-
Notifications
You must be signed in to change notification settings - Fork 5.4k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Do not force "hypervisor" flag #22
Conversation
Do not force "hypervisor" flag in order to make possible hidding hypervisor. This is needed for running Hyper-V nested in KVM.
Thanks for the contribution, but qemu does not accept patches via pull-request. Please close this pull-request and submit your patch to the mailing list: |
While I was testing multi-threaded TCG I discovered once consequence of using locking around memory_region_dispatch is that virt-io transactions could dead lock trying to grab the main mutex. This is due to the virt-io driver writing data back into the system memory: #0 0x00007ffff119dcc9 in __GI_raise (sig=sig@entry=6) at ../nptl/sysdeps/unix/sysv/linux/raise.c:56 qemu#1 0x00007ffff11a10d8 in __GI_abort () at abort.c:89 qemu#2 0x00005555555f9b24 in error_exit (err=<optimised out>, msg=msg@entry=0x5555559f3710 <__func__.6011> "qemu_mutex_lock") at util/qemu-thread-posix.c:48 qemu#3 0x000055555594d630 in qemu_mutex_lock (mutex=mutex@entry=0x555555e62e60 <qemu_global_mutex>) at util/qemu-thread-posix.c:79 qemu#4 0x0000555555631a84 in qemu_mutex_lock_iothread () at /home/alex/lsrc/qemu/qemu.git/cpus.c:1128 qemu#5 0x000055555560dd1a in stw_phys_internal (endian=DEVICE_LITTLE_ENDIAN, val=1, addr=<optimised out>, as=0x555555e08060 <address_space_memory>) at /home/alex/lsrc/qemu/qemu.git/exec.c:3010 qemu#6 stw_le_phys (as=as@entry=0x555555e08060 <address_space_memory>, addr=<optimised out>, val=1) at /home/alex/lsrc/qemu/qemu.git/exec.c:3024 qemu#7 0x0000555555696ae5 in virtio_stw_phys (vdev=<optimised out>, value=<optimised out>, pa=<optimised out>) at /home/alex/lsrc/qemu/qemu.git/include/hw/virtio/virtio-access.h:61 qemu#8 vring_avail_event (vq=0x55555648dc00, vq=0x55555648dc00, vq=0x55555648dc00, val=<optimised out>) at /home/alex/lsrc/qemu/qemu.git/hw/virtio/virtio.c:214 qemu#9 virtqueue_pop (vq=0x55555648dc00, elem=elem@entry=0x7fff1403fd98) at /home/alex/lsrc/qemu/qemu.git/hw/virtio/virtio.c:472 qemu#10 0x0000555555653cd1 in virtio_blk_get_request (s=0x555556486830) at /home/alex/lsrc/qemu/qemu.git/hw/block/virtio-blk.c:122 qemu#11 virtio_blk_handle_output (vdev=<optimised out>, vq=<optimised out>) at /home/alex/lsrc/qemu/qemu.git/hw/block/virtio-blk.c:446 qemu#12 0x00005555556414e1 in access_with_adjusted_size (addr=addr@entry=80, value=value@entry=0x7fffa93052b0, size=size@entry=4, access_size_min=<optimised out>, access_size_max=<optimised out>, access=0x5555556413e0 <memory_region_write_accessor>, mr=0x555556b80388) at /home/alex/lsrc/qemu/qemu.git/memory.c:461 qemu#13 0x00005555556471b7 in memory_region_dispatch_write (size=4, data=0, addr=80, mr=0x555556b80388) at /home/alex/lsrc/qemu/qemu.git/memory.c:1103 qemu#14 io_mem_write (mr=mr@entry=0x555556b80388, addr=80, val=<optimised out>, size=size@entry=4) at /home/alex/lsrc/qemu/qemu.git/memory.c:2003 qemu#15 0x000055555560ad6b in address_space_rw_internal (as=<optimised out>, addr=167788112, buf=buf@entry=0x7fffa9305380 "", len=4, is_write=is_write@entry=true, unlocked=<optimised out>, unlocked@entry=false) at /home/alex/lsrc/qemu/qemu.git/exec.c:2318 qemu#16 0x000055555560aea8 in address_space_rw (is_write=true, len=<optimised out>, buf=0x7fffa9305380 "", addr=<optimised out>, as=<optimised out>) at /home/alex/lsrc/qemu/qemu.git/exec.c:2392 qemu#17 address_space_write (len=<optimised out>, buf=0x7fffa9305380 "", addr=<optimised out>, as=<optimised out>) at /home/alex/lsrc/qemu/qemu.git/exec.c:2404 qemu#18 subpage_write (opaque=<optimised out>, addr=<optimised out>, value=<optimised out>, len=<optimised out>) at /home/alex/lsrc/qemu/qemu.git/exec.c:1963 qemu#19 0x00005555556414e1 in access_with_adjusted_size (addr=addr@entry=592, value=value@entry=0x7fffa9305420, size=size@entry=4, access_size_min=<optimised out>, access_size_max=<optimised out>, access=0x5555556413e0 <memory_region_write_accessor>, mr=0x555556bfca20) at /home/alex/lsrc/qemu/qemu.git/memory.c:461 qemu#20 0x00005555556471b7 in memory_region_dispatch_write (size=4, data=0, addr=592, mr=0x555556bfca20) at /home/alex/lsrc/qemu/qemu.git/memory.c:1103 qemu#21 io_mem_write (mr=mr@entry=0x555556bfca20, addr=addr@entry=592, val=val@entry=0, size=size@entry=4) at /home/alex/lsrc/qemu/qemu.git/memory.c:2003 qemu#22 0x000055555564ce16 in io_writel (retaddr=140736492182797, addr=4027616848, val=0, physaddr=592, env=0x55555649e9b0) at /home/alex/lsrc/qemu/qemu.git/softmmu_template.h:386 qemu#23 helper_le_stl_mmu (env=0x55555649e9b0, addr=<optimised out>, val=0, mmu_idx=<optimised out>, retaddr=140736492182797) at /home/alex/lsrc/qemu/qemu.git/softmmu_template.h:426 qemu#24 0x00007fffc49f9d0f in code_gen_buffer () qemu#25 0x00005555556109dc in cpu_tb_exec (tb_ptr=0x7fffc49f9c60 <code_gen_buffer+8371296> "A\213n\374\205\355\017\205\233\001", cpu=0x555556496750) at /home/alex/lsrc/qemu/qemu.git/cpu-exec.c:179 qemu#26 cpu_arm_exec (env=env@entry=0x55555649e9b0) at /home/alex/lsrc/qemu/qemu.git/cpu-exec.c:524 qemu#27 0x0000555555630f28 in tcg_cpu_exec (env=0x55555649e9b0) at /home/alex/lsrc/qemu/qemu.git/cpus.c:1344 qemu#28 tcg_exec_all (cpu=0x555556496750) at /home/alex/lsrc/qemu/qemu.git/cpus.c:1392 qemu#29 qemu_tcg_cpu_thread_fn (arg=0x555556496750) at /home/alex/lsrc/qemu/qemu.git/cpus.c:1037 qemu#30 0x00007ffff1534182 in start_thread (arg=0x7fffa9306700) at pthread_create.c:312 qemu#31 0x00007ffff126147d in clone () at ../sysdeps/unix/sysv/linux/x86_64/clone.S:111 The fix in this patch makes the global/iothread mutex recursive (only if called from the same thread-id). As other threads are still blocked memory is still consistent all the way through. This seems neater than having to do a trylock each time. Tested-by: Alex Bennée <alex.bennee@linaro.org>
While I was testing multi-threaded TCG I discovered once consequence of using locking around memory_region_dispatch is that virt-io transactions could dead lock trying to grab the main mutex. This is due to the virt-io driver writing data back into the system memory: #0 0x00007ffff119dcc9 in __GI_raise (sig=sig@entry=6) at ../nptl/sysdeps/unix/sysv/linux/raise.c:56 qemu#1 0x00007ffff11a10d8 in __GI_abort () at abort.c:89 qemu#2 0x00005555555f9b24 in error_exit (err=<optimised out>, msg=msg@entry=0x5555559f3710 <__func__.6011> "qemu_mutex_lock") at util/qemu-thread-posix.c:48 qemu#3 0x000055555594d630 in qemu_mutex_lock (mutex=mutex@entry=0x555555e62e60 <qemu_global_mutex>) at util/qemu-thread-posix.c:79 qemu#4 0x0000555555631a84 in qemu_mutex_lock_iothread () at /home/alex/lsrc/qemu/qemu.git/cpus.c:1128 qemu#5 0x000055555560dd1a in stw_phys_internal (endian=DEVICE_LITTLE_ENDIAN, val=1, addr=<optimised out>, as=0x555555e08060 <address_space_memory>) at /home/alex/lsrc/qemu/qemu.git/exec.c:3010 qemu#6 stw_le_phys (as=as@entry=0x555555e08060 <address_space_memory>, addr=<optimised out>, val=1) at /home/alex/lsrc/qemu/qemu.git/exec.c:3024 qemu#7 0x0000555555696ae5 in virtio_stw_phys (vdev=<optimised out>, value=<optimised out>, pa=<optimised out>) at /home/alex/lsrc/qemu/qemu.git/include/hw/virtio/virtio-access.h:61 qemu#8 vring_avail_event (vq=0x55555648dc00, vq=0x55555648dc00, vq=0x55555648dc00, val=<optimised out>) at /home/alex/lsrc/qemu/qemu.git/hw/virtio/virtio.c:214 qemu#9 virtqueue_pop (vq=0x55555648dc00, elem=elem@entry=0x7fff1403fd98) at /home/alex/lsrc/qemu/qemu.git/hw/virtio/virtio.c:472 qemu#10 0x0000555555653cd1 in virtio_blk_get_request (s=0x555556486830) at /home/alex/lsrc/qemu/qemu.git/hw/block/virtio-blk.c:122 qemu#11 virtio_blk_handle_output (vdev=<optimised out>, vq=<optimised out>) at /home/alex/lsrc/qemu/qemu.git/hw/block/virtio-blk.c:446 qemu#12 0x00005555556414e1 in access_with_adjusted_size (addr=addr@entry=80, value=value@entry=0x7fffa93052b0, size=size@entry=4, access_size_min=<optimised out>, access_size_max=<optimised out>, access=0x5555556413e0 <memory_region_write_accessor>, mr=0x555556b80388) at /home/alex/lsrc/qemu/qemu.git/memory.c:461 qemu#13 0x00005555556471b7 in memory_region_dispatch_write (size=4, data=0, addr=80, mr=0x555556b80388) at /home/alex/lsrc/qemu/qemu.git/memory.c:1103 qemu#14 io_mem_write (mr=mr@entry=0x555556b80388, addr=80, val=<optimised out>, size=size@entry=4) at /home/alex/lsrc/qemu/qemu.git/memory.c:2003 qemu#15 0x000055555560ad6b in address_space_rw_internal (as=<optimised out>, addr=167788112, buf=buf@entry=0x7fffa9305380 "", len=4, is_write=is_write@entry=true, unlocked=<optimised out>, unlocked@entry=false) at /home/alex/lsrc/qemu/qemu.git/exec.c:2318 qemu#16 0x000055555560aea8 in address_space_rw (is_write=true, len=<optimised out>, buf=0x7fffa9305380 "", addr=<optimised out>, as=<optimised out>) at /home/alex/lsrc/qemu/qemu.git/exec.c:2392 qemu#17 address_space_write (len=<optimised out>, buf=0x7fffa9305380 "", addr=<optimised out>, as=<optimised out>) at /home/alex/lsrc/qemu/qemu.git/exec.c:2404 qemu#18 subpage_write (opaque=<optimised out>, addr=<optimised out>, value=<optimised out>, len=<optimised out>) at /home/alex/lsrc/qemu/qemu.git/exec.c:1963 qemu#19 0x00005555556414e1 in access_with_adjusted_size (addr=addr@entry=592, value=value@entry=0x7fffa9305420, size=size@entry=4, access_size_min=<optimised out>, access_size_max=<optimised out>, access=0x5555556413e0 <memory_region_write_accessor>, mr=0x555556bfca20) at /home/alex/lsrc/qemu/qemu.git/memory.c:461 qemu#20 0x00005555556471b7 in memory_region_dispatch_write (size=4, data=0, addr=592, mr=0x555556bfca20) at /home/alex/lsrc/qemu/qemu.git/memory.c:1103 qemu#21 io_mem_write (mr=mr@entry=0x555556bfca20, addr=addr@entry=592, val=val@entry=0, size=size@entry=4) at /home/alex/lsrc/qemu/qemu.git/memory.c:2003 qemu#22 0x000055555564ce16 in io_writel (retaddr=140736492182797, addr=4027616848, val=0, physaddr=592, env=0x55555649e9b0) at /home/alex/lsrc/qemu/qemu.git/softmmu_template.h:386 qemu#23 helper_le_stl_mmu (env=0x55555649e9b0, addr=<optimised out>, val=0, mmu_idx=<optimised out>, retaddr=140736492182797) at /home/alex/lsrc/qemu/qemu.git/softmmu_template.h:426 qemu#24 0x00007fffc49f9d0f in code_gen_buffer () qemu#25 0x00005555556109dc in cpu_tb_exec (tb_ptr=0x7fffc49f9c60 <code_gen_buffer+8371296> "A\213n\374\205\355\017\205\233\001", cpu=0x555556496750) at /home/alex/lsrc/qemu/qemu.git/cpu-exec.c:179 qemu#26 cpu_arm_exec (env=env@entry=0x55555649e9b0) at /home/alex/lsrc/qemu/qemu.git/cpu-exec.c:524 qemu#27 0x0000555555630f28 in tcg_cpu_exec (env=0x55555649e9b0) at /home/alex/lsrc/qemu/qemu.git/cpus.c:1344 qemu#28 tcg_exec_all (cpu=0x555556496750) at /home/alex/lsrc/qemu/qemu.git/cpus.c:1392 qemu#29 qemu_tcg_cpu_thread_fn (arg=0x555556496750) at /home/alex/lsrc/qemu/qemu.git/cpus.c:1037 qemu#30 0x00007ffff1534182 in start_thread (arg=0x7fffa9306700) at pthread_create.c:312 qemu#31 0x00007ffff126147d in clone () at ../sysdeps/unix/sysv/linux/x86_64/clone.S:111 The fix in this patch makes the global/iothread mutex recursive. However as condition variables are involved we deal with this in our own code by tracking the number of locks held by the thread. This seems neater than having to do a trylock each time. Tested-by: Alex Bennée <alex.bennee@linaro.org> --- v2 - don't actually use pthread recursion mechanism - convert rest of qemu_mutex_lock(&global_global_mutex) to iothread - emulate recursion with thread local tracking
target-mips: add Unified Hosting Interface (UHI) support Signed-off-by: Leon Alrae <leon.alrae@imgtec.com>
Back in the 2.3.0 release we declared qcow[2] encryption as deprecated, warning people that it would be removed in a future release. commit a1f688f Author: Markus Armbruster <armbru@redhat.com> Date: Fri Mar 13 21:09:40 2015 +0100 block: Deprecate QCOW/QCOW2 encryption The code still exists today, but by a (happy?) accident we entirely broke the ability to use qcow[2] encryption in the system emulators in the 2.4.0 release due to commit 8336aaf Author: Daniel P. Berrange <berrange@redhat.com> Date: Tue May 12 17:09:18 2015 +0100 qcow2/qcow: protect against uninitialized encryption key This commit was designed to prevent future coding bugs which might cause QEMU to read/write data on an encrypted block device in plain text mode before a decryption key is set. It turns out this preventative measure was a little too good, because we already had a long standing bug where QEMU read encrypted data in plain text mode during system emulator startup, in order to guess disk geometry: Thread 10 (Thread 0x7fffd3fff700 (LWP 30373)): #0 0x00007fffe90b1a28 in raise () at /lib64/libc.so.6 #1 0x00007fffe90b362a in abort () at /lib64/libc.so.6 #2 0x00007fffe90aa227 in __assert_fail_base () at /lib64/libc.so.6 #3 0x00007fffe90aa2d2 in () at /lib64/libc.so.6 #4 0x000055555587ae19 in qcow2_co_readv (bs=0x5555562accb0, sector_num=0, remaining_sectors=1, qiov=0x7fffffffd260) at block/qcow2.c:1229 #5 0x000055555589b60d in bdrv_aligned_preadv (bs=bs@entry=0x5555562accb0, req=req@entry=0x7fffd3ffea50, offset=offset@entry=0, bytes=bytes@entry=512, align=align@entry=512, qiov=qiov@entry=0x7fffffffd260, flags=0) at block/io.c:908 #6 0x000055555589b8bc in bdrv_co_do_preadv (bs=0x5555562accb0, offset=0, bytes=512, qiov=0x7fffffffd260, flags=<optimized out>) at block/io.c:999 #7 0x000055555589c375 in bdrv_rw_co_entry (opaque=0x7fffffffd210) at block/io.c:544 #8 0x000055555586933b in coroutine_thread (opaque=0x555557876310) at coroutine-gthread.c:134 #9 0x00007ffff64e1835 in g_thread_proxy (data=0x5555562b5590) at gthread.c:778 #10 0x00007ffff6bb760a in start_thread () at /lib64/libpthread.so.0 #11 0x00007fffe917f59d in clone () at /lib64/libc.so.6 Thread 1 (Thread 0x7ffff7ecab40 (LWP 30343)): #0 0x00007fffe91797a9 in syscall () at /lib64/libc.so.6 #1 0x00007ffff64ff87f in g_cond_wait (cond=cond@entry=0x555555e085f0 <coroutine_cond>, mutex=mutex@entry=0x555555e08600 <coroutine_lock>) at gthread-posix.c:1397 #2 0x00005555558692c3 in qemu_coroutine_switch (co=<optimized out>) at coroutine-gthread.c:117 #3 0x00005555558692c3 in qemu_coroutine_switch (from_=0x5555562b5e30, to_=to_@entry=0x555557876310, action=action@entry=COROUTINE_ENTER) at coroutine-gthread.c:175 #4 0x0000555555868a90 in qemu_coroutine_enter (co=0x555557876310, opaque=0x0) at qemu-coroutine.c:116 #5 0x0000555555859b84 in thread_pool_completion_bh (opaque=0x7fffd40010e0) at thread-pool.c:187 #6 0x0000555555859514 in aio_bh_poll (ctx=ctx@entry=0x5555562953b0) at async.c:85 #7 0x0000555555864d10 in aio_dispatch (ctx=ctx@entry=0x5555562953b0) at aio-posix.c:135 #8 0x0000555555864f75 in aio_poll (ctx=ctx@entry=0x5555562953b0, blocking=blocking@entry=true) at aio-posix.c:291 #9 0x000055555589c40d in bdrv_prwv_co (bs=bs@entry=0x5555562accb0, offset=offset@entry=0, qiov=qiov@entry=0x7fffffffd260, is_write=is_write@entry=false, flags=flags@entry=(unknown: 0)) at block/io.c:591 #10 0x000055555589c503 in bdrv_rw_co (bs=bs@entry=0x5555562accb0, sector_num=sector_num@entry=0, buf=buf@entry=0x7fffffffd2e0 "\321,", nb_sectors=nb_sectors@entry=21845, is_write=is_write@entry=false, flags=flags@entry=(unknown: 0)) at block/io.c:614 #11 0x000055555589c562 in bdrv_read_unthrottled (nb_sectors=21845, buf=0x7fffffffd2e0 "\321,", sector_num=0, bs=0x5555562accb0) at block/io.c:622 #12 0x000055555589c562 in bdrv_read_unthrottled (bs=0x5555562accb0, sector_num=sector_num@entry=0, buf=buf@entry=0x7fffffffd2e0 "\321,", nb_sectors=nb_sectors@entry=21845) at block/io.c:634 nb_sectors@entry=1) at block/block-backend.c:504 #14 0x0000555555752e9f in guess_disk_lchs (blk=blk@entry=0x5555562a5290, pcylinders=pcylinders@entry=0x7fffffffd52c, pheads=pheads@entry=0x7fffffffd530, psectors=psectors@entry=0x7fffffffd534) at hw/block/hd-geometry.c:68 #15 0x0000555555752ff7 in hd_geometry_guess (blk=0x5555562a5290, pcyls=pcyls@entry=0x555557875d1c, pheads=pheads@entry=0x555557875d20, psecs=psecs@entry=0x555557875d24, ptrans=ptrans@entry=0x555557875d28) at hw/block/hd-geometry.c:133 #16 0x0000555555752b87 in blkconf_geometry (conf=conf@entry=0x555557875d00, ptrans=ptrans@entry=0x555557875d28, cyls_max=cyls_max@entry=65536, heads_max=heads_max@entry=16, secs_max=secs_max@entry=255, errp=errp@entry=0x7fffffffd5e0) at hw/block/block.c:71 #17 0x0000555555799bc4 in ide_dev_initfn (dev=0x555557875c80, kind=IDE_HD) at hw/ide/qdev.c:174 #18 0x0000555555768394 in device_realize (dev=0x555557875c80, errp=0x7fffffffd640) at hw/core/qdev.c:247 #19 0x0000555555769a81 in device_set_realized (obj=0x555557875c80, value=<optimized out>, errp=0x7fffffffd730) at hw/core/qdev.c:1058 #20 0x00005555558240ce in property_set_bool (obj=0x555557875c80, v=<optimized out>, opaque=0x555557875de0, name=<optimized out>, errp=0x7fffffffd730) at qom/object.c:1514 #21 0x0000555555826c87 in object_property_set_qobject (obj=obj@entry=0x555557875c80, value=value@entry=0x55555784bcb0, name=name@entry=0x55555591cb3d "realized", errp=errp@entry=0x7fffffffd730) at qom/qom-qobject.c:24 #22 0x0000555555825760 in object_property_set_bool (obj=obj@entry=0x555557875c80, value=value@entry=true, name=name@entry=0x55555591cb3d "realized", errp=errp@entry=0x7fffffffd730) at qom/object.c:905 #23 0x000055555576897b in qdev_init_nofail (dev=dev@entry=0x555557875c80) at hw/core/qdev.c:380 #24 0x0000555555799ead in ide_create_drive (bus=bus@entry=0x555557629630, unit=unit@entry=0, drive=0x5555562b77e0) at hw/ide/qdev.c:122 #25 0x000055555579a746 in pci_ide_create_devs (dev=dev@entry=0x555557628db0, hd_table=hd_table@entry=0x7fffffffd830) at hw/ide/pci.c:440 #26 0x000055555579b165 in pci_piix3_ide_init (bus=<optimized out>, hd_table=0x7fffffffd830, devfn=<optimized out>) at hw/ide/piix.c:218 #27 0x000055555568ca55 in pc_init1 (machine=0x5555562960a0, pci_enabled=1, kvmclock_enabled=<optimized out>) at /home/berrange/src/virt/qemu/hw/i386/pc_piix.c:256 #28 0x0000555555603ab2 in main (argc=<optimized out>, argv=<optimized out>, envp=<optimized out>) at vl.c:4249 So the safety net is correctly preventing QEMU reading cipher text as if it were plain text, during startup and aborting QEMU to avoid bad usage of this data. For added fun this bug only happens if the encrypted qcow2 file happens to have data written to the first cluster, otherwise the cluster won't be allocated and so qcow2 would not try the decryption routines at all, just return all 0's. That no one even noticed, let alone reported, this bug that has shipped in 2.4.0, 2.5.0 and 2.6.0 shows that the number of actual users of encrypted qcow2 is approximately zero. So rather than fix the crash, and backport it to stable releases, just go ahead with what we have warned users about and disable any use of qcow2 encryption in the system emulators. qemu-img/qemu-io/qemu-nbd are still able to access qcow2 encrypted images for the sake of data conversion. In the future, qcow2 will gain support for the alternative luks format, but when this happens it'll be using the '-object secret' infrastructure for getting keys, which avoids this problematic scenario entirely. Signed-off-by: Daniel P. Berrange <berrange@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
ahci-test /x86_64/ahci/io/dma/lba28/retry triggers the following leak: Direct leak of 16 byte(s) in 1 object(s) allocated from: #0 0x7fc4b2a25e20 in malloc (/lib64/libasan.so.3+0xc6e20) qemu#1 0x7fc4993bce58 in g_malloc (/lib64/libglib-2.0.so.0+0x4ee58) qemu#2 0x556a187d4b34 in ahci_populate_sglist hw/ide/ahci.c:896 qemu#3 0x556a187d8237 in ahci_dma_prepare_buf hw/ide/ahci.c:1367 qemu#4 0x556a187b5a1a in ide_dma_cb hw/ide/core.c:844 qemu#5 0x556a187d7eec in ahci_start_dma hw/ide/ahci.c:1333 qemu#6 0x556a187b650b in ide_start_dma hw/ide/core.c:921 qemu#7 0x556a187b61e6 in ide_sector_start_dma hw/ide/core.c:911 qemu#8 0x556a187b9e26 in cmd_write_dma hw/ide/core.c:1486 qemu#9 0x556a187bd519 in ide_exec_cmd hw/ide/core.c:2027 qemu#10 0x556a187d71c5 in handle_reg_h2d_fis hw/ide/ahci.c:1204 qemu#11 0x556a187d7681 in handle_cmd hw/ide/ahci.c:1254 qemu#12 0x556a187d168a in check_cmd hw/ide/ahci.c:510 qemu#13 0x556a187d0afc in ahci_port_write hw/ide/ahci.c:314 qemu#14 0x556a187d105d in ahci_mem_write hw/ide/ahci.c:435 qemu#15 0x556a1831d959 in memory_region_write_accessor /home/elmarco/src/qemu/memory.c:525 qemu#16 0x556a1831dc35 in access_with_adjusted_size /home/elmarco/src/qemu/memory.c:591 qemu#17 0x556a18323ce3 in memory_region_dispatch_write /home/elmarco/src/qemu/memory.c:1262 qemu#18 0x556a1828cf67 in address_space_write_continue /home/elmarco/src/qemu/exec.c:2578 qemu#19 0x556a1828d20b in address_space_write /home/elmarco/src/qemu/exec.c:2635 qemu#20 0x556a1828d92b in address_space_rw /home/elmarco/src/qemu/exec.c:2737 qemu#21 0x556a1828daf7 in cpu_physical_memory_rw /home/elmarco/src/qemu/exec.c:2746 qemu#22 0x556a183068d3 in cpu_physical_memory_write /home/elmarco/src/qemu/include/exec/cpu-common.h:72 qemu#23 0x556a18308194 in qtest_process_command /home/elmarco/src/qemu/qtest.c:382 qemu#24 0x556a18309999 in qtest_process_inbuf /home/elmarco/src/qemu/qtest.c:573 qemu#25 0x556a18309a4a in qtest_read /home/elmarco/src/qemu/qtest.c:585 qemu#26 0x556a18598b85 in qemu_chr_be_write_impl /home/elmarco/src/qemu/qemu-char.c:387 qemu#27 0x556a18598c52 in qemu_chr_be_write /home/elmarco/src/qemu/qemu-char.c:399 qemu#28 0x556a185a2afa in tcp_chr_read /home/elmarco/src/qemu/qemu-char.c:2902 qemu#29 0x556a18cbaf52 in qio_channel_fd_source_dispatch io/channel-watch.c:84 Follow John Snow recommendation: Everywhere else ncq_err is used, it is accompanied by a list cleanup except for ncq_cb, which is the case you are fixing here. Move the sglist destruction inside of ncq_err and then delete it from the other two locations to keep it tidy. Call dma_buf_commit in ide_dma_cb after the early return. Though, this is also a little wonky because this routine does more than clear the list, but it is at the moment the centralized "we're done with the sglist" function and none of the other side effects that occur in dma_buf_commit will interfere with the reset that occurs from ide_restart_bh, I think Signed-off-by: Marc-André Lureau <marcandre.lureau@redhat.com>
Since aa5cb7f, the chardevs are being cleaned up when leaving qemu. However, the monitor has still references to them, which may lead to crashes when running atexit() and trying to send monitor events: #0 0x00007fffdb18f6f5 in __GI_raise (sig=sig@entry=6) at ../sysdeps/unix/sysv/linux/raise.c:54 qemu#1 0x00007fffdb1912fa in __GI_abort () at abort.c:89 qemu#2 0x0000555555c263e7 in error_exit (err=22, msg=0x555555d47980 <__func__.13537> "qemu_mutex_lock") at util/qemu-thread-posix.c:39 qemu#3 0x0000555555c26488 in qemu_mutex_lock (mutex=0x5555567a2420) at util/qemu-thread-posix.c:66 qemu#4 0x00005555558c52db in qemu_chr_fe_write (s=0x5555567a2420, buf=0x55555740dc40 "{\"timestamp\": {\"seconds\": 1470041716, \"microseconds\": 989699}, \"event\": \"SPICE_DISCONNECTED\", \"data\": {\"server\": {\"port\": \"5900\", \"family\": \"ipv4\", \"host\": \"127.0.0.1\"}, \"client\": {\"port\": \"40272\", \"f"..., len=240) at qemu-char.c:280 qemu#5 0x0000555555787cad in monitor_flush_locked (mon=0x5555567bd9e0) at /home/elmarco/src/qemu/monitor.c:311 qemu#6 0x0000555555787e46 in monitor_puts (mon=0x5555567bd9e0, str=0x5555567a44ef "") at /home/elmarco/src/qemu/monitor.c:353 qemu#7 0x00005555557880fe in monitor_json_emitter (mon=0x5555567bd9e0, data=0x5555567c73a0) at /home/elmarco/src/qemu/monitor.c:401 qemu#8 0x00005555557882d2 in monitor_qapi_event_emit (event=QAPI_EVENT_SPICE_DISCONNECTED, qdict=0x5555567c73a0) at /home/elmarco/src/qemu/monitor.c:472 qemu#9 0x000055555578838f in monitor_qapi_event_queue (event=QAPI_EVENT_SPICE_DISCONNECTED, qdict=0x5555567c73a0, errp=0x7fffffffca88) at /home/elmarco/src/qemu/monitor.c:497 qemu#10 0x0000555555c15541 in qapi_event_send_spice_disconnected (server=0x5555571139d0, client=0x5555570d0db0, errp=0x5555566c0428 <error_abort>) at qapi-event.c:1038 qemu#11 0x0000555555b11bc6 in channel_event (event=3, info=0x5555570d6c00) at ui/spice-core.c:248 qemu#12 0x00007fffdcc9983a in adapter_channel_event (event=3, info=0x5555570d6c00) at reds.c:120 qemu#13 0x00007fffdcc99a25 in reds_handle_channel_event (reds=0x5555567a9d60, event=3, info=0x5555570d6c00) at reds.c:324 qemu#14 0x00007fffdcc7d4c4 in main_dispatcher_self_handle_channel_event (self=0x5555567b28b0, event=3, info=0x5555570d6c00) at main-dispatcher.c:175 qemu#15 0x00007fffdcc7d5b1 in main_dispatcher_channel_event (self=0x5555567b28b0, event=3, info=0x5555570d6c00) at main-dispatcher.c:194 qemu#16 0x00007fffdcca7674 in reds_stream_push_channel_event (s=0x5555570d9910, event=3) at reds-stream.c:354 qemu#17 0x00007fffdcca749b in reds_stream_free (s=0x5555570d9910) at reds-stream.c:323 qemu#18 0x00007fffdccb5dad in snd_disconnect_channel (channel=0x5555576a89a0) at sound.c:229 qemu#19 0x00007fffdccb9e57 in snd_detach_common (worker=0x555557739720) at sound.c:1589 qemu#20 0x00007fffdccb9f0e in snd_detach_playback (sin=0x5555569fe3f8) at sound.c:1602 qemu#21 0x00007fffdcca3373 in spice_server_remove_interface (sin=0x5555569fe3f8) at reds.c:3387 qemu#22 0x00005555558ff6e2 in line_out_fini (hw=0x5555569fe370) at audio/spiceaudio.c:152 qemu#23 0x00005555558f909e in audio_atexit () at audio/audio.c:1754 qemu#24 0x00007fffdb1941e8 in __run_exit_handlers (status=0, listp=0x7fffdb5175d8 <__exit_funcs>, run_list_atexit=run_list_atexit@entry=true) at exit.c:82 qemu#25 0x00007fffdb194235 in __GI_exit (status=<optimized out>) at exit.c:104 qemu#26 0x00007fffdb17b738 in __libc_start_main (main=0x5555558d7874 <main>, argc=67, argv=0x7fffffffcf48, init=<optimized out>, fini=<optimized out>, rtld_fini=<optimized out>, stack_end=0x7fffffffcf38) at ../csu/libc-start.c:323 Add a monitor_cleanup() functions to remove all the monitors before cleaning up the chardev. Note that we are "losing" some events that used to be sent during atexit(). Signed-off-by: Marc-André Lureau <marcandre.lureau@redhat.com>
The vnc_server_info_get will allocate the VncServerInfo struct and then call vnc_init_basic_info_from_server_addr to populate the basic fields. If this returns an error though, the qapi_free_VncServerInfo call will then crash because the VncServerInfo struct instance was not properly NULL-initialized and thus contains random stack garbage. #0 0x00007f1987c8e6f5 in raise () at /lib64/libc.so.6 qemu#1 0x00007f1987c902fa in abort () at /lib64/libc.so.6 qemu#2 0x00007f1987ccf600 in __libc_message () at /lib64/libc.so.6 qemu#3 0x00007f1987cd7d4a in _int_free () at /lib64/libc.so.6 qemu#4 0x00007f1987cdb2ac in free () at /lib64/libc.so.6 qemu#5 0x00007f198b654f6e in g_free () at /lib64/libglib-2.0.so.0 qemu#6 0x0000559193cdcf54 in visit_type_str (v=v@entry= 0x5591972f14b0, name=name@entry=0x559193de1e29 "host", obj=obj@entry=0x5591961dbfa0, errp=errp@entry=0x7fffd7899d80) at qapi/qapi-visit-core.c:255 qemu#7 0x0000559193cca8f3 in visit_type_VncBasicInfo_members (v=v@entry= 0x5591972f14b0, obj=obj@entry=0x5591961dbfa0, errp=errp@entry=0x7fffd7899dc0) at qapi-visit.c:12307 qemu#8 0x0000559193ccb523 in visit_type_VncServerInfo_members (v=v@entry= 0x5591972f14b0, obj=0x5591961dbfa0, errp=errp@entry=0x7fffd7899e00) at qapi-visit.c:12632 qemu#9 0x0000559193ccb60b in visit_type_VncServerInfo (v=v@entry= 0x5591972f14b0, name=name@entry=0x0, obj=obj@entry=0x7fffd7899e48, errp=errp@entry=0x0) at qapi-visit.c:12658 qemu#10 0x0000559193cb53d8 in qapi_free_VncServerInfo (obj=<optimized out>) at qapi-types.c:3970 qemu#11 0x0000559193c1e6ba in vnc_server_info_get (vd=0x7f1951498010) at ui/vnc.c:233 qemu#12 0x0000559193c24275 in vnc_connect (vs=0x559197b2f200, vs=0x559197b2f200, event=QAPI_EVENT_VNC_CONNECTED) at ui/vnc.c:284 qemu#13 0x0000559193c24275 in vnc_connect (vd=vd@entry=0x7f1951498010, sioc=sioc@entry=0x559196bf9c00, skipauth=skipauth@entry=tru e, websocket=websocket@entry=false) at ui/vnc.c:3039 qemu#14 0x0000559193c25806 in vnc_display_add_client (id=<optimized out>, csock=<optimized out>, skipauth=<optimized out>) at ui/vnc.c:3877 qemu#15 0x0000559193a90c28 in qmp_marshal_add_client (args=<optimized out>, ret=<optimized out>, errp=0x7fffd7899f90) at qmp-marshal.c:105 qemu#16 0x000055919399c2b7 in handle_qmp_command (parser=<optimized out>, tokens=<optimized out>) at /home/berrange/src/virt/qemu/monitor.c:3971 qemu#17 0x0000559193ce3307 in json_message_process_token (lexer=0x559194ab0838, input=0x559194a6d940, type=JSON_RCURLY, x=111, y=1 2) at qobject/json-streamer.c:105 qemu#18 0x0000559193cfa90d in json_lexer_feed_char (lexer=lexer@entry=0x559194ab0838, ch=125 '}', flush=flush@entry=false) at qobject/json-lexer.c:319 qemu#19 0x0000559193cfaa1e in json_lexer_feed (lexer=0x559194ab0838, buffer=<optimized out>, size=<optimized out>) at qobject/json-lexer.c:369 qemu#20 0x0000559193ce33c9 in json_message_parser_feed (parser=<optimized out>, buffer=<optimized out>, size=<optimized out>) at qobject/json-streamer.c:124 qemu#21 0x000055919399a85b in monitor_qmp_read (opaque=<optimized out>, buf=<optimized out>, size=<optimized out>) at /home/berrange/src/virt/qemu/monitor.c:3987 qemu#22 0x0000559193a87d00 in tcp_chr_read (chan=<optimized out>, cond=<optimized out>, opaque=0x559194a7d900) at qemu-char.c:2895 qemu#23 0x00007f198b64f703 in g_main_context_dispatch () at /lib64/libglib-2.0.so.0 qemu#24 0x0000559193c484b3 in main_loop_wait () at main-loop.c:213 qemu#25 0x0000559193c484b3 in main_loop_wait (timeout=<optimized out>) at main-loop.c:258 qemu#26 0x0000559193c484b3 in main_loop_wait (nonblocking=<optimized out>) at main-loop.c:506 qemu#27 0x0000559193964c55 in main () at vl.c:1908 qemu#28 0x0000559193964c55 in main (argc=<optimized out>, argv=<optimized out>, envp=<optimized out>) at vl.c:4603 This was introduced in commit 98481bf Author: Eric Blake <eblake@redhat.com> Date: Mon Oct 26 16:34:45 2015 -0600 vnc: Hoist allocation of VncBasicInfo to callers which added error reporting for vnc_init_basic_info_from_server_addr but didn't change the g_malloc calls to g_malloc0. Signed-off-by: Daniel P. Berrange <berrange@redhat.com>
The vnc_server_info_get will allocate the VncServerInfo struct and then call vnc_init_basic_info_from_server_addr to populate the basic fields. If this returns an error though, the qapi_free_VncServerInfo call will then crash because the VncServerInfo struct instance was not properly NULL-initialized and thus contains random stack garbage. #0 0x00007f1987c8e6f5 in raise () at /lib64/libc.so.6 #1 0x00007f1987c902fa in abort () at /lib64/libc.so.6 #2 0x00007f1987ccf600 in __libc_message () at /lib64/libc.so.6 #3 0x00007f1987cd7d4a in _int_free () at /lib64/libc.so.6 #4 0x00007f1987cdb2ac in free () at /lib64/libc.so.6 #5 0x00007f198b654f6e in g_free () at /lib64/libglib-2.0.so.0 #6 0x0000559193cdcf54 in visit_type_str (v=v@entry= 0x5591972f14b0, name=name@entry=0x559193de1e29 "host", obj=obj@entry=0x5591961dbfa0, errp=errp@entry=0x7fffd7899d80) at qapi/qapi-visit-core.c:255 #7 0x0000559193cca8f3 in visit_type_VncBasicInfo_members (v=v@entry= 0x5591972f14b0, obj=obj@entry=0x5591961dbfa0, errp=errp@entry=0x7fffd7899dc0) at qapi-visit.c:12307 #8 0x0000559193ccb523 in visit_type_VncServerInfo_members (v=v@entry= 0x5591972f14b0, obj=0x5591961dbfa0, errp=errp@entry=0x7fffd7899e00) at qapi-visit.c:12632 #9 0x0000559193ccb60b in visit_type_VncServerInfo (v=v@entry= 0x5591972f14b0, name=name@entry=0x0, obj=obj@entry=0x7fffd7899e48, errp=errp@entry=0x0) at qapi-visit.c:12658 #10 0x0000559193cb53d8 in qapi_free_VncServerInfo (obj=<optimized out>) at qapi-types.c:3970 #11 0x0000559193c1e6ba in vnc_server_info_get (vd=0x7f1951498010) at ui/vnc.c:233 #12 0x0000559193c24275 in vnc_connect (vs=0x559197b2f200, vs=0x559197b2f200, event=QAPI_EVENT_VNC_CONNECTED) at ui/vnc.c:284 #13 0x0000559193c24275 in vnc_connect (vd=vd@entry=0x7f1951498010, sioc=sioc@entry=0x559196bf9c00, skipauth=skipauth@entry=tru e, websocket=websocket@entry=false) at ui/vnc.c:3039 #14 0x0000559193c25806 in vnc_display_add_client (id=<optimized out>, csock=<optimized out>, skipauth=<optimized out>) at ui/vnc.c:3877 #15 0x0000559193a90c28 in qmp_marshal_add_client (args=<optimized out>, ret=<optimized out>, errp=0x7fffd7899f90) at qmp-marshal.c:105 #16 0x000055919399c2b7 in handle_qmp_command (parser=<optimized out>, tokens=<optimized out>) at /home/berrange/src/virt/qemu/monitor.c:3971 #17 0x0000559193ce3307 in json_message_process_token (lexer=0x559194ab0838, input=0x559194a6d940, type=JSON_RCURLY, x=111, y=1 2) at qobject/json-streamer.c:105 #18 0x0000559193cfa90d in json_lexer_feed_char (lexer=lexer@entry=0x559194ab0838, ch=125 '}', flush=flush@entry=false) at qobject/json-lexer.c:319 #19 0x0000559193cfaa1e in json_lexer_feed (lexer=0x559194ab0838, buffer=<optimized out>, size=<optimized out>) at qobject/json-lexer.c:369 #20 0x0000559193ce33c9 in json_message_parser_feed (parser=<optimized out>, buffer=<optimized out>, size=<optimized out>) at qobject/json-streamer.c:124 #21 0x000055919399a85b in monitor_qmp_read (opaque=<optimized out>, buf=<optimized out>, size=<optimized out>) at /home/berrange/src/virt/qemu/monitor.c:3987 #22 0x0000559193a87d00 in tcp_chr_read (chan=<optimized out>, cond=<optimized out>, opaque=0x559194a7d900) at qemu-char.c:2895 #23 0x00007f198b64f703 in g_main_context_dispatch () at /lib64/libglib-2.0.so.0 #24 0x0000559193c484b3 in main_loop_wait () at main-loop.c:213 #25 0x0000559193c484b3 in main_loop_wait (timeout=<optimized out>) at main-loop.c:258 #26 0x0000559193c484b3 in main_loop_wait (nonblocking=<optimized out>) at main-loop.c:506 #27 0x0000559193964c55 in main () at vl.c:1908 #28 0x0000559193964c55 in main (argc=<optimized out>, argv=<optimized out>, envp=<optimized out>) at vl.c:4603 This was introduced in commit 98481bf Author: Eric Blake <eblake@redhat.com> Date: Mon Oct 26 16:34:45 2015 -0600 vnc: Hoist allocation of VncBasicInfo to callers which added error reporting for vnc_init_basic_info_from_server_addr but didn't change the g_malloc calls to g_malloc0. Signed-off-by: Daniel P. Berrange <berrange@redhat.com> Message-id: 1470134726-15697-3-git-send-email-berrange@redhat.com Signed-off-by: Gerd Hoffmann <kraxel@redhat.com>
ahci-test /x86_64/ahci/io/dma/lba28/retry triggers the following leak: Direct leak of 16 byte(s) in 1 object(s) allocated from: #0 0x7fc4b2a25e20 in malloc (/lib64/libasan.so.3+0xc6e20) #1 0x7fc4993bce58 in g_malloc (/lib64/libglib-2.0.so.0+0x4ee58) #2 0x556a187d4b34 in ahci_populate_sglist hw/ide/ahci.c:896 qemu#3 0x556a187d8237 in ahci_dma_prepare_buf hw/ide/ahci.c:1367 qemu#4 0x556a187b5a1a in ide_dma_cb hw/ide/core.c:844 qemu#5 0x556a187d7eec in ahci_start_dma hw/ide/ahci.c:1333 qemu#6 0x556a187b650b in ide_start_dma hw/ide/core.c:921 qemu#7 0x556a187b61e6 in ide_sector_start_dma hw/ide/core.c:911 qemu#8 0x556a187b9e26 in cmd_write_dma hw/ide/core.c:1486 qemu#9 0x556a187bd519 in ide_exec_cmd hw/ide/core.c:2027 qemu#10 0x556a187d71c5 in handle_reg_h2d_fis hw/ide/ahci.c:1204 qemu#11 0x556a187d7681 in handle_cmd hw/ide/ahci.c:1254 qemu#12 0x556a187d168a in check_cmd hw/ide/ahci.c:510 qemu#13 0x556a187d0afc in ahci_port_write hw/ide/ahci.c:314 qemu#14 0x556a187d105d in ahci_mem_write hw/ide/ahci.c:435 qemu#15 0x556a1831d959 in memory_region_write_accessor /home/elmarco/src/qemu/memory.c:525 qemu#16 0x556a1831dc35 in access_with_adjusted_size /home/elmarco/src/qemu/memory.c:591 qemu#17 0x556a18323ce3 in memory_region_dispatch_write /home/elmarco/src/qemu/memory.c:1262 qemu#18 0x556a1828cf67 in address_space_write_continue /home/elmarco/src/qemu/exec.c:2578 qemu#19 0x556a1828d20b in address_space_write /home/elmarco/src/qemu/exec.c:2635 qemu#20 0x556a1828d92b in address_space_rw /home/elmarco/src/qemu/exec.c:2737 qemu#21 0x556a1828daf7 in cpu_physical_memory_rw /home/elmarco/src/qemu/exec.c:2746 qemu#22 0x556a183068d3 in cpu_physical_memory_write /home/elmarco/src/qemu/include/exec/cpu-common.h:72 qemu#23 0x556a18308194 in qtest_process_command /home/elmarco/src/qemu/qtest.c:382 qemu#24 0x556a18309999 in qtest_process_inbuf /home/elmarco/src/qemu/qtest.c:573 qemu#25 0x556a18309a4a in qtest_read /home/elmarco/src/qemu/qtest.c:585 qemu#26 0x556a18598b85 in qemu_chr_be_write_impl /home/elmarco/src/qemu/qemu-char.c:387 qemu#27 0x556a18598c52 in qemu_chr_be_write /home/elmarco/src/qemu/qemu-char.c:399 qemu#28 0x556a185a2afa in tcp_chr_read /home/elmarco/src/qemu/qemu-char.c:2902 qemu#29 0x556a18cbaf52 in qio_channel_fd_source_dispatch io/channel-watch.c:84 Follow John Snow recommendation: Everywhere else ncq_err is used, it is accompanied by a list cleanup except for ncq_cb, which is the case you are fixing here. Move the sglist destruction inside of ncq_err and then delete it from the other two locations to keep it tidy. Call dma_buf_commit in ide_dma_cb after the early return. Though, this is also a little wonky because this routine does more than clear the list, but it is at the moment the centralized "we're done with the sglist" function and none of the other side effects that occur in dma_buf_commit will interfere with the reset that occurs from ide_restart_bh, I think Signed-off-by: Marc-André Lureau <marcandre.lureau@redhat.com> Reviewed-by: John Snow <jsnow@redhat.com>
Since aa5cb7f, the chardevs are being cleaned up when leaving qemu. However, the monitor has still references to them, which may lead to crashes when running atexit() and trying to send monitor events: #0 0x00007fffdb18f6f5 in __GI_raise (sig=sig@entry=6) at ../sysdeps/unix/sysv/linux/raise.c:54 #1 0x00007fffdb1912fa in __GI_abort () at abort.c:89 #2 0x0000555555c263e7 in error_exit (err=22, msg=0x555555d47980 <__func__.13537> "qemu_mutex_lock") at util/qemu-thread-posix.c:39 #3 0x0000555555c26488 in qemu_mutex_lock (mutex=0x5555567a2420) at util/qemu-thread-posix.c:66 #4 0x00005555558c52db in qemu_chr_fe_write (s=0x5555567a2420, buf=0x55555740dc40 "{\"timestamp\": {\"seconds\": 1470041716, \"microseconds\": 989699}, \"event\": \"SPICE_DISCONNECTED\", \"data\": {\"server\": {\"port\": \"5900\", \"family\": \"ipv4\", \"host\": \"127.0.0.1\"}, \"client\": {\"port\": \"40272\", \"f"..., len=240) at qemu-char.c:280 #5 0x0000555555787cad in monitor_flush_locked (mon=0x5555567bd9e0) at /home/elmarco/src/qemu/monitor.c:311 #6 0x0000555555787e46 in monitor_puts (mon=0x5555567bd9e0, str=0x5555567a44ef "") at /home/elmarco/src/qemu/monitor.c:353 #7 0x00005555557880fe in monitor_json_emitter (mon=0x5555567bd9e0, data=0x5555567c73a0) at /home/elmarco/src/qemu/monitor.c:401 #8 0x00005555557882d2 in monitor_qapi_event_emit (event=QAPI_EVENT_SPICE_DISCONNECTED, qdict=0x5555567c73a0) at /home/elmarco/src/qemu/monitor.c:472 #9 0x000055555578838f in monitor_qapi_event_queue (event=QAPI_EVENT_SPICE_DISCONNECTED, qdict=0x5555567c73a0, errp=0x7fffffffca88) at /home/elmarco/src/qemu/monitor.c:497 #10 0x0000555555c15541 in qapi_event_send_spice_disconnected (server=0x5555571139d0, client=0x5555570d0db0, errp=0x5555566c0428 <error_abort>) at qapi-event.c:1038 #11 0x0000555555b11bc6 in channel_event (event=3, info=0x5555570d6c00) at ui/spice-core.c:248 #12 0x00007fffdcc9983a in adapter_channel_event (event=3, info=0x5555570d6c00) at reds.c:120 #13 0x00007fffdcc99a25 in reds_handle_channel_event (reds=0x5555567a9d60, event=3, info=0x5555570d6c00) at reds.c:324 #14 0x00007fffdcc7d4c4 in main_dispatcher_self_handle_channel_event (self=0x5555567b28b0, event=3, info=0x5555570d6c00) at main-dispatcher.c:175 #15 0x00007fffdcc7d5b1 in main_dispatcher_channel_event (self=0x5555567b28b0, event=3, info=0x5555570d6c00) at main-dispatcher.c:194 #16 0x00007fffdcca7674 in reds_stream_push_channel_event (s=0x5555570d9910, event=3) at reds-stream.c:354 #17 0x00007fffdcca749b in reds_stream_free (s=0x5555570d9910) at reds-stream.c:323 #18 0x00007fffdccb5dad in snd_disconnect_channel (channel=0x5555576a89a0) at sound.c:229 #19 0x00007fffdccb9e57 in snd_detach_common (worker=0x555557739720) at sound.c:1589 #20 0x00007fffdccb9f0e in snd_detach_playback (sin=0x5555569fe3f8) at sound.c:1602 #21 0x00007fffdcca3373 in spice_server_remove_interface (sin=0x5555569fe3f8) at reds.c:3387 #22 0x00005555558ff6e2 in line_out_fini (hw=0x5555569fe370) at audio/spiceaudio.c:152 #23 0x00005555558f909e in audio_atexit () at audio/audio.c:1754 #24 0x00007fffdb1941e8 in __run_exit_handlers (status=0, listp=0x7fffdb5175d8 <__exit_funcs>, run_list_atexit=run_list_atexit@entry=true) at exit.c:82 #25 0x00007fffdb194235 in __GI_exit (status=<optimized out>) at exit.c:104 #26 0x00007fffdb17b738 in __libc_start_main (main=0x5555558d7874 <main>, argc=67, argv=0x7fffffffcf48, init=<optimized out>, fini=<optimized out>, rtld_fini=<optimized out>, stack_end=0x7fffffffcf38) at ../csu/libc-start.c:323 Add a monitor_cleanup() functions to remove all the monitors before cleaning up the chardev. Note that we are "losing" some events that used to be sent during atexit(). Signed-off-by: Marc-André Lureau <marcandre.lureau@redhat.com> Message-Id: <20160801112343.29082-2-marcandre.lureau@redhat.com> Reviewed-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Markus Armbruster <armbru@redhat.com> Signed-off-by: Markus Armbruster <armbru@redhat.com>
Program terminated with signal SIGSEGV, Segmentation fault. #0 0x000055baf6ab4adc in qemu_opt_foreach (opts=0x0, func=0x55baf696b650 <net_vhost_chardev_opts>, opaque=0x7ffc51368c00, errp=0x7ffc51368e48) at util/qemu-option.c:617 617 QTAILQ_FOREACH(opt, &opts->head, next) { [Current thread is 1 (Thread 0x7f1d4970bb40 (LWP 6603))] (gdb) bt #0 0x000055baf6ab4adc in qemu_opt_foreach (opts=0x0, func=0x55baf696b650 <net_vhost_chardev_opts>, opaque=0x7ffc51368c00, errp=0x7ffc51368e48) at util/qemu-option.c:617 qemu#1 0x000055baf696b7da in net_vhost_parse_chardev (opts=0x55baf8ff9260, errp=0x7ffc51368e48) at net/vhost-user.c:314 qemu#2 0x000055baf696b985 in net_init_vhost_user (netdev=0x55baf8ff9250, name=0x55baf879d270 "hostnet2", peer=0x0, errp=0x7ffc51368e48) at net/vhost-user.c:360 qemu#3 0x000055baf6960216 in net_client_init1 (object=0x55baf8ff9250, is_netdev=true, errp=0x7ffc51368e48) at net/net.c:1051 qemu#4 0x000055baf6960518 in net_client_init (opts=0x55baf776e7e0, is_netdev=true, errp=0x7ffc51368f00) at net/net.c:1108 qemu#5 0x000055baf696083f in netdev_add (opts=0x55baf776e7e0, errp=0x7ffc51368f00) at net/net.c:1186 qemu#6 0x000055baf69608c7 in qmp_netdev_add (qdict=0x55baf7afaf60, ret=0x7ffc51368f50, errp=0x7ffc51368f48) at net/net.c:1205 qemu#7 0x000055baf6622135 in handle_qmp_command (parser=0x55baf77fb590, tokens=0x7f1d24011960) at /path/to/qemu.git/monitor.c:3978 qemu#8 0x000055baf6a9d099 in json_message_process_token (lexer=0x55baf77fb598, input=0x55baf75acd20, type=JSON_RCURLY, x=113, y=19) at qobject/json-streamer.c:105 qemu#9 0x000055baf6abf7aa in json_lexer_feed_char (lexer=0x55baf77fb598, ch=125 '}', flush=false) at qobject/json-lexer.c:319 qemu#10 0x000055baf6abf8f2 in json_lexer_feed (lexer=0x55baf77fb598, buffer=0x7ffc51369170 "}R\204\367\272U", size=1) at qobject/json-lexer.c:369 qemu#11 0x000055baf6a9d13c in json_message_parser_feed (parser=0x55baf77fb590, buffer=0x7ffc51369170 "}R\204\367\272U", size=1) at qobject/json-streamer.c:124 qemu#12 0x000055baf66221f7 in monitor_qmp_read (opaque=0x55baf77fb530, buf=0x7ffc51369170 "}R\204\367\272U", size=1) at /path/to/qemu.git/monitor.c:3994 qemu#13 0x000055baf6757014 in qemu_chr_be_write_impl (s=0x55baf7610a40, buf=0x7ffc51369170 "}R\204\367\272U", len=1) at qemu-char.c:387 qemu#14 0x000055baf6757076 in qemu_chr_be_write (s=0x55baf7610a40, buf=0x7ffc51369170 "}R\204\367\272U", len=1) at qemu-char.c:399 qemu#15 0x000055baf675b3b0 in tcp_chr_read (chan=0x55baf90244b0, cond=G_IO_IN, opaque=0x55baf7610a40) at qemu-char.c:2927 qemu#16 0x000055baf6a5d655 in qio_channel_fd_source_dispatch (source=0x55baf7610df0, callback=0x55baf675b25a <tcp_chr_read>, user_data=0x55baf7610a40) at io/channel-watch.c:84 qemu#17 0x00007f1d3e80cbbd in g_main_context_dispatch () from /usr/lib64/libglib-2.0.so.0 qemu#18 0x000055baf69d3720 in glib_pollfds_poll () at main-loop.c:213 qemu#19 0x000055baf69d37fd in os_host_main_loop_wait (timeout=126000000) at main-loop.c:258 qemu#20 0x000055baf69d38ad in main_loop_wait (nonblocking=0) at main-loop.c:506 qemu#21 0x000055baf676587b in main_loop () at vl.c:1908 qemu#22 0x000055baf676d3bf in main (argc=101, argv=0x7ffc5136a6c8, envp=0x7ffc5136a9f8) at vl.c:4604 (gdb) p opts $1 = (QemuOpts *) 0x0 The crash occurred when I tried to attach vhost-user net: {"execute":"chardev-add","arguments":{"id":"charnet2","backend":{"type":"socket","data":{"addr":{"type":"unix","data":{"path":"/var/run/openvswitch/vhost-user1"}},"wait":false,"server":false}}},"id":"libvirt-19"} {"return": {}, "id": "libvirt-19"} {"execute":"netdev_add","arguments":{"type":"vhost-user","chardev":"charnet2","id":"hostnet2"},"id":"libvirt-20"} 2016-08-16 14:52:18.274+0000: 6456: error : qemuMonitorIORead:586 : Unable to read from monitor: Connection reset by peer The solution is to teach qemu_opt_foreach() to take a shortcut if @opts is NULL. Signed-off-by: Michal Privoznik <mprivozn@redhat.com>
ahci-test /x86_64/ahci/io/dma/lba28/retry triggers the following leak: Direct leak of 16 byte(s) in 1 object(s) allocated from: #0 0x7fc4b2a25e20 in malloc (/lib64/libasan.so.3+0xc6e20) #1 0x7fc4993bce58 in g_malloc (/lib64/libglib-2.0.so.0+0x4ee58) #2 0x556a187d4b34 in ahci_populate_sglist hw/ide/ahci.c:896 #3 0x556a187d8237 in ahci_dma_prepare_buf hw/ide/ahci.c:1367 #4 0x556a187b5a1a in ide_dma_cb hw/ide/core.c:844 #5 0x556a187d7eec in ahci_start_dma hw/ide/ahci.c:1333 #6 0x556a187b650b in ide_start_dma hw/ide/core.c:921 #7 0x556a187b61e6 in ide_sector_start_dma hw/ide/core.c:911 #8 0x556a187b9e26 in cmd_write_dma hw/ide/core.c:1486 #9 0x556a187bd519 in ide_exec_cmd hw/ide/core.c:2027 #10 0x556a187d71c5 in handle_reg_h2d_fis hw/ide/ahci.c:1204 #11 0x556a187d7681 in handle_cmd hw/ide/ahci.c:1254 #12 0x556a187d168a in check_cmd hw/ide/ahci.c:510 #13 0x556a187d0afc in ahci_port_write hw/ide/ahci.c:314 #14 0x556a187d105d in ahci_mem_write hw/ide/ahci.c:435 #15 0x556a1831d959 in memory_region_write_accessor /home/elmarco/src/qemu/memory.c:525 #16 0x556a1831dc35 in access_with_adjusted_size /home/elmarco/src/qemu/memory.c:591 #17 0x556a18323ce3 in memory_region_dispatch_write /home/elmarco/src/qemu/memory.c:1262 #18 0x556a1828cf67 in address_space_write_continue /home/elmarco/src/qemu/exec.c:2578 #19 0x556a1828d20b in address_space_write /home/elmarco/src/qemu/exec.c:2635 #20 0x556a1828d92b in address_space_rw /home/elmarco/src/qemu/exec.c:2737 #21 0x556a1828daf7 in cpu_physical_memory_rw /home/elmarco/src/qemu/exec.c:2746 #22 0x556a183068d3 in cpu_physical_memory_write /home/elmarco/src/qemu/include/exec/cpu-common.h:72 #23 0x556a18308194 in qtest_process_command /home/elmarco/src/qemu/qtest.c:382 #24 0x556a18309999 in qtest_process_inbuf /home/elmarco/src/qemu/qtest.c:573 #25 0x556a18309a4a in qtest_read /home/elmarco/src/qemu/qtest.c:585 #26 0x556a18598b85 in qemu_chr_be_write_impl /home/elmarco/src/qemu/qemu-char.c:387 #27 0x556a18598c52 in qemu_chr_be_write /home/elmarco/src/qemu/qemu-char.c:399 #28 0x556a185a2afa in tcp_chr_read /home/elmarco/src/qemu/qemu-char.c:2902 #29 0x556a18cbaf52 in qio_channel_fd_source_dispatch io/channel-watch.c:84 Follow John Snow recommendation: Everywhere else ncq_err is used, it is accompanied by a list cleanup except for ncq_cb, which is the case you are fixing here. Move the sglist destruction inside of ncq_err and then delete it from the other two locations to keep it tidy. Call dma_buf_commit in ide_dma_cb after the early return. Though, this is also a little wonky because this routine does more than clear the list, but it is at the moment the centralized "we're done with the sglist" function and none of the other side effects that occur in dma_buf_commit will interfere with the reset that occurs from ide_restart_bh, I think Signed-off-by: Marc-André Lureau <marcandre.lureau@redhat.com> Reviewed-by: John Snow <jsnow@redhat.com> (cherry picked from commit 5839df7) Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
The vnc_server_info_get will allocate the VncServerInfo struct and then call vnc_init_basic_info_from_server_addr to populate the basic fields. If this returns an error though, the qapi_free_VncServerInfo call will then crash because the VncServerInfo struct instance was not properly NULL-initialized and thus contains random stack garbage. #0 0x00007f1987c8e6f5 in raise () at /lib64/libc.so.6 #1 0x00007f1987c902fa in abort () at /lib64/libc.so.6 #2 0x00007f1987ccf600 in __libc_message () at /lib64/libc.so.6 #3 0x00007f1987cd7d4a in _int_free () at /lib64/libc.so.6 #4 0x00007f1987cdb2ac in free () at /lib64/libc.so.6 #5 0x00007f198b654f6e in g_free () at /lib64/libglib-2.0.so.0 #6 0x0000559193cdcf54 in visit_type_str (v=v@entry= 0x5591972f14b0, name=name@entry=0x559193de1e29 "host", obj=obj@entry=0x5591961dbfa0, errp=errp@entry=0x7fffd7899d80) at qapi/qapi-visit-core.c:255 #7 0x0000559193cca8f3 in visit_type_VncBasicInfo_members (v=v@entry= 0x5591972f14b0, obj=obj@entry=0x5591961dbfa0, errp=errp@entry=0x7fffd7899dc0) at qapi-visit.c:12307 #8 0x0000559193ccb523 in visit_type_VncServerInfo_members (v=v@entry= 0x5591972f14b0, obj=0x5591961dbfa0, errp=errp@entry=0x7fffd7899e00) at qapi-visit.c:12632 #9 0x0000559193ccb60b in visit_type_VncServerInfo (v=v@entry= 0x5591972f14b0, name=name@entry=0x0, obj=obj@entry=0x7fffd7899e48, errp=errp@entry=0x0) at qapi-visit.c:12658 #10 0x0000559193cb53d8 in qapi_free_VncServerInfo (obj=<optimized out>) at qapi-types.c:3970 #11 0x0000559193c1e6ba in vnc_server_info_get (vd=0x7f1951498010) at ui/vnc.c:233 #12 0x0000559193c24275 in vnc_connect (vs=0x559197b2f200, vs=0x559197b2f200, event=QAPI_EVENT_VNC_CONNECTED) at ui/vnc.c:284 #13 0x0000559193c24275 in vnc_connect (vd=vd@entry=0x7f1951498010, sioc=sioc@entry=0x559196bf9c00, skipauth=skipauth@entry=tru e, websocket=websocket@entry=false) at ui/vnc.c:3039 #14 0x0000559193c25806 in vnc_display_add_client (id=<optimized out>, csock=<optimized out>, skipauth=<optimized out>) at ui/vnc.c:3877 #15 0x0000559193a90c28 in qmp_marshal_add_client (args=<optimized out>, ret=<optimized out>, errp=0x7fffd7899f90) at qmp-marshal.c:105 #16 0x000055919399c2b7 in handle_qmp_command (parser=<optimized out>, tokens=<optimized out>) at /home/berrange/src/virt/qemu/monitor.c:3971 #17 0x0000559193ce3307 in json_message_process_token (lexer=0x559194ab0838, input=0x559194a6d940, type=JSON_RCURLY, x=111, y=1 2) at qobject/json-streamer.c:105 #18 0x0000559193cfa90d in json_lexer_feed_char (lexer=lexer@entry=0x559194ab0838, ch=125 '}', flush=flush@entry=false) at qobject/json-lexer.c:319 #19 0x0000559193cfaa1e in json_lexer_feed (lexer=0x559194ab0838, buffer=<optimized out>, size=<optimized out>) at qobject/json-lexer.c:369 #20 0x0000559193ce33c9 in json_message_parser_feed (parser=<optimized out>, buffer=<optimized out>, size=<optimized out>) at qobject/json-streamer.c:124 #21 0x000055919399a85b in monitor_qmp_read (opaque=<optimized out>, buf=<optimized out>, size=<optimized out>) at /home/berrange/src/virt/qemu/monitor.c:3987 #22 0x0000559193a87d00 in tcp_chr_read (chan=<optimized out>, cond=<optimized out>, opaque=0x559194a7d900) at qemu-char.c:2895 #23 0x00007f198b64f703 in g_main_context_dispatch () at /lib64/libglib-2.0.so.0 #24 0x0000559193c484b3 in main_loop_wait () at main-loop.c:213 #25 0x0000559193c484b3 in main_loop_wait (timeout=<optimized out>) at main-loop.c:258 #26 0x0000559193c484b3 in main_loop_wait (nonblocking=<optimized out>) at main-loop.c:506 #27 0x0000559193964c55 in main () at vl.c:1908 #28 0x0000559193964c55 in main (argc=<optimized out>, argv=<optimized out>, envp=<optimized out>) at vl.c:4603 This was introduced in commit 98481bf Author: Eric Blake <eblake@redhat.com> Date: Mon Oct 26 16:34:45 2015 -0600 vnc: Hoist allocation of VncBasicInfo to callers which added error reporting for vnc_init_basic_info_from_server_addr but didn't change the g_malloc calls to g_malloc0. Signed-off-by: Daniel P. Berrange <berrange@redhat.com> Message-id: 1470134726-15697-3-git-send-email-berrange@redhat.com Signed-off-by: Gerd Hoffmann <kraxel@redhat.com> (cherry picked from commit 3e7f136) Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
With a Spice port chardev, it is possible to reenter monitor_qapi_event_queue() (when the client disconnects for example). This will dead-lock on monitor_lock. Instead, use some TLS variables to check for recursion and queue the events. Fixes: (gdb) bt #0 0x00007fa69e7217fd in __lll_lock_wait () at /lib64/libpthread.so.0 #1 0x00007fa69e71acf4 in pthread_mutex_lock () at /lib64/libpthread.so.0 #2 0x0000563303567619 in qemu_mutex_lock_impl (mutex=0x563303d3e220 <monitor_lock>, file=0x5633036589a8 "/home/elmarco/src/qq/monitor.c", line=645) at /home/elmarco/src/qq/util/qemu-thread-posix.c:66 #3 0x0000563302fa6c25 in monitor_qapi_event_queue (event=QAPI_EVENT_SPICE_DISCONNECTED, qdict=0x56330602bde0, errp=0x7ffc6ab5e728) at /home/elmarco/src/qq/monitor.c:645 #4 0x0000563303549aca in qapi_event_send_spice_disconnected (server=0x563305afd630, client=0x563305745360, errp=0x563303d8d0f0 <error_abort>) at qapi/qapi-events-ui.c:149 #5 0x00005633033e600f in channel_event (event=3, info=0x5633061b0050) at /home/elmarco/src/qq/ui/spice-core.c:235 #6 0x00007fa69f6c86bb in reds_handle_channel_event (reds=<optimized out>, event=3, info=0x5633061b0050) at reds.c:316 #7 0x00007fa69f6b193b in main_dispatcher_self_handle_channel_event (info=0x5633061b0050, event=3, self=0x563304e088c0) at main-dispatcher.c:197 #8 0x00007fa69f6b193b in main_dispatcher_channel_event (self=0x563304e088c0, event=event@entry=3, info=0x5633061b0050) at main-dispatcher.c:197 #9 0x00007fa69f6d0833 in red_stream_push_channel_event (s=s@entry=0x563305ad8f50, event=event@entry=3) at red-stream.c:414 #10 0x00007fa69f6d086b in red_stream_free (s=0x563305ad8f50) at red-stream.c:388 #11 0x00007fa69f6b7ddc in red_channel_client_finalize (object=0x563304df2360) at red-channel-client.c:347 #12 0x00007fa6a56b7fb9 in g_object_unref () at /lib64/libgobject-2.0.so.0 #13 0x00007fa69f6ba212 in red_channel_client_push (rcc=0x563304df2360) at red-channel-client.c:1341 #14 0x00007fa69f68b259 in red_char_device_send_msg_to_client (client=<optimized out>, msg=0x5633059b6310, dev=0x563304e08bc0) at char-device.c:305 #15 0x00007fa69f68b259 in red_char_device_send_msg_to_clients (msg=0x5633059b6310, dev=0x563304e08bc0) at char-device.c:305 #16 0x00007fa69f68b259 in red_char_device_read_from_device (dev=0x563304e08bc0) at char-device.c:353 #17 0x000056330317d01d in spice_chr_write (chr=0x563304cafe20, buf=0x563304cc50b0 "{\"timestamp\": {\"seconds\": 1532944763, \"microseconds\": 326636}, \"event\": \"SHUTDOWN\", \"data\": {\"guest\": false}}\r\n", len=111) at /home/elmarco/src/qq/chardev/spice.c:199 #18 0x00005633034deee7 in qemu_chr_write_buffer (s=0x563304cafe20, buf=0x563304cc50b0 "{\"timestamp\": {\"seconds\": 1532944763, \"microseconds\": 326636}, \"event\": \"SHUTDOWN\", \"data\": {\"guest\": false}}\r\n", len=111, offset=0x7ffc6ab5ea70, write_all=false) at /home/elmarco/src/qq/chardev/char.c:112 #19 0x00005633034df054 in qemu_chr_write (s=0x563304cafe20, buf=0x563304cc50b0 "{\"timestamp\": {\"seconds\": 1532944763, \"microseconds\": 326636}, \"event\": \"SHUTDOWN\", \"data\": {\"guest\": false}}\r\n", len=111, write_all=false) at /home/elmarco/src/qq/chardev/char.c:147 #20 0x00005633034e1e13 in qemu_chr_fe_write (be=0x563304dbb800, buf=0x563304cc50b0 "{\"timestamp\": {\"seconds\": 1532944763, \"microseconds\": 326636}, \"event\": \"SHUTDOWN\", \"data\": {\"guest\": false}}\r\n", len=111) at /home/elmarco/src/qq/chardev/char-fe.c:42 #21 0x0000563302fa6334 in monitor_flush_locked (mon=0x563304dbb800) at /home/elmarco/src/qq/monitor.c:425 #22 0x0000563302fa6520 in monitor_puts (mon=0x563304dbb800, str=0x563305de7e9e "") at /home/elmarco/src/qq/monitor.c:468 #23 0x0000563302fa680c in qmp_send_response (mon=0x563304dbb800, rsp=0x563304df5730) at /home/elmarco/src/qq/monitor.c:517 #24 0x0000563302fa6905 in qmp_queue_response (mon=0x563304dbb800, rsp=0x563304df5730) at /home/elmarco/src/qq/monitor.c:538 #25 0x0000563302fa6b5b in monitor_qapi_event_emit (event=QAPI_EVENT_SHUTDOWN, qdict=0x563304df5730) at /home/elmarco/src/qq/monitor.c:624 #26 0x0000563302fa6c4b in monitor_qapi_event_queue (event=QAPI_EVENT_SHUTDOWN, qdict=0x563304df5730, errp=0x7ffc6ab5ed00) at /home/elmarco/src/qq/monitor.c:649 #27 0x0000563303548cce in qapi_event_send_shutdown (guest=false, errp=0x563303d8d0f0 <error_abort>) at qapi/qapi-events-run-state.c:58 #28 0x000056330313bcd7 in main_loop_should_exit () at /home/elmarco/src/qq/vl.c:1822 #29 0x000056330313bde3 in main_loop () at /home/elmarco/src/qq/vl.c:1862 #30 0x0000563303143781 in main (argc=3, argv=0x7ffc6ab5f068, envp=0x7ffc6ab5f088) at /home/elmarco/src/qq/vl.c:4644 Note that error report is now moved to the first caller, which may receive an error for a recursed event. This is probably fine (95% of callers use &error_abort, the rest have NULL error and ignore it) Signed-off-by: Marc-André Lureau <marcandre.lureau@redhat.com> Message-Id: <20180731150144.14022-1-marcandre.lureau@redhat.com> Reviewed-by: Markus Armbruster <armbru@redhat.com> [*_no_recurse renamed to *_no_reenter, local variables reordered] Signed-off-by: Markus Armbruster <armbru@redhat.com>
In qemu_laio_process_completions_and_submit, the AioContext is acquired before the ioq_submit iteration and after qemu_laio_process_completions, but the latter is not thread safe either. This change avoids a number of random crashes when the Main Thread and an IO Thread collide processing completions for the same AioContext. This is an example of such crash: - The IO Thread is trying to acquire the AioContext at aio_co_enter, which evidences that it didn't lock it before: Thread 3 (Thread 0x7fdfd8bd8700 (LWP 36743)): #0 0x00007fdfe0dd542d in __lll_lock_wait () at ../nptl/sysdeps/unix/sysv/linux/x86_64/lowlevellock.S:135 #1 0x00007fdfe0dd0de6 in _L_lock_870 () at /lib64/libpthread.so.0 #2 0x00007fdfe0dd0cdf in __GI___pthread_mutex_lock (mutex=mutex@entry=0x5631fde0e6c0) at ../nptl/pthread_mutex_lock.c:114 #3 0x00005631fc0603a7 in qemu_mutex_lock_impl (mutex=0x5631fde0e6c0, file=0x5631fc23520f "util/async.c", line=511) at util/qemu-thread-posix.c:66 #4 0x00005631fc05b558 in aio_co_enter (ctx=0x5631fde0e660, co=0x7fdfcc0c2b40) at util/async.c:493 #5 0x00005631fc05b5ac in aio_co_wake (co=<optimized out>) at util/async.c:478 #6 0x00005631fbfc51ad in qemu_laio_process_completion (laiocb=<optimized out>) at block/linux-aio.c:104 #7 0x00005631fbfc523c in qemu_laio_process_completions (s=s@entry=0x7fdfc0297670) at block/linux-aio.c:222 #8 0x00005631fbfc5499 in qemu_laio_process_completions_and_submit (s=0x7fdfc0297670) at block/linux-aio.c:237 #9 0x00005631fc05d978 in aio_dispatch_handlers (ctx=ctx@entry=0x5631fde0e660) at util/aio-posix.c:406 #10 0x00005631fc05e3ea in aio_poll (ctx=0x5631fde0e660, blocking=blocking@entry=true) at util/aio-posix.c:693 #11 0x00005631fbd7ad96 in iothread_run (opaque=0x5631fde0e1c0) at iothread.c:64 #12 0x00007fdfe0dcee25 in start_thread (arg=0x7fdfd8bd8700) at pthread_create.c:308 #13 0x00007fdfe0afc34d in clone () at ../sysdeps/unix/sysv/linux/x86_64/clone.S:113 - The Main Thread is also processing completions from the same AioContext, and crashes due to failed assertion at util/iov.c:78: Thread 1 (Thread 0x7fdfeb5eac80 (LWP 36740)): #0 0x00007fdfe0a391f7 in __GI_raise (sig=sig@entry=6) at ../nptl/sysdeps/unix/sysv/linux/raise.c:56 #1 0x00007fdfe0a3a8e8 in __GI_abort () at abort.c:90 #2 0x00007fdfe0a32266 in __assert_fail_base (fmt=0x7fdfe0b84e68 "%s%s%s:%u: %s%sAssertion `%s' failed.\n%n", assertion=assertion@entry=0x5631fc238ccb "offset == 0", file=file@entry=0x5631fc23698e "util/iov.c", line=line@entry=78, function=function@entry=0x5631fc236adc <__PRETTY_FUNCTION__.15220> "iov_memset") at assert.c:92 #3 0x00007fdfe0a32312 in __GI___assert_fail (assertion=assertion@entry=0x5631fc238ccb "offset == 0", file=file@entry=0x5631fc23698e "util/iov.c", line=line@entry=78, function=function@entry=0x5631fc236adc <__PRETTY_FUNCTION__.15220> "iov_memset") at assert.c:101 #4 0x00005631fc065287 in iov_memset (iov=<optimized out>, iov_cnt=<optimized out>, offset=<optimized out>, offset@entry=65536, fillc=fillc@entry=0, bytes=15515191315812405248) at util/iov.c:78 #5 0x00005631fc065a63 in qemu_iovec_memset (qiov=<optimized out>, offset=offset@entry=65536, fillc=fillc@entry=0, bytes=<optimized out>) at util/iov.c:410 #6 0x00005631fbfc5178 in qemu_laio_process_completion (laiocb=0x7fdd920df630) at block/linux-aio.c:88 #7 0x00005631fbfc523c in qemu_laio_process_completions (s=s@entry=0x7fdfc0297670) at block/linux-aio.c:222 #8 0x00005631fbfc5499 in qemu_laio_process_completions_and_submit (s=0x7fdfc0297670) at block/linux-aio.c:237 #9 0x00005631fbfc54ed in qemu_laio_poll_cb (opaque=<optimized out>) at block/linux-aio.c:272 #10 0x00005631fc05d85e in run_poll_handlers_once (ctx=ctx@entry=0x5631fde0e660) at util/aio-posix.c:497 #11 0x00005631fc05e2ca in aio_poll (blocking=false, ctx=0x5631fde0e660) at util/aio-posix.c:574 #12 0x00005631fc05e2ca in aio_poll (ctx=0x5631fde0e660, blocking=blocking@entry=false) at util/aio-posix.c:604 #13 0x00005631fbfcb8a3 in bdrv_do_drained_begin (ignore_parent=<optimized out>, recursive=<optimized out>, bs=<optimized out>) at block/io.c:273 #14 0x00005631fbfcb8a3 in bdrv_do_drained_begin (bs=0x5631fe8b6200, recursive=<optimized out>, parent=0x0, ignore_bds_parents=<optimized out>, poll=<optimized out>) at block/io.c:390 #15 0x00005631fbfbcd2e in blk_drain (blk=0x5631fe83ac80) at block/block-backend.c:1590 #16 0x00005631fbfbe138 in blk_remove_bs (blk=blk@entry=0x5631fe83ac80) at block/block-backend.c:774 #17 0x00005631fbfbe3d6 in blk_unref (blk=0x5631fe83ac80) at block/block-backend.c:401 #18 0x00005631fbfbe3d6 in blk_unref (blk=0x5631fe83ac80) at block/block-backend.c:449 #19 0x00005631fbfc9a69 in commit_complete (job=0x5631fe8b94b0, opaque=0x7fdfcc1bb080) at block/commit.c:92 #20 0x00005631fbf7d662 in job_defer_to_main_loop_bh (opaque=0x7fdfcc1b4560) at job.c:973 #21 0x00005631fc05ad41 in aio_bh_poll (bh=0x7fdfcc01ad90) at util/async.c:90 #22 0x00005631fc05ad41 in aio_bh_poll (ctx=ctx@entry=0x5631fddffdb0) at util/async.c:118 #23 0x00005631fc05e210 in aio_dispatch (ctx=0x5631fddffdb0) at util/aio-posix.c:436 #24 0x00005631fc05ac1e in aio_ctx_dispatch (source=<optimized out>, callback=<optimized out>, user_data=<optimized out>) at util/async.c:261 #25 0x00007fdfeaae44c9 in g_main_context_dispatch (context=0x5631fde00140) at gmain.c:3201 #26 0x00007fdfeaae44c9 in g_main_context_dispatch (context=context@entry=0x5631fde00140) at gmain.c:3854 #27 0x00005631fc05d503 in main_loop_wait () at util/main-loop.c:215 #28 0x00005631fc05d503 in main_loop_wait (timeout=<optimized out>) at util/main-loop.c:238 #29 0x00005631fc05d503 in main_loop_wait (nonblocking=nonblocking@entry=0) at util/main-loop.c:497 #30 0x00005631fbd81412 in main_loop () at vl.c:1866 #31 0x00005631fbc18ff3 in main (argc=<optimized out>, argv=<optimized out>, envp=<optimized out>) at vl.c:4647 - A closer examination shows that s->io_q.in_flight appears to have gone backwards: (gdb) frame 7 #7 0x00005631fbfc523c in qemu_laio_process_completions (s=s@entry=0x7fdfc0297670) at block/linux-aio.c:222 222 qemu_laio_process_completion(laiocb); (gdb) p s $2 = (LinuxAioState *) 0x7fdfc0297670 (gdb) p *s $3 = {aio_context = 0x5631fde0e660, ctx = 0x7fdfeb43b000, e = {rfd = 33, wfd = 33}, io_q = {plugged = 0, in_queue = 0, in_flight = 4294967280, blocked = false, pending = {sqh_first = 0x0, sqh_last = 0x7fdfc0297698}}, completion_bh = 0x7fdfc0280ef0, event_idx = 21, event_max = 241} (gdb) p/x s->io_q.in_flight $4 = 0xfffffff0 Signed-off-by: Sergio Lopez <slp@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Both virtio-blk and virtio-scsi use virtio_queue_empty() as the loop condition in VQ handlers (virtio_blk_handle_vq, virtio_scsi_handle_cmd_vq). When a device is marked broken in virtqueue_pop, for example if a vIOMMU address translation failed, we want to break out of the loop. This fixes a hanging problem when booting a CentOS 3.10.0-862.el7.x86_64 kernel: $ qemu-system-x86_64 \ ... \ -device intel-iommu,intremap=on,caching-mode=on,eim=on,device-iotlb=on \ -device virtio-scsi-pci,iommu_platform=on,ats=on,id=scsi0,bus=pci.4,addr=0x0 The dead loop happens immediately when the kernel boots and initializes the device, where virtio_scsi_data_plane_handle_cmd will not return: > ... > qemu#13 0x00005586602b7793 in virtio_scsi_handle_cmd_vq > qemu#14 0x00005586602b8d66 in virtio_scsi_data_plane_handle_cmd > qemu#15 0x00005586602ddab7 in virtio_queue_notify_aio_vq > qemu#16 0x00005586602dfc9f in virtio_queue_host_notifier_aio_poll > qemu#17 0x00005586607885da in run_poll_handlers_once > qemu#18 0x000055866078880e in try_poll_mode > qemu#19 0x00005586607888eb in aio_poll > qemu#20 0x0000558660784561 in aio_wait_bh_oneshot > qemu#21 0x00005586602b9582 in virtio_scsi_dataplane_stop > qemu#22 0x00005586605a7110 in virtio_bus_stop_ioeventfd > qemu#23 0x00005586605a9426 in virtio_pci_stop_ioeventfd > qemu#24 0x00005586605ab808 in virtio_pci_common_write > qemu#25 0x0000558660242396 in memory_region_write_accessor > qemu#26 0x00005586602425ab in access_with_adjusted_size > qemu#27 0x0000558660245281 in memory_region_dispatch_write > qemu#28 0x00005586601e008e in flatview_write_continue > qemu#29 0x00005586601e01d8 in flatview_write > qemu#30 0x00005586601e04de in address_space_write > qemu#31 0x00005586601e052f in address_space_rw > qemu#32 0x00005586602607f2 in kvm_cpu_exec > qemu#33 0x0000558660227148 in qemu_kvm_cpu_thread_fn > qemu#34 0x000055866078bde7 in qemu_thread_start > qemu#35 0x00007f5784906594 in start_thread > qemu#36 0x00007f5784639e6f in clone With this patch, virtio_queue_empty will now return 1 as soon as the vdev is marked as broken, after a "virtio: zero sized buffers are not allowed" error. To be consistent, update virtio_queue_empty_rcu as well. Signed-off-by: Fam Zheng <famz@redhat.com> --- v2: - Drop ATS condition from the patch description since it is not essential. - Drop patch 2. [Paolo]
Both virtio-blk and virtio-scsi use virtio_queue_empty() as the loop condition in VQ handlers (virtio_blk_handle_vq, virtio_scsi_handle_cmd_vq). When a device is marked broken in virtqueue_pop, for example if a vIOMMU address translation failed, we want to break out of the loop. This fixes a hanging problem when booting a CentOS 3.10.0-862.el7.x86_64 kernel with ATS enabled: $ qemu-system-x86_64 \ ... \ -device intel-iommu,intremap=on,caching-mode=on,eim=on,device-iotlb=on \ -device virtio-scsi-pci,iommu_platform=on,ats=on,id=scsi0,bus=pci.4,addr=0x0 The dead loop happens immediately when the kernel boots and initializes the device, where virtio_scsi_data_plane_handle_cmd will not return: > ... > #13 0x00005586602b7793 in virtio_scsi_handle_cmd_vq > #14 0x00005586602b8d66 in virtio_scsi_data_plane_handle_cmd > #15 0x00005586602ddab7 in virtio_queue_notify_aio_vq > #16 0x00005586602dfc9f in virtio_queue_host_notifier_aio_poll > #17 0x00005586607885da in run_poll_handlers_once > #18 0x000055866078880e in try_poll_mode > #19 0x00005586607888eb in aio_poll > #20 0x0000558660784561 in aio_wait_bh_oneshot > #21 0x00005586602b9582 in virtio_scsi_dataplane_stop > #22 0x00005586605a7110 in virtio_bus_stop_ioeventfd > #23 0x00005586605a9426 in virtio_pci_stop_ioeventfd > #24 0x00005586605ab808 in virtio_pci_common_write > #25 0x0000558660242396 in memory_region_write_accessor > #26 0x00005586602425ab in access_with_adjusted_size > #27 0x0000558660245281 in memory_region_dispatch_write > #28 0x00005586601e008e in flatview_write_continue > #29 0x00005586601e01d8 in flatview_write > #30 0x00005586601e04de in address_space_write > #31 0x00005586601e052f in address_space_rw > #32 0x00005586602607f2 in kvm_cpu_exec > #33 0x0000558660227148 in qemu_kvm_cpu_thread_fn > #34 0x000055866078bde7 in qemu_thread_start > #35 0x00007f5784906594 in start_thread > #36 0x00007f5784639e6f in clone With this patch, virtio_queue_empty will now return 1 as soon as the vdev is marked as broken, after a "virtio: zero sized buffers are not allowed" error. To be consistent, update virtio_queue_empty_rcu as well. Signed-off-by: Fam Zheng <famz@redhat.com> Message-Id: <20180910145616.8598-2-famz@redhat.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Both virtio-blk and virtio-scsi use virtio_queue_empty() as the loop condition in VQ handlers (virtio_blk_handle_vq, virtio_scsi_handle_cmd_vq). When a device is marked broken in virtqueue_pop, for example if a vIOMMU address translation failed, we want to break out of the loop. This fixes a hanging problem when booting a CentOS 3.10.0-862.el7.x86_64 kernel with ATS enabled: $ qemu-system-x86_64 \ ... \ -device intel-iommu,intremap=on,caching-mode=on,eim=on,device-iotlb=on \ -device virtio-scsi-pci,iommu_platform=on,ats=on,id=scsi0,bus=pci.4,addr=0x0 The dead loop happens immediately when the kernel boots and initializes the device, where virtio_scsi_data_plane_handle_cmd will not return: > ... > qemu#13 0x00005586602b7793 in virtio_scsi_handle_cmd_vq > qemu#14 0x00005586602b8d66 in virtio_scsi_data_plane_handle_cmd > qemu#15 0x00005586602ddab7 in virtio_queue_notify_aio_vq > qemu#16 0x00005586602dfc9f in virtio_queue_host_notifier_aio_poll > qemu#17 0x00005586607885da in run_poll_handlers_once > qemu#18 0x000055866078880e in try_poll_mode > qemu#19 0x00005586607888eb in aio_poll > qemu#20 0x0000558660784561 in aio_wait_bh_oneshot > qemu#21 0x00005586602b9582 in virtio_scsi_dataplane_stop > qemu#22 0x00005586605a7110 in virtio_bus_stop_ioeventfd > qemu#23 0x00005586605a9426 in virtio_pci_stop_ioeventfd > qemu#24 0x00005586605ab808 in virtio_pci_common_write > qemu#25 0x0000558660242396 in memory_region_write_accessor > qemu#26 0x00005586602425ab in access_with_adjusted_size > qemu#27 0x0000558660245281 in memory_region_dispatch_write > qemu#28 0x00005586601e008e in flatview_write_continue > qemu#29 0x00005586601e01d8 in flatview_write > qemu#30 0x00005586601e04de in address_space_write > qemu#31 0x00005586601e052f in address_space_rw > qemu#32 0x00005586602607f2 in kvm_cpu_exec > qemu#33 0x0000558660227148 in qemu_kvm_cpu_thread_fn > qemu#34 0x000055866078bde7 in qemu_thread_start > qemu#35 0x00007f5784906594 in start_thread > qemu#36 0x00007f5784639e6f in clone With this patch, virtio_queue_empty will now return 1 as soon as the vdev is marked as broken, after a "virtio: zero sized buffers are not allowed" error. To be consistent, update virtio_queue_empty_rcu as well. Signed-off-by: Fam Zheng <famz@redhat.com> Message-Id: <20180910145616.8598-2-famz@redhat.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
In qemu_laio_process_completions_and_submit, the AioContext is acquired before the ioq_submit iteration and after qemu_laio_process_completions, but the latter is not thread safe either. This change avoids a number of random crashes when the Main Thread and an IO Thread collide processing completions for the same AioContext. This is an example of such crash: - The IO Thread is trying to acquire the AioContext at aio_co_enter, which evidences that it didn't lock it before: Thread 3 (Thread 0x7fdfd8bd8700 (LWP 36743)): #0 0x00007fdfe0dd542d in __lll_lock_wait () at ../nptl/sysdeps/unix/sysv/linux/x86_64/lowlevellock.S:135 qemu#1 0x00007fdfe0dd0de6 in _L_lock_870 () at /lib64/libpthread.so.0 qemu#2 0x00007fdfe0dd0cdf in __GI___pthread_mutex_lock (mutex=mutex@entry=0x5631fde0e6c0) at ../nptl/pthread_mutex_lock.c:114 qemu#3 0x00005631fc0603a7 in qemu_mutex_lock_impl (mutex=0x5631fde0e6c0, file=0x5631fc23520f "util/async.c", line=511) at util/qemu-thread-posix.c:66 qemu#4 0x00005631fc05b558 in aio_co_enter (ctx=0x5631fde0e660, co=0x7fdfcc0c2b40) at util/async.c:493 qemu#5 0x00005631fc05b5ac in aio_co_wake (co=<optimized out>) at util/async.c:478 qemu#6 0x00005631fbfc51ad in qemu_laio_process_completion (laiocb=<optimized out>) at block/linux-aio.c:104 qemu#7 0x00005631fbfc523c in qemu_laio_process_completions (s=s@entry=0x7fdfc0297670) at block/linux-aio.c:222 qemu#8 0x00005631fbfc5499 in qemu_laio_process_completions_and_submit (s=0x7fdfc0297670) at block/linux-aio.c:237 qemu#9 0x00005631fc05d978 in aio_dispatch_handlers (ctx=ctx@entry=0x5631fde0e660) at util/aio-posix.c:406 qemu#10 0x00005631fc05e3ea in aio_poll (ctx=0x5631fde0e660, blocking=blocking@entry=true) at util/aio-posix.c:693 qemu#11 0x00005631fbd7ad96 in iothread_run (opaque=0x5631fde0e1c0) at iothread.c:64 qemu#12 0x00007fdfe0dcee25 in start_thread (arg=0x7fdfd8bd8700) at pthread_create.c:308 qemu#13 0x00007fdfe0afc34d in clone () at ../sysdeps/unix/sysv/linux/x86_64/clone.S:113 - The Main Thread is also processing completions from the same AioContext, and crashes due to failed assertion at util/iov.c:78: Thread 1 (Thread 0x7fdfeb5eac80 (LWP 36740)): #0 0x00007fdfe0a391f7 in __GI_raise (sig=sig@entry=6) at ../nptl/sysdeps/unix/sysv/linux/raise.c:56 qemu#1 0x00007fdfe0a3a8e8 in __GI_abort () at abort.c:90 qemu#2 0x00007fdfe0a32266 in __assert_fail_base (fmt=0x7fdfe0b84e68 "%s%s%s:%u: %s%sAssertion `%s' failed.\n%n", assertion=assertion@entry=0x5631fc238ccb "offset == 0", file=file@entry=0x5631fc23698e "util/iov.c", line=line@entry=78, function=function@entry=0x5631fc236adc <__PRETTY_FUNCTION__.15220> "iov_memset") at assert.c:92 qemu#3 0x00007fdfe0a32312 in __GI___assert_fail (assertion=assertion@entry=0x5631fc238ccb "offset == 0", file=file@entry=0x5631fc23698e "util/iov.c", line=line@entry=78, function=function@entry=0x5631fc236adc <__PRETTY_FUNCTION__.15220> "iov_memset") at assert.c:101 qemu#4 0x00005631fc065287 in iov_memset (iov=<optimized out>, iov_cnt=<optimized out>, offset=<optimized out>, offset@entry=65536, fillc=fillc@entry=0, bytes=15515191315812405248) at util/iov.c:78 qemu#5 0x00005631fc065a63 in qemu_iovec_memset (qiov=<optimized out>, offset=offset@entry=65536, fillc=fillc@entry=0, bytes=<optimized out>) at util/iov.c:410 qemu#6 0x00005631fbfc5178 in qemu_laio_process_completion (laiocb=0x7fdd920df630) at block/linux-aio.c:88 qemu#7 0x00005631fbfc523c in qemu_laio_process_completions (s=s@entry=0x7fdfc0297670) at block/linux-aio.c:222 qemu#8 0x00005631fbfc5499 in qemu_laio_process_completions_and_submit (s=0x7fdfc0297670) at block/linux-aio.c:237 qemu#9 0x00005631fbfc54ed in qemu_laio_poll_cb (opaque=<optimized out>) at block/linux-aio.c:272 qemu#10 0x00005631fc05d85e in run_poll_handlers_once (ctx=ctx@entry=0x5631fde0e660) at util/aio-posix.c:497 qemu#11 0x00005631fc05e2ca in aio_poll (blocking=false, ctx=0x5631fde0e660) at util/aio-posix.c:574 qemu#12 0x00005631fc05e2ca in aio_poll (ctx=0x5631fde0e660, blocking=blocking@entry=false) at util/aio-posix.c:604 qemu#13 0x00005631fbfcb8a3 in bdrv_do_drained_begin (ignore_parent=<optimized out>, recursive=<optimized out>, bs=<optimized out>) at block/io.c:273 qemu#14 0x00005631fbfcb8a3 in bdrv_do_drained_begin (bs=0x5631fe8b6200, recursive=<optimized out>, parent=0x0, ignore_bds_parents=<optimized out>, poll=<optimized out>) at block/io.c:390 qemu#15 0x00005631fbfbcd2e in blk_drain (blk=0x5631fe83ac80) at block/block-backend.c:1590 qemu#16 0x00005631fbfbe138 in blk_remove_bs (blk=blk@entry=0x5631fe83ac80) at block/block-backend.c:774 qemu#17 0x00005631fbfbe3d6 in blk_unref (blk=0x5631fe83ac80) at block/block-backend.c:401 qemu#18 0x00005631fbfbe3d6 in blk_unref (blk=0x5631fe83ac80) at block/block-backend.c:449 qemu#19 0x00005631fbfc9a69 in commit_complete (job=0x5631fe8b94b0, opaque=0x7fdfcc1bb080) at block/commit.c:92 qemu#20 0x00005631fbf7d662 in job_defer_to_main_loop_bh (opaque=0x7fdfcc1b4560) at job.c:973 qemu#21 0x00005631fc05ad41 in aio_bh_poll (bh=0x7fdfcc01ad90) at util/async.c:90 qemu#22 0x00005631fc05ad41 in aio_bh_poll (ctx=ctx@entry=0x5631fddffdb0) at util/async.c:118 qemu#23 0x00005631fc05e210 in aio_dispatch (ctx=0x5631fddffdb0) at util/aio-posix.c:436 qemu#24 0x00005631fc05ac1e in aio_ctx_dispatch (source=<optimized out>, callback=<optimized out>, user_data=<optimized out>) at util/async.c:261 qemu#25 0x00007fdfeaae44c9 in g_main_context_dispatch (context=0x5631fde00140) at gmain.c:3201 qemu#26 0x00007fdfeaae44c9 in g_main_context_dispatch (context=context@entry=0x5631fde00140) at gmain.c:3854 qemu#27 0x00005631fc05d503 in main_loop_wait () at util/main-loop.c:215 qemu#28 0x00005631fc05d503 in main_loop_wait (timeout=<optimized out>) at util/main-loop.c:238 qemu#29 0x00005631fc05d503 in main_loop_wait (nonblocking=nonblocking@entry=0) at util/main-loop.c:497 qemu#30 0x00005631fbd81412 in main_loop () at vl.c:1866 qemu#31 0x00005631fbc18ff3 in main (argc=<optimized out>, argv=<optimized out>, envp=<optimized out>) at vl.c:4647 - A closer examination shows that s->io_q.in_flight appears to have gone backwards: (gdb) frame 7 qemu#7 0x00005631fbfc523c in qemu_laio_process_completions (s=s@entry=0x7fdfc0297670) at block/linux-aio.c:222 222 qemu_laio_process_completion(laiocb); (gdb) p s $2 = (LinuxAioState *) 0x7fdfc0297670 (gdb) p *s $3 = {aio_context = 0x5631fde0e660, ctx = 0x7fdfeb43b000, e = {rfd = 33, wfd = 33}, io_q = {plugged = 0, in_queue = 0, in_flight = 4294967280, blocked = false, pending = {sqh_first = 0x0, sqh_last = 0x7fdfc0297698}}, completion_bh = 0x7fdfc0280ef0, event_idx = 21, event_max = 241} (gdb) p/x s->io_q.in_flight $4 = 0xfffffff0 Signed-off-by: Sergio Lopez <slp@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Let start from the beginning: Commit b9e413d (in 2.9) "block: explicitly acquire aiocontext in aio callbacks that need it" added pairs of aio_context_acquire/release to mirror_write_complete and mirror_read_complete, when they were aio callbacks for blk_aio_* calls. Then, commit 2e1990b (in 3.0) "block/mirror: Convert to coroutines" dropped these blk_aio_* calls, than mirror_write_complete and mirror_read_complete are not callbacks more, and don't need additional aiocontext acquiring. Furthermore, mirror_read_complete calls blk_co_pwritev inside these pair of aio_context_acquire/release, which leads to the following dead-lock with mirror: (gdb) info thr Id Target Id Frame 3 Thread (LWP 145412) "qemu-system-x86" syscall () 2 Thread (LWP 145416) "qemu-system-x86" __lll_lock_wait () * 1 Thread (LWP 145411) "qemu-system-x86" __lll_lock_wait () (gdb) bt #0 __lll_lock_wait () #1 _L_lock_812 () #2 __GI___pthread_mutex_lock #3 qemu_mutex_lock_impl (mutex=0x561032dce420 <qemu_global_mutex>, file=0x5610327d8654 "util/main-loop.c", line=236) at util/qemu-thread-posix.c:66 #4 qemu_mutex_lock_iothread_impl #5 os_host_main_loop_wait (timeout=480116000) at util/main-loop.c:236 #6 main_loop_wait (nonblocking=0) at util/main-loop.c:497 #7 main_loop () at vl.c:1892 #8 main Printing contents of qemu_global_mutex, I see that "__owner = 145416", so, thr1 is main loop, and now it wants BQL, which is owned by thr2. (gdb) thr 2 (gdb) bt #0 __lll_lock_wait () #1 _L_lock_870 () #2 __GI___pthread_mutex_lock #3 qemu_mutex_lock_impl (mutex=0x561034d25dc0, ... #4 aio_context_acquire (ctx=0x561034d25d60) #5 dma_blk_cb #6 dma_blk_io #7 dma_blk_read #8 ide_dma_cb #9 bmdma_cmd_writeb #10 bmdma_write #11 memory_region_write_accessor #12 access_with_adjusted_size #15 flatview_write #16 address_space_write #17 address_space_rw #18 kvm_handle_io #19 kvm_cpu_exec #20 qemu_kvm_cpu_thread_fn #21 qemu_thread_start #22 start_thread #23 clone () Printing mutex in fr 2, I see "__owner = 145411", so thr2 wants aio context mutex, which is owned by thr1. Classic dead-lock. Then, let's check that aio context is hold by mirror coroutine: just print coroutine stack of first tracked request in mirror job target: (gdb) [...] (gdb) qemu coroutine 0x561035dd0860 #0 qemu_coroutine_switch #1 qemu_coroutine_yield #2 qemu_co_mutex_lock_slowpath #3 qemu_co_mutex_lock #4 qcow2_co_pwritev #5 bdrv_driver_pwritev #6 bdrv_aligned_pwritev #7 bdrv_co_pwritev #8 blk_co_pwritev #9 mirror_read_complete () at block/mirror.c:232 #10 mirror_co_read () at block/mirror.c:370 #11 coroutine_trampoline #12 __start_context Yes it is mirror_read_complete calling blk_co_pwritev after acquiring aio context. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
RH-Author: Kevin Wolf <kwolf@redhat.com> Message-id: <20181010202213.7372-14-kwolf@redhat.com> Patchwork-id: 82603 O-Subject: [RHEL-8 qemu-kvm PATCH 23/44] block/linux-aio: acquire AioContext before qemu_laio_process_completions Bugzilla: 1637976 RH-Acked-by: Max Reitz <mreitz@redhat.com> RH-Acked-by: John Snow <jsnow@redhat.com> RH-Acked-by: Thomas Huth <thuth@redhat.com> From: Sergio Lopez <slp@redhat.com> In qemu_laio_process_completions_and_submit, the AioContext is acquired before the ioq_submit iteration and after qemu_laio_process_completions, but the latter is not thread safe either. This change avoids a number of random crashes when the Main Thread and an IO Thread collide processing completions for the same AioContext. This is an example of such crash: - The IO Thread is trying to acquire the AioContext at aio_co_enter, which evidences that it didn't lock it before: Thread 3 (Thread 0x7fdfd8bd8700 (LWP 36743)): #0 0x00007fdfe0dd542d in __lll_lock_wait () at ../nptl/sysdeps/unix/sysv/linux/x86_64/lowlevellock.S:135 qemu#1 0x00007fdfe0dd0de6 in _L_lock_870 () at /lib64/libpthread.so.0 qemu#2 0x00007fdfe0dd0cdf in __GI___pthread_mutex_lock (mutex=mutex@entry=0x5631fde0e6c0) at ../nptl/pthread_mutex_lock.c:114 qemu#3 0x00005631fc0603a7 in qemu_mutex_lock_impl (mutex=0x5631fde0e6c0, file=0x5631fc23520f "util/async.c", line=511) at util/qemu-thread-posix.c:66 qemu#4 0x00005631fc05b558 in aio_co_enter (ctx=0x5631fde0e660, co=0x7fdfcc0c2b40) at util/async.c:493 qemu#5 0x00005631fc05b5ac in aio_co_wake (co=<optimized out>) at util/async.c:478 qemu#6 0x00005631fbfc51ad in qemu_laio_process_completion (laiocb=<optimized out>) at block/linux-aio.c:104 qemu#7 0x00005631fbfc523c in qemu_laio_process_completions (s=s@entry=0x7fdfc0297670) at block/linux-aio.c:222 qemu#8 0x00005631fbfc5499 in qemu_laio_process_completions_and_submit (s=0x7fdfc0297670) at block/linux-aio.c:237 qemu#9 0x00005631fc05d978 in aio_dispatch_handlers (ctx=ctx@entry=0x5631fde0e660) at util/aio-posix.c:406 qemu#10 0x00005631fc05e3ea in aio_poll (ctx=0x5631fde0e660, blocking=blocking@entry=true) at util/aio-posix.c:693 qemu#11 0x00005631fbd7ad96 in iothread_run (opaque=0x5631fde0e1c0) at iothread.c:64 qemu#12 0x00007fdfe0dcee25 in start_thread (arg=0x7fdfd8bd8700) at pthread_create.c:308 qemu#13 0x00007fdfe0afc34d in clone () at ../sysdeps/unix/sysv/linux/x86_64/clone.S:113 - The Main Thread is also processing completions from the same AioContext, and crashes due to failed assertion at util/iov.c:78: Thread 1 (Thread 0x7fdfeb5eac80 (LWP 36740)): #0 0x00007fdfe0a391f7 in __GI_raise (sig=sig@entry=6) at ../nptl/sysdeps/unix/sysv/linux/raise.c:56 qemu#1 0x00007fdfe0a3a8e8 in __GI_abort () at abort.c:90 qemu#2 0x00007fdfe0a32266 in __assert_fail_base (fmt=0x7fdfe0b84e68 "%s%s%s:%u: %s%sAssertion `%s' failed.\n%n", assertion=assertion@entry=0x5631fc238ccb "offset == 0", file=file@entry=0x5631fc23698e "util/iov.c", line=line@entry=78, function=function@entry=0x5631fc236adc <__PRETTY_FUNCTION__.15220> "iov_memset") at assert.c:92 qemu#3 0x00007fdfe0a32312 in __GI___assert_fail (assertion=assertion@entry=0x5631fc238ccb "offset == 0", file=file@entry=0x5631fc23698e "util/iov.c", line=line@entry=78, function=function@entry=0x5631fc236adc <__PRETTY_FUNCTION__.15220> "iov_memset") at assert.c:101 qemu#4 0x00005631fc065287 in iov_memset (iov=<optimized out>, iov_cnt=<optimized out>, offset=<optimized out>, offset@entry=65536, fillc=fillc@entry=0, bytes=15515191315812405248) at util/iov.c:78 qemu#5 0x00005631fc065a63 in qemu_iovec_memset (qiov=<optimized out>, offset=offset@entry=65536, fillc=fillc@entry=0, bytes=<optimized out>) at util/iov.c:410 qemu#6 0x00005631fbfc5178 in qemu_laio_process_completion (laiocb=0x7fdd920df630) at block/linux-aio.c:88 qemu#7 0x00005631fbfc523c in qemu_laio_process_completions (s=s@entry=0x7fdfc0297670) at block/linux-aio.c:222 qemu#8 0x00005631fbfc5499 in qemu_laio_process_completions_and_submit (s=0x7fdfc0297670) at block/linux-aio.c:237 qemu#9 0x00005631fbfc54ed in qemu_laio_poll_cb (opaque=<optimized out>) at block/linux-aio.c:272 qemu#10 0x00005631fc05d85e in run_poll_handlers_once (ctx=ctx@entry=0x5631fde0e660) at util/aio-posix.c:497 qemu#11 0x00005631fc05e2ca in aio_poll (blocking=false, ctx=0x5631fde0e660) at util/aio-posix.c:574 qemu#12 0x00005631fc05e2ca in aio_poll (ctx=0x5631fde0e660, blocking=blocking@entry=false) at util/aio-posix.c:604 qemu#13 0x00005631fbfcb8a3 in bdrv_do_drained_begin (ignore_parent=<optimized out>, recursive=<optimized out>, bs=<optimized out>) at block/io.c:273 qemu#14 0x00005631fbfcb8a3 in bdrv_do_drained_begin (bs=0x5631fe8b6200, recursive=<optimized out>, parent=0x0, ignore_bds_parents=<optimized out>, poll=<optimized out>) at block/io.c:390 qemu#15 0x00005631fbfbcd2e in blk_drain (blk=0x5631fe83ac80) at block/block-backend.c:1590 qemu#16 0x00005631fbfbe138 in blk_remove_bs (blk=blk@entry=0x5631fe83ac80) at block/block-backend.c:774 qemu#17 0x00005631fbfbe3d6 in blk_unref (blk=0x5631fe83ac80) at block/block-backend.c:401 qemu#18 0x00005631fbfbe3d6 in blk_unref (blk=0x5631fe83ac80) at block/block-backend.c:449 qemu#19 0x00005631fbfc9a69 in commit_complete (job=0x5631fe8b94b0, opaque=0x7fdfcc1bb080) at block/commit.c:92 qemu#20 0x00005631fbf7d662 in job_defer_to_main_loop_bh (opaque=0x7fdfcc1b4560) at job.c:973 qemu#21 0x00005631fc05ad41 in aio_bh_poll (bh=0x7fdfcc01ad90) at util/async.c:90 qemu#22 0x00005631fc05ad41 in aio_bh_poll (ctx=ctx@entry=0x5631fddffdb0) at util/async.c:118 qemu#23 0x00005631fc05e210 in aio_dispatch (ctx=0x5631fddffdb0) at util/aio-posix.c:436 qemu#24 0x00005631fc05ac1e in aio_ctx_dispatch (source=<optimized out>, callback=<optimized out>, user_data=<optimized out>) at util/async.c:261 qemu#25 0x00007fdfeaae44c9 in g_main_context_dispatch (context=0x5631fde00140) at gmain.c:3201 qemu#26 0x00007fdfeaae44c9 in g_main_context_dispatch (context=context@entry=0x5631fde00140) at gmain.c:3854 qemu#27 0x00005631fc05d503 in main_loop_wait () at util/main-loop.c:215 qemu#28 0x00005631fc05d503 in main_loop_wait (timeout=<optimized out>) at util/main-loop.c:238 qemu#29 0x00005631fc05d503 in main_loop_wait (nonblocking=nonblocking@entry=0) at util/main-loop.c:497 qemu#30 0x00005631fbd81412 in main_loop () at vl.c:1866 qemu#31 0x00005631fbc18ff3 in main (argc=<optimized out>, argv=<optimized out>, envp=<optimized out>) at vl.c:4647 - A closer examination shows that s->io_q.in_flight appears to have gone backwards: (gdb) frame 7 qemu#7 0x00005631fbfc523c in qemu_laio_process_completions (s=s@entry=0x7fdfc0297670) at block/linux-aio.c:222 222 qemu_laio_process_completion(laiocb); (gdb) p s $2 = (LinuxAioState *) 0x7fdfc0297670 (gdb) p *s $3 = {aio_context = 0x5631fde0e660, ctx = 0x7fdfeb43b000, e = {rfd = 33, wfd = 33}, io_q = {plugged = 0, in_queue = 0, in_flight = 4294967280, blocked = false, pending = {sqh_first = 0x0, sqh_last = 0x7fdfc0297698}}, completion_bh = 0x7fdfc0280ef0, event_idx = 21, event_max = 241} (gdb) p/x s->io_q.in_flight $4 = 0xfffffff0 Signed-off-by: Sergio Lopez <slp@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> (cherry picked from commit e091f0e) Signed-off-by: Kevin Wolf <kwolf@redhat.com> Signed-off-by: Danilo C. L. de Paula <ddepaula@redhat.com>
Let start from the beginning: Commit b9e413d (in 2.9) "block: explicitly acquire aiocontext in aio callbacks that need it" added pairs of aio_context_acquire/release to mirror_write_complete and mirror_read_complete, when they were aio callbacks for blk_aio_* calls. Then, commit 2e1990b (in 3.0) "block/mirror: Convert to coroutines" dropped these blk_aio_* calls, than mirror_write_complete and mirror_read_complete are not callbacks more, and don't need additional aiocontext acquiring. Furthermore, mirror_read_complete calls blk_co_pwritev inside these pair of aio_context_acquire/release, which leads to the following dead-lock with mirror: (gdb) info thr Id Target Id Frame 3 Thread (LWP 145412) "qemu-system-x86" syscall () 2 Thread (LWP 145416) "qemu-system-x86" __lll_lock_wait () * 1 Thread (LWP 145411) "qemu-system-x86" __lll_lock_wait () (gdb) bt #0 __lll_lock_wait () #1 _L_lock_812 () #2 __GI___pthread_mutex_lock #3 qemu_mutex_lock_impl (mutex=0x561032dce420 <qemu_global_mutex>, file=0x5610327d8654 "util/main-loop.c", line=236) at util/qemu-thread-posix.c:66 #4 qemu_mutex_lock_iothread_impl #5 os_host_main_loop_wait (timeout=480116000) at util/main-loop.c:236 #6 main_loop_wait (nonblocking=0) at util/main-loop.c:497 #7 main_loop () at vl.c:1892 #8 main Printing contents of qemu_global_mutex, I see that "__owner = 145416", so, thr1 is main loop, and now it wants BQL, which is owned by thr2. (gdb) thr 2 (gdb) bt #0 __lll_lock_wait () #1 _L_lock_870 () #2 __GI___pthread_mutex_lock #3 qemu_mutex_lock_impl (mutex=0x561034d25dc0, ... #4 aio_context_acquire (ctx=0x561034d25d60) #5 dma_blk_cb #6 dma_blk_io #7 dma_blk_read #8 ide_dma_cb #9 bmdma_cmd_writeb #10 bmdma_write #11 memory_region_write_accessor #12 access_with_adjusted_size #15 flatview_write #16 address_space_write #17 address_space_rw #18 kvm_handle_io #19 kvm_cpu_exec #20 qemu_kvm_cpu_thread_fn #21 qemu_thread_start #22 start_thread #23 clone () Printing mutex in fr 2, I see "__owner = 145411", so thr2 wants aio context mutex, which is owned by thr1. Classic dead-lock. Then, let's check that aio context is hold by mirror coroutine: just print coroutine stack of first tracked request in mirror job target: (gdb) [...] (gdb) qemu coroutine 0x561035dd0860 #0 qemu_coroutine_switch #1 qemu_coroutine_yield #2 qemu_co_mutex_lock_slowpath #3 qemu_co_mutex_lock #4 qcow2_co_pwritev #5 bdrv_driver_pwritev #6 bdrv_aligned_pwritev #7 bdrv_co_pwritev #8 blk_co_pwritev #9 mirror_read_complete () at block/mirror.c:232 #10 mirror_co_read () at block/mirror.c:370 #11 coroutine_trampoline #12 __start_context Yes it is mirror_read_complete calling blk_co_pwritev after acquiring aio context. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> (cherry picked from commit d12ade5) Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
Even for block nodes with bs->drv == NULL, we can't just ignore a bdrv_set_aio_context() call. Leaving the node in its old context can mean that it's still in an iothread context in bdrv_close_all() during shutdown, resulting in an attempted unlock of the AioContext lock which we don't hold. This is an example stack trace of a related crash: #0 0x00007ffff59da57f in raise () at /lib64/libc.so.6 #1 0x00007ffff59c4895 in abort () at /lib64/libc.so.6 #2 0x0000555555b97b1e in error_exit (err=<optimized out>, msg=msg@entry=0x555555d386d0 <__func__.19059> "qemu_mutex_unlock_impl") at util/qemu-thread-posix.c:36 #3 0x0000555555b97f7f in qemu_mutex_unlock_impl (mutex=mutex@entry=0x5555568002f0, file=file@entry=0x555555d378df "util/async.c", line=line@entry=507) at util/qemu-thread-posix.c:97 #4 0x0000555555b92f55 in aio_context_release (ctx=ctx@entry=0x555556800290) at util/async.c:507 #5 0x0000555555b05cf8 in bdrv_prwv_co (child=child@entry=0x7fffc80012f0, offset=offset@entry=131072, qiov=qiov@entry=0x7fffffffd4f0, is_write=is_write@entry=true, flags=flags@entry=0) at block/io.c:833 #6 0x0000555555b060a9 in bdrv_pwritev (qiov=0x7fffffffd4f0, offset=131072, child=0x7fffc80012f0) at block/io.c:990 #7 0x0000555555b060a9 in bdrv_pwrite (child=0x7fffc80012f0, offset=131072, buf=<optimized out>, bytes=<optimized out>) at block/io.c:990 #8 0x0000555555ae172b in qcow2_cache_entry_flush (bs=bs@entry=0x555556810680, c=c@entry=0x5555568cc740, i=i@entry=0) at block/qcow2-cache.c:51 #9 0x0000555555ae18dd in qcow2_cache_write (bs=bs@entry=0x555556810680, c=0x5555568cc740) at block/qcow2-cache.c:248 #10 0x0000555555ae15de in qcow2_cache_flush (bs=0x555556810680, c=<optimized out>) at block/qcow2-cache.c:259 #11 0x0000555555ae16b1 in qcow2_cache_flush_dependency (c=0x5555568a1700, c=0x5555568a1700, bs=0x555556810680) at block/qcow2-cache.c:194 #12 0x0000555555ae16b1 in qcow2_cache_entry_flush (bs=bs@entry=0x555556810680, c=c@entry=0x5555568a1700, i=i@entry=0) at block/qcow2-cache.c:194 #13 0x0000555555ae18dd in qcow2_cache_write (bs=bs@entry=0x555556810680, c=0x5555568a1700) at block/qcow2-cache.c:248 #14 0x0000555555ae15de in qcow2_cache_flush (bs=bs@entry=0x555556810680, c=<optimized out>) at block/qcow2-cache.c:259 #15 0x0000555555ad242c in qcow2_inactivate (bs=bs@entry=0x555556810680) at block/qcow2.c:2124 #16 0x0000555555ad2590 in qcow2_close (bs=0x555556810680) at block/qcow2.c:2153 #17 0x0000555555ab0c62 in bdrv_close (bs=0x555556810680) at block.c:3358 #18 0x0000555555ab0c62 in bdrv_delete (bs=0x555556810680) at block.c:3542 #19 0x0000555555ab0c62 in bdrv_unref (bs=0x555556810680) at block.c:4598 #20 0x0000555555af4d72 in blk_remove_bs (blk=blk@entry=0x5555568103d0) at block/block-backend.c:785 #21 0x0000555555af4dbb in blk_remove_all_bs () at block/block-backend.c:483 #22 0x0000555555aae02f in bdrv_close_all () at block.c:3412 #23 0x00005555557f9796 in main (argc=<optimized out>, argv=<optimized out>, envp=<optimized out>) at vl.c:4776 The reproducer I used is a qcow2 image on gluster volume, where the virtual disk size (4 GB) is larger than the gluster volume size (64M), so we can easily trigger an ENOSPC. This backend is assigned to a virtio-blk device using an iothread, and then from the guest a 'dd if=/dev/zero of=/dev/vda bs=1G count=1' causes the VM to stop because of an I/O error. qemu_gluster_co_flush_to_disk() sets bs->drv = NULL on error, so when virtio-blk stops the dataplane, the block nodes stay in the iothread AioContext. A 'quit' monitor command issued from this paused state crashes the process. Fixes: https://bugzilla.redhat.com/show_bug.cgi?id=1631227 Cc: qemu-stable@nongnu.org Signed-off-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Reviewed-by: Stefano Garzarella <sgarzare@redhat.com>
Even for block nodes with bs->drv == NULL, we can't just ignore a bdrv_set_aio_context() call. Leaving the node in its old context can mean that it's still in an iothread context in bdrv_close_all() during shutdown, resulting in an attempted unlock of the AioContext lock which we don't hold. This is an example stack trace of a related crash: #0 0x00007ffff59da57f in raise () at /lib64/libc.so.6 #1 0x00007ffff59c4895 in abort () at /lib64/libc.so.6 #2 0x0000555555b97b1e in error_exit (err=<optimized out>, msg=msg@entry=0x555555d386d0 <__func__.19059> "qemu_mutex_unlock_impl") at util/qemu-thread-posix.c:36 #3 0x0000555555b97f7f in qemu_mutex_unlock_impl (mutex=mutex@entry=0x5555568002f0, file=file@entry=0x555555d378df "util/async.c", line=line@entry=507) at util/qemu-thread-posix.c:97 #4 0x0000555555b92f55 in aio_context_release (ctx=ctx@entry=0x555556800290) at util/async.c:507 #5 0x0000555555b05cf8 in bdrv_prwv_co (child=child@entry=0x7fffc80012f0, offset=offset@entry=131072, qiov=qiov@entry=0x7fffffffd4f0, is_write=is_write@entry=true, flags=flags@entry=0) at block/io.c:833 #6 0x0000555555b060a9 in bdrv_pwritev (qiov=0x7fffffffd4f0, offset=131072, child=0x7fffc80012f0) at block/io.c:990 #7 0x0000555555b060a9 in bdrv_pwrite (child=0x7fffc80012f0, offset=131072, buf=<optimized out>, bytes=<optimized out>) at block/io.c:990 #8 0x0000555555ae172b in qcow2_cache_entry_flush (bs=bs@entry=0x555556810680, c=c@entry=0x5555568cc740, i=i@entry=0) at block/qcow2-cache.c:51 #9 0x0000555555ae18dd in qcow2_cache_write (bs=bs@entry=0x555556810680, c=0x5555568cc740) at block/qcow2-cache.c:248 #10 0x0000555555ae15de in qcow2_cache_flush (bs=0x555556810680, c=<optimized out>) at block/qcow2-cache.c:259 #11 0x0000555555ae16b1 in qcow2_cache_flush_dependency (c=0x5555568a1700, c=0x5555568a1700, bs=0x555556810680) at block/qcow2-cache.c:194 #12 0x0000555555ae16b1 in qcow2_cache_entry_flush (bs=bs@entry=0x555556810680, c=c@entry=0x5555568a1700, i=i@entry=0) at block/qcow2-cache.c:194 #13 0x0000555555ae18dd in qcow2_cache_write (bs=bs@entry=0x555556810680, c=0x5555568a1700) at block/qcow2-cache.c:248 #14 0x0000555555ae15de in qcow2_cache_flush (bs=bs@entry=0x555556810680, c=<optimized out>) at block/qcow2-cache.c:259 #15 0x0000555555ad242c in qcow2_inactivate (bs=bs@entry=0x555556810680) at block/qcow2.c:2124 #16 0x0000555555ad2590 in qcow2_close (bs=0x555556810680) at block/qcow2.c:2153 #17 0x0000555555ab0c62 in bdrv_close (bs=0x555556810680) at block.c:3358 #18 0x0000555555ab0c62 in bdrv_delete (bs=0x555556810680) at block.c:3542 #19 0x0000555555ab0c62 in bdrv_unref (bs=0x555556810680) at block.c:4598 #20 0x0000555555af4d72 in blk_remove_bs (blk=blk@entry=0x5555568103d0) at block/block-backend.c:785 #21 0x0000555555af4dbb in blk_remove_all_bs () at block/block-backend.c:483 #22 0x0000555555aae02f in bdrv_close_all () at block.c:3412 #23 0x00005555557f9796 in main (argc=<optimized out>, argv=<optimized out>, envp=<optimized out>) at vl.c:4776 The reproducer I used is a qcow2 image on gluster volume, where the virtual disk size (4 GB) is larger than the gluster volume size (64M), so we can easily trigger an ENOSPC. This backend is assigned to a virtio-blk device using an iothread, and then from the guest a 'dd if=/dev/zero of=/dev/vda bs=1G count=1' causes the VM to stop because of an I/O error. qemu_gluster_co_flush_to_disk() sets bs->drv = NULL on error, so when virtio-blk stops the dataplane, the block nodes stay in the iothread AioContext. A 'quit' monitor command issued from this paused state crashes the process. Fixes: https://bugzilla.redhat.com/show_bug.cgi?id=1631227 Cc: qemu-stable@nongnu.org Signed-off-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Reviewed-by: Stefano Garzarella <sgarzare@redhat.com> (cherry picked from commit 1bffe1a) *drop context dependency on e64f25f Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
Even for block nodes with bs->drv == NULL, we can't just ignore a bdrv_set_aio_context() call. Leaving the node in its old context can mean that it's still in an iothread context in bdrv_close_all() during shutdown, resulting in an attempted unlock of the AioContext lock which we don't hold. This is an example stack trace of a related crash: #0 0x00007ffff59da57f in raise () at /lib64/libc.so.6 #1 0x00007ffff59c4895 in abort () at /lib64/libc.so.6 #2 0x0000555555b97b1e in error_exit (err=<optimized out>, msg=msg@entry=0x555555d386d0 <__func__.19059> "qemu_mutex_unlock_impl") at util/qemu-thread-posix.c:36 #3 0x0000555555b97f7f in qemu_mutex_unlock_impl (mutex=mutex@entry=0x5555568002f0, file=file@entry=0x555555d378df "util/async.c", line=line@entry=507) at util/qemu-thread-posix.c:97 #4 0x0000555555b92f55 in aio_context_release (ctx=ctx@entry=0x555556800290) at util/async.c:507 #5 0x0000555555b05cf8 in bdrv_prwv_co (child=child@entry=0x7fffc80012f0, offset=offset@entry=131072, qiov=qiov@entry=0x7fffffffd4f0, is_write=is_write@entry=true, flags=flags@entry=0) at block/io.c:833 #6 0x0000555555b060a9 in bdrv_pwritev (qiov=0x7fffffffd4f0, offset=131072, child=0x7fffc80012f0) at block/io.c:990 #7 0x0000555555b060a9 in bdrv_pwrite (child=0x7fffc80012f0, offset=131072, buf=<optimized out>, bytes=<optimized out>) at block/io.c:990 #8 0x0000555555ae172b in qcow2_cache_entry_flush (bs=bs@entry=0x555556810680, c=c@entry=0x5555568cc740, i=i@entry=0) at block/qcow2-cache.c:51 #9 0x0000555555ae18dd in qcow2_cache_write (bs=bs@entry=0x555556810680, c=0x5555568cc740) at block/qcow2-cache.c:248 #10 0x0000555555ae15de in qcow2_cache_flush (bs=0x555556810680, c=<optimized out>) at block/qcow2-cache.c:259 #11 0x0000555555ae16b1 in qcow2_cache_flush_dependency (c=0x5555568a1700, c=0x5555568a1700, bs=0x555556810680) at block/qcow2-cache.c:194 #12 0x0000555555ae16b1 in qcow2_cache_entry_flush (bs=bs@entry=0x555556810680, c=c@entry=0x5555568a1700, i=i@entry=0) at block/qcow2-cache.c:194 #13 0x0000555555ae18dd in qcow2_cache_write (bs=bs@entry=0x555556810680, c=0x5555568a1700) at block/qcow2-cache.c:248 #14 0x0000555555ae15de in qcow2_cache_flush (bs=bs@entry=0x555556810680, c=<optimized out>) at block/qcow2-cache.c:259 #15 0x0000555555ad242c in qcow2_inactivate (bs=bs@entry=0x555556810680) at block/qcow2.c:2124 #16 0x0000555555ad2590 in qcow2_close (bs=0x555556810680) at block/qcow2.c:2153 #17 0x0000555555ab0c62 in bdrv_close (bs=0x555556810680) at block.c:3358 #18 0x0000555555ab0c62 in bdrv_delete (bs=0x555556810680) at block.c:3542 #19 0x0000555555ab0c62 in bdrv_unref (bs=0x555556810680) at block.c:4598 #20 0x0000555555af4d72 in blk_remove_bs (blk=blk@entry=0x5555568103d0) at block/block-backend.c:785 #21 0x0000555555af4dbb in blk_remove_all_bs () at block/block-backend.c:483 #22 0x0000555555aae02f in bdrv_close_all () at block.c:3412 #23 0x00005555557f9796 in main (argc=<optimized out>, argv=<optimized out>, envp=<optimized out>) at vl.c:4776 The reproducer I used is a qcow2 image on gluster volume, where the virtual disk size (4 GB) is larger than the gluster volume size (64M), so we can easily trigger an ENOSPC. This backend is assigned to a virtio-blk device using an iothread, and then from the guest a 'dd if=/dev/zero of=/dev/vda bs=1G count=1' causes the VM to stop because of an I/O error. qemu_gluster_co_flush_to_disk() sets bs->drv = NULL on error, so when virtio-blk stops the dataplane, the block nodes stay in the iothread AioContext. A 'quit' monitor command issued from this paused state crashes the process. Fixes: https://bugzilla.redhat.com/show_bug.cgi?id=1631227 Cc: qemu-stable@nongnu.org Signed-off-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Reviewed-by: Stefano Garzarella <sgarzare@redhat.com> (cherry picked from commit 1bffe1a) Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
All paths that lead to bdrv_backup_top_drop(), except for the call from backup_clean(), imply that the BDS AioContext has already been acquired, so doing it there too can potentially lead to QEMU hanging on AIO_WAIT_WHILE(). An easy way to trigger this situation is by issuing a two actions transaction, with a proper and a bogus blockdev-backup, so the second one will trigger a rollback. This will trigger a hang with an stack trace like this one: #0 0x00007fb680c75016 in __GI_ppoll (fds=0x55e74580f7c0, nfds=1, timeout=<optimized out>, timeout@entry=0x0, sigmask=sigmask@entry=0x0) at ../sysdeps/unix/sysv/linux/ppoll.c:39 qemu#1 0x000055e743386e09 in ppoll (__ss=0x0, __timeout=0x0, __nfds=<optimized out>, __fds=<optimized out>) at /usr/include/bits/poll2.h:77 qemu#2 0x000055e743386e09 in qemu_poll_ns (fds=<optimized out>, nfds=<optimized out>, timeout=<optimized out>) at util/qemu-timer.c:336 qemu#3 0x000055e743388dc4 in aio_poll (ctx=0x55e7458925d0, blocking=blocking@entry=true) at util/aio-posix.c:669 qemu#4 0x000055e743305dea in bdrv_flush (bs=bs@entry=0x55e74593c0d0) at block/io.c:2878 qemu#5 0x000055e7432be58e in bdrv_close (bs=0x55e74593c0d0) at block.c:4017 qemu#6 0x000055e7432be58e in bdrv_delete (bs=<optimized out>) at block.c:4262 qemu#7 0x000055e7432be58e in bdrv_unref (bs=bs@entry=0x55e74593c0d0) at block.c:5644 qemu#8 0x000055e743316b9b in bdrv_backup_top_drop (bs=bs@entry=0x55e74593c0d0) at block/backup-top.c:273 qemu#9 0x000055e74331461f in backup_job_create (job_id=0x0, bs=bs@entry=0x55e7458d5820, target=target@entry=0x55e74589f640, speed=0, sync_mode=MIRROR_SYNC_MODE_FULL, sync_bitmap=sync_bitmap@entry=0x0, bitmap_mode=BITMAP_SYNC_MODE_ON_SUCCESS, compress=false, filter_node_name=0x0, on_source_error=BLOCKDEV_ON_ERROR_REPORT, on_target_error=BLOCKDEV_ON_ERROR_REPORT, creation_flags=0, cb=0x0, opaque=0x0, txn=0x0, errp=0x7ffddfd1efb0) at block/backup.c:478 qemu#10 0x000055e74315bc52 in do_backup_common (backup=backup@entry=0x55e746c066d0, bs=bs@entry=0x55e7458d5820, target_bs=target_bs@entry=0x55e74589f640, aio_context=aio_context@entry=0x55e7458a91e0, txn=txn@entry=0x0, errp=errp@entry=0x7ffddfd1efb0) at blockdev.c:3580 qemu#11 0x000055e74315c37c in do_blockdev_backup (backup=backup@entry=0x55e746c066d0, txn=0x0, errp=errp@entry=0x7ffddfd1efb0) at /usr/src/debug/qemu-kvm-4.2.0-2.module+el8.2.0+5135+ed3b2489.x86_64/./qapi/qapi-types-block-core.h:1492 qemu#12 0x000055e74315c449 in blockdev_backup_prepare (common=0x55e746a8de90, errp=0x7ffddfd1f018) at blockdev.c:1885 qemu#13 0x000055e743160152 in qmp_transaction (dev_list=<optimized out>, has_props=<optimized out>, props=0x55e7467fe2c0, errp=errp@entry=0x7ffddfd1f088) at blockdev.c:2340 qemu#14 0x000055e743287ff5 in qmp_marshal_transaction (args=<optimized out>, ret=<optimized out>, errp=0x7ffddfd1f0f8) at qapi/qapi-commands-transaction.c:44 qemu#15 0x000055e74333de6c in do_qmp_dispatch (errp=0x7ffddfd1f0f0, allow_oob=<optimized out>, request=<optimized out>, cmds=0x55e743c28d60 <qmp_commands>) at qapi/qmp-dispatch.c:132 qemu#16 0x000055e74333de6c in qmp_dispatch (cmds=0x55e743c28d60 <qmp_commands>, request=<optimized out>, allow_oob=<optimized out>) at qapi/qmp-dispatch.c:175 qemu#17 0x000055e74325c061 in monitor_qmp_dispatch (mon=0x55e745908030, req=<optimized out>) at monitor/qmp.c:145 qemu#18 0x000055e74325c6fa in monitor_qmp_bh_dispatcher (data=<optimized out>) at monitor/qmp.c:234 qemu#19 0x000055e743385866 in aio_bh_call (bh=0x55e745807ae0) at util/async.c:117 qemu#20 0x000055e743385866 in aio_bh_poll (ctx=ctx@entry=0x55e7458067a0) at util/async.c:117 qemu#21 0x000055e743388c54 in aio_dispatch (ctx=0x55e7458067a0) at util/aio-posix.c:459 qemu#22 0x000055e743385742 in aio_ctx_dispatch (source=<optimized out>, callback=<optimized out>, user_data=<optimized out>) at util/async.c:260 qemu#23 0x00007fb68543e67d in g_main_dispatch (context=0x55e745893a40) at gmain.c:3176 qemu#24 0x00007fb68543e67d in g_main_context_dispatch (context=context@entry=0x55e745893a40) at gmain.c:3829 qemu#25 0x000055e743387d08 in glib_pollfds_poll () at util/main-loop.c:219 qemu#26 0x000055e743387d08 in os_host_main_loop_wait (timeout=<optimized out>) at util/main-loop.c:242 qemu#27 0x000055e743387d08 in main_loop_wait (nonblocking=<optimized out>) at util/main-loop.c:518 qemu#28 0x000055e74316a3c1 in main_loop () at vl.c:1828 qemu#29 0x000055e743016a72 in main (argc=<optimized out>, argv=<optimized out>, envp=<optimized out>) at vl.c:4504 Fix this by not acquiring the AioContext there, and ensuring all paths leading to it have it already acquired (backup_clean()). RHBZ: https://bugzilla.redhat.com/show_bug.cgi?id=1782111 Signed-off-by: Sergio Lopez <slp@redhat.com>
Dirty map addition and removal functions are not acquiring to BDS AioContext, while they may call to code that expects it to be acquired. This may trigger a crash with a stack trace like this one: #0 0x00007f0ef146370f in __GI_raise (sig=sig@entry=6) at ../sysdeps/unix/sysv/linux/raise.c:50 qemu#1 0x00007f0ef144db25 in __GI_abort () at abort.c:79 qemu#2 0x0000565022294dce in error_exit (err=<optimized out>, msg=msg@entry=0x56502243a730 <__func__.16350> "qemu_mutex_unlock_impl") at util/qemu-thread-posix.c:36 qemu#3 0x00005650222950ba in qemu_mutex_unlock_impl (mutex=mutex@entry=0x5650244b0240, file=file@entry=0x565022439adf "util/async.c", line=line@entry=526) at util/qemu-thread-posix.c:108 qemu#4 0x0000565022290029 in aio_context_release (ctx=ctx@entry=0x5650244b01e0) at util/async.c:526 qemu#5 0x000056502221cd08 in bdrv_can_store_new_dirty_bitmap (bs=bs@entry=0x5650244dc820, name=name@entry=0x56502481d360 "bitmap1", granularity=granularity@entry=65536, errp=errp@entry=0x7fff22831718) at block/dirty-bitmap.c:542 qemu#6 0x000056502206ae53 in qmp_block_dirty_bitmap_add (errp=0x7fff22831718, disabled=false, has_disabled=<optimized out>, persistent=<optimized out>, has_persistent=true, granularity=65536, has_granularity=<optimized out>, name=0x56502481d360 "bitmap1", node=<optimized out>) at blockdev.c:2894 qemu#7 0x000056502206ae53 in qmp_block_dirty_bitmap_add (node=<optimized out>, name=0x56502481d360 "bitmap1", has_granularity=<optimized out>, granularity=<optimized out>, has_persistent=true, persistent=<optimized out>, has_disabled=false, disabled=false, errp=0x7fff22831718) at blockdev.c:2856 qemu#8 0x00005650221847a3 in qmp_marshal_block_dirty_bitmap_add (args=<optimized out>, ret=<optimized out>, errp=0x7fff22831798) at qapi/qapi-commands-block-core.c:651 qemu#9 0x0000565022247e6c in do_qmp_dispatch (errp=0x7fff22831790, allow_oob=<optimized out>, request=<optimized out>, cmds=0x565022b32d60 <qmp_commands>) at qapi/qmp-dispatch.c:132 qemu#10 0x0000565022247e6c in qmp_dispatch (cmds=0x565022b32d60 <qmp_commands>, request=<optimized out>, allow_oob=<optimized out>) at qapi/qmp-dispatch.c:175 qemu#11 0x0000565022166061 in monitor_qmp_dispatch (mon=0x56502450faa0, req=<optimized out>) at monitor/qmp.c:145 qemu#12 0x00005650221666fa in monitor_qmp_bh_dispatcher (data=<optimized out>) at monitor/qmp.c:234 qemu#13 0x000056502228f866 in aio_bh_call (bh=0x56502440eae0) at util/async.c:117 qemu#14 0x000056502228f866 in aio_bh_poll (ctx=ctx@entry=0x56502440d7a0) at util/async.c:117 qemu#15 0x0000565022292c54 in aio_dispatch (ctx=0x56502440d7a0) at util/aio-posix.c:459 qemu#16 0x000056502228f742 in aio_ctx_dispatch (source=<optimized out>, callback=<optimized out>, user_data=<optimized out>) at util/async.c:260 qemu#17 0x00007f0ef5ce667d in g_main_dispatch (context=0x56502449aa40) at gmain.c:3176 qemu#18 0x00007f0ef5ce667d in g_main_context_dispatch (context=context@entry=0x56502449aa40) at gmain.c:3829 qemu#19 0x0000565022291d08 in glib_pollfds_poll () at util/main-loop.c:219 qemu#20 0x0000565022291d08 in os_host_main_loop_wait (timeout=<optimized out>) at util/main-loop.c:242 qemu#21 0x0000565022291d08 in main_loop_wait (nonblocking=<optimized out>) at util/main-loop.c:518 qemu#22 0x00005650220743c1 in main_loop () at vl.c:1828 qemu#23 0x0000565021f20a72 in main (argc=<optimized out>, argv=<optimized out>, envp=<optimized out>) at vl.c:4504 Fix this by acquiring the AioContext at qmp_block_dirty_bitmap_add() and qmp_block_dirty_bitmap_add(). RHBZ: https://bugzilla.redhat.com/show_bug.cgi?id=1782175 Signed-off-by: Sergio Lopez <slp@redhat.com>
external_snapshot_abort() calls to bdrv_set_backing_hd(), which returns state->old_bs to the main AioContext, as it's intended to be used then the BDS is going to be released. As that's not the case when aborting an external snapshot, return it to the AioContext it was before the call. This issue can be triggered by issuing a transaction with two actions, a proper blockdev-snapshot-sync and a bogus one, so the second will trigger a transaction abort. This results in a crash with an stack trace like this one: #0 0x00007fa1048b28df in __GI_raise (sig=sig@entry=6) at ../sysdeps/unix/sysv/linux/raise.c:50 qemu#1 0x00007fa10489ccf5 in __GI_abort () at abort.c:79 qemu#2 0x00007fa10489cbc9 in __assert_fail_base (fmt=0x7fa104a03300 "%s%s%s:%u: %s%sAssertion `%s' failed.\n%n", assertion=0x5572240b44d8 "bdrv_get_aio_context(old_bs) == bdrv_get_aio_context(new_bs)", file=0x557224014d30 "block.c", line=2240, function=<optimized out>) at assert.c:92 qemu#3 0x00007fa1048aae96 in __GI___assert_fail (assertion=assertion@entry=0x5572240b44d8 "bdrv_get_aio_context(old_bs) == bdrv_get_aio_context(new_bs)", file=file@entry=0x557224014d30 "block.c", line=line@entry=2240, function=function@entry=0x5572240b5d60 <__PRETTY_FUNCTION__.31620> "bdrv_replace_child_noperm") at assert.c:101 qemu#4 0x0000557223e631f8 in bdrv_replace_child_noperm (child=0x557225b9c980, new_bs=new_bs@entry=0x557225c42e40) at block.c:2240 qemu#5 0x0000557223e68be7 in bdrv_replace_node (from=0x557226951a60, to=0x557225c42e40, errp=0x5572247d6138 <error_abort>) at block.c:4196 qemu#6 0x0000557223d069c4 in external_snapshot_abort (common=0x557225d7e170) at blockdev.c:1731 qemu#7 0x0000557223d069c4 in external_snapshot_abort (common=0x557225d7e170) at blockdev.c:1717 qemu#8 0x0000557223d09013 in qmp_transaction (dev_list=<optimized out>, has_props=<optimized out>, props=0x557225cc7d70, errp=errp@entry=0x7ffe704c0c98) at blockdev.c:2360 qemu#9 0x0000557223e32085 in qmp_marshal_transaction (args=<optimized out>, ret=<optimized out>, errp=0x7ffe704c0d08) at qapi/qapi-commands-transaction.c:44 qemu#10 0x0000557223ee798c in do_qmp_dispatch (errp=0x7ffe704c0d00, allow_oob=<optimized out>, request=<optimized out>, cmds=0x5572247d3cc0 <qmp_commands>) at qapi/qmp-dispatch.c:132 qemu#11 0x0000557223ee798c in qmp_dispatch (cmds=0x5572247d3cc0 <qmp_commands>, request=<optimized out>, allow_oob=<optimized out>) at qapi/qmp-dispatch.c:175 qemu#12 0x0000557223e06141 in monitor_qmp_dispatch (mon=0x557225c69ff0, req=<optimized out>) at monitor/qmp.c:120 qemu#13 0x0000557223e0678a in monitor_qmp_bh_dispatcher (data=<optimized out>) at monitor/qmp.c:209 qemu#14 0x0000557223f2f366 in aio_bh_call (bh=0x557225b9dc60) at util/async.c:117 qemu#15 0x0000557223f2f366 in aio_bh_poll (ctx=ctx@entry=0x557225b9c840) at util/async.c:117 qemu#16 0x0000557223f32754 in aio_dispatch (ctx=0x557225b9c840) at util/aio-posix.c:459 qemu#17 0x0000557223f2f242 in aio_ctx_dispatch (source=<optimized out>, callback=<optimized out>, user_data=<optimized out>) at util/async.c:260 qemu#18 0x00007fa10913467d in g_main_dispatch (context=0x557225c28e80) at gmain.c:3176 qemu#19 0x00007fa10913467d in g_main_context_dispatch (context=context@entry=0x557225c28e80) at gmain.c:3829 qemu#20 0x0000557223f31808 in glib_pollfds_poll () at util/main-loop.c:219 qemu#21 0x0000557223f31808 in os_host_main_loop_wait (timeout=<optimized out>) at util/main-loop.c:242 qemu#22 0x0000557223f31808 in main_loop_wait (nonblocking=<optimized out>) at util/main-loop.c:518 qemu#23 0x0000557223d13201 in main_loop () at vl.c:1828 qemu#24 0x0000557223bbfb82 in main (argc=<optimized out>, argv=<optimized out>, envp=<optimized out>) at vl.c:4504 RHBZ: https://bugzilla.redhat.com/show_bug.cgi?id=1779036 Signed-off-by: Sergio Lopez <slp@redhat.com>
All paths that lead to bdrv_backup_top_drop(), except for the call from backup_clean(), imply that the BDS AioContext has already been acquired, so doing it there too can potentially lead to QEMU hanging on AIO_WAIT_WHILE(). An easy way to trigger this situation is by issuing a two actions transaction, with a proper and a bogus blockdev-backup, so the second one will trigger a rollback. This will trigger a hang with an stack trace like this one: #0 0x00007fb680c75016 in __GI_ppoll (fds=0x55e74580f7c0, nfds=1, timeout=<optimized out>, timeout@entry=0x0, sigmask=sigmask@entry=0x0) at ../sysdeps/unix/sysv/linux/ppoll.c:39 qemu#1 0x000055e743386e09 in ppoll (__ss=0x0, __timeout=0x0, __nfds=<optimized out>, __fds=<optimized out>) at /usr/include/bits/poll2.h:77 qemu#2 0x000055e743386e09 in qemu_poll_ns (fds=<optimized out>, nfds=<optimized out>, timeout=<optimized out>) at util/qemu-timer.c:336 qemu#3 0x000055e743388dc4 in aio_poll (ctx=0x55e7458925d0, blocking=blocking@entry=true) at util/aio-posix.c:669 qemu#4 0x000055e743305dea in bdrv_flush (bs=bs@entry=0x55e74593c0d0) at block/io.c:2878 qemu#5 0x000055e7432be58e in bdrv_close (bs=0x55e74593c0d0) at block.c:4017 qemu#6 0x000055e7432be58e in bdrv_delete (bs=<optimized out>) at block.c:4262 qemu#7 0x000055e7432be58e in bdrv_unref (bs=bs@entry=0x55e74593c0d0) at block.c:5644 qemu#8 0x000055e743316b9b in bdrv_backup_top_drop (bs=bs@entry=0x55e74593c0d0) at block/backup-top.c:273 qemu#9 0x000055e74331461f in backup_job_create (job_id=0x0, bs=bs@entry=0x55e7458d5820, target=target@entry=0x55e74589f640, speed=0, sync_mode=MIRROR_SYNC_MODE_FULL, sync_bitmap=sync_bitmap@entry=0x0, bitmap_mode=BITMAP_SYNC_MODE_ON_SUCCESS, compress=false, filter_node_name=0x0, on_source_error=BLOCKDEV_ON_ERROR_REPORT, on_target_error=BLOCKDEV_ON_ERROR_REPORT, creation_flags=0, cb=0x0, opaque=0x0, txn=0x0, errp=0x7ffddfd1efb0) at block/backup.c:478 qemu#10 0x000055e74315bc52 in do_backup_common (backup=backup@entry=0x55e746c066d0, bs=bs@entry=0x55e7458d5820, target_bs=target_bs@entry=0x55e74589f640, aio_context=aio_context@entry=0x55e7458a91e0, txn=txn@entry=0x0, errp=errp@entry=0x7ffddfd1efb0) at blockdev.c:3580 qemu#11 0x000055e74315c37c in do_blockdev_backup (backup=backup@entry=0x55e746c066d0, txn=0x0, errp=errp@entry=0x7ffddfd1efb0) at /usr/src/debug/qemu-kvm-4.2.0-2.module+el8.2.0+5135+ed3b2489.x86_64/./qapi/qapi-types-block-core.h:1492 qemu#12 0x000055e74315c449 in blockdev_backup_prepare (common=0x55e746a8de90, errp=0x7ffddfd1f018) at blockdev.c:1885 qemu#13 0x000055e743160152 in qmp_transaction (dev_list=<optimized out>, has_props=<optimized out>, props=0x55e7467fe2c0, errp=errp@entry=0x7ffddfd1f088) at blockdev.c:2340 qemu#14 0x000055e743287ff5 in qmp_marshal_transaction (args=<optimized out>, ret=<optimized out>, errp=0x7ffddfd1f0f8) at qapi/qapi-commands-transaction.c:44 qemu#15 0x000055e74333de6c in do_qmp_dispatch (errp=0x7ffddfd1f0f0, allow_oob=<optimized out>, request=<optimized out>, cmds=0x55e743c28d60 <qmp_commands>) at qapi/qmp-dispatch.c:132 qemu#16 0x000055e74333de6c in qmp_dispatch (cmds=0x55e743c28d60 <qmp_commands>, request=<optimized out>, allow_oob=<optimized out>) at qapi/qmp-dispatch.c:175 qemu#17 0x000055e74325c061 in monitor_qmp_dispatch (mon=0x55e745908030, req=<optimized out>) at monitor/qmp.c:145 qemu#18 0x000055e74325c6fa in monitor_qmp_bh_dispatcher (data=<optimized out>) at monitor/qmp.c:234 qemu#19 0x000055e743385866 in aio_bh_call (bh=0x55e745807ae0) at util/async.c:117 qemu#20 0x000055e743385866 in aio_bh_poll (ctx=ctx@entry=0x55e7458067a0) at util/async.c:117 qemu#21 0x000055e743388c54 in aio_dispatch (ctx=0x55e7458067a0) at util/aio-posix.c:459 qemu#22 0x000055e743385742 in aio_ctx_dispatch (source=<optimized out>, callback=<optimized out>, user_data=<optimized out>) at util/async.c:260 qemu#23 0x00007fb68543e67d in g_main_dispatch (context=0x55e745893a40) at gmain.c:3176 qemu#24 0x00007fb68543e67d in g_main_context_dispatch (context=context@entry=0x55e745893a40) at gmain.c:3829 qemu#25 0x000055e743387d08 in glib_pollfds_poll () at util/main-loop.c:219 qemu#26 0x000055e743387d08 in os_host_main_loop_wait (timeout=<optimized out>) at util/main-loop.c:242 qemu#27 0x000055e743387d08 in main_loop_wait (nonblocking=<optimized out>) at util/main-loop.c:518 qemu#28 0x000055e74316a3c1 in main_loop () at vl.c:1828 qemu#29 0x000055e743016a72 in main (argc=<optimized out>, argv=<optimized out>, envp=<optimized out>) at vl.c:4504 Fix this by not acquiring the AioContext there, and ensuring all paths leading to it have it already acquired (backup_clean()). RHBZ: https://bugzilla.redhat.com/show_bug.cgi?id=1782111 Signed-off-by: Sergio Lopez <slp@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Dirty map addition and removal functions are not acquiring to BDS AioContext, while they may call to code that expects it to be acquired. This may trigger a crash with a stack trace like this one: #0 0x00007f0ef146370f in __GI_raise (sig=sig@entry=6) at ../sysdeps/unix/sysv/linux/raise.c:50 qemu#1 0x00007f0ef144db25 in __GI_abort () at abort.c:79 qemu#2 0x0000565022294dce in error_exit (err=<optimized out>, msg=msg@entry=0x56502243a730 <__func__.16350> "qemu_mutex_unlock_impl") at util/qemu-thread-posix.c:36 qemu#3 0x00005650222950ba in qemu_mutex_unlock_impl (mutex=mutex@entry=0x5650244b0240, file=file@entry=0x565022439adf "util/async.c", line=line@entry=526) at util/qemu-thread-posix.c:108 qemu#4 0x0000565022290029 in aio_context_release (ctx=ctx@entry=0x5650244b01e0) at util/async.c:526 qemu#5 0x000056502221cd08 in bdrv_can_store_new_dirty_bitmap (bs=bs@entry=0x5650244dc820, name=name@entry=0x56502481d360 "bitmap1", granularity=granularity@entry=65536, errp=errp@entry=0x7fff22831718) at block/dirty-bitmap.c:542 qemu#6 0x000056502206ae53 in qmp_block_dirty_bitmap_add (errp=0x7fff22831718, disabled=false, has_disabled=<optimized out>, persistent=<optimized out>, has_persistent=true, granularity=65536, has_granularity=<optimized out>, name=0x56502481d360 "bitmap1", node=<optimized out>) at blockdev.c:2894 qemu#7 0x000056502206ae53 in qmp_block_dirty_bitmap_add (node=<optimized out>, name=0x56502481d360 "bitmap1", has_granularity=<optimized out>, granularity=<optimized out>, has_persistent=true, persistent=<optimized out>, has_disabled=false, disabled=false, errp=0x7fff22831718) at blockdev.c:2856 qemu#8 0x00005650221847a3 in qmp_marshal_block_dirty_bitmap_add (args=<optimized out>, ret=<optimized out>, errp=0x7fff22831798) at qapi/qapi-commands-block-core.c:651 qemu#9 0x0000565022247e6c in do_qmp_dispatch (errp=0x7fff22831790, allow_oob=<optimized out>, request=<optimized out>, cmds=0x565022b32d60 <qmp_commands>) at qapi/qmp-dispatch.c:132 qemu#10 0x0000565022247e6c in qmp_dispatch (cmds=0x565022b32d60 <qmp_commands>, request=<optimized out>, allow_oob=<optimized out>) at qapi/qmp-dispatch.c:175 qemu#11 0x0000565022166061 in monitor_qmp_dispatch (mon=0x56502450faa0, req=<optimized out>) at monitor/qmp.c:145 qemu#12 0x00005650221666fa in monitor_qmp_bh_dispatcher (data=<optimized out>) at monitor/qmp.c:234 qemu#13 0x000056502228f866 in aio_bh_call (bh=0x56502440eae0) at util/async.c:117 qemu#14 0x000056502228f866 in aio_bh_poll (ctx=ctx@entry=0x56502440d7a0) at util/async.c:117 qemu#15 0x0000565022292c54 in aio_dispatch (ctx=0x56502440d7a0) at util/aio-posix.c:459 qemu#16 0x000056502228f742 in aio_ctx_dispatch (source=<optimized out>, callback=<optimized out>, user_data=<optimized out>) at util/async.c:260 qemu#17 0x00007f0ef5ce667d in g_main_dispatch (context=0x56502449aa40) at gmain.c:3176 qemu#18 0x00007f0ef5ce667d in g_main_context_dispatch (context=context@entry=0x56502449aa40) at gmain.c:3829 qemu#19 0x0000565022291d08 in glib_pollfds_poll () at util/main-loop.c:219 qemu#20 0x0000565022291d08 in os_host_main_loop_wait (timeout=<optimized out>) at util/main-loop.c:242 qemu#21 0x0000565022291d08 in main_loop_wait (nonblocking=<optimized out>) at util/main-loop.c:518 qemu#22 0x00005650220743c1 in main_loop () at vl.c:1828 qemu#23 0x0000565021f20a72 in main (argc=<optimized out>, argv=<optimized out>, envp=<optimized out>) at vl.c:4504 Fix this by acquiring the AioContext at qmp_block_dirty_bitmap_add() and qmp_block_dirty_bitmap_add(). RHBZ: https://bugzilla.redhat.com/show_bug.cgi?id=1782175 Signed-off-by: Sergio Lopez <slp@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
external_snapshot_abort() calls to bdrv_set_backing_hd(), which returns state->old_bs to the main AioContext, as it's intended to be used then the BDS is going to be released. As that's not the case when aborting an external snapshot, return it to the AioContext it was before the call. This issue can be triggered by issuing a transaction with two actions, a proper blockdev-snapshot-sync and a bogus one, so the second will trigger a transaction abort. This results in a crash with an stack trace like this one: #0 0x00007fa1048b28df in __GI_raise (sig=sig@entry=6) at ../sysdeps/unix/sysv/linux/raise.c:50 qemu#1 0x00007fa10489ccf5 in __GI_abort () at abort.c:79 qemu#2 0x00007fa10489cbc9 in __assert_fail_base (fmt=0x7fa104a03300 "%s%s%s:%u: %s%sAssertion `%s' failed.\n%n", assertion=0x5572240b44d8 "bdrv_get_aio_context(old_bs) == bdrv_get_aio_context(new_bs)", file=0x557224014d30 "block.c", line=2240, function=<optimized out>) at assert.c:92 qemu#3 0x00007fa1048aae96 in __GI___assert_fail (assertion=assertion@entry=0x5572240b44d8 "bdrv_get_aio_context(old_bs) == bdrv_get_aio_context(new_bs)", file=file@entry=0x557224014d30 "block.c", line=line@entry=2240, function=function@entry=0x5572240b5d60 <__PRETTY_FUNCTION__.31620> "bdrv_replace_child_noperm") at assert.c:101 qemu#4 0x0000557223e631f8 in bdrv_replace_child_noperm (child=0x557225b9c980, new_bs=new_bs@entry=0x557225c42e40) at block.c:2240 qemu#5 0x0000557223e68be7 in bdrv_replace_node (from=0x557226951a60, to=0x557225c42e40, errp=0x5572247d6138 <error_abort>) at block.c:4196 qemu#6 0x0000557223d069c4 in external_snapshot_abort (common=0x557225d7e170) at blockdev.c:1731 qemu#7 0x0000557223d069c4 in external_snapshot_abort (common=0x557225d7e170) at blockdev.c:1717 qemu#8 0x0000557223d09013 in qmp_transaction (dev_list=<optimized out>, has_props=<optimized out>, props=0x557225cc7d70, errp=errp@entry=0x7ffe704c0c98) at blockdev.c:2360 qemu#9 0x0000557223e32085 in qmp_marshal_transaction (args=<optimized out>, ret=<optimized out>, errp=0x7ffe704c0d08) at qapi/qapi-commands-transaction.c:44 qemu#10 0x0000557223ee798c in do_qmp_dispatch (errp=0x7ffe704c0d00, allow_oob=<optimized out>, request=<optimized out>, cmds=0x5572247d3cc0 <qmp_commands>) at qapi/qmp-dispatch.c:132 qemu#11 0x0000557223ee798c in qmp_dispatch (cmds=0x5572247d3cc0 <qmp_commands>, request=<optimized out>, allow_oob=<optimized out>) at qapi/qmp-dispatch.c:175 qemu#12 0x0000557223e06141 in monitor_qmp_dispatch (mon=0x557225c69ff0, req=<optimized out>) at monitor/qmp.c:120 qemu#13 0x0000557223e0678a in monitor_qmp_bh_dispatcher (data=<optimized out>) at monitor/qmp.c:209 qemu#14 0x0000557223f2f366 in aio_bh_call (bh=0x557225b9dc60) at util/async.c:117 qemu#15 0x0000557223f2f366 in aio_bh_poll (ctx=ctx@entry=0x557225b9c840) at util/async.c:117 qemu#16 0x0000557223f32754 in aio_dispatch (ctx=0x557225b9c840) at util/aio-posix.c:459 qemu#17 0x0000557223f2f242 in aio_ctx_dispatch (source=<optimized out>, callback=<optimized out>, user_data=<optimized out>) at util/async.c:260 qemu#18 0x00007fa10913467d in g_main_dispatch (context=0x557225c28e80) at gmain.c:3176 qemu#19 0x00007fa10913467d in g_main_context_dispatch (context=context@entry=0x557225c28e80) at gmain.c:3829 qemu#20 0x0000557223f31808 in glib_pollfds_poll () at util/main-loop.c:219 qemu#21 0x0000557223f31808 in os_host_main_loop_wait (timeout=<optimized out>) at util/main-loop.c:242 qemu#22 0x0000557223f31808 in main_loop_wait (nonblocking=<optimized out>) at util/main-loop.c:518 qemu#23 0x0000557223d13201 in main_loop () at vl.c:1828 qemu#24 0x0000557223bbfb82 in main (argc=<optimized out>, argv=<optimized out>, envp=<optimized out>) at vl.c:4504 RHBZ: https://bugzilla.redhat.com/show_bug.cgi?id=1779036 Signed-off-by: Sergio Lopez <slp@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Coverity reports: *** CID 1419387: Memory - illegal accesses (OVERRUN) /hw/hppa/dino.c: 267 in dino_chip_read_with_attrs() 261 val = s->ilr & s->imr & s->icr; 262 break; 263 case DINO_TOC_ADDR: 264 val = s->toc_addr; 265 break; 266 case DINO_GMASK ... DINO_TLTIM: >>> CID 1419387: Memory - illegal accesses (OVERRUN) >>> Overrunning array "s->reg800" of 12 4-byte elements at element index 12 (byte offset 48) using index "(addr - 2048UL) / 4UL" (which evaluates to 12). 267 val = s->reg800[(addr - DINO_GMASK) / 4]; 268 if (addr == DINO_PAMR) { 269 val &= ~0x01; /* LSB is hardwired to 0 */ 270 } 271 if (addr == DINO_MLTIM) { 272 val &= ~0x07; /* 3 LSB are hardwired to 0 */ *** CID 1419393: Memory - corruptions (OVERRUN) /hw/hppa/dino.c: 363 in dino_chip_write_with_attrs() 357 /* These registers are read-only. */ 358 break; 359 360 case DINO_GMASK ... DINO_TLTIM: 361 i = (addr - DINO_GMASK) / 4; 362 val &= reg800_keep_bits[i]; >>> CID 1419393: Memory - corruptions (OVERRUN) >>> Overrunning array "s->reg800" of 12 4-byte elements at element index 12 (byte offset 48) using index "i" (which evaluates to 12). 363 s->reg800[i] = val; 364 break; 365 366 default: 367 /* Controlled by dino_chip_mem_valid above. */ 368 g_assert_not_reached(); *** CID 1419394: Memory - illegal accesses (OVERRUN) /hw/hppa/dino.c: 362 in dino_chip_write_with_attrs() 356 case DINO_IRR1: 357 /* These registers are read-only. */ 358 break; 359 360 case DINO_GMASK ... DINO_TLTIM: 361 i = (addr - DINO_GMASK) / 4; >>> CID 1419394: Memory - illegal accesses (OVERRUN) >>> Overrunning array "reg800_keep_bits" of 12 4-byte elements at element index 12 (byte offset 48) using index "i" (which evaluates to 12). 362 val &= reg800_keep_bits[i]; 363 s->reg800[i] = val; 364 break; 365 366 default: 367 /* Controlled by dino_chip_mem_valid above. */ Indeed the array should contain 13 entries, the undocumented register 0x82c is missing. Fix by increasing the array size and adding the missing register. CID 1419387 can be verified with: $ echo x 0xfff80830 | hppa-softmmu/qemu-system-hppa -S -monitor stdio -display none QEMU 4.2.50 monitor - type 'help' for more information (qemu) x 0xfff80830 qemu/hw/hppa/dino.c:267:15: runtime error: index 12 out of bounds for type 'uint32_t [12]' SUMMARY: UndefinedBehaviorSanitizer: undefined-behavior /home/phil/source/qemu/hw/hppa/dino.c:267:15 in 00000000fff80830: 0x00000000 and CID 1419393/1419394 with: $ echo writeb 0xfff80830 0x69 \ | hppa-softmmu/qemu-system-hppa -S -accel qtest -qtest stdio -display none [I 1581634452.654113] OPENED [R +4.105415] writeb 0xfff80830 0x69 qemu/hw/hppa/dino.c:362:16: runtime error: index 12 out of bounds for type 'const uint32_t [12]' SUMMARY: UndefinedBehaviorSanitizer: undefined-behavior qemu/hw/hppa/dino.c:362:16 in ================================================================= ==29607==ERROR: AddressSanitizer: global-buffer-overflow on address 0x5577dae32f30 at pc 0x5577d93f2463 bp 0x7ffd97ea11b0 sp 0x7ffd97ea11a8 READ of size 4 at 0x5577dae32f30 thread T0 #0 0x5577d93f2462 in dino_chip_write_with_attrs qemu/hw/hppa/dino.c:362:16 #1 0x5577d9025664 in memory_region_write_with_attrs_accessor qemu/memory.c:503:12 #2 0x5577d9024920 in access_with_adjusted_size qemu/memory.c:539:18 #3 0x5577d9023608 in memory_region_dispatch_write qemu/memory.c:1482:13 qemu#4 0x5577d8e3177a in flatview_write_continue qemu/exec.c:3166:23 qemu#5 0x5577d8e20357 in flatview_write qemu/exec.c:3206:14 qemu#6 0x5577d8e1fef4 in address_space_write qemu/exec.c:3296:18 qemu#7 0x5577d8e20693 in address_space_rw qemu/exec.c:3306:16 qemu#8 0x5577d9011595 in qtest_process_command qemu/qtest.c:432:13 qemu#9 0x5577d900d19f in qtest_process_inbuf qemu/qtest.c:705:9 qemu#10 0x5577d900ca22 in qtest_read qemu/qtest.c:717:5 qemu#11 0x5577da8c4254 in qemu_chr_be_write_impl qemu/chardev/char.c:183:9 qemu#12 0x5577da8c430c in qemu_chr_be_write qemu/chardev/char.c:195:9 qemu#13 0x5577da8cf587 in fd_chr_read qemu/chardev/char-fd.c:68:9 qemu#14 0x5577da9836cd in qio_channel_fd_source_dispatch qemu/io/channel-watch.c:84:12 qemu#15 0x7faf44509ecc in g_main_context_dispatch (/lib64/libglib-2.0.so.0+0x4fecc) qemu#16 0x5577dab75f96 in glib_pollfds_poll qemu/util/main-loop.c:219:9 qemu#17 0x5577dab74797 in os_host_main_loop_wait qemu/util/main-loop.c:242:5 qemu#18 0x5577dab7435a in main_loop_wait qemu/util/main-loop.c:518:11 qemu#19 0x5577d9514eb3 in main_loop qemu/vl.c:1682:9 qemu#20 0x5577d950699d in main qemu/vl.c:4450:5 qemu#21 0x7faf41a87f42 in __libc_start_main (/lib64/libc.so.6+0x23f42) qemu#22 0x5577d8cd4d4d in _start (qemu/build/sanitizer/hppa-softmmu/qemu-system-hppa+0x1256d4d) 0x5577dae32f30 is located 0 bytes to the right of global variable 'reg800_keep_bits' defined in 'qemu/hw/hppa/dino.c:87:23' (0x5577dae32f00) of size 48 SUMMARY: AddressSanitizer: global-buffer-overflow qemu/hw/hppa/dino.c:362:16 in dino_chip_write_with_attrs Shadow bytes around the buggy address: 0x0aaf7b5be590: 00 f9 f9 f9 f9 f9 f9 f9 00 02 f9 f9 f9 f9 f9 f9 0x0aaf7b5be5a0: 07 f9 f9 f9 f9 f9 f9 f9 07 f9 f9 f9 f9 f9 f9 f9 0x0aaf7b5be5b0: 07 f9 f9 f9 f9 f9 f9 f9 00 00 00 00 00 00 00 00 0x0aaf7b5be5c0: 00 00 00 02 f9 f9 f9 f9 00 00 00 00 00 00 00 00 0x0aaf7b5be5d0: 00 00 00 00 00 00 00 00 00 00 00 03 f9 f9 f9 f9 =>0x0aaf7b5be5e0: 00 00 00 00 00 00[f9]f9 f9 f9 f9 f9 00 00 00 00 0x0aaf7b5be5f0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 0x0aaf7b5be600: 00 00 01 f9 f9 f9 f9 f9 00 00 00 00 07 f9 f9 f9 0x0aaf7b5be610: f9 f9 f9 f9 00 00 00 00 00 00 00 00 00 00 00 00 0x0aaf7b5be620: 00 00 00 05 f9 f9 f9 f9 00 00 00 00 07 f9 f9 f9 0x0aaf7b5be630: f9 f9 f9 f9 00 00 f9 f9 f9 f9 f9 f9 07 f9 f9 f9 Shadow byte legend (one shadow byte represents 8 application bytes): Addressable: 00 Partially addressable: 01 02 03 04 05 06 07 Heap left redzone: fa Freed heap region: fd Stack left redzone: f1 Stack mid redzone: f2 Stack right redzone: f3 Stack after return: f5 Stack use after scope: f8 Global redzone: f9 Global init order: f6 Poisoned by user: f7 Container overflow: fc Array cookie: ac Intra object redzone: bb ASan internal: fe Left alloca redzone: ca Right alloca redzone: cb Shadow gap: cc ==29607==ABORTING Fixes: Covertiy CID 1419387 / 1419393 / 1419394 (commit 1809259) Acked-by: Helge Deller <deller@gmx.de> Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-Id: <20200218063355.18577-3-f4bug@amsat.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
There is a use-after-free possible: bdrv_unref_child() leaves bs->backing freed but not NULL. bdrv_attach_child may produce nested polling loop due to drain, than access of freed pointer is possible. I've produced the following crash on 30 iotest with modified code. It does not reproduce on master, but still seems possible: #0 __strcmp_avx2 () at /lib64/libc.so.6 #1 bdrv_backing_overridden (bs=0x55c9d3cc2060) at block.c:6350 #2 bdrv_refresh_filename (bs=0x55c9d3cc2060) at block.c:6404 #3 bdrv_backing_attach (c=0x55c9d48e5520) at block.c:1063 #4 bdrv_replace_child_noperm (child=child@entry=0x55c9d48e5520, new_bs=new_bs@entry=0x55c9d3cc2060) at block.c:2290 #5 bdrv_replace_child (child=child@entry=0x55c9d48e5520, new_bs=new_bs@entry=0x55c9d3cc2060) at block.c:2320 #6 bdrv_root_attach_child (child_bs=child_bs@entry=0x55c9d3cc2060, child_name=child_name@entry=0x55c9d241d478 "backing", child_role=child_role@entry=0x55c9d26ecee0 <child_backing>, ctx=<optimized out>, perm=<optimized out>, shared_perm=21, opaque=0x55c9d3c5a3d0, errp=0x7ffd117108e0) at block.c:2424 #7 bdrv_attach_child (parent_bs=parent_bs@entry=0x55c9d3c5a3d0, child_bs=child_bs@entry=0x55c9d3cc2060, child_name=child_name@entry=0x55c9d241d478 "backing", child_role=child_role@entry=0x55c9d26ecee0 <child_backing>, errp=errp@entry=0x7ffd117108e0) at block.c:5876 #8 in bdrv_set_backing_hd (bs=bs@entry=0x55c9d3c5a3d0, backing_hd=backing_hd@entry=0x55c9d3cc2060, errp=errp@entry=0x7ffd117108e0) at block.c:2576 #9 stream_prepare (job=0x55c9d49d84a0) at block/stream.c:150 #10 job_prepare (job=0x55c9d49d84a0) at job.c:761 #11 job_txn_apply (txn=<optimized out>, fn=<optimized out>) at job.c:145 #12 job_do_finalize (job=0x55c9d49d84a0) at job.c:778 #13 job_completed_txn_success (job=0x55c9d49d84a0) at job.c:832 #14 job_completed (job=0x55c9d49d84a0) at job.c:845 #15 job_completed (job=0x55c9d49d84a0) at job.c:836 #16 job_exit (opaque=0x55c9d49d84a0) at job.c:864 #17 aio_bh_call (bh=0x55c9d471a160) at util/async.c:117 #18 aio_bh_poll (ctx=ctx@entry=0x55c9d3c46720) at util/async.c:117 #19 aio_poll (ctx=ctx@entry=0x55c9d3c46720, blocking=blocking@entry=true) at util/aio-posix.c:728 #20 bdrv_parent_drained_begin_single (poll=true, c=0x55c9d3d558f0) at block/io.c:121 #21 bdrv_parent_drained_begin_single (c=c@entry=0x55c9d3d558f0, poll=poll@entry=true) at block/io.c:114 #22 bdrv_replace_child_noperm (child=child@entry=0x55c9d3d558f0, new_bs=new_bs@entry=0x55c9d3d27300) at block.c:2258 #23 bdrv_replace_child (child=child@entry=0x55c9d3d558f0, new_bs=new_bs@entry=0x55c9d3d27300) at block.c:2320 #24 bdrv_root_attach_child (child_bs=child_bs@entry=0x55c9d3d27300, child_name=child_name@entry=0x55c9d241d478 "backing", child_role=child_role@entry=0x55c9d26ecee0 <child_backing>, ctx=<optimized out>, perm=<optimized out>, shared_perm=21, opaque=0x55c9d3cc2060, errp=0x7ffd11710c60) at block.c:2424 #25 bdrv_attach_child (parent_bs=parent_bs@entry=0x55c9d3cc2060, child_bs=child_bs@entry=0x55c9d3d27300, child_name=child_name@entry=0x55c9d241d478 "backing", child_role=child_role@entry=0x55c9d26ecee0 <child_backing>, errp=errp@entry=0x7ffd11710c60) at block.c:5876 #26 bdrv_set_backing_hd (bs=bs@entry=0x55c9d3cc2060, backing_hd=backing_hd@entry=0x55c9d3d27300, errp=errp@entry=0x7ffd11710c60) at block.c:2576 #27 stream_prepare (job=0x55c9d495ead0) at block/stream.c:150 ... Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Message-Id: <20200316060631.30052-2-vsementsov@virtuozzo.com> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Reviewed-by: John Snow <jsnow@redhat.com> Signed-off-by: Max Reitz <mreitz@redhat.com>
Thank you for your interest in the QEMU project. This repository is a read-only mirror of the project's master QEMU welcomes contributions of code (either fixing bugs or adding new |
Do not force "hypervisor" flag in order to make possible hidding hypervisor. This is needed for running Hyper-V nested in KVM.