1 files changed, 216 insertions, 80 deletions

diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c
index 9ce6d1c6cac1..6dcbaa218b7a 100644
--- a/fs/fuse/dev.c
+++ b/fs/fuse/dev.c
@@ -6,7 +6,9 @@
   See the file COPYING.
 */
 
+#include "dev_uring_i.h"
 #include "fuse_i.h"
+#include "fuse_dev_i.h"
 
 #include <linux/init.h>
 #include <linux/module.h>
@@ -28,21 +30,100 @@
 MODULE_ALIAS_MISCDEV(FUSE_MINOR);
 MODULE_ALIAS("devname:fuse");
 
-/* Ordinary requests have even IDs, while interrupts IDs are odd */
-#define FUSE_INT_REQ_BIT (1ULL << 0)
-#define FUSE_REQ_ID_STEP (1ULL << 1)
-
 static struct kmem_cache *fuse_req_cachep;
 
-static void end_requests(struct list_head *head);
+const unsigned long fuse_timeout_timer_freq =
+	secs_to_jiffies(FUSE_TIMEOUT_TIMER_FREQ);
 
-static struct fuse_dev *fuse_get_dev(struct file *file)
+bool fuse_request_expired(struct fuse_conn *fc, struct list_head *list)
 {
-	/*
-	 * Lockless access is OK, because file->private data is set
-	 * once during mount and is valid until the file is released.
-	 */
-	return READ_ONCE(file->private_data);
+	struct fuse_req *req;
+
+	req = list_first_entry_or_null(list, struct fuse_req, list);
+	if (!req)
+		return false;
+	return time_is_before_jiffies(req->create_time + fc->timeout.req_timeout);
+}
+
+bool fuse_fpq_processing_expired(struct fuse_conn *fc, struct list_head *processing)
+{
+	int i;
+
+	for (i = 0; i < FUSE_PQ_HASH_SIZE; i++)
+		if (fuse_request_expired(fc, &processing[i]))
+			return true;
+
+	return false;
+}
+
+/*
+ * Check if any requests aren't being completed by the time the request timeout
+ * elapses. To do so, we:
+ * - check the fiq pending list
+ * - check the bg queue
+ * - check the fpq io and processing lists
+ *
+ * To make this fast, we only check against the head request on each list since
+ * these are generally queued in order of creation time (eg newer requests get
+ * queued to the tail). We might miss a few edge cases (eg requests transitioning
+ * between lists, re-sent requests at the head of the pending list having a
+ * later creation time than other requests on that list, etc.) but that is fine
+ * since if the request never gets fulfilled, it will eventually be caught.
+ */
+void fuse_check_timeout(struct work_struct *work)
+{
+	struct delayed_work *dwork = to_delayed_work(work);
+	struct fuse_conn *fc = container_of(dwork, struct fuse_conn,
+					    timeout.work);
+	struct fuse_iqueue *fiq = &fc->iq;
+	struct fuse_dev *fud;
+	struct fuse_pqueue *fpq;
+	bool expired = false;
+
+	if (!atomic_read(&fc->num_waiting))
+	    goto out;
+
+	spin_lock(&fiq->lock);
+	expired = fuse_request_expired(fc, &fiq->pending);
+	spin_unlock(&fiq->lock);
+	if (expired)
+		goto abort_conn;
+
+	spin_lock(&fc->bg_lock);
+	expired = fuse_request_expired(fc, &fc->bg_queue);
+	spin_unlock(&fc->bg_lock);
+	if (expired)
+		goto abort_conn;
+
+	spin_lock(&fc->lock);
+	if (!fc->connected) {
+		spin_unlock(&fc->lock);
+		return;
+	}
+	list_for_each_entry(fud, &fc->devices, entry) {
+		fpq = &fud->pq;
+		spin_lock(&fpq->lock);
+		if (fuse_request_expired(fc, &fpq->io) ||
+		    fuse_fpq_processing_expired(fc, fpq->processing)) {
+			spin_unlock(&fpq->lock);
+			spin_unlock(&fc->lock);
+			goto abort_conn;
+		}
+
+		spin_unlock(&fpq->lock);
+	}
+	spin_unlock(&fc->lock);
+
+	if (fuse_uring_request_expired(fc))
+	    goto abort_conn;
+
+out:
+	queue_delayed_work(system_wq, &fc->timeout.work,
+			   fuse_timeout_timer_freq);
+	return;
+
+abort_conn:
+	fuse_abort_conn(fc);
 }
 
 static void fuse_request_init(struct fuse_mount *fm, struct fuse_req *req)
@@ -53,6 +134,7 @@ static void fuse_request_init(struct fuse_mount *fm, struct fuse_req *req)
 	refcount_set(&req->count, 1);
 	__set_bit(FR_PENDING, &req->flags);
 	req->fm = fm;
+	req->create_time = jiffies;
 }
 
 static struct fuse_req *fuse_request_alloc(struct fuse_mount *fm, gfp_t flags)
@@ -89,7 +171,8 @@ void fuse_set_initialized(struct fuse_conn *fc)
 
 static bool fuse_block_alloc(struct fuse_conn *fc, bool for_background)
 {
-	return !fc->initialized || (for_background && fc->blocked);
+	return !fc->initialized || (for_background && fc->blocked) ||
+	       (fc->io_uring && fc->connected && !fuse_uring_ready(fc));
 }
 
 static void fuse_drop_waiting(struct fuse_conn *fc)
@@ -234,7 +317,7 @@ u64 fuse_get_unique(struct fuse_iqueue *fiq)
 }
 EXPORT_SYMBOL_GPL(fuse_get_unique);
 
-static unsigned int fuse_req_hash(u64 unique)
+unsigned int fuse_req_hash(u64 unique)
 {
 	return hash_long(unique & ~FUSE_INT_REQ_BIT, FUSE_PQ_HASH_BITS);
 }
@@ -250,7 +333,8 @@ __releases(fiq->lock)
 	spin_unlock(&fiq->lock);
 }
 
-static void fuse_dev_queue_forget(struct fuse_iqueue *fiq, struct fuse_forget_link *forget)
+void fuse_dev_queue_forget(struct fuse_iqueue *fiq,
+			   struct fuse_forget_link *forget)
 {
 	spin_lock(&fiq->lock);
 	if (fiq->connected) {
@@ -263,7 +347,7 @@ static void fuse_dev_queue_forget(struct fuse_iqueue *fiq, struct fuse_forget_li
 	}
 }
 
-static void fuse_dev_queue_interrupt(struct fuse_iqueue *fiq, struct fuse_req *req)
+void fuse_dev_queue_interrupt(struct fuse_iqueue *fiq, struct fuse_req *req)
 {
 	spin_lock(&fiq->lock);
 	if (list_empty(&req->intr_entry)) {
@@ -418,6 +502,24 @@ static int queue_interrupt(struct fuse_req *req)
 	return 0;
 }
 
+bool fuse_remove_pending_req(struct fuse_req *req, spinlock_t *lock)
+{
+	spin_lock(lock);
+	if (test_bit(FR_PENDING, &req->flags)) {
+		/*
+		 * FR_PENDING does not get cleared as the request will end
+		 * up in destruction anyway.
+		 */
+		list_del(&req->list);
+		spin_unlock(lock);
+		__fuse_put_request(req);
+		req->out.h.error = -EINTR;
+		return true;
+	}
+	spin_unlock(lock);
+	return false;
+}
+
 static void request_wait_answer(struct fuse_req *req)
 {
 	struct fuse_conn *fc = req->fm->fc;
@@ -439,22 +541,20 @@ static void request_wait_answer(struct fuse_req *req)
 	}
 
 	if (!test_bit(FR_FORCE, &req->flags)) {
+		bool removed;
+
 		/* Only fatal signals may interrupt this */
 		err = wait_event_killable(req->waitq,
 					test_bit(FR_FINISHED, &req->flags));
 		if (!err)
 			return;
 
-		spin_lock(&fiq->lock);
-		/* Request is not yet in userspace, bail out */
-		if (test_bit(FR_PENDING, &req->flags)) {
-			list_del(&req->list);
-			spin_unlock(&fiq->lock);
-			__fuse_put_request(req);
-			req->out.h.error = -EINTR;
+		if (test_bit(FR_URING, &req->flags))
+			removed = fuse_uring_remove_pending_req(req);
+		else
+			removed = fuse_remove_pending_req(req, &fiq->lock);
+		if (removed)
 			return;
-		}
-		spin_unlock(&fiq->lock);
 	}
 
 	/*
@@ -580,7 +680,25 @@ ssize_t __fuse_simple_request(struct mnt_idmap *idmap,
 	return ret;
 }
 
-static bool fuse_request_queue_background(struct fuse_req *req)
+#ifdef CONFIG_FUSE_IO_URING
+static bool fuse_request_queue_background_uring(struct fuse_conn *fc,
+					       struct fuse_req *req)
+{
+	struct fuse_iqueue *fiq = &fc->iq;
+
+	req->in.h.unique = fuse_get_unique(fiq);
+	req->in.h.len = sizeof(struct fuse_in_header) +
+		fuse_len_args(req->args->in_numargs,
+			      (struct fuse_arg *) req->args->in_args);
+
+	return fuse_uring_queue_bq_req(req);
+}
+#endif
+
+/*
+ * @return true if queued
+ */
+static int fuse_request_queue_background(struct fuse_req *req)
 {
 	struct fuse_mount *fm = req->fm;
 	struct fuse_conn *fc = fm->fc;
@@ -592,6 +710,12 @@ static bool fuse_request_queue_background(struct fuse_req *req)
 		atomic_inc(&fc->num_waiting);
 	}
 	__set_bit(FR_ISREPLY, &req->flags);
+
+#ifdef CONFIG_FUSE_IO_URING
+	if (fuse_uring_ready(fc))
+		return fuse_request_queue_background_uring(fc, req);
+#endif
+
 	spin_lock(&fc->bg_lock);
 	if (likely(fc->connected)) {
 		fc->num_background++;
@@ -692,22 +816,8 @@ static int unlock_request(struct fuse_req *req)
 	return err;
 }
 
-struct fuse_copy_state {
-	int write;
-	struct fuse_req *req;
-	struct iov_iter *iter;
-	struct pipe_buffer *pipebufs;
-	struct pipe_buffer *currbuf;
-	struct pipe_inode_info *pipe;
-	unsigned long nr_segs;
-	struct page *pg;
-	unsigned len;
-	unsigned offset;
-	unsigned move_pages:1;
-};
-
-static void fuse_copy_init(struct fuse_copy_state *cs, int write,
-			   struct iov_iter *iter)
+void fuse_copy_init(struct fuse_copy_state *cs, int write,
+		    struct iov_iter *iter)
 {
 	memset(cs, 0, sizeof(*cs));
 	cs->write = write;
@@ -814,6 +924,9 @@ static int fuse_copy_do(struct fuse_copy_state *cs, void **val, unsigned *size)
 	*size -= ncpy;
 	cs->len -= ncpy;
 	cs->offset += ncpy;
+	if (cs->is_uring)
+		cs->ring.copied_sz += ncpy;
+
 	return ncpy;
 }
 
@@ -1074,9 +1187,9 @@ static int fuse_copy_one(struct fuse_copy_state *cs, void *val, unsigned size)
 }
 
 /* Copy request arguments to/from userspace buffer */
-static int fuse_copy_args(struct fuse_copy_state *cs, unsigned numargs,
-			  unsigned argpages, struct fuse_arg *args,
-			  int zeroing)
+int fuse_copy_args(struct fuse_copy_state *cs, unsigned numargs,
+		   unsigned argpages, struct fuse_arg *args,
+		   int zeroing)
 {
 	int err = 0;
 	unsigned i;
@@ -1455,7 +1568,7 @@ static ssize_t fuse_dev_splice_read(struct file *in, loff_t *ppos,
 	if (ret < 0)
 		goto out;
 
-	if (pipe_occupancy(pipe->head, pipe->tail) + cs.nr_segs > pipe->max_usage) {
+	if (pipe_buf_usage(pipe) + cs.nr_segs > pipe->max_usage) {
 		ret = -EIO;
 		goto out;
 	}
@@ -1531,14 +1644,10 @@ static int fuse_notify_inval_entry(struct fuse_conn *fc, unsigned int size,
 				   struct fuse_copy_state *cs)
 {
 	struct fuse_notify_inval_entry_out outarg;
-	int err = -ENOMEM;
-	char *buf;
+	int err;
+	char *buf = NULL;
 	struct qstr name;
 
-	buf = kzalloc(FUSE_NAME_MAX + 1, GFP_KERNEL);
-	if (!buf)
-		goto err;
-
 	err = -EINVAL;
 	if (size < sizeof(outarg))
 		goto err;
@@ -1548,13 +1657,18 @@ static int fuse_notify_inval_entry(struct fuse_conn *fc, unsigned int size,
 		goto err;
 
 	err = -ENAMETOOLONG;
-	if (outarg.namelen > FUSE_NAME_MAX)
+	if (outarg.namelen > fc->name_max)
 		goto err;
 
 	err = -EINVAL;
 	if (size != sizeof(outarg) + outarg.namelen + 1)
 		goto err;
 
+	err = -ENOMEM;
+	buf = kzalloc(outarg.namelen + 1, GFP_KERNEL);
+	if (!buf)
+		goto err;
+
 	name.name = buf;
 	name.len = outarg.namelen;
 	err = fuse_copy_one(cs, buf, outarg.namelen + 1);
@@ -1579,14 +1693,10 @@ static int fuse_notify_delete(struct fuse_conn *fc, unsigned int size,
 			      struct fuse_copy_state *cs)
 {
 	struct fuse_notify_delete_out outarg;
-	int err = -ENOMEM;
-	char *buf;
+	int err;
+	char *buf = NULL;
 	struct qstr name;
 
-	buf = kzalloc(FUSE_NAME_MAX + 1, GFP_KERNEL);
-	if (!buf)
-		goto err;
-
 	err = -EINVAL;
 	if (size < sizeof(outarg))
 		goto err;
@@ -1596,13 +1706,18 @@ static int fuse_notify_delete(struct fuse_conn *fc, unsigned int size,
 		goto err;
 
 	err = -ENAMETOOLONG;
-	if (outarg.namelen > FUSE_NAME_MAX)
+	if (outarg.namelen > fc->name_max)
 		goto err;
 
 	err = -EINVAL;
 	if (size != sizeof(outarg) + outarg.namelen + 1)
 		goto err;
 
+	err = -ENOMEM;
+	buf = kzalloc(outarg.namelen + 1, GFP_KERNEL);
+	if (!buf)
+		goto err;
+
 	name.name = buf;
 	name.len = outarg.namelen;
 	err = fuse_copy_one(cs, buf, outarg.namelen + 1);
@@ -1766,7 +1881,7 @@ static int fuse_retrieve(struct fuse_mount *fm, struct inode *inode,
 	args = &ap->args;
 	args->nodeid = outarg->nodeid;
 	args->opcode = FUSE_NOTIFY_REPLY;
-	args->in_numargs = 2;
+	args->in_numargs = 3;
 	args->in_pages = true;
 	args->end = fuse_retrieve_end;
 
@@ -1794,9 +1909,10 @@ static int fuse_retrieve(struct fuse_mount *fm, struct inode *inode,
 	}
 	ra->inarg.offset = outarg->offset;
 	ra->inarg.size = total_len;
-	args->in_args[0].size = sizeof(ra->inarg);
-	args->in_args[0].value = &ra->inarg;
-	args->in_args[1].size = total_len;
+	fuse_set_zero_arg0(args);
+	args->in_args[1].size = sizeof(ra->inarg);
+	args->in_args[1].value = &ra->inarg;
+	args->in_args[2].size = total_len;
 
 	err = fuse_simple_notify_reply(fm, args, outarg->notify_unique);
 	if (err)
@@ -1891,7 +2007,7 @@ static void fuse_resend(struct fuse_conn *fc)
 		spin_unlock(&fiq->lock);
 		list_for_each_entry(req, &to_queue, list)
 			clear_bit(FR_PENDING, &req->flags);
-		end_requests(&to_queue);
+		fuse_dev_end_requests(&to_queue);
 		return;
 	}
 	/* iq and pq requests are both oldest to newest */
@@ -1940,7 +2056,7 @@ static int fuse_notify(struct fuse_conn *fc, enum fuse_notify_code code,
 }
 
 /* Look up request on processing list by unique ID */
-static struct fuse_req *request_find(struct fuse_pqueue *fpq, u64 unique)
+struct fuse_req *fuse_request_find(struct fuse_pqueue *fpq, u64 unique)
 {
 	unsigned int hash = fuse_req_hash(unique);
 	struct fuse_req *req;
@@ -1952,10 +2068,17 @@ static struct fuse_req *request_find(struct fuse_pqueue *fpq, u64 unique)
 	return NULL;
 }
 
-static int copy_out_args(struct fuse_copy_state *cs, struct fuse_args *args,
-			 unsigned nbytes)
+int fuse_copy_out_args(struct fuse_copy_state *cs, struct fuse_args *args,
+		       unsigned nbytes)
 {
-	unsigned reqsize = sizeof(struct fuse_out_header);
+
+	unsigned int reqsize = 0;
+
+	/*
+	 * Uring has all headers separated from args - args is payload only
+	 */
+	if (!cs->is_uring)
+		reqsize = sizeof(struct fuse_out_header);
 
 	reqsize += fuse_len_args(args->out_numargs, args->out_args);
 
@@ -2017,7 +2140,7 @@ static ssize_t fuse_dev_do_write(struct fuse_dev *fud,
 	spin_lock(&fpq->lock);
 	req = NULL;
 	if (fpq->connected)
-		req = request_find(fpq, oh.unique & ~FUSE_INT_REQ_BIT);
+		req = fuse_request_find(fpq, oh.unique & ~FUSE_INT_REQ_BIT);
 
 	err = -ENOENT;
 	if (!req) {
@@ -2055,7 +2178,7 @@ static ssize_t fuse_dev_do_write(struct fuse_dev *fud,
 	if (oh.error)
 		err = nbytes != sizeof(oh) ? -EINVAL : 0;
 	else
-		err = copy_out_args(cs, req->args, nbytes);
+		err = fuse_copy_out_args(cs, req->args, nbytes);
 	fuse_copy_finish(cs);
 
 	spin_lock(&fpq->lock);
@@ -2097,7 +2220,7 @@ static ssize_t fuse_dev_splice_write(struct pipe_inode_info *pipe,
 				     struct file *out, loff_t *ppos,
 				     size_t len, unsigned int flags)
 {
-	unsigned int head, tail, mask, count;
+	unsigned int head, tail, count;
 	unsigned nbuf;
 	unsigned idx;
 	struct pipe_buffer *bufs;
@@ -2114,8 +2237,7 @@ static ssize_t fuse_dev_splice_write(struct pipe_inode_info *pipe,
 
 	head = pipe->head;
 	tail = pipe->tail;
-	mask = pipe->ring_size - 1;
-	count = head - tail;
+	count = pipe_occupancy(head, tail);
 
 	bufs = kvmalloc_array(count, sizeof(struct pipe_buffer), GFP_KERNEL);
 	if (!bufs) {
@@ -2125,8 +2247,8 @@ static ssize_t fuse_dev_splice_write(struct pipe_inode_info *pipe,
 
 	nbuf = 0;
 	rem = 0;
-	for (idx = tail; idx != head && rem < len; idx++)
-		rem += pipe->bufs[idx & mask].len;
+	for (idx = tail; !pipe_empty(head, idx) && rem < len; idx++)
+		rem += pipe_buf(pipe, idx)->len;
 
 	ret = -EINVAL;
 	if (rem < len)
@@ -2137,10 +2259,10 @@ static ssize_t fuse_dev_splice_write(struct pipe_inode_info *pipe,
 		struct pipe_buffer *ibuf;
 		struct pipe_buffer *obuf;
 
-		if (WARN_ON(nbuf >= count || tail == head))
+		if (WARN_ON(nbuf >= count || pipe_empty(head, tail)))
 			goto out_free;
 
-		ibuf = &pipe->bufs[tail & mask];
+		ibuf = pipe_buf(pipe, tail);
 		obuf = &bufs[nbuf];
 
 		if (rem >= ibuf->len) {
@@ -2210,7 +2332,7 @@ static __poll_t fuse_dev_poll(struct file *file, poll_table *wait)
 }
 
 /* Abort all requests on the given list (pending or processing) */
-static void end_requests(struct list_head *head)
+void fuse_dev_end_requests(struct list_head *head)
 {
 	while (!list_empty(head)) {
 		struct fuse_req *req;
@@ -2266,6 +2388,9 @@ void fuse_abort_conn(struct fuse_conn *fc)
 		LIST_HEAD(to_end);
 		unsigned int i;
 
+		if (fc->timeout.req_timeout)
+			cancel_delayed_work(&fc->timeout.work);
+
 		/* Background queuing checks fc->connected under bg_lock */
 		spin_lock(&fc->bg_lock);
 		fc->connected = 0;
@@ -2313,7 +2438,13 @@ void fuse_abort_conn(struct fuse_conn *fc)
 		wake_up_all(&fc->blocked_waitq);
 		spin_unlock(&fc->lock);
 
-		end_requests(&to_end);
+		fuse_dev_end_requests(&to_end);
+
+		/*
+		 * fc->lock must not be taken to avoid conflicts with io-uring
+		 * locks
+		 */
+		fuse_uring_abort(fc);
 	} else {
 		spin_unlock(&fc->lock);
 	}
@@ -2325,6 +2456,8 @@ void fuse_wait_aborted(struct fuse_conn *fc)
 	/* matches implicit memory barrier in fuse_drop_waiting() */
 	smp_mb();
 	wait_event(fc->blocked_waitq, atomic_read(&fc->num_waiting) == 0);
+
+	fuse_uring_wait_stopped_queues(fc);
 }
 
 int fuse_dev_release(struct inode *inode, struct file *file)
@@ -2343,7 +2476,7 @@ int fuse_dev_release(struct inode *inode, struct file *file)
 			list_splice_init(&fpq->processing[i], &to_end);
 		spin_unlock(&fpq->lock);
 
-		end_requests(&to_end);
+		fuse_dev_end_requests(&to_end);
 
 		/* Are we the last open device? */
 		if (atomic_dec_and_test(&fc->dev_count)) {
@@ -2481,6 +2614,9 @@ const struct file_operations fuse_dev_operations = {
 	.fasync		= fuse_dev_fasync,
 	.unlocked_ioctl = fuse_dev_ioctl,
 	.compat_ioctl   = compat_ptr_ioctl,
+#ifdef CONFIG_FUSE_IO_URING
+	.uring_cmd	= fuse_uring_cmd,
+#endif
 };
 EXPORT_SYMBOL_GPL(fuse_dev_operations);