qemu/block/blkverify.c

Ignoring revisions in .git-blame-ignore-revs. Click here to bypass and see the normal blame view.

339 lines
9.9 KiB
C
Raw Normal View History

/*
* Block protocol for block driver correctness testing
*
* Copyright (C) 2010 IBM, Corp.
*
* This work is licensed under the terms of the GNU GPL, version 2 or later.
* See the COPYING file in the top-level directory.
*/
#include "qemu/osdep.h"
2016-03-14 11:01:28 +03:00
#include "qapi/error.h"
#include "qemu/sockets.h" /* for EINPROGRESS on Windows */
#include "block/block-io.h"
#include "block/block_int.h"
#include "qapi/qmp/qdict.h"
#include "qapi/qmp/qstring.h"
#include "qemu/cutils.h"
#include "qemu/module.h"
#include "qemu/option.h"
#include "qemu/memalign.h"
typedef struct {
BdrvChild *test_file;
} BDRVBlkverifyState;
typedef struct BlkverifyRequest {
Coroutine *co;
BlockDriverState *bs;
/* Request metadata */
bool is_write;
uint64_t offset;
uint64_t bytes;
int flags;
int (*request_fn)(BdrvChild *, int64_t, int64_t, QEMUIOVector *,
BdrvRequestFlags);
int ret; /* test image result */
int raw_ret; /* raw image result */
unsigned int done; /* completion counter */
QEMUIOVector *qiov; /* user I/O vector */
QEMUIOVector *raw_qiov; /* cloned I/O vector for raw file */
} BlkverifyRequest;
static void G_GNUC_PRINTF(2, 3) blkverify_err(BlkverifyRequest *r,
const char *fmt, ...)
{
va_list ap;
va_start(ap, fmt);
fprintf(stderr, "blkverify: %s offset=%" PRId64 " bytes=%" PRId64 " ",
r->is_write ? "write" : "read", r->offset, r->bytes);
vfprintf(stderr, fmt, ap);
fprintf(stderr, "\n");
va_end(ap);
exit(1);
}
/* Valid blkverify filenames look like blkverify:path/to/raw_image:path/to/image */
static void blkverify_parse_filename(const char *filename, QDict *options,
Error **errp)
{
const char *c;
QString *raw_path;
/* Parse the blkverify: prefix */
if (!strstart(filename, "blkverify:", &filename)) {
/* There was no prefix; therefore, all options have to be already
present in the QDict (except for the filename) */
qdict_put_str(options, "x-image", filename);
return;
}
/* Parse the raw image filename */
c = strchr(filename, ':');
if (c == NULL) {
error_setg(errp, "blkverify requires raw copy and original image path");
return;
}
/* TODO Implement option pass-through and set raw.filename here */
raw_path = qstring_from_substr(filename, 0, c - filename);
qdict_put(options, "x-raw", raw_path);
/* TODO Allow multi-level nesting and set file.filename here */
filename = c + 1;
qdict_put_str(options, "x-image", filename);
}
static QemuOptsList runtime_opts = {
.name = "blkverify",
.head = QTAILQ_HEAD_INITIALIZER(runtime_opts.head),
.desc = {
{
.name = "x-raw",
.type = QEMU_OPT_STRING,
.help = "[internal use only, will be removed]",
},
{
.name = "x-image",
.type = QEMU_OPT_STRING,
.help = "[internal use only, will be removed]",
},
{ /* end of list */ }
},
};
static int blkverify_open(BlockDriverState *bs, QDict *options, int flags,
Error **errp)
{
BDRVBlkverifyState *s = bs->opaque;
QemuOpts *opts;
int ret;
opts = qemu_opts_create(&runtime_opts, NULL, 0, &error_abort);
if (!qemu_opts_absorb_qdict(opts, options, errp)) {
ret = -EINVAL;
goto fail;
}
/* Open the raw file */
ret = bdrv_open_file_child(qemu_opt_get(opts, "x-raw"), options, "raw",
bs, errp);
if (ret < 0) {
goto fail;
}
/* Open the test file */
s->test_file = bdrv_open_child(qemu_opt_get(opts, "x-image"), options,
"test", bs, &child_of_bds, BDRV_CHILD_DATA,
false, errp);
if (!s->test_file) {
ret = -EINVAL;
goto fail;
}
bs->supported_write_flags = BDRV_REQ_WRITE_UNCHANGED;
bs->supported_zero_flags = BDRV_REQ_WRITE_UNCHANGED;
ret = 0;
fail:
qemu_opts_del(opts);
return ret;
}
static void blkverify_close(BlockDriverState *bs)
{
BDRVBlkverifyState *s = bs->opaque;
bdrv_graph_wrlock(NULL);
bdrv_unref_child(bs, s->test_file);
s->test_file = NULL;
bdrv_graph_wrunlock();
}
static int64_t coroutine_fn GRAPH_RDLOCK
blkverify_co_getlength(BlockDriverState *bs)
{
BDRVBlkverifyState *s = bs->opaque;
2023-01-13 23:42:04 +03:00
return bdrv_co_getlength(s->test_file->bs);
}
static void coroutine_fn blkverify_do_test_req(void *opaque)
{
BlkverifyRequest *r = opaque;
BDRVBlkverifyState *s = r->bs->opaque;
r->ret = r->request_fn(s->test_file, r->offset, r->bytes, r->qiov,
r->flags);
r->done++;
qemu_coroutine_enter_if_inactive(r->co);
}
static void coroutine_fn blkverify_do_raw_req(void *opaque)
{
BlkverifyRequest *r = opaque;
r->raw_ret = r->request_fn(r->bs->file, r->offset, r->bytes, r->raw_qiov,
r->flags);
r->done++;
qemu_coroutine_enter_if_inactive(r->co);
}
static int coroutine_fn
blkverify_co_prwv(BlockDriverState *bs, BlkverifyRequest *r, uint64_t offset,
uint64_t bytes, QEMUIOVector *qiov, QEMUIOVector *raw_qiov,
int flags, bool is_write)
{
Coroutine *co_a, *co_b;
*r = (BlkverifyRequest) {
.co = qemu_coroutine_self(),
.bs = bs,
.offset = offset,
.bytes = bytes,
.qiov = qiov,
.raw_qiov = raw_qiov,
.flags = flags,
.is_write = is_write,
.request_fn = is_write ? bdrv_co_pwritev : bdrv_co_preadv,
};
co_a = qemu_coroutine_create(blkverify_do_test_req, r);
co_b = qemu_coroutine_create(blkverify_do_raw_req, r);
qemu_coroutine_enter(co_a);
qemu_coroutine_enter(co_b);
while (r->done < 2) {
qemu_coroutine_yield();
}
if (r->ret != r->raw_ret) {
blkverify_err(r, "return value mismatch %d != %d", r->ret, r->raw_ret);
}
return r->ret;
}
static int coroutine_fn
block: use int64_t instead of uint64_t in driver read handlers We are generally moving to int64_t for both offset and bytes parameters on all io paths. Main motivation is realization of 64-bit write_zeroes operation for fast zeroing large disk chunks, up to the whole disk. We chose signed type, to be consistent with off_t (which is signed) and with possibility for signed return type (where negative value means error). So, convert driver read handlers parameters which are already 64bit to signed type. While being here, convert also flags parameter to be BdrvRequestFlags. Now let's consider all callers. Simple git grep '\->bdrv_\(aio\|co\)_preadv\(_part\)\?' shows that's there three callers of driver function: bdrv_driver_preadv() in block/io.c, passes int64_t, checked by bdrv_check_qiov_request() to be non-negative. qcow2_load_vmstate() does bdrv_check_qiov_request(). do_perform_cow_read() has uint64_t argument. And a lot of things in qcow2 driver are uint64_t, so converting it is big job. But we must not work with requests that don't satisfy bdrv_check_qiov_request(), so let's just assert it here. Still, the functions may be called directly, not only by drv->... Let's check: git grep '\.bdrv_\(aio\|co\)_preadv\(_part\)\?\s*=' | \ awk '{print $4}' | sed 's/,//' | sed 's/&//' | sort | uniq | \ while read func; do git grep "$func(" | \ grep -v "$func(BlockDriverState"; done The only one such caller: QEMUIOVector qiov = QEMU_IOVEC_INIT_BUF(qiov, &data, 1); ... ret = bdrv_replace_test_co_preadv(bs, 0, 1, &qiov, 0); in tests/unit/test-bdrv-drain.c, and it's OK obviously. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Message-Id: <20210903102807.27127-4-vsementsov@virtuozzo.com> Reviewed-by: Eric Blake <eblake@redhat.com> [eblake: fix typos] Signed-off-by: Eric Blake <eblake@redhat.com>
2021-09-03 13:27:59 +03:00
blkverify_co_preadv(BlockDriverState *bs, int64_t offset, int64_t bytes,
QEMUIOVector *qiov, BdrvRequestFlags flags)
{
BlkverifyRequest r;
QEMUIOVector raw_qiov;
void *buf;
ssize_t cmp_offset;
int ret;
buf = qemu_blockalign(bs->file->bs, qiov->size);
qemu_iovec_init(&raw_qiov, qiov->niov);
qemu_iovec_clone(&raw_qiov, qiov, buf);
block: add BDRV_REQ_REGISTERED_BUF request flag Block drivers may optimize I/O requests accessing buffers previously registered with bdrv_register_buf(). Checking whether all elements of a request's QEMUIOVector are within previously registered buffers is expensive, so we need a hint from the user to avoid costly checks. Add a BDRV_REQ_REGISTERED_BUF request flag to indicate that all QEMUIOVector elements in an I/O request are known to be within previously registered buffers. Always pass the flag through to driver read/write functions. There is little harm in passing the flag to a driver that does not use it. Passing the flag to drivers avoids changes across many block drivers. Filter drivers would need to explicitly support the flag and pass through to their children when the children support it. That's a lot of code changes and it's hard to remember to do that everywhere, leading to silent reduced performance when the flag is accidentally dropped. The only problematic scenario with the approach in this patch is when a driver passes the flag through to internal I/O requests that don't use the same I/O buffer. In that case the hint may be set when it should actually be clear. This is a rare case though so the risk is low. Some drivers have assert(!flags), which no longer works when BDRV_REQ_REGISTERED_BUF is passed in. These assertions aren't very useful anyway since the functions are called almost exclusively by bdrv_driver_preadv/pwritev() so if we get flags handling right there then the assertion is not needed. Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 20221013185908.1297568-7-stefanha@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
2022-10-13 21:59:01 +03:00
ret = blkverify_co_prwv(bs, &r, offset, bytes, qiov, &raw_qiov,
flags & ~BDRV_REQ_REGISTERED_BUF, false);
cmp_offset = qemu_iovec_compare(qiov, &raw_qiov);
if (cmp_offset != -1) {
blkverify_err(&r, "contents mismatch at offset %" PRId64,
offset + cmp_offset);
}
qemu_iovec_destroy(&raw_qiov);
qemu_vfree(buf);
return ret;
}
static int coroutine_fn
block: use int64_t instead of uint64_t in driver write handlers We are generally moving to int64_t for both offset and bytes parameters on all io paths. Main motivation is realization of 64-bit write_zeroes operation for fast zeroing large disk chunks, up to the whole disk. We chose signed type, to be consistent with off_t (which is signed) and with possibility for signed return type (where negative value means error). So, convert driver write handlers parameters which are already 64bit to signed type. While being here, convert also flags parameter to be BdrvRequestFlags. Now let's consider all callers. Simple git grep '\->bdrv_\(aio\|co\)_pwritev\(_part\)\?' shows that's there three callers of driver function: bdrv_driver_pwritev() and bdrv_driver_pwritev_compressed() in block/io.c, both pass int64_t, checked by bdrv_check_qiov_request() to be non-negative. qcow2_save_vmstate() does bdrv_check_qiov_request(). Still, the functions may be called directly, not only by drv->... Let's check: git grep '\.bdrv_\(aio\|co\)_pwritev\(_part\)\?\s*=' | \ awk '{print $4}' | sed 's/,//' | sed 's/&//' | sort | uniq | \ while read func; do git grep "$func(" | \ grep -v "$func(BlockDriverState"; done shows several callers: qcow2: qcow2_co_truncate() write at most up to @offset, which is checked in generic qcow2_co_truncate() by bdrv_check_request(). qcow2_co_pwritev_compressed_task() pass the request (or part of the request) that already went through normal write path, so it should be OK qcow: qcow_co_pwritev_compressed() pass int64_t, it's updated by this patch quorum: quorum_co_pwrite_zeroes() pass int64_t and int - OK throttle: throttle_co_pwritev_compressed() pass int64_t, it's updated by this patch vmdk: vmdk_co_pwritev_compressed() pass int64_t, it's updated by this patch Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Message-Id: <20210903102807.27127-5-vsementsov@virtuozzo.com> Reviewed-by: Eric Blake <eblake@redhat.com> Signed-off-by: Eric Blake <eblake@redhat.com>
2021-09-03 13:28:00 +03:00
blkverify_co_pwritev(BlockDriverState *bs, int64_t offset, int64_t bytes,
QEMUIOVector *qiov, BdrvRequestFlags flags)
{
BlkverifyRequest r;
return blkverify_co_prwv(bs, &r, offset, bytes, qiov, qiov, flags, true);
}
static int coroutine_fn GRAPH_RDLOCK blkverify_co_flush(BlockDriverState *bs)
{
BDRVBlkverifyState *s = bs->opaque;
/* Only flush test file, the raw file is not important */
return bdrv_co_flush(s->test_file->bs);
}
static bool GRAPH_RDLOCK
blkverify_recurse_can_replace(BlockDriverState *bs,
BlockDriverState *to_replace)
{
BDRVBlkverifyState *s = bs->opaque;
/*
* blkverify quits the whole qemu process if there is a mismatch
* between bs->file->bs and s->test_file->bs. Therefore, we know
* know that both must match bs and we can recurse down to either.
*/
return bdrv_recurse_can_replace(bs->file->bs, to_replace) ||
bdrv_recurse_can_replace(s->test_file->bs, to_replace);
}
static void blkverify_refresh_filename(BlockDriverState *bs)
{
BDRVBlkverifyState *s = bs->opaque;
if (bs->file->bs->exact_filename[0]
&& s->test_file->bs->exact_filename[0])
{
int ret = snprintf(bs->exact_filename, sizeof(bs->exact_filename),
"blkverify:%s:%s",
bs->file->bs->exact_filename,
s->test_file->bs->exact_filename);
if (ret >= sizeof(bs->exact_filename)) {
/* An overflow makes the filename unusable, so do not report any */
bs->exact_filename[0] = 0;
}
}
}
static char *blkverify_dirname(BlockDriverState *bs, Error **errp)
{
/* In general, there are two BDSs with different dirnames below this one;
* so there is no unique dirname we could return (unless both are equal by
* chance). Therefore, to be consistent, just always return NULL. */
error_setg(errp, "Cannot generate a base directory for blkverify nodes");
return NULL;
}
static BlockDriver bdrv_blkverify = {
.format_name = "blkverify",
.protocol_name = "blkverify",
.instance_size = sizeof(BDRVBlkverifyState),
.bdrv_parse_filename = blkverify_parse_filename,
.bdrv_file_open = blkverify_open,
.bdrv_close = blkverify_close,
.bdrv_child_perm = bdrv_default_perms,
2023-01-13 23:42:04 +03:00
.bdrv_co_getlength = blkverify_co_getlength,
.bdrv_refresh_filename = blkverify_refresh_filename,
.bdrv_dirname = blkverify_dirname,
.bdrv_co_preadv = blkverify_co_preadv,
.bdrv_co_pwritev = blkverify_co_pwritev,
.bdrv_co_flush = blkverify_co_flush,
.is_filter = true,
.bdrv_recurse_can_replace = blkverify_recurse_can_replace,
};
static void bdrv_blkverify_init(void)
{
bdrv_register(&bdrv_blkverify);
}
block_init(bdrv_blkverify_init);