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, 441 insertions, 0 deletions

diff --git a/drivers/gpu/drm/nouveau/nouveau_sched.c b/drivers/gpu/drm/nouveau/nouveau_sched.c
new file mode 100644
index 000000000000..88217185e0f3
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nouveau_sched.c
@@ -0,0 +1,441 @@
+// SPDX-License-Identifier: MIT
+
+#include <linux/slab.h>
+#include <drm/gpu_scheduler.h>
+#include <drm/drm_syncobj.h>
+
+#include "nouveau_drv.h"
+#include "nouveau_gem.h"
+#include "nouveau_mem.h"
+#include "nouveau_dma.h"
+#include "nouveau_exec.h"
+#include "nouveau_abi16.h"
+#include "nouveau_sched.h"
+
+/* FIXME
+ *
+ * We want to make sure that jobs currently executing can't be deferred by
+ * other jobs competing for the hardware. Otherwise we might end up with job
+ * timeouts just because of too many clients submitting too many jobs. We don't
+ * want jobs to time out because of system load, but because of the job being
+ * too bulky.
+ *
+ * For now allow for up to 16 concurrent jobs in flight until we know how many
+ * rings the hardware can process in parallel.
+ */
+#define NOUVEAU_SCHED_HW_SUBMISSIONS		16
+#define NOUVEAU_SCHED_JOB_TIMEOUT_MS		10000
+
+int
+nouveau_job_init(struct nouveau_job *job,
+		 struct nouveau_job_args *args)
+{
+	struct nouveau_sched_entity *entity = args->sched_entity;
+	int ret;
+
+	job->file_priv = args->file_priv;
+	job->cli = nouveau_cli(args->file_priv);
+	job->entity = entity;
+
+	job->sync = args->sync;
+	job->resv_usage = args->resv_usage;
+
+	job->ops = args->ops;
+
+	job->in_sync.count = args->in_sync.count;
+	if (job->in_sync.count) {
+		if (job->sync)
+			return -EINVAL;
+
+		job->in_sync.data = kmemdup(args->in_sync.s,
+					 sizeof(*args->in_sync.s) *
+					 args->in_sync.count,
+					 GFP_KERNEL);
+		if (!job->in_sync.data)
+			return -ENOMEM;
+	}
+
+	job->out_sync.count = args->out_sync.count;
+	if (job->out_sync.count) {
+		if (job->sync) {
+			ret = -EINVAL;
+			goto err_free_in_sync;
+		}
+
+		job->out_sync.data = kmemdup(args->out_sync.s,
+					  sizeof(*args->out_sync.s) *
+					  args->out_sync.count,
+					  GFP_KERNEL);
+		if (!job->out_sync.data) {
+			ret = -ENOMEM;
+			goto err_free_in_sync;
+		}
+
+		job->out_sync.objs = kcalloc(job->out_sync.count,
+					     sizeof(*job->out_sync.objs),
+					     GFP_KERNEL);
+		if (!job->out_sync.objs) {
+			ret = -ENOMEM;
+			goto err_free_out_sync;
+		}
+
+		job->out_sync.chains = kcalloc(job->out_sync.count,
+					       sizeof(*job->out_sync.chains),
+					       GFP_KERNEL);
+		if (!job->out_sync.chains) {
+			ret = -ENOMEM;
+			goto err_free_objs;
+		}
+
+	}
+
+	ret = drm_sched_job_init(&job->base, &entity->base, NULL);
+	if (ret)
+		goto err_free_chains;
+
+	job->state = NOUVEAU_JOB_INITIALIZED;
+
+	return 0;
+
+err_free_chains:
+	kfree(job->out_sync.chains);
+err_free_objs:
+	kfree(job->out_sync.objs);
+err_free_out_sync:
+	kfree(job->out_sync.data);
+err_free_in_sync:
+	kfree(job->in_sync.data);
+return ret;
+}
+
+void
+nouveau_job_free(struct nouveau_job *job)
+{
+	kfree(job->in_sync.data);
+	kfree(job->out_sync.data);
+	kfree(job->out_sync.objs);
+	kfree(job->out_sync.chains);
+}
+
+void nouveau_job_fini(struct nouveau_job *job)
+{
+	dma_fence_put(job->done_fence);
+	drm_sched_job_cleanup(&job->base);
+	job->ops->free(job);
+}
+
+static int
+sync_find_fence(struct nouveau_job *job,
+		struct drm_nouveau_sync *sync,
+		struct dma_fence **fence)
+{
+	u32 stype = sync->flags & DRM_NOUVEAU_SYNC_TYPE_MASK;
+	u64 point = 0;
+	int ret;
+
+	if (stype != DRM_NOUVEAU_SYNC_SYNCOBJ &&
+	    stype != DRM_NOUVEAU_SYNC_TIMELINE_SYNCOBJ)
+		return -EOPNOTSUPP;
+
+	if (stype == DRM_NOUVEAU_SYNC_TIMELINE_SYNCOBJ)
+		point = sync->timeline_value;
+
+	ret = drm_syncobj_find_fence(job->file_priv,
+				     sync->handle, point,
+				     0 /* flags */, fence);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+static int
+nouveau_job_add_deps(struct nouveau_job *job)
+{
+	struct dma_fence *in_fence = NULL;
+	int ret, i;
+
+	for (i = 0; i < job->in_sync.count; i++) {
+		struct drm_nouveau_sync *sync = &job->in_sync.data[i];
+
+		ret = sync_find_fence(job, sync, &in_fence);
+		if (ret) {
+			NV_PRINTK(warn, job->cli,
+				  "Failed to find syncobj (-> in): handle=%d\n",
+				  sync->handle);
+			return ret;
+		}
+
+		ret = drm_sched_job_add_dependency(&job->base, in_fence);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+static void
+nouveau_job_fence_attach_cleanup(struct nouveau_job *job)
+{
+	int i;
+
+	for (i = 0; i < job->out_sync.count; i++) {
+		struct drm_syncobj *obj = job->out_sync.objs[i];
+		struct dma_fence_chain *chain = job->out_sync.chains[i];
+
+		if (obj)
+			drm_syncobj_put(obj);
+
+		if (chain)
+			dma_fence_chain_free(chain);
+	}
+}
+
+static int
+nouveau_job_fence_attach_prepare(struct nouveau_job *job)
+{
+	int i, ret;
+
+	for (i = 0; i < job->out_sync.count; i++) {
+		struct drm_nouveau_sync *sync = &job->out_sync.data[i];
+		struct drm_syncobj **pobj = &job->out_sync.objs[i];
+		struct dma_fence_chain **pchain = &job->out_sync.chains[i];
+		u32 stype = sync->flags & DRM_NOUVEAU_SYNC_TYPE_MASK;
+
+		if (stype != DRM_NOUVEAU_SYNC_SYNCOBJ &&
+		    stype != DRM_NOUVEAU_SYNC_TIMELINE_SYNCOBJ) {
+			ret = -EINVAL;
+			goto err_sync_cleanup;
+		}
+
+		*pobj = drm_syncobj_find(job->file_priv, sync->handle);
+		if (!*pobj) {
+			NV_PRINTK(warn, job->cli,
+				  "Failed to find syncobj (-> out): handle=%d\n",
+				  sync->handle);
+			ret = -ENOENT;
+			goto err_sync_cleanup;
+		}
+
+		if (stype == DRM_NOUVEAU_SYNC_TIMELINE_SYNCOBJ) {
+			*pchain = dma_fence_chain_alloc();
+			if (!*pchain) {
+				ret = -ENOMEM;
+				goto err_sync_cleanup;
+			}
+		}
+	}
+
+	return 0;
+
+err_sync_cleanup:
+	nouveau_job_fence_attach_cleanup(job);
+	return ret;
+}
+
+static void
+nouveau_job_fence_attach(struct nouveau_job *job)
+{
+	struct dma_fence *fence = job->done_fence;
+	int i;
+
+	for (i = 0; i < job->out_sync.count; i++) {
+		struct drm_nouveau_sync *sync = &job->out_sync.data[i];
+		struct drm_syncobj **pobj = &job->out_sync.objs[i];
+		struct dma_fence_chain **pchain = &job->out_sync.chains[i];
+		u32 stype = sync->flags & DRM_NOUVEAU_SYNC_TYPE_MASK;
+
+		if (stype == DRM_NOUVEAU_SYNC_TIMELINE_SYNCOBJ) {
+			drm_syncobj_add_point(*pobj, *pchain, fence,
+					      sync->timeline_value);
+		} else {
+			drm_syncobj_replace_fence(*pobj, fence);
+		}
+
+		drm_syncobj_put(*pobj);
+		*pobj = NULL;
+		*pchain = NULL;
+	}
+}
+
+int
+nouveau_job_submit(struct nouveau_job *job)
+{
+	struct nouveau_sched_entity *entity = to_nouveau_sched_entity(job->base.entity);
+	struct dma_fence *done_fence = NULL;
+	int ret;
+
+	ret = nouveau_job_add_deps(job);
+	if (ret)
+		goto err;
+
+	ret = nouveau_job_fence_attach_prepare(job);
+	if (ret)
+		goto err;
+
+	/* Make sure the job appears on the sched_entity's queue in the same
+	 * order as it was submitted.
+	 */
+	mutex_lock(&entity->mutex);
+
+	/* Guarantee we won't fail after the submit() callback returned
+	 * successfully.
+	 */
+	if (job->ops->submit) {
+		ret = job->ops->submit(job);
+		if (ret)
+			goto err_cleanup;
+	}
+
+	drm_sched_job_arm(&job->base);
+	job->done_fence = dma_fence_get(&job->base.s_fence->finished);
+	if (job->sync)
+		done_fence = dma_fence_get(job->done_fence);
+
+	/* If a sched job depends on a dma-fence from a job from the same GPU
+	 * scheduler instance, but a different scheduler entity, the GPU
+	 * scheduler does only wait for the particular job to be scheduled,
+	 * rather than for the job to fully complete. This is due to the GPU
+	 * scheduler assuming that there is a scheduler instance per ring.
+	 * However, the current implementation, in order to avoid arbitrary
+	 * amounts of kthreads, has a single scheduler instance while scheduler
+	 * entities represent rings.
+	 *
+	 * As a workaround, set the DRM_SCHED_FENCE_DONT_PIPELINE for all
+	 * out-fences in order to force the scheduler to wait for full job
+	 * completion for dependent jobs from different entities and same
+	 * scheduler instance.
+	 *
+	 * There is some work in progress [1] to address the issues of firmware
+	 * schedulers; once it is in-tree the scheduler topology in Nouveau
+	 * should be re-worked accordingly.
+	 *
+	 * [1] https://lore.kernel.org/dri-devel/20230801205103.627779-1-matthew.brost@intel.com/
+	 */
+	set_bit(DRM_SCHED_FENCE_DONT_PIPELINE, &job->done_fence->flags);
+
+	if (job->ops->armed_submit)
+		job->ops->armed_submit(job);
+
+	nouveau_job_fence_attach(job);
+
+	/* Set job state before pushing the job to the scheduler,
+	 * such that we do not overwrite the job state set in run().
+	 */
+	job->state = NOUVEAU_JOB_SUBMIT_SUCCESS;
+
+	drm_sched_entity_push_job(&job->base);
+
+	mutex_unlock(&entity->mutex);
+
+	if (done_fence) {
+		dma_fence_wait(done_fence, true);
+		dma_fence_put(done_fence);
+	}
+
+	return 0;
+
+err_cleanup:
+	mutex_unlock(&entity->mutex);
+	nouveau_job_fence_attach_cleanup(job);
+err:
+	job->state = NOUVEAU_JOB_SUBMIT_FAILED;
+	return ret;
+}
+
+bool
+nouveau_sched_entity_qwork(struct nouveau_sched_entity *entity,
+			   struct work_struct *work)
+{
+	return queue_work(entity->sched_wq, work);
+}
+
+static struct dma_fence *
+nouveau_job_run(struct nouveau_job *job)
+{
+	struct dma_fence *fence;
+
+	fence = job->ops->run(job);
+	if (IS_ERR(fence))
+		job->state = NOUVEAU_JOB_RUN_FAILED;
+	else
+		job->state = NOUVEAU_JOB_RUN_SUCCESS;
+
+	return fence;
+}
+
+static struct dma_fence *
+nouveau_sched_run_job(struct drm_sched_job *sched_job)
+{
+	struct nouveau_job *job = to_nouveau_job(sched_job);
+
+	return nouveau_job_run(job);
+}
+
+static enum drm_gpu_sched_stat
+nouveau_sched_timedout_job(struct drm_sched_job *sched_job)
+{
+	struct nouveau_job *job = to_nouveau_job(sched_job);
+
+	NV_PRINTK(warn, job->cli, "Job timed out.\n");
+
+	if (job->ops->timeout)
+		return job->ops->timeout(job);
+
+	return DRM_GPU_SCHED_STAT_ENODEV;
+}
+
+static void
+nouveau_sched_free_job(struct drm_sched_job *sched_job)
+{
+	struct nouveau_job *job = to_nouveau_job(sched_job);
+
+	nouveau_job_fini(job);
+}
+
+int nouveau_sched_entity_init(struct nouveau_sched_entity *entity,
+			      struct drm_gpu_scheduler *sched,
+			      struct workqueue_struct *sched_wq)
+{
+	mutex_init(&entity->mutex);
+	spin_lock_init(&entity->job.list.lock);
+	INIT_LIST_HEAD(&entity->job.list.head);
+	init_waitqueue_head(&entity->job.wq);
+
+	entity->sched_wq = sched_wq;
+	return drm_sched_entity_init(&entity->base,
+				     DRM_SCHED_PRIORITY_NORMAL,
+				     &sched, 1, NULL);
+}
+
+void
+nouveau_sched_entity_fini(struct nouveau_sched_entity *entity)
+{
+	drm_sched_entity_destroy(&entity->base);
+}
+
+static const struct drm_sched_backend_ops nouveau_sched_ops = {
+	.run_job = nouveau_sched_run_job,
+	.timedout_job = nouveau_sched_timedout_job,
+	.free_job = nouveau_sched_free_job,
+};
+
+int nouveau_sched_init(struct nouveau_drm *drm)
+{
+	struct drm_gpu_scheduler *sched = &drm->sched;
+	long job_hang_limit = msecs_to_jiffies(NOUVEAU_SCHED_JOB_TIMEOUT_MS);
+
+	drm->sched_wq = create_singlethread_workqueue("nouveau_sched_wq");
+	if (!drm->sched_wq)
+		return -ENOMEM;
+
+	return drm_sched_init(sched, &nouveau_sched_ops,
+			      NOUVEAU_SCHED_HW_SUBMISSIONS, 0, job_hang_limit,
+			      NULL, NULL, "nouveau_sched", drm->dev->dev);
+}
+
+void nouveau_sched_fini(struct nouveau_drm *drm)
+{
+	destroy_workqueue(drm->sched_wq);
+	drm_sched_fini(&drm->sched);
+}