#include <linux/cache.h>
#include <linux/module.h>
#include <linux/highmem.h>
-#include <linux/divert.h>
#include <linux/mount.h>
#include <linux/security.h>
#include <linux/syscalls.h>
#include <linux/kmod.h>
#include <linux/audit.h>
#include <linux/wireless.h>
+#include <linux/nsproxy.h>
#include <asm/uaccess.h>
#include <asm/unistd.h>
#include <linux/netfilter.h>
static int sock_no_open(struct inode *irrelevant, struct file *dontcare);
-static ssize_t sock_aio_read(struct kiocb *iocb, char __user *buf,
- size_t size, loff_t pos);
-static ssize_t sock_aio_write(struct kiocb *iocb, const char __user *buf,
- size_t size, loff_t pos);
+static ssize_t sock_aio_read(struct kiocb *iocb, const struct iovec *iov,
+ unsigned long nr_segs, loff_t pos);
+static ssize_t sock_aio_write(struct kiocb *iocb, const struct iovec *iov,
+ unsigned long nr_segs, loff_t pos);
static int sock_mmap(struct file *file, struct vm_area_struct *vma);
static int sock_close(struct inode *inode, struct file *file);
unsigned int cmd, unsigned long arg);
#endif
static int sock_fasync(int fd, struct file *filp, int on);
-static ssize_t sock_readv(struct file *file, const struct iovec *vector,
- unsigned long count, loff_t *ppos);
-static ssize_t sock_writev(struct file *file, const struct iovec *vector,
- unsigned long count, loff_t *ppos);
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,
+ unsigned int flags);
/*
* Socket files have a set of 'special' operations as well as the generic file ones. These don't appear
* in the operation structures but are done directly via the socketcall() multiplexor.
*/
-static struct file_operations socket_file_ops = {
+static const struct file_operations socket_file_ops = {
.owner = THIS_MODULE,
.llseek = no_llseek,
.aio_read = sock_aio_read,
.open = sock_no_open, /* special open code to disallow open via /proc */
.release = sock_close,
.fasync = sock_fasync,
- .readv = sock_readv,
- .writev = sock_writev,
.sendpage = sock_sendpage,
.splice_write = generic_splice_sendpage,
+ .splice_read = sock_splice_read,
};
/*
#define SOCKFS_MAGIC 0x534F434B
-static kmem_cache_t *sock_inode_cachep __read_mostly;
+static struct kmem_cache *sock_inode_cachep __read_mostly;
static struct inode *sock_alloc_inode(struct super_block *sb)
{
struct socket_alloc *ei;
- ei = kmem_cache_alloc(sock_inode_cachep, SLAB_KERNEL);
+ ei = kmem_cache_alloc(sock_inode_cachep, GFP_KERNEL);
if (!ei)
return NULL;
init_waitqueue_head(&ei->socket.wait);
ei->socket.ops = NULL;
ei->socket.sk = NULL;
ei->socket.file = NULL;
- ei->socket.flags = 0;
return &ei->vfs_inode;
}
container_of(inode, struct socket_alloc, vfs_inode));
}
-static void init_once(void *foo, kmem_cache_t *cachep, unsigned long flags)
+static void init_once(struct kmem_cache *cachep, void *foo)
{
struct socket_alloc *ei = (struct socket_alloc *)foo;
- if ((flags & (SLAB_CTOR_VERIFY|SLAB_CTOR_CONSTRUCTOR))
- == SLAB_CTOR_CONSTRUCTOR)
- inode_init_once(&ei->vfs_inode);
+ inode_init_once(&ei->vfs_inode);
}
static int init_inodecache(void)
(SLAB_HWCACHE_ALIGN |
SLAB_RECLAIM_ACCOUNT |
SLAB_MEM_SPREAD),
- init_once,
- NULL);
+ init_once);
if (sock_inode_cachep == NULL)
return -ENOMEM;
return 0;
static int sockfs_delete_dentry(struct dentry *dentry)
{
- return 1;
+ /*
+ * At creation time, we pretended this dentry was hashed
+ * (by clearing DCACHE_UNHASHED bit in d_flags)
+ * At delete time, we restore the truth : not hashed.
+ * (so that dput() can proceed correctly)
+ */
+ dentry->d_flags |= DCACHE_UNHASHED;
+ return 0;
}
+
+/*
+ * sockfs_dname() is called from d_path().
+ */
+static char *sockfs_dname(struct dentry *dentry, char *buffer, int buflen)
+{
+ return dynamic_dname(dentry, buffer, buflen, "socket:[%lu]",
+ dentry->d_inode->i_ino);
+}
+
static struct dentry_operations sockfs_dentry_operations = {
.d_delete = sockfs_delete_dentry,
+ .d_dname = sockfs_dname,
};
/*
static int sock_attach_fd(struct socket *sock, struct file *file)
{
- struct qstr this;
- char name[32];
+ struct dentry *dentry;
+ struct qstr name = { .name = "" };
- this.len = sprintf(name, "[%lu]", SOCK_INODE(sock)->i_ino);
- this.name = name;
- this.hash = SOCK_INODE(sock)->i_ino;
-
- file->f_dentry = d_alloc(sock_mnt->mnt_sb->s_root, &this);
- if (unlikely(!file->f_dentry))
+ dentry = d_alloc(sock_mnt->mnt_sb->s_root, &name);
+ if (unlikely(!dentry))
return -ENOMEM;
- file->f_dentry->d_op = &sockfs_dentry_operations;
- d_add(file->f_dentry, SOCK_INODE(sock));
- file->f_vfsmnt = mntget(sock_mnt);
- file->f_mapping = file->f_dentry->d_inode->i_mapping;
+ dentry->d_op = &sockfs_dentry_operations;
+ /*
+ * We dont want to push this dentry into global dentry hash table.
+ * We pretend dentry is already hashed, by unsetting DCACHE_UNHASHED
+ * This permits a working /proc/$pid/fd/XXX on sockets
+ */
+ dentry->d_flags &= ~DCACHE_UNHASHED;
+ d_instantiate(dentry, SOCK_INODE(sock));
sock->file = file;
- file->f_op = SOCK_INODE(sock)->i_fop = &socket_file_ops;
- file->f_mode = FMODE_READ | FMODE_WRITE;
+ init_file(file, sock_mnt, dentry, FMODE_READ | FMODE_WRITE,
+ &socket_file_ops);
+ SOCK_INODE(sock)->i_fop = &socket_file_ops;
file->f_flags = O_RDWR;
file->f_pos = 0;
file->private_data = sock;
static struct socket *sock_from_file(struct file *file, int *err)
{
- struct inode *inode;
- struct socket *sock;
-
if (file->f_op == &socket_file_ops)
return file->private_data; /* set in sock_map_fd */
- inode = file->f_dentry->d_inode;
- if (!S_ISSOCK(inode->i_mode)) {
- *err = -ENOTSOCK;
- return NULL;
- }
-
- sock = SOCKET_I(inode);
- if (sock->file != file) {
- printk(KERN_ERR "socki_lookup: socket file changed!\n");
- sock->file = file;
- }
- return sock;
+ *err = -ENOTSOCK;
+ return NULL;
}
/**
return result;
}
+/*
+ * called from sock_recv_timestamp() if sock_flag(sk, SOCK_RCVTSTAMP)
+ */
+void __sock_recv_timestamp(struct msghdr *msg, struct sock *sk,
+ struct sk_buff *skb)
+{
+ ktime_t kt = skb->tstamp;
+
+ if (!sock_flag(sk, SOCK_RCVTSTAMPNS)) {
+ struct timeval tv;
+ /* Race occurred between timestamp enabling and packet
+ receiving. Fill in the current time for now. */
+ if (kt.tv64 == 0)
+ kt = ktime_get_real();
+ skb->tstamp = kt;
+ tv = ktime_to_timeval(kt);
+ put_cmsg(msg, SOL_SOCKET, SCM_TIMESTAMP, sizeof(tv), &tv);
+ } else {
+ struct timespec ts;
+ /* Race occurred between timestamp enabling and packet
+ receiving. Fill in the current time for now. */
+ if (kt.tv64 == 0)
+ kt = ktime_get_real();
+ skb->tstamp = kt;
+ ts = ktime_to_timespec(kt);
+ put_cmsg(msg, SOL_SOCKET, SCM_TIMESTAMPNS, sizeof(ts), &ts);
+ }
+}
+
+EXPORT_SYMBOL_GPL(__sock_recv_timestamp);
+
static inline int __sock_recvmsg(struct kiocb *iocb, struct socket *sock,
struct msghdr *msg, size_t size, int flags)
{
return sock->ops->sendpage(sock, page, offset, size, flags);
}
+static ssize_t sock_splice_read(struct file *file, loff_t *ppos,
+ struct pipe_inode_info *pipe, size_t len,
+ unsigned int flags)
+{
+ struct socket *sock = file->private_data;
+
+ if (unlikely(!sock->ops->splice_read))
+ return -EINVAL;
+
+ return sock->ops->splice_read(sock, ppos, pipe, len, flags);
+}
+
static struct sock_iocb *alloc_sock_iocb(struct kiocb *iocb,
- char __user *ubuf, size_t size,
struct sock_iocb *siocb)
{
if (!is_sync_kiocb(iocb)) {
}
siocb->kiocb = iocb;
- siocb->async_iov.iov_base = ubuf;
- siocb->async_iov.iov_len = size;
-
iocb->private = siocb;
return siocb;
}
static ssize_t do_sock_read(struct msghdr *msg, struct kiocb *iocb,
- struct file *file, struct iovec *iov,
- unsigned long nr_segs)
+ struct file *file, const struct iovec *iov,
+ unsigned long nr_segs)
{
struct socket *sock = file->private_data;
size_t size = 0;
return __sock_recvmsg(iocb, sock, msg, size, msg->msg_flags);
}
-static ssize_t sock_readv(struct file *file, const struct iovec *iov,
- unsigned long nr_segs, loff_t *ppos)
-{
- struct kiocb iocb;
- struct sock_iocb siocb;
- struct msghdr msg;
- int ret;
-
- init_sync_kiocb(&iocb, NULL);
- iocb.private = &siocb;
-
- ret = do_sock_read(&msg, &iocb, file, (struct iovec *)iov, nr_segs);
- if (-EIOCBQUEUED == ret)
- ret = wait_on_sync_kiocb(&iocb);
- return ret;
-}
-
-static ssize_t sock_aio_read(struct kiocb *iocb, char __user *ubuf,
- size_t count, loff_t pos)
+static ssize_t sock_aio_read(struct kiocb *iocb, const struct iovec *iov,
+ unsigned long nr_segs, loff_t pos)
{
struct sock_iocb siocb, *x;
if (pos != 0)
return -ESPIPE;
- if (count == 0) /* Match SYS5 behaviour */
+
+ if (iocb->ki_left == 0) /* Match SYS5 behaviour */
return 0;
- x = alloc_sock_iocb(iocb, ubuf, count, &siocb);
+
+ x = alloc_sock_iocb(iocb, &siocb);
if (!x)
return -ENOMEM;
- return do_sock_read(&x->async_msg, iocb, iocb->ki_filp,
- &x->async_iov, 1);
+ return do_sock_read(&x->async_msg, iocb, iocb->ki_filp, iov, nr_segs);
}
static ssize_t do_sock_write(struct msghdr *msg, struct kiocb *iocb,
- struct file *file, struct iovec *iov,
- unsigned long nr_segs)
+ struct file *file, const struct iovec *iov,
+ unsigned long nr_segs)
{
struct socket *sock = file->private_data;
size_t size = 0;
return __sock_sendmsg(iocb, sock, msg, size);
}
-static ssize_t sock_writev(struct file *file, const struct iovec *iov,
- unsigned long nr_segs, loff_t *ppos)
-{
- struct msghdr msg;
- struct kiocb iocb;
- struct sock_iocb siocb;
- int ret;
-
- init_sync_kiocb(&iocb, NULL);
- iocb.private = &siocb;
-
- ret = do_sock_write(&msg, &iocb, file, (struct iovec *)iov, nr_segs);
- if (-EIOCBQUEUED == ret)
- ret = wait_on_sync_kiocb(&iocb);
- return ret;
-}
-
-static ssize_t sock_aio_write(struct kiocb *iocb, const char __user *ubuf,
- size_t count, loff_t pos)
+static ssize_t sock_aio_write(struct kiocb *iocb, const struct iovec *iov,
+ unsigned long nr_segs, loff_t pos)
{
struct sock_iocb siocb, *x;
if (pos != 0)
return -ESPIPE;
- if (count == 0) /* Match SYS5 behaviour */
- return 0;
- x = alloc_sock_iocb(iocb, (void __user *)ubuf, count, &siocb);
+ x = alloc_sock_iocb(iocb, &siocb);
if (!x)
return -ENOMEM;
- return do_sock_write(&x->async_msg, iocb, iocb->ki_filp,
- &x->async_iov, 1);
+ return do_sock_write(&x->async_msg, iocb, iocb->ki_filp, iov, nr_segs);
}
/*
*/
static DEFINE_MUTEX(br_ioctl_mutex);
-static int (*br_ioctl_hook) (unsigned int cmd, void __user *arg) = NULL;
+static int (*br_ioctl_hook) (struct net *, unsigned int cmd, void __user *arg) = NULL;
-void brioctl_set(int (*hook) (unsigned int, void __user *))
+void brioctl_set(int (*hook) (struct net *, unsigned int, void __user *))
{
mutex_lock(&br_ioctl_mutex);
br_ioctl_hook = hook;
EXPORT_SYMBOL(brioctl_set);
static DEFINE_MUTEX(vlan_ioctl_mutex);
-static int (*vlan_ioctl_hook) (void __user *arg);
+static int (*vlan_ioctl_hook) (struct net *, void __user *arg);
-void vlan_ioctl_set(int (*hook) (void __user *))
+void vlan_ioctl_set(int (*hook) (struct net *, void __user *))
{
mutex_lock(&vlan_ioctl_mutex);
vlan_ioctl_hook = hook;
static long sock_ioctl(struct file *file, unsigned cmd, unsigned long arg)
{
struct socket *sock;
+ struct sock *sk;
void __user *argp = (void __user *)arg;
int pid, err;
+ struct net *net;
sock = file->private_data;
+ sk = sock->sk;
+ net = sock_net(sk);
if (cmd >= SIOCDEVPRIVATE && cmd <= (SIOCDEVPRIVATE + 15)) {
- err = dev_ioctl(cmd, argp);
+ err = dev_ioctl(net, cmd, argp);
} else
#ifdef CONFIG_WIRELESS_EXT
if (cmd >= SIOCIWFIRST && cmd <= SIOCIWLAST) {
- err = dev_ioctl(cmd, argp);
+ err = dev_ioctl(net, cmd, argp);
} else
#endif /* CONFIG_WIRELESS_EXT */
switch (cmd) {
break;
case FIOGETOWN:
case SIOCGPGRP:
- err = put_user(sock->file->f_owner.pid,
+ err = put_user(f_getown(sock->file),
(int __user *)argp);
break;
case SIOCGIFBR:
mutex_lock(&br_ioctl_mutex);
if (br_ioctl_hook)
- err = br_ioctl_hook(cmd, argp);
+ err = br_ioctl_hook(net, cmd, argp);
mutex_unlock(&br_ioctl_mutex);
break;
case SIOCGIFVLAN:
mutex_lock(&vlan_ioctl_mutex);
if (vlan_ioctl_hook)
- err = vlan_ioctl_hook(argp);
+ err = vlan_ioctl_hook(net, argp);
mutex_unlock(&vlan_ioctl_mutex);
break;
- case SIOCGIFDIVERT:
- case SIOCSIFDIVERT:
- /* Convert this to call through a hook */
- err = divert_ioctl(cmd, argp);
- break;
case SIOCADDDLCI:
case SIOCDELDLCI:
err = -ENOPKG;
if (!dlci_ioctl_hook)
request_module("dlci");
- if (dlci_ioctl_hook) {
- mutex_lock(&dlci_ioctl_mutex);
+ mutex_lock(&dlci_ioctl_mutex);
+ if (dlci_ioctl_hook)
err = dlci_ioctl_hook(cmd, argp);
- mutex_unlock(&dlci_ioctl_mutex);
- }
+ mutex_unlock(&dlci_ioctl_mutex);
break;
default:
err = sock->ops->ioctl(sock, cmd, arg);
* to the NIC driver.
*/
if (err == -ENOIOCTLCMD)
- err = dev_ioctl(cmd, argp);
+ err = dev_ioctl(net, cmd, argp);
break;
}
return err;
if (!sock || !sock->fasync_list)
return -1;
switch (how) {
- case 1:
-
+ case SOCK_WAKE_WAITD:
if (test_bit(SOCK_ASYNC_WAITDATA, &sock->flags))
break;
goto call_kill;
- case 2:
+ case SOCK_WAKE_SPACE:
if (!test_and_clear_bit(SOCK_ASYNC_NOSPACE, &sock->flags))
break;
/* fall through */
- case 0:
+ case SOCK_WAKE_IO:
call_kill:
__kill_fasync(sock->fasync_list, SIGIO, band);
break;
- case 3:
+ case SOCK_WAKE_URG:
__kill_fasync(sock->fasync_list, SIGURG, band);
}
return 0;
}
-static int __sock_create(int family, int type, int protocol,
+static int __sock_create(struct net *net, int family, int type, int protocol,
struct socket **res, int kern)
{
int err;
/* Now protected by module ref count */
rcu_read_unlock();
- err = pf->create(sock, protocol);
+ err = pf->create(net, sock, protocol);
if (err < 0)
goto out_module_put;
module_put(pf->owner);
err = security_socket_post_create(sock, family, type, protocol, kern);
if (err)
- goto out_release;
+ goto out_sock_release;
*res = sock;
return 0;
int sock_create(int family, int type, int protocol, struct socket **res)
{
- return __sock_create(family, type, protocol, res, 0);
+ return __sock_create(current->nsproxy->net_ns, family, type, protocol, res, 0);
}
int sock_create_kern(int family, int type, int protocol, struct socket **res)
{
- return __sock_create(family, type, protocol, res, 1);
+ return __sock_create(&init_net, family, type, protocol, res, 1);
}
asmlinkage long sys_socket(int family, int type, int protocol)
{
struct socket *sock1, *sock2;
int fd1, fd2, err;
+ struct file *newfile1, *newfile2;
/*
* Obtain the first socket and check if the underlying protocol
if (err < 0)
goto out_release_both;
- fd1 = fd2 = -1;
+ fd1 = sock_alloc_fd(&newfile1);
+ if (unlikely(fd1 < 0)) {
+ err = fd1;
+ goto out_release_both;
+ }
- err = sock_map_fd(sock1);
- if (err < 0)
+ fd2 = sock_alloc_fd(&newfile2);
+ if (unlikely(fd2 < 0)) {
+ err = fd2;
+ put_filp(newfile1);
+ put_unused_fd(fd1);
goto out_release_both;
- fd1 = err;
+ }
- err = sock_map_fd(sock2);
- if (err < 0)
- goto out_close_1;
- fd2 = err;
+ err = sock_attach_fd(sock1, newfile1);
+ if (unlikely(err < 0)) {
+ goto out_fd2;
+ }
+ err = sock_attach_fd(sock2, newfile2);
+ if (unlikely(err < 0)) {
+ fput(newfile1);
+ goto out_fd1;
+ }
+
+ err = audit_fd_pair(fd1, fd2);
+ if (err < 0) {
+ fput(newfile1);
+ fput(newfile2);
+ goto out_fd;
+ }
+
+ fd_install(fd1, newfile1);
+ fd_install(fd2, newfile2);
/* fd1 and fd2 may be already another descriptors.
* Not kernel problem.
*/
sys_close(fd1);
return err;
-out_close_1:
- sock_release(sock2);
- sys_close(fd1);
- return err;
-
out_release_both:
sock_release(sock2);
out_release_1:
sock_release(sock1);
out:
return err;
+
+out_fd2:
+ put_filp(newfile1);
+ sock_release(sock1);
+out_fd1:
+ put_filp(newfile2);
+ sock_release(sock2);
+out_fd:
+ put_unused_fd(fd1);
+ put_unused_fd(fd2);
+ goto out;
}
/*
int err, fput_needed;
sock = sockfd_lookup_light(fd, &err, &fput_needed);
- if(sock) {
+ if (sock) {
err = move_addr_to_kernel(umyaddr, addrlen, address);
if (err >= 0) {
err = security_socket_bind(sock,
* ready for listening.
*/
-int sysctl_somaxconn = SOMAXCONN;
-
asmlinkage long sys_listen(int fd, int backlog)
{
struct socket *sock;
int err, fput_needed;
+ int somaxconn;
sock = sockfd_lookup_light(fd, &err, &fput_needed);
if (sock) {
- if ((unsigned)backlog > sysctl_somaxconn)
- backlog = sysctl_somaxconn;
+ somaxconn = sock_net(sock->sk)->core.sysctl_somaxconn;
+ if ((unsigned)backlog > somaxconn)
+ backlog = somaxconn;
err = security_socket_listen(sock, backlog);
if (!err)
err = sock_attach_fd(newsock, newfile);
if (err < 0)
- goto out_fd;
+ goto out_fd_simple;
err = security_socket_accept(sock, newsock);
if (err)
fput_light(sock->file, fput_needed);
out:
return err;
+out_fd_simple:
+ sock_release(newsock);
+ put_filp(newfile);
+ put_unused_fd(newfd);
+ goto out_put;
out_fd:
fput(newfile);
put_unused_fd(newfd);
struct msghdr msg;
struct iovec iov;
int fput_needed;
- struct file *sock_file;
-
- sock_file = fget_light(fd, &fput_needed);
- if (!sock_file)
- return -EBADF;
- sock = sock_from_file(sock_file, &err);
+ sock = sockfd_lookup_light(fd, &err, &fput_needed);
if (!sock)
- goto out_put;
+ goto out;
+
iov.iov_base = buff;
iov.iov_len = len;
msg.msg_name = NULL;
err = sock_sendmsg(sock, &msg, len);
out_put:
- fput_light(sock_file, fput_needed);
+ fput_light(sock->file, fput_needed);
+out:
return err;
}
struct msghdr msg;
char address[MAX_SOCK_ADDR];
int err, err2;
- struct file *sock_file;
int fput_needed;
- sock_file = fget_light(fd, &fput_needed);
- if (!sock_file)
- return -EBADF;
-
- sock = sock_from_file(sock_file, &err);
+ sock = sockfd_lookup_light(fd, &err, &fput_needed);
if (!sock)
goto out;
if (err2 < 0)
err = err2;
}
+
+ fput_light(sock->file, fput_needed);
out:
- fput_light(sock_file, fput_needed);
return err;
}
* kernel msghdr to use the kernel address space)
*/
- uaddr = (void __user *)msg_sys.msg_name;
+ uaddr = (__force void __user *)msg_sys.msg_name;
uaddr_len = COMPAT_NAMELEN(msg);
if (MSG_CMSG_COMPAT & flags) {
err = verify_compat_iovec(&msg_sys, iov, addr, VERIFY_WRITE);
total_len = err;
cmsg_ptr = (unsigned long)msg_sys.msg_control;
- msg_sys.msg_flags = 0;
- if (MSG_CMSG_COMPAT & flags)
- msg_sys.msg_flags = MSG_CMSG_COMPAT;
+ msg_sys.msg_flags = flags & (MSG_CMSG_CLOEXEC|MSG_CMSG_COMPAT);
if (sock->file->f_flags & O_NONBLOCK)
flags |= MSG_DONTWAIT;
err = sock->ops->accept(sock, *newsock, flags);
if (err < 0) {
sock_release(*newsock);
+ *newsock = NULL;
goto done;
}
}
int kernel_connect(struct socket *sock, struct sockaddr *addr, int addrlen,
- int flags)
+ int flags)
{
return sock->ops->connect(sock, addr, addrlen, flags);
}
return err;
}
-/* ABI emulation layers need these two */
-EXPORT_SYMBOL(move_addr_to_kernel);
-EXPORT_SYMBOL(move_addr_to_user);
+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(kernel_setsockopt);
EXPORT_SYMBOL(kernel_sendpage);
EXPORT_SYMBOL(kernel_sock_ioctl);
+EXPORT_SYMBOL(kernel_sock_shutdown);
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff