summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorDavid S. Miller <davem@davemloft.net>2019-07-03 13:51:54 -0700
committerDavid S. Miller <davem@davemloft.net>2019-07-03 13:51:54 -0700
commite227701c4583f0408cac33eca0fa96ac4b8ff7d9 (patch)
tree6e69af0ce25e7e72a67b17d98fc57015c93fa127
parent2559d7c4dd0eb17e6454fc7f52f9c5ea63a272df (diff)
parent6f24080e8a1e5572045067507c7905cbe6bc64cc (diff)
downloadlinux-e227701c4583f0408cac33eca0fa96ac4b8ff7d9.tar.bz2
Merge branch 'net-ICW-sendmsg-recvmsg'
Paolo Abeni says: ==================== net: use ICW for sk_proto->{send,recv}msg This series extends ICW usage to one of the few remaining spots in fast-path still hitting per packet retpoline overhead, namely the sk_proto->{send,recv}msg calls. The first 3 patches in this series refactor the existing code so that applying the ICW macros is straight-forward: we demux inet_{recv,send}msg in ipv4 and ipv6 variants so that each of them can easily select the appropriate TCP or UDP direct call. While at it, a new helper is created to avoid excessive code duplication, and the current ICWs for inet_{recv,send}msg are adjusted accordingly. The last 2 patches really introduce the new ICW use-case, respectively for the ipv6 and the ipv4 code path. This gives up to 5% performance improvement under UDP flood, and smaller but measurable gains for TCP RR workloads. v1 -> v2: - drop inet6_{recv,send}msg declaration from header file, prefer ICW macro instead - avoid unneeded reclaration for udp_sendmsg, as suggested by Willem ==================== Acked-by: Willem de Bruijn <willemb@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
-rw-r--r--include/net/inet_common.h1
-rw-r--r--net/ipv4/af_inet.c31
-rw-r--r--net/ipv6/af_inet6.c41
-rw-r--r--net/socket.c23
4 files changed, 69 insertions, 27 deletions
diff --git a/include/net/inet_common.h b/include/net/inet_common.h
index 975901a95c0f..ae2ba897675c 100644
--- a/include/net/inet_common.h
+++ b/include/net/inet_common.h
@@ -25,6 +25,7 @@ int inet_dgram_connect(struct socket *sock, struct sockaddr *uaddr,
int addr_len, int flags);
int inet_accept(struct socket *sock, struct socket *newsock, int flags,
bool kern);
+int inet_send_prepare(struct sock *sk);
int inet_sendmsg(struct socket *sock, struct msghdr *msg, size_t size);
ssize_t inet_sendpage(struct socket *sock, struct page *page, int offset,
size_t size, int flags);
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 52bdb881a506..ed2301ef872e 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -784,10 +784,8 @@ int inet_getname(struct socket *sock, struct sockaddr *uaddr,
}
EXPORT_SYMBOL(inet_getname);
-int inet_sendmsg(struct socket *sock, struct msghdr *msg, size_t size)
+int inet_send_prepare(struct sock *sk)
{
- struct sock *sk = sock->sk;
-
sock_rps_record_flow(sk);
/* We may need to bind the socket. */
@@ -795,7 +793,19 @@ int inet_sendmsg(struct socket *sock, struct msghdr *msg, size_t size)
inet_autobind(sk))
return -EAGAIN;
- return sk->sk_prot->sendmsg(sk, msg, size);
+ return 0;
+}
+EXPORT_SYMBOL_GPL(inet_send_prepare);
+
+int inet_sendmsg(struct socket *sock, struct msghdr *msg, size_t size)
+{
+ struct sock *sk = sock->sk;
+
+ if (unlikely(inet_send_prepare(sk)))
+ return -EAGAIN;
+
+ return INDIRECT_CALL_2(sk->sk_prot->sendmsg, tcp_sendmsg, udp_sendmsg,
+ sk, msg, size);
}
EXPORT_SYMBOL(inet_sendmsg);
@@ -804,11 +814,7 @@ ssize_t inet_sendpage(struct socket *sock, struct page *page, int offset,
{
struct sock *sk = sock->sk;
- sock_rps_record_flow(sk);
-
- /* We may need to bind the socket. */
- if (!inet_sk(sk)->inet_num && !sk->sk_prot->no_autobind &&
- inet_autobind(sk))
+ if (unlikely(inet_send_prepare(sk)))
return -EAGAIN;
if (sk->sk_prot->sendpage)
@@ -817,6 +823,8 @@ ssize_t inet_sendpage(struct socket *sock, struct page *page, int offset,
}
EXPORT_SYMBOL(inet_sendpage);
+INDIRECT_CALLABLE_DECLARE(int udp_recvmsg(struct sock *, struct msghdr *,
+ size_t, int, int, int *));
int inet_recvmsg(struct socket *sock, struct msghdr *msg, size_t size,
int flags)
{
@@ -827,8 +835,9 @@ int inet_recvmsg(struct socket *sock, struct msghdr *msg, size_t size,
if (likely(!(flags & MSG_ERRQUEUE)))
sock_rps_record_flow(sk);
- err = sk->sk_prot->recvmsg(sk, msg, size, flags & MSG_DONTWAIT,
- flags & ~MSG_DONTWAIT, &addr_len);
+ err = INDIRECT_CALL_2(sk->sk_prot->recvmsg, tcp_recvmsg, udp_recvmsg,
+ sk, msg, size, flags & MSG_DONTWAIT,
+ flags & ~MSG_DONTWAIT, &addr_len);
if (err >= 0)
msg->msg_namelen = addr_len;
return err;
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 8369af32cef6..ef37e0574f54 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -564,6 +564,39 @@ int inet6_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
}
EXPORT_SYMBOL(inet6_ioctl);
+INDIRECT_CALLABLE_DECLARE(int udpv6_sendmsg(struct sock *, struct msghdr *,
+ size_t));
+int inet6_sendmsg(struct socket *sock, struct msghdr *msg, size_t size)
+{
+ struct sock *sk = sock->sk;
+
+ if (unlikely(inet_send_prepare(sk)))
+ return -EAGAIN;
+
+ return INDIRECT_CALL_2(sk->sk_prot->sendmsg, tcp_sendmsg, udpv6_sendmsg,
+ sk, msg, size);
+}
+
+INDIRECT_CALLABLE_DECLARE(int udpv6_recvmsg(struct sock *, struct msghdr *,
+ size_t, int, int, int *));
+int inet6_recvmsg(struct socket *sock, struct msghdr *msg, size_t size,
+ int flags)
+{
+ struct sock *sk = sock->sk;
+ int addr_len = 0;
+ int err;
+
+ if (likely(!(flags & MSG_ERRQUEUE)))
+ sock_rps_record_flow(sk);
+
+ err = INDIRECT_CALL_2(sk->sk_prot->recvmsg, tcp_recvmsg, udpv6_recvmsg,
+ sk, msg, size, flags & MSG_DONTWAIT,
+ flags & ~MSG_DONTWAIT, &addr_len);
+ if (err >= 0)
+ msg->msg_namelen = addr_len;
+ return err;
+}
+
const struct proto_ops inet6_stream_ops = {
.family = PF_INET6,
.owner = THIS_MODULE,
@@ -580,8 +613,8 @@ const struct proto_ops inet6_stream_ops = {
.shutdown = inet_shutdown, /* ok */
.setsockopt = sock_common_setsockopt, /* ok */
.getsockopt = sock_common_getsockopt, /* ok */
- .sendmsg = inet_sendmsg, /* ok */
- .recvmsg = inet_recvmsg, /* ok */
+ .sendmsg = inet6_sendmsg, /* retpoline's sake */
+ .recvmsg = inet6_recvmsg, /* retpoline's sake */
#ifdef CONFIG_MMU
.mmap = tcp_mmap,
#endif
@@ -614,8 +647,8 @@ const struct proto_ops inet6_dgram_ops = {
.shutdown = inet_shutdown, /* ok */
.setsockopt = sock_common_setsockopt, /* ok */
.getsockopt = sock_common_getsockopt, /* ok */
- .sendmsg = inet_sendmsg, /* ok */
- .recvmsg = inet_recvmsg, /* ok */
+ .sendmsg = inet6_sendmsg, /* retpoline's sake */
+ .recvmsg = inet6_recvmsg, /* retpoline's sake */
.mmap = sock_no_mmap,
.sendpage = sock_no_sendpage,
.set_peek_off = sk_set_peek_off,
diff --git a/net/socket.c b/net/socket.c
index 963df5dbdd54..a865708940f9 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -103,13 +103,6 @@
#include <net/busy_poll.h>
#include <linux/errqueue.h>
-/* proto_ops for ipv4 and ipv6 use the same {recv,send}msg function */
-#if IS_ENABLED(CONFIG_INET)
-#define INDIRECT_CALL_INET4(f, f1, ...) INDIRECT_CALL_1(f, f1, __VA_ARGS__)
-#else
-#define INDIRECT_CALL_INET4(f, f1, ...) f(__VA_ARGS__)
-#endif
-
#ifdef CONFIG_NET_RX_BUSY_POLL
unsigned int sysctl_net_busy_read __read_mostly;
unsigned int sysctl_net_busy_poll __read_mostly;
@@ -641,10 +634,13 @@ EXPORT_SYMBOL(__sock_tx_timestamp);
INDIRECT_CALLABLE_DECLARE(int inet_sendmsg(struct socket *, struct msghdr *,
size_t));
+INDIRECT_CALLABLE_DECLARE(int inet6_sendmsg(struct socket *, struct msghdr *,
+ size_t));
static inline int sock_sendmsg_nosec(struct socket *sock, struct msghdr *msg)
{
- int ret = INDIRECT_CALL_INET4(sock->ops->sendmsg, inet_sendmsg, sock,
- msg, msg_data_left(msg));
+ int ret = INDIRECT_CALL_INET(sock->ops->sendmsg, inet6_sendmsg,
+ inet_sendmsg, sock, msg,
+ msg_data_left(msg));
BUG_ON(ret == -EIOCBQUEUED);
return ret;
}
@@ -870,12 +866,15 @@ void __sock_recv_ts_and_drops(struct msghdr *msg, struct sock *sk,
EXPORT_SYMBOL_GPL(__sock_recv_ts_and_drops);
INDIRECT_CALLABLE_DECLARE(int inet_recvmsg(struct socket *, struct msghdr *,
- size_t , int ));
+ size_t, int));
+INDIRECT_CALLABLE_DECLARE(int inet6_recvmsg(struct socket *, struct msghdr *,
+ size_t, int));
static inline int sock_recvmsg_nosec(struct socket *sock, struct msghdr *msg,
int flags)
{
- return INDIRECT_CALL_INET4(sock->ops->recvmsg, inet_recvmsg, sock, msg,
- msg_data_left(msg), flags);
+ return INDIRECT_CALL_INET(sock->ops->recvmsg, inet6_recvmsg,
+ inet_recvmsg, sock, msg, msg_data_left(msg),
+ flags);
}
/**