* 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
-
-#include <termios.h>
-#include <unistd.h>
+#include "qemu/osdep.h"
#include <termios.h>
#include <glib/gprintf.h>
-#include "config-host.h"
#include "sysemu/sysemu.h"
#include "trace.h"
+#include "qapi/error.h"
#include "qemu/sockets.h"
-#include <sys/mman.h>
#include <libgen.h>
-#include <setjmp.h>
#include <sys/signal.h>
+#include "qemu/cutils.h"
#ifdef CONFIG_LINUX
#include <sys/syscall.h>
#ifdef __FreeBSD__
#include <sys/sysctl.h>
+#include <sys/user.h>
+#include <libutil.h>
+#endif
+
+#include "qemu/mmap-alloc.h"
+
+#ifdef CONFIG_DEBUG_STACK_USAGE
+#include "qemu/error-report.h"
#endif
-#include <qemu/mmap-alloc.h>
+#define MAX_MEM_PREALLOC_THREAD_COUNT 16
+
+struct MemsetThread {
+ char *addr;
+ uint64_t numpages;
+ uint64_t hpagesize;
+ QemuThread pgthread;
+ sigjmp_buf env;
+};
+typedef struct MemsetThread MemsetThread;
+
+static MemsetThread *memset_thread;
+static int memset_num_threads;
+static bool memset_thread_failed;
int qemu_get_thread_id(void)
{
return;
}
}
- dir = dirname(p);
+ dir = g_path_get_dirname(p);
pstrcpy(exec_dir, sizeof(exec_dir), dir);
+
+ g_free(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);
+ int i;
+ if (memset_thread) {
+ for (i = 0; i < memset_num_threads; i++) {
+ if (qemu_thread_is_self(&memset_thread[i].pgthread)) {
+ siglongjmp(memset_thread[i].env, 1);
+ }
+ }
+ }
+}
+
+static void *do_touch_pages(void *arg)
+{
+ MemsetThread *memset_args = (MemsetThread *)arg;
+ char *addr = memset_args->addr;
+ uint64_t numpages = memset_args->numpages;
+ uint64_t hpagesize = memset_args->hpagesize;
+ sigset_t set, oldset;
+ int i = 0;
+
+ /* unblock SIGBUS */
+ sigemptyset(&set);
+ sigaddset(&set, SIGBUS);
+ pthread_sigmask(SIG_UNBLOCK, &set, &oldset);
+
+ if (sigsetjmp(memset_args->env, 1)) {
+ memset_thread_failed = true;
+ } else {
+ for (i = 0; i < numpages; i++) {
+ /*
+ * Read & write back the same value, so we don't
+ * corrupt existing user/app data that might be
+ * stored.
+ *
+ * 'volatile' to stop compiler optimizing this away
+ * to a no-op
+ *
+ * TODO: get a better solution from kernel so we
+ * don't need to write at all so we don't cause
+ * wear on the storage backing the region...
+ */
+ *(volatile char *)addr = *addr;
+ addr += hpagesize;
+ }
+ }
+ pthread_sigmask(SIG_SETMASK, &oldset, NULL);
+ return NULL;
+}
+
+static inline int get_memset_num_threads(int smp_cpus)
+{
+ long host_procs = sysconf(_SC_NPROCESSORS_ONLN);
+ int ret = 1;
+
+ if (host_procs > 0) {
+ ret = MIN(MIN(host_procs, MAX_MEM_PREALLOC_THREAD_COUNT), smp_cpus);
+ }
+ /* In case sysconf() fails, we fall back to single threaded */
+ return ret;
}
-void os_mem_prealloc(int fd, char *area, size_t memory)
+static bool touch_all_pages(char *area, size_t hpagesize, size_t numpages,
+ int smp_cpus)
+{
+ uint64_t numpages_per_thread, size_per_thread;
+ char *addr = area;
+ int i = 0;
+
+ memset_thread_failed = false;
+ memset_num_threads = get_memset_num_threads(smp_cpus);
+ memset_thread = g_new0(MemsetThread, memset_num_threads);
+ numpages_per_thread = (numpages / memset_num_threads);
+ size_per_thread = (hpagesize * numpages_per_thread);
+ for (i = 0; i < memset_num_threads; i++) {
+ memset_thread[i].addr = addr;
+ memset_thread[i].numpages = (i == (memset_num_threads - 1)) ?
+ numpages : numpages_per_thread;
+ memset_thread[i].hpagesize = hpagesize;
+ qemu_thread_create(&memset_thread[i].pgthread, "touch_pages",
+ do_touch_pages, &memset_thread[i],
+ QEMU_THREAD_JOINABLE);
+ addr += size_per_thread;
+ numpages -= numpages_per_thread;
+ }
+ for (i = 0; i < memset_num_threads; i++) {
+ qemu_thread_join(&memset_thread[i].pgthread);
+ }
+ g_free(memset_thread);
+ memset_thread = NULL;
+
+ return memset_thread_failed;
+}
+
+void os_mem_prealloc(int fd, char *area, size_t memory, int smp_cpus,
+ Error **errp)
{
int ret;
struct sigaction act, oldact;
- sigset_t set, oldset;
+ size_t hpagesize = qemu_fd_getpagesize(fd);
+ size_t numpages = DIV_ROUND_UP(memory, hpagesize);
memset(&act, 0, sizeof(act));
act.sa_handler = &sigbus_handler;
ret = sigaction(SIGBUS, &act, &oldact);
if (ret) {
- perror("os_mem_prealloc: failed to install signal handler");
- exit(1);
+ error_setg_errno(errp, errno,
+ "os_mem_prealloc: failed to install signal handler");
+ return;
}
- /* unblock SIGBUS */
- sigemptyset(&set);
- sigaddset(&set, SIGBUS);
- pthread_sigmask(SIG_UNBLOCK, &set, &oldset);
+ /* touch pages simultaneously */
+ if (touch_all_pages(area, hpagesize, numpages, smp_cpus)) {
+ error_setg(errp, "os_mem_prealloc: Insufficient free host memory "
+ "pages available to allocate guest RAM\n");
+ }
- if (sigsetjmp(sigjump, 1)) {
- fprintf(stderr, "os_mem_prealloc: Insufficient free host memory "
- "pages available to allocate guest RAM\n");
+ ret = sigaction(SIGBUS, &oldact, NULL);
+ if (ret) {
+ /* Terminate QEMU since it can't recover from error */
+ perror("os_mem_prealloc: failed to reinstall signal handler");
exit(1);
- } else {
- int i;
- size_t hpagesize = qemu_fd_getpagesize(fd);
- size_t numpages = DIV_ROUND_UP(memory, hpagesize);
-
- /* MAP_POPULATE silently ignores failures */
- for (i = 0; i < numpages; 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);
}
}
}
+char *qemu_get_pid_name(pid_t pid)
+{
+ char *name = NULL;
+
+#if defined(__FreeBSD__)
+ /* BSDs don't have /proc, but they provide a nice substitute */
+ struct kinfo_proc *proc = kinfo_getproc(pid);
+
+ if (proc) {
+ name = g_strdup(proc->ki_comm);
+ free(proc);
+ }
+#else
+ /* Assume a system with reasonable procfs */
+ char *pid_path;
+ size_t len;
+
+ pid_path = g_strdup_printf("/proc/%d/cmdline", pid);
+ g_file_get_contents(pid_path, &name, &len, NULL);
+ g_free(pid_path);
+#endif
+
+ return name;
+}
+
+
pid_t qemu_fork(Error **errp)
{
sigset_t oldmask, newmask;
}
return pid;
}
+
+void *qemu_alloc_stack(size_t *sz)
+{
+ void *ptr, *guardpage;
+#ifdef CONFIG_DEBUG_STACK_USAGE
+ void *ptr2;
+#endif
+ size_t pagesz = getpagesize();
+#ifdef _SC_THREAD_STACK_MIN
+ /* avoid stacks smaller than _SC_THREAD_STACK_MIN */
+ long min_stack_sz = sysconf(_SC_THREAD_STACK_MIN);
+ *sz = MAX(MAX(min_stack_sz, 0), *sz);
+#endif
+ /* adjust stack size to a multiple of the page size */
+ *sz = ROUND_UP(*sz, pagesz);
+ /* allocate one extra page for the guard page */
+ *sz += pagesz;
+
+ ptr = mmap(NULL, *sz, PROT_READ | PROT_WRITE,
+ MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
+ if (ptr == MAP_FAILED) {
+ abort();
+ }
+
+#if defined(HOST_IA64)
+ /* separate register stack */
+ guardpage = ptr + (((*sz - pagesz) / 2) & ~pagesz);
+#elif defined(HOST_HPPA)
+ /* stack grows up */
+ guardpage = ptr + *sz - pagesz;
+#else
+ /* stack grows down */
+ guardpage = ptr;
+#endif
+ if (mprotect(guardpage, pagesz, PROT_NONE) != 0) {
+ abort();
+ }
+
+#ifdef CONFIG_DEBUG_STACK_USAGE
+ for (ptr2 = ptr + pagesz; ptr2 < ptr + *sz; ptr2 += sizeof(uint32_t)) {
+ *(uint32_t *)ptr2 = 0xdeadbeaf;
+ }
+#endif
+
+ return ptr;
+}
+
+#ifdef CONFIG_DEBUG_STACK_USAGE
+static __thread unsigned int max_stack_usage;
+#endif
+
+void qemu_free_stack(void *stack, size_t sz)
+{
+#ifdef CONFIG_DEBUG_STACK_USAGE
+ unsigned int usage;
+ void *ptr;
+
+ for (ptr = stack + getpagesize(); ptr < stack + sz;
+ ptr += sizeof(uint32_t)) {
+ if (*(uint32_t *)ptr != 0xdeadbeaf) {
+ break;
+ }
+ }
+ usage = sz - (uintptr_t) (ptr - stack);
+ if (usage > max_stack_usage) {
+ error_report("thread %d max stack usage increased from %u to %u",
+ qemu_get_thread_id(), max_stack_usage, usage);
+ max_stack_usage = usage;
+ }
+#endif
+
+ munmap(stack, sz);
+}
+
+void sigaction_invoke(struct sigaction *action,
+ struct qemu_signalfd_siginfo *info)
+{
+ siginfo_t si = { 0 };
+ si.si_signo = info->ssi_signo;
+ si.si_errno = info->ssi_errno;
+ si.si_code = info->ssi_code;
+
+ /* Convert the minimal set of fields defined by POSIX.
+ * Positive si_code values are reserved for kernel-generated
+ * signals, where the valid siginfo fields are determined by
+ * the signal number. But according to POSIX, it is unspecified
+ * whether SI_USER and SI_QUEUE have values less than or equal to
+ * zero.
+ */
+ if (info->ssi_code == SI_USER || info->ssi_code == SI_QUEUE ||
+ info->ssi_code <= 0) {
+ /* SIGTERM, etc. */
+ si.si_pid = info->ssi_pid;
+ si.si_uid = info->ssi_uid;
+ } else if (info->ssi_signo == SIGILL || info->ssi_signo == SIGFPE ||
+ info->ssi_signo == SIGSEGV || info->ssi_signo == SIGBUS) {
+ si.si_addr = (void *)(uintptr_t)info->ssi_addr;
+ } else if (info->ssi_signo == SIGCHLD) {
+ si.si_pid = info->ssi_pid;
+ si.si_status = info->ssi_status;
+ si.si_uid = info->ssi_uid;
+ }
+ action->sa_sigaction(info->ssi_signo, &si, NULL);
+}
projects / mirror_qemu.git / blobdiff