#include "block/blockjob.h"
#include "qemu/module.h"
#include "qapi/qmp/qjson.h"
+#include "sysemu/block-backend.h"
#include "sysemu/sysemu.h"
-#include "sysemu/blockdev.h" /* FIXME layering violation */
#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;
};
#define NOT_DONE 0x7fffffff /* used while emulated sync operation in progress */
-#define COROUTINE_POOL_RESERVATION 64 /* number of coroutines to reserve */
-
-static void bdrv_dev_change_media_cb(BlockDriverState *bs, bool load);
-static BlockDriverAIOCB *bdrv_aio_readv_em(BlockDriverState *bs,
- int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
- BlockDriverCompletionFunc *cb, void *opaque);
-static BlockDriverAIOCB *bdrv_aio_writev_em(BlockDriverState *bs,
- int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
- BlockDriverCompletionFunc *cb, void *opaque);
-static int coroutine_fn bdrv_co_readv_em(BlockDriverState *bs,
- int64_t sector_num, int nb_sectors,
- QEMUIOVector *iov);
-static int coroutine_fn bdrv_co_writev_em(BlockDriverState *bs,
- int64_t sector_num, int nb_sectors,
- QEMUIOVector *iov);
-static int coroutine_fn bdrv_co_do_preadv(BlockDriverState *bs,
- int64_t offset, unsigned int bytes, QEMUIOVector *qiov,
- BdrvRequestFlags flags);
-static int coroutine_fn bdrv_co_do_pwritev(BlockDriverState *bs,
- int64_t offset, unsigned int bytes, QEMUIOVector *qiov,
- BdrvRequestFlags flags);
-static BlockDriverAIOCB *bdrv_co_aio_rw_vector(BlockDriverState *bs,
- int64_t sector_num,
- QEMUIOVector *qiov,
- int nb_sectors,
- BdrvRequestFlags flags,
- BlockDriverCompletionFunc *cb,
- void *opaque,
- bool is_write);
-static void coroutine_fn bdrv_co_do_rw(void *opaque);
-static int coroutine_fn bdrv_co_do_write_zeroes(BlockDriverState *bs,
- int64_t sector_num, int nb_sectors, BdrvRequestFlags flags);
-
static QTAILQ_HEAD(, BlockDriverState) bdrv_states =
QTAILQ_HEAD_INITIALIZER(bdrv_states);
static QLIST_HEAD(, BlockDriver) bdrv_drivers =
QLIST_HEAD_INITIALIZER(bdrv_drivers);
+static void bdrv_dirty_bitmap_truncate(BlockDriverState *bs);
/* If non-zero, use only whitelisted block drivers */
static int use_bdrv_whitelist;
}
#endif
-/* throttling disk I/O limits */
-void bdrv_set_io_limits(BlockDriverState *bs,
- ThrottleConfig *cfg)
-{
- int i;
-
- throttle_config(&bs->throttle_state, cfg);
-
- for (i = 0; i < 2; i++) {
- qemu_co_enter_next(&bs->throttled_reqs[i]);
- }
-}
-
-/* this function drain all the throttled IOs */
-static bool bdrv_start_throttled_reqs(BlockDriverState *bs)
-{
- bool drained = false;
- bool enabled = bs->io_limits_enabled;
- int i;
-
- bs->io_limits_enabled = false;
-
- for (i = 0; i < 2; i++) {
- while (qemu_co_enter_next(&bs->throttled_reqs[i])) {
- drained = true;
- }
- }
-
- bs->io_limits_enabled = enabled;
-
- return drained;
-}
-
-void bdrv_io_limits_disable(BlockDriverState *bs)
-{
- bs->io_limits_enabled = false;
-
- bdrv_start_throttled_reqs(bs);
-
- throttle_destroy(&bs->throttle_state);
-}
-
-static void bdrv_throttle_read_timer_cb(void *opaque)
-{
- BlockDriverState *bs = opaque;
- qemu_co_enter_next(&bs->throttled_reqs[0]);
-}
-
-static void bdrv_throttle_write_timer_cb(void *opaque)
-{
- BlockDriverState *bs = opaque;
- qemu_co_enter_next(&bs->throttled_reqs[1]);
-}
-
-/* should be called before bdrv_set_io_limits if a limit is set */
-void bdrv_io_limits_enable(BlockDriverState *bs)
-{
- assert(!bs->io_limits_enabled);
- throttle_init(&bs->throttle_state,
- bdrv_get_aio_context(bs),
- QEMU_CLOCK_VIRTUAL,
- bdrv_throttle_read_timer_cb,
- bdrv_throttle_write_timer_cb,
- bs);
- bs->io_limits_enabled = true;
-}
-
-/* This function makes an IO wait if needed
- *
- * @nb_sectors: the number of sectors of the IO
- * @is_write: is the IO a write
- */
-static void bdrv_io_limits_intercept(BlockDriverState *bs,
- unsigned int bytes,
- bool is_write)
-{
- /* does this io must wait */
- bool must_wait = throttle_schedule_timer(&bs->throttle_state, is_write);
-
- /* if must wait or any request of this type throttled queue the IO */
- if (must_wait ||
- !qemu_co_queue_empty(&bs->throttled_reqs[is_write])) {
- qemu_co_queue_wait(&bs->throttled_reqs[is_write]);
- }
-
- /* the IO will be executed, do the accounting */
- throttle_account(&bs->throttle_state, is_write, bytes);
-
-
- /* if the next request must wait -> do nothing */
- if (throttle_schedule_timer(&bs->throttle_state, is_write)) {
- return;
- }
-
- /* else queue next request for execution */
- qemu_co_queue_next(&bs->throttled_reqs[is_write]);
-}
-
size_t bdrv_opt_mem_align(BlockDriverState *bs)
{
if (!bs || !bs->drv) {
}
/* check if the path starts with "<protocol>:" */
-static int path_has_protocol(const char *path)
+int path_has_protocol(const char *path)
{
const char *p;
}
}
-void bdrv_get_full_backing_filename(BlockDriverState *bs, char *dest, size_t sz)
+void bdrv_get_full_backing_filename_from_filename(const char *backed,
+ const char *backing,
+ char *dest, size_t sz,
+ Error **errp)
{
- if (bs->backing_file[0] == '\0' || path_has_protocol(bs->backing_file)) {
- pstrcpy(dest, sz, bs->backing_file);
+ 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, bs->filename, bs->backing_file);
+ path_combine(dest, sz, backed, backing);
}
}
-void bdrv_register(BlockDriver *bdrv)
+void bdrv_get_full_backing_filename(BlockDriverState *bs, char *dest, size_t sz,
+ Error **errp)
{
- /* Block drivers without coroutine functions need emulation */
- if (!bdrv->bdrv_co_readv) {
- bdrv->bdrv_co_readv = bdrv_co_readv_em;
- bdrv->bdrv_co_writev = bdrv_co_writev_em;
+ char *backed = bs->exact_filename[0] ? bs->exact_filename : bs->filename;
- /* bdrv_co_readv_em()/brdv_co_writev_em() work in terms of aio, so if
- * the block driver lacks aio we need to emulate that too.
- */
- if (!bdrv->bdrv_aio_readv) {
- /* add AIO emulation layer */
- bdrv->bdrv_aio_readv = bdrv_aio_readv_em;
- bdrv->bdrv_aio_writev = bdrv_aio_writev_em;
- }
- }
+ bdrv_get_full_backing_filename_from_filename(backed, bs->backing_file,
+ dest, sz, errp);
+}
+
+void bdrv_register(BlockDriver *bdrv)
+{
+ bdrv_setup_io_funcs(bdrv);
QLIST_INSERT_HEAD(&bdrv_drivers, bdrv, list);
}
-static bool bdrv_is_valid_name(const char *name)
+BlockDriverState *bdrv_new_root(void)
{
- return qemu_opts_id_wellformed(name);
+ BlockDriverState *bs = bdrv_new();
+
+ QTAILQ_INSERT_TAIL(&bdrv_states, bs, device_list);
+ return bs;
}
-/* create a new block device (by default it is empty) */
-BlockDriverState *bdrv_new(const char *device_name, Error **errp)
+BlockDriverState *bdrv_new(void)
{
BlockDriverState *bs;
int i;
- if (*device_name && !bdrv_is_valid_name(device_name)) {
- error_setg(errp, "Invalid device name");
- return NULL;
- }
-
- if (bdrv_find(device_name)) {
- error_setg(errp, "Device with id '%s' already exists",
- device_name);
- return NULL;
- }
- if (bdrv_find_node(device_name)) {
- error_setg(errp,
- "Device name '%s' conflicts with an existing node name",
- device_name);
- return NULL;
- }
-
bs = g_new0(BlockDriverState, 1);
QLIST_INIT(&bs->dirty_bitmaps);
- pstrcpy(bs->device_name, sizeof(bs->device_name), device_name);
- if (device_name[0] != '\0') {
- QTAILQ_INSERT_TAIL(&bdrv_states, bs, device_list);
- }
for (i = 0; i < BLOCK_OP_TYPE_MAX; i++) {
QLIST_INIT(&bs->op_blockers[i]);
}
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;
}
return ret;
}
-void bdrv_refresh_limits(BlockDriverState *bs, Error **errp)
+/**
+ * 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;
- Error *local_err = NULL;
- memset(&bs->bl, 0, sizeof(bs->bl));
-
- if (!drv) {
- return;
+ if (drv && drv->bdrv_probe_blocksizes) {
+ return drv->bdrv_probe_blocksizes(bs, bsz);
}
- /* Take some limits from the children as a default */
- if (bs->file) {
- bdrv_refresh_limits(bs->file, &local_err);
- if (local_err) {
- error_propagate(errp, local_err);
- return;
- }
- bs->bl.opt_transfer_length = bs->file->bl.opt_transfer_length;
- bs->bl.opt_mem_alignment = bs->file->bl.opt_mem_alignment;
- } else {
- bs->bl.opt_mem_alignment = 512;
- }
+ return -ENOTSUP;
+}
- if (bs->backing_hd) {
- bdrv_refresh_limits(bs->backing_hd, &local_err);
- if (local_err) {
- error_propagate(errp, local_err);
- return;
- }
- bs->bl.opt_transfer_length =
- MAX(bs->bl.opt_transfer_length,
- bs->backing_hd->bl.opt_transfer_length);
- bs->bl.opt_mem_alignment =
- MAX(bs->bl.opt_mem_alignment,
- bs->backing_hd->bl.opt_mem_alignment);
- }
+/**
+ * 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;
- /* Then let the driver override it */
- if (drv->bdrv_refresh_limits) {
- drv->bdrv_refresh_limits(bs, errp);
+ if (drv && drv->bdrv_probe_geometry) {
+ return drv->bdrv_probe_geometry(bs, geo);
}
+
+ return -ENOTSUP;
}
/*
}
BlockDriver *bdrv_find_protocol(const char *filename,
- bool allow_protocol_prefix)
+ bool allow_protocol_prefix,
+ Error **errp)
{
BlockDriver *drv1;
char protocol[128];
}
if (!path_has_protocol(filename) || !allow_protocol_prefix) {
- return bdrv_find_format("file");
+ return &bdrv_file;
}
p = strchr(filename, ':');
return drv1;
}
}
+
+ error_setg(errp, "Unknown protocol '%s'", protocol);
return NULL;
}
+/*
+ * Guess image format by probing its contents.
+ * This is not a good idea when your image is raw (CVE-2008-2004), but
+ * we do it anyway for backward compatibility.
+ *
+ * @buf contains the image's first @buf_size bytes.
+ * @buf_size is the buffer size in bytes (generally BLOCK_PROBE_BUF_SIZE,
+ * but can be smaller if the image file is smaller)
+ * @filename is its filename.
+ *
+ * For all block drivers, call the bdrv_probe() method to get its
+ * probing score.
+ * Return the first block driver with the highest probing score.
+ */
+BlockDriver *bdrv_probe_all(const uint8_t *buf, int buf_size,
+ const char *filename)
+{
+ int score_max = 0, score;
+ BlockDriver *drv = NULL, *d;
+
+ QLIST_FOREACH(d, &bdrv_drivers, list) {
+ if (d->bdrv_probe) {
+ score = d->bdrv_probe(buf, buf_size, filename);
+ if (score > score_max) {
+ score_max = score;
+ drv = d;
+ }
+ }
+ }
+
+ return drv;
+}
+
static int find_image_format(BlockDriverState *bs, const char *filename,
BlockDriver **pdrv, Error **errp)
{
- int score, score_max;
- BlockDriver *drv1, *drv;
- uint8_t buf[2048];
+ BlockDriver *drv;
+ uint8_t buf[BLOCK_PROBE_BUF_SIZE];
int ret = 0;
/* Return the raw BlockDriver * to scsi-generic devices or empty drives */
if (bs->sg || !bdrv_is_inserted(bs) || bdrv_getlength(bs) == 0) {
- drv = bdrv_find_format("raw");
- if (!drv) {
- error_setg(errp, "Could not find raw image format");
- ret = -ENOENT;
- }
- *pdrv = drv;
+ *pdrv = &bdrv_raw;
return ret;
}
return ret;
}
- score_max = 0;
- drv = NULL;
- QLIST_FOREACH(drv1, &bdrv_drivers, list) {
- if (drv1->bdrv_probe) {
- score = drv1->bdrv_probe(buf, ret, filename);
- if (score > score_max) {
- score_max = score;
- drv = drv1;
- }
- }
- }
+ drv = bdrv_probe_all(buf, ret, filename);
if (!drv) {
error_setg(errp, "Could not determine image format: No compatible "
"driver found");
return 0;
}
-/**
- * The copy-on-read flag is actually a reference count so multiple users may
- * use the feature without worrying about clobbering its previous state.
- * Copy-on-read stays enabled until all users have called to disable it.
- */
-void bdrv_enable_copy_on_read(BlockDriverState *bs)
-{
- bs->copy_on_read++;
-}
-
-void bdrv_disable_copy_on_read(BlockDriverState *bs)
-{
- assert(bs->copy_on_read > 0);
- bs->copy_on_read--;
-}
-
/*
* Returns the flags that a temporary snapshot should get, based on the
* originally requested flags (the originally requested image will have flags
}
/* Check for empty string or invalid characters */
- if (!bdrv_is_valid_name(node_name)) {
+ if (!id_wellformed(node_name)) {
error_setg(errp, "Invalid node name");
return;
}
/* takes care of avoiding namespaces collisions */
- if (bdrv_find(node_name)) {
+ if (blk_by_name(node_name)) {
error_setg(errp, "node-name=%s is conflicting with a device id",
node_name);
return;
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'",
- bs->device_name);
+ "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);
{
char *backing_filename = g_malloc0(PATH_MAX);
int ret = 0;
- BlockDriver *back_drv = NULL;
BlockDriverState *backing_hd;
Error *local_err = 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) {
goto free_exit;
}
- backing_hd = bdrv_new("", errp);
+ backing_hd = bdrv_new();
- if (bs->backing_format[0] != '\0') {
- back_drv = bdrv_find_format(bs->backing_format);
+ if (bs->backing_format[0] != '\0' && !qdict_haskey(options, "driver")) {
+ qdict_put(options, "driver", qstring_from_str(bs->backing_format));
}
assert(bs->backing_hd == NULL);
ret = bdrv_open(&backing_hd,
*backing_filename ? backing_filename : NULL, NULL, options,
- bdrv_backing_flags(bs->open_flags), back_drv, &local_err);
+ bdrv_backing_flags(bs->open_flags), NULL, &local_err);
if (ret < 0) {
bdrv_unref(backing_hd);
backing_hd = NULL;
/* TODO: extra byte is a hack to ensure MAX_PATH space on Windows. */
char *tmp_filename = g_malloc0(PATH_MAX + 1);
int64_t total_size;
- BlockDriver *bdrv_qcow2;
QemuOpts *opts = NULL;
QDict *snapshot_options;
BlockDriverState *bs_snapshot;
goto out;
}
- bdrv_qcow2 = bdrv_find_format("qcow2");
- opts = qemu_opts_create(bdrv_qcow2->create_opts, NULL, 0,
+ opts = qemu_opts_create(bdrv_qcow2.create_opts, NULL, 0,
&error_abort);
- qemu_opt_set_number(opts, BLOCK_OPT_SIZE, total_size);
- ret = bdrv_create(bdrv_qcow2, tmp_filename, opts, &local_err);
+ 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) {
error_setg_errno(errp, -ret, "Could not create temporary overlay "
qdict_put(snapshot_options, "file.filename",
qstring_from_str(tmp_filename));
- bs_snapshot = bdrv_new("", &error_abort);
+ bs_snapshot = bdrv_new();
ret = bdrv_open(&bs_snapshot, NULL, NULL, snapshot_options,
- flags, bdrv_qcow2, &local_err);
+ flags, &bdrv_qcow2, &local_err);
if (ret < 0) {
error_propagate(errp, local_err);
goto out;
if (*pbs) {
bs = *pbs;
} else {
- bs = bdrv_new("", &error_abort);
+ bs = bdrv_new();
}
/* NULL means an empty set of options */
}
/* Image format probing */
+ bs->probed = !drv;
if (!drv && file) {
ret = find_image_format(file, filename, &drv, &local_err);
if (ret < 0) {
} else {
error_setg(errp, "Block format '%s' used by device '%s' doesn't "
"support the option '%s'", drv->format_name,
- bs->device_name, entry->key);
+ bdrv_get_device_name(bs), entry->key);
}
ret = -EINVAL;
}
if (!bdrv_key_required(bs)) {
- bdrv_dev_change_media_cb(bs, true);
+ if (bs->blk) {
+ blk_dev_change_media_cb(bs->blk, true);
+ }
} else if (!runstate_check(RUN_STATE_PRELAUNCH)
&& !runstate_check(RUN_STATE_INMIGRATE)
&& !runstate_check(RUN_STATE_PAUSED)) { /* HACK */
* 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,
- reopen_state->bs->device_name);
+ 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, reopen_state->bs->device_name,
- "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;
}
}
- bdrv_dev_change_media_cb(bs, false);
+ if (bs->blk) {
+ blk_dev_change_media_cb(bs->blk, false);
+ }
/*throttling disk I/O limits*/
if (bs->io_limits_enabled) {
}
}
-/* Check if any requests are in-flight (including throttled requests) */
-static bool bdrv_requests_pending(BlockDriverState *bs)
-{
- if (!QLIST_EMPTY(&bs->tracked_requests)) {
- return true;
- }
- if (!qemu_co_queue_empty(&bs->throttled_reqs[0])) {
- return true;
- }
- if (!qemu_co_queue_empty(&bs->throttled_reqs[1])) {
- return true;
- }
- if (bs->file && bdrv_requests_pending(bs->file)) {
- return true;
- }
- if (bs->backing_hd && bdrv_requests_pending(bs->backing_hd)) {
- return true;
- }
- return false;
-}
-
-/*
- * Wait for pending requests to complete across all BlockDriverStates
- *
- * This function does not flush data to disk, use bdrv_flush_all() for that
- * after calling this function.
- *
- * Note that completion of an asynchronous I/O operation can trigger any
- * number of other I/O operations on other devices---for example a coroutine
- * can be arbitrarily complex and a constant flow of I/O can come until the
- * coroutine is complete. Because of this, it is not possible to have a
- * function to drain a single device's I/O queue.
- */
-void bdrv_drain_all(void)
-{
- /* Always run first iteration so any pending completion BHs run */
- bool busy = true;
- BlockDriverState *bs;
-
- while (busy) {
- busy = false;
-
- QTAILQ_FOREACH(bs, &bdrv_states, device_list) {
- AioContext *aio_context = bdrv_get_aio_context(bs);
- bool bs_busy;
-
- aio_context_acquire(aio_context);
- bdrv_flush_io_queue(bs);
- bdrv_start_throttled_reqs(bs);
- bs_busy = bdrv_requests_pending(bs);
- bs_busy |= aio_poll(aio_context, bs_busy);
- aio_context_release(aio_context);
-
- busy |= bs_busy;
- }
- }
-}
-
/* make a BlockDriverState anonymous by removing from bdrv_state and
* graph_bdrv_state list.
Also, NULL terminate the device_name to prevent double remove */
void bdrv_make_anon(BlockDriverState *bs)
{
- if (bs->device_name[0] != '\0') {
+ /*
+ * Take care to remove bs from bdrv_states only when it's actually
+ * in it. Note that bs->device_list.tqe_prev is initially null,
+ * and gets set to non-null by QTAILQ_INSERT_TAIL(). Establish
+ * the useful invariant "bs in bdrv_states iff bs->tqe_prev" by
+ * resetting it to null on remove.
+ */
+ if (bs->device_list.tqe_prev) {
QTAILQ_REMOVE(&bdrv_states, bs, device_list);
+ bs->device_list.tqe_prev = NULL;
}
- bs->device_name[0] = '\0';
if (bs->node_name[0] != '\0') {
QTAILQ_REMOVE(&graph_bdrv_states, bs, node_list);
}
/* move some fields that need to stay attached to the device */
/* dev info */
- bs_dest->dev_ops = bs_src->dev_ops;
- bs_dest->dev_opaque = bs_src->dev_opaque;
- bs_dest->dev = bs_src->dev;
bs_dest->guest_block_size = bs_src->guest_block_size;
bs_dest->copy_on_read = bs_src->copy_on_read;
bs_dest->job = bs_src->job;
/* keep the same entry in bdrv_states */
- pstrcpy(bs_dest->device_name, sizeof(bs_dest->device_name),
- bs_src->device_name);
bs_dest->device_list = bs_src->device_list;
+ bs_dest->blk = bs_src->blk;
+
memcpy(bs_dest->op_blockers, bs_src->op_blockers,
sizeof(bs_dest->op_blockers));
}
* This will modify the BlockDriverState fields, and swap contents
* between bs_new and bs_old. Both bs_new and bs_old are modified.
*
- * bs_new is required to be anonymous.
+ * bs_new must not be attached to a BlockBackend.
*
* This function does not create any image files.
*/
QTAILQ_REMOVE(&graph_bdrv_states, bs_old, node_list);
}
- /* bs_new must be anonymous and shouldn't have anything fancy enabled */
- assert(bs_new->device_name[0] == '\0');
+ /* bs_new must be unattached and shouldn't have anything fancy enabled */
+ assert(!bs_new->blk);
assert(QLIST_EMPTY(&bs_new->dirty_bitmaps));
assert(bs_new->job == NULL);
- assert(bs_new->dev == NULL);
assert(bs_new->io_limits_enabled == false);
assert(!throttle_have_timer(&bs_new->throttle_state));
bdrv_move_feature_fields(bs_old, bs_new);
bdrv_move_feature_fields(bs_new, &tmp);
- /* bs_new shouldn't be in bdrv_states even after the swap! */
- assert(bs_new->device_name[0] == '\0');
+ /* bs_new must remain unattached */
+ assert(!bs_new->blk);
/* Check a few fields that should remain attached to the device */
- assert(bs_new->dev == NULL);
assert(bs_new->job == NULL);
assert(bs_new->io_limits_enabled == false);
assert(!throttle_have_timer(&bs_new->throttle_state));
* This will modify the BlockDriverState fields, and swap contents
* between bs_new and bs_top. Both bs_new and bs_top are modified.
*
- * bs_new is required to be anonymous.
+ * bs_new must not be attached to a BlockBackend.
*
* This function does not create any image files.
*/
static void bdrv_delete(BlockDriverState *bs)
{
- assert(!bs->dev);
assert(!bs->job);
assert(bdrv_op_blocker_is_empty(bs));
assert(!bs->refcnt);
/* remove from list, if necessary */
bdrv_make_anon(bs);
- drive_info_del(drive_get_by_blockdev(bs));
g_free(bs);
}
-int bdrv_attach_dev(BlockDriverState *bs, void *dev)
-/* TODO change to DeviceState *dev when all users are qdevified */
-{
- if (bs->dev) {
- return -EBUSY;
- }
- bs->dev = dev;
- bdrv_iostatus_reset(bs);
-
- /* We're expecting I/O from the device so bump up coroutine pool size */
- qemu_coroutine_adjust_pool_size(COROUTINE_POOL_RESERVATION);
- return 0;
-}
-
-/* TODO qdevified devices don't use this, remove when devices are qdevified */
-void bdrv_attach_dev_nofail(BlockDriverState *bs, void *dev)
-{
- if (bdrv_attach_dev(bs, dev) < 0) {
- abort();
- }
-}
-
-void bdrv_detach_dev(BlockDriverState *bs, void *dev)
-/* TODO change to DeviceState *dev when all users are qdevified */
-{
- assert(bs->dev == dev);
- bs->dev = NULL;
- bs->dev_ops = NULL;
- bs->dev_opaque = NULL;
- bs->guest_block_size = 512;
- qemu_coroutine_adjust_pool_size(-COROUTINE_POOL_RESERVATION);
-}
-
-/* TODO change to return DeviceState * when all users are qdevified */
-void *bdrv_get_attached_dev(BlockDriverState *bs)
-{
- return bs->dev;
-}
-
-void bdrv_set_dev_ops(BlockDriverState *bs, const BlockDevOps *ops,
- void *opaque)
-{
- bs->dev_ops = ops;
- bs->dev_opaque = opaque;
-}
-
-static void bdrv_dev_change_media_cb(BlockDriverState *bs, bool load)
-{
- if (bs->dev_ops && bs->dev_ops->change_media_cb) {
- bool tray_was_closed = !bdrv_dev_is_tray_open(bs);
- bs->dev_ops->change_media_cb(bs->dev_opaque, load);
- if (tray_was_closed) {
- /* tray open */
- qapi_event_send_device_tray_moved(bdrv_get_device_name(bs),
- true, &error_abort);
- }
- if (load) {
- /* tray close */
- qapi_event_send_device_tray_moved(bdrv_get_device_name(bs),
- false, &error_abort);
- }
- }
-}
-
-bool bdrv_dev_has_removable_media(BlockDriverState *bs)
-{
- return !bs->dev || (bs->dev_ops && bs->dev_ops->change_media_cb);
-}
-
-void bdrv_dev_eject_request(BlockDriverState *bs, bool force)
-{
- if (bs->dev_ops && bs->dev_ops->eject_request_cb) {
- bs->dev_ops->eject_request_cb(bs->dev_opaque, force);
- }
-}
-
-bool bdrv_dev_is_tray_open(BlockDriverState *bs)
-{
- if (bs->dev_ops && bs->dev_ops->is_tray_open) {
- return bs->dev_ops->is_tray_open(bs->dev_opaque);
- }
- return false;
-}
-
-static void bdrv_dev_resize_cb(BlockDriverState *bs)
-{
- if (bs->dev_ops && bs->dev_ops->resize_cb) {
- bs->dev_ops->resize_cb(bs->dev_opaque);
- }
-}
-
-bool bdrv_dev_is_medium_locked(BlockDriverState *bs)
-{
- if (bs->dev_ops && bs->dev_ops->is_medium_locked) {
- return bs->dev_ops->is_medium_locked(bs->dev_opaque);
- }
- return false;
-}
-
/*
* Run consistency checks on an image
*
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) {
return 0;
}
-/**
- * Remove an active request from the tracked requests list
- *
- * This function should be called when a tracked request is completing.
+/*
+ * Return values:
+ * 0 - success
+ * -EINVAL - backing format specified, but no file
+ * -ENOSPC - can't update the backing file because no space is left in the
+ * image file header
+ * -ENOTSUP - format driver doesn't support changing the backing file
*/
-static void tracked_request_end(BdrvTrackedRequest *req)
+int bdrv_change_backing_file(BlockDriverState *bs,
+ const char *backing_file, const char *backing_fmt)
{
- if (req->serialising) {
- req->bs->serialising_in_flight--;
- }
-
- QLIST_REMOVE(req, list);
- qemu_co_queue_restart_all(&req->wait_queue);
-}
+ BlockDriver *drv = bs->drv;
+ int ret;
-/**
- * Add an active request to the tracked requests list
- */
-static void tracked_request_begin(BdrvTrackedRequest *req,
- BlockDriverState *bs,
- int64_t offset,
- unsigned int bytes, bool is_write)
-{
- *req = (BdrvTrackedRequest){
- .bs = bs,
- .offset = offset,
- .bytes = bytes,
- .is_write = is_write,
- .co = qemu_coroutine_self(),
- .serialising = false,
- .overlap_offset = offset,
- .overlap_bytes = bytes,
- };
+ /* Backing file format doesn't make sense without a backing file */
+ if (backing_fmt && !backing_file) {
+ return -EINVAL;
+ }
- qemu_co_queue_init(&req->wait_queue);
+ if (drv->bdrv_change_backing_file != NULL) {
+ ret = drv->bdrv_change_backing_file(bs, backing_file, backing_fmt);
+ } else {
+ ret = -ENOTSUP;
+ }
- QLIST_INSERT_HEAD(&bs->tracked_requests, req, list);
-}
-
-static void mark_request_serialising(BdrvTrackedRequest *req, uint64_t align)
-{
- int64_t overlap_offset = req->offset & ~(align - 1);
- unsigned int overlap_bytes = ROUND_UP(req->offset + req->bytes, align)
- - overlap_offset;
-
- if (!req->serialising) {
- req->bs->serialising_in_flight++;
- req->serialising = true;
- }
-
- req->overlap_offset = MIN(req->overlap_offset, overlap_offset);
- req->overlap_bytes = MAX(req->overlap_bytes, overlap_bytes);
-}
-
-/**
- * Round a region to cluster boundaries
- */
-void bdrv_round_to_clusters(BlockDriverState *bs,
- int64_t sector_num, int nb_sectors,
- int64_t *cluster_sector_num,
- int *cluster_nb_sectors)
-{
- BlockDriverInfo bdi;
-
- if (bdrv_get_info(bs, &bdi) < 0 || bdi.cluster_size == 0) {
- *cluster_sector_num = sector_num;
- *cluster_nb_sectors = nb_sectors;
- } else {
- int64_t c = bdi.cluster_size / BDRV_SECTOR_SIZE;
- *cluster_sector_num = QEMU_ALIGN_DOWN(sector_num, c);
- *cluster_nb_sectors = QEMU_ALIGN_UP(sector_num - *cluster_sector_num +
- nb_sectors, c);
- }
-}
-
-static int bdrv_get_cluster_size(BlockDriverState *bs)
-{
- BlockDriverInfo bdi;
- int ret;
-
- ret = bdrv_get_info(bs, &bdi);
- if (ret < 0 || bdi.cluster_size == 0) {
- return bs->request_alignment;
- } else {
- return bdi.cluster_size;
- }
-}
-
-static bool tracked_request_overlaps(BdrvTrackedRequest *req,
- int64_t offset, unsigned int bytes)
-{
- /* aaaa bbbb */
- if (offset >= req->overlap_offset + req->overlap_bytes) {
- return false;
- }
- /* bbbb aaaa */
- if (req->overlap_offset >= offset + bytes) {
- return false;
- }
- return true;
-}
-
-static bool coroutine_fn wait_serialising_requests(BdrvTrackedRequest *self)
-{
- BlockDriverState *bs = self->bs;
- BdrvTrackedRequest *req;
- bool retry;
- bool waited = false;
-
- if (!bs->serialising_in_flight) {
- return false;
- }
-
- do {
- retry = false;
- QLIST_FOREACH(req, &bs->tracked_requests, list) {
- if (req == self || (!req->serialising && !self->serialising)) {
- continue;
- }
- if (tracked_request_overlaps(req, self->overlap_offset,
- self->overlap_bytes))
- {
- /* Hitting this means there was a reentrant request, for
- * example, a block driver issuing nested requests. This must
- * never happen since it means deadlock.
- */
- assert(qemu_coroutine_self() != req->co);
-
- /* If the request is already (indirectly) waiting for us, or
- * will wait for us as soon as it wakes up, then just go on
- * (instead of producing a deadlock in the former case). */
- if (!req->waiting_for) {
- self->waiting_for = req;
- qemu_co_queue_wait(&req->wait_queue);
- self->waiting_for = NULL;
- retry = true;
- waited = true;
- break;
- }
- }
- }
- } while (retry);
-
- return waited;
-}
-
-/*
- * Return values:
- * 0 - success
- * -EINVAL - backing format specified, but no file
- * -ENOSPC - can't update the backing file because no space is left in the
- * image file header
- * -ENOTSUP - format driver doesn't support changing the backing file
- */
-int bdrv_change_backing_file(BlockDriverState *bs,
- const char *backing_file, const char *backing_fmt)
-{
- BlockDriver *drv = bs->drv;
- int ret;
-
- /* Backing file format doesn't make sense without a backing file */
- if (backing_fmt && !backing_file) {
- return -EINVAL;
- }
-
- if (drv->bdrv_change_backing_file != NULL) {
- ret = drv->bdrv_change_backing_file(bs, backing_file, backing_fmt);
- } else {
- ret = -ENOTSUP;
- }
-
- if (ret == 0) {
- pstrcpy(bs->backing_file, sizeof(bs->backing_file), backing_file ?: "");
- pstrcpy(bs->backing_format, sizeof(bs->backing_format), backing_fmt ?: "");
- }
- return ret;
+ if (ret == 0) {
+ pstrcpy(bs->backing_file, sizeof(bs->backing_file), backing_file ?: "");
+ pstrcpy(bs->backing_format, sizeof(bs->backing_format), backing_fmt ?: "");
+ }
+ return ret;
}
/*
return ret;
}
-
-static int bdrv_check_byte_request(BlockDriverState *bs, int64_t offset,
- size_t size)
+/**
+ * Truncate file to 'offset' bytes (needed only for file protocols)
+ */
+int bdrv_truncate(BlockDriverState *bs, int64_t offset)
{
- int64_t len;
-
- if (size > INT_MAX) {
- return -EIO;
- }
-
- if (!bdrv_is_inserted(bs))
+ BlockDriver *drv = bs->drv;
+ int ret;
+ if (!drv)
return -ENOMEDIUM;
+ if (!drv->bdrv_truncate)
+ return -ENOTSUP;
+ if (bs->read_only)
+ return -EACCES;
- if (bs->growable)
- return 0;
-
- len = bdrv_getlength(bs);
-
- if (offset < 0)
- return -EIO;
-
- if ((offset > len) || (len - offset < size))
- 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) {
- return -EIO;
+ 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 bdrv_check_byte_request(bs, sector_num * BDRV_SECTOR_SIZE,
- nb_sectors * BDRV_SECTOR_SIZE);
+ return ret;
}
-typedef struct RwCo {
- BlockDriverState *bs;
- int64_t offset;
- QEMUIOVector *qiov;
- bool is_write;
- int ret;
- BdrvRequestFlags flags;
-} RwCo;
-
-static void coroutine_fn bdrv_rw_co_entry(void *opaque)
+/**
+ * Length of a allocated file in bytes. Sparse files are counted by actual
+ * allocated space. Return < 0 if error or unknown.
+ */
+int64_t bdrv_get_allocated_file_size(BlockDriverState *bs)
{
- RwCo *rwco = opaque;
-
- if (!rwco->is_write) {
- rwco->ret = bdrv_co_do_preadv(rwco->bs, rwco->offset,
- rwco->qiov->size, rwco->qiov,
- rwco->flags);
- } else {
- rwco->ret = bdrv_co_do_pwritev(rwco->bs, rwco->offset,
- rwco->qiov->size, rwco->qiov,
- rwco->flags);
+ BlockDriver *drv = bs->drv;
+ if (!drv) {
+ return -ENOMEDIUM;
+ }
+ if (drv->bdrv_get_allocated_file_size) {
+ return drv->bdrv_get_allocated_file_size(bs);
+ }
+ if (bs->file) {
+ return bdrv_get_allocated_file_size(bs->file);
}
+ return -ENOTSUP;
}
-/*
- * Process a vectored synchronous request using coroutines
+/**
+ * Return number of sectors on success, -errno on error.
*/
-static int bdrv_prwv_co(BlockDriverState *bs, int64_t offset,
- QEMUIOVector *qiov, bool is_write,
- BdrvRequestFlags flags)
+int64_t bdrv_nb_sectors(BlockDriverState *bs)
{
- Coroutine *co;
- RwCo rwco = {
- .bs = bs,
- .offset = offset,
- .qiov = qiov,
- .is_write = is_write,
- .ret = NOT_DONE,
- .flags = flags,
- };
-
- /**
- * In sync call context, when the vcpu is blocked, this throttling timer
- * will not fire; so the I/O throttling function has to be disabled here
- * if it has been enabled.
- */
- if (bs->io_limits_enabled) {
- fprintf(stderr, "Disabling I/O throttling on '%s' due "
- "to synchronous I/O.\n", bdrv_get_device_name(bs));
- bdrv_io_limits_disable(bs);
- }
+ BlockDriver *drv = bs->drv;
- if (qemu_in_coroutine()) {
- /* Fast-path if already in coroutine context */
- bdrv_rw_co_entry(&rwco);
- } else {
- AioContext *aio_context = bdrv_get_aio_context(bs);
+ if (!drv)
+ return -ENOMEDIUM;
- co = qemu_coroutine_create(bdrv_rw_co_entry);
- qemu_coroutine_enter(co, &rwco);
- while (rwco.ret == NOT_DONE) {
- aio_poll(aio_context, true);
+ if (drv->has_variable_length) {
+ int ret = refresh_total_sectors(bs, bs->total_sectors);
+ if (ret < 0) {
+ return ret;
}
}
- return rwco.ret;
+ return bs->total_sectors;
}
-/*
- * Process a synchronous request using coroutines
+/**
+ * Return length in bytes on success, -errno on error.
+ * The length is always a multiple of BDRV_SECTOR_SIZE.
*/
-static int bdrv_rw_co(BlockDriverState *bs, int64_t sector_num, uint8_t *buf,
- int nb_sectors, bool is_write, BdrvRequestFlags flags)
+int64_t bdrv_getlength(BlockDriverState *bs)
{
- QEMUIOVector qiov;
- struct iovec iov = {
- .iov_base = (void *)buf,
- .iov_len = nb_sectors * BDRV_SECTOR_SIZE,
- };
-
- if (nb_sectors < 0 || nb_sectors > INT_MAX / BDRV_SECTOR_SIZE) {
- return -EINVAL;
- }
-
- qemu_iovec_init_external(&qiov, &iov, 1);
- return bdrv_prwv_co(bs, sector_num << BDRV_SECTOR_BITS,
- &qiov, is_write, flags);
-}
+ int64_t ret = bdrv_nb_sectors(bs);
-/* return < 0 if error. See bdrv_write() for the return codes */
-int bdrv_read(BlockDriverState *bs, int64_t sector_num,
- uint8_t *buf, int nb_sectors)
-{
- return bdrv_rw_co(bs, sector_num, buf, nb_sectors, false, 0);
+ return ret < 0 ? ret : ret * BDRV_SECTOR_SIZE;
}
-/* Just like bdrv_read(), but with I/O throttling temporarily disabled */
-int bdrv_read_unthrottled(BlockDriverState *bs, int64_t sector_num,
- uint8_t *buf, int nb_sectors)
+/* return 0 as number of sectors if no device present or error */
+void bdrv_get_geometry(BlockDriverState *bs, uint64_t *nb_sectors_ptr)
{
- bool enabled;
- int ret;
+ int64_t nb_sectors = bdrv_nb_sectors(bs);
- enabled = bs->io_limits_enabled;
- bs->io_limits_enabled = false;
- ret = bdrv_read(bs, sector_num, buf, nb_sectors);
- bs->io_limits_enabled = enabled;
- return ret;
+ *nb_sectors_ptr = nb_sectors < 0 ? 0 : nb_sectors;
}
-/* Return < 0 if error. Important errors are:
- -EIO generic I/O error (may happen for all errors)
- -ENOMEDIUM No media inserted.
- -EINVAL Invalid sector number or nb_sectors
- -EACCES Trying to write a read-only device
-*/
-int bdrv_write(BlockDriverState *bs, int64_t sector_num,
- const uint8_t *buf, int nb_sectors)
+void bdrv_set_on_error(BlockDriverState *bs, BlockdevOnError on_read_error,
+ BlockdevOnError on_write_error)
{
- return bdrv_rw_co(bs, sector_num, (uint8_t *)buf, nb_sectors, true, 0);
+ bs->on_read_error = on_read_error;
+ bs->on_write_error = on_write_error;
}
-int bdrv_write_zeroes(BlockDriverState *bs, int64_t sector_num,
- int nb_sectors, BdrvRequestFlags flags)
+BlockdevOnError bdrv_get_on_error(BlockDriverState *bs, bool is_read)
{
- return bdrv_rw_co(bs, sector_num, NULL, nb_sectors, true,
- BDRV_REQ_ZERO_WRITE | flags);
+ return is_read ? bs->on_read_error : bs->on_write_error;
}
-/*
- * Completely zero out a block device with the help of bdrv_write_zeroes.
- * The operation is sped up by checking the block status and only writing
- * zeroes to the device if they currently do not return zeroes. Optional
- * flags are passed through to bdrv_write_zeroes (e.g. BDRV_REQ_MAY_UNMAP).
- *
- * Returns < 0 on error, 0 on success. For error codes see bdrv_write().
- */
-int bdrv_make_zero(BlockDriverState *bs, BdrvRequestFlags flags)
+BlockErrorAction bdrv_get_error_action(BlockDriverState *bs, bool is_read, int error)
{
- int64_t target_sectors, ret, nb_sectors, sector_num = 0;
- int n;
-
- target_sectors = bdrv_nb_sectors(bs);
- if (target_sectors < 0) {
- return target_sectors;
- }
+ BlockdevOnError on_err = is_read ? bs->on_read_error : bs->on_write_error;
- for (;;) {
- nb_sectors = target_sectors - sector_num;
- if (nb_sectors <= 0) {
- return 0;
- }
- if (nb_sectors > INT_MAX) {
- nb_sectors = INT_MAX;
- }
- ret = bdrv_get_block_status(bs, sector_num, nb_sectors, &n);
- if (ret < 0) {
- error_report("error getting block status at sector %" PRId64 ": %s",
- sector_num, strerror(-ret));
- return ret;
- }
- if (ret & BDRV_BLOCK_ZERO) {
- sector_num += n;
- continue;
- }
- ret = bdrv_write_zeroes(bs, sector_num, n, flags);
- if (ret < 0) {
- error_report("error writing zeroes at sector %" PRId64 ": %s",
- sector_num, strerror(-ret));
- return ret;
- }
- sector_num += n;
+ switch (on_err) {
+ case BLOCKDEV_ON_ERROR_ENOSPC:
+ return (error == ENOSPC) ?
+ BLOCK_ERROR_ACTION_STOP : BLOCK_ERROR_ACTION_REPORT;
+ case BLOCKDEV_ON_ERROR_STOP:
+ return BLOCK_ERROR_ACTION_STOP;
+ case BLOCKDEV_ON_ERROR_REPORT:
+ return BLOCK_ERROR_ACTION_REPORT;
+ case BLOCKDEV_ON_ERROR_IGNORE:
+ return BLOCK_ERROR_ACTION_IGNORE;
+ default:
+ abort();
}
}
-int bdrv_pread(BlockDriverState *bs, int64_t offset, void *buf, int bytes)
+static void send_qmp_error_event(BlockDriverState *bs,
+ BlockErrorAction action,
+ bool is_read, int error)
{
- QEMUIOVector qiov;
- struct iovec iov = {
- .iov_base = (void *)buf,
- .iov_len = bytes,
- };
- int ret;
+ IoOperationType optype;
- if (bytes < 0) {
- return -EINVAL;
- }
-
- qemu_iovec_init_external(&qiov, &iov, 1);
- ret = bdrv_prwv_co(bs, offset, &qiov, false, 0);
- if (ret < 0) {
- return ret;
- }
-
- return bytes;
+ optype = is_read ? IO_OPERATION_TYPE_READ : IO_OPERATION_TYPE_WRITE;
+ qapi_event_send_block_io_error(bdrv_get_device_name(bs), optype, action,
+ bdrv_iostatus_is_enabled(bs),
+ error == ENOSPC, strerror(error),
+ &error_abort);
}
-int bdrv_pwritev(BlockDriverState *bs, int64_t offset, QEMUIOVector *qiov)
+/* This is done by device models because, while the block layer knows
+ * about the error, it does not know whether an operation comes from
+ * the device or the block layer (from a job, for example).
+ */
+void bdrv_error_action(BlockDriverState *bs, BlockErrorAction action,
+ bool is_read, int error)
{
- int ret;
+ assert(error >= 0);
- ret = bdrv_prwv_co(bs, offset, qiov, true, 0);
- if (ret < 0) {
- return ret;
- }
+ if (action == BLOCK_ERROR_ACTION_STOP) {
+ /* First set the iostatus, so that "info block" returns an iostatus
+ * that matches the events raised so far (an additional error iostatus
+ * is fine, but not a lost one).
+ */
+ bdrv_iostatus_set_err(bs, error);
- return qiov->size;
+ /* Then raise the request to stop the VM and the event.
+ * qemu_system_vmstop_request_prepare has two effects. First,
+ * it ensures that the STOP event always comes after the
+ * BLOCK_IO_ERROR event. Second, it ensures that even if management
+ * can observe the STOP event and do a "cont" before the STOP
+ * event is issued, the VM will not stop. In this case, vm_start()
+ * also ensures that the STOP/RESUME pair of events is emitted.
+ */
+ qemu_system_vmstop_request_prepare();
+ send_qmp_error_event(bs, action, is_read, error);
+ qemu_system_vmstop_request(RUN_STATE_IO_ERROR);
+ } else {
+ send_qmp_error_event(bs, action, is_read, error);
+ }
}
-int bdrv_pwrite(BlockDriverState *bs, int64_t offset,
- const void *buf, int bytes)
+int bdrv_is_read_only(BlockDriverState *bs)
{
- QEMUIOVector qiov;
- struct iovec iov = {
- .iov_base = (void *) buf,
- .iov_len = bytes,
- };
-
- if (bytes < 0) {
- return -EINVAL;
- }
-
- qemu_iovec_init_external(&qiov, &iov, 1);
- return bdrv_pwritev(bs, offset, &qiov);
-}
-
-/*
- * Writes to the file and ensures that no writes are reordered across this
- * request (acts as a barrier)
- *
- * Returns 0 on success, -errno in error cases.
- */
-int bdrv_pwrite_sync(BlockDriverState *bs, int64_t offset,
- const void *buf, int count)
-{
- int ret;
-
- ret = bdrv_pwrite(bs, offset, buf, count);
- if (ret < 0) {
- return ret;
- }
-
- /* No flush needed for cache modes that already do it */
- if (bs->enable_write_cache) {
- bdrv_flush(bs);
- }
-
- return 0;
-}
-
-static int coroutine_fn bdrv_co_do_copy_on_readv(BlockDriverState *bs,
- int64_t sector_num, int nb_sectors, QEMUIOVector *qiov)
-{
- /* Perform I/O through a temporary buffer so that users who scribble over
- * their read buffer while the operation is in progress do not end up
- * modifying the image file. This is critical for zero-copy guest I/O
- * where anything might happen inside guest memory.
- */
- void *bounce_buffer;
-
- BlockDriver *drv = bs->drv;
- struct iovec iov;
- QEMUIOVector bounce_qiov;
- int64_t cluster_sector_num;
- int cluster_nb_sectors;
- size_t skip_bytes;
- int ret;
-
- /* Cover entire cluster so no additional backing file I/O is required when
- * allocating cluster in the image file.
- */
- bdrv_round_to_clusters(bs, sector_num, nb_sectors,
- &cluster_sector_num, &cluster_nb_sectors);
-
- trace_bdrv_co_do_copy_on_readv(bs, sector_num, nb_sectors,
- cluster_sector_num, cluster_nb_sectors);
-
- iov.iov_len = cluster_nb_sectors * BDRV_SECTOR_SIZE;
- iov.iov_base = bounce_buffer = qemu_try_blockalign(bs, iov.iov_len);
- if (bounce_buffer == NULL) {
- ret = -ENOMEM;
- goto err;
- }
-
- qemu_iovec_init_external(&bounce_qiov, &iov, 1);
-
- ret = drv->bdrv_co_readv(bs, cluster_sector_num, cluster_nb_sectors,
- &bounce_qiov);
- if (ret < 0) {
- goto err;
- }
-
- if (drv->bdrv_co_write_zeroes &&
- buffer_is_zero(bounce_buffer, iov.iov_len)) {
- ret = bdrv_co_do_write_zeroes(bs, cluster_sector_num,
- cluster_nb_sectors, 0);
- } else {
- /* This does not change the data on the disk, it is not necessary
- * to flush even in cache=writethrough mode.
- */
- ret = drv->bdrv_co_writev(bs, cluster_sector_num, cluster_nb_sectors,
- &bounce_qiov);
- }
-
- if (ret < 0) {
- /* It might be okay to ignore write errors for guest requests. If this
- * is a deliberate copy-on-read then we don't want to ignore the error.
- * Simply report it in all cases.
- */
- goto err;
- }
-
- skip_bytes = (sector_num - cluster_sector_num) * BDRV_SECTOR_SIZE;
- qemu_iovec_from_buf(qiov, 0, bounce_buffer + skip_bytes,
- nb_sectors * BDRV_SECTOR_SIZE);
-
-err:
- qemu_vfree(bounce_buffer);
- return ret;
-}
-
-/*
- * Forwards an already correctly aligned request to the BlockDriver. This
- * handles copy on read and zeroing after EOF; any other features must be
- * implemented by the caller.
- */
-static int coroutine_fn bdrv_aligned_preadv(BlockDriverState *bs,
- BdrvTrackedRequest *req, int64_t offset, unsigned int bytes,
- int64_t align, QEMUIOVector *qiov, int flags)
-{
- BlockDriver *drv = bs->drv;
- int ret;
-
- int64_t sector_num = offset >> BDRV_SECTOR_BITS;
- unsigned int nb_sectors = bytes >> BDRV_SECTOR_BITS;
-
- assert((offset & (BDRV_SECTOR_SIZE - 1)) == 0);
- assert((bytes & (BDRV_SECTOR_SIZE - 1)) == 0);
- assert(!qiov || bytes == qiov->size);
-
- /* Handle Copy on Read and associated serialisation */
- if (flags & BDRV_REQ_COPY_ON_READ) {
- /* If we touch the same cluster it counts as an overlap. This
- * guarantees that allocating writes will be serialized and not race
- * with each other for the same cluster. For example, in copy-on-read
- * it ensures that the CoR read and write operations are atomic and
- * guest writes cannot interleave between them. */
- mark_request_serialising(req, bdrv_get_cluster_size(bs));
- }
-
- wait_serialising_requests(req);
-
- if (flags & BDRV_REQ_COPY_ON_READ) {
- int pnum;
-
- ret = bdrv_is_allocated(bs, sector_num, nb_sectors, &pnum);
- if (ret < 0) {
- goto out;
- }
-
- if (!ret || pnum != nb_sectors) {
- ret = bdrv_co_do_copy_on_readv(bs, sector_num, nb_sectors, qiov);
- goto out;
- }
- }
-
- /* Forward the request to the BlockDriver */
- if (!(bs->zero_beyond_eof && bs->growable)) {
- ret = drv->bdrv_co_readv(bs, sector_num, nb_sectors, qiov);
- } else {
- /* Read zeros after EOF of growable BDSes */
- int64_t total_sectors, max_nb_sectors;
-
- total_sectors = bdrv_nb_sectors(bs);
- if (total_sectors < 0) {
- ret = total_sectors;
- goto out;
- }
-
- max_nb_sectors = ROUND_UP(MAX(0, total_sectors - sector_num),
- align >> BDRV_SECTOR_BITS);
- if (max_nb_sectors > 0) {
- QEMUIOVector local_qiov;
- size_t local_sectors;
-
- max_nb_sectors = MIN(max_nb_sectors, SIZE_MAX / BDRV_SECTOR_BITS);
- local_sectors = MIN(max_nb_sectors, nb_sectors);
-
- qemu_iovec_init(&local_qiov, qiov->niov);
- qemu_iovec_concat(&local_qiov, qiov, 0,
- local_sectors * BDRV_SECTOR_SIZE);
-
- ret = drv->bdrv_co_readv(bs, sector_num, local_sectors,
- &local_qiov);
-
- qemu_iovec_destroy(&local_qiov);
- } else {
- ret = 0;
- }
-
- /* Reading beyond end of file is supposed to produce zeroes */
- if (ret == 0 && total_sectors < sector_num + nb_sectors) {
- uint64_t offset = MAX(0, total_sectors - sector_num);
- uint64_t bytes = (sector_num + nb_sectors - offset) *
- BDRV_SECTOR_SIZE;
- qemu_iovec_memset(qiov, offset * BDRV_SECTOR_SIZE, 0, bytes);
- }
- }
-
-out:
- return ret;
-}
-
-/*
- * Handle a read request in coroutine context
- */
-static int coroutine_fn bdrv_co_do_preadv(BlockDriverState *bs,
- int64_t offset, unsigned int bytes, QEMUIOVector *qiov,
- BdrvRequestFlags flags)
-{
- 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);
- uint8_t *head_buf = NULL;
- uint8_t *tail_buf = NULL;
- QEMUIOVector local_qiov;
- bool use_local_qiov = false;
- int ret;
-
- if (!drv) {
- return -ENOMEDIUM;
- }
- if (bdrv_check_byte_request(bs, offset, bytes)) {
- return -EIO;
- }
-
- if (bs->copy_on_read) {
- flags |= BDRV_REQ_COPY_ON_READ;
- }
-
- /* throttling disk I/O */
- if (bs->io_limits_enabled) {
- bdrv_io_limits_intercept(bs, bytes, false);
- }
-
- /* Align read if necessary by padding qiov */
- if (offset & (align - 1)) {
- head_buf = qemu_blockalign(bs, align);
- qemu_iovec_init(&local_qiov, qiov->niov + 2);
- qemu_iovec_add(&local_qiov, head_buf, offset & (align - 1));
- qemu_iovec_concat(&local_qiov, qiov, 0, qiov->size);
- use_local_qiov = true;
-
- bytes += offset & (align - 1);
- offset = offset & ~(align - 1);
- }
-
- if ((offset + bytes) & (align - 1)) {
- if (!use_local_qiov) {
- qemu_iovec_init(&local_qiov, qiov->niov + 1);
- qemu_iovec_concat(&local_qiov, qiov, 0, qiov->size);
- use_local_qiov = true;
- }
- tail_buf = qemu_blockalign(bs, align);
- qemu_iovec_add(&local_qiov, tail_buf,
- align - ((offset + bytes) & (align - 1)));
-
- bytes = ROUND_UP(bytes, align);
- }
-
- tracked_request_begin(&req, bs, offset, bytes, false);
- ret = bdrv_aligned_preadv(bs, &req, offset, bytes, align,
- use_local_qiov ? &local_qiov : qiov,
- flags);
- tracked_request_end(&req);
-
- if (use_local_qiov) {
- qemu_iovec_destroy(&local_qiov);
- qemu_vfree(head_buf);
- qemu_vfree(tail_buf);
- }
-
- return ret;
-}
-
-static int coroutine_fn bdrv_co_do_readv(BlockDriverState *bs,
- int64_t sector_num, int nb_sectors, QEMUIOVector *qiov,
- BdrvRequestFlags flags)
-{
- if (nb_sectors < 0 || nb_sectors > (UINT_MAX >> BDRV_SECTOR_BITS)) {
- return -EINVAL;
- }
-
- return bdrv_co_do_preadv(bs, sector_num << BDRV_SECTOR_BITS,
- nb_sectors << BDRV_SECTOR_BITS, qiov, flags);
-}
-
-int coroutine_fn bdrv_co_readv(BlockDriverState *bs, int64_t sector_num,
- int nb_sectors, QEMUIOVector *qiov)
-{
- trace_bdrv_co_readv(bs, sector_num, nb_sectors);
-
- return bdrv_co_do_readv(bs, sector_num, nb_sectors, qiov, 0);
-}
-
-int coroutine_fn bdrv_co_copy_on_readv(BlockDriverState *bs,
- int64_t sector_num, int nb_sectors, QEMUIOVector *qiov)
-{
- trace_bdrv_co_copy_on_readv(bs, sector_num, nb_sectors);
-
- return bdrv_co_do_readv(bs, sector_num, nb_sectors, qiov,
- 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
-
-static int coroutine_fn bdrv_co_do_write_zeroes(BlockDriverState *bs,
- int64_t sector_num, int nb_sectors, BdrvRequestFlags flags)
-{
- BlockDriver *drv = bs->drv;
- QEMUIOVector qiov;
- 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;
-
- while (nb_sectors > 0 && !ret) {
- int num = nb_sectors;
-
- /* Align request. Block drivers can expect the "bulk" of the request
- * to be aligned.
- */
- if (bs->bl.write_zeroes_alignment
- && num > bs->bl.write_zeroes_alignment) {
- if (sector_num % bs->bl.write_zeroes_alignment != 0) {
- /* Make a small request up to the first aligned sector. */
- num = bs->bl.write_zeroes_alignment;
- num -= sector_num % bs->bl.write_zeroes_alignment;
- } else if ((sector_num + num) % bs->bl.write_zeroes_alignment != 0) {
- /* Shorten the request to the last aligned sector. num cannot
- * underflow because num > bs->bl.write_zeroes_alignment.
- */
- num -= (sector_num + num) % bs->bl.write_zeroes_alignment;
- }
- }
-
- /* limit request size */
- if (num > max_write_zeroes) {
- num = max_write_zeroes;
- }
-
- ret = -ENOTSUP;
- /* First try the efficient write zeroes operation */
- if (drv->bdrv_co_write_zeroes) {
- ret = drv->bdrv_co_write_zeroes(bs, sector_num, num, flags);
- }
-
- if (ret == -ENOTSUP) {
- /* Fall back to bounce buffer if write zeroes is unsupported */
- iov.iov_len = num * BDRV_SECTOR_SIZE;
- if (iov.iov_base == NULL) {
- iov.iov_base = qemu_try_blockalign(bs, num * BDRV_SECTOR_SIZE);
- if (iov.iov_base == NULL) {
- ret = -ENOMEM;
- goto fail;
- }
- memset(iov.iov_base, 0, num * BDRV_SECTOR_SIZE);
- }
- qemu_iovec_init_external(&qiov, &iov, 1);
-
- ret = drv->bdrv_co_writev(bs, sector_num, num, &qiov);
-
- /* Keep bounce buffer around if it is big enough for all
- * all future requests.
- */
- if (num < max_write_zeroes) {
- qemu_vfree(iov.iov_base);
- iov.iov_base = NULL;
- }
- }
-
- sector_num += num;
- nb_sectors -= num;
- }
-
-fail:
- qemu_vfree(iov.iov_base);
- return ret;
-}
-
-/*
- * Forwards an already correctly aligned write request to the BlockDriver.
- */
-static int coroutine_fn bdrv_aligned_pwritev(BlockDriverState *bs,
- BdrvTrackedRequest *req, int64_t offset, unsigned int bytes,
- QEMUIOVector *qiov, int flags)
-{
- BlockDriver *drv = bs->drv;
- bool waited;
- int ret;
-
- int64_t sector_num = offset >> BDRV_SECTOR_BITS;
- unsigned int nb_sectors = bytes >> BDRV_SECTOR_BITS;
-
- assert((offset & (BDRV_SECTOR_SIZE - 1)) == 0);
- assert((bytes & (BDRV_SECTOR_SIZE - 1)) == 0);
- assert(!qiov || bytes == qiov->size);
-
- waited = wait_serialising_requests(req);
- assert(!waited || !req->serialising);
- assert(req->overlap_offset <= offset);
- assert(offset + bytes <= req->overlap_offset + req->overlap_bytes);
-
- ret = notifier_with_return_list_notify(&bs->before_write_notifiers, req);
-
- if (!ret && bs->detect_zeroes != BLOCKDEV_DETECT_ZEROES_OPTIONS_OFF &&
- !(flags & BDRV_REQ_ZERO_WRITE) && drv->bdrv_co_write_zeroes &&
- qemu_iovec_is_zero(qiov)) {
- flags |= BDRV_REQ_ZERO_WRITE;
- if (bs->detect_zeroes == BLOCKDEV_DETECT_ZEROES_OPTIONS_UNMAP) {
- flags |= BDRV_REQ_MAY_UNMAP;
- }
- }
-
- if (ret < 0) {
- /* Do nothing, write notifier decided to fail this request */
- } else if (flags & BDRV_REQ_ZERO_WRITE) {
- BLKDBG_EVENT(bs, BLKDBG_PWRITEV_ZERO);
- ret = bdrv_co_do_write_zeroes(bs, sector_num, nb_sectors, flags);
- } else {
- BLKDBG_EVENT(bs, BLKDBG_PWRITEV);
- ret = drv->bdrv_co_writev(bs, sector_num, nb_sectors, qiov);
- }
- BLKDBG_EVENT(bs, BLKDBG_PWRITEV_DONE);
-
- if (ret == 0 && !bs->enable_write_cache) {
- ret = bdrv_co_flush(bs);
- }
-
- bdrv_set_dirty(bs, sector_num, nb_sectors);
-
- block_acct_highest_sector(&bs->stats, sector_num, nb_sectors);
-
- if (bs->growable && ret >= 0) {
- bs->total_sectors = MAX(bs->total_sectors, sector_num + nb_sectors);
- }
-
- return ret;
-}
-
-/*
- * Handle a write request in coroutine context
- */
-static int coroutine_fn bdrv_co_do_pwritev(BlockDriverState *bs,
- int64_t offset, unsigned int bytes, QEMUIOVector *qiov,
- BdrvRequestFlags flags)
-{
- BdrvTrackedRequest req;
- /* TODO Lift BDRV_SECTOR_SIZE restriction in BlockDriver interface */
- uint64_t align = MAX(BDRV_SECTOR_SIZE, bs->request_alignment);
- uint8_t *head_buf = NULL;
- uint8_t *tail_buf = NULL;
- QEMUIOVector local_qiov;
- bool use_local_qiov = false;
- int ret;
-
- if (!bs->drv) {
- return -ENOMEDIUM;
- }
- if (bs->read_only) {
- return -EACCES;
- }
- if (bdrv_check_byte_request(bs, offset, bytes)) {
- return -EIO;
- }
-
- /* throttling disk I/O */
- if (bs->io_limits_enabled) {
- bdrv_io_limits_intercept(bs, bytes, true);
- }
-
- /*
- * Align write if necessary by performing a read-modify-write cycle.
- * Pad qiov with the read parts and be sure to have a tracked request not
- * only for bdrv_aligned_pwritev, but also for the reads of the RMW cycle.
- */
- tracked_request_begin(&req, bs, offset, bytes, true);
-
- if (offset & (align - 1)) {
- QEMUIOVector head_qiov;
- struct iovec head_iov;
-
- mark_request_serialising(&req, align);
- wait_serialising_requests(&req);
-
- head_buf = qemu_blockalign(bs, align);
- head_iov = (struct iovec) {
- .iov_base = head_buf,
- .iov_len = align,
- };
- qemu_iovec_init_external(&head_qiov, &head_iov, 1);
-
- BLKDBG_EVENT(bs, BLKDBG_PWRITEV_RMW_HEAD);
- ret = bdrv_aligned_preadv(bs, &req, offset & ~(align - 1), align,
- align, &head_qiov, 0);
- if (ret < 0) {
- goto fail;
- }
- BLKDBG_EVENT(bs, BLKDBG_PWRITEV_RMW_AFTER_HEAD);
-
- qemu_iovec_init(&local_qiov, qiov->niov + 2);
- qemu_iovec_add(&local_qiov, head_buf, offset & (align - 1));
- qemu_iovec_concat(&local_qiov, qiov, 0, qiov->size);
- use_local_qiov = true;
-
- bytes += offset & (align - 1);
- offset = offset & ~(align - 1);
- }
-
- if ((offset + bytes) & (align - 1)) {
- QEMUIOVector tail_qiov;
- struct iovec tail_iov;
- size_t tail_bytes;
- bool waited;
-
- mark_request_serialising(&req, align);
- waited = wait_serialising_requests(&req);
- assert(!waited || !use_local_qiov);
-
- tail_buf = qemu_blockalign(bs, align);
- tail_iov = (struct iovec) {
- .iov_base = tail_buf,
- .iov_len = align,
- };
- qemu_iovec_init_external(&tail_qiov, &tail_iov, 1);
-
- BLKDBG_EVENT(bs, BLKDBG_PWRITEV_RMW_TAIL);
- ret = bdrv_aligned_preadv(bs, &req, (offset + bytes) & ~(align - 1), align,
- align, &tail_qiov, 0);
- if (ret < 0) {
- goto fail;
- }
- BLKDBG_EVENT(bs, BLKDBG_PWRITEV_RMW_AFTER_TAIL);
-
- if (!use_local_qiov) {
- qemu_iovec_init(&local_qiov, qiov->niov + 1);
- qemu_iovec_concat(&local_qiov, qiov, 0, qiov->size);
- use_local_qiov = true;
- }
-
- tail_bytes = (offset + bytes) & (align - 1);
- qemu_iovec_add(&local_qiov, tail_buf + tail_bytes, align - tail_bytes);
-
- bytes = ROUND_UP(bytes, align);
- }
-
- ret = bdrv_aligned_pwritev(bs, &req, offset, bytes,
- use_local_qiov ? &local_qiov : qiov,
- flags);
-
-fail:
- tracked_request_end(&req);
-
- if (use_local_qiov) {
- qemu_iovec_destroy(&local_qiov);
- }
- qemu_vfree(head_buf);
- qemu_vfree(tail_buf);
-
- return ret;
-}
-
-static int coroutine_fn bdrv_co_do_writev(BlockDriverState *bs,
- int64_t sector_num, int nb_sectors, QEMUIOVector *qiov,
- BdrvRequestFlags flags)
-{
- if (nb_sectors < 0 || nb_sectors > (INT_MAX >> BDRV_SECTOR_BITS)) {
- return -EINVAL;
- }
-
- return bdrv_co_do_pwritev(bs, sector_num << BDRV_SECTOR_BITS,
- nb_sectors << BDRV_SECTOR_BITS, qiov, flags);
-}
-
-int coroutine_fn bdrv_co_writev(BlockDriverState *bs, int64_t sector_num,
- int nb_sectors, QEMUIOVector *qiov)
-{
- trace_bdrv_co_writev(bs, sector_num, nb_sectors);
-
- return bdrv_co_do_writev(bs, sector_num, nb_sectors, qiov, 0);
-}
-
-int coroutine_fn bdrv_co_write_zeroes(BlockDriverState *bs,
- int64_t sector_num, int nb_sectors,
- BdrvRequestFlags flags)
-{
- trace_bdrv_co_write_zeroes(bs, sector_num, nb_sectors, flags);
-
- if (!(bs->open_flags & BDRV_O_UNMAP)) {
- flags &= ~BDRV_REQ_MAY_UNMAP;
- }
-
- return bdrv_co_do_writev(bs, sector_num, nb_sectors, NULL,
- BDRV_REQ_ZERO_WRITE | flags);
-}
-
-/**
- * Truncate file to 'offset' bytes (needed only for file protocols)
- */
-int bdrv_truncate(BlockDriverState *bs, int64_t offset)
-{
- BlockDriver *drv = bs->drv;
- int ret;
- if (!drv)
- return -ENOMEDIUM;
- if (!drv->bdrv_truncate)
- return -ENOTSUP;
- if (bs->read_only)
- return -EACCES;
-
- ret = drv->bdrv_truncate(bs, offset);
- if (ret == 0) {
- ret = refresh_total_sectors(bs, offset >> BDRV_SECTOR_BITS);
- bdrv_dev_resize_cb(bs);
- }
- return ret;
-}
-
-/**
- * Length of a allocated file in bytes. Sparse files are counted by actual
- * allocated space. Return < 0 if error or unknown.
- */
-int64_t bdrv_get_allocated_file_size(BlockDriverState *bs)
-{
- BlockDriver *drv = bs->drv;
- if (!drv) {
- return -ENOMEDIUM;
- }
- if (drv->bdrv_get_allocated_file_size) {
- return drv->bdrv_get_allocated_file_size(bs);
- }
- if (bs->file) {
- return bdrv_get_allocated_file_size(bs->file);
- }
- return -ENOTSUP;
-}
-
-/**
- * Return number of sectors on success, -errno on error.
- */
-int64_t bdrv_nb_sectors(BlockDriverState *bs)
-{
- BlockDriver *drv = bs->drv;
-
- if (!drv)
- return -ENOMEDIUM;
-
- if (drv->has_variable_length) {
- int ret = refresh_total_sectors(bs, bs->total_sectors);
- if (ret < 0) {
- return ret;
- }
- }
- return bs->total_sectors;
-}
-
-/**
- * Return length in bytes on success, -errno on error.
- * The length is always a multiple of BDRV_SECTOR_SIZE.
- */
-int64_t bdrv_getlength(BlockDriverState *bs)
-{
- int64_t ret = bdrv_nb_sectors(bs);
-
- return ret < 0 ? ret : ret * BDRV_SECTOR_SIZE;
-}
-
-/* return 0 as number of sectors if no device present or error */
-void bdrv_get_geometry(BlockDriverState *bs, uint64_t *nb_sectors_ptr)
-{
- int64_t nb_sectors = bdrv_nb_sectors(bs);
-
- *nb_sectors_ptr = nb_sectors < 0 ? 0 : nb_sectors;
-}
-
-void bdrv_set_on_error(BlockDriverState *bs, BlockdevOnError on_read_error,
- BlockdevOnError on_write_error)
-{
- bs->on_read_error = on_read_error;
- bs->on_write_error = on_write_error;
-}
-
-BlockdevOnError bdrv_get_on_error(BlockDriverState *bs, bool is_read)
-{
- return is_read ? bs->on_read_error : bs->on_write_error;
-}
-
-BlockErrorAction bdrv_get_error_action(BlockDriverState *bs, bool is_read, int error)
-{
- BlockdevOnError on_err = is_read ? bs->on_read_error : bs->on_write_error;
-
- switch (on_err) {
- case BLOCKDEV_ON_ERROR_ENOSPC:
- return (error == ENOSPC) ?
- BLOCK_ERROR_ACTION_STOP : BLOCK_ERROR_ACTION_REPORT;
- case BLOCKDEV_ON_ERROR_STOP:
- return BLOCK_ERROR_ACTION_STOP;
- case BLOCKDEV_ON_ERROR_REPORT:
- return BLOCK_ERROR_ACTION_REPORT;
- case BLOCKDEV_ON_ERROR_IGNORE:
- return BLOCK_ERROR_ACTION_IGNORE;
- default:
- abort();
- }
-}
-
-static void send_qmp_error_event(BlockDriverState *bs,
- BlockErrorAction action,
- bool is_read, int error)
-{
- BlockErrorAction ac;
-
- ac = is_read ? IO_OPERATION_TYPE_READ : IO_OPERATION_TYPE_WRITE;
- qapi_event_send_block_io_error(bdrv_get_device_name(bs), ac, action,
- bdrv_iostatus_is_enabled(bs),
- error == ENOSPC, strerror(error),
- &error_abort);
-}
-
-/* This is done by device models because, while the block layer knows
- * about the error, it does not know whether an operation comes from
- * the device or the block layer (from a job, for example).
- */
-void bdrv_error_action(BlockDriverState *bs, BlockErrorAction action,
- bool is_read, int error)
-{
- assert(error >= 0);
-
- if (action == BLOCK_ERROR_ACTION_STOP) {
- /* First set the iostatus, so that "info block" returns an iostatus
- * that matches the events raised so far (an additional error iostatus
- * is fine, but not a lost one).
- */
- bdrv_iostatus_set_err(bs, error);
-
- /* Then raise the request to stop the VM and the event.
- * qemu_system_vmstop_request_prepare has two effects. First,
- * it ensures that the STOP event always comes after the
- * BLOCK_IO_ERROR event. Second, it ensures that even if management
- * can observe the STOP event and do a "cont" before the STOP
- * event is issued, the VM will not stop. In this case, vm_start()
- * also ensures that the STOP/RESUME pair of events is emitted.
- */
- qemu_system_vmstop_request_prepare();
- send_qmp_error_event(bs, action, is_read, error);
- qemu_system_vmstop_request(RUN_STATE_IO_ERROR);
- } else {
- send_qmp_error_event(bs, action, is_read, error);
- }
-}
-
-int bdrv_is_read_only(BlockDriverState *bs)
-{
- return bs->read_only;
+ return bs->read_only;
}
int bdrv_is_sg(BlockDriverState *bs)
bs->valid_key = 0;
} else if (!bs->valid_key) {
bs->valid_key = 1;
- /* call the change callback now, we skipped it on open */
- bdrv_dev_change_media_cb(bs, true);
+ if (bs->blk) {
+ /* call the change callback now, we skipped it on open */
+ blk_dev_change_media_cb(bs->blk, true);
+ }
}
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 */
-BlockDriverState *bdrv_find(const char *name)
-{
- BlockDriverState *bs;
-
- QTAILQ_FOREACH(bs, &bdrv_states, device_list) {
- if (!strcmp(name, bs->device_name)) {
- return bs;
- }
- }
- return 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;
}
const char *node_name,
Error **errp)
{
- BlockDriverState *bs = NULL;
+ BlockBackend *blk;
+ BlockDriverState *bs;
if (device) {
- bs = bdrv_find(device);
+ blk = blk_by_name(device);
- if (bs) {
- return bs;
+ if (blk) {
+ return blk_bs(blk);
}
}
return top != NULL;
}
+BlockDriverState *bdrv_next_node(BlockDriverState *bs)
+{
+ if (!bs) {
+ return QTAILQ_FIRST(&graph_bdrv_states);
+ }
+ return QTAILQ_NEXT(bs, node_list);
+}
+
BlockDriverState *bdrv_next(BlockDriverState *bs)
{
if (!bs) {
return QTAILQ_NEXT(bs, device_list);
}
-void bdrv_iterate(void (*it)(void *opaque, BlockDriverState *bs), void *opaque)
+const char *bdrv_get_node_name(const BlockDriverState *bs)
{
- BlockDriverState *bs;
-
- QTAILQ_FOREACH(bs, &bdrv_states, device_list) {
- it(opaque, bs);
- }
+ return bs->node_name;
}
-const char *bdrv_get_device_name(BlockDriverState *bs)
+/* TODO check what callers really want: bs->node_name or blk_name() */
+const char *bdrv_get_device_name(const BlockDriverState *bs)
{
- return bs->device_name;
+ return bs->blk ? blk_name(bs->blk) : "";
}
-int bdrv_get_flags(BlockDriverState *bs)
+/* 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->open_flags;
+ return bs->blk ? blk_name(bs->blk) : bs->node_name;
}
-int bdrv_flush_all(void)
+int bdrv_get_flags(BlockDriverState *bs)
{
- BlockDriverState *bs;
- int result = 0;
-
- QTAILQ_FOREACH(bs, &bdrv_states, device_list) {
- AioContext *aio_context = bdrv_get_aio_context(bs);
- int ret;
-
- aio_context_acquire(aio_context);
- ret = bdrv_flush(bs);
- if (ret < 0 && !result) {
- result = ret;
- }
- aio_context_release(aio_context);
- }
-
- return result;
+ return bs->open_flags;
}
int bdrv_has_zero_init_1(BlockDriverState *bs)
return false;
}
-typedef struct BdrvCoGetBlockStatusData {
- BlockDriverState *bs;
- BlockDriverState *base;
- int64_t sector_num;
- int nb_sectors;
- int *pnum;
- int64_t ret;
- bool done;
-} BdrvCoGetBlockStatusData;
-
-/*
- * Returns true iff the specified sector is present in the disk image. Drivers
- * not implementing the functionality are assumed to not support backing files,
- * hence all their sectors are reported as allocated.
- *
- * If 'sector_num' is beyond the end of the disk image the return value is 0
- * and 'pnum' is set to 0.
- *
- * 'pnum' is set to the number of sectors (including and immediately following
- * the specified sector) that are known to be in the same
- * allocated/unallocated state.
- *
- * 'nb_sectors' is the max value 'pnum' should be set to. If nb_sectors goes
- * beyond the end of the disk image it will be clamped.
- */
-static int64_t coroutine_fn bdrv_co_get_block_status(BlockDriverState *bs,
- int64_t sector_num,
- int nb_sectors, int *pnum)
-{
- int64_t total_sectors;
- int64_t n;
- int64_t ret, ret2;
-
- total_sectors = bdrv_nb_sectors(bs);
- if (total_sectors < 0) {
- return total_sectors;
- }
-
- if (sector_num >= total_sectors) {
- *pnum = 0;
- return 0;
- }
-
- n = total_sectors - sector_num;
- if (n < nb_sectors) {
- nb_sectors = n;
- }
-
- if (!bs->drv->bdrv_co_get_block_status) {
- *pnum = nb_sectors;
- ret = BDRV_BLOCK_DATA | BDRV_BLOCK_ALLOCATED;
- if (bs->drv->protocol_name) {
- ret |= BDRV_BLOCK_OFFSET_VALID | (sector_num * BDRV_SECTOR_SIZE);
- }
- return ret;
- }
-
- ret = bs->drv->bdrv_co_get_block_status(bs, sector_num, nb_sectors, pnum);
- if (ret < 0) {
- *pnum = 0;
- return ret;
- }
-
- if (ret & BDRV_BLOCK_RAW) {
- assert(ret & BDRV_BLOCK_OFFSET_VALID);
- return bdrv_get_block_status(bs->file, ret >> BDRV_SECTOR_BITS,
- *pnum, pnum);
- }
-
- if (ret & (BDRV_BLOCK_DATA | BDRV_BLOCK_ZERO)) {
- ret |= BDRV_BLOCK_ALLOCATED;
- }
-
- if (!(ret & BDRV_BLOCK_DATA) && !(ret & BDRV_BLOCK_ZERO)) {
- if (bdrv_unallocated_blocks_are_zero(bs)) {
- ret |= BDRV_BLOCK_ZERO;
- } else if (bs->backing_hd) {
- BlockDriverState *bs2 = bs->backing_hd;
- int64_t nb_sectors2 = bdrv_nb_sectors(bs2);
- if (nb_sectors2 >= 0 && sector_num >= nb_sectors2) {
- ret |= BDRV_BLOCK_ZERO;
- }
- }
- }
-
- if (bs->file &&
- (ret & BDRV_BLOCK_DATA) && !(ret & BDRV_BLOCK_ZERO) &&
- (ret & BDRV_BLOCK_OFFSET_VALID)) {
- ret2 = bdrv_co_get_block_status(bs->file, ret >> BDRV_SECTOR_BITS,
- *pnum, pnum);
- if (ret2 >= 0) {
- /* Ignore errors. This is just providing extra information, it
- * is useful but not necessary.
- */
- ret |= (ret2 & BDRV_BLOCK_ZERO);
- }
- }
-
- return ret;
-}
-
-/* Coroutine wrapper for bdrv_get_block_status() */
-static void coroutine_fn bdrv_get_block_status_co_entry(void *opaque)
-{
- BdrvCoGetBlockStatusData *data = opaque;
- BlockDriverState *bs = data->bs;
-
- data->ret = bdrv_co_get_block_status(bs, data->sector_num, data->nb_sectors,
- data->pnum);
- data->done = true;
-}
-
-/*
- * Synchronous wrapper around bdrv_co_get_block_status().
- *
- * See bdrv_co_get_block_status() for details.
- */
-int64_t bdrv_get_block_status(BlockDriverState *bs, int64_t sector_num,
- int nb_sectors, int *pnum)
-{
- Coroutine *co;
- BdrvCoGetBlockStatusData data = {
- .bs = bs,
- .sector_num = sector_num,
- .nb_sectors = nb_sectors,
- .pnum = pnum,
- .done = false,
- };
-
- if (qemu_in_coroutine()) {
- /* Fast-path if already in coroutine context */
- bdrv_get_block_status_co_entry(&data);
- } else {
- AioContext *aio_context = bdrv_get_aio_context(bs);
-
- co = qemu_coroutine_create(bdrv_get_block_status_co_entry);
- qemu_coroutine_enter(co, &data);
- while (!data.done) {
- aio_poll(aio_context, true);
- }
- }
- return data.ret;
-}
-
-int coroutine_fn bdrv_is_allocated(BlockDriverState *bs, int64_t sector_num,
- int nb_sectors, int *pnum)
-{
- int64_t ret = bdrv_get_block_status(bs, sector_num, nb_sectors, pnum);
- if (ret < 0) {
- return ret;
- }
- return !!(ret & BDRV_BLOCK_ALLOCATED);
-}
-
-/*
- * Given an image chain: ... -> [BASE] -> [INTER1] -> [INTER2] -> [TOP]
- *
- * Return true if the given sector is allocated in any image between
- * BASE and TOP (inclusive). BASE can be NULL to check if the given
- * sector is allocated in any image of the chain. Return false otherwise.
- *
- * 'pnum' is set to the number of sectors (including and immediately following
- * the specified sector) that are known to be in the same
- * allocated/unallocated state.
- *
- */
-int bdrv_is_allocated_above(BlockDriverState *top,
- BlockDriverState *base,
- int64_t sector_num,
- int nb_sectors, int *pnum)
-{
- BlockDriverState *intermediate;
- int ret, n = nb_sectors;
-
- intermediate = top;
- while (intermediate && intermediate != base) {
- int pnum_inter;
- ret = bdrv_is_allocated(intermediate, sector_num, nb_sectors,
- &pnum_inter);
- if (ret < 0) {
- return ret;
- } else if (ret) {
- *pnum = pnum_inter;
- return 1;
- }
-
- /*
- * [sector_num, nb_sectors] is unallocated on top but intermediate
- * might have
- *
- * [sector_num+x, nr_sectors] allocated.
- */
- if (n > pnum_inter &&
- (intermediate == top ||
- sector_num + pnum_inter < intermediate->total_sectors)) {
- n = pnum_inter;
- }
-
- intermediate = intermediate->backing_hd;
- }
-
- *pnum = n;
- return 0;
-}
-
const char *bdrv_get_encrypted_filename(BlockDriverState *bs)
{
if (bs->backing_hd && bs->backing_hd->encrypted)
pstrcpy(filename, filename_size, bs->backing_file);
}
-int bdrv_write_compressed(BlockDriverState *bs, int64_t sector_num,
- const uint8_t *buf, int nb_sectors)
-{
- BlockDriver *drv = bs->drv;
- if (!drv)
- return -ENOMEDIUM;
- if (!drv->bdrv_write_compressed)
- return -ENOTSUP;
- if (bdrv_check_request(bs, sector_num, nb_sectors))
- return -EIO;
-
- assert(QLIST_EMPTY(&bs->dirty_bitmaps));
-
- return drv->bdrv_write_compressed(bs, sector_num, buf, nb_sectors);
-}
-
int bdrv_get_info(BlockDriverState *bs, BlockDriverInfo *bdi)
{
BlockDriver *drv = bs->drv;
ImageInfoSpecific *bdrv_get_specific_info(BlockDriverState *bs)
{
BlockDriver *drv = bs->drv;
- if (drv && drv->bdrv_get_specific_info) {
- return drv->bdrv_get_specific_info(bs);
- }
- return NULL;
-}
-
-int bdrv_save_vmstate(BlockDriverState *bs, const uint8_t *buf,
- int64_t pos, int size)
-{
- QEMUIOVector qiov;
- struct iovec iov = {
- .iov_base = (void *) buf,
- .iov_len = size,
- };
-
- qemu_iovec_init_external(&qiov, &iov, 1);
- return bdrv_writev_vmstate(bs, &qiov, pos);
-}
-
-int bdrv_writev_vmstate(BlockDriverState *bs, QEMUIOVector *qiov, int64_t pos)
-{
- BlockDriver *drv = bs->drv;
-
- if (!drv) {
- return -ENOMEDIUM;
- } else if (drv->bdrv_save_vmstate) {
- return drv->bdrv_save_vmstate(bs, qiov, pos);
- } else if (bs->file) {
- return bdrv_writev_vmstate(bs->file, qiov, pos);
- }
-
- return -ENOTSUP;
-}
-
-int bdrv_load_vmstate(BlockDriverState *bs, uint8_t *buf,
- int64_t pos, int size)
-{
- BlockDriver *drv = bs->drv;
- if (!drv)
- return -ENOMEDIUM;
- if (drv->bdrv_load_vmstate)
- return drv->bdrv_load_vmstate(bs, buf, pos, size);
- if (bs->file)
- return bdrv_load_vmstate(bs->file, buf, pos, size);
- return -ENOTSUP;
+ if (drv && drv->bdrv_get_specific_info) {
+ return drv->bdrv_get_specific_info(bs);
+ }
+ return NULL;
}
void bdrv_debug_event(BlockDriverState *bs, BlkDebugEvent event)
if (!bs->drv) {
return 0;
}
-
- if (!bs->backing_hd) {
- return 0;
- }
-
- return 1 + bdrv_get_backing_file_depth(bs->backing_hd);
-}
-
-/**************************************************************/
-/* async I/Os */
-
-BlockDriverAIOCB *bdrv_aio_readv(BlockDriverState *bs, int64_t sector_num,
- QEMUIOVector *qiov, int nb_sectors,
- BlockDriverCompletionFunc *cb, void *opaque)
-{
- trace_bdrv_aio_readv(bs, sector_num, nb_sectors, opaque);
-
- return bdrv_co_aio_rw_vector(bs, sector_num, qiov, nb_sectors, 0,
- cb, opaque, false);
-}
-
-BlockDriverAIOCB *bdrv_aio_writev(BlockDriverState *bs, int64_t sector_num,
- QEMUIOVector *qiov, int nb_sectors,
- BlockDriverCompletionFunc *cb, void *opaque)
-{
- trace_bdrv_aio_writev(bs, sector_num, nb_sectors, opaque);
-
- return bdrv_co_aio_rw_vector(bs, sector_num, qiov, nb_sectors, 0,
- cb, opaque, true);
-}
-
-BlockDriverAIOCB *bdrv_aio_write_zeroes(BlockDriverState *bs,
- int64_t sector_num, int nb_sectors, BdrvRequestFlags flags,
- BlockDriverCompletionFunc *cb, void *opaque)
-{
- trace_bdrv_aio_write_zeroes(bs, sector_num, nb_sectors, flags, opaque);
-
- return bdrv_co_aio_rw_vector(bs, sector_num, NULL, nb_sectors,
- BDRV_REQ_ZERO_WRITE | flags,
- cb, opaque, true);
-}
-
-
-typedef struct MultiwriteCB {
- int error;
- int num_requests;
- int num_callbacks;
- struct {
- BlockDriverCompletionFunc *cb;
- void *opaque;
- QEMUIOVector *free_qiov;
- } callbacks[];
-} MultiwriteCB;
-
-static void multiwrite_user_cb(MultiwriteCB *mcb)
-{
- int i;
-
- for (i = 0; i < mcb->num_callbacks; i++) {
- mcb->callbacks[i].cb(mcb->callbacks[i].opaque, mcb->error);
- if (mcb->callbacks[i].free_qiov) {
- qemu_iovec_destroy(mcb->callbacks[i].free_qiov);
- }
- g_free(mcb->callbacks[i].free_qiov);
- }
-}
-
-static void multiwrite_cb(void *opaque, int ret)
-{
- MultiwriteCB *mcb = opaque;
-
- trace_multiwrite_cb(mcb, ret);
-
- if (ret < 0 && !mcb->error) {
- mcb->error = ret;
- }
-
- mcb->num_requests--;
- if (mcb->num_requests == 0) {
- multiwrite_user_cb(mcb);
- g_free(mcb);
- }
-}
-
-static int multiwrite_req_compare(const void *a, const void *b)
-{
- const BlockRequest *req1 = a, *req2 = b;
-
- /*
- * Note that we can't simply subtract req2->sector from req1->sector
- * here as that could overflow the return value.
- */
- if (req1->sector > req2->sector) {
- return 1;
- } else if (req1->sector < req2->sector) {
- return -1;
- } else {
- return 0;
- }
-}
-
-/*
- * Takes a bunch of requests and tries to merge them. Returns the number of
- * requests that remain after merging.
- */
-static int multiwrite_merge(BlockDriverState *bs, BlockRequest *reqs,
- int num_reqs, MultiwriteCB *mcb)
-{
- int i, outidx;
-
- // Sort requests by start sector
- qsort(reqs, num_reqs, sizeof(*reqs), &multiwrite_req_compare);
-
- // Check if adjacent requests touch the same clusters. If so, combine them,
- // filling up gaps with zero sectors.
- outidx = 0;
- for (i = 1; i < num_reqs; i++) {
- int merge = 0;
- int64_t oldreq_last = reqs[outidx].sector + reqs[outidx].nb_sectors;
-
- // Handle exactly sequential writes and overlapping writes.
- if (reqs[i].sector <= oldreq_last) {
- merge = 1;
- }
-
- if (reqs[outidx].qiov->niov + reqs[i].qiov->niov + 1 > IOV_MAX) {
- merge = 0;
- }
-
- if (merge) {
- size_t size;
- QEMUIOVector *qiov = g_malloc0(sizeof(*qiov));
- qemu_iovec_init(qiov,
- reqs[outidx].qiov->niov + reqs[i].qiov->niov + 1);
-
- // Add the first request to the merged one. If the requests are
- // overlapping, drop the last sectors of the first request.
- size = (reqs[i].sector - reqs[outidx].sector) << 9;
- qemu_iovec_concat(qiov, reqs[outidx].qiov, 0, size);
-
- // We should need to add any zeros between the two requests
- assert (reqs[i].sector <= oldreq_last);
-
- // Add the second request
- qemu_iovec_concat(qiov, reqs[i].qiov, 0, reqs[i].qiov->size);
-
- // Add tail of first request, if necessary
- if (qiov->size < reqs[outidx].qiov->size) {
- qemu_iovec_concat(qiov, reqs[outidx].qiov, qiov->size,
- reqs[outidx].qiov->size - qiov->size);
- }
-
- reqs[outidx].nb_sectors = qiov->size >> 9;
- reqs[outidx].qiov = qiov;
-
- mcb->callbacks[i].free_qiov = reqs[outidx].qiov;
- } else {
- outidx++;
- reqs[outidx].sector = reqs[i].sector;
- reqs[outidx].nb_sectors = reqs[i].nb_sectors;
- reqs[outidx].qiov = reqs[i].qiov;
- }
- }
-
- return outidx + 1;
-}
-
-/*
- * Submit multiple AIO write requests at once.
- *
- * On success, the function returns 0 and all requests in the reqs array have
- * been submitted. In error case this function returns -1, and any of the
- * requests may or may not be submitted yet. In particular, this means that the
- * callback will be called for some of the requests, for others it won't. The
- * caller must check the error field of the BlockRequest to wait for the right
- * callbacks (if error != 0, no callback will be called).
- *
- * The implementation may modify the contents of the reqs array, e.g. to merge
- * requests. However, the fields opaque and error are left unmodified as they
- * are used to signal failure for a single request to the caller.
- */
-int bdrv_aio_multiwrite(BlockDriverState *bs, BlockRequest *reqs, int num_reqs)
-{
- MultiwriteCB *mcb;
- int i;
-
- /* don't submit writes if we don't have a medium */
- if (bs->drv == NULL) {
- for (i = 0; i < num_reqs; i++) {
- reqs[i].error = -ENOMEDIUM;
- }
- return -1;
- }
-
- if (num_reqs == 0) {
- return 0;
- }
-
- // Create MultiwriteCB structure
- mcb = g_malloc0(sizeof(*mcb) + num_reqs * sizeof(*mcb->callbacks));
- mcb->num_requests = 0;
- mcb->num_callbacks = num_reqs;
-
- for (i = 0; i < num_reqs; i++) {
- mcb->callbacks[i].cb = reqs[i].cb;
- mcb->callbacks[i].opaque = reqs[i].opaque;
- }
-
- // Check for mergable requests
- num_reqs = multiwrite_merge(bs, reqs, num_reqs, mcb);
-
- trace_bdrv_aio_multiwrite(mcb, mcb->num_callbacks, num_reqs);
-
- /* Run the aio requests. */
- mcb->num_requests = num_reqs;
- for (i = 0; i < num_reqs; i++) {
- bdrv_co_aio_rw_vector(bs, reqs[i].sector, reqs[i].qiov,
- reqs[i].nb_sectors, reqs[i].flags,
- multiwrite_cb, mcb,
- true);
- }
-
- return 0;
-}
-
-void bdrv_aio_cancel(BlockDriverAIOCB *acb)
-{
- qemu_aio_ref(acb);
- bdrv_aio_cancel_async(acb);
- while (acb->refcnt > 1) {
- if (acb->aiocb_info->get_aio_context) {
- aio_poll(acb->aiocb_info->get_aio_context(acb), true);
- } else if (acb->bs) {
- aio_poll(bdrv_get_aio_context(acb->bs), true);
- } else {
- abort();
- }
- }
- qemu_aio_unref(acb);
-}
-
-/* Async version of aio cancel. The caller is not blocked if the acb implements
- * cancel_async, otherwise we do nothing and let the request normally complete.
- * In either case the completion callback must be called. */
-void bdrv_aio_cancel_async(BlockDriverAIOCB *acb)
-{
- if (acb->aiocb_info->cancel_async) {
- acb->aiocb_info->cancel_async(acb);
- }
-}
-
-/**************************************************************/
-/* async block device emulation */
-
-typedef struct BlockDriverAIOCBSync {
- BlockDriverAIOCB common;
- QEMUBH *bh;
- int ret;
- /* vector translation state */
- QEMUIOVector *qiov;
- uint8_t *bounce;
- int is_write;
-} BlockDriverAIOCBSync;
-
-static const AIOCBInfo bdrv_em_aiocb_info = {
- .aiocb_size = sizeof(BlockDriverAIOCBSync),
-};
-
-static void bdrv_aio_bh_cb(void *opaque)
-{
- BlockDriverAIOCBSync *acb = opaque;
-
- if (!acb->is_write && acb->ret >= 0) {
- qemu_iovec_from_buf(acb->qiov, 0, acb->bounce, acb->qiov->size);
- }
- qemu_vfree(acb->bounce);
- acb->common.cb(acb->common.opaque, acb->ret);
- qemu_bh_delete(acb->bh);
- acb->bh = NULL;
- qemu_aio_unref(acb);
-}
-
-static BlockDriverAIOCB *bdrv_aio_rw_vector(BlockDriverState *bs,
- int64_t sector_num,
- QEMUIOVector *qiov,
- int nb_sectors,
- BlockDriverCompletionFunc *cb,
- void *opaque,
- int is_write)
-
-{
- BlockDriverAIOCBSync *acb;
-
- acb = qemu_aio_get(&bdrv_em_aiocb_info, bs, cb, opaque);
- acb->is_write = is_write;
- acb->qiov = qiov;
- acb->bounce = qemu_try_blockalign(bs, qiov->size);
- acb->bh = aio_bh_new(bdrv_get_aio_context(bs), bdrv_aio_bh_cb, acb);
-
- if (acb->bounce == NULL) {
- acb->ret = -ENOMEM;
- } else if (is_write) {
- qemu_iovec_to_buf(acb->qiov, 0, acb->bounce, qiov->size);
- acb->ret = bs->drv->bdrv_write(bs, sector_num, acb->bounce, nb_sectors);
- } else {
- acb->ret = bs->drv->bdrv_read(bs, sector_num, acb->bounce, nb_sectors);
- }
-
- qemu_bh_schedule(acb->bh);
-
- return &acb->common;
-}
-
-static BlockDriverAIOCB *bdrv_aio_readv_em(BlockDriverState *bs,
- int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
- BlockDriverCompletionFunc *cb, void *opaque)
-{
- return bdrv_aio_rw_vector(bs, sector_num, qiov, nb_sectors, cb, opaque, 0);
-}
-
-static BlockDriverAIOCB *bdrv_aio_writev_em(BlockDriverState *bs,
- int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
- BlockDriverCompletionFunc *cb, void *opaque)
-{
- return bdrv_aio_rw_vector(bs, sector_num, qiov, nb_sectors, cb, opaque, 1);
-}
-
-
-typedef struct BlockDriverAIOCBCoroutine {
- BlockDriverAIOCB common;
- BlockRequest req;
- bool is_write;
- bool *done;
- QEMUBH* bh;
-} BlockDriverAIOCBCoroutine;
-
-static const AIOCBInfo bdrv_em_co_aiocb_info = {
- .aiocb_size = sizeof(BlockDriverAIOCBCoroutine),
-};
-
-static void bdrv_co_em_bh(void *opaque)
-{
- BlockDriverAIOCBCoroutine *acb = opaque;
-
- acb->common.cb(acb->common.opaque, acb->req.error);
-
- qemu_bh_delete(acb->bh);
- qemu_aio_unref(acb);
-}
-
-/* Invoke bdrv_co_do_readv/bdrv_co_do_writev */
-static void coroutine_fn bdrv_co_do_rw(void *opaque)
-{
- BlockDriverAIOCBCoroutine *acb = opaque;
- BlockDriverState *bs = acb->common.bs;
-
- if (!acb->is_write) {
- acb->req.error = bdrv_co_do_readv(bs, acb->req.sector,
- acb->req.nb_sectors, acb->req.qiov, acb->req.flags);
- } else {
- acb->req.error = bdrv_co_do_writev(bs, acb->req.sector,
- 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);
-}
-
-static BlockDriverAIOCB *bdrv_co_aio_rw_vector(BlockDriverState *bs,
- int64_t sector_num,
- QEMUIOVector *qiov,
- int nb_sectors,
- BdrvRequestFlags flags,
- BlockDriverCompletionFunc *cb,
- void *opaque,
- bool is_write)
-{
- Coroutine *co;
- BlockDriverAIOCBCoroutine *acb;
-
- acb = qemu_aio_get(&bdrv_em_co_aiocb_info, bs, cb, opaque);
- acb->req.sector = sector_num;
- acb->req.nb_sectors = nb_sectors;
- acb->req.qiov = qiov;
- acb->req.flags = flags;
- acb->is_write = is_write;
-
- co = qemu_coroutine_create(bdrv_co_do_rw);
- qemu_coroutine_enter(co, acb);
-
- return &acb->common;
-}
-
-static void coroutine_fn bdrv_aio_flush_co_entry(void *opaque)
-{
- BlockDriverAIOCBCoroutine *acb = opaque;
- 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);
-}
-
-BlockDriverAIOCB *bdrv_aio_flush(BlockDriverState *bs,
- BlockDriverCompletionFunc *cb, void *opaque)
-{
- trace_bdrv_aio_flush(bs, opaque);
-
- Coroutine *co;
- BlockDriverAIOCBCoroutine *acb;
-
- acb = qemu_aio_get(&bdrv_em_co_aiocb_info, bs, cb, opaque);
-
- co = qemu_coroutine_create(bdrv_aio_flush_co_entry);
- qemu_coroutine_enter(co, acb);
-
- return &acb->common;
-}
-
-static void coroutine_fn bdrv_aio_discard_co_entry(void *opaque)
-{
- BlockDriverAIOCBCoroutine *acb = opaque;
- 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);
-}
-
-BlockDriverAIOCB *bdrv_aio_discard(BlockDriverState *bs,
- int64_t sector_num, int nb_sectors,
- BlockDriverCompletionFunc *cb, void *opaque)
-{
- Coroutine *co;
- BlockDriverAIOCBCoroutine *acb;
-
- trace_bdrv_aio_discard(bs, sector_num, nb_sectors, opaque);
-
- acb = qemu_aio_get(&bdrv_em_co_aiocb_info, bs, cb, opaque);
- 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);
-
- return &acb->common;
-}
-
-void bdrv_init(void)
-{
- module_call_init(MODULE_INIT_BLOCK);
-}
-
-void bdrv_init_with_whitelist(void)
-{
- use_bdrv_whitelist = 1;
- bdrv_init();
-}
-
-void *qemu_aio_get(const AIOCBInfo *aiocb_info, BlockDriverState *bs,
- BlockDriverCompletionFunc *cb, void *opaque)
-{
- BlockDriverAIOCB *acb;
-
- acb = g_slice_alloc(aiocb_info->aiocb_size);
- acb->aiocb_info = aiocb_info;
- acb->bs = bs;
- acb->cb = cb;
- acb->opaque = opaque;
- acb->refcnt = 1;
- return acb;
-}
-
-void qemu_aio_ref(void *p)
-{
- BlockDriverAIOCB *acb = p;
- acb->refcnt++;
-}
-
-void qemu_aio_unref(void *p)
-{
- BlockDriverAIOCB *acb = p;
- assert(acb->refcnt > 0);
- if (--acb->refcnt == 0) {
- g_slice_free1(acb->aiocb_info->aiocb_size, acb);
- }
-}
-
-/**************************************************************/
-/* Coroutine block device emulation */
-
-typedef struct CoroutineIOCompletion {
- Coroutine *coroutine;
- int ret;
-} CoroutineIOCompletion;
-
-static void bdrv_co_io_em_complete(void *opaque, int ret)
-{
- CoroutineIOCompletion *co = opaque;
-
- co->ret = ret;
- qemu_coroutine_enter(co->coroutine, NULL);
-}
-
-static int coroutine_fn bdrv_co_io_em(BlockDriverState *bs, int64_t sector_num,
- int nb_sectors, QEMUIOVector *iov,
- bool is_write)
-{
- CoroutineIOCompletion co = {
- .coroutine = qemu_coroutine_self(),
- };
- BlockDriverAIOCB *acb;
-
- if (is_write) {
- acb = bs->drv->bdrv_aio_writev(bs, sector_num, iov, nb_sectors,
- bdrv_co_io_em_complete, &co);
- } else {
- acb = bs->drv->bdrv_aio_readv(bs, sector_num, iov, nb_sectors,
- bdrv_co_io_em_complete, &co);
- }
-
- trace_bdrv_co_io_em(bs, sector_num, nb_sectors, is_write, acb);
- if (!acb) {
- return -EIO;
- }
- qemu_coroutine_yield();
-
- return co.ret;
-}
-
-static int coroutine_fn bdrv_co_readv_em(BlockDriverState *bs,
- int64_t sector_num, int nb_sectors,
- QEMUIOVector *iov)
-{
- return bdrv_co_io_em(bs, sector_num, nb_sectors, iov, false);
-}
-
-static int coroutine_fn bdrv_co_writev_em(BlockDriverState *bs,
- int64_t sector_num, int nb_sectors,
- QEMUIOVector *iov)
-{
- return bdrv_co_io_em(bs, sector_num, nb_sectors, iov, true);
-}
-
-static void coroutine_fn bdrv_flush_co_entry(void *opaque)
-{
- RwCo *rwco = opaque;
-
- rwco->ret = bdrv_co_flush(rwco->bs);
-}
-
-int coroutine_fn bdrv_co_flush(BlockDriverState *bs)
-{
- int ret;
-
- if (!bs || !bdrv_is_inserted(bs) || bdrv_is_read_only(bs)) {
- return 0;
- }
-
- /* Write back cached data to the OS even with cache=unsafe */
- BLKDBG_EVENT(bs->file, BLKDBG_FLUSH_TO_OS);
- if (bs->drv->bdrv_co_flush_to_os) {
- ret = bs->drv->bdrv_co_flush_to_os(bs);
- if (ret < 0) {
- return ret;
- }
- }
-
- /* But don't actually force it to the disk with cache=unsafe */
- if (bs->open_flags & BDRV_O_NO_FLUSH) {
- goto flush_parent;
- }
-
- BLKDBG_EVENT(bs->file, BLKDBG_FLUSH_TO_DISK);
- if (bs->drv->bdrv_co_flush_to_disk) {
- ret = bs->drv->bdrv_co_flush_to_disk(bs);
- } else if (bs->drv->bdrv_aio_flush) {
- BlockDriverAIOCB *acb;
- CoroutineIOCompletion co = {
- .coroutine = qemu_coroutine_self(),
- };
-
- acb = bs->drv->bdrv_aio_flush(bs, bdrv_co_io_em_complete, &co);
- if (acb == NULL) {
- ret = -EIO;
- } else {
- qemu_coroutine_yield();
- ret = co.ret;
- }
- } else {
- /*
- * Some block drivers always operate in either writethrough or unsafe
- * mode and don't support bdrv_flush therefore. Usually qemu doesn't
- * know how the server works (because the behaviour is hardcoded or
- * depends on server-side configuration), so we can't ensure that
- * everything is safe on disk. Returning an error doesn't work because
- * that would break guests even if the server operates in writethrough
- * mode.
- *
- * Let's hope the user knows what he's doing.
- */
- ret = 0;
- }
- if (ret < 0) {
- return ret;
+
+ if (!bs->backing_hd) {
+ return 0;
}
- /* Now flush the underlying protocol. It will also have BDRV_O_NO_FLUSH
- * in the case of cache=unsafe, so there are no useless flushes.
- */
-flush_parent:
- return bdrv_co_flush(bs->file);
+ return 1 + bdrv_get_backing_file_depth(bs->backing_hd);
+}
+
+void bdrv_init(void)
+{
+ module_call_init(MODULE_INIT_BLOCK);
+}
+
+void bdrv_init_with_whitelist(void)
+{
+ use_bdrv_whitelist = 1;
+ bdrv_init();
}
void bdrv_invalidate_cache(BlockDriverState *bs, Error **errp)
return;
}
+ if (!(bs->open_flags & BDRV_O_INCOMING)) {
+ return;
+ }
+ bs->open_flags &= ~BDRV_O_INCOMING;
+
if (bs->drv->bdrv_invalidate_cache) {
bs->drv->bdrv_invalidate_cache(bs, &local_err);
} else if (bs->file) {
}
}
-void bdrv_clear_incoming_migration_all(void)
-{
- BlockDriverState *bs;
-
- QTAILQ_FOREACH(bs, &bdrv_states, device_list) {
- AioContext *aio_context = bdrv_get_aio_context(bs);
-
- aio_context_acquire(aio_context);
- bs->open_flags = bs->open_flags & ~(BDRV_O_INCOMING);
- aio_context_release(aio_context);
- }
-}
-
-int bdrv_flush(BlockDriverState *bs)
-{
- Coroutine *co;
- RwCo rwco = {
- .bs = bs,
- .ret = NOT_DONE,
- };
-
- if (qemu_in_coroutine()) {
- /* Fast-path if already in coroutine context */
- bdrv_flush_co_entry(&rwco);
- } else {
- AioContext *aio_context = bdrv_get_aio_context(bs);
-
- co = qemu_coroutine_create(bdrv_flush_co_entry);
- qemu_coroutine_enter(co, &rwco);
- while (rwco.ret == NOT_DONE) {
- aio_poll(aio_context, true);
- }
- }
-
- return rwco.ret;
-}
-
-typedef struct DiscardCo {
- BlockDriverState *bs;
- int64_t sector_num;
- int nb_sectors;
- int ret;
-} DiscardCo;
-static void coroutine_fn bdrv_discard_co_entry(void *opaque)
-{
- DiscardCo *rwco = opaque;
-
- 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;
-
- if (!bs->drv) {
- return -ENOMEDIUM;
- } else if (bdrv_check_request(bs, sector_num, nb_sectors)) {
- return -EIO;
- } else if (bs->read_only) {
- return -EROFS;
- }
-
- bdrv_reset_dirty(bs, sector_num, nb_sectors);
-
- /* Do nothing if disabled. */
- if (!(bs->open_flags & BDRV_O_UNMAP)) {
- return 0;
- }
-
- if (!bs->drv->bdrv_co_discard && !bs->drv->bdrv_aio_discard) {
- return 0;
- }
-
- max_discard = bs->bl.max_discard ? bs->bl.max_discard : MAX_DISCARD_DEFAULT;
- while (nb_sectors > 0) {
- int ret;
- int num = nb_sectors;
-
- /* align request */
- if (bs->bl.discard_alignment &&
- num >= bs->bl.discard_alignment &&
- sector_num % bs->bl.discard_alignment) {
- if (num > bs->bl.discard_alignment) {
- num = bs->bl.discard_alignment;
- }
- num -= sector_num % bs->bl.discard_alignment;
- }
-
- /* limit request size */
- if (num > max_discard) {
- num = max_discard;
- }
-
- if (bs->drv->bdrv_co_discard) {
- ret = bs->drv->bdrv_co_discard(bs, sector_num, num);
- } else {
- BlockDriverAIOCB *acb;
- CoroutineIOCompletion co = {
- .coroutine = qemu_coroutine_self(),
- };
-
- acb = bs->drv->bdrv_aio_discard(bs, sector_num, nb_sectors,
- bdrv_co_io_em_complete, &co);
- if (acb == NULL) {
- return -EIO;
- } else {
- qemu_coroutine_yield();
- ret = co.ret;
- }
- }
- if (ret && ret != -ENOTSUP) {
- return ret;
- }
-
- sector_num += num;
- nb_sectors -= num;
- }
- return 0;
-}
-
-int bdrv_discard(BlockDriverState *bs, int64_t sector_num, int nb_sectors)
-{
- Coroutine *co;
- DiscardCo rwco = {
- .bs = bs,
- .sector_num = sector_num,
- .nb_sectors = nb_sectors,
- .ret = NOT_DONE,
- };
-
- if (qemu_in_coroutine()) {
- /* Fast-path if already in coroutine context */
- bdrv_discard_co_entry(&rwco);
- } else {
- AioContext *aio_context = bdrv_get_aio_context(bs);
-
- co = qemu_coroutine_create(bdrv_discard_co_entry);
- qemu_coroutine_enter(co, &rwco);
- while (rwco.ret == NOT_DONE) {
- aio_poll(aio_context, true);
- }
- }
-
- return rwco.ret;
-}
-
/**************************************************************/
/* removable device support */
void bdrv_eject(BlockDriverState *bs, bool eject_flag)
{
BlockDriver *drv = bs->drv;
+ const char *device_name;
if (drv && drv->bdrv_eject) {
drv->bdrv_eject(bs, eject_flag);
}
- if (bs->device_name[0] != '\0') {
- qapi_event_send_device_tray_moved(bdrv_get_device_name(bs),
+ device_name = bdrv_get_device_name(bs);
+ if (device_name[0] != '\0') {
+ qapi_event_send_device_tray_moved(device_name,
eject_flag, &error_abort);
}
}
}
}
-/* needed for generic scsi interface */
+void bdrv_set_guest_block_size(BlockDriverState *bs, int align)
+{
+ bs->guest_block_size = align;
+}
-int bdrv_ioctl(BlockDriverState *bs, unsigned long int req, void *buf)
+BdrvDirtyBitmap *bdrv_find_dirty_bitmap(BlockDriverState *bs, const char *name)
{
- BlockDriver *drv = bs->drv;
+ BdrvDirtyBitmap *bm;
- if (drv && drv->bdrv_ioctl)
- return drv->bdrv_ioctl(bs, req, buf);
- return -ENOTSUP;
+ assert(name);
+ QLIST_FOREACH(bm, &bs->dirty_bitmaps, list) {
+ if (bm->name && !strcmp(name, bm->name)) {
+ return bm;
+ }
+ }
+ return NULL;
}
-BlockDriverAIOCB *bdrv_aio_ioctl(BlockDriverState *bs,
- unsigned long int req, void *buf,
- BlockDriverCompletionFunc *cb, void *opaque)
+void bdrv_dirty_bitmap_make_anon(BdrvDirtyBitmap *bitmap)
{
- BlockDriver *drv = bs->drv;
+ assert(!bdrv_dirty_bitmap_frozen(bitmap));
+ g_free(bitmap->name);
+ bitmap->name = NULL;
+}
- if (drv && drv->bdrv_aio_ioctl)
- return drv->bdrv_aio_ioctl(bs, req, buf, cb, opaque);
- return 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);
+
+ 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");
+ errno = -bitmap_size;
+ return NULL;
+ }
+ bitmap = g_new0(BdrvDirtyBitmap, 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;
}
-void bdrv_set_guest_block_size(BlockDriverState *bs, int align)
+bool bdrv_dirty_bitmap_frozen(BdrvDirtyBitmap *bitmap)
{
- bs->guest_block_size = align;
+ return bitmap->successor;
}
-void *qemu_blockalign(BlockDriverState *bs, size_t size)
+bool bdrv_dirty_bitmap_enabled(BdrvDirtyBitmap *bitmap)
{
- return qemu_memalign(bdrv_opt_mem_align(bs), size);
+ return !(bitmap->disabled || bitmap->successor);
}
-void *qemu_try_blockalign(BlockDriverState *bs, size_t size)
+/**
+ * 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)
{
- size_t align = bdrv_opt_mem_align(bs);
+ 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);
- /* Ensure that NULL is never returned on success */
- assert(align > 0);
- if (size == 0) {
- size = align;
+ /* Create an anonymous successor */
+ granularity = bdrv_dirty_bitmap_granularity(bitmap);
+ child = bdrv_create_dirty_bitmap(bs, granularity, NULL, errp);
+ if (!child) {
+ return -1;
}
- return qemu_try_memalign(align, size);
+ /* 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;
}
-/*
- * Check if all memory in this vector is sector aligned.
+/**
+ * For a bitmap with a successor, yield our name to the successor,
+ * delete the old bitmap, and return a handle to the new bitmap.
*/
-bool bdrv_qiov_is_aligned(BlockDriverState *bs, QEMUIOVector *qiov)
+BdrvDirtyBitmap *bdrv_dirty_bitmap_abdicate(BlockDriverState *bs,
+ BdrvDirtyBitmap *bitmap,
+ Error **errp)
{
- int i;
- size_t alignment = bdrv_opt_mem_align(bs);
+ char *name;
+ BdrvDirtyBitmap *successor = bitmap->successor;
- for (i = 0; i < qiov->niov; i++) {
- if ((uintptr_t) qiov->iov[i].iov_base % alignment) {
- return false;
- }
- if (qiov->iov[i].iov_len % alignment) {
- return false;
- }
+ if (successor == NULL) {
+ error_setg(errp, "Cannot relinquish control if "
+ "there's no successor present");
+ return NULL;
}
- return true;
+ name = bitmap->name;
+ bitmap->name = NULL;
+ successor->name = name;
+ bitmap->successor = NULL;
+ bdrv_release_dirty_bitmap(bs, bitmap);
+
+ return successor;
}
-BdrvDirtyBitmap *bdrv_create_dirty_bitmap(BlockDriverState *bs, int granularity,
- Error **errp)
+/**
+ * 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)
{
- int64_t bitmap_size;
- BdrvDirtyBitmap *bitmap;
+ BdrvDirtyBitmap *successor = parent->successor;
- assert((granularity & (granularity - 1)) == 0);
+ if (!successor) {
+ error_setg(errp, "Cannot reclaim a successor when none is present");
+ return NULL;
+ }
- granularity >>= BDRV_SECTOR_BITS;
- assert(granularity);
- bitmap_size = bdrv_nb_sectors(bs);
- if (bitmap_size < 0) {
- error_setg_errno(errp, -bitmap_size, "could not get length of device");
- errno = -bitmap_size;
+ if (!hbitmap_merge(parent->bitmap, successor->bitmap)) {
+ error_setg(errp, "Merging of parent and successor bitmap failed");
return NULL;
}
- bitmap = g_new0(BdrvDirtyBitmap, 1);
- bitmap->bitmap = hbitmap_alloc(bitmap_size, ffs(granularity) - 1);
- QLIST_INSERT_HEAD(&bs->dirty_bitmaps, bitmap, list);
- return bitmap;
+ 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_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);
+}
+
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)
+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",
- bs->device_name, error_get_pretty(blocker->reason));
+ 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;
+ }
+
+ if (!drv->create_opts) {
+ error_setg(errp, "Format driver '%s' does not support image creation",
+ drv->format_name);
+ return;
+ }
+
+ if (!proto_drv->create_opts) {
+ error_setg(errp, "Protocol driver '%s' does not support image creation",
+ proto_drv->format_name);
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) {
- error_setg_errno(errp, -ret, "Could not open '%s': %s",
- backing_file,
- error_get_pretty(local_err));
- error_free(local_err);
- local_err = NULL;
goto out;
}
size = bdrv_getlength(bs);
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 {
}
if (!quiet) {
- printf("Formatting '%s', fmt=%s ", filename, fmt);
- qemu_opts_print(opts);
+ printf("Formatting '%s', fmt=%s", filename, fmt);
+ qemu_opts_print(opts, " ");
puts("");
}
abort();
}
-void bdrv_add_before_write_notifier(BlockDriverState *bs,
- NotifierWithReturn *notifier)
-{
- notifier_with_return_list_add(&bs->before_write_notifiers, notifier);
-}
-
-int bdrv_amend_options(BlockDriverState *bs, QemuOpts *opts)
+int bdrv_amend_options(BlockDriverState *bs, QemuOpts *opts,
+ BlockDriverAmendStatusCB *status_cb)
{
if (!bs->drv->bdrv_amend_options) {
return -ENOTSUP;
}
- return bs->drv->bdrv_amend_options(bs, opts);
+ return bs->drv->bdrv_amend_options(bs, opts, status_cb);
}
/* This function will be called by the bdrv_recurse_is_first_non_filter method
BlockDriverState *check_to_replace_node(const char *node_name, Error **errp)
{
BlockDriverState *to_replace_bs = bdrv_find_node(node_name);
+ AioContext *aio_context;
+
if (!to_replace_bs) {
error_setg(errp, "Node name '%s' not found", node_name);
return NULL;
}
+ aio_context = bdrv_get_aio_context(to_replace_bs);
+ aio_context_acquire(aio_context);
+
if (bdrv_op_is_blocked(to_replace_bs, BLOCK_OP_TYPE_REPLACE, errp)) {
- return NULL;
+ to_replace_bs = NULL;
+ goto out;
}
/* We don't want arbitrary node of the BDS chain to be replaced only the top
*/
if (!bdrv_is_first_non_filter(to_replace_bs)) {
error_setg(errp, "Only top most non filter can be replaced");
- return NULL;
+ to_replace_bs = NULL;
+ goto out;
}
+out:
+ aio_context_release(aio_context);
return to_replace_bs;
}
-void bdrv_io_plug(BlockDriverState *bs)
-{
- BlockDriver *drv = bs->drv;
- if (drv && drv->bdrv_io_plug) {
- drv->bdrv_io_plug(bs);
- } else if (bs->file) {
- bdrv_io_plug(bs->file);
- }
-}
-
-void bdrv_io_unplug(BlockDriverState *bs)
-{
- BlockDriver *drv = bs->drv;
- if (drv && drv->bdrv_io_unplug) {
- drv->bdrv_io_unplug(bs);
- } else if (bs->file) {
- bdrv_io_unplug(bs->file);
- }
-}
-
-void bdrv_flush_io_queue(BlockDriverState *bs)
-{
- BlockDriver *drv = bs->drv;
- if (drv && drv->bdrv_flush_io_queue) {
- drv->bdrv_flush_io_queue(bs);
- } else if (bs->file) {
- bdrv_flush_io_queue(bs->file);
- }
-}
-
static bool append_open_options(QDict *d, BlockDriverState *bs)
{
const QDictEntry *entry;
projects / mirror_qemu.git / blobdiff