#include <linux/wireless.h>
#include <linux/nsproxy.h>
#include <linux/magic.h>
+#include <linux/slab.h>
#include <asm/uaccess.h>
#include <asm/unistd.h>
ei = kmem_cache_alloc(sock_inode_cachep, GFP_KERNEL);
if (!ei)
return NULL;
- init_waitqueue_head(&ei->socket.wait);
+ ei->socket.wq = kmalloc(sizeof(struct socket_wq), GFP_KERNEL);
+ if (!ei->socket.wq) {
+ kmem_cache_free(sock_inode_cachep, ei);
+ return NULL;
+ }
+ init_waitqueue_head(&ei->socket.wq->wait);
+ ei->socket.wq->fasync_list = NULL;
- ei->socket.fasync_list = NULL;
ei->socket.state = SS_UNCONNECTED;
ei->socket.flags = 0;
ei->socket.ops = NULL;
return &ei->vfs_inode;
}
+
+static void wq_free_rcu(struct rcu_head *head)
+{
+ struct socket_wq *wq = container_of(head, struct socket_wq, rcu);
+
+ kfree(wq);
+}
+
static void sock_destroy_inode(struct inode *inode)
{
- kmem_cache_free(sock_inode_cachep,
- container_of(inode, struct socket_alloc, vfs_inode));
+ struct socket_alloc *ei;
+
+ ei = container_of(inode, struct socket_alloc, vfs_inode);
+ call_rcu(&ei->socket.wq->rcu, wq_free_rcu);
+ kmem_cache_free(sock_inode_cachep, ei);
}
static void init_once(void *foo)
.kill_sb = kill_anon_super,
};
-static int sockfs_delete_dentry(struct dentry *dentry)
-{
- /*
- * 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 const struct dentry_operations sockfs_dentry_operations = {
- .d_delete = sockfs_delete_dentry,
.d_dname = sockfs_dname,
};
* but we take care of internal coherence yet.
*/
-static int sock_alloc_fd(struct file **filep, int flags)
+static int sock_alloc_file(struct socket *sock, struct file **f, int flags)
{
+ struct qstr name = { .name = "" };
+ struct path path;
+ struct file *file;
int fd;
fd = get_unused_fd_flags(flags);
- if (likely(fd >= 0)) {
- struct file *file = get_empty_filp();
-
- *filep = file;
- if (unlikely(!file)) {
- put_unused_fd(fd);
- return -ENFILE;
- }
- } else
- *filep = NULL;
- return fd;
-}
+ if (unlikely(fd < 0))
+ return fd;
-static int sock_attach_fd(struct socket *sock, struct file *file, int flags)
-{
- struct dentry *dentry;
- struct qstr name = { .name = "" };
-
- dentry = d_alloc(sock_mnt->mnt_sb->s_root, &name);
- if (unlikely(!dentry))
+ path.dentry = d_alloc(sock_mnt->mnt_sb->s_root, &name);
+ if (unlikely(!path.dentry)) {
+ put_unused_fd(fd);
return -ENOMEM;
+ }
+ path.mnt = mntget(sock_mnt);
- 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));
+ path.dentry->d_op = &sockfs_dentry_operations;
+ d_instantiate(path.dentry, SOCK_INODE(sock));
+ SOCK_INODE(sock)->i_fop = &socket_file_ops;
- sock->file = file;
- init_file(file, sock_mnt, dentry, FMODE_READ | FMODE_WRITE,
+ file = alloc_file(&path, FMODE_READ | FMODE_WRITE,
&socket_file_ops);
- SOCK_INODE(sock)->i_fop = &socket_file_ops;
+ if (unlikely(!file)) {
+ /* drop dentry, keep inode */
+ atomic_inc(&path.dentry->d_inode->i_count);
+ path_put(&path);
+ put_unused_fd(fd);
+ return -ENFILE;
+ }
+
+ sock->file = file;
file->f_flags = O_RDWR | (flags & O_NONBLOCK);
file->f_pos = 0;
file->private_data = sock;
- return 0;
+ *f = file;
+ return fd;
}
int sock_map_fd(struct socket *sock, int flags)
{
struct file *newfile;
- int fd = sock_alloc_fd(&newfile, flags);
+ int fd = sock_alloc_file(sock, &newfile, flags);
- if (likely(fd >= 0)) {
- int err = sock_attach_fd(sock, newfile, flags);
-
- if (unlikely(err < 0)) {
- put_filp(newfile);
- put_unused_fd(fd);
- return err;
- }
+ if (likely(fd >= 0))
fd_install(fd, newfile);
- }
+
return fd;
}
module_put(owner);
}
- if (sock->fasync_list)
+ if (sock->wq->fasync_list)
printk(KERN_ERR "sock_release: fasync list not empty!\n");
percpu_sub(sockets_in_use, 1);
put_cmsg(msg, SOL_SOCKET, SCM_TIMESTAMP,
sizeof(tv), &tv);
} else {
- struct timespec ts;
- skb_get_timestampns(skb, &ts);
+ skb_get_timestampns(skb, &ts[0]);
put_cmsg(msg, SOL_SOCKET, SCM_TIMESTAMPNS,
- sizeof(ts), &ts);
+ sizeof(ts[0]), &ts[0]);
}
}
sizeof(__u32), &skb->dropcount);
}
-void sock_recv_ts_and_drops(struct msghdr *msg, struct sock *sk,
+void __sock_recv_ts_and_drops(struct msghdr *msg, struct sock *sk,
struct sk_buff *skb)
{
sock_recv_timestamp(msg, sk, skb);
sock_recv_drops(msg, sk, skb);
}
-EXPORT_SYMBOL_GPL(sock_recv_ts_and_drops);
+EXPORT_SYMBOL_GPL(__sock_recv_ts_and_drops);
static inline int __sock_recvmsg_nosec(struct kiocb *iocb, struct socket *sock,
struct msghdr *msg, size_t size, int flags)
* 1. fasync_list is modified only under process context socket lock
* i.e. under semaphore.
* 2. fasync_list is used under read_lock(&sk->sk_callback_lock)
- * or under socket lock.
- * 3. fasync_list can be used from softirq context, so that
- * modification under socket lock have to be enhanced with
- * write_lock_bh(&sk->sk_callback_lock).
- * --ANK (990710)
+ * or under socket lock
*/
static int sock_fasync(int fd, struct file *filp, int on)
{
- struct fasync_struct *fa, *fna = NULL, **prev;
- struct socket *sock;
- struct sock *sk;
-
- if (on) {
- fna = kmalloc(sizeof(struct fasync_struct), GFP_KERNEL);
- if (fna == NULL)
- return -ENOMEM;
- }
-
- sock = filp->private_data;
+ struct socket *sock = filp->private_data;
+ struct sock *sk = sock->sk;
- sk = sock->sk;
- if (sk == NULL) {
- kfree(fna);
+ if (sk == NULL)
return -EINVAL;
- }
lock_sock(sk);
- spin_lock(&filp->f_lock);
- if (on)
- filp->f_flags |= FASYNC;
- else
- filp->f_flags &= ~FASYNC;
- spin_unlock(&filp->f_lock);
-
- prev = &(sock->fasync_list);
-
- for (fa = *prev; fa != NULL; prev = &fa->fa_next, fa = *prev)
- if (fa->fa_file == filp)
- break;
-
- if (on) {
- if (fa != NULL) {
- write_lock_bh(&sk->sk_callback_lock);
- fa->fa_fd = fd;
- write_unlock_bh(&sk->sk_callback_lock);
+ fasync_helper(fd, filp, on, &sock->wq->fasync_list);
- kfree(fna);
- goto out;
- }
- fna->fa_file = filp;
- fna->fa_fd = fd;
- fna->magic = FASYNC_MAGIC;
- fna->fa_next = sock->fasync_list;
- write_lock_bh(&sk->sk_callback_lock);
- sock->fasync_list = fna;
+ if (!sock->wq->fasync_list)
+ sock_reset_flag(sk, SOCK_FASYNC);
+ else
sock_set_flag(sk, SOCK_FASYNC);
- write_unlock_bh(&sk->sk_callback_lock);
- } else {
- if (fa != NULL) {
- write_lock_bh(&sk->sk_callback_lock);
- *prev = fa->fa_next;
- if (!sock->fasync_list)
- sock_reset_flag(sk, SOCK_FASYNC);
- write_unlock_bh(&sk->sk_callback_lock);
- kfree(fa);
- }
- }
-out:
- release_sock(sock->sk);
+ release_sock(sk);
return 0;
}
-/* This function may be called only under socket lock or callback_lock */
+/* This function may be called only under socket lock or callback_lock or rcu_lock */
int sock_wake_async(struct socket *sock, int how, int band)
{
- if (!sock || !sock->fasync_list)
+ struct socket_wq *wq;
+
+ if (!sock)
return -1;
+ rcu_read_lock();
+ wq = rcu_dereference(sock->wq);
+ if (!wq || !wq->fasync_list) {
+ rcu_read_unlock();
+ return -1;
+ }
switch (how) {
case SOCK_WAKE_WAITD:
if (test_bit(SOCK_ASYNC_WAITDATA, &sock->flags))
/* fall through */
case SOCK_WAKE_IO:
call_kill:
- __kill_fasync(sock->fasync_list, SIGIO, band);
+ kill_fasync(&wq->fasync_list, SIGIO, band);
break;
case SOCK_WAKE_URG:
- __kill_fasync(sock->fasync_list, SIGURG, band);
+ kill_fasync(&wq->fasync_list, SIGURG, band);
}
+ rcu_read_unlock();
return 0;
}
if (err < 0)
goto out_release_both;
- fd1 = sock_alloc_fd(&newfile1, flags & O_CLOEXEC);
+ fd1 = sock_alloc_file(sock1, &newfile1, flags);
if (unlikely(fd1 < 0)) {
err = fd1;
goto out_release_both;
}
- fd2 = sock_alloc_fd(&newfile2, flags & O_CLOEXEC);
+ fd2 = sock_alloc_file(sock2, &newfile2, flags);
if (unlikely(fd2 < 0)) {
err = fd2;
- put_filp(newfile1);
- put_unused_fd(fd1);
- goto out_release_both;
- }
-
- err = sock_attach_fd(sock1, newfile1, flags & O_NONBLOCK);
- if (unlikely(err < 0)) {
- goto out_fd2;
- }
-
- err = sock_attach_fd(sock2, newfile2, flags & O_NONBLOCK);
- if (unlikely(err < 0)) {
fput(newfile1);
- goto out_fd1;
+ put_unused_fd(fd1);
+ sock_release(sock2);
+ goto out;
}
audit_fd_pair(fd1, fd2);
sock_release(sock1);
out:
return err;
-
-out_fd2:
- put_filp(newfile1);
- sock_release(sock1);
-out_fd1:
- put_filp(newfile2);
- sock_release(sock2);
- put_unused_fd(fd1);
- put_unused_fd(fd2);
- goto out;
}
/*
*/
__module_get(newsock->ops->owner);
- newfd = sock_alloc_fd(&newfile, flags & O_CLOEXEC);
+ newfd = sock_alloc_file(newsock, &newfile, flags);
if (unlikely(newfd < 0)) {
err = newfd;
sock_release(newsock);
goto out_put;
}
- err = sock_attach_fd(newsock, newfile, flags & O_NONBLOCK);
- if (err < 0)
- goto out_fd_simple;
-
err = security_socket_accept(sock, newsock);
if (err)
goto out_fd;
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);
int fput_needed, err, datagrams;
struct socket *sock;
struct mmsghdr __user *entry;
+ struct compat_mmsghdr __user *compat_entry;
struct msghdr msg_sys;
struct timespec end_time;
goto out_put;
entry = mmsg;
+ compat_entry = (struct compat_mmsghdr __user *)mmsg;
while (datagrams < vlen) {
/*
* No need to ask LSM for more than the first datagram.
*/
- err = __sys_recvmsg(sock, (struct msghdr __user *)entry,
- &msg_sys, flags, datagrams);
- if (err < 0)
- break;
- err = put_user(err, &entry->msg_len);
+ if (MSG_CMSG_COMPAT & flags) {
+ err = __sys_recvmsg(sock, (struct msghdr __user *)compat_entry,
+ &msg_sys, flags, datagrams);
+ if (err < 0)
+ break;
+ err = __put_user(err, &compat_entry->msg_len);
+ ++compat_entry;
+ } else {
+ err = __sys_recvmsg(sock, (struct msghdr __user *)entry,
+ &msg_sys, flags, datagrams);
+ if (err < 0)
+ break;
+ err = put_user(err, &entry->msg_len);
+ ++entry;
+ }
+
if (err)
break;
- ++entry;
++datagrams;
+ /* MSG_WAITFORONE turns on MSG_DONTWAIT after one packet */
+ if (flags & MSG_WAITFORONE)
+ flags |= MSG_DONTWAIT;
+
if (timeout) {
ktime_get_ts(timeout);
*timeout = timespec_sub(end_time, *timeout);
return dev_ioctl(net, cmd, uifr);
default:
return -EINVAL;
- };
+ }
}
static int siocdevprivate_ioctl(struct net *net, unsigned int cmd,