static int qcow2_cache_entry_flush(BlockDriverState *bs, Qcow2Cache *c, int i)
{
BDRVQcowState *s = bs->opaque;
int ret = 0;
if (!c->entries[i].dirty || !c->entries[i].offset) {
return 0;
}
trace_qcow2_cache_entry_flush(qemu_coroutine_self(),
c == s->l2_table_cache, i);
if (c->depends) {
ret = qcow2_cache_flush_dependency(bs, c);
} else if (c->depends_on_flush) {
ret = bdrv_flush(bs->file);
if (ret >= 0) {
c->depends_on_flush = false;
}
}
if (ret < 0) {
return ret;
}
if (c == s->refcount_block_cache) {
ret = qcow2_pre_write_overlap_check(bs,
QCOW2_OL_DEFAULT & ~QCOW2_OL_REFCOUNT_BLOCK,
c->entries[i].offset, s->cluster_size);
} else if (c == s->l2_table_cache) {
ret = qcow2_pre_write_overlap_check(bs,
QCOW2_OL_DEFAULT & ~QCOW2_OL_ACTIVE_L2,
c->entries[i].offset, s->cluster_size);
} else {
ret = qcow2_pre_write_overlap_check(bs, QCOW2_OL_DEFAULT,
c->entries[i].offset, s->cluster_size);
}
if (ret < 0) {
return ret;
}
if (c == s->refcount_block_cache) {
BLKDBG_EVENT(bs->file, BLKDBG_REFBLOCK_UPDATE_PART);
} else if (c == s->l2_table_cache) {
BLKDBG_EVENT(bs->file, BLKDBG_L2_UPDATE);
}
ret = bdrv_pwrite(bs->file, c->entries[i].offset, c->entries[i].table,
s->cluster_size);
if (ret < 0) {
return ret;
}
c->entries[i].dirty = false;
return 0;
}
static int qcow2_cache_do_get(BlockDriverState *bs, Qcow2Cache *c,
uint64_t offset, void **table, bool read_from_disk)
{
BDRVQcowState *s = bs->opaque;
int i;
int ret;
trace_qcow2_cache_get(qemu_coroutine_self(), c == s->l2_table_cache,
offset, read_from_disk);
/* Check if the table is already cached */
for (i = 0; i < c->size; i++) {
if (c->entries[i].offset == offset) {
goto found;
}
}
/* If not, write a table back and replace it */
i = qcow2_cache_find_entry_to_replace(c);
trace_qcow2_cache_get_replace_entry(qemu_coroutine_self(),
c == s->l2_table_cache, i);
if (i < 0) {
return i;
}
ret = qcow2_cache_entry_flush(bs, c, i);
if (ret < 0) {
return ret;
}
trace_qcow2_cache_get_read(qemu_coroutine_self(),
c == s->l2_table_cache, i);
c->entries[i].offset = 0;
if (read_from_disk) {
if (c == s->l2_table_cache) {
BLKDBG_EVENT(bs->file, BLKDBG_L2_LOAD);
}
ret = bdrv_pread(bs->file, offset, c->entries[i].table, s->cluster_size);
if (ret < 0) {
return ret;
}
}
/* Give the table some hits for the start so that it won't be replaced
* immediately. The number 32 is completely arbitrary. */
c->entries[i].cache_hits = 32;
c->entries[i].offset = offset;
/* And return the right table */
found:
c->entries[i].cache_hits++;
c->entries[i].ref++;
*table = c->entries[i].table;
trace_qcow2_cache_get_done(qemu_coroutine_self(),
c == s->l2_table_cache, i);
return 0;
}
void qed_read_l2_table(BDRVQEDState *s, QEDRequest *request, uint64_t offset,
BlockDriverCompletionFunc *cb, void *opaque)
{
QEDReadL2TableCB *read_l2_table_cb;
qed_unref_l2_cache_entry(request->l2_table);
/* Check for cached L2 entry */
request->l2_table = qed_find_l2_cache_entry(&s->l2_cache, offset);
if (request->l2_table) {
cb(opaque, 0);
return;
}
request->l2_table = qed_alloc_l2_cache_entry(&s->l2_cache);
request->l2_table->table = qed_alloc_table(s);
read_l2_table_cb = gencb_alloc(sizeof(*read_l2_table_cb), cb, opaque);
read_l2_table_cb->s = s;
read_l2_table_cb->l2_offset = offset;
read_l2_table_cb->request = request;
BLKDBG_EVENT(s->bs->file, BLKDBG_L2_LOAD);
qed_read_table(s, offset, request->l2_table->table,
qed_read_l2_table_cb, read_l2_table_cb);
}
void qed_write_l1_table(BDRVQEDState *s, unsigned int index, unsigned int n,
BlockDriverCompletionFunc *cb, void *opaque)
{
BLKDBG_EVENT(s->bs->file, BLKDBG_L1_UPDATE);
qed_write_table(s, s->header.l1_table_offset,
s->l1_table, index, n, false, cb, opaque);
}
void qed_write_l2_table(BDRVQEDState *s, QEDRequest *request,
unsigned int index, unsigned int n, bool flush,
BlockDriverCompletionFunc *cb, void *opaque)
{
BLKDBG_EVENT(s->bs->file, BLKDBG_L2_UPDATE);
qed_write_table(s, request->l2_table->offset,
request->l2_table->table, index, n, flush, cb, opaque);
}
static int coroutine_fn
raw_co_writev_flags(BlockDriverState *bs, int64_t sector_num, int nb_sectors,
QEMUIOVector *qiov, int flags)
{
void *buf = NULL;
BlockDriver *drv;
QEMUIOVector local_qiov;
int ret;
if (bs->probed && sector_num == 0) {
/* As long as these conditions are true, we can't get partial writes to
* the probe buffer and can just directly check the request. */
QEMU_BUILD_BUG_ON(BLOCK_PROBE_BUF_SIZE != 512);
QEMU_BUILD_BUG_ON(BDRV_SECTOR_SIZE != 512);
if (nb_sectors == 0) {
/* qemu_iovec_to_buf() would fail, but we want to return success
* instead of -EINVAL in this case. */
return 0;
}
buf = qemu_try_blockalign(bs->file->bs, 512);
if (!buf) {
ret = -ENOMEM;
goto fail;
}
ret = qemu_iovec_to_buf(qiov, 0, buf, 512);
if (ret != 512) {
ret = -EINVAL;
goto fail;
}
drv = bdrv_probe_all(buf, 512, NULL);
if (drv != bs->drv) {
ret = -EPERM;
goto fail;
}
/* Use the checked buffer, a malicious guest might be overwriting its
* original buffer in the background. */
qemu_iovec_init(&local_qiov, qiov->niov + 1);
qemu_iovec_add(&local_qiov, buf, 512);
qemu_iovec_concat(&local_qiov, qiov, 512, qiov->size - 512);
qiov = &local_qiov;
}
BLKDBG_EVENT(bs->file, BLKDBG_WRITE_AIO);
ret = bdrv_co_do_pwritev(bs->file->bs, sector_num * BDRV_SECTOR_SIZE,
nb_sectors * BDRV_SECTOR_SIZE, qiov, flags);
fail:
if (qiov == &local_qiov) {
qemu_iovec_destroy(&local_qiov);
}
qemu_vfree(buf);
return ret;
}
static int load_refcount_block(BlockDriverState *bs,
int64_t refcount_block_offset,
void **refcount_block)
{
BDRVQcowState *s = bs->opaque;
int ret;
BLKDBG_EVENT(bs->file, BLKDBG_REFBLOCK_LOAD);
ret = qcow2_cache_get(bs, s->refcount_block_cache, refcount_block_offset,
refcount_block);
return ret;
}
static int qcow2_cache_entry_flush(BlockDriverState *bs, Qcow2Cache *c, int i)
{
BDRVQcowState *s = bs->opaque;
int ret = 0;
if (!c->entries[i].dirty || !c->entries[i].offset) {
return 0;
}
if (c->depends) {
ret = qcow2_cache_flush_dependency(bs, c);
} else if (c->depends_on_flush) {
ret = bdrv_flush(bs->file);
if (ret >= 0) {
c->depends_on_flush = false;
}
}
if (ret < 0) {
return ret;
}
if (c == s->refcount_block_cache) {
BLKDBG_EVENT(bs->file, BLKDBG_REFBLOCK_UPDATE_PART);
} else if (c == s->l2_table_cache) {
BLKDBG_EVENT(bs->file, BLKDBG_L2_UPDATE);
}
ret = bdrv_pwrite(bs->file, c->entries[i].offset, c->entries[i].table,
s->cluster_size);
if (ret < 0) {
return ret;
}
c->entries[i].dirty = false;
return 0;
}
static int write_refcount_block(BlockDriverState *bs)
{
BDRVQcowState *s = bs->opaque;
size_t size = s->cluster_size;
if (s->refcount_block_cache_offset == 0) {
return 0;
}
BLKDBG_EVENT(bs->file, BLKDBG_REFBLOCK_UPDATE);
if (bdrv_pwrite_sync(bs->file, s->refcount_block_cache_offset,
s->refcount_block_cache, size) < 0)
{
return -EIO;
}
return 0;
}
int qcow2_refcount_init(BlockDriverState *bs)
{
BDRVQcowState *s = bs->opaque;
int ret, refcount_table_size2, i;
refcount_table_size2 = s->refcount_table_size * sizeof(uint64_t);
s->refcount_table = g_malloc(refcount_table_size2);
if (s->refcount_table_size > 0) {
BLKDBG_EVENT(bs->file, BLKDBG_REFTABLE_LOAD);
ret = bdrv_pread(bs->file, s->refcount_table_offset,
s->refcount_table, refcount_table_size2);
if (ret != refcount_table_size2)
goto fail;
for(i = 0; i < s->refcount_table_size; i++)
be64_to_cpus(&s->refcount_table[i]);
}
return 0;
fail:
return -ENOMEM;
}
static int load_refcount_block(BlockDriverState *bs,
int64_t refcount_block_offset)
{
BDRVQcowState *s = bs->opaque;
int ret;
if (cache_refcount_updates) {
ret = write_refcount_block(bs);
if (ret < 0) {
return ret;
}
}
BLKDBG_EVENT(bs->file, BLKDBG_REFBLOCK_LOAD);
ret = bdrv_pread(bs->file, refcount_block_offset, s->refcount_block_cache,
s->cluster_size);
if (ret < 0) {
return ret;
}
s->refcount_block_cache_offset = refcount_block_offset;
return 0;
}
static int coroutine_fn raw_co_readv(BlockDriverState *bs, int64_t sector_num,
int nb_sectors, QEMUIOVector *qiov)
{
BLKDBG_EVENT(bs->file, BLKDBG_READ_AIO);
return bdrv_co_readv(bs->file->bs, sector_num, nb_sectors, qiov);
}
static int qcow2_cache_do_get(BlockDriverState *bs, Qcow2Cache *c,
uint64_t offset, void **table, bool read_from_disk)
{
BDRVQcowState *s = bs->opaque;
int i;
int ret;
int lookup_index;
uint64_t min_lru_counter = UINT64_MAX;
int min_lru_index = -1;
trace_qcow2_cache_get(qemu_coroutine_self(), c == s->l2_table_cache,
offset, read_from_disk);
/* Check if the table is already cached */
i = lookup_index = (offset / s->cluster_size * 4) % c->size;
do {
const Qcow2CachedTable *t = &c->entries[i];
if (t->offset == offset) {
goto found;
}
if (t->ref == 0 && t->lru_counter < min_lru_counter) {
min_lru_counter = t->lru_counter;
min_lru_index = i;
}
if (++i == c->size) {
i = 0;
}
} while (i != lookup_index);
if (min_lru_index == -1) {
/* This can't happen in current synchronous code, but leave the check
* here as a reminder for whoever starts using AIO with the cache */
abort();
}
/* Cache miss: write a table back and replace it */
i = min_lru_index;
trace_qcow2_cache_get_replace_entry(qemu_coroutine_self(),
c == s->l2_table_cache, i);
if (i < 0) {
return i;
}
ret = qcow2_cache_entry_flush(bs, c, i);
if (ret < 0) {
return ret;
}
trace_qcow2_cache_get_read(qemu_coroutine_self(),
c == s->l2_table_cache, i);
c->entries[i].offset = 0;
if (read_from_disk) {
if (c == s->l2_table_cache) {
BLKDBG_EVENT(bs->file, BLKDBG_L2_LOAD);
}
ret = bdrv_pread(bs->file, offset, qcow2_cache_get_table_addr(bs, c, i),
s->cluster_size);
if (ret < 0) {
return ret;
}
}
c->entries[i].offset = offset;
/* And return the right table */
found:
c->entries[i].ref++;
*table = qcow2_cache_get_table_addr(bs, c, i);
trace_qcow2_cache_get_done(qemu_coroutine_self(),
c == s->l2_table_cache, i);
return 0;
}
