diff options
Diffstat (limited to 'drivers/gpu/drm/i915/i915_gem_execbuffer.c')
-rw-r--r-- | drivers/gpu/drm/i915/i915_gem_execbuffer.c | 326 |
1 files changed, 199 insertions, 127 deletions
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c index d269ecf46e2..20fef6c5026 100644 --- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c @@ -35,6 +35,9 @@ #define __EXEC_OBJECT_HAS_PIN (1<<31) #define __EXEC_OBJECT_HAS_FENCE (1<<30) +#define __EXEC_OBJECT_NEEDS_BIAS (1<<28) + +#define BATCH_OFFSET_BIAS (256*1024) struct eb_vmas { struct list_head vmas; @@ -91,6 +94,7 @@ eb_lookup_vmas(struct eb_vmas *eb, struct i915_address_space *vm, struct drm_file *file) { + struct drm_i915_private *dev_priv = vm->dev->dev_private; struct drm_i915_gem_object *obj; struct list_head objects; int i, ret; @@ -125,6 +129,20 @@ eb_lookup_vmas(struct eb_vmas *eb, i = 0; while (!list_empty(&objects)) { struct i915_vma *vma; + struct i915_address_space *bind_vm = vm; + + if (exec[i].flags & EXEC_OBJECT_NEEDS_GTT && + USES_FULL_PPGTT(vm->dev)) { + ret = -EINVAL; + goto err; + } + + /* If we have secure dispatch, or the userspace assures us that + * they know what they're doing, use the GGTT VM. + */ + if (((args->flags & I915_EXEC_SECURE) && + (i == (args->buffer_count - 1)))) + bind_vm = &dev_priv->gtt.base; obj = list_first_entry(&objects, struct drm_i915_gem_object, @@ -138,7 +156,7 @@ eb_lookup_vmas(struct eb_vmas *eb, * from the (obj, vm) we don't run the risk of creating * duplicated vmas for the same vm. */ - vma = i915_gem_obj_lookup_or_create_vma(obj, vm); + vma = i915_gem_obj_lookup_or_create_vma(obj, bind_vm); if (IS_ERR(vma)) { DRM_DEBUG("Failed to lookup VMA\n"); ret = PTR_ERR(vma); @@ -217,7 +235,7 @@ i915_gem_execbuffer_unreserve_vma(struct i915_vma *vma) i915_gem_object_unpin_fence(obj); if (entry->flags & __EXEC_OBJECT_HAS_PIN) - i915_gem_object_unpin(obj); + vma->pin_count--; entry->flags &= ~(__EXEC_OBJECT_HAS_FENCE | __EXEC_OBJECT_HAS_PIN); } @@ -327,8 +345,7 @@ relocate_entry_gtt(struct drm_i915_gem_object *obj, static int i915_gem_execbuffer_relocate_entry(struct drm_i915_gem_object *obj, struct eb_vmas *eb, - struct drm_i915_gem_relocation_entry *reloc, - struct i915_address_space *vm) + struct drm_i915_gem_relocation_entry *reloc) { struct drm_device *dev = obj->base.dev; struct drm_gem_object *target_obj; @@ -352,8 +369,10 @@ i915_gem_execbuffer_relocate_entry(struct drm_i915_gem_object *obj, if (unlikely(IS_GEN6(dev) && reloc->write_domain == I915_GEM_DOMAIN_INSTRUCTION && !target_i915_obj->has_global_gtt_mapping)) { - i915_gem_gtt_bind_object(target_i915_obj, - target_i915_obj->cache_level); + struct i915_vma *vma = + list_first_entry(&target_i915_obj->vma_list, + typeof(*vma), vma_link); + vma->bind_vma(vma, target_i915_obj->cache_level, GLOBAL_BIND); } /* Validate that the target is in a valid r/w GPU domain */ @@ -451,8 +470,7 @@ i915_gem_execbuffer_relocate_vma(struct i915_vma *vma, do { u64 offset = r->presumed_offset; - ret = i915_gem_execbuffer_relocate_entry(vma->obj, eb, r, - vma->vm); + ret = i915_gem_execbuffer_relocate_entry(vma->obj, eb, r); if (ret) return ret; @@ -481,8 +499,7 @@ i915_gem_execbuffer_relocate_vma_slow(struct i915_vma *vma, int i, ret; for (i = 0; i < entry->relocation_count; i++) { - ret = i915_gem_execbuffer_relocate_entry(vma->obj, eb, &relocs[i], - vma->vm); + ret = i915_gem_execbuffer_relocate_entry(vma->obj, eb, &relocs[i]); if (ret) return ret; } @@ -527,21 +544,28 @@ i915_gem_execbuffer_reserve_vma(struct i915_vma *vma, struct intel_ring_buffer *ring, bool *need_reloc) { - struct drm_i915_private *dev_priv = ring->dev->dev_private; + struct drm_i915_gem_object *obj = vma->obj; struct drm_i915_gem_exec_object2 *entry = vma->exec_entry; bool has_fenced_gpu_access = INTEL_INFO(ring->dev)->gen < 4; - bool need_fence, need_mappable; - struct drm_i915_gem_object *obj = vma->obj; + bool need_fence; + uint64_t flags; int ret; + flags = 0; + need_fence = has_fenced_gpu_access && entry->flags & EXEC_OBJECT_NEEDS_FENCE && obj->tiling_mode != I915_TILING_NONE; - need_mappable = need_fence || need_reloc_mappable(vma); + if (need_fence || need_reloc_mappable(vma)) + flags |= PIN_MAPPABLE; + + if (entry->flags & EXEC_OBJECT_NEEDS_GTT) + flags |= PIN_GLOBAL; + if (entry->flags & __EXEC_OBJECT_NEEDS_BIAS) + flags |= BATCH_OFFSET_BIAS | PIN_OFFSET_BIAS; - ret = i915_gem_object_pin(obj, vma->vm, entry->alignment, need_mappable, - false); + ret = i915_gem_object_pin(obj, vma->vm, entry->alignment, flags); if (ret) return ret; @@ -560,14 +584,6 @@ i915_gem_execbuffer_reserve_vma(struct i915_vma *vma, } } - /* Ensure ppgtt mapping exists if needed */ - if (dev_priv->mm.aliasing_ppgtt && !obj->has_aliasing_ppgtt_mapping) { - i915_ppgtt_bind_object(dev_priv->mm.aliasing_ppgtt, - obj, obj->cache_level); - - obj->has_aliasing_ppgtt_mapping = 1; - } - if (entry->offset != vma->node.start) { entry->offset = vma->node.start; *need_reloc = true; @@ -578,13 +594,39 @@ i915_gem_execbuffer_reserve_vma(struct i915_vma *vma, obj->base.pending_write_domain = I915_GEM_DOMAIN_RENDER; } - if (entry->flags & EXEC_OBJECT_NEEDS_GTT && - !obj->has_global_gtt_mapping) - i915_gem_gtt_bind_object(obj, obj->cache_level); - return 0; } +static bool +eb_vma_misplaced(struct i915_vma *vma, bool has_fenced_gpu_access) +{ + struct drm_i915_gem_exec_object2 *entry = vma->exec_entry; + struct drm_i915_gem_object *obj = vma->obj; + bool need_fence, need_mappable; + + need_fence = + has_fenced_gpu_access && + entry->flags & EXEC_OBJECT_NEEDS_FENCE && + obj->tiling_mode != I915_TILING_NONE; + need_mappable = need_fence || need_reloc_mappable(vma); + + WARN_ON((need_mappable || need_fence) && + !i915_is_ggtt(vma->vm)); + + if (entry->alignment && + vma->node.start & (entry->alignment - 1)) + return true; + + if (need_mappable && !obj->map_and_fenceable) + return true; + + if (entry->flags & __EXEC_OBJECT_NEEDS_BIAS && + vma->node.start < BATCH_OFFSET_BIAS) + return true; + + return false; +} + static int i915_gem_execbuffer_reserve(struct intel_ring_buffer *ring, struct list_head *vmas, @@ -646,26 +688,10 @@ i915_gem_execbuffer_reserve(struct intel_ring_buffer *ring, /* Unbind any ill-fitting objects or pin. */ list_for_each_entry(vma, vmas, exec_list) { - struct drm_i915_gem_exec_object2 *entry = vma->exec_entry; - bool need_fence, need_mappable; - - obj = vma->obj; - if (!drm_mm_node_allocated(&vma->node)) continue; - need_fence = - has_fenced_gpu_access && - entry->flags & EXEC_OBJECT_NEEDS_FENCE && - obj->tiling_mode != I915_TILING_NONE; - need_mappable = need_fence || need_reloc_mappable(vma); - - WARN_ON((need_mappable || need_fence) && - !i915_is_ggtt(vma->vm)); - - if ((entry->alignment && - vma->node.start & (entry->alignment - 1)) || - (need_mappable && !obj->map_and_fenceable)) + if (eb_vma_misplaced(vma, has_fenced_gpu_access)) ret = i915_vma_unbind(vma); else ret = i915_gem_execbuffer_reserve_vma(vma, ring, need_relocs); @@ -766,9 +792,9 @@ i915_gem_execbuffer_relocate_slow(struct drm_device *dev, * relocations were valid. */ for (j = 0; j < exec[i].relocation_count; j++) { - if (copy_to_user(&user_relocs[j].presumed_offset, - &invalid_offset, - sizeof(invalid_offset))) { + if (__copy_to_user(&user_relocs[j].presumed_offset, + &invalid_offset, + sizeof(invalid_offset))) { ret = -EFAULT; mutex_lock(&dev->struct_mutex); goto err; @@ -891,7 +917,7 @@ validate_exec_list(struct drm_i915_gem_exec_object2 *exec, if (!access_ok(VERIFY_WRITE, ptr, length)) return -EFAULT; - if (likely(!i915_prefault_disable)) { + if (likely(!i915.prefault_disable)) { if (fault_in_multipages_readable(ptr, length)) return -EFAULT; } @@ -900,22 +926,27 @@ validate_exec_list(struct drm_i915_gem_exec_object2 *exec, return 0; } -static int +static struct i915_hw_context * i915_gem_validate_context(struct drm_device *dev, struct drm_file *file, - const u32 ctx_id) + struct intel_ring_buffer *ring, const u32 ctx_id) { + struct i915_hw_context *ctx = NULL; struct i915_ctx_hang_stats *hs; - hs = i915_gem_context_get_hang_stats(dev, file, ctx_id); - if (IS_ERR(hs)) - return PTR_ERR(hs); + if (ring->id != RCS && ctx_id != DEFAULT_CONTEXT_ID) + return ERR_PTR(-EINVAL); + ctx = i915_gem_context_get(file->driver_priv, ctx_id); + if (IS_ERR(ctx)) + return ctx; + + hs = &ctx->hang_stats; if (hs->banned) { DRM_DEBUG("Context %u tried to submit while banned\n", ctx_id); - return -EIO; + return ERR_PTR(-EIO); } - return 0; + return ctx; } static void @@ -939,7 +970,9 @@ i915_gem_execbuffer_move_to_active(struct list_head *vmas, if (obj->base.write_domain) { obj->dirty = 1; obj->last_write_seqno = intel_ring_get_seqno(ring); - if (obj->pin_count) /* check for potential scanout */ + /* check for potential scanout */ + if (i915_gem_obj_ggtt_bound(obj) && + i915_gem_obj_to_ggtt(obj)->pin_count) intel_mark_fb_busy(obj, ring); } @@ -964,7 +997,7 @@ static int i915_reset_gen7_sol_offsets(struct drm_device *dev, struct intel_ring_buffer *ring) { - drm_i915_private_t *dev_priv = dev->dev_private; + struct drm_i915_private *dev_priv = dev->dev_private; int ret, i; if (!IS_GEN7(dev) || ring != &dev_priv->ring[RCS]) @@ -985,20 +1018,40 @@ i915_reset_gen7_sol_offsets(struct drm_device *dev, return 0; } +static struct drm_i915_gem_object * +eb_get_batch(struct eb_vmas *eb) +{ + struct i915_vma *vma = list_entry(eb->vmas.prev, typeof(*vma), exec_list); + + /* + * SNA is doing fancy tricks with compressing batch buffers, which leads + * to negative relocation deltas. Usually that works out ok since the + * relocate address is still positive, except when the batch is placed + * very low in the GTT. Ensure this doesn't happen. + * + * Note that actual hangs have only been observed on gen7, but for + * paranoia do it everywhere. + */ + vma->exec_entry->flags |= __EXEC_OBJECT_NEEDS_BIAS; + + return vma->obj; +} + static int i915_gem_do_execbuffer(struct drm_device *dev, void *data, struct drm_file *file, struct drm_i915_gem_execbuffer2 *args, - struct drm_i915_gem_exec_object2 *exec, - struct i915_address_space *vm) + struct drm_i915_gem_exec_object2 *exec) { - drm_i915_private_t *dev_priv = dev->dev_private; + struct drm_i915_private *dev_priv = dev->dev_private; struct eb_vmas *eb; struct drm_i915_gem_object *batch_obj; struct drm_clip_rect *cliprects = NULL; struct intel_ring_buffer *ring; + struct i915_hw_context *ctx; + struct i915_address_space *vm; const u32 ctx_id = i915_execbuffer2_get_context_id(*args); - u32 exec_start, exec_len; + u32 exec_start = args->batch_start_offset, exec_len; u32 mask, flags; int ret, mode, i; bool need_relocs; @@ -1020,41 +1073,17 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data, if (args->flags & I915_EXEC_IS_PINNED) flags |= I915_DISPATCH_PINNED; - switch (args->flags & I915_EXEC_RING_MASK) { - case I915_EXEC_DEFAULT: - case I915_EXEC_RENDER: - ring = &dev_priv->ring[RCS]; - break; - case I915_EXEC_BSD: - ring = &dev_priv->ring[VCS]; - if (ctx_id != DEFAULT_CONTEXT_ID) { - DRM_DEBUG("Ring %s doesn't support contexts\n", - ring->name); - return -EPERM; - } - break; - case I915_EXEC_BLT: - ring = &dev_priv->ring[BCS]; - if (ctx_id != DEFAULT_CONTEXT_ID) { - DRM_DEBUG("Ring %s doesn't support contexts\n", - ring->name); - return -EPERM; - } - break; - case I915_EXEC_VEBOX: - ring = &dev_priv->ring[VECS]; - if (ctx_id != DEFAULT_CONTEXT_ID) { - DRM_DEBUG("Ring %s doesn't support contexts\n", - ring->name); - return -EPERM; - } - break; - - default: + if ((args->flags & I915_EXEC_RING_MASK) > I915_NUM_RINGS) { DRM_DEBUG("execbuf with unknown ring: %d\n", (int)(args->flags & I915_EXEC_RING_MASK)); return -EINVAL; } + + if ((args->flags & I915_EXEC_RING_MASK) == I915_EXEC_DEFAULT) + ring = &dev_priv->ring[RCS]; + else + ring = &dev_priv->ring[(args->flags & I915_EXEC_RING_MASK) - 1]; + if (!intel_ring_initialized(ring)) { DRM_DEBUG("execbuf with invalid ring: %d\n", (int)(args->flags & I915_EXEC_RING_MASK)); @@ -1136,11 +1165,18 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data, goto pre_mutex_err; } - ret = i915_gem_validate_context(dev, file, ctx_id); - if (ret) { + ctx = i915_gem_validate_context(dev, file, ring, ctx_id); + if (IS_ERR(ctx)) { mutex_unlock(&dev->struct_mutex); + ret = PTR_ERR(ctx); goto pre_mutex_err; - } + } + + i915_gem_context_reference(ctx); + + vm = ctx->vm; + if (!USES_FULL_PPGTT(dev)) + vm = &dev_priv->gtt.base; eb = eb_create(args); if (eb == NULL) { @@ -1155,7 +1191,7 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data, goto err; /* take note of the batch buffer before we might reorder the lists */ - batch_obj = list_entry(eb->vmas.prev, struct i915_vma, exec_list)->obj; + batch_obj = eb_get_batch(eb); /* Move the objects en-masse into the GTT, evicting if necessary. */ need_relocs = (args->flags & I915_EXEC_NO_RELOC) == 0; @@ -1184,17 +1220,46 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data, } batch_obj->base.pending_read_domains |= I915_GEM_DOMAIN_COMMAND; + if (i915_needs_cmd_parser(ring)) { + ret = i915_parse_cmds(ring, + batch_obj, + args->batch_start_offset, + file->is_master); + if (ret) + goto err; + + /* + * XXX: Actually do this when enabling batch copy... + * + * Set the DISPATCH_SECURE bit to remove the NON_SECURE bit + * from MI_BATCH_BUFFER_START commands issued in the + * dispatch_execbuffer implementations. We specifically don't + * want that set when the command parser is enabled. + */ + } + /* snb/ivb/vlv conflate the "batch in ppgtt" bit with the "non-secure * batch" bit. Hence we need to pin secure batches into the global gtt. * hsw should have this fixed, but bdw mucks it up again. */ - if (flags & I915_DISPATCH_SECURE && !batch_obj->has_global_gtt_mapping) - i915_gem_gtt_bind_object(batch_obj, batch_obj->cache_level); + if (flags & I915_DISPATCH_SECURE && + !batch_obj->has_global_gtt_mapping) { + /* When we have multiple VMs, we'll need to make sure that we + * allocate space first */ + struct i915_vma *vma = i915_gem_obj_to_ggtt(batch_obj); + BUG_ON(!vma); + vma->bind_vma(vma, batch_obj->cache_level, GLOBAL_BIND); + } + + if (flags & I915_DISPATCH_SECURE) + exec_start += i915_gem_obj_ggtt_offset(batch_obj); + else + exec_start += i915_gem_obj_offset(batch_obj, vm); ret = i915_gem_execbuffer_move_to_gpu(ring, &eb->vmas); if (ret) goto err; - ret = i915_switch_context(ring, file, ctx_id); + ret = i915_switch_context(ring, ctx); if (ret) goto err; @@ -1219,8 +1284,7 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data, goto err; } - exec_start = i915_gem_obj_offset(batch_obj, vm) + - args->batch_start_offset; + exec_len = args->batch_len; if (cliprects) { for (i = 0; i < args->num_cliprects; i++) { @@ -1249,6 +1313,8 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data, i915_gem_execbuffer_retire_commands(dev, file, ring, batch_obj); err: + /* the request owns the ref now */ + i915_gem_context_unreference(ctx); eb_destroy(eb); mutex_unlock(&dev->struct_mutex); @@ -1270,7 +1336,6 @@ int i915_gem_execbuffer(struct drm_device *dev, void *data, struct drm_file *file) { - struct drm_i915_private *dev_priv = dev->dev_private; struct drm_i915_gem_execbuffer *args = data; struct drm_i915_gem_execbuffer2 exec2; struct drm_i915_gem_exec_object *exec_list = NULL; @@ -1326,21 +1391,23 @@ i915_gem_execbuffer(struct drm_device *dev, void *data, exec2.flags = I915_EXEC_RENDER; i915_execbuffer2_set_context_id(exec2, 0); - ret = i915_gem_do_execbuffer(dev, data, file, &exec2, exec2_list, - &dev_priv->gtt.base); + ret = i915_gem_do_execbuffer(dev, data, file, &exec2, exec2_list); if (!ret) { + struct drm_i915_gem_exec_object __user *user_exec_list = + to_user_ptr(args->buffers_ptr); + /* Copy the new buffer offsets back to the user's exec list. */ - for (i = 0; i < args->buffer_count; i++) - exec_list[i].offset = exec2_list[i].offset; - /* ... and back out to userspace */ - ret = copy_to_user(to_user_ptr(args->buffers_ptr), - exec_list, - sizeof(*exec_list) * args->buffer_count); - if (ret) { - ret = -EFAULT; - DRM_DEBUG("failed to copy %d exec entries " - "back to user (%d)\n", - args->buffer_count, ret); + for (i = 0; i < args->buffer_count; i++) { + ret = __copy_to_user(&user_exec_list[i].offset, + &exec2_list[i].offset, + sizeof(user_exec_list[i].offset)); + if (ret) { + ret = -EFAULT; + DRM_DEBUG("failed to copy %d exec entries " + "back to user (%d)\n", + args->buffer_count, ret); + break; + } } } @@ -1353,7 +1420,6 @@ int i915_gem_execbuffer2(struct drm_device *dev, void *data, struct drm_file *file) { - struct drm_i915_private *dev_priv = dev->dev_private; struct drm_i915_gem_execbuffer2 *args = data; struct drm_i915_gem_exec_object2 *exec2_list = NULL; int ret; @@ -1384,18 +1450,24 @@ i915_gem_execbuffer2(struct drm_device *dev, void *data, return -EFAULT; } - ret = i915_gem_do_execbuffer(dev, data, file, args, exec2_list, - &dev_priv->gtt.base); + ret = i915_gem_do_execbuffer(dev, data, file, args, exec2_list); if (!ret) { /* Copy the new buffer offsets back to the user's exec list. */ - ret = copy_to_user(to_user_ptr(args->buffers_ptr), - exec2_list, - sizeof(*exec2_list) * args->buffer_count); - if (ret) { - ret = -EFAULT; - DRM_DEBUG("failed to copy %d exec entries " - "back to user (%d)\n", - args->buffer_count, ret); + struct drm_i915_gem_exec_object2 *user_exec_list = + to_user_ptr(args->buffers_ptr); + int i; + + for (i = 0; i < args->buffer_count; i++) { + ret = __copy_to_user(&user_exec_list[i].offset, + &exec2_list[i].offset, + sizeof(user_exec_list[i].offset)); + if (ret) { + ret = -EFAULT; + DRM_DEBUG("failed to copy %d exec entries " + "back to user\n", + args->buffer_count); + break; + } } } |