Backmerge tag 'v5.18-rc5' of git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux into drm-next

Linux 5.18-rc5

There was a build fix for arm I wanted in drm-next, so backmerge rather then cherry-pick.

Signed-off-by: Dave Airlie <airlied@redhat.com>

4 files changed, 28 insertions, 6 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index 71633a1fedfd..01853431249d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -128,6 +128,8 @@ static int amdgpu_cs_parser_init(struct amdgpu_cs_parser *p, union drm_amdgpu_cs
 		goto free_chunk;
 	}
 
+	mutex_lock(&p->ctx->lock);
+
 	/* skip guilty context job */
 	if (atomic_read(&p->ctx->guilty) == 1) {
 		ret = -ECANCELED;
@@ -688,6 +690,7 @@ static void amdgpu_cs_parser_fini(struct amdgpu_cs_parser *parser, int error,
 	dma_fence_put(parser->fence);
 
 	if (parser->ctx) {
+		mutex_unlock(&parser->ctx->lock);
 		amdgpu_ctx_put(parser->ctx);
 	}
 	if (parser->bo_list)
@@ -1136,6 +1139,9 @@ static int amdgpu_cs_dependencies(struct amdgpu_device *adev,
 {
 	int i, r;
 
+	/* TODO: Investigate why we still need the context lock */
+	mutex_unlock(&p->ctx->lock);
+
 	for (i = 0; i < p->nchunks; ++i) {
 		struct amdgpu_cs_chunk *chunk;
 
@@ -1146,32 +1152,34 @@ static int amdgpu_cs_dependencies(struct amdgpu_device *adev,
 		case AMDGPU_CHUNK_ID_SCHEDULED_DEPENDENCIES:
 			r = amdgpu_cs_process_fence_dep(p, chunk);
 			if (r)
-				return r;
+				goto out;
 			break;
 		case AMDGPU_CHUNK_ID_SYNCOBJ_IN:
 			r = amdgpu_cs_process_syncobj_in_dep(p, chunk);
 			if (r)
-				return r;
+				goto out;
 			break;
 		case AMDGPU_CHUNK_ID_SYNCOBJ_OUT:
 			r = amdgpu_cs_process_syncobj_out_dep(p, chunk);
 			if (r)
-				return r;
+				goto out;
 			break;
 		case AMDGPU_CHUNK_ID_SYNCOBJ_TIMELINE_WAIT:
 			r = amdgpu_cs_process_syncobj_timeline_in_dep(p, chunk);
 			if (r)
-				return r;
+				goto out;
 			break;
 		case AMDGPU_CHUNK_ID_SYNCOBJ_TIMELINE_SIGNAL:
 			r = amdgpu_cs_process_syncobj_timeline_out_dep(p, chunk);
 			if (r)
-				return r;
+				goto out;
 			break;
 		}
 	}
 
-	return 0;
+out:
+	mutex_lock(&p->ctx->lock);
+	return r;
 }
 
 static void amdgpu_cs_post_dependencies(struct amdgpu_cs_parser *p)
@@ -1332,6 +1340,7 @@ int amdgpu_cs_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
 		goto out;
 
 	r = amdgpu_cs_submit(&parser, cs);
+
 out:
 	amdgpu_cs_parser_fini(&parser, r, reserved_buffers);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
index 5981c7d9bd48..8f0e6d93bb9c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
@@ -237,6 +237,7 @@ static int amdgpu_ctx_init(struct amdgpu_device *adev,
 
 	kref_init(&ctx->refcount);
 	spin_lock_init(&ctx->ring_lock);
+	mutex_init(&ctx->lock);
 
 	ctx->reset_counter = atomic_read(&adev->gpu_reset_counter);
 	ctx->reset_counter_query = ctx->reset_counter;
@@ -357,6 +358,7 @@ static void amdgpu_ctx_fini(struct kref *ref)
 		drm_dev_exit(idx);
 	}
 
+	mutex_destroy(&ctx->lock);
 	kfree(ctx);
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.h
index d0cbfcea90f7..142f2f87d44c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.h
@@ -49,6 +49,7 @@ struct amdgpu_ctx {
 	bool				preamble_presented;
 	int32_t				init_priority;
 	int32_t				override_priority;
+	struct mutex			lock;
 	atomic_t			guilty;
 	unsigned long			ras_counter_ce;
 	unsigned long			ras_counter_ue;
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
index a455e59f41f4..20946bc7fc93 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
@@ -1151,6 +1151,16 @@ static int gmc_v10_0_set_clockgating_state(void *handle,
 	int r;
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
+	/*
+	 * The issue mmhub can't disconnect from DF with MMHUB clock gating being disabled
+	 * is a new problem observed at DF 3.0.3, however with the same suspend sequence not
+	 * seen any issue on the DF 3.0.2 series platform.
+	 */
+	if (adev->in_s0ix && adev->ip_versions[DF_HWIP][0] > IP_VERSION(3, 0, 2)) {
+		dev_dbg(adev->dev, "keep mmhub clock gating being enabled for s0ix\n");
+		return 0;
+	}
+
 	r = adev->mmhub.funcs->set_clockgating(adev, state);
 	if (r)
 		return r;