#include "qapi/qmp/qjson.h"
#include "sysemu/block-backend.h"
#include "sysemu/sysemu.h"
+#include "sysemu/qtest.h"
#include "qemu/notify.h"
#include "block/coroutine.h"
#include "block/qapi.h"
#include <windows.h>
#endif
+/**
+ * A BdrvDirtyBitmap can be in three possible states:
+ * (1) successor is NULL and disabled is false: full r/w mode
+ * (2) successor is NULL and disabled is true: read only mode ("disabled")
+ * (3) successor is set: frozen mode.
+ * A frozen bitmap cannot be renamed, deleted, anonymized, cleared, set,
+ * or enabled. A frozen bitmap can only abdicate() or reclaim().
+ */
struct BdrvDirtyBitmap {
- HBitmap *bitmap;
+ HBitmap *bitmap; /* Dirty sector bitmap implementation */
+ BdrvDirtyBitmap *successor; /* Anonymous child; implies frozen status */
+ char *name; /* Optional non-empty unique ID */
+ int64_t size; /* Size of the bitmap (Number of sectors) */
+ bool disabled; /* Bitmap is read-only */
QLIST_ENTRY(BdrvDirtyBitmap) list;
};
static QLIST_HEAD(, BlockDriver) bdrv_drivers =
QLIST_HEAD_INITIALIZER(bdrv_drivers);
+static void bdrv_set_dirty(BlockDriverState *bs, int64_t cur_sector,
+ int nr_sectors);
+static void bdrv_reset_dirty(BlockDriverState *bs, int64_t cur_sector,
+ int nr_sectors);
+static void bdrv_dirty_bitmap_truncate(BlockDriverState *bs);
/* If non-zero, use only whitelisted block drivers */
static int use_bdrv_whitelist;
/* should be called before bdrv_set_io_limits if a limit is set */
void bdrv_io_limits_enable(BlockDriverState *bs)
{
+ int clock_type = QEMU_CLOCK_REALTIME;
+
+ if (qtest_enabled()) {
+ /* For testing block IO throttling only */
+ clock_type = QEMU_CLOCK_VIRTUAL;
+ }
assert(!bs->io_limits_enabled);
throttle_init(&bs->throttle_state,
bdrv_get_aio_context(bs),
- QEMU_CLOCK_VIRTUAL,
+ clock_type,
bdrv_throttle_read_timer_cb,
bdrv_throttle_write_timer_cb,
bs);
void bdrv_get_full_backing_filename_from_filename(const char *backed,
const char *backing,
- char *dest, size_t sz)
+ char *dest, size_t sz,
+ Error **errp)
{
- if (backing[0] == '\0' || path_has_protocol(backing)) {
+ if (backing[0] == '\0' || path_has_protocol(backing) ||
+ path_is_absolute(backing))
+ {
pstrcpy(dest, sz, backing);
+ } else if (backed[0] == '\0' || strstart(backed, "json:", NULL)) {
+ error_setg(errp, "Cannot use relative backing file names for '%s'",
+ backed);
} else {
path_combine(dest, sz, backed, backing);
}
}
-void bdrv_get_full_backing_filename(BlockDriverState *bs, char *dest, size_t sz)
+void bdrv_get_full_backing_filename(BlockDriverState *bs, char *dest, size_t sz,
+ Error **errp)
{
- bdrv_get_full_backing_filename_from_filename(bs->filename, bs->backing_file,
- dest, sz);
+ char *backed = bs->exact_filename[0] ? bs->exact_filename : bs->filename;
+
+ bdrv_get_full_backing_filename_from_filename(backed, bs->backing_file,
+ dest, sz, errp);
}
void bdrv_register(BlockDriver *bdrv)
Error *local_err = NULL;
int ret;
- drv = bdrv_find_protocol(filename, true);
+ drv = bdrv_find_protocol(filename, true, errp);
if (drv == NULL) {
- error_setg(errp, "Could not find protocol for file '%s'", filename);
return -ENOENT;
}
}
}
+/**
+ * Try to get @bs's logical and physical block size.
+ * On success, store them in @bsz struct and return 0.
+ * On failure return -errno.
+ * @bs must not be empty.
+ */
+int bdrv_probe_blocksizes(BlockDriverState *bs, BlockSizes *bsz)
+{
+ BlockDriver *drv = bs->drv;
+
+ if (drv && drv->bdrv_probe_blocksizes) {
+ return drv->bdrv_probe_blocksizes(bs, bsz);
+ }
+
+ return -ENOTSUP;
+}
+
+/**
+ * Try to get @bs's geometry (cyls, heads, sectors).
+ * On success, store them in @geo struct and return 0.
+ * On failure return -errno.
+ * @bs must not be empty.
+ */
+int bdrv_probe_geometry(BlockDriverState *bs, HDGeometry *geo)
+{
+ BlockDriver *drv = bs->drv;
+
+ if (drv && drv->bdrv_probe_geometry) {
+ return drv->bdrv_probe_geometry(bs, geo);
+ }
+
+ return -ENOTSUP;
+}
+
/*
* Create a uniquely-named empty temporary file.
* Return 0 upon success, otherwise a negative errno value.
}
BlockDriver *bdrv_find_protocol(const char *filename,
- bool allow_protocol_prefix)
+ bool allow_protocol_prefix,
+ Error **errp)
{
BlockDriver *drv1;
char protocol[128];
return drv1;
}
}
+
+ error_setg(errp, "Unknown protocol '%s'", protocol);
return NULL;
}
bs->zero_beyond_eof = true;
open_flags = bdrv_open_flags(bs, flags);
bs->read_only = !(open_flags & BDRV_O_RDWR);
- bs->growable = !!(flags & BDRV_O_PROTOCOL);
if (use_bdrv_whitelist && !bdrv_is_whitelisted(drv, bs->read_only)) {
error_setg(errp,
goto free_and_fail;
}
+ if (bs->encrypted) {
+ error_report("Encrypted images are deprecated");
+ error_printf("Support for them will be removed in a future release.\n"
+ "You can use 'qemu-img convert' to convert your image"
+ " to an unencrypted one.\n");
+ }
+
ret = refresh_total_sectors(bs, bs->total_sectors);
if (ret < 0) {
error_setg_errno(errp, -ret, "Could not refresh total sector count");
} else {
if (!drvname && protocol) {
if (filename) {
- drv = bdrv_find_protocol(filename, parse_filename);
+ drv = bdrv_find_protocol(filename, parse_filename, errp);
if (!drv) {
- error_setg(errp, "Unknown protocol");
return -EINVAL;
}
bdrv_op_unblock_all(bs->backing_hd, bs->backing_blocker);
} else if (backing_hd) {
error_setg(&bs->backing_blocker,
- "device is used as backing hd of '%s'",
- bdrv_get_device_name(bs));
+ "node is used as backing hd of '%s'",
+ bdrv_get_device_or_node_name(bs));
}
bs->backing_hd = backing_hd;
bdrv_op_block_all(bs->backing_hd, bs->backing_blocker);
/* Otherwise we won't be able to commit due to check in bdrv_commit */
- bdrv_op_unblock(bs->backing_hd, BLOCK_OP_TYPE_COMMIT,
+ bdrv_op_unblock(bs->backing_hd, BLOCK_OP_TYPE_COMMIT_TARGET,
bs->backing_blocker);
out:
bdrv_refresh_limits(bs, NULL);
QDECREF(options);
goto free_exit;
} else {
- bdrv_get_full_backing_filename(bs, backing_filename, PATH_MAX);
+ bdrv_get_full_backing_filename(bs, backing_filename, PATH_MAX,
+ &local_err);
+ if (local_err) {
+ ret = -EINVAL;
+ error_propagate(errp, local_err);
+ QDECREF(options);
+ goto free_exit;
+ }
}
if (!bs->drv || !bs->drv->supports_backing) {
opts = qemu_opts_create(bdrv_qcow2.create_opts, NULL, 0,
&error_abort);
- qemu_opt_set_number(opts, BLOCK_OPT_SIZE, total_size);
+ qemu_opt_set_number(opts, BLOCK_OPT_SIZE, total_size, &error_abort);
ret = bdrv_create(&bdrv_qcow2, tmp_filename, opts, &local_err);
qemu_opts_del(opts);
if (ret < 0) {
* to r/w */
if (!(reopen_state->bs->open_flags & BDRV_O_ALLOW_RDWR) &&
reopen_state->flags & BDRV_O_RDWR) {
- error_set(errp, QERR_DEVICE_IS_READ_ONLY,
- bdrv_get_device_name(reopen_state->bs));
+ error_setg(errp, "Node '%s' is read only",
+ bdrv_get_device_or_node_name(reopen_state->bs));
goto error;
}
} else {
/* It is currently mandatory to have a bdrv_reopen_prepare()
* handler for each supported drv. */
- error_set(errp, QERR_BLOCK_FORMAT_FEATURE_NOT_SUPPORTED,
- drv->format_name, bdrv_get_device_name(reopen_state->bs),
- "reopening of file");
+ error_setg(errp, "Block format '%s' used by node '%s' "
+ "does not support reopening files", drv->format_name,
+ bdrv_get_device_or_node_name(reopen_state->bs));
ret = -1;
goto error;
}
bs->encrypted = 0;
bs->valid_key = 0;
bs->sg = 0;
- bs->growable = 0;
bs->zero_beyond_eof = false;
QDECREF(bs->options);
bs->options = NULL;
bool busy = true;
BlockDriverState *bs;
+ QTAILQ_FOREACH(bs, &bdrv_states, device_list) {
+ AioContext *aio_context = bdrv_get_aio_context(bs);
+
+ aio_context_acquire(aio_context);
+ if (bs->job) {
+ block_job_pause(bs->job);
+ }
+ aio_context_release(aio_context);
+ }
+
while (busy) {
busy = false;
aio_context_release(aio_context);
}
}
+
+ QTAILQ_FOREACH(bs, &bdrv_states, device_list) {
+ AioContext *aio_context = bdrv_get_aio_context(bs);
+
+ aio_context_acquire(aio_context);
+ if (bs->job) {
+ block_job_resume(bs->job);
+ }
+ aio_context_release(aio_context);
+ }
}
/* make a BlockDriverState anonymous by removing from bdrv_state and
int n, ro, open_flags;
int ret = 0;
uint8_t *buf = NULL;
- char filename[PATH_MAX];
if (!drv)
return -ENOMEDIUM;
return -ENOTSUP;
}
- if (bdrv_op_is_blocked(bs, BLOCK_OP_TYPE_COMMIT, NULL) ||
- bdrv_op_is_blocked(bs->backing_hd, BLOCK_OP_TYPE_COMMIT, NULL)) {
+ if (bdrv_op_is_blocked(bs, BLOCK_OP_TYPE_COMMIT_SOURCE, NULL) ||
+ bdrv_op_is_blocked(bs->backing_hd, BLOCK_OP_TYPE_COMMIT_TARGET, NULL)) {
return -EBUSY;
}
ro = bs->backing_hd->read_only;
- /* Use pstrcpy (not strncpy): filename must be NUL-terminated. */
- pstrcpy(filename, sizeof(filename), bs->backing_hd->filename);
open_flags = bs->backing_hd->open_flags;
if (ro) {
static int bdrv_check_byte_request(BlockDriverState *bs, int64_t offset,
size_t size)
{
- int64_t len;
-
- if (size > INT_MAX) {
+ if (size > BDRV_REQUEST_MAX_SECTORS << BDRV_SECTOR_BITS) {
return -EIO;
}
- if (!bdrv_is_inserted(bs))
+ if (!bdrv_is_inserted(bs)) {
return -ENOMEDIUM;
+ }
- if (bs->growable)
- return 0;
-
- len = bdrv_getlength(bs);
-
- if (offset < 0)
- return -EIO;
-
- if ((offset > len) || (len - offset < size))
+ if (offset < 0) {
return -EIO;
+ }
return 0;
}
static int bdrv_check_request(BlockDriverState *bs, int64_t sector_num,
int nb_sectors)
{
- if (nb_sectors < 0 || nb_sectors > INT_MAX / BDRV_SECTOR_SIZE) {
+ if (nb_sectors < 0 || nb_sectors > BDRV_REQUEST_MAX_SECTORS) {
return -EIO;
}
.iov_len = nb_sectors * BDRV_SECTOR_SIZE,
};
- if (nb_sectors < 0 || nb_sectors > INT_MAX / BDRV_SECTOR_SIZE) {
+ if (nb_sectors < 0 || nb_sectors > BDRV_REQUEST_MAX_SECTORS) {
return -EINVAL;
}
}
for (;;) {
- nb_sectors = target_sectors - sector_num;
+ nb_sectors = MIN(target_sectors - sector_num, BDRV_REQUEST_MAX_SECTORS);
if (nb_sectors <= 0) {
return 0;
}
- if (nb_sectors > INT_MAX / BDRV_SECTOR_SIZE) {
- nb_sectors = INT_MAX / BDRV_SECTOR_SIZE;
- }
ret = bdrv_get_block_status(bs, sector_num, nb_sectors, &n);
if (ret < 0) {
error_report("error getting block status at sector %" PRId64 ": %s",
}
/* Forward the request to the BlockDriver */
- if (!(bs->zero_beyond_eof && bs->growable)) {
+ if (!bs->zero_beyond_eof) {
ret = drv->bdrv_co_readv(bs, sector_num, nb_sectors, qiov);
} else {
- /* Read zeros after EOF of growable BDSes */
+ /* Read zeros after EOF */
int64_t total_sectors, max_nb_sectors;
total_sectors = bdrv_nb_sectors(bs);
return ret;
}
+static inline uint64_t bdrv_get_align(BlockDriverState *bs)
+{
+ /* TODO Lift BDRV_SECTOR_SIZE restriction in BlockDriver interface */
+ return MAX(BDRV_SECTOR_SIZE, bs->request_alignment);
+}
+
+static inline bool bdrv_req_is_aligned(BlockDriverState *bs,
+ int64_t offset, size_t bytes)
+{
+ int64_t align = bdrv_get_align(bs);
+ return !(offset & (align - 1) || (bytes & (align - 1)));
+}
+
/*
* Handle a read request in coroutine context
*/
BlockDriver *drv = bs->drv;
BdrvTrackedRequest req;
- /* TODO Lift BDRV_SECTOR_SIZE restriction in BlockDriver interface */
- uint64_t align = MAX(BDRV_SECTOR_SIZE, bs->request_alignment);
+ uint64_t align = bdrv_get_align(bs);
uint8_t *head_buf = NULL;
uint8_t *tail_buf = NULL;
QEMUIOVector local_qiov;
if (!drv) {
return -ENOMEDIUM;
}
- if (bdrv_check_byte_request(bs, offset, bytes)) {
- return -EIO;
+
+ ret = bdrv_check_byte_request(bs, offset, bytes);
+ if (ret < 0) {
+ return ret;
}
if (bs->copy_on_read) {
int64_t sector_num, int nb_sectors, QEMUIOVector *qiov,
BdrvRequestFlags flags)
{
- if (nb_sectors < 0 || nb_sectors > (UINT_MAX >> BDRV_SECTOR_BITS)) {
+ if (nb_sectors < 0 || nb_sectors > BDRV_REQUEST_MAX_SECTORS) {
return -EINVAL;
}
BDRV_REQ_COPY_ON_READ);
}
-/* if no limit is specified in the BlockLimits use a default
- * of 32768 512-byte sectors (16 MiB) per request.
- */
-#define MAX_WRITE_ZEROES_DEFAULT 32768
+#define MAX_WRITE_ZEROES_BOUNCE_BUFFER 32768
static int coroutine_fn bdrv_co_do_write_zeroes(BlockDriverState *bs,
int64_t sector_num, int nb_sectors, BdrvRequestFlags flags)
struct iovec iov = {0};
int ret = 0;
- int max_write_zeroes = bs->bl.max_write_zeroes ?
- bs->bl.max_write_zeroes : MAX_WRITE_ZEROES_DEFAULT;
+ int max_write_zeroes = MIN_NON_ZERO(bs->bl.max_write_zeroes,
+ BDRV_REQUEST_MAX_SECTORS);
while (nb_sectors > 0 && !ret) {
int num = nb_sectors;
if (ret == -ENOTSUP) {
/* Fall back to bounce buffer if write zeroes is unsupported */
+ int max_xfer_len = MIN_NON_ZERO(bs->bl.max_transfer_length,
+ MAX_WRITE_ZEROES_BOUNCE_BUFFER);
+ num = MIN(num, max_xfer_len);
iov.iov_len = num * BDRV_SECTOR_SIZE;
if (iov.iov_base == NULL) {
iov.iov_base = qemu_try_blockalign(bs, num * BDRV_SECTOR_SIZE);
/* Keep bounce buffer around if it is big enough for all
* all future requests.
*/
- if (num < max_write_zeroes) {
+ if (num < max_xfer_len) {
qemu_vfree(iov.iov_base);
iov.iov_base = NULL;
}
block_acct_highest_sector(&bs->stats, sector_num, nb_sectors);
- if (bs->growable && ret >= 0) {
+ if (ret >= 0) {
bs->total_sectors = MAX(bs->total_sectors, sector_num + nb_sectors);
}
BdrvRequestFlags flags)
{
BdrvTrackedRequest req;
- /* TODO Lift BDRV_SECTOR_SIZE restriction in BlockDriver interface */
- uint64_t align = MAX(BDRV_SECTOR_SIZE, bs->request_alignment);
+ uint64_t align = bdrv_get_align(bs);
uint8_t *head_buf = NULL;
uint8_t *tail_buf = NULL;
QEMUIOVector local_qiov;
if (bs->read_only) {
return -EACCES;
}
- if (bdrv_check_byte_request(bs, offset, bytes)) {
- return -EIO;
+
+ ret = bdrv_check_byte_request(bs, offset, bytes);
+ if (ret < 0) {
+ return ret;
}
/* throttling disk I/O */
bytes = ROUND_UP(bytes, align);
}
+ if (use_local_qiov) {
+ /* Local buffer may have non-zero data. */
+ flags &= ~BDRV_REQ_ZERO_WRITE;
+ }
ret = bdrv_aligned_pwritev(bs, &req, offset, bytes,
use_local_qiov ? &local_qiov : qiov,
flags);
int64_t sector_num, int nb_sectors, QEMUIOVector *qiov,
BdrvRequestFlags flags)
{
- if (nb_sectors < 0 || nb_sectors > (INT_MAX >> BDRV_SECTOR_BITS)) {
+ if (nb_sectors < 0 || nb_sectors > BDRV_REQUEST_MAX_SECTORS) {
return -EINVAL;
}
int64_t sector_num, int nb_sectors,
BdrvRequestFlags flags)
{
+ int ret;
+
trace_bdrv_co_write_zeroes(bs, sector_num, nb_sectors, flags);
if (!(bs->open_flags & BDRV_O_UNMAP)) {
flags &= ~BDRV_REQ_MAY_UNMAP;
}
+ if (bdrv_req_is_aligned(bs, sector_num << BDRV_SECTOR_BITS,
+ nb_sectors << BDRV_SECTOR_BITS)) {
+ ret = bdrv_co_do_writev(bs, sector_num, nb_sectors, NULL,
+ BDRV_REQ_ZERO_WRITE | flags);
+ } else {
+ uint8_t *buf;
+ QEMUIOVector local_qiov;
+ size_t bytes = nb_sectors << BDRV_SECTOR_BITS;
+
+ buf = qemu_memalign(bdrv_opt_mem_align(bs), bytes);
+ memset(buf, 0, bytes);
+ qemu_iovec_init(&local_qiov, 1);
+ qemu_iovec_add(&local_qiov, buf, bytes);
- return bdrv_co_do_writev(bs, sector_num, nb_sectors, NULL,
- BDRV_REQ_ZERO_WRITE | flags);
+ ret = bdrv_co_do_writev(bs, sector_num, nb_sectors, &local_qiov,
+ BDRV_REQ_ZERO_WRITE | flags);
+ qemu_vfree(buf);
+ }
+ return ret;
}
/**
ret = drv->bdrv_truncate(bs, offset);
if (ret == 0) {
ret = refresh_total_sectors(bs, offset >> BDRV_SECTOR_BITS);
+ bdrv_dirty_bitmap_truncate(bs);
if (bs->blk) {
blk_dev_resize_cb(bs->blk);
}
return ret;
}
+/*
+ * Provide an encryption key for @bs.
+ * If @key is non-null:
+ * If @bs is not encrypted, fail.
+ * Else if the key is invalid, fail.
+ * Else set @bs's key to @key, replacing the existing key, if any.
+ * If @key is null:
+ * If @bs is encrypted and still lacks a key, fail.
+ * Else do nothing.
+ * On failure, store an error object through @errp if non-null.
+ */
+void bdrv_add_key(BlockDriverState *bs, const char *key, Error **errp)
+{
+ if (key) {
+ if (!bdrv_is_encrypted(bs)) {
+ error_setg(errp, "Node '%s' is not encrypted",
+ bdrv_get_device_or_node_name(bs));
+ } else if (bdrv_set_key(bs, key) < 0) {
+ error_set(errp, QERR_INVALID_PASSWORD);
+ }
+ } else {
+ if (bdrv_key_required(bs)) {
+ error_set(errp, ERROR_CLASS_DEVICE_ENCRYPTED,
+ "'%s' (%s) is encrypted",
+ bdrv_get_device_or_node_name(bs),
+ bdrv_get_encrypted_filename(bs));
+ }
+ }
+}
+
const char *bdrv_get_format_name(BlockDriverState *bs)
{
return bs->drv ? bs->drv->format_name : NULL;
g_free(formats);
}
-/* This function is to find block backend bs */
-/* TODO convert callers to blk_by_name(), then remove */
-BlockDriverState *bdrv_find(const char *name)
-{
- BlockBackend *blk = blk_by_name(name);
-
- return blk ? blk_bs(blk) : NULL;
-}
-
/* This function is to find a node in the bs graph */
BlockDriverState *bdrv_find_node(const char *node_name)
{
}
/* Put this QMP function here so it can access the static graph_bdrv_states. */
-BlockDeviceInfoList *bdrv_named_nodes_list(void)
+BlockDeviceInfoList *bdrv_named_nodes_list(Error **errp)
{
BlockDeviceInfoList *list, *entry;
BlockDriverState *bs;
list = NULL;
QTAILQ_FOREACH(bs, &graph_bdrv_states, node_list) {
+ BlockDeviceInfo *info = bdrv_block_device_info(bs, errp);
+ if (!info) {
+ qapi_free_BlockDeviceInfoList(list);
+ return NULL;
+ }
entry = g_malloc0(sizeof(*entry));
- entry->value = bdrv_block_device_info(bs);
+ entry->value = info;
entry->next = list;
list = entry;
}
return bs->blk ? blk_name(bs->blk) : "";
}
+/* This can be used to identify nodes that might not have a device
+ * name associated. Since node and device names live in the same
+ * namespace, the result is unambiguous. The exception is if both are
+ * absent, then this returns an empty (non-null) string. */
+const char *bdrv_get_device_or_node_name(const BlockDriverState *bs)
+{
+ return bs->blk ? blk_name(bs->blk) : bs->node_name;
+}
+
int bdrv_get_flags(BlockDriverState *bs)
{
return bs->open_flags;
const uint8_t *buf, int nb_sectors)
{
BlockDriver *drv = bs->drv;
- if (!drv)
+ int ret;
+
+ if (!drv) {
return -ENOMEDIUM;
- if (!drv->bdrv_write_compressed)
+ }
+ if (!drv->bdrv_write_compressed) {
return -ENOTSUP;
- if (bdrv_check_request(bs, sector_num, nb_sectors))
- return -EIO;
+ }
+ ret = bdrv_check_request(bs, sector_num, nb_sectors);
+ if (ret < 0) {
+ return ret;
+ }
assert(QLIST_EMPTY(&bs->dirty_bitmaps));
}
}
+ block_acct_merge_done(&bs->stats, BLOCK_ACCT_WRITE, num_reqs - outidx - 1);
+
return outidx + 1;
}
BlockAIOCB common;
BlockRequest req;
bool is_write;
+ bool need_bh;
bool *done;
QEMUBH* bh;
} BlockAIOCBCoroutine;
.aiocb_size = sizeof(BlockAIOCBCoroutine),
};
+static void bdrv_co_complete(BlockAIOCBCoroutine *acb)
+{
+ if (!acb->need_bh) {
+ acb->common.cb(acb->common.opaque, acb->req.error);
+ qemu_aio_unref(acb);
+ }
+}
+
static void bdrv_co_em_bh(void *opaque)
{
BlockAIOCBCoroutine *acb = opaque;
- acb->common.cb(acb->common.opaque, acb->req.error);
-
+ assert(!acb->need_bh);
qemu_bh_delete(acb->bh);
- qemu_aio_unref(acb);
+ bdrv_co_complete(acb);
+}
+
+static void bdrv_co_maybe_schedule_bh(BlockAIOCBCoroutine *acb)
+{
+ acb->need_bh = false;
+ if (acb->req.error != -EINPROGRESS) {
+ BlockDriverState *bs = acb->common.bs;
+
+ acb->bh = aio_bh_new(bdrv_get_aio_context(bs), bdrv_co_em_bh, acb);
+ qemu_bh_schedule(acb->bh);
+ }
}
/* Invoke bdrv_co_do_readv/bdrv_co_do_writev */
acb->req.nb_sectors, acb->req.qiov, acb->req.flags);
}
- acb->bh = aio_bh_new(bdrv_get_aio_context(bs), bdrv_co_em_bh, acb);
- qemu_bh_schedule(acb->bh);
+ bdrv_co_complete(acb);
}
static BlockAIOCB *bdrv_co_aio_rw_vector(BlockDriverState *bs,
BlockAIOCBCoroutine *acb;
acb = qemu_aio_get(&bdrv_em_co_aiocb_info, bs, cb, opaque);
+ acb->need_bh = true;
+ acb->req.error = -EINPROGRESS;
acb->req.sector = sector_num;
acb->req.nb_sectors = nb_sectors;
acb->req.qiov = qiov;
co = qemu_coroutine_create(bdrv_co_do_rw);
qemu_coroutine_enter(co, acb);
+ bdrv_co_maybe_schedule_bh(acb);
return &acb->common;
}
BlockDriverState *bs = acb->common.bs;
acb->req.error = bdrv_co_flush(bs);
- acb->bh = aio_bh_new(bdrv_get_aio_context(bs), bdrv_co_em_bh, acb);
- qemu_bh_schedule(acb->bh);
+ bdrv_co_complete(acb);
}
BlockAIOCB *bdrv_aio_flush(BlockDriverState *bs,
BlockAIOCBCoroutine *acb;
acb = qemu_aio_get(&bdrv_em_co_aiocb_info, bs, cb, opaque);
+ acb->need_bh = true;
+ acb->req.error = -EINPROGRESS;
co = qemu_coroutine_create(bdrv_aio_flush_co_entry);
qemu_coroutine_enter(co, acb);
+ bdrv_co_maybe_schedule_bh(acb);
return &acb->common;
}
BlockDriverState *bs = acb->common.bs;
acb->req.error = bdrv_co_discard(bs, acb->req.sector, acb->req.nb_sectors);
- acb->bh = aio_bh_new(bdrv_get_aio_context(bs), bdrv_co_em_bh, acb);
- qemu_bh_schedule(acb->bh);
+ bdrv_co_complete(acb);
}
BlockAIOCB *bdrv_aio_discard(BlockDriverState *bs,
trace_bdrv_aio_discard(bs, sector_num, nb_sectors, opaque);
acb = qemu_aio_get(&bdrv_em_co_aiocb_info, bs, cb, opaque);
+ acb->need_bh = true;
+ acb->req.error = -EINPROGRESS;
acb->req.sector = sector_num;
acb->req.nb_sectors = nb_sectors;
co = qemu_coroutine_create(bdrv_aio_discard_co_entry);
qemu_coroutine_enter(co, acb);
+ bdrv_co_maybe_schedule_bh(acb);
return &acb->common;
}
rwco->ret = bdrv_co_discard(rwco->bs, rwco->sector_num, rwco->nb_sectors);
}
-/* if no limit is specified in the BlockLimits use a default
- * of 32768 512-byte sectors (16 MiB) per request.
- */
-#define MAX_DISCARD_DEFAULT 32768
-
int coroutine_fn bdrv_co_discard(BlockDriverState *bs, int64_t sector_num,
int nb_sectors)
{
- int max_discard;
+ int max_discard, ret;
if (!bs->drv) {
return -ENOMEDIUM;
- } else if (bdrv_check_request(bs, sector_num, nb_sectors)) {
- return -EIO;
+ }
+
+ ret = bdrv_check_request(bs, sector_num, nb_sectors);
+ if (ret < 0) {
+ return ret;
} else if (bs->read_only) {
return -EROFS;
}
return 0;
}
- max_discard = bs->bl.max_discard ? bs->bl.max_discard : MAX_DISCARD_DEFAULT;
+ max_discard = MIN_NON_ZERO(bs->bl.max_discard, BDRV_REQUEST_MAX_SECTORS);
while (nb_sectors > 0) {
int ret;
int num = nb_sectors;
return true;
}
-BdrvDirtyBitmap *bdrv_create_dirty_bitmap(BlockDriverState *bs, int granularity,
+BdrvDirtyBitmap *bdrv_find_dirty_bitmap(BlockDriverState *bs, const char *name)
+{
+ BdrvDirtyBitmap *bm;
+
+ assert(name);
+ QLIST_FOREACH(bm, &bs->dirty_bitmaps, list) {
+ if (bm->name && !strcmp(name, bm->name)) {
+ return bm;
+ }
+ }
+ return NULL;
+}
+
+void bdrv_dirty_bitmap_make_anon(BdrvDirtyBitmap *bitmap)
+{
+ assert(!bdrv_dirty_bitmap_frozen(bitmap));
+ g_free(bitmap->name);
+ bitmap->name = NULL;
+}
+
+BdrvDirtyBitmap *bdrv_create_dirty_bitmap(BlockDriverState *bs,
+ uint32_t granularity,
+ const char *name,
Error **errp)
{
int64_t bitmap_size;
BdrvDirtyBitmap *bitmap;
+ uint32_t sector_granularity;
assert((granularity & (granularity - 1)) == 0);
- granularity >>= BDRV_SECTOR_BITS;
- assert(granularity);
+ if (name && bdrv_find_dirty_bitmap(bs, name)) {
+ error_setg(errp, "Bitmap already exists: %s", name);
+ return NULL;
+ }
+ sector_granularity = granularity >> BDRV_SECTOR_BITS;
+ assert(sector_granularity);
bitmap_size = bdrv_nb_sectors(bs);
if (bitmap_size < 0) {
error_setg_errno(errp, -bitmap_size, "could not get length of device");
return NULL;
}
bitmap = g_new0(BdrvDirtyBitmap, 1);
- bitmap->bitmap = hbitmap_alloc(bitmap_size, ffs(granularity) - 1);
+ bitmap->bitmap = hbitmap_alloc(bitmap_size, ctz32(sector_granularity));
+ bitmap->size = bitmap_size;
+ bitmap->name = g_strdup(name);
+ bitmap->disabled = false;
QLIST_INSERT_HEAD(&bs->dirty_bitmaps, bitmap, list);
return bitmap;
}
+bool bdrv_dirty_bitmap_frozen(BdrvDirtyBitmap *bitmap)
+{
+ return bitmap->successor;
+}
+
+bool bdrv_dirty_bitmap_enabled(BdrvDirtyBitmap *bitmap)
+{
+ return !(bitmap->disabled || bitmap->successor);
+}
+
+/**
+ * Create a successor bitmap destined to replace this bitmap after an operation.
+ * Requires that the bitmap is not frozen and has no successor.
+ */
+int bdrv_dirty_bitmap_create_successor(BlockDriverState *bs,
+ BdrvDirtyBitmap *bitmap, Error **errp)
+{
+ uint64_t granularity;
+ BdrvDirtyBitmap *child;
+
+ if (bdrv_dirty_bitmap_frozen(bitmap)) {
+ error_setg(errp, "Cannot create a successor for a bitmap that is "
+ "currently frozen");
+ return -1;
+ }
+ assert(!bitmap->successor);
+
+ /* Create an anonymous successor */
+ granularity = bdrv_dirty_bitmap_granularity(bitmap);
+ child = bdrv_create_dirty_bitmap(bs, granularity, NULL, errp);
+ if (!child) {
+ return -1;
+ }
+
+ /* Successor will be on or off based on our current state. */
+ child->disabled = bitmap->disabled;
+
+ /* Install the successor and freeze the parent */
+ bitmap->successor = child;
+ return 0;
+}
+
+/**
+ * For a bitmap with a successor, yield our name to the successor,
+ * delete the old bitmap, and return a handle to the new bitmap.
+ */
+BdrvDirtyBitmap *bdrv_dirty_bitmap_abdicate(BlockDriverState *bs,
+ BdrvDirtyBitmap *bitmap,
+ Error **errp)
+{
+ char *name;
+ BdrvDirtyBitmap *successor = bitmap->successor;
+
+ if (successor == NULL) {
+ error_setg(errp, "Cannot relinquish control if "
+ "there's no successor present");
+ return NULL;
+ }
+
+ name = bitmap->name;
+ bitmap->name = NULL;
+ successor->name = name;
+ bitmap->successor = NULL;
+ bdrv_release_dirty_bitmap(bs, bitmap);
+
+ return successor;
+}
+
+/**
+ * In cases of failure where we can no longer safely delete the parent,
+ * we may wish to re-join the parent and child/successor.
+ * The merged parent will be un-frozen, but not explicitly re-enabled.
+ */
+BdrvDirtyBitmap *bdrv_reclaim_dirty_bitmap(BlockDriverState *bs,
+ BdrvDirtyBitmap *parent,
+ Error **errp)
+{
+ BdrvDirtyBitmap *successor = parent->successor;
+
+ if (!successor) {
+ error_setg(errp, "Cannot reclaim a successor when none is present");
+ return NULL;
+ }
+
+ if (!hbitmap_merge(parent->bitmap, successor->bitmap)) {
+ error_setg(errp, "Merging of parent and successor bitmap failed");
+ return NULL;
+ }
+ bdrv_release_dirty_bitmap(bs, successor);
+ parent->successor = NULL;
+
+ return parent;
+}
+
+/**
+ * Truncates _all_ bitmaps attached to a BDS.
+ */
+static void bdrv_dirty_bitmap_truncate(BlockDriverState *bs)
+{
+ BdrvDirtyBitmap *bitmap;
+ uint64_t size = bdrv_nb_sectors(bs);
+
+ QLIST_FOREACH(bitmap, &bs->dirty_bitmaps, list) {
+ if (bdrv_dirty_bitmap_frozen(bitmap)) {
+ continue;
+ }
+ hbitmap_truncate(bitmap->bitmap, size);
+ }
+}
+
void bdrv_release_dirty_bitmap(BlockDriverState *bs, BdrvDirtyBitmap *bitmap)
{
BdrvDirtyBitmap *bm, *next;
QLIST_FOREACH_SAFE(bm, &bs->dirty_bitmaps, list, next) {
if (bm == bitmap) {
+ assert(!bdrv_dirty_bitmap_frozen(bm));
QLIST_REMOVE(bitmap, list);
hbitmap_free(bitmap->bitmap);
+ g_free(bitmap->name);
g_free(bitmap);
return;
}
}
}
+void bdrv_disable_dirty_bitmap(BdrvDirtyBitmap *bitmap)
+{
+ assert(!bdrv_dirty_bitmap_frozen(bitmap));
+ bitmap->disabled = true;
+}
+
+void bdrv_enable_dirty_bitmap(BdrvDirtyBitmap *bitmap)
+{
+ assert(!bdrv_dirty_bitmap_frozen(bitmap));
+ bitmap->disabled = false;
+}
+
BlockDirtyInfoList *bdrv_query_dirty_bitmaps(BlockDriverState *bs)
{
BdrvDirtyBitmap *bm;
QLIST_FOREACH(bm, &bs->dirty_bitmaps, list) {
BlockDirtyInfo *info = g_new0(BlockDirtyInfo, 1);
BlockDirtyInfoList *entry = g_new0(BlockDirtyInfoList, 1);
- info->count = bdrv_get_dirty_count(bs, bm);
- info->granularity =
- ((int64_t) BDRV_SECTOR_SIZE << hbitmap_granularity(bm->bitmap));
+ info->count = bdrv_get_dirty_count(bm);
+ info->granularity = bdrv_dirty_bitmap_granularity(bm);
+ info->has_name = !!bm->name;
+ info->name = g_strdup(bm->name);
+ info->frozen = bdrv_dirty_bitmap_frozen(bm);
entry->value = info;
*plist = entry;
plist = &entry->next;
}
}
-void bdrv_dirty_iter_init(BlockDriverState *bs,
- BdrvDirtyBitmap *bitmap, HBitmapIter *hbi)
+/**
+ * Chooses a default granularity based on the existing cluster size,
+ * but clamped between [4K, 64K]. Defaults to 64K in the case that there
+ * is no cluster size information available.
+ */
+uint32_t bdrv_get_default_bitmap_granularity(BlockDriverState *bs)
+{
+ BlockDriverInfo bdi;
+ uint32_t granularity;
+
+ if (bdrv_get_info(bs, &bdi) >= 0 && bdi.cluster_size > 0) {
+ granularity = MAX(4096, bdi.cluster_size);
+ granularity = MIN(65536, granularity);
+ } else {
+ granularity = 65536;
+ }
+
+ return granularity;
+}
+
+uint32_t bdrv_dirty_bitmap_granularity(BdrvDirtyBitmap *bitmap)
+{
+ return BDRV_SECTOR_SIZE << hbitmap_granularity(bitmap->bitmap);
+}
+
+void bdrv_dirty_iter_init(BdrvDirtyBitmap *bitmap, HBitmapIter *hbi)
{
hbitmap_iter_init(hbi, bitmap->bitmap, 0);
}
-void bdrv_set_dirty(BlockDriverState *bs, int64_t cur_sector,
- int nr_sectors)
+void bdrv_set_dirty_bitmap(BdrvDirtyBitmap *bitmap,
+ int64_t cur_sector, int nr_sectors)
+{
+ assert(bdrv_dirty_bitmap_enabled(bitmap));
+ hbitmap_set(bitmap->bitmap, cur_sector, nr_sectors);
+}
+
+void bdrv_reset_dirty_bitmap(BdrvDirtyBitmap *bitmap,
+ int64_t cur_sector, int nr_sectors)
+{
+ assert(bdrv_dirty_bitmap_enabled(bitmap));
+ hbitmap_reset(bitmap->bitmap, cur_sector, nr_sectors);
+}
+
+void bdrv_clear_dirty_bitmap(BdrvDirtyBitmap *bitmap)
+{
+ assert(bdrv_dirty_bitmap_enabled(bitmap));
+ hbitmap_reset(bitmap->bitmap, 0, bitmap->size);
+}
+
+static void bdrv_set_dirty(BlockDriverState *bs, int64_t cur_sector,
+ int nr_sectors)
{
BdrvDirtyBitmap *bitmap;
QLIST_FOREACH(bitmap, &bs->dirty_bitmaps, list) {
+ if (!bdrv_dirty_bitmap_enabled(bitmap)) {
+ continue;
+ }
hbitmap_set(bitmap->bitmap, cur_sector, nr_sectors);
}
}
-void bdrv_reset_dirty(BlockDriverState *bs, int64_t cur_sector, int nr_sectors)
+static void bdrv_reset_dirty(BlockDriverState *bs, int64_t cur_sector,
+ int nr_sectors)
{
BdrvDirtyBitmap *bitmap;
QLIST_FOREACH(bitmap, &bs->dirty_bitmaps, list) {
+ if (!bdrv_dirty_bitmap_enabled(bitmap)) {
+ continue;
+ }
hbitmap_reset(bitmap->bitmap, cur_sector, nr_sectors);
}
}
-int64_t bdrv_get_dirty_count(BlockDriverState *bs, BdrvDirtyBitmap *bitmap)
+/**
+ * Advance an HBitmapIter to an arbitrary offset.
+ */
+void bdrv_set_dirty_iter(HBitmapIter *hbi, int64_t offset)
+{
+ assert(hbi->hb);
+ hbitmap_iter_init(hbi, hbi->hb, offset);
+}
+
+int64_t bdrv_get_dirty_count(BdrvDirtyBitmap *bitmap)
{
return hbitmap_count(bitmap->bitmap);
}
if (!QLIST_EMPTY(&bs->op_blockers[op])) {
blocker = QLIST_FIRST(&bs->op_blockers[op]);
if (errp) {
- error_setg(errp, "Device '%s' is busy: %s",
- bdrv_get_device_name(bs),
+ error_setg(errp, "Node '%s' is busy: %s",
+ bdrv_get_device_or_node_name(bs),
error_get_pretty(blocker->reason));
}
return true;
return;
}
- proto_drv = bdrv_find_protocol(filename, true);
+ proto_drv = bdrv_find_protocol(filename, true, errp);
if (!proto_drv) {
- error_setg(errp, "Unknown protocol '%s'", filename);
return;
}
/* Create parameter list with default values */
opts = qemu_opts_create(create_opts, NULL, 0, &error_abort);
- qemu_opt_set_number(opts, BLOCK_OPT_SIZE, img_size);
+ qemu_opt_set_number(opts, BLOCK_OPT_SIZE, img_size, &error_abort);
/* Parse -o options */
if (options) {
- if (qemu_opts_do_parse(opts, options, NULL) != 0) {
+ qemu_opts_do_parse(opts, options, NULL, &local_err);
+ if (local_err) {
+ error_report_err(local_err);
+ local_err = NULL;
error_setg(errp, "Invalid options for file format '%s'", fmt);
goto out;
}
}
if (base_filename) {
- if (qemu_opt_set(opts, BLOCK_OPT_BACKING_FILE, base_filename)) {
+ qemu_opt_set(opts, BLOCK_OPT_BACKING_FILE, base_filename, &local_err);
+ if (local_err) {
error_setg(errp, "Backing file not supported for file format '%s'",
fmt);
goto out;
}
if (base_fmt) {
- if (qemu_opt_set(opts, BLOCK_OPT_BACKING_FMT, base_fmt)) {
+ qemu_opt_set(opts, BLOCK_OPT_BACKING_FMT, base_fmt, &local_err);
+ if (local_err) {
error_setg(errp, "Backing file format not supported for file "
"format '%s'", fmt);
goto out;
if (size == -1) {
if (backing_file) {
BlockDriverState *bs;
+ char *full_backing = g_new0(char, PATH_MAX);
int64_t size;
int back_flags;
+ bdrv_get_full_backing_filename_from_filename(filename, backing_file,
+ full_backing, PATH_MAX,
+ &local_err);
+ if (local_err) {
+ g_free(full_backing);
+ goto out;
+ }
+
/* backing files always opened read-only */
back_flags =
flags & ~(BDRV_O_RDWR | BDRV_O_SNAPSHOT | BDRV_O_NO_BACKING);
bs = NULL;
- ret = bdrv_open(&bs, backing_file, NULL, NULL, back_flags,
+ ret = bdrv_open(&bs, full_backing, NULL, NULL, back_flags,
backing_drv, &local_err);
+ g_free(full_backing);
if (ret < 0) {
goto out;
}
goto out;
}
- qemu_opt_set_number(opts, BLOCK_OPT_SIZE, size);
+ qemu_opt_set_number(opts, BLOCK_OPT_SIZE, size, &error_abort);
bdrv_unref(bs);
} else {
projects / qemu.git / blobdiff