X-Git-Url: https://repo.jachan.dev/qemu.git/blobdiff_plain/00f82b8a3166514f634c1c010c3b6175bcc6403b..4aa401f39e048e71020cceb59f126ab941095a42:/osdep.c diff --git a/osdep.c b/osdep.c index 46434af605..3b25297a25 100644 --- a/osdep.c +++ b/osdep.c @@ -24,249 +24,383 @@ #include #include #include +#include #include #include #include #include -#ifdef HOST_SOLARIS + +/* Needed early for CONFIG_BSD etc. */ +#include "config-host.h" + +#if defined(CONFIG_MADVISE) || defined(CONFIG_POSIX_MADVISE) +#include +#endif + +#ifdef CONFIG_SOLARIS #include #include +/* See MySQL bug #7156 (http://bugs.mysql.com/bug.php?id=7156) for + discussion about Solaris header problems */ +extern int madvise(caddr_t, size_t, int); #endif #include "qemu-common.h" -#include "sysemu.h" +#include "trace.h" +#include "qemu_socket.h" +#include "monitor.h" -#ifdef _WIN32 -#define WIN32_LEAN_AND_MEAN -#include -#elif defined(_BSD) -#include -#else -#include -#endif +static bool fips_enabled = false; + +static const char *qemu_version = QEMU_VERSION; -#if defined(_WIN32) -void *qemu_memalign(size_t alignment, size_t size) +int socket_set_cork(int fd, int v) { - return VirtualAlloc(NULL, size, MEM_COMMIT, PAGE_READWRITE); +#if defined(SOL_TCP) && defined(TCP_CORK) + return setsockopt(fd, SOL_TCP, TCP_CORK, &v, sizeof(v)); +#else + return 0; +#endif } -void *qemu_vmalloc(size_t size) +int qemu_madvise(void *addr, size_t len, int advice) { - /* FIXME: this is not exactly optimal solution since VirtualAlloc - has 64Kb granularity, but at least it guarantees us that the - memory is page aligned. */ - return VirtualAlloc(NULL, size, MEM_COMMIT, PAGE_READWRITE); + 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 } -void qemu_vfree(void *ptr) +#ifndef _WIN32 +/* + * Dups an fd and sets the flags + */ +static int qemu_dup_flags(int fd, int flags) { - VirtualFree(ptr, 0, MEM_RELEASE); -} + int ret; + int serrno; + int dup_flags; + int setfl_flags; +#ifdef F_DUPFD_CLOEXEC + ret = fcntl(fd, F_DUPFD_CLOEXEC, 0); #else + ret = dup(fd); + if (ret != -1) { + qemu_set_cloexec(ret); + } +#endif + if (ret == -1) { + goto fail; + } -#if defined(USE_KQEMU) + dup_flags = fcntl(ret, F_GETFL); + if (dup_flags == -1) { + goto fail; + } -#include -#include -#include + if ((flags & O_SYNC) != (dup_flags & O_SYNC)) { + errno = EINVAL; + goto fail; + } -static void *kqemu_vmalloc(size_t size) -{ - static int phys_ram_fd = -1; - static int phys_ram_size = 0; - const char *tmpdir; - char phys_ram_file[1024]; - void *ptr; -#ifdef HOST_SOLARIS - struct statvfs stfs; -#else - struct statfs stfs; + /* Set/unset flags that we can with fcntl */ + setfl_flags = O_APPEND | O_ASYNC | O_NONBLOCK; +#ifdef O_NOATIME + setfl_flags |= O_NOATIME; #endif +#ifdef O_DIRECT + setfl_flags |= O_DIRECT; +#endif + dup_flags &= ~setfl_flags; + dup_flags |= (flags & setfl_flags); + if (fcntl(ret, F_SETFL, dup_flags) == -1) { + goto fail; + } - if (phys_ram_fd < 0) { - tmpdir = getenv("QEMU_TMPDIR"); - if (!tmpdir) -#ifdef HOST_SOLARIS - tmpdir = "/tmp"; - if (statvfs(tmpdir, &stfs) == 0) { -#else - tmpdir = "/dev/shm"; - if (statfs(tmpdir, &stfs) == 0) { + /* 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; +} #endif - int64_t free_space; - int ram_mb; - - free_space = (int64_t)stfs.f_bavail * stfs.f_bsize; - if ((ram_size + 8192 * 1024) >= free_space) { - ram_mb = (ram_size / (1024 * 1024)); - fprintf(stderr, - "You do not have enough space in '%s' for the %d MB of QEMU virtual RAM.\n", - tmpdir, ram_mb); - if (strcmp(tmpdir, "/dev/shm") == 0) { - fprintf(stderr, "To have more space available provided you have enough RAM and swap, do as root:\n" - "mount -o remount,size=%dm /dev/shm\n", - ram_mb + 16); - } else { - fprintf(stderr, - "Use the '-m' option of QEMU to diminish the amount of virtual RAM or use the\n" - "QEMU_TMPDIR environment variable to set another directory where the QEMU\n" - "temporary RAM file will be opened.\n"); - } - fprintf(stderr, "Or disable the accelerator module with -no-kqemu\n"); - exit(1); - } + +/* + * 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; } - snprintf(phys_ram_file, sizeof(phys_ram_file), "%s/qemuXXXXXX", - tmpdir); - phys_ram_fd = mkstemp(phys_ram_file); - if (phys_ram_fd < 0) { - fprintf(stderr, - "warning: could not create temporary file in '%s'.\n" - "Use QEMU_TMPDIR to select a directory in a tmpfs filesystem.\n" - "Using '/tmp' as fallback.\n", - tmpdir); - snprintf(phys_ram_file, sizeof(phys_ram_file), "%s/qemuXXXXXX", - "/tmp"); - phys_ram_fd = mkstemp(phys_ram_file); - if (phys_ram_fd < 0) { - fprintf(stderr, "Could not create temporary memory file '%s'\n", - phys_ram_file); - exit(1); - } + + fd = monitor_fdset_get_fd(fdset_id, flags); + if (fd == -1) { + return -1; } - unlink(phys_ram_file); + + 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; } - size = (size + 4095) & ~4095; - ftruncate(phys_ram_fd, phys_ram_size + size); - ptr = mmap(NULL, - size, - PROT_WRITE | PROT_READ, MAP_SHARED, - phys_ram_fd, phys_ram_size); - if (ptr == MAP_FAILED) { - fprintf(stderr, "Could not map physical memory\n"); - exit(1); +#endif + + if (flags & O_CREAT) { + va_list ap; + + va_start(ap, flags); + mode = va_arg(ap, int); + va_end(ap); } - phys_ram_size += size; - return ptr; + +#ifdef O_CLOEXEC + ret = open(name, flags | O_CLOEXEC, mode); +#else + ret = open(name, flags, mode); + if (ret >= 0) { + qemu_set_cloexec(ret); + } +#endif + + return ret; } -static void kqemu_vfree(void *ptr) +int qemu_close(int fd) { - /* may be useful some day, but currently we do not need to free */ + 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); } -#endif +/* + * 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; -void *qemu_memalign(size_t alignment, size_t size) + 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) { -#if defined(_POSIX_C_SOURCE) int ret; - void *ptr; - ret = posix_memalign(&ptr, alignment, size); - if (ret != 0) - return NULL; - return ptr; -#elif defined(_BSD) - return valloc(size); -#else - return memalign(alignment, size); + +#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; } -/* alloc shared memory pages */ -void *qemu_vmalloc(size_t size) +/* + * Accept a connection and set FD_CLOEXEC + */ +int qemu_accept(int s, struct sockaddr *addr, socklen_t *addrlen) { -#if defined(USE_KQEMU) - if (kqemu_allowed) - return kqemu_vmalloc(size); -#endif -#ifdef _BSD - return valloc(size); -#else - return memalign(4096, size); + 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_vfree(void *ptr) +/* + * A variant of send(2) which handles partial write. + * + * Return the number of bytes transferred, which is only + * smaller than `count' if there is an error. + * + * This function won'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_send_full(int fd, const void *buf, size_t count, int flags) { -#if defined(USE_KQEMU) - if (kqemu_allowed) - kqemu_vfree(ptr); -#endif - free(ptr); -} + ssize_t ret = 0; + ssize_t total = 0; -#endif + while (count) { + ret = send(fd, buf, count, flags); + if (ret < 0) { + if (errno == EINTR) { + continue; + } + break; + } + + count -= ret; + buf += ret; + total += ret; + } + + return total; +} -int qemu_create_pidfile(const char *filename) +/* + * A variant of recv(2) which handles partial write. + * + * Return the number of bytes transferred, which is only + * smaller than `count' if there is an error. + * + * This function won'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_recv_full(int fd, void *buf, size_t count, int flags) { - char buffer[128]; - int len; -#ifndef _WIN32 - int fd; + ssize_t ret = 0; + ssize_t total = 0; - fd = open(filename, O_RDWR | O_CREAT, 0600); - if (fd == -1) - return -1; + while (count) { + ret = qemu_recv(fd, buf, count, flags); + if (ret <= 0) { + if (ret < 0 && errno == EINTR) { + continue; + } + break; + } - if (lockf(fd, F_TLOCK, 0) == -1) - return -1; + count -= ret; + buf += ret; + total += ret; + } - len = snprintf(buffer, sizeof(buffer), "%ld\n", (long)getpid()); - if (write(fd, buffer, len) != len) - return -1; -#else - HANDLE file; - DWORD flags; - OVERLAPPED overlap; - BOOL ret; - - /* Open for writing with no sharing. */ - file = CreateFile(filename, GENERIC_WRITE, 0, NULL, - OPEN_ALWAYS, FILE_ATTRIBUTE_NORMAL, NULL); - - if (file == INVALID_HANDLE_VALUE) - return -1; - - flags = LOCKFILE_EXCLUSIVE_LOCK | LOCKFILE_FAIL_IMMEDIATELY; - overlap.hEvent = 0; - /* Lock 1 byte. */ - ret = LockFileEx(file, flags, 0, 0, 1, &overlap); - if (ret == 0) - return -1; - - /* Write PID to file. */ - len = snprintf(buffer, sizeof(buffer), "%ld\n", (long)getpid()); - ret = WriteFileEx(file, (LPCVOID)buffer, (DWORD)len, - &overlap, NULL); - if (ret == 0) - return -1; -#endif - return 0; + return total; } -#ifdef _WIN32 +void qemu_set_version(const char *version) +{ + qemu_version = version; +} -/* Offset between 1/1/1601 and 1/1/1970 in 100 nanosec units */ -#define _W32_FT_OFFSET (116444736000000000ULL) +const char *qemu_get_version(void) +{ + return qemu_version; +} -int qemu_gettimeofday(qemu_timeval *tp) +void fips_set_state(bool requested) { - union { - unsigned long long ns100; /*time since 1 Jan 1601 in 100ns units */ - FILETIME ft; - } _now; - - if(tp) - { - GetSystemTimeAsFileTime (&_now.ft); - tp->tv_usec=(long)((_now.ns100 / 10ULL) % 1000000ULL ); - tp->tv_sec= (long)((_now.ns100 - _W32_FT_OFFSET) / 10000000ULL); +#ifdef __linux__ + if (requested) { + FILE *fds = fopen("/proc/sys/crypto/fips_enabled", "r"); + if (fds != NULL) { + fips_enabled = (fgetc(fds) == '1'); + fclose(fds); + } } - /* Always return 0 as per Open Group Base Specifications Issue 6. - Do not set errno on error. */ - return 0; +#else + fips_enabled = false; +#endif /* __linux__ */ + +#ifdef _FIPS_DEBUG + fprintf(stderr, "FIPS mode %s (requested %s)\n", + (fips_enabled ? "enabled" : "disabled"), + (requested ? "enabled" : "disabled")); +#endif +} + +bool fips_get_state(void) +{ + return fips_enabled; } -#endif /* _WIN32 */