netdev - [PATCH net-next 2/2] io_uring: ignore POLLIN for recvmsg on MSG

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date:   Thu, 20 Aug 2020 16:49:54 -0700
From:   Luke Hsiao <luke.w.hsiao@...il.com>
To:     David Miller <davem@...emloft.net>
Cc:     netdev@...r.kernel.org, Jens Axboe <axboe@...nel.dk>,
        Luke Hsiao <lukehsiao@...gle.com>,
        Arjun Roy <arjunroy@...gle.com>,
        Soheil Hassas Yeganeh <soheil@...gle.com>,
        Eric Dumazet <edumazet@...gle.com>
Subject: [PATCH net-next 2/2] io_uring: ignore POLLIN for recvmsg on MSG_ERRQUEUE

From: Luke Hsiao <lukehsiao@...gle.com>

Currently, io_uring's recvmsg subscribes to both POLLERR and POLLIN. In
the context of TCP tx zero-copy, this is inefficient since we are only
reading the error queue and not using recvmsg to read POLLIN responses.

This patch was tested by using a simple sending program to call recvmsg
using io_uring with MSG_ERRQUEUE set and verifying with printks that the
POLLIN is correctly unset when the msg flags are MSG_ERRQUEUE.

Signed-off-by: Arjun Roy <arjunroy@...gle.com>
Signed-off-by: Soheil Hassas Yeganeh <soheil@...gle.com>
Acked-by: Eric Dumazet <edumazet@...gle.com>
Signed-off-by: Luke Hsiao <lukehsiao@...gle.com>
---
 fs/io_uring.c | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

diff --git a/fs/io_uring.c b/fs/io_uring.c
index dc506b75659c..664ce8739615 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -79,6 +79,7 @@
 #include <linux/splice.h>
 #include <linux/task_work.h>
 #include <linux/pagemap.h>
+#include <linux/socket.h>
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/io_uring.h>
@@ -4902,7 +4903,8 @@ static __poll_t __io_arm_poll_handler(struct io_kiocb *req,
 	return mask;
 }
 
-static bool io_arm_poll_handler(struct io_kiocb *req)
+static bool io_arm_poll_handler(struct io_kiocb *req,
+				const struct io_uring_sqe *sqe)
 {
 	const struct io_op_def *def = &io_op_defs[req->opcode];
 	struct io_ring_ctx *ctx = req->ctx;
@@ -4932,6 +4934,11 @@ static bool io_arm_poll_handler(struct io_kiocb *req)
 		mask |= POLLIN | POLLRDNORM;
 	if (def->pollout)
 		mask |= POLLOUT | POLLWRNORM;
+
+	/* If reading from MSG_ERRQUEUE using recvmsg, ignore POLLIN */
+	if (req->opcode == IORING_OP_RECVMSG && (sqe->msg_flags & MSG_ERRQUEUE))
+		mask &= ~(POLLIN);
+
 	mask |= POLLERR | POLLPRI;
 
 	ipt.pt._qproc = io_async_queue_proc;
@@ -6146,7 +6153,7 @@ static void __io_queue_sqe(struct io_kiocb *req, const struct io_uring_sqe *sqe,
 	 * doesn't support non-blocking read/write attempts
 	 */
 	if (ret == -EAGAIN && !(req->flags & REQ_F_NOWAIT)) {
-		if (!io_arm_poll_handler(req)) {
+		if (!io_arm_poll_handler(req, sqe)) {
 punt:
 			ret = io_prep_work_files(req);
 			if (unlikely(ret))
-- 
2.28.0.297.g1956fa8f8d-goog