1 files changed, 212 insertions, 153 deletions

diff --git a/fs/fuse/virtio_fs.c b/fs/fuse/virtio_fs.c
index 6af3f131e468..bade74768903 100644
--- a/fs/fuse/virtio_fs.c
+++ b/fs/fuse/virtio_fs.c
@@ -30,10 +30,12 @@ struct virtio_fs_vq {
 	struct virtqueue *vq;     /* protected by ->lock */
 	struct work_struct done_work;
 	struct list_head queued_reqs;
+	struct list_head end_reqs;	/* End these requests */
 	struct delayed_work dispatch_work;
 	struct fuse_dev *fud;
 	bool connected;
 	long in_flight;
+	struct completion in_flight_zero; /* No inflight requests */
 	char name[24];
 } ____cacheline_aligned_in_smp;
 
@@ -47,13 +49,20 @@ struct virtio_fs {
 	unsigned int num_request_queues; /* number of request queues */
 };
 
-struct virtio_fs_forget {
+struct virtio_fs_forget_req {
 	struct fuse_in_header ih;
 	struct fuse_forget_in arg;
+};
+
+struct virtio_fs_forget {
 	/* This request can be temporarily queued on virt queue */
 	struct list_head list;
+	struct virtio_fs_forget_req req;
 };
 
+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;
@@ -66,6 +75,21 @@ static inline struct fuse_pqueue *vq_to_fpq(struct virtqueue *vq)
 	return &vq_to_fsvq(vq)->fud->pq;
 }
 
+/* Should be called with fsvq->lock held. */
+static inline void inc_in_flight_req(struct virtio_fs_vq *fsvq)
+{
+	fsvq->in_flight++;
+}
+
+/* Should be called with fsvq->lock held. */
+static inline void dec_in_flight_req(struct virtio_fs_vq *fsvq)
+{
+	WARN_ON(fsvq->in_flight <= 0);
+	fsvq->in_flight--;
+	if (!fsvq->in_flight)
+		complete(&fsvq->in_flight_zero);
+}
+
 static void release_virtio_fs_obj(struct kref *ref)
 {
 	struct virtio_fs *vfs = container_of(ref, struct virtio_fs, refcount);
@@ -94,51 +118,46 @@ static void virtio_fs_drain_queue(struct virtio_fs_vq *fsvq)
 	WARN_ON(fsvq->in_flight < 0);
 
 	/* Wait for in flight requests to finish.*/
-	while (1) {
-		spin_lock(&fsvq->lock);
-		if (!fsvq->in_flight) {
-			spin_unlock(&fsvq->lock);
-			break;
-		}
+	spin_lock(&fsvq->lock);
+	if (fsvq->in_flight) {
+		/* We are holding virtio_fs_mutex. There should not be any
+		 * waiters waiting for completion.
+		 */
+		reinit_completion(&fsvq->in_flight_zero);
+		spin_unlock(&fsvq->lock);
+		wait_for_completion(&fsvq->in_flight_zero);
+	} else {
 		spin_unlock(&fsvq->lock);
-		/* TODO use completion instead of timeout */
-		usleep_range(1000, 2000);
 	}
 
 	flush_work(&fsvq->done_work);
 	flush_delayed_work(&fsvq->dispatch_work);
 }
 
-static inline void drain_hiprio_queued_reqs(struct virtio_fs_vq *fsvq)
-{
-	struct virtio_fs_forget *forget;
-
-	spin_lock(&fsvq->lock);
-	while (1) {
-		forget = list_first_entry_or_null(&fsvq->queued_reqs,
-						struct virtio_fs_forget, list);
-		if (!forget)
-			break;
-		list_del(&forget->list);
-		kfree(forget);
-	}
-	spin_unlock(&fsvq->lock);
-}
-
-static void virtio_fs_drain_all_queues(struct virtio_fs *fs)
+static void virtio_fs_drain_all_queues_locked(struct virtio_fs *fs)
 {
 	struct virtio_fs_vq *fsvq;
 	int i;
 
 	for (i = 0; i < fs->nvqs; i++) {
 		fsvq = &fs->vqs[i];
-		if (i == VQ_HIPRIO)
-			drain_hiprio_queued_reqs(fsvq);
-
 		virtio_fs_drain_queue(fsvq);
 	}
 }
 
+static void virtio_fs_drain_all_queues(struct virtio_fs *fs)
+{
+	/* Provides mutual exclusion between ->remove and ->kill_sb
+	 * paths. We don't want both of these draining queue at the
+	 * same time. Current completion logic reinits completion
+	 * and that means there should not be any other thread
+	 * doing reinit or waiting for completion already.
+	 */
+	mutex_lock(&virtio_fs_mutex);
+	virtio_fs_drain_all_queues_locked(fs);
+	mutex_unlock(&virtio_fs_mutex);
+}
+
 static void virtio_fs_start_all_queues(struct virtio_fs *fs)
 {
 	struct virtio_fs_vq *fsvq;
@@ -253,74 +272,148 @@ static void virtio_fs_hiprio_done_work(struct work_struct *work)
 
 		while ((req = virtqueue_get_buf(vq, &len)) != NULL) {
 			kfree(req);
-			fsvq->in_flight--;
+			dec_in_flight_req(fsvq);
 		}
 	} while (!virtqueue_enable_cb(vq) && likely(!virtqueue_is_broken(vq)));
 	spin_unlock(&fsvq->lock);
 }
 
-static void virtio_fs_dummy_dispatch_work(struct work_struct *work)
+static void virtio_fs_request_dispatch_work(struct work_struct *work)
 {
-}
-
-static void virtio_fs_hiprio_dispatch_work(struct work_struct *work)
-{
-	struct virtio_fs_forget *forget;
+	struct fuse_req *req;
 	struct virtio_fs_vq *fsvq = container_of(work, struct virtio_fs_vq,
 						 dispatch_work.work);
-	struct virtqueue *vq = fsvq->vq;
-	struct scatterlist sg;
-	struct scatterlist *sgs[] = {&sg};
-	bool notify;
+	struct fuse_conn *fc = fsvq->fud->fc;
 	int ret;
 
 	pr_debug("virtio-fs: worker %s called.\n", __func__);
 	while (1) {
 		spin_lock(&fsvq->lock);
-		forget = list_first_entry_or_null(&fsvq->queued_reqs,
-					struct virtio_fs_forget, list);
-		if (!forget) {
+		req = list_first_entry_or_null(&fsvq->end_reqs, struct fuse_req,
+					       list);
+		if (!req) {
 			spin_unlock(&fsvq->lock);
-			return;
+			break;
 		}
 
-		list_del(&forget->list);
-		if (!fsvq->connected) {
+		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);
-			kfree(forget);
-			continue;
+			return;
 		}
+		list_del_init(&req->list);
+		spin_unlock(&fsvq->lock);
 
-		sg_init_one(&sg, forget, sizeof(*forget));
-
-		/* Enqueue the request */
-		dev_dbg(&vq->vdev->dev, "%s\n", __func__);
-		ret = virtqueue_add_sgs(vq, sgs, 1, 0, forget, GFP_ATOMIC);
+		ret = virtio_fs_enqueue_req(fsvq, req, true);
 		if (ret < 0) {
 			if (ret == -ENOMEM || ret == -ENOSPC) {
-				pr_debug("virtio-fs: Could not queue FORGET: err=%d. Will try later\n",
-					 ret);
-				list_add_tail(&forget->list,
-						&fsvq->queued_reqs);
+				spin_lock(&fsvq->lock);
+				list_add_tail(&req->list, &fsvq->queued_reqs);
 				schedule_delayed_work(&fsvq->dispatch_work,
-						msecs_to_jiffies(1));
-			} else {
-				pr_debug("virtio-fs: Could not queue FORGET: err=%d. Dropping it.\n",
-					 ret);
-				kfree(forget);
+						      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);
+		}
+	}
+}
+
+/*
+ * Returns 1 if queue is full and sender should wait a bit before sending
+ * next request, 0 otherwise.
+ */
+static int send_forget_request(struct virtio_fs_vq *fsvq,
+			       struct virtio_fs_forget *forget,
+			       bool in_flight)
+{
+	struct scatterlist sg;
+	struct virtqueue *vq;
+	int ret = 0;
+	bool notify;
+	struct virtio_fs_forget_req *req = &forget->req;
+
+	spin_lock(&fsvq->lock);
+	if (!fsvq->connected) {
+		if (in_flight)
+			dec_in_flight_req(fsvq);
+		kfree(forget);
+		goto out;
+	}
+
+	sg_init_one(&sg, req, sizeof(*req));
+	vq = fsvq->vq;
+	dev_dbg(&vq->vdev->dev, "%s\n", __func__);
+
+	ret = virtqueue_add_outbuf(vq, &sg, 1, forget, GFP_ATOMIC);
+	if (ret < 0) {
+		if (ret == -ENOMEM || ret == -ENOSPC) {
+			pr_debug("virtio-fs: Could not queue FORGET: err=%d. Will try later\n",
+				 ret);
+			list_add_tail(&forget->list, &fsvq->queued_reqs);
+			schedule_delayed_work(&fsvq->dispatch_work,
+					      msecs_to_jiffies(1));
+			if (!in_flight)
+				inc_in_flight_req(fsvq);
+			/* Queue is full */
+			ret = 1;
+		} else {
+			pr_debug("virtio-fs: Could not queue FORGET: err=%d. Dropping it.\n",
+				 ret);
+			kfree(forget);
+			if (in_flight)
+				dec_in_flight_req(fsvq);
+		}
+		goto out;
+	}
+
+	if (!in_flight)
+		inc_in_flight_req(fsvq);
+	notify = virtqueue_kick_prepare(vq);
+	spin_unlock(&fsvq->lock);
+
+	if (notify)
+		virtqueue_notify(vq);
+	return ret;
+out:
+	spin_unlock(&fsvq->lock);
+	return ret;
+}
+
+static void virtio_fs_hiprio_dispatch_work(struct work_struct *work)
+{
+	struct virtio_fs_forget *forget;
+	struct virtio_fs_vq *fsvq = container_of(work, struct virtio_fs_vq,
+						 dispatch_work.work);
+	pr_debug("virtio-fs: worker %s called.\n", __func__);
+	while (1) {
+		spin_lock(&fsvq->lock);
+		forget = list_first_entry_or_null(&fsvq->queued_reqs,
+					struct virtio_fs_forget, list);
+		if (!forget) {
 			spin_unlock(&fsvq->lock);
 			return;
 		}
 
-		fsvq->in_flight++;
-		notify = virtqueue_kick_prepare(vq);
+		list_del(&forget->list);
 		spin_unlock(&fsvq->lock);
-
-		if (notify)
-			virtqueue_notify(vq);
-		pr_debug("virtio-fs: worker %s dispatched one forget request.\n",
-			 __func__);
+		if (send_forget_request(fsvq, forget, true))
+			return;
 	}
 }
 
@@ -452,7 +545,7 @@ static void virtio_fs_requests_done_work(struct work_struct *work)
 
 		fuse_request_end(fc, req);
 		spin_lock(&fsvq->lock);
-		fsvq->in_flight--;
+		dec_in_flight_req(fsvq);
 		spin_unlock(&fsvq->lock);
 	}
 }
@@ -502,8 +595,10 @@ static int virtio_fs_setup_vqs(struct virtio_device *vdev,
 	names[VQ_HIPRIO] = fs->vqs[VQ_HIPRIO].name;
 	INIT_WORK(&fs->vqs[VQ_HIPRIO].done_work, virtio_fs_hiprio_done_work);
 	INIT_LIST_HEAD(&fs->vqs[VQ_HIPRIO].queued_reqs);
+	INIT_LIST_HEAD(&fs->vqs[VQ_HIPRIO].end_reqs);
 	INIT_DELAYED_WORK(&fs->vqs[VQ_HIPRIO].dispatch_work,
 			virtio_fs_hiprio_dispatch_work);
+	init_completion(&fs->vqs[VQ_HIPRIO].in_flight_zero);
 	spin_lock_init(&fs->vqs[VQ_HIPRIO].lock);
 
 	/* Initialize the requests virtqueues */
@@ -511,8 +606,10 @@ static int virtio_fs_setup_vqs(struct virtio_device *vdev,
 		spin_lock_init(&fs->vqs[i].lock);
 		INIT_WORK(&fs->vqs[i].done_work, virtio_fs_requests_done_work);
 		INIT_DELAYED_WORK(&fs->vqs[i].dispatch_work,
-					virtio_fs_dummy_dispatch_work);
+				  virtio_fs_request_dispatch_work);
 		INIT_LIST_HEAD(&fs->vqs[i].queued_reqs);
+		INIT_LIST_HEAD(&fs->vqs[i].end_reqs);
+		init_completion(&fs->vqs[i].in_flight_zero);
 		snprintf(fs->vqs[i].name, sizeof(fs->vqs[i].name),
 			 "requests.%u", i - VQ_REQUEST);
 		callbacks[i] = virtio_fs_vq_done;
@@ -606,7 +703,7 @@ static void virtio_fs_remove(struct virtio_device *vdev)
 	/* This device is going away. No one should get new reference */
 	list_del_init(&fs->list);
 	virtio_fs_stop_all_queues(fs);
-	virtio_fs_drain_all_queues(fs);
+	virtio_fs_drain_all_queues_locked(fs);
 	vdev->config->reset(vdev);
 	virtio_fs_cleanup_vqs(vdev, fs);
 
@@ -631,12 +728,12 @@ static int virtio_fs_restore(struct virtio_device *vdev)
 }
 #endif /* CONFIG_PM_SLEEP */
 
-const static struct virtio_device_id id_table[] = {
+static const struct virtio_device_id id_table[] = {
 	{ VIRTIO_ID_FS, VIRTIO_DEV_ANY_ID },
 	{},
 };
 
-const static unsigned int feature_table[] = {};
+static const unsigned int feature_table[] = {};
 
 static struct virtio_driver virtio_fs_driver = {
 	.driver.name		= KBUILD_MODNAME,
@@ -657,14 +754,10 @@ __releases(fiq->lock)
 {
 	struct fuse_forget_link *link;
 	struct virtio_fs_forget *forget;
-	struct scatterlist sg;
-	struct scatterlist *sgs[] = {&sg};
+	struct virtio_fs_forget_req *req;
 	struct virtio_fs *fs;
-	struct virtqueue *vq;
 	struct virtio_fs_vq *fsvq;
-	bool notify;
 	u64 unique;
-	int ret;
 
 	link = fuse_dequeue_forget(fiq, 1, NULL);
 	unique = fuse_get_unique(fiq);
@@ -675,56 +768,19 @@ __releases(fiq->lock)
 
 	/* Allocate a buffer for the request */
 	forget = kmalloc(sizeof(*forget), GFP_NOFS | __GFP_NOFAIL);
+	req = &forget->req;
 
-	forget->ih = (struct fuse_in_header){
+	req->ih = (struct fuse_in_header){
 		.opcode = FUSE_FORGET,
 		.nodeid = link->forget_one.nodeid,
 		.unique = unique,
-		.len = sizeof(*forget),
+		.len = sizeof(*req),
 	};
-	forget->arg = (struct fuse_forget_in){
+	req->arg = (struct fuse_forget_in){
 		.nlookup = link->forget_one.nlookup,
 	};
 
-	sg_init_one(&sg, forget, sizeof(*forget));
-
-	/* Enqueue the request */
-	spin_lock(&fsvq->lock);
-
-	if (!fsvq->connected) {
-		kfree(forget);
-		spin_unlock(&fsvq->lock);
-		goto out;
-	}
-
-	vq = fsvq->vq;
-	dev_dbg(&vq->vdev->dev, "%s\n", __func__);
-
-	ret = virtqueue_add_sgs(vq, sgs, 1, 0, forget, GFP_ATOMIC);
-	if (ret < 0) {
-		if (ret == -ENOMEM || ret == -ENOSPC) {
-			pr_debug("virtio-fs: Could not queue FORGET: err=%d. Will try later.\n",
-				 ret);
-			list_add_tail(&forget->list, &fsvq->queued_reqs);
-			schedule_delayed_work(&fsvq->dispatch_work,
-					msecs_to_jiffies(1));
-		} else {
-			pr_debug("virtio-fs: Could not queue FORGET: err=%d. Dropping it.\n",
-				 ret);
-			kfree(forget);
-		}
-		spin_unlock(&fsvq->lock);
-		goto out;
-	}
-
-	fsvq->in_flight++;
-	notify = virtqueue_kick_prepare(vq);
-
-	spin_unlock(&fsvq->lock);
-
-	if (notify)
-		virtqueue_notify(vq);
-out:
+	send_forget_request(fsvq, forget, false);
 	kfree(link);
 }
 
@@ -819,7 +875,7 @@ 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];
@@ -835,6 +891,7 @@ static int virtio_fs_enqueue_req(struct virtio_fs_vq *fsvq,
 	unsigned int i;
 	int ret;
 	bool notify;
+	struct fuse_pqueue *fpq;
 
 	/* Does the sglist fit on the stack? */
 	total_sgs = sg_count_fuse_req(req);
@@ -889,7 +946,17 @@ static int virtio_fs_enqueue_req(struct virtio_fs_vq *fsvq,
 		goto out;
 	}
 
-	fsvq->in_flight++;
+	/* Request successfully sent. */
+	fpq = &fsvq->fud->pq;
+	spin_lock(&fpq->lock);
+	list_add_tail(&req->list, fpq->processing);
+	spin_unlock(&fpq->lock);
+	set_bit(FR_SENT, &req->flags);
+	/* matches barrier in request_wait_answer() */
+	smp_mb__after_atomic();
+
+	if (!in_flight)
+		inc_in_flight_req(fsvq);
 	notify = virtqueue_kick_prepare(vq);
 
 	spin_unlock(&fsvq->lock);
@@ -915,9 +982,8 @@ __releases(fiq->lock)
 {
 	unsigned int queue_id = VQ_REQUEST; /* TODO multiqueue */
 	struct virtio_fs *fs;
-	struct fuse_conn *fc;
 	struct fuse_req *req;
-	struct fuse_pqueue *fpq;
+	struct virtio_fs_vq *fsvq;
 	int ret;
 
 	WARN_ON(list_empty(&fiq->pending));
@@ -928,49 +994,41 @@ __releases(fiq->lock)
 	spin_unlock(&fiq->lock);
 
 	fs = fiq->priv;
-	fc = fs->vqs[queue_id].fud->fc;
 
 	pr_debug("%s: opcode %u unique %#llx nodeid %#llx in.len %u out.len %u\n",
 		  __func__, req->in.h.opcode, req->in.h.unique,
 		 req->in.h.nodeid, req->in.h.len,
 		 fuse_len_args(req->args->out_numargs, req->args->out_args));
 
-	fpq = &fs->vqs[queue_id].fud->pq;
-	spin_lock(&fpq->lock);
-	if (!fpq->connected) {
-		spin_unlock(&fpq->lock);
-		req->out.h.error = -ENODEV;
-		pr_err("virtio-fs: %s disconnected\n", __func__);
-		fuse_request_end(fc, req);
-		return;
-	}
-	list_add_tail(&req->list, fpq->processing);
-	spin_unlock(&fpq->lock);
-	set_bit(FR_SENT, &req->flags);
-	/* matches barrier in request_wait_answer() */
-	smp_mb__after_atomic();
-
-retry:
-	ret = virtio_fs_enqueue_req(&fs->vqs[queue_id], req);
+	fsvq = &fs->vqs[queue_id];
+	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);
-		spin_lock(&fpq->lock);
-		clear_bit(FR_SENT, &req->flags);
-		list_del_init(&req->list);
-		spin_unlock(&fpq->lock);
-		fuse_request_end(fc, req);
+
+		/* Can't end request in submission context. Use a worker */
+		spin_lock(&fsvq->lock);
+		list_add_tail(&req->list, &fsvq->end_reqs);
+		schedule_delayed_work(&fsvq->dispatch_work, 0);
+		spin_unlock(&fsvq->lock);
 		return;
 	}
 }
 
-const static struct fuse_iqueue_ops virtio_fs_fiq_ops = {
+static const struct fuse_iqueue_ops virtio_fs_fiq_ops = {
 	.wake_forget_and_unlock		= virtio_fs_wake_forget_and_unlock,
 	.wake_interrupt_and_unlock	= virtio_fs_wake_interrupt_and_unlock,
 	.wake_pending_and_unlock	= virtio_fs_wake_pending_and_unlock,
@@ -992,6 +1050,7 @@ static int virtio_fs_fill_super(struct super_block *sb)
 		.destroy = true,
 		.no_control = true,
 		.no_force_umount = true,
+		.no_mount_options = true,
 	};
 
 	mutex_lock(&virtio_fs_mutex);