Merge tag 'drm-next-2023-08-30' of git://anongit.freedesktop.org/drm/drm

Pull drm updates from Dave Airlie:
 "The drm core grew a new generic gpu virtual address manager, and new
  execution locking helpers. These are used by nouveau now to provide
  uAPI support for the userspace Vulkan driver. AMD had a bunch of new
  IP core support, loads of refactoring around fbdev, but mostly just
  the usual amount of stuff across the board.

  core:
   - fix gfp flags in drmm_kmalloc

  gpuva:
   - add new generic GPU VA manager (for nouveau initially)

  syncobj:
   - add new DRM_IOCTL_SYNCOBJ_EVENTFD ioctl

  dma-buf:
   - acquire resv lock for mmap() in exporters
   - support dma-buf self import automatically
   - docs fixes

  backlight:
   - fix fbdev interactions

  atomic:
   - improve logging

  prime:
   - remove struct gem_prim_mmap plus driver updates

  gem:
   - drm_exec: add locking over multiple GEM objects
   - fix lockdep checking

  fbdev:
   - make fbdev userspace interfaces optional
   - use linux device instead of fbdev device
   - use deferred i/o helper macros in various drivers
   - Make FB core selectable without drivers
   - Remove obsolete flags FBINFO_DEFAULT and FBINFO_FLAG_DEFAULT
   - Add helper macros and Kconfig tokens for DMA-allocated framebuffer

  ttm:
   - support init_on_free
   - swapout fixes

  panel:
   - panel-edp: Support AUO B116XAB01.4
   - Support Visionox R66451 plus DT bindings
   - ld9040:
      - Backlight support
      - magic improved
      - Kconfig fix
   - Convert to of_device_get_match_data()
   - Fix Kconfig dependencies
   - simple:
      - Set bpc value to fix warning
      - Set connector type for AUO T215HVN01
      - Support Innolux G156HCE-L01 plus DT bindings
   - ili9881: Support TDO TL050HDV35 LCD panel plus DT bindings
   - startek: Support KD070FHFID015 MIPI-DSI panel plus DT bindings
   - sitronix-st7789v:
      - Support Inanbo T28CP45TN89 plus DT bindings
      - Support EDT ET028013DMA plus DT bindings
      - Various cleanups
   - edp: Add timings for N140HCA-EAC
   - Allow panels and touchscreens to power sequence together
   - Fix Innolux G156HCE-L01 LVDS clock

  bridge:
   - debugfs for chains support
   - dw-hdmi:
      - Improve support for YUV420 bus format
      - CEC suspend/resume
      - update EDID on HDMI detect
   - dw-mipi-dsi: Fix enable/disable of DSI controller
   - lt9611uxc: Use MODULE_FIRMWARE()
   - ps8640: Remove broken EDID code
   - samsung-dsim: Fix command transfer
   - tc358764:
      - Handle HS/VS polarity
      - Use BIT() macro
      - Various cleanups
   - adv7511: Fix low refresh rate
   - anx7625:
      - Switch to macros instead of hardcoded values
      - locking fixes
   - tc358767: fix hardware delays
   - sitronix-st7789v:
      - Support panel orientation
      - Support rotation property
      - Add support for Jasonic JT240MHQS-HWT-EK-E3 plus DT bindings

  amdgpu:
   - SDMA 6.1.0 support
   - HDP 6.1 support
   - SMUIO 14.0 support
   - PSP 14.0 support
   - IH 6.1 support
   - Lots of checkpatch cleanups
   - GFX 9.4.3 updates
   - Add USB PD and IFWI flashing documentation
   - GPUVM updates
   - RAS fixes
   - DRR fixes
   - FAMS fixes
   - Virtual display fixes
   - Soft IH fixes
   - SMU13 fixes
   - Rework PSP firmware loading for other IPs
   - Kernel doc fixes
   - DCN 3.0.1 fixes
   - LTTPR fixes
   - DP MST fixes
   - DCN 3.1.6 fixes
   - SMU 13.x fixes
   - PSP 13.x fixes
   - SubVP fixes
   - GC 9.4.3 fixes
   - Display bandwidth calculation fixes
   - VCN4 secure submission fixes
   - Allow building DC on RISC-V
   - Add visible FB info to bo_print_info
   - HBR3 fixes
   - GFX9 MCBP fix
   - GMC10 vmhub index fix
   - GMC11 vmhub index fix
   - Create a new doorbell manager
   - SR-IOV fixes
   - initial freesync panel replay support
   - revert zpos properly until igt regression is fixeed
   - use TTM to manage doorbell BAR
   - Expose both current and average power via hwmon if supported

  amdkfd:
   - Cleanup CRIU dma-buf handling
   - Use KIQ to unmap HIQ
   - GFX 9.4.3 debugger updates
   - GFX 9.4.2 debugger fixes
   - Enable cooperative groups fof gfx11
   - SVM fixes
   - Convert older APUs to use dGPU path like newer APUs
   - Drop IOMMUv2 path as it is no longer used
   - TBA fix for aldebaran

  i915:
   - ICL+ DSI modeset sequence
   - HDCP improvements
   - MTL display fixes and cleanups
   - HSW/BDW PSR1 restored
   - Init DDI ports in VBT order
   - General display refactors
   - Start using plane scale factor for relative data rate
   - Use shmem for dpt objects
   - Expose RPS thresholds in sysfs
   - Apply GuC SLPC min frequency softlimit correctly
   - Extend Wa_14015795083 to TGL, RKL, DG1 and ADL
   - Fix a VMA UAF for multi-gt platform
   - Do not use stolen on MTL due to HW bug
   - Check HuC and GuC version compatibility on MTL
   - avoid infinite GPU waits due to premature release of request memory
   - Fixes and updates for GSC memory allocation
   - Display SDVO fixes
   - Take stolen handling out of FBC code
   - Make i915_coherent_map_type GT-centric
   - Simplify shmem_create_from_object map_type

  msm:
   - SM6125 MDSS support
   - DPU: SM6125 DPU support
   - DSI: runtime PM support, burst mode support
   - DSI PHY: SM6125 support in 14nm DSI PHY driver
   - GPU: prepare for a7xx
   - fix a690 firmware
   - disable relocs on a6xx and newer

  radeon:
   - Lots of checkpatch cleanups

  ast:
   - improve device-model detection
   - Represent BMV as virtual connector
   - Report DP connection status

  nouveau:
   - add new exec/bind interface to support Vulkan
   - document some getparam ioctls
   - improve VRAM detection
   - various fixes/cleanups
   - workraound DPCD issues

  ivpu:
   - MMU updates
   - debugfs support
   - Support vpu4

  virtio:
   - add sync object support

  atmel-hlcdc:
   - Support inverted pixclock polarity

  etnaviv:
   - runtime PM cleanups
   - hang handling fixes

  exynos:
   - use fbdev DMA helpers
   - fix possible NULL ptr dereference

  komeda:
   - always attach encoder

  omapdrm:
   - use fbdev DMA helpers
ingenic:
   - kconfig regmap fixes

  loongson:
   - support display controller

  mediatek:
   - Small mtk-dpi cleanups
   - DisplayPort: support eDP and aux-bus
   - Fix coverity issues
   - Fix potential memory leak if vmap() fail

  mgag200:
   - minor fixes

  mxsfb:
   - support disabling overlay planes

  panfrost:
   - fix sync in IRQ handling

  ssd130x:
   - Support per-controller default resolution plus DT bindings
   - Reduce memory-allocation overhead
   - Improve intermediate buffer size computation
   - Fix allocation of temporary buffers
   - Fix pitch computation
   - Fix shadow plane allocation

  tegra:
   - use fbdev DMA helpers
   - Convert to devm_platform_ioremap_resource()
   - support bridge/connector
   - enable PM

  tidss:
   - Support TI AM625 plus DT bindings
   - Implement new connector model plus driver updates

  vkms:
   - improve write back support
   - docs fixes
   - support gamma LUT

  zynqmp-dpsub:
   - misc fixes"

* tag 'drm-next-2023-08-30' of git://anongit.freedesktop.org/drm/drm: (1327 commits)
  drm/gpuva_mgr: remove unused prev pointer in __drm_gpuva_sm_map()
  drm/tests/drm_kunit_helpers: Place correct function name in the comment header
  drm/nouveau: uapi: don't pass NO_PREFETCH flag implicitly
  drm/nouveau: uvmm: fix unset region pointer on remap
  drm/nouveau: sched: avoid job races between entities
  drm/i915: Fix HPD polling, reenabling the output poll work as needed
  drm: Add an HPD poll helper to reschedule the poll work
  drm/i915: Fix TLB-Invalidation seqno store
  drm/ttm/tests: Fix type conversion in ttm_pool_test
  drm/msm/a6xx: Bail out early if setting GPU OOB fails
  drm/msm/a6xx: Move LLC accessors to the common header
  drm/msm/a6xx: Introduce a6xx_llc_read
  drm/ttm/tests: Require MMU when testing
  drm/panel: simple: Fix Innolux G156HCE-L01 LVDS clock
  Revert "Revert "drm/amdgpu/display: change pipe policy for DCN 2.0""
  drm/amdgpu: Add memory vendor information
  drm/amd: flush any delayed gfxoff on suspend entry
  drm/amdgpu: skip fence GFX interrupts disable/enable for S0ix
  drm/amdgpu: Remove gfxoff check in GFX v9.4.3
  drm/amd/pm: Update pci link speed for smu v13.0.6
  ...

1 files changed, 244 insertions, 12 deletions

diff --git a/drivers/gpu/drm/virtio/virtgpu_submit.c b/drivers/gpu/drm/virtio/virtgpu_submit.c
index cf3c04b16a7a..3c00135ead45 100644
--- a/drivers/gpu/drm/virtio/virtgpu_submit.c
+++ b/drivers/gpu/drm/virtio/virtgpu_submit.c
@@ -14,11 +14,24 @@
 #include <linux/uaccess.h>
 
 #include <drm/drm_file.h>
+#include <drm/drm_syncobj.h>
 #include <drm/virtgpu_drm.h>
 
 #include "virtgpu_drv.h"
 
+struct virtio_gpu_submit_post_dep {
+	struct drm_syncobj *syncobj;
+	struct dma_fence_chain *chain;
+	u64 point;
+};
+
 struct virtio_gpu_submit {
+	struct virtio_gpu_submit_post_dep *post_deps;
+	unsigned int num_out_syncobjs;
+
+	struct drm_syncobj **in_syncobjs;
+	unsigned int num_in_syncobjs;
+
 	struct virtio_gpu_object_array *buflist;
 	struct drm_virtgpu_execbuffer *exbuf;
 	struct virtio_gpu_fence *out_fence;
@@ -59,18 +72,211 @@ static int virtio_gpu_dma_fence_wait(struct virtio_gpu_submit *submit,
 	return 0;
 }
 
+static void virtio_gpu_free_syncobjs(struct drm_syncobj **syncobjs,
+				     u32 nr_syncobjs)
+{
+	u32 i = nr_syncobjs;
+
+	while (i--) {
+		if (syncobjs[i])
+			drm_syncobj_put(syncobjs[i]);
+	}
+
+	kvfree(syncobjs);
+}
+
+static int
+virtio_gpu_parse_deps(struct virtio_gpu_submit *submit)
+{
+	struct drm_virtgpu_execbuffer *exbuf = submit->exbuf;
+	struct drm_virtgpu_execbuffer_syncobj syncobj_desc;
+	size_t syncobj_stride = exbuf->syncobj_stride;
+	u32 num_in_syncobjs = exbuf->num_in_syncobjs;
+	struct drm_syncobj **syncobjs;
+	int ret = 0, i;
+
+	if (!num_in_syncobjs)
+		return 0;
+
+	/*
+	 * kvalloc at first tries to allocate memory using kmalloc and
+	 * falls back to vmalloc only on failure. It also uses __GFP_NOWARN
+	 * internally for allocations larger than a page size, preventing
+	 * storm of KMSG warnings.
+	 */
+	syncobjs = kvcalloc(num_in_syncobjs, sizeof(*syncobjs), GFP_KERNEL);
+	if (!syncobjs)
+		return -ENOMEM;
+
+	for (i = 0; i < num_in_syncobjs; i++) {
+		u64 address = exbuf->in_syncobjs + i * syncobj_stride;
+		struct dma_fence *fence;
+
+		memset(&syncobj_desc, 0, sizeof(syncobj_desc));
+
+		if (copy_from_user(&syncobj_desc,
+				   u64_to_user_ptr(address),
+				   min(syncobj_stride, sizeof(syncobj_desc)))) {
+			ret = -EFAULT;
+			break;
+		}
+
+		if (syncobj_desc.flags & ~VIRTGPU_EXECBUF_SYNCOBJ_FLAGS) {
+			ret = -EINVAL;
+			break;
+		}
+
+		ret = drm_syncobj_find_fence(submit->file, syncobj_desc.handle,
+					     syncobj_desc.point, 0, &fence);
+		if (ret)
+			break;
+
+		ret = virtio_gpu_dma_fence_wait(submit, fence);
+
+		dma_fence_put(fence);
+		if (ret)
+			break;
+
+		if (syncobj_desc.flags & VIRTGPU_EXECBUF_SYNCOBJ_RESET) {
+			syncobjs[i] = drm_syncobj_find(submit->file,
+						       syncobj_desc.handle);
+			if (!syncobjs[i]) {
+				ret = -EINVAL;
+				break;
+			}
+		}
+	}
+
+	if (ret) {
+		virtio_gpu_free_syncobjs(syncobjs, i);
+		return ret;
+	}
+
+	submit->num_in_syncobjs = num_in_syncobjs;
+	submit->in_syncobjs = syncobjs;
+
+	return ret;
+}
+
+static void virtio_gpu_reset_syncobjs(struct drm_syncobj **syncobjs,
+				      u32 nr_syncobjs)
+{
+	u32 i;
+
+	for (i = 0; i < nr_syncobjs; i++) {
+		if (syncobjs[i])
+			drm_syncobj_replace_fence(syncobjs[i], NULL);
+	}
+}
+
+static void
+virtio_gpu_free_post_deps(struct virtio_gpu_submit_post_dep *post_deps,
+			  u32 nr_syncobjs)
+{
+	u32 i = nr_syncobjs;
+
+	while (i--) {
+		kfree(post_deps[i].chain);
+		drm_syncobj_put(post_deps[i].syncobj);
+	}
+
+	kvfree(post_deps);
+}
+
+static int virtio_gpu_parse_post_deps(struct virtio_gpu_submit *submit)
+{
+	struct drm_virtgpu_execbuffer *exbuf = submit->exbuf;
+	struct drm_virtgpu_execbuffer_syncobj syncobj_desc;
+	struct virtio_gpu_submit_post_dep *post_deps;
+	u32 num_out_syncobjs = exbuf->num_out_syncobjs;
+	size_t syncobj_stride = exbuf->syncobj_stride;
+	int ret = 0, i;
+
+	if (!num_out_syncobjs)
+		return 0;
+
+	post_deps = kvcalloc(num_out_syncobjs, sizeof(*post_deps), GFP_KERNEL);
+	if (!post_deps)
+		return -ENOMEM;
+
+	for (i = 0; i < num_out_syncobjs; i++) {
+		u64 address = exbuf->out_syncobjs + i * syncobj_stride;
+
+		memset(&syncobj_desc, 0, sizeof(syncobj_desc));
+
+		if (copy_from_user(&syncobj_desc,
+				   u64_to_user_ptr(address),
+				   min(syncobj_stride, sizeof(syncobj_desc)))) {
+			ret = -EFAULT;
+			break;
+		}
+
+		post_deps[i].point = syncobj_desc.point;
+
+		if (syncobj_desc.flags) {
+			ret = -EINVAL;
+			break;
+		}
+
+		if (syncobj_desc.point) {
+			post_deps[i].chain = dma_fence_chain_alloc();
+			if (!post_deps[i].chain) {
+				ret = -ENOMEM;
+				break;
+			}
+		}
+
+		post_deps[i].syncobj = drm_syncobj_find(submit->file,
+							syncobj_desc.handle);
+		if (!post_deps[i].syncobj) {
+			kfree(post_deps[i].chain);
+			ret = -EINVAL;
+			break;
+		}
+	}
+
+	if (ret) {
+		virtio_gpu_free_post_deps(post_deps, i);
+		return ret;
+	}
+
+	submit->num_out_syncobjs = num_out_syncobjs;
+	submit->post_deps = post_deps;
+
+	return 0;
+}
+
+static void
+virtio_gpu_process_post_deps(struct virtio_gpu_submit *submit)
+{
+	struct virtio_gpu_submit_post_dep *post_deps = submit->post_deps;
+
+	if (post_deps) {
+		struct dma_fence *fence = &submit->out_fence->f;
+		u32 i;
+
+		for (i = 0; i < submit->num_out_syncobjs; i++) {
+			if (post_deps[i].chain) {
+				drm_syncobj_add_point(post_deps[i].syncobj,
+						      post_deps[i].chain,
+						      fence, post_deps[i].point);
+				post_deps[i].chain = NULL;
+			} else {
+				drm_syncobj_replace_fence(post_deps[i].syncobj,
+							  fence);
+			}
+		}
+	}
+}
+
 static int virtio_gpu_fence_event_create(struct drm_device *dev,
 					 struct drm_file *file,
 					 struct virtio_gpu_fence *fence,
 					 u32 ring_idx)
 {
-	struct virtio_gpu_fpriv *vfpriv = file->driver_priv;
 	struct virtio_gpu_fence_event *e = NULL;
 	int ret;
 
-	if (!(vfpriv->ring_idx_mask & BIT_ULL(ring_idx)))
-		return 0;
-
 	e = kzalloc(sizeof(*e), GFP_KERNEL);
 	if (!e)
 		return -ENOMEM;
@@ -122,6 +328,10 @@ static int virtio_gpu_init_submit_buflist(struct virtio_gpu_submit *submit)
 
 static void virtio_gpu_cleanup_submit(struct virtio_gpu_submit *submit)
 {
+	virtio_gpu_reset_syncobjs(submit->in_syncobjs, submit->num_in_syncobjs);
+	virtio_gpu_free_syncobjs(submit->in_syncobjs, submit->num_in_syncobjs);
+	virtio_gpu_free_post_deps(submit->post_deps, submit->num_out_syncobjs);
+
 	if (!IS_ERR(submit->buf))
 		kvfree(submit->buf);
 
@@ -164,18 +374,31 @@ static int virtio_gpu_init_submit(struct virtio_gpu_submit *submit,
 	struct virtio_gpu_fpriv *vfpriv = file->driver_priv;
 	struct virtio_gpu_device *vgdev = dev->dev_private;
 	struct virtio_gpu_fence *out_fence;
+	bool drm_fence_event;
 	int err;
 
 	memset(submit, 0, sizeof(*submit));
 
-	out_fence = virtio_gpu_fence_alloc(vgdev, fence_ctx, ring_idx);
-	if (!out_fence)
-		return -ENOMEM;
-
-	err = virtio_gpu_fence_event_create(dev, file, out_fence, ring_idx);
-	if (err) {
-		dma_fence_put(&out_fence->f);
-		return err;
+	if ((exbuf->flags & VIRTGPU_EXECBUF_RING_IDX) &&
+	    (vfpriv->ring_idx_mask & BIT_ULL(ring_idx)))
+		drm_fence_event = true;
+	else
+		drm_fence_event = false;
+
+	if ((exbuf->flags & VIRTGPU_EXECBUF_FENCE_FD_OUT) ||
+	    exbuf->num_out_syncobjs ||
+	    exbuf->num_bo_handles ||
+	    drm_fence_event)
+		out_fence = virtio_gpu_fence_alloc(vgdev, fence_ctx, ring_idx);
+	else
+		out_fence = NULL;
+
+	if (drm_fence_event) {
+		err = virtio_gpu_fence_event_create(dev, file, out_fence, ring_idx);
+		if (err) {
+			dma_fence_put(&out_fence->f);
+			return err;
+		}
 	}
 
 	submit->out_fence = out_fence;
@@ -283,6 +506,14 @@ int virtio_gpu_execbuffer_ioctl(struct drm_device *dev, void *data,
 	if (ret)
 		goto cleanup;
 
+	ret = virtio_gpu_parse_post_deps(&submit);
+	if (ret)
+		goto cleanup;
+
+	ret = virtio_gpu_parse_deps(&submit);
+	if (ret)
+		goto cleanup;
+
 	/*
 	 * Await in-fences in the end of the job submission path to
 	 * optimize the path by proceeding directly to the submission
@@ -303,6 +534,7 @@ int virtio_gpu_execbuffer_ioctl(struct drm_device *dev, void *data,
 	 * the job submission path.
 	 */
 	virtio_gpu_install_out_fence_fd(&submit);
+	virtio_gpu_process_post_deps(&submit);
 	virtio_gpu_complete_submit(&submit);
 cleanup:
 	virtio_gpu_cleanup_submit(&submit);