_RANGE 0x8FFFF +#define SKL_DMC_DC3_DC5_COUNT _MMIO(0x80030) +#define SKL_DMC_DC5_DC6_COUNT _MMIO(0x8002C) +#define BXT_DMC_DC3_DC5_COUNT _MMIO(0x80038) #define TGL_DMC_DEBUG_DC5_COUNT _MMIO(0x101084) #define TGL_DMC_DEBUG_DC6_COUNT _MMIO(0x101088) #define DG1_DMC_DEBUG_DC5_COUNT _MMIO(0x134154) @@ -7820,6 +7878,8 @@ enum { #define GEN8_PIPE_FIFO_UNDERRUN (1 << 31) #define GEN8_PIPE_CDCLK_CRC_ERROR (1 << 29) #define GEN8_PIPE_CDCLK_CRC_DONE (1 << 28) +#define XELPD_PIPE_SOFT_UNDERRUN (1 << 22) +#define XELPD_PIPE_HARD_UNDERRUN (1 << 21) #define GEN8_PIPE_CURSOR_FAULT (1 << 10) #define GEN8_PIPE_SPRITE_FAULT (1 << 9) #define GEN8_PIPE_PRIMARY_FAULT (1 << 8) @@ -8115,13 +8175,29 @@ enum { #define DISP_DATA_PARTITION_5_6 (1 << 6) #define DISP_IPC_ENABLE (1 << 3) -#define _DBUF_CTL_S1 0x45008 -#define _DBUF_CTL_S2 0x44FE8 -#define DBUF_CTL_S(slice) _MMIO(_PICK_EVEN(slice, _DBUF_CTL_S1, _DBUF_CTL_S2)) +/* + * The below are numbered starting from "S1" on gen11/gen12, but starting + * with gen13 display, the bspec switches to a 0-based numbering scheme + * (although the addresses stay the same so new S0 = old S1, new S1 = old S2). + * We'll just use the 0-based numbering here for all platforms since it's the + * way things will be named by the hardware team going forward, plus it's more + * consistent with how most of the rest of our registers are named. + */ +#define _DBUF_CTL_S0 0x45008 +#define _DBUF_CTL_S1 0x44FE8 +#define _DBUF_CTL_S2 0x44300 +#define _DBUF_CTL_S3 0x44304 +#define DBUF_CTL_S(slice) _MMIO(_PICK(slice, \ + _DBUF_CTL_S0, \ + _DBUF_CTL_S1, \ + _DBUF_CTL_S2, \ + _DBUF_CTL_S3)) #define DBUF_POWER_REQUEST REG_BIT(31) #define DBUF_POWER_STATE REG_BIT(30) #define DBUF_TRACKER_STATE_SERVICE_MASK REG_GENMASK(23, 19) #define DBUF_TRACKER_STATE_SERVICE(x) REG_FIELD_PREP(DBUF_TRACKER_STATE_SERVICE_MASK, x) +#define DBUF_MIN_TRACKER_STATE_SERVICE_MASK REG_GENMASK(18, 16) /* ADL-P+ */ +#define DBUF_MIN_TRACKER_STATE_SERVICE(x) REG_FIELD_PREP(DBUF_MIN_TRACKER_STATE_SERVICE_MASK, x) /* ADL-P+ */ #define GEN7_MSG_CTL _MMIO(0x45010) #define WAIT_FOR_PCH_RESET_ACK (1 << 1) @@ -8306,6 +8382,7 @@ enum { #define _PIPEC_CHICKEN 0x72038 #define PIPE_CHICKEN(pipe) _MMIO_PIPE(pipe, _PIPEA_CHICKEN,\ _PIPEB_CHICKEN) +#define UNDERRUN_RECOVERY_DISABLE REG_BIT(30) #define PIXEL_ROUNDING_TRUNC_FB_PASSTHRU (1 << 15) #define PER_PIXEL_ALPHA_BYPASS_EN (1 << 7) @@ -9831,7 +9908,7 @@ enum skl_power_gate { #define TRANS_HDCP_CONF(trans) _MMIO_TRANS(trans, _TRANSA_HDCP_CONF, \ _TRANSB_HDCP_CONF) #define HDCP_CONF(dev_priv, trans, port) \ - (INTEL_GEN(dev_priv) >= 12 ? \ + (GRAPHICS_VER(dev_priv) >= 12 ? \ TRANS_HDCP_CONF(trans) : \ PORT_HDCP_CONF(port)) @@ -9844,7 +9921,7 @@ enum skl_power_gate { _TRANSA_HDCP_ANINIT, \ _TRANSB_HDCP_ANINIT) #define HDCP_ANINIT(dev_priv, trans, port) \ - (INTEL_GEN(dev_priv) >= 12 ? \ + (GRAPHICS_VER(dev_priv) >= 12 ? \ TRANS_HDCP_ANINIT(trans) : \ PORT_HDCP_ANINIT(port)) @@ -9854,7 +9931,7 @@ enum skl_power_gate { #define TRANS_HDCP_ANLO(trans) _MMIO_TRANS(trans, _TRANSA_HDCP_ANLO, \ _TRANSB_HDCP_ANLO) #define HDCP_ANLO(dev_priv, trans, port) \ - (INTEL_GEN(dev_priv) >= 12 ? \ + (GRAPHICS_VER(dev_priv) >= 12 ? \ TRANS_HDCP_ANLO(trans) : \ PORT_HDCP_ANLO(port)) @@ -9864,7 +9941,7 @@ enum skl_power_gate { #define TRANS_HDCP_ANHI(trans) _MMIO_TRANS(trans, _TRANSA_HDCP_ANHI, \ _TRANSB_HDCP_ANHI) #define HDCP_ANHI(dev_priv, trans, port) \ - (INTEL_GEN(dev_priv) >= 12 ? \ + (GRAPHICS_VER(dev_priv) >= 12 ? \ TRANS_HDCP_ANHI(trans) : \ PORT_HDCP_ANHI(port)) @@ -9875,7 +9952,7 @@ enum skl_power_gate { _TRANSA_HDCP_BKSVLO, \ _TRANSB_HDCP_BKSVLO) #define HDCP_BKSVLO(dev_priv, trans, port) \ - (INTEL_GEN(dev_priv) >= 12 ? \ + (GRAPHICS_VER(dev_priv) >= 12 ? \ TRANS_HDCP_BKSVLO(trans) : \ PORT_HDCP_BKSVLO(port)) @@ -9886,7 +9963,7 @@ enum skl_power_gate { _TRANSA_HDCP_BKSVHI, \ _TRANSB_HDCP_BKSVHI) #define HDCP_BKSVHI(dev_priv, trans, port) \ - (INTEL_GEN(dev_priv) >= 12 ? \ + (GRAPHICS_VER(dev_priv) >= 12 ? \ TRANS_HDCP_BKSVHI(trans) : \ PORT_HDCP_BKSVHI(port)) @@ -9897,7 +9974,7 @@ enum skl_power_gate { _TRANSA_HDCP_RPRIME, \ _TRANSB_HDCP_RPRIME) #define HDCP_RPRIME(dev_priv, trans, port) \ - (INTEL_GEN(dev_priv) >= 12 ? \ + (GRAPHICS_VER(dev_priv) >= 12 ? \ TRANS_HDCP_RPRIME(trans) : \ PORT_HDCP_RPRIME(port)) @@ -9908,7 +9985,7 @@ enum skl_power_gate { _TRANSA_HDCP_STATUS, \ _TRANSB_HDCP_STATUS) #define HDCP_STATUS(dev_priv, trans, port) \ - (INTEL_GEN(dev_priv) >= 12 ? \ + (GRAPHICS_VER(dev_priv) >= 12 ? \ TRANS_HDCP_STATUS(trans) : \ PORT_HDCP_STATUS(port)) @@ -9949,7 +10026,7 @@ enum skl_power_gate { #define AUTH_FORCE_CLR_INPUTCTR BIT(19) #define AUTH_CLR_KEYS BIT(18) #define HDCP2_AUTH(dev_priv, trans, port) \ - (INTEL_GEN(dev_priv) >= 12 ? \ + (GRAPHICS_VER(dev_priv) >= 12 ? \ TRANS_HDCP2_AUTH(trans) : \ PORT_HDCP2_AUTH(port)) @@ -9960,7 +10037,7 @@ enum skl_power_gate { _TRANSB_HDCP2_CTL) #define CTL_LINK_ENCRYPTION_REQ BIT(31) #define HDCP2_CTL(dev_priv, trans, port) \ - (INTEL_GEN(dev_priv) >= 12 ? \ + (GRAPHICS_VER(dev_priv) >= 12 ? \ TRANS_HDCP2_CTL(trans) : \ PORT_HDCP2_CTL(port)) @@ -9974,7 +10051,7 @@ enum skl_power_gate { #define LINK_AUTH_STATUS BIT(21) #define LINK_ENCRYPTION_STATUS BIT(20) #define HDCP2_STATUS(dev_priv, trans, port) \ - (INTEL_GEN(dev_priv) >= 12 ? \ + (GRAPHICS_VER(dev_priv) >= 12 ? \ TRANS_HDCP2_STATUS(trans) : \ PORT_HDCP2_STATUS(port)) @@ -9996,7 +10073,7 @@ enum skl_power_gate { #define STREAM_ENCRYPTION_STATUS BIT(31) #define STREAM_TYPE_STATUS BIT(30) #define HDCP2_STREAM_STATUS(dev_priv, trans, port) \ - (INTEL_GEN(dev_priv) >= 12 ? \ + (GRAPHICS_VER(dev_priv) >= 12 ? \ TRANS_HDCP2_STREAM_STATUS(trans) : \ PIPE_HDCP2_STREAM_STATUS(pipe)) @@ -10012,7 +10089,7 @@ enum skl_power_gate { _TRANSB_HDCP2_AUTH_STREAM) #define AUTH_STREAM_TYPE BIT(31) #define HDCP2_AUTH_STREAM(dev_priv, trans, port) \ - (INTEL_GEN(dev_priv) >= 12 ? \ + (GRAPHICS_VER(dev_priv) >= 12 ? \ TRANS_HDCP2_AUTH_STREAM(trans) : \ PORT_HDCP2_AUTH_STREAM(port)) @@ -10128,8 +10205,10 @@ enum skl_power_gate { #define DDI_BUF_CTL_ENABLE (1 << 31) #define DDI_BUF_TRANS_SELECT(n) ((n) << 24) #define DDI_BUF_EMP_MASK (0xf << 24) +#define DDI_BUF_PHY_LINK_RATE(r) ((r) << 20) #define DDI_BUF_PORT_REVERSAL (1 << 16) #define DDI_BUF_IS_IDLE (1 << 7) +#define DDI_BUF_CTL_TC_PHY_OWNERSHIP REG_BIT(6) #define DDI_A_4_LANES (1 << 4) #define DDI_PORT_WIDTH(width) (((width) - 1) << 1) #define DDI_PORT_WIDTH_MASK (7 << 1) @@ -10492,6 +10571,14 @@ enum skl_power_gate { #define DG1_DPLL_ENABLE(pll) _MMIO_PLL3(pll, DPLL0_ENABLE, DPLL1_ENABLE, \ _MG_PLL1_ENABLE, _MG_PLL2_ENABLE) +/* ADL-P Type C PLL */ +#define PORTTC1_PLL_ENABLE 0x46038 +#define PORTTC2_PLL_ENABLE 0x46040 + +#define ADLP_PORTTC_PLL_ENABLE(tc_port) _MMIO_PORT((tc_port), \ + PORTTC1_PLL_ENABLE, \ + PORTTC2_PLL_ENABLE) + #define _MG_REFCLKIN_CTL_PORT1 0x16892C #define _MG_REFCLKIN_CTL_PORT2 0x16992C #define _MG_REFCLKIN_CTL_PORT3 0x16A92C @@ -10906,6 +10993,8 @@ enum skl_power_gate { #define BXT_DE_PLL_ENABLE _MMIO(0x46070) #define BXT_DE_PLL_PLL_ENABLE (1 << 31) #define BXT_DE_PLL_LOCK (1 << 30) +#define BXT_DE_PLL_FREQ_REQ (1 << 23) +#define BXT_DE_PLL_FREQ_REQ_ACK (1 << 22) #define CNL_CDCLK_PLL_RATIO(x) (x) #define CNL_CDCLK_PLL_RATIO_MASK 0xff @@ -11280,6 +11369,12 @@ enum skl_power_gate { #define ICL_ESC_CLK_DIV_SHIFT 0 #define DSI_MAX_ESC_CLK 20000 /* in KHz */ +#define _ADL_MIPIO_REG 0x180 +#define ADL_MIPIO_DW(port, dw) _MMIO(_ICL_COMBOPHY(port) + _ADL_MIPIO_REG + 4 * (dw)) +#define TX_ESC_CLK_DIV_PHY_SEL REGBIT(16) +#define TX_ESC_CLK_DIV_PHY_MASK REG_GENMASK(23, 16) +#define TX_ESC_CLK_DIV_PHY REG_FIELD_PREP(TX_ESC_CLK_DIV_PHY_MASK, 0x7f) + #define _DSI_CMD_FRMCTL_0 0x6b034 #define _DSI_CMD_FRMCTL_1 0x6b834 #define DSI_CMD_FRMCTL(port) _MMIO_PORT(port, \ @@ -12566,6 +12661,15 @@ enum skl_power_gate { #define DP_PIN_ASSIGNMENT_MASK(idx) (0xf << ((idx) * 4)) #define DP_PIN_ASSIGNMENT(idx, x) ((x) << ((idx) * 4)) +#define _TCSS_DDI_STATUS_1 0x161500 +#define _TCSS_DDI_STATUS_2 0x161504 +#define TCSS_DDI_STATUS(tc) _MMIO(_PICK_EVEN(tc, \ + _TCSS_DDI_STATUS_1, \ + _TCSS_DDI_STATUS_2)) +#define TCSS_DDI_STATUS_READY REG_BIT(2) +#define TCSS_DDI_STATUS_HPD_LIVE_STATUS_TBT REG_BIT(1) +#define TCSS_DDI_STATUS_HPD_LIVE_STATUS_ALT REG_BIT(0) + /* This register controls the Display State Buffer (DSB) engines. */ #define _DSBSL_INSTANCE_BASE 0x70B00 #define DSBSL_INSTANCE(pipe, id) (_DSBSL_INSTANCE_BASE + \ diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c index 970d8f4986bb..1014c71cf7f5 100644 --- a/drivers/gpu/drm/i915/i915_request.c +++ b/drivers/gpu/drm/i915/i915_request.c @@ -1176,12 +1176,12 @@ __emit_semaphore_wait(struct i915_request *to, struct i915_request *from, u32 seqno) { - const int has_token = INTEL_GEN(to->engine->i915) >= 12; + const int has_token = GRAPHICS_VER(to->engine->i915) >= 12; u32 hwsp_offset; int len, err; u32 *cs; - GEM_BUG_ON(INTEL_GEN(to->engine->i915) < 8); + GEM_BUG_ON(GRAPHICS_VER(to->engine->i915) < 8); GEM_BUG_ON(i915_request_has_initial_breadcrumb(to)); /* We need to pin the signaler's HWSP until we are finished reading. */ @@ -1594,8 +1594,8 @@ i915_request_await_object(struct i915_request *to, struct dma_fence **shared; unsigned int count, i; - ret = dma_resv_get_fences_rcu(obj->base.resv, - &excl, &count, &shared); + ret = dma_resv_get_fences(obj->base.resv, &excl, &count, + &shared); if (ret) return ret; @@ -1611,7 +1611,7 @@ i915_request_await_object(struct i915_request *to, dma_fence_put(shared[i]); kfree(shared); } else { - excl = dma_resv_get_excl_rcu(obj->base.resv); + excl = dma_resv_get_excl_unlocked(obj->base.resv); } if (excl) { diff --git a/drivers/gpu/drm/i915/i915_suspend.c b/drivers/gpu/drm/i915/i915_suspend.c index 5fcc32821e18..f7b55f34dba8 100644 --- a/drivers/gpu/drm/i915/i915_suspend.c +++ b/drivers/gpu/drm/i915/i915_suspend.c @@ -38,14 +38,14 @@ static void intel_save_swf(struct drm_i915_private *dev_priv) int i; /* Scratch space */ - if (IS_GEN(dev_priv, 2) && IS_MOBILE(dev_priv)) { + if (GRAPHICS_VER(dev_priv) == 2 && IS_MOBILE(dev_priv)) { for (i = 0; i < 7; i++) { dev_priv->regfile.saveSWF0[i] = intel_de_read(dev_priv, SWF0(i)); dev_priv->regfile.saveSWF1[i] = intel_de_read(dev_priv, SWF1(i)); } for (i = 0; i < 3; i++) dev_priv->regfile.saveSWF3[i] = intel_de_read(dev_priv, SWF3(i)); - } else if (IS_GEN(dev_priv, 2)) { + } else if (GRAPHICS_VER(dev_priv) == 2) { for (i = 0; i < 7; i++) dev_priv->regfile.saveSWF1[i] = intel_de_read(dev_priv, SWF1(i)); } else if (HAS_GMCH(dev_priv)) { @@ -63,14 +63,14 @@ static void intel_restore_swf(struct drm_i915_private *dev_priv) int i; /* Scratch space */ - if (IS_GEN(dev_priv, 2) && IS_MOBILE(dev_priv)) { + if (GRAPHICS_VER(dev_priv) == 2 && IS_MOBILE(dev_priv)) { for (i = 0; i < 7; i++) { intel_de_write(dev_priv, SWF0(i), dev_priv->regfile.saveSWF0[i]); intel_de_write(dev_priv, SWF1(i), dev_priv->regfile.saveSWF1[i]); } for (i = 0; i < 3; i++) intel_de_write(dev_priv, SWF3(i), dev_priv->regfile.saveSWF3[i]); - } else if (IS_GEN(dev_priv, 2)) { + } else if (GRAPHICS_VER(dev_priv) == 2) { for (i = 0; i < 7; i++) intel_de_write(dev_priv, SWF1(i), dev_priv->regfile.saveSWF1[i]); } else if (HAS_GMCH(dev_priv)) { @@ -91,10 +91,10 @@ void i915_save_display(struct drm_i915_private *dev_priv) return; /* Display arbitration control */ - if (INTEL_GEN(dev_priv) <= 4) + if (GRAPHICS_VER(dev_priv) <= 4) dev_priv->regfile.saveDSPARB = intel_de_read(dev_priv, DSPARB); - if (IS_GEN(dev_priv, 4)) + if (GRAPHICS_VER(dev_priv) == 4) pci_read_config_word(pdev, GCDGMBUS, &dev_priv->regfile.saveGCDGMBUS); @@ -110,12 +110,12 @@ void i915_restore_display(struct drm_i915_private *dev_priv) intel_restore_swf(dev_priv); - if (IS_GEN(dev_priv, 4)) + if (GRAPHICS_VER(dev_priv) == 4) pci_write_config_word(pdev, GCDGMBUS, dev_priv->regfile.saveGCDGMBUS); /* Display arbitration */ - if (INTEL_GEN(dev_priv) <= 4) + if (GRAPHICS_VER(dev_priv) <= 4) intel_de_write(dev_priv, DSPARB, dev_priv->regfile.saveDSPARB); /* only restore FBC info on the platform that supports FBC*/ diff --git a/drivers/gpu/drm/i915/i915_sw_fence.c b/drivers/gpu/drm/i915/i915_sw_fence.c index 2744558f3050..c589a681da77 100644 --- a/drivers/gpu/drm/i915/i915_sw_fence.c +++ b/drivers/gpu/drm/i915/i915_sw_fence.c @@ -582,7 +582,7 @@ int i915_sw_fence_await_reservation(struct i915_sw_fence *fence, struct dma_fence **shared; unsigned int count, i; - ret = dma_resv_get_fences_rcu(resv, &excl, &count, &shared); + ret = dma_resv_get_fences(resv, &excl, &count, &shared); if (ret) return ret; @@ -606,7 +606,7 @@ int i915_sw_fence_await_reservation(struct i915_sw_fence *fence, dma_fence_put(shared[i]); kfree(shared); } else { - excl = dma_resv_get_excl_rcu(resv); + excl = dma_resv_get_excl_unlocked(resv); } if (ret >= 0 && excl && excl->ops != exclude) { diff --git a/drivers/gpu/drm/i915/i915_sysfs.c b/drivers/gpu/drm/i915/i915_sysfs.c index 4c6b5d52b5ca..b099e09ccc32 100644 --- a/drivers/gpu/drm/i915/i915_sysfs.c +++ b/drivers/gpu/drm/i915/i915_sysfs.c @@ -595,7 +595,7 @@ void i915_setup_sysfs(struct drm_i915_private *dev_priv) ret = 0; if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) ret = sysfs_create_files(&kdev->kobj, vlv_attrs); - else if (INTEL_GEN(dev_priv) >= 6) + else if (GRAPHICS_VER(dev_priv) >= 6) ret = sysfs_create_files(&kdev->kobj, gen6_attrs); if (ret) drm_err(&dev_priv->drm, "RPS sysfs setup failed\n"); diff --git a/drivers/gpu/drm/i915/i915_vgpu.c b/drivers/gpu/drm/i915/i915_vgpu.c index 172799277dd5..31a105bc1792 100644 --- a/drivers/gpu/drm/i915/i915_vgpu.c +++ b/drivers/gpu/drm/i915/i915_vgpu.c @@ -74,7 +74,7 @@ void intel_vgpu_detect(struct drm_i915_private *dev_priv) * we do not support VGT on older gens, return early so we don't have * to consider differently numbered or sized MMIO bars */ - if (INTEL_GEN(dev_priv) < 6) + if (GRAPHICS_VER(dev_priv) < 6) return; shared_area = pci_iomap_range(pdev, 0, VGT_PVINFO_PAGE, VGT_PVINFO_SIZE); diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c index a6cd0fa62847..b319fd3f91cc 100644 --- a/drivers/gpu/drm/i915/i915_vma.c +++ b/drivers/gpu/drm/i915/i915_vma.c @@ -274,7 +274,7 @@ i915_vma_instance(struct drm_i915_gem_object *obj, { struct i915_vma *vma; - GEM_BUG_ON(view && !i915_is_ggtt(vm)); + GEM_BUG_ON(view && !i915_is_ggtt_or_dpt(vm)); GEM_BUG_ON(!atomic_read(&vm->open)); spin_lock(&obj->vma.lock); diff --git a/drivers/gpu/drm/i915/i915_vma.h b/drivers/gpu/drm/i915/i915_vma.h index 8df784a026d2..dc6926d89626 100644 --- a/drivers/gpu/drm/i915/i915_vma.h +++ b/drivers/gpu/drm/i915/i915_vma.h @@ -68,6 +68,11 @@ static inline bool i915_vma_is_ggtt(const struct i915_vma *vma) return test_bit(I915_VMA_GGTT_BIT, __i915_vma_flags(vma)); } +static inline bool i915_vma_is_dpt(const struct i915_vma *vma) +{ + return i915_is_dpt(vma->vm); +} + static inline bool i915_vma_has_ggtt_write(const struct i915_vma *vma) { return test_bit(I915_VMA_GGTT_WRITE_BIT, __i915_vma_flags(vma)); @@ -158,7 +163,7 @@ i915_vma_compare(struct i915_vma *vma, { ptrdiff_t cmp; - GEM_BUG_ON(view && !i915_is_ggtt(vm)); + GEM_BUG_ON(view && !i915_is_ggtt_or_dpt(vm)); cmp = ptrdiff(vma->vm, vm); if (cmp) diff --git a/drivers/gpu/drm/i915/intel_device_info.c b/drivers/gpu/drm/i915/intel_device_info.c index 8cb58a238c68..7eaa92fee421 100644 --- a/drivers/gpu/drm/i915/intel_device_info.c +++ b/drivers/gpu/drm/i915/intel_device_info.c @@ -257,10 +257,10 @@ void intel_device_info_runtime_init(struct drm_i915_private *dev_priv) if (IS_ADLS_DISPLAY_STEP(dev_priv, STEP_A0, STEP_A0)) for_each_pipe(dev_priv, pipe) runtime->num_scalers[pipe] = 0; - else if (INTEL_GEN(dev_priv) >= 10) { + else if (GRAPHICS_VER(dev_priv) >= 10) { for_each_pipe(dev_priv, pipe) runtime->num_scalers[pipe] = 2; - } else if (IS_GEN(dev_priv, 9)) { + } else if (GRAPHICS_VER(dev_priv) == 9) { runtime->num_scalers[PIPE_A] = 2; runtime->num_scalers[PIPE_B] = 2; runtime->num_scalers[PIPE_C] = 1; @@ -271,10 +271,10 @@ void intel_device_info_runtime_init(struct drm_i915_private *dev_priv) if (DISPLAY_VER(dev_priv) >= 13 || HAS_D12_PLANE_MINIMIZATION(dev_priv)) for_each_pipe(dev_priv, pipe) runtime->num_sprites[pipe] = 4; - else if (INTEL_GEN(dev_priv) >= 11) + else if (GRAPHICS_VER(dev_priv) >= 11) for_each_pipe(dev_priv, pipe) runtime->num_sprites[pipe] = 6; - else if (IS_GEN(dev_priv, 10) || IS_GEMINILAKE(dev_priv)) + else if (GRAPHICS_VER(dev_priv) == 10 || IS_GEMINILAKE(dev_priv)) for_each_pipe(dev_priv, pipe) runtime->num_sprites[pipe] = 3; else if (IS_BROXTON(dev_priv)) { @@ -293,12 +293,12 @@ void intel_device_info_runtime_init(struct drm_i915_private *dev_priv) } else if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) { for_each_pipe(dev_priv, pipe) runtime->num_sprites[pipe] = 2; - } else if (INTEL_GEN(dev_priv) >= 5 || IS_G4X(dev_priv)) { + } else if (GRAPHICS_VER(dev_priv) >= 5 || IS_G4X(dev_priv)) { for_each_pipe(dev_priv, pipe) runtime->num_sprites[pipe] = 1; } - if (HAS_DISPLAY(dev_priv) && IS_GEN_RANGE(dev_priv, 7, 8) && + if (HAS_DISPLAY(dev_priv) && IS_GRAPHICS_VER(dev_priv, 7, 8) && HAS_PCH_SPLIT(dev_priv)) { u32 fuse_strap = intel_de_read(dev_priv, FUSE_STRAP); u32 sfuse_strap = intel_de_read(dev_priv, SFUSE_STRAP); @@ -325,7 +325,7 @@ void intel_device_info_runtime_init(struct drm_i915_private *dev_priv) info->pipe_mask &= ~BIT(PIPE_C); info->cpu_transcoder_mask &= ~BIT(TRANSCODER_C); } - } else if (HAS_DISPLAY(dev_priv) && INTEL_GEN(dev_priv) >= 9) { + } else if (HAS_DISPLAY(dev_priv) && GRAPHICS_VER(dev_priv) >= 9) { u32 dfsm = intel_de_read(dev_priv, SKL_DFSM); if (dfsm & SKL_DFSM_PIPE_A_DISABLE) { @@ -340,7 +340,7 @@ void intel_device_info_runtime_init(struct drm_i915_private *dev_priv) info->pipe_mask &= ~BIT(PIPE_C); info->cpu_transcoder_mask &= ~BIT(TRANSCODER_C); } - if (INTEL_GEN(dev_priv) >= 12 && + if (GRAPHICS_VER(dev_priv) >= 12 && (dfsm & TGL_DFSM_PIPE_D_DISABLE)) { info->pipe_mask &= ~BIT(PIPE_D); info->cpu_transcoder_mask &= ~BIT(TRANSCODER_D); @@ -352,15 +352,15 @@ void intel_device_info_runtime_init(struct drm_i915_private *dev_priv) if (dfsm & SKL_DFSM_DISPLAY_PM_DISABLE) info->display.has_fbc = 0; - if (INTEL_GEN(dev_priv) >= 11 && (dfsm & ICL_DFSM_DMC_DISABLE)) - info->display.has_csr = 0; + if (GRAPHICS_VER(dev_priv) >= 11 && (dfsm & ICL_DFSM_DMC_DISABLE)) + info->display.has_dmc = 0; - if (INTEL_GEN(dev_priv) >= 10 && + if (GRAPHICS_VER(dev_priv) >= 10 && (dfsm & CNL_DFSM_DISPLAY_DSC_DISABLE)) info->display.has_dsc = 0; } - if (IS_GEN(dev_priv, 6) && intel_vtd_active()) { + if (GRAPHICS_VER(dev_priv) == 6 && intel_vtd_active()) { drm_info(&dev_priv->drm, "Disabling ppGTT for VT-d support\n"); info->ppgtt_type = INTEL_PPGTT_NONE; diff --git a/drivers/gpu/drm/i915/intel_device_info.h b/drivers/gpu/drm/i915/intel_device_info.h index e98b36959736..b326aff65cd6 100644 --- a/drivers/gpu/drm/i915/intel_device_info.h +++ b/drivers/gpu/drm/i915/intel_device_info.h @@ -141,7 +141,7 @@ enum intel_ppgtt_type { #define DEV_INFO_DISPLAY_FOR_EACH_FLAG(func) \ /* Keep in alphabetical order */ \ func(cursor_needs_physical); \ - func(has_csr); \ + func(has_dmc); \ func(has_ddi); \ func(has_dp_mst); \ func(has_dsb); \ @@ -185,6 +185,8 @@ struct intel_device_info { u8 abox_mask; + u8 has_cdclk_crawl; /* does support CDCLK crawling */ + #define DEFINE_FLAG(name) u8 name:1 DEV_INFO_FOR_EACH_FLAG(DEFINE_FLAG); #undef DEFINE_FLAG diff --git a/drivers/gpu/drm/i915/intel_dram.c b/drivers/gpu/drm/i915/intel_dram.c index 1e53c017c30d..50fdea84ba70 100644 --- a/drivers/gpu/drm/i915/intel_dram.c +++ b/drivers/gpu/drm/i915/intel_dram.c @@ -121,7 +121,7 @@ skl_dram_get_dimm_info(struct drm_i915_private *i915, struct dram_dimm_info *dimm, int channel, char dimm_name, u16 val) { - if (INTEL_GEN(i915) >= 10) { + if (GRAPHICS_VER(i915) >= 10) { dimm->size = cnl_get_dimm_size(val); dimm->width = cnl_get_dimm_width(val); dimm->ranks = cnl_get_dimm_ranks(val); @@ -422,7 +422,7 @@ static int icl_pcode_read_mem_global_info(struct drm_i915_private *dev_priv) if (ret) return ret; - if (IS_GEN(dev_priv, 12)) { + if (GRAPHICS_VER(dev_priv) == 12) { switch (val & 0xf) { case 0: dram_info->type = INTEL_DRAM_DDR4; @@ -501,12 +501,12 @@ void intel_dram_detect(struct drm_i915_private *i915) */ dram_info->wm_lv_0_adjust_needed = !IS_GEN9_LP(i915); - if (INTEL_GEN(i915) < 9 || !HAS_DISPLAY(i915)) + if (GRAPHICS_VER(i915) < 9 || !HAS_DISPLAY(i915)) return; - if (INTEL_GEN(i915) >= 12) + if (GRAPHICS_VER(i915) >= 12) ret = gen12_get_dram_info(i915); - else if (INTEL_GEN(i915) >= 11) + else if (GRAPHICS_VER(i915) >= 11) ret = gen11_get_dram_info(i915); else if (IS_GEN9_LP(i915)) ret = bxt_get_dram_info(i915); @@ -535,7 +535,7 @@ void intel_dram_edram_detect(struct drm_i915_private *i915) { u32 edram_cap = 0; - if (!(IS_HASWELL(i915) || IS_BROADWELL(i915) || INTEL_GEN(i915) >= 9)) + if (!(IS_HASWELL(i915) || IS_BROADWELL(i915) || GRAPHICS_VER(i915) >= 9)) return; edram_cap = __raw_uncore_read32(&i915->uncore, HSW_EDRAM_CAP); @@ -549,7 +549,7 @@ void intel_dram_edram_detect(struct drm_i915_private *i915) * The needed capability bits for size calculation are not there with * pre gen9 so return 128MB always. */ - if (INTEL_GEN(i915) < 9) + if (GRAPHICS_VER(i915) < 9) i915->edram_size_mb = 128; else i915->edram_size_mb = gen9_edram_size_mb(i915, edram_cap); diff --git a/drivers/gpu/drm/i915/intel_pch.c b/drivers/gpu/drm/i915/intel_pch.c index 98a17dd1bda4..4e92ae19189e 100644 --- a/drivers/gpu/drm/i915/intel_pch.c +++ b/drivers/gpu/drm/i915/intel_pch.c @@ -13,17 +13,17 @@ intel_pch_type(const struct drm_i915_private *dev_priv, unsigned short id) switch (id) { case INTEL_PCH_IBX_DEVICE_ID_TYPE: drm_dbg_kms(&dev_priv->drm, "Found Ibex Peak PCH\n"); - drm_WARN_ON(&dev_priv->drm, !IS_GEN(dev_priv, 5)); + drm_WARN_ON(&dev_priv->drm, GRAPHICS_VER(dev_priv) != 5); return PCH_IBX; case INTEL_PCH_CPT_DEVICE_ID_TYPE: drm_dbg_kms(&dev_priv->drm, "Found CougarPoint PCH\n"); drm_WARN_ON(&dev_priv->drm, - !IS_GEN(dev_priv, 6) && !IS_IVYBRIDGE(dev_priv)); + GRAPHICS_VER(dev_priv) != 6 && !IS_IVYBRIDGE(dev_priv)); return PCH_CPT; case INTEL_PCH_PPT_DEVICE_ID_TYPE: drm_dbg_kms(&dev_priv->drm, "Found PantherPoint PCH\n"); drm_WARN_ON(&dev_priv->drm, - !IS_GEN(dev_priv, 6) && !IS_IVYBRIDGE(dev_priv)); + GRAPHICS_VER(dev_priv) != 6 && !IS_IVYBRIDGE(dev_priv)); /* PantherPoint is CPT compatible */ return PCH_CPT; case INTEL_PCH_LPT_DEVICE_ID_TYPE: @@ -181,9 +181,9 @@ intel_virt_detect_pch(const struct drm_i915_private *dev_priv, id = INTEL_PCH_LPT_LP_DEVICE_ID_TYPE; else if (IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv)) id = INTEL_PCH_LPT_DEVICE_ID_TYPE; - else if (IS_GEN(dev_priv, 6) || IS_IVYBRIDGE(dev_priv)) + else if (GRAPHICS_VER(dev_priv) == 6 || IS_IVYBRIDGE(dev_priv)) id = INTEL_PCH_CPT_DEVICE_ID_TYPE; - else if (IS_GEN(dev_priv, 5)) + else if (GRAPHICS_VER(dev_priv) == 5) id = INTEL_PCH_IBX_DEVICE_ID_TYPE; if (id) diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c index 15d9a64e7b4c..45fefa0ed160 100644 --- a/drivers/gpu/drm/i915/intel_pm.c +++ b/drivers/gpu/drm/i915/intel_pm.c @@ -2983,7 +2983,9 @@ static void intel_fixup_cur_wm_latency(struct drm_i915_private *dev_priv, int ilk_wm_max_level(const struct drm_i915_private *dev_priv) { /* how many WM levels are we expecting */ - if (DISPLAY_VER(dev_priv) >= 9) + if (HAS_HW_SAGV_WM(dev_priv)) + return 5; + else if (DISPLAY_VER(dev_priv) >= 9) return 7; else if (IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv)) return 4; @@ -4011,8 +4013,9 @@ static int intel_compute_sagv_mask(struct intel_atomic_state *state) * latter from the plane commit hooks (especially in the legacy * cursor case) */ - pipe_wm->use_sagv_wm = DISPLAY_VER(dev_priv) >= 12 && - intel_can_enable_sagv(dev_priv, new_bw_state); + pipe_wm->use_sagv_wm = !HAS_HW_SAGV_WM(dev_priv) && + DISPLAY_VER(dev_priv) >= 12 && + intel_can_enable_sagv(dev_priv, new_bw_state); } if (intel_can_enable_sagv(dev_priv, new_bw_state) != @@ -4054,6 +4057,20 @@ skl_ddb_entry_for_slices(struct drm_i915_private *dev_priv, u8 slice_mask, WARN_ON(ddb->end > INTEL_INFO(dev_priv)->dbuf.size); } +static unsigned int mbus_ddb_offset(struct drm_i915_private *i915, u8 slice_mask) +{ + struct skl_ddb_entry ddb; + + if (slice_mask & (BIT(DBUF_S1) | BIT(DBUF_S2))) + slice_mask = BIT(DBUF_S1); + else if (slice_mask & (BIT(DBUF_S3) | BIT(DBUF_S4))) + slice_mask = BIT(DBUF_S3); + + skl_ddb_entry_for_slices(i915, slice_mask, &ddb); + + return ddb.start; +} + u32 skl_ddb_dbuf_slice_mask(struct drm_i915_private *dev_priv, const struct skl_ddb_entry *entry) { @@ -4146,6 +4163,7 @@ skl_crtc_allocate_ddb(struct intel_atomic_state *state, struct intel_crtc *crtc) struct intel_crtc_state *crtc_state; struct skl_ddb_entry ddb_slices; enum pipe pipe = crtc->pipe; + unsigned int mbus_offset = 0; u32 ddb_range_size; u32 dbuf_slice_mask; u32 start, end; @@ -4160,6 +4178,7 @@ skl_crtc_allocate_ddb(struct intel_atomic_state *state, struct intel_crtc *crtc) dbuf_slice_mask = new_dbuf_state->slices[pipe]; skl_ddb_entry_for_slices(dev_priv, dbuf_slice_mask, &ddb_slices); + mbus_offset = mbus_ddb_offset(dev_priv, dbuf_slice_mask); ddb_range_size = skl_ddb_entry_size(&ddb_slices); intel_crtc_dbuf_weights(new_dbuf_state, pipe, @@ -4168,11 +4187,11 @@ skl_crtc_allocate_ddb(struct intel_atomic_state *state, struct intel_crtc *crtc) start = ddb_range_size * weight_start / weight_total; end = ddb_range_size * weight_end / weight_total; - new_dbuf_state->ddb[pipe].start = ddb_slices.start + start; - new_dbuf_state->ddb[pipe].end = ddb_slices.start + end; - + new_dbuf_state->ddb[pipe].start = ddb_slices.start - mbus_offset + start; + new_dbuf_state->ddb[pipe].end = ddb_slices.start - mbus_offset + end; out: - if (skl_ddb_entry_equal(&old_dbuf_state->ddb[pipe], + if (old_dbuf_state->slices[pipe] == new_dbuf_state->slices[pipe] && + skl_ddb_entry_equal(&old_dbuf_state->ddb[pipe], &new_dbuf_state->ddb[pipe])) return 0; @@ -4184,7 +4203,12 @@ out: if (IS_ERR(crtc_state)) return PTR_ERR(crtc_state); - crtc_state->wm.skl.ddb = new_dbuf_state->ddb[pipe]; + /* + * Used for checking overlaps, so we need absolute + * offsets instead of MBUS relative offsets. + */ + crtc_state->wm.skl.ddb.start = mbus_offset + new_dbuf_state->ddb[pipe].start; + crtc_state->wm.skl.ddb.end = mbus_offset + new_dbuf_state->ddb[pipe].end; drm_dbg_kms(&dev_priv->drm, "[CRTC:%d:%s] dbuf slices 0x%x -> 0x%x, ddb (%d - %d) -> (%d - %d), active pipes 0x%x -> 0x%x\n", @@ -4242,7 +4266,6 @@ skl_cursor_allocation(const struct intel_crtc_state *crtc_state, static void skl_ddb_entry_init_from_hw(struct drm_i915_private *dev_priv, struct skl_ddb_entry *entry, u32 reg) { - entry->start = reg & DDB_ENTRY_MASK; entry->end = (reg >> DDB_ENTRY_END_SHIFT) & DDB_ENTRY_MASK; @@ -4367,6 +4390,7 @@ skl_plane_downscale_amount(const struct intel_crtc_state *crtc_state, struct dbuf_slice_conf_entry { u8 active_pipes; u8 dbuf_mask[I915_MAX_PIPES]; + bool join_mbus; }; /* @@ -4555,6 +4579,137 @@ static const struct dbuf_slice_conf_entry tgl_allowed_dbufs[] = {} }; +static const struct dbuf_slice_conf_entry adlp_allowed_dbufs[] = { + { + .active_pipes = BIT(PIPE_A), + .dbuf_mask = { + [PIPE_A] = BIT(DBUF_S1) | BIT(DBUF_S2) | BIT(DBUF_S3) | BIT(DBUF_S4), + }, + .join_mbus = true, + }, + { + .active_pipes = BIT(PIPE_B), + .dbuf_mask = { + [PIPE_B] = BIT(DBUF_S1) | BIT(DBUF_S2) | BIT(DBUF_S3) | BIT(DBUF_S4), + }, + .join_mbus = true, + }, + { + .active_pipes = BIT(PIPE_A) | BIT(PIPE_B), + .dbuf_mask = { + [PIPE_A] = BIT(DBUF_S1) | BIT(DBUF_S2), + [PIPE_B] = BIT(DBUF_S3) | BIT(DBUF_S4), + }, + }, + { + .active_pipes = BIT(PIPE_C), + .dbuf_mask = { + [PIPE_C] = BIT(DBUF_S3) | BIT(DBUF_S4), + }, + }, + { + .active_pipes = BIT(PIPE_A) | BIT(PIPE_C), + .dbuf_mask = { + [PIPE_A] = BIT(DBUF_S1) | BIT(DBUF_S2), + [PIPE_C] = BIT(DBUF_S3) | BIT(DBUF_S4), + }, + }, + { + .active_pipes = BIT(PIPE_B) | BIT(PIPE_C), + .dbuf_mask = { + [PIPE_B] = BIT(DBUF_S3) | BIT(DBUF_S4), + [PIPE_C] = BIT(DBUF_S3) | BIT(DBUF_S4), + }, + }, + { + .active_pipes = BIT(PIPE_A) | BIT(PIPE_B) | BIT(PIPE_C), + .dbuf_mask = { + [PIPE_A] = BIT(DBUF_S1) | BIT(DBUF_S2), + [PIPE_B] = BIT(DBUF_S3) | BIT(DBUF_S4), + [PIPE_C] = BIT(DBUF_S3) | BIT(DBUF_S4), + }, + }, + { + .active_pipes = BIT(PIPE_D), + .dbuf_mask = { + [PIPE_D] = BIT(DBUF_S1) | BIT(DBUF_S2), + }, + }, + { + .active_pipes = BIT(PIPE_A) | BIT(PIPE_D), + .dbuf_mask = { + [PIPE_A] = BIT(DBUF_S1) | BIT(DBUF_S2), + [PIPE_D] = BIT(DBUF_S1) | BIT(DBUF_S2), + }, + }, + { + .active_pipes = BIT(PIPE_B) | BIT(PIPE_D), + .dbuf_mask = { + [PIPE_B] = BIT(DBUF_S3) | BIT(DBUF_S4), + [PIPE_D] = BIT(DBUF_S1) | BIT(DBUF_S2), + }, + }, + { + .active_pipes = BIT(PIPE_A) | BIT(PIPE_B) | BIT(PIPE_D), + .dbuf_mask = { + [PIPE_A] = BIT(DBUF_S1) | BIT(DBUF_S2), + [PIPE_B] = BIT(DBUF_S3) | BIT(DBUF_S4), + [PIPE_D] = BIT(DBUF_S1) | BIT(DBUF_S2), + }, + }, + { + .active_pipes = BIT(PIPE_C) | BIT(PIPE_D), + .dbuf_mask = { + [PIPE_C] = BIT(DBUF_S3) | BIT(DBUF_S4), + [PIPE_D] = BIT(DBUF_S1) | BIT(DBUF_S2), + }, + }, + { + .active_pipes = BIT(PIPE_A) | BIT(PIPE_C) | BIT(PIPE_D), + .dbuf_mask = { + [PIPE_A] = BIT(DBUF_S1) | BIT(DBUF_S2), + [PIPE_C] = BIT(DBUF_S3) | BIT(DBUF_S4), + [PIPE_D] = BIT(DBUF_S1) | BIT(DBUF_S2), + }, + }, + { + .active_pipes = BIT(PIPE_B) | BIT(PIPE_C) | BIT(PIPE_D), + .dbuf_mask = { + [PIPE_B] = BIT(DBUF_S3) | BIT(DBUF_S4), + [PIPE_C] = BIT(DBUF_S3) | BIT(DBUF_S4), + [PIPE_D] = BIT(DBUF_S1) | BIT(DBUF_S2), + }, + }, + { + .active_pipes = BIT(PIPE_A) | BIT(PIPE_B) | BIT(PIPE_C) | BIT(PIPE_D), + .dbuf_mask = { + [PIPE_A] = BIT(DBUF_S1) | BIT(DBUF_S2), + [PIPE_B] = BIT(DBUF_S3) | BIT(DBUF_S4), + [PIPE_C] = BIT(DBUF_S3) | BIT(DBUF_S4), + [PIPE_D] = BIT(DBUF_S1) | BIT(DBUF_S2), + }, + }, + {} + +}; + +static bool check_mbus_joined(u8 active_pipes, + const struct dbuf_slice_conf_entry *dbuf_slices) +{ + int i; + + for (i = 0; i < dbuf_slices[i].active_pipes; i++) { + if (dbuf_slices[i].active_pipes == active_pipes) + return dbuf_slices[i].join_mbus; + } + return false; +} + +static bool adlp_check_mbus_joined(u8 active_pipes) +{ + return check_mbus_joined(active_pipes, adlp_allowed_dbufs); +} + static u8 compute_dbuf_slices(enum pipe pipe, u8 active_pipes, const struct dbuf_slice_conf_entry *dbuf_slices) { @@ -4594,12 +4749,19 @@ static u8 tgl_compute_dbuf_slices(enum pipe pipe, u8 active_pipes) return compute_dbuf_slices(pipe, active_pipes, tgl_allowed_dbufs); } +static u32 adlp_compute_dbuf_slices(enum pipe pipe, u32 active_pipes) +{ + return compute_dbuf_slices(pipe, active_pipes, adlp_allowed_dbufs); +} + static u8 skl_compute_dbuf_slices(struct intel_crtc *crtc, u8 active_pipes) { struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); enum pipe pipe = crtc->pipe; - if (DISPLAY_VER(dev_priv) == 12) + if (IS_ALDERLAKE_P(dev_priv)) + return adlp_compute_dbuf_slices(pipe, active_pipes); + else if (DISPLAY_VER(dev_priv) == 12) return tgl_compute_dbuf_slices(pipe, active_pipes); else if (DISPLAY_VER(dev_priv) == 11) return icl_compute_dbuf_slices(pipe, active_pipes); @@ -5619,6 +5781,13 @@ void skl_write_plane_wm(struct intel_plane *plane, skl_write_wm_level(dev_priv, PLANE_WM_TRANS(pipe, plane_id), skl_plane_trans_wm(pipe_wm, plane_id)); + if (HAS_HW_SAGV_WM(dev_priv)) { + skl_write_wm_level(dev_priv, PLANE_WM_SAGV(pipe, plane_id), + &wm->sagv.wm0); + skl_write_wm_level(dev_priv, PLANE_WM_SAGV_TRANS(pipe, plane_id), + &wm->sagv.trans_wm); + } + if (DISPLAY_VER(dev_priv) >= 11) { skl_ddb_entry_write(dev_priv, PLANE_BUF_CFG(pipe, plane_id), ddb_y); @@ -5652,6 +5821,15 @@ void skl_write_cursor_wm(struct intel_plane *plane, skl_write_wm_level(dev_priv, CUR_WM_TRANS(pipe), skl_plane_trans_wm(pipe_wm, plane_id)); + if (HAS_HW_SAGV_WM(dev_priv)) { + const struct skl_plane_wm *wm = &pipe_wm->planes[plane_id]; + + skl_write_wm_level(dev_priv, CUR_WM_SAGV(pipe), + &wm->sagv.wm0); + skl_write_wm_level(dev_priv, CUR_WM_SAGV_TRANS(pipe), + &wm->sagv.trans_wm); + } + skl_ddb_entry_write(dev_priv, CUR_BUF_CFG(pipe), ddb); } @@ -5813,16 +5991,29 @@ skl_compute_ddb(struct intel_atomic_state *state) new_dbuf_state->enabled_slices = intel_dbuf_enabled_slices(new_dbuf_state); - if (old_dbuf_state->enabled_slices != new_dbuf_state->enabled_slices) { + if (IS_ALDERLAKE_P(dev_priv)) + new_dbuf_state->joined_mbus = adlp_check_mbus_joined(new_dbuf_state->active_pipes); + + if (old_dbuf_state->enabled_slices != new_dbuf_state->enabled_slices || + old_dbuf_state->joined_mbus != new_dbuf_state->joined_mbus) { ret = intel_atomic_serialize_global_state(&new_dbuf_state->base); if (ret) return ret; + if (old_dbuf_state->joined_mbus != new_dbuf_state->joined_mbus) { + /* TODO: Implement vblank synchronized MBUS joining changes */ + ret = intel_modeset_all_pipes(state); + if (ret) + return ret; + } + drm_dbg_kms(&dev_priv->drm, - "Enabled dbuf slices 0x%x -> 0x%x (total dbuf slices 0x%x)\n", + "Enabled dbuf slices 0x%x -> 0x%x (total dbuf slices 0x%x), mbus joined? %s->%s\n", old_dbuf_state->enabled_slices, new_dbuf_state->enabled_slices, - INTEL_INFO(dev_priv)->dbuf.slice_mask); + INTEL_INFO(dev_priv)->dbuf.slice_mask, + yesno(old_dbuf_state->joined_mbus), + yesno(new_dbuf_state->joined_mbus)); } for_each_new_intel_crtc_in_state(state, crtc, new_crtc_state, i) { @@ -6016,6 +6207,15 @@ static bool skl_plane_selected_wm_equals(struct intel_plane *plane, return false; } + if (HAS_HW_SAGV_WM(i915)) { + const struct skl_plane_wm *old_wm = &old_pipe_wm->planes[plane->id]; + const struct skl_plane_wm *new_wm = &new_pipe_wm->planes[plane->id]; + + if (!skl_wm_level_equals(&old_wm->sagv.wm0, &new_wm->sagv.wm0) || + !skl_wm_level_equals(&old_wm->sagv.trans_wm, &new_wm->sagv.trans_wm)) + return false; + } + return skl_wm_level_equals(skl_plane_trans_wm(old_pipe_wm, plane->id), skl_plane_trans_wm(new_pipe_wm, plane->id)); } @@ -6234,7 +6434,25 @@ void skl_pipe_wm_get_hw_state(struct intel_crtc *crtc, skl_wm_level_from_reg_val(val, &wm->trans_wm); - if (DISPLAY_VER(dev_priv) >= 12) { + if (HAS_HW_SAGV_WM(dev_priv)) { + if (plane_id != PLANE_CURSOR) + val = intel_uncore_read(&dev_priv->uncore, + PLANE_WM_SAGV(pipe, plane_id)); + else + val = intel_uncore_read(&dev_priv->uncore, + CUR_WM_SAGV(pipe)); + + skl_wm_level_from_reg_val(val, &wm->sagv.wm0); + + if (plane_id != PLANE_CURSOR) + val = intel_uncore_read(&dev_priv->uncore, + PLANE_WM_SAGV_TRANS(pipe, plane_id)); + else + val = intel_uncore_read(&dev_priv->uncore, + CUR_WM_SAGV_TRANS(pipe)); + + skl_wm_level_from_reg_val(val, &wm->sagv.trans_wm); + } else if (DISPLAY_VER(dev_priv) >= 12) { wm->sagv.wm0 = wm->wm[0]; wm->sagv.trans_wm = wm->trans_wm; } @@ -6247,10 +6465,14 @@ void skl_wm_get_hw_state(struct drm_i915_private *dev_priv) to_intel_dbuf_state(dev_priv->dbuf.obj.state); struct intel_crtc *crtc; + if (IS_ALDERLAKE_P(dev_priv)) + dbuf_state->joined_mbus = intel_de_read(dev_priv, MBUS_CTL) & MBUS_JOIN; + for_each_intel_crtc(&dev_priv->drm, crtc) { struct intel_crtc_state *crtc_state = to_intel_crtc_state(crtc->base.state); enum pipe pipe = crtc->pipe; + unsigned int mbus_offset; enum plane_id plane_id; skl_pipe_wm_get_hw_state(crtc, &crtc_state->wm.skl.optimal); @@ -6276,13 +6498,20 @@ void skl_wm_get_hw_state(struct drm_i915_private *dev_priv) dbuf_state->weight[pipe] = intel_crtc_ddb_weight(crtc_state); - crtc_state->wm.skl.ddb = dbuf_state->ddb[pipe]; + /* + * Used for checking overlaps, so we need absolute + * offsets instead of MBUS relative offsets. + */ + mbus_offset = mbus_ddb_offset(dev_priv, dbuf_state->slices[pipe]); + crtc_state->wm.skl.ddb.start = mbus_offset + dbuf_state->ddb[pipe].start; + crtc_state->wm.skl.ddb.end = mbus_offset + dbuf_state->ddb[pipe].end; drm_dbg_kms(&dev_priv->drm, - "[CRTC:%d:%s] dbuf slices 0x%x, ddb (%d - %d), active pipes 0x%x\n", + "[CRTC:%d:%s] dbuf slices 0x%x, ddb (%d - %d), active pipes 0x%x, mbus joined: %s\n", crtc->base.base.id, crtc->base.name, dbuf_state->slices[pipe], dbuf_state->ddb[pipe].start, - dbuf_state->ddb[pipe].end, dbuf_state->active_pipes); + dbuf_state->ddb[pipe].end, dbuf_state->active_pipes, + yesno(dbuf_state->joined_mbus)); } dbuf_state->enabled_slices = dev_priv->dbuf.enabled_slices; @@ -7630,9 +7859,9 @@ void intel_init_clock_gating_hooks(struct drm_i915_private *dev_priv) dev_priv->display.init_clock_gating = adlp_init_clock_gating; else if (IS_DG1(dev_priv)) dev_priv->display.init_clock_gating = dg1_init_clock_gating; - else if (IS_GEN(dev_priv, 12)) + else if (GRAPHICS_VER(dev_priv) == 12) dev_priv->display.init_clock_gating = gen12lp_init_clock_gating; - else if (IS_GEN(dev_priv, 11)) + else if (GRAPHICS_VER(dev_priv) == 11) dev_priv->display.init_clock_gating = icl_init_clock_gating; else if (IS_CANNONLAKE(dev_priv)) dev_priv->display.init_clock_gating = cnl_init_clock_gating; @@ -7656,9 +7885,9 @@ void intel_init_clock_gating_hooks(struct drm_i915_private *dev_priv) dev_priv->display.init_clock_gating = ivb_init_clock_gating; else if (IS_VALLEYVIEW(dev_priv)) dev_priv->display.init_clock_gating = vlv_init_clock_gating; - else if (IS_GEN(dev_priv, 6)) + else if (GRAPHICS_VER(dev_priv) == 6) dev_priv->display.init_clock_gating = gen6_init_clock_gating; - else if (IS_GEN(dev_priv, 5)) + else if (GRAPHICS_VER(dev_priv) == 5) dev_priv->display.init_clock_gating = ilk_init_clock_gating; else if (IS_G4X(dev_priv)) dev_priv->display.init_clock_gating = g4x_init_clock_gating; @@ -7666,11 +7895,11 @@ void intel_init_clock_gating_hooks(struct drm_i915_private *dev_priv) dev_priv->display.init_clock_gating = i965gm_init_clock_gating; else if (IS_I965G(dev_priv)) dev_priv->display.init_clock_gating = i965g_init_clock_gating; - else if (IS_GEN(dev_priv, 3)) + else if (GRAPHICS_VER(dev_priv) == 3) dev_priv->display.init_clock_gating = gen3_init_clock_gating; else if (IS_I85X(dev_priv) || IS_I865G(dev_priv)) dev_priv->display.init_clock_gating = i85x_init_clock_gating; - else if (IS_GEN(dev_priv, 2)) + else if (GRAPHICS_VER(dev_priv) == 2) dev_priv->display.init_clock_gating = i830_init_clock_gating; else { MISSING_CASE(INTEL_DEVID(dev_priv)); @@ -7684,7 +7913,7 @@ void intel_init_pm(struct drm_i915_private *dev_priv) /* For cxsr */ if (IS_PINEVIEW(dev_priv)) pnv_get_mem_freq(dev_priv); - else if (IS_GEN(dev_priv, 5)) + else if (GRAPHICS_VER(dev_priv) == 5) ilk_get_mem_freq(dev_priv); if (intel_has_sagv(dev_priv)) @@ -7816,6 +8045,45 @@ int intel_dbuf_init(struct drm_i915_private *dev_priv) return 0; } +/* + * Configure MBUS_CTL and all DBUF_CTL_S of each slice to join_mbus state before + * update the request state of all DBUS slices. + */ +static void update_mbus_pre_enable(struct intel_atomic_state *state) +{ + struct drm_i915_private *dev_priv = to_i915(state->base.dev); + u32 mbus_ctl, dbuf_min_tracker_val; + enum dbuf_slice slice; + const struct intel_dbuf_state *dbuf_state = + intel_atomic_get_new_dbuf_state(state); + + if (!IS_ALDERLAKE_P(dev_priv)) + return; + + /* + * TODO: Implement vblank synchronized MBUS joining changes. + * Must be properly coordinated with dbuf reprogramming. + */ + if (dbuf_state->joined_mbus) { + mbus_ctl = MBUS_HASHING_MODE_1x4 | MBUS_JOIN | + MBUS_JOIN_PIPE_SELECT_NONE; + dbuf_min_tracker_val = DBUF_MIN_TRACKER_STATE_SERVICE(3); + } else { + mbus_ctl = MBUS_HASHING_MODE_2x2 | + MBUS_JOIN_PIPE_SELECT_NONE; + dbuf_min_tracker_val = DBUF_MIN_TRACKER_STATE_SERVICE(1); + } + + intel_de_rmw(dev_priv, MBUS_CTL, + MBUS_HASHING_MODE_MASK | MBUS_JOIN | + MBUS_JOIN_PIPE_SELECT_MASK, mbus_ctl); + + for_each_dbuf_slice(dev_priv, slice) + intel_de_rmw(dev_priv, DBUF_CTL_S(slice), + DBUF_MIN_TRACKER_STATE_SERVICE_MASK, + dbuf_min_tracker_val); +} + void intel_dbuf_pre_plane_update(struct intel_atomic_state *state) { struct drm_i915_private *dev_priv = to_i915(state->base.dev); @@ -7825,11 +8093,13 @@ void intel_dbuf_pre_plane_update(struct intel_atomic_state *state) intel_atomic_get_old_dbuf_state(state); if (!new_dbuf_state || - new_dbuf_state->enabled_slices == old_dbuf_state->enabled_slices) + ((new_dbuf_state->enabled_slices == old_dbuf_state->enabled_slices) + && (new_dbuf_state->joined_mbus == old_dbuf_state->joined_mbus))) return; WARN_ON(!new_dbuf_state->base.changed); + update_mbus_pre_enable(state); gen9_dbuf_slices_update(dev_priv, old_dbuf_state->enabled_slices | new_dbuf_state->enabled_slices); @@ -7844,7 +8114,8 @@ void intel_dbuf_post_plane_update(struct intel_atomic_state *state) intel_atomic_get_old_dbuf_state(state); if (!new_dbuf_state || - new_dbuf_state->enabled_slices == old_dbuf_state->enabled_slices) + ((new_dbuf_state->enabled_slices == old_dbuf_state->enabled_slices) + && (new_dbuf_state->joined_mbus == old_dbuf_state->joined_mbus))) return; WARN_ON(!new_dbuf_state->base.changed); diff --git a/drivers/gpu/drm/i915/intel_pm.h b/drivers/gpu/drm/i915/intel_pm.h index 669c8d505677..91f23b7f0af2 100644 --- a/drivers/gpu/drm/i915/intel_pm.h +++ b/drivers/gpu/drm/i915/intel_pm.h @@ -78,13 +78,11 @@ struct intel_dbuf_state { struct skl_ddb_entry ddb[I915_MAX_PIPES]; unsigned int weight[I915_MAX_PIPES]; u8 slices[I915_MAX_PIPES]; - u8 enabled_slices; u8 active_pipes; + bool joined_mbus; }; -int intel_dbuf_init(struct drm_i915_private *dev_priv); - struct intel_dbuf_state * intel_atomic_get_dbuf_state(struct intel_atomic_state *state); diff --git a/drivers/gpu/drm/i915/intel_sideband.c b/drivers/gpu/drm/i915/intel_sideband.c index 0ec0cf191955..f0a82b37bd1a 100644 --- a/drivers/gpu/drm/i915/intel_sideband.c +++ b/drivers/gpu/drm/i915/intel_sideband.c @@ -430,7 +430,7 @@ static int __sandybridge_pcode_rw(struct drm_i915_private *i915, if (is_read && val1) *val1 = intel_uncore_read_fw(uncore, GEN6_PCODE_DATA1); - if (INTEL_GEN(i915) > 6) + if (GRAPHICS_VER(i915) > 6) return gen7_check_mailbox_status(mbox); else return gen6_check_mailbox_status(mbox); diff --git a/drivers/gpu/drm/i915/intel_uncore.c b/drivers/gpu/drm/i915/intel_uncore.c index b4aaf8b7109f..1bed8f666048 100644 --- a/drivers/gpu/drm/i915/intel_uncore.c +++ b/drivers/gpu/drm/i915/intel_uncore.c @@ -1635,7 +1635,7 @@ static int intel_uncore_fw_domains_init(struct intel_uncore *uncore) #define fw_domain_init(uncore__, id__, set__, ack__) \ (ret ?: (ret = __fw_domain_init((uncore__), (id__), (set__), (ack__)))) - if (INTEL_GEN(i915) >= 11) { + if (GRAPHICS_VER(i915) >= 11) { /* we'll prune the domains of missing engines later */ intel_engine_mask_t emask = INTEL_INFO(i915)->platform_engine_mask; int i; @@ -1665,7 +1665,7 @@ static int intel_uncore_fw_domains_init(struct intel_uncore *uncore) FORCEWAKE_MEDIA_VEBOX_GEN11(i), FORCEWAKE_ACK_MEDIA_VEBOX_GEN11(i)); } - } else if (IS_GEN_RANGE(i915, 9, 10)) { + } else if (IS_GRAPHICS_VER(i915, 9, 10)) { uncore->funcs.force_wake_get = fw_domains_get_with_fallback; uncore->funcs.force_wake_put = fw_domains_put; fw_domain_init(uncore, FW_DOMAIN_ID_RENDER, @@ -1733,7 +1733,7 @@ static int intel_uncore_fw_domains_init(struct intel_uncore *uncore) fw_domain_init(uncore, FW_DOMAIN_ID_RENDER, FORCEWAKE, FORCEWAKE_ACK); } - } else if (IS_GEN(i915, 6)) { + } else if (GRAPHICS_VER(i915) == 6) { uncore->funcs.force_wake_get = fw_domains_get_with_thread_status; uncore->funcs.force_wake_put = fw_domains_put; @@ -1800,7 +1800,7 @@ static int uncore_mmio_setup(struct intel_uncore *uncore) int mmio_bar; int mmio_size; - mmio_bar = IS_GEN(i915, 2) ? 1 : 0; + mmio_bar = GRAPHICS_VER(i915) == 2 ? 1 : 0; /* * Before gen4, the registers and the GTT are behind different BARs. * However, from gen4 onwards, the registers and the GTT are shared @@ -1810,7 +1810,7 @@ static int uncore_mmio_setup(struct intel_uncore *uncore) * generations up to Ironlake. * For dgfx chips register range is expanded to 4MB. */ - if (INTEL_GEN(i915) < 5) + if (GRAPHICS_VER(i915) < 5) mmio_size = 512 * 1024; else if (IS_DGFX(i915)) mmio_size = 4 * 1024 * 1024; @@ -1849,7 +1849,7 @@ static void uncore_raw_init(struct intel_uncore *uncore) if (intel_vgpu_active(uncore->i915)) { ASSIGN_RAW_WRITE_MMIO_VFUNCS(uncore, vgpu); ASSIGN_RAW_READ_MMIO_VFUNCS(uncore, vgpu); - } else if (IS_GEN(uncore->i915, 5)) { + } else if (GRAPHICS_VER(uncore->i915) == 5) { ASSIGN_RAW_WRITE_MMIO_VFUNCS(uncore, gen5); ASSIGN_RAW_READ_MMIO_VFUNCS(uncore, gen5); } else { @@ -1870,7 +1870,7 @@ static int uncore_forcewake_init(struct intel_uncore *uncore) return ret; forcewake_early_sanitize(uncore, 0); - if (IS_GEN_RANGE(i915, 6, 7)) { + if (IS_GRAPHICS_VER(i915, 6, 7)) { ASSIGN_WRITE_MMIO_VFUNCS(uncore, gen6); if (IS_VALLEYVIEW(i915)) { @@ -1879,7 +1879,7 @@ static int uncore_forcewake_init(struct intel_uncore *uncore) } else { ASSIGN_READ_MMIO_VFUNCS(uncore, gen6); } - } else if (IS_GEN(i915, 8)) { + } else if (GRAPHICS_VER(i915) == 8) { if (IS_CHERRYVIEW(i915)) { ASSIGN_FW_DOMAINS_TABLE(uncore, __chv_fw_ranges); ASSIGN_WRITE_MMIO_VFUNCS(uncore, fwtable); @@ -1888,11 +1888,11 @@ static int uncore_forcewake_init(struct intel_uncore *uncore) ASSIGN_WRITE_MMIO_VFUNCS(uncore, gen8); ASSIGN_READ_MMIO_VFUNCS(uncore, gen6); } - } else if (IS_GEN_RANGE(i915, 9, 10)) { + } else if (IS_GRAPHICS_VER(i915, 9, 10)) { ASSIGN_FW_DOMAINS_TABLE(uncore, __gen9_fw_ranges); ASSIGN_WRITE_MMIO_VFUNCS(uncore, fwtable); ASSIGN_READ_MMIO_VFUNCS(uncore, fwtable); - } else if (IS_GEN(i915, 11)) { + } else if (GRAPHICS_VER(i915) == 11) { ASSIGN_FW_DOMAINS_TABLE(uncore, __gen11_fw_ranges); ASSIGN_WRITE_MMIO_VFUNCS(uncore, gen11_fwtable); ASSIGN_READ_MMIO_VFUNCS(uncore, gen11_fwtable); @@ -1952,7 +1952,7 @@ int intel_uncore_init_mmio(struct intel_uncore *uncore) if (IS_VALLEYVIEW(i915) || IS_CHERRYVIEW(i915)) uncore->flags |= UNCORE_HAS_DBG_UNCLAIMED; - if (IS_GEN_RANGE(i915, 6, 7)) + if (IS_GRAPHICS_VER(i915, 6, 7)) uncore->flags |= UNCORE_HAS_FIFO; /* clear out unclaimed reg detection bit */ @@ -1979,7 +1979,7 @@ void intel_uncore_prune_engine_fw_domains(struct intel_uncore *uncore, enum forcewake_domain_id domain_id; int i; - if (!intel_uncore_has_forcewake(uncore) || INTEL_GEN(uncore->i915) < 11) + if (!intel_uncore_has_forcewake(uncore) || GRAPHICS_VER(uncore->i915) < 11) return; for (i = 0; i < I915_MAX_VCS; i++) { diff --git a/drivers/gpu/drm/i915/intel_wopcm.c b/drivers/gpu/drm/i915/intel_wopcm.c index ec776591e1cf..8309455f13ea 100644 --- a/drivers/gpu/drm/i915/intel_wopcm.c +++ b/drivers/gpu/drm/i915/intel_wopcm.c @@ -81,7 +81,7 @@ void intel_wopcm_init_early(struct intel_wopcm *wopcm) if (!HAS_GT_UC(i915)) return; - if (INTEL_GEN(i915) >= 11) + if (GRAPHICS_VER(i915) >= 11) wopcm->size = GEN11_WOPCM_SIZE; else wopcm->size = GEN9_WOPCM_SIZE; @@ -93,7 +93,7 @@ static u32 context_reserved_size(struct drm_i915_private *i915) { if (IS_GEN9_LP(i915)) return BXT_WOPCM_RC6_CTX_RESERVED; - else if (INTEL_GEN(i915) >= 10) + else if (GRAPHICS_VER(i915) >= 10) return CNL_WOPCM_HW_CTX_RESERVED; else return 0; @@ -145,11 +145,11 @@ static bool check_hw_restrictions(struct drm_i915_private *i915, u32 guc_wopcm_base, u32 guc_wopcm_size, u32 huc_fw_size) { - if (IS_GEN(i915, 9) && !gen9_check_dword_gap(i915, guc_wopcm_base, - guc_wopcm_size)) + if (GRAPHICS_VER(i915) == 9 && !gen9_check_dword_gap(i915, guc_wopcm_base, + guc_wopcm_size)) return false; - if (IS_GEN(i915, 9) && + if (GRAPHICS_VER(i915) == 9 && !gen9_check_huc_fw_fits(i915, guc_wopcm_size, huc_fw_size)) return false; diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c index 0a1472bb12bc..f843a5040706 100644 --- a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c +++ b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c @@ -1884,9 +1884,9 @@ static int igt_cs_tlb(void *arg) u32 *cs = batch + i * 64 / sizeof(*cs); u64 addr = (vm->total - PAGE_SIZE) + i * sizeof(u32); - GEM_BUG_ON(INTEL_GEN(i915) < 6); + GEM_BUG_ON(GRAPHICS_VER(i915) < 6); cs[0] = MI_STORE_DWORD_IMM_GEN4; - if (INTEL_GEN(i915) >= 8) { + if (GRAPHICS_VER(i915) >= 8) { cs[1] = lower_32_bits(addr); cs[2] = upper_32_bits(addr); cs[3] = i; diff --git a/drivers/gpu/drm/i915/selftests/i915_perf.c b/drivers/gpu/drm/i915/selftests/i915_perf.c index bfb0290967a1..9e9a6cb1d9e5 100644 --- a/drivers/gpu/drm/i915/selftests/i915_perf.c +++ b/drivers/gpu/drm/i915/selftests/i915_perf.c @@ -98,7 +98,7 @@ test_stream(struct i915_perf *perf) I915_ENGINE_CLASS_RENDER, 0), .sample_flags = SAMPLE_OA_REPORT, - .oa_format = IS_GEN(perf->i915, 12) ? + .oa_format = GRAPHICS_VER(perf->i915) == 12 ? I915_OA_FORMAT_A32u40_A4u32_B8_C8 : I915_OA_FORMAT_C4_B8, }; struct i915_perf_stream *stream; @@ -162,7 +162,7 @@ static int write_timestamp(struct i915_request *rq, int slot) return PTR_ERR(cs); len = 5; - if (INTEL_GEN(rq->engine->i915) >= 8) + if (GRAPHICS_VER(rq->engine->i915) >= 8) len++; *cs++ = GFX_OP_PIPE_CONTROL(len); @@ -363,7 +363,7 @@ static int live_noa_gpr(void *arg) } cmd = MI_STORE_REGISTER_MEM; - if (INTEL_GEN(i915) >= 8) + if (GRAPHICS_VER(i915) >= 8) cmd++; cmd |= MI_USE_GGTT; diff --git a/drivers/gpu/drm/i915/selftests/i915_request.c b/drivers/gpu/drm/i915/selftests/i915_request.c index ee8e753d98ce..db367a6721c5 100644 --- a/drivers/gpu/drm/i915/selftests/i915_request.c +++ b/drivers/gpu/drm/i915/selftests/i915_request.c @@ -963,7 +963,7 @@ out_batch: static struct i915_vma *recursive_batch(struct drm_i915_private *i915) { struct drm_i915_gem_object *obj; - const int gen = INTEL_GEN(i915); + const int ver = GRAPHICS_VER(i915); struct i915_vma *vma; u32 *cmd; int err; @@ -988,11 +988,11 @@ static struct i915_vma *recursive_batch(struct drm_i915_private *i915) goto err; } - if (gen >= 8) { + if (ver >= 8) { *cmd++ = MI_BATCH_BUFFER_START | 1 << 8 | 1; *cmd++ = lower_32_bits(vma->node.start); *cmd++ = upper_32_bits(vma->node.start); - } else if (gen >= 6) { + } else if (ver >= 6) { *cmd++ = MI_BATCH_BUFFER_START | 1 << 8; *cmd++ = lower_32_bits(vma->node.start); } else { @@ -2482,7 +2482,7 @@ static int perf_request_latency(void *arg) struct pm_qos_request qos; int err = 0; - if (INTEL_GEN(i915) < 8) /* per-engine CS timestamp, semaphores */ + if (GRAPHICS_VER(i915) < 8) /* per-engine CS timestamp, semaphores */ return 0; cpu_latency_qos_add_request(&qos, 0); /* disable cstates */ diff --git a/drivers/gpu/drm/i915/selftests/igt_spinner.c b/drivers/gpu/drm/i915/selftests/igt_spinner.c index 5fe397b7d1d9..24d87d0fc747 100644 --- a/drivers/gpu/drm/i915/selftests/igt_spinner.c +++ b/drivers/gpu/drm/i915/selftests/igt_spinner.c @@ -174,15 +174,15 @@ igt_spinner_create_request(struct igt_spinner *spin, batch = spin->batch; - if (INTEL_GEN(rq->engine->i915) >= 8) { + if (GRAPHICS_VER(rq->engine->i915) >= 8) { *batch++ = MI_STORE_DWORD_IMM_GEN4; *batch++ = lower_32_bits(hws_address(hws, rq)); *batch++ = upper_32_bits(hws_address(hws, rq)); - } else if (INTEL_GEN(rq->engine->i915) >= 6) { + } else if (GRAPHICS_VER(rq->engine->i915) >= 6) { *batch++ = MI_STORE_DWORD_IMM_GEN4; *batch++ = 0; *batch++ = hws_address(hws, rq); - } else if (INTEL_GEN(rq->engine->i915) >= 4) { + } else if (GRAPHICS_VER(rq->engine->i915) >= 4) { *batch++ = MI_STORE_DWORD_IMM_GEN4 | MI_USE_GGTT; *batch++ = 0; *batch++ = hws_address(hws, rq); @@ -194,11 +194,11 @@ igt_spinner_create_request(struct igt_spinner *spin, *batch++ = arbitration_command; - if (INTEL_GEN(rq->engine->i915) >= 8) + if (GRAPHICS_VER(rq->engine->i915) >= 8) *batch++ = MI_BATCH_BUFFER_START | BIT(8) | 1; else if (IS_HASWELL(rq->engine->i915)) *batch++ = MI_BATCH_BUFFER_START | MI_BATCH_PPGTT_HSW; - else if (INTEL_GEN(rq->engine->i915) >= 6) + else if (GRAPHICS_VER(rq->engine->i915) >= 6) *batch++ = MI_BATCH_BUFFER_START; else *batch++ = MI_BATCH_BUFFER_START | MI_BATCH_GTT; @@ -216,7 +216,7 @@ igt_spinner_create_request(struct igt_spinner *spin, } flags = 0; - if (INTEL_GEN(rq->engine->i915) <= 5) + if (GRAPHICS_VER(rq->engine->i915) <= 5) flags |= I915_DISPATCH_SECURE; err = engine->emit_bb_start(rq, vma->node.start, PAGE_SIZE, flags); diff --git a/drivers/gpu/drm/i915/selftests/intel_uncore.c b/drivers/gpu/drm/i915/selftests/intel_uncore.c index f76c9bcec735..8ef9e6a4ad05 100644 --- a/drivers/gpu/drm/i915/selftests/intel_uncore.c +++ b/drivers/gpu/drm/i915/selftests/intel_uncore.c @@ -321,7 +321,7 @@ static int live_fw_table(void *arg) /* Confirm the table we load is still valid */ return intel_fw_table_check(gt->uncore->fw_domains_table, gt->uncore->fw_domains_table_entries, - INTEL_GEN(gt->i915) >= 9); + GRAPHICS_VER(gt->i915) >= 9); } int intel_uncore_live_selftests(struct drm_i915_private *i915) diff --git a/drivers/gpu/drm/mediatek/mtk_disp_color.c b/drivers/gpu/drm/mediatek/mtk_disp_color.c index 63f411ab393b..6f4c80bbc0eb 100644 --- a/drivers/gpu/drm/mediatek/mtk_disp_color.c +++ b/drivers/gpu/drm/mediatek/mtk_disp_color.c @@ -30,9 +30,8 @@ struct mtk_disp_color_data { unsigned int color_offset; }; -/** +/* * struct mtk_disp_color - DISP_COLOR driver structure - * @ddp_comp: structure containing type enum and hardware resources * @crtc: associated crtc to report irq events to * @data: platform colour driver data */ diff --git a/drivers/gpu/drm/mediatek/mtk_disp_gamma.c b/drivers/gpu/drm/mediatek/mtk_disp_gamma.c index 3ebf91e0ab41..3a5815ab4079 100644 --- a/drivers/gpu/drm/mediatek/mtk_disp_gamma.c +++ b/drivers/gpu/drm/mediatek/mtk_disp_gamma.c @@ -29,10 +29,8 @@ struct mtk_disp_gamma_data { bool has_dither; }; -/** +/* * struct mtk_disp_gamma - DISP_GAMMA driver structure - * @ddp_comp - structure containing type enum and hardware resources - * @crtc - associated crtc to report irq events to */ struct mtk_disp_gamma { struct clk *clk; diff --git a/drivers/gpu/drm/mediatek/mtk_disp_ovl.c b/drivers/gpu/drm/mediatek/mtk_disp_ovl.c index 961f87f8d4d1..fa9d79963cd3 100644 --- a/drivers/gpu/drm/mediatek/mtk_disp_ovl.c +++ b/drivers/gpu/drm/mediatek/mtk_disp_ovl.c @@ -66,9 +66,8 @@ struct mtk_disp_ovl_data { bool smi_id_en; }; -/** +/* * struct mtk_disp_ovl - DISP_OVL driver structure - * @ddp_comp: structure containing type enum and hardware resources * @crtc: associated crtc to report vblank events to * @data: platform data */ diff --git a/drivers/gpu/drm/mediatek/mtk_disp_rdma.c b/drivers/gpu/drm/mediatek/mtk_disp_rdma.c index 728aaadfea8c..705f28ceb4dd 100644 --- a/drivers/gpu/drm/mediatek/mtk_disp_rdma.c +++ b/drivers/gpu/drm/mediatek/mtk_disp_rdma.c @@ -55,10 +55,8 @@ struct mtk_disp_rdma_data { unsigned int fifo_size; }; -/** +/* * struct mtk_disp_rdma - DISP_RDMA driver structure - * @ddp_comp: structure containing type enum and hardware resources - * @crtc: associated crtc to report irq events to * @data: local driver data */ struct mtk_disp_rdma { diff --git a/drivers/gpu/drm/msm/Kconfig b/drivers/gpu/drm/msm/Kconfig index 10f693ea89d3..52536e7adb95 100644 --- a/drivers/gpu/drm/msm/Kconfig +++ b/drivers/gpu/drm/msm/Kconfig @@ -7,6 +7,8 @@ config DRM_MSM depends on IOMMU_SUPPORT depends on OF && COMMON_CLK depends on QCOM_OCMEM || QCOM_OCMEM=n + depends on QCOM_LLCC || QCOM_LLCC=n + depends on QCOM_COMMAND_DB || QCOM_COMMAND_DB=n select IOMMU_IO_PGTABLE select QCOM_MDT_LOADER if ARCH_QCOM select REGULATOR @@ -15,7 +17,6 @@ config DRM_MSM select SHMEM select TMPFS select QCOM_SCM if ARCH_QCOM - select QCOM_COMMAND_DB if ARCH_QCOM select WANT_DEV_COREDUMP select SND_SOC_HDMI_CODEC if SND_SOC select SYNC_FILE diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c index 56df86e5f740..a94a43de95ef 100644 --- a/drivers/gpu/drm/msm/msm_gem.c +++ b/drivers/gpu/drm/msm/msm_gem.c @@ -817,9 +817,9 @@ int msm_gem_sync_object(struct drm_gem_object *obj, struct dma_fence *fence; int i, ret; - fobj = dma_resv_get_list(obj->resv); + fobj = dma_resv_shared_list(obj->resv); if (!fobj || (fobj->shared_count == 0)) { - fence = dma_resv_get_excl(obj->resv); + fence = dma_resv_excl_fence(obj->resv); /* don't need to wait on our own fences, since ring is fifo */ if (fence && (fence->context != fctx->context)) { ret = dma_fence_wait(fence, true); @@ -915,8 +915,7 @@ int msm_gem_cpu_prep(struct drm_gem_object *obj, uint32_t op, ktime_t *timeout) op & MSM_PREP_NOSYNC ? 0 : timeout_to_jiffies(timeout); long ret; - ret = dma_resv_wait_timeout_rcu(obj->resv, write, - true, remain); + ret = dma_resv_wait_timeout(obj->resv, write, true, remain); if (ret == 0) return remain == 0 ? -EBUSY : -ETIMEDOUT; else if (ret < 0) @@ -1025,7 +1024,7 @@ void msm_gem_describe(struct drm_gem_object *obj, struct seq_file *m, } rcu_read_lock(); - fobj = rcu_dereference(robj->fence); + fobj = dma_resv_shared_list(robj); if (fobj) { unsigned int i, shared_count = fobj->shared_count; @@ -1035,7 +1034,7 @@ void msm_gem_describe(struct drm_gem_object *obj, struct seq_file *m, } } - fence = rcu_dereference(robj->fence_excl); + fence = dma_resv_excl_fence(robj); if (fence) describe_fence(fence, "Exclusive", m); rcu_read_unlock(); diff --git a/drivers/gpu/drm/nouveau/dispnv50/wndw.c b/drivers/gpu/drm/nouveau/dispnv50/wndw.c index 0cb1f9d848d3..8d048bacd6f0 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/wndw.c +++ b/drivers/gpu/drm/nouveau/dispnv50/wndw.c @@ -561,7 +561,7 @@ nv50_wndw_prepare_fb(struct drm_plane *plane, struct drm_plane_state *state) asyw->image.handle[0] = ctxdma->object.handle; } - asyw->state.fence = dma_resv_get_excl_rcu(nvbo->bo.base.resv); + asyw->state.fence = dma_resv_get_excl_unlocked(nvbo->bo.base.resv); asyw->image.offset[0] = nvbo->offset; if (wndw->func->prepare) { diff --git a/drivers/gpu/drm/nouveau/nouveau_abi16.c b/drivers/gpu/drm/nouveau/nouveau_abi16.c index 0a9334deffe2..b45ec3086285 100644 --- a/drivers/gpu/drm/nouveau/nouveau_abi16.c +++ b/drivers/gpu/drm/nouveau/nouveau_abi16.c @@ -312,7 +312,7 @@ nouveau_abi16_ioctl_channel_alloc(ABI16_IOCTL_ARGS) init->pushbuf_domains = NOUVEAU_GEM_DOMAIN_VRAM | NOUVEAU_GEM_DOMAIN_GART; else - if (chan->chan->push.buffer->bo.mem.mem_type == TTM_PL_VRAM) + if (chan->chan->push.buffer->bo.resource->mem_type == TTM_PL_VRAM) init->pushbuf_domains = NOUVEAU_GEM_DOMAIN_VRAM; else init->pushbuf_domains = NOUVEAU_GEM_DOMAIN_GART; diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c index c390f24f25f3..520b1ea9d16c 100644 --- a/drivers/gpu/drm/nouveau/nouveau_bo.c +++ b/drivers/gpu/drm/nouveau/nouveau_bo.c @@ -433,7 +433,7 @@ nouveau_bo_pin(struct nouveau_bo *nvbo, uint32_t domain, bool contig) if (nvbo->bo.pin_count) { bool error = evict; - switch (bo->mem.mem_type) { + switch (bo->resource->mem_type) { case TTM_PL_VRAM: error |= !(domain & NOUVEAU_GEM_DOMAIN_VRAM); break; @@ -446,7 +446,7 @@ nouveau_bo_pin(struct nouveau_bo *nvbo, uint32_t domain, bool contig) if (error) { NV_ERROR(drm, "bo %p pinned elsewhere: " "0x%08x vs 0x%08x\n", bo, - bo->mem.mem_type, domain); + bo->resource->mem_type, domain); ret = -EBUSY; } ttm_bo_pin(&nvbo->bo); @@ -467,7 +467,7 @@ nouveau_bo_pin(struct nouveau_bo *nvbo, uint32_t domain, bool contig) ttm_bo_pin(&nvbo->bo); - switch (bo->mem.mem_type) { + switch (bo->resource->mem_type) { case TTM_PL_VRAM: drm->gem.vram_available -= bo->base.size; break; @@ -498,7 +498,7 @@ nouveau_bo_unpin(struct nouveau_bo *nvbo) ttm_bo_unpin(&nvbo->bo); if (!nvbo->bo.pin_count) { - switch (bo->mem.mem_type) { + switch (bo->resource->mem_type) { case TTM_PL_VRAM: drm->gem.vram_available += bo->base.size; break; @@ -523,7 +523,7 @@ nouveau_bo_map(struct nouveau_bo *nvbo) if (ret) return ret; - ret = ttm_bo_kmap(&nvbo->bo, 0, nvbo->bo.mem.num_pages, &nvbo->kmap); + ret = ttm_bo_kmap(&nvbo->bo, 0, nvbo->bo.resource->num_pages, &nvbo->kmap); ttm_bo_unreserve(&nvbo->bo); return ret; @@ -737,7 +737,7 @@ nouveau_bo_evict_flags(struct ttm_buffer_object *bo, struct ttm_placement *pl) { struct nouveau_bo *nvbo = nouveau_bo(bo); - switch (bo->mem.mem_type) { + switch (bo->resource->mem_type) { case TTM_PL_VRAM: nouveau_bo_placement_set(nvbo, NOUVEAU_GEM_DOMAIN_GART, NOUVEAU_GEM_DOMAIN_CPU); @@ -754,7 +754,7 @@ static int nouveau_bo_move_prep(struct nouveau_drm *drm, struct ttm_buffer_object *bo, struct ttm_resource *reg) { - struct nouveau_mem *old_mem = nouveau_mem(&bo->mem); + struct nouveau_mem *old_mem = nouveau_mem(bo->resource); struct nouveau_mem *new_mem = nouveau_mem(reg); struct nvif_vmm *vmm = &drm->client.vmm.vmm; int ret; @@ -809,7 +809,7 @@ nouveau_bo_move_m2mf(struct ttm_buffer_object *bo, int evict, mutex_lock_nested(&cli->mutex, SINGLE_DEPTH_NESTING); ret = nouveau_fence_sync(nouveau_bo(bo), chan, true, ctx->interruptible); if (ret == 0) { - ret = drm->ttm.move(chan, bo, &bo->mem, new_reg); + ret = drm->ttm.move(chan, bo, bo->resource, new_reg); if (ret == 0) { ret = nouveau_fence_new(chan, false, &fence); if (ret == 0) { @@ -918,12 +918,8 @@ static void nouveau_bo_move_ntfy(struct ttm_buffer_object *bo, } } - if (new_reg) { - if (new_reg->mm_node) - nvbo->offset = (new_reg->start << PAGE_SHIFT); - else - nvbo->offset = 0; - } + if (new_reg) + nvbo->offset = (new_reg->start << PAGE_SHIFT); } @@ -955,7 +951,7 @@ nouveau_bo_vm_cleanup(struct ttm_buffer_object *bo, { struct nouveau_drm *drm = nouveau_bdev(bo->bdev); struct drm_device *dev = drm->dev; - struct dma_fence *fence = dma_resv_get_excl(bo->base.resv); + struct dma_fence *fence = dma_resv_excl_fence(bo->base.resv); nv10_bo_put_tile_region(dev, *old_tile, fence); *old_tile = new_tile; @@ -969,7 +965,7 @@ nouveau_bo_move(struct ttm_buffer_object *bo, bool evict, { struct nouveau_drm *drm = nouveau_bdev(bo->bdev); struct nouveau_bo *nvbo = nouveau_bo(bo); - struct ttm_resource *old_reg = &bo->mem; + struct ttm_resource *old_reg = bo->resource; struct nouveau_drm_tile *new_tile = NULL; int ret = 0; @@ -1009,7 +1005,7 @@ nouveau_bo_move(struct ttm_buffer_object *bo, bool evict, if (old_reg->mem_type == TTM_PL_TT && new_reg->mem_type == TTM_PL_SYSTEM) { nouveau_ttm_tt_unbind(bo->bdev, bo->ttm); - ttm_resource_free(bo, &bo->mem); + ttm_resource_free(bo, &bo->resource); ttm_bo_assign_mem(bo, new_reg); goto out; } @@ -1045,7 +1041,7 @@ out: } out_ntfy: if (ret) { - nouveau_bo_move_ntfy(bo, &bo->mem); + nouveau_bo_move_ntfy(bo, bo->resource); } return ret; } @@ -1170,7 +1166,7 @@ out: list_del_init(&nvbo->io_reserve_lru); drm_vma_node_unmap(&nvbo->bo.base.vma_node, bdev->dev_mapping); - nouveau_ttm_io_mem_free_locked(drm, &nvbo->bo.mem); + nouveau_ttm_io_mem_free_locked(drm, nvbo->bo.resource); goto retry; } @@ -1200,12 +1196,12 @@ vm_fault_t nouveau_ttm_fault_reserve_notify(struct ttm_buffer_object *bo) /* as long as the bo isn't in vram, and isn't tiled, we've got * nothing to do here. */ - if (bo->mem.mem_type != TTM_PL_VRAM) { + if (bo->resource->mem_type != TTM_PL_VRAM) { if (drm->client.device.info.family < NV_DEVICE_INFO_V0_TESLA || !nvbo->kind) return 0; - if (bo->mem.mem_type != TTM_PL_SYSTEM) + if (bo->resource->mem_type != TTM_PL_SYSTEM) return 0; nouveau_bo_placement_set(nvbo, NOUVEAU_GEM_DOMAIN_GART, 0); @@ -1213,7 +1209,7 @@ vm_fault_t nouveau_ttm_fault_reserve_notify(struct ttm_buffer_object *bo) } else { /* make sure bo is in mappable vram */ if (drm->client.device.info.family >= NV_DEVICE_INFO_V0_TESLA || - bo->mem.start + bo->mem.num_pages < mappable) + bo->resource->start + bo->resource->num_pages < mappable) return 0; for (i = 0; i < nvbo->placement.num_placement; ++i) { diff --git a/drivers/gpu/drm/nouveau/nouveau_chan.c b/drivers/gpu/drm/nouveau/nouveau_chan.c index 7cfac265fd45..40362600eed2 100644 --- a/drivers/gpu/drm/nouveau/nouveau_chan.c +++ b/drivers/gpu/drm/nouveau/nouveau_chan.c @@ -212,7 +212,7 @@ nouveau_channel_prep(struct nouveau_drm *drm, struct nvif_device *device, args.start = 0; args.limit = chan->vmm->vmm.limit - 1; } else - if (chan->push.buffer->bo.mem.mem_type == TTM_PL_VRAM) { + if (chan->push.buffer->bo.resource->mem_type == TTM_PL_VRAM) { if (device->info.family == NV_DEVICE_INFO_V0_TNT) { /* nv04 vram pushbuf hack, retarget to its location in * the framebuffer bar rather than direct vram access.. diff --git a/drivers/gpu/drm/nouveau/nouveau_fbcon.c b/drivers/gpu/drm/nouveau/nouveau_fbcon.c index 93ac78bda750..4f9b3aa5deda 100644 --- a/drivers/gpu/drm/nouveau/nouveau_fbcon.c +++ b/drivers/gpu/drm/nouveau/nouveau_fbcon.c @@ -378,7 +378,7 @@ nouveau_fbcon_create(struct drm_fb_helper *helper, FBINFO_HWACCEL_FILLRECT | FBINFO_HWACCEL_IMAGEBLIT; info->fbops = &nouveau_fbcon_sw_ops; - info->fix.smem_start = nvbo->bo.mem.bus.offset; + info->fix.smem_start = nvbo->bo.resource->bus.offset; info->fix.smem_len = nvbo->bo.base.size; info->screen_base = nvbo_kmap_obj_iovirtual(nvbo); diff --git a/drivers/gpu/drm/nouveau/nouveau_fence.c b/drivers/gpu/drm/nouveau/nouveau_fence.c index e5dcbf67de7e..6b43918035df 100644 --- a/drivers/gpu/drm/nouveau/nouveau_fence.c +++ b/drivers/gpu/drm/nouveau/nouveau_fence.c @@ -355,8 +355,8 @@ nouveau_fence_sync(struct nouveau_bo *nvbo, struct nouveau_channel *chan, bool e return ret; } - fobj = dma_resv_get_list(resv); - fence = dma_resv_get_excl(resv); + fobj = dma_resv_shared_list(resv); + fence = dma_resv_excl_fence(resv); if (fence && (!exclusive || !fobj || !fobj->shared_count)) { struct nouveau_channel *prev = NULL; diff --git a/drivers/gpu/drm/nouveau/nouveau_gem.c b/drivers/gpu/drm/nouveau/nouveau_gem.c index 722e1decc202..5b27845075a1 100644 --- a/drivers/gpu/drm/nouveau/nouveau_gem.c +++ b/drivers/gpu/drm/nouveau/nouveau_gem.c @@ -276,7 +276,7 @@ nouveau_gem_info(struct drm_file *file_priv, struct drm_gem_object *gem, if (is_power_of_2(nvbo->valid_domains)) rep->domain = nvbo->valid_domains; - else if (nvbo->bo.mem.mem_type == TTM_PL_TT) + else if (nvbo->bo.resource->mem_type == TTM_PL_TT) rep->domain = NOUVEAU_GEM_DOMAIN_GART; else rep->domain = NOUVEAU_GEM_DOMAIN_VRAM; @@ -347,11 +347,11 @@ nouveau_gem_set_domain(struct drm_gem_object *gem, uint32_t read_domains, valid_domains &= ~(NOUVEAU_GEM_DOMAIN_VRAM | NOUVEAU_GEM_DOMAIN_GART); if ((domains & NOUVEAU_GEM_DOMAIN_VRAM) && - bo->mem.mem_type == TTM_PL_VRAM) + bo->resource->mem_type == TTM_PL_VRAM) pref_domains |= NOUVEAU_GEM_DOMAIN_VRAM; else if ((domains & NOUVEAU_GEM_DOMAIN_GART) && - bo->mem.mem_type == TTM_PL_TT) + bo->resource->mem_type == TTM_PL_TT) pref_domains |= NOUVEAU_GEM_DOMAIN_GART; else if (domains & NOUVEAU_GEM_DOMAIN_VRAM) @@ -561,13 +561,13 @@ validate_list(struct nouveau_channel *chan, struct nouveau_cli *cli, if (drm->client.device.info.family < NV_DEVICE_INFO_V0_TESLA) { if (nvbo->offset == b->presumed.offset && - ((nvbo->bo.mem.mem_type == TTM_PL_VRAM && + ((nvbo->bo.resource->mem_type == TTM_PL_VRAM && b->presumed.domain & NOUVEAU_GEM_DOMAIN_VRAM) || - (nvbo->bo.mem.mem_type == TTM_PL_TT && + (nvbo->bo.resource->mem_type == TTM_PL_TT && b->presumed.domain & NOUVEAU_GEM_DOMAIN_GART))) continue; - if (nvbo->bo.mem.mem_type == TTM_PL_TT) + if (nvbo->bo.resource->mem_type == TTM_PL_TT) b->presumed.domain = NOUVEAU_GEM_DOMAIN_GART; else b->presumed.domain = NOUVEAU_GEM_DOMAIN_VRAM; @@ -681,7 +681,7 @@ nouveau_gem_pushbuf_reloc_apply(struct nouveau_cli *cli, } if (!nvbo->kmap.virtual) { - ret = ttm_bo_kmap(&nvbo->bo, 0, nvbo->bo.mem.num_pages, + ret = ttm_bo_kmap(&nvbo->bo, 0, nvbo->bo.resource->num_pages, &nvbo->kmap); if (ret) { NV_PRINTK(err, cli, "failed kmap for reloc\n"); @@ -870,7 +870,7 @@ revalidate: if (unlikely(cmd != req->suffix0)) { if (!nvbo->kmap.virtual) { ret = ttm_bo_kmap(&nvbo->bo, 0, - nvbo->bo.mem. + nvbo->bo.resource-> num_pages, &nvbo->kmap); if (ret) { @@ -964,8 +964,8 @@ nouveau_gem_ioctl_cpu_prep(struct drm_device *dev, void *data, return -ENOENT; nvbo = nouveau_gem_object(gem); - lret = dma_resv_wait_timeout_rcu(nvbo->bo.base.resv, write, true, - no_wait ? 0 : 30 * HZ); + lret = dma_resv_wait_timeout(nvbo->bo.base.resv, write, true, + no_wait ? 0 : 30 * HZ); if (!lret) ret = -EBUSY; else if (lret > 0) diff --git a/drivers/gpu/drm/nouveau/nouveau_mem.c b/drivers/gpu/drm/nouveau/nouveau_mem.c index a1049e9feee1..0de6549fb875 100644 --- a/drivers/gpu/drm/nouveau/nouveau_mem.c +++ b/drivers/gpu/drm/nouveau/nouveau_mem.c @@ -178,25 +178,24 @@ void nouveau_mem_del(struct ttm_resource *reg) { struct nouveau_mem *mem = nouveau_mem(reg); - if (!mem) - return; + nouveau_mem_fini(mem); - kfree(reg->mm_node); - reg->mm_node = NULL; + kfree(mem); } int nouveau_mem_new(struct nouveau_cli *cli, u8 kind, u8 comp, - struct ttm_resource *reg) + struct ttm_resource **res) { struct nouveau_mem *mem; if (!(mem = kzalloc(sizeof(*mem), GFP_KERNEL))) return -ENOMEM; + mem->cli = cli; mem->kind = kind; mem->comp = comp; - reg->mm_node = mem; + *res = &mem->base; return 0; } diff --git a/drivers/gpu/drm/nouveau/nouveau_mem.h b/drivers/gpu/drm/nouveau/nouveau_mem.h index 7df3848e85aa..2c01166a90f2 100644 --- a/drivers/gpu/drm/nouveau/nouveau_mem.h +++ b/drivers/gpu/drm/nouveau/nouveau_mem.h @@ -6,13 +6,8 @@ struct ttm_tt; #include <nvif/mem.h> #include <nvif/vmm.h> -static inline struct nouveau_mem * -nouveau_mem(struct ttm_resource *reg) -{ - return reg->mm_node; -} - struct nouveau_mem { + struct ttm_resource base; struct nouveau_cli *cli; u8 kind; u8 comp; @@ -20,8 +15,14 @@ struct nouveau_mem { struct nvif_vma vma[2]; }; +static inline struct nouveau_mem * +nouveau_mem(struct ttm_resource *reg) +{ + return container_of(reg, struct nouveau_mem, base); +} + int nouveau_mem_new(struct nouveau_cli *, u8 kind, u8 comp, - struct ttm_resource *); + struct ttm_resource **); void nouveau_mem_del(struct ttm_resource *); int nouveau_mem_vram(struct ttm_resource *, bool contig, u8 page); int nouveau_mem_host(struct ttm_resource *, struct ttm_tt *); diff --git a/drivers/gpu/drm/nouveau/nouveau_ttm.c b/drivers/gpu/drm/nouveau/nouveau_ttm.c index 65430912ff72..f4c2e46b6fe1 100644 --- a/drivers/gpu/drm/nouveau/nouveau_ttm.c +++ b/drivers/gpu/drm/nouveau/nouveau_ttm.c @@ -26,6 +26,8 @@ #include <linux/limits.h> #include <linux/swiotlb.h> +#include <drm/ttm/ttm_range_manager.h> + #include "nouveau_drv.h" #include "nouveau_gem.h" #include "nouveau_mem.h" @@ -43,7 +45,7 @@ static int nouveau_vram_manager_new(struct ttm_resource_manager *man, struct ttm_buffer_object *bo, const struct ttm_place *place, - struct ttm_resource *reg) + struct ttm_resource **res) { struct nouveau_bo *nvbo = nouveau_bo(bo); struct nouveau_drm *drm = nouveau_bdev(bo->bdev); @@ -52,13 +54,15 @@ nouveau_vram_manager_new(struct ttm_resource_manager *man, if (drm->client.device.info.ram_size == 0) return -ENOMEM; - ret = nouveau_mem_new(&drm->master, nvbo->kind, nvbo->comp, reg); + ret = nouveau_mem_new(&drm->master, nvbo->kind, nvbo->comp, res); if (ret) return ret; - ret = nouveau_mem_vram(reg, nvbo->contig, nvbo->page); + ttm_resource_init(bo, place, *res); + + ret = nouveau_mem_vram(*res, nvbo->contig, nvbo->page); if (ret) { - nouveau_mem_del(reg); + nouveau_mem_del(*res); return ret; } @@ -74,17 +78,18 @@ static int nouveau_gart_manager_new(struct ttm_resource_manager *man, struct ttm_buffer_object *bo, const struct ttm_place *place, - struct ttm_resource *reg) + struct ttm_resource **res) { struct nouveau_bo *nvbo = nouveau_bo(bo); struct nouveau_drm *drm = nouveau_bdev(bo->bdev); int ret; - ret = nouveau_mem_new(&drm->master, nvbo->kind, nvbo->comp, reg); + ret = nouveau_mem_new(&drm->master, nvbo->kind, nvbo->comp, res); if (ret) return ret; - reg->start = 0; + ttm_resource_init(bo, place, *res); + (*res)->start = 0; return 0; } @@ -97,26 +102,27 @@ static int nv04_gart_manager_new(struct ttm_resource_manager *man, struct ttm_buffer_object *bo, const struct ttm_place *place, - struct ttm_resource *reg) + struct ttm_resource **res) { struct nouveau_bo *nvbo = nouveau_bo(bo); struct nouveau_drm *drm = nouveau_bdev(bo->bdev); struct nouveau_mem *mem; int ret; - ret = nouveau_mem_new(&drm->master, nvbo->kind, nvbo->comp, reg); - mem = nouveau_mem(reg); + ret = nouveau_mem_new(&drm->master, nvbo->kind, nvbo->comp, res); if (ret) return ret; + mem = nouveau_mem(*res); + ttm_resource_init(bo, place, *res); ret = nvif_vmm_get(&mem->cli->vmm.vmm, PTES, false, 12, 0, - (long)reg->num_pages << PAGE_SHIFT, &mem->vma[0]); + (long)(*res)->num_pages << PAGE_SHIFT, &mem->vma[0]); if (ret) { - nouveau_mem_del(reg); + nouveau_mem_del(*res); return ret; } - reg->start = mem->vma[0].addr >> PAGE_SHIFT; + (*res)->start = mem->vma[0].addr >> PAGE_SHIFT; return 0; } diff --git a/drivers/gpu/drm/nouveau/nouveau_vmm.c b/drivers/gpu/drm/nouveau/nouveau_vmm.c index a49e88129c92..67d6619fcd5e 100644 --- a/drivers/gpu/drm/nouveau/nouveau_vmm.c +++ b/drivers/gpu/drm/nouveau/nouveau_vmm.c @@ -77,7 +77,7 @@ int nouveau_vma_new(struct nouveau_bo *nvbo, struct nouveau_vmm *vmm, struct nouveau_vma **pvma) { - struct nouveau_mem *mem = nouveau_mem(&nvbo->bo.mem); + struct nouveau_mem *mem = nouveau_mem(nvbo->bo.resource); struct nouveau_vma *vma; struct nvif_vma tmp; int ret; @@ -96,7 +96,7 @@ nouveau_vma_new(struct nouveau_bo *nvbo, struct nouveau_vmm *vmm, vma->fence = NULL; list_add_tail(&vma->head, &nvbo->vma_list); - if (nvbo->bo.mem.mem_type != TTM_PL_SYSTEM && + if (nvbo->bo.resource->mem_type != TTM_PL_SYSTEM && mem->mem.page == nvbo->page) { ret = nvif_vmm_get(&vmm->vmm, LAZY, false, mem->mem.page, 0, mem->mem.size, &tmp); diff --git a/drivers/gpu/drm/nouveau/nv17_fence.c b/drivers/gpu/drm/nouveau/nv17_fence.c index b1cd8d7dd87d..07c2e0878c24 100644 --- a/drivers/gpu/drm/nouveau/nv17_fence.c +++ b/drivers/gpu/drm/nouveau/nv17_fence.c @@ -77,8 +77,8 @@ static int nv17_fence_context_new(struct nouveau_channel *chan) { struct nv10_fence_priv *priv = chan->drm->fence; + struct ttm_resource *reg = priv->bo->bo.resource; struct nv10_fence_chan *fctx; - struct ttm_resource *reg = &priv->bo->bo.mem; u32 start = reg->start * PAGE_SIZE; u32 limit = start + priv->bo->bo.base.size - 1; int ret = 0; diff --git a/drivers/gpu/drm/nouveau/nv50_fence.c b/drivers/gpu/drm/nouveau/nv50_fence.c index 1625826505f6..ea1e1f480bfe 100644 --- a/drivers/gpu/drm/nouveau/nv50_fence.c +++ b/drivers/gpu/drm/nouveau/nv50_fence.c @@ -37,7 +37,7 @@ nv50_fence_context_new(struct nouveau_channel *chan) { struct nv10_fence_priv *priv = chan->drm->fence; struct nv10_fence_chan *fctx; - struct ttm_resource *reg = &priv->bo->bo.mem; + struct ttm_resource *reg = priv->bo->bo.resource; u32 start = reg->start * PAGE_SIZE; u32 limit = start + priv->bo->bo.base.size - 1; int ret; diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/mc/tu102.c b/drivers/gpu/drm/nouveau/nvkm/subdev/mc/tu102.c index 58db83ebadc5..a96084b34a78 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/mc/tu102.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/mc/tu102.c @@ -46,7 +46,7 @@ tu102_mc_intr_update(struct tu102_mc *mc) nvkm_wr32(device, 0xb81610, 0x6); } -void +static void tu102_mc_intr_unarm(struct nvkm_mc *base) { struct tu102_mc *mc = tu102_mc(base); @@ -58,7 +58,7 @@ tu102_mc_intr_unarm(struct nvkm_mc *base) spin_unlock_irqrestore(&mc->lock, flags); } -void +static void tu102_mc_intr_rearm(struct nvkm_mc *base) { struct tu102_mc *mc = tu102_mc(base); @@ -70,7 +70,7 @@ tu102_mc_intr_rearm(struct nvkm_mc *base) spin_unlock_irqrestore(&mc->lock, flags); } -void +static void tu102_mc_intr_mask(struct nvkm_mc *base, u32 mask, u32 intr) { struct tu102_mc *mc = tu102_mc(base); diff --git a/drivers/gpu/drm/panel/panel-elida-kd35t133.c b/drivers/gpu/drm/panel/panel-elida-kd35t133.c index fe5ac3ef9018..4787f0833264 100644 --- a/drivers/gpu/drm/panel/panel-elida-kd35t133.c +++ b/drivers/gpu/drm/panel/panel-elida-kd35t133.c @@ -42,6 +42,7 @@ struct kd35t133 { struct gpio_desc *reset_gpio; struct regulator *vdd; struct regulator *iovcc; + enum drm_panel_orientation orientation; bool prepared; }; @@ -216,6 +217,7 @@ static int kd35t133_get_modes(struct drm_panel *panel, connector->display_info.width_mm = mode->width_mm; connector->display_info.height_mm = mode->height_mm; drm_mode_probed_add(connector, mode); + drm_connector_set_panel_orientation(connector, ctx->orientation); return 1; } @@ -258,6 +260,12 @@ static int kd35t133_probe(struct mipi_dsi_device *dsi) return ret; } + ret = of_drm_get_panel_orientation(dev->of_node, &ctx->orientation); + if (ret < 0) { + dev_err(dev, "%pOF: failed to get orientation %d\n", dev->of_node, ret); + return ret; + } + mipi_dsi_set_drvdata(dsi, ctx); ctx->dev = dev; diff --git a/drivers/gpu/drm/panel/panel-raspberrypi-touchscreen.c b/drivers/gpu/drm/panel/panel-raspberrypi-touchscreen.c index 5e9ccefb88f6..2229f1af2ca8 100644 --- a/drivers/gpu/drm/panel/panel-raspberrypi-touchscreen.c +++ b/drivers/gpu/drm/panel/panel-raspberrypi-touchscreen.c @@ -29,7 +29,7 @@ * DEALINGS IN THE SOFTWARE. */ -/** +/* * Raspberry Pi 7" touchscreen panel driver. * * The 7" touchscreen consists of a DPI LCD panel, a Toshiba diff --git a/drivers/gpu/drm/panel/panel-sitronix-st7701.c b/drivers/gpu/drm/panel/panel-sitronix-st7701.c index 4d2a149b202c..320a2a8fd459 100644 --- a/drivers/gpu/drm/panel/panel-sitronix-st7701.c +++ b/drivers/gpu/drm/panel/panel-sitronix-st7701.c @@ -38,7 +38,7 @@ #define DSI_CMD2_BK1_SPD2 0xC2 /* Source EQ2 Setting */ #define DSI_CMD2_BK1_MIPISET1 0xD0 /* MIPI Setting 1 */ -/** +/* * Command2 with BK function selection. * * BIT[4, 0]: [CN2, BKXSEL] diff --git a/drivers/gpu/drm/panfrost/panfrost_device.h b/drivers/gpu/drm/panfrost/panfrost_device.h index 597cf1459b0a..f614e98771e4 100644 --- a/drivers/gpu/drm/panfrost/panfrost_device.h +++ b/drivers/gpu/drm/panfrost/panfrost_device.h @@ -45,6 +45,7 @@ struct panfrost_features { u32 thread_max_workgroup_sz; u32 thread_max_barrier_sz; u32 coherency_features; + u32 afbc_features; u32 texture_features[4]; u32 js_features[16]; diff --git a/drivers/gpu/drm/panfrost/panfrost_drv.c b/drivers/gpu/drm/panfrost/panfrost_drv.c index ca07098a6141..075ec0ef746c 100644 --- a/drivers/gpu/drm/panfrost/panfrost_drv.c +++ b/drivers/gpu/drm/panfrost/panfrost_drv.c @@ -63,6 +63,7 @@ static int panfrost_ioctl_get_param(struct drm_device *ddev, void *data, struct PANFROST_FEATURE(THREAD_MAX_BARRIER_SZ, thread_max_barrier_sz); PANFROST_FEATURE(COHERENCY_FEATURES, coherency_features); + PANFROST_FEATURE(AFBC_FEATURES, afbc_features); PANFROST_FEATURE_ARRAY(TEXTURE_FEATURES, texture_features, 3); PANFROST_FEATURE_ARRAY(JS_FEATURES, js_features, 15); PANFROST_FEATURE(NR_CORE_GROUPS, nr_core_groups); @@ -311,8 +312,7 @@ panfrost_ioctl_wait_bo(struct drm_device *dev, void *data, if (!gem_obj) return -ENOENT; - ret = dma_resv_wait_timeout_rcu(gem_obj->resv, true, - true, timeout); + ret = dma_resv_wait_timeout(gem_obj->resv, true, true, timeout); if (!ret) ret = timeout ? -ETIMEDOUT : -EBUSY; @@ -547,6 +547,7 @@ DEFINE_DRM_GEM_FOPS(panfrost_drm_driver_fops); * Panfrost driver version: * - 1.0 - initial interface * - 1.1 - adds HEAP and NOEXEC flags for CREATE_BO + * - 1.2 - adds AFBC_FEATURES query */ static const struct drm_driver panfrost_drm_driver = { .driver_features = DRIVER_RENDER | DRIVER_GEM | DRIVER_SYNCOBJ, @@ -559,7 +560,7 @@ static const struct drm_driver panfrost_drm_driver = { .desc = "panfrost DRM", .date = "20180908", .major = 1, - .minor = 1, + .minor = 2, .gem_create_object = panfrost_gem_create_object, .prime_handle_to_fd = drm_gem_prime_handle_to_fd, diff --git a/drivers/gpu/drm/panfrost/panfrost_gpu.c b/drivers/gpu/drm/panfrost/panfrost_gpu.c index 2aae636f1cf5..0e70e27fd8c3 100644 --- a/drivers/gpu/drm/panfrost/panfrost_gpu.c +++ b/drivers/gpu/drm/panfrost/panfrost_gpu.c @@ -228,6 +228,7 @@ static void panfrost_gpu_init_features(struct panfrost_device *pfdev) pfdev->features.thread_max_workgroup_sz = gpu_read(pfdev, GPU_THREAD_MAX_WORKGROUP_SIZE); pfdev->features.thread_max_barrier_sz = gpu_read(pfdev, GPU_THREAD_MAX_BARRIER_SIZE); pfdev->features.coherency_features = gpu_read(pfdev, GPU_COHERENCY_FEATURES); + pfdev->features.afbc_features = gpu_read(pfdev, GPU_AFBC_FEATURES); for (i = 0; i < 4; i++) pfdev->features.texture_features[i] = gpu_read(pfdev, GPU_TEXTURE_FEATURES(i)); diff --git a/drivers/gpu/drm/panfrost/panfrost_job.c b/drivers/gpu/drm/panfrost/panfrost_job.c index 6003cfeb1322..2df3e999a38d 100644 --- a/drivers/gpu/drm/panfrost/panfrost_job.c +++ b/drivers/gpu/drm/panfrost/panfrost_job.c @@ -203,7 +203,7 @@ static void panfrost_acquire_object_fences(struct drm_gem_object **bos, int i; for (i = 0; i < bo_count; i++) - implicit_fences[i] = dma_resv_get_excl_rcu(bos[i]->resv); + implicit_fences[i] = dma_resv_get_excl_unlocked(bos[i]->resv); } static void panfrost_attach_object_fences(struct drm_gem_object **bos, diff --git a/drivers/gpu/drm/panfrost/panfrost_regs.h b/drivers/gpu/drm/panfrost/panfrost_regs.h index eddaa62ad8b0..dc9df5457f1c 100644 --- a/drivers/gpu/drm/panfrost/panfrost_regs.h +++ b/drivers/gpu/drm/panfrost/panfrost_regs.h @@ -82,6 +82,7 @@ #define GPU_TEXTURE_FEATURES(n) (0x0B0 + ((n) * 4)) #define GPU_JS_FEATURES(n) (0x0C0 + ((n) * 4)) +#define GPU_AFBC_FEATURES (0x4C) /* (RO) AFBC support on Bifrost */ #define GPU_SHADER_PRESENT_LO 0x100 /* (RO) Shader core present bitmap, low word */ #define GPU_SHADER_PRESENT_HI 0x104 /* (RO) Shader core present bitmap, high word */ diff --git a/drivers/gpu/drm/pl111/Kconfig b/drivers/gpu/drm/pl111/Kconfig index 80f6748055e3..3aae387a96af 100644 --- a/drivers/gpu/drm/pl111/Kconfig +++ b/drivers/gpu/drm/pl111/Kconfig @@ -3,6 +3,7 @@ config DRM_PL111 tristate "DRM Support for PL111 CLCD Controller" depends on DRM depends on ARM || ARM64 || COMPILE_TEST + depends on VEXPRESS_CONFIG || VEXPRESS_CONFIG=n depends on COMMON_CLK select DRM_KMS_HELPER select DRM_KMS_CMA_HELPER diff --git a/drivers/gpu/drm/qxl/qxl_debugfs.c b/drivers/gpu/drm/qxl/qxl_debugfs.c index 183d15e2cf58..1f9a59601bb1 100644 --- a/drivers/gpu/drm/qxl/qxl_debugfs.c +++ b/drivers/gpu/drm/qxl/qxl_debugfs.c @@ -61,7 +61,7 @@ qxl_debugfs_buffers_info(struct seq_file *m, void *data) int rel; rcu_read_lock(); - fobj = rcu_dereference(bo->tbo.base.resv->fence); + fobj = dma_resv_shared_list(bo->tbo.base.resv); rel = fobj ? fobj->shared_count : 0; rcu_read_unlock(); diff --git a/drivers/gpu/drm/qxl/qxl_drv.h b/drivers/gpu/drm/qxl/qxl_drv.h index 20a0f3ab84ad..dd6abee55f56 100644 --- a/drivers/gpu/drm/qxl/qxl_drv.h +++ b/drivers/gpu/drm/qxl/qxl_drv.h @@ -292,12 +292,12 @@ qxl_bo_physical_address(struct qxl_device *qdev, struct qxl_bo *bo, unsigned long offset) { struct qxl_memslot *slot = - (bo->tbo.mem.mem_type == TTM_PL_VRAM) + (bo->tbo.resource->mem_type == TTM_PL_VRAM) ? &qdev->main_slot : &qdev->surfaces_slot; - /* TODO - need to hold one of the locks to read bo->tbo.mem.start */ + /* TODO - need to hold one of the locks to read bo->tbo.resource->start */ - return slot->high_bits | ((bo->tbo.mem.start << PAGE_SHIFT) + offset); + return slot->high_bits | ((bo->tbo.resource->start << PAGE_SHIFT) + offset); } /* qxl_display.c */ diff --git a/drivers/gpu/drm/qxl/qxl_dumb.c b/drivers/gpu/drm/qxl/qxl_dumb.c index a635d9fdf8ac..d636ba685451 100644 --- a/drivers/gpu/drm/qxl/qxl_dumb.c +++ b/drivers/gpu/drm/qxl/qxl_dumb.c @@ -58,6 +58,8 @@ int qxl_mode_dumb_create(struct drm_file *file_priv, surf.height = args->height; surf.stride = pitch; surf.format = format; + surf.data = 0; + r = qxl_gem_object_create_with_handle(qdev, file_priv, QXL_GEM_DOMAIN_CPU, args->size, &surf, &qobj, diff --git a/drivers/gpu/drm/qxl/qxl_object.c b/drivers/gpu/drm/qxl/qxl_object.c index 6e26d70f2f07..fbb36e3e8564 100644 --- a/drivers/gpu/drm/qxl/qxl_object.c +++ b/drivers/gpu/drm/qxl/qxl_object.c @@ -212,14 +212,14 @@ void *qxl_bo_kmap_atomic_page(struct qxl_device *qdev, struct io_mapping *map; struct dma_buf_map bo_map; - if (bo->tbo.mem.mem_type == TTM_PL_VRAM) + if (bo->tbo.resource->mem_type == TTM_PL_VRAM) map = qdev->vram_mapping; - else if (bo->tbo.mem.mem_type == TTM_PL_PRIV) + else if (bo->tbo.resource->mem_type == TTM_PL_PRIV) map = qdev->surface_mapping; else goto fallback; - offset = bo->tbo.mem.start << PAGE_SHIFT; + offset = bo->tbo.resource->start << PAGE_SHIFT; return io_mapping_map_atomic_wc(map, offset + page_offset); fallback: if (bo->kptr) { @@ -266,8 +266,8 @@ int qxl_bo_vunmap(struct qxl_bo *bo) void qxl_bo_kunmap_atomic_page(struct qxl_device *qdev, struct qxl_bo *bo, void *pmap) { - if ((bo->tbo.mem.mem_type != TTM_PL_VRAM) && - (bo->tbo.mem.mem_type != TTM_PL_PRIV)) + if ((bo->tbo.resource->mem_type != TTM_PL_VRAM) && + (bo->tbo.resource->mem_type != TTM_PL_PRIV)) goto fallback; io_mapping_unmap_atomic(pmap); diff --git a/drivers/gpu/drm/qxl/qxl_ttm.c b/drivers/gpu/drm/qxl/qxl_ttm.c index 47afe95d04a1..19fd39d9a00c 100644 --- a/drivers/gpu/drm/qxl/qxl_ttm.c +++ b/drivers/gpu/drm/qxl/qxl_ttm.c @@ -32,6 +32,7 @@ #include <drm/ttm/ttm_bo_api.h> #include <drm/ttm/ttm_bo_driver.h> #include <drm/ttm/ttm_placement.h> +#include <drm/ttm/ttm_range_manager.h> #include "qxl_drv.h" #include "qxl_object.h" @@ -131,7 +132,7 @@ static void qxl_bo_move_notify(struct ttm_buffer_object *bo, qbo = to_qxl_bo(bo); qdev = to_qxl(qbo->tbo.base.dev); - if (bo->mem.mem_type == TTM_PL_PRIV && qbo->surface_id) + if (bo->resource->mem_type == TTM_PL_PRIV && qbo->surface_id) qxl_surface_evict(qdev, qbo, new_mem ? true : false); } @@ -140,7 +141,7 @@ static int qxl_bo_move(struct ttm_buffer_object *bo, bool evict, struct ttm_resource *new_mem, struct ttm_place *hop) { - struct ttm_resource *old_mem = &bo->mem; + struct ttm_resource *old_mem = bo->resource; int ret; qxl_bo_move_notify(bo, new_mem); diff --git a/drivers/gpu/drm/radeon/radeon_cs.c b/drivers/gpu/drm/radeon/radeon_cs.c index 80a3bee933d6..9ed2b2700e0a 100644 --- a/drivers/gpu/drm/radeon/radeon_cs.c +++ b/drivers/gpu/drm/radeon/radeon_cs.c @@ -400,8 +400,8 @@ static int cmp_size_smaller_first(void *priv, const struct list_head *a, struct radeon_bo_list *lb = list_entry(b, struct radeon_bo_list, tv.head); /* Sort A before B if A is smaller. */ - return (int)la->robj->tbo.mem.num_pages - - (int)lb->robj->tbo.mem.num_pages; + return (int)la->robj->tbo.resource->num_pages - + (int)lb->robj->tbo.resource->num_pages; } /** @@ -516,7 +516,7 @@ static int radeon_bo_vm_update_pte(struct radeon_cs_parser *p, } r = radeon_vm_bo_update(rdev, vm->ib_bo_va, - &rdev->ring_tmp_bo.bo->tbo.mem); + rdev->ring_tmp_bo.bo->tbo.resource); if (r) return r; @@ -530,7 +530,7 @@ static int radeon_bo_vm_update_pte(struct radeon_cs_parser *p, return -EINVAL; } - r = radeon_vm_bo_update(rdev, bo_va, &bo->tbo.mem); + r = radeon_vm_bo_update(rdev, bo_va, bo->tbo.resource); if (r) return r; diff --git a/drivers/gpu/drm/radeon/radeon_display.c b/drivers/gpu/drm/radeon/radeon_display.c index 652af7a134bd..406681317419 100644 --- a/drivers/gpu/drm/radeon/radeon_display.c +++ b/drivers/gpu/drm/radeon/radeon_display.c @@ -533,7 +533,7 @@ static int radeon_crtc_page_flip_target(struct drm_crtc *crtc, DRM_ERROR("failed to pin new rbo buffer before flip\n"); goto cleanup; } - work->fence = dma_fence_get(dma_resv_get_excl(new_rbo->tbo.base.resv)); + work->fence = dma_fence_get(dma_resv_excl_fence(new_rbo->tbo.base.resv)); radeon_bo_get_tiling_flags(new_rbo, &tiling_flags, NULL); radeon_bo_unreserve(new_rbo); diff --git a/drivers/gpu/drm/radeon/radeon_gem.c b/drivers/gpu/drm/radeon/radeon_gem.c index ff8849827d61..458f92a70887 100644 --- a/drivers/gpu/drm/radeon/radeon_gem.c +++ b/drivers/gpu/drm/radeon/radeon_gem.c @@ -161,7 +161,7 @@ static int radeon_gem_set_domain(struct drm_gem_object *gobj, } if (domain == RADEON_GEM_DOMAIN_CPU) { /* Asking for cpu access wait for object idle */ - r = dma_resv_wait_timeout_rcu(robj->tbo.base.resv, true, true, 30 * HZ); + r = dma_resv_wait_timeout(robj->tbo.base.resv, true, true, 30 * HZ); if (!r) r = -EBUSY; @@ -523,13 +523,13 @@ int radeon_gem_busy_ioctl(struct drm_device *dev, void *data, } robj = gem_to_radeon_bo(gobj); - r = dma_resv_test_signaled_rcu(robj->tbo.base.resv, true); + r = dma_resv_test_signaled(robj->tbo.base.resv, true); if (r == 0) r = -EBUSY; else r = 0; - cur_placement = READ_ONCE(robj->tbo.mem.mem_type); + cur_placement = READ_ONCE(robj->tbo.resource->mem_type); args->domain = radeon_mem_type_to_domain(cur_placement); drm_gem_object_put(gobj); return r; @@ -552,14 +552,14 @@ int radeon_gem_wait_idle_ioctl(struct drm_device *dev, void *data, } robj = gem_to_radeon_bo(gobj); - ret = dma_resv_wait_timeout_rcu(robj->tbo.base.resv, true, true, 30 * HZ); + ret = dma_resv_wait_timeout(robj->tbo.base.resv, true, true, 30 * HZ); if (ret == 0) r = -EBUSY; else if (ret < 0) r = ret; /* Flush HDP cache via MMIO if necessary */ - cur_placement = READ_ONCE(robj->tbo.mem.mem_type); + cur_placement = READ_ONCE(robj->tbo.resource->mem_type); if (rdev->asic->mmio_hdp_flush && radeon_mem_type_to_domain(cur_placement) == RADEON_GEM_DOMAIN_VRAM) robj->rdev->asic->mmio_hdp_flush(rdev); @@ -643,7 +643,7 @@ static void radeon_gem_va_update_vm(struct radeon_device *rdev, goto error_free; list_for_each_entry(entry, &list, head) { - domain = radeon_mem_type_to_domain(entry->bo->mem.mem_type); + domain = radeon_mem_type_to_domain(entry->bo->resource->mem_type); /* if anything is swapped out don't swap it in here, just abort and wait for the next CS */ if (domain == RADEON_GEM_DOMAIN_CPU) @@ -656,7 +656,7 @@ static void radeon_gem_va_update_vm(struct radeon_device *rdev, goto error_unlock; if (bo_va->it.start) - r = radeon_vm_bo_update(rdev, bo_va, &bo_va->bo->tbo.mem); + r = radeon_vm_bo_update(rdev, bo_va, bo_va->bo->tbo.resource); error_unlock: mutex_unlock(&bo_va->vm->mutex); @@ -860,7 +860,7 @@ static int radeon_debugfs_gem_info_show(struct seq_file *m, void *unused) unsigned domain; const char *placement; - domain = radeon_mem_type_to_domain(rbo->tbo.mem.mem_type); + domain = radeon_mem_type_to_domain(rbo->tbo.resource->mem_type); switch (domain) { case RADEON_GEM_DOMAIN_VRAM: placement = "VRAM"; diff --git a/drivers/gpu/drm/radeon/radeon_mn.c b/drivers/gpu/drm/radeon/radeon_mn.c index e37c9a57a7c3..9fa88549c89e 100644 --- a/drivers/gpu/drm/radeon/radeon_mn.c +++ b/drivers/gpu/drm/radeon/radeon_mn.c @@ -66,8 +66,8 @@ static bool radeon_mn_invalidate(struct mmu_interval_notifier *mn, return true; } - r = dma_resv_wait_timeout_rcu(bo->tbo.base.resv, true, false, - MAX_SCHEDULE_TIMEOUT); + r = dma_resv_wait_timeout(bo->tbo.base.resv, true, false, + MAX_SCHEDULE_TIMEOUT); if (r <= 0) DRM_ERROR("(%ld) failed to wait for user bo\n", r); diff --git a/drivers/gpu/drm/radeon/radeon_object.c b/drivers/gpu/drm/radeon/radeon_object.c index cee11c55fd15..bfaaa3c969a3 100644 --- a/drivers/gpu/drm/radeon/radeon_object.c +++ b/drivers/gpu/drm/radeon/radeon_object.c @@ -76,7 +76,7 @@ static void radeon_ttm_bo_destroy(struct ttm_buffer_object *tbo) bo = container_of(tbo, struct radeon_bo, tbo); - radeon_update_memory_usage(bo, bo->tbo.mem.mem_type, -1); + radeon_update_memory_usage(bo, bo->tbo.resource->mem_type, -1); mutex_lock(&bo->rdev->gem.mutex); list_del_init(&bo->list); @@ -250,7 +250,7 @@ int radeon_bo_kmap(struct radeon_bo *bo, void **ptr) } return 0; } - r = ttm_bo_kmap(&bo->tbo, 0, bo->tbo.mem.num_pages, &bo->kmap); + r = ttm_bo_kmap(&bo->tbo, 0, bo->tbo.resource->num_pages, &bo->kmap); if (r) { return r; } @@ -359,7 +359,7 @@ void radeon_bo_unpin(struct radeon_bo *bo) { ttm_bo_unpin(&bo->tbo); if (!bo->tbo.pin_count) { - if (bo->tbo.mem.mem_type == TTM_PL_VRAM) + if (bo->tbo.resource->mem_type == TTM_PL_VRAM) bo->rdev->vram_pin_size -= radeon_bo_size(bo); else bo->rdev->gart_pin_size -= radeon_bo_size(bo); @@ -506,7 +506,7 @@ int radeon_bo_list_validate(struct radeon_device *rdev, u32 domain = lobj->preferred_domains; u32 allowed = lobj->allowed_domains; u32 current_domain = - radeon_mem_type_to_domain(bo->tbo.mem.mem_type); + radeon_mem_type_to_domain(bo->tbo.resource->mem_type); /* Check if this buffer will be moved and don't move it * if we have moved too many buffers for this IB already. @@ -605,7 +605,7 @@ int radeon_bo_get_surface_reg(struct radeon_bo *bo) out: radeon_set_surface_reg(rdev, i, bo->tiling_flags, bo->pitch, - bo->tbo.mem.start << PAGE_SHIFT, + bo->tbo.resource->start << PAGE_SHIFT, bo->tbo.base.size); return 0; } @@ -711,7 +711,7 @@ int radeon_bo_check_tiling(struct radeon_bo *bo, bool has_moved, return 0; } - if (bo->tbo.mem.mem_type != TTM_PL_VRAM) { + if (bo->tbo.resource->mem_type != TTM_PL_VRAM) { if (!has_moved) return 0; @@ -743,7 +743,7 @@ void radeon_bo_move_notify(struct ttm_buffer_object *bo, if (!new_mem) return; - radeon_update_memory_usage(rbo, bo->mem.mem_type, -1); + radeon_update_memory_usage(rbo, bo->resource->mem_type, -1); radeon_update_memory_usage(rbo, new_mem->mem_type, 1); } @@ -760,11 +760,11 @@ vm_fault_t radeon_bo_fault_reserve_notify(struct ttm_buffer_object *bo) rbo = container_of(bo, struct radeon_bo, tbo); radeon_bo_check_tiling(rbo, 0, 0); rdev = rbo->rdev; - if (bo->mem.mem_type != TTM_PL_VRAM) + if (bo->resource->mem_type != TTM_PL_VRAM) return 0; - size = bo->mem.num_pages << PAGE_SHIFT; - offset = bo->mem.start << PAGE_SHIFT; + size = bo->resource->num_pages << PAGE_SHIFT; + offset = bo->resource->start << PAGE_SHIFT; if ((offset + size) <= rdev->mc.visible_vram_size) return 0; @@ -786,7 +786,7 @@ vm_fault_t radeon_bo_fault_reserve_notify(struct ttm_buffer_object *bo) radeon_ttm_placement_from_domain(rbo, RADEON_GEM_DOMAIN_GTT); r = ttm_bo_validate(bo, &rbo->placement, &ctx); } else if (likely(!r)) { - offset = bo->mem.start << PAGE_SHIFT; + offset = bo->resource->start << PAGE_SHIFT; /* this should never happen */ if ((offset + size) > rdev->mc.visible_vram_size) return VM_FAULT_SIGBUS; diff --git a/drivers/gpu/drm/radeon/radeon_object.h b/drivers/gpu/drm/radeon/radeon_object.h index fd4116bdde0f..1739c6a142cd 100644 --- a/drivers/gpu/drm/radeon/radeon_object.h +++ b/drivers/gpu/drm/radeon/radeon_object.h @@ -95,7 +95,7 @@ static inline u64 radeon_bo_gpu_offset(struct radeon_bo *bo) rdev = radeon_get_rdev(bo->tbo.bdev); - switch (bo->tbo.mem.mem_type) { + switch (bo->tbo.resource->mem_type) { case TTM_PL_TT: start = rdev->mc.gtt_start; break; @@ -104,7 +104,7 @@ static inline u64 radeon_bo_gpu_offset(struct radeon_bo *bo) break; } - return (bo->tbo.mem.start << PAGE_SHIFT) + start; + return (bo->tbo.resource->start << PAGE_SHIFT) + start; } static inline unsigned long radeon_bo_size(struct radeon_bo *bo) diff --git a/drivers/gpu/drm/radeon/radeon_pm.c b/drivers/gpu/drm/radeon/radeon_pm.c index 3861c0b98fcf..c67b6ddb29a4 100644 --- a/drivers/gpu/drm/radeon/radeon_pm.c +++ b/drivers/gpu/drm/radeon/radeon_pm.c @@ -154,7 +154,7 @@ static void radeon_unmap_vram_bos(struct radeon_device *rdev) return; list_for_each_entry_safe(bo, n, &rdev->gem.objects, list) { - if (bo->tbo.mem.mem_type == TTM_PL_VRAM) + if (bo->tbo.resource->mem_type == TTM_PL_VRAM) ttm_bo_unmap_virtual(&bo->tbo); } } diff --git a/drivers/gpu/drm/radeon/radeon_sync.c b/drivers/gpu/drm/radeon/radeon_sync.c index 5d3302945076..9257b60144c4 100644 --- a/drivers/gpu/drm/radeon/radeon_sync.c +++ b/drivers/gpu/drm/radeon/radeon_sync.c @@ -98,14 +98,14 @@ int radeon_sync_resv(struct radeon_device *rdev, int r = 0; /* always sync to the exclusive fence */ - f = dma_resv_get_excl(resv); + f = dma_resv_excl_fence(resv); fence = f ? to_radeon_fence(f) : NULL; if (fence && fence->rdev == rdev) radeon_sync_fence(sync, fence); else if (f) r = dma_fence_wait(f, true); - flist = dma_resv_get_list(resv); + flist = dma_resv_shared_list(resv); if (shared || !flist || r) return r; diff --git a/drivers/gpu/drm/radeon/radeon_trace.h b/drivers/gpu/drm/radeon/radeon_trace.h index 1729cb9a95c5..c9fed5f2b870 100644 --- a/drivers/gpu/drm/radeon/radeon_trace.h +++ b/drivers/gpu/drm/radeon/radeon_trace.h @@ -22,7 +22,7 @@ TRACE_EVENT(radeon_bo_create, TP_fast_assign( __entry->bo = bo; - __entry->pages = bo->tbo.mem.num_pages; + __entry->pages = bo->tbo.resource->num_pages; ), TP_printk("bo=%p, pages=%u", __entry->bo, __entry->pages) ); diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c index a71d94f7067b..ad2a5a791bba 100644 --- a/drivers/gpu/drm/radeon/radeon_ttm.c +++ b/drivers/gpu/drm/radeon/radeon_ttm.c @@ -45,6 +45,7 @@ #include <drm/ttm/ttm_bo_api.h> #include <drm/ttm/ttm_bo_driver.h> #include <drm/ttm/ttm_placement.h> +#include <drm/ttm/ttm_range_manager.h> #include "radeon_reg.h" #include "radeon.h" @@ -98,12 +99,12 @@ static void radeon_evict_flags(struct ttm_buffer_object *bo, return; } rbo = container_of(bo, struct radeon_bo, tbo); - switch (bo->mem.mem_type) { + switch (bo->resource->mem_type) { case TTM_PL_VRAM: if (rbo->rdev->ring[radeon_copy_ring_index(rbo->rdev)].ready == false) radeon_ttm_placement_from_domain(rbo, RADEON_GEM_DOMAIN_CPU); else if (rbo->rdev->mc.visible_vram_size < rbo->rdev->mc.real_vram_size && - bo->mem.start < (rbo->rdev->mc.visible_vram_size >> PAGE_SHIFT)) { + bo->resource->start < (rbo->rdev->mc.visible_vram_size >> PAGE_SHIFT)) { unsigned fpfn = rbo->rdev->mc.visible_vram_size >> PAGE_SHIFT; int i; @@ -195,9 +196,9 @@ static int radeon_bo_move(struct ttm_buffer_object *bo, bool evict, struct ttm_resource *new_mem, struct ttm_place *hop) { + struct ttm_resource *old_mem = bo->resource; struct radeon_device *rdev; struct radeon_bo *rbo; - struct ttm_resource *old_mem = &bo->mem; int r; if (new_mem->mem_type == TTM_PL_TT) { @@ -229,7 +230,7 @@ static int radeon_bo_move(struct ttm_buffer_object *bo, bool evict, if (old_mem->mem_type == TTM_PL_TT && new_mem->mem_type == TTM_PL_SYSTEM) { radeon_ttm_tt_unbind(bo->bdev, bo->ttm); - ttm_resource_free(bo, &bo->mem); + ttm_resource_free(bo, &bo->resource); ttm_bo_assign_mem(bo, new_mem); goto out; } diff --git a/drivers/gpu/drm/radeon/radeon_uvd.c b/drivers/gpu/drm/radeon/radeon_uvd.c index 753da95e6abb..2ea86919d953 100644 --- a/drivers/gpu/drm/radeon/radeon_uvd.c +++ b/drivers/gpu/drm/radeon/radeon_uvd.c @@ -479,7 +479,7 @@ static int radeon_uvd_cs_msg(struct radeon_cs_parser *p, struct radeon_bo *bo, return -EINVAL; } - f = dma_resv_get_excl(bo->tbo.base.resv); + f = dma_resv_excl_fence(bo->tbo.base.resv); if (f) { r = radeon_fence_wait((struct radeon_fence *)f, false); if (r) { diff --git a/drivers/gpu/drm/sti/sti_hda.c b/drivers/gpu/drm/sti/sti_hda.c index 5c2b650b561d..03f3377f918c 100644 --- a/drivers/gpu/drm/sti/sti_hda.c +++ b/drivers/gpu/drm/sti/sti_hda.c @@ -272,7 +272,7 @@ static void hda_write(struct sti_hda *hda, u32 val, int offset) } /** - * Search for a video mode in the supported modes table + * hda_get_mode_idx - Search for a video mode in the supported modes table * * @mode: mode being searched * @idx: index of the found mode @@ -292,7 +292,7 @@ static bool hda_get_mode_idx(struct drm_display_mode mode, int *idx) } /** - * Enable the HD DACS + * hda_enable_hd_dacs - Enable the HD DACS * * @hda: pointer to HD analog structure * @enable: true if HD DACS need to be enabled, else false @@ -380,7 +380,7 @@ static void hda_debugfs_init(struct sti_hda *hda, struct drm_minor *minor) } /** - * Configure AWG, writing instructions + * sti_hda_configure_awg - Configure AWG, writing instructions * * @hda: pointer to HD analog structure * @awg_instr: pointer to AWG instructions table diff --git a/drivers/gpu/drm/sti/sti_hdmi_tx3g4c28phy.c b/drivers/gpu/drm/sti/sti_hdmi_tx3g4c28phy.c index d5f94dca0d32..d25ecd4f4b67 100644 --- a/drivers/gpu/drm/sti/sti_hdmi_tx3g4c28phy.c +++ b/drivers/gpu/drm/sti/sti_hdmi_tx3g4c28phy.c @@ -67,7 +67,7 @@ static struct hdmi_phy_config hdmiphy_config[NB_HDMI_PHY_CONFIG] = { }; /** - * Start hdmi phy macro cell tx3g4c28 + * sti_hdmi_tx3g4c28phy_start - Start hdmi phy macro cell tx3g4c28 * * @hdmi: pointer on the hdmi internal structure * @@ -179,7 +179,7 @@ err: } /** - * Stop hdmi phy macro cell tx3g4c28 + * sti_hdmi_tx3g4c28phy_stop - Stop hdmi phy macro cell tx3g4c28 * * @hdmi: pointer on the hdmi internal structure */ diff --git a/drivers/gpu/drm/sti/sti_hqvdp.c b/drivers/gpu/drm/sti/sti_hqvdp.c index edbb99f53de1..d09b08995b12 100644 --- a/drivers/gpu/drm/sti/sti_hqvdp.c +++ b/drivers/gpu/drm/sti/sti_hqvdp.c @@ -782,7 +782,7 @@ static void sti_hqvdp_disable(struct sti_hqvdp *hqvdp) } /** - * sti_vdp_vtg_cb + * sti_hqvdp_vtg_cb * @nb: notifier block * @evt: event message * @data: private data diff --git a/drivers/gpu/drm/sti/sti_tvout.c b/drivers/gpu/drm/sti/sti_tvout.c index df3817f0fd30..2499715a69b7 100644 --- a/drivers/gpu/drm/sti/sti_tvout.c +++ b/drivers/gpu/drm/sti/sti_tvout.c @@ -153,7 +153,7 @@ static void tvout_write(struct sti_tvout *tvout, u32 val, int offset) } /** - * Set the clipping mode of a VIP + * tvout_vip_set_color_order - Set the clipping mode of a VIP * * @tvout: tvout structure * @reg: register to set @@ -177,7 +177,7 @@ static void tvout_vip_set_color_order(struct sti_tvout *tvout, int reg, } /** - * Set the clipping mode of a VIP + * tvout_vip_set_clip_mode - Set the clipping mode of a VIP * * @tvout: tvout structure * @reg: register to set @@ -193,7 +193,7 @@ static void tvout_vip_set_clip_mode(struct sti_tvout *tvout, int reg, u32 range) } /** - * Set the rounded value of a VIP + * tvout_vip_set_rnd - Set the rounded value of a VIP * * @tvout: tvout structure * @reg: register to set @@ -209,7 +209,7 @@ static void tvout_vip_set_rnd(struct sti_tvout *tvout, int reg, u32 rnd) } /** - * Select the VIP input + * tvout_vip_set_sel_input - Select the VIP input * * @tvout: tvout structure * @reg: register to set @@ -247,7 +247,7 @@ static void tvout_vip_set_sel_input(struct sti_tvout *tvout, } /** - * Select the input video signed or unsigned + * tvout_vip_set_in_vid_fmt - Select the input video signed or unsigned * * @tvout: tvout structure * @reg: register to set @@ -264,7 +264,7 @@ static void tvout_vip_set_in_vid_fmt(struct sti_tvout *tvout, } /** - * Set preformatter matrix + * tvout_preformatter_set_matrix - Set preformatter matrix * * @tvout: tvout structure * @mode: display mode structure @@ -289,7 +289,7 @@ static void tvout_preformatter_set_matrix(struct sti_tvout *tvout, } /** - * Start VIP block for DVO output + * tvout_dvo_start - Start VIP block for DVO output * * @tvout: pointer on tvout structure * @main_path: true if main path has to be used in the vip configuration @@ -343,7 +343,7 @@ static void tvout_dvo_start(struct sti_tvout *tvout, bool main_path) } /** - * Start VIP block for HDMI output + * tvout_hdmi_start - Start VIP block for HDMI output * * @tvout: pointer on tvout structure * @main_path: true if main path has to be used in the vip configuration @@ -392,7 +392,7 @@ static void tvout_hdmi_start(struct sti_tvout *tvout, bool main_path) } /** - * Start HDF VIP and HD DAC + * tvout_hda_start - Start HDF VIP and HD DAC * * @tvout: pointer on tvout structure * @main_path: true if main path has to be used in the vip configuration diff --git a/drivers/gpu/drm/stm/ltdc.c b/drivers/gpu/drm/stm/ltdc.c index e99771b947b6..08b71248044d 100644 --- a/drivers/gpu/drm/stm/ltdc.c +++ b/drivers/gpu/drm/stm/ltdc.c @@ -531,7 +531,6 @@ static void ltdc_crtc_mode_set_nofb(struct drm_crtc *crtc) struct drm_encoder *encoder = NULL; struct drm_bridge *bridge = NULL; struct drm_display_mode *mode = &crtc->state->adjusted_mode; - struct videomode vm; u32 hsync, vsync, accum_hbp, accum_vbp, accum_act_w, accum_act_h; u32 total_width, total_height; u32 bus_flags = 0; @@ -570,31 +569,33 @@ static void ltdc_crtc_mode_set_nofb(struct drm_crtc *crtc) } } - drm_display_mode_to_videomode(mode, &vm); - DRM_DEBUG_DRIVER("CRTC:%d mode:%s\n", crtc->base.id, mode->name); - DRM_DEBUG_DRIVER("Video mode: %dx%d", vm.hactive, vm.vactive); + DRM_DEBUG_DRIVER("Video mode: %dx%d", mode->hdisplay, mode->vdisplay); DRM_DEBUG_DRIVER(" hfp %d hbp %d hsl %d vfp %d vbp %d vsl %d\n", - vm.hfront_porch, vm.hback_porch, vm.hsync_len, - vm.vfront_porch, vm.vback_porch, vm.vsync_len); + mode->hsync_start - mode->hdisplay, + mode->htotal - mode->hsync_end, + mode->hsync_end - mode->hsync_start, + mode->vsync_start - mode->vdisplay, + mode->vtotal - mode->vsync_end, + mode->vsync_end - mode->vsync_start); /* Convert video timings to ltdc timings */ - hsync = vm.hsync_len - 1; - vsync = vm.vsync_len - 1; - accum_hbp = hsync + vm.hback_porch; - accum_vbp = vsync + vm.vback_porch; - accum_act_w = accum_hbp + vm.hactive; - accum_act_h = accum_vbp + vm.vactive; - total_width = accum_act_w + vm.hfront_porch; - total_height = accum_act_h + vm.vfront_porch; + hsync = mode->hsync_end - mode->hsync_start - 1; + vsync = mode->vsync_end - mode->vsync_start - 1; + accum_hbp = mode->htotal - mode->hsync_start - 1; + accum_vbp = mode->vtotal - mode->vsync_start - 1; + accum_act_w = accum_hbp + mode->hdisplay; + accum_act_h = accum_vbp + mode->vdisplay; + total_width = mode->htotal - 1; + total_height = mode->vtotal - 1; /* Configures the HS, VS, DE and PC polarities. Default Active Low */ val = 0; - if (vm.flags & DISPLAY_FLAGS_HSYNC_HIGH) + if (mode->flags & DRM_MODE_FLAG_PHSYNC) val |= GCR_HSPOL; - if (vm.flags & DISPLAY_FLAGS_VSYNC_HIGH) + if (mode->flags & DRM_MODE_FLAG_PVSYNC) val |= GCR_VSPOL; if (bus_flags & DRM_BUS_FLAG_DE_LOW) diff --git a/drivers/gpu/drm/sun4i/sun8i_ui_layer.c b/drivers/gpu/drm/sun4i/sun8i_ui_layer.c index 0db164a774a1..e779855bcd6e 100644 --- a/drivers/gpu/drm/sun4i/sun8i_ui_layer.c +++ b/drivers/gpu/drm/sun4i/sun8i_ui_layer.c @@ -370,6 +370,11 @@ static const u32 sun8i_ui_layer_formats[] = { DRM_FORMAT_XRGB8888, }; +static const uint64_t sun8i_layer_modifiers[] = { + DRM_FORMAT_MOD_LINEAR, + DRM_FORMAT_MOD_INVALID +}; + struct sun8i_ui_layer *sun8i_ui_layer_init_one(struct drm_device *drm, struct sun8i_mixer *mixer, int index) @@ -392,7 +397,7 @@ struct sun8i_ui_layer *sun8i_ui_layer_init_one(struct drm_device *drm, &sun8i_ui_layer_funcs, sun8i_ui_layer_formats, ARRAY_SIZE(sun8i_ui_layer_formats), - NULL, type, NULL); + sun8i_layer_modifiers, type, NULL); if (ret) { dev_err(drm->dev, "Couldn't initialize layer\n"); return ERR_PTR(ret); diff --git a/drivers/gpu/drm/sun4i/sun8i_vi_layer.c b/drivers/gpu/drm/sun4i/sun8i_vi_layer.c index 46420780db59..1c86c2dd0bbf 100644 --- a/drivers/gpu/drm/sun4i/sun8i_vi_layer.c +++ b/drivers/gpu/drm/sun4i/sun8i_vi_layer.c @@ -534,6 +534,11 @@ static const u32 sun8i_vi_layer_de3_formats[] = { DRM_FORMAT_YVU422, }; +static const uint64_t sun8i_layer_modifiers[] = { + DRM_FORMAT_MOD_LINEAR, + DRM_FORMAT_MOD_INVALID +}; + struct sun8i_vi_layer *sun8i_vi_layer_init_one(struct drm_device *drm, struct sun8i_mixer *mixer, int index) @@ -560,7 +565,8 @@ struct sun8i_vi_layer *sun8i_vi_layer_init_one(struct drm_device *drm, ret = drm_universal_plane_init(drm, &layer->plane, 0, &sun8i_vi_layer_funcs, formats, format_count, - NULL, DRM_PLANE_TYPE_OVERLAY, NULL); + sun8i_layer_modifiers, + DRM_PLANE_TYPE_OVERLAY, NULL); if (ret) { dev_err(drm->dev, "Couldn't initialize layer\n"); return ERR_PTR(ret); diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c index 51a94fd63bd7..db53fecca696 100644 --- a/drivers/gpu/drm/ttm/ttm_bo.c +++ b/drivers/gpu/drm/ttm/ttm_bo.c @@ -58,7 +58,7 @@ static void ttm_bo_mem_space_debug(struct ttm_buffer_object *bo, int i, mem_type; drm_printf(&p, "No space for %p (%lu pages, %zuK, %zuM)\n", - bo, bo->mem.num_pages, bo->base.size >> 10, + bo, bo->resource->num_pages, bo->base.size >> 10, bo->base.size >> 20); for (i = 0; i < placement->num_placement; i++) { mem_type = placement->placement[i].mem_type; @@ -109,7 +109,7 @@ void ttm_bo_move_to_lru_tail(struct ttm_buffer_object *bo, bdev->funcs->del_from_lru_notify(bo); if (bulk && !bo->pin_count) { - switch (bo->mem.mem_type) { + switch (bo->resource->mem_type) { case TTM_PL_TT: ttm_bo_bulk_move_set_pos(&bulk->tt[bo->priority], bo); break; @@ -163,11 +163,13 @@ static int ttm_bo_handle_move_mem(struct ttm_buffer_object *bo, struct ttm_operation_ctx *ctx, struct ttm_place *hop) { + struct ttm_resource_manager *old_man, *new_man; struct ttm_device *bdev = bo->bdev; - struct ttm_resource_manager *old_man = ttm_manager_type(bdev, bo->mem.mem_type); - struct ttm_resource_manager *new_man = ttm_manager_type(bdev, mem->mem_type); int ret; + old_man = ttm_manager_type(bdev, bo->resource->mem_type); + new_man = ttm_manager_type(bdev, mem->mem_type); + ttm_bo_unmap_virtual(bo); /* @@ -200,7 +202,7 @@ static int ttm_bo_handle_move_mem(struct ttm_buffer_object *bo, return 0; out_err: - new_man = ttm_manager_type(bdev, bo->mem.mem_type); + new_man = ttm_manager_type(bdev, bo->resource->mem_type); if (!new_man->use_tt) ttm_bo_tt_destroy(bo); @@ -221,7 +223,7 @@ static void ttm_bo_cleanup_memtype_use(struct ttm_buffer_object *bo) bo->bdev->funcs->delete_mem_notify(bo); ttm_bo_tt_destroy(bo); - ttm_resource_free(bo, &bo->mem); + ttm_resource_free(bo, &bo->resource); } static int ttm_bo_individualize_resv(struct ttm_buffer_object *bo) @@ -259,8 +261,8 @@ static void ttm_bo_flush_all_fences(struct ttm_buffer_object *bo) int i; rcu_read_lock(); - fobj = rcu_dereference(resv->fence); - fence = rcu_dereference(resv->fence_excl); + fobj = dma_resv_shared_list(resv); + fence = dma_resv_excl_fence(resv); if (fence && !fence->ops->signaled) dma_fence_enable_sw_signaling(fence); @@ -294,7 +296,7 @@ static int ttm_bo_cleanup_refs(struct ttm_buffer_object *bo, struct dma_resv *resv = &bo->base._resv; int ret; - if (dma_resv_test_signaled_rcu(resv, true)) + if (dma_resv_test_signaled(resv, true)) ret = 0; else ret = -EBUSY; @@ -306,8 +308,8 @@ static int ttm_bo_cleanup_refs(struct ttm_buffer_object *bo, dma_resv_unlock(bo->base.resv); spin_unlock(&bo->bdev->lru_lock); - lret = dma_resv_wait_timeout_rcu(resv, true, interruptible, - 30 * HZ); + lret = dma_resv_wait_timeout(resv, true, interruptible, + 30 * HZ); if (lret < 0) return lret; @@ -409,18 +411,18 @@ static void ttm_bo_release(struct kref *kref) /* Last resort, if we fail to allocate memory for the * fences block for the BO to become idle */ - dma_resv_wait_timeout_rcu(bo->base.resv, true, false, - 30 * HZ); + dma_resv_wait_timeout(bo->base.resv, true, false, + 30 * HZ); } if (bo->bdev->funcs->release_notify) bo->bdev->funcs->release_notify(bo); drm_vma_offset_remove(bdev->vma_manager, &bo->base.vma_node); - ttm_mem_io_free(bdev, &bo->mem); + ttm_mem_io_free(bdev, bo->resource); } - if (!dma_resv_test_signaled_rcu(bo->base.resv, true) || + if (!dma_resv_test_signaled(bo->base.resv, true) || !dma_resv_trylock(bo->base.resv)) { /* The BO is not idle, resurrect it for delayed destroy */ ttm_bo_flush_all_fences(bo); @@ -438,7 +440,7 @@ static void ttm_bo_release(struct kref *kref) */ if (bo->pin_count) { bo->pin_count = 0; - ttm_bo_move_to_lru_tail(bo, &bo->mem, NULL); + ttm_bo_move_to_lru_tail(bo, bo->resource, NULL); } kref_init(&bo->kref); @@ -487,7 +489,7 @@ static int ttm_bo_evict(struct ttm_buffer_object *bo, struct ttm_operation_ctx *ctx) { struct ttm_device *bdev = bo->bdev; - struct ttm_resource evict_mem; + struct ttm_resource *evict_mem; struct ttm_placement placement; struct ttm_place hop; int ret = 0; @@ -501,10 +503,15 @@ static int ttm_bo_evict(struct ttm_buffer_object *bo, bdev->funcs->evict_flags(bo, &placement); if (!placement.num_placement && !placement.num_busy_placement) { - ttm_bo_wait(bo, false, false); + ret = ttm_bo_wait(bo, true, false); + if (ret) + return ret; - ttm_bo_cleanup_memtype_use(bo); - return ttm_tt_create(bo, false); + /* + * Since we've already synced, this frees backing store + * immediately. + */ + return ttm_bo_pipeline_gutting(bo); } ret = ttm_bo_mem_space(bo, &placement, &evict_mem, ctx); @@ -517,7 +524,7 @@ static int ttm_bo_evict(struct ttm_buffer_object *bo, goto out; } - ret = ttm_bo_handle_move_mem(bo, &evict_mem, true, ctx, &hop); + ret = ttm_bo_handle_move_mem(bo, evict_mem, true, ctx, &hop); if (unlikely(ret)) { WARN(ret == -EMULTIHOP, "Unexpected multihop in eviction - likely driver bug\n"); if (ret != -ERESTARTSYS) @@ -531,11 +538,15 @@ out: bool ttm_bo_eviction_valuable(struct ttm_buffer_object *bo, const struct ttm_place *place) { + dma_resv_assert_held(bo->base.resv); + if (bo->resource->mem_type == TTM_PL_SYSTEM) + return true; + /* Don't evict this BO if it's outside of the * requested placement range */ - if (place->fpfn >= (bo->mem.start + bo->mem.num_pages) || - (place->lpfn && place->lpfn <= bo->mem.start)) + if (place->fpfn >= (bo->resource->start + bo->resource->num_pages) || + (place->lpfn && place->lpfn <= bo->resource->start)) return false; return true; @@ -553,7 +564,9 @@ EXPORT_SYMBOL(ttm_bo_eviction_valuable); * b. Otherwise, trylock it. */ static bool ttm_bo_evict_swapout_allowable(struct ttm_buffer_object *bo, - struct ttm_operation_ctx *ctx, bool *locked, bool *busy) + struct ttm_operation_ctx *ctx, + const struct ttm_place *place, + bool *locked, bool *busy) { bool ret = false; @@ -571,6 +584,14 @@ static bool ttm_bo_evict_swapout_allowable(struct ttm_buffer_object *bo, *busy = !ret; } + if (ret && place && !bo->bdev->funcs->eviction_valuable(bo, place)) { + ret = false; + if (*locked) { + dma_resv_unlock(bo->base.resv); + *locked = false; + } + } + return ret; } @@ -625,20 +646,14 @@ int ttm_mem_evict_first(struct ttm_device *bdev, list_for_each_entry(bo, &man->lru[i], lru) { bool busy; - if (!ttm_bo_evict_swapout_allowable(bo, ctx, &locked, - &busy)) { + if (!ttm_bo_evict_swapout_allowable(bo, ctx, place, + &locked, &busy)) { if (busy && !busy_bo && ticket != dma_resv_locking_ctx(bo->base.resv)) busy_bo = bo; continue; } - if (place && !bdev->funcs->eviction_valuable(bo, - place)) { - if (locked) - dma_resv_unlock(bo->base.resv); - continue; - } if (!ttm_bo_get_unless_zero(bo)) { if (locked) dma_resv_unlock(bo->base.resv); @@ -726,14 +741,15 @@ static int ttm_bo_add_move_fence(struct ttm_buffer_object *bo, */ static int ttm_bo_mem_force_space(struct ttm_buffer_object *bo, const struct ttm_place *place, - struct ttm_resource *mem, + struct ttm_resource **mem, struct ttm_operation_ctx *ctx) { struct ttm_device *bdev = bo->bdev; - struct ttm_resource_manager *man = ttm_manager_type(bdev, mem->mem_type); + struct ttm_resource_manager *man; struct ww_acquire_ctx *ticket; int ret; + man = ttm_manager_type(bdev, place->mem_type); ticket = dma_resv_locking_ctx(bo->base.resv); do { ret = ttm_resource_alloc(bo, place, mem); @@ -747,37 +763,7 @@ static int ttm_bo_mem_force_space(struct ttm_buffer_object *bo, return ret; } while (1); - return ttm_bo_add_move_fence(bo, man, mem, ctx->no_wait_gpu); -} - -/** - * ttm_bo_mem_placement - check if placement is compatible - * @bo: BO to find memory for - * @place: where to search - * @mem: the memory object to fill in - * - * Check if placement is compatible and fill in mem structure. - * Returns -EBUSY if placement won't work or negative error code. - * 0 when placement can be used. - */ -static int ttm_bo_mem_placement(struct ttm_buffer_object *bo, - const struct ttm_place *place, - struct ttm_resource *mem) -{ - struct ttm_device *bdev = bo->bdev; - struct ttm_resource_manager *man; - - man = ttm_manager_type(bdev, place->mem_type); - if (!man || !ttm_resource_manager_used(man)) - return -EBUSY; - - mem->mem_type = place->mem_type; - mem->placement = place->flags; - - spin_lock(&bo->bdev->lru_lock); - ttm_bo_move_to_lru_tail(bo, mem, NULL); - spin_unlock(&bo->bdev->lru_lock); - return 0; + return ttm_bo_add_move_fence(bo, man, *mem, ctx->no_wait_gpu); } /* @@ -790,7 +776,7 @@ static int ttm_bo_mem_placement(struct ttm_buffer_object *bo, */ int ttm_bo_mem_space(struct ttm_buffer_object *bo, struct ttm_placement *placement, - struct ttm_resource *mem, + struct ttm_resource **mem, struct ttm_operation_ctx *ctx) { struct ttm_device *bdev = bo->bdev; @@ -805,8 +791,8 @@ int ttm_bo_mem_space(struct ttm_buffer_object *bo, const struct ttm_place *place = &placement->placement[i]; struct ttm_resource_manager *man; - ret = ttm_bo_mem_placement(bo, place, mem); - if (ret) + man = ttm_manager_type(bdev, place->mem_type); + if (!man || !ttm_resource_manager_used(man)) continue; type_found = true; @@ -816,8 +802,7 @@ int ttm_bo_mem_space(struct ttm_buffer_object *bo, if (unlikely(ret)) goto error; - man = ttm_manager_type(bdev, mem->mem_type); - ret = ttm_bo_add_move_fence(bo, man, mem, ctx->no_wait_gpu); + ret = ttm_bo_add_move_fence(bo, man, *mem, ctx->no_wait_gpu); if (unlikely(ret)) { ttm_resource_free(bo, mem); if (ret == -EBUSY) @@ -830,9 +815,10 @@ int ttm_bo_mem_space(struct ttm_buffer_object *bo, for (i = 0; i < placement->num_busy_placement; ++i) { const struct ttm_place *place = &placement->busy_placement[i]; + struct ttm_resource_manager *man; - ret = ttm_bo_mem_placement(bo, place, mem); - if (ret) + man = ttm_manager_type(bdev, place->mem_type); + if (!man || !ttm_resource_manager_used(man)) continue; type_found = true; @@ -851,7 +837,7 @@ int ttm_bo_mem_space(struct ttm_buffer_object *bo, } error: - if (bo->mem.mem_type == TTM_PL_SYSTEM && !bo->pin_count) + if (bo->resource->mem_type == TTM_PL_SYSTEM && !bo->pin_count) ttm_bo_move_to_lru_tail_unlocked(bo); return ret; @@ -859,12 +845,12 @@ error: EXPORT_SYMBOL(ttm_bo_mem_space); static int ttm_bo_bounce_temp_buffer(struct ttm_buffer_object *bo, - struct ttm_resource *mem, + struct ttm_resource **mem, struct ttm_operation_ctx *ctx, struct ttm_place *hop) { struct ttm_placement hop_placement; - struct ttm_resource hop_mem; + struct ttm_resource *hop_mem; int ret; hop_placement.num_placement = hop_placement.num_busy_placement = 1; @@ -875,7 +861,7 @@ static int ttm_bo_bounce_temp_buffer(struct ttm_buffer_object *bo, if (ret) return ret; /* move to the bounce domain */ - ret = ttm_bo_handle_move_mem(bo, &hop_mem, false, ctx, NULL); + ret = ttm_bo_handle_move_mem(bo, hop_mem, false, ctx, NULL); if (ret) { ttm_resource_free(bo, &hop_mem); return ret; @@ -887,14 +873,12 @@ static int ttm_bo_move_buffer(struct ttm_buffer_object *bo, struct ttm_placement *placement, struct ttm_operation_ctx *ctx) { + struct ttm_resource *mem; struct ttm_place hop; - struct ttm_resource mem; int ret; dma_resv_assert_held(bo->base.resv); - memset(&hop, 0, sizeof(hop)); - /* * Determine where to move the buffer. * @@ -908,7 +892,7 @@ static int ttm_bo_move_buffer(struct ttm_buffer_object *bo, if (ret) return ret; bounce: - ret = ttm_bo_handle_move_mem(bo, &mem, false, ctx, &hop); + ret = ttm_bo_handle_move_mem(bo, mem, false, ctx, &hop); if (ret == -EMULTIHOP) { ret = ttm_bo_bounce_temp_buffer(bo, &mem, ctx, &hop); if (ret) @@ -976,18 +960,13 @@ int ttm_bo_validate(struct ttm_buffer_object *bo, /* * Remove the backing store if no placement is given. */ - if (!placement->num_placement && !placement->num_busy_placement) { - ret = ttm_bo_pipeline_gutting(bo); - if (ret) - return ret; - - return ttm_tt_create(bo, false); - } + if (!placement->num_placement && !placement->num_busy_placement) + return ttm_bo_pipeline_gutting(bo); /* * Check whether we need to move buffer. */ - if (!ttm_bo_mem_compat(placement, &bo->mem, &new_flags)) { + if (!ttm_bo_mem_compat(placement, bo->resource, &new_flags)) { ret = ttm_bo_move_buffer(bo, placement, ctx); if (ret) return ret; @@ -995,7 +974,7 @@ int ttm_bo_validate(struct ttm_buffer_object *bo, /* * We might need to add a TTM. */ - if (bo->mem.mem_type == TTM_PL_SYSTEM) { + if (bo->resource->mem_type == TTM_PL_SYSTEM) { ret = ttm_tt_create(bo, true); if (ret) return ret; @@ -1017,7 +996,7 @@ int ttm_bo_init_reserved(struct ttm_device *bdev, { static const struct ttm_place sys_mem = { .mem_type = TTM_PL_SYSTEM }; bool locked; - int ret = 0; + int ret; bo->destroy = destroy ? destroy : ttm_bo_default_destroy; @@ -1027,7 +1006,6 @@ int ttm_bo_init_reserved(struct ttm_device *bdev, bo->bdev = bdev; bo->type = type; bo->page_alignment = page_alignment; - ttm_resource_alloc(bo, &sys_mem, &bo->mem); bo->moving = NULL; bo->pin_count = 0; bo->sg = sg; @@ -1039,6 +1017,12 @@ int ttm_bo_init_reserved(struct ttm_device *bdev, } atomic_inc(&ttm_glob.bo_count); + ret = ttm_resource_alloc(bo, &sys_mem, &bo->resource); + if (unlikely(ret)) { + ttm_bo_put(bo); + return ret; + } + /* * For ttm_bo_type_device buffers, allocate * address space from the device. @@ -1046,7 +1030,7 @@ int ttm_bo_init_reserved(struct ttm_device *bdev, if (bo->type == ttm_bo_type_device || bo->type == ttm_bo_type_sg) ret = drm_vma_offset_add(bdev->vma_manager, &bo->base.vma_node, - bo->mem.num_pages); + bo->resource->num_pages); /* passed reservation objects should already be locked, * since otherwise lockdep will be angered in radeon. @@ -1108,7 +1092,7 @@ void ttm_bo_unmap_virtual(struct ttm_buffer_object *bo) struct ttm_device *bdev = bo->bdev; drm_vma_node_unmap(&bo->base.vma_node, bdev->dev_mapping); - ttm_mem_io_free(bdev, &bo->mem); + ttm_mem_io_free(bdev, bo->resource); } EXPORT_SYMBOL(ttm_bo_unmap_virtual); @@ -1118,14 +1102,14 @@ int ttm_bo_wait(struct ttm_buffer_object *bo, long timeout = 15 * HZ; if (no_wait) { - if (dma_resv_test_signaled_rcu(bo->base.resv, true)) + if (dma_resv_test_signaled(bo->base.resv, true)) return 0; else return -EBUSY; } - timeout = dma_resv_wait_timeout_rcu(bo->base.resv, true, - interruptible, timeout); + timeout = dma_resv_wait_timeout(bo->base.resv, true, interruptible, + timeout); if (timeout < 0) return timeout; @@ -1140,10 +1124,19 @@ EXPORT_SYMBOL(ttm_bo_wait); int ttm_bo_swapout(struct ttm_buffer_object *bo, struct ttm_operation_ctx *ctx, gfp_t gfp_flags) { + struct ttm_place place; bool locked; int ret; - if (!ttm_bo_evict_swapout_allowable(bo, ctx, &locked, NULL)) + /* + * While the bo may already reside in SYSTEM placement, set + * SYSTEM as new placement to cover also the move further below. + * The driver may use the fact that we're moving from SYSTEM + * as an indication that we're about to swap out. + */ + memset(&place, 0, sizeof(place)); + place.mem_type = TTM_PL_SYSTEM; + if (!ttm_bo_evict_swapout_allowable(bo, ctx, &place, &locked, NULL)) return -EBUSY; if (!ttm_bo_get_unless_zero(bo)) { @@ -1165,21 +1158,17 @@ int ttm_bo_swapout(struct ttm_buffer_object *bo, struct ttm_operation_ctx *ctx, /* * Move to system cached */ - if (bo->mem.mem_type != TTM_PL_SYSTEM) { + if (bo->resource->mem_type != TTM_PL_SYSTEM) { struct ttm_operation_ctx ctx = { false, false }; - struct ttm_resource evict_mem; - struct ttm_place place, hop; + struct ttm_resource *evict_mem; + struct ttm_place hop; - memset(&place, 0, sizeof(place)); memset(&hop, 0, sizeof(hop)); - - place.mem_type = TTM_PL_SYSTEM; - ret = ttm_resource_alloc(bo, &place, &evict_mem); if (unlikely(ret)) goto out; - ret = ttm_bo_handle_move_mem(bo, &evict_mem, true, &ctx, &hop); + ret = ttm_bo_handle_move_mem(bo, evict_mem, true, &ctx, &hop); if (unlikely(ret != 0)) { WARN(ret == -EMULTIHOP, "Unexpected multihop in swaput - likely driver bug.\n"); goto out; @@ -1202,7 +1191,8 @@ int ttm_bo_swapout(struct ttm_buffer_object *bo, struct ttm_operation_ctx *ctx, if (bo->bdev->funcs->swap_notify) bo->bdev->funcs->swap_notify(bo); - ret = ttm_tt_swapout(bo->bdev, bo->ttm, gfp_flags); + if (ttm_tt_is_populated(bo->ttm)) + ret = ttm_tt_swapout(bo->bdev, bo->ttm, gfp_flags); out: /* diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c b/drivers/gpu/drm/ttm/ttm_bo_util.c index ae8b61460724..2f57f824e6db 100644 --- a/drivers/gpu/drm/ttm/ttm_bo_util.c +++ b/drivers/gpu/drm/ttm/ttm_bo_util.c @@ -31,6 +31,7 @@ #include <drm/ttm/ttm_bo_driver.h> #include <drm/ttm/ttm_placement.h> +#include <drm/drm_cache.h> #include <drm/drm_vma_manager.h> #include <linux/dma-buf-map.h> #include <linux/io.h> @@ -72,190 +73,112 @@ void ttm_mem_io_free(struct ttm_device *bdev, mem->bus.addr = NULL; } -static int ttm_resource_ioremap(struct ttm_device *bdev, - struct ttm_resource *mem, - void **virtual) +/** + * ttm_move_memcpy - Helper to perform a memcpy ttm move operation. + * @bo: The struct ttm_buffer_object. + * @new_mem: The struct ttm_resource we're moving to (copy destination). + * @new_iter: A struct ttm_kmap_iter representing the destination resource. + * @src_iter: A struct ttm_kmap_iter representing the source resource. + * + * This function is intended to be able to move out async under a + * dma-fence if desired. + */ +void ttm_move_memcpy(struct ttm_buffer_object *bo, + u32 num_pages, + struct ttm_kmap_iter *dst_iter, + struct ttm_kmap_iter *src_iter) { - int ret; - void *addr; - - *virtual = NULL; - ret = ttm_mem_io_reserve(bdev, mem); - if (ret || !mem->bus.is_iomem) - return ret; + const struct ttm_kmap_iter_ops *dst_ops = dst_iter->ops; + const struct ttm_kmap_iter_ops *src_ops = src_iter->ops; + struct ttm_tt *ttm = bo->ttm; + struct dma_buf_map src_map, dst_map; + pgoff_t i; - if (mem->bus.addr) { - addr = mem->bus.addr; - } else { - size_t bus_size = (size_t)mem->num_pages << PAGE_SHIFT; + /* Single TTM move. NOP */ + if (dst_ops->maps_tt && src_ops->maps_tt) + return; - if (mem->bus.caching == ttm_write_combined) - addr = ioremap_wc(mem->bus.offset, bus_size); -#ifdef CONFIG_X86 - else if (mem->bus.caching == ttm_cached) - addr = ioremap_cache(mem->bus.offset, bus_size); -#endif - else - addr = ioremap(mem->bus.offset, bus_size); - if (!addr) { - ttm_mem_io_free(bdev, mem); - return -ENOMEM; + /* Don't move nonexistent data. Clear destination instead. */ + if (src_ops->maps_tt && (!ttm || !ttm_tt_is_populated(ttm))) { + if (ttm && !(ttm->page_flags & TTM_PAGE_FLAG_ZERO_ALLOC)) + return; + + for (i = 0; i < num_pages; ++i) { + dst_ops->map_local(dst_iter, &dst_map, i); + if (dst_map.is_iomem) + memset_io(dst_map.vaddr_iomem, 0, PAGE_SIZE); + else + memset(dst_map.vaddr, 0, PAGE_SIZE); + if (dst_ops->unmap_local) + dst_ops->unmap_local(dst_iter, &dst_map); } + return; } - *virtual = addr; - return 0; -} - -static void ttm_resource_iounmap(struct ttm_device *bdev, - struct ttm_resource *mem, - void *virtual) -{ - if (virtual && mem->bus.addr == NULL) - iounmap(virtual); - ttm_mem_io_free(bdev, mem); -} - -static int ttm_copy_io_page(void *dst, void *src, unsigned long page) -{ - uint32_t *dstP = - (uint32_t *) ((unsigned long)dst + (page << PAGE_SHIFT)); - uint32_t *srcP = - (uint32_t *) ((unsigned long)src + (page << PAGE_SHIFT)); - - int i; - for (i = 0; i < PAGE_SIZE / sizeof(uint32_t); ++i) - iowrite32(ioread32(srcP++), dstP++); - return 0; -} - -static int ttm_copy_io_ttm_page(struct ttm_tt *ttm, void *src, - unsigned long page, - pgprot_t prot) -{ - struct page *d = ttm->pages[page]; - void *dst; - - if (!d) - return -ENOMEM; - - src = (void *)((unsigned long)src + (page << PAGE_SHIFT)); - dst = kmap_atomic_prot(d, prot); - if (!dst) - return -ENOMEM; - - memcpy_fromio(dst, src, PAGE_SIZE); - - kunmap_atomic(dst); - - return 0; -} - -static int ttm_copy_ttm_io_page(struct ttm_tt *ttm, void *dst, - unsigned long page, - pgprot_t prot) -{ - struct page *s = ttm->pages[page]; - void *src; - - if (!s) - return -ENOMEM; - - dst = (void *)((unsigned long)dst + (page << PAGE_SHIFT)); - src = kmap_atomic_prot(s, prot); - if (!src) - return -ENOMEM; - memcpy_toio(dst, src, PAGE_SIZE); + for (i = 0; i < num_pages; ++i) { + dst_ops->map_local(dst_iter, &dst_map, i); + src_ops->map_local(src_iter, &src_map, i); - kunmap_atomic(src); + drm_memcpy_from_wc(&dst_map, &src_map, PAGE_SIZE); - return 0; + if (src_ops->unmap_local) + src_ops->unmap_local(src_iter, &src_map); + if (dst_ops->unmap_local) + dst_ops->unmap_local(dst_iter, &dst_map); + } } +EXPORT_SYMBOL(ttm_move_memcpy); int ttm_bo_move_memcpy(struct ttm_buffer_object *bo, struct ttm_operation_ctx *ctx, - struct ttm_resource *new_mem) + struct ttm_resource *dst_mem) { struct ttm_device *bdev = bo->bdev; - struct ttm_resource_manager *man = ttm_manager_type(bdev, new_mem->mem_type); + struct ttm_resource_manager *dst_man = + ttm_manager_type(bo->bdev, dst_mem->mem_type); struct ttm_tt *ttm = bo->ttm; - struct ttm_resource *old_mem = &bo->mem; - struct ttm_resource old_copy = *old_mem; - void *old_iomap; - void *new_iomap; - int ret; - unsigned long i; - - ret = ttm_bo_wait_ctx(bo, ctx); - if (ret) - return ret; - - ret = ttm_resource_ioremap(bdev, old_mem, &old_iomap); - if (ret) - return ret; - ret = ttm_resource_ioremap(bdev, new_mem, &new_iomap); - if (ret) - goto out; - - /* - * Single TTM move. NOP. - */ - if (old_iomap == NULL && new_iomap == NULL) - goto out2; - - /* - * Don't move nonexistent data. Clear destination instead. - */ - if (old_iomap == NULL && - (ttm == NULL || (!ttm_tt_is_populated(ttm) && - !(ttm->page_flags & TTM_PAGE_FLAG_SWAPPED)))) { - memset_io(new_iomap, 0, new_mem->num_pages*PAGE_SIZE); - goto out2; - } + struct ttm_resource *src_mem = bo->resource; + struct ttm_resource_manager *src_man = + ttm_manager_type(bdev, src_mem->mem_type); + struct ttm_resource src_copy = *src_mem; + union { + struct ttm_kmap_iter_tt tt; + struct ttm_kmap_iter_linear_io io; + } _dst_iter, _src_iter; + struct ttm_kmap_iter *dst_iter, *src_iter; + int ret = 0; - /* - * TTM might be null for moves within the same region. - */ - if (ttm) { + if (ttm && ((ttm->page_flags & TTM_PAGE_FLAG_SWAPPED) || + dst_man->use_tt)) { ret = ttm_tt_populate(bdev, ttm, ctx); if (ret) - goto out1; + return ret; } - for (i = 0; i < new_mem->num_pages; ++i) { - if (old_iomap == NULL) { - pgprot_t prot = ttm_io_prot(bo, old_mem, PAGE_KERNEL); - ret = ttm_copy_ttm_io_page(ttm, new_iomap, i, - prot); - } else if (new_iomap == NULL) { - pgprot_t prot = ttm_io_prot(bo, new_mem, PAGE_KERNEL); - ret = ttm_copy_io_ttm_page(ttm, old_iomap, i, - prot); - } else { - ret = ttm_copy_io_page(new_iomap, old_iomap, i); - } - if (ret) - goto out1; + dst_iter = ttm_kmap_iter_linear_io_init(&_dst_iter.io, bdev, dst_mem); + if (PTR_ERR(dst_iter) == -EINVAL && dst_man->use_tt) + dst_iter = ttm_kmap_iter_tt_init(&_dst_iter.tt, bo->ttm); + if (IS_ERR(dst_iter)) + return PTR_ERR(dst_iter); + + src_iter = ttm_kmap_iter_linear_io_init(&_src_iter.io, bdev, src_mem); + if (PTR_ERR(src_iter) == -EINVAL && src_man->use_tt) + src_iter = ttm_kmap_iter_tt_init(&_src_iter.tt, bo->ttm); + if (IS_ERR(src_iter)) { + ret = PTR_ERR(src_iter); + goto out_src_iter; } - mb(); -out2: - old_copy = *old_mem; - ttm_bo_assign_mem(bo, new_mem); + ttm_move_memcpy(bo, dst_mem->num_pages, dst_iter, src_iter); + src_copy = *src_mem; + ttm_bo_move_sync_cleanup(bo, dst_mem); - if (!man->use_tt) - ttm_bo_tt_destroy(bo); + if (!src_iter->ops->maps_tt) + ttm_kmap_iter_linear_io_fini(&_src_iter.io, bdev, &src_copy); +out_src_iter: + if (!dst_iter->ops->maps_tt) + ttm_kmap_iter_linear_io_fini(&_dst_iter.io, bdev, dst_mem); -out1: - ttm_resource_iounmap(bdev, old_mem, new_iomap); -out: - ttm_resource_iounmap(bdev, &old_copy, old_iomap); - - /* - * On error, keep the mm node! - */ - if (!ret) - ttm_resource_free(bo, &old_copy); return ret; } EXPORT_SYMBOL(ttm_bo_move_memcpy); @@ -336,27 +259,7 @@ pgprot_t ttm_io_prot(struct ttm_buffer_object *bo, struct ttm_resource *res, man = ttm_manager_type(bo->bdev, res->mem_type); caching = man->use_tt ? bo->ttm->caching : res->bus.caching; - /* Cached mappings need no adjustment */ - if (caching == ttm_cached) - return tmp; - -#if defined(__i386__) || defined(__x86_64__) - if (caching == ttm_write_combined) - tmp = pgprot_writecombine(tmp); - else if (boot_cpu_data.x86 > 3) - tmp = pgprot_noncached(tmp); -#endif -#if defined(__ia64__) || defined(__arm__) || defined(__aarch64__) || \ - defined(__powerpc__) || defined(__mips__) - if (caching == ttm_write_combined) - tmp = pgprot_writecombine(tmp); - else - tmp = pgprot_noncached(tmp); -#endif -#if defined(__sparc__) - tmp = pgprot_noncached(tmp); -#endif - return tmp; + return ttm_prot_from_caching(caching, tmp); } EXPORT_SYMBOL(ttm_io_prot); @@ -365,24 +268,23 @@ static int ttm_bo_ioremap(struct ttm_buffer_object *bo, unsigned long size, struct ttm_bo_kmap_obj *map) { - struct ttm_resource *mem = &bo->mem; + struct ttm_resource *mem = bo->resource; - if (bo->mem.bus.addr) { + if (bo->resource->bus.addr) { map->bo_kmap_type = ttm_bo_map_premapped; - map->virtual = (void *)(((u8 *)bo->mem.bus.addr) + offset); + map->virtual = ((u8 *)bo->resource->bus.addr) + offset; } else { + resource_size_t res = bo->resource->bus.offset + offset; + map->bo_kmap_type = ttm_bo_map_iomap; if (mem->bus.caching == ttm_write_combined) - map->virtual = ioremap_wc(bo->mem.bus.offset + offset, - size); + map->virtual = ioremap_wc(res, size); #ifdef CONFIG_X86 else if (mem->bus.caching == ttm_cached) - map->virtual = ioremap_cache(bo->mem.bus.offset + offset, - size); + map->virtual = ioremap_cache(res, size); #endif else - map->virtual = ioremap(bo->mem.bus.offset + offset, - size); + map->virtual = ioremap(res, size); } return (!map->virtual) ? -ENOMEM : 0; } @@ -392,7 +294,7 @@ static int ttm_bo_kmap_ttm(struct ttm_buffer_object *bo, unsigned long num_pages, struct ttm_bo_kmap_obj *map) { - struct ttm_resource *mem = &bo->mem; + struct ttm_resource *mem = bo->resource; struct ttm_operation_ctx ctx = { .interruptible = false, .no_wait_gpu = false @@ -438,15 +340,15 @@ int ttm_bo_kmap(struct ttm_buffer_object *bo, map->virtual = NULL; map->bo = bo; - if (num_pages > bo->mem.num_pages) + if (num_pages > bo->resource->num_pages) return -EINVAL; - if ((start_page + num_pages) > bo->mem.num_pages) + if ((start_page + num_pages) > bo->resource->num_pages) return -EINVAL; - ret = ttm_mem_io_reserve(bo->bdev, &bo->mem); + ret = ttm_mem_io_reserve(bo->bdev, bo->resource); if (ret) return ret; - if (!bo->mem.bus.is_iomem) { + if (!bo->resource->bus.is_iomem) { return ttm_bo_kmap_ttm(bo, start_page, num_pages, map); } else { offset = start_page << PAGE_SHIFT; @@ -475,7 +377,7 @@ void ttm_bo_kunmap(struct ttm_bo_kmap_obj *map) default: BUG(); } - ttm_mem_io_free(map->bo->bdev, &map->bo->mem); + ttm_mem_io_free(map->bo->bdev, map->bo->resource); map->virtual = NULL; map->page = NULL; } @@ -483,7 +385,7 @@ EXPORT_SYMBOL(ttm_bo_kunmap); int ttm_bo_vmap(struct ttm_buffer_object *bo, struct dma_buf_map *map) { - struct ttm_resource *mem = &bo->mem; + struct ttm_resource *mem = bo->resource; int ret; ret = ttm_mem_io_reserve(bo->bdev, mem); @@ -542,7 +444,7 @@ EXPORT_SYMBOL(ttm_bo_vmap); void ttm_bo_vunmap(struct ttm_buffer_object *bo, struct dma_buf_map *map) { - struct ttm_resource *mem = &bo->mem; + struct ttm_resource *mem = bo->resource; if (dma_buf_map_is_null(map)) return; @@ -553,7 +455,7 @@ void ttm_bo_vunmap(struct ttm_buffer_object *bo, struct dma_buf_map *map) iounmap(map->vaddr_iomem); dma_buf_map_clear(map); - ttm_mem_io_free(bo->bdev, &bo->mem); + ttm_mem_io_free(bo->bdev, bo->resource); } EXPORT_SYMBOL(ttm_bo_vunmap); @@ -567,7 +469,7 @@ static int ttm_bo_wait_free_node(struct ttm_buffer_object *bo, if (!dst_use_tt) ttm_bo_tt_destroy(bo); - ttm_resource_free(bo, &bo->mem); + ttm_resource_free(bo, &bo->resource); return 0; } @@ -605,6 +507,7 @@ static int ttm_bo_move_to_ghost(struct ttm_buffer_object *bo, ghost_obj->ttm = NULL; else bo->ttm = NULL; + bo->resource = NULL; dma_resv_unlock(&ghost_obj->base._resv); ttm_bo_put(ghost_obj); @@ -615,7 +518,9 @@ static void ttm_bo_move_pipeline_evict(struct ttm_buffer_object *bo, struct dma_fence *fence) { struct ttm_device *bdev = bo->bdev; - struct ttm_resource_manager *from = ttm_manager_type(bdev, bo->mem.mem_type); + struct ttm_resource_manager *from; + + from = ttm_manager_type(bdev, bo->resource->mem_type); /** * BO doesn't have a TTM we need to bind/unbind. Just remember @@ -628,7 +533,7 @@ static void ttm_bo_move_pipeline_evict(struct ttm_buffer_object *bo, } spin_unlock(&from->move_lock); - ttm_resource_free(bo, &bo->mem); + ttm_resource_free(bo, &bo->resource); dma_fence_put(bo->moving); bo->moving = dma_fence_get(fence); @@ -641,7 +546,7 @@ int ttm_bo_move_accel_cleanup(struct ttm_buffer_object *bo, struct ttm_resource *new_mem) { struct ttm_device *bdev = bo->bdev; - struct ttm_resource_manager *from = ttm_manager_type(bdev, bo->mem.mem_type); + struct ttm_resource_manager *from = ttm_manager_type(bdev, bo->resource->mem_type); struct ttm_resource_manager *man = ttm_manager_type(bdev, new_mem->mem_type); int ret = 0; @@ -662,26 +567,82 @@ int ttm_bo_move_accel_cleanup(struct ttm_buffer_object *bo, } EXPORT_SYMBOL(ttm_bo_move_accel_cleanup); +/** + * ttm_bo_pipeline_gutting - purge the contents of a bo + * @bo: The buffer object + * + * Purge the contents of a bo, async if the bo is not idle. + * After a successful call, the bo is left unpopulated in + * system placement. The function may wait uninterruptible + * for idle on OOM. + * + * Return: 0 if successful, negative error code on failure. + */ int ttm_bo_pipeline_gutting(struct ttm_buffer_object *bo) { static const struct ttm_place sys_mem = { .mem_type = TTM_PL_SYSTEM }; struct ttm_buffer_object *ghost; + struct ttm_resource *sys_res; + struct ttm_tt *ttm; int ret; - ret = ttm_buffer_object_transfer(bo, &ghost); + ret = ttm_resource_alloc(bo, &sys_mem, &sys_res); if (ret) return ret; + /* If already idle, no need for ghost object dance. */ + ret = ttm_bo_wait(bo, false, true); + if (ret != -EBUSY) { + if (!bo->ttm) { + /* See comment below about clearing. */ + ret = ttm_tt_create(bo, true); + if (ret) + goto error_free_sys_mem; + } else { + ttm_tt_unpopulate(bo->bdev, bo->ttm); + if (bo->type == ttm_bo_type_device) + ttm_tt_mark_for_clear(bo->ttm); + } + ttm_resource_free(bo, &bo->resource); + ttm_bo_assign_mem(bo, sys_res); + return 0; + } + + /* + * We need an unpopulated ttm_tt after giving our current one, + * if any, to the ghost object. And we can't afford to fail + * creating one *after* the operation. If the bo subsequently gets + * resurrected, make sure it's cleared (if ttm_bo_type_device) + * to avoid leaking sensitive information to user-space. + */ + + ttm = bo->ttm; + bo->ttm = NULL; + ret = ttm_tt_create(bo, true); + swap(bo->ttm, ttm); + if (ret) + goto error_free_sys_mem; + + ret = ttm_buffer_object_transfer(bo, &ghost); + if (ret) + goto error_destroy_tt; + ret = dma_resv_copy_fences(&ghost->base._resv, bo->base.resv); /* Last resort, wait for the BO to be idle when we are OOM */ if (ret) ttm_bo_wait(bo, false, false); - ttm_resource_alloc(bo, &sys_mem, &bo->mem); - bo->ttm = NULL; - dma_resv_unlock(&ghost->base._resv); ttm_bo_put(ghost); - + bo->ttm = ttm; + bo->resource = NULL; + ttm_bo_assign_mem(bo, sys_res); return 0; + +error_destroy_tt: + ttm_tt_destroy(bo->bdev, ttm); + +error_free_sys_mem: + ttm_resource_free(bo, &sys_res); + return ret; } diff --git a/drivers/gpu/drm/ttm/ttm_bo_vm.c b/drivers/gpu/drm/ttm/ttm_bo_vm.c index 9bd15cb39145..f56be5bc0861 100644 --- a/drivers/gpu/drm/ttm/ttm_bo_vm.c +++ b/drivers/gpu/drm/ttm/ttm_bo_vm.c @@ -102,7 +102,7 @@ static unsigned long ttm_bo_io_mem_pfn(struct ttm_buffer_object *bo, if (bdev->funcs->io_mem_pfn) return bdev->funcs->io_mem_pfn(bo, page_offset); - return (bo->mem.bus.offset >> PAGE_SHIFT) + page_offset; + return (bo->resource->bus.offset >> PAGE_SHIFT) + page_offset; } /** @@ -200,10 +200,10 @@ static vm_fault_t ttm_bo_vm_insert_huge(struct vm_fault *vmf, /* Fault should not cross bo boundary. */ page_offset &= ~(fault_page_size - 1); - if (page_offset + fault_page_size > bo->mem.num_pages) + if (page_offset + fault_page_size > bo->resource->num_pages) goto out_fallback; - if (bo->mem.bus.is_iomem) + if (bo->resource->bus.is_iomem) pfn = ttm_bo_io_mem_pfn(bo, page_offset); else pfn = page_to_pfn(ttm->pages[page_offset]); @@ -213,7 +213,7 @@ static vm_fault_t ttm_bo_vm_insert_huge(struct vm_fault *vmf, goto out_fallback; /* Check that memory is contiguous. */ - if (!bo->mem.bus.is_iomem) { + if (!bo->resource->bus.is_iomem) { for (i = 1; i < fault_page_size; ++i) { if (page_to_pfn(ttm->pages[page_offset + i]) != pfn + i) goto out_fallback; @@ -299,7 +299,7 @@ vm_fault_t ttm_bo_vm_fault_reserved(struct vm_fault *vmf, if (unlikely(ret != 0)) return ret; - err = ttm_mem_io_reserve(bdev, &bo->mem); + err = ttm_mem_io_reserve(bdev, bo->resource); if (unlikely(err != 0)) return VM_FAULT_SIGBUS; @@ -308,11 +308,11 @@ vm_fault_t ttm_bo_vm_fault_reserved(struct vm_fault *vmf, page_last = vma_pages(vma) + vma->vm_pgoff - drm_vma_node_start(&bo->base.vma_node); - if (unlikely(page_offset >= bo->mem.num_pages)) + if (unlikely(page_offset >= bo->resource->num_pages)) return VM_FAULT_SIGBUS; - prot = ttm_io_prot(bo, &bo->mem, prot); - if (!bo->mem.bus.is_iomem) { + prot = ttm_io_prot(bo, bo->resource, prot); + if (!bo->resource->bus.is_iomem) { struct ttm_operation_ctx ctx = { .interruptible = false, .no_wait_gpu = false, @@ -337,7 +337,7 @@ vm_fault_t ttm_bo_vm_fault_reserved(struct vm_fault *vmf, * first page. */ for (i = 0; i < num_prefault; ++i) { - if (bo->mem.bus.is_iomem) { + if (bo->resource->bus.is_iomem) { pfn = ttm_bo_io_mem_pfn(bo, page_offset); } else { page = ttm->pages[page_offset]; @@ -359,12 +359,7 @@ vm_fault_t ttm_bo_vm_fault_reserved(struct vm_fault *vmf, * at arbitrary times while the data is mmap'ed. * See vmf_insert_mixed_prot() for a discussion. */ - if (vma->vm_flags & VM_MIXEDMAP) - ret = vmf_insert_mixed_prot(vma, address, - __pfn_to_pfn_t(pfn, PFN_DEV), - prot); - else - ret = vmf_insert_pfn_prot(vma, address, pfn, prot); + ret = vmf_insert_pfn_prot(vma, address, pfn, prot); /* Never error on prefaulted PTEs */ if (unlikely((ret & VM_FAULT_ERROR))) { @@ -411,15 +406,9 @@ vm_fault_t ttm_bo_vm_dummy_page(struct vm_fault *vmf, pgprot_t prot) pfn = page_to_pfn(page); /* Prefault the entire VMA range right away to avoid further faults */ - for (address = vma->vm_start; address < vma->vm_end; address += PAGE_SIZE) { - - if (vma->vm_flags & VM_MIXEDMAP) - ret = vmf_insert_mixed_prot(vma, address, - __pfn_to_pfn_t(pfn, PFN_DEV), - prot); - else - ret = vmf_insert_pfn_prot(vma, address, pfn, prot); - } + for (address = vma->vm_start; address < vma->vm_end; + address += PAGE_SIZE) + ret = vmf_insert_pfn_prot(vma, address, pfn, prot); return ret; } @@ -521,14 +510,14 @@ int ttm_bo_vm_access(struct vm_area_struct *vma, unsigned long addr, << PAGE_SHIFT); int ret; - if (len < 1 || (offset + len) >> PAGE_SHIFT > bo->mem.num_pages) + if (len < 1 || (offset + len) >> PAGE_SHIFT > bo->resource->num_pages) return -EIO; ret = ttm_bo_reserve(bo, true, false, NULL); if (ret) return ret; - switch (bo->mem.mem_type) { + switch (bo->resource->mem_type) { case TTM_PL_SYSTEM: if (unlikely(bo->ttm->page_flags & TTM_PAGE_FLAG_SWAPPED)) { ret = ttm_tt_swapin(bo->ttm); @@ -560,8 +549,14 @@ static const struct vm_operations_struct ttm_bo_vm_ops = { .access = ttm_bo_vm_access, }; -static void ttm_bo_mmap_vma_setup(struct ttm_buffer_object *bo, struct vm_area_struct *vma) +int ttm_bo_mmap_obj(struct vm_area_struct *vma, struct ttm_buffer_object *bo) { + /* Enforce no COW since would have really strange behavior with it. */ + if (is_cow_mapping(vma->vm_flags)) + return -EINVAL; + + ttm_bo_get(bo); + /* * Drivers may want to override the vm_ops field. Otherwise we * use TTM's default callbacks. @@ -576,21 +571,8 @@ static void ttm_bo_mmap_vma_setup(struct ttm_buffer_object *bo, struct vm_area_s vma->vm_private_data = bo; - /* - * We'd like to use VM_PFNMAP on shared mappings, where - * (vma->vm_flags & VM_SHARED) != 0, for performance reasons, - * but for some reason VM_PFNMAP + x86 PAT + write-combine is very - * bad for performance. Until that has been sorted out, use - * VM_MIXEDMAP on all mappings. See freedesktop.org bug #75719 - */ - vma->vm_flags |= VM_MIXEDMAP; + vma->vm_flags |= VM_PFNMAP; vma->vm_flags |= VM_IO | VM_DONTEXPAND | VM_DONTDUMP; -} - -int ttm_bo_mmap_obj(struct vm_area_struct *vma, struct ttm_buffer_object *bo) -{ - ttm_bo_get(bo); - ttm_bo_mmap_vma_setup(bo, vma); return 0; } EXPORT_SYMBOL(ttm_bo_mmap_obj); diff --git a/drivers/gpu/drm/ttm/ttm_module.c b/drivers/gpu/drm/ttm/ttm_module.c index 56b0efdba1a9..997c458f68a9 100644 --- a/drivers/gpu/drm/ttm/ttm_module.c +++ b/drivers/gpu/drm/ttm/ttm_module.c @@ -31,12 +31,47 @@ */ #include <linux/module.h> #include <linux/device.h> +#include <linux/pgtable.h> #include <linux/sched.h> #include <linux/debugfs.h> #include <drm/drm_sysfs.h> +#include <drm/ttm/ttm_caching.h> #include "ttm_module.h" +/** + * ttm_prot_from_caching - Modify the page protection according to the + * ttm cacing mode + * @caching: The ttm caching mode + * @tmp: The original page protection + * + * Return: The modified page protection + */ +pgprot_t ttm_prot_from_caching(enum ttm_caching caching, pgprot_t tmp) +{ + /* Cached mappings need no adjustment */ + if (caching == ttm_cached) + return tmp; + +#if defined(__i386__) || defined(__x86_64__) + if (caching == ttm_write_combined) + tmp = pgprot_writecombine(tmp); + else if (boot_cpu_data.x86 > 3) + tmp = pgprot_noncached(tmp); +#endif +#if defined(__ia64__) || defined(__arm__) || defined(__aarch64__) || \ + defined(__powerpc__) || defined(__mips__) + if (caching == ttm_write_combined) + tmp = pgprot_writecombine(tmp); + else + tmp = pgprot_noncached(tmp); +#endif +#if defined(__sparc__) + tmp = pgprot_noncached(tmp); +#endif + return tmp; +} + struct dentry *ttm_debugfs_root; static int __init ttm_init(void) diff --git a/drivers/gpu/drm/ttm/ttm_range_manager.c b/drivers/gpu/drm/ttm/ttm_range_manager.c index b9d5da6e6a81..03395386e8a7 100644 --- a/drivers/gpu/drm/ttm/ttm_range_manager.c +++ b/drivers/gpu/drm/ttm/ttm_range_manager.c @@ -29,12 +29,13 @@ * Authors: Thomas Hellstrom <thellstrom-at-vmware-dot-com> */ -#include <drm/ttm/ttm_bo_driver.h> +#include <drm/ttm/ttm_device.h> #include <drm/ttm/ttm_placement.h> +#include <drm/ttm/ttm_range_manager.h> +#include <drm/ttm/ttm_bo_api.h> #include <drm/drm_mm.h> #include <linux/slab.h> #include <linux/spinlock.h> -#include <linux/module.h> /* * Currently we use a spinlock for the lock, but a mutex *may* be @@ -57,11 +58,11 @@ to_range_manager(struct ttm_resource_manager *man) static int ttm_range_man_alloc(struct ttm_resource_manager *man, struct ttm_buffer_object *bo, const struct ttm_place *place, - struct ttm_resource *mem) + struct ttm_resource **res) { struct ttm_range_manager *rman = to_range_manager(man); + struct ttm_range_mgr_node *node; struct drm_mm *mm = &rman->mm; - struct drm_mm_node *node; enum drm_mm_insert_mode mode; unsigned long lpfn; int ret; @@ -70,7 +71,7 @@ static int ttm_range_man_alloc(struct ttm_resource_manager *man, if (!lpfn) lpfn = man->size; - node = kzalloc(sizeof(*node), GFP_KERNEL); + node = kzalloc(struct_size(node, mm_nodes, 1), GFP_KERNEL); if (!node) return -ENOMEM; @@ -78,35 +79,36 @@ static int ttm_range_man_alloc(struct ttm_resource_manager *man, if (place->flags & TTM_PL_FLAG_TOPDOWN) mode = DRM_MM_INSERT_HIGH; + ttm_resource_init(bo, place, &node->base); + spin_lock(&rman->lock); - ret = drm_mm_insert_node_in_range(mm, node, mem->num_pages, + ret = drm_mm_insert_node_in_range(mm, &node->mm_nodes[0], + node->base.num_pages, bo->page_alignment, 0, place->fpfn, lpfn, mode); spin_unlock(&rman->lock); if (unlikely(ret)) { kfree(node); - } else { - mem->mm_node = node; - mem->start = node->start; + return ret; } - return ret; + node->base.start = node->mm_nodes[0].start; + *res = &node->base; + return 0; } static void ttm_range_man_free(struct ttm_resource_manager *man, - struct ttm_resource *mem) + struct ttm_resource *res) { + struct ttm_range_mgr_node *node = to_ttm_range_mgr_node(res); struct ttm_range_manager *rman = to_range_manager(man); - if (mem->mm_node) { - spin_lock(&rman->lock); - drm_mm_remove_node(mem->mm_node); - spin_unlock(&rman->lock); + spin_lock(&rman->lock); + drm_mm_remove_node(&node->mm_nodes[0]); + spin_unlock(&rman->lock); - kfree(mem->mm_node); - mem->mm_node = NULL; - } + kfree(node); } static void ttm_range_man_debug(struct ttm_resource_manager *man, @@ -125,6 +127,17 @@ static const struct ttm_resource_manager_func ttm_range_manager_func = { .debug = ttm_range_man_debug }; +/** + * ttm_range_man_init + * + * @bdev: ttm device + * @type: memory manager type + * @use_tt: if the memory manager uses tt + * @p_size: size of area to be managed in pages. + * + * Initialise a generic range manager for the selected memory type. + * The range manager is installed for this device in the type slot. + */ int ttm_range_man_init(struct ttm_device *bdev, unsigned type, bool use_tt, unsigned long p_size) @@ -152,6 +165,14 @@ int ttm_range_man_init(struct ttm_device *bdev, } EXPORT_SYMBOL(ttm_range_man_init); +/** + * ttm_range_man_fini + * + * @bdev: ttm device + * @type: memory manager type + * + * Remove the generic range manager from a slot and tear it down. + */ int ttm_range_man_fini(struct ttm_device *bdev, unsigned type) { diff --git a/drivers/gpu/drm/ttm/ttm_resource.c b/drivers/gpu/drm/ttm/ttm_resource.c index 59e2b7157e41..2431717376e7 100644 --- a/drivers/gpu/drm/ttm/ttm_resource.c +++ b/drivers/gpu/drm/ttm/ttm_resource.c @@ -22,17 +22,17 @@ * Authors: Christian König */ +#include <linux/dma-buf-map.h> +#include <linux/io-mapping.h> +#include <linux/scatterlist.h> + #include <drm/ttm/ttm_resource.h> #include <drm/ttm/ttm_bo_driver.h> -int ttm_resource_alloc(struct ttm_buffer_object *bo, - const struct ttm_place *place, - struct ttm_resource *res) +void ttm_resource_init(struct ttm_buffer_object *bo, + const struct ttm_place *place, + struct ttm_resource *res) { - struct ttm_resource_manager *man = - ttm_manager_type(bo->bdev, place->mem_type); - - res->mm_node = NULL; res->start = 0; res->num_pages = PFN_UP(bo->base.size); res->mem_type = place->mem_type; @@ -41,18 +41,29 @@ int ttm_resource_alloc(struct ttm_buffer_object *bo, res->bus.offset = 0; res->bus.is_iomem = false; res->bus.caching = ttm_cached; - - return man->func->alloc(man, bo, place, res); } +EXPORT_SYMBOL(ttm_resource_init); -void ttm_resource_free(struct ttm_buffer_object *bo, struct ttm_resource *res) +int ttm_resource_alloc(struct ttm_buffer_object *bo, + const struct ttm_place *place, + struct ttm_resource **res_ptr) { struct ttm_resource_manager *man = - ttm_manager_type(bo->bdev, res->mem_type); + ttm_manager_type(bo->bdev, place->mem_type); - man->func->free(man, res); - res->mm_node = NULL; - res->mem_type = TTM_PL_SYSTEM; + return man->func->alloc(man, bo, place, res_ptr); +} + +void ttm_resource_free(struct ttm_buffer_object *bo, struct ttm_resource **res) +{ + struct ttm_resource_manager *man; + + if (!*res) + return; + + man = ttm_manager_type(bo->bdev, (*res)->mem_type); + man->func->free(man, *res); + *res = NULL; } EXPORT_SYMBOL(ttm_resource_free); @@ -147,3 +158,192 @@ void ttm_resource_manager_debug(struct ttm_resource_manager *man, man->func->debug(man, p); } EXPORT_SYMBOL(ttm_resource_manager_debug); + +static void ttm_kmap_iter_iomap_map_local(struct ttm_kmap_iter *iter, + struct dma_buf_map *dmap, + pgoff_t i) +{ + struct ttm_kmap_iter_iomap *iter_io = + container_of(iter, typeof(*iter_io), base); + void __iomem *addr; + +retry: + while (i >= iter_io->cache.end) { + iter_io->cache.sg = iter_io->cache.sg ? + sg_next(iter_io->cache.sg) : iter_io->st->sgl; + iter_io->cache.i = iter_io->cache.end; + iter_io->cache.end += sg_dma_len(iter_io->cache.sg) >> + PAGE_SHIFT; + iter_io->cache.offs = sg_dma_address(iter_io->cache.sg) - + iter_io->start; + } + + if (i < iter_io->cache.i) { + iter_io->cache.end = 0; + iter_io->cache.sg = NULL; + goto retry; + } + + addr = io_mapping_map_local_wc(iter_io->iomap, iter_io->cache.offs + + (((resource_size_t)i - iter_io->cache.i) + << PAGE_SHIFT)); + dma_buf_map_set_vaddr_iomem(dmap, addr); +} + +static void ttm_kmap_iter_iomap_unmap_local(struct ttm_kmap_iter *iter, + struct dma_buf_map *map) +{ + io_mapping_unmap_local(map->vaddr_iomem); +} + +static const struct ttm_kmap_iter_ops ttm_kmap_iter_io_ops = { + .map_local = ttm_kmap_iter_iomap_map_local, + .unmap_local = ttm_kmap_iter_iomap_unmap_local, + .maps_tt = false, +}; + +/** + * ttm_kmap_iter_iomap_init - Initialize a struct ttm_kmap_iter_iomap + * @iter_io: The struct ttm_kmap_iter_iomap to initialize. + * @iomap: The struct io_mapping representing the underlying linear io_memory. + * @st: sg_table into @iomap, representing the memory of the struct + * ttm_resource. + * @start: Offset that needs to be subtracted from @st to make + * sg_dma_address(st->sgl) - @start == 0 for @iomap start. + * + * Return: Pointer to the embedded struct ttm_kmap_iter. + */ +struct ttm_kmap_iter * +ttm_kmap_iter_iomap_init(struct ttm_kmap_iter_iomap *iter_io, + struct io_mapping *iomap, + struct sg_table *st, + resource_size_t start) +{ + iter_io->base.ops = &ttm_kmap_iter_io_ops; + iter_io->iomap = iomap; + iter_io->st = st; + iter_io->start = start; + memset(&iter_io->cache, 0, sizeof(iter_io->cache)); + + return &iter_io->base; +} +EXPORT_SYMBOL(ttm_kmap_iter_iomap_init); + +/** + * DOC: Linear io iterator + * + * This code should die in the not too near future. Best would be if we could + * make io-mapping use memremap for all io memory, and have memremap + * implement a kmap_local functionality. We could then strip a huge amount of + * code. These linear io iterators are implemented to mimic old functionality, + * and they don't use kmap_local semantics at all internally. Rather ioremap or + * friends, and at least on 32-bit they add global TLB flushes and points + * of failure. + */ + +static void ttm_kmap_iter_linear_io_map_local(struct ttm_kmap_iter *iter, + struct dma_buf_map *dmap, + pgoff_t i) +{ + struct ttm_kmap_iter_linear_io *iter_io = + container_of(iter, typeof(*iter_io), base); + + *dmap = iter_io->dmap; + dma_buf_map_incr(dmap, i * PAGE_SIZE); +} + +static const struct ttm_kmap_iter_ops ttm_kmap_iter_linear_io_ops = { + .map_local = ttm_kmap_iter_linear_io_map_local, + .maps_tt = false, +}; + +/** + * ttm_kmap_iter_linear_io_init - Initialize an iterator for linear io memory + * @iter_io: The iterator to initialize + * @bdev: The TTM device + * @mem: The ttm resource representing the iomap. + * + * This function is for internal TTM use only. It sets up a memcpy kmap iterator + * pointing at a linear chunk of io memory. + * + * Return: A pointer to the embedded struct ttm_kmap_iter or error pointer on + * failure. + */ +struct ttm_kmap_iter * +ttm_kmap_iter_linear_io_init(struct ttm_kmap_iter_linear_io *iter_io, + struct ttm_device *bdev, + struct ttm_resource *mem) +{ + int ret; + + ret = ttm_mem_io_reserve(bdev, mem); + if (ret) + goto out_err; + if (!mem->bus.is_iomem) { + ret = -EINVAL; + goto out_io_free; + } + + if (mem->bus.addr) { + dma_buf_map_set_vaddr(&iter_io->dmap, mem->bus.addr); + iter_io->needs_unmap = false; + } else { + size_t bus_size = (size_t)mem->num_pages << PAGE_SHIFT; + + iter_io->needs_unmap = true; + memset(&iter_io->dmap, 0, sizeof(iter_io->dmap)); + if (mem->bus.caching == ttm_write_combined) + dma_buf_map_set_vaddr_iomem(&iter_io->dmap, + ioremap_wc(mem->bus.offset, + bus_size)); + else if (mem->bus.caching == ttm_cached) + dma_buf_map_set_vaddr(&iter_io->dmap, + memremap(mem->bus.offset, bus_size, + MEMREMAP_WB | + MEMREMAP_WT | + MEMREMAP_WC)); + + /* If uncached requested or if mapping cached or wc failed */ + if (dma_buf_map_is_null(&iter_io->dmap)) + dma_buf_map_set_vaddr_iomem(&iter_io->dmap, + ioremap(mem->bus.offset, + bus_size)); + + if (dma_buf_map_is_null(&iter_io->dmap)) { + ret = -ENOMEM; + goto out_io_free; + } + } + + iter_io->base.ops = &ttm_kmap_iter_linear_io_ops; + return &iter_io->base; + +out_io_free: + ttm_mem_io_free(bdev, mem); +out_err: + return ERR_PTR(ret); +} + +/** + * ttm_kmap_iter_linear_io_fini - Clean up an iterator for linear io memory + * @iter_io: The iterator to initialize + * @bdev: The TTM device + * @mem: The ttm resource representing the iomap. + * + * This function is for internal TTM use only. It cleans up a memcpy kmap + * iterator initialized by ttm_kmap_iter_linear_io_init. + */ +void +ttm_kmap_iter_linear_io_fini(struct ttm_kmap_iter_linear_io *iter_io, + struct ttm_device *bdev, + struct ttm_resource *mem) +{ + if (iter_io->needs_unmap && dma_buf_map_is_set(&iter_io->dmap)) { + if (iter_io->dmap.is_iomem) + iounmap(iter_io->dmap.vaddr_iomem); + else + memunmap(iter_io->dmap.vaddr); + } + + ttm_mem_io_free(bdev, mem); +} diff --git a/drivers/gpu/drm/ttm/ttm_sys_manager.c b/drivers/gpu/drm/ttm/ttm_sys_manager.c index 474221e863d0..63aca52f75e1 100644 --- a/drivers/gpu/drm/ttm/ttm_sys_manager.c +++ b/drivers/gpu/drm/ttm/ttm_sys_manager.c @@ -3,20 +3,27 @@ #include <drm/ttm/ttm_resource.h> #include <drm/ttm/ttm_device.h> #include <drm/ttm/ttm_placement.h> +#include <linux/slab.h> #include "ttm_module.h" static int ttm_sys_man_alloc(struct ttm_resource_manager *man, struct ttm_buffer_object *bo, const struct ttm_place *place, - struct ttm_resource *mem) + struct ttm_resource **res) { + *res = kzalloc(sizeof(**res), GFP_KERNEL); + if (!*res) + return -ENOMEM; + + ttm_resource_init(bo, place, *res); return 0; } static void ttm_sys_man_free(struct ttm_resource_manager *man, - struct ttm_resource *mem) + struct ttm_resource *res) { + kfree(res); } static const struct ttm_resource_manager_func ttm_sys_manager_func = { diff --git a/drivers/gpu/drm/ttm/ttm_tt.c b/drivers/gpu/drm/ttm/ttm_tt.c index 539e0232cb3b..24031a8acd2d 100644 --- a/drivers/gpu/drm/ttm/ttm_tt.c +++ b/drivers/gpu/drm/ttm/ttm_tt.c @@ -415,7 +415,7 @@ DEFINE_SHOW_ATTRIBUTE(ttm_tt_debugfs_shrink); #endif -/** +/* * ttm_tt_mgr_init - register with the MM shrinker * * Register with the MM shrinker for swapping out BOs. @@ -433,3 +433,48 @@ void ttm_tt_mgr_init(unsigned long num_pages, unsigned long num_dma32_pages) if (!ttm_dma32_pages_limit) ttm_dma32_pages_limit = num_dma32_pages; } + +static void ttm_kmap_iter_tt_map_local(struct ttm_kmap_iter *iter, + struct dma_buf_map *dmap, + pgoff_t i) +{ + struct ttm_kmap_iter_tt *iter_tt = + container_of(iter, typeof(*iter_tt), base); + + dma_buf_map_set_vaddr(dmap, kmap_local_page_prot(iter_tt->tt->pages[i], + iter_tt->prot)); +} + +static void ttm_kmap_iter_tt_unmap_local(struct ttm_kmap_iter *iter, + struct dma_buf_map *map) +{ + kunmap_local(map->vaddr); +} + +static const struct ttm_kmap_iter_ops ttm_kmap_iter_tt_ops = { + .map_local = ttm_kmap_iter_tt_map_local, + .unmap_local = ttm_kmap_iter_tt_unmap_local, + .maps_tt = true, +}; + +/** + * ttm_kmap_iter_tt_init - Initialize a struct ttm_kmap_iter_tt + * @iter_tt: The struct ttm_kmap_iter_tt to initialize. + * @tt: Struct ttm_tt holding page pointers of the struct ttm_resource. + * + * Return: Pointer to the embedded struct ttm_kmap_iter. + */ +struct ttm_kmap_iter * +ttm_kmap_iter_tt_init(struct ttm_kmap_iter_tt *iter_tt, + struct ttm_tt *tt) +{ + iter_tt->base.ops = &ttm_kmap_iter_tt_ops; + iter_tt->tt = tt; + if (tt) + iter_tt->prot = ttm_prot_from_caching(tt->caching, PAGE_KERNEL); + else + iter_tt->prot = PAGE_KERNEL; + + return &iter_tt->base; +} +EXPORT_SYMBOL(ttm_kmap_iter_tt_init); diff --git a/drivers/gpu/drm/vboxvideo/hgsmi_base.c b/drivers/gpu/drm/vboxvideo/hgsmi_base.c index 361d3193258e..8c041d7ce4f1 100644 --- a/drivers/gpu/drm/vboxvideo/hgsmi_base.c +++ b/drivers/gpu/drm/vboxvideo/hgsmi_base.c @@ -9,7 +9,8 @@ #include "hgsmi_ch_setup.h" /** - * Inform the host of the location of the host flags in VRAM via an HGSMI cmd. + * hgsmi_report_flags_location - Inform the host of the location of + * the host flags in VRAM via an HGSMI cmd. * Return: 0 or negative errno value. * @ctx: The context of the guest heap to use. * @location: The offset chosen for the flags within guest VRAM. @@ -33,7 +34,8 @@ int hgsmi_report_flags_location(struct gen_pool *ctx, u32 location) } /** - * Notify the host of HGSMI-related guest capabilities via an HGSMI command. + * hgsmi_send_caps_info - Notify the host of HGSMI-related guest capabilities + * via an HGSMI command. * Return: 0 or negative errno value. * @ctx: The context of the guest heap to use. * @caps: The capabilities to report, see vbva_caps. @@ -71,7 +73,8 @@ int hgsmi_test_query_conf(struct gen_pool *ctx) } /** - * Query the host for an HGSMI configuration parameter via an HGSMI command. + * hgsmi_query_conf - Query the host for an HGSMI configuration + * parameter via an HGSMI command. * Return: 0 or negative errno value. * @ctx: The context containing the heap used. * @index: The index of the parameter to query. @@ -99,7 +102,8 @@ int hgsmi_query_conf(struct gen_pool *ctx, u32 index, u32 *value_ret) } /** - * Pass the host a new mouse pointer shape via an HGSMI command. + * hgsmi_update_pointer_shape - Pass the host a new mouse pointer shape + * via an HGSMI command. * Return: 0 or negative errno value. * @ctx: The context containing the heap to be used. * @flags: Cursor flags. @@ -171,9 +175,10 @@ int hgsmi_update_pointer_shape(struct gen_pool *ctx, u32 flags, } /** - * Report the guest cursor position. The host may wish to use this information - * to re-position its own cursor (though this is currently unlikely). The - * current host cursor position is returned. + * hgsmi_cursor_position - Report the guest cursor position. The host may + * wish to use this information to re-position its + * own cursor (though this is currently unlikely). + * The current host cursor position is returned. * Return: 0 or negative errno value. * @ctx: The context containing the heap used. * @report_position: Are we reporting a position? diff --git a/drivers/gpu/drm/vboxvideo/modesetting.c b/drivers/gpu/drm/vboxvideo/modesetting.c index 7580b9002379..10b32d986b95 100644 --- a/drivers/gpu/drm/vboxvideo/modesetting.c +++ b/drivers/gpu/drm/vboxvideo/modesetting.c @@ -8,9 +8,11 @@ #include "hgsmi_channels.h" /** - * Set a video mode via an HGSMI request. The views must have been - * initialised first using @a VBoxHGSMISendViewInfo and if the mode is being - * set on the first display then it must be set first using registers. + * hgsmi_process_display_info - Set a video mode via an HGSMI request. + * The views must have been initialised first + * using @a VBoxHGSMISendViewInfo and if the mode + * is being set on the first display then it must + * be set first using registers. * @ctx: The context containing the heap to use. * @display: The screen number. * @origin_x: The horizontal displacement relative to the first scrn. @@ -51,10 +53,12 @@ void hgsmi_process_display_info(struct gen_pool *ctx, u32 display, } /** - * Report the rectangle relative to which absolute pointer events should be - * expressed. This information remains valid until the next VBVA resize event - * for any screen, at which time it is reset to the bounding rectangle of all - * virtual screens. + * hgsmi_update_input_mapping - Report the rectangle relative to which absolute + * pointer events should be expressed. This + * information remains valid until the next VBVA + * resize event for any screen, at which time it is + * reset to the bounding rectangle of all virtual + * screens. * Return: 0 or negative errno value. * @ctx: The context containing the heap to use. * @origin_x: Upper left X co-ordinate relative to the first screen. @@ -84,7 +88,7 @@ int hgsmi_update_input_mapping(struct gen_pool *ctx, s32 origin_x, s32 origin_y, } /** - * Get most recent video mode hints. + * hgsmi_get_mode_hints - Get most recent video mode hints. * Return: 0 or negative errno value. * @ctx: The context containing the heap to use. * @screens: The number of screens to query hints for, starting at 0. diff --git a/drivers/gpu/drm/vc4/vc4_hdmi.c b/drivers/gpu/drm/vc4/vc4_hdmi.c index f9de8632a28b..3c4cc133e3df 100644 --- a/drivers/gpu/drm/vc4/vc4_hdmi.c +++ b/drivers/gpu/drm/vc4/vc4_hdmi.c @@ -166,10 +166,9 @@ vc4_hdmi_connector_detect(struct drm_connector *connector, bool force) struct vc4_hdmi *vc4_hdmi = connector_to_vc4_hdmi(connector); bool connected = false; - if (vc4_hdmi->hpd_gpio) { - if (gpio_get_value_cansleep(vc4_hdmi->hpd_gpio) ^ - vc4_hdmi->hpd_active_low) - connected = true; + if (vc4_hdmi->hpd_gpio && + gpiod_get_value_cansleep(vc4_hdmi->hpd_gpio)) { + connected = true; } else if (drm_probe_ddc(vc4_hdmi->ddc)) { connected = true; } else if (HDMI_READ(HDMI_HOTPLUG) & VC4_HDMI_HOTPLUG_CONNECTED) { @@ -2105,7 +2104,6 @@ static int vc4_hdmi_bind(struct device *dev, struct device *master, void *data) struct vc4_hdmi *vc4_hdmi; struct drm_encoder *encoder; struct device_node *ddc_node; - u32 value; int ret; vc4_hdmi = devm_kzalloc(dev, sizeof(*vc4_hdmi), GFP_KERNEL); @@ -2144,18 +2142,10 @@ static int vc4_hdmi_bind(struct device *dev, struct device *master, void *data) /* Only use the GPIO HPD pin if present in the DT, otherwise * we'll use the HDMI core's register. */ - if (of_find_property(dev->of_node, "hpd-gpios", &value)) { - enum of_gpio_flags hpd_gpio_flags; - - vc4_hdmi->hpd_gpio = of_get_named_gpio_flags(dev->of_node, - "hpd-gpios", 0, - &hpd_gpio_flags); - if (vc4_hdmi->hpd_gpio < 0) { - ret = vc4_hdmi->hpd_gpio; - goto err_unprepare_hsm; - } - - vc4_hdmi->hpd_active_low = hpd_gpio_flags & OF_GPIO_ACTIVE_LOW; + vc4_hdmi->hpd_gpio = devm_gpiod_get_optional(dev, "hpd", GPIOD_IN); + if (IS_ERR(vc4_hdmi->hpd_gpio)) { + ret = PTR_ERR(vc4_hdmi->hpd_gpio); + goto err_put_ddc; } vc4_hdmi->disable_wifi_frequencies = @@ -2209,8 +2199,8 @@ err_destroy_conn: vc4_hdmi_connector_destroy(&vc4_hdmi->connector); err_destroy_encoder: drm_encoder_cleanup(encoder); -err_unprepare_hsm: pm_runtime_disable(dev); +err_put_ddc: put_device(&vc4_hdmi->ddc->dev); return ret; diff --git a/drivers/gpu/drm/vc4/vc4_hdmi.h b/drivers/gpu/drm/vc4/vc4_hdmi.h index 39bd2c413ec0..884d245507a9 100644 --- a/drivers/gpu/drm/vc4/vc4_hdmi.h +++ b/drivers/gpu/drm/vc4/vc4_hdmi.h @@ -148,8 +148,7 @@ struct vc4_hdmi { /* VC5 Only */ void __iomem *rm_regs; - int hpd_gpio; - bool hpd_active_low; + struct gpio_desc *hpd_gpio; /* * On some systems (like the RPi4), some modes are in the same diff --git a/drivers/gpu/drm/vgem/vgem_drv.c b/drivers/gpu/drm/vgem/vgem_drv.c index a0e75f1d5d01..bf38a7e319d1 100644 --- a/drivers/gpu/drm/vgem/vgem_drv.c +++ b/drivers/gpu/drm/vgem/vgem_drv.c @@ -25,7 +25,7 @@ * Ben Widawsky <ben@bwidawsk.net> */ -/** +/* * This is vgem, a (non-hardware-backed) GEM service. This is used by Mesa's * software renderer and the X server for efficient buffer sharing. */ diff --git a/drivers/gpu/drm/vgem/vgem_fence.c b/drivers/gpu/drm/vgem/vgem_fence.c index 2902dc6e64fa..bd6f75285fd9 100644 --- a/drivers/gpu/drm/vgem/vgem_fence.c +++ b/drivers/gpu/drm/vgem/vgem_fence.c @@ -151,8 +151,7 @@ int vgem_fence_attach_ioctl(struct drm_device *dev, /* Check for a conflicting fence */ resv = obj->resv; - if (!dma_resv_test_signaled_rcu(resv, - arg->flags & VGEM_FENCE_WRITE)) { + if (!dma_resv_test_signaled(resv, arg->flags & VGEM_FENCE_WRITE)) { ret = -EBUSY; goto err_fence; } diff --git a/drivers/gpu/drm/virtio/virtgpu_ioctl.c b/drivers/gpu/drm/virtio/virtgpu_ioctl.c index 669f2ee39515..5c1ad1596889 100644 --- a/drivers/gpu/drm/virtio/virtgpu_ioctl.c +++ b/drivers/gpu/drm/virtio/virtgpu_ioctl.c @@ -451,10 +451,9 @@ static int virtio_gpu_wait_ioctl(struct drm_device *dev, void *data, return -ENOENT; if (args->flags & VIRTGPU_WAIT_NOWAIT) { - ret = dma_resv_test_signaled_rcu(obj->resv, true); + ret = dma_resv_test_signaled(obj->resv, true); } else { - ret = dma_resv_wait_timeout_rcu(obj->resv, true, true, - timeout); + ret = dma_resv_wait_timeout(obj->resv, true, true, timeout); } if (ret == 0) ret = -EBUSY; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_blit.c b/drivers/gpu/drm/vmwgfx/vmwgfx_blit.c index cdbd5a870711..09fe20e918f9 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_blit.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_blit.c @@ -483,10 +483,10 @@ int vmw_bo_cpu_blit(struct ttm_buffer_object *dst, d.src_addr = NULL; d.dst_pages = dst->ttm->pages; d.src_pages = src->ttm->pages; - d.dst_num_pages = dst->mem.num_pages; - d.src_num_pages = src->mem.num_pages; - d.dst_prot = ttm_io_prot(dst, &dst->mem, PAGE_KERNEL); - d.src_prot = ttm_io_prot(src, &src->mem, PAGE_KERNEL); + d.dst_num_pages = dst->resource->num_pages; + d.src_num_pages = src->resource->num_pages; + d.dst_prot = ttm_io_prot(dst, dst->resource, PAGE_KERNEL); + d.src_prot = ttm_io_prot(src, src->resource, PAGE_KERNEL); d.diff = diff; for (j = 0; j < h; ++j) { diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c index 04dd49c4c257..362f56d5b12b 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c @@ -103,7 +103,7 @@ int vmw_bo_pin_in_placement(struct vmw_private *dev_priv, goto err; if (buf->base.pin_count > 0) - ret = ttm_bo_mem_compat(placement, &bo->mem, + ret = ttm_bo_mem_compat(placement, bo->resource, &new_flags) == true ? 0 : -EINVAL; else ret = ttm_bo_validate(bo, placement, &ctx); @@ -145,7 +145,7 @@ int vmw_bo_pin_in_vram_or_gmr(struct vmw_private *dev_priv, goto err; if (buf->base.pin_count > 0) { - ret = ttm_bo_mem_compat(&vmw_vram_gmr_placement, &bo->mem, + ret = ttm_bo_mem_compat(&vmw_vram_gmr_placement, bo->resource, &new_flags) == true ? 0 : -EINVAL; goto out_unreserve; } @@ -211,7 +211,7 @@ int vmw_bo_pin_in_start_of_vram(struct vmw_private *dev_priv, uint32_t new_flags; place = vmw_vram_placement.placement[0]; - place.lpfn = bo->mem.num_pages; + place.lpfn = bo->resource->num_pages; placement.num_placement = 1; placement.placement = &place; placement.num_busy_placement = 1; @@ -227,22 +227,22 @@ int vmw_bo_pin_in_start_of_vram(struct vmw_private *dev_priv, * In that case, evict it first because TTM isn't good at handling * that situation. */ - if (bo->mem.mem_type == TTM_PL_VRAM && - bo->mem.start < bo->mem.num_pages && - bo->mem.start > 0 && + if (bo->resource->mem_type == TTM_PL_VRAM && + bo->resource->start < bo->resource->num_pages && + bo->resource->start > 0 && buf->base.pin_count == 0) { ctx.interruptible = false; (void) ttm_bo_validate(bo, &vmw_sys_placement, &ctx); } if (buf->base.pin_count > 0) - ret = ttm_bo_mem_compat(&placement, &bo->mem, + ret = ttm_bo_mem_compat(&placement, bo->resource, &new_flags) == true ? 0 : -EINVAL; else ret = ttm_bo_validate(bo, &placement, &ctx); /* For some reason we didn't end up at the start of vram */ - WARN_ON(ret == 0 && bo->mem.start != 0); + WARN_ON(ret == 0 && bo->resource->start != 0); if (!ret) vmw_bo_pin_reserved(buf, true); @@ -293,11 +293,11 @@ err: void vmw_bo_get_guest_ptr(const struct ttm_buffer_object *bo, SVGAGuestPtr *ptr) { - if (bo->mem.mem_type == TTM_PL_VRAM) { + if (bo->resource->mem_type == TTM_PL_VRAM) { ptr->gmrId = SVGA_GMR_FRAMEBUFFER; - ptr->offset = bo->mem.start << PAGE_SHIFT; + ptr->offset = bo->resource->start << PAGE_SHIFT; } else { - ptr->gmrId = bo->mem.start; + ptr->gmrId = bo->resource->start; ptr->offset = 0; } } @@ -316,7 +316,7 @@ void vmw_bo_pin_reserved(struct vmw_buffer_object *vbo, bool pin) struct ttm_place pl; struct ttm_placement placement; struct ttm_buffer_object *bo = &vbo->base; - uint32_t old_mem_type = bo->mem.mem_type; + uint32_t old_mem_type = bo->resource->mem_type; int ret; dma_resv_assert_held(bo->base.resv); @@ -326,8 +326,8 @@ void vmw_bo_pin_reserved(struct vmw_buffer_object *vbo, bool pin) pl.fpfn = 0; pl.lpfn = 0; - pl.mem_type = bo->mem.mem_type; - pl.flags = bo->mem.placement; + pl.mem_type = bo->resource->mem_type; + pl.flags = bo->resource->placement; memset(&placement, 0, sizeof(placement)); placement.num_placement = 1; @@ -335,7 +335,7 @@ void vmw_bo_pin_reserved(struct vmw_buffer_object *vbo, bool pin) ret = ttm_bo_validate(bo, &placement, &ctx); - BUG_ON(ret != 0 || bo->mem.mem_type != old_mem_type); + BUG_ON(ret != 0 || bo->resource->mem_type != old_mem_type); if (pin) ttm_bo_pin(bo); @@ -369,7 +369,7 @@ void *vmw_bo_map_and_cache(struct vmw_buffer_object *vbo) if (virtual) return virtual; - ret = ttm_bo_kmap(bo, 0, bo->mem.num_pages, &vbo->map); + ret = ttm_bo_kmap(bo, 0, bo->resource->num_pages, &vbo->map); if (ret) DRM_ERROR("Buffer object map failed: %d.\n", ret); @@ -743,9 +743,9 @@ static int vmw_user_bo_synccpu_grab(struct vmw_user_buffer_object *user_bo, if (flags & drm_vmw_synccpu_allow_cs) { long lret; - lret = dma_resv_wait_timeout_rcu - (bo->base.resv, true, true, - nonblock ? 0 : MAX_SCHEDULE_TIMEOUT); + lret = dma_resv_wait_timeout(bo->base.resv, true, true, + nonblock ? 0 : + MAX_SCHEDULE_TIMEOUT); if (!lret) return -EBUSY; else if (lret < 0) @@ -1197,7 +1197,7 @@ void vmw_bo_move_notify(struct ttm_buffer_object *bo, * With other types of moves, the underlying pages stay the same, * and the map can be kept. */ - if (mem->mem_type == TTM_PL_VRAM || bo->mem.mem_type == TTM_PL_VRAM) + if (mem->mem_type == TTM_PL_VRAM || bo->resource->mem_type == TTM_PL_VRAM) vmw_bo_unmap(vbo); /* @@ -1205,6 +1205,6 @@ void vmw_bo_move_notify(struct ttm_buffer_object *bo, * read back all resource content first, and unbind the MOB from * the resource. */ - if (mem->mem_type != VMW_PL_MOB && bo->mem.mem_type == VMW_PL_MOB) + if (mem->mem_type != VMW_PL_MOB && bo->resource->mem_type == VMW_PL_MOB) vmw_resource_unbind_list(vbo); } diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_cmd.c b/drivers/gpu/drm/vmwgfx/vmwgfx_cmd.c index 9c89189a226d..956b85e35cef 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_cmd.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_cmd.c @@ -576,11 +576,11 @@ static int vmw_cmd_emit_dummy_legacy_query(struct vmw_private *dev_priv, cmd->body.cid = cid; cmd->body.type = SVGA3D_QUERYTYPE_OCCLUSION; - if (bo->mem.mem_type == TTM_PL_VRAM) { + if (bo->resource->mem_type == TTM_PL_VRAM) { cmd->body.guestResult.gmrId = SVGA_GMR_FRAMEBUFFER; - cmd->body.guestResult.offset = bo->mem.start << PAGE_SHIFT; + cmd->body.guestResult.offset = bo->resource->start << PAGE_SHIFT; } else { - cmd->body.guestResult.gmrId = bo->mem.start; + cmd->body.guestResult.gmrId = bo->resource->start; cmd->body.guestResult.offset = 0; } @@ -621,8 +621,8 @@ static int vmw_cmd_emit_dummy_gb_query(struct vmw_private *dev_priv, cmd->header.size = sizeof(cmd->body); cmd->body.cid = cid; cmd->body.type = SVGA3D_QUERYTYPE_OCCLUSION; - BUG_ON(bo->mem.mem_type != VMW_PL_MOB); - cmd->body.mobid = bo->mem.start; + BUG_ON(bo->resource->mem_type != VMW_PL_MOB); + cmd->body.mobid = bo->resource->start; cmd->body.offset = 0; vmw_cmd_commit(dev_priv, sizeof(*cmd)); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf.c index 05ca310ed61a..6bb4961e64a5 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf.c @@ -889,7 +889,7 @@ static int vmw_cmdbuf_space_pool(struct vmw_cmdbuf_man *man, header->cmd = man->map + offset; if (man->using_mob) { cb_hdr->flags = SVGA_CB_FLAG_MOB; - cb_hdr->ptr.mob.mobid = man->cmd_space->mem.start; + cb_hdr->ptr.mob.mobid = man->cmd_space->resource->start; cb_hdr->ptr.mob.mobOffset = offset; } else { cb_hdr->ptr.pa = (u64)man->handle + (u64)offset; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_context.c b/drivers/gpu/drm/vmwgfx/vmwgfx_context.c index 3ed9914cb994..dffe3804ad3e 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_context.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_context.c @@ -346,7 +346,7 @@ static int vmw_gb_context_bind(struct vmw_resource *res, } *cmd; struct ttm_buffer_object *bo = val_buf->bo; - BUG_ON(bo->mem.mem_type != VMW_PL_MOB); + BUG_ON(bo->resource->mem_type != VMW_PL_MOB); cmd = VMW_CMD_RESERVE(dev_priv, sizeof(*cmd)); if (unlikely(cmd == NULL)) @@ -355,7 +355,7 @@ static int vmw_gb_context_bind(struct vmw_resource *res, cmd->header.id = SVGA_3D_CMD_BIND_GB_CONTEXT; cmd->header.size = sizeof(cmd->body); cmd->body.cid = res->id; - cmd->body.mobid = bo->mem.start; + cmd->body.mobid = bo->resource->start; cmd->body.validContents = res->backup_dirty; res->backup_dirty = false; vmw_cmd_commit(dev_priv, sizeof(*cmd)); @@ -385,7 +385,7 @@ static int vmw_gb_context_unbind(struct vmw_resource *res, uint8_t *cmd; - BUG_ON(bo->mem.mem_type != VMW_PL_MOB); + BUG_ON(bo->resource->mem_type != VMW_PL_MOB); mutex_lock(&dev_priv->binding_mutex); vmw_binding_state_scrub(uctx->cbs); @@ -513,7 +513,7 @@ static int vmw_dx_context_bind(struct vmw_resource *res, } *cmd; struct ttm_buffer_object *bo = val_buf->bo; - BUG_ON(bo->mem.mem_type != VMW_PL_MOB); + BUG_ON(bo->resource->mem_type != VMW_PL_MOB); cmd = VMW_CMD_RESERVE(dev_priv, sizeof(*cmd)); if (unlikely(cmd == NULL)) @@ -522,7 +522,7 @@ static int vmw_dx_context_bind(struct vmw_resource *res, cmd->header.id = SVGA_3D_CMD_DX_BIND_CONTEXT; cmd->header.size = sizeof(cmd->body); cmd->body.cid = res->id; - cmd->body.mobid = bo->mem.start; + cmd->body.mobid = bo->resource->start; cmd->body.validContents = res->backup_dirty; res->backup_dirty = false; vmw_cmd_commit(dev_priv, sizeof(*cmd)); @@ -594,7 +594,7 @@ static int vmw_dx_context_unbind(struct vmw_resource *res, uint8_t *cmd; - BUG_ON(bo->mem.mem_type != VMW_PL_MOB); + BUG_ON(bo->resource->mem_type != VMW_PL_MOB); mutex_lock(&dev_priv->binding_mutex); vmw_dx_context_scrub_cotables(res, readback); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_cotable.c b/drivers/gpu/drm/vmwgfx/vmwgfx_cotable.c index b40aa002bf2b..c84a16c1def0 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_cotable.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_cotable.c @@ -173,7 +173,7 @@ static int vmw_cotable_unscrub(struct vmw_resource *res) SVGA3dCmdDXSetCOTable body; } *cmd; - WARN_ON_ONCE(bo->mem.mem_type != VMW_PL_MOB); + WARN_ON_ONCE(bo->resource->mem_type != VMW_PL_MOB); dma_resv_assert_held(bo->base.resv); cmd = VMW_CMD_RESERVE(dev_priv, sizeof(*cmd)); @@ -181,12 +181,12 @@ static int vmw_cotable_unscrub(struct vmw_resource *res) return -ENOMEM; WARN_ON(vcotbl->ctx->id == SVGA3D_INVALID_ID); - WARN_ON(bo->mem.mem_type != VMW_PL_MOB); + WARN_ON(bo->resource->mem_type != VMW_PL_MOB); cmd->header.id = SVGA_3D_CMD_DX_SET_COTABLE; cmd->header.size = sizeof(cmd->body); cmd->body.cid = vcotbl->ctx->id; cmd->body.type = vcotbl->type; - cmd->body.mobid = bo->mem.start; + cmd->body.mobid = bo->resource->start; cmd->body.validSizeInBytes = vcotbl->size_read_back; vmw_cmd_commit_flush(dev_priv, sizeof(*cmd)); @@ -315,7 +315,7 @@ static int vmw_cotable_unbind(struct vmw_resource *res, if (!vmw_resource_mob_attached(res)) return 0; - WARN_ON_ONCE(bo->mem.mem_type != VMW_PL_MOB); + WARN_ON_ONCE(bo->resource->mem_type != VMW_PL_MOB); dma_resv_assert_held(bo->base.resv); mutex_lock(&dev_priv->binding_mutex); @@ -431,7 +431,7 @@ static int vmw_cotable_resize(struct vmw_resource *res, size_t new_size) * Do a page by page copy of COTables. This eliminates slow vmap()s. * This should really be a TTM utility. */ - for (i = 0; i < old_bo->mem.num_pages; ++i) { + for (i = 0; i < old_bo->resource->num_pages; ++i) { bool dummy; ret = ttm_bo_kmap(old_bo, i, 1, &old_map); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c index 32a84dff3fbf..a2b8464b3f56 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c @@ -735,7 +735,7 @@ static int vmw_rebind_all_dx_query(struct vmw_resource *ctx_res) cmd->header.id = SVGA_3D_CMD_DX_BIND_ALL_QUERY; cmd->header.size = sizeof(cmd->body); cmd->body.cid = ctx_res->id; - cmd->body.mobid = dx_query_mob->base.mem.start; + cmd->body.mobid = dx_query_mob->base.resource->start; vmw_cmd_commit(dev_priv, sizeof(*cmd)); vmw_context_bind_dx_query(ctx_res, dx_query_mob); @@ -1046,7 +1046,7 @@ static int vmw_query_bo_switch_prepare(struct vmw_private *dev_priv, if (unlikely(new_query_bo != sw_context->cur_query_bo)) { - if (unlikely(new_query_bo->base.mem.num_pages > 4)) { + if (unlikely(new_query_bo->base.resource->num_pages > 4)) { VMW_DEBUG_USER("Query buffer too large.\n"); return -EINVAL; } @@ -3710,16 +3710,16 @@ static void vmw_apply_relocations(struct vmw_sw_context *sw_context) list_for_each_entry(reloc, &sw_context->bo_relocations, head) { bo = &reloc->vbo->base; - switch (bo->mem.mem_type) { + switch (bo->resource->mem_type) { case TTM_PL_VRAM: - reloc->location->offset += bo->mem.start << PAGE_SHIFT; + reloc->location->offset += bo->resource->start << PAGE_SHIFT; reloc->location->gmrId = SVGA_GMR_FRAMEBUFFER; break; case VMW_PL_GMR: - reloc->location->gmrId = bo->mem.start; + reloc->location->gmrId = bo->resource->start; break; case VMW_PL_MOB: - *reloc->mob_loc = bo->mem.start; + *reloc->mob_loc = bo->resource->start; break; default: BUG(); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_gmrid_manager.c b/drivers/gpu/drm/vmwgfx/vmwgfx_gmrid_manager.c index 1774960d1b89..28ceb749a733 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_gmrid_manager.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_gmrid_manager.c @@ -52,11 +52,17 @@ static struct vmwgfx_gmrid_man *to_gmrid_manager(struct ttm_resource_manager *ma static int vmw_gmrid_man_get_node(struct ttm_resource_manager *man, struct ttm_buffer_object *bo, const struct ttm_place *place, - struct ttm_resource *mem) + struct ttm_resource **res) { struct vmwgfx_gmrid_man *gman = to_gmrid_manager(man); int id; + *res = kmalloc(sizeof(**res), GFP_KERNEL); + if (!*res) + return -ENOMEM; + + ttm_resource_init(bo, place, *res); + id = ida_alloc_max(&gman->gmr_ida, gman->max_gmr_ids - 1, GFP_KERNEL); if (id < 0) return id; @@ -64,36 +70,34 @@ static int vmw_gmrid_man_get_node(struct ttm_resource_manager *man, spin_lock(&gman->lock); if (gman->max_gmr_pages > 0) { - gman->used_gmr_pages += mem->num_pages; + gman->used_gmr_pages += (*res)->num_pages; if (unlikely(gman->used_gmr_pages > gman->max_gmr_pages)) goto nospace; } - mem->mm_node = gman; - mem->start = id; + (*res)->start = id; spin_unlock(&gman->lock); return 0; nospace: - gman->used_gmr_pages -= mem->num_pages; + gman->used_gmr_pages -= (*res)->num_pages; spin_unlock(&gman->lock); ida_free(&gman->gmr_ida, id); + kfree(*res); return -ENOSPC; } static void vmw_gmrid_man_put_node(struct ttm_resource_manager *man, - struct ttm_resource *mem) + struct ttm_resource *res) { struct vmwgfx_gmrid_man *gman = to_gmrid_manager(man); - if (mem->mm_node) { - ida_free(&gman->gmr_ida, mem->start); - spin_lock(&gman->lock); - gman->used_gmr_pages -= mem->num_pages; - spin_unlock(&gman->lock); - mem->mm_node = NULL; - } + ida_free(&gman->gmr_ida, res->start); + spin_lock(&gman->lock); + gman->used_gmr_pages -= res->num_pages; + spin_unlock(&gman->lock); + kfree(res); } static const struct ttm_resource_manager_func vmw_gmrid_manager_func; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_page_dirty.c b/drivers/gpu/drm/vmwgfx/vmwgfx_page_dirty.c index 45c9c6a7f1d6..e5a9a5cbd01a 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_page_dirty.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_page_dirty.c @@ -232,7 +232,7 @@ void vmw_bo_dirty_unmap(struct vmw_buffer_object *vbo, int vmw_bo_dirty_add(struct vmw_buffer_object *vbo) { struct vmw_bo_dirty *dirty = vbo->dirty; - pgoff_t num_pages = vbo->base.mem.num_pages; + pgoff_t num_pages = vbo->base.resource->num_pages; size_t size, acc_size; int ret; static struct ttm_operation_ctx ctx = { @@ -413,7 +413,7 @@ vm_fault_t vmw_bo_vm_mkwrite(struct vm_fault *vmf) return ret; page_offset = vmf->pgoff - drm_vma_node_start(&bo->base.vma_node); - if (unlikely(page_offset >= bo->mem.num_pages)) { + if (unlikely(page_offset >= bo->resource->num_pages)) { ret = VM_FAULT_SIGBUS; goto out_unlock; } @@ -456,7 +456,7 @@ vm_fault_t vmw_bo_vm_fault(struct vm_fault *vmf) page_offset = vmf->pgoff - drm_vma_node_start(&bo->base.vma_node); - if (page_offset >= bo->mem.num_pages || + if (page_offset >= bo->resource->num_pages || vmw_resources_clean(vbo, page_offset, page_offset + PAGE_SIZE, &allowed_prefault)) { @@ -529,7 +529,7 @@ vm_fault_t vmw_bo_vm_huge_fault(struct vm_fault *vmf, page_offset = vmf->pgoff - drm_vma_node_start(&bo->base.vma_node); - if (page_offset >= bo->mem.num_pages || + if (page_offset >= bo->resource->num_pages || vmw_resources_clean(vbo, page_offset, page_offset + PAGE_SIZE, &allowed_prefault)) { diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c index 62ea920addc3..7b45393ad98e 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c @@ -1166,7 +1166,7 @@ int vmw_resources_clean(struct vmw_buffer_object *vbo, pgoff_t start, if (bo->moving) dma_fence_put(bo->moving); bo->moving = dma_fence_get - (dma_resv_get_excl(bo->base.resv)); + (dma_resv_excl_fence(bo->base.resv)); } return 0; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_shader.c b/drivers/gpu/drm/vmwgfx/vmwgfx_shader.c index b391975871a5..b3c8d2da6f1a 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_shader.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_shader.c @@ -254,7 +254,7 @@ static int vmw_gb_shader_bind(struct vmw_resource *res, } *cmd; struct ttm_buffer_object *bo = val_buf->bo; - BUG_ON(bo->mem.mem_type != VMW_PL_MOB); + BUG_ON(bo->resource->mem_type != VMW_PL_MOB); cmd = VMW_CMD_RESERVE(dev_priv, sizeof(*cmd)); if (unlikely(cmd == NULL)) @@ -263,7 +263,7 @@ static int vmw_gb_shader_bind(struct vmw_resource *res, cmd->header.id = SVGA_3D_CMD_BIND_GB_SHADER; cmd->header.size = sizeof(cmd->body); cmd->body.shid = res->id; - cmd->body.mobid = bo->mem.start; + cmd->body.mobid = bo->resource->start; cmd->body.offsetInBytes = res->backup_offset; res->backup_dirty = false; vmw_cmd_commit(dev_priv, sizeof(*cmd)); @@ -282,7 +282,7 @@ static int vmw_gb_shader_unbind(struct vmw_resource *res, } *cmd; struct vmw_fence_obj *fence; - BUG_ON(res->backup->base.mem.mem_type != VMW_PL_MOB); + BUG_ON(res->backup->base.resource->mem_type != VMW_PL_MOB); cmd = VMW_CMD_RESERVE(dev_priv, sizeof(*cmd)); if (unlikely(cmd == NULL)) @@ -402,7 +402,7 @@ static int vmw_dx_shader_unscrub(struct vmw_resource *res) cmd->header.size = sizeof(cmd->body); cmd->body.cid = shader->ctx->id; cmd->body.shid = shader->id; - cmd->body.mobid = res->backup->base.mem.start; + cmd->body.mobid = res->backup->base.resource->start; cmd->body.offsetInBytes = res->backup_offset; vmw_cmd_commit(dev_priv, sizeof(*cmd)); @@ -450,7 +450,7 @@ static int vmw_dx_shader_bind(struct vmw_resource *res, struct vmw_private *dev_priv = res->dev_priv; struct ttm_buffer_object *bo = val_buf->bo; - BUG_ON(bo->mem.mem_type != VMW_PL_MOB); + BUG_ON(bo->resource->mem_type != VMW_PL_MOB); mutex_lock(&dev_priv->binding_mutex); vmw_dx_shader_unscrub(res); mutex_unlock(&dev_priv->binding_mutex); @@ -513,7 +513,7 @@ static int vmw_dx_shader_unbind(struct vmw_resource *res, struct vmw_fence_obj *fence; int ret; - BUG_ON(res->backup->base.mem.mem_type != VMW_PL_MOB); + BUG_ON(res->backup->base.resource->mem_type != VMW_PL_MOB); mutex_lock(&dev_priv->binding_mutex); ret = vmw_dx_shader_scrub(res); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_streamoutput.c b/drivers/gpu/drm/vmwgfx/vmwgfx_streamoutput.c index 1dd042a20a66..c8efa4a6c995 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_streamoutput.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_streamoutput.c @@ -106,7 +106,7 @@ static int vmw_dx_streamoutput_unscrub(struct vmw_resource *res) cmd->header.id = SVGA_3D_CMD_DX_BIND_STREAMOUTPUT; cmd->header.size = sizeof(cmd->body); cmd->body.soid = so->id; - cmd->body.mobid = res->backup->base.mem.start; + cmd->body.mobid = res->backup->base.resource->start; cmd->body.offsetInBytes = res->backup_offset; cmd->body.sizeInBytes = so->size; vmw_cmd_commit(dev_priv, sizeof(*cmd)); @@ -142,7 +142,7 @@ static int vmw_dx_streamoutput_bind(struct vmw_resource *res, struct ttm_buffer_object *bo = val_buf->bo; int ret; - if (WARN_ON(bo->mem.mem_type != VMW_PL_MOB)) + if (WARN_ON(bo->resource->mem_type != VMW_PL_MOB)) return -EINVAL; mutex_lock(&dev_priv->binding_mutex); @@ -197,7 +197,7 @@ static int vmw_dx_streamoutput_unbind(struct vmw_resource *res, bool readback, struct vmw_fence_obj *fence; int ret; - if (WARN_ON(res->backup->base.mem.mem_type != VMW_PL_MOB)) + if (WARN_ON(res->backup->base.resource->mem_type != VMW_PL_MOB)) return -EINVAL; mutex_lock(&dev_priv->binding_mutex); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c b/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c index 8ead06574850..0835468bb2ee 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c @@ -1212,7 +1212,7 @@ static int vmw_gb_surface_bind(struct vmw_resource *res, uint32_t submit_size; struct ttm_buffer_object *bo = val_buf->bo; - BUG_ON(bo->mem.mem_type != VMW_PL_MOB); + BUG_ON(bo->resource->mem_type != VMW_PL_MOB); submit_size = sizeof(*cmd1) + (res->backup_dirty ? sizeof(*cmd2) : 0); @@ -1223,7 +1223,7 @@ static int vmw_gb_surface_bind(struct vmw_resource *res, cmd1->header.id = SVGA_3D_CMD_BIND_GB_SURFACE; cmd1->header.size = sizeof(cmd1->body); cmd1->body.sid = res->id; - cmd1->body.mobid = bo->mem.start; + cmd1->body.mobid = bo->resource->start; if (res->backup_dirty) { cmd2 = (void *) &cmd1[1]; cmd2->header.id = SVGA_3D_CMD_UPDATE_GB_SURFACE; @@ -1266,7 +1266,7 @@ static int vmw_gb_surface_unbind(struct vmw_resource *res, uint8_t *cmd; - BUG_ON(bo->mem.mem_type != VMW_PL_MOB); + BUG_ON(bo->resource->mem_type != VMW_PL_MOB); submit_size = sizeof(*cmd3) + (readback ? sizeof(*cmd1) : sizeof(*cmd2)); cmd = VMW_CMD_RESERVE(dev_priv, submit_size); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_thp.c b/drivers/gpu/drm/vmwgfx/vmwgfx_thp.c index 5ccc35b3194c..2a3d3468e4e0 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_thp.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_thp.c @@ -7,6 +7,7 @@ #include "vmwgfx_drv.h" #include <drm/ttm/ttm_bo_driver.h> #include <drm/ttm/ttm_placement.h> +#include <drm/ttm/ttm_range_manager.h> /** * struct vmw_thp_manager - Range manager implementing huge page alignment @@ -50,20 +51,22 @@ static int vmw_thp_insert_aligned(struct ttm_buffer_object *bo, static int vmw_thp_get_node(struct ttm_resource_manager *man, struct ttm_buffer_object *bo, const struct ttm_place *place, - struct ttm_resource *mem) + struct ttm_resource **res) { struct vmw_thp_manager *rman = to_thp_manager(man); struct drm_mm *mm = &rman->mm; - struct drm_mm_node *node; + struct ttm_range_mgr_node *node; unsigned long align_pages; unsigned long lpfn; enum drm_mm_insert_mode mode = DRM_MM_INSERT_BEST; int ret; - node = kzalloc(sizeof(*node), GFP_KERNEL); + node = kzalloc(struct_size(node, mm_nodes, 1), GFP_KERNEL); if (!node) return -ENOMEM; + ttm_resource_init(bo, place, &node->base); + lpfn = place->lpfn; if (!lpfn) lpfn = man->size; @@ -75,23 +78,26 @@ static int vmw_thp_get_node(struct ttm_resource_manager *man, spin_lock(&rman->lock); if (IS_ENABLED(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD)) { align_pages = (HPAGE_PUD_SIZE >> PAGE_SHIFT); - if (mem->num_pages >= align_pages) { - ret = vmw_thp_insert_aligned(bo, mm, node, align_pages, - place, mem, lpfn, mode); + if (node->base.num_pages >= align_pages) { + ret = vmw_thp_insert_aligned(bo, mm, &node->mm_nodes[0], + align_pages, place, + &node->base, lpfn, mode); if (!ret) goto found_unlock; } } align_pages = (HPAGE_PMD_SIZE >> PAGE_SHIFT); - if (mem->num_pages >= align_pages) { - ret = vmw_thp_insert_aligned(bo, mm, node, align_pages, place, - mem, lpfn, mode); + if (node->base.num_pages >= align_pages) { + ret = vmw_thp_insert_aligned(bo, mm, &node->mm_nodes[0], + align_pages, place, &node->base, + lpfn, mode); if (!ret) goto found_unlock; } - ret = drm_mm_insert_node_in_range(mm, node, mem->num_pages, + ret = drm_mm_insert_node_in_range(mm, &node->mm_nodes[0], + node->base.num_pages, bo->page_alignment, 0, place->fpfn, lpfn, mode); found_unlock: @@ -100,28 +106,24 @@ found_unlock: if (unlikely(ret)) { kfree(node); } else { - mem->mm_node = node; - mem->start = node->start; + node->base.start = node->mm_nodes[0].start; + *res = &node->base; } return ret; } - - static void vmw_thp_put_node(struct ttm_resource_manager *man, - struct ttm_resource *mem) + struct ttm_resource *res) { + struct ttm_range_mgr_node *node = to_ttm_range_mgr_node(res); struct vmw_thp_manager *rman = to_thp_manager(man); - if (mem->mm_node) { - spin_lock(&rman->lock); - drm_mm_remove_node(mem->mm_node); - spin_unlock(&rman->lock); + spin_lock(&rman->lock); + drm_mm_remove_node(&node->mm_nodes[0]); + spin_unlock(&rman->lock); - kfree(mem->mm_node); - mem->mm_node = NULL; - } + kfree(node); } int vmw_thp_init(struct vmw_private *dev_priv) diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c b/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c index 35b03fe21161..0488042fb287 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c @@ -719,7 +719,7 @@ static int vmw_move(struct ttm_buffer_object *bo, struct ttm_resource *new_mem, struct ttm_place *hop) { - struct ttm_resource_manager *old_man = ttm_manager_type(bo->bdev, bo->mem.mem_type); + struct ttm_resource_manager *old_man = ttm_manager_type(bo->bdev, bo->resource->mem_type); struct ttm_resource_manager *new_man = ttm_manager_type(bo->bdev, new_mem->mem_type); int ret; @@ -729,11 +729,11 @@ static int vmw_move(struct ttm_buffer_object *bo, return ret; } - vmw_move_notify(bo, &bo->mem, new_mem); + vmw_move_notify(bo, bo->resource, new_mem); if (old_man->use_tt && new_man->use_tt) { - if (bo->mem.mem_type == TTM_PL_SYSTEM) { - ttm_bo_assign_mem(bo, new_mem); + if (bo->resource->mem_type == TTM_PL_SYSTEM) { + ttm_bo_move_null(bo, new_mem); return 0; } ret = ttm_bo_wait_ctx(bo, ctx); @@ -741,7 +741,7 @@ static int vmw_move(struct ttm_buffer_object *bo, goto fail; vmw_ttm_unbind(bo->bdev, bo->ttm); - ttm_resource_free(bo, &bo->mem); + ttm_resource_free(bo, &bo->resource); ttm_bo_assign_mem(bo, new_mem); return 0; } else { @@ -751,7 +751,7 @@ static int vmw_move(struct ttm_buffer_object *bo, } return 0; fail: - vmw_move_notify(bo, new_mem, &bo->mem); + vmw_move_notify(bo, new_mem, bo->resource); return ret; } |