/*
 *  Linux syscalls
 *
 *  Copyright (c) 2003 Fabrice Bellard
 *
 *  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 program is distributed in the hope that it will be useful,
 *  but WITHOUT ANY WARRANTY; without even the implied warranty of
 *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 *  GNU General Public License for more details.
 *
 *  You should have received a copy of the GNU General Public License
 *  along with this program; if not, see <http://www.gnu.org/licenses/>.
 */
#define _ATFILE_SOURCE
#include "qemu/osdep.h"
#include "qemu/cutils.h"
#include "qemu/path.h"
#include <elf.h>
#include <endian.h>
#include <grp.h>
#include <sys/ipc.h>
#include <sys/msg.h>
#include <sys/wait.h>
#include <sys/mount.h>
#include <sys/file.h>
#include <sys/fsuid.h>
#include <sys/personality.h>
#include <sys/prctl.h>
#include <sys/resource.h>
#include <sys/swap.h>
#include <linux/capability.h>
#include <sched.h>
#include <sys/timex.h>
#include <sys/socket.h>
#include <sys/un.h>
#include <sys/uio.h>
#include <poll.h>
#include <sys/times.h>
#include <sys/shm.h>
#include <sys/sem.h>
#include <sys/statfs.h>
#include <utime.h>
#include <sys/sysinfo.h>
#include <sys/signalfd.h>
//#include <sys/user.h>
#include <netinet/ip.h>
#include <netinet/tcp.h>
#include <linux/wireless.h>
#include <linux/icmp.h>
#include <linux/icmpv6.h>
#include <linux/errqueue.h>
#include <linux/random.h>
#include "qemu-common.h"
#ifdef CONFIG_TIMERFD
#include <sys/timerfd.h>
#endif
#ifdef TARGET_GPROF
#include <sys/gmon.h>
#endif
#ifdef CONFIG_EVENTFD
#include <sys/eventfd.h>
#endif
#ifdef CONFIG_EPOLL
#include <sys/epoll.h>
#endif
#ifdef CONFIG_ATTR
#include "qemu/xattr.h"
#endif
#ifdef CONFIG_SENDFILE
#include <sys/sendfile.h>
#endif

#define termios host_termios
#define winsize host_winsize
#define termio host_termio
#define sgttyb host_sgttyb /* same as target */
#define tchars host_tchars /* same as target */
#define ltchars host_ltchars /* same as target */

#include <linux/termios.h>
#include <linux/unistd.h>
#include <linux/cdrom.h>
#include <linux/hdreg.h>
#include <linux/soundcard.h>
#include <linux/kd.h>
#include <linux/mtio.h>
#include <linux/fs.h>
#if defined(CONFIG_FIEMAP)
#include <linux/fiemap.h>
#endif
#include <linux/fb.h>
#if defined(CONFIG_USBFS)
#include <linux/usbdevice_fs.h>
#include <linux/usb/ch9.h>
#endif
#include <linux/vt.h>
#include <linux/dm-ioctl.h>
#include <linux/reboot.h>
#include <linux/route.h>
#include <linux/filter.h>
#include <linux/blkpg.h>
#include <netpacket/packet.h>
#include <linux/netlink.h>
#include "linux_loop.h"
#include "uname.h"

#include "qemu.h"
#include "fd-trans.h"

#ifndef CLONE_IO
#define CLONE_IO                0x80000000      /* Clone io context */
#endif

/* We can't directly call the host clone syscall, because this will
 * badly confuse libc (breaking mutexes, for example). So we must
 * divide clone flags into:
 *  * flag combinations that look like pthread_create()
 *  * flag combinations that look like fork()
 *  * flags we can implement within QEMU itself
 *  * flags we can't support and will return an error for
 */
/* For thread creation, all these flags must be present; for
 * fork, none must be present.
 */
#define CLONE_THREAD_FLAGS                              \
    (CLONE_VM | CLONE_FS | CLONE_FILES |                \
     CLONE_SIGHAND | CLONE_THREAD | CLONE_SYSVSEM)

/* These flags are ignored:
 * CLONE_DETACHED is now ignored by the kernel;
 * CLONE_IO is just an optimisation hint to the I/O scheduler
 */
#define CLONE_IGNORED_FLAGS                     \
    (CLONE_DETACHED | CLONE_IO)

/* Flags for fork which we can implement within QEMU itself */
#define CLONE_OPTIONAL_FORK_FLAGS               \
    (CLONE_SETTLS | CLONE_PARENT_SETTID |       \
     CLONE_CHILD_CLEARTID | CLONE_CHILD_SETTID)

/* Flags for thread creation which we can implement within QEMU itself */
#define CLONE_OPTIONAL_THREAD_FLAGS                             \
    (CLONE_SETTLS | CLONE_PARENT_SETTID |                       \
     CLONE_CHILD_CLEARTID | CLONE_CHILD_SETTID | CLONE_PARENT)

#define CLONE_INVALID_FORK_FLAGS                                        \
    (~(CSIGNAL | CLONE_OPTIONAL_FORK_FLAGS | CLONE_IGNORED_FLAGS))

#define CLONE_INVALID_THREAD_FLAGS                                      \
    (~(CSIGNAL | CLONE_THREAD_FLAGS | CLONE_OPTIONAL_THREAD_FLAGS |     \
       CLONE_IGNORED_FLAGS))

/* CLONE_VFORK is special cased early in do_fork(). The other flag bits
 * have almost all been allocated. We cannot support any of
 * CLONE_NEWNS, CLONE_NEWCGROUP, CLONE_NEWUTS, CLONE_NEWIPC,
 * CLONE_NEWUSER, CLONE_NEWPID, CLONE_NEWNET, CLONE_PTRACE, CLONE_UNTRACED.
 * The checks against the invalid thread masks above will catch these.
 * (The one remaining unallocated bit is 0x1000 which used to be CLONE_PID.)
 */

/* Define DEBUG_ERESTARTSYS to force every syscall to be restarted
 * once. This exercises the codepaths for restart.
 */
//#define DEBUG_ERESTARTSYS

//#include <linux/msdos_fs.h>
#define VFAT_IOCTL_READDIR_BOTH         _IOR('r', 1, struct linux_dirent [2])
#define VFAT_IOCTL_READDIR_SHORT        _IOR('r', 2, struct linux_dirent [2])

#undef _syscall0
#undef _syscall1
#undef _syscall2
#undef _syscall3
#undef _syscall4
#undef _syscall5
#undef _syscall6

#define _syscall0(type,name)            \
static type name (void)                 \
{                                       \
        return syscall(__NR_##name);    \
}

#define _syscall1(type,name,type1,arg1)         \
static type name (type1 arg1)                   \
{                                               \
        return syscall(__NR_##name, arg1);      \
}

#define _syscall2(type,name,type1,arg1,type2,arg2)      \
static type name (type1 arg1,type2 arg2)                \
{                                                       \
        return syscall(__NR_##name, arg1, arg2);        \
}

#define _syscall3(type,name,type1,arg1,type2,arg2,type3,arg3)   \
static type name (type1 arg1,type2 arg2,type3 arg3)             \
{                                                               \
        return syscall(__NR_##name, arg1, arg2, arg3);          \
}

#define _syscall4(type,name,type1,arg1,type2,arg2,type3,arg3,type4,arg4)        \
static type name (type1 arg1,type2 arg2,type3 arg3,type4 arg4)                  \
{                                                                               \
        return syscall(__NR_##name, arg1, arg2, arg3, arg4);                    \
}

#define _syscall5(type,name,type1,arg1,type2,arg2,type3,arg3,type4,arg4,        \
                  type5,arg5)                                                   \
static type name (type1 arg1,type2 arg2,type3 arg3,type4 arg4,type5 arg5)       \
{                                                                               \
        return syscall(__NR_##name, arg1, arg2, arg3, arg4, arg5);              \
}


#define _syscall6(type,name,type1,arg1,type2,arg2,type3,arg3,type4,arg4,        \
                  type5,arg5,type6,arg6)                                        \
static type name (type1 arg1,type2 arg2,type3 arg3,type4 arg4,type5 arg5,       \
                  type6 arg6)                                                   \
{                                                                               \
        return syscall(__NR_##name, arg1, arg2, arg3, arg4, arg5, arg6);        \
}


#define __NR_sys_uname __NR_uname
#define __NR_sys_getcwd1 __NR_getcwd
#define __NR_sys_getdents __NR_getdents
#define __NR_sys_getdents64 __NR_getdents64
#define __NR_sys_getpriority __NR_getpriority
#define __NR_sys_rt_sigqueueinfo __NR_rt_sigqueueinfo
#define __NR_sys_rt_tgsigqueueinfo __NR_rt_tgsigqueueinfo
#define __NR_sys_syslog __NR_syslog
#define __NR_sys_futex __NR_futex
#define __NR_sys_inotify_init __NR_inotify_init
#define __NR_sys_inotify_add_watch __NR_inotify_add_watch
#define __NR_sys_inotify_rm_watch __NR_inotify_rm_watch

#if defined(__alpha__) || defined(__x86_64__) || defined(__s390x__)
#define __NR__llseek __NR_lseek
#endif

/* Newer kernel ports have llseek() instead of _llseek() */
#if defined(TARGET_NR_llseek) && !defined(TARGET_NR__llseek)
#define TARGET_NR__llseek TARGET_NR_llseek
#endif

#define __NR_sys_gettid __NR_gettid
_syscall0(int, sys_gettid)

/* For the 64-bit guest on 32-bit host case we must emulate
 * getdents using getdents64, because otherwise the host
 * might hand us back more dirent records than we can fit
 * into the guest buffer after structure format conversion.
 * Otherwise we emulate getdents with getdents if the host has it.
 */
#if defined(__NR_getdents) && HOST_LONG_BITS >= TARGET_ABI_BITS
#define EMULATE_GETDENTS_WITH_GETDENTS
#endif

#if defined(TARGET_NR_getdents) && defined(EMULATE_GETDENTS_WITH_GETDENTS)
_syscall3(int, sys_getdents, uint, fd, struct linux_dirent *, dirp, uint, count);
#endif
#if (defined(TARGET_NR_getdents) && \
      !defined(EMULATE_GETDENTS_WITH_GETDENTS)) || \
    (defined(TARGET_NR_getdents64) && defined(__NR_getdents64))
_syscall3(int, sys_getdents64, uint, fd, struct linux_dirent64 *, dirp, uint, count);
#endif
#if defined(TARGET_NR__llseek) && defined(__NR_llseek)
_syscall5(int, _llseek,  uint,  fd, ulong, hi, ulong, lo,
          loff_t *, res, uint, wh);
#endif
_syscall3(int, sys_rt_sigqueueinfo, pid_t, pid, int, sig, siginfo_t *, uinfo)
_syscall4(int, sys_rt_tgsigqueueinfo, pid_t, pid, pid_t, tid, int, sig,
          siginfo_t *, uinfo)
_syscall3(int,sys_syslog,int,type,char*,bufp,int,len)
#ifdef __NR_exit_group
_syscall1(int,exit_group,int,error_code)
#endif
#if defined(TARGET_NR_set_tid_address) && defined(__NR_set_tid_address)
_syscall1(int,set_tid_address,int *,tidptr)
#endif
#if defined(TARGET_NR_futex) && defined(__NR_futex)
_syscall6(int,sys_futex,int *,uaddr,int,op,int,val,
          const struct timespec *,timeout,int *,uaddr2,int,val3)
#endif
#define __NR_sys_sched_getaffinity __NR_sched_getaffinity
_syscall3(int, sys_sched_getaffinity, pid_t, pid, unsigned int, len,
          unsigned long *, user_mask_ptr);
#define __NR_sys_sched_setaffinity __NR_sched_setaffinity
_syscall3(int, sys_sched_setaffinity, pid_t, pid, unsigned int, len,
          unsigned long *, user_mask_ptr);
#define __NR_sys_getcpu __NR_getcpu
_syscall3(int, sys_getcpu, unsigned *, cpu, unsigned *, node, void *, tcache);
_syscall4(int, reboot, int, magic1, int, magic2, unsigned int, cmd,
          void *, arg);
_syscall2(int, capget, struct __user_cap_header_struct *, header,
          struct __user_cap_data_struct *, data);
_syscall2(int, capset, struct __user_cap_header_struct *, header,
          struct __user_cap_data_struct *, data);
#if defined(TARGET_NR_ioprio_get) && defined(__NR_ioprio_get)
_syscall2(int, ioprio_get, int, which, int, who)
#endif
#if defined(TARGET_NR_ioprio_set) && defined(__NR_ioprio_set)
_syscall3(int, ioprio_set, int, which, int, who, int, ioprio)
#endif
#if defined(TARGET_NR_getrandom) && defined(__NR_getrandom)
_syscall3(int, getrandom, void *, buf, size_t, buflen, unsigned int, flags)
#endif

#if defined(TARGET_NR_kcmp) && defined(__NR_kcmp)
_syscall5(int, kcmp, pid_t, pid1, pid_t, pid2, int, type,
          unsigned long, idx1, unsigned long, idx2)
#endif

static bitmask_transtbl fcntl_flags_tbl[] = {
  { TARGET_O_ACCMODE,   TARGET_O_WRONLY,    O_ACCMODE,   O_WRONLY,    },
  { TARGET_O_ACCMODE,   TARGET_O_RDWR,      O_ACCMODE,   O_RDWR,      },
  { TARGET_O_CREAT,     TARGET_O_CREAT,     O_CREAT,     O_CREAT,     },
  { TARGET_O_EXCL,      TARGET_O_EXCL,      O_EXCL,      O_EXCL,      },
  { TARGET_O_NOCTTY,    TARGET_O_NOCTTY,    O_NOCTTY,    O_NOCTTY,    },
  { TARGET_O_TRUNC,     TARGET_O_TRUNC,     O_TRUNC,     O_TRUNC,     },
  { TARGET_O_APPEND,    TARGET_O_APPEND,    O_APPEND,    O_APPEND,    },
  { TARGET_O_NONBLOCK,  TARGET_O_NONBLOCK,  O_NONBLOCK,  O_NONBLOCK,  },
  { TARGET_O_SYNC,      TARGET_O_DSYNC,     O_SYNC,      O_DSYNC,     },
  { TARGET_O_SYNC,      TARGET_O_SYNC,      O_SYNC,      O_SYNC,      },
  { TARGET_FASYNC,      TARGET_FASYNC,      FASYNC,      FASYNC,      },
  { TARGET_O_DIRECTORY, TARGET_O_DIRECTORY, O_DIRECTORY, O_DIRECTORY, },
  { TARGET_O_NOFOLLOW,  TARGET_O_NOFOLLOW,  O_NOFOLLOW,  O_NOFOLLOW,  },
#if defined(O_DIRECT)
  { TARGET_O_DIRECT,    TARGET_O_DIRECT,    O_DIRECT,    O_DIRECT,    },
#endif
#if defined(O_NOATIME)
  { TARGET_O_NOATIME,   TARGET_O_NOATIME,   O_NOATIME,   O_NOATIME    },
#endif
#if defined(O_CLOEXEC)
  { TARGET_O_CLOEXEC,   TARGET_O_CLOEXEC,   O_CLOEXEC,   O_CLOEXEC    },
#endif
#if defined(O_PATH)
  { TARGET_O_PATH,      TARGET_O_PATH,      O_PATH,      O_PATH       },
#endif
#if defined(O_TMPFILE)
  { TARGET_O_TMPFILE,   TARGET_O_TMPFILE,   O_TMPFILE,   O_TMPFILE    },
#endif
  /* Don't terminate the list prematurely on 64-bit host+guest.  */
#if TARGET_O_LARGEFILE != 0 || O_LARGEFILE != 0
  { TARGET_O_LARGEFILE, TARGET_O_LARGEFILE, O_LARGEFILE, O_LARGEFILE, },
#endif
  { 0, 0, 0, 0 }
};

static int sys_getcwd1(char *buf, size_t size)
{
  if (getcwd(buf, size) == NULL) {
      /* getcwd() sets errno */
      return (-1);
  }
  return strlen(buf)+1;
}

#ifdef TARGET_NR_utimensat
#if defined(__NR_utimensat)
#define __NR_sys_utimensat __NR_utimensat
_syscall4(int,sys_utimensat,int,dirfd,const char *,pathname,
          const struct timespec *,tsp,int,flags)
#else
static int sys_utimensat(int dirfd, const char *pathname,
                         const struct timespec times[2], int flags)
{
    errno = ENOSYS;
    return -1;
}
#endif
#endif /* TARGET_NR_utimensat */

#ifdef TARGET_NR_renameat2
#if defined(__NR_renameat2)
#define __NR_sys_renameat2 __NR_renameat2
_syscall5(int, sys_renameat2, int, oldfd, const char *, old, int, newfd,
          const char *, new, unsigned int, flags)
#else
static int sys_renameat2(int oldfd, const char *old,
                         int newfd, const char *new, int flags)
{
    if (flags == 0) {
        return renameat(oldfd, old, newfd, new);
    }
    errno = ENOSYS;
    return -1;
}
#endif
#endif /* TARGET_NR_renameat2 */

#ifdef CONFIG_INOTIFY
#include <sys/inotify.h>

#if defined(TARGET_NR_inotify_init) && defined(__NR_inotify_init)
static int sys_inotify_init(void)
{
  return (inotify_init());
}
#endif
#if defined(TARGET_NR_inotify_add_watch) && defined(__NR_inotify_add_watch)
static int sys_inotify_add_watch(int fd,const char *pathname, int32_t mask)
{
  return (inotify_add_watch(fd, pathname, mask));
}
#endif
#if defined(TARGET_NR_inotify_rm_watch) && defined(__NR_inotify_rm_watch)
static int sys_inotify_rm_watch(int fd, int32_t wd)
{
  return (inotify_rm_watch(fd, wd));
}
#endif
#ifdef CONFIG_INOTIFY1
#if defined(TARGET_NR_inotify_init1) && defined(__NR_inotify_init1)
static int sys_inotify_init1(int flags)
{
  return (inotify_init1(flags));
}
#endif
#endif
#else
/* Userspace can usually survive runtime without inotify */
#undef TARGET_NR_inotify_init
#undef TARGET_NR_inotify_init1
#undef TARGET_NR_inotify_add_watch
#undef TARGET_NR_inotify_rm_watch
#endif /* CONFIG_INOTIFY  */

#if defined(TARGET_NR_prlimit64)
#ifndef __NR_prlimit64
# define __NR_prlimit64 -1
#endif
#define __NR_sys_prlimit64 __NR_prlimit64
/* The glibc rlimit structure may not be that used by the underlying syscall */
struct host_rlimit64 {
    uint64_t rlim_cur;
    uint64_t rlim_max;
};
_syscall4(int, sys_prlimit64, pid_t, pid, int, resource,
          const struct host_rlimit64 *, new_limit,
          struct host_rlimit64 *, old_limit)
#endif


#if defined(TARGET_NR_timer_create)
/* Maxiumum of 32 active POSIX timers allowed at any one time. */
static timer_t g_posix_timers[32] = { 0, } ;

static inline int next_free_host_timer(void)
{
    int k ;
    /* FIXME: Does finding the next free slot require a lock? */
    for (k = 0; k < ARRAY_SIZE(g_posix_timers); k++) {
        if (g_posix_timers[k] == 0) {
            g_posix_timers[k] = (timer_t) 1;
            return k;
        }
    }
    return -1;
}
#endif

/* ARM EABI and MIPS expect 64bit types aligned even on pairs or registers */
#ifdef TARGET_ARM
static inline int regpairs_aligned(void *cpu_env, int num)
{
    return ((((CPUARMState *)cpu_env)->eabi) == 1) ;
}
#elif defined(TARGET_MIPS) && (TARGET_ABI_BITS == 32)
static inline int regpairs_aligned(void *cpu_env, int num) { return 1; }
#elif defined(TARGET_PPC) && !defined(TARGET_PPC64)
/* SysV AVI for PPC32 expects 64bit parameters to be passed on odd/even pairs
 * of registers which translates to the same as ARM/MIPS, because we start with
 * r3 as arg1 */
static inline int regpairs_aligned(void *cpu_env, int num) { return 1; }
#elif defined(TARGET_SH4)
/* SH4 doesn't align register pairs, except for p{read,write}64 */
static inline int regpairs_aligned(void *cpu_env, int num)
{
    switch (num) {
    case TARGET_NR_pread64:
    case TARGET_NR_pwrite64:
        return 1;

    default:
        return 0;
    }
}
#elif defined(TARGET_XTENSA)
static inline int regpairs_aligned(void *cpu_env, int num) { return 1; }
#else
static inline int regpairs_aligned(void *cpu_env, int num) { return 0; }
#endif

#define ERRNO_TABLE_SIZE 1200

/* target_to_host_errno_table[] is initialized from
 * host_to_target_errno_table[] in syscall_init(). */
static uint16_t target_to_host_errno_table[ERRNO_TABLE_SIZE] = {
};

/*
 * This list is the union of errno values overridden in asm-<arch>/errno.h
 * minus the errnos that are not actually generic to all archs.
 */
static uint16_t host_to_target_errno_table[ERRNO_TABLE_SIZE] = {
    [EAGAIN]            = TARGET_EAGAIN,
    [EIDRM]             = TARGET_EIDRM,
    [ECHRNG]            = TARGET_ECHRNG,
    [EL2NSYNC]          = TARGET_EL2NSYNC,
    [EL3HLT]            = TARGET_EL3HLT,
    [EL3RST]            = TARGET_EL3RST,
    [ELNRNG]            = TARGET_ELNRNG,
    [EUNATCH]           = TARGET_EUNATCH,
    [ENOCSI]            = TARGET_ENOCSI,
    [EL2HLT]            = TARGET_EL2HLT,
    [EDEADLK]           = TARGET_EDEADLK,
    [ENOLCK]            = TARGET_ENOLCK,
    [EBADE]             = TARGET_EBADE,
    [EBADR]             = TARGET_EBADR,
    [EXFULL]            = TARGET_EXFULL,
    [ENOANO]            = TARGET_ENOANO,
    [EBADRQC]           = TARGET_EBADRQC,
    [EBADSLT]           = TARGET_EBADSLT,
    [EBFONT]            = TARGET_EBFONT,
    [ENOSTR]            = TARGET_ENOSTR,
    [ENODATA]           = TARGET_ENODATA,
    [ETIME]             = TARGET_ETIME,
    [ENOSR]             = TARGET_ENOSR,
    [ENONET]            = TARGET_ENONET,
    [ENOPKG]            = TARGET_ENOPKG,
    [EREMOTE]           = TARGET_EREMOTE,
    [ENOLINK]           = TARGET_ENOLINK,
    [EADV]              = TARGET_EADV,
    [ESRMNT]            = TARGET_ESRMNT,
    [ECOMM]             = TARGET_ECOMM,
    [EPROTO]            = TARGET_EPROTO,
    [EDOTDOT]           = TARGET_EDOTDOT,
    [EMULTIHOP]         = TARGET_EMULTIHOP,
    [EBADMSG]           = TARGET_EBADMSG,
    [ENAMETOOLONG]      = TARGET_ENAMETOOLONG,
    [EOVERFLOW]         = TARGET_EOVERFLOW,
    [ENOTUNIQ]          = TARGET_ENOTUNIQ,
    [EBADFD]            = TARGET_EBADFD,
    [EREMCHG]           = TARGET_EREMCHG,
    [ELIBACC]           = TARGET_ELIBACC,
    [ELIBBAD]           = TARGET_ELIBBAD,
    [ELIBSCN]           = TARGET_ELIBSCN,
    [ELIBMAX]           = TARGET_ELIBMAX,
    [ELIBEXEC]          = TARGET_ELIBEXEC,
    [EILSEQ]            = TARGET_EILSEQ,
    [ENOSYS]            = TARGET_ENOSYS,
    [ELOOP]             = TARGET_ELOOP,
    [ERESTART]          = TARGET_ERESTART,
    [ESTRPIPE]          = TARGET_ESTRPIPE,
    [ENOTEMPTY]         = TARGET_ENOTEMPTY,
    [EUSERS]            = TARGET_EUSERS,
    [ENOTSOCK]          = TARGET_ENOTSOCK,
    [EDESTADDRREQ]      = TARGET_EDESTADDRREQ,
    [EMSGSIZE]          = TARGET_EMSGSIZE,
    [EPROTOTYPE]        = TARGET_EPROTOTYPE,
    [ENOPROTOOPT]       = TARGET_ENOPROTOOPT,
    [EPROTONOSUPPORT]   = TARGET_EPROTONOSUPPORT,
    [ESOCKTNOSUPPORT]   = TARGET_ESOCKTNOSUPPORT,
    [EOPNOTSUPP]        = TARGET_EOPNOTSUPP,
    [EPFNOSUPPORT]      = TARGET_EPFNOSUPPORT,
    [EAFNOSUPPORT]      = TARGET_EAFNOSUPPORT,
    [EADDRINUSE]        = TARGET_EADDRINUSE,
    [EADDRNOTAVAIL]     = TARGET_EADDRNOTAVAIL,
    [ENETDOWN]          = TARGET_ENETDOWN,
    [ENETUNREACH]       = TARGET_ENETUNREACH,
    [ENETRESET]         = TARGET_ENETRESET,
    [ECONNABORTED]      = TARGET_ECONNABORTED,
    [ECONNRESET]        = TARGET_ECONNRESET,
    [ENOBUFS]           = TARGET_ENOBUFS,
    [EISCONN]           = TARGET_EISCONN,
    [ENOTCONN]          = TARGET_ENOTCONN,
    [EUCLEAN]           = TARGET_EUCLEAN,
    [ENOTNAM]           = TARGET_ENOTNAM,
    [ENAVAIL]           = TARGET_ENAVAIL,
    [EISNAM]            = TARGET_EISNAM,
    [EREMOTEIO]         = TARGET_EREMOTEIO,
    [EDQUOT]            = TARGET_EDQUOT,
    [ESHUTDOWN]         = TARGET_ESHUTDOWN,
    [ETOOMANYREFS]      = TARGET_ETOOMANYREFS,
    [ETIMEDOUT]         = TARGET_ETIMEDOUT,
    [ECONNREFUSED]      = TARGET_ECONNREFUSED,
    [EHOSTDOWN]         = TARGET_EHOSTDOWN,
    [EHOSTUNREACH]      = TARGET_EHOSTUNREACH,
    [EALREADY]          = TARGET_EALREADY,
    [EINPROGRESS]       = TARGET_EINPROGRESS,
    [ESTALE]            = TARGET_ESTALE,
    [ECANCELED]         = TARGET_ECANCELED,
    [ENOMEDIUM]         = TARGET_ENOMEDIUM,
    [EMEDIUMTYPE]       = TARGET_EMEDIUMTYPE,
#ifdef ENOKEY
    [ENOKEY]            = TARGET_ENOKEY,
#endif
#ifdef EKEYEXPIRED
    [EKEYEXPIRED]       = TARGET_EKEYEXPIRED,
#endif
#ifdef EKEYREVOKED
    [EKEYREVOKED]       = TARGET_EKEYREVOKED,
#endif
#ifdef EKEYREJECTED
    [EKEYREJECTED]      = TARGET_EKEYREJECTED,
#endif
#ifdef EOWNERDEAD
    [EOWNERDEAD]        = TARGET_EOWNERDEAD,
#endif
#ifdef ENOTRECOVERABLE
    [ENOTRECOVERABLE]   = TARGET_ENOTRECOVERABLE,
#endif
#ifdef ENOMSG
    [ENOMSG]            = TARGET_ENOMSG,
#endif
#ifdef ERKFILL
    [ERFKILL]           = TARGET_ERFKILL,
#endif
#ifdef EHWPOISON
    [EHWPOISON]         = TARGET_EHWPOISON,
#endif
};

static inline int host_to_target_errno(int err)
{
    if (err >= 0 && err < ERRNO_TABLE_SIZE &&
        host_to_target_errno_table[err]) {
        return host_to_target_errno_table[err];
    }
    return err;
}

static inline int target_to_host_errno(int err)
{
    if (err >= 0 && err < ERRNO_TABLE_SIZE &&
        target_to_host_errno_table[err]) {
        return target_to_host_errno_table[err];
    }
    return err;
}

static inline abi_long get_errno(abi_long ret)
{
    if (ret == -1)
        return -host_to_target_errno(errno);
    else
        return ret;
}

const char *target_strerror(int err)
{
    if (err == TARGET_ERESTARTSYS) {
        return "To be restarted";
    }
    if (err == TARGET_QEMU_ESIGRETURN) {
        return "Successful exit from sigreturn";
    }

    if ((err >= ERRNO_TABLE_SIZE) || (err < 0)) {
        return NULL;
    }
    return strerror(target_to_host_errno(err));
}

#define safe_syscall0(type, name) \
static type safe_##name(void) \
{ \
    return safe_syscall(__NR_##name); \
}

#define safe_syscall1(type, name, type1, arg1) \
static type safe_##name(type1 arg1) \
{ \
    return safe_syscall(__NR_##name, arg1); \
}

#define safe_syscall2(type, name, type1, arg1, type2, arg2) \
static type safe_##name(type1 arg1, type2 arg2) \
{ \
    return safe_syscall(__NR_##name, arg1, arg2); \
}

#define safe_syscall3(type, name, type1, arg1, type2, arg2, type3, arg3) \
static type safe_##name(type1 arg1, type2 arg2, type3 arg3) \
{ \
    return safe_syscall(__NR_##name, arg1, arg2, arg3); \
}

#define safe_syscall4(type, name, type1, arg1, type2, arg2, type3, arg3, \
    type4, arg4) \
static type safe_##name(type1 arg1, type2 arg2, type3 arg3, type4 arg4) \
{ \
    return safe_syscall(__NR_##name, arg1, arg2, arg3, arg4); \
}

#define safe_syscall5(type, name, type1, arg1, type2, arg2, type3, arg3, \
    type4, arg4, type5, arg5) \
static type safe_##name(type1 arg1, type2 arg2, type3 arg3, type4 arg4, \
    type5 arg5) \
{ \
    return safe_syscall(__NR_##name, arg1, arg2, arg3, arg4, arg5); \
}

#define safe_syscall6(type, name, type1, arg1, type2, arg2, type3, arg3, \
    type4, arg4, type5, arg5, type6, arg6) \
static type safe_##name(type1 arg1, type2 arg2, type3 arg3, type4 arg4, \
    type5 arg5, type6 arg6) \
{ \
    return safe_syscall(__NR_##name, arg1, arg2, arg3, arg4, arg5, arg6); \
}

safe_syscall3(ssize_t, read, int, fd, void *, buff, size_t, count)
safe_syscall3(ssize_t, write, int, fd, const void *, buff, size_t, count)
safe_syscall4(int, openat, int, dirfd, const char *, pathname, \
              int, flags, mode_t, mode)
safe_syscall4(pid_t, wait4, pid_t, pid, int *, status, int, options, \
              struct rusage *, rusage)
safe_syscall5(int, waitid, idtype_t, idtype, id_t, id, siginfo_t *, infop, \
              int, options, struct rusage *, rusage)
safe_syscall3(int, execve, const char *, filename, char **, argv, char **, envp)
safe_syscall6(int, pselect6, int, nfds, fd_set *, readfds, fd_set *, writefds, \
              fd_set *, exceptfds, struct timespec *, timeout, void *, sig)
safe_syscall5(int, ppoll, struct pollfd *, ufds, unsigned int, nfds,
              struct timespec *, tsp, const sigset_t *, sigmask,
              size_t, sigsetsize)
safe_syscall6(int, epoll_pwait, int, epfd, struct epoll_event *, events,
              int, maxevents, int, timeout, const sigset_t *, sigmask,
              size_t, sigsetsize)
safe_syscall6(int,futex,int *,uaddr,int,op,int,val, \
              const struct timespec *,timeout,int *,uaddr2,int,val3)
safe_syscall2(int, rt_sigsuspend, sigset_t *, newset, size_t, sigsetsize)
safe_syscall2(int, kill, pid_t, pid, int, sig)
safe_syscall2(int, tkill, int, tid, int, sig)
safe_syscall3(int, tgkill, int, tgid, int, pid, int, sig)
safe_syscall3(ssize_t, readv, int, fd, const struct iovec *, iov, int, iovcnt)
safe_syscall3(ssize_t, writev, int, fd, const struct iovec *, iov, int, iovcnt)
safe_syscall5(ssize_t, preadv, int, fd, const struct iovec *, iov, int, iovcnt,
              unsigned long, pos_l, unsigned long, pos_h)
safe_syscall5(ssize_t, pwritev, int, fd, const struct iovec *, iov, int, iovcnt,
              unsigned long, pos_l, unsigned long, pos_h)
safe_syscall3(int, connect, int, fd, const struct sockaddr *, addr,
              socklen_t, addrlen)
safe_syscall6(ssize_t, sendto, int, fd, const void *, buf, size_t, len,
              int, flags, const struct sockaddr *, addr, socklen_t, addrlen)
safe_syscall6(ssize_t, recvfrom, int, fd, void *, buf, size_t, len,
              int, flags, struct sockaddr *, addr, socklen_t *, addrlen)
safe_syscall3(ssize_t, sendmsg, int, fd, const struct msghdr *, msg, int, flags)
safe_syscall3(ssize_t, recvmsg, int, fd, struct msghdr *, msg, int, flags)
safe_syscall2(int, flock, int, fd, int, operation)
safe_syscall4(int, rt_sigtimedwait, const sigset_t *, these, siginfo_t *, uinfo,
              const struct timespec *, uts, size_t, sigsetsize)
safe_syscall4(int, accept4, int, fd, struct sockaddr *, addr, socklen_t *, len,
              int, flags)
safe_syscall2(int, nanosleep, const struct timespec *, req,
              struct timespec *, rem)
#ifdef TARGET_NR_clock_nanosleep
safe_syscall4(int, clock_nanosleep, const clockid_t, clock, int, flags,
              const struct timespec *, req, struct timespec *, rem)
#endif
#ifdef __NR_msgsnd
safe_syscall4(int, msgsnd, int, msgid, const void *, msgp, size_t, sz,
              int, flags)
safe_syscall5(int, msgrcv, int, msgid, void *, msgp, size_t, sz,
              long, msgtype, int, flags)
safe_syscall4(int, semtimedop, int, semid, struct sembuf *, tsops,
              unsigned, nsops, const struct timespec *, timeout)
#else
/* This host kernel architecture uses a single ipc syscall; fake up
 * wrappers for the sub-operations to hide this implementation detail.
 * Annoyingly we can't include linux/ipc.h to get the constant definitions
 * for the call parameter because some structs in there conflict with the
 * sys/ipc.h ones. So we just define them here, and rely on them being
 * the same for all host architectures.
 */
#define Q_SEMTIMEDOP 4
#define Q_MSGSND 11
#define Q_MSGRCV 12
#define Q_IPCCALL(VERSION, OP) ((VERSION) << 16 | (OP))

safe_syscall6(int, ipc, int, call, long, first, long, second, long, third,
              void *, ptr, long, fifth)
static int safe_msgsnd(int msgid, const void *msgp, size_t sz, int flags)
{
    return safe_ipc(Q_IPCCALL(0, Q_MSGSND), msgid, sz, flags, (void *)msgp, 0);
}
static int safe_msgrcv(int msgid, void *msgp, size_t sz, long type, int flags)
{
    return safe_ipc(Q_IPCCALL(1, Q_MSGRCV), msgid, sz, flags, msgp, type);
}
static int safe_semtimedop(int semid, struct sembuf *tsops, unsigned nsops,
                           const struct timespec *timeout)
{
    return safe_ipc(Q_IPCCALL(0, Q_SEMTIMEDOP), semid, nsops, 0, tsops,
                    (long)timeout);
}
#endif
#if defined(TARGET_NR_mq_open) && defined(__NR_mq_open)
safe_syscall5(int, mq_timedsend, int, mqdes, const char *, msg_ptr,
              size_t, len, unsigned, prio, const struct timespec *, timeout)
safe_syscall5(int, mq_timedreceive, int, mqdes, char *, msg_ptr,
              size_t, len, unsigned *, prio, const struct timespec *, timeout)
#endif
/* We do ioctl like this rather than via safe_syscall3 to preserve the
 * "third argument might be integer or pointer or not present" behaviour of
 * the libc function.
 */
#define safe_ioctl(...) safe_syscall(__NR_ioctl, __VA_ARGS__)
/* Similarly for fcntl. Note that callers must always:
 *  pass the F_GETLK64 etc constants rather than the unsuffixed F_GETLK
 *  use the flock64 struct rather than unsuffixed flock
 * This will then work and use a 64-bit offset for both 32-bit and 64-bit hosts.
 */
#ifdef __NR_fcntl64
#define safe_fcntl(...) safe_syscall(__NR_fcntl64, __VA_ARGS__)
#else
#define safe_fcntl(...) safe_syscall(__NR_fcntl, __VA_ARGS__)
#endif

static inline int host_to_target_sock_type(int host_type)
{
    int target_type;

    switch (host_type & 0xf /* SOCK_TYPE_MASK */) {
    case SOCK_DGRAM:
        target_type = TARGET_SOCK_DGRAM;
        break;
    case SOCK_STREAM:
        target_type = TARGET_SOCK_STREAM;
        break;
    default:
        target_type = host_type & 0xf /* SOCK_TYPE_MASK */;
        break;
    }

#if defined(SOCK_CLOEXEC)
    if (host_type & SOCK_CLOEXEC) {
        target_type |= TARGET_SOCK_CLOEXEC;
    }
#endif

#if defined(SOCK_NONBLOCK)
    if (host_type & SOCK_NONBLOCK) {
        target_type |= TARGET_SOCK_NONBLOCK;
    }
#endif

    return target_type;
}

static abi_ulong target_brk;
static abi_ulong target_original_brk;
static abi_ulong brk_page;

void target_set_brk(abi_ulong new_brk)
{
    target_original_brk = target_brk = HOST_PAGE_ALIGN(new_brk);
    brk_page = HOST_PAGE_ALIGN(target_brk);
}

//#define DEBUGF_BRK(message, args...) do { fprintf(stderr, (message), ## args); } while (0)
#define DEBUGF_BRK(message, args...)

/* do_brk() must return target values and target errnos. */
abi_long do_brk(abi_ulong new_brk)
{
    abi_long mapped_addr;
    abi_ulong new_alloc_size;

    DEBUGF_BRK("do_brk(" TARGET_ABI_FMT_lx ") -> ", new_brk);

    if (!new_brk) {
        DEBUGF_BRK(TARGET_ABI_FMT_lx " (!new_brk)\n", target_brk);
        return target_brk;
    }
    if (new_brk < target_original_brk) {
        DEBUGF_BRK(TARGET_ABI_FMT_lx " (new_brk < target_original_brk)\n",
                   target_brk);
        return target_brk;
    }

    /* If the new brk is less than the highest page reserved to the
     * target heap allocation, set it and we're almost done...  */
    if (new_brk <= brk_page) {
        /* Heap contents are initialized to zero, as for anonymous
         * mapped pages.  */
        if (new_brk > target_brk) {
            memset(g2h(target_brk), 0, new_brk - target_brk);
        }
        target_brk = new_brk;
        DEBUGF_BRK(TARGET_ABI_FMT_lx " (new_brk <= brk_page)\n", target_brk);
        return target_brk;
    }

    /* We need to allocate more memory after the brk... Note that
     * we don't use MAP_FIXED because that will map over the top of
     * any existing mapping (like the one with the host libc or qemu
     * itself); instead we treat "mapped but at wrong address" as
     * a failure and unmap again.
     */
    new_alloc_size = HOST_PAGE_ALIGN(new_brk - brk_page);
    mapped_addr = get_errno(target_mmap(brk_page, new_alloc_size,
                                        PROT_READ|PROT_WRITE,
                                        MAP_ANON|MAP_PRIVATE, 0, 0));

    if (mapped_addr == brk_page) {
        /* Heap contents are initialized to zero, as for anonymous
         * mapped pages.  Technically the new pages are already
         * initialized to zero since they *are* anonymous mapped
         * pages, however we have to take care with the contents that
         * come from the remaining part of the previous page: it may
         * contains garbage data due to a previous heap usage (grown
         * then shrunken).  */
        memset(g2h(target_brk), 0, brk_page - target_brk);

        target_brk = new_brk;
        brk_page = HOST_PAGE_ALIGN(target_brk);
        DEBUGF_BRK(TARGET_ABI_FMT_lx " (mapped_addr == brk_page)\n",
            target_brk);
        return target_brk;
    } else if (mapped_addr != -1) {
        /* Mapped but at wrong address, meaning there wasn't actually
         * enough space for this brk.
         */
        target_munmap(mapped_addr, new_alloc_size);
        mapped_addr = -1;
        DEBUGF_BRK(TARGET_ABI_FMT_lx " (mapped_addr != -1)\n", target_brk);
    }
    else {
        DEBUGF_BRK(TARGET_ABI_FMT_lx " (otherwise)\n", target_brk);
    }

#if defined(TARGET_ALPHA)
    /* We (partially) emulate OSF/1 on Alpha, which requires we
       return a proper errno, not an unchanged brk value.  */
    return -TARGET_ENOMEM;
#endif
    /* For everything else, return the previous break. */
    return target_brk;
}

static inline abi_long copy_from_user_fdset(fd_set *fds,
                                            abi_ulong target_fds_addr,
                                            int n)
{
    int i, nw, j, k;
    abi_ulong b, *target_fds;

    nw = DIV_ROUND_UP(n, TARGET_ABI_BITS);
    if (!(target_fds = lock_user(VERIFY_READ,
                                 target_fds_addr,
                                 sizeof(abi_ulong) * nw,
                                 1)))
        return -TARGET_EFAULT;

    FD_ZERO(fds);
    k = 0;
    for (i = 0; i < nw; i++) {
        /* grab the abi_ulong */
        __get_user(b, &target_fds[i]);
        for (j = 0; j < TARGET_ABI_BITS; j++) {
            /* check the bit inside the abi_ulong */
            if ((b >> j) & 1)
                FD_SET(k, fds);
            k++;
        }
    }

    unlock_user(target_fds, target_fds_addr, 0);

    return 0;
}

static inline abi_ulong copy_from_user_fdset_ptr(fd_set *fds, fd_set **fds_ptr,
                                                 abi_ulong target_fds_addr,
                                                 int n)
{
    if (target_fds_addr) {
        if (copy_from_user_fdset(fds, target_fds_addr, n))
            return -TARGET_EFAULT;
        *fds_ptr = fds;
    } else {
        *fds_ptr = NULL;
    }
    return 0;
}

static inline abi_long copy_to_user_fdset(abi_ulong target_fds_addr,
                                          const fd_set *fds,
                                          int n)
{
    int i, nw, j, k;
    abi_long v;
    abi_ulong *target_fds;

    nw = DIV_ROUND_UP(n, TARGET_ABI_BITS);
    if (!(target_fds = lock_user(VERIFY_WRITE,
                                 target_fds_addr,
                                 sizeof(abi_ulong) * nw,
                                 0)))
        return -TARGET_EFAULT;

    k = 0;
    for (i = 0; i < nw; i++) {
        v = 0;
        for (j = 0; j < TARGET_ABI_BITS; j++) {
            v |= ((abi_ulong)(FD_ISSET(k, fds) != 0) << j);
            k++;
        }
        __put_user(v, &target_fds[i]);
    }

    unlock_user(target_fds, target_fds_addr, sizeof(abi_ulong) * nw);

    return 0;
}

#if defined(__alpha__)
#define HOST_HZ 1024
#else
#define HOST_HZ 100
#endif

static inline abi_long host_to_target_clock_t(long ticks)
{
#if HOST_HZ == TARGET_HZ
    return ticks;
#else
    return ((int64_t)ticks * TARGET_HZ) / HOST_HZ;
#endif
}

static inline abi_long host_to_target_rusage(abi_ulong target_addr,
                                             const struct rusage *rusage)
{
    struct target_rusage *target_rusage;

    if (!lock_user_struct(VERIFY_WRITE, target_rusage, target_addr, 0))
        return -TARGET_EFAULT;
    target_rusage->ru_utime.tv_sec = tswapal(rusage->ru_utime.tv_sec);
    target_rusage->ru_utime.tv_usec = tswapal(rusage->ru_utime.tv_usec);
    target_rusage->ru_stime.tv_sec = tswapal(rusage->ru_stime.tv_sec);
    target_rusage->ru_stime.tv_usec = tswapal(rusage->ru_stime.tv_usec);
    target_rusage->ru_maxrss = tswapal(rusage->ru_maxrss);
    target_rusage->ru_ixrss = tswapal(rusage->ru_ixrss);
    target_rusage->ru_idrss = tswapal(rusage->ru_idrss);
    target_rusage->ru_isrss = tswapal(rusage->ru_isrss);
    target_rusage->ru_minflt = tswapal(rusage->ru_minflt);
    target_rusage->ru_majflt = tswapal(rusage->ru_majflt);
    target_rusage->ru_nswap = tswapal(rusage->ru_nswap);
    target_rusage->ru_inblock = tswapal(rusage->ru_inblock);
    target_rusage->ru_oublock = tswapal(rusage->ru_oublock);
    target_rusage->ru_msgsnd = tswapal(rusage->ru_msgsnd);
    target_rusage->ru_msgrcv = tswapal(rusage->ru_msgrcv);
    target_rusage->ru_nsignals = tswapal(rusage->ru_nsignals);
    target_rusage->ru_nvcsw = tswapal(rusage->ru_nvcsw);
    target_rusage->ru_nivcsw = tswapal(rusage->ru_nivcsw);
    unlock_user_struct(target_rusage, target_addr, 1);

    return 0;
}

static inline rlim_t target_to_host_rlim(abi_ulong target_rlim)
{
    abi_ulong target_rlim_swap;
    rlim_t result;
    
    target_rlim_swap = tswapal(target_rlim);
    if (target_rlim_swap == TARGET_RLIM_INFINITY)
        return RLIM_INFINITY;

    result = target_rlim_swap;
    if (target_rlim_swap != (rlim_t)result)
        return RLIM_INFINITY;
    
    return result;
}

static inline abi_ulong host_to_target_rlim(rlim_t rlim)
{
    abi_ulong target_rlim_swap;
    abi_ulong result;
    
    if (rlim == RLIM_INFINITY || rlim != (abi_long)rlim)
        target_rlim_swap = TARGET_RLIM_INFINITY;
    else
        target_rlim_swap = rlim;
    result = tswapal(target_rlim_swap);
    
    return result;
}

static inline int target_to_host_resource(int code)
{
    switch (code) {
    case TARGET_RLIMIT_AS:
        return RLIMIT_AS;
    case TARGET_RLIMIT_CORE:
        return RLIMIT_CORE;
    case TARGET_RLIMIT_CPU:
        return RLIMIT_CPU;
    case TARGET_RLIMIT_DATA:
        return RLIMIT_DATA;
    case TARGET_RLIMIT_FSIZE:
        return RLIMIT_FSIZE;
    case TARGET_RLIMIT_LOCKS:
        return RLIMIT_LOCKS;
    case TARGET_RLIMIT_MEMLOCK:
        return RLIMIT_MEMLOCK;
    case TARGET_RLIMIT_MSGQUEUE:
        return RLIMIT_MSGQUEUE;
    case TARGET_RLIMIT_NICE:
        return RLIMIT_NICE;
    case TARGET_RLIMIT_NOFILE:
        return RLIMIT_NOFILE;
    case TARGET_RLIMIT_NPROC:
        return RLIMIT_NPROC;
    case TARGET_RLIMIT_RSS:
        return RLIMIT_RSS;
    case TARGET_RLIMIT_RTPRIO:
        return RLIMIT_RTPRIO;
    case TARGET_RLIMIT_SIGPENDING:
        return RLIMIT_SIGPENDING;
    case TARGET_RLIMIT_STACK:
        return RLIMIT_STACK;
    default:
        return code;
    }
}

static inline abi_long copy_from_user_timeval(struct timeval *tv,
                                              abi_ulong target_tv_addr)
{
    struct target_timeval *target_tv;

    if (!lock_user_struct(VERIFY_READ, target_tv, target_tv_addr, 1))
        return -TARGET_EFAULT;

    __get_user(tv->tv_sec, &target_tv->tv_sec);
    __get_user(tv->tv_usec, &target_tv->tv_usec);

    unlock_user_struct(target_tv, target_tv_addr, 0);

    return 0;
}

static inline abi_long copy_to_user_timeval(abi_ulong target_tv_addr,
                                            const struct timeval *tv)
{
    struct target_timeval *target_tv;

    if (!lock_user_struct(VERIFY_WRITE, target_tv, target_tv_addr, 0))
        return -TARGET_EFAULT;

    __put_user(tv->tv_sec, &target_tv->tv_sec);
    __put_user(tv->tv_usec, &target_tv->tv_usec);

    unlock_user_struct(target_tv, target_tv_addr, 1);

    return 0;
}

static inline abi_long copy_from_user_timezone(struct timezone *tz,
                                               abi_ulong target_tz_addr)
{
    struct target_timezone *target_tz;

    if (!lock_user_struct(VERIFY_READ, target_tz, target_tz_addr, 1)) {
        return -TARGET_EFAULT;
    }

    __get_user(tz->tz_minuteswest, &target_tz->tz_minuteswest);
    __get_user(tz->tz_dsttime, &target_tz->tz_dsttime);

    unlock_user_struct(target_tz, target_tz_addr, 0);

    return 0;
}

#if defined(TARGET_NR_mq_open) && defined(__NR_mq_open)
#include <mqueue.h>

static inline abi_long copy_from_user_mq_attr(struct mq_attr *attr,
                                              abi_ulong target_mq_attr_addr)
{
    struct target_mq_attr *target_mq_attr;

    if (!lock_user_struct(VERIFY_READ, target_mq_attr,
                          target_mq_attr_addr, 1))
        return -TARGET_EFAULT;

    __get_user(attr->mq_flags, &target_mq_attr->mq_flags);
    __get_user(attr->mq_maxmsg, &target_mq_attr->mq_maxmsg);
    __get_user(attr->mq_msgsize, &target_mq_attr->mq_msgsize);
    __get_user(attr->mq_curmsgs, &target_mq_attr->mq_curmsgs);

    unlock_user_struct(target_mq_attr, target_mq_attr_addr, 0);

    return 0;
}

static inline abi_long copy_to_user_mq_attr(abi_ulong target_mq_attr_addr,
                                            const struct mq_attr *attr)
{
    struct target_mq_attr *target_mq_attr;

    if (!lock_user_struct(VERIFY_WRITE, target_mq_attr,
                          target_mq_attr_addr, 0))
        return -TARGET_EFAULT;

    __put_user(attr->mq_flags, &target_mq_attr->mq_flags);
    __put_user(attr->mq_maxmsg, &target_mq_attr->mq_maxmsg);
    __put_user(attr->mq_msgsize, &target_mq_attr->mq_msgsize);
    __put_user(attr->mq_curmsgs, &target_mq_attr->mq_curmsgs);

    unlock_user_struct(target_mq_attr, target_mq_attr_addr, 1);

    return 0;
}
#endif

#if defined(TARGET_NR_select) || defined(TARGET_NR__newselect)
/* do_select() must return target values and target errnos. */
static abi_long do_select(int n,
                          abi_ulong rfd_addr, abi_ulong wfd_addr,
                          abi_ulong efd_addr, abi_ulong target_tv_addr)
{
    fd_set rfds, wfds, efds;
    fd_set *rfds_ptr, *wfds_ptr, *efds_ptr;
    struct timeval tv;
    struct timespec ts, *ts_ptr;
    abi_long ret;

    ret = copy_from_user_fdset_ptr(&rfds, &rfds_ptr, rfd_addr, n);
    if (ret) {
        return ret;
    }
    ret = copy_from_user_fdset_ptr(&wfds, &wfds_ptr, wfd_addr, n);
    if (ret) {
        return ret;
    }
    ret = copy_from_user_fdset_ptr(&efds, &efds_ptr, efd_addr, n);
    if (ret) {
        return ret;
    }

    if (target_tv_addr) {
        if (copy_from_user_timeval(&tv, target_tv_addr))
            return -TARGET_EFAULT;
        ts.tv_sec = tv.tv_sec;
        ts.tv_nsec = tv.tv_usec * 1000;
        ts_ptr = &ts;
    } else {
        ts_ptr = NULL;
    }

    ret = get_errno(safe_pselect6(n, rfds_ptr, wfds_ptr, efds_ptr,
                                  ts_ptr, NULL));

    if (!is_error(ret)) {
        if (rfd_addr && copy_to_user_fdset(rfd_addr, &rfds, n))
            return -TARGET_EFAULT;
        if (wfd_addr && copy_to_user_fdset(wfd_addr, &wfds, n))
            return -TARGET_EFAULT;
        if (efd_addr && copy_to_user_fdset(efd_addr, &efds, n))
            return -TARGET_EFAULT;

        if (target_tv_addr) {
            tv.tv_sec = ts.tv_sec;
            tv.tv_usec = ts.tv_nsec / 1000;
            if (copy_to_user_timeval(target_tv_addr, &tv)) {
                return -TARGET_EFAULT;
            }
        }
    }

    return ret;
}

#if defined(TARGET_WANT_OLD_SYS_SELECT)
static abi_long do_old_select(abi_ulong arg1)
{
    struct target_sel_arg_struct *sel;
    abi_ulong inp, outp, exp, tvp;
    long nsel;

    if (!lock_user_struct(VERIFY_READ, sel, arg1, 1)) {
        return -TARGET_EFAULT;
    }

    nsel = tswapal(sel->n);
    inp = tswapal(sel->inp);
    outp = tswapal(sel->outp);
    exp = tswapal(sel->exp);
    tvp = tswapal(sel->tvp);

    unlock_user_struct(sel, arg1, 0);

    return do_select(nsel, inp, outp, exp, tvp);
}
#endif
#endif

static abi_long do_pipe2(int host_pipe[], int flags)
{
#ifdef CONFIG_PIPE2
    return pipe2(host_pipe, flags);
#else
    return -ENOSYS;
#endif
}

static abi_long do_pipe(void *cpu_env, abi_ulong pipedes,
                        int flags, int is_pipe2)
{
    int host_pipe[2];
    abi_long ret;
    ret = flags ? do_pipe2(host_pipe, flags) : pipe(host_pipe);

    if (is_error(ret))
        return get_errno(ret);

    /* Several targets have special calling conventions for the original
       pipe syscall, but didn't replicate this into the pipe2 syscall.  */
    if (!is_pipe2) {
#if defined(TARGET_ALPHA)
        ((CPUAlphaState *)cpu_env)->ir[IR_A4] = host_pipe[1];
        return host_pipe[0];
#elif defined(TARGET_MIPS)
        ((CPUMIPSState*)cpu_env)->active_tc.gpr[3] = host_pipe[1];
        return host_pipe[0];
#elif defined(TARGET_SH4)
        ((CPUSH4State*)cpu_env)->gregs[1] = host_pipe[1];
        return host_pipe[0];
#elif defined(TARGET_SPARC)
        ((CPUSPARCState*)cpu_env)->regwptr[1] = host_pipe[1];
        return host_pipe[0];
#endif
    }

    if (put_user_s32(host_pipe[0], pipedes)
        || put_user_s32(host_pipe[1], pipedes + sizeof(host_pipe[0])))
        return -TARGET_EFAULT;
    return get_errno(ret);
}

static inline abi_long target_to_host_ip_mreq(struct ip_mreqn *mreqn,
                                              abi_ulong target_addr,
                                              socklen_t len)
{
    struct target_ip_mreqn *target_smreqn;

    target_smreqn = lock_user(VERIFY_READ, target_addr, len, 1);
    if (!target_smreqn)
        return -TARGET_EFAULT;
    mreqn->imr_multiaddr.s_addr = target_smreqn->imr_multiaddr.s_addr;
    mreqn->imr_address.s_addr = target_smreqn->imr_address.s_addr;
    if (len == sizeof(struct target_ip_mreqn))
        mreqn->imr_ifindex = tswapal(target_smreqn->imr_ifindex);
    unlock_user(target_smreqn, target_addr, 0);

    return 0;
}

static inline abi_long target_to_host_sockaddr(int fd, struct sockaddr *addr,
                                               abi_ulong target_addr,
                                               socklen_t len)
{
    const socklen_t unix_maxlen = sizeof (struct sockaddr_un);
    sa_family_t sa_family;
    struct target_sockaddr *target_saddr;

    if (fd_trans_target_to_host_addr(fd)) {
        return fd_trans_target_to_host_addr(fd)(addr, target_addr, len);
    }

    target_saddr = lock_user(VERIFY_READ, target_addr, len, 1);
    if (!target_saddr)
        return -TARGET_EFAULT;

    sa_family = tswap16(target_saddr->sa_family);

    /* Oops. The caller might send a incomplete sun_path; sun_path
     * must be terminated by \0 (see the manual page), but
     * unfortunately it is quite common to specify sockaddr_un
     * length as "strlen(x->sun_path)" while it should be
     * "strlen(...) + 1". We'll fix that here if needed.
     * Linux kernel has a similar feature.
     */

    if (sa_family == AF_UNIX) {
        if (len < unix_maxlen && len > 0) {
            char *cp = (char*)target_saddr;

            if ( cp[len-1] && !cp[len] )
                len++;
        }
        if (len > unix_maxlen)
            len = unix_maxlen;
    }

    memcpy(addr, target_saddr, len);
    addr->sa_family = sa_family;
    if (sa_family == AF_NETLINK) {
        struct sockaddr_nl *nladdr;

        nladdr = (struct sockaddr_nl *)addr;
        nladdr->nl_pid = tswap32(nladdr->nl_pid);
        nladdr->nl_groups = tswap32(nladdr->nl_groups);
    } else if (sa_family == AF_PACKET) {
        struct target_sockaddr_ll *lladdr;

        lladdr = (struct target_sockaddr_ll *)addr;
        lladdr->sll_ifindex = tswap32(lladdr->sll_ifindex);
        lladdr->sll_hatype = tswap16(lladdr->sll_hatype);
    }
    unlock_user(target_saddr, target_addr, 0);

    return 0;
}

static inline abi_long host_to_target_sockaddr(abi_ulong target_addr,
                                               struct sockaddr *addr,
                                               socklen_t len)
{
    struct target_sockaddr *target_saddr;

    if (len == 0) {
        return 0;
    }
    assert(addr);

    target_saddr = lock_user(VERIFY_WRITE, target_addr, len, 0);
    if (!target_saddr)
        return -TARGET_EFAULT;
    memcpy(target_saddr, addr, len);
    if (len >= offsetof(struct target_sockaddr, sa_family) +
        sizeof(target_saddr->sa_family)) {
        target_saddr->sa_family = tswap16(addr->sa_family);
    }
    if (addr->sa_family == AF_NETLINK && len >= sizeof(struct sockaddr_nl)) {
        struct sockaddr_nl *target_nl = (struct sockaddr_nl *)target_saddr;
        target_nl->nl_pid = tswap32(target_nl->nl_pid);
        target_nl->nl_groups = tswap32(target_nl->nl_groups);
    } else if (addr->sa_family == AF_PACKET) {
        struct sockaddr_ll *target_ll = (struct sockaddr_ll *)target_saddr;
        target_ll->sll_ifindex = tswap32(target_ll->sll_ifindex);
        target_ll->sll_hatype = tswap16(target_ll->sll_hatype);
    } else if (addr->sa_family == AF_INET6 &&
               len >= sizeof(struct target_sockaddr_in6)) {
        struct target_sockaddr_in6 *target_in6 =
               (struct target_sockaddr_in6 *)target_saddr;
        target_in6->sin6_scope_id = tswap16(target_in6->sin6_scope_id);
    }
    unlock_user(target_saddr, target_addr, len);

    return 0;
}

static inline abi_long target_to_host_cmsg(struct msghdr *msgh,
                                           struct target_msghdr *target_msgh)
{
    struct cmsghdr *cmsg = CMSG_FIRSTHDR(msgh);
    abi_long msg_controllen;
    abi_ulong target_cmsg_addr;
    struct target_cmsghdr *target_cmsg, *target_cmsg_start;
    socklen_t space = 0;
    
    msg_controllen = tswapal(target_msgh->msg_controllen);
    if (msg_controllen < sizeof (struct target_cmsghdr)) 
        goto the_end;
    target_cmsg_addr = tswapal(target_msgh->msg_control);
    target_cmsg = lock_user(VERIFY_READ, target_cmsg_addr, msg_controllen, 1);
    target_cmsg_start = target_cmsg;
    if (!target_cmsg)
        return -TARGET_EFAULT;

    while (cmsg && target_cmsg) {
        void *data = CMSG_DATA(cmsg);
        void *target_data = TARGET_CMSG_DATA(target_cmsg);

        int len = tswapal(target_cmsg->cmsg_len)
            - sizeof(struct target_cmsghdr);

        space += CMSG_SPACE(len);
        if (space > msgh->msg_controllen) {
            space -= CMSG_SPACE(len);
            /* This is a QEMU bug, since we allocated the payload
             * area ourselves (unlike overflow in host-to-target
             * conversion, which is just the guest giving us a buffer
             * that's too small). It can't happen for the payload types
             * we currently support; if it becomes an issue in future
             * we would need to improve our allocation strategy to
             * something more intelligent than "twice the size of the
             * target buffer we're reading from".
             */
            gemu_log("Host cmsg overflow\n");
            break;
        }

        if (tswap32(target_cmsg->cmsg_level) == TARGET_SOL_SOCKET) {
            cmsg->cmsg_level = SOL_SOCKET;
        } else {
            cmsg->cmsg_level = tswap32(target_cmsg->cmsg_level);
        }
        cmsg->cmsg_type = tswap32(target_cmsg->cmsg_type);
        cmsg->cmsg_len = CMSG_LEN(len);

        if (cmsg->cmsg_level == SOL_SOCKET && cmsg->cmsg_type == SCM_RIGHTS) {
            int *fd = (int *)data;
            int *target_fd = (int *)target_data;
            int i, numfds = len / sizeof(int);

            for (i = 0; i < numfds; i++) {
                __get_user(fd[i], target_fd + i);
            }
        } else if (cmsg->cmsg_level == SOL_SOCKET
               &&  cmsg->cmsg_type == SCM_CREDENTIALS) {
            struct ucred *cred = (struct ucred *)data;
            struct target_ucred *target_cred =
                (struct target_ucred *)target_data;

            __get_user(cred->pid, &target_cred->pid);
            __get_user(cred->uid, &target_cred->uid);
            __get_user(cred->gid, &target_cred->gid);
        } else {
            gemu_log("Unsupported ancillary data: %d/%d\n",
                                        cmsg->cmsg_level, cmsg->cmsg_type);
            memcpy(data, target_data, len);
        }

        cmsg = CMSG_NXTHDR(msgh, cmsg);
        target_cmsg = TARGET_CMSG_NXTHDR(target_msgh, target_cmsg,
                                         target_cmsg_start);
    }
    unlock_user(target_cmsg, target_cmsg_addr, 0);
 the_end:
    msgh->msg_controllen = space;
    return 0;
}

static inline abi_long host_to_target_cmsg(struct target_msghdr *target_msgh,
                                           struct msghdr *msgh)
{
    struct cmsghdr *cmsg = CMSG_FIRSTHDR(msgh);
    abi_long msg_controllen;
    abi_ulong target_cmsg_addr;
    struct target_cmsghdr *target_cmsg, *target_cmsg_start;
    socklen_t space = 0;

    msg_controllen = tswapal(target_msgh->msg_controllen);
    if (msg_controllen < sizeof (struct target_cmsghdr)) 
        goto the_end;
    target_cmsg_addr = tswapal(target_msgh->msg_control);
    target_cmsg = lock_user(VERIFY_WRITE, target_cmsg_addr, msg_controllen, 0);
    target_cmsg_start = target_cmsg;
    if (!target_cmsg)
        return -TARGET_EFAULT;

    while (cmsg && target_cmsg) {
        void *data = CMSG_DATA(cmsg);
        void *target_data = TARGET_CMSG_DATA(target_cmsg);

        int len = cmsg->cmsg_len - sizeof(struct cmsghdr);
        int tgt_len, tgt_space;

        /* We never copy a half-header but may copy half-data;
         * this is Linux's behaviour in put_cmsg(). Note that
         * truncation here is a guest problem (which we report
         * to the guest via the CTRUNC bit), unlike truncation
         * in target_to_host_cmsg, which is a QEMU bug.
         */
        if (msg_controllen < sizeof(struct target_cmsghdr)) {
            target_msgh->msg_flags |= tswap32(MSG_CTRUNC);
            break;
        }

        if (cmsg->cmsg_level == SOL_SOCKET) {
            target_cmsg->cmsg_level = tswap32(TARGET_SOL_SOCKET);
        } else {
            target_cmsg->cmsg_level = tswap32(cmsg->cmsg_level);
        }
        target_cmsg->cmsg_type = tswap32(cmsg->cmsg_type);

        /* Payload types which need a different size of payload on
         * the target must adjust tgt_len here.
         */
        tgt_len = len;
        switch (cmsg->cmsg_level) {
        case SOL_SOCKET:
            switch (cmsg->cmsg_type) {
            case SO_TIMESTAMP:
                tgt_len = sizeof(struct target_timeval);
                break;
            default:
                break;
            }
            break;
        default:
            break;
        }

        if (msg_controllen < TARGET_CMSG_LEN(tgt_len)) {
            target_msgh->msg_flags |= tswap32(MSG_CTRUNC);
            tgt_len = msg_controllen - sizeof(struct target_cmsghdr);
        }

        /* We must now copy-and-convert len bytes of payload
         * into tgt_len bytes of destination space. Bear in mind
         * that in both source and destination we may be dealing
         * with a truncated value!
         */
        switch (cmsg->cmsg_level) {
        case SOL_SOCKET:
            switch (cmsg->cmsg_type) {
            case SCM_RIGHTS:
            {
                int *fd = (int *)data;
                int *target_fd = (int *)target_data;
                int i, numfds = tgt_len / sizeof(int);

                for (i = 0; i < numfds; i++) {
                    __put_user(fd[i], target_fd + i);
                }
                break;
            }
            case SO_TIMESTAMP:
            {
                struct timeval *tv = (struct timeval *)data;
                struct target_timeval *target_tv =
                    (struct target_timeval *)target_data;

                if (len != sizeof(struct timeval) ||
                    tgt_len != sizeof(struct target_timeval)) {
                    goto unimplemented;
                }

                /* copy struct timeval to target */
                __put_user(tv->tv_sec, &target_tv->tv_sec);
                __put_user(tv->tv_usec, &target_tv->tv_usec);
                break;
            }
            case SCM_CREDENTIALS:
            {
                struct ucred *cred = (struct ucred *)data;
                struct target_ucred *target_cred =
                    (struct target_ucred *)target_data;

                __put_user(cred->pid, &target_cred->pid);
                __put_user(cred->uid, &target_cred->uid);
                __put_user(cred->gid, &target_cred->gid);
                break;
            }
            default:
                goto unimplemented;
            }
            break;

        case SOL_IP:
            switch (cmsg->cmsg_type) {
            case IP_TTL:
            {
                uint32_t *v = (uint32_t *)data;
                uint32_t *t_int = (uint32_t *)target_data;

                if (len != sizeof(uint32_t) ||
                    tgt_len != sizeof(uint32_t)) {
                    goto unimplemented;
                }
                __put_user(*v, t_int);
                break;
            }
            case IP_RECVERR:
            {
                struct errhdr_t {
                   struct sock_extended_err ee;
                   struct sockaddr_in offender;
                };
                struct errhdr_t *errh = (struct errhdr_t *)data;
                struct errhdr_t *target_errh =
                    (struct errhdr_t *)target_data;

                if (len != sizeof(struct errhdr_t) ||
                    tgt_len != sizeof(struct errhdr_t)) {
                    goto unimplemented;
                }
                __put_user(errh->ee.ee_errno, &target_errh->ee.ee_errno);
                __put_user(errh->ee.ee_origin, &target_errh->ee.ee_origin);
                __put_user(errh->ee.ee_type,  &target_errh->ee.ee_type);
                __put_user(errh->ee.ee_code, &target_errh->ee.ee_code);
                __put_user(errh->ee.ee_pad, &target_errh->ee.ee_pad);
                __put_user(errh->ee.ee_info, &target_errh->ee.ee_info);
                __put_user(errh->ee.ee_data, &target_errh->ee.ee_data);
                host_to_target_sockaddr((unsigned long) &target_errh->offender,
                    (void *) &errh->offender, sizeof(errh->offender));
                break;
            }
            default:
                goto unimplemented;
            }
            break;

        case SOL_IPV6:
            switch (cmsg->cmsg_type) {
            case IPV6_HOPLIMIT:
            {
                uint32_t *v = (uint32_t *)data;
                uint32_t *t_int = (uint32_t *)target_data;

                if (len != sizeof(uint32_t) ||
                    tgt_len != sizeof(uint32_t)) {
                    goto unimplemented;
                }
                __put_user(*v, t_int);
                break;
            }
            case IPV6_RECVERR:
            {
                struct errhdr6_t {
                   struct sock_extended_err ee;
                   struct sockaddr_in6 offender;
                };
                struct errhdr6_t *errh = (struct errhdr6_t *)data;
                struct errhdr6_t *target_errh =
                    (struct errhdr6_t *)target_data;

                if (len != sizeof(struct errhdr6_t) ||
                    tgt_len != sizeof(struct errhdr6_t)) {
                    goto unimplemented;
                }
                __put_user(errh->ee.ee_errno, &target_errh->ee.ee_errno);
                __put_user(errh->ee.ee_origin, &target_errh->ee.ee_origin);
                __put_user(errh->ee.ee_type,  &target_errh->ee.ee_type);
                __put_user(errh->ee.ee_code, &target_errh->ee.ee_code);
                __put_user(errh->ee.ee_pad, &target_errh->ee.ee_pad);
                __put_user(errh->ee.ee_info, &target_errh->ee.ee_info);
                __put_user(errh->ee.ee_data, &target_errh->ee.ee_data);
                host_to_target_sockaddr((unsigned long) &target_errh->offender,
                    (void *) &errh->offender, sizeof(errh->offender));
                break;
            }
            default:
                goto unimplemented;
            }
            break;

        default:
        unimplemented:
            gemu_log("Unsupported ancillary data: %d/%d\n",
                                        cmsg->cmsg_level, cmsg->cmsg_type);
            memcpy(target_data, data, MIN(len, tgt_len));
            if (tgt_len > len) {
                memset(target_data + len, 0, tgt_len - len);
            }
        }

        target_cmsg->cmsg_len = tswapal(TARGET_CMSG_LEN(tgt_len));
        tgt_space = TARGET_CMSG_SPACE(tgt_len);
        if (msg_controllen < tgt_space) {
            tgt_space = msg_controllen;
        }
        msg_controllen -= tgt_space;
        space += tgt_space;
        cmsg = CMSG_NXTHDR(msgh, cmsg);
        target_cmsg = TARGET_CMSG_NXTHDR(target_msgh, target_cmsg,
                                         target_cmsg_start);
    }
    unlock_user(target_cmsg, target_cmsg_addr, space);
 the_end:
    target_msgh->msg_controllen = tswapal(space);
    return 0;
}

/* do_setsockopt() Must return target values and target errnos. */
static abi_long do_setsockopt(int sockfd, int level, int optname,
                              abi_ulong optval_addr, socklen_t optlen)
{
    abi_long ret;
    int val;
    struct ip_mreqn *ip_mreq;
    struct ip_mreq_source *ip_mreq_source;

    switch(level) {
    case SOL_TCP:
        /* TCP options all take an 'int' value.  */
        if (optlen < sizeof(uint32_t))
            return -TARGET_EINVAL;

        if (get_user_u32(val, optval_addr))
            return -TARGET_EFAULT;
        ret = get_errno(setsockopt(sockfd, level, optname, &val, sizeof(val)));
        break;
    case SOL_IP:
        switch(optname) {
        case IP_TOS:
        case IP_TTL:
        case IP_HDRINCL:
        case IP_ROUTER_ALERT:
        case IP_RECVOPTS:
        case IP_RETOPTS:
        case IP_PKTINFO:
        case IP_MTU_DISCOVER:
        case IP_RECVERR:
        case IP_RECVTTL:
        case IP_RECVTOS:
#ifdef IP_FREEBIND
        case IP_FREEBIND:
#endif
        case IP_MULTICAST_TTL:
        case IP_MULTICAST_LOOP:
            val = 0;
            if (optlen >= sizeof(uint32_t)) {
                if (get_user_u32(val, optval_addr))
                    return -TARGET_EFAULT;
            } else if (optlen >= 1) {
                if (get_user_u8(val, optval_addr))
                    return -TARGET_EFAULT;
            }
            ret = get_errno(setsockopt(sockfd, level, optname, &val, sizeof(val)));
            break;
        case IP_ADD_MEMBERSHIP:
        case IP_DROP_MEMBERSHIP:
            if (optlen < sizeof (struct target_ip_mreq) ||
                optlen > sizeof (struct target_ip_mreqn))
                return -TARGET_EINVAL;

            ip_mreq = (struct ip_mreqn *) alloca(optlen);
            target_to_host_ip_mreq(ip_mreq, optval_addr, optlen);
            ret = get_errno(setsockopt(sockfd, level, optname, ip_mreq, optlen));
            break;

        case IP_BLOCK_SOURCE:
        case IP_UNBLOCK_SOURCE:
        case IP_ADD_SOURCE_MEMBERSHIP:
        case IP_DROP_SOURCE_MEMBERSHIP:
            if (optlen != sizeof (struct target_ip_mreq_source))
                return -TARGET_EINVAL;

            ip_mreq_source = lock_user(VERIFY_READ, optval_addr, optlen, 1);
            ret = get_errno(setsockopt(sockfd, level, optname, ip_mreq_source, optlen));
            unlock_user (ip_mreq_source, optval_addr, 0);
            break;

        default:
            goto unimplemented;
        }
        break;
    case SOL_IPV6:
        switch (optname) {
        case IPV6_MTU_DISCOVER:
        case IPV6_MTU:
        case IPV6_V6ONLY:
        case IPV6_RECVPKTINFO:
        case IPV6_UNICAST_HOPS:
        case IPV6_MULTICAST_HOPS:
        case IPV6_MULTICAST_LOOP:
        case IPV6_RECVERR:
        case IPV6_RECVHOPLIMIT:
        case IPV6_2292HOPLIMIT:
        case IPV6_CHECKSUM:
            val = 0;
            if (optlen < sizeof(uint32_t)) {
                return -TARGET_EINVAL;
            }
            if (get_user_u32(val, optval_addr)) {
                return -TARGET_EFAULT;
            }
            ret = get_errno(setsockopt(sockfd, level, optname,
                                       &val, sizeof(val)));
            break;
        case IPV6_PKTINFO:
        {
            struct in6_pktinfo pki;

            if (optlen < sizeof(pki)) {
                return -TARGET_EINVAL;
            }

            if (copy_from_user(&pki, optval_addr, sizeof(pki))) {
                return -TARGET_EFAULT;
            }

            pki.ipi6_ifindex = tswap32(pki.ipi6_ifindex);

            ret = get_errno(setsockopt(sockfd, level, optname,
                                       &pki, sizeof(pki)));
            break;
        }
        default:
            goto unimplemented;
        }
        break;
    case SOL_ICMPV6:
        switch (optname) {
        case ICMPV6_FILTER:
        {
            struct icmp6_filter icmp6f;

            if (optlen > sizeof(icmp6f)) {
                optlen = sizeof(icmp6f);
            }

            if (copy_from_user(&icmp6f, optval_addr, optlen)) {
                return -TARGET_EFAULT;
            }

            for (val = 0; val < 8; val++) {
                icmp6f.data[val] = tswap32(icmp6f.data[val]);
            }

            ret = get_errno(setsockopt(sockfd, level, optname,
                                       &icmp6f, optlen));
            break;
        }
        default:
            goto unimplemented;
        }
        break;
    case SOL_RAW:
        switch (optname) {
        case ICMP_FILTER:
        case IPV6_CHECKSUM:
            /* those take an u32 value */
            if (optlen < sizeof(uint32_t)) {
                return -TARGET_EINVAL;
            }

            if (get_user_u32(val, optval_addr)) {
                return -TARGET_EFAULT;
            }
            ret = get_errno(setsockopt(sockfd, level, optname,
                                       &val, sizeof(val)));
            break;

        default:
            goto unimplemented;
        }
        break;
    case TARGET_SOL_SOCKET:
        switch (optname) {
        case TARGET_SO_RCVTIMEO:
        {
                struct timeval tv;

                optname = SO_RCVTIMEO;

set_timeout:
                if (optlen != sizeof(struct target_timeval)) {
                    return -TARGET_EINVAL;
                }

                if (copy_from_user_timeval(&tv, optval_addr)) {
                    return -TARGET_EFAULT;
                }

                ret = get_errno(setsockopt(sockfd, SOL_SOCKET, optname,
                                &tv, sizeof(tv)));
                return ret;
        }
        case TARGET_SO_SNDTIMEO:
                optname = SO_SNDTIMEO;
                goto set_timeout;
        case TARGET_SO_ATTACH_FILTER:
        {
                struct target_sock_fprog *tfprog;
                struct target_sock_filter *tfilter;
                struct sock_fprog fprog;
                struct sock_filter *filter;
                int i;

                if (optlen != sizeof(*tfprog)) {
                    return -TARGET_EINVAL;
                }
                if (!lock_user_struct(VERIFY_READ, tfprog, optval_addr, 0)) {
                    return -TARGET_EFAULT;
                }
                if (!lock_user_struct(VERIFY_READ, tfilter,
                                      tswapal(tfprog->filter), 0)) {
                    unlock_user_struct(tfprog, optval_addr, 1);
                    return -TARGET_EFAULT;
                }

                fprog.len = tswap16(tfprog->len);
                filter = g_try_new(struct sock_filter, fprog.len);
                if (filter == NULL) {
                    unlock_user_struct(tfilter, tfprog->filter, 1);
                    unlock_user_struct(tfprog, optval_addr, 1);
                    return -TARGET_ENOMEM;
                }
                for (i = 0; i < fprog.len; i++) {
                    filter[i].code = tswap16(tfilter[i].code);
                    filter[i].jt = tfilter[i].jt;
                    filter[i].jf = tfilter[i].jf;
                    filter[i].k = tswap32(tfilter[i].k);

                }
                fprog.filter = filter;

                ret = get_errno(setsockopt(sockfd, SOL_SOCKET,
                                SO_ATTACH_FILTER, &fprog, sizeof(fprog)));
                g_free(filter);

                unlock_user_struct(tfilter, tfprog->filter, 1);
                unlock_user_struct(tfprog, optval_addr, 1);
                return ret;
        }
        case TARGET_SO_BINDTODEVICE:
        {
                char *dev_ifname, *addr_ifname;

                if (optlen > IFNAMSIZ - 1) {
                    optlen = IFNAMSIZ - 1;
                }
                dev_ifname = lock_user(VERIFY_READ, optval_addr, optlen, 1);
                if (!dev_ifname) {
                    return -TARGET_EFAULT;
                }
                optname = SO_BINDTODEVICE;
                addr_ifname = alloca(IFNAMSIZ);
                memcpy(addr_ifname, dev_ifname, optlen);
                addr_ifname[optlen] = 0;
                ret = get_errno(setsockopt(sockfd, SOL_SOCKET, optname,
                                           addr_ifname, optlen));
                unlock_user (dev_ifname, optval_addr, 0);
                return ret;
        }
        case TARGET_SO_LINGER:
        {
                struct linger lg;
                struct target_linger *tlg;

                if (optlen != sizeof(struct target_linger)) {
                    return -TARGET_EINVAL;
                }
                if (!lock_user_struct(VERIFY_READ, tlg, optval_addr, 1)) {
                    return -TARGET_EFAULT;
                }
                __get_user(lg.l_onoff, &tlg->l_onoff);
                __get_user(lg.l_linger, &tlg->l_linger);
                ret = get_errno(setsockopt(sockfd, SOL_SOCKET, SO_LINGER,
                                &lg, sizeof(lg)));
                unlock_user_struct(tlg, optval_addr, 0);
                return ret;
        }
            /* Options with 'int' argument.  */
        case TARGET_SO_DEBUG:
                optname = SO_DEBUG;
                break;
        case TARGET_SO_REUSEADDR:
                optname = SO_REUSEADDR;
                break;
#ifdef SO_REUSEPORT
        case TARGET_SO_REUSEPORT:
                optname = SO_REUSEPORT;
                break;
#endif
        case TARGET_SO_TYPE:
                optname = SO_TYPE;
                break;
        case TARGET_SO_ERROR:
                optname = SO_ERROR;
                break;
        case TARGET_SO_DONTROUTE:
                optname = SO_DONTROUTE;
                break;
        case TARGET_SO_BROADCAST:
                optname = SO_BROADCAST;
                break;
        case TARGET_SO_SNDBUF:
                optname = SO_SNDBUF;
                break;
        case TARGET_SO_SNDBUFFORCE:
                optname = SO_SNDBUFFORCE;
                break;
        case TARGET_SO_RCVBUF:
                optname = SO_RCVBUF;
                break;
        case TARGET_SO_RCVBUFFORCE:
                optname = SO_RCVBUFFORCE;
                break;
        case TARGET_SO_KEEPALIVE:
                optname = SO_KEEPALIVE;
                break;
        case TARGET_SO_OOBINLINE:
                optname = SO_OOBINLINE;
                break;
        case TARGET_SO_NO_CHECK:
                optname = SO_NO_CHECK;
                break;
        case TARGET_SO_PRIORITY:
                optname = SO_PRIORITY;
                break;
#ifdef SO_BSDCOMPAT
        case TARGET_SO_BSDCOMPAT:
                optname = SO_BSDCOMPAT;
                break;
#endif
        case TARGET_SO_PASSCRED:
                optname = SO_PASSCRED;
                break;
        case TARGET_SO_PASSSEC:
                optname = SO_PASSSEC;
                break;
        case TARGET_SO_TIMESTAMP:
                optname = SO_TIMESTAMP;
                break;
        case TARGET_SO_RCVLOWAT:
                optname = SO_RCVLOWAT;
                break;
        default:
            goto unimplemented;
        }
        if (optlen < sizeof(uint32_t))
            return -TARGET_EINVAL;

        if (get_user_u32(val, optval_addr))
            return -TARGET_EFAULT;
        ret = get_errno(setsockopt(sockfd, SOL_SOCKET, optname, &val, sizeof(val)));
        break;
    default:
    unimplemented:
        gemu_log("Unsupported setsockopt level=%d optname=%d\n", level, optname);
        ret = -TARGET_ENOPROTOOPT;
    }
    return ret;
}

/* do_getsockopt() Must return target values and target errnos. */
static abi_long do_getsockopt(int sockfd, int level, int optname,
                              abi_ulong optval_addr, abi_ulong optlen)
{
    abi_long ret;
    int len, val;
    socklen_t lv;

    switch(level) {
    case TARGET_SOL_SOCKET:
        level = SOL_SOCKET;
        switch (optname) {
        /* These don't just return a single integer */
        case TARGET_SO_RCVTIMEO:
        case TARGET_SO_SNDTIMEO:
        case TARGET_SO_PEERNAME:
            goto unimplemented;
        case TARGET_SO_PEERCRED: {
            struct ucred cr;
            socklen_t crlen;
            struct target_ucred *tcr;

            if (get_user_u32(len, optlen)) {
                return -TARGET_EFAULT;
            }
            if (len < 0) {
                return -TARGET_EINVAL;
            }

            crlen = sizeof(cr);
            ret = get_errno(getsockopt(sockfd, level, SO_PEERCRED,
                                       &cr, &crlen));
            if (ret < 0) {
                return ret;
            }
            if (len > crlen) {
                len = crlen;
            }
            if (!lock_user_struct(VERIFY_WRITE, tcr, optval_addr, 0)) {
                return -TARGET_EFAULT;
            }
            __put_user(cr.pid, &tcr->pid);
            __put_user(cr.uid, &tcr->uid);
            __put_user(cr.gid, &tcr->gid);
            unlock_user_struct(tcr, optval_addr, 1);
            if (put_user_u32(len, optlen)) {
                return -TARGET_EFAULT;
            }
            break;
        }
        case TARGET_SO_LINGER:
        {
            struct linger lg;
            socklen_t lglen;
            struct target_linger *tlg;

            if (get_user_u32(len, optlen)) {
                return -TARGET_EFAULT;
            }
            if (len < 0) {
                return -TARGET_EINVAL;
            }

            lglen = sizeof(lg);
            ret = get_errno(getsockopt(sockfd, level, SO_LINGER,
                                       &lg, &lglen));
            if (ret < 0) {
                return ret;
            }
            if (len > lglen) {
                len = lglen;
            }
            if (!lock_user_struct(VERIFY_WRITE, tlg, optval_addr, 0)) {
                return -TARGET_EFAULT;
            }
            __put_user(lg.l_onoff, &tlg->l_onoff);
            __put_user(lg.l_linger, &tlg->l_linger);
            unlock_user_struct(tlg, optval_addr, 1);
            if (put_user_u32(len, optlen)) {
                return -TARGET_EFAULT;
            }
            break;
        }
        /* Options with 'int' argument.  */
        case TARGET_SO_DEBUG:
            optname = SO_DEBUG;
            goto int_case;
        case TARGET_SO_REUSEADDR:
            optname = SO_REUSEADDR;
            goto int_case;
#ifdef SO_REUSEPORT
        case TARGET_SO_REUSEPORT:
            optname = SO_REUSEPORT;
            goto int_case;
#endif
        case TARGET_SO_TYPE:
            optname = SO_TYPE;
            goto int_case;
        case TARGET_SO_ERROR:
            optname = SO_ERROR;
            goto int_case;
        case TARGET_SO_DONTROUTE:
            optname = SO_DONTROUTE;
            goto int_case;
        case TARGET_SO_BROADCAST:
            optname = SO_BROADCAST;
            goto int_case;
        case TARGET_SO_SNDBUF:
            optname = SO_SNDBUF;
            goto int_case;
        case TARGET_SO_RCVBUF:
            optname = SO_RCVBUF;
            goto int_case;
        case TARGET_SO_KEEPALIVE:
            optname = SO_KEEPALIVE;
            goto int_case;
        case TARGET_SO_OOBINLINE:
            optname = SO_OOBINLINE;
            goto int_case;
        case TARGET_SO_NO_CHECK:
            optname = SO_NO_CHECK;
            goto int_case;
        case TARGET_SO_PRIORITY:
            optname = SO_PRIORITY;
            goto int_case;
#ifdef SO_BSDCOMPAT
        case TARGET_SO_BSDCOMPAT:
            optname = SO_BSDCOMPAT;
            goto int_case;
#endif
        case TARGET_SO_PASSCRED:
            optname = SO_PASSCRED;
            goto int_case;
        case TARGET_SO_TIMESTAMP:
            optname = SO_TIMESTAMP;
            goto int_case;
        case TARGET_SO_RCVLOWAT:
            optname = SO_RCVLOWAT;
            goto int_case;
        case TARGET_SO_ACCEPTCONN:
            optname = SO_ACCEPTCONN;
            goto int_case;
        default:
            goto int_case;
        }
        break;
    case SOL_TCP:
        /* TCP options all take an 'int' value.  */
    int_case:
        if (get_user_u32(len, optlen))
            return -TARGET_EFAULT;
        if (len < 0)
            return -TARGET_EINVAL;
        lv = sizeof(lv);
        ret = get_errno(getsockopt(sockfd, level, optname, &val, &lv));
        if (ret < 0)
            return ret;
        if (optname == SO_TYPE) {
            val = host_to_target_sock_type(val);
        }
        if (len > lv)
            len = lv;
        if (len == 4) {
            if (put_user_u32(val, optval_addr))
                return -TARGET_EFAULT;
        } else {
            if (put_user_u8(val, optval_addr))
                return -TARGET_EFAULT;
        }
        if (put_user_u32(len, optlen))
            return -TARGET_EFAULT;
        break;
    case SOL_IP:
        switch(optname) {
        case IP_TOS:
        case IP_TTL:
        case IP_HDRINCL:
        case IP_ROUTER_ALERT:
        case IP_RECVOPTS:
        case IP_RETOPTS:
        case IP_PKTINFO:
        case IP_MTU_DISCOVER:
        case IP_RECVERR:
        case IP_RECVTOS:
#ifdef IP_FREEBIND
        case IP_FREEBIND:
#endif
        case IP_MULTICAST_TTL:
        case IP_MULTICAST_LOOP:
            if (get_user_u32(len, optlen))
                return -TARGET_EFAULT;
            if (len < 0)
                return -TARGET_EINVAL;
            lv = sizeof(lv);
            ret = get_errno(getsockopt(sockfd, level, optname, &val, &lv));
            if (ret < 0)
                return ret;
            if (len < sizeof(int) && len > 0 && val >= 0 && val < 255) {
                len = 1;
                if (put_user_u32(len, optlen)
                    || put_user_u8(val, optval_addr))
                    return -TARGET_EFAULT;
            } else {
                if (len > sizeof(int))
                    len = sizeof(int);
                if (put_user_u32(len, optlen)
                    || put_user_u32(val, optval_addr))
                    return -TARGET_EFAULT;
            }
            break;
        default:
            ret = -TARGET_ENOPROTOOPT;
            break;
        }
        break;
    case SOL_IPV6:
        switch (optname) {
        case IPV6_MTU_DISCOVER:
        case IPV6_MTU:
        case IPV6_V6ONLY:
        case IPV6_RECVPKTINFO:
        case IPV6_UNICAST_HOPS:
        case IPV6_MULTICAST_HOPS:
        case IPV6_MULTICAST_LOOP:
        case IPV6_RECVERR:
        case IPV6_RECVHOPLIMIT:
        case IPV6_2292HOPLIMIT:
        case IPV6_CHECKSUM:
            if (get_user_u32(len, optlen))
                return -TARGET_EFAULT;
            if (len < 0)
                return -TARGET_EINVAL;
            lv = sizeof(lv);
            ret = get_errno(getsockopt(sockfd, level, optname, &val, &lv));
            if (ret < 0)
                return ret;
            if (len < sizeof(int) && len > 0 && val >= 0 && val < 255) {
                len = 1;
                if (put_user_u32(len, optlen)
                    || put_user_u8(val, optval_addr))
                    return -TARGET_EFAULT;
            } else {
                if (len > sizeof(int))
                    len = sizeof(int);
                if (put_user_u32(len, optlen)
                    || put_user_u32(val, optval_addr))
                    return -TARGET_EFAULT;
            }
            break;
        default:
            ret = -TARGET_ENOPROTOOPT;
            break;
        }
        break;
    default:
    unimplemented:
        gemu_log("getsockopt level=%d optname=%d not yet supported\n",
                 level, optname);
        ret = -TARGET_EOPNOTSUPP;
        break;
    }
    return ret;
}

/* Convert target low/high pair representing file offset into the host
 * low/high pair. This function doesn't handle offsets bigger than 64 bits
 * as the kernel doesn't handle them either.
 */
static void target_to_host_low_high(abi_ulong tlow,
                                    abi_ulong thigh,
                                    unsigned long *hlow,
                                    unsigned long *hhigh)
{
    uint64_t off = tlow |
        ((unsigned long long)thigh << TARGET_LONG_BITS / 2) <<
        TARGET_LONG_BITS / 2;

    *hlow = off;
    *hhigh = (off >> HOST_LONG_BITS / 2) >> HOST_LONG_BITS / 2;
}

static struct iovec *lock_iovec(int type, abi_ulong target_addr,
                                abi_ulong count, int copy)
{
    struct target_iovec *target_vec;
    struct iovec *vec;
    abi_ulong total_len, max_len;
    int i;
    int err = 0;
    bool bad_address = false;

    if (count == 0) {
        errno = 0;
        return NULL;
    }
    if (count > IOV_MAX) {
        errno = EINVAL;
        return NULL;
    }

    vec = g_try_new0(struct iovec, count);
    if (vec == NULL) {
        errno = ENOMEM;
        return NULL;
    }

    target_vec = lock_user(VERIFY_READ, target_addr,
                           count * sizeof(struct target_iovec), 1);
    if (target_vec == NULL) {
        err = EFAULT;
        goto fail2;
    }

    /* ??? If host page size > target page size, this will result in a
       value larger than what we can actually support.  */
    max_len = 0x7fffffff & TARGET_PAGE_MASK;
    total_len = 0;

    for (i = 0; i < count; i++) {
        abi_ulong base = tswapal(target_vec[i].iov_base);
        abi_long len = tswapal(target_vec[i].iov_len);

        if (len < 0) {
            err = EINVAL;
            goto fail;
        } else if (len == 0) {
            /* Zero length pointer is ignored.  */
            vec[i].iov_base = 0;
        } else {
            vec[i].iov_base = lock_user(type, base, len, copy);
            /* If the first buffer pointer is bad, this is a fault.  But
             * subsequent bad buffers will result in a partial write; this
             * is realized by filling the vector with null pointers and
             * zero lengths. */
            if (!vec[i].iov_base) {
                if (i == 0) {
                    err = EFAULT;
                    goto fail;
                } else {
                    bad_address = true;
                }
            }
            if (bad_address) {
                len = 0;
            }
            if (len > max_len - total_len) {
                len = max_len - total_len;
            }
        }
        vec[i].iov_len = len;
        total_len += len;
    }

    unlock_user(target_vec, target_addr, 0);
    return vec;

 fail:
    while (--i >= 0) {
        if (tswapal(target_vec[i].iov_len) > 0) {
            unlock_user(vec[i].iov_base, tswapal(target_vec[i].iov_base), 0);
        }
    }
    unlock_user(target_vec, target_addr, 0);
 fail2:
    g_free(vec);
    errno = err;
    return NULL;
}

static void unlock_iovec(struct iovec *vec, abi_ulong target_addr,
                         abi_ulong count, int copy)
{
    struct target_iovec *target_vec;
    int i;

    target_vec = lock_user(VERIFY_READ, target_addr,
                           count * sizeof(struct target_iovec), 1);
    if (target_vec) {
        for (i = 0; i < count; i++) {
            abi_ulong base = tswapal(target_vec[i].iov_base);
            abi_long len = tswapal(target_vec[i].iov_len);
            if (len < 0) {
                break;
            }
            unlock_user(vec[i].iov_base, base, copy ? vec[i].iov_len : 0);
        }
        unlock_user(target_vec, target_addr, 0);
    }

    g_free(vec);
}

static inline int target_to_host_sock_type(int *type)
{
    int host_type = 0;
    int target_type = *type;

    switch (target_type & TARGET_SOCK_TYPE_MASK) {
    case TARGET_SOCK_DGRAM:
        host_type = SOCK_DGRAM;
        break;
    case TARGET_SOCK_STREAM:
        host_type = SOCK_STREAM;
        break;
    default:
        host_type = target_type & TARGET_SOCK_TYPE_MASK;
        break;
    }
    if (target_type & TARGET_SOCK_CLOEXEC) {
#if defined(SOCK_CLOEXEC)
        host_type |= SOCK_CLOEXEC;
#else
        return -TARGET_EINVAL;
#endif
    }
    if (target_type & TARGET_SOCK_NONBLOCK) {
#if defined(SOCK_NONBLOCK)
        host_type |= SOCK_NONBLOCK;
#elif !defined(O_NONBLOCK)
        return -TARGET_EINVAL;
#endif
    }
    *type = host_type;
    return 0;
}

/* Try to emulate socket type flags after socket creation.  */
static int sock_flags_fixup(int fd, int target_type)
{
#if !defined(SOCK_NONBLOCK) && defined(O_NONBLOCK)
    if (target_type & TARGET_SOCK_NONBLOCK) {
        int flags = fcntl(fd, F_GETFL);
        if (fcntl(fd, F_SETFL, O_NONBLOCK | flags) == -1) {
            close(fd);
            return -TARGET_EINVAL;
        }
    }
#endif
    return fd;
}

/* do_socket() Must return target values and target errnos. */
static abi_long do_socket(int domain, int type, int protocol)
{
    int target_type = type;
    int ret;

    ret = target_to_host_sock_type(&type);
    if (ret) {
        return ret;
    }

    if (domain == PF_NETLINK && !(
#ifdef CONFIG_RTNETLINK
         protocol == NETLINK_ROUTE ||
#endif
         protocol == NETLINK_KOBJECT_UEVENT ||
         protocol == NETLINK_AUDIT)) {
        return -EPFNOSUPPORT;
    }

    if (domain == AF_PACKET ||
        (domain == AF_INET && type == SOCK_PACKET)) {
        protocol = tswap16(protocol);
    }

    ret = get_errno(socket(domain, type, protocol));
    if (ret >= 0) {
        ret = sock_flags_fixup(ret, target_type);
        if (type == SOCK_PACKET) {
            /* Manage an obsolete case :
             * if socket type is SOCK_PACKET, bind by name
             */
            fd_trans_register(ret, &target_packet_trans);
        } else if (domain == PF_NETLINK) {
            switch (protocol) {
#ifdef CONFIG_RTNETLINK
            case NETLINK_ROUTE:
                fd_trans_register(ret, &target_netlink_route_trans);
                break;
#endif
            case NETLINK_KOBJECT_UEVENT:
                /* nothing to do: messages are strings */
                break;
            case NETLINK_AUDIT:
                fd_trans_register(ret, &target_netlink_audit_trans);
                break;
            default:
                g_assert_not_reached();
            }
        }
    }
    return ret;
}

/* do_bind() Must return target values and target errnos. */
static abi_long do_bind(int sockfd, abi_ulong target_addr,
                        socklen_t addrlen)
{
    void *addr;
    abi_long ret;

    if ((int)addrlen < 0) {
        return -TARGET_EINVAL;
    }

    addr = alloca(addrlen+1);

    ret = target_to_host_sockaddr(sockfd, addr, target_addr, addrlen);
    if (ret)
        return ret;

    return get_errno(bind(sockfd, addr, addrlen));
}

/* do_connect() Must return target values and target errnos. */
static abi_long do_connect(int sockfd, abi_ulong target_addr,
                           socklen_t addrlen)
{
    void *addr;
    abi_long ret;

    if ((int)addrlen < 0) {
        return -TARGET_EINVAL;
    }

    addr = alloca(addrlen+1);

    ret = target_to_host_sockaddr(sockfd, addr, target_addr, addrlen);
    if (ret)
        return ret;

    return get_errno(safe_connect(sockfd, addr, addrlen));
}

/* do_sendrecvmsg_locked() Must return target values and target errnos. */
static abi_long do_sendrecvmsg_locked(int fd, struct target_msghdr *msgp,
                                      int flags, int send)
{
    abi_long ret, len;
    struct msghdr msg;
    abi_ulong count;
    struct iovec *vec;
    abi_ulong target_vec;

    if (msgp->msg_name) {
        msg.msg_namelen = tswap32(msgp->msg_namelen);
        msg.msg_name = alloca(msg.msg_namelen+1);
        ret = target_to_host_sockaddr(fd, msg.msg_name,
                                      tswapal(msgp->msg_name),
                                      msg.msg_namelen);
        if (ret == -TARGET_EFAULT) {
            /* For connected sockets msg_name and msg_namelen must
             * be ignored, so returning EFAULT immediately is wrong.
             * Instead, pass a bad msg_name to the host kernel, and
             * let it decide whether to return EFAULT or not.
             */
            msg.msg_name = (void *)-1;
        } else if (ret) {
            goto out2;
        }
    } else {
        msg.msg_name = NULL;
        msg.msg_namelen = 0;
    }
    msg.msg_controllen = 2 * tswapal(msgp->msg_controllen);
    msg.msg_control = alloca(msg.msg_controllen);
    memset(msg.msg_control, 0, msg.msg_controllen);

    msg.msg_flags = tswap32(msgp->msg_flags);

    count = tswapal(msgp->msg_iovlen);
    target_vec = tswapal(msgp->msg_iov);

    if (count > IOV_MAX) {
        /* sendrcvmsg returns a different errno for this condition than
         * readv/writev, so we must catch it here before lock_iovec() does.
         */
        ret = -TARGET_EMSGSIZE;
        goto out2;
    }

    vec = lock_iovec(send ? VERIFY_READ : VERIFY_WRITE,
                     target_vec, count, send);
    if (vec == NULL) {
        ret = -host_to_target_errno(errno);
        goto out2;
    }
    msg.msg_iovlen = count;
    msg.msg_iov = vec;

    if (send) {
        if (fd_trans_target_to_host_data(fd)) {
            void *host_msg;

            host_msg = g_malloc(msg.msg_iov->iov_len);
            memcpy(host_msg, msg.msg_iov->iov_base, msg.msg_iov->iov_len);
            ret = fd_trans_target_to_host_data(fd)(host_msg,
                                                   msg.msg_iov->iov_len);
            if (ret >= 0) {
                msg.msg_iov->iov_base = host_msg;
                ret = get_errno(safe_sendmsg(fd, &msg, flags));
            }
            g_free(host_msg);
        } else {
            ret = target_to_host_cmsg(&msg, msgp);
            if (ret == 0) {
                ret = get_errno(safe_sendmsg(fd, &msg, flags));
            }
        }
    } else {
        ret = get_errno(safe_recvmsg(fd, &msg, flags));
        if (!is_error(ret)) {
            len = ret;
            if (fd_trans_host_to_target_data(fd)) {
                ret = fd_trans_host_to_target_data(fd)(msg.msg_iov->iov_base,
                                               MIN(msg.msg_iov->iov_len, len));
            } else {
                ret = host_to_target_cmsg(msgp, &msg);
            }
            if (!is_error(ret)) {
                msgp->msg_namelen = tswap32(msg.msg_namelen);
                msgp->msg_flags = tswap32(msg.msg_flags);
                if (msg.msg_name != NULL && msg.msg_name != (void *)-1) {
                    ret = host_to_target_sockaddr(tswapal(msgp->msg_name),
                                    msg.msg_name, msg.msg_namelen);
                    if (ret) {
                        goto out;
                    }
                }

                ret = len;
            }
        }
    }

out:
    unlock_iovec(vec, target_vec, count, !send);
out2:
    return ret;
}

static abi_long do_sendrecvmsg(int fd, abi_ulong target_msg,
                               int flags, int send)
{
    abi_long ret;
    struct target_msghdr *msgp;

    if (!lock_user_struct(send ? VERIFY_READ : VERIFY_WRITE,
                          msgp,
                          target_msg,
                          send ? 1 : 0)) {
        return -TARGET_EFAULT;
    }
    ret = do_sendrecvmsg_locked(fd, msgp, flags, send);
    unlock_user_struct(msgp, target_msg, send ? 0 : 1);
    return ret;
}

/* We don't rely on the C library to have sendmmsg/recvmmsg support,
 * so it might not have this *mmsg-specific flag either.
 */
#ifndef MSG_WAITFORONE
#define MSG_WAITFORONE 0x10000
#endif

static abi_long do_sendrecvmmsg(int fd, abi_ulong target_msgvec,
                                unsigned int vlen, unsigned int flags,
                                int send)
{
    struct target_mmsghdr *mmsgp;
    abi_long ret = 0;
    int i;

    if (vlen > UIO_MAXIOV) {
        vlen = UIO_MAXIOV;
    }

    mmsgp = lock_user(VERIFY_WRITE, target_msgvec, sizeof(*mmsgp) * vlen, 1);
    if (!mmsgp) {
        return -TARGET_EFAULT;
    }

    for (i = 0; i < vlen; i++) {
        ret = do_sendrecvmsg_locked(fd, &mmsgp[i].msg_hdr, flags, send);
        if (is_error(ret)) {
            break;
        }
        mmsgp[i].msg_len = tswap32(ret);
        /* MSG_WAITFORONE turns on MSG_DONTWAIT after one packet */
        if (flags & MSG_WAITFORONE) {
            flags |= MSG_DONTWAIT;
        }
    }

    unlock_user(mmsgp, target_msgvec, sizeof(*mmsgp) * i);

    /* Return number of datagrams sent if we sent any at all;
     * otherwise return the error.
     */
    if (i) {
        return i;
    }
    return ret;
}

/* do_accept4() Must return target values and target errnos. */
static abi_long do_accept4(int fd, abi_ulong target_addr,
                           abi_ulong target_addrlen_addr, int flags)
{
    socklen_t addrlen, ret_addrlen;
    void *addr;
    abi_long ret;
    int host_flags;

    host_flags = target_to_host_bitmask(flags, fcntl_flags_tbl);

    if (target_addr == 0) {
        return get_errno(safe_accept4(fd, NULL, NULL, host_flags));
    }

    /* linux returns EINVAL if addrlen pointer is invalid */
    if (get_user_u32(addrlen, target_addrlen_addr))
        return -TARGET_EINVAL;

    if ((int)addrlen < 0) {
        return -TARGET_EINVAL;
    }

    if (!access_ok(VERIFY_WRITE, target_addr, addrlen))
        return -TARGET_EINVAL;

    addr = alloca(addrlen);

    ret_addrlen = addrlen;
    ret = get_errno(safe_accept4(fd, addr, &ret_addrlen, host_flags));
    if (!is_error(ret)) {
        host_to_target_sockaddr(target_addr, addr, MIN(addrlen, ret_addrlen));
        if (put_user_u32(ret_addrlen, target_addrlen_addr)) {
            ret = -TARGET_EFAULT;
        }
    }
    return ret;
}

/* do_getpeername() Must return target values and target errnos. */
static abi_long do_getpeername(int fd, abi_ulong target_addr,
                               abi_ulong target_addrlen_addr)
{
    socklen_t addrlen, ret_addrlen;
    void *addr;
    abi_long ret;

    if (get_user_u32(addrlen, target_addrlen_addr))
        return -TARGET_EFAULT;

    if ((int)addrlen < 0) {
        return -TARGET_EINVAL;
    }

    if (!access_ok(VERIFY_WRITE, target_addr, addrlen))
        return -TARGET_EFAULT;

    addr = alloca(addrlen);

    ret_addrlen = addrlen;
    ret = get_errno(getpeername(fd, addr, &ret_addrlen));
    if (!is_error(ret)) {
        host_to_target_sockaddr(target_addr, addr, MIN(addrlen, ret_addrlen));
        if (put_user_u32(ret_addrlen, target_addrlen_addr)) {
            ret = -TARGET_EFAULT;
        }
    }
    return ret;
}

/* do_getsockname() Must return target values and target errnos. */
static abi_long do_getsockname(int fd, abi_ulong target_addr,
                               abi_ulong target_addrlen_addr)
{
    socklen_t addrlen, ret_addrlen;
    void *addr;
    abi_long ret;

    if (get_user_u32(addrlen, target_addrlen_addr))
        return -TARGET_EFAULT;

    if ((int)addrlen < 0) {
        return -TARGET_EINVAL;
    }

    if (!access_ok(VERIFY_WRITE, target_addr, addrlen))
        return -TARGET_EFAULT;

    addr = alloca(addrlen);

    ret_addrlen = addrlen;
    ret = get_errno(getsockname(fd, addr, &ret_addrlen));
    if (!is_error(ret)) {
        host_to_target_sockaddr(target_addr, addr, MIN(addrlen, ret_addrlen));
        if (put_user_u32(ret_addrlen, target_addrlen_addr)) {
            ret = -TARGET_EFAULT;
        }
    }
    return ret;
}

/* do_socketpair() Must return target values and target errnos. */
static abi_long do_socketpair(int domain, int type, int protocol,
                              abi_ulong target_tab_addr)
{
    int tab[2];
    abi_long ret;

    target_to_host_sock_type(&type);

    ret = get_errno(socketpair(domain, type, protocol, tab));
    if (!is_error(ret)) {
        if (put_user_s32(tab[0], target_tab_addr)
            || put_user_s32(tab[1], target_tab_addr + sizeof(tab[0])))
            ret = -TARGET_EFAULT;
    }
    return ret;
}

/* do_sendto() Must return target values and target errnos. */
static abi_long do_sendto(int fd, abi_ulong msg, size_t len, int flags,
                          abi_ulong target_addr, socklen_t addrlen)
{
    void *addr;
    void *host_msg;
    void *copy_msg = NULL;
    abi_long ret;

    if ((int)addrlen < 0) {
        return -TARGET_EINVAL;
    }

    host_msg = lock_user(VERIFY_READ, msg, len, 1);
    if (!host_msg)
        return -TARGET_EFAULT;
    if (fd_trans_target_to_host_data(fd)) {
        copy_msg = host_msg;
        host_msg = g_malloc(len);
        memcpy(host_msg, copy_msg, len);
        ret = fd_trans_target_to_host_data(fd)(host_msg, len);
        if (ret < 0) {
            goto fail;
        }
    }
    if (target_addr) {
        addr = alloca(addrlen+1);
        ret = target_to_host_sockaddr(fd, addr, target_addr, addrlen);
        if (ret) {
            goto fail;
        }
        ret = get_errno(safe_sendto(fd, host_msg, len, flags, addr, addrlen));
    } else {
        ret = get_errno(safe_sendto(fd, host_msg, len, flags, NULL, 0));
    }
fail:
    if (copy_msg) {
        g_free(host_msg);
        host_msg = copy_msg;
    }
    unlock_user(host_msg, msg, 0);
    return ret;
}