diff options
| author | Rodrigo Vivi <rodrigo.vivi@intel.com> | 2023-03-28 10:30:57 -0400 |
|---|---|---|
| committer | Rodrigo Vivi <rodrigo.vivi@intel.com> | 2023-03-28 10:30:57 -0400 |
| commit | cecdd52a3dd312564f81a39df08378b7b39a2654 (patch) | |
| tree | 149c75714b5a8c9688b32a264b75b8c033106da4 /drivers/gpu/drm/i915 | |
| parent | 42b4c479025d92b2a4869bd233f20159ae9ce692 (diff) | |
| parent | 46f28427f6f824b6cff06fa025a55350b7de454a (diff) | |
Merge drm/drm-next into drm-intel-next
Catch up with 6.3-rc cycle...
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Diffstat (limited to 'drivers/gpu/drm/i915')
89 files changed, 2030 insertions, 1161 deletions
diff --git a/drivers/gpu/drm/i915/Kconfig b/drivers/gpu/drm/i915/Kconfig index 9c0990c0ec87..98f4e44976e0 100644 --- a/drivers/gpu/drm/i915/Kconfig +++ b/drivers/gpu/drm/i915/Kconfig @@ -118,18 +118,16 @@ config DRM_I915_USERPTR If in doubt, say "Y". -config DRM_I915_GVT - bool - config DRM_I915_GVT_KVMGT tristate "Enable KVM host support Intel GVT-g graphics virtualization" depends on DRM_I915 depends on X86 depends on 64BIT depends on KVM - depends on VFIO_MDEV + depends on VFIO select DRM_I915_GVT select KVM_EXTERNAL_WRITE_TRACKING + select VFIO_MDEV help Choose this option if you want to enable Intel GVT-g graphics @@ -171,3 +169,6 @@ menu "drm/i915 Unstable Evolution" depends on DRM_I915 source "drivers/gpu/drm/i915/Kconfig.unstable" endmenu + +config DRM_I915_GVT + bool diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c index 37d03380b844..b53a1d969344 100644 --- a/drivers/gpu/drm/i915/display/intel_display.c +++ b/drivers/gpu/drm/i915/display/intel_display.c @@ -5893,6 +5893,10 @@ int intel_modeset_all_pipes(struct intel_atomic_state *state, if (ret) return ret; + ret = intel_dp_mst_add_topology_state_for_crtc(state, crtc); + if (ret) + return ret; + ret = intel_atomic_add_affected_planes(state, crtc); if (ret) return ret; diff --git a/drivers/gpu/drm/i915/display/intel_dp_mst.c b/drivers/gpu/drm/i915/display/intel_dp_mst.c index ddc65adb4c00..a860cbc5dbea 100644 --- a/drivers/gpu/drm/i915/display/intel_dp_mst.c +++ b/drivers/gpu/drm/i915/display/intel_dp_mst.c @@ -531,8 +531,14 @@ static void intel_mst_disable_dp(struct intel_atomic_state *state, struct intel_dp *intel_dp = &dig_port->dp; struct intel_connector *connector = to_intel_connector(old_conn_state->connector); - struct drm_dp_mst_topology_state *mst_state = - drm_atomic_get_mst_topology_state(&state->base, &intel_dp->mst_mgr); + struct drm_dp_mst_topology_state *old_mst_state = + drm_atomic_get_old_mst_topology_state(&state->base, &intel_dp->mst_mgr); + struct drm_dp_mst_topology_state *new_mst_state = + drm_atomic_get_new_mst_topology_state(&state->base, &intel_dp->mst_mgr); + const struct drm_dp_mst_atomic_payload *old_payload = + drm_atomic_get_mst_payload_state(old_mst_state, connector->port); + struct drm_dp_mst_atomic_payload *new_payload = + drm_atomic_get_mst_payload_state(new_mst_state, connector->port); struct drm_i915_private *i915 = to_i915(connector->base.dev); drm_dbg_kms(&i915->drm, "active links %d\n", @@ -540,8 +546,8 @@ static void intel_mst_disable_dp(struct intel_atomic_state *state, intel_hdcp_disable(intel_mst->connector); - drm_dp_remove_payload(&intel_dp->mst_mgr, mst_state, - drm_atomic_get_mst_payload_state(mst_state, connector->port)); + drm_dp_remove_payload(&intel_dp->mst_mgr, new_mst_state, + old_payload, new_payload); intel_audio_codec_disable(encoder, old_crtc_state, old_conn_state); } @@ -1230,3 +1236,64 @@ bool intel_dp_mst_is_slave_trans(const struct intel_crtc_state *crtc_state) return crtc_state->mst_master_transcoder != INVALID_TRANSCODER && crtc_state->mst_master_transcoder != crtc_state->cpu_transcoder; } + +/** + * intel_dp_mst_add_topology_state_for_connector - add MST topology state for a connector + * @state: atomic state + * @connector: connector to add the state for + * @crtc: the CRTC @connector is attached to + * + * Add the MST topology state for @connector to @state. + * + * Returns 0 on success, negative error code on failure. + */ +static int +intel_dp_mst_add_topology_state_for_connector(struct intel_atomic_state *state, + struct intel_connector *connector, + struct intel_crtc *crtc) +{ + struct drm_dp_mst_topology_state *mst_state; + + if (!connector->mst_port) + return 0; + + mst_state = drm_atomic_get_mst_topology_state(&state->base, + &connector->mst_port->mst_mgr); + if (IS_ERR(mst_state)) + return PTR_ERR(mst_state); + + mst_state->pending_crtc_mask |= drm_crtc_mask(&crtc->base); + + return 0; +} + +/** + * intel_dp_mst_add_topology_state_for_crtc - add MST topology state for a CRTC + * @state: atomic state + * @crtc: CRTC to add the state for + * + * Add the MST topology state for @crtc to @state. + * + * Returns 0 on success, negative error code on failure. + */ +int intel_dp_mst_add_topology_state_for_crtc(struct intel_atomic_state *state, + struct intel_crtc *crtc) +{ + struct drm_connector *_connector; + struct drm_connector_state *conn_state; + int i; + + for_each_new_connector_in_state(&state->base, _connector, conn_state, i) { + struct intel_connector *connector = to_intel_connector(_connector); + int ret; + + if (conn_state->crtc != &crtc->base) + continue; + + ret = intel_dp_mst_add_topology_state_for_connector(state, connector, crtc); + if (ret) + return ret; + } + + return 0; +} diff --git a/drivers/gpu/drm/i915/display/intel_dp_mst.h b/drivers/gpu/drm/i915/display/intel_dp_mst.h index f7301de6cdfb..f1815bb72267 100644 --- a/drivers/gpu/drm/i915/display/intel_dp_mst.h +++ b/drivers/gpu/drm/i915/display/intel_dp_mst.h @@ -8,6 +8,8 @@ #include <linux/types.h> +struct intel_atomic_state; +struct intel_crtc; struct intel_crtc_state; struct intel_digital_port; struct intel_dp; @@ -18,5 +20,7 @@ int intel_dp_mst_encoder_active_links(struct intel_digital_port *dig_port); bool intel_dp_mst_is_master_trans(const struct intel_crtc_state *crtc_state); bool intel_dp_mst_is_slave_trans(const struct intel_crtc_state *crtc_state); bool intel_dp_mst_source_support(struct intel_dp *intel_dp); +int intel_dp_mst_add_topology_state_for_crtc(struct intel_atomic_state *state, + struct intel_crtc *crtc); #endif /* __INTEL_DP_MST_H__ */ diff --git a/drivers/gpu/drm/i915/display/intel_fbdev.c b/drivers/gpu/drm/i915/display/intel_fbdev.c index a0d0f14d8c14..673bcdfb7ff6 100644 --- a/drivers/gpu/drm/i915/display/intel_fbdev.c +++ b/drivers/gpu/drm/i915/display/intel_fbdev.c @@ -364,6 +364,7 @@ static void intel_fbdev_destroy(struct intel_fbdev *ifbdev) if (ifbdev->fb) drm_framebuffer_remove(&ifbdev->fb->base); + drm_fb_helper_unprepare(&ifbdev->helper); kfree(ifbdev); } @@ -544,10 +545,12 @@ int intel_fbdev_init(struct drm_device *dev) return -ENOMEM; mutex_init(&ifbdev->hpd_lock); - drm_fb_helper_prepare(dev, &ifbdev->helper, &intel_fb_helper_funcs); + drm_fb_helper_prepare(dev, &ifbdev->helper, 32, &intel_fb_helper_funcs); - if (!intel_fbdev_init_bios(dev, ifbdev)) - ifbdev->preferred_bpp = 32; + if (intel_fbdev_init_bios(dev, ifbdev)) + ifbdev->helper.preferred_bpp = ifbdev->preferred_bpp; + else + ifbdev->preferred_bpp = ifbdev->helper.preferred_bpp; ret = drm_fb_helper_init(dev, &ifbdev->helper); if (ret) { @@ -566,8 +569,7 @@ static void intel_fbdev_initial_config(void *data, async_cookie_t cookie) struct intel_fbdev *ifbdev = data; /* Due to peculiar init order wrt to hpd handling this is separate. */ - if (drm_fb_helper_initial_config(&ifbdev->helper, - ifbdev->preferred_bpp)) + if (drm_fb_helper_initial_config(&ifbdev->helper)) intel_fbdev_unregister(to_i915(ifbdev->helper.dev)); } diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c index 454e73a433c8..6d639ca24dfb 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_context.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c @@ -1096,16 +1096,15 @@ static struct i915_gem_engines *alloc_engines(unsigned int count) static struct i915_gem_engines *default_engines(struct i915_gem_context *ctx, struct intel_sseu rcs_sseu) { - const struct intel_gt *gt = to_gt(ctx->i915); + const unsigned int max = I915_NUM_ENGINES; struct intel_engine_cs *engine; struct i915_gem_engines *e, *err; - enum intel_engine_id id; - e = alloc_engines(I915_NUM_ENGINES); + e = alloc_engines(max); if (!e) return ERR_PTR(-ENOMEM); - for_each_engine(engine, gt, id) { + for_each_uabi_engine(engine, ctx->i915) { struct intel_context *ce; struct intel_sseu sseu = {}; int ret; @@ -1113,7 +1112,7 @@ static struct i915_gem_engines *default_engines(struct i915_gem_context *ctx, if (engine->legacy_idx == INVALID_ENGINE) continue; - GEM_BUG_ON(engine->legacy_idx >= I915_NUM_ENGINES); + GEM_BUG_ON(engine->legacy_idx >= max); GEM_BUG_ON(e->engines[engine->legacy_idx]); ce = intel_context_create(engine); @@ -1861,11 +1860,19 @@ static int get_ppgtt(struct drm_i915_file_private *file_priv, vm = ctx->vm; GEM_BUG_ON(!vm); + /* + * Get a reference for the allocated handle. Once the handle is + * visible in the vm_xa table, userspace could try to close it + * from under our feet, so we need to hold the extra reference + * first. + */ + i915_vm_get(vm); + err = xa_alloc(&file_priv->vm_xa, &id, vm, xa_limit_32b, GFP_KERNEL); - if (err) + if (err) { + i915_vm_put(vm); return err; - - i915_vm_get(vm); + } GEM_BUG_ON(id == 0); /* reserved for invalid/unassigned ppgtt */ args->value = id; diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c index 94d86ee24693..9dce2957b4e5 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c @@ -3486,6 +3486,13 @@ err_request: eb.composite_fence : &eb.requests[0]->fence); + if (unlikely(eb.gem_context->syncobj)) { + drm_syncobj_replace_fence(eb.gem_context->syncobj, + eb.composite_fence ? + eb.composite_fence : + &eb.requests[0]->fence); + } + if (out_fence) { if (err == 0) { fd_install(out_fence_fd, out_fence->file); @@ -3497,13 +3504,6 @@ err_request: } } - if (unlikely(eb.gem_context->syncobj)) { - drm_syncobj_replace_fence(eb.gem_context->syncobj, - eb.composite_fence ? - eb.composite_fence : - &eb.requests[0]->fence); - } - if (!out_fence && eb.composite_fence) dma_fence_put(eb.composite_fence); diff --git a/drivers/gpu/drm/i915/gem/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/i915_gem_mman.c index 4f69bff63068..d3c1dee16af2 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_mman.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_mman.c @@ -697,7 +697,7 @@ insert: GEM_BUG_ON(lookup_mmo(obj, mmap_type) != mmo); out: if (file) - drm_vma_node_allow(&mmo->vma_node, file); + drm_vma_node_allow_once(&mmo->vma_node, file); return mmo; err: @@ -979,7 +979,7 @@ int i915_gem_mmap(struct file *filp, struct vm_area_struct *vma) i915_gem_object_put(obj); return -EINVAL; } - vma->vm_flags &= ~VM_MAYWRITE; + vm_flags_clear(vma, VM_MAYWRITE); } anon = mmap_singleton(to_i915(dev)); @@ -988,7 +988,7 @@ int i915_gem_mmap(struct file *filp, struct vm_area_struct *vma) return PTR_ERR(anon); } - vma->vm_flags |= VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP | VM_IO; + vm_flags_set(vma, VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP | VM_IO); /* * We keep the ref on mmo->obj, not vm_file, but we require diff --git a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c index 114443096841..37d1efcd3ca6 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c @@ -596,7 +596,7 @@ static int shmem_object_init(struct intel_memory_region *mem, mapping_set_gfp_mask(mapping, mask); GEM_BUG_ON(!(mapping_gfp_mask(mapping) & __GFP_RECLAIM)); - i915_gem_object_init(obj, &i915_gem_shmem_ops, &lock_class, 0); + i915_gem_object_init(obj, &i915_gem_shmem_ops, &lock_class, flags); obj->mem_flags |= I915_BO_FLAG_STRUCT_PAGE; obj->write_domain = I915_GEM_DOMAIN_CPU; obj->read_domains = I915_GEM_DOMAIN_CPU; diff --git a/drivers/gpu/drm/i915/gem/i915_gem_stolen.c b/drivers/gpu/drm/i915/gem/i915_gem_stolen.c index 90a967374b1a..d8e06e783e30 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_stolen.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_stolen.c @@ -909,7 +909,7 @@ i915_gem_stolen_lmem_setup(struct drm_i915_private *i915, u16 type, dsm_base = intel_uncore_read64(uncore, GEN12_DSMBASE) & GEN12_BDSM_MASK; if (WARN_ON(lmem_size < dsm_base)) return ERR_PTR(-ENODEV); - dsm_size = lmem_size - dsm_base; + dsm_size = ALIGN_DOWN(lmem_size - dsm_base, SZ_1M); } io_size = dsm_size; diff --git a/drivers/gpu/drm/i915/gem/i915_gem_tiling.c b/drivers/gpu/drm/i915/gem/i915_gem_tiling.c index 04bb909acdec..a049ca0b7980 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_tiling.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_tiling.c @@ -305,10 +305,6 @@ i915_gem_object_set_tiling(struct drm_i915_gem_object *obj, spin_unlock(&obj->vma.lock); obj->tiling_and_stride = tiling | stride; - i915_gem_object_unlock(obj); - - /* Force the fence to be reacquired for GTT access */ - i915_gem_object_release_mmap_gtt(obj); /* Try to preallocate memory required to save swizzling on put-pages */ if (i915_gem_object_needs_bit17_swizzle(obj)) { @@ -321,6 +317,11 @@ i915_gem_object_set_tiling(struct drm_i915_gem_object *obj, obj->bit_17 = NULL; } + i915_gem_object_unlock(obj); + + /* Force the fence to be reacquired for GTT access */ + i915_gem_object_release_mmap_gtt(obj); + return 0; } diff --git a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c index 8cfed1bef629..341b94672abc 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c @@ -274,8 +274,6 @@ static struct ttm_tt *i915_ttm_tt_create(struct ttm_buffer_object *bo, { struct drm_i915_private *i915 = container_of(bo->bdev, typeof(*i915), bdev); - struct ttm_resource_manager *man = - ttm_manager_type(bo->bdev, bo->resource->mem_type); struct drm_i915_gem_object *obj = i915_ttm_to_gem(bo); unsigned long ccs_pages = 0; enum ttm_caching caching; @@ -289,8 +287,8 @@ static struct ttm_tt *i915_ttm_tt_create(struct ttm_buffer_object *bo, if (!i915_tt) return NULL; - if (obj->flags & I915_BO_ALLOC_CPU_CLEAR && - man->use_tt) + if (obj->flags & I915_BO_ALLOC_CPU_CLEAR && (!bo->resource || + ttm_manager_type(bo->bdev, bo->resource->mem_type)->use_tt)) page_flags |= TTM_TT_FLAG_ZERO_ALLOC; caching = i915_ttm_select_tt_caching(obj); @@ -474,7 +472,7 @@ static int i915_ttm_shrink(struct drm_i915_gem_object *obj, unsigned int flags) struct ttm_placement place = {}; int ret; - if (!bo->ttm || bo->resource->mem_type != TTM_PL_SYSTEM) + if (!bo->ttm || i915_ttm_cpu_maps_iomem(bo->resource)) return 0; GEM_BUG_ON(!i915_tt->is_shmem); @@ -513,7 +511,13 @@ static void i915_ttm_delete_mem_notify(struct ttm_buffer_object *bo) { struct drm_i915_gem_object *obj = i915_ttm_to_gem(bo); - if (bo->resource && !i915_ttm_is_ghost_object(bo)) { + /* + * This gets called twice by ttm, so long as we have a ttm resource or + * ttm_tt then we can still safely call this. Due to pipeline-gutting, + * we maybe have NULL bo->resource, but in that case we should always + * have a ttm alive (like if the pages are swapped out). + */ + if ((bo->resource || bo->ttm) && !i915_ttm_is_ghost_object(bo)) { __i915_gem_object_pages_fini(obj); i915_ttm_free_cached_io_rsgt(obj); } @@ -1058,7 +1062,27 @@ static vm_fault_t vm_fault_ttm(struct vm_fault *vmf) return VM_FAULT_SIGBUS; } - if (!i915_ttm_resource_mappable(bo->resource)) { + /* + * This must be swapped out with shmem ttm_tt (pipeline-gutting). + * Calling ttm_bo_validate() here with TTM_PL_SYSTEM should only go as + * far as far doing a ttm_bo_move_null(), which should skip all the + * other junk. + */ + if (!bo->resource) { + struct ttm_operation_ctx ctx = { + .interruptible = true, + .no_wait_gpu = true, /* should be idle already */ + }; + int err; + + GEM_BUG_ON(!bo->ttm || !(bo->ttm->page_flags & TTM_TT_FLAG_SWAPPED)); + + err = ttm_bo_validate(bo, i915_ttm_sys_placement(), &ctx); + if (err) { + dma_resv_unlock(bo->base.resv); + return VM_FAULT_SIGBUS; + } + } else if (!i915_ttm_resource_mappable(bo->resource)) { int err = -ENODEV; int i; diff --git a/drivers/gpu/drm/i915/gem/i915_gem_ttm.h b/drivers/gpu/drm/i915/gem/i915_gem_ttm.h index 2a94a99ef76b..f8f6bed1b297 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_ttm.h +++ b/drivers/gpu/drm/i915/gem/i915_gem_ttm.h @@ -98,7 +98,7 @@ static inline bool i915_ttm_gtt_binds_lmem(struct ttm_resource *mem) static inline bool i915_ttm_cpu_maps_iomem(struct ttm_resource *mem) { /* Once / if we support GGTT, this is also false for cached ttm_tts */ - return mem->mem_type != I915_PL_SYSTEM; + return mem && mem->mem_type != I915_PL_SYSTEM; } bool i915_ttm_resource_mappable(struct ttm_resource *res); 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 2ebaaf4d663c..d030182ca176 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_ttm_move.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_ttm_move.c @@ -103,7 +103,27 @@ void i915_ttm_adjust_gem_after_move(struct drm_i915_gem_object *obj) { struct ttm_buffer_object *bo = i915_gem_to_ttm(obj); unsigned int cache_level; + unsigned int mem_flags; unsigned int i; + int mem_type; + + /* + * We might have been purged (or swapped out) if the resource is NULL, + * in which case the SYSTEM placement is the closest match to describe + * the current domain. If the object is ever used in this state then we + * will require moving it again. + */ + if (!bo->resource) { + mem_flags = I915_BO_FLAG_STRUCT_PAGE; + mem_type = I915_PL_SYSTEM; + cache_level = I915_CACHE_NONE; + } else { + mem_flags = i915_ttm_cpu_maps_iomem(bo->resource) ? I915_BO_FLAG_IOMEM : + I915_BO_FLAG_STRUCT_PAGE; + mem_type = bo->resource->mem_type; + cache_level = i915_ttm_cache_level(to_i915(bo->base.dev), bo->resource, + bo->ttm); + } /* * If object was moved to an allowable region, update the object @@ -111,11 +131,11 @@ void i915_ttm_adjust_gem_after_move(struct drm_i915_gem_object *obj) * in an allowable region, it's evicted and we don't update the * object region. */ - if (intel_region_to_ttm_type(obj->mm.region) != bo->resource->mem_type) { + if (intel_region_to_ttm_type(obj->mm.region) != mem_type) { for (i = 0; i < obj->mm.n_placements; ++i) { struct intel_memory_region *mr = obj->mm.placements[i]; - if (intel_region_to_ttm_type(mr) == bo->resource->mem_type && + if (intel_region_to_ttm_type(mr) == mem_type && mr != obj->mm.region) { i915_gem_object_release_memory_region(obj); i915_gem_object_init_memory_region(obj, mr); @@ -125,12 +145,8 @@ void i915_ttm_adjust_gem_after_move(struct drm_i915_gem_object *obj) } obj->mem_flags &= ~(I915_BO_FLAG_STRUCT_PAGE | I915_BO_FLAG_IOMEM); + obj->mem_flags |= mem_flags; - obj->mem_flags |= i915_ttm_cpu_maps_iomem(bo->resource) ? I915_BO_FLAG_IOMEM : - I915_BO_FLAG_STRUCT_PAGE; - - cache_level = i915_ttm_cache_level(to_i915(bo->base.dev), bo->resource, - bo->ttm); i915_gem_object_set_cache_coherency(obj, cache_level); } @@ -565,6 +581,32 @@ int i915_ttm_move(struct ttm_buffer_object *bo, bool evict, return 0; } + if (!bo->resource) { + if (dst_mem->mem_type != TTM_PL_SYSTEM) { + hop->mem_type = TTM_PL_SYSTEM; + hop->flags = TTM_PL_FLAG_TEMPORARY; + return -EMULTIHOP; + } + + /* + * This is only reached when first creating the object, or if + * the object was purged or swapped out (pipeline-gutting). For + * the former we can safely skip all of the below since we are + * only using a dummy SYSTEM placement here. And with the latter + * we will always re-enter here with bo->resource set correctly + * (as per the above), since this is part of a multi-hop + * sequence, where at the end we can do the move for real. + * + * The special case here is when the dst_mem is TTM_PL_SYSTEM, + * which doens't require any kind of move, so it should be safe + * to skip all the below and call ttm_bo_move_null() here, where + * the caller in __i915_ttm_get_pages() will take care of the + * rest, since we should have a valid ttm_tt. + */ + ttm_bo_move_null(bo, dst_mem); + return 0; + } + ret = i915_ttm_move_notify(bo); if (ret) return ret; @@ -669,6 +711,10 @@ int i915_gem_obj_copy_ttm(struct drm_i915_gem_object *dst, assert_object_held(dst); assert_object_held(src); + + if (GEM_WARN_ON(!src_bo->resource || !dst_bo->resource)) + return -EINVAL; + i915_deps_init(&deps, GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN); ret = dma_resv_reserve_fences(src_bo->base.resv, 1); diff --git a/drivers/gpu/drm/i915/gem/i915_gem_ttm_pm.c b/drivers/gpu/drm/i915/gem/i915_gem_ttm_pm.c index 7e67742bc65e..dfe39c8e74d8 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_ttm_pm.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_ttm_pm.c @@ -53,7 +53,7 @@ static int i915_ttm_backup(struct i915_gem_apply_to_region *apply, unsigned int flags; int err = 0; - if (bo->resource->mem_type == I915_PL_SYSTEM || obj->ttm.backup) + if (!i915_ttm_cpu_maps_iomem(bo->resource) || obj->ttm.backup) return 0; if (pm_apply->allow_gpu && i915_gem_object_evictable(obj)) @@ -187,7 +187,10 @@ static int i915_ttm_restore(struct i915_gem_apply_to_region *apply, return err; /* Content may have been swapped. */ - err = ttm_tt_populate(backup_bo->bdev, backup_bo->ttm, &ctx); + if (!backup_bo->resource) + err = ttm_bo_validate(backup_bo, i915_ttm_sys_placement(), &ctx); + if (!err) + err = ttm_tt_populate(backup_bo->bdev, backup_bo->ttm, &ctx); if (!err) { err = i915_gem_obj_copy_ttm(obj, backup, pm_apply->allow_gpu, false); 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 3bb1f7f0110e..ff81af4c8202 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 @@ -108,31 +108,30 @@ struct tiled_blits { u32 height; }; -static bool supports_x_tiling(const struct drm_i915_private *i915) +static bool fastblit_supports_x_tiling(const struct drm_i915_private *i915) { int gen = GRAPHICS_VER(i915); + /* XY_FAST_COPY_BLT does not exist on pre-gen9 platforms */ + drm_WARN_ON(&i915->drm, gen < 9); + if (gen < 12) return true; - if (!HAS_LMEM(i915) || IS_DG1(i915)) + if (GRAPHICS_VER_FULL(i915) < IP_VER(12, 50)) return false; - return true; + return HAS_DISPLAY(i915); } static bool fast_blit_ok(const struct blit_buffer *buf) { - int gen = GRAPHICS_VER(buf->vma->vm->i915); - - if (gen < 9) + /* XY_FAST_COPY_BLT does not exist on pre-gen9 platforms */ + if (GRAPHICS_VER(buf->vma->vm->i915) < 9) return false; - if (gen < 12) - return true; - /* filter out platforms with unsupported X-tile support in fastblit */ - if (buf->tiling == CLIENT_TILING_X && !supports_x_tiling(buf->vma->vm->i915)) + if (buf->tiling == CLIENT_TILING_X && !fastblit_supports_x_tiling(buf->vma->vm->i915)) return false; return true; diff --git a/drivers/gpu/drm/i915/gt/intel_context.c b/drivers/gpu/drm/i915/gt/intel_context.c index e94365b08f1e..2aa63ec521b8 100644 --- a/drivers/gpu/drm/i915/gt/intel_context.c +++ b/drivers/gpu/drm/i915/gt/intel_context.c @@ -528,7 +528,7 @@ retry: return rq; } -struct i915_request *intel_context_find_active_request(struct intel_context *ce) +struct i915_request *intel_context_get_active_request(struct intel_context *ce) { struct intel_context *parent = intel_context_to_parent(ce); struct i915_request *rq, *active = NULL; @@ -552,6 +552,8 @@ struct i915_request *intel_context_find_active_request(struct intel_context *ce) active = rq; } + if (active) + active = i915_request_get_rcu(active); spin_unlock_irqrestore(&parent->guc_state.lock, flags); return active; diff --git a/drivers/gpu/drm/i915/gt/intel_context.h b/drivers/gpu/drm/i915/gt/intel_context.h index fb62b7b8cbcd..0a8d553da3f4 100644 --- a/drivers/gpu/drm/i915/gt/intel_context.h +++ b/drivers/gpu/drm/i915/gt/intel_context.h @@ -268,8 +268,7 @@ int intel_context_prepare_remote_request(struct intel_context *ce, struct i915_request *intel_context_create_request(struct intel_context *ce); -struct i915_request * -intel_context_find_active_request(struct intel_context *ce); +struct i915_request *intel_context_get_active_request(struct intel_context *ce); static inline bool intel_context_is_barrier(const struct intel_context *ce) { diff --git a/drivers/gpu/drm/i915/gt/intel_engine.h b/drivers/gpu/drm/i915/gt/intel_engine.h index 0e24af5efee9..b58c30ac8ef0 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine.h +++ b/drivers/gpu/drm/i915/gt/intel_engine.h @@ -250,8 +250,8 @@ void intel_engine_dump_active_requests(struct list_head *requests, ktime_t intel_engine_get_busy_time(struct intel_engine_cs *engine, ktime_t *now); -struct i915_request * -intel_engine_execlist_find_hung_request(struct intel_engine_cs *engine); +void intel_engine_get_hung_entity(struct intel_engine_cs *engine, + struct intel_context **ce, struct i915_request **rq); u32 intel_engine_context_size(struct intel_gt *gt, u8 class); struct intel_context * diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c index 922f1bb22dc6..ad3413242100 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c +++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c @@ -9,6 +9,7 @@ #include "gem/i915_gem_context.h" #include "gem/i915_gem_internal.h" +#include "gt/intel_gt_print.h" #include "gt/intel_gt_regs.h" #include "i915_cmd_parser.h" @@ -1143,12 +1144,130 @@ err_put: return ret; } +static int intel_engine_init_tlb_invalidation(struct intel_engine_cs *engine) +{ + static const union intel_engine_tlb_inv_reg gen8_regs[] = { + [RENDER_CLASS].reg = GEN8_RTCR, + [VIDEO_DECODE_CLASS].reg = GEN8_M1TCR, /* , GEN8_M2TCR */ + [VIDEO_ENHANCEMENT_CLASS].reg = GEN8_VTCR, + [COPY_ENGINE_CLASS].reg = GEN8_BTCR, + }; + static const union intel_engine_tlb_inv_reg gen12_regs[] = { + [RENDER_CLASS].reg = GEN12_GFX_TLB_INV_CR, + [VIDEO_DECODE_CLASS].reg = GEN12_VD_TLB_INV_CR, + [VIDEO_ENHANCEMENT_CLASS].reg = GEN12_VE_TLB_INV_CR, + [COPY_ENGINE_CLASS].reg = GEN12_BLT_TLB_INV_CR, + [COMPUTE_CLASS].reg = GEN12_COMPCTX_TLB_INV_CR, + }; + static const union intel_engine_tlb_inv_reg xehp_regs[] = { + [RENDER_CLASS].mcr_reg = XEHP_GFX_TLB_INV_CR, + [VIDEO_DECODE_CLASS].mcr_reg = XEHP_VD_TLB_INV_CR, + [VIDEO_ENHANCEMENT_CLASS].mcr_reg = XEHP_VE_TLB_INV_CR, + [COPY_ENGINE_CLASS].mcr_reg = XEHP_BLT_TLB_INV_CR, + [COMPUTE_CLASS].mcr_reg = XEHP_COMPCTX_TLB_INV_CR, + }; + static const union intel_engine_tlb_inv_reg xelpmp_regs[] = { + [VIDEO_DECODE_CLASS].reg = GEN12_VD_TLB_INV_CR, + [VIDEO_ENHANCEMENT_CLASS].reg = GEN12_VE_TLB_INV_CR, + [OTHER_CLASS].reg = XELPMP_GSC_TLB_INV_CR, + }; + struct drm_i915_private *i915 = engine->i915; + const unsigned int instance = engine->instance; + const unsigned int class = engine->class; + const union intel_engine_tlb_inv_reg *regs; + union intel_engine_tlb_inv_reg reg; + unsigned int num = 0; + u32 val; + + /* + * New platforms should not be added with catch-all-newer (>=) + * condition so that any later platform added triggers the below warning + * and in turn mandates a human cross-check of whether the invalidation + * flows have compatible semantics. + * + * For instance with the 11.00 -> 12.00 transition three out of five + * respective engine registers were moved to masked type. Then after the + * 12.00 -> 12.50 transition multi cast handling is required too. + */ + + if (engine->gt->type == GT_MEDIA) { + if (MEDIA_VER_FULL(i915) == IP_VER(13, 0)) { + regs = xelpmp_regs; + num = ARRAY_SIZE(xelpmp_regs); + } + } else { + if (GRAPHICS_VER_FULL(i915) == IP_VER(12, 71) || + GRAPHICS_VER_FULL(i915) == IP_VER(12, 70) || + GRAPHICS_VER_FULL(i915) == IP_VER(12, 50) || + GRAPHICS_VER_FULL(i915) == IP_VER(12, 55)) { + regs = xehp_regs; + num = ARRAY_SIZE(xehp_regs); + } else if (GRAPHICS_VER_FULL(i915) == IP_VER(12, 0) || + GRAPHICS_VER_FULL(i915) == IP_VER(12, 10)) { + regs = gen12_regs; + num = ARRAY_SIZE(gen12_regs); + } else if (GRAPHICS_VER(i915) >= 8 && GRAPHICS_VER(i915) <= 11) { + regs = gen8_regs; + num = ARRAY_SIZE(gen8_regs); + } else if (GRAPHICS_VER(i915) < 8) { + return 0; + } + } + + if (gt_WARN_ONCE(engine->gt, !num, + "Platform does not implement TLB invalidation!")) + return -ENODEV; + + if (gt_WARN_ON_ONCE(engine->gt, + class >= num || + (!regs[class].reg.reg && + !regs[class].mcr_reg.reg))) + return -ERANGE; + + reg = regs[class]; + + if (regs == xelpmp_regs && class == OTHER_CLASS) { + /* + * There's only a single GSC instance, but it uses register bit + * 1 instead of either 0 or OTHER_GSC_INSTANCE. + */ + GEM_WARN_ON(instance != OTHER_GSC_INSTANCE); + val = 1; + } else if (regs == gen8_regs && class == VIDEO_DECODE_CLASS && instance == 1) { + reg.reg = GEN8_M2TCR; + val = 0; + } else { + val = instance; + } + + val = BIT(val); + + engine->tlb_inv.mcr = regs == xehp_regs; + engine->tlb_inv.reg = reg; + engine->tlb_inv.done = val; + + if (GRAPHICS_VER(i915) >= 12 && + (engine->class == VIDEO_DECODE_CLASS || + engine->class == VIDEO_ENHANCEMENT_CLASS || + engine->class == COMPUTE_CLASS || + engine->class == OTHER_CLASS)) + engine->tlb_inv.request = _MASKED_BIT_ENABLE(val); + else + engine->tlb_inv.request = val; + + return 0; +} + static int engine_setup_common(struct intel_engine_cs *engine) { int err; init_llist_head(&engine->barrier_tasks); + err = intel_engine_init_tlb_invalidation(engine); + if (err) + return err; + err = init_status_page(engine); if (err) return err; @@ -1584,11 +1703,8 @@ static u32 __cs_pending_mi_force_wakes(struct intel_engine_cs *engine) }; u32 val; - if (!_reg[engine->id].reg) { - drm_err(&engine->i915->drm, - "MSG IDLE undefined for engine id %u\n", engine->id); + if (!_reg[engine->id].reg) return 0; - } val = intel_uncore_read(engine->uncore, _reg[engine->id]); @@ -1942,13 +2058,13 @@ static const char *repr_timer(const struct timer_list *t) static void intel_engine_print_registers(struct intel_engine_cs *engine, struct drm_printer *m) { - struct drm_i915_private *dev_priv = engine->i915; + struct drm_i915_private *i915 = engine->i915; struct intel_engine_execlists * const execlists = &engine->execlists; u64 addr; - if (engine->id == RENDER_CLASS && IS_GRAPHICS_VER(dev_priv, 4, 7)) + if (engine->id == RENDER_CLASS && IS_GRAPHICS_VER(i915, 4, 7)) drm_printf(m, "\tCCID: 0x%08x\n", ENGINE_READ(engine, CCID)); - if (HAS_EXECLISTS(dev_priv)) { + if (HAS_EXECLISTS(i915)) { drm_printf(m, "\tEL_STAT_HI: 0x%08x\n", ENGINE_READ(engine, RING_EXECLIST_STATUS_HI)); drm_printf(m, "\tEL_STAT_LO: 0x%08x\n", @@ -1969,7 +2085,7 @@ static void intel_engine_print_registers(struct intel_engine_cs *engine, ENGINE_READ(engine, RING_MI_MODE) & (MODE_IDLE) ? " [idle]" : ""); } - if (GRAPHICS_VER(dev_priv) >= 6) { + if (GRAPHICS_VER(i915) >= 6) { drm_printf(m, "\tRING_IMR: 0x%08x\n", ENGINE_READ(engine, RING_IMR)); drm_printf(m, "\tRING_ESR: 0x%08x\n", @@ -1986,15 +2102,15 @@ static void intel_engine_print_registers(struct intel_engine_cs *engine, addr = intel_engine_get_last_batch_head(engine); drm_printf(m, "\tBBADDR: 0x%08x_%08x\n", upper_32_bits(addr), lower_32_bits(addr)); - if (GRAPHICS_VER(dev_priv) >= 8) + if (GRAPHICS_VER(i915) >= 8) addr = ENGINE_READ64(engine, RING_DMA_FADD, RING_DMA_FADD_UDW); - else if (GRAPHICS_VER(dev_priv) >= 4) + else if (GRAPHICS_VER(i915) >= 4) addr = ENGINE_READ(engine, RING_DMA_FADD); else addr = ENGINE_READ(engine, DMA_FADD_I8XX); drm_printf(m, "\tDMA_FADDR: 0x%08x_%08x\n", upper_32_bits(addr), lower_32_bits(addr)); - if (GRAPHICS_VER(dev_priv) >= 4) { + if (GRAPHICS_VER(i915) >= 4) { drm_printf(m, "\tIPEIR: 0x%08x\n", ENGINE_READ(engine, RING_IPEIR)); drm_printf(m, "\tIPEHR: 0x%08x\n", @@ -2004,7 +2120,7 @@ static void intel_engine_print_registers(struct intel_engine_cs *engine, drm_printf(m, "\tIPEHR: 0x%08x\n", ENGINE_READ(engine, IPEHR)); } - if (HAS_EXECLISTS(dev_priv) && !intel_engine_uses_guc(engine)) { + if (HAS_EXECLISTS(i915) && !intel_engine_uses_guc(engine)) { struct i915_request * const *port, *rq; const u32 *hws = &engine->status_page.addr[I915_HWS_CSB_BUF0_INDEX]; @@ -2070,7 +2186,7 @@ static void intel_engine_print_registers(struct intel_engine_cs *engine, } rcu_read_unlock(); i915_sched_engine_active_unlock_bh(engine->sched_engine); - } else if (GRAPHICS_VER(dev_priv) > 6) { + } else if (GRAPHICS_VER(i915) > 6) { drm_printf(m, "\tPP_DIR_BASE: 0x%08x\n", ENGINE_READ(engine, RING_PP_DIR_BASE)); drm_printf(m, "\tPP_DIR_BASE_READ: 0x%08x\n", @@ -2114,17 +2230,6 @@ static void print_request_ring(struct drm_printer *m, struct i915_request *rq) } } -static unsigned long list_count(struct list_head *list) -{ - struct list_head *pos; - unsigned long count = 0; - - list_for_each(pos, list) - count++; - - return count; -} - static unsigned long read_ul(void *p, size_t x) { return *(unsigned long *)(p + x); @@ -2216,11 +2321,11 @@ void intel_engine_dump_active_requests(struct list_head *requests, } } -static void engine_dump_active_requests(struct intel_engine_cs *engine, struct drm_printer *m) +static void engine_dump_active_requests(struct intel_engine_cs *engine, + struct drm_printer *m) { + struct intel_context *hung_ce = NULL; struct i915_request *hung_rq = NULL; - struct intel_context *ce; - bool guc; /* * No need for an engine->irq_seqno_barrier() before the seqno reads. @@ -2229,27 +2334,22 @@ static void engine_dump_active_requests(struct intel_engine_cs *engine, struct d * But the intention here is just to report an instantaneous snapshot * so that's fine. */ - lockdep_assert_held(&engine->sched_engine->lock); + intel_engine_get_hung_entity(engine, &hung_ce, &hung_rq); drm_printf(m, "\tRequests:\n"); - guc = intel_uc_uses_guc_submission(&engine->gt->uc); - if (guc) { - ce = intel_engine_get_hung_context(engine); - if (ce) - hung_rq = intel_context_find_active_request(ce); - } else { - hung_rq = intel_engine_execlist_find_hung_request(engine); - } - if (hung_rq) engine_dump_request(hung_rq, m, "\t\thung"); + else if (hung_ce) + drm_printf(m, "\t\tGot hung ce but no hung rq!\n"); - if (guc) + if (intel_uc_uses_guc_submission(&engine->gt->uc)) intel_guc_dump_active_requests(engine, hung_rq, m); else - intel_engine_dump_active_requests(&engine->sched_engine->requests, - hung_rq, m); + intel_execlists_dump_active_requests(engine, hung_rq, m); + + if (hung_rq) + i915_request_put(hung_rq); } void intel_engine_dump(struct intel_engine_cs *engine, @@ -2259,7 +2359,6 @@ void intel_engine_dump(struct intel_engine_cs *engine, struct i915_gpu_error * const error = &engine->i915->gpu_error; struct i915_request *rq; intel_wakeref_t wakeref; - unsigned long flags; ktime_t dummy; if (header) { @@ -2296,13 +2395,8 @@ void intel_engine_dump(struct intel_engine_cs *engine, i915_reset_count(error)); print_properties(engine, m); - spin_lock_irqsave(&engine->sched_engine->lock, flags); engine_dump_active_requests(engine, m); - drm_printf(m, "\tOn hold?: %lu\n", - list_count(&engine->sched_engine->hold)); - spin_unlock_irqrestore(&engine->sched_engine->lock, flags); - drm_printf(m, "\tMMIO base: 0x%08x\n", engine->mmio_base); wakeref = intel_runtime_pm_get_if_in_use(engine->uncore->rpm); if (wakeref) { @@ -2348,8 +2442,7 @@ intel_engine_create_virtual(struct intel_engine_cs **siblings, return siblings[0]->cops->create_virtual(siblings, count, flags); } -struct i915_request * -intel_engine_execlist_find_hung_request(struct intel_engine_cs *engine) +static struct i915_request *engine_execlist_find_hung_request(struct intel_engine_cs *engine) { struct i915_request *request, *active = NULL; @@ -2401,6 +2494,33 @@ intel_engine_execlist_find_hung_request(struct intel_engine_cs *engine) return active; } +void intel_engine_get_hung_entity(struct intel_engine_cs *engine, + struct intel_context **ce, struct i915_request **rq) +{ + unsigned long flags; + + *ce = intel_engine_get_hung_context(engine); + if (*ce) { + intel_engine_clear_hung_context(engine); + + *rq = intel_context_get_active_request(*ce); + return; + } + + /* + * Getting here with GuC enabled means it is a forced error capture + * with no actual hang. So, no need to attempt the execlist search. + */ + if (intel_uc_uses_guc_submission(&engine->gt->uc)) + return; + + spin_lock_irqsave(&engine->sched_engine->lock, flags); + *rq = engine_execlist_find_hung_request(engine); + if (*rq) + *rq = i915_request_get_rcu(*rq); + spin_unlock_irqrestore(&engine->sched_engine->lock, flags); +} + void xehp_enable_ccs_engines(struct intel_engine_cs *engine) { /* diff --git a/drivers/gpu/drm/i915/gt/intel_engine_regs.h b/drivers/gpu/drm/i915/gt/intel_engine_regs.h index ee3efd06ee54..6b9d9f837669 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_regs.h +++ b/drivers/gpu/drm/i915/gt/intel_engine_regs.h @@ -81,6 +81,7 @@ #define RING_EIR(base) _MMIO((base) + 0xb0) #define RING_EMR(base) _MMIO((base) + 0xb4) #define RING_ESR(base) _MMIO((base) + 0xb8) +#define GEN12_STATE_ACK_DEBUG(base) _MMIO((base) + 0xbc) #define RING_INSTPM(base) _MMIO((base) + 0xc0) #define RING_CMD_CCTL(base) _MMIO((base) + 0xc4) #define ACTHD(base) _MMIO((base) + 0xc8) diff --git a/drivers/gpu/drm/i915/gt/intel_engine_types.h b/drivers/gpu/drm/i915/gt/intel_engine_types.h index 4fd54fb8810f..0a071e5da1a8 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_types.h +++ b/drivers/gpu/drm/i915/gt/intel_engine_types.h @@ -341,6 +341,18 @@ struct intel_engine_guc_stats { u64 start_gt_clk; }; +union intel_engine_tlb_inv_reg { + i915_reg_t reg; + i915_mcr_reg_t mcr_reg; +}; + +struct intel_engine_tlb_inv { + bool mcr; + union intel_engine_tlb_inv_reg reg; + u32 request; + u32 done; +}; + struct intel_engine_cs { struct drm_i915_private *i915; struct intel_gt *gt; @@ -372,6 +384,8 @@ struct intel_engine_cs { u32 context_size; u32 mmio_base; + struct intel_engine_tlb_inv tlb_inv; + /* * Some w/a require forcewake to be held (which prevents RC6) while * a particular engine is active. If so, we set fw_domain to which diff --git a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c index 18ffe55282e5..1bbe6708d0a7 100644 --- a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c +++ b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c @@ -4150,6 +4150,22 @@ void intel_execlists_show_requests(struct intel_engine_cs *engine, spin_unlock_irqrestore(&sched_engine->lock, flags); } +void intel_execlists_dump_active_requests(struct intel_engine_cs *engine, + struct i915_request *hung_rq, + struct drm_printer *m) +{ + unsigned long flags; + + spin_lock_irqsave(&engine->sched_engine->lock, flags); + + intel_engine_dump_active_requests(&engine->sched_engine->requests, hung_rq, m); + + drm_printf(m, "\tOn hold?: %zu\n", + list_count_nodes(&engine->sched_engine->hold)); + + spin_unlock_irqrestore(&engine->sched_engine->lock, flags); +} + #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST) #include "selftest_execlists.c" #endif diff --git a/drivers/gpu/drm/i915/gt/intel_execlists_submission.h b/drivers/gpu/drm/i915/gt/intel_execlists_submission.h index a1aa92c983a5..d2c7d45ea062 100644 --- a/drivers/gpu/drm/i915/gt/intel_execlists_submission.h +++ b/drivers/gpu/drm/i915/gt/intel_execlists_submission.h @@ -32,6 +32,10 @@ void intel_execlists_show_requests(struct intel_engine_cs *engine, int indent), unsigned int max); +void intel_execlists_dump_active_requests(struct intel_engine_cs *engine, + struct i915_request *hung_rq, + struct drm_printer *m); + bool intel_engine_in_execlists_submission_mode(const struct intel_engine_cs *engine); diff --git a/drivers/gpu/drm/i915/gt/intel_gpu_commands.h b/drivers/gpu/drm/i915/gt/intel_gpu_commands.h index 454179884801..5d143e2a8db0 100644 --- a/drivers/gpu/drm/i915/gt/intel_gpu_commands.h +++ b/drivers/gpu/drm/i915/gt/intel_gpu_commands.h @@ -394,6 +394,7 @@ #define MI_LOAD_URB_MEM MI_INSTR(0x2C, 0) #define MI_STORE_URB_MEM MI_INSTR(0x2D, 0) #define MI_CONDITIONAL_BATCH_BUFFER_END MI_INSTR(0x36, 0) +#define MI_DO_COMPARE REG_BIT(21) #define STATE_BASE_ADDRESS \ ((0x3 << 29) | (0x0 << 27) | (0x1 << 24) | (0x1 << 16)) diff --git a/drivers/gpu/drm/i915/gt/intel_gsc.h b/drivers/gpu/drm/i915/gt/intel_gsc.h index fcac1775e9c3..7ab3ca0f9f26 100644 --- a/drivers/gpu/drm/i915/gt/intel_gsc.h +++ b/drivers/gpu/drm/i915/gt/intel_gsc.h @@ -33,7 +33,7 @@ struct intel_gsc { } intf[INTEL_GSC_NUM_INTERFACES]; }; -void intel_gsc_init(struct intel_gsc *gsc, struct drm_i915_private *dev_priv); +void intel_gsc_init(struct intel_gsc *gsc, struct drm_i915_private *i915); void intel_gsc_fini(struct intel_gsc *gsc); void intel_gsc_irq_handler(struct intel_gt *gt, u32 iir); diff --git a/drivers/gpu/drm/i915/gt/intel_gt.c b/drivers/gpu/drm/i915/gt/intel_gt.c index f4f694f12907..256cecf99dd1 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt.c +++ b/drivers/gpu/drm/i915/gt/intel_gt.c @@ -784,6 +784,29 @@ void intel_gt_driver_unregister(struct intel_gt *gt) intel_gsc_fini(>->gsc); /* + * If we unload the driver and wedge before the GSC worker is complete, + * the worker will hit an error on its submission to the GSC engine and + * then exit. This is hard to hit for a user, but it is reproducible + * with skipping selftests. The error is handled gracefully by the + * worker, so there are no functional issues, but we still end up with + * an error message in dmesg, which is something we want to avoid as + * this is a supported scenario. We could modify the worker to better + * handle a wedging occurring during its execution, but that gets + * complicated for a couple of reasons: + * - We do want the error on runtime wedging, because there are + * implications for subsystems outside of GT (i.e., PXP, HDCP), it's + * only the error on driver unload that we want to silence. + * - The worker is responsible for multiple submissions (GSC FW load, + * HuC auth, SW proxy), so all of those will have to be adapted to + * handle the wedged_on_fini scenario. + * Therefore, it's much simpler to just wait for the worker to be done + * before wedging on driver removal, also considering that the worker + * will likely already be idle in the great majority of non-selftest + * scenarios. + */ + intel_gsc_uc_flush_work(>->uc.gsc); + + /* * Upon unregistering the device to prevent any new users, cancel * all in-flight requests so that we can quickly unbind the active * resources. @@ -981,35 +1004,6 @@ void intel_gt_info_print(const struct intel_gt_info *info, intel_sseu_dump(&info->sseu, p); } -struct reg_and_bit { - union { - i915_reg_t reg; - i915_mcr_reg_t mcr_reg; - }; - u32 bit; -}; - -static struct reg_and_bit -get_reg_and_bit(const struct intel_engine_cs *engine, const bool gen8, - const i915_reg_t *regs, const unsigned int num) -{ - const unsigned int class = engine->class; - struct reg_and_bit rb = { }; - - if (gt_WARN_ON_ONCE(engine->gt, class >= num || !regs[class].reg)) - return rb; - - rb.reg = regs[class]; - if (gen8 && class == VIDEO_DECODE_CLASS) - rb.reg.reg += 4 * engine->instance; /* GEN8_M2TCR */ - else - rb.bit = engine->instance; - - rb.bit = BIT(rb.bit); - - return rb; -} - /* * HW architecture suggest typical invalidation time at 40us, * with pessimistic cases up to 100us and a recommendation to @@ -1023,14 +1017,20 @@ get_reg_and_bit(const struct intel_engine_cs *engine, const bool gen8, * but are now considered MCR registers. Since they exist within a GAM range, * the primary instance of the register rolls up the status from each unit. */ -static int wait_for_invalidate(struct intel_gt *gt, struct reg_and_bit rb) +static int wait_for_invalidate(struct intel_engine_cs *engine) { - if (GRAPHICS_VER_FULL(gt->i915) >= IP_VER(12, 50)) - return intel_gt_mcr_wait_for_reg(gt, rb.mcr_reg, rb.bit, 0, + if (engine->tlb_inv.mcr) + return intel_gt_mcr_wait_for_reg(engine->gt, + engine->tlb_inv.reg.mcr_reg, + engine->tlb_inv.done, + 0, TLB_INVAL_TIMEOUT_US, TLB_INVAL_TIMEOUT_MS); else - return __intel_wait_for_register_fw(gt->uncore, rb.reg, rb.bit, 0, + return __intel_wait_for_register_fw(engine->gt->uncore, + engine->tlb_inv.reg.reg, + engine->tlb_inv.done, + 0, TLB_INVAL_TIMEOUT_US, TLB_INVAL_TIMEOUT_MS, NULL); @@ -1038,62 +1038,14 @@ static int wait_for_invalidate(struct intel_gt *gt, struct reg_and_bit rb) static void mmio_invalidate_full(struct intel_gt *gt) { - static const i915_reg_t gen8_regs[] = { - [RENDER_CLASS] = GEN8_RTCR, - [VIDEO_DECODE_CLASS] = GEN8_M1TCR, /* , GEN8_M2TCR */ - [VIDEO_ENHANCEMENT_CLASS] = GEN8_VTCR, - [COPY_ENGINE_CLASS] = GEN8_BTCR, - }; - static const i915_reg_t gen12_regs[] = { - [RENDER_CLASS] = GEN12_GFX_TLB_INV_CR, - [VIDEO_DECODE_CLASS] = GEN12_VD_TLB_INV_CR, - [VIDEO_ENHANCEMENT_CLASS] = GEN12_VE_TLB_INV_CR, - [COPY_ENGINE_CLASS] = GEN12_BLT_TLB_INV_CR, - [COMPUTE_CLASS] = GEN12_COMPCTX_TLB_INV_CR, - }; - static const i915_mcr_reg_t xehp_regs[] = { - [RENDER_CLASS] = XEHP_GFX_TLB_INV_CR, - [VIDEO_DECODE_CLASS] = XEHP_VD_TLB_INV_CR, - [VIDEO_ENHANCEMENT_CLASS] = XEHP_VE_TLB_INV_CR, - [COPY_ENGINE_CLASS] = XEHP_BLT_TLB_INV_CR, - [COMPUTE_CLASS] = XEHP_COMPCTX_TLB_INV_CR, - }; struct drm_i915_private *i915 = gt->i915; struct intel_uncore *uncore = gt->uncore; struct intel_engine_cs *engine; intel_engine_mask_t awake, tmp; enum intel_engine_id id; - const i915_reg_t *regs; - unsigned int num = 0; unsigned long flags; - /* - * New platforms should not be added with catch-all-newer (>=) - * condition so that any later platform added triggers the below warning - * and in turn mandates a human cross-check of whether the invalidation - * flows have compatible semantics. - * - * For instance with the 11.00 -> 12.00 transition three out of five - * respective engine registers were moved to masked type. Then after the - * 12.00 -> 12.50 transition multi cast handling is required too. - */ - - if (GRAPHICS_VER_FULL(i915) == IP_VER(12, 50) || - GRAPHICS_VER_FULL(i915) == IP_VER(12, 55)) { - regs = NULL; - num = ARRAY_SIZE(xehp_regs); - } else if (GRAPHICS_VER_FULL(i915) == IP_VER(12, 0) || - GRAPHICS_VER_FULL(i915) == IP_VER(12, 10)) { - regs = gen12_regs; - num = ARRAY_SIZE(gen12_regs); - } else if (GRAPHICS_VER(i915) >= 8 && GRAPHICS_VER(i915) <= 11) { - regs = gen8_regs; - num = ARRAY_SIZE(gen8_regs); - } else if (GRAPHICS_VER(i915) < 8) { - return; - } - - if (gt_WARN_ONCE(gt, !num, "Platform does not implement TLB invalidation!")) + if (GRAPHICS_VER(i915) < 8) return; intel_uncore_forcewake_get(uncore, FORCEWAKE_ALL); @@ -1103,33 +1055,18 @@ static void mmio_invalidate_full(struct intel_gt *gt) awake = 0; for_each_engine(engine, gt, id) { - struct reg_and_bit rb; - if (!intel_engine_pm_is_awake(engine)) continue; - if (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 50)) { - u32 val = BIT(engine->instance); - - if (engine->class == VIDEO_DECODE_CLASS || - engine->class == VIDEO_ENHANCEMENT_CLASS || - engine->class == COMPUTE_CLASS) - val = _MASKED_BIT_ENABLE(val); + if (engine->tlb_inv.mcr) intel_gt_mcr_multicast_write_fw(gt, - xehp_regs[engine->class], - val); - } else { - rb = get_reg_and_bit(engine, regs == gen8_regs, regs, num); - if (!i915_mmio_reg_offset(rb.reg)) - continue; - - if (GRAPHICS_VER(i915) == 12 && (engine->class == VIDEO_DECODE_CLASS || - engine->class == VIDEO_ENHANCEMENT_CLASS || - engine->class == COMPUTE_CLASS)) - rb.bit = _MASKED_BIT_ENABLE(rb.bit); - - intel_uncore_write_fw(uncore, rb.reg, rb.bit); - } + engine->tlb_inv.reg.mcr_reg, + engine->tlb_inv.request); + else + intel_uncore_write_fw(uncore, + engine->tlb_inv.reg.reg, + engine->tlb_inv.request); + awake |= engine->mask; } @@ -1148,17 +1085,9 @@ static void mmio_invalidate_full(struct intel_gt *gt) intel_gt_mcr_unlock(gt, flags); for_each_engine_masked(engine, gt, awake, tmp) { - struct reg_and_bit rb; - - if (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 50)) { - rb.mcr_reg = xehp_regs[engine->class]; - rb.bit = BIT(engine->instance); - } else { - rb = get_reg_and_bit(engine, regs == gen8_regs, regs, num); - } - - if (wait_for_invalidate(gt, rb)) - gt_err_ratelimited(gt, "%s TLB invalidation did not complete in %ums!\n", + if (wait_for_invalidate(engine)) + gt_err_ratelimited(gt, + "%s TLB invalidation did not complete in %ums!\n", engine->name, TLB_INVAL_TIMEOUT_MS); } @@ -1204,3 +1133,7 @@ unlock: mutex_unlock(>->tlb.invalidate_lock); } } + +#if IS_ENABLED(CONFIG_DRM_I915_SELFTEST) +#include "selftest_tlb.c" +#endif diff --git a/drivers/gpu/drm/i915/gt/intel_gt_mcr.c b/drivers/gpu/drm/i915/gt/intel_gt_mcr.c index 169393a7ad88..0b414eae1683 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_mcr.c +++ b/drivers/gpu/drm/i915/gt/intel_gt_mcr.c @@ -35,7 +35,7 @@ * ignored. */ -#define HAS_MSLICE_STEERING(dev_priv) (INTEL_INFO(dev_priv)->has_mslice_steering) +#define HAS_MSLICE_STEERING(i915) (INTEL_INFO(i915)->has_mslice_steering) static const char * const intel_steering_types[] = { "L3BANK", @@ -364,6 +364,7 @@ static u32 rw_with_mcr_steering(struct intel_gt *gt, * function call. */ void intel_gt_mcr_lock(struct intel_gt *gt, unsigned long *flags) + __acquires(>->mcr_lock) { unsigned long __flags; int err = 0; @@ -410,6 +411,7 @@ void intel_gt_mcr_lock(struct intel_gt *gt, unsigned long *flags) * Context: Releases gt->mcr_lock */ void intel_gt_mcr_unlock(struct intel_gt *gt, unsigned long flags) + __releases(>->mcr_lock) { spin_unlock_irqrestore(>->mcr_lock, flags); @@ -559,12 +561,15 @@ static bool reg_needs_read_steering(struct intel_gt *gt, i915_mcr_reg_t reg, enum intel_steering_type type) { - const u32 offset = i915_mmio_reg_offset(reg); + u32 offset = i915_mmio_reg_offset(reg); const struct intel_mmio_range *entry; if (likely(!gt->steering_table[type])) return false; + if (IS_GSI_REG(offset)) + offset += gt->uncore->gsi_offset; + for (entry = gt->steering_table[type]; entry->end; entry++) { if (offset >= entry->start && offset <= entry->end) return true; diff --git a/drivers/gpu/drm/i915/gt/intel_gt_pm.c b/drivers/gpu/drm/i915/gt/intel_gt_pm.c index 85ae7dc079f2..e02cb90723ae 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_pm.c +++ b/drivers/gpu/drm/i915/gt/intel_gt_pm.c @@ -20,31 +20,10 @@ #include "intel_rc6.h" #include "intel_rps.h" #include "intel_wakeref.h" -#include "intel_pcode.h" #include "pxp/intel_pxp_pm.h" #define I915_GT_SUSPEND_IDLE_TIMEOUT (HZ / 2) -static void mtl_media_busy(struct intel_gt *gt) -{ - /* Wa_14017073508: mtl */ - if (IS_MTL_GRAPHICS_STEP(gt->i915, P, STEP_A0, STEP_B0) && - gt->type == GT_MEDIA) - snb_pcode_write_p(gt->uncore, PCODE_MBOX_GT_STATE, - PCODE_MBOX_GT_STATE_MEDIA_BUSY, - PCODE_MBOX_GT_STATE_DOMAIN_MEDIA, 0); -} - -static void mtl_media_idle(struct intel_gt *gt) -{ - /* Wa_14017073508: mtl */ - if (IS_MTL_GRAPHICS_STEP(gt->i915, P, STEP_A0, STEP_B0) && - gt->type == GT_MEDIA) - snb_pcode_write_p(gt->uncore, PCODE_MBOX_GT_STATE, - PCODE_MBOX_GT_STATE_MEDIA_NOT_BUSY, - PCODE_MBOX_GT_STATE_DOMAIN_MEDIA, 0); -} - static void user_forcewake(struct intel_gt *gt, bool suspend) { int count = atomic_read(>->user_wakeref); @@ -92,9 +71,6 @@ static int __gt_unpark(struct intel_wakeref *wf) GT_TRACE(gt, "\n"); - /* Wa_14017073508: mtl */ - mtl_media_busy(gt); - /* * It seems that the DMC likes to transition between the DC states a lot * when there are no connected displays (no active power domains) during @@ -144,9 +120,6 @@ static int __gt_park(struct intel_wakeref *wf) GEM_BUG_ON(!wakeref); intel_display_power_put_async(i915, POWER_DOMAIN_GT_IRQ, wakeref); - /* Wa_14017073508: mtl */ - mtl_media_idle(gt); - return 0; } diff --git a/drivers/gpu/drm/i915/gt/intel_gt_print.h b/drivers/gpu/drm/i915/gt/intel_gt_print.h index 5d9da355ce24..55a336a9ff06 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_print.h +++ b/drivers/gpu/drm/i915/gt/intel_gt_print.h @@ -28,6 +28,9 @@ #define gt_err_ratelimited(_gt, _fmt, ...) \ drm_err_ratelimited(&(_gt)->i915->drm, "GT%u: " _fmt, (_gt)->info.id, ##__VA_ARGS__) +#define gt_notice_ratelimited(_gt, _fmt, ...) \ + dev_notice_ratelimited((_gt)->i915->drm.dev, "GT%u: " _fmt, (_gt)->info.id, ##__VA_ARGS__) + #define gt_probe_error(_gt, _fmt, ...) \ do { \ if (i915_error_injected()) \ diff --git a/drivers/gpu/drm/i915/gt/intel_gt_regs.h b/drivers/gpu/drm/i915/gt/intel_gt_regs.h index 49a614b03fe8..4aecb5a7b631 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_regs.h +++ b/drivers/gpu/drm/i915/gt/intel_gt_regs.h @@ -405,6 +405,8 @@ #define GEN9_WM_CHICKEN3 _MMIO(0x5588) #define GEN9_FACTOR_IN_CLR_VAL_HIZ (1 << 9) +#define XEHP_CULLBIT1 MCR_REG(0x6100) + #define CHICKEN_RASTER_1 MCR_REG(0x6204) #define DIS_SF_ROUND_NEAREST_EVEN REG_BIT(8) @@ -455,10 +457,12 @@ #define HZ_DEPTH_TEST_LE_GE_OPT_DISABLE REG_BIT(13) #define BDW_HIZ_POWER_COMPILER_CLOCK_GATING_DISABLE REG_BIT(3) +#define XEHP_CULLBIT2 MCR_REG(0x7030) + #define GEN8_L3CNTLREG _MMIO(0x7034) #define GEN8_ERRDETBCTRL (1 << 9) -#define PSS_MODE2 _MMIO(0x703c) +#define XEHP_PSS_MODE2 MCR_REG(0x703c) #define SCOREBOARD_STALL_FLUSH_CONTROL REG_BIT(5) #define GEN7_SC_INSTDONE _MMIO(0x7100) @@ -474,6 +478,9 @@ #define HDC_FORCE_NON_COHERENT (1 << 4) #define HDC_BARRIER_PERFORMANCE_DISABLE (1 << 10) +#define COMMON_SLICE_CHICKEN4 _MMIO(0x7300) +#define DISABLE_TDC_LOAD_BALANCING_CALC REG_BIT(6) + #define GEN8_HDC_CHICKEN1 _MMIO(0x7304) #define GEN11_COMMON_SLICE_CHICKEN3 _MMIO(0x7304) @@ -680,10 +687,7 @@ #define GEN6_RSTCTL _MMIO(0x9420) #define GEN7_MISCCPCTL _MMIO(0x9424) -#define GEN7_DOP_CLOCK_GATE_ENABLE (1 << 0) - -#define GEN8_MISCCPCTL MCR_REG(0x9424) -#define GEN8_DOP_CLOCK_GATE_ENABLE REG_BIT(0) +#define GEN7_DOP_CLOCK_GATE_ENABLE REG_BIT(0) #define GEN12_DOP_CLOCK_GATE_RENDER_ENABLE REG_BIT(1) #define GEN8_DOP_CLOCK_GATE_CFCLK_ENABLE (1 << 2) #define GEN8_DOP_CLOCK_GATE_GUC_ENABLE (1 << 4) @@ -766,9 +770,6 @@ #define GEN10_DFR_RATIO_EN_AND_CHICKEN MCR_REG(0x9550) #define DFR_DISABLE (1 << 9) -#define INF_UNIT_LEVEL_CLKGATE MCR_REG(0x9560) -#define CGPSF_CLKGATE_DIS (1 << 3) - #define MICRO_BP0_0 _MMIO(0x9800) #define MICRO_BP0_2 _MMIO(0x9804) #define MICRO_BP0_1 _MMIO(0x9808) @@ -973,7 +974,7 @@ #define GEN7_WA_FOR_GEN7_L3_CONTROL 0x3C47FF8C #define GEN7_L3AGDIS (1 << 19) -#define XEHPC_LNCFMISCCFGREG0 _MMIO(0xb01c) +#define XEHPC_LNCFMISCCFGREG0 MCR_REG(0xb01c) #define XEHPC_HOSTCACHEEN REG_BIT(1) #define XEHPC_OVRLSCCC REG_BIT(0) @@ -1036,7 +1037,7 @@ #define XEHP_L3SCQREG7 MCR_REG(0xb188) #define BLEND_FILL_CACHING_OPT_DIS REG_BIT(3) -#define XEHPC_L3SCRUB _MMIO(0xb18c) +#define XEHPC_L3SCRUB MCR_REG(0xb18c) #define SCRUB_CL_DWNGRADE_SHARED REG_BIT(12) #define SCRUB_RATE_PER_BANK_MASK REG_GENMASK(2, 0) #define SCRUB_RATE_4B_PER_CLK REG_FIELD_PREP(SCRUB_RATE_PER_BANK_MASK, 0x6) @@ -1090,20 +1091,24 @@ #define XEHP_BLT_TLB_INV_CR MCR_REG(0xcee4) #define GEN12_COMPCTX_TLB_INV_CR _MMIO(0xcf04) #define XEHP_COMPCTX_TLB_INV_CR MCR_REG(0xcf04) +#define XELPMP_GSC_TLB_INV_CR _MMIO(0xcf04) /* media GT only */ #define XEHP_MERT_MOD_CTRL MCR_REG(0xcf28) #define RENDER_MOD_CTRL MCR_REG(0xcf2c) #define COMP_MOD_CTRL MCR_REG(0xcf30) -#define VDBX_MOD_CTRL MCR_REG(0xcf34) -#define VEBX_MOD_CTRL MCR_REG(0xcf38) +#define XELPMP_GSC_MOD_CTRL _MMIO(0xcf30) /* media GT only */ +#define XEHP_VDBX_MOD_CTRL MCR_REG(0xcf34) +#define XELPMP_VDBX_MOD_CTRL _MMIO(0xcf34) +#define XEHP_VEBX_MOD_CTRL MCR_REG(0xcf38) +#define XELPMP_VEBX_MOD_CTRL _MMIO(0xcf38) #define FORCE_MISS_FTLB REG_BIT(3) -#define GEN12_GAMSTLB_CTRL _MMIO(0xcf4c) +#define XEHP_GAMSTLB_CTRL MCR_REG(0xcf4c) #define CONTROL_BLOCK_CLKGATE_DIS REG_BIT(12) #define EGRESS_BLOCK_CLKGATE_DIS REG_BIT(11) #define TAG_BLOCK_CLKGATE_DIS REG_BIT(7) -#define GEN12_GAMCNTRL_CTRL _MMIO(0xcf54) +#define XEHP_GAMCNTRL_CTRL MCR_REG(0xcf54) #define INVALIDATION_BROADCAST_MODE_DIS REG_BIT(12) #define GLOBAL_INVALIDATION_MODE REG_BIT(2) diff --git a/drivers/gpu/drm/i915/gt/intel_gt_sysfs.c b/drivers/gpu/drm/i915/gt/intel_gt_sysfs.c index 6629e4c72b6b..33cba406b569 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_sysfs.c +++ b/drivers/gpu/drm/i915/gt/intel_gt_sysfs.c @@ -72,7 +72,7 @@ static void kobj_gt_release(struct kobject *kobj) { } -static struct kobj_type kobj_gt_type = { +static const struct kobj_type kobj_gt_type = { .release = kobj_gt_release, .sysfs_ops = &kobj_sysfs_ops, .default_groups = id_groups, diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c index 7771a19008c6..81a96c52a92b 100644 --- a/drivers/gpu/drm/i915/gt/intel_lrc.c +++ b/drivers/gpu/drm/i915/gt/intel_lrc.c @@ -288,39 +288,6 @@ static const u8 dg2_xcs_offsets[] = { END }; -static const u8 mtl_xcs_offsets[] = { - NOP(1), - LRI(13, POSTED), - REG16(0x244), - REG(0x034), - REG(0x030), - REG(0x038), - REG(0x03c), - REG(0x168), - REG(0x140), - REG(0x110), - REG(0x1c0), - REG(0x1c4), - REG(0x1c8), - REG(0x180), - REG16(0x2b4), - NOP(4), - - NOP(1), - LRI(9, POSTED), - REG16(0x3a8), - REG16(0x28c), - REG16(0x288), - REG16(0x284), - REG16(0x280), - REG16(0x27c), - REG16(0x278), - REG16(0x274), - REG16(0x270), - - END -}; - static const u8 gen8_rcs_offsets[] = { NOP(1), LRI(14, POSTED), @@ -739,9 +706,7 @@ static const u8 *reg_offsets(const struct intel_engine_cs *engine) else return gen8_rcs_offsets; } else { - if (GRAPHICS_VER_FULL(engine->i915) >= IP_VER(12, 70)) - return mtl_xcs_offsets; - else if (GRAPHICS_VER_FULL(engine->i915) >= IP_VER(12, 55)) + if (GRAPHICS_VER_FULL(engine->i915) >= IP_VER(12, 55)) return dg2_xcs_offsets; else if (GRAPHICS_VER(engine->i915) >= 12) return gen12_xcs_offsets; @@ -1351,16 +1316,16 @@ static u32 * dg2_emit_rcs_hang_wabb(const struct intel_context *ce, u32 *cs) { *cs++ = MI_LOAD_REGISTER_IMM(1); - *cs++ = i915_mmio_reg_offset(GEN12_STATE_ACK_DEBUG); + *cs++ = i915_mmio_reg_offset(GEN12_STATE_ACK_DEBUG(ce->engine->mmio_base)); *cs++ = 0x21; *cs++ = MI_LOAD_REGISTER_REG; *cs++ = i915_mmio_reg_offset(RING_NOPID(ce->engine->mmio_base)); - *cs++ = i915_mmio_reg_offset(GEN12_CULLBIT1); + *cs++ = i915_mmio_reg_offset(XEHP_CULLBIT1); *cs++ = MI_LOAD_REGISTER_REG; *cs++ = i915_mmio_reg_offset(RING_NOPID(ce->engine->mmio_base)); - *cs++ = i915_mmio_reg_offset(GEN12_CULLBIT2); + *cs++ = i915_mmio_reg_offset(XEHP_CULLBIT2); return cs; } diff --git a/drivers/gpu/drm/i915/gt/intel_rc6.c b/drivers/gpu/drm/i915/gt/intel_rc6.c index 5c91622dfca4..f4150f61f39c 100644 --- a/drivers/gpu/drm/i915/gt/intel_rc6.c +++ b/drivers/gpu/drm/i915/gt/intel_rc6.c @@ -486,6 +486,7 @@ static bool bxt_check_bios_rc6_setup(struct intel_rc6 *rc6) static bool rc6_supported(struct intel_rc6 *rc6) { struct drm_i915_private *i915 = rc6_to_i915(rc6); + struct intel_gt *gt = rc6_to_gt(rc6); if (!HAS_RC6(i915)) return false; @@ -502,6 +503,13 @@ static bool rc6_supported(struct intel_rc6 *rc6) return false; } + if (IS_MTL_MEDIA_STEP(gt->i915, STEP_A0, STEP_B0) && + gt->type == GT_MEDIA) { + drm_notice(&i915->drm, + "Media RC6 disabled on A step\n"); + return false; + } + return true; } diff --git a/drivers/gpu/drm/i915/gt/intel_reset_types.h b/drivers/gpu/drm/i915/gt/intel_reset_types.h index 9312b29f5a97..80351f0a856c 100644 --- a/drivers/gpu/drm/i915/gt/intel_reset_types.h +++ b/drivers/gpu/drm/i915/gt/intel_reset_types.h @@ -51,7 +51,7 @@ struct intel_reset { /** * Waitqueue to signal when the reset has completed. Used by clients - * that wait for dev_priv->mm.wedged to settle. + * that wait for i915->mm.wedged to settle. */ wait_queue_head_t queue; diff --git a/drivers/gpu/drm/i915/gt/intel_ring.c b/drivers/gpu/drm/i915/gt/intel_ring.c index 15ec64d881c4..fb99143be98e 100644 --- a/drivers/gpu/drm/i915/gt/intel_ring.c +++ b/drivers/gpu/drm/i915/gt/intel_ring.c @@ -53,7 +53,7 @@ int intel_ring_pin(struct intel_ring *ring, struct i915_gem_ww_ctx *ww) if (unlikely(ret)) goto err_unpin; - if (i915_vma_is_map_and_fenceable(vma)) { + if (i915_vma_is_map_and_fenceable(vma) && !HAS_LLC(vma->vm->i915)) { addr = (void __force *)i915_vma_pin_iomap(vma); } else { int type = i915_coherent_map_type(vma->vm->i915, vma->obj, false); @@ -98,7 +98,7 @@ void intel_ring_unpin(struct intel_ring *ring) return; i915_vma_unset_ggtt_write(vma); - if (i915_vma_is_map_and_fenceable(vma)) + if (i915_vma_is_map_and_fenceable(vma) && !HAS_LLC(vma->vm->i915)) i915_vma_unpin_iomap(vma); else i915_gem_object_unpin_map(vma->obj); @@ -116,7 +116,7 @@ static struct i915_vma *create_ring_vma(struct i915_ggtt *ggtt, int size) obj = i915_gem_object_create_lmem(i915, size, I915_BO_ALLOC_VOLATILE | I915_BO_ALLOC_PM_VOLATILE); - if (IS_ERR(obj) && i915_ggtt_has_aperture(ggtt)) + if (IS_ERR(obj) && i915_ggtt_has_aperture(ggtt) && !HAS_LLC(i915)) obj = i915_gem_object_create_stolen(i915, size); if (IS_ERR(obj)) obj = i915_gem_object_create_internal(i915, size); diff --git a/drivers/gpu/drm/i915/gt/intel_ring_submission.c b/drivers/gpu/drm/i915/gt/intel_ring_submission.c index 827adb0cfaea..3fd795c3263f 100644 --- a/drivers/gpu/drm/i915/gt/intel_ring_submission.c +++ b/drivers/gpu/drm/i915/gt/intel_ring_submission.c @@ -1052,9 +1052,9 @@ static void gen6_bsd_set_default_submission(struct intel_engine_cs *engine) static void ring_release(struct intel_engine_cs *engine) { - struct drm_i915_private *dev_priv = engine->i915; + struct drm_i915_private *i915 = engine->i915; - drm_WARN_ON(&dev_priv->drm, GRAPHICS_VER(dev_priv) > 2 && + drm_WARN_ON(&i915->drm, GRAPHICS_VER(i915) > 2 && (ENGINE_READ(engine, RING_MI_MODE) & MODE_IDLE) == 0); intel_engine_cleanup_common(engine); diff --git a/drivers/gpu/drm/i915/gt/intel_rps_types.h b/drivers/gpu/drm/i915/gt/intel_rps_types.h index 9173ec75f2b8..6507fa3f6d1e 100644 --- a/drivers/gpu/drm/i915/gt/intel_rps_types.h +++ b/drivers/gpu/drm/i915/gt/intel_rps_types.h @@ -57,7 +57,7 @@ struct intel_rps { /* * work, interrupts_enabled and pm_iir are protected by - * dev_priv->irq_lock + * i915->irq_lock */ struct timer_list timer; struct work_struct work; diff --git a/drivers/gpu/drm/i915/gt/intel_sseu.h b/drivers/gpu/drm/i915/gt/intel_sseu.h index aa87d3832d60..d7e8c374f153 100644 --- a/drivers/gpu/drm/i915/gt/intel_sseu.h +++ b/drivers/gpu/drm/i915/gt/intel_sseu.h @@ -27,7 +27,7 @@ struct drm_printer; * is only relevant to pre-Xe_HP platforms (Xe_HP and beyond use the * I915_MAX_SS_FUSE_BITS value below). */ -#define GEN_MAX_SS_PER_HSW_SLICE 6 +#define GEN_MAX_SS_PER_HSW_SLICE 8 /* * Maximum number of 32-bit registers used by hardware to express the diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.c b/drivers/gpu/drm/i915/gt/intel_workarounds.c index 9e4fd6329663..e7ee24bcad89 100644 --- a/drivers/gpu/drm/i915/gt/intel_workarounds.c +++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c @@ -30,6 +30,9 @@ * creation to have a "primed golden context", i.e. a context image that * already contains the changes needed to all the registers. * + * Context workarounds should be implemented in the \*_ctx_workarounds_init() + * variants respective to the targeted platforms. + * * - Engine workarounds: the list of these WAs is applied whenever the specific * engine is reset. It's also possible that a set of engine classes share a * common power domain and they are reset together. This happens on some @@ -42,15 +45,28 @@ * saves/restores their values before/after the reset takes place. See * ``drivers/gpu/drm/i915/gt/uc/intel_guc_ads.c`` for reference. * + * Workarounds for registers specific to RCS and CCS should be implemented in + * rcs_engine_wa_init() and ccs_engine_wa_init(), respectively; those for + * registers belonging to BCS, VCS or VECS should be implemented in + * xcs_engine_wa_init(). Workarounds for registers not belonging to a specific + * engine's MMIO range but that are part of of the common RCS/CCS reset domain + * should be implemented in general_render_compute_wa_init(). + * * - GT workarounds: the list of these WAs is applied whenever these registers * revert to their default values: on GPU reset, suspend/resume [1]_, etc. * + * GT workarounds should be implemented in the \*_gt_workarounds_init() + * variants respective to the targeted platforms. + * * - Register whitelist: some workarounds need to be implemented in userspace, * but need to touch privileged registers. The whitelist in the kernel * instructs the hardware to allow the access to happen. From the kernel side, * this is just a special case of a MMIO workaround (as we write the list of * these to/be-whitelisted registers to some special HW registers). * + * Register whitelisting should be done in the \*_whitelist_build() variants + * respective to the targeted platforms. + * * - Workaround batchbuffers: buffers that get executed automatically by the * hardware on every HW context restore. These buffers are created and * programmed in the default context so the hardware always go through those @@ -225,6 +241,12 @@ wa_write(struct i915_wa_list *wal, i915_reg_t reg, u32 set) } static void +wa_mcr_write(struct i915_wa_list *wal, i915_mcr_reg_t reg, u32 set) +{ + wa_mcr_write_clr_set(wal, reg, ~0, set); +} + +static void wa_write_or(struct i915_wa_list *wal, i915_reg_t reg, u32 set) { wa_write_clr_set(wal, reg, set, set); @@ -721,9 +743,13 @@ static void gen12_ctx_workarounds_init(struct intel_engine_cs *engine, FF_MODE2_GS_TIMER_224, 0, false); - if (!IS_DG1(i915)) + if (!IS_DG1(i915)) { /* Wa_1806527549 */ wa_masked_en(wal, HIZ_CHICKEN, HZ_DEPTH_TEST_LE_GE_OPT_DISABLE); + + /* Wa_1606376872 */ + wa_masked_en(wal, COMMON_SLICE_CHICKEN4, DISABLE_TDC_LOAD_BALANCING_CALC); + } } static void dg1_ctx_workarounds_init(struct intel_engine_cs *engine, @@ -777,7 +803,7 @@ static void dg2_ctx_workarounds_init(struct intel_engine_cs *engine, /* Wa_18018764978:dg2 */ if (IS_DG2_GRAPHICS_STEP(engine->i915, G10, STEP_C0, STEP_FOREVER) || IS_DG2_G11(engine->i915) || IS_DG2_G12(engine->i915)) - wa_masked_en(wal, PSS_MODE2, SCOREBOARD_STALL_FLUSH_CONTROL); + wa_mcr_masked_en(wal, XEHP_PSS_MODE2, SCOREBOARD_STALL_FLUSH_CONTROL); /* Wa_15010599737:dg2 */ wa_mcr_masked_en(wal, CHICKEN_RASTER_1, DIS_SF_ROUND_NEAREST_EVEN); @@ -805,7 +831,7 @@ static void mtl_ctx_workarounds_init(struct intel_engine_cs *engine, wa_mcr_masked_en(wal, VFLSKPD, VF_PREFETCH_TLB_DIS); /* Wa_18018764978 */ - wa_masked_en(wal, PSS_MODE2, SCOREBOARD_STALL_FLUSH_CONTROL); + wa_mcr_masked_en(wal, XEHP_PSS_MODE2, SCOREBOARD_STALL_FLUSH_CONTROL); } /* Wa_18019271663 */ @@ -1383,6 +1409,13 @@ icl_gt_workarounds_init(struct intel_gt *gt, struct i915_wa_list *wal) GAMT_CHKN_BIT_REG, GAMT_CHKN_DISABLE_L3_COH_PIPE); + /* + * Wa_1408615072:icl,ehl (vsunit) + * Wa_1407596294:icl,ehl (hsunit) + */ + wa_write_or(wal, UNSLICE_UNIT_LEVEL_CLKGATE, + VSUNIT_CLKGATE_DIS | HSUNIT_CLKGATE_DIS); + /* Wa_1407352427:icl,ehl */ wa_write_or(wal, UNSLICE_UNIT_LEVEL_CLKGATE2, PSDUNIT_CLKGATE_DIS); @@ -1443,21 +1476,15 @@ gen12_gt_workarounds_init(struct intel_gt *gt, struct i915_wa_list *wal) static void dg1_gt_workarounds_init(struct intel_gt *gt, struct i915_wa_list *wal) { - struct drm_i915_private *i915 = gt->i915; - gen12_gt_workarounds_init(gt, wal); /* Wa_1409420604:dg1 */ - if (IS_DG1(i915)) - wa_mcr_write_or(wal, - SUBSLICE_UNIT_LEVEL_CLKGATE2, - CPSSUNIT_CLKGATE_DIS); + wa_mcr_write_or(wal, SUBSLICE_UNIT_LEVEL_CLKGATE2, + CPSSUNIT_CLKGATE_DIS); /* Wa_1408615072:dg1 */ /* Empirical testing shows this register is unaffected by engine reset. */ - if (IS_DG1(i915)) - wa_write_or(wal, UNSLICE_UNIT_LEVEL_CLKGATE2, - VSUNIT_CLKGATE_DIS_TGL); + wa_write_or(wal, UNSLICE_UNIT_LEVEL_CLKGATE2, VSUNIT_CLKGATE_DIS_TGL); } static void @@ -1470,6 +1497,12 @@ xehpsdv_gt_workarounds_init(struct intel_gt *gt, struct i915_wa_list *wal) /* Wa_1409757795:xehpsdv */ wa_mcr_write_or(wal, SCCGCTL94DC, CG3DDISURB); + /* Wa_18011725039:xehpsdv */ + if (IS_XEHPSDV_GRAPHICS_STEP(i915, STEP_A1, STEP_B0)) { + wa_mcr_masked_dis(wal, MLTICTXCTL, TDONRENDER); + wa_mcr_write_or(wal, L3SQCREG1_CCS0, FLUSHALLNONCOH); + } + /* Wa_16011155590:xehpsdv */ if (IS_XEHPSDV_GRAPHICS_STEP(i915, STEP_A0, STEP_B0)) wa_write_or(wal, UNSLICE_UNIT_LEVEL_CLKGATE, @@ -1512,6 +1545,16 @@ xehpsdv_gt_workarounds_init(struct intel_gt *gt, struct i915_wa_list *wal) /* Wa_14011060649:xehpsdv */ wa_14011060649(gt, wal); + + /* Wa_14012362059:xehpsdv */ + wa_mcr_write_or(wal, XEHP_MERT_MOD_CTRL, FORCE_MISS_FTLB); + + /* Wa_14014368820:xehpsdv */ + wa_mcr_write_or(wal, XEHP_GAMCNTRL_CTRL, + INVALIDATION_BROADCAST_MODE_DIS | GLOBAL_INVALIDATION_MODE); + + /* Wa_14010670810:xehpsdv */ + wa_mcr_write_or(wal, XEHP_L3NODEARBCFG, XEHP_LNESPARE); } static void @@ -1552,6 +1595,12 @@ dg2_gt_workarounds_init(struct intel_gt *gt, struct i915_wa_list *wal) DSS_ROUTER_CLKGATE_DIS); } + if (IS_DG2_GRAPHICS_STEP(gt->i915, G10, STEP_A0, STEP_B0) || + IS_DG2_GRAPHICS_STEP(gt->i915, G11, STEP_A0, STEP_B0)) { + /* Wa_14012362059:dg2 */ + wa_mcr_write_or(wal, XEHP_MERT_MOD_CTRL, FORCE_MISS_FTLB); + } + if (IS_DG2_GRAPHICS_STEP(gt->i915, G10, STEP_A0, STEP_B0)) { /* Wa_14010948348:dg2_g10 */ wa_write_or(wal, UNSLCGCTL9430, MSQDUNIT_CLKGATE_DIS); @@ -1597,20 +1646,32 @@ dg2_gt_workarounds_init(struct intel_gt *gt, struct i915_wa_list *wal) /* Wa_14011028019:dg2_g10 */ wa_mcr_write_or(wal, SSMCGCTL9530, RTFUNIT_CLKGATE_DIS); + + /* Wa_14010680813:dg2_g10 */ + wa_mcr_write_or(wal, XEHP_GAMSTLB_CTRL, + CONTROL_BLOCK_CLKGATE_DIS | + EGRESS_BLOCK_CLKGATE_DIS | + TAG_BLOCK_CLKGATE_DIS); } /* Wa_14014830051:dg2 */ wa_mcr_write_clr(wal, SARB_CHICKEN1, COMP_CKN_IN); - /* - * The following are not actually "workarounds" but rather - * recommended tuning settings documented in the bspec's - * performance guide section. - */ - wa_mcr_write_or(wal, XEHP_SQCM, EN_32B_ACCESS); - /* Wa_14015795083 */ - wa_mcr_write_clr(wal, GEN8_MISCCPCTL, GEN12_DOP_CLOCK_GATE_RENDER_ENABLE); + wa_write_clr(wal, GEN7_MISCCPCTL, GEN12_DOP_CLOCK_GATE_RENDER_ENABLE); + + /* Wa_18018781329 */ + wa_mcr_write_or(wal, RENDER_MOD_CTRL, FORCE_MISS_FTLB); + wa_mcr_write_or(wal, COMP_MOD_CTRL, FORCE_MISS_FTLB); + wa_mcr_write_or(wal, XEHP_VDBX_MOD_CTRL, FORCE_MISS_FTLB); + wa_mcr_write_or(wal, XEHP_VEBX_MOD_CTRL, FORCE_MISS_FTLB); + + /* Wa_1509235366:dg2 */ + wa_mcr_write_or(wal, XEHP_GAMCNTRL_CTRL, + INVALIDATION_BROADCAST_MODE_DIS | GLOBAL_INVALIDATION_MODE); + + /* Wa_14010648519:dg2 */ + wa_mcr_write_or(wal, XEHP_L3NODEARBCFG, XEHP_LNESPARE); } static void @@ -1619,17 +1680,31 @@ pvc_gt_workarounds_init(struct intel_gt *gt, struct i915_wa_list *wal) pvc_init_mcr(gt, wal); /* Wa_14015795083 */ - wa_mcr_write_clr(wal, GEN8_MISCCPCTL, GEN12_DOP_CLOCK_GATE_RENDER_ENABLE); + wa_write_clr(wal, GEN7_MISCCPCTL, GEN12_DOP_CLOCK_GATE_RENDER_ENABLE); + + /* Wa_18018781329 */ + wa_mcr_write_or(wal, RENDER_MOD_CTRL, FORCE_MISS_FTLB); + wa_mcr_write_or(wal, COMP_MOD_CTRL, FORCE_MISS_FTLB); + wa_mcr_write_or(wal, XEHP_VDBX_MOD_CTRL, FORCE_MISS_FTLB); + wa_mcr_write_or(wal, XEHP_VEBX_MOD_CTRL, FORCE_MISS_FTLB); + + /* Wa_16016694945 */ + wa_mcr_masked_en(wal, XEHPC_LNCFMISCCFGREG0, XEHPC_OVRLSCCC); } static void xelpg_gt_workarounds_init(struct intel_gt *gt, struct i915_wa_list *wal) { - /* Wa_14014830051 */ if (IS_MTL_GRAPHICS_STEP(gt->i915, M, STEP_A0, STEP_B0) || - IS_MTL_GRAPHICS_STEP(gt->i915, P, STEP_A0, STEP_B0)) + IS_MTL_GRAPHICS_STEP(gt->i915, P, STEP_A0, STEP_B0)) { + /* Wa_14014830051 */ wa_mcr_write_clr(wal, SARB_CHICKEN1, COMP_CKN_IN); + /* Wa_18018781329 */ + wa_mcr_write_or(wal, RENDER_MOD_CTRL, FORCE_MISS_FTLB); + wa_mcr_write_or(wal, COMP_MOD_CTRL, FORCE_MISS_FTLB); + } + /* * Unlike older platforms, we no longer setup implicit steering here; * all MCR accesses are explicitly steered. @@ -1640,16 +1715,53 @@ xelpg_gt_workarounds_init(struct intel_gt *gt, struct i915_wa_list *wal) static void xelpmp_gt_workarounds_init(struct intel_gt *gt, struct i915_wa_list *wal) { - /* FIXME: Actual workarounds will be added in future patch(es) */ + if (IS_MTL_MEDIA_STEP(gt->i915, STEP_A0, STEP_B0)) { + /* + * Wa_18018781329 + * + * Note that although these registers are MCR on the primary + * GT, the media GT's versions are regular singleton registers. + */ + wa_write_or(wal, XELPMP_GSC_MOD_CTRL, FORCE_MISS_FTLB); + wa_write_or(wal, XELPMP_VDBX_MOD_CTRL, FORCE_MISS_FTLB); + wa_write_or(wal, XELPMP_VEBX_MOD_CTRL, FORCE_MISS_FTLB); + } debug_dump_steering(gt); } +/* + * The bspec performance guide has recommended MMIO tuning settings. These + * aren't truly "workarounds" but we want to program them through the + * workaround infrastructure to make sure they're (re)applied at the proper + * times. + * + * The programming in this function is for settings that persist through + * engine resets and also are not part of any engine's register state context. + * I.e., settings that only need to be re-applied in the event of a full GT + * reset. + */ +static void gt_tuning_settings(struct intel_gt *gt, struct i915_wa_list *wal) +{ + if (IS_PONTEVECCHIO(gt->i915)) { + wa_mcr_write(wal, XEHPC_L3SCRUB, + SCRUB_CL_DWNGRADE_SHARED | SCRUB_RATE_4B_PER_CLK); + wa_mcr_masked_en(wal, XEHPC_LNCFMISCCFGREG0, XEHPC_HOSTCACHEEN); + } + + if (IS_DG2(gt->i915)) { + wa_mcr_write_or(wal, XEHP_L3SCQREG7, BLEND_FILL_CACHING_OPT_DIS); + wa_mcr_write_or(wal, XEHP_SQCM, EN_32B_ACCESS); + } +} + static void gt_init_workarounds(struct intel_gt *gt, struct i915_wa_list *wal) { struct drm_i915_private *i915 = gt->i915; + gt_tuning_settings(gt, wal); + if (gt->type == GT_MEDIA) { if (MEDIA_VER(i915) >= 13) xelpmp_gt_workarounds_init(gt, wal); @@ -2075,23 +2187,20 @@ static void tgl_whitelist_build(struct intel_engine_cs *engine) /* Wa_1806527549:tgl */ whitelist_reg(w, HIZ_CHICKEN); + + /* Required by recommended tuning setting (not a workaround) */ + whitelist_reg(w, GEN11_COMMON_SLICE_CHICKEN3); + break; default: break; } } -static void xehpsdv_whitelist_build(struct intel_engine_cs *engine) -{ - allow_read_ctx_timestamp(engine); -} - static void dg2_whitelist_build(struct intel_engine_cs *engine) { struct i915_wa_list *w = &engine->whitelist; - allow_read_ctx_timestamp(engine); - switch (engine->class) { case RENDER_CLASS: /* @@ -2108,6 +2217,9 @@ static void dg2_whitelist_build(struct intel_engine_cs *engine) RING_FORCE_TO_NONPRIV_ACCESS_RD | RING_FORCE_TO_NONPRIV_RANGE_4); + /* Required by recommended tuning setting (not a workaround) */ + whitelist_mcr_reg(w, XEHP_COMMON_SLICE_CHICKEN3); + break; case COMPUTE_CLASS: /* Wa_16011157294:dg2_g10 */ @@ -2139,12 +2251,25 @@ static void blacklist_trtt(struct intel_engine_cs *engine) static void pvc_whitelist_build(struct intel_engine_cs *engine) { - allow_read_ctx_timestamp(engine); - /* Wa_16014440446:pvc */ blacklist_trtt(engine); } +static void mtl_whitelist_build(struct intel_engine_cs *engine) +{ + struct i915_wa_list *w = &engine->whitelist; + + switch (engine->class) { + case RENDER_CLASS: + /* Required by recommended tuning setting (not a workaround) */ + whitelist_mcr_reg(w, XEHP_COMMON_SLICE_CHICKEN3); + + break; + default: + break; + } +} + void intel_engine_init_whitelist(struct intel_engine_cs *engine) { struct drm_i915_private *i915 = engine->i915; @@ -2153,13 +2278,13 @@ void intel_engine_init_whitelist(struct intel_engine_cs *engine) wa_init_start(w, engine->gt, "whitelist", engine->name); if (IS_METEORLAKE(i915)) - ; /* noop; none at this time */ + mtl_whitelist_build(engine); else if (IS_PONTEVECCHIO(i915)) pvc_whitelist_build(engine); else if (IS_DG2(i915)) dg2_whitelist_build(engine); else if (IS_XEHPSDV(i915)) - xehpsdv_whitelist_build(engine); + ; /* none needed */ else if (GRAPHICS_VER(i915) == 12) tgl_whitelist_build(engine); else if (GRAPHICS_VER(i915) == 11) @@ -2276,10 +2401,6 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal) /* Wa_1509727124 */ wa_mcr_masked_en(wal, GEN10_SAMPLER_MODE, SC_DISABLE_POWER_OPTIMIZATION_EBB); - - /* Wa_22013037850 */ - wa_mcr_write_or(wal, LSC_CHICKEN_BIT_0_UDW, - DISABLE_128B_EVICTION_COMMAND_UDW); } if (IS_DG2_GRAPHICS_STEP(i915, G10, STEP_B0, STEP_FOREVER) || @@ -2290,12 +2411,6 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal) GEN12_DISABLE_READ_SUPPRESSION); } - if (IS_DG2(i915)) { - /* Wa_1509235366:dg2 */ - wa_write_or(wal, GEN12_GAMCNTRL_CTRL, INVALIDATION_BROADCAST_MODE_DIS | - GLOBAL_INVALIDATION_MODE); - } - if (IS_DG2_GRAPHICS_STEP(i915, G11, STEP_A0, STEP_B0)) { /* Wa_14013392000:dg2_g11 */ wa_mcr_masked_en(wal, GEN8_ROW_CHICKEN2, GEN12_ENABLE_LARGE_GRF_MODE); @@ -2308,21 +2423,6 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal) GEN12_DISABLE_HDR_PAST_PAYLOAD_HOLD_FIX); } - if (IS_DG2_GRAPHICS_STEP(i915, G10, STEP_B0, STEP_C0) || - IS_DG2_G11(i915)) { - /* - * Wa_22012826095:dg2 - * Wa_22013059131:dg2 - */ - wa_mcr_write_clr_set(wal, LSC_CHICKEN_BIT_0_UDW, - MAXREQS_PER_BANK, - REG_FIELD_PREP(MAXREQS_PER_BANK, 2)); - - /* Wa_22013059131:dg2 */ - wa_mcr_write_or(wal, LSC_CHICKEN_BIT_0, - FORCE_1_SUB_MESSAGE_PER_FRAGMENT); - } - /* Wa_1308578152:dg2_g10 when first gslice is fused off */ if (IS_DG2_GRAPHICS_STEP(i915, G10, STEP_B0, STEP_C0) && needs_wa_1308578152(engine)) { @@ -2347,28 +2447,14 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal) */ wa_mcr_masked_en(wal, GEN8_ROW_CHICKEN, MDQ_ARBITRATION_MODE | UGM_BACKUP_MODE); - - /* - * Wa_14010918519:dg2_g10 - * - * LSC_CHICKEN_BIT_0 always reads back as 0 is this stepping, - * so ignoring verification. - */ - wa_mcr_add(wal, LSC_CHICKEN_BIT_0_UDW, 0, - FORCE_SLM_FENCE_SCOPE_TO_TILE | FORCE_UGM_FENCE_SCOPE_TO_TILE, - 0, false); } - if (IS_DG2_GRAPHICS_STEP(i915, G10, STEP_A0, STEP_B0)) { + if (IS_DG2_GRAPHICS_STEP(i915, G10, STEP_A0, STEP_B0)) /* Wa_22010430635:dg2 */ wa_mcr_masked_en(wal, GEN9_ROW_CHICKEN4, GEN12_DISABLE_GRF_CLEAR); - /* Wa_14010648519:dg2 */ - wa_mcr_write_or(wal, XEHP_L3NODEARBCFG, XEHP_LNESPARE); - } - /* Wa_14013202645:dg2 */ if (IS_DG2_GRAPHICS_STEP(i915, G10, STEP_B0, STEP_C0) || IS_DG2_GRAPHICS_STEP(i915, G11, STEP_A0, STEP_B0)) @@ -2380,18 +2466,6 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal) wa_mcr_masked_en(wal, GEN9_HALF_SLICE_CHICKEN7, DG2_DISABLE_ROUND_ENABLE_ALLOW_FOR_SSLA); - if (IS_DG2_GRAPHICS_STEP(engine->i915, G10, STEP_A0, STEP_B0)) { - /* Wa_14010680813:dg2_g10 */ - wa_write_or(wal, GEN12_GAMSTLB_CTRL, CONTROL_BLOCK_CLKGATE_DIS | - EGRESS_BLOCK_CLKGATE_DIS | TAG_BLOCK_CLKGATE_DIS); - } - - if (IS_DG2_GRAPHICS_STEP(engine->i915, G10, STEP_A0, STEP_B0) || - IS_DG2_GRAPHICS_STEP(engine->i915, G11, STEP_A0, STEP_B0)) { - /* Wa_14012362059:dg2 */ - wa_mcr_write_or(wal, XEHP_MERT_MOD_CTRL, FORCE_MISS_FTLB); - } - if (IS_DG2_GRAPHICS_STEP(i915, G11, STEP_B0, STEP_FOREVER) || IS_DG2_G10(i915)) { /* Wa_22014600077:dg2 */ @@ -2512,13 +2586,6 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal) GEN11_ENABLE_32_PLANE_MODE); /* - * Wa_1408615072:icl,ehl (vsunit) - * Wa_1407596294:icl,ehl (hsunit) - */ - wa_write_or(wal, UNSLICE_UNIT_LEVEL_CLKGATE, - VSUNIT_CLKGATE_DIS | HSUNIT_CLKGATE_DIS); - - /* * Wa_1408767742:icl[a2..forever],ehl[all] * Wa_1605460711:icl[a0..c0] */ @@ -2872,16 +2939,8 @@ static void add_render_compute_tuning_settings(struct drm_i915_private *i915, struct i915_wa_list *wal) { - if (IS_PONTEVECCHIO(i915)) { - wa_write(wal, XEHPC_L3SCRUB, - SCRUB_CL_DWNGRADE_SHARED | SCRUB_RATE_4B_PER_CLK); - wa_masked_en(wal, XEHPC_LNCFMISCCFGREG0, XEHPC_HOSTCACHEEN); - } - - if (IS_DG2(i915)) { - wa_mcr_write_or(wal, XEHP_L3SCQREG7, BLEND_FILL_CACHING_OPT_DIS); + if (IS_DG2(i915)) wa_mcr_write_clr_set(wal, RT_CTRL, STACKID_CTRL, STACKID_CTRL_512); - } /* * This tuning setting proves beneficial only on ATS-M designs; the @@ -2914,14 +2973,17 @@ general_render_compute_wa_init(struct intel_engine_cs *engine, struct i915_wa_li if (IS_MTL_GRAPHICS_STEP(i915, M, STEP_A0, STEP_B0) || IS_MTL_GRAPHICS_STEP(i915, P, STEP_A0, STEP_B0) || + IS_DG2_GRAPHICS_STEP(i915, G10, STEP_B0, STEP_FOREVER) || + IS_DG2_G11(i915) || IS_DG2_G12(i915)) { + /* Wa_22013037850 */ + wa_mcr_write_or(wal, LSC_CHICKEN_BIT_0_UDW, + DISABLE_128B_EVICTION_COMMAND_UDW); + } + + if (IS_MTL_GRAPHICS_STEP(i915, M, STEP_A0, STEP_B0) || + IS_MTL_GRAPHICS_STEP(i915, P, STEP_A0, STEP_B0) || IS_PONTEVECCHIO(i915) || IS_DG2(i915)) { - /* Wa_18018781329 */ - wa_mcr_write_or(wal, RENDER_MOD_CTRL, FORCE_MISS_FTLB); - wa_mcr_write_or(wal, COMP_MOD_CTRL, FORCE_MISS_FTLB); - wa_mcr_write_or(wal, VDBX_MOD_CTRL, FORCE_MISS_FTLB); - wa_mcr_write_or(wal, VEBX_MOD_CTRL, FORCE_MISS_FTLB); - /* Wa_22014226127 */ wa_mcr_write_or(wal, LSC_CHICKEN_BIT_0, DISABLE_D8_D16_COASLESCE); } @@ -2933,9 +2995,31 @@ general_render_compute_wa_init(struct intel_engine_cs *engine, struct i915_wa_li wa_masked_en(wal, VFG_PREEMPTION_CHICKEN, POLYGON_TRIFAN_LINELOOP_DISABLE); } - if (IS_PONTEVECCHIO(i915)) { - /* Wa_16016694945 */ - wa_masked_en(wal, XEHPC_LNCFMISCCFGREG0, XEHPC_OVRLSCCC); + if (IS_DG2_GRAPHICS_STEP(i915, G10, STEP_B0, STEP_C0) || + IS_DG2_G11(i915)) { + /* + * Wa_22012826095:dg2 + * Wa_22013059131:dg2 + */ + wa_mcr_write_clr_set(wal, LSC_CHICKEN_BIT_0_UDW, + MAXREQS_PER_BANK, + REG_FIELD_PREP(MAXREQS_PER_BANK, 2)); + + /* Wa_22013059131:dg2 */ + wa_mcr_write_or(wal, LSC_CHICKEN_BIT_0, + FORCE_1_SUB_MESSAGE_PER_FRAGMENT); + } + + if (IS_DG2_GRAPHICS_STEP(i915, G10, STEP_A0, STEP_B0)) { + /* + * Wa_14010918519:dg2_g10 + * + * LSC_CHICKEN_BIT_0 always reads back as 0 is this stepping, + * so ignoring verification. + */ + wa_mcr_add(wal, LSC_CHICKEN_BIT_0_UDW, 0, + FORCE_SLM_FENCE_SCOPE_TO_TILE | FORCE_UGM_FENCE_SCOPE_TO_TILE, + 0, false); } if (IS_XEHPSDV(i915)) { @@ -2949,25 +3033,9 @@ general_render_compute_wa_init(struct intel_engine_cs *engine, struct i915_wa_li GEN9_ROW_CHICKEN4, GEN12_DISABLE_GRF_CLEAR); - /* Wa_14010670810:xehpsdv */ - wa_mcr_write_or(wal, XEHP_L3NODEARBCFG, XEHP_LNESPARE); - /* Wa_14010449647:xehpsdv */ wa_mcr_masked_en(wal, GEN8_HALF_SLICE_CHICKEN1, GEN7_PSD_SINGLE_PORT_DISPATCH_ENABLE); - - /* Wa_18011725039:xehpsdv */ - if (IS_XEHPSDV_GRAPHICS_STEP(i915, STEP_A1, STEP_B0)) { - wa_mcr_masked_dis(wal, MLTICTXCTL, TDONRENDER); - wa_mcr_write_or(wal, L3SQCREG1_CCS0, FLUSHALLNONCOH); - } - - /* Wa_14012362059:xehpsdv */ - wa_mcr_write_or(wal, XEHP_MERT_MOD_CTRL, FORCE_MISS_FTLB); - - /* Wa_14014368820:xehpsdv */ - wa_write_or(wal, GEN12_GAMCNTRL_CTRL, INVALIDATION_BROADCAST_MODE_DIS | - GLOBAL_INVALIDATION_MODE); } if (IS_DG2(i915) || IS_PONTEVECCHIO(i915)) { diff --git a/drivers/gpu/drm/i915/gt/selftest_gt_pm.c b/drivers/gpu/drm/i915/gt/selftest_gt_pm.c index b46425aeb2f0..0971241707ce 100644 --- a/drivers/gpu/drm/i915/gt/selftest_gt_pm.c +++ b/drivers/gpu/drm/i915/gt/selftest_gt_pm.c @@ -63,8 +63,8 @@ static void measure_clocks(struct intel_engine_cs *engine, udelay(1000); - dt[i] = ktime_sub(ktime_get(), dt[i]); cycles[i] += read_timestamp(engine); + dt[i] = ktime_sub(ktime_get(), dt[i]); local_irq_enable(); } diff --git a/drivers/gpu/drm/i915/gt/selftest_rps.c b/drivers/gpu/drm/i915/gt/selftest_rps.c index 6755bbc4ebda..84e77e8dbba1 100644 --- a/drivers/gpu/drm/i915/gt/selftest_rps.c +++ b/drivers/gpu/drm/i915/gt/selftest_rps.c @@ -299,13 +299,13 @@ int live_rps_clock_interval(void *arg) for (i = 0; i < 5; i++) { preempt_disable(); - dt_[i] = ktime_get(); cycles_[i] = -intel_uncore_read_fw(gt->uncore, GEN6_RP_CUR_UP_EI); + dt_[i] = ktime_get(); udelay(1000); - dt_[i] = ktime_sub(ktime_get(), dt_[i]); cycles_[i] += intel_uncore_read_fw(gt->uncore, GEN6_RP_CUR_UP_EI); + dt_[i] = ktime_sub(ktime_get(), dt_[i]); preempt_enable(); } @@ -537,8 +537,8 @@ static u64 __measure_frequency(u32 *cntr, int duration_ms) { u64 dc, dt; - dt = ktime_get(); dc = READ_ONCE(*cntr); + dt = ktime_get(); usleep_range(1000 * duration_ms, 2000 * duration_ms); dc = READ_ONCE(*cntr) - dc; dt = ktime_get() - dt; @@ -566,8 +566,8 @@ static u64 __measure_cs_frequency(struct intel_engine_cs *engine, { u64 dc, dt; - dt = ktime_get(); dc = intel_uncore_read_fw(engine->uncore, CS_GPR(0)); + dt = ktime_get(); usleep_range(1000 * duration_ms, 2000 * duration_ms); dc = intel_uncore_read_fw(engine->uncore, CS_GPR(0)) - dc; dt = ktime_get() - dt; @@ -1094,8 +1094,8 @@ static u64 __measure_power(int duration_ms) { u64 dE, dt; - dt = ktime_get(); dE = librapl_energy_uJ(); + dt = ktime_get(); usleep_range(1000 * duration_ms, 2000 * duration_ms); dE = librapl_energy_uJ() - dE; dt = ktime_get() - dt; diff --git a/drivers/gpu/drm/i915/gt/selftest_tlb.c b/drivers/gpu/drm/i915/gt/selftest_tlb.c new file mode 100644 index 000000000000..e6cac1f15d6e --- /dev/null +++ b/drivers/gpu/drm/i915/gt/selftest_tlb.c @@ -0,0 +1,388 @@ +// SPDX-License-Identifier: MIT +/* + * Copyright © 2022 Intel Corporation + */ + +#include "i915_selftest.h" + +#include "gem/i915_gem_internal.h" +#include "gem/i915_gem_region.h" + +#include "gen8_engine_cs.h" +#include "i915_gem_ww.h" +#include "intel_engine_regs.h" +#include "intel_gpu_commands.h" +#include "intel_context.h" +#include "intel_gt.h" +#include "intel_ring.h" + +#include "selftests/igt_flush_test.h" +#include "selftests/i915_random.h" + +static void vma_set_qw(struct i915_vma *vma, u64 addr, u64 val) +{ + GEM_BUG_ON(addr < i915_vma_offset(vma)); + GEM_BUG_ON(addr >= i915_vma_offset(vma) + i915_vma_size(vma) + sizeof(val)); + memset64(page_mask_bits(vma->obj->mm.mapping) + + (addr - i915_vma_offset(vma)), val, 1); +} + +static int +pte_tlbinv(struct intel_context *ce, + struct i915_vma *va, + struct i915_vma *vb, + u64 align, + void (*tlbinv)(struct i915_address_space *vm, u64 addr, u64 length), + u64 length, + struct rnd_state *prng) +{ + struct drm_i915_gem_object *batch; + struct drm_mm_node vb_node; + struct i915_request *rq; + struct i915_vma *vma; + u64 addr; + int err; + u32 *cs; + + batch = i915_gem_object_create_internal(ce->vm->i915, 4096); + if (IS_ERR(batch)) + return PTR_ERR(batch); + + vma = i915_vma_instance(batch, ce->vm, NULL); + if (IS_ERR(vma)) { + err = PTR_ERR(vma); + goto out; + } + + err = i915_vma_pin(vma, 0, 0, PIN_USER); + if (err) + goto out; + + /* Pin va at random but aligned offset after vma */ + addr = round_up(vma->node.start + vma->node.size, align); + /* MI_CONDITIONAL_BATCH_BUFFER_END limits address to 48b */ + addr = igt_random_offset(prng, addr, min(ce->vm->total, BIT_ULL(48)), + va->size, align); + err = i915_vma_pin(va, 0, 0, addr | PIN_OFFSET_FIXED | PIN_USER); + if (err) { + pr_err("Cannot pin at %llx+%llx\n", addr, va->size); + goto out; + } + GEM_BUG_ON(i915_vma_offset(va) != addr); + if (vb != va) { + vb_node = vb->node; + vb->node = va->node; /* overwrites the _same_ PTE */ + } + + /* + * Now choose random dword at the 1st pinned page. + * + * SZ_64K pages on dg1 require that the whole PT be marked + * containing 64KiB entries. So we make sure that vma + * covers the whole PT, despite being randomly aligned to 64KiB + * and restrict our sampling to the 2MiB PT within where + * we know that we will be using 64KiB pages. + */ + if (align == SZ_64K) + addr = round_up(addr, SZ_2M); + addr = igt_random_offset(prng, addr, addr + align, 8, 8); + + if (va != vb) + pr_info("%s(%s): Sampling %llx, with alignment %llx, using PTE size %x (phys %x, sg %x), invalidate:%llx+%llx\n", + ce->engine->name, va->obj->mm.region->name ?: "smem", + addr, align, va->resource->page_sizes_gtt, + va->page_sizes.phys, va->page_sizes.sg, + addr & -length, length); + + cs = i915_gem_object_pin_map_unlocked(batch, I915_MAP_WC); + *cs++ = MI_NOOP; /* for later termination */ + /* + * Sample the target to see if we spot the updated backing store. + * Gen8 VCS compares immediate value with bitwise-and of two + * consecutive DWORDS pointed by addr, other gen/engines compare value + * with DWORD pointed by addr. Moreover we want to exercise DWORD size + * invalidations. To fulfill all these requirements below values + * have been chosen. + */ + *cs++ = MI_CONDITIONAL_BATCH_BUFFER_END | MI_DO_COMPARE | 2; + *cs++ = 0; /* break if *addr == 0 */ + *cs++ = lower_32_bits(addr); + *cs++ = upper_32_bits(addr); + vma_set_qw(va, addr, -1); + vma_set_qw(vb, addr, 0); + + /* Keep sampling until we get bored */ + *cs++ = MI_BATCH_BUFFER_START | BIT(8) | 1; + *cs++ = lower_32_bits(i915_vma_offset(vma)); + *cs++ = upper_32_bits(i915_vma_offset(vma)); + + i915_gem_object_flush_map(batch); + + rq = i915_request_create(ce); + if (IS_ERR(rq)) { + err = PTR_ERR(rq); + goto out_va; + } + + err = rq->engine->emit_bb_start(rq, i915_vma_offset(vma), 0, 0); + if (err) { + i915_request_add(rq); + goto out_va; + } + + i915_request_get(rq); + i915_request_add(rq); + + /* Short sleep to sanitycheck the batch is spinning before we begin */ + msleep(10); + if (va == vb) { + if (!i915_request_completed(rq)) { + pr_err("%s(%s): Semaphore sanitycheck failed %llx, with alignment %llx, using PTE size %x (phys %x, sg %x)\n", + ce->engine->name, va->obj->mm.region->name ?: "smem", + addr, align, va->resource->page_sizes_gtt, + va->page_sizes.phys, va->page_sizes.sg); + err = -EIO; + } + } else if (!i915_request_completed(rq)) { + struct i915_vma_resource vb_res = { + .bi.pages = vb->obj->mm.pages, + .bi.page_sizes = vb->obj->mm.page_sizes, + .start = i915_vma_offset(vb), + .vma_size = i915_vma_size(vb) + }; + unsigned int pte_flags = 0; + + /* Flip the PTE between A and B */ + if (i915_gem_object_is_lmem(vb->obj)) + pte_flags |= PTE_LM; + ce->vm->insert_entries(ce->vm, &vb_res, 0, pte_flags); + + /* Flush the PTE update to concurrent HW */ + tlbinv(ce->vm, addr & -length, length); + + if (wait_for(i915_request_completed(rq), HZ / 2)) { + pr_err("%s: Request did not complete; the COND_BBE did not read the updated PTE\n", + ce->engine->name); + err = -EINVAL; + } + } else { + pr_err("Spinner ended unexpectedly\n"); + err = -EIO; + } + i915_request_put(rq); + + cs = page_mask_bits(batch->mm.mapping); + *cs = MI_BATCH_BUFFER_END; + wmb(); + +out_va: + if (vb != va) + vb->node = vb_node; + i915_vma_unpin(va); + if (i915_vma_unbind_unlocked(va)) + err = -EIO; +out: + i915_gem_object_put(batch); + return err; +} + +static struct drm_i915_gem_object *create_lmem(struct intel_gt *gt) +{ + /* + * Allocation of largest possible page size allows to test all types + * of pages. + */ + return i915_gem_object_create_lmem(gt->i915, SZ_1G, I915_BO_ALLOC_CONTIGUOUS); +} + +static struct drm_i915_gem_object *create_smem(struct intel_gt *gt) +{ + /* + * SZ_64K pages require covering the whole 2M PT (gen8 to tgl/dg1). + * While that does not require the whole 2M block to be contiguous + * it is easier to make it so, since we need that for SZ_2M pagees. + * Since we randomly offset the start of the vma, we need a 4M object + * so that there is a 2M range within it is suitable for SZ_64K PTE. + */ + return i915_gem_object_create_internal(gt->i915, SZ_4M); +} + +static int +mem_tlbinv(struct intel_gt *gt, + struct drm_i915_gem_object *(*create_fn)(struct intel_gt *), + void (*tlbinv)(struct i915_address_space *vm, u64 addr, u64 length)) +{ + unsigned int ppgtt_size = RUNTIME_INFO(gt->i915)->ppgtt_size; + struct intel_engine_cs *engine; + struct drm_i915_gem_object *A, *B; + struct i915_ppgtt *ppgtt; + struct i915_vma *va, *vb; + enum intel_engine_id id; + I915_RND_STATE(prng); + void *vaddr; + int err; + + /* + * Check that the TLB invalidate is able to revoke an active + * page. We load a page into a spinning COND_BBE loop and then + * remap that page to a new physical address. The old address, and + * so the loop keeps spinning, is retained in the TLB cache until + * we issue an invalidate. + */ + + A = create_fn(gt); + if (IS_ERR(A)) + return PTR_ERR(A); + + vaddr = i915_gem_object_pin_map_unlocked(A, I915_MAP_WC); + if (IS_ERR(vaddr)) { + err = PTR_ERR(vaddr); + goto out_a; + } + + B = create_fn(gt); + if (IS_ERR(B)) { + err = PTR_ERR(B); + goto out_a; + } + + vaddr = i915_gem_object_pin_map_unlocked(B, I915_MAP_WC); + if (IS_ERR(vaddr)) { + err = PTR_ERR(vaddr); + goto out_b; + } + + GEM_BUG_ON(A->base.size != B->base.size); + if ((A->mm.page_sizes.phys | B->mm.page_sizes.phys) & (A->base.size - 1)) + pr_warn("Failed to allocate contiguous pages for size %zx\n", + A->base.size); + + ppgtt = i915_ppgtt_create(gt, 0); + if (IS_ERR(ppgtt)) { + err = PTR_ERR(ppgtt); + goto out_b; + } + + va = i915_vma_instance(A, &ppgtt->vm, NULL); + if (IS_ERR(va)) { + err = PTR_ERR(va); + goto out_vm; + } + + vb = i915_vma_instance(B, &ppgtt->vm, NULL); + if (IS_ERR(vb)) { + err = PTR_ERR(vb); + goto out_vm; + } + + err = 0; + for_each_engine(engine, gt, id) { + struct i915_gem_ww_ctx ww; + struct intel_context *ce; + int bit; + + ce = intel_context_create(engine); + if (IS_ERR(ce)) { + err = PTR_ERR(ce); + break; + } + + i915_vm_put(ce->vm); + ce->vm = i915_vm_get(&ppgtt->vm); + + for_i915_gem_ww(&ww, err, true) + err = intel_context_pin_ww(ce, &ww); + if (err) + goto err_put; + + for_each_set_bit(bit, + (unsigned long *)&RUNTIME_INFO(gt->i915)->page_sizes, + BITS_PER_TYPE(RUNTIME_INFO(gt->i915)->page_sizes)) { + unsigned int len; + + if (BIT_ULL(bit) < i915_vm_obj_min_alignment(va->vm, va->obj)) + continue; + + /* sanitycheck the semaphore wake up */ + err = pte_tlbinv(ce, va, va, + BIT_ULL(bit), + NULL, SZ_4K, + &prng); + if (err) + goto err_unpin; + + for (len = 2; len <= ppgtt_size; len = min(2 * len, ppgtt_size)) { + err = pte_tlbinv(ce, va, vb, + BIT_ULL(bit), + tlbinv, + BIT_ULL(len), + &prng); + if (err) + goto err_unpin; + if (len == ppgtt_size) + break; + } + } +err_unpin: + intel_context_unpin(ce); +err_put: + intel_context_put(ce); + if (err) + break; + } + + if (igt_flush_test(gt->i915)) + err = -EIO; + +out_vm: + i915_vm_put(&ppgtt->vm); +out_b: + i915_gem_object_put(B); +out_a: + i915_gem_object_put(A); + return err; +} + +static void tlbinv_full(struct i915_address_space *vm, u64 addr, u64 length) +{ + intel_gt_invalidate_tlb(vm->gt, intel_gt_tlb_seqno(vm->gt) | 1); +} + +static int invalidate_full(void *arg) +{ + struct intel_gt *gt = arg; + int err; + + if (GRAPHICS_VER(gt->i915) < 8) + return 0; /* TLB invalidate not implemented */ + + err = mem_tlbinv(gt, create_smem, tlbinv_full); + if (err == 0) + err = mem_tlbinv(gt, create_lmem, tlbinv_full); + if (err == -ENODEV || err == -ENXIO) + err = 0; + + return err; +} + +int intel_tlb_live_selftests(struct drm_i915_private *i915) +{ + static const struct i915_subtest tests[] = { + SUBTEST(invalidate_full), + }; + struct intel_gt *gt; + unsigned int i; + + for_each_gt(gt, i915, i) { + int err; + + if (intel_gt_is_wedged(gt)) + continue; + + err = intel_gt_live_subtests(tests, gt); + if (err) + return err; + } + + return 0; +} diff --git a/drivers/gpu/drm/i915/gt/sysfs_engines.c b/drivers/gpu/drm/i915/gt/sysfs_engines.c index f2d9858d827c..021f51d9b456 100644 --- a/drivers/gpu/drm/i915/gt/sysfs_engines.c +++ b/drivers/gpu/drm/i915/gt/sysfs_engines.c @@ -24,37 +24,37 @@ static struct intel_engine_cs *kobj_to_engine(struct kobject *kobj) static ssize_t name_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { - return sprintf(buf, "%s\n", kobj_to_engine(kobj)->name); + return sysfs_emit(buf, "%s\n", kobj_to_engine(kobj)->name); } -static struct kobj_attribute name_attr = +static const struct kobj_attribute name_attr = __ATTR(name, 0444, name_show, NULL); static ssize_t class_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { - return sprintf(buf, "%d\n", kobj_to_engine(kobj)->uabi_class); + return sysfs_emit(buf, "%d\n", kobj_to_engine(kobj)->uabi_class); } -static struct kobj_attribute class_attr = +static const struct kobj_attribute class_attr = __ATTR(class, 0444, class_show, NULL); static ssize_t inst_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { - return sprintf(buf, "%d\n", kobj_to_engine(kobj)->uabi_instance); + return sysfs_emit(buf, "%d\n", kobj_to_engine(kobj)->uabi_instance); } -static struct kobj_attribute inst_attr = +static const struct kobj_attribute inst_attr = __ATTR(instance, 0444, inst_show, NULL); static ssize_t mmio_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { - return sprintf(buf, "0x%x\n", kobj_to_engine(kobj)->mmio_base); + return sysfs_emit(buf, "0x%x\n", kobj_to_engine(kobj)->mmio_base); } -static struct kobj_attribute mmio_attr = +static const struct kobj_attribute mmio_attr = __ATTR(mmio_base, 0444, mmio_show, NULL); static const char * const vcs_caps[] = { @@ -107,11 +107,9 @@ __caps_show(struct intel_engine_cs *engine, for_each_set_bit(n, &caps, show_unknown ? BITS_PER_LONG : count) { if (n >= count || !repr[n]) { if (GEM_WARN_ON(show_unknown)) - len += snprintf(buf + len, PAGE_SIZE - len, - "[%x] ", n); + len += sysfs_emit_at(buf, len, "[%x] ", n); } else { - len += snprintf(buf + len, PAGE_SIZE - len, - "%s ", repr[n]); + len += sysfs_emit_at(buf, len, "%s ", repr[n]); } if (GEM_WARN_ON(len >= PAGE_SIZE)) break; @@ -127,7 +125,7 @@ caps_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) return __caps_show(engine, engine->uabi_capabilities, buf, true); } -static struct kobj_attribute caps_attr = +static const struct kobj_attribute caps_attr = __ATTR(capabilities, 0444, caps_show, NULL); static ssize_t @@ -136,7 +134,7 @@ all_caps_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) return __caps_show(kobj_to_engine(kobj), -1, buf, false); } -static struct kobj_attribute all_caps_attr = +static const struct kobj_attribute all_caps_attr = __ATTR(known_capabilities, 0444, all_caps_show, NULL); static ssize_t @@ -182,10 +180,10 @@ max_spin_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { struct intel_engine_cs *engine = kobj_to_engine(kobj); - return sprintf(buf, "%lu\n", engine->props.max_busywait_duration_ns); + return sysfs_emit(buf, "%lu\n", engine->props.max_busywait_duration_ns); } -static struct kobj_attribute max_spin_attr = +static const struct kobj_attribute max_spin_attr = __ATTR(max_busywait_duration_ns, 0644, max_spin_show, max_spin_store); static ssize_t @@ -193,10 +191,10 @@ max_spin_default(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { struct intel_engine_cs *engine = kobj_to_engine(kobj); - return sprintf(buf, "%lu\n", engine->defaults.max_busywait_duration_ns); + return sysfs_emit(buf, "%lu\n", engine->defaults.max_busywait_duration_ns); } -static struct kobj_attribute max_spin_def = +static const struct kobj_attribute max_spin_def = __ATTR(max_busywait_duration_ns, 0444, max_spin_default, NULL); static ssize_t @@ -236,10 +234,10 @@ timeslice_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { struct intel_engine_cs *engine = kobj_to_engine(kobj); - return sprintf(buf, "%lu\n", engine->props.timeslice_duration_ms); + return sysfs_emit(buf, "%lu\n", engine->props.timeslice_duration_ms); } -static struct kobj_attribute timeslice_duration_attr = +static const struct kobj_attribute timeslice_duration_attr = __ATTR(timeslice_duration_ms, 0644, timeslice_show, timeslice_store); static ssize_t @@ -247,10 +245,10 @@ timeslice_default(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { struct intel_engine_cs *engine = kobj_to_engine(kobj); - return sprintf(buf, "%lu\n", engine->defaults.timeslice_duration_ms); + return sysfs_emit(buf, "%lu\n", engine->defaults.timeslice_duration_ms); } -static struct kobj_attribute timeslice_duration_def = +static const struct kobj_attribute timeslice_duration_def = __ATTR(timeslice_duration_ms, 0444, timeslice_default, NULL); static ssize_t @@ -287,10 +285,10 @@ stop_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { struct intel_engine_cs *engine = kobj_to_engine(kobj); - return sprintf(buf, "%lu\n", engine->props.stop_timeout_ms); + return sysfs_emit(buf, "%lu\n", engine->props.stop_timeout_ms); } -static struct kobj_attribute stop_timeout_attr = +static const struct kobj_attribute stop_timeout_attr = __ATTR(stop_timeout_ms, 0644, stop_show, stop_store); static ssize_t @@ -298,10 +296,10 @@ stop_default(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { struct intel_engine_cs *engine = kobj_to_engine(kobj); - return sprintf(buf, "%lu\n", engine->defaults.stop_timeout_ms); + return sysfs_emit(buf, "%lu\n", engine->defaults.stop_timeout_ms); } -static struct kobj_attribute stop_timeout_def = +static const struct kobj_attribute stop_timeout_def = __ATTR(stop_timeout_ms, 0444, stop_default, NULL); static ssize_t @@ -343,10 +341,10 @@ preempt_timeout_show(struct kobject *kobj, struct kobj_attribute *attr, { struct intel_engine_cs *engine = kobj_to_engine(kobj); - return sprintf(buf, "%lu\n", engine->props.preempt_timeout_ms); + return sysfs_emit(buf, "%lu\n", engine->props.preempt_timeout_ms); } -static struct kobj_attribute preempt_timeout_attr = +static const struct kobj_attribute preempt_timeout_attr = __ATTR(preempt_timeout_ms, 0644, preempt_timeout_show, preempt_timeout_store); static ssize_t @@ -355,10 +353,10 @@ preempt_timeout_default(struct kobject *kobj, struct kobj_attribute *attr, { struct intel_engine_cs *engine = kobj_to_engine(kobj); - return sprintf(buf, "%lu\n", engine->defaults.preempt_timeout_ms); + return sysfs_emit(buf, "%lu\n", engine->defaults.preempt_timeout_ms); } -static struct kobj_attribute preempt_timeout_def = +static const struct kobj_attribute preempt_timeout_def = __ATTR(preempt_timeout_ms, 0444, preempt_timeout_default, NULL); static ssize_t @@ -399,10 +397,10 @@ heartbeat_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { struct intel_engine_cs *engine = kobj_to_engine(kobj); - return sprintf(buf, "%lu\n", engine->props.heartbeat_interval_ms); + return sysfs_emit(buf, "%lu\n", engine->props.heartbeat_interval_ms); } -static struct kobj_attribute heartbeat_interval_attr = +static const struct kobj_attribute heartbeat_interval_attr = __ATTR(heartbeat_interval_ms, 0644, heartbeat_show, heartbeat_store); static ssize_t @@ -410,10 +408,10 @@ heartbeat_default(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { struct intel_engine_cs *engine = kobj_to_engine(kobj); - return sprintf(buf, "%lu\n", engine->defaults.heartbeat_interval_ms); + return sysfs_emit(buf, "%lu\n", engine->defaults.heartbeat_interval_ms); } -static struct kobj_attribute heartbeat_interval_def = +static const struct kobj_attribute heartbeat_interval_def = __ATTR(heartbeat_interval_ms, 0444, heartbeat_default, NULL); static void kobj_engine_release(struct kobject *kobj) @@ -421,7 +419,7 @@ static void kobj_engine_release(struct kobject *kobj) kfree(kobj); } -static struct kobj_type kobj_engine_type = { +static const struct kobj_type kobj_engine_type = { .release = kobj_engine_release, .sysfs_ops = &kobj_sysfs_ops }; @@ -449,7 +447,7 @@ kobj_engine(struct kobject *dir, struct intel_engine_cs *engine) static void add_defaults(struct kobj_engine *parent) { - static const struct attribute *files[] = { + static const struct attribute * const files[] = { &max_spin_def.attr, &stop_timeout_def.attr, #if CONFIG_DRM_I915_HEARTBEAT_INTERVAL @@ -485,7 +483,7 @@ static void add_defaults(struct kobj_engine *parent) void intel_engines_add_sysfs(struct drm_i915_private *i915) { - static const struct attribute *files[] = { + static const struct attribute * const files[] = { &name_attr.attr, &class_attr.attr, &inst_attr.attr, diff --git a/drivers/gpu/drm/i915/gt/uc/intel_gsc_fw.c b/drivers/gpu/drm/i915/gt/uc/intel_gsc_fw.c index e73d4440c5e8..1d9fdfb11268 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_gsc_fw.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_gsc_fw.c @@ -6,6 +6,7 @@ #include "gt/intel_engine_pm.h" #include "gt/intel_gpu_commands.h" #include "gt/intel_gt.h" +#include "gt/intel_gt_print.h" #include "gt/intel_ring.h" #include "intel_gsc_fw.h" @@ -88,9 +89,8 @@ out_rq: i915_request_put(rq); if (err) - drm_err(&gsc_uc_to_gt(gsc)->i915->drm, - "Request submission for GSC load failed (%d)\n", - err); + gt_err(gsc_uc_to_gt(gsc), "Request submission for GSC load failed %pe\n", + ERR_PTR(err)); return err; } @@ -200,8 +200,7 @@ int intel_gsc_uc_fw_upload(struct intel_gsc_uc *gsc) /* FW is not fully operational until we enable SW proxy */ intel_uc_fw_change_status(gsc_fw, INTEL_UC_FIRMWARE_TRANSFERRED); - drm_info(>->i915->drm, "Loaded GSC firmware %s\n", - gsc_fw->file_selected.path); + gt_info(gt, "Loaded GSC firmware %s\n", gsc_fw->file_selected.path); return 0; diff --git a/drivers/gpu/drm/i915/gt/uc/intel_gsc_uc.c b/drivers/gpu/drm/i915/gt/uc/intel_gsc_uc.c index fd21dbd2663b..2d5b70b3384c 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_gsc_uc.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_gsc_uc.c @@ -6,6 +6,7 @@ #include <linux/types.h> #include "gt/intel_gt.h" +#include "gt/intel_gt_print.h" #include "intel_gsc_uc.h" #include "intel_gsc_fw.h" #include "i915_drv.h" @@ -59,7 +60,6 @@ int intel_gsc_uc_init(struct intel_gsc_uc *gsc) { static struct lock_class_key gsc_lock; struct intel_gt *gt = gsc_uc_to_gt(gsc); - struct drm_i915_private *i915 = gt->i915; struct intel_engine_cs *engine = gt->engine[GSC0]; struct intel_context *ce; struct i915_vma *vma; @@ -81,8 +81,7 @@ int intel_gsc_uc_init(struct intel_gsc_uc *gsc) I915_GEM_HWS_GSC_ADDR, &gsc_lock, "gsc_context"); if (IS_ERR(ce)) { - drm_err(>->i915->drm, - "failed to create GSC CS ctx for FW communication\n"); + gt_err(gt, "failed to create GSC CS ctx for FW communication\n"); err = PTR_ERR(ce); goto out_vma; } @@ -98,7 +97,7 @@ out_vma: out_fw: intel_uc_fw_fini(&gsc->fw); out: - i915_probe_error(i915, "failed with %d\n", err); + gt_probe_error(gt, "GSC init failed %pe\n", ERR_PTR(err)); return err; } @@ -117,7 +116,7 @@ void intel_gsc_uc_fini(struct intel_gsc_uc *gsc) intel_uc_fw_fini(&gsc->fw); } -void intel_gsc_uc_suspend(struct intel_gsc_uc *gsc) +void intel_gsc_uc_flush_work(struct intel_gsc_uc *gsc) { if (!intel_uc_fw_is_loadable(&gsc->fw)) return; @@ -125,6 +124,25 @@ void intel_gsc_uc_suspend(struct intel_gsc_uc *gsc) flush_work(&gsc->work); } +void intel_gsc_uc_resume(struct intel_gsc_uc *gsc) +{ + if (!intel_uc_fw_is_loadable(&gsc->fw)) + return; + + /* + * we only want to start the GSC worker from here in the actual resume + * flow and not during driver load. This is because GSC load is slow and + * therefore we want to make sure that the default state init completes + * first to not slow down the init thread. A separate call to + * intel_gsc_uc_load_start will ensure that the GSC is loaded during + * driver load. + */ + if (!gsc_uc_to_gt(gsc)->engine[GSC0]->default_state) + return; + + intel_gsc_uc_load_start(gsc); +} + void intel_gsc_uc_load_start(struct intel_gsc_uc *gsc) { if (!intel_uc_fw_is_loadable(&gsc->fw)) diff --git a/drivers/gpu/drm/i915/gt/uc/intel_gsc_uc.h b/drivers/gpu/drm/i915/gt/uc/intel_gsc_uc.h index 03fd0a8e8db1..5f50fa1ff8b9 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_gsc_uc.h +++ b/drivers/gpu/drm/i915/gt/uc/intel_gsc_uc.h @@ -26,6 +26,8 @@ void intel_gsc_uc_init_early(struct intel_gsc_uc *gsc); int intel_gsc_uc_init(struct intel_gsc_uc *gsc); void intel_gsc_uc_fini(struct intel_gsc_uc *gsc); void intel_gsc_uc_suspend(struct intel_gsc_uc *gsc); +void intel_gsc_uc_resume(struct intel_gsc_uc *gsc); +void intel_gsc_uc_flush_work(struct intel_gsc_uc *gsc); void intel_gsc_uc_load_start(struct intel_gsc_uc *gsc); static inline bool intel_gsc_uc_is_supported(struct intel_gsc_uc *gsc) diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc.c b/drivers/gpu/drm/i915/gt/uc/intel_guc.c index 1bccc175f9e6..d76508fa3af7 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc.c @@ -11,6 +11,7 @@ #include "intel_guc.h" #include "intel_guc_ads.h" #include "intel_guc_capture.h" +#include "intel_guc_print.h" #include "intel_guc_slpc.h" #include "intel_guc_submission.h" #include "i915_drv.h" @@ -94,8 +95,8 @@ static void gen9_enable_guc_interrupts(struct intel_guc *guc) assert_rpm_wakelock_held(>->i915->runtime_pm); spin_lock_irq(gt->irq_lock); - WARN_ON_ONCE(intel_uncore_read(gt->uncore, GEN8_GT_IIR(2)) & - gt->pm_guc_events); + guc_WARN_ON_ONCE(guc, intel_uncore_read(gt->uncore, GEN8_GT_IIR(2)) & + gt->pm_guc_events); gen6_gt_pm_enable_irq(gt, gt->pm_guc_events); spin_unlock_irq(gt->irq_lock); @@ -342,7 +343,7 @@ static void guc_init_params(struct intel_guc *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]); + guc_dbg(guc, "param[%2d] = %#x\n", i, params[i]); } /* @@ -389,7 +390,6 @@ void intel_guc_dump_time_info(struct intel_guc *guc, struct drm_printer *p) int intel_guc_init(struct intel_guc *guc) { - struct intel_gt *gt = guc_to_gt(guc); int ret; ret = intel_uc_fw_init(&guc->fw); @@ -451,7 +451,7 @@ err_fw: intel_uc_fw_fini(&guc->fw); out: intel_uc_fw_change_status(&guc->fw, INTEL_UC_FIRMWARE_INIT_FAIL); - i915_probe_error(gt->i915, "failed with %d\n", ret); + guc_probe_error(guc, "failed with %pe\n", ERR_PTR(ret)); return ret; } @@ -480,7 +480,6 @@ void intel_guc_fini(struct intel_guc *guc) int intel_guc_send_mmio(struct intel_guc *guc, const u32 *request, u32 len, u32 *response_buf, u32 response_buf_size) { - struct drm_i915_private *i915 = guc_to_gt(guc)->i915; struct intel_uncore *uncore = guc_to_gt(guc)->uncore; u32 header; int i; @@ -515,7 +514,7 @@ retry: 10, 10, &header); if (unlikely(ret)) { timeout: - drm_err(&i915->drm, "mmio request %#x: no reply %x\n", + guc_err(guc, "mmio request %#x: no reply %x\n", request[0], header); goto out; } @@ -537,7 +536,7 @@ timeout: if (FIELD_GET(GUC_HXG_MSG_0_TYPE, header) == GUC_HXG_TYPE_NO_RESPONSE_RETRY) { u32 reason = FIELD_GET(GUC_HXG_RETRY_MSG_0_REASON, header); - drm_dbg(&i915->drm, "mmio request %#x: retrying, reason %u\n", + guc_dbg(guc, "mmio request %#x: retrying, reason %u\n", request[0], reason); goto retry; } @@ -546,7 +545,7 @@ timeout: u32 hint = FIELD_GET(GUC_HXG_FAILURE_MSG_0_HINT, header); u32 error = FIELD_GET(GUC_HXG_FAILURE_MSG_0_ERROR, header); - drm_err(&i915->drm, "mmio request %#x: failure %x/%u\n", + guc_err(guc, "mmio request %#x: failure %x/%u\n", request[0], error, hint); ret = -ENXIO; goto out; @@ -554,7 +553,7 @@ timeout: if (FIELD_GET(GUC_HXG_MSG_0_TYPE, header) != GUC_HXG_TYPE_RESPONSE_SUCCESS) { proto: - drm_err(&i915->drm, "mmio request %#x: unexpected reply %#x\n", + guc_err(guc, "mmio request %#x: unexpected reply %#x\n", request[0], header); ret = -EPROTO; goto out; @@ -597,9 +596,9 @@ int intel_guc_to_host_process_recv_msg(struct intel_guc *guc, msg = payload[0] & guc->msg_enabled_mask; if (msg & INTEL_GUC_RECV_MSG_CRASH_DUMP_POSTED) - drm_err(&guc_to_gt(guc)->i915->drm, "Received early GuC crash dump notification!\n"); + guc_err(guc, "Received early 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"); + guc_err(guc, "Received early exception notification!\n"); return 0; } @@ -653,7 +652,8 @@ int intel_guc_suspend(struct intel_guc *guc) */ ret = intel_guc_send_mmio(guc, action, ARRAY_SIZE(action), NULL, 0); if (ret) - DRM_ERROR("GuC suspend: RESET_CLIENT action failed with error %d!\n", ret); + guc_err(guc, "suspend: RESET_CLIENT action failed with %pe\n", + ERR_PTR(ret)); } /* Signal that the GuC isn't running. */ @@ -828,12 +828,11 @@ static int __guc_action_self_cfg(struct intel_guc *guc, u16 key, u16 len, u64 va 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); + guc_probe_error(guc, "Unsuccessful self-config (%pe) key %#hx value %#llx\n", + ERR_PTR(err), key, value); return err; } 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 a7f737c4792e..69ce06faf8cd 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_ads.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_ads.c @@ -15,6 +15,7 @@ #include "intel_guc_ads.h" #include "intel_guc_capture.h" #include "intel_guc_fwif.h" +#include "intel_guc_print.h" #include "intel_uc.h" #include "i915_drv.h" @@ -427,7 +428,7 @@ static long guc_mmio_reg_state_create(struct intel_guc *guc) guc->ads_regset = temp_set.storage; - drm_dbg(&guc_to_gt(guc)->i915->drm, "Used %zu KB for temporary ADS regset\n", + guc_dbg(guc, "Used %zu KB for temporary ADS regset\n", (temp_set.storage_max * sizeof(struct guc_mmio_reg)) >> 10); return total * sizeof(struct guc_mmio_reg); @@ -621,7 +622,7 @@ static void guc_init_golden_context(struct intel_guc *guc) engine = find_engine_state(gt, engine_class); if (!engine) { - drm_err(>->i915->drm, "No engine state recorded for class %d!\n", + guc_err(guc, "No engine state recorded for class %d!\n", engine_class); ads_blob_write(guc, ads.eng_state_size[guc_class], 0); ads_blob_write(guc, ads.golden_context_lrca[guc_class], 0); @@ -646,7 +647,6 @@ static int guc_capture_prep_lists(struct intel_guc *guc) { struct intel_gt *gt = guc_to_gt(guc); - struct drm_i915_private *i915 = guc_to_gt(guc)->i915; u32 ads_ggtt, capture_offset, null_ggtt, total_size = 0; struct guc_gt_system_info local_info; struct iosys_map info_map; @@ -751,7 +751,7 @@ engine_instance_list: } if (guc->ads_capture_size && guc->ads_capture_size != PAGE_ALIGN(total_size)) - drm_warn(&i915->drm, "GuC->ADS->Capture alloc size changed from %d to %d\n", + guc_warn(guc, "ADS capture alloc size changed from %d to %d\n", guc->ads_capture_size, PAGE_ALIGN(total_size)); return PAGE_ALIGN(total_size); diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_capture.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_capture.c index 1c1b85073b4b..cf49188db6a6 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_capture.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_capture.c @@ -15,6 +15,7 @@ #include "guc_capture_fwif.h" #include "intel_guc_capture.h" #include "intel_guc_fwif.h" +#include "intel_guc_print.h" #include "i915_drv.h" #include "i915_gpu_error.h" #include "i915_irq.h" @@ -353,7 +354,6 @@ guc_capture_alloc_steered_lists_xe_hpg(struct intel_guc *guc, u32 ipver) { struct intel_gt *gt = guc_to_gt(guc); - struct drm_i915_private *i915 = guc_to_gt(guc)->i915; struct sseu_dev_info *sseu; int slice, subslice, i, iter, num_steer_regs, num_tot_regs = 0; const struct __guc_mmio_reg_descr_group *list; @@ -402,7 +402,7 @@ guc_capture_alloc_steered_lists_xe_hpg(struct intel_guc *guc, } } - drm_dbg(&i915->drm, "GuC-capture found %d-ext-regs.\n", num_tot_regs); + guc_dbg(guc, "capture found %d ext-regs.\n", num_tot_regs); guc->capture->extlists = extlists; } @@ -477,7 +477,6 @@ guc_capture_list_init(struct intel_guc *guc, u32 owner, u32 type, u32 classid, struct guc_mmio_reg *ptr, u16 num_entries) { u32 i = 0, j = 0; - struct drm_i915_private *i915 = guc_to_gt(guc)->i915; const struct __guc_mmio_reg_descr_group *reglists = guc->capture->reglists; struct __guc_mmio_reg_descr_group *extlists = guc->capture->extlists; const struct __guc_mmio_reg_descr_group *match; @@ -509,8 +508,7 @@ guc_capture_list_init(struct intel_guc *guc, u32 owner, u32 type, u32 classid, } } if (i < num_entries) - drm_dbg(&i915->drm, "GuC-capture: Init reglist short %d out %d.\n", - (int)i, (int)num_entries); + guc_dbg(guc, "Got short capture reglist init: %d out %d.\n", i, num_entries); return 0; } @@ -540,12 +538,11 @@ guc_capture_getlistsize(struct intel_guc *guc, u32 owner, u32 type, u32 classid, size_t *size, bool is_purpose_est) { struct intel_guc_state_capture *gc = guc->capture; - struct drm_i915_private *i915 = guc_to_gt(guc)->i915; struct __guc_capture_ads_cache *cache = &gc->ads_cache[owner][type][classid]; int num_regs; if (!gc->reglists) { - drm_warn(&i915->drm, "GuC-capture: No reglist on this device\n"); + guc_warn(guc, "No capture reglist for this device\n"); return -ENODEV; } @@ -557,9 +554,9 @@ guc_capture_getlistsize(struct intel_guc *guc, u32 owner, u32 type, u32 classid, if (!is_purpose_est && owner == GUC_CAPTURE_LIST_INDEX_PF && !guc_capture_get_one_list(gc->reglists, owner, type, classid)) { if (type == GUC_CAPTURE_LIST_TYPE_GLOBAL) - drm_warn(&i915->drm, "Missing GuC-Err-Cap reglist Global!\n"); + guc_warn(guc, "Missing capture reglist: global!\n"); else - drm_warn(&i915->drm, "Missing GuC-Err-Cap reglist %s(%u):%s(%u)!\n", + guc_warn(guc, "Missing capture reglist: %s(%u):%s(%u)!\n", __stringify_type(type), type, __stringify_engclass(classid), classid); return -ENODATA; @@ -592,7 +589,6 @@ intel_guc_capture_getlist(struct intel_guc *guc, u32 owner, u32 type, u32 classi { struct intel_guc_state_capture *gc = guc->capture; struct __guc_capture_ads_cache *cache = &gc->ads_cache[owner][type][classid]; - struct drm_i915_private *i915 = guc_to_gt(guc)->i915; struct guc_debug_capture_list *listnode; int ret, num_regs; u8 *caplist, *tmp; @@ -623,7 +619,7 @@ intel_guc_capture_getlist(struct intel_guc *guc, u32 owner, u32 type, u32 classi caplist = kzalloc(size, GFP_KERNEL); if (!caplist) { - drm_dbg(&i915->drm, "GuC-capture: failed to alloc cached caplist"); + guc_dbg(guc, "Failed to alloc cached register capture list"); return -ENOMEM; } @@ -653,7 +649,6 @@ intel_guc_capture_getnullheader(struct intel_guc *guc, void **outptr, size_t *size) { struct intel_guc_state_capture *gc = guc->capture; - struct drm_i915_private *i915 = guc_to_gt(guc)->i915; int tmp = sizeof(u32) * 4; void *null_header; @@ -665,7 +660,7 @@ intel_guc_capture_getnullheader(struct intel_guc *guc, null_header = kzalloc(tmp, GFP_KERNEL); if (!null_header) { - drm_dbg(&i915->drm, "GuC-capture: failed to alloc cached nulllist"); + guc_dbg(guc, "Failed to alloc cached register capture null list"); return -ENOMEM; } @@ -727,7 +722,6 @@ guc_capture_output_min_size_est(struct intel_guc *guc) static void check_guc_capture_size(struct intel_guc *guc) { - struct drm_i915_private *i915 = guc_to_gt(guc)->i915; int min_size = guc_capture_output_min_size_est(guc); int spare_size = min_size * GUC_CAPTURE_OVERBUFFER_MULTIPLIER; u32 buffer_size = intel_guc_log_section_size_capture(&guc->log); @@ -741,13 +735,13 @@ static void check_guc_capture_size(struct intel_guc *guc) * INTEL_GUC_STATE_CAPTURE_EVENT_STATUS_NOSPACE. */ if (min_size < 0) - drm_warn(&i915->drm, "Failed to calculate GuC error state capture buffer minimum size: %d!\n", + guc_warn(guc, "Failed to calculate error state capture buffer minimum size: %d!\n", min_size); else if (min_size > buffer_size) - drm_warn(&i915->drm, "GuC error state capture buffer maybe small: %d < %d\n", + guc_warn(guc, "Error state capture buffer maybe small: %d < %d\n", buffer_size, min_size); else if (spare_size > buffer_size) - drm_dbg(&i915->drm, "GuC error state capture buffer lacks spare size: %d < %d (min = %d)\n", + guc_dbg(guc, "Error state capture buffer lacks spare size: %d < %d (min = %d)\n", buffer_size, spare_size, min_size); } @@ -848,7 +842,6 @@ static int guc_capture_log_remove_dw(struct intel_guc *guc, struct __guc_capture_bufstate *buf, u32 *dw) { - struct drm_i915_private *i915 = guc_to_gt(guc)->i915; int tries = 2; int avail = 0; u32 *src_data; @@ -865,7 +858,7 @@ guc_capture_log_remove_dw(struct intel_guc *guc, struct __guc_capture_bufstate * return 4; } if (avail) - drm_dbg(&i915->drm, "GuC-Cap-Logs not dword aligned, skipping.\n"); + guc_dbg(guc, "Register capture log not dword aligned, skipping.\n"); buf->rd = 0; } @@ -1118,13 +1111,12 @@ static void __guc_capture_create_prealloc_nodes(struct intel_guc *guc) { struct __guc_capture_parsed_output *node = NULL; - struct drm_i915_private *i915 = guc_to_gt(guc)->i915; int i; for (i = 0; i < PREALLOC_NODES_MAX_COUNT; ++i) { node = guc_capture_alloc_one_node(guc); if (!node) { - drm_warn(&i915->drm, "GuC Capture pre-alloc-cache failure\n"); + guc_warn(guc, "Register capture pre-alloc-cache failure\n"); /* dont free the priors, use what we got and cleanup at shutdown */ return; } @@ -1169,7 +1161,6 @@ guc_capture_create_prealloc_nodes(struct intel_guc *guc) static int guc_capture_extract_reglists(struct intel_guc *guc, struct __guc_capture_bufstate *buf) { - struct drm_i915_private *i915 = guc_to_gt(guc)->i915; struct guc_state_capture_group_header_t ghdr = {0}; struct guc_state_capture_header_t hdr = {0}; struct __guc_capture_parsed_output *node = NULL; @@ -1183,7 +1174,7 @@ guc_capture_extract_reglists(struct intel_guc *guc, struct __guc_capture_bufstat if (!i) return -ENODATA; if (i % sizeof(u32)) { - drm_warn(&i915->drm, "GuC Capture new entries unaligned\n"); + guc_warn(guc, "Got mis-aligned register capture entries\n"); ret = -EIO; goto bailout; } @@ -1301,7 +1292,7 @@ guc_capture_extract_reglists(struct intel_guc *guc, struct __guc_capture_bufstat break; } if (datatype != GUC_CAPTURE_LIST_TYPE_GLOBAL) - drm_dbg(&i915->drm, "GuC Capture missing global dump: %08x!\n", + guc_dbg(guc, "Register capture missing global dump: %08x!\n", datatype); } node->is_partial = is_partial; @@ -1322,7 +1313,7 @@ guc_capture_extract_reglists(struct intel_guc *guc, struct __guc_capture_bufstat numregs = FIELD_GET(CAP_HDR_NUM_MMIOS, hdr.num_mmios); if (numregs > guc->capture->max_mmio_per_node) { - drm_dbg(&i915->drm, "GuC Capture list extraction clipped by prealloc!\n"); + guc_dbg(guc, "Register capture list extraction clipped by prealloc!\n"); numregs = guc->capture->max_mmio_per_node; } node->reginfo[datatype].num_regs = numregs; @@ -1367,7 +1358,6 @@ static void __guc_capture_process_output(struct intel_guc *guc) { unsigned int buffer_size, read_offset, write_offset, full_count; struct intel_uc *uc = container_of(guc, typeof(*uc), guc); - struct drm_i915_private *i915 = guc_to_gt(guc)->i915; struct guc_log_buffer_state log_buf_state_local; struct guc_log_buffer_state *log_buf_state; struct __guc_capture_bufstate buf; @@ -1403,7 +1393,8 @@ static void __guc_capture_process_output(struct intel_guc *guc) write_offset = buffer_size; } else if (unlikely((read_offset > buffer_size) || (write_offset > buffer_size))) { - drm_err(&i915->drm, "invalid GuC log capture buffer state!\n"); + guc_err(guc, "Register capture buffer in invalid state: read = 0x%X, size = 0x%X!\n", + read_offset, buffer_size); /* copy whole buffer as offsets are unreliable */ read_offset = 0; write_offset = buffer_size; @@ -1506,7 +1497,7 @@ int intel_guc_capture_print_engine_node(struct drm_i915_error_state_buf *ebuf, if (!ebuf || !ee) return -EINVAL; - cap = ee->capture; + cap = ee->guc_capture; if (!cap || !ee->engine) return -ENODEV; @@ -1571,13 +1562,34 @@ int intel_guc_capture_print_engine_node(struct drm_i915_error_state_buf *ebuf, #endif //CONFIG_DRM_I915_CAPTURE_ERROR +static void guc_capture_find_ecode(struct intel_engine_coredump *ee) +{ + struct gcap_reg_list_info *reginfo; + struct guc_mmio_reg *regs; + i915_reg_t reg_ipehr = RING_IPEHR(0); + i915_reg_t reg_instdone = RING_INSTDONE(0); + int i; + + if (!ee->guc_capture_node) + return; + + reginfo = ee->guc_capture_node->reginfo + GUC_CAPTURE_LIST_TYPE_ENGINE_INSTANCE; + regs = reginfo->regs; + for (i = 0; i < reginfo->num_regs; i++) { + if (regs[i].offset == reg_ipehr.reg) + ee->ipehr = regs[i].value; + else if (regs[i].offset == reg_instdone.reg) + ee->instdone.instdone = regs[i].value; + } +} + void intel_guc_capture_free_node(struct intel_engine_coredump *ee) { if (!ee || !ee->guc_capture_node) return; - guc_capture_add_node_to_cachelist(ee->capture, ee->guc_capture_node); - ee->capture = NULL; + guc_capture_add_node_to_cachelist(ee->guc_capture, ee->guc_capture_node); + ee->guc_capture = NULL; ee->guc_capture_node = NULL; } @@ -1586,13 +1598,11 @@ void intel_guc_capture_get_matching_node(struct intel_gt *gt, struct intel_context *ce) { struct __guc_capture_parsed_output *n, *ntmp; - struct drm_i915_private *i915; struct intel_guc *guc; if (!gt || !ee || !ce) return; - i915 = gt->i915; guc = >->uc.guc; if (!guc->capture) return; @@ -1606,16 +1616,18 @@ void intel_guc_capture_get_matching_node(struct intel_gt *gt, list_for_each_entry_safe(n, ntmp, &guc->capture->outlist, link) { if (n->eng_inst == GUC_ID_TO_ENGINE_INSTANCE(ee->engine->guc_id) && n->eng_class == GUC_ID_TO_ENGINE_CLASS(ee->engine->guc_id) && - n->guc_id && n->guc_id == ce->guc_id.id && - (n->lrca & CTX_GTT_ADDRESS_MASK) && (n->lrca & CTX_GTT_ADDRESS_MASK) == - (ce->lrc.lrca & CTX_GTT_ADDRESS_MASK)) { + n->guc_id == ce->guc_id.id && + (n->lrca & CTX_GTT_ADDRESS_MASK) == (ce->lrc.lrca & CTX_GTT_ADDRESS_MASK)) { list_del(&n->link); ee->guc_capture_node = n; - ee->capture = guc->capture; + ee->guc_capture = guc->capture; + guc_capture_find_ecode(ee); return; } } - drm_dbg(&i915->drm, "GuC capture can't match ee to node\n"); + + guc_warn(guc, "No register capture node found for 0x%04X / 0x%08X\n", + ce->guc_id.id, ce->lrc.lrca); } void intel_guc_capture_process(struct intel_guc *guc) 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 2b22065e87bf..1803a633ed64 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c @@ -11,38 +11,23 @@ #include "i915_drv.h" #include "intel_guc_ct.h" -#include "gt/intel_gt.h" +#include "intel_guc_print.h" static inline struct intel_guc *ct_to_guc(struct intel_guc_ct *ct) { return container_of(ct, struct intel_guc, ct); } -static inline struct intel_gt *ct_to_gt(struct intel_guc_ct *ct) -{ - return guc_to_gt(ct_to_guc(ct)); -} - -static inline struct drm_i915_private *ct_to_i915(struct intel_guc_ct *ct) -{ - return ct_to_gt(ct)->i915; -} - -static inline struct drm_device *ct_to_drm(struct intel_guc_ct *ct) -{ - return &ct_to_i915(ct)->drm; -} - #define CT_ERROR(_ct, _fmt, ...) \ - drm_err(ct_to_drm(_ct), "CT: " _fmt, ##__VA_ARGS__) + guc_err(ct_to_guc(_ct), "CT: " _fmt, ##__VA_ARGS__) #ifdef CONFIG_DRM_I915_DEBUG_GUC #define CT_DEBUG(_ct, _fmt, ...) \ - drm_dbg(ct_to_drm(_ct), "CT: " _fmt, ##__VA_ARGS__) + guc_dbg(ct_to_guc(_ct), "CT: " _fmt, ##__VA_ARGS__) #else #define CT_DEBUG(...) do { } while (0) #endif #define CT_PROBE_ERROR(_ct, _fmt, ...) \ - i915_probe_error(ct_to_i915(ct), "CT: " _fmt, ##__VA_ARGS__) + guc_probe_error(ct_to_guc(ct), "CT: " _fmt, ##__VA_ARGS__) /** * DOC: CTB Blob 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 5b86b2e286e0..69133420c78b 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_fw.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_fw.c @@ -13,6 +13,7 @@ #include "gt/intel_gt_mcr.h" #include "gt/intel_gt_regs.h" #include "intel_guc_fw.h" +#include "intel_guc_print.h" #include "i915_drv.h" static void guc_prepare_xfer(struct intel_gt *gt) @@ -38,9 +39,8 @@ static void guc_prepare_xfer(struct intel_gt *gt) if (GRAPHICS_VER(uncore->i915) == 9) { /* DOP Clock Gating Enable for GuC clocks */ - intel_gt_mcr_multicast_write(gt, GEN8_MISCCPCTL, - GEN8_DOP_CLOCK_GATE_GUC_ENABLE | - intel_gt_mcr_read_any(gt, GEN8_MISCCPCTL)); + intel_uncore_rmw(uncore, GEN7_MISCCPCTL, 0, + GEN8_DOP_CLOCK_GATE_GUC_ENABLE); /* allows for 5us (in 10ns units) before GT can go to RC6 */ intel_uncore_write(uncore, GUC_ARAT_C6DIS, 0x1FF); @@ -103,8 +103,10 @@ static inline bool guc_ready(struct intel_uncore *uncore, u32 *status) return uk_val == INTEL_GUC_LOAD_STATUS_READY; } -static int guc_wait_ucode(struct intel_uncore *uncore) +static int guc_wait_ucode(struct intel_guc *guc) { + struct intel_gt *gt = guc_to_gt(guc); + struct intel_uncore *uncore = gt->uncore; u32 status; int ret; @@ -127,10 +129,8 @@ static int guc_wait_ucode(struct intel_uncore *uncore) */ ret = wait_for(guc_ready(uncore, &status), 200); if (ret) { - struct drm_device *drm = &uncore->i915->drm; - - drm_info(drm, "GuC load failed: status = 0x%08X\n", status); - drm_info(drm, "GuC load failed: status: Reset = %d, " + guc_info(guc, "load failed: status = 0x%08X\n", status); + guc_info(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), @@ -140,12 +140,12 @@ 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_info(drm, "GuC firmware signature verification failed\n"); + guc_info(guc, "firmware signature verification failed\n"); ret = -ENOEXEC; } if (REG_FIELD_GET(GS_UKERNEL_MASK, status) == INTEL_GUC_LOAD_STATUS_EXCEPTION) { - drm_info(drm, "GuC firmware exception. EIP: %#x\n", + guc_info(guc, "firmware exception. EIP: %#x\n", intel_uncore_read(uncore, SOFT_SCRATCH(13))); ret = -ENXIO; } @@ -194,7 +194,7 @@ int intel_guc_fw_upload(struct intel_guc *guc) if (ret) goto out; - ret = guc_wait_ucode(uncore); + ret = guc_wait_ucode(guc); if (ret) goto out; 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 68331c538b0a..195db8c9d420 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_log.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_log.c @@ -12,6 +12,7 @@ #include "i915_memcpy.h" #include "intel_guc_capture.h" #include "intel_guc_log.h" +#include "intel_guc_print.h" #if defined(CONFIG_DRM_I915_DEBUG_GUC) #define GUC_LOG_DEFAULT_CRASH_BUFFER_SIZE SZ_2M @@ -39,7 +40,6 @@ struct guc_log_section { static void _guc_log_init_sizes(struct intel_guc_log *log) { struct intel_guc *guc = log_to_guc(log); - struct drm_i915_private *i915 = guc_to_gt(guc)->i915; static const struct guc_log_section sections[GUC_LOG_SECTIONS_LIMIT] = { { GUC_LOG_CRASH_MASK >> GUC_LOG_CRASH_SHIFT, @@ -82,12 +82,12 @@ static void _guc_log_init_sizes(struct intel_guc_log *log) } if (!IS_ALIGNED(log->sizes[i].bytes, log->sizes[i].units)) - drm_err(&i915->drm, "Mis-aligned GuC log %s size: 0x%X vs 0x%X!", + guc_err(guc, "Mis-aligned log %s size: 0x%X vs 0x%X!\n", sections[i].name, log->sizes[i].bytes, log->sizes[i].units); log->sizes[i].count = log->sizes[i].bytes / log->sizes[i].units; if (!log->sizes[i].count) { - drm_err(&i915->drm, "Zero GuC log %s size!", sections[i].name); + guc_err(guc, "Zero log %s size!\n", sections[i].name); } else { /* Size is +1 unit */ log->sizes[i].count--; @@ -95,14 +95,14 @@ static void _guc_log_init_sizes(struct intel_guc_log *log) /* Clip to field size */ if (log->sizes[i].count > sections[i].max) { - drm_err(&i915->drm, "GuC log %s size too large: %d vs %d!", + guc_err(guc, "log %s size too large: %d vs %d!\n", sections[i].name, log->sizes[i].count + 1, sections[i].max + 1); log->sizes[i].count = sections[i].max; } } if (log->sizes[GUC_LOG_SECTIONS_CRASH].units != log->sizes[GUC_LOG_SECTIONS_DEBUG].units) { - drm_err(&i915->drm, "Unit mis-match for GuC log crash and debug sections: %d vs %d!", + guc_err(guc, "Unit mismatch for crash and debug sections: %d vs %d!\n", log->sizes[GUC_LOG_SECTIONS_CRASH].units, log->sizes[GUC_LOG_SECTIONS_DEBUG].units); log->sizes[GUC_LOG_SECTIONS_CRASH].units = log->sizes[GUC_LOG_SECTIONS_DEBUG].units; @@ -333,8 +333,7 @@ bool intel_guc_check_log_buf_overflow(struct intel_guc_log *log, log->stats[type].sampled_overflow += 16; } - dev_notice_ratelimited(guc_to_gt(log_to_guc(log))->i915->drm.dev, - "GuC log buffer overflow\n"); + guc_notice_ratelimited(log_to_guc(log), "log buffer overflow\n"); } return overflow; @@ -374,6 +373,7 @@ size_t intel_guc_get_log_buffer_offset(struct intel_guc_log *log, static void _guc_log_copy_debuglogs_for_relay(struct intel_guc_log *log) { + struct intel_guc *guc = log_to_guc(log); unsigned int buffer_size, read_offset, write_offset, bytes_to_copy, full_cnt; struct guc_log_buffer_state *log_buf_state, *log_buf_snapshot_state; struct guc_log_buffer_state log_buf_state_local; @@ -383,7 +383,7 @@ static void _guc_log_copy_debuglogs_for_relay(struct intel_guc_log *log) mutex_lock(&log->relay.lock); - if (WARN_ON(!intel_guc_log_relay_created(log))) + if (guc_WARN_ON(guc, !intel_guc_log_relay_created(log))) goto out_unlock; /* Get the pointer to shared GuC log buffer */ @@ -398,7 +398,7 @@ static void _guc_log_copy_debuglogs_for_relay(struct intel_guc_log *log) * Used rate limited to avoid deluge of messages, logs might be * getting consumed by User at a slow rate. */ - DRM_ERROR_RATELIMITED("no sub-buffer to copy general logs\n"); + guc_err_ratelimited(guc, "no sub-buffer to copy general logs\n"); log->relay.full_count++; goto out_unlock; @@ -451,7 +451,7 @@ static void _guc_log_copy_debuglogs_for_relay(struct intel_guc_log *log) write_offset = buffer_size; } else if (unlikely((read_offset > buffer_size) || (write_offset > buffer_size))) { - DRM_ERROR("invalid log buffer state\n"); + guc_err(guc, "invalid log buffer state\n"); /* copy whole buffer as offsets are unreliable */ read_offset = 0; write_offset = buffer_size; @@ -520,7 +520,7 @@ void intel_guc_log_init_early(struct intel_guc_log *log) static int guc_log_relay_create(struct intel_guc_log *log) { struct intel_guc *guc = log_to_guc(log); - struct drm_i915_private *dev_priv = guc_to_gt(guc)->i915; + struct drm_i915_private *i915 = guc_to_gt(guc)->i915; struct rchan *guc_log_relay_chan; size_t n_subbufs, subbuf_size; int ret; @@ -543,11 +543,11 @@ static int guc_log_relay_create(struct intel_guc_log *log) n_subbufs = 8; guc_log_relay_chan = relay_open("guc_log", - dev_priv->drm.primary->debugfs_root, + i915->drm.primary->debugfs_root, subbuf_size, n_subbufs, - &relay_callbacks, dev_priv); + &relay_callbacks, i915); if (!guc_log_relay_chan) { - DRM_ERROR("Couldn't create relay chan for GuC logging\n"); + guc_err(guc, "Couldn't create relay channel for logging\n"); ret = -ENOMEM; return ret; @@ -570,7 +570,7 @@ static void guc_log_relay_destroy(struct intel_guc_log *log) static void guc_log_copy_debuglogs_for_relay(struct intel_guc_log *log) { struct intel_guc *guc = log_to_guc(log); - struct drm_i915_private *dev_priv = guc_to_gt(guc)->i915; + struct drm_i915_private *i915 = guc_to_gt(guc)->i915; intel_wakeref_t wakeref; _guc_log_copy_debuglogs_for_relay(log); @@ -579,7 +579,7 @@ static void guc_log_copy_debuglogs_for_relay(struct intel_guc_log *log) * Generally device is expected to be active only at this * time, so get/put should be really quick. */ - with_intel_runtime_pm(&dev_priv->runtime_pm, wakeref) + with_intel_runtime_pm(&i915->runtime_pm, wakeref) guc_action_flush_log_complete(guc); } @@ -596,9 +596,8 @@ static u32 __get_default_log_level(struct intel_guc_log *log) } if (i915->params.guc_log_level > GUC_LOG_LEVEL_MAX) { - DRM_WARN("Incompatible option detected: %s=%d, %s!\n", - "guc_log_level", i915->params.guc_log_level, - "verbosity too high"); + guc_warn(guc, "Log verbosity param out of range: %d > %d!\n", + i915->params.guc_log_level, GUC_LOG_LEVEL_MAX); return (IS_ENABLED(CONFIG_DRM_I915_DEBUG) || IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM)) ? GUC_LOG_LEVEL_MAX : GUC_LOG_LEVEL_DISABLED; @@ -641,15 +640,15 @@ int intel_guc_log_create(struct intel_guc_log *log) log->buf_addr = vaddr; log->level = __get_default_log_level(log); - DRM_DEBUG_DRIVER("guc_log_level=%d (%s, verbose:%s, verbosity:%d)\n", - log->level, str_enabled_disabled(log->level), - str_yes_no(GUC_LOG_LEVEL_IS_VERBOSE(log->level)), - GUC_LOG_LEVEL_TO_VERBOSITY(log->level)); + guc_dbg(guc, "guc_log_level=%d (%s, verbose:%s, verbosity:%d)\n", + log->level, str_enabled_disabled(log->level), + str_yes_no(GUC_LOG_LEVEL_IS_VERBOSE(log->level)), + GUC_LOG_LEVEL_TO_VERBOSITY(log->level)); return 0; err: - DRM_ERROR("Failed to allocate or map GuC log buffer. %d\n", ret); + guc_err(guc, "Failed to allocate or map log buffer %pe\n", ERR_PTR(ret)); return ret; } @@ -662,7 +661,7 @@ void intel_guc_log_destroy(struct intel_guc_log *log) int intel_guc_log_set_level(struct intel_guc_log *log, u32 level) { struct intel_guc *guc = log_to_guc(log); - struct drm_i915_private *dev_priv = guc_to_gt(guc)->i915; + struct drm_i915_private *i915 = guc_to_gt(guc)->i915; intel_wakeref_t wakeref; int ret = 0; @@ -676,25 +675,25 @@ int intel_guc_log_set_level(struct intel_guc_log *log, u32 level) if (level < GUC_LOG_LEVEL_DISABLED || level > GUC_LOG_LEVEL_MAX) return -EINVAL; - mutex_lock(&dev_priv->drm.struct_mutex); + mutex_lock(&i915->drm.struct_mutex); if (log->level == level) goto out_unlock; - with_intel_runtime_pm(&dev_priv->runtime_pm, wakeref) + with_intel_runtime_pm(&i915->runtime_pm, wakeref) ret = guc_action_control_log(guc, GUC_LOG_LEVEL_IS_VERBOSE(level), GUC_LOG_LEVEL_IS_ENABLED(level), GUC_LOG_LEVEL_TO_VERBOSITY(level)); if (ret) { - DRM_DEBUG_DRIVER("guc_log_control action failed %d\n", ret); + guc_dbg(guc, "guc_log_control action failed %pe\n", ERR_PTR(ret)); goto out_unlock; } log->level = level; out_unlock: - mutex_unlock(&dev_priv->drm.struct_mutex); + mutex_unlock(&i915->drm.struct_mutex); return ret; } @@ -905,7 +904,7 @@ int intel_guc_log_dump(struct intel_guc_log *log, struct drm_printer *p, map = i915_gem_object_pin_map_unlocked(obj, I915_MAP_WC); if (IS_ERR(map)) { - DRM_DEBUG("Failed to pin object\n"); + guc_dbg(guc, "Failed to pin log object: %pe\n", map); drm_puts(p, "(log data unaccessible)\n"); free_page((unsigned long)page); return PTR_ERR(map); diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_print.h b/drivers/gpu/drm/i915/gt/uc/intel_guc_print.h new file mode 100644 index 000000000000..2465d05638b4 --- /dev/null +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_print.h @@ -0,0 +1,51 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright © 2023 Intel Corporation + */ + +#ifndef __INTEL_GUC_PRINT__ +#define __INTEL_GUC_PRINT__ + +#include "gt/intel_gt.h" +#include "gt/intel_gt_print.h" + +#define guc_printk(_guc, _level, _fmt, ...) \ + gt_##_level(guc_to_gt(_guc), "GUC: " _fmt, ##__VA_ARGS__) + +#define guc_err(_guc, _fmt, ...) \ + guc_printk((_guc), err, _fmt, ##__VA_ARGS__) + +#define guc_warn(_guc, _fmt, ...) \ + guc_printk((_guc), warn, _fmt, ##__VA_ARGS__) + +#define guc_notice(_guc, _fmt, ...) \ + guc_printk((_guc), notice, _fmt, ##__VA_ARGS__) + +#define guc_info(_guc, _fmt, ...) \ + guc_printk((_guc), info, _fmt, ##__VA_ARGS__) + +#define guc_dbg(_guc, _fmt, ...) \ + guc_printk((_guc), dbg, _fmt, ##__VA_ARGS__) + +#define guc_err_ratelimited(_guc, _fmt, ...) \ + guc_printk((_guc), err_ratelimited, _fmt, ##__VA_ARGS__) + +#define guc_notice_ratelimited(_guc, _fmt, ...) \ + guc_printk((_guc), notice_ratelimited, _fmt, ##__VA_ARGS__) + +#define guc_probe_error(_guc, _fmt, ...) \ + guc_printk((_guc), probe_error, _fmt, ##__VA_ARGS__) + +#define guc_WARN(_guc, _cond, _fmt, ...) \ + gt_WARN(guc_to_gt(_guc), _cond, "GUC: " _fmt, ##__VA_ARGS__) + +#define guc_WARN_ONCE(_guc, _cond, _fmt, ...) \ + gt_WARN_ONCE(guc_to_gt(_guc), _cond, "GUC: " _fmt, ##__VA_ARGS__) + +#define guc_WARN_ON(_guc, _cond) \ + gt_WARN(guc_to_gt(_guc), _cond, "%s(%s)", "guc_WARN_ON", __stringify(_cond)) + +#define guc_WARN_ON_ONCE(_guc, _cond) \ + gt_WARN_ONCE(guc_to_gt(_guc), _cond, "%s(%s)", "guc_WARN_ON_ONCE", __stringify(_cond)) + +#endif /* __INTEL_GUC_PRINT__ */ diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_rc.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_rc.c index b5855091cf6a..1adec6de223c 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_rc.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_rc.c @@ -6,25 +6,15 @@ #include <linux/string_helpers.h> #include "intel_guc_rc.h" +#include "intel_guc_print.h" #include "gt/intel_gt.h" #include "i915_drv.h" static bool __guc_rc_supported(struct intel_guc *guc) { - struct intel_gt *gt = guc_to_gt(guc); - - /* - * Wa_14017073508: mtl - * Do not enable gucrc to avoid additional interrupts which - * may disrupt pcode wa. - */ - if (IS_MTL_GRAPHICS_STEP(gt->i915, P, STEP_A0, STEP_B0) && - gt->type == GT_MEDIA) - return false; - /* GuC RC is unavailable for pre-Gen12 */ return guc->submission_supported && - GRAPHICS_VER(gt->i915) >= 12; + GRAPHICS_VER(guc_to_gt(guc)->i915) >= 12; } static bool __guc_rc_selected(struct intel_guc *guc) @@ -70,13 +60,12 @@ static int __guc_rc_control(struct intel_guc *guc, bool enable) ret = guc_action_control_gucrc(guc, enable); if (ret) { - i915_probe_error(guc_to_gt(guc)->i915, "Failed to %s GuC RC (%pe)\n", - str_enable_disable(enable), ERR_PTR(ret)); + guc_probe_error(guc, "Failed to %s RC (%pe)\n", + str_enable_disable(enable), ERR_PTR(ret)); return ret; } - drm_info(>->i915->drm, "GuC RC: %s\n", - str_enabled_disabled(enable)); + guc_info(guc, "RC %s\n", str_enabled_disabled(enable)); return 0; } diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.c index 63464933cbce..026d73855f36 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.c @@ -9,6 +9,7 @@ #include "i915_drv.h" #include "i915_reg.h" #include "intel_guc_slpc.h" +#include "intel_guc_print.h" #include "intel_mchbar_regs.h" #include "gt/intel_gt.h" #include "gt/intel_gt_regs.h" @@ -171,14 +172,12 @@ static int guc_action_slpc_query(struct intel_guc *guc, u32 offset) static int slpc_query_task_state(struct intel_guc_slpc *slpc) { struct intel_guc *guc = slpc_to_guc(slpc); - struct drm_i915_private *i915 = slpc_to_i915(slpc); u32 offset = intel_guc_ggtt_offset(guc, slpc->vma); int ret; ret = guc_action_slpc_query(guc, offset); if (unlikely(ret)) - i915_probe_error(i915, "Failed to query task state (%pe)\n", - ERR_PTR(ret)); + guc_probe_error(guc, "Failed to query task state: %pe\n", ERR_PTR(ret)); drm_clflush_virt_range(slpc->vaddr, SLPC_PAGE_SIZE_BYTES); @@ -188,15 +187,14 @@ static int slpc_query_task_state(struct intel_guc_slpc *slpc) static int slpc_set_param(struct intel_guc_slpc *slpc, u8 id, u32 value) { struct intel_guc *guc = slpc_to_guc(slpc); - struct drm_i915_private *i915 = slpc_to_i915(slpc); int ret; GEM_BUG_ON(id >= SLPC_MAX_PARAM); ret = guc_action_slpc_set_param(guc, id, value); if (ret) - i915_probe_error(i915, "Failed to set param %d to %u (%pe)\n", - id, value, ERR_PTR(ret)); + guc_probe_error(guc, "Failed to set param %d to %u: %pe\n", + id, value, ERR_PTR(ret)); return ret; } @@ -212,8 +210,8 @@ static int slpc_unset_param(struct intel_guc_slpc *slpc, u8 id) static int slpc_force_min_freq(struct intel_guc_slpc *slpc, u32 freq) { - struct drm_i915_private *i915 = slpc_to_i915(slpc); struct intel_guc *guc = slpc_to_guc(slpc); + struct drm_i915_private *i915 = slpc_to_i915(slpc); intel_wakeref_t wakeref; int ret = 0; @@ -236,9 +234,8 @@ static int slpc_force_min_freq(struct intel_guc_slpc *slpc, u32 freq) SLPC_PARAM_GLOBAL_MIN_GT_UNSLICE_FREQ_MHZ, freq); if (ret) - drm_notice(&i915->drm, - "Failed to send set_param for min freq(%d): (%d)\n", - freq, ret); + guc_notice(guc, "Failed to send set_param for min freq(%d): %pe\n", + freq, ERR_PTR(ret)); } return ret; @@ -267,7 +264,6 @@ static void slpc_boost_work(struct work_struct *work) int intel_guc_slpc_init(struct intel_guc_slpc *slpc) { struct intel_guc *guc = slpc_to_guc(slpc); - struct drm_i915_private *i915 = slpc_to_i915(slpc); u32 size = PAGE_ALIGN(sizeof(struct slpc_shared_data)); int err; @@ -275,9 +271,7 @@ int intel_guc_slpc_init(struct intel_guc_slpc *slpc) err = intel_guc_allocate_and_map_vma(guc, size, &slpc->vma, (void **)&slpc->vaddr); if (unlikely(err)) { - i915_probe_error(i915, - "Failed to allocate SLPC struct (err=%pe)\n", - ERR_PTR(err)); + guc_probe_error(guc, "Failed to allocate SLPC struct: %pe\n", ERR_PTR(err)); return err; } @@ -338,7 +332,6 @@ static int guc_action_slpc_reset(struct intel_guc *guc, u32 offset) static int slpc_reset(struct intel_guc_slpc *slpc) { - struct drm_i915_private *i915 = slpc_to_i915(slpc); struct intel_guc *guc = slpc_to_guc(slpc); u32 offset = intel_guc_ggtt_offset(guc, slpc->vma); int ret; @@ -346,15 +339,14 @@ static int slpc_reset(struct intel_guc_slpc *slpc) ret = guc_action_slpc_reset(guc, offset); if (unlikely(ret < 0)) { - i915_probe_error(i915, "SLPC reset action failed (%pe)\n", - ERR_PTR(ret)); + guc_probe_error(guc, "SLPC reset action failed: %pe\n", ERR_PTR(ret)); return ret; } if (!ret) { if (wait_for(slpc_is_running(slpc), SLPC_RESET_TIMEOUT_MS)) { - i915_probe_error(i915, "SLPC not enabled! State = %s\n", - slpc_get_state_string(slpc)); + guc_probe_error(guc, "SLPC not enabled! State = %s\n", + slpc_get_state_string(slpc)); return -EIO; } } @@ -495,8 +487,8 @@ int intel_guc_slpc_set_min_freq(struct intel_guc_slpc *slpc, u32 val) SLPC_PARAM_IGNORE_EFFICIENT_FREQUENCY, val < slpc->rp1_freq); if (ret) { - i915_probe_error(i915, "Failed to toggle efficient freq (%pe)\n", - ERR_PTR(ret)); + guc_probe_error(slpc_to_guc(slpc), "Failed to toggle efficient freq: %pe\n", + ERR_PTR(ret)); goto out; } @@ -611,15 +603,12 @@ static int slpc_set_softlimits(struct intel_guc_slpc *slpc) static bool is_slpc_min_freq_rpmax(struct intel_guc_slpc *slpc) { - struct drm_i915_private *i915 = slpc_to_i915(slpc); int slpc_min_freq; int ret; ret = intel_guc_slpc_get_min_freq(slpc, &slpc_min_freq); if (ret) { - drm_err(&i915->drm, - "Failed to get min freq: (%d)\n", - ret); + guc_err(slpc_to_guc(slpc), "Failed to get min freq: %pe\n", ERR_PTR(ret)); return false; } @@ -685,9 +674,8 @@ int intel_guc_slpc_override_gucrc_mode(struct intel_guc_slpc *slpc, u32 mode) with_intel_runtime_pm(&i915->runtime_pm, wakeref) { ret = slpc_set_param(slpc, SLPC_PARAM_PWRGATE_RC_MODE, mode); if (ret) - drm_err(&i915->drm, - "Override gucrc mode %d failed %d\n", - mode, ret); + guc_err(slpc_to_guc(slpc), "Override RC mode %d failed: %pe\n", + mode, ERR_PTR(ret)); } return ret; @@ -702,9 +690,7 @@ int intel_guc_slpc_unset_gucrc_mode(struct intel_guc_slpc *slpc) with_intel_runtime_pm(&i915->runtime_pm, wakeref) { ret = slpc_unset_param(slpc, SLPC_PARAM_PWRGATE_RC_MODE); if (ret) - drm_err(&i915->drm, - "Unsetting gucrc mode failed %d\n", - ret); + guc_err(slpc_to_guc(slpc), "Unsetting RC mode failed: %pe\n", ERR_PTR(ret)); } return ret; @@ -725,7 +711,7 @@ int intel_guc_slpc_unset_gucrc_mode(struct intel_guc_slpc *slpc) */ int intel_guc_slpc_enable(struct intel_guc_slpc *slpc) { - struct drm_i915_private *i915 = slpc_to_i915(slpc); + struct intel_guc *guc = slpc_to_guc(slpc); int ret; GEM_BUG_ON(!slpc->vma); @@ -734,8 +720,7 @@ int intel_guc_slpc_enable(struct intel_guc_slpc *slpc) ret = slpc_reset(slpc); if (unlikely(ret < 0)) { - i915_probe_error(i915, "SLPC Reset event returned (%pe)\n", - ERR_PTR(ret)); + guc_probe_error(guc, "SLPC Reset event returned: %pe\n", ERR_PTR(ret)); return ret; } @@ -743,7 +728,7 @@ int intel_guc_slpc_enable(struct intel_guc_slpc *slpc) if (unlikely(ret < 0)) return ret; - intel_guc_pm_intrmsk_enable(to_gt(i915)); + intel_guc_pm_intrmsk_enable(slpc_to_gt(slpc)); slpc_get_rp_values(slpc); @@ -753,16 +738,14 @@ int intel_guc_slpc_enable(struct intel_guc_slpc *slpc) /* Set SLPC max limit to RP0 */ ret = slpc_use_fused_rp0(slpc); if (unlikely(ret)) { - i915_probe_error(i915, "Failed to set SLPC max to RP0 (%pe)\n", - ERR_PTR(ret)); + guc_probe_error(guc, "Failed to set SLPC max to RP0: %pe\n", ERR_PTR(ret)); return ret; } /* Revert SLPC min/max to softlimits if necessary */ ret = slpc_set_softlimits(slpc); if (unlikely(ret)) { - i915_probe_error(i915, "Failed to set SLPC softlimits (%pe)\n", - ERR_PTR(ret)); + guc_probe_error(guc, "Failed to set SLPC softlimits: %pe\n", ERR_PTR(ret)); return ret; } 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 b436dd7f12e4..88e881b100cf 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c @@ -27,6 +27,7 @@ #include "intel_guc_ads.h" #include "intel_guc_capture.h" +#include "intel_guc_print.h" #include "intel_guc_submission.h" #include "i915_drv.h" @@ -1351,6 +1352,16 @@ static ktime_t guc_engine_busyness(struct intel_engine_cs *engine, ktime_t *now) return ns_to_ktime(total); } +static void guc_enable_busyness_worker(struct intel_guc *guc) +{ + mod_delayed_work(system_highpri_wq, &guc->timestamp.work, guc->timestamp.ping_delay); +} + +static void guc_cancel_busyness_worker(struct intel_guc *guc) +{ + cancel_delayed_work_sync(&guc->timestamp.work); +} + static void __reset_guc_busyness_stats(struct intel_guc *guc) { struct intel_gt *gt = guc_to_gt(guc); @@ -1359,7 +1370,7 @@ static void __reset_guc_busyness_stats(struct intel_guc *guc) unsigned long flags; ktime_t unused; - cancel_delayed_work_sync(&guc->timestamp.work); + guc_cancel_busyness_worker(guc); spin_lock_irqsave(&guc->timestamp.lock, flags); @@ -1415,8 +1426,7 @@ static void guc_timestamp_ping(struct work_struct *wrk) intel_gt_reset_unlock(gt, srcu); - mod_delayed_work(system_highpri_wq, &guc->timestamp.work, - guc->timestamp.ping_delay); + guc_enable_busyness_worker(guc); } static int guc_action_enable_usage_stats(struct intel_guc *guc) @@ -1431,21 +1441,26 @@ static int guc_action_enable_usage_stats(struct intel_guc *guc) return intel_guc_send(guc, action, ARRAY_SIZE(action)); } -static void guc_init_engine_stats(struct intel_guc *guc) +static int guc_init_engine_stats(struct intel_guc *guc) { struct intel_gt *gt = guc_to_gt(guc); intel_wakeref_t wakeref; + int ret; - mod_delayed_work(system_highpri_wq, &guc->timestamp.work, - guc->timestamp.ping_delay); + with_intel_runtime_pm(>->i915->runtime_pm, wakeref) + ret = guc_action_enable_usage_stats(guc); - with_intel_runtime_pm(>->i915->runtime_pm, wakeref) { - int ret = guc_action_enable_usage_stats(guc); + if (ret) + guc_err(guc, "Failed to enable usage stats: %pe\n", ERR_PTR(ret)); + else + guc_enable_busyness_worker(guc); - if (ret) - drm_err(>->i915->drm, - "Failed to enable usage stats: %d!\n", ret); - } + return ret; +} + +static void guc_fini_engine_stats(struct intel_guc *guc) +{ + guc_cancel_busyness_worker(guc); } void intel_guc_busyness_park(struct intel_gt *gt) @@ -1460,7 +1475,7 @@ void intel_guc_busyness_park(struct intel_gt *gt) * and causes an unclaimed register access warning. Cancel the worker * synchronously here. */ - cancel_delayed_work_sync(&guc->timestamp.work); + guc_cancel_busyness_worker(guc); /* * Before parking, we should sample engine busyness stats if we need to. @@ -1487,8 +1502,7 @@ void intel_guc_busyness_unpark(struct intel_gt *gt) spin_lock_irqsave(&guc->timestamp.lock, flags); guc_update_pm_timestamp(guc, &unused); spin_unlock_irqrestore(&guc->timestamp.lock, flags); - mod_delayed_work(system_highpri_wq, &guc->timestamp.work, - guc->timestamp.ping_delay); + guc_enable_busyness_worker(guc); } static inline bool @@ -1702,7 +1716,7 @@ static void __guc_reset_context(struct intel_context *ce, intel_engine_mask_t st goto next_context; guilty = false; - rq = intel_context_find_active_request(ce); + rq = intel_context_get_active_request(ce); if (!rq) { head = ce->ring->tail; goto out_replay; @@ -1715,6 +1729,7 @@ static void __guc_reset_context(struct intel_context *ce, intel_engine_mask_t st head = intel_ring_wrap(ce->ring, rq->head); __i915_request_reset(rq, guilty); + i915_request_put(rq); out_replay: guc_reset_state(ce, head, guilty); next_context: @@ -3585,8 +3600,7 @@ static int guc_request_alloc(struct i915_request *rq) intel_context_sched_disable_unpin(ce); else if (intel_context_is_closed(ce)) if (wait_for(context_close_done(ce), 1500)) - drm_warn(&guc_to_gt(guc)->i915->drm, - "timed out waiting on context sched close before realloc\n"); + guc_warn(guc, "timed out waiting on context sched close before realloc\n"); /* * Call pin_guc_id here rather than in the pinning step as with * dma_resv, contexts can be repeatedly pinned / unpinned trashing the @@ -4102,9 +4116,11 @@ static void guc_set_default_submission(struct intel_engine_cs *engine) engine->submit_request = guc_submit_request; } -static inline void guc_kernel_context_pin(struct intel_guc *guc, - struct intel_context *ce) +static inline int guc_kernel_context_pin(struct intel_guc *guc, + struct intel_context *ce) { + int ret; + /* * Note: we purposefully do not check the returns below because * the registration can only fail if a reset is just starting. @@ -4112,16 +4128,24 @@ static inline void guc_kernel_context_pin(struct intel_guc *guc, * isn't happening and even it did this code would be run again. */ - if (context_guc_id_invalid(ce)) - pin_guc_id(guc, ce); + if (context_guc_id_invalid(ce)) { + ret = pin_guc_id(guc, ce); + + if (ret < 0) + return ret; + } if (!test_bit(CONTEXT_GUC_INIT, &ce->flags)) guc_context_init(ce); - try_context_registration(ce, true); + ret = try_context_registration(ce, true); + if (ret) + unpin_guc_id(guc, ce); + + return ret; } -static inline void guc_init_lrc_mapping(struct intel_guc *guc) +static inline int guc_init_submission(struct intel_guc *guc) { struct intel_gt *gt = guc_to_gt(guc); struct intel_engine_cs *engine; @@ -4148,9 +4172,17 @@ static inline void guc_init_lrc_mapping(struct intel_guc *guc) struct intel_context *ce; list_for_each_entry(ce, &engine->pinned_contexts_list, - pinned_contexts_link) - guc_kernel_context_pin(guc, ce); + pinned_contexts_link) { + int ret = guc_kernel_context_pin(guc, ce); + + if (ret) { + /* No point in trying to clean up as i915 will wedge on failure */ + return ret; + } + } } + + return 0; } static void guc_release(struct intel_engine_cs *engine) @@ -4349,11 +4381,14 @@ static int __guc_action_set_scheduling_policies(struct intel_guc *guc, ret = intel_guc_send(guc, (u32 *)&policy->h2g, __guc_scheduling_policy_action_size(policy)); - if (ret < 0) + if (ret < 0) { + guc_probe_error(guc, "Failed to configure global scheduling policies: %pe!\n", + ERR_PTR(ret)); return ret; + } if (ret != policy->count) { - drm_warn(&guc_to_gt(guc)->i915->drm, "GuC global scheduler policy processed %d of %d KLVs!", + guc_warn(guc, "global scheduler policy processed %d of %d KLVs!", ret, policy->count); if (ret > policy->count) return -EPROTO; @@ -4367,7 +4402,7 @@ static int guc_init_global_schedule_policy(struct intel_guc *guc) struct scheduling_policy policy; struct intel_gt *gt = guc_to_gt(guc); intel_wakeref_t wakeref; - int ret = 0; + int ret; if (GUC_SUBMIT_VER(guc) < MAKE_GUC_VER(1, 1, 0)) return 0; @@ -4385,39 +4420,62 @@ static int guc_init_global_schedule_policy(struct intel_guc *guc) yield, ARRAY_SIZE(yield)); ret = __guc_action_set_scheduling_policies(guc, &policy); - if (ret) - i915_probe_error(gt->i915, - "Failed to configure global scheduling policies: %pe!\n", - ERR_PTR(ret)); } return ret; } -void intel_guc_submission_enable(struct intel_guc *guc) +static void guc_route_semaphores(struct intel_guc *guc, bool to_guc) { struct intel_gt *gt = guc_to_gt(guc); + u32 val; - /* Enable and route to GuC */ - if (GRAPHICS_VER(gt->i915) >= 12) - intel_uncore_write(gt->uncore, GEN12_GUC_SEM_INTR_ENABLES, - GUC_SEM_INTR_ROUTE_TO_GUC | - GUC_SEM_INTR_ENABLE_ALL); + if (GRAPHICS_VER(gt->i915) < 12) + return; + + if (to_guc) + val = GUC_SEM_INTR_ROUTE_TO_GUC | GUC_SEM_INTR_ENABLE_ALL; + else + val = 0; - guc_init_lrc_mapping(guc); - guc_init_engine_stats(guc); - guc_init_global_schedule_policy(guc); + intel_uncore_write(gt->uncore, GEN12_GUC_SEM_INTR_ENABLES, val); } -void intel_guc_submission_disable(struct intel_guc *guc) +int intel_guc_submission_enable(struct intel_guc *guc) { - struct intel_gt *gt = guc_to_gt(guc); + int ret; + + /* Semaphore interrupt enable and route to GuC */ + guc_route_semaphores(guc, true); + + ret = guc_init_submission(guc); + if (ret) + goto fail_sem; + + ret = guc_init_engine_stats(guc); + if (ret) + goto fail_sem; + + ret = guc_init_global_schedule_policy(guc); + if (ret) + goto fail_stats; + + return 0; + +fail_stats: + guc_fini_engine_stats(guc); +fail_sem: + guc_route_semaphores(guc, false); + return ret; +} - /* Note: By the time we're here, GuC may have already been reset */ +/* Note: By the time we're here, GuC may have already been reset */ +void intel_guc_submission_disable(struct intel_guc *guc) +{ + guc_cancel_busyness_worker(guc); - /* Disable and route to host */ - if (GRAPHICS_VER(gt->i915) >= 12) - intel_uncore_write(gt->uncore, GEN12_GUC_SEM_INTR_ENABLES, 0x0); + /* Semaphore interrupt disable and route to host */ + guc_route_semaphores(guc, false); } static bool __guc_submission_supported(struct intel_guc *guc) @@ -4487,21 +4545,18 @@ g2h_context_lookup(struct intel_guc *guc, u32 ctx_id) struct intel_context *ce; if (unlikely(ctx_id >= GUC_MAX_CONTEXT_ID)) { - drm_err(&guc_to_gt(guc)->i915->drm, - "Invalid ctx_id %u\n", ctx_id); + guc_err(guc, "Invalid ctx_id %u\n", ctx_id); return NULL; } ce = __get_context(guc, ctx_id); if (unlikely(!ce)) { - drm_err(&guc_to_gt(guc)->i915->drm, - "Context is NULL, ctx_id %u\n", ctx_id); + guc_err(guc, "Context is NULL, ctx_id %u\n", ctx_id); return NULL; } if (unlikely(intel_context_is_child(ce))) { - drm_err(&guc_to_gt(guc)->i915->drm, - "Context is child, ctx_id %u\n", ctx_id); + guc_err(guc, "Context is child, ctx_id %u\n", ctx_id); return NULL; } @@ -4516,7 +4571,7 @@ int intel_guc_deregister_done_process_msg(struct intel_guc *guc, u32 ctx_id; if (unlikely(len < 1)) { - drm_err(&guc_to_gt(guc)->i915->drm, "Invalid length %u\n", len); + guc_err(guc, "Invalid length %u\n", len); return -EPROTO; } ctx_id = msg[0]; @@ -4568,7 +4623,7 @@ int intel_guc_sched_done_process_msg(struct intel_guc *guc, u32 ctx_id; if (unlikely(len < 2)) { - drm_err(&guc_to_gt(guc)->i915->drm, "Invalid length %u\n", len); + guc_err(guc, "Invalid length %u\n", len); return -EPROTO; } ctx_id = msg[0]; @@ -4580,8 +4635,7 @@ int intel_guc_sched_done_process_msg(struct intel_guc *guc, if (unlikely(context_destroyed(ce) || (!context_pending_enable(ce) && !context_pending_disable(ce)))) { - drm_err(&guc_to_gt(guc)->i915->drm, - "Bad context sched_state 0x%x, ctx_id %u\n", + guc_err(guc, "Bad context sched_state 0x%x, ctx_id %u\n", ce->guc_state.sched_state, ctx_id); return -EPROTO; } @@ -4665,12 +4719,16 @@ static void guc_handle_context_reset(struct intel_guc *guc, { trace_intel_context_reset(ce); + guc_dbg(guc, "Got context reset notification: 0x%04X on %s, exiting = %s, banned = %s\n", + ce->guc_id.id, ce->engine->name, + str_yes_no(intel_context_is_exiting(ce)), + str_yes_no(intel_context_is_banned(ce))); + if (likely(intel_context_is_schedulable(ce))) { capture_error_state(guc, ce); guc_context_replay(ce); } else { - drm_info(&guc_to_gt(guc)->i915->drm, - "Ignoring context reset notification of exiting context 0x%04X on %s", + guc_info(guc, "Ignoring context reset notification of exiting context 0x%04X on %s", ce->guc_id.id, ce->engine->name); } } @@ -4683,7 +4741,7 @@ int intel_guc_context_reset_process_msg(struct intel_guc *guc, int ctx_id; if (unlikely(len != 1)) { - drm_err(&guc_to_gt(guc)->i915->drm, "Invalid length %u", len); + guc_err(guc, "Invalid length %u", len); return -EPROTO; } @@ -4716,13 +4774,13 @@ int intel_guc_error_capture_process_msg(struct intel_guc *guc, u32 status; if (unlikely(len != 1)) { - drm_dbg(&guc_to_gt(guc)->i915->drm, "Invalid length %u", len); + guc_dbg(guc, "Invalid length %u", len); return -EPROTO; } status = msg[0] & INTEL_GUC_STATE_CAPTURE_EVENT_STATUS_MASK; if (status == INTEL_GUC_STATE_CAPTURE_EVENT_STATUS_NOSPACE) - drm_warn(&guc_to_gt(guc)->i915->drm, "G2H-Error capture no space"); + guc_warn(guc, "No space for error capture"); intel_guc_capture_process(guc); @@ -4754,24 +4812,36 @@ static void reset_fail_worker_func(struct work_struct *w) guc->submission_state.reset_fail_mask = 0; spin_unlock_irqrestore(&guc->submission_state.lock, flags); - if (likely(reset_fail_mask)) + if (likely(reset_fail_mask)) { + struct intel_engine_cs *engine; + enum intel_engine_id id; + + /* + * GuC is toast at this point - it dead loops after sending the failed + * reset notification. So need to manually determine the guilty context. + * Note that it should be reliable to do this here because the GuC is + * toast and will not be scheduling behind the KMD's back. + */ + for_each_engine_masked(engine, gt, reset_fail_mask, id) + intel_guc_find_hung_context(engine); + intel_gt_handle_error(gt, reset_fail_mask, I915_ERROR_CAPTURE, - "GuC failed to reset engine mask=0x%x\n", + "GuC failed to reset engine mask=0x%x", reset_fail_mask); + } } int intel_guc_engine_failure_process_msg(struct intel_guc *guc, const u32 *msg, u32 len) { struct intel_engine_cs *engine; - struct intel_gt *gt = guc_to_gt(guc); u8 guc_class, instance; u32 reason; unsigned long flags; if (unlikely(len != 3)) { - drm_err(>->i915->drm, "Invalid length %u", len); + guc_err(guc, "Invalid length %u", len); return -EPROTO; } @@ -4781,8 +4851,7 @@ int intel_guc_engine_failure_process_msg(struct intel_guc *guc, engine = intel_guc_lookup_engine(guc, guc_class, instance); if (unlikely(!engine)) { - drm_err(>->i915->drm, - "Invalid engine %d:%d", guc_class, instance); + guc_err(guc, "Invalid engine %d:%d", guc_class, instance); return -EPROTO; } @@ -4790,7 +4859,7 @@ int intel_guc_engine_failure_process_msg(struct intel_guc *guc, * This is an unexpected failure of a hardware feature. So, log a real * error message not just the informational that comes with the reset. */ - drm_err(>->i915->drm, "GuC engine reset request failed on %d:%d (%s) because 0x%08X", + guc_err(guc, "Engine reset failed on %d:%d (%s) because 0x%08X", guc_class, instance, engine->name, reason); spin_lock_irqsave(&guc->submission_state.lock, flags); @@ -4820,6 +4889,8 @@ void intel_guc_find_hung_context(struct intel_engine_cs *engine) xa_lock_irqsave(&guc->context_lookup, flags); xa_for_each(&guc->context_lookup, index, ce) { + bool found; + if (!kref_get_unless_zero(&ce->ref)) continue; @@ -4836,10 +4907,18 @@ void intel_guc_find_hung_context(struct intel_engine_cs *engine) goto next; } + found = false; + spin_lock(&ce->guc_state.lock); list_for_each_entry(rq, &ce->guc_state.requests, sched.link) { if (i915_test_request_state(rq) != I915_REQUEST_ACTIVE) continue; + found = true; + break; + } + spin_unlock(&ce->guc_state.lock); + + if (found) { intel_engine_set_hung_context(engine, ce); /* Can only cope with one hang at a time... */ @@ -4847,6 +4926,7 @@ void intel_guc_find_hung_context(struct intel_engine_cs *engine) xa_lock(&guc->context_lookup); goto done; } + next: intel_context_put(ce); xa_lock(&guc->context_lookup); @@ -5342,8 +5422,8 @@ guc_create_virtual(struct intel_engine_cs **siblings, unsigned int count, GEM_BUG_ON(!is_power_of_2(sibling->mask)); if (sibling->mask & ve->base.mask) { - DRM_DEBUG("duplicate %s entry in load balancer\n", - sibling->name); + guc_dbg(guc, "duplicate %s entry in load balancer\n", + sibling->name); err = -EINVAL; goto err_put; } @@ -5352,8 +5432,8 @@ guc_create_virtual(struct intel_engine_cs **siblings, unsigned int count, ve->base.logical_mask |= sibling->logical_mask; if (n != 0 && ve->base.class != sibling->class) { - DRM_DEBUG("invalid mixing of engine class, sibling %d, already %d\n", - sibling->class, ve->base.class); + guc_dbg(guc, "invalid mixing of engine class, sibling %d, already %d\n", + sibling->class, ve->base.class); err = -EINVAL; goto err_put; } else if (n == 0) { diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.h b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.h index 5a95a9f0a8e3..c57b29cdb1a6 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.h +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.h @@ -15,7 +15,7 @@ struct intel_engine_cs; void intel_guc_submission_init_early(struct intel_guc *guc); int intel_guc_submission_init(struct intel_guc *guc); -void intel_guc_submission_enable(struct intel_guc *guc); +int intel_guc_submission_enable(struct intel_guc *guc); void intel_guc_submission_disable(struct intel_guc *guc); void intel_guc_submission_fini(struct intel_guc *guc); int intel_guc_preempt_work_create(struct intel_guc *guc); diff --git a/drivers/gpu/drm/i915/gt/uc/intel_huc.c b/drivers/gpu/drm/i915/gt/uc/intel_huc.c index 410905da8e97..72884e21470b 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_huc.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_huc.c @@ -6,6 +6,7 @@ #include <linux/types.h> #include "gt/intel_gt.h" +#include "gt/intel_gt_print.h" #include "intel_guc_reg.h" #include "intel_huc.h" #include "i915_drv.h" @@ -13,6 +14,15 @@ #include <linux/device/bus.h> #include <linux/mei_aux.h> +#define huc_printk(_huc, _level, _fmt, ...) \ + gt_##_level(huc_to_gt(_huc), "HuC: " _fmt, ##__VA_ARGS__) +#define huc_err(_huc, _fmt, ...) huc_printk((_huc), err, _fmt, ##__VA_ARGS__) +#define huc_warn(_huc, _fmt, ...) huc_printk((_huc), warn, _fmt, ##__VA_ARGS__) +#define huc_notice(_huc, _fmt, ...) huc_printk((_huc), notice, _fmt, ##__VA_ARGS__) +#define huc_info(_huc, _fmt, ...) huc_printk((_huc), info, _fmt, ##__VA_ARGS__) +#define huc_dbg(_huc, _fmt, ...) huc_printk((_huc), dbg, _fmt, ##__VA_ARGS__) +#define huc_probe_error(_huc, _fmt, ...) huc_printk((_huc), probe_error, _fmt, ##__VA_ARGS__) + /** * DOC: HuC * @@ -107,11 +117,9 @@ static enum hrtimer_restart huc_delayed_load_timer_callback(struct hrtimer *hrti if (!intel_huc_is_authenticated(huc)) { if (huc->delayed_load.status == INTEL_HUC_WAITING_ON_GSC) - drm_notice(&huc_to_gt(huc)->i915->drm, - "timed out waiting for MEI GSC init to load HuC\n"); + huc_notice(huc, "timed out waiting for MEI GSC\n"); else if (huc->delayed_load.status == INTEL_HUC_WAITING_ON_PXP) - drm_notice(&huc_to_gt(huc)->i915->drm, - "timed out waiting for MEI PXP init to load HuC\n"); + huc_notice(huc, "timed out waiting for MEI PXP\n"); else MISSING_CASE(huc->delayed_load.status); @@ -174,8 +182,7 @@ static int gsc_notifier(struct notifier_block *nb, unsigned long action, void *d case BUS_NOTIFY_DRIVER_NOT_BOUND: /* mei driver fails to be bound */ case BUS_NOTIFY_UNBIND_DRIVER: /* mei driver about to be unbound */ - drm_info(&huc_to_gt(huc)->i915->drm, - "mei driver not bound, disabling HuC load\n"); + huc_info(huc, "MEI driver not bound, disabling load\n"); gsc_init_error(huc); break; } @@ -193,8 +200,7 @@ void intel_huc_register_gsc_notifier(struct intel_huc *huc, struct bus_type *bus huc->delayed_load.nb.notifier_call = gsc_notifier; ret = bus_register_notifier(bus, &huc->delayed_load.nb); if (ret) { - drm_err(&huc_to_gt(huc)->i915->drm, - "failed to register GSC notifier\n"); + huc_err(huc, "failed to register GSC notifier %pe\n", ERR_PTR(ret)); huc->delayed_load.nb.notifier_call = NULL; gsc_init_error(huc); } @@ -306,29 +312,25 @@ static int check_huc_loading_mode(struct intel_huc *huc) GSC_LOADS_HUC; if (fw_needs_gsc != hw_uses_gsc) { - drm_err(>->i915->drm, - "mismatch between HuC FW (%s) and HW (%s) load modes\n", - HUC_LOAD_MODE_STRING(fw_needs_gsc), - HUC_LOAD_MODE_STRING(hw_uses_gsc)); + huc_err(huc, "mismatch between FW (%s) and HW (%s) load modes\n", + HUC_LOAD_MODE_STRING(fw_needs_gsc), HUC_LOAD_MODE_STRING(hw_uses_gsc)); return -ENOEXEC; } /* make sure we can access the GSC via the mei driver if we need it */ if (!(IS_ENABLED(CONFIG_INTEL_MEI_PXP) && IS_ENABLED(CONFIG_INTEL_MEI_GSC)) && fw_needs_gsc) { - drm_info(>->i915->drm, - "Can't load HuC due to missing MEI modules\n"); + huc_info(huc, "can't load due to missing MEI modules\n"); return -EIO; } - drm_dbg(>->i915->drm, "GSC loads huc=%s\n", str_yes_no(fw_needs_gsc)); + huc_dbg(huc, "loaded by GSC = %s\n", str_yes_no(fw_needs_gsc)); return 0; } int intel_huc_init(struct intel_huc *huc) { - struct drm_i915_private *i915 = huc_to_gt(huc)->i915; int err; err = check_huc_loading_mode(huc); @@ -345,7 +347,7 @@ int intel_huc_init(struct intel_huc *huc) out: intel_uc_fw_change_status(&huc->fw, INTEL_UC_FIRMWARE_INIT_FAIL); - drm_info(&i915->drm, "HuC init failed with %d\n", err); + huc_info(huc, "initialization failed %pe\n", ERR_PTR(err)); return err; } @@ -389,13 +391,13 @@ int intel_huc_wait_for_auth_complete(struct intel_huc *huc) delayed_huc_load_complete(huc); if (ret) { - drm_err(>->i915->drm, "HuC: Firmware not verified %d\n", ret); + huc_err(huc, "firmware not verified %pe\n", ERR_PTR(ret)); intel_uc_fw_change_status(&huc->fw, INTEL_UC_FIRMWARE_LOAD_FAIL); return ret; } intel_uc_fw_change_status(&huc->fw, INTEL_UC_FIRMWARE_RUNNING); - drm_info(>->i915->drm, "HuC authenticated\n"); + huc_info(huc, "authenticated!\n"); return 0; } @@ -430,7 +432,7 @@ int intel_huc_auth(struct intel_huc *huc) ret = intel_guc_auth_huc(guc, intel_guc_ggtt_offset(guc, huc->fw.rsa_data)); if (ret) { - DRM_ERROR("HuC: GuC did not ack Auth request %d\n", ret); + huc_err(huc, "authentication by GuC failed %pe\n", ERR_PTR(ret)); goto fail; } @@ -442,7 +444,7 @@ int intel_huc_auth(struct intel_huc *huc) return 0; fail: - i915_probe_error(gt->i915, "HuC: Authentication failed %d\n", ret); + huc_probe_error(huc, "authentication failed %pe\n", ERR_PTR(ret)); return ret; } diff --git a/drivers/gpu/drm/i915/gt/uc/intel_uc.c b/drivers/gpu/drm/i915/gt/uc/intel_uc.c index 9a8a1abf71d7..4ccb4be4c9cb 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_uc.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_uc.c @@ -6,11 +6,13 @@ #include <linux/string_helpers.h> #include "gt/intel_gt.h" +#include "gt/intel_gt_print.h" #include "gt/intel_reset.h" #include "intel_gsc_fw.h" #include "intel_gsc_uc.h" #include "intel_guc.h" #include "intel_guc_ads.h" +#include "intel_guc_print.h" #include "intel_guc_submission.h" #include "gt/intel_rps.h" #include "intel_uc.h" @@ -67,29 +69,29 @@ static int __intel_uc_reset_hw(struct intel_uc *uc) ret = intel_reset_guc(gt); if (ret) { - DRM_ERROR("Failed to reset GuC, ret = %d\n", ret); + gt_err(gt, "Failed to reset GuC, ret = %d\n", ret); return ret; } guc_status = intel_uncore_read(gt->uncore, GUC_STATUS); - WARN(!(guc_status & GS_MIA_IN_RESET), - "GuC status: 0x%x, MIA core expected to be in reset\n", - guc_status); + gt_WARN(gt, !(guc_status & GS_MIA_IN_RESET), + "GuC status: 0x%x, MIA core expected to be in reset\n", + guc_status); return ret; } static void __confirm_options(struct intel_uc *uc) { - struct drm_i915_private *i915 = uc_to_gt(uc)->i915; + struct intel_gt *gt = uc_to_gt(uc); + struct drm_i915_private *i915 = gt->i915; - drm_dbg(&i915->drm, - "enable_guc=%d (guc:%s submission:%s huc:%s slpc:%s)\n", - i915->params.enable_guc, - str_yes_no(intel_uc_wants_guc(uc)), - str_yes_no(intel_uc_wants_guc_submission(uc)), - str_yes_no(intel_uc_wants_huc(uc)), - str_yes_no(intel_uc_wants_guc_slpc(uc))); + gt_dbg(gt, "enable_guc=%d (guc:%s submission:%s huc:%s slpc:%s)\n", + i915->params.enable_guc, + str_yes_no(intel_uc_wants_guc(uc)), + str_yes_no(intel_uc_wants_guc_submission(uc)), + str_yes_no(intel_uc_wants_huc(uc)), + str_yes_no(intel_uc_wants_guc_slpc(uc))); if (i915->params.enable_guc == 0) { GEM_BUG_ON(intel_uc_wants_guc(uc)); @@ -100,26 +102,22 @@ static void __confirm_options(struct intel_uc *uc) } if (!intel_uc_supports_guc(uc)) - drm_info(&i915->drm, - "Incompatible option enable_guc=%d - %s\n", - i915->params.enable_guc, "GuC is not supported!"); + gt_info(gt, "Incompatible option enable_guc=%d - %s\n", + i915->params.enable_guc, "GuC is not supported!"); if (i915->params.enable_guc & ENABLE_GUC_LOAD_HUC && !intel_uc_supports_huc(uc)) - drm_info(&i915->drm, - "Incompatible option enable_guc=%d - %s\n", - i915->params.enable_guc, "HuC is not supported!"); + gt_info(gt, "Incompatible option enable_guc=%d - %s\n", + i915->params.enable_guc, "HuC is not supported!"); if (i915->params.enable_guc & ENABLE_GUC_SUBMISSION && !intel_uc_supports_guc_submission(uc)) - drm_info(&i915->drm, - "Incompatible option enable_guc=%d - %s\n", - i915->params.enable_guc, "GuC submission is N/A"); + gt_info(gt, "Incompatible option enable_guc=%d - %s\n", + i915->params.enable_guc, "GuC submission is N/A"); if (i915->params.enable_guc & ~ENABLE_GUC_MASK) - drm_info(&i915->drm, - "Incompatible option enable_guc=%d - %s\n", - i915->params.enable_guc, "undocumented flag"); + gt_info(gt, "Incompatible option enable_guc=%d - %s\n", + i915->params.enable_guc, "undocumented flag"); } void intel_uc_init_early(struct intel_uc *uc) @@ -141,6 +139,7 @@ void intel_uc_init_early(struct intel_uc *uc) void intel_uc_init_late(struct intel_uc *uc) { intel_guc_init_late(&uc->guc); + intel_gsc_uc_load_start(&uc->gsc); } void intel_uc_driver_late_release(struct intel_uc *uc) @@ -252,15 +251,13 @@ static int guc_enable_communication(struct intel_guc *guc) intel_guc_ct_event_handler(&guc->ct); spin_unlock_irq(gt->irq_lock); - drm_dbg(&i915->drm, "GuC communication enabled\n"); + guc_dbg(guc, "communication enabled\n"); return 0; } static void guc_disable_communication(struct intel_guc *guc) { - struct drm_i915_private *i915 = guc_to_gt(guc)->i915; - /* * Events generated during or after CT disable are logged by guc in * via mmio. Make sure the register is clear before disabling CT since @@ -280,11 +277,12 @@ static void guc_disable_communication(struct intel_guc *guc) */ guc_get_mmio_msg(guc); - drm_dbg(&i915->drm, "GuC communication disabled\n"); + guc_dbg(guc, "communication disabled\n"); } static void __uc_fetch_firmwares(struct intel_uc *uc) { + struct intel_gt *gt = uc_to_gt(uc); int err; GEM_BUG_ON(!intel_uc_wants_guc(uc)); @@ -293,15 +291,13 @@ static void __uc_fetch_firmwares(struct intel_uc *uc) if (err) { /* Make sure we transition out of transient "SELECTED" state */ if (intel_uc_wants_huc(uc)) { - drm_dbg(&uc_to_gt(uc)->i915->drm, - "Failed to fetch GuC: %d disabling HuC\n", err); + gt_dbg(gt, "Failed to fetch GuC fw (%pe) disabling HuC\n", ERR_PTR(err)); intel_uc_fw_change_status(&uc->huc.fw, INTEL_UC_FIRMWARE_ERROR); } if (intel_uc_wants_gsc_uc(uc)) { - drm_dbg(&uc_to_gt(uc)->i915->drm, - "Failed to fetch GuC: %d disabling GSC\n", err); + gt_dbg(gt, "Failed to fetch GuC fw (%pe) disabling GSC\n", ERR_PTR(err)); intel_uc_fw_change_status(&uc->gsc.fw, INTEL_UC_FIRMWARE_ERROR); } @@ -382,7 +378,7 @@ static int uc_init_wopcm(struct intel_uc *uc) int err; if (unlikely(!base || !size)) { - i915_probe_error(gt->i915, "Unsuccessful WOPCM partitioning\n"); + gt_probe_error(gt, "Unsuccessful WOPCM partitioning\n"); return -E2BIG; } @@ -413,13 +409,13 @@ static int uc_init_wopcm(struct intel_uc *uc) return 0; err_out: - i915_probe_error(gt->i915, "Failed to init uC WOPCM registers!\n"); - i915_probe_error(gt->i915, "%s(%#x)=%#x\n", "DMA_GUC_WOPCM_OFFSET", - i915_mmio_reg_offset(DMA_GUC_WOPCM_OFFSET), - intel_uncore_read(uncore, DMA_GUC_WOPCM_OFFSET)); - i915_probe_error(gt->i915, "%s(%#x)=%#x\n", "GUC_WOPCM_SIZE", - i915_mmio_reg_offset(GUC_WOPCM_SIZE), - intel_uncore_read(uncore, GUC_WOPCM_SIZE)); + gt_probe_error(gt, "Failed to init uC WOPCM registers!\n"); + gt_probe_error(gt, "%s(%#x)=%#x\n", "DMA_GUC_WOPCM_OFFSET", + i915_mmio_reg_offset(DMA_GUC_WOPCM_OFFSET), + intel_uncore_read(uncore, DMA_GUC_WOPCM_OFFSET)); + gt_probe_error(gt, "%s(%#x)=%#x\n", "GUC_WOPCM_SIZE", + i915_mmio_reg_offset(GUC_WOPCM_SIZE), + intel_uncore_read(uncore, GUC_WOPCM_SIZE)); return err; } @@ -449,20 +445,19 @@ 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) +static void print_fw_ver(struct intel_gt *gt, 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.%u\n", - intel_uc_fw_type_repr(fw->type), fw->file_selected.path, - fw->file_selected.ver.major, - fw->file_selected.ver.minor, - fw->file_selected.ver.patch); + gt_info(gt, "%s firmware %s version %u.%u.%u\n", + intel_uc_fw_type_repr(fw->type), fw->file_selected.path, + fw->file_selected.ver.major, + fw->file_selected.ver.minor, + fw->file_selected.ver.patch); } static int __uc_init_hw(struct intel_uc *uc) { - struct drm_i915_private *i915 = uc_to_gt(uc)->i915; + struct intel_gt *gt = uc_to_gt(uc); + struct drm_i915_private *i915 = gt->i915; struct intel_guc *guc = &uc->guc; struct intel_huc *huc = &uc->huc; int ret, attempts; @@ -470,10 +465,10 @@ 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); + print_fw_ver(gt, &guc->fw); if (intel_uc_uses_huc(uc)) - print_fw_ver(uc, &huc->fw); + print_fw_ver(gt, &huc->fw); if (!intel_uc_fw_is_loadable(&guc->fw)) { ret = __uc_check_hw(uc) || @@ -514,8 +509,8 @@ static int __uc_init_hw(struct intel_uc *uc) if (ret == 0) break; - DRM_DEBUG_DRIVER("GuC fw load failed: %d; will reset and " - "retry %d more time(s)\n", ret, attempts); + gt_dbg(gt, "GuC fw load failed (%pe) will reset and retry %d more time(s)\n", + ERR_PTR(ret), attempts); } /* Did we succeded or run out of retries? */ @@ -537,8 +532,11 @@ static int __uc_init_hw(struct intel_uc *uc) else intel_huc_auth(huc); - if (intel_uc_uses_guc_submission(uc)) - intel_guc_submission_enable(guc); + if (intel_uc_uses_guc_submission(uc)) { + ret = intel_guc_submission_enable(guc); + if (ret) + goto err_log_capture; + } if (intel_uc_uses_guc_slpc(uc)) { ret = intel_guc_slpc_enable(&guc->slpc); @@ -549,12 +547,8 @@ static int __uc_init_hw(struct intel_uc *uc) intel_rps_lower_unslice(&uc_to_gt(uc)->rps); } - intel_gsc_uc_load_start(&uc->gsc); - - drm_info(&i915->drm, "GuC submission %s\n", - str_enabled_disabled(intel_uc_uses_guc_submission(uc))); - drm_info(&i915->drm, "GuC SLPC %s\n", - str_enabled_disabled(intel_uc_uses_guc_slpc(uc))); + guc_info(guc, "submission %s\n", str_enabled_disabled(intel_uc_uses_guc_submission(uc))); + guc_info(guc, "SLPC %s\n", str_enabled_disabled(intel_uc_uses_guc_slpc(uc))); return 0; @@ -572,12 +566,12 @@ err_out: __uc_sanitize(uc); if (!ret) { - drm_notice(&i915->drm, "GuC is uninitialized\n"); + gt_notice(gt, "GuC is uninitialized\n"); /* We want to run without GuC submission */ return 0; } - i915_probe_error(i915, "GuC initialization failed %d\n", ret); + gt_probe_error(gt, "GuC initialization failed %pe\n", ERR_PTR(ret)); /* We want to keep KMS alive */ return -EIO; @@ -680,7 +674,7 @@ void intel_uc_suspend(struct intel_uc *uc) int err; /* flush the GSC worker */ - intel_gsc_uc_suspend(&uc->gsc); + intel_gsc_uc_flush_work(&uc->gsc); if (!intel_guc_is_ready(guc)) { guc->interrupts.enabled = false; @@ -690,7 +684,7 @@ void intel_uc_suspend(struct intel_uc *uc) with_intel_runtime_pm(&uc_to_gt(uc)->i915->runtime_pm, wakeref) { err = intel_guc_suspend(guc); if (err) - DRM_DEBUG_DRIVER("Failed to suspend GuC, err=%d", err); + guc_dbg(guc, "Failed to suspend, %pe", ERR_PTR(err)); } } @@ -718,10 +712,12 @@ static int __uc_resume(struct intel_uc *uc, bool enable_communication) err = intel_guc_resume(guc); if (err) { - DRM_DEBUG_DRIVER("Failed to resume GuC, err=%d", err); + guc_dbg(guc, "Failed to resume, %pe", ERR_PTR(err)); return err; } + intel_gsc_uc_resume(&uc->gsc); + 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 65672ff82605..264c952f777b 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c @@ -11,6 +11,7 @@ #include <drm/drm_print.h> #include "gem/i915_gem_lmem.h" +#include "gt/intel_gt_print.h" #include "intel_uc_fw.h" #include "intel_uc_fw_abi.h" #include "i915_drv.h" @@ -44,11 +45,10 @@ void intel_uc_fw_change_status(struct intel_uc_fw *uc_fw, enum intel_uc_fw_status status) { uc_fw->__status = status; - drm_dbg(&__uc_fw_to_gt(uc_fw)->i915->drm, - "%s firmware -> %s\n", - intel_uc_fw_type_repr(uc_fw->type), - status == INTEL_UC_FIRMWARE_SELECTED ? - uc_fw->file_selected.path : intel_uc_fw_status_repr(status)); + gt_dbg(__uc_fw_to_gt(uc_fw), "%s firmware -> %s\n", + intel_uc_fw_type_repr(uc_fw->type), + status == INTEL_UC_FIRMWARE_SELECTED ? + uc_fw->file_selected.path : intel_uc_fw_status_repr(status)); } #endif @@ -562,15 +562,14 @@ static int check_ccs_header(struct intel_gt *gt, const struct firmware *fw, struct intel_uc_fw *uc_fw) { - struct drm_i915_private *i915 = gt->i915; struct uc_css_header *css; size_t size; /* Check the size of the blob before examining buffer contents */ if (unlikely(fw->size < sizeof(struct uc_css_header))) { - drm_warn(&i915->drm, "%s firmware %s: invalid size: %zu < %zu\n", - intel_uc_fw_type_repr(uc_fw->type), uc_fw->file_selected.path, - fw->size, sizeof(struct uc_css_header)); + gt_warn(gt, "%s firmware %s: invalid size: %zu < %zu\n", + intel_uc_fw_type_repr(uc_fw->type), uc_fw->file_selected.path, + fw->size, sizeof(struct uc_css_header)); return -ENODATA; } @@ -580,10 +579,9 @@ static int check_ccs_header(struct intel_gt *gt, size = (css->header_size_dw - css->key_size_dw - css->modulus_size_dw - css->exponent_size_dw) * sizeof(u32); if (unlikely(size != sizeof(struct uc_css_header))) { - drm_warn(&i915->drm, - "%s firmware %s: unexpected header size: %zu != %zu\n", - intel_uc_fw_type_repr(uc_fw->type), uc_fw->file_selected.path, - fw->size, sizeof(struct uc_css_header)); + gt_warn(gt, "%s firmware %s: unexpected header size: %zu != %zu\n", + intel_uc_fw_type_repr(uc_fw->type), uc_fw->file_selected.path, + fw->size, sizeof(struct uc_css_header)); return -EPROTO; } @@ -596,18 +594,18 @@ static int check_ccs_header(struct intel_gt *gt, /* At least, it should have header, uCode and RSA. Size of all three. */ size = sizeof(struct uc_css_header) + uc_fw->ucode_size + uc_fw->rsa_size; if (unlikely(fw->size < size)) { - drm_warn(&i915->drm, "%s firmware %s: invalid size: %zu < %zu\n", - intel_uc_fw_type_repr(uc_fw->type), uc_fw->file_selected.path, - fw->size, size); + gt_warn(gt, "%s firmware %s: invalid size: %zu < %zu\n", + intel_uc_fw_type_repr(uc_fw->type), uc_fw->file_selected.path, + fw->size, size); return -ENOEXEC; } /* Sanity check whether this fw is not larger than whole WOPCM memory */ size = __intel_uc_fw_get_upload_size(uc_fw); if (unlikely(size >= gt->wopcm.size)) { - drm_warn(&i915->drm, "%s firmware %s: invalid size: %zu > %zu\n", - intel_uc_fw_type_repr(uc_fw->type), uc_fw->file_selected.path, - size, (size_t)gt->wopcm.size); + gt_warn(gt, "%s firmware %s: invalid size: %zu > %zu\n", + intel_uc_fw_type_repr(uc_fw->type), uc_fw->file_selected.path, + size, (size_t)gt->wopcm.size); return -E2BIG; } @@ -635,20 +633,20 @@ static bool guc_check_version_range(struct intel_uc_fw *uc_fw) */ if (!is_ver_8bit(&uc_fw->file_selected.ver)) { - drm_warn(&__uc_fw_to_gt(uc_fw)->i915->drm, "%s firmware: invalid file version: 0x%02X:%02X:%02X\n", - intel_uc_fw_type_repr(uc_fw->type), - uc_fw->file_selected.ver.major, - uc_fw->file_selected.ver.minor, - uc_fw->file_selected.ver.patch); + gt_warn(__uc_fw_to_gt(uc_fw), "%s firmware: invalid file version: 0x%02X:%02X:%02X\n", + intel_uc_fw_type_repr(uc_fw->type), + uc_fw->file_selected.ver.major, + uc_fw->file_selected.ver.minor, + uc_fw->file_selected.ver.patch); return false; } if (!is_ver_8bit(&guc->submission_version)) { - drm_warn(&__uc_fw_to_gt(uc_fw)->i915->drm, "%s firmware: invalid submit version: 0x%02X:%02X:%02X\n", - intel_uc_fw_type_repr(uc_fw->type), - guc->submission_version.major, - guc->submission_version.minor, - guc->submission_version.patch); + gt_warn(__uc_fw_to_gt(uc_fw), "%s firmware: invalid submit version: 0x%02X:%02X:%02X\n", + intel_uc_fw_type_repr(uc_fw->type), + guc->submission_version.major, + guc->submission_version.minor, + guc->submission_version.patch); return false; } @@ -687,10 +685,9 @@ static int try_firmware_load(struct intel_uc_fw *uc_fw, const struct firmware ** return err; if ((*fw)->size > INTEL_UC_RSVD_GGTT_PER_FW) { - drm_err(>->i915->drm, - "%s firmware %s: size (%zuKB) exceeds max supported size (%uKB)\n", - intel_uc_fw_type_repr(uc_fw->type), uc_fw->file_selected.path, - (*fw)->size / SZ_1K, INTEL_UC_RSVD_GGTT_PER_FW / SZ_1K); + gt_err(gt, "%s firmware %s: size (%zuKB) exceeds max supported size (%uKB)\n", + intel_uc_fw_type_repr(uc_fw->type), uc_fw->file_selected.path, + (*fw)->size / SZ_1K, INTEL_UC_RSVD_GGTT_PER_FW / SZ_1K); /* try to find another blob to load */ release_firmware(*fw); @@ -768,10 +765,10 @@ int intel_uc_fw_fetch(struct intel_uc_fw *uc_fw) if (uc_fw->file_wanted.ver.major && uc_fw->file_selected.ver.major) { /* Check the file's major version was as it claimed */ if (uc_fw->file_selected.ver.major != uc_fw->file_wanted.ver.major) { - drm_notice(&i915->drm, "%s firmware %s: unexpected version: %u.%u != %u.%u\n", - intel_uc_fw_type_repr(uc_fw->type), uc_fw->file_selected.path, - uc_fw->file_selected.ver.major, uc_fw->file_selected.ver.minor, - uc_fw->file_wanted.ver.major, uc_fw->file_wanted.ver.minor); + gt_notice(gt, "%s firmware %s: unexpected version: %u.%u != %u.%u\n", + intel_uc_fw_type_repr(uc_fw->type), uc_fw->file_selected.path, + uc_fw->file_selected.ver.major, uc_fw->file_selected.ver.minor, + uc_fw->file_wanted.ver.major, uc_fw->file_wanted.ver.minor); if (!intel_uc_fw_is_overridden(uc_fw)) { err = -ENOEXEC; goto fail; @@ -786,16 +783,14 @@ int intel_uc_fw_fetch(struct intel_uc_fw *uc_fw) /* Preserve the version that was really wanted */ memcpy(&uc_fw->file_wanted, &file_ideal, sizeof(uc_fw->file_wanted)); - drm_notice(&i915->drm, - "%s firmware %s (%d.%d) is recommended, but only %s (%d.%d) was found\n", - intel_uc_fw_type_repr(uc_fw->type), - uc_fw->file_wanted.path, - uc_fw->file_wanted.ver.major, uc_fw->file_wanted.ver.minor, - uc_fw->file_selected.path, - uc_fw->file_selected.ver.major, uc_fw->file_selected.ver.minor); - drm_info(&i915->drm, - "Consider updating your linux-firmware pkg or downloading from %s\n", - INTEL_UC_FIRMWARE_URL); + gt_notice(gt, "%s firmware %s (%d.%d) is recommended, but only %s (%d.%d) was found\n", + intel_uc_fw_type_repr(uc_fw->type), + uc_fw->file_wanted.path, + uc_fw->file_wanted.ver.major, uc_fw->file_wanted.ver.minor, + uc_fw->file_selected.path, + uc_fw->file_selected.ver.major, uc_fw->file_selected.ver.minor); + gt_info(gt, "Consider updating your linux-firmware pkg or downloading from %s\n", + INTEL_UC_FIRMWARE_URL); } if (HAS_LMEM(i915)) { @@ -823,10 +818,10 @@ fail: INTEL_UC_FIRMWARE_MISSING : INTEL_UC_FIRMWARE_ERROR); - i915_probe_error(i915, "%s firmware %s: fetch failed with error %d\n", - intel_uc_fw_type_repr(uc_fw->type), uc_fw->file_selected.path, err); - drm_info(&i915->drm, "%s firmware(s) can be downloaded from %s\n", - intel_uc_fw_type_repr(uc_fw->type), INTEL_UC_FIRMWARE_URL); + gt_probe_error(gt, "%s firmware %s: fetch failed %pe\n", + intel_uc_fw_type_repr(uc_fw->type), uc_fw->file_selected.path, ERR_PTR(err)); + gt_info(gt, "%s firmware(s) can be downloaded from %s\n", + intel_uc_fw_type_repr(uc_fw->type), INTEL_UC_FIRMWARE_URL); release_firmware(fw); /* OK even if fw is NULL */ return err; @@ -932,9 +927,9 @@ static int uc_fw_xfer(struct intel_uc_fw *uc_fw, u32 dst_offset, u32 dma_flags) /* Wait for DMA to finish */ ret = intel_wait_for_register_fw(uncore, DMA_CTRL, START_DMA, 0, 100); if (ret) - drm_err(>->i915->drm, "DMA for %s fw failed, DMA_CTRL=%u\n", - intel_uc_fw_type_repr(uc_fw->type), - intel_uncore_read_fw(uncore, DMA_CTRL)); + gt_err(gt, "DMA for %s fw failed, DMA_CTRL=%u\n", + intel_uc_fw_type_repr(uc_fw->type), + intel_uncore_read_fw(uncore, DMA_CTRL)); /* Disable the bits once DMA is over */ intel_uncore_write_fw(uncore, DMA_CTRL, _MASKED_BIT_DISABLE(dma_flags)); @@ -950,9 +945,8 @@ int intel_uc_fw_mark_load_failed(struct intel_uc_fw *uc_fw, int err) GEM_BUG_ON(!intel_uc_fw_is_loadable(uc_fw)); - i915_probe_error(gt->i915, "Failed to load %s firmware %s (%d)\n", - intel_uc_fw_type_repr(uc_fw->type), uc_fw->file_selected.path, - err); + gt_probe_error(gt, "Failed to load %s firmware %s %pe\n", + intel_uc_fw_type_repr(uc_fw->type), uc_fw->file_selected.path, ERR_PTR(err)); intel_uc_fw_change_status(uc_fw, INTEL_UC_FIRMWARE_LOAD_FAIL); return err; @@ -1078,15 +1072,15 @@ int intel_uc_fw_init(struct intel_uc_fw *uc_fw) err = i915_gem_object_pin_pages_unlocked(uc_fw->obj); if (err) { - DRM_DEBUG_DRIVER("%s fw pin-pages err=%d\n", - intel_uc_fw_type_repr(uc_fw->type), err); + gt_dbg(__uc_fw_to_gt(uc_fw), "%s fw pin-pages failed %pe\n", + intel_uc_fw_type_repr(uc_fw->type), ERR_PTR(err)); goto out; } err = uc_fw_rsa_data_create(uc_fw); if (err) { - DRM_DEBUG_DRIVER("%s fw rsa data creation failed, err=%d\n", - intel_uc_fw_type_repr(uc_fw->type), err); + gt_dbg(__uc_fw_to_gt(uc_fw), "%s fw rsa data creation failed %pe\n", + intel_uc_fw_type_repr(uc_fw->type), ERR_PTR(err)); goto out_unpin; } diff --git a/drivers/gpu/drm/i915/gt/uc/selftest_guc.c b/drivers/gpu/drm/i915/gt/uc/selftest_guc.c index e28518fe8b90..1fd760539f77 100644 --- a/drivers/gpu/drm/i915/gt/uc/selftest_guc.c +++ b/drivers/gpu/drm/i915/gt/uc/selftest_guc.c @@ -3,6 +3,8 @@ * Copyright �� 2021 Intel Corporation */ +#include "gt/intel_gt_print.h" +#include "intel_guc_print.h" #include "selftests/igt_spinner.h" #include "selftests/intel_scheduler_helpers.h" @@ -65,7 +67,7 @@ static int intel_guc_scrub_ctbs(void *arg) ce = intel_context_create(engine); if (IS_ERR(ce)) { ret = PTR_ERR(ce); - drm_err(>->i915->drm, "Failed to create context, %d: %d\n", i, ret); + gt_err(gt, "Failed to create context %d: %pe\n", i, ce); goto err; } @@ -86,7 +88,7 @@ static int intel_guc_scrub_ctbs(void *arg) if (IS_ERR(rq)) { ret = PTR_ERR(rq); - drm_err(>->i915->drm, "Failed to create request, %d: %d\n", i, ret); + gt_err(gt, "Failed to create request %d: %pe\n", i, rq); goto err; } @@ -96,7 +98,7 @@ static int intel_guc_scrub_ctbs(void *arg) for (i = 0; i < 3; ++i) { ret = i915_request_wait(last[i], 0, HZ); if (ret < 0) { - drm_err(>->i915->drm, "Last request failed to complete: %d\n", ret); + gt_err(gt, "Last request failed to complete: %pe\n", ERR_PTR(ret)); goto err; } i915_request_put(last[i]); @@ -113,7 +115,7 @@ static int intel_guc_scrub_ctbs(void *arg) /* GT will not idle if G2H are lost */ ret = intel_gt_wait_for_idle(gt, HZ); if (ret < 0) { - drm_err(>->i915->drm, "GT failed to idle: %d\n", ret); + gt_err(gt, "GT failed to idle: %pe\n", ERR_PTR(ret)); goto err; } @@ -153,7 +155,7 @@ static int intel_guc_steal_guc_ids(void *arg) ce = kcalloc(GUC_MAX_CONTEXT_ID, sizeof(*ce), GFP_KERNEL); if (!ce) { - drm_err(>->i915->drm, "Context array allocation failed\n"); + guc_err(guc, "Context array allocation failed\n"); return -ENOMEM; } @@ -166,25 +168,25 @@ static int intel_guc_steal_guc_ids(void *arg) ce[context_index] = intel_context_create(engine); if (IS_ERR(ce[context_index])) { ret = PTR_ERR(ce[context_index]); + guc_err(guc, "Failed to create context: %pe\n", ce[context_index]); ce[context_index] = NULL; - drm_err(>->i915->drm, "Failed to create context: %d\n", ret); goto err_wakeref; } ret = igt_spinner_init(&spin, engine->gt); if (ret) { - drm_err(>->i915->drm, "Failed to create spinner: %d\n", ret); + guc_err(guc, "Failed to create spinner: %pe\n", ERR_PTR(ret)); goto err_contexts; } spin_rq = igt_spinner_create_request(&spin, ce[context_index], MI_ARB_CHECK); if (IS_ERR(spin_rq)) { ret = PTR_ERR(spin_rq); - drm_err(>->i915->drm, "Failed to create spinner request: %d\n", ret); + guc_err(guc, "Failed to create spinner request: %pe\n", spin_rq); goto err_contexts; } ret = request_add_spin(spin_rq, &spin); if (ret) { - drm_err(>->i915->drm, "Failed to add Spinner request: %d\n", ret); + guc_err(guc, "Failed to add Spinner request: %pe\n", ERR_PTR(ret)); goto err_spin_rq; } @@ -192,9 +194,9 @@ static int intel_guc_steal_guc_ids(void *arg) while (ret != -EAGAIN) { ce[++context_index] = intel_context_create(engine); if (IS_ERR(ce[context_index])) { - ret = PTR_ERR(ce[context_index--]); - ce[context_index] = NULL; - drm_err(>->i915->drm, "Failed to create context: %d\n", ret); + ret = PTR_ERR(ce[context_index]); + guc_err(guc, "Failed to create context: %pe\n", ce[context_index]); + ce[context_index--] = NULL; goto err_spin_rq; } @@ -203,8 +205,8 @@ static int intel_guc_steal_guc_ids(void *arg) ret = PTR_ERR(rq); rq = NULL; if (ret != -EAGAIN) { - drm_err(>->i915->drm, "Failed to create request, %d: %d\n", - context_index, ret); + guc_err(guc, "Failed to create request %d: %pe\n", + context_index, ERR_PTR(ret)); goto err_spin_rq; } } else { @@ -218,7 +220,7 @@ static int intel_guc_steal_guc_ids(void *arg) igt_spinner_end(&spin); ret = intel_selftest_wait_for_rq(spin_rq); if (ret) { - drm_err(>->i915->drm, "Spin request failed to complete: %d\n", ret); + guc_err(guc, "Spin request failed to complete: %pe\n", ERR_PTR(ret)); i915_request_put(last); goto err_spin_rq; } @@ -230,7 +232,7 @@ static int intel_guc_steal_guc_ids(void *arg) ret = i915_request_wait(last, 0, HZ * 30); i915_request_put(last); if (ret < 0) { - drm_err(>->i915->drm, "Last request failed to complete: %d\n", ret); + guc_err(guc, "Last request failed to complete: %pe\n", ERR_PTR(ret)); goto err_spin_rq; } @@ -238,7 +240,7 @@ static int intel_guc_steal_guc_ids(void *arg) rq = nop_user_request(ce[context_index], NULL); if (IS_ERR(rq)) { ret = PTR_ERR(rq); - drm_err(>->i915->drm, "Failed to steal guc_id, %d: %d\n", context_index, ret); + guc_err(guc, "Failed to steal guc_id %d: %pe\n", context_index, rq); goto err_spin_rq; } @@ -246,20 +248,20 @@ static int intel_guc_steal_guc_ids(void *arg) ret = i915_request_wait(rq, 0, HZ); i915_request_put(rq); if (ret < 0) { - drm_err(>->i915->drm, "Request with stolen guc_id failed to complete: %d\n", ret); + guc_err(guc, "Request with stolen guc_id failed to complete: %pe\n", ERR_PTR(ret)); goto err_spin_rq; } /* Wait for idle */ ret = intel_gt_wait_for_idle(gt, HZ * 30); if (ret < 0) { - drm_err(>->i915->drm, "GT failed to idle: %d\n", ret); + guc_err(guc, "GT failed to idle: %pe\n", ERR_PTR(ret)); goto err_spin_rq; } /* Verify a guc_id was stolen */ if (guc->number_guc_id_stolen == number_guc_id_stolen) { - drm_err(>->i915->drm, "No guc_id was stolen"); + guc_err(guc, "No guc_id was stolen"); ret = -EINVAL; } else { ret = 0; diff --git a/drivers/gpu/drm/i915/gt/uc/selftest_guc_hangcheck.c b/drivers/gpu/drm/i915/gt/uc/selftest_guc_hangcheck.c index d91b58f70403..34b5d952e2bc 100644 --- a/drivers/gpu/drm/i915/gt/uc/selftest_guc_hangcheck.c +++ b/drivers/gpu/drm/i915/gt/uc/selftest_guc_hangcheck.c @@ -3,6 +3,7 @@ * Copyright © 2022 Intel Corporation */ +#include "gt/intel_gt_print.h" #include "selftests/igt_spinner.h" #include "selftests/igt_reset.h" #include "selftests/intel_scheduler_helpers.h" @@ -45,7 +46,7 @@ static int intel_hang_guc(void *arg) ctx = kernel_context(gt->i915, NULL); if (IS_ERR(ctx)) { - drm_err(>->i915->drm, "Failed get kernel context: %ld\n", PTR_ERR(ctx)); + gt_err(gt, "Failed get kernel context: %pe\n", ctx); return PTR_ERR(ctx); } @@ -54,7 +55,7 @@ static int intel_hang_guc(void *arg) ce = intel_context_create(engine); if (IS_ERR(ce)) { ret = PTR_ERR(ce); - drm_err(>->i915->drm, "Failed to create spinner request: %d\n", ret); + gt_err(gt, "Failed to create spinner request: %pe\n", ce); goto err; } @@ -63,13 +64,13 @@ static int intel_hang_guc(void *arg) old_beat = engine->props.heartbeat_interval_ms; ret = intel_engine_set_heartbeat(engine, BEAT_INTERVAL); if (ret) { - drm_err(>->i915->drm, "Failed to boost heatbeat interval: %d\n", ret); + gt_err(gt, "Failed to boost heatbeat interval: %pe\n", ERR_PTR(ret)); goto err; } ret = igt_spinner_init(&spin, engine->gt); if (ret) { - drm_err(>->i915->drm, "Failed to create spinner: %d\n", ret); + gt_err(gt, "Failed to create spinner: %pe\n", ERR_PTR(ret)); goto err; } @@ -77,28 +78,28 @@ static int intel_hang_guc(void *arg) intel_context_put(ce); if (IS_ERR(rq)) { ret = PTR_ERR(rq); - drm_err(>->i915->drm, "Failed to create spinner request: %d\n", ret); + gt_err(gt, "Failed to create spinner request: %pe\n", rq); goto err_spin; } ret = request_add_spin(rq, &spin); if (ret) { i915_request_put(rq); - drm_err(>->i915->drm, "Failed to add Spinner request: %d\n", ret); + gt_err(gt, "Failed to add Spinner request: %pe\n", ERR_PTR(ret)); goto err_spin; } ret = intel_reset_guc(gt); if (ret) { i915_request_put(rq); - drm_err(>->i915->drm, "Failed to reset GuC, ret = %d\n", ret); + gt_err(gt, "Failed to reset GuC: %pe\n", ERR_PTR(ret)); goto err_spin; } guc_status = intel_uncore_read(gt->uncore, GUC_STATUS); if (!(guc_status & GS_MIA_IN_RESET)) { i915_request_put(rq); - drm_err(>->i915->drm, "GuC failed to reset: status = 0x%08X\n", guc_status); + gt_err(gt, "Failed to reset GuC: status = 0x%08X\n", guc_status); ret = -EIO; goto err_spin; } @@ -107,12 +108,12 @@ static int intel_hang_guc(void *arg) ret = intel_selftest_wait_for_rq(rq); i915_request_put(rq); if (ret) { - drm_err(>->i915->drm, "Request failed to complete: %d\n", ret); + gt_err(gt, "Request failed to complete: %pe\n", ERR_PTR(ret)); goto err_spin; } if (i915_reset_count(global) == reset_count) { - drm_err(>->i915->drm, "Failed to record a GPU reset\n"); + gt_err(gt, "Failed to record a GPU reset\n"); ret = -EINVAL; goto err_spin; } @@ -132,7 +133,7 @@ err_spin: ret = intel_selftest_wait_for_rq(rq); i915_request_put(rq); if (ret) { - drm_err(>->i915->drm, "No-op failed to complete: %d\n", ret); + gt_err(gt, "No-op failed to complete: %pe\n", ERR_PTR(ret)); goto err; } } diff --git a/drivers/gpu/drm/i915/gt/uc/selftest_guc_multi_lrc.c b/drivers/gpu/drm/i915/gt/uc/selftest_guc_multi_lrc.c index d17982c36d25..a40e7c32e613 100644 --- a/drivers/gpu/drm/i915/gt/uc/selftest_guc_multi_lrc.c +++ b/drivers/gpu/drm/i915/gt/uc/selftest_guc_multi_lrc.c @@ -3,6 +3,7 @@ * Copyright �� 2019 Intel Corporation */ +#include "gt/intel_gt_print.h" #include "selftests/igt_spinner.h" #include "selftests/igt_reset.h" #include "selftests/intel_scheduler_helpers.h" @@ -115,30 +116,30 @@ static int __intel_guc_multi_lrc_basic(struct intel_gt *gt, unsigned int class) parent = multi_lrc_create_parent(gt, class, 0); if (IS_ERR(parent)) { - drm_err(>->i915->drm, "Failed creating contexts: %ld", PTR_ERR(parent)); + gt_err(gt, "Failed creating contexts: %pe\n", parent); return PTR_ERR(parent); } else if (!parent) { - drm_dbg(>->i915->drm, "Not enough engines in class: %d", class); + gt_dbg(gt, "Not enough engines in class: %d\n", class); return 0; } rq = multi_lrc_nop_request(parent); if (IS_ERR(rq)) { ret = PTR_ERR(rq); - drm_err(>->i915->drm, "Failed creating requests: %d", ret); + gt_err(gt, "Failed creating requests: %pe\n", rq); goto out; } ret = intel_selftest_wait_for_rq(rq); if (ret) - drm_err(>->i915->drm, "Failed waiting on request: %d", ret); + gt_err(gt, "Failed waiting on request: %pe\n", ERR_PTR(ret)); i915_request_put(rq); if (ret >= 0) { ret = intel_gt_wait_for_idle(gt, HZ * 5); if (ret < 0) - drm_err(>->i915->drm, "GT failed to idle: %d\n", ret); + gt_err(gt, "GT failed to idle: %pe\n", ERR_PTR(ret)); } out: diff --git a/drivers/gpu/drm/i915/gvt/debugfs.c b/drivers/gpu/drm/i915/gvt/debugfs.c index 9f1c209d9251..baccbf1761b7 100644 --- a/drivers/gpu/drm/i915/gvt/debugfs.c +++ b/drivers/gpu/drm/i915/gvt/debugfs.c @@ -147,9 +147,25 @@ vgpu_scan_nonprivbb_set(void *data, u64 val) return 0; } -DEFINE_SIMPLE_ATTRIBUTE(vgpu_scan_nonprivbb_fops, - vgpu_scan_nonprivbb_get, vgpu_scan_nonprivbb_set, - "0x%llx\n"); +DEFINE_DEBUGFS_ATTRIBUTE(vgpu_scan_nonprivbb_fops, + vgpu_scan_nonprivbb_get, vgpu_scan_nonprivbb_set, + "0x%llx\n"); + +static int vgpu_status_get(void *data, u64 *val) +{ + struct intel_vgpu *vgpu = (struct intel_vgpu *)data; + + *val = 0; + + if (test_bit(INTEL_VGPU_STATUS_ATTACHED, vgpu->status)) + *val |= (1 << INTEL_VGPU_STATUS_ATTACHED); + if (test_bit(INTEL_VGPU_STATUS_ACTIVE, vgpu->status)) + *val |= (1 << INTEL_VGPU_STATUS_ACTIVE); + + return 0; +} + +DEFINE_DEBUGFS_ATTRIBUTE(vgpu_status_fops, vgpu_status_get, NULL, "0x%llx\n"); /** * intel_gvt_debugfs_add_vgpu - register debugfs entries for a vGPU @@ -162,11 +178,12 @@ void intel_gvt_debugfs_add_vgpu(struct intel_vgpu *vgpu) snprintf(name, 16, "vgpu%d", vgpu->id); vgpu->debugfs = debugfs_create_dir(name, vgpu->gvt->debugfs_root); - debugfs_create_bool("active", 0444, vgpu->debugfs, &vgpu->active); debugfs_create_file("mmio_diff", 0444, vgpu->debugfs, vgpu, &vgpu_mmio_diff_fops); - debugfs_create_file("scan_nonprivbb", 0644, vgpu->debugfs, vgpu, - &vgpu_scan_nonprivbb_fops); + debugfs_create_file_unsafe("scan_nonprivbb", 0644, vgpu->debugfs, vgpu, + &vgpu_scan_nonprivbb_fops); + debugfs_create_file_unsafe("status", 0644, vgpu->debugfs, vgpu, + &vgpu_status_fops); } /** @@ -175,8 +192,13 @@ void intel_gvt_debugfs_add_vgpu(struct intel_vgpu *vgpu) */ void intel_gvt_debugfs_remove_vgpu(struct intel_vgpu *vgpu) { - debugfs_remove_recursive(vgpu->debugfs); - vgpu->debugfs = NULL; + struct intel_gvt *gvt = vgpu->gvt; + struct drm_minor *minor = gvt->gt->i915->drm.primary; + + if (minor->debugfs_root && gvt->debugfs_root) { + debugfs_remove_recursive(vgpu->debugfs); + vgpu->debugfs = NULL; + } } /** @@ -199,6 +221,10 @@ void intel_gvt_debugfs_init(struct intel_gvt *gvt) */ void intel_gvt_debugfs_clean(struct intel_gvt *gvt) { - debugfs_remove_recursive(gvt->debugfs_root); - gvt->debugfs_root = NULL; + struct drm_minor *minor = gvt->gt->i915->drm.primary; + + if (minor->debugfs_root) { + debugfs_remove_recursive(gvt->debugfs_root); + gvt->debugfs_root = NULL; + } } diff --git a/drivers/gpu/drm/i915/gvt/dmabuf.c b/drivers/gpu/drm/i915/gvt/dmabuf.c index 7af09eb24ac0..6834f9fe40cf 100644 --- a/drivers/gpu/drm/i915/gvt/dmabuf.c +++ b/drivers/gpu/drm/i915/gvt/dmabuf.c @@ -136,7 +136,8 @@ static void dmabuf_gem_object_free(struct kref *kref) struct list_head *pos; struct intel_vgpu_dmabuf_obj *dmabuf_obj; - if (vgpu && vgpu->active && !list_empty(&vgpu->dmabuf_obj_list_head)) { + if (vgpu && test_bit(INTEL_VGPU_STATUS_ACTIVE, vgpu->status) && + !list_empty(&vgpu->dmabuf_obj_list_head)) { list_for_each(pos, &vgpu->dmabuf_obj_list_head) { dmabuf_obj = list_entry(pos, struct intel_vgpu_dmabuf_obj, list); if (dmabuf_obj == obj) { diff --git a/drivers/gpu/drm/i915/gvt/firmware.c b/drivers/gpu/drm/i915/gvt/firmware.c index a683c22d5b64..4dd52ac2043e 100644 --- a/drivers/gpu/drm/i915/gvt/firmware.c +++ b/drivers/gpu/drm/i915/gvt/firmware.c @@ -45,7 +45,7 @@ struct gvt_firmware_header { u64 cfg_space_offset; /* offset in the file */ u64 mmio_size; u64 mmio_offset; /* offset in the file */ - unsigned char data[1]; + unsigned char data[]; }; #define dev_to_drm_minor(d) dev_get_drvdata((d)) @@ -77,7 +77,7 @@ static int expose_firmware_sysfs(struct intel_gvt *gvt) unsigned long size, crc32_start; int ret; - size = sizeof(*h) + info->mmio_size + info->cfg_space_size; + size = offsetof(struct gvt_firmware_header, data) + info->mmio_size + info->cfg_space_size; firmware = vzalloc(size); if (!firmware) return -ENOMEM; @@ -171,7 +171,7 @@ static int verify_firmware(struct intel_gvt *gvt, mem = (fw->data + h->cfg_space_offset); id = *(u16 *)(mem + PCI_VENDOR_ID); - VERIFY("vender id", id, pdev->vendor); + VERIFY("vendor id", id, pdev->vendor); id = *(u16 *)(mem + PCI_DEVICE_ID); VERIFY("device id", id, pdev->device); diff --git a/drivers/gpu/drm/i915/gvt/gtt.c b/drivers/gpu/drm/i915/gvt/gtt.c index 51e5e8fb505b..4ec85308379a 100644 --- a/drivers/gpu/drm/i915/gvt/gtt.c +++ b/drivers/gpu/drm/i915/gvt/gtt.c @@ -55,7 +55,7 @@ static bool intel_gvt_is_valid_gfn(struct intel_vgpu *vgpu, unsigned long gfn) int idx; bool ret; - if (!vgpu->attached) + if (!test_bit(INTEL_VGPU_STATUS_ATTACHED, vgpu->status)) return false; idx = srcu_read_lock(&kvm->srcu); @@ -1178,7 +1178,7 @@ static int is_2MB_gtt_possible(struct intel_vgpu *vgpu, if (!HAS_PAGE_SIZES(vgpu->gvt->gt->i915, I915_GTT_PAGE_SIZE_2M)) return 0; - if (!vgpu->attached) + if (!test_bit(INTEL_VGPU_STATUS_ATTACHED, vgpu->status)) return -EINVAL; pfn = gfn_to_pfn(vgpu->vfio_device.kvm, ops->get_pfn(entry)); if (is_error_noslot_pfn(pfn)) @@ -1209,10 +1209,8 @@ static int split_2MB_gtt_entry(struct intel_vgpu *vgpu, for_each_shadow_entry(sub_spt, &sub_se, sub_index) { ret = intel_gvt_dma_map_guest_page(vgpu, start_gfn + sub_index, PAGE_SIZE, &dma_addr); - if (ret) { - ppgtt_invalidate_spt(spt); - return ret; - } + if (ret) + goto err; sub_se.val64 = se->val64; /* Copy the PAT field from PDE. */ @@ -1231,6 +1229,17 @@ static int split_2MB_gtt_entry(struct intel_vgpu *vgpu, ops->set_pfn(se, sub_spt->shadow_page.mfn); ppgtt_set_shadow_entry(spt, se, index); return 0; +err: + /* Cancel the existing addess mappings of DMA addr. */ + for_each_present_shadow_entry(sub_spt, &sub_se, sub_index) { + gvt_vdbg_mm("invalidate 4K entry\n"); + ppgtt_invalidate_pte(sub_spt, &sub_se); + } + /* Release the new allocated spt. */ + trace_spt_change(sub_spt->vgpu->id, "release", sub_spt, + sub_spt->guest_page.gfn, sub_spt->shadow_page.type); + ppgtt_free_spt(sub_spt); + return ret; } static int split_64KB_gtt_entry(struct intel_vgpu *vgpu, diff --git a/drivers/gpu/drm/i915/gvt/gvt.h b/drivers/gpu/drm/i915/gvt/gvt.h index 62823c0e13ab..2d65800d8e93 100644 --- a/drivers/gpu/drm/i915/gvt/gvt.h +++ b/drivers/gpu/drm/i915/gvt/gvt.h @@ -172,13 +172,18 @@ struct intel_vgpu_submission { #define KVMGT_DEBUGFS_FILENAME "kvmgt_nr_cache_entries" +enum { + INTEL_VGPU_STATUS_ATTACHED = 0, + INTEL_VGPU_STATUS_ACTIVE, + INTEL_VGPU_STATUS_NR_BITS, +}; + struct intel_vgpu { struct vfio_device vfio_device; struct intel_gvt *gvt; struct mutex vgpu_lock; int id; - bool active; - bool attached; + DECLARE_BITMAP(status, INTEL_VGPU_STATUS_NR_BITS); bool pv_notified; bool failsafe; unsigned int resetting_eng; @@ -467,7 +472,7 @@ void intel_vgpu_write_fence(struct intel_vgpu *vgpu, #define for_each_active_vgpu(gvt, vgpu, id) \ idr_for_each_entry((&(gvt)->vgpu_idr), (vgpu), (id)) \ - for_each_if(vgpu->active) + for_each_if(test_bit(INTEL_VGPU_STATUS_ACTIVE, vgpu->status)) static inline void intel_vgpu_write_pci_bar(struct intel_vgpu *vgpu, u32 offset, u32 val, bool low) @@ -725,7 +730,7 @@ static inline bool intel_gvt_mmio_is_cmd_write_patch( static inline int intel_gvt_read_gpa(struct intel_vgpu *vgpu, unsigned long gpa, void *buf, unsigned long len) { - if (!vgpu->attached) + if (!test_bit(INTEL_VGPU_STATUS_ATTACHED, vgpu->status)) return -ESRCH; return vfio_dma_rw(&vgpu->vfio_device, gpa, buf, len, false); } @@ -743,7 +748,7 @@ static inline int intel_gvt_read_gpa(struct intel_vgpu *vgpu, unsigned long gpa, static inline int intel_gvt_write_gpa(struct intel_vgpu *vgpu, unsigned long gpa, void *buf, unsigned long len) { - if (!vgpu->attached) + if (!test_bit(INTEL_VGPU_STATUS_ATTACHED, vgpu->status)) return -ESRCH; return vfio_dma_rw(&vgpu->vfio_device, gpa, buf, len, true); } diff --git a/drivers/gpu/drm/i915/gvt/interrupt.c b/drivers/gpu/drm/i915/gvt/interrupt.c index a6b2021b665f..68eca023bbc6 100644 --- a/drivers/gpu/drm/i915/gvt/interrupt.c +++ b/drivers/gpu/drm/i915/gvt/interrupt.c @@ -433,7 +433,7 @@ static int inject_virtual_interrupt(struct intel_vgpu *vgpu) * enabled by guest. so if msi_trigger is null, success is still * returned and don't inject interrupt into guest. */ - if (!vgpu->attached) + if (!test_bit(INTEL_VGPU_STATUS_ATTACHED, vgpu->status)) return -ESRCH; if (vgpu->msi_trigger && eventfd_signal(vgpu->msi_trigger, 1) != 1) return -EFAULT; diff --git a/drivers/gpu/drm/i915/gvt/kvmgt.c b/drivers/gpu/drm/i915/gvt/kvmgt.c index f5451adcd489..de675d799c7d 100644 --- a/drivers/gpu/drm/i915/gvt/kvmgt.c +++ b/drivers/gpu/drm/i915/gvt/kvmgt.c @@ -638,7 +638,7 @@ static bool __kvmgt_vgpu_exist(struct intel_vgpu *vgpu) mutex_lock(&vgpu->gvt->lock); for_each_active_vgpu(vgpu->gvt, itr, id) { - if (!itr->attached) + if (!test_bit(INTEL_VGPU_STATUS_ATTACHED, itr->status)) continue; if (vgpu->vfio_device.kvm == itr->vfio_device.kvm) { @@ -655,9 +655,6 @@ static int intel_vgpu_open_device(struct vfio_device *vfio_dev) { struct intel_vgpu *vgpu = vfio_dev_to_vgpu(vfio_dev); - if (vgpu->attached) - return -EEXIST; - if (!vgpu->vfio_device.kvm || vgpu->vfio_device.kvm->mm != current->mm) { gvt_vgpu_err("KVM is required to use Intel vGPU\n"); @@ -667,14 +664,14 @@ static int intel_vgpu_open_device(struct vfio_device *vfio_dev) if (__kvmgt_vgpu_exist(vgpu)) return -EEXIST; - vgpu->attached = true; - vgpu->track_node.track_write = kvmgt_page_track_write; vgpu->track_node.track_flush_slot = kvmgt_page_track_flush_slot; kvm_get_kvm(vgpu->vfio_device.kvm); kvm_page_track_register_notifier(vgpu->vfio_device.kvm, &vgpu->track_node); + set_bit(INTEL_VGPU_STATUS_ATTACHED, vgpu->status); + debugfs_create_ulong(KVMGT_DEBUGFS_FILENAME, 0444, vgpu->debugfs, &vgpu->nr_cache_entries); @@ -698,12 +695,11 @@ static void intel_vgpu_close_device(struct vfio_device *vfio_dev) { struct intel_vgpu *vgpu = vfio_dev_to_vgpu(vfio_dev); - if (!vgpu->attached) - return; - intel_gvt_release_vgpu(vgpu); - debugfs_remove(debugfs_lookup(KVMGT_DEBUGFS_FILENAME, vgpu->debugfs)); + clear_bit(INTEL_VGPU_STATUS_ATTACHED, vgpu->status); + + debugfs_lookup_and_remove(KVMGT_DEBUGFS_FILENAME, vgpu->debugfs); kvm_page_track_unregister_notifier(vgpu->vfio_device.kvm, &vgpu->track_node); @@ -718,8 +714,6 @@ static void intel_vgpu_close_device(struct vfio_device *vfio_dev) vgpu->dma_addr_cache = RB_ROOT; intel_vgpu_release_msi_eventfd_ctx(vgpu); - - vgpu->attached = false; } static u64 intel_vgpu_get_bar_addr(struct intel_vgpu *vgpu, int bar) @@ -1512,9 +1506,6 @@ static void intel_vgpu_remove(struct mdev_device *mdev) { struct intel_vgpu *vgpu = dev_get_drvdata(&mdev->dev); - if (WARN_ON_ONCE(vgpu->attached)) - return; - vfio_unregister_group_dev(&vgpu->vfio_device); vfio_put_device(&vgpu->vfio_device); } @@ -1559,7 +1550,7 @@ int intel_gvt_page_track_add(struct intel_vgpu *info, u64 gfn) struct kvm_memory_slot *slot; int idx; - if (!info->attached) + if (!test_bit(INTEL_VGPU_STATUS_ATTACHED, info->status)) return -ESRCH; idx = srcu_read_lock(&kvm->srcu); @@ -1589,8 +1580,8 @@ int intel_gvt_page_track_remove(struct intel_vgpu *info, u64 gfn) struct kvm_memory_slot *slot; int idx; - if (!info->attached) - return 0; + if (!test_bit(INTEL_VGPU_STATUS_ATTACHED, info->status)) + return -ESRCH; idx = srcu_read_lock(&kvm->srcu); slot = gfn_to_memslot(kvm, gfn); @@ -1668,7 +1659,7 @@ int intel_gvt_dma_map_guest_page(struct intel_vgpu *vgpu, unsigned long gfn, struct gvt_dma *entry; int ret; - if (!vgpu->attached) + if (!test_bit(INTEL_VGPU_STATUS_ATTACHED, vgpu->status)) return -EINVAL; mutex_lock(&vgpu->cache_lock); @@ -1714,8 +1705,8 @@ int intel_gvt_dma_pin_guest_page(struct intel_vgpu *vgpu, dma_addr_t dma_addr) struct gvt_dma *entry; int ret = 0; - if (!vgpu->attached) - return -ENODEV; + if (!test_bit(INTEL_VGPU_STATUS_ATTACHED, vgpu->status)) + return -EINVAL; mutex_lock(&vgpu->cache_lock); entry = __gvt_cache_find_dma_addr(vgpu, dma_addr); @@ -1742,7 +1733,7 @@ void intel_gvt_dma_unmap_guest_page(struct intel_vgpu *vgpu, { struct gvt_dma *entry; - if (!vgpu->attached) + if (!test_bit(INTEL_VGPU_STATUS_ATTACHED, vgpu->status)) return; mutex_lock(&vgpu->cache_lock); @@ -1778,7 +1769,7 @@ static void intel_gvt_test_and_emulate_vblank(struct intel_gvt *gvt) idr_for_each_entry((&(gvt)->vgpu_idr), (vgpu), (id)) { if (test_and_clear_bit(INTEL_GVT_REQUEST_EMULATE_VBLANK + id, (void *)&gvt->service_request)) { - if (vgpu->active) + if (test_bit(INTEL_VGPU_STATUS_ACTIVE, vgpu->status)) intel_vgpu_emulate_vblank(vgpu); } } diff --git a/drivers/gpu/drm/i915/gvt/scheduler.c b/drivers/gpu/drm/i915/gvt/scheduler.c index 9cd8fcbf7cad..f4055804aad1 100644 --- a/drivers/gpu/drm/i915/gvt/scheduler.c +++ b/drivers/gpu/drm/i915/gvt/scheduler.c @@ -695,6 +695,7 @@ intel_vgpu_shadow_mm_pin(struct intel_vgpu_workload *workload) if (workload->shadow_mm->type != INTEL_GVT_MM_PPGTT || !workload->shadow_mm->ppgtt_mm.shadowed) { + intel_vgpu_unpin_mm(workload->shadow_mm); gvt_vgpu_err("workload shadow ppgtt isn't ready\n"); return -EINVAL; } @@ -865,7 +866,8 @@ pick_next_workload(struct intel_gvt *gvt, struct intel_engine_cs *engine) goto out; } - if (!scheduler->current_vgpu->active || + if (!test_bit(INTEL_VGPU_STATUS_ACTIVE, + scheduler->current_vgpu->status) || list_empty(workload_q_head(scheduler->current_vgpu, engine))) goto out; diff --git a/drivers/gpu/drm/i915/gvt/vgpu.c b/drivers/gpu/drm/i915/gvt/vgpu.c index 3c529c2705dd..08ad1bd651f1 100644 --- a/drivers/gpu/drm/i915/gvt/vgpu.c +++ b/drivers/gpu/drm/i915/gvt/vgpu.c @@ -166,9 +166,7 @@ void intel_gvt_clean_vgpu_types(struct intel_gvt *gvt) */ void intel_gvt_activate_vgpu(struct intel_vgpu *vgpu) { - mutex_lock(&vgpu->vgpu_lock); - vgpu->active = true; - mutex_unlock(&vgpu->vgpu_lock); + set_bit(INTEL_VGPU_STATUS_ACTIVE, vgpu->status); } /** @@ -183,7 +181,7 @@ void intel_gvt_deactivate_vgpu(struct intel_vgpu *vgpu) { mutex_lock(&vgpu->vgpu_lock); - vgpu->active = false; + clear_bit(INTEL_VGPU_STATUS_ACTIVE, vgpu->status); if (atomic_read(&vgpu->submission.running_workload_num)) { mutex_unlock(&vgpu->vgpu_lock); @@ -228,7 +226,8 @@ void intel_gvt_destroy_vgpu(struct intel_vgpu *vgpu) struct intel_gvt *gvt = vgpu->gvt; struct drm_i915_private *i915 = gvt->gt->i915; - drm_WARN(&i915->drm, vgpu->active, "vGPU is still active!\n"); + drm_WARN(&i915->drm, test_bit(INTEL_VGPU_STATUS_ACTIVE, vgpu->status), + "vGPU is still active!\n"); /* * remove idr first so later clean can judge if need to stop @@ -285,8 +284,7 @@ struct intel_vgpu *intel_gvt_create_idle_vgpu(struct intel_gvt *gvt) if (ret) goto out_free_vgpu; - vgpu->active = false; - + clear_bit(INTEL_VGPU_STATUS_ACTIVE, vgpu->status); return vgpu; out_free_vgpu: @@ -325,7 +323,7 @@ int intel_gvt_create_vgpu(struct intel_vgpu *vgpu, ret = idr_alloc(&gvt->vgpu_idr, vgpu, IDLE_VGPU_IDR + 1, GVT_MAX_VGPU, GFP_KERNEL); if (ret < 0) - goto out_unlock;; + goto out_unlock; vgpu->id = ret; vgpu->sched_ctl.weight = conf->weight; diff --git a/drivers/gpu/drm/i915/i915_active.c b/drivers/gpu/drm/i915/i915_active.c index 7412abf166a8..8ef93889061a 100644 --- a/drivers/gpu/drm/i915/i915_active.c +++ b/drivers/gpu/drm/i915/i915_active.c @@ -92,8 +92,7 @@ static void debug_active_init(struct i915_active *ref) static void debug_active_activate(struct i915_active *ref) { lockdep_assert_held(&ref->tree_lock); - if (!atomic_read(&ref->count)) /* before the first inc */ - debug_object_activate(ref, &active_debug_desc); + debug_object_activate(ref, &active_debug_desc); } static void debug_active_deactivate(struct i915_active *ref) @@ -422,12 +421,12 @@ replace_barrier(struct i915_active *ref, struct i915_active_fence *active) * we can use it to substitute for the pending idle-barrer * request that we want to emit on the kernel_context. */ - __active_del_barrier(ref, node_from_active(active)); - return true; + return __active_del_barrier(ref, node_from_active(active)); } int i915_active_add_request(struct i915_active *ref, struct i915_request *rq) { + u64 idx = i915_request_timeline(rq)->fence_context; struct dma_fence *fence = &rq->fence; struct i915_active_fence *active; int err; @@ -437,16 +436,19 @@ int i915_active_add_request(struct i915_active *ref, struct i915_request *rq) if (err) return err; - active = active_instance(ref, i915_request_timeline(rq)->fence_context); - if (!active) { - err = -ENOMEM; - goto out; - } + do { + active = active_instance(ref, idx); + if (!active) { + err = -ENOMEM; + goto out; + } + + if (replace_barrier(ref, active)) { + RCU_INIT_POINTER(active->fence, NULL); + atomic_dec(&ref->count); + } + } while (unlikely(is_barrier(active))); - if (replace_barrier(ref, active)) { - RCU_INIT_POINTER(active->fence, NULL); - atomic_dec(&ref->count); - } if (!__i915_active_fence_set(active, fence)) __i915_active_acquire(ref); diff --git a/drivers/gpu/drm/i915/i915_driver.c b/drivers/gpu/drm/i915/i915_driver.c index 12b5296ee744..da249337c23b 100644 --- a/drivers/gpu/drm/i915/i915_driver.c +++ b/drivers/gpu/drm/i915/i915_driver.c @@ -483,13 +483,17 @@ static int i915_driver_hw_probe(struct drm_i915_private *dev_priv) if (ret) goto err_ggtt; - ret = intel_memory_regions_hw_probe(dev_priv); + /* + * Make sure we probe lmem before we probe stolen-lmem. The BAR size + * might be different due to bar resizing. + */ + ret = intel_gt_tiles_init(dev_priv); if (ret) goto err_ggtt; - ret = intel_gt_tiles_init(dev_priv); + ret = intel_memory_regions_hw_probe(dev_priv); if (ret) - goto err_mem_regions; + goto err_ggtt; ret = i915_ggtt_enable_hw(dev_priv); if (ret) { @@ -938,8 +942,7 @@ static void i915_driver_lastclose(struct drm_device *dev) intel_fbdev_restore_mode(i915); - if (HAS_DISPLAY(i915)) - vga_switcheroo_process_delayed_switch(); + vga_switcheroo_process_delayed_switch(); } static void i915_driver_postclose(struct drm_device *dev, struct drm_file *file) diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index 52122228222f..de6a3cd3f46e 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -685,6 +685,10 @@ IS_SUBPLATFORM(const struct drm_i915_private *i915, (IS_METEORLAKE(__i915) && \ IS_DISPLAY_STEP(__i915, since, until)) +#define IS_MTL_MEDIA_STEP(__i915, since, until) \ + (IS_METEORLAKE(__i915) && \ + IS_MEDIA_STEP(__i915, since, until)) + /* * DG2 hardware steppings are a bit unusual. The hardware design was forked to * create three variants (G10, G11, and G12) which each have distinct diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c index 9d5d5a397b64..f020c0086fbc 100644 --- a/drivers/gpu/drm/i915/i915_gpu_error.c +++ b/drivers/gpu/drm/i915/i915_gpu_error.c @@ -505,6 +505,7 @@ static void error_print_context(struct drm_i915_error_state_buf *m, header, ctx->comm, ctx->pid, ctx->sched_attr.priority, ctx->guilty, ctx->active, ctx->total_runtime, ctx->avg_runtime); + err_printf(m, " context timeline seqno %u\n", ctx->hwsp_seqno); } static struct i915_vma_coredump * @@ -1370,14 +1371,14 @@ static void engine_record_execlists(struct intel_engine_coredump *ee) } static bool record_context(struct i915_gem_context_coredump *e, - const struct i915_request *rq) + struct intel_context *ce) { struct i915_gem_context *ctx; struct task_struct *task; bool simulated; rcu_read_lock(); - ctx = rcu_dereference(rq->context->gem_context); + ctx = rcu_dereference(ce->gem_context); if (ctx && !kref_get_unless_zero(&ctx->ref)) ctx = NULL; rcu_read_unlock(); @@ -1395,9 +1396,11 @@ static bool record_context(struct i915_gem_context_coredump *e, e->sched_attr = ctx->sched; e->guilty = atomic_read(&ctx->guilty_count); e->active = atomic_read(&ctx->active_count); + e->hwsp_seqno = (ce->timeline && ce->timeline->hwsp_seqno) ? + *ce->timeline->hwsp_seqno : ~0U; - e->total_runtime = intel_context_get_total_runtime_ns(rq->context); - e->avg_runtime = intel_context_get_avg_runtime_ns(rq->context); + e->total_runtime = intel_context_get_total_runtime_ns(ce); + e->avg_runtime = intel_context_get_avg_runtime_ns(ce); simulated = i915_gem_context_no_error_capture(ctx); @@ -1532,15 +1535,37 @@ intel_engine_coredump_alloc(struct intel_engine_cs *engine, gfp_t gfp, u32 dump_ return ee; } +static struct intel_engine_capture_vma * +engine_coredump_add_context(struct intel_engine_coredump *ee, + struct intel_context *ce, + gfp_t gfp) +{ + struct intel_engine_capture_vma *vma = NULL; + + ee->simulated |= record_context(&ee->context, ce); + if (ee->simulated) + return NULL; + + /* + * We need to copy these to an anonymous buffer + * as the simplest method to avoid being overwritten + * by userspace. + */ + vma = capture_vma(vma, ce->ring->vma, "ring", gfp); + vma = capture_vma(vma, ce->state, "HW context", gfp); + + return vma; +} + struct intel_engine_capture_vma * intel_engine_coredump_add_request(struct intel_engine_coredump *ee, struct i915_request *rq, gfp_t gfp) { - struct intel_engine_capture_vma *vma = NULL; + struct intel_engine_capture_vma *vma; - ee->simulated |= record_context(&ee->context, rq); - if (ee->simulated) + vma = engine_coredump_add_context(ee, rq->context, gfp); + if (!vma) return NULL; /* @@ -1550,8 +1575,6 @@ intel_engine_coredump_add_request(struct intel_engine_coredump *ee, */ 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); ee->rq_head = rq->head; ee->rq_post = rq->postfix; @@ -1596,54 +1619,36 @@ capture_engine(struct intel_engine_cs *engine, { struct intel_engine_capture_vma *capture = NULL; struct intel_engine_coredump *ee; - struct intel_context *ce; + struct intel_context *ce = NULL; struct i915_request *rq = NULL; - unsigned long flags; ee = intel_engine_coredump_alloc(engine, ALLOW_FAIL, dump_flags); if (!ee) return NULL; - ce = intel_engine_get_hung_context(engine); - if (ce) { - intel_engine_clear_hung_context(engine); - rq = intel_context_find_active_request(ce); - if (!rq || !i915_request_started(rq)) - goto no_request_capture; - } else { - /* - * Getting here with GuC enabled means it is a forced error capture - * with no actual hang. So, no need to attempt the execlist search. - */ - if (!intel_uc_uses_guc_submission(&engine->gt->uc)) { - spin_lock_irqsave(&engine->sched_engine->lock, flags); - rq = intel_engine_execlist_find_hung_request(engine); - spin_unlock_irqrestore(&engine->sched_engine->lock, - flags); - } - } - if (rq) - rq = i915_request_get_rcu(rq); + intel_engine_get_hung_entity(engine, &ce, &rq); + if (rq && !i915_request_started(rq)) + drm_info(&engine->gt->i915->drm, "Got hung context on %s with active request %lld:%lld [0x%04X] not yet started\n", + engine->name, rq->fence.context, rq->fence.seqno, ce->guc_id.id); - if (!rq) - goto no_request_capture; - - capture = intel_engine_coredump_add_request(ee, rq, ATOMIC_MAYFAIL); - if (!capture) { + if (rq) { + capture = intel_engine_coredump_add_request(ee, rq, ATOMIC_MAYFAIL); i915_request_put(rq); - goto no_request_capture; + } else if (ce) { + capture = engine_coredump_add_context(ee, ce, ATOMIC_MAYFAIL); } - if (dump_flags & CORE_DUMP_FLAG_IS_GUC_CAPTURE) - intel_guc_capture_get_matching_node(engine->gt, ee, ce); - intel_engine_coredump_add_vma(ee, capture, compress); - i915_request_put(rq); + if (capture) { + intel_engine_coredump_add_vma(ee, capture, compress); - return ee; + if (dump_flags & CORE_DUMP_FLAG_IS_GUC_CAPTURE) + intel_guc_capture_get_matching_node(engine->gt, ee, ce); + } else { + kfree(ee); + ee = NULL; + } -no_request_capture: - kfree(ee); - return NULL; + return ee; } static void diff --git a/drivers/gpu/drm/i915/i915_gpu_error.h b/drivers/gpu/drm/i915/i915_gpu_error.h index efc75cc2ffdb..a91932cc6531 100644 --- a/drivers/gpu/drm/i915/i915_gpu_error.h +++ b/drivers/gpu/drm/i915/i915_gpu_error.h @@ -94,7 +94,7 @@ struct intel_engine_coredump { struct intel_instdone instdone; /* GuC matched capture-lists info */ - struct intel_guc_state_capture *capture; + struct intel_guc_state_capture *guc_capture; struct __guc_capture_parsed_output *guc_capture_node; struct i915_gem_context_coredump { @@ -107,6 +107,7 @@ struct intel_engine_coredump { int active; int guilty; struct i915_sched_attr sched_attr; + u32 hwsp_seqno; } context; struct i915_vma_coredump *vma; diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index 431505314927..f80c36233a77 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -6487,15 +6487,6 @@ /* XEHP_PCODE_FREQUENCY_CONFIG param2 */ #define PCODE_MBOX_DOMAIN_NONE 0x0 #define PCODE_MBOX_DOMAIN_MEDIAFF 0x3 - -/* Wa_14017210380: mtl */ -#define PCODE_MBOX_GT_STATE 0x50 -/* sub-commands (param1) */ -#define PCODE_MBOX_GT_STATE_MEDIA_BUSY 0x1 -#define PCODE_MBOX_GT_STATE_MEDIA_NOT_BUSY 0x2 -/* param2 */ -#define PCODE_MBOX_GT_STATE_DOMAIN_MEDIA 0x1 - #define GEN6_PCODE_DATA _MMIO(0x138128) #define GEN6_PCODE_FREQ_IA_RATIO_SHIFT 8 #define GEN6_PCODE_FREQ_RING_RATIO_SHIFT 16 @@ -7726,10 +7717,6 @@ enum skl_power_gate { #define CLKGATE_DIS_MISC _MMIO(0x46534) #define CLKGATE_DIS_MISC_DMASC_GATING_DIS REG_BIT(21) -#define GEN12_CULLBIT1 _MMIO(0x6100) -#define GEN12_CULLBIT2 _MMIO(0x7030) -#define GEN12_STATE_ACK_DEBUG _MMIO(0x20BC) - #define _MTL_CLKGATE_DIS_TRANS_A 0x604E8 #define _MTL_CLKGATE_DIS_TRANS_B 0x614E8 #define MTL_CLKGATE_DIS_TRANS(trans) _MMIO_TRANS2(trans, _MTL_CLKGATE_DIS_TRANS_A) diff --git a/drivers/gpu/drm/i915/i915_switcheroo.c b/drivers/gpu/drm/i915/i915_switcheroo.c index 23777d500cdf..f45bd6b6cede 100644 --- a/drivers/gpu/drm/i915/i915_switcheroo.c +++ b/drivers/gpu/drm/i915/i915_switcheroo.c @@ -19,6 +19,10 @@ static void i915_switcheroo_set_state(struct pci_dev *pdev, dev_err(&pdev->dev, "DRM not initialized, aborting switch.\n"); return; } + if (!HAS_DISPLAY(i915)) { + dev_err(&pdev->dev, "Device state not initialized, aborting switch.\n"); + return; + } if (state == VGA_SWITCHEROO_ON) { drm_info(&i915->drm, "switched on\n"); @@ -44,7 +48,7 @@ static bool i915_switcheroo_can_switch(struct pci_dev *pdev) * locking inversion with the driver load path. And the access here is * completely racy anyway. So don't bother with locking for now. */ - return i915 && atomic_read(&i915->drm.open_count) == 0; + return i915 && HAS_DISPLAY(i915) && atomic_read(&i915->drm.open_count) == 0; } static const struct vga_switcheroo_client_ops i915_switcheroo_ops = { diff --git a/drivers/gpu/drm/i915/i915_ttm_buddy_manager.c b/drivers/gpu/drm/i915/i915_ttm_buddy_manager.c index a72698a2dbc8..a1bc804cfa15 100644 --- a/drivers/gpu/drm/i915/i915_ttm_buddy_manager.c +++ b/drivers/gpu/drm/i915/i915_ttm_buddy_manager.c @@ -139,13 +139,6 @@ static int i915_ttm_buddy_man_alloc(struct ttm_resource_manager *man, mutex_unlock(&bman->lock); - if (place->lpfn - place->fpfn == n_pages) - bman_res->base.start = place->fpfn; - else if (lpfn <= bman->visible_size) - bman_res->base.start = 0; - else - bman_res->base.start = bman->visible_size; - *res = &bman_res->base; return 0; diff --git a/drivers/gpu/drm/i915/intel_pcode.c b/drivers/gpu/drm/i915/intel_pcode.c index a234d9b4ed14..3db2ba439bb5 100644 --- a/drivers/gpu/drm/i915/intel_pcode.c +++ b/drivers/gpu/drm/i915/intel_pcode.c @@ -204,15 +204,42 @@ out: #undef COND } +static int pcode_init_wait(struct intel_uncore *uncore, int timeout_ms) +{ + if (__intel_wait_for_register_fw(uncore, + GEN6_PCODE_MAILBOX, + GEN6_PCODE_READY, 0, + 500, timeout_ms, + NULL)) + return -EPROBE_DEFER; + + return skl_pcode_request(uncore, + DG1_PCODE_STATUS, + DG1_UNCORE_GET_INIT_STATUS, + DG1_UNCORE_INIT_STATUS_COMPLETE, + DG1_UNCORE_INIT_STATUS_COMPLETE, timeout_ms); +} + int intel_pcode_init(struct intel_uncore *uncore) { + int err; + if (!IS_DGFX(uncore->i915)) return 0; - return skl_pcode_request(uncore, DG1_PCODE_STATUS, - DG1_UNCORE_GET_INIT_STATUS, - DG1_UNCORE_INIT_STATUS_COMPLETE, - DG1_UNCORE_INIT_STATUS_COMPLETE, 180000); + /* + * Wait 10 seconds so that the punit to settle and complete + * any outstanding transactions upon module load + */ + err = pcode_init_wait(uncore, 10000); + + if (err) { + drm_notice(&uncore->i915->drm, + "Waiting for HW initialisation...\n"); + err = pcode_init_wait(uncore, 180000); + } + + return err; } int snb_pcode_read_p(struct intel_uncore *uncore, u32 mbcmd, u32 p1, u32 p2, u32 *val) diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c index b11b82e384b1..c45af0d981fd 100644 --- a/drivers/gpu/drm/i915/intel_pm.c +++ b/drivers/gpu/drm/i915/intel_pm.c @@ -328,8 +328,8 @@ static void gen8_set_l3sqc_credits(struct drm_i915_private *dev_priv, u32 val; /* WaTempDisableDOPClkGating:bdw */ - misccpctl = intel_gt_mcr_multicast_rmw(to_gt(dev_priv), GEN8_MISCCPCTL, - GEN8_DOP_CLOCK_GATE_ENABLE, 0); + misccpctl = intel_uncore_rmw(&dev_priv->uncore, GEN7_MISCCPCTL, + GEN7_DOP_CLOCK_GATE_ENABLE, 0); val = intel_gt_mcr_read_any(to_gt(dev_priv), GEN8_L3SQCREG1); val &= ~L3_PRIO_CREDITS_MASK; @@ -343,7 +343,7 @@ static void gen8_set_l3sqc_credits(struct drm_i915_private *dev_priv, */ intel_gt_mcr_read_any(to_gt(dev_priv), GEN8_L3SQCREG1); udelay(1); - intel_gt_mcr_multicast_write(to_gt(dev_priv), GEN8_MISCCPCTL, misccpctl); + intel_uncore_write(&dev_priv->uncore, GEN7_MISCCPCTL, misccpctl); } static void icl_init_clock_gating(struct drm_i915_private *dev_priv) @@ -481,8 +481,8 @@ static void skl_init_clock_gating(struct drm_i915_private *dev_priv) gen9_init_clock_gating(dev_priv); /* WaDisableDopClockGating:skl */ - intel_gt_mcr_multicast_rmw(to_gt(dev_priv), GEN8_MISCCPCTL, - GEN8_DOP_CLOCK_GATE_ENABLE, 0); + intel_uncore_rmw(&dev_priv->uncore, GEN7_MISCCPCTL, + GEN7_DOP_CLOCK_GATE_ENABLE, 0); /* WAC6entrylatency:skl */ intel_uncore_rmw(&dev_priv->uncore, FBC_LLC_READ_CTRL, 0, FBC_LLC_FULLY_OPEN); diff --git a/drivers/gpu/drm/i915/intel_uncore.c b/drivers/gpu/drm/i915/intel_uncore.c index f4b3b2063018..e1e1f34490c8 100644 --- a/drivers/gpu/drm/i915/intel_uncore.c +++ b/drivers/gpu/drm/i915/intel_uncore.c @@ -2748,14 +2748,25 @@ static void driver_initiated_flr(struct intel_uncore *uncore) /* Trigger the actual Driver-FLR */ intel_uncore_rmw_fw(uncore, GU_CNTL, 0, DRIVERFLR); + /* Wait for hardware teardown to complete */ + ret = intel_wait_for_register_fw(uncore, GU_CNTL, + DRIVERFLR, 0, + flr_timeout_ms); + if (ret) { + drm_err(&i915->drm, "Driver-FLR-teardown wait completion failed! %d\n", ret); + return; + } + + /* Wait for hardware/firmware re-init to complete */ ret = intel_wait_for_register_fw(uncore, GU_DEBUG, DRIVERFLR_STATUS, DRIVERFLR_STATUS, flr_timeout_ms); if (ret) { - drm_err(&i915->drm, "wait for Driver-FLR completion failed! %d\n", ret); + drm_err(&i915->drm, "Driver-FLR-reinit wait completion failed! %d\n", ret); return; } + /* Clear sticky completion status */ intel_uncore_write_fw(uncore, GU_DEBUG, DRIVERFLR_STATUS); } diff --git a/drivers/gpu/drm/i915/pxp/intel_pxp_huc.c b/drivers/gpu/drm/i915/pxp/intel_pxp_huc.c index 64609d1b1c0f..23431c36b60b 100644 --- a/drivers/gpu/drm/i915/pxp/intel_pxp_huc.c +++ b/drivers/gpu/drm/i915/pxp/intel_pxp_huc.c @@ -38,7 +38,7 @@ int intel_pxp_huc_load_and_auth(struct intel_pxp *pxp) huc_in.header.command_id = PXP43_CMDID_START_HUC_AUTH; huc_in.header.status = 0; huc_in.header.buffer_len = sizeof(huc_in.huc_base_address); - huc_in.huc_base_address = huc_phys_addr; + huc_in.huc_base_address = cpu_to_le64(huc_phys_addr); err = intel_pxp_tee_stream_message(pxp, client_id, fence_id, &huc_in, sizeof(huc_in), diff --git a/drivers/gpu/drm/i915/selftests/i915_live_selftests.h b/drivers/gpu/drm/i915/selftests/i915_live_selftests.h index aaf8a380e5c7..5aee6c9a8295 100644 --- a/drivers/gpu/drm/i915/selftests/i915_live_selftests.h +++ b/drivers/gpu/drm/i915/selftests/i915_live_selftests.h @@ -25,6 +25,7 @@ selftest(gt_lrc, intel_lrc_live_selftests) selftest(gt_mocs, intel_mocs_live_selftests) selftest(gt_pm, intel_gt_pm_live_selftests) selftest(gt_heartbeat, intel_heartbeat_live_selftests) +selftest(gt_tlb, intel_tlb_live_selftests) selftest(requests, i915_request_live_selftests) selftest(migrate, intel_migrate_live_selftests) selftest(active, i915_active_live_selftests) diff --git a/drivers/gpu/drm/i915/selftests/i915_request.c b/drivers/gpu/drm/i915/selftests/i915_request.c index 6fe22b096bdd..a9b79888c193 100644 --- a/drivers/gpu/drm/i915/selftests/i915_request.c +++ b/drivers/gpu/drm/i915/selftests/i915_request.c @@ -957,18 +957,18 @@ static int live_cancel_request(void *arg) return 0; } -static struct i915_vma *empty_batch(struct drm_i915_private *i915) +static struct i915_vma *empty_batch(struct intel_gt *gt) { struct drm_i915_gem_object *obj; struct i915_vma *vma; u32 *cmd; int err; - obj = i915_gem_object_create_internal(i915, PAGE_SIZE); + obj = i915_gem_object_create_internal(gt->i915, PAGE_SIZE); if (IS_ERR(obj)) return ERR_CAST(obj); - cmd = i915_gem_object_pin_map_unlocked(obj, I915_MAP_WB); + cmd = i915_gem_object_pin_map_unlocked(obj, I915_MAP_WC); if (IS_ERR(cmd)) { err = PTR_ERR(cmd); goto err; @@ -979,15 +979,15 @@ static struct i915_vma *empty_batch(struct drm_i915_private *i915) __i915_gem_object_flush_map(obj, 0, 64); i915_gem_object_unpin_map(obj); - intel_gt_chipset_flush(to_gt(i915)); + intel_gt_chipset_flush(gt); - vma = i915_vma_instance(obj, &to_gt(i915)->ggtt->vm, NULL); + vma = i915_vma_instance(obj, gt->vm, NULL); if (IS_ERR(vma)) { err = PTR_ERR(vma); goto err; } - err = i915_vma_pin(vma, 0, 0, PIN_USER | PIN_GLOBAL); + err = i915_vma_pin(vma, 0, 0, PIN_USER); if (err) goto err; @@ -1005,6 +1005,14 @@ err: return ERR_PTR(err); } +static int emit_bb_start(struct i915_request *rq, struct i915_vma *batch) +{ + return rq->engine->emit_bb_start(rq, + i915_vma_offset(batch), + i915_vma_size(batch), + 0); +} + static struct i915_request * empty_request(struct intel_engine_cs *engine, struct i915_vma *batch) @@ -1016,10 +1024,7 @@ empty_request(struct intel_engine_cs *engine, if (IS_ERR(request)) return request; - err = engine->emit_bb_start(request, - i915_vma_offset(batch), - i915_vma_size(batch), - I915_DISPATCH_SECURE); + err = emit_bb_start(request, batch); if (err) goto out_request; @@ -1034,8 +1039,7 @@ static int live_empty_request(void *arg) struct drm_i915_private *i915 = arg; struct intel_engine_cs *engine; struct igt_live_test t; - struct i915_vma *batch; - int err = 0; + int err; /* * Submit various sized batches of empty requests, to each engine @@ -1043,16 +1047,17 @@ static int live_empty_request(void *arg) * the overhead of submitting requests to the hardware. */ - batch = empty_batch(i915); - if (IS_ERR(batch)) - return PTR_ERR(batch); - for_each_uabi_engine(engine, i915) { IGT_TIMEOUT(end_time); struct i915_request *request; + struct i915_vma *batch; unsigned long n, prime; ktime_t times[2] = {}; + batch = empty_batch(engine->gt); + if (IS_ERR(batch)) + return PTR_ERR(batch); + err = igt_live_test_begin(&t, i915, __func__, engine->name); if (err) goto out_batch; @@ -1100,27 +1105,29 @@ static int live_empty_request(void *arg) engine->name, ktime_to_ns(times[0]), prime, div64_u64(ktime_to_ns(times[1]), prime)); +out_batch: + i915_vma_unpin(batch); + i915_vma_put(batch); + if (err) + break; } -out_batch: - i915_vma_unpin(batch); - i915_vma_put(batch); return err; } -static struct i915_vma *recursive_batch(struct drm_i915_private *i915) +static struct i915_vma *recursive_batch(struct intel_gt *gt) { struct drm_i915_gem_object *obj; - const int ver = GRAPHICS_VER(i915); + const int ver = GRAPHICS_VER(gt->i915); struct i915_vma *vma; u32 *cmd; int err; - obj = i915_gem_object_create_internal(i915, PAGE_SIZE); + obj = i915_gem_object_create_internal(gt->i915, PAGE_SIZE); if (IS_ERR(obj)) return ERR_CAST(obj); - vma = i915_vma_instance(obj, to_gt(i915)->vm, NULL); + vma = i915_vma_instance(obj, gt->vm, NULL); if (IS_ERR(vma)) { err = PTR_ERR(vma); goto err; @@ -1152,7 +1159,7 @@ static struct i915_vma *recursive_batch(struct drm_i915_private *i915) __i915_gem_object_flush_map(obj, 0, 64); i915_gem_object_unpin_map(obj); - intel_gt_chipset_flush(to_gt(i915)); + intel_gt_chipset_flush(gt); return vma; @@ -1186,7 +1193,6 @@ static int live_all_engines(void *arg) struct intel_engine_cs *engine; struct i915_request **request; struct igt_live_test t; - struct i915_vma *batch; unsigned int idx; int err; @@ -1204,42 +1210,44 @@ static int live_all_engines(void *arg) if (err) goto out_free; - batch = recursive_batch(i915); - if (IS_ERR(batch)) { - err = PTR_ERR(batch); - pr_err("%s: Unable to create batch, err=%d\n", __func__, err); - goto out_free; - } - - i915_vma_lock(batch); - idx = 0; for_each_uabi_engine(engine, i915) { + struct i915_vma *batch; + + batch = recursive_batch(engine->gt); + if (IS_ERR(batch)) { + err = PTR_ERR(batch); + pr_err("%s: Unable to create batch, err=%d\n", + __func__, err); + goto out_free; + } + + i915_vma_lock(batch); request[idx] = intel_engine_create_kernel_request(engine); if (IS_ERR(request[idx])) { err = PTR_ERR(request[idx]); pr_err("%s: Request allocation failed with err=%d\n", __func__, err); - goto out_request; + goto out_unlock; } + GEM_BUG_ON(request[idx]->context->vm != batch->vm); err = i915_vma_move_to_active(batch, request[idx], 0); GEM_BUG_ON(err); - err = engine->emit_bb_start(request[idx], - i915_vma_offset(batch), - i915_vma_size(batch), - 0); + err = emit_bb_start(request[idx], batch); GEM_BUG_ON(err); request[idx]->batch = batch; i915_request_get(request[idx]); i915_request_add(request[idx]); idx++; +out_unlock: + i915_vma_unlock(batch); + if (err) + goto out_request; } - i915_vma_unlock(batch); - idx = 0; for_each_uabi_engine(engine, i915) { if (i915_request_completed(request[idx])) { @@ -1251,17 +1259,23 @@ static int live_all_engines(void *arg) idx++; } - err = recursive_batch_resolve(batch); - if (err) { - pr_err("%s: failed to resolve batch, err=%d\n", __func__, err); - goto out_request; + idx = 0; + for_each_uabi_engine(engine, i915) { + err = recursive_batch_resolve(request[idx]->batch); + if (err) { + pr_err("%s: failed to resolve batch, err=%d\n", + __func__, err); + goto out_request; + } + idx++; } idx = 0; for_each_uabi_engine(engine, i915) { + struct i915_request *rq = request[idx]; long timeout; - timeout = i915_request_wait(request[idx], 0, + timeout = i915_request_wait(rq, 0, MAX_SCHEDULE_TIMEOUT); if (timeout < 0) { err = timeout; @@ -1270,8 +1284,10 @@ static int live_all_engines(void *arg) goto out_request; } - GEM_BUG_ON(!i915_request_completed(request[idx])); - i915_request_put(request[idx]); + GEM_BUG_ON(!i915_request_completed(rq)); + i915_vma_unpin(rq->batch); + i915_vma_put(rq->batch); + i915_request_put(rq); request[idx] = NULL; idx++; } @@ -1281,12 +1297,18 @@ static int live_all_engines(void *arg) out_request: idx = 0; for_each_uabi_engine(engine, i915) { - if (request[idx]) - i915_request_put(request[idx]); + struct i915_request *rq = request[idx]; + + if (!rq) + continue; + + if (rq->batch) { + i915_vma_unpin(rq->batch); + i915_vma_put(rq->batch); + } + i915_request_put(rq); idx++; } - i915_vma_unpin(batch); - i915_vma_put(batch); out_free: kfree(request); return err; @@ -1322,7 +1344,7 @@ static int live_sequential_engines(void *arg) for_each_uabi_engine(engine, i915) { struct i915_vma *batch; - batch = recursive_batch(i915); + batch = recursive_batch(engine->gt); if (IS_ERR(batch)) { err = PTR_ERR(batch); pr_err("%s: Unable to create batch for %s, err=%d\n", @@ -1338,6 +1360,7 @@ static int live_sequential_engines(void *arg) __func__, engine->name, err); goto out_unlock; } + GEM_BUG_ON(request[idx]->context->vm != batch->vm); if (prev) { err = i915_request_await_dma_fence(request[idx], @@ -1353,10 +1376,7 @@ static int live_sequential_engines(void *arg) err = i915_vma_move_to_active(batch, request[idx], 0); GEM_BUG_ON(err); - err = engine->emit_bb_start(request[idx], - i915_vma_offset(batch), - i915_vma_size(batch), - 0); + err = emit_bb_start(request[idx], batch); GEM_BUG_ON(err); request[idx]->batch = batch; diff --git a/drivers/gpu/drm/i915/selftests/igt_flush_test.c b/drivers/gpu/drm/i915/selftests/igt_flush_test.c index b484e12df417..29110abb4fe0 100644 --- a/drivers/gpu/drm/i915/selftests/igt_flush_test.c +++ b/drivers/gpu/drm/i915/selftests/igt_flush_test.c @@ -14,21 +14,27 @@ int igt_flush_test(struct drm_i915_private *i915) { - struct intel_gt *gt = to_gt(i915); - int ret = intel_gt_is_wedged(gt) ? -EIO : 0; + struct intel_gt *gt; + unsigned int i; + int ret = 0; - cond_resched(); + for_each_gt(gt, i915, i) { + if (intel_gt_is_wedged(gt)) + ret = -EIO; - if (intel_gt_wait_for_idle(gt, HZ * 3) == -ETIME) { - pr_err("%pS timed out, cancelling all further testing.\n", - __builtin_return_address(0)); + cond_resched(); - GEM_TRACE("%pS timed out.\n", - __builtin_return_address(0)); - GEM_TRACE_DUMP(); + if (intel_gt_wait_for_idle(gt, HZ * 3) == -ETIME) { + pr_err("%pS timed out, cancelling all further testing.\n", + __builtin_return_address(0)); - intel_gt_set_wedged(gt); - ret = -EIO; + GEM_TRACE("%pS timed out.\n", + __builtin_return_address(0)); + GEM_TRACE_DUMP(); + + intel_gt_set_wedged(gt); + ret = -EIO; + } } return ret; diff --git a/drivers/gpu/drm/i915/selftests/intel_scheduler_helpers.c b/drivers/gpu/drm/i915/selftests/intel_scheduler_helpers.c index 310fb83c527e..2990dd4d4a0d 100644 --- a/drivers/gpu/drm/i915/selftests/intel_scheduler_helpers.c +++ b/drivers/gpu/drm/i915/selftests/intel_scheduler_helpers.c @@ -28,8 +28,7 @@ struct intel_engine_cs *intel_selftest_find_any_engine(struct intel_gt *gt) int intel_selftest_modify_policy(struct intel_engine_cs *engine, struct intel_selftest_saved_policy *saved, - u32 modify_type) - + enum selftest_scheduler_modify modify_type) { int err; |