sock: add SOCK_ZEROCOPY sockopt

The send call ignores unknown flags. Legacy applications may already unwittingly pass MSG_ZEROCOPY. Continue to ignore this flag unless a socket opts in to zerocopy. Introduce socket option SO_ZEROCOPY to enable MSG_ZEROCOPY processing. Processes can also query this socket option to detect kernel support for the feature. Older kernels will return ENOPROTOOPT. Signed-off-by: Willem de Bruijn <willemb@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
mariux64 · Aug 4, 2017 · 76851d1 · 76851d1
1 parent 5226779
commit 76851d1
Show file tree

Hide file tree

Showing 13 changed files with 43 additions and 0 deletions.
diff --git a/arch/alpha/include/uapi/asm/socket.h b/arch/alpha/include/uapi/asm/socket.h
@@ -109,4 +109,6 @@
 
 #define SO_PEERGROUPS		59
 
+#define SO_ZEROCOPY		60
+
 #endif /* _UAPI_ASM_SOCKET_H */
diff --git a/arch/frv/include/uapi/asm/socket.h b/arch/frv/include/uapi/asm/socket.h
@@ -102,5 +102,7 @@
 
 #define SO_PEERGROUPS		59
 
+#define SO_ZEROCOPY		60
+
 #endif /* _ASM_SOCKET_H */
 
diff --git a/arch/ia64/include/uapi/asm/socket.h b/arch/ia64/include/uapi/asm/socket.h
@@ -111,4 +111,6 @@
 
 #define SO_PEERGROUPS		59
 
+#define SO_ZEROCOPY		60
+
 #endif /* _ASM_IA64_SOCKET_H */
diff --git a/arch/m32r/include/uapi/asm/socket.h b/arch/m32r/include/uapi/asm/socket.h
@@ -102,4 +102,6 @@
 
 #define SO_PEERGROUPS		59
 
+#define SO_ZEROCOPY		60
+
 #endif /* _ASM_M32R_SOCKET_H */
diff --git a/arch/mips/include/uapi/asm/socket.h b/arch/mips/include/uapi/asm/socket.h
@@ -120,4 +120,6 @@
 
 #define SO_PEERGROUPS		59
 
+#define SO_ZEROCOPY		60
+
 #endif /* _UAPI_ASM_SOCKET_H */
diff --git a/arch/mn10300/include/uapi/asm/socket.h b/arch/mn10300/include/uapi/asm/socket.h
@@ -102,4 +102,6 @@
 
 #define SO_PEERGROUPS		59
 
+#define SO_ZEROCOPY		60
+
 #endif /* _ASM_SOCKET_H */
diff --git a/arch/parisc/include/uapi/asm/socket.h b/arch/parisc/include/uapi/asm/socket.h
@@ -101,4 +101,6 @@
 
 #define SO_PEERGROUPS		0x4034
 
+#define SO_ZEROCOPY		0x4035
+
 #endif /* _UAPI_ASM_SOCKET_H */
diff --git a/arch/s390/include/uapi/asm/socket.h b/arch/s390/include/uapi/asm/socket.h
@@ -108,4 +108,6 @@
 
 #define SO_PEERGROUPS		59
 
+#define SO_ZEROCOPY		60
+
 #endif /* _ASM_SOCKET_H */
diff --git a/arch/sparc/include/uapi/asm/socket.h b/arch/sparc/include/uapi/asm/socket.h
@@ -98,6 +98,8 @@
 
 #define SO_PEERGROUPS		0x003d
 
+#define SO_ZEROCOPY		0x003e
+
 /* Security levels - as per NRL IPv6 - don't actually do anything */
 #define SO_SECURITY_AUTHENTICATION		0x5001
 #define SO_SECURITY_ENCRYPTION_TRANSPORT	0x5002

diff --git a/arch/xtensa/include/uapi/asm/socket.h b/arch/xtensa/include/uapi/asm/socket.h
@@ -113,4 +113,6 @@
 
 #define SO_PEERGROUPS		59
 
+#define SO_ZEROCOPY		60
+
 #endif	/* _XTENSA_SOCKET_H */
diff --git a/include/uapi/asm-generic/socket.h b/include/uapi/asm-generic/socket.h
@@ -104,4 +104,6 @@
 
 #define SO_PEERGROUPS		59
 
+#define SO_ZEROCOPY		60
+
 #endif /* __ASM_GENERIC_SOCKET_H */
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
@@ -922,6 +922,9 @@ struct ubuf_info *sock_zerocopy_alloc(struct sock *sk, size_t size)
 
 	WARN_ON_ONCE(!in_task());
 
+	if (!sock_flag(sk, SOCK_ZEROCOPY))
+		return NULL;
+
 	skb = sock_omalloc(sk, 0, GFP_KERNEL);
 	if (!skb)
 		return NULL;

diff --git a/net/core/sock.c b/net/core/sock.c
@@ -1055,6 +1055,20 @@ int sock_setsockopt(struct socket *sock, int level, int optname,
 		if (val == 1)
 			dst_negative_advice(sk);
 		break;
+
+	case SO_ZEROCOPY:
+		if (sk->sk_family != PF_INET && sk->sk_family != PF_INET6)
+			ret = -ENOTSUPP;
+		else if (sk->sk_protocol != IPPROTO_TCP)
+			ret = -ENOTSUPP;
+		else if (sk->sk_state != TCP_CLOSE)
+			ret = -EBUSY;
+		else if (val < 0 || val > 1)
+			ret = -EINVAL;
+		else
+			sock_valbool_flag(sk, SOCK_ZEROCOPY, valbool);
+		break;
+
 	default:
 		ret = -ENOPROTOOPT;
 		break;
@@ -1383,6 +1397,10 @@ int sock_getsockopt(struct socket *sock, int level, int optname,
 		v.val64 = sock_gen_cookie(sk);
 		break;
 
+	case SO_ZEROCOPY:
+		v.val = sock_flag(sk, SOCK_ZEROCOPY);
+		break;
+
 	default:
 		/* We implement the SO_SNDLOWAT etc to not be settable
 		 * (1003.1g 7).