sock: Introduce the SO_PEEK_OFF sock option

This one specifies where to start MSG_PEEK-ing queue data from. When
set to negative value means that MSG_PEEK works as ususally -- peeks
from the head of the queue always.

When some bytes are peeked from queue and the peeking offset is non
negative it is moved forward so that the next peek will return next
portion of data.

When non-peeking recvmsg occurs and the peeking offset is non negative
is is moved backward so that the next peek will still peek the proper
data (i.e. the one that would have been picked if there were no non
peeking recv in between).

The offset is set using per-proto opteration to let the protocol handle
the locking issues and to check whether the peeking offset feature is
supported by the protocol the socket belongs to.
Signed-off-by: NPavel Emelyanov <xemul@parallels.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

arch/alpha/include/asm/socket.h

@@ -71,6 +71,7 @@
 
 #define SO_WIFI_STATUS		41
 #define SCM_WIFI_STATUS		SO_WIFI_STATUS
+#define SO_PEEK_OFF		42
 
 /* O_NONBLOCK clashes with the bits used for socket types.  Therefore we
  * have to define SOCK_NONBLOCK to a different value here.

arch/arm/include/asm/socket.h

@@ -64,5 +64,6 @@
 
 #define SO_WIFI_STATUS		41
 #define SCM_WIFI_STATUS		SO_WIFI_STATUS
+#define SO_PEEK_OFF		42
 
 #endif /* _ASM_SOCKET_H */

arch/avr32/include/asm/socket.h

@@ -64,5 +64,6 @@
 
 #define SO_WIFI_STATUS		41
 #define SCM_WIFI_STATUS		SO_WIFI_STATUS
+#define SO_PEEK_OFF		42
 
 #endif /* __ASM_AVR32_SOCKET_H */

arch/cris/include/asm/socket.h

@@ -66,6 +66,7 @@
 
 #define SO_WIFI_STATUS		41
 #define SCM_WIFI_STATUS		SO_WIFI_STATUS
+#define SO_PEEK_OFF		42
 
 #endif /* _ASM_SOCKET_H */
 

arch/frv/include/asm/socket.h

@@ -64,6 +64,7 @@
 
 #define SO_WIFI_STATUS		41
 #define SCM_WIFI_STATUS		SO_WIFI_STATUS
+#define SO_PEEK_OFF		42
 
 #endif /* _ASM_SOCKET_H */
 

arch/h8300/include/asm/socket.h

@@ -64,5 +64,6 @@
 
 #define SO_WIFI_STATUS		41
 #define SCM_WIFI_STATUS		SO_WIFI_STATUS
+#define SO_PEEK_OFF		42
 
 #endif /* _ASM_SOCKET_H */

arch/ia64/include/asm/socket.h

@@ -73,5 +73,6 @@
 
 #define SO_WIFI_STATUS		41
 #define SCM_WIFI_STATUS		SO_WIFI_STATUS
+#define SO_PEEK_OFF		42
 
 #endif /* _ASM_IA64_SOCKET_H */

arch/m32r/include/asm/socket.h

@@ -64,5 +64,6 @@
 
 #define SO_WIFI_STATUS		41
 #define SCM_WIFI_STATUS		SO_WIFI_STATUS
+#define SO_PEEK_OFF		42
 
 #endif /* _ASM_M32R_SOCKET_H */

arch/m68k/include/asm/socket.h

@@ -64,5 +64,6 @@
 
 #define SO_WIFI_STATUS		41
 #define SCM_WIFI_STATUS		SO_WIFI_STATUS
+#define SO_PEEK_OFF		42
 
 #endif /* _ASM_SOCKET_H */

arch/mips/include/asm/socket.h

@@ -84,6 +84,7 @@ To add: #define SO_REUSEPORT 0x0200	/* Allow local address and port reuse.  */
 
 #define SO_WIFI_STATUS		41
 #define SCM_WIFI_STATUS		SO_WIFI_STATUS
+#define SO_PEEK_OFF		42
 
 #ifdef __KERNEL__
 

arch/mn10300/include/asm/socket.h

@@ -64,5 +64,6 @@
 
 #define SO_WIFI_STATUS		41
 #define SCM_WIFI_STATUS		SO_WIFI_STATUS
+#define SO_PEEK_OFF		42
 
 #endif /* _ASM_SOCKET_H */

arch/parisc/include/asm/socket.h

@@ -63,6 +63,7 @@
 
 #define SO_WIFI_STATUS		0x4022
 #define SCM_WIFI_STATUS		SO_WIFI_STATUS
+#define SO_PEEK_OFF		0x4023
 
 /* O_NONBLOCK clashes with the bits used for socket types.  Therefore we
  * have to define SOCK_NONBLOCK to a different value here.

arch/powerpc/include/asm/socket.h

@@ -71,5 +71,6 @@
 
 #define SO_WIFI_STATUS		41
 #define SCM_WIFI_STATUS		SO_WIFI_STATUS
+#define SO_PEEK_OFF		42
 
 #endif	/* _ASM_POWERPC_SOCKET_H */

arch/s390/include/asm/socket.h

@@ -72,5 +72,6 @@
 
 #define SO_WIFI_STATUS		41
 #define SCM_WIFI_STATUS		SO_WIFI_STATUS
+#define SO_PEEK_OFF		42
 
 #endif /* _ASM_SOCKET_H */

arch/sparc/include/asm/socket.h

@@ -60,6 +60,7 @@
 
 #define SO_WIFI_STATUS		0x0025
 #define SCM_WIFI_STATUS		SO_WIFI_STATUS
+#define SO_PEEK_OFF		0x0026
 
 /* Security levels - as per NRL IPv6 - don't actually do anything */
 #define SO_SECURITY_AUTHENTICATION		0x5001

arch/xtensa/include/asm/socket.h

@@ -75,5 +75,6 @@
 
 #define SO_WIFI_STATUS		41
 #define SCM_WIFI_STATUS		SO_WIFI_STATUS
+#define SO_PEEK_OFF		42
 
 #endif	/* _XTENSA_SOCKET_H */

include/asm-generic/socket.h

@@ -67,4 +67,5 @@
 
 #define SO_WIFI_STATUS		41
 #define SCM_WIFI_STATUS	SO_WIFI_STATUS
+#define SO_PEEK_OFF		42
 #endif /* __ASM_GENERIC_SOCKET_H */

include/linux/net.h

@@ -206,6 +206,7 @@ struct proto_ops {
 				      int offset, size_t size, int flags);
 	ssize_t 	(*splice_read)(struct socket *sock,  loff_t *ppos,
 				       struct pipe_inode_info *pipe, size_t len, unsigned int flags);
+	void		(*set_peek_off)(struct sock *sk, int val);
 };
 
 #define DECLARE_SOCKADDR(type, dst, src)	\

include/net/sock.h

@@ -357,6 +357,7 @@ struct sock {
 	struct page		*sk_sndmsg_page;
 	struct sk_buff		*sk_send_head;
 	__u32			sk_sndmsg_off;
+	__s32			sk_peek_off;
 	int			sk_write_pending;
 #ifdef CONFIG_SECURITY
 	void			*sk_security;
@@ -373,6 +374,30 @@ struct sock {
 	void                    (*sk_destruct)(struct sock *sk);
 };
 
+static inline int sk_peek_offset(struct sock *sk, int flags)
+{
+	if ((flags & MSG_PEEK) && (sk->sk_peek_off >= 0))
+		return sk->sk_peek_off;
+	else
+		return 0;
+}
+
+static inline void sk_peek_offset_bwd(struct sock *sk, int val)
+{
+	if (sk->sk_peek_off >= 0) {
+		if (sk->sk_peek_off >= val)
+			sk->sk_peek_off -= val;
+		else
+			sk->sk_peek_off = 0;
+	}
+}
+
+static inline void sk_peek_offset_fwd(struct sock *sk, int val)
+{
+	if (sk->sk_peek_off >= 0)
+		sk->sk_peek_off += val;
+}
+
 /*
  * Hashed lists helper routines
  */

net/core/sock.c

@@ -793,6 +793,12 @@ int sock_setsockopt(struct socket *sock, int level, int optname,
 		sock_valbool_flag(sk, SOCK_WIFI_STATUS, valbool);
 		break;
 
+	case SO_PEEK_OFF:
+		if (sock->ops->set_peek_off)
+			sock->ops->set_peek_off(sk, val);
+		else
+			ret = -EOPNOTSUPP;
+		break;
 	default:
 		ret = -ENOPROTOOPT;
 		break;
@@ -1018,6 +1024,12 @@ int sock_getsockopt(struct socket *sock, int level, int optname,
 		v.val = !!sock_flag(sk, SOCK_WIFI_STATUS);
 		break;
 
+	case SO_PEEK_OFF:
+		if (!sock->ops->set_peek_off)
+			return -EOPNOTSUPP;
+
+		v.val = sk->sk_peek_off;
+		break;
 	default:
 		return -ENOPROTOOPT;
 	}
@@ -2092,6 +2104,7 @@ void sock_init_data(struct socket *sock, struct sock *sk)
 
 	sk->sk_sndmsg_page	=	NULL;
 	sk->sk_sndmsg_off	=	0;
+	sk->sk_peek_off		=	-1;
 
 	sk->sk_peer_pid 	=	NULL;
 	sk->sk_peer_cred	=	NULL;