37 Коммитов
| Автор | SHA1 | Сообщение | Дата |
|---|---|---|---|
Anton Blanchard
|
228e548e60 |
net: Add sendmmsg socket system call
This patch adds a multiple message send syscall and is the send
version of the existing recvmmsg syscall. This is heavily
based on the patch by Arnaldo that added recvmmsg.
I wrote a microbenchmark to test the performance gains of using
this new syscall:
http://ozlabs.org/~anton/junkcode/sendmmsg_test.c
The test was run on a ppc64 box with a 10 Gbit network card. The
benchmark can send both UDP and RAW ethernet packets.
64B UDP
batch pkts/sec
1 804570
2 872800 (+ 8 %)
4 916556 (+14 %)
8 939712 (+17 %)
16 952688 (+18 %)
32 956448 (+19 %)
64 964800 (+20 %)
64B raw socket
batch pkts/sec
1 1201449
2 1350028 (+12 %)
4 1461416 (+22 %)
8
|
|
David S. Miller
|
8acfe468b0 |
net: Limit socket I/O iovec total length to INT_MAX.
This helps protect us from overflow issues down in the individual protocol sendmsg/recvmsg handlers. Once we hit INT_MAX we truncate out the rest of the iovec by setting the iov_len members to zero. This works because: 1) For SOCK_STREAM and SOCK_SEQPACKET sockets, partial writes are allowed and the application will just continue with another write to send the rest of the data. 2) For datagram oriented sockets, where there must be a one-to-one correspondance between write() calls and packets on the wire, INT_MAX is going to be far larger than the packet size limit the protocol is going to check for and signal with -EMSGSIZE. Based upon a patch by Linus Torvalds. Signed-off-by: David S. Miller <davem@davemloft.net> |
|
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
|
|
|
Eric Dumazet
|
bc10502dba |
net: use __packed annotation
cleanup patch. Use new __packed annotation in net/ and include/ (except netfilter) Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net> |
|
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> |
|
Heiko Carstens
|
de039f02d8 |
net: use compat helper functions in compat_sys_recvmmsg
Use (get|put)_compat_timespec helper functions to simplify the code. Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com> Acked-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net> |
|
|
Heiko Carstens
|
60c2ffd3d2 |
net: fix compat_sys_recvmmsg parameter type
compat_sys_recvmmsg has a compat_timespec parameter and not a timespec parameter. This way we also get rid of an odd cast. Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com> Acked-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net> |
|
Jean-Mickael Guerin
|
5b23136bcf |
net: compat_sys_recvmmsg user timespec arg can be NULL
We must test if user timespec is non-NULL before copying from userpace, same as sys_recvmmsg(). Commiter note: changed it so that we have just one branch. 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> |
|
roel kluin
|
65a1c4fffa |
net: Cleanup redundant tests on unsigned
optlen is unsigned so the `< 0' test is never true. Signed-off-by: Roel Kluin <roel.kluin@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net> |
|
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> |
|
|
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> |
|
Johannes Berg
|
1dacc76d00 |
net/compat/wext: send different messages to compat tasks
Wireless extensions have the unfortunate problem that events are multicast netlink messages, and are not independent of pointer size. Thus, currently 32-bit tasks on 64-bit platforms cannot properly receive events and fail with all kinds of strange problems, for instance wpa_supplicant never notices disassociations, due to the way the 64-bit event looks (to a 32-bit process), the fact that the address is all zeroes is lost, it thinks instead it is 00:00:00:00:01:00. The same problem existed with the ioctls, until David Miller fixed those some time ago in an heroic effort. A different problem caused by this is that we cannot send the ASSOCREQIE/ASSOCRESPIE events because sending them causes a 32-bit wpa_supplicant on a 64-bit system to overwrite its internal information, which is worse than it not getting the information at all -- so we currently resort to sending a custom string event that it then parses. This, however, has a severe size limitation we are frequently hitting with modern access points; this limitation would can be lifted after this patch by sending the correct binary, not custom, event. A similar problem apparently happens for some other netlink users on x86_64 with 32-bit tasks due to the alignment for 64-bit quantities. In order to fix these problems, I have implemented a way to send compat messages to tasks. When sending an event, we send the non-compat event data together with a compat event data in skb_shinfo(main_skb)->frag_list. Then, when the event is read from the socket, the netlink code makes sure to pass out only the skb that is compatible with the task. This approach was suggested by David Miller, my original approach required always sending two skbs but that had various small problems. To determine whether compat is needed or not, I have used the MSG_CMSG_COMPAT flag, and adjusted the call path for recv and recvfrom to include it, even if those calls do not have a cmsg parameter. I have not solved one small part of the problem, and I don't think it is necessary to: if a 32-bit application uses read() rather than any form of recvmsg() it will still get the wrong (64-bit) event. However, neither do applications actually do this, nor would it be a regression. Signed-off-by: Johannes Berg <johannes@sipsolutions.net> Signed-off-by: David S. Miller <davem@davemloft.net> |
|
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> |
|
Ulrich Drepper
|
de11defebf |
reintroduce accept4
Introduce a new accept4() system call. The addition of this system call matches analogous changes in 2.6.27 (dup3(), evenfd2(), signalfd4(), inotify_init1(), epoll_create1(), pipe2()) which added new system calls that differed from analogous traditional system calls in adding a flags argument that can be used to access additional functionality. The accept4() system call is exactly the same as accept(), except that it adds a flags bit-mask argument. Two flags are initially implemented. (Most of the new system calls in 2.6.27 also had both of these flags.) SOCK_CLOEXEC causes the close-on-exec (FD_CLOEXEC) flag to be enabled for the new file descriptor returned by accept4(). This is a useful security feature to avoid leaking information in a multithreaded program where one thread is doing an accept() at the same time as another thread is doing a fork() plus exec(). More details here: http://udrepper.livejournal.com/20407.html "Secure File Descriptor Handling", Ulrich Drepper). The other flag is SOCK_NONBLOCK, which causes the O_NONBLOCK flag to be enabled on the new open file description created by accept4(). (This flag is merely a convenience, saving the use of additional calls fcntl(F_GETFL) and fcntl (F_SETFL) to achieve the same result. Here's a test program. Works on x86-32. Should work on x86-64, but I (mtk) don't have a system to hand to test with. It tests accept4() with each of the four possible combinations of SOCK_CLOEXEC and SOCK_NONBLOCK set/clear in 'flags', and verifies that the appropriate flags are set on the file descriptor/open file description returned by accept4(). I tested Ulrich's patch in this thread by applying against 2.6.28-rc2, and it passes according to my test program. /* test_accept4.c Copyright (C) 2008, Linux Foundation, written by Michael Kerrisk <mtk.manpages@gmail.com> Licensed under the GNU GPLv2 or later. */ #define _GNU_SOURCE #include <unistd.h> #include <sys/syscall.h> #include <sys/socket.h> #include <netinet/in.h> #include <stdlib.h> #include <fcntl.h> #include <stdio.h> #include <string.h> #define PORT_NUM 33333 #define die(msg) do { perror(msg); exit(EXIT_FAILURE); } while (0) /**********************************************************************/ /* The following is what we need until glibc gets a wrapper for accept4() */ /* Flags for socket(), socketpair(), accept4() */ #ifndef SOCK_CLOEXEC #define SOCK_CLOEXEC O_CLOEXEC #endif #ifndef SOCK_NONBLOCK #define SOCK_NONBLOCK O_NONBLOCK #endif #ifdef __x86_64__ #define SYS_accept4 288 #elif __i386__ #define USE_SOCKETCALL 1 #define SYS_ACCEPT4 18 #else #error "Sorry -- don't know the syscall # on this architecture" #endif static int accept4(int fd, struct sockaddr *sockaddr, socklen_t *addrlen, int flags) { printf("Calling accept4(): flags = %x", flags); if (flags != 0) { printf(" ("); if (flags & SOCK_CLOEXEC) printf("SOCK_CLOEXEC"); if ((flags & SOCK_CLOEXEC) && (flags & SOCK_NONBLOCK)) printf(" "); if (flags & SOCK_NONBLOCK) printf("SOCK_NONBLOCK"); printf(")"); } printf("\n"); #if USE_SOCKETCALL long args[6]; args[0] = fd; args[1] = (long) sockaddr; args[2] = (long) addrlen; args[3] = flags; return syscall(SYS_socketcall, SYS_ACCEPT4, args); #else return syscall(SYS_accept4, fd, sockaddr, addrlen, flags); #endif } /**********************************************************************/ static int do_test(int lfd, struct sockaddr_in *conn_addr, int closeonexec_flag, int nonblock_flag) { int connfd, acceptfd; int fdf, flf, fdf_pass, flf_pass; struct sockaddr_in claddr; socklen_t addrlen; printf("=======================================\n"); connfd = socket(AF_INET, SOCK_STREAM, 0); if (connfd == -1) die("socket"); if (connect(connfd, (struct sockaddr *) conn_addr, sizeof(struct sockaddr_in)) == -1) die("connect"); addrlen = sizeof(struct sockaddr_in); acceptfd = accept4(lfd, (struct sockaddr *) &claddr, &addrlen, closeonexec_flag | nonblock_flag); if (acceptfd == -1) { perror("accept4()"); close(connfd); return 0; } fdf = fcntl(acceptfd, F_GETFD); if (fdf == -1) die("fcntl:F_GETFD"); fdf_pass = ((fdf & FD_CLOEXEC) != 0) == ((closeonexec_flag & SOCK_CLOEXEC) != 0); printf("Close-on-exec flag is %sset (%s); ", (fdf & FD_CLOEXEC) ? "" : "not ", fdf_pass ? "OK" : "failed"); flf = fcntl(acceptfd, F_GETFL); if (flf == -1) die("fcntl:F_GETFD"); flf_pass = ((flf & O_NONBLOCK) != 0) == ((nonblock_flag & SOCK_NONBLOCK) !=0); printf("nonblock flag is %sset (%s)\n", (flf & O_NONBLOCK) ? "" : "not ", flf_pass ? "OK" : "failed"); close(acceptfd); close(connfd); printf("Test result: %s\n", (fdf_pass && flf_pass) ? "PASS" : "FAIL"); return fdf_pass && flf_pass; } static int create_listening_socket(int port_num) { struct sockaddr_in svaddr; int lfd; int optval; memset(&svaddr, 0, sizeof(struct sockaddr_in)); svaddr.sin_family = AF_INET; svaddr.sin_addr.s_addr = htonl(INADDR_ANY); svaddr.sin_port = htons(port_num); lfd = socket(AF_INET, SOCK_STREAM, 0); if (lfd == -1) die("socket"); optval = 1; if (setsockopt(lfd, SOL_SOCKET, SO_REUSEADDR, &optval, sizeof(optval)) == -1) die("setsockopt"); if (bind(lfd, (struct sockaddr *) &svaddr, sizeof(struct sockaddr_in)) == -1) die("bind"); if (listen(lfd, 5) == -1) die("listen"); return lfd; } int main(int argc, char *argv[]) { struct sockaddr_in conn_addr; int lfd; int port_num; int passed; passed = 1; port_num = (argc > 1) ? atoi(argv[1]) : PORT_NUM; memset(&conn_addr, 0, sizeof(struct sockaddr_in)); conn_addr.sin_family = AF_INET; conn_addr.sin_addr.s_addr = htonl(INADDR_LOOPBACK); conn_addr.sin_port = htons(port_num); lfd = create_listening_socket(port_num); if (!do_test(lfd, &conn_addr, 0, 0)) passed = 0; if (!do_test(lfd, &conn_addr, SOCK_CLOEXEC, 0)) passed = 0; if (!do_test(lfd, &conn_addr, 0, SOCK_NONBLOCK)) passed = 0; if (!do_test(lfd, &conn_addr, SOCK_CLOEXEC, SOCK_NONBLOCK)) passed = 0; close(lfd); exit(passed ? EXIT_SUCCESS : EXIT_FAILURE); } [mtk.manpages@gmail.com: rewrote changelog, updated test program] Signed-off-by: Ulrich Drepper <drepper@redhat.com> Tested-by: Michael Kerrisk <mtk.manpages@gmail.com> Acked-by: Michael Kerrisk <mtk.manpages@gmail.com> Cc: <linux-api@vger.kernel.org> Cc: <linux-arch@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> |
|
|
Patrick Ohly
|
d35aac10eb |
net: put_cmsg_compat + SO_TIMESTAMP[NS]: use same name for value as caller
In __sock_recv_timestamp() the additional SCM_TIMESTAMP[NS] is used. This has the same value as SO_TIMESTAMP[NS], so this is a purely cosmetic change. Signed-off-by: Patrick Ohly <patrick.ohly@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net> |
|
|
Ulrich Drepper
|
aaca0bdca5 |
flag parameters: paccept
This patch is by far the most complex in the series. It adds a new syscall
paccept. This syscall differs from accept in that it adds (at the userlevel)
two additional parameters:
- a signal mask
- a flags value
The flags parameter can be used to set flag like SOCK_CLOEXEC. This is
imlpemented here as well. Some people argued that this is a property which
should be inherited from the file desriptor for the server but this is against
POSIX. Additionally, we really want the signal mask parameter as well
(similar to pselect, ppoll, etc). So an interface change in inevitable.
The flag value is the same as for socket and socketpair. I think diverging
here will only create confusion. Similar to the filesystem interfaces where
the use of the O_* constants differs, it is acceptable here.
The signal mask is handled as for pselect etc. The mask is temporarily
installed for the thread and removed before the call returns. I modeled the
code after pselect. If there is a problem it's likely also in pselect.
For architectures which use socketcall I maintained this interface instead of
adding a system call. The symmetry shouldn't be broken.
The following test must be adjusted for architectures other than x86 and
x86-64 and in case the syscall numbers changed.
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
#include <errno.h>
#include <fcntl.h>
#include <pthread.h>
#include <signal.h>
#include <stdio.h>
#include <unistd.h>
#include <netinet/in.h>
#include <sys/socket.h>
#include <sys/syscall.h>
#ifndef __NR_paccept
# ifdef __x86_64__
# define __NR_paccept 288
# elif defined __i386__
# define SYS_PACCEPT 18
# define USE_SOCKETCALL 1
# else
# error "need __NR_paccept"
# endif
#endif
#ifdef USE_SOCKETCALL
# define paccept(fd, addr, addrlen, mask, flags) \
({ long args[6] = { \
(long) fd, (long) addr, (long) addrlen, (long) mask, 8, (long) flags }; \
syscall (__NR_socketcall, SYS_PACCEPT, args); })
#else
# define paccept(fd, addr, addrlen, mask, flags) \
syscall (__NR_paccept, fd, addr, addrlen, mask, 8, flags)
#endif
#define PORT 57392
#define SOCK_CLOEXEC O_CLOEXEC
static pthread_barrier_t b;
static void *
tf (void *arg)
{
pthread_barrier_wait (&b);
int s = socket (AF_INET, SOCK_STREAM, 0);
struct sockaddr_in sin;
sin.sin_family = AF_INET;
sin.sin_addr.s_addr = htonl (INADDR_LOOPBACK);
sin.sin_port = htons (PORT);
connect (s, (const struct sockaddr *) &sin, sizeof (sin));
close (s);
pthread_barrier_wait (&b);
s = socket (AF_INET, SOCK_STREAM, 0);
sin.sin_port = htons (PORT);
connect (s, (const struct sockaddr *) &sin, sizeof (sin));
close (s);
pthread_barrier_wait (&b);
pthread_barrier_wait (&b);
sleep (2);
pthread_kill ((pthread_t) arg, SIGUSR1);
return NULL;
}
static void
handler (int s)
{
}
int
main (void)
{
pthread_barrier_init (&b, NULL, 2);
struct sockaddr_in sin;
pthread_t th;
if (pthread_create (&th, NULL, tf, (void *) pthread_self ()) != 0)
{
puts ("pthread_create failed");
return 1;
}
int s = socket (AF_INET, SOCK_STREAM, 0);
int reuse = 1;
setsockopt (s, SOL_SOCKET, SO_REUSEADDR, &reuse, sizeof (reuse));
sin.sin_family = AF_INET;
sin.sin_addr.s_addr = htonl (INADDR_LOOPBACK);
sin.sin_port = htons (PORT);
bind (s, (struct sockaddr *) &sin, sizeof (sin));
listen (s, SOMAXCONN);
pthread_barrier_wait (&b);
int s2 = paccept (s, NULL, 0, NULL, 0);
if (s2 < 0)
{
puts ("paccept(0) failed");
return 1;
}
int coe = fcntl (s2, F_GETFD);
if (coe & FD_CLOEXEC)
{
puts ("paccept(0) set close-on-exec-flag");
return 1;
}
close (s2);
pthread_barrier_wait (&b);
s2 = paccept (s, NULL, 0, NULL, SOCK_CLOEXEC);
if (s2 < 0)
{
puts ("paccept(SOCK_CLOEXEC) failed");
return 1;
}
coe = fcntl (s2, F_GETFD);
if ((coe & FD_CLOEXEC) == 0)
{
puts ("paccept(SOCK_CLOEXEC) does not set close-on-exec flag");
return 1;
}
close (s2);
pthread_barrier_wait (&b);
struct sigaction sa;
sa.sa_handler = handler;
sa.sa_flags = 0;
sigemptyset (&sa.sa_mask);
sigaction (SIGUSR1, &sa, NULL);
sigset_t ss;
pthread_sigmask (SIG_SETMASK, NULL, &ss);
sigaddset (&ss, SIGUSR1);
pthread_sigmask (SIG_SETMASK, &ss, NULL);
sigdelset (&ss, SIGUSR1);
alarm (4);
pthread_barrier_wait (&b);
errno = 0 ;
s2 = paccept (s, NULL, 0, &ss, 0);
if (s2 != -1 || errno != EINTR)
{
puts ("paccept did not fail with EINTR");
return 1;
}
close (s);
puts ("OK");
return 0;
}
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
[akpm@linux-foundation.org: make it compile]
[akpm@linux-foundation.org: add sys_ni stub]
Signed-off-by: Ulrich Drepper <drepper@redhat.com>
Acked-by: Davide Libenzi <davidel@xmailserver.org>
Cc: Michael Kerrisk <mtk.manpages@googlemail.com>
Cc: <linux-arch@vger.kernel.org>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Roland McGrath <roland@redhat.com>
Cc: Kyle McMartin <kyle@mcmartin.ca>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
|
|
YOSHIFUJI Hideaki
|
230b183921 |
net: Use standard structures for generic socket address structures.
Use sockaddr_storage{} for generic socket address storage
and ensures proper alignment.
Use sockaddr{} for pointers to omit several casts.
Signed-off-by: YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
David L Stevens
|
42908c69f6 |
net: Add compat support for getsockopt (MCAST_MSFILTER)
This patch adds support for getsockopt for MCAST_MSFILTER for both IPv4 and IPv6. It depends on the previous setsockopt patch, and uses the same method. Signed-off-by: David L Stevens <dlstevens@us.ibm.com> Signed-off-by: YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org> Signed-off-by: David S. Miller <davem@davemloft.net> |
|
|
David L Stevens
|
be666e0a13 |
net: Several cleanups for the setsockopt compat support.
1) added missing "__user" for kgsr and kgf pointers
2) verify read for only GROUP_FILTER_SIZE(0). The group_filter
structure definition (via RFC) includes space for one source
in the source list array, but that source need not be present.
So, sizeof(group_filter) > GROUP_FILTER_SIZE(0). Fixed
the user read-check for minimum length to use the smaller size.
3) remove unneeded "&" for gf_slist addresses
Signed-off-by: David L Stevens <dlstevens@us.ibm.com>
Signed-off-by: YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
|
David L Stevens
|
dae5029548 |
ipv4/ipv6 compat: Fix SSM applications on 64bit kernels.
Add support on 64-bit kernels for seting 32-bit compatible MCAST* socket options. Signed-off-by: David L Stevens <dlstevens@us.ibm.com> Signed-off-by: David S. Miller <davem@davemloft.net> |
|
Patrick McHardy
|
3bc3fe5eed |
[NETFILTER]: ip6_tables: add compat support
Signed-off-by: Patrick McHardy <kaber@trash.net> Signed-off-by: David S. Miller <davem@davemloft.net> |
|
|
Patrick McHardy
|
6e23ae2a48 |
[NETFILTER]: Introduce NF_INET_ hook values
The IPv4 and IPv6 hook values are identical, yet some code tries to figure out the "correct" value by looking at the address family. Introduce NF_INET_* values for both IPv4 and IPv6. The old values are kept in a #ifndef __KERNEL__ section for userspace compatibility. Signed-off-by: Patrick McHardy <kaber@trash.net> Acked-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net> |
|
Wei Yongjun
|
1ac70e7ad2 |
[NET]: Fix function put_cmsg() which may cause usr application memory overflow
When used function put_cmsg() to copy kernel information to user
application memory, if the memory length given by user application is
not enough, by the bad length calculate of msg.msg_controllen,
put_cmsg() function may cause the msg.msg_controllen to be a large
value, such as 0xFFFFFFF0, so the following put_cmsg() can also write
data to usr application memory even usr has no valid memory to store
this. This may cause usr application memory overflow.
int put_cmsg(struct msghdr * msg, int level, int type, int len, void *data)
{
struct cmsghdr __user *cm
= (__force struct cmsghdr __user *)msg->msg_control;
struct cmsghdr cmhdr;
int cmlen = CMSG_LEN(len);
~~~~~~~~~~~~~~~~~~~~~
int err;
if (MSG_CMSG_COMPAT & msg->msg_flags)
return put_cmsg_compat(msg, level, type, len, data);
if (cm==NULL || msg->msg_controllen < sizeof(*cm)) {
msg->msg_flags |= MSG_CTRUNC;
return 0; /* XXX: return error? check spec. */
}
if (msg->msg_controllen < cmlen) {
~~~~~~~~~~~~~~~~~~~~~~~~
msg->msg_flags |= MSG_CTRUNC;
cmlen = msg->msg_controllen;
}
cmhdr.cmsg_level = level;
cmhdr.cmsg_type = type;
cmhdr.cmsg_len = cmlen;
err = -EFAULT;
if (copy_to_user(cm, &cmhdr, sizeof cmhdr))
goto out;
if (copy_to_user(CMSG_DATA(cm), data, cmlen - sizeof(struct cmsghdr)))
goto out;
cmlen = CMSG_SPACE(len);
~~~~~~~~~~~~~~~~~~~~~~~~~~~
If MSG_CTRUNC flags is set, msg->msg_controllen is less than
CMSG_SPACE(len), "msg->msg_controllen -= cmlen" will cause unsinged int
type msg->msg_controllen to be a large value.
~~~~~~~~~~~~~~~~~~~~~~~~~~~
msg->msg_control += cmlen;
msg->msg_controllen -= cmlen;
~~~~~~~~~~~~~~~~~~~~~
err = 0;
out:
return err;
}
The same promble exists in put_cmsg_compat(). This patch can fix this
problem.
Signed-off-by: Wei Yongjun <yjwei@cn.fujitsu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
|
Ulrich Drepper
|
4a19542e5f |
O_CLOEXEC for SCM_RIGHTS
Part two in the O_CLOEXEC saga: adding support for file descriptors received
through Unix domain sockets.
The patch is once again pretty minimal, it introduces a new flag for recvmsg
and passes it just like the existing MSG_CMSG_COMPAT flag. I think this bit
is not used otherwise but the networking people will know better.
This new flag is not recognized by recvfrom and recv. These functions cannot
be used for that purpose and the asymmetry this introduces is not worse than
the already existing MSG_CMSG_COMPAT situations.
The patch must be applied on the patch which introduced O_CLOEXEC. It has to
remove static from the new get_unused_fd_flags function but since scm.c cannot
live in a module the function still hasn't to be exported.
Here's a test program to make sure the code works. It's so much longer than
the actual patch...
#include <errno.h>
#include <error.h>
#include <fcntl.h>
#include <stdio.h>
#include <string.h>
#include <unistd.h>
#include <sys/socket.h>
#include <sys/un.h>
#ifndef O_CLOEXEC
# define O_CLOEXEC 02000000
#endif
#ifndef MSG_CMSG_CLOEXEC
# define MSG_CMSG_CLOEXEC 0x40000000
#endif
int
main (int argc, char *argv[])
{
if (argc > 1)
{
int fd = atol (argv[1]);
printf ("child: fd = %d\n", fd);
if (fcntl (fd, F_GETFD) == 0 || errno != EBADF)
{
puts ("file descriptor valid in child");
return 1;
}
return 0;
}
struct sockaddr_un sun;
strcpy (sun.sun_path, "./testsocket");
sun.sun_family = AF_UNIX;
char databuf[] = "hello";
struct iovec iov[1];
iov[0].iov_base = databuf;
iov[0].iov_len = sizeof (databuf);
union
{
struct cmsghdr hdr;
char bytes[CMSG_SPACE (sizeof (int))];
} buf;
struct msghdr msg = { .msg_iov = iov, .msg_iovlen = 1,
.msg_control = buf.bytes,
.msg_controllen = sizeof (buf) };
struct cmsghdr *cmsg = CMSG_FIRSTHDR (&msg);
cmsg->cmsg_level = SOL_SOCKET;
cmsg->cmsg_type = SCM_RIGHTS;
cmsg->cmsg_len = CMSG_LEN (sizeof (int));
msg.msg_controllen = cmsg->cmsg_len;
pid_t child = fork ();
if (child == -1)
error (1, errno, "fork");
if (child == 0)
{
int sock = socket (PF_UNIX, SOCK_STREAM, 0);
if (sock < 0)
error (1, errno, "socket");
if (bind (sock, (struct sockaddr *) &sun, sizeof (sun)) < 0)
error (1, errno, "bind");
if (listen (sock, SOMAXCONN) < 0)
error (1, errno, "listen");
int conn = accept (sock, NULL, NULL);
if (conn == -1)
error (1, errno, "accept");
*(int *) CMSG_DATA (cmsg) = sock;
if (sendmsg (conn, &msg, MSG_NOSIGNAL) < 0)
error (1, errno, "sendmsg");
return 0;
}
/* For a test suite this should be more robust like a
barrier in shared memory. */
sleep (1);
int sock = socket (PF_UNIX, SOCK_STREAM, 0);
if (sock < 0)
error (1, errno, "socket");
if (connect (sock, (struct sockaddr *) &sun, sizeof (sun)) < 0)
error (1, errno, "connect");
unlink (sun.sun_path);
*(int *) CMSG_DATA (cmsg) = -1;
if (recvmsg (sock, &msg, MSG_CMSG_CLOEXEC) < 0)
error (1, errno, "recvmsg");
int fd = *(int *) CMSG_DATA (cmsg);
if (fd == -1)
error (1, 0, "no descriptor received");
char fdname[20];
snprintf (fdname, sizeof (fdname), "%d", fd);
execl ("/proc/self/exe", argv[0], fdname, NULL);
puts ("execl failed");
return 1;
}
[akpm@linux-foundation.org: Fix fastcall inconsistency noted by Michael Buesch]
[akpm@linux-foundation.org: build fix]
Signed-off-by: Ulrich Drepper <drepper@redhat.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Michael Buesch <mb@bu3sch.de>
Cc: Michael Kerrisk <mtk-manpages@gmx.net>
Acked-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
|
|
Eric Dumazet
|
92f37fd2ee |
[NET]: Adding SO_TIMESTAMPNS / SCM_TIMESTAMPNS support
Now that network timestamps use ktime_t infrastructure, we can add a new SOL_SOCKET sockopt SO_TIMESTAMPNS. This command is similar to SO_TIMESTAMP, but permits transmission of a 'timespec struct' instead of a 'timeval struct' control message. (nanosecond resolution instead of microsecond) Control message is labelled SCM_TIMESTAMPNS instead of SCM_TIMESTAMP A socket cannot mix SO_TIMESTAMP and SO_TIMESTAMPNS : the two modes are mutually exclusive. sock_recv_timestamp() became too big to be fully inlined so I added a __sock_recv_timestamp() helper function. Signed-off-by: Eric Dumazet <dada1@cosmosbay.com> CC: linux-arch@vger.kernel.org Signed-off-by: David S. Miller <davem@davemloft.net> |
|
Stephen Hemminger
|
e71a4783aa |
[NET] core: whitespace cleanup
Fix whitespace around keywords. Fix indentation especially of switch statements. Signed-off-by: Stephen Hemminger <shemminger@linux-foundation.org> Signed-off-by: David S. Miller <davem@davemloft.net> |
|
|
Eric Dumazet
|
ae40eb1ef3 |
[NET]: Introduce SIOCGSTAMPNS ioctl to get timestamps with nanosec resolution
Now network timestamps use ktime_t infrastructure, we can add a new ioctl() SIOCGSTAMPNS command to get timestamps in 'struct timespec'. User programs can thus access to nanosecond resolution. Signed-off-by: Eric Dumazet <dada1@cosmosbay.com> CC: Stephen Hemminger <shemminger@linux-foundation.org> Signed-off-by: David S. Miller <davem@davemloft.net> |
|
|
Eric Dumazet
|
b7aa0bf70c |
[NET]: convert network timestamps to ktime_t
We currently use a special structure (struct skb_timeval) and plain 'struct timeval' to store packet timestamps in sk_buffs and struct sock. This has some drawbacks : - Fixed resolution of micro second. - Waste of space on 64bit platforms where sizeof(struct timeval)=16 I suggest using ktime_t that is a nice abstraction of high resolution time services, currently capable of nanosecond resolution. As sizeof(ktime_t) is 8 bytes, using ktime_t in 'struct sock' permits a 8 byte shrink of this structure on 64bit architectures. Some other structures also benefit from this size reduction (struct ipq in ipv4/ip_fragment.c, struct frag_queue in ipv6/reassembly.c, ...) Once this ktime infrastructure adopted, we can more easily provide nanosecond resolution on top of it. (ioctl SIOCGSTAMPNS and/or SO_TIMESTAMPNS/SCM_TIMESTAMPNS) Note : this patch includes a bug correction in compat_sock_get_timestamp() where a "err = 0;" was missing (so this syscall returned -ENOENT instead of 0) Signed-off-by: Eric Dumazet <dada1@cosmosbay.com> CC: Stephen Hemminger <shemminger@linux-foundation.org> CC: John find <linux.kernel@free.fr> Signed-off-by: David S. Miller <davem@davemloft.net> |
|
Tim Schmielau
|
cd354f1ae7 |
[PATCH] remove many unneeded #includes of sched.h
After Al Viro (finally) succeeded in removing the sched.h #include in module.h recently, it makes sense again to remove other superfluous sched.h includes. There are quite a lot of files which include it but don't actually need anything defined in there. Presumably these includes were once needed for macros that used to live in sched.h, but moved to other header files in the course of cleaning it up. To ease the pain, this time I did not fiddle with any header files and only removed #includes from .c-files, which tend to cause less trouble. Compile tested against 2.6.20-rc2 and 2.6.20-rc2-mm2 (with offsets) on alpha, arm, i386, ia64, mips, powerpc, and x86_64 with allnoconfig, defconfig, allmodconfig, and allyesconfig as well as a few randconfigs on x86_64 and all configs in arch/arm/configs on arm. I also checked that no new warnings were introduced by the patch (actually, some warnings are removed that were emitted by unnecessarily included header files). Signed-off-by: Tim Schmielau <tim@physik3.uni-rostock.de> Acked-by: Russell King <rmk+kernel@arm.linux.org.uk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> |
|
|
YOSHIFUJI Hideaki
|
4768fbcbcf |
[NET]: Fix whitespace errors.
Signed-off-by: YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org> Signed-off-by: David S. Miller <davem@davemloft.net> |
|
Miklos Szeredi
|
effee6a000 |
[NET]: File descriptor loss while receiving SCM_RIGHTS
If more than one file descriptor was sent with an SCM_RIGHTS message, and on the receiving end, after installing a nonzero (but not all) file descritpors the process runs out of fds, then the already installed fds will be lost (userspace will have no way of knowing about them). The following patch makes sure, that at least the already installed fds are sent to userspace. It doesn't solve the issue of losing file descriptors in case of an EFAULT on the userspace buffer. Signed-off-by: Miklos Szeredi <miklos@szeredi.hu> Signed-off-by: David S. Miller <davem@davemloft.net> |
|
Dmitry Mishin
|
2722971cbe |
[NETFILTER]: iptables 32bit compat layer
This patch extends current iptables compatibility layer in order to get
32bit iptables to work on 64bit kernel. Current layer is insufficient due
to alignment checks both in kernel and user space tools.
Patch is for current net-2.6.17 with addition of move of ipt_entry_{match|
target} definitions to xt_entry_{match|target}.
Signed-off-by: Dmitry Mishin <dim@openvz.org>
Acked-off-by: Kirill Korotaev <dev@openvz.org>
Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Shaun Pereira
|
f0ac261441 |
[NET]: socket timestamp 32 bit handler for 64 bit kernel
Get socket timestamp handler function that does not use the ioctl32_hash_table. Signed-off-by: Shaun Pereira <spereira@tusc.com.au> Acked-by: Arnd Bergmann <arnd@arndb.de> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: David S. Miller <davem@davemloft.net> |
|
|
Dmitry Mishin
|
3fdadf7d27 |
[NET]: {get|set}sockopt compatibility layer
This patch extends {get|set}sockopt compatibility layer in order to
move protocol specific parts to their place and avoid huge universal
net/compat.c file in the future.
Signed-off-by: Dmitry Mishin <dim@openvz.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Al Viro
|
8920e8f94c |
[PATCH] Fix 32bit sendmsg() flaw
When we copy 32bit ->msg_control contents to kernel, we walk the same userland data twice without sanity checks on the second pass. Second version of this patch: the original broke with 64-bit arches running 32-bit-compat-mode executables doing sendmsg() syscalls with unaligned CMSG data areas Another thing is that we use kmalloc() to allocate and sock_kfree_s() to free afterwards; less serious, but also needs fixing. Signed-off-by: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: David Woodhouse <dwmw2@infradead.org> Signed-off-by: Chris Wright <chrisw@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org> |
|
Andrew Morton
|
d64d387372 |
[NET]: Fix memory leak in sys_{send,recv}msg() w/compat
From: Dave Johnson <djohnson+linux-kernel@sw.starentnetworks.com> sendmsg()/recvmsg() syscalls from o32/n32 apps to a 64bit kernel will cause a kernel memory leak if iov_len > UIO_FASTIOV for each syscall! This is because both sys_sendmsg() and verify_compat_iovec() kmalloc a new iovec structure. Only the one from sys_sendmsg() is free'ed. I wrote a simple test program to confirm this after identifying the problem: http://davej.org/programs/testsendmsg.c Note that the below fix will break solaris_sendmsg()/solaris_recvmsg() as it also calls verify_compat_iovec() but expects it to malloc internally. [ I fixed that. -DaveM ] Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: David S. Miller <davem@davemloft.net> |
|
Linus Torvalds
|
1da177e4c3 |
Linux-2.6.12-rc2
Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip! |