diff options
author | Arnaldo Carvalho de Melo <acme@redhat.com> | 2009-10-12 23:40:10 -0700 |
---|---|---|
committer | David S. Miller <davem@davemloft.net> | 2009-10-12 23:40:10 -0700 |
commit | a2e2725541fad72416326798c2d7fa4dafb7d337 (patch) | |
tree | 6174be11da607e83eb8efb3775114ad4d6e0ca3a /include/linux | |
parent | c05e85a06e376f6b6d59e71e5333d707e956d78b (diff) | |
download | op-kernel-dev-a2e2725541fad72416326798c2d7fa4dafb7d337.zip op-kernel-dev-a2e2725541fad72416326798c2d7fa4dafb7d337.tar.gz |
net: Introduce recvmmsg socket syscall
Meaning receive multiple messages, reducing the number of syscalls and
net stack entry/exit operations.
Next patches will introduce mechanisms where protocols that want to
optimize this operation will provide an unlocked_recvmsg operation.
This takes into account comments made by:
. Paul Moore: sock_recvmsg is called only for the first datagram,
sock_recvmsg_nosec is used for the rest.
. Caitlin Bestler: recvmmsg now has a struct timespec timeout, that
works in the same fashion as the ppoll one.
If the underlying protocol returns a datagram with MSG_OOB set, this
will make recvmmsg return right away with as many datagrams (+ the OOB
one) it has received so far.
. RĂ©mi Denis-Courmont & Steven Whitehouse: If we receive N < vlen
datagrams and then recvmsg returns an error, recvmmsg will return
the successfully received datagrams, store the error and return it
in the next call.
This paves the way for a subsequent optimization, sk_prot->unlocked_recvmsg,
where we will be able to acquire the lock only at batch start and end, not at
every underlying recvmsg call.
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'include/linux')
-rw-r--r-- | include/linux/net.h | 1 | ||||
-rw-r--r-- | include/linux/socket.h | 10 | ||||
-rw-r--r-- | include/linux/syscalls.h | 4 |
3 files changed, 15 insertions, 0 deletions
diff --git a/include/linux/net.h b/include/linux/net.h index 529a093..b42bb60 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -41,6 +41,7 @@ #define SYS_SENDMSG 16 /* sys_sendmsg(2) */ #define SYS_RECVMSG 17 /* sys_recvmsg(2) */ #define SYS_ACCEPT4 18 /* sys_accept4(2) */ +#define SYS_RECVMMSG 19 /* sys_recvmmsg(2) */ typedef enum { SS_FREE = 0, /* not allocated */ diff --git a/include/linux/socket.h b/include/linux/socket.h index 3273a0c..59966f1 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -65,6 +65,12 @@ struct msghdr { unsigned msg_flags; }; +/* For recvmmsg/sendmmsg */ +struct mmsghdr { + struct msghdr msg_hdr; + unsigned msg_len; +}; + /* * POSIX 1003.1g - ancillary data object information * Ancillary data consits of a sequence of pairs of @@ -312,6 +318,10 @@ extern int move_addr_to_user(struct sockaddr *kaddr, int klen, void __user *uadd extern int move_addr_to_kernel(void __user *uaddr, int ulen, struct sockaddr *kaddr); extern int put_cmsg(struct msghdr*, int level, int type, int len, void *data); +struct timespec; + +extern int __sys_recvmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen, + unsigned int flags, struct timespec *timeout); #endif #endif /* not kernel and not glibc */ #endif /* _LINUX_SOCKET_H */ diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index a990ace..714f063 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -25,6 +25,7 @@ struct linux_dirent64; struct list_head; struct msgbuf; struct msghdr; +struct mmsghdr; struct msqid_ds; struct new_utsname; struct nfsctl_arg; @@ -677,6 +678,9 @@ asmlinkage long sys_recv(int, void __user *, size_t, unsigned); asmlinkage long sys_recvfrom(int, void __user *, size_t, unsigned, struct sockaddr __user *, int __user *); asmlinkage long sys_recvmsg(int fd, struct msghdr __user *msg, unsigned flags); +asmlinkage long sys_recvmmsg(int fd, struct mmsghdr __user *msg, + unsigned int vlen, unsigned flags, + struct timespec __user *timeout); asmlinkage long sys_socket(int, int, int); asmlinkage long sys_socketpair(int, int, int, int __user *); asmlinkage long sys_socketcall(int call, unsigned long __user *args); |