Merge tag 'drm-msm-next-2023-12-15' of https://gitlab.freedesktop.org/drm/msm into drm-next

Updates for v6.8:

Core:
- Add support for SDM670, SM8650
- Handle the CFG interconnect to fix the obscure hangs / timeouts
  on register write
- Kconfig fix for QMP dependency
- DT schema fixes

DPU:
- Add support for SDM670, SM8650
- Enable SmartDMA on SM8350 and SM8450
- Correct UBWC settings for SC8280XP
- Fix catalog settings for SC8180X
- Actually make use of the version to switch between QSEED3/3LITE/4
  scalers
- Use devres-managed and drm-managed allocations where appropriate
- misc other fixes
- Enabled YUV writeback on SC7280, SM8250
- Enabled writeback on SM8350, SM8450
- CRC fix when encoder is selected as the input source
- other misc fixes

MDP4:
- Use devres-managed and drm-managed allocations where appropriate
- flush vblank event on CRTC disable

MDP5:
- Use devres-managed and drm-managed allocations where appropriate

DP:
- Add support for SM8650
- Enable PM runtime support
- Merge msm-specific debugfs dir with the generic one
- Described DisplayPort on SM8150 in DeviceTree bindings
- Moved dp_display_get_next_bridge() to probe()

DSI:
- Add support for SM8650
- Enable PM runtime support

GPU/GEM:
- demote userspace triggerable warnings to debug
- add GEM object metadata UAPI
- move GPU devcoredumps to GPU device
- fix hangcheck to skip retired submits
- expose UBWC config to userspace
- fix a680 chip-id
- drm_exec conversion
- drm/ci: remove rebase-merge directory (to unblock CI)

[airlied: fix drm_exec/amd interaction]
Signed-off-by: Dave Airlie <[email protected]>
From: Rob Clark <[email protected]>
Link: https://patchwork.freedesktop.org/patch/msgid/CAF6AEGs9auYqmo-7NSd9FsbNBCDf7aBevd=4xkcF3A5G_OGvMQ@mail.gmail.com

1 files changed, 23 insertions, 21 deletions

diff --git a/drivers/gpu/drm/msm/msm_gpu.c b/drivers/gpu/drm/msm/msm_gpu.c
index 7f64c6667300..095390774f22 100644
--- a/drivers/gpu/drm/msm/msm_gpu.c
+++ b/drivers/gpu/drm/msm/msm_gpu.c
@@ -292,8 +292,7 @@ static void msm_gpu_crashstate_capture(struct msm_gpu *gpu,
 	/* Set the active crash state to be dumped on failure */
 	gpu->crashstate = state;
 
-	/* FIXME: Release the crashstate if this errors out? */
-	dev_coredumpm(gpu->dev->dev, THIS_MODULE, gpu, 0, GFP_KERNEL,
+	dev_coredumpm(&gpu->pdev->dev, THIS_MODULE, gpu, 0, GFP_KERNEL,
 		msm_gpu_devcoredump_read, msm_gpu_devcoredump_free);
 }
 #else
@@ -366,29 +365,31 @@ static void recover_worker(struct kthread_work *work)
 	DRM_DEV_ERROR(dev->dev, "%s: hangcheck recover!\n", gpu->name);
 
 	submit = find_submit(cur_ring, cur_ring->memptrs->fence + 1);
-	if (submit) {
-		/* Increment the fault counts */
-		submit->queue->faults++;
-		if (submit->aspace)
-			submit->aspace->faults++;
 
-		get_comm_cmdline(submit, &comm, &cmd);
+	/*
+	 * If the submit retired while we were waiting for the worker to run,
+	 * or waiting to acquire the gpu lock, then nothing more to do.
+	 */
+	if (!submit)
+		goto out_unlock;
 
-		if (comm && cmd) {
-			DRM_DEV_ERROR(dev->dev, "%s: offending task: %s (%s)\n",
-				gpu->name, comm, cmd);
+	/* Increment the fault counts */
+	submit->queue->faults++;
+	if (submit->aspace)
+		submit->aspace->faults++;
 
-			msm_rd_dump_submit(priv->hangrd, submit,
-				"offending task: %s (%s)", comm, cmd);
-		} else {
-			msm_rd_dump_submit(priv->hangrd, submit, NULL);
-		}
+	get_comm_cmdline(submit, &comm, &cmd);
+
+	if (comm && cmd) {
+		DRM_DEV_ERROR(dev->dev, "%s: offending task: %s (%s)\n",
+			      gpu->name, comm, cmd);
+
+		msm_rd_dump_submit(priv->hangrd, submit,
+				   "offending task: %s (%s)", comm, cmd);
 	} else {
-		/*
-		 * We couldn't attribute this fault to any particular context,
-		 * so increment the global fault count instead.
-		 */
-		gpu->global_faults++;
+		DRM_DEV_ERROR(dev->dev, "%s: offending task: unknown\n", gpu->name);
+
+		msm_rd_dump_submit(priv->hangrd, submit, NULL);
 	}
 
 	/* Record the crash state */
@@ -441,6 +442,7 @@ static void recover_worker(struct kthread_work *work)
 
 	pm_runtime_put(&gpu->pdev->dev);
 
+out_unlock:
 	mutex_unlock(&gpu->lock);
 
 	msm_gpu_retire(gpu);