qemu-e2k/util/osdep.c

550 lines
12 KiB
C
Raw Normal View History

/*
* QEMU low level functions
*
* Copyright (c) 2003 Fabrice Bellard
*
* 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.
*/
#include "qemu/osdep.h"
/* Needed early for CONFIG_BSD etc. */
#ifdef CONFIG_SOLARIS
#include <sys/statvfs.h>
Introduce qemu_madvise() vl.c has a Sun-specific hack to supply a prototype for madvise(), but the call site has apparently moved to arch_init.c. Haiku doesn't implement madvise() in favor of posix_madvise(). OpenBSD and Solaris 10 don't implement posix_madvise() but madvise(). MinGW implements neither. Check for madvise() and posix_madvise() in configure and supply qemu_madvise() as wrapper. Prefer madvise() over posix_madvise() due to flag availability. Convert all callers to use qemu_madvise() and QEMU_MADV_*. Note that on Solaris the warning is fixed by moving the madvise() prototype, not by qemu_madvise() itself. It helps with porting though, and it simplifies most call sites. v7 -> v8: * Some versions of MinGW have no sys/mman.h header. Reported by Blue Swirl. v6 -> v7: * Adopt madvise() rather than posix_madvise() semantics for returning errors. * Use EINVAL in place of ENOTSUP. v5 -> v6: * Replace two leftover instances of POSIX_MADV_NORMAL with QEMU_MADV_INVALID. Spotted by Blue Swirl. v4 -> v5: * Introduce QEMU_MADV_INVALID, suggested by Alexander Graf. Note that this relies on -1 not being a valid advice value. v3 -> v4: * Eliminate #ifdefs at qemu_advise() call sites. Requested by Blue Swirl. This will currently break the check in kvm-all.c by calling madvise() with a supported flag, which will not fail. Ideas/patches welcome. v2 -> v3: * Reuse the *_MADV_* defines for QEMU_MADV_*. Suggested by Alexander Graf. * Add configure check for madvise(), too. Add defines to Makefile, not QEMU_CFLAGS. Convert all callers, untested. Suggested by Blue Swirl. * Keep Solaris' madvise() prototype around. Pointed out by Alexander Graf. * Display configure check results. v1 -> v2: * Don't rely on posix_madvise() availability, add qemu_madvise(). Suggested by Blue Swirl. Signed-off-by: Andreas Färber <afaerber@opensolaris.org> Cc: Blue Swirl <blauwirbel@gmail.com> Cc: Alexander Graf <agraf@suse.de> Cc: Andrea Arcangeli <aarcange@redhat.com> Signed-off-by: Blue Swirl <blauwirbel@gmail.com>
2010-09-25 13:26:05 +02:00
/* See MySQL bug #7156 (http://bugs.mysql.com/bug.php?id=7156) for
discussion about Solaris header problems */
extern int madvise(char *, size_t, int);
#endif
#include "qemu-common.h"
#include "qemu/cutils.h"
#include "qemu/sockets.h"
#include "qemu/error-report.h"
#include "monitor/monitor.h"
static bool fips_enabled = false;
static const char *hw_version = QEMU_HW_VERSION;
int socket_set_cork(int fd, int v)
{
#if defined(SOL_TCP) && defined(TCP_CORK)
return qemu_setsockopt(fd, SOL_TCP, TCP_CORK, &v, sizeof(v));
#else
return 0;
#endif
}
int socket_set_nodelay(int fd)
{
int v = 1;
return qemu_setsockopt(fd, IPPROTO_TCP, TCP_NODELAY, &v, sizeof(v));
}
Introduce qemu_madvise() vl.c has a Sun-specific hack to supply a prototype for madvise(), but the call site has apparently moved to arch_init.c. Haiku doesn't implement madvise() in favor of posix_madvise(). OpenBSD and Solaris 10 don't implement posix_madvise() but madvise(). MinGW implements neither. Check for madvise() and posix_madvise() in configure and supply qemu_madvise() as wrapper. Prefer madvise() over posix_madvise() due to flag availability. Convert all callers to use qemu_madvise() and QEMU_MADV_*. Note that on Solaris the warning is fixed by moving the madvise() prototype, not by qemu_madvise() itself. It helps with porting though, and it simplifies most call sites. v7 -> v8: * Some versions of MinGW have no sys/mman.h header. Reported by Blue Swirl. v6 -> v7: * Adopt madvise() rather than posix_madvise() semantics for returning errors. * Use EINVAL in place of ENOTSUP. v5 -> v6: * Replace two leftover instances of POSIX_MADV_NORMAL with QEMU_MADV_INVALID. Spotted by Blue Swirl. v4 -> v5: * Introduce QEMU_MADV_INVALID, suggested by Alexander Graf. Note that this relies on -1 not being a valid advice value. v3 -> v4: * Eliminate #ifdefs at qemu_advise() call sites. Requested by Blue Swirl. This will currently break the check in kvm-all.c by calling madvise() with a supported flag, which will not fail. Ideas/patches welcome. v2 -> v3: * Reuse the *_MADV_* defines for QEMU_MADV_*. Suggested by Alexander Graf. * Add configure check for madvise(), too. Add defines to Makefile, not QEMU_CFLAGS. Convert all callers, untested. Suggested by Blue Swirl. * Keep Solaris' madvise() prototype around. Pointed out by Alexander Graf. * Display configure check results. v1 -> v2: * Don't rely on posix_madvise() availability, add qemu_madvise(). Suggested by Blue Swirl. Signed-off-by: Andreas Färber <afaerber@opensolaris.org> Cc: Blue Swirl <blauwirbel@gmail.com> Cc: Alexander Graf <agraf@suse.de> Cc: Andrea Arcangeli <aarcange@redhat.com> Signed-off-by: Blue Swirl <blauwirbel@gmail.com>
2010-09-25 13:26:05 +02:00
int qemu_madvise(void *addr, size_t len, int advice)
{
if (advice == QEMU_MADV_INVALID) {
errno = EINVAL;
return -1;
}
#if defined(CONFIG_MADVISE)
return madvise(addr, len, advice);
#elif defined(CONFIG_POSIX_MADVISE)
return posix_madvise(addr, len, advice);
#else
errno = EINVAL;
return -1;
#endif
}
static int qemu_mprotect__osdep(void *addr, size_t size, int prot)
{
g_assert(!((uintptr_t)addr & ~qemu_real_host_page_mask));
g_assert(!(size & ~qemu_real_host_page_mask));
#ifdef _WIN32
DWORD old_protect;
if (!VirtualProtect(addr, size, prot, &old_protect)) {
error_report("%s: VirtualProtect failed with error code %ld",
__func__, GetLastError());
return -1;
}
return 0;
#else
if (mprotect(addr, size, prot)) {
error_report("%s: mprotect failed: %s", __func__, strerror(errno));
return -1;
}
return 0;
#endif
}
int qemu_mprotect_rwx(void *addr, size_t size)
{
#ifdef _WIN32
return qemu_mprotect__osdep(addr, size, PAGE_EXECUTE_READWRITE);
#else
return qemu_mprotect__osdep(addr, size, PROT_READ | PROT_WRITE | PROT_EXEC);
#endif
}
int qemu_mprotect_none(void *addr, size_t size)
{
#ifdef _WIN32
return qemu_mprotect__osdep(addr, size, PAGE_NOACCESS);
#else
return qemu_mprotect__osdep(addr, size, PROT_NONE);
#endif
}
#ifndef _WIN32
static int fcntl_op_setlk = -1;
static int fcntl_op_getlk = -1;
/*
* Dups an fd and sets the flags
*/
static int qemu_dup_flags(int fd, int flags)
{
int ret;
int serrno;
int dup_flags;
ret = qemu_dup(fd);
if (ret == -1) {
goto fail;
}
dup_flags = fcntl(ret, F_GETFL);
if (dup_flags == -1) {
goto fail;
}
if ((flags & O_SYNC) != (dup_flags & O_SYNC)) {
errno = EINVAL;
goto fail;
}
/* Set/unset flags that we can with fcntl */
if (fcntl(ret, F_SETFL, flags) == -1) {
goto fail;
}
/* Truncate the file in the cases that open() would truncate it */
if (flags & O_TRUNC ||
((flags & (O_CREAT | O_EXCL)) == (O_CREAT | O_EXCL))) {
if (ftruncate(ret, 0) == -1) {
goto fail;
}
}
return ret;
fail:
serrno = errno;
if (ret != -1) {
close(ret);
}
errno = serrno;
return -1;
}
int qemu_dup(int fd)
{
int ret;
#ifdef F_DUPFD_CLOEXEC
ret = fcntl(fd, F_DUPFD_CLOEXEC, 0);
#else
ret = dup(fd);
if (ret != -1) {
qemu_set_cloexec(ret);
}
#endif
return ret;
}
static int qemu_parse_fdset(const char *param)
{
return qemu_parse_fd(param);
}
static void qemu_probe_lock_ops(void)
{
if (fcntl_op_setlk == -1) {
#ifdef F_OFD_SETLK
int fd;
int ret;
struct flock fl = {
.l_whence = SEEK_SET,
.l_start = 0,
.l_len = 0,
.l_type = F_WRLCK,
};
fd = open("/dev/null", O_RDWR);
if (fd < 0) {
fprintf(stderr,
"Failed to open /dev/null for OFD lock probing: %s\n",
strerror(errno));
fcntl_op_setlk = F_SETLK;
fcntl_op_getlk = F_GETLK;
return;
}
ret = fcntl(fd, F_OFD_GETLK, &fl);
close(fd);
if (!ret) {
fcntl_op_setlk = F_OFD_SETLK;
fcntl_op_getlk = F_OFD_GETLK;
} else {
fcntl_op_setlk = F_SETLK;
fcntl_op_getlk = F_GETLK;
}
#else
fcntl_op_setlk = F_SETLK;
fcntl_op_getlk = F_GETLK;
#endif
}
}
bool qemu_has_ofd_lock(void)
{
qemu_probe_lock_ops();
#ifdef F_OFD_SETLK
return fcntl_op_setlk == F_OFD_SETLK;
#else
return false;
#endif
}
static int qemu_lock_fcntl(int fd, int64_t start, int64_t len, int fl_type)
{
int ret;
struct flock fl = {
.l_whence = SEEK_SET,
.l_start = start,
.l_len = len,
.l_type = fl_type,
};
qemu_probe_lock_ops();
do {
ret = fcntl(fd, fcntl_op_setlk, &fl);
} while (ret == -1 && errno == EINTR);
return ret == -1 ? -errno : 0;
}
int qemu_lock_fd(int fd, int64_t start, int64_t len, bool exclusive)
{
return qemu_lock_fcntl(fd, start, len, exclusive ? F_WRLCK : F_RDLCK);
}
int qemu_unlock_fd(int fd, int64_t start, int64_t len)
{
return qemu_lock_fcntl(fd, start, len, F_UNLCK);
}
int qemu_lock_fd_test(int fd, int64_t start, int64_t len, bool exclusive)
{
int ret;
struct flock fl = {
.l_whence = SEEK_SET,
.l_start = start,
.l_len = len,
.l_type = exclusive ? F_WRLCK : F_RDLCK,
};
qemu_probe_lock_ops();
ret = fcntl(fd, fcntl_op_getlk, &fl);
if (ret == -1) {
return -errno;
} else {
return fl.l_type == F_UNLCK ? 0 : -EAGAIN;
}
}
#endif
/*
* Opens a file with FD_CLOEXEC set
*/
int qemu_open(const char *name, int flags, ...)
{
int ret;
int mode = 0;
#ifndef _WIN32
const char *fdset_id_str;
/* Attempt dup of fd from fd set */
if (strstart(name, "/dev/fdset/", &fdset_id_str)) {
int64_t fdset_id;
int fd, dupfd;
fdset_id = qemu_parse_fdset(fdset_id_str);
if (fdset_id == -1) {
errno = EINVAL;
return -1;
}
fd = monitor_fdset_get_fd(fdset_id, flags);
if (fd < 0) {
errno = -fd;
return -1;
}
dupfd = qemu_dup_flags(fd, flags);
if (dupfd == -1) {
return -1;
}
ret = monitor_fdset_dup_fd_add(fdset_id, dupfd);
if (ret == -1) {
close(dupfd);
errno = EINVAL;
return -1;
}
return dupfd;
}
#endif
if (flags & O_CREAT) {
va_list ap;
va_start(ap, flags);
mode = va_arg(ap, int);
va_end(ap);
}
#ifdef O_CLOEXEC
ret = open(name, flags | O_CLOEXEC, mode);
#else
ret = open(name, flags, mode);
if (ret >= 0) {
qemu_set_cloexec(ret);
}
#endif
#ifdef O_DIRECT
if (ret == -1 && errno == EINVAL && (flags & O_DIRECT)) {
error_report("file system may not support O_DIRECT");
errno = EINVAL; /* in case it was clobbered */
}
#endif /* O_DIRECT */
return ret;
}
int qemu_close(int fd)
{
int64_t fdset_id;
/* Close fd that was dup'd from an fdset */
fdset_id = monitor_fdset_dup_fd_find(fd);
if (fdset_id != -1) {
int ret;
ret = close(fd);
if (ret == 0) {
monitor_fdset_dup_fd_remove(fd);
}
return ret;
}
return close(fd);
}
/*
* A variant of write(2) which handles partial write.
*
* Return the number of bytes transferred.
* Set errno if fewer than `count' bytes are written.
*
* This function don't work with non-blocking fd's.
* Any of the possibilities with non-bloking fd's is bad:
* - return a short write (then name is wrong)
* - busy wait adding (errno == EAGAIN) to the loop
*/
ssize_t qemu_write_full(int fd, const void *buf, size_t count)
{
ssize_t ret = 0;
ssize_t total = 0;
while (count) {
ret = write(fd, buf, count);
if (ret < 0) {
if (errno == EINTR)
continue;
break;
}
count -= ret;
buf += ret;
total += ret;
}
return total;
}
/*
* Opens a socket with FD_CLOEXEC set
*/
int qemu_socket(int domain, int type, int protocol)
{
int ret;
#ifdef SOCK_CLOEXEC
ret = socket(domain, type | SOCK_CLOEXEC, protocol);
if (ret != -1 || errno != EINVAL) {
return ret;
}
#endif
ret = socket(domain, type, protocol);
if (ret >= 0) {
qemu_set_cloexec(ret);
}
return ret;
}
/*
* Accept a connection and set FD_CLOEXEC
*/
int qemu_accept(int s, struct sockaddr *addr, socklen_t *addrlen)
{
int ret;
#ifdef CONFIG_ACCEPT4
ret = accept4(s, addr, addrlen, SOCK_CLOEXEC);
if (ret != -1 || errno != ENOSYS) {
return ret;
}
#endif
ret = accept(s, addr, addrlen);
if (ret >= 0) {
qemu_set_cloexec(ret);
}
return ret;
}
void qemu_set_hw_version(const char *version)
{
hw_version = version;
}
const char *qemu_hw_version(void)
{
return hw_version;
}
void fips_set_state(bool requested)
{
#ifdef __linux__
if (requested) {
FILE *fds = fopen("/proc/sys/crypto/fips_enabled", "r");
if (fds != NULL) {
fips_enabled = (fgetc(fds) == '1');
fclose(fds);
}
}
#else
fips_enabled = false;
#endif /* __linux__ */
#ifdef _FIPS_DEBUG
fprintf(stderr, "FIPS mode %s (requested %s)\n",
avoid TABs in files that only contain a few Most files that have TABs only contain a handful of them. Change them to spaces so that we don't confuse people. disas, standard-headers, linux-headers and libdecnumber are imported from other projects and probably should be exempted from the check. Outside those, after this patch the following files still contain both 8-space and TAB sequences at the beginning of the line. Many of them have a majority of TABs, or were initially committed with all tabs. bsd-user/i386/target_syscall.h bsd-user/x86_64/target_syscall.h crypto/aes.c hw/audio/fmopl.c hw/audio/fmopl.h hw/block/tc58128.c hw/display/cirrus_vga.c hw/display/xenfb.c hw/dma/etraxfs_dma.c hw/intc/sh_intc.c hw/misc/mst_fpga.c hw/net/pcnet.c hw/sh4/sh7750.c hw/timer/m48t59.c hw/timer/sh_timer.c include/crypto/aes.h include/disas/bfd.h include/hw/sh4/sh.h libdecnumber/decNumber.c linux-headers/asm-generic/unistd.h linux-headers/linux/kvm.h linux-user/alpha/target_syscall.h linux-user/arm/nwfpe/double_cpdo.c linux-user/arm/nwfpe/fpa11_cpdt.c linux-user/arm/nwfpe/fpa11_cprt.c linux-user/arm/nwfpe/fpa11.h linux-user/flat.h linux-user/flatload.c linux-user/i386/target_syscall.h linux-user/ppc/target_syscall.h linux-user/sparc/target_syscall.h linux-user/syscall.c linux-user/syscall_defs.h linux-user/x86_64/target_syscall.h slirp/cksum.c slirp/if.c slirp/ip.h slirp/ip_icmp.c slirp/ip_icmp.h slirp/ip_input.c slirp/ip_output.c slirp/mbuf.c slirp/misc.c slirp/sbuf.c slirp/socket.c slirp/socket.h slirp/tcp_input.c slirp/tcpip.h slirp/tcp_output.c slirp/tcp_subr.c slirp/tcp_timer.c slirp/tftp.c slirp/udp.c slirp/udp.h target/cris/cpu.h target/cris/mmu.c target/cris/op_helper.c target/sh4/helper.c target/sh4/op_helper.c target/sh4/translate.c tcg/sparc/tcg-target.inc.c tests/tcg/cris/check_addo.c tests/tcg/cris/check_moveq.c tests/tcg/cris/check_swap.c tests/tcg/multiarch/test-mmap.c ui/vnc-enc-hextile-template.h ui/vnc-enc-zywrle.h util/envlist.c util/readline.c The following have only TABs: bsd-user/i386/target_signal.h bsd-user/sparc64/target_signal.h bsd-user/sparc64/target_syscall.h bsd-user/sparc/target_signal.h bsd-user/sparc/target_syscall.h bsd-user/x86_64/target_signal.h crypto/desrfb.c hw/audio/intel-hda-defs.h hw/core/uboot_image.h hw/sh4/sh7750_regnames.c hw/sh4/sh7750_regs.h include/hw/cris/etraxfs_dma.h linux-user/alpha/termbits.h linux-user/arm/nwfpe/fpopcode.h linux-user/arm/nwfpe/fpsr.h linux-user/arm/syscall_nr.h linux-user/arm/target_signal.h linux-user/cris/target_signal.h linux-user/i386/target_signal.h linux-user/linux_loop.h linux-user/m68k/target_signal.h linux-user/microblaze/target_signal.h linux-user/mips64/target_signal.h linux-user/mips/target_signal.h linux-user/mips/target_syscall.h linux-user/mips/termbits.h linux-user/ppc/target_signal.h linux-user/sh4/target_signal.h linux-user/sh4/termbits.h linux-user/sparc64/target_syscall.h linux-user/sparc/target_signal.h linux-user/x86_64/target_signal.h linux-user/x86_64/termbits.h pc-bios/optionrom/optionrom.h slirp/mbuf.h slirp/misc.h slirp/sbuf.h slirp/tcp.h slirp/tcp_timer.h slirp/tcp_var.h target/i386/svm.h target/sparc/asi.h target/xtensa/core-dc232b/xtensa-modules.inc.c target/xtensa/core-dc233c/xtensa-modules.inc.c target/xtensa/core-de212/core-isa.h target/xtensa/core-de212/xtensa-modules.inc.c target/xtensa/core-fsf/xtensa-modules.inc.c target/xtensa/core-sample_controller/core-isa.h target/xtensa/core-sample_controller/xtensa-modules.inc.c target/xtensa/core-test_kc705_be/core-isa.h target/xtensa/core-test_kc705_be/xtensa-modules.inc.c tests/tcg/cris/check_abs.c tests/tcg/cris/check_addc.c tests/tcg/cris/check_addcm.c tests/tcg/cris/check_addoq.c tests/tcg/cris/check_bound.c tests/tcg/cris/check_ftag.c tests/tcg/cris/check_int64.c tests/tcg/cris/check_lz.c tests/tcg/cris/check_openpf5.c tests/tcg/cris/check_sigalrm.c tests/tcg/cris/crisutils.h tests/tcg/cris/sys.c tests/tcg/i386/test-i386-ssse3.c ui/vgafont.h Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Message-Id: <20181213223737.11793-3-pbonzini@redhat.com> Reviewed-by: Aleksandar Markovic <amarkovic@wavecomp.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Reviewed-by: Wainer dos Santos Moschetta <wainersm@redhat.com> Acked-by: Richard Henderson <richard.henderson@linaro.org> Acked-by: Eric Blake <eblake@redhat.com> Acked-by: David Gibson <david@gibson.dropbear.id.au> Reviewed-by: Stefan Markovic <smarkovic@wavecomp.com> Reviewed-by: Michael S. Tsirkin <mst@redhat.com> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
2018-12-13 23:37:37 +01:00
(fips_enabled ? "enabled" : "disabled"),
(requested ? "enabled" : "disabled"));
#endif
}
bool fips_get_state(void)
{
return fips_enabled;
}
#ifdef _WIN32
static void socket_cleanup(void)
{
WSACleanup();
}
#endif
int socket_init(void)
{
#ifdef _WIN32
WSADATA Data;
int ret, err;
ret = WSAStartup(MAKEWORD(2, 2), &Data);
if (ret != 0) {
err = WSAGetLastError();
fprintf(stderr, "WSAStartup: %d\n", err);
return -1;
}
atexit(socket_cleanup);
#endif
return 0;
}
#ifndef CONFIG_IOVEC
/* helper function for iov_send_recv() */
static ssize_t
readv_writev(int fd, const struct iovec *iov, int iov_cnt, bool do_write)
{
unsigned i = 0;
ssize_t ret = 0;
while (i < iov_cnt) {
ssize_t r = do_write
? write(fd, iov[i].iov_base, iov[i].iov_len)
: read(fd, iov[i].iov_base, iov[i].iov_len);
if (r > 0) {
ret += r;
} else if (!r) {
break;
} else if (errno == EINTR) {
continue;
} else {
/* else it is some "other" error,
* only return if there was no data processed. */
if (ret == 0) {
ret = -1;
}
break;
}
i++;
}
return ret;
}
ssize_t
readv(int fd, const struct iovec *iov, int iov_cnt)
{
return readv_writev(fd, iov, iov_cnt, false);
}
ssize_t
writev(int fd, const struct iovec *iov, int iov_cnt)
{
return readv_writev(fd, iov, iov_cnt, true);
}
#endif