Virtio-fs devices might allocate significant resources to virtio queues such as CPU cores that busy poll on the queue. The device indicates how many request queues it can support and the driver should initialize the number of queues that they want to utilize.
In this patch we limit the number of initialized request queues to the number of CPUs, to limit the resource consumption on the device-side and to prepare for the upcoming multi-queue patch. Signed-off-by: Peter-Jan Gootzen <[email protected]> Signed-off-by: Yoray Zack <[email protected]> Suggested-by: Max Gurtovoy <[email protected]> Reviewed-by: Max Gurtovoy <[email protected]> --- fs/fuse/virtio_fs.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/fs/fuse/virtio_fs.c b/fs/fuse/virtio_fs.c index 322af827a232..2745fa484dcb 100644 --- a/fs/fuse/virtio_fs.c +++ b/fs/fuse/virtio_fs.c @@ -751,6 +751,9 @@ static int virtio_fs_setup_vqs(struct virtio_device *vdev, if (fs->num_request_queues == 0) return -EINVAL; + /* Truncate nr of request queues to nr_cpu_id */ + fs->num_request_queues = min_t(unsigned int, fs->num_request_queues, + nr_cpu_ids); fs->nvqs = VQ_REQUEST + fs->num_request_queues; fs->vqs = kcalloc(fs->nvqs, sizeof(fs->vqs[VQ_HIPRIO]), GFP_KERNEL); if (!fs->vqs) -- 2.34.1
