// SPDX-License-Identifier: GPL-2.0-or-later
/*
 * NET          An implementation of the SOCKET network access protocol.
 *
 * Version:     @(#)socket.c    1.1.93  18/02/95
 *
 * Authors:     Orest Zborowski, <obz@Kodak.COM>
 *              Ross Biro
 *              Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
 *
 * Fixes:
 *              Anonymous       :       NOTSOCK/BADF cleanup. Error fix in
 *                                      shutdown()
 *              Alan Cox        :       verify_area() fixes
 *              Alan Cox        :       Removed DDI
 *              Jonathan Kamens :       SOCK_DGRAM reconnect bug
 *              Alan Cox        :       Moved a load of checks to the very
 *                                      top level.
 *              Alan Cox        :       Move address structures to/from user
 *                                      mode above the protocol layers.
 *              Rob Janssen     :       Allow 0 length sends.
 *              Alan Cox        :       Asynchronous I/O support (cribbed from the
 *                                      tty drivers).
 *              Niibe Yutaka    :       Asynchronous I/O for writes (4.4BSD style)
 *              Jeff Uphoff     :       Made max number of sockets command-line
 *                                      configurable.
 *              Matti Aarnio    :       Made the number of sockets dynamic,
 *                                      to be allocated when needed, and mr.
 *                                      Uphoff's max is used as max to be
 *                                      allowed to allocate.
 *              Linus           :       Argh. removed all the socket allocation
 *                                      altogether: it's in the inode now.
 *              Alan Cox        :       Made sock_alloc()/sock_release() public
 *                                      for NetROM and future kernel nfsd type
 *                                      stuff.
 *              Alan Cox        :       sendmsg/recvmsg basics.
 *              Tom Dyas        :       Export net symbols.
 *              Marcin Dalecki  :       Fixed problems with CONFIG_NET="n".
 *              Alan Cox        :       Added thread locking to sys_* calls
 *                                      for sockets. May have errors at the
 *                                      moment.
 *              Kevin Buhr      :       Fixed the dumb errors in the above.
 *              Andi Kleen      :       Some small cleanups, optimizations,
 *                                      and fixed a copy_from_user() bug.
 *              Tigran Aivazian :       sys_send(args) calls sys_sendto(args, NULL, 0)
 *              Tigran Aivazian :       Made listen(2) backlog sanity checks
 *                                      protocol-independent
 *
 *      This module is effectively the top level interface to the BSD socket
 *      paradigm.
 *
 *      Based upon Swansea University Computer Society NET3.039
 */

#include <linux/ethtool.h>
#include <linux/mm.h>
#include <linux/socket.h>
#include <linux/file.h>
#include <linux/net.h>
#include <linux/interrupt.h>
#include <linux/thread_info.h>
#include <linux/rcupdate.h>
#include <linux/netdevice.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <linux/mutex.h>
#include <linux/if_bridge.h>
#include <linux/if_vlan.h>
#include <linux/ptp_classify.h>
#include <linux/init.h>
#include <linux/poll.h>
#include <linux/cache.h>
#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>
#include <linux/kmod.h>
#include <linux/audit.h>
#include <linux/wireless.h>
#include <linux/nsproxy.h>
#include <linux/magic.h>
#include <linux/slab.h>
#include <linux/xattr.h>
#include <linux/nospec.h>
#include <linux/indirect_call_wrapper.h>

#include <linux/uaccess.h>
#include <asm/unistd.h>

#include <net/compat.h>
#include <net/wext.h>
#include <net/cls_cgroup.h>

#include <net/sock.h>
#include <linux/netfilter.h>

#include <linux/if_tun.h>
#include <linux/ipv6_route.h>
#include <linux/route.h>
#include <linux/termios.h>
#include <linux/sockios.h>
#include <net/busy_poll.h>
#include <linux/errqueue.h>
#include <linux/ptp_clock_kernel.h>

#ifdef CONFIG_NET_RX_BUSY_POLL
unsigned int sysctl_net_busy_read __read_mostly;
unsigned int sysctl_net_busy_poll __read_mostly;
#endif

static ssize_t sock_read_iter(struct kiocb *iocb, struct iov_iter *to);
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 __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
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);

#ifdef CONFIG_PROC_FS
static void sock_show_fdinfo(struct seq_file *m, struct file *f)
{
        struct socket *sock = f->private_data;

        if (sock->ops->show_fdinfo)
                sock->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
 *      in the operation structures but are done directly via the socketcall() multiplexor.
 */

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,
        .unlocked_ioctl = sock_ioctl,
#ifdef CONFIG_COMPAT
        .compat_ioctl = compat_sock_ioctl,
#endif
        .mmap =         sock_mmap,
        .release =      sock_close,
        .fasync =       sock_fasync,
        .sendpage =     sock_sendpage,
        .splice_write = generic_splice_sendpage,
        .splice_read =  sock_splice_read,
        .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",
};

/*
 *      The protocol list. Each protocol is registered in here.
 */

static DEFINE_SPINLOCK(net_family_lock);
static const struct net_proto_family __rcu *net_families[NPROTO] __read_mostly;

/*
 * Support routines.
 * Move socket addresses back and forth across the kernel/user
 * divide and look after the messy bits.
 */

/**
 *      move_addr_to_kernel     -       copy a socket address into kernel space
 *      @uaddr: Address in user space
 *      @kaddr: Address in kernel space
 *      @ulen: Length in user space
 *
 *      The address is copied into kernel space. If the provided address is
 *      too long an error code of -EINVAL is returned. If the copy gives
 *      invalid addresses -EFAULT is returned. On a success 0 is returned.
 */

int move_addr_to_kernel(void __user *uaddr, int ulen, struct sockaddr_storage *kaddr)
{
        if (ulen < 0 || ulen > sizeof(struct sockaddr_storage))
                return -EINVAL;
        if (ulen == 0)
                return 0;
        if (copy_from_user(kaddr, uaddr, ulen))
                return -EFAULT;
        return audit_sockaddr(ulen, kaddr);
}

/**
 *      move_addr_to_user       -       copy an address to user space
 *      @kaddr: kernel space address
 *      @klen: length of address in kernel
 *      @uaddr: user space address
 *      @ulen: pointer to user length field
 *
 *      The value pointed to by ulen on entry is the buffer length available.
 *      This is overwritten with the buffer space used. -EINVAL is returned
 *      if an overlong buffer is specified or a negative buffer size. -EFAULT
 *      is returned if either the buffer or the length field are not
 *      accessible.
 *      After copying the data up to the limit the user specifies, the true
 *      length of the data is written over the length limit the user
 *      specified. Zero is returned for a success.
 */

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 (len > klen)
                len = klen;
        if (len < 0)
                return -EINVAL;
        if (len) {
                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);
}

static struct kmem_cache *sock_inode_cachep __ro_after_init;

static struct inode *sock_alloc_inode(struct super_block *sb)
{
        struct socket_alloc *ei;

        ei = kmem_cache_alloc(sock_inode_cachep, GFP_KERNEL);
        if (!ei)
                return NULL;
        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;
        ei->socket.ops = NULL;
        ei->socket.sk = NULL;
        ei->socket.file = NULL;

        return &ei->vfs_inode;
}

static void sock_free_inode(struct inode *inode)
{
        struct socket_alloc *ei;

        ei = container_of(inode, struct socket_alloc, vfs_inode);
        kmem_cache_free(sock_inode_cachep, ei);
}

static void init_once(void *foo)
{
        struct socket_alloc *ei = (struct socket_alloc *)foo;

        inode_init_once(&ei->vfs_inode);
}

static void init_inodecache(void)
{
        sock_inode_cachep = kmem_cache_create("sock_inode_cache",
                                              sizeof(struct socket_alloc),
                                              0,
                                              (SLAB_HWCACHE_ALIGN |
                                               SLAB_RECLAIM_ACCOUNT |
                                               SLAB_MEM_SPREAD | SLAB_ACCOUNT),
                                              init_once);
        BUG_ON(sock_inode_cachep == NULL);
}

static const struct super_operations sockfs_ops = {
        .alloc_inode    = sock_alloc_inode,
        .free_inode     = sock_free_inode,
        .statfs         = simple_statfs,
};

/*
 * sockfs_dname() is called from d_path().
 */
static char *sockfs_dname(struct dentry *dentry, char *buffer, int buflen)
{
        return dynamic_dname(dentry, buffer, buflen, "socket:[%lu]",
                                d_inode(dentry)->i_ino);
}

static const struct dentry_operations sockfs_dentry_operations = {
        .d_dname  = sockfs_dname,
};

static int sockfs_xattr_get(const struct xattr_handler *handler,
                            struct dentry *dentry, struct inode *inode,
                            const char *suffix, void *value, size_t size)
{
        if (value) {
                if (dentry->d_name.len + 1 > size)
                        return -ERANGE;
                memcpy(value, dentry->d_name.name, dentry->d_name.len + 1);
        }
        return dentry->d_name.len + 1;
}

#define XATTR_SOCKPROTONAME_SUFFIX "sockprotoname"
#define XATTR_NAME_SOCKPROTONAME (XATTR_SYSTEM_PREFIX XATTR_SOCKPROTONAME_SUFFIX)
#define XATTR_NAME_SOCKPROTONAME_LEN (sizeof(XATTR_NAME_SOCKPROTONAME)-1)

static const struct xattr_handler sockfs_xattr_handler = {
        .name = XATTR_NAME_SOCKPROTONAME,
        .get = sockfs_xattr_get,
};

static int sockfs_security_xattr_set(const struct xattr_handler *handler,
                                     struct user_namespace *mnt_userns,
                                     struct dentry *dentry, struct inode *inode,
                                     const char *suffix, const void *value,
                                     size_t size, int flags)
{
        /* Handled by LSM. */
        return -EAGAIN;
}

static const struct xattr_handler sockfs_security_xattr_handler = {
        .prefix = XATTR_SECURITY_PREFIX,
        .set = sockfs_security_xattr_set,
};

static const struct xattr_handler *sockfs_xattr_handlers[] = {
        &sockfs_xattr_handler,
        &sockfs_security_xattr_handler,
        NULL
};

static int sockfs_init_fs_context(struct fs_context *fc)
{
        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",
        .init_fs_context = sockfs_init_fs_context,
        .kill_sb =      kill_anon_super,
};

/*
 *      Obtains the first available file descriptor and sets it up for use.
 *
 *      These functions create file structures and maps them to fd space
 *      of the current process. On success it returns file descriptor
 *      and file struct implicitly stored in sock->file.
 *      Note that another thread may close file descriptor before we return
 *      from this function. We use the fact that now we do not refer
 *      to socket after mapping. If one day we will need it, this
 *      function will increment ref. count on file by 1.
 *
 *      In any case returned fd MAY BE not valid!
 *      This race condition is unavoidable
 *      with shared fd spaces, we cannot solve it inside kernel,
 *      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 the return is a ERR pointer (see linux/err.h).
 *      This function uses GFP_KERNEL internally.
 */

struct file *sock_alloc_file(struct socket *sock, int flags, const char *dname)
{
        struct file *file;

        if (!dname)
                dname = sock->sk ? sock->sk->sk_prot_creator->name : "";

        file = alloc_file_pseudo(SOCK_INODE(sock), sock_mnt, dname,
                                O_RDWR | (flags & O_NONBLOCK),
                                &socket_file_ops);
        if (IS_ERR(file)) {
                sock_release(sock);
                return file;
        }

        sock->file = file;
        file->private_data = sock;
        stream_open(SOCK_INODE(sock), file);
        return file;
}
EXPORT_SYMBOL(sock_alloc_file);

static int sock_map_fd(struct socket *sock, int flags)
{
        struct file *newfile;
        int fd = get_unused_fd_flags(flags);
        if (unlikely(fd < 0)) {
                sock_release(sock);
                return fd;
        }

        newfile = sock_alloc_file(sock, flags, NULL);
        if (!IS_ERR(newfile)) {
                fd_install(fd, newfile);
                return fd;
        }

        put_unused_fd(fd);
        return PTR_ERR(newfile);
}

/**
 *      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 */

        return NULL;
}
EXPORT_SYMBOL(sock_from_file);

/**
 *      sockfd_lookup - Go from a file number to its socket slot
 *      @fd: file handle
 *      @err: pointer to an error code return
 *
 *      The file handle passed in is locked and the socket it is bound
 *      to is returned. If an error occurs the err pointer is overwritten
 *      with a negative errno code and NULL is returned. The function checks
 *      for both invalid handles and passing a handle which is not a socket.
 *
 *      On a success the socket object pointer is returned.
 */

struct socket *sockfd_lookup(int fd, int *err)
{
        struct file *file;
        struct socket *sock;

        file = fget(fd);
        if (!file) {
                *err = -EBADF;
                return NULL;
        }

        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);
                if (likely(sock)) {
                        *fput_needed = f.flags & FDPUT_FPUT;
                        return sock;
                }
                *err = -ENOTSOCK;
                fdput(f);
        }
        return NULL;
}

static ssize_t sockfs_listxattr(struct dentry *dentry, char *buffer,
                                size_t size)
{
        ssize_t len;
        ssize_t used = 0;

        len = security_inode_listsecurity(d_inode(dentry), buffer, size);
        if (len < 0)
                return len;
        used += len;
        if (buffer) {
                if (size < used)
                        return -ERANGE;
                buffer += len;
        }

        len = (XATTR_NAME_SOCKPROTONAME_LEN + 1);
        used += len;
        if (buffer) {
                if (size < used)
                        return -ERANGE;
                memcpy(buffer, XATTR_NAME_SOCKPROTONAME, len);
                buffer += len;
        }

        return used;
}

static int sockfs_setattr(struct user_namespace *mnt_userns,
                          struct dentry *dentry, struct iattr *iattr)
{
        int err = simple_setattr(&init_user_ns, dentry, iattr);

        if (!err && (iattr->ia_valid & ATTR_UID)) {
                struct socket *sock = SOCKET_I(d_inode(dentry));

                if (sock->sk)
                        sock->sk->sk_uid = iattr->ia_uid;
                else
                        err = -ENOENT;
        }

        return err;
}

static const struct inode_operations sockfs_inode_ops = {
        .listxattr = sockfs_listxattr,
        .setattr = sockfs_setattr,
};

/**
 *      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. This functions uses GFP_KERNEL internally.
 */

struct socket *sock_alloc(void)
{
        struct inode *inode;
        struct socket *sock;

        inode = new_inode_pseudo(sock_mnt->mnt_sb);
        if (!inode)
                return NULL;

        sock = SOCKET_I(inode);

        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;

        return sock;
}
EXPORT_SYMBOL(sock_alloc);

static void __sock_release(struct socket *sock, struct inode *inode)
{
        if (sock->ops) {
                struct module *owner = sock->ops->owner;

                if (inode)
                        inode_lock(inode);
                sock->ops->release(sock);
                sock->sk = NULL;
                if (inode)
                        inode_unlock(inode);
                sock->ops = NULL;
                module_put(owner);
        }

        if (sock->wq.fasync_list)
                pr_err("%s: fasync list not empty!\n", __func__);

        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)
{
        u8 flags = *tx_flags;

        if (tsflags & SOF_TIMESTAMPING_TX_HARDWARE)
                flags |= SKBTX_HW_TSTAMP;

        if (tsflags & SOF_TIMESTAMPING_TX_SOFTWARE)
                flags |= SKBTX_SW_TSTAMP;

        if (tsflags & SOF_TIMESTAMPING_TX_SCHED)
                flags |= SKBTX_SCHED_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 inline int sock_sendmsg_nosec(struct socket *sock, struct msghdr *msg)
{
        int ret = INDIRECT_CALL_INET(sock->ops->sendmsg, inet6_sendmsg,
                                     inet_sendmsg, sock, msg,
                                     msg_data_left(msg));
        BUG_ON(ret == -EIOCBQUEUED);
        return ret;
}

/**
 *      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)
{
        int err = security_socket_sendmsg(sock, msg,
                                          msg_data_left(msg));

        return err ?: sock_sendmsg_nosec(sock, msg);
}
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, vec, num, size);
        return sock_sendmsg(sock, msg);
}
EXPORT_SYMBOL(kernel_sendmsg);

/**
 *      kernel_sendmsg_locked - send a message through @sock (kernel-space)
 *      @sk: sock
 *      @msg: message header
 *      @vec: output s/g array
 *      @num: output s/g 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.
 *      Caller must hold @sk.
 */

int kernel_sendmsg_locked(struct sock *sk, struct msghdr *msg,
                          struct kvec *vec, size_t num, size_t size)
{
        struct socket *sock = sk->sk_socket;

        if (!sock->ops->sendmsg_locked)
                return sock_no_sendmsg_locked(sk, msg, size);

        iov_iter_kvec(&msg->msg_iter, WRITE, vec, num, size);

        return sock->ops->sendmsg_locked(sk, msg, msg_data_left(msg));
}
EXPORT_SYMBOL(kernel_sendmsg_locked);

static bool skb_is_err_queue(const struct sk_buff *skb)
{
        /* pkt_type of skbs enqueued on the error queue are set to
         * PACKET_OUTGOING in skb_set_err_queue(). This is only safe to do
         * in recvmsg, since skbs received on a local socket will never
         * have a pkt_type of PACKET_OUTGOING.
         */
        return skb->pkt_type == PACKET_OUTGOING;
}

/* On transmit, software and hardware timestamps are returned independently.
 * As the two skb clones share the hardware timestamp, which may be updated
 * 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_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)
{
        return skb->tstamp && !false_tstamp && skb_is_err_queue(skb);
}

static void put_ts_pktinfo(struct msghdr *msg, struct sk_buff *skb)
{
        struct scm_ts_pktinfo ts_pktinfo;
        struct net_device *orig_dev;

        if (!skb_mac_header_was_set(skb))
                return;

        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();

        ts_pktinfo.pkt_length = skb->len - skb_mac_offset(skb);
        put_cmsg(msg, SOL_SOCKET, SCM_TIMESTAMPING_PKTINFO,
                 sizeof(ts_pktinfo), &ts_pktinfo);
}

/*
 * called from sock_recv_timestamp() if sock_flag(sk, SOCK_RCVTSTAMP)
 */
void __sock_recv_timestamp(struct msghdr *msg, struct sock *sk,
        struct sk_buff *skb)
{
        int need_software_tstamp = sock_flag(sk, SOCK_RCVTSTAMP);
        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);

        /* Race occurred between timestamp enabling and packet
           receiving.  Fill in the current time for now. */
        if (need_software_tstamp && skb->tstamp == 0) {
                __net_timestamp(skb);
                false_tstamp = 1;
        }

        if (need_software_tstamp) {
                if (!sock_flag(sk, SOCK_RCVTSTAMPNS)) {
                        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 {
                        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_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)) {
                if (sk->sk_tsflags & SOF_TIMESTAMPING_BIND_PHC)
                        ptp_convert_timestamp(shhwtstamps, sk->sk_bind_phc);

                if (ktime_to_timespec64_cond(shhwtstamps->hwtstamp,
                                             tss.ts + 2)) {
                        empty = 0;

                        if ((sk->sk_tsflags & SOF_TIMESTAMPING_OPT_PKTINFO) &&
                            !skb_is_err_queue(skb))
                                put_ts_pktinfo(msg, skb);
                }
        }
        if (!empty) {
                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)
                        put_cmsg(msg, SOL_SOCKET, SCM_TIMESTAMPING_OPT_STATS,
                                 skb->len, skb->data);
        }
}
EXPORT_SYMBOL_GPL(__sock_recv_timestamp);

void __sock_recv_wifi_status(struct msghdr *msg, struct sock *sk,
        struct sk_buff *skb)
{
        int ack;

        if (!sock_flag(sk, SOCK_WIFI_STATUS))
                return;
        if (!skb->wifi_acked_valid)
                return;

        ack = skb->wifi_acked;

        put_cmsg(msg, SOL_SOCKET, SCM_WIFI_STATUS, sizeof(ack), &ack);
}
EXPORT_SYMBOL_GPL(__sock_recv_wifi_status);

static inline void sock_recv_drops(struct msghdr *msg, struct sock *sk,
                                   struct sk_buff *skb)
{
        if (sock_flag(sk, SOCK_RXQ_OVFL) && skb && SOCK_SKB_CB(skb)->dropcount)
                put_cmsg(msg, SOL_SOCKET, SO_RXQ_OVFL,
                        sizeof(__u32), &SOCK_SKB_CB(skb)->dropcount);
}

void __sock_recv_ts_and_drops(struct msghdr *msg, struct sock *sk,
        struct sk_buff *skb)
{
        sock_recv_timestamp(msg, sk, skb);
        sock_recv_drops(msg, sk, skb);
}
EXPORT_SYMBOL_GPL(__sock_recv_ts_and_drops);

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 inline int sock_recvmsg_nosec(struct socket *sock, struct msghdr *msg,
                                     int flags)
{
        return INDIRECT_CALL_INET(sock->ops->recvmsg, inet6_recvmsg,
                                  inet_recvmsg, sock, msg, msg_data_left(msg),
                                  flags);
}

/**
 *      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);

        return err ?: sock_recvmsg_nosec(sock, msg, 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...)
 *
 *      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.
 */

int kernel_recvmsg(struct socket *sock, struct msghdr *msg,
                   struct kvec *vec, size_t num, size_t size, int flags)
{
        msg->msg_control_is_user = false;
        iov_iter_kvec(&msg->msg_iter, READ, 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)
{
        struct socket *sock;
        int flags;

        sock = file->private_data;

        flags = (file->f_flags & O_NONBLOCK) ? MSG_DONTWAIT : 0;
        /* more is a combination of MSG_MORE and MSG_SENDPAGE_NOTLAST */
        flags |= more;

        return kernel_sendpage(sock, page, offset, size, flags);
}

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 = file->private_data;

        if (unlikely(!sock->ops->splice_read))
                return generic_file_splice_read(file, ppos, pipe, len, flags);

        return sock->ops->splice_read(sock, ppos, pipe, len, flags);
}

static ssize_t sock_read_iter(struct kiocb *iocb, struct iov_iter *to)
{
        struct file *file = iocb->ki_filp;
        struct socket *sock = file->private_data;
        struct msghdr msg = {.msg_iter = *to,
                             .msg_iocb = iocb};
        ssize_t res;

        if (file->f_flags & O_NONBLOCK || (iocb->ki_flags & IOCB_NOWAIT))
                msg.msg_flags = MSG_DONTWAIT;

        if (iocb->ki_pos != 0)
                return -ESPIPE;

        if (!iov_iter_count(to))        /* Match SYS5 behaviour */
                return 0;

        res = sock_recvmsg(sock, &msg, msg.msg_flags);
        *to = msg.msg_iter;
        return res;
}

static ssize_t sock_write_iter(struct kiocb *iocb, struct iov_iter *from)
{
        struct file *file = iocb->ki_filp;
        struct socket *sock = file->private_data;
        struct msghdr msg = {.msg_iter = *from,
                             .msg_iocb = iocb};
        ssize_t res;

        if (iocb->ki_pos != 0)
                return -ESPIPE;

        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);
        *from = msg.msg_iter;
        return res;
}

/*
 * Atomic setting of ioctl hooks to avoid race
 * with module unload.
 */

static DEFINE_MUTEX(br_ioctl_mutex);
static int (*br_ioctl_hook) (struct net *, unsigned int cmd, void __user *arg);

void brioctl_set(int (*hook) (struct net *, unsigned int, void __user *))
{
        mutex_lock(&br_ioctl_mutex);
        br_ioctl_hook = hook;
        mutex_unlock(&br_ioctl_mutex);
}
EXPORT_SYMBOL(brioctl_set);

static DEFINE_MUTEX(vlan_ioctl_mutex);
static int (*vlan_ioctl_hook) (struct net *, void __user *arg);

void vlan_ioctl_set(int (*hook) (struct net *, void __user *))
{
        mutex_lock(&vlan_ioctl_mutex);
        vlan_ioctl_hook = hook;
        mutex_unlock(&vlan_ioctl_mutex);
}
EXPORT_SYMBOL(vlan_ioctl_set);

static long sock_do_ioctl(struct net *net, struct socket *sock,
                          unsigned int cmd, unsigned long arg)
{
        int err;
        void __user *argp = (void __user *)arg;

        err = sock->ops->ioctl(sock, cmd, arg);

        /*
         * If this ioctl is unknown try to hand it down
         * to the NIC driver.
         */
        if (err != -ENOIOCTLCMD)
                return err;

        if (cmd == SIOCGIFCONF) {
                struct ifconf ifc;
                if (copy_from_user(&ifc, argp, sizeof(struct ifconf)))
                        return -EFAULT;
                rtnl_lock();
                err = dev_ifconf(net, &ifc, sizeof(struct ifreq));
                rtnl_unlock();
                if (!err && copy_to_user(argp, &ifc, sizeof(struct ifconf)))
                        err = -EFAULT;
        } else {
                struct ifreq ifr;
                bool need_copyout;
                if (copy_from_user(&ifr, argp, sizeof(struct ifreq)))
                        return -EFAULT;
                err = dev_ioctl(net, cmd, &ifr, &need_copyout);
                if (!err && need_copyout)
                        if (copy_to_user(argp, &ifr, sizeof(struct ifreq)))
                                return -EFAULT;
        }
        return err;
}

/*
 *      With an ioctl, arg may well be a user mode pointer, but we don't know
 *      what to do with it - that's up to the protocol still.
 */

static long sock_ioctl(struct file *file, unsigned cmd, unsigned long arg)
{
        struct socket *sock;
        struct sock *sk;
        void __user *argp = (void __user *)arg;
        int pid, err;
        struct net *net;

        sock = file->private_data;
        sk = sock->sk;
        net = sock_net(sk);
        if (unlikely(cmd >= SIOCDEVPRIVATE && cmd <= (SIOCDEVPRIVATE + 15))) {
                struct ifreq ifr;
                bool need_copyout;
                if (copy_from_user(&ifr, argp, sizeof(struct ifreq)))
                        return -EFAULT;
                err = dev_ioctl(net, cmd, &ifr, &need_copyout);
                if (!err && need_copyout)
                        if (copy_to_user(argp, &ifr, sizeof(struct ifreq)))
                                return -EFAULT;
        } else
#ifdef CONFIG_WEXT_CORE
        if (cmd >= SIOCIWFIRST && cmd <= SIOCIWLAST) {
                err = wext_handle_ioctl(net, cmd, argp);
        } else
#endif
                switch (cmd) {
                case FIOSETOWN:
                case SIOCSPGRP:
                        err = -EFAULT;
                        if (get_user(pid, (int __user *)argp))
                                break;
                        err = f_setown(sock->file, pid, 1);
                        break;
                case FIOGETOWN:
                case SIOCGPGRP:
                        err = put_user(f_getown(sock->file),
                                       (int __user *)argp);
                        break;
                case SIOCGIFBR:
                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);
                        break;
                case SIOCGIFVLAN:
                case SIOCSIFVLAN:
                        err = -ENOPKG;
                        if (!vlan_ioctl_hook)
                                request_module("8021q");

                        mutex_lock(&vlan_ioctl_mutex);
                        if (vlan_ioctl_hook)
                                err = vlan_ioctl_hook(net, argp);
                        mutex_unlock(&vlan_ioctl_mutex);
                        break;
                case SIOCGSKNS:
                        err = -EPERM;
                        if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
                                break;

                        err = open_related_ns(&net->ns, get_net_ns);
                        break;
                case SIOCGSTAMP_OLD:
                case SIOCGSTAMPNS_OLD:
                        if (!sock->ops->gettstamp) {
                                err = -ENOIOCTLCMD;
                                break;
                        }
                        err = sock->ops->gettstamp(sock, argp,
                                                   cmd == SIOCGSTAMP_OLD,
                                                   !IS_ENABLED(CONFIG_64BIT));
                        break;
                case SIOCGSTAMP_NEW:
                case SIOCGSTAMPNS_NEW:
                        if (!sock->ops->gettstamp) {
                                err = -ENOIOCTLCMD;
                                break;
                        }
                        err = sock->ops->gettstamp(sock, argp,
                                                   cmd == SIOCGSTAMP_NEW,
                                                   false);
                        break;
                default:
                        err = sock_do_ioctl(net, sock, cmd, arg);
                        break;
                }
        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;
        struct socket *sock = NULL;

        err = security_socket_create(family, type, protocol, 1);
        if (err)
                goto out;

        sock = sock_alloc();
        if (!sock) {
                err = -ENOMEM;
                goto out;
        }

        sock->type = type;
        err = security_socket_post_create(sock, family, type, protocol, 1);
        if (err)
                goto out_release;

out:
        *res = sock;
        return err;
out_release:
        sock_release(sock);
        sock = NULL;
        goto out;
}
EXPORT_SYMBOL(sock_create_lite);

/* No kernel lock held - perfect */
static __poll_t sock_poll(struct file *file, poll_table *wait)
{
        struct socket *sock = file->private_data;
        __poll_t events = poll_requested_events(wait), flag = 0;

        if (!sock->ops->poll)
                return 0;

        if (sk_can_busy_loop(sock->sk)) {
                /* 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 sock->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);
}

static int sock_close(struct inode *inode, struct file *filp)
{
        __sock_release(SOCKET_I(inode), inode);
        return 0;
}

/*
 *      Update the socket async list
 *
 *      Fasync_list locking strategy.
 *
 *      1. fasync_list is modified only under process context socket lock
 *         i.e. under semaphore.
 *      2. fasync_list is used under read_lock(&sk->sk_callback_lock)
 *         or under socket lock
 */

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 = &sock->wq;

        if (sk == NULL)
                return -EINVAL;

        lock_sock(sk);
        fasync_helper(fd, filp, on, &wq->fasync_list);

        if (!wq->fasync_list)
                sock_reset_flag(sk, SOCK_FASYNC);
        else
                sock_set_flag(sk, SOCK_FASYNC);

        release_sock(sk);
        return 0;
}

/* This function may be called only under rcu_lock */

int sock_wake_async(struct socket_wq *wq, int how, int band)
{
        if (!wq || !wq->fasync_list)
                return -1;

        switch (how) {
        case SOCK_WAKE_WAITD:
                if (test_bit(SOCKWQ_ASYNC_WAITDATA, &wq->flags))
                        break;
                goto call_kill;
        case SOCK_WAKE_SPACE:
                if (!test_and_clear_bit(SOCKWQ_ASYNC_NOSPACE, &wq->flags))
                        break;
                fallthrough;
        case SOCK_WAKE_IO:
call_kill:
                kill_fasync(&wq->fasync_list, SIGIO, band);
                break;
        case SOCK_WAKE_URG:
                kill_fasync(&wq->fasync_list, SIGURG, band);
        }

        return 0;
}
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)
{
        int err;
        struct socket *sock;
        const struct net_proto_family *pf;

        /*
         *      Check protocol is in range
         */
        if (family < 0 || family >= NPROTO)
                return -EAFNOSUPPORT;
        if (type < 0 || type >= SOCK_MAX)
                return -EINVAL;

        /* Compatibility.

           This uglymoron is moved from INET layer to here to avoid
           deadlock in module load.
         */
        if (family == PF_INET && type == SOCK_PACKET) {
                pr_info_once("%s uses obsolete (PF_INET,SOCK_PACKET)\n",
                             current->comm);
                family = PF_PACKET;
        }

        err = security_socket_create(family, type, protocol, kern);
        if (err)
                return err;

        /*
         *      Allocate the socket and allow the family to set things up. if
         *      the protocol is 0, the family is instructed to select an appropriate
         *      default.
         */
        sock = sock_alloc();
        if (!sock) {
                net_warn_ratelimited("socket: no more sockets\n");
                return -ENFILE; /* Not exactly a match, but its the
                                   closest posix thing */
        }

        sock->type = type;

#ifdef CONFIG_MODULES
        /* Attempt to load a protocol module if the find failed.
         *
         * 12/09/1996 Marcin: But! this makes REALLY only sense, if the user
         * requested real, full-featured networking support upon configuration.
         * Otherwise module support will break!
         */
        if (rcu_access_pointer(net_families[family]) == NULL)
                request_module("net-pf-%d", family);
#endif

        rcu_read_lock();
        pf = rcu_dereference(net_families[family]);
        err = -EAFNOSUPPORT;
        if (!pf)
                goto out_release;

        /*
         * We will call the ->create function, that possibly is in a loadable
         * module, so we have to bump that loadable module refcnt first.
         */
        if (!try_module_get(pf->owner))
                goto out_release;

        /* Now protected by module ref count */
        rcu_read_unlock();

        err = pf->create(net, sock, protocol, kern);
        if (err < 0)
                goto out_module_put;

        /*
         * Now to bump the refcnt of the [loadable] module that owns this
         * socket at sock_release time we decrement its refcnt.
         */
        if (!try_module_get(sock->ops->owner))
                goto out_module_busy;

        /*
         * Now that we're done with the ->create function, the [loadable]
         * module can have its refcnt decremented
         */
        module_put(pf->owner);
        err = security_socket_post_create(sock, family, type, protocol, kern);
        if (err)
                goto out_sock_release;
        *res = sock;

        return 0;

out_module_busy:
        err = -EAFNOSUPPORT;
out_module_put:
        sock->ops = NULL;
        module_put(pf->owner);
out_sock_release:
        sock_release(sock);
        return err;

out_release:
        rcu_read_unlock();
        goto out_sock_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);

int __sys_socket(int family, int type, int protocol)
{
        int retval;
        struct socket *sock;
        int flags;

        /* Check the SOCK_* constants for consistency.  */
        BUILD_BUG_ON(SOCK_CLOEXEC != O_CLOEXEC);
        BUILD_BUG_ON((SOCK_MAX | SOCK_TYPE_MASK) != SOCK_TYPE_MASK);
        BUILD_BUG_ON(SOCK_CLOEXEC & SOCK_TYPE_MASK);
        BUILD_BUG_ON(SOCK_NONBLOCK & SOCK_TYPE_MASK);

        flags = type & ~SOCK_TYPE_MASK;
        if (flags & ~(SOCK_CLOEXEC | SOCK_NONBLOCK))
                return -EINVAL;
        type &= SOCK_TYPE_MASK;

        if (SOCK_NONBLOCK != O_NONBLOCK && (flags & SOCK_NONBLOCK))
                flags = (flags & ~SOCK_NONBLOCK) | O_NONBLOCK;

        retval = sock_create(family, type, protocol, &sock);
        if (retval < 0)
                return retval;

        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.
 */

int __sys_socketpair(int family, int type, int protocol, int __user *usockvec)
{
        struct socket *sock1, *sock2;
        int fd1, fd2, err;
        struct file *newfile1, *newfile2;
        int flags;

        flags = type & ~SOCK_TYPE_MASK;
        if (flags & ~(SOCK_CLOEXEC | SOCK_NONBLOCK))
                return -EINVAL;
        type &= SOCK_TYPE_MASK;

        if (SOCK_NONBLOCK != O_NONBLOCK && (flags & SOCK_NONBLOCK))
                flags = (flags & ~SOCK_NONBLOCK) | O_NONBLOCK;

        /*
         * 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 (unlikely(err < 0))
                goto out;

        err = sock_create(family, type, protocol, &sock2);
        if (unlikely(err < 0)) {
                sock_release(sock1);
                goto out;
        }

        err = security_socket_socketpair(sock1, sock2);
        if (unlikely(err)) {
                sock_release(sock2);
                sock_release(sock1);
                goto out;
        }

        err = 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);
                sock_release(sock2);
                goto out;
        }

        newfile2 = sock_alloc_file(sock2, flags, NULL);
        if (IS_ERR(newfile2)) {
                err = PTR_ERR(newfile2);
                fput(newfile1);
                goto out;
        }

        audit_fd_pair(fd1, fd2);

        fd_install(fd1, newfile1);
        fd_install(fd2, newfile2);
        return 0;

out:
        put_unused_fd(fd2);
        put_unused_fd(fd1);
        return err;
}

SYSCALL_DEFINE4(socketpair, int, family, int, type, int, protocol,
                int __user *, usockvec)
{
        return __sys_socketpair(family, type, protocol, usockvec);
}

/*
 *      Bind a name to a socket. Nothing much to do here since it's
 *      the protocol's responsibility to handle the local address.
 *
 *      We move the socket address to kernel space before we call
 *      the protocol layer (having also checked the address is ok).
 */

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) {
                        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;
}

SYSCALL_DEFINE3(bind, int, fd, struct sockaddr __user *, umyaddr, int, addrlen)
{
        return __sys_bind(fd, umyaddr, addrlen);
}

/*
 *      Perform a listen. Basically, we allow the protocol to do anything
 *      necessary for a listen, and if that works, we mark the socket as
 *      ready for listening.
 */

int __sys_listen(int fd, int backlog)
{
        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;

                err = security_socket_listen(sock, backlog);
                if (!err)
                        err = sock->ops->listen(sock, backlog);

                fput_light(sock->file, fput_needed);
        }
        return err;
}

SYSCALL_DEFINE2(listen, int, fd, int, backlog)
{
        return __sys_listen(fd, backlog);
}

int __sys_accept4_file(struct file *file, unsigned file_flags,
                       struct sockaddr __user *upeer_sockaddr,
                       int __user *upeer_addrlen, int flags,
                       unsigned long nofile)
{
        struct socket *sock, *newsock;
        struct file *newfile;
        int err, len, newfd;
        struct sockaddr_storage address;

        if (flags & ~(SOCK_CLOEXEC | SOCK_NONBLOCK))
                return -EINVAL;

        if (SOCK_NONBLOCK != O_NONBLOCK && (flags & SOCK_NONBLOCK))
                flags = (flags & ~SOCK_NONBLOCK) | O_NONBLOCK;

        sock = sock_from_file(file);
        if (!sock) {
                err = -ENOTSOCK;
                goto out;
        }

        err = -ENFILE;
        newsock = sock_alloc();
        if (!newsock)
                goto out;

        newsock->type = sock->type;
        newsock->ops = sock->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);

        newfd = __get_unused_fd_flags(flags, nofile);
        if (unlikely(newfd < 0)) {
                err = newfd;
                sock_release(newsock);
                goto out;
        }
        newfile = sock_alloc_file(newsock, flags, sock->sk->sk_prot_creator->name);
        if (IS_ERR(newfile)) {
                err = PTR_ERR(newfile);
                put_unused_fd(newfd);
                goto out;
        }

        err = security_socket_accept(sock, newsock);
        if (err)
                goto out_fd;

        err = sock->ops->accept(sock, newsock, sock->file->f_flags | file_flags,
                                        false);
        if (err < 0)
                goto out_fd;

        if (upeer_sockaddr) {
                len = newsock->ops->getname(newsock,
                                        (struct sockaddr *)&address, 2);
                if (len < 0) {
                        err = -ECONNABORTED;
                        goto out_fd;
                }
                err = move_addr_to_user(&address,
                                        len, upeer_sockaddr, upeer_addrlen);
                if (err < 0)
                        goto out_fd;
        }

        /* File flags are not inherited via accept() unlike another OSes. */

        fd_install(newfd, newfile);
        err = newfd;
out:
        return err;
out_fd:
        fput(newfile);
        put_unused_fd(newfd);
        goto out;

}

/*
 *      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)
{
        int ret = -EBADF;
        struct fd f;

        f = fdget(fd);
        if (f.file) {
                ret = __sys_accept4_file(f.file, 0, upeer_sockaddr,
                                                upeer_addrlen, flags,
                                                rlimit(RLIMIT_NOFILE));
                fdput(f);
        }

        return ret;
}

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);
}

/*
 *      Attempt to connect to a socket with the server address.  The address
 *      is in user space so we verify it is OK and move it to kernel space.
 *
 *      For 1003.1g we need to add clean support for a bind to AF_UNSPEC to
 *      break bindings
 *
 *      NOTE: 1003.1g draft 6.3 is broken with respect to AX.25/NetROM and
 *      other SEQPACKET protocols that take time to connect() as it doesn't
 *      include the -EINPROGRESS status for such sockets.
 */

int __sys_connect_file(struct file *file, struct sockaddr_storage *address,
                       int addrlen, int file_flags)
{
        struct socket *sock;
        int err;

        sock = sock_from_file(file);
        if (!sock) {
                err = -ENOTSOCK;
                goto out;
        }

        err =
            security_socket_connect(sock, (struct sockaddr *)address, addrlen);
        if (err)
                goto out;

        err = sock->ops->connect(sock, (struct sockaddr *)address, addrlen,
                                 sock->file->f_flags | file_flags);
out:
        return err;
}

int __sys_connect(int fd, struct sockaddr __user *uservaddr, int addrlen)
{
        int ret = -EBADF;
        struct fd f;

        f = fdget(fd);
        if (f.file) {
                struct sockaddr_storage address;

                ret = move_addr_to_kernel(uservaddr, addrlen, &address);
                if (!ret)
                        ret = __sys_connect_file(f.file, &address, addrlen, 0);
                fdput(f);
        }

        return ret;
}

SYSCALL_DEFINE3(connect, int, fd, struct sockaddr __user *, uservaddr,
                int, addrlen)
{
        return __sys_connect(fd, uservaddr, addrlen);
}

/*
 *      Get the local address ('name') of a socket object. Move the obtained
 *      name to user space.
 */

int __sys_getsockname(int fd, struct sockaddr __user *usockaddr,
                      int __user *usockaddr_len)
{
        struct socket *sock;
        struct sockaddr_storage address;
        int err, fput_needed;

        sock = sockfd_lookup_light(fd, &err, &fput_needed);
        if (!sock)
                goto out;

        err = security_socket_getsockname(sock);
        if (err)
                goto out_put;

        err = sock->ops->getname(sock, (struct sockaddr *)&address, 0);
        if (err < 0)
                goto out_put;
        /* "err" is actually length in this case */
        err = move_addr_to_user(&address, err, usockaddr, usockaddr_len);

out_put:
        fput_light(sock->file, fput_needed);
out:
        return err;
}

SYSCALL_DEFINE3(getsockname, int, fd, struct sockaddr __user *, usockaddr,
                int __user *, usockaddr_len)
{
        return __sys_getsockname(fd, usockaddr, usockaddr_len);
}

/*
 *      Get the remote address ('name') of a socket object. Move the obtained
 *      name to user space.
 */

int __sys_getpeername(int fd, struct sockaddr __user *usockaddr,
                      int __user *usockaddr_len)
{
        struct socket *sock;
        struct sockaddr_storage address;
        int err, fput_needed;

        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;
                }

                err = sock->ops->getname(sock, (struct sockaddr *)&address, 1);
                if (err >= 0)
                        /* "err" is actually length in this case */
                        err = move_addr_to_user(&address, err, usockaddr,
                                                usockaddr_len);
                fput_light(sock->file, fput_needed);
        }
        return err;
}

SYSCALL_DEFINE3(getpeername, int, fd, struct sockaddr __user *, usockaddr,
                int __user *, usockaddr_len)
{
        return __sys_getpeername(fd, usockaddr, usockaddr_len);
}

/*
 *      Send a datagram to a given address. We move the address into kernel
 *      space and check the user space data area is readable before invoking
 *      the protocol.
 */
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);
        if (unlikely(err))
                return err;