*
*/
+#include "qemu-timer.h"
#include "trace.h"
#include "qed.h"
+#include "qerror.h"
static void qed_aio_cancel(BlockDriverAIOCB *blockacb)
{
return 0;
}
+typedef struct {
+ GenericCB gencb;
+ BDRVQEDState *s;
+ struct iovec iov;
+ QEMUIOVector qiov;
+ int nsectors;
+ uint8_t *buf;
+} QEDWriteHeaderCB;
+
+static void qed_write_header_cb(void *opaque, int ret)
+{
+ QEDWriteHeaderCB *write_header_cb = opaque;
+
+ qemu_vfree(write_header_cb->buf);
+ gencb_complete(write_header_cb, ret);
+}
+
+static void qed_write_header_read_cb(void *opaque, int ret)
+{
+ QEDWriteHeaderCB *write_header_cb = opaque;
+ BDRVQEDState *s = write_header_cb->s;
+ BlockDriverAIOCB *acb;
+
+ if (ret) {
+ qed_write_header_cb(write_header_cb, ret);
+ return;
+ }
+
+ /* Update header */
+ qed_header_cpu_to_le(&s->header, (QEDHeader *)write_header_cb->buf);
+
+ acb = bdrv_aio_writev(s->bs->file, 0, &write_header_cb->qiov,
+ write_header_cb->nsectors, qed_write_header_cb,
+ write_header_cb);
+ if (!acb) {
+ qed_write_header_cb(write_header_cb, -EIO);
+ }
+}
+
+/**
+ * Update header in-place (does not rewrite backing filename or other strings)
+ *
+ * This function only updates known header fields in-place and does not affect
+ * extra data after the QED header.
+ */
+static void qed_write_header(BDRVQEDState *s, BlockDriverCompletionFunc cb,
+ void *opaque)
+{
+ /* We must write full sectors for O_DIRECT but cannot necessarily generate
+ * the data following the header if an unrecognized compat feature is
+ * active. Therefore, first read the sectors containing the header, update
+ * them, and write back.
+ */
+
+ BlockDriverAIOCB *acb;
+ int nsectors = (sizeof(QEDHeader) + BDRV_SECTOR_SIZE - 1) /
+ BDRV_SECTOR_SIZE;
+ size_t len = nsectors * BDRV_SECTOR_SIZE;
+ QEDWriteHeaderCB *write_header_cb = gencb_alloc(sizeof(*write_header_cb),
+ cb, opaque);
+
+ write_header_cb->s = s;
+ write_header_cb->nsectors = nsectors;
+ write_header_cb->buf = qemu_blockalign(s->bs, len);
+ write_header_cb->iov.iov_base = write_header_cb->buf;
+ write_header_cb->iov.iov_len = len;
+ qemu_iovec_init_external(&write_header_cb->qiov, &write_header_cb->iov, 1);
+
+ acb = bdrv_aio_readv(s->bs->file, 0, &write_header_cb->qiov, nsectors,
+ qed_write_header_read_cb, write_header_cb);
+ if (!acb) {
+ qed_write_header_cb(write_header_cb, -EIO);
+ }
+}
+
static uint64_t qed_max_image_size(uint32_t cluster_size, uint32_t table_size)
{
uint64_t table_entries;
static void qed_aio_next_io(void *opaque, int ret);
+static void qed_plug_allocating_write_reqs(BDRVQEDState *s)
+{
+ assert(!s->allocating_write_reqs_plugged);
+
+ s->allocating_write_reqs_plugged = true;
+}
+
+static void qed_unplug_allocating_write_reqs(BDRVQEDState *s)
+{
+ QEDAIOCB *acb;
+
+ assert(s->allocating_write_reqs_plugged);
+
+ s->allocating_write_reqs_plugged = false;
+
+ acb = QSIMPLEQ_FIRST(&s->allocating_write_reqs);
+ if (acb) {
+ qed_aio_next_io(acb, 0);
+ }
+}
+
+static void qed_finish_clear_need_check(void *opaque, int ret)
+{
+ /* Do nothing */
+}
+
+static void qed_flush_after_clear_need_check(void *opaque, int ret)
+{
+ BDRVQEDState *s = opaque;
+
+ bdrv_aio_flush(s->bs, qed_finish_clear_need_check, s);
+
+ /* No need to wait until flush completes */
+ qed_unplug_allocating_write_reqs(s);
+}
+
+static void qed_clear_need_check(void *opaque, int ret)
+{
+ BDRVQEDState *s = opaque;
+
+ if (ret) {
+ qed_unplug_allocating_write_reqs(s);
+ return;
+ }
+
+ s->header.features &= ~QED_F_NEED_CHECK;
+ qed_write_header(s, qed_flush_after_clear_need_check, s);
+}
+
+static void qed_need_check_timer_cb(void *opaque)
+{
+ BDRVQEDState *s = opaque;
+
+ /* The timer should only fire when allocating writes have drained */
+ assert(!QSIMPLEQ_FIRST(&s->allocating_write_reqs));
+
+ trace_qed_need_check_timer_cb(s);
+
+ qed_plug_allocating_write_reqs(s);
+
+ /* Ensure writes are on disk before clearing flag */
+ bdrv_aio_flush(s->bs, qed_clear_need_check, s);
+}
+
+static void qed_start_need_check_timer(BDRVQEDState *s)
+{
+ trace_qed_start_need_check_timer(s);
+
+ /* Use vm_clock so we don't alter the image file while suspended for
+ * migration.
+ */
+ qemu_mod_timer(s->need_check_timer, qemu_get_clock_ns(vm_clock) +
+ get_ticks_per_sec() * QED_NEED_CHECK_TIMEOUT);
+}
+
+/* It's okay to call this multiple times or when no timer is started */
+static void qed_cancel_need_check_timer(BDRVQEDState *s)
+{
+ trace_qed_cancel_need_check_timer(s);
+ qemu_del_timer(s->need_check_timer);
+}
+
static int bdrv_qed_open(BlockDriverState *bs, int flags)
{
BDRVQEDState *s = bs->opaque;
return -EINVAL;
}
if (s->header.features & ~QED_FEATURE_MASK) {
- return -ENOTSUP; /* image uses unsupported feature bits */
+ /* image uses unsupported feature bits */
+ char buf[64];
+ snprintf(buf, sizeof(buf), "%" PRIx64,
+ s->header.features & ~QED_FEATURE_MASK);
+ qerror_report(QERR_UNKNOWN_BLOCK_FORMAT_FEATURE,
+ bs->device_name, "QED", buf);
+ return -ENOTSUP;
}
if (!qed_is_cluster_size_valid(s->header.cluster_size)) {
return -EINVAL;
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 (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)) {
+ BdrvCheckResult result = {0};
+
+ ret = qed_check(s, &result, true);
+ if (ret) {
+ goto out;
+ }
+ if (!result.corruptions && !result.check_errors) {
+ /* Ensure fixes reach storage before clearing check bit */
+ bdrv_flush(s->bs);
+
+ s->header.features &= ~QED_F_NEED_CHECK;
+ qed_write_header_sync(s);
+ }
+ }
+ }
+
+ s->need_check_timer = qemu_new_timer_ns(vm_clock,
+ qed_need_check_timer_cb, s);
+
+out:
if (ret) {
qed_free_l2_cache(&s->l2_cache);
qemu_vfree(s->l1_table);
{
BDRVQEDState *s = bs->opaque;
+ qed_cancel_need_check_timer(s);
+ qemu_free_timer(s->need_check_timer);
+
+ /* Ensure writes reach stable storage */
+ bdrv_flush(bs->file);
+
+ /* Clean shutdown, no check required on next open */
+ if (s->header.features & QED_F_NEED_CHECK) {
+ s->header.features &= ~QED_F_NEED_CHECK;
+ qed_write_header_sync(s);
+ }
+
qed_free_l2_cache(&s->l2_cache);
qemu_vfree(s->l1_table);
}
return ret;
}
+ /* File must start empty and grow, check truncate is supported */
+ ret = bdrv_truncate(bs, 0);
+ if (ret < 0) {
+ goto out;
+ }
+
if (backing_file) {
header.features |= QED_F_BACKING_FILE;
header.backing_filename_offset = sizeof(le_header);
{
QEDIsAllocatedCB *cb = opaque;
*cb->pnum = len / BDRV_SECTOR_SIZE;
- cb->is_allocated = ret == QED_CLUSTER_FOUND;
+ cb->is_allocated = (ret == QED_CLUSTER_FOUND || ret == QED_CLUSTER_ZERO);
}
static int bdrv_qed_is_allocated(BlockDriverState *bs, int64_t sector_num,
* @table: L2 table
* @index: First cluster index
* @n: Number of contiguous clusters
- * @cluster: First cluster byte offset in image file
+ * @cluster: First cluster offset
+ *
+ * The cluster offset may be an allocated byte offset in the image file, the
+ * zero cluster marker, or the unallocated cluster marker.
*/
static void qed_update_l2_table(BDRVQEDState *s, QEDTable *table, int index,
unsigned int n, uint64_t cluster)
int i;
for (i = index; i < index + n; i++) {
table->offsets[i] = cluster;
- cluster += s->header.cluster_size;
+ if (!qed_offset_is_unalloc_cluster(cluster) &&
+ !qed_offset_is_zero_cluster(cluster)) {
+ cluster += s->header.cluster_size;
+ }
}
}
acb = QSIMPLEQ_FIRST(&s->allocating_write_reqs);
if (acb) {
qed_aio_next_io(acb, 0);
+ } else if (s->header.features & QED_F_NEED_CHECK) {
+ qed_start_need_check_timer(s);
}
}
}
qed_aio_write_postfill, acb);
}
+/**
+ * Check if the QED_F_NEED_CHECK bit should be set during allocating write
+ */
+static bool qed_should_set_need_check(BDRVQEDState *s)
+{
+ /* The flush before L2 update path ensures consistency */
+ if (s->bs->backing_hd) {
+ return false;
+ }
+
+ return !(s->header.features & QED_F_NEED_CHECK);
+}
+
/**
* Write new data cluster
*
{
BDRVQEDState *s = acb_to_s(acb);
+ /* Cancel timer when the first allocating request comes in */
+ if (QSIMPLEQ_EMPTY(&s->allocating_write_reqs)) {
+ qed_cancel_need_check_timer(s);
+ }
+
/* Freeze this request if another allocating write is in progress */
if (acb != QSIMPLEQ_FIRST(&s->allocating_write_reqs)) {
QSIMPLEQ_INSERT_TAIL(&s->allocating_write_reqs, acb, next);
}
- if (acb != QSIMPLEQ_FIRST(&s->allocating_write_reqs)) {
+ if (acb != QSIMPLEQ_FIRST(&s->allocating_write_reqs) ||
+ s->allocating_write_reqs_plugged) {
return; /* wait for existing request to finish */
}
acb->cur_cluster = qed_alloc_clusters(s, acb->cur_nclusters);
qemu_iovec_copy(&acb->cur_qiov, acb->qiov, acb->qiov_offset, len);
- /* Write new cluster */
- qed_aio_write_prefill(acb, 0);
+ if (qed_should_set_need_check(s)) {
+ s->header.features |= QED_F_NEED_CHECK;
+ qed_write_header(s, qed_aio_write_prefill, acb);
+ } else {
+ qed_aio_write_prefill(acb, 0);
+ }
}
/**
case QED_CLUSTER_L2:
case QED_CLUSTER_L1:
+ case QED_CLUSTER_ZERO:
qed_aio_write_alloc(acb, len);
break;
qemu_iovec_copy(&acb->cur_qiov, acb->qiov, acb->qiov_offset, len);
- /* Handle backing file and unallocated sparse hole reads */
- if (ret != QED_CLUSTER_FOUND) {
+ /* Handle zero cluster and backing file reads */
+ if (ret == QED_CLUSTER_ZERO) {
+ qemu_iovec_memset(&acb->cur_qiov, 0, acb->cur_qiov.size);
+ qed_aio_next_io(acb, 0);
+ return;
+ } else if (ret != QED_CLUSTER_FOUND) {
qed_read_backing_file(s, acb->cur_pos, &acb->cur_qiov,
qed_aio_next_io, acb);
return;
static int bdrv_qed_truncate(BlockDriverState *bs, int64_t offset)
{
- return -ENOTSUP;
+ BDRVQEDState *s = bs->opaque;
+ uint64_t old_image_size;
+ int ret;
+
+ if (!qed_is_image_size_valid(offset, s->header.cluster_size,
+ s->header.table_size)) {
+ return -EINVAL;
+ }
+
+ /* Shrinking is currently not supported */
+ if ((uint64_t)offset < s->header.image_size) {
+ return -ENOTSUP;
+ }
+
+ old_image_size = s->header.image_size;
+ s->header.image_size = offset;
+ ret = qed_write_header_sync(s);
+ if (ret < 0) {
+ s->header.image_size = old_image_size;
+ }
+ return ret;
}
static int64_t bdrv_qed_getlength(BlockDriverState *bs)
static int bdrv_qed_check(BlockDriverState *bs, BdrvCheckResult *result)
{
- return -ENOTSUP;
+ BDRVQEDState *s = bs->opaque;
+
+ return qed_check(s, result, false);
}
static QEMUOptionParameter qed_create_options[] = {
}, {
.name = BLOCK_OPT_CLUSTER_SIZE,
.type = OPT_SIZE,
- .help = "Cluster size (in bytes)"
+ .help = "Cluster size (in bytes)",
+ .value = { .n = QED_DEFAULT_CLUSTER_SIZE },
}, {
.name = BLOCK_OPT_TABLE_SIZE,
.type = OPT_SIZE,
projects / qemu.git / blobdiff