* [PULL 01/15] block/vhdx: add check for truncated image files
2019-10-14 16:03 [PULL 00/15] Block layer patches Kevin Wolf
@ 2019-10-14 16:03 ` Kevin Wolf
2019-10-14 16:03 ` [PULL 02/15] block: implement bdrv_snapshot_goto for blkreplay Kevin Wolf
` (8 subsequent siblings)
9 siblings, 0 replies; 15+ messages in thread
From: Kevin Wolf @ 2019-10-14 16:03 UTC (permalink / raw)
To: qemu-block; +Cc: kwolf, peter.maydell, qemu-devel
From: Peter Lieven <pl@kamp.de>
qemu is currently not able to detect truncated vhdx image files.
Add a basic check if all allocated blocks are reachable at open and
report all errors during bdrv_co_check.
Signed-off-by: Peter Lieven <pl@kamp.de>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
---
block/vhdx.c | 120 +++++++++++++++++++++++++++++++++++++++++++--------
1 file changed, 103 insertions(+), 17 deletions(-)
diff --git a/block/vhdx.c b/block/vhdx.c
index 6a09d0a55c..371f226286 100644
--- a/block/vhdx.c
+++ b/block/vhdx.c
@@ -24,6 +24,7 @@
#include "qemu/option.h"
#include "qemu/crc32c.h"
#include "qemu/bswap.h"
+#include "qemu/error-report.h"
#include "vhdx.h"
#include "migration/blocker.h"
#include "qemu/uuid.h"
@@ -235,6 +236,9 @@ static int vhdx_region_check(BDRVVHDXState *s, uint64_t start, uint64_t length)
end = start + length;
QLIST_FOREACH(r, &s->regions, entries) {
if (!((start >= r->end) || (end <= r->start))) {
+ error_report("VHDX region %" PRIu64 "-%" PRIu64 " overlaps with "
+ "region %" PRIu64 "-%." PRIu64, start, end, r->start,
+ r->end);
ret = -EINVAL;
goto exit;
}
@@ -877,6 +881,95 @@ static void vhdx_calc_bat_entries(BDRVVHDXState *s)
}
+static int vhdx_check_bat_entries(BlockDriverState *bs, int *errcnt)
+{
+ BDRVVHDXState *s = bs->opaque;
+ int64_t image_file_size = bdrv_getlength(bs->file->bs);
+ uint64_t payblocks = s->chunk_ratio;
+ uint64_t i;
+ int ret = 0;
+
+ if (image_file_size < 0) {
+ error_report("Could not determinate VHDX image file size.");
+ return image_file_size;
+ }
+
+ for (i = 0; i < s->bat_entries; i++) {
+ if ((s->bat[i] & VHDX_BAT_STATE_BIT_MASK) ==
+ PAYLOAD_BLOCK_FULLY_PRESENT) {
+ uint64_t offset = s->bat[i] & VHDX_BAT_FILE_OFF_MASK;
+ /*
+ * Allow that the last block exists only partially. The VHDX spec
+ * states that the image file can only grow in blocksize increments,
+ * but QEMU created images with partial last blocks in the past.
+ */
+ uint32_t block_length = MIN(s->block_size,
+ bs->total_sectors * BDRV_SECTOR_SIZE - i * s->block_size);
+ /*
+ * Check for BAT entry overflow.
+ */
+ if (offset > INT64_MAX - s->block_size) {
+ error_report("VHDX BAT entry %" PRIu64 " offset overflow.", i);
+ ret = -EINVAL;
+ if (!errcnt) {
+ break;
+ }
+ (*errcnt)++;
+ }
+ /*
+ * Check if fully allocated BAT entries do not reside after
+ * end of the image file.
+ */
+ if (offset >= image_file_size) {
+ error_report("VHDX BAT entry %" PRIu64 " start offset %" PRIu64
+ " points after end of file (%" PRIi64 "). Image"
+ " has probably been truncated.",
+ i, offset, image_file_size);
+ ret = -EINVAL;
+ if (!errcnt) {
+ break;
+ }
+ (*errcnt)++;
+ } else if (offset + block_length > image_file_size) {
+ error_report("VHDX BAT entry %" PRIu64 " end offset %" PRIu64
+ " points after end of file (%" PRIi64 "). Image"
+ " has probably been truncated.",
+ i, offset + block_length - 1, image_file_size);
+ ret = -EINVAL;
+ if (!errcnt) {
+ break;
+ }
+ (*errcnt)++;
+ }
+
+ /*
+ * verify populated BAT field file offsets against
+ * region table and log entries
+ */
+ if (payblocks--) {
+ /* payload bat entries */
+ int ret2;
+ ret2 = vhdx_region_check(s, offset, s->block_size);
+ if (ret2 < 0) {
+ ret = -EINVAL;
+ if (!errcnt) {
+ break;
+ }
+ (*errcnt)++;
+ }
+ } else {
+ payblocks = s->chunk_ratio;
+ /*
+ * Once differencing files are supported, verify sector bitmap
+ * blocks here
+ */
+ }
+ }
+ }
+
+ return ret;
+}
+
static void vhdx_close(BlockDriverState *bs)
{
BDRVVHDXState *s = bs->opaque;
@@ -981,25 +1074,15 @@ static int vhdx_open(BlockDriverState *bs, QDict *options, int flags,
goto fail;
}
- uint64_t payblocks = s->chunk_ratio;
- /* endian convert, and verify populated BAT field file offsets against
- * region table and log entries */
+ /* endian convert populated BAT field entires */
for (i = 0; i < s->bat_entries; i++) {
s->bat[i] = le64_to_cpu(s->bat[i]);
- if (payblocks--) {
- /* payload bat entries */
- if ((s->bat[i] & VHDX_BAT_STATE_BIT_MASK) ==
- PAYLOAD_BLOCK_FULLY_PRESENT) {
- ret = vhdx_region_check(s, s->bat[i] & VHDX_BAT_FILE_OFF_MASK,
- s->block_size);
- if (ret < 0) {
- goto fail;
- }
- }
- } else {
- payblocks = s->chunk_ratio;
- /* Once differencing files are supported, verify sector bitmap
- * blocks here */
+ }
+
+ if (!(flags & BDRV_O_CHECK)) {
+ ret = vhdx_check_bat_entries(bs, NULL);
+ if (ret < 0) {
+ goto fail;
}
}
@@ -2072,6 +2155,9 @@ static int coroutine_fn vhdx_co_check(BlockDriverState *bs,
if (s->log_replayed_on_open) {
result->corruptions_fixed++;
}
+
+ vhdx_check_bat_entries(bs, &result->corruptions);
+
return 0;
}
--
2.20.1
^ permalink raw reply related [flat|nested] 15+ messages in thread* [PULL 02/15] block: implement bdrv_snapshot_goto for blkreplay
2019-10-14 16:03 [PULL 00/15] Block layer patches Kevin Wolf
2019-10-14 16:03 ` [PULL 01/15] block/vhdx: add check for truncated image files Kevin Wolf
@ 2019-10-14 16:03 ` Kevin Wolf
2019-10-14 16:03 ` [PULL 03/15] replay: disable default snapshot for record/replay Kevin Wolf
` (7 subsequent siblings)
9 siblings, 0 replies; 15+ messages in thread
From: Kevin Wolf @ 2019-10-14 16:03 UTC (permalink / raw)
To: qemu-block; +Cc: kwolf, peter.maydell, qemu-devel
From: Pavel Dovgalyuk <pavel.dovgaluk@ispras.ru>
This patch enables making snapshots with blkreplay used in
block devices.
This function is required to make bdrv_snapshot_goto without
calling .bdrv_open which is not implemented.
Signed-off-by: Pavel Dovgalyuk <pavel.dovgaluk@ispras.ru>
Acked-by: Kevin Wolf <kwolf@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
---
block/blkreplay.c | 8 ++++++++
1 file changed, 8 insertions(+)
diff --git a/block/blkreplay.c b/block/blkreplay.c
index 2b7931b940..c96ac8f4bc 100644
--- a/block/blkreplay.c
+++ b/block/blkreplay.c
@@ -126,6 +126,12 @@ static int coroutine_fn blkreplay_co_flush(BlockDriverState *bs)
return ret;
}
+static int blkreplay_snapshot_goto(BlockDriverState *bs,
+ const char *snapshot_id)
+{
+ return bdrv_snapshot_goto(bs->file->bs, snapshot_id, NULL);
+}
+
static BlockDriver bdrv_blkreplay = {
.format_name = "blkreplay",
.instance_size = 0,
@@ -140,6 +146,8 @@ static BlockDriver bdrv_blkreplay = {
.bdrv_co_pwrite_zeroes = blkreplay_co_pwrite_zeroes,
.bdrv_co_pdiscard = blkreplay_co_pdiscard,
.bdrv_co_flush = blkreplay_co_flush,
+
+ .bdrv_snapshot_goto = blkreplay_snapshot_goto,
};
static void bdrv_blkreplay_init(void)
--
2.20.1
^ permalink raw reply related [flat|nested] 15+ messages in thread* [PULL 03/15] replay: disable default snapshot for record/replay
2019-10-14 16:03 [PULL 00/15] Block layer patches Kevin Wolf
2019-10-14 16:03 ` [PULL 01/15] block/vhdx: add check for truncated image files Kevin Wolf
2019-10-14 16:03 ` [PULL 02/15] block: implement bdrv_snapshot_goto for blkreplay Kevin Wolf
@ 2019-10-14 16:03 ` Kevin Wolf
2019-10-14 16:03 ` [PULL 04/15] replay: update docs for record/replay with block devices Kevin Wolf
` (6 subsequent siblings)
9 siblings, 0 replies; 15+ messages in thread
From: Kevin Wolf @ 2019-10-14 16:03 UTC (permalink / raw)
To: qemu-block; +Cc: kwolf, peter.maydell, qemu-devel
From: Pavel Dovgalyuk <pavel.dovgaluk@ispras.ru>
This patch disables setting '-snapshot' option on by default
in record/replay mode. This is needed for creating vmstates in record
and replay modes.
Signed-off-by: Pavel Dovgalyuk <pavel.dovgaluk@ispras.ru>
Acked-by: Kevin Wolf <kwolf@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
---
vl.c | 10 ++++++++--
1 file changed, 8 insertions(+), 2 deletions(-)
diff --git a/vl.c b/vl.c
index 0a295e5d77..fce9ce2364 100644
--- a/vl.c
+++ b/vl.c
@@ -1203,7 +1203,7 @@ static void configure_blockdev(BlockdevOptionsQueue *bdo_queue,
qapi_free_BlockdevOptions(bdo->bdo);
g_free(bdo);
}
- if (snapshot || replay_mode != REPLAY_MODE_NONE) {
+ if (snapshot) {
qemu_opts_foreach(qemu_find_opts("drive"), drive_enable_snapshot,
NULL, NULL);
}
@@ -3066,7 +3066,13 @@ int main(int argc, char **argv, char **envp)
drive_add(IF_PFLASH, -1, optarg, PFLASH_OPTS);
break;
case QEMU_OPTION_snapshot:
- snapshot = 1;
+ {
+ Error *blocker = NULL;
+ snapshot = 1;
+ error_setg(&blocker, QERR_REPLAY_NOT_SUPPORTED,
+ "-snapshot");
+ replay_add_blocker(blocker);
+ }
break;
case QEMU_OPTION_numa:
opts = qemu_opts_parse_noisily(qemu_find_opts("numa"),
--
2.20.1
^ permalink raw reply related [flat|nested] 15+ messages in thread* [PULL 04/15] replay: update docs for record/replay with block devices
2019-10-14 16:03 [PULL 00/15] Block layer patches Kevin Wolf
` (2 preceding siblings ...)
2019-10-14 16:03 ` [PULL 03/15] replay: disable default snapshot for record/replay Kevin Wolf
@ 2019-10-14 16:03 ` Kevin Wolf
2019-10-14 16:03 ` [PULL 05/15] replay: don't drain/flush bdrv queue while RR is working Kevin Wolf
` (5 subsequent siblings)
9 siblings, 0 replies; 15+ messages in thread
From: Kevin Wolf @ 2019-10-14 16:03 UTC (permalink / raw)
To: qemu-block; +Cc: kwolf, peter.maydell, qemu-devel
From: Pavel Dovgalyuk <Pavel.Dovgaluk@ispras.ru>
This patch updates the description of the command lines for using
record/replay with attached block devices.
Signed-off-by: Pavel Dovgalyuk <Pavel.Dovgaluk@ispras.ru>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
---
docs/replay.txt | 12 +++++++++---
1 file changed, 9 insertions(+), 3 deletions(-)
diff --git a/docs/replay.txt b/docs/replay.txt
index ee6aee9861..ce97c3f72f 100644
--- a/docs/replay.txt
+++ b/docs/replay.txt
@@ -27,7 +27,7 @@ Usage of the record/replay:
* First, record the execution with the following command line:
qemu-system-i386 \
-icount shift=7,rr=record,rrfile=replay.bin \
- -drive file=disk.qcow2,if=none,id=img-direct \
+ -drive file=disk.qcow2,if=none,snapshot,id=img-direct \
-drive driver=blkreplay,if=none,image=img-direct,id=img-blkreplay \
-device ide-hd,drive=img-blkreplay \
-netdev user,id=net1 -device rtl8139,netdev=net1 \
@@ -35,7 +35,7 @@ Usage of the record/replay:
* After recording, you can replay it by using another command line:
qemu-system-i386 \
-icount shift=7,rr=replay,rrfile=replay.bin \
- -drive file=disk.qcow2,if=none,id=img-direct \
+ -drive file=disk.qcow2,if=none,snapshot,id=img-direct \
-drive driver=blkreplay,if=none,image=img-direct,id=img-blkreplay \
-device ide-hd,drive=img-blkreplay \
-netdev user,id=net1 -device rtl8139,netdev=net1 \
@@ -223,7 +223,7 @@ Block devices record/replay module intercepts calls of
bdrv coroutine functions at the top of block drivers stack.
To record and replay block operations the drive must be configured
as following:
- -drive file=disk.qcow2,if=none,id=img-direct
+ -drive file=disk.qcow2,if=none,snapshot,id=img-direct
-drive driver=blkreplay,if=none,image=img-direct,id=img-blkreplay
-device ide-hd,drive=img-blkreplay
@@ -252,6 +252,12 @@ This snapshot is created at start of recording and restored at start
of replaying. It also can be loaded while replaying to roll back
the execution.
+'snapshot' flag of the disk image must be removed to save the snapshots
+in the overlay (or original image) instead of using the temporary overlay.
+ -drive file=disk.ovl,if=none,id=img-direct
+ -drive driver=blkreplay,if=none,image=img-direct,id=img-blkreplay
+ -device ide-hd,drive=img-blkreplay
+
Use QEMU monitor to create additional snapshots. 'savevm <name>' command
created the snapshot and 'loadvm <name>' restores it. To prevent corruption
of the original disk image, use overlay files linked to the original images.
--
2.20.1
^ permalink raw reply related [flat|nested] 15+ messages in thread* [PULL 05/15] replay: don't drain/flush bdrv queue while RR is working
2019-10-14 16:03 [PULL 00/15] Block layer patches Kevin Wolf
` (3 preceding siblings ...)
2019-10-14 16:03 ` [PULL 04/15] replay: update docs for record/replay with block devices Kevin Wolf
@ 2019-10-14 16:03 ` Kevin Wolf
2019-10-14 16:03 ` [PULL 06/15] replay: finish record/replay before closing the disks Kevin Wolf
` (4 subsequent siblings)
9 siblings, 0 replies; 15+ messages in thread
From: Kevin Wolf @ 2019-10-14 16:03 UTC (permalink / raw)
To: qemu-block; +Cc: kwolf, peter.maydell, qemu-devel
From: Pavel Dovgalyuk <Pavel.Dovgaluk@ispras.ru>
In record/replay mode bdrv queue is controlled by replay mechanism.
It does not allow saving or loading the snapshots
when bdrv queue is not empty. Stopping the VM is not blocked by nonempty
queue, but flushing the queue is still impossible there,
because it may cause deadlocks in replay mode.
This patch disables bdrv_drain_all and bdrv_flush_all in
record/replay mode.
Stopping the machine when the IO requests are not finished is needed
for the debugging. E.g., breakpoint may be set at the specified step,
and forcing the IO requests to finish may break the determinism
of the execution.
Signed-off-by: Pavel Dovgalyuk <pavel.dovgaluk@ispras.ru>
Acked-by: Kevin Wolf <kwolf@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
---
block/io.c | 28 ++++++++++++++++++++++++++++
cpus.c | 2 --
2 files changed, 28 insertions(+), 2 deletions(-)
diff --git a/block/io.c b/block/io.c
index 4f9ee97c2b..834841142a 100644
--- a/block/io.c
+++ b/block/io.c
@@ -33,6 +33,7 @@
#include "qapi/error.h"
#include "qemu/error-report.h"
#include "qemu/main-loop.h"
+#include "sysemu/replay.h"
#define NOT_DONE 0x7fffffff /* used while emulated sync operation in progress */
@@ -600,6 +601,15 @@ void bdrv_drain_all_begin(void)
return;
}
+ /*
+ * bdrv queue is managed by record/replay,
+ * waiting for finishing the I/O requests may
+ * be infinite
+ */
+ if (replay_events_enabled()) {
+ return;
+ }
+
/* AIO_WAIT_WHILE() with a NULL context can only be called from the main
* loop AioContext, so make sure we're in the main context. */
assert(qemu_get_current_aio_context() == qemu_get_aio_context());
@@ -629,6 +639,15 @@ void bdrv_drain_all_end(void)
BlockDriverState *bs = NULL;
int drained_end_counter = 0;
+ /*
+ * bdrv queue is managed by record/replay,
+ * waiting for finishing the I/O requests may
+ * be endless
+ */
+ if (replay_events_enabled()) {
+ return;
+ }
+
while ((bs = bdrv_next_all_states(bs))) {
AioContext *aio_context = bdrv_get_aio_context(bs);
@@ -2124,6 +2143,15 @@ int bdrv_flush_all(void)
BlockDriverState *bs = NULL;
int result = 0;
+ /*
+ * bdrv queue is managed by record/replay,
+ * creating new flush request for stopping
+ * the VM may break the determinism
+ */
+ if (replay_events_enabled()) {
+ return result;
+ }
+
for (bs = bdrv_first(&it); bs; bs = bdrv_next(&it)) {
AioContext *aio_context = bdrv_get_aio_context(bs);
int ret;
diff --git a/cpus.c b/cpus.c
index d2c61ff155..367f0657c5 100644
--- a/cpus.c
+++ b/cpus.c
@@ -1097,7 +1097,6 @@ static int do_vm_stop(RunState state, bool send_stop)
}
bdrv_drain_all();
- replay_disable_events();
ret = bdrv_flush_all();
return ret;
@@ -2181,7 +2180,6 @@ int vm_prepare_start(void)
/* We are sending this now, but the CPUs will be resumed shortly later */
qapi_event_send_resume();
- replay_enable_events();
cpu_enable_ticks();
runstate_set(RUN_STATE_RUNNING);
vm_state_notify(1, RUN_STATE_RUNNING);
--
2.20.1
^ permalink raw reply related [flat|nested] 15+ messages in thread* [PULL 06/15] replay: finish record/replay before closing the disks
2019-10-14 16:03 [PULL 00/15] Block layer patches Kevin Wolf
` (4 preceding siblings ...)
2019-10-14 16:03 ` [PULL 05/15] replay: don't drain/flush bdrv queue while RR is working Kevin Wolf
@ 2019-10-14 16:03 ` Kevin Wolf
2019-10-14 16:03 ` [PULL 07/15] replay: add BH oneshot event for block layer Kevin Wolf
` (3 subsequent siblings)
9 siblings, 0 replies; 15+ messages in thread
From: Kevin Wolf @ 2019-10-14 16:03 UTC (permalink / raw)
To: qemu-block; +Cc: kwolf, peter.maydell, qemu-devel
From: Pavel Dovgalyuk <Pavel.Dovgaluk@ispras.ru>
After recent updates block devices cannot be closed on qemu exit.
This happens due to the block request polling when replay is not finished.
Therefore now we stop execution recording before closing the block devices.
Signed-off-by: Pavel Dovgalyuk <pavel.dovgaluk@ispras.ru>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
---
replay/replay.c | 2 ++
vl.c | 1 +
2 files changed, 3 insertions(+)
diff --git a/replay/replay.c b/replay/replay.c
index 713395b33d..5cc25bd2f8 100644
--- a/replay/replay.c
+++ b/replay/replay.c
@@ -385,6 +385,8 @@ void replay_finish(void)
g_free(replay_snapshot);
replay_snapshot = NULL;
+ replay_mode = REPLAY_MODE_NONE;
+
replay_finish_events();
}
diff --git a/vl.c b/vl.c
index fce9ce2364..57d4fd726f 100644
--- a/vl.c
+++ b/vl.c
@@ -4524,6 +4524,7 @@ int main(int argc, char **argv, char **envp)
/* No more vcpu or device emulation activity beyond this point */
vm_shutdown();
+ replay_finish();
job_cancel_sync_all();
bdrv_close_all();
--
2.20.1
^ permalink raw reply related [flat|nested] 15+ messages in thread* [PULL 07/15] replay: add BH oneshot event for block layer
2019-10-14 16:03 [PULL 00/15] Block layer patches Kevin Wolf
` (5 preceding siblings ...)
2019-10-14 16:03 ` [PULL 06/15] replay: finish record/replay before closing the disks Kevin Wolf
@ 2019-10-14 16:03 ` Kevin Wolf
2019-10-14 16:03 ` [PULL 08/15] block: Reject misaligned write requests with BDRV_REQ_NO_FALLBACK Kevin Wolf
` (2 subsequent siblings)
9 siblings, 0 replies; 15+ messages in thread
From: Kevin Wolf @ 2019-10-14 16:03 UTC (permalink / raw)
To: qemu-block; +Cc: kwolf, peter.maydell, qemu-devel
From: Pavel Dovgalyuk <Pavel.Dovgaluk@ispras.ru>
Replay is capable of recording normal BH events, but sometimes
there are single use callbacks scheduled with aio_bh_schedule_oneshot
function. This patch enables recording and replaying such callbacks.
Block layer uses these events for calling the completion function.
Replaying these calls makes the execution deterministic.
Signed-off-by: Pavel Dovgalyuk <Pavel.Dovgaluk@ispras.ru>
Acked-by: Kevin Wolf <kwolf@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
---
include/sysemu/replay.h | 4 ++++
replay/replay-internal.h | 1 +
block/block-backend.c | 9 ++++++---
block/io.c | 4 ++--
block/iscsi.c | 5 +++--
block/nfs.c | 6 ++++--
block/null.c | 4 +++-
block/nvme.c | 6 ++++--
block/rbd.c | 5 +++--
block/vxhs.c | 5 +++--
replay/replay-events.c | 16 ++++++++++++++++
stubs/replay-user.c | 9 +++++++++
stubs/Makefile.objs | 1 +
13 files changed, 59 insertions(+), 16 deletions(-)
create mode 100644 stubs/replay-user.c
diff --git a/include/sysemu/replay.h b/include/sysemu/replay.h
index dfc7a31c66..8df517298c 100644
--- a/include/sysemu/replay.h
+++ b/include/sysemu/replay.h
@@ -15,6 +15,7 @@
#include "qapi/qapi-types-misc.h"
#include "qapi/qapi-types-run-state.h"
#include "qapi/qapi-types-ui.h"
+#include "block/aio.h"
/* replay clock kinds */
enum ReplayClockKind {
@@ -140,6 +141,9 @@ void replay_enable_events(void);
bool replay_events_enabled(void);
/*! Adds bottom half event to the queue */
void replay_bh_schedule_event(QEMUBH *bh);
+/* Adds oneshot bottom half event to the queue */
+void replay_bh_schedule_oneshot_event(AioContext *ctx,
+ QEMUBHFunc *cb, void *opaque);
/*! Adds input event to the queue */
void replay_input_event(QemuConsole *src, InputEvent *evt);
/*! Adds input sync event to the queue */
diff --git a/replay/replay-internal.h b/replay/replay-internal.h
index afba9a3e0c..55fca1ac6b 100644
--- a/replay/replay-internal.h
+++ b/replay/replay-internal.h
@@ -51,6 +51,7 @@ enum ReplayEvents {
enum ReplayAsyncEventKind {
REPLAY_ASYNC_EVENT_BH,
+ REPLAY_ASYNC_EVENT_BH_ONESHOT,
REPLAY_ASYNC_EVENT_INPUT,
REPLAY_ASYNC_EVENT_INPUT_SYNC,
REPLAY_ASYNC_EVENT_CHAR_READ,
diff --git a/block/block-backend.c b/block/block-backend.c
index 1c605d5444..eb22ff306e 100644
--- a/block/block-backend.c
+++ b/block/block-backend.c
@@ -18,6 +18,8 @@
#include "hw/qdev-core.h"
#include "sysemu/blockdev.h"
#include "sysemu/runstate.h"
+#include "sysemu/sysemu.h"
+#include "sysemu/replay.h"
#include "qapi/error.h"
#include "qapi/qapi-events-block.h"
#include "qemu/id.h"
@@ -1306,7 +1308,8 @@ BlockAIOCB *blk_abort_aio_request(BlockBackend *blk,
acb->blk = blk;
acb->ret = ret;
- aio_bh_schedule_oneshot(blk_get_aio_context(blk), error_callback_bh, acb);
+ replay_bh_schedule_oneshot_event(blk_get_aio_context(blk),
+ error_callback_bh, acb);
return &acb->common;
}
@@ -1362,8 +1365,8 @@ static BlockAIOCB *blk_aio_prwv(BlockBackend *blk, int64_t offset, int bytes,
acb->has_returned = true;
if (acb->rwco.ret != NOT_DONE) {
- aio_bh_schedule_oneshot(blk_get_aio_context(blk),
- blk_aio_complete_bh, acb);
+ replay_bh_schedule_oneshot_event(blk_get_aio_context(blk),
+ blk_aio_complete_bh, acb);
}
return &acb->common;
diff --git a/block/io.c b/block/io.c
index 834841142a..8b6dace056 100644
--- a/block/io.c
+++ b/block/io.c
@@ -369,8 +369,8 @@ static void coroutine_fn bdrv_co_yield_to_drain(BlockDriverState *bs,
if (bs) {
bdrv_inc_in_flight(bs);
}
- aio_bh_schedule_oneshot(bdrv_get_aio_context(bs),
- bdrv_co_drain_bh_cb, &data);
+ replay_bh_schedule_oneshot_event(bdrv_get_aio_context(bs),
+ bdrv_co_drain_bh_cb, &data);
qemu_coroutine_yield();
/* If we are resumed from some other event (such as an aio completion or a
diff --git a/block/iscsi.c b/block/iscsi.c
index 506bf5f875..2ced15066a 100644
--- a/block/iscsi.c
+++ b/block/iscsi.c
@@ -40,6 +40,7 @@
#include "qemu/module.h"
#include "qemu/option.h"
#include "qemu/uuid.h"
+#include "sysemu/replay.h"
#include "qapi/error.h"
#include "qapi/qapi-commands-misc.h"
#include "qapi/qmp/qdict.h"
@@ -280,8 +281,8 @@ iscsi_co_generic_cb(struct iscsi_context *iscsi, int status,
}
if (iTask->co) {
- aio_bh_schedule_oneshot(iTask->iscsilun->aio_context,
- iscsi_co_generic_bh_cb, iTask);
+ replay_bh_schedule_oneshot_event(iTask->iscsilun->aio_context,
+ iscsi_co_generic_bh_cb, iTask);
} else {
iTask->complete = 1;
}
diff --git a/block/nfs.c b/block/nfs.c
index f39acfdb28..40f23495a0 100644
--- a/block/nfs.c
+++ b/block/nfs.c
@@ -37,6 +37,8 @@
#include "qemu/option.h"
#include "qemu/uri.h"
#include "qemu/cutils.h"
+#include "sysemu/sysemu.h"
+#include "sysemu/replay.h"
#include "qapi/qapi-visit-block-core.h"
#include "qapi/qmp/qdict.h"
#include "qapi/qmp/qstring.h"
@@ -257,8 +259,8 @@ nfs_co_generic_cb(int ret, struct nfs_context *nfs, void *data,
if (task->ret < 0) {
error_report("NFS Error: %s", nfs_get_error(nfs));
}
- aio_bh_schedule_oneshot(task->client->aio_context,
- nfs_co_generic_bh_cb, task);
+ replay_bh_schedule_oneshot_event(task->client->aio_context,
+ nfs_co_generic_bh_cb, task);
}
static int coroutine_fn nfs_co_preadv(BlockDriverState *bs, uint64_t offset,
diff --git a/block/null.c b/block/null.c
index 699aa295cb..15e1d56746 100644
--- a/block/null.c
+++ b/block/null.c
@@ -17,6 +17,7 @@
#include "qemu/module.h"
#include "qemu/option.h"
#include "block/block_int.h"
+#include "sysemu/replay.h"
#define NULL_OPT_LATENCY "latency-ns"
#define NULL_OPT_ZEROES "read-zeroes"
@@ -179,7 +180,8 @@ static inline BlockAIOCB *null_aio_common(BlockDriverState *bs,
timer_mod_ns(&acb->timer,
qemu_clock_get_ns(QEMU_CLOCK_REALTIME) + s->latency_ns);
} else {
- aio_bh_schedule_oneshot(bdrv_get_aio_context(bs), null_bh_cb, acb);
+ replay_bh_schedule_oneshot_event(bdrv_get_aio_context(bs),
+ null_bh_cb, acb);
}
return &acb->common;
}
diff --git a/block/nvme.c b/block/nvme.c
index 5be3a39b63..910872ec59 100644
--- a/block/nvme.c
+++ b/block/nvme.c
@@ -23,6 +23,7 @@
#include "qemu/option.h"
#include "qemu/vfio-helpers.h"
#include "block/block_int.h"
+#include "sysemu/replay.h"
#include "trace.h"
#include "block/nvme.h"
@@ -351,7 +352,8 @@ static bool nvme_process_completion(BDRVNVMeState *s, NVMeQueuePair *q)
smp_mb_release();
*q->cq.doorbell = cpu_to_le32(q->cq.head);
if (!qemu_co_queue_empty(&q->free_req_queue)) {
- aio_bh_schedule_oneshot(s->aio_context, nvme_free_req_queue_cb, q);
+ replay_bh_schedule_oneshot_event(s->aio_context,
+ nvme_free_req_queue_cb, q);
}
}
q->busy = false;
@@ -935,7 +937,7 @@ static void nvme_rw_cb(void *opaque, int ret)
/* The rw coroutine hasn't yielded, don't try to enter. */
return;
}
- aio_bh_schedule_oneshot(data->ctx, nvme_rw_cb_bh, data);
+ replay_bh_schedule_oneshot_event(data->ctx, nvme_rw_cb_bh, data);
}
static coroutine_fn int nvme_co_prw_aligned(BlockDriverState *bs,
diff --git a/block/rbd.c b/block/rbd.c
index 057af43d48..c71e45d7c3 100644
--- a/block/rbd.c
+++ b/block/rbd.c
@@ -22,6 +22,7 @@
#include "block/qdict.h"
#include "crypto/secret.h"
#include "qemu/cutils.h"
+#include "sysemu/replay.h"
#include "qapi/qmp/qstring.h"
#include "qapi/qmp/qdict.h"
#include "qapi/qmp/qjson.h"
@@ -884,8 +885,8 @@ static void rbd_finish_aiocb(rbd_completion_t c, RADOSCB *rcb)
rcb->ret = rbd_aio_get_return_value(c);
rbd_aio_release(c);
- aio_bh_schedule_oneshot(bdrv_get_aio_context(acb->common.bs),
- rbd_finish_bh, rcb);
+ replay_bh_schedule_oneshot_event(bdrv_get_aio_context(acb->common.bs),
+ rbd_finish_bh, rcb);
}
static int rbd_aio_discard_wrapper(rbd_image_t image,
diff --git a/block/vxhs.c b/block/vxhs.c
index 77fd5eb20d..d79fc97df6 100644
--- a/block/vxhs.c
+++ b/block/vxhs.c
@@ -22,6 +22,7 @@
#include "qapi/error.h"
#include "qemu/uuid.h"
#include "crypto/tlscredsx509.h"
+#include "sysemu/replay.h"
#define VXHS_OPT_FILENAME "filename"
#define VXHS_OPT_VDISK_ID "vdisk-id"
@@ -105,8 +106,8 @@ static void vxhs_iio_callback(void *ctx, uint32_t opcode, uint32_t error)
trace_vxhs_iio_callback(error);
}
- aio_bh_schedule_oneshot(bdrv_get_aio_context(acb->common.bs),
- vxhs_complete_aio_bh, acb);
+ replay_bh_schedule_oneshot_event(bdrv_get_aio_context(acb->common.bs),
+ vxhs_complete_aio_bh, acb);
break;
default:
diff --git a/replay/replay-events.c b/replay/replay-events.c
index 008e80f636..302b84043a 100644
--- a/replay/replay-events.c
+++ b/replay/replay-events.c
@@ -36,6 +36,9 @@ static void replay_run_event(Event *event)
case REPLAY_ASYNC_EVENT_BH:
aio_bh_call(event->opaque);
break;
+ case REPLAY_ASYNC_EVENT_BH_ONESHOT:
+ ((QEMUBHFunc *)event->opaque)(event->opaque2);
+ break;
case REPLAY_ASYNC_EVENT_INPUT:
qemu_input_event_send_impl(NULL, (InputEvent *)event->opaque);
qapi_free_InputEvent((InputEvent *)event->opaque);
@@ -131,6 +134,17 @@ void replay_bh_schedule_event(QEMUBH *bh)
}
}
+void replay_bh_schedule_oneshot_event(AioContext *ctx,
+ QEMUBHFunc *cb, void *opaque)
+{
+ if (events_enabled) {
+ uint64_t id = replay_get_current_icount();
+ replay_add_event(REPLAY_ASYNC_EVENT_BH_ONESHOT, cb, opaque, id);
+ } else {
+ aio_bh_schedule_oneshot(ctx, cb, opaque);
+ }
+}
+
void replay_add_input_event(struct InputEvent *event)
{
replay_add_event(REPLAY_ASYNC_EVENT_INPUT, event, NULL, 0);
@@ -161,6 +175,7 @@ static void replay_save_event(Event *event, int checkpoint)
/* save event-specific data */
switch (event->event_kind) {
case REPLAY_ASYNC_EVENT_BH:
+ case REPLAY_ASYNC_EVENT_BH_ONESHOT:
replay_put_qword(event->id);
break;
case REPLAY_ASYNC_EVENT_INPUT:
@@ -216,6 +231,7 @@ static Event *replay_read_event(int checkpoint)
/* Events that has not to be in the queue */
switch (replay_state.read_event_kind) {
case REPLAY_ASYNC_EVENT_BH:
+ case REPLAY_ASYNC_EVENT_BH_ONESHOT:
if (replay_state.read_event_id == -1) {
replay_state.read_event_id = replay_get_qword();
}
diff --git a/stubs/replay-user.c b/stubs/replay-user.c
new file mode 100644
index 0000000000..2ad9e27203
--- /dev/null
+++ b/stubs/replay-user.c
@@ -0,0 +1,9 @@
+#include "qemu/osdep.h"
+#include "sysemu/replay.h"
+#include "sysemu/sysemu.h"
+
+void replay_bh_schedule_oneshot_event(AioContext *ctx,
+ QEMUBHFunc *cb, void *opaque)
+{
+ aio_bh_schedule_oneshot(ctx, cb, opaque);
+}
diff --git a/stubs/Makefile.objs b/stubs/Makefile.objs
index 9c7393b08c..4a50e95ec3 100644
--- a/stubs/Makefile.objs
+++ b/stubs/Makefile.objs
@@ -20,6 +20,7 @@ stub-obj-y += monitor.o
stub-obj-y += notify-event.o
stub-obj-y += qtest.o
stub-obj-y += replay.o
+stub-obj-y += replay-user.o
stub-obj-y += runstate-check.o
stub-obj-y += set-fd-handler.o
stub-obj-y += sysbus.o
--
2.20.1
^ permalink raw reply related [flat|nested] 15+ messages in thread* [PULL 08/15] block: Reject misaligned write requests with BDRV_REQ_NO_FALLBACK
2019-10-14 16:03 [PULL 00/15] Block layer patches Kevin Wolf
` (6 preceding siblings ...)
2019-10-14 16:03 ` [PULL 07/15] replay: add BH oneshot event for block layer Kevin Wolf
@ 2019-10-14 16:03 ` Kevin Wolf
2019-10-14 16:03 ` [PULL 09/15] iotests/028: Fix for long $TEST_DIRs Kevin Wolf
2019-10-15 16:09 ` [PULL 00/15] Block layer patches Peter Maydell
9 siblings, 0 replies; 15+ messages in thread
From: Kevin Wolf @ 2019-10-14 16:03 UTC (permalink / raw)
To: qemu-block; +Cc: kwolf, peter.maydell, qemu-devel
From: Alberto Garcia <berto@igalia.com>
The BDRV_REQ_NO_FALLBACK flag means that an operation should only be
performed if it can be offloaded or otherwise performed efficiently.
However a misaligned write request requires a RMW so we should return
an error and let the caller decide how to proceed.
This hits an assertion since commit c8bb23cbdb if the required
alignment is larger than the cluster size:
qemu-img create -f qcow2 -o cluster_size=2k img.qcow2 4G
qemu-io -c "open -o driver=qcow2,file.align=4k blkdebug::img.qcow2" \
-c 'write 0 512'
qemu-io: block/io.c:1127: bdrv_driver_pwritev: Assertion `!(flags & BDRV_REQ_NO_FALLBACK)' failed.
Aborted
The reason is that when writing to an unallocated cluster we try to
skip the copy-on-write part and zeroize it using BDRV_REQ_NO_FALLBACK
instead, resulting in a write request that is too small (2KB cluster
size vs 4KB required alignment).
Signed-off-by: Alberto Garcia <berto@igalia.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
---
block/io.c | 7 +++++
tests/qemu-iotests/268 | 55 ++++++++++++++++++++++++++++++++++++++
tests/qemu-iotests/268.out | 7 +++++
tests/qemu-iotests/group | 1 +
4 files changed, 70 insertions(+)
create mode 100755 tests/qemu-iotests/268
create mode 100644 tests/qemu-iotests/268.out
diff --git a/block/io.c b/block/io.c
index 8b6dace056..f0b86c1d19 100644
--- a/block/io.c
+++ b/block/io.c
@@ -2090,6 +2090,13 @@ int coroutine_fn bdrv_co_pwritev_part(BdrvChild *child,
return ret;
}
+ /* If the request is misaligned then we can't make it efficient */
+ if ((flags & BDRV_REQ_NO_FALLBACK) &&
+ !QEMU_IS_ALIGNED(offset | bytes, align))
+ {
+ return -ENOTSUP;
+ }
+
bdrv_inc_in_flight(bs);
/*
* Align write if necessary by performing a read-modify-write cycle.
diff --git a/tests/qemu-iotests/268 b/tests/qemu-iotests/268
new file mode 100755
index 0000000000..78c3f4db3a
--- /dev/null
+++ b/tests/qemu-iotests/268
@@ -0,0 +1,55 @@
+#!/usr/bin/env bash
+#
+# Test write request with required alignment larger than the cluster size
+#
+# Copyright (C) 2019 Igalia, S.L.
+# Author: Alberto Garcia <berto@igalia.com>
+#
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 2 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program. If not, see <http://www.gnu.org/licenses/>.
+#
+
+# creator
+owner=berto@igalia.com
+
+seq=`basename $0`
+echo "QA output created by $seq"
+
+status=1 # failure is the default!
+
+_cleanup()
+{
+ _cleanup_test_img
+}
+trap "_cleanup; exit \$status" 0 1 2 3 15
+
+# get standard environment, filters and checks
+. ./common.rc
+. ./common.filter
+
+_supported_fmt qcow2
+_supported_proto file
+
+echo
+echo "== Required alignment larger than cluster size =="
+
+CLUSTER_SIZE=2k _make_test_img 1M
+# Since commit c8bb23cbdb writing to an unallocated cluster fills the
+# empty COW areas with bdrv_write_zeroes(flags=BDRV_REQ_NO_FALLBACK)
+$QEMU_IO -c "open -o driver=$IMGFMT,file.align=4k blkdebug::$TEST_IMG" \
+ -c "write 0 512" | _filter_qemu_io
+
+# success, all done
+echo "*** done"
+rm -f $seq.full
+status=0
diff --git a/tests/qemu-iotests/268.out b/tests/qemu-iotests/268.out
new file mode 100644
index 0000000000..2ed6c68529
--- /dev/null
+++ b/tests/qemu-iotests/268.out
@@ -0,0 +1,7 @@
+QA output created by 268
+
+== Required alignment larger than cluster size ==
+Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1048576
+wrote 512/512 bytes at offset 0
+512 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+*** done
diff --git a/tests/qemu-iotests/group b/tests/qemu-iotests/group
index 5805a79d9e..4c861f7eed 100644
--- a/tests/qemu-iotests/group
+++ b/tests/qemu-iotests/group
@@ -278,3 +278,4 @@
265 rw auto quick
266 rw quick
267 rw auto quick snapshot
+268 rw auto quick
--
2.20.1
^ permalink raw reply related [flat|nested] 15+ messages in thread* [PULL 09/15] iotests/028: Fix for long $TEST_DIRs
2019-10-14 16:03 [PULL 00/15] Block layer patches Kevin Wolf
` (7 preceding siblings ...)
2019-10-14 16:03 ` [PULL 08/15] block: Reject misaligned write requests with BDRV_REQ_NO_FALLBACK Kevin Wolf
@ 2019-10-14 16:03 ` Kevin Wolf
2019-10-15 16:09 ` [PULL 00/15] Block layer patches Peter Maydell
9 siblings, 0 replies; 15+ messages in thread
From: Kevin Wolf @ 2019-10-14 16:03 UTC (permalink / raw)
To: qemu-block; +Cc: kwolf, peter.maydell, qemu-devel
From: Max Reitz <mreitz@redhat.com>
For long test image paths, the order of the "Formatting" line and the
"(qemu)" prompt after a drive_backup HMP command may be reversed. In
fact, the interaction between the prompt and the line may lead to the
"Formatting" to being greppable at all after "read"-ing it (if the
prompt injects an IFS character into the "Formatting" string).
So just wait until we get a prompt. At that point, the block job must
have been started, so "info block-jobs" will only return "No active
jobs" once it is done.
Reported-by: Thomas Huth <thuth@redhat.com>
Signed-off-by: Max Reitz <mreitz@redhat.com>
Reviewed-by: John Snow <jsnow@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
---
tests/qemu-iotests/028 | 11 ++++++++---
tests/qemu-iotests/028.out | 1 -
2 files changed, 8 insertions(+), 4 deletions(-)
diff --git a/tests/qemu-iotests/028 b/tests/qemu-iotests/028
index 71301ec6e5..bba1ee59ae 100755
--- a/tests/qemu-iotests/028
+++ b/tests/qemu-iotests/028
@@ -119,9 +119,14 @@ fi
# Silence output since it contains the disk image path and QEMU's readline
# character echoing makes it very hard to filter the output. Plus, there
# is no telling how many times the command will repeat before succeeding.
-_send_qemu_cmd $h "drive_backup disk ${TEST_IMG}.copy" "(qemu)" >/dev/null
-_send_qemu_cmd $h "" "Formatting" | _filter_img_create
-qemu_cmd_repeat=20 _send_qemu_cmd $h "info block-jobs" "No active jobs" >/dev/null
+# (Note that creating the image results in a "Formatting..." message over
+# stdout, which is the same channel the monitor uses. We cannot reliably
+# wait for it because the monitor output may interact with it in such a
+# way that _timed_wait_for cannot read it. However, once the block job is
+# done, we know that the "Formatting..." message must have appeared
+# already, so the output is still deterministic.)
+silent=y _send_qemu_cmd $h "drive_backup disk ${TEST_IMG}.copy" "(qemu)"
+silent=y qemu_cmd_repeat=20 _send_qemu_cmd $h "info block-jobs" "No active jobs"
_send_qemu_cmd $h "info block-jobs" "No active jobs"
_send_qemu_cmd $h 'quit' ""
diff --git a/tests/qemu-iotests/028.out b/tests/qemu-iotests/028.out
index 7d54aeb003..37aed84436 100644
--- a/tests/qemu-iotests/028.out
+++ b/tests/qemu-iotests/028.out
@@ -468,7 +468,6 @@ No errors were found on the image.
block-backup
-Formatting 'TEST_DIR/t.IMGFMT.copy', fmt=IMGFMT size=4294968832 backing_file=TEST_DIR/t.IMGFMT.base backing_fmt=IMGFMT
(qemu) info block-jobs
No active jobs
=== IO: pattern 195
--
2.20.1
^ permalink raw reply related [flat|nested] 15+ messages in thread* Re: [PULL 00/15] Block layer patches
2019-10-14 16:03 [PULL 00/15] Block layer patches Kevin Wolf
` (8 preceding siblings ...)
2019-10-14 16:03 ` [PULL 09/15] iotests/028: Fix for long $TEST_DIRs Kevin Wolf
@ 2019-10-15 16:09 ` Peter Maydell
9 siblings, 0 replies; 15+ messages in thread
From: Peter Maydell @ 2019-10-15 16:09 UTC (permalink / raw)
To: Kevin Wolf; +Cc: QEMU Developers, Qemu-block
On Mon, 14 Oct 2019 at 17:03, Kevin Wolf <kwolf@redhat.com> wrote:
>
> The following changes since commit 22dbfdecc3c52228d3489da3fe81da92b21197bf:
>
> Merge remote-tracking branch 'remotes/awilliam/tags/vfio-update-20191010.0' into staging (2019-10-14 15:09:08 +0100)
>
> are available in the Git repository at:
>
> git://repo.or.cz/qemu/kevin.git tags/for-upstream
>
> for you to fetch changes up to a1406a9262a087d9ec9627b88da13c4590b61dae:
>
> iotests: Test large write request to qcow2 file (2019-10-14 17:12:48 +0200)
>
> ----------------------------------------------------------------
> Block layer patches:
>
> - block: Fix crash with qcow2 partial cluster COW with small cluster
> sizes (misaligned write requests with BDRV_REQ_NO_FALLBACK)
> - qcow2: Fix integer overflow potentially causing corruption with huge
> requests
> - vhdx: Detect truncated image files
> - tools: Support help options for --object
> - Various block-related replay improvements
> - iotests/028: Fix for long $TEST_DIRs
Applied, thanks.
Please update the changelog at https://wiki.qemu.org/ChangeLog/4.2
for any user-visible changes.
-- PMM
^ permalink raw reply [flat|nested] 15+ messages in thread