[PATCH] drm/virtio: kick vq outside of the vq lock

[PATCH] drm/virtio: kick vq outside of the vq lock

[Chia-I Wu]

Replace virtqueue_kick by virtqueue_kick_prepare, which requires
serialization, and virtqueue_notify, which does not.  Repurpose the
return values to indicate whether the vq should be notified.

This fixes a lock contention with qemu host.  When the guest calls
vibad rtqueue_notify, the qemu vcpu thread exits the guest and waits
for the qemu iothread to perform the MMIO.  If the qemu iothread is
still processing the prior buffer, and if the prior buffer is cheap
to GPU, the iothread will go ahead and generate an IRQ for the
guest.  A worker thread in the guest will call
virtio_gpu_dequeue_ctrl_func.  If virtqueue_notify was called with
the vq lock held, the worker thread would busy wait inside
virtio_gpu_dequeue_ctrl_func.

Signed-off-by: Chia-I Wu <olvaffe@gmail.com>
---
 drivers/gpu/drm/virtio/virtgpu_vq.c | 19 +++++++++++++------
 1 file changed, 13 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/virtio/virtgpu_vq.c b/drivers/gpu/drm/virtio/virtgpu_vq.c
index 6c1a90717535..e96f88fe5c83 100644
--- a/drivers/gpu/drm/virtio/virtgpu_vq.c
+++ b/drivers/gpu/drm/virtio/virtgpu_vq.c
@@ -291,11 +291,9 @@ static int virtio_gpu_queue_ctrl_buffer_locked(struct virtio_gpu_device *vgdev,
 		trace_virtio_gpu_cmd_queue(vq,
 			(struct virtio_gpu_ctrl_hdr *)vbuf->buf);
 
-		virtqueue_kick(vq);
+		ret = virtqueue_kick_prepare(vq);
 	}
 
-	if (!ret)
-		ret = vq->num_free;
 	return ret;
 }
 
@@ -307,6 +305,10 @@ static int virtio_gpu_queue_ctrl_buffer(struct virtio_gpu_device *vgdev,
 	spin_lock(&vgdev->ctrlq.qlock);
 	rc = virtio_gpu_queue_ctrl_buffer_locked(vgdev, vbuf);
 	spin_unlock(&vgdev->ctrlq.qlock);
+
+	if (rc > 0)
+		virtqueue_notify(vgdev->ctrlq.vq);
+
 	return rc;
 }
 
@@ -339,6 +341,10 @@ static int virtio_gpu_queue_fenced_ctrl_buffer(struct virtio_gpu_device *vgdev,
 		virtio_gpu_fence_emit(vgdev, hdr, fence);
 	rc = virtio_gpu_queue_ctrl_buffer_locked(vgdev, vbuf);
 	spin_unlock(&vgdev->ctrlq.qlock);
+
+	if (rc > 0)
+		virtqueue_notify(vgdev->ctrlq.vq);
+
 	return rc;
 }
 
@@ -369,13 +375,14 @@ static int virtio_gpu_queue_cursor(struct virtio_gpu_device *vgdev,
 		trace_virtio_gpu_cmd_queue(vq,
 			(struct virtio_gpu_ctrl_hdr *)vbuf->buf);
 
-		virtqueue_kick(vq);
+		ret = virtqueue_kick_prepare(vq);
 	}
 
 	spin_unlock(&vgdev->cursorq.qlock);
 
-	if (!ret)
-		ret = vq->num_free;
+	if (ret > 0)
+		virtqueue_notify(vq);
+
 	return ret;
 }
 
-- 
2.22.0.410.gd8fdbe21b5-goog

[PATCH] drm/virtio: kick vq outside of the vq lock

[Chia-I Wu]

Replace virtqueue_kick by virtqueue_kick_prepare, which requires
serialization, and virtqueue_notify, which does not.  Repurpose the
return values to indicate whether the vq should be notified.

This fixes a lock contention with qemu host.  When the guest calls
vibad rtqueue_notify, the qemu vcpu thread exits the guest and waits
for the qemu iothread to perform the MMIO.  If the qemu iothread is
still processing the prior buffer, and if the prior buffer is cheap
to GPU, the iothread will go ahead and generate an IRQ for the
guest.  A worker thread in the guest will call
virtio_gpu_dequeue_ctrl_func.  If virtqueue_notify was called with
the vq lock held, the worker thread would busy wait inside
virtio_gpu_dequeue_ctrl_func.

Signed-off-by: Chia-I Wu <olvaffe@gmail.com>
---
 drivers/gpu/drm/virtio/virtgpu_vq.c | 19 +++++++++++++------
 1 file changed, 13 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/virtio/virtgpu_vq.c b/drivers/gpu/drm/virtio/virtgpu_vq.c
index 6c1a90717535..e96f88fe5c83 100644
--- a/drivers/gpu/drm/virtio/virtgpu_vq.c
+++ b/drivers/gpu/drm/virtio/virtgpu_vq.c
@@ -291,11 +291,9 @@ static int virtio_gpu_queue_ctrl_buffer_locked(struct virtio_gpu_device *vgdev,
 		trace_virtio_gpu_cmd_queue(vq,
 			(struct virtio_gpu_ctrl_hdr *)vbuf->buf);
 
-		virtqueue_kick(vq);
+		ret = virtqueue_kick_prepare(vq);
 	}
 
-	if (!ret)
-		ret = vq->num_free;
 	return ret;
 }
 
@@ -307,6 +305,10 @@ static int virtio_gpu_queue_ctrl_buffer(struct virtio_gpu_device *vgdev,
 	spin_lock(&vgdev->ctrlq.qlock);
 	rc = virtio_gpu_queue_ctrl_buffer_locked(vgdev, vbuf);
 	spin_unlock(&vgdev->ctrlq.qlock);
+
+	if (rc > 0)
+		virtqueue_notify(vgdev->ctrlq.vq);
+
 	return rc;
 }
 
@@ -339,6 +341,10 @@ static int virtio_gpu_queue_fenced_ctrl_buffer(struct virtio_gpu_device *vgdev,
 		virtio_gpu_fence_emit(vgdev, hdr, fence);
 	rc = virtio_gpu_queue_ctrl_buffer_locked(vgdev, vbuf);
 	spin_unlock(&vgdev->ctrlq.qlock);
+
+	if (rc > 0)
+		virtqueue_notify(vgdev->ctrlq.vq);
+
 	return rc;
 }
 
@@ -369,13 +375,14 @@ static int virtio_gpu_queue_cursor(struct virtio_gpu_device *vgdev,
 		trace_virtio_gpu_cmd_queue(vq,
 			(struct virtio_gpu_ctrl_hdr *)vbuf->buf);
 
-		virtqueue_kick(vq);
+		ret = virtqueue_kick_prepare(vq);
 	}
 
 	spin_unlock(&vgdev->cursorq.qlock);
 
-	if (!ret)
-		ret = vq->num_free;
+	if (ret > 0)
+		virtqueue_notify(vq);
+
 	return ret;
 }
 
-- 
2.22.0.410.gd8fdbe21b5-goog

_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/dri-devel

[PATCH] drm/virtio: kick vq outside of the vq lock

[Chia-I Wu]

Replace virtqueue_kick by virtqueue_kick_prepare, which requires
serialization, and virtqueue_notify, which does not.  Repurpose the
return values to indicate whether the vq should be notified.

This fixes a bad spinlock contention when the host is qemu.  When
the guest calls virtqueue_notify, the qemu vcpu thread exits the
guest and waits for the qemu iothread to perform the MMIO.  If the
qemu iothread is still processing the prior buffer, and if the prior
buffer is cheap to GPU, the iothread will go ahead and generate an
IRQ.  A worker thread in the guest might start running
virtio_gpu_dequeue_ctrl_func.  If virtqueue_notify was called with
the vq lock held, the worker thread would have to busy wait inside
virtio_gpu_dequeue_ctrl_func.

v2: fix scrambled commit message

Signed-off-by: Chia-I Wu <olvaffe@gmail.com>
---
 drivers/gpu/drm/virtio/virtgpu_vq.c | 19 +++++++++++++------
 1 file changed, 13 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/virtio/virtgpu_vq.c b/drivers/gpu/drm/virtio/virtgpu_vq.c
index 6c1a90717535..e96f88fe5c83 100644
--- a/drivers/gpu/drm/virtio/virtgpu_vq.c
+++ b/drivers/gpu/drm/virtio/virtgpu_vq.c
@@ -291,11 +291,9 @@ static int virtio_gpu_queue_ctrl_buffer_locked(struct virtio_gpu_device *vgdev,
 		trace_virtio_gpu_cmd_queue(vq,
 			(struct virtio_gpu_ctrl_hdr *)vbuf->buf);
 
-		virtqueue_kick(vq);
+		ret = virtqueue_kick_prepare(vq);
 	}
 
-	if (!ret)
-		ret = vq->num_free;
 	return ret;
 }
 
@@ -307,6 +305,10 @@ static int virtio_gpu_queue_ctrl_buffer(struct virtio_gpu_device *vgdev,
 	spin_lock(&vgdev->ctrlq.qlock);
 	rc = virtio_gpu_queue_ctrl_buffer_locked(vgdev, vbuf);
 	spin_unlock(&vgdev->ctrlq.qlock);
+
+	if (rc > 0)
+		virtqueue_notify(vgdev->ctrlq.vq);
+
 	return rc;
 }
 
@@ -339,6 +341,10 @@ static int virtio_gpu_queue_fenced_ctrl_buffer(struct virtio_gpu_device *vgdev,
 		virtio_gpu_fence_emit(vgdev, hdr, fence);
 	rc = virtio_gpu_queue_ctrl_buffer_locked(vgdev, vbuf);
 	spin_unlock(&vgdev->ctrlq.qlock);
+
+	if (rc > 0)
+		virtqueue_notify(vgdev->ctrlq.vq);
+
 	return rc;
 }
 
@@ -369,13 +375,14 @@ static int virtio_gpu_queue_cursor(struct virtio_gpu_device *vgdev,
 		trace_virtio_gpu_cmd_queue(vq,
 			(struct virtio_gpu_ctrl_hdr *)vbuf->buf);
 
-		virtqueue_kick(vq);
+		ret = virtqueue_kick_prepare(vq);
 	}
 
 	spin_unlock(&vgdev->cursorq.qlock);
 
-	if (!ret)
-		ret = vq->num_free;
+	if (ret > 0)
+		virtqueue_notify(vq);
+
 	return ret;
 }
 
-- 
2.22.0.410.gd8fdbe21b5-goog

[PATCH] drm/virtio: kick vq outside of the vq lock

[Chia-I Wu]

Replace virtqueue_kick by virtqueue_kick_prepare, which requires
serialization, and virtqueue_notify, which does not.  Repurpose the
return values to indicate whether the vq should be notified.

This fixes a bad spinlock contention when the host is qemu.  When
the guest calls virtqueue_notify, the qemu vcpu thread exits the
guest and waits for the qemu iothread to perform the MMIO.  If the
qemu iothread is still processing the prior buffer, and if the prior
buffer is cheap to GPU, the iothread will go ahead and generate an
IRQ.  A worker thread in the guest might start running
virtio_gpu_dequeue_ctrl_func.  If virtqueue_notify was called with
the vq lock held, the worker thread would have to busy wait inside
virtio_gpu_dequeue_ctrl_func.

v2: fix scrambled commit message

Signed-off-by: Chia-I Wu <olvaffe@gmail.com>
---
 drivers/gpu/drm/virtio/virtgpu_vq.c | 19 +++++++++++++------
 1 file changed, 13 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/virtio/virtgpu_vq.c b/drivers/gpu/drm/virtio/virtgpu_vq.c
index 6c1a90717535..e96f88fe5c83 100644
--- a/drivers/gpu/drm/virtio/virtgpu_vq.c
+++ b/drivers/gpu/drm/virtio/virtgpu_vq.c
@@ -291,11 +291,9 @@ static int virtio_gpu_queue_ctrl_buffer_locked(struct virtio_gpu_device *vgdev,
 		trace_virtio_gpu_cmd_queue(vq,
 			(struct virtio_gpu_ctrl_hdr *)vbuf->buf);
 
-		virtqueue_kick(vq);
+		ret = virtqueue_kick_prepare(vq);
 	}
 
-	if (!ret)
-		ret = vq->num_free;
 	return ret;
 }
 
@@ -307,6 +305,10 @@ static int virtio_gpu_queue_ctrl_buffer(struct virtio_gpu_device *vgdev,
 	spin_lock(&vgdev->ctrlq.qlock);
 	rc = virtio_gpu_queue_ctrl_buffer_locked(vgdev, vbuf);
 	spin_unlock(&vgdev->ctrlq.qlock);
+
+	if (rc > 0)
+		virtqueue_notify(vgdev->ctrlq.vq);
+
 	return rc;
 }
 
@@ -339,6 +341,10 @@ static int virtio_gpu_queue_fenced_ctrl_buffer(struct virtio_gpu_device *vgdev,
 		virtio_gpu_fence_emit(vgdev, hdr, fence);
 	rc = virtio_gpu_queue_ctrl_buffer_locked(vgdev, vbuf);
 	spin_unlock(&vgdev->ctrlq.qlock);
+
+	if (rc > 0)
+		virtqueue_notify(vgdev->ctrlq.vq);
+
 	return rc;
 }
 
@@ -369,13 +375,14 @@ static int virtio_gpu_queue_cursor(struct virtio_gpu_device *vgdev,
 		trace_virtio_gpu_cmd_queue(vq,
 			(struct virtio_gpu_ctrl_hdr *)vbuf->buf);
 
-		virtqueue_kick(vq);
+		ret = virtqueue_kick_prepare(vq);
 	}
 
 	spin_unlock(&vgdev->cursorq.qlock);
 
-	if (!ret)
-		ret = vq->num_free;
+	if (ret > 0)
+		virtqueue_notify(vq);
+
 	return ret;
 }
 
-- 
2.22.0.410.gd8fdbe21b5-goog

Re: [PATCH] drm/virtio: kick vq outside of the vq lock

[Gerd Hoffmann]

> @@ -291,11 +291,9 @@ static int virtio_gpu_queue_ctrl_buffer_locked(struct virtio_gpu_device *vgdev,
>  		trace_virtio_gpu_cmd_queue(vq,
>  			(struct virtio_gpu_ctrl_hdr *)vbuf->buf);
>  
> -		virtqueue_kick(vq);
> +		ret = virtqueue_kick_prepare(vq);
>  	}
>  
> -	if (!ret)
> -		ret = vq->num_free;

Hmm.  Change looks unrelated.

On a closer look it seems this is basically dead code.
virtio_gpu_queue_ctrl_buffer_locked is called by
virtio_gpu_queue_ctrl_buffer and virtio_gpu_queue_fenced_ctrl_buffer.
The call sites for these two functions all ignore the return value.

So it is a valid change, but it should go to a separate patch.  And
while being at it virtio_gpu_queue_ctrl_buffer and
virtio_gpu_queue_fenced_ctrl_buffer can be changed to return void.

Otherwise the patch looks fine.  Nice analysis btw.

cheers,
  Gerd

Re: [PATCH] drm/virtio: kick vq outside of the vq lock

[Gerd Hoffmann]

> @@ -291,11 +291,9 @@ static int virtio_gpu_queue_ctrl_buffer_locked(struct virtio_gpu_device *vgdev,
>  		trace_virtio_gpu_cmd_queue(vq,
>  			(struct virtio_gpu_ctrl_hdr *)vbuf->buf);
>  
> -		virtqueue_kick(vq);
> +		ret = virtqueue_kick_prepare(vq);
>  	}
>  
> -	if (!ret)
> -		ret = vq->num_free;

Hmm.  Change looks unrelated.

On a closer look it seems this is basically dead code.
virtio_gpu_queue_ctrl_buffer_locked is called by
virtio_gpu_queue_ctrl_buffer and virtio_gpu_queue_fenced_ctrl_buffer.
The call sites for these two functions all ignore the return value.

So it is a valid change, but it should go to a separate patch.  And
while being at it virtio_gpu_queue_ctrl_buffer and
virtio_gpu_queue_fenced_ctrl_buffer can be changed to return void.

Otherwise the patch looks fine.  Nice analysis btw.

cheers,
  Gerd

[PATCH] drm/virtio: kick vq outside of the vq lock

[Chia-I Wu]

Replace virtqueue_kick by virtqueue_kick_prepare, which requires
serialization, and virtqueue_notify, which does not.  Repurpose the
return values to indicate whether the vq should be notified.

This fixes a lock contention with qemu host.  When the guest calls
vibad rtqueue_notify, the qemu vcpu thread exits the guest and waits
for the qemu iothread to perform the MMIO.  If the qemu iothread is
still processing the prior buffer, and if the prior buffer is cheap
to GPU, the iothread will go ahead and generate an IRQ for the
guest.  A worker thread in the guest will call
virtio_gpu_dequeue_ctrl_func.  If virtqueue_notify was called with
the vq lock held, the worker thread would busy wait inside
virtio_gpu_dequeue_ctrl_func.

Signed-off-by: Chia-I Wu <olvaffe@gmail.com>
---
 drivers/gpu/drm/virtio/virtgpu_vq.c | 19 +++++++++++++------
 1 file changed, 13 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/virtio/virtgpu_vq.c b/drivers/gpu/drm/virtio/virtgpu_vq.c
index 6c1a90717535..e96f88fe5c83 100644
--- a/drivers/gpu/drm/virtio/virtgpu_vq.c
+++ b/drivers/gpu/drm/virtio/virtgpu_vq.c
@@ -291,11 +291,9 @@ static int virtio_gpu_queue_ctrl_buffer_locked(struct virtio_gpu_device *vgdev,
 		trace_virtio_gpu_cmd_queue(vq,
 			(struct virtio_gpu_ctrl_hdr *)vbuf->buf);
 
-		virtqueue_kick(vq);
+		ret = virtqueue_kick_prepare(vq);
 	}
 
-	if (!ret)
-		ret = vq->num_free;
 	return ret;
 }
 
@@ -307,6 +305,10 @@ static int virtio_gpu_queue_ctrl_buffer(struct virtio_gpu_device *vgdev,
 	spin_lock(&vgdev->ctrlq.qlock);
 	rc = virtio_gpu_queue_ctrl_buffer_locked(vgdev, vbuf);
 	spin_unlock(&vgdev->ctrlq.qlock);
+
+	if (rc > 0)
+		virtqueue_notify(vgdev->ctrlq.vq);
+
 	return rc;
 }
 
@@ -339,6 +341,10 @@ static int virtio_gpu_queue_fenced_ctrl_buffer(struct virtio_gpu_device *vgdev,
 		virtio_gpu_fence_emit(vgdev, hdr, fence);
 	rc = virtio_gpu_queue_ctrl_buffer_locked(vgdev, vbuf);
 	spin_unlock(&vgdev->ctrlq.qlock);
+
+	if (rc > 0)
+		virtqueue_notify(vgdev->ctrlq.vq);
+
 	return rc;
 }
 
@@ -369,13 +375,14 @@ static int virtio_gpu_queue_cursor(struct virtio_gpu_device *vgdev,
 		trace_virtio_gpu_cmd_queue(vq,
 			(struct virtio_gpu_ctrl_hdr *)vbuf->buf);
 
-		virtqueue_kick(vq);
+		ret = virtqueue_kick_prepare(vq);
 	}
 
 	spin_unlock(&vgdev->cursorq.qlock);
 
-	if (!ret)
-		ret = vq->num_free;
+	if (ret > 0)
+		virtqueue_notify(vq);
+
 	return ret;
 }
 
-- 
2.22.0.410.gd8fdbe21b5-goog