/**
* Find the offset of a data cluster
*
* @s: QED state
* @request: L2 cache entry
* @pos: Byte position in device
* @len: Number of bytes
* @cb: Completion function
* @opaque: User data for completion function
*
* This function translates a position in the block device to an offset in the
* image file. It invokes the cb completion callback to report back the
* translated offset or unallocated range in the image file.
*
* If the L2 table exists, request->l2_table points to the L2 table cache entry
* and the caller must free the reference when they are finished. The cache
* entry is exposed in this way to avoid callers having to read the L2 table
* again later during request processing. If request->l2_table is non-NULL it
* will be unreferenced before taking on the new cache entry.
*/
void qed_find_cluster(BDRVQEDState *s, QEDRequest *request, uint64_t pos,
size_t len, QEDFindClusterFunc *cb, void *opaque)
{
QEDFindClusterCB *find_cluster_cb;
uint64_t l2_offset;
/* Limit length to L2 boundary. Requests are broken up at the L2 boundary
* so that a request acts on one L2 table at a time.
*/
len = MIN(len, (((pos >> s->l1_shift) + 1) << s->l1_shift) - pos);
l2_offset = s->l1_table->offsets[qed_l1_index(s, pos)];
if (qed_offset_is_unalloc_cluster(l2_offset)) {
cb(opaque, QED_CLUSTER_L1, 0, len);
return;
}
if (!qed_check_table_offset(s, l2_offset)) {
cb(opaque, -EINVAL, 0, 0);
return;
}
find_cluster_cb = g_malloc(sizeof(*find_cluster_cb));
find_cluster_cb->s = s;
find_cluster_cb->pos = pos;
find_cluster_cb->len = len;
find_cluster_cb->cb = cb;
find_cluster_cb->opaque = opaque;
find_cluster_cb->request = request;
qed_read_l2_table(s, request, l2_offset,
qed_find_cluster_cb, find_cluster_cb);
}
static int bdrv_qed_open(BlockDriverState *bs, QDict *options, int flags,
Error **errp)
{
BDRVQEDState *s = bs->opaque;
QEDHeader le_header;
int64_t file_size;
int ret;
s->bs = bs;
QSIMPLEQ_INIT(&s->allocating_write_reqs);
ret = bdrv_pread(bs->file, 0, &le_header, sizeof(le_header));
if (ret < 0) {
return ret;
}
qed_header_le_to_cpu(&le_header, &s->header);
if (s->header.magic != QED_MAGIC) {
error_setg(errp, "Image not in QED format");
return -EINVAL;
}
if (s->header.features & ~QED_FEATURE_MASK) {
/* image uses unsupported feature bits */
char buf[64];
snprintf(buf, sizeof(buf), "%" PRIx64,
s->header.features & ~QED_FEATURE_MASK);
error_set(errp, QERR_UNKNOWN_BLOCK_FORMAT_FEATURE,
bs->device_name, "QED", buf);
return -ENOTSUP;
}
if (!qed_is_cluster_size_valid(s->header.cluster_size)) {
return -EINVAL;
}
/* Round down file size to the last cluster */
file_size = bdrv_getlength(bs->file);
if (file_size < 0) {
return file_size;
}
s->file_size = qed_start_of_cluster(s, file_size);
if (!qed_is_table_size_valid(s->header.table_size)) {
return -EINVAL;
}
if (!qed_is_image_size_valid(s->header.image_size,
s->header.cluster_size,
s->header.table_size)) {
return -EINVAL;
}
if (!qed_check_table_offset(s, s->header.l1_table_offset)) {
return -EINVAL;
}
s->table_nelems = (s->header.cluster_size * s->header.table_size) /
sizeof(uint64_t);
s->l2_shift = ffs(s->header.cluster_size) - 1;
s->l2_mask = s->table_nelems - 1;
s->l1_shift = s->l2_shift + ffs(s->table_nelems) - 1;
if ((s->header.features & QED_F_BACKING_FILE)) {
if ((uint64_t)s->header.backing_filename_offset +
s->header.backing_filename_size >
s->header.cluster_size * s->header.header_size) {
return -EINVAL;
}
ret = qed_read_string(bs->file, s->header.backing_filename_offset,
s->header.backing_filename_size, bs->backing_file,
sizeof(bs->backing_file));
if (ret < 0) {
return ret;
}
if (s->header.features & QED_F_BACKING_FORMAT_NO_PROBE) {
pstrcpy(bs->backing_format, sizeof(bs->backing_format), "raw");
}
}
/* Reset unknown autoclear feature bits. This is a backwards
* compatibility mechanism that allows images to be opened by older
* programs, which "knock out" unknown feature bits. When an image is
* opened by a newer program again it can detect that the autoclear
* feature is no longer valid.
*/
if ((s->header.autoclear_features & ~QED_AUTOCLEAR_FEATURE_MASK) != 0 &&
!bdrv_is_read_only(bs->file) && !(flags & BDRV_O_INCOMING)) {
s->header.autoclear_features &= QED_AUTOCLEAR_FEATURE_MASK;
ret = qed_write_header_sync(s);
if (ret) {
return ret;
}
/* From here on only known autoclear feature bits are valid */
bdrv_flush(bs->file);
}
s->l1_table = qed_alloc_table(s);
qed_init_l2_cache(&s->l2_cache);
ret = qed_read_l1_table_sync(s);
if (ret) {
goto out;
}
/* If image was not closed cleanly, check consistency */
if (!(flags & BDRV_O_CHECK) && (s->header.features & QED_F_NEED_CHECK)) {
/* Read-only images cannot be fixed. There is no risk of corruption
* since write operations are not possible. Therefore, allow
* potentially inconsistent images to be opened read-only. This can
* aid data recovery from an otherwise inconsistent image.
*/
if (!bdrv_is_read_only(bs->file) &&
!(flags & BDRV_O_INCOMING)) {
BdrvCheckResult result = {0};
ret = qed_check(s, &result, true);
if (ret) {
goto out;
}
}
}
bdrv_qed_attach_aio_context(bs, bdrv_get_aio_context(bs));
out:
if (ret) {
qed_free_l2_cache(&s->l2_cache);
qemu_vfree(s->l1_table);
}
return ret;
}
/**
* Descend tables and check each cluster is referenced once only
*/
static int qed_check_l1_table(QEDCheck *check, QEDTable *table)
{
BDRVQEDState *s = check->s;
unsigned int i, num_invalid_l1 = 0;
int ret, last_error = 0;
/* Mark L1 table clusters used */
qed_set_used_clusters(check, s->header.l1_table_offset,
s->header.table_size);
for (i = 0; i < s->table_nelems; i++) {
unsigned int num_invalid_l2;
uint64_t offset = table->offsets[i];
if (qed_offset_is_unalloc_cluster(offset)) {
continue;
}
/* Detect invalid L2 offset */
if (!qed_check_table_offset(s, offset)) {
/* Clear invalid offset */
if (check->fix) {
table->offsets[i] = 0;
} else {
check->result->corruptions++;
}
num_invalid_l1++;
continue;
}
if (!qed_set_used_clusters(check, offset, s->header.table_size)) {
continue; /* skip an invalid table */
}
ret = qed_read_l2_table_sync(s, &check->request, offset);
if (ret) {
check->result->check_errors++;
last_error = ret;
continue;
}
num_invalid_l2 = qed_check_l2_table(check,
check->request.l2_table->table);
/* Write out fixed L2 table */
if (num_invalid_l2 > 0 && check->fix) {
ret = qed_write_l2_table_sync(s, &check->request, 0,
s->table_nelems, false);
if (ret) {
check->result->check_errors++;
last_error = ret;
continue;
}
}
}
/* Drop reference to final table */
qed_unref_l2_cache_entry(check->request.l2_table);
check->request.l2_table = NULL;
/* Write out fixed L1 table */
if (num_invalid_l1 > 0 && check->fix) {
ret = qed_write_l1_table_sync(s, 0, s->table_nelems);
if (ret) {
check->result->check_errors++;
last_error = ret;
}
}
return last_error;
}
