[PATCH v3 00/13] drm/msm: drm scheduler conversion and cleanups

[PATCH v3 00/13] drm/msm: drm scheduler conversion and cleanups

[Rob Clark]

From: Rob Clark <robdclark@chromium.org>

Conversion to gpu_scheduler, and bonus removal of
drm_gem_object_put_locked()

v2: Fix priority mixup (msm UAPI has lower numeric priority value as
    higher priority, inverse of drm/scheduler) and add some comments
    in the UAPI header to clarify.

    Now that we move active refcnt get into msm_gem_submit, add a
    patch to mark all bos busy before pinning, to avoid evicting bos
    used in same batch.

    Fix bo locking for cmdstream dumping ($debugfs/n/{rd,hangrd})

v3: Add a patch to drop submit bo_list and instead use -EALREADY
    to detect errors with same obj appearing multiple times in the
    submit ioctl bos table.  Otherwise, with struct_mutex locking
    dropped, we'd need to move insertion into and removal from
    bo_list under the obj lock.

Rob Clark (13):
  drm/msm: Docs and misc cleanup
  drm/msm: Small submitqueue creation cleanup
  drm/msm: drop drm_gem_object_put_locked()
  drm: Drop drm_gem_object_put_locked()
  drm/msm/submit: Simplify out-fence-fd handling
  drm/msm: Consolidate submit bo state
  drm/msm: Track "seqno" fences by idr
  drm/msm: Return ERR_PTR() from submit_create()
  drm/msm: Conversion to drm scheduler
  drm/msm: Drop submit bo_list
  drm/msm: Drop struct_mutex in submit path
  drm/msm: Utilize gpu scheduler priorities
  drm/msm/gem: Mark active before pinning

 drivers/gpu/drm/drm_gem.c                   |  22 --
 drivers/gpu/drm/msm/Kconfig                 |   1 +
 drivers/gpu/drm/msm/adreno/a5xx_debugfs.c   |   4 +-
 drivers/gpu/drm/msm/adreno/a5xx_gpu.c       |   6 +-
 drivers/gpu/drm/msm/adreno/a5xx_power.c     |   2 +-
 drivers/gpu/drm/msm/adreno/a5xx_preempt.c   |   7 +-
 drivers/gpu/drm/msm/adreno/a6xx_gmu.c       |  12 +-
 drivers/gpu/drm/msm/adreno/a6xx_gpu.c       |   2 +-
 drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c |   4 +-
 drivers/gpu/drm/msm/adreno/adreno_gpu.c     |   6 +-
 drivers/gpu/drm/msm/msm_drv.c               |  30 +-
 drivers/gpu/drm/msm/msm_fence.c             |  39 ---
 drivers/gpu/drm/msm/msm_fence.h             |   2 -
 drivers/gpu/drm/msm/msm_gem.c               |  94 +-----
 drivers/gpu/drm/msm/msm_gem.h               |  47 +--
 drivers/gpu/drm/msm/msm_gem_submit.c        | 344 ++++++++++++--------
 drivers/gpu/drm/msm/msm_gpu.c               |  46 +--
 drivers/gpu/drm/msm/msm_gpu.h               |  78 ++++-
 drivers/gpu/drm/msm/msm_rd.c                |   6 +-
 drivers/gpu/drm/msm/msm_ringbuffer.c        |  70 +++-
 drivers/gpu/drm/msm/msm_ringbuffer.h        |  12 +
 drivers/gpu/drm/msm/msm_submitqueue.c       |  53 ++-
 include/drm/drm_gem.h                       |   2 -
 include/uapi/drm/msm_drm.h                  |  14 +-
 24 files changed, 516 insertions(+), 387 deletions(-)

-- 
2.31.1

[PATCH v3 01/13] drm/msm: Docs and misc cleanup

[Rob Clark]

From: Rob Clark <robdclark@chromium.org>

Fix a couple incorrect or misspelt comments, and add submitqueue doc
comment.

Signed-off-by: Rob Clark <robdclark@chromium.org>
Acked-by: Christian König <christian.koenig@amd.com>
---
 drivers/gpu/drm/msm/msm_gem.h         |  3 +--
 drivers/gpu/drm/msm/msm_gem_submit.c  |  1 +
 drivers/gpu/drm/msm/msm_gpu.h         | 15 +++++++++++++++
 drivers/gpu/drm/msm/msm_ringbuffer.c  |  2 +-
 drivers/gpu/drm/msm/msm_submitqueue.c |  9 +++++----
 5 files changed, 23 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/msm/msm_gem.h b/drivers/gpu/drm/msm/msm_gem.h
index 405f8411e395..d69fcb37ce17 100644
--- a/drivers/gpu/drm/msm/msm_gem.h
+++ b/drivers/gpu/drm/msm/msm_gem.h
@@ -313,8 +313,7 @@ void msm_gem_vunmap(struct drm_gem_object *obj);
 
 /* Created per submit-ioctl, to track bo's and cmdstream bufs, etc,
  * associated with the cmdstream submission for synchronization (and
- * make it easier to unwind when things go wrong, etc).  This only
- * lasts for the duration of the submit-ioctl.
+ * make it easier to unwind when things go wrong, etc).
  */
 struct msm_gem_submit {
 	struct kref ref;
diff --git a/drivers/gpu/drm/msm/msm_gem_submit.c b/drivers/gpu/drm/msm/msm_gem_submit.c
index 44f84bfd0c0e..6d46f9275a40 100644
--- a/drivers/gpu/drm/msm/msm_gem_submit.c
+++ b/drivers/gpu/drm/msm/msm_gem_submit.c
@@ -655,6 +655,7 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data,
 	bool has_ww_ticket = false;
 	unsigned i;
 	int ret, submitid;
+
 	if (!gpu)
 		return -ENXIO;
 
diff --git a/drivers/gpu/drm/msm/msm_gpu.h b/drivers/gpu/drm/msm/msm_gpu.h
index 710c3fedfbf3..96efcb31e502 100644
--- a/drivers/gpu/drm/msm/msm_gpu.h
+++ b/drivers/gpu/drm/msm/msm_gpu.h
@@ -250,6 +250,21 @@ struct msm_gpu_perfcntr {
 	const char *name;
 };
 
+/**
+ * A submitqueue is associated with a gl context or vk queue (or equiv)
+ * in userspace.
+ *
+ * @id:        userspace id for the submitqueue, unique within the drm_file
+ * @flags:     userspace flags for the submitqueue, specified at creation
+ *             (currently unusued)
+ * @prio:      the submitqueue priority
+ * @faults:    the number of GPU hangs associated with this submitqueue
+ * @ctx:       the per-drm_file context associated with the submitqueue (ie.
+ *             which set of pgtables do submits jobs associated with the
+ *             submitqueue use)
+ * @node:      node in the context's list of submitqueues
+ * @ref:       reference count
+ */
 struct msm_gpu_submitqueue {
 	int id;
 	u32 flags;
diff --git a/drivers/gpu/drm/msm/msm_ringbuffer.c b/drivers/gpu/drm/msm/msm_ringbuffer.c
index 7e92d9532454..054461662af5 100644
--- a/drivers/gpu/drm/msm/msm_ringbuffer.c
+++ b/drivers/gpu/drm/msm/msm_ringbuffer.c
@@ -32,7 +32,7 @@ struct msm_ringbuffer *msm_ringbuffer_new(struct msm_gpu *gpu, int id,
 
 	if (IS_ERR(ring->start)) {
 		ret = PTR_ERR(ring->start);
-		ring->start = 0;
+		ring->start = NULL;
 		goto fail;
 	}
 
diff --git a/drivers/gpu/drm/msm/msm_submitqueue.c b/drivers/gpu/drm/msm/msm_submitqueue.c
index c3d206105d28..e5eef11ed014 100644
--- a/drivers/gpu/drm/msm/msm_submitqueue.c
+++ b/drivers/gpu/drm/msm/msm_submitqueue.c
@@ -98,17 +98,18 @@ int msm_submitqueue_create(struct drm_device *drm, struct msm_file_private *ctx,
 	return 0;
 }
 
+/*
+ * Create the default submit-queue (id==0), used for backwards compatibility
+ * for userspace that pre-dates the introduction of submitqueues.
+ */
 int msm_submitqueue_init(struct drm_device *drm, struct msm_file_private *ctx)
 {
 	struct msm_drm_private *priv = drm->dev_private;
 	int default_prio;
 
-	if (!ctx)
-		return 0;
-
 	/*
 	 * Select priority 2 as the "default priority" unless nr_rings is less
-	 * than 2 and then pick the lowest pirority
+	 * than 2 and then pick the lowest priority
 	 */
 	default_prio = priv->gpu ?
 		clamp_t(uint32_t, 2, 0, priv->gpu->nr_rings - 1) : 0;
-- 
2.31.1

[PATCH v3 02/13] drm/msm: Small submitqueue creation cleanup

[Rob Clark]

From: Rob Clark <robdclark@chromium.org>

If we don't have a gpu, there is no need to create a submitqueue, which
lets us simplify the error handling and submitqueue creation.

Signed-off-by: Rob Clark <robdclark@chromium.org>
Acked-by: Christian König <christian.koenig@amd.com>
---
 drivers/gpu/drm/msm/msm_submitqueue.c | 22 +++++++++++-----------
 1 file changed, 11 insertions(+), 11 deletions(-)

diff --git a/drivers/gpu/drm/msm/msm_submitqueue.c b/drivers/gpu/drm/msm/msm_submitqueue.c
index e5eef11ed014..9e9fec61d629 100644
--- a/drivers/gpu/drm/msm/msm_submitqueue.c
+++ b/drivers/gpu/drm/msm/msm_submitqueue.c
@@ -66,6 +66,12 @@ int msm_submitqueue_create(struct drm_device *drm, struct msm_file_private *ctx,
 	if (!ctx)
 		return -ENODEV;
 
+	if (!priv->gpu)
+		return -ENODEV;
+
+	if (prio >= priv->gpu->nr_rings)
+		return -EINVAL;
+
 	queue = kzalloc(sizeof(*queue), GFP_KERNEL);
 
 	if (!queue)
@@ -73,15 +79,7 @@ int msm_submitqueue_create(struct drm_device *drm, struct msm_file_private *ctx,
 
 	kref_init(&queue->ref);
 	queue->flags = flags;
-
-	if (priv->gpu) {
-		if (prio >= priv->gpu->nr_rings) {
-			kfree(queue);
-			return -EINVAL;
-		}
-
-		queue->prio = prio;
-	}
+	queue->prio = prio;
 
 	write_lock(&ctx->queuelock);
 
@@ -107,12 +105,14 @@ int msm_submitqueue_init(struct drm_device *drm, struct msm_file_private *ctx)
 	struct msm_drm_private *priv = drm->dev_private;
 	int default_prio;
 
+	if (!priv->gpu)
+		return -ENODEV;
+
 	/*
 	 * Select priority 2 as the "default priority" unless nr_rings is less
 	 * than 2 and then pick the lowest priority
 	 */
-	default_prio = priv->gpu ?
-		clamp_t(uint32_t, 2, 0, priv->gpu->nr_rings - 1) : 0;
+	default_prio = clamp_t(uint32_t, 2, 0, priv->gpu->nr_rings - 1);
 
 	INIT_LIST_HEAD(&ctx->submitqueues);
 
-- 
2.31.1

[PATCH v3 03/13] drm/msm: drop drm_gem_object_put_locked()

[Rob Clark]

From: Rob Clark <robdclark@chromium.org>

No idea why we were still using this.  It certainly hasn't been needed
for some time.  So drop the pointless twin codepaths.

Signed-off-by: Rob Clark <robdclark@chromium.org>
Acked-by: Christian König <christian.koenig@amd.com>
---
 drivers/gpu/drm/msm/adreno/a5xx_debugfs.c   |  4 +-
 drivers/gpu/drm/msm/adreno/a5xx_gpu.c       |  6 +--
 drivers/gpu/drm/msm/adreno/a5xx_power.c     |  2 +-
 drivers/gpu/drm/msm/adreno/a5xx_preempt.c   |  7 ++-
 drivers/gpu/drm/msm/adreno/a6xx_gmu.c       | 12 ++---
 drivers/gpu/drm/msm/adreno/a6xx_gpu.c       |  2 +-
 drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c |  4 +-
 drivers/gpu/drm/msm/adreno/adreno_gpu.c     |  2 +-
 drivers/gpu/drm/msm/msm_gem.c               | 56 ++++-----------------
 drivers/gpu/drm/msm/msm_gem.h               |  7 +--
 drivers/gpu/drm/msm/msm_gem_submit.c        |  2 +-
 drivers/gpu/drm/msm/msm_gpu.c               |  4 +-
 drivers/gpu/drm/msm/msm_ringbuffer.c        |  2 +-
 13 files changed, 33 insertions(+), 77 deletions(-)

diff --git a/drivers/gpu/drm/msm/adreno/a5xx_debugfs.c b/drivers/gpu/drm/msm/adreno/a5xx_debugfs.c
index fc2c905b6c9e..c9d11d57aed6 100644
--- a/drivers/gpu/drm/msm/adreno/a5xx_debugfs.c
+++ b/drivers/gpu/drm/msm/adreno/a5xx_debugfs.c
@@ -117,13 +117,13 @@ reset_set(void *data, u64 val)
 
 	if (a5xx_gpu->pm4_bo) {
 		msm_gem_unpin_iova(a5xx_gpu->pm4_bo, gpu->aspace);
-		drm_gem_object_put_locked(a5xx_gpu->pm4_bo);
+		drm_gem_object_put(a5xx_gpu->pm4_bo);
 		a5xx_gpu->pm4_bo = NULL;
 	}
 
 	if (a5xx_gpu->pfp_bo) {
 		msm_gem_unpin_iova(a5xx_gpu->pfp_bo, gpu->aspace);
-		drm_gem_object_put_locked(a5xx_gpu->pfp_bo);
+		drm_gem_object_put(a5xx_gpu->pfp_bo);
 		a5xx_gpu->pfp_bo = NULL;
 	}
 
diff --git a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
index 7a271de9a212..0a93ed1d6b06 100644
--- a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
@@ -1415,7 +1415,7 @@ struct a5xx_gpu_state {
 static int a5xx_crashdumper_init(struct msm_gpu *gpu,
 		struct a5xx_crashdumper *dumper)
 {
-	dumper->ptr = msm_gem_kernel_new_locked(gpu->dev,
+	dumper->ptr = msm_gem_kernel_new(gpu->dev,
 		SZ_1M, MSM_BO_WC, gpu->aspace,
 		&dumper->bo, &dumper->iova);
 
@@ -1517,7 +1517,7 @@ static void a5xx_gpu_state_get_hlsq_regs(struct msm_gpu *gpu,
 
 	if (a5xx_crashdumper_run(gpu, &dumper)) {
 		kfree(a5xx_state->hlsqregs);
-		msm_gem_kernel_put(dumper.bo, gpu->aspace, true);
+		msm_gem_kernel_put(dumper.bo, gpu->aspace);
 		return;
 	}
 
@@ -1525,7 +1525,7 @@ static void a5xx_gpu_state_get_hlsq_regs(struct msm_gpu *gpu,
 	memcpy(a5xx_state->hlsqregs, dumper.ptr + (256 * SZ_1K),
 		count * sizeof(u32));
 
-	msm_gem_kernel_put(dumper.bo, gpu->aspace, true);
+	msm_gem_kernel_put(dumper.bo, gpu->aspace);
 }
 
 static struct msm_gpu_state *a5xx_gpu_state_get(struct msm_gpu *gpu)
diff --git a/drivers/gpu/drm/msm/adreno/a5xx_power.c b/drivers/gpu/drm/msm/adreno/a5xx_power.c
index cdb165236a88..0e63a1429189 100644
--- a/drivers/gpu/drm/msm/adreno/a5xx_power.c
+++ b/drivers/gpu/drm/msm/adreno/a5xx_power.c
@@ -362,7 +362,7 @@ void a5xx_gpmu_ucode_init(struct msm_gpu *gpu)
 	 */
 	bosize = (cmds_size + (cmds_size / TYPE4_MAX_PAYLOAD) + 1) << 2;
 
-	ptr = msm_gem_kernel_new_locked(drm, bosize,
+	ptr = msm_gem_kernel_new(drm, bosize,
 		MSM_BO_WC | MSM_BO_GPU_READONLY, gpu->aspace,
 		&a5xx_gpu->gpmu_bo, &a5xx_gpu->gpmu_iova);
 	if (IS_ERR(ptr))
diff --git a/drivers/gpu/drm/msm/adreno/a5xx_preempt.c b/drivers/gpu/drm/msm/adreno/a5xx_preempt.c
index ee72510ff8ce..8abc9a2b114a 100644
--- a/drivers/gpu/drm/msm/adreno/a5xx_preempt.c
+++ b/drivers/gpu/drm/msm/adreno/a5xx_preempt.c
@@ -240,7 +240,7 @@ static int preempt_init_ring(struct a5xx_gpu *a5xx_gpu,
 		A5XX_PREEMPT_COUNTER_SIZE,
 		MSM_BO_WC, gpu->aspace, &counters_bo, &counters_iova);
 	if (IS_ERR(counters)) {
-		msm_gem_kernel_put(bo, gpu->aspace, true);
+		msm_gem_kernel_put(bo, gpu->aspace);
 		return PTR_ERR(counters);
 	}
 
@@ -272,9 +272,8 @@ void a5xx_preempt_fini(struct msm_gpu *gpu)
 	int i;
 
 	for (i = 0; i < gpu->nr_rings; i++) {
-		msm_gem_kernel_put(a5xx_gpu->preempt_bo[i], gpu->aspace, true);
-		msm_gem_kernel_put(a5xx_gpu->preempt_counters_bo[i],
-			gpu->aspace, true);
+		msm_gem_kernel_put(a5xx_gpu->preempt_bo[i], gpu->aspace);
+		msm_gem_kernel_put(a5xx_gpu->preempt_counters_bo[i], gpu->aspace);
 	}
 }
 
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
index b349692219b7..d7cec7f0dde0 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
@@ -1129,12 +1129,12 @@ int a6xx_gmu_stop(struct a6xx_gpu *a6xx_gpu)
 
 static void a6xx_gmu_memory_free(struct a6xx_gmu *gmu)
 {
-	msm_gem_kernel_put(gmu->hfi.obj, gmu->aspace, false);
-	msm_gem_kernel_put(gmu->debug.obj, gmu->aspace, false);
-	msm_gem_kernel_put(gmu->icache.obj, gmu->aspace, false);
-	msm_gem_kernel_put(gmu->dcache.obj, gmu->aspace, false);
-	msm_gem_kernel_put(gmu->dummy.obj, gmu->aspace, false);
-	msm_gem_kernel_put(gmu->log.obj, gmu->aspace, false);
+	msm_gem_kernel_put(gmu->hfi.obj, gmu->aspace);
+	msm_gem_kernel_put(gmu->debug.obj, gmu->aspace);
+	msm_gem_kernel_put(gmu->icache.obj, gmu->aspace);
+	msm_gem_kernel_put(gmu->dcache.obj, gmu->aspace);
+	msm_gem_kernel_put(gmu->dummy.obj, gmu->aspace);
+	msm_gem_kernel_put(gmu->log.obj, gmu->aspace);
 
 	gmu->aspace->mmu->funcs->detach(gmu->aspace->mmu);
 	msm_gem_address_space_put(gmu->aspace);
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
index 91f637b908f4..55ea136b8933 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
@@ -1035,7 +1035,7 @@ static int a6xx_hw_init(struct msm_gpu *gpu)
 
 	if (adreno_gpu->base.hw_apriv || a6xx_gpu->has_whereami) {
 		if (!a6xx_gpu->shadow_bo) {
-			a6xx_gpu->shadow = msm_gem_kernel_new_locked(gpu->dev,
+			a6xx_gpu->shadow = msm_gem_kernel_new(gpu->dev,
 				sizeof(u32) * gpu->nr_rings,
 				MSM_BO_WC | MSM_BO_MAP_PRIV,
 				gpu->aspace, &a6xx_gpu->shadow_bo,
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c
index ad4ea0ed5d99..e8f65cd8eca6 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c
@@ -112,7 +112,7 @@ static void *state_kmemdup(struct a6xx_gpu_state *a6xx_state, void *src,
 static int a6xx_crashdumper_init(struct msm_gpu *gpu,
 		struct a6xx_crashdumper *dumper)
 {
-	dumper->ptr = msm_gem_kernel_new_locked(gpu->dev,
+	dumper->ptr = msm_gem_kernel_new(gpu->dev,
 		SZ_1M, MSM_BO_WC, gpu->aspace,
 		&dumper->bo, &dumper->iova);
 
@@ -961,7 +961,7 @@ struct msm_gpu_state *a6xx_gpu_state_get(struct msm_gpu *gpu)
 		a6xx_get_clusters(gpu, a6xx_state, dumper);
 		a6xx_get_dbgahb_clusters(gpu, a6xx_state, dumper);
 
-		msm_gem_kernel_put(dumper->bo, gpu->aspace, true);
+		msm_gem_kernel_put(dumper->bo, gpu->aspace);
 	}
 
 	if (snapshot_debugbus)
diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
index 9f5a30234b33..bad4809b68ef 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
@@ -390,7 +390,7 @@ struct drm_gem_object *adreno_fw_create_bo(struct msm_gpu *gpu,
 	struct drm_gem_object *bo;
 	void *ptr;
 
-	ptr = msm_gem_kernel_new_locked(gpu->dev, fw->size - 4,
+	ptr = msm_gem_kernel_new(gpu->dev, fw->size - 4,
 		MSM_BO_WC | MSM_BO_GPU_READONLY, gpu->aspace, &bo, iova);
 
 	if (IS_ERR(ptr))
diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c
index 5b665ed8a605..4e99c448b83a 100644
--- a/drivers/gpu/drm/msm/msm_gem.c
+++ b/drivers/gpu/drm/msm/msm_gem.c
@@ -1064,7 +1064,7 @@ void msm_gem_describe_objects(struct list_head *list, struct seq_file *m)
 }
 #endif
 
-/* don't call directly!  Use drm_gem_object_put_locked() and friends */
+/* don't call directly!  Use drm_gem_object_put() */
 void msm_gem_free_object(struct drm_gem_object *obj)
 {
 	struct msm_gem_object *msm_obj = to_msm_bo(obj);
@@ -1195,8 +1195,7 @@ static int msm_gem_new_impl(struct drm_device *dev,
 	return 0;
 }
 
-static struct drm_gem_object *_msm_gem_new(struct drm_device *dev,
-		uint32_t size, uint32_t flags, bool struct_mutex_locked)
+struct drm_gem_object *msm_gem_new(struct drm_device *dev, uint32_t size, uint32_t flags)
 {
 	struct msm_drm_private *priv = dev->dev_private;
 	struct msm_gem_object *msm_obj;
@@ -1283,26 +1282,10 @@ static struct drm_gem_object *_msm_gem_new(struct drm_device *dev,
 	return obj;
 
 fail:
-	if (struct_mutex_locked) {
-		drm_gem_object_put_locked(obj);
-	} else {
-		drm_gem_object_put(obj);
-	}
+	drm_gem_object_put(obj);
 	return ERR_PTR(ret);
 }
 
-struct drm_gem_object *msm_gem_new_locked(struct drm_device *dev,
-		uint32_t size, uint32_t flags)
-{
-	return _msm_gem_new(dev, size, flags, true);
-}
-
-struct drm_gem_object *msm_gem_new(struct drm_device *dev,
-		uint32_t size, uint32_t flags)
-{
-	return _msm_gem_new(dev, size, flags, false);
-}
-
 struct drm_gem_object *msm_gem_import(struct drm_device *dev,
 		struct dma_buf *dmabuf, struct sg_table *sgt)
 {
@@ -1361,12 +1344,12 @@ struct drm_gem_object *msm_gem_import(struct drm_device *dev,
 	return ERR_PTR(ret);
 }
 
-static void *_msm_gem_kernel_new(struct drm_device *dev, uint32_t size,
+void *msm_gem_kernel_new(struct drm_device *dev, uint32_t size,
 		uint32_t flags, struct msm_gem_address_space *aspace,
-		struct drm_gem_object **bo, uint64_t *iova, bool locked)
+		struct drm_gem_object **bo, uint64_t *iova)
 {
 	void *vaddr;
-	struct drm_gem_object *obj = _msm_gem_new(dev, size, flags, locked);
+	struct drm_gem_object *obj = msm_gem_new(dev, size, flags);
 	int ret;
 
 	if (IS_ERR(obj))
@@ -1390,42 +1373,21 @@ static void *_msm_gem_kernel_new(struct drm_device *dev, uint32_t size,
 
 	return vaddr;
 err:
-	if (locked)
-		drm_gem_object_put_locked(obj);
-	else
-		drm_gem_object_put(obj);
+	drm_gem_object_put(obj);
 
 	return ERR_PTR(ret);
 
 }
 
-void *msm_gem_kernel_new(struct drm_device *dev, uint32_t size,
-		uint32_t flags, struct msm_gem_address_space *aspace,
-		struct drm_gem_object **bo, uint64_t *iova)
-{
-	return _msm_gem_kernel_new(dev, size, flags, aspace, bo, iova, false);
-}
-
-void *msm_gem_kernel_new_locked(struct drm_device *dev, uint32_t size,
-		uint32_t flags, struct msm_gem_address_space *aspace,
-		struct drm_gem_object **bo, uint64_t *iova)
-{
-	return _msm_gem_kernel_new(dev, size, flags, aspace, bo, iova, true);
-}
-
 void msm_gem_kernel_put(struct drm_gem_object *bo,
-		struct msm_gem_address_space *aspace, bool locked)
+		struct msm_gem_address_space *aspace)
 {
 	if (IS_ERR_OR_NULL(bo))
 		return;
 
 	msm_gem_put_vaddr(bo);
 	msm_gem_unpin_iova(bo, aspace);
-
-	if (locked)
-		drm_gem_object_put_locked(bo);
-	else
-		drm_gem_object_put(bo);
+	drm_gem_object_put(bo);
 }
 
 void msm_gem_object_set_name(struct drm_gem_object *bo, const char *fmt, ...)
diff --git a/drivers/gpu/drm/msm/msm_gem.h b/drivers/gpu/drm/msm/msm_gem.h
index d69fcb37ce17..71ccf87a646b 100644
--- a/drivers/gpu/drm/msm/msm_gem.h
+++ b/drivers/gpu/drm/msm/msm_gem.h
@@ -154,16 +154,11 @@ int msm_gem_new_handle(struct drm_device *dev, struct drm_file *file,
 		uint32_t size, uint32_t flags, uint32_t *handle, char *name);
 struct drm_gem_object *msm_gem_new(struct drm_device *dev,
 		uint32_t size, uint32_t flags);
-struct drm_gem_object *msm_gem_new_locked(struct drm_device *dev,
-		uint32_t size, uint32_t flags);
 void *msm_gem_kernel_new(struct drm_device *dev, uint32_t size,
 		uint32_t flags, struct msm_gem_address_space *aspace,
 		struct drm_gem_object **bo, uint64_t *iova);
-void *msm_gem_kernel_new_locked(struct drm_device *dev, uint32_t size,
-		uint32_t flags, struct msm_gem_address_space *aspace,
-		struct drm_gem_object **bo, uint64_t *iova);
 void msm_gem_kernel_put(struct drm_gem_object *bo,
-		struct msm_gem_address_space *aspace, bool locked);
+		struct msm_gem_address_space *aspace);
 struct drm_gem_object *msm_gem_import(struct drm_device *dev,
 		struct dma_buf *dmabuf, struct sg_table *sgt);
 __printf(2, 3)
diff --git a/drivers/gpu/drm/msm/msm_gem_submit.c b/drivers/gpu/drm/msm/msm_gem_submit.c
index 6d46f9275a40..e789f68d5be1 100644
--- a/drivers/gpu/drm/msm/msm_gem_submit.c
+++ b/drivers/gpu/drm/msm/msm_gem_submit.c
@@ -452,7 +452,7 @@ static void submit_cleanup(struct msm_gem_submit *submit)
 		struct msm_gem_object *msm_obj = submit->bos[i].obj;
 		submit_unlock_unpin_bo(submit, i, false);
 		list_del_init(&msm_obj->submit_entry);
-		drm_gem_object_put_locked(&msm_obj->base);
+		drm_gem_object_put(&msm_obj->base);
 	}
 }
 
diff --git a/drivers/gpu/drm/msm/msm_gpu.c b/drivers/gpu/drm/msm/msm_gpu.c
index c4ed8694f721..a0589666b1a3 100644
--- a/drivers/gpu/drm/msm/msm_gpu.c
+++ b/drivers/gpu/drm/msm/msm_gpu.c
@@ -992,7 +992,7 @@ int msm_gpu_init(struct drm_device *drm, struct platform_device *pdev,
 		gpu->rb[i] = NULL;
 	}
 
-	msm_gem_kernel_put(gpu->memptrs_bo, gpu->aspace, false);
+	msm_gem_kernel_put(gpu->memptrs_bo, gpu->aspace);
 
 	platform_set_drvdata(pdev, NULL);
 	return ret;
@@ -1011,7 +1011,7 @@ void msm_gpu_cleanup(struct msm_gpu *gpu)
 		gpu->rb[i] = NULL;
 	}
 
-	msm_gem_kernel_put(gpu->memptrs_bo, gpu->aspace, false);
+	msm_gem_kernel_put(gpu->memptrs_bo, gpu->aspace);
 
 	if (!IS_ERR_OR_NULL(gpu->aspace)) {
 		gpu->aspace->mmu->funcs->detach(gpu->aspace->mmu);
diff --git a/drivers/gpu/drm/msm/msm_ringbuffer.c b/drivers/gpu/drm/msm/msm_ringbuffer.c
index 054461662af5..437cca57d005 100644
--- a/drivers/gpu/drm/msm/msm_ringbuffer.c
+++ b/drivers/gpu/drm/msm/msm_ringbuffer.c
@@ -67,7 +67,7 @@ void msm_ringbuffer_destroy(struct msm_ringbuffer *ring)
 
 	msm_fence_context_free(ring->fctx);
 
-	msm_gem_kernel_put(ring->bo, ring->gpu->aspace, false);
+	msm_gem_kernel_put(ring->bo, ring->gpu->aspace);
 
 	kfree(ring);
 }
-- 
2.31.1

[PATCH v3 05/13] drm/msm/submit: Simplify out-fence-fd handling

[Rob Clark]

From: Rob Clark <robdclark@chromium.org>

No need for this to be split in two parts.

Signed-off-by: Rob Clark <robdclark@chromium.org>
Acked-by: Christian König <christian.koenig@amd.com>
---
 drivers/gpu/drm/msm/msm_gem_submit.c | 10 +++-------
 1 file changed, 3 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/msm/msm_gem_submit.c b/drivers/gpu/drm/msm/msm_gem_submit.c
index e789f68d5be1..8abd743adfb0 100644
--- a/drivers/gpu/drm/msm/msm_gem_submit.c
+++ b/drivers/gpu/drm/msm/msm_gem_submit.c
@@ -645,7 +645,6 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data,
 	struct msm_file_private *ctx = file->driver_priv;
 	struct msm_gem_submit *submit;
 	struct msm_gpu *gpu = priv->gpu;
-	struct sync_file *sync_file = NULL;
 	struct msm_gpu_submitqueue *queue;
 	struct msm_ringbuffer *ring;
 	struct msm_submit_post_dep *post_deps = NULL;
@@ -824,22 +823,19 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data,
 	}
 
 	if (args->flags & MSM_SUBMIT_FENCE_FD_OUT) {
-		sync_file = sync_file_create(submit->fence);
+		struct sync_file *sync_file = sync_file_create(submit->fence);
 		if (!sync_file) {
 			ret = -ENOMEM;
 			goto out;
 		}
+		fd_install(out_fence_fd, sync_file->file);
+		args->fence_fd = out_fence_fd;
 	}
 
 	msm_gpu_submit(gpu, submit);
 
 	args->fence = submit->fence->seqno;
 
-	if (args->flags & MSM_SUBMIT_FENCE_FD_OUT) {
-		fd_install(out_fence_fd, sync_file->file);
-		args->fence_fd = out_fence_fd;
-	}
-
 	msm_reset_syncobjs(syncobjs_to_reset, args->nr_in_syncobjs);
 	msm_process_post_deps(post_deps, args->nr_out_syncobjs,
 	                      submit->fence);
-- 
2.31.1

[PATCH v3 06/13] drm/msm: Consolidate submit bo state

[Rob Clark]

From: Rob Clark <robdclark@chromium.org>

Move all the locked/active/pinned state handling to msm_gem_submit.c.
In particular, for drm/scheduler, we'll need to do all this before
pushing the submit job to the scheduler.  But while we're at it we can
get rid of the dupicate pin and refcnt.

Signed-off-by: Rob Clark <robdclark@chromium.org>
Acked-by: Christian König <christian.koenig@amd.com>
---
 drivers/gpu/drm/msm/msm_gem.h        |  2 +
 drivers/gpu/drm/msm/msm_gem_submit.c | 92 ++++++++++++++++++++++------
 drivers/gpu/drm/msm/msm_gpu.c        | 29 +--------
 3 files changed, 75 insertions(+), 48 deletions(-)

diff --git a/drivers/gpu/drm/msm/msm_gem.h b/drivers/gpu/drm/msm/msm_gem.h
index 71ccf87a646b..da3af702a6c8 100644
--- a/drivers/gpu/drm/msm/msm_gem.h
+++ b/drivers/gpu/drm/msm/msm_gem.h
@@ -361,6 +361,8 @@ static inline void msm_gem_submit_put(struct msm_gem_submit *submit)
 	kref_put(&submit->ref, __msm_gem_submit_destroy);
 }
 
+void msm_submit_retire(struct msm_gem_submit *submit);
+
 /* helper to determine of a buffer in submit should be dumped, used for both
  * devcoredump and debugfs cmdstream dumping:
  */
diff --git a/drivers/gpu/drm/msm/msm_gem_submit.c b/drivers/gpu/drm/msm/msm_gem_submit.c
index 8abd743adfb0..4f02fa3c78f9 100644
--- a/drivers/gpu/drm/msm/msm_gem_submit.c
+++ b/drivers/gpu/drm/msm/msm_gem_submit.c
@@ -23,8 +23,8 @@
 
 /* make sure these don't conflict w/ MSM_SUBMIT_BO_x */
 #define BO_VALID    0x8000   /* is current addr in cmdstream correct/valid? */
-#define BO_LOCKED   0x4000
-#define BO_PINNED   0x2000
+#define BO_LOCKED   0x4000   /* obj lock is held */
+#define BO_PINNED   0x2000   /* obj is pinned and on active list */
 
 static struct msm_gem_submit *submit_create(struct drm_device *dev,
 		struct msm_gpu *gpu,
@@ -220,21 +220,33 @@ static int submit_lookup_cmds(struct msm_gem_submit *submit,
 	return ret;
 }
 
-static void submit_unlock_unpin_bo(struct msm_gem_submit *submit,
-		int i, bool backoff)
+/* Unwind bo state, according to cleanup_flags.  In the success case, only
+ * the lock is dropped at the end of the submit (and active/pin ref is dropped
+ * later when the submit is retired).
+ */
+static void submit_cleanup_bo(struct msm_gem_submit *submit, int i,
+		unsigned cleanup_flags)
 {
-	struct msm_gem_object *msm_obj = submit->bos[i].obj;
+	struct drm_gem_object *obj = &submit->bos[i].obj->base;
+	unsigned flags = submit->bos[i].flags & cleanup_flags;
 
-	if (submit->bos[i].flags & BO_PINNED)
-		msm_gem_unpin_iova_locked(&msm_obj->base, submit->aspace);
+	if (flags & BO_PINNED) {
+		msm_gem_unpin_iova_locked(obj, submit->aspace);
+		msm_gem_active_put(obj);
+	}
 
-	if (submit->bos[i].flags & BO_LOCKED)
-		dma_resv_unlock(msm_obj->base.resv);
+	if (flags & BO_LOCKED)
+		dma_resv_unlock(obj->resv);
 
-	if (backoff && !(submit->bos[i].flags & BO_VALID))
-		submit->bos[i].iova = 0;
+	submit->bos[i].flags &= ~cleanup_flags;
+}
 
-	submit->bos[i].flags &= ~(BO_LOCKED | BO_PINNED);
+static void submit_unlock_unpin_bo(struct msm_gem_submit *submit, int i)
+{
+	submit_cleanup_bo(submit, i, BO_PINNED | BO_LOCKED);
+
+	if (!(submit->bos[i].flags & BO_VALID))
+		submit->bos[i].iova = 0;
 }
 
 /* This is where we make sure all the bo's are reserved and pin'd: */
@@ -266,10 +278,10 @@ static int submit_lock_objects(struct msm_gem_submit *submit)
 
 fail:
 	for (; i >= 0; i--)
-		submit_unlock_unpin_bo(submit, i, true);
+		submit_unlock_unpin_bo(submit, i);
 
 	if (slow_locked > 0)
-		submit_unlock_unpin_bo(submit, slow_locked, true);
+		submit_unlock_unpin_bo(submit, slow_locked);
 
 	if (ret == -EDEADLK) {
 		struct msm_gem_object *msm_obj = submit->bos[contended].obj;
@@ -325,16 +337,18 @@ static int submit_pin_objects(struct msm_gem_submit *submit)
 	submit->valid = true;
 
 	for (i = 0; i < submit->nr_bos; i++) {
-		struct msm_gem_object *msm_obj = submit->bos[i].obj;
+		struct drm_gem_object *obj = &submit->bos[i].obj->base;
 		uint64_t iova;
 
 		/* if locking succeeded, pin bo: */
-		ret = msm_gem_get_and_pin_iova_locked(&msm_obj->base,
+		ret = msm_gem_get_and_pin_iova_locked(obj,
 				submit->aspace, &iova);
 
 		if (ret)
 			break;
 
+		msm_gem_active_get(obj, submit->gpu);
+
 		submit->bos[i].flags |= BO_PINNED;
 
 		if (iova == submit->bos[i].iova) {
@@ -350,6 +364,20 @@ static int submit_pin_objects(struct msm_gem_submit *submit)
 	return ret;
 }
 
+static void submit_attach_object_fences(struct msm_gem_submit *submit)
+{
+	int i;
+
+	for (i = 0; i < submit->nr_bos; i++) {
+		struct drm_gem_object *obj = &submit->bos[i].obj->base;
+
+		if (submit->bos[i].flags & MSM_SUBMIT_BO_WRITE)
+			dma_resv_add_excl_fence(obj->resv, submit->fence);
+		else if (submit->bos[i].flags & MSM_SUBMIT_BO_READ)
+			dma_resv_add_shared_fence(obj->resv, submit->fence);
+	}
+}
+
 static int submit_bo(struct msm_gem_submit *submit, uint32_t idx,
 		struct msm_gem_object **obj, uint64_t *iova, bool *valid)
 {
@@ -444,18 +472,40 @@ static int submit_reloc(struct msm_gem_submit *submit, struct msm_gem_object *ob
 	return ret;
 }
 
-static void submit_cleanup(struct msm_gem_submit *submit)
+/* Cleanup submit at end of ioctl.  In the error case, this also drops
+ * references, unpins, and drops active refcnt.  In the non-error case,
+ * this is done when the submit is retired.
+ */
+static void submit_cleanup(struct msm_gem_submit *submit, bool error)
 {
+	unsigned cleanup_flags = BO_LOCKED;
 	unsigned i;
 
+	if (error)
+		cleanup_flags |= BO_PINNED;
+
 	for (i = 0; i < submit->nr_bos; i++) {
 		struct msm_gem_object *msm_obj = submit->bos[i].obj;
-		submit_unlock_unpin_bo(submit, i, false);
+		submit_cleanup_bo(submit, i, cleanup_flags);
 		list_del_init(&msm_obj->submit_entry);
-		drm_gem_object_put(&msm_obj->base);
+		if (error)
+			drm_gem_object_put(&msm_obj->base);
 	}
 }
 
+void msm_submit_retire(struct msm_gem_submit *submit)
+{
+	int i;
+
+	for (i = 0; i < submit->nr_bos; i++) {
+		struct drm_gem_object *obj = &submit->bos[i].obj->base;
+
+		msm_gem_lock(obj);
+		submit_cleanup_bo(submit, i, BO_PINNED);
+		msm_gem_unlock(obj);
+		drm_gem_object_put(obj);
+	}
+}
 
 struct msm_submit_post_dep {
 	struct drm_syncobj *syncobj;
@@ -832,6 +882,8 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data,
 		args->fence_fd = out_fence_fd;
 	}
 
+	submit_attach_object_fences(submit);
+
 	msm_gpu_submit(gpu, submit);
 
 	args->fence = submit->fence->seqno;
@@ -844,7 +896,7 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data,
 out:
 	pm_runtime_put(&gpu->pdev->dev);
 out_pre_pm:
-	submit_cleanup(submit);
+	submit_cleanup(submit, !!ret);
 	if (has_ww_ticket)
 		ww_acquire_fini(&submit->ticket);
 	msm_gem_submit_put(submit);
diff --git a/drivers/gpu/drm/msm/msm_gpu.c b/drivers/gpu/drm/msm/msm_gpu.c
index a0589666b1a3..5bfc4d24a956 100644
--- a/drivers/gpu/drm/msm/msm_gpu.c
+++ b/drivers/gpu/drm/msm/msm_gpu.c
@@ -647,7 +647,6 @@ static void retire_submit(struct msm_gpu *gpu, struct msm_ringbuffer *ring,
 	volatile struct msm_gpu_submit_stats *stats;
 	u64 elapsed, clock = 0;
 	unsigned long flags;
-	int i;
 
 	stats = &ring->memptrs->stats[index];
 	/* Convert 19.2Mhz alwayson ticks to nanoseconds for elapsed time */
@@ -663,15 +662,7 @@ static void retire_submit(struct msm_gpu *gpu, struct msm_ringbuffer *ring,
 	trace_msm_gpu_submit_retired(submit, elapsed, clock,
 		stats->alwayson_start, stats->alwayson_end);
 
-	for (i = 0; i < submit->nr_bos; i++) {
-		struct drm_gem_object *obj = &submit->bos[i].obj->base;
-
-		msm_gem_lock(obj);
-		msm_gem_active_put(obj);
-		msm_gem_unpin_iova_locked(obj, submit->aspace);
-		msm_gem_unlock(obj);
-		drm_gem_object_put(obj);
-	}
+	msm_submit_retire(submit);
 
 	pm_runtime_mark_last_busy(&gpu->pdev->dev);
 	pm_runtime_put_autosuspend(&gpu->pdev->dev);
@@ -748,7 +739,6 @@ void msm_gpu_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit)
 	struct msm_drm_private *priv = dev->dev_private;
 	struct msm_ringbuffer *ring = submit->ring;
 	unsigned long flags;
-	int i;
 
 	WARN_ON(!mutex_is_locked(&dev->struct_mutex));
 
@@ -762,23 +752,6 @@ void msm_gpu_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit)
 
 	update_sw_cntrs(gpu);
 
-	for (i = 0; i < submit->nr_bos; i++) {
-		struct msm_gem_object *msm_obj = submit->bos[i].obj;
-		struct drm_gem_object *drm_obj = &msm_obj->base;
-		uint64_t iova;
-
-		/* submit takes a reference to the bo and iova until retired: */
-		drm_gem_object_get(&msm_obj->base);
-		msm_gem_get_and_pin_iova_locked(&msm_obj->base, submit->aspace, &iova);
-
-		if (submit->bos[i].flags & MSM_SUBMIT_BO_WRITE)
-			dma_resv_add_excl_fence(drm_obj->resv, submit->fence);
-		else if (submit->bos[i].flags & MSM_SUBMIT_BO_READ)
-			dma_resv_add_shared_fence(drm_obj->resv, submit->fence);
-
-		msm_gem_active_get(drm_obj, gpu);
-	}
-
 	/*
 	 * ring->submits holds a ref to the submit, to deal with the case
 	 * that a submit completes before msm_ioctl_gem_submit() returns.
-- 
2.31.1

[PATCH v3 07/13] drm/msm: Track "seqno" fences by idr

[Rob Clark]

From: Rob Clark <robdclark@chromium.org>

Previously the (non-fd) fence returned from submit ioctl was a raw
seqno, which is scoped to the ring.  But from UABI standpoint, the
ioctls related to seqno fences all specify a submitqueue.  We can
take advantage of that to replace the seqno fences with a cyclic idr
handle.

This is in preperation for moving to drm scheduler, at which point
the submit ioctl will return after queuing the submit job to the
scheduler, but before the submit is written into the ring (and
therefore before a ring seqno has been assigned).  Which means we
need to replace the dma_fence that userspace may need to wait on
with a scheduler fence.

Signed-off-by: Rob Clark <robdclark@chromium.org>
Acked-by: Christian König <christian.koenig@amd.com>
---
 drivers/gpu/drm/msm/msm_drv.c         | 30 +++++++++++++++++++--
 drivers/gpu/drm/msm/msm_fence.c       | 39 ---------------------------
 drivers/gpu/drm/msm/msm_fence.h       |  2 --
 drivers/gpu/drm/msm/msm_gem.h         |  1 +
 drivers/gpu/drm/msm/msm_gem_submit.c  | 23 +++++++++++++++-
 drivers/gpu/drm/msm/msm_gpu.h         |  5 ++++
 drivers/gpu/drm/msm/msm_submitqueue.c |  5 ++++
 7 files changed, 61 insertions(+), 44 deletions(-)

diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c
index 9b8fa2ad0d84..1594ae39d54f 100644
--- a/drivers/gpu/drm/msm/msm_drv.c
+++ b/drivers/gpu/drm/msm/msm_drv.c
@@ -911,6 +911,7 @@ static int msm_ioctl_wait_fence(struct drm_device *dev, void *data,
 	ktime_t timeout = to_ktime(args->timeout);
 	struct msm_gpu_submitqueue *queue;
 	struct msm_gpu *gpu = priv->gpu;
+	struct dma_fence *fence;
 	int ret;
 
 	if (args->pad) {
@@ -925,10 +926,35 @@ static int msm_ioctl_wait_fence(struct drm_device *dev, void *data,
 	if (!queue)
 		return -ENOENT;
 
-	ret = msm_wait_fence(gpu->rb[queue->prio]->fctx, args->fence, &timeout,
-		true);
+	/*
+	 * Map submitqueue scoped "seqno" (which is actually an idr key)
+	 * back to underlying dma-fence
+	 *
+	 * The fence is removed from the fence_idr when the submit is
+	 * retired, so if the fence is not found it means there is nothing
+	 * to wait for
+	 */
+	ret = mutex_lock_interruptible(&queue->lock);
+	if (ret)
+		return ret;
+	fence = idr_find(&queue->fence_idr, args->fence);
+	if (fence)
+		fence = dma_fence_get_rcu(fence);
+	mutex_unlock(&queue->lock);
+
+	if (!fence)
+		return 0;
 
+	ret = dma_fence_wait_timeout(fence, true, timeout_to_jiffies(&timeout));
+	if (ret == 0) {
+		ret = -ETIMEDOUT;
+	} else if (ret != -ERESTARTSYS) {
+		ret = 0;
+	}
+
+	dma_fence_put(fence);
 	msm_submitqueue_put(queue);
+
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/msm/msm_fence.c b/drivers/gpu/drm/msm/msm_fence.c
index b92a9091a1e2..d8228029708e 100644
--- a/drivers/gpu/drm/msm/msm_fence.c
+++ b/drivers/gpu/drm/msm/msm_fence.c
@@ -45,45 +45,6 @@ static inline bool fence_completed(struct msm_fence_context *fctx, uint32_t fenc
 		(int32_t)(*fctx->fenceptr - fence) >= 0;
 }
 
-/* legacy path for WAIT_FENCE ioctl: */
-int msm_wait_fence(struct msm_fence_context *fctx, uint32_t fence,
-		ktime_t *timeout, bool interruptible)
-{
-	int ret;
-
-	if (fence > fctx->last_fence) {
-		DRM_ERROR_RATELIMITED("%s: waiting on invalid fence: %u (of %u)\n",
-				fctx->name, fence, fctx->last_fence);
-		return -EINVAL;
-	}
-
-	if (!timeout) {
-		/* no-wait: */
-		ret = fence_completed(fctx, fence) ? 0 : -EBUSY;
-	} else {
-		unsigned long remaining_jiffies = timeout_to_jiffies(timeout);
-
-		if (interruptible)
-			ret = wait_event_interruptible_timeout(fctx->event,
-				fence_completed(fctx, fence),
-				remaining_jiffies);
-		else
-			ret = wait_event_timeout(fctx->event,
-				fence_completed(fctx, fence),
-				remaining_jiffies);
-
-		if (ret == 0) {
-			DBG("timeout waiting for fence: %u (completed: %u)",
-					fence, fctx->completed_fence);
-			ret = -ETIMEDOUT;
-		} else if (ret != -ERESTARTSYS) {
-			ret = 0;
-		}
-	}
-
-	return ret;
-}
-
 /* called from workqueue */
 void msm_update_fence(struct msm_fence_context *fctx, uint32_t fence)
 {
diff --git a/drivers/gpu/drm/msm/msm_fence.h b/drivers/gpu/drm/msm/msm_fence.h
index 6ab97062ff1a..6de97d0f5153 100644
--- a/drivers/gpu/drm/msm/msm_fence.h
+++ b/drivers/gpu/drm/msm/msm_fence.h
@@ -57,8 +57,6 @@ struct msm_fence_context * msm_fence_context_alloc(struct drm_device *dev,
 		volatile uint32_t *fenceptr, const char *name);
 void msm_fence_context_free(struct msm_fence_context *fctx);
 
-int msm_wait_fence(struct msm_fence_context *fctx, uint32_t fence,
-		ktime_t *timeout, bool interruptible);
 void msm_update_fence(struct msm_fence_context *fctx, uint32_t fence);
 
 struct dma_fence * msm_fence_alloc(struct msm_fence_context *fctx);
diff --git a/drivers/gpu/drm/msm/msm_gem.h b/drivers/gpu/drm/msm/msm_gem.h
index da3af702a6c8..e0579abda5b9 100644
--- a/drivers/gpu/drm/msm/msm_gem.h
+++ b/drivers/gpu/drm/msm/msm_gem.h
@@ -320,6 +320,7 @@ struct msm_gem_submit {
 	struct ww_acquire_ctx ticket;
 	uint32_t seqno;		/* Sequence number of the submit on the ring */
 	struct dma_fence *fence;
+	int fence_id;       /* key into queue->fence_idr */
 	struct msm_gpu_submitqueue *queue;
 	struct pid *pid;    /* submitting process */
 	bool fault_dumped;  /* Limit devcoredump dumping to one per submit */
diff --git a/drivers/gpu/drm/msm/msm_gem_submit.c b/drivers/gpu/drm/msm/msm_gem_submit.c
index 4f02fa3c78f9..f6f595aae2c5 100644
--- a/drivers/gpu/drm/msm/msm_gem_submit.c
+++ b/drivers/gpu/drm/msm/msm_gem_submit.c
@@ -68,7 +68,14 @@ void __msm_gem_submit_destroy(struct kref *kref)
 			container_of(kref, struct msm_gem_submit, ref);
 	unsigned i;
 
+	if (submit->fence_id) {
+		mutex_lock(&submit->queue->lock);
+		idr_remove(&submit->queue->fence_idr, submit->fence_id);
+		mutex_unlock(&submit->queue->lock);
+	}
+
 	dma_fence_put(submit->fence);
+
 	put_pid(submit->pid);
 	msm_submitqueue_put(submit->queue);
 
@@ -872,6 +879,20 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data,
 		goto out;
 	}
 
+	/*
+	 * Allocate an id which can be used by WAIT_FENCE ioctl to map back
+	 * to the underlying fence.
+	 */
+	mutex_lock(&queue->lock);
+	submit->fence_id = idr_alloc_cyclic(&queue->fence_idr,
+			submit->fence, 0, INT_MAX, GFP_KERNEL);
+	mutex_unlock(&queue->lock);
+	if (submit->fence_id < 0) {
+		ret = submit->fence_id = 0;
+		submit->fence_id = 0;
+		goto out;
+	}
+
 	if (args->flags & MSM_SUBMIT_FENCE_FD_OUT) {
 		struct sync_file *sync_file = sync_file_create(submit->fence);
 		if (!sync_file) {
@@ -886,7 +907,7 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data,
 
 	msm_gpu_submit(gpu, submit);
 
-	args->fence = submit->fence->seqno;
+	args->fence = submit->fence_id;
 
 	msm_reset_syncobjs(syncobjs_to_reset, args->nr_in_syncobjs);
 	msm_process_post_deps(post_deps, args->nr_out_syncobjs,
diff --git a/drivers/gpu/drm/msm/msm_gpu.h b/drivers/gpu/drm/msm/msm_gpu.h
index 96efcb31e502..579627252540 100644
--- a/drivers/gpu/drm/msm/msm_gpu.h
+++ b/drivers/gpu/drm/msm/msm_gpu.h
@@ -263,6 +263,9 @@ struct msm_gpu_perfcntr {
  *             which set of pgtables do submits jobs associated with the
  *             submitqueue use)
  * @node:      node in the context's list of submitqueues
+ * @fence_idr: maps fence-id to dma_fence for userspace visible fence
+ *             seqno, protected by submitqueue lock
+ * @lock:      submitqueue lock
  * @ref:       reference count
  */
 struct msm_gpu_submitqueue {
@@ -272,6 +275,8 @@ struct msm_gpu_submitqueue {
 	int faults;
 	struct msm_file_private *ctx;
 	struct list_head node;
+	struct idr fence_idr;
+	struct mutex lock;
 	struct kref ref;
 };
 
diff --git a/drivers/gpu/drm/msm/msm_submitqueue.c b/drivers/gpu/drm/msm/msm_submitqueue.c
index 9e9fec61d629..66f8d0fb38b0 100644
--- a/drivers/gpu/drm/msm/msm_submitqueue.c
+++ b/drivers/gpu/drm/msm/msm_submitqueue.c
@@ -12,6 +12,8 @@ void msm_submitqueue_destroy(struct kref *kref)
 	struct msm_gpu_submitqueue *queue = container_of(kref,
 		struct msm_gpu_submitqueue, ref);
 
+	idr_destroy(&queue->fence_idr);
+
 	msm_file_private_put(queue->ctx);
 
 	kfree(queue);
@@ -89,6 +91,9 @@ int msm_submitqueue_create(struct drm_device *drm, struct msm_file_private *ctx,
 	if (id)
 		*id = queue->id;
 
+	idr_init(&queue->fence_idr);
+	mutex_init(&queue->lock);
+
 	list_add_tail(&queue->node, &ctx->submitqueues);
 
 	write_unlock(&ctx->queuelock);
-- 
2.31.1

[PATCH v3 08/13] drm/msm: Return ERR_PTR() from submit_create()

[Rob Clark]

From: Rob Clark <robdclark@chromium.org>

In the next patch, we start having more than a single potential failure
reason.

Signed-off-by: Rob Clark <robdclark@chromium.org>
Acked-by: Christian König <christian.koenig@amd.com>
---
 drivers/gpu/drm/msm/msm_gem_submit.c | 21 +++++++++------------
 1 file changed, 9 insertions(+), 12 deletions(-)

diff --git a/drivers/gpu/drm/msm/msm_gem_submit.c b/drivers/gpu/drm/msm/msm_gem_submit.c
index f6f595aae2c5..f570155bc086 100644
--- a/drivers/gpu/drm/msm/msm_gem_submit.c
+++ b/drivers/gpu/drm/msm/msm_gem_submit.c
@@ -32,30 +32,27 @@ static struct msm_gem_submit *submit_create(struct drm_device *dev,
 		uint32_t nr_cmds)
 {
 	struct msm_gem_submit *submit;
-	uint64_t sz = struct_size(submit, bos, nr_bos) +
-				  ((u64)nr_cmds * sizeof(submit->cmd[0]));
+	uint64_t sz;
+
+	sz = struct_size(submit, bos, nr_bos) +
+			((u64)nr_cmds * sizeof(submit->cmd[0]));
 
 	if (sz > SIZE_MAX)
-		return NULL;
+		return ERR_PTR(-ENOMEM);
 
-	submit = kmalloc(sz, GFP_KERNEL | __GFP_NOWARN | __GFP_NORETRY);
+	submit = kzalloc(sz, GFP_KERNEL | __GFP_NOWARN | __GFP_NORETRY);
 	if (!submit)
-		return NULL;
+		return ERR_PTR(-ENOMEM);
 
 	kref_init(&submit->ref);
 	submit->dev = dev;
 	submit->aspace = queue->ctx->aspace;
 	submit->gpu = gpu;
-	submit->fence = NULL;
 	submit->cmd = (void *)&submit->bos[nr_bos];
 	submit->queue = queue;
 	submit->ring = gpu->rb[queue->prio];
 	submit->fault_dumped = false;
 
-	/* initially, until copy_from_user() and bo lookup succeeds: */
-	submit->nr_bos = 0;
-	submit->nr_cmds = 0;
-
 	INIT_LIST_HEAD(&submit->node);
 	INIT_LIST_HEAD(&submit->bo_list);
 
@@ -799,8 +796,8 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data,
 
 	submit = submit_create(dev, gpu, queue, args->nr_bos,
 		args->nr_cmds);
-	if (!submit) {
-		ret = -ENOMEM;
+	if (IS_ERR(submit)) {
+		ret = PTR_ERR(submit);
 		goto out_unlock;
 	}
 
-- 
2.31.1

[PATCH v3 09/13] drm/msm: Conversion to drm scheduler

[Rob Clark]

From: Rob Clark <robdclark@chromium.org>

For existing adrenos, there is one or more ringbuffer, depending on
whether preemption is supported.  When preemption is supported, each
ringbuffer has it's own priority.  A submitqueue (which maps to a
gl context or vk queue in userspace) is mapped to a specific ring-
buffer at creation time, based on the submitqueue's priority.

Each ringbuffer has it's own drm_gpu_scheduler.  Each submitqueue
maps to a drm_sched_entity.  And each submit maps to a drm_sched_job.

Closes: https://gitlab.freedesktop.org/drm/msm/-/issues/4
Signed-off-by: Rob Clark <robdclark@chromium.org>
Acked-by: Christian König <christian.koenig@amd.com>
---
 drivers/gpu/drm/msm/Kconfig           |   1 +
 drivers/gpu/drm/msm/msm_gem.c         |  35 ------
 drivers/gpu/drm/msm/msm_gem.h         |  26 ++++-
 drivers/gpu/drm/msm/msm_gem_submit.c  | 161 +++++++++++++-------------
 drivers/gpu/drm/msm/msm_gpu.c         |  13 +--
 drivers/gpu/drm/msm/msm_gpu.h         |   2 +
 drivers/gpu/drm/msm/msm_rd.c          |   6 +-
 drivers/gpu/drm/msm/msm_ringbuffer.c  |  66 +++++++++++
 drivers/gpu/drm/msm/msm_ringbuffer.h  |  12 ++
 drivers/gpu/drm/msm/msm_submitqueue.c |  26 +++++
 10 files changed, 217 insertions(+), 131 deletions(-)

diff --git a/drivers/gpu/drm/msm/Kconfig b/drivers/gpu/drm/msm/Kconfig
index 52536e7adb95..dc7f3e40850b 100644
--- a/drivers/gpu/drm/msm/Kconfig
+++ b/drivers/gpu/drm/msm/Kconfig
@@ -14,6 +14,7 @@ config DRM_MSM
 	select REGULATOR
 	select DRM_KMS_HELPER
 	select DRM_PANEL
+	select DRM_SCHED
 	select SHMEM
 	select TMPFS
 	select QCOM_SCM if ARCH_QCOM
diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c
index 4e99c448b83a..a527a6b1d6ba 100644
--- a/drivers/gpu/drm/msm/msm_gem.c
+++ b/drivers/gpu/drm/msm/msm_gem.c
@@ -806,41 +806,6 @@ void msm_gem_vunmap(struct drm_gem_object *obj)
 	msm_obj->vaddr = NULL;
 }
 
-/* must be called before _move_to_active().. */
-int msm_gem_sync_object(struct drm_gem_object *obj,
-		struct msm_fence_context *fctx, bool exclusive)
-{
-	struct dma_resv_list *fobj;
-	struct dma_fence *fence;
-	int i, ret;
-
-	fobj = dma_resv_shared_list(obj->resv);
-	if (!fobj || (fobj->shared_count == 0)) {
-		fence = dma_resv_excl_fence(obj->resv);
-		/* don't need to wait on our own fences, since ring is fifo */
-		if (fence && (fence->context != fctx->context)) {
-			ret = dma_fence_wait(fence, true);
-			if (ret)
-				return ret;
-		}
-	}
-
-	if (!exclusive || !fobj)
-		return 0;
-
-	for (i = 0; i < fobj->shared_count; i++) {
-		fence = rcu_dereference_protected(fobj->shared[i],
-						dma_resv_held(obj->resv));
-		if (fence->context != fctx->context) {
-			ret = dma_fence_wait(fence, true);
-			if (ret)
-				return ret;
-		}
-	}
-
-	return 0;
-}
-
 void msm_gem_active_get(struct drm_gem_object *obj, struct msm_gpu *gpu)
 {
 	struct msm_gem_object *msm_obj = to_msm_bo(obj);
diff --git a/drivers/gpu/drm/msm/msm_gem.h b/drivers/gpu/drm/msm/msm_gem.h
index e0579abda5b9..a48114058ff9 100644
--- a/drivers/gpu/drm/msm/msm_gem.h
+++ b/drivers/gpu/drm/msm/msm_gem.h
@@ -9,6 +9,7 @@
 
 #include <linux/kref.h>
 #include <linux/dma-resv.h>
+#include "drm/gpu_scheduler.h"
 #include "msm_drv.h"
 
 /* Make all GEM related WARN_ON()s ratelimited.. when things go wrong they
@@ -143,8 +144,6 @@ void *msm_gem_get_vaddr_active(struct drm_gem_object *obj);
 void msm_gem_put_vaddr_locked(struct drm_gem_object *obj);
 void msm_gem_put_vaddr(struct drm_gem_object *obj);
 int msm_gem_madvise(struct drm_gem_object *obj, unsigned madv);
-int msm_gem_sync_object(struct drm_gem_object *obj,
-		struct msm_fence_context *fctx, bool exclusive);
 void msm_gem_active_get(struct drm_gem_object *obj, struct msm_gpu *gpu);
 void msm_gem_active_put(struct drm_gem_object *obj);
 int msm_gem_cpu_prep(struct drm_gem_object *obj, uint32_t op, ktime_t *timeout);
@@ -311,6 +310,7 @@ void msm_gem_vunmap(struct drm_gem_object *obj);
  * make it easier to unwind when things go wrong, etc).
  */
 struct msm_gem_submit {
+	struct drm_sched_job base;
 	struct kref ref;
 	struct drm_device *dev;
 	struct msm_gpu *gpu;
@@ -319,7 +319,22 @@ struct msm_gem_submit {
 	struct list_head bo_list;
 	struct ww_acquire_ctx ticket;
 	uint32_t seqno;		/* Sequence number of the submit on the ring */
-	struct dma_fence *fence;
+
+	/* Array of struct dma_fence * to block on before submitting this job.
+	 */
+	struct xarray deps;
+	unsigned long last_dep;
+
+	/* Hw fence, which is created when the scheduler executes the job, and
+	 * is signaled when the hw finishes (via seqno write from cmdstream)
+	 */
+	struct dma_fence *hw_fence;
+
+	/* Userspace visible fence, which is signaled by the scheduler after
+	 * the hw_fence is signaled.
+	 */
+	struct dma_fence *user_fence;
+
 	int fence_id;       /* key into queue->fence_idr */
 	struct msm_gpu_submitqueue *queue;
 	struct pid *pid;    /* submitting process */
@@ -350,6 +365,11 @@ struct msm_gem_submit {
 	} bos[];
 };
 
+static inline struct msm_gem_submit *to_msm_submit(struct drm_sched_job *job)
+{
+	return container_of(job, struct msm_gem_submit, base);
+}
+
 void __msm_gem_submit_destroy(struct kref *kref);
 
 static inline void msm_gem_submit_get(struct msm_gem_submit *submit)
diff --git a/drivers/gpu/drm/msm/msm_gem_submit.c b/drivers/gpu/drm/msm/msm_gem_submit.c
index f570155bc086..2b158433a6e5 100644
--- a/drivers/gpu/drm/msm/msm_gem_submit.c
+++ b/drivers/gpu/drm/msm/msm_gem_submit.c
@@ -33,6 +33,7 @@ static struct msm_gem_submit *submit_create(struct drm_device *dev,
 {
 	struct msm_gem_submit *submit;
 	uint64_t sz;
+	int ret;
 
 	sz = struct_size(submit, bos, nr_bos) +
 			((u64)nr_cmds * sizeof(submit->cmd[0]));
@@ -44,6 +45,14 @@ static struct msm_gem_submit *submit_create(struct drm_device *dev,
 	if (!submit)
 		return ERR_PTR(-ENOMEM);
 
+	ret = drm_sched_job_init(&submit->base, &queue->entity, queue);
+	if (ret) {
+		kfree(submit);
+		return ERR_PTR(ret);
+	}
+
+	xa_init_flags(&submit->deps, XA_FLAGS_ALLOC);
+
 	kref_init(&submit->ref);
 	submit->dev = dev;
 	submit->aspace = queue->ctx->aspace;
@@ -63,6 +72,8 @@ void __msm_gem_submit_destroy(struct kref *kref)
 {
 	struct msm_gem_submit *submit =
 			container_of(kref, struct msm_gem_submit, ref);
+	unsigned long index;
+	struct dma_fence *fence;
 	unsigned i;
 
 	if (submit->fence_id) {
@@ -71,7 +82,14 @@ void __msm_gem_submit_destroy(struct kref *kref)
 		mutex_unlock(&submit->queue->lock);
 	}
 
-	dma_fence_put(submit->fence);
+	xa_for_each (&submit->deps, index, fence) {
+		dma_fence_put(fence);
+	}
+
+	xa_destroy(&submit->deps);
+
+	dma_fence_put(submit->user_fence);
+	dma_fence_put(submit->hw_fence);
 
 	put_pid(submit->pid);
 	msm_submitqueue_put(submit->queue);
@@ -307,7 +325,7 @@ static int submit_fence_sync(struct msm_gem_submit *submit, bool no_implicit)
 	int i, ret = 0;
 
 	for (i = 0; i < submit->nr_bos; i++) {
-		struct msm_gem_object *msm_obj = submit->bos[i].obj;
+		struct drm_gem_object *obj = &submit->bos[i].obj->base;
 		bool write = submit->bos[i].flags & MSM_SUBMIT_BO_WRITE;
 
 		if (!write) {
@@ -316,8 +334,7 @@ static int submit_fence_sync(struct msm_gem_submit *submit, bool no_implicit)
 			 * strange place to call it.  OTOH this is a
 			 * convenient can-fail point to hook it in.
 			 */
-			ret = dma_resv_reserve_shared(msm_obj->base.resv,
-								1);
+			ret = dma_resv_reserve_shared(obj->resv, 1);
 			if (ret)
 				return ret;
 		}
@@ -325,7 +342,7 @@ static int submit_fence_sync(struct msm_gem_submit *submit, bool no_implicit)
 		if (no_implicit)
 			continue;
 
-		ret = msm_gem_sync_object(&msm_obj->base, submit->ring->fctx,
+		ret = drm_gem_fence_array_add_implicit(&submit->deps, obj,
 			write);
 		if (ret)
 			break;
@@ -376,9 +393,9 @@ static void submit_attach_object_fences(struct msm_gem_submit *submit)
 		struct drm_gem_object *obj = &submit->bos[i].obj->base;
 
 		if (submit->bos[i].flags & MSM_SUBMIT_BO_WRITE)
-			dma_resv_add_excl_fence(obj->resv, submit->fence);
+			dma_resv_add_excl_fence(obj->resv, submit->user_fence);
 		else if (submit->bos[i].flags & MSM_SUBMIT_BO_READ)
-			dma_resv_add_shared_fence(obj->resv, submit->fence);
+			dma_resv_add_shared_fence(obj->resv, submit->user_fence);
 	}
 }
 
@@ -517,12 +534,12 @@ struct msm_submit_post_dep {
 	struct dma_fence_chain *chain;
 };
 
-static struct drm_syncobj **msm_wait_deps(struct drm_device *dev,
-                                          struct drm_file *file,
-                                          uint64_t in_syncobjs_addr,
-                                          uint32_t nr_in_syncobjs,
-                                          size_t syncobj_stride,
-                                          struct msm_ringbuffer *ring)
+static struct drm_syncobj **msm_parse_deps(struct msm_gem_submit *submit,
+                                           struct drm_file *file,
+                                           uint64_t in_syncobjs_addr,
+                                           uint32_t nr_in_syncobjs,
+                                           size_t syncobj_stride,
+                                           struct msm_ringbuffer *ring)
 {
 	struct drm_syncobj **syncobjs = NULL;
 	struct drm_msm_gem_submit_syncobj syncobj_desc = {0};
@@ -546,7 +563,7 @@ static struct drm_syncobj **msm_wait_deps(struct drm_device *dev,
 		}
 
 		if (syncobj_desc.point &&
-		    !drm_core_check_feature(dev, DRIVER_SYNCOBJ_TIMELINE)) {
+		    !drm_core_check_feature(submit->dev, DRIVER_SYNCOBJ_TIMELINE)) {
 			ret = -EOPNOTSUPP;
 			break;
 		}
@@ -561,10 +578,7 @@ static struct drm_syncobj **msm_wait_deps(struct drm_device *dev,
 		if (ret)
 			break;
 
-		if (!dma_fence_match_context(fence, ring->fctx->context))
-			ret = dma_fence_wait(fence, true);
-
-		dma_fence_put(fence);
+		ret = drm_gem_fence_array_add(&submit->deps, fence);
 		if (ret)
 			break;
 
@@ -741,47 +755,6 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data,
 	trace_msm_gpu_submit(pid_nr(pid), ring->id, submitid,
 		args->nr_bos, args->nr_cmds);
 
-	if (args->flags & MSM_SUBMIT_FENCE_FD_IN) {
-		struct dma_fence *in_fence;
-
-		in_fence = sync_file_get_fence(args->fence_fd);
-
-		if (!in_fence)
-			return -EINVAL;
-
-		/*
-		 * Wait if the fence is from a foreign context, or if the fence
-		 * array contains any fence from a foreign context.
-		 */
-		ret = 0;
-		if (!dma_fence_match_context(in_fence, ring->fctx->context))
-			ret = dma_fence_wait(in_fence, true);
-
-		dma_fence_put(in_fence);
-		if (ret)
-			return ret;
-	}
-
-	if (args->flags & MSM_SUBMIT_SYNCOBJ_IN) {
-		syncobjs_to_reset = msm_wait_deps(dev, file,
-		                                  args->in_syncobjs,
-		                                  args->nr_in_syncobjs,
-		                                  args->syncobj_stride, ring);
-		if (IS_ERR(syncobjs_to_reset))
-			return PTR_ERR(syncobjs_to_reset);
-	}
-
-	if (args->flags & MSM_SUBMIT_SYNCOBJ_OUT) {
-		post_deps = msm_parse_post_deps(dev, file,
-		                                args->out_syncobjs,
-		                                args->nr_out_syncobjs,
-		                                args->syncobj_stride);
-		if (IS_ERR(post_deps)) {
-			ret = PTR_ERR(post_deps);
-			goto out_post_unlock;
-		}
-	}
-
 	ret = mutex_lock_interruptible(&dev->struct_mutex);
 	if (ret)
 		goto out_post_unlock;
@@ -807,22 +780,50 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data,
 	if (args->flags & MSM_SUBMIT_SUDO)
 		submit->in_rb = true;
 
+	if (args->flags & MSM_SUBMIT_FENCE_FD_IN) {
+		struct dma_fence *in_fence;
+
+		in_fence = sync_file_get_fence(args->fence_fd);
+
+		if (!in_fence) {
+			ret = -EINVAL;
+			goto out_unlock;
+		}
+
+		ret = drm_gem_fence_array_add(&submit->deps, in_fence);
+		if (ret)
+			goto out_unlock;
+	}
+
+	if (args->flags & MSM_SUBMIT_SYNCOBJ_IN) {
+		syncobjs_to_reset = msm_parse_deps(submit, file,
+		                                   args->in_syncobjs,
+		                                   args->nr_in_syncobjs,
+		                                   args->syncobj_stride, ring);
+		if (IS_ERR(syncobjs_to_reset)) {
+			ret = PTR_ERR(syncobjs_to_reset);
+			goto out_unlock;
+		}
+	}
+
+	if (args->flags & MSM_SUBMIT_SYNCOBJ_OUT) {
+		post_deps = msm_parse_post_deps(dev, file,
+		                                args->out_syncobjs,
+		                                args->nr_out_syncobjs,
+		                                args->syncobj_stride);
+		if (IS_ERR(post_deps)) {
+			ret = PTR_ERR(post_deps);
+			goto out_unlock;
+		}
+	}
+
 	ret = submit_lookup_objects(submit, args, file);
 	if (ret)
-		goto out_pre_pm;
+		goto out;
 
 	ret = submit_lookup_cmds(submit, args, file);
 	if (ret)
-		goto out_pre_pm;
-
-	/*
-	 * Thanks to dev_pm_opp opp_table_lock interactions with mm->mmap_sem
-	 * in the resume path, we need to to rpm get before we lock objs.
-	 * Which unfortunately might involve powering up the GPU sooner than
-	 * is necessary.  But at least in the explicit fencing case, we will
-	 * have already done all the fence waiting.
-	 */
-	pm_runtime_get_sync(&gpu->pdev->dev);
+		goto out;
 
 	/* copy_*_user while holding a ww ticket upsets lockdep */
 	ww_acquire_init(&submit->ticket, &reservation_ww_class);
@@ -869,12 +870,7 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data,
 
 	submit->nr_cmds = i;
 
-	submit->fence = msm_fence_alloc(ring->fctx);
-	if (IS_ERR(submit->fence)) {
-		ret = PTR_ERR(submit->fence);
-		submit->fence = NULL;
-		goto out;
-	}
+	submit->user_fence = dma_fence_get(&submit->base.s_fence->finished);
 
 	/*
 	 * Allocate an id which can be used by WAIT_FENCE ioctl to map back
@@ -882,7 +878,7 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data,
 	 */
 	mutex_lock(&queue->lock);
 	submit->fence_id = idr_alloc_cyclic(&queue->fence_idr,
-			submit->fence, 0, INT_MAX, GFP_KERNEL);
+			submit->user_fence, 0, INT_MAX, GFP_KERNEL);
 	mutex_unlock(&queue->lock);
 	if (submit->fence_id < 0) {
 		ret = submit->fence_id = 0;
@@ -891,7 +887,7 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data,
 	}
 
 	if (args->flags & MSM_SUBMIT_FENCE_FD_OUT) {
-		struct sync_file *sync_file = sync_file_create(submit->fence);
+		struct sync_file *sync_file = sync_file_create(submit->user_fence);
 		if (!sync_file) {
 			ret = -ENOMEM;
 			goto out;
@@ -902,18 +898,19 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data,
 
 	submit_attach_object_fences(submit);
 
-	msm_gpu_submit(gpu, submit);
+	/* The scheduler owns a ref now: */
+	msm_gem_submit_get(submit);
+
+	drm_sched_entity_push_job(&submit->base, &queue->entity);
 
 	args->fence = submit->fence_id;
 
 	msm_reset_syncobjs(syncobjs_to_reset, args->nr_in_syncobjs);
 	msm_process_post_deps(post_deps, args->nr_out_syncobjs,
-	                      submit->fence);
+	                      submit->user_fence);
 
 
 out:
-	pm_runtime_put(&gpu->pdev->dev);
-out_pre_pm:
 	submit_cleanup(submit, !!ret);
 	if (has_ww_ticket)
 		ww_acquire_fini(&submit->ticket);
diff --git a/drivers/gpu/drm/msm/msm_gpu.c b/drivers/gpu/drm/msm/msm_gpu.c
index 5bfc4d24a956..8a3a592da3a4 100644
--- a/drivers/gpu/drm/msm/msm_gpu.c
+++ b/drivers/gpu/drm/msm/msm_gpu.c
@@ -176,8 +176,8 @@ static void update_fences(struct msm_gpu *gpu, struct msm_ringbuffer *ring,
 			break;
 
 		msm_update_fence(submit->ring->fctx,
-			submit->fence->seqno);
-		dma_fence_signal(submit->fence);
+			submit->hw_fence->seqno);
+		dma_fence_signal(submit->hw_fence);
 	}
 	spin_unlock_irqrestore(&ring->submit_lock, flags);
 }
@@ -380,10 +380,6 @@ static void recover_worker(struct kthread_work *work)
 			put_task_struct(task);
 		}
 
-		/* msm_rd_dump_submit() needs bo locked to dump: */
-		for (i = 0; i < submit->nr_bos; i++)
-			msm_gem_lock(&submit->bos[i].obj->base);
-
 		if (comm && cmd) {
 			DRM_DEV_ERROR(dev->dev, "%s: offending task: %s (%s)\n",
 				gpu->name, comm, cmd);
@@ -393,9 +389,6 @@ static void recover_worker(struct kthread_work *work)
 		} else {
 			msm_rd_dump_submit(priv->hangrd, submit, NULL);
 		}
-
-		for (i = 0; i < submit->nr_bos; i++)
-			msm_gem_unlock(&submit->bos[i].obj->base);
 	}
 
 	/* Record the crash state */
@@ -704,7 +697,7 @@ static void retire_submits(struct msm_gpu *gpu)
 			 * been signalled, then later submits are not signalled
 			 * either, so we are also done.
 			 */
-			if (submit && dma_fence_is_signaled(submit->fence)) {
+			if (submit && dma_fence_is_signaled(submit->hw_fence)) {
 				retire_submit(gpu, ring, submit);
 			} else {
 				break;
diff --git a/drivers/gpu/drm/msm/msm_gpu.h b/drivers/gpu/drm/msm/msm_gpu.h
index 579627252540..b912cacaecc0 100644
--- a/drivers/gpu/drm/msm/msm_gpu.h
+++ b/drivers/gpu/drm/msm/msm_gpu.h
@@ -267,6 +267,7 @@ struct msm_gpu_perfcntr {
  *             seqno, protected by submitqueue lock
  * @lock:      submitqueue lock
  * @ref:       reference count
+ * @entity: the submit job-queue
  */
 struct msm_gpu_submitqueue {
 	int id;
@@ -278,6 +279,7 @@ struct msm_gpu_submitqueue {
 	struct idr fence_idr;
 	struct mutex lock;
 	struct kref ref;
+	struct drm_sched_entity entity;
 };
 
 struct msm_gpu_state_bo {
diff --git a/drivers/gpu/drm/msm/msm_rd.c b/drivers/gpu/drm/msm/msm_rd.c
index 659e5cc4b40a..b55398a34fa4 100644
--- a/drivers/gpu/drm/msm/msm_rd.c
+++ b/drivers/gpu/drm/msm/msm_rd.c
@@ -325,15 +325,19 @@ static void snapshot_buf(struct msm_rd_state *rd,
 	if (!(submit->bos[idx].flags & MSM_SUBMIT_BO_READ))
 		return;
 
+	msm_gem_lock(&obj->base);
 	buf = msm_gem_get_vaddr_active(&obj->base);
 	if (IS_ERR(buf))
-		return;
+		goto out_unlock;
 
 	buf += offset;
 
 	rd_write_section(rd, RD_BUFFER_CONTENTS, buf, size);
 
 	msm_gem_put_vaddr_locked(&obj->base);
+
+out_unlock:
+	msm_gem_unlock(&obj->base);
 }
 
 /* called under struct_mutex */
diff --git a/drivers/gpu/drm/msm/msm_ringbuffer.c b/drivers/gpu/drm/msm/msm_ringbuffer.c
index 437cca57d005..5643f579ac46 100644
--- a/drivers/gpu/drm/msm/msm_ringbuffer.c
+++ b/drivers/gpu/drm/msm/msm_ringbuffer.c
@@ -7,10 +7,64 @@
 #include "msm_ringbuffer.h"
 #include "msm_gpu.h"
 
+/**
+ * The max # of jobs to write into the hw ringbuffer.
+ */
+static uint num_hw_submissions = 8;
+MODULE_PARM_DESC(num_hw_submissions, "The max number of HW submissions (default 8)");
+module_param(num_hw_submissions, uint, 0600);
+
+static struct dma_fence *msm_job_dependency(struct drm_sched_job *job,
+		struct drm_sched_entity *s_entity)
+{
+	struct msm_gem_submit *submit = to_msm_submit(job);
+
+	if (!xa_empty(&submit->deps))
+		return xa_erase(&submit->deps, submit->last_dep++);
+
+	return NULL;
+}
+
+static struct dma_fence *msm_job_run(struct drm_sched_job *job)
+{
+	struct msm_gem_submit *submit = to_msm_submit(job);
+	struct msm_gpu *gpu = submit->gpu;
+
+	submit->hw_fence = msm_fence_alloc(submit->ring->fctx);
+
+	pm_runtime_get_sync(&gpu->pdev->dev);
+
+	/* TODO move submit path over to using a per-ring lock.. */
+	mutex_lock(&gpu->dev->struct_mutex);
+
+	msm_gpu_submit(gpu, submit);
+
+	mutex_unlock(&gpu->dev->struct_mutex);
+
+	pm_runtime_put(&gpu->pdev->dev);
+
+	return dma_fence_get(submit->hw_fence);
+}
+
+static void msm_job_free(struct drm_sched_job *job)
+{
+	struct msm_gem_submit *submit = to_msm_submit(job);
+
+	drm_sched_job_cleanup(job);
+	msm_gem_submit_put(submit);
+}
+
+const struct drm_sched_backend_ops msm_sched_ops = {
+	.dependency = msm_job_dependency,
+	.run_job = msm_job_run,
+	.free_job = msm_job_free
+};
+
 struct msm_ringbuffer *msm_ringbuffer_new(struct msm_gpu *gpu, int id,
 		void *memptrs, uint64_t memptrs_iova)
 {
 	struct msm_ringbuffer *ring;
+	long sched_timeout;
 	char name[32];
 	int ret;
 
@@ -45,6 +99,16 @@ struct msm_ringbuffer *msm_ringbuffer_new(struct msm_gpu *gpu, int id,
 	ring->memptrs = memptrs;
 	ring->memptrs_iova = memptrs_iova;
 
+	 /* currently managing hangcheck ourselves: */
+	sched_timeout = MAX_SCHEDULE_TIMEOUT;
+
+	ret = drm_sched_init(&ring->sched, &msm_sched_ops,
+			num_hw_submissions, 0, sched_timeout,
+			NULL, to_msm_bo(ring->bo)->name);
+	if (ret) {
+		goto fail;
+	}
+
 	INIT_LIST_HEAD(&ring->submits);
 	spin_lock_init(&ring->submit_lock);
 	spin_lock_init(&ring->preempt_lock);
@@ -65,6 +129,8 @@ void msm_ringbuffer_destroy(struct msm_ringbuffer *ring)
 	if (IS_ERR_OR_NULL(ring))
 		return;
 
+	drm_sched_fini(&ring->sched);
+
 	msm_fence_context_free(ring->fctx);
 
 	msm_gem_kernel_put(ring->bo, ring->gpu->aspace);
diff --git a/drivers/gpu/drm/msm/msm_ringbuffer.h b/drivers/gpu/drm/msm/msm_ringbuffer.h
index fe55d4a1aa16..d8c63df4e9ca 100644
--- a/drivers/gpu/drm/msm/msm_ringbuffer.h
+++ b/drivers/gpu/drm/msm/msm_ringbuffer.h
@@ -7,6 +7,7 @@
 #ifndef __MSM_RINGBUFFER_H__
 #define __MSM_RINGBUFFER_H__
 
+#include "drm/gpu_scheduler.h"
 #include "msm_drv.h"
 
 #define rbmemptr(ring, member)  \
@@ -40,8 +41,19 @@ struct msm_ringbuffer {
 	struct drm_gem_object *bo;
 	uint32_t *start, *end, *cur, *next;
 
+	/*
+	 * The job scheduler for this ring.
+	 */
+	struct drm_gpu_scheduler sched;
+
 	/*
 	 * List of in-flight submits on this ring.  Protected by submit_lock.
+	 *
+	 * Currently just submits that are already written into the ring, not
+	 * submits that are still in drm_gpu_scheduler's queues.  At a later
+	 * step we could probably move to letting drm_gpu_scheduler manage
+	 * hangcheck detection and keep track of submit jobs that are in-
+	 * flight.
 	 */
 	struct list_head submits;
 	spinlock_t submit_lock;
diff --git a/drivers/gpu/drm/msm/msm_submitqueue.c b/drivers/gpu/drm/msm/msm_submitqueue.c
index 66f8d0fb38b0..682ba2a7c0ec 100644
--- a/drivers/gpu/drm/msm/msm_submitqueue.c
+++ b/drivers/gpu/drm/msm/msm_submitqueue.c
@@ -14,6 +14,8 @@ void msm_submitqueue_destroy(struct kref *kref)
 
 	idr_destroy(&queue->fence_idr);
 
+	drm_sched_entity_destroy(&queue->entity);
+
 	msm_file_private_put(queue->ctx);
 
 	kfree(queue);
@@ -64,6 +66,9 @@ int msm_submitqueue_create(struct drm_device *drm, struct msm_file_private *ctx,
 {
 	struct msm_drm_private *priv = drm->dev_private;
 	struct msm_gpu_submitqueue *queue;
+	struct msm_ringbuffer *ring;
+	struct drm_gpu_scheduler *sched;
+	int ret;
 
 	if (!ctx)
 		return -ENODEV;
@@ -83,6 +88,27 @@ int msm_submitqueue_create(struct drm_device *drm, struct msm_file_private *ctx,
 	queue->flags = flags;
 	queue->prio = prio;
 
+	ring = priv->gpu->rb[prio];
+	sched = &ring->sched;
+
+	/*
+	 * TODO we can allow more priorities than we have ringbuffers by
+	 * mapping:
+	 *
+	 *    ring = prio / 3;
+	 *    ent_prio = DRM_SCHED_PRIORITY_MIN + (prio % 3);
+	 *
+	 * Probably avoid using DRM_SCHED_PRIORITY_KERNEL as that is
+	 * treated specially in places.
+	 */
+	ret = drm_sched_entity_init(&queue->entity,
+			DRM_SCHED_PRIORITY_NORMAL,
+			&sched, 1, NULL);
+	if (ret) {
+		kfree(queue);
+		return ret;
+	}
+
 	write_lock(&ctx->queuelock);
 
 	queue->ctx = msm_file_private_get(ctx);
-- 
2.31.1

[PATCH v3 10/13] drm/msm: Drop submit bo_list

[Rob Clark]

From: Rob Clark <robdclark@chromium.org>

This was only used to detect userspace including the same bo multiple
times in a submit.  But ww_mutex can already tell us this.

When we drop struct_mutex around the submit ioctl, we'd otherwise need
to lock the bo before adding it to the bo_list.  But since ww_mutex can
already tell us this, it is simpler just to remove the bo_list.

Signed-off-by: Rob Clark <robdclark@chromium.org>
---
 drivers/gpu/drm/msm/msm_gem.c        |  1 -
 drivers/gpu/drm/msm/msm_gem.h        |  8 --------
 drivers/gpu/drm/msm/msm_gem_submit.c | 28 +++++++++++++---------------
 3 files changed, 13 insertions(+), 24 deletions(-)

diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c
index a527a6b1d6ba..af199ef53d2f 100644
--- a/drivers/gpu/drm/msm/msm_gem.c
+++ b/drivers/gpu/drm/msm/msm_gem.c
@@ -1151,7 +1151,6 @@ static int msm_gem_new_impl(struct drm_device *dev,
 	msm_obj->flags = flags;
 	msm_obj->madv = MSM_MADV_WILLNEED;
 
-	INIT_LIST_HEAD(&msm_obj->submit_entry);
 	INIT_LIST_HEAD(&msm_obj->vmas);
 
 	*obj = &msm_obj->base;
diff --git a/drivers/gpu/drm/msm/msm_gem.h b/drivers/gpu/drm/msm/msm_gem.h
index a48114058ff9..f9e3ffb2309a 100644
--- a/drivers/gpu/drm/msm/msm_gem.h
+++ b/drivers/gpu/drm/msm/msm_gem.h
@@ -88,13 +88,6 @@ struct msm_gem_object {
 	 */
 	struct list_head mm_list;
 
-	/* Transiently in the process of submit ioctl, objects associated
-	 * with the submit are on submit->bo_list.. this only lasts for
-	 * the duration of the ioctl, so one bo can never be on multiple
-	 * submit lists.
-	 */
-	struct list_head submit_entry;
-
 	struct page **pages;
 	struct sg_table *sgt;
 	void *vaddr;
@@ -316,7 +309,6 @@ struct msm_gem_submit {
 	struct msm_gpu *gpu;
 	struct msm_gem_address_space *aspace;
 	struct list_head node;   /* node in ring submit list */
-	struct list_head bo_list;
 	struct ww_acquire_ctx ticket;
 	uint32_t seqno;		/* Sequence number of the submit on the ring */
 
diff --git a/drivers/gpu/drm/msm/msm_gem_submit.c b/drivers/gpu/drm/msm/msm_gem_submit.c
index 2b158433a6e5..e11e4bb63695 100644
--- a/drivers/gpu/drm/msm/msm_gem_submit.c
+++ b/drivers/gpu/drm/msm/msm_gem_submit.c
@@ -63,7 +63,6 @@ static struct msm_gem_submit *submit_create(struct drm_device *dev,
 	submit->fault_dumped = false;
 
 	INIT_LIST_HEAD(&submit->node);
-	INIT_LIST_HEAD(&submit->bo_list);
 
 	return submit;
 }
@@ -143,7 +142,6 @@ static int submit_lookup_objects(struct msm_gem_submit *submit,
 
 	for (i = 0; i < args->nr_bos; i++) {
 		struct drm_gem_object *obj;
-		struct msm_gem_object *msm_obj;
 
 		/* normally use drm_gem_object_lookup(), but for bulk lookup
 		 * all under single table_lock just hit object_idr directly:
@@ -155,20 +153,9 @@ static int submit_lookup_objects(struct msm_gem_submit *submit,
 			goto out_unlock;
 		}
 
-		msm_obj = to_msm_bo(obj);
-
-		if (!list_empty(&msm_obj->submit_entry)) {
-			DRM_ERROR("handle %u at index %u already on submit list\n",
-					submit->bos[i].handle, i);
-			ret = -EINVAL;
-			goto out_unlock;
-		}
-
 		drm_gem_object_get(obj);
 
-		submit->bos[i].obj = msm_obj;
-
-		list_add_tail(&msm_obj->submit_entry, &submit->bo_list);
+		submit->bos[i].obj = to_msm_bo(obj);
 	}
 
 out_unlock:
@@ -299,6 +286,12 @@ static int submit_lock_objects(struct msm_gem_submit *submit)
 	return 0;
 
 fail:
+	if (ret == -EALREADY) {
+		DRM_ERROR("handle %u at index %u already on submit list\n",
+				submit->bos[i].handle, i);
+		ret = -EINVAL;
+	}
+
 	for (; i >= 0; i--)
 		submit_unlock_unpin_bo(submit, i);
 
@@ -315,6 +308,12 @@ static int submit_lock_objects(struct msm_gem_submit *submit)
 			slow_locked = contended;
 			goto retry;
 		}
+
+		/* Not expecting -EALREADY here, if the bo was already
+		 * locked, we should have gotten -EALREADY already from
+		 * the dma_resv_lock_interruptable() call.
+		 */
+		WARN_ON_ONCE(ret == -EALREADY);
 	}
 
 	return ret;
@@ -508,7 +507,6 @@ static void submit_cleanup(struct msm_gem_submit *submit, bool error)
 	for (i = 0; i < submit->nr_bos; i++) {
 		struct msm_gem_object *msm_obj = submit->bos[i].obj;
 		submit_cleanup_bo(submit, i, cleanup_flags);
-		list_del_init(&msm_obj->submit_entry);
 		if (error)
 			drm_gem_object_put(&msm_obj->base);
 	}
-- 
2.31.1

[PATCH v3 11/13] drm/msm: Drop struct_mutex in submit path

[Rob Clark]

From: Rob Clark <robdclark@chromium.org>

It is sufficient to serialize on the submit queue now.

Signed-off-by: Rob Clark <robdclark@chromium.org>
Acked-by: Christian König <christian.koenig@amd.com>
---
 drivers/gpu/drm/msm/msm_gem_submit.c | 12 +++++-------
 1 file changed, 5 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/msm/msm_gem_submit.c b/drivers/gpu/drm/msm/msm_gem_submit.c
index e11e4bb63695..450efe59abb5 100644
--- a/drivers/gpu/drm/msm/msm_gem_submit.c
+++ b/drivers/gpu/drm/msm/msm_gem_submit.c
@@ -709,7 +709,7 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data,
 	struct msm_drm_private *priv = dev->dev_private;
 	struct drm_msm_gem_submit *args = data;
 	struct msm_file_private *ctx = file->driver_priv;
-	struct msm_gem_submit *submit;
+	struct msm_gem_submit *submit = NULL;
 	struct msm_gpu *gpu = priv->gpu;
 	struct msm_gpu_submitqueue *queue;
 	struct msm_ringbuffer *ring;
@@ -753,7 +753,7 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data,
 	trace_msm_gpu_submit(pid_nr(pid), ring->id, submitid,
 		args->nr_bos, args->nr_cmds);
 
-	ret = mutex_lock_interruptible(&dev->struct_mutex);
+	ret = mutex_lock_interruptible(&queue->lock);
 	if (ret)
 		goto out_post_unlock;
 
@@ -874,10 +874,8 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data,
 	 * Allocate an id which can be used by WAIT_FENCE ioctl to map back
 	 * to the underlying fence.
 	 */
-	mutex_lock(&queue->lock);
 	submit->fence_id = idr_alloc_cyclic(&queue->fence_idr,
 			submit->user_fence, 0, INT_MAX, GFP_KERNEL);
-	mutex_unlock(&queue->lock);
 	if (submit->fence_id < 0) {
 		ret = submit->fence_id = 0;
 		submit->fence_id = 0;
@@ -912,12 +910,12 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data,
 	submit_cleanup(submit, !!ret);
 	if (has_ww_ticket)
 		ww_acquire_fini(&submit->ticket);
-	msm_gem_submit_put(submit);
 out_unlock:
 	if (ret && (out_fence_fd >= 0))
 		put_unused_fd(out_fence_fd);
-	mutex_unlock(&dev->struct_mutex);
-
+	mutex_unlock(&queue->lock);
+	if (submit)
+		msm_gem_submit_put(submit);
 out_post_unlock:
 	if (!IS_ERR_OR_NULL(post_deps)) {
 		for (i = 0; i < args->nr_out_syncobjs; ++i) {
-- 
2.31.1

[PATCH v3 12/13] drm/msm: Utilize gpu scheduler priorities

[Rob Clark]

From: Rob Clark <robdclark@chromium.org>

The drm/scheduler provides additional prioritization on top of that
provided by however many number of ringbuffers (each with their own
priority level) is supported on a given generation.  Expose the
additional levels of priority to userspace and map the userspace
priority back to ring (first level of priority) and schedular priority
(additional priority levels within the ring).

Signed-off-by: Rob Clark <robdclark@chromium.org>
Acked-by: Christian König <christian.koenig@amd.com>
---
 drivers/gpu/drm/msm/adreno/adreno_gpu.c |  4 +-
 drivers/gpu/drm/msm/msm_gem_submit.c    |  4 +-
 drivers/gpu/drm/msm/msm_gpu.h           | 58 ++++++++++++++++++++++++-
 drivers/gpu/drm/msm/msm_submitqueue.c   | 35 +++++++--------
 include/uapi/drm/msm_drm.h              | 14 +++++-
 5 files changed, 88 insertions(+), 27 deletions(-)

diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
index bad4809b68ef..748665232d29 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
@@ -261,8 +261,8 @@ int adreno_get_param(struct msm_gpu *gpu, uint32_t param, uint64_t *value)
 			return ret;
 		}
 		return -EINVAL;
-	case MSM_PARAM_NR_RINGS:
-		*value = gpu->nr_rings;
+	case MSM_PARAM_PRIORITIES:
+		*value = gpu->nr_rings * NR_SCHED_PRIORITIES;
 		return 0;
 	case MSM_PARAM_PP_PGTABLE:
 		*value = 0;
diff --git a/drivers/gpu/drm/msm/msm_gem_submit.c b/drivers/gpu/drm/msm/msm_gem_submit.c
index 450efe59abb5..c2ecec5b11c4 100644
--- a/drivers/gpu/drm/msm/msm_gem_submit.c
+++ b/drivers/gpu/drm/msm/msm_gem_submit.c
@@ -59,7 +59,7 @@ static struct msm_gem_submit *submit_create(struct drm_device *dev,
 	submit->gpu = gpu;
 	submit->cmd = (void *)&submit->bos[nr_bos];
 	submit->queue = queue;
-	submit->ring = gpu->rb[queue->prio];
+	submit->ring = gpu->rb[queue->ring_nr];
 	submit->fault_dumped = false;
 
 	INIT_LIST_HEAD(&submit->node);
@@ -749,7 +749,7 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data,
 	/* Get a unique identifier for the submission for logging purposes */
 	submitid = atomic_inc_return(&ident) - 1;
 
-	ring = gpu->rb[queue->prio];
+	ring = gpu->rb[queue->ring_nr];
 	trace_msm_gpu_submit(pid_nr(pid), ring->id, submitid,
 		args->nr_bos, args->nr_cmds);
 
diff --git a/drivers/gpu/drm/msm/msm_gpu.h b/drivers/gpu/drm/msm/msm_gpu.h
index b912cacaecc0..0e4b45bff2e6 100644
--- a/drivers/gpu/drm/msm/msm_gpu.h
+++ b/drivers/gpu/drm/msm/msm_gpu.h
@@ -250,6 +250,59 @@ struct msm_gpu_perfcntr {
 	const char *name;
 };
 
+/*
+ * The number of priority levels provided by drm gpu scheduler.  The
+ * DRM_SCHED_PRIORITY_KERNEL priority level is treated specially in some
+ * cases, so we don't use it (no need for kernel generated jobs).
+ */
+#define NR_SCHED_PRIORITIES (1 + DRM_SCHED_PRIORITY_HIGH - DRM_SCHED_PRIORITY_MIN)
+
+/**
+ * msm_gpu_convert_priority - Map userspace priority to ring # and sched priority
+ *
+ * @gpu:        the gpu instance
+ * @prio:       the userspace priority level
+ * @ring_nr:    [out] the ringbuffer the userspace priority maps to
+ * @sched_prio: [out] the gpu scheduler priority level which the userspace
+ *              priority maps to
+ *
+ * With drm/scheduler providing it's own level of prioritization, our total
+ * number of available priority levels is (nr_rings * NR_SCHED_PRIORITIES).
+ * Each ring is associated with it's own scheduler instance.  However, our
+ * UABI is that lower numerical values are higher priority.  So mapping the
+ * single userspace priority level into ring_nr and sched_prio takes some
+ * care.  The userspace provided priority (when a submitqueue is created)
+ * is mapped to ring nr and scheduler priority as such:
+ *
+ *   ring_nr    = userspace_prio / NR_SCHED_PRIORITIES
+ *   sched_prio = NR_SCHED_PRIORITIES -
+ *                (userspace_prio % NR_SCHED_PRIORITIES) - 1
+ *
+ * This allows generations without preemption (nr_rings==1) to have some
+ * amount of prioritization, and provides more priority levels for gens
+ * that do have preemption.
+ */
+static inline int msm_gpu_convert_priority(struct msm_gpu *gpu, int prio,
+		unsigned *ring_nr, enum drm_sched_priority *sched_prio)
+{
+	unsigned rn, sp;
+
+	rn = div_u64_rem(prio, NR_SCHED_PRIORITIES, &sp);
+
+	/* invert sched priority to map to higher-numeric-is-higher-
+	 * priority convention
+	 */
+	sp = NR_SCHED_PRIORITIES - sp - 1;
+
+	if (rn >= gpu->nr_rings)
+		return -EINVAL;
+
+	*ring_nr = rn;
+	*sched_prio = sp;
+
+	return 0;
+}
+
 /**
  * A submitqueue is associated with a gl context or vk queue (or equiv)
  * in userspace.
@@ -257,7 +310,8 @@ struct msm_gpu_perfcntr {
  * @id:        userspace id for the submitqueue, unique within the drm_file
  * @flags:     userspace flags for the submitqueue, specified at creation
  *             (currently unusued)
- * @prio:      the submitqueue priority
+ * @ring_nr:   the ringbuffer used by this submitqueue, which is determined
+ *             by the submitqueue's priority
  * @faults:    the number of GPU hangs associated with this submitqueue
  * @ctx:       the per-drm_file context associated with the submitqueue (ie.
  *             which set of pgtables do submits jobs associated with the
@@ -272,7 +326,7 @@ struct msm_gpu_perfcntr {
 struct msm_gpu_submitqueue {
 	int id;
 	u32 flags;
-	u32 prio;
+	u32 ring_nr;
 	int faults;
 	struct msm_file_private *ctx;
 	struct list_head node;
diff --git a/drivers/gpu/drm/msm/msm_submitqueue.c b/drivers/gpu/drm/msm/msm_submitqueue.c
index 682ba2a7c0ec..32a55d81b58b 100644
--- a/drivers/gpu/drm/msm/msm_submitqueue.c
+++ b/drivers/gpu/drm/msm/msm_submitqueue.c
@@ -68,6 +68,8 @@ int msm_submitqueue_create(struct drm_device *drm, struct msm_file_private *ctx,
 	struct msm_gpu_submitqueue *queue;
 	struct msm_ringbuffer *ring;
 	struct drm_gpu_scheduler *sched;
+	enum drm_sched_priority sched_prio;
+	unsigned ring_nr;
 	int ret;
 
 	if (!ctx)
@@ -76,8 +78,9 @@ int msm_submitqueue_create(struct drm_device *drm, struct msm_file_private *ctx,
 	if (!priv->gpu)
 		return -ENODEV;
 
-	if (prio >= priv->gpu->nr_rings)
-		return -EINVAL;
+	ret = msm_gpu_convert_priority(priv->gpu, prio, &ring_nr, &sched_prio);
+	if (ret)
+		return ret;
 
 	queue = kzalloc(sizeof(*queue), GFP_KERNEL);
 
@@ -86,24 +89,13 @@ int msm_submitqueue_create(struct drm_device *drm, struct msm_file_private *ctx,
 
 	kref_init(&queue->ref);
 	queue->flags = flags;
-	queue->prio = prio;
+	queue->ring_nr = ring_nr;
 
-	ring = priv->gpu->rb[prio];
+	ring = priv->gpu->rb[ring_nr];
 	sched = &ring->sched;
 
-	/*
-	 * TODO we can allow more priorities than we have ringbuffers by
-	 * mapping:
-	 *
-	 *    ring = prio / 3;
-	 *    ent_prio = DRM_SCHED_PRIORITY_MIN + (prio % 3);
-	 *
-	 * Probably avoid using DRM_SCHED_PRIORITY_KERNEL as that is
-	 * treated specially in places.
-	 */
 	ret = drm_sched_entity_init(&queue->entity,
-			DRM_SCHED_PRIORITY_NORMAL,
-			&sched, 1, NULL);
+			sched_prio, &sched, 1, NULL);
 	if (ret) {
 		kfree(queue);
 		return ret;
@@ -134,16 +126,19 @@ int msm_submitqueue_create(struct drm_device *drm, struct msm_file_private *ctx,
 int msm_submitqueue_init(struct drm_device *drm, struct msm_file_private *ctx)
 {
 	struct msm_drm_private *priv = drm->dev_private;
-	int default_prio;
+	int default_prio, max_priority;
 
 	if (!priv->gpu)
 		return -ENODEV;
 
+	max_priority = (priv->gpu->nr_rings * NR_SCHED_PRIORITIES) - 1;
+
 	/*
-	 * Select priority 2 as the "default priority" unless nr_rings is less
-	 * than 2 and then pick the lowest priority
+	 * Pick a medium priority level as default.  Lower numeric value is
+	 * higher priority, so round-up to pick a priority that is not higher
+	 * than the middle priority level.
 	 */
-	default_prio = clamp_t(uint32_t, 2, 0, priv->gpu->nr_rings - 1);
+	default_prio = DIV_ROUND_UP(max_priority, 2);
 
 	INIT_LIST_HEAD(&ctx->submitqueues);
 
diff --git a/include/uapi/drm/msm_drm.h b/include/uapi/drm/msm_drm.h
index f075851021c3..6b8fffc28a50 100644
--- a/include/uapi/drm/msm_drm.h
+++ b/include/uapi/drm/msm_drm.h
@@ -73,11 +73,19 @@ struct drm_msm_timespec {
 #define MSM_PARAM_MAX_FREQ   0x04
 #define MSM_PARAM_TIMESTAMP  0x05
 #define MSM_PARAM_GMEM_BASE  0x06
-#define MSM_PARAM_NR_RINGS   0x07
+#define MSM_PARAM_PRIORITIES 0x07  /* The # of priority levels */
 #define MSM_PARAM_PP_PGTABLE 0x08  /* => 1 for per-process pagetables, else 0 */
 #define MSM_PARAM_FAULTS     0x09
 #define MSM_PARAM_SUSPENDS   0x0a
 
+/* For backwards compat.  The original support for preemption was based on
+ * a single ring per priority level so # of priority levels equals the #
+ * of rings.  With drm/scheduler providing additional levels of priority,
+ * the number of priorities is greater than the # of rings.  The param is
+ * renamed to better reflect this.
+ */
+#define MSM_PARAM_NR_RINGS   MSM_PARAM_PRIORITIES
+
 struct drm_msm_param {
 	__u32 pipe;           /* in, MSM_PIPE_x */
 	__u32 param;          /* in, MSM_PARAM_x */
@@ -304,6 +312,10 @@ struct drm_msm_gem_madvise {
 
 #define MSM_SUBMITQUEUE_FLAGS (0)
 
+/*
+ * The submitqueue priority should be between 0 and MSM_PARAM_PRIORITIES-1,
+ * a lower numeric value is higher priority.
+ */
 struct drm_msm_submitqueue {
 	__u32 flags;   /* in, MSM_SUBMITQUEUE_x */
 	__u32 prio;    /* in, Priority level */
-- 
2.31.1

[PATCH v3 13/13] drm/msm/gem: Mark active before pinning

[Rob Clark]

From: Rob Clark <robdclark@chromium.org>

Mark all the bos in the submit as active, before pinning, to prevent
evicting a buffer in the same submit to make room for a buffer earlier
in the table.

Signed-off-by: Rob Clark <robdclark@chromium.org>
---
 drivers/gpu/drm/msm/msm_gem.c        |  2 --
 drivers/gpu/drm/msm/msm_gem_submit.c | 28 ++++++++++++++++++++--------
 2 files changed, 20 insertions(+), 10 deletions(-)

diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c
index af199ef53d2f..15b1804fa64e 100644
--- a/drivers/gpu/drm/msm/msm_gem.c
+++ b/drivers/gpu/drm/msm/msm_gem.c
@@ -131,7 +131,6 @@ static struct page **get_pages(struct drm_gem_object *obj)
 		if (msm_obj->flags & (MSM_BO_WC|MSM_BO_UNCACHED))
 			sync_for_device(msm_obj);
 
-		GEM_WARN_ON(msm_obj->active_count);
 		update_inactive(msm_obj);
 	}
 
@@ -815,7 +814,6 @@ void msm_gem_active_get(struct drm_gem_object *obj, struct msm_gpu *gpu)
 	GEM_WARN_ON(!msm_gem_is_locked(obj));
 	GEM_WARN_ON(msm_obj->madv != MSM_MADV_WILLNEED);
 	GEM_WARN_ON(msm_obj->dontneed);
-	GEM_WARN_ON(!msm_obj->sgt);
 
 	if (msm_obj->active_count++ == 0) {
 		mutex_lock(&priv->mm_lock);
diff --git a/drivers/gpu/drm/msm/msm_gem_submit.c b/drivers/gpu/drm/msm/msm_gem_submit.c
index c2ecec5b11c4..fc25a85eb1ca 100644
--- a/drivers/gpu/drm/msm/msm_gem_submit.c
+++ b/drivers/gpu/drm/msm/msm_gem_submit.c
@@ -24,7 +24,8 @@
 /* make sure these don't conflict w/ MSM_SUBMIT_BO_x */
 #define BO_VALID    0x8000   /* is current addr in cmdstream correct/valid? */
 #define BO_LOCKED   0x4000   /* obj lock is held */
-#define BO_PINNED   0x2000   /* obj is pinned and on active list */
+#define BO_ACTIVE   0x2000   /* active refcnt is held */
+#define BO_PINNED   0x1000   /* obj is pinned and on active list */
 
 static struct msm_gem_submit *submit_create(struct drm_device *dev,
 		struct msm_gpu *gpu,
@@ -239,10 +240,11 @@ static void submit_cleanup_bo(struct msm_gem_submit *submit, int i,
 	struct drm_gem_object *obj = &submit->bos[i].obj->base;
 	unsigned flags = submit->bos[i].flags & cleanup_flags;
 
-	if (flags & BO_PINNED) {
+	if (flags & BO_PINNED)
 		msm_gem_unpin_iova_locked(obj, submit->aspace);
+
+	if (flags & BO_ACTIVE)
 		msm_gem_active_put(obj);
-	}
 
 	if (flags & BO_LOCKED)
 		dma_resv_unlock(obj->resv);
@@ -252,7 +254,7 @@ static void submit_cleanup_bo(struct msm_gem_submit *submit, int i,
 
 static void submit_unlock_unpin_bo(struct msm_gem_submit *submit, int i)
 {
-	submit_cleanup_bo(submit, i, BO_PINNED | BO_LOCKED);
+	submit_cleanup_bo(submit, i, BO_PINNED | BO_ACTIVE | BO_LOCKED);
 
 	if (!(submit->bos[i].flags & BO_VALID))
 		submit->bos[i].iova = 0;
@@ -356,6 +358,18 @@ static int submit_pin_objects(struct msm_gem_submit *submit)
 
 	submit->valid = true;
 
+	/*
+	 * Increment active_count first, so if under memory pressure, we
+	 * don't inadvertently evict a bo needed by the submit in order
+	 * to pin an earlier bo in the same submit.
+	 */
+	for (i = 0; i < submit->nr_bos; i++) {
+		struct drm_gem_object *obj = &submit->bos[i].obj->base;
+
+		msm_gem_active_get(obj, submit->gpu);
+		submit->bos[i].flags |= BO_ACTIVE;
+	}
+
 	for (i = 0; i < submit->nr_bos; i++) {
 		struct drm_gem_object *obj = &submit->bos[i].obj->base;
 		uint64_t iova;
@@ -367,8 +381,6 @@ static int submit_pin_objects(struct msm_gem_submit *submit)
 		if (ret)
 			break;
 
-		msm_gem_active_get(obj, submit->gpu);
-
 		submit->bos[i].flags |= BO_PINNED;
 
 		if (iova == submit->bos[i].iova) {
@@ -502,7 +514,7 @@ static void submit_cleanup(struct msm_gem_submit *submit, bool error)
 	unsigned i;
 
 	if (error)
-		cleanup_flags |= BO_PINNED;
+		cleanup_flags |= BO_PINNED | BO_ACTIVE;
 
 	for (i = 0; i < submit->nr_bos; i++) {
 		struct msm_gem_object *msm_obj = submit->bos[i].obj;
@@ -520,7 +532,7 @@ void msm_submit_retire(struct msm_gem_submit *submit)
 		struct drm_gem_object *obj = &submit->bos[i].obj->base;
 
 		msm_gem_lock(obj);
-		submit_cleanup_bo(submit, i, BO_PINNED);
+		submit_cleanup_bo(submit, i, BO_PINNED | BO_ACTIVE);
 		msm_gem_unlock(obj);
 		drm_gem_object_put(obj);
 	}
-- 
2.31.1