Merge tag 'drm-next-2024-07-26' of https://gitlab.freedesktop.org/drm/kernel

Pull drm fixes from Dave Airlie:
 "Fixes for rc1, mostly amdgpu, i915 and xe, with some other misc ones,
  doesn't seem to be anything too serious.

  amdgpu:
   - Bump driver version for GFX12 DCC
   - DC documention warning fixes
   - VCN unified queue power fix
   - SMU fix
   - RAS fix
   - Display corruption fix
   - SDMA 5.2 workaround
   - GFX12 fixes
   - Uninitialized variable fix
   - VCN/JPEG 4.0.3 fixes
   - Misc display fixes
   - RAS fixes
   - VCN4/5 harvest fix
   - GPU reset fix

  i915:
   - Reset intel_dp->link_trained before retraining the link
   - Don't switch the LTTPR mode on an active link
   - Do not consider preemption during execlists_dequeue for gen8
   - Allow NULL memory region

  xe:
   - xe_exec ioctl minor fix on sync entry cleanup upon error
   - SRIOV: limit VF LMEM provisioning
   - Wedge mode fixes

  v3d:
   - fix indirect dispatch on newer v3d revs

  panel:
   - fix panel backlight bindings"

* tag 'drm-next-2024-07-26' of https://gitlab.freedesktop.org/drm/kernel: (39 commits)
  drm/amdgpu: reset vm state machine after gpu reset(vram lost)
  drm/amdgpu: add missed harvest check for VCN IP v4/v5
  drm/amdgpu: Fix eeprom max record count
  drm/amdgpu: fix ras UE error injection failure issue
  drm/amd/display: Remove ASSERT if significance is zero in math_ceil2
  drm/amd/display: Check for NULL pointer
  drm/amdgpu/vcn: Use offsets local to VCN/JPEG in VF
  drm/amdgpu: Add empty HDP flush function to VCN v4.0.3
  drm/amdgpu: Add empty HDP flush function to JPEG v4.0.3
  drm/amd/amdgpu: Fix uninitialized variable warnings
  drm/amdgpu: Fix atomics on GFX12
  drm/amdgpu/sdma5.2: Update wptr registers as well as doorbell
  drm/i915: Allow NULL memory region
  drm/i915/gt: Do not consider preemption during execlists_dequeue for gen8
  dt-bindings: display: panel: samsung,atna33xc20: Document ATNA45AF01
  drm/xe: Don't suspend device upon wedge
  drm/xe: Wedge the entire device
  drm/xe/pf: Limit fair VF LMEM provisioning
  drm/xe/exec: Fix minor bug related to xe_sync_entry_cleanup
  drm/amd/display: fix corruption with high refresh rates on DCN 3.0
  ...

1 files changed, 13 insertions, 3 deletions

diff --git a/drivers/gpu/drm/v3d/v3d_sched.c b/drivers/gpu/drm/v3d/v3d_sched.c
index 03df37a3acf5..271a6d0f5aca 100644
--- a/drivers/gpu/drm/v3d/v3d_sched.c
+++ b/drivers/gpu/drm/v3d/v3d_sched.c
@@ -331,7 +331,8 @@ v3d_rewrite_csd_job_wg_counts_from_indirect(struct v3d_cpu_job *job)
 	struct v3d_bo *bo = to_v3d_bo(job->base.bo[0]);
 	struct v3d_bo *indirect = to_v3d_bo(indirect_csd->indirect);
 	struct drm_v3d_submit_csd *args = &indirect_csd->job->args;
-	u32 *wg_counts;
+	struct v3d_dev *v3d = job->base.v3d;
+	u32 num_batches, *wg_counts;
 
 	v3d_get_bo_vaddr(bo);
 	v3d_get_bo_vaddr(indirect);
@@ -344,8 +345,17 @@ v3d_rewrite_csd_job_wg_counts_from_indirect(struct v3d_cpu_job *job)
 	args->cfg[0] = wg_counts[0] << V3D_CSD_CFG012_WG_COUNT_SHIFT;
 	args->cfg[1] = wg_counts[1] << V3D_CSD_CFG012_WG_COUNT_SHIFT;
 	args->cfg[2] = wg_counts[2] << V3D_CSD_CFG012_WG_COUNT_SHIFT;
-	args->cfg[4] = DIV_ROUND_UP(indirect_csd->wg_size, 16) *
-		       (wg_counts[0] * wg_counts[1] * wg_counts[2]) - 1;
+
+	num_batches = DIV_ROUND_UP(indirect_csd->wg_size, 16) *
+		      (wg_counts[0] * wg_counts[1] * wg_counts[2]);
+
+	/* V3D 7.1.6 and later don't subtract 1 from the number of batches */
+	if (v3d->ver < 71 || (v3d->ver == 71 && v3d->rev < 6))
+		args->cfg[4] = num_batches - 1;
+	else
+		args->cfg[4] = num_batches;
+
+	WARN_ON(args->cfg[4] == ~0);
 
 	for (int i = 0; i < 3; i++) {
 		/* 0xffffffff indicates that the uniform rewrite is not needed */