block/raw-posix: Try both FIEMAP and SEEK_HOLE

The current version of raw-posix always uses ioctl(FS_IOC_FIEMAP) if
FIEMAP is available; lseek with SEEK_HOLE/SEEK_DATA are not even
compiled in in this case. However, there may be implementations which
support the latter but not the former (e.g., NFSv4.2) as well as vice
versa.

To cover both cases, try FIEMAP first (as this will return -ENOTSUP if
not supported instead of returning a failsafe value (everything
allocated as a single extent)) and if that does not work, fall back to
SEEK_HOLE/SEEK_DATA.

Signed-off-by: Max Reitz <mreitz@redhat.com>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>

diff --git a/block/raw-posix.c b/block/raw-posix.c
index 3ce026db589a887389a43163d793943ace61f257..6586a0c9e1a602715ff526d65dac791af411fc5b 100644 (file)
--- a/block/raw-posix.c
+++ b/block/raw-posix.c
@@ -146,6 +146,9 @@ typedef struct BDRVRawState {
     bool has_discard:1;
     bool has_write_zeroes:1;
     bool discard_zeroes:1;
+#ifdef CONFIG_FIEMAP
+    bool skip_fiemap;
+#endif
 } BDRVRawState;
 
 typedef struct BDRVRawReopenState {
@@ -1272,53 +1275,29 @@ static int raw_create(const char *filename, QEMUOptionParameter *options,
     return result;
 }
 
-/*
- * Returns true iff the specified sector is present in the disk image. Drivers
- * not implementing the functionality are assumed to not support backing files,
- * hence all their sectors are reported as allocated.
- *
- * If 'sector_num' is beyond the end of the disk image the return value is 0
- * and 'pnum' is set to 0.
- *
- * 'pnum' is set to the number of sectors (including and immediately following
- * the specified sector) that are known to be in the same
- * allocated/unallocated state.
- *
- * 'nb_sectors' is the max value 'pnum' should be set to.  If nb_sectors goes
- * beyond the end of the disk image it will be clamped.
- */
-static int64_t coroutine_fn raw_co_get_block_status(BlockDriverState *bs,
-                                            int64_t sector_num,
-                                            int nb_sectors, int *pnum)
+static int64_t try_fiemap(BlockDriverState *bs, off_t start, off_t *data,
+                          off_t *hole, int nb_sectors, int *pnum)
 {
-    off_t start, data, hole;
-    int64_t ret;
-
-    ret = fd_open(bs);
-    if (ret < 0) {
-        return ret;
-    }
-
-    start = sector_num * BDRV_SECTOR_SIZE;
-    ret = BDRV_BLOCK_DATA | BDRV_BLOCK_OFFSET_VALID | start;
-
 #ifdef CONFIG_FIEMAP
-
     BDRVRawState *s = bs->opaque;
+    int64_t ret = BDRV_BLOCK_DATA | BDRV_BLOCK_OFFSET_VALID | start;
     struct {
         struct fiemap fm;
         struct fiemap_extent fe;
     } f;
 
+    if (s->skip_fiemap) {
+        return -ENOTSUP;
+    }
+
     f.fm.fm_start = start;
     f.fm.fm_length = (int64_t)nb_sectors * BDRV_SECTOR_SIZE;
     f.fm.fm_flags = 0;
     f.fm.fm_extent_count = 1;
     f.fm.fm_reserved = 0;
     if (ioctl(s->fd, FS_IOC_FIEMAP, &f) == -1) {
-        /* Assume everything is allocated.  */
-        *pnum = nb_sectors;
-        return ret;
+        s->skip_fiemap = true;
+        return -errno;
     }
 
     if (f.fm.fm_mapped_extents == 0) {
@@ -1326,44 +1305,92 @@ static int64_t coroutine_fn raw_co_get_block_status(BlockDriverState *bs,
          * f.fm.fm_start + f.fm.fm_length must be clamped to the file size!
          */
         off_t length = lseek(s->fd, 0, SEEK_END);
-        hole = f.fm.fm_start;
-        data = MIN(f.fm.fm_start + f.fm.fm_length, length);
+        *hole = f.fm.fm_start;
+        *data = MIN(f.fm.fm_start + f.fm.fm_length, length);
     } else {
-        data = f.fe.fe_logical;
-        hole = f.fe.fe_logical + f.fe.fe_length;
+        *data = f.fe.fe_logical;
+        *hole = f.fe.fe_logical + f.fe.fe_length;
         if (f.fe.fe_flags & FIEMAP_EXTENT_UNWRITTEN) {
             ret |= BDRV_BLOCK_ZERO;
         }
     }
 
-#elif defined SEEK_HOLE && defined SEEK_DATA
+    return ret;
+#else
+    return -ENOTSUP;
+#endif
+}
 
+static int64_t try_seek_hole(BlockDriverState *bs, off_t start, off_t *data,
+                             off_t *hole, int *pnum)
+{
+#if defined SEEK_HOLE && defined SEEK_DATA
     BDRVRawState *s = bs->opaque;
 
-    hole = lseek(s->fd, start, SEEK_HOLE);
-    if (hole == -1) {
+    *hole = lseek(s->fd, start, SEEK_HOLE);
+    if (*hole == -1) {
         /* -ENXIO indicates that sector_num was past the end of the file.
          * There is a virtual hole there.  */
         assert(errno != -ENXIO);
 
-        /* Most likely EINVAL.  Assume everything is allocated.  */
-        *pnum = nb_sectors;
-        return ret;
+        return -errno;
     }
 
-    if (hole > start) {
-        data = start;
+    if (*hole > start) {
+        *data = start;
     } else {
         /* On a hole.  We need another syscall to find its end.  */
-        data = lseek(s->fd, start, SEEK_DATA);
-        if (data == -1) {
-            data = lseek(s->fd, 0, SEEK_END);
+        *data = lseek(s->fd, start, SEEK_DATA);
+        if (*data == -1) {
+            *data = lseek(s->fd, 0, SEEK_END);
         }
     }
+
+    return BDRV_BLOCK_DATA | BDRV_BLOCK_OFFSET_VALID | start;
 #else
-    data = 0;
-    hole = start + nb_sectors * BDRV_SECTOR_SIZE;
+    return -ENOTSUP;
 #endif
+}
+
+/*
+ * Returns true iff the specified sector is present in the disk image. Drivers
+ * not implementing the functionality are assumed to not support backing files,
+ * hence all their sectors are reported as allocated.
+ *
+ * If 'sector_num' is beyond the end of the disk image the return value is 0
+ * and 'pnum' is set to 0.
+ *
+ * 'pnum' is set to the number of sectors (including and immediately following
+ * the specified sector) that are known to be in the same
+ * allocated/unallocated state.
+ *
+ * 'nb_sectors' is the max value 'pnum' should be set to.  If nb_sectors goes
+ * beyond the end of the disk image it will be clamped.
+ */
+static int64_t coroutine_fn raw_co_get_block_status(BlockDriverState *bs,
+                                                    int64_t sector_num,
+                                                    int nb_sectors, int *pnum)
+{
+    off_t start, data = 0, hole = 0;
+    int64_t ret;
+
+    ret = fd_open(bs);
+    if (ret < 0) {
+        return ret;
+    }
+
+    start = sector_num * BDRV_SECTOR_SIZE;
+
+    ret = try_fiemap(bs, start, &data, &hole, nb_sectors, pnum);
+    if (ret < 0) {
+        ret = try_seek_hole(bs, start, &data, &hole, pnum);
+        if (ret < 0) {
+            /* Assume everything is allocated. */
+            data = 0;
+            hole = start + nb_sectors * BDRV_SECTOR_SIZE;
+            ret = BDRV_BLOCK_DATA | BDRV_BLOCK_OFFSET_VALID | start;
+        }
+    }
 
     if (data <= start) {
         /* On a data extent, compute sectors to the end of the extent.  */