On 03/17/2016 04:02 PM, Paolo Bonzini wrote: > > > On 17/03/2016 13:39, Christian Borntraeger wrote: >> As an interesting side note, I updated my system from F20 to F23 some days >> ago >> (after the initial report). While To Bo is still on a F20 system. I was not >> able >> to reproduce the original crash on f23. but going back to F20 made this >> problem re-appear. >> >> Stack trace of thread 26429: >> #0 0x00000000802008aa tracked_request_begin >> (qemu-system-s390x) >> #1 0x0000000080203f3c bdrv_co_do_preadv (qemu-system-s390x) >> #2 0x000000008020567c bdrv_co_do_readv (qemu-system-s390x) >> #3 0x000000008025d0f4 coroutine_trampoline >> (qemu-system-s390x) >> #4 0x000003ff943d150a __makecontext_ret (libc.so.6) >> >> this is with patch 2-4 plus the removal of virtio_queue_host_notifier_read. >> >> Without removing virtio_queue_host_notifier_read, I get the same mutex >> lockup (as expected). >> >> Maybe we have two independent issues here and this is some old bug in glibc >> or >> whatever? > > I'm happy to try and reproduce on x86 if you give me some instruction > (RHEL7 should be close enough to Fedora 20). > > Can you add an assert in virtio_blk_handle_output to catch reentrancy, like
that was quick (let me know if I should recompile with debugging) (gdb) thread apply all bt Thread 5 (Thread 0x3ff7b8ff910 (LWP 236419)): #0 0x000003ff7cdfcf56 in syscall () from /lib64/libc.so.6 #1 0x000000001022452e in futex_wait (val=<optimized out>, ev=<optimized out>) at /home/cborntra/REPOS/qemu/util/qemu-thread-posix.c:292 #2 qemu_event_wait (ev=ev@entry=0x1082b5c4 <rcu_call_ready_event>) at /home/cborntra/REPOS/qemu/util/qemu-thread-posix.c:399 #3 0x000000001023353a in call_rcu_thread (opaque=<optimized out>) at /home/cborntra/REPOS/qemu/util/rcu.c:250 #4 0x000003ff7cf084c6 in start_thread () from /lib64/libpthread.so.0 #5 0x000003ff7ce02ec2 in thread_start () from /lib64/libc.so.6 Thread 4 (Thread 0x3ff78eca910 (LWP 236426)): #0 0x000003ff7cdf819a in ioctl () from /lib64/libc.so.6 #1 0x000000001005ddf8 in kvm_vcpu_ioctl (cpu=cpu@entry=0x10c27d40, type=type@entry=44672) at /home/cborntra/REPOS/qemu/kvm-all.c:1984 #2 0x000000001005df1c in kvm_cpu_exec (cpu=cpu@entry=0x10c27d40) at /home/cborntra/REPOS/qemu/kvm-all.c:1834 #3 0x000000001004b1be in qemu_kvm_cpu_thread_fn (arg=0x10c27d40) at /home/cborntra/REPOS/qemu/cpus.c:1050 #4 0x000003ff7cf084c6 in start_thread () from /lib64/libpthread.so.0 #5 0x000003ff7ce02ec2 in thread_start () from /lib64/libc.so.6 Thread 3 (Thread 0x3ff7e8dcbb0 (LWP 236395)): #0 0x000003ff7cdf66e6 in ppoll () from /lib64/libc.so.6 #1 0x00000000101a5e08 in ppoll (__ss=0x0, __timeout=0x3ffd6afe8a0, __nfds=<optimized out>, __fds=<optimized out>) at /usr/include/bits/poll2.h:77 #2 qemu_poll_ns (fds=<optimized out>, nfds=<optimized out>, timeout=timeout@entry=1034000000) at /home/cborntra/REPOS/qemu/qemu-timer.c:325 #3 0x00000000101a56f2 in os_host_main_loop_wait (timeout=1034000000) at /home/cborntra/REPOS/qemu/main-loop.c:251 #4 main_loop_wait (nonblocking=<optimized out>) at /home/cborntra/REPOS/qemu/main-loop.c:505 #5 0x00000000100136d6 in main_loop () at /home/cborntra/REPOS/qemu/vl.c:1933 #6 main (argc=<optimized out>, argv=<optimized out>, envp=<optimized out>) at /home/cborntra/REPOS/qemu/vl.c:4656 Thread 2 (Thread 0x3ff7b0ff910 (LWP 236421)): #0 0x000003ff7cdf66e6 in ppoll () from /lib64/libc.so.6 #1 0x00000000101a5e28 in ppoll (__ss=0x0, __timeout=0x0, __nfds=<optimized out>, __fds=<optimized out>) at /usr/include/bits/poll2.h:77 #2 qemu_poll_ns (fds=<optimized out>, nfds=<optimized out>, timeout=timeout@entry=-1) at /home/cborntra/REPOS/qemu/qemu-timer.c:313 #3 0x00000000101a727c in aio_poll (ctx=0x10880560, blocking=<optimized out>) at /home/cborntra/REPOS/qemu/aio-posix.c:453 #4 0x00000000100d39f0 in iothread_run (opaque=0x10880020) at /home/cborntra/REPOS/qemu/iothread.c:46 #5 0x000003ff7cf084c6 in start_thread () from /lib64/libpthread.so.0 #6 0x000003ff7ce02ec2 in thread_start () from /lib64/libc.so.6 Thread 1 (Thread 0x3ff57fff910 (LWP 236427)): #0 0x000003ff7cd3b650 in raise () from /lib64/libc.so.6 #1 0x000003ff7cd3ced8 in abort () from /lib64/libc.so.6 #2 0x000003ff7cd33666 in __assert_fail_base () from /lib64/libc.so.6 #3 0x000003ff7cd336f4 in __assert_fail () from /lib64/libc.so.6 #4 0x000000001007a3c4 in virtio_blk_handle_output (vdev=<optimized out>, vq=<optimized out>) at /home/cborntra/REPOS/qemu/hw/block/virtio-blk.c:595 #5 0x000000001009390e in virtio_queue_notify_vq (vq=0x10d77c70) at /home/cborntra/REPOS/qemu/hw/virtio/virtio.c:1095 #6 0x0000000010095894 in virtio_queue_notify_vq (vq=<optimized out>) at /home/cborntra/REPOS/qemu/hw/virtio/virtio.c:1091 #7 virtio_queue_notify (vdev=<optimized out>, n=n@entry=0) at /home/cborntra/REPOS/qemu/hw/virtio/virtio.c:1101 #8 0x00000000100a17c8 in virtio_ccw_hcall_notify (args=<optimized out>) at /home/cborntra/REPOS/qemu/hw/s390x/s390-virtio-ccw.c:66 #9 0x000000001009c210 in s390_virtio_hypercall (env=env@entry=0x10c75aa0) at /home/cborntra/REPOS/qemu/hw/s390x/s390-virtio-hcall.c:35 #10 0x00000000100cb4e8 in handle_hypercall (run=<optimized out>, cpu=0x10c6d7d0) at /home/cborntra/REPOS/qemu/target-s390x/kvm.c:1283 #11 handle_diag (ipb=<optimized out>, run=0x3ff78680000, cpu=0x10c6d7d0) at /home/cborntra/REPOS/qemu/target-s390x/kvm.c:1352 #12 handle_instruction (run=0x3ff78680000, cpu=0x10c6d7d0) at /home/cborntra/REPOS/qemu/target-s390x/kvm.c:1799 #13 handle_intercept (cpu=0x10c6d7d0) at /home/cborntra/REPOS/qemu/target-s390x/kvm.c:1842 #14 kvm_arch_handle_exit (cs=cs@entry=0x10c6d7d0, run=run@entry=0x3ff78680000) at /home/cborntra/REPOS/qemu/target-s390x/kvm.c:2028 #15 0x000000001005df70 in kvm_cpu_exec (cpu=cpu@entry=0x10c6d7d0) at /home/cborntra/REPOS/qemu/kvm-all.c:1921 #16 0x000000001004b1be in qemu_kvm_cpu_thread_fn (arg=0x10c6d7d0) at /home/cborntra/REPOS/qemu/cpus.c:1050 #17 0x000003ff7cf084c6 in start_thread () from /lib64/libpthread.so.0 #18 0x000003ff7ce02ec2 in thread_start () from /lib64/libc.so.6
