[Qemu-devel] [PULL 3/8] exec: Fix memory allocation when memory path names new file

[Paolo Bonzini]

From: Markus Armbruster <address@hidden>

Commit 8d31d6b extended file_ram_alloc() to accept file names in
addition to directory names.  Even though it passes O_CREAT to open(),
it actually works only for existing files.  Reproducer adapted from
the commit's qemu-doc.texi update:

    $ qemu-system-x86_64 -object 
memory-backend-file,size=2M,mem-path=/dev/hugepages/my-shmem-file,id=mb1
    qemu-system-x86_64: -object 
memory-backend-file,size=2M,mem-path=/dev/hugepages/my-shmem-file,id=mb1: 
failed to get page size of file /dev/hugepages/my-shmem-file: No such file or 
directory

This is because we first get the page size for @path, then open the
actual file.  Unwise even before the flawed commit, because the
directory could change in between, invalidating the page size.
Unlikely to bite in practice.

Rearrange the code to create the file (if necessary) before getting
its page size.  Carefully avoid TOCTTOU conditions with a method
suggested by Paolo Bonzini.

While there, replace "hugepages" by "guest RAM" in error messages,
because host memory backends can be used for purposes other than huge
pages, e.g. /dev/shm/ shared memory.  Help text of -mem-path agrees.

Cc: Paolo Bonzini <address@hidden>
Signed-off-by: Markus Armbruster <address@hidden>
Message-Id: <address@hidden>
Signed-off-by: Paolo Bonzini <address@hidden>
---
 exec.c | 107 +++++++++++++++++++++++++++++++++++++++--------------------------
 1 file changed, 64 insertions(+), 43 deletions(-)

diff --git a/exec.c b/exec.c
index f09dd4e..3380836 100644
--- a/exec.c
+++ b/exec.c
@@ -1233,19 +1233,17 @@ void qemu_mutex_unlock_ramlist(void)
 
 #define HUGETLBFS_MAGIC       0x958458f6
 
-static long gethugepagesize(const char *path, Error **errp)
+static long gethugepagesize(int fd)
 {
     struct statfs fs;
     int ret;
 
     do {
-        ret = statfs(path, &fs);
+        ret = fstatfs(fd, &fs);
     } while (ret != 0 && errno == EINTR);
 
     if (ret != 0) {
-        error_setg_errno(errp, errno, "failed to get page size of file %s",
-                         path);
-        return 0;
+        return -1;
     }
 
     return fs.f_bsize;
@@ -1256,60 +1254,79 @@ static void *file_ram_alloc(RAMBlock *block,
                             const char *path,
                             Error **errp)
 {
-    struct stat st;
+    bool unlink_on_error = false;
     char *filename;
     char *sanitized_name;
     char *c;
     void *area;
     int fd;
-    uint64_t hpagesize;
-    Error *local_err = NULL;
-
-    hpagesize = gethugepagesize(path, &local_err);
-    if (local_err) {
-        error_propagate(errp, local_err);
-        goto error;
-    }
-    block->mr->align = hpagesize;
-
-    if (memory < hpagesize) {
-        error_setg(errp, "memory size 0x" RAM_ADDR_FMT " must be equal to "
-                   "or larger than huge page size 0x%" PRIx64,
-                   memory, hpagesize);
-        goto error;
-    }
+    int64_t hpagesize;
 
     if (kvm_enabled() && !kvm_has_sync_mmu()) {
         error_setg(errp,
                    "host lacks kvm mmu notifiers, -mem-path unsupported");
-        goto error;
+        return NULL;
     }
 
-    if (!stat(path, &st) && S_ISDIR(st.st_mode)) {
-        /* Make name safe to use with mkstemp by replacing '/' with '_'. */
-        sanitized_name = g_strdup(memory_region_name(block->mr));
-        for (c = sanitized_name; *c != '\0'; c++) {
-            if (*c == '/') {
-                *c = '_';
-            }
+    for (;;) {
+        fd = open(path, O_RDWR);
+        if (fd >= 0) {
+            /* @path names an existing file, use it */
+            break;
         }
+        if (errno == ENOENT) {
+            /* @path names a file that doesn't exist, create it */
+            fd = open(path, O_RDWR | O_CREAT | O_EXCL, 0644);
+            if (fd >= 0) {
+                unlink_on_error = true;
+                break;
+            }
+        } else if (errno == EISDIR) {
+            /* @path names a directory, create a file there */
+            /* Make name safe to use with mkstemp by replacing '/' with '_'. */
+            sanitized_name = g_strdup(memory_region_name(block->mr));
+            for (c = sanitized_name; *c != '\0'; c++) {
+                if (*c == '/') {
+                    *c = '_';
+                }
+            }
 
-        filename = g_strdup_printf("%s/qemu_back_mem.%s.XXXXXX", path,
-                                   sanitized_name);
-        g_free(sanitized_name);
+            filename = g_strdup_printf("%s/qemu_back_mem.%s.XXXXXX", path,
+                                       sanitized_name);
+            g_free(sanitized_name);
 
-        fd = mkstemp(filename);
-        if (fd >= 0) {
-            unlink(filename);
+            fd = mkstemp(filename);
+            if (fd >= 0) {
+                unlink(filename);
+                g_free(filename);
+                break;
+            }
+            g_free(filename);
         }
-        g_free(filename);
-    } else {
-        fd = open(path, O_RDWR | O_CREAT, 0644);
+        if (errno != EEXIST && errno != EINTR) {
+            error_setg_errno(errp, errno,
+                             "can't open backing store %s for guest RAM",
+                             path);
+            goto error;
+        }
+        /*
+         * Try again on EINTR and EEXIST.  The latter happens when
+         * something else creates the file between our two open().
+         */
     }
 
-    if (fd < 0) {
-        error_setg_errno(errp, errno,
-                         "unable to create backing store for hugepages");
+    hpagesize = gethugepagesize(fd);
+    if (hpagesize < 0) {
+        error_setg_errno(errp, errno, "can't get page size for %s",
+                         path);
+        goto error;
+    }
+    block->mr->align = hpagesize;
+
+    if (memory < hpagesize) {
+        error_setg(errp, "memory size 0x" RAM_ADDR_FMT " must be equal to "
+                   "or larger than page size 0x%" PRIx64,
+                   memory, hpagesize);
         goto error;
     }
 
@@ -1328,7 +1345,7 @@ static void *file_ram_alloc(RAMBlock *block,
     area = qemu_ram_mmap(fd, memory, hpagesize, block->flags & RAM_SHARED);
     if (area == MAP_FAILED) {
         error_setg_errno(errp, errno,
-                         "unable to map backing store for hugepages");
+                         "unable to map backing store for guest RAM");
         close(fd);
         goto error;
     }
@@ -1341,6 +1358,10 @@ static void *file_ram_alloc(RAMBlock *block,
     return area;
 
 error:
+    if (unlink_on_error) {
+        unlink(path);
+    }
+    close(fd);
     return NULL;
 }
 #endif
-- 
1.8.3.1