From 986957da44f8674e67090a0be14463297683094e Mon Sep 17 00:00:00 2001 From: Vivek Goyal Date: Tue, 15 Oct 2019 13:46:26 -0400 Subject: [PATCH] virtiofs: Retry request submission from worker context task #28910367 commit a9bfd9dd3417561d06c81de04f6d6c1e0c9b3d44 upstream If regular request queue gets full, currently we sleep for a bit and retrying submission in submitter's context. This assumes submitter is not holding any spin lock. But this assumption is not true for background requests. For background requests, we are called with fc->bg_lock held. This can lead to deadlock where one thread is trying submission with fc->bg_lock held while request completion thread has called fuse_request_end() which tries to acquire fc->bg_lock and gets blocked. As request completion thread gets blocked, it does not make further progress and that means queue does not get empty and submitter can't submit more requests. To solve this issue, retry submission with the help of a worker, instead of retrying in submitter's context. We already do this for hiprio/forget requests. Reported-by: Chirantan Ekbote Signed-off-by: Vivek Goyal Signed-off-by: Miklos Szeredi (cherry picked from commit a9bfd9dd3417561d06c81de04f6d6c1e0c9b3d44) Signed-off-by: Liu Bo Reviewed-by: Joseph Qi --- fs/fuse/virtio_fs.c | 61 ++++++++++++++++++++++++++++++++++++++------- 1 file changed, 52 insertions(+), 9 deletions(-) diff --git a/fs/fuse/virtio_fs.c b/fs/fuse/virtio_fs.c index 2c7a84d9affa..955e9a94b2b1 100644 --- a/fs/fuse/virtio_fs.c +++ b/fs/fuse/virtio_fs.c @@ -54,6 +54,9 @@ struct virtio_fs_forget { struct list_head list; }; +static int virtio_fs_enqueue_req(struct virtio_fs_vq *fsvq, + struct fuse_req *req, bool in_flight); + static inline struct virtio_fs_vq *vq_to_fsvq(struct virtqueue *vq) { struct virtio_fs *fs = vq->vdev->priv; @@ -255,6 +258,7 @@ static void virtio_fs_request_dispatch_work(struct work_struct *work) struct virtio_fs_vq *fsvq = container_of(work, struct virtio_fs_vq, dispatch_work.work); struct fuse_conn *fc = fsvq->fud->fc; + int ret; pr_debug("virtio-fs: worker %s called.\n", __func__); while (1) { @@ -263,13 +267,45 @@ static void virtio_fs_request_dispatch_work(struct work_struct *work) list); if (!req) { spin_unlock(&fsvq->lock); - return; + break; } list_del_init(&req->list); spin_unlock(&fsvq->lock); fuse_request_end(fc, req); } + + /* Dispatch pending requests */ + while (1) { + spin_lock(&fsvq->lock); + req = list_first_entry_or_null(&fsvq->queued_reqs, + struct fuse_req, list); + if (!req) { + spin_unlock(&fsvq->lock); + return; + } + list_del_init(&req->list); + spin_unlock(&fsvq->lock); + + ret = virtio_fs_enqueue_req(fsvq, req, true); + if (ret < 0) { + if (ret == -ENOMEM || ret == -ENOSPC) { + spin_lock(&fsvq->lock); + list_add_tail(&req->list, &fsvq->queued_reqs); + schedule_delayed_work(&fsvq->dispatch_work, + msecs_to_jiffies(1)); + spin_unlock(&fsvq->lock); + return; + } + req->out.h.error = ret; + spin_lock(&fsvq->lock); + dec_in_flight_req(fsvq); + spin_unlock(&fsvq->lock); + pr_err("virtio-fs: virtio_fs_enqueue_req() failed %d\n", + ret); + fuse_request_end(fc, req); + } + } } static void virtio_fs_hiprio_dispatch_work(struct work_struct *work) @@ -825,7 +861,7 @@ static unsigned int sg_init_fuse_args(struct scatterlist *sg, /* Add a request to a virtqueue and kick the device */ static int virtio_fs_enqueue_req(struct virtio_fs_vq *fsvq, - struct fuse_req *req) + struct fuse_req *req, bool in_flight) { /* requests need at least 4 elements */ struct scatterlist *stack_sgs[6]; @@ -904,7 +940,8 @@ static int virtio_fs_enqueue_req(struct virtio_fs_vq *fsvq, /* matches barrier in request_wait_answer() */ smp_mb__after_atomic(); - inc_in_flight_req(fsvq); + if (!in_flight) + inc_in_flight_req(fsvq); notify = virtqueue_kick_prepare(vq); spin_unlock(&fsvq->lock); @@ -950,15 +987,21 @@ __releases(fiq->lock) req->in.h.nodeid, req->in.h.len, fuse_len_args(req->out.numargs, req->out.args)); -retry: fsvq = &fs->vqs[queue_id]; - ret = virtio_fs_enqueue_req(fsvq, req); + ret = virtio_fs_enqueue_req(fsvq, req, false); if (ret < 0) { if (ret == -ENOMEM || ret == -ENOSPC) { - /* Virtqueue full. Retry submission */ - /* TODO use completion instead of timeout */ - usleep_range(20, 30); - goto retry; + /* + * Virtqueue full. Retry submission from worker + * context as we might be holding fc->bg_lock. + */ + spin_lock(&fsvq->lock); + list_add_tail(&req->list, &fsvq->queued_reqs); + inc_in_flight_req(fsvq); + schedule_delayed_work(&fsvq->dispatch_work, + msecs_to_jiffies(1)); + spin_unlock(&fsvq->lock); + return; } req->out.h.error = ret; pr_err("virtio-fs: virtio_fs_enqueue_req() failed %d\n", ret); -- GitLab