diff options
Diffstat (limited to 'net/socket.c')
| -rw-r--r-- | net/socket.c | 1136 |
1 files changed, 453 insertions, 683 deletions
diff --git a/net/socket.c b/net/socket.c index 2eecf1517f76..00da9ce3dba0 100644 --- a/net/socket.c +++ b/net/socket.c @@ -52,6 +52,8 @@ * Based upon Swansea University Computer Society NET3.039 */ +#include <linux/bpf-cgroup.h> +#include <linux/ethtool.h> #include <linux/mm.h> #include <linux/socket.h> #include <linux/file.h> @@ -64,7 +66,6 @@ #include <linux/seq_file.h> #include <linux/mutex.h> #include <linux/if_bridge.h> -#include <linux/if_frad.h> #include <linux/if_vlan.h> #include <linux/ptp_classify.h> #include <linux/init.h> @@ -104,6 +105,7 @@ #include <linux/sockios.h> #include <net/busy_poll.h> #include <linux/errqueue.h> +#include <linux/ptp_clock_kernel.h> #ifdef CONFIG_NET_RX_BUSY_POLL unsigned int sysctl_net_busy_read __read_mostly; @@ -165,6 +167,55 @@ static const struct file_operations socket_file_ops = { .show_fdinfo = sock_show_fdinfo, }; +static const char * const pf_family_names[] = { + [PF_UNSPEC] = "PF_UNSPEC", + [PF_UNIX] = "PF_UNIX/PF_LOCAL", + [PF_INET] = "PF_INET", + [PF_AX25] = "PF_AX25", + [PF_IPX] = "PF_IPX", + [PF_APPLETALK] = "PF_APPLETALK", + [PF_NETROM] = "PF_NETROM", + [PF_BRIDGE] = "PF_BRIDGE", + [PF_ATMPVC] = "PF_ATMPVC", + [PF_X25] = "PF_X25", + [PF_INET6] = "PF_INET6", + [PF_ROSE] = "PF_ROSE", + [PF_DECnet] = "PF_DECnet", + [PF_NETBEUI] = "PF_NETBEUI", + [PF_SECURITY] = "PF_SECURITY", + [PF_KEY] = "PF_KEY", + [PF_NETLINK] = "PF_NETLINK/PF_ROUTE", + [PF_PACKET] = "PF_PACKET", + [PF_ASH] = "PF_ASH", + [PF_ECONET] = "PF_ECONET", + [PF_ATMSVC] = "PF_ATMSVC", + [PF_RDS] = "PF_RDS", + [PF_SNA] = "PF_SNA", + [PF_IRDA] = "PF_IRDA", + [PF_PPPOX] = "PF_PPPOX", + [PF_WANPIPE] = "PF_WANPIPE", + [PF_LLC] = "PF_LLC", + [PF_IB] = "PF_IB", + [PF_MPLS] = "PF_MPLS", + [PF_CAN] = "PF_CAN", + [PF_TIPC] = "PF_TIPC", + [PF_BLUETOOTH] = "PF_BLUETOOTH", + [PF_IUCV] = "PF_IUCV", + [PF_RXRPC] = "PF_RXRPC", + [PF_ISDN] = "PF_ISDN", + [PF_PHONET] = "PF_PHONET", + [PF_IEEE802154] = "PF_IEEE802154", + [PF_CAIF] = "PF_CAIF", + [PF_ALG] = "PF_ALG", + [PF_NFC] = "PF_NFC", + [PF_VSOCK] = "PF_VSOCK", + [PF_KCM] = "PF_KCM", + [PF_QIPCRTR] = "PF_QIPCRTR", + [PF_SMC] = "PF_SMC", + [PF_XDP] = "PF_XDP", + [PF_MCTP] = "PF_MCTP", +}; + /* * The protocol list. Each protocol is registered in here. */ @@ -250,7 +301,7 @@ static struct inode *sock_alloc_inode(struct super_block *sb) { struct socket_alloc *ei; - ei = kmem_cache_alloc(sock_inode_cachep, GFP_KERNEL); + ei = alloc_inode_sb(sb, sock_inode_cachep, GFP_KERNEL); if (!ei) return NULL; init_waitqueue_head(&ei->socket.wq.wait); @@ -304,7 +355,7 @@ static const struct super_operations sockfs_ops = { */ static char *sockfs_dname(struct dentry *dentry, char *buffer, int buflen) { - return dynamic_dname(dentry, buffer, buflen, "socket:[%lu]", + return dynamic_dname(buffer, buflen, "socket:[%lu]", d_inode(dentry)->i_ino); } @@ -334,6 +385,7 @@ static const struct xattr_handler sockfs_xattr_handler = { }; static int sockfs_security_xattr_set(const struct xattr_handler *handler, + struct user_namespace *mnt_userns, struct dentry *dentry, struct inode *inode, const char *suffix, const void *value, size_t size, int flags) @@ -445,17 +497,15 @@ static int sock_map_fd(struct socket *sock, int flags) /** * sock_from_file - Return the &socket bounded to @file. * @file: file - * @err: pointer to an error code return * - * On failure returns %NULL and assigns -ENOTSOCK to @err. + * On failure returns %NULL. */ -struct socket *sock_from_file(struct file *file, int *err) +struct socket *sock_from_file(struct file *file) { if (file->f_op == &socket_file_ops) - return file->private_data; /* set in sock_map_fd */ + return file->private_data; /* set in sock_alloc_file */ - *err = -ENOTSOCK; return NULL; } EXPORT_SYMBOL(sock_from_file); @@ -484,9 +534,11 @@ struct socket *sockfd_lookup(int fd, int *err) return NULL; } - sock = sock_from_file(file, err); - if (!sock) + sock = sock_from_file(file); + if (!sock) { + *err = -ENOTSOCK; fput(file); + } return sock; } EXPORT_SYMBOL(sockfd_lookup); @@ -498,11 +550,12 @@ static struct socket *sockfd_lookup_light(int fd, int *err, int *fput_needed) *err = -EBADF; if (f.file) { - sock = sock_from_file(f.file, err); + sock = sock_from_file(f.file); if (likely(sock)) { - *fput_needed = f.flags; + *fput_needed = f.flags & FDPUT_FPUT; return sock; } + *err = -ENOTSOCK; fdput(f); } return NULL; @@ -536,9 +589,10 @@ static ssize_t sockfs_listxattr(struct dentry *dentry, char *buffer, return used; } -static int sockfs_setattr(struct dentry *dentry, struct iattr *iattr) +static int sockfs_setattr(struct user_namespace *mnt_userns, + struct dentry *dentry, struct iattr *iattr) { - int err = simple_setattr(dentry, iattr); + int err = simple_setattr(&init_user_ns, dentry, iattr); if (!err && (iattr->ia_valid & ATTR_UID)) { struct socket *sock = SOCKET_I(d_inode(dentry)); @@ -586,15 +640,6 @@ struct socket *sock_alloc(void) } EXPORT_SYMBOL(sock_alloc); -/** - * sock_release - close a socket - * @sock: socket to close - * - * The socket is released from the protocol stack if it has a release - * callback, and the inode is then released if the socket is bound to - * an inode not a file. - */ - static void __sock_release(struct socket *sock, struct inode *inode) { if (sock->ops) { @@ -620,6 +665,14 @@ static void __sock_release(struct socket *sock, struct inode *inode) sock->file = NULL; } +/** + * sock_release - close a socket + * @sock: socket to close + * + * The socket is released from the protocol stack if it has a release + * callback, and the inode is then released if the socket is bound to + * an inode not a file. + */ void sock_release(struct socket *sock) { __sock_release(sock, NULL); @@ -630,9 +683,18 @@ void __sock_tx_timestamp(__u16 tsflags, __u8 *tx_flags) { u8 flags = *tx_flags; - if (tsflags & SOF_TIMESTAMPING_TX_HARDWARE) + if (tsflags & SOF_TIMESTAMPING_TX_HARDWARE) { flags |= SKBTX_HW_TSTAMP; + /* PTP hardware clocks can provide a free running cycle counter + * as a time base for virtual clocks. Tell driver to use the + * free running cycle counter for timestamp if socket is bound + * to virtual clock. + */ + if (tsflags & SOF_TIMESTAMPING_BIND_PHC) + flags |= SKBTX_HW_TSTAMP_USE_CYCLES; + } + if (tsflags & SOF_TIMESTAMPING_TX_SOFTWARE) flags |= SKBTX_SW_TSTAMP; @@ -743,7 +805,28 @@ static bool skb_is_swtx_tstamp(const struct sk_buff *skb, int false_tstamp) return skb->tstamp && !false_tstamp && skb_is_err_queue(skb); } -static void put_ts_pktinfo(struct msghdr *msg, struct sk_buff *skb) +static ktime_t get_timestamp(struct sock *sk, struct sk_buff *skb, int *if_index) +{ + bool cycles = sk->sk_tsflags & SOF_TIMESTAMPING_BIND_PHC; + struct skb_shared_hwtstamps *shhwtstamps = skb_hwtstamps(skb); + struct net_device *orig_dev; + ktime_t hwtstamp; + + rcu_read_lock(); + orig_dev = dev_get_by_napi_id(skb_napi_id(skb)); + if (orig_dev) { + *if_index = orig_dev->ifindex; + hwtstamp = netdev_get_tstamp(orig_dev, shhwtstamps, cycles); + } else { + hwtstamp = shhwtstamps->hwtstamp; + } + rcu_read_unlock(); + + return hwtstamp; +} + +static void put_ts_pktinfo(struct msghdr *msg, struct sk_buff *skb, + int if_index) { struct scm_ts_pktinfo ts_pktinfo; struct net_device *orig_dev; @@ -753,11 +836,14 @@ static void put_ts_pktinfo(struct msghdr *msg, struct sk_buff *skb) memset(&ts_pktinfo, 0, sizeof(ts_pktinfo)); - rcu_read_lock(); - orig_dev = dev_get_by_napi_id(skb_napi_id(skb)); - if (orig_dev) - ts_pktinfo.if_index = orig_dev->ifindex; - rcu_read_unlock(); + if (!if_index) { + rcu_read_lock(); + orig_dev = dev_get_by_napi_id(skb_napi_id(skb)); + if (orig_dev) + if_index = orig_dev->ifindex; + rcu_read_unlock(); + } + ts_pktinfo.if_index = if_index; ts_pktinfo.pkt_length = skb->len - skb_mac_offset(skb); put_cmsg(msg, SOL_SOCKET, SCM_TIMESTAMPING_PKTINFO, @@ -777,6 +863,8 @@ void __sock_recv_timestamp(struct msghdr *msg, struct sock *sk, int empty = 1, false_tstamp = 0; struct skb_shared_hwtstamps *shhwtstamps = skb_hwtstamps(skb); + int if_index; + ktime_t hwtstamp; /* Race occurred between timestamp enabling and packet receiving. Fill in the current time for now. */ @@ -823,12 +911,24 @@ void __sock_recv_timestamp(struct msghdr *msg, struct sock *sk, empty = 0; if (shhwtstamps && (sk->sk_tsflags & SOF_TIMESTAMPING_RAW_HARDWARE) && - !skb_is_swtx_tstamp(skb, false_tstamp) && - ktime_to_timespec64_cond(shhwtstamps->hwtstamp, tss.ts + 2)) { - empty = 0; - if ((sk->sk_tsflags & SOF_TIMESTAMPING_OPT_PKTINFO) && - !skb_is_err_queue(skb)) - put_ts_pktinfo(msg, skb); + !skb_is_swtx_tstamp(skb, false_tstamp)) { + if_index = 0; + if (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP_NETDEV) + hwtstamp = get_timestamp(sk, skb, &if_index); + else + hwtstamp = shhwtstamps->hwtstamp; + + if (sk->sk_tsflags & SOF_TIMESTAMPING_BIND_PHC) + hwtstamp = ptp_convert_timestamp(&hwtstamp, + sk->sk_bind_phc); + + if (ktime_to_timespec64_cond(hwtstamp, tss.ts + 2)) { + empty = 0; + + if ((sk->sk_tsflags & SOF_TIMESTAMPING_OPT_PKTINFO) && + !skb_is_err_queue(skb)) + put_ts_pktinfo(msg, skb, if_index); + } } if (!empty) { if (sock_flag(sk, SOCK_TSTAMP_NEW)) @@ -868,13 +968,22 @@ static inline void sock_recv_drops(struct msghdr *msg, struct sock *sk, sizeof(__u32), &SOCK_SKB_CB(skb)->dropcount); } -void __sock_recv_ts_and_drops(struct msghdr *msg, struct sock *sk, - struct sk_buff *skb) +static void sock_recv_mark(struct msghdr *msg, struct sock *sk, + struct sk_buff *skb) +{ + if (sock_flag(sk, SOCK_RCVMARK) && skb) + put_cmsg(msg, SOL_SOCKET, SO_MARK, sizeof(__u32), + &skb->mark); +} + +void __sock_recv_cmsgs(struct msghdr *msg, struct sock *sk, + struct sk_buff *skb) { sock_recv_timestamp(msg, sk, skb); sock_recv_drops(msg, sk, skb); + sock_recv_mark(msg, sk, skb); } -EXPORT_SYMBOL_GPL(__sock_recv_ts_and_drops); +EXPORT_SYMBOL_GPL(__sock_recv_cmsgs); INDIRECT_CALLABLE_DECLARE(int inet_recvmsg(struct socket *, struct msghdr *, size_t, int)); @@ -924,14 +1033,9 @@ EXPORT_SYMBOL(sock_recvmsg); int kernel_recvmsg(struct socket *sock, struct msghdr *msg, struct kvec *vec, size_t num, size_t size, int flags) { - mm_segment_t oldfs = get_fs(); - int result; - + msg->msg_control_is_user = false; iov_iter_kvec(&msg->msg_iter, READ, vec, num, size); - set_fs(KERNEL_DS); - result = sock_recvmsg(sock, msg, flags); - set_fs(oldfs); - return result; + return sock_recvmsg(sock, msg, flags); } EXPORT_SYMBOL(kernel_recvmsg); @@ -1012,9 +1116,13 @@ static ssize_t sock_write_iter(struct kiocb *iocb, struct iov_iter *from) */ static DEFINE_MUTEX(br_ioctl_mutex); -static int (*br_ioctl_hook) (struct net *, unsigned int cmd, void __user *arg); +static int (*br_ioctl_hook)(struct net *net, struct net_bridge *br, + unsigned int cmd, struct ifreq *ifr, + void __user *uarg); -void brioctl_set(int (*hook) (struct net *, unsigned int, void __user *)) +void brioctl_set(int (*hook)(struct net *net, struct net_bridge *br, + unsigned int cmd, struct ifreq *ifr, + void __user *uarg)) { mutex_lock(&br_ioctl_mutex); br_ioctl_hook = hook; @@ -1022,6 +1130,22 @@ void brioctl_set(int (*hook) (struct net *, unsigned int, void __user *)) } EXPORT_SYMBOL(brioctl_set); +int br_ioctl_call(struct net *net, struct net_bridge *br, unsigned int cmd, + struct ifreq *ifr, void __user *uarg) +{ + int err = -ENOPKG; + + if (!br_ioctl_hook) + request_module("bridge"); + + mutex_lock(&br_ioctl_mutex); + if (br_ioctl_hook) + err = br_ioctl_hook(net, br, cmd, ifr, uarg); + mutex_unlock(&br_ioctl_mutex); + + return err; +} + static DEFINE_MUTEX(vlan_ioctl_mutex); static int (*vlan_ioctl_hook) (struct net *, void __user *arg); @@ -1033,22 +1157,14 @@ void vlan_ioctl_set(int (*hook) (struct net *, void __user *)) } EXPORT_SYMBOL(vlan_ioctl_set); -static DEFINE_MUTEX(dlci_ioctl_mutex); -static int (*dlci_ioctl_hook) (unsigned int, void __user *); - -void dlci_ioctl_set(int (*hook) (unsigned int, void __user *)) -{ - mutex_lock(&dlci_ioctl_mutex); - dlci_ioctl_hook = hook; - mutex_unlock(&dlci_ioctl_mutex); -} -EXPORT_SYMBOL(dlci_ioctl_set); - static long sock_do_ioctl(struct net *net, struct socket *sock, unsigned int cmd, unsigned long arg) { + struct ifreq ifr; + bool need_copyout; int err; void __user *argp = (void __user *)arg; + void __user *data; err = sock->ops->ioctl(sock, cmd, arg); @@ -1059,25 +1175,16 @@ static long sock_do_ioctl(struct net *net, struct socket *sock, if (err != -ENOIOCTLCMD) return err; - if (cmd == SIOCGIFCONF) { - struct ifconf ifc; - if (copy_from_user(&ifc, argp, sizeof(struct ifconf))) - return -EFAULT; - rtnl_lock(); - err = dev_ifconf(net, &ifc, sizeof(struct ifreq)); - rtnl_unlock(); - if (!err && copy_to_user(argp, &ifc, sizeof(struct ifconf))) - err = -EFAULT; - } else { - struct ifreq ifr; - bool need_copyout; - if (copy_from_user(&ifr, argp, sizeof(struct ifreq))) + if (!is_socket_ioctl_cmd(cmd)) + return -ENOTTY; + + if (get_user_ifreq(&ifr, &data, argp)) + return -EFAULT; + err = dev_ioctl(net, cmd, &ifr, data, &need_copyout); + if (!err && need_copyout) + if (put_user_ifreq(&ifr, argp)) return -EFAULT; - err = dev_ioctl(net, cmd, &ifr, &need_copyout); - if (!err && need_copyout) - if (copy_to_user(argp, &ifr, sizeof(struct ifreq))) - return -EFAULT; - } + return err; } @@ -1086,19 +1193,6 @@ static long sock_do_ioctl(struct net *net, struct socket *sock, * what to do with it - that's up to the protocol still. */ -/** - * get_net_ns - increment the refcount of the network namespace - * @ns: common namespace (net) - * - * Returns the net's common namespace. - */ - -struct ns_common *get_net_ns(struct ns_common *ns) -{ - return &get_net(container_of(ns, struct net, ns))->ns; -} -EXPORT_SYMBOL_GPL(get_net_ns); - static long sock_ioctl(struct file *file, unsigned cmd, unsigned long arg) { struct socket *sock; @@ -1112,12 +1206,13 @@ static long sock_ioctl(struct file *file, unsigned cmd, unsigned long arg) net = sock_net(sk); if (unlikely(cmd >= SIOCDEVPRIVATE && cmd <= (SIOCDEVPRIVATE + 15))) { struct ifreq ifr; + void __user *data; bool need_copyout; - if (copy_from_user(&ifr, argp, sizeof(struct ifreq))) + if (get_user_ifreq(&ifr, &data, argp)) return -EFAULT; - err = dev_ioctl(net, cmd, &ifr, &need_copyout); + err = dev_ioctl(net, cmd, &ifr, data, &need_copyout); if (!err && need_copyout) - if (copy_to_user(argp, &ifr, sizeof(struct ifreq))) + if (put_user_ifreq(&ifr, argp)) return -EFAULT; } else #ifdef CONFIG_WEXT_CORE @@ -1142,14 +1237,7 @@ static long sock_ioctl(struct file *file, unsigned cmd, unsigned long arg) case SIOCSIFBR: case SIOCBRADDBR: case SIOCBRDELBR: - err = -ENOPKG; - if (!br_ioctl_hook) - request_module("bridge"); - - mutex_lock(&br_ioctl_mutex); - if (br_ioctl_hook) - err = br_ioctl_hook(net, cmd, argp); - mutex_unlock(&br_ioctl_mutex); + err = br_ioctl_call(net, NULL, cmd, NULL, argp); break; case SIOCGIFVLAN: case SIOCSIFVLAN: @@ -1162,17 +1250,6 @@ static long sock_ioctl(struct file *file, unsigned cmd, unsigned long arg) err = vlan_ioctl_hook(net, argp); mutex_unlock(&vlan_ioctl_mutex); break; - case SIOCADDDLCI: - case SIOCDELDLCI: - err = -ENOPKG; - if (!dlci_ioctl_hook) - request_module("dlci"); - - mutex_lock(&dlci_ioctl_mutex); - if (dlci_ioctl_hook) - err = dlci_ioctl_hook(cmd, argp); - mutex_unlock(&dlci_ioctl_mutex); - break; case SIOCGSKNS: err = -EPERM; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) @@ -1200,6 +1277,11 @@ static long sock_ioctl(struct file *file, unsigned cmd, unsigned long arg) cmd == SIOCGSTAMP_NEW, false); break; + + case SIOCGIFCONF: + err = dev_ifconf(net, argp); + break; + default: err = sock_do_ioctl(net, sock, cmd, arg); break; @@ -1331,7 +1413,7 @@ int sock_wake_async(struct socket_wq *wq, int how, int band) case SOCK_WAKE_SPACE: if (!test_and_clear_bit(SOCKWQ_ASYNC_NOSPACE, &wq->flags)) break; - /* fall through */ + fallthrough; case SOCK_WAKE_IO: call_kill: kill_fasync(&wq->fasync_list, SIGIO, band); @@ -1503,11 +1585,10 @@ int sock_create_kern(struct net *net, int family, int type, int protocol, struct } EXPORT_SYMBOL(sock_create_kern); -int __sys_socket(int family, int type, int protocol) +static struct socket *__sys_socket_create(int family, int type, int protocol) { - int retval; struct socket *sock; - int flags; + int retval; /* Check the SOCK_* constants for consistency. */ BUILD_BUG_ON(SOCK_CLOEXEC != O_CLOEXEC); @@ -1515,17 +1596,50 @@ int __sys_socket(int family, int type, int protocol) 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; + if ((type & ~SOCK_TYPE_MASK) & ~(SOCK_CLOEXEC | SOCK_NONBLOCK)) + return ERR_PTR(-EINVAL); type &= SOCK_TYPE_MASK; + retval = sock_create(family, type, protocol, &sock); + if (retval < 0) + return ERR_PTR(retval); + + return sock; +} + +struct file *__sys_socket_file(int family, int type, int protocol) +{ + struct socket *sock; + struct file *file; + int flags; + + sock = __sys_socket_create(family, type, protocol); + if (IS_ERR(sock)) + return ERR_CAST(sock); + + flags = 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) - return retval; + file = sock_alloc_file(sock, flags, NULL); + if (IS_ERR(file)) + sock_release(sock); + + return file; +} + +int __sys_socket(int family, int type, int protocol) +{ + struct socket *sock; + int flags; + + sock = __sys_socket_create(family, type, protocol); + if (IS_ERR(sock)) + return PTR_ERR(sock); + + flags = type & ~SOCK_TYPE_MASK; + if (SOCK_NONBLOCK != O_NONBLOCK && (flags & SOCK_NONBLOCK)) + flags = (flags & ~SOCK_NONBLOCK) | O_NONBLOCK; return sock_map_fd(sock, flags & (O_CLOEXEC | O_NONBLOCK)); } @@ -1687,7 +1801,7 @@ int __sys_listen(int fd, int backlog) sock = sockfd_lookup_light(fd, &err, &fput_needed); if (sock) { - somaxconn = sock_net(sock->sk)->core.sysctl_somaxconn; + somaxconn = READ_ONCE(sock_net(sock->sk)->core.sysctl_somaxconn); if ((unsigned int)backlog > somaxconn) backlog = somaxconn; @@ -1705,30 +1819,22 @@ SYSCALL_DEFINE2(listen, int, fd, int, backlog) return __sys_listen(fd, backlog); } -int __sys_accept4_file(struct file *file, unsigned file_flags, +struct file *do_accept(struct file *file, unsigned file_flags, struct sockaddr __user *upeer_sockaddr, - int __user *upeer_addrlen, int flags, - unsigned long nofile) + int __user *upeer_addrlen, int flags) { struct socket *sock, *newsock; struct file *newfile; - int err, len, newfd; + int err, len; 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 = sock_from_file(file, &err); + sock = sock_from_file(file); if (!sock) - goto out; + return ERR_PTR(-ENOTSOCK); - err = -ENFILE; newsock = sock_alloc(); if (!newsock) - goto out; + return ERR_PTR(-ENFILE); newsock->type = sock->type; newsock->ops = sock->ops; @@ -1739,18 +1845,9 @@ int __sys_accept4_file(struct file *file, unsigned file_flags, */ __module_get(newsock->ops->owner); - newfd = __get_unused_fd_flags(flags, nofile); - if (unlikely(newfd < 0)) { - err = newfd; - sock_release(newsock); - goto out; - } newfile = sock_alloc_file(newsock, flags, sock->sk->sk_prot_creator->name); - if (IS_ERR(newfile)) { - err = PTR_ERR(newfile); - put_unused_fd(newfd); - goto out; - } + if (IS_ERR(newfile)) + return newfile; err = security_socket_accept(sock, newsock); if (err) @@ -1775,16 +1872,36 @@ int __sys_accept4_file(struct file *file, unsigned file_flags, } /* File flags are not inherited via accept() unlike another OSes. */ - - fd_install(newfd, newfile); - err = newfd; -out: - return err; + return newfile; out_fd: fput(newfile); - put_unused_fd(newfd); - goto out; + return ERR_PTR(err); +} +static int __sys_accept4_file(struct file *file, struct sockaddr __user *upeer_sockaddr, + int __user *upeer_addrlen, int flags) +{ + struct file *newfile; + int newfd; + + if (flags & ~(SOCK_CLOEXEC | SOCK_NONBLOCK)) + return -EINVAL; + + if (SOCK_NONBLOCK != O_NONBLOCK && (flags & SOCK_NONBLOCK)) + flags = (flags & ~SOCK_NONBLOCK) | O_NONBLOCK; + + newfd = get_unused_fd_flags(flags); + if (unlikely(newfd < 0)) + return newfd; + + newfile = do_accept(file, 0, upeer_sockaddr, upeer_addrlen, + flags); + if (IS_ERR(newfile)) { + put_unused_fd(newfd); + return PTR_ERR(newfile); + } + fd_install(newfd, newfile); + return newfd; } /* @@ -1807,11 +1924,9 @@ int __sys_accept4(int fd, struct sockaddr __user *upeer_sockaddr, f = fdget(fd); if (f.file) { - ret = __sys_accept4_file(f.file, 0, upeer_sockaddr, - upeer_addrlen, flags, - rlimit(RLIMIT_NOFILE)); - if (f.flags) - fput(f.file); + ret = __sys_accept4_file(f.file, upeer_sockaddr, + upeer_addrlen, flags); + fdput(f); } return ret; @@ -1847,9 +1962,11 @@ int __sys_connect_file(struct file *file, struct sockaddr_storage *address, struct socket *sock; int err; - sock = sock_from_file(file, &err); - if (!sock) + sock = sock_from_file(file); + if (!sock) { + err = -ENOTSOCK; goto out; + } err = security_socket_connect(sock, (struct sockaddr *)address, addrlen); @@ -1874,8 +1991,7 @@ int __sys_connect(int fd, struct sockaddr __user *uservaddr, int addrlen) ret = move_addr_to_kernel(uservaddr, addrlen, &address); if (!ret) ret = __sys_connect_file(f.file, &address, addrlen, 0); - if (f.flags) - fput(f.file); + fdput(f); } return ret; @@ -1910,7 +2026,7 @@ int __sys_getsockname(int fd, struct sockaddr __user *usockaddr, err = sock->ops->getname(sock, (struct sockaddr *)&address, 0); if (err < 0) goto out_put; - /* "err" is actually length in this case */ + /* "err" is actually length in this case */ err = move_addr_to_user(&address, err, usockaddr, usockaddr_len); out_put: @@ -1987,6 +2103,7 @@ int __sys_sendto(int fd, void __user *buff, size_t len, unsigned int flags, msg.msg_control = NULL; msg.msg_controllen = 0; msg.msg_namelen = 0; + msg.msg_ubuf = NULL; if (addr) { err = move_addr_to_kernel(addr, addr_len, &address); if (err < 0) @@ -2030,10 +2147,13 @@ SYSCALL_DEFINE4(send, int, fd, void __user *, buff, size_t, len, int __sys_recvfrom(int fd, void __user *ubuf, size_t size, unsigned int flags, struct sockaddr __user *addr, int __user *addr_len) { + struct sockaddr_storage address; + struct msghdr msg = { + /* Save some cycles and don't copy the address if not needed */ + .msg_name = addr ? (struct sockaddr *)&address : NULL, + }; struct socket *sock; struct iovec iov; - struct msghdr msg; - struct sockaddr_storage address; int err, err2; int fput_needed; @@ -2044,14 +2164,6 @@ int __sys_recvfrom(int fd, void __user *ubuf, size_t size, unsigned int flags, if (!sock) goto out; - msg.msg_control = NULL; - msg.msg_controllen = 0; - /* Save some cycles and don't copy the address if not needed */ - msg.msg_name = addr ? (struct sockaddr *)&address : NULL; - /* We assume all kernel code knows the size of sockaddr_storage */ - msg.msg_namelen = 0; - msg.msg_iocb = NULL; - msg.msg_flags = 0; if (sock->file->f_flags & O_NONBLOCK) flags |= MSG_DONTWAIT; err = sock_recvmsg(sock, &msg, flags); @@ -2085,15 +2197,25 @@ SYSCALL_DEFINE4(recv, int, fd, void __user *, ubuf, size_t, size, return __sys_recvfrom(fd, ubuf, size, flags, NULL, NULL); } +static bool sock_use_custom_sol_socket(const struct socket *sock) +{ + const struct sock *sk = sock->sk; + + /* Use sock->ops->setsockopt() for MPTCP */ + return IS_ENABLED(CONFIG_MPTCP) && + sk->sk_protocol == IPPROTO_MPTCP && + sk->sk_type == SOCK_STREAM && + (sk->sk_family == AF_INET || sk->sk_family == AF_INET6); +} + /* * Set a socket option. Because we don't know the option lengths we have * to pass the user mode parameter for the protocols to sort out. */ - -static int __sys_setsockopt(int fd, int level, int optname, - char __user *optval, int optlen) +int __sys_setsockopt(int fd, int level, int optname, char __user *user_optval, + int optlen) { - mm_segment_t oldfs = get_fs(); + sockptr_t optval = USER_SOCKPTR(user_optval); char *kernel_optval = NULL; int err, fput_needed; struct socket *sock; @@ -2102,43 +2224,36 @@ static int __sys_setsockopt(int fd, int level, int optname, return -EINVAL; sock = sockfd_lookup_light(fd, &err, &fput_needed); - if (sock != NULL) { - err = security_socket_setsockopt(sock, level, optname); - if (err) - goto out_put; - - err = BPF_CGROUP_RUN_PROG_SETSOCKOPT(sock->sk, &level, - &optname, optval, &optlen, - &kernel_optval); + if (!sock) + return err; - if (err < 0) { - goto out_put; - } else if (err > 0) { - err = 0; - goto out_put; - } + err = security_socket_setsockopt(sock, level, optname); + if (err) + goto out_put; - if (kernel_optval) { - set_fs(KERNEL_DS); - optval = (char __user __force *)kernel_optval; - } + if (!in_compat_syscall()) + err = BPF_CGROUP_RUN_PROG_SETSOCKOPT(sock->sk, &level, &optname, + user_optval, &optlen, + &kernel_optval); + if (err < 0) + goto out_put; + if (err > 0) { + err = 0; + goto out_put; + } - if (level == SOL_SOCKET) - err = - sock_setsockopt(sock, level, optname, optval, + if (kernel_optval) + optval = KERNEL_SOCKPTR(kernel_optval); + if (level == SOL_SOCKET && !sock_use_custom_sol_socket(sock)) + err = sock_setsockopt(sock, level, optname, optval, optlen); + else if (unlikely(!sock->ops->setsockopt)) + err = -EOPNOTSUPP; + else + err = sock->ops->setsockopt(sock, level, optname, optval, optlen); - else - err = - sock->ops->setsockopt(sock, level, optname, optval, - optlen); - - if (kernel_optval) { - set_fs(oldfs); - kfree(kernel_optval); - } + kfree(kernel_optval); out_put: - fput_light(sock->file, fput_needed); - } + fput_light(sock->file, fput_needed); return err; } @@ -2148,41 +2263,45 @@ SYSCALL_DEFINE5(setsockopt, int, fd, int, level, int, optname, return __sys_setsockopt(fd, level, optname, optval, optlen); } +INDIRECT_CALLABLE_DECLARE(bool tcp_bpf_bypass_getsockopt(int level, + int optname)); + /* * Get a socket option. Because we don't know the option lengths we have * to pass a user mode parameter for the protocols to sort out. */ - -static int __sys_getsockopt(int fd, int level, int optname, - char __user *optval, int __user *optlen) +int __sys_getsockopt(int fd, int level, int optname, char __user *optval, + int __user *optlen) { int err, fput_needed; struct socket *sock; int max_optlen; sock = sockfd_lookup_light(fd, &err, &fput_needed); - if (sock != NULL) { - err = security_socket_getsockopt(sock, level, optname); - if (err) - goto out_put; + if (!sock) + return err; + + err = security_socket_getsockopt(sock, level, optname); + if (err) + goto out_put; + if (!in_compat_syscall()) max_optlen = BPF_CGROUP_GETSOCKOPT_MAX_OPTLEN(optlen); - if (level == SOL_SOCKET) - err = - sock_getsockopt(sock, level, optname, optval, + if (level == SOL_SOCKET) + err = sock_getsockopt(sock, level, optname, optval, optlen); + else if (unlikely(!sock->ops->getsockopt)) + err = -EOPNOTSUPP; + else + err = sock->ops->getsockopt(sock, level, optname, optval, optlen); - else - err = - sock->ops->getsockopt(sock, level, optname, optval, - optlen); + if (!in_compat_syscall()) err = BPF_CGROUP_RUN_PROG_GETSOCKOPT(sock->sk, level, optname, - optval, optlen, - max_optlen, err); + optval, optlen, max_optlen, + err); out_put: - fput_light(sock->file, fput_needed); - } + fput_light(sock->file, fput_needed); return err; } @@ -2196,6 +2315,17 @@ SYSCALL_DEFINE5(getsockopt, int, fd, int, level, int, optname, * Shutdown a socket. */ +int __sys_shutdown_sock(struct socket *sock, int how) +{ + int err; + + err = security_socket_shutdown(sock, how); + if (!err) + err = sock->ops->shutdown(sock, how); + + return err; +} + int __sys_shutdown(int fd, int how) { int err, fput_needed; @@ -2203,9 +2333,7 @@ int __sys_shutdown(int fd, int how) sock = sockfd_lookup_light(fd, &err, &fput_needed); if (sock != NULL) { - err = security_socket_shutdown(sock, how); - if (!err) - err = sock->ops->shutdown(sock, how); + err = __sys_shutdown_sock(sock, how); fput_light(sock->file, fput_needed); } return err; @@ -2228,23 +2356,20 @@ struct used_address { unsigned int name_len; }; -static int copy_msghdr_from_user(struct msghdr *kmsg, - struct user_msghdr __user *umsg, - struct sockaddr __user **save_addr, - struct iovec **iov) +int __copy_msghdr(struct msghdr *kmsg, + struct user_msghdr *msg, + struct sockaddr __user **save_addr) { - struct user_msghdr msg; ssize_t err; - if (copy_from_user(&msg, umsg, sizeof(*umsg))) - return -EFAULT; + kmsg->msg_control_is_user = true; + kmsg->msg_get_inq = 0; + kmsg->msg_control_user = msg->msg_control; + kmsg->msg_controllen = msg->msg_controllen; + kmsg->msg_flags = msg->msg_flags; - kmsg->msg_control = (void __force *)msg.msg_control; - kmsg->msg_controllen = msg.msg_controllen; - kmsg->msg_flags = msg.msg_flags; - - kmsg->msg_namelen = msg.msg_namelen; - if (!msg.msg_name) + kmsg->msg_namelen = msg->msg_namelen; + if (!msg->msg_name) kmsg->msg_namelen = 0; if (kmsg->msg_namelen < 0) @@ -2254,11 +2379,11 @@ static int copy_msghdr_from_user(struct msghdr *kmsg, kmsg->msg_namelen = sizeof(struct sockaddr_storage); if (save_addr) - *save_addr = msg.msg_name; + *save_addr = msg->msg_name; - if (msg.msg_name && kmsg->msg_namelen) { + if (msg->msg_name && kmsg->msg_namelen) { if (!save_addr) { - err = move_addr_to_kernel(msg.msg_name, + err = move_addr_to_kernel(msg->msg_name, kmsg->msg_namelen, kmsg->msg_name); if (err < 0) @@ -2269,10 +2394,28 @@ static int copy_msghdr_from_user(struct msghdr *kmsg, kmsg->msg_namelen = 0; } - if (msg.msg_iovlen > UIO_MAXIOV) + if (msg->msg_iovlen > UIO_MAXIOV) return -EMSGSIZE; kmsg->msg_iocb = NULL; + kmsg->msg_ubuf = NULL; + return 0; +} + +static int copy_msghdr_from_user(struct msghdr *kmsg, + struct user_msghdr __user *umsg, + struct sockaddr __user **save_addr, + struct iovec **iov) +{ + struct user_msghdr msg; + ssize_t err; + + if (copy_from_user(&msg, umsg, sizeof(*umsg))) + return -EFAULT; + + err = __copy_msghdr(kmsg, &msg, save_addr); + if (err) + return err; err = import_iovec(save_addr ? READ : WRITE, msg.msg_iov, msg.msg_iovlen, @@ -2314,16 +2457,10 @@ static int ____sys_sendmsg(struct socket *sock, struct msghdr *msg_sys, goto out; } err = -EFAULT; - /* - * Careful! Before this, msg_sys->msg_control contains a user pointer. - * Afterwards, it will be a kernel pointer. Thus the compiler-assisted - * checking falls down on this. - */ - if (copy_from_user(ctl_buf, - (void __user __force *)msg_sys->msg_control, - ctl_len)) + if (copy_from_user(ctl_buf, msg_sys->msg_control_user, ctl_len)) goto out_freectl; msg_sys->msg_control = ctl_buf; + msg_sys->msg_control_is_user = false; } msg_sys->msg_flags = flags; @@ -2408,10 +2545,6 @@ static int ___sys_sendmsg(struct socket *sock, struct user_msghdr __user *msg, long __sys_sendmsg_sock(struct socket *sock, struct msghdr *msg, unsigned int flags) { - /* disallow ancillary data requests from this path */ - if (msg->msg_control || msg->msg_controllen) - return -EINVAL; - return ____sys_sendmsg(sock, msg, flags, NULL, 0); } @@ -2620,10 +2753,6 @@ long __sys_recvmsg_sock(struct socket *sock, struct msghdr *msg, struct user_msghdr __user *umsg, struct sockaddr __user *uaddr, unsigned int flags) { - /* disallow ancillary data requests from this path */ - if (msg->msg_control || msg->msg_controllen) - return -EINVAL; - return ____sys_recvmsg(sock, msg, umsg, uaddr, flags, 0); } @@ -2991,7 +3120,7 @@ int sock_register(const struct net_proto_family *ops) } spin_unlock(&net_family_lock); - pr_info("NET: Registered protocol family %d\n", ops->family); + pr_info("NET: Registered %s protocol family\n", pf_family_names[ops->family]); return err; } EXPORT_SYMBOL(sock_register); @@ -3019,7 +3148,7 @@ void sock_unregister(int family) synchronize_rcu(); - pr_info("NET: Unregistered protocol family %d\n", family); + pr_info("NET: Unregistered %s protocol family\n", pf_family_names[family]); } EXPORT_SYMBOL(sock_unregister); @@ -3051,7 +3180,7 @@ static int __init sock_init(void) err = register_filesystem(&sock_fs_type); if (err) - goto out_fs; + goto out; sock_mnt = kern_mount(&sock_fs_type); if (IS_ERR(sock_mnt)) { err = PTR_ERR(sock_mnt); @@ -3074,7 +3203,6 @@ out: out_mount: unregister_filesystem(&sock_fs_type); -out_fs: goto out; } @@ -3088,154 +3216,55 @@ void socket_seq_show(struct seq_file *seq) } #endif /* CONFIG_PROC_FS */ -#ifdef CONFIG_COMPAT -static int compat_dev_ifconf(struct net *net, struct compat_ifconf __user *uifc32) +/* Handle the fact that while struct ifreq has the same *layout* on + * 32/64 for everything but ifreq::ifru_ifmap and ifreq::ifru_data, + * which are handled elsewhere, it still has different *size* due to + * ifreq::ifru_ifmap (which is 16 bytes on 32 bit, 24 bytes on 64-bit, + * resulting in struct ifreq being 32 and 40 bytes respectively). + * As a result, if the struct happens to be at the end of a page and + * the next page isn't readable/writable, we get a fault. To prevent + * that, copy back and forth to the full size. + */ +int get_user_ifreq(struct ifreq *ifr, void __user **ifrdata, void __user *arg) { - struct compat_ifconf ifc32; - struct ifconf ifc; - int err; + if (in_compat_syscall()) { + struct compat_ifreq *ifr32 = (struct compat_ifreq *)ifr; - if (copy_from_user(&ifc32, uifc32, sizeof(struct compat_ifconf))) - return -EFAULT; + memset(ifr, 0, sizeof(*ifr)); + if (copy_from_user(ifr32, arg, sizeof(*ifr32))) + return -EFAULT; - ifc.ifc_len = ifc32.ifc_len; - ifc.ifc_req = compat_ptr(ifc32.ifcbuf); + if (ifrdata) + *ifrdata = compat_ptr(ifr32->ifr_data); - rtnl_lock(); - err = dev_ifconf(net, &ifc, sizeof(struct compat_ifreq)); - rtnl_unlock(); - if (err) - return err; + return 0; + } - ifc32.ifc_len = ifc.ifc_len; - if (copy_to_user(uifc32, &ifc32, sizeof(struct compat_ifconf))) + if (copy_from_user(ifr, arg, sizeof(*ifr))) return -EFAULT; + if (ifrdata) + *ifrdata = ifr->ifr_data; + return 0; } +EXPORT_SYMBOL(get_user_ifreq); -static int ethtool_ioctl(struct net *net, struct compat_ifreq __user *ifr32) +int put_user_ifreq(struct ifreq *ifr, void __user *arg) { - struct compat_ethtool_rxnfc __user *compat_rxnfc; - bool convert_in = false, convert_out = false; - size_t buf_size = 0; - struct ethtool_rxnfc __user *rxnfc = NULL; - struct ifreq ifr; - u32 rule_cnt = 0, actual_rule_cnt; - u32 ethcmd; - u32 data; - int ret; - - if (get_user(data, &ifr32->ifr_ifru.ifru_data)) - return -EFAULT; + size_t size = sizeof(*ifr); - compat_rxnfc = compat_ptr(data); + if (in_compat_syscall()) + size = sizeof(struct compat_ifreq); - if (get_user(ethcmd, &compat_rxnfc->cmd)) + if (copy_to_user(arg, ifr, size)) return -EFAULT; - /* Most ethtool structures are defined without padding. - * Unfortunately struct ethtool_rxnfc is an exception. - */ - switch (ethcmd) { - default: - break; - case ETHTOOL_GRXCLSRLALL: - /* Buffer size is variable */ - if (get_user(rule_cnt, &compat_rxnfc->rule_cnt)) - return -EFAULT; - if (rule_cnt > KMALLOC_MAX_SIZE / sizeof(u32)) - return -ENOMEM; - buf_size += rule_cnt * sizeof(u32); - /* fall through */ - case ETHTOOL_GRXRINGS: - case ETHTOOL_GRXCLSRLCNT: - case ETHTOOL_GRXCLSRULE: - case ETHTOOL_SRXCLSRLINS: - convert_out = true; - /* fall through */ - case ETHTOOL_SRXCLSRLDEL: - buf_size += sizeof(struct ethtool_rxnfc); - convert_in = true; - rxnfc = compat_alloc_user_space(buf_size); - break; - } - - if (copy_from_user(&ifr.ifr_name, &ifr32->ifr_name, IFNAMSIZ)) - return -EFAULT; - - ifr.ifr_data = convert_in ? rxnfc : (void __user *)compat_rxnfc; - - if (convert_in) { - /* We expect there to be holes between fs.m_ext and - * fs.ring_cookie and at the end of fs, but nowhere else. - */ - BUILD_BUG_ON(offsetof(struct compat_ethtool_rxnfc, fs.m_ext) + - sizeof(compat_rxnfc->fs.m_ext) != - offsetof(struct ethtool_rxnfc, fs.m_ext) + - sizeof(rxnfc->fs.m_ext)); - BUILD_BUG_ON( - offsetof(struct compat_ethtool_rxnfc, fs.location) - - offsetof(struct compat_ethtool_rxnfc, fs.ring_cookie) != - offsetof(struct ethtool_rxnfc, fs.location) - - offsetof(struct ethtool_rxnfc, fs.ring_cookie)); - - if (copy_in_user(rxnfc, compat_rxnfc, - (void __user *)(&rxnfc->fs.m_ext + 1) - - (void __user *)rxnfc) || - copy_in_user(&rxnfc->fs.ring_cookie, - &compat_rxnfc->fs.ring_cookie, - (void __user *)(&rxnfc->fs.location + 1) - - (void __user *)&rxnfc->fs.ring_cookie)) - return -EFAULT; - if (ethcmd == ETHTOOL_GRXCLSRLALL) { - if (put_user(rule_cnt, &rxnfc->rule_cnt)) - return -EFAULT; - } else if (copy_in_user(&rxnfc->rule_cnt, - &compat_rxnfc->rule_cnt, - sizeof(rxnfc->rule_cnt))) - return -EFAULT; - } - - ret = dev_ioctl(net, SIOCETHTOOL, &ifr, NULL); - if (ret) - return ret; - - if (convert_out) { - if (copy_in_user(compat_rxnfc, rxnfc, - (const void __user *)(&rxnfc->fs.m_ext + 1) - - (const void __user *)rxnfc) || - copy_in_user(&compat_rxnfc->fs.ring_cookie, - &rxnfc->fs.ring_cookie, - (const void __user *)(&rxnfc->fs.location + 1) - - (const void __user *)&rxnfc->fs.ring_cookie) || - copy_in_user(&compat_rxnfc->rule_cnt, &rxnfc->rule_cnt, - sizeof(rxnfc->rule_cnt))) - return -EFAULT; - - if (ethcmd == ETHTOOL_GRXCLSRLALL) { - /* As an optimisation, we only copy the actual - * number of rules that the underlying - * function returned. Since Mallory might - * change the rule count in user memory, we - * check that it is less than the rule count - * originally given (as the user buffer size), - * which has been range-checked. - */ - if (get_user(actual_rule_cnt, &rxnfc->rule_cnt)) - return -EFAULT; - if (actual_rule_cnt < rule_cnt) - rule_cnt = actual_rule_cnt; - if (copy_in_user(&compat_rxnfc->rule_locs[0], - &rxnfc->rule_locs[0], - rule_cnt * sizeof(u32))) - return -EFAULT; - } - } - return 0; } +EXPORT_SYMBOL(put_user_ifreq); +#ifdef CONFIG_COMPAT static int compat_siocwandev(struct net *net, struct compat_ifreq __user *uifr32) { compat_uptr_t uptr32; @@ -3243,7 +3272,7 @@ static int compat_siocwandev(struct net *net, struct compat_ifreq __user *uifr32 void __user *saved; int err; - if (copy_from_user(&ifr, uifr32, sizeof(struct compat_ifreq))) + if (get_user_ifreq(&ifr, NULL, uifr32)) return -EFAULT; if (get_user(uptr32, &uifr32->ifr_settings.ifs_ifsu)) @@ -3252,10 +3281,10 @@ static int compat_siocwandev(struct net *net, struct compat_ifreq __user *uifr32 saved = ifr.ifr_settings.ifs_ifsu.raw_hdlc; ifr.ifr_settings.ifs_ifsu.raw_hdlc = compat_ptr(uptr32); - err = dev_ioctl(net, SIOCWANDEV, &ifr, NULL); + err = dev_ioctl(net, SIOCWANDEV, &ifr, NULL, NULL); if (!err) { ifr.ifr_settings.ifs_ifsu.raw_hdlc = saved; - if (copy_to_user(uifr32, &ifr, sizeof(struct compat_ifreq))) + if (put_user_ifreq(&ifr, uifr32)) err = -EFAULT; } return err; @@ -3266,200 +3295,15 @@ static int compat_ifr_data_ioctl(struct net *net, unsigned int cmd, struct compat_ifreq __user *u_ifreq32) { struct ifreq ifreq; - u32 data32; - - if (copy_from_user(ifreq.ifr_name, u_ifreq32->ifr_name, IFNAMSIZ)) - return -EFAULT; - if (get_user(data32, &u_ifreq32->ifr_data)) - return -EFAULT; - ifreq.ifr_data = compat_ptr(data32); - - return dev_ioctl(net, cmd, &ifreq, NULL); -} - -static int compat_ifreq_ioctl(struct net *net, struct socket *sock, - unsigned int cmd, - struct compat_ifreq __user *uifr32) -{ - struct ifreq __user *uifr; - int err; - - /* Handle the fact that while struct ifreq has the same *layout* on - * 32/64 for everything but ifreq::ifru_ifmap and ifreq::ifru_data, - * which are handled elsewhere, it still has different *size* due to - * ifreq::ifru_ifmap (which is 16 bytes on 32 bit, 24 bytes on 64-bit, - * resulting in struct ifreq being 32 and 40 bytes respectively). - * As a result, if the struct happens to be at the end of a page and - * the next page isn't readable/writable, we get a fault. To prevent - * that, copy back and forth to the full size. - */ - - 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: - case SIOCGIFNAME: - 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; - int err; + void __user *data; - 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) + if (!is_socket_ioctl_cmd(cmd)) + return -ENOTTY; + if (get_user_ifreq(&ifreq, &data, u_ifreq32)) return -EFAULT; + ifreq.ifr_data = data; - err = dev_ioctl(net, cmd, &ifr, NULL); - - 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; -} - -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 = (char __user __force *)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 compatible 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; + return dev_ioctl(net, cmd, &ifreq, data, NULL); } static int compat_sock_ioctl_trans(struct file *file, struct socket *sock, @@ -3470,24 +3314,11 @@ static int compat_sock_ioctl_trans(struct file *file, struct socket *sock, struct net *net = sock_net(sk); if (cmd >= SIOCDEVPRIVATE && cmd <= (SIOCDEVPRIVATE + 15)) - return compat_ifr_data_ioctl(net, cmd, argp); + return sock_ioctl(file, cmd, (unsigned long)argp); switch (cmd) { - case SIOCSIFBR: - case SIOCGIFBR: - return old_bridge_ioctl(argp); - case SIOCGIFCONF: - return compat_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 SIOCADDRT: - case SIOCDELRT: - return routing_ioctl(net, sock, cmd, argp); case SIOCGSTAMP_OLD: case SIOCGSTAMPNS_OLD: if (!sock->ops->gettstamp) @@ -3495,6 +3326,7 @@ static int compat_sock_ioctl_trans(struct file *file, struct socket *sock, return sock->ops->gettstamp(sock, argp, cmd == SIOCGSTAMP_OLD, !COMPAT_USE_64BIT_TIME); + case SIOCETHTOOL: case SIOCBONDSLAVEINFOQUERY: case SIOCBONDINFOQUERY: case SIOCSHWTSTAMP: @@ -3509,15 +3341,18 @@ static int compat_sock_ioctl_trans(struct file *file, struct socket *sock, case SIOCBRDELBR: case SIOCGIFVLAN: case SIOCSIFVLAN: - case SIOCADDDLCI: - case SIOCDELDLCI: case SIOCGSKNS: case SIOCGSTAMP_NEW: case SIOCGSTAMPNS_NEW: + case SIOCGIFCONF: + case SIOCSIFBR: + case SIOCGIFBR: return sock_ioctl(file, cmd, arg); case SIOCGIFFLAGS: case SIOCSIFFLAGS: + case SIOCGIFMAP: + case SIOCSIFMAP: case SIOCGIFMETRIC: case SIOCSIFMETRIC: case SIOCGIFMTU: @@ -3554,8 +3389,6 @@ static int compat_sock_ioctl_trans(struct file *file, struct socket *sock, case SIOCBONDRELEASE: case SIOCBONDSETHWADDR: case SIOCBONDCHANGEACTIVE: - return compat_ifreq_ioctl(net, sock, cmd, argp); - case SIOCSARP: case SIOCGARP: case SIOCDARP: @@ -3665,7 +3498,7 @@ EXPORT_SYMBOL(kernel_accept); * @addrlen: address length * @flags: flags (O_NONBLOCK, ...) * - * For datagram sockets, @addr is the addres to which datagrams are sent + * For datagram sockets, @addr is the address to which datagrams are sent * by default, and the only address from which datagrams are received. * For stream sockets, attempts to connect to @addr. * Returns 0 or an error code. @@ -3684,7 +3517,7 @@ EXPORT_SYMBOL(kernel_connect); * @addr: address holder * * Fills the @addr pointer with the address which the socket is bound. - * Returns 0 or an error code. + * Returns the length of the address in bytes or an error code. */ int kernel_getsockname(struct socket *sock, struct sockaddr *addr) @@ -3694,12 +3527,12 @@ int kernel_getsockname(struct socket *sock, struct sockaddr *addr) EXPORT_SYMBOL(kernel_getsockname); /** - * kernel_peername - get the address which the socket is connected (kernel space) + * kernel_getpeername - get the address which the socket is connected (kernel space) * @sock: socket * @addr: address holder * * Fills the @addr pointer with the address which the socket is connected. - * Returns 0 or an error code. + * Returns the length of the address in bytes or an error code. */ int kernel_getpeername(struct socket *sock, struct sockaddr *addr) @@ -3709,71 +3542,6 @@ int kernel_getpeername(struct socket *sock, struct sockaddr *addr) EXPORT_SYMBOL(kernel_getpeername); /** - * kernel_getsockopt - get a socket option (kernel space) - * @sock: socket - * @level: API level (SOL_SOCKET, ...) - * @optname: option tag - * @optval: option value - * @optlen: option length - * - * Assigns the option length to @optlen. - * Returns 0 or an error. - */ - -int kernel_getsockopt(struct socket *sock, int level, int optname, - char *optval, int *optlen) -{ - mm_segment_t oldfs = get_fs(); - char __user *uoptval; - int __user *uoptlen; - int err; - - uoptval = (char __user __force *) optval; - uoptlen = (int __user __force *) optlen; - - set_fs(KERNEL_DS); - if (level == SOL_SOCKET) - err = sock_getsockopt(sock, level, optname, uoptval, uoptlen); - else - err = sock->ops->getsockopt(sock, level, optname, uoptval, - uoptlen); - set_fs(oldfs); - return err; -} -EXPORT_SYMBOL(kernel_getsockopt); - -/** - * kernel_setsockopt - set a socket option (kernel space) - * @sock: socket - * @level: API level (SOL_SOCKET, ...) - * @optname: option tag - * @optval: option value - * @optlen: option length - * - * Returns 0 or an error. - */ - -int kernel_setsockopt(struct socket *sock, int level, int optname, - char *optval, unsigned int optlen) -{ - mm_segment_t oldfs = get_fs(); - char __user *uoptval; - int err; - - uoptval = (char __user __force *) optval; - - set_fs(KERNEL_DS); - if (level == SOL_SOCKET) - err = sock_setsockopt(sock, level, optname, uoptval, optlen); - else - err = sock->ops->setsockopt(sock, level, optname, uoptval, - optlen); - set_fs(oldfs); - return err; -} -EXPORT_SYMBOL(kernel_setsockopt); - -/** * kernel_sendpage - send a &page through a socket (kernel space) * @sock: socket * @page: page @@ -3787,9 +3555,11 @@ EXPORT_SYMBOL(kernel_setsockopt); int kernel_sendpage(struct socket *sock, struct page *page, int offset, size_t size, int flags) { - if (sock->ops->sendpage) + if (sock->ops->sendpage) { + /* Warn in case the improper page to zero-copy send */ + WARN_ONCE(!sendpage_ok(page), "improper page for zero-copy send"); return sock->ops->sendpage(sock, page, offset, size, flags); - + } return sock_no_sendpage(sock, page, offset, size, flags); } EXPORT_SYMBOL(kernel_sendpage); @@ -3820,7 +3590,7 @@ int kernel_sendpage_locked(struct sock *sk, struct page *page, int offset, EXPORT_SYMBOL(kernel_sendpage_locked); /** - * kernel_shutdown - shut down part of a full-duplex connection (kernel space) + * kernel_sock_shutdown - shut down part of a full-duplex connection (kernel space) * @sock: socket * @how: connection part * |