[Qemu-devel] [patch 1/2] qemu: mempath: prefault pages manually

[Marcelo Tosatti]

MAP_POPULATE mmap flag does not cause mmap to fail if allocation
of the entire area is not performed. HugeTLBfs performs reservation 
of pages on a global basis: any further restriction to the reserved memory 
such as cpusets placement or numa node policy is performed at 
fault time only.

Manually fault in pages at allocation time. This allows memory restrictions
to be applied before guest initialization.

Signed-off-by: Marcelo Tosatti <address@hidden>

Index: qemu/exec.c
===================================================================
--- qemu.orig/exec.c
+++ qemu/exec.c
@@ -918,6 +918,13 @@ static long gethugepagesize(const char *
     return fs.f_bsize;
 }
 
+sigjmp_buf sigjump;
+
+static void sigbus_handler(int signal)
+{
+    siglongjmp(sigjump, 1);
+}
+
 static void *file_ram_alloc(RAMBlock *block,
                             ram_addr_t memory,
                             const char *path)
@@ -927,9 +934,6 @@ static void *file_ram_alloc(RAMBlock *bl
     char *c;
     void *area;
     int fd;
-#ifdef MAP_POPULATE
-    int flags;
-#endif
     unsigned long hpagesize;
 
     hpagesize = gethugepagesize(path);
@@ -977,21 +981,57 @@ static void *file_ram_alloc(RAMBlock *bl
     if (ftruncate(fd, memory))
         perror("ftruncate");
 
-#ifdef MAP_POPULATE
-    /* NB: MAP_POPULATE won't exhaustively alloc all phys pages in the case
-     * MAP_PRIVATE is requested.  For mem_prealloc we mmap as MAP_SHARED
-     * to sidestep this quirk.
-     */
-    flags = mem_prealloc ? MAP_POPULATE | MAP_SHARED : MAP_PRIVATE;
-    area = mmap(0, memory, PROT_READ | PROT_WRITE, flags, fd, 0);
-#else
     area = mmap(0, memory, PROT_READ | PROT_WRITE, MAP_PRIVATE, fd, 0);
-#endif
     if (area == MAP_FAILED) {
         perror("file_ram_alloc: can't mmap RAM pages");
         close(fd);
         return (NULL);
     }
+
+    if (mem_prealloc) {
+        int ret, i;
+        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("file_ram_alloc: fail to install signal handler");
+            exit(1);
+        }
+
+        /* unblock SIGBUS */
+        pthread_sigmask(SIG_BLOCK, NULL, &oldset);
+        sigemptyset(&set);
+        sigaddset(&set, SIGBUS);
+        pthread_sigmask(SIG_UNBLOCK, &set, NULL);
+
+        if (sigsetjmp(sigjump, 1)) {
+            fprintf(stderr, "file_ram_alloc: failed to preallocate pages\n");
+            exit(1);
+        }
+
+        /* MAP_POPULATE silently ignores failures */
+        for (i = 0; i < (memory/hpagesize)-1; i++) {
+            memset(area + (hpagesize*i), 0, 1);
+        }
+
+        ret = sigaction(SIGBUS, &oldact, NULL);
+        if (ret) {
+            perror("file_ram_alloc: fail to reinstall signal handler");
+            exit(1);
+        }
+
+        if (sigismember(&oldset, SIGBUS)) {
+            sigemptyset(&set);
+            sigaddset(&set, SIGBUS);
+            pthread_sigmask(SIG_BLOCK, &set, NULL);
+        }
+    }
+
     block->fd = fd;
     return area;
 }
Index: qemu/vl.c
===================================================================
--- qemu.orig/vl.c
+++ qemu/vl.c
@@ -188,9 +188,7 @@ static int display_remote;
 const char* keyboard_layout = NULL;
 ram_addr_t ram_size;
 const char *mem_path = NULL;
-#ifdef MAP_POPULATE
 int mem_prealloc = 0; /* force preallocation of physical target memory */
-#endif
 int nb_nics;
 NICInfo nd_table[MAX_NICS];
 int autostart;
@@ -3205,11 +3203,9 @@ int main(int argc, char **argv, char **e
             case QEMU_OPTION_mempath:
                 mem_path = optarg;
                 break;
-#ifdef MAP_POPULATE
             case QEMU_OPTION_mem_prealloc:
                 mem_prealloc = 1;
                 break;
-#endif
             case QEMU_OPTION_d:
                 log_mask = optarg;
                 break;
Index: qemu/qemu-options.def
===================================================================
--- qemu.orig/qemu-options.def
+++ qemu/qemu-options.def
@@ -66,11 +66,9 @@ stringify(DEFAULT_RAM_SIZE) "]\n", QEMU_
 DEF("mem-path", HAS_ARG, QEMU_OPTION_mempath,
 "-mem-path FILE  provide backing storage for guest RAM\n", QEMU_ARCH_ALL)
 
-#ifdef MAP_POPULATE
 DEF("mem-prealloc", 0, QEMU_OPTION_mem_prealloc,
 "-mem-prealloc   preallocate guest memory (use with -mem-path)\n",
 QEMU_ARCH_ALL)
-#endif
 
 DEF("k", HAS_ARG, QEMU_OPTION_k,
 "-k language     use keyboard layout (for example 'fr' for French)\n",
Index: git/qemu/qemu-options.hx
===================================================================
--- qemu.orig/qemu-options.hx
+++ qemu/qemu-options.hx
@@ -228,7 +228,6 @@ STEXI
 Allocate guest RAM from a temporarily created file in @var{path}.
 ETEXI
 
-#ifdef MAP_POPULATE
 DEF("mem-prealloc", 0, QEMU_OPTION_mem_prealloc,
     "-mem-prealloc   preallocate guest memory (use with -mem-path)\n",
     QEMU_ARCH_ALL)
@@ -237,7 +236,6 @@ STEXI
 @findex -mem-prealloc
 Preallocate memory when using -mem-path.
 ETEXI
-#endif
 
 DEF("k", HAS_ARG, QEMU_OPTION_k,
     "-k language     use keyboard layout (for example 'fr' for French)\n",