X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=net%2Fsocket.c;h=5e8d0af3c0e73b3537c1852eee2c15a917e4a605;hb=ccc2d97cb7c798e785c9f198de243e2b59f7073b;hp=92fab9e1c6021deeec2cc2bf33056013755fbceb;hpb=9c55e01c0cc835818475a6ce8c4d684df9949ac8;p=safe%2Fjmp%2Flinux-2.6 diff --git a/net/socket.c b/net/socket.c index 92fab9e..5e8d0af 100644 --- a/net/socket.c +++ b/net/socket.c @@ -63,6 +63,7 @@ #include #include #include +#include #include #include #include @@ -85,15 +86,24 @@ #include #include #include +#include +#include #include #include #include +#include #include #include +#include +#include +#include +#include +#include + static int sock_no_open(struct inode *irrelevant, struct file *dontcare); static ssize_t sock_aio_read(struct kiocb *iocb, const struct iovec *iov, unsigned long nr_segs, loff_t pos); @@ -179,9 +189,9 @@ static DEFINE_PER_CPU(int, sockets_in_use) = 0; * invalid addresses -EFAULT is returned. On a success 0 is returned. */ -int move_addr_to_kernel(void __user *uaddr, int ulen, void *kaddr) +int move_addr_to_kernel(void __user *uaddr, int ulen, struct sockaddr *kaddr) { - if (ulen < 0 || ulen > MAX_SOCK_ADDR) + if (ulen < 0 || ulen > sizeof(struct sockaddr_storage)) return -EINVAL; if (ulen == 0) return 0; @@ -207,7 +217,7 @@ int move_addr_to_kernel(void __user *uaddr, int ulen, void *kaddr) * specified. Zero is returned for a success. */ -int move_addr_to_user(void *kaddr, int klen, void __user *uaddr, +int move_addr_to_user(struct sockaddr *kaddr, int klen, void __user *uaddr, int __user *ulen) { int err; @@ -218,7 +228,7 @@ int move_addr_to_user(void *kaddr, int klen, void __user *uaddr, return err; if (len > klen) len = klen; - if (len < 0 || len > MAX_SOCK_ADDR) + if (len < 0 || len > sizeof(struct sockaddr_storage)) return -EINVAL; if (len) { if (audit_sockaddr(klen, kaddr)) @@ -233,8 +243,6 @@ int move_addr_to_user(void *kaddr, int klen, void __user *uaddr, return __put_user(klen, ulen); } -#define SOCKFS_MAGIC 0x534F434B - static struct kmem_cache *sock_inode_cachep __read_mostly; static struct inode *sock_alloc_inode(struct super_block *sb) @@ -262,7 +270,7 @@ static void sock_destroy_inode(struct inode *inode) container_of(inode, struct socket_alloc, vfs_inode)); } -static void init_once(struct kmem_cache *cachep, void *foo) +static void init_once(void *foo) { struct socket_alloc *ei = (struct socket_alloc *)foo; @@ -283,7 +291,7 @@ static int init_inodecache(void) return 0; } -static struct super_operations sockfs_ops = { +static const struct super_operations sockfs_ops = { .alloc_inode = sock_alloc_inode, .destroy_inode =sock_destroy_inode, .statfs = simple_statfs, @@ -305,18 +313,6 @@ static struct file_system_type sock_fs_type = { .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(). */ @@ -326,8 +322,7 @@ static char *sockfs_dname(struct dentry *dentry, char *buffer, int buflen) dentry->d_inode->i_ino); } -static struct dentry_operations sockfs_dentry_operations = { - .d_delete = sockfs_delete_dentry, +static const struct dentry_operations sockfs_dentry_operations = { .d_dname = sockfs_dname, }; @@ -348,68 +343,55 @@ static struct dentry_operations sockfs_dentry_operations = { * but we take care of internal coherence yet. */ -static int sock_alloc_fd(struct file **filep) +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(); - 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; -} - -static int sock_attach_fd(struct socket *sock, struct file *file) -{ - struct dentry *dentry; - struct qstr name = { .name = "" }; + fd = get_unused_fd_flags(flags); + if (unlikely(fd < 0)) + return fd; - 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; - file->f_flags = O_RDWR; + 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 sock_map_fd(struct socket *sock, int flags) { struct file *newfile; - int fd = sock_alloc_fd(&newfile); - - if (likely(fd >= 0)) { - int err = sock_attach_fd(sock, newfile); + int fd = sock_alloc_file(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; } @@ -487,12 +469,12 @@ static struct socket *sock_alloc(void) sock = SOCKET_I(inode); + kmemcheck_annotate_bitfield(sock, type); inode->i_mode = S_IFSOCK | S_IRWXUGO; - inode->i_uid = current->fsuid; - inode->i_gid = current->fsgid; + inode->i_uid = current_fsuid(); + inode->i_gid = current_fsgid(); - get_cpu_var(sockets_in_use)++; - put_cpu_var(sockets_in_use); + percpu_add(sockets_in_use, 1); return sock; } @@ -534,8 +516,7 @@ void sock_release(struct socket *sock) if (sock->fasync_list) printk(KERN_ERR "sock_release: fasync list not empty!\n"); - get_cpu_var(sockets_in_use)--; - put_cpu_var(sockets_in_use); + percpu_sub(sockets_in_use, 1); if (!sock->file) { iput(SOCK_INODE(sock)); return; @@ -543,6 +524,18 @@ void sock_release(struct socket *sock) sock->file = NULL; } +int sock_tx_timestamp(struct msghdr *msg, struct sock *sk, + union skb_shared_tx *shtx) +{ + shtx->flags = 0; + if (sock_flag(sk, SOCK_TIMESTAMPING_TX_HARDWARE)) + shtx->hardware = 1; + if (sock_flag(sk, SOCK_TIMESTAMPING_TX_SOFTWARE)) + shtx->software = 1; + return 0; +} +EXPORT_SYMBOL(sock_tx_timestamp); + static inline int __sock_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, size_t size) { @@ -593,41 +586,87 @@ int kernel_sendmsg(struct socket *sock, struct msghdr *msg, return result; } +static int ktime2ts(ktime_t kt, struct timespec *ts) +{ + if (kt.tv64) { + *ts = ktime_to_timespec(kt); + return 1; + } else { + return 0; + } +} + /* * 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); + int need_software_tstamp = sock_flag(sk, SOCK_RCVTSTAMP); + struct timespec ts[3]; + int empty = 1; + struct skb_shared_hwtstamps *shhwtstamps = + skb_hwtstamps(skb); + + /* Race occurred between timestamp enabling and packet + receiving. Fill in the current time for now. */ + if (need_software_tstamp && skb->tstamp.tv64 == 0) + __net_timestamp(skb); + + if (need_software_tstamp) { + if (!sock_flag(sk, SOCK_RCVTSTAMPNS)) { + struct timeval tv; + skb_get_timestamp(skb, &tv); + put_cmsg(msg, SOL_SOCKET, SCM_TIMESTAMP, + sizeof(tv), &tv); + } else { + struct timespec ts; + skb_get_timestampns(skb, &ts); + put_cmsg(msg, SOL_SOCKET, SCM_TIMESTAMPNS, + sizeof(ts), &ts); + } + } + + + memset(ts, 0, sizeof(ts)); + if (skb->tstamp.tv64 && + sock_flag(sk, SOCK_TIMESTAMPING_SOFTWARE)) { + skb_get_timestampns(skb, ts + 0); + empty = 0; } + if (shhwtstamps) { + if (sock_flag(sk, SOCK_TIMESTAMPING_SYS_HARDWARE) && + ktime2ts(shhwtstamps->syststamp, ts + 1)) + empty = 0; + if (sock_flag(sk, SOCK_TIMESTAMPING_RAW_HARDWARE) && + ktime2ts(shhwtstamps->hwtstamp, ts + 2)) + empty = 0; + } + if (!empty) + put_cmsg(msg, SOL_SOCKET, + SCM_TIMESTAMPING, 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) +inline void sock_recv_drops(struct msghdr *msg, struct sock *sk, struct sk_buff *skb) +{ + if (sock_flag(sk, SOCK_RXQ_OVFL) && skb && skb->dropcount) + put_cmsg(msg, SOL_SOCKET, SO_RXQ_OVFL, + sizeof(__u32), &skb->dropcount); +} + +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); + +static inline int __sock_recvmsg_nosec(struct kiocb *iocb, struct socket *sock, + struct msghdr *msg, size_t size, int flags) { - int err; struct sock_iocb *si = kiocb_to_siocb(iocb); si->sock = sock; @@ -636,13 +675,17 @@ static inline int __sock_recvmsg(struct kiocb *iocb, struct socket *sock, si->size = size; si->flags = flags; - err = security_socket_recvmsg(sock, msg, size, flags); - if (err) - return err; - return sock->ops->recvmsg(iocb, sock, msg, size, flags); } +static inline int __sock_recvmsg(struct kiocb *iocb, struct socket *sock, + struct msghdr *msg, size_t size, int flags) +{ + int err = security_socket_recvmsg(sock, msg, size, flags); + + return err ?: __sock_recvmsg_nosec(iocb, sock, msg, size, flags); +} + int sock_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, int flags) { @@ -658,6 +701,21 @@ int sock_recvmsg(struct socket *sock, struct msghdr *msg, return ret; } +static int sock_recvmsg_nosec(struct socket *sock, struct msghdr *msg, + size_t size, int flags) +{ + struct kiocb iocb; + struct sock_iocb siocb; + int ret; + + init_sync_kiocb(&iocb, NULL); + iocb.private = &siocb; + ret = __sock_recvmsg_nosec(&iocb, sock, msg, size, flags); + if (-EIOCBQUEUED == ret) + ret = wait_on_sync_kiocb(&iocb); + return ret; +} + int kernel_recvmsg(struct socket *sock, struct msghdr *msg, struct kvec *vec, size_t num, size_t size, int flags) { @@ -692,7 +750,7 @@ static ssize_t sock_sendpage(struct file *file, struct page *page, if (more) flags |= MSG_MORE; - return sock->ops->sendpage(sock, page, offset, size, flags); + return kernel_sendpage(sock, page, offset, size, flags); } static ssize_t sock_splice_read(struct file *file, loff_t *ppos, @@ -701,6 +759,9 @@ static ssize_t sock_splice_read(struct file *file, loff_t *ppos, { struct socket *sock = file->private_data; + if (unlikely(!sock->ops->splice_read)) + return -EINVAL; + return sock->ops->splice_read(sock, ppos, pipe, len, flags); } @@ -839,6 +900,24 @@ void dlci_ioctl_set(int (*hook) (unsigned int, void __user *)) EXPORT_SYMBOL(dlci_ioctl_set); +static long sock_do_ioctl(struct net *net, struct socket *sock, + unsigned int cmd, unsigned long arg) +{ + int err; + void __user *argp = (void __user *)arg; + + err = sock->ops->ioctl(sock, cmd, arg); + + /* + * If this ioctl is unknown try to hand it down + * to the NIC driver. + */ + if (err == -ENOIOCTLCMD) + err = dev_ioctl(net, cmd, argp); + + return err; +} + /* * With an ioctl, arg may well be a user mode pointer, but we don't know * what to do with it - that's up to the protocol still. @@ -854,15 +933,15 @@ static long sock_ioctl(struct file *file, unsigned cmd, unsigned long arg) sock = file->private_data; sk = sock->sk; - net = sk->sk_net; + net = sock_net(sk); if (cmd >= SIOCDEVPRIVATE && cmd <= (SIOCDEVPRIVATE + 15)) { err = dev_ioctl(net, cmd, argp); } else -#ifdef CONFIG_WIRELESS_EXT +#ifdef CONFIG_WEXT_CORE if (cmd >= SIOCIWFIRST && cmd <= SIOCIWLAST) { err = dev_ioctl(net, cmd, argp); } else -#endif /* CONFIG_WIRELESS_EXT */ +#endif switch (cmd) { case FIOSETOWN: case SIOCSPGRP: @@ -906,21 +985,13 @@ static long sock_ioctl(struct file *file, unsigned cmd, unsigned long arg) 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); - - /* - * If this ioctl is unknown try to hand it down - * to the NIC driver. - */ - if (err == -ENOIOCTLCMD) - err = dev_ioctl(net, cmd, argp); + err = sock_do_ioctl(net, sock, cmd, arg); break; } return err; @@ -985,7 +1056,6 @@ static int sock_close(struct inode *inode, struct file *filp) printk(KERN_DEBUG "sock_close: NULL inode\n"); return 0; } - sock_fasync(-1, filp, 0); sock_release(SOCKET_I(inode)); return 0; } @@ -1027,6 +1097,13 @@ static int sock_fasync(int fd, struct file *filp, int on) 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) @@ -1048,11 +1125,14 @@ static int sock_fasync(int fd, struct file *filp, int on) fna->fa_next = sock->fasync_list; write_lock_bh(&sk->sk_callback_lock); sock->fasync_list = fna; + 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); } @@ -1070,20 +1150,19 @@ int sock_wake_async(struct socket *sock, int how, int band) 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; @@ -1138,7 +1217,7 @@ static int __sock_create(struct net *net, int family, int type, int protocol, sock->type = type; -#if defined(CONFIG_KMOD) +#ifdef CONFIG_MODULES /* Attempt to load a protocol module if the find failed. * * 12/09/1996 Marcin: But! this makes REALLY only sense, if the user @@ -1165,7 +1244,7 @@ static int __sock_create(struct net *net, int family, int type, int protocol, /* Now protected by module ref count */ rcu_read_unlock(); - err = pf->create(net, sock, protocol); + err = pf->create(net, sock, protocol, kern); if (err < 0) goto out_module_put; @@ -1212,16 +1291,31 @@ int sock_create_kern(int family, int type, int protocol, struct socket **res) return __sock_create(&init_net, family, type, protocol, res, 1); } -asmlinkage long sys_socket(int family, int type, int protocol) +SYSCALL_DEFINE3(socket, int, family, int, type, int, protocol) { int retval; struct socket *sock; + int flags; + + /* Check the SOCK_* constants for consistency. */ + BUILD_BUG_ON(SOCK_CLOEXEC != O_CLOEXEC); + BUILD_BUG_ON((SOCK_MAX | SOCK_TYPE_MASK) != SOCK_TYPE_MASK); + BUILD_BUG_ON(SOCK_CLOEXEC & SOCK_TYPE_MASK); + BUILD_BUG_ON(SOCK_NONBLOCK & SOCK_TYPE_MASK); + + flags = type & ~SOCK_TYPE_MASK; + if (flags & ~(SOCK_CLOEXEC | SOCK_NONBLOCK)) + return -EINVAL; + type &= SOCK_TYPE_MASK; + + if (SOCK_NONBLOCK != O_NONBLOCK && (flags & SOCK_NONBLOCK)) + flags = (flags & ~SOCK_NONBLOCK) | O_NONBLOCK; retval = sock_create(family, type, protocol, &sock); if (retval < 0) goto out; - retval = sock_map_fd(sock); + retval = sock_map_fd(sock, flags & (O_CLOEXEC | O_NONBLOCK)); if (retval < 0) goto out_release; @@ -1238,12 +1332,21 @@ out_release: * Create a pair of connected sockets. */ -asmlinkage long sys_socketpair(int family, int type, int protocol, - int __user *usockvec) +SYSCALL_DEFINE4(socketpair, int, family, int, type, int, protocol, + int __user *, usockvec) { struct socket *sock1, *sock2; int fd1, fd2, err; struct file *newfile1, *newfile2; + int flags; + + flags = type & ~SOCK_TYPE_MASK; + if (flags & ~(SOCK_CLOEXEC | SOCK_NONBLOCK)) + return -EINVAL; + type &= SOCK_TYPE_MASK; + + if (SOCK_NONBLOCK != O_NONBLOCK && (flags & SOCK_NONBLOCK)) + flags = (flags & ~SOCK_NONBLOCK) | O_NONBLOCK; /* * Obtain the first socket and check if the underlying protocol @@ -1262,38 +1365,22 @@ asmlinkage long sys_socketpair(int family, int type, int protocol, if (err < 0) goto out_release_both; - fd1 = sock_alloc_fd(&newfile1); + fd1 = sock_alloc_file(sock1, &newfile1, flags); if (unlikely(fd1 < 0)) { err = fd1; goto out_release_both; } - fd2 = sock_alloc_fd(&newfile2); + 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); - 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; + put_unused_fd(fd1); + sock_release(sock2); + goto out; } + audit_fd_pair(fd1, fd2); fd_install(fd1, newfile1); fd_install(fd2, newfile2); /* fd1 and fd2 may be already another descriptors. @@ -1316,17 +1403,6 @@ 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; } /* @@ -1337,23 +1413,23 @@ out_fd: * the protocol layer (having also checked the address is ok). */ -asmlinkage long sys_bind(int fd, struct sockaddr __user *umyaddr, int addrlen) +SYSCALL_DEFINE3(bind, int, fd, struct sockaddr __user *, umyaddr, int, addrlen) { struct socket *sock; - char address[MAX_SOCK_ADDR]; + struct sockaddr_storage address; int err, fput_needed; sock = sockfd_lookup_light(fd, &err, &fput_needed); if (sock) { - err = move_addr_to_kernel(umyaddr, addrlen, address); + err = move_addr_to_kernel(umyaddr, addrlen, (struct sockaddr *)&address); if (err >= 0) { err = security_socket_bind(sock, - (struct sockaddr *)address, + (struct sockaddr *)&address, addrlen); if (!err) err = sock->ops->bind(sock, (struct sockaddr *) - address, addrlen); + &address, addrlen); } fput_light(sock->file, fput_needed); } @@ -1366,17 +1442,17 @@ asmlinkage long sys_bind(int fd, struct sockaddr __user *umyaddr, int addrlen) * ready for listening. */ -int sysctl_somaxconn __read_mostly = SOMAXCONN; - -asmlinkage long sys_listen(int fd, int backlog) +SYSCALL_DEFINE2(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) @@ -1399,13 +1475,19 @@ asmlinkage long sys_listen(int fd, int backlog) * clean when we restucture accept also. */ -asmlinkage long sys_accept(int fd, struct sockaddr __user *upeer_sockaddr, - int __user *upeer_addrlen) +SYSCALL_DEFINE4(accept4, int, fd, struct sockaddr __user *, upeer_sockaddr, + int __user *, upeer_addrlen, int, flags) { struct socket *sock, *newsock; struct file *newfile; int err, len, newfd, fput_needed; - char address[MAX_SOCK_ADDR]; + struct sockaddr_storage address; + + if (flags & ~(SOCK_CLOEXEC | SOCK_NONBLOCK)) + return -EINVAL; + + if (SOCK_NONBLOCK != O_NONBLOCK && (flags & SOCK_NONBLOCK)) + flags = (flags & ~SOCK_NONBLOCK) | O_NONBLOCK; sock = sockfd_lookup_light(fd, &err, &fput_needed); if (!sock) @@ -1424,17 +1506,13 @@ asmlinkage long sys_accept(int fd, struct sockaddr __user *upeer_sockaddr, */ __module_get(newsock->ops->owner); - newfd = sock_alloc_fd(&newfile); + 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); - if (err < 0) - goto out_fd_simple; - err = security_socket_accept(sock, newsock); if (err) goto out_fd; @@ -1444,13 +1522,13 @@ asmlinkage long sys_accept(int fd, struct sockaddr __user *upeer_sockaddr, goto out_fd; if (upeer_sockaddr) { - if (newsock->ops->getname(newsock, (struct sockaddr *)address, + if (newsock->ops->getname(newsock, (struct sockaddr *)&address, &len, 2) < 0) { err = -ECONNABORTED; goto out_fd; } - err = move_addr_to_user(address, len, upeer_sockaddr, - upeer_addrlen); + err = move_addr_to_user((struct sockaddr *)&address, + len, upeer_sockaddr, upeer_addrlen); if (err < 0) goto out_fd; } @@ -1460,23 +1538,22 @@ asmlinkage long sys_accept(int fd, struct sockaddr __user *upeer_sockaddr, fd_install(newfd, newfile); err = newfd; - security_socket_post_accept(sock, newsock); - out_put: 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); goto out_put; } +SYSCALL_DEFINE3(accept, int, fd, struct sockaddr __user *, upeer_sockaddr, + int __user *, upeer_addrlen) +{ + return sys_accept4(fd, upeer_sockaddr, upeer_addrlen, 0); +} + /* * Attempt to connect to a socket with the server address. The address * is in user space so we verify it is OK and move it to kernel space. @@ -1489,26 +1566,26 @@ out_fd: * include the -EINPROGRESS status for such sockets. */ -asmlinkage long sys_connect(int fd, struct sockaddr __user *uservaddr, - int addrlen) +SYSCALL_DEFINE3(connect, int, fd, struct sockaddr __user *, uservaddr, + int, addrlen) { struct socket *sock; - char address[MAX_SOCK_ADDR]; + struct sockaddr_storage address; int err, fput_needed; sock = sockfd_lookup_light(fd, &err, &fput_needed); if (!sock) goto out; - err = move_addr_to_kernel(uservaddr, addrlen, address); + err = move_addr_to_kernel(uservaddr, addrlen, (struct sockaddr *)&address); if (err < 0) goto out_put; err = - security_socket_connect(sock, (struct sockaddr *)address, addrlen); + security_socket_connect(sock, (struct sockaddr *)&address, addrlen); if (err) goto out_put; - err = sock->ops->connect(sock, (struct sockaddr *)address, addrlen, + err = sock->ops->connect(sock, (struct sockaddr *)&address, addrlen, sock->file->f_flags); out_put: fput_light(sock->file, fput_needed); @@ -1521,11 +1598,11 @@ out: * name to user space. */ -asmlinkage long sys_getsockname(int fd, struct sockaddr __user *usockaddr, - int __user *usockaddr_len) +SYSCALL_DEFINE3(getsockname, int, fd, struct sockaddr __user *, usockaddr, + int __user *, usockaddr_len) { struct socket *sock; - char address[MAX_SOCK_ADDR]; + struct sockaddr_storage address; int len, err, fput_needed; sock = sockfd_lookup_light(fd, &err, &fput_needed); @@ -1536,10 +1613,10 @@ asmlinkage long sys_getsockname(int fd, struct sockaddr __user *usockaddr, if (err) goto out_put; - err = sock->ops->getname(sock, (struct sockaddr *)address, &len, 0); + err = sock->ops->getname(sock, (struct sockaddr *)&address, &len, 0); if (err) goto out_put; - err = move_addr_to_user(address, len, usockaddr, usockaddr_len); + err = move_addr_to_user((struct sockaddr *)&address, len, usockaddr, usockaddr_len); out_put: fput_light(sock->file, fput_needed); @@ -1552,11 +1629,11 @@ out: * name to user space. */ -asmlinkage long sys_getpeername(int fd, struct sockaddr __user *usockaddr, - int __user *usockaddr_len) +SYSCALL_DEFINE3(getpeername, int, fd, struct sockaddr __user *, usockaddr, + int __user *, usockaddr_len) { struct socket *sock; - char address[MAX_SOCK_ADDR]; + struct sockaddr_storage address; int len, err, fput_needed; sock = sockfd_lookup_light(fd, &err, &fput_needed); @@ -1568,10 +1645,10 @@ asmlinkage long sys_getpeername(int fd, struct sockaddr __user *usockaddr, } err = - sock->ops->getname(sock, (struct sockaddr *)address, &len, + sock->ops->getname(sock, (struct sockaddr *)&address, &len, 1); if (!err) - err = move_addr_to_user(address, len, usockaddr, + err = move_addr_to_user((struct sockaddr *)&address, len, usockaddr, usockaddr_len); fput_light(sock->file, fput_needed); } @@ -1584,26 +1661,21 @@ asmlinkage long sys_getpeername(int fd, struct sockaddr __user *usockaddr, * the protocol. */ -asmlinkage long sys_sendto(int fd, void __user *buff, size_t len, - unsigned flags, struct sockaddr __user *addr, - int addr_len) +SYSCALL_DEFINE6(sendto, int, fd, void __user *, buff, size_t, len, + unsigned, flags, struct sockaddr __user *, addr, + int, addr_len) { struct socket *sock; - char address[MAX_SOCK_ADDR]; + struct sockaddr_storage address; int err; struct msghdr msg; struct iovec iov; int fput_needed; - struct file *sock_file; - sock_file = fget_light(fd, &fput_needed); - err = -EBADF; - if (!sock_file) + sock = sockfd_lookup_light(fd, &err, &fput_needed); + if (!sock) goto out; - sock = sock_from_file(sock_file, &err); - if (!sock) - goto out_put; iov.iov_base = buff; iov.iov_len = len; msg.msg_name = NULL; @@ -1613,10 +1685,10 @@ asmlinkage long sys_sendto(int fd, void __user *buff, size_t len, msg.msg_controllen = 0; msg.msg_namelen = 0; if (addr) { - err = move_addr_to_kernel(addr, addr_len, address); + err = move_addr_to_kernel(addr, addr_len, (struct sockaddr *)&address); if (err < 0) goto out_put; - msg.msg_name = address; + msg.msg_name = (struct sockaddr *)&address; msg.msg_namelen = addr_len; } if (sock->file->f_flags & O_NONBLOCK) @@ -1625,7 +1697,7 @@ asmlinkage long sys_sendto(int fd, void __user *buff, size_t len, err = sock_sendmsg(sock, &msg, len); out_put: - fput_light(sock_file, fput_needed); + fput_light(sock->file, fput_needed); out: return err; } @@ -1634,7 +1706,8 @@ out: * Send a datagram down a socket. */ -asmlinkage long sys_send(int fd, void __user *buff, size_t len, unsigned flags) +SYSCALL_DEFINE4(send, int, fd, void __user *, buff, size_t, len, + unsigned, flags) { return sys_sendto(fd, buff, len, flags, NULL, 0); } @@ -1645,26 +1718,20 @@ asmlinkage long sys_send(int fd, void __user *buff, size_t len, unsigned flags) * sender address from kernel to user space. */ -asmlinkage long sys_recvfrom(int fd, void __user *ubuf, size_t size, - unsigned flags, struct sockaddr __user *addr, - int __user *addr_len) +SYSCALL_DEFINE6(recvfrom, int, fd, void __user *, ubuf, size_t, size, + unsigned, flags, struct sockaddr __user *, addr, + int __user *, addr_len) { struct socket *sock; struct iovec iov; struct msghdr msg; - char address[MAX_SOCK_ADDR]; + struct sockaddr_storage address; int err, err2; - struct file *sock_file; int fput_needed; - sock_file = fget_light(fd, &fput_needed); - err = -EBADF; - if (!sock_file) - goto out; - - sock = sock_from_file(sock_file, &err); + sock = sockfd_lookup_light(fd, &err, &fput_needed); if (!sock) - goto out_put; + goto out; msg.msg_control = NULL; msg.msg_controllen = 0; @@ -1672,19 +1739,20 @@ asmlinkage long sys_recvfrom(int fd, void __user *ubuf, size_t size, msg.msg_iov = &iov; iov.iov_len = size; iov.iov_base = ubuf; - msg.msg_name = address; - msg.msg_namelen = MAX_SOCK_ADDR; + msg.msg_name = (struct sockaddr *)&address; + msg.msg_namelen = sizeof(address); if (sock->file->f_flags & O_NONBLOCK) flags |= MSG_DONTWAIT; err = sock_recvmsg(sock, &msg, size, flags); if (err >= 0 && addr != NULL) { - err2 = move_addr_to_user(address, msg.msg_namelen, addr, addr_len); + err2 = move_addr_to_user((struct sockaddr *)&address, + msg.msg_namelen, addr, addr_len); if (err2 < 0) err = err2; } -out_put: - fput_light(sock_file, fput_needed); + + fput_light(sock->file, fput_needed); out: return err; } @@ -1704,8 +1772,8 @@ asmlinkage long sys_recv(int fd, void __user *ubuf, size_t size, * to pass the user mode parameter for the protocols to sort out. */ -asmlinkage long sys_setsockopt(int fd, int level, int optname, - char __user *optval, int optlen) +SYSCALL_DEFINE5(setsockopt, int, fd, int, level, int, optname, + char __user *, optval, int, optlen) { int err, fput_needed; struct socket *sock; @@ -1738,8 +1806,8 @@ out_put: * to pass a user mode parameter for the protocols to sort out. */ -asmlinkage long sys_getsockopt(int fd, int level, int optname, - char __user *optval, int __user *optlen) +SYSCALL_DEFINE5(getsockopt, int, fd, int, level, int, optname, + char __user *, optval, int __user *, optlen) { int err, fput_needed; struct socket *sock; @@ -1768,7 +1836,7 @@ out_put: * Shutdown a socket. */ -asmlinkage long sys_shutdown(int fd, int how) +SYSCALL_DEFINE2(shutdown, int, fd, int, how) { int err, fput_needed; struct socket *sock; @@ -1794,12 +1862,12 @@ asmlinkage long sys_shutdown(int fd, int how) * BSD sendmsg interface */ -asmlinkage long sys_sendmsg(int fd, struct msghdr __user *msg, unsigned flags) +SYSCALL_DEFINE3(sendmsg, int, fd, struct msghdr __user *, msg, unsigned, flags) { struct compat_msghdr __user *msg_compat = (struct compat_msghdr __user *)msg; struct socket *sock; - char address[MAX_SOCK_ADDR]; + struct sockaddr_storage address; struct iovec iovstack[UIO_FASTIOV], *iov = iovstack; unsigned char ctl[sizeof(struct cmsghdr) + 20] __attribute__ ((aligned(sizeof(__kernel_size_t)))); @@ -1837,9 +1905,13 @@ asmlinkage long sys_sendmsg(int fd, struct msghdr __user *msg, unsigned flags) /* This will also move the address data into kernel space */ if (MSG_CMSG_COMPAT & flags) { - err = verify_compat_iovec(&msg_sys, iov, address, VERIFY_READ); + err = verify_compat_iovec(&msg_sys, iov, + (struct sockaddr *)&address, + VERIFY_READ); } else - err = verify_iovec(&msg_sys, iov, address, VERIFY_READ); + err = verify_iovec(&msg_sys, iov, + (struct sockaddr *)&address, + VERIFY_READ); if (err < 0) goto out_freeiov; total_len = err; @@ -1892,52 +1964,41 @@ out: return err; } -/* - * BSD recvmsg interface - */ - -asmlinkage long sys_recvmsg(int fd, struct msghdr __user *msg, - unsigned int flags) +static int __sys_recvmsg(struct socket *sock, struct msghdr __user *msg, + struct msghdr *msg_sys, unsigned flags, int nosec) { struct compat_msghdr __user *msg_compat = (struct compat_msghdr __user *)msg; - struct socket *sock; struct iovec iovstack[UIO_FASTIOV]; struct iovec *iov = iovstack; - struct msghdr msg_sys; unsigned long cmsg_ptr; int err, iov_size, total_len, len; - int fput_needed; /* kernel mode address */ - char addr[MAX_SOCK_ADDR]; + struct sockaddr_storage addr; /* user mode address pointers */ struct sockaddr __user *uaddr; int __user *uaddr_len; if (MSG_CMSG_COMPAT & flags) { - if (get_compat_msghdr(&msg_sys, msg_compat)) + 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); - if (!sock) - goto out; - err = -EMSGSIZE; - if (msg_sys.msg_iovlen > UIO_MAXIOV) - goto out_put; + if (msg_sys->msg_iovlen > UIO_MAXIOV) + goto out; /* Check whether to allocate the iovec area */ err = -ENOMEM; - iov_size = msg_sys.msg_iovlen * sizeof(struct iovec); - if (msg_sys.msg_iovlen > UIO_FASTIOV) { + iov_size = msg_sys->msg_iovlen * sizeof(struct iovec); + if (msg_sys->msg_iovlen > UIO_FASTIOV) { iov = sock_kmalloc(sock->sk, iov_size, GFP_KERNEL); if (!iov) - goto out_put; + goto out; } /* @@ -1945,41 +2006,47 @@ asmlinkage long sys_recvmsg(int fd, struct msghdr __user *msg, * kernel msghdr to use the kernel address space) */ - uaddr = (__force 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); + err = verify_compat_iovec(msg_sys, iov, + (struct sockaddr *)&addr, + VERIFY_WRITE); } else - err = verify_iovec(&msg_sys, iov, addr, VERIFY_WRITE); + err = verify_iovec(msg_sys, iov, + (struct sockaddr *)&addr, + VERIFY_WRITE); if (err < 0) goto out_freeiov; total_len = err; - cmsg_ptr = (unsigned long)msg_sys.msg_control; - msg_sys.msg_flags = flags & (MSG_CMSG_CLOEXEC|MSG_CMSG_COMPAT); + cmsg_ptr = (unsigned long)msg_sys->msg_control; + msg_sys->msg_flags = flags & (MSG_CMSG_CLOEXEC|MSG_CMSG_COMPAT); if (sock->file->f_flags & O_NONBLOCK) flags |= MSG_DONTWAIT; - err = sock_recvmsg(sock, &msg_sys, total_len, flags); + err = (nosec ? sock_recvmsg_nosec : sock_recvmsg)(sock, msg_sys, + total_len, flags); if (err < 0) goto out_freeiov; len = err; if (uaddr != NULL) { - err = move_addr_to_user(addr, msg_sys.msg_namelen, uaddr, + err = move_addr_to_user((struct sockaddr *)&addr, + msg_sys->msg_namelen, uaddr, uaddr_len); if (err < 0) goto out_freeiov; } - err = __put_user((msg_sys.msg_flags & ~MSG_CMSG_COMPAT), + err = __put_user((msg_sys->msg_flags & ~MSG_CMSG_COMPAT), COMPAT_FLAGS(msg)); if (err) goto out_freeiov; if (MSG_CMSG_COMPAT & flags) - err = __put_user((unsigned long)msg_sys.msg_control - cmsg_ptr, + err = __put_user((unsigned long)msg_sys->msg_control - cmsg_ptr, &msg_compat->msg_controllen); else - err = __put_user((unsigned long)msg_sys.msg_control - cmsg_ptr, + err = __put_user((unsigned long)msg_sys->msg_control - cmsg_ptr, &msg->msg_controllen); if (err) goto out_freeiov; @@ -1988,20 +2055,166 @@ asmlinkage long sys_recvmsg(int fd, struct msghdr __user *msg, out_freeiov: if (iov != iovstack) sock_kfree_s(sock->sk, iov, iov_size); -out_put: +out: + return err; +} + +/* + * BSD recvmsg interface + */ + +SYSCALL_DEFINE3(recvmsg, int, fd, struct msghdr __user *, msg, + unsigned int, flags) +{ + int fput_needed, err; + struct msghdr msg_sys; + struct socket *sock = sockfd_lookup_light(fd, &err, &fput_needed); + + if (!sock) + goto out; + + err = __sys_recvmsg(sock, msg, &msg_sys, flags, 0); + fput_light(sock->file, fput_needed); out: return err; } -#ifdef __ARCH_WANT_SYS_SOCKETCALL +/* + * Linux recvmmsg interface + */ + +int __sys_recvmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen, + unsigned int flags, struct timespec *timeout) +{ + 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; + + if (timeout && + poll_select_set_timeout(&end_time, timeout->tv_sec, + timeout->tv_nsec)) + return -EINVAL; + + datagrams = 0; + + sock = sockfd_lookup_light(fd, &err, &fput_needed); + if (!sock) + return err; + + err = sock_error(sock->sk); + if (err) + 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. + */ + 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; + ++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); + if (timeout->tv_sec < 0) { + timeout->tv_sec = timeout->tv_nsec = 0; + break; + } + + /* Timeout, return less than vlen datagrams */ + if (timeout->tv_nsec == 0 && timeout->tv_sec == 0) + break; + } + + /* Out of band data, return right away */ + if (msg_sys.msg_flags & MSG_OOB) + break; + } + +out_put: + fput_light(sock->file, fput_needed); + + if (err == 0) + return datagrams; + + if (datagrams != 0) { + /* + * We may return less entries than requested (vlen) if the + * sock is non block and there aren't enough datagrams... + */ + if (err != -EAGAIN) { + /* + * ... or if recvmsg returns an error after we + * received some datagrams, where we record the + * error to return on the next call or if the + * app asks about it using getsockopt(SO_ERROR). + */ + sock->sk->sk_err = -err; + } + + return datagrams; + } + + return err; +} + +SYSCALL_DEFINE5(recvmmsg, int, fd, struct mmsghdr __user *, mmsg, + unsigned int, vlen, unsigned int, flags, + struct timespec __user *, timeout) +{ + int datagrams; + struct timespec timeout_sys; + + if (!timeout) + return __sys_recvmmsg(fd, mmsg, vlen, flags, NULL); + + if (copy_from_user(&timeout_sys, timeout, sizeof(timeout_sys))) + return -EFAULT; + + datagrams = __sys_recvmmsg(fd, mmsg, vlen, flags, &timeout_sys); + + if (datagrams > 0 && + copy_to_user(timeout, &timeout_sys, sizeof(timeout_sys))) + datagrams = -EFAULT; + + return datagrams; +} + +#ifdef __ARCH_WANT_SYS_SOCKETCALL /* Argument list sizes for sys_socketcall */ #define AL(x) ((x) * sizeof(unsigned long)) -static const unsigned char nargs[18]={ +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(6),AL(2),AL(5),AL(5),AL(3),AL(3), + AL(4),AL(5) }; #undef AL @@ -2014,22 +2227,25 @@ static const unsigned char nargs[18]={ * it is set by the callees. */ -asmlinkage long sys_socketcall(int call, unsigned long __user *args) +SYSCALL_DEFINE2(socketcall, int, call, unsigned long __user *, args) { unsigned long a[6]; unsigned long a0, a1; int err; + unsigned int len; - if (call < 1 || call > SYS_RECVMSG) + if (call < 1 || call > SYS_RECVMMSG) + return -EINVAL; + + len = nargs[call]; + if (len > sizeof(a)) return -EINVAL; /* copy_from_user should be SMP safe. */ - if (copy_from_user(a, args, nargs[call])) + if (copy_from_user(a, args, len)) return -EFAULT; - err = audit_socketcall(nargs[call] / sizeof(unsigned long), a); - if (err) - return err; + audit_socketcall(nargs[call] / sizeof(unsigned long), a); a0 = a[0]; a1 = a[1]; @@ -2048,9 +2264,8 @@ asmlinkage long sys_socketcall(int call, unsigned long __user *args) err = sys_listen(a0, a1); break; case SYS_ACCEPT: - err = - sys_accept(a0, (struct sockaddr __user *)a1, - (int __user *)a[2]); + err = sys_accept4(a0, (struct sockaddr __user *)a1, + (int __user *)a[2], 0); break; case SYS_GETSOCKNAME: err = @@ -2097,6 +2312,14 @@ asmlinkage long sys_socketcall(int call, unsigned long __user *args) case SYS_RECVMSG: err = sys_recvmsg(a0, (struct msghdr __user *)a1, a[2]); break; + case SYS_RECVMMSG: + err = sys_recvmmsg(a0, (struct mmsghdr __user *)a1, a[2], a[3], + (struct timespec __user *)a[4]); + break; + case SYS_ACCEPT4: + err = sys_accept4(a0, (struct sockaddr __user *)a1, + (int __user *)a[2], a[3]); + break; default: err = -EINVAL; break; @@ -2215,15 +2438,573 @@ void socket_seq_show(struct seq_file *seq) #endif /* CONFIG_PROC_FS */ #ifdef CONFIG_COMPAT +static int do_siocgstamp(struct net *net, struct socket *sock, + unsigned int cmd, struct compat_timeval __user *up) +{ + mm_segment_t old_fs = get_fs(); + struct timeval ktv; + int err; + + set_fs(KERNEL_DS); + err = sock_do_ioctl(net, sock, cmd, (unsigned long)&ktv); + set_fs(old_fs); + if (!err) { + err = put_user(ktv.tv_sec, &up->tv_sec); + err |= __put_user(ktv.tv_usec, &up->tv_usec); + } + return err; +} + +static int do_siocgstampns(struct net *net, struct socket *sock, + unsigned int cmd, struct compat_timespec __user *up) +{ + mm_segment_t old_fs = get_fs(); + struct timespec kts; + int err; + + set_fs(KERNEL_DS); + err = sock_do_ioctl(net, sock, cmd, (unsigned long)&kts); + set_fs(old_fs); + if (!err) { + err = put_user(kts.tv_sec, &up->tv_sec); + err |= __put_user(kts.tv_nsec, &up->tv_nsec); + } + return err; +} + +static int dev_ifname32(struct net *net, struct compat_ifreq __user *uifr32) +{ + struct ifreq __user *uifr; + int err; + + uifr = compat_alloc_user_space(sizeof(struct ifreq)); + if (copy_in_user(uifr, uifr32, sizeof(struct compat_ifreq))) + return -EFAULT; + + err = dev_ioctl(net, SIOCGIFNAME, uifr); + if (err) + return err; + + if (copy_in_user(uifr32, uifr, sizeof(struct compat_ifreq))) + return -EFAULT; + + return 0; +} + +static int dev_ifconf(struct net *net, struct compat_ifconf __user *uifc32) +{ + struct compat_ifconf ifc32; + struct ifconf ifc; + struct ifconf __user *uifc; + struct compat_ifreq __user *ifr32; + struct ifreq __user *ifr; + unsigned int i, j; + int err; + + if (copy_from_user(&ifc32, uifc32, sizeof(struct compat_ifconf))) + return -EFAULT; + + if (ifc32.ifcbuf == 0) { + ifc32.ifc_len = 0; + ifc.ifc_len = 0; + 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); + 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)) { + if (copy_in_user(ifr, ifr32, sizeof(struct compat_ifreq))) + return -EFAULT; + ifr++; + ifr32++; + } + } + if (copy_to_user(uifc, &ifc, sizeof(struct ifconf))) + return -EFAULT; + + err = dev_ioctl(net, SIOCGIFCONF, uifc); + if (err) + return err; + + if (copy_from_user(&ifc, uifc, sizeof(struct ifconf))) + return -EFAULT; + + 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))) + return -EFAULT; + ifr32++; + ifr++; + } + + if (ifc32.ifcbuf == 0) { + /* Translate from 64-bit structure multiple to + * a 32-bit one. + */ + i = ifc.ifc_len; + i = ((i / sizeof(struct ifreq)) * sizeof(struct compat_ifreq)); + ifc32.ifc_len = i; + } else { + ifc32.ifc_len = i; + } + if (copy_to_user(uifc32, &ifc32, sizeof(struct compat_ifconf))) + return -EFAULT; + + return 0; +} + +static int ethtool_ioctl(struct net *net, struct compat_ifreq __user *ifr32) +{ + struct ifreq __user *ifr; + u32 data; + void __user *datap; + + ifr = compat_alloc_user_space(sizeof(*ifr)); + + if (copy_in_user(&ifr->ifr_name, &ifr32->ifr_name, IFNAMSIZ)) + return -EFAULT; + + if (get_user(data, &ifr32->ifr_ifru.ifru_data)) + return -EFAULT; + + datap = compat_ptr(data); + if (put_user(datap, &ifr->ifr_ifru.ifru_data)) + return -EFAULT; + + return dev_ioctl(net, SIOCETHTOOL, ifr); +} + +static int compat_siocwandev(struct net *net, struct compat_ifreq __user *uifr32) +{ + void __user *uptr; + compat_uptr_t uptr32; + struct ifreq __user *uifr; + + uifr = compat_alloc_user_space(sizeof (*uifr)); + if (copy_in_user(uifr, uifr32, sizeof(struct compat_ifreq))) + return -EFAULT; + + if (get_user(uptr32, &uifr32->ifr_settings.ifs_ifsu)) + return -EFAULT; + + uptr = compat_ptr(uptr32); + + if (put_user(uptr, &uifr->ifr_settings.ifs_ifsu.raw_hdlc)) + return -EFAULT; + + return dev_ioctl(net, SIOCWANDEV, uifr); +} + +static int bond_ioctl(struct net *net, unsigned int cmd, + struct compat_ifreq __user *ifr32) +{ + struct ifreq kifr; + struct ifreq __user *uifr; + mm_segment_t old_fs; + int err; + u32 data; + void __user *datap; + + switch (cmd) { + case SIOCBONDENSLAVE: + case SIOCBONDRELEASE: + case SIOCBONDSETHWADDR: + case SIOCBONDCHANGEACTIVE: + if (copy_from_user(&kifr, ifr32, sizeof(struct compat_ifreq))) + return -EFAULT; + + old_fs = get_fs(); + set_fs (KERNEL_DS); + err = dev_ioctl(net, cmd, &kifr); + set_fs (old_fs); + + return err; + case SIOCBONDSLAVEINFOQUERY: + case SIOCBONDINFOQUERY: + uifr = compat_alloc_user_space(sizeof(*uifr)); + if (copy_in_user(&uifr->ifr_name, &ifr32->ifr_name, IFNAMSIZ)) + return -EFAULT; + + if (get_user(data, &ifr32->ifr_ifru.ifru_data)) + return -EFAULT; + + datap = compat_ptr(data); + if (put_user(datap, &uifr->ifr_ifru.ifru_data)) + return -EFAULT; + + return dev_ioctl(net, cmd, uifr); + default: + return -EINVAL; + }; +} + +static int siocdevprivate_ioctl(struct net *net, unsigned int cmd, + struct compat_ifreq __user *u_ifreq32) +{ + struct ifreq __user *u_ifreq64; + char tmp_buf[IFNAMSIZ]; + void __user *data64; + u32 data32; + + if (copy_from_user(&tmp_buf[0], &(u_ifreq32->ifr_ifrn.ifrn_name[0]), + IFNAMSIZ)) + return -EFAULT; + if (__get_user(data32, &u_ifreq32->ifr_ifru.ifru_data)) + return -EFAULT; + data64 = compat_ptr(data32); + + u_ifreq64 = compat_alloc_user_space(sizeof(*u_ifreq64)); + + /* Don't check these user accesses, just let that get trapped + * in the ioctl handler instead. + */ + if (copy_to_user(&u_ifreq64->ifr_ifrn.ifrn_name[0], &tmp_buf[0], + IFNAMSIZ)) + return -EFAULT; + if (__put_user(data64, &u_ifreq64->ifr_ifru.ifru_data)) + return -EFAULT; + + return dev_ioctl(net, cmd, u_ifreq64); +} + +static int dev_ifsioc(struct net *net, struct socket *sock, + unsigned int cmd, struct compat_ifreq __user *uifr32) +{ + struct ifreq __user *uifr; + int err; + + uifr = compat_alloc_user_space(sizeof(*uifr)); + if (copy_in_user(uifr, uifr32, sizeof(*uifr32))) + return -EFAULT; + + err = sock_do_ioctl(net, sock, cmd, (unsigned long)uifr); + + if (!err) { + switch (cmd) { + case SIOCGIFFLAGS: + case SIOCGIFMETRIC: + case SIOCGIFMTU: + case SIOCGIFMEM: + case SIOCGIFHWADDR: + case SIOCGIFINDEX: + case SIOCGIFADDR: + case SIOCGIFBRDADDR: + case SIOCGIFDSTADDR: + case SIOCGIFNETMASK: + case SIOCGIFPFLAGS: + case SIOCGIFTXQLEN: + case SIOCGMIIPHY: + case SIOCGMIIREG: + if (copy_in_user(uifr32, uifr, sizeof(*uifr32))) + err = -EFAULT; + break; + } + } + return err; +} + +static int compat_sioc_ifmap(struct net *net, unsigned int cmd, + struct compat_ifreq __user *uifr32) +{ + struct ifreq ifr; + struct compat_ifmap __user *uifmap32; + mm_segment_t old_fs; + int err; + + uifmap32 = &uifr32->ifr_ifru.ifru_map; + err = copy_from_user(&ifr, uifr32, sizeof(ifr.ifr_name)); + err |= __get_user(ifr.ifr_map.mem_start, &uifmap32->mem_start); + err |= __get_user(ifr.ifr_map.mem_end, &uifmap32->mem_end); + err |= __get_user(ifr.ifr_map.base_addr, &uifmap32->base_addr); + err |= __get_user(ifr.ifr_map.irq, &uifmap32->irq); + err |= __get_user(ifr.ifr_map.dma, &uifmap32->dma); + err |= __get_user(ifr.ifr_map.port, &uifmap32->port); + if (err) + return -EFAULT; + + old_fs = get_fs(); + set_fs (KERNEL_DS); + err = dev_ioctl(net, cmd, (void __user *)&ifr); + set_fs (old_fs); + + if (cmd == SIOCGIFMAP && !err) { + err = copy_to_user(uifr32, &ifr, sizeof(ifr.ifr_name)); + err |= __put_user(ifr.ifr_map.mem_start, &uifmap32->mem_start); + err |= __put_user(ifr.ifr_map.mem_end, &uifmap32->mem_end); + err |= __put_user(ifr.ifr_map.base_addr, &uifmap32->base_addr); + err |= __put_user(ifr.ifr_map.irq, &uifmap32->irq); + err |= __put_user(ifr.ifr_map.dma, &uifmap32->dma); + err |= __put_user(ifr.ifr_map.port, &uifmap32->port); + if (err) + err = -EFAULT; + } + return err; +} + +static int compat_siocshwtstamp(struct net *net, struct compat_ifreq __user *uifr32) +{ + void __user *uptr; + compat_uptr_t uptr32; + struct ifreq __user *uifr; + + uifr = compat_alloc_user_space(sizeof (*uifr)); + if (copy_in_user(uifr, uifr32, sizeof(struct compat_ifreq))) + return -EFAULT; + + if (get_user(uptr32, &uifr32->ifr_data)) + return -EFAULT; + + uptr = compat_ptr(uptr32); + + if (put_user(uptr, &uifr->ifr_data)) + return -EFAULT; + + return dev_ioctl(net, SIOCSHWTSTAMP, uifr); +} + +struct rtentry32 { + 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! */ + /* char * */ u32 rt_dev; /* forcing the device at add */ + u32 rt_mtu; /* per route MTU/Window */ + u32 rt_window; /* Window clamping */ + unsigned short rt_irtt; /* Initial RTT */ +}; + +struct in6_rtmsg32 { + struct in6_addr rtmsg_dst; + struct in6_addr rtmsg_src; + struct in6_addr rtmsg_gateway; + u32 rtmsg_type; + u16 rtmsg_dst_len; + u16 rtmsg_src_len; + u32 rtmsg_metric; + u32 rtmsg_info; + u32 rtmsg_flags; + s32 rtmsg_ifindex; +}; + +static int routing_ioctl(struct net *net, struct socket *sock, + unsigned int cmd, void __user *argp) +{ + int ret; + void *r = NULL; + struct in6_rtmsg r6; + struct rtentry r4; + char devname[16]; + u32 rtdev; + mm_segment_t old_fs = get_fs(); + + 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), + 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)); + + r = (void *) &r6; + } else { /* ipv4 */ + struct rtentry32 __user *ur4 = argp; + 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)); + if (rtdev) { + ret |= copy_from_user (devname, compat_ptr(rtdev), 15); + r4.rt_dev = devname; devname[15] = 0; + } else + r4.rt_dev = NULL; + + r = (void *) &r4; + } + + if (ret) { + ret = -EFAULT; + goto out; + } + + set_fs (KERNEL_DS); + ret = sock_do_ioctl(net, sock, cmd, (unsigned long) r); + set_fs (old_fs); + +out: + return ret; +} + +/* Since old style bridge ioctl's endup using SIOCDEVPRIVATE + * for some operations; this forces use of the newer bridge-utils that + * use compatiable ioctls + */ +static int old_bridge_ioctl(compat_ulong_t __user *argp) +{ + compat_ulong_t tmp; + + if (get_user(tmp, argp)) + return -EFAULT; + if (tmp == BRCTL_GET_VERSION) + return BRCTL_VERSION + 1; + return -EINVAL; +} + +static int compat_sock_ioctl_trans(struct file *file, struct socket *sock, + unsigned int cmd, unsigned long arg) +{ + void __user *argp = compat_ptr(arg); + struct sock *sk = sock->sk; + struct net *net = sock_net(sk); + + if (cmd >= SIOCDEVPRIVATE && cmd <= (SIOCDEVPRIVATE + 15)) + return siocdevprivate_ioctl(net, cmd, argp); + + switch (cmd) { + case SIOCSIFBR: + case SIOCGIFBR: + return old_bridge_ioctl(argp); + case SIOCGIFNAME: + return dev_ifname32(net, argp); + case SIOCGIFCONF: + return dev_ifconf(net, argp); + case SIOCETHTOOL: + return ethtool_ioctl(net, argp); + case SIOCWANDEV: + return compat_siocwandev(net, argp); + case SIOCGIFMAP: + case SIOCSIFMAP: + return compat_sioc_ifmap(net, cmd, argp); + case SIOCBONDENSLAVE: + case SIOCBONDRELEASE: + case SIOCBONDSETHWADDR: + case SIOCBONDSLAVEINFOQUERY: + case SIOCBONDINFOQUERY: + case SIOCBONDCHANGEACTIVE: + return bond_ioctl(net, cmd, argp); + case SIOCADDRT: + case SIOCDELRT: + return routing_ioctl(net, sock, cmd, argp); + case SIOCGSTAMP: + return do_siocgstamp(net, sock, cmd, argp); + case SIOCGSTAMPNS: + return do_siocgstampns(net, sock, cmd, argp); + case SIOCSHWTSTAMP: + return compat_siocshwtstamp(net, argp); + + case FIOSETOWN: + case SIOCSPGRP: + case FIOGETOWN: + case SIOCGPGRP: + case SIOCBRADDBR: + case SIOCBRDELBR: + case SIOCGIFVLAN: + case SIOCSIFVLAN: + case SIOCADDDLCI: + case SIOCDELDLCI: + return sock_ioctl(file, cmd, arg); + + case SIOCGIFFLAGS: + case SIOCSIFFLAGS: + case SIOCGIFMETRIC: + case SIOCSIFMETRIC: + case SIOCGIFMTU: + case SIOCSIFMTU: + case SIOCGIFMEM: + case SIOCSIFMEM: + case SIOCGIFHWADDR: + case SIOCSIFHWADDR: + case SIOCADDMULTI: + case SIOCDELMULTI: + case SIOCGIFINDEX: + case SIOCGIFADDR: + case SIOCSIFADDR: + case SIOCSIFHWBROADCAST: + case SIOCDIFADDR: + case SIOCGIFBRDADDR: + case SIOCSIFBRDADDR: + case SIOCGIFDSTADDR: + case SIOCSIFDSTADDR: + case SIOCGIFNETMASK: + case SIOCSIFNETMASK: + case SIOCSIFPFLAGS: + case SIOCGIFPFLAGS: + case SIOCGIFTXQLEN: + case SIOCSIFTXQLEN: + case SIOCBRADDIF: + case SIOCBRDELIF: + case SIOCSIFNAME: + case SIOCGMIIPHY: + case SIOCGMIIREG: + case SIOCSMIIREG: + return dev_ifsioc(net, sock, cmd, argp); + + case SIOCSARP: + case SIOCGARP: + case SIOCDARP: + case SIOCATMARK: + return sock_do_ioctl(net, sock, cmd, arg); + } + + /* Prevent warning from compat_sys_ioctl, these always + * result in -EINVAL in the native case anyway. */ + switch (cmd) { + case SIOCRTMSG: + case SIOCGIFCOUNT: + case SIOCSRARP: + case SIOCGRARP: + case SIOCDRARP: + case SIOCSIFLINK: + case SIOCGIFSLAVE: + case SIOCSIFSLAVE: + return -EINVAL; + } + + return -ENOIOCTLCMD; +} + static long compat_sock_ioctl(struct file *file, unsigned cmd, unsigned long arg) { struct socket *sock = file->private_data; int ret = -ENOIOCTLCMD; + struct sock *sk; + struct net *net; + + sk = sock->sk; + net = sock_net(sk); if (sock->ops->compat_ioctl) ret = sock->ops->compat_ioctl(sock, cmd, arg); + if (ret == -ENOIOCTLCMD && + (cmd >= SIOCIWFIRST && cmd <= SIOCIWLAST)) + ret = compat_wext_handle_ioctl(net, cmd, arg); + + if (ret == -ENOIOCTLCMD) + ret = compat_sock_ioctl_trans(file, sock, cmd, arg); + return ret; } #endif @@ -2256,6 +3037,7 @@ int kernel_accept(struct socket *sock, struct socket **newsock, int flags) } (*newsock)->ops = sock->ops; + __module_get((*newsock)->ops->owner); done: return err; @@ -2296,7 +3078,7 @@ int kernel_getsockopt(struct socket *sock, int level, int optname, } int kernel_setsockopt(struct socket *sock, int level, int optname, - char *optval, int optlen) + char *optval, unsigned int optlen) { mm_segment_t oldfs = get_fs(); int err; @@ -2337,9 +3119,6 @@ int kernel_sock_shutdown(struct socket *sock, enum sock_shutdown_cmd how) return sock->ops->shutdown(sock, how); } -/* ABI emulation layers need these two */ -EXPORT_SYMBOL(move_addr_to_kernel); -EXPORT_SYMBOL(move_addr_to_user); EXPORT_SYMBOL(sock_create); EXPORT_SYMBOL(sock_create_kern); EXPORT_SYMBOL(sock_create_lite);