diff options
85 files changed, 2165 insertions, 953 deletions
diff --git a/Documentation/gpu/i915.rst b/Documentation/gpu/i915.rst index b7d801993bfa..bcaefc952764 100644 --- a/Documentation/gpu/i915.rst +++ b/Documentation/gpu/i915.rst @@ -539,6 +539,7 @@ GuC ABI .. kernel-doc:: drivers/gpu/drm/i915/gt/uc/abi/guc_communication_mmio_abi.h .. kernel-doc:: drivers/gpu/drm/i915/gt/uc/abi/guc_communication_ctb_abi.h .. kernel-doc:: drivers/gpu/drm/i915/gt/uc/abi/guc_actions_abi.h +.. kernel-doc:: drivers/gpu/drm/i915/gt/uc/abi/guc_klvs_abi.h HuC --- diff --git a/drivers/gpu/drm/i915/Makefile b/drivers/gpu/drm/i915/Makefile index 1b62b9f65196..aa86ac33effc 100644 --- a/drivers/gpu/drm/i915/Makefile +++ b/drivers/gpu/drm/i915/Makefile @@ -174,7 +174,7 @@ i915-y += \ i915_trace_points.o \ i915_ttm_buddy_manager.o \ i915_vma.o \ - i915_vma_snapshot.o \ + i915_vma_resource.o \ intel_wopcm.o # general-purpose microcontroller (GuC) support diff --git a/drivers/gpu/drm/i915/display/intel_dpt.c b/drivers/gpu/drm/i915/display/intel_dpt.c index 8f674745e7e0..63a83d5f85a1 100644 --- a/drivers/gpu/drm/i915/display/intel_dpt.c +++ b/drivers/gpu/drm/i915/display/intel_dpt.c @@ -48,7 +48,7 @@ static void dpt_insert_page(struct i915_address_space *vm, } static void dpt_insert_entries(struct i915_address_space *vm, - struct i915_vma *vma, + struct i915_vma_resource *vma_res, enum i915_cache_level level, u32 flags) { @@ -64,8 +64,8 @@ static void dpt_insert_entries(struct i915_address_space *vm, * not to allow the user to override access to a read only page. */ - i = vma->node.start / I915_GTT_PAGE_SIZE; - for_each_sgt_daddr(addr, sgt_iter, vma->pages) + i = vma_res->start / I915_GTT_PAGE_SIZE; + for_each_sgt_daddr(addr, sgt_iter, vma_res->bi.pages) gen8_set_pte(&base[i++], pte_encode | addr); } @@ -76,35 +76,38 @@ static void dpt_clear_range(struct i915_address_space *vm, static void dpt_bind_vma(struct i915_address_space *vm, struct i915_vm_pt_stash *stash, - struct i915_vma *vma, + struct i915_vma_resource *vma_res, enum i915_cache_level cache_level, u32 flags) { - struct drm_i915_gem_object *obj = vma->obj; u32 pte_flags; + if (vma_res->bound_flags) + return; + /* Applicable to VLV (gen8+ do not support RO in the GGTT) */ pte_flags = 0; - if (vma->vm->has_read_only && i915_gem_object_is_readonly(obj)) + if (vm->has_read_only && vma_res->bi.readonly) pte_flags |= PTE_READ_ONLY; - if (i915_gem_object_is_lmem(obj)) + if (vma_res->bi.lmem) pte_flags |= PTE_LM; - vma->vm->insert_entries(vma->vm, vma, cache_level, pte_flags); + vm->insert_entries(vm, vma_res, cache_level, pte_flags); - vma->page_sizes.gtt = I915_GTT_PAGE_SIZE; + vma_res->page_sizes_gtt = I915_GTT_PAGE_SIZE; /* * Without aliasing PPGTT there's no difference between * GLOBAL/LOCAL_BIND, it's all the same ptes. Hence unconditionally * upgrade to both bound if we bind either to avoid double-binding. */ - atomic_or(I915_VMA_GLOBAL_BIND | I915_VMA_LOCAL_BIND, &vma->flags); + vma_res->bound_flags = I915_VMA_GLOBAL_BIND | I915_VMA_LOCAL_BIND; } -static void dpt_unbind_vma(struct i915_address_space *vm, struct i915_vma *vma) +static void dpt_unbind_vma(struct i915_address_space *vm, + struct i915_vma_resource *vma_res) { - vm->clear_range(vm, vma->node.start, vma->size); + vm->clear_range(vm, vma_res->start, vma_res->vma_size); } static void dpt_cleanup(struct i915_address_space *vm) diff --git a/drivers/gpu/drm/i915/display/intel_fbc.c b/drivers/gpu/drm/i915/display/intel_fbc.c index 160fd2bdafe5..c0a973eeb405 100644 --- a/drivers/gpu/drm/i915/display/intel_fbc.c +++ b/drivers/gpu/drm/i915/display/intel_fbc.c @@ -595,7 +595,7 @@ static void ivb_fbc_activate(struct intel_fbc *fbc) else if (DISPLAY_VER(i915) == 9) skl_fbc_program_cfb_stride(fbc); - if (i915->ggtt.num_fences) + if (to_gt(i915)->ggtt->num_fences) snb_fbc_program_fence(fbc); intel_de_write(i915, ILK_DPFC_CONTROL, diff --git a/drivers/gpu/drm/i915/display/intel_fbdev.c b/drivers/gpu/drm/i915/display/intel_fbdev.c index adc3a81be9f7..41d279db2be6 100644 --- a/drivers/gpu/drm/i915/display/intel_fbdev.c +++ b/drivers/gpu/drm/i915/display/intel_fbdev.c @@ -180,7 +180,7 @@ static int intelfb_create(struct drm_fb_helper *helper, struct drm_device *dev = helper->dev; struct drm_i915_private *dev_priv = to_i915(dev); struct pci_dev *pdev = to_pci_dev(dev_priv->drm.dev); - struct i915_ggtt *ggtt = &dev_priv->ggtt; + struct i915_ggtt *ggtt = to_gt(dev_priv)->ggtt; const struct i915_ggtt_view view = { .type = I915_GGTT_VIEW_NORMAL, }; diff --git a/drivers/gpu/drm/i915/display/intel_plane_initial.c b/drivers/gpu/drm/i915/display/intel_plane_initial.c index 01ce1d72297f..e4186a0b8edb 100644 --- a/drivers/gpu/drm/i915/display/intel_plane_initial.c +++ b/drivers/gpu/drm/i915/display/intel_plane_initial.c @@ -94,7 +94,7 @@ initial_plane_vma(struct drm_i915_private *i915, goto err_obj; } - vma = i915_vma_instance(obj, &i915->ggtt.vm, NULL); + vma = i915_vma_instance(obj, &to_gt(i915)->ggtt->vm, NULL); if (IS_ERR(vma)) goto err_obj; diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c index cad3f0b2be9e..ebbac2ea0833 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_context.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c @@ -564,16 +564,13 @@ set_proto_ctx_engines_parallel_submit(struct i915_user_extension __user *base, container_of_user(base, typeof(*ext), base); const struct set_proto_ctx_engines *set = data; struct drm_i915_private *i915 = set->i915; + struct i915_engine_class_instance prev_engine; u64 flags; int err = 0, n, i, j; u16 slot, width, num_siblings; struct intel_engine_cs **siblings = NULL; intel_engine_mask_t prev_mask; - /* FIXME: This is NIY for execlists */ - if (!(intel_uc_uses_guc_submission(&to_gt(i915)->uc))) - return -ENODEV; - if (get_user(slot, &ext->engine_index)) return -EFAULT; @@ -583,6 +580,13 @@ set_proto_ctx_engines_parallel_submit(struct i915_user_extension __user *base, if (get_user(num_siblings, &ext->num_siblings)) return -EFAULT; + if (!intel_uc_uses_guc_submission(&to_gt(i915)->uc) && + num_siblings != 1) { + drm_dbg(&i915->drm, "Only 1 sibling (%d) supported in non-GuC mode\n", + num_siblings); + return -EINVAL; + } + if (slot >= set->num_engines) { drm_dbg(&i915->drm, "Invalid placement value, %d >= %d\n", slot, set->num_engines); @@ -629,7 +633,6 @@ set_proto_ctx_engines_parallel_submit(struct i915_user_extension __user *base, /* Create contexts / engines */ for (i = 0; i < width; ++i) { intel_engine_mask_t current_mask = 0; - struct i915_engine_class_instance prev_engine; for (j = 0; j < num_siblings; ++j) { struct i915_engine_class_instance ci; diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.h b/drivers/gpu/drm/i915/gem/i915_gem_context.h index babfecb17ad1..e5b0f66ea1fe 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_context.h +++ b/drivers/gpu/drm/i915/gem/i915_gem_context.h @@ -174,7 +174,7 @@ i915_gem_context_get_eb_vm(struct i915_gem_context *ctx) vm = ctx->vm; if (!vm) - vm = &ctx->i915->ggtt.vm; + vm = &to_gt(ctx->i915)->ggtt->vm; vm = i915_vm_get(vm); return vm; diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c index e7f548a22970..2065e5e44fac 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c @@ -29,7 +29,6 @@ #include "i915_gem_ioctls.h" #include "i915_trace.h" #include "i915_user_extensions.h" -#include "i915_vma_snapshot.h" struct eb_vma { struct i915_vma *vma; @@ -1095,7 +1094,7 @@ static inline struct i915_ggtt *cache_to_ggtt(struct reloc_cache *cache) { struct drm_i915_private *i915 = container_of(cache, struct i915_execbuffer, reloc_cache)->i915; - return &i915->ggtt; + return to_gt(i915)->ggtt; } static void reloc_cache_unmap(struct reloc_cache *cache) @@ -1411,7 +1410,7 @@ eb_relocate_entry(struct i915_execbuffer *eb, mutex_lock(&vma->vm->mutex); err = i915_vma_bind(target->vma, target->vma->obj->cache_level, - PIN_GLOBAL, NULL); + PIN_GLOBAL, NULL, NULL); mutex_unlock(&vma->vm->mutex); reloc_cache_remap(&eb->reloc_cache, ev->vma->obj); if (err) @@ -1941,7 +1940,6 @@ static void eb_capture_stage(struct i915_execbuffer *eb) { const unsigned int count = eb->buffer_count; unsigned int i = count, j; - struct i915_vma_snapshot *vsnap; while (i--) { struct eb_vma *ev = &eb->vma[i]; @@ -1951,11 +1949,6 @@ static void eb_capture_stage(struct i915_execbuffer *eb) if (!(flags & EXEC_OBJECT_CAPTURE)) continue; - vsnap = i915_vma_snapshot_alloc(GFP_KERNEL); - if (!vsnap) - continue; - - i915_vma_snapshot_init(vsnap, vma, "user"); for_each_batch_create_order(eb, j) { struct i915_capture_list *capture; @@ -1964,10 +1957,9 @@ static void eb_capture_stage(struct i915_execbuffer *eb) continue; capture->next = eb->capture_lists[j]; - capture->vma_snapshot = i915_vma_snapshot_get(vsnap); + capture->vma_res = i915_vma_resource_get(vma->resource); eb->capture_lists[j] = capture; } - i915_vma_snapshot_put(vsnap); } } @@ -3150,7 +3142,7 @@ eb_composite_fence_create(struct i915_execbuffer *eb, int out_fence_fd) fence_array = dma_fence_array_create(eb->num_batches, fences, eb->context->parallel.fence_context, - eb->context->parallel.seqno, + eb->context->parallel.seqno++, false); if (!fence_array) { kfree(fences); @@ -3270,9 +3262,8 @@ eb_requests_create(struct i915_execbuffer *eb, struct dma_fence *in_fence, * _onstack interface. */ if (eb->batches[i]->vma) - i915_vma_snapshot_init_onstack(&eb->requests[i]->batch_snapshot, - eb->batches[i]->vma, - "batch"); + eb->requests[i]->batch_res = + i915_vma_resource_get(eb->batches[i]->vma->resource); if (eb->batch_pool) { GEM_BUG_ON(intel_context_is_parallel(eb->context)); intel_gt_buffer_pool_mark_active(eb->batch_pool, diff --git a/drivers/gpu/drm/i915/gem/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/i915_gem_mman.c index 1478c02a82cb..5ac2506f4ee8 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_mman.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_mman.c @@ -295,7 +295,7 @@ static vm_fault_t vm_fault_gtt(struct vm_fault *vmf) struct drm_device *dev = obj->base.dev; struct drm_i915_private *i915 = to_i915(dev); struct intel_runtime_pm *rpm = &i915->runtime_pm; - struct i915_ggtt *ggtt = &i915->ggtt; + struct i915_ggtt *ggtt = to_gt(i915)->ggtt; bool write = area->vm_flags & VM_WRITE; struct i915_gem_ww_ctx ww; intel_wakeref_t wakeref; @@ -388,16 +388,16 @@ retry: assert_rpm_wakelock_held(rpm); /* Mark as being mmapped into userspace for later revocation */ - mutex_lock(&i915->ggtt.vm.mutex); + mutex_lock(&to_gt(i915)->ggtt->vm.mutex); if (!i915_vma_set_userfault(vma) && !obj->userfault_count++) - list_add(&obj->userfault_link, &i915->ggtt.userfault_list); - mutex_unlock(&i915->ggtt.vm.mutex); + list_add(&obj->userfault_link, &to_gt(i915)->ggtt->userfault_list); + mutex_unlock(&to_gt(i915)->ggtt->vm.mutex); /* Track the mmo associated with the fenced vma */ vma->mmo = mmo; if (CONFIG_DRM_I915_USERFAULT_AUTOSUSPEND) - intel_wakeref_auto(&i915->ggtt.userfault_wakeref, + intel_wakeref_auto(&to_gt(i915)->ggtt->userfault_wakeref, msecs_to_jiffies_timeout(CONFIG_DRM_I915_USERFAULT_AUTOSUSPEND)); if (write) { @@ -512,7 +512,7 @@ void i915_gem_object_release_mmap_gtt(struct drm_i915_gem_object *obj) * wakeref. */ wakeref = intel_runtime_pm_get(&i915->runtime_pm); - mutex_lock(&i915->ggtt.vm.mutex); + mutex_lock(&to_gt(i915)->ggtt->vm.mutex); if (!obj->userfault_count) goto out; @@ -530,7 +530,7 @@ void i915_gem_object_release_mmap_gtt(struct drm_i915_gem_object *obj) wmb(); out: - mutex_unlock(&i915->ggtt.vm.mutex); + mutex_unlock(&to_gt(i915)->ggtt->vm.mutex); intel_runtime_pm_put(&i915->runtime_pm, wakeref); } @@ -736,13 +736,14 @@ i915_gem_dumb_mmap_offset(struct drm_file *file, u32 handle, u64 *offset) { + struct drm_i915_private *i915 = to_i915(dev); enum i915_mmap_type mmap_type; if (HAS_LMEM(to_i915(dev))) mmap_type = I915_MMAP_TYPE_FIXED; else if (pat_enabled()) mmap_type = I915_MMAP_TYPE_WC; - else if (!i915_ggtt_has_aperture(&to_i915(dev)->ggtt)) + else if (!i915_ggtt_has_aperture(to_gt(i915)->ggtt)) return -ENODEV; else mmap_type = I915_MMAP_TYPE_GTT; @@ -790,7 +791,7 @@ i915_gem_mmap_offset_ioctl(struct drm_device *dev, void *data, switch (args->flags) { case I915_MMAP_OFFSET_GTT: - if (!i915_ggtt_has_aperture(&i915->ggtt)) + if (!i915_ggtt_has_aperture(to_gt(i915)->ggtt)) return -ENODEV; type = I915_MMAP_TYPE_GTT; break; diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.c b/drivers/gpu/drm/i915/gem/i915_gem_object.c index d87b508b59b1..1a9e1f940a7d 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_object.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_object.c @@ -756,6 +756,18 @@ i915_gem_object_get_moving_fence(struct drm_i915_gem_object *obj) return dma_fence_get(i915_gem_to_ttm(obj)->moving); } +void i915_gem_object_set_moving_fence(struct drm_i915_gem_object *obj, + struct dma_fence *fence) +{ + struct dma_fence **moving = &i915_gem_to_ttm(obj)->moving; + + if (*moving == fence) + return; + + dma_fence_put(*moving); + *moving = dma_fence_get(fence); +} + /** * i915_gem_object_wait_moving_fence - Wait for the object's moving fence if any * @obj: The object whose moving fence to wait for. diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.h b/drivers/gpu/drm/i915/gem/i915_gem_object.h index f66d46882ea7..02c37fe4a535 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_object.h +++ b/drivers/gpu/drm/i915/gem/i915_gem_object.h @@ -459,7 +459,6 @@ i915_gem_object_unpin_pages(struct drm_i915_gem_object *obj) int __i915_gem_object_put_pages(struct drm_i915_gem_object *obj); int i915_gem_object_truncate(struct drm_i915_gem_object *obj); -void i915_gem_object_writeback(struct drm_i915_gem_object *obj); /** * i915_gem_object_pin_map - return a contiguous mapping of the entire object @@ -524,6 +523,9 @@ i915_gem_object_finish_access(struct drm_i915_gem_object *obj) struct dma_fence * i915_gem_object_get_moving_fence(struct drm_i915_gem_object *obj); +void i915_gem_object_set_moving_fence(struct drm_i915_gem_object *obj, + struct dma_fence *fence); + int i915_gem_object_wait_moving_fence(struct drm_i915_gem_object *obj, bool intr); diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h index 4b4829eb16c2..71e778ecaeb8 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h +++ b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h @@ -15,6 +15,7 @@ #include "i915_active.h" #include "i915_selftest.h" +#include "i915_vma_resource.h" struct drm_i915_gem_object; struct intel_fronbuffer; @@ -57,10 +58,26 @@ struct drm_i915_gem_object_ops { void (*put_pages)(struct drm_i915_gem_object *obj, struct sg_table *pages); int (*truncate)(struct drm_i915_gem_object *obj); - void (*writeback)(struct drm_i915_gem_object *obj); - int (*shrinker_release_pages)(struct drm_i915_gem_object *obj, - bool no_gpu_wait, - bool should_writeback); + /** + * shrink - Perform further backend specific actions to facilate + * shrinking. + * @obj: The gem object + * @flags: Extra flags to control shrinking behaviour in the backend + * + * Possible values for @flags: + * + * I915_GEM_OBJECT_SHRINK_WRITEBACK - Try to perform writeback of the + * backing pages, if supported. + * + * I915_GEM_OBJECT_SHRINK_NO_GPU_WAIT - Don't wait for the object to + * idle. Active objects can be considered later. The TTM backend for + * example might have aync migrations going on, which don't use any + * i915_vma to track the active GTT binding, and hence having an unbound + * object might not be enough. + */ +#define I915_GEM_OBJECT_SHRINK_WRITEBACK BIT(0) +#define I915_GEM_OBJECT_SHRINK_NO_GPU_WAIT BIT(1) + int (*shrink)(struct drm_i915_gem_object *obj, unsigned int flags); int (*pread)(struct drm_i915_gem_object *obj, const struct drm_i915_gem_pread *arg); @@ -550,31 +567,7 @@ struct drm_i915_gem_object { struct sg_table *pages; void *mapping; - struct i915_page_sizes { - /** - * The sg mask of the pages sg_table. i.e the mask of - * of the lengths for each sg entry. - */ - unsigned int phys; - - /** - * The gtt page sizes we are allowed to use given the - * sg mask and the supported page sizes. This will - * express the smallest unit we can use for the whole - * object, as well as the larger sizes we may be able - * to use opportunistically. - */ - unsigned int sg; - - /** - * The actual gtt page size usage. Since we can have - * multiple vma associated with this object we need to - * prevent any trampling of state, hence a copy of this - * struct also lives in each vma, therefore the gtt - * value here should only be read/write through the vma. - */ - unsigned int gtt; - } page_sizes; + struct i915_page_sizes page_sizes; I915_SELFTEST_DECLARE(unsigned int page_mask); diff --git a/drivers/gpu/drm/i915/gem/i915_gem_pages.c b/drivers/gpu/drm/i915/gem/i915_gem_pages.c index 9f429ed6e78a..7d2211fbe548 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_pages.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_pages.c @@ -167,16 +167,6 @@ int i915_gem_object_truncate(struct drm_i915_gem_object *obj) return 0; } -/* Try to discard unwanted pages */ -void i915_gem_object_writeback(struct drm_i915_gem_object *obj) -{ - assert_object_held_shared(obj); - GEM_BUG_ON(i915_gem_object_has_pages(obj)); - - if (obj->ops->writeback) - obj->ops->writeback(obj); -} - static void __i915_gem_object_reset_page_iter(struct drm_i915_gem_object *obj) { struct radix_tree_iter iter; diff --git a/drivers/gpu/drm/i915/gem/i915_gem_pm.c b/drivers/gpu/drm/i915/gem/i915_gem_pm.c index ac56124760e1..6da68b38f00f 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_pm.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_pm.c @@ -23,7 +23,7 @@ void i915_gem_suspend(struct drm_i915_private *i915) { GEM_TRACE("%s\n", dev_name(i915->drm.dev)); - intel_wakeref_auto(&i915->ggtt.userfault_wakeref, 0); + intel_wakeref_auto(&to_gt(i915)->ggtt->userfault_wakeref, 0); flush_workqueue(i915->wq); /* diff --git a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c index cc9fe258fba7..6c57b0a79c8a 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c @@ -331,6 +331,21 @@ shmem_writeback(struct drm_i915_gem_object *obj) __shmem_writeback(obj->base.size, obj->base.filp->f_mapping); } +static int shmem_shrink(struct drm_i915_gem_object *obj, unsigned int flags) +{ + switch (obj->mm.madv) { + case I915_MADV_DONTNEED: + return i915_gem_object_truncate(obj); + case __I915_MADV_PURGED: + return 0; + } + + if (flags & I915_GEM_OBJECT_SHRINK_WRITEBACK) + shmem_writeback(obj); + + return 0; +} + void __i915_gem_object_release_shmem(struct drm_i915_gem_object *obj, struct sg_table *pages, @@ -503,7 +518,7 @@ const struct drm_i915_gem_object_ops i915_gem_shmem_ops = { .get_pages = shmem_get_pages, .put_pages = shmem_put_pages, .truncate = shmem_truncate, - .writeback = shmem_writeback, + .shrink = shmem_shrink, .pwrite = shmem_pwrite, .pread = shmem_pread, diff --git a/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c b/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c index cc927e49d21f..6a6ff98a8746 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c @@ -57,21 +57,17 @@ static int drop_pages(struct drm_i915_gem_object *obj, static int try_to_writeback(struct drm_i915_gem_object *obj, unsigned int flags) { - if (obj->ops->shrinker_release_pages) - return obj->ops->shrinker_release_pages(obj, - !(flags & I915_SHRINK_ACTIVE), - flags & I915_SHRINK_WRITEBACK); - - switch (obj->mm.madv) { - case I915_MADV_DONTNEED: - i915_gem_object_truncate(obj); - return 0; - case __I915_MADV_PURGED: - return 0; - } + if (obj->ops->shrink) { + unsigned int shrink_flags = 0; + + if (!(flags & I915_SHRINK_ACTIVE)) + shrink_flags |= I915_GEM_OBJECT_SHRINK_NO_GPU_WAIT; - if (flags & I915_SHRINK_WRITEBACK) - i915_gem_object_writeback(obj); + if (flags & I915_SHRINK_WRITEBACK) + shrink_flags |= I915_GEM_OBJECT_SHRINK_WRITEBACK; + + return obj->ops->shrink(obj, shrink_flags); + } return 0; } @@ -401,9 +397,9 @@ i915_gem_shrinker_vmap(struct notifier_block *nb, unsigned long event, void *ptr I915_SHRINK_VMAPS); /* We also want to clear any cached iomaps as they wrap vmap */ - mutex_lock(&i915->ggtt.vm.mutex); + mutex_lock(&to_gt(i915)->ggtt->vm.mutex); list_for_each_entry_safe(vma, next, - &i915->ggtt.vm.bound_list, vm_link) { + &to_gt(i915)->ggtt->vm.bound_list, vm_link) { unsigned long count = vma->node.size >> PAGE_SHIFT; struct drm_i915_gem_object *obj = vma->obj; @@ -418,7 +414,7 @@ i915_gem_shrinker_vmap(struct notifier_block *nb, unsigned long event, void *ptr i915_gem_object_unlock(obj); } - mutex_unlock(&i915->ggtt.vm.mutex); + mutex_unlock(&to_gt(i915)->ggtt->vm.mutex); *(unsigned long *)ptr += freed_pages; return NOTIFY_DONE; diff --git a/drivers/gpu/drm/i915/gem/i915_gem_stolen.c b/drivers/gpu/drm/i915/gem/i915_gem_stolen.c index 7df50fd6cc7b..26975d857776 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_stolen.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_stolen.c @@ -71,7 +71,7 @@ void i915_gem_stolen_remove_node(struct drm_i915_private *i915, static int i915_adjust_stolen(struct drm_i915_private *i915, struct resource *dsm) { - struct i915_ggtt *ggtt = &i915->ggtt; + struct i915_ggtt *ggtt = to_gt(i915)->ggtt; struct intel_uncore *uncore = ggtt->vm.gt->uncore; struct resource *r; @@ -582,6 +582,7 @@ i915_pages_create_for_stolen(struct drm_device *dev, static int i915_gem_object_get_pages_stolen(struct drm_i915_gem_object *obj) { + struct drm_i915_private *i915 = to_i915(obj->base.dev); struct sg_table *pages = i915_pages_create_for_stolen(obj->base.dev, obj->stolen->start, @@ -589,7 +590,7 @@ static int i915_gem_object_get_pages_stolen(struct drm_i915_gem_object *obj) if (IS_ERR(pages)) return PTR_ERR(pages); - dbg_poison(&to_i915(obj->base.dev)->ggtt, + dbg_poison(to_gt(i915)->ggtt, sg_dma_address(pages->sgl), sg_dma_len(pages->sgl), POISON_INUSE); @@ -602,9 +603,10 @@ static int i915_gem_object_get_pages_stolen(struct drm_i915_gem_object *obj) static void i915_gem_object_put_pages_stolen(struct drm_i915_gem_object *obj, struct sg_table *pages) { + struct drm_i915_private *i915 = to_i915(obj->base.dev); /* Should only be called from i915_gem_object_release_stolen() */ - dbg_poison(&to_i915(obj->base.dev)->ggtt, + dbg_poison(to_gt(i915)->ggtt, sg_dma_address(pages->sgl), sg_dma_len(pages->sgl), POISON_FREE); diff --git a/drivers/gpu/drm/i915/gem/i915_gem_tiling.c b/drivers/gpu/drm/i915/gem/i915_gem_tiling.c index ef4d0f7dc118..c3d432e314c9 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_tiling.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_tiling.c @@ -181,7 +181,8 @@ static int i915_gem_object_fence_prepare(struct drm_i915_gem_object *obj, int tiling_mode, unsigned int stride) { - struct i915_ggtt *ggtt = &to_i915(obj->base.dev)->ggtt; + struct drm_i915_private *i915 = to_i915(obj->base.dev); + struct i915_ggtt *ggtt = to_gt(i915)->ggtt; struct i915_vma *vma, *vn; LIST_HEAD(unbind); int ret = 0; @@ -336,7 +337,7 @@ i915_gem_set_tiling_ioctl(struct drm_device *dev, void *data, struct drm_i915_gem_object *obj; int err; - if (!dev_priv->ggtt.num_fences) + if (!to_gt(dev_priv)->ggtt->num_fences) return -EOPNOTSUPP; obj = i915_gem_object_lookup(file, args->handle); @@ -362,9 +363,9 @@ i915_gem_set_tiling_ioctl(struct drm_device *dev, void *data, args->stride = 0; } else { if (args->tiling_mode == I915_TILING_X) - args->swizzle_mode = to_i915(dev)->ggtt.bit_6_swizzle_x; + args->swizzle_mode = to_gt(dev_priv)->ggtt->bit_6_swizzle_x; else - args->swizzle_mode = to_i915(dev)->ggtt.bit_6_swizzle_y; + args->swizzle_mode = to_gt(dev_priv)->ggtt->bit_6_swizzle_y; /* Hide bit 17 swizzling from the user. This prevents old Mesa * from aborting the application on sw fallbacks to bit 17, @@ -419,7 +420,7 @@ i915_gem_get_tiling_ioctl(struct drm_device *dev, void *data, struct drm_i915_gem_object *obj; int err = -ENOENT; - if (!dev_priv->ggtt.num_fences) + if (!to_gt(dev_priv)->ggtt->num_fences) return -EOPNOTSUPP; rcu_read_lock(); @@ -435,10 +436,10 @@ i915_gem_get_tiling_ioctl(struct drm_device *dev, void *data, switch (args->tiling_mode) { case I915_TILING_X: - args->swizzle_mode = dev_priv->ggtt.bit_6_swizzle_x; + args->swizzle_mode = to_gt(dev_priv)->ggtt->bit_6_swizzle_x; break; case I915_TILING_Y: - args->swizzle_mode = dev_priv->ggtt.bit_6_swizzle_y; + args->swizzle_mode = to_gt(dev_priv)->ggtt->bit_6_swizzle_y; break; default: case I915_TILING_NONE: diff --git a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c index de3fe79b665a..84cae740b4a5 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c @@ -424,16 +424,14 @@ int i915_ttm_purge(struct drm_i915_gem_object *obj) return 0; } -static int i915_ttm_shrinker_release_pages(struct drm_i915_gem_object *obj, - bool no_wait_gpu, - bool should_writeback) +static int i915_ttm_shrink(struct drm_i915_gem_object *obj, unsigned int flags) { struct ttm_buffer_object *bo = i915_gem_to_ttm(obj); struct i915_ttm_tt *i915_tt = container_of(bo->ttm, typeof(*i915_tt), ttm); struct ttm_operation_ctx ctx = { .interruptible = true, - .no_wait_gpu = no_wait_gpu, + .no_wait_gpu = flags & I915_GEM_OBJECT_SHRINK_NO_GPU_WAIT, }; struct ttm_placement place = {}; int ret; @@ -467,7 +465,7 @@ static int i915_ttm_shrinker_release_pages(struct drm_i915_gem_object *obj, return ret; } - if (should_writeback) + if (flags & I915_GEM_OBJECT_SHRINK_WRITEBACK) __shmem_writeback(obj->base.size, i915_tt->filp->f_mapping); return 0; @@ -977,7 +975,7 @@ static const struct drm_i915_gem_object_ops i915_gem_ttm_obj_ops = { .get_pages = i915_ttm_get_pages, .put_pages = i915_ttm_put_pages, .truncate = i915_ttm_truncate, - .shrinker_release_pages = i915_ttm_shrinker_release_pages, + .shrink = i915_ttm_shrink, .adjust_lru = i915_ttm_adjust_lru, .delayed_free = i915_ttm_delayed_free, diff --git a/drivers/gpu/drm/i915/gem/i915_gem_ttm_move.c b/drivers/gpu/drm/i915/gem/i915_gem_ttm_move.c index ee9612a3ee5e..1de306c03aaf 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_ttm_move.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_ttm_move.c @@ -142,7 +142,16 @@ int i915_ttm_move_notify(struct ttm_buffer_object *bo) struct drm_i915_gem_object *obj = i915_ttm_to_gem(bo); int ret; - ret = i915_gem_object_unbind(obj, I915_GEM_OBJECT_UNBIND_ACTIVE); + /* + * Note: The async unbinding here will actually transform the + * blocking wait for unbind into a wait before finally submitting + * evict / migration blit and thus stall the migration timeline + * which may not be good for overall throughput. We should make + * sure we await the unbind fences *after* the migration blit + * instead of *before* as we currently do. + */ + ret = i915_gem_object_unbind(obj, I915_GEM_OBJECT_UNBIND_ACTIVE | + I915_GEM_OBJECT_UNBIND_ASYNC); if (ret) return ret; @@ -525,7 +534,7 @@ int i915_ttm_move(struct ttm_buffer_object *bo, bool evict, return ret; } - migration_fence = __i915_ttm_move(bo, ctx, clear, dst_mem, bo->ttm, + migration_fence = __i915_ttm_move(bo, ctx, clear, dst_mem, ttm, dst_rsgt, true, &deps); i915_deps_fini(&deps); } diff --git a/drivers/gpu/drm/i915/gem/selftests/huge_pages.c b/drivers/gpu/drm/i915/gem/selftests/huge_pages.c index 11f0aa65f8a3..26f997c376a2 100644 --- a/drivers/gpu/drm/i915/gem/selftests/huge_pages.c +++ b/drivers/gpu/drm/i915/gem/selftests/huge_pages.c @@ -370,9 +370,9 @@ static int igt_check_page_sizes(struct i915_vma *vma) err = -EINVAL; } - if (!HAS_PAGE_SIZES(i915, vma->page_sizes.gtt)) { + if (!HAS_PAGE_SIZES(i915, vma->resource->page_sizes_gtt)) { pr_err("unsupported page_sizes.gtt=%u, supported=%u\n", - vma->page_sizes.gtt & ~supported, supported); + vma->resource->page_sizes_gtt & ~supported, supported); err = -EINVAL; } @@ -403,15 +403,9 @@ static int igt_check_page_sizes(struct i915_vma *vma) if (i915_gem_object_is_lmem(obj) && IS_ALIGNED(vma->node.start, SZ_2M) && vma->page_sizes.sg & SZ_2M && - vma->page_sizes.gtt < SZ_2M) { + vma->resource->page_sizes_gtt < SZ_2M) { pr_err("gtt pages mismatch for LMEM, expected 2M GTT pages, sg(%u), gtt(%u)\n", - vma->page_sizes.sg, vma->page_sizes.gtt); - err = -EINVAL; - } - - if (obj->mm.page_sizes.gtt) { - pr_err("obj->page_sizes.gtt(%u) should never be set\n", - obj->mm.page_sizes.gtt); + vma->page_sizes.sg, vma->resource->page_sizes_gtt); err = -EINVAL; } @@ -547,9 +541,9 @@ static int igt_mock_memory_region_huge_pages(void *arg) goto out_unpin; } - if (vma->page_sizes.gtt != page_size) { + if (vma->resource->page_sizes_gtt != page_size) { pr_err("%s page_sizes.gtt=%u, expected=%u\n", - __func__, vma->page_sizes.gtt, + __func__, vma->resource->page_sizes_gtt, page_size); err = -EINVAL; goto out_unpin; @@ -630,9 +624,9 @@ static int igt_mock_ppgtt_misaligned_dma(void *arg) err = igt_check_page_sizes(vma); - if (vma->page_sizes.gtt != page_size) { + if (vma->resource->page_sizes_gtt != page_size) { pr_err("page_sizes.gtt=%u, expected %u\n", - vma->page_sizes.gtt, page_size); + vma->resource->page_sizes_gtt, page_size); err = -EINVAL; } @@ -657,9 +651,10 @@ static int igt_mock_ppgtt_misaligned_dma(void *arg) err = igt_check_page_sizes(vma); - if (vma->page_sizes.gtt != I915_GTT_PAGE_SIZE_4K) { + if (vma->resource->page_sizes_gtt != I915_GTT_PAGE_SIZE_4K) { pr_err("page_sizes.gtt=%u, expected %llu\n", - vma->page_sizes.gtt, I915_GTT_PAGE_SIZE_4K); + vma->resource->page_sizes_gtt, + I915_GTT_PAGE_SIZE_4K); err = -EINVAL; } @@ -805,9 +800,9 @@ static int igt_mock_ppgtt_huge_fill(void *arg) } } - if (vma->page_sizes.gtt != expected_gtt) { + if (vma->resource->page_sizes_gtt != expected_gtt) { pr_err("gtt=%u, expected=%u, size=%zd, single=%s\n", - vma->page_sizes.gtt, expected_gtt, + vma->resource->page_sizes_gtt, expected_gtt, obj->base.size, yesno(!!single)); err = -EINVAL; break; @@ -961,10 +956,10 @@ static int igt_mock_ppgtt_64K(void *arg) } } - if (vma->page_sizes.gtt != expected_gtt) { + if (vma->resource->page_sizes_gtt != expected_gtt) { pr_err("gtt=%u, expected=%u, i=%d, single=%s\n", - vma->page_sizes.gtt, expected_gtt, i, - yesno(!!single)); + vma->resource->page_sizes_gtt, + expected_gtt, i, yesno(!!single)); err = -EINVAL; goto out_vma_unpin; } diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_client_blt.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_client_blt.c index 75947e9dada2..c08f766e6e15 100644 --- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_client_blt.c +++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_client_blt.c @@ -543,7 +543,7 @@ static bool has_bit17_swizzle(int sw) static bool bad_swizzling(struct drm_i915_private *i915) { - struct i915_ggtt *ggtt = &i915->ggtt; + struct i915_ggtt *ggtt = to_gt(i915)->ggtt; if (i915->quirks & QUIRK_PIN_SWIZZLED_PAGES) return true; diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c index 3f41fe5ec9d4..80d99b9c694f 100644 --- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c +++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c @@ -1374,7 +1374,7 @@ static int igt_ctx_readonly(void *arg) goto out_file; } - vm = ctx->vm ?: &i915->ggtt.alias->vm; + vm = ctx->vm ?: &to_gt(i915)->ggtt->alias->vm; if (!vm || !vm->has_read_only) { err = 0; goto out_file; diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_migrate.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_migrate.c index ecb691c81d1e..d534141b2cf7 100644 --- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_migrate.c +++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_migrate.c @@ -4,8 +4,13 @@ */ #include "gt/intel_migrate.h" +#include "gt/intel_gpu_commands.h" #include "gem/i915_gem_ttm_move.h" +#include "i915_deps.h" + +#include "selftests/igt_spinner.h" + static int igt_fill_check_buffer(struct drm_i915_gem_object *obj, bool fill) { @@ -101,7 +106,8 @@ static int igt_same_create_migrate(void *arg) } static int lmem_pages_migrate_one(struct i915_gem_ww_ctx *ww, - struct drm_i915_gem_object *obj) + struct drm_i915_gem_object *obj, + struct i915_vma *vma) { int err; @@ -109,6 +115,24 @@ static int lmem_pages_migrate_one(struct i915_gem_ww_ctx *ww, if (err) return err; + if (vma) { + err = i915_vma_pin_ww(vma, ww, obj->base.size, 0, + 0UL | PIN_OFFSET_FIXED | + PIN_USER); + if (err) { + if (err != -EINTR && err != ERESTARTSYS && + err != -EDEADLK) + pr_err("Failed to pin vma.\n"); + return err; + } + + i915_vma_unpin(vma); + } + + /* + * Migration will implicitly unbind (asynchronously) any bound + * vmas. + */ if (i915_gem_object_is_lmem(obj)) { err = i915_gem_object_migrate(obj, ww, INTEL_REGION_SMEM); if (err) { @@ -149,11 +173,15 @@ static int lmem_pages_migrate_one(struct i915_gem_ww_ctx *ww, return err; } -static int igt_lmem_pages_migrate(void *arg) +static int __igt_lmem_pages_migrate(struct intel_gt *gt, + struct i915_address_space *vm, + struct i915_deps *deps, + struct igt_spinner *spin, + struct dma_fence *spin_fence) { - struct intel_gt *gt = arg; struct drm_i915_private *i915 = gt->i915; struct drm_i915_gem_object *obj; + struct i915_vma *vma = NULL; struct i915_gem_ww_ctx ww; struct i915_request *rq; int err; @@ -165,6 +193,14 @@ static int igt_lmem_pages_migrate(void *arg) if (IS_ERR(obj)) return PTR_ERR(obj); + if (vm) { + vma = i915_vma_instance(obj, vm, NULL); + if (IS_ERR(vma)) { + err = PTR_ERR(vma); + goto out_put; + } + } + /* Initial GPU fill, sync, CPU initialization. */ for_i915_gem_ww(&ww, err, true) { err = i915_gem_object_lock(obj, &ww); @@ -175,25 +211,23 @@ static int igt_lmem_pages_migrate(void *arg) if (err) continue; - err = intel_migrate_clear(>->migrate, &ww, NULL, + err = intel_migrate_clear(>->migrate, &ww, deps, obj->mm.pages->sgl, obj->cache_level, i915_gem_object_is_lmem(obj), 0xdeadbeaf, &rq); if (rq) { dma_resv_add_excl_fence(obj->base.resv, &rq->fence); + i915_gem_object_set_moving_fence(obj, &rq->fence); i915_request_put(rq); } if (err) continue; - err = i915_gem_object_wait(obj, I915_WAIT_INTERRUPTIBLE, - 5 * HZ); - if (err) - continue; - - err = igt_fill_check_buffer(obj, true); - if (err) - continue; + if (!vma) { + err = igt_fill_check_buffer(obj, true); + if (err) + continue; + } } if (err) goto out_put; @@ -204,7 +238,7 @@ static int igt_lmem_pages_migrate(void *arg) */ for (i = 1; i <= 5; ++i) { for_i915_gem_ww(&ww, err, true) - err = lmem_pages_migrate_one(&ww, obj); + err = lmem_pages_migrate_one(&ww, obj, vma); if (err) goto out_put; } @@ -213,12 +247,27 @@ static int igt_lmem_pages_migrate(void *arg) if (err) goto out_put; + if (spin) { + if (dma_fence_is_signaled(spin_fence)) { + pr_err("Spinner was terminated by hangcheck.\n"); + err = -EBUSY; + goto out_unlock; + } + igt_spinner_end(spin); + } + /* Finally sync migration and check content. */ err = i915_gem_object_wait_migration(obj, true); if (err) goto out_unlock; - err = igt_fill_check_buffer(obj, false); + if (vma) { + err = i915_vma_wait_for_bind(vma); + if (err) + goto out_unlock; + } else { + err = igt_fill_check_buffer(obj, false); + } out_unlock: i915_gem_object_unlock(obj); @@ -231,6 +280,7 @@ out_put: static int igt_lmem_pages_failsafe_migrate(void *arg) { int fail_gpu, fail_alloc, ret; + struct intel_gt *gt = arg; for (fail_gpu = 0; fail_gpu < 2; ++fail_gpu) { for (fail_alloc = 0; fail_alloc < 2; ++fail_alloc) { @@ -238,7 +288,118 @@ static int igt_lmem_pages_failsafe_migrate(void *arg) fail_gpu, fail_alloc); i915_ttm_migrate_set_failure_modes(fail_gpu, fail_alloc); - ret = igt_lmem_pages_migrate(arg); + ret = __igt_lmem_pages_migrate(gt, NULL, NULL, NULL, NULL); + if (ret) + goto out_err; + } + } + +out_err: + i915_ttm_migrate_set_failure_modes(false, false); + return ret; +} + +/* + * This subtest tests that unbinding at migration is indeed performed + * async. We launch a spinner and a number of migrations depending on + * that spinner to have terminated. Before each migration we bind a + * vma, which should then be async unbound by the migration operation. + * If we are able to schedule migrations without blocking while the + * spinner is still running, those unbinds are indeed async and non- + * blocking. + * + * Note that each async bind operation is awaiting the previous migration + * due to the moving fence resulting from the migration. + */ +static int igt_async_migrate(struct intel_gt *gt) +{ + struct intel_engine_cs *engine; + enum intel_engine_id id; + struct i915_ppgtt *ppgtt; + struct igt_spinner spin; + int err; + + ppgtt = i915_ppgtt_create(gt, 0); + if (IS_ERR(ppgtt)) + return PTR_ERR(ppgtt); + + if (igt_spinner_init(&spin, gt)) { + err = -ENOMEM; + goto out_spin; + } + + for_each_engine(engine, gt, id) { + struct ttm_operation_ctx ctx = { + .interruptible = true + }; + struct dma_fence *spin_fence; + struct intel_context *ce; + struct i915_request *rq; + struct i915_deps deps; + + ce = intel_context_create(engine); + if (IS_ERR(ce)) { + err = PTR_ERR(ce); + goto out_ce; + } + + /* + * Use MI_NOOP, making the spinner non-preemptible. If there + * is a code path where we fail async operation due to the + * running spinner, we will block and fail to end the + * spinner resulting in a deadlock. But with a non- + * preemptible spinner, hangcheck will terminate the spinner + * for us, and we will later detect that and fail the test. + */ + rq = igt_spinner_create_request(&spin, ce, MI_NOOP); + intel_context_put(ce); + if (IS_ERR(rq)) { + err = PTR_ERR(rq); + goto out_ce; + } + + i915_deps_init(&deps, GFP_KERNEL); + err = i915_deps_add_dependency(&deps, &rq->fence, &ctx); + spin_fence = dma_fence_get(&rq->fence); + i915_request_add(rq); + if (err) + goto out_ce; + + err = __igt_lmem_pages_migrate(gt, &ppgtt->vm, &deps, &spin, + spin_fence); + i915_deps_fini(&deps); + dma_fence_put(spin_fence); + if (err) + goto out_ce; + } + +out_ce: + igt_spinner_fini(&spin); +out_spin: + i915_vm_put(&ppgtt->vm); + + return err; +} + +/* + * Setting ASYNC_FAIL_ALLOC to 2 will simulate memory allocation failure while + * arming the migration error check and block async migration. This + * will cause us to deadlock and hangcheck will terminate the spinner + * causing the test to fail. + */ +#define ASYNC_FAIL_ALLOC 1 +static int igt_lmem_async_migrate(void *arg) +{ + int fail_gpu, fail_alloc, ret; + struct intel_gt *gt = arg; + + for (fail_gpu = 0; fail_gpu < 2; ++fail_gpu) { + for (fail_alloc = 0; fail_alloc < ASYNC_FAIL_ALLOC; ++fail_alloc) { + pr_info("Simulated failure modes: gpu: %d, alloc: %d\n", + fail_gpu, fail_alloc); + i915_ttm_migrate_set_failure_modes(fail_gpu, + fail_alloc); + ret = igt_async_migrate(gt); if (ret) goto out_err; } @@ -256,6 +417,7 @@ int i915_gem_migrate_live_selftests(struct drm_i915_private *i915) SUBTEST(igt_lmem_create_migrate), SUBTEST(igt_same_create_migrate), SUBTEST(igt_lmem_pages_failsafe_migrate), + SUBTEST(igt_lmem_async_migrate), }; if (!HAS_LMEM(i915)) diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c index c6291429b00c..f61356b72b1c 100644 --- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c +++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c @@ -307,7 +307,7 @@ static int igt_partial_tiling(void *arg) int tiling; int err; - if (!i915_ggtt_has_aperture(&i915->ggtt)) + if (!i915_ggtt_has_aperture(to_gt(i915)->ggtt)) return 0; /* We want to check the page mapping and fencing of a large object @@ -320,7 +320,7 @@ static int igt_partial_tiling(void *arg) obj = huge_gem_object(i915, nreal << PAGE_SHIFT, - (1 + next_prime_number(i915->ggtt.vm.total >> PAGE_SHIFT)) << PAGE_SHIFT); + (1 + next_prime_number(to_gt(i915)->ggtt->vm.total >> PAGE_SHIFT)) << PAGE_SHIFT); if (IS_ERR(obj)) return PTR_ERR(obj); @@ -366,10 +366,10 @@ static int igt_partial_tiling(void *arg) tile.tiling = tiling; switch (tiling) { case I915_TILING_X: - tile.swizzle = i915->ggtt.bit_6_swizzle_x; + tile.swizzle = to_gt(i915)->ggtt->bit_6_swizzle_x; break; case I915_TILING_Y: - tile.swizzle = i915->ggtt.bit_6_swizzle_y; + tile.swizzle = to_gt(i915)->ggtt->bit_6_swizzle_y; break; } @@ -440,7 +440,7 @@ static int igt_smoke_tiling(void *arg) IGT_TIMEOUT(end); int err; - if (!i915_ggtt_has_aperture(&i915->ggtt)) + if (!i915_ggtt_has_aperture(to_gt(i915)->ggtt)) return 0; /* @@ -457,7 +457,7 @@ static int igt_smoke_tiling(void *arg) obj = huge_gem_object(i915, nreal << PAGE_SHIFT, - (1 + next_prime_number(i915->ggtt.vm.total >> PAGE_SHIFT)) << PAGE_SHIFT); + (1 + next_prime_number(to_gt(i915)->ggtt->vm.total >> PAGE_SHIFT)) << PAGE_SHIFT); if (IS_ERR(obj)) return PTR_ERR(obj); @@ -486,10 +486,10 @@ static int igt_smoke_tiling(void *arg) break; case I915_TILING_X: - tile.swizzle = i915->ggtt.bit_6_swizzle_x; + tile.swizzle = to_gt(i915)->ggtt->bit_6_swizzle_x; break; case I915_TILING_Y: - tile.swizzle = i915->ggtt.bit_6_swizzle_y; + tile.swizzle = to_gt(i915)->ggtt->bit_6_swizzle_y; break; } @@ -856,6 +856,7 @@ static int wc_check(struct drm_i915_gem_object *obj) static bool can_mmap(struct drm_i915_gem_object *obj, enum i915_mmap_type type) { + struct drm_i915_private *i915 = to_i915(obj->base.dev); bool no_map; if (obj->ops->mmap_offset) @@ -864,7 +865,7 @@ static bool can_mmap(struct drm_i915_gem_object *obj, enum i915_mmap_type type) return false; if (type == I915_MMAP_TYPE_GTT && - !i915_ggtt_has_aperture(&to_i915(obj->base.dev)->ggtt)) + !i915_ggtt_has_aperture(to_gt(i915)->ggtt)) return false; i915_gem_object_lock(obj, NULL); diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_object.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_object.c index 740ee8086a27..fe0a890775e2 100644 --- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_object.c +++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_object.c @@ -43,7 +43,7 @@ static int igt_gem_huge(void *arg) obj = huge_gem_object(i915, nreal * PAGE_SIZE, - i915->ggtt.vm.total + PAGE_SIZE); + to_gt(i915)->ggtt->vm.total + PAGE_SIZE); if (IS_ERR(obj)) return PTR_ERR(obj); diff --git a/drivers/gpu/drm/i915/gt/gen6_ppgtt.c b/drivers/gpu/drm/i915/gt/gen6_ppgtt.c index 6e9292918bfc..d657ffd6c86a 100644 --- a/drivers/gpu/drm/i915/gt/gen6_ppgtt.c +++ b/drivers/gpu/drm/i915/gt/gen6_ppgtt.c @@ -104,17 +104,17 @@ static void gen6_ppgtt_clear_range(struct i915_address_space *vm, } static void gen6_ppgtt_insert_entries(struct i915_address_space *vm, - struct i915_vma *vma, + struct i915_vma_resource *vma_res, enum i915_cache_level cache_level, u32 flags) { struct i915_ppgtt *ppgtt = i915_vm_to_ppgtt(vm); struct i915_page_directory * const pd = ppgtt->pd; - unsigned int first_entry = vma->node.start / I915_GTT_PAGE_SIZE; + unsigned int first_entry = vma_res->start / I915_GTT_PAGE_SIZE; unsigned int act_pt = first_entry / GEN6_PTES; unsigned int act_pte = first_entry % GEN6_PTES; const u32 pte_encode = vm->pte_encode(0, cache_level, flags); - struct sgt_dma iter = sgt_dma(vma); + struct sgt_dma iter = sgt_dma(vma_res); gen6_pte_t *vaddr; GEM_BUG_ON(!pd->entry[act_pt]); @@ -140,7 +140,7 @@ static void gen6_ppgtt_insert_entries(struct i915_address_space *vm, } } while (1); - vma->page_sizes.gtt = I915_GTT_PAGE_SIZE; + vma_res->page_sizes_gtt = I915_GTT_PAGE_SIZE; } static void gen6_flush_pd(struct gen6_ppgtt *ppgtt, u64 start, u64 end) @@ -271,13 +271,13 @@ static void gen6_ppgtt_cleanup(struct i915_address_space *vm) static void pd_vma_bind(struct i915_address_space *vm, struct i915_vm_pt_stash *stash, - struct i915_vma *vma, + struct i915_vma_resource *vma_res, enum i915_cache_level cache_level, u32 unused) { struct i915_ggtt *ggtt = i915_vm_to_ggtt(vm); - struct gen6_ppgtt *ppgtt = vma->private; - u32 ggtt_offset = i915_ggtt_offset(vma) / I915_GTT_PAGE_SIZE; + struct gen6_ppgtt *ppgtt = vma_res->private; + u32 ggtt_offset = vma_res->start / I915_GTT_PAGE_SIZE; ppgtt->pp_dir = ggtt_offset * sizeof(gen6_pte_t) << 10; ppgtt->pd_addr = (gen6_pte_t __iomem *)ggtt->gsm + ggtt_offset; @@ -285,9 +285,10 @@ static void pd_vma_bind(struct i915_address_space *vm, gen6_flush_pd(ppgtt, 0, ppgtt->base.vm.total); } -static void pd_vma_unbind(struct i915_address_space *vm, struct i915_vma *vma) +static void pd_vma_unbind(struct i915_address_space *vm, + struct i915_vma_resource *vma_res) { - struct gen6_ppgtt *ppgtt = vma->private; + struct gen6_ppgtt *ppgtt = vma_res->private; struct i915_page_directory * const pd = ppgtt->base.pd; struct i915_page_table *pt; unsigned int pde; diff --git a/drivers/gpu/drm/i915/gt/gen8_ppgtt.c b/drivers/gpu/drm/i915/gt/gen8_ppgtt.c index b012c50f7ce7..c43e724afa9f 100644 --- a/drivers/gpu/drm/i915/gt/gen8_ppgtt.c +++ b/drivers/gpu/drm/i915/gt/gen8_ppgtt.c @@ -453,20 +453,21 @@ gen8_ppgtt_insert_pte(struct i915_ppgtt *ppgtt, return idx; } -static void gen8_ppgtt_insert_huge(struct i915_vma *vma, +static void gen8_ppgtt_insert_huge(struct i915_address_space *vm, + struct i915_vma_resource *vma_res, struct sgt_dma *iter, enum i915_cache_level cache_level, u32 flags) { const gen8_pte_t pte_encode = gen8_pte_encode(0, cache_level, flags); unsigned int rem = sg_dma_len(iter->sg); - u64 start = vma->node.start; + u64 start = vma_res->start; - GEM_BUG_ON(!i915_vm_is_4lvl(vma->vm)); + GEM_BUG_ON(!i915_vm_is_4lvl(vm)); do { struct i915_page_directory * const pdp = - gen8_pdp_for_page_address(vma->vm, start); + gen8_pdp_for_page_address(vm, start); struct i915_page_directory * const pd = i915_pd_entry(pdp, __gen8_pte_index(start, 2)); gen8_pte_t encode = pte_encode; @@ -475,7 +476,7 @@ static void gen8_ppgtt_insert_huge(struct i915_vma *vma, gen8_pte_t *vaddr; u16 index; - if (vma->page_sizes.sg & I915_GTT_PAGE_SIZE_2M && + if (vma_res->bi.page_sizes.sg & I915_GTT_PAGE_SIZE_2M && IS_ALIGNED(iter->dma, I915_GTT_PAGE_SIZE_2M) && rem >= I915_GTT_PAGE_SIZE_2M && !__gen8_pte_index(start, 0)) { @@ -492,7 +493,7 @@ static void gen8_ppgtt_insert_huge(struct i915_vma *vma, page_size = I915_GTT_PAGE_SIZE; if (!index && - vma->page_sizes.sg & I915_GTT_PAGE_SIZE_64K && + vma_res->bi.page_sizes.sg & I915_GTT_PAGE_SIZE_64K && IS_ALIGNED(iter->dma, I915_GTT_PAGE_SIZE_64K) && (IS_ALIGNED(rem, I915_GTT_PAGE_SIZE_64K) || rem >= (I915_PDES - index) * I915_GTT_PAGE_SIZE)) @@ -541,9 +542,9 @@ static void gen8_ppgtt_insert_huge(struct i915_vma *vma, */ if (maybe_64K != -1 && (index == I915_PDES || - (i915_vm_has_scratch_64K(vma->vm) && - !iter->sg && IS_ALIGNED(vma->node.start + - vma->node.size, + (i915_vm_has_scratch_64K(vm) && + !iter->sg && IS_ALIGNED(vma_res->start + + vma_res->node_size, I915_GTT_PAGE_SIZE_2M)))) { vaddr = px_vaddr(pd); vaddr[maybe_64K] |= GEN8_PDE_IPS_64K; @@ -559,10 +560,10 @@ static void gen8_ppgtt_insert_huge(struct i915_vma *vma, * instead - which we detect as missing results during * selftests. */ - if (I915_SELFTEST_ONLY(vma->vm->scrub_64K)) { + if (I915_SELFTEST_ONLY(vm->scrub_64K)) { u16 i; - encode = vma->vm->scratch[0]->encode; + encode = vm->scratch[0]->encode; vaddr = px_vaddr(i915_pt_entry(pd, maybe_64K)); for (i = 1; i < index; i += 16) @@ -572,22 +573,22 @@ static void gen8_ppgtt_insert_huge(struct i915_vma *vma, } } - vma->page_sizes.gtt |= page_size; + vma_res->page_sizes_gtt |= page_size; } while (iter->sg && sg_dma_len(iter->sg)); } static void gen8_ppgtt_insert(struct i915_address_space *vm, - struct i915_vma *vma, + struct i915_vma_resource *vma_res, enum i915_cache_level cache_level, u32 flags) { struct i915_ppgtt * const ppgtt = i915_vm_to_ppgtt(vm); - struct sgt_dma iter = sgt_dma(vma); + struct sgt_dma iter = sgt_dma(vma_res); - if (vma->page_sizes.sg > I915_GTT_PAGE_SIZE) { - gen8_ppgtt_insert_huge(vma, &iter, cache_level, flags); + if (vma_res->bi.page_sizes.sg > I915_GTT_PAGE_SIZE) { + gen8_ppgtt_insert_huge(vm, vma_res, &iter, cache_level, flags); } else { - u64 idx = vma->node.start >> GEN8_PTE_SHIFT; + u64 idx = vma_res->start >> GEN8_PTE_SHIFT; do { struct i915_page_directory * const pdp = @@ -597,7 +598,7 @@ static void gen8_ppgtt_insert(struct i915_address_space *vm, cache_level, flags); } while (idx); - vma->page_sizes.gtt = I915_GTT_PAGE_SIZE; + vma_res->page_sizes_gtt = I915_GTT_PAGE_SIZE; } } diff --git a/drivers/gpu/drm/i915/gt/intel_context.c b/drivers/gpu/drm/i915/gt/intel_context.c index ba083d800a08..5d0ec7c49b6a 100644 --- a/drivers/gpu/drm/i915/gt/intel_context.c +++ b/drivers/gpu/drm/i915/gt/intel_context.c @@ -79,7 +79,8 @@ static int intel_context_active_acquire(struct intel_context *ce) __i915_active_acquire(&ce->active); - if (intel_context_is_barrier(ce) || intel_engine_uses_guc(ce->engine)) + if (intel_context_is_barrier(ce) || intel_engine_uses_guc(ce->engine) || + intel_context_is_parallel(ce)) return 0; /* Preallocate tracking nodes */ @@ -563,7 +564,6 @@ void intel_context_bind_parent_child(struct intel_context *parent, * Callers responsibility to validate that this function is used * correctly but we use GEM_BUG_ON here ensure that they do. */ - GEM_BUG_ON(!intel_engine_uses_guc(parent->engine)); GEM_BUG_ON(intel_context_is_pinned(parent)); GEM_BUG_ON(intel_context_is_child(parent)); GEM_BUG_ON(intel_context_is_pinned(child)); diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c index 352254e001b4..d1daa4cc2895 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c +++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c @@ -1708,18 +1708,15 @@ static void intel_engine_print_registers(struct intel_engine_cs *engine, static void print_request_ring(struct drm_printer *m, struct i915_request *rq) { - struct i915_vma_snapshot *vsnap = &rq->batch_snapshot; + struct i915_vma_resource *vma_res = rq->batch_res; void *ring; int size; - if (!i915_vma_snapshot_present(vsnap)) - vsnap = NULL; - drm_printf(m, "[head %04x, postfix %04x, tail %04x, batch 0x%08x_%08x]:\n", rq->head, rq->postfix, rq->tail, - vsnap ? upper_32_bits(vsnap->gtt_offset) : ~0u, - vsnap ? lower_32_bits(vsnap->gtt_offset) : ~0u); + vma_res ? upper_32_bits(vma_res->start) : ~0u, + vma_res ? lower_32_bits(vma_res->start) : ~0u); size = rq->tail - rq->head; if (rq->tail < rq->head) diff --git a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c index a69df5e9e77a..be56d0b41892 100644 --- a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c +++ b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c @@ -2599,6 +2599,43 @@ static void execlists_context_cancel_request(struct intel_context *ce, current->comm); } +static struct intel_context * +execlists_create_parallel(struct intel_engine_cs **engines, + unsigned int num_siblings, + unsigned int width) +{ + struct intel_context *parent = NULL, *ce, *err; + int i; + + GEM_BUG_ON(num_siblings != 1); + + for (i = 0; i < width; ++i) { + ce = intel_context_create(engines[i]); + if (IS_ERR(ce)) { + err = ce; + goto unwind; + } + + if (i == 0) + parent = ce; + else + intel_context_bind_parent_child(parent, ce); + } + + parent->parallel.fence_context = dma_fence_context_alloc(1); + + intel_context_set_nopreempt(parent); + for_each_child(parent, ce) + intel_context_set_nopreempt(ce); + + return parent; + +unwind: + if (parent) + intel_context_put(parent); + return err; +} + static const struct intel_context_ops execlists_context_ops = { .flags = COPS_HAS_INFLIGHT, @@ -2617,6 +2654,7 @@ static const struct intel_context_ops execlists_context_ops = { .reset = lrc_reset, .destroy = lrc_destroy, + .create_parallel = execlists_create_parallel, .create_virtual = execlists_create_virtual, }; diff --git a/drivers/gpu/drm/i915/gt/intel_ggtt.c b/drivers/gpu/drm/i915/gt/intel_ggtt.c index 5263dda7f8d5..a1b2761bc16e 100644 --- a/drivers/gpu/drm/i915/gt/intel_ggtt.c +++ b/drivers/gpu/drm/i915/gt/intel_ggtt.c @@ -86,7 +86,7 @@ int i915_ggtt_init_hw(struct drm_i915_private *i915) * beyond the end of the batch buffer, across the page boundary, * and beyond the end of the GTT if we do not provide a guard. */ - ret = ggtt_init_hw(&i915->ggtt); + ret = ggtt_init_hw(to_gt(i915)->ggtt); if (ret) return ret; @@ -142,7 +142,7 @@ void i915_ggtt_suspend_vm(struct i915_address_space *vm) continue; if (!i915_vma_is_bound(vma, I915_VMA_GLOBAL_BIND)) { - __i915_vma_evict(vma); + __i915_vma_evict(vma, false); drm_mm_remove_node(&vma->node); } } @@ -235,7 +235,7 @@ static void gen8_ggtt_insert_page(struct i915_address_space *vm, } static void gen8_ggtt_insert_entries(struct i915_address_space *vm, - struct i915_vma *vma, + struct i915_vma_resource *vma_res, enum i915_cache_level level, u32 flags) { @@ -252,10 +252,10 @@ static void gen8_ggtt_insert_entries(struct i915_address_space *vm, */ gte = (gen8_pte_t __iomem *)ggtt->gsm; - gte += vma->node.start / I915_GTT_PAGE_SIZE; - end = gte + vma->node.size / I915_GTT_PAGE_SIZE; + gte += vma_res->start / I915_GTT_PAGE_SIZE; + end = gte + vma_res->node_size / I915_GTT_PAGE_SIZE; - for_each_sgt_daddr(addr, iter, vma->pages) + for_each_sgt_daddr(addr, iter, vma_res->bi.pages) gen8_set_pte(gte++, pte_encode | addr); GEM_BUG_ON(gte > end); @@ -292,7 +292,7 @@ static void gen6_ggtt_insert_page(struct i915_address_space *vm, * through the GMADR mapped BAR (i915->mm.gtt->gtt). */ static void gen6_ggtt_insert_entries(struct i915_address_space *vm, - struct i915_vma *vma, + struct i915_vma_resource *vma_res, enum i915_cache_level level, u32 flags) { @@ -303,10 +303,10 @@ static void gen6_ggtt_insert_entries(struct i915_address_space *vm, dma_addr_t addr; gte = (gen6_pte_t __iomem *)ggtt->gsm; - gte += vma->node.start / I915_GTT_PAGE_SIZE; - end = gte + vma->node.size / I915_GTT_PAGE_SIZE; + gte += vma_res->start / I915_GTT_PAGE_SIZE; + end = gte + vma_res->node_size / I915_GTT_PAGE_SIZE; - for_each_sgt_daddr(addr, iter, vma->pages) + for_each_sgt_daddr(addr, iter, vma_res->bi.pages) iowrite32(vm->pte_encode(addr, level, flags), gte++); GEM_BUG_ON(gte > end); @@ -389,7 +389,7 @@ static void bxt_vtd_ggtt_insert_page__BKL(struct i915_address_space *vm, struct insert_entries { struct i915_address_space *vm; - struct i915_vma *vma; + struct i915_vma_resource *vma_res; enum i915_cache_level level; u32 flags; }; @@ -398,18 +398,18 @@ static int bxt_vtd_ggtt_insert_entries__cb(void *_arg) { struct insert_entries *arg = _arg; - gen8_ggtt_insert_entries(arg->vm, arg->vma, arg->level, arg->flags); + gen8_ggtt_insert_entries(arg->vm, arg->vma_res, arg->level, arg->flags); bxt_vtd_ggtt_wa(arg->vm); return 0; } static void bxt_vtd_ggtt_insert_entries__BKL(struct i915_address_space *vm, - struct i915_vma *vma, + struct i915_vma_resource *vma_res, enum i915_cache_level level, u32 flags) { - struct insert_entries arg = { vm, vma, level, flags }; + struct insert_entries arg = { vm, vma_res, level, flags }; stop_machine(bxt_vtd_ggtt_insert_entries__cb, &arg, NULL); } @@ -448,14 +448,14 @@ static void i915_ggtt_insert_page(struct i915_address_space *vm, } static void i915_ggtt_insert_entries(struct i915_address_space *vm, - struct i915_vma *vma, + struct i915_vma_resource *vma_res, enum i915_cache_level cache_level, u32 unused) { unsigned int flags = (cache_level == I915_CACHE_NONE) ? AGP_USER_MEMORY : AGP_USER_CACHED_MEMORY; - intel_gtt_insert_sg_entries(vma->pages, vma->node.start >> PAGE_SHIFT, + intel_gtt_insert_sg_entries(vma_res->bi.pages, vma_res->start >> PAGE_SHIFT, flags); } @@ -467,30 +467,32 @@ static void i915_ggtt_clear_range(struct i915_address_space *vm, static void ggtt_bind_vma(struct i915_address_space *vm, struct i915_vm_pt_stash *stash, - struct i915_vma *vma, + struct i915_vma_resource *vma_res, enum i915_cache_level cache_level, u32 flags) { - struct drm_i915_gem_object *obj = vma->obj; u32 pte_flags; - if (i915_vma_is_bound(vma, ~flags & I915_VMA_BIND_MASK)) + if (vma_res->bound_flags & (~flags & I915_VMA_BIND_MASK)) return; + vma_res->bound_flags |= flags; + /* Applicable to VLV (gen8+ do not support RO in the GGTT) */ pte_flags = 0; - if (i915_gem_object_is_readonly(obj)) + if (vma_res->bi.readonly) pte_flags |= PTE_READ_ONLY; - if (i915_gem_object_is_lmem(obj)) + if (vma_res->bi.lmem) pte_flags |= PTE_LM; - vm->insert_entries(vm, vma, cache_level, pte_flags); - vma->page_sizes.gtt = I915_GTT_PAGE_SIZE; + vm->insert_entries(vm, vma_res, cache_level, pte_flags); + vma_res->page_sizes_gtt = I915_GTT_PAGE_SIZE; } -static void ggtt_unbind_vma(struct i915_address_space *vm, struct i915_vma *vma) +static void ggtt_unbind_vma(struct i915_address_space *vm, + struct i915_vma_resource *vma_res) { - vm->clear_range(vm, vma->node.start, vma->size); + vm->clear_range(vm, vma_res->start, vma_res->vma_size); } static int ggtt_reserve_guc_top(struct i915_ggtt *ggtt) @@ -623,7 +625,7 @@ err: static void aliasing_gtt_bind_vma(struct i915_address_space *vm, struct i915_vm_pt_stash *stash, - struct i915_vma *vma, + struct i915_vma_resource *vma_res, enum i915_cache_level cache_level, u32 flags) { @@ -631,25 +633,27 @@ static void aliasing_gtt_bind_vma(struct i915_address_space *vm, /* Currently applicable only to VLV */ pte_flags = 0; - if (i915_gem_object_is_readonly(vma->obj)) + if (vma_res->bi.readonly) pte_flags |= PTE_READ_ONLY; if (flags & I915_VMA_LOCAL_BIND) ppgtt_bind_vma(&i915_vm_to_ggtt(vm)->alias->vm, - stash, vma, cache_level, flags); + stash, vma_res, cache_level, flags); if (flags & I915_VMA_GLOBAL_BIND) - vm->insert_entries(vm, vma, cache_level, pte_flags); + vm->insert_entries(vm, vma_res, cache_level, pte_flags); + + vma_res->bound_flags |= flags; } static void aliasing_gtt_unbind_vma(struct i915_address_space *vm, - struct i915_vma *vma) + struct i915_vma_resource *vma_res) { - if (i915_vma_is_bound(vma, I915_VMA_GLOBAL_BIND)) - vm->clear_range(vm, vma->node.start, vma->size); + if (vma_res->bound_flags & I915_VMA_GLOBAL_BIND) + vm->clear_range(vm, vma_res->start, vma_res->vma_size); - if (i915_vma_is_bound(vma, I915_VMA_LOCAL_BIND)) - ppgtt_unbind_vma(&i915_vm_to_ggtt(vm)->alias->vm, vma); + if (vma_res->bound_flags & I915_VMA_LOCAL_BIND) + ppgtt_unbind_vma(&i915_vm_to_ggtt(vm)->alias->vm, vma_res); } static int init_aliasing_ppgtt(struct i915_ggtt *ggtt) @@ -722,14 +726,14 @@ int i915_init_ggtt(struct drm_i915_private *i915) { int ret; - ret = init_ggtt(&i915->ggtt); + ret = init_ggtt(to_gt(i915)->ggtt); if (ret) return ret; if (INTEL_PPGTT(i915) == INTEL_PPGTT_ALIASING) { - ret = init_aliasing_ppgtt(&i915->ggtt); + ret = init_aliasing_ppgtt(to_gt(i915)->ggtt); if (ret) - cleanup_init_ggtt(&i915->ggtt); + cleanup_init_ggtt(to_gt(i915)->ggtt); } return 0; @@ -772,7 +776,7 @@ static void ggtt_cleanup_hw(struct i915_ggtt *ggtt) */ void i915_ggtt_driver_release(struct drm_i915_private *i915) { - struct i915_ggtt *ggtt = &i915->ggtt; + struct i915_ggtt *ggtt = to_gt(i915)->ggtt; fini_aliasing_ppgtt(ggtt); @@ -787,7 +791,7 @@ void i915_ggtt_driver_release(struct drm_i915_private *i915) */ void i915_ggtt_driver_late_release(struct drm_i915_private *i915) { - struct i915_ggtt *ggtt = &i915->ggtt; + struct i915_ggtt *ggtt = to_gt(i915)->ggtt; GEM_WARN_ON(kref_read(&ggtt->vm.resv_ref) != 1); dma_resv_fini(&ggtt->vm._resv); @@ -1208,7 +1212,7 @@ int i915_ggtt_probe_hw(struct drm_i915_private *i915) { int ret; - ret = ggtt_probe_hw(&i915->ggtt, to_gt(i915)); + ret = ggtt_probe_hw(to_gt(i915)->ggtt, to_gt(i915)); if (ret) return ret; @@ -1280,7 +1284,7 @@ bool i915_ggtt_resume_vm(struct i915_address_space *vm) atomic_read(&vma->flags) & I915_VMA_BIND_MASK; GEM_BUG_ON(!was_bound); - vma->ops->bind_vma(vm, NULL, vma, + vma->ops->bind_vma(vm, NULL, vma->resource, obj ? obj->cache_level : 0, was_bound); if (obj) { /* only used during resume => exclusive access */ diff --git a/drivers/gpu/drm/i915/gt/intel_ggtt_fencing.c b/drivers/gpu/drm/i915/gt/intel_ggtt_fencing.c index f8948de72036..beabf3bc9b75 100644 --- a/drivers/gpu/drm/i915/gt/intel_ggtt_fencing.c +++ b/drivers/gpu/drm/i915/gt/intel_ggtt_fencing.c @@ -728,8 +728,8 @@ static void detect_bit_6_swizzle(struct i915_ggtt *ggtt) swizzle_y = I915_BIT_6_SWIZZLE_NONE; } - i915->ggtt.bit_6_swizzle_x = swizzle_x; - i915->ggtt.bit_6_swizzle_y = swizzle_y; + to_gt(i915)->ggtt->bit_6_swizzle_x = swizzle_x; + to_gt(i915)->ggtt->bit_6_swizzle_y = swizzle_y; } /* @@ -896,7 +896,7 @@ void intel_gt_init_swizzling(struct intel_gt *gt) struct intel_uncore *uncore = gt->uncore; if (GRAPHICS_VER(i915) < 5 || - i915->ggtt.bit_6_swizzle_x == I915_BIT_6_SWIZZLE_NONE) + to_gt(i915)->ggtt->bit_6_swizzle_x == I915_BIT_6_SWIZZLE_NONE) return; intel_uncore_rmw(uncore, DISP_ARB_CTL, 0, DISP_TILE_SURFACE_SWIZZLING); diff --git a/drivers/gpu/drm/i915/gt/intel_gt.c b/drivers/gpu/drm/i915/gt/intel_gt.c index f98f0fb21efb..298ff32c8d0c 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt.c +++ b/drivers/gpu/drm/i915/gt/intel_gt.c @@ -3,6 +3,7 @@ * Copyright © 2019 Intel Corporation */ +#include <drm/drm_managed.h> #include <drm/intel-gtt.h> #include "intel_gt_debugfs.h" @@ -85,9 +86,11 @@ int intel_gt_probe_lmem(struct intel_gt *gt) return 0; } -void intel_gt_init_hw_early(struct intel_gt *gt, struct i915_ggtt *ggtt) +int intel_gt_assign_ggtt(struct intel_gt *gt) { - gt->ggtt = ggtt; + gt->ggtt = drmm_kzalloc(>->i915->drm, sizeof(*gt->ggtt), GFP_KERNEL); + + return gt->ggtt ? 0 : -ENOMEM; } static const struct intel_mmio_range icl_l3bank_steering_table[] = { diff --git a/drivers/gpu/drm/i915/gt/intel_gt.h b/drivers/gpu/drm/i915/gt/intel_gt.h index 3ace129eb2af..94e1bac8c0cc 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt.h +++ b/drivers/gpu/drm/i915/gt/intel_gt.h @@ -36,7 +36,7 @@ static inline struct intel_gt *huc_to_gt(struct intel_huc *huc) void intel_gt_init_early(struct intel_gt *gt, struct drm_i915_private *i915); void __intel_gt_init_early(struct intel_gt *gt, struct drm_i915_private *i915); -void intel_gt_init_hw_early(struct intel_gt *gt, struct i915_ggtt *ggtt); +int intel_gt_assign_ggtt(struct intel_gt *gt); int intel_gt_probe_lmem(struct intel_gt *gt); int intel_gt_init_mmio(struct intel_gt *gt); int __must_check intel_gt_init_hw(struct intel_gt *gt); diff --git a/drivers/gpu/drm/i915/gt/intel_gtt.c b/drivers/gpu/drm/i915/gt/intel_gtt.c index a94be0306464..46be4197b93f 100644 --- a/drivers/gpu/drm/i915/gt/intel_gtt.c +++ b/drivers/gpu/drm/i915/gt/intel_gtt.c @@ -161,6 +161,9 @@ static void __i915_vm_release(struct work_struct *work) struct i915_address_space *vm = container_of(work, struct i915_address_space, release_work); + /* Synchronize async unbinds. */ + i915_vma_resource_bind_dep_sync_all(vm); + vm->cleanup(vm); i915_address_space_fini(vm); @@ -189,6 +192,7 @@ void i915_address_space_init(struct i915_address_space *vm, int subclass) if (!kref_read(&vm->resv_ref)) kref_init(&vm->resv_ref); + vm->pending_unbind = RB_ROOT_CACHED; INIT_WORK(&vm->release_work, __i915_vm_release); atomic_set(&vm->open, 1); diff --git a/drivers/gpu/drm/i915/gt/intel_gtt.h b/drivers/gpu/drm/i915/gt/intel_gtt.h index 177b42b935a1..8073438b67c8 100644 --- a/drivers/gpu/drm/i915/gt/intel_gtt.h +++ b/drivers/gpu/drm/i915/gt/intel_gtt.h @@ -27,6 +27,7 @@ #include "gt/intel_reset.h" #include "i915_selftest.h" +#include "i915_vma_resource.h" #include "i915_vma_types.h" #define I915_GFP_ALLOW_FAIL (GFP_KERNEL | __GFP_RETRY_MAYFAIL | __GFP_NOWARN) @@ -200,7 +201,7 @@ struct i915_vma_ops { /* Map an object into an address space with the given cache flags. */ void (*bind_vma)(struct i915_address_space *vm, struct i915_vm_pt_stash *stash, - struct i915_vma *vma, + struct i915_vma_resource *vma_res, enum i915_cache_level cache_level, u32 flags); /* @@ -208,7 +209,8 @@ struct i915_vma_ops { * setting the valid PTE entries to a reserved scratch page. */ void (*unbind_vma)(struct i915_address_space *vm, - struct i915_vma *vma); + struct i915_vma_resource *vma_res); + }; struct i915_address_space { @@ -263,6 +265,9 @@ struct i915_address_space { /* Flags used when creating page-table objects for this vm */ unsigned long lmem_pt_obj_flags; + /* Interval tree for pending unbind vma resources */ + struct rb_root_cached pending_unbind; + struct drm_i915_gem_object * (*alloc_pt_dma)(struct i915_address_space *vm, int sz); struct drm_i915_gem_object * @@ -285,7 +290,7 @@ struct i915_address_space { enum i915_cache_level cache_level, u32 flags); void (*insert_entries)(struct i915_address_space *vm, - struct i915_vma *vma, + struct i915_vma_resource *vma_res, enum i915_cache_level cache_level, u32 flags); void (*cleanup)(struct i915_address_space *vm); @@ -600,11 +605,11 @@ void gen6_ggtt_invalidate(struct i915_ggtt *ggtt); void ppgtt_bind_vma(struct i915_address_space *vm, struct i915_vm_pt_stash *stash, - struct i915_vma *vma, + struct i915_vma_resource *vma_res, enum i915_cache_level cache_level, u32 flags); void ppgtt_unbind_vma(struct i915_address_space *vm, - struct i915_vma *vma); + struct i915_vma_resource *vma_res); void gtt_write_workarounds(struct intel_gt *gt); @@ -627,8 +632,8 @@ __vm_create_scratch_for_read_pinned(struct i915_address_space *vm, unsigned long static inline struct sgt_dma { struct scatterlist *sg; dma_addr_t dma, max; -} sgt_dma(struct i915_vma *vma) { - struct scatterlist *sg = vma->pages->sgl; +} sgt_dma(struct i915_vma_resource *vma_res) { + struct scatterlist *sg = vma_res->bi.pages->sgl; dma_addr_t addr = sg_dma_address(sg); return (struct sgt_dma){ sg, addr, addr + sg_dma_len(sg) }; diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c index b3489599e4de..84456ffeb4cd 100644 --- a/drivers/gpu/drm/i915/gt/intel_lrc.c +++ b/drivers/gpu/drm/i915/gt/intel_lrc.c @@ -1065,6 +1065,10 @@ lrc_pin(struct intel_context *ce, void lrc_unpin(struct intel_context *ce) { + if (unlikely(ce->parallel.last_rq)) { + i915_request_put(ce->parallel.last_rq); + ce->parallel.last_rq = NULL; + } check_redzone((void *)ce->lrc_reg_state - LRC_STATE_OFFSET, ce->engine); } diff --git a/drivers/gpu/drm/i915/gt/intel_ppgtt.c b/drivers/gpu/drm/i915/gt/intel_ppgtt.c index 083b3090c69c..48e6e2f87700 100644 --- a/drivers/gpu/drm/i915/gt/intel_ppgtt.c +++ b/drivers/gpu/drm/i915/gt/intel_ppgtt.c @@ -179,32 +179,34 @@ struct i915_ppgtt *i915_ppgtt_create(struct intel_gt *gt, void ppgtt_bind_vma(struct i915_address_space *vm, struct i915_vm_pt_stash *stash, - struct i915_vma *vma, + struct i915_vma_resource *vma_res, enum i915_cache_level cache_level, u32 flags) { u32 pte_flags; - if (!test_bit(I915_VMA_ALLOC_BIT, __i915_vma_flags(vma))) { - vm->allocate_va_range(vm, stash, vma->node.start, vma->size); - set_bit(I915_VMA_ALLOC_BIT, __i915_vma_flags(vma)); + if (!vma_res->allocated) { + vm->allocate_va_range(vm, stash, vma_res->start, + vma_res->vma_size); + vma_res->allocated = true; } /* Applicable to VLV, and gen8+ */ pte_flags = 0; - if (i915_gem_object_is_readonly(vma->obj)) + if (vma_res->bi.readonly) pte_flags |= PTE_READ_ONLY; - if (i915_gem_object_is_lmem(vma->obj)) + if (vma_res->bi.lmem) pte_flags |= PTE_LM; - vm->insert_entries(vm, vma, cache_level, pte_flags); + vm->insert_entries(vm, vma_res, cache_level, pte_flags); wmb(); } -void ppgtt_unbind_vma(struct i915_address_space *vm, struct i915_vma *vma) +void ppgtt_unbind_vma(struct i915_address_space *vm, + struct i915_vma_resource *vma_res) { - if (test_and_clear_bit(I915_VMA_ALLOC_BIT, __i915_vma_flags(vma))) - vm->clear_range(vm, vma->node.start, vma->size); + if (vma_res->allocated) + vm->clear_range(vm, vma_res->start, vma_res->vma_size); } static unsigned long pd_count(u64 size, int shift) diff --git a/drivers/gpu/drm/i915/gt/intel_region_lmem.c b/drivers/gpu/drm/i915/gt/intel_region_lmem.c index fde2dcb59809..21215a080088 100644 --- a/drivers/gpu/drm/i915/gt/intel_region_lmem.c +++ b/drivers/gpu/drm/i915/gt/intel_region_lmem.c @@ -15,7 +15,7 @@ static int init_fake_lmem_bar(struct intel_memory_region *mem) { struct drm_i915_private *i915 = mem->i915; - struct i915_ggtt *ggtt = &i915->ggtt; + struct i915_ggtt *ggtt = to_gt(i915)->ggtt; unsigned long n; int ret; @@ -131,7 +131,7 @@ intel_gt_setup_fake_lmem(struct intel_gt *gt) if (!i915->params.fake_lmem_start) return ERR_PTR(-ENODEV); - GEM_BUG_ON(i915_ggtt_has_aperture(&i915->ggtt)); + GEM_BUG_ON(i915_ggtt_has_aperture(to_gt(i915)->ggtt)); /* Your mappable aperture belongs to me now! */ mappable_end = pci_resource_len(pdev, 2); diff --git a/drivers/gpu/drm/i915/gt/selftest_reset.c b/drivers/gpu/drm/i915/gt/selftest_reset.c index 8a873f6bda7f..37c38bdd5f47 100644 --- a/drivers/gpu/drm/i915/gt/selftest_reset.c +++ b/drivers/gpu/drm/i915/gt/selftest_reset.c @@ -19,7 +19,7 @@ __igt_reset_stolen(struct intel_gt *gt, intel_engine_mask_t mask, const char *msg) { - struct i915_ggtt *ggtt = >->i915->ggtt; + struct i915_ggtt *ggtt = gt->ggtt; const struct resource *dsm = >->i915->dsm; resource_size_t num_pages, page; struct intel_engine_cs *engine; diff --git a/drivers/gpu/drm/i915/gt/uc/abi/guc_actions_abi.h b/drivers/gpu/drm/i915/gt/uc/abi/guc_actions_abi.h index fe5d7d261797..7afdadc7656f 100644 --- a/drivers/gpu/drm/i915/gt/uc/abi/guc_actions_abi.h +++ b/drivers/gpu/drm/i915/gt/uc/abi/guc_actions_abi.h @@ -7,9 +7,9 @@ #define _ABI_GUC_ACTIONS_ABI_H /** - * DOC: HOST2GUC_REGISTER_CTB + * DOC: HOST2GUC_SELF_CFG * - * This message is used as part of the `CTB based communication`_ setup. + * This message is used by Host KMD to setup of the `GuC Self Config KLVs`_. * * This message must be sent as `MMIO HXG Message`_. * @@ -22,20 +22,18 @@ * | +-------+--------------------------------------------------------------+ * | | 27:16 | DATA0 = MBZ | * | +-------+--------------------------------------------------------------+ - * | | 15:0 | ACTION = _`GUC_ACTION_HOST2GUC_REGISTER_CTB` = 0x4505 | + * | | 15:0 | ACTION = _`GUC_ACTION_HOST2GUC_SELF_CFG` = 0x0508 | * +---+-------+--------------------------------------------------------------+ - * | 1 | 31:12 | RESERVED = MBZ | + * | 1 | 31:16 | **KLV_KEY** - KLV key, see `GuC Self Config KLVs`_ | * | +-------+--------------------------------------------------------------+ - * | | 11:8 | **TYPE** - type for the `CT Buffer`_ | + * | | 15:0 | **KLV_LEN** - KLV length | * | | | | - * | | | - _`GUC_CTB_TYPE_HOST2GUC` = 0 | - * | | | - _`GUC_CTB_TYPE_GUC2HOST` = 1 | - * | +-------+--------------------------------------------------------------+ - * | | 7:0 | **SIZE** - size of the `CT Buffer`_ in 4K units minus 1 | + * | | | - 32 bit KLV = 1 | + * | | | - 64 bit KLV = 2 | * +---+-------+--------------------------------------------------------------+ - * | 2 | 31:0 | **DESC_ADDR** - GGTT address of the `CTB Descriptor`_ | + * | 2 | 31:0 | **VALUE32** - Bits 31-0 of the KLV value | * +---+-------+--------------------------------------------------------------+ - * | 3 | 31:0 | **BUFF_ADDF** - GGTT address of the `CT Buffer`_ | + * | 3 | 31:0 | **VALUE64** - Bits 63-32 of the KLV value (**KLV_LEN** = 2) | * +---+-------+--------------------------------------------------------------+ * * +---+-------+--------------------------------------------------------------+ @@ -45,28 +43,25 @@ * | +-------+--------------------------------------------------------------+ * | | 30:28 | TYPE = GUC_HXG_TYPE_RESPONSE_SUCCESS_ | * | +-------+--------------------------------------------------------------+ - * | | 27:0 | DATA0 = MBZ | + * | | 27:0 | DATA0 = **NUM** - 1 if KLV was parsed, 0 if not recognized | * +---+-------+--------------------------------------------------------------+ */ -#define GUC_ACTION_HOST2GUC_REGISTER_CTB 0x4505 +#define GUC_ACTION_HOST2GUC_SELF_CFG 0x0508 -#define HOST2GUC_REGISTER_CTB_REQUEST_MSG_LEN (GUC_HXG_REQUEST_MSG_MIN_LEN + 3u) -#define HOST2GUC_REGISTER_CTB_REQUEST_MSG_0_MBZ GUC_HXG_REQUEST_MSG_0_DATA0 -#define HOST2GUC_REGISTER_CTB_REQUEST_MSG_1_MBZ (0xfffff << 12) -#define HOST2GUC_REGISTER_CTB_REQUEST_MSG_1_TYPE (0xf << 8) -#define GUC_CTB_TYPE_HOST2GUC 0u -#define GUC_CTB_TYPE_GUC2HOST 1u -#define HOST2GUC_REGISTER_CTB_REQUEST_MSG_1_SIZE (0xff << 0) -#define HOST2GUC_REGISTER_CTB_REQUEST_MSG_2_DESC_ADDR GUC_HXG_REQUEST_MSG_n_DATAn -#define HOST2GUC_REGISTER_CTB_REQUEST_MSG_3_BUFF_ADDR GUC_HXG_REQUEST_MSG_n_DATAn +#define HOST2GUC_SELF_CFG_REQUEST_MSG_LEN (GUC_HXG_REQUEST_MSG_MIN_LEN + 3u) +#define HOST2GUC_SELF_CFG_REQUEST_MSG_0_MBZ GUC_HXG_REQUEST_MSG_0_DATA0 +#define HOST2GUC_SELF_CFG_REQUEST_MSG_1_KLV_KEY (0xffff << 16) +#define HOST2GUC_SELF_CFG_REQUEST_MSG_1_KLV_LEN (0xffff << 0) +#define HOST2GUC_SELF_CFG_REQUEST_MSG_2_VALUE32 GUC_HXG_REQUEST_MSG_n_DATAn +#define HOST2GUC_SELF_CFG_REQUEST_MSG_3_VALUE64 GUC_HXG_REQUEST_MSG_n_DATAn -#define HOST2GUC_REGISTER_CTB_RESPONSE_MSG_LEN GUC_HXG_RESPONSE_MSG_MIN_LEN -#define HOST2GUC_REGISTER_CTB_RESPONSE_MSG_0_MBZ GUC_HXG_RESPONSE_MSG_0_DATA0 +#define HOST2GUC_SELF_CFG_RESPONSE_MSG_LEN GUC_HXG_RESPONSE_MSG_MIN_LEN +#define HOST2GUC_SELF_CFG_RESPONSE_MSG_0_NUM GUC_HXG_RESPONSE_MSG_0_DATA0 /** - * DOC: HOST2GUC_DEREGISTER_CTB + * DOC: HOST2GUC_CONTROL_CTB * - * This message is used as part of the `CTB based communication`_ teardown. + * This H2G action allows Vf Host to enable or disable H2G and G2H `CT Buffer`_. * * This message must be sent as `MMIO HXG Message`_. * @@ -79,15 +74,12 @@ * | +-------+--------------------------------------------------------------+ * | | 27:16 | DATA0 = MBZ | * | +-------+--------------------------------------------------------------+ - * | | 15:0 | ACTION = _`GUC_ACTION_HOST2GUC_DEREGISTER_CTB` = 0x4506 | + * | | 15:0 | ACTION = _`GUC_ACTION_HOST2GUC_CONTROL_CTB` = 0x4509 | * +---+-------+--------------------------------------------------------------+ - * | 1 | 31:12 | RESERVED = MBZ | - * | +-------+--------------------------------------------------------------+ - * | | 11:8 | **TYPE** - type of the `CT Buffer`_ | + * | 1 | 31:0 | **CONTROL** - control `CTB based communication`_ | * | | | | - * | | | see `GUC_ACTION_HOST2GUC_REGISTER_CTB`_ | - * | +-------+--------------------------------------------------------------+ - * | | 7:0 | RESERVED = MBZ | + * | | | - _`GUC_CTB_CONTROL_DISABLE` = 0 | + * | | | - _`GUC_CTB_CONTROL_ENABLE` = 1 | * +---+-------+--------------------------------------------------------------+ * * +---+-------+--------------------------------------------------------------+ @@ -100,16 +92,16 @@ * | | 27:0 | DATA0 = MBZ | * +---+-------+--------------------------------------------------------------+ */ -#define GUC_ACTION_HOST2GUC_DEREGISTER_CTB 0x4506 +#define GUC_ACTION_HOST2GUC_CONTROL_CTB 0x4509 -#define HOST2GUC_DEREGISTER_CTB_REQUEST_MSG_LEN (GUC_HXG_REQUEST_MSG_MIN_LEN + 1u) -#define HOST2GUC_DEREGISTER_CTB_REQUEST_MSG_0_MBZ GUC_HXG_REQUEST_MSG_0_DATA0 -#define HOST2GUC_DEREGISTER_CTB_REQUEST_MSG_1_MBZ (0xfffff << 12) -#define HOST2GUC_DEREGISTER_CTB_REQUEST_MSG_1_TYPE (0xf << 8) -#define HOST2GUC_DEREGISTER_CTB_REQUEST_MSG_1_MBZ2 (0xff << 0) +#define HOST2GUC_CONTROL_CTB_REQUEST_MSG_LEN (GUC_HXG_REQUEST_MSG_MIN_LEN + 1u) +#define HOST2GUC_CONTROL_CTB_REQUEST_MSG_0_MBZ GUC_HXG_REQUEST_MSG_0_DATA0 +#define HOST2GUC_CONTROL_CTB_REQUEST_MSG_1_CONTROL GUC_HXG_REQUEST_MSG_n_DATAn +#define GUC_CTB_CONTROL_DISABLE 0u +#define GUC_CTB_CONTROL_ENABLE 1u -#define HOST2GUC_DEREGISTER_CTB_RESPONSE_MSG_LEN GUC_HXG_RESPONSE_MSG_MIN_LEN -#define HOST2GUC_DEREGISTER_CTB_RESPONSE_MSG_0_MBZ GUC_HXG_RESPONSE_MSG_0_DATA0 +#define HOST2GUC_CONTROL_CTB_RESPONSE_MSG_LEN GUC_HXG_RESPONSE_MSG_MIN_LEN +#define HOST2GUC_CONTROL_CTB_RESPONSE_MSG_0_MBZ GUC_HXG_RESPONSE_MSG_0_DATA0 /* legacy definitions */ @@ -143,8 +135,12 @@ enum intel_guc_action { INTEL_GUC_ACTION_DEREGISTER_COMMAND_TRANSPORT_BUFFER = 0x4506, INTEL_GUC_ACTION_DEREGISTER_CONTEXT_DONE = 0x4600, INTEL_GUC_ACTION_REGISTER_CONTEXT_MULTI_LRC = 0x4601, - INTEL_GUC_ACTION_RESET_CLIENT = 0x5507, + INTEL_GUC_ACTION_CLIENT_SOFT_RESET = 0x5507, INTEL_GUC_ACTION_SET_ENG_UTIL_BUFF = 0x550A, + INTEL_GUC_ACTION_STATE_CAPTURE_NOTIFICATION = 0x8002, + INTEL_GUC_ACTION_NOTIFY_FLUSH_LOG_BUFFER_TO_FILE = 0x8003, + INTEL_GUC_ACTION_NOTIFY_CRASH_DUMP_POSTED = 0x8004, + INTEL_GUC_ACTION_NOTIFY_EXCEPTION = 0x8005, INTEL_GUC_ACTION_LIMIT }; diff --git a/drivers/gpu/drm/i915/gt/uc/abi/guc_errors_abi.h b/drivers/gpu/drm/i915/gt/uc/abi/guc_errors_abi.h index 488b6061ee89..c20658ee85a5 100644 --- a/drivers/gpu/drm/i915/gt/uc/abi/guc_errors_abi.h +++ b/drivers/gpu/drm/i915/gt/uc/abi/guc_errors_abi.h @@ -11,4 +11,27 @@ enum intel_guc_response_status { INTEL_GUC_RESPONSE_STATUS_GENERIC_FAIL = 0xF000, }; +enum intel_guc_load_status { + INTEL_GUC_LOAD_STATUS_DEFAULT = 0x00, + INTEL_GUC_LOAD_STATUS_START = 0x01, + INTEL_GUC_LOAD_STATUS_ERROR_DEVID_BUILD_MISMATCH = 0x02, + INTEL_GUC_LOAD_STATUS_GUC_PREPROD_BUILD_MISMATCH = 0x03, + INTEL_GUC_LOAD_STATUS_ERROR_DEVID_INVALID_GUCTYPE = 0x04, + INTEL_GUC_LOAD_STATUS_GDT_DONE = 0x10, + INTEL_GUC_LOAD_STATUS_IDT_DONE = 0x20, + INTEL_GUC_LOAD_STATUS_LAPIC_DONE = 0x30, + INTEL_GUC_LOAD_STATUS_GUCINT_DONE = 0x40, + INTEL_GUC_LOAD_STATUS_DPC_READY = 0x50, + INTEL_GUC_LOAD_STATUS_DPC_ERROR = 0x60, + INTEL_GUC_LOAD_STATUS_EXCEPTION = 0x70, + INTEL_GUC_LOAD_STATUS_INIT_DATA_INVALID = 0x71, + INTEL_GUC_LOAD_STATUS_PXP_TEARDOWN_CTRL_ENABLED = 0x72, + INTEL_GUC_LOAD_STATUS_INVALID_INIT_DATA_RANGE_START, + INTEL_GUC_LOAD_STATUS_MPU_DATA_INVALID = 0x73, + INTEL_GUC_LOAD_STATUS_INIT_MMIO_SAVE_RESTORE_INVALID = 0x74, + INTEL_GUC_LOAD_STATUS_INVALID_INIT_DATA_RANGE_END, + + INTEL_GUC_LOAD_STATUS_READY = 0xF0, +}; + #endif /* _ABI_GUC_ERRORS_ABI_H */ diff --git a/drivers/gpu/drm/i915/gt/uc/abi/guc_klvs_abi.h b/drivers/gpu/drm/i915/gt/uc/abi/guc_klvs_abi.h new file mode 100644 index 000000000000..f0814a57c191 --- /dev/null +++ b/drivers/gpu/drm/i915/gt/uc/abi/guc_klvs_abi.h @@ -0,0 +1,82 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright © 2021 Intel Corporation + */ + +#ifndef _ABI_GUC_KLVS_ABI_H +#define _ABI_GUC_KLVS_ABI_H + +/** + * DOC: GuC KLV + * + * +---+-------+--------------------------------------------------------------+ + * | | Bits | Description | + * +===+=======+==============================================================+ + * | 0 | 31:16 | **KEY** - KLV key identifier | + * | | | - `GuC Self Config KLVs`_ | + * | | | | + * | +-------+--------------------------------------------------------------+ + * | | 15:0 | **LEN** - length of VALUE (in 32bit dwords) | + * +---+-------+--------------------------------------------------------------+ + * | 1 | 31:0 | **VALUE** - actual value of the KLV (format depends on KEY) | + * +---+-------+ | + * |...| | | + * +---+-------+ | + * | n | 31:0 | | + * +---+-------+--------------------------------------------------------------+ + */ + +#define GUC_KLV_LEN_MIN 1u +#define GUC_KLV_0_KEY (0xffff << 16) +#define GUC_KLV_0_LEN (0xffff << 0) +#define GUC_KLV_n_VALUE (0xffffffff << 0) + +/** + * DOC: GuC Self Config KLVs + * + * `GuC KLV`_ keys available for use with HOST2GUC_SELF_CFG_. + * + * _`GUC_KLV_SELF_CFG_H2G_CTB_ADDR` : 0x0902 + * Refers to 64 bit Global Gfx address of H2G `CT Buffer`_. + * Should be above WOPCM address but below APIC base address for native mode. + * + * _`GUC_KLV_SELF_CFG_H2G_CTB_DESCRIPTOR_ADDR` : 0x0903 + * Refers to 64 bit Global Gfx address of H2G `CTB Descriptor`_. + * Should be above WOPCM address but below APIC base address for native mode. + * + * _`GUC_KLV_SELF_CFG_H2G_CTB_SIZE` : 0x0904 + * Refers to size of H2G `CT Buffer`_ in bytes. + * Should be a multiple of 4K. + * + * _`GUC_KLV_SELF_CFG_G2H_CTB_ADDR` : 0x0905 + * Refers to 64 bit Global Gfx address of G2H `CT Buffer`_. + * Should be above WOPCM address but below APIC base address for native mode. + * + * _`GUC_KLV_SELF_CFG_G2H_CTB_DESCRIPTOR_ADDR` : 0x0906 + * Refers to 64 bit Global Gfx address of G2H `CTB Descriptor`_. + * Should be above WOPCM address but below APIC base address for native mode. + * + * _`GUC_KLV_SELF_CFG_G2H_CTB_SIZE` : 0x0907 + * Refers to size of G2H `CT Buffer`_ in bytes. + * Should be a multiple of 4K. + */ + +#define GUC_KLV_SELF_CFG_H2G_CTB_ADDR_KEY 0x0902 +#define GUC_KLV_SELF_CFG_H2G_CTB_ADDR_LEN 2u + +#define GUC_KLV_SELF_CFG_H2G_CTB_DESCRIPTOR_ADDR_KEY 0x0903 +#define GUC_KLV_SELF_CFG_H2G_CTB_DESCRIPTOR_ADDR_LEN 2u + +#define GUC_KLV_SELF_CFG_H2G_CTB_SIZE_KEY 0x0904 +#define GUC_KLV_SELF_CFG_H2G_CTB_SIZE_LEN 1u + +#define GUC_KLV_SELF_CFG_G2H_CTB_ADDR_KEY 0x0905 +#define GUC_KLV_SELF_CFG_G2H_CTB_ADDR_LEN 2u + +#define GUC_KLV_SELF_CFG_G2H_CTB_DESCRIPTOR_ADDR_KEY 0x0906 +#define GUC_KLV_SELF_CFG_G2H_CTB_DESCRIPTOR_ADDR_LEN 2u + +#define GUC_KLV_SELF_CFG_G2H_CTB_SIZE_KEY 0x0907 +#define GUC_KLV_SELF_CFG_G2H_CTB_SIZE_LEN 1u + +#endif /* _ABI_GUC_KLVS_ABI_H */ diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc.c b/drivers/gpu/drm/i915/gt/uc/intel_guc.c index 6e228343e8cb..cbec51f4dec3 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc.c @@ -182,6 +182,9 @@ void intel_guc_init_early(struct intel_guc *guc) guc->send_regs.count = GUC_MAX_MMIO_MSG_LEN; BUILD_BUG_ON(GUC_MAX_MMIO_MSG_LEN > SOFT_SCRATCH_COUNT); } + + intel_guc_enable_msg(guc, INTEL_GUC_RECV_MSG_EXCEPTION | + INTEL_GUC_RECV_MSG_CRASH_DUMP_POSTED); } void intel_guc_init_late(struct intel_guc *guc) @@ -222,32 +225,48 @@ static u32 guc_ctl_log_params_flags(struct intel_guc *guc) u32 flags; #if (((CRASH_BUFFER_SIZE) % SZ_1M) == 0) - #define UNIT SZ_1M - #define FLAG GUC_LOG_ALLOC_IN_MEGABYTE + #define LOG_UNIT SZ_1M + #define LOG_FLAG GUC_LOG_LOG_ALLOC_UNITS #else - #define UNIT SZ_4K - #define FLAG 0 + #define LOG_UNIT SZ_4K + #define LOG_FLAG 0 + #endif + + #if (((CAPTURE_BUFFER_SIZE) % SZ_1M) == 0) + #define CAPTURE_UNIT SZ_1M + #define CAPTURE_FLAG GUC_LOG_CAPTURE_ALLOC_UNITS + #else + #define CAPTURE_UNIT SZ_4K + #define CAPTURE_FLAG 0 #endif BUILD_BUG_ON(!CRASH_BUFFER_SIZE); - BUILD_BUG_ON(!IS_ALIGNED(CRASH_BUFFER_SIZE, UNIT)); + BUILD_BUG_ON(!IS_ALIGNED(CRASH_BUFFER_SIZE, LOG_UNIT)); BUILD_BUG_ON(!DEBUG_BUFFER_SIZE); - BUILD_BUG_ON(!IS_ALIGNED(DEBUG_BUFFER_SIZE, UNIT)); + BUILD_BUG_ON(!IS_ALIGNED(DEBUG_BUFFER_SIZE, LOG_UNIT)); + BUILD_BUG_ON(!CAPTURE_BUFFER_SIZE); + BUILD_BUG_ON(!IS_ALIGNED(CAPTURE_BUFFER_SIZE, CAPTURE_UNIT)); - BUILD_BUG_ON((CRASH_BUFFER_SIZE / UNIT - 1) > + BUILD_BUG_ON((CRASH_BUFFER_SIZE / LOG_UNIT - 1) > (GUC_LOG_CRASH_MASK >> GUC_LOG_CRASH_SHIFT)); - BUILD_BUG_ON((DEBUG_BUFFER_SIZE / UNIT - 1) > + BUILD_BUG_ON((DEBUG_BUFFER_SIZE / LOG_UNIT - 1) > (GUC_LOG_DEBUG_MASK >> GUC_LOG_DEBUG_SHIFT)); + BUILD_BUG_ON((CAPTURE_BUFFER_SIZE / CAPTURE_UNIT - 1) > + (GUC_LOG_CAPTURE_MASK >> GUC_LOG_CAPTURE_SHIFT)); flags = GUC_LOG_VALID | GUC_LOG_NOTIFY_ON_HALF_FULL | - FLAG | - ((CRASH_BUFFER_SIZE / UNIT - 1) << GUC_LOG_CRASH_SHIFT) | - ((DEBUG_BUFFER_SIZE / UNIT - 1) << GUC_LOG_DEBUG_SHIFT) | + CAPTURE_FLAG | + LOG_FLAG | + ((CRASH_BUFFER_SIZE / LOG_UNIT - 1) << GUC_LOG_CRASH_SHIFT) | + ((DEBUG_BUFFER_SIZE / LOG_UNIT - 1) << GUC_LOG_DEBUG_SHIFT) | + ((CAPTURE_BUFFER_SIZE / CAPTURE_UNIT - 1) << GUC_LOG_CAPTURE_SHIFT) | (offset << GUC_LOG_BUF_ADDR_SHIFT); - #undef UNIT - #undef FLAG + #undef LOG_UNIT + #undef LOG_FLAG + #undef CAPTURE_UNIT + #undef CAPTURE_FLAG return flags; } @@ -260,6 +279,26 @@ static u32 guc_ctl_ads_flags(struct intel_guc *guc) return flags; } +static u32 guc_ctl_wa_flags(struct intel_guc *guc) +{ + struct intel_gt *gt = guc_to_gt(guc); + u32 flags = 0; + + /* Wa_22012773006:gen11,gen12 < XeHP */ + if (GRAPHICS_VER(gt->i915) >= 11 && + GRAPHICS_VER_FULL(gt->i915) < IP_VER(12, 50)) + flags |= GUC_WA_POLLCS; + + return flags; +} + +static u32 guc_ctl_devid(struct intel_guc *guc) +{ + struct drm_i915_private *i915 = guc_to_gt(guc)->i915; + + return (INTEL_DEVID(i915) << 16) | INTEL_REVID(i915); +} + /* * Initialise the GuC parameter block before starting the firmware * transfer. These parameters are read by the firmware on startup @@ -276,6 +315,8 @@ static void guc_init_params(struct intel_guc *guc) params[GUC_CTL_FEATURE] = guc_ctl_feature_flags(guc); params[GUC_CTL_DEBUG] = guc_ctl_debug_flags(guc); params[GUC_CTL_ADS] = guc_ctl_ads_flags(guc); + params[GUC_CTL_WA] = guc_ctl_wa_flags(guc); + params[GUC_CTL_DEVID] = guc_ctl_devid(guc); for (i = 0; i < GUC_CTL_MAX_DWORDS; i++) DRM_DEBUG_DRIVER("param[%2d] = %#x\n", i, params[i]); @@ -513,9 +554,10 @@ int intel_guc_to_host_process_recv_msg(struct intel_guc *guc, /* Make sure to handle only enabled messages */ msg = payload[0] & guc->msg_enabled_mask; - if (msg & (INTEL_GUC_RECV_MSG_FLUSH_LOG_BUFFER | - INTEL_GUC_RECV_MSG_CRASH_DUMP_POSTED)) - intel_guc_log_handle_flush_event(&guc->log); + if (msg & INTEL_GUC_RECV_MSG_CRASH_DUMP_POSTED) + drm_err(&guc_to_gt(guc)->i915->drm, "Received early GuC crash dump notification!\n"); + if (msg & INTEL_GUC_RECV_MSG_EXCEPTION) + drm_err(&guc_to_gt(guc)->i915->drm, "Received early GuC exception notification!\n"); return 0; } @@ -549,7 +591,7 @@ int intel_guc_suspend(struct intel_guc *guc) { int ret; u32 action[] = { - INTEL_GUC_ACTION_RESET_CLIENT, + INTEL_GUC_ACTION_CLIENT_SOFT_RESET, }; if (!intel_guc_is_ready(guc)) @@ -713,6 +755,56 @@ int intel_guc_allocate_and_map_vma(struct intel_guc *guc, u32 size, return 0; } +static int __guc_action_self_cfg(struct intel_guc *guc, u16 key, u16 len, u64 value) +{ + u32 request[HOST2GUC_SELF_CFG_REQUEST_MSG_LEN] = { + FIELD_PREP(GUC_HXG_MSG_0_ORIGIN, GUC_HXG_ORIGIN_HOST) | + FIELD_PREP(GUC_HXG_MSG_0_TYPE, GUC_HXG_TYPE_REQUEST) | + FIELD_PREP(GUC_HXG_REQUEST_MSG_0_ACTION, GUC_ACTION_HOST2GUC_SELF_CFG), + FIELD_PREP(HOST2GUC_SELF_CFG_REQUEST_MSG_1_KLV_KEY, key) | + FIELD_PREP(HOST2GUC_SELF_CFG_REQUEST_MSG_1_KLV_LEN, len), + FIELD_PREP(HOST2GUC_SELF_CFG_REQUEST_MSG_2_VALUE32, lower_32_bits(value)), + FIELD_PREP(HOST2GUC_SELF_CFG_REQUEST_MSG_3_VALUE64, upper_32_bits(value)), + }; + int ret; + + GEM_BUG_ON(len > 2); + GEM_BUG_ON(len == 1 && upper_32_bits(value)); + + /* Self config must go over MMIO */ + ret = intel_guc_send_mmio(guc, request, ARRAY_SIZE(request), NULL, 0); + + if (unlikely(ret < 0)) + return ret; + if (unlikely(ret > 1)) + return -EPROTO; + if (unlikely(!ret)) + return -ENOKEY; + + return 0; +} + +static int __guc_self_cfg(struct intel_guc *guc, u16 key, u16 len, u64 value) +{ + struct drm_i915_private *i915 = guc_to_gt(guc)->i915; + int err = __guc_action_self_cfg(guc, key, len, value); + + if (unlikely(err)) + i915_probe_error(i915, "Unsuccessful self-config (%pe) key %#hx value %#llx\n", + ERR_PTR(err), key, value); + return err; +} + +int intel_guc_self_cfg32(struct intel_guc *guc, u16 key, u32 value) +{ + return __guc_self_cfg(guc, key, 1, value); +} + +int intel_guc_self_cfg64(struct intel_guc *guc, u16 key, u64 value) +{ + return __guc_self_cfg(guc, key, 2, value); +} + /** * intel_guc_load_status - dump information about GuC load status * @guc: the GuC diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc.h b/drivers/gpu/drm/i915/gt/uc/intel_guc.h index f9240d4baa69..9d26a86fe557 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc.h +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc.h @@ -328,6 +328,8 @@ int intel_guc_resume(struct intel_guc *guc); struct i915_vma *intel_guc_allocate_vma(struct intel_guc *guc, u32 size); int intel_guc_allocate_and_map_vma(struct intel_guc *guc, u32 size, struct i915_vma **out_vma, void **out_vaddr); +int intel_guc_self_cfg32(struct intel_guc *guc, u16 key, u32 value); +int intel_guc_self_cfg64(struct intel_guc *guc, u16 key, u64 value); static inline bool intel_guc_is_supported(struct intel_guc *guc) { @@ -404,6 +406,8 @@ int intel_guc_context_reset_process_msg(struct intel_guc *guc, const u32 *msg, u32 len); int intel_guc_engine_failure_process_msg(struct intel_guc *guc, const u32 *msg, u32 len); +int intel_guc_error_capture_process_msg(struct intel_guc *guc, + const u32 *msg, u32 len); void intel_guc_find_hung_context(struct intel_engine_cs *engine); diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_ads.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_ads.c index 1a1edae67e4e..aa767540ca2a 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_ads.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_ads.c @@ -40,6 +40,10 @@ * +---------------------------------------+ * | padding | * +---------------------------------------+ <== 4K aligned + * | capture lists | + * +---------------------------------------+ + * | padding | + * +---------------------------------------+ <== 4K aligned * | private data | * +---------------------------------------+ * | padding | @@ -65,6 +69,12 @@ static u32 guc_ads_golden_ctxt_size(struct intel_guc *guc) return PAGE_ALIGN(guc->ads_golden_ctxt_size); } +static u32 guc_ads_capture_size(struct intel_guc *guc) +{ + /* FIXME: Allocate a proper capture list */ + return PAGE_ALIGN(PAGE_SIZE); +} + static u32 guc_ads_private_data_size(struct intel_guc *guc) { return PAGE_ALIGN(guc->fw.private_data_size); @@ -85,7 +95,7 @@ static u32 guc_ads_golden_ctxt_offset(struct intel_guc *guc) return PAGE_ALIGN(offset); } -static u32 guc_ads_private_data_offset(struct intel_guc *guc) +static u32 guc_ads_capture_offset(struct intel_guc *guc) { u32 offset; @@ -95,6 +105,16 @@ static u32 guc_ads_private_data_offset(struct intel_guc *guc) return PAGE_ALIGN(offset); } +static u32 guc_ads_private_data_offset(struct intel_guc *guc) +{ + u32 offset; + + offset = guc_ads_capture_offset(guc) + + guc_ads_capture_size(guc); + + return PAGE_ALIGN(offset); +} + static u32 guc_ads_blob_size(struct intel_guc *guc) { return guc_ads_private_data_offset(guc) + @@ -499,6 +519,26 @@ static void guc_init_golden_context(struct intel_guc *guc) GEM_BUG_ON(guc->ads_golden_ctxt_size != total_size); } +static void guc_capture_list_init(struct intel_guc *guc, struct __guc_ads_blob *blob) +{ + int i, j; + u32 addr_ggtt, offset; + + offset = guc_ads_capture_offset(guc); + addr_ggtt = intel_guc_ggtt_offset(guc, guc->ads_vma) + offset; + + /* FIXME: Populate a proper capture list */ + + for (i = 0; i < GUC_CAPTURE_LIST_INDEX_MAX; i++) { + for (j = 0; j < GUC_MAX_ENGINE_CLASSES; j++) { + blob->ads.capture_instance[i][j] = addr_ggtt; + blob->ads.capture_class[i][j] = addr_ggtt; + } + + blob->ads.capture_global[i] = addr_ggtt; + } +} + static void __guc_ads_init(struct intel_guc *guc) { struct intel_gt *gt = guc_to_gt(guc); @@ -532,6 +572,9 @@ static void __guc_ads_init(struct intel_guc *guc) base = intel_guc_ggtt_offset(guc, guc->ads_vma); + /* Capture list for hang debug */ + guc_capture_list_init(guc, blob); + /* ADS */ blob->ads.scheduler_policies = base + ptr_offset(blob, policies); blob->ads.gt_system_info = base + ptr_offset(blob, system_info); diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c index aa6dd6415202..de89d40abd38 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c @@ -112,18 +112,6 @@ void intel_guc_ct_init_early(struct intel_guc_ct *ct) init_waitqueue_head(&ct->wq); } -static inline const char *guc_ct_buffer_type_to_str(u32 type) -{ - switch (type) { - case GUC_CTB_TYPE_HOST2GUC: - return "SEND"; - case GUC_CTB_TYPE_GUC2HOST: - return "RECV"; - default: - return "<invalid>"; - } -} - static void guc_ct_buffer_desc_init(struct guc_ct_buffer_desc *desc) { memset(desc, 0, sizeof(*desc)); @@ -156,71 +144,65 @@ static void guc_ct_buffer_init(struct intel_guc_ct_buffer *ctb, guc_ct_buffer_reset(ctb); } -static int guc_action_register_ct_buffer(struct intel_guc *guc, u32 type, - u32 desc_addr, u32 buff_addr, u32 size) +static int guc_action_control_ctb(struct intel_guc *guc, u32 control) { - u32 request[HOST2GUC_REGISTER_CTB_REQUEST_MSG_LEN] = { + u32 request[HOST2GUC_CONTROL_CTB_REQUEST_MSG_LEN] = { FIELD_PREP(GUC_HXG_MSG_0_ORIGIN, GUC_HXG_ORIGIN_HOST) | FIELD_PREP(GUC_HXG_MSG_0_TYPE, GUC_HXG_TYPE_REQUEST) | - FIELD_PREP(GUC_HXG_REQUEST_MSG_0_ACTION, GUC_ACTION_HOST2GUC_REGISTER_CTB), - FIELD_PREP(HOST2GUC_REGISTER_CTB_REQUEST_MSG_1_SIZE, size / SZ_4K - 1) | - FIELD_PREP(HOST2GUC_REGISTER_CTB_REQUEST_MSG_1_TYPE, type), - FIELD_PREP(HOST2GUC_REGISTER_CTB_REQUEST_MSG_2_DESC_ADDR, desc_addr), - FIELD_PREP(HOST2GUC_REGISTER_CTB_REQUEST_MSG_3_BUFF_ADDR, buff_addr), + FIELD_PREP(GUC_HXG_REQUEST_MSG_0_ACTION, GUC_ACTION_HOST2GUC_CONTROL_CTB), + FIELD_PREP(HOST2GUC_CONTROL_CTB_REQUEST_MSG_1_CONTROL, control), }; int ret; - GEM_BUG_ON(type != GUC_CTB_TYPE_HOST2GUC && type != GUC_CTB_TYPE_GUC2HOST); - GEM_BUG_ON(size % SZ_4K); + GEM_BUG_ON(control != GUC_CTB_CONTROL_DISABLE && control != GUC_CTB_CONTROL_ENABLE); - /* CT registration must go over MMIO */ + /* CT control must go over MMIO */ ret = intel_guc_send_mmio(guc, request, ARRAY_SIZE(request), NULL, 0); return ret > 0 ? -EPROTO : ret; } -static int ct_register_buffer(struct intel_guc_ct *ct, u32 type, - u32 desc_addr, u32 buff_addr, u32 size) +static int ct_control_enable(struct intel_guc_ct *ct, bool enable) { int err; - err = i915_inject_probe_error(guc_to_gt(ct_to_guc(ct))->i915, -ENXIO); + err = guc_action_control_ctb(ct_to_guc(ct), enable ? + GUC_CTB_CONTROL_ENABLE : GUC_CTB_CONTROL_DISABLE); if (unlikely(err)) - return err; + CT_PROBE_ERROR(ct, "Failed to control/%s CTB (%pe)\n", + enabledisable(enable), ERR_PTR(err)); - err = guc_action_register_ct_buffer(ct_to_guc(ct), type, - desc_addr, buff_addr, size); - if (unlikely(err)) - CT_ERROR(ct, "Failed to register %s buffer (%pe)\n", - guc_ct_buffer_type_to_str(type), ERR_PTR(err)); return err; } -static int guc_action_deregister_ct_buffer(struct intel_guc *guc, u32 type) +static int ct_register_buffer(struct intel_guc_ct *ct, bool send, + u32 desc_addr, u32 buff_addr, u32 size) { - u32 request[HOST2GUC_DEREGISTER_CTB_REQUEST_MSG_LEN] = { - FIELD_PREP(GUC_HXG_MSG_0_ORIGIN, GUC_HXG_ORIGIN_HOST) | - FIELD_PREP(GUC_HXG_MSG_0_TYPE, GUC_HXG_TYPE_REQUEST) | - FIELD_PREP(GUC_HXG_REQUEST_MSG_0_ACTION, GUC_ACTION_HOST2GUC_DEREGISTER_CTB), - FIELD_PREP(HOST2GUC_DEREGISTER_CTB_REQUEST_MSG_1_TYPE, type), - }; - int ret; - - GEM_BUG_ON(type != GUC_CTB_TYPE_HOST2GUC && type != GUC_CTB_TYPE_GUC2HOST); - - /* CT deregistration must go over MMIO */ - ret = intel_guc_send_mmio(guc, request, ARRAY_SIZE(request), NULL, 0); + int err; - return ret > 0 ? -EPROTO : ret; -} + err = intel_guc_self_cfg64(ct_to_guc(ct), send ? + GUC_KLV_SELF_CFG_H2G_CTB_DESCRIPTOR_ADDR_KEY : + GUC_KLV_SELF_CFG_G2H_CTB_DESCRIPTOR_ADDR_KEY, + desc_addr); + if (unlikely(err)) + goto failed; -static int ct_deregister_buffer(struct intel_guc_ct *ct, u32 type) -{ - int err = guc_action_deregister_ct_buffer(ct_to_guc(ct), type); + err = intel_guc_self_cfg64(ct_to_guc(ct), send ? + GUC_KLV_SELF_CFG_H2G_CTB_ADDR_KEY : + GUC_KLV_SELF_CFG_G2H_CTB_ADDR_KEY, + buff_addr); + if (unlikely(err)) + goto failed; + err = intel_guc_self_cfg32(ct_to_guc(ct), send ? + GUC_KLV_SELF_CFG_H2G_CTB_SIZE_KEY : + GUC_KLV_SELF_CFG_G2H_CTB_SIZE_KEY, + size); if (unlikely(err)) - CT_ERROR(ct, "Failed to deregister %s buffer (%pe)\n", - guc_ct_buffer_type_to_str(type), ERR_PTR(err)); +failed: + CT_PROBE_ERROR(ct, "Failed to register %s buffer (%pe)\n", + send ? "SEND" : "RECV", ERR_PTR(err)); + return err; } @@ -308,7 +290,7 @@ void intel_guc_ct_fini(struct intel_guc_ct *ct) int intel_guc_ct_enable(struct intel_guc_ct *ct) { struct intel_guc *guc = ct_to_guc(ct); - u32 base, desc, cmds; + u32 base, desc, cmds, size; void *blob; int err; @@ -333,27 +315,27 @@ int intel_guc_ct_enable(struct intel_guc_ct *ct) */ desc = base + ptrdiff(ct->ctbs.recv.desc, blob); cmds = base + ptrdiff(ct->ctbs.recv.cmds, blob); - err = ct_register_buffer(ct, GUC_CTB_TYPE_GUC2HOST, - desc, cmds, ct->ctbs.recv.size * 4); - + size = ct->ctbs.recv.size * 4; + err = ct_register_buffer(ct, false, desc, cmds, size); if (unlikely(err)) goto err_out; desc = base + ptrdiff(ct->ctbs.send.desc, blob); cmds = base + ptrdiff(ct->ctbs.send.cmds, blob); - err = ct_register_buffer(ct, GUC_CTB_TYPE_HOST2GUC, - desc, cmds, ct->ctbs.send.size * 4); + size = ct->ctbs.send.size * 4; + err = ct_register_buffer(ct, true, desc, cmds, size); + if (unlikely(err)) + goto err_out; + err = ct_control_enable(ct, true); if (unlikely(err)) - goto err_deregister; + goto err_out; ct->enabled = true; ct->stall_time = KTIME_MAX; return 0; -err_deregister: - ct_deregister_buffer(ct, GUC_CTB_TYPE_GUC2HOST); err_out: CT_PROBE_ERROR(ct, "Failed to enable CTB (%pe)\n", ERR_PTR(err)); return err; @@ -372,8 +354,7 @@ void intel_guc_ct_disable(struct intel_guc_ct *ct) ct->enabled = false; if (intel_guc_is_fw_running(guc)) { - ct_deregister_buffer(ct, GUC_CTB_TYPE_HOST2GUC); - ct_deregister_buffer(ct, GUC_CTB_TYPE_GUC2HOST); + ct_control_enable(ct, false); } } @@ -662,6 +643,7 @@ static int ct_send(struct intel_guc_ct *ct, struct ct_request request; unsigned long flags; unsigned int sleep_period_ms = 1; + bool send_again; u32 fence; int err; @@ -671,6 +653,9 @@ static int ct_send(struct intel_guc_ct *ct, GEM_BUG_ON(!response_buf && response_buf_size); might_sleep(); +resend: + send_again = false; + /* * We use a lazy spin wait loop here as we believe that if the CT * buffers are sized correctly the flow control condition should be @@ -725,6 +710,13 @@ retry: goto unlink; } + if (FIELD_GET(GUC_HXG_MSG_0_TYPE, *status) == GUC_HXG_TYPE_NO_RESPONSE_RETRY) { + CT_DEBUG(ct, "retrying request %#x (%u)\n", *action, + FIELD_GET(GUC_HXG_RETRY_MSG_0_REASON, *status)); + send_again = true; + goto unlink; + } + if (FIELD_GET(GUC_HXG_MSG_0_TYPE, *status) != GUC_HXG_TYPE_RESPONSE_SUCCESS) { err = -EIO; goto unlink; @@ -747,6 +739,9 @@ unlink: list_del(&request.link); spin_unlock_irqrestore(&ct->requests.lock, flags); + if (unlikely(send_again)) + goto resend; + return err; } @@ -918,6 +913,7 @@ static int ct_handle_response(struct intel_guc_ct *ct, struct ct_incoming_msg *r GEM_BUG_ON(len < GUC_HXG_MSG_MIN_LEN); GEM_BUG_ON(FIELD_GET(GUC_HXG_MSG_0_ORIGIN, hxg[0]) != GUC_HXG_ORIGIN_GUC); GEM_BUG_ON(FIELD_GET(GUC_HXG_MSG_0_TYPE, hxg[0]) != GUC_HXG_TYPE_RESPONSE_SUCCESS && + FIELD_GET(GUC_HXG_MSG_0_TYPE, hxg[0]) != GUC_HXG_TYPE_NO_RESPONSE_RETRY && FIELD_GET(GUC_HXG_MSG_0_TYPE, hxg[0]) != GUC_HXG_TYPE_RESPONSE_FAILURE); CT_DEBUG(ct, "response fence %u status %#x\n", fence, hxg[0]); @@ -990,9 +986,27 @@ static int ct_process_request(struct intel_guc_ct *ct, struct ct_incoming_msg *r case INTEL_GUC_ACTION_CONTEXT_RESET_NOTIFICATION: ret = intel_guc_context_reset_process_msg(guc, payload, len); break; + case INTEL_GUC_ACTION_STATE_CAPTURE_NOTIFICATION: + ret = intel_guc_error_capture_process_msg(guc, payload, len); + if (unlikely(ret)) + CT_ERROR(ct, "error capture notification failed %x %*ph\n", + action, 4 * len, payload); + break; case INTEL_GUC_ACTION_ENGINE_FAILURE_NOTIFICATION: ret = intel_guc_engine_failure_process_msg(guc, payload, len); break; + case INTEL_GUC_ACTION_NOTIFY_FLUSH_LOG_BUFFER_TO_FILE: + intel_guc_log_handle_flush_event(&guc->log); + ret = 0; + break; + case INTEL_GUC_ACTION_NOTIFY_CRASH_DUMP_POSTED: + CT_ERROR(ct, "Received GuC crash dump notification!\n"); + ret = 0; + break; + case INTEL_GUC_ACTION_NOTIFY_EXCEPTION: + CT_ERROR(ct, "Received GuC exception notification!\n"); + ret = 0; + break; default: ret = -EOPNOTSUPP; break; @@ -1098,6 +1112,7 @@ static int ct_handle_hxg(struct intel_guc_ct *ct, struct ct_incoming_msg *msg) break; case GUC_HXG_TYPE_RESPONSE_SUCCESS: case GUC_HXG_TYPE_RESPONSE_FAILURE: + case GUC_HXG_TYPE_NO_RESPONSE_RETRY: err = ct_handle_response(ct, msg); break; default: diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_fw.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_fw.c index 31420ce1ce6b..f773e7f35bc1 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_fw.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_fw.c @@ -90,11 +90,10 @@ static int guc_xfer_rsa(struct intel_uc_fw *guc_fw, static inline bool guc_ready(struct intel_uncore *uncore, u32 *status) { u32 val = intel_uncore_read(uncore, GUC_STATUS); - u32 uk_val = val & GS_UKERNEL_MASK; + u32 uk_val = REG_FIELD_GET(GS_UKERNEL_MASK, val); *status = val; - return (uk_val == GS_UKERNEL_READY) || - ((val & GS_MIA_CORE_STATE) && (uk_val == GS_UKERNEL_LAPIC_DONE)); + return uk_val == INTEL_GUC_LOAD_STATUS_READY; } static int guc_wait_ucode(struct intel_uncore *uncore) @@ -105,17 +104,26 @@ static int guc_wait_ucode(struct intel_uncore *uncore) /* * Wait for the GuC to start up. * NB: Docs recommend not using the interrupt for completion. - * Measurements indicate this should take no more than 20ms, so a + * Measurements indicate this should take no more than 20ms + * (assuming the GT clock is at maximum frequency). So, a * timeout here indicates that the GuC has failed and is unusable. * (Higher levels of the driver may decide to reset the GuC and * attempt the ucode load again if this happens.) + * + * FIXME: There is a known (but exceedingly unlikely) race condition + * where the asynchronous frequency management code could reduce + * the GT clock while a GuC reload is in progress (during a full + * GT reset). A fix is in progress but there are complex locking + * issues to be resolved. In the meantime bump the timeout to + * 200ms. Even at slowest clock, this should be sufficient. And + * in the working case, a larger timeout makes no difference. */ - ret = wait_for(guc_ready(uncore, &status), 100); + ret = wait_for(guc_ready(uncore, &status), 200); if (ret) { struct drm_device *drm = &uncore->i915->drm; - drm_dbg(drm, "GuC load failed: status = 0x%08X\n", status); - drm_dbg(drm, "GuC load failed: status: Reset = %d, " + drm_info(drm, "GuC load failed: status = 0x%08X\n", status); + drm_info(drm, "GuC load failed: status: Reset = %d, " "BootROM = 0x%02X, UKernel = 0x%02X, " "MIA = 0x%02X, Auth = 0x%02X\n", REG_FIELD_GET(GS_MIA_IN_RESET, status), @@ -125,13 +133,13 @@ static int guc_wait_ucode(struct intel_uncore *uncore) REG_FIELD_GET(GS_AUTH_STATUS_MASK, status)); if ((status & GS_BOOTROM_MASK) == GS_BOOTROM_RSA_FAILED) { - drm_dbg(drm, "GuC firmware signature verification failed\n"); + drm_info(drm, "GuC firmware signature verification failed\n"); ret = -ENOEXEC; } - if ((status & GS_UKERNEL_MASK) == GS_UKERNEL_EXCEPTION) { - drm_dbg(drm, "GuC firmware exception. EIP: %#x\n", - intel_uncore_read(uncore, SOFT_SCRATCH(13))); + if (REG_FIELD_GET(GS_UKERNEL_MASK, status) == INTEL_GUC_LOAD_STATUS_EXCEPTION) { + drm_info(drm, "GuC firmware exception. EIP: %#x\n", + intel_uncore_read(uncore, SOFT_SCRATCH(13))); ret = -ENXIO; } } diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_fwif.h b/drivers/gpu/drm/i915/gt/uc/intel_guc_fwif.h index 7072e30e99f4..6a4612a852e2 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_fwif.h +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_fwif.h @@ -16,6 +16,7 @@ #include "abi/guc_errors_abi.h" #include "abi/guc_communication_mmio_abi.h" #include "abi/guc_communication_ctb_abi.h" +#include "abi/guc_klvs_abi.h" #include "abi/guc_messages_abi.h" /* Payload length only i.e. don't include G2H header length */ @@ -84,19 +85,24 @@ #define GUC_STAGE_DESC_ATTR_TERMINATED BIT(7) #define GUC_CTL_LOG_PARAMS 0 -#define GUC_LOG_VALID (1 << 0) -#define GUC_LOG_NOTIFY_ON_HALF_FULL (1 << 1) -#define GUC_LOG_ALLOC_IN_MEGABYTE (1 << 3) +#define GUC_LOG_VALID BIT(0) +#define GUC_LOG_NOTIFY_ON_HALF_FULL BIT(1) +#define GUC_LOG_CAPTURE_ALLOC_UNITS BIT(2) +#define GUC_LOG_LOG_ALLOC_UNITS BIT(3) #define GUC_LOG_CRASH_SHIFT 4 #define GUC_LOG_CRASH_MASK (0x3 << GUC_LOG_CRASH_SHIFT) #define GUC_LOG_DEBUG_SHIFT 6 #define GUC_LOG_DEBUG_MASK (0xF << GUC_LOG_DEBUG_SHIFT) +#define GUC_LOG_CAPTURE_SHIFT 10 +#define GUC_LOG_CAPTURE_MASK (0x3 << GUC_LOG_CAPTURE_SHIFT) #define GUC_LOG_BUF_ADDR_SHIFT 12 #define GUC_CTL_WA 1 +#define GUC_WA_POLLCS BIT(18) + #define GUC_CTL_FEATURE 2 -#define GUC_CTL_DISABLE_SCHEDULER (1 << 14) #define GUC_CTL_ENABLE_SLPC BIT(2) +#define GUC_CTL_DISABLE_SCHEDULER BIT(14) #define GUC_CTL_DEBUG 3 #define GUC_LOG_VERBOSITY_SHIFT 0 @@ -116,6 +122,8 @@ #define GUC_ADS_ADDR_SHIFT 1 #define GUC_ADS_ADDR_MASK (0xFFFFF << GUC_ADS_ADDR_SHIFT) +#define GUC_CTL_DEVID 5 + #define GUC_CTL_MAX_DWORDS (SOFT_SCRATCH_COUNT - 2) /* [1..14] */ /* Generic GT SysInfo data types */ @@ -263,7 +271,10 @@ struct guc_mmio_reg { u32 offset; u32 value; u32 flags; -#define GUC_REGSET_MASKED (1 << 0) + u32 mask; +#define GUC_REGSET_MASKED BIT(0) +#define GUC_REGSET_MASKED_WITH_VALUE BIT(2) +#define GUC_REGSET_RESTORE_ONLY BIT(3) } __packed; /* GuC register sets */ @@ -280,6 +291,12 @@ struct guc_gt_system_info { u32 generic_gt_sysinfo[GUC_GENERIC_GT_SYSINFO_MAX]; } __packed; +enum { + GUC_CAPTURE_LIST_INDEX_PF = 0, + GUC_CAPTURE_LIST_INDEX_VF = 1, + GUC_CAPTURE_LIST_INDEX_MAX = 2, +}; + /* GuC Additional Data Struct */ struct guc_ads { struct guc_mmio_reg_set reg_state_list[GUC_MAX_ENGINE_CLASSES][GUC_MAX_INSTANCES_PER_CLASS]; @@ -291,7 +308,11 @@ struct guc_ads { u32 golden_context_lrca[GUC_MAX_ENGINE_CLASSES]; u32 eng_state_size[GUC_MAX_ENGINE_CLASSES]; u32 private_data; - u32 reserved[15]; + u32 reserved2; + u32 capture_instance[GUC_CAPTURE_LIST_INDEX_MAX][GUC_MAX_ENGINE_CLASSES]; + u32 capture_class[GUC_CAPTURE_LIST_INDEX_MAX][GUC_MAX_ENGINE_CLASSES]; + u32 capture_global[GUC_CAPTURE_LIST_INDEX_MAX]; + u32 reserved[14]; } __packed; /* Engine usage stats */ @@ -312,6 +333,7 @@ struct guc_engine_usage { enum guc_log_buffer_type { GUC_DEBUG_LOG_BUFFER, GUC_CRASH_DUMP_LOG_BUFFER, + GUC_CAPTURE_LOG_BUFFER, GUC_MAX_LOG_BUFFER }; @@ -342,6 +364,7 @@ struct guc_log_buffer_state { u32 write_ptr; u32 size; u32 sampled_write_ptr; + u32 wrap_offset; union { struct { u32 flush_to_file:1; @@ -382,7 +405,7 @@ struct guc_shared_ctx_data { /* This action will be programmed in C1BC - SOFT_SCRATCH_15_REG */ enum intel_guc_recv_message { INTEL_GUC_RECV_MSG_CRASH_DUMP_POSTED = BIT(1), - INTEL_GUC_RECV_MSG_FLUSH_LOG_BUFFER = BIT(3) + INTEL_GUC_RECV_MSG_EXCEPTION = BIT(30), }; #endif diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_log.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_log.c index ac0931f0374b..be35f0570396 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_log.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_log.c @@ -55,20 +55,6 @@ static int guc_action_control_log(struct intel_guc *guc, bool enable, return intel_guc_send(guc, action, ARRAY_SIZE(action)); } -static void guc_log_enable_flush_events(struct intel_guc_log *log) -{ - intel_guc_enable_msg(log_to_guc(log), - INTEL_GUC_RECV_MSG_FLUSH_LOG_BUFFER | - INTEL_GUC_RECV_MSG_CRASH_DUMP_POSTED); -} - -static void guc_log_disable_flush_events(struct intel_guc_log *log) -{ - intel_guc_disable_msg(log_to_guc(log), - INTEL_GUC_RECV_MSG_FLUSH_LOG_BUFFER | - INTEL_GUC_RECV_MSG_CRASH_DUMP_POSTED); -} - /* * Sub buffer switch callback. Called whenever relay has to switch to a new * sub buffer, relay stays on the same sub buffer if 0 is returned. @@ -201,6 +187,8 @@ static unsigned int guc_get_log_buffer_size(enum guc_log_buffer_type type) return DEBUG_BUFFER_SIZE; case GUC_CRASH_DUMP_LOG_BUFFER: return CRASH_BUFFER_SIZE; + case GUC_CAPTURE_LOG_BUFFER: + return CAPTURE_BUFFER_SIZE; default: MISSING_CASE(type); } @@ -463,14 +451,19 @@ int intel_guc_log_create(struct intel_guc_log *log) * +-------------------------------+ 32B * | Debug state header | * +-------------------------------+ 64B + * | Capture state header | + * +-------------------------------+ 96B * | | * +===============================+ PAGE_SIZE (4KB) * | Crash Dump logs | * +===============================+ + CRASH_SIZE * | Debug logs | * +===============================+ + DEBUG_SIZE + * | Capture logs | + * +===============================+ + CAPTURE_SIZE */ - guc_log_size = PAGE_SIZE + CRASH_BUFFER_SIZE + DEBUG_BUFFER_SIZE; + guc_log_size = PAGE_SIZE + CRASH_BUFFER_SIZE + DEBUG_BUFFER_SIZE + + CAPTURE_BUFFER_SIZE; vma = intel_guc_allocate_vma(guc, guc_log_size); if (IS_ERR(vma)) { @@ -592,8 +585,6 @@ int intel_guc_log_relay_start(struct intel_guc_log *log) if (log->relay.started) return -EEXIST; - guc_log_enable_flush_events(log); - /* * When GuC is logging without us relaying to userspace, we're ignoring * the flush notification. This means that we need to unconditionally @@ -640,7 +631,6 @@ static void guc_log_relay_stop(struct intel_guc_log *log) if (!log->relay.started) return; - guc_log_disable_flush_events(log); intel_synchronize_irq(i915); flush_work(&log->relay.flush_work); @@ -661,7 +651,8 @@ void intel_guc_log_relay_close(struct intel_guc_log *log) void intel_guc_log_handle_flush_event(struct intel_guc_log *log) { - queue_work(system_highpri_wq, &log->relay.flush_work); + if (log->relay.started) + queue_work(system_highpri_wq, &log->relay.flush_work); } static const char * @@ -672,6 +663,8 @@ stringify_guc_log_type(enum guc_log_buffer_type type) return "DEBUG"; case GUC_CRASH_DUMP_LOG_BUFFER: return "CRASH"; + case GUC_CAPTURE_LOG_BUFFER: + return "CAPTURE"; default: MISSING_CASE(type); } diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_log.h b/drivers/gpu/drm/i915/gt/uc/intel_guc_log.h index fe6ab7550a14..d7e1b6471fed 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_log.h +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_log.h @@ -18,12 +18,15 @@ struct intel_guc; #if defined(CONFIG_DRM_I915_DEBUG_GUC) #define CRASH_BUFFER_SIZE SZ_2M #define DEBUG_BUFFER_SIZE SZ_16M +#define CAPTURE_BUFFER_SIZE SZ_4M #elif defined(CONFIG_DRM_I915_DEBUG_GEM) #define CRASH_BUFFER_SIZE SZ_1M #define DEBUG_BUFFER_SIZE SZ_2M +#define CAPTURE_BUFFER_SIZE SZ_1M #else #define CRASH_BUFFER_SIZE SZ_8K #define DEBUG_BUFFER_SIZE SZ_64K +#define CAPTURE_BUFFER_SIZE SZ_16K #endif /* diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_reg.h b/drivers/gpu/drm/i915/gt/uc/intel_guc_reg.h index b37fc2ffaef2..e6bd66d6ce5a 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_reg.h +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_reg.h @@ -22,10 +22,6 @@ #define GS_BOOTROM_JUMP_PASSED (0x76 << GS_BOOTROM_SHIFT) #define GS_UKERNEL_SHIFT 8 #define GS_UKERNEL_MASK (0xFF << GS_UKERNEL_SHIFT) -#define GS_UKERNEL_LAPIC_DONE (0x30 << GS_UKERNEL_SHIFT) -#define GS_UKERNEL_DPC_ERROR (0x60 << GS_UKERNEL_SHIFT) -#define GS_UKERNEL_EXCEPTION (0x70 << GS_UKERNEL_SHIFT) -#define GS_UKERNEL_READY (0xF0 << GS_UKERNEL_SHIFT) #define GS_MIA_SHIFT 16 #define GS_MIA_MASK (0x07 << GS_MIA_SHIFT) #define GS_MIA_CORE_STATE (0x01 << GS_MIA_SHIFT) diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c index e7517206af82..c13f123ae16e 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c @@ -1349,7 +1349,8 @@ submission_disabled(struct intel_guc *guc) struct i915_sched_engine * const sched_engine = guc->sched_engine; return unlikely(!sched_engine || - !__tasklet_is_enabled(&sched_engine->tasklet)); + !__tasklet_is_enabled(&sched_engine->tasklet) || + intel_gt_is_wedged(guc_to_gt(guc))); } static void disable_submission(struct intel_guc *guc) @@ -1725,7 +1726,7 @@ void intel_guc_submission_reset_finish(struct intel_guc *guc) { /* Reset called during driver load or during wedge? */ if (unlikely(!guc_submission_initialized(guc) || - test_bit(I915_WEDGED, &guc_to_gt(guc)->reset.flags))) { + intel_gt_is_wedged(guc_to_gt(guc)))) { return; } @@ -3248,8 +3249,6 @@ static void guc_parent_context_unpin(struct intel_context *ce) GEM_BUG_ON(!intel_context_is_parent(ce)); GEM_BUG_ON(!intel_engine_is_virtual(ce->engine)); - if (ce->parallel.last_rq) - i915_request_put(ce->parallel.last_rq); unpin_guc_id(guc, ce); lrc_unpin(ce); } @@ -3979,6 +3978,11 @@ static void guc_handle_context_reset(struct intel_guc *guc, !context_blocked(ce))) { capture_error_state(guc, ce); guc_context_replay(ce); + } else { + drm_err(&guc_to_gt(guc)->i915->drm, + "Invalid GuC engine reset notificaion for 0x%04X on %s: banned = %d, blocked = %d", + ce->guc_id.id, ce->engine->name, intel_context_is_banned(ce), + context_blocked(ce)); } } @@ -4017,6 +4021,24 @@ int intel_guc_context_reset_process_msg(struct intel_guc *guc, return 0; } +int intel_guc_error_capture_process_msg(struct intel_guc *guc, + const u32 *msg, u32 len) +{ + int status; + + if (unlikely(len != 1)) { + drm_dbg(&guc_to_gt(guc)->i915->drm, "Invalid length %u", len); + return -EPROTO; + } + + status = msg[0]; + drm_info(&guc_to_gt(guc)->i915->drm, "Got error capture: status = %d", status); + + /* FIXME: Do something with the capture */ + + return 0; +} + static struct intel_engine_cs * guc_lookup_engine(struct intel_guc *guc, u8 guc_class, u8 instance) { diff --git a/drivers/gpu/drm/i915/gt/uc/intel_huc.c b/drivers/gpu/drm/i915/gt/uc/intel_huc.c index d10b227ac4aa..556829de9c17 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_huc.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_huc.c @@ -124,6 +124,7 @@ int intel_huc_auth(struct intel_huc *huc) } intel_uc_fw_change_status(&huc->fw, INTEL_UC_FIRMWARE_RUNNING); + drm_info(>->i915->drm, "HuC authenticated\n"); return 0; fail: diff --git a/drivers/gpu/drm/i915/gt/uc/intel_uc.c b/drivers/gpu/drm/i915/gt/uc/intel_uc.c index 09ed29df67bc..da199aa6989f 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_uc.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_uc.c @@ -432,6 +432,15 @@ static int __uc_check_hw(struct intel_uc *uc) return 0; } +static void print_fw_ver(struct intel_uc *uc, struct intel_uc_fw *fw) +{ + struct drm_i915_private *i915 = uc_to_gt(uc)->i915; + + drm_info(&i915->drm, "%s firmware %s version %u.%u\n", + intel_uc_fw_type_repr(fw->type), fw->path, + fw->major_ver_found, fw->minor_ver_found); +} + static int __uc_init_hw(struct intel_uc *uc) { struct drm_i915_private *i915 = uc_to_gt(uc)->i915; @@ -442,6 +451,11 @@ static int __uc_init_hw(struct intel_uc *uc) GEM_BUG_ON(!intel_uc_supports_guc(uc)); GEM_BUG_ON(!intel_uc_wants_guc(uc)); + print_fw_ver(uc, &guc->fw); + + if (intel_uc_uses_huc(uc)) + print_fw_ver(uc, &huc->fw); + if (!intel_uc_fw_is_loadable(&guc->fw)) { ret = __uc_check_hw(uc) || intel_uc_fw_is_overridden(&guc->fw) || @@ -507,24 +521,11 @@ static int __uc_init_hw(struct intel_uc *uc) intel_rps_lower_unslice(&uc_to_gt(uc)->rps); } - drm_info(&i915->drm, "%s firmware %s version %u.%u %s:%s\n", - intel_uc_fw_type_repr(INTEL_UC_FW_TYPE_GUC), guc->fw.path, - guc->fw.major_ver_found, guc->fw.minor_ver_found, - "submission", + drm_info(&i915->drm, "GuC submission %s\n", enableddisabled(intel_uc_uses_guc_submission(uc))); - - drm_info(&i915->drm, "GuC SLPC: %s\n", + drm_info(&i915->drm, "GuC SLPC %s\n", enableddisabled(intel_uc_uses_guc_slpc(uc))); - if (intel_uc_uses_huc(uc)) { - drm_info(&i915->drm, "%s firmware %s version %u.%u %s:%s\n", - intel_uc_fw_type_repr(INTEL_UC_FW_TYPE_HUC), - huc->fw.path, - huc->fw.major_ver_found, huc->fw.minor_ver_found, - "authenticated", - yesno(intel_huc_is_authenticated(huc))); - } - return 0; /* diff --git a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c index a5af05bde6f2..62db14d41042 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c @@ -49,21 +49,21 @@ void intel_uc_fw_change_status(struct intel_uc_fw *uc_fw, * firmware as TGL. */ #define INTEL_GUC_FIRMWARE_DEFS(fw_def, guc_def) \ - fw_def(ALDERLAKE_P, 0, guc_def(adlp, 62, 0, 3)) \ - fw_def(ALDERLAKE_S, 0, guc_def(tgl, 62, 0, 0)) \ - fw_def(DG1, 0, guc_def(dg1, 62, 0, 0)) \ - fw_def(ROCKETLAKE, 0, guc_def(tgl, 62, 0, 0)) \ - fw_def(TIGERLAKE, 0, guc_def(tgl, 62, 0, 0)) \ - fw_def(JASPERLAKE, 0, guc_def(ehl, 62, 0, 0)) \ - fw_def(ELKHARTLAKE, 0, guc_def(ehl, 62, 0, 0)) \ - fw_def(ICELAKE, 0, guc_def(icl, 62, 0, 0)) \ - fw_def(COMETLAKE, 5, guc_def(cml, 62, 0, 0)) \ - fw_def(COMETLAKE, 0, guc_def(kbl, 62, 0, 0)) \ - fw_def(COFFEELAKE, 0, guc_def(kbl, 62, 0, 0)) \ - fw_def(GEMINILAKE, 0, guc_def(glk, 62, 0, 0)) \ - fw_def(KABYLAKE, 0, guc_def(kbl, 62, 0, 0)) \ - fw_def(BROXTON, 0, guc_def(bxt, 62, 0, 0)) \ - fw_def(SKYLAKE, 0, guc_def(skl, 62, 0, 0)) + fw_def(ALDERLAKE_P, 0, guc_def(adlp, 69, 0, 3)) \ + fw_def(ALDERLAKE_S, 0, guc_def(tgl, 69, 0, 3)) \ + fw_def(DG1, 0, guc_def(dg1, 69, 0, 3)) \ + fw_def(ROCKETLAKE, 0, guc_def(tgl, 69, 0, 3)) \ + fw_def(TIGERLAKE, 0, guc_def(tgl, 69, 0, 3)) \ + fw_def(JASPERLAKE, 0, guc_def(ehl, 69, 0, 3)) \ + fw_def(ELKHARTLAKE, 0, guc_def(ehl, 69, 0, 3)) \ + fw_def(ICELAKE, 0, guc_def(icl, 69, 0, 3)) \ + fw_def(COMETLAKE, 5, guc_def(cml, 69, 0, 3)) \ + fw_def(COMETLAKE, 0, guc_def(kbl, 69, 0, 3)) \ + fw_def(COFFEELAKE, 0, guc_def(kbl, 69, 0, 3)) \ + fw_def(GEMINILAKE, 0, guc_def(glk, 69, 0, 3)) \ + fw_def(KABYLAKE, 0, guc_def(kbl, 69, 0, 3)) \ + fw_def(BROXTON, 0, guc_def(bxt, 69, 0, 3)) \ + fw_def(SKYLAKE, 0, guc_def(skl, 69, 0, 3)) #define INTEL_HUC_FIRMWARE_DEFS(fw_def, huc_def) \ fw_def(ALDERLAKE_P, 0, huc_def(tgl, 7, 9, 3)) \ @@ -448,20 +448,19 @@ static void uc_fw_bind_ggtt(struct intel_uc_fw *uc_fw) { struct drm_i915_gem_object *obj = uc_fw->obj; struct i915_ggtt *ggtt = __uc_fw_to_gt(uc_fw)->ggtt; - struct i915_vma *dummy = &uc_fw->dummy; + struct i915_vma_resource *dummy = &uc_fw->dummy; u32 pte_flags = 0; - dummy->node.start = uc_fw_ggtt_offset(uc_fw); - dummy->node.size = obj->base.size; - dummy->pages = obj->mm.pages; - dummy->vm = &ggtt->vm; + dummy->start = uc_fw_ggtt_offset(uc_fw); + dummy->node_size = obj->base.size; + dummy->bi.pages = obj->mm.pages; GEM_BUG_ON(!i915_gem_object_has_pinned_pages(obj)); - GEM_BUG_ON(dummy->node.size > ggtt->uc_fw.size); + GEM_BUG_ON(dummy->node_size > ggtt->uc_fw.size); /* uc_fw->obj cache domains were not controlled across suspend */ if (i915_gem_object_has_struct_page(obj)) - drm_clflush_sg(dummy->pages); + drm_clflush_sg(dummy->bi.pages); if (i915_gem_object_is_lmem(obj)) pte_flags |= PTE_LM; diff --git a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.h b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.h index d9d1dc0b4cbb..3229018877d3 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.h +++ b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.h @@ -85,7 +85,7 @@ struct intel_uc_fw { * threaded as it done during driver load (inherently single threaded) * or during a GT reset (mutex guarantees single threaded). */ - struct i915_vma dummy; + struct i915_vma_resource dummy; struct i915_vma *rsa_data; /* diff --git a/drivers/gpu/drm/i915/gvt/dmabuf.c b/drivers/gpu/drm/i915/gvt/dmabuf.c index 8e65cd8258b9..94c3eb1586b0 100644 --- a/drivers/gpu/drm/i915/gvt/dmabuf.c +++ b/drivers/gpu/drm/i915/gvt/dmabuf.c @@ -84,7 +84,7 @@ static int vgpu_gem_get_pages( kfree(st); return ret; } - gtt_entries = (gen8_pte_t __iomem *)dev_priv->ggtt.gsm + + gtt_entries = (gen8_pte_t __iomem *)to_gt(dev_priv)->ggtt->gsm + (fb_info->start >> PAGE_SHIFT); for_each_sg(st->sgl, sg, page_num, i) { dma_addr_t dma_addr = diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c index e0e052cdf8b8..f3141b58d912 100644 --- a/drivers/gpu/drm/i915/i915_debugfs.c +++ b/drivers/gpu/drm/i915/i915_debugfs.c @@ -170,7 +170,8 @@ i915_debugfs_describe_obj(struct seq_file *m, struct drm_i915_gem_object *obj) 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)); + stringify_page_sizes(vma->resource->page_sizes_gtt, + NULL, 0)); if (i915_vma_is_ggtt(vma) || i915_vma_is_dpt(vma)) { switch (vma->ggtt_view.type) { case I915_GGTT_VIEW_NORMAL: @@ -390,9 +391,9 @@ static int i915_swizzle_info(struct seq_file *m, void *data) intel_wakeref_t wakeref; seq_printf(m, "bit6 swizzle for X-tiling = %s\n", - swizzle_string(dev_priv->ggtt.bit_6_swizzle_x)); + swizzle_string(to_gt(dev_priv)->ggtt->bit_6_swizzle_x)); seq_printf(m, "bit6 swizzle for Y-tiling = %s\n", - swizzle_string(dev_priv->ggtt.bit_6_swizzle_y)); + swizzle_string(to_gt(dev_priv)->ggtt->bit_6_swizzle_y)); if (dev_priv->quirks & QUIRK_PIN_SWIZZLED_PAGES) seq_puts(m, "L-shaped memory detected\n"); diff --git a/drivers/gpu/drm/i915/i915_driver.c b/drivers/gpu/drm/i915/i915_driver.c index 95174938b160..5f2343389b5e 100644 --- a/drivers/gpu/drm/i915/i915_driver.c +++ b/drivers/gpu/drm/i915/i915_driver.c @@ -571,6 +571,10 @@ static int i915_driver_hw_probe(struct drm_i915_private *dev_priv) i915_perf_init(dev_priv); + ret = intel_gt_assign_ggtt(to_gt(dev_priv)); + if (ret) + goto err_perf; + ret = i915_ggtt_probe_hw(dev_priv); if (ret) goto err_perf; @@ -587,8 +591,6 @@ static int i915_driver_hw_probe(struct drm_i915_private *dev_priv) if (ret) goto err_ggtt; - intel_gt_init_hw_early(to_gt(dev_priv), &dev_priv->ggtt); - ret = intel_gt_probe_lmem(to_gt(dev_priv)); if (ret) goto err_mem_regions; @@ -1146,7 +1148,7 @@ static int i915_drm_suspend(struct drm_device *dev) /* Must be called before GGTT is suspended. */ intel_dpt_suspend(dev_priv); - i915_ggtt_suspend(&dev_priv->ggtt); + i915_ggtt_suspend(to_gt(dev_priv)->ggtt); i915_save_display(dev_priv); @@ -1270,7 +1272,7 @@ static int i915_drm_resume(struct drm_device *dev) if (ret) drm_err(&dev_priv->drm, "failed to re-enable GGTT\n"); - i915_ggtt_resume(&dev_priv->ggtt); + i915_ggtt_resume(to_gt(dev_priv)->ggtt); /* Must be called after GGTT is resumed. */ intel_dpt_resume(dev_priv); diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index 0c70ab08fc0c..b61a1c785739 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -838,8 +838,6 @@ struct drm_i915_private { struct drm_atomic_state *modeset_restore_state; struct drm_modeset_acquire_ctx reset_ctx; - struct i915_ggtt ggtt; /* VM representing the global address space */ - struct i915_gem_mm mm; /* Kernel Modesetting */ @@ -1681,6 +1679,7 @@ int i915_gem_object_unbind(struct drm_i915_gem_object *obj, #define I915_GEM_OBJECT_UNBIND_BARRIER BIT(1) #define I915_GEM_OBJECT_UNBIND_TEST BIT(2) #define I915_GEM_OBJECT_UNBIND_VM_TRYLOCK BIT(3) +#define I915_GEM_OBJECT_UNBIND_ASYNC BIT(4) void i915_gem_runtime_suspend(struct drm_i915_private *dev_priv); @@ -1759,7 +1758,7 @@ static inline bool i915_gem_object_needs_bit17_swizzle(struct drm_i915_gem_objec { struct drm_i915_private *i915 = to_i915(obj->base.dev); - return i915->ggtt.bit_6_swizzle_x == I915_BIT_6_SWIZZLE_9_10_17 && + return to_gt(i915)->ggtt->bit_6_swizzle_x == I915_BIT_6_SWIZZLE_9_10_17 && i915_gem_object_is_tiled(obj); } diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index 915bf431f320..3d6c00f845a3 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -88,7 +88,8 @@ int i915_gem_get_aperture_ioctl(struct drm_device *dev, void *data, struct drm_file *file) { - struct i915_ggtt *ggtt = &to_i915(dev)->ggtt; + struct drm_i915_private *i915 = to_i915(dev); + struct i915_ggtt *ggtt = to_gt(i915)->ggtt; struct drm_i915_gem_get_aperture *args = data; struct i915_vma *vma; u64 pinned; @@ -155,10 +156,16 @@ try_again: spin_unlock(&obj->vma.lock); if (vma) { + bool vm_trylock = !!(flags & I915_GEM_OBJECT_UNBIND_VM_TRYLOCK); ret = -EBUSY; - if (flags & I915_GEM_OBJECT_UNBIND_ACTIVE || - !i915_vma_is_active(vma)) { - if (flags & I915_GEM_OBJECT_UNBIND_VM_TRYLOCK) { + if (flags & I915_GEM_OBJECT_UNBIND_ASYNC) { + assert_object_held(vma->obj); + ret = i915_vma_unbind_async(vma, vm_trylock); + } + + if (ret == -EBUSY && (flags & I915_GEM_OBJECT_UNBIND_ACTIVE || + !i915_vma_is_active(vma))) { + if (vm_trylock) { if (mutex_trylock(&vma->vm->mutex)) { ret = __i915_vma_unbind(vma); mutex_unlock(&vma->vm->mutex); @@ -289,7 +296,7 @@ static struct i915_vma *i915_gem_gtt_prepare(struct drm_i915_gem_object *obj, bool write) { struct drm_i915_private *i915 = to_i915(obj->base.dev); - struct i915_ggtt *ggtt = &i915->ggtt; + struct i915_ggtt *ggtt = to_gt(i915)->ggtt; struct i915_vma *vma; struct i915_gem_ww_ctx ww; int ret; @@ -350,7 +357,7 @@ static void i915_gem_gtt_cleanup(struct drm_i915_gem_object *obj, struct i915_vma *vma) { struct drm_i915_private *i915 = to_i915(obj->base.dev); - struct i915_ggtt *ggtt = &i915->ggtt; + struct i915_ggtt *ggtt = to_gt(i915)->ggtt; i915_gem_object_unpin_pages(obj); if (drm_mm_node_allocated(node)) { @@ -366,7 +373,7 @@ i915_gem_gtt_pread(struct drm_i915_gem_object *obj, const struct drm_i915_gem_pread *args) { struct drm_i915_private *i915 = to_i915(obj->base.dev); - struct i915_ggtt *ggtt = &i915->ggtt; + struct i915_ggtt *ggtt = to_gt(i915)->ggtt; intel_wakeref_t wakeref; struct drm_mm_node node; void __user *user_data; @@ -522,7 +529,7 @@ i915_gem_gtt_pwrite_fast(struct drm_i915_gem_object *obj, const struct drm_i915_gem_pwrite *args) { struct drm_i915_private *i915 = to_i915(obj->base.dev); - struct i915_ggtt *ggtt = &i915->ggtt; + struct i915_ggtt *ggtt = to_gt(i915)->ggtt; struct intel_runtime_pm *rpm = &i915->runtime_pm; intel_wakeref_t wakeref; struct drm_mm_node node; @@ -823,7 +830,7 @@ void i915_gem_runtime_suspend(struct drm_i915_private *i915) */ list_for_each_entry_safe(obj, on, - &i915->ggtt.userfault_list, userfault_link) + &to_gt(i915)->ggtt->userfault_list, userfault_link) __i915_gem_object_release_mmap_gtt(obj); /* @@ -831,8 +838,8 @@ void i915_gem_runtime_suspend(struct drm_i915_private *i915) * in use by hardware (i.e. they are pinned), we should not be powering * down! All other fences will be reacquired by the user upon waking. */ - for (i = 0; i < i915->ggtt.num_fences; i++) { - struct i915_fence_reg *reg = &i915->ggtt.fence_regs[i]; + for (i = 0; i < to_gt(i915)->ggtt->num_fences; i++) { + struct i915_fence_reg *reg = &to_gt(i915)->ggtt->fence_regs[i]; /* * Ideally we want to assert that the fence register is not @@ -873,7 +880,7 @@ i915_gem_object_ggtt_pin_ww(struct drm_i915_gem_object *obj, u64 size, u64 alignment, u64 flags) { struct drm_i915_private *i915 = to_i915(obj->base.dev); - struct i915_ggtt *ggtt = &i915->ggtt; + struct i915_ggtt *ggtt = to_gt(i915)->ggtt; struct i915_vma *vma; int ret; @@ -1123,7 +1130,7 @@ err_unlock: /* Minimal basic recovery for KMS */ ret = i915_ggtt_enable_hw(dev_priv); - i915_ggtt_resume(&dev_priv->ggtt); + i915_ggtt_resume(to_gt(dev_priv)->ggtt); intel_init_clock_gating(dev_priv); } @@ -1146,7 +1153,7 @@ void i915_gem_driver_unregister(struct drm_i915_private *i915) void i915_gem_driver_remove(struct drm_i915_private *dev_priv) { - intel_wakeref_auto_fini(&dev_priv->ggtt.userfault_wakeref); + intel_wakeref_auto_fini(&to_gt(dev_priv)->ggtt->userfault_wakeref); i915_gem_suspend_late(dev_priv); intel_gt_driver_remove(to_gt(dev_priv)); diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c index cd5f2348a187..2f2ba7a2955d 100644 --- a/drivers/gpu/drm/i915/i915_gem_gtt.c +++ b/drivers/gpu/drm/i915/i915_gem_gtt.c @@ -56,7 +56,7 @@ void i915_gem_gtt_finish_pages(struct drm_i915_gem_object *obj, struct sg_table *pages) { struct drm_i915_private *i915 = to_i915(obj->base.dev); - struct i915_ggtt *ggtt = &i915->ggtt; + struct i915_ggtt *ggtt = to_gt(i915)->ggtt; /* XXX This does not prevent more requests being submitted! */ if (unlikely(ggtt->do_idle_maps)) @@ -103,7 +103,7 @@ int i915_gem_gtt_reserve(struct i915_address_space *vm, GEM_BUG_ON(!IS_ALIGNED(size, I915_GTT_PAGE_SIZE)); GEM_BUG_ON(!IS_ALIGNED(offset, I915_GTT_MIN_ALIGNMENT)); GEM_BUG_ON(range_overflows(offset, size, vm->total)); - GEM_BUG_ON(vm == &vm->i915->ggtt.alias->vm); + GEM_BUG_ON(vm == &to_gt(vm->i915)->ggtt->alias->vm); GEM_BUG_ON(drm_mm_node_allocated(node)); node->size = size; @@ -201,7 +201,7 @@ int i915_gem_gtt_insert(struct i915_address_space *vm, GEM_BUG_ON(start >= end); GEM_BUG_ON(start > 0 && !IS_ALIGNED(start, I915_GTT_PAGE_SIZE)); GEM_BUG_ON(end < U64_MAX && !IS_ALIGNED(end, I915_GTT_PAGE_SIZE)); - GEM_BUG_ON(vm == &vm->i915->ggtt.alias->vm); + GEM_BUG_ON(vm == &to_gt(vm->i915)->ggtt->alias->vm); GEM_BUG_ON(drm_mm_node_allocated(node)); if (unlikely(range_overflows(start, size, end))) diff --git a/drivers/gpu/drm/i915/i915_getparam.c b/drivers/gpu/drm/i915/i915_getparam.c index 7f80ad247bc8..5b8a2157d797 100644 --- a/drivers/gpu/drm/i915/i915_getparam.c +++ b/drivers/gpu/drm/i915/i915_getparam.c @@ -31,7 +31,7 @@ int i915_getparam_ioctl(struct drm_device *dev, void *data, value = pdev->revision; break; case I915_PARAM_NUM_FENCES_AVAIL: - value = i915->ggtt.num_fences; + value = to_gt(i915)->ggtt->num_fences; break; case I915_PARAM_HAS_OVERLAY: value = !!i915->overlay; diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c index 5ae812d60abe..f8c4336cba89 100644 --- a/drivers/gpu/drm/i915/i915_gpu_error.c +++ b/drivers/gpu/drm/i915/i915_gpu_error.c @@ -48,7 +48,6 @@ #include "i915_gpu_error.h" #include "i915_memcpy.h" #include "i915_scatterlist.h" -#include "i915_vma_snapshot.h" #define ALLOW_FAIL (__GFP_KSWAPD_RECLAIM | __GFP_RETRY_MAYFAIL | __GFP_NOWARN) #define ATOMIC_MAYFAIL (GFP_ATOMIC | __GFP_NOWARN) @@ -1013,8 +1012,10 @@ void __i915_gpu_coredump_free(struct kref *error_ref) static struct i915_vma_coredump * i915_vma_coredump_create(const struct intel_gt *gt, - const struct i915_vma_snapshot *vsnap, - struct i915_vma_compress *compress) + const struct i915_vma_resource *vma_res, + struct i915_vma_compress *compress, + const char *name) + { struct i915_ggtt *ggtt = gt->ggtt; const u64 slot = ggtt->error_capture.start; @@ -1024,7 +1025,7 @@ i915_vma_coredump_create(const struct intel_gt *gt, might_sleep(); - if (!vsnap || !vsnap->pages || !compress) + if (!vma_res || !vma_res->bi.pages || !compress) return NULL; dst = kmalloc(sizeof(*dst), ALLOW_FAIL); @@ -1037,12 +1038,12 @@ i915_vma_coredump_create(const struct intel_gt *gt, } INIT_LIST_HEAD(&dst->page_list); - strcpy(dst->name, vsnap->name); + strcpy(dst->name, name); dst->next = NULL; - dst->gtt_offset = vsnap->gtt_offset; - dst->gtt_size = vsnap->gtt_size; - dst->gtt_page_sizes = vsnap->page_sizes; + dst->gtt_offset = vma_res->start; + dst->gtt_size = vma_res->node_size; + dst->gtt_page_sizes = vma_res->page_sizes_gtt; dst->unused = 0; ret = -EINVAL; @@ -1050,7 +1051,7 @@ i915_vma_coredump_create(const struct intel_gt *gt, void __iomem *s; dma_addr_t dma; - for_each_sgt_daddr(dma, iter, vsnap->pages) { + for_each_sgt_daddr(dma, iter, vma_res->bi.pages) { mutex_lock(&ggtt->error_mutex); ggtt->vm.insert_page(&ggtt->vm, dma, slot, I915_CACHE_NONE, 0); @@ -1068,11 +1069,11 @@ i915_vma_coredump_create(const struct intel_gt *gt, if (ret) break; } - } else if (vsnap->mr && vsnap->mr->type != INTEL_MEMORY_SYSTEM) { - struct intel_memory_region *mem = vsnap->mr; + } else if (vma_res->bi.lmem) { + struct intel_memory_region *mem = vma_res->mr; dma_addr_t dma; - for_each_sgt_daddr(dma, iter, vsnap->pages) { + for_each_sgt_daddr(dma, iter, vma_res->bi.pages) { void __iomem *s; s = io_mapping_map_wc(&mem->iomap, @@ -1088,7 +1089,7 @@ i915_vma_coredump_create(const struct intel_gt *gt, } else { struct page *page; - for_each_sgt_page(page, iter, vsnap->pages) { + for_each_sgt_page(page, iter, vma_res->bi.pages) { void *s; drm_clflush_pages(&page, 1); @@ -1324,33 +1325,32 @@ static bool record_context(struct i915_gem_context_coredump *e, struct intel_engine_capture_vma { struct intel_engine_capture_vma *next; - struct i915_vma_snapshot *vsnap; + struct i915_vma_resource *vma_res; char name[16]; bool lockdep_cookie; }; static struct intel_engine_capture_vma * capture_vma_snapshot(struct intel_engine_capture_vma *next, - struct i915_vma_snapshot *vsnap, - gfp_t gfp) + struct i915_vma_resource *vma_res, + gfp_t gfp, const char *name) { struct intel_engine_capture_vma *c; - if (!i915_vma_snapshot_present(vsnap)) + if (!vma_res) return next; c = kmalloc(sizeof(*c), gfp); if (!c) return next; - if (!i915_vma_snapshot_resource_pin(vsnap, &c->lockdep_cookie)) { + if (!i915_vma_resource_hold(vma_res, &c->lockdep_cookie)) { kfree(c); return next; } - strcpy(c->name, vsnap->name); - c->vsnap = vsnap; - i915_vma_snapshot_get(vsnap); + strcpy(c->name, name); + c->vma_res = i915_vma_resource_get(vma_res); c->next = next; return c; @@ -1362,8 +1362,6 @@ capture_vma(struct intel_engine_capture_vma *next, const char *name, gfp_t gfp) { - struct i915_vma_snapshot *vsnap; - if (!vma) return next; @@ -1372,19 +1370,10 @@ capture_vma(struct intel_engine_capture_vma *next, * to a struct i915_vma_snapshot at command submission time. * Not here. */ - GEM_WARN_ON(!i915_vma_is_pinned(vma)); - if (!i915_vma_is_pinned(vma)) - return next; - - vsnap = i915_vma_snapshot_alloc(gfp); - if (!vsnap) + if (GEM_WARN_ON(!i915_vma_is_pinned(vma))) return next; - i915_vma_snapshot_init(vsnap, vma, name); - next = capture_vma_snapshot(next, vsnap, gfp); - - /* FIXME: Replace on async unbind. */ - i915_vma_snapshot_put(vsnap); + next = capture_vma_snapshot(next, vma->resource, gfp, name); return next; } @@ -1397,7 +1386,8 @@ capture_user(struct intel_engine_capture_vma *capture, struct i915_capture_list *c; for (c = rq->capture_list; c; c = c->next) - capture = capture_vma_snapshot(capture, c->vma_snapshot, gfp); + capture = capture_vma_snapshot(capture, c->vma_res, gfp, + "user"); return capture; } @@ -1415,16 +1405,19 @@ static struct i915_vma_coredump * create_vma_coredump(const struct intel_gt *gt, struct i915_vma *vma, const char *name, struct i915_vma_compress *compress) { - struct i915_vma_coredump *ret; - struct i915_vma_snapshot tmp; + struct i915_vma_coredump *ret = NULL; + struct i915_vma_resource *vma_res; + bool lockdep_cookie; if (!vma) return NULL; - GEM_WARN_ON(!i915_vma_is_pinned(vma)); - i915_vma_snapshot_init_onstack(&tmp, vma, name); - ret = i915_vma_coredump_create(gt, &tmp, compress); - i915_vma_snapshot_put_onstack(&tmp); + vma_res = vma->resource; + + if (i915_vma_resource_hold(vma_res, &lockdep_cookie)) { + ret = i915_vma_coredump_create(gt, vma_res, compress, name); + i915_vma_resource_unhold(vma_res, lockdep_cookie); + } return ret; } @@ -1471,7 +1464,7 @@ intel_engine_coredump_add_request(struct intel_engine_coredump *ee, * as the simplest method to avoid being overwritten * by userspace. */ - vma = capture_vma_snapshot(vma, &rq->batch_snapshot, gfp); + vma = capture_vma_snapshot(vma, rq->batch_res, gfp, "batch"); vma = capture_user(vma, rq, gfp); vma = capture_vma(vma, rq->ring->vma, "ring", gfp); vma = capture_vma(vma, rq->context->state, "HW context", gfp); @@ -1492,14 +1485,14 @@ intel_engine_coredump_add_vma(struct intel_engine_coredump *ee, while (capture) { struct intel_engine_capture_vma *this = capture; - struct i915_vma_snapshot *vsnap = this->vsnap; + struct i915_vma_resource *vma_res = this->vma_res; add_vma(ee, - i915_vma_coredump_create(engine->gt, - vsnap, compress)); + i915_vma_coredump_create(engine->gt, vma_res, + compress, this->name)); - i915_vma_snapshot_resource_unpin(vsnap, this->lockdep_cookie); - i915_vma_snapshot_put(vsnap); + i915_vma_resource_unhold(vma_res, this->lockdep_cookie); + i915_vma_resource_put(vma_res); capture = this->next; kfree(this); diff --git a/drivers/gpu/drm/i915/i915_module.c b/drivers/gpu/drm/i915/i915_module.c index f6bcd2f89257..a8f175960b34 100644 --- a/drivers/gpu/drm/i915/i915_module.c +++ b/drivers/gpu/drm/i915/i915_module.c @@ -17,6 +17,7 @@ #include "i915_scheduler.h" #include "i915_selftest.h" #include "i915_vma.h" +#include "i915_vma_resource.h" static int i915_check_nomodeset(void) { @@ -64,6 +65,8 @@ static const struct { .exit = i915_scheduler_module_exit }, { .init = i915_vma_module_init, .exit = i915_vma_module_exit }, + { .init = i915_vma_resource_module_init, + .exit = i915_vma_resource_module_exit }, { .init = i915_mock_selftests }, { .init = i915_pmu_init, .exit = i915_pmu_exit }, diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c index 170bba913c30..f9faf7697453 100644 --- a/drivers/gpu/drm/i915/i915_perf.c +++ b/drivers/gpu/drm/i915/i915_perf.c @@ -1630,8 +1630,8 @@ static int alloc_noa_wait(struct i915_perf_stream *stream) struct drm_i915_gem_object *bo; struct i915_vma *vma; const u64 delay_ticks = 0xffffffffffffffff - - intel_gt_ns_to_clock_interval(stream->perf->i915->ggtt.vm.gt, - atomic64_read(&stream->perf->noa_programming_delay)); + intel_gt_ns_to_clock_interval(to_gt(stream->perf->i915), + atomic64_read(&stream->perf->noa_programming_delay)); const u32 base = stream->engine->mmio_base; #define CS_GPR(x) GEN8_RING_CS_GPR(base, x) u32 *batch, *ts0, *cs, *jump; @@ -2114,7 +2114,7 @@ gen8_update_reg_state_unlocked(const struct intel_context *ce, u32 ctx_oactxctrl = stream->perf->ctx_oactxctrl_offset; u32 ctx_flexeu0 = stream->perf->ctx_flexeu0_offset; /* The MMIO offsets for Flex EU registers aren't contiguous */ - i915_reg_t flex_regs[] = { + static const i915_reg_t flex_regs[] = { EU_PERF_CNTL0, EU_PERF_CNTL1, EU_PERF_CNTL2, @@ -3542,7 +3542,7 @@ err: static u64 oa_exponent_to_ns(struct i915_perf *perf, int exponent) { - return intel_gt_clock_interval_to_ns(perf->i915->ggtt.vm.gt, + return intel_gt_clock_interval_to_ns(to_gt(perf->i915), 2ULL << exponent); } diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c index 76cf5ac91e94..ba3a70b2cc57 100644 --- a/drivers/gpu/drm/i915/i915_request.c +++ b/drivers/gpu/drm/i915/i915_request.c @@ -116,8 +116,10 @@ static void i915_fence_release(struct dma_fence *fence) rq->guc_prio != GUC_PRIO_FINI); i915_request_free_capture_list(fetch_and_zero(&rq->capture_list)); - if (i915_vma_snapshot_present(&rq->batch_snapshot)) - i915_vma_snapshot_put_onstack(&rq->batch_snapshot); + if (rq->batch_res) { + i915_vma_resource_put(rq->batch_res); + rq->batch_res = NULL; + } /* * The request is put onto a RCU freelist (i.e. the address @@ -308,7 +310,7 @@ void i915_request_free_capture_list(struct i915_capture_list *capture) while (capture) { struct i915_capture_list *next = capture->next; - i915_vma_snapshot_put(capture->vma_snapshot); + i915_vma_resource_put(capture->vma_res); kfree(capture); capture = next; } @@ -854,7 +856,7 @@ static void __i915_request_ctor(void *arg) i915_sw_fence_init(&rq->semaphore, semaphore_notify); clear_capture_list(rq); - rq->batch_snapshot.present = false; + rq->batch_res = NULL; init_llist_head(&rq->execute_cb); } @@ -960,7 +962,7 @@ __i915_request_create(struct intel_context *ce, gfp_t gfp) __rq_init_watchdog(rq); assert_capture_list_is_null(rq); GEM_BUG_ON(!llist_empty(&rq->execute_cb)); - GEM_BUG_ON(i915_vma_snapshot_present(&rq->batch_snapshot)); + GEM_BUG_ON(rq->batch_res); /* * Reserve space in the ring buffer for all the commands required to diff --git a/drivers/gpu/drm/i915/i915_request.h b/drivers/gpu/drm/i915/i915_request.h index 170ee78c2858..28b1f9db5487 100644 --- a/drivers/gpu/drm/i915/i915_request.h +++ b/drivers/gpu/drm/i915/i915_request.h @@ -40,7 +40,7 @@ #include "i915_scheduler.h" #include "i915_selftest.h" #include "i915_sw_fence.h" -#include "i915_vma_snapshot.h" +#include "i915_vma_resource.h" #include <uapi/drm/i915_drm.h> @@ -52,7 +52,7 @@ struct i915_request; #if IS_ENABLED(CONFIG_DRM_I915_CAPTURE_ERROR) struct i915_capture_list { - struct i915_vma_snapshot *vma_snapshot; + struct i915_vma_resource *vma_res; struct i915_capture_list *next; }; @@ -300,7 +300,7 @@ struct i915_request { /** Batch buffer pointer for selftest internal use. */ I915_SELFTEST_DECLARE(struct i915_vma *batch); - struct i915_vma_snapshot batch_snapshot; + struct i915_vma_resource *batch_res; #if IS_ENABLED(CONFIG_DRM_I915_CAPTURE_ERROR) /** diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c index 29a858c53bdd..9d859b0a3fbe 100644 --- a/drivers/gpu/drm/i915/i915_vma.c +++ b/drivers/gpu/drm/i915/i915_vma.c @@ -37,6 +37,7 @@ #include "i915_sw_fence_work.h" #include "i915_trace.h" #include "i915_vma.h" +#include "i915_vma_resource.h" static struct kmem_cache *slab_vmas; @@ -284,7 +285,7 @@ struct i915_vma_work { struct dma_fence_work base; struct i915_address_space *vm; struct i915_vm_pt_stash stash; - struct i915_vma *vma; + struct i915_vma_resource *vma_res; struct drm_i915_gem_object *pinned; struct i915_sw_dma_fence_cb cb; enum i915_cache_level cache_level; @@ -294,23 +295,24 @@ struct i915_vma_work { static void __vma_bind(struct dma_fence_work *work) { struct i915_vma_work *vw = container_of(work, typeof(*vw), base); - struct i915_vma *vma = vw->vma; + struct i915_vma_resource *vma_res = vw->vma_res; + + vma_res->ops->bind_vma(vma_res->vm, &vw->stash, + vma_res, vw->cache_level, vw->flags); - vma->ops->bind_vma(vw->vm, &vw->stash, - vma, vw->cache_level, vw->flags); } static void __vma_release(struct dma_fence_work *work) { struct i915_vma_work *vw = container_of(work, typeof(*vw), base); - if (vw->pinned) { - __i915_gem_object_unpin_pages(vw->pinned); + if (vw->pinned) i915_gem_object_put(vw->pinned); - } i915_vm_free_pt_stash(vw->vm, &vw->stash); i915_vm_put(vw->vm); + if (vw->vma_res) + i915_vma_resource_put(vw->vma_res); } static const struct dma_fence_work_ops bind_ops = { @@ -374,12 +376,27 @@ static int i915_vma_verify_bind_complete(struct i915_vma *vma) #define i915_vma_verify_bind_complete(_vma) 0 #endif +I915_SELFTEST_EXPORT void +i915_vma_resource_init_from_vma(struct i915_vma_resource *vma_res, + struct i915_vma *vma) +{ + struct drm_i915_gem_object *obj = vma->obj; + + i915_vma_resource_init(vma_res, vma->vm, vma->pages, &vma->page_sizes, + obj->mm.rsgt, i915_gem_object_is_readonly(obj), + i915_gem_object_is_lmem(obj), obj->mm.region, + vma->ops, vma->private, vma->node.start, + vma->node.size, vma->size); +} + /** * i915_vma_bind - Sets up PTEs for an VMA in it's corresponding address space. * @vma: VMA to map * @cache_level: mapping cache level * @flags: flags like global or local mapping * @work: preallocated worker for allocating and binding the PTE + * @vma_res: pointer to a preallocated vma resource. The resource is either + * consumed or freed. * * DMA addresses are taken from the scatter-gather table of this object (or of * this VMA in case of non-default GGTT views) and PTE entries set up. @@ -388,10 +405,12 @@ static int i915_vma_verify_bind_complete(struct i915_vma *vma) int i915_vma_bind(struct i915_vma *vma, enum i915_cache_level cache_level, u32 flags, - struct i915_vma_work *work) + struct i915_vma_work *work, + struct i915_vma_resource *vma_res) { u32 bind_flags; u32 vma_flags; + int ret; lockdep_assert_held(&vma->vm->mutex); GEM_BUG_ON(!drm_mm_node_allocated(&vma->node)); @@ -399,11 +418,15 @@ int i915_vma_bind(struct i915_vma *vma, if (GEM_DEBUG_WARN_ON(range_overflows(vma->node.start, vma->node.size, - vma->vm->total))) + vma->vm->total))) { + i915_vma_resource_free(vma_res); return -ENODEV; + } - if (GEM_DEBUG_WARN_ON(!flags)) + if (GEM_DEBUG_WARN_ON(!flags)) { + i915_vma_resource_free(vma_res); return -EINVAL; + } bind_flags = flags; bind_flags &= I915_VMA_GLOBAL_BIND | I915_VMA_LOCAL_BIND; @@ -412,16 +435,44 @@ int i915_vma_bind(struct i915_vma *vma, vma_flags &= I915_VMA_GLOBAL_BIND | I915_VMA_LOCAL_BIND; bind_flags &= ~vma_flags; - if (bind_flags == 0) + if (bind_flags == 0) { + i915_vma_resource_free(vma_res); return 0; + } GEM_BUG_ON(!atomic_read(&vma->pages_count)); + /* Wait for or await async unbinds touching our range */ + if (work && bind_flags & vma->vm->bind_async_flags) + ret = i915_vma_resource_bind_dep_await(vma->vm, + &work->base.chain, + vma->node.start, + vma->node.size, + true, + GFP_NOWAIT | + __GFP_RETRY_MAYFAIL | + __GFP_NOWARN); + else + ret = i915_vma_resource_bind_dep_sync(vma->vm, vma->node.start, + vma->node.size, true); + if (ret) { + i915_vma_resource_free(vma_res); + return ret; + } + + if (vma->resource || !vma_res) { + /* Rebinding with an additional I915_VMA_*_BIND */ + GEM_WARN_ON(!vma_flags); + kfree(vma_res); + } else { + i915_vma_resource_init_from_vma(vma_res, vma); + vma->resource = vma_res; + } trace_i915_vma_bind(vma, bind_flags); if (work && bind_flags & vma->vm->bind_async_flags) { struct dma_fence *prev; - work->vma = vma; + work->vma_res = i915_vma_resource_get(vma->resource); work->cache_level = cache_level; work->flags = bind_flags; @@ -444,17 +495,27 @@ int i915_vma_bind(struct i915_vma *vma, work->base.dma.error = 0; /* enable the queue_work() */ - __i915_gem_object_pin_pages(vma->obj); - work->pinned = i915_gem_object_get(vma->obj); + /* + * If we don't have the refcounted pages list, keep a reference + * on the object to avoid waiting for the async bind to + * complete in the object destruction path. + */ + if (!work->vma_res->bi.pages_rsgt) + work->pinned = i915_gem_object_get(vma->obj); } else { if (vma->obj) { int ret; ret = i915_gem_object_wait_moving_fence(vma->obj, true); - if (ret) + if (ret) { + i915_vma_resource_free(vma->resource); + vma->resource = NULL; + return ret; + } } - vma->ops->bind_vma(vma->vm, NULL, vma, cache_level, bind_flags); + vma->ops->bind_vma(vma->vm, NULL, vma->resource, cache_level, + bind_flags); } atomic_or(bind_flags, &vma->flags); @@ -1224,6 +1285,7 @@ int i915_vma_pin_ww(struct i915_vma *vma, struct i915_gem_ww_ctx *ww, { struct i915_vma_work *work = NULL; struct dma_fence *moving = NULL; + struct i915_vma_resource *vma_res = NULL; intel_wakeref_t wakeref = 0; unsigned int bound; int err; @@ -1278,6 +1340,12 @@ int i915_vma_pin_ww(struct i915_vma *vma, struct i915_gem_ww_ctx *ww, } } + vma_res = i915_vma_resource_alloc(); + if (IS_ERR(vma_res)) { + err = PTR_ERR(vma_res); + goto err_fence; + } + /* * Differentiate between user/kernel vma inside the aliasing-ppgtt. * @@ -1298,7 +1366,7 @@ int i915_vma_pin_ww(struct i915_vma *vma, struct i915_gem_ww_ctx *ww, err = mutex_lock_interruptible_nested(&vma->vm->mutex, !(flags & PIN_GLOBAL)); if (err) - goto err_fence; + goto err_vma_res; /* No more allocations allowed now we hold vm->mutex */ @@ -1339,7 +1407,8 @@ int i915_vma_pin_ww(struct i915_vma *vma, struct i915_gem_ww_ctx *ww, GEM_BUG_ON(!vma->pages); err = i915_vma_bind(vma, vma->obj->cache_level, - flags, work); + flags, work, vma_res); + vma_res = NULL; if (err) goto err_remove; @@ -1362,6 +1431,8 @@ err_active: i915_active_release(&vma->active); err_unlock: mutex_unlock(&vma->vm->mutex); +err_vma_res: + kfree(vma_res); err_fence: if (work) dma_fence_work_commit_imm(&work->base); @@ -1512,6 +1583,7 @@ void i915_vma_release(struct kref *ref) i915_vm_put(vma->vm); i915_active_fini(&vma->active); + GEM_WARN_ON(vma->resource); i915_vma_free(vma); } @@ -1658,8 +1730,11 @@ int _i915_vma_move_to_active(struct i915_vma *vma, return 0; } -void __i915_vma_evict(struct i915_vma *vma) +struct dma_fence *__i915_vma_evict(struct i915_vma *vma, bool async) { + struct i915_vma_resource *vma_res = vma->resource; + struct dma_fence *unbind_fence; + GEM_BUG_ON(i915_vma_is_pinned(vma)); if (i915_vma_is_map_and_fenceable(vma)) { @@ -1690,15 +1765,36 @@ void __i915_vma_evict(struct i915_vma *vma) GEM_BUG_ON(vma->fence); GEM_BUG_ON(i915_vma_has_userfault(vma)); - if (likely(atomic_read(&vma->vm->open))) { - trace_i915_vma_unbind(vma); - vma->ops->unbind_vma(vma->vm, vma); - } + /* Object backend must be async capable. */ + GEM_WARN_ON(async && !vma->resource->bi.pages_rsgt); + + /* If vm is not open, unbind is a nop. */ + vma_res->needs_wakeref = i915_vma_is_bound(vma, I915_VMA_GLOBAL_BIND) && + atomic_read(&vma->vm->open); + trace_i915_vma_unbind(vma); + + unbind_fence = i915_vma_resource_unbind(vma_res); + vma->resource = NULL; + atomic_and(~(I915_VMA_BIND_MASK | I915_VMA_ERROR | I915_VMA_GGTT_WRITE), &vma->flags); i915_vma_detach(vma); + + if (!async && unbind_fence) { + dma_fence_wait(unbind_fence, false); + dma_fence_put(unbind_fence); + unbind_fence = NULL; + } + + /* + * Binding itself may not have completed until the unbind fence signals, + * so don't drop the pages until that happens, unless the resource is + * async_capable. + */ + vma_unbind_pages(vma); + return unbind_fence; } int __i915_vma_unbind(struct i915_vma *vma) @@ -1725,12 +1821,47 @@ int __i915_vma_unbind(struct i915_vma *vma) return ret; GEM_BUG_ON(i915_vma_is_active(vma)); - __i915_vma_evict(vma); + __i915_vma_evict(vma, false); drm_mm_remove_node(&vma->node); /* pairs with i915_vma_release() */ return 0; } +static struct dma_fence *__i915_vma_unbind_async(struct i915_vma *vma) +{ + struct dma_fence *fence; + + lockdep_assert_held(&vma->vm->mutex); + + if (!drm_mm_node_allocated(&vma->node)) + return NULL; + + if (i915_vma_is_pinned(vma) || + &vma->obj->mm.rsgt->table != vma->resource->bi.pages) + return ERR_PTR(-EAGAIN); + + /* + * We probably need to replace this with awaiting the fences of the + * object's dma_resv when the vma active goes away. When doing that + * we need to be careful to not add the vma_resource unbind fence + * immediately to the object's dma_resv, because then unbinding + * the next vma from the object, in case there are many, will + * actually await the unbinding of the previous vmas, which is + * undesirable. + */ + if (i915_sw_fence_await_active(&vma->resource->chain, &vma->active, + I915_ACTIVE_AWAIT_EXCL | + I915_ACTIVE_AWAIT_ACTIVE) < 0) { + return ERR_PTR(-EBUSY); + } + + fence = __i915_vma_evict(vma, true); + + drm_mm_remove_node(&vma->node); /* pairs with i915_vma_release() */ + + return fence; +} + int i915_vma_unbind(struct i915_vma *vma) { struct i915_address_space *vm = vma->vm; @@ -1767,6 +1898,68 @@ out_rpm: return err; } +int i915_vma_unbind_async(struct i915_vma *vma, bool trylock_vm) +{ + struct drm_i915_gem_object *obj = vma->obj; + struct i915_address_space *vm = vma->vm; + intel_wakeref_t wakeref = 0; + struct dma_fence *fence; + int err; + + /* + * We need the dma-resv lock since we add the + * unbind fence to the dma-resv object. + */ + assert_object_held(obj); + + if (!drm_mm_node_allocated(&vma->node)) + return 0; + + if (i915_vma_is_pinned(vma)) { + vma_print_allocator(vma, "is pinned"); + return -EAGAIN; + } + + if (!obj->mm.rsgt) + return -EBUSY; + + err = dma_resv_reserve_shared(obj->base.resv, 1); + if (err) + return -EBUSY; + + /* + * It would be great if we could grab this wakeref from the + * async unbind work if needed, but we can't because it uses + * kmalloc and it's in the dma-fence signalling critical path. + */ + if (i915_vma_is_bound(vma, I915_VMA_GLOBAL_BIND)) + wakeref = intel_runtime_pm_get(&vm->i915->runtime_pm); + + if (trylock_vm && !mutex_trylock(&vm->mutex)) { + err = -EBUSY; + goto out_rpm; + } else if (!trylock_vm) { + err = mutex_lock_interruptible_nested(&vm->mutex, !wakeref); + if (err) + goto out_rpm; + } + + fence = __i915_vma_unbind_async(vma); + mutex_unlock(&vm->mutex); + if (IS_ERR_OR_NULL(fence)) { + err = PTR_ERR_OR_ZERO(fence); + goto out_rpm; + } + + dma_resv_add_shared_fence(obj->base.resv, fence); + dma_fence_put(fence); + +out_rpm: + if (wakeref) + intel_runtime_pm_put(&vm->i915->runtime_pm, wakeref); + return err; +} + struct i915_vma *i915_vma_make_unshrinkable(struct i915_vma *vma) { i915_gem_object_make_unshrinkable(vma->obj); diff --git a/drivers/gpu/drm/i915/i915_vma.h b/drivers/gpu/drm/i915/i915_vma.h index 32719431b3df..a560bae04e7e 100644 --- a/drivers/gpu/drm/i915/i915_vma.h +++ b/drivers/gpu/drm/i915/i915_vma.h @@ -37,6 +37,7 @@ #include "i915_active.h" #include "i915_request.h" +#include "i915_vma_resource.h" #include "i915_vma_types.h" struct i915_vma * @@ -204,16 +205,18 @@ struct i915_vma_work *i915_vma_work(void); int i915_vma_bind(struct i915_vma *vma, enum i915_cache_level cache_level, u32 flags, - struct i915_vma_work *work); + struct i915_vma_work *work, + struct i915_vma_resource *vma_res); bool i915_gem_valid_gtt_space(struct i915_vma *vma, unsigned long color); bool i915_vma_misplaced(const struct i915_vma *vma, u64 size, u64 alignment, u64 flags); void __i915_vma_set_map_and_fenceable(struct i915_vma *vma); void i915_vma_revoke_mmap(struct i915_vma *vma); -void __i915_vma_evict(struct i915_vma *vma); +struct dma_fence *__i915_vma_evict(struct i915_vma *vma, bool async); int __i915_vma_unbind(struct i915_vma *vma); int __must_check i915_vma_unbind(struct i915_vma *vma); +int __must_check i915_vma_unbind_async(struct i915_vma *vma, bool trylock_vm); void i915_vma_unlink_ctx(struct i915_vma *vma); void i915_vma_close(struct i915_vma *vma); void i915_vma_reopen(struct i915_vma *vma); @@ -337,12 +340,6 @@ void __iomem *i915_vma_pin_iomap(struct i915_vma *vma); */ void i915_vma_unpin_iomap(struct i915_vma *vma); -static inline struct page *i915_vma_first_page(struct i915_vma *vma) -{ - GEM_BUG_ON(!vma->pages); - return sg_page(vma->pages->sgl); -} - /** * i915_vma_pin_fence - pin fencing state * @vma: vma to pin fencing for @@ -428,6 +425,26 @@ static inline int i915_vma_sync(struct i915_vma *vma) return i915_active_wait(&vma->active); } +/** + * i915_vma_get_current_resource - Get the current resource of the vma + * @vma: The vma to get the current resource from. + * + * It's illegal to call this function if the vma is not bound. + * + * Return: A refcounted pointer to the current vma resource + * of the vma, assuming the vma is bound. + */ +static inline struct i915_vma_resource * +i915_vma_get_current_resource(struct i915_vma *vma) +{ + return i915_vma_resource_get(vma->resource); +} + +#if IS_ENABLED(CONFIG_DRM_I915_SELFTEST) +void i915_vma_resource_init_from_vma(struct i915_vma_resource *vma_res, + struct i915_vma *vma); +#endif + void i915_vma_module_exit(void); int i915_vma_module_init(void); diff --git a/drivers/gpu/drm/i915/i915_vma_resource.c b/drivers/gpu/drm/i915/i915_vma_resource.c new file mode 100644 index 000000000000..1f41c0c699eb --- /dev/null +++ b/drivers/gpu/drm/i915/i915_vma_resource.c @@ -0,0 +1,417 @@ +// SPDX-License-Identifier: MIT +/* + * Copyright © 2021 Intel Corporation + */ + +#include <linux/interval_tree_generic.h> +#include <linux/slab.h> + +#include "i915_sw_fence.h" +#include "i915_vma_resource.h" +#include "i915_drv.h" +#include "intel_memory_region.h" + +#include "gt/intel_gtt.h" + +static struct kmem_cache *slab_vma_resources; + +/** + * DOC: + * We use a per-vm interval tree to keep track of vma_resources + * scheduled for unbind but not yet unbound. The tree is protected by + * the vm mutex, and nodes are removed just after the unbind fence signals. + * The removal takes the vm mutex from a kernel thread which we need to + * keep in mind so that we don't grab the mutex and try to wait for all + * pending unbinds to complete, because that will temporaryily block many + * of the workqueue threads, and people will get angry. + * + * We should consider using a single ordered fence per VM instead but that + * requires ordering the unbinds and might introduce unnecessary waiting + * for unrelated unbinds. Amount of code will probably be roughly the same + * due to the simplicity of using the interval tree interface. + * + * Another drawback of this interval tree is that the complexity of insertion + * and removal of fences increases as O(ln(pending_unbinds)) instead of + * O(1) for a single fence without interval tree. + */ +#define VMA_RES_START(_node) ((_node)->start) +#define VMA_RES_LAST(_node) ((_node)->start + (_node)->node_size - 1) +INTERVAL_TREE_DEFINE(struct i915_vma_resource, rb, + u64, __subtree_last, + VMA_RES_START, VMA_RES_LAST, static, vma_res_itree); + +/* Callbacks for the unbind dma-fence. */ + +/** + * i915_vma_resource_alloc - Allocate a vma resource + * + * Return: A pointer to a cleared struct i915_vma_resource or + * a -ENOMEM error pointer if allocation fails. + */ +struct i915_vma_resource *i915_vma_resource_alloc(void) +{ + struct i915_vma_resource *vma_res = + kmem_cache_zalloc(slab_vma_resources, GFP_KERNEL); + + return vma_res ? vma_res : ERR_PTR(-ENOMEM); +} + +/** + * i915_vma_resource_free - Free a vma resource + * @vma_res: The vma resource to free. + */ +void i915_vma_resource_free(struct i915_vma_resource *vma_res) +{ + kmem_cache_free(slab_vma_resources, vma_res); +} + +static const char *get_driver_name(struct dma_fence *fence) +{ + return "vma unbind fence"; +} + +static const char *get_timeline_name(struct dma_fence *fence) +{ + return "unbound"; +} + +static void unbind_fence_free_rcu(struct rcu_head *head) +{ + struct i915_vma_resource *vma_res = + container_of(head, typeof(*vma_res), unbind_fence.rcu); + + i915_vma_resource_free(vma_res); +} + +static void unbind_fence_release(struct dma_fence *fence) +{ + struct i915_vma_resource *vma_res = + container_of(fence, typeof(*vma_res), unbind_fence); + + i915_sw_fence_fini(&vma_res->chain); + + call_rcu(&fence->rcu, unbind_fence_free_rcu); +} + +static struct dma_fence_ops unbind_fence_ops = { + .get_driver_name = get_driver_name, + .get_timeline_name = get_timeline_name, + .release = unbind_fence_release, +}; + +static void __i915_vma_resource_unhold(struct i915_vma_resource *vma_res) +{ + struct i915_address_space *vm; + + if (!refcount_dec_and_test(&vma_res->hold_count)) + return; + + dma_fence_signal(&vma_res->unbind_fence); + + vm = vma_res->vm; + if (vma_res->wakeref) + intel_runtime_pm_put(&vm->i915->runtime_pm, vma_res->wakeref); + + vma_res->vm = NULL; + if (!RB_EMPTY_NODE(&vma_res->rb)) { + mutex_lock(&vm->mutex); + vma_res_itree_remove(vma_res, &vm->pending_unbind); + mutex_unlock(&vm->mutex); + } + + if (vma_res->bi.pages_rsgt) + i915_refct_sgt_put(vma_res->bi.pages_rsgt); +} + +/** + * i915_vma_resource_unhold - Unhold the signaling of the vma resource unbind + * fence. + * @vma_res: The vma resource. + * @lockdep_cookie: The lockdep cookie returned from i915_vma_resource_hold. + * + * The function may leave a dma_fence critical section. + */ +void i915_vma_resource_unhold(struct i915_vma_resource *vma_res, + bool lockdep_cookie) +{ + dma_fence_end_signalling(lockdep_cookie); + + if (IS_ENABLED(CONFIG_PROVE_LOCKING)) { + unsigned long irq_flags; + + /* Inefficient open-coded might_lock_irqsave() */ + spin_lock_irqsave(&vma_res->lock, irq_flags); + spin_unlock_irqrestore(&vma_res->lock, irq_flags); + } + + __i915_vma_resource_unhold(vma_res); +} + +/** + * i915_vma_resource_hold - Hold the signaling of the vma resource unbind fence. + * @vma_res: The vma resource. + * @lockdep_cookie: Pointer to a bool serving as a lockdep cooke that should + * be given as an argument to the pairing i915_vma_resource_unhold. + * + * If returning true, the function enters a dma_fence signalling critical + * section if not in one already. + * + * Return: true if holding successful, false if not. + */ +bool i915_vma_resource_hold(struct i915_vma_resource *vma_res, + bool *lockdep_cookie) +{ + bool held = refcount_inc_not_zero(&vma_res->hold_count); + + if (held) + *lockdep_cookie = dma_fence_begin_signalling(); + + return held; +} + +static void i915_vma_resource_unbind_work(struct work_struct *work) +{ + struct i915_vma_resource *vma_res = + container_of(work, typeof(*vma_res), work); + struct i915_address_space *vm = vma_res->vm; + bool lockdep_cookie; + + lockdep_cookie = dma_fence_begin_signalling(); + if (likely(atomic_read(&vm->open))) + vma_res->ops->unbind_vma(vm, vma_res); + + dma_fence_end_signalling(lockdep_cookie); + __i915_vma_resource_unhold(vma_res); + i915_vma_resource_put(vma_res); +} + +static int +i915_vma_resource_fence_notify(struct i915_sw_fence *fence, + enum i915_sw_fence_notify state) +{ + struct i915_vma_resource *vma_res = + container_of(fence, typeof(*vma_res), chain); + struct dma_fence *unbind_fence = + &vma_res->unbind_fence; + + switch (state) { + case FENCE_COMPLETE: + dma_fence_get(unbind_fence); + if (vma_res->immediate_unbind) { + i915_vma_resource_unbind_work(&vma_res->work); + } else { + INIT_WORK(&vma_res->work, i915_vma_resource_unbind_work); + queue_work(system_unbound_wq, &vma_res->work); + } + break; + case FENCE_FREE: + i915_vma_resource_put(vma_res); + break; + } + + return NOTIFY_DONE; +} + +/** + * i915_vma_resource_unbind - Unbind a vma resource + * @vma_res: The vma resource to unbind. + * + * At this point this function does little more than publish a fence that + * signals immediately unless signaling is held back. + * + * Return: A refcounted pointer to a dma-fence that signals when unbinding is + * complete. + */ +struct dma_fence *i915_vma_resource_unbind(struct i915_vma_resource *vma_res) +{ + struct i915_address_space *vm = vma_res->vm; + + /* Reference for the sw fence */ + i915_vma_resource_get(vma_res); + + /* Caller must already have a wakeref in this case. */ + if (vma_res->needs_wakeref) + vma_res->wakeref = intel_runtime_pm_get_if_in_use(&vm->i915->runtime_pm); + + if (atomic_read(&vma_res->chain.pending) <= 1) { + RB_CLEAR_NODE(&vma_res->rb); + vma_res->immediate_unbind = 1; + } else { + vma_res_itree_insert(vma_res, &vma_res->vm->pending_unbind); + } + + i915_sw_fence_commit(&vma_res->chain); + + return &vma_res->unbind_fence; +} + +/** + * __i915_vma_resource_init - Initialize a vma resource. + * @vma_res: The vma resource to initialize + * + * Initializes the private members of a vma resource. + */ +void __i915_vma_resource_init(struct i915_vma_resource *vma_res) +{ + spin_lock_init(&vma_res->lock); + dma_fence_init(&vma_res->unbind_fence, &unbind_fence_ops, + &vma_res->lock, 0, 0); + refcount_set(&vma_res->hold_count, 1); + i915_sw_fence_init(&vma_res->chain, i915_vma_resource_fence_notify); +} + +static void +i915_vma_resource_color_adjust_range(struct i915_address_space *vm, + u64 *start, + u64 *end) +{ + if (i915_vm_has_cache_coloring(vm)) { + if (*start) + *start -= I915_GTT_PAGE_SIZE; + *end += I915_GTT_PAGE_SIZE; + } +} + +/** + * i915_vma_resource_bind_dep_sync - Wait for / sync all unbinds touching a + * certain vm range. + * @vm: The vm to look at. + * @offset: The range start. + * @size: The range size. + * @intr: Whether to wait interrubtible. + * + * The function needs to be called with the vm lock held. + * + * Return: Zero on success, -ERESTARTSYS if interrupted and @intr==true + */ +int i915_vma_resource_bind_dep_sync(struct i915_address_space *vm, + u64 offset, + u64 size, + bool intr) +{ + struct i915_vma_resource *node; + u64 last = offset + size - 1; + + lockdep_assert_held(&vm->mutex); + might_sleep(); + + i915_vma_resource_color_adjust_range(vm, &offset, &last); + node = vma_res_itree_iter_first(&vm->pending_unbind, offset, last); + while (node) { + int ret = dma_fence_wait(&node->unbind_fence, intr); + + if (ret) + return ret; + + node = vma_res_itree_iter_next(node, offset, last); + } + + return 0; +} + +/** + * i915_vma_resource_bind_dep_sync_all - Wait for / sync all unbinds of a vm, + * releasing the vm lock while waiting. + * @vm: The vm to look at. + * + * The function may not be called with the vm lock held. + * Typically this is called at vm destruction to finish any pending + * unbind operations. The vm mutex is released while waiting to avoid + * stalling kernel workqueues trying to grab the mutex. + */ +void i915_vma_resource_bind_dep_sync_all(struct i915_address_space *vm) +{ + struct i915_vma_resource *node; + struct dma_fence *fence; + + do { + fence = NULL; + mutex_lock(&vm->mutex); + node = vma_res_itree_iter_first(&vm->pending_unbind, 0, + U64_MAX); + if (node) + fence = dma_fence_get_rcu(&node->unbind_fence); + mutex_unlock(&vm->mutex); + + if (fence) { + /* + * The wait makes sure the node eventually removes + * itself from the tree. + */ + dma_fence_wait(fence, false); + dma_fence_put(fence); + } + } while (node); +} + +/** + * i915_vma_resource_bind_dep_await - Have a struct i915_sw_fence await all + * pending unbinds in a certain range of a vm. + * @vm: The vm to look at. + * @sw_fence: The struct i915_sw_fence that will be awaiting the unbinds. + * @offset: The range start. + * @size: The range size. + * @intr: Whether to wait interrubtible. + * @gfp: Allocation mode for memory allocations. + * + * The function makes @sw_fence await all pending unbinds in a certain + * vm range before calling the complete notifier. To be able to await + * each individual unbind, the function needs to allocate memory using + * the @gpf allocation mode. If that fails, the function will instead + * wait for the unbind fence to signal, using @intr to judge whether to + * wait interruptible or not. Note that @gfp should ideally be selected so + * as to avoid any expensive memory allocation stalls and rather fail and + * synchronize itself. For now the vm mutex is required when calling this + * function with means that @gfp can't call into direct reclaim. In reality + * this means that during heavy memory pressure, we will sync in this + * function. + * + * Return: Zero on success, -ERESTARTSYS if interrupted and @intr==true + */ +int i915_vma_resource_bind_dep_await(struct i915_address_space *vm, + struct i915_sw_fence *sw_fence, + u64 offset, + u64 size, + bool intr, + gfp_t gfp) +{ + struct i915_vma_resource *node; + u64 last = offset + size - 1; + + lockdep_assert_held(&vm->mutex); + might_alloc(gfp); + might_sleep(); + + i915_vma_resource_color_adjust_range(vm, &offset, &last); + node = vma_res_itree_iter_first(&vm->pending_unbind, offset, last); + while (node) { + int ret; + + ret = i915_sw_fence_await_dma_fence(sw_fence, + &node->unbind_fence, + 0, gfp); + if (ret < 0) { + ret = dma_fence_wait(&node->unbind_fence, intr); + if (ret) + return ret; + } + + node = vma_res_itree_iter_next(node, offset, last); + } + + return 0; +} + +void i915_vma_resource_module_exit(void) +{ + kmem_cache_destroy(slab_vma_resources); +} + +int __init i915_vma_resource_module_init(void) +{ + slab_vma_resources = KMEM_CACHE(i915_vma_resource, SLAB_HWCACHE_ALIGN); + if (!slab_vma_resources) + return -ENOMEM; + + return 0; +} diff --git a/drivers/gpu/drm/i915/i915_vma_resource.h b/drivers/gpu/drm/i915/i915_vma_resource.h new file mode 100644 index 000000000000..25913913baa6 --- /dev/null +++ b/drivers/gpu/drm/i915/i915_vma_resource.h @@ -0,0 +1,234 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright © 2021 Intel Corporation + */ + +#ifndef __I915_VMA_RESOURCE_H__ +#define __I915_VMA_RESOURCE_H__ + +#include <linux/dma-fence.h> +#include <linux/refcount.h> + +#include "i915_gem.h" +#include "i915_scatterlist.h" +#include "i915_sw_fence.h" +#include "intel_runtime_pm.h" + +struct intel_memory_region; + +struct i915_page_sizes { + /** + * The sg mask of the pages sg_table. i.e the mask of + * the lengths for each sg entry. + */ + unsigned int phys; + + /** + * The gtt page sizes we are allowed to use given the + * sg mask and the supported page sizes. This will + * express the smallest unit we can use for the whole + * object, as well as the larger sizes we may be able + * to use opportunistically. + */ + unsigned int sg; +}; + +/** + * struct i915_vma_resource - Snapshotted unbind information. + * @unbind_fence: Fence to mark unbinding complete. Note that this fence + * is not considered published until unbind is scheduled, and as such it + * is illegal to access this fence before scheduled unbind other than + * for refcounting. + * @lock: The @unbind_fence lock. + * @hold_count: Number of holders blocking the fence from finishing. + * The vma itself is keeping a hold, which is released when unbind + * is scheduled. + * @work: Work struct for deferred unbind work. + * @chain: Pointer to struct i915_sw_fence used to await dependencies. + * @rb: Rb node for the vm's pending unbind interval tree. + * @__subtree_last: Interval tree private member. + * @vm: non-refcounted pointer to the vm. This is for internal use only and + * this member is cleared after vm_resource unbind. + * @mr: The memory region of the object pointed to by the vma. + * @ops: Pointer to the backend i915_vma_ops. + * @private: Bind backend private info. + * @start: Offset into the address space of bind range start. + * @node_size: Size of the allocated range manager node. + * @vma_size: Bind size. + * @page_sizes_gtt: Resulting page sizes from the bind operation. + * @bound_flags: Flags indicating binding status. + * @allocated: Backend private data. TODO: Should move into @private. + * @immediate_unbind: Unbind can be done immediately and doesn't need to be + * deferred to a work item awaiting unsignaled fences. This is a hack. + * (dma_fence_work uses a fence flag for this, but this seems slightly + * cleaner). + * + * The lifetime of a struct i915_vma_resource is from a binding request to + * the actual possible asynchronous unbind has completed. + */ +struct i915_vma_resource { + struct dma_fence unbind_fence; + /* See above for description of the lock. */ + spinlock_t lock; + refcount_t hold_count; + struct work_struct work; + struct i915_sw_fence chain; + struct rb_node rb; + u64 __subtree_last; + struct i915_address_space *vm; + intel_wakeref_t wakeref; + + /** + * struct i915_vma_bindinfo - Information needed for async bind + * only but that can be dropped after the bind has taken place. + * Consider making this a separate argument to the bind_vma + * op, coalescing with other arguments like vm, stash, cache_level + * and flags + * @pages: The pages sg-table. + * @page_sizes: Page sizes of the pages. + * @pages_rsgt: Refcounted sg-table when delayed object destruction + * is supported. May be NULL. + * @readonly: Whether the vma should be bound read-only. + * @lmem: Whether the vma points to lmem. + */ + struct i915_vma_bindinfo { + struct sg_table *pages; + struct i915_page_sizes page_sizes; + struct i915_refct_sgt *pages_rsgt; + bool readonly:1; + bool lmem:1; + } bi; + +#if IS_ENABLED(CONFIG_DRM_I915_CAPTURE_ERROR) + struct intel_memory_region *mr; +#endif + const struct i915_vma_ops *ops; + void *private; + u64 start; + u64 node_size; + u64 vma_size; + u32 page_sizes_gtt; + + u32 bound_flags; + bool allocated:1; + bool immediate_unbind:1; + bool needs_wakeref:1; +}; + +bool i915_vma_resource_hold(struct i915_vma_resource *vma_res, + bool *lockdep_cookie); + +void i915_vma_resource_unhold(struct i915_vma_resource *vma_res, + bool lockdep_cookie); + +struct i915_vma_resource *i915_vma_resource_alloc(void); + +void i915_vma_resource_free(struct i915_vma_resource *vma_res); + +struct dma_fence *i915_vma_resource_unbind(struct i915_vma_resource *vma_res); + +void __i915_vma_resource_init(struct i915_vma_resource *vma_res); + +/** + * i915_vma_resource_get - Take a reference on a vma resource + * @vma_res: The vma resource on which to take a reference. + * + * Return: The @vma_res pointer + */ +static inline struct i915_vma_resource +*i915_vma_resource_get(struct i915_vma_resource *vma_res) +{ + dma_fence_get(&vma_res->unbind_fence); + return vma_res; +} + +/** + * i915_vma_resource_put - Release a reference to a struct i915_vma_resource + * @vma_res: The resource + */ +static inline void i915_vma_resource_put(struct i915_vma_resource *vma_res) +{ + dma_fence_put(&vma_res->unbind_fence); +} + +/** + * i915_vma_resource_init - Initialize a vma resource. + * @vma_res: The vma resource to initialize + * @vm: Pointer to the vm. + * @pages: The pages sg-table. + * @page_sizes: Page sizes of the pages. + * @pages_rsgt: Pointer to a struct i915_refct_sgt of an object with + * delayed destruction. + * @readonly: Whether the vma should be bound read-only. + * @lmem: Whether the vma points to lmem. + * @mr: The memory region of the object the vma points to. + * @ops: The backend ops. + * @private: Bind backend private info. + * @start: Offset into the address space of bind range start. + * @node_size: Size of the allocated range manager node. + * @size: Bind size. + * + * Initializes a vma resource allocated using i915_vma_resource_alloc(). + * The reason for having separate allocate and initialize function is that + * initialization may need to be performed from under a lock where + * allocation is not allowed. + */ +static inline void i915_vma_resource_init(struct i915_vma_resource *vma_res, + struct i915_address_space *vm, + struct sg_table *pages, + const struct i915_page_sizes *page_sizes, + struct i915_refct_sgt *pages_rsgt, + bool readonly, + bool lmem, + struct intel_memory_region *mr, + const struct i915_vma_ops *ops, + void *private, + u64 start, + u64 node_size, + u64 size) +{ + __i915_vma_resource_init(vma_res); + vma_res->vm = vm; + vma_res->bi.pages = pages; + vma_res->bi.page_sizes = *page_sizes; + if (pages_rsgt) + vma_res->bi.pages_rsgt = i915_refct_sgt_get(pages_rsgt); + vma_res->bi.readonly = readonly; + vma_res->bi.lmem = lmem; +#if IS_ENABLED(CONFIG_DRM_I915_CAPTURE_ERROR) + vma_res->mr = mr; +#endif + vma_res->ops = ops; + vma_res->private = private; + vma_res->start = start; + vma_res->node_size = node_size; + vma_res->vma_size = size; +} + +static inline void i915_vma_resource_fini(struct i915_vma_resource *vma_res) +{ + GEM_BUG_ON(refcount_read(&vma_res->hold_count) != 1); + if (vma_res->bi.pages_rsgt) + i915_refct_sgt_put(vma_res->bi.pages_rsgt); + i915_sw_fence_fini(&vma_res->chain); +} + +int i915_vma_resource_bind_dep_sync(struct i915_address_space *vm, + u64 first, + u64 last, + bool intr); + +int i915_vma_resource_bind_dep_await(struct i915_address_space *vm, + struct i915_sw_fence *sw_fence, + u64 first, + u64 last, + bool intr, + gfp_t gfp); + +void i915_vma_resource_bind_dep_sync_all(struct i915_address_space *vm); + +void i915_vma_resource_module_exit(void); + +int i915_vma_resource_module_init(void); + +#endif diff --git a/drivers/gpu/drm/i915/i915_vma_snapshot.c b/drivers/gpu/drm/i915/i915_vma_snapshot.c deleted file mode 100644 index 2949ceea9884..000000000000 --- a/drivers/gpu/drm/i915/i915_vma_snapshot.c +++ /dev/null @@ -1,134 +0,0 @@ -// SPDX-License-Identifier: MIT -/* - * Copyright © 2021 Intel Corporation - */ - -#include "i915_vma_snapshot.h" -#include "i915_vma_types.h" -#include "i915_vma.h" - -/** - * i915_vma_snapshot_init - Initialize a struct i915_vma_snapshot from - * a struct i915_vma. - * @vsnap: The i915_vma_snapshot to init. - * @vma: A struct i915_vma used to initialize @vsnap. - * @name: Name associated with the snapshot. The character pointer needs to - * stay alive over the lifitime of the shapsot - */ -void i915_vma_snapshot_init(struct i915_vma_snapshot *vsnap, - struct i915_vma *vma, - const char *name) -{ - if (!i915_vma_is_pinned(vma)) - assert_object_held(vma->obj); - - vsnap->name = name; - vsnap->size = vma->size; - vsnap->obj_size = vma->obj->base.size; - vsnap->gtt_offset = vma->node.start; - vsnap->gtt_size = vma->node.size; - vsnap->page_sizes = vma->page_sizes.gtt; - vsnap->pages = vma->pages; - vsnap->pages_rsgt = NULL; - vsnap->mr = NULL; - if (vma->obj->mm.rsgt) - vsnap->pages_rsgt = i915_refct_sgt_get(vma->obj->mm.rsgt); - vsnap->mr = vma->obj->mm.region; - kref_init(&vsnap->kref); - vsnap->vma_resource = &vma->active; - vsnap->onstack = false; - vsnap->present = true; -} - -/** - * i915_vma_snapshot_init_onstack - Initialize a struct i915_vma_snapshot from - * a struct i915_vma, but avoid kfreeing it on last put. - * @vsnap: The i915_vma_snapshot to init. - * @vma: A struct i915_vma used to initialize @vsnap. - * @name: Name associated with the snapshot. The character pointer needs to - * stay alive over the lifitime of the shapsot - */ -void i915_vma_snapshot_init_onstack(struct i915_vma_snapshot *vsnap, - struct i915_vma *vma, - const char *name) -{ - i915_vma_snapshot_init(vsnap, vma, name); - vsnap->onstack = true; -} - -static void vma_snapshot_release(struct kref *ref) -{ - struct i915_vma_snapshot *vsnap = - container_of(ref, typeof(*vsnap), kref); - - vsnap->present = false; - if (vsnap->pages_rsgt) - i915_refct_sgt_put(vsnap->pages_rsgt); - if (!vsnap->onstack) - kfree(vsnap); -} - -/** - * i915_vma_snapshot_put - Put an i915_vma_snapshot pointer reference - * @vsnap: The pointer reference - */ -void i915_vma_snapshot_put(struct i915_vma_snapshot *vsnap) -{ - kref_put(&vsnap->kref, vma_snapshot_release); -} - -/** - * i915_vma_snapshot_put_onstack - Put an onstcak i915_vma_snapshot pointer - * reference and varify that the structure is released - * @vsnap: The pointer reference - * - * This function is intended to be paired with a i915_vma_init_onstack() - * and should be called before exiting the scope that declared or - * freeing the structure that embedded @vsnap to verify that all references - * have been released. - */ -void i915_vma_snapshot_put_onstack(struct i915_vma_snapshot *vsnap) -{ - if (!kref_put(&vsnap->kref, vma_snapshot_release)) - GEM_BUG_ON(1); -} - -/** - * i915_vma_snapshot_resource_pin - Temporarily block the memory the - * vma snapshot is pointing to from being released. - * @vsnap: The vma snapshot. - * @lockdep_cookie: Pointer to bool needed for lockdep support. This needs - * to be passed to the paired i915_vma_snapshot_resource_unpin. - * - * This function will temporarily try to hold up a fence or similar structure - * and will therefore enter a fence signaling critical section. - * - * Return: true if we succeeded in blocking the memory from being released, - * false otherwise. - */ -bool i915_vma_snapshot_resource_pin(struct i915_vma_snapshot *vsnap, - bool *lockdep_cookie) -{ - bool pinned = i915_active_acquire_if_busy(vsnap->vma_resource); - - if (pinned) - *lockdep_cookie = dma_fence_begin_signalling(); - - return pinned; -} - -/** - * i915_vma_snapshot_resource_unpin - Unblock vma snapshot memory from - * being released. - * @vsnap: The vma snapshot. - * @lockdep_cookie: Cookie returned from matching i915_vma_resource_pin(). - * - * Might leave a fence signalling critical section and signal a fence. - */ -void i915_vma_snapshot_resource_unpin(struct i915_vma_snapshot *vsnap, - bool lockdep_cookie) -{ - dma_fence_end_signalling(lockdep_cookie); - - return i915_active_release(vsnap->vma_resource); -} diff --git a/drivers/gpu/drm/i915/i915_vma_snapshot.h b/drivers/gpu/drm/i915/i915_vma_snapshot.h deleted file mode 100644 index 940581df4622..000000000000 --- a/drivers/gpu/drm/i915/i915_vma_snapshot.h +++ /dev/null @@ -1,112 +0,0 @@ -/* SPDX-License-Identifier: MIT */ -/* - * Copyright © 2021 Intel Corporation - */ -#ifndef _I915_VMA_SNAPSHOT_H_ -#define _I915_VMA_SNAPSHOT_H_ - -#include <linux/kref.h> -#include <linux/slab.h> -#include <linux/types.h> - -struct i915_active; -struct i915_refct_sgt; -struct i915_vma; -struct intel_memory_region; -struct sg_table; - -/** - * DOC: Simple utilities for snapshotting GPU vma metadata, later used for - * error capture. Vi use a separate header for this to avoid issues due to - * recursive header includes. - */ - -/** - * struct i915_vma_snapshot - Snapshot of vma metadata. - * @size: The vma size in bytes. - * @obj_size: The size of the underlying object in bytes. - * @gtt_offset: The gtt offset the vma is bound to. - * @gtt_size: The size in bytes allocated for the vma in the GTT. - * @pages: The struct sg_table pointing to the pages bound. - * @pages_rsgt: The refcounted sg_table holding the reference for @pages if any. - * @mr: The memory region pointed for the pages bound. - * @kref: Reference for this structure. - * @vma_resource: FIXME: A means to keep the unbind fence from signaling. - * Temporarily while we have only sync unbinds, and still use the vma - * active, we use that. With async unbinding we need a signaling refcount - * for the unbind fence. - * @page_sizes: The vma GTT page sizes information. - * @onstack: Whether the structure shouldn't be freed on final put. - * @present: Whether the structure is present and initialized. - */ -struct i915_vma_snapshot { - const char *name; - size_t size; - size_t obj_size; - size_t gtt_offset; - size_t gtt_size; - struct sg_table *pages; - struct i915_refct_sgt *pages_rsgt; - struct intel_memory_region *mr; - struct kref kref; - struct i915_active *vma_resource; - u32 page_sizes; - bool onstack:1; - bool present:1; -}; - -void i915_vma_snapshot_init(struct i915_vma_snapshot *vsnap, - struct i915_vma *vma, - const char *name); - -void i915_vma_snapshot_init_onstack(struct i915_vma_snapshot *vsnap, - struct i915_vma *vma, - const char *name); - -void i915_vma_snapshot_put(struct i915_vma_snapshot *vsnap); - -void i915_vma_snapshot_put_onstack(struct i915_vma_snapshot *vsnap); - -bool i915_vma_snapshot_resource_pin(struct i915_vma_snapshot *vsnap, - bool *lockdep_cookie); - -void i915_vma_snapshot_resource_unpin(struct i915_vma_snapshot *vsnap, - bool lockdep_cookie); - -/** - * i915_vma_snapshot_alloc - Allocate a struct i915_vma_snapshot - * @gfp: Allocation mode. - * - * Return: A pointer to a struct i915_vma_snapshot if successful. - * NULL otherwise. - */ -static inline struct i915_vma_snapshot *i915_vma_snapshot_alloc(gfp_t gfp) -{ - return kmalloc(sizeof(struct i915_vma_snapshot), gfp); -} - -/** - * i915_vma_snapshot_get - Take a reference on a struct i915_vma_snapshot - * - * Return: A pointer to a struct i915_vma_snapshot. - */ -static inline struct i915_vma_snapshot * -i915_vma_snapshot_get(struct i915_vma_snapshot *vsnap) -{ - kref_get(&vsnap->kref); - return vsnap; -} - -/** - * i915_vma_snapshot_present - Whether a struct i915_vma_snapshot is - * present and initialized. - * - * Return: true if present and initialized; false otherwise. - */ -static inline bool -i915_vma_snapshot_present(const struct i915_vma_snapshot *vsnap) -{ - return vsnap && vsnap->present; -} - -#endif diff --git a/drivers/gpu/drm/i915/i915_vma_types.h b/drivers/gpu/drm/i915/i915_vma_types.h index ca575e129ced..88370dadca82 100644 --- a/drivers/gpu/drm/i915/i915_vma_types.h +++ b/drivers/gpu/drm/i915/i915_vma_types.h @@ -95,6 +95,8 @@ enum i915_cache_level; * */ +struct i915_vma_resource; + struct intel_remapped_plane_info { /* in gtt pages */ u32 offset:31; @@ -247,22 +249,20 @@ struct i915_vma { #define I915_VMA_BIND_MASK (I915_VMA_GLOBAL_BIND | I915_VMA_LOCAL_BIND) -#define I915_VMA_ALLOC_BIT 12 - -#define I915_VMA_ERROR_BIT 13 +#define I915_VMA_ERROR_BIT 12 #define I915_VMA_ERROR ((int)BIT(I915_VMA_ERROR_BIT)) -#define I915_VMA_GGTT_BIT 14 -#define I915_VMA_CAN_FENCE_BIT 15 -#define I915_VMA_USERFAULT_BIT 16 -#define I915_VMA_GGTT_WRITE_BIT 17 +#define I915_VMA_GGTT_BIT 13 +#define I915_VMA_CAN_FENCE_BIT 14 +#define I915_VMA_USERFAULT_BIT 15 +#define I915_VMA_GGTT_WRITE_BIT 16 #define I915_VMA_GGTT ((int)BIT(I915_VMA_GGTT_BIT)) #define I915_VMA_CAN_FENCE ((int)BIT(I915_VMA_CAN_FENCE_BIT)) #define I915_VMA_USERFAULT ((int)BIT(I915_VMA_USERFAULT_BIT)) #define I915_VMA_GGTT_WRITE ((int)BIT(I915_VMA_GGTT_WRITE_BIT)) -#define I915_VMA_SCANOUT_BIT 18 +#define I915_VMA_SCANOUT_BIT 17 #define I915_VMA_SCANOUT ((int)BIT(I915_VMA_SCANOUT_BIT)) struct i915_active active; @@ -291,6 +291,9 @@ struct i915_vma { struct list_head evict_link; struct list_head closed_link; + + /** The async vma resource. Protected by the vm_mutex */ + struct i915_vma_resource *resource; }; #endif diff --git a/drivers/gpu/drm/i915/selftests/i915_gem.c b/drivers/gpu/drm/i915/selftests/i915_gem.c index b5576888cd78..1628b81d0a35 100644 --- a/drivers/gpu/drm/i915/selftests/i915_gem.c +++ b/drivers/gpu/drm/i915/selftests/i915_gem.c @@ -41,7 +41,7 @@ static int switch_to_context(struct i915_gem_context *ctx) static void trash_stolen(struct drm_i915_private *i915) { - struct i915_ggtt *ggtt = &i915->ggtt; + struct i915_ggtt *ggtt = to_gt(i915)->ggtt; const u64 slot = ggtt->error_capture.start; const resource_size_t size = resource_size(&i915->dsm); unsigned long page; @@ -99,7 +99,7 @@ static void igt_pm_suspend(struct drm_i915_private *i915) intel_wakeref_t wakeref; with_intel_runtime_pm(&i915->runtime_pm, wakeref) { - i915_ggtt_suspend(&i915->ggtt); + i915_ggtt_suspend(to_gt(i915)->ggtt); i915_gem_suspend_late(i915); } } @@ -109,7 +109,7 @@ static void igt_pm_hibernate(struct drm_i915_private *i915) intel_wakeref_t wakeref; with_intel_runtime_pm(&i915->runtime_pm, wakeref) { - i915_ggtt_suspend(&i915->ggtt); + i915_ggtt_suspend(to_gt(i915)->ggtt); i915_gem_freeze(i915); i915_gem_freeze_late(i915); @@ -125,7 +125,7 @@ static void igt_pm_resume(struct drm_i915_private *i915) * that runtime-pm just works. */ with_intel_runtime_pm(&i915->runtime_pm, wakeref) { - i915_ggtt_resume(&i915->ggtt); + i915_ggtt_resume(to_gt(i915)->ggtt); i915_gem_resume(i915); } } diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c index 575705c3bce9..076d860ce01a 100644 --- a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c +++ b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c @@ -32,6 +32,7 @@ #include "i915_random.h" #include "i915_selftest.h" +#include "i915_vma_resource.h" #include "mock_drm.h" #include "mock_gem_device.h" @@ -238,11 +239,11 @@ static int lowlevel_hole(struct i915_address_space *vm, unsigned long end_time) { I915_RND_STATE(seed_prng); - struct i915_vma *mock_vma; + struct i915_vma_resource *mock_vma_res; unsigned int size; - mock_vma = kzalloc(sizeof(*mock_vma), GFP_KERNEL); - if (!mock_vma) + mock_vma_res = kzalloc(sizeof(*mock_vma_res), GFP_KERNEL); + if (!mock_vma_res) return -ENOMEM; /* Keep creating larger objects until one cannot fit into the hole */ @@ -268,7 +269,7 @@ static int lowlevel_hole(struct i915_address_space *vm, break; } while (count >>= 1); if (!count) { - kfree(mock_vma); + kfree(mock_vma_res); return -ENOMEM; } GEM_BUG_ON(!order); @@ -342,12 +343,12 @@ alloc_vm_end: break; } - mock_vma->pages = obj->mm.pages; - mock_vma->node.size = BIT_ULL(size); - mock_vma->node.start = addr; + mock_vma_res->bi.pages = obj->mm.pages; + mock_vma_res->node_size = BIT_ULL(size); + mock_vma_res->start = addr; with_intel_runtime_pm(vm->gt->uncore->rpm, wakeref) - vm->insert_entries(vm, mock_vma, + vm->insert_entries(vm, mock_vma_res, I915_CACHE_NONE, 0); } count = n; @@ -370,7 +371,7 @@ alloc_vm_end: cleanup_freed_objects(vm->i915); } - kfree(mock_vma); + kfree(mock_vma_res); return 0; } @@ -1122,7 +1123,7 @@ static int exercise_ggtt(struct drm_i915_private *i915, u64 hole_start, u64 hole_end, unsigned long end_time)) { - struct i915_ggtt *ggtt = &i915->ggtt; + struct i915_ggtt *ggtt = to_gt(i915)->ggtt; u64 hole_start, hole_end, last = 0; struct drm_mm_node *node; IGT_TIMEOUT(end_time); @@ -1182,7 +1183,7 @@ static int igt_ggtt_page(void *arg) const unsigned int count = PAGE_SIZE/sizeof(u32); I915_RND_STATE(prng); struct drm_i915_private *i915 = arg; - struct i915_ggtt *ggtt = &i915->ggtt; + struct i915_ggtt *ggtt = to_gt(i915)->ggtt; struct drm_i915_gem_object *obj; intel_wakeref_t wakeref; struct drm_mm_node tmp; @@ -1279,6 +1280,7 @@ static void track_vma_bind(struct i915_vma *vma) atomic_set(&vma->pages_count, I915_VMA_PAGES_ACTIVE); __i915_gem_object_pin_pages(obj); vma->pages = obj->mm.pages; + vma->resource->bi.pages = vma->pages; mutex_lock(&vma->vm->mutex); list_add_tail(&vma->vm_link, &vma->vm->bound_list); @@ -1336,6 +1338,33 @@ static int igt_mock_drunk(void *arg) return exercise_mock(ggtt->vm.i915, drunk_hole); } +static int reserve_gtt_with_resource(struct i915_vma *vma, u64 offset) +{ + struct i915_address_space *vm = vma->vm; + struct i915_vma_resource *vma_res; + struct drm_i915_gem_object *obj = vma->obj; + int err; + + vma_res = i915_vma_resource_alloc(); + if (IS_ERR(vma_res)) + return PTR_ERR(vma_res); + + mutex_lock(&vm->mutex); + err = i915_gem_gtt_reserve(vm, &vma->node, obj->base.size, + offset, + obj->cache_level, + 0); + if (!err) { + i915_vma_resource_init_from_vma(vma_res, vma); + vma->resource = vma_res; + } else { + kfree(vma_res); + } + mutex_unlock(&vm->mutex); + + return err; +} + static int igt_gtt_reserve(void *arg) { struct i915_ggtt *ggtt = arg; @@ -1370,20 +1399,13 @@ static int igt_gtt_reserve(void *arg) } list_add(&obj->st_link, &objects); - vma = i915_vma_instance(obj, &ggtt->vm, NULL); if (IS_ERR(vma)) { err = PTR_ERR(vma); goto out; } - mutex_lock(&ggtt->vm.mutex); - err = i915_gem_gtt_reserve(&ggtt->vm, &vma->node, - obj->base.size, - total, - obj->cache_level, - 0); - mutex_unlock(&ggtt->vm.mutex); + err = reserve_gtt_with_resource(vma, total); if (err) { pr_err("i915_gem_gtt_reserve (pass 1) failed at %llu/%llu with err=%d\n", total, ggtt->vm.total, err); @@ -1429,13 +1451,7 @@ static int igt_gtt_reserve(void *arg) goto out; } - mutex_lock(&ggtt->vm.mutex); - err = i915_gem_gtt_reserve(&ggtt->vm, &vma->node, - obj->base.size, - total, - obj->cache_level, - 0); - mutex_unlock(&ggtt->vm.mutex); + err = reserve_gtt_with_resource(vma, total); if (err) { pr_err("i915_gem_gtt_reserve (pass 2) failed at %llu/%llu with err=%d\n", total, ggtt->vm.total, err); @@ -1476,13 +1492,7 @@ static int igt_gtt_reserve(void *arg) 2 * I915_GTT_PAGE_SIZE, I915_GTT_MIN_ALIGNMENT); - mutex_lock(&ggtt->vm.mutex); - err = i915_gem_gtt_reserve(&ggtt->vm, &vma->node, - obj->base.size, - offset, - obj->cache_level, - 0); - mutex_unlock(&ggtt->vm.mutex); + err = reserve_gtt_with_resource(vma, offset); if (err) { pr_err("i915_gem_gtt_reserve (pass 3) failed at %llu/%llu with err=%d\n", total, ggtt->vm.total, err); @@ -1509,6 +1519,31 @@ out: return err; } +static int insert_gtt_with_resource(struct i915_vma *vma) +{ + struct i915_address_space *vm = vma->vm; + struct i915_vma_resource *vma_res; + struct drm_i915_gem_object *obj = vma->obj; + int err; + + vma_res = i915_vma_resource_alloc(); + if (IS_ERR(vma_res)) + return PTR_ERR(vma_res); + + mutex_lock(&vm->mutex); + err = i915_gem_gtt_insert(vm, &vma->node, obj->base.size, 0, + obj->cache_level, 0, vm->total, 0); + if (!err) { + i915_vma_resource_init_from_vma(vma_res, vma); + vma->resource = vma_res; + } else { + kfree(vma_res); + } + mutex_unlock(&vm->mutex); + + return err; +} + static int igt_gtt_insert(void *arg) { struct i915_ggtt *ggtt = arg; @@ -1593,12 +1628,7 @@ static int igt_gtt_insert(void *arg) goto out; } - mutex_lock(&ggtt->vm.mutex); - err = i915_gem_gtt_insert(&ggtt->vm, &vma->node, - obj->base.size, 0, obj->cache_level, - 0, ggtt->vm.total, - 0); - mutex_unlock(&ggtt->vm.mutex); + err = insert_gtt_with_resource(vma); if (err == -ENOSPC) { /* maxed out the GGTT space */ i915_gem_object_put(obj); @@ -1653,12 +1683,7 @@ static int igt_gtt_insert(void *arg) goto out; } - mutex_lock(&ggtt->vm.mutex); - err = i915_gem_gtt_insert(&ggtt->vm, &vma->node, - obj->base.size, 0, obj->cache_level, - 0, ggtt->vm.total, - 0); - mutex_unlock(&ggtt->vm.mutex); + err = insert_gtt_with_resource(vma); if (err) { pr_err("i915_gem_gtt_insert (pass 2) failed at %llu/%llu with err=%d\n", total, ggtt->vm.total, err); @@ -1702,12 +1727,7 @@ static int igt_gtt_insert(void *arg) goto out; } - mutex_lock(&ggtt->vm.mutex); - err = i915_gem_gtt_insert(&ggtt->vm, &vma->node, - obj->base.size, 0, obj->cache_level, - 0, ggtt->vm.total, - 0); - mutex_unlock(&ggtt->vm.mutex); + err = insert_gtt_with_resource(vma); if (err) { pr_err("i915_gem_gtt_insert (pass 3) failed at %llu/%llu with err=%d\n", total, ggtt->vm.total, err); @@ -1737,26 +1757,28 @@ int i915_gem_gtt_mock_selftests(void) SUBTEST(igt_gtt_insert), }; struct drm_i915_private *i915; - struct i915_ggtt *ggtt; + struct intel_gt *gt; int err; i915 = mock_gem_device(); if (!i915) return -ENOMEM; - ggtt = kmalloc(sizeof(*ggtt), GFP_KERNEL); - if (!ggtt) { - err = -ENOMEM; + /* allocate the ggtt */ + err = intel_gt_assign_ggtt(to_gt(i915)); + if (err) goto out_put; - } - mock_init_ggtt(i915, ggtt); - err = i915_subtests(tests, ggtt); + gt = to_gt(i915); + + mock_init_ggtt(gt); + + err = i915_subtests(tests, gt->ggtt); mock_device_flush(i915); i915_gem_drain_freed_objects(i915); - mock_fini_ggtt(ggtt); - kfree(ggtt); + mock_fini_ggtt(gt->ggtt); + out_put: mock_destroy_device(i915); return err; @@ -1939,6 +1961,7 @@ static int igt_cs_tlb(void *arg) struct i915_vm_pt_stash stash = {}; struct i915_request *rq; struct i915_gem_ww_ctx ww; + struct i915_vma_resource *vma_res; u64 offset; offset = igt_random_offset(&prng, @@ -1959,6 +1982,13 @@ static int igt_cs_tlb(void *arg) if (err) goto end; + vma_res = i915_vma_resource_alloc(); + if (IS_ERR(vma_res)) { + i915_vma_put_pages(vma); + err = PTR_ERR(vma_res); + goto end; + } + i915_gem_ww_ctx_init(&ww, false); retry: err = i915_vm_lock_objects(vm, &ww); @@ -1980,33 +2010,41 @@ end_ww: goto retry; } i915_gem_ww_ctx_fini(&ww); - if (err) + if (err) { + kfree(vma_res); goto end; + } + i915_vma_resource_init_from_vma(vma_res, vma); /* Prime the TLB with the dummy pages */ for (i = 0; i < count; i++) { - vma->node.start = offset + i * PAGE_SIZE; - vm->insert_entries(vm, vma, I915_CACHE_NONE, 0); + vma_res->start = offset + i * PAGE_SIZE; + vm->insert_entries(vm, vma_res, I915_CACHE_NONE, + 0); - rq = submit_batch(ce, vma->node.start); + rq = submit_batch(ce, vma_res->start); if (IS_ERR(rq)) { err = PTR_ERR(rq); + i915_vma_resource_fini(vma_res); + kfree(vma_res); goto end; } i915_request_put(rq); } - + i915_vma_resource_fini(vma_res); i915_vma_put_pages(vma); err = context_sync(ce); if (err) { pr_err("%s: dummy setup timed out\n", ce->engine->name); + kfree(vma_res); goto end; } vma = i915_vma_instance(act, vm, NULL); if (IS_ERR(vma)) { + kfree(vma_res); err = PTR_ERR(vma); goto end; } @@ -2014,19 +2052,22 @@ end_ww: i915_gem_object_lock(act, NULL); err = i915_vma_get_pages(vma); i915_gem_object_unlock(act); - if (err) + if (err) { + kfree(vma_res); goto end; + } + i915_vma_resource_init_from_vma(vma_res, vma); /* Replace the TLB with target batches */ for (i = 0; i < count; i++) { struct i915_request *rq; u32 *cs = batch + i * 64 / sizeof(*cs); u64 addr; - vma->node.start = offset + i * PAGE_SIZE; - vm->insert_entries(vm, vma, I915_CACHE_NONE, 0); + vma_res->start = offset + i * PAGE_SIZE; + vm->insert_entries(vm, vma_res, I915_CACHE_NONE, 0); - addr = vma->node.start + i * 64; + addr = vma_res->start + i * 64; cs[4] = MI_NOOP; cs[6] = lower_32_bits(addr); cs[7] = upper_32_bits(addr); @@ -2035,6 +2076,8 @@ end_ww: rq = submit_batch(ce, addr); if (IS_ERR(rq)) { err = PTR_ERR(rq); + i915_vma_resource_fini(vma_res); + kfree(vma_res); goto end; } @@ -2051,6 +2094,8 @@ end_ww: } end_spin(batch, count - 1); + i915_vma_resource_fini(vma_res); + kfree(vma_res); i915_vma_put_pages(vma); err = context_sync(ce); @@ -2114,7 +2159,7 @@ int i915_gem_gtt_live_selftests(struct drm_i915_private *i915) SUBTEST(igt_cs_tlb), }; - GEM_BUG_ON(offset_in_page(i915->ggtt.vm.total)); + GEM_BUG_ON(offset_in_page(to_gt(i915)->ggtt->vm.total)); return i915_subtests(tests, i915); } diff --git a/drivers/gpu/drm/i915/selftests/i915_request.c b/drivers/gpu/drm/i915/selftests/i915_request.c index 92a859b34190..7f66f6d299b2 100644 --- a/drivers/gpu/drm/i915/selftests/i915_request.c +++ b/drivers/gpu/drm/i915/selftests/i915_request.c @@ -843,7 +843,7 @@ static struct i915_vma *empty_batch(struct drm_i915_private *i915) intel_gt_chipset_flush(to_gt(i915)); - vma = i915_vma_instance(obj, &i915->ggtt.vm, NULL); + vma = i915_vma_instance(obj, &to_gt(i915)->ggtt->vm, NULL); if (IS_ERR(vma)) { err = PTR_ERR(vma); goto err; diff --git a/drivers/gpu/drm/i915/selftests/i915_vma.c b/drivers/gpu/drm/i915/selftests/i915_vma.c index 5c5809dfe9b2..de37cfa4c65f 100644 --- a/drivers/gpu/drm/i915/selftests/i915_vma.c +++ b/drivers/gpu/drm/i915/selftests/i915_vma.c @@ -922,26 +922,28 @@ int i915_vma_mock_selftests(void) SUBTEST(igt_vma_partial), }; struct drm_i915_private *i915; - struct i915_ggtt *ggtt; + struct intel_gt *gt; int err; i915 = mock_gem_device(); if (!i915) return -ENOMEM; - ggtt = kmalloc(sizeof(*ggtt), GFP_KERNEL); - if (!ggtt) { - err = -ENOMEM; + /* allocate the ggtt */ + err = intel_gt_assign_ggtt(to_gt(i915)); + if (err) goto out_put; - } - mock_init_ggtt(i915, ggtt); - err = i915_subtests(tests, ggtt); + gt = to_gt(i915); + + mock_init_ggtt(gt); + + err = i915_subtests(tests, gt->ggtt); mock_device_flush(i915); i915_gem_drain_freed_objects(i915); - mock_fini_ggtt(ggtt); - kfree(ggtt); + mock_fini_ggtt(gt->ggtt); + out_put: mock_destroy_device(i915); return err; @@ -982,7 +984,7 @@ static int igt_vma_remapped_gtt(void *arg) intel_wakeref_t wakeref; int err = 0; - if (!i915_ggtt_has_aperture(&i915->ggtt)) + if (!i915_ggtt_has_aperture(to_gt(i915)->ggtt)) return 0; obj = i915_gem_object_create_internal(i915, 10 * 10 * PAGE_SIZE); diff --git a/drivers/gpu/drm/i915/selftests/mock_gem_device.c b/drivers/gpu/drm/i915/selftests/mock_gem_device.c index 8aa7b1d33865..28a0f054009a 100644 --- a/drivers/gpu/drm/i915/selftests/mock_gem_device.c +++ b/drivers/gpu/drm/i915/selftests/mock_gem_device.c @@ -69,7 +69,7 @@ static void mock_device_release(struct drm_device *dev) i915_gem_drain_workqueue(i915); i915_gem_drain_freed_objects(i915); - mock_fini_ggtt(&i915->ggtt); + mock_fini_ggtt(to_gt(i915)->ggtt); destroy_workqueue(i915->wq); intel_region_ttm_device_fini(i915); @@ -194,8 +194,13 @@ struct drm_i915_private *mock_gem_device(void) mock_init_contexts(i915); - mock_init_ggtt(i915, &i915->ggtt); - to_gt(i915)->vm = i915_vm_get(&i915->ggtt.vm); + /* allocate the ggtt */ + ret = intel_gt_assign_ggtt(to_gt(i915)); + if (ret) + goto err_unlock; + + mock_init_ggtt(to_gt(i915)); + to_gt(i915)->vm = i915_vm_get(&to_gt(i915)->ggtt->vm); mkwrite_device_info(i915)->platform_engine_mask = BIT(0); to_gt(i915)->info.engine_mask = BIT(0); diff --git a/drivers/gpu/drm/i915/selftests/mock_gtt.c b/drivers/gpu/drm/i915/selftests/mock_gtt.c index 1802baf80a17..568840e7ca66 100644 --- a/drivers/gpu/drm/i915/selftests/mock_gtt.c +++ b/drivers/gpu/drm/i915/selftests/mock_gtt.c @@ -33,23 +33,23 @@ static void mock_insert_page(struct i915_address_space *vm, } static void mock_insert_entries(struct i915_address_space *vm, - struct i915_vma *vma, + struct i915_vma_resource *vma_res, enum i915_cache_level level, u32 flags) { } static void mock_bind_ppgtt(struct i915_address_space *vm, struct i915_vm_pt_stash *stash, - struct i915_vma *vma, + struct i915_vma_resource *vma_res, enum i915_cache_level cache_level, u32 flags) { GEM_BUG_ON(flags & I915_VMA_GLOBAL_BIND); - set_bit(I915_VMA_LOCAL_BIND_BIT, __i915_vma_flags(vma)); + vma_res->bound_flags |= flags; } static void mock_unbind_ppgtt(struct i915_address_space *vm, - struct i915_vma *vma) + struct i915_vma_resource *vma_res) { } @@ -93,23 +93,23 @@ struct i915_ppgtt *mock_ppgtt(struct drm_i915_private *i915, const char *name) static void mock_bind_ggtt(struct i915_address_space *vm, struct i915_vm_pt_stash *stash, - struct i915_vma *vma, + struct i915_vma_resource *vma_res, enum i915_cache_level cache_level, u32 flags) { } static void mock_unbind_ggtt(struct i915_address_space *vm, - struct i915_vma *vma) + struct i915_vma_resource *vma_res) { } -void mock_init_ggtt(struct drm_i915_private *i915, struct i915_ggtt *ggtt) +void mock_init_ggtt(struct intel_gt *gt) { - memset(ggtt, 0, sizeof(*ggtt)); + struct i915_ggtt *ggtt = gt->ggtt; - ggtt->vm.gt = to_gt(i915); - ggtt->vm.i915 = i915; + ggtt->vm.gt = gt; + ggtt->vm.i915 = gt->i915; ggtt->vm.is_ggtt = true; ggtt->gmadr = (struct resource) DEFINE_RES_MEM(0, 2048 * PAGE_SIZE); @@ -128,7 +128,6 @@ void mock_init_ggtt(struct drm_i915_private *i915, struct i915_ggtt *ggtt) ggtt->vm.vma_ops.unbind_vma = mock_unbind_ggtt; i915_address_space_init(&ggtt->vm, VM_CLASS_GGTT); - to_gt(i915)->ggtt = ggtt; } void mock_fini_ggtt(struct i915_ggtt *ggtt) diff --git a/drivers/gpu/drm/i915/selftests/mock_gtt.h b/drivers/gpu/drm/i915/selftests/mock_gtt.h index e3f224f43beb..d6eb90bd7f3f 100644 --- a/drivers/gpu/drm/i915/selftests/mock_gtt.h +++ b/drivers/gpu/drm/i915/selftests/mock_gtt.h @@ -27,8 +27,9 @@ struct drm_i915_private; struct i915_ggtt; +struct intel_gt; -void mock_init_ggtt(struct drm_i915_private *i915, struct i915_ggtt *ggtt); +void mock_init_ggtt(struct intel_gt *gt); void mock_fini_ggtt(struct i915_ggtt *ggtt); struct i915_ppgtt *mock_ppgtt(struct drm_i915_private *i915, const char *name); |