*
*/
+#include "qemu-timer.h"
+#include "trace.h"
#include "qed.h"
+#include "qerror.h"
+
+static void qed_aio_cancel(BlockDriverAIOCB *blockacb)
+{
+ QEDAIOCB *acb = (QEDAIOCB *)blockacb;
+ bool finished = false;
+
+ /* Wait for the request to finish */
+ acb->finished = &finished;
+ while (!finished) {
+ qemu_aio_wait();
+ }
+}
+
+static AIOPool qed_aio_pool = {
+ .aiocb_size = sizeof(QEDAIOCB),
+ .cancel = qed_aio_cancel,
+};
static int bdrv_qed_probe(const uint8_t *buf, int buf_size,
const char *filename)
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;
return 0;
}
+/**
+ * Allocate new clusters
+ *
+ * @s: QED state
+ * @n: Number of contiguous clusters to allocate
+ * @ret: Offset of first allocated cluster
+ *
+ * This function only produces the offset where the new clusters should be
+ * written. It updates BDRVQEDState but does not make any changes to the image
+ * file.
+ */
+static uint64_t qed_alloc_clusters(BDRVQEDState *s, unsigned int n)
+{
+ uint64_t offset = s->file_size;
+ s->file_size += n * s->header.cluster_size;
+ return offset;
+}
+
+QEDTable *qed_alloc_table(BDRVQEDState *s)
+{
+ /* Honor O_DIRECT memory alignment requirements */
+ return qemu_blockalign(s->bs,
+ s->header.cluster_size * s->header.table_size);
+}
+
+/**
+ * Allocate a new zeroed L2 table
+ */
+static CachedL2Table *qed_new_l2_table(BDRVQEDState *s)
+{
+ CachedL2Table *l2_table = qed_alloc_l2_cache_entry(&s->l2_cache);
+
+ l2_table->table = qed_alloc_table(s);
+ l2_table->offset = qed_alloc_clusters(s, s->header.table_size);
+
+ memset(l2_table->table->offsets, 0,
+ s->header.cluster_size * s->header.table_size);
+ return l2_table;
+}
+
+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;
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 -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;
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 (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);
+ }
return ret;
}
static void bdrv_qed_close(BlockDriverState *bs)
{
+ 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);
}
static int bdrv_qed_flush(BlockDriverState *bs)
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);
backing_file, backing_fmt);
}
+typedef struct {
+ int is_allocated;
+ int *pnum;
+} QEDIsAllocatedCB;
+
+static void qed_is_allocated_cb(void *opaque, int ret, uint64_t offset, size_t len)
+{
+ QEDIsAllocatedCB *cb = opaque;
+ *cb->pnum = len / BDRV_SECTOR_SIZE;
+ cb->is_allocated = (ret == QED_CLUSTER_FOUND || ret == QED_CLUSTER_ZERO);
+}
+
static int bdrv_qed_is_allocated(BlockDriverState *bs, int64_t sector_num,
int nb_sectors, int *pnum)
{
- return -ENOTSUP;
+ BDRVQEDState *s = bs->opaque;
+ uint64_t pos = (uint64_t)sector_num * BDRV_SECTOR_SIZE;
+ size_t len = (size_t)nb_sectors * BDRV_SECTOR_SIZE;
+ QEDIsAllocatedCB cb = {
+ .is_allocated = -1,
+ .pnum = pnum,
+ };
+ QEDRequest request = { .l2_table = NULL };
+
+ async_context_push();
+
+ qed_find_cluster(s, &request, pos, len, qed_is_allocated_cb, &cb);
+
+ while (cb.is_allocated == -1) {
+ qemu_aio_wait();
+ }
+
+ async_context_pop();
+
+ qed_unref_l2_cache_entry(request.l2_table);
+
+ return cb.is_allocated;
}
static int bdrv_qed_make_empty(BlockDriverState *bs)
return -ENOTSUP;
}
+static BDRVQEDState *acb_to_s(QEDAIOCB *acb)
+{
+ return acb->common.bs->opaque;
+}
+
+/**
+ * Read from the backing file or zero-fill if no backing file
+ *
+ * @s: QED state
+ * @pos: Byte position in device
+ * @qiov: Destination I/O vector
+ * @cb: Completion function
+ * @opaque: User data for completion function
+ *
+ * This function reads qiov->size bytes starting at pos from the backing file.
+ * If there is no backing file then zeroes are read.
+ */
+static void qed_read_backing_file(BDRVQEDState *s, uint64_t pos,
+ QEMUIOVector *qiov,
+ BlockDriverCompletionFunc *cb, void *opaque)
+{
+ BlockDriverAIOCB *aiocb;
+ uint64_t backing_length = 0;
+ size_t size;
+
+ /* If there is a backing file, get its length. Treat the absence of a
+ * backing file like a zero length backing file.
+ */
+ if (s->bs->backing_hd) {
+ int64_t l = bdrv_getlength(s->bs->backing_hd);
+ if (l < 0) {
+ cb(opaque, l);
+ return;
+ }
+ backing_length = l;
+ }
+
+ /* Zero all sectors if reading beyond the end of the backing file */
+ if (pos >= backing_length ||
+ pos + qiov->size > backing_length) {
+ qemu_iovec_memset(qiov, 0, qiov->size);
+ }
+
+ /* Complete now if there are no backing file sectors to read */
+ if (pos >= backing_length) {
+ cb(opaque, 0);
+ return;
+ }
+
+ /* If the read straddles the end of the backing file, shorten it */
+ size = MIN((uint64_t)backing_length - pos, qiov->size);
+
+ BLKDBG_EVENT(s->bs->file, BLKDBG_READ_BACKING);
+ aiocb = bdrv_aio_readv(s->bs->backing_hd, pos / BDRV_SECTOR_SIZE,
+ qiov, size / BDRV_SECTOR_SIZE, cb, opaque);
+ if (!aiocb) {
+ cb(opaque, -EIO);
+ }
+}
+
+typedef struct {
+ GenericCB gencb;
+ BDRVQEDState *s;
+ QEMUIOVector qiov;
+ struct iovec iov;
+ uint64_t offset;
+} CopyFromBackingFileCB;
+
+static void qed_copy_from_backing_file_cb(void *opaque, int ret)
+{
+ CopyFromBackingFileCB *copy_cb = opaque;
+ qemu_vfree(copy_cb->iov.iov_base);
+ gencb_complete(©_cb->gencb, ret);
+}
+
+static void qed_copy_from_backing_file_write(void *opaque, int ret)
+{
+ CopyFromBackingFileCB *copy_cb = opaque;
+ BDRVQEDState *s = copy_cb->s;
+ BlockDriverAIOCB *aiocb;
+
+ if (ret) {
+ qed_copy_from_backing_file_cb(copy_cb, ret);
+ return;
+ }
+
+ BLKDBG_EVENT(s->bs->file, BLKDBG_COW_WRITE);
+ aiocb = bdrv_aio_writev(s->bs->file, copy_cb->offset / BDRV_SECTOR_SIZE,
+ ©_cb->qiov,
+ copy_cb->qiov.size / BDRV_SECTOR_SIZE,
+ qed_copy_from_backing_file_cb, copy_cb);
+ if (!aiocb) {
+ qed_copy_from_backing_file_cb(copy_cb, -EIO);
+ }
+}
+
+/**
+ * Copy data from backing file into the image
+ *
+ * @s: QED state
+ * @pos: Byte position in device
+ * @len: Number of bytes
+ * @offset: Byte offset in image file
+ * @cb: Completion function
+ * @opaque: User data for completion function
+ */
+static void qed_copy_from_backing_file(BDRVQEDState *s, uint64_t pos,
+ uint64_t len, uint64_t offset,
+ BlockDriverCompletionFunc *cb,
+ void *opaque)
+{
+ CopyFromBackingFileCB *copy_cb;
+
+ /* Skip copy entirely if there is no work to do */
+ if (len == 0) {
+ cb(opaque, 0);
+ return;
+ }
+
+ copy_cb = gencb_alloc(sizeof(*copy_cb), cb, opaque);
+ copy_cb->s = s;
+ copy_cb->offset = offset;
+ copy_cb->iov.iov_base = qemu_blockalign(s->bs, len);
+ copy_cb->iov.iov_len = len;
+ qemu_iovec_init_external(©_cb->qiov, ©_cb->iov, 1);
+
+ qed_read_backing_file(s, pos, ©_cb->qiov,
+ qed_copy_from_backing_file_write, copy_cb);
+}
+
+/**
+ * Link one or more contiguous clusters into a table
+ *
+ * @s: QED state
+ * @table: L2 table
+ * @index: First cluster index
+ * @n: Number of contiguous clusters
+ * @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;
+ if (!qed_offset_is_unalloc_cluster(cluster) &&
+ !qed_offset_is_zero_cluster(cluster)) {
+ cluster += s->header.cluster_size;
+ }
+ }
+}
+
+static void qed_aio_complete_bh(void *opaque)
+{
+ QEDAIOCB *acb = opaque;
+ BlockDriverCompletionFunc *cb = acb->common.cb;
+ void *user_opaque = acb->common.opaque;
+ int ret = acb->bh_ret;
+ bool *finished = acb->finished;
+
+ qemu_bh_delete(acb->bh);
+ qemu_aio_release(acb);
+
+ /* Invoke callback */
+ cb(user_opaque, ret);
+
+ /* Signal cancel completion */
+ if (finished) {
+ *finished = true;
+ }
+}
+
+static void qed_aio_complete(QEDAIOCB *acb, int ret)
+{
+ BDRVQEDState *s = acb_to_s(acb);
+
+ trace_qed_aio_complete(s, acb, ret);
+
+ /* Free resources */
+ qemu_iovec_destroy(&acb->cur_qiov);
+ qed_unref_l2_cache_entry(acb->request.l2_table);
+
+ /* Arrange for a bh to invoke the completion function */
+ acb->bh_ret = ret;
+ acb->bh = qemu_bh_new(qed_aio_complete_bh, acb);
+ qemu_bh_schedule(acb->bh);
+
+ /* Start next allocating write request waiting behind this one. Note that
+ * requests enqueue themselves when they first hit an unallocated cluster
+ * but they wait until the entire request is finished before waking up the
+ * next request in the queue. This ensures that we don't cycle through
+ * requests multiple times but rather finish one at a time completely.
+ */
+ if (acb == QSIMPLEQ_FIRST(&s->allocating_write_reqs)) {
+ QSIMPLEQ_REMOVE_HEAD(&s->allocating_write_reqs, next);
+ 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);
+ }
+ }
+}
+
+/**
+ * Commit the current L2 table to the cache
+ */
+static void qed_commit_l2_update(void *opaque, int ret)
+{
+ QEDAIOCB *acb = opaque;
+ BDRVQEDState *s = acb_to_s(acb);
+ CachedL2Table *l2_table = acb->request.l2_table;
+
+ qed_commit_l2_cache_entry(&s->l2_cache, l2_table);
+
+ /* This is guaranteed to succeed because we just committed the entry to the
+ * cache.
+ */
+ acb->request.l2_table = qed_find_l2_cache_entry(&s->l2_cache,
+ l2_table->offset);
+ assert(acb->request.l2_table != NULL);
+
+ qed_aio_next_io(opaque, ret);
+}
+
+/**
+ * Update L1 table with new L2 table offset and write it out
+ */
+static void qed_aio_write_l1_update(void *opaque, int ret)
+{
+ QEDAIOCB *acb = opaque;
+ BDRVQEDState *s = acb_to_s(acb);
+ int index;
+
+ if (ret) {
+ qed_aio_complete(acb, ret);
+ return;
+ }
+
+ index = qed_l1_index(s, acb->cur_pos);
+ s->l1_table->offsets[index] = acb->request.l2_table->offset;
+
+ qed_write_l1_table(s, index, 1, qed_commit_l2_update, acb);
+}
+
+/**
+ * Update L2 table with new cluster offsets and write them out
+ */
+static void qed_aio_write_l2_update(void *opaque, int ret)
+{
+ QEDAIOCB *acb = opaque;
+ BDRVQEDState *s = acb_to_s(acb);
+ bool need_alloc = acb->find_cluster_ret == QED_CLUSTER_L1;
+ int index;
+
+ if (ret) {
+ goto err;
+ }
+
+ if (need_alloc) {
+ qed_unref_l2_cache_entry(acb->request.l2_table);
+ acb->request.l2_table = qed_new_l2_table(s);
+ }
+
+ index = qed_l2_index(s, acb->cur_pos);
+ qed_update_l2_table(s, acb->request.l2_table->table, index, acb->cur_nclusters,
+ acb->cur_cluster);
+
+ if (need_alloc) {
+ /* Write out the whole new L2 table */
+ qed_write_l2_table(s, &acb->request, 0, s->table_nelems, true,
+ qed_aio_write_l1_update, acb);
+ } else {
+ /* Write out only the updated part of the L2 table */
+ qed_write_l2_table(s, &acb->request, index, acb->cur_nclusters, false,
+ qed_aio_next_io, acb);
+ }
+ return;
+
+err:
+ qed_aio_complete(acb, ret);
+}
+
+/**
+ * Flush new data clusters before updating the L2 table
+ *
+ * This flush is necessary when a backing file is in use. A crash during an
+ * allocating write could result in empty clusters in the image. If the write
+ * only touched a subregion of the cluster, then backing image sectors have
+ * been lost in the untouched region. The solution is to flush after writing a
+ * new data cluster and before updating the L2 table.
+ */
+static void qed_aio_write_flush_before_l2_update(void *opaque, int ret)
+{
+ QEDAIOCB *acb = opaque;
+ BDRVQEDState *s = acb_to_s(acb);
+
+ if (!bdrv_aio_flush(s->bs->file, qed_aio_write_l2_update, opaque)) {
+ qed_aio_complete(acb, -EIO);
+ }
+}
+
+/**
+ * Write data to the image file
+ */
+static void qed_aio_write_main(void *opaque, int ret)
+{
+ QEDAIOCB *acb = opaque;
+ BDRVQEDState *s = acb_to_s(acb);
+ uint64_t offset = acb->cur_cluster +
+ qed_offset_into_cluster(s, acb->cur_pos);
+ BlockDriverCompletionFunc *next_fn;
+ BlockDriverAIOCB *file_acb;
+
+ trace_qed_aio_write_main(s, acb, ret, offset, acb->cur_qiov.size);
+
+ if (ret) {
+ qed_aio_complete(acb, ret);
+ return;
+ }
+
+ if (acb->find_cluster_ret == QED_CLUSTER_FOUND) {
+ next_fn = qed_aio_next_io;
+ } else {
+ if (s->bs->backing_hd) {
+ next_fn = qed_aio_write_flush_before_l2_update;
+ } else {
+ next_fn = qed_aio_write_l2_update;
+ }
+ }
+
+ BLKDBG_EVENT(s->bs->file, BLKDBG_WRITE_AIO);
+ file_acb = bdrv_aio_writev(s->bs->file, offset / BDRV_SECTOR_SIZE,
+ &acb->cur_qiov,
+ acb->cur_qiov.size / BDRV_SECTOR_SIZE,
+ next_fn, acb);
+ if (!file_acb) {
+ qed_aio_complete(acb, -EIO);
+ }
+}
+
+/**
+ * Populate back untouched region of new data cluster
+ */
+static void qed_aio_write_postfill(void *opaque, int ret)
+{
+ QEDAIOCB *acb = opaque;
+ BDRVQEDState *s = acb_to_s(acb);
+ uint64_t start = acb->cur_pos + acb->cur_qiov.size;
+ uint64_t len =
+ qed_start_of_cluster(s, start + s->header.cluster_size - 1) - start;
+ uint64_t offset = acb->cur_cluster +
+ qed_offset_into_cluster(s, acb->cur_pos) +
+ acb->cur_qiov.size;
+
+ if (ret) {
+ qed_aio_complete(acb, ret);
+ return;
+ }
+
+ trace_qed_aio_write_postfill(s, acb, start, len, offset);
+ qed_copy_from_backing_file(s, start, len, offset,
+ qed_aio_write_main, acb);
+}
+
+/**
+ * Populate front untouched region of new data cluster
+ */
+static void qed_aio_write_prefill(void *opaque, int ret)
+{
+ QEDAIOCB *acb = opaque;
+ BDRVQEDState *s = acb_to_s(acb);
+ uint64_t start = qed_start_of_cluster(s, acb->cur_pos);
+ uint64_t len = qed_offset_into_cluster(s, acb->cur_pos);
+
+ trace_qed_aio_write_prefill(s, acb, start, len, acb->cur_cluster);
+ qed_copy_from_backing_file(s, start, len, acb->cur_cluster,
+ 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
+ *
+ * @acb: Write request
+ * @len: Length in bytes
+ *
+ * This path is taken when writing to previously unallocated clusters.
+ */
+static void qed_aio_write_alloc(QEDAIOCB *acb, size_t len)
+{
+ 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) ||
+ s->allocating_write_reqs_plugged) {
+ return; /* wait for existing request to finish */
+ }
+
+ acb->cur_nclusters = qed_bytes_to_clusters(s,
+ qed_offset_into_cluster(s, acb->cur_pos) + len);
+ acb->cur_cluster = qed_alloc_clusters(s, acb->cur_nclusters);
+ qemu_iovec_copy(&acb->cur_qiov, acb->qiov, acb->qiov_offset, len);
+
+ 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);
+ }
+}
+
+/**
+ * Write data cluster in place
+ *
+ * @acb: Write request
+ * @offset: Cluster offset in bytes
+ * @len: Length in bytes
+ *
+ * This path is taken when writing to already allocated clusters.
+ */
+static void qed_aio_write_inplace(QEDAIOCB *acb, uint64_t offset, size_t len)
+{
+ /* Calculate the I/O vector */
+ acb->cur_cluster = offset;
+ qemu_iovec_copy(&acb->cur_qiov, acb->qiov, acb->qiov_offset, len);
+
+ /* Do the actual write */
+ qed_aio_write_main(acb, 0);
+}
+
+/**
+ * Write data cluster
+ *
+ * @opaque: Write request
+ * @ret: QED_CLUSTER_FOUND, QED_CLUSTER_L2, QED_CLUSTER_L1,
+ * or -errno
+ * @offset: Cluster offset in bytes
+ * @len: Length in bytes
+ *
+ * Callback from qed_find_cluster().
+ */
+static void qed_aio_write_data(void *opaque, int ret,
+ uint64_t offset, size_t len)
+{
+ QEDAIOCB *acb = opaque;
+
+ trace_qed_aio_write_data(acb_to_s(acb), acb, ret, offset, len);
+
+ acb->find_cluster_ret = ret;
+
+ switch (ret) {
+ case QED_CLUSTER_FOUND:
+ qed_aio_write_inplace(acb, offset, len);
+ break;
+
+ case QED_CLUSTER_L2:
+ case QED_CLUSTER_L1:
+ case QED_CLUSTER_ZERO:
+ qed_aio_write_alloc(acb, len);
+ break;
+
+ default:
+ qed_aio_complete(acb, ret);
+ break;
+ }
+}
+
+/**
+ * Read data cluster
+ *
+ * @opaque: Read request
+ * @ret: QED_CLUSTER_FOUND, QED_CLUSTER_L2, QED_CLUSTER_L1,
+ * or -errno
+ * @offset: Cluster offset in bytes
+ * @len: Length in bytes
+ *
+ * Callback from qed_find_cluster().
+ */
+static void qed_aio_read_data(void *opaque, int ret,
+ uint64_t offset, size_t len)
+{
+ QEDAIOCB *acb = opaque;
+ BDRVQEDState *s = acb_to_s(acb);
+ BlockDriverState *bs = acb->common.bs;
+ BlockDriverAIOCB *file_acb;
+
+ /* Adjust offset into cluster */
+ offset += qed_offset_into_cluster(s, acb->cur_pos);
+
+ trace_qed_aio_read_data(s, acb, ret, offset, len);
+
+ if (ret < 0) {
+ goto err;
+ }
+
+ qemu_iovec_copy(&acb->cur_qiov, acb->qiov, acb->qiov_offset, len);
+
+ /* 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;
+ }
+
+ BLKDBG_EVENT(bs->file, BLKDBG_READ_AIO);
+ file_acb = bdrv_aio_readv(bs->file, offset / BDRV_SECTOR_SIZE,
+ &acb->cur_qiov,
+ acb->cur_qiov.size / BDRV_SECTOR_SIZE,
+ qed_aio_next_io, acb);
+ if (!file_acb) {
+ ret = -EIO;
+ goto err;
+ }
+ return;
+
+err:
+ qed_aio_complete(acb, ret);
+}
+
+/**
+ * Begin next I/O or complete the request
+ */
+static void qed_aio_next_io(void *opaque, int ret)
+{
+ QEDAIOCB *acb = opaque;
+ BDRVQEDState *s = acb_to_s(acb);
+ QEDFindClusterFunc *io_fn =
+ acb->is_write ? qed_aio_write_data : qed_aio_read_data;
+
+ trace_qed_aio_next_io(s, acb, ret, acb->cur_pos + acb->cur_qiov.size);
+
+ /* Handle I/O error */
+ if (ret) {
+ qed_aio_complete(acb, ret);
+ return;
+ }
+
+ acb->qiov_offset += acb->cur_qiov.size;
+ acb->cur_pos += acb->cur_qiov.size;
+ qemu_iovec_reset(&acb->cur_qiov);
+
+ /* Complete request */
+ if (acb->cur_pos >= acb->end_pos) {
+ qed_aio_complete(acb, 0);
+ return;
+ }
+
+ /* Find next cluster and start I/O */
+ qed_find_cluster(s, &acb->request,
+ acb->cur_pos, acb->end_pos - acb->cur_pos,
+ io_fn, acb);
+}
+
+static BlockDriverAIOCB *qed_aio_setup(BlockDriverState *bs,
+ int64_t sector_num,
+ QEMUIOVector *qiov, int nb_sectors,
+ BlockDriverCompletionFunc *cb,
+ void *opaque, bool is_write)
+{
+ QEDAIOCB *acb = qemu_aio_get(&qed_aio_pool, bs, cb, opaque);
+
+ trace_qed_aio_setup(bs->opaque, acb, sector_num, nb_sectors,
+ opaque, is_write);
+
+ acb->is_write = is_write;
+ acb->finished = NULL;
+ acb->qiov = qiov;
+ acb->qiov_offset = 0;
+ acb->cur_pos = (uint64_t)sector_num * BDRV_SECTOR_SIZE;
+ acb->end_pos = acb->cur_pos + nb_sectors * BDRV_SECTOR_SIZE;
+ acb->request.l2_table = NULL;
+ qemu_iovec_init(&acb->cur_qiov, qiov->niov);
+
+ /* Start request */
+ qed_aio_next_io(acb, 0);
+ return &acb->common;
+}
+
static BlockDriverAIOCB *bdrv_qed_aio_readv(BlockDriverState *bs,
int64_t sector_num,
QEMUIOVector *qiov, int nb_sectors,
BlockDriverCompletionFunc *cb,
void *opaque)
{
- return NULL;
+ return qed_aio_setup(bs, sector_num, qiov, nb_sectors, cb, opaque, false);
}
static BlockDriverAIOCB *bdrv_qed_aio_writev(BlockDriverState *bs,
BlockDriverCompletionFunc *cb,
void *opaque)
{
- return NULL;
+ return qed_aio_setup(bs, sector_num, qiov, nb_sectors, cb, opaque, true);
}
static BlockDriverAIOCB *bdrv_qed_aio_flush(BlockDriverState *bs,
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,