netdev - [PATCH net-next 4/5] io_uring/net: move charging socket out of zc io

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]

Message-ID: <1e55ad85b726d50a45bdd35fc04e1565d3ba7896.1719190216.git.asml.silence@gmail.com>
Date: Thu, 27 Jun 2024 13:59:44 +0100
From: Pavel Begunkov <asml.silence@...il.com>
To: io-uring@...r.kernel.org,
	netdev@...r.kernel.org
Cc: Jens Axboe <axboe@...nel.dk>,
	asml.silence@...il.com,
	"David S . Miller" <davem@...emloft.net>,
	Jakub Kicinski <kuba@...nel.org>,
	David Ahern <dsahern@...nel.org>,
	Eric Dumazet <edumazet@...gle.com>,
	Willem de Bruijn <willemdebruijn.kernel@...il.com>
Subject: [PATCH net-next 4/5] io_uring/net: move charging socket out of zc io_uring

Currently, io_uring's io_sg_from_iter() duplicates the part of
__zerocopy_sg_from_iter() charging pages to the socket. It'd be too easy
to miss while changing it in net/, the chunk is not the most
straightforward for outside users and full of internal implementation
details. io_uring is not a good place to keep it, deduplicate it by
moving out of the callback into __zerocopy_sg_from_iter().

Signed-off-by: Pavel Begunkov <asml.silence@...il.com>
---
 include/linux/skbuff.h |  3 +++
 include/linux/socket.h |  2 +-
 io_uring/net.c         | 16 ++++------------
 net/core/datagram.c    | 10 +++++-----
 4 files changed, 13 insertions(+), 18 deletions(-)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index f4cda3fbdb75..9c29bdd5596d 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -1703,6 +1703,9 @@ int __zerocopy_sg_from_iter(struct msghdr *msg, struct sock *sk,
 			    struct sk_buff *skb, struct iov_iter *from,
 			    size_t length);
 
+int zerocopy_fill_skb_from_iter(struct sk_buff *skb,
+				struct iov_iter *from, size_t length);
+
 static inline int skb_zerocopy_iter_dgram(struct sk_buff *skb,
 					  struct msghdr *msg, int len)
 {
diff --git a/include/linux/socket.h b/include/linux/socket.h
index 89d16b90370b..2a1ff91d1914 100644
--- a/include/linux/socket.h
+++ b/include/linux/socket.h
@@ -76,7 +76,7 @@ struct msghdr {
 	__kernel_size_t	msg_controllen;	/* ancillary data buffer length */
 	struct kiocb	*msg_iocb;	/* ptr to iocb for async requests */
 	struct ubuf_info *msg_ubuf;
-	int (*sg_from_iter)(struct sock *sk, struct sk_buff *skb,
+	int (*sg_from_iter)(struct sk_buff *skb,
 			    struct iov_iter *from, size_t length);
 };
 
diff --git a/io_uring/net.c b/io_uring/net.c
index 7c98c4d50946..84a7602bcef1 100644
--- a/io_uring/net.c
+++ b/io_uring/net.c
@@ -1265,14 +1265,14 @@ int io_send_zc_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 	return io_sendmsg_prep_setup(req, req->opcode == IORING_OP_SENDMSG_ZC);
 }
 
-static int io_sg_from_iter_iovec(struct sock *sk, struct sk_buff *skb,
+static int io_sg_from_iter_iovec(struct sk_buff *skb,
 				 struct iov_iter *from, size_t length)
 {
 	skb_zcopy_downgrade_managed(skb);
-	return __zerocopy_sg_from_iter(NULL, sk, skb, from, length);
+	return zerocopy_fill_skb_from_iter(skb, from, length);
 }
 
-static int io_sg_from_iter(struct sock *sk, struct sk_buff *skb,
+static int io_sg_from_iter(struct sk_buff *skb,
 			   struct iov_iter *from, size_t length)
 {
 	struct skb_shared_info *shinfo = skb_shinfo(skb);
@@ -1285,7 +1285,7 @@ static int io_sg_from_iter(struct sock *sk, struct sk_buff *skb,
 	if (!frag)
 		shinfo->flags |= SKBFL_MANAGED_FRAG_REFS;
 	else if (unlikely(!skb_zcopy_managed(skb)))
-		return __zerocopy_sg_from_iter(NULL, sk, skb, from, length);
+		return zerocopy_fill_skb_from_iter(skb, from, length);
 
 	bi.bi_size = min(from->count, length);
 	bi.bi_bvec_done = from->iov_offset;
@@ -1312,14 +1312,6 @@ static int io_sg_from_iter(struct sock *sk, struct sk_buff *skb,
 	skb->data_len += copied;
 	skb->len += copied;
 	skb->truesize += truesize;
-
-	if (sk && sk->sk_type == SOCK_STREAM) {
-		sk_wmem_queued_add(sk, truesize);
-		if (!skb_zcopy_pure(skb))
-			sk_mem_charge(sk, truesize);
-	} else {
-		refcount_add(truesize, &skb->sk->sk_wmem_alloc);
-	}
 	return ret;
 }
 
diff --git a/net/core/datagram.c b/net/core/datagram.c
index 2b24d69b1e94..554316c40883 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -610,8 +610,8 @@ int skb_copy_datagram_from_iter(struct sk_buff *skb, int offset,
 }
 EXPORT_SYMBOL(skb_copy_datagram_from_iter);
 
-static int zerocopy_fill_skb_from_iter(struct sk_buff *skb,
-					struct iov_iter *from, size_t length)
+int zerocopy_fill_skb_from_iter(struct sk_buff *skb,
+				struct iov_iter *from, size_t length)
 {
 	int frag = skb_shinfo(skb)->nr_frags;
 
@@ -687,11 +687,11 @@ int __zerocopy_sg_from_iter(struct msghdr *msg, struct sock *sk,
 	int ret;
 
 	if (msg && msg->msg_ubuf && msg->sg_from_iter)
-		return msg->sg_from_iter(sk, skb, from, length);
+		ret = msg->sg_from_iter(skb, from, length);
+	else
+		ret = zerocopy_fill_skb_from_iter(skb, from, length);
 
-	ret = zerocopy_fill_skb_from_iter(skb, from, length);
 	truesize = skb->truesize - orig_size;
-
 	if (sk && sk->sk_type == SOCK_STREAM) {
 		sk_wmem_queued_add(sk, truesize);
 		if (!skb_zcopy_pure(skb))
-- 
2.44.0