diff mbox series

[RFC,v7,11/16] fuse: {uring} Allow to queue fg requests through io-uring

Message ID 20241127-fuse-uring-for-6-10-rfc4-v7-11-934b3a69baca@ddn.com (mailing list archive)
State New
Headers show
Series fuse: fuse-over-io-uring | expand

Commit Message

Bernd Schubert Nov. 27, 2024, 1:40 p.m. UTC
This prepares queueing and sending foreground requests through
io-uring.

Signed-off-by: Bernd Schubert <bschubert@ddn.com>
---
 fs/fuse/dev.c         |   5 +-
 fs/fuse/dev_uring.c   | 159 ++++++++++++++++++++++++++++++++++++++++++++++++++
 fs/fuse/dev_uring_i.h |   8 +++
 fs/fuse/fuse_dev_i.h  |   5 ++
 4 files changed, 175 insertions(+), 2 deletions(-)
diff mbox series

Patch

diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c
index ed85a5f2d6c360b8401b174bc97cc135d87e90d9..c53deb690cc9c7958741cd144fcad166b5721e11 100644
--- a/fs/fuse/dev.c
+++ b/fs/fuse/dev.c
@@ -237,7 +237,8 @@  __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) {
@@ -250,7 +251,7 @@  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)) {
diff --git a/fs/fuse/dev_uring.c b/fs/fuse/dev_uring.c
index b5bb78b5f5902c8b87f3e196baaa05640380046d..b1c56ccf828ec2d4cd921906fb42901fefcc6cc5 100644
--- a/fs/fuse/dev_uring.c
+++ b/fs/fuse/dev_uring.c
@@ -24,6 +24,12 @@  bool fuse_uring_enabled(void)
 	return enable_uring;
 }
 
+struct fuse_uring_cmd_pdu {
+	struct fuse_ring_ent *ring_ent;
+};
+
+const struct fuse_iqueue_ops fuse_io_uring_ops;
+
 static void fuse_uring_req_end(struct fuse_ring_ent *ring_ent, bool set_err,
 			       int error)
 {
@@ -773,6 +779,31 @@  static int fuse_uring_commit_fetch(struct io_uring_cmd *cmd, int issue_flags,
 	return 0;
 }
 
+static bool is_ring_ready(struct fuse_ring *ring, int current_qid)
+{
+	int qid;
+	struct fuse_ring_queue *queue;
+	bool ready = true;
+
+	for (qid = 0; qid < ring->nr_queues && ready; qid++) {
+		if (current_qid == qid)
+			continue;
+
+		queue = ring->queues[qid];
+		if (!queue) {
+			ready = false;
+			break;
+		}
+
+		spin_lock(&queue->lock);
+		if (list_empty(&queue->ent_avail_queue))
+			ready = false;
+		spin_unlock(&queue->lock);
+	}
+
+	return ready;
+}
+
 /*
  * fuse_uring_req_fetch command handling
  */
@@ -781,11 +812,23 @@  static void _fuse_uring_fetch(struct fuse_ring_ent *ring_ent,
 			      unsigned int issue_flags)
 {
 	struct fuse_ring_queue *queue = ring_ent->queue;
+	struct fuse_ring *ring = queue->ring;
+	struct fuse_conn *fc = ring->fc;
+	struct fuse_iqueue *fiq = &fc->iq;
 
 	spin_lock(&queue->lock);
 	fuse_uring_ent_avail(ring_ent, queue);
 	ring_ent->cmd = cmd;
 	spin_unlock(&queue->lock);
+
+	if (!ring->ready) {
+		bool ready = is_ring_ready(ring, queue->qid);
+
+		if (ready) {
+			WRITE_ONCE(ring->ready, true);
+			fiq->ops = &fuse_io_uring_ops;
+		}
+	}
 }
 
 /*
@@ -945,3 +988,119 @@  int fuse_uring_cmd(struct io_uring_cmd *cmd, unsigned int issue_flags)
 
 	return -EIOCBQUEUED;
 }
+
+/*
+ * This prepares and sends the ring request in fuse-uring task context.
+ * User buffers are not mapped yet - the application does not have permission
+ * to write to it - this has to be executed in ring task context.
+ */
+static void
+fuse_uring_send_req_in_task(struct io_uring_cmd *cmd,
+			    unsigned int issue_flags)
+{
+	struct fuse_uring_cmd_pdu *pdu = (struct fuse_uring_cmd_pdu *)cmd->pdu;
+	struct fuse_ring_ent *ring_ent = pdu->ring_ent;
+	struct fuse_ring_queue *queue = ring_ent->queue;
+	int err;
+
+	BUILD_BUG_ON(sizeof(pdu) > sizeof(cmd->pdu));
+
+	err = fuse_uring_prepare_send(ring_ent);
+	if (err)
+		goto err;
+
+	io_uring_cmd_done(cmd, 0, 0, issue_flags);
+
+	spin_lock(&queue->lock);
+	ring_ent->state = FRRS_USERSPACE;
+	list_move(&ring_ent->list, &queue->ent_in_userspace);
+	spin_unlock(&queue->lock);
+	return;
+err:
+	fuse_uring_next_fuse_req(ring_ent, queue);
+}
+
+static struct fuse_ring_queue *fuse_uring_task_to_queue(struct fuse_ring *ring)
+{
+	unsigned int qid;
+	struct fuse_ring_queue *queue;
+
+	qid = task_cpu(current);
+
+	if (WARN_ONCE(qid >= ring->nr_queues,
+		      "Core number (%u) exceeds nr ueues (%zu)\n", qid,
+		      ring->nr_queues))
+		qid = 0;
+
+	queue = ring->queues[qid];
+	if (WARN_ONCE(!queue, "Missing queue for qid %d\n", qid))
+		return NULL;
+
+	return queue;
+}
+
+/* queue a fuse request and send it if a ring entry is available */
+void fuse_uring_queue_fuse_req(struct fuse_iqueue *fiq, struct fuse_req *req)
+{
+	struct fuse_conn *fc = req->fm->fc;
+	struct fuse_ring *ring = fc->ring;
+	struct fuse_ring_queue *queue;
+	struct fuse_ring_ent *ring_ent = NULL;
+	int err;
+
+	err = -EINVAL;
+	queue = fuse_uring_task_to_queue(ring);
+	if (!queue)
+		goto err;
+
+	if (req->in.h.opcode != FUSE_NOTIFY_REPLY)
+		req->in.h.unique = fuse_get_unique(fiq);
+	spin_lock(&queue->lock);
+	err = -ENOTCONN;
+	if (unlikely(queue->stopped))
+		goto err_unlock;
+
+	if (!list_empty(&queue->ent_avail_queue)) {
+		ring_ent = list_first_entry(&queue->ent_avail_queue,
+					    struct fuse_ring_ent, list);
+
+		fuse_uring_add_req_to_ring_ent(ring_ent, req);
+	} else {
+		list_add_tail(&req->list, &queue->fuse_req_queue);
+	}
+	spin_unlock(&queue->lock);
+
+	if (ring_ent) {
+		struct io_uring_cmd *cmd = ring_ent->cmd;
+		struct fuse_uring_cmd_pdu *pdu =
+			(struct fuse_uring_cmd_pdu *)cmd->pdu;
+
+		err = -EIO;
+		if (WARN_ON_ONCE(ring_ent->state != FRRS_FUSE_REQ))
+			goto err;
+
+		pdu->ring_ent = ring_ent;
+		io_uring_cmd_complete_in_task(cmd, fuse_uring_send_req_in_task);
+	}
+
+	return;
+
+err_unlock:
+	spin_unlock(&queue->lock);
+err:
+	req->out.h.error = err;
+	clear_bit(FR_PENDING, &req->flags);
+	fuse_request_end(req);
+}
+
+const struct fuse_iqueue_ops fuse_io_uring_ops = {
+	/* should be send over io-uring as enhancement */
+	.send_forget = fuse_dev_queue_forget,
+
+	/*
+	 * could be send over io-uring, but interrupts should be rare,
+	 * no need to make the code complex
+	 */
+	.send_interrupt = fuse_dev_queue_interrupt,
+	.send_req = fuse_uring_queue_fuse_req,
+};
diff --git a/fs/fuse/dev_uring_i.h b/fs/fuse/dev_uring_i.h
index 52259714ffc59a38b21f834ae5e317fe818863dc..19867d27894f9d985e224111ea586c82b4b4cfe8 100644
--- a/fs/fuse/dev_uring_i.h
+++ b/fs/fuse/dev_uring_i.h
@@ -119,6 +119,8 @@  struct fuse_ring {
 	unsigned long teardown_time;
 
 	atomic_t queue_refs;
+
+	bool ready;
 };
 
 bool fuse_uring_enabled(void);
@@ -126,6 +128,7 @@  void fuse_uring_destruct(struct fuse_conn *fc);
 void fuse_uring_stop_queues(struct fuse_ring *ring);
 void fuse_uring_abort_end_requests(struct fuse_ring *ring);
 int fuse_uring_cmd(struct io_uring_cmd *cmd, unsigned int issue_flags);
+void fuse_uring_queue_fuse_req(struct fuse_iqueue *fiq, struct fuse_req *req);
 
 static inline void fuse_uring_abort(struct fuse_conn *fc)
 {
@@ -149,6 +152,11 @@  static inline void fuse_uring_wait_stopped_queues(struct fuse_conn *fc)
 			   atomic_read(&ring->queue_refs) == 0);
 }
 
+static inline bool fuse_uring_ready(struct fuse_conn *fc)
+{
+	return fc->ring && fc->ring->ready;
+}
+
 #else /* CONFIG_FUSE_IO_URING */
 
 struct fuse_ring;
diff --git a/fs/fuse/fuse_dev_i.h b/fs/fuse/fuse_dev_i.h
index d7bf72dabd84c3896d1447380649e2f4d20b0643..1d1c1e9848fba8dae46651e28809f73e165e74fe 100644
--- a/fs/fuse/fuse_dev_i.h
+++ b/fs/fuse/fuse_dev_i.h
@@ -17,6 +17,8 @@  struct fuse_arg;
 struct fuse_args;
 struct fuse_pqueue;
 struct fuse_req;
+struct fuse_iqueue;
+struct fuse_forget_link;
 
 struct fuse_copy_state {
 	int write;
@@ -58,6 +60,9 @@  int fuse_copy_args(struct fuse_copy_state *cs, unsigned int numargs,
 		   int zeroing);
 int fuse_copy_out_args(struct fuse_copy_state *cs, struct fuse_args *args,
 		       unsigned int nbytes);
+void fuse_dev_queue_forget(struct fuse_iqueue *fiq,
+			   struct fuse_forget_link *forget);
+void fuse_dev_queue_interrupt(struct fuse_iqueue *fiq, struct fuse_req *req);
 
 #endif