public inbox for [email protected]
 help / color / mirror / Atom feed
From: Pavel Begunkov <[email protected]>
To: [email protected], [email protected],
	[email protected]
Cc: "David S . Miller" <[email protected]>,
	Jakub Kicinski <[email protected]>,
	Jonathan Lemon <[email protected]>,
	Willem de Bruijn <[email protected]>,
	Jens Axboe <[email protected]>,
	[email protected], Pavel Begunkov <[email protected]>
Subject: [RFC net-next v3 21/29] io_uring: wire send zc request type
Date: Tue, 28 Jun 2022 19:56:43 +0100	[thread overview]
Message-ID: <b8af7329752169ad0fef9e5d8d41c40327a91fa1.1653992701.git.asml.silence@gmail.com> (raw)
In-Reply-To: <[email protected]>

Add a new io_uring opcode IORING_OP_SENDZC. The main distinction from
IORING_OP_SEND is that the user should specify a notification slot
index in sqe::notification_idx and the buffers are safe to reuse only
when the used notification is flushed and completes.

Signed-off-by: Pavel Begunkov <[email protected]>
---
 fs/io_uring.c                 | 103 +++++++++++++++++++++++++++++++++-
 include/uapi/linux/io_uring.h |   5 ++
 2 files changed, 106 insertions(+), 2 deletions(-)

diff --git a/fs/io_uring.c b/fs/io_uring.c
index a88c9c73ed1d..4a1a1d43e9b3 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -716,6 +716,14 @@ struct io_sr_msg {
 	unsigned int			flags;
 };
 
+struct io_sendzc {
+	struct file			*file;
+	void __user			*buf;
+	size_t				len;
+	u16				slot_idx;
+	int				msg_flags;
+};
+
 struct io_open {
 	struct file			*file;
 	int				dfd;
@@ -1044,6 +1052,7 @@ struct io_kiocb {
 		struct io_socket	sock;
 		struct io_nop		nop;
 		struct io_uring_cmd	uring_cmd;
+		struct io_sendzc	msgzc;
 	};
 
 	u8				opcode;
@@ -1384,6 +1393,13 @@ static const struct io_op_def io_op_defs[] = {
 		.needs_async_setup	= 1,
 		.async_size		= uring_cmd_pdu_size(1),
 	},
+	[IORING_OP_SENDZC] = {
+		.needs_file		= 1,
+		.unbound_nonreg_file	= 1,
+		.pollout		= 1,
+		.audit_skip		= 1,
+		.ioprio			= 1,
+	},
 };
 
 /* requests with any of those set should undergo io_disarm_next() */
@@ -1525,6 +1541,8 @@ const char *io_uring_get_opcode(u8 opcode)
 		return "SOCKET";
 	case IORING_OP_URING_CMD:
 		return "URING_CMD";
+	case IORING_OP_SENDZC:
+		return "URING_SENDZC";
 	case IORING_OP_LAST:
 		return "INVALID";
 	}
@@ -2920,7 +2938,6 @@ static struct io_notif *io_alloc_notif(struct io_ring_ctx *ctx,
 	return notif;
 }
 
-__attribute__((unused))
 static inline struct io_notif *io_get_notif(struct io_ring_ctx *ctx,
 					    struct io_notif_slot *slot)
 {
@@ -2929,7 +2946,6 @@ static inline struct io_notif *io_get_notif(struct io_ring_ctx *ctx,
 	return slot->notif;
 }
 
-__attribute__((unused))
 static inline struct io_notif_slot *io_get_notif_slot(struct io_ring_ctx *ctx,
 						      int idx)
 	__must_hold(&ctx->uring_lock)
@@ -6546,6 +6562,83 @@ static int io_send(struct io_kiocb *req, unsigned int issue_flags)
 	return 0;
 }
 
+static int io_sendzc_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
+{
+	struct io_sendzc *zc = &req->msgzc;
+
+	if (READ_ONCE(sqe->ioprio) || READ_ONCE(sqe->addr2) || READ_ONCE(sqe->__pad2[0]))
+		return -EINVAL;
+
+	zc->buf = u64_to_user_ptr(READ_ONCE(sqe->addr));
+	zc->len = READ_ONCE(sqe->len);
+	zc->msg_flags = READ_ONCE(sqe->msg_flags) | MSG_NOSIGNAL;
+	zc->slot_idx = READ_ONCE(sqe->notification_idx);
+	if (zc->msg_flags & MSG_DONTWAIT)
+		req->flags |= REQ_F_NOWAIT;
+#ifdef CONFIG_COMPAT
+	if (req->ctx->compat)
+		zc->msg_flags |= MSG_CMSG_COMPAT;
+#endif
+	return 0;
+}
+
+static int io_sendzc(struct io_kiocb *req, unsigned int issue_flags)
+{
+	struct io_ring_ctx *ctx = req->ctx;
+	struct io_sendzc *zc = &req->msgzc;
+	struct io_notif_slot *notif_slot;
+	struct io_notif *notif;
+	struct msghdr msg;
+	struct iovec iov;
+	struct socket *sock;
+	unsigned msg_flags;
+	int ret, min_ret = 0;
+
+	if (issue_flags & IO_URING_F_UNLOCKED)
+		return -EAGAIN;
+	sock = sock_from_file(req->file);
+	if (unlikely(!sock))
+		return -ENOTSOCK;
+
+	notif_slot = io_get_notif_slot(ctx, zc->slot_idx);
+	if (!notif_slot)
+		return -EINVAL;
+	notif = io_get_notif(ctx, notif_slot);
+	if (!notif)
+		return -ENOMEM;
+
+	msg.msg_name = NULL;
+	msg.msg_control = NULL;
+	msg.msg_controllen = 0;
+	msg.msg_namelen = 0;
+	msg.msg_managed_data = 0;
+
+	ret = import_single_range(WRITE, zc->buf, zc->len, &iov, &msg.msg_iter);
+	if (unlikely(ret))
+		return ret;
+
+	msg_flags = zc->msg_flags | MSG_ZEROCOPY;
+	if (issue_flags & IO_URING_F_NONBLOCK)
+		msg_flags |= MSG_DONTWAIT;
+	if (msg_flags & MSG_WAITALL)
+		min_ret = iov_iter_count(&msg.msg_iter);
+
+	msg.msg_flags = msg_flags;
+	msg.msg_ubuf = &notif->uarg;
+	ret = sock_sendmsg(sock, &msg);
+
+	if (unlikely(ret < min_ret)) {
+		if (ret == -EAGAIN && (issue_flags & IO_URING_F_NONBLOCK))
+			return -EAGAIN;
+		if (ret == -ERESTARTSYS)
+			ret = -EINTR;
+		req_set_fail(req);
+	}
+
+	__io_req_complete(req, issue_flags, ret, 0);
+	return 0;
+}
+
 static int __io_recvmsg_copy_hdr(struct io_kiocb *req,
 				 struct io_async_msghdr *iomsg)
 {
@@ -7064,6 +7157,7 @@ IO_NETOP_PREP_ASYNC(connect);
 IO_NETOP_PREP(accept);
 IO_NETOP_PREP(socket);
 IO_NETOP_PREP(shutdown);
+IO_NETOP_PREP(sendzc);
 IO_NETOP_FN(send);
 IO_NETOP_FN(recv);
 #endif /* CONFIG_NET */
@@ -8389,6 +8483,8 @@ static int io_req_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 	case IORING_OP_SENDMSG:
 	case IORING_OP_SEND:
 		return io_sendmsg_prep(req, sqe);
+	case IORING_OP_SENDZC:
+		return io_sendzc_prep(req, sqe);
 	case IORING_OP_RECVMSG:
 	case IORING_OP_RECV:
 		return io_recvmsg_prep(req, sqe);
@@ -8689,6 +8785,9 @@ static int io_issue_sqe(struct io_kiocb *req, unsigned int issue_flags)
 	case IORING_OP_SEND:
 		ret = io_send(req, issue_flags);
 		break;
+	case IORING_OP_SENDZC:
+		ret = io_sendzc(req, issue_flags);
+		break;
 	case IORING_OP_RECVMSG:
 		ret = io_recvmsg(req, issue_flags);
 		break;
diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index 19b9d7a2da29..6c6f20ae5a95 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -61,6 +61,10 @@ struct io_uring_sqe {
 	union {
 		__s32	splice_fd_in;
 		__u32	file_index;
+		struct {
+			__u16	notification_idx;
+			__u16	__pad;
+		} __attribute__((packed));
 	};
 	union {
 		struct {
@@ -190,6 +194,7 @@ enum io_uring_op {
 	IORING_OP_GETXATTR,
 	IORING_OP_SOCKET,
 	IORING_OP_URING_CMD,
+	IORING_OP_SENDZC,
 
 	/* this goes last, obviously */
 	IORING_OP_LAST,
-- 
2.36.1


  parent reply	other threads:[~2022-06-28 19:01 UTC|newest]

Thread overview: 47+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-06-28 18:56 [RFC net-next v3 00/29] io_uring zerocopy send Pavel Begunkov
2022-06-28 18:56 ` [RFC net-next v3 01/29] ipv4: avoid partial copy for zc Pavel Begunkov
2022-06-28 18:56 ` [RFC net-next v3 02/29] ipv6: " Pavel Begunkov
2022-06-28 18:56 ` [RFC net-next v3 03/29] skbuff: add SKBFL_DONT_ORPHAN flag Pavel Begunkov
2022-06-28 18:56 ` [RFC net-next v3 04/29] skbuff: carry external ubuf_info in msghdr Pavel Begunkov
2022-06-28 18:56 ` [RFC net-next v3 05/29] net: bvec specific path in zerocopy_sg_from_iter Pavel Begunkov
2022-06-28 20:06   ` Al Viro
2022-06-28 21:33     ` Pavel Begunkov
2022-06-28 22:52   ` David Ahern
2022-07-04 13:31     ` Pavel Begunkov
2022-07-05  2:28       ` David Ahern
2022-07-05 14:03         ` Pavel Begunkov
2022-07-05 22:09           ` Pavel Begunkov
2022-07-06 15:11             ` David Ahern
2022-06-28 18:56 ` [RFC net-next v3 06/29] net: optimise bvec-based zc page referencing Pavel Begunkov
2022-06-28 18:56 ` [RFC net-next v3 07/29] net: don't track pfmemalloc for managed frags Pavel Begunkov
2022-06-28 18:56 ` [RFC net-next v3 08/29] skbuff: don't mix ubuf_info of different types Pavel Begunkov
2022-06-28 18:56 ` [RFC net-next v3 09/29] ipv4/udp: support zc with managed data Pavel Begunkov
2022-06-28 18:56 ` [RFC net-next v3 10/29] ipv6/udp: " Pavel Begunkov
2022-06-28 18:56 ` [RFC net-next v3 11/29] tcp: " Pavel Begunkov
2022-06-28 18:56 ` [RFC net-next v3 12/29] tcp: kill extra io_uring's uarg refcounting Pavel Begunkov
2022-06-28 18:56 ` [RFC net-next v3 13/29] net: let callers provide extra ubuf_info refs Pavel Begunkov
2022-06-28 18:56 ` [RFC net-next v3 14/29] io_uring: opcode independent fixed buf import Pavel Begunkov
2022-06-28 18:56 ` [RFC net-next v3 15/29] io_uring: add zc notification infrastructure Pavel Begunkov
2022-06-28 18:56 ` [RFC net-next v3 16/29] io_uring: cache struct io_notif Pavel Begunkov
2022-06-28 18:56 ` [RFC net-next v3 17/29] io_uring: complete notifiers in tw Pavel Begunkov
2022-06-28 18:56 ` [RFC net-next v3 18/29] io_uring: add notification slot registration Pavel Begunkov
2022-06-28 18:56 ` [RFC net-next v3 19/29] io_uring: rename IORING_OP_FILES_UPDATE Pavel Begunkov
2022-06-28 18:56 ` [RFC net-next v3 20/29] io_uring: add zc notification flush requests Pavel Begunkov
2022-06-28 18:56 ` Pavel Begunkov [this message]
2022-06-28 18:56 ` [RFC net-next v3 22/29] io_uring: account locked pages for non-fixed zc Pavel Begunkov
2022-06-28 18:56 ` [RFC net-next v3 23/29] io_uring: allow to pass addr into sendzc Pavel Begunkov
2022-06-29  7:42   ` Stefan Metzmacher
2022-06-29  9:53     ` Pavel Begunkov
2022-08-13  8:45       ` Stefan Metzmacher
2022-08-15  9:46         ` Pavel Begunkov
2022-08-15 11:40           ` Stefan Metzmacher
2022-08-15 12:19             ` Pavel Begunkov
2022-08-15 13:30               ` Stefan Metzmacher
2022-08-15 14:09                 ` Pavel Begunkov
2022-06-28 18:56 ` [RFC net-next v3 24/29] io_uring: add rsrc referencing for notifiers Pavel Begunkov
2022-06-28 18:56 ` [RFC net-next v3 25/29] io_uring: sendzc with fixed buffers Pavel Begunkov
2022-06-28 18:56 ` [RFC net-next v3 26/29] io_uring: flush notifiers after sendzc Pavel Begunkov
2022-06-28 18:56 ` [RFC net-next v3 27/29] io_uring: allow to override zc tag on flush Pavel Begunkov
2022-06-28 18:56 ` [RFC net-next v3 28/29] io_uring: batch submission notif referencing Pavel Begunkov
2022-06-28 18:56 ` [RFC net-next v3 29/29] selftests/io_uring: test zerocopy send Pavel Begunkov
2022-06-28 19:03 ` [RFC net-next v3 00/29] io_uring " Pavel Begunkov

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 \
    --in-reply-to=b8af7329752169ad0fef9e5d8d41c40327a91fa1.1653992701.git.asml.silence@gmail.com \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [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