#include "qemu/osdep.h"
#include "qemu/mmap-alloc.h"
#include "qemu/host-utils.h"
+#include "qemu/cutils.h"
+#include "qemu/error-report.h"
#define HUGETLBFS_MAGIC 0x958458f6
#ifdef CONFIG_LINUX
#include <sys/vfs.h>
+#include <linux/magic.h>
#endif
+QemuFsType qemu_fd_getfs(int fd)
+{
+#ifdef CONFIG_LINUX
+ struct statfs fs;
+ int ret;
+
+ if (fd < 0) {
+ return QEMU_FS_TYPE_UNKNOWN;
+ }
+
+ do {
+ ret = fstatfs(fd, &fs);
+ } while (ret != 0 && errno == EINTR);
+
+ switch (fs.f_type) {
+ case TMPFS_MAGIC:
+ return QEMU_FS_TYPE_TMPFS;
+ case HUGETLBFS_MAGIC:
+ return QEMU_FS_TYPE_HUGETLBFS;
+ default:
+ return QEMU_FS_TYPE_UNKNOWN;
+ }
+#else
+ return QEMU_FS_TYPE_UNKNOWN;
+#endif
+}
+
size_t qemu_fd_getpagesize(int fd)
{
#ifdef CONFIG_LINUX
#endif
#endif
- return qemu_real_host_page_size;
+ return qemu_real_host_page_size();
}
-size_t qemu_mempath_getpagesize(const char *mem_path)
+#define OVERCOMMIT_MEMORY_PATH "/proc/sys/vm/overcommit_memory"
+static bool map_noreserve_effective(int fd, uint32_t qemu_map_flags)
{
-#ifdef CONFIG_LINUX
- struct statfs fs;
- int ret;
+#if defined(__linux__)
+ const bool readonly = qemu_map_flags & QEMU_MAP_READONLY;
+ const bool shared = qemu_map_flags & QEMU_MAP_SHARED;
+ gchar *content = NULL;
+ const char *endptr;
+ unsigned int tmp;
- if (mem_path) {
- do {
- ret = statfs(mem_path, &fs);
- } while (ret != 0 && errno == EINTR);
+ /*
+ * hugeltb accounting is different than ordinary swap reservation:
+ * a) Hugetlb pages from the pool are reserved for both private and
+ * shared mappings. For shared mappings, all mappers have to specify
+ * MAP_NORESERVE.
+ * b) MAP_NORESERVE is not affected by /proc/sys/vm/overcommit_memory.
+ */
+ if (qemu_fd_getpagesize(fd) != qemu_real_host_page_size()) {
+ return true;
+ }
- if (ret != 0) {
- fprintf(stderr, "Couldn't statfs() memory path: %s\n",
- strerror(errno));
- exit(1);
- }
+ /*
+ * Accountable mappings in the kernel that can be affected by MAP_NORESEVE
+ * are private writable mappings (see mm/mmap.c:accountable_mapping() in
+ * Linux). For all shared or readonly mappings, MAP_NORESERVE is always
+ * implicitly active -- no reservation; this includes shmem. The only
+ * exception is shared anonymous memory, it is accounted like private
+ * anonymous memory.
+ */
+ if (readonly || (shared && fd >= 0)) {
+ return true;
+ }
- if (fs.f_type == HUGETLBFS_MAGIC) {
- /* It's hugepage, return the huge page size */
- return fs.f_bsize;
+ /*
+ * MAP_NORESERVE is globally ignored for applicable !hugetlb mappings when
+ * memory overcommit is set to "never". Sparse memory regions aren't really
+ * possible in this system configuration.
+ *
+ * Bail out now instead of silently committing way more memory than
+ * currently desired by the user.
+ */
+ if (g_file_get_contents(OVERCOMMIT_MEMORY_PATH, &content, NULL, NULL) &&
+ !qemu_strtoui(content, &endptr, 0, &tmp) &&
+ (!endptr || *endptr == '\n')) {
+ if (tmp == 2) {
+ error_report("Skipping reservation of swap space is not supported:"
+ " \"" OVERCOMMIT_MEMORY_PATH "\" is \"2\"");
+ return false;
}
+ return true;
}
-#ifdef __sparc__
- /* SPARC Linux needs greater alignment than the pagesize */
- return QEMU_VMALLOC_ALIGN;
-#endif
+ /* this interface has been around since Linux 2.6 */
+ error_report("Skipping reservation of swap space is not supported:"
+ " Could not read: \"" OVERCOMMIT_MEMORY_PATH "\"");
+ return false;
#endif
-
- return qemu_real_host_page_size;
+ /*
+ * E.g., FreeBSD used to define MAP_NORESERVE, never implemented it,
+ * and removed it a while ago.
+ */
+ error_report("Skipping reservation of swap space is not supported");
+ return false;
}
/*
* We do this unless we are using the system page size, in which case
* anonymous memory is OK.
*/
- if (fd == -1 || qemu_fd_getpagesize(fd) == qemu_real_host_page_size) {
+ if (fd == -1 || qemu_fd_getpagesize(fd) == qemu_real_host_page_size()) {
fd = -1;
flags |= MAP_ANONYMOUS;
} else {
return mmap(0, size, PROT_NONE, flags, fd, 0);
}
+/*
+ * Activate memory in a reserved region from the given fd (if any), to make
+ * it accessible.
+ */
+static void *mmap_activate(void *ptr, size_t size, int fd,
+ uint32_t qemu_map_flags, off_t map_offset)
+{
+ const bool noreserve = qemu_map_flags & QEMU_MAP_NORESERVE;
+ const bool readonly = qemu_map_flags & QEMU_MAP_READONLY;
+ const bool shared = qemu_map_flags & QEMU_MAP_SHARED;
+ const bool sync = qemu_map_flags & QEMU_MAP_SYNC;
+ const int prot = PROT_READ | (readonly ? 0 : PROT_WRITE);
+ int map_sync_flags = 0;
+ int flags = MAP_FIXED;
+ void *activated_ptr;
+
+ if (noreserve && !map_noreserve_effective(fd, qemu_map_flags)) {
+ return MAP_FAILED;
+ }
+
+ flags |= fd == -1 ? MAP_ANONYMOUS : 0;
+ flags |= shared ? MAP_SHARED : MAP_PRIVATE;
+ flags |= noreserve ? MAP_NORESERVE : 0;
+ if (shared && sync) {
+ map_sync_flags = MAP_SYNC | MAP_SHARED_VALIDATE;
+ }
+
+ activated_ptr = mmap(ptr, size, prot, flags | map_sync_flags, fd,
+ map_offset);
+ if (activated_ptr == MAP_FAILED && map_sync_flags) {
+ if (errno == ENOTSUP) {
+ char *proc_link = g_strdup_printf("/proc/self/fd/%d", fd);
+ char *file_name = g_malloc0(PATH_MAX);
+ int len = readlink(proc_link, file_name, PATH_MAX - 1);
+
+ if (len < 0) {
+ len = 0;
+ }
+ file_name[len] = '\0';
+ fprintf(stderr, "Warning: requesting persistence across crashes "
+ "for backend file %s failed. Proceeding without "
+ "persistence, data might become corrupted in case of host "
+ "crash.\n", file_name);
+ g_free(proc_link);
+ g_free(file_name);
+ warn_report("Using non DAX backing file with 'pmem=on' option"
+ " is deprecated");
+ }
+ /*
+ * If mmap failed with MAP_SHARED_VALIDATE | MAP_SYNC, we will try
+ * again without these flags to handle backwards compatibility.
+ */
+ activated_ptr = mmap(ptr, size, prot, flags, fd, map_offset);
+ }
+ return activated_ptr;
+}
+
static inline size_t mmap_guard_pagesize(int fd)
{
#if defined(__powerpc64__) && defined(__linux__)
/* Mappings in the same segment must share the same page size */
return qemu_fd_getpagesize(fd);
#else
- return qemu_real_host_page_size;
+ return qemu_real_host_page_size();
#endif
}
void *qemu_ram_mmap(int fd,
size_t size,
size_t align,
- bool readonly,
- bool shared,
- bool is_pmem,
+ uint32_t qemu_map_flags,
off_t map_offset)
{
const size_t guard_pagesize = mmap_guard_pagesize(fd);
- int prot;
- int flags;
- int map_sync_flags = 0;
- size_t offset;
- size_t total;
- void *guardptr;
- void *ptr;
+ size_t offset, total;
+ void *ptr, *guardptr;
/*
* Note: this always allocates at least one extra page of virtual address
/* Always align to host page size */
assert(align >= guard_pagesize);
- flags = MAP_FIXED;
- flags |= fd == -1 ? MAP_ANONYMOUS : 0;
- flags |= shared ? MAP_SHARED : MAP_PRIVATE;
- if (shared && is_pmem) {
- map_sync_flags = MAP_SYNC | MAP_SHARED_VALIDATE;
- }
-
offset = QEMU_ALIGN_UP((uintptr_t)guardptr, align) - (uintptr_t)guardptr;
- prot = PROT_READ | (readonly ? 0 : PROT_WRITE);
-
- ptr = mmap(guardptr + offset, size, prot,
- flags | map_sync_flags, fd, map_offset);
-
- if (ptr == MAP_FAILED && map_sync_flags) {
- if (errno == ENOTSUP) {
- char *proc_link, *file_name;
- int len;
- proc_link = g_strdup_printf("/proc/self/fd/%d", fd);
- file_name = g_malloc0(PATH_MAX);
- len = readlink(proc_link, file_name, PATH_MAX - 1);
- if (len < 0) {
- len = 0;
- }
- file_name[len] = '\0';
- fprintf(stderr, "Warning: requesting persistence across crashes "
- "for backend file %s failed. Proceeding without "
- "persistence, data might become corrupted in case of host "
- "crash.\n", file_name);
- g_free(proc_link);
- g_free(file_name);
- }
- /*
- * if map failed with MAP_SHARED_VALIDATE | MAP_SYNC,
- * we will remove these flags to handle compatibility.
- */
- ptr = mmap(guardptr + offset, size, prot, flags, fd, map_offset);
- }
-
+ ptr = mmap_activate(guardptr + offset, size, fd, qemu_map_flags,
+ map_offset);
if (ptr == MAP_FAILED) {
munmap(guardptr, total);
return MAP_FAILED;