return MIN(nb_sectors, ret);
}
+static uint32_t host_cluster_index(BDRVParallelsState *s, int64_t off)
+{
+ off -= s->data_start << BDRV_SECTOR_BITS;
+ return off / s->cluster_size;
+}
+
static int64_t block_status(BDRVParallelsState *s, int64_t sector_num,
int nb_sectors, int *pnum)
{
return start_off;
}
+static void parallels_set_bat_entry(BDRVParallelsState *s,
+ uint32_t index, uint32_t offset)
+{
+ s->bat_bitmap[index] = cpu_to_le32(offset);
+ bitmap_set(s->bat_dirty_bmap, bat_entry_off(index) / s->bat_dirty_block, 1);
+}
+
+static int mark_used(BlockDriverState *bs, unsigned long *bitmap,
+ uint32_t bitmap_size, int64_t off, uint32_t count)
+{
+ BDRVParallelsState *s = bs->opaque;
+ uint32_t cluster_index = host_cluster_index(s, off);
+ unsigned long next_used;
+ if (cluster_index + count > bitmap_size) {
+ return -E2BIG;
+ }
+ next_used = find_next_bit(bitmap, bitmap_size, cluster_index);
+ if (next_used < cluster_index + count) {
+ return -EBUSY;
+ }
+ bitmap_set(bitmap, cluster_index, count);
+ return 0;
+}
+
+/*
+ * Collect used bitmap. The image can contain errors, we should fill the
+ * bitmap anyway, as much as we can. This information will be used for
+ * error resolution.
+ */
+static int parallels_fill_used_bitmap(BlockDriverState *bs)
+{
+ BDRVParallelsState *s = bs->opaque;
+ int64_t payload_bytes;
+ uint32_t i;
+ int err = 0;
+
+ payload_bytes = bdrv_getlength(bs->file->bs);
+ if (payload_bytes < 0) {
+ return payload_bytes;
+ }
+ payload_bytes -= s->data_start * BDRV_SECTOR_SIZE;
+ if (payload_bytes < 0) {
+ return -EINVAL;
+ }
+
+ s->used_bmap_size = DIV_ROUND_UP(payload_bytes, s->cluster_size);
+ if (s->used_bmap_size == 0) {
+ return 0;
+ }
+ s->used_bmap = bitmap_try_new(s->used_bmap_size);
+ if (s->used_bmap == NULL) {
+ return -ENOMEM;
+ }
+
+ for (i = 0; i < s->bat_size; i++) {
+ int err2;
+ int64_t host_off = bat2sect(s, i) << BDRV_SECTOR_BITS;
+ if (host_off == 0) {
+ continue;
+ }
+
+ err2 = mark_used(bs, s->used_bmap, s->used_bmap_size, host_off, 1);
+ if (err2 < 0 && err == 0) {
+ err = err2;
+ }
+ }
+ return err;
+}
+
+static void parallels_free_used_bitmap(BlockDriverState *bs)
+{
+ BDRVParallelsState *s = bs->opaque;
+ s->used_bmap_size = 0;
+ g_free(s->used_bmap);
+}
+
static int64_t coroutine_fn GRAPH_RDLOCK
allocate_clusters(BlockDriverState *bs, int64_t sector_num,
int nb_sectors, int *pnum)
{
int ret = 0;
BDRVParallelsState *s = bs->opaque;
- int64_t pos, space, idx, to_allocate, i, len;
+ int64_t i, pos, idx, to_allocate, first_free, host_off;
pos = block_status(s, sector_num, nb_sectors, pnum);
if (pos > 0) {
idx = sector_num / s->tracks;
to_allocate = DIV_ROUND_UP(sector_num + *pnum, s->tracks) - idx;
- /* This function is called only by parallels_co_writev(), which will never
+ /*
+ * This function is called only by parallels_co_writev(), which will never
* pass a sector_num at or beyond the end of the image (because the block
* layer never passes such a sector_num to that function). Therefore, idx
* is always below s->bat_size.
* exceed the image end. Therefore, idx + to_allocate cannot exceed
* s->bat_size.
* Note that s->bat_size is an unsigned int, therefore idx + to_allocate
- * will always fit into a uint32_t. */
+ * will always fit into a uint32_t.
+ */
assert(idx < s->bat_size && idx + to_allocate <= s->bat_size);
- space = to_allocate * s->tracks;
- len = bdrv_getlength(bs->file->bs);
- if (len < 0) {
- return len;
- }
- if (s->data_end + space > (len >> BDRV_SECTOR_BITS)) {
- space += s->prealloc_size;
+ first_free = find_first_zero_bit(s->used_bmap, s->used_bmap_size);
+ if (first_free == s->used_bmap_size) {
+ uint32_t new_usedsize;
+ int64_t bytes = to_allocate * s->cluster_size;
+ bytes += s->prealloc_size * BDRV_SECTOR_SIZE;
+
+ host_off = s->data_end * BDRV_SECTOR_SIZE;
+
/*
* We require the expanded size to read back as zero. If the
* user permitted truncation, we try that; but if it fails, we
* force the safer-but-slower fallocate.
*/
if (s->prealloc_mode == PRL_PREALLOC_MODE_TRUNCATE) {
- ret = bdrv_co_truncate(bs->file,
- (s->data_end + space) << BDRV_SECTOR_BITS,
+ ret = bdrv_co_truncate(bs->file, host_off + bytes,
false, PREALLOC_MODE_OFF,
BDRV_REQ_ZERO_WRITE, NULL);
if (ret == -ENOTSUP) {
}
}
if (s->prealloc_mode == PRL_PREALLOC_MODE_FALLOCATE) {
- ret = bdrv_co_pwrite_zeroes(bs->file,
- s->data_end << BDRV_SECTOR_BITS,
- space << BDRV_SECTOR_BITS, 0);
+ ret = bdrv_co_pwrite_zeroes(bs->file, host_off, bytes, 0);
}
if (ret < 0) {
return ret;
}
+
+ new_usedsize = s->used_bmap_size + bytes / s->cluster_size;
+ s->used_bmap = bitmap_zero_extend(s->used_bmap, s->used_bmap_size,
+ new_usedsize);
+ s->used_bmap_size = new_usedsize;
+ } else {
+ int64_t next_used;
+ next_used = find_next_bit(s->used_bmap, s->used_bmap_size, first_free);
+
+ /* Not enough continuous clusters in the middle, adjust the size */
+ if (next_used - first_free < to_allocate) {
+ to_allocate = next_used - first_free;
+ *pnum = (idx + to_allocate) * s->tracks - sector_num;
+ }
+
+ host_off = s->data_start * BDRV_SECTOR_SIZE;
+ host_off += first_free * s->cluster_size;
+
+ /*
+ * No need to preallocate if we are using tail area from the above
+ * branch. In the other case we are likely re-using hole. Preallocate
+ * the space if required by the prealloc_mode.
+ */
+ if (s->prealloc_mode == PRL_PREALLOC_MODE_FALLOCATE &&
+ host_off < s->data_end * BDRV_SECTOR_SIZE) {
+ ret = bdrv_co_pwrite_zeroes(bs->file, host_off,
+ s->cluster_size * to_allocate, 0);
+ if (ret < 0) {
+ return ret;
+ }
+ }
}
- /* Try to read from backing to fill empty clusters
+ /*
+ * Try to read from backing to fill empty clusters
* FIXME: 1. previous write_zeroes may be redundant
* 2. most of data we read from backing will be rewritten by
* parallels_co_writev. On aligned-to-cluster write we do not need
* this read at all.
* 3. it would be good to combine write of data from backing and new
- * data into one write call */
+ * data into one write call.
+ */
if (bs->backing) {
int64_t nb_cow_sectors = to_allocate * s->tracks;
int64_t nb_cow_bytes = nb_cow_sectors << BDRV_SECTOR_BITS;
}
}
+ ret = mark_used(bs, s->used_bmap, s->used_bmap_size, host_off, to_allocate);
+ if (ret < 0) {
+ /* Image consistency is broken. Alarm! */
+ return ret;
+ }
for (i = 0; i < to_allocate; i++) {
- s->bat_bitmap[idx + i] = cpu_to_le32(s->data_end / s->off_multiplier);
- s->data_end += s->tracks;
- bitmap_set(s->bat_dirty_bmap,
- bat_entry_off(idx + i) / s->bat_dirty_block, 1);
+ parallels_set_bat_entry(s, idx + i,
+ host_off / BDRV_SECTOR_SIZE / s->off_multiplier);
+ host_off += s->cluster_size;
+ }
+ if (host_off > s->data_end * BDRV_SECTOR_SIZE) {
+ s->data_end = host_off / BDRV_SECTOR_SIZE;
}
return bat2sect(s, idx) + sector_num % s->tracks;
static int coroutine_fn GRAPH_RDLOCK
-parallels_co_check(BlockDriverState *bs, BdrvCheckResult *res,
- BdrvCheckMode fix)
+parallels_co_pdiscard(BlockDriverState *bs, int64_t offset, int64_t bytes)
{
+ int ret = 0;
+ uint32_t cluster, count;
BDRVParallelsState *s = bs->opaque;
- int64_t size, prev_off, high_off;
- int ret;
- uint32_t i;
- bool flush_bat = false;
- size = bdrv_getlength(bs->file->bs);
- if (size < 0) {
- res->check_errors++;
- return size;
+ /*
+ * The image does not support ZERO mark inside the BAT, which means that
+ * stale data could be exposed from the backing file.
+ */
+ if (bs->backing) {
+ return -ENOTSUP;
+ }
+
+ if (!QEMU_IS_ALIGNED(offset, s->cluster_size)) {
+ return -ENOTSUP;
+ } else if (!QEMU_IS_ALIGNED(bytes, s->cluster_size)) {
+ return -ENOTSUP;
}
+ cluster = offset / s->cluster_size;
+ count = bytes / s->cluster_size;
+
qemu_co_mutex_lock(&s->lock);
- if (s->header_unclean) {
- fprintf(stderr, "%s image was not closed correctly\n",
- fix & BDRV_FIX_ERRORS ? "Repairing" : "ERROR");
- res->corruptions++;
- if (fix & BDRV_FIX_ERRORS) {
- /* parallels_close will do the job right */
- res->corruptions_fixed++;
- s->header_unclean = false;
+ for (; count > 0; cluster++, count--) {
+ int64_t host_off = bat2sect(s, cluster) << BDRV_SECTOR_BITS;
+ if (host_off == 0) {
+ continue;
+ }
+
+ ret = bdrv_co_pdiscard(bs->file, host_off, s->cluster_size);
+ if (ret < 0) {
+ goto done;
}
+
+ parallels_set_bat_entry(s, cluster, 0);
+ bitmap_clear(s->used_bmap, host_cluster_index(s, host_off), 1);
}
+done:
+ qemu_co_mutex_unlock(&s->lock);
+ return ret;
+}
- res->bfi.total_clusters = s->bat_size;
- res->bfi.compressed_clusters = 0; /* compression is not supported */
+static int coroutine_fn GRAPH_RDLOCK
+parallels_co_pwrite_zeroes(BlockDriverState *bs, int64_t offset, int64_t bytes,
+ BdrvRequestFlags flags)
+{
+ /*
+ * The zero flag is missed in the Parallels format specification. We can
+ * resort to discard if we have no backing file (this condition is checked
+ * inside parallels_co_pdiscard().
+ */
+ return parallels_co_pdiscard(bs, offset, bytes);
+}
- high_off = 0;
- prev_off = 0;
- for (i = 0; i < s->bat_size; i++) {
- int64_t off = bat2sect(s, i) << BDRV_SECTOR_BITS;
- if (off == 0) {
- prev_off = 0;
- continue;
+
+static void parallels_check_unclean(BlockDriverState *bs,
+ BdrvCheckResult *res,
+ BdrvCheckMode fix)
+{
+ BDRVParallelsState *s = bs->opaque;
+
+ if (!s->header_unclean) {
+ return;
+ }
+
+ fprintf(stderr, "%s image was not closed correctly\n",
+ fix & BDRV_FIX_ERRORS ? "Repairing" : "ERROR");
+ res->corruptions++;
+ if (fix & BDRV_FIX_ERRORS) {
+ /* parallels_close will do the job right */
+ res->corruptions_fixed++;
+ s->header_unclean = false;
+ }
+}
+
+/*
+ * Returns true if data_off is correct, otherwise false. In both cases
+ * correct_offset is set to the proper value.
+ */
+static bool parallels_test_data_off(BDRVParallelsState *s,
+ int64_t file_nb_sectors,
+ uint32_t *correct_offset)
+{
+ uint32_t data_off, min_off;
+ bool old_magic;
+
+ /*
+ * There are two slightly different image formats: with "WithoutFreeSpace"
+ * or "WithouFreSpacExt" magic words. Call the first one as "old magic".
+ * In such images data_off field can be zero. In this case the offset is
+ * calculated as the end of BAT table plus some padding to ensure sector
+ * size alignment.
+ */
+ old_magic = !memcmp(s->header->magic, HEADER_MAGIC, 16);
+
+ min_off = DIV_ROUND_UP(bat_entry_off(s->bat_size), BDRV_SECTOR_SIZE);
+ if (!old_magic) {
+ min_off = ROUND_UP(min_off, s->cluster_size / BDRV_SECTOR_SIZE);
+ }
+
+ if (correct_offset) {
+ *correct_offset = min_off;
+ }
+
+ data_off = le32_to_cpu(s->header->data_off);
+ if (data_off == 0 && old_magic) {
+ return true;
+ }
+
+ if (data_off < min_off || data_off > file_nb_sectors) {
+ return false;
+ }
+
+ if (correct_offset) {
+ *correct_offset = data_off;
+ }
+
+ return true;
+}
+
+static int coroutine_fn GRAPH_RDLOCK
+parallels_check_data_off(BlockDriverState *bs, BdrvCheckResult *res,
+ BdrvCheckMode fix)
+{
+ BDRVParallelsState *s = bs->opaque;
+ int64_t file_size;
+ uint32_t data_off;
+
+ file_size = bdrv_co_nb_sectors(bs->file->bs);
+ if (file_size < 0) {
+ res->check_errors++;
+ return file_size;
+ }
+
+ if (parallels_test_data_off(s, file_size, &data_off)) {
+ return 0;
+ }
+
+ res->corruptions++;
+ if (fix & BDRV_FIX_ERRORS) {
+ int err;
+ s->header->data_off = cpu_to_le32(data_off);
+ s->data_start = data_off;
+
+ parallels_free_used_bitmap(bs);
+ err = parallels_fill_used_bitmap(bs);
+ if (err == -ENOMEM) {
+ res->check_errors++;
+ return err;
}
- /* cluster outside the image */
- if (off > size) {
+ res->corruptions_fixed++;
+ }
+
+ fprintf(stderr, "%s data_off field has incorrect value\n",
+ fix & BDRV_FIX_ERRORS ? "Repairing" : "ERROR");
+
+ return 0;
+}
+
+static int coroutine_fn GRAPH_RDLOCK
+parallels_check_outside_image(BlockDriverState *bs, BdrvCheckResult *res,
+ BdrvCheckMode fix)
+{
+ BDRVParallelsState *s = bs->opaque;
+ uint32_t i;
+ int64_t off, high_off, size;
+
+ size = bdrv_co_getlength(bs->file->bs);
+ if (size < 0) {
+ res->check_errors++;
+ return size;
+ }
+
+ high_off = 0;
+ for (i = 0; i < s->bat_size; i++) {
+ off = bat2sect(s, i) << BDRV_SECTOR_BITS;
+ if (off + s->cluster_size > size) {
fprintf(stderr, "%s cluster %u is outside image\n",
fix & BDRV_FIX_ERRORS ? "Repairing" : "ERROR", i);
res->corruptions++;
if (fix & BDRV_FIX_ERRORS) {
- prev_off = 0;
- s->bat_bitmap[i] = 0;
+ parallels_set_bat_entry(s, i, 0);
res->corruptions_fixed++;
- flush_bat = true;
- continue;
}
+ continue;
}
-
- res->bfi.allocated_clusters++;
- if (off > high_off) {
+ if (high_off < off) {
high_off = off;
}
+ }
- if (prev_off != 0 && (prev_off + s->cluster_size) != off) {
- res->bfi.fragmented_clusters++;
- }
- prev_off = off;
+ if (high_off == 0) {
+ res->image_end_offset = s->data_end << BDRV_SECTOR_BITS;
+ } else {
+ res->image_end_offset = high_off + s->cluster_size;
+ s->data_end = res->image_end_offset >> BDRV_SECTOR_BITS;
}
- ret = 0;
- if (flush_bat) {
- ret = bdrv_co_pwrite_sync(bs->file, 0, s->header_size, s->header, 0);
- if (ret < 0) {
- res->check_errors++;
- goto out;
- }
+ return 0;
+}
+
+static int coroutine_fn GRAPH_RDLOCK
+parallels_check_leak(BlockDriverState *bs, BdrvCheckResult *res,
+ BdrvCheckMode fix, bool explicit)
+{
+ BDRVParallelsState *s = bs->opaque;
+ int64_t size;
+ int ret;
+
+ size = bdrv_co_getlength(bs->file->bs);
+ if (size < 0) {
+ res->check_errors++;
+ return size;
}
- res->image_end_offset = high_off + s->cluster_size;
if (size > res->image_end_offset) {
int64_t count;
count = DIV_ROUND_UP(size - res->image_end_offset, s->cluster_size);
- fprintf(stderr, "%s space leaked at the end of the image %" PRId64 "\n",
- fix & BDRV_FIX_LEAKS ? "Repairing" : "ERROR",
- size - res->image_end_offset);
- res->leaks += count;
+ if (explicit) {
+ fprintf(stderr,
+ "%s space leaked at the end of the image %" PRId64 "\n",
+ fix & BDRV_FIX_LEAKS ? "Repairing" : "ERROR",
+ size - res->image_end_offset);
+ res->leaks += count;
+ }
if (fix & BDRV_FIX_LEAKS) {
Error *local_err = NULL;
if (ret < 0) {
error_report_err(local_err);
res->check_errors++;
- goto out;
+ return ret;
+ }
+ if (explicit) {
+ res->leaks_fixed += count;
}
- res->leaks_fixed += count;
}
}
-out:
- qemu_co_mutex_unlock(&s->lock);
+ return 0;
+}
+
+static int coroutine_fn GRAPH_RDLOCK
+parallels_check_duplicate(BlockDriverState *bs, BdrvCheckResult *res,
+ BdrvCheckMode fix)
+{
+ BDRVParallelsState *s = bs->opaque;
+ int64_t host_off, host_sector, guest_sector;
+ unsigned long *bitmap;
+ uint32_t i, bitmap_size, bat_entry;
+ int n, ret = 0;
+ uint64_t *buf = NULL;
+ bool fixed = false;
+
+ /*
+ * Create a bitmap of used clusters.
+ * If a bit is set, there is a BAT entry pointing to this cluster.
+ * Loop through the BAT entries, check bits relevant to an entry offset.
+ * If bit is set, this entry is duplicated. Otherwise set the bit.
+ *
+ * We shouldn't worry about newly allocated clusters outside the image
+ * because they are created higher then any existing cluster pointed by
+ * a BAT entry.
+ */
+ bitmap_size = host_cluster_index(s, res->image_end_offset);
+ if (bitmap_size == 0) {
+ return 0;
+ }
+ if (res->image_end_offset % s->cluster_size) {
+ /* A not aligned image end leads to a bitmap shorter by 1 */
+ bitmap_size++;
+ }
+
+ bitmap = bitmap_new(bitmap_size);
+
+ buf = qemu_blockalign(bs, s->cluster_size);
+
+ for (i = 0; i < s->bat_size; i++) {
+ host_off = bat2sect(s, i) << BDRV_SECTOR_BITS;
+ if (host_off == 0) {
+ continue;
+ }
+
+ ret = mark_used(bs, bitmap, bitmap_size, host_off, 1);
+ assert(ret != -E2BIG);
+ if (ret == 0) {
+ continue;
+ }
+
+ /* this cluster duplicates another one */
+ fprintf(stderr, "%s duplicate offset in BAT entry %u\n",
+ fix & BDRV_FIX_ERRORS ? "Repairing" : "ERROR", i);
+
+ res->corruptions++;
+
+ if (!(fix & BDRV_FIX_ERRORS)) {
+ continue;
+ }
+
+ /*
+ * Reset the entry and allocate a new cluster
+ * for the relevant guest offset. In this way we let
+ * the lower layer to place the new cluster properly.
+ * Copy the original cluster to the allocated one.
+ * But before save the old offset value for repairing
+ * if we have an error.
+ */
+ bat_entry = s->bat_bitmap[i];
+ parallels_set_bat_entry(s, i, 0);
+
+ ret = bdrv_co_pread(bs->file, host_off, s->cluster_size, buf, 0);
+ if (ret < 0) {
+ res->check_errors++;
+ goto out_repair_bat;
+ }
+
+ guest_sector = (i * (int64_t)s->cluster_size) >> BDRV_SECTOR_BITS;
+ host_sector = allocate_clusters(bs, guest_sector, s->tracks, &n);
+ if (host_sector < 0) {
+ res->check_errors++;
+ goto out_repair_bat;
+ }
+ host_off = host_sector << BDRV_SECTOR_BITS;
+
+ ret = bdrv_co_pwrite(bs->file, host_off, s->cluster_size, buf, 0);
+ if (ret < 0) {
+ res->check_errors++;
+ goto out_repair_bat;
+ }
+
+ if (host_off + s->cluster_size > res->image_end_offset) {
+ res->image_end_offset = host_off + s->cluster_size;
+ }
+
+ /*
+ * In the future allocate_cluster() will reuse holed offsets
+ * inside the image. Keep the used clusters bitmap content
+ * consistent for the new allocated clusters too.
+ *
+ * Note, clusters allocated outside the current image are not
+ * considered, and the bitmap size doesn't change. This specifically
+ * means that -E2BIG is OK.
+ */
+ ret = mark_used(bs, bitmap, bitmap_size, host_off, 1);
+ if (ret == -EBUSY) {
+ res->check_errors++;
+ goto out_repair_bat;
+ }
+
+ fixed = true;
+ res->corruptions_fixed++;
+
+ }
+
+ if (fixed) {
+ /*
+ * When new clusters are allocated, the file size increases by
+ * 128 Mb. We need to truncate the file to the right size. Let
+ * the leak fix code make its job without res changing.
+ */
+ ret = parallels_check_leak(bs, res, fix, false);
+ }
+
+out_free:
+ g_free(buf);
+ g_free(bitmap);
+ return ret;
+/*
+ * We can get here only from places where index and old_offset have
+ * meaningful values.
+ */
+out_repair_bat:
+ s->bat_bitmap[i] = bat_entry;
+ goto out_free;
+}
+
+static void parallels_collect_statistics(BlockDriverState *bs,
+ BdrvCheckResult *res,
+ BdrvCheckMode fix)
+{
+ BDRVParallelsState *s = bs->opaque;
+ int64_t off, prev_off;
+ uint32_t i;
+
+ res->bfi.total_clusters = s->bat_size;
+ res->bfi.compressed_clusters = 0; /* compression is not supported */
+
+ prev_off = 0;
+ for (i = 0; i < s->bat_size; i++) {
+ off = bat2sect(s, i) << BDRV_SECTOR_BITS;
+ /*
+ * If BDRV_FIX_ERRORS is not set, out-of-image BAT entries were not
+ * fixed. Skip not allocated and out-of-image BAT entries.
+ */
+ if (off == 0 || off + s->cluster_size > res->image_end_offset) {
+ prev_off = 0;
+ continue;
+ }
+
+ if (prev_off != 0 && (prev_off + s->cluster_size) != off) {
+ res->bfi.fragmented_clusters++;
+ }
+ prev_off = off;
+ res->bfi.allocated_clusters++;
+ }
+}
+
+static int coroutine_fn GRAPH_RDLOCK
+parallels_co_check(BlockDriverState *bs, BdrvCheckResult *res,
+ BdrvCheckMode fix)
+{
+ BDRVParallelsState *s = bs->opaque;
+ int ret;
+
+ WITH_QEMU_LOCK_GUARD(&s->lock) {
+ parallels_check_unclean(bs, res, fix);
+
+ ret = parallels_check_data_off(bs, res, fix);
+ if (ret < 0) {
+ return ret;
+ }
+
+ ret = parallels_check_outside_image(bs, res, fix);
+ if (ret < 0) {
+ return ret;
+ }
+
+ ret = parallels_check_leak(bs, res, fix, true);
+ if (ret < 0) {
+ return ret;
+ }
+
+ ret = parallels_check_duplicate(bs, res, fix);
+ if (ret < 0) {
+ return ret;
+ }
+
+ parallels_collect_statistics(bs, res, fix);
+ }
+
+ ret = bdrv_co_flush(bs);
+ if (ret < 0) {
+ res->check_errors++;
+ }
+
return ret;
}
-static int coroutine_fn parallels_co_create(BlockdevCreateOptions* opts,
- Error **errp)
+static int coroutine_fn GRAPH_UNLOCKED
+parallels_co_create(BlockdevCreateOptions* opts, Error **errp)
{
BlockdevCreateOptionsParallels *parallels_opts;
BlockDriverState *bs;
goto out;
}
-static int coroutine_fn GRAPH_RDLOCK
+static int coroutine_fn GRAPH_UNLOCKED
parallels_co_create_opts(BlockDriver *drv, const char *filename,
QemuOpts *opts, Error **errp)
{
return bdrv_pwrite_sync(bs->file, 0, size, s->header, 0);
}
+
+static int parallels_opts_prealloc(BlockDriverState *bs, QDict *options,
+ Error **errp)
+{
+ int err;
+ char *buf;
+ int64_t bytes;
+ BDRVParallelsState *s = bs->opaque;
+ Error *local_err = NULL;
+ QemuOpts *opts = qemu_opts_create(¶llels_runtime_opts, NULL, 0, errp);
+ if (!opts) {
+ return -ENOMEM;
+ }
+
+ err = -EINVAL;
+ if (!qemu_opts_absorb_qdict(opts, options, errp)) {
+ goto done;
+ }
+
+ bytes = qemu_opt_get_size_del(opts, PARALLELS_OPT_PREALLOC_SIZE, 0);
+ s->prealloc_size = bytes >> BDRV_SECTOR_BITS;
+ buf = qemu_opt_get_del(opts, PARALLELS_OPT_PREALLOC_MODE);
+ /* prealloc_mode can be downgraded later during allocate_clusters */
+ s->prealloc_mode = qapi_enum_parse(&prealloc_mode_lookup, buf,
+ PRL_PREALLOC_MODE_FALLOCATE,
+ &local_err);
+ g_free(buf);
+ if (local_err != NULL) {
+ error_propagate(errp, local_err);
+ goto done;
+ }
+ err = 0;
+
+done:
+ qemu_opts_del(opts);
+ return err;
+}
+
static int parallels_open(BlockDriverState *bs, QDict *options, int flags,
Error **errp)
{
BDRVParallelsState *s = bs->opaque;
ParallelsHeader ph;
int ret, size, i;
- QemuOpts *opts = NULL;
- Error *local_err = NULL;
- char *buf;
+ int64_t file_nb_sectors, sector;
+ uint32_t data_start;
+ bool need_check = false;
+
+ ret = parallels_opts_prealloc(bs, options, errp);
+ if (ret < 0) {
+ return ret;
+ }
ret = bdrv_open_file_child(NULL, options, "file", bs, errp);
if (ret < 0) {
return ret;
}
+ file_nb_sectors = bdrv_nb_sectors(bs->file->bs);
+ if (file_nb_sectors < 0) {
+ return -EINVAL;
+ }
+
ret = bdrv_pread(bs->file, 0, sizeof(ph), &ph, 0);
if (ret < 0) {
- goto fail;
+ return ret;
}
bs->total_sectors = le64_to_cpu(ph.nb_sectors);
s->tracks = le32_to_cpu(ph.tracks);
if (s->tracks == 0) {
error_setg(errp, "Invalid image: Zero sectors per track");
- ret = -EINVAL;
- goto fail;
+ return -EINVAL;
}
if (s->tracks > INT32_MAX/513) {
error_setg(errp, "Invalid image: Too big cluster");
- ret = -EFBIG;
- goto fail;
+ return -EFBIG;
}
+ s->prealloc_size = MAX(s->tracks, s->prealloc_size);
s->cluster_size = s->tracks << BDRV_SECTOR_BITS;
s->bat_size = le32_to_cpu(ph.bat_entries);
if (s->bat_size > INT_MAX / sizeof(uint32_t)) {
error_setg(errp, "Catalog too large");
- ret = -EFBIG;
- goto fail;
+ return -EFBIG;
}
size = bat_entry_off(s->bat_size);
s->header_size = ROUND_UP(size, bdrv_opt_mem_align(bs->file->bs));
s->header = qemu_try_blockalign(bs->file->bs, s->header_size);
if (s->header == NULL) {
- ret = -ENOMEM;
- goto fail;
- }
- s->data_end = le32_to_cpu(ph.data_off);
- if (s->data_end == 0) {
- s->data_end = ROUND_UP(bat_entry_off(s->bat_size), BDRV_SECTOR_SIZE);
- }
- if (s->data_end < s->header_size) {
- /* there is not enough unused space to fit to block align between BAT
- and actual data. We can't avoid read-modify-write... */
- s->header_size = size;
+ return -ENOMEM;
}
ret = bdrv_pread(bs->file, 0, s->header_size, s->header, 0);
}
s->bat_bitmap = (uint32_t *)(s->header + 1);
- for (i = 0; i < s->bat_size; i++) {
- int64_t off = bat2sect(s, i);
- if (off >= s->data_end) {
- s->data_end = off + s->tracks;
- }
- }
-
if (le32_to_cpu(ph.inuse) == HEADER_INUSE_MAGIC) {
- /* Image was not closed correctly. The check is mandatory */
- s->header_unclean = true;
- if ((flags & BDRV_O_RDWR) && !(flags & BDRV_O_CHECK)) {
- error_setg(errp, "parallels: Image was not closed correctly; "
- "cannot be opened read/write");
- ret = -EACCES;
- goto fail;
- }
- }
-
- opts = qemu_opts_create(¶llels_runtime_opts, NULL, 0, errp);
- if (!opts) {
- goto fail_options;
+ need_check = s->header_unclean = true;
}
- if (!qemu_opts_absorb_qdict(opts, options, errp)) {
- goto fail_options;
+ {
+ bool ok = parallels_test_data_off(s, file_nb_sectors, &data_start);
+ need_check = need_check || !ok;
}
- s->prealloc_size =
- qemu_opt_get_size_del(opts, PARALLELS_OPT_PREALLOC_SIZE, 0);
- s->prealloc_size = MAX(s->tracks, s->prealloc_size >> BDRV_SECTOR_BITS);
- buf = qemu_opt_get_del(opts, PARALLELS_OPT_PREALLOC_MODE);
- /* prealloc_mode can be downgraded later during allocate_clusters */
- s->prealloc_mode = qapi_enum_parse(&prealloc_mode_lookup, buf,
- PRL_PREALLOC_MODE_FALLOCATE,
- &local_err);
- g_free(buf);
- if (local_err != NULL) {
- error_propagate(errp, local_err);
- goto fail_options;
+ s->data_start = data_start;
+ s->data_end = s->data_start;
+ if (s->data_end < (s->header_size >> BDRV_SECTOR_BITS)) {
+ /*
+ * There is not enough unused space to fit to block align between BAT
+ * and actual data. We can't avoid read-modify-write...
+ */
+ s->header_size = size;
}
if (ph.ext_off) {
bitmap_new(DIV_ROUND_UP(s->header_size, s->bat_dirty_block));
/* Disable migration until bdrv_activate method is added */
+ bdrv_graph_rdlock_main_loop();
error_setg(&s->migration_blocker, "The Parallels format used by node '%s' "
"does not support live migration",
bdrv_get_device_or_node_name(bs));
- ret = migrate_add_blocker(s->migration_blocker, errp);
+ bdrv_graph_rdunlock_main_loop();
+
+ ret = migrate_add_blocker_normal(&s->migration_blocker, errp);
if (ret < 0) {
- error_free(s->migration_blocker);
goto fail;
}
qemu_co_mutex_init(&s->lock);
+
+ for (i = 0; i < s->bat_size; i++) {
+ sector = bat2sect(s, i);
+ if (sector + s->tracks > s->data_end) {
+ s->data_end = sector + s->tracks;
+ }
+ }
+ need_check = need_check || s->data_end > file_nb_sectors;
+
+ if (!need_check) {
+ ret = parallels_fill_used_bitmap(bs);
+ if (ret == -ENOMEM) {
+ goto fail;
+ }
+ need_check = need_check || ret < 0; /* These are correctable errors */
+ }
+
+ /*
+ * We don't repair the image here if it's opened for checks. Also we don't
+ * want to change inactive images and can't change readonly images.
+ */
+ if ((flags & (BDRV_O_CHECK | BDRV_O_INACTIVE)) || !(flags & BDRV_O_RDWR)) {
+ return 0;
+ }
+
+ /* Repair the image if corruption was detected. */
+ if (need_check) {
+ BdrvCheckResult res;
+ ret = bdrv_check(bs, &res, BDRV_FIX_ERRORS | BDRV_FIX_LEAKS);
+ if (ret < 0) {
+ error_setg_errno(errp, -ret, "Could not repair corrupted image");
+ migrate_del_blocker(&s->migration_blocker);
+ goto fail;
+ }
+ }
return 0;
fail_format:
error_setg(errp, "Image not in Parallels format");
-fail_options:
- ret = -EINVAL;
+ return -EINVAL;
+
fail:
+ /*
+ * "s" object was allocated by g_malloc0 so we can safely
+ * try to free its fields even they were not allocated.
+ */
+ parallels_free_used_bitmap(bs);
+
+ g_free(s->bat_dirty_bmap);
qemu_vfree(s->header);
return ret;
}
PREALLOC_MODE_OFF, 0, NULL);
}
+ parallels_free_used_bitmap(bs);
+
g_free(s->bat_dirty_bmap);
qemu_vfree(s->header);
- migrate_del_blocker(s->migration_blocker);
- error_free(s->migration_blocker);
+ migrate_del_blocker(&s->migration_blocker);
+}
+
+static bool parallels_is_support_dirty_bitmaps(BlockDriverState *bs)
+{
+ return 1;
}
static BlockDriver bdrv_parallels = {
- .format_name = "parallels",
- .instance_size = sizeof(BDRVParallelsState),
- .bdrv_probe = parallels_probe,
- .bdrv_open = parallels_open,
- .bdrv_close = parallels_close,
- .bdrv_child_perm = bdrv_default_perms,
- .bdrv_co_block_status = parallels_co_block_status,
- .bdrv_has_zero_init = bdrv_has_zero_init_1,
- .bdrv_co_flush_to_os = parallels_co_flush_to_os,
- .bdrv_co_readv = parallels_co_readv,
- .bdrv_co_writev = parallels_co_writev,
- .is_format = true,
- .supports_backing = true,
- .bdrv_co_create = parallels_co_create,
- .bdrv_co_create_opts = parallels_co_create_opts,
- .bdrv_co_check = parallels_co_check,
- .create_opts = ¶llels_create_opts,
+ .format_name = "parallels",
+ .instance_size = sizeof(BDRVParallelsState),
+ .create_opts = ¶llels_create_opts,
+ .is_format = true,
+ .supports_backing = true,
+
+ .bdrv_has_zero_init = bdrv_has_zero_init_1,
+ .bdrv_supports_persistent_dirty_bitmap = parallels_is_support_dirty_bitmaps,
+
+ .bdrv_probe = parallels_probe,
+ .bdrv_open = parallels_open,
+ .bdrv_close = parallels_close,
+ .bdrv_child_perm = bdrv_default_perms,
+ .bdrv_co_block_status = parallels_co_block_status,
+ .bdrv_co_flush_to_os = parallels_co_flush_to_os,
+ .bdrv_co_readv = parallels_co_readv,
+ .bdrv_co_writev = parallels_co_writev,
+ .bdrv_co_create = parallels_co_create,
+ .bdrv_co_create_opts = parallels_co_create_opts,
+ .bdrv_co_check = parallels_co_check,
+ .bdrv_co_pdiscard = parallels_co_pdiscard,
+ .bdrv_co_pwrite_zeroes = parallels_co_pwrite_zeroes,
};
static void bdrv_parallels_init(void)
projects / mirror_qemu.git / blobdiff