Commit graph

157 commits

Author SHA1 Message Date
Eric Dumazet
c6d409cfd0 From abbffa2aa9bd6f8df16d0d0a102af677510d8b9a Mon Sep 17 00:00:00 2001
From: Eric Dumazet <eric.dumazet@gmail.com>
Date: Thu, 3 Jun 2010 04:29:41 +0000
Subject: [PATCH 2/3] net: net/socket.c and net/compat.c cleanups

cleanup patch, to match modern coding style.

Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/compat.c |   47 ++++++++---------
 net/socket.c |  165 ++++++++++++++++++++++++++++------------------------------
 2 files changed, 102 insertions(+), 110 deletions(-)

diff --git a/net/compat.c b/net/compat.c
index 1cf7590..63d260e 100644
--- a/net/compat.c
+++ b/net/compat.c
@@ -81,7 +81,7 @@ int verify_compat_iovec(struct msghdr *kern_msg, struct iovec *kern_iov,
 	int tot_len;

 	if (kern_msg->msg_namelen) {
-		if (mode==VERIFY_READ) {
+		if (mode == VERIFY_READ) {
 			int err = move_addr_to_kernel(kern_msg->msg_name,
 						      kern_msg->msg_namelen,
 						      kern_address);
@@ -354,7 +354,7 @@ static int do_set_attach_filter(struct socket *sock, int level, int optname,
 static int do_set_sock_timeout(struct socket *sock, int level,
 		int optname, char __user *optval, unsigned int optlen)
 {
-	struct compat_timeval __user *up = (struct compat_timeval __user *) optval;
+	struct compat_timeval __user *up = (struct compat_timeval __user *)optval;
 	struct timeval ktime;
 	mm_segment_t old_fs;
 	int err;
@@ -367,7 +367,7 @@ static int do_set_sock_timeout(struct socket *sock, int level,
 		return -EFAULT;
 	old_fs = get_fs();
 	set_fs(KERNEL_DS);
-	err = sock_setsockopt(sock, level, optname, (char *) &ktime, sizeof(ktime));
+	err = sock_setsockopt(sock, level, optname, (char *)&ktime, sizeof(ktime));
 	set_fs(old_fs);

 	return err;
@@ -389,11 +389,10 @@ asmlinkage long compat_sys_setsockopt(int fd, int level, int optname,
 				char __user *optval, unsigned int optlen)
 {
 	int err;
-	struct socket *sock;
+	struct socket *sock = sockfd_lookup(fd, &err);

-	if ((sock = sockfd_lookup(fd, &err))!=NULL)
-	{
-		err = security_socket_setsockopt(sock,level,optname);
+	if (sock) {
+		err = security_socket_setsockopt(sock, level, optname);
 		if (err) {
 			sockfd_put(sock);
 			return err;
@@ -453,7 +452,7 @@ static int compat_sock_getsockopt(struct socket *sock, int level, int optname,
 int compat_sock_get_timestamp(struct sock *sk, struct timeval __user *userstamp)
 {
 	struct compat_timeval __user *ctv =
-			(struct compat_timeval __user*) userstamp;
+			(struct compat_timeval __user *) userstamp;
 	int err = -ENOENT;
 	struct timeval tv;

@@ -477,7 +476,7 @@ EXPORT_SYMBOL(compat_sock_get_timestamp);
 int compat_sock_get_timestampns(struct sock *sk, struct timespec __user *userstamp)
 {
 	struct compat_timespec __user *ctv =
-			(struct compat_timespec __user*) userstamp;
+			(struct compat_timespec __user *) userstamp;
 	int err = -ENOENT;
 	struct timespec ts;

@@ -502,12 +501,10 @@ asmlinkage long compat_sys_getsockopt(int fd, int level, int optname,
 				char __user *optval, int __user *optlen)
 {
 	int err;
-	struct socket *sock;
+	struct socket *sock = sockfd_lookup(fd, &err);

-	if ((sock = sockfd_lookup(fd, &err))!=NULL)
-	{
-		err = security_socket_getsockopt(sock, level,
-							   optname);
+	if (sock) {
+		err = security_socket_getsockopt(sock, level, optname);
 		if (err) {
 			sockfd_put(sock);
 			return err;
@@ -557,7 +554,7 @@ struct compat_group_filter {

 int compat_mc_setsockopt(struct sock *sock, int level, int optname,
 	char __user *optval, unsigned int optlen,
-	int (*setsockopt)(struct sock *,int,int,char __user *,unsigned int))
+	int (*setsockopt)(struct sock *, int, int, char __user *, unsigned int))
 {
 	char __user	*koptval = optval;
 	int		koptlen = optlen;
@@ -640,12 +637,11 @@ int compat_mc_setsockopt(struct sock *sock, int level, int optname,
 	}
 	return setsockopt(sock, level, optname, koptval, koptlen);
 }
-
 EXPORT_SYMBOL(compat_mc_setsockopt);

 int compat_mc_getsockopt(struct sock *sock, int level, int optname,
 	char __user *optval, int __user *optlen,
-	int (*getsockopt)(struct sock *,int,int,char __user *,int __user *))
+	int (*getsockopt)(struct sock *, int, int, char __user *, int __user *))
 {
 	struct compat_group_filter __user *gf32 = (void *)optval;
 	struct group_filter __user *kgf;
@@ -681,7 +677,7 @@ int compat_mc_getsockopt(struct sock *sock, int level, int optname,
 	    __put_user(interface, &kgf->gf_interface) ||
 	    __put_user(fmode, &kgf->gf_fmode) ||
 	    __put_user(numsrc, &kgf->gf_numsrc) ||
-	    copy_in_user(&kgf->gf_group,&gf32->gf_group,sizeof(kgf->gf_group)))
+	    copy_in_user(&kgf->gf_group, &gf32->gf_group, sizeof(kgf->gf_group)))
 		return -EFAULT;

 	err = getsockopt(sock, level, optname, (char __user *)kgf, koptlen);
@@ -714,21 +710,22 @@ int compat_mc_getsockopt(struct sock *sock, int level, int optname,
 		copylen = numsrc * sizeof(gf32->gf_slist[0]);
 		if (copylen > klen)
 			copylen = klen;
-	        if (copy_in_user(gf32->gf_slist, kgf->gf_slist, copylen))
+		if (copy_in_user(gf32->gf_slist, kgf->gf_slist, copylen))
 			return -EFAULT;
 	}
 	return err;
 }
-
 EXPORT_SYMBOL(compat_mc_getsockopt);

 /* Argument list sizes for compat_sys_socketcall */
 #define AL(x) ((x) * sizeof(u32))
-static unsigned char nas[20]={AL(0),AL(3),AL(3),AL(3),AL(2),AL(3),
-				AL(3),AL(3),AL(4),AL(4),AL(4),AL(6),
-				AL(6),AL(2),AL(5),AL(5),AL(3),AL(3),
-				AL(4),AL(5)};
+static unsigned char nas[20] = {
+	AL(0), AL(3), AL(3), AL(3), AL(2), AL(3),
+	AL(3), AL(3), AL(4), AL(4), AL(4), AL(6),
+	AL(6), AL(2), AL(5), AL(5), AL(3), AL(3),
+	AL(4), AL(5)
+};
 #undef AL

 asmlinkage long compat_sys_sendmsg(int fd, struct compat_msghdr __user *msg, unsigned flags)
@@ -827,7 +824,7 @@ asmlinkage long compat_sys_socketcall(int call, u32 __user *args)
 					  compat_ptr(a[4]), compat_ptr(a[5]));
 		break;
 	case SYS_SHUTDOWN:
-		ret = sys_shutdown(a0,a1);
+		ret = sys_shutdown(a0, a1);
 		break;
 	case SYS_SETSOCKOPT:
 		ret = compat_sys_setsockopt(a0, a1, a[2],
diff --git a/net/socket.c b/net/socket.c
index 367d547..b63c051 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -124,7 +124,7 @@ static int sock_fasync(int fd, struct file *filp, int on);
 static ssize_t sock_sendpage(struct file *file, struct page *page,
 			     int offset, size_t size, loff_t *ppos, int more);
 static ssize_t sock_splice_read(struct file *file, loff_t *ppos,
-			        struct pipe_inode_info *pipe, size_t len,
+				struct pipe_inode_info *pipe, size_t len,
 				unsigned int flags);

 /*
@@ -162,7 +162,7 @@ static const struct net_proto_family *net_families[NPROTO] __read_mostly;
  *	Statistics counters of the socket lists
  */

-static DEFINE_PER_CPU(int, sockets_in_use) = 0;
+static DEFINE_PER_CPU(int, sockets_in_use);

 /*
  * Support routines.
@@ -309,9 +309,9 @@ static int init_inodecache(void)
 }

 static const struct super_operations sockfs_ops = {
-	.alloc_inode =	sock_alloc_inode,
-	.destroy_inode =sock_destroy_inode,
-	.statfs =	simple_statfs,
+	.alloc_inode	= sock_alloc_inode,
+	.destroy_inode	= sock_destroy_inode,
+	.statfs		= simple_statfs,
 };

 static int sockfs_get_sb(struct file_system_type *fs_type,
@@ -411,6 +411,7 @@ int sock_map_fd(struct socket *sock, int flags)

 	return fd;
 }
+EXPORT_SYMBOL(sock_map_fd);

 static struct socket *sock_from_file(struct file *file, int *err)
 {
@@ -422,7 +423,7 @@ static struct socket *sock_from_file(struct file *file, int *err)
 }

 /**
- *	sockfd_lookup	- 	Go from a file number to its socket slot
+ *	sockfd_lookup - Go from a file number to its socket slot
  *	@fd: file handle
  *	@err: pointer to an error code return
  *
@@ -450,6 +451,7 @@ struct socket *sockfd_lookup(int fd, int *err)
 		fput(file);
 	return sock;
 }
+EXPORT_SYMBOL(sockfd_lookup);

 static struct socket *sockfd_lookup_light(int fd, int *err, int *fput_needed)
 {
@@ -540,6 +542,7 @@ void sock_release(struct socket *sock)
 	}
 	sock->file = NULL;
 }
+EXPORT_SYMBOL(sock_release);

 int sock_tx_timestamp(struct msghdr *msg, struct sock *sk,
 		      union skb_shared_tx *shtx)
@@ -586,6 +589,7 @@ int sock_sendmsg(struct socket *sock, struct msghdr *msg, size_t size)
 		ret = wait_on_sync_kiocb(&iocb);
 	return ret;
 }
+EXPORT_SYMBOL(sock_sendmsg);

 int kernel_sendmsg(struct socket *sock, struct msghdr *msg,
 		   struct kvec *vec, size_t num, size_t size)
@@ -604,6 +608,7 @@ int kernel_sendmsg(struct socket *sock, struct msghdr *msg,
 	set_fs(oldfs);
 	return result;
 }
+EXPORT_SYMBOL(kernel_sendmsg);

 static int ktime2ts(ktime_t kt, struct timespec *ts)
 {
@@ -664,7 +669,6 @@ void __sock_recv_timestamp(struct msghdr *msg, struct sock *sk,
 		put_cmsg(msg, SOL_SOCKET,
 			 SCM_TIMESTAMPING, sizeof(ts), &ts);
 }
-
 EXPORT_SYMBOL_GPL(__sock_recv_timestamp);

 inline void sock_recv_drops(struct msghdr *msg, struct sock *sk, struct sk_buff *skb)
@@ -720,6 +724,7 @@ int sock_recvmsg(struct socket *sock, struct msghdr *msg,
 		ret = wait_on_sync_kiocb(&iocb);
 	return ret;
 }
+EXPORT_SYMBOL(sock_recvmsg);

 static int sock_recvmsg_nosec(struct socket *sock, struct msghdr *msg,
 			      size_t size, int flags)
@@ -752,6 +757,7 @@ int kernel_recvmsg(struct socket *sock, struct msghdr *msg,
 	set_fs(oldfs);
 	return result;
 }
+EXPORT_SYMBOL(kernel_recvmsg);

 static void sock_aio_dtor(struct kiocb *iocb)
 {
@@ -774,7 +780,7 @@ static ssize_t sock_sendpage(struct file *file, struct page *page,
 }

 static ssize_t sock_splice_read(struct file *file, loff_t *ppos,
-			        struct pipe_inode_info *pipe, size_t len,
+				struct pipe_inode_info *pipe, size_t len,
 				unsigned int flags)
 {
 	struct socket *sock = file->private_data;
@@ -887,7 +893,7 @@ static ssize_t sock_aio_write(struct kiocb *iocb, const struct iovec *iov,
  */

 static DEFINE_MUTEX(br_ioctl_mutex);
-static int (*br_ioctl_hook) (struct net *, unsigned int cmd, void __user *arg) = NULL;
+static int (*br_ioctl_hook) (struct net *, unsigned int cmd, void __user *arg);

 void brioctl_set(int (*hook) (struct net *, unsigned int, void __user *))
 {
@@ -895,7 +901,6 @@ void brioctl_set(int (*hook) (struct net *, unsigned int, void __user *))
 	br_ioctl_hook = hook;
 	mutex_unlock(&br_ioctl_mutex);
 }
-
 EXPORT_SYMBOL(brioctl_set);

 static DEFINE_MUTEX(vlan_ioctl_mutex);
@@ -907,7 +912,6 @@ void vlan_ioctl_set(int (*hook) (struct net *, void __user *))
 	vlan_ioctl_hook = hook;
 	mutex_unlock(&vlan_ioctl_mutex);
 }
-
 EXPORT_SYMBOL(vlan_ioctl_set);

 static DEFINE_MUTEX(dlci_ioctl_mutex);
@@ -919,7 +923,6 @@ void dlci_ioctl_set(int (*hook) (unsigned int, void __user *))
 	dlci_ioctl_hook = hook;
 	mutex_unlock(&dlci_ioctl_mutex);
 }
-
 EXPORT_SYMBOL(dlci_ioctl_set);

 static long sock_do_ioctl(struct net *net, struct socket *sock,
@@ -1047,6 +1050,7 @@ out_release:
 	sock = NULL;
 	goto out;
 }
+EXPORT_SYMBOL(sock_create_lite);

 /* No kernel lock held - perfect */
 static unsigned int sock_poll(struct file *file, poll_table *wait)
@@ -1147,6 +1151,7 @@ call_kill:
 	rcu_read_unlock();
 	return 0;
 }
+EXPORT_SYMBOL(sock_wake_async);

 static int __sock_create(struct net *net, int family, int type, int protocol,
 			 struct socket **res, int kern)
@@ -1265,11 +1270,13 @@ int sock_create(int family, int type, int protocol, struct socket **res)
 {
 	return __sock_create(current->nsproxy->net_ns, family, type, protocol, res, 0);
 }
+EXPORT_SYMBOL(sock_create);

 int sock_create_kern(int family, int type, int protocol, struct socket **res)
 {
 	return __sock_create(&init_net, family, type, protocol, res, 1);
 }
+EXPORT_SYMBOL(sock_create_kern);

 SYSCALL_DEFINE3(socket, int, family, int, type, int, protocol)
 {
@@ -1474,7 +1481,8 @@ SYSCALL_DEFINE4(accept4, int, fd, struct sockaddr __user *, upeer_sockaddr,
 		goto out;

 	err = -ENFILE;
-	if (!(newsock = sock_alloc()))
+	newsock = sock_alloc();
+	if (!newsock)
 		goto out_put;

 	newsock->type = sock->type;
@@ -1861,8 +1869,7 @@ SYSCALL_DEFINE3(sendmsg, int, fd, struct msghdr __user *, msg, unsigned, flags)
 	if (MSG_CMSG_COMPAT & flags) {
 		if (get_compat_msghdr(&msg_sys, msg_compat))
 			return -EFAULT;
-	}
-	else if (copy_from_user(&msg_sys, msg, sizeof(struct msghdr)))
+	} else if (copy_from_user(&msg_sys, msg, sizeof(struct msghdr)))
 		return -EFAULT;

 	sock = sockfd_lookup_light(fd, &err, &fput_needed);
@@ -1964,8 +1971,7 @@ static int __sys_recvmsg(struct socket *sock, struct msghdr __user *msg,
 	if (MSG_CMSG_COMPAT & flags) {
 		if (get_compat_msghdr(msg_sys, msg_compat))
 			return -EFAULT;
-	}
-	else if (copy_from_user(msg_sys, msg, sizeof(struct msghdr)))
+	} else if (copy_from_user(msg_sys, msg, sizeof(struct msghdr)))
 		return -EFAULT;

 	err = -EMSGSIZE;
@@ -2191,10 +2197,10 @@ SYSCALL_DEFINE5(recvmmsg, int, fd, struct mmsghdr __user *, mmsg,
 /* Argument list sizes for sys_socketcall */
 #define AL(x) ((x) * sizeof(unsigned long))
 static const unsigned char nargs[20] = {
-	AL(0),AL(3),AL(3),AL(3),AL(2),AL(3),
-	AL(3),AL(3),AL(4),AL(4),AL(4),AL(6),
-	AL(6),AL(2),AL(5),AL(5),AL(3),AL(3),
-	AL(4),AL(5)
+	AL(0), AL(3), AL(3), AL(3), AL(2), AL(3),
+	AL(3), AL(3), AL(4), AL(4), AL(4), AL(6),
+	AL(6), AL(2), AL(5), AL(5), AL(3), AL(3),
+	AL(4), AL(5)
 };

 #undef AL
@@ -2340,6 +2346,7 @@ int sock_register(const struct net_proto_family *ops)
 	printk(KERN_INFO "NET: Registered protocol family %d\n", ops->family);
 	return err;
 }
+EXPORT_SYMBOL(sock_register);

 /**
  *	sock_unregister - remove a protocol handler
@@ -2366,6 +2373,7 @@ void sock_unregister(int family)

 	printk(KERN_INFO "NET: Unregistered protocol family %d\n", family);
 }
+EXPORT_SYMBOL(sock_unregister);

 static int __init sock_init(void)
 {
@@ -2490,13 +2498,13 @@ static int dev_ifconf(struct net *net, struct compat_ifconf __user *uifc32)
 		ifc.ifc_req = NULL;
 		uifc = compat_alloc_user_space(sizeof(struct ifconf));
 	} else {
-		size_t len =((ifc32.ifc_len / sizeof (struct compat_ifreq)) + 1) *
-			sizeof (struct ifreq);
+		size_t len = ((ifc32.ifc_len / sizeof(struct compat_ifreq)) + 1) *
+			sizeof(struct ifreq);
 		uifc = compat_alloc_user_space(sizeof(struct ifconf) + len);
 		ifc.ifc_len = len;
 		ifr = ifc.ifc_req = (void __user *)(uifc + 1);
 		ifr32 = compat_ptr(ifc32.ifcbuf);
-		for (i = 0; i < ifc32.ifc_len; i += sizeof (struct compat_ifreq)) {
+		for (i = 0; i < ifc32.ifc_len; i += sizeof(struct compat_ifreq)) {
 			if (copy_in_user(ifr, ifr32, sizeof(struct compat_ifreq)))
 				return -EFAULT;
 			ifr++;
@@ -2516,9 +2524,9 @@ static int dev_ifconf(struct net *net, struct compat_ifconf __user *uifc32)
 	ifr = ifc.ifc_req;
 	ifr32 = compat_ptr(ifc32.ifcbuf);
 	for (i = 0, j = 0;
-             i + sizeof (struct compat_ifreq) <= ifc32.ifc_len && j < ifc.ifc_len;
-	     i += sizeof (struct compat_ifreq), j += sizeof (struct ifreq)) {
-		if (copy_in_user(ifr32, ifr, sizeof (struct compat_ifreq)))
+	     i + sizeof(struct compat_ifreq) <= ifc32.ifc_len && j < ifc.ifc_len;
+	     i += sizeof(struct compat_ifreq), j += sizeof(struct ifreq)) {
+		if (copy_in_user(ifr32, ifr, sizeof(struct compat_ifreq)))
 			return -EFAULT;
 		ifr32++;
 		ifr++;
@@ -2567,7 +2575,7 @@ static int compat_siocwandev(struct net *net, struct compat_ifreq __user *uifr32
 	compat_uptr_t uptr32;
 	struct ifreq __user *uifr;

-	uifr = compat_alloc_user_space(sizeof (*uifr));
+	uifr = compat_alloc_user_space(sizeof(*uifr));
 	if (copy_in_user(uifr, uifr32, sizeof(struct compat_ifreq)))
 		return -EFAULT;

@@ -2601,9 +2609,9 @@ static int bond_ioctl(struct net *net, unsigned int cmd,
 			return -EFAULT;

 		old_fs = get_fs();
-		set_fs (KERNEL_DS);
+		set_fs(KERNEL_DS);
 		err = dev_ioctl(net, cmd, &kifr);
-		set_fs (old_fs);
+		set_fs(old_fs);

 		return err;
 	case SIOCBONDSLAVEINFOQUERY:
@@ -2710,9 +2718,9 @@ static int compat_sioc_ifmap(struct net *net, unsigned int cmd,
 		return -EFAULT;

 	old_fs = get_fs();
-	set_fs (KERNEL_DS);
+	set_fs(KERNEL_DS);
 	err = dev_ioctl(net, cmd, (void __user *)&ifr);
-	set_fs (old_fs);
+	set_fs(old_fs);

 	if (cmd == SIOCGIFMAP && !err) {
 		err = copy_to_user(uifr32, &ifr, sizeof(ifr.ifr_name));
@@ -2734,7 +2742,7 @@ static int compat_siocshwtstamp(struct net *net, struct compat_ifreq __user *uif
 	compat_uptr_t uptr32;
 	struct ifreq __user *uifr;

-	uifr = compat_alloc_user_space(sizeof (*uifr));
+	uifr = compat_alloc_user_space(sizeof(*uifr));
 	if (copy_in_user(uifr, uifr32, sizeof(struct compat_ifreq)))
 		return -EFAULT;

@@ -2750,20 +2758,20 @@ static int compat_siocshwtstamp(struct net *net, struct compat_ifreq __user *uif
 }

 struct rtentry32 {
-	u32   		rt_pad1;
+	u32		rt_pad1;
 	struct sockaddr rt_dst;         /* target address               */
 	struct sockaddr rt_gateway;     /* gateway addr (RTF_GATEWAY)   */
 	struct sockaddr rt_genmask;     /* target network mask (IP)     */
-	unsigned short  rt_flags;
-	short           rt_pad2;
-	u32   		rt_pad3;
-	unsigned char   rt_tos;
-	unsigned char   rt_class;
-	short           rt_pad4;
-	short           rt_metric;      /* +1 for binary compatibility! */
+	unsigned short	rt_flags;
+	short		rt_pad2;
+	u32		rt_pad3;
+	unsigned char	rt_tos;
+	unsigned char	rt_class;
+	short		rt_pad4;
+	short		rt_metric;      /* +1 for binary compatibility! */
 	/* char * */ u32 rt_dev;        /* forcing the device at add    */
-	u32   		rt_mtu;         /* per route MTU/Window         */
-	u32   		rt_window;      /* Window clamping              */
+	u32		rt_mtu;         /* per route MTU/Window         */
+	u32		rt_window;      /* Window clamping              */
 	unsigned short  rt_irtt;        /* Initial RTT                  */
 };

@@ -2793,29 +2801,29 @@ static int routing_ioctl(struct net *net, struct socket *sock,

 	if (sock && sock->sk && sock->sk->sk_family == AF_INET6) { /* ipv6 */
 		struct in6_rtmsg32 __user *ur6 = argp;
-		ret = copy_from_user (&r6.rtmsg_dst, &(ur6->rtmsg_dst),
+		ret = copy_from_user(&r6.rtmsg_dst, &(ur6->rtmsg_dst),
 			3 * sizeof(struct in6_addr));
-		ret |= __get_user (r6.rtmsg_type, &(ur6->rtmsg_type));
-		ret |= __get_user (r6.rtmsg_dst_len, &(ur6->rtmsg_dst_len));
-		ret |= __get_user (r6.rtmsg_src_len, &(ur6->rtmsg_src_len));
-		ret |= __get_user (r6.rtmsg_metric, &(ur6->rtmsg_metric));
-		ret |= __get_user (r6.rtmsg_info, &(ur6->rtmsg_info));
-		ret |= __get_user (r6.rtmsg_flags, &(ur6->rtmsg_flags));
-		ret |= __get_user (r6.rtmsg_ifindex, &(ur6->rtmsg_ifindex));
+		ret |= __get_user(r6.rtmsg_type, &(ur6->rtmsg_type));
+		ret |= __get_user(r6.rtmsg_dst_len, &(ur6->rtmsg_dst_len));
+		ret |= __get_user(r6.rtmsg_src_len, &(ur6->rtmsg_src_len));
+		ret |= __get_user(r6.rtmsg_metric, &(ur6->rtmsg_metric));
+		ret |= __get_user(r6.rtmsg_info, &(ur6->rtmsg_info));
+		ret |= __get_user(r6.rtmsg_flags, &(ur6->rtmsg_flags));
+		ret |= __get_user(r6.rtmsg_ifindex, &(ur6->rtmsg_ifindex));

 		r = (void *) &r6;
 	} else { /* ipv4 */
 		struct rtentry32 __user *ur4 = argp;
-		ret = copy_from_user (&r4.rt_dst, &(ur4->rt_dst),
+		ret = copy_from_user(&r4.rt_dst, &(ur4->rt_dst),
 					3 * sizeof(struct sockaddr));
-		ret |= __get_user (r4.rt_flags, &(ur4->rt_flags));
-		ret |= __get_user (r4.rt_metric, &(ur4->rt_metric));
-		ret |= __get_user (r4.rt_mtu, &(ur4->rt_mtu));
-		ret |= __get_user (r4.rt_window, &(ur4->rt_window));
-		ret |= __get_user (r4.rt_irtt, &(ur4->rt_irtt));
-		ret |= __get_user (rtdev, &(ur4->rt_dev));
+		ret |= __get_user(r4.rt_flags, &(ur4->rt_flags));
+		ret |= __get_user(r4.rt_metric, &(ur4->rt_metric));
+		ret |= __get_user(r4.rt_mtu, &(ur4->rt_mtu));
+		ret |= __get_user(r4.rt_window, &(ur4->rt_window));
+		ret |= __get_user(r4.rt_irtt, &(ur4->rt_irtt));
+		ret |= __get_user(rtdev, &(ur4->rt_dev));
 		if (rtdev) {
-			ret |= copy_from_user (devname, compat_ptr(rtdev), 15);
+			ret |= copy_from_user(devname, compat_ptr(rtdev), 15);
 			r4.rt_dev = devname; devname[15] = 0;
 		} else
 			r4.rt_dev = NULL;
@@ -2828,9 +2836,9 @@ static int routing_ioctl(struct net *net, struct socket *sock,
 		goto out;
 	}

-	set_fs (KERNEL_DS);
+	set_fs(KERNEL_DS);
 	ret = sock_do_ioctl(net, sock, cmd, (unsigned long) r);
-	set_fs (old_fs);
+	set_fs(old_fs);

 out:
 	return ret;
@@ -2993,11 +3001,13 @@ int kernel_bind(struct socket *sock, struct sockaddr *addr, int addrlen)
 {
 	return sock->ops->bind(sock, addr, addrlen);
 }
+EXPORT_SYMBOL(kernel_bind);

 int kernel_listen(struct socket *sock, int backlog)
 {
 	return sock->ops->listen(sock, backlog);
 }
+EXPORT_SYMBOL(kernel_listen);

 int kernel_accept(struct socket *sock, struct socket **newsock, int flags)
 {
@@ -3022,24 +3032,28 @@ int kernel_accept(struct socket *sock, struct socket **newsock, int flags)
 done:
 	return err;
 }
+EXPORT_SYMBOL(kernel_accept);

 int kernel_connect(struct socket *sock, struct sockaddr *addr, int addrlen,
 		   int flags)
 {
 	return sock->ops->connect(sock, addr, addrlen, flags);
 }
+EXPORT_SYMBOL(kernel_connect);

 int kernel_getsockname(struct socket *sock, struct sockaddr *addr,
 			 int *addrlen)
 {
 	return sock->ops->getname(sock, addr, addrlen, 0);
 }
+EXPORT_SYMBOL(kernel_getsockname);

 int kernel_getpeername(struct socket *sock, struct sockaddr *addr,
 			 int *addrlen)
 {
 	return sock->ops->getname(sock, addr, addrlen, 1);
 }
+EXPORT_SYMBOL(kernel_getpeername);

 int kernel_getsockopt(struct socket *sock, int level, int optname,
 			char *optval, int *optlen)
@@ -3056,6 +3070,7 @@ int kernel_getsockopt(struct socket *sock, int level, int optname,
 	set_fs(oldfs);
 	return err;
 }
+EXPORT_SYMBOL(kernel_getsockopt);

 int kernel_setsockopt(struct socket *sock, int level, int optname,
 			char *optval, unsigned int optlen)
@@ -3072,6 +3087,7 @@ int kernel_setsockopt(struct socket *sock, int level, int optname,
 	set_fs(oldfs);
 	return err;
 }
+EXPORT_SYMBOL(kernel_setsockopt);

 int kernel_sendpage(struct socket *sock, struct page *page, int offset,
 		    size_t size, int flags)
@@ -3083,6 +3099,7 @@ int kernel_sendpage(struct socket *sock, struct page *page, int offset,

 	return sock_no_sendpage(sock, page, offset, size, flags);
 }
+EXPORT_SYMBOL(kernel_sendpage);

 int kernel_sock_ioctl(struct socket *sock, int cmd, unsigned long arg)
 {
@@ -3095,33 +3112,11 @@ int kernel_sock_ioctl(struct socket *sock, int cmd, unsigned long arg)

 	return err;
 }
+EXPORT_SYMBOL(kernel_sock_ioctl);

 int kernel_sock_shutdown(struct socket *sock, enum sock_shutdown_cmd how)
 {
 	return sock->ops->shutdown(sock, how);
 }
-
-EXPORT_SYMBOL(sock_create);
-EXPORT_SYMBOL(sock_create_kern);
-EXPORT_SYMBOL(sock_create_lite);
-EXPORT_SYMBOL(sock_map_fd);
-EXPORT_SYMBOL(sock_recvmsg);
-EXPORT_SYMBOL(sock_register);
-EXPORT_SYMBOL(sock_release);
-EXPORT_SYMBOL(sock_sendmsg);
-EXPORT_SYMBOL(sock_unregister);
-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);
 EXPORT_SYMBOL(kernel_sock_shutdown);
+
--
1.7.0.4
2010-06-03 20:03:40 -07:00
Herbert Xu
f845172531 cls_cgroup: Store classid in struct sock
Up until now cls_cgroup has relied on fetching the classid out of
the current executing thread.  This runs into trouble when a packet
processing is delayed in which case it may execute out of another
thread's context.

Furthermore, even when a packet is not delayed we may fail to
classify it if soft IRQs have been disabled, because this scenario
is indistinguishable from one where a packet unrelated to the
current thread is processed by a real soft IRQ.

In fact, the current semantics is inherently broken, as a single
skb may be constructed out of the writes of two different tasks.
A different manifestation of this problem is when the TCP stack
transmits in response of an incoming ACK.  This is currently
unclassified.

As we already have a concept of packet ownership for accounting
purposes in the skb->sk pointer, this is a natural place to store
the classid in a persistent manner.

This patch adds the cls_cgroup classid in struct sock, filling up
an existing hole on 64-bit :)

The value is set at socket creation time.  So all sockets created
via socket(2) automatically gains the ID of the thread creating it.
Whenever another process touches the socket by either reading or
writing to it, we will change the socket classid to that of the
process if it has a valid (non-zero) classid.

For sockets created on inbound connections through accept(2), we
inherit the classid of the original listening socket through
sk_clone, possibly preceding the actual accept(2) call.

In order to minimise risks, I have not made this the authoritative
classid.  For now it is only used as a backup when we execute
with soft IRQs disabled.  Once we're completely happy with its
semantics we can use it as the sole classid.

Footnote: I have rearranged the error path on cls_group module
creation.  If we didn't do this, then there is a window where
someone could create a tc rule using cls_group before the cgroup
subsystem has been registered.

Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
2010-05-24 00:12:34 -07:00
Joe Perches
ccbd6a5a4f net: Remove unnecessary semicolons after switch statements
Also added an explicit break; to avoid
a fallthrough in net/ipv4/tcp_input.c

Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2010-05-17 17:44:35 -07:00
Eric Dumazet
4381548237 net: sock_def_readable() and friends RCU conversion
sk_callback_lock rwlock actually protects sk->sk_sleep pointer, so we
need two atomic operations (and associated dirtying) per incoming
packet.

RCU conversion is pretty much needed :

1) Add a new structure, called "struct socket_wq" to hold all fields
that will need rcu_read_lock() protection (currently: a
wait_queue_head_t and a struct fasync_struct pointer).

[Future patch will add a list anchor for wakeup coalescing]

2) Attach one of such structure to each "struct socket" created in
sock_alloc_inode().

3) Respect RCU grace period when freeing a "struct socket_wq"

4) Change sk_sleep pointer in "struct sock" by sk_wq, pointer to "struct
socket_wq"

5) Change sk_sleep() function to use new sk->sk_wq instead of
sk->sk_sleep

6) Change sk_has_sleeper() to wq_has_sleeper() that must be used inside
a rcu_read_lock() section.

7) Change all sk_has_sleeper() callers to :
  - Use rcu_read_lock() instead of read_lock(&sk->sk_callback_lock)
  - Use wq_has_sleeper() to eventually wakeup tasks.
  - Use rcu_read_unlock() instead of read_unlock(&sk->sk_callback_lock)

8) sock_wake_async() is modified to use rcu protection as well.

9) Exceptions :
  macvtap, drivers/net/tun.c, af_unix use integrated "struct socket_wq"
instead of dynamically allocated ones. They dont need rcu freeing.

Some cleanups or followups are probably needed, (possible
sk_callback_lock conversion to a spinlock for example...).

Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2010-05-01 15:00:15 -07:00
Eric Dumazet
767dd03369 net: speedup sock_recv_ts_and_drops()
sock_recv_ts_and_drops() is fat and slow (~ 4% of cpu time on some
profiles)

We can test all socket flags at once to make fast path fast again.

Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2010-04-30 16:29:42 -07:00
Eric Dumazet
989a297920 fasync: RCU and fine grained locking
kill_fasync() uses a central rwlock, candidate for RCU conversion, to
avoid cache line ping pongs on SMP.

fasync_remove_entry() and fasync_add_entry() can disable IRQS on a short
section instead during whole list scan.

Use a spinlock per fasync_struct to synchronize kill_fasync_rcu() and
fasync_{remove|add}_entry(). This spinlock is IRQ safe, so sock_fasync()
doesnt need its own implementation and can use fasync_helper(), to
reduce code size and complexity.

We can remove __kill_fasync() direct use in net/socket.c, and rename it
to kill_fasync_rcu().

Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Lai Jiangshan <laijs@cn.fujitsu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2010-04-21 16:19:29 -07:00
David S. Miller
871039f02f Merge branch 'master' of master.kernel.org:/pub/scm/linux/kernel/git/davem/net-2.6
Conflicts:
	drivers/net/stmmac/stmmac_main.c
	drivers/net/wireless/wl12xx/wl1271_cmd.c
	drivers/net/wireless/wl12xx/wl1271_main.c
	drivers/net/wireless/wl12xx/wl1271_spi.c
	net/core/ethtool.c
	net/mac80211/scan.c
2010-04-11 14:53:53 -07:00
David S. Miller
4a35ecf8bf Merge branch 'master' of master.kernel.org:/pub/scm/linux/kernel/git/davem/net-2.6
Conflicts:
	drivers/net/bonding/bond_main.c
	drivers/net/via-velocity.c
	drivers/net/wireless/iwlwifi/iwl-agn.c
2010-04-06 23:53:30 -07:00
Hagen Paul Pfeifer
842509b859 socket: remove duplicate declaration of struct timespec
struct timespec ts was alreay defined. Reuse the previously
defined one and reduce the memory footprint on the stack by
16 bytes.

Signed-off-by: Hagen Paul Pfeifer <hagen@jauu.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
2010-04-06 19:50:20 -07:00
Tejun Heo
5a0e3ad6af include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h
percpu.h is included by sched.h and module.h and thus ends up being
included when building most .c files.  percpu.h includes slab.h which
in turn includes gfp.h making everything defined by the two files
universally available and complicating inclusion dependencies.

percpu.h -> slab.h dependency is about to be removed.  Prepare for
this change by updating users of gfp and slab facilities include those
headers directly instead of assuming availability.  As this conversion
needs to touch large number of source files, the following script is
used as the basis of conversion.

  http://userweb.kernel.org/~tj/misc/slabh-sweep.py

The script does the followings.

* Scan files for gfp and slab usages and update includes such that
  only the necessary includes are there.  ie. if only gfp is used,
  gfp.h, if slab is used, slab.h.

* When the script inserts a new include, it looks at the include
  blocks and try to put the new include such that its order conforms
  to its surrounding.  It's put in the include block which contains
  core kernel includes, in the same order that the rest are ordered -
  alphabetical, Christmas tree, rev-Xmas-tree or at the end if there
  doesn't seem to be any matching order.

* If the script can't find a place to put a new include (mostly
  because the file doesn't have fitting include block), it prints out
  an error message indicating which .h file needs to be added to the
  file.

The conversion was done in the following steps.

1. The initial automatic conversion of all .c files updated slightly
   over 4000 files, deleting around 700 includes and adding ~480 gfp.h
   and ~3000 slab.h inclusions.  The script emitted errors for ~400
   files.

2. Each error was manually checked.  Some didn't need the inclusion,
   some needed manual addition while adding it to implementation .h or
   embedding .c file was more appropriate for others.  This step added
   inclusions to around 150 files.

3. The script was run again and the output was compared to the edits
   from #2 to make sure no file was left behind.

4. Several build tests were done and a couple of problems were fixed.
   e.g. lib/decompress_*.c used malloc/free() wrappers around slab
   APIs requiring slab.h to be added manually.

5. The script was run on all .h files but without automatically
   editing them as sprinkling gfp.h and slab.h inclusions around .h
   files could easily lead to inclusion dependency hell.  Most gfp.h
   inclusion directives were ignored as stuff from gfp.h was usually
   wildly available and often used in preprocessor macros.  Each
   slab.h inclusion directive was examined and added manually as
   necessary.

6. percpu.h was updated not to include slab.h.

7. Build test were done on the following configurations and failures
   were fixed.  CONFIG_GCOV_KERNEL was turned off for all tests (as my
   distributed build env didn't work with gcov compiles) and a few
   more options had to be turned off depending on archs to make things
   build (like ipr on powerpc/64 which failed due to missing writeq).

   * x86 and x86_64 UP and SMP allmodconfig and a custom test config.
   * powerpc and powerpc64 SMP allmodconfig
   * sparc and sparc64 SMP allmodconfig
   * ia64 SMP allmodconfig
   * s390 SMP allmodconfig
   * alpha SMP allmodconfig
   * um on x86_64 SMP allmodconfig

8. percpu.h modifications were reverted so that it could be applied as
   a separate patch and serve as bisection point.

Given the fact that I had only a couple of failures from tests on step
6, I'm fairly confident about the coverage of this conversion patch.
If there is a breakage, it's likely to be something in one of the arch
headers which should be easily discoverable easily on most builds of
the specific arch.

Signed-off-by: Tejun Heo <tj@kernel.org>
Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-30 22:02:32 +09:00
Brandon L Black
71c5c1595c net: Add MSG_WAITFORONE flag to recvmmsg
Add new flag MSG_WAITFORONE for the recvmmsg() syscall.
When this flag is specified for a blocking socket, recvmmsg()
will only block until at least 1 packet is available.  The
default behavior is to block until all vlen packets are
available.  This flag has no effect on non-blocking sockets
or when used in combination with MSG_DONTWAIT.

Signed-off-by: Brandon L Black <blblack@gmail.com>
Acked-by: Ulrich Drepper <drepper@redhat.com>
Acked-by: Eric Dumazet <eric.dumazet@gmail.com>
Acked-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2010-03-27 08:29:01 -07:00
Nick Piggin
a3a065e3f1 fs: no games with DCACHE_UNHASHED
Filesystems outside the regular namespace do not have to clear DCACHE_UNHASHED
in order to have a working /proc/$pid/fd/XXX. Nothing in proc prevents the
fd link from being used if its dentry is not in the hash.

Also, it does not get put into the dcache hash if DCACHE_UNHASHED is clear;
that depends on the filesystem calling d_add or d_rehash.

So delete the misleading comments and needless code.

Acked-by: Miklos Szeredi <mszeredi@suse.cz>
Signed-off-by: Nick Piggin <npiggin@suse.de>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2009-12-17 10:51:40 -05:00
Al Viro
2c48b9c455 switch alloc_file() to passing struct path
... and have the caller grab both mnt and dentry; kill
leak in infiniband, while we are at it.

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2009-12-16 12:16:42 -05:00
Al Viro
cc3808f8c3 switch sock_alloc_file() to alloc_file()
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2009-12-16 12:16:42 -05:00
Al Viro
7cbe66b6b5 merge sock_alloc_fd/sock_attach_fd into a new helper
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2009-12-16 12:16:41 -05:00
Al Viro
198de4d7ac reorder alloc_fd/attach_fd in socketpair()
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2009-12-16 12:16:41 -05:00
Jean-Mickael Guerin
d7256d0eb4 net: compat_mmsghdr must be used in sys_recvmmsg
Both to traverse the entries and to set the msg_len field.

Commiter note: folded two patches and avoided one branch repeating the
compat test.

Signed-off-by: Jean-Mickael Guerin <jean-mickael.guerin@6wind.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2009-12-02 01:23:23 -08:00
Arnd Bergmann
805003a41c net/atm: move all compat_ioctl handling to atm/ioctl.c
We have two implementations of the compat_ioctl handling for ATM, the
one that we have had for ages in fs/compat_ioctl.c and the one added to
net/atm/ioctl.c by David Woodhouse. Unfortunately, both versions are
incomplete, and in practice we use a very confusing combination of the
two.

For ioctl numbers that have the same identifier on 32 and 64 bit systems,
we go directly through the compat_ioctl socket operation, for those that

differ, we do a conversion in fs/compat_ioctl.c.

This patch moves both variants into the vcc_compat_ioctl() function,
while preserving the current behaviour. It also kills off the COMPATIBLE_IOCTL
definitions that we never use here.
Doing it this way is clearly not a good solution, but I hope it is a
step into the right direction, so that someone is able to clean up this
mess for real.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Cc: David Woodhouse <dwmw2@infradead.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2009-11-11 19:22:23 -08:00
Arnd Bergmann
a2116ed223 net/compat: fix dev_ifsioc emulation corner cases
Handling for SIOCSHWTSTAMP is broken on architectures
with a split user/kernel address space like s390,
because it passes a real user pointer while using
set_fs(KERNEL_DS).
A similar problem might arise the next time somebody
adds code to dev_ifsioc.

Split up dev_ifsioc into three separate functions for
SIOCSHWTSTAMP, SIOC*IFMAP and all other numbers so
we can get rid of set_fs in all potentially affected
cases.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Cc: Patrick Ohly <patrick.ohly@intel.com>
Cc: David S. Miller <davem@davemloft.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
2009-11-11 19:22:22 -08:00
Arnd Bergmann
7a50a240c4 net/compat_ioctl: support SIOCWANDEV
This adds compat_ioctl support for SIOCWANDEV, which has
always been missing.

The definition of struct compat_ifreq was missing an
ifru_settings fields that is needed to support SIOCWANDEV,
so add that and clean up the whitespace damage in the
struct definition.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
2009-11-08 20:57:03 -08:00
Arnd Bergmann
fab2532ba5 net, compat_ioctl: fix SIOCGMII ioctls
SIOCGMIIPHY and SIOCGMIIREG return data through ifreq,
so it needs to be converted on the way out as well.

SIOCGIFPFLAGS is unused, but has the same problem in theory.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
2009-11-08 20:56:21 -08:00
Arnd Bergmann
9177efd399 net, compat_ioctl: handle more ioctls correctly
The MII ioctls and SIOCSIFNAME need to go through ifsioc conversion,
which they never did so far. Some others are not implemented in the
native path, so we can just return -EINVAL directly.

Add IFSLAVE ioctls to the EINVAL list and move it to the end to
optimize the code path for the common case.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
2009-11-06 23:11:15 -08:00
Arnd Bergmann
6b96018b28 compat: move sockios handling to net/socket.c
This removes the original socket compat_ioctl code
from fs/compat_ioctl.c and converts the code from the copy
in net/socket.c into a single function. We add a few cycles
of runtime to compat_sock_ioctl() with the long switch()
statement, but gain some cycles in return by simplifying
the call chain to get there.

Due to better inlining, save 1.5kb of object size in the
process, and enable further savings:

before:
   text    data     bss     dec     hex filename
  13540   18008    2080   33628    835c obj/fs/compat_ioctl.o
  14565     636      40   15241    3b89 obj/net/socket.o

after:
   text    data     bss     dec     hex filename
   8916   15176    2080   26172    663c obj/fs/compat_ioctl.o
  20725     636      40   21401    5399 obj/net/socket.o

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
2009-11-06 23:10:54 -08:00
Arnd Bergmann
7a229387d3 net: copy socket ioctl code to net/socket.h
This makes an identical copy of the socket compat_ioctl code
from fs/compat_ioctl.c to net/socket.c, as a preparation
for moving the functionality in a way that can be easily
reviewed.

The code is hidden inside of #if 0 and gets activated in the
patch that will make it work.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
2009-11-06 23:00:29 -08:00
Eric Paris
3f378b6844 net: pass kern to net_proto_family create function
The generic __sock_create function has a kern argument which allows the
security system to make decisions based on if a socket is being created by
the kernel or by userspace.  This patch passes that flag to the
net_proto_family specific create function, so it can do the same thing.

Signed-off-by: Eric Paris <eparis@redhat.com>
Acked-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2009-11-05 22:18:14 -08:00
Arnaldo Carvalho de Melo
a2e2725541 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.

. Rémi 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>
2009-10-12 23:40:10 -07:00
Neil Horman
3b885787ea net: Generalize socket rx gap / receive queue overflow cmsg
Create a new socket level option to report number of queue overflows

Recently I augmented the AF_PACKET protocol to report the number of frames lost
on the socket receive queue between any two enqueued frames.  This value was
exported via a SOL_PACKET level cmsg.  AFter I completed that work it was
requested that this feature be generalized so that any datagram oriented socket
could make use of this option.  As such I've created this patch, It creates a
new SOL_SOCKET level option called SO_RXQ_OVFL, which when enabled exports a
SOL_SOCKET level cmsg that reports the nubmer of times the sk_receive_queue
overflowed between any two given frames.  It also augments the AF_PACKET
protocol to take advantage of this new feature (as it previously did not touch
sk->sk_drops, which this patch uses to record the overflow count).  Tested
successfully by me.

Notes:

1) Unlike my previous patch, this patch simply records the sk_drops value, which
is not a number of drops between packets, but rather a total number of drops.
Deltas must be computed in user space.

2) While this patch currently works with datagram oriented protocols, it will
also be accepted by non-datagram oriented protocols. I'm not sure if thats
agreeable to everyone, but my argument in favor of doing so is that, for those
protocols which aren't applicable to this option, sk_drops will always be zero,
and reporting no drops on a receive queue that isn't used for those
non-participating protocols seems reasonable to me.  This also saves us having
to code in a per-protocol opt in mechanism.

3) This applies cleanly to net-next assuming that commit
977750076d (my af packet cmsg patch) is reverted

Signed-off-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2009-10-12 13:26:31 -07:00
David S. Miller
8aa0f64ac3 Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/linville/wireless-next-2.6 2009-10-09 14:40:09 -07:00
Johannes Berg
3d23e349d8 wext: refactor
Refactor wext to
 * split out iwpriv handling
 * split out iwspy handling
 * split out procfs support
 * allow cfg80211 to have wireless extensions compat code
   w/o CONFIG_WIRELESS_EXT

After this, drivers need to
 - select WIRELESS_EXT	- for wext support
 - select WEXT_PRIV	- for iwpriv support
 - select WEXT_SPY	- for iwspy support

except cfg80211 -- which gets new hooks in wext-core.c
and can then get wext handlers without CONFIG_WIRELESS_EXT.

Wireless extensions procfs support is auto-selected
based on PROC_FS and anything that requires the wext core
(i.e. WIRELESS_EXT or CFG80211_WEXT).

Signed-off-by: Johannes Berg <johannes@sipsolutions.net>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
2009-10-07 16:39:43 -04:00
Eric Dumazet
bcdce7195e net: speedup sk_wake_async()
An incoming datagram must bring into cpu cache *lot* of cache lines,
in particular : (other parts omitted (hash chains, ip route cache...))

On 32bit arches :

offsetof(struct sock, sk_rcvbuf)       =0x30    (read)
offsetof(struct sock, sk_lock)         =0x34   (rw)

offsetof(struct sock, sk_sleep)        =0x50 (read)
offsetof(struct sock, sk_rmem_alloc)   =0x64   (rw)
offsetof(struct sock, sk_receive_queue)=0x74   (rw)

offsetof(struct sock, sk_forward_alloc)=0x98   (rw)

offsetof(struct sock, sk_callback_lock)=0xcc    (rw)
offsetof(struct sock, sk_drops)        =0xd8 (read if we add dropcount support, rw if frame dropped)
offsetof(struct sock, sk_filter)       =0xf8    (read)

offsetof(struct sock, sk_socket)       =0x138 (read)

offsetof(struct sock, sk_data_ready)   =0x15c   (read)


We can avoid sk->sk_socket and socket->fasync_list referencing on sockets
with no fasync() structures. (socket->fasync_list ptr is probably already in cache
because it shares a cache line with socket->wait, ie location pointed by sk->sk_sleep)

This avoids one cache line load per incoming packet for common cases (no fasync())

We can leave (or even move in a future patch) sk->sk_socket in a cold location

Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2009-10-06 17:28:29 -07:00
David S. Miller
b7058842c9 net: Make setsockopt() optlen be unsigned.
This provides safety against negative optlen at the type
level instead of depending upon (sometimes non-trivial)
checks against this sprinkled all over the the place, in
each and every implementation.

Based upon work done by Arjan van de Ven and feedback
from Linus Torvalds.

Signed-off-by: David S. Miller <davem@davemloft.net>
2009-09-30 16:12:20 -07:00
Arjan van de Ven
47379052b5 net: Add explicit bound checks in net/socket.c
The sys_socketcall() function has a very clever system for the copy
size of its arguments. Unfortunately, gcc cannot deal with this in
terms of proving that the copy_from_user() is then always in bounds.
This is the last (well 9th of this series, but last in the kernel) such
case around.

With this patch, we can turn on code to make having the boundary provably
right for the whole kernel, and detect introduction of new security
accidents of this type early on.

Signed-off-by: Arjan van de Ven <arjan@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2009-09-28 12:57:44 -07:00
Nick Black
1fd7317d02 Move magic numbers into magic.h
Move various magic-number definitions into magic.h.

Signed-off-by: Nick Black <dank@qemfd.net>
Acked-by: Pekka Enberg <penberg@cs.helsinki.fi>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Casey Schaufler <casey@schaufler-ca.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-09-23 07:39:28 -07:00
Alexey Dobriyan
b87221de6a const: mark remaining super_operations const
Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-09-22 07:17:24 -07:00
Eric Dumazet
29a020d35f [PATCH] net: kmemcheck annotation in struct socket
struct socket has a 16 bit hole that triggers kmemcheck warnings.

As suggested by Ingo, use kmemcheck annotations

Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Acked-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: David S. Miller <davem@davemloft.net>
2009-09-15 02:39:20 -07:00
Linus Torvalds
e694958388 Make sock_sendpage() use kernel_sendpage()
kernel_sendpage() does the proper default case handling for when the
socket doesn't have a native sendpage implementation.

Now, arguably this might be something that we could instead solve by
just specifying that all protocols should do it themselves at the
protocol level, but we really only care about the common protocols.
Does anybody really care about sendpage on something like Appletalk? Not
likely.

Acked-by: David S. Miller <davem@davemloft.net>
Acked-by: Julien TINNES <julien@cr0.org>
Acked-by: Tavis Ormandy <taviso@sdf.lonestar.org>
Cc: stable@kernel.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-08-13 10:57:26 -07:00
Linus Torvalds
3989203290 Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-2.6
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-2.6:
  b44: Use kernel DMA addresses for the kernel DMA API
  forcedeth: Fix resume from hibernation regression.
  xfrm: fix fragmentation on inter family tunnels
  ibm_newemac: Fix dangerous struct assumption
  gigaset: documentation update
  gigaset: in file ops, check for device disconnect before anything else
  bas_gigaset: use tasklet_hi_schedule for timing critical tasklets
  net/802/fddi.c: add MODULE_LICENSE
  smsc911x: remove unused #include <linux/version.h>
  axnet_cs: fix phy_id detection for bogus Asix chip.
  bnx2: Use request_firmware()
  b44: Fix sizes passed to b44_sync_dma_desc_for_{device,cpu}()
  socket: use percpu_add() while updating sockets_in_use
  virtio_net: Set the mac config only when VIRITO_NET_F_MAC
  myri_sbus: use request_firmware
  e1000: fix loss of multicast packets
  vxge: should include tcp.h

Conflict in firmware/WHENCE (SCSI vs net firmware)
2009-04-06 18:05:43 -07:00
Eric Dumazet
4e69489a0a socket: use percpu_add() while updating sockets_in_use
sock_alloc() currently uses following code to update sockets_in_use

get_cpu_var(sockets_in_use)++;
put_cpu_var(sockets_in_use);

This translates to :

c0436274:       b8 01 00 00 00          mov    $0x1,%eax
c0436279:       e8 42 40 df ff          call   c022a2c0 <add_preempt_count>
c043627e:       bb 20 4f 6a c0          mov    $0xc06a4f20,%ebx
c0436283:       e8 18 ca f0 ff          call   c0342ca0 <debug_smp_processor_id>
c0436288:       03 1c 85 60 4a 65 c0    add    -0x3f9ab5a0(,%eax,4),%ebx
c043628f:       ff 03                   incl   (%ebx)
c0436291:       b8 01 00 00 00          mov    $0x1,%eax
c0436296:       e8 75 3f df ff          call   c022a210 <sub_preempt_count>
c043629b:       89 e0                   mov    %esp,%eax
c043629d:       25 00 e0 ff ff          and    $0xffffe000,%eax
c04362a2:       f6 40 08 08             testb  $0x8,0x8(%eax)
c04362a6:       75 07                   jne    c04362af <sock_alloc+0x7f>
c04362a8:       8d 46 d8                lea    -0x28(%esi),%eax
c04362ab:       5b                      pop    %ebx
c04362ac:       5e                      pop    %esi
c04362ad:       c9                      leave
c04362ae:       c3                      ret
c04362af:       e8 cc 5d 09 00          call   c04cc080 <preempt_schedule>
c04362b4:       8d 74 26 00             lea    0x0(%esi,%eiz,1),%esi
c04362b8:       eb ee                   jmp    c04362a8 <sock_alloc+0x78>

While percpu_add(sockets_in_use, 1) translates to a single instruction :

c0436275:   64 83 05 20 5f 6a c0    addl   $0x1,%fs:0xc06a5f20

Signed-off-by: Eric Dumazet <dada1@cosmosbay.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2009-04-04 16:41:09 -07:00
Paul Moore
8651d5c0b1 lsm: Remove the socket_post_accept() hook
The socket_post_accept() hook is not currently used by any in-tree modules
and its existence continues to cause problems by confusing people about
what can be safely accomplished using this hook.  If a legitimate need for
this hook arises in the future it can always be reintroduced.

Signed-off-by: Paul Moore <paul.moore@hp.com>
Signed-off-by: James Morris <jmorris@namei.org>
2009-03-28 15:01:37 +11:00
Linus Torvalds
3ae5080f4c Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs-2.6
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs-2.6: (37 commits)
  fs: avoid I_NEW inodes
  Merge code for single and multiple-instance mounts
  Remove get_init_pts_sb()
  Move common mknod_ptmx() calls into caller
  Parse mount options just once and copy them to super block
  Unroll essentials of do_remount_sb() into devpts
  vfs: simple_set_mnt() should return void
  fs: move bdev code out of buffer.c
  constify dentry_operations: rest
  constify dentry_operations: configfs
  constify dentry_operations: sysfs
  constify dentry_operations: JFS
  constify dentry_operations: OCFS2
  constify dentry_operations: GFS2
  constify dentry_operations: FAT
  constify dentry_operations: FUSE
  constify dentry_operations: procfs
  constify dentry_operations: ecryptfs
  constify dentry_operations: CIFS
  constify dentry_operations: AFS
  ...
2009-03-27 16:23:12 -07:00
Al Viro
3ba13d179e constify dentry_operations: rest
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2009-03-27 14:44:03 -04:00
Linus Torvalds
8e9d208972 Merge branch 'bkl-removal' of git://git.lwn.net/linux-2.6
* 'bkl-removal' of git://git.lwn.net/linux-2.6:
  Rationalize fasync return values
  Move FASYNC bit handling to f_op->fasync()
  Use f_lock to protect f_flags
  Rename struct file->f_ep_lock
2009-03-26 16:14:02 -07:00
Jonathan Corbet
76398425bb Move FASYNC bit handling to f_op->fasync()
Removing the BKL from FASYNC handling ran into the challenge of keeping the
setting of the FASYNC bit in filp->f_flags atomic with regard to calls to
the underlying fasync() function.  Andi Kleen suggested moving the handling
of that bit into fasync(); this patch does exactly that.  As a result, we
have a couple of internal API changes: fasync() must now manage the FASYNC
bit, and it will be called without the BKL held.

As it happens, every fasync() implementation in the kernel with one
exception calls fasync_helper().  So, if we make fasync_helper() set the
FASYNC bit, we can avoid making any changes to the other fasync()
functions - as long as those functions, themselves, have proper locking.
Most fasync() implementations do nothing but call fasync_helper() - which
has its own lock - so they are easily verified as correct.  The BKL had
already been pushed down into the rest.

The networking code has its own version of fasync_helper(), so that code
has been augmented with explicit FASYNC bit handling.

Cc: Al Viro <viro@ZenIV.linux.org.uk>
Cc: David Miller <davem@davemloft.net>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jonathan Corbet <corbet@lwn.net>
2009-03-16 08:32:27 -06:00
Patrick Ohly
20d4947353 net: socket infrastructure for SO_TIMESTAMPING
The overlap with the old SO_TIMESTAMP[NS] options is handled so
that time stamping in software (net_enable_timestamp()) is
enabled when SO_TIMESTAMP[NS] and/or SO_TIMESTAMPING_RX_SOFTWARE
is set.  It's disabled if all of these are off.

Signed-off-by: Patrick Ohly <patrick.ohly@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2009-02-15 22:43:35 -08:00
Heiko Carstens
3e0fa65f8b [CVE-2009-0029] System call wrappers part 22
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
2009-01-14 14:15:27 +01:00
Heiko Carstens
20f37034fb [CVE-2009-0029] System call wrappers part 21
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
2009-01-14 14:15:26 +01:00
Heiko Carstens
754fe8d297 [CVE-2009-0029] System call wrappers part 07
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
2009-01-14 14:15:20 +01:00
Al Viro
157cf649a7 sanitize audit_fd_pair()
* no allocations
* return void

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2009-01-04 15:14:41 -05:00
Al Viro
f3298dc4f2 sanitize audit_socketcall
* don't bother with allocations
* now that it can't fail, make it return void

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2009-01-04 15:14:39 -05:00
Linus Torvalds
0191b625ca Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next-2.6
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next-2.6: (1429 commits)
  net: Allow dependancies of FDDI & Tokenring to be modular.
  igb: Fix build warning when DCA is disabled.
  net: Fix warning fallout from recent NAPI interface changes.
  gro: Fix potential use after free
  sfc: If AN is enabled, always read speed/duplex from the AN advertising bits
  sfc: When disabling the NIC, close the device rather than unregistering it
  sfc: SFT9001: Add cable diagnostics
  sfc: Add support for multiple PHY self-tests
  sfc: Merge top-level functions for self-tests
  sfc: Clean up PHY mode management in loopback self-test
  sfc: Fix unreliable link detection in some loopback modes
  sfc: Generate unique names for per-NIC workqueues
  802.3ad: use standard ethhdr instead of ad_header
  802.3ad: generalize out mac address initializer
  802.3ad: initialize ports LACPDU from const initializer
  802.3ad: remove typedef around ad_system
  802.3ad: turn ports is_individual into a bool
  802.3ad: turn ports is_enabled into a bool
  802.3ad: make ntt bool
  ixgbe: Fix set_ringparam in ixgbe to use the same memory pools.
  ...

Fixed trivial IPv4/6 address printing conflicts in fs/cifs/connect.c due
to the conversion to %pI (in this networking merge) and the addition of
doing IPv6 addresses (from the earlier merge of CIFS).
2008-12-28 12:49:40 -08:00