diff options
Diffstat (limited to 'drivers/gpu')
28 files changed, 191 insertions, 128 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c index e1cde6b80027..3b0f2ec6eec7 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c @@ -51,7 +51,7 @@ struct amdgpu_mn { /* objects protected by lock */ struct mutex lock; - struct rb_root objects; + struct rb_root_cached objects; }; struct amdgpu_mn_node { @@ -76,8 +76,8 @@ static void amdgpu_mn_destroy(struct work_struct *work) mutex_lock(&adev->mn_lock); mutex_lock(&rmn->lock); hash_del(&rmn->node); - rbtree_postorder_for_each_entry_safe(node, next_node, &rmn->objects, - it.rb) { + rbtree_postorder_for_each_entry_safe(node, next_node, + &rmn->objects.rb_root, it.rb) { list_for_each_entry_safe(bo, next_bo, &node->bos, mn_list) { bo->mn = NULL; list_del_init(&bo->mn_list); @@ -221,7 +221,7 @@ static struct amdgpu_mn *amdgpu_mn_get(struct amdgpu_device *adev) rmn->mm = mm; rmn->mn.ops = &amdgpu_mn_ops; mutex_init(&rmn->lock); - rmn->objects = RB_ROOT; + rmn->objects = RB_ROOT_CACHED; r = __mmu_notifier_register(&rmn->mn, mm); if (r) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index 6b1343e5541d..b9a5a77eedaf 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -2475,7 +2475,7 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm, u64 flags; uint64_t init_pde_value = 0; - vm->va = RB_ROOT; + vm->va = RB_ROOT_CACHED; vm->client_id = atomic64_inc_return(&adev->vm_manager.client_counter); for (i = 0; i < AMDGPU_MAX_VMHUBS; i++) vm->reserved_vmid[i] = NULL; @@ -2596,10 +2596,11 @@ void amdgpu_vm_fini(struct amdgpu_device *adev, struct amdgpu_vm *vm) amd_sched_entity_fini(vm->entity.sched, &vm->entity); - if (!RB_EMPTY_ROOT(&vm->va)) { + if (!RB_EMPTY_ROOT(&vm->va.rb_root)) { dev_err(adev->dev, "still active bo inside vm\n"); } - rbtree_postorder_for_each_entry_safe(mapping, tmp, &vm->va, rb) { + rbtree_postorder_for_each_entry_safe(mapping, tmp, + &vm->va.rb_root, rb) { list_del(&mapping->list); amdgpu_vm_it_remove(mapping, &vm->va); kfree(mapping); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h index ba6691b58ee7..6716355403ec 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h @@ -118,7 +118,7 @@ struct amdgpu_vm_pt { struct amdgpu_vm { /* tree of virtual addresses mapped */ - struct rb_root va; + struct rb_root_cached va; /* protecting invalidated */ spinlock_t status_lock; diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/rv_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/rv_hwmgr.c index edc5fb6412d9..2c3e6baf2524 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/rv_hwmgr.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/rv_hwmgr.c @@ -317,8 +317,8 @@ static int rv_tf_set_num_active_display(struct pp_hwmgr *hwmgr, void *input, } static const struct phm_master_table_item rv_set_power_state_list[] = { - { NULL, rv_tf_set_clock_limit }, - { NULL, rv_tf_set_num_active_display }, + { .tableFunction = rv_tf_set_clock_limit }, + { .tableFunction = rv_tf_set_num_active_display }, { } }; @@ -391,7 +391,7 @@ static int rv_tf_disable_gfx_off(struct pp_hwmgr *hwmgr, } static const struct phm_master_table_item rv_disable_dpm_list[] = { - {NULL, rv_tf_disable_gfx_off}, + { .tableFunction = rv_tf_disable_gfx_off }, { }, }; @@ -416,7 +416,7 @@ static int rv_tf_enable_gfx_off(struct pp_hwmgr *hwmgr, } static const struct phm_master_table_item rv_enable_dpm_list[] = { - {NULL, rv_tf_enable_gfx_off}, + { .tableFunction = rv_tf_enable_gfx_off }, { }, }; diff --git a/drivers/gpu/drm/drm_mm.c b/drivers/gpu/drm/drm_mm.c index f794089d30ac..61a1c8ea74bc 100644 --- a/drivers/gpu/drm/drm_mm.c +++ b/drivers/gpu/drm/drm_mm.c @@ -169,7 +169,7 @@ INTERVAL_TREE_DEFINE(struct drm_mm_node, rb, struct drm_mm_node * __drm_mm_interval_first(const struct drm_mm *mm, u64 start, u64 last) { - return drm_mm_interval_tree_iter_first((struct rb_root *)&mm->interval_tree, + return drm_mm_interval_tree_iter_first((struct rb_root_cached *)&mm->interval_tree, start, last) ?: (struct drm_mm_node *)&mm->head_node; } EXPORT_SYMBOL(__drm_mm_interval_first); @@ -180,6 +180,7 @@ static void drm_mm_interval_tree_add_node(struct drm_mm_node *hole_node, struct drm_mm *mm = hole_node->mm; struct rb_node **link, *rb; struct drm_mm_node *parent; + bool leftmost = true; node->__subtree_last = LAST(node); @@ -196,9 +197,10 @@ static void drm_mm_interval_tree_add_node(struct drm_mm_node *hole_node, rb = &hole_node->rb; link = &hole_node->rb.rb_right; + leftmost = false; } else { rb = NULL; - link = &mm->interval_tree.rb_node; + link = &mm->interval_tree.rb_root.rb_node; } while (*link) { @@ -208,14 +210,15 @@ static void drm_mm_interval_tree_add_node(struct drm_mm_node *hole_node, parent->__subtree_last = node->__subtree_last; if (node->start < parent->start) link = &parent->rb.rb_left; - else + else { link = &parent->rb.rb_right; + leftmost = true; + } } rb_link_node(&node->rb, rb, link); - rb_insert_augmented(&node->rb, - &mm->interval_tree, - &drm_mm_interval_tree_augment); + rb_insert_augmented_cached(&node->rb, &mm->interval_tree, leftmost, + &drm_mm_interval_tree_augment); } #define RB_INSERT(root, member, expr) do { \ @@ -577,7 +580,7 @@ void drm_mm_replace_node(struct drm_mm_node *old, struct drm_mm_node *new) *new = *old; list_replace(&old->node_list, &new->node_list); - rb_replace_node(&old->rb, &new->rb, &old->mm->interval_tree); + rb_replace_node(&old->rb, &new->rb, &old->mm->interval_tree.rb_root); if (drm_mm_hole_follows(old)) { list_replace(&old->hole_stack, &new->hole_stack); @@ -863,7 +866,7 @@ void drm_mm_init(struct drm_mm *mm, u64 start, u64 size) mm->color_adjust = NULL; INIT_LIST_HEAD(&mm->hole_stack); - mm->interval_tree = RB_ROOT; + mm->interval_tree = RB_ROOT_CACHED; mm->holes_size = RB_ROOT; mm->holes_addr = RB_ROOT; diff --git a/drivers/gpu/drm/drm_vma_manager.c b/drivers/gpu/drm/drm_vma_manager.c index d9100b565198..28f1226576f8 100644 --- a/drivers/gpu/drm/drm_vma_manager.c +++ b/drivers/gpu/drm/drm_vma_manager.c @@ -147,7 +147,7 @@ struct drm_vma_offset_node *drm_vma_offset_lookup_locked(struct drm_vma_offset_m struct rb_node *iter; unsigned long offset; - iter = mgr->vm_addr_space_mm.interval_tree.rb_node; + iter = mgr->vm_addr_space_mm.interval_tree.rb_root.rb_node; best = NULL; while (likely(iter)) { diff --git a/drivers/gpu/drm/i915/gvt/handlers.c b/drivers/gpu/drm/i915/gvt/handlers.c index 3502a59166ff..2294466dd415 100644 --- a/drivers/gpu/drm/i915/gvt/handlers.c +++ b/drivers/gpu/drm/i915/gvt/handlers.c @@ -2659,7 +2659,6 @@ static int init_skl_mmio_info(struct intel_gvt *gvt) MMIO_D(HSW_PWR_WELL_CTL_BIOS(SKL_DISP_PW_MISC_IO), D_SKL_PLUS); MMIO_DH(HSW_PWR_WELL_CTL_DRIVER(SKL_DISP_PW_MISC_IO), D_SKL_PLUS, NULL, skl_power_well_ctl_write); - MMIO_DH(GEN6_PCODE_MAILBOX, D_SKL_PLUS, NULL, mailbox_write); MMIO_D(0xa210, D_SKL_PLUS); MMIO_D(GEN9_MEDIA_PG_IDLE_HYSTERESIS, D_SKL_PLUS); diff --git a/drivers/gpu/drm/i915/i915_cmd_parser.c b/drivers/gpu/drm/i915/i915_cmd_parser.c index f0cb22cc0dd6..8ba932b22f7c 100644 --- a/drivers/gpu/drm/i915/i915_cmd_parser.c +++ b/drivers/gpu/drm/i915/i915_cmd_parser.c @@ -1073,7 +1073,7 @@ static u32 *copy_batch(struct drm_i915_gem_object *dst_obj, goto unpin_src; } - dst = i915_gem_object_pin_map(dst_obj, I915_MAP_WB); + dst = i915_gem_object_pin_map(dst_obj, I915_MAP_FORCE_WB); if (IS_ERR(dst)) goto unpin_dst; diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c index a36216bd2a84..e4d4b6b41e26 100644 --- a/drivers/gpu/drm/i915/i915_debugfs.c +++ b/drivers/gpu/drm/i915/i915_debugfs.c @@ -4308,10 +4308,10 @@ i915_drop_caches_set(void *data, u64 val) fs_reclaim_acquire(GFP_KERNEL); if (val & DROP_BOUND) - i915_gem_shrink(dev_priv, LONG_MAX, I915_SHRINK_BOUND); + i915_gem_shrink(dev_priv, LONG_MAX, NULL, I915_SHRINK_BOUND); if (val & DROP_UNBOUND) - i915_gem_shrink(dev_priv, LONG_MAX, I915_SHRINK_UNBOUND); + i915_gem_shrink(dev_priv, LONG_MAX, NULL, I915_SHRINK_UNBOUND); if (val & DROP_SHRINK_ALL) i915_gem_shrink_all(dev_priv); diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c index 43100229613c..9f45cfeae775 100644 --- a/drivers/gpu/drm/i915/i915_drv.c +++ b/drivers/gpu/drm/i915/i915_drv.c @@ -1891,9 +1891,15 @@ void i915_reset(struct drm_i915_private *i915, unsigned int flags) /* * Everything depends on having the GTT running, so we need to start - * there. Fortunately we don't need to do this unless we reset the - * chip at a PCI level. - * + * there. + */ + ret = i915_ggtt_enable_hw(i915); + if (ret) { + DRM_ERROR("Failed to re-enable GGTT following reset %d\n", ret); + goto error; + } + + /* * Next we need to restore the context, but we don't use those * yet either... * diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index 60267e375e88..18d9da53282b 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -3479,6 +3479,9 @@ void __i915_gem_object_invalidate(struct drm_i915_gem_object *obj); enum i915_map_type { I915_MAP_WB = 0, I915_MAP_WC, +#define I915_MAP_OVERRIDE BIT(31) + I915_MAP_FORCE_WB = I915_MAP_WB | I915_MAP_OVERRIDE, + I915_MAP_FORCE_WC = I915_MAP_WC | I915_MAP_OVERRIDE, }; /** @@ -3742,6 +3745,7 @@ i915_gem_object_create_internal(struct drm_i915_private *dev_priv, /* i915_gem_shrinker.c */ unsigned long i915_gem_shrink(struct drm_i915_private *dev_priv, unsigned long target, + unsigned long *nr_scanned, unsigned flags); #define I915_SHRINK_PURGEABLE 0x1 #define I915_SHRINK_UNBOUND 0x2 diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index b9e8e0d6e97b..57317715977f 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -695,12 +695,11 @@ flush_write_domain(struct drm_i915_gem_object *obj, unsigned int flush_domains) switch (obj->base.write_domain) { case I915_GEM_DOMAIN_GTT: if (INTEL_GEN(dev_priv) >= 6 && !HAS_LLC(dev_priv)) { - if (intel_runtime_pm_get_if_in_use(dev_priv)) { - spin_lock_irq(&dev_priv->uncore.lock); - POSTING_READ_FW(RING_ACTHD(dev_priv->engine[RCS]->mmio_base)); - spin_unlock_irq(&dev_priv->uncore.lock); - intel_runtime_pm_put(dev_priv); - } + intel_runtime_pm_get(dev_priv); + spin_lock_irq(&dev_priv->uncore.lock); + POSTING_READ_FW(RING_ACTHD(dev_priv->engine[RCS]->mmio_base)); + spin_unlock_irq(&dev_priv->uncore.lock); + intel_runtime_pm_put(dev_priv); } intel_fb_obj_flush(obj, @@ -2213,7 +2212,7 @@ i915_gem_object_put_pages_gtt(struct drm_i915_gem_object *obj, static void __i915_gem_object_reset_page_iter(struct drm_i915_gem_object *obj) { struct radix_tree_iter iter; - void **slot; + void __rcu **slot; radix_tree_for_each_slot(slot, &obj->mm.get_page.radix, &iter, 0) radix_tree_delete(&obj->mm.get_page.radix, iter.index); @@ -2354,7 +2353,7 @@ rebuild_st: goto err_sg; } - i915_gem_shrink(dev_priv, 2 * page_count, *s++); + i915_gem_shrink(dev_priv, 2 * page_count, NULL, *s++); cond_resched(); /* We've tried hard to allocate the memory by reaping @@ -2553,6 +2552,9 @@ static void *i915_gem_object_map(const struct drm_i915_gem_object *obj, GEM_BUG_ON(i != n_pages); switch (type) { + default: + MISSING_CASE(type); + /* fallthrough to use PAGE_KERNEL anyway */ case I915_MAP_WB: pgprot = PAGE_KERNEL; break; @@ -2583,7 +2585,9 @@ void *i915_gem_object_pin_map(struct drm_i915_gem_object *obj, if (ret) return ERR_PTR(ret); - pinned = true; + pinned = !(type & I915_MAP_OVERRIDE); + type &= ~I915_MAP_OVERRIDE; + if (!atomic_inc_not_zero(&obj->mm.pages_pin_count)) { if (unlikely(IS_ERR_OR_NULL(obj->mm.pages))) { ret = ____i915_gem_object_get_pages(obj); @@ -3258,7 +3262,13 @@ void i915_gem_close_object(struct drm_gem_object *gem, struct drm_file *file) vma = radix_tree_delete(&ctx->handles_vma, lut->handle); - if (!i915_vma_is_ggtt(vma)) + GEM_BUG_ON(vma->obj != obj); + + /* We allow the process to have multiple handles to the same + * vma, in the same fd namespace, by virtue of flink/open. + */ + GEM_BUG_ON(!vma->open_count); + if (!--vma->open_count && !i915_vma_is_ggtt(vma)) i915_vma_close(vma); list_del(&lut->obj_link); @@ -5015,7 +5025,7 @@ int i915_gem_freeze_late(struct drm_i915_private *dev_priv) * the objects as well, see i915_gem_freeze() */ - i915_gem_shrink(dev_priv, -1UL, I915_SHRINK_UNBOUND); + i915_gem_shrink(dev_priv, -1UL, NULL, I915_SHRINK_UNBOUND); i915_gem_drain_freed_objects(dev_priv); mutex_lock(&dev_priv->drm.struct_mutex); diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c index 4c2016237d61..50d5e24f91a9 100644 --- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c @@ -285,7 +285,7 @@ static int eb_create(struct i915_execbuffer *eb) * direct lookup. */ do { - unsigned int flags; + gfp_t flags; /* While we can still reduce the allocation size, don't * raise a warning and allow the allocation to fail. @@ -720,6 +720,7 @@ static int eb_lookup_vmas(struct i915_execbuffer *eb) goto err_obj; } + vma->open_count++; list_add(&lut->obj_link, &obj->lut_list); list_add(&lut->ctx_link, &eb->ctx->handles_list); lut->ctx = eb->ctx; @@ -1070,7 +1071,9 @@ static int __reloc_gpu_alloc(struct i915_execbuffer *eb, return PTR_ERR(obj); cmd = i915_gem_object_pin_map(obj, - cache->has_llc ? I915_MAP_WB : I915_MAP_WC); + cache->has_llc ? + I915_MAP_FORCE_WB : + I915_MAP_FORCE_WC); i915_gem_object_unpin_pages(obj); if (IS_ERR(cmd)) return PTR_ERR(cmd); @@ -1526,7 +1529,7 @@ static int eb_copy_relocations(const struct i915_execbuffer *eb) min_t(u64, BIT_ULL(31), size - copied); if (__copy_from_user((char *)relocs + copied, - (char *)urelocs + copied, + (char __user *)urelocs + copied, len)) { kvfree(relocs); err = -EFAULT; diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c index d60f38adc4c4..0d5a988b3867 100644 --- a/drivers/gpu/drm/i915/i915_gem_gtt.c +++ b/drivers/gpu/drm/i915/i915_gem_gtt.c @@ -2062,7 +2062,7 @@ int i915_gem_gtt_prepare_pages(struct drm_i915_gem_object *obj, */ GEM_BUG_ON(obj->mm.pages == pages); } while (i915_gem_shrink(to_i915(obj->base.dev), - obj->base.size >> PAGE_SHIFT, + obj->base.size >> PAGE_SHIFT, NULL, I915_SHRINK_BOUND | I915_SHRINK_UNBOUND | I915_SHRINK_ACTIVE)); @@ -2754,10 +2754,10 @@ static void cnl_setup_private_ppat(struct drm_i915_private *dev_priv) I915_WRITE(GEN10_PAT_INDEX(1), GEN8_PPAT_WC | GEN8_PPAT_LLCELLC); I915_WRITE(GEN10_PAT_INDEX(2), GEN8_PPAT_WT | GEN8_PPAT_LLCELLC); I915_WRITE(GEN10_PAT_INDEX(3), GEN8_PPAT_UC); - I915_WRITE(GEN10_PAT_INDEX(4), GEN8_PPAT_LLCELLC | GEN8_PPAT_AGE(0)); - I915_WRITE(GEN10_PAT_INDEX(5), GEN8_PPAT_LLCELLC | GEN8_PPAT_AGE(1)); - I915_WRITE(GEN10_PAT_INDEX(6), GEN8_PPAT_LLCELLC | GEN8_PPAT_AGE(2)); - I915_WRITE(GEN10_PAT_INDEX(7), GEN8_PPAT_LLCELLC | GEN8_PPAT_AGE(3)); + I915_WRITE(GEN10_PAT_INDEX(4), GEN8_PPAT_WB | GEN8_PPAT_LLCELLC | GEN8_PPAT_AGE(0)); + I915_WRITE(GEN10_PAT_INDEX(5), GEN8_PPAT_WB | GEN8_PPAT_LLCELLC | GEN8_PPAT_AGE(1)); + I915_WRITE(GEN10_PAT_INDEX(6), GEN8_PPAT_WB | GEN8_PPAT_LLCELLC | GEN8_PPAT_AGE(2)); + I915_WRITE(GEN10_PAT_INDEX(7), GEN8_PPAT_WB | GEN8_PPAT_LLCELLC | GEN8_PPAT_AGE(3)); } /* The GGTT and PPGTT need a private PPAT setup in order to handle cacheability diff --git a/drivers/gpu/drm/i915/i915_gem_shrinker.c b/drivers/gpu/drm/i915/i915_gem_shrinker.c index 77fb39808131..74002b2d1b6f 100644 --- a/drivers/gpu/drm/i915/i915_gem_shrinker.c +++ b/drivers/gpu/drm/i915/i915_gem_shrinker.c @@ -136,6 +136,7 @@ static bool unsafe_drop_pages(struct drm_i915_gem_object *obj) * i915_gem_shrink - Shrink buffer object caches * @dev_priv: i915 device * @target: amount of memory to make available, in pages + * @nr_scanned: optional output for number of pages scanned (incremental) * @flags: control flags for selecting cache types * * This function is the main interface to the shrinker. It will try to release @@ -158,7 +159,9 @@ static bool unsafe_drop_pages(struct drm_i915_gem_object *obj) */ unsigned long i915_gem_shrink(struct drm_i915_private *dev_priv, - unsigned long target, unsigned flags) + unsigned long target, + unsigned long *nr_scanned, + unsigned flags) { const struct { struct list_head *list; @@ -169,6 +172,7 @@ i915_gem_shrink(struct drm_i915_private *dev_priv, { NULL, 0 }, }, *phase; unsigned long count = 0; + unsigned long scanned = 0; bool unlock; if (!shrinker_lock(dev_priv, &unlock)) @@ -249,6 +253,7 @@ i915_gem_shrink(struct drm_i915_private *dev_priv, count += obj->base.size >> PAGE_SHIFT; } mutex_unlock(&obj->mm.lock); + scanned += obj->base.size >> PAGE_SHIFT; } } list_splice_tail(&still_in_list, phase->list); @@ -261,6 +266,8 @@ i915_gem_shrink(struct drm_i915_private *dev_priv, shrinker_unlock(dev_priv, unlock); + if (nr_scanned) + *nr_scanned += scanned; return count; } @@ -283,7 +290,7 @@ unsigned long i915_gem_shrink_all(struct drm_i915_private *dev_priv) unsigned long freed; intel_runtime_pm_get(dev_priv); - freed = i915_gem_shrink(dev_priv, -1UL, + freed = i915_gem_shrink(dev_priv, -1UL, NULL, I915_SHRINK_BOUND | I915_SHRINK_UNBOUND | I915_SHRINK_ACTIVE); @@ -329,23 +336,28 @@ i915_gem_shrinker_scan(struct shrinker *shrinker, struct shrink_control *sc) unsigned long freed; bool unlock; + sc->nr_scanned = 0; + if (!shrinker_lock(dev_priv, &unlock)) return SHRINK_STOP; freed = i915_gem_shrink(dev_priv, sc->nr_to_scan, + &sc->nr_scanned, I915_SHRINK_BOUND | I915_SHRINK_UNBOUND | I915_SHRINK_PURGEABLE); if (freed < sc->nr_to_scan) freed += i915_gem_shrink(dev_priv, - sc->nr_to_scan - freed, + sc->nr_to_scan - sc->nr_scanned, + &sc->nr_scanned, I915_SHRINK_BOUND | I915_SHRINK_UNBOUND); if (freed < sc->nr_to_scan && current_is_kswapd()) { intel_runtime_pm_get(dev_priv); freed += i915_gem_shrink(dev_priv, - sc->nr_to_scan - freed, + sc->nr_to_scan - sc->nr_scanned, + &sc->nr_scanned, I915_SHRINK_ACTIVE | I915_SHRINK_BOUND | I915_SHRINK_UNBOUND); @@ -354,7 +366,7 @@ i915_gem_shrinker_scan(struct shrinker *shrinker, struct shrink_control *sc) shrinker_unlock(dev_priv, unlock); - return freed; + return sc->nr_scanned ? freed : SHRINK_STOP; } static bool @@ -453,7 +465,7 @@ i915_gem_shrinker_vmap(struct notifier_block *nb, unsigned long event, void *ptr goto out; intel_runtime_pm_get(dev_priv); - freed_pages += i915_gem_shrink(dev_priv, -1UL, + freed_pages += i915_gem_shrink(dev_priv, -1UL, NULL, I915_SHRINK_BOUND | I915_SHRINK_UNBOUND | I915_SHRINK_ACTIVE | diff --git a/drivers/gpu/drm/i915/i915_gem_userptr.c b/drivers/gpu/drm/i915/i915_gem_userptr.c index f152a38d7079..23fd18bd1b56 100644 --- a/drivers/gpu/drm/i915/i915_gem_userptr.c +++ b/drivers/gpu/drm/i915/i915_gem_userptr.c @@ -49,7 +49,7 @@ struct i915_mmu_notifier { spinlock_t lock; struct hlist_node node; struct mmu_notifier mn; - struct rb_root objects; + struct rb_root_cached objects; struct workqueue_struct *wq; }; @@ -123,7 +123,7 @@ static void i915_gem_userptr_mn_invalidate_range_start(struct mmu_notifier *_mn, struct interval_tree_node *it; LIST_HEAD(cancelled); - if (RB_EMPTY_ROOT(&mn->objects)) + if (RB_EMPTY_ROOT(&mn->objects.rb_root)) return; /* interval ranges are inclusive, but invalidate range is exclusive */ @@ -172,7 +172,7 @@ i915_mmu_notifier_create(struct mm_struct *mm) spin_lock_init(&mn->lock); mn->mn.ops = &i915_gem_userptr_notifier; - mn->objects = RB_ROOT; + mn->objects = RB_ROOT_CACHED; mn->wq = alloc_workqueue("i915-userptr-release", WQ_UNBOUND, 0); if (mn->wq == NULL) { kfree(mn); diff --git a/drivers/gpu/drm/i915/i915_trace.h b/drivers/gpu/drm/i915/i915_trace.h index b24a83d43559..6fd5c57e21f6 100644 --- a/drivers/gpu/drm/i915/i915_trace.h +++ b/drivers/gpu/drm/i915/i915_trace.h @@ -38,7 +38,7 @@ TRACE_EVENT(intel_cpu_fifo_underrun, ); TRACE_EVENT(intel_pch_fifo_underrun, - TP_PROTO(struct drm_i915_private *dev_priv, enum transcoder pch_transcoder), + TP_PROTO(struct drm_i915_private *dev_priv, enum pipe pch_transcoder), TP_ARGS(dev_priv, pch_transcoder), TP_STRUCT__entry( @@ -48,7 +48,7 @@ TRACE_EVENT(intel_pch_fifo_underrun, ), TP_fast_assign( - enum pipe pipe = (enum pipe)pch_transcoder; + enum pipe pipe = pch_transcoder; __entry->pipe = pipe; __entry->frame = dev_priv->drm.driver->get_vblank_counter(&dev_priv->drm, pipe); __entry->scanline = intel_get_crtc_scanline(intel_get_crtc_for_pipe(dev_priv, pipe)); diff --git a/drivers/gpu/drm/i915/i915_vma.h b/drivers/gpu/drm/i915/i915_vma.h index 1fd61e88cfd0..e811067c7724 100644 --- a/drivers/gpu/drm/i915/i915_vma.h +++ b/drivers/gpu/drm/i915/i915_vma.h @@ -59,6 +59,12 @@ struct i915_vma { u32 fence_size; u32 fence_alignment; + /** + * Count of the number of times this vma has been opened by different + * handles (but same file) for execbuf, i.e. the number of aliases + * that exist in the ctx->handle_vmas LUT for this vma. + */ + unsigned int open_count; unsigned int flags; /** * How many users have pinned this object in GTT space. The following diff --git a/drivers/gpu/drm/i915/intel_color.c b/drivers/gpu/drm/i915/intel_color.c index 8e4e829682b9..ff9ecd211abb 100644 --- a/drivers/gpu/drm/i915/intel_color.c +++ b/drivers/gpu/drm/i915/intel_color.c @@ -107,7 +107,7 @@ static void ctm_mult_by_limited(uint64_t *result, int64_t *input) } } -void i9xx_load_ycbcr_conversion_matrix(struct intel_crtc *intel_crtc) +static void i9xx_load_ycbcr_conversion_matrix(struct intel_crtc *intel_crtc) { int pipe = intel_crtc->pipe; struct drm_i915_private *dev_priv = to_i915(intel_crtc->base.dev); diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index 0e93ec201fe3..f17275519484 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -2288,17 +2288,13 @@ void intel_add_fb_offsets(int *x, int *y, } } -/* - * Input tile dimensions and pitch must already be - * rotated to match x and y, and in pixel units. - */ -static u32 _intel_adjust_tile_offset(int *x, int *y, - unsigned int tile_width, - unsigned int tile_height, - unsigned int tile_size, - unsigned int pitch_tiles, - u32 old_offset, - u32 new_offset) +static u32 __intel_adjust_tile_offset(int *x, int *y, + unsigned int tile_width, + unsigned int tile_height, + unsigned int tile_size, + unsigned int pitch_tiles, + u32 old_offset, + u32 new_offset) { unsigned int pitch_pixels = pitch_tiles * tile_width; unsigned int tiles; @@ -2319,18 +2315,13 @@ static u32 _intel_adjust_tile_offset(int *x, int *y, return new_offset; } -/* - * Adjust the tile offset by moving the difference into - * the x/y offsets. - */ -static u32 intel_adjust_tile_offset(int *x, int *y, - const struct intel_plane_state *state, int plane, - u32 old_offset, u32 new_offset) +static u32 _intel_adjust_tile_offset(int *x, int *y, + const struct drm_framebuffer *fb, int plane, + unsigned int rotation, + u32 old_offset, u32 new_offset) { - const struct drm_i915_private *dev_priv = to_i915(state->base.plane->dev); - const struct drm_framebuffer *fb = state->base.fb; + const struct drm_i915_private *dev_priv = to_i915(fb->dev); unsigned int cpp = fb->format->cpp[plane]; - unsigned int rotation = state->base.rotation; unsigned int pitch = intel_fb_pitch(fb, plane, rotation); WARN_ON(new_offset > old_offset); @@ -2349,9 +2340,9 @@ static u32 intel_adjust_tile_offset(int *x, int *y, pitch_tiles = pitch / (tile_width * cpp); } - _intel_adjust_tile_offset(x, y, tile_width, tile_height, - tile_size, pitch_tiles, - old_offset, new_offset); + __intel_adjust_tile_offset(x, y, tile_width, tile_height, + tile_size, pitch_tiles, + old_offset, new_offset); } else { old_offset += *y * pitch + *x * cpp; @@ -2363,6 +2354,19 @@ static u32 intel_adjust_tile_offset(int *x, int *y, } /* + * Adjust the tile offset by moving the difference into + * the x/y offsets. + */ +static u32 intel_adjust_tile_offset(int *x, int *y, + const struct intel_plane_state *state, int plane, + u32 old_offset, u32 new_offset) +{ + return _intel_adjust_tile_offset(x, y, state->base.fb, plane, + state->base.rotation, + old_offset, new_offset); +} + +/* * Computes the linear offset to the base tile and adjusts * x, y. bytes per pixel is assumed to be a power-of-two. * @@ -2413,9 +2417,9 @@ static u32 _intel_compute_tile_offset(const struct drm_i915_private *dev_priv, offset = (tile_rows * pitch_tiles + tiles) * tile_size; offset_aligned = offset & ~alignment; - _intel_adjust_tile_offset(x, y, tile_width, tile_height, - tile_size, pitch_tiles, - offset, offset_aligned); + __intel_adjust_tile_offset(x, y, tile_width, tile_height, + tile_size, pitch_tiles, + offset, offset_aligned); } else { offset = *y * pitch + *x * cpp; offset_aligned = offset & ~alignment; @@ -2447,16 +2451,24 @@ u32 intel_compute_tile_offset(int *x, int *y, rotation, alignment); } -/* Convert the fb->offset[] linear offset into x/y offsets */ -static void intel_fb_offset_to_xy(int *x, int *y, - const struct drm_framebuffer *fb, int plane) +/* Convert the fb->offset[] into x/y offsets */ +static int intel_fb_offset_to_xy(int *x, int *y, + const struct drm_framebuffer *fb, int plane) { - unsigned int cpp = fb->format->cpp[plane]; - unsigned int pitch = fb->pitches[plane]; - u32 linear_offset = fb->offsets[plane]; + struct drm_i915_private *dev_priv = to_i915(fb->dev); + + if (fb->modifier != DRM_FORMAT_MOD_LINEAR && + fb->offsets[plane] % intel_tile_size(dev_priv)) + return -EINVAL; - *y = linear_offset / pitch; - *x = linear_offset % pitch / cpp; + *x = 0; + *y = 0; + + _intel_adjust_tile_offset(x, y, + fb, plane, DRM_MODE_ROTATE_0, + fb->offsets[plane], 0); + + return 0; } static unsigned int intel_fb_modifier_to_tiling(uint64_t fb_modifier) @@ -2523,12 +2535,18 @@ intel_fill_fb_info(struct drm_i915_private *dev_priv, unsigned int cpp, size; u32 offset; int x, y; + int ret; cpp = fb->format->cpp[i]; width = drm_framebuffer_plane_width(fb->width, fb, i); height = drm_framebuffer_plane_height(fb->height, fb, i); - intel_fb_offset_to_xy(&x, &y, fb, i); + ret = intel_fb_offset_to_xy(&x, &y, fb, i); + if (ret) { + DRM_DEBUG_KMS("bad fb plane %d offset: 0x%x\n", + i, fb->offsets[i]); + return ret; + } if ((fb->modifier == I915_FORMAT_MOD_Y_TILED_CCS || fb->modifier == I915_FORMAT_MOD_Yf_TILED_CCS) && i == 1) { @@ -2539,11 +2557,13 @@ intel_fill_fb_info(struct drm_i915_private *dev_priv, int ccs_x, ccs_y; intel_tile_dims(fb, i, &tile_width, &tile_height); + tile_width *= hsub; + tile_height *= vsub; - ccs_x = (x * hsub) % (tile_width * hsub); - ccs_y = (y * vsub) % (tile_height * vsub); - main_x = intel_fb->normal[0].x % (tile_width * hsub); - main_y = intel_fb->normal[0].y % (tile_height * vsub); + ccs_x = (x * hsub) % tile_width; + ccs_y = (y * vsub) % tile_height; + main_x = intel_fb->normal[0].x % tile_width; + main_y = intel_fb->normal[0].y % tile_height; /* * CCS doesn't have its own x/y offset register, so the intra CCS tile @@ -2569,7 +2589,7 @@ intel_fill_fb_info(struct drm_i915_private *dev_priv, * fb layout agrees with the fence layout. We already check that the * fb stride matches the fence stride elsewhere. */ - if (i915_gem_object_is_tiled(intel_fb->obj) && + if (i == 0 && i915_gem_object_is_tiled(intel_fb->obj) && (x + width) * cpp > fb->pitches[i]) { DRM_DEBUG_KMS("bad fb plane %d offset: 0x%x\n", i, fb->offsets[i]); @@ -2632,10 +2652,10 @@ intel_fill_fb_info(struct drm_i915_private *dev_priv, * We only keep the x/y offsets, so push all of the * gtt offset into the x/y offsets. */ - _intel_adjust_tile_offset(&x, &y, - tile_width, tile_height, - tile_size, pitch_tiles, - gtt_offset_rotated * tile_size, 0); + __intel_adjust_tile_offset(&x, &y, + tile_width, tile_height, + tile_size, pitch_tiles, + gtt_offset_rotated * tile_size, 0); gtt_offset_rotated += rot_info->plane[i].width * rot_info->plane[i].height; diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c index 4fd4853b2250..64134947c0aa 100644 --- a/drivers/gpu/drm/i915/intel_dp.c +++ b/drivers/gpu/drm/i915/intel_dp.c @@ -5273,7 +5273,7 @@ intel_dp_init_panel_power_sequencer(struct drm_device *dev, * seems sufficient to avoid this problem. */ if (dev_priv->quirks & QUIRK_INCREASE_T12_DELAY) { - vbt.t11_t12 = max_t(u16, vbt.t11_t12, 800 * 10); + vbt.t11_t12 = max_t(u16, vbt.t11_t12, 900 * 10); DRM_DEBUG_KMS("Increasing T12 panel delay as per the quirk to %d\n", vbt.t11_t12); } diff --git a/drivers/gpu/drm/i915/intel_fbc.c b/drivers/gpu/drm/i915/intel_fbc.c index 3fca9fa39a8e..8c8ead2276e0 100644 --- a/drivers/gpu/drm/i915/intel_fbc.c +++ b/drivers/gpu/drm/i915/intel_fbc.c @@ -406,9 +406,7 @@ static void intel_fbc_work_fn(struct work_struct *__work) struct drm_vblank_crtc *vblank = &dev_priv->drm.vblank[crtc->pipe]; if (drm_crtc_vblank_get(&crtc->base)) { - DRM_ERROR("vblank not available for FBC on pipe %c\n", - pipe_name(crtc->pipe)); - + /* CRTC is now off, leave FBC deactivated */ mutex_lock(&fbc->lock); work->scheduled = false; mutex_unlock(&fbc->lock); diff --git a/drivers/gpu/drm/i915/intel_fifo_underrun.c b/drivers/gpu/drm/i915/intel_fifo_underrun.c index 5a7cca32c0fa..04689600e337 100644 --- a/drivers/gpu/drm/i915/intel_fifo_underrun.c +++ b/drivers/gpu/drm/i915/intel_fifo_underrun.c @@ -187,11 +187,11 @@ static void broadwell_set_fifo_underrun_reporting(struct drm_device *dev, } static void ibx_set_fifo_underrun_reporting(struct drm_device *dev, - enum transcoder pch_transcoder, + enum pipe pch_transcoder, bool enable) { struct drm_i915_private *dev_priv = to_i915(dev); - uint32_t bit = (pch_transcoder == TRANSCODER_A) ? + uint32_t bit = (pch_transcoder == PIPE_A) ? SDE_TRANSA_FIFO_UNDER : SDE_TRANSB_FIFO_UNDER; if (enable) @@ -203,7 +203,7 @@ static void ibx_set_fifo_underrun_reporting(struct drm_device *dev, static void cpt_check_pch_fifo_underruns(struct intel_crtc *crtc) { struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); - enum transcoder pch_transcoder = (enum transcoder) crtc->pipe; + enum pipe pch_transcoder = crtc->pipe; uint32_t serr_int = I915_READ(SERR_INT); lockdep_assert_held(&dev_priv->irq_lock); @@ -215,12 +215,12 @@ static void cpt_check_pch_fifo_underruns(struct intel_crtc *crtc) POSTING_READ(SERR_INT); trace_intel_pch_fifo_underrun(dev_priv, pch_transcoder); - DRM_ERROR("pch fifo underrun on pch transcoder %s\n", - transcoder_name(pch_transcoder)); + DRM_ERROR("pch fifo underrun on pch transcoder %c\n", + pipe_name(pch_transcoder)); } static void cpt_set_fifo_underrun_reporting(struct drm_device *dev, - enum transcoder pch_transcoder, + enum pipe pch_transcoder, bool enable, bool old) { struct drm_i915_private *dev_priv = to_i915(dev); @@ -238,8 +238,8 @@ static void cpt_set_fifo_underrun_reporting(struct drm_device *dev, if (old && I915_READ(SERR_INT) & SERR_INT_TRANS_FIFO_UNDERRUN(pch_transcoder)) { - DRM_ERROR("uncleared pch fifo underrun on pch transcoder %s\n", - transcoder_name(pch_transcoder)); + DRM_ERROR("uncleared pch fifo underrun on pch transcoder %c\n", + pipe_name(pch_transcoder)); } } } @@ -395,8 +395,8 @@ void intel_pch_fifo_underrun_irq_handler(struct drm_i915_private *dev_priv, if (intel_set_pch_fifo_underrun_reporting(dev_priv, pch_transcoder, false)) { trace_intel_pch_fifo_underrun(dev_priv, pch_transcoder); - DRM_ERROR("PCH transcoder %s FIFO underrun\n", - transcoder_name(pch_transcoder)); + DRM_ERROR("PCH transcoder %c FIFO underrun\n", + pipe_name(pch_transcoder)); } } diff --git a/drivers/gpu/drm/i915/intel_i2c.c b/drivers/gpu/drm/i915/intel_i2c.c index 6698826954e1..eb5827110d8f 100644 --- a/drivers/gpu/drm/i915/intel_i2c.c +++ b/drivers/gpu/drm/i915/intel_i2c.c @@ -649,7 +649,7 @@ static void gmbus_unlock_bus(struct i2c_adapter *adapter, mutex_unlock(&dev_priv->gmbus_mutex); } -const struct i2c_lock_operations gmbus_lock_ops = { +static const struct i2c_lock_operations gmbus_lock_ops = { .lock_bus = gmbus_lock_bus, .trylock_bus = gmbus_trylock_bus, .unlock_bus = gmbus_unlock_bus, diff --git a/drivers/gpu/drm/i915/intel_sdvo.c b/drivers/gpu/drm/i915/intel_sdvo.c index 3dc38c2ef4c3..29a3b0f5bec7 100644 --- a/drivers/gpu/drm/i915/intel_sdvo.c +++ b/drivers/gpu/drm/i915/intel_sdvo.c @@ -2980,7 +2980,7 @@ static void proxy_unlock_bus(struct i2c_adapter *adapter, sdvo->i2c->lock_ops->unlock_bus(sdvo->i2c, flags); } -const struct i2c_lock_operations proxy_lock_ops = { +static const struct i2c_lock_operations proxy_lock_ops = { .lock_bus = proxy_lock_bus, .trylock_bus = proxy_trylock_bus, .unlock_bus = proxy_unlock_bus, diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h index ec63bc5e9de7..8cbaeec090c9 100644 --- a/drivers/gpu/drm/radeon/radeon.h +++ b/drivers/gpu/drm/radeon/radeon.h @@ -924,7 +924,7 @@ struct radeon_vm_id { struct radeon_vm { struct mutex mutex; - struct rb_root va; + struct rb_root_cached va; /* protecting invalidated and freed */ spinlock_t status_lock; diff --git a/drivers/gpu/drm/radeon/radeon_mn.c b/drivers/gpu/drm/radeon/radeon_mn.c index 896f2cf51e4e..1d62288b7ee3 100644 --- a/drivers/gpu/drm/radeon/radeon_mn.c +++ b/drivers/gpu/drm/radeon/radeon_mn.c @@ -50,7 +50,7 @@ struct radeon_mn { /* objects protected by lock */ struct mutex lock; - struct rb_root objects; + struct rb_root_cached objects; }; struct radeon_mn_node { @@ -75,8 +75,8 @@ static void radeon_mn_destroy(struct work_struct *work) mutex_lock(&rdev->mn_lock); mutex_lock(&rmn->lock); hash_del(&rmn->node); - rbtree_postorder_for_each_entry_safe(node, next_node, &rmn->objects, - it.rb) { + rbtree_postorder_for_each_entry_safe(node, next_node, + &rmn->objects.rb_root, it.rb) { interval_tree_remove(&node->it, &rmn->objects); list_for_each_entry_safe(bo, next_bo, &node->bos, mn_list) { @@ -205,7 +205,7 @@ static struct radeon_mn *radeon_mn_get(struct radeon_device *rdev) rmn->mm = mm; rmn->mn.ops = &radeon_mn_ops; mutex_init(&rmn->lock); - rmn->objects = RB_ROOT; + rmn->objects = RB_ROOT_CACHED; r = __mmu_notifier_register(&rmn->mn, mm); if (r) diff --git a/drivers/gpu/drm/radeon/radeon_vm.c b/drivers/gpu/drm/radeon/radeon_vm.c index 5e82b408d522..e5c0e635e371 100644 --- a/drivers/gpu/drm/radeon/radeon_vm.c +++ b/drivers/gpu/drm/radeon/radeon_vm.c @@ -1185,7 +1185,7 @@ int radeon_vm_init(struct radeon_device *rdev, struct radeon_vm *vm) vm->ids[i].last_id_use = NULL; } mutex_init(&vm->mutex); - vm->va = RB_ROOT; + vm->va = RB_ROOT_CACHED; spin_lock_init(&vm->status_lock); INIT_LIST_HEAD(&vm->invalidated); INIT_LIST_HEAD(&vm->freed); @@ -1232,10 +1232,11 @@ void radeon_vm_fini(struct radeon_device *rdev, struct radeon_vm *vm) struct radeon_bo_va *bo_va, *tmp; int i, r; - if (!RB_EMPTY_ROOT(&vm->va)) { + if (!RB_EMPTY_ROOT(&vm->va.rb_root)) { dev_err(rdev->dev, "still active bo inside vm\n"); } - rbtree_postorder_for_each_entry_safe(bo_va, tmp, &vm->va, it.rb) { + rbtree_postorder_for_each_entry_safe(bo_va, tmp, + &vm->va.rb_root, it.rb) { interval_tree_remove(&bo_va->it, &vm->va); r = radeon_bo_reserve(bo_va->bo, false); if (!r) { |