[PATCH RFC v3 11/17] fuse: {uring} Add uring sqe commit and fetch support

[Bernd Schubert <bschubert@ddn.com>]

This adds support for fuse request completion through ring SQEs
(FUSE_URING_REQ_COMMIT_AND_FETCH handling). After committing
the ring entry it becomes available for new fuse requests.
Handling of requests through the ring (SQE/CQE handling)
is complete now.

Fuse request data are copied through the mmaped ring buffer,
there is no support for any zero copy yet.

Signed-off-by: Bernd Schubert <bschubert@ddn.com>
---
 fs/fuse/dev_uring.c   | 407 ++++++++++++++++++++++++++++++++++++++++++++++++++
 fs/fuse/dev_uring_i.h |  21 +++
 2 files changed, 428 insertions(+)

diff --git a/fs/fuse/dev_uring.c b/fs/fuse/dev_uring.c
index 46c2274193bf..96347751668e 100644
--- a/fs/fuse/dev_uring.c
+++ b/fs/fuse/dev_uring.c
@@ -29,6 +29,26 @@
 #include <linux/topology.h>
 #include <linux/io_uring/cmd.h>
 
+struct fuse_uring_cmd_pdu {
+	struct fuse_ring_ent *ring_ent;
+};
+
+/*
+ * Finalize a fuse request, then fetch and send the next entry, if available
+ */
+static void fuse_uring_req_end(struct fuse_ring_ent *ring_ent,
+			       bool set_err, int error)
+{
+	struct fuse_req *req = ring_ent->fuse_req;
+
+	if (set_err)
+		req->out.h.error = error;
+
+	clear_bit(FR_SENT, &req->flags);
+	fuse_request_end(ring_ent->fuse_req);
+	ring_ent->fuse_req = NULL;
+}
+
 static int fuse_ring_ring_ent_unset_userspace(struct fuse_ring_ent *ent)
 {
 	if (WARN_ON_ONCE(ent->state != FRRS_USERSPACE))
@@ -40,6 +60,13 @@ static int fuse_ring_ring_ent_unset_userspace(struct fuse_ring_ent *ent)
 	return 0;
 }
 
+static void
+fuse_uring_async_send_to_ring(struct io_uring_cmd *cmd,
+			      unsigned int issue_flags)
+{
+	io_uring_cmd_done(cmd, 0, 0, issue_flags);
+}
+
 /* Update conn limits according to ring values */
 static void fuse_uring_conn_cfg_limits(struct fuse_ring *ring)
 {
@@ -65,6 +92,9 @@ static void fuse_uring_queue_cfg(struct fuse_ring_queue *queue, int qid,
 
 	INIT_LIST_HEAD(&queue->sync_ent_avail_queue);
 	INIT_LIST_HEAD(&queue->async_ent_avail_queue);
+	INIT_LIST_HEAD(&queue->ent_in_userspace);
+	INIT_LIST_HEAD(&queue->sync_fuse_req_queue);
+	INIT_LIST_HEAD(&queue->async_fuse_req_queue);
 
 	for (tag = 0; tag < ring->queue_depth; tag++) {
 		struct fuse_ring_ent *ent = &queue->ring_ent[tag];
@@ -173,6 +203,200 @@ int fuse_uring_conn_cfg(struct file *file, void __user *argp)
 	return res;
 }
 
+/*
+ * Checks for errors and stores it into the request
+ */
+static int fuse_uring_out_header_has_err(struct fuse_out_header *oh,
+					 struct fuse_req *req,
+					 struct fuse_conn *fc)
+{
+	int err;
+
+	if (oh->unique == 0) {
+		/* Not supportd through request based uring, this needs another
+		 * ring from user space to kernel
+		 */
+		pr_warn("Unsupported fuse-notify\n");
+		err = -EINVAL;
+		goto seterr;
+	}
+
+	if (oh->error <= -512 || oh->error > 0) {
+		err = -EINVAL;
+		goto seterr;
+	}
+
+	if (oh->error) {
+		err = oh->error;
+		pr_devel("%s:%d err=%d op=%d req-ret=%d", __func__, __LINE__,
+			 err, req->args->opcode, req->out.h.error);
+		goto err; /* error already set */
+	}
+
+	if ((oh->unique & ~FUSE_INT_REQ_BIT) != req->in.h.unique) {
+		pr_warn("Unpexted seqno mismatch, expected: %llu got %llu\n",
+			req->in.h.unique, oh->unique & ~FUSE_INT_REQ_BIT);
+		err = -ENOENT;
+		goto seterr;
+	}
+
+	/* Is it an interrupt reply ID?	 */
+	if (oh->unique & FUSE_INT_REQ_BIT) {
+		err = 0;
+		if (oh->error == -ENOSYS)
+			fc->no_interrupt = 1;
+		else if (oh->error == -EAGAIN) {
+			/* XXX Interrupts not handled yet */
+			/* err = queue_interrupt(req); */
+			pr_warn("Intrerupt EAGAIN not supported yet");
+			err = -EINVAL;
+		}
+
+		goto seterr;
+	}
+
+	return 0;
+
+seterr:
+	pr_devel("%s:%d err=%d op=%d req-ret=%d", __func__, __LINE__, err,
+		 req->args->opcode, req->out.h.error);
+	oh->error = err;
+err:
+	pr_devel("%s:%d err=%d op=%d req-ret=%d", __func__, __LINE__, err,
+		 req->args->opcode, req->out.h.error);
+	return err;
+}
+
+static int fuse_uring_copy_from_ring(struct fuse_ring *ring,
+				     struct fuse_req *req,
+				     struct fuse_ring_ent *ent)
+{
+	struct fuse_ring_req __user *rreq = ent->rreq;
+	struct fuse_copy_state cs;
+	struct fuse_args *args = req->args;
+	struct iov_iter iter;
+	int err;
+	int res_arg_len;
+
+	err = copy_from_user(&res_arg_len, &rreq->in_out_arg_len,
+			     sizeof(res_arg_len));
+	if (err)
+		return err;
+
+	err = import_ubuf(ITER_SOURCE, (void __user *)&rreq->in_out_arg,
+			  ent->max_arg_len, &iter);
+	if (err)
+		return err;
+
+	fuse_copy_init(&cs, 0, &iter);
+	cs.is_uring = 1;
+	cs.req = req;
+
+	return fuse_copy_out_args(&cs, args, res_arg_len);
+}
+
+ /*
+  * Copy data from the req to the ring buffer
+  */
+static int fuse_uring_copy_to_ring(struct fuse_ring *ring, struct fuse_req *req,
+				   struct fuse_ring_ent *ent)
+{
+	struct fuse_ring_req __user *rreq = ent->rreq;
+	struct fuse_copy_state cs;
+	struct fuse_args *args = req->args;
+	int err, res;
+	struct iov_iter iter;
+
+	err = import_ubuf(ITER_DEST, (void __user *)&rreq->in_out_arg,
+			  ent->max_arg_len, &iter);
+	if (err) {
+		pr_info("Import user buffer failed\n");
+		return err;
+	}
+
+	fuse_copy_init(&cs, 1, &iter);
+	cs.is_uring = 1;
+	cs.req = req;
+	err = fuse_copy_args(&cs, args->in_numargs, args->in_pages,
+			     (struct fuse_arg *)args->in_args, 0);
+	if (err) {
+		pr_info("%s fuse_copy_args failed\n", __func__);
+		return err;
+	}
+
+	BUILD_BUG_ON((sizeof(rreq->in_out_arg_len) != sizeof(cs.ring.offset)));
+	res = copy_to_user(&rreq->in_out_arg_len, &cs.ring.offset,
+			   sizeof(rreq->in_out_arg_len));
+	err = res > 0 ? -EFAULT : res;
+
+	return err;
+}
+
+static int
+fuse_uring_prepare_send(struct fuse_ring_ent *ring_ent)
+{
+	struct fuse_ring_req *rreq = ring_ent->rreq;
+	struct fuse_ring_queue *queue = ring_ent->queue;
+	struct fuse_ring *ring = queue->ring;
+	struct fuse_req *req = ring_ent->fuse_req;
+	int err = 0, res;
+
+	if (WARN_ON(ring_ent->state != FRRS_FUSE_REQ)) {
+		pr_err("qid=%d tag=%d ring-req=%p buf_req=%p invalid state %d on send\n",
+		       queue->qid, ring_ent->tag, ring_ent, rreq,
+		       ring_ent->state);
+		err = -EIO;
+	}
+
+	if (err)
+		return err;
+
+	pr_devel("%s qid=%d tag=%d state=%d cmd-done op=%d unique=%llu\n",
+		 __func__, queue->qid, ring_ent->tag, ring_ent->state,
+		 req->in.h.opcode, req->in.h.unique);
+
+	/* copy the request */
+	err = fuse_uring_copy_to_ring(ring, req, ring_ent);
+	if (unlikely(err)) {
+		pr_info("Copy to ring failed: %d\n", err);
+		goto err;
+	}
+
+	/* copy fuse_in_header */
+	res = copy_to_user(&rreq->in, &req->in.h, sizeof(rreq->in));
+	err = res > 0 ? -EFAULT : res;
+	if (err)
+		goto err;
+
+	set_bit(FR_SENT, &req->flags);
+	return 0;
+
+err:
+	fuse_uring_req_end(ring_ent, true, err);
+	return err;
+}
+
+/*
+ * Write data to the ring buffer and send the request to userspace,
+ * userspace will read it
+ * This is comparable with classical read(/dev/fuse)
+ */
+static int fuse_uring_send_next_to_ring(struct fuse_ring_ent *ring_ent)
+{
+	int err = 0;
+
+	err = fuse_uring_prepare_send(ring_ent);
+	if (err)
+		goto err;
+
+	io_uring_cmd_complete_in_task(ring_ent->cmd,
+				      fuse_uring_async_send_to_ring);
+	return 0;
+
+err:
+	return err;
+}
+
 /*
  * Put a ring request onto hold, it is no longer used for now.
  */
@@ -206,6 +430,166 @@ static void fuse_uring_ent_avail(struct fuse_ring_ent *ring_ent,
 	ring_ent->state = FRRS_WAIT;
 }
 
+/*
+ * Assign a fuse queue entry to the given entry
+ */
+static void fuse_uring_add_req_to_ring_ent(struct fuse_ring_ent *ring_ent,
+					   struct fuse_req *req)
+{
+	lockdep_assert_held(&ring_ent->queue->lock);
+
+	if (WARN_ON_ONCE(ring_ent->state != FRRS_WAIT &&
+			 ring_ent->state != FRRS_COMMIT)) {
+		pr_warn("%s qid=%d tag=%d state=%d async=%d\n", __func__,
+			ring_ent->queue->qid, ring_ent->tag, ring_ent->state,
+			ring_ent->async);
+	}
+	list_del_init(&req->list);
+	clear_bit(FR_PENDING, &req->flags);
+	ring_ent->fuse_req = req;
+	ring_ent->state = FRRS_FUSE_REQ;
+}
+
+/*
+ * Release the ring entry and fetch the next fuse request if available
+ *
+ * @return true if a new request has been fetched
+ */
+static bool fuse_uring_ent_assign_req(struct fuse_ring_ent *ring_ent)
+	__must_hold(&queue->lock)
+{
+	struct fuse_req *req = NULL;
+	struct fuse_ring_queue *queue = ring_ent->queue;
+	struct list_head *req_queue = ring_ent->async ?
+					      &queue->async_fuse_req_queue :
+					      &queue->sync_fuse_req_queue;
+
+	lockdep_assert_held(&queue->lock);
+
+	/* get and assign the next entry while it is still holding the lock */
+	if (!list_empty(req_queue)) {
+		req = list_first_entry(req_queue, struct fuse_req, list);
+		fuse_uring_add_req_to_ring_ent(ring_ent, req);
+		list_del_init(&ring_ent->list);
+	}
+
+	return req ? true : false;
+}
+
+/*
+ * Read data from the ring buffer, which user space has written to
+ * This is comparible with handling of classical write(/dev/fuse).
+ * Also make the ring request available again for new fuse requests.
+ */
+static void fuse_uring_commit(struct fuse_ring_ent *ring_ent,
+			      unsigned int issue_flags)
+{
+	struct fuse_ring *ring = ring_ent->queue->ring;
+	struct fuse_conn *fc = ring->fc;
+	struct fuse_ring_req *rreq = ring_ent->rreq;
+	struct fuse_req *req = ring_ent->fuse_req;
+	ssize_t err = 0;
+	bool set_err = false;
+
+	err = copy_from_user(&req->out.h, &rreq->out, sizeof(req->out.h));
+	if (err) {
+		req->out.h.error = err;
+		goto out;
+	}
+
+	err = fuse_uring_out_header_has_err(&req->out.h, req, fc);
+	if (err) {
+		/* req->out.h.error already set */
+		pr_devel("%s:%d err=%zd oh->err=%d\n", __func__, __LINE__, err,
+			 req->out.h.error);
+		goto out;
+	}
+
+	err = fuse_uring_copy_from_ring(ring, req, ring_ent);
+	if (err)
+		set_err = true;
+
+out:
+	pr_devel("%s:%d ret=%zd op=%d req-ret=%d\n", __func__, __LINE__, err,
+		 req->args->opcode, req->out.h.error);
+	fuse_uring_req_end(ring_ent, set_err, err);
+}
+
+/*
+ * Get the next fuse req and send it
+ */
+static void fuse_uring_next_fuse_req(struct fuse_ring_ent *ring_ent,
+				    struct fuse_ring_queue *queue)
+{
+	int has_next, err;
+	int prev_state = ring_ent->state;
+
+	WARN_ON_ONCE(!list_empty(&ring_ent->list));
+
+	do {
+		spin_lock(&queue->lock);
+		has_next = fuse_uring_ent_assign_req(ring_ent);
+		if (!has_next) {
+			fuse_uring_ent_avail(ring_ent, queue);
+			spin_unlock(&queue->lock);
+			break; /* no request left */
+		}
+		spin_unlock(&queue->lock);
+
+		err = fuse_uring_send_next_to_ring(ring_ent);
+		if (err) {
+			ring_ent->state = prev_state;
+			continue;
+		}
+
+		err = 0;
+		spin_lock(&queue->lock);
+		ring_ent->state = FRRS_USERSPACE;
+		list_add(&ring_ent->list, &queue->ent_in_userspace);
+		spin_unlock(&queue->lock);
+	} while (err);
+}
+
+/* FUSE_URING_REQ_COMMIT_AND_FETCH handler */
+static int fuse_uring_commit_fetch(struct fuse_ring_ent *ring_ent,
+				   struct io_uring_cmd *cmd, int issue_flags)
+__releases(ring_ent->queue->lock)
+{
+	int err;
+	struct fuse_ring_queue *queue = ring_ent->queue;
+	struct fuse_ring *ring = queue->ring;
+
+	err = -ENOTCONN;
+	if (unlikely(!ring->ready)) {
+		pr_info("commit and fetch, but fuse-uring is not ready.");
+		return err;
+	}
+
+	err = -EALREADY;
+	if (ring_ent->state != FRRS_USERSPACE) {
+		pr_info("qid=%d tag=%d state %d SQE already handled\n",
+			queue->qid, ring_ent->tag, ring_ent->state);
+		return err;
+	}
+
+	fuse_ring_ring_ent_unset_userspace(ring_ent);
+
+	ring_ent->cmd = cmd;
+	spin_unlock(&queue->lock);
+
+	/* without the queue lock, as other locks are taken */
+	fuse_uring_commit(ring_ent, issue_flags);
+
+	/*
+	 * Fetching the next request is absolutely required as queued
+	 * fuse requests would otherwise not get processed - committing
+	 * and fetching is done in one step vs legacy fuse, which has separated
+	 * read (fetch request) and write (commit result).
+	 */
+	fuse_uring_next_fuse_req(ring_ent, queue);
+	return 0;
+}
+
 /*
  * fuse_uring_req_fetch command handling
  */
@@ -250,6 +634,7 @@ __must_hold(ring_ent->queue->lock)
 	return 0;
 }
 
+/* FUSE_URING_REQ_FETCH handler */
 static int fuse_uring_fetch(struct fuse_ring_ent *ring_ent,
 			    struct io_uring_cmd *cmd, unsigned int issue_flags)
 	__releases(ring_ent->queue->lock)
@@ -339,10 +724,32 @@ int fuse_uring_cmd(struct io_uring_cmd *cmd, unsigned int issue_flags)
 	if (unlikely(fc->aborted || queue->stopped))
 		goto err_unlock;
 
+	ring_ent->rreq = (void __user *)cmd_req->buf_ptr;
+	ring_ent->max_arg_len = cmd_req->buf_len -
+				offsetof(struct fuse_ring_req, in_out_arg);
+	ret = -EINVAL;
+	if (cmd_req->buf_len < ring->req_buf_sz) {
+		pr_info("Invalid req buf len, expected: %zd got %d\n",
+			ring->req_buf_sz, cmd_req->buf_len);
+		goto err_unlock;
+	}
+
+	ring_ent->rreq = (void __user *)cmd_req->buf_ptr;
+	ring_ent->max_arg_len = cmd_req->buf_len -
+				offsetof(struct fuse_ring_req, in_out_arg);
+	if (cmd_req->buf_len < ring->req_buf_sz) {
+		pr_info("Invalid req buf len, expected: %zd got %d\n",
+			ring->req_buf_sz, cmd_req->buf_len);
+		goto err_unlock;
+	}
+
 	switch (cmd_op) {
 	case FUSE_URING_REQ_FETCH:
 		ret = fuse_uring_fetch(ring_ent, cmd, issue_flags);
 		break;
+	case FUSE_URING_REQ_COMMIT_AND_FETCH:
+		ret = fuse_uring_commit_fetch(ring_ent, cmd, issue_flags);
+		break;
 	default:
 		ret = -EINVAL;
 		pr_devel("Unknown uring command %d", cmd_op);
diff --git a/fs/fuse/dev_uring_i.h b/fs/fuse/dev_uring_i.h
index 6561f4178cac..697963e5d524 100644
--- a/fs/fuse/dev_uring_i.h
+++ b/fs/fuse/dev_uring_i.h
@@ -26,6 +26,9 @@ enum fuse_ring_req_state {
 	/* The ring request waits for a new fuse request */
 	FRRS_WAIT,
 
+	/* The ring req got assigned a fuse req */
+	FRRS_FUSE_REQ,
+
 	/* request is in or on the way to user space */
 	FRRS_USERSPACE,
 };
@@ -47,6 +50,17 @@ struct fuse_ring_ent {
 	struct list_head list;
 
 	struct io_uring_cmd *cmd;
+
+	/* fuse_req assigned to the ring entry */
+	struct fuse_req *fuse_req;
+
+	/*
+	 * buffer provided by fuse server
+	 */
+	struct fuse_ring_req __user *rreq;
+
+	/* struct fuse_ring_req::in_out_arg size*/
+	size_t max_arg_len;
 };
 
 struct fuse_ring_queue {
@@ -69,6 +83,13 @@ struct fuse_ring_queue {
 	struct list_head async_ent_avail_queue;
 	struct list_head sync_ent_avail_queue;
 
+	/* fuse fg/bg request types */
+	struct list_head async_fuse_req_queue;
+	struct list_head sync_fuse_req_queue;
+
+	/* entries sent to userspace */
+	struct list_head ent_in_userspace;
+
 	/*
 	 * available number of sync requests,
 	 * loosely bound to fuse foreground requests

-- 
2.43.0