*/
#include <linux/mm.h>
-#include <linux/smp_lock.h>
#include <linux/socket.h>
#include <linux/file.h>
#include <linux/net.h>
#include <linux/interrupt.h>
+#include <linux/rcupdate.h>
#include <linux/netdevice.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#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/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);
* 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,
};
* The protocol list. Each protocol is registered in here.
*/
-static struct net_proto_family *net_families[NPROTO];
-
-#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT)
-static atomic_t net_family_lockct = ATOMIC_INIT(0);
static DEFINE_SPINLOCK(net_family_lock);
-
-/* The strategy is: modifications net_family vector are short, do not
- sleep and veeery rare, but read access should be free of any exclusive
- locks.
- */
-
-static void net_family_write_lock(void)
-{
- spin_lock(&net_family_lock);
- while (atomic_read(&net_family_lockct) != 0) {
- spin_unlock(&net_family_lock);
-
- yield();
-
- spin_lock(&net_family_lock);
- }
-}
-
-static __inline__ void net_family_write_unlock(void)
-{
- spin_unlock(&net_family_lock);
-}
-
-static __inline__ void net_family_read_lock(void)
-{
- atomic_inc(&net_family_lockct);
- spin_unlock_wait(&net_family_lock);
-}
-
-static __inline__ void net_family_read_unlock(void)
-{
- atomic_dec(&net_family_lockct);
-}
-
-#else
-#define net_family_write_lock() do { } while(0)
-#define net_family_write_unlock() do { } while(0)
-#define net_family_read_lock() do { } while(0)
-#define net_family_read_unlock() do { } while(0)
-#endif
+static const struct net_proto_family *net_families[NPROTO] __read_mostly;
/*
* Statistics counters of the socket lists
#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(void *foo, struct kmem_cache *cachep, unsigned long flags)
{
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)
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];
-
- this.len = sprintf(name, "[%lu]", SOCK_INODE(sock)->i_ino);
- this.name = name;
- this.hash = SOCK_INODE(sock)->i_ino;
+ struct qstr name = { .name = "" };
- file->f_dentry = d_alloc(sock_mnt->mnt_sb->s_root, &this);
- if (unlikely(!file->f_dentry))
+ file->f_path.dentry = d_alloc(sock_mnt->mnt_sb->s_root, &name);
+ if (unlikely(!file->f_path.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;
+ file->f_path.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
+ */
+ file->f_path.dentry->d_flags &= ~DCACHE_UNHASHED;
+ d_instantiate(file->f_path.dentry, SOCK_INODE(sock));
+ file->f_path.mnt = mntget(sock_mnt);
+ file->f_mapping = file->f_path.dentry->d_inode->i_mapping;
sock->file = file;
file->f_op = SOCK_INODE(sock)->i_fop = &socket_file_ops;
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)
{
}
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 */
+
+ if (iocb->ki_left == 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);
}
/*
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:
err = vlan_ioctl_hook(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;
{
int err;
struct socket *sock;
+ const struct net_proto_family *pf;
/*
* Check protocol is in range
if (err)
return err;
+ /*
+ * Allocate the socket and allow the family to set things up. if
+ * the protocol is 0, the family is instructed to select an appropriate
+ * default.
+ */
+ sock = sock_alloc();
+ if (!sock) {
+ if (net_ratelimit())
+ printk(KERN_WARNING "socket: no more sockets\n");
+ return -ENFILE; /* Not exactly a match, but its the
+ closest posix thing */
+ }
+
+ sock->type = type;
+
#if defined(CONFIG_KMOD)
/* Attempt to load a protocol module if the find failed.
*
* requested real, full-featured networking support upon configuration.
* Otherwise module support will break!
*/
- if (net_families[family] == NULL) {
+ if (net_families[family] == NULL)
request_module("net-pf-%d", family);
- }
#endif
- net_family_read_lock();
- if (net_families[family] == NULL) {
- err = -EAFNOSUPPORT;
- goto out;
- }
-
-/*
- * Allocate the socket and allow the family to set things up. if
- * the protocol is 0, the family is instructed to select an appropriate
- * default.
- */
-
- if (!(sock = sock_alloc())) {
- if (net_ratelimit())
- printk(KERN_WARNING "socket: no more sockets\n");
- err = -ENFILE; /* Not exactly a match, but its the
- closest posix thing */
- goto out;
- }
-
- sock->type = type;
+ rcu_read_lock();
+ pf = rcu_dereference(net_families[family]);
+ err = -EAFNOSUPPORT;
+ if (!pf)
+ goto out_release;
/*
* We will call the ->create function, that possibly is in a loadable
* module, so we have to bump that loadable module refcnt first.
*/
- err = -EAFNOSUPPORT;
- if (!try_module_get(net_families[family]->owner))
+ if (!try_module_get(pf->owner))
goto out_release;
- if ((err = net_families[family]->create(sock, protocol)) < 0) {
- sock->ops = NULL;
+ /* Now protected by module ref count */
+ rcu_read_unlock();
+
+ err = pf->create(sock, protocol);
+ if (err < 0)
goto out_module_put;
- }
/*
* Now to bump the refcnt of the [loadable] module that owns this
* socket at sock_release time we decrement its refcnt.
*/
- if (!try_module_get(sock->ops->owner)) {
- sock->ops = NULL;
- goto out_module_put;
- }
+ if (!try_module_get(sock->ops->owner))
+ goto out_module_busy;
+
/*
* Now that we're done with the ->create function, the [loadable]
* module can have its refcnt decremented
*/
- module_put(net_families[family]->owner);
- *res = sock;
+ module_put(pf->owner);
err = security_socket_post_create(sock, family, type, protocol, kern);
if (err)
goto out_release;
+ *res = sock;
-out:
- net_family_read_unlock();
- return err;
+ return 0;
+
+out_module_busy:
+ err = -EAFNOSUPPORT;
out_module_put:
- module_put(net_families[family]->owner);
-out_release:
+ sock->ops = NULL;
+ module_put(pf->owner);
+out_sock_release:
sock_release(sock);
- goto out;
+ return err;
+
+out_release:
+ rcu_read_unlock();
+ goto out_sock_release;
}
int sock_create(int family, int type, int protocol, struct socket **res)
{
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))
+ goto out_release_both;
- err = sock_map_fd(sock1);
- if (err < 0)
+ fd2 = sock_alloc_fd(&newfile2);
+ if (unlikely(fd2 < 0)) {
+ 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;
+int sysctl_somaxconn __read_mostly = SOMAXCONN;
asmlinkage long sys_listen(int fd, int backlog)
{
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 file *sock_file;
sock_file = fget_light(fd, &fput_needed);
+ err = -EBADF;
if (!sock_file)
- return -EBADF;
+ goto out;
sock = sock_from_file(sock_file, &err);
if (!sock)
out_put:
fput_light(sock_file, fput_needed);
+out:
return err;
}
int fput_needed;
sock_file = fget_light(fd, &fput_needed);
+ err = -EBADF;
if (!sock_file)
- return -EBADF;
+ goto out;
sock = sock_from_file(sock_file, &err);
if (!sock)
- goto out;
+ goto out_put;
msg.msg_control = NULL;
msg.msg_controllen = 0;
if (err2 < 0)
err = err2;
}
-out:
+out_put:
fput_light(sock_file, fput_needed);
+out:
return err;
}
#endif /* __ARCH_WANT_SYS_SOCKETCALL */
-/*
+/**
+ * sock_register - add a socket protocol handler
+ * @ops: description of protocol
+ *
* This function is called by a protocol handler that wants to
* advertise its address family, and have it linked into the
- * SOCKET module.
+ * socket interface. The value ops->family coresponds to the
+ * socket system call protocol family.
*/
-
-int sock_register(struct net_proto_family *ops)
+int sock_register(const struct net_proto_family *ops)
{
int err;
NPROTO);
return -ENOBUFS;
}
- net_family_write_lock();
- err = -EEXIST;
- if (net_families[ops->family] == NULL) {
+
+ spin_lock(&net_family_lock);
+ if (net_families[ops->family])
+ err = -EEXIST;
+ else {
net_families[ops->family] = ops;
err = 0;
}
- net_family_write_unlock();
+ spin_unlock(&net_family_lock);
+
printk(KERN_INFO "NET: Registered protocol family %d\n", ops->family);
return err;
}
-/*
+/**
+ * sock_unregister - remove a protocol handler
+ * @family: protocol family to remove
+ *
* This function is called by a protocol handler that wants to
* remove its address family, and have it unlinked from the
- * SOCKET module.
+ * new socket creation.
+ *
+ * If protocol handler is a module, then it can use module reference
+ * counts to protect against new references. If protocol handler is not
+ * a module then it needs to provide its own protection in
+ * the ops->create routine.
*/
-
-int sock_unregister(int family)
+void sock_unregister(int family)
{
- if (family < 0 || family >= NPROTO)
- return -1;
+ BUG_ON(family < 0 || family >= NPROTO);
- net_family_write_lock();
+ spin_lock(&net_family_lock);
net_families[family] = NULL;
- net_family_write_unlock();
+ spin_unlock(&net_family_lock);
+
+ synchronize_rcu();
+
printk(KERN_INFO "NET: Unregistered protocol family %d\n", family);
- return 0;
}
static int __init sock_init(void)
}
int kernel_connect(struct socket *sock, struct sockaddr *addr, int addrlen,
- int flags)
+ int flags)
{
return sock->ops->connect(sock, addr, addrlen, flags);
}