oslib-posix.c

/*
 * os-posix-lib.c
 *
 * Copyright (c) 2003-2008 Fabrice Bellard
 * Copyright (c) 2010 Red Hat, Inc.
 *
 * QEMU library functions on POSIX which are shared between QEMU and
 * the QEMU tools.
 *
 * Permission is hereby granted, free of charge, to any person obtaining a copy
 * of this software and associated documentation files (the "Software"), to deal
 * in the Software without restriction, including without limitation the rights
 * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
 * copies of the Software, and to permit persons to whom the Software is
 * furnished to do so, subject to the following conditions:
 *
 * The above copyright notice and this permission notice shall be included in
 * all copies or substantial portions of the Software.
 *
 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
 * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
 * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
 * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
 * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
 * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
 * THE SOFTWARE.
 */

/* The following block of code temporarily renames the daemon() function so the
   compiler does not see the warning associated with it in stdlib.h on OSX */
#ifdef __APPLE__
#define daemon qemu_fake_daemon_function
#include <stdlib.h>
#undef daemon
extern int daemon(int, int);
#endif

#if defined(__linux__) && (defined(__x86_64__) || defined(__arm__))
   /* Use 2 MiB alignment so transparent hugepages can be used by KVM.
      Valgrind does not support alignments larger than 1 MiB,
      therefore we need special code which handles running on Valgrind. */
#  define QEMU_VMALLOC_ALIGN (512 * 4096)
#elif defined(__linux__) && defined(__s390x__)
   /* Use 1 MiB (segment size) alignment so gmap can be used by KVM. */
#  define QEMU_VMALLOC_ALIGN (256 * 4096)
#else
#  define QEMU_VMALLOC_ALIGN getpagesize()
#endif
#define HUGETLBFS_MAGIC       0x958458f6

#include <termios.h>
#include <unistd.h>

#include <glib/gprintf.h>

#include "config-host.h"
#include "sysemu/sysemu.h"
#include "trace.h"
#include "qemu/sockets.h"
#include <sys/mman.h>
#include <libgen.h>
#include <setjmp.h>
#include <sys/signal.h>

#ifdef CONFIG_LINUX
#include <sys/syscall.h>
#include <sys/vfs.h>
#endif

#ifdef __FreeBSD__
#include <sys/sysctl.h>
#endif

int qemu_get_thread_id(void)
{
#if defined(__linux__)
    return syscall(SYS_gettid);
#else
    return getpid();
#endif
}

int qemu_daemon(int nochdir, int noclose)
{
    return daemon(nochdir, noclose);
}

void *qemu_oom_check(void *ptr)
{
    if (ptr == NULL) {
        fprintf(stderr, "Failed to allocate memory: %s\n", strerror(errno));
        abort();
    }
    return ptr;
}

void *qemu_try_memalign(size_t alignment, size_t size)
{
    void *ptr;

    if (alignment < sizeof(void*)) {
        alignment = sizeof(void*);
    }

#if defined(_POSIX_C_SOURCE) && !defined(__sun__)
    int ret;
    ret = posix_memalign(&ptr, alignment, size);
    if (ret != 0) {
        errno = ret;
        ptr = NULL;
    }
#elif defined(CONFIG_BSD)
    ptr = valloc(size);
#else
    ptr = memalign(alignment, size);
#endif
    trace_qemu_memalign(alignment, size, ptr);
    return ptr;
}

void *qemu_memalign(size_t alignment, size_t size)
{
    return qemu_oom_check(qemu_try_memalign(alignment, size));
}

/* alloc shared memory pages */
void *qemu_anon_ram_alloc(size_t size)
{
    size_t align = QEMU_VMALLOC_ALIGN;
    size_t total = size + align - getpagesize();
    void *ptr = mmap(0, total, PROT_READ | PROT_WRITE,
                     MAP_ANONYMOUS | MAP_PRIVATE, -1, 0);
    size_t offset = QEMU_ALIGN_UP((uintptr_t)ptr, align) - (uintptr_t)ptr;

    if (ptr == MAP_FAILED) {
        return NULL;
    }

    ptr += offset;
    total -= offset;

    if (offset > 0) {
        munmap(ptr - offset, offset);
    }
    if (total > size) {
        munmap(ptr + size, total - size);
    }

    trace_qemu_anon_ram_alloc(size, ptr);
    return ptr;
}

void qemu_vfree(void *ptr)
{
    trace_qemu_vfree(ptr);
    free(ptr);
}

void qemu_anon_ram_free(void *ptr, size_t size)
{
    trace_qemu_anon_ram_free(ptr, size);
    if (ptr) {
        munmap(ptr, size);
    }
}

void qemu_set_block(int fd)
{
    int f;
    f = fcntl(fd, F_GETFL);
    fcntl(fd, F_SETFL, f & ~O_NONBLOCK);
}

void qemu_set_nonblock(int fd)
{
    int f;
    f = fcntl(fd, F_GETFL);
    fcntl(fd, F_SETFL, f | O_NONBLOCK);
}

int socket_set_fast_reuse(int fd)
{
    int val = 1, ret;

    ret = setsockopt(fd, SOL_SOCKET, SO_REUSEADDR,
                     (const char *)&val, sizeof(val));

    assert(ret == 0);

    return ret;
}

void qemu_set_cloexec(int fd)
{
    int f;
    f = fcntl(fd, F_GETFD);
    fcntl(fd, F_SETFD, f | FD_CLOEXEC);
}

/*
 * Creates a pipe with FD_CLOEXEC set on both file descriptors
 */
int qemu_pipe(int pipefd[2])
{
    int ret;

#ifdef CONFIG_PIPE2
    ret = pipe2(pipefd, O_CLOEXEC);
    if (ret != -1 || errno != ENOSYS) {
        return ret;
    }
#endif
    ret = pipe(pipefd);
    if (ret == 0) {
        qemu_set_cloexec(pipefd[0]);
        qemu_set_cloexec(pipefd[1]);
    }

    return ret;
}

int qemu_utimens(const char *path, const struct timespec *times)
{
    struct timeval tv[2], tv_now;
    struct stat st;
    int i;
#ifdef CONFIG_UTIMENSAT
    int ret;

    ret = utimensat(AT_FDCWD, path, times, AT_SYMLINK_NOFOLLOW);
    if (ret != -1 || errno != ENOSYS) {
        return ret;
    }
#endif
    /* Fallback: use utimes() instead of utimensat() */

    /* happy if special cases */
    if (times[0].tv_nsec == UTIME_OMIT && times[1].tv_nsec == UTIME_OMIT) {
        return 0;
    }
    if (times[0].tv_nsec == UTIME_NOW && times[1].tv_nsec == UTIME_NOW) {
        return utimes(path, NULL);
    }

    /* prepare for hard cases */
    if (times[0].tv_nsec == UTIME_NOW || times[1].tv_nsec == UTIME_NOW) {
        gettimeofday(&tv_now, NULL);
    }
    if (times[0].tv_nsec == UTIME_OMIT || times[1].tv_nsec == UTIME_OMIT) {
        stat(path, &st);
    }

    for (i = 0; i < 2; i++) {
        if (times[i].tv_nsec == UTIME_NOW) {
            tv[i].tv_sec = tv_now.tv_sec;
            tv[i].tv_usec = tv_now.tv_usec;
        } else if (times[i].tv_nsec == UTIME_OMIT) {
            tv[i].tv_sec = (i == 0) ? st.st_atime : st.st_mtime;
            tv[i].tv_usec = 0;
        } else {
            tv[i].tv_sec = times[i].tv_sec;
            tv[i].tv_usec = times[i].tv_nsec / 1000;
        }
    }

    return utimes(path, &tv[0]);
}

char *
qemu_get_local_state_pathname(const char *relative_pathname)
{
    return g_strdup_printf("%s/%s", CONFIG_QEMU_LOCALSTATEDIR,
                           relative_pathname);
}

void qemu_set_tty_echo(int fd, bool echo)
{
    struct termios tty;

    tcgetattr(fd, &tty);

    if (echo) {
        tty.c_lflag |= ECHO | ECHONL | ICANON | IEXTEN;
    } else {
        tty.c_lflag &= ~(ECHO | ECHONL | ICANON | IEXTEN);
    }

    tcsetattr(fd, TCSANOW, &tty);
}

static char exec_dir[PATH_MAX];

void qemu_init_exec_dir(const char *argv0)
{
    char *dir;
    char *p = NULL;
    char buf[PATH_MAX];

    assert(!exec_dir[0]);

#if defined(__linux__)
    {
        int len;
        len = readlink("/proc/self/exe", buf, sizeof(buf) - 1);
        if (len > 0) {
            buf[len] = 0;
            p = buf;
        }
    }
#elif defined(__FreeBSD__)
    {
        static int mib[4] = {CTL_KERN, KERN_PROC, KERN_PROC_PATHNAME, -1};
        size_t len = sizeof(buf) - 1;

        *buf = '\0';
        if (!sysctl(mib, ARRAY_SIZE(mib), buf, &len, NULL, 0) &&
            *buf) {
            buf[sizeof(buf) - 1] = '\0';
            p = buf;
        }
    }
#endif
    /* If we don't have any way of figuring out the actual executable
       location then try argv[0].  */
    if (!p) {
        if (!argv0) {
            return;
        }
        p = realpath(argv0, buf);
        if (!p) {
            return;
        }
    }
    dir = dirname(p);

    pstrcpy(exec_dir, sizeof(exec_dir), dir);
}

char *qemu_get_exec_dir(void)
{
    return g_strdup(exec_dir);
}

static sigjmp_buf sigjump;

static void sigbus_handler(int signal)
{
    siglongjmp(sigjump, 1);
}

static size_t fd_getpagesize(int fd)
{
#ifdef CONFIG_LINUX
    struct statfs fs;
    int ret;

    if (fd != -1) {
        do {
            ret = fstatfs(fd, &fs);
        } while (ret != 0 && errno == EINTR);

        if (ret == 0 && fs.f_type == HUGETLBFS_MAGIC) {
            return fs.f_bsize;
        }
    }
#endif

    return getpagesize();
}

void os_mem_prealloc(int fd, char *area, size_t memory)
{
    int ret;
    struct sigaction act, oldact;
    sigset_t set, oldset;

    memset(&act, 0, sizeof(act));
    act.sa_handler = &sigbus_handler;
    act.sa_flags = 0;

    ret = sigaction(SIGBUS, &act, &oldact);
    if (ret) {
        perror("os_mem_prealloc: failed to install signal handler");
        exit(1);
    }

    /* unblock SIGBUS */
    sigemptyset(&set);
    sigaddset(&set, SIGBUS);
    pthread_sigmask(SIG_UNBLOCK, &set, &oldset);

    if (sigsetjmp(sigjump, 1)) {
        fprintf(stderr, "os_mem_prealloc: failed to preallocate pages\n");
        exit(1);
    } else {
        int i;
        size_t hpagesize = fd_getpagesize(fd);

        /* MAP_POPULATE silently ignores failures */
        memory = (memory + hpagesize - 1) & -hpagesize;
        for (i = 0; i < (memory / hpagesize); i++) {
            memset(area + (hpagesize * i), 0, 1);
        }

        ret = sigaction(SIGBUS, &oldact, NULL);
        if (ret) {
            perror("os_mem_prealloc: failed to reinstall signal handler");
            exit(1);
        }

        pthread_sigmask(SIG_SETMASK, &oldset, NULL);
    }
}