diff mbox series

[net-next,v5,3/4] sock: add MSG_ZEROCOPY notification mechanism based on msg_control

Message ID 20240613233133.2463193-4-zijianzhang@bytedance.com (mailing list archive)
State Superseded
Delegated to: Netdev Maintainers
Headers show
Series net: A lightweight zero-copy notification | expand

Checks

Context Check Description
netdev/series_format success Posting correctly formatted
netdev/tree_selection success Clearly marked for net-next, async
netdev/ynl success Generated files up to date; no warnings/errors; no diff in generated;
netdev/fixes_present success Fixes tag not required for -next series
netdev/header_inline success No static functions without inline keyword in header files
netdev/build_32bit success Errors and warnings before: 6245 this patch: 6245
netdev/build_tools success Errors and warnings before: 0 this patch: 0
netdev/cc_maintainers warning 16 maintainers not CCed: James.Bottomley@HansenPartnership.com linux-alpha@vger.kernel.org deller@gmx.de mattst88@gmail.com richard.henderson@linaro.org kuba@kernel.org ink@jurassic.park.msu.ru arnd@arndb.de pabeni@redhat.com dsahern@kernel.org linux-arch@vger.kernel.org sparclinux@vger.kernel.org andreas@gaisler.com tsbogend@alpha.franken.de linux-parisc@vger.kernel.org linux-mips@vger.kernel.org
netdev/build_clang success Errors and warnings before: 2002 this patch: 2002
netdev/verify_signedoff success Signed-off-by tag matches author and committer
netdev/deprecated_api success None detected
netdev/check_selftest success No net selftest shell script
netdev/verify_fixes success No Fixes tag
netdev/build_allmodconfig_warn success Errors and warnings before: 16144 this patch: 16144
netdev/checkpatch warning WARNING: line length of 94 exceeds 80 columns WARNING: line length of 95 exceeds 80 columns
netdev/build_clang_rust success No Rust files in patch. Skipping build
netdev/kdoc success Errors and warnings before: 13 this patch: 13
netdev/source_inline success Was 0 now: 0
netdev/contest success net-next-2024-06-16--18-00 (tests: 659)

Commit Message

Zijian Zhang June 13, 2024, 11:31 p.m. UTC 
From: Zijian Zhang <zijianzhang@bytedance.com>

The MSG_ZEROCOPY flag enables copy avoidance for socket send calls.
However, zerocopy is not a free lunch. Apart from the management of user
pages, the combination of poll + recvmsg to receive notifications incurs
unignorable overhead in the applications. The overhead of such sometimes
might be more than the CPU savings from zerocopy. We try to solve this
problem with a new notification mechanism based on msgcontrol.

This new mechanism aims to reduce the overhead associated with receiving
notifications by embedding them directly into user arguments passed with
each sendmsg control message. By doing so, we can significantly reduce
the complexity and overhead for managing notifications. In an ideal
pattern, the user will keep calling sendmsg with SCM_ZC_NOTIFICATION
msg_control, and the notification will be delivered as soon as possible.

Signed-off-by: Zijian Zhang <zijianzhang@bytedance.com>
Signed-off-by: Xiaochun Lu <xiaochun.lu@bytedance.com>
---
 arch/alpha/include/uapi/asm/socket.h  |  2 +
 arch/mips/include/uapi/asm/socket.h   |  2 +
 arch/parisc/include/uapi/asm/socket.h |  2 +
 arch/sparc/include/uapi/asm/socket.h  |  2 +
 include/net/sock.h                    |  2 +-
 include/uapi/asm-generic/socket.h     |  2 +
 include/uapi/linux/socket.h           | 10 +++++
 net/core/sock.c                       | 63 ++++++++++++++++++++++++++-
 net/ipv4/ip_sockglue.c                |  2 +-
 net/ipv6/datagram.c                   |  2 +-
 10 files changed, 84 insertions(+), 5 deletions(-)
diff mbox series

Patch

diff --git a/arch/alpha/include/uapi/asm/socket.h b/arch/alpha/include/uapi/asm/socket.h
index e94f621903fe..7761a4e0ea2c 100644
--- a/arch/alpha/include/uapi/asm/socket.h
+++ b/arch/alpha/include/uapi/asm/socket.h
@@ -140,6 +140,8 @@ 
 #define SO_PASSPIDFD		76
 #define SO_PEERPIDFD		77
 
+#define SCM_ZC_NOTIFICATION 78
+
 #if !defined(__KERNEL__)
 
 #if __BITS_PER_LONG == 64
diff --git a/arch/mips/include/uapi/asm/socket.h b/arch/mips/include/uapi/asm/socket.h
index 60ebaed28a4c..89edc51380f0 100644
--- a/arch/mips/include/uapi/asm/socket.h
+++ b/arch/mips/include/uapi/asm/socket.h
@@ -151,6 +151,8 @@ 
 #define SO_PASSPIDFD		76
 #define SO_PEERPIDFD		77
 
+#define SCM_ZC_NOTIFICATION 78
+
 #if !defined(__KERNEL__)
 
 #if __BITS_PER_LONG == 64
diff --git a/arch/parisc/include/uapi/asm/socket.h b/arch/parisc/include/uapi/asm/socket.h
index be264c2b1a11..2911b43e6a9d 100644
--- a/arch/parisc/include/uapi/asm/socket.h
+++ b/arch/parisc/include/uapi/asm/socket.h
@@ -132,6 +132,8 @@ 
 #define SO_PASSPIDFD		0x404A
 #define SO_PEERPIDFD		0x404B
 
+#define SCM_ZC_NOTIFICATION 0x404C
+
 #if !defined(__KERNEL__)
 
 #if __BITS_PER_LONG == 64
diff --git a/arch/sparc/include/uapi/asm/socket.h b/arch/sparc/include/uapi/asm/socket.h
index 682da3714686..dc045e87cc8e 100644
--- a/arch/sparc/include/uapi/asm/socket.h
+++ b/arch/sparc/include/uapi/asm/socket.h
@@ -133,6 +133,8 @@ 
 #define SO_PASSPIDFD             0x0055
 #define SO_PEERPIDFD             0x0056
 
+#define SCM_ZC_NOTIFICATION 0x0057
+
 #if !defined(__KERNEL__)
 
 
diff --git a/include/net/sock.h b/include/net/sock.h
index b30ea0c342a6..f31c67d15c35 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -1799,7 +1799,7 @@  static inline void sockcm_init(struct sockcm_cookie *sockc,
 	};
 }
 
-int __sock_cmsg_send(struct sock *sk, struct cmsghdr *cmsg,
+int __sock_cmsg_send(struct sock *sk, struct msghdr *msg, struct cmsghdr *cmsg,
 		     struct sockcm_cookie *sockc);
 int sock_cmsg_send(struct sock *sk, struct msghdr *msg,
 		   struct sockcm_cookie *sockc);
diff --git a/include/uapi/asm-generic/socket.h b/include/uapi/asm-generic/socket.h
index 8ce8a39a1e5f..7474c8a244bc 100644
--- a/include/uapi/asm-generic/socket.h
+++ b/include/uapi/asm-generic/socket.h
@@ -135,6 +135,8 @@ 
 #define SO_PASSPIDFD		76
 #define SO_PEERPIDFD		77
 
+#define SCM_ZC_NOTIFICATION 78
+
 #if !defined(__KERNEL__)
 
 #if __BITS_PER_LONG == 64 || (defined(__x86_64__) && defined(__ILP32__))
diff --git a/include/uapi/linux/socket.h b/include/uapi/linux/socket.h
index d3fcd3b5ec53..26bee6291c6c 100644
--- a/include/uapi/linux/socket.h
+++ b/include/uapi/linux/socket.h
@@ -2,6 +2,8 @@ 
 #ifndef _UAPI_LINUX_SOCKET_H
 #define _UAPI_LINUX_SOCKET_H
 
+#include <linux/types.h>
+
 /*
  * Desired design of maximum size and alignment (see RFC2553)
  */
@@ -35,4 +37,12 @@  struct __kernel_sockaddr_storage {
 #define SOCK_TXREHASH_DISABLED	0
 #define SOCK_TXREHASH_ENABLED	1
 
+#define SOCK_ZC_INFO_MAX 16
+
+struct zc_info_elem {
+	__u32 lo;
+	__u32 hi;
+	__u8 zerocopy;
+};
+
 #endif /* _UAPI_LINUX_SOCKET_H */
diff --git a/net/core/sock.c b/net/core/sock.c
index 69baddcfbd8c..d7d029f9aa0a 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -2826,7 +2826,7 @@  struct sk_buff *sock_alloc_send_pskb(struct sock *sk, unsigned long header_len,
 }
 EXPORT_SYMBOL(sock_alloc_send_pskb);
 
-int __sock_cmsg_send(struct sock *sk, struct cmsghdr *cmsg,
+int __sock_cmsg_send(struct sock *sk, struct msghdr *msg, struct cmsghdr *cmsg,
 		     struct sockcm_cookie *sockc)
 {
 	u32 tsflags;
@@ -2863,6 +2863,65 @@  int __sock_cmsg_send(struct sock *sk, struct cmsghdr *cmsg,
 	case SCM_RIGHTS:
 	case SCM_CREDENTIALS:
 		break;
+	case SCM_ZC_NOTIFICATION: {
+		struct zc_info_elem zc_info_kern[SOCK_ZC_INFO_MAX];
+		int cmsg_data_len, zc_info_elem_num;
+		struct sk_buff_head *q, local_q;
+		struct sock_exterr_skb *serr;
+		unsigned long flags;
+		struct sk_buff *skb;
+		int ret, sz, i = 0;
+
+		if (!sock_flag(sk, SOCK_ZEROCOPY) || sk->sk_family == PF_RDS)
+			return -EINVAL;
+
+		cmsg_data_len = cmsg->cmsg_len - sizeof(struct cmsghdr);
+		if (cmsg_data_len % sizeof(struct zc_info_elem))
+			return -EINVAL;
+
+		zc_info_elem_num = cmsg_data_len / sizeof(struct zc_info_elem);
+		if (!zc_info_elem_num || zc_info_elem_num > SOCK_ZC_INFO_MAX)
+			return -EINVAL;
+
+		q = &sk->sk_error_queue;
+		skb_queue_head_init(&local_q);
+		spin_lock_irqsave(&q->lock, flags);
+		skb = skb_peek(q);
+		while (skb && i < zc_info_elem_num) {
+			struct sk_buff *skb_next = skb_peek_next(skb, q);
+
+			serr = SKB_EXT_ERR(skb);
+			if (serr->ee.ee_errno == 0 &&
+			    serr->ee.ee_origin == SO_EE_ORIGIN_ZEROCOPY) {
+				zc_info_kern[i].hi = serr->ee.ee_data;
+				zc_info_kern[i].lo = serr->ee.ee_info;
+				zc_info_kern[i].zerocopy = !(serr->ee.ee_code
+								& SO_EE_CODE_ZEROCOPY_COPIED);
+				__skb_unlink(skb, q);
+				__skb_queue_tail(&local_q, skb);
+				i++;
+			}
+			skb = skb_next;
+		}
+		spin_unlock_irqrestore(&q->lock, flags);
+
+		if (i == 0)
+			break;
+
+		sz = i * sizeof(struct zc_info_elem);
+		ret = put_cmsg_user_tx(msg, SOL_SOCKET, SCM_ZC_NOTIFICATION, sz, zc_info_kern);
+
+		if (unlikely(ret)) {
+			spin_lock_irqsave(&q->lock, flags);
+			skb_queue_splice_init(&local_q, q);
+			spin_unlock_irqrestore(&q->lock, flags);
+			return -ret;
+		}
+
+		while ((skb = __skb_dequeue(&local_q)))
+			consume_skb(skb);
+		break;
+	}
 	default:
 		return -EINVAL;
 	}
@@ -2881,7 +2940,7 @@  int sock_cmsg_send(struct sock *sk, struct msghdr *msg,
 			return -EINVAL;
 		if (cmsg->cmsg_level != SOL_SOCKET)
 			continue;
-		ret = __sock_cmsg_send(sk, cmsg, sockc);
+		ret = __sock_cmsg_send(sk, msg, cmsg, sockc);
 		if (ret)
 			return ret;
 	}
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index cf377377b52d..6360b8ba9c84 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -267,7 +267,7 @@  int ip_cmsg_send(struct sock *sk, struct msghdr *msg, struct ipcm_cookie *ipc,
 		}
 #endif
 		if (cmsg->cmsg_level == SOL_SOCKET) {
-			err = __sock_cmsg_send(sk, cmsg, &ipc->sockc);
+			err = __sock_cmsg_send(sk, msg, cmsg, &ipc->sockc);
 			if (err)
 				return err;
 			continue;
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index fff78496803d..c9ae30acf895 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -777,7 +777,7 @@  int ip6_datagram_send_ctl(struct net *net, struct sock *sk,
 		}
 
 		if (cmsg->cmsg_level == SOL_SOCKET) {
-			err = __sock_cmsg_send(sk, cmsg, &ipc6->sockc);
+			err = __sock_cmsg_send(sk, msg, cmsg, &ipc6->sockc);
 			if (err)
 				return err;
 			continue;