From: Neil Horman <nhorman@redhat.com>
Subject: [RHEL 5.1] PATCH: expand in-kernel socket api
Date: Wed, 11 Apr 2007 13:23:38 -0400
Bugzilla: 213287
Message-Id: <20070411172338.GB19373@hmsendeavour.rdu.redhat.com>
Changelog: [net] expand in-kernel socket api


Hey all-
	This is an upstream backport to expand the in-kernel sockets api.  dlm
has a potential to hang due to some processing latency.  While the hang issue
can in and of itself be solved with some socket buffer size tuning, further
performance gains and code improvements can be made using the sctp peeloff
operation, which is implemented as a socket option.  Since dlm is in-kernel, we
need a clean method for accessing socket operations from the kernel, and this
backport provides that.  Fixes bz 213287.

Thanks & Regards
Neil


--- linux-2.6.18.noarch/include/linux/net.h.orig	2007-04-11 11:10:38.000000000 -0400
+++ linux-2.6.18.noarch/include/linux/net.h	2007-04-11 11:20:45.000000000 -0400
@@ -209,6 +209,25 @@ extern int   	     kernel_recvmsg(struct
 				    struct kvec *vec, size_t num,
 				    size_t len, int flags);
 
+extern int kernel_bind(struct socket *sock, struct sockaddr *addr,
+		       int addrlen);
+extern int kernel_listen(struct socket *sock, int backlog);
+extern int kernel_accept(struct socket *sock, struct socket **newsock,
+			 int flags);
+extern int kernel_connect(struct socket *sock, struct sockaddr *addr,
+			  int addrlen, int flags);
+extern int kernel_getsockname(struct socket *sock, struct sockaddr *addr,
+			      int *addrlen);
+extern int kernel_getpeername(struct socket *sock, struct sockaddr *addr,
+			      int *addrlen);
+extern int kernel_getsockopt(struct socket *sock, int level, int optname,
+			     char *optval, int *optlen);
+extern int kernel_setsockopt(struct socket *sock, int level, int optname,
+			     char *optval, int optlen);
+extern int kernel_sendpage(struct socket *sock, struct page *page, int offset,
+			   size_t size, int flags);
+extern int kernel_sock_ioctl(struct socket *sock, int cmd, unsigned long arg);
+
 #ifndef CONFIG_SMP
 #define SOCKOPS_WRAPPED(name) name
 #define SOCKOPS_WRAP(name, fam)
--- linux-2.6.18.noarch/net/socket.c.orig	2007-04-11 11:11:28.000000000 -0400
+++ linux-2.6.18.noarch/net/socket.c	2007-04-11 11:20:45.000000000 -0400
@@ -2226,6 +2226,109 @@ static long compat_sock_ioctl(struct fil
 }
 #endif
 
+int kernel_bind(struct socket *sock, struct sockaddr *addr, int addrlen)
+{
+	return sock->ops->bind(sock, addr, addrlen);
+}
+
+int kernel_listen(struct socket *sock, int backlog)
+{
+	return sock->ops->listen(sock, backlog);
+}
+
+int kernel_accept(struct socket *sock, struct socket **newsock, int flags)
+{
+	struct sock *sk = sock->sk;
+	int err;
+
+	err = sock_create_lite(sk->sk_family, sk->sk_type, sk->sk_protocol,
+			       newsock);
+	if (err < 0)
+		goto done;
+
+	err = sock->ops->accept(sock, *newsock, flags);
+	if (err < 0) {
+		sock_release(*newsock);
+		goto done;
+	}
+
+	(*newsock)->ops = sock->ops;
+
+done:
+	return err;
+}
+
+int kernel_connect(struct socket *sock, struct sockaddr *addr, int addrlen,
+                   int flags)
+{
+	return sock->ops->connect(sock, addr, addrlen, flags);
+}
+
+int kernel_getsockname(struct socket *sock, struct sockaddr *addr,
+			 int *addrlen)
+{
+	return sock->ops->getname(sock, addr, addrlen, 0);
+}
+
+int kernel_getpeername(struct socket *sock, struct sockaddr *addr,
+			 int *addrlen)
+{
+	return sock->ops->getname(sock, addr, addrlen, 1);
+}
+
+int kernel_getsockopt(struct socket *sock, int level, int optname,
+			char *optval, int *optlen)
+{
+	mm_segment_t oldfs = get_fs();
+	int err;
+
+	set_fs(KERNEL_DS);
+	if (level == SOL_SOCKET)
+		err = sock_getsockopt(sock, level, optname, optval, optlen);
+	else
+		err = sock->ops->getsockopt(sock, level, optname, optval,
+					    optlen);
+	set_fs(oldfs);
+	return err;
+}
+
+int kernel_setsockopt(struct socket *sock, int level, int optname,
+			char *optval, int optlen)
+{
+	mm_segment_t oldfs = get_fs();
+	int err;
+
+	set_fs(KERNEL_DS);
+	if (level == SOL_SOCKET)
+		err = sock_setsockopt(sock, level, optname, optval, optlen);
+	else
+		err = sock->ops->setsockopt(sock, level, optname, optval,
+					    optlen);
+	set_fs(oldfs);
+	return err;
+}
+
+int kernel_sendpage(struct socket *sock, struct page *page, int offset,
+		    size_t size, int flags)
+{
+	if (sock->ops->sendpage)
+		return sock->ops->sendpage(sock, page, offset, size, flags);
+
+	return sock_no_sendpage(sock, page, offset, size, flags);
+}
+
+int kernel_sock_ioctl(struct socket *sock, int cmd, unsigned long arg)
+{
+	mm_segment_t oldfs = get_fs();
+	int err;
+
+	set_fs(KERNEL_DS);
+	err = sock->ops->ioctl(sock, cmd, arg);
+	set_fs(oldfs);
+
+	return err;
+}
+
 /* ABI emulation layers need these two */
 EXPORT_SYMBOL(move_addr_to_kernel);
 EXPORT_SYMBOL(move_addr_to_user);
@@ -2242,3 +2345,13 @@ EXPORT_SYMBOL(sock_wake_async);
 EXPORT_SYMBOL(sockfd_lookup);
 EXPORT_SYMBOL(kernel_sendmsg);
 EXPORT_SYMBOL(kernel_recvmsg);
+EXPORT_SYMBOL(kernel_bind);
+EXPORT_SYMBOL(kernel_listen);
+EXPORT_SYMBOL(kernel_accept);
+EXPORT_SYMBOL(kernel_connect);
+EXPORT_SYMBOL(kernel_getsockname);
+EXPORT_SYMBOL(kernel_getpeername);
+EXPORT_SYMBOL(kernel_getsockopt);
+EXPORT_SYMBOL(kernel_setsockopt);
+EXPORT_SYMBOL(kernel_sendpage);
+EXPORT_SYMBOL(kernel_sock_ioctl);
-- 
/***************************************************
 *Neil Horman
 *Software Engineer
 *Red Hat, Inc.
 *nhorman@redhat.com
 *gpg keyid: 1024D / 0x92A74FA1
 *http://pgp.mit.edu
 ***************************************************/