public inbox for [email protected]
 help / color / mirror / Atom feed
From: Jens Axboe <[email protected]>
To: [email protected]
Cc: [email protected], Jens Axboe <[email protected]>
Subject: [PATCH 2/2] io_uring: add support for passing fixed file descriptors
Date: Fri, 17 Jun 2022 07:45:04 -0600	[thread overview]
Message-ID: <[email protected]> (raw)
In-Reply-To: <[email protected]>

With IORING_OP_MSG_RING, one ring can send a message to another ring.
Extend that support to also allow sending a fixed file descriptor to
that ring, enabling one ring to pass a registered descriptor to another
one.

Arguments are extended to pass in:

sqe->addr3	fixed file slot in source ring
sqe->file_index	fixed file slot in destination ring

IORING_OP_MSG_RING is extended to take a command argument in sqe->addr.
If set to zero (or IORING_MSG_DATA), it sends just a message like before.
If set to IORING_MSG_SEND_FD, a fixed file descriptor is sent according
to the above arguments.

Undecided:
	- Should we post a cqe with the send, or require that the sender
	  just link a separate IORING_OP_MSG_RING? This makes error
	  handling easier, as we cannot easily retract the installed
	  file descriptor if the target CQ ring is full. Right now we do
	  fill a CQE. If the request completes with -EOVERFLOW, then the
	  sender must re-send a CQE if the target must get notified.

	- Add an IORING_MSG_MOVE_FD which moves the descriptor, removing
	  it from the source ring when installed in the target? Again
	  error handling is difficult.

Signed-off-by: Jens Axboe <[email protected]>
---
 include/uapi/linux/io_uring.h |   8 +++
 io_uring/msg_ring.c           | 122 ++++++++++++++++++++++++++++++++--
 2 files changed, 123 insertions(+), 7 deletions(-)

diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index 8715f0942ec2..dbdaeef3ea89 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -264,6 +264,14 @@ enum io_uring_op {
  */
 #define IORING_ACCEPT_MULTISHOT	(1U << 0)
 
+/*
+ * IORING_OP_MSG_RING command types, stored in sqe->addr
+ */
+enum {
+	IORING_MSG_DATA,	/* pass sqe->len as 'res' and off as user_data */
+	IORING_MSG_SEND_FD,	/* send a registered fd to another ring */
+};
+
 /*
  * IO completion data structure (Completion Queue Entry)
  */
diff --git a/io_uring/msg_ring.c b/io_uring/msg_ring.c
index b02be2349652..e9d6fb25d141 100644
--- a/io_uring/msg_ring.c
+++ b/io_uring/msg_ring.c
@@ -3,46 +3,154 @@
 #include <linux/errno.h>
 #include <linux/file.h>
 #include <linux/slab.h>
+#include <linux/nospec.h>
 #include <linux/io_uring.h>
 
 #include <uapi/linux/io_uring.h>
 
 #include "io_uring.h"
+#include "rsrc.h"
+#include "filetable.h"
 #include "msg_ring.h"
 
 struct io_msg {
 	struct file			*file;
 	u64 user_data;
 	u32 len;
+	u32 cmd;
+	u32 src_fd;
+	u32 dst_fd;
 };
 
+static int io_msg_ring_data(struct io_kiocb *req)
+{
+	struct io_ring_ctx *target_ctx = req->file->private_data;
+	struct io_msg *msg = io_kiocb_to_cmd(req);
+
+	if (msg->src_fd || msg->dst_fd)
+		return -EINVAL;
+
+	if (io_post_aux_cqe(target_ctx, msg->user_data, msg->len, 0))
+		return 0;
+
+	return -EOVERFLOW;
+}
+
+static void io_double_unlock_ctx(struct io_ring_ctx *ctx,
+				 struct io_ring_ctx *octx,
+				 unsigned int issue_flags)
+{
+	if (issue_flags & IO_URING_F_UNLOCKED)
+		mutex_unlock(&ctx->uring_lock);
+	mutex_unlock(&octx->uring_lock);
+}
+
+static int io_double_lock_ctx(struct io_ring_ctx *ctx,
+			      struct io_ring_ctx *octx,
+			      unsigned int issue_flags)
+{
+	/*
+	 * To ensure proper ordering between the two ctxs, we can only
+	 * attempt a trylock on the target. If that fails and we already have
+	 * the source ctx lock, punt to io-wq.
+	 */
+	if (!(issue_flags & IO_URING_F_UNLOCKED)) {
+		if (!mutex_trylock(&octx->uring_lock))
+			return -EAGAIN;
+		return 0;
+	}
+
+	/* Always grab smallest value ctx first. */
+	if (ctx < octx) {
+		mutex_lock(&ctx->uring_lock);
+		mutex_lock(&octx->uring_lock);
+	} else if (ctx > octx) {
+		mutex_lock(&octx->uring_lock);
+		mutex_lock(&ctx->uring_lock);
+	}
+
+	return 0;
+}
+
+static int io_msg_send_fd(struct io_kiocb *req, unsigned int issue_flags)
+{
+	struct io_ring_ctx *target_ctx = req->file->private_data;
+	struct io_msg *msg = io_kiocb_to_cmd(req);
+	struct io_ring_ctx *ctx = req->ctx;
+	unsigned long file_ptr;
+	struct file *src_file;
+	int ret;
+
+	if (target_ctx == ctx)
+		return -EINVAL;
+
+	ret = io_double_lock_ctx(ctx, target_ctx, issue_flags);
+	if (unlikely(ret))
+		return ret;
+
+	ret = -EBADF;
+	if (unlikely(msg->src_fd >= ctx->nr_user_files))
+		goto err_unlock;
+
+	msg->src_fd = array_index_nospec(msg->src_fd, ctx->nr_user_files);
+	file_ptr = io_fixed_file_slot(&ctx->file_table, msg->src_fd)->file_ptr;
+	src_file = (struct file *) (file_ptr & FFS_MASK);
+	get_file(src_file);
+
+	ret = __io_fixed_fd_install(target_ctx, src_file, msg->dst_fd);
+	if (ret < 0) {
+		fput(src_file);
+		goto err_unlock;
+	}
+
+	/*
+	 * If this fails, the target still received the file descriptor but
+	 * wasn't notified of the fact. This means that if this request
+	 * completes with -EOVERFLOW, then the sender must ensure that a
+	 * later IORING_OP_MSG_RING delivers the message.
+	 */
+	if (!io_post_aux_cqe(target_ctx, msg->user_data, msg->len, 0))
+		ret = -EOVERFLOW;
+err_unlock:
+	io_double_unlock_ctx(ctx, target_ctx, issue_flags);
+	return ret;
+}
+
 int io_msg_ring_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 {
 	struct io_msg *msg = io_kiocb_to_cmd(req);
 
-	if (unlikely(sqe->addr || sqe->rw_flags || sqe->splice_fd_in ||
-		     sqe->buf_index || sqe->personality))
+	if (unlikely(sqe->rw_flags || sqe->buf_index || sqe->personality))
 		return -EINVAL;
 
 	msg->user_data = READ_ONCE(sqe->off);
 	msg->len = READ_ONCE(sqe->len);
+	msg->cmd = READ_ONCE(sqe->addr);
+	msg->src_fd = READ_ONCE(sqe->addr3);
+	msg->dst_fd = READ_ONCE(sqe->file_index);
 	return 0;
 }
 
 int io_msg_ring(struct io_kiocb *req, unsigned int issue_flags)
 {
 	struct io_msg *msg = io_kiocb_to_cmd(req);
-	struct io_ring_ctx *target_ctx;
 	int ret;
 
 	ret = -EBADFD;
 	if (!io_is_uring_fops(req->file))
 		goto done;
 
-	ret = -EOVERFLOW;
-	target_ctx = req->file->private_data;
-	if (io_post_aux_cqe(target_ctx, msg->user_data, msg->len, 0))
-		ret = 0;
+	switch (msg->cmd) {
+	case IORING_MSG_DATA:
+		ret = io_msg_ring_data(req);
+		break;
+	case IORING_MSG_SEND_FD:
+		ret = io_msg_send_fd(req, issue_flags);
+		break;
+	default:
+		ret = -EINVAL;
+		break;
+	}
 
 done:
 	if (ret < 0)
-- 
2.35.1


  parent reply	other threads:[~2022-06-17 13:45 UTC|newest]

Thread overview: 13+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-06-17 13:45 [PATCHSET RFC for-next 0/2] Add direct descriptor ring passing Jens Axboe
2022-06-17 13:45 ` [PATCH 1/2] io_uring: split out fixed file installation and removal Jens Axboe
2022-06-17 13:45 ` Jens Axboe [this message]
2022-06-18 11:02   ` [PATCH 2/2] io_uring: add support for passing fixed file descriptors Hao Xu
2022-06-18 11:34     ` Jens Axboe
2022-06-18 12:47       ` Hao Xu
2022-06-18 12:50         ` Jens Axboe
2022-06-18 13:09           ` Hao Xu
2022-06-18 13:16             ` Jens Axboe
2022-06-18 13:27               ` Hao Xu
2022-06-17 14:07 ` [PATCHSET RFC for-next 0/2] Add direct descriptor ring passing Jens Axboe
  -- strict thread matches above, loose matches on Subject: below --
2022-06-19  1:59 [PATCHSET v2 " Jens Axboe
2022-06-19  1:59 ` [PATCH 2/2] io_uring: add support for passing fixed file descriptors Jens Axboe
2022-06-22 23:16 [PATCHSET v3] Add direct descriptor ring passing Jens Axboe
2022-06-22 23:16 ` [PATCH 2/2] io_uring: add support for passing fixed file descriptors Jens Axboe

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox