Merge tag 'drm-next-2021-11-12' of git://anongit.freedesktop.org/drm/drm

Pull more drm updates from Dave Airlie:
 "I missed a drm-misc-next pull for the main pull last week. It wasn't
  that major and isn't the bulk of this at all. This has a bunch of
  fixes all over, a lot for amdgpu and i915.

  bridge:
   - HPD improvments for lt9611uxc
   - eDP aux-bus support for ps8640
   - LVDS data-mapping selection support

  ttm:
   - remove huge page functionality (needs reworking)
   - fix a race condition during BO eviction

  panels:
   - add some new panels

  fbdev:
   - fix double-free
   - remove unused scrolling acceleration
   - CONFIG_FB dep improvements

  locking:
   - improve contended locking logging
   - naming collision fix

  dma-buf:
   - add dma_resv_for_each_fence iterator
   - fix fence refcounting bug
   - name locking fixesA

  prime:
   - fix object references during mmap

  nouveau:
   - various code style changes
   - refcount fix
   - device removal fixes
   - protect client list with a mutex
   - fix CE0 address calculation

  i915:
   - DP rates related fixes
   - Revert disabling dual eDP that was causing state readout problems
   - put the cdclk vtables in const data
   - Fix DVO port type for older platforms
   - Fix blankscreen by turning DP++ TMDS output buffers on encoder->shutdown
   - CCS FBs related fixes
   - Fix recursive lock in GuC submission
   - Revert guc_id from i915_request tracepoint
   - Build fix around dmabuf

  amdgpu:
   - GPU reset fix
   - Aldebaran fix
   - Yellow Carp fixes
   - DCN2.1 DMCUB fix
   - IOMMU regression fix for Picasso
   - DSC display fixes
   - BPC display calculation fixes
   - Other misc display fixes
   - Don't allow partial copy from user for DC debugfs
   - SRIOV fixes
   - GFX9 CSB pin count fix
   - Various IP version check fixes
   - DP 2.0 fixes
   - Limit DCN1 MPO fix to DCN1

  amdkfd:
   - SVM fixes
   - Fix gfx version for renoir
   - Reset fixes

  udl:
   - timeout fix

  imx:
   - circular locking fix

  virtio:
   - NULL ptr deref fix"

* tag 'drm-next-2021-11-12' of git://anongit.freedesktop.org/drm/drm: (126 commits)
  drm/ttm: Double check mem_type of BO while eviction
  drm/amdgpu: add missed support for UVD IP_VERSION(3, 0, 64)
  drm/amdgpu: drop jpeg IP initialization in SRIOV case
  drm/amd/display: reject both non-zero src_x and src_y only for DCN1x
  drm/amd/display: Add callbacks for DMUB HPD IRQ notifications
  drm/amd/display: Don't lock connection_mutex for DMUB HPD
  drm/amd/display: Add comment where CONFIG_DRM_AMD_DC_DCN macro ends
  drm/amdkfd: Fix retry fault drain race conditions
  drm/amdkfd: lower the VAs base offset to 8KB
  drm/amd/display: fix exit from amdgpu_dm_atomic_check() abruptly
  drm/amd/amdgpu: fix the kfd pre_reset sequence in sriov
  drm/amdgpu: fix uvd crash on Polaris12 during driver unloading
  drm/i915/adlp/fb: Prevent the mapping of redundant trailing padding NULL pages
  drm/i915/fb: Fix rounding error in subsampled plane size calculation
  drm/i915/hdmi: Turn DP++ TMDS output buffers back on in encoder->shutdown()
  drm/locking: fix __stack_depot_* name conflict
  drm/virtio: Fix NULL dereference error in virtio_gpu_poll
  drm/amdgpu: fix SI handling in amdgpu_device_asic_has_dc_support()
  drm/amdgpu: Fix dangling kfd_bo pointer for shared BOs
  drm/amd/amdkfd: Don't sent command to HWS on kfd reset
  ...

1 files changed, 16 insertions, 9 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 6e40cc1bc6dc..5625f7736e37 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -2398,10 +2398,6 @@ static int amdgpu_device_ip_init(struct amdgpu_device *adev)
 	if (!adev->gmc.xgmi.pending_reset)
 		amdgpu_amdkfd_device_init(adev);
 
-	r = amdgpu_amdkfd_resume_iommu(adev);
-	if (r)
-		goto init_failed;
-
 	amdgpu_fru_get_product_info(adev);
 
 init_failed:
@@ -3171,11 +3167,21 @@ bool amdgpu_device_asic_has_dc_support(enum amd_asic_type asic_type)
 {
 	switch (asic_type) {
 #if defined(CONFIG_DRM_AMD_DC)
-#if defined(CONFIG_DRM_AMD_DC_SI)
 	case CHIP_TAHITI:
 	case CHIP_PITCAIRN:
 	case CHIP_VERDE:
 	case CHIP_OLAND:
+		/*
+		 * We have systems in the wild with these ASICs that require
+		 * LVDS and VGA support which is not supported with DC.
+		 *
+		 * Fallback to the non-DC driver here by default so as not to
+		 * cause regressions.
+		 */
+#if defined(CONFIG_DRM_AMD_DC_SI)
+		return amdgpu_dc > 0;
+#else
+		return false;
 #endif
 	case CHIP_BONAIRE:
 	case CHIP_KAVERI:
@@ -4287,8 +4293,6 @@ static int amdgpu_device_reset_sriov(struct amdgpu_device *adev,
 	if (r)
 		return r;
 
-	amdgpu_amdkfd_pre_reset(adev);
-
 	/* Resume IP prior to SMC */
 	r = amdgpu_device_ip_reinit_early_sriov(adev);
 	if (r)
@@ -4850,6 +4854,9 @@ static void amdgpu_device_recheck_guilty_jobs(
 
 		/* clear job's guilty and depend the folowing step to decide the real one */
 		drm_sched_reset_karma(s_job);
+		/* for the real bad job, it will be resubmitted twice, adding a dma_fence_get
+		 * to make sure fence is balanced */
+		dma_fence_get(s_job->s_fence->parent);
 		drm_sched_resubmit_jobs_ext(&ring->sched, 1);
 
 		ret = dma_fence_wait_timeout(s_job->s_fence->parent, false, ring->sched.timeout);
@@ -4885,6 +4892,7 @@ retry:
 
 		/* got the hw fence, signal finished fence */
 		atomic_dec(ring->sched.score);
+		dma_fence_put(s_job->s_fence->parent);
 		dma_fence_get(&s_job->s_fence->finished);
 		dma_fence_signal(&s_job->s_fence->finished);
 		dma_fence_put(&s_job->s_fence->finished);
@@ -5020,8 +5028,7 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
 
 		cancel_delayed_work_sync(&tmp_adev->delayed_init_work);
 
-		if (!amdgpu_sriov_vf(tmp_adev))
-			amdgpu_amdkfd_pre_reset(tmp_adev);
+		amdgpu_amdkfd_pre_reset(tmp_adev);
 
 		/*
 		 * Mark these ASICs to be reseted as untracked first