block/backup: add 'always' bitmap sync policy

[qemu.git] / block / file-posix.c

diff --git a/block/file-posix.c b/block/file-posix.c
index 6e6bf3f4a57b63edcf5cdf4c7fa94c5c5a41231d..b8b4dad553ab298db217571f93d58683bec0ca3d 100644 (file)
--- a/block/file-posix.c
+++ b/block/file-posix.c
@@ -146,6 +146,7 @@ typedef struct BDRVRawState {
     uint64_t locked_shared_perm;
 
     int perm_change_fd;
+    int perm_change_flags;
     BDRVReopenState *reopen_state;
 
 #ifdef CONFIG_XFS
@@ -322,6 +323,7 @@ static void raw_probe_alignment(BlockDriverState *bs, int fd, Error **errp)
     BDRVRawState *s = bs->opaque;
     char *buf;
     size_t max_align = MAX(MAX_BLOCKSIZE, getpagesize());
+    size_t alignments[] = {1, 512, 1024, 2048, 4096};
 
     /* For SCSI generic devices the alignment is not really used.
        With buffered I/O, we don't have any restrictions. */
@@ -348,25 +350,38 @@ static void raw_probe_alignment(BlockDriverState *bs, int fd, Error **errp)
     }
 #endif
 
-    /* If we could not get the sizes so far, we can only guess them */
-    if (!s->buf_align) {
+    /*
+     * If we could not get the sizes so far, we can only guess them. First try
+     * to detect request alignment, since it is more likely to succeed. Then
+     * try to detect buf_align, which cannot be detected in some cases (e.g.
+     * Gluster). If buf_align cannot be detected, we fallback to the value of
+     * request_alignment.
+     */
+
+    if (!bs->bl.request_alignment) {
+        int i;
         size_t align;
-        buf = qemu_memalign(max_align, 2 * max_align);
-        for (align = 512; align <= max_align; align <<= 1) {
-            if (raw_is_io_aligned(fd, buf + align, max_align)) {
-                s->buf_align = align;
+        buf = qemu_memalign(max_align, max_align);
+        for (i = 0; i < ARRAY_SIZE(alignments); i++) {
+            align = alignments[i];
+            if (raw_is_io_aligned(fd, buf, align)) {
+                /* Fallback to safe value. */
+                bs->bl.request_alignment = (align != 1) ? align : max_align;
                 break;
             }
         }
         qemu_vfree(buf);
     }
 
-    if (!bs->bl.request_alignment) {
+    if (!s->buf_align) {
+        int i;
         size_t align;
-        buf = qemu_memalign(s->buf_align, max_align);
-        for (align = 512; align <= max_align; align <<= 1) {
-            if (raw_is_io_aligned(fd, buf, align)) {
-                bs->bl.request_alignment = align;
+        buf = qemu_memalign(max_align, 2 * max_align);
+        for (i = 0; i < ARRAY_SIZE(alignments); i++) {
+            align = alignments[i];
+            if (raw_is_io_aligned(fd, buf + align, max_align)) {
+                /* Fallback to request_aligment. */
+                s->buf_align = (align != 1) ? align : bs->bl.request_alignment;
                 break;
             }
         }
@@ -1037,15 +1052,13 @@ static void raw_reopen_abort(BDRVReopenState *state)
     s->reopen_state = NULL;
 }
 
-static int hdev_get_max_transfer_length(BlockDriverState *bs, int fd)
+static int sg_get_max_transfer_length(int fd)
 {
 #ifdef BLKSECTGET
     int max_bytes = 0;
-    short max_sectors = 0;
-    if (bs->sg && ioctl(fd, BLKSECTGET, &max_bytes) == 0) {
+
+    if (ioctl(fd, BLKSECTGET, &max_bytes) == 0) {
         return max_bytes;
-    } else if (!bs->sg && ioctl(fd, BLKSECTGET, &max_sectors) == 0) {
-        return max_sectors << BDRV_SECTOR_BITS;
     } else {
         return -errno;
     }
@@ -1054,25 +1067,31 @@ static int hdev_get_max_transfer_length(BlockDriverState *bs, int fd)
 #endif
 }
 
-static int hdev_get_max_segments(const struct stat *st)
+static int sg_get_max_segments(int fd)
 {
 #ifdef CONFIG_LINUX
     char buf[32];
     const char *end;
-    char *sysfspath;
+    char *sysfspath = NULL;
     int ret;
-    int fd = -1;
+    int sysfd = -1;
     long max_segments;
+    struct stat st;
+
+    if (fstat(fd, &st)) {
+        ret = -errno;
+        goto out;
+    }
 
     sysfspath = g_strdup_printf("/sys/dev/block/%u:%u/queue/max_segments",
-                                major(st->st_rdev), minor(st->st_rdev));
-    fd = open(sysfspath, O_RDONLY);
-    if (fd == -1) {
+                                major(st.st_rdev), minor(st.st_rdev));
+    sysfd = open(sysfspath, O_RDONLY);
+    if (sysfd == -1) {
         ret = -errno;
         goto out;
     }
     do {
-        ret = read(fd, buf, sizeof(buf) - 1);
+        ret = read(sysfd, buf, sizeof(buf) - 1);
     } while (ret == -1 && errno == EINTR);
     if (ret < 0) {
         ret = -errno;
@@ -1089,8 +1108,8 @@ static int hdev_get_max_segments(const struct stat *st)
     }
 
 out:
-    if (fd != -1) {
-        close(fd);
+    if (sysfd != -1) {
+        close(sysfd);
     }
     g_free(sysfspath);
     return ret;
@@ -1102,19 +1121,17 @@ out:
 static void raw_refresh_limits(BlockDriverState *bs, Error **errp)
 {
     BDRVRawState *s = bs->opaque;
-    struct stat st;
 
-    if (!fstat(s->fd, &st)) {
-        if (S_ISBLK(st.st_mode) || S_ISCHR(st.st_mode)) {
-            int ret = hdev_get_max_transfer_length(bs, s->fd);
-            if (ret > 0 && ret <= BDRV_REQUEST_MAX_BYTES) {
-                bs->bl.max_transfer = pow2floor(ret);
-            }
-            ret = hdev_get_max_segments(&st);
-            if (ret > 0) {
-                bs->bl.max_transfer = MIN(bs->bl.max_transfer,
-                                          ret * getpagesize());
-            }
+    if (bs->sg) {
+        int ret = sg_get_max_transfer_length(s->fd);
+
+        if (ret > 0 && ret <= BDRV_REQUEST_MAX_BYTES) {
+            bs->bl.max_transfer = pow2floor(ret);
+        }
+
+        ret = sg_get_max_segments(s->fd);
+        if (ret > 0) {
+            bs->bl.max_transfer = MIN(bs->bl.max_transfer, ret * getpagesize());
         }
     }
 
@@ -2752,7 +2769,11 @@ static QemuOptsList raw_create_opts = {
         {
             .name = BLOCK_OPT_PREALLOC,
             .type = QEMU_OPT_STRING,
-            .help = "Preallocation mode (allowed values: off, falloc, full)"
+            .help = "Preallocation mode (allowed values: off"
+#ifdef CONFIG_POSIX_FALLOCATE
+                    ", falloc"
+#endif
+                    ", full)"
         },
         { /* end of list */ }
     }
@@ -2784,6 +2805,7 @@ static int raw_check_perm(BlockDriverState *bs, uint64_t perm, uint64_t shared,
         assert(s->reopen_state->shared_perm == shared);
         rs = s->reopen_state->opaque;
         s->perm_change_fd = rs->fd;
+        s->perm_change_flags = rs->open_flags;
     } else {
         /* We may need a new fd if auto-read-only switches the mode */
         ret = raw_reconfigure_getfd(bs, bs->open_flags, &open_flags, perm,
@@ -2792,6 +2814,7 @@ static int raw_check_perm(BlockDriverState *bs, uint64_t perm, uint64_t shared,
             return ret;
         } else if (ret != s->fd) {
             s->perm_change_fd = ret;
+            s->perm_change_flags = open_flags;
         }
     }
 
@@ -2830,6 +2853,7 @@ static void raw_set_perm(BlockDriverState *bs, uint64_t perm, uint64_t shared)
     if (s->perm_change_fd && s->fd != s->perm_change_fd) {
         qemu_close(s->fd);
         s->fd = s->perm_change_fd;
+        s->open_flags = s->perm_change_flags;
     }
     s->perm_change_fd = 0;