Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
From:   Rob Clark <robdclark@gmail.com>
To:     dri-devel@lists.freedesktop.org
Cc:     freedreno@lists.freedesktop.org, linux-arm-msm@vger.kernel.org,
        Rob Clark <robdclark@chromium.org>,
        Rob Clark <robdclark@gmail.com>,
        Abhinav Kumar <quic_abhinavk@quicinc.com>,
        Dmitry Baryshkov <dmitry.baryshkov@linaro.org>,
        Sean Paul <sean@poorly.run>, David Airlie <airlied@linux.ie>,
        Daniel Vetter <daniel@ffwll.ch>,
        linux-kernel@vger.kernel.org (open list)
Subject: [PATCH 05/15] drm/msm: Split out idr_lock
Date:   Sat, 25 Jun 2022 15:54:40 -0700
Message-Id: <20220625225454.81039-6-robdclark@gmail.com>
In-Reply-To: <20220625225454.81039-1-robdclark@gmail.com>
References: <20220625225454.81039-1-robdclark@gmail.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

From: Rob Clark <robdclark@chromium.org>

Otherwise if we hit reclaim pinning objects in the submit path, we'll be
blocking retire_worker trying to free a submit.

Signed-off-by: Rob Clark <robdclark@chromium.org>
---
 drivers/gpu/drm/msm/msm_drv.c         |  4 ++--
 drivers/gpu/drm/msm/msm_gem_submit.c  | 10 ++++++++--
 drivers/gpu/drm/msm/msm_gpu.h         |  4 +++-
 drivers/gpu/drm/msm/msm_submitqueue.c |  1 +
 4 files changed, 14 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c
index acc940d32ab4..ace91ead2caf 100644
--- a/drivers/gpu/drm/msm/msm_drv.c
+++ b/drivers/gpu/drm/msm/msm_drv.c
@@ -838,13 +838,13 @@ static int wait_fence(struct msm_gpu_submitqueue *queue, uint32_t fence_id,
 	 * retired, so if the fence is not found it means there is nothing
 	 * to wait for
 	 */
-	ret = mutex_lock_interruptible(&queue->lock);
+	ret = mutex_lock_interruptible(&queue->idr_lock);
 	if (ret)
 		return ret;
 	fence = idr_find(&queue->fence_idr, fence_id);
 	if (fence)
 		fence = dma_fence_get_rcu(fence);
-	mutex_unlock(&queue->lock);
+	mutex_unlock(&queue->idr_lock);
 
 	if (!fence)
 		return 0;
diff --git a/drivers/gpu/drm/msm/msm_gem_submit.c b/drivers/gpu/drm/msm/msm_gem_submit.c
index c7819781879c..16c662808522 100644
--- a/drivers/gpu/drm/msm/msm_gem_submit.c
+++ b/drivers/gpu/drm/msm/msm_gem_submit.c
@@ -72,9 +72,9 @@ void __msm_gem_submit_destroy(struct kref *kref)
 	unsigned i;
 
 	if (submit->fence_id) {
-		mutex_lock(&submit->queue->lock);
+		mutex_lock(&submit->queue->idr_lock);
 		idr_remove(&submit->queue->fence_idr, submit->fence_id);
-		mutex_unlock(&submit->queue->lock);
+		mutex_unlock(&submit->queue->idr_lock);
 	}
 
 	dma_fence_put(submit->user_fence);
@@ -881,6 +881,8 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data,
 
 	submit->nr_cmds = i;
 
+	mutex_lock(&queue->idr_lock);
+
 	/*
 	 * If using userspace provided seqno fence, validate that the id
 	 * is available before arming sched job.  Since access to fence_idr
@@ -889,6 +891,7 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data,
 	 */
 	if ((args->flags & MSM_SUBMIT_FENCE_SN_IN) &&
 			idr_find(&queue->fence_idr, args->fence)) {
+		mutex_unlock(&queue->idr_lock);
 		ret = -EINVAL;
 		goto out;
 	}
@@ -921,6 +924,9 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data,
 						    submit->user_fence, 1,
 						    INT_MAX, GFP_KERNEL);
 	}
+
+	mutex_unlock(&queue->idr_lock);
+
 	if (submit->fence_id < 0) {
 		ret = submit->fence_id;
 		submit->fence_id = 0;
diff --git a/drivers/gpu/drm/msm/msm_gpu.h b/drivers/gpu/drm/msm/msm_gpu.h
index 4911943ba53b..4ca56d96344a 100644
--- a/drivers/gpu/drm/msm/msm_gpu.h
+++ b/drivers/gpu/drm/msm/msm_gpu.h
@@ -457,7 +457,8 @@ static inline int msm_gpu_convert_priority(struct msm_gpu *gpu, int prio,
  * @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
+ * @idr_lock:  for serializing access to fence_idr
+ * @lock:      submitqueue lock for serializing submits on a queue
  * @ref:       reference count
  * @entity:    the submit job-queue
  */
@@ -470,6 +471,7 @@ struct msm_gpu_submitqueue {
 	struct msm_file_private *ctx;
 	struct list_head node;
 	struct idr fence_idr;
+	struct mutex idr_lock;
 	struct mutex lock;
 	struct kref ref;
 	struct drm_sched_entity *entity;
diff --git a/drivers/gpu/drm/msm/msm_submitqueue.c b/drivers/gpu/drm/msm/msm_submitqueue.c
index f486a3cd4e55..c6929e205b51 100644
--- a/drivers/gpu/drm/msm/msm_submitqueue.c
+++ b/drivers/gpu/drm/msm/msm_submitqueue.c
@@ -200,6 +200,7 @@ int msm_submitqueue_create(struct drm_device *drm, struct msm_file_private *ctx,
 		*id = queue->id;
 
 	idr_init(&queue->fence_idr);
+	mutex_init(&queue->idr_lock);
 	mutex_init(&queue->lock);
 
 	list_add_tail(&queue->node, &ctx->submitqueues);
-- 
2.36.1