From: @kuhnchen18 Reviewed-by: @imxcc,@imxcc Signed-off-by: @imxcc,@imxcc
This commit is contained in:
commit
23414fd767
114
blockjob-Fix-crash-with-IOthread-when-block-commit-a.patch
Normal file
114
blockjob-Fix-crash-with-IOthread-when-block-commit-a.patch
Normal file
@ -0,0 +1,114 @@
|
|||||||
|
From e37cda3452309d147f1f7aec3c74249001e3db0c Mon Sep 17 00:00:00 2001
|
||||||
|
From: Michael Qiu <qiudayu@huayun.com>
|
||||||
|
Date: Wed, 12 May 2021 21:54:37 +0800
|
||||||
|
Subject: [PATCH] blockjob: Fix crash with IOthread when block commit after
|
||||||
|
snapshot
|
||||||
|
|
||||||
|
Currently, if guest has workloads, IO thread will acquire aio_context
|
||||||
|
lock before do io_submit, it leads to segmentfault when do block commit
|
||||||
|
after snapshot. Just like below:
|
||||||
|
|
||||||
|
Program received signal SIGSEGV, Segmentation fault.
|
||||||
|
|
||||||
|
[Switching to Thread 0x7f7c7d91f700 (LWP 99907)]
|
||||||
|
0x00005576d0f65aab in bdrv_mirror_top_pwritev at ../block/mirror.c:1437
|
||||||
|
1437 ../block/mirror.c: No such file or directory.
|
||||||
|
(gdb) p s->job
|
||||||
|
$17 = (MirrorBlockJob *) 0x0
|
||||||
|
(gdb) p s->stop
|
||||||
|
$18 = false
|
||||||
|
|
||||||
|
Call trace of IO thread:
|
||||||
|
0 0x00005576d0f65aab in bdrv_mirror_top_pwritev at ../block/mirror.c:1437
|
||||||
|
1 0x00005576d0f7f3ab in bdrv_driver_pwritev at ../block/io.c:1174
|
||||||
|
2 0x00005576d0f8139d in bdrv_aligned_pwritev at ../block/io.c:1988
|
||||||
|
3 0x00005576d0f81b65 in bdrv_co_pwritev_part at ../block/io.c:2156
|
||||||
|
4 0x00005576d0f8e6b7 in blk_do_pwritev_part at ../block/block-backend.c:1260
|
||||||
|
5 0x00005576d0f8e84d in blk_aio_write_entry at ../block/block-backend.c:1476
|
||||||
|
...
|
||||||
|
|
||||||
|
Switch to qemu main thread:
|
||||||
|
0 0x00007f903be704ed in __lll_lock_wait at
|
||||||
|
/lib/../lib64/libpthread.so.0
|
||||||
|
1 0x00007f903be6bde6 in _L_lock_941 at /lib/../lib64/libpthread.so.0
|
||||||
|
2 0x00007f903be6bcdf in pthread_mutex_lock at
|
||||||
|
/lib/../lib64/libpthread.so.0
|
||||||
|
3 0x0000564b21456889 in qemu_mutex_lock_impl at
|
||||||
|
../util/qemu-thread-posix.c:79
|
||||||
|
4 0x0000564b213af8a5 in block_job_add_bdrv at ../blockjob.c:224
|
||||||
|
5 0x0000564b213b00ad in block_job_create at ../blockjob.c:440
|
||||||
|
6 0x0000564b21357c0a in mirror_start_job at ../block/mirror.c:1622
|
||||||
|
7 0x0000564b2135a9af in commit_active_start at ../block/mirror.c:1867
|
||||||
|
8 0x0000564b2133d132 in qmp_block_commit at ../blockdev.c:2768
|
||||||
|
9 0x0000564b2141fef3 in qmp_marshal_block_commit at
|
||||||
|
qapi/qapi-commands-block-core.c:346
|
||||||
|
10 0x0000564b214503c9 in do_qmp_dispatch_bh at
|
||||||
|
../qapi/qmp-dispatch.c:110
|
||||||
|
11 0x0000564b21451996 in aio_bh_poll at ../util/async.c:164
|
||||||
|
12 0x0000564b2146018e in aio_dispatch at ../util/aio-posix.c:381
|
||||||
|
13 0x0000564b2145187e in aio_ctx_dispatch at ../util/async.c:306
|
||||||
|
14 0x00007f9040239049 in g_main_context_dispatch at
|
||||||
|
/lib/../lib64/libglib-2.0.so.0
|
||||||
|
15 0x0000564b21447368 in main_loop_wait at ../util/main-loop.c:232
|
||||||
|
16 0x0000564b21447368 in main_loop_wait at ../util/main-loop.c:255
|
||||||
|
17 0x0000564b21447368 in main_loop_wait at ../util/main-loop.c:531
|
||||||
|
18 0x0000564b212304e1 in qemu_main_loop at ../softmmu/runstate.c:721
|
||||||
|
19 0x0000564b20f7975e in main at ../softmmu/main.c:50
|
||||||
|
|
||||||
|
In IO thread when do bdrv_mirror_top_pwritev, the job is NULL, and stop field
|
||||||
|
is false, this means the MirrorBDSOpaque "s" object has not been initialized
|
||||||
|
yet, and this object is initialized by block_job_create(), but the initialize
|
||||||
|
process is stuck in acquiring the lock.
|
||||||
|
|
||||||
|
In this situation, IO thread come to bdrv_mirror_top_pwritev(),which means that
|
||||||
|
mirror-top node is already inserted into block graph, but its bs->opaque->job
|
||||||
|
is not initialized.
|
||||||
|
|
||||||
|
The root cause is that qemu main thread do release/acquire when hold the lock,
|
||||||
|
at the same time, IO thread get the lock after release stage, and the crash
|
||||||
|
occured.
|
||||||
|
|
||||||
|
Actually, in this situation, job->job.aio_context will not equal to
|
||||||
|
qemu_get_aio_context(), and will be the same as bs->aio_context,
|
||||||
|
thus, no need to release the lock, becasue bdrv_root_attach_child()
|
||||||
|
will not change the context.
|
||||||
|
|
||||||
|
This patch fix this issue.
|
||||||
|
|
||||||
|
Fixes: 132ada80 "block: Adjust AioContexts when attaching nodes"
|
||||||
|
|
||||||
|
Signed-off-by: Michael Qiu <qiudayu@huayun.com>
|
||||||
|
Message-Id: <20210203024059.52683-1-08005325@163.com>
|
||||||
|
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
|
||||||
|
---
|
||||||
|
blockjob.c | 8 ++++++--
|
||||||
|
1 file changed, 6 insertions(+), 2 deletions(-)
|
||||||
|
|
||||||
|
diff --git a/blockjob.c b/blockjob.c
|
||||||
|
index 74abb97bfd..72865a4a6e 100644
|
||||||
|
--- a/blockjob.c
|
||||||
|
+++ b/blockjob.c
|
||||||
|
@@ -223,14 +223,18 @@ int block_job_add_bdrv(BlockJob *job, const char *name, BlockDriverState *bs,
|
||||||
|
uint64_t perm, uint64_t shared_perm, Error **errp)
|
||||||
|
{
|
||||||
|
BdrvChild *c;
|
||||||
|
+ bool need_context_ops;
|
||||||
|
|
||||||
|
bdrv_ref(bs);
|
||||||
|
- if (job->job.aio_context != qemu_get_aio_context()) {
|
||||||
|
+
|
||||||
|
+ need_context_ops = bdrv_get_aio_context(bs) != job->job.aio_context;
|
||||||
|
+
|
||||||
|
+ if (need_context_ops && job->job.aio_context != qemu_get_aio_context()) {
|
||||||
|
aio_context_release(job->job.aio_context);
|
||||||
|
}
|
||||||
|
c = bdrv_root_attach_child(bs, name, &child_job, job->job.aio_context,
|
||||||
|
perm, shared_perm, job, errp);
|
||||||
|
- if (job->job.aio_context != qemu_get_aio_context()) {
|
||||||
|
+ if (need_context_ops && job->job.aio_context != qemu_get_aio_context()) {
|
||||||
|
aio_context_acquire(job->job.aio_context);
|
||||||
|
}
|
||||||
|
if (c == NULL) {
|
||||||
|
--
|
||||||
|
2.27.0
|
||||||
|
|
||||||
@ -1,6 +1,6 @@
|
|||||||
Name: qemu
|
Name: qemu
|
||||||
Version: 4.1.0
|
Version: 4.1.0
|
||||||
Release: 57
|
Release: 58
|
||||||
Epoch: 2
|
Epoch: 2
|
||||||
Summary: QEMU is a generic and open source machine emulator and virtualizer
|
Summary: QEMU is a generic and open source machine emulator and virtualizer
|
||||||
License: GPLv2 and BSD and MIT and CC-BY-SA-4.0
|
License: GPLv2 and BSD and MIT and CC-BY-SA-4.0
|
||||||
@ -326,6 +326,7 @@ Patch0313: tz-ppc-add-dummy-read-write-methods.patch
|
|||||||
Patch0314: imx7-ccm-add-digprog-mmio-write-method.patch
|
Patch0314: imx7-ccm-add-digprog-mmio-write-method.patch
|
||||||
Patch0315: util-cacheinfo-fix-crash-when-compiling-with-uClibc.patch
|
Patch0315: util-cacheinfo-fix-crash-when-compiling-with-uClibc.patch
|
||||||
Patch0316: arm-cpu-Fixed-function-undefined-error-at-compile-ti.patch
|
Patch0316: arm-cpu-Fixed-function-undefined-error-at-compile-ti.patch
|
||||||
|
Patch0317: blockjob-Fix-crash-with-IOthread-when-block-commit-a.patch
|
||||||
|
|
||||||
BuildRequires: flex
|
BuildRequires: flex
|
||||||
BuildRequires: bison
|
BuildRequires: bison
|
||||||
@ -719,6 +720,9 @@ getent passwd qemu >/dev/null || \
|
|||||||
%endif
|
%endif
|
||||||
|
|
||||||
%changelog
|
%changelog
|
||||||
|
* Fri May 28 2021 Chen Qun <kuhn.chenqun@huawei.com>
|
||||||
|
- blockjob: Fix crash with IOthread when block commit after snapshot
|
||||||
|
|
||||||
* Thu 20 May 2021 zhouli57 <zhouli57@huawei.com>
|
* Thu 20 May 2021 zhouli57 <zhouli57@huawei.com>
|
||||||
- arm/cpu: Fixed function undefined error at compile time under arm
|
- arm/cpu: Fixed function undefined error at compile time under arm
|
||||||
|
|
||||||
|
|||||||
Loading…
x
Reference in New Issue
Block a user