diff options
Diffstat (limited to 'net/socket.c')
| -rw-r--r-- | net/socket.c | 2948 |
1 files changed, 1618 insertions, 1330 deletions
diff --git a/net/socket.c b/net/socket.c index ad22df1ffbd1..136b98c54fb3 100644 --- a/net/socket.c +++ b/net/socket.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * NET An implementation of the SOCKET network access protocol. * @@ -45,22 +46,18 @@ * Tigran Aivazian : Made listen(2) backlog sanity checks * protocol-independent * - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - * - * * This module is effectively the top level interface to the BSD socket * paradigm. * * 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> +#include <linux/splice.h> #include <linux/net.h> #include <linux/interrupt.h> #include <linux/thread_info.h> @@ -70,7 +67,6 @@ #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> @@ -79,6 +75,7 @@ #include <linux/module.h> #include <linux/highmem.h> #include <linux/mount.h> +#include <linux/pseudo_fs.h> #include <linux/security.h> #include <linux/syscalls.h> #include <linux/compat.h> @@ -89,6 +86,9 @@ #include <linux/magic.h> #include <linux/slab.h> #include <linux/xattr.h> +#include <linux/nospec.h> +#include <linux/indirect_call_wrapper.h> +#include <linux/io_uring/net.h> #include <linux/uaccess.h> #include <asm/unistd.h> @@ -103,10 +103,14 @@ #include <linux/if_tun.h> #include <linux/ipv6_route.h> #include <linux/route.h> +#include <linux/termios.h> #include <linux/sockios.h> -#include <linux/atalk.h> #include <net/busy_poll.h> #include <linux/errqueue.h> +#include <linux/ptp_clock_kernel.h> +#include <trace/events/sock.h> + +#include "core/dev.h" #ifdef CONFIG_NET_RX_BUSY_POLL unsigned int sysctl_net_busy_read __read_mostly; @@ -118,7 +122,7 @@ static ssize_t sock_write_iter(struct kiocb *iocb, struct iov_iter *from); static int sock_mmap(struct file *file, struct vm_area_struct *vma); static int sock_close(struct inode *inode, struct file *file); -static unsigned int sock_poll(struct file *file, +static __poll_t sock_poll(struct file *file, struct poll_table_struct *wait); static long sock_ioctl(struct file *file, unsigned int cmd, unsigned long arg); #ifdef CONFIG_COMPAT @@ -126,11 +130,23 @@ static long compat_sock_ioctl(struct file *file, unsigned int cmd, unsigned long arg); #endif static int sock_fasync(int fd, struct file *filp, int on); -static ssize_t sock_sendpage(struct file *file, struct page *page, - int offset, size_t size, loff_t *ppos, int more); static ssize_t sock_splice_read(struct file *file, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags); +static void sock_splice_eof(struct file *file); + +#ifdef CONFIG_PROC_FS +static void sock_show_fdinfo(struct seq_file *m, struct file *f) +{ + struct socket *sock = f->private_data; + const struct proto_ops *ops = READ_ONCE(sock->ops); + + if (ops->show_fdinfo) + ops->show_fdinfo(m, sock); +} +#else +#define sock_show_fdinfo NULL +#endif /* * Socket files have a set of 'special' operations as well as the generic file ones. These don't appear @@ -139,7 +155,6 @@ static ssize_t sock_splice_read(struct file *file, loff_t *ppos, static const struct file_operations socket_file_ops = { .owner = THIS_MODULE, - .llseek = no_llseek, .read_iter = sock_read_iter, .write_iter = sock_write_iter, .poll = sock_poll, @@ -147,12 +162,63 @@ static const struct file_operations socket_file_ops = { #ifdef CONFIG_COMPAT .compat_ioctl = compat_sock_ioctl, #endif + .uring_cmd = io_uring_cmd_sock, .mmap = sock_mmap, .release = sock_close, .fasync = sock_fasync, - .sendpage = sock_sendpage, - .splice_write = generic_splice_sendpage, + .splice_write = splice_to_socket, .splice_read = sock_splice_read, + .splice_eof = sock_splice_eof, + .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", }; /* @@ -163,12 +229,6 @@ static DEFINE_SPINLOCK(net_family_lock); static const struct net_proto_family __rcu *net_families[NPROTO] __read_mostly; /* - * Statistics counters of the socket lists - */ - -static DEFINE_PER_CPU(int, sockets_in_use); - -/* * Support routines. * Move socket addresses back and forth across the kernel/user * divide and look after the messy bits. @@ -216,49 +276,55 @@ int move_addr_to_kernel(void __user *uaddr, int ulen, struct sockaddr_storage *k static int move_addr_to_user(struct sockaddr_storage *kaddr, int klen, void __user *uaddr, int __user *ulen) { - int err; int len; BUG_ON(klen > sizeof(struct sockaddr_storage)); - err = get_user(len, ulen); - if (err) - return err; + + if (can_do_masked_user_access()) + ulen = masked_user_access_begin(ulen); + else if (!user_access_begin(ulen, 4)) + return -EFAULT; + + unsafe_get_user(len, ulen, efault_end); + if (len > klen) len = klen; - if (len < 0) - return -EINVAL; + /* + * "fromlen shall refer to the value before truncation.." + * 1003.1g + */ + if (len >= 0) + unsafe_put_user(klen, ulen, efault_end); + + user_access_end(); + if (len) { + if (len < 0) + return -EINVAL; if (audit_sockaddr(klen, kaddr)) return -ENOMEM; if (copy_to_user(uaddr, kaddr, len)) return -EFAULT; } - /* - * "fromlen shall refer to the value before truncation.." - * 1003.1g - */ - return __put_user(klen, ulen); + return 0; + +efault_end: + user_access_end(); + return -EFAULT; } -static struct kmem_cache *sock_inode_cachep __read_mostly; +static struct kmem_cache *sock_inode_cachep __ro_after_init; static struct inode *sock_alloc_inode(struct super_block *sb) { struct socket_alloc *ei; - struct socket_wq *wq; - ei = kmem_cache_alloc(sock_inode_cachep, GFP_KERNEL); + ei = alloc_inode_sb(sb, sock_inode_cachep, GFP_KERNEL); if (!ei) return NULL; - wq = kmalloc(sizeof(*wq), GFP_KERNEL); - if (!wq) { - kmem_cache_free(sock_inode_cachep, ei); - return NULL; - } - init_waitqueue_head(&wq->wait); - wq->fasync_list = NULL; - wq->flags = 0; - RCU_INIT_POINTER(ei->socket.wq, wq); + init_waitqueue_head(&ei->socket.wq.wait); + ei->socket.wq.fasync_list = NULL; + ei->socket.wq.flags = 0; ei->socket.state = SS_UNCONNECTED; ei->socket.flags = 0; @@ -269,14 +335,11 @@ static struct inode *sock_alloc_inode(struct super_block *sb) return &ei->vfs_inode; } -static void sock_destroy_inode(struct inode *inode) +static void sock_free_inode(struct inode *inode) { struct socket_alloc *ei; - struct socket_wq *wq; ei = container_of(inode, struct socket_alloc, vfs_inode); - wq = rcu_dereference_protected(ei->socket.wq, 1); - kfree_rcu(wq, rcu); kmem_cache_free(sock_inode_cachep, ei); } @@ -294,14 +357,14 @@ static void init_inodecache(void) 0, (SLAB_HWCACHE_ALIGN | SLAB_RECLAIM_ACCOUNT | - SLAB_MEM_SPREAD | SLAB_ACCOUNT), + SLAB_ACCOUNT), init_once); BUG_ON(sock_inode_cachep == NULL); } static const struct super_operations sockfs_ops = { .alloc_inode = sock_alloc_inode, - .destroy_inode = sock_destroy_inode, + .free_inode = sock_free_inode, .statfs = simple_statfs, }; @@ -310,7 +373,7 @@ 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); } @@ -340,6 +403,7 @@ static const struct xattr_handler sockfs_xattr_handler = { }; static int sockfs_security_xattr_set(const struct xattr_handler *handler, + struct mnt_idmap *idmap, struct dentry *dentry, struct inode *inode, const char *suffix, const void *value, size_t size, int flags) @@ -353,25 +417,28 @@ static const struct xattr_handler sockfs_security_xattr_handler = { .set = sockfs_security_xattr_set, }; -static const struct xattr_handler *sockfs_xattr_handlers[] = { +static const struct xattr_handler * const sockfs_xattr_handlers[] = { &sockfs_xattr_handler, &sockfs_security_xattr_handler, NULL }; -static struct dentry *sockfs_mount(struct file_system_type *fs_type, - int flags, const char *dev_name, void *data) +static int sockfs_init_fs_context(struct fs_context *fc) { - return mount_pseudo_xattr(fs_type, "socket:", &sockfs_ops, - sockfs_xattr_handlers, - &sockfs_dentry_operations, SOCKFS_MAGIC); + struct pseudo_fs_context *ctx = init_pseudo(fc, SOCKFS_MAGIC); + if (!ctx) + return -ENOMEM; + ctx->ops = &sockfs_ops; + ctx->dops = &sockfs_dentry_operations; + ctx->xattr = sockfs_xattr_handlers; + return 0; } static struct vfsmount *sock_mnt __read_mostly; static struct file_system_type sock_fs_type = { .name = "sockfs", - .mount = sockfs_mount, + .init_fs_context = sockfs_init_fs_context, .kill_sb = kill_anon_super, }; @@ -392,38 +459,44 @@ static struct file_system_type sock_fs_type = { * but we take care of internal coherence yet. */ +/** + * sock_alloc_file - Bind a &socket to a &file + * @sock: socket + * @flags: file status flags + * @dname: protocol name + * + * Returns the &file bound with @sock, implicitly storing it + * in sock->file. If dname is %NULL, sets to "". + * + * On failure @sock is released, and an ERR pointer is returned. + * + * This function uses GFP_KERNEL internally. + */ + struct file *sock_alloc_file(struct socket *sock, int flags, const char *dname) { - struct qstr name = { .name = "" }; - struct path path; struct file *file; - if (dname) { - name.name = dname; - name.len = strlen(name.name); - } else if (sock->sk) { - name.name = sock->sk->sk_prot_creator->name; - name.len = strlen(name.name); - } - path.dentry = d_alloc_pseudo(sock_mnt->mnt_sb, &name); - if (unlikely(!path.dentry)) - return ERR_PTR(-ENOMEM); - path.mnt = mntget(sock_mnt); - - d_instantiate(path.dentry, SOCK_INODE(sock)); + if (!dname) + dname = sock->sk ? sock->sk->sk_prot_creator->name : ""; - file = alloc_file(&path, FMODE_READ | FMODE_WRITE, - &socket_file_ops); + file = alloc_file_pseudo(SOCK_INODE(sock), sock_mnt, dname, + O_RDWR | (flags & O_NONBLOCK), + &socket_file_ops); if (IS_ERR(file)) { - /* drop dentry, keep inode */ - ihold(d_inode(path.dentry)); - path_put(&path); + sock_release(sock); return file; } + file->f_mode |= FMODE_NOWAIT; sock->file = file; - file->f_flags = O_RDWR | (flags & O_NONBLOCK); file->private_data = sock; + stream_open(SOCK_INODE(sock), file); + /* + * Disable permission and pre-content events, but enable legacy + * inotify events for legacy users. + */ + file_set_fsnotify_mode(file, FMODE_NONOTIFY_PERM); return file; } EXPORT_SYMBOL(sock_alloc_file); @@ -432,11 +505,13 @@ static int sock_map_fd(struct socket *sock, int flags) { struct file *newfile; int fd = get_unused_fd_flags(flags); - if (unlikely(fd < 0)) + if (unlikely(fd < 0)) { + sock_release(sock); return fd; + } newfile = sock_alloc_file(sock, flags, NULL); - if (likely(!IS_ERR(newfile))) { + if (!IS_ERR(newfile)) { fd_install(fd, newfile); return fd; } @@ -445,12 +520,18 @@ static int sock_map_fd(struct socket *sock, int flags) return PTR_ERR(newfile); } -struct socket *sock_from_file(struct file *file, int *err) +/** + * sock_from_file - Return the &socket bounded to @file. + * @file: file + * + * On failure returns %NULL. + */ + +struct socket *sock_from_file(struct file *file) { - if (file->f_op == &socket_file_ops) - return file->private_data; /* set in sock_map_fd */ + if (likely(file->f_op == &socket_file_ops)) + return file->private_data; /* set in sock_alloc_file */ - *err = -ENOTSOCK; return NULL; } EXPORT_SYMBOL(sock_from_file); @@ -479,30 +560,15 @@ 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); -static struct socket *sockfd_lookup_light(int fd, int *err, int *fput_needed) -{ - struct fd f = fdget(fd); - struct socket *sock; - - *err = -EBADF; - if (f.file) { - sock = sock_from_file(f.file, err); - if (likely(sock)) { - *fput_needed = f.flags; - return sock; - } - fdput(f); - } - return NULL; -} - static ssize_t sockfs_listxattr(struct dentry *dentry, char *buffer, size_t size) { @@ -531,14 +597,20 @@ 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 mnt_idmap *idmap, + struct dentry *dentry, struct iattr *iattr) { - int err = simple_setattr(dentry, iattr); + int err = simple_setattr(&nop_mnt_idmap, dentry, iattr); if (!err && (iattr->ia_valid & ATTR_UID)) { struct socket *sock = SOCKET_I(d_inode(dentry)); - sock->sk->sk_uid = iattr->ia_uid; + if (sock->sk) { + /* Paired with READ_ONCE() in sk_uid() */ + WRITE_ONCE(sock->sk->sk_uid, iattr->ia_uid); + } else { + err = -ENOENT; + } } return err; @@ -550,11 +622,11 @@ static const struct inode_operations sockfs_inode_ops = { }; /** - * sock_alloc - allocate a socket + * sock_alloc - allocate a socket * * Allocate a new inode and socket object. The two are bound together * and initialised. The socket is then returned. If we are out of inodes - * NULL is returned. + * NULL is returned. This functions uses GFP_KERNEL internally. */ struct socket *sock_alloc(void) @@ -568,55 +640,63 @@ struct socket *sock_alloc(void) sock = SOCKET_I(inode); - kmemcheck_annotate_bitfield(sock, type); inode->i_ino = get_next_ino(); inode->i_mode = S_IFSOCK | S_IRWXUGO; inode->i_uid = current_fsuid(); inode->i_gid = current_fsgid(); inode->i_op = &sockfs_inode_ops; - this_cpu_add(sockets_in_use, 1); return sock; } 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. - */ - -void sock_release(struct socket *sock) +static void __sock_release(struct socket *sock, struct inode *inode) { - if (sock->ops) { - struct module *owner = sock->ops->owner; + const struct proto_ops *ops = READ_ONCE(sock->ops); + + if (ops) { + struct module *owner = ops->owner; - sock->ops->release(sock); + if (inode) + inode_lock(inode); + ops->release(sock); + sock->sk = NULL; + if (inode) + inode_unlock(inode); sock->ops = NULL; module_put(owner); } - if (rcu_dereference_protected(sock->wq, 1)->fasync_list) + if (sock->wq.fasync_list) pr_err("%s: fasync list not empty!\n", __func__); - this_cpu_sub(sockets_in_use, 1); if (!sock->file) { iput(SOCK_INODE(sock)); return; } 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); +} EXPORT_SYMBOL(sock_release); -void __sock_tx_timestamp(__u16 tsflags, __u8 *tx_flags) +void __sock_tx_timestamp(__u32 tsflags, __u8 *tx_flags) { u8 flags = *tx_flags; if (tsflags & SOF_TIMESTAMPING_TX_HARDWARE) - flags |= SKBTX_HW_TSTAMP; + flags |= SKBTX_HW_TSTAMP_NOBPF; if (tsflags & SOF_TIMESTAMPING_TX_SOFTWARE) flags |= SKBTX_SW_TSTAMP; @@ -624,30 +704,88 @@ void __sock_tx_timestamp(__u16 tsflags, __u8 *tx_flags) if (tsflags & SOF_TIMESTAMPING_TX_SCHED) flags |= SKBTX_SCHED_TSTAMP; + if (tsflags & SOF_TIMESTAMPING_TX_COMPLETION) + flags |= SKBTX_COMPLETION_TSTAMP; + *tx_flags = flags; } EXPORT_SYMBOL(__sock_tx_timestamp); +INDIRECT_CALLABLE_DECLARE(int inet_sendmsg(struct socket *, struct msghdr *, + size_t)); +INDIRECT_CALLABLE_DECLARE(int inet6_sendmsg(struct socket *, struct msghdr *, + size_t)); + +static noinline void call_trace_sock_send_length(struct sock *sk, int ret, + int flags) +{ + trace_sock_send_length(sk, ret, 0); +} + static inline int sock_sendmsg_nosec(struct socket *sock, struct msghdr *msg) { - int ret = sock->ops->sendmsg(sock, msg, msg_data_left(msg)); + int ret = INDIRECT_CALL_INET(READ_ONCE(sock->ops)->sendmsg, inet6_sendmsg, + inet_sendmsg, sock, msg, + msg_data_left(msg)); BUG_ON(ret == -EIOCBQUEUED); + + if (trace_sock_send_length_enabled()) + call_trace_sock_send_length(sock->sk, ret, 0); return ret; } -int sock_sendmsg(struct socket *sock, struct msghdr *msg) +static int __sock_sendmsg(struct socket *sock, struct msghdr *msg) { int err = security_socket_sendmsg(sock, msg, msg_data_left(msg)); return err ?: sock_sendmsg_nosec(sock, msg); } + +/** + * sock_sendmsg - send a message through @sock + * @sock: socket + * @msg: message to send + * + * Sends @msg through @sock, passing through LSM. + * Returns the number of bytes sent, or an error code. + */ +int sock_sendmsg(struct socket *sock, struct msghdr *msg) +{ + struct sockaddr_storage *save_addr = (struct sockaddr_storage *)msg->msg_name; + struct sockaddr_storage address; + int save_len = msg->msg_namelen; + int ret; + + if (msg->msg_name) { + memcpy(&address, msg->msg_name, msg->msg_namelen); + msg->msg_name = &address; + } + + ret = __sock_sendmsg(sock, msg); + msg->msg_name = save_addr; + msg->msg_namelen = save_len; + + return ret; +} EXPORT_SYMBOL(sock_sendmsg); +/** + * kernel_sendmsg - send a message through @sock (kernel-space) + * @sock: socket + * @msg: message header + * @vec: kernel vec + * @num: vec array length + * @size: total message data size + * + * Builds the message data with @vec and sends it through @sock. + * Returns the number of bytes sent, or an error code. + */ + int kernel_sendmsg(struct socket *sock, struct msghdr *msg, struct kvec *vec, size_t num, size_t size) { - iov_iter_kvec(&msg->msg_iter, WRITE | ITER_KVEC, vec, num, size); + iov_iter_kvec(&msg->msg_iter, ITER_SOURCE, vec, num, size); return sock_sendmsg(sock, msg); } EXPORT_SYMBOL(kernel_sendmsg); @@ -667,7 +805,7 @@ static bool skb_is_err_queue(const struct sk_buff *skb) * before the software timestamp is received, a hardware TX timestamp may be * returned only if there is no software TX timestamp. Ignore false software * timestamps, which may be made in the __sock_recv_timestamp() call when the - * option SO_TIMESTAMP(NS) is enabled on the socket, even when the skb has a + * option SO_TIMESTAMP_OLD(NS) is enabled on the socket, even when the skb has a * hardware timestamp. */ static bool skb_is_swtx_tstamp(const struct sk_buff *skb, int false_tstamp) @@ -675,7 +813,28 @@ 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 = READ_ONCE(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; @@ -685,17 +844,66 @@ 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, sizeof(ts_pktinfo), &ts_pktinfo); } +bool skb_has_tx_timestamp(struct sk_buff *skb, const struct sock *sk) +{ + const struct sock_exterr_skb *serr = SKB_EXT_ERR(skb); + u32 tsflags = READ_ONCE(sk->sk_tsflags); + + if (serr->ee.ee_errno != ENOMSG || + serr->ee.ee_origin != SO_EE_ORIGIN_TIMESTAMPING) + return false; + + /* software time stamp available and wanted */ + if ((tsflags & SOF_TIMESTAMPING_SOFTWARE) && skb->tstamp) + return true; + /* hardware time stamps available and wanted */ + return (tsflags & SOF_TIMESTAMPING_RAW_HARDWARE) && + skb_hwtstamps(skb)->hwtstamp; +} + +int skb_get_tx_timestamp(struct sk_buff *skb, struct sock *sk, + struct timespec64 *ts) +{ + u32 tsflags = READ_ONCE(sk->sk_tsflags); + ktime_t hwtstamp; + int if_index = 0; + + if ((tsflags & SOF_TIMESTAMPING_SOFTWARE) && + ktime_to_timespec64_cond(skb->tstamp, ts)) + return SOF_TIMESTAMPING_TX_SOFTWARE; + + if (!(tsflags & SOF_TIMESTAMPING_RAW_HARDWARE) || + skb_is_swtx_tstamp(skb, false)) + return -ENOENT; + + if (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP_NETDEV) + hwtstamp = get_timestamp(sk, skb, &if_index); + else + hwtstamp = skb_hwtstamps(skb)->hwtstamp; + + if (tsflags & SOF_TIMESTAMPING_BIND_PHC) + hwtstamp = ptp_convert_timestamp(&hwtstamp, + READ_ONCE(sk->sk_bind_phc)); + if (!ktime_to_timespec64_cond(hwtstamp, ts)) + return -ENOENT; + + return SOF_TIMESTAMPING_TX_HARDWARE; +} + /* * called from sock_recv_timestamp() if sock_flag(sk, SOCK_RCVTSTAMP) */ @@ -703,10 +911,14 @@ void __sock_recv_timestamp(struct msghdr *msg, struct sock *sk, struct sk_buff *skb) { int need_software_tstamp = sock_flag(sk, SOCK_RCVTSTAMP); - struct scm_timestamping tss; + int new_tstamp = sock_flag(sk, SOCK_TSTAMP_NEW); + struct scm_timestamping_internal tss; int empty = 1, false_tstamp = 0; struct skb_shared_hwtstamps *shhwtstamps = skb_hwtstamps(skb); + int if_index; + ktime_t hwtstamp; + u32 tsflags; /* Race occurred between timestamp enabling and packet receiving. Fill in the current time for now. */ @@ -717,34 +929,73 @@ void __sock_recv_timestamp(struct msghdr *msg, struct sock *sk, 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); + if (new_tstamp) { + struct __kernel_sock_timeval tv; + + skb_get_new_timestamp(skb, &tv); + put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMP_NEW, + sizeof(tv), &tv); + } else { + struct __kernel_old_timeval tv; + + skb_get_timestamp(skb, &tv); + put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMP_OLD, + sizeof(tv), &tv); + } } else { - struct timespec ts; - skb_get_timestampns(skb, &ts); - put_cmsg(msg, SOL_SOCKET, SCM_TIMESTAMPNS, - sizeof(ts), &ts); + if (new_tstamp) { + struct __kernel_timespec ts; + + skb_get_new_timestampns(skb, &ts); + put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMPNS_NEW, + sizeof(ts), &ts); + } else { + struct __kernel_old_timespec ts; + + skb_get_timestampns(skb, &ts); + put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMPNS_OLD, + sizeof(ts), &ts); + } } } memset(&tss, 0, sizeof(tss)); - if ((sk->sk_tsflags & SOF_TIMESTAMPING_SOFTWARE) && - ktime_to_timespec_cond(skb->tstamp, tss.ts + 0)) + tsflags = READ_ONCE(sk->sk_tsflags); + if ((tsflags & SOF_TIMESTAMPING_SOFTWARE && + (tsflags & SOF_TIMESTAMPING_RX_SOFTWARE || + skb_is_err_queue(skb) || + !(tsflags & SOF_TIMESTAMPING_OPT_RX_FILTER))) && + ktime_to_timespec64_cond(skb->tstamp, tss.ts + 0)) empty = 0; if (shhwtstamps && - (sk->sk_tsflags & SOF_TIMESTAMPING_RAW_HARDWARE) && - !skb_is_swtx_tstamp(skb, false_tstamp) && - ktime_to_timespec_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); + (tsflags & SOF_TIMESTAMPING_RAW_HARDWARE && + (tsflags & SOF_TIMESTAMPING_RX_HARDWARE || + skb_is_err_queue(skb) || + !(tsflags & SOF_TIMESTAMPING_OPT_RX_FILTER))) && + !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 (tsflags & SOF_TIMESTAMPING_BIND_PHC) + hwtstamp = ptp_convert_timestamp(&hwtstamp, + READ_ONCE(sk->sk_bind_phc)); + + if (ktime_to_timespec64_cond(hwtstamp, tss.ts + 2)) { + empty = 0; + + if ((tsflags & SOF_TIMESTAMPING_OPT_PKTINFO) && + !skb_is_err_queue(skb)) + put_ts_pktinfo(msg, skb, if_index); + } } if (!empty) { - put_cmsg(msg, SOL_SOCKET, - SCM_TIMESTAMPING, sizeof(tss), &tss); + if (sock_flag(sk, SOCK_TSTAMP_NEW)) + put_cmsg_scm_timestamping64(msg, &tss); + else + put_cmsg_scm_timestamping(msg, &tss); if (skb_is_err_queue(skb) && skb->len && SKB_EXT_ERR(skb)->opt_stats) @@ -754,6 +1005,7 @@ void __sock_recv_timestamp(struct msghdr *msg, struct sock *sk, } EXPORT_SYMBOL_GPL(__sock_recv_timestamp); +#ifdef CONFIG_WIRELESS void __sock_recv_wifi_status(struct msghdr *msg, struct sock *sk, struct sk_buff *skb) { @@ -769,6 +1021,7 @@ void __sock_recv_wifi_status(struct msghdr *msg, struct sock *sk, put_cmsg(msg, SOL_SOCKET, SCM_WIFI_STATUS, sizeof(ack), &ack); } EXPORT_SYMBOL_GPL(__sock_recv_wifi_status); +#endif static inline void sock_recv_drops(struct msghdr *msg, struct sock *sk, struct sk_buff *skb) @@ -778,20 +1031,68 @@ 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) { + /* We must use a bounce buffer for CONFIG_HARDENED_USERCOPY=y */ + __u32 mark = skb->mark; + + put_cmsg(msg, SOL_SOCKET, SO_MARK, sizeof(__u32), &mark); + } +} + +static void sock_recv_priority(struct msghdr *msg, struct sock *sk, + struct sk_buff *skb) +{ + if (sock_flag(sk, SOCK_RCVPRIORITY) && skb) { + __u32 priority = skb->priority; + + put_cmsg(msg, SOL_SOCKET, SO_PRIORITY, sizeof(__u32), &priority); + } +} + +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); + sock_recv_priority(msg, sk, skb); +} +EXPORT_SYMBOL_GPL(__sock_recv_cmsgs); + +INDIRECT_CALLABLE_DECLARE(int inet_recvmsg(struct socket *, struct msghdr *, + size_t, int)); +INDIRECT_CALLABLE_DECLARE(int inet6_recvmsg(struct socket *, struct msghdr *, + size_t, int)); + +static noinline void call_trace_sock_recv_length(struct sock *sk, int ret, int flags) +{ + trace_sock_recv_length(sk, ret, flags); } -EXPORT_SYMBOL_GPL(__sock_recv_ts_and_drops); static inline int sock_recvmsg_nosec(struct socket *sock, struct msghdr *msg, int flags) { - return sock->ops->recvmsg(sock, msg, msg_data_left(msg), flags); + int ret = INDIRECT_CALL_INET(READ_ONCE(sock->ops)->recvmsg, + inet6_recvmsg, + inet_recvmsg, sock, msg, + msg_data_left(msg), flags); + if (trace_sock_recv_length_enabled()) + call_trace_sock_recv_length(sock->sk, ret, flags); + return ret; } +/** + * sock_recvmsg - receive a message from @sock + * @sock: socket + * @msg: message to receive + * @flags: message flags + * + * Receives @msg from @sock, passing through LSM. Returns the total number + * of bytes received, or an error. + */ int sock_recvmsg(struct socket *sock, struct msghdr *msg, int flags) { int err = security_socket_recvmsg(sock, msg, msg_data_left(msg), flags); @@ -801,59 +1102,52 @@ int sock_recvmsg(struct socket *sock, struct msghdr *msg, int flags) EXPORT_SYMBOL(sock_recvmsg); /** - * kernel_recvmsg - Receive a message from a socket (kernel space) - * @sock: The socket to receive the message from - * @msg: Received message - * @vec: Input s/g array for message data - * @num: Size of input s/g array - * @size: Number of bytes to read - * @flags: Message flags (MSG_DONTWAIT, etc...) + * kernel_recvmsg - Receive a message from a socket (kernel space) + * @sock: The socket to receive the message from + * @msg: Received message + * @vec: Input s/g array for message data + * @num: Size of input s/g array + * @size: Number of bytes to read + * @flags: Message flags (MSG_DONTWAIT, etc...) * - * On return the msg structure contains the scatter/gather array passed in the - * vec argument. The array is modified so that it consists of the unfilled - * portion of the original array. + * On return the msg structure contains the scatter/gather array passed in the + * vec argument. The array is modified so that it consists of the unfilled + * portion of the original array. * - * The returned value is the total number of bytes received, or an error. + * The returned value is the total number of bytes received, or an error. */ + 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; - - iov_iter_kvec(&msg->msg_iter, READ | ITER_KVEC, vec, num, size); - set_fs(KERNEL_DS); - result = sock_recvmsg(sock, msg, flags); - set_fs(oldfs); - return result; + msg->msg_control_is_user = false; + iov_iter_kvec(&msg->msg_iter, ITER_DEST, vec, num, size); + return sock_recvmsg(sock, msg, flags); } EXPORT_SYMBOL(kernel_recvmsg); -static ssize_t sock_sendpage(struct file *file, struct page *page, - int offset, size_t size, loff_t *ppos, int more) +static ssize_t sock_splice_read(struct file *file, loff_t *ppos, + struct pipe_inode_info *pipe, size_t len, + unsigned int flags) { - struct socket *sock; - int flags; - - sock = file->private_data; + struct socket *sock = file->private_data; + const struct proto_ops *ops; - flags = (file->f_flags & O_NONBLOCK) ? MSG_DONTWAIT : 0; - /* more is a combination of MSG_MORE and MSG_SENDPAGE_NOTLAST */ - flags |= more; + ops = READ_ONCE(sock->ops); + if (unlikely(!ops->splice_read)) + return copy_splice_read(file, ppos, pipe, len, flags); - return kernel_sendpage(sock, page, offset, size, flags); + return ops->splice_read(sock, ppos, pipe, len, flags); } -static ssize_t sock_splice_read(struct file *file, loff_t *ppos, - struct pipe_inode_info *pipe, size_t len, - unsigned int flags) +static void sock_splice_eof(struct file *file) { struct socket *sock = file->private_data; + const struct proto_ops *ops; - if (unlikely(!sock->ops->splice_read)) - return -EINVAL; - - return sock->ops->splice_read(sock, ppos, pipe, len, flags); + ops = READ_ONCE(sock->ops); + if (ops->splice_eof) + ops->splice_eof(sock); } static ssize_t sock_read_iter(struct kiocb *iocb, struct iov_iter *to) @@ -864,7 +1158,7 @@ static ssize_t sock_read_iter(struct kiocb *iocb, struct iov_iter *to) .msg_iocb = iocb}; ssize_t res; - if (file->f_flags & O_NONBLOCK) + if (file->f_flags & O_NONBLOCK || (iocb->ki_flags & IOCB_NOWAIT)) msg.msg_flags = MSG_DONTWAIT; if (iocb->ki_pos != 0) @@ -889,13 +1183,16 @@ static ssize_t sock_write_iter(struct kiocb *iocb, struct iov_iter *from) if (iocb->ki_pos != 0) return -ESPIPE; - if (file->f_flags & O_NONBLOCK) + if (file->f_flags & O_NONBLOCK || (iocb->ki_flags & IOCB_NOWAIT)) msg.msg_flags = MSG_DONTWAIT; if (sock->type == SOCK_SEQPACKET) msg.msg_flags |= MSG_EOR; - res = sock_sendmsg(sock, &msg); + if (iocb->ki_flags & IOCB_NOSIGNAL) + msg.msg_flags |= MSG_NOSIGNAL; + + res = __sock_sendmsg(sock, &msg); *from = msg.msg_iter; return res; } @@ -906,9 +1203,11 @@ 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, unsigned int cmd, + void __user *uarg); -void brioctl_set(int (*hook) (struct net *, unsigned int, void __user *)) +void brioctl_set(int (*hook)(struct net *net, unsigned int cmd, + void __user *uarg)) { mutex_lock(&br_ioctl_mutex); br_ioctl_hook = hook; @@ -916,6 +1215,21 @@ void brioctl_set(int (*hook) (struct net *, unsigned int, void __user *)) } EXPORT_SYMBOL(brioctl_set); +int br_ioctl_call(struct net *net, unsigned int cmd, 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, cmd, uarg); + mutex_unlock(&br_ioctl_mutex); + + return err; +} + static DEFINE_MUTEX(vlan_ioctl_mutex); static int (*vlan_ioctl_hook) (struct net *, void __user *arg); @@ -927,31 +1241,34 @@ 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) + unsigned int cmd, unsigned long arg) { + const struct proto_ops *ops = READ_ONCE(sock->ops); + struct ifreq ifr; + bool need_copyout; int err; void __user *argp = (void __user *)arg; + void __user *data; - err = sock->ops->ioctl(sock, cmd, arg); + err = 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); + if (err != -ENOIOCTLCMD) + return err; + + 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; return err; } @@ -961,13 +1278,9 @@ static long sock_do_ioctl(struct net *net, struct socket *sock, * what to do with it - that's up to the protocol still. */ -static struct ns_common *get_net_ns(struct ns_common *ns) -{ - return &get_net(container_of(ns, struct net, ns))->ns; -} - static long sock_ioctl(struct file *file, unsigned cmd, unsigned long arg) { + const struct proto_ops *ops; struct socket *sock; struct sock *sk; void __user *argp = (void __user *)arg; @@ -975,14 +1288,23 @@ static long sock_ioctl(struct file *file, unsigned cmd, unsigned long arg) struct net *net; sock = file->private_data; + ops = READ_ONCE(sock->ops); sk = sock->sk; net = sock_net(sk); - if (cmd >= SIOCDEVPRIVATE && cmd <= (SIOCDEVPRIVATE + 15)) { - err = dev_ioctl(net, cmd, argp); + if (unlikely(cmd >= SIOCDEVPRIVATE && cmd <= (SIOCDEVPRIVATE + 15))) { + struct ifreq ifr; + void __user *data; + bool need_copyout; + 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; } else #ifdef CONFIG_WEXT_CORE if (cmd >= SIOCIWFIRST && cmd <= SIOCIWLAST) { - err = dev_ioctl(net, cmd, argp); + err = wext_handle_ioctl(net, cmd, argp); } else #endif switch (cmd) { @@ -1002,14 +1324,9 @@ 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); + case SIOCBRADDIF: + case SIOCBRDELIF: + err = br_ioctl_call(net, cmd, argp); break; case SIOCGIFVLAN: case SIOCSIFVLAN: @@ -1022,17 +1339,6 @@ 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)) @@ -1040,6 +1346,31 @@ static long sock_ioctl(struct file *file, unsigned cmd, unsigned long arg) err = open_related_ns(&net->ns, get_net_ns); break; + case SIOCGSTAMP_OLD: + case SIOCGSTAMPNS_OLD: + if (!ops->gettstamp) { + err = -ENOIOCTLCMD; + break; + } + err = ops->gettstamp(sock, argp, + cmd == SIOCGSTAMP_OLD, + !IS_ENABLED(CONFIG_64BIT)); + break; + case SIOCGSTAMP_NEW: + case SIOCGSTAMPNS_NEW: + if (!ops->gettstamp) { + err = -ENOIOCTLCMD; + break; + } + err = ops->gettstamp(sock, argp, + cmd == SIOCGSTAMP_NEW, + false); + break; + + case SIOCGIFCONF: + err = dev_ifconf(net, argp); + break; + default: err = sock_do_ioctl(net, sock, cmd, arg); break; @@ -1047,6 +1378,19 @@ static long sock_ioctl(struct file *file, unsigned cmd, unsigned long arg) return err; } +/** + * sock_create_lite - creates a socket + * @family: protocol family (AF_INET, ...) + * @type: communication type (SOCK_STREAM, ...) + * @protocol: protocol (0, ...) + * @res: new socket + * + * Creates a new socket and assigns it to @res, passing through LSM. + * The new socket initialization is not complete, see kernel_accept(). + * Returns 0 or an error. On failure @res is set to %NULL. + * This function internally uses GFP_KERNEL. + */ + int sock_create_lite(int family, int type, int protocol, struct socket **res) { int err; @@ -1078,38 +1422,37 @@ out_release: EXPORT_SYMBOL(sock_create_lite); /* No kernel lock held - perfect */ -static unsigned int sock_poll(struct file *file, poll_table *wait) +static __poll_t sock_poll(struct file *file, poll_table *wait) { - unsigned int busy_flag = 0; - struct socket *sock; + struct socket *sock = file->private_data; + const struct proto_ops *ops = READ_ONCE(sock->ops); + __poll_t events = poll_requested_events(wait), flag = 0; - /* - * We can't return errors to poll, so it's either yes or no. - */ - sock = file->private_data; + if (!ops->poll) + return 0; if (sk_can_busy_loop(sock->sk)) { - /* this socket can poll_ll so tell the system call */ - busy_flag = POLL_BUSY_LOOP; - - /* once, only if requested by syscall */ - if (wait && (wait->_key & POLL_BUSY_LOOP)) + /* poll once if requested by the syscall */ + if (events & POLL_BUSY_LOOP) sk_busy_loop(sock->sk, 1); + + /* if this socket can poll_ll, tell the system call */ + flag = POLL_BUSY_LOOP; } - return busy_flag | sock->ops->poll(file, sock, wait); + return ops->poll(file, sock, wait) | flag; } static int sock_mmap(struct file *file, struct vm_area_struct *vma) { struct socket *sock = file->private_data; - return sock->ops->mmap(file, sock, vma); + return READ_ONCE(sock->ops)->mmap(file, sock, vma); } static int sock_close(struct inode *inode, struct file *filp) { - sock_release(SOCKET_I(inode)); + __sock_release(SOCKET_I(inode), inode); return 0; } @@ -1128,13 +1471,12 @@ static int sock_fasync(int fd, struct file *filp, int on) { struct socket *sock = filp->private_data; struct sock *sk = sock->sk; - struct socket_wq *wq; + struct socket_wq *wq = &sock->wq; if (sk == NULL) return -EINVAL; lock_sock(sk); - wq = rcu_dereference_protected(sock->wq, lockdep_sock_is_held(sk)); fasync_helper(fd, filp, on, &wq->fasync_list); if (!wq->fasync_list) @@ -1161,7 +1503,7 @@ 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); @@ -1174,6 +1516,21 @@ call_kill: } EXPORT_SYMBOL(sock_wake_async); +/** + * __sock_create - creates a socket + * @net: net namespace + * @family: protocol family (AF_INET, ...) + * @type: communication type (SOCK_STREAM, ...) + * @protocol: protocol (0, ...) + * @res: new socket + * @kern: boolean for kernel space sockets + * + * Creates a new socket and assigns it to @res, passing through LSM. + * Returns 0 or an error. On failure @res is set to %NULL. @kern must + * be set to true if the socket resides in kernel space. + * This function internally uses GFP_KERNEL. + */ + int __sock_create(struct net *net, int family, int type, int protocol, struct socket **res, int kern) { @@ -1246,8 +1603,15 @@ int __sock_create(struct net *net, int family, int type, int protocol, rcu_read_unlock(); err = pf->create(net, sock, protocol, kern); - if (err < 0) + if (err < 0) { + /* ->create should release the allocated sock->sk object on error + * and make sure sock->sk is set to NULL to avoid use-after-free + */ + DEBUG_NET_WARN_ONCE(sock->sk, + "%ps must clear sock->sk on failure, family: %d, type: %d, protocol: %d\n", + pf->create, family, type, protocol); goto out_module_put; + } /* * Now to bump the refcnt of the [loadable] module that owns this @@ -1283,23 +1647,45 @@ out_release: } EXPORT_SYMBOL(__sock_create); +/** + * sock_create - creates a socket + * @family: protocol family (AF_INET, ...) + * @type: communication type (SOCK_STREAM, ...) + * @protocol: protocol (0, ...) + * @res: new socket + * + * A wrapper around __sock_create(). + * Returns 0 or an error. This function internally uses GFP_KERNEL. + */ + int sock_create(int family, int type, int protocol, struct socket **res) { return __sock_create(current->nsproxy->net_ns, family, type, protocol, res, 0); } EXPORT_SYMBOL(sock_create); +/** + * sock_create_kern - creates a socket (kernel space) + * @net: net namespace + * @family: protocol family (AF_INET, ...) + * @type: communication type (SOCK_STREAM, ...) + * @protocol: protocol (0, ...) + * @res: new socket + * + * A wrapper around __sock_create(). + * Returns 0 or an error. This function internally uses GFP_KERNEL. + */ + int sock_create_kern(struct net *net, int family, int type, int protocol, struct socket **res) { return __sock_create(net, family, type, protocol, res, 1); } EXPORT_SYMBOL(sock_create_kern); -SYSCALL_DEFINE3(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); @@ -1307,37 +1693,79 @@ SYSCALL_DEFINE3(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; + 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) - goto out; + return sock_alloc_file(sock, flags, NULL); +} - retval = sock_map_fd(sock, flags & (O_CLOEXEC | O_NONBLOCK)); - if (retval < 0) - goto out_release; +/* A hook for bpf progs to attach to and update socket protocol. + * + * A static noinline declaration here could cause the compiler to + * optimize away the function. A global noinline declaration will + * keep the definition, but may optimize away the callsite. + * Therefore, __weak is needed to ensure that the call is still + * emitted, by telling the compiler that we don't know what the + * function might eventually be. + */ -out: - /* It may be already another descriptor 8) Not kernel problem. */ - return retval; +__bpf_hook_start(); -out_release: - sock_release(sock); - return retval; +__weak noinline int update_socket_protocol(int family, int type, int protocol) +{ + return protocol; +} + +__bpf_hook_end(); + +int __sys_socket(int family, int type, int protocol) +{ + struct socket *sock; + int flags; + + sock = __sys_socket_create(family, type, + update_socket_protocol(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)); +} + +SYSCALL_DEFINE3(socket, int, family, int, type, int, protocol) +{ + return __sys_socket(family, type, protocol); } /* * Create a pair of connected sockets. */ -SYSCALL_DEFINE4(socketpair, int, family, int, type, int, protocol, - int __user *, usockvec) +int __sys_socketpair(int family, int type, int protocol, int __user *usockvec) { struct socket *sock1, *sock2; int fd1, fd2, err; @@ -1353,87 +1781,99 @@ SYSCALL_DEFINE4(socketpair, int, family, int, type, int, protocol, flags = (flags & ~SOCK_NONBLOCK) | O_NONBLOCK; /* + * reserve descriptors and make sure we won't fail + * to return them to userland. + */ + fd1 = get_unused_fd_flags(flags); + if (unlikely(fd1 < 0)) + return fd1; + + fd2 = get_unused_fd_flags(flags); + if (unlikely(fd2 < 0)) { + put_unused_fd(fd1); + return fd2; + } + + err = put_user(fd1, &usockvec[0]); + if (err) + goto out; + + err = put_user(fd2, &usockvec[1]); + if (err) + goto out; + + /* * Obtain the first socket and check if the underlying protocol * supports the socketpair call. */ err = sock_create(family, type, protocol, &sock1); - if (err < 0) + if (unlikely(err < 0)) goto out; err = sock_create(family, type, protocol, &sock2); - if (err < 0) - goto out_release_1; - - err = sock1->ops->socketpair(sock1, sock2); - if (err < 0) - goto out_release_both; + if (unlikely(err < 0)) { + sock_release(sock1); + goto out; + } - fd1 = get_unused_fd_flags(flags); - if (unlikely(fd1 < 0)) { - err = fd1; - goto out_release_both; + err = security_socket_socketpair(sock1, sock2); + if (unlikely(err)) { + sock_release(sock2); + sock_release(sock1); + goto out; } - fd2 = get_unused_fd_flags(flags); - if (unlikely(fd2 < 0)) { - err = fd2; - goto out_put_unused_1; + err = READ_ONCE(sock1->ops)->socketpair(sock1, sock2); + if (unlikely(err < 0)) { + sock_release(sock2); + sock_release(sock1); + goto out; } newfile1 = sock_alloc_file(sock1, flags, NULL); if (IS_ERR(newfile1)) { err = PTR_ERR(newfile1); - goto out_put_unused_both; + sock_release(sock2); + goto out; } newfile2 = sock_alloc_file(sock2, flags, NULL); if (IS_ERR(newfile2)) { err = PTR_ERR(newfile2); - goto out_fput_1; + fput(newfile1); + goto out; } - err = put_user(fd1, &usockvec[0]); - if (err) - goto out_fput_both; - - err = put_user(fd2, &usockvec[1]); - if (err) - goto out_fput_both; - audit_fd_pair(fd1, fd2); fd_install(fd1, newfile1); fd_install(fd2, newfile2); - /* fd1 and fd2 may be already another descriptors. - * Not kernel problem. - */ - return 0; -out_fput_both: - fput(newfile2); - fput(newfile1); +out: put_unused_fd(fd2); put_unused_fd(fd1); - goto out; + return err; +} -out_fput_1: - fput(newfile1); - put_unused_fd(fd2); - put_unused_fd(fd1); - sock_release(sock2); - goto out; +SYSCALL_DEFINE4(socketpair, int, family, int, type, int, protocol, + int __user *, usockvec) +{ + return __sys_socketpair(family, type, protocol, usockvec); +} -out_put_unused_both: - put_unused_fd(fd2); -out_put_unused_1: - put_unused_fd(fd1); -out_release_both: - sock_release(sock2); -out_release_1: - sock_release(sock1); -out: +int __sys_bind_socket(struct socket *sock, struct sockaddr_storage *address, + int addrlen) +{ + int err; + + err = security_socket_bind(sock, (struct sockaddr *)address, + addrlen); + if (!err) + err = READ_ONCE(sock->ops)->bind(sock, + (struct sockaddr_unsized *)address, + addrlen); return err; } @@ -1445,27 +1885,29 @@ out: * the protocol layer (having also checked the address is ok). */ -SYSCALL_DEFINE3(bind, int, fd, struct sockaddr __user *, umyaddr, int, addrlen) +int __sys_bind(int fd, struct sockaddr __user *umyaddr, int addrlen) { struct socket *sock; 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); - if (err >= 0) { - err = security_socket_bind(sock, - (struct sockaddr *)&address, - addrlen); - if (!err) - err = sock->ops->bind(sock, - (struct sockaddr *) - &address, addrlen); - } - fput_light(sock->file, fput_needed); - } - return err; + CLASS(fd, f)(fd); + int err; + + if (fd_empty(f)) + return -EBADF; + sock = sock_from_file(fd_file(f)); + if (unlikely(!sock)) + return -ENOTSOCK; + + err = move_addr_to_kernel(umyaddr, addrlen, &address); + if (unlikely(err)) + return err; + + return __sys_bind_socket(sock, &address, addrlen); +} + +SYSCALL_DEFINE3(bind, int, fd, struct sockaddr __user *, umyaddr, int, addrlen) +{ + return __sys_bind(fd, umyaddr, addrlen); } /* @@ -1473,97 +1915,83 @@ SYSCALL_DEFINE3(bind, int, fd, struct sockaddr __user *, umyaddr, int, addrlen) * necessary for a listen, and if that works, we mark the socket as * ready for listening. */ +int __sys_listen_socket(struct socket *sock, int backlog) +{ + int somaxconn, err; -SYSCALL_DEFINE2(listen, int, fd, int, backlog) + somaxconn = READ_ONCE(sock_net(sock->sk)->core.sysctl_somaxconn); + if ((unsigned int)backlog > somaxconn) + backlog = somaxconn; + + err = security_socket_listen(sock, backlog); + if (!err) + err = READ_ONCE(sock->ops)->listen(sock, backlog); + return err; +} + +int __sys_listen(int fd, int backlog) { + CLASS(fd, f)(fd); struct socket *sock; - int err, fput_needed; - int somaxconn; - sock = sockfd_lookup_light(fd, &err, &fput_needed); - if (sock) { - somaxconn = sock_net(sock->sk)->core.sysctl_somaxconn; - if ((unsigned int)backlog > somaxconn) - backlog = somaxconn; + if (fd_empty(f)) + return -EBADF; + sock = sock_from_file(fd_file(f)); + if (unlikely(!sock)) + return -ENOTSOCK; - err = security_socket_listen(sock, backlog); - if (!err) - err = sock->ops->listen(sock, backlog); - - fput_light(sock->file, fput_needed); - } - return err; + return __sys_listen_socket(sock, backlog); } -/* - * For accept, we attempt to create a new socket, set up the link - * with the client, wake up the client, then return the new - * connected fd. We collect the address of the connector in kernel - * space and move it to user at the very end. This is unclean because - * we open the socket then return an error. - * - * 1003.1g adds the ability to recvmsg() to query connection pending - * status to recvmsg. We need to add that support in a way thats - * clean when we restucture accept also. - */ +SYSCALL_DEFINE2(listen, int, fd, int, backlog) +{ + return __sys_listen(fd, backlog); +} -SYSCALL_DEFINE4(accept4, int, fd, struct sockaddr __user *, upeer_sockaddr, - int __user *, upeer_addrlen, int, flags) +struct file *do_accept(struct file *file, struct proto_accept_arg *arg, + struct sockaddr __user *upeer_sockaddr, + int __user *upeer_addrlen, int flags) { struct socket *sock, *newsock; struct file *newfile; - int err, len, newfd, fput_needed; + int err, len; struct sockaddr_storage address; + const struct proto_ops *ops; - 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); + sock = sock_from_file(file); if (!sock) - goto out; + return ERR_PTR(-ENOTSOCK); - err = -ENFILE; newsock = sock_alloc(); if (!newsock) - goto out_put; + return ERR_PTR(-ENFILE); + ops = READ_ONCE(sock->ops); newsock->type = sock->type; - newsock->ops = sock->ops; + newsock->ops = ops; /* * We don't need try_module_get here, as the listening socket (sock) * has the protocol module (sock->ops->owner) held. */ - __module_get(newsock->ops->owner); + __module_get(ops->owner); - newfd = get_unused_fd_flags(flags); - if (unlikely(newfd < 0)) { - err = newfd; - sock_release(newsock); - goto out_put; - } newfile = sock_alloc_file(newsock, flags, sock->sk->sk_prot_creator->name); - if (IS_ERR(newfile)) { - err = PTR_ERR(newfile); - put_unused_fd(newfd); - sock_release(newsock); - goto out_put; - } + if (IS_ERR(newfile)) + return newfile; err = security_socket_accept(sock, newsock); if (err) goto out_fd; - err = sock->ops->accept(sock, newsock, sock->file->f_flags, false); + arg->flags |= sock->file->f_flags; + err = ops->accept(sock, newsock, arg); if (err < 0) goto out_fd; if (upeer_sockaddr) { - if (newsock->ops->getname(newsock, (struct sockaddr *)&address, - &len, 2) < 0) { + len = ops->getname(newsock, (struct sockaddr *)&address, 2); + if (len < 0) { err = -ECONNABORTED; goto out_fd; } @@ -1574,24 +2002,59 @@ SYSCALL_DEFINE4(accept4, int, fd, struct sockaddr __user *, upeer_sockaddr, } /* File flags are not inherited via accept() unlike another OSes. */ - - fd_install(newfd, newfile); - err = newfd; - -out_put: - fput_light(sock->file, fput_needed); -out: - return err; + return newfile; out_fd: fput(newfile); - put_unused_fd(newfd); - goto out_put; + return ERR_PTR(err); +} + +static int __sys_accept4_file(struct file *file, struct sockaddr __user *upeer_sockaddr, + int __user *upeer_addrlen, int flags) +{ + struct proto_accept_arg arg = { }; + + if (flags & ~(SOCK_CLOEXEC | SOCK_NONBLOCK)) + return -EINVAL; + + if (SOCK_NONBLOCK != O_NONBLOCK && (flags & SOCK_NONBLOCK)) + flags = (flags & ~SOCK_NONBLOCK) | O_NONBLOCK; + + return FD_ADD(flags, do_accept(file, &arg, upeer_sockaddr, upeer_addrlen, flags)); +} + +/* + * For accept, we attempt to create a new socket, set up the link + * with the client, wake up the client, then return the new + * connected fd. We collect the address of the connector in kernel + * space and move it to user at the very end. This is unclean because + * we open the socket then return an error. + * + * 1003.1g adds the ability to recvmsg() to query connection pending + * status to recvmsg. We need to add that support in a way thats + * clean when we restructure accept also. + */ + +int __sys_accept4(int fd, struct sockaddr __user *upeer_sockaddr, + int __user *upeer_addrlen, int flags) +{ + CLASS(fd, f)(fd); + + if (fd_empty(f)) + return -EBADF; + return __sys_accept4_file(fd_file(f), upeer_sockaddr, + upeer_addrlen, flags); +} + +SYSCALL_DEFINE4(accept4, int, fd, struct sockaddr __user *, upeer_sockaddr, + int __user *, upeer_addrlen, int, flags) +{ + return __sys_accept4(fd, upeer_sockaddr, upeer_addrlen, flags); } SYSCALL_DEFINE3(accept, int, fd, struct sockaddr __user *, upeer_sockaddr, int __user *, upeer_addrlen) { - return sys_accept4(fd, upeer_sockaddr, upeer_addrlen, 0); + return __sys_accept4(fd, upeer_sockaddr, upeer_addrlen, 0); } /* @@ -1606,93 +2069,98 @@ SYSCALL_DEFINE3(accept, int, fd, struct sockaddr __user *, upeer_sockaddr, * include the -EINPROGRESS status for such sockets. */ -SYSCALL_DEFINE3(connect, int, fd, struct sockaddr __user *, uservaddr, - int, addrlen) +int __sys_connect_file(struct file *file, struct sockaddr_storage *address, + int addrlen, int file_flags) { struct socket *sock; - struct sockaddr_storage address; - int err, fput_needed; + int err; - sock = sockfd_lookup_light(fd, &err, &fput_needed); - if (!sock) + sock = sock_from_file(file); + if (!sock) { + err = -ENOTSOCK; goto out; - err = move_addr_to_kernel(uservaddr, addrlen, &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; + goto out; - err = sock->ops->connect(sock, (struct sockaddr *)&address, addrlen, - sock->file->f_flags); -out_put: - fput_light(sock->file, fput_needed); + err = READ_ONCE(sock->ops)->connect(sock, (struct sockaddr_unsized *)address, + addrlen, sock->file->f_flags | file_flags); out: return err; } -/* - * Get the local address ('name') of a socket object. Move the obtained - * name to user space. - */ - -SYSCALL_DEFINE3(getsockname, int, fd, struct sockaddr __user *, usockaddr, - int __user *, usockaddr_len) +int __sys_connect(int fd, struct sockaddr __user *uservaddr, int addrlen) { - struct socket *sock; struct sockaddr_storage address; - int len, err, fput_needed; + CLASS(fd, f)(fd); + int ret; - sock = sockfd_lookup_light(fd, &err, &fput_needed); - if (!sock) - goto out; + if (fd_empty(f)) + return -EBADF; - err = security_socket_getsockname(sock); - if (err) - goto out_put; + ret = move_addr_to_kernel(uservaddr, addrlen, &address); + if (ret) + return ret; - 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); + return __sys_connect_file(fd_file(f), &address, addrlen, 0); +} -out_put: - fput_light(sock->file, fput_needed); -out: - return err; +SYSCALL_DEFINE3(connect, int, fd, struct sockaddr __user *, uservaddr, + int, addrlen) +{ + return __sys_connect(fd, uservaddr, addrlen); +} + +int do_getsockname(struct socket *sock, int peer, + struct sockaddr __user *usockaddr, int __user *usockaddr_len) +{ + struct sockaddr_storage address; + int err; + + if (peer) + err = security_socket_getpeername(sock); + else + err = security_socket_getsockname(sock); + if (err) + return err; + err = READ_ONCE(sock->ops)->getname(sock, (struct sockaddr *)&address, peer); + if (err < 0) + return err; + /* "err" is actually length in this case */ + return move_addr_to_user(&address, err, usockaddr, usockaddr_len); } /* - * Get the remote address ('name') of a socket object. Move the obtained - * name to user space. + * Get the remote or local address ('name') of a socket object. Move the + * obtained name to user space. */ - -SYSCALL_DEFINE3(getpeername, int, fd, struct sockaddr __user *, usockaddr, - int __user *, usockaddr_len) +int __sys_getsockname(int fd, struct sockaddr __user *usockaddr, + int __user *usockaddr_len, int peer) { struct socket *sock; - struct sockaddr_storage address; - int len, err, fput_needed; + CLASS(fd, f)(fd); - sock = sockfd_lookup_light(fd, &err, &fput_needed); - if (sock != NULL) { - err = security_socket_getpeername(sock); - if (err) { - fput_light(sock->file, fput_needed); - return err; - } + if (fd_empty(f)) + return -EBADF; + sock = sock_from_file(fd_file(f)); + if (unlikely(!sock)) + return -ENOTSOCK; + return do_getsockname(sock, peer, usockaddr, usockaddr_len); +} - err = - sock->ops->getname(sock, (struct sockaddr *)&address, &len, - 1); - if (!err) - err = move_addr_to_user(&address, len, usockaddr, - usockaddr_len); - fput_light(sock->file, fput_needed); - } - return err; +SYSCALL_DEFINE3(getsockname, int, fd, struct sockaddr __user *, usockaddr, + int __user *, usockaddr_len) +{ + return __sys_getsockname(fd, usockaddr, usockaddr_len, 0); +} + +SYSCALL_DEFINE3(getpeername, int, fd, struct sockaddr __user *, usockaddr, + int __user *, usockaddr_len) +{ + return __sys_getsockname(fd, usockaddr, usockaddr_len, 1); } /* @@ -1700,45 +2168,49 @@ SYSCALL_DEFINE3(getpeername, int, fd, struct sockaddr __user *, usockaddr, * space and check the user space data area is readable before invoking * the protocol. */ - -SYSCALL_DEFINE6(sendto, int, fd, void __user *, buff, size_t, len, - unsigned int, flags, struct sockaddr __user *, addr, - int, addr_len) +int __sys_sendto(int fd, void __user *buff, size_t len, unsigned int flags, + struct sockaddr __user *addr, int addr_len) { struct socket *sock; struct sockaddr_storage address; int err; struct msghdr msg; - struct iovec iov; - int fput_needed; - err = import_single_range(WRITE, buff, len, &iov, &msg.msg_iter); + err = import_ubuf(ITER_SOURCE, buff, len, &msg.msg_iter); if (unlikely(err)) return err; - sock = sockfd_lookup_light(fd, &err, &fput_needed); - if (!sock) - goto out; + + CLASS(fd, f)(fd); + if (fd_empty(f)) + return -EBADF; + sock = sock_from_file(fd_file(f)); + if (unlikely(!sock)) + return -ENOTSOCK; msg.msg_name = NULL; 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) - goto out_put; + return err; msg.msg_name = (struct sockaddr *)&address; msg.msg_namelen = addr_len; } + flags &= ~MSG_INTERNAL_SENDMSG_FLAGS; if (sock->file->f_flags & O_NONBLOCK) flags |= MSG_DONTWAIT; msg.msg_flags = flags; - err = sock_sendmsg(sock, &msg); + return __sock_sendmsg(sock, &msg); +} -out_put: - fput_light(sock->file, fput_needed); -out: - return err; +SYSCALL_DEFINE6(sendto, int, fd, void __user *, buff, size_t, len, + unsigned int, flags, struct sockaddr __user *, addr, + int, addr_len) +{ + return __sys_sendto(fd, buff, len, flags, addr, addr_len); } /* @@ -1748,7 +2220,7 @@ out: SYSCALL_DEFINE4(send, int, fd, void __user *, buff, size_t, len, unsigned int, flags) { - return sys_sendto(fd, buff, len, flags, NULL, 0); + return __sys_sendto(fd, buff, len, flags, NULL, 0); } /* @@ -1756,33 +2228,29 @@ SYSCALL_DEFINE4(send, int, fd, void __user *, buff, size_t, len, * sender. We verify the buffers are writable and if needed move the * sender address from kernel to user space. */ - -SYSCALL_DEFINE6(recvfrom, int, fd, void __user *, ubuf, size_t, size, - unsigned int, flags, struct sockaddr __user *, addr, - int __user *, addr_len) +int __sys_recvfrom(int fd, void __user *ubuf, size_t size, unsigned int flags, + struct sockaddr __user *addr, int __user *addr_len) { - struct socket *sock; - struct iovec iov; - struct msghdr msg; 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; int err, err2; - int fput_needed; - err = import_single_range(READ, ubuf, size, &iov, &msg.msg_iter); + err = import_ubuf(ITER_DEST, ubuf, size, &msg.msg_iter); if (unlikely(err)) return err; - sock = sockfd_lookup_light(fd, &err, &fput_needed); - 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; + CLASS(fd, f)(fd); + + if (fd_empty(f)) + return -EBADF; + sock = sock_from_file(fd_file(f)); + if (unlikely(!sock)) + return -ENOTSOCK; + if (sock->file->f_flags & O_NONBLOCK) flags |= MSG_DONTWAIT; err = sock_recvmsg(sock, &msg, flags); @@ -1793,12 +2261,16 @@ SYSCALL_DEFINE6(recvfrom, int, fd, void __user *, ubuf, size_t, size, if (err2 < 0) err = err2; } - - fput_light(sock->file, fput_needed); -out: return err; } +SYSCALL_DEFINE6(recvfrom, int, fd, void __user *, ubuf, size_t, size, + unsigned int, flags, struct sockaddr __user *, addr, + int __user *, addr_len) +{ + return __sys_recvfrom(fd, ubuf, size, flags, addr, addr_len); +} + /* * Receive a datagram from a socket. */ @@ -1806,93 +2278,181 @@ out: SYSCALL_DEFINE4(recv, int, fd, void __user *, ubuf, size_t, size, unsigned int, flags) { - return sys_recvfrom(fd, ubuf, size, flags, NULL, NULL); + return __sys_recvfrom(fd, ubuf, size, flags, NULL, NULL); } -/* - * 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 bool sock_use_custom_sol_socket(const struct socket *sock) +{ + return test_bit(SOCK_CUSTOM_SOCKOPT, &sock->flags); +} -SYSCALL_DEFINE5(setsockopt, int, fd, int, level, int, optname, - char __user *, optval, int, optlen) +int do_sock_setsockopt(struct socket *sock, bool compat, int level, + int optname, sockptr_t optval, int optlen) { - int err, fput_needed; - struct socket *sock; + const struct proto_ops *ops; + char *kernel_optval = NULL; + int err; if (optlen < 0) 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 = security_socket_setsockopt(sock, level, optname); + if (err) + goto out_put; - if (level == SOL_SOCKET) - err = - sock_setsockopt(sock, level, optname, optval, + if (!compat) + err = BPF_CGROUP_RUN_PROG_SETSOCKOPT(sock->sk, &level, &optname, + optval, &optlen, + &kernel_optval); + if (err < 0) + goto out_put; + if (err > 0) { + err = 0; + goto out_put; + } + + if (kernel_optval) + optval = KERNEL_SOCKPTR(kernel_optval); + ops = READ_ONCE(sock->ops); + if (level == SOL_SOCKET && !sock_use_custom_sol_socket(sock)) + err = sock_setsockopt(sock, level, optname, optval, optlen); + else if (unlikely(!ops->setsockopt)) + err = -EOPNOTSUPP; + else + err = ops->setsockopt(sock, level, optname, optval, optlen); - else - err = - sock->ops->setsockopt(sock, level, optname, optval, - optlen); + kfree(kernel_optval); out_put: - fput_light(sock->file, fput_needed); + return err; +} +EXPORT_SYMBOL(do_sock_setsockopt); + +/* 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. + */ +int __sys_setsockopt(int fd, int level, int optname, char __user *user_optval, + int optlen) +{ + sockptr_t optval = USER_SOCKPTR(user_optval); + bool compat = in_compat_syscall(); + struct socket *sock; + CLASS(fd, f)(fd); + + if (fd_empty(f)) + return -EBADF; + sock = sock_from_file(fd_file(f)); + if (unlikely(!sock)) + return -ENOTSOCK; + + return do_sock_setsockopt(sock, compat, level, optname, optval, optlen); +} + +SYSCALL_DEFINE5(setsockopt, int, fd, int, level, int, optname, + char __user *, optval, int, optlen) +{ + return __sys_setsockopt(fd, level, optname, optval, optlen); +} + +INDIRECT_CALLABLE_DECLARE(bool tcp_bpf_bypass_getsockopt(int level, + int optname)); + +int do_sock_getsockopt(struct socket *sock, bool compat, int level, + int optname, sockptr_t optval, sockptr_t optlen) +{ + int max_optlen __maybe_unused = 0; + const struct proto_ops *ops; + int err; + + err = security_socket_getsockopt(sock, level, optname); + if (err) + return err; + + if (!compat) + copy_from_sockptr(&max_optlen, optlen, sizeof(int)); + + ops = READ_ONCE(sock->ops); + if (level == SOL_SOCKET) { + err = sk_getsockopt(sock->sk, level, optname, optval, optlen); + } else if (unlikely(!ops->getsockopt)) { + err = -EOPNOTSUPP; + } else { + if (WARN_ONCE(optval.is_kernel || optlen.is_kernel, + "Invalid argument type")) + return -EOPNOTSUPP; + + err = ops->getsockopt(sock, level, optname, optval.user, + optlen.user); } + + if (!compat) + err = BPF_CGROUP_RUN_PROG_GETSOCKOPT(sock->sk, level, optname, + optval, optlen, max_optlen, + err); + return err; } +EXPORT_SYMBOL(do_sock_getsockopt); /* * 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. */ - -SYSCALL_DEFINE5(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; + CLASS(fd, f)(fd); - sock = sockfd_lookup_light(fd, &err, &fput_needed); - if (sock != NULL) { - err = security_socket_getsockopt(sock, level, optname); - if (err) - goto out_put; + if (fd_empty(f)) + return -EBADF; + sock = sock_from_file(fd_file(f)); + if (unlikely(!sock)) + return -ENOTSOCK; - if (level == SOL_SOCKET) - err = - sock_getsockopt(sock, level, optname, optval, - optlen); - else - err = - sock->ops->getsockopt(sock, level, optname, optval, - optlen); -out_put: - fput_light(sock->file, fput_needed); - } - return err; + return do_sock_getsockopt(sock, in_compat_syscall(), level, optname, + USER_SOCKPTR(optval), USER_SOCKPTR(optlen)); +} + +SYSCALL_DEFINE5(getsockopt, int, fd, int, level, int, optname, + char __user *, optval, int __user *, optlen) +{ + return __sys_getsockopt(fd, level, optname, optval, optlen); } /* * Shutdown a socket. */ -SYSCALL_DEFINE2(shutdown, int, fd, int, how) +int __sys_shutdown_sock(struct socket *sock, int how) { - int err, fput_needed; - struct socket *sock; + int err; + + err = security_socket_shutdown(sock, how); + if (!err) + err = READ_ONCE(sock->ops)->shutdown(sock, 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); - fput_light(sock->file, fput_needed); - } return err; } +int __sys_shutdown(int fd, int how) +{ + struct socket *sock; + CLASS(fd, f)(fd); + + if (fd_empty(f)) + return -EBADF; + sock = sock_from_file(fd_file(f)); + if (unlikely(!sock)) + return -ENOTSOCK; + + return __sys_shutdown_sock(sock, how); +} + +SYSCALL_DEFINE2(shutdown, int, fd, int, how) +{ + return __sys_shutdown(fd, how); +} + /* A couple of helpful macros for getting the address of the 32/64 bit * fields which are the same type (int / unsigned) on our platforms. */ @@ -1905,23 +2465,20 @@ 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 = (void __force *)msg.msg_control; - kmsg->msg_controllen = msg.msg_controllen; - kmsg->msg_flags = msg.msg_flags; + 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_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) @@ -1931,11 +2488,11 @@ 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) @@ -1946,25 +2503,39 @@ 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; +} - return import_iovec(save_addr ? READ : WRITE, +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 ? ITER_DEST : ITER_SOURCE, msg.msg_iov, msg.msg_iovlen, UIO_FASTIOV, iov, &kmsg->msg_iter); + return err < 0 ? err : 0; } -static int ___sys_sendmsg(struct socket *sock, struct user_msghdr __user *msg, - struct msghdr *msg_sys, unsigned int flags, - struct used_address *used_address, - unsigned int allowed_msghdr_flags) +static int ____sys_sendmsg(struct socket *sock, struct msghdr *msg_sys, + unsigned int flags, struct used_address *used_address, + unsigned int allowed_msghdr_flags) { - struct compat_msghdr __user *msg_compat = - (struct compat_msghdr __user *)msg; - struct sockaddr_storage address; - struct iovec iovstack[UIO_FASTIOV], *iov = iovstack; unsigned char ctl[sizeof(struct cmsghdr) + 20] __aligned(sizeof(__kernel_size_t)); /* 20 is size of ipv6_pktinfo */ @@ -1972,19 +2543,10 @@ static int ___sys_sendmsg(struct socket *sock, struct user_msghdr __user *msg, int ctl_len; ssize_t err; - msg_sys->msg_name = &address; - - if (MSG_CMSG_COMPAT & flags) - err = get_compat_msghdr(msg_sys, msg_compat, NULL, &iov); - else - err = copy_msghdr_from_user(msg_sys, msg, NULL, &iov); - if (err < 0) - return err; - err = -ENOBUFS; if (msg_sys->msg_controllen > INT_MAX) - goto out_freeiov; + goto out; flags |= (msg_sys->msg_flags & allowed_msghdr_flags); ctl_len = msg_sys->msg_controllen; if ((MSG_CMSG_COMPAT & flags) && ctl_len) { @@ -1992,7 +2554,7 @@ static int ___sys_sendmsg(struct socket *sock, struct user_msghdr __user *msg, cmsghdr_from_user_compat_to_kern(msg_sys, sock->sk, ctl, sizeof(ctl)); if (err) - goto out_freeiov; + goto out; ctl_buf = msg_sys->msg_control; ctl_len = msg_sys->msg_controllen; } else if (ctl_len) { @@ -2001,20 +2563,15 @@ static int ___sys_sendmsg(struct socket *sock, struct user_msghdr __user *msg, if (ctl_len > sizeof(ctl)) { ctl_buf = sock_kmalloc(sock->sk, ctl_len, GFP_KERNEL); if (ctl_buf == NULL) - goto out_freeiov; + 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; } + flags &= ~MSG_INTERNAL_SENDMSG_FLAGS; msg_sys->msg_flags = flags; if (sock->file->f_flags & O_NONBLOCK) @@ -2032,7 +2589,7 @@ static int ___sys_sendmsg(struct socket *sock, struct user_msghdr __user *msg, err = sock_sendmsg_nosec(sock, msg_sys); goto out_freectl; } - err = sock_sendmsg(sock, msg_sys); + err = __sock_sendmsg(sock, msg_sys); /* * If this is sendmmsg() and sending to current destination address was * successful, remember it. @@ -2047,7 +2604,47 @@ static int ___sys_sendmsg(struct socket *sock, struct user_msghdr __user *msg, out_freectl: if (ctl_buf != ctl) sock_kfree_s(sock->sk, ctl_buf, ctl_len); -out_freeiov: +out: + return err; +} + +static int sendmsg_copy_msghdr(struct msghdr *msg, + struct user_msghdr __user *umsg, unsigned flags, + struct iovec **iov) +{ + int err; + + if (flags & MSG_CMSG_COMPAT) { + struct compat_msghdr __user *msg_compat; + + msg_compat = (struct compat_msghdr __user *) umsg; + err = get_compat_msghdr(msg, msg_compat, NULL, iov); + } else { + err = copy_msghdr_from_user(msg, umsg, NULL, iov); + } + if (err < 0) + return err; + + return 0; +} + +static int ___sys_sendmsg(struct socket *sock, struct user_msghdr __user *msg, + struct msghdr *msg_sys, unsigned int flags, + struct used_address *used_address, + unsigned int allowed_msghdr_flags) +{ + struct sockaddr_storage address; + struct iovec iovstack[UIO_FASTIOV], *iov = iovstack; + ssize_t err; + + msg_sys->msg_name = &address; + + err = sendmsg_copy_msghdr(msg_sys, msg, flags, &iov); + if (err < 0) + return err; + + err = ____sys_sendmsg(sock, msg_sys, flags, used_address, + allowed_msghdr_flags); kfree(iov); return err; } @@ -2055,29 +2652,35 @@ out_freeiov: /* * BSD sendmsg interface */ +long __sys_sendmsg_sock(struct socket *sock, struct msghdr *msg, + unsigned int flags) +{ + return ____sys_sendmsg(sock, msg, flags, NULL, 0); +} -long __sys_sendmsg(int fd, struct user_msghdr __user *msg, unsigned flags) +long __sys_sendmsg(int fd, struct user_msghdr __user *msg, unsigned int flags, + bool forbid_cmsg_compat) { - int fput_needed, err; struct msghdr msg_sys; struct socket *sock; - sock = sockfd_lookup_light(fd, &err, &fput_needed); - if (!sock) - goto out; + if (forbid_cmsg_compat && (flags & MSG_CMSG_COMPAT)) + return -EINVAL; - err = ___sys_sendmsg(sock, msg, &msg_sys, flags, NULL, 0); + CLASS(fd, f)(fd); - fput_light(sock->file, fput_needed); -out: - return err; + if (fd_empty(f)) + return -EBADF; + sock = sock_from_file(fd_file(f)); + if (unlikely(!sock)) + return -ENOTSOCK; + + return ___sys_sendmsg(sock, msg, &msg_sys, flags, NULL, 0); } SYSCALL_DEFINE3(sendmsg, int, fd, struct user_msghdr __user *, msg, unsigned int, flags) { - if (flags & MSG_CMSG_COMPAT) - return -EINVAL; - return __sys_sendmsg(fd, msg, flags); + return __sys_sendmsg(fd, msg, flags, true); } /* @@ -2085,9 +2688,9 @@ SYSCALL_DEFINE3(sendmsg, int, fd, struct user_msghdr __user *, msg, unsigned int */ int __sys_sendmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen, - unsigned int flags) + unsigned int flags, bool forbid_cmsg_compat) { - int fput_needed, err, datagrams; + int err, datagrams; struct socket *sock; struct mmsghdr __user *entry; struct compat_mmsghdr __user *compat_entry; @@ -2095,14 +2698,21 @@ int __sys_sendmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen, struct used_address used_address; unsigned int oflags = flags; + if (forbid_cmsg_compat && (flags & MSG_CMSG_COMPAT)) + return -EINVAL; + if (vlen > UIO_MAXIOV) vlen = UIO_MAXIOV; datagrams = 0; - sock = sockfd_lookup_light(fd, &err, &fput_needed); - if (!sock) - return err; + CLASS(fd, f)(fd); + + if (fd_empty(f)) + return -EBADF; + sock = sock_from_file(fd_file(f)); + if (unlikely(!sock)) + return -ENOTSOCK; used_address.name_len = UINT_MAX; entry = mmsg; @@ -2139,8 +2749,6 @@ int __sys_sendmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen, cond_resched(); } - fput_light(sock->file, fput_needed); - /* We only return an error if no datagrams were able to be sent */ if (datagrams != 0) return datagrams; @@ -2151,38 +2759,44 @@ int __sys_sendmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen, SYSCALL_DEFINE4(sendmmsg, int, fd, struct mmsghdr __user *, mmsg, unsigned int, vlen, unsigned int, flags) { - if (flags & MSG_CMSG_COMPAT) - return -EINVAL; - return __sys_sendmmsg(fd, mmsg, vlen, flags); + return __sys_sendmmsg(fd, mmsg, vlen, flags, true); } -static int ___sys_recvmsg(struct socket *sock, struct user_msghdr __user *msg, - struct msghdr *msg_sys, unsigned int flags, int nosec) +static int recvmsg_copy_msghdr(struct msghdr *msg, + struct user_msghdr __user *umsg, unsigned flags, + struct sockaddr __user **uaddr, + struct iovec **iov) { - struct compat_msghdr __user *msg_compat = - (struct compat_msghdr __user *)msg; - struct iovec iovstack[UIO_FASTIOV]; - struct iovec *iov = iovstack; - unsigned long cmsg_ptr; - int len; ssize_t err; - /* kernel mode address */ - struct sockaddr_storage addr; + if (MSG_CMSG_COMPAT & flags) { + struct compat_msghdr __user *msg_compat; - /* user mode address pointers */ - struct sockaddr __user *uaddr; - int __user *uaddr_len = COMPAT_NAMELEN(msg); - - msg_sys->msg_name = &addr; - - if (MSG_CMSG_COMPAT & flags) - err = get_compat_msghdr(msg_sys, msg_compat, &uaddr, &iov); - else - err = copy_msghdr_from_user(msg_sys, msg, &uaddr, &iov); + msg_compat = (struct compat_msghdr __user *) umsg; + err = get_compat_msghdr(msg, msg_compat, uaddr, iov); + } else { + err = copy_msghdr_from_user(msg, umsg, uaddr, iov); + } if (err < 0) return err; + return 0; +} + +static int ____sys_recvmsg(struct socket *sock, struct msghdr *msg_sys, + struct user_msghdr __user *msg, + struct sockaddr __user *uaddr, + unsigned int flags, int nosec) +{ + struct compat_msghdr __user *msg_compat = + (struct compat_msghdr __user *) msg; + int __user *uaddr_len = COMPAT_NAMELEN(msg); + struct sockaddr_storage addr; + unsigned long cmsg_ptr; + int len; + ssize_t err; + + msg_sys->msg_name = &addr; cmsg_ptr = (unsigned long)msg_sys->msg_control; msg_sys->msg_flags = flags & (MSG_CMSG_CLOEXEC|MSG_CMSG_COMPAT); @@ -2191,9 +2805,14 @@ static int ___sys_recvmsg(struct socket *sock, struct user_msghdr __user *msg, if (sock->file->f_flags & O_NONBLOCK) flags |= MSG_DONTWAIT; - err = (nosec ? sock_recvmsg_nosec : sock_recvmsg)(sock, msg_sys, flags); + + if (unlikely(nosec)) + err = sock_recvmsg_nosec(sock, msg_sys, flags); + else + err = sock_recvmsg(sock, msg_sys, flags); + if (err < 0) - goto out_freeiov; + goto out; len = err; if (uaddr != NULL) { @@ -2201,12 +2820,12 @@ static int ___sys_recvmsg(struct socket *sock, struct user_msghdr __user *msg, msg_sys->msg_namelen, uaddr, uaddr_len); if (err < 0) - goto out_freeiov; + goto out; } err = __put_user((msg_sys->msg_flags & ~MSG_CMSG_COMPAT), COMPAT_FLAGS(msg)); if (err) - goto out_freeiov; + goto out; if (MSG_CMSG_COMPAT & flags) err = __put_user((unsigned long)msg_sys->msg_control - cmsg_ptr, &msg_compat->msg_controllen); @@ -2214,10 +2833,25 @@ static int ___sys_recvmsg(struct socket *sock, struct user_msghdr __user *msg, err = __put_user((unsigned long)msg_sys->msg_control - cmsg_ptr, &msg->msg_controllen); if (err) - goto out_freeiov; + goto out; err = len; +out: + return err; +} -out_freeiov: +static int ___sys_recvmsg(struct socket *sock, struct user_msghdr __user *msg, + struct msghdr *msg_sys, unsigned int flags, int nosec) +{ + struct iovec iovstack[UIO_FASTIOV], *iov = iovstack; + /* user mode address pointers */ + struct sockaddr __user *uaddr; + ssize_t err; + + err = recvmsg_copy_msghdr(msg_sys, msg, flags, &uaddr, &iov); + if (err < 0) + return err; + + err = ____sys_recvmsg(sock, msg_sys, msg, uaddr, flags, nosec); kfree(iov); return err; } @@ -2226,39 +2860,48 @@ out_freeiov: * BSD recvmsg interface */ -long __sys_recvmsg(int fd, struct user_msghdr __user *msg, unsigned flags) +long __sys_recvmsg_sock(struct socket *sock, struct msghdr *msg, + struct user_msghdr __user *umsg, + struct sockaddr __user *uaddr, unsigned int flags) +{ + return ____sys_recvmsg(sock, msg, umsg, uaddr, flags, 0); +} + +long __sys_recvmsg(int fd, struct user_msghdr __user *msg, unsigned int flags, + bool forbid_cmsg_compat) { - int fput_needed, err; struct msghdr msg_sys; struct socket *sock; - sock = sockfd_lookup_light(fd, &err, &fput_needed); - if (!sock) - goto out; + if (forbid_cmsg_compat && (flags & MSG_CMSG_COMPAT)) + return -EINVAL; - err = ___sys_recvmsg(sock, msg, &msg_sys, flags, 0); + CLASS(fd, f)(fd); - fput_light(sock->file, fput_needed); -out: - return err; + if (fd_empty(f)) + return -EBADF; + sock = sock_from_file(fd_file(f)); + if (unlikely(!sock)) + return -ENOTSOCK; + + return ___sys_recvmsg(sock, msg, &msg_sys, flags, 0); } SYSCALL_DEFINE3(recvmsg, int, fd, struct user_msghdr __user *, msg, unsigned int, flags) { - if (flags & MSG_CMSG_COMPAT) - return -EINVAL; - return __sys_recvmsg(fd, msg, flags); + return __sys_recvmsg(fd, msg, flags, true); } /* * Linux recvmmsg interface */ -int __sys_recvmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen, - unsigned int flags, struct timespec *timeout) +static int do_recvmmsg(int fd, struct mmsghdr __user *mmsg, + unsigned int vlen, unsigned int flags, + struct timespec64 *timeout) { - int fput_needed, err, datagrams; + int err = 0, datagrams; struct socket *sock; struct mmsghdr __user *entry; struct compat_mmsghdr __user *compat_entry; @@ -2273,14 +2916,18 @@ int __sys_recvmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen, datagrams = 0; - sock = sockfd_lookup_light(fd, &err, &fput_needed); - if (!sock) - return err; + CLASS(fd, f)(fd); - err = sock_error(sock->sk); - if (err) { - datagrams = err; - goto out_put; + if (fd_empty(f)) + return -EBADF; + sock = sock_from_file(fd_file(f)); + if (unlikely(!sock)) + return -ENOTSOCK; + + if (likely(!(flags & MSG_ERRQUEUE))) { + err = sock_error(sock->sk); + if (err) + return err; } entry = mmsg; @@ -2319,8 +2966,7 @@ int __sys_recvmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen, if (timeout) { ktime_get_ts64(&timeout64); - *timeout = timespec64_to_timespec( - timespec64_sub(end_time, timeout64)); + *timeout = timespec64_sub(end_time, timeout64); if (timeout->tv_sec < 0) { timeout->tv_sec = timeout->tv_nsec = 0; break; @@ -2338,12 +2984,10 @@ int __sys_recvmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen, } if (err == 0) - goto out_put; + return datagrams; - if (datagrams == 0) { - datagrams = err; - goto out_put; - } + if (datagrams == 0) + return err; /* * We may return less entries than requested (vlen) if the @@ -2356,39 +3000,64 @@ int __sys_recvmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen, * error to return on the next call or if the * app asks about it using getsockopt(SO_ERROR). */ - sock->sk->sk_err = -err; + WRITE_ONCE(sock->sk->sk_err, -err); } -out_put: - fput_light(sock->file, fput_needed); - return datagrams; } -SYSCALL_DEFINE5(recvmmsg, int, fd, struct mmsghdr __user *, mmsg, - unsigned int, vlen, unsigned int, flags, - struct timespec __user *, timeout) +int __sys_recvmmsg(int fd, struct mmsghdr __user *mmsg, + unsigned int vlen, unsigned int flags, + struct __kernel_timespec __user *timeout, + struct old_timespec32 __user *timeout32) { int datagrams; - struct timespec timeout_sys; - - if (flags & MSG_CMSG_COMPAT) - return -EINVAL; + struct timespec64 timeout_sys; - if (!timeout) - return __sys_recvmmsg(fd, mmsg, vlen, flags, NULL); + if (timeout && get_timespec64(&timeout_sys, timeout)) + return -EFAULT; - if (copy_from_user(&timeout_sys, timeout, sizeof(timeout_sys))) + if (timeout32 && get_old_timespec32(&timeout_sys, timeout32)) return -EFAULT; - datagrams = __sys_recvmmsg(fd, mmsg, vlen, flags, &timeout_sys); + if (!timeout && !timeout32) + return do_recvmmsg(fd, mmsg, vlen, flags, NULL); + + datagrams = do_recvmmsg(fd, mmsg, vlen, flags, &timeout_sys); + + if (datagrams <= 0) + return datagrams; + + if (timeout && put_timespec64(&timeout_sys, timeout)) + datagrams = -EFAULT; - if (datagrams > 0 && - copy_to_user(timeout, &timeout_sys, sizeof(timeout_sys))) + if (timeout32 && put_old_timespec32(&timeout_sys, timeout32)) datagrams = -EFAULT; return datagrams; } +SYSCALL_DEFINE5(recvmmsg, int, fd, struct mmsghdr __user *, mmsg, + unsigned int, vlen, unsigned int, flags, + struct __kernel_timespec __user *, timeout) +{ + if (flags & MSG_CMSG_COMPAT) + return -EINVAL; + + return __sys_recvmmsg(fd, mmsg, vlen, flags, timeout, NULL); +} + +#ifdef CONFIG_COMPAT_32BIT_TIME +SYSCALL_DEFINE5(recvmmsg_time32, int, fd, struct mmsghdr __user *, mmsg, + unsigned int, vlen, unsigned int, flags, + struct old_timespec32 __user *, timeout) +{ + if (flags & MSG_CMSG_COMPAT) + return -EINVAL; + + return __sys_recvmmsg(fd, mmsg, vlen, flags, NULL, timeout); +} +#endif + #ifdef __ARCH_WANT_SYS_SOCKETCALL /* Argument list sizes for sys_socketcall */ #define AL(x) ((x) * sizeof(unsigned long)) @@ -2418,6 +3087,7 @@ SYSCALL_DEFINE2(socketcall, int, call, unsigned long __user *, args) if (call < 1 || call > SYS_SENDMMSG) return -EINVAL; + call = array_index_nospec(call, SYS_SENDMMSG + 1); len = nargs[call]; if (len > sizeof(a)) @@ -2436,76 +3106,89 @@ SYSCALL_DEFINE2(socketcall, int, call, unsigned long __user *, args) switch (call) { case SYS_SOCKET: - err = sys_socket(a0, a1, a[2]); + err = __sys_socket(a0, a1, a[2]); break; case SYS_BIND: - err = sys_bind(a0, (struct sockaddr __user *)a1, a[2]); + err = __sys_bind(a0, (struct sockaddr __user *)a1, a[2]); break; case SYS_CONNECT: - err = sys_connect(a0, (struct sockaddr __user *)a1, a[2]); + err = __sys_connect(a0, (struct sockaddr __user *)a1, a[2]); break; case SYS_LISTEN: - err = sys_listen(a0, a1); + err = __sys_listen(a0, a1); break; case SYS_ACCEPT: - err = sys_accept4(a0, (struct sockaddr __user *)a1, - (int __user *)a[2], 0); + err = __sys_accept4(a0, (struct sockaddr __user *)a1, + (int __user *)a[2], 0); break; case SYS_GETSOCKNAME: err = - sys_getsockname(a0, (struct sockaddr __user *)a1, - (int __user *)a[2]); + __sys_getsockname(a0, (struct sockaddr __user *)a1, + (int __user *)a[2], 0); break; case SYS_GETPEERNAME: err = - sys_getpeername(a0, (struct sockaddr __user *)a1, - (int __user *)a[2]); + __sys_getsockname(a0, (struct sockaddr __user *)a1, + (int __user *)a[2], 1); break; case SYS_SOCKETPAIR: - err = sys_socketpair(a0, a1, a[2], (int __user *)a[3]); + err = __sys_socketpair(a0, a1, a[2], (int __user *)a[3]); break; case SYS_SEND: - err = sys_send(a0, (void __user *)a1, a[2], a[3]); + err = __sys_sendto(a0, (void __user *)a1, a[2], a[3], + NULL, 0); break; case SYS_SENDTO: - err = sys_sendto(a0, (void __user *)a1, a[2], a[3], - (struct sockaddr __user *)a[4], a[5]); + err = __sys_sendto(a0, (void __user *)a1, a[2], a[3], + (struct sockaddr __user *)a[4], a[5]); break; case SYS_RECV: - err = sys_recv(a0, (void __user *)a1, a[2], a[3]); + err = __sys_recvfrom(a0, (void __user *)a1, a[2], a[3], + NULL, NULL); break; case SYS_RECVFROM: - err = sys_recvfrom(a0, (void __user *)a1, a[2], a[3], - (struct sockaddr __user *)a[4], - (int __user *)a[5]); + err = __sys_recvfrom(a0, (void __user *)a1, a[2], a[3], + (struct sockaddr __user *)a[4], + (int __user *)a[5]); break; case SYS_SHUTDOWN: - err = sys_shutdown(a0, a1); + err = __sys_shutdown(a0, a1); break; case SYS_SETSOCKOPT: - err = sys_setsockopt(a0, a1, a[2], (char __user *)a[3], a[4]); + err = __sys_setsockopt(a0, a1, a[2], (char __user *)a[3], + a[4]); break; case SYS_GETSOCKOPT: err = - sys_getsockopt(a0, a1, a[2], (char __user *)a[3], - (int __user *)a[4]); + __sys_getsockopt(a0, a1, a[2], (char __user *)a[3], + (int __user *)a[4]); break; case SYS_SENDMSG: - err = sys_sendmsg(a0, (struct user_msghdr __user *)a1, a[2]); + err = __sys_sendmsg(a0, (struct user_msghdr __user *)a1, + a[2], true); break; case SYS_SENDMMSG: - err = sys_sendmmsg(a0, (struct mmsghdr __user *)a1, a[2], a[3]); + err = __sys_sendmmsg(a0, (struct mmsghdr __user *)a1, a[2], + a[3], true); break; case SYS_RECVMSG: - err = sys_recvmsg(a0, (struct user_msghdr __user *)a1, a[2]); + err = __sys_recvmsg(a0, (struct user_msghdr __user *)a1, + a[2], true); break; case SYS_RECVMMSG: - err = sys_recvmmsg(a0, (struct mmsghdr __user *)a1, a[2], a[3], - (struct timespec __user *)a[4]); + if (IS_ENABLED(CONFIG_64BIT)) + err = __sys_recvmmsg(a0, (struct mmsghdr __user *)a1, + a[2], a[3], + (struct __kernel_timespec __user *)a[4], + NULL); + else + err = __sys_recvmmsg(a0, (struct mmsghdr __user *)a1, + a[2], a[3], NULL, + (struct old_timespec32 __user *)a[4]); break; case SYS_ACCEPT4: - err = sys_accept4(a0, (struct sockaddr __user *)a1, - (int __user *)a[2], a[3]); + err = __sys_accept4(a0, (struct sockaddr __user *)a1, + (int __user *)a[2], a[3]); break; default: err = -EINVAL; @@ -2544,7 +3227,7 @@ 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); @@ -2572,10 +3255,15 @@ 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); +bool sock_is_registered(int family) +{ + return family < NPROTO && rcu_access_pointer(net_families[family]); +} + static int __init sock_init(void) { int err; @@ -2599,7 +3287,7 @@ 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); @@ -2622,7 +3310,6 @@ out: out_mount: unregister_filesystem(&sock_fs_type); -out_fs: goto out; } @@ -2631,513 +3318,99 @@ core_initcall(sock_init); /* early initcall */ #ifdef CONFIG_PROC_FS void socket_seq_show(struct seq_file *seq) { - int cpu; - int counter = 0; - - for_each_possible_cpu(cpu) - counter += per_cpu(sockets_in_use, cpu); - - /* It can be negative, by the way. 8) */ - if (counter < 0) - counter = 0; - - seq_printf(seq, "sockets: used %d\n", counter); + seq_printf(seq, "sockets: used %d\n", + sock_inuse_get(seq->private)); } #endif /* CONFIG_PROC_FS */ -#ifdef CONFIG_COMPAT -static int do_siocgstamp(struct net *net, struct socket *sock, - unsigned int cmd, void __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 = compat_put_timeval(&ktv, up); - - return err; -} - -static int do_siocgstampns(struct net *net, struct socket *sock, - unsigned int cmd, void __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 = compat_put_timespec(&kts, up); - - return err; -} - -static int dev_ifname32(struct net *net, struct compat_ifreq __user *uifr32) +/* 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 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 (in_compat_syscall()) { + struct compat_ifreq *ifr32 = (struct compat_ifreq *)ifr; - if (copy_in_user(uifr32, uifr, sizeof(struct compat_ifreq))) - return -EFAULT; - - return 0; -} + memset(ifr, 0, sizeof(*ifr)); + if (copy_from_user(ifr32, arg, sizeof(*ifr32))) + return -EFAULT; -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 (ifrdata) + *ifrdata = compat_ptr(ifr32->ifr_data); - if (copy_from_user(&ifc32, uifc32, sizeof(struct compat_ifconf))) - return -EFAULT; - - memset(&ifc, 0, sizeof(ifc)); - 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++; - } + return 0; } - 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))) + if (copy_from_user(ifr, arg, sizeof(*ifr))) 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; + 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 = ALIGN(sizeof(struct ifreq), 8); - struct ethtool_rxnfc __user *rxnfc; - struct ifreq __user *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; - break; - } - - ifr = compat_alloc_user_space(buf_size); - rxnfc = (void __user *)ifr + ALIGN(sizeof(struct ifreq), 8); - - if (copy_in_user(&ifr->ifr_name, &ifr32->ifr_name, IFNAMSIZ)) - return -EFAULT; - - if (put_user(convert_in ? rxnfc : compat_ptr(data), - &ifr->ifr_ifru.ifru_data)) - return -EFAULT; - - 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) || - copy_in_user(&rxnfc->rule_cnt, &compat_rxnfc->rule_cnt, - sizeof(rxnfc->rule_cnt))) - return -EFAULT; - } - - ret = dev_ioctl(net, SIOCETHTOOL, ifr); - 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) { - void __user *uptr; compat_uptr_t uptr32; - struct ifreq __user *uifr; + struct ifreq ifr; + void __user *saved; + int err; - uifr = compat_alloc_user_space(sizeof(*uifr)); - if (copy_in_user(uifr, uifr32, sizeof(struct compat_ifreq))) + if (get_user_ifreq(&ifr, NULL, uifr32)) return -EFAULT; if (get_user(uptr32, &uifr32->ifr_settings.ifs_ifsu)) return -EFAULT; - uptr = compat_ptr(uptr32); + saved = ifr.ifr_settings.ifs_ifsu.raw_hdlc; + ifr.ifr_settings.ifs_ifsu.raw_hdlc = 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; - mm_segment_t old_fs; - int err; - - 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, - (struct ifreq __user __force *) &kifr); - set_fs(old_fs); - - return err; - default: - return -ENOIOCTLCMD; + err = dev_ioctl(net, SIOCWANDEV, &ifr, NULL, NULL); + if (!err) { + ifr.ifr_settings.ifs_ifsu.raw_hdlc = saved; + if (put_user_ifreq(&ifr, uifr32)) + err = -EFAULT; } + return err; } /* Handle ioctls that use ifreq::ifr_data and just need struct ifreq converted */ static int compat_ifr_data_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)); - - 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; + struct ifreq ifreq; + 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; - old_fs = get_fs(); - set_fs(KERNEL_DS); - err = dev_ioctl(net, cmd, (void __user __force *)&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; -} - -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, @@ -3146,37 +3419,23 @@ static int compat_sock_ioctl_trans(struct file *file, struct socket *sock, void __user *argp = compat_ptr(arg); struct sock *sk = sock->sk; struct net *net = sock_net(sk); + const struct proto_ops *ops; 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 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 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 SIOCGSTAMP_OLD: + case SIOCGSTAMPNS_OLD: + ops = READ_ONCE(sock->ops); + if (!ops->gettstamp) + return -ENOIOCTLCMD; + return ops->gettstamp(sock, argp, cmd == SIOCGSTAMP_OLD, + !COMPAT_USE_64BIT_TIME); + + case SIOCETHTOOL: case SIOCBONDSLAVEINFOQUERY: case SIOCBONDINFOQUERY: case SIOCSHWTSTAMP: @@ -3189,15 +3448,22 @@ static int compat_sock_ioctl_trans(struct file *file, struct socket *sock, case SIOCGPGRP: case SIOCBRADDBR: case SIOCBRDELBR: + case SIOCBRADDIF: + case SIOCBRDELIF: 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: @@ -3223,17 +3489,20 @@ static int compat_sock_ioctl_trans(struct file *file, struct socket *sock, case SIOCGIFPFLAGS: case SIOCGIFTXQLEN: case SIOCSIFTXQLEN: - case SIOCBRADDIF: - case SIOCBRDELIF: + case SIOCGIFNAME: case SIOCSIFNAME: case SIOCGMIIPHY: case SIOCGMIIREG: case SIOCSMIIREG: - return dev_ifsioc(net, sock, cmd, argp); - + case SIOCBONDENSLAVE: + case SIOCBONDRELEASE: + case SIOCBONDSETHWADDR: + case SIOCBONDCHANGEACTIVE: case SIOCSARP: case SIOCGARP: case SIOCDARP: + case SIOCOUTQ: + case SIOCOUTQNSD: case SIOCATMARK: return sock_do_ioctl(net, sock, cmd, arg); } @@ -3245,6 +3514,7 @@ static long compat_sock_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { struct socket *sock = file->private_data; + const struct proto_ops *ops = READ_ONCE(sock->ops); int ret = -ENOIOCTLCMD; struct sock *sk; struct net *net; @@ -3252,8 +3522,8 @@ static long compat_sock_ioctl(struct file *file, unsigned int cmd, sk = sock->sk; net = sock_net(sk); - if (sock->ops->compat_ioctl) - ret = sock->ops->compat_ioctl(sock, cmd, arg); + if (ops->compat_ioctl) + ret = ops->compat_ioctl(sock, cmd, arg); if (ret == -ENOIOCTLCMD && (cmd >= SIOCIWFIRST && cmd <= SIOCIWLAST)) @@ -3266,21 +3536,59 @@ static long compat_sock_ioctl(struct file *file, unsigned int cmd, } #endif -int kernel_bind(struct socket *sock, struct sockaddr *addr, int addrlen) +/** + * kernel_bind - bind an address to a socket (kernel space) + * @sock: socket + * @addr: address + * @addrlen: length of address + * + * Returns 0 or an error. + */ + +int kernel_bind(struct socket *sock, struct sockaddr_unsized *addr, int addrlen) { - return sock->ops->bind(sock, addr, addrlen); + struct sockaddr_storage address; + + memcpy(&address, addr, addrlen); + + return READ_ONCE(sock->ops)->bind(sock, (struct sockaddr_unsized *)&address, + addrlen); } EXPORT_SYMBOL(kernel_bind); +/** + * kernel_listen - move socket to listening state (kernel space) + * @sock: socket + * @backlog: pending connections queue size + * + * Returns 0 or an error. + */ + int kernel_listen(struct socket *sock, int backlog) { - return sock->ops->listen(sock, backlog); + return READ_ONCE(sock->ops)->listen(sock, backlog); } EXPORT_SYMBOL(kernel_listen); +/** + * kernel_accept - accept a connection (kernel space) + * @sock: listening socket + * @newsock: new connected socket + * @flags: flags + * + * @flags must be SOCK_CLOEXEC, SOCK_NONBLOCK or 0. + * If it fails, @newsock is guaranteed to be %NULL. + * Returns 0 or an error. + */ + int kernel_accept(struct socket *sock, struct socket **newsock, int flags) { struct sock *sk = sock->sk; + const struct proto_ops *ops = READ_ONCE(sock->ops); + struct proto_accept_arg arg = { + .flags = flags, + .kern = true, + }; int err; err = sock_create_lite(sk->sk_family, sk->sk_type, sk->sk_protocol, @@ -3288,124 +3596,105 @@ int kernel_accept(struct socket *sock, struct socket **newsock, int flags) if (err < 0) goto done; - err = sock->ops->accept(sock, *newsock, flags, true); + err = ops->accept(sock, *newsock, &arg); if (err < 0) { sock_release(*newsock); *newsock = NULL; goto done; } - (*newsock)->ops = sock->ops; - __module_get((*newsock)->ops->owner); + (*newsock)->ops = ops; + __module_get(ops->owner); done: return err; } EXPORT_SYMBOL(kernel_accept); -int kernel_connect(struct socket *sock, struct sockaddr *addr, int addrlen, +/** + * kernel_connect - connect a socket (kernel space) + * @sock: socket + * @addr: address + * @addrlen: address length + * @flags: flags (O_NONBLOCK, ...) + * + * 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. + */ + +int kernel_connect(struct socket *sock, struct sockaddr_unsized *addr, int addrlen, int flags) { - return sock->ops->connect(sock, addr, addrlen, flags); -} -EXPORT_SYMBOL(kernel_connect); + struct sockaddr_storage address; -int kernel_getsockname(struct socket *sock, struct sockaddr *addr, - int *addrlen) -{ - return sock->ops->getname(sock, addr, addrlen, 0); -} -EXPORT_SYMBOL(kernel_getsockname); + memcpy(&address, addr, addrlen); -int kernel_getpeername(struct socket *sock, struct sockaddr *addr, - int *addrlen) -{ - return sock->ops->getname(sock, addr, addrlen, 1); + return READ_ONCE(sock->ops)->connect(sock, (struct sockaddr_unsized *)&address, + addrlen, flags); } -EXPORT_SYMBOL(kernel_getpeername); - -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; +EXPORT_SYMBOL(kernel_connect); - 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_getsockname - get the address which the socket is bound (kernel space) + * @sock: socket + * @addr: address holder + * + * Fills the @addr pointer with the address which the socket is bound. + * Returns the length of the address in bytes or an error code. + */ -int kernel_setsockopt(struct socket *sock, int level, int optname, - char *optval, unsigned int optlen) +int kernel_getsockname(struct socket *sock, struct sockaddr *addr) { - 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; + return READ_ONCE(sock->ops)->getname(sock, addr, 0); } -EXPORT_SYMBOL(kernel_setsockopt); - -int kernel_sendpage(struct socket *sock, struct page *page, int offset, - size_t size, int flags) -{ - if (sock->ops->sendpage) - return sock->ops->sendpage(sock, page, offset, size, flags); +EXPORT_SYMBOL(kernel_getsockname); - return sock_no_sendpage(sock, page, offset, size, flags); -} -EXPORT_SYMBOL(kernel_sendpage); +/** + * 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 the length of the address in bytes or an error code. + */ -int kernel_sock_ioctl(struct socket *sock, int cmd, unsigned long arg) +int kernel_getpeername(struct socket *sock, struct sockaddr *addr) { - mm_segment_t oldfs = get_fs(); - int err; - - set_fs(KERNEL_DS); - err = sock->ops->ioctl(sock, cmd, arg); - set_fs(oldfs); - - return err; + return READ_ONCE(sock->ops)->getname(sock, addr, 1); } -EXPORT_SYMBOL(kernel_sock_ioctl); +EXPORT_SYMBOL(kernel_getpeername); + +/** + * kernel_sock_shutdown - shut down part of a full-duplex connection (kernel space) + * @sock: socket + * @how: connection part + * + * Returns 0 or an error. + */ int kernel_sock_shutdown(struct socket *sock, enum sock_shutdown_cmd how) { - return sock->ops->shutdown(sock, how); + return READ_ONCE(sock->ops)->shutdown(sock, how); } EXPORT_SYMBOL(kernel_sock_shutdown); -/* This routine returns the IP overhead imposed by a socket i.e. - * the length of the underlying IP header, depending on whether - * this is an IPv4 or IPv6 socket and the length from IP options turned - * on at the socket. Assumes that the caller has a lock on the socket. +/** + * kernel_sock_ip_overhead - returns the IP overhead imposed by a socket + * @sk: socket + * + * This routine returns the IP overhead imposed by a socket i.e. + * the length of the underlying IP header, depending on whether + * this is an IPv4 or IPv6 socket and the length from IP options turned + * on at the socket. Assumes that the caller has a lock on the socket. */ + u32 kernel_sock_ip_overhead(struct sock *sk) { struct inet_sock *inet; struct ip_options_rcu *opt; u32 overhead = 0; - bool owned_by_user; #if IS_ENABLED(CONFIG_IPV6) struct ipv6_pinfo *np; struct ipv6_txoptions *optv6 = NULL; @@ -3414,13 +3703,12 @@ u32 kernel_sock_ip_overhead(struct sock *sk) if (!sk) return overhead; - owned_by_user = sock_owned_by_user(sk); switch (sk->sk_family) { case AF_INET: inet = inet_sk(sk); overhead += sizeof(struct iphdr); opt = rcu_dereference_protected(inet->inet_opt, - owned_by_user); + sock_owned_by_user(sk)); if (opt) overhead += opt->opt.optlen; return overhead; @@ -3430,7 +3718,7 @@ u32 kernel_sock_ip_overhead(struct sock *sk) overhead += sizeof(struct ipv6hdr); if (np) optv6 = rcu_dereference_protected(np->opt, - owned_by_user); + sock_owned_by_user(sk)); if (optv6) overhead += (optv6->opt_flen + optv6->opt_nflen); return overhead; |