Merge tag 'topic/i915-gem-next-2021-03-26' of ssh://git.freedesktop.o…

…rg/git/drm/drm into drm-next

special i915-gem-next pull as requested

- Conversion to dma_resv_locking, obj->mm.lock is gone (Maarten, with
  help from Thomas Hellström)
- watchdog (Tvrtko, one patch to cancel individual request from Chris)
- legacy ioctl cleanup (Jason+Ashutosh)
- i915-gem TODO and RFC process doc (me)
- i915_ prefix for vma_lookup (Liam Howlett) just because I spotted it
  and put it in here too

Signed-off-by: Dave Airlie <airlied@redhat.com>

From: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/YF24MHoOSjpKFEXA@phenom.ffwll.local

Documentation/gpu/index.rst

@@ -16,6 +16,7 @@ Linux GPU Driver Developer's Guide
    vga-switcheroo
    vgaarbiter
    todo
+   rfc/index
 
 .. only::  subproject and html
 

Documentation/gpu/rfc/index.rst

@@ -0,0 +1,17 @@
+===============
+GPU RFC Section
+===============
+
+For complex work, especially new uapi, it is often good to nail the high level
+design issues before getting lost in the code details. This section is meant to
+host such documentation:
+
+* Each RFC should be a section in this file, explaining the goal and main design
+  considerations. Especially for uapi make sure you Cc: all relevant project
+  mailing lists and involved people outside of dri-devel.
+
+* For uapi structures add a file to this directory with and then pull the
+  kerneldoc in like with real uapi headers.
+
+* Once the code has landed move all the documentation to the right places in
+  the main core, helper or driver sections.

drivers/gpu/drm/i915/Kconfig.profile

@@ -1,3 +1,17 @@
+config DRM_I915_REQUEST_TIMEOUT
+	int "Default timeout for requests (ms)"
+	default 20000 # milliseconds
+	help
+	  Configures the default timeout after which any user submissions will
+	  be forcefully terminated.
+
+	  Beware setting this value lower, or close to heartbeat interval
+	  rounded to whole seconds times three, in order to avoid allowing
+	  misbehaving applications causing total rendering failure in unrelated
+	  clients.
+
+	  May be 0 to disable the timeout.
+
 config DRM_I915_FENCE_TIMEOUT
 	int "Timeout for unsignaled foreign fences (ms, jiffy granularity)"
 	default 10000 # milliseconds

drivers/gpu/drm/i915/Makefile

@@ -139,7 +139,6 @@ gem-y += \
 	gem/i915_gem_dmabuf.o \
 	gem/i915_gem_domain.o \
 	gem/i915_gem_execbuffer.o \
-	gem/i915_gem_fence.o \
 	gem/i915_gem_internal.o \
 	gem/i915_gem_object.o \
 	gem/i915_gem_object_blt.o \

drivers/gpu/drm/i915/TODO.txt

@@ -0,0 +1,41 @@
+gem/gt TODO items
+-----------------
+
+- For discrete memory manager, merge enough dg1 to be able to refactor it to
+  TTM. Then land pci ids (just in case that turns up an uapi problem). TTM has
+  improved a lot the past 2 years, there's no reason anymore not to use it.
+
+- Come up with a plan what to do with drm/scheduler and how to get there.
+
+- Roll out dma_fence critical section annotations.
+
+- There's a lot of complexity added past few years to make relocations faster.
+  That doesn't make sense given hw and gpu apis moved away from this model years
+  ago:
+  1. Land a modern pre-bound uapi like VM_BIND
+  2. Any complexity added in this area past few years which can't be justified
+  with VM_BIND using userspace should be removed. Looking at amdgpu dma_resv on
+  the bo and vm, plus some lru locks is all that needed. No complex rcu,
+  refcounts, caching, ... on everything.
+  This is the matching task on the vm side compared to ttm/dma_resv on the
+  backing storage side.
+
+- i915_sw_fence seems to be the main structure for the i915-gem dma_fence model.
+  How-to-dma_fence is core and drivers really shouldn't build their own world
+  here, treating everything else as a fixed platform. i915_sw_fence concepts
+  should be moved to dma_fence, drm/scheduler or atomic commit helpers. Or
+  removed if dri-devel consensus is that it's not a good idea. Once that's done
+  maybe even remove it if there's nothing left.
+
+Smaller things:
+- i915_utils.h needs to be moved to the right places.
+
+- dma_fence_work should be in drivers/dma-buf
+
+- i915_mm.c should be moved to the right places. Some of the helpers also look a
+  bit fishy:
+
+  https://lore.kernel.org/linux-mm/20210301083320.943079-1-hch@lst.de/
+
+- tasklet helpers in i915_gem.h also look a bit misplaced and should
+  probably be moved to tasklet headers.

drivers/gpu/drm/i915/display/intel_display.c

@@ -1091,6 +1091,7 @@ static bool intel_plane_uses_fence(const struct intel_plane_state *plane_state)
 
 struct i915_vma *
 intel_pin_and_fence_fb_obj(struct drm_framebuffer *fb,
+			   bool phys_cursor,
 			   const struct i915_ggtt_view *view,
 			   bool uses_fence,
 			   unsigned long *out_flags)
@@ -1099,14 +1100,19 @@ intel_pin_and_fence_fb_obj(struct drm_framebuffer *fb,
 	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct drm_i915_gem_object *obj = intel_fb_obj(fb);
 	intel_wakeref_t wakeref;
+	struct i915_gem_ww_ctx ww;
 	struct i915_vma *vma;
 	unsigned int pinctl;
 	u32 alignment;
+	int ret;
 
 	if (drm_WARN_ON(dev, !i915_gem_object_is_framebuffer(obj)))
 		return ERR_PTR(-EINVAL);
 
-	alignment = intel_surf_alignment(fb, 0);
+	if (phys_cursor)
+		alignment = intel_cursor_alignment(dev_priv);
+	else
+		alignment = intel_surf_alignment(fb, 0);
 	if (drm_WARN_ON(dev, alignment && !is_power_of_2(alignment)))
 		return ERR_PTR(-EINVAL);
 
@@ -1141,14 +1147,26 @@ intel_pin_and_fence_fb_obj(struct drm_framebuffer *fb,
 	if (HAS_GMCH(dev_priv))
 		pinctl |= PIN_MAPPABLE;
 
-	vma = i915_gem_object_pin_to_display_plane(obj,
-						   alignment, view, pinctl);
-	if (IS_ERR(vma))
+	i915_gem_ww_ctx_init(&ww, true);
+retry:
+	ret = i915_gem_object_lock(obj, &ww);
+	if (!ret && phys_cursor)
+		ret = i915_gem_object_attach_phys(obj, alignment);
+	if (!ret)
+		ret = i915_gem_object_pin_pages(obj);
+	if (ret)
 		goto err;
 
-	if (uses_fence && i915_vma_is_map_and_fenceable(vma)) {
-		int ret;
+	if (!ret) {
+		vma = i915_gem_object_pin_to_display_plane(obj, &ww, alignment,
+							   view, pinctl);
+		if (IS_ERR(vma)) {
+			ret = PTR_ERR(vma);
+			goto err_unpin;
+		}
+	}
 
+	if (uses_fence && i915_vma_is_map_and_fenceable(vma)) {
 		/*
 		 * Install a fence for tiled scan-out. Pre-i965 always needs a
 		 * fence, whereas 965+ only requires a fence if using
@@ -1169,16 +1187,28 @@ intel_pin_and_fence_fb_obj(struct drm_framebuffer *fb,
 		ret = i915_vma_pin_fence(vma);
 		if (ret != 0 && INTEL_GEN(dev_priv) < 4) {
 			i915_vma_unpin(vma);
-			vma = ERR_PTR(ret);
-			goto err;
+			goto err_unpin;
 		}
+		ret = 0;
 
-		if (ret == 0 && vma->fence)
+		if (vma->fence)
 			*out_flags |= PLANE_HAS_FENCE;
 	}
 
 	i915_vma_get(vma);
+
+err_unpin:
+	i915_gem_object_unpin_pages(obj);
 err:
+	if (ret == -EDEADLK) {
+		ret = i915_gem_ww_ctx_backoff(&ww);
+		if (!ret)
+			goto retry;
+	}
+	i915_gem_ww_ctx_fini(&ww);
+	if (ret)
+		vma = ERR_PTR(ret);
+
 	atomic_dec(&dev_priv->gpu_error.pending_fb_pin);
 	intel_runtime_pm_put(&dev_priv->runtime_pm, wakeref);
 	return vma;
@@ -11333,19 +11363,11 @@ int intel_plane_pin_fb(struct intel_plane_state *plane_state)
 	struct drm_i915_private *dev_priv = to_i915(plane->base.dev);
 	struct drm_framebuffer *fb = plane_state->hw.fb;
 	struct i915_vma *vma;
+	bool phys_cursor =
+		plane->id == PLANE_CURSOR &&
+		INTEL_INFO(dev_priv)->display.cursor_needs_physical;
 
-	if (plane->id == PLANE_CURSOR &&
-	    INTEL_INFO(dev_priv)->display.cursor_needs_physical) {
-		struct drm_i915_gem_object *obj = intel_fb_obj(fb);
-		const int align = intel_cursor_alignment(dev_priv);
-		int err;
-
-		err = i915_gem_object_attach_phys(obj, align);
-		if (err)
-			return err;
-	}
-
-	vma = intel_pin_and_fence_fb_obj(fb,
+	vma = intel_pin_and_fence_fb_obj(fb, phys_cursor,
 					 &plane_state->view,
 					 intel_plane_uses_fence(plane_state),
 					 &plane_state->flags);
@@ -11437,13 +11459,8 @@ intel_prepare_plane_fb(struct drm_plane *_plane,
 	if (!obj)
 		return 0;
 
-	ret = i915_gem_object_pin_pages(obj);
-	if (ret)
-		return ret;
 
 	ret = intel_plane_pin_fb(new_plane_state);
-
-	i915_gem_object_unpin_pages(obj);
 	if (ret)
 		return ret;
 
@@ -11905,7 +11922,7 @@ static int intel_user_framebuffer_create_handle(struct drm_framebuffer *fb,
 	struct drm_i915_gem_object *obj = intel_fb_obj(fb);
 	struct drm_i915_private *i915 = to_i915(obj->base.dev);
 
-	if (obj->userptr.mm) {
+	if (i915_gem_object_is_userptr(obj)) {
 		drm_dbg(&i915->drm,
 			"attempting to use a userptr for a framebuffer, denied\n");
 		return -EINVAL;

drivers/gpu/drm/i915/display/intel_display.h

@@ -573,7 +573,7 @@ void intel_release_load_detect_pipe(struct drm_connector *connector,
 				    struct intel_load_detect_pipe *old,
 				    struct drm_modeset_acquire_ctx *ctx);
 struct i915_vma *
-intel_pin_and_fence_fb_obj(struct drm_framebuffer *fb,
+intel_pin_and_fence_fb_obj(struct drm_framebuffer *fb, bool phys_cursor,
 			   const struct i915_ggtt_view *view,
 			   bool uses_fence,
 			   unsigned long *out_flags);

drivers/gpu/drm/i915/display/intel_dsb.c

@@ -293,7 +293,7 @@ void intel_dsb_prepare(struct intel_crtc_state *crtc_state)
 		goto out;
 	}
 
-	buf = i915_gem_object_pin_map(vma->obj, I915_MAP_WC);
+	buf = i915_gem_object_pin_map_unlocked(vma->obj, I915_MAP_WC);
 	if (IS_ERR(buf)) {
 		drm_err(&i915->drm, "Command buffer creation failed\n");
 		i915_vma_unpin_and_release(&vma, I915_VMA_RELEASE_MAP);

drivers/gpu/drm/i915/display/intel_fbdev.c

@@ -211,7 +211,7 @@ static int intelfb_create(struct drm_fb_helper *helper,
 	 * This also validates that any existing fb inherited from the
 	 * BIOS is suitable for own access.
 	 */
-	vma = intel_pin_and_fence_fb_obj(&ifbdev->fb->base,
+	vma = intel_pin_and_fence_fb_obj(&ifbdev->fb->base, false,
 					 &view, false, &flags);
 	if (IS_ERR(vma)) {
 		ret = PTR_ERR(vma);

drivers/gpu/drm/i915/display/intel_overlay.c

@@ -755,6 +755,32 @@ static u32 overlay_cmd_reg(struct drm_intel_overlay_put_image *params)
 	return cmd;
 }
 
+static struct i915_vma *intel_overlay_pin_fb(struct drm_i915_gem_object *new_bo)
+{
+	struct i915_gem_ww_ctx ww;
+	struct i915_vma *vma;
+	int ret;
+
+	i915_gem_ww_ctx_init(&ww, true);
+retry:
+	ret = i915_gem_object_lock(new_bo, &ww);
+	if (!ret) {
+		vma = i915_gem_object_pin_to_display_plane(new_bo, &ww, 0,
+							   NULL, PIN_MAPPABLE);
+		ret = PTR_ERR_OR_ZERO(vma);
+	}
+	if (ret == -EDEADLK) {
+		ret = i915_gem_ww_ctx_backoff(&ww);
+		if (!ret)
+			goto retry;
+	}
+	i915_gem_ww_ctx_fini(&ww);
+	if (ret)
+		return ERR_PTR(ret);
+
+	return vma;
+}
+
 static int intel_overlay_do_put_image(struct intel_overlay *overlay,
 				      struct drm_i915_gem_object *new_bo,
 				      struct drm_intel_overlay_put_image *params)
@@ -776,12 +802,10 @@ static int intel_overlay_do_put_image(struct intel_overlay *overlay,
 
 	atomic_inc(&dev_priv->gpu_error.pending_fb_pin);
 
-	vma = i915_gem_object_pin_to_display_plane(new_bo,
-						   0, NULL, PIN_MAPPABLE);
-	if (IS_ERR(vma)) {
-		ret = PTR_ERR(vma);
+	vma = intel_overlay_pin_fb(new_bo);
+	if (IS_ERR(vma))
 		goto out_pin_section;
-	}
+
 	i915_gem_object_flush_frontbuffer(new_bo, ORIGIN_DIRTYFB);
 
 	if (!overlay->active) {

drivers/gpu/drm/i915/gem/i915_gem_clflush.c

@@ -27,15 +27,8 @@ static void __do_clflush(struct drm_i915_gem_object *obj)
 static int clflush_work(struct dma_fence_work *base)
 {
 	struct clflush *clflush = container_of(base, typeof(*clflush), base);
-	struct drm_i915_gem_object *obj = clflush->obj;
-	int err;
 
-	err = i915_gem_object_pin_pages(obj);
-	if (err)
-		return err;
-
-	__do_clflush(obj);
-	i915_gem_object_unpin_pages(obj);
+	__do_clflush(clflush->obj);
 
 	return 0;
 }
@@ -44,6 +37,7 @@ static void clflush_release(struct dma_fence_work *base)
 {
 	struct clflush *clflush = container_of(base, typeof(*clflush), base);
 
+	i915_gem_object_unpin_pages(clflush->obj);
 	i915_gem_object_put(clflush->obj);
 }
 
@@ -63,6 +57,11 @@ static struct clflush *clflush_work_create(struct drm_i915_gem_object *obj)
 	if (!clflush)
 		return NULL;
 
+	if (__i915_gem_object_get_pages(obj) < 0) {
+		kfree(clflush);
+		return NULL;
+	}
+
 	dma_fence_work_init(&clflush->base, &clflush_ops);
 	clflush->obj = i915_gem_object_get(obj); /* obj <-> clflush cycle */