block/io.c | 10 +++++++--- include/block/block.h | 22 ++++++++++++++-------- 2 files changed, 21 insertions(+), 11 deletions(-)
During block job completion, nothing is preventing
block_job_defer_to_main_loop_bh from being called in a nested
aio_poll(), which is a trouble, such as in this code path:
qmp_block_commit
commit_active_start
bdrv_reopen
bdrv_reopen_multiple
bdrv_reopen_prepare
bdrv_flush
aio_poll
aio_bh_poll
aio_bh_call
block_job_defer_to_main_loop_bh
stream_complete
bdrv_reopen
block_job_defer_to_main_loop_bh is the last step of the stream job,
which should have been "paused" by the bdrv_drained_begin/end in
bdrv_reopen_multiple, but it is not done because it's in the form of a
main loop BH.
Similar to why block jobs should be paused between drained_begin and
drained_end, BHs they schedule must be excluded as well. To achieve
this, this patch forces draining the BH in BDRV_POLL_WHILE.
Also because the BH in question can do bdrv_unref and child replacing,
protect @bs carefully to avoid use-after-free.
As a side effect this fixes a hang in block_job_detach_aio_context
during system_reset when a block job is ready:
#0 0x0000555555aa79f3 in bdrv_drain_recurse
#1 0x0000555555aa825d in bdrv_drained_begin
#2 0x0000555555aa8449 in bdrv_drain
#3 0x0000555555a9c356 in blk_drain
#4 0x0000555555aa3cfd in mirror_drain
#5 0x0000555555a66e11 in block_job_detach_aio_context
#6 0x0000555555a62f4d in bdrv_detach_aio_context
#7 0x0000555555a63116 in bdrv_set_aio_context
#8 0x0000555555a9d326 in blk_set_aio_context
#9 0x00005555557e38da in virtio_blk_data_plane_stop
#10 0x00005555559f9d5f in virtio_bus_stop_ioeventfd
#11 0x00005555559fa49b in virtio_bus_stop_ioeventfd
#12 0x00005555559f6a18 in virtio_pci_stop_ioeventfd
#13 0x00005555559f6a18 in virtio_pci_reset
#14 0x00005555559139a9 in qdev_reset_one
#15 0x0000555555916738 in qbus_walk_children
#16 0x0000555555913318 in qdev_walk_children
#17 0x0000555555916738 in qbus_walk_children
#18 0x00005555559168ca in qemu_devices_reset
#19 0x000055555581fcbb in pc_machine_reset
#20 0x00005555558a4d96 in qemu_system_reset
#21 0x000055555577157a in main_loop_should_exit
#22 0x000055555577157a in main_loop
#23 0x000055555577157a in main
The rationale is that the loop in block_job_detach_aio_context cannot
make any progress in pausing/completing the job, because bs->in_flight
is 0, so bdrv_drain doesn't process the block_job_defer_to_main_loop
BH. With this patch, it does.
Reported-by: Jeff Cody <jcody@redhat.com>
Signed-off-by: Fam Zheng <famz@redhat.com>
---
v3: Report all aio_poll() progress as waited_. [Kevin]
v2: Do the BH poll in BDRV_POLL_WHILE to cover bdrv_drain_all_begin as
well. [Kevin]
---
block/io.c | 10 +++++++---
include/block/block.h | 22 ++++++++++++++--------
2 files changed, 21 insertions(+), 11 deletions(-)
diff --git a/block/io.c b/block/io.c
index 8706bfa..a472157 100644
--- a/block/io.c
+++ b/block/io.c
@@ -158,7 +158,7 @@ bool bdrv_requests_pending(BlockDriverState *bs)
static bool bdrv_drain_recurse(BlockDriverState *bs)
{
- BdrvChild *child;
+ BdrvChild *child, *tmp;
bool waited;
waited = BDRV_POLL_WHILE(bs, atomic_read(&bs->in_flight) > 0);
@@ -167,8 +167,12 @@ static bool bdrv_drain_recurse(BlockDriverState *bs)
bs->drv->bdrv_drain(bs);
}
- QLIST_FOREACH(child, &bs->children, next) {
- waited |= bdrv_drain_recurse(child->bs);
+ QLIST_FOREACH_SAFE(child, &bs->children, next, tmp) {
+ BlockDriverState *bs = child->bs;
+ assert(bs->refcnt > 0);
+ bdrv_ref(bs);
+ waited |= bdrv_drain_recurse(bs);
+ bdrv_unref(bs);
}
return waited;
diff --git a/include/block/block.h b/include/block/block.h
index 97d4330..5ddc0cf 100644
--- a/include/block/block.h
+++ b/include/block/block.h
@@ -381,12 +381,13 @@ void bdrv_drain_all(void);
#define BDRV_POLL_WHILE(bs, cond) ({ \
bool waited_ = false; \
+ bool busy_ = true; \
BlockDriverState *bs_ = (bs); \
AioContext *ctx_ = bdrv_get_aio_context(bs_); \
if (aio_context_in_iothread(ctx_)) { \
- while ((cond)) { \
- aio_poll(ctx_, true); \
- waited_ = true; \
+ while ((cond) || busy_) { \
+ busy_ = aio_poll(ctx_, (cond)); \
+ waited_ |= !!(cond) | busy_; \
} \
} else { \
assert(qemu_get_current_aio_context() == \
@@ -398,11 +399,16 @@ void bdrv_drain_all(void);
*/ \
assert(!bs_->wakeup); \
bs_->wakeup = true; \
- while ((cond)) { \
- aio_context_release(ctx_); \
- aio_poll(qemu_get_aio_context(), true); \
- aio_context_acquire(ctx_); \
- waited_ = true; \
+ while (busy_) { \
+ if ((cond)) { \
+ waited_ = busy_ = true; \
+ aio_context_release(ctx_); \
+ aio_poll(qemu_get_aio_context(), true); \
+ aio_context_acquire(ctx_); \
+ } else { \
+ busy_ = aio_poll(ctx_, false); \
+ waited_ |= busy_; \
+ } \
} \
bs_->wakeup = false; \
} \
--
2.9.3
Am 18.04.2017 um 12:39 hat Fam Zheng geschrieben: > During block job completion, nothing is preventing > block_job_defer_to_main_loop_bh from being called in a nested > aio_poll(), which is a trouble, such as in this code path: > > qmp_block_commit > commit_active_start > bdrv_reopen > bdrv_reopen_multiple > bdrv_reopen_prepare > bdrv_flush > aio_poll > aio_bh_poll > aio_bh_call > block_job_defer_to_main_loop_bh > stream_complete > bdrv_reopen > > block_job_defer_to_main_loop_bh is the last step of the stream job, > which should have been "paused" by the bdrv_drained_begin/end in > bdrv_reopen_multiple, but it is not done because it's in the form of a > main loop BH. > > Similar to why block jobs should be paused between drained_begin and > drained_end, BHs they schedule must be excluded as well. To achieve > this, this patch forces draining the BH in BDRV_POLL_WHILE. > > Also because the BH in question can do bdrv_unref and child replacing, > protect @bs carefully to avoid use-after-free. > > As a side effect this fixes a hang in block_job_detach_aio_context > during system_reset when a block job is ready: > > #0 0x0000555555aa79f3 in bdrv_drain_recurse > #1 0x0000555555aa825d in bdrv_drained_begin > #2 0x0000555555aa8449 in bdrv_drain > #3 0x0000555555a9c356 in blk_drain > #4 0x0000555555aa3cfd in mirror_drain > #5 0x0000555555a66e11 in block_job_detach_aio_context > #6 0x0000555555a62f4d in bdrv_detach_aio_context > #7 0x0000555555a63116 in bdrv_set_aio_context > #8 0x0000555555a9d326 in blk_set_aio_context > #9 0x00005555557e38da in virtio_blk_data_plane_stop > #10 0x00005555559f9d5f in virtio_bus_stop_ioeventfd > #11 0x00005555559fa49b in virtio_bus_stop_ioeventfd > #12 0x00005555559f6a18 in virtio_pci_stop_ioeventfd > #13 0x00005555559f6a18 in virtio_pci_reset > #14 0x00005555559139a9 in qdev_reset_one > #15 0x0000555555916738 in qbus_walk_children > #16 0x0000555555913318 in qdev_walk_children > #17 0x0000555555916738 in qbus_walk_children > #18 0x00005555559168ca in qemu_devices_reset > #19 0x000055555581fcbb in pc_machine_reset > #20 0x00005555558a4d96 in qemu_system_reset > #21 0x000055555577157a in main_loop_should_exit > #22 0x000055555577157a in main_loop > #23 0x000055555577157a in main > > The rationale is that the loop in block_job_detach_aio_context cannot > make any progress in pausing/completing the job, because bs->in_flight > is 0, so bdrv_drain doesn't process the block_job_defer_to_main_loop > BH. With this patch, it does. > > Reported-by: Jeff Cody <jcody@redhat.com> > Signed-off-by: Fam Zheng <famz@redhat.com> Reviewed-by: Kevin Wolf <kwolf@redhat.com>
On Tue, Apr 18, 2017 at 06:39:48PM +0800, Fam Zheng wrote: > During block job completion, nothing is preventing > block_job_defer_to_main_loop_bh from being called in a nested > aio_poll(), which is a trouble, such as in this code path: > > qmp_block_commit > commit_active_start > bdrv_reopen > bdrv_reopen_multiple > bdrv_reopen_prepare > bdrv_flush > aio_poll > aio_bh_poll > aio_bh_call > block_job_defer_to_main_loop_bh > stream_complete > bdrv_reopen > > block_job_defer_to_main_loop_bh is the last step of the stream job, > which should have been "paused" by the bdrv_drained_begin/end in > bdrv_reopen_multiple, but it is not done because it's in the form of a > main loop BH. > > Similar to why block jobs should be paused between drained_begin and > drained_end, BHs they schedule must be excluded as well. To achieve > this, this patch forces draining the BH in BDRV_POLL_WHILE. > > Also because the BH in question can do bdrv_unref and child replacing, > protect @bs carefully to avoid use-after-free. > > As a side effect this fixes a hang in block_job_detach_aio_context > during system_reset when a block job is ready: > > #0 0x0000555555aa79f3 in bdrv_drain_recurse > #1 0x0000555555aa825d in bdrv_drained_begin > #2 0x0000555555aa8449 in bdrv_drain > #3 0x0000555555a9c356 in blk_drain > #4 0x0000555555aa3cfd in mirror_drain > #5 0x0000555555a66e11 in block_job_detach_aio_context > #6 0x0000555555a62f4d in bdrv_detach_aio_context > #7 0x0000555555a63116 in bdrv_set_aio_context > #8 0x0000555555a9d326 in blk_set_aio_context > #9 0x00005555557e38da in virtio_blk_data_plane_stop > #10 0x00005555559f9d5f in virtio_bus_stop_ioeventfd > #11 0x00005555559fa49b in virtio_bus_stop_ioeventfd > #12 0x00005555559f6a18 in virtio_pci_stop_ioeventfd > #13 0x00005555559f6a18 in virtio_pci_reset > #14 0x00005555559139a9 in qdev_reset_one > #15 0x0000555555916738 in qbus_walk_children > #16 0x0000555555913318 in qdev_walk_children > #17 0x0000555555916738 in qbus_walk_children > #18 0x00005555559168ca in qemu_devices_reset > #19 0x000055555581fcbb in pc_machine_reset > #20 0x00005555558a4d96 in qemu_system_reset > #21 0x000055555577157a in main_loop_should_exit > #22 0x000055555577157a in main_loop > #23 0x000055555577157a in main > > The rationale is that the loop in block_job_detach_aio_context cannot > make any progress in pausing/completing the job, because bs->in_flight > is 0, so bdrv_drain doesn't process the block_job_defer_to_main_loop > BH. With this patch, it does. > > Reported-by: Jeff Cody <jcody@redhat.com> > Signed-off-by: Fam Zheng <famz@redhat.com> > Verified this fixes the deadlock condition from my report: Tested-by: Jeff Cody <jcody@redhat.com> > --- > > v3: Report all aio_poll() progress as waited_. [Kevin] > > v2: Do the BH poll in BDRV_POLL_WHILE to cover bdrv_drain_all_begin as > well. [Kevin] > --- > block/io.c | 10 +++++++--- > include/block/block.h | 22 ++++++++++++++-------- > 2 files changed, 21 insertions(+), 11 deletions(-) > > diff --git a/block/io.c b/block/io.c > index 8706bfa..a472157 100644 > --- a/block/io.c > +++ b/block/io.c > @@ -158,7 +158,7 @@ bool bdrv_requests_pending(BlockDriverState *bs) > > static bool bdrv_drain_recurse(BlockDriverState *bs) > { > - BdrvChild *child; > + BdrvChild *child, *tmp; > bool waited; > > waited = BDRV_POLL_WHILE(bs, atomic_read(&bs->in_flight) > 0); > @@ -167,8 +167,12 @@ static bool bdrv_drain_recurse(BlockDriverState *bs) > bs->drv->bdrv_drain(bs); > } > > - QLIST_FOREACH(child, &bs->children, next) { > - waited |= bdrv_drain_recurse(child->bs); > + QLIST_FOREACH_SAFE(child, &bs->children, next, tmp) { > + BlockDriverState *bs = child->bs; > + assert(bs->refcnt > 0); > + bdrv_ref(bs); > + waited |= bdrv_drain_recurse(bs); > + bdrv_unref(bs); > } > > return waited; > diff --git a/include/block/block.h b/include/block/block.h > index 97d4330..5ddc0cf 100644 > --- a/include/block/block.h > +++ b/include/block/block.h > @@ -381,12 +381,13 @@ void bdrv_drain_all(void); > > #define BDRV_POLL_WHILE(bs, cond) ({ \ > bool waited_ = false; \ > + bool busy_ = true; \ > BlockDriverState *bs_ = (bs); \ > AioContext *ctx_ = bdrv_get_aio_context(bs_); \ > if (aio_context_in_iothread(ctx_)) { \ > - while ((cond)) { \ > - aio_poll(ctx_, true); \ > - waited_ = true; \ > + while ((cond) || busy_) { \ > + busy_ = aio_poll(ctx_, (cond)); \ > + waited_ |= !!(cond) | busy_; \ > } \ > } else { \ > assert(qemu_get_current_aio_context() == \ > @@ -398,11 +399,16 @@ void bdrv_drain_all(void); > */ \ > assert(!bs_->wakeup); \ > bs_->wakeup = true; \ > - while ((cond)) { \ > - aio_context_release(ctx_); \ > - aio_poll(qemu_get_aio_context(), true); \ > - aio_context_acquire(ctx_); \ > - waited_ = true; \ > + while (busy_) { \ > + if ((cond)) { \ > + waited_ = busy_ = true; \ > + aio_context_release(ctx_); \ > + aio_poll(qemu_get_aio_context(), true); \ > + aio_context_acquire(ctx_); \ > + } else { \ > + busy_ = aio_poll(ctx_, false); \ > + waited_ |= busy_; \ > + } \ > } \ > bs_->wakeup = false; \ > } \ > -- > 2.9.3 >
On 18/04/2017 12:39, Fam Zheng wrote: > + QLIST_FOREACH_SAFE(child, &bs->children, next, tmp) { > + BlockDriverState *bs = child->bs; > + assert(bs->refcnt > 0); > + bdrv_ref(bs); > + waited |= bdrv_drain_recurse(bs); > + bdrv_unref(bs); > } I think this accesses global state that is not protected by the AioContext lock? Paolo
On Tue, 04/18 14:36, Paolo Bonzini wrote: > > > On 18/04/2017 12:39, Fam Zheng wrote: > > + QLIST_FOREACH_SAFE(child, &bs->children, next, tmp) { > > + BlockDriverState *bs = child->bs; > > + assert(bs->refcnt > 0); > > + bdrv_ref(bs); > > + waited |= bdrv_drain_recurse(bs); > > + bdrv_unref(bs); > > } > > I think this accesses global state that is not protected by the > AioContext lock? Good catch! If called from IOThread, this bdrv_unref is simply wrong, although in practice it cannot delete bs because of the reference held by the owning device. It may be better to wrap the bdrv_ref/bdrv_unref calls with if (qemu_get_current_aio_context() == qemu_get_aio_context()) because only the main loop needs it. Will make this hunk a separate patch in v4. Fam
© 2016 - 2024 Red Hat, Inc.