diff options
Diffstat (limited to 'drivers/gpu/drm/i915/i915_gem.c')
| -rw-r--r-- | drivers/gpu/drm/i915/i915_gem.c | 122 |
1 files changed, 88 insertions, 34 deletions
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index fcc73a6ab503..0c8aa57ce83b 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -802,6 +802,11 @@ void i915_gem_flush_ggtt_writes(struct drm_i915_private *dev_priv) * that was!). */ + wmb(); + + if (INTEL_INFO(dev_priv)->has_coherent_ggtt) + return; + i915_gem_chipset_flush(dev_priv); intel_runtime_pm_get(dev_priv); @@ -1122,11 +1127,7 @@ i915_gem_shmem_pread(struct drm_i915_gem_object *obj, offset = offset_in_page(args->offset); for (idx = args->offset >> PAGE_SHIFT; remain; idx++) { struct page *page = i915_gem_object_get_page(obj, idx); - int length; - - length = remain; - if (offset + length > PAGE_SIZE) - length = PAGE_SIZE - offset; + unsigned int length = min_t(u64, remain, PAGE_SIZE - offset); ret = shmem_pread(page, offset, length, user_data, page_to_phys(page) & obj_do_bit17_swizzling, @@ -1570,11 +1571,7 @@ i915_gem_shmem_pwrite(struct drm_i915_gem_object *obj, offset = offset_in_page(args->offset); for (idx = args->offset >> PAGE_SHIFT; remain; idx++) { struct page *page = i915_gem_object_get_page(obj, idx); - int length; - - length = remain; - if (offset + length > PAGE_SIZE) - length = PAGE_SIZE - offset; + unsigned int length = min_t(u64, remain, PAGE_SIZE - offset); ret = shmem_pwrite(page, offset, length, user_data, page_to_phys(page) & obj_do_bit17_swizzling, @@ -1906,7 +1903,7 @@ i915_gem_mmap_ioctl(struct drm_device *dev, void *data, return 0; } -static unsigned int tile_row_pages(struct drm_i915_gem_object *obj) +static unsigned int tile_row_pages(const struct drm_i915_gem_object *obj) { return i915_gem_object_get_tile_row_size(obj) >> PAGE_SHIFT; } @@ -1965,7 +1962,7 @@ int i915_gem_mmap_gtt_version(void) } static inline struct i915_ggtt_view -compute_partial_view(struct drm_i915_gem_object *obj, +compute_partial_view(const struct drm_i915_gem_object *obj, pgoff_t page_offset, unsigned int chunk) { @@ -2013,7 +2010,7 @@ vm_fault_t i915_gem_fault(struct vm_fault *vmf) struct drm_device *dev = obj->base.dev; struct drm_i915_private *dev_priv = to_i915(dev); struct i915_ggtt *ggtt = &dev_priv->ggtt; - bool write = !!(vmf->flags & FAULT_FLAG_WRITE); + bool write = area->vm_flags & VM_WRITE; struct i915_vma *vma; pgoff_t page_offset; int ret; @@ -2501,7 +2498,9 @@ static bool i915_sg_trim(struct sg_table *orig_st) new_sg = new_st.sgl; for_each_sg(orig_st->sgl, sg, orig_st->nents, i) { sg_set_page(new_sg, sg_page(sg), sg->length, 0); - /* called before being DMA mapped, no need to copy sg->dma_* */ + sg_dma_address(new_sg) = sg_dma_address(sg); + sg_dma_len(new_sg) = sg_dma_len(sg); + new_sg = sg_next(new_sg); } GEM_BUG_ON(new_sg); /* Should walk exactly nents and hit the end */ @@ -2528,13 +2527,21 @@ static int i915_gem_object_get_pages_gtt(struct drm_i915_gem_object *obj) gfp_t noreclaim; int ret; - /* Assert that the object is not currently in any GPU domain. As it + /* + * Assert that the object is not currently in any GPU domain. As it * wasn't in the GTT, there shouldn't be any way it could have been in * a GPU cache */ GEM_BUG_ON(obj->read_domains & I915_GEM_GPU_DOMAINS); GEM_BUG_ON(obj->write_domain & I915_GEM_GPU_DOMAINS); + /* + * If there's no chance of allocating enough pages for the whole + * object, bail early. + */ + if (page_count > totalram_pages) + return -ENOMEM; + st = kmalloc(sizeof(*st), GFP_KERNEL); if (st == NULL) return -ENOMEM; @@ -2545,7 +2552,8 @@ rebuild_st: return -ENOMEM; } - /* Get the list of pages out of our struct file. They'll be pinned + /* + * Get the list of pages out of our struct file. They'll be pinned * at this point until we release them. * * Fail silently without starting the shrinker @@ -2577,7 +2585,8 @@ rebuild_st: i915_gem_shrink(dev_priv, 2 * page_count, NULL, *s++); cond_resched(); - /* We've tried hard to allocate the memory by reaping + /* + * We've tried hard to allocate the memory by reaping * our own buffer, now let the real VM do its job and * go down in flames if truly OOM. * @@ -2589,7 +2598,8 @@ rebuild_st: /* reclaim and warn, but no oom */ gfp = mapping_gfp_mask(mapping); - /* Our bo are always dirty and so we require + /* + * Our bo are always dirty and so we require * kswapd to reclaim our pages (direct reclaim * does not effectively begin pageout of our * buffers on its own). However, direct reclaim @@ -2633,7 +2643,8 @@ rebuild_st: ret = i915_gem_gtt_prepare_pages(obj, st); if (ret) { - /* DMA remapping failed? One possible cause is that + /* + * DMA remapping failed? One possible cause is that * it could not reserve enough large entries, asking * for PAGE_SIZE chunks instead may be helpful. */ @@ -2667,7 +2678,8 @@ err_pages: sg_free_table(st); kfree(st); - /* shmemfs first checks if there is enough memory to allocate the page + /* + * shmemfs first checks if there is enough memory to allocate the page * and reports ENOSPC should there be insufficient, along with the usual * ENOMEM for a genuine allocation failure. * @@ -3307,8 +3319,8 @@ void i915_gem_set_wedged(struct drm_i915_private *i915) intel_engine_dump(engine, &p, "%s\n", engine->name); } - set_bit(I915_WEDGED, &i915->gpu_error.flags); - smp_mb__after_atomic(); + if (test_and_set_bit(I915_WEDGED, &i915->gpu_error.flags)) + goto out; /* * First, stop submission to hw, but do not yet complete requests by @@ -3324,7 +3336,8 @@ void i915_gem_set_wedged(struct drm_i915_private *i915) i915->caps.scheduler = 0; /* Even if the GPU reset fails, it should still stop the engines */ - intel_gpu_reset(i915, ALL_ENGINES); + if (INTEL_GEN(i915) >= 5) + intel_gpu_reset(i915, ALL_ENGINES); /* * Make sure no one is running the old callback before we proceed with @@ -3367,6 +3380,7 @@ void i915_gem_set_wedged(struct drm_i915_private *i915) i915_gem_reset_finish_engine(engine); } +out: GEM_TRACE("end\n"); wake_up_all(&i915->gpu_error.reset_queue); @@ -3418,6 +3432,9 @@ bool i915_gem_unset_wedged(struct drm_i915_private *i915) i915_retire_requests(i915); GEM_BUG_ON(i915->gt.active_requests); + if (!intel_gpu_reset(i915, ALL_ENGINES)) + intel_engines_sanitize(i915); + /* * Undo nop_submit_request. We prevent all new i915 requests from * being queued (by disallowing execbuf whilst wedged) so having @@ -3816,6 +3833,12 @@ int i915_gem_wait_for_idle(struct drm_i915_private *i915, if (timeout < 0) return timeout; } + if (GEM_SHOW_DEBUG() && !timeout) { + /* Presume that timeout was non-zero to begin with! */ + dev_warn(&i915->drm.pdev->dev, + "Missed idle-completion interrupt!\n"); + GEM_TRACE_DUMP(); + } err = wait_for_engines(i915); if (err) @@ -5388,8 +5411,19 @@ static int __intel_engines_record_defaults(struct drm_i915_private *i915) assert_kernel_context_is_current(i915); + /* + * Immediately park the GPU so that we enable powersaving and + * treat it as idle. The next time we issue a request, we will + * unpark and start using the engine->pinned_default_state, otherwise + * it is in limbo and an early reset may fail. + */ + __i915_gem_park(i915); + for_each_engine(engine, i915, id) { struct i915_vma *state; + void *vaddr; + + GEM_BUG_ON(to_intel_context(ctx, engine)->pin_count); state = to_intel_context(ctx, engine)->state; if (!state) @@ -5412,6 +5446,16 @@ static int __intel_engines_record_defaults(struct drm_i915_private *i915) goto err_active; engine->default_state = i915_gem_object_get(state->obj); + + /* Check we can acquire the image of the context state */ + vaddr = i915_gem_object_pin_map(engine->default_state, + I915_MAP_FORCE_WB); + if (IS_ERR(vaddr)) { + err = PTR_ERR(vaddr); + goto err_active; + } + + i915_gem_object_unpin_map(engine->default_state); } if (IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM)) { @@ -5592,6 +5636,8 @@ err_uc_misc: i915_gem_cleanup_userptr(dev_priv); if (ret == -EIO) { + mutex_lock(&dev_priv->drm.struct_mutex); + /* * Allow engine initialisation to fail by marking the GPU as * wedged. But we only want to do this where the GPU is angry, @@ -5602,7 +5648,14 @@ err_uc_misc: "Failed to initialize GPU, declaring it wedged!\n"); i915_gem_set_wedged(dev_priv); } - ret = 0; + + /* Minimal basic recovery for KMS */ + ret = i915_ggtt_enable_hw(dev_priv); + i915_gem_restore_gtt_mappings(dev_priv); + i915_gem_restore_fences(dev_priv); + intel_init_clock_gating(dev_priv); + + mutex_unlock(&dev_priv->drm.struct_mutex); } i915_gem_drain_freed_objects(dev_priv); @@ -5612,6 +5665,7 @@ err_uc_misc: void i915_gem_fini(struct drm_i915_private *dev_priv) { i915_gem_suspend_late(dev_priv); + intel_disable_gt_powersave(dev_priv); /* Flush any outstanding unpin_work. */ i915_gem_drain_workqueue(dev_priv); @@ -5623,6 +5677,8 @@ void i915_gem_fini(struct drm_i915_private *dev_priv) i915_gem_contexts_fini(dev_priv); mutex_unlock(&dev_priv->drm.struct_mutex); + intel_cleanup_gt_powersave(dev_priv); + intel_uc_fini_misc(dev_priv); i915_gem_cleanup_userptr(dev_priv); @@ -5996,7 +6052,8 @@ i915_gem_object_get_sg(struct drm_i915_gem_object *obj, count = __sg_page_count(sg); while (idx + count <= n) { - unsigned long exception, i; + void *entry; + unsigned long i; int ret; /* If we cannot allocate and insert this entry, or the @@ -6011,12 +6068,9 @@ i915_gem_object_get_sg(struct drm_i915_gem_object *obj, if (ret && ret != -EEXIST) goto scan; - exception = - RADIX_TREE_EXCEPTIONAL_ENTRY | - idx << RADIX_TREE_EXCEPTIONAL_SHIFT; + entry = xa_mk_value(idx); for (i = 1; i < count; i++) { - ret = radix_tree_insert(&iter->radix, idx + i, - (void *)exception); + ret = radix_tree_insert(&iter->radix, idx + i, entry); if (ret && ret != -EEXIST) goto scan; } @@ -6054,15 +6108,14 @@ lookup: GEM_BUG_ON(!sg); /* If this index is in the middle of multi-page sg entry, - * the radixtree will contain an exceptional entry that points + * the radix tree will contain a value entry that points * to the start of that range. We will return the pointer to * the base page and the offset of this page within the * sg entry's range. */ *offset = 0; - if (unlikely(radix_tree_exception(sg))) { - unsigned long base = - (unsigned long)sg >> RADIX_TREE_EXCEPTIONAL_SHIFT; + if (unlikely(xa_is_value(sg))) { + unsigned long base = xa_to_value(sg); sg = radix_tree_lookup(&iter->radix, base); GEM_BUG_ON(!sg); @@ -6182,4 +6235,5 @@ err_unlock: #include "selftests/huge_pages.c" #include "selftests/i915_gem_object.c" #include "selftests/i915_gem_coherency.c" +#include "selftests/i915_gem.c" #endif |