diff options
Diffstat (limited to 'results/classifier/001/mistranslation')
| -rw-r--r-- | results/classifier/001/mistranslation/14887122 | 258 | ||||
| -rw-r--r-- | results/classifier/001/mistranslation/22219210 | 43 | ||||
| -rw-r--r-- | results/classifier/001/mistranslation/23270873 | 692 | ||||
| -rw-r--r-- | results/classifier/001/mistranslation/24930826 | 33 | ||||
| -rw-r--r-- | results/classifier/001/mistranslation/25842545 | 202 | ||||
| -rw-r--r-- | results/classifier/001/mistranslation/26430026 | 165 | ||||
| -rw-r--r-- | results/classifier/001/mistranslation/36568044 | 4581 | ||||
| -rw-r--r-- | results/classifier/001/mistranslation/64322995 | 54 | ||||
| -rw-r--r-- | results/classifier/001/mistranslation/70294255 | 1061 | ||||
| -rw-r--r-- | results/classifier/001/mistranslation/71456293 | 1486 | ||||
| -rw-r--r-- | results/classifier/001/mistranslation/74466963 | 1878 | ||||
| -rw-r--r-- | results/classifier/001/mistranslation/74545755 | 344 | ||||
| -rw-r--r-- | results/classifier/001/mistranslation/80604314 | 1480 | ||||
| -rw-r--r-- | results/classifier/001/mistranslation/80615920 | 348 |
14 files changed, 12625 insertions, 0 deletions
diff --git a/results/classifier/001/mistranslation/14887122 b/results/classifier/001/mistranslation/14887122 new file mode 100644 index 000000000..f13db3b86 --- /dev/null +++ b/results/classifier/001/mistranslation/14887122 @@ -0,0 +1,258 @@ +mistranslation: 0.930 +semantic: 0.928 +instruction: 0.905 +other: 0.890 + +[BUG][RFC] CPR transfer Issues: Socket permissions and PID files + +Hello, + +While testing CPR transfer I encountered two issues. The first is that the +transfer fails when running with pidfiles due to the destination qemu process +attempting to create the pidfile while it is still locked by the source +process. The second is that the transfer fails when running with the -run-with +user=$USERID parameter. This is because the destination qemu process creates +the UNIX sockets used for the CPR transfer before dropping to the lower +permissioned user, which causes them to be owned by the original user. The +source qemu process then does not have permission to connect to it because it +is already running as the lesser permissioned user. + +Reproducing the first issue: + +Create a source and destination qemu instance associated with the same VM where +both processes have the -pidfile parameter passed on the command line. You +should see the following error on the command line of the second process: + +qemu-system-x86_64: cannot create PID file: Cannot lock pid file: Resource +temporarily unavailable + +Reproducing the second issue: + +Create a source and destination qemu instance associated with the same VM where +both processes have -run-with user=$USERID passed on the command line, where +$USERID is a different user from the one launching the processes. Then attempt +a CPR transfer using UNIX sockets for the main and cpr sockets. You should +receive the following error via QMP: +{"error": {"class": "GenericError", "desc": "Failed to connect to 'cpr.sock': +Permission denied"}} + +I provided a minimal patch that works around the second issue. + +Thank you, +Ben Chaney + +--- +include/system/os-posix.h | 4 ++++ +os-posix.c | 8 -------- +util/qemu-sockets.c | 21 +++++++++++++++++++++ +3 files changed, 25 insertions(+), 8 deletions(-) + +diff --git a/include/system/os-posix.h b/include/system/os-posix.h +index ce5b3bccf8..2a414a914a 100644 +--- a/include/system/os-posix.h ++++ b/include/system/os-posix.h +@@ -55,6 +55,10 @@ void os_setup_limits(void); +void os_setup_post(void); +int os_mlock(bool on_fault); + ++extern struct passwd *user_pwd; ++extern uid_t user_uid; ++extern gid_t user_gid; ++ +/** +* qemu_alloc_stack: +* @sz: pointer to a size_t holding the requested usable stack size +diff --git a/os-posix.c b/os-posix.c +index 52925c23d3..9369b312a0 100644 +--- a/os-posix.c ++++ b/os-posix.c +@@ -86,14 +86,6 @@ void os_set_proc_name(const char *s) +} + + +-/* +- * Must set all three of these at once. +- * Legal combinations are unset by name by uid +- */ +-static struct passwd *user_pwd; /* NULL non-NULL NULL */ +-static uid_t user_uid = (uid_t)-1; /* -1 -1 >=0 */ +-static gid_t user_gid = (gid_t)-1; /* -1 -1 >=0 */ +- +/* +* Prepare to change user ID. user_id can be one of 3 forms: +* - a username, in which case user ID will be changed to its uid, +diff --git a/util/qemu-sockets.c b/util/qemu-sockets.c +index 77477c1cd5..987977ead9 100644 +--- a/util/qemu-sockets.c ++++ b/util/qemu-sockets.c +@@ -871,6 +871,14 @@ static bool saddr_is_tight(UnixSocketAddress *saddr) +#endif +} + ++/* ++ * Must set all three of these at once. ++ * Legal combinations are unset by name by uid ++ */ ++struct passwd *user_pwd; /* NULL non-NULL NULL */ ++uid_t user_uid = (uid_t)-1; /* -1 -1 >=0 */ ++gid_t user_gid = (gid_t)-1; /* -1 -1 >=0 */ ++ +static int unix_listen_saddr(UnixSocketAddress *saddr, +int num, +Error **errp) +@@ -947,6 +955,19 @@ static int unix_listen_saddr(UnixSocketAddress *saddr, +error_setg_errno(errp, errno, "Failed to bind socket to %s", path); +goto err; +} ++ if (user_pwd) { ++ if (chown(un.sun_path, user_pwd->pw_uid, user_pwd->pw_gid) < 0) { ++ error_setg_errno(errp, errno, "Failed to change permissions on socket %s", +path); ++ goto err; ++ } ++ } ++ else if (user_uid != -1 && user_gid != -1) { ++ if (chown(un.sun_path, user_uid, user_gid) < 0) { ++ error_setg_errno(errp, errno, "Failed to change permissions on socket %s", +path); ++ goto err; ++ } ++ } ++ +if (listen(sock, num) < 0) { +error_setg_errno(errp, errno, "Failed to listen on socket"); +goto err; +-- +2.40.1 + +Thank you Ben. I appreciate you testing CPR and shaking out the bugs. +I will study these and propose patches. + +My initial reaction to the pidfile issue is that the orchestration layer must +pass a different filename when starting the destination qemu instance. When +using live update without containers, these types of resource conflicts in the +global namespaces are a known issue. + +- Steve + +On 3/14/2025 2:33 PM, Chaney, Ben wrote: +Hello, + +While testing CPR transfer I encountered two issues. The first is that the +transfer fails when running with pidfiles due to the destination qemu process +attempting to create the pidfile while it is still locked by the source +process. The second is that the transfer fails when running with the -run-with +user=$USERID parameter. This is because the destination qemu process creates +the UNIX sockets used for the CPR transfer before dropping to the lower +permissioned user, which causes them to be owned by the original user. The +source qemu process then does not have permission to connect to it because it +is already running as the lesser permissioned user. + +Reproducing the first issue: + +Create a source and destination qemu instance associated with the same VM where +both processes have the -pidfile parameter passed on the command line. You +should see the following error on the command line of the second process: + +qemu-system-x86_64: cannot create PID file: Cannot lock pid file: Resource +temporarily unavailable + +Reproducing the second issue: + +Create a source and destination qemu instance associated with the same VM where +both processes have -run-with user=$USERID passed on the command line, where +$USERID is a different user from the one launching the processes. Then attempt +a CPR transfer using UNIX sockets for the main and cpr sockets. You should +receive the following error via QMP: +{"error": {"class": "GenericError", "desc": "Failed to connect to 'cpr.sock': +Permission denied"}} + +I provided a minimal patch that works around the second issue. + +Thank you, +Ben Chaney + +--- +include/system/os-posix.h | 4 ++++ +os-posix.c | 8 -------- +util/qemu-sockets.c | 21 +++++++++++++++++++++ +3 files changed, 25 insertions(+), 8 deletions(-) + +diff --git a/include/system/os-posix.h b/include/system/os-posix.h +index ce5b3bccf8..2a414a914a 100644 +--- a/include/system/os-posix.h ++++ b/include/system/os-posix.h +@@ -55,6 +55,10 @@ void os_setup_limits(void); +void os_setup_post(void); +int os_mlock(bool on_fault); + ++extern struct passwd *user_pwd; ++extern uid_t user_uid; ++extern gid_t user_gid; ++ +/** +* qemu_alloc_stack: +* @sz: pointer to a size_t holding the requested usable stack size +diff --git a/os-posix.c b/os-posix.c +index 52925c23d3..9369b312a0 100644 +--- a/os-posix.c ++++ b/os-posix.c +@@ -86,14 +86,6 @@ void os_set_proc_name(const char *s) +} + + +-/* +- * Must set all three of these at once. +- * Legal combinations are unset by name by uid +- */ +-static struct passwd *user_pwd; /* NULL non-NULL NULL */ +-static uid_t user_uid = (uid_t)-1; /* -1 -1 >=0 */ +-static gid_t user_gid = (gid_t)-1; /* -1 -1 >=0 */ +- +/* +* Prepare to change user ID. user_id can be one of 3 forms: +* - a username, in which case user ID will be changed to its uid, +diff --git a/util/qemu-sockets.c b/util/qemu-sockets.c +index 77477c1cd5..987977ead9 100644 +--- a/util/qemu-sockets.c ++++ b/util/qemu-sockets.c +@@ -871,6 +871,14 @@ static bool saddr_is_tight(UnixSocketAddress *saddr) +#endif +} + ++/* ++ * Must set all three of these at once. ++ * Legal combinations are unset by name by uid ++ */ ++struct passwd *user_pwd; /* NULL non-NULL NULL */ ++uid_t user_uid = (uid_t)-1; /* -1 -1 >=0 */ ++gid_t user_gid = (gid_t)-1; /* -1 -1 >=0 */ ++ +static int unix_listen_saddr(UnixSocketAddress *saddr, +int num, +Error **errp) +@@ -947,6 +955,19 @@ static int unix_listen_saddr(UnixSocketAddress *saddr, +error_setg_errno(errp, errno, "Failed to bind socket to %s", path); +goto err; +} ++ if (user_pwd) { ++ if (chown(un.sun_path, user_pwd->pw_uid, user_pwd->pw_gid) < 0) { ++ error_setg_errno(errp, errno, "Failed to change permissions on socket %s", +path); ++ goto err; ++ } ++ } ++ else if (user_uid != -1 && user_gid != -1) { ++ if (chown(un.sun_path, user_uid, user_gid) < 0) { ++ error_setg_errno(errp, errno, "Failed to change permissions on socket %s", +path); ++ goto err; ++ } ++ } ++ +if (listen(sock, num) < 0) { +error_setg_errno(errp, errno, "Failed to listen on socket"); +goto err; +-- +2.40.1 + diff --git a/results/classifier/001/mistranslation/22219210 b/results/classifier/001/mistranslation/22219210 new file mode 100644 index 000000000..95c3f61d1 --- /dev/null +++ b/results/classifier/001/mistranslation/22219210 @@ -0,0 +1,43 @@ +mistranslation: 0.472 +semantic: 0.387 +other: 0.345 +instruction: 0.261 + +[BUG][CPU hot-plug]CPU hot-plugs cause the qemu process to coredump + +Hello,Recently, when I was developing CPU hot-plugs under the loongarch +architecture, +I found that there was a problem with qemu cpu hot-plugs under x86 +architecture, +which caused the qemu process coredump when repeatedly inserting and +unplugging +the CPU when the TCG was accelerated. + + +The specific operation process is as follows: + +1.Use the following command to start the virtual machine + +qemu-system-x86_64 \ +-machine q35 \ +-cpu Broadwell-IBRS \ +-smp 1,maxcpus=4,sockets=4,cores=1,threads=1 \ +-m 4G \ +-drive file=~/anolis-8.8.qcow2 \ +-serial stdio  \ +-monitor telnet:localhost:4498,server,nowait + + +2.Enter QEMU Monitor via telnet for repeated CPU insertion and unplugging + +telnet 127.0.0.1 4498 +(qemu) device_add +Broadwell-IBRS-x86_64-cpu,socket-id=1,core-id=0,thread-id=0,id=cpu1 +(qemu) device_del cpu1 +(qemu) device_add +Broadwell-IBRS-x86_64-cpu,socket-id=1,core-id=0,thread-id=0,id=cpu1 +3.You will notice that the QEMU process has a coredump + +# malloc(): unsorted double linked list corrupted +Aborted (core dumped) + diff --git a/results/classifier/001/mistranslation/23270873 b/results/classifier/001/mistranslation/23270873 new file mode 100644 index 000000000..e4d4789c4 --- /dev/null +++ b/results/classifier/001/mistranslation/23270873 @@ -0,0 +1,692 @@ +mistranslation: 0.881 +other: 0.839 +instruction: 0.755 +semantic: 0.752 + +[Qemu-devel] [BUG?] aio_get_linux_aio: Assertion `ctx->linux_aio' failed + +Hi, + +I am seeing some strange QEMU assertion failures for qemu on s390x, +which prevents a guest from starting. + +Git bisecting points to the following commit as the source of the error. + +commit ed6e2161715c527330f936d44af4c547f25f687e +Author: Nishanth Aravamudan <address@hidden> +Date: Fri Jun 22 12:37:00 2018 -0700 + + linux-aio: properly bubble up errors from initialization + + laio_init() can fail for a couple of reasons, which will lead to a NULL + pointer dereference in laio_attach_aio_context(). + + To solve this, add a aio_setup_linux_aio() function which is called + early in raw_open_common. If this fails, propagate the error up. The + signature of aio_get_linux_aio() was not modified, because it seems + preferable to return the actual errno from the possible failing + initialization calls. + + Additionally, when the AioContext changes, we need to associate a + LinuxAioState with the new AioContext. Use the bdrv_attach_aio_context + callback and call the new aio_setup_linux_aio(), which will allocate a +new AioContext if needed, and return errors on failures. If it +fails for +any reason, fallback to threaded AIO with an error message, as the + device is already in-use by the guest. + + Add an assert that aio_get_linux_aio() cannot return NULL. + + Signed-off-by: Nishanth Aravamudan <address@hidden> + Message-id: address@hidden + Signed-off-by: Stefan Hajnoczi <address@hidden> +Not sure what is causing this assertion to fail. Here is the qemu +command line of the guest, from qemu log, which throws this error: +LC_ALL=C PATH=/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin +QEMU_AUDIO_DRV=none /usr/local/bin/qemu-system-s390x -name +guest=rt_vm1,debug-threads=on -S -object +secret,id=masterKey0,format=raw,file=/var/lib/libvirt/qemu/domain-21-rt_vm1/master-key.aes +-machine s390-ccw-virtio-2.12,accel=kvm,usb=off,dump-guest-core=off -m +1024 -realtime mlock=off -smp 4,sockets=4,cores=1,threads=1 -object +iothread,id=iothread1 -uuid 0cde16cd-091d-41bd-9ac2-5243df5c9a0d +-display none -no-user-config -nodefaults -chardev +socket,id=charmonitor,fd=28,server,nowait -mon +chardev=charmonitor,id=monitor,mode=control -rtc base=utc -no-shutdown +-boot strict=on -drive +file=/dev/mapper/360050763998b0883980000002a000031,format=raw,if=none,id=drive-virtio-disk0,cache=none,aio=native +-device +virtio-blk-ccw,iothread=iothread1,scsi=off,devno=fe.0.0001,drive=drive-virtio-disk0,id=virtio-disk0,bootindex=1,write-cache=on +-netdev tap,fd=30,id=hostnet0,vhost=on,vhostfd=31 -device +virtio-net-ccw,netdev=hostnet0,id=net0,mac=02:3a:c8:67:95:84,devno=fe.0.0000 +-netdev tap,fd=32,id=hostnet1,vhost=on,vhostfd=33 -device +virtio-net-ccw,netdev=hostnet1,id=net1,mac=52:54:00:2a:e5:08,devno=fe.0.0002 +-chardev pty,id=charconsole0 -device +sclpconsole,chardev=charconsole0,id=console0 -device +virtio-balloon-ccw,id=balloon0,devno=fe.3.ffba -sandbox +on,obsolete=deny,elevateprivileges=deny,spawn=deny,resourcecontrol=deny +-msg timestamp=on +2018-07-17 15:48:42.252+0000: Domain id=21 is tainted: high-privileges +2018-07-17T15:48:42.279380Z qemu-system-s390x: -chardev +pty,id=charconsole0: char device redirected to /dev/pts/3 (label +charconsole0) +qemu-system-s390x: util/async.c:339: aio_get_linux_aio: Assertion +`ctx->linux_aio' failed. +2018-07-17 15:48:43.309+0000: shutting down, reason=failed + + +Any help debugging this would be greatly appreciated. + +Thank you +Farhan + +On 17.07.2018 [13:25:53 -0400], Farhan Ali wrote: +> +Hi, +> +> +I am seeing some strange QEMU assertion failures for qemu on s390x, +> +which prevents a guest from starting. +> +> +Git bisecting points to the following commit as the source of the error. +> +> +commit ed6e2161715c527330f936d44af4c547f25f687e +> +Author: Nishanth Aravamudan <address@hidden> +> +Date: Fri Jun 22 12:37:00 2018 -0700 +> +> +linux-aio: properly bubble up errors from initialization +> +> +laio_init() can fail for a couple of reasons, which will lead to a NULL +> +pointer dereference in laio_attach_aio_context(). +> +> +To solve this, add a aio_setup_linux_aio() function which is called +> +early in raw_open_common. If this fails, propagate the error up. The +> +signature of aio_get_linux_aio() was not modified, because it seems +> +preferable to return the actual errno from the possible failing +> +initialization calls. +> +> +Additionally, when the AioContext changes, we need to associate a +> +LinuxAioState with the new AioContext. Use the bdrv_attach_aio_context +> +callback and call the new aio_setup_linux_aio(), which will allocate a +> +new AioContext if needed, and return errors on failures. If it fails for +> +any reason, fallback to threaded AIO with an error message, as the +> +device is already in-use by the guest. +> +> +Add an assert that aio_get_linux_aio() cannot return NULL. +> +> +Signed-off-by: Nishanth Aravamudan <address@hidden> +> +Message-id: address@hidden +> +Signed-off-by: Stefan Hajnoczi <address@hidden> +> +> +> +Not sure what is causing this assertion to fail. Here is the qemu command +> +line of the guest, from qemu log, which throws this error: +> +> +> +LC_ALL=C PATH=/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin +> +QEMU_AUDIO_DRV=none /usr/local/bin/qemu-system-s390x -name +> +guest=rt_vm1,debug-threads=on -S -object +> +secret,id=masterKey0,format=raw,file=/var/lib/libvirt/qemu/domain-21-rt_vm1/master-key.aes +> +-machine s390-ccw-virtio-2.12,accel=kvm,usb=off,dump-guest-core=off -m 1024 +> +-realtime mlock=off -smp 4,sockets=4,cores=1,threads=1 -object +> +iothread,id=iothread1 -uuid 0cde16cd-091d-41bd-9ac2-5243df5c9a0d -display +> +none -no-user-config -nodefaults -chardev +> +socket,id=charmonitor,fd=28,server,nowait -mon +> +chardev=charmonitor,id=monitor,mode=control -rtc base=utc -no-shutdown -boot +> +strict=on -drive +> +file=/dev/mapper/360050763998b0883980000002a000031,format=raw,if=none,id=drive-virtio-disk0,cache=none,aio=native +> +-device +> +virtio-blk-ccw,iothread=iothread1,scsi=off,devno=fe.0.0001,drive=drive-virtio-disk0,id=virtio-disk0,bootindex=1,write-cache=on +> +-netdev tap,fd=30,id=hostnet0,vhost=on,vhostfd=31 -device +> +virtio-net-ccw,netdev=hostnet0,id=net0,mac=02:3a:c8:67:95:84,devno=fe.0.0000 +> +-netdev tap,fd=32,id=hostnet1,vhost=on,vhostfd=33 -device +> +virtio-net-ccw,netdev=hostnet1,id=net1,mac=52:54:00:2a:e5:08,devno=fe.0.0002 +> +-chardev pty,id=charconsole0 -device +> +sclpconsole,chardev=charconsole0,id=console0 -device +> +virtio-balloon-ccw,id=balloon0,devno=fe.3.ffba -sandbox +> +on,obsolete=deny,elevateprivileges=deny,spawn=deny,resourcecontrol=deny -msg +> +timestamp=on +> +> +> +> +2018-07-17 15:48:42.252+0000: Domain id=21 is tainted: high-privileges +> +2018-07-17T15:48:42.279380Z qemu-system-s390x: -chardev pty,id=charconsole0: +> +char device redirected to /dev/pts/3 (label charconsole0) +> +qemu-system-s390x: util/async.c:339: aio_get_linux_aio: Assertion +> +`ctx->linux_aio' failed. +> +2018-07-17 15:48:43.309+0000: shutting down, reason=failed +> +> +> +Any help debugging this would be greatly appreciated. +iiuc, this possibly implies AIO was not actually used previously on this +guest (it might have silently been falling back to threaded IO?). I +don't have access to s390x, but would it be possible to run qemu under +gdb and see if aio_setup_linux_aio is being called at all (I think it +might not be, but I'm not sure why), and if so, if it's for the context +in question? + +If it's not being called first, could you see what callpath is calling +aio_get_linux_aio when this assertion trips? + +Thanks! +-Nish + +On 07/17/2018 04:52 PM, Nishanth Aravamudan wrote: +iiuc, this possibly implies AIO was not actually used previously on this +guest (it might have silently been falling back to threaded IO?). I +don't have access to s390x, but would it be possible to run qemu under +gdb and see if aio_setup_linux_aio is being called at all (I think it +might not be, but I'm not sure why), and if so, if it's for the context +in question? + +If it's not being called first, could you see what callpath is calling +aio_get_linux_aio when this assertion trips? + +Thanks! +-Nish +Hi Nishant, +From the coredump of the guest this is the call trace that calls +aio_get_linux_aio: +Stack trace of thread 145158: +#0 0x000003ff94dbe274 raise (libc.so.6) +#1 0x000003ff94da39a8 abort (libc.so.6) +#2 0x000003ff94db62ce __assert_fail_base (libc.so.6) +#3 0x000003ff94db634c __assert_fail (libc.so.6) +#4 0x000002aa20db067a aio_get_linux_aio (qemu-system-s390x) +#5 0x000002aa20d229a8 raw_aio_plug (qemu-system-s390x) +#6 0x000002aa20d309ee bdrv_io_plug (qemu-system-s390x) +#7 0x000002aa20b5a8ea virtio_blk_handle_vq (qemu-system-s390x) +#8 0x000002aa20db2f6e aio_dispatch_handlers (qemu-system-s390x) +#9 0x000002aa20db3c34 aio_poll (qemu-system-s390x) +#10 0x000002aa20be32a2 iothread_run (qemu-system-s390x) +#11 0x000003ff94f879a8 start_thread (libpthread.so.0) +#12 0x000003ff94e797ee thread_start (libc.so.6) + + +Thanks for taking a look and responding. + +Thanks +Farhan + +On 07/18/2018 09:42 AM, Farhan Ali wrote: +On 07/17/2018 04:52 PM, Nishanth Aravamudan wrote: +iiuc, this possibly implies AIO was not actually used previously on this +guest (it might have silently been falling back to threaded IO?). I +don't have access to s390x, but would it be possible to run qemu under +gdb and see if aio_setup_linux_aio is being called at all (I think it +might not be, but I'm not sure why), and if so, if it's for the context +in question? + +If it's not being called first, could you see what callpath is calling +aio_get_linux_aio when this assertion trips? + +Thanks! +-Nish +Hi Nishant, +From the coredump of the guest this is the call trace that calls +aio_get_linux_aio: +Stack trace of thread 145158: +#0 0x000003ff94dbe274 raise (libc.so.6) +#1 0x000003ff94da39a8 abort (libc.so.6) +#2 0x000003ff94db62ce __assert_fail_base (libc.so.6) +#3 0x000003ff94db634c __assert_fail (libc.so.6) +#4 0x000002aa20db067a aio_get_linux_aio (qemu-system-s390x) +#5 0x000002aa20d229a8 raw_aio_plug (qemu-system-s390x) +#6 0x000002aa20d309ee bdrv_io_plug (qemu-system-s390x) +#7 0x000002aa20b5a8ea virtio_blk_handle_vq (qemu-system-s390x) +#8 0x000002aa20db2f6e aio_dispatch_handlers (qemu-system-s390x) +#9 0x000002aa20db3c34 aio_poll (qemu-system-s390x) +#10 0x000002aa20be32a2 iothread_run (qemu-system-s390x) +#11 0x000003ff94f879a8 start_thread (libpthread.so.0) +#12 0x000003ff94e797ee thread_start (libc.so.6) + + +Thanks for taking a look and responding. + +Thanks +Farhan +Trying to debug a little further, the block device in this case is a +"host device". And looking at your commit carefully you use the +bdrv_attach_aio_context callback to setup a Linux AioContext. +For some reason the "host device" struct (BlockDriver bdrv_host_device +in block/file-posix.c) does not have a bdrv_attach_aio_context defined. +So a simple change of adding the callback to the struct solves the issue +and the guest starts fine. +diff --git a/block/file-posix.c b/block/file-posix.c +index 28824aa..b8d59fb 100644 +--- a/block/file-posix.c ++++ b/block/file-posix.c +@@ -3135,6 +3135,7 @@ static BlockDriver bdrv_host_device = { + .bdrv_refresh_limits = raw_refresh_limits, + .bdrv_io_plug = raw_aio_plug, + .bdrv_io_unplug = raw_aio_unplug, ++ .bdrv_attach_aio_context = raw_aio_attach_aio_context, + + .bdrv_co_truncate = raw_co_truncate, + .bdrv_getlength = raw_getlength, +I am not too familiar with block device code in QEMU, so not sure if +this is the right fix or if there are some underlying problems. +Thanks +Farhan + +On 18.07.2018 [11:10:27 -0400], Farhan Ali wrote: +> +> +> +On 07/18/2018 09:42 AM, Farhan Ali wrote: +> +> +> +> +> +> On 07/17/2018 04:52 PM, Nishanth Aravamudan wrote: +> +> > iiuc, this possibly implies AIO was not actually used previously on this +> +> > guest (it might have silently been falling back to threaded IO?). I +> +> > don't have access to s390x, but would it be possible to run qemu under +> +> > gdb and see if aio_setup_linux_aio is being called at all (I think it +> +> > might not be, but I'm not sure why), and if so, if it's for the context +> +> > in question? +> +> > +> +> > If it's not being called first, could you see what callpath is calling +> +> > aio_get_linux_aio when this assertion trips? +> +> > +> +> > Thanks! +> +> > -Nish +> +> +> +> +> +> Hi Nishant, +> +> +> +> From the coredump of the guest this is the call trace that calls +> +> aio_get_linux_aio: +> +> +> +> +> +> Stack trace of thread 145158: +> +> #0 0x000003ff94dbe274 raise (libc.so.6) +> +> #1 0x000003ff94da39a8 abort (libc.so.6) +> +> #2 0x000003ff94db62ce __assert_fail_base (libc.so.6) +> +> #3 0x000003ff94db634c __assert_fail (libc.so.6) +> +> #4 0x000002aa20db067a aio_get_linux_aio (qemu-system-s390x) +> +> #5 0x000002aa20d229a8 raw_aio_plug (qemu-system-s390x) +> +> #6 0x000002aa20d309ee bdrv_io_plug (qemu-system-s390x) +> +> #7 0x000002aa20b5a8ea virtio_blk_handle_vq (qemu-system-s390x) +> +> #8 0x000002aa20db2f6e aio_dispatch_handlers (qemu-system-s390x) +> +> #9 0x000002aa20db3c34 aio_poll (qemu-system-s390x) +> +> #10 0x000002aa20be32a2 iothread_run (qemu-system-s390x) +> +> #11 0x000003ff94f879a8 start_thread (libpthread.so.0) +> +> #12 0x000003ff94e797ee thread_start (libc.so.6) +> +> +> +> +> +> Thanks for taking a look and responding. +> +> +> +> Thanks +> +> Farhan +> +> +> +> +> +> +> +> +Trying to debug a little further, the block device in this case is a "host +> +device". And looking at your commit carefully you use the +> +bdrv_attach_aio_context callback to setup a Linux AioContext. +> +> +For some reason the "host device" struct (BlockDriver bdrv_host_device in +> +block/file-posix.c) does not have a bdrv_attach_aio_context defined. +> +So a simple change of adding the callback to the struct solves the issue and +> +the guest starts fine. +> +> +> +diff --git a/block/file-posix.c b/block/file-posix.c +> +index 28824aa..b8d59fb 100644 +> +--- a/block/file-posix.c +> ++++ b/block/file-posix.c +> +@@ -3135,6 +3135,7 @@ static BlockDriver bdrv_host_device = { +> +.bdrv_refresh_limits = raw_refresh_limits, +> +.bdrv_io_plug = raw_aio_plug, +> +.bdrv_io_unplug = raw_aio_unplug, +> ++ .bdrv_attach_aio_context = raw_aio_attach_aio_context, +> +> +.bdrv_co_truncate = raw_co_truncate, +> +.bdrv_getlength = raw_getlength, +> +> +> +> +I am not too familiar with block device code in QEMU, so not sure if +> +this is the right fix or if there are some underlying problems. +Oh this is quite embarassing! I only added the bdrv_attach_aio_context +callback for the file-backed device. Your fix is definitely corect for +host device. Let me make sure there weren't any others missed and I will +send out a properly formatted patch. Thank you for the quick testing and +turnaround! + +-Nish + +On 07/18/2018 08:52 PM, Nishanth Aravamudan wrote: +> +On 18.07.2018 [11:10:27 -0400], Farhan Ali wrote: +> +> +> +> +> +> On 07/18/2018 09:42 AM, Farhan Ali wrote: +> +>> +> +>> +> +>> On 07/17/2018 04:52 PM, Nishanth Aravamudan wrote: +> +>>> iiuc, this possibly implies AIO was not actually used previously on this +> +>>> guest (it might have silently been falling back to threaded IO?). I +> +>>> don't have access to s390x, but would it be possible to run qemu under +> +>>> gdb and see if aio_setup_linux_aio is being called at all (I think it +> +>>> might not be, but I'm not sure why), and if so, if it's for the context +> +>>> in question? +> +>>> +> +>>> If it's not being called first, could you see what callpath is calling +> +>>> aio_get_linux_aio when this assertion trips? +> +>>> +> +>>> Thanks! +> +>>> -Nish +> +>> +> +>> +> +>> Hi Nishant, +> +>> +> +>> From the coredump of the guest this is the call trace that calls +> +>> aio_get_linux_aio: +> +>> +> +>> +> +>> Stack trace of thread 145158: +> +>> #0 0x000003ff94dbe274 raise (libc.so.6) +> +>> #1 0x000003ff94da39a8 abort (libc.so.6) +> +>> #2 0x000003ff94db62ce __assert_fail_base (libc.so.6) +> +>> #3 0x000003ff94db634c __assert_fail (libc.so.6) +> +>> #4 0x000002aa20db067a aio_get_linux_aio (qemu-system-s390x) +> +>> #5 0x000002aa20d229a8 raw_aio_plug (qemu-system-s390x) +> +>> #6 0x000002aa20d309ee bdrv_io_plug (qemu-system-s390x) +> +>> #7 0x000002aa20b5a8ea virtio_blk_handle_vq (qemu-system-s390x) +> +>> #8 0x000002aa20db2f6e aio_dispatch_handlers (qemu-system-s390x) +> +>> #9 0x000002aa20db3c34 aio_poll (qemu-system-s390x) +> +>> #10 0x000002aa20be32a2 iothread_run (qemu-system-s390x) +> +>> #11 0x000003ff94f879a8 start_thread (libpthread.so.0) +> +>> #12 0x000003ff94e797ee thread_start (libc.so.6) +> +>> +> +>> +> +>> Thanks for taking a look and responding. +> +>> +> +>> Thanks +> +>> Farhan +> +>> +> +>> +> +>> +> +> +> +> Trying to debug a little further, the block device in this case is a "host +> +> device". And looking at your commit carefully you use the +> +> bdrv_attach_aio_context callback to setup a Linux AioContext. +> +> +> +> For some reason the "host device" struct (BlockDriver bdrv_host_device in +> +> block/file-posix.c) does not have a bdrv_attach_aio_context defined. +> +> So a simple change of adding the callback to the struct solves the issue and +> +> the guest starts fine. +> +> +> +> +> +> diff --git a/block/file-posix.c b/block/file-posix.c +> +> index 28824aa..b8d59fb 100644 +> +> --- a/block/file-posix.c +> +> +++ b/block/file-posix.c +> +> @@ -3135,6 +3135,7 @@ static BlockDriver bdrv_host_device = { +> +> .bdrv_refresh_limits = raw_refresh_limits, +> +> .bdrv_io_plug = raw_aio_plug, +> +> .bdrv_io_unplug = raw_aio_unplug, +> +> + .bdrv_attach_aio_context = raw_aio_attach_aio_context, +> +> +> +> .bdrv_co_truncate = raw_co_truncate, +> +> .bdrv_getlength = raw_getlength, +> +> +> +> +> +> +> +> I am not too familiar with block device code in QEMU, so not sure if +> +> this is the right fix or if there are some underlying problems. +> +> +Oh this is quite embarassing! I only added the bdrv_attach_aio_context +> +callback for the file-backed device. Your fix is definitely corect for +> +host device. Let me make sure there weren't any others missed and I will +> +send out a properly formatted patch. Thank you for the quick testing and +> +turnaround! +Farhan, can you respin your patch with proper sign-off and patch description? +Adding qemu-block. + +Hi Christian, + +On 19.07.2018 [08:55:20 +0200], Christian Borntraeger wrote: +> +> +> +On 07/18/2018 08:52 PM, Nishanth Aravamudan wrote: +> +> On 18.07.2018 [11:10:27 -0400], Farhan Ali wrote: +> +>> +> +>> +> +>> On 07/18/2018 09:42 AM, Farhan Ali wrote: +<snip> + +> +>> I am not too familiar with block device code in QEMU, so not sure if +> +>> this is the right fix or if there are some underlying problems. +> +> +> +> Oh this is quite embarassing! I only added the bdrv_attach_aio_context +> +> callback for the file-backed device. Your fix is definitely corect for +> +> host device. Let me make sure there weren't any others missed and I will +> +> send out a properly formatted patch. Thank you for the quick testing and +> +> turnaround! +> +> +Farhan, can you respin your patch with proper sign-off and patch description? +> +Adding qemu-block. +I sent it yesterday, sorry I didn't cc everyone from this e-mail: +http://lists.nongnu.org/archive/html/qemu-block/2018-07/msg00516.html +Thanks, +Nish + diff --git a/results/classifier/001/mistranslation/24930826 b/results/classifier/001/mistranslation/24930826 new file mode 100644 index 000000000..5f79c452f --- /dev/null +++ b/results/classifier/001/mistranslation/24930826 @@ -0,0 +1,33 @@ +mistranslation: 0.637 +instruction: 0.555 +other: 0.535 +semantic: 0.487 + +[Qemu-devel] [BUG] vhost-user: hot-unplug vhost-user nic for windows guest OS will fail with 100% reproduce rate + +Hi, guys + +I met a problem when hot-unplug vhost-user nic for Windows 2008 rc2 sp1 64 +(Guest OS) + +The xml of nic is as followed: +<interface type='vhostuser'> + <mac address='52:54:00:3b:83:aa'/> + <source type='unix' path='/var/run/vhost-user/port1' mode='client'/> + <target dev='port1'/> + <model type='virtio'/> + <driver queues='4'/> + <address type='pci' domain='0x0000' bus='0x00' slot='0x08' function='0x0'/> +</interface> + +Firstly, I use virsh attach-device win2008 vif.xml to hot-plug a nic for Guest +OS. This operation returns success. +After guest OS discover nic successfully, I use virsh detach-device win2008 +vif.xml to hot-unplug it. This operation will fail with 100% reproduce rate. + +However, if I hot-plug and hot-unplug virtio-net nic , it will not fail. + +I have analysis the process of qmp_device_del , I found that qemu have inject +interrupt to acpi to let it notice guest OS to remove nic. +I guess there is something wrong in Windows when handle the interrupt. + diff --git a/results/classifier/001/mistranslation/25842545 b/results/classifier/001/mistranslation/25842545 new file mode 100644 index 000000000..1ebfe2889 --- /dev/null +++ b/results/classifier/001/mistranslation/25842545 @@ -0,0 +1,202 @@ +mistranslation: 0.928 +other: 0.912 +instruction: 0.835 +semantic: 0.829 + +[Qemu-devel] [Bug?] Guest pause because VMPTRLD failed in KVM + +Hello, + + We encountered a problem that a guest paused because the KMOD report VMPTRLD +failed. + +The related information is as follows: + +1) Qemu command: + /usr/bin/qemu-kvm -name omu1 -S -machine pc-i440fx-2.3,accel=kvm,usb=off -cpu +host -m 15625 -realtime mlock=off -smp 8,sockets=1,cores=8,threads=1 -uuid +a2aacfff-6583-48b4-b6a4-e6830e519931 -no-user-config -nodefaults -chardev +socket,id=charmonitor,path=/var/lib/libvirt/qemu/omu1.monitor,server,nowait +-mon chardev=charmonitor,id=monitor,mode=control -rtc base=utc -no-shutdown +-boot strict=on -device piix3-usb-uhci,id=usb,bus=pci.0,addr=0x1.0x2 -device +virtio-serial-pci,id=virtio-serial0,bus=pci.0,addr=0x5 -drive +file=/home/env/guest1.qcow2,if=none,id=drive-virtio-disk0,format=qcow2,cache=none,aio=native + -device +virtio-blk-pci,scsi=off,bus=pci.0,addr=0x6,drive=drive-virtio-disk0,id=virtio-disk0 + -drive +file=/home/env/guest_300G.img,if=none,id=drive-virtio-disk1,format=raw,cache=none,aio=native + -device +virtio-blk-pci,scsi=off,bus=pci.0,addr=0x7,drive=drive-virtio-disk1,id=virtio-disk1 + -netdev tap,fd=25,id=hostnet0,vhost=on,vhostfd=26 -device +virtio-net-pci,netdev=hostnet0,id=net0,mac=00:00:80:05:00:00,bus=pci.0,addr=0x3 +-netdev tap,fd=27,id=hostnet1,vhost=on,vhostfd=28 -device +virtio-net-pci,netdev=hostnet1,id=net1,mac=00:00:80:05:00:01,bus=pci.0,addr=0x4 +-chardev pty,id=charserial0 -device isa-serial,chardev=charserial0,id=serial0 +-device usb-tablet,id=input0 -vnc 0.0.0.0:0 -device +cirrus-vga,id=video0,vgamem_mb=16,bus=pci.0,addr=0x2 -device +virtio-balloon-pci,id=balloon0,bus=pci.0,addr=0x8 -msg timestamp=on + + 2) Qemu log: + KVM: entry failed, hardware error 0x4 + RAX=00000000ffffffed RBX=ffff8803fa2d7fd8 RCX=0100000000000000 +RDX=0000000000000000 + RSI=0000000000000000 RDI=0000000000000046 RBP=ffff8803fa2d7e90 +RSP=ffff8803fa2efe90 + R8 =0000000000000000 R9 =0000000000000000 R10=0000000000000000 +R11=000000000000b69a + R12=0000000000000001 R13=ffffffff81a25b40 R14=0000000000000000 +R15=ffff8803fa2d7fd8 + RIP=ffffffff81053e16 RFL=00000286 [--S--P-] CPL=0 II=0 A20=1 SMM=0 HLT=0 + ES =0000 0000000000000000 ffffffff 00c00000 + CS =0010 0000000000000000 ffffffff 00a09b00 DPL=0 CS64 [-RA] + SS =0018 0000000000000000 ffffffff 00c09300 DPL=0 DS [-WA] + DS =0000 0000000000000000 ffffffff 00c00000 + FS =0000 0000000000000000 ffffffff 00c00000 + GS =0000 ffff88040f540000 ffffffff 00c00000 + LDT=0000 0000000000000000 ffffffff 00c00000 + TR =0040 ffff88040f550a40 00002087 00008b00 DPL=0 TSS64-busy + GDT= ffff88040f549000 0000007f + IDT= ffffffffff529000 00000fff + CR0=80050033 CR2=00007f81ca0c5000 CR3=00000003f5081000 CR4=000407e0 + DR0=0000000000000000 DR1=0000000000000000 DR2=0000000000000000 +DR3=0000000000000000 + DR6=00000000ffff0ff0 DR7=0000000000000400 + EFER=0000000000000d01 + Code=?? ?? ?? ?? ?? ?? ?? ?? ?? ?? ?? ?? ?? ?? ?? ?? ?? ?? ?? ?? <??> ?? ?? +?? ?? ?? ?? ?? ?? ?? ?? ?? ?? ?? ?? ?? ?? ?? ?? ?? ?? ?? ?? ?? ?? ?? ?? ?? ?? ?? + + 3) Demsg + [347315.028339] kvm: vmptrld ffff8817ec5f0000/17ec5f0000 failed + klogd 1.4.1, ---------- state change ---------- + [347315.039506] kvm: vmptrld ffff8817ec5f0000/17ec5f0000 failed + [347315.051728] kvm: vmptrld ffff8817ec5f0000/17ec5f0000 failed + [347315.057472] vmwrite error: reg 6c0a value ffff88307e66e480 (err +2120672384) + [347315.064567] Pid: 69523, comm: qemu-kvm Tainted: GF X +3.0.93-0.8-default #1 + [347315.064569] Call Trace: + [347315.064587] [<ffffffff810049d5>] dump_trace+0x75/0x300 + [347315.064595] [<ffffffff8145e3e3>] dump_stack+0x69/0x6f + [347315.064617] [<ffffffffa03738de>] vmx_vcpu_load+0x11e/0x1d0 [kvm_intel] + [347315.064647] [<ffffffffa029a204>] kvm_arch_vcpu_load+0x44/0x1d0 [kvm] + [347315.064669] [<ffffffff81054ee1>] finish_task_switch+0x81/0xe0 + [347315.064676] [<ffffffff8145f0b4>] thread_return+0x3b/0x2a7 + [347315.064687] [<ffffffffa028d9b5>] kvm_vcpu_block+0x65/0xa0 [kvm] + [347315.064703] [<ffffffffa02a16d1>] __vcpu_run+0xd1/0x260 [kvm] + [347315.064732] [<ffffffffa02a2418>] kvm_arch_vcpu_ioctl_run+0x68/0x1a0 +[kvm] + [347315.064759] [<ffffffffa028ecee>] kvm_vcpu_ioctl+0x38e/0x580 [kvm] + [347315.064771] [<ffffffff8116bdfb>] do_vfs_ioctl+0x8b/0x3b0 + [347315.064776] [<ffffffff8116c1c1>] sys_ioctl+0xa1/0xb0 + [347315.064783] [<ffffffff81469272>] system_call_fastpath+0x16/0x1b + [347315.064797] [<00007fee51969ce7>] 0x7fee51969ce6 + [347315.064799] vmwrite error: reg 6c0c value ffff88307e664000 (err +2120630272) + [347315.064802] Pid: 69523, comm: qemu-kvm Tainted: GF X +3.0.93-0.8-default #1 + [347315.064803] Call Trace: + [347315.064807] [<ffffffff810049d5>] dump_trace+0x75/0x300 + [347315.064811] [<ffffffff8145e3e3>] dump_stack+0x69/0x6f + [347315.064817] [<ffffffffa03738ec>] vmx_vcpu_load+0x12c/0x1d0 [kvm_intel] + [347315.064832] [<ffffffffa029a204>] kvm_arch_vcpu_load+0x44/0x1d0 [kvm] + [347315.064851] [<ffffffff81054ee1>] finish_task_switch+0x81/0xe0 + [347315.064855] [<ffffffff8145f0b4>] thread_return+0x3b/0x2a7 + [347315.064865] [<ffffffffa028d9b5>] kvm_vcpu_block+0x65/0xa0 [kvm] + [347315.064880] [<ffffffffa02a16d1>] __vcpu_run+0xd1/0x260 [kvm] + [347315.064907] [<ffffffffa02a2418>] kvm_arch_vcpu_ioctl_run+0x68/0x1a0 +[kvm] + [347315.064933] [<ffffffffa028ecee>] kvm_vcpu_ioctl+0x38e/0x580 [kvm] + [347315.064943] [<ffffffff8116bdfb>] do_vfs_ioctl+0x8b/0x3b0 + [347315.064947] [<ffffffff8116c1c1>] sys_ioctl+0xa1/0xb0 + [347315.064951] [<ffffffff81469272>] system_call_fastpath+0x16/0x1b + [347315.064957] [<00007fee51969ce7>] 0x7fee51969ce6 + [347315.064959] vmwrite error: reg 6c10 value 0 (err 0) + + 4) The isssue can't be reporduced. I search the Intel VMX sepc about reaseons +of vmptrld failure: + The instruction fails if its operand is not properly aligned, sets +unsupported physical-address bits, or is equal to the VMXON + pointer. In addition, the instruction fails if the 32 bits in memory +referenced by the operand do not match the VMCS + revision identifier supported by this processor. + + But I can't find any cues from the KVM source code. It seems each + error conditions is impossible in theory. :( + +Any suggestions will be appreciated! Paolo? + +-- +Regards, +-Gonglei + +On 10/11/2016 15:10, gong lei wrote: +> +4) The isssue can't be reporduced. I search the Intel VMX sepc about +> +reaseons +> +of vmptrld failure: +> +The instruction fails if its operand is not properly aligned, sets +> +unsupported physical-address bits, or is equal to the VMXON +> +pointer. In addition, the instruction fails if the 32 bits in memory +> +referenced by the operand do not match the VMCS +> +revision identifier supported by this processor. +> +> +But I can't find any cues from the KVM source code. It seems each +> +error conditions is impossible in theory. :( +Yes, it should not happen. :( + +If it's not reproducible, it's really hard to say what it was, except a +random memory corruption elsewhere or even a bit flip (!). + +Paolo + +On 2016/11/17 20:39, Paolo Bonzini wrote: +> +> +On 10/11/2016 15:10, gong lei wrote: +> +> 4) The isssue can't be reporduced. I search the Intel VMX sepc about +> +> reaseons +> +> of vmptrld failure: +> +> The instruction fails if its operand is not properly aligned, sets +> +> unsupported physical-address bits, or is equal to the VMXON +> +> pointer. In addition, the instruction fails if the 32 bits in memory +> +> referenced by the operand do not match the VMCS +> +> revision identifier supported by this processor. +> +> +> +> But I can't find any cues from the KVM source code. It seems each +> +> error conditions is impossible in theory. :( +> +Yes, it should not happen. :( +> +> +If it's not reproducible, it's really hard to say what it was, except a +> +random memory corruption elsewhere or even a bit flip (!). +> +> +Paolo +Thanks for your reply, Paolo :) + +-- +Regards, +-Gonglei + diff --git a/results/classifier/001/mistranslation/26430026 b/results/classifier/001/mistranslation/26430026 new file mode 100644 index 000000000..ead1f32fd --- /dev/null +++ b/results/classifier/001/mistranslation/26430026 @@ -0,0 +1,165 @@ +mistranslation: 0.915 +semantic: 0.904 +instruction: 0.888 +other: 0.813 + +[BUG] cxl,i386: e820 mappings may not be correct for cxl + +Context included below from prior discussion + - `cxl create-region` would fail on inability to allocate memory + - traced this down to the memory region being marked RESERVED + - E820 map marks the CXL fixed memory window as RESERVED + + +Re: x86 errors, I found that region worked with this patch. (I also +added the SRAT patches the Davidlohr posted, but I do not think they are +relevant). + +I don't think this is correct, and setting this to E820_RAM causes the +system to fail to boot at all, but with this change `cxl create-region` +succeeds, which suggests our e820 mappings in the i386 machine are +incorrect. + +Anyone who can help or have an idea as to what e820 should actually be +doing with this region, or if this is correct and something else is +failing, please help! + + +diff --git a/hw/i386/pc.c b/hw/i386/pc.c +index 566accf7e6..a5e688a742 100644 +--- a/hw/i386/pc.c ++++ b/hw/i386/pc.c +@@ -1077,7 +1077,7 @@ void pc_memory_init(PCMachineState *pcms, + memory_region_init_io(&fw->mr, OBJECT(machine), &cfmws_ops, fw, + "cxl-fixed-memory-region", fw->size); + memory_region_add_subregion(system_memory, fw->base, &fw->mr); +- e820_add_entry(fw->base, fw->size, E820_RESERVED); ++ e820_add_entry(fw->base, fw->size, E820_NVS); + cxl_fmw_base += fw->size; + cxl_resv_end = cxl_fmw_base; + } + + +On Mon, Oct 10, 2022 at 05:32:42PM +0100, Jonathan Cameron wrote: +> +> +> > but i'm not sure of what to do with this info. We have some proof +> +> > that real hardware works with this no problem, and the only difference +> +> > is that the EFI/bios/firmware is setting the memory regions as `usable` +> +> > or `soft reserved`, which would imply the EDK2 is the blocker here +> +> > regardless of the OS driver status. +> +> > +> +> > But I'd seen elsewhere you had gotten some of this working, and I'm +> +> > failing to get anything working at the moment. If you have any input i +> +> > would greatly appreciate the help. +> +> > +> +> > QEMU config: +> +> > +> +> > /opt/qemu-cxl2/bin/qemu-system-x86_64 \ +> +> > -drive +> +> > file=/var/lib/libvirt/images/cxl.qcow2,format=qcow2,index=0,media=d\ +> +> > -m 2G,slots=4,maxmem=4G \ +> +> > -smp 4 \ +> +> > -machine type=q35,accel=kvm,cxl=on \ +> +> > -enable-kvm \ +> +> > -nographic \ +> +> > -device pxb-cxl,id=cxl.0,bus=pcie.0,bus_nr=52 \ +> +> > -device cxl-rp,id=rp0,bus=cxl.0,chassis=0,slot=0 \ +> +> > -object memory-backend-file,id=cxl-mem0,mem-path=/tmp/cxl-mem0,size=256M \ +> +> > -object memory-backend-file,id=lsa0,mem-path=/tmp/cxl-lsa0,size=256M \ +> +> > -device cxl-type3,bus=rp0,pmem=true,memdev=cxl-mem0,lsa=lsa0,id=cxl-pmem0 +> +> > \ +> +> > -M cxl-fmw.0.targets.0=cxl.0,cxl-fmw.0.size=256M +> +> > +> +> > I'd seen on the lists that you had seen issues with single-rp setups, +> +> > but no combination of configuration I've tried (including all the ones +> +> > in the docs and tests) lead to a successful region creation with +> +> > `cxl create-region` +> +> +> +> Hmm. Let me have a play. I've not run x86 tests for a while so +> +> perhaps something is missing there. +> +> +> +> I'm carrying a patch to override check_last_peer() in +> +> cxl_port_setup_targets() as that is wrong for some combinations, +> +> but that doesn't look like it's related to what you are seeing. +> +> +I'm not sure if it's relevant, but turned out I'd forgotten I'm carrying 3 +> +patches that aren't upstream (and one is a horrible hack). +> +> +Hack: +https://lore.kernel.org/linux-cxl/20220819094655.000005ed@huawei.com/ +> +Shouldn't affect a simple case like this... +> +> +https://lore.kernel.org/linux-cxl/20220819093133.00006c22@huawei.com/T/#t +> +(Dan's version) +> +> +https://lore.kernel.org/linux-cxl/20220815154044.24733-1-Jonathan.Cameron@huawei.com/T/#t +> +> +For writes to work you will currently need two rps (nothing on the second is +> +fine) +> +as we still haven't resolved if the kernel should support an HDM decoder on +> +a host bridge with one port. I think it should (Spec allows it), others +> +unconvinced. +> +> +Note I haven't shifted over to x86 yet so may still be something different +> +from +> +arm64. +> +> +Jonathan +> +> + diff --git a/results/classifier/001/mistranslation/36568044 b/results/classifier/001/mistranslation/36568044 new file mode 100644 index 000000000..719c03c74 --- /dev/null +++ b/results/classifier/001/mistranslation/36568044 @@ -0,0 +1,4581 @@ +mistranslation: 0.962 +instruction: 0.930 +other: 0.930 +semantic: 0.923 + +[BUG, RFC] cpr-transfer: qxl guest driver crashes after migration + +Hi all, + +We've been experimenting with cpr-transfer migration mode recently and +have discovered the following issue with the guest QXL driver: + +Run migration source: +> +EMULATOR=/path/to/emulator +> +ROOTFS=/path/to/image +> +QMPSOCK=/var/run/alma8qmp-src.sock +> +> +$EMULATOR -enable-kvm \ +> +-machine q35 \ +> +-cpu host -smp 2 -m 2G \ +> +-object +> +memory-backend-file,id=ram0,size=2G,mem-path=/dev/shm/ram0,share=on\ +> +-machine memory-backend=ram0 \ +> +-machine aux-ram-share=on \ +> +-drive file=$ROOTFS,media=disk,if=virtio \ +> +-qmp unix:$QMPSOCK,server=on,wait=off \ +> +-nographic \ +> +-device qxl-vga +Run migration target: +> +EMULATOR=/path/to/emulator +> +ROOTFS=/path/to/image +> +QMPSOCK=/var/run/alma8qmp-dst.sock +> +> +> +> +$EMULATOR -enable-kvm \ +> +-machine q35 \ +> +-cpu host -smp 2 -m 2G \ +> +-object +> +memory-backend-file,id=ram0,size=2G,mem-path=/dev/shm/ram0,share=on\ +> +-machine memory-backend=ram0 \ +> +-machine aux-ram-share=on \ +> +-drive file=$ROOTFS,media=disk,if=virtio \ +> +-qmp unix:$QMPSOCK,server=on,wait=off \ +> +-nographic \ +> +-device qxl-vga \ +> +-incoming tcp:0:44444 \ +> +-incoming '{"channel-type": "cpr", "addr": { "transport": "socket", +> +"type": "unix", "path": "/var/run/alma8cpr-dst.sock"}}' +Launch the migration: +> +QMPSHELL=/root/src/qemu/master/scripts/qmp/qmp-shell +> +QMPSOCK=/var/run/alma8qmp-src.sock +> +> +$QMPSHELL -p $QMPSOCK <<EOF +> +migrate-set-parameters mode=cpr-transfer +> +migrate +> +channels=[{"channel-type":"main","addr":{"transport":"socket","type":"inet","host":"0","port":"44444"}},{"channel-type":"cpr","addr":{"transport":"socket","type":"unix","path":"/var/run/alma8cpr-dst.sock"}}] +> +EOF +Then, after a while, QXL guest driver on target crashes spewing the +following messages: +> +[ 73.962002] [TTM] Buffer eviction failed +> +[ 73.962072] qxl 0000:00:02.0: object_init failed for (3149824, 0x00000001) +> +[ 73.962081] [drm:qxl_alloc_bo_reserved [qxl]] *ERROR* failed to allocate +> +VRAM BO +That seems to be a known kernel QXL driver bug: +https://lore.kernel.org/all/20220907094423.93581-1-min_halo@163.com/T/ +https://lore.kernel.org/lkml/ZTgydqRlK6WX_b29@eldamar.lan/ +(the latter discussion contains that reproduce script which speeds up +the crash in the guest): +> +#!/bin/bash +> +> +chvt 3 +> +> +for j in $(seq 80); do +> +echo "$(date) starting round $j" +> +if [ "$(journalctl --boot | grep "failed to allocate VRAM BO")" != "" +> +]; then +> +echo "bug was reproduced after $j tries" +> +exit 1 +> +fi +> +for i in $(seq 100); do +> +dmesg > /dev/tty3 +> +done +> +done +> +> +echo "bug could not be reproduced" +> +exit 0 +The bug itself seems to remain unfixed, as I was able to reproduce that +with Fedora 41 guest, as well as AlmaLinux 8 guest. However our +cpr-transfer code also seems to be buggy as it triggers the crash - +without the cpr-transfer migration the above reproduce doesn't lead to +crash on the source VM. + +I suspect that, as cpr-transfer doesn't migrate the guest memory, but +rather passes it through the memory backend object, our code might +somehow corrupt the VRAM. However, I wasn't able to trace the +corruption so far. + +Could somebody help the investigation and take a look into this? Any +suggestions would be appreciated. Thanks! + +Andrey + +On 2/28/2025 12:39 PM, Andrey Drobyshev wrote: +Hi all, + +We've been experimenting with cpr-transfer migration mode recently and +have discovered the following issue with the guest QXL driver: + +Run migration source: +EMULATOR=/path/to/emulator +ROOTFS=/path/to/image +QMPSOCK=/var/run/alma8qmp-src.sock + +$EMULATOR -enable-kvm \ + -machine q35 \ + -cpu host -smp 2 -m 2G \ + -object +memory-backend-file,id=ram0,size=2G,mem-path=/dev/shm/ram0,share=on\ + -machine memory-backend=ram0 \ + -machine aux-ram-share=on \ + -drive file=$ROOTFS,media=disk,if=virtio \ + -qmp unix:$QMPSOCK,server=on,wait=off \ + -nographic \ + -device qxl-vga +Run migration target: +EMULATOR=/path/to/emulator +ROOTFS=/path/to/image +QMPSOCK=/var/run/alma8qmp-dst.sock +$EMULATOR -enable-kvm \ +-machine q35 \ + -cpu host -smp 2 -m 2G \ + -object +memory-backend-file,id=ram0,size=2G,mem-path=/dev/shm/ram0,share=on\ + -machine memory-backend=ram0 \ + -machine aux-ram-share=on \ + -drive file=$ROOTFS,media=disk,if=virtio \ + -qmp unix:$QMPSOCK,server=on,wait=off \ + -nographic \ + -device qxl-vga \ + -incoming tcp:0:44444 \ + -incoming '{"channel-type": "cpr", "addr": { "transport": "socket", "type": "unix", +"path": "/var/run/alma8cpr-dst.sock"}}' +Launch the migration: +QMPSHELL=/root/src/qemu/master/scripts/qmp/qmp-shell +QMPSOCK=/var/run/alma8qmp-src.sock + +$QMPSHELL -p $QMPSOCK <<EOF + migrate-set-parameters mode=cpr-transfer + migrate +channels=[{"channel-type":"main","addr":{"transport":"socket","type":"inet","host":"0","port":"44444"}},{"channel-type":"cpr","addr":{"transport":"socket","type":"unix","path":"/var/run/alma8cpr-dst.sock"}}] +EOF +Then, after a while, QXL guest driver on target crashes spewing the +following messages: +[ 73.962002] [TTM] Buffer eviction failed +[ 73.962072] qxl 0000:00:02.0: object_init failed for (3149824, 0x00000001) +[ 73.962081] [drm:qxl_alloc_bo_reserved [qxl]] *ERROR* failed to allocate +VRAM BO +That seems to be a known kernel QXL driver bug: +https://lore.kernel.org/all/20220907094423.93581-1-min_halo@163.com/T/ +https://lore.kernel.org/lkml/ZTgydqRlK6WX_b29@eldamar.lan/ +(the latter discussion contains that reproduce script which speeds up +the crash in the guest): +#!/bin/bash + +chvt 3 + +for j in $(seq 80); do + echo "$(date) starting round $j" + if [ "$(journalctl --boot | grep "failed to allocate VRAM BO")" != "" +]; then + echo "bug was reproduced after $j tries" + exit 1 + fi + for i in $(seq 100); do + dmesg > /dev/tty3 + done +done + +echo "bug could not be reproduced" +exit 0 +The bug itself seems to remain unfixed, as I was able to reproduce that +with Fedora 41 guest, as well as AlmaLinux 8 guest. However our +cpr-transfer code also seems to be buggy as it triggers the crash - +without the cpr-transfer migration the above reproduce doesn't lead to +crash on the source VM. + +I suspect that, as cpr-transfer doesn't migrate the guest memory, but +rather passes it through the memory backend object, our code might +somehow corrupt the VRAM. However, I wasn't able to trace the +corruption so far. + +Could somebody help the investigation and take a look into this? Any +suggestions would be appreciated. Thanks! +Possibly some memory region created by qxl is not being preserved. +Try adding these traces to see what is preserved: + +-trace enable='*cpr*' +-trace enable='*ram_alloc*' + +- Steve + +On 2/28/2025 1:13 PM, Steven Sistare wrote: +On 2/28/2025 12:39 PM, Andrey Drobyshev wrote: +Hi all, + +We've been experimenting with cpr-transfer migration mode recently and +have discovered the following issue with the guest QXL driver: + +Run migration source: +EMULATOR=/path/to/emulator +ROOTFS=/path/to/image +QMPSOCK=/var/run/alma8qmp-src.sock + +$EMULATOR -enable-kvm \ +    -machine q35 \ +    -cpu host -smp 2 -m 2G \ +    -object +memory-backend-file,id=ram0,size=2G,mem-path=/dev/shm/ram0,share=on\ +    -machine memory-backend=ram0 \ +    -machine aux-ram-share=on \ +    -drive file=$ROOTFS,media=disk,if=virtio \ +    -qmp unix:$QMPSOCK,server=on,wait=off \ +    -nographic \ +    -device qxl-vga +Run migration target: +EMULATOR=/path/to/emulator +ROOTFS=/path/to/image +QMPSOCK=/var/run/alma8qmp-dst.sock +$EMULATOR -enable-kvm \ +    -machine q35 \ +    -cpu host -smp 2 -m 2G \ +    -object +memory-backend-file,id=ram0,size=2G,mem-path=/dev/shm/ram0,share=on\ +    -machine memory-backend=ram0 \ +    -machine aux-ram-share=on \ +    -drive file=$ROOTFS,media=disk,if=virtio \ +    -qmp unix:$QMPSOCK,server=on,wait=off \ +    -nographic \ +    -device qxl-vga \ +    -incoming tcp:0:44444 \ +    -incoming '{"channel-type": "cpr", "addr": { "transport": "socket", "type": "unix", +"path": "/var/run/alma8cpr-dst.sock"}}' +Launch the migration: +QMPSHELL=/root/src/qemu/master/scripts/qmp/qmp-shell +QMPSOCK=/var/run/alma8qmp-src.sock + +$QMPSHELL -p $QMPSOCK <<EOF +    migrate-set-parameters mode=cpr-transfer +    migrate +channels=[{"channel-type":"main","addr":{"transport":"socket","type":"inet","host":"0","port":"44444"}},{"channel-type":"cpr","addr":{"transport":"socket","type":"unix","path":"/var/run/alma8cpr-dst.sock"}}] +EOF +Then, after a while, QXL guest driver on target crashes spewing the +following messages: +[  73.962002] [TTM] Buffer eviction failed +[  73.962072] qxl 0000:00:02.0: object_init failed for (3149824, 0x00000001) +[  73.962081] [drm:qxl_alloc_bo_reserved [qxl]] *ERROR* failed to allocate +VRAM BO +That seems to be a known kernel QXL driver bug: +https://lore.kernel.org/all/20220907094423.93581-1-min_halo@163.com/T/ +https://lore.kernel.org/lkml/ZTgydqRlK6WX_b29@eldamar.lan/ +(the latter discussion contains that reproduce script which speeds up +the crash in the guest): +#!/bin/bash + +chvt 3 + +for j in $(seq 80); do +        echo "$(date) starting round $j" +        if [ "$(journalctl --boot | grep "failed to allocate VRAM BO")" != "" +]; then +                echo "bug was reproduced after $j tries" +                exit 1 +        fi +        for i in $(seq 100); do +                dmesg > /dev/tty3 +        done +done + +echo "bug could not be reproduced" +exit 0 +The bug itself seems to remain unfixed, as I was able to reproduce that +with Fedora 41 guest, as well as AlmaLinux 8 guest. However our +cpr-transfer code also seems to be buggy as it triggers the crash - +without the cpr-transfer migration the above reproduce doesn't lead to +crash on the source VM. + +I suspect that, as cpr-transfer doesn't migrate the guest memory, but +rather passes it through the memory backend object, our code might +somehow corrupt the VRAM. However, I wasn't able to trace the +corruption so far. + +Could somebody help the investigation and take a look into this? Any +suggestions would be appreciated. Thanks! +Possibly some memory region created by qxl is not being preserved. +Try adding these traces to see what is preserved: + +-trace enable='*cpr*' +-trace enable='*ram_alloc*' +Also try adding this patch to see if it flags any ram blocks as not +compatible with cpr. A message is printed at migration start time. +1740667681-257312-1-git-send-email-steven.sistare@oracle.com +/">https://lore.kernel.org/qemu-devel/ +1740667681-257312-1-git-send-email-steven.sistare@oracle.com +/ +- Steve + +On 2/28/25 8:20 PM, Steven Sistare wrote: +> +On 2/28/2025 1:13 PM, Steven Sistare wrote: +> +> On 2/28/2025 12:39 PM, Andrey Drobyshev wrote: +> +>> Hi all, +> +>> +> +>> We've been experimenting with cpr-transfer migration mode recently and +> +>> have discovered the following issue with the guest QXL driver: +> +>> +> +>> Run migration source: +> +>>> EMULATOR=/path/to/emulator +> +>>> ROOTFS=/path/to/image +> +>>> QMPSOCK=/var/run/alma8qmp-src.sock +> +>>> +> +>>> $EMULATOR -enable-kvm \ +> +>>>     -machine q35 \ +> +>>>     -cpu host -smp 2 -m 2G \ +> +>>>     -object memory-backend-file,id=ram0,size=2G,mem-path=/dev/shm/ +> +>>> ram0,share=on\ +> +>>>     -machine memory-backend=ram0 \ +> +>>>     -machine aux-ram-share=on \ +> +>>>     -drive file=$ROOTFS,media=disk,if=virtio \ +> +>>>     -qmp unix:$QMPSOCK,server=on,wait=off \ +> +>>>     -nographic \ +> +>>>     -device qxl-vga +> +>> +> +>> Run migration target: +> +>>> EMULATOR=/path/to/emulator +> +>>> ROOTFS=/path/to/image +> +>>> QMPSOCK=/var/run/alma8qmp-dst.sock +> +>>> $EMULATOR -enable-kvm \ +> +>>>     -machine q35 \ +> +>>>     -cpu host -smp 2 -m 2G \ +> +>>>     -object memory-backend-file,id=ram0,size=2G,mem-path=/dev/shm/ +> +>>> ram0,share=on\ +> +>>>     -machine memory-backend=ram0 \ +> +>>>     -machine aux-ram-share=on \ +> +>>>     -drive file=$ROOTFS,media=disk,if=virtio \ +> +>>>     -qmp unix:$QMPSOCK,server=on,wait=off \ +> +>>>     -nographic \ +> +>>>     -device qxl-vga \ +> +>>>     -incoming tcp:0:44444 \ +> +>>>     -incoming '{"channel-type": "cpr", "addr": { "transport": +> +>>> "socket", "type": "unix", "path": "/var/run/alma8cpr-dst.sock"}}' +> +>> +> +>> +> +>> Launch the migration: +> +>>> QMPSHELL=/root/src/qemu/master/scripts/qmp/qmp-shell +> +>>> QMPSOCK=/var/run/alma8qmp-src.sock +> +>>> +> +>>> $QMPSHELL -p $QMPSOCK <<EOF +> +>>>     migrate-set-parameters mode=cpr-transfer +> +>>>     migrate channels=[{"channel-type":"main","addr": +> +>>> {"transport":"socket","type":"inet","host":"0","port":"44444"}}, +> +>>> {"channel-type":"cpr","addr": +> +>>> {"transport":"socket","type":"unix","path":"/var/run/alma8cpr- +> +>>> dst.sock"}}] +> +>>> EOF +> +>> +> +>> Then, after a while, QXL guest driver on target crashes spewing the +> +>> following messages: +> +>>> [  73.962002] [TTM] Buffer eviction failed +> +>>> [  73.962072] qxl 0000:00:02.0: object_init failed for (3149824, +> +>>> 0x00000001) +> +>>> [  73.962081] [drm:qxl_alloc_bo_reserved [qxl]] *ERROR* failed to +> +>>> allocate VRAM BO +> +>> +> +>> That seems to be a known kernel QXL driver bug: +> +>> +> +>> +https://lore.kernel.org/all/20220907094423.93581-1-min_halo@163.com/T/ +> +>> +https://lore.kernel.org/lkml/ZTgydqRlK6WX_b29@eldamar.lan/ +> +>> +> +>> (the latter discussion contains that reproduce script which speeds up +> +>> the crash in the guest): +> +>>> #!/bin/bash +> +>>> +> +>>> chvt 3 +> +>>> +> +>>> for j in $(seq 80); do +> +>>>         echo "$(date) starting round $j" +> +>>>         if [ "$(journalctl --boot | grep "failed to allocate VRAM +> +>>> BO")" != "" ]; then +> +>>>                 echo "bug was reproduced after $j tries" +> +>>>                 exit 1 +> +>>>         fi +> +>>>         for i in $(seq 100); do +> +>>>                 dmesg > /dev/tty3 +> +>>>         done +> +>>> done +> +>>> +> +>>> echo "bug could not be reproduced" +> +>>> exit 0 +> +>> +> +>> The bug itself seems to remain unfixed, as I was able to reproduce that +> +>> with Fedora 41 guest, as well as AlmaLinux 8 guest. However our +> +>> cpr-transfer code also seems to be buggy as it triggers the crash - +> +>> without the cpr-transfer migration the above reproduce doesn't lead to +> +>> crash on the source VM. +> +>> +> +>> I suspect that, as cpr-transfer doesn't migrate the guest memory, but +> +>> rather passes it through the memory backend object, our code might +> +>> somehow corrupt the VRAM. However, I wasn't able to trace the +> +>> corruption so far. +> +>> +> +>> Could somebody help the investigation and take a look into this? Any +> +>> suggestions would be appreciated. Thanks! +> +> +> +> Possibly some memory region created by qxl is not being preserved. +> +> Try adding these traces to see what is preserved: +> +> +> +> -trace enable='*cpr*' +> +> -trace enable='*ram_alloc*' +> +> +Also try adding this patch to see if it flags any ram blocks as not +> +compatible with cpr. A message is printed at migration start time. +> + +https://lore.kernel.org/qemu-devel/1740667681-257312-1-git-send-email- +> +steven.sistare@oracle.com/ +> +> +- Steve +> +With the traces enabled + the "migration: ram block cpr blockers" patch +applied: + +Source: +> +cpr_find_fd pc.bios, id 0 returns -1 +> +cpr_save_fd pc.bios, id 0, fd 22 +> +qemu_ram_alloc_shared pc.bios size 262144 max_size 262144 fd 22 host +> +0x7fec18e00000 +> +cpr_find_fd pc.rom, id 0 returns -1 +> +cpr_save_fd pc.rom, id 0, fd 23 +> +qemu_ram_alloc_shared pc.rom size 131072 max_size 131072 fd 23 host +> +0x7fec18c00000 +> +cpr_find_fd 0000:00:01.0/e1000e.rom, id 0 returns -1 +> +cpr_save_fd 0000:00:01.0/e1000e.rom, id 0, fd 24 +> +qemu_ram_alloc_shared 0000:00:01.0/e1000e.rom size 262144 max_size 262144 fd +> +24 host 0x7fec18a00000 +> +cpr_find_fd 0000:00:02.0/vga.vram, id 0 returns -1 +> +cpr_save_fd 0000:00:02.0/vga.vram, id 0, fd 25 +> +qemu_ram_alloc_shared 0000:00:02.0/vga.vram size 67108864 max_size 67108864 +> +fd 25 host 0x7feb77e00000 +> +cpr_find_fd 0000:00:02.0/qxl.vrom, id 0 returns -1 +> +cpr_save_fd 0000:00:02.0/qxl.vrom, id 0, fd 27 +> +qemu_ram_alloc_shared 0000:00:02.0/qxl.vrom size 8192 max_size 8192 fd 27 +> +host 0x7fec18800000 +> +cpr_find_fd 0000:00:02.0/qxl.vram, id 0 returns -1 +> +cpr_save_fd 0000:00:02.0/qxl.vram, id 0, fd 28 +> +qemu_ram_alloc_shared 0000:00:02.0/qxl.vram size 67108864 max_size 67108864 +> +fd 28 host 0x7feb73c00000 +> +cpr_find_fd 0000:00:02.0/qxl.rom, id 0 returns -1 +> +cpr_save_fd 0000:00:02.0/qxl.rom, id 0, fd 34 +> +qemu_ram_alloc_shared 0000:00:02.0/qxl.rom size 65536 max_size 65536 fd 34 +> +host 0x7fec18600000 +> +cpr_find_fd /rom@etc/acpi/tables, id 0 returns -1 +> +cpr_save_fd /rom@etc/acpi/tables, id 0, fd 35 +> +qemu_ram_alloc_shared /rom@etc/acpi/tables size 131072 max_size 2097152 fd 35 +> +host 0x7fec18200000 +> +cpr_find_fd /rom@etc/table-loader, id 0 returns -1 +> +cpr_save_fd /rom@etc/table-loader, id 0, fd 36 +> +qemu_ram_alloc_shared /rom@etc/table-loader size 4096 max_size 65536 fd 36 +> +host 0x7feb8b600000 +> +cpr_find_fd /rom@etc/acpi/rsdp, id 0 returns -1 +> +cpr_save_fd /rom@etc/acpi/rsdp, id 0, fd 37 +> +qemu_ram_alloc_shared /rom@etc/acpi/rsdp size 4096 max_size 4096 fd 37 host +> +0x7feb8b400000 +> +> +cpr_state_save cpr-transfer mode +> +cpr_transfer_output /var/run/alma8cpr-dst.sock +Target: +> +cpr_transfer_input /var/run/alma8cpr-dst.sock +> +cpr_state_load cpr-transfer mode +> +cpr_find_fd pc.bios, id 0 returns 20 +> +qemu_ram_alloc_shared pc.bios size 262144 max_size 262144 fd 20 host +> +0x7fcdc9800000 +> +cpr_find_fd pc.rom, id 0 returns 19 +> +qemu_ram_alloc_shared pc.rom size 131072 max_size 131072 fd 19 host +> +0x7fcdc9600000 +> +cpr_find_fd 0000:00:01.0/e1000e.rom, id 0 returns 18 +> +qemu_ram_alloc_shared 0000:00:01.0/e1000e.rom size 262144 max_size 262144 fd +> +18 host 0x7fcdc9400000 +> +cpr_find_fd 0000:00:02.0/vga.vram, id 0 returns 17 +> +qemu_ram_alloc_shared 0000:00:02.0/vga.vram size 67108864 max_size 67108864 +> +fd 17 host 0x7fcd27e00000 +> +cpr_find_fd 0000:00:02.0/qxl.vrom, id 0 returns 16 +> +qemu_ram_alloc_shared 0000:00:02.0/qxl.vrom size 8192 max_size 8192 fd 16 +> +host 0x7fcdc9200000 +> +cpr_find_fd 0000:00:02.0/qxl.vram, id 0 returns 15 +> +qemu_ram_alloc_shared 0000:00:02.0/qxl.vram size 67108864 max_size 67108864 +> +fd 15 host 0x7fcd23c00000 +> +cpr_find_fd 0000:00:02.0/qxl.rom, id 0 returns 14 +> +qemu_ram_alloc_shared 0000:00:02.0/qxl.rom size 65536 max_size 65536 fd 14 +> +host 0x7fcdc8800000 +> +cpr_find_fd /rom@etc/acpi/tables, id 0 returns 13 +> +qemu_ram_alloc_shared /rom@etc/acpi/tables size 131072 max_size 2097152 fd 13 +> +host 0x7fcdc8400000 +> +cpr_find_fd /rom@etc/table-loader, id 0 returns 11 +> +qemu_ram_alloc_shared /rom@etc/table-loader size 4096 max_size 65536 fd 11 +> +host 0x7fcdc8200000 +> +cpr_find_fd /rom@etc/acpi/rsdp, id 0 returns 10 +> +qemu_ram_alloc_shared /rom@etc/acpi/rsdp size 4096 max_size 4096 fd 10 host +> +0x7fcd3be00000 +Looks like both vga.vram and qxl.vram are being preserved (with the same +addresses), and no incompatible ram blocks are found during migration. + +Andrey + +On 2/28/25 8:35 PM, Andrey Drobyshev wrote: +> +On 2/28/25 8:20 PM, Steven Sistare wrote: +> +> On 2/28/2025 1:13 PM, Steven Sistare wrote: +> +>> On 2/28/2025 12:39 PM, Andrey Drobyshev wrote: +> +>>> Hi all, +> +>>> +> +>>> We've been experimenting with cpr-transfer migration mode recently and +> +>>> have discovered the following issue with the guest QXL driver: +> +>>> +> +>>> Run migration source: +> +>>>> EMULATOR=/path/to/emulator +> +>>>> ROOTFS=/path/to/image +> +>>>> QMPSOCK=/var/run/alma8qmp-src.sock +> +>>>> +> +>>>> $EMULATOR -enable-kvm \ +> +>>>>     -machine q35 \ +> +>>>>     -cpu host -smp 2 -m 2G \ +> +>>>>     -object memory-backend-file,id=ram0,size=2G,mem-path=/dev/shm/ +> +>>>> ram0,share=on\ +> +>>>>     -machine memory-backend=ram0 \ +> +>>>>     -machine aux-ram-share=on \ +> +>>>>     -drive file=$ROOTFS,media=disk,if=virtio \ +> +>>>>     -qmp unix:$QMPSOCK,server=on,wait=off \ +> +>>>>     -nographic \ +> +>>>>     -device qxl-vga +> +>>> +> +>>> Run migration target: +> +>>>> EMULATOR=/path/to/emulator +> +>>>> ROOTFS=/path/to/image +> +>>>> QMPSOCK=/var/run/alma8qmp-dst.sock +> +>>>> $EMULATOR -enable-kvm \ +> +>>>>     -machine q35 \ +> +>>>>     -cpu host -smp 2 -m 2G \ +> +>>>>     -object memory-backend-file,id=ram0,size=2G,mem-path=/dev/shm/ +> +>>>> ram0,share=on\ +> +>>>>     -machine memory-backend=ram0 \ +> +>>>>     -machine aux-ram-share=on \ +> +>>>>     -drive file=$ROOTFS,media=disk,if=virtio \ +> +>>>>     -qmp unix:$QMPSOCK,server=on,wait=off \ +> +>>>>     -nographic \ +> +>>>>     -device qxl-vga \ +> +>>>>     -incoming tcp:0:44444 \ +> +>>>>     -incoming '{"channel-type": "cpr", "addr": { "transport": +> +>>>> "socket", "type": "unix", "path": "/var/run/alma8cpr-dst.sock"}}' +> +>>> +> +>>> +> +>>> Launch the migration: +> +>>>> QMPSHELL=/root/src/qemu/master/scripts/qmp/qmp-shell +> +>>>> QMPSOCK=/var/run/alma8qmp-src.sock +> +>>>> +> +>>>> $QMPSHELL -p $QMPSOCK <<EOF +> +>>>>     migrate-set-parameters mode=cpr-transfer +> +>>>>     migrate channels=[{"channel-type":"main","addr": +> +>>>> {"transport":"socket","type":"inet","host":"0","port":"44444"}}, +> +>>>> {"channel-type":"cpr","addr": +> +>>>> {"transport":"socket","type":"unix","path":"/var/run/alma8cpr- +> +>>>> dst.sock"}}] +> +>>>> EOF +> +>>> +> +>>> Then, after a while, QXL guest driver on target crashes spewing the +> +>>> following messages: +> +>>>> [  73.962002] [TTM] Buffer eviction failed +> +>>>> [  73.962072] qxl 0000:00:02.0: object_init failed for (3149824, +> +>>>> 0x00000001) +> +>>>> [  73.962081] [drm:qxl_alloc_bo_reserved [qxl]] *ERROR* failed to +> +>>>> allocate VRAM BO +> +>>> +> +>>> That seems to be a known kernel QXL driver bug: +> +>>> +> +>>> +https://lore.kernel.org/all/20220907094423.93581-1-min_halo@163.com/T/ +> +>>> +https://lore.kernel.org/lkml/ZTgydqRlK6WX_b29@eldamar.lan/ +> +>>> +> +>>> (the latter discussion contains that reproduce script which speeds up +> +>>> the crash in the guest): +> +>>>> #!/bin/bash +> +>>>> +> +>>>> chvt 3 +> +>>>> +> +>>>> for j in $(seq 80); do +> +>>>>         echo "$(date) starting round $j" +> +>>>>         if [ "$(journalctl --boot | grep "failed to allocate VRAM +> +>>>> BO")" != "" ]; then +> +>>>>                 echo "bug was reproduced after $j tries" +> +>>>>                 exit 1 +> +>>>>         fi +> +>>>>         for i in $(seq 100); do +> +>>>>                 dmesg > /dev/tty3 +> +>>>>         done +> +>>>> done +> +>>>> +> +>>>> echo "bug could not be reproduced" +> +>>>> exit 0 +> +>>> +> +>>> The bug itself seems to remain unfixed, as I was able to reproduce that +> +>>> with Fedora 41 guest, as well as AlmaLinux 8 guest. However our +> +>>> cpr-transfer code also seems to be buggy as it triggers the crash - +> +>>> without the cpr-transfer migration the above reproduce doesn't lead to +> +>>> crash on the source VM. +> +>>> +> +>>> I suspect that, as cpr-transfer doesn't migrate the guest memory, but +> +>>> rather passes it through the memory backend object, our code might +> +>>> somehow corrupt the VRAM. However, I wasn't able to trace the +> +>>> corruption so far. +> +>>> +> +>>> Could somebody help the investigation and take a look into this? Any +> +>>> suggestions would be appreciated. Thanks! +> +>> +> +>> Possibly some memory region created by qxl is not being preserved. +> +>> Try adding these traces to see what is preserved: +> +>> +> +>> -trace enable='*cpr*' +> +>> -trace enable='*ram_alloc*' +> +> +> +> Also try adding this patch to see if it flags any ram blocks as not +> +> compatible with cpr. A message is printed at migration start time. +> +>  +https://lore.kernel.org/qemu-devel/1740667681-257312-1-git-send-email- +> +> steven.sistare@oracle.com/ +> +> +> +> - Steve +> +> +> +> +With the traces enabled + the "migration: ram block cpr blockers" patch +> +applied: +> +> +Source: +> +> cpr_find_fd pc.bios, id 0 returns -1 +> +> cpr_save_fd pc.bios, id 0, fd 22 +> +> qemu_ram_alloc_shared pc.bios size 262144 max_size 262144 fd 22 host +> +> 0x7fec18e00000 +> +> cpr_find_fd pc.rom, id 0 returns -1 +> +> cpr_save_fd pc.rom, id 0, fd 23 +> +> qemu_ram_alloc_shared pc.rom size 131072 max_size 131072 fd 23 host +> +> 0x7fec18c00000 +> +> cpr_find_fd 0000:00:01.0/e1000e.rom, id 0 returns -1 +> +> cpr_save_fd 0000:00:01.0/e1000e.rom, id 0, fd 24 +> +> qemu_ram_alloc_shared 0000:00:01.0/e1000e.rom size 262144 max_size 262144 fd +> +> 24 host 0x7fec18a00000 +> +> cpr_find_fd 0000:00:02.0/vga.vram, id 0 returns -1 +> +> cpr_save_fd 0000:00:02.0/vga.vram, id 0, fd 25 +> +> qemu_ram_alloc_shared 0000:00:02.0/vga.vram size 67108864 max_size 67108864 +> +> fd 25 host 0x7feb77e00000 +> +> cpr_find_fd 0000:00:02.0/qxl.vrom, id 0 returns -1 +> +> cpr_save_fd 0000:00:02.0/qxl.vrom, id 0, fd 27 +> +> qemu_ram_alloc_shared 0000:00:02.0/qxl.vrom size 8192 max_size 8192 fd 27 +> +> host 0x7fec18800000 +> +> cpr_find_fd 0000:00:02.0/qxl.vram, id 0 returns -1 +> +> cpr_save_fd 0000:00:02.0/qxl.vram, id 0, fd 28 +> +> qemu_ram_alloc_shared 0000:00:02.0/qxl.vram size 67108864 max_size 67108864 +> +> fd 28 host 0x7feb73c00000 +> +> cpr_find_fd 0000:00:02.0/qxl.rom, id 0 returns -1 +> +> cpr_save_fd 0000:00:02.0/qxl.rom, id 0, fd 34 +> +> qemu_ram_alloc_shared 0000:00:02.0/qxl.rom size 65536 max_size 65536 fd 34 +> +> host 0x7fec18600000 +> +> cpr_find_fd /rom@etc/acpi/tables, id 0 returns -1 +> +> cpr_save_fd /rom@etc/acpi/tables, id 0, fd 35 +> +> qemu_ram_alloc_shared /rom@etc/acpi/tables size 131072 max_size 2097152 fd +> +> 35 host 0x7fec18200000 +> +> cpr_find_fd /rom@etc/table-loader, id 0 returns -1 +> +> cpr_save_fd /rom@etc/table-loader, id 0, fd 36 +> +> qemu_ram_alloc_shared /rom@etc/table-loader size 4096 max_size 65536 fd 36 +> +> host 0x7feb8b600000 +> +> cpr_find_fd /rom@etc/acpi/rsdp, id 0 returns -1 +> +> cpr_save_fd /rom@etc/acpi/rsdp, id 0, fd 37 +> +> qemu_ram_alloc_shared /rom@etc/acpi/rsdp size 4096 max_size 4096 fd 37 host +> +> 0x7feb8b400000 +> +> +> +> cpr_state_save cpr-transfer mode +> +> cpr_transfer_output /var/run/alma8cpr-dst.sock +> +> +Target: +> +> cpr_transfer_input /var/run/alma8cpr-dst.sock +> +> cpr_state_load cpr-transfer mode +> +> cpr_find_fd pc.bios, id 0 returns 20 +> +> qemu_ram_alloc_shared pc.bios size 262144 max_size 262144 fd 20 host +> +> 0x7fcdc9800000 +> +> cpr_find_fd pc.rom, id 0 returns 19 +> +> qemu_ram_alloc_shared pc.rom size 131072 max_size 131072 fd 19 host +> +> 0x7fcdc9600000 +> +> cpr_find_fd 0000:00:01.0/e1000e.rom, id 0 returns 18 +> +> qemu_ram_alloc_shared 0000:00:01.0/e1000e.rom size 262144 max_size 262144 fd +> +> 18 host 0x7fcdc9400000 +> +> cpr_find_fd 0000:00:02.0/vga.vram, id 0 returns 17 +> +> qemu_ram_alloc_shared 0000:00:02.0/vga.vram size 67108864 max_size 67108864 +> +> fd 17 host 0x7fcd27e00000 +> +> cpr_find_fd 0000:00:02.0/qxl.vrom, id 0 returns 16 +> +> qemu_ram_alloc_shared 0000:00:02.0/qxl.vrom size 8192 max_size 8192 fd 16 +> +> host 0x7fcdc9200000 +> +> cpr_find_fd 0000:00:02.0/qxl.vram, id 0 returns 15 +> +> qemu_ram_alloc_shared 0000:00:02.0/qxl.vram size 67108864 max_size 67108864 +> +> fd 15 host 0x7fcd23c00000 +> +> cpr_find_fd 0000:00:02.0/qxl.rom, id 0 returns 14 +> +> qemu_ram_alloc_shared 0000:00:02.0/qxl.rom size 65536 max_size 65536 fd 14 +> +> host 0x7fcdc8800000 +> +> cpr_find_fd /rom@etc/acpi/tables, id 0 returns 13 +> +> qemu_ram_alloc_shared /rom@etc/acpi/tables size 131072 max_size 2097152 fd +> +> 13 host 0x7fcdc8400000 +> +> cpr_find_fd /rom@etc/table-loader, id 0 returns 11 +> +> qemu_ram_alloc_shared /rom@etc/table-loader size 4096 max_size 65536 fd 11 +> +> host 0x7fcdc8200000 +> +> cpr_find_fd /rom@etc/acpi/rsdp, id 0 returns 10 +> +> qemu_ram_alloc_shared /rom@etc/acpi/rsdp size 4096 max_size 4096 fd 10 host +> +> 0x7fcd3be00000 +> +> +Looks like both vga.vram and qxl.vram are being preserved (with the same +> +addresses), and no incompatible ram blocks are found during migration. +> +Sorry, addressed are not the same, of course. However corresponding ram +blocks do seem to be preserved and initialized. + +On 2/28/2025 1:37 PM, Andrey Drobyshev wrote: +On 2/28/25 8:35 PM, Andrey Drobyshev wrote: +On 2/28/25 8:20 PM, Steven Sistare wrote: +On 2/28/2025 1:13 PM, Steven Sistare wrote: +On 2/28/2025 12:39 PM, Andrey Drobyshev wrote: +Hi all, + +We've been experimenting with cpr-transfer migration mode recently and +have discovered the following issue with the guest QXL driver: + +Run migration source: +EMULATOR=/path/to/emulator +ROOTFS=/path/to/image +QMPSOCK=/var/run/alma8qmp-src.sock + +$EMULATOR -enable-kvm \ +     -machine q35 \ +     -cpu host -smp 2 -m 2G \ +     -object memory-backend-file,id=ram0,size=2G,mem-path=/dev/shm/ +ram0,share=on\ +     -machine memory-backend=ram0 \ +     -machine aux-ram-share=on \ +     -drive file=$ROOTFS,media=disk,if=virtio \ +     -qmp unix:$QMPSOCK,server=on,wait=off \ +     -nographic \ +     -device qxl-vga +Run migration target: +EMULATOR=/path/to/emulator +ROOTFS=/path/to/image +QMPSOCK=/var/run/alma8qmp-dst.sock +$EMULATOR -enable-kvm \ +     -machine q35 \ +     -cpu host -smp 2 -m 2G \ +     -object memory-backend-file,id=ram0,size=2G,mem-path=/dev/shm/ +ram0,share=on\ +     -machine memory-backend=ram0 \ +     -machine aux-ram-share=on \ +     -drive file=$ROOTFS,media=disk,if=virtio \ +     -qmp unix:$QMPSOCK,server=on,wait=off \ +     -nographic \ +     -device qxl-vga \ +     -incoming tcp:0:44444 \ +     -incoming '{"channel-type": "cpr", "addr": { "transport": +"socket", "type": "unix", "path": "/var/run/alma8cpr-dst.sock"}}' +Launch the migration: +QMPSHELL=/root/src/qemu/master/scripts/qmp/qmp-shell +QMPSOCK=/var/run/alma8qmp-src.sock + +$QMPSHELL -p $QMPSOCK <<EOF +     migrate-set-parameters mode=cpr-transfer +     migrate channels=[{"channel-type":"main","addr": +{"transport":"socket","type":"inet","host":"0","port":"44444"}}, +{"channel-type":"cpr","addr": +{"transport":"socket","type":"unix","path":"/var/run/alma8cpr- +dst.sock"}}] +EOF +Then, after a while, QXL guest driver on target crashes spewing the +following messages: +[  73.962002] [TTM] Buffer eviction failed +[  73.962072] qxl 0000:00:02.0: object_init failed for (3149824, +0x00000001) +[  73.962081] [drm:qxl_alloc_bo_reserved [qxl]] *ERROR* failed to +allocate VRAM BO +That seems to be a known kernel QXL driver bug: +https://lore.kernel.org/all/20220907094423.93581-1-min_halo@163.com/T/ +https://lore.kernel.org/lkml/ZTgydqRlK6WX_b29@eldamar.lan/ +(the latter discussion contains that reproduce script which speeds up +the crash in the guest): +#!/bin/bash + +chvt 3 + +for j in $(seq 80); do +         echo "$(date) starting round $j" +         if [ "$(journalctl --boot | grep "failed to allocate VRAM +BO")" != "" ]; then +                 echo "bug was reproduced after $j tries" +                 exit 1 +         fi +         for i in $(seq 100); do +                 dmesg > /dev/tty3 +         done +done + +echo "bug could not be reproduced" +exit 0 +The bug itself seems to remain unfixed, as I was able to reproduce that +with Fedora 41 guest, as well as AlmaLinux 8 guest. However our +cpr-transfer code also seems to be buggy as it triggers the crash - +without the cpr-transfer migration the above reproduce doesn't lead to +crash on the source VM. + +I suspect that, as cpr-transfer doesn't migrate the guest memory, but +rather passes it through the memory backend object, our code might +somehow corrupt the VRAM. However, I wasn't able to trace the +corruption so far. + +Could somebody help the investigation and take a look into this? Any +suggestions would be appreciated. Thanks! +Possibly some memory region created by qxl is not being preserved. +Try adding these traces to see what is preserved: + +-trace enable='*cpr*' +-trace enable='*ram_alloc*' +Also try adding this patch to see if it flags any ram blocks as not +compatible with cpr. A message is printed at migration start time. +  +https://lore.kernel.org/qemu-devel/1740667681-257312-1-git-send-email- +steven.sistare@oracle.com/ + +- Steve +With the traces enabled + the "migration: ram block cpr blockers" patch +applied: + +Source: +cpr_find_fd pc.bios, id 0 returns -1 +cpr_save_fd pc.bios, id 0, fd 22 +qemu_ram_alloc_shared pc.bios size 262144 max_size 262144 fd 22 host +0x7fec18e00000 +cpr_find_fd pc.rom, id 0 returns -1 +cpr_save_fd pc.rom, id 0, fd 23 +qemu_ram_alloc_shared pc.rom size 131072 max_size 131072 fd 23 host +0x7fec18c00000 +cpr_find_fd 0000:00:01.0/e1000e.rom, id 0 returns -1 +cpr_save_fd 0000:00:01.0/e1000e.rom, id 0, fd 24 +qemu_ram_alloc_shared 0000:00:01.0/e1000e.rom size 262144 max_size 262144 fd 24 +host 0x7fec18a00000 +cpr_find_fd 0000:00:02.0/vga.vram, id 0 returns -1 +cpr_save_fd 0000:00:02.0/vga.vram, id 0, fd 25 +qemu_ram_alloc_shared 0000:00:02.0/vga.vram size 67108864 max_size 67108864 fd +25 host 0x7feb77e00000 +cpr_find_fd 0000:00:02.0/qxl.vrom, id 0 returns -1 +cpr_save_fd 0000:00:02.0/qxl.vrom, id 0, fd 27 +qemu_ram_alloc_shared 0000:00:02.0/qxl.vrom size 8192 max_size 8192 fd 27 host +0x7fec18800000 +cpr_find_fd 0000:00:02.0/qxl.vram, id 0 returns -1 +cpr_save_fd 0000:00:02.0/qxl.vram, id 0, fd 28 +qemu_ram_alloc_shared 0000:00:02.0/qxl.vram size 67108864 max_size 67108864 fd +28 host 0x7feb73c00000 +cpr_find_fd 0000:00:02.0/qxl.rom, id 0 returns -1 +cpr_save_fd 0000:00:02.0/qxl.rom, id 0, fd 34 +qemu_ram_alloc_shared 0000:00:02.0/qxl.rom size 65536 max_size 65536 fd 34 host +0x7fec18600000 +cpr_find_fd /rom@etc/acpi/tables, id 0 returns -1 +cpr_save_fd /rom@etc/acpi/tables, id 0, fd 35 +qemu_ram_alloc_shared /rom@etc/acpi/tables size 131072 max_size 2097152 fd 35 +host 0x7fec18200000 +cpr_find_fd /rom@etc/table-loader, id 0 returns -1 +cpr_save_fd /rom@etc/table-loader, id 0, fd 36 +qemu_ram_alloc_shared /rom@etc/table-loader size 4096 max_size 65536 fd 36 host +0x7feb8b600000 +cpr_find_fd /rom@etc/acpi/rsdp, id 0 returns -1 +cpr_save_fd /rom@etc/acpi/rsdp, id 0, fd 37 +qemu_ram_alloc_shared /rom@etc/acpi/rsdp size 4096 max_size 4096 fd 37 host +0x7feb8b400000 + +cpr_state_save cpr-transfer mode +cpr_transfer_output /var/run/alma8cpr-dst.sock +Target: +cpr_transfer_input /var/run/alma8cpr-dst.sock +cpr_state_load cpr-transfer mode +cpr_find_fd pc.bios, id 0 returns 20 +qemu_ram_alloc_shared pc.bios size 262144 max_size 262144 fd 20 host +0x7fcdc9800000 +cpr_find_fd pc.rom, id 0 returns 19 +qemu_ram_alloc_shared pc.rom size 131072 max_size 131072 fd 19 host +0x7fcdc9600000 +cpr_find_fd 0000:00:01.0/e1000e.rom, id 0 returns 18 +qemu_ram_alloc_shared 0000:00:01.0/e1000e.rom size 262144 max_size 262144 fd 18 +host 0x7fcdc9400000 +cpr_find_fd 0000:00:02.0/vga.vram, id 0 returns 17 +qemu_ram_alloc_shared 0000:00:02.0/vga.vram size 67108864 max_size 67108864 fd +17 host 0x7fcd27e00000 +cpr_find_fd 0000:00:02.0/qxl.vrom, id 0 returns 16 +qemu_ram_alloc_shared 0000:00:02.0/qxl.vrom size 8192 max_size 8192 fd 16 host +0x7fcdc9200000 +cpr_find_fd 0000:00:02.0/qxl.vram, id 0 returns 15 +qemu_ram_alloc_shared 0000:00:02.0/qxl.vram size 67108864 max_size 67108864 fd +15 host 0x7fcd23c00000 +cpr_find_fd 0000:00:02.0/qxl.rom, id 0 returns 14 +qemu_ram_alloc_shared 0000:00:02.0/qxl.rom size 65536 max_size 65536 fd 14 host +0x7fcdc8800000 +cpr_find_fd /rom@etc/acpi/tables, id 0 returns 13 +qemu_ram_alloc_shared /rom@etc/acpi/tables size 131072 max_size 2097152 fd 13 +host 0x7fcdc8400000 +cpr_find_fd /rom@etc/table-loader, id 0 returns 11 +qemu_ram_alloc_shared /rom@etc/table-loader size 4096 max_size 65536 fd 11 host +0x7fcdc8200000 +cpr_find_fd /rom@etc/acpi/rsdp, id 0 returns 10 +qemu_ram_alloc_shared /rom@etc/acpi/rsdp size 4096 max_size 4096 fd 10 host +0x7fcd3be00000 +Looks like both vga.vram and qxl.vram are being preserved (with the same +addresses), and no incompatible ram blocks are found during migration. +Sorry, addressed are not the same, of course. However corresponding ram +blocks do seem to be preserved and initialized. +So far, I have not reproduced the guest driver failure. + +However, I have isolated places where new QEMU improperly writes to +the qxl memory regions prior to starting the guest, by mmap'ing them +readonly after cpr: + + qemu_ram_alloc_internal() + if (reused && (strstr(name, "qxl") || strstr("name", "vga"))) + ram_flags |= RAM_READONLY; + new_block = qemu_ram_alloc_from_fd(...) + +I have attached a draft fix; try it and let me know. +My console window looks fine before and after cpr, using +-vnc $hostip:0 -vga qxl + +- Steve +0001-hw-qxl-cpr-support-preliminary.patch +Description: +Text document + +On 3/4/25 9:05 PM, Steven Sistare wrote: +> +On 2/28/2025 1:37 PM, Andrey Drobyshev wrote: +> +> On 2/28/25 8:35 PM, Andrey Drobyshev wrote: +> +>> On 2/28/25 8:20 PM, Steven Sistare wrote: +> +>>> On 2/28/2025 1:13 PM, Steven Sistare wrote: +> +>>>> On 2/28/2025 12:39 PM, Andrey Drobyshev wrote: +> +>>>>> Hi all, +> +>>>>> +> +>>>>> We've been experimenting with cpr-transfer migration mode recently +> +>>>>> and +> +>>>>> have discovered the following issue with the guest QXL driver: +> +>>>>> +> +>>>>> Run migration source: +> +>>>>>> EMULATOR=/path/to/emulator +> +>>>>>> ROOTFS=/path/to/image +> +>>>>>> QMPSOCK=/var/run/alma8qmp-src.sock +> +>>>>>> +> +>>>>>> $EMULATOR -enable-kvm \ +> +>>>>>>      -machine q35 \ +> +>>>>>>      -cpu host -smp 2 -m 2G \ +> +>>>>>>      -object memory-backend-file,id=ram0,size=2G,mem-path=/dev/shm/ +> +>>>>>> ram0,share=on\ +> +>>>>>>      -machine memory-backend=ram0 \ +> +>>>>>>      -machine aux-ram-share=on \ +> +>>>>>>      -drive file=$ROOTFS,media=disk,if=virtio \ +> +>>>>>>      -qmp unix:$QMPSOCK,server=on,wait=off \ +> +>>>>>>      -nographic \ +> +>>>>>>      -device qxl-vga +> +>>>>> +> +>>>>> Run migration target: +> +>>>>>> EMULATOR=/path/to/emulator +> +>>>>>> ROOTFS=/path/to/image +> +>>>>>> QMPSOCK=/var/run/alma8qmp-dst.sock +> +>>>>>> $EMULATOR -enable-kvm \ +> +>>>>>>      -machine q35 \ +> +>>>>>>      -cpu host -smp 2 -m 2G \ +> +>>>>>>      -object memory-backend-file,id=ram0,size=2G,mem-path=/dev/shm/ +> +>>>>>> ram0,share=on\ +> +>>>>>>      -machine memory-backend=ram0 \ +> +>>>>>>      -machine aux-ram-share=on \ +> +>>>>>>      -drive file=$ROOTFS,media=disk,if=virtio \ +> +>>>>>>      -qmp unix:$QMPSOCK,server=on,wait=off \ +> +>>>>>>      -nographic \ +> +>>>>>>      -device qxl-vga \ +> +>>>>>>      -incoming tcp:0:44444 \ +> +>>>>>>      -incoming '{"channel-type": "cpr", "addr": { "transport": +> +>>>>>> "socket", "type": "unix", "path": "/var/run/alma8cpr-dst.sock"}}' +> +>>>>> +> +>>>>> +> +>>>>> Launch the migration: +> +>>>>>> QMPSHELL=/root/src/qemu/master/scripts/qmp/qmp-shell +> +>>>>>> QMPSOCK=/var/run/alma8qmp-src.sock +> +>>>>>> +> +>>>>>> $QMPSHELL -p $QMPSOCK <<EOF +> +>>>>>>      migrate-set-parameters mode=cpr-transfer +> +>>>>>>      migrate channels=[{"channel-type":"main","addr": +> +>>>>>> {"transport":"socket","type":"inet","host":"0","port":"44444"}}, +> +>>>>>> {"channel-type":"cpr","addr": +> +>>>>>> {"transport":"socket","type":"unix","path":"/var/run/alma8cpr- +> +>>>>>> dst.sock"}}] +> +>>>>>> EOF +> +>>>>> +> +>>>>> Then, after a while, QXL guest driver on target crashes spewing the +> +>>>>> following messages: +> +>>>>>> [  73.962002] [TTM] Buffer eviction failed +> +>>>>>> [  73.962072] qxl 0000:00:02.0: object_init failed for (3149824, +> +>>>>>> 0x00000001) +> +>>>>>> [  73.962081] [drm:qxl_alloc_bo_reserved [qxl]] *ERROR* failed to +> +>>>>>> allocate VRAM BO +> +>>>>> +> +>>>>> That seems to be a known kernel QXL driver bug: +> +>>>>> +> +>>>>> +https://lore.kernel.org/all/20220907094423.93581-1- +> +>>>>> min_halo@163.com/T/ +> +>>>>> +https://lore.kernel.org/lkml/ZTgydqRlK6WX_b29@eldamar.lan/ +> +>>>>> +> +>>>>> (the latter discussion contains that reproduce script which speeds up +> +>>>>> the crash in the guest): +> +>>>>>> #!/bin/bash +> +>>>>>> +> +>>>>>> chvt 3 +> +>>>>>> +> +>>>>>> for j in $(seq 80); do +> +>>>>>>          echo "$(date) starting round $j" +> +>>>>>>          if [ "$(journalctl --boot | grep "failed to allocate VRAM +> +>>>>>> BO")" != "" ]; then +> +>>>>>>                  echo "bug was reproduced after $j tries" +> +>>>>>>                  exit 1 +> +>>>>>>          fi +> +>>>>>>          for i in $(seq 100); do +> +>>>>>>                  dmesg > /dev/tty3 +> +>>>>>>          done +> +>>>>>> done +> +>>>>>> +> +>>>>>> echo "bug could not be reproduced" +> +>>>>>> exit 0 +> +>>>>> +> +>>>>> The bug itself seems to remain unfixed, as I was able to reproduce +> +>>>>> that +> +>>>>> with Fedora 41 guest, as well as AlmaLinux 8 guest. However our +> +>>>>> cpr-transfer code also seems to be buggy as it triggers the crash - +> +>>>>> without the cpr-transfer migration the above reproduce doesn't +> +>>>>> lead to +> +>>>>> crash on the source VM. +> +>>>>> +> +>>>>> I suspect that, as cpr-transfer doesn't migrate the guest memory, but +> +>>>>> rather passes it through the memory backend object, our code might +> +>>>>> somehow corrupt the VRAM. However, I wasn't able to trace the +> +>>>>> corruption so far. +> +>>>>> +> +>>>>> Could somebody help the investigation and take a look into this? Any +> +>>>>> suggestions would be appreciated. Thanks! +> +>>>> +> +>>>> Possibly some memory region created by qxl is not being preserved. +> +>>>> Try adding these traces to see what is preserved: +> +>>>> +> +>>>> -trace enable='*cpr*' +> +>>>> -trace enable='*ram_alloc*' +> +>>> +> +>>> Also try adding this patch to see if it flags any ram blocks as not +> +>>> compatible with cpr. A message is printed at migration start time. +> +>>>   +https://lore.kernel.org/qemu-devel/1740667681-257312-1-git-send- +> +>>> email- +> +>>> steven.sistare@oracle.com/ +> +>>> +> +>>> - Steve +> +>>> +> +>> +> +>> With the traces enabled + the "migration: ram block cpr blockers" patch +> +>> applied: +> +>> +> +>> Source: +> +>>> cpr_find_fd pc.bios, id 0 returns -1 +> +>>> cpr_save_fd pc.bios, id 0, fd 22 +> +>>> qemu_ram_alloc_shared pc.bios size 262144 max_size 262144 fd 22 host +> +>>> 0x7fec18e00000 +> +>>> cpr_find_fd pc.rom, id 0 returns -1 +> +>>> cpr_save_fd pc.rom, id 0, fd 23 +> +>>> qemu_ram_alloc_shared pc.rom size 131072 max_size 131072 fd 23 host +> +>>> 0x7fec18c00000 +> +>>> cpr_find_fd 0000:00:01.0/e1000e.rom, id 0 returns -1 +> +>>> cpr_save_fd 0000:00:01.0/e1000e.rom, id 0, fd 24 +> +>>> qemu_ram_alloc_shared 0000:00:01.0/e1000e.rom size 262144 max_size +> +>>> 262144 fd 24 host 0x7fec18a00000 +> +>>> cpr_find_fd 0000:00:02.0/vga.vram, id 0 returns -1 +> +>>> cpr_save_fd 0000:00:02.0/vga.vram, id 0, fd 25 +> +>>> qemu_ram_alloc_shared 0000:00:02.0/vga.vram size 67108864 max_size +> +>>> 67108864 fd 25 host 0x7feb77e00000 +> +>>> cpr_find_fd 0000:00:02.0/qxl.vrom, id 0 returns -1 +> +>>> cpr_save_fd 0000:00:02.0/qxl.vrom, id 0, fd 27 +> +>>> qemu_ram_alloc_shared 0000:00:02.0/qxl.vrom size 8192 max_size 8192 +> +>>> fd 27 host 0x7fec18800000 +> +>>> cpr_find_fd 0000:00:02.0/qxl.vram, id 0 returns -1 +> +>>> cpr_save_fd 0000:00:02.0/qxl.vram, id 0, fd 28 +> +>>> qemu_ram_alloc_shared 0000:00:02.0/qxl.vram size 67108864 max_size +> +>>> 67108864 fd 28 host 0x7feb73c00000 +> +>>> cpr_find_fd 0000:00:02.0/qxl.rom, id 0 returns -1 +> +>>> cpr_save_fd 0000:00:02.0/qxl.rom, id 0, fd 34 +> +>>> qemu_ram_alloc_shared 0000:00:02.0/qxl.rom size 65536 max_size 65536 +> +>>> fd 34 host 0x7fec18600000 +> +>>> cpr_find_fd /rom@etc/acpi/tables, id 0 returns -1 +> +>>> cpr_save_fd /rom@etc/acpi/tables, id 0, fd 35 +> +>>> qemu_ram_alloc_shared /rom@etc/acpi/tables size 131072 max_size +> +>>> 2097152 fd 35 host 0x7fec18200000 +> +>>> cpr_find_fd /rom@etc/table-loader, id 0 returns -1 +> +>>> cpr_save_fd /rom@etc/table-loader, id 0, fd 36 +> +>>> qemu_ram_alloc_shared /rom@etc/table-loader size 4096 max_size 65536 +> +>>> fd 36 host 0x7feb8b600000 +> +>>> cpr_find_fd /rom@etc/acpi/rsdp, id 0 returns -1 +> +>>> cpr_save_fd /rom@etc/acpi/rsdp, id 0, fd 37 +> +>>> qemu_ram_alloc_shared /rom@etc/acpi/rsdp size 4096 max_size 4096 fd +> +>>> 37 host 0x7feb8b400000 +> +>>> +> +>>> cpr_state_save cpr-transfer mode +> +>>> cpr_transfer_output /var/run/alma8cpr-dst.sock +> +>> +> +>> Target: +> +>>> cpr_transfer_input /var/run/alma8cpr-dst.sock +> +>>> cpr_state_load cpr-transfer mode +> +>>> cpr_find_fd pc.bios, id 0 returns 20 +> +>>> qemu_ram_alloc_shared pc.bios size 262144 max_size 262144 fd 20 host +> +>>> 0x7fcdc9800000 +> +>>> cpr_find_fd pc.rom, id 0 returns 19 +> +>>> qemu_ram_alloc_shared pc.rom size 131072 max_size 131072 fd 19 host +> +>>> 0x7fcdc9600000 +> +>>> cpr_find_fd 0000:00:01.0/e1000e.rom, id 0 returns 18 +> +>>> qemu_ram_alloc_shared 0000:00:01.0/e1000e.rom size 262144 max_size +> +>>> 262144 fd 18 host 0x7fcdc9400000 +> +>>> cpr_find_fd 0000:00:02.0/vga.vram, id 0 returns 17 +> +>>> qemu_ram_alloc_shared 0000:00:02.0/vga.vram size 67108864 max_size +> +>>> 67108864 fd 17 host 0x7fcd27e00000 +> +>>> cpr_find_fd 0000:00:02.0/qxl.vrom, id 0 returns 16 +> +>>> qemu_ram_alloc_shared 0000:00:02.0/qxl.vrom size 8192 max_size 8192 +> +>>> fd 16 host 0x7fcdc9200000 +> +>>> cpr_find_fd 0000:00:02.0/qxl.vram, id 0 returns 15 +> +>>> qemu_ram_alloc_shared 0000:00:02.0/qxl.vram size 67108864 max_size +> +>>> 67108864 fd 15 host 0x7fcd23c00000 +> +>>> cpr_find_fd 0000:00:02.0/qxl.rom, id 0 returns 14 +> +>>> qemu_ram_alloc_shared 0000:00:02.0/qxl.rom size 65536 max_size 65536 +> +>>> fd 14 host 0x7fcdc8800000 +> +>>> cpr_find_fd /rom@etc/acpi/tables, id 0 returns 13 +> +>>> qemu_ram_alloc_shared /rom@etc/acpi/tables size 131072 max_size +> +>>> 2097152 fd 13 host 0x7fcdc8400000 +> +>>> cpr_find_fd /rom@etc/table-loader, id 0 returns 11 +> +>>> qemu_ram_alloc_shared /rom@etc/table-loader size 4096 max_size 65536 +> +>>> fd 11 host 0x7fcdc8200000 +> +>>> cpr_find_fd /rom@etc/acpi/rsdp, id 0 returns 10 +> +>>> qemu_ram_alloc_shared /rom@etc/acpi/rsdp size 4096 max_size 4096 fd +> +>>> 10 host 0x7fcd3be00000 +> +>> +> +>> Looks like both vga.vram and qxl.vram are being preserved (with the same +> +>> addresses), and no incompatible ram blocks are found during migration. +> +> +> +> Sorry, addressed are not the same, of course. However corresponding ram +> +> blocks do seem to be preserved and initialized. +> +> +So far, I have not reproduced the guest driver failure. +> +> +However, I have isolated places where new QEMU improperly writes to +> +the qxl memory regions prior to starting the guest, by mmap'ing them +> +readonly after cpr: +> +> + qemu_ram_alloc_internal() +> +   if (reused && (strstr(name, "qxl") || strstr("name", "vga"))) +> +       ram_flags |= RAM_READONLY; +> +   new_block = qemu_ram_alloc_from_fd(...) +> +> +I have attached a draft fix; try it and let me know. +> +My console window looks fine before and after cpr, using +> +-vnc $hostip:0 -vga qxl +> +> +- Steve +Regarding the reproduce: when I launch the buggy version with the same +options as you, i.e. "-vnc 0.0.0.0:$port -vga qxl", and do cpr-transfer, +my VNC client silently hangs on the target after a while. Could it +happen on your stand as well? Could you try launching VM with +"-nographic -device qxl-vga"? That way VM's serial console is given you +directly in the shell, so when qxl driver crashes you're still able to +inspect the kernel messages. + +As for your patch, I can report that it doesn't resolve the issue as it +is. But I was able to track down another possible memory corruption +using your approach with readonly mmap'ing: + +> +Program terminated with signal SIGSEGV, Segmentation fault. +> +#0 init_qxl_ram (d=0x5638996e0e70) at ../hw/display/qxl.c:412 +> +412 d->ram->magic = cpu_to_le32(QXL_RAM_MAGIC); +> +[Current thread is 1 (Thread 0x7f1a4f83b480 (LWP 229798))] +> +(gdb) bt +> +#0 init_qxl_ram (d=0x5638996e0e70) at ../hw/display/qxl.c:412 +> +#1 0x0000563896e7f467 in qxl_realize_common (qxl=0x5638996e0e70, +> +errp=0x7ffd3c2b8170) at ../hw/display/qxl.c:2142 +> +#2 0x0000563896e7fda1 in qxl_realize_primary (dev=0x5638996e0e70, +> +errp=0x7ffd3c2b81d0) at ../hw/display/qxl.c:2257 +> +#3 0x0000563896c7e8f2 in pci_qdev_realize (qdev=0x5638996e0e70, +> +errp=0x7ffd3c2b8250) at ../hw/pci/pci.c:2174 +> +#4 0x00005638970eb54b in device_set_realized (obj=0x5638996e0e70, +> +value=true, errp=0x7ffd3c2b84e0) at ../hw/core/qdev.c:494 +> +#5 0x00005638970f5e14 in property_set_bool (obj=0x5638996e0e70, +> +v=0x5638996f3770, name=0x56389759b141 "realized", opaque=0x5638987893d0, +> +errp=0x7ffd3c2b84e0) +> +at ../qom/object.c:2374 +> +#6 0x00005638970f39f8 in object_property_set (obj=0x5638996e0e70, +> +name=0x56389759b141 "realized", v=0x5638996f3770, errp=0x7ffd3c2b84e0) +> +at ../qom/object.c:1449 +> +#7 0x00005638970f8586 in object_property_set_qobject (obj=0x5638996e0e70, +> +name=0x56389759b141 "realized", value=0x5638996df900, errp=0x7ffd3c2b84e0) +> +at ../qom/qom-qobject.c:28 +> +#8 0x00005638970f3d8d in object_property_set_bool (obj=0x5638996e0e70, +> +name=0x56389759b141 "realized", value=true, errp=0x7ffd3c2b84e0) +> +at ../qom/object.c:1519 +> +#9 0x00005638970eacb0 in qdev_realize (dev=0x5638996e0e70, +> +bus=0x563898cf3c20, errp=0x7ffd3c2b84e0) at ../hw/core/qdev.c:276 +> +#10 0x0000563896dba675 in qdev_device_add_from_qdict (opts=0x5638996dfe50, +> +from_json=false, errp=0x7ffd3c2b84e0) at ../system/qdev-monitor.c:714 +> +#11 0x0000563896dba721 in qdev_device_add (opts=0x563898786150, +> +errp=0x56389855dc40 <error_fatal>) at ../system/qdev-monitor.c:733 +> +#12 0x0000563896dc48f1 in device_init_func (opaque=0x0, opts=0x563898786150, +> +errp=0x56389855dc40 <error_fatal>) at ../system/vl.c:1207 +> +#13 0x000056389737a6cc in qemu_opts_foreach +> +(list=0x563898427b60 <qemu_device_opts>, func=0x563896dc48ca +> +<device_init_func>, opaque=0x0, errp=0x56389855dc40 <error_fatal>) +> +at ../util/qemu-option.c:1135 +> +#14 0x0000563896dc89b5 in qemu_create_cli_devices () at ../system/vl.c:2745 +> +#15 0x0000563896dc8c00 in qmp_x_exit_preconfig (errp=0x56389855dc40 +> +<error_fatal>) at ../system/vl.c:2806 +> +#16 0x0000563896dcb5de in qemu_init (argc=33, argv=0x7ffd3c2b8948) at +> +../system/vl.c:3838 +> +#17 0x0000563897297323 in main (argc=33, argv=0x7ffd3c2b8948) at +> +../system/main.c:72 +So the attached adjusted version of your patch does seem to help. At +least I can't reproduce the crash on my stand. + +I'm wondering, could it be useful to explicitly mark all the reused +memory regions readonly upon cpr-transfer, and then make them writable +back again after the migration is done? That way we will be segfaulting +early on instead of debugging tricky memory corruptions. + +Andrey +0001-hw-qxl-cpr-support-preliminary.patch +Description: +Text Data + +On 3/5/2025 11:50 AM, Andrey Drobyshev wrote: +On 3/4/25 9:05 PM, Steven Sistare wrote: +On 2/28/2025 1:37 PM, Andrey Drobyshev wrote: +On 2/28/25 8:35 PM, Andrey Drobyshev wrote: +On 2/28/25 8:20 PM, Steven Sistare wrote: +On 2/28/2025 1:13 PM, Steven Sistare wrote: +On 2/28/2025 12:39 PM, Andrey Drobyshev wrote: +Hi all, + +We've been experimenting with cpr-transfer migration mode recently +and +have discovered the following issue with the guest QXL driver: + +Run migration source: +EMULATOR=/path/to/emulator +ROOTFS=/path/to/image +QMPSOCK=/var/run/alma8qmp-src.sock + +$EMULATOR -enable-kvm \ +      -machine q35 \ +      -cpu host -smp 2 -m 2G \ +      -object memory-backend-file,id=ram0,size=2G,mem-path=/dev/shm/ +ram0,share=on\ +      -machine memory-backend=ram0 \ +      -machine aux-ram-share=on \ +      -drive file=$ROOTFS,media=disk,if=virtio \ +      -qmp unix:$QMPSOCK,server=on,wait=off \ +      -nographic \ +      -device qxl-vga +Run migration target: +EMULATOR=/path/to/emulator +ROOTFS=/path/to/image +QMPSOCK=/var/run/alma8qmp-dst.sock +$EMULATOR -enable-kvm \ +      -machine q35 \ +      -cpu host -smp 2 -m 2G \ +      -object memory-backend-file,id=ram0,size=2G,mem-path=/dev/shm/ +ram0,share=on\ +      -machine memory-backend=ram0 \ +      -machine aux-ram-share=on \ +      -drive file=$ROOTFS,media=disk,if=virtio \ +      -qmp unix:$QMPSOCK,server=on,wait=off \ +      -nographic \ +      -device qxl-vga \ +      -incoming tcp:0:44444 \ +      -incoming '{"channel-type": "cpr", "addr": { "transport": +"socket", "type": "unix", "path": "/var/run/alma8cpr-dst.sock"}}' +Launch the migration: +QMPSHELL=/root/src/qemu/master/scripts/qmp/qmp-shell +QMPSOCK=/var/run/alma8qmp-src.sock + +$QMPSHELL -p $QMPSOCK <<EOF +      migrate-set-parameters mode=cpr-transfer +      migrate channels=[{"channel-type":"main","addr": +{"transport":"socket","type":"inet","host":"0","port":"44444"}}, +{"channel-type":"cpr","addr": +{"transport":"socket","type":"unix","path":"/var/run/alma8cpr- +dst.sock"}}] +EOF +Then, after a while, QXL guest driver on target crashes spewing the +following messages: +[  73.962002] [TTM] Buffer eviction failed +[  73.962072] qxl 0000:00:02.0: object_init failed for (3149824, +0x00000001) +[  73.962081] [drm:qxl_alloc_bo_reserved [qxl]] *ERROR* failed to +allocate VRAM BO +That seems to be a known kernel QXL driver bug: +https://lore.kernel.org/all/20220907094423.93581-1- +min_halo@163.com/T/ +https://lore.kernel.org/lkml/ZTgydqRlK6WX_b29@eldamar.lan/ +(the latter discussion contains that reproduce script which speeds up +the crash in the guest): +#!/bin/bash + +chvt 3 + +for j in $(seq 80); do +          echo "$(date) starting round $j" +          if [ "$(journalctl --boot | grep "failed to allocate VRAM +BO")" != "" ]; then +                  echo "bug was reproduced after $j tries" +                  exit 1 +          fi +          for i in $(seq 100); do +                  dmesg > /dev/tty3 +          done +done + +echo "bug could not be reproduced" +exit 0 +The bug itself seems to remain unfixed, as I was able to reproduce +that +with Fedora 41 guest, as well as AlmaLinux 8 guest. However our +cpr-transfer code also seems to be buggy as it triggers the crash - +without the cpr-transfer migration the above reproduce doesn't +lead to +crash on the source VM. + +I suspect that, as cpr-transfer doesn't migrate the guest memory, but +rather passes it through the memory backend object, our code might +somehow corrupt the VRAM. However, I wasn't able to trace the +corruption so far. + +Could somebody help the investigation and take a look into this? Any +suggestions would be appreciated. Thanks! +Possibly some memory region created by qxl is not being preserved. +Try adding these traces to see what is preserved: + +-trace enable='*cpr*' +-trace enable='*ram_alloc*' +Also try adding this patch to see if it flags any ram blocks as not +compatible with cpr. A message is printed at migration start time. +   +https://lore.kernel.org/qemu-devel/1740667681-257312-1-git-send- +email- +steven.sistare@oracle.com/ + +- Steve +With the traces enabled + the "migration: ram block cpr blockers" patch +applied: + +Source: +cpr_find_fd pc.bios, id 0 returns -1 +cpr_save_fd pc.bios, id 0, fd 22 +qemu_ram_alloc_shared pc.bios size 262144 max_size 262144 fd 22 host +0x7fec18e00000 +cpr_find_fd pc.rom, id 0 returns -1 +cpr_save_fd pc.rom, id 0, fd 23 +qemu_ram_alloc_shared pc.rom size 131072 max_size 131072 fd 23 host +0x7fec18c00000 +cpr_find_fd 0000:00:01.0/e1000e.rom, id 0 returns -1 +cpr_save_fd 0000:00:01.0/e1000e.rom, id 0, fd 24 +qemu_ram_alloc_shared 0000:00:01.0/e1000e.rom size 262144 max_size +262144 fd 24 host 0x7fec18a00000 +cpr_find_fd 0000:00:02.0/vga.vram, id 0 returns -1 +cpr_save_fd 0000:00:02.0/vga.vram, id 0, fd 25 +qemu_ram_alloc_shared 0000:00:02.0/vga.vram size 67108864 max_size +67108864 fd 25 host 0x7feb77e00000 +cpr_find_fd 0000:00:02.0/qxl.vrom, id 0 returns -1 +cpr_save_fd 0000:00:02.0/qxl.vrom, id 0, fd 27 +qemu_ram_alloc_shared 0000:00:02.0/qxl.vrom size 8192 max_size 8192 +fd 27 host 0x7fec18800000 +cpr_find_fd 0000:00:02.0/qxl.vram, id 0 returns -1 +cpr_save_fd 0000:00:02.0/qxl.vram, id 0, fd 28 +qemu_ram_alloc_shared 0000:00:02.0/qxl.vram size 67108864 max_size +67108864 fd 28 host 0x7feb73c00000 +cpr_find_fd 0000:00:02.0/qxl.rom, id 0 returns -1 +cpr_save_fd 0000:00:02.0/qxl.rom, id 0, fd 34 +qemu_ram_alloc_shared 0000:00:02.0/qxl.rom size 65536 max_size 65536 +fd 34 host 0x7fec18600000 +cpr_find_fd /rom@etc/acpi/tables, id 0 returns -1 +cpr_save_fd /rom@etc/acpi/tables, id 0, fd 35 +qemu_ram_alloc_shared /rom@etc/acpi/tables size 131072 max_size +2097152 fd 35 host 0x7fec18200000 +cpr_find_fd /rom@etc/table-loader, id 0 returns -1 +cpr_save_fd /rom@etc/table-loader, id 0, fd 36 +qemu_ram_alloc_shared /rom@etc/table-loader size 4096 max_size 65536 +fd 36 host 0x7feb8b600000 +cpr_find_fd /rom@etc/acpi/rsdp, id 0 returns -1 +cpr_save_fd /rom@etc/acpi/rsdp, id 0, fd 37 +qemu_ram_alloc_shared /rom@etc/acpi/rsdp size 4096 max_size 4096 fd +37 host 0x7feb8b400000 + +cpr_state_save cpr-transfer mode +cpr_transfer_output /var/run/alma8cpr-dst.sock +Target: +cpr_transfer_input /var/run/alma8cpr-dst.sock +cpr_state_load cpr-transfer mode +cpr_find_fd pc.bios, id 0 returns 20 +qemu_ram_alloc_shared pc.bios size 262144 max_size 262144 fd 20 host +0x7fcdc9800000 +cpr_find_fd pc.rom, id 0 returns 19 +qemu_ram_alloc_shared pc.rom size 131072 max_size 131072 fd 19 host +0x7fcdc9600000 +cpr_find_fd 0000:00:01.0/e1000e.rom, id 0 returns 18 +qemu_ram_alloc_shared 0000:00:01.0/e1000e.rom size 262144 max_size +262144 fd 18 host 0x7fcdc9400000 +cpr_find_fd 0000:00:02.0/vga.vram, id 0 returns 17 +qemu_ram_alloc_shared 0000:00:02.0/vga.vram size 67108864 max_size +67108864 fd 17 host 0x7fcd27e00000 +cpr_find_fd 0000:00:02.0/qxl.vrom, id 0 returns 16 +qemu_ram_alloc_shared 0000:00:02.0/qxl.vrom size 8192 max_size 8192 +fd 16 host 0x7fcdc9200000 +cpr_find_fd 0000:00:02.0/qxl.vram, id 0 returns 15 +qemu_ram_alloc_shared 0000:00:02.0/qxl.vram size 67108864 max_size +67108864 fd 15 host 0x7fcd23c00000 +cpr_find_fd 0000:00:02.0/qxl.rom, id 0 returns 14 +qemu_ram_alloc_shared 0000:00:02.0/qxl.rom size 65536 max_size 65536 +fd 14 host 0x7fcdc8800000 +cpr_find_fd /rom@etc/acpi/tables, id 0 returns 13 +qemu_ram_alloc_shared /rom@etc/acpi/tables size 131072 max_size +2097152 fd 13 host 0x7fcdc8400000 +cpr_find_fd /rom@etc/table-loader, id 0 returns 11 +qemu_ram_alloc_shared /rom@etc/table-loader size 4096 max_size 65536 +fd 11 host 0x7fcdc8200000 +cpr_find_fd /rom@etc/acpi/rsdp, id 0 returns 10 +qemu_ram_alloc_shared /rom@etc/acpi/rsdp size 4096 max_size 4096 fd +10 host 0x7fcd3be00000 +Looks like both vga.vram and qxl.vram are being preserved (with the same +addresses), and no incompatible ram blocks are found during migration. +Sorry, addressed are not the same, of course. However corresponding ram +blocks do seem to be preserved and initialized. +So far, I have not reproduced the guest driver failure. + +However, I have isolated places where new QEMU improperly writes to +the qxl memory regions prior to starting the guest, by mmap'ing them +readonly after cpr: + +  qemu_ram_alloc_internal() +    if (reused && (strstr(name, "qxl") || strstr("name", "vga"))) +        ram_flags |= RAM_READONLY; +    new_block = qemu_ram_alloc_from_fd(...) + +I have attached a draft fix; try it and let me know. +My console window looks fine before and after cpr, using +-vnc $hostip:0 -vga qxl + +- Steve +Regarding the reproduce: when I launch the buggy version with the same +options as you, i.e. "-vnc 0.0.0.0:$port -vga qxl", and do cpr-transfer, +my VNC client silently hangs on the target after a while. Could it +happen on your stand as well? +cpr does not preserve the vnc connection and session. To test, I specify +port 0 for the source VM and port 1 for the dest. When the src vnc goes +dormant the dest vnc becomes active. +Could you try launching VM with +"-nographic -device qxl-vga"? That way VM's serial console is given you +directly in the shell, so when qxl driver crashes you're still able to +inspect the kernel messages. +I have been running like that, but have not reproduced the qxl driver crash, +and I suspect my guest image+kernel is too old. However, once I realized the +issue was post-cpr modification of qxl memory, I switched my attention to the +fix. +As for your patch, I can report that it doesn't resolve the issue as it +is. But I was able to track down another possible memory corruption +using your approach with readonly mmap'ing: +Program terminated with signal SIGSEGV, Segmentation fault. +#0 init_qxl_ram (d=0x5638996e0e70) at ../hw/display/qxl.c:412 +412 d->ram->magic = cpu_to_le32(QXL_RAM_MAGIC); +[Current thread is 1 (Thread 0x7f1a4f83b480 (LWP 229798))] +(gdb) bt +#0 init_qxl_ram (d=0x5638996e0e70) at ../hw/display/qxl.c:412 +#1 0x0000563896e7f467 in qxl_realize_common (qxl=0x5638996e0e70, +errp=0x7ffd3c2b8170) at ../hw/display/qxl.c:2142 +#2 0x0000563896e7fda1 in qxl_realize_primary (dev=0x5638996e0e70, +errp=0x7ffd3c2b81d0) at ../hw/display/qxl.c:2257 +#3 0x0000563896c7e8f2 in pci_qdev_realize (qdev=0x5638996e0e70, +errp=0x7ffd3c2b8250) at ../hw/pci/pci.c:2174 +#4 0x00005638970eb54b in device_set_realized (obj=0x5638996e0e70, value=true, +errp=0x7ffd3c2b84e0) at ../hw/core/qdev.c:494 +#5 0x00005638970f5e14 in property_set_bool (obj=0x5638996e0e70, v=0x5638996f3770, +name=0x56389759b141 "realized", opaque=0x5638987893d0, errp=0x7ffd3c2b84e0) + at ../qom/object.c:2374 +#6 0x00005638970f39f8 in object_property_set (obj=0x5638996e0e70, name=0x56389759b141 +"realized", v=0x5638996f3770, errp=0x7ffd3c2b84e0) + at ../qom/object.c:1449 +#7 0x00005638970f8586 in object_property_set_qobject (obj=0x5638996e0e70, +name=0x56389759b141 "realized", value=0x5638996df900, errp=0x7ffd3c2b84e0) + at ../qom/qom-qobject.c:28 +#8 0x00005638970f3d8d in object_property_set_bool (obj=0x5638996e0e70, +name=0x56389759b141 "realized", value=true, errp=0x7ffd3c2b84e0) + at ../qom/object.c:1519 +#9 0x00005638970eacb0 in qdev_realize (dev=0x5638996e0e70, bus=0x563898cf3c20, +errp=0x7ffd3c2b84e0) at ../hw/core/qdev.c:276 +#10 0x0000563896dba675 in qdev_device_add_from_qdict (opts=0x5638996dfe50, +from_json=false, errp=0x7ffd3c2b84e0) at ../system/qdev-monitor.c:714 +#11 0x0000563896dba721 in qdev_device_add (opts=0x563898786150, errp=0x56389855dc40 +<error_fatal>) at ../system/qdev-monitor.c:733 +#12 0x0000563896dc48f1 in device_init_func (opaque=0x0, opts=0x563898786150, +errp=0x56389855dc40 <error_fatal>) at ../system/vl.c:1207 +#13 0x000056389737a6cc in qemu_opts_foreach + (list=0x563898427b60 <qemu_device_opts>, func=0x563896dc48ca <device_init_func>, +opaque=0x0, errp=0x56389855dc40 <error_fatal>) + at ../util/qemu-option.c:1135 +#14 0x0000563896dc89b5 in qemu_create_cli_devices () at ../system/vl.c:2745 +#15 0x0000563896dc8c00 in qmp_x_exit_preconfig (errp=0x56389855dc40 +<error_fatal>) at ../system/vl.c:2806 +#16 0x0000563896dcb5de in qemu_init (argc=33, argv=0x7ffd3c2b8948) at +../system/vl.c:3838 +#17 0x0000563897297323 in main (argc=33, argv=0x7ffd3c2b8948) at +../system/main.c:72 +So the attached adjusted version of your patch does seem to help. At +least I can't reproduce the crash on my stand. +Thanks for the stack trace; the calls to SPICE_RING_INIT in init_qxl_ram are +definitely harmful. Try V2 of the patch, attached, which skips the lines +of init_qxl_ram that modify guest memory. +I'm wondering, could it be useful to explicitly mark all the reused +memory regions readonly upon cpr-transfer, and then make them writable +back again after the migration is done? That way we will be segfaulting +early on instead of debugging tricky memory corruptions. +It's a useful debugging technique, but changing protection on a large memory +region +can be too expensive for production due to TLB shootdowns. + +Also, there are cases where writes are performed but the value is guaranteed to +be the same: + qxl_post_load() + qxl_set_mode() + d->rom->mode = cpu_to_le32(modenr); +The value is the same because mode and shadow_rom.mode were passed in vmstate +from old qemu. + +- Steve +0001-hw-qxl-cpr-support-preliminary-V2.patch +Description: +Text document + +On 3/5/25 22:19, Steven Sistare wrote: +On 3/5/2025 11:50 AM, Andrey Drobyshev wrote: +On 3/4/25 9:05 PM, Steven Sistare wrote: +On 2/28/2025 1:37 PM, Andrey Drobyshev wrote: +On 2/28/25 8:35 PM, Andrey Drobyshev wrote: +On 2/28/25 8:20 PM, Steven Sistare wrote: +On 2/28/2025 1:13 PM, Steven Sistare wrote: +On 2/28/2025 12:39 PM, Andrey Drobyshev wrote: +Hi all, + +We've been experimenting with cpr-transfer migration mode recently +and +have discovered the following issue with the guest QXL driver: + +Run migration source: +EMULATOR=/path/to/emulator +ROOTFS=/path/to/image +QMPSOCK=/var/run/alma8qmp-src.sock + +$EMULATOR -enable-kvm \ +      -machine q35 \ +      -cpu host -smp 2 -m 2G \ +      -object +memory-backend-file,id=ram0,size=2G,mem-path=/dev/shm/ +ram0,share=on\ +      -machine memory-backend=ram0 \ +      -machine aux-ram-share=on \ +      -drive file=$ROOTFS,media=disk,if=virtio \ +      -qmp unix:$QMPSOCK,server=on,wait=off \ +      -nographic \ +      -device qxl-vga +Run migration target: +EMULATOR=/path/to/emulator +ROOTFS=/path/to/image +QMPSOCK=/var/run/alma8qmp-dst.sock +$EMULATOR -enable-kvm \ +      -machine q35 \ +      -cpu host -smp 2 -m 2G \ +      -object +memory-backend-file,id=ram0,size=2G,mem-path=/dev/shm/ +ram0,share=on\ +      -machine memory-backend=ram0 \ +      -machine aux-ram-share=on \ +      -drive file=$ROOTFS,media=disk,if=virtio \ +      -qmp unix:$QMPSOCK,server=on,wait=off \ +      -nographic \ +      -device qxl-vga \ +      -incoming tcp:0:44444 \ +      -incoming '{"channel-type": "cpr", "addr": { "transport": +"socket", "type": "unix", "path": "/var/run/alma8cpr-dst.sock"}}' +Launch the migration: +QMPSHELL=/root/src/qemu/master/scripts/qmp/qmp-shell +QMPSOCK=/var/run/alma8qmp-src.sock + +$QMPSHELL -p $QMPSOCK <<EOF +      migrate-set-parameters mode=cpr-transfer +      migrate channels=[{"channel-type":"main","addr": +{"transport":"socket","type":"inet","host":"0","port":"44444"}}, +{"channel-type":"cpr","addr": +{"transport":"socket","type":"unix","path":"/var/run/alma8cpr- +dst.sock"}}] +EOF +Then, after a while, QXL guest driver on target crashes spewing +the +following messages: +[  73.962002] [TTM] Buffer eviction failed +[  73.962072] qxl 0000:00:02.0: object_init failed for (3149824, +0x00000001) +[  73.962081] [drm:qxl_alloc_bo_reserved [qxl]] *ERROR* +failed to +allocate VRAM BO +That seems to be a known kernel QXL driver bug: +https://lore.kernel.org/all/20220907094423.93581-1- +min_halo@163.com/T/ +https://lore.kernel.org/lkml/ZTgydqRlK6WX_b29@eldamar.lan/ +(the latter discussion contains that reproduce script which +speeds up +the crash in the guest): +#!/bin/bash + +chvt 3 + +for j in $(seq 80); do +          echo "$(date) starting round $j" +          if [ "$(journalctl --boot | grep "failed to +allocate VRAM +BO")" != "" ]; then +                  echo "bug was reproduced after $j tries" +                  exit 1 +          fi +          for i in $(seq 100); do +                  dmesg > /dev/tty3 +          done +done + +echo "bug could not be reproduced" +exit 0 +The bug itself seems to remain unfixed, as I was able to reproduce +that +with Fedora 41 guest, as well as AlmaLinux 8 guest. However our +cpr-transfer code also seems to be buggy as it triggers the +crash - +without the cpr-transfer migration the above reproduce doesn't +lead to +crash on the source VM. +I suspect that, as cpr-transfer doesn't migrate the guest +memory, but +rather passes it through the memory backend object, our code might +somehow corrupt the VRAM. However, I wasn't able to trace the +corruption so far. +Could somebody help the investigation and take a look into +this? Any +suggestions would be appreciated. Thanks! +Possibly some memory region created by qxl is not being preserved. +Try adding these traces to see what is preserved: + +-trace enable='*cpr*' +-trace enable='*ram_alloc*' +Also try adding this patch to see if it flags any ram blocks as not +compatible with cpr. A message is printed at migration start time. +https://lore.kernel.org/qemu-devel/1740667681-257312-1-git-send- +email- +steven.sistare@oracle.com/ + +- Steve +With the traces enabled + the "migration: ram block cpr blockers" +patch +applied: + +Source: +cpr_find_fd pc.bios, id 0 returns -1 +cpr_save_fd pc.bios, id 0, fd 22 +qemu_ram_alloc_shared pc.bios size 262144 max_size 262144 fd 22 host +0x7fec18e00000 +cpr_find_fd pc.rom, id 0 returns -1 +cpr_save_fd pc.rom, id 0, fd 23 +qemu_ram_alloc_shared pc.rom size 131072 max_size 131072 fd 23 host +0x7fec18c00000 +cpr_find_fd 0000:00:01.0/e1000e.rom, id 0 returns -1 +cpr_save_fd 0000:00:01.0/e1000e.rom, id 0, fd 24 +qemu_ram_alloc_shared 0000:00:01.0/e1000e.rom size 262144 max_size +262144 fd 24 host 0x7fec18a00000 +cpr_find_fd 0000:00:02.0/vga.vram, id 0 returns -1 +cpr_save_fd 0000:00:02.0/vga.vram, id 0, fd 25 +qemu_ram_alloc_shared 0000:00:02.0/vga.vram size 67108864 max_size +67108864 fd 25 host 0x7feb77e00000 +cpr_find_fd 0000:00:02.0/qxl.vrom, id 0 returns -1 +cpr_save_fd 0000:00:02.0/qxl.vrom, id 0, fd 27 +qemu_ram_alloc_shared 0000:00:02.0/qxl.vrom size 8192 max_size 8192 +fd 27 host 0x7fec18800000 +cpr_find_fd 0000:00:02.0/qxl.vram, id 0 returns -1 +cpr_save_fd 0000:00:02.0/qxl.vram, id 0, fd 28 +qemu_ram_alloc_shared 0000:00:02.0/qxl.vram size 67108864 max_size +67108864 fd 28 host 0x7feb73c00000 +cpr_find_fd 0000:00:02.0/qxl.rom, id 0 returns -1 +cpr_save_fd 0000:00:02.0/qxl.rom, id 0, fd 34 +qemu_ram_alloc_shared 0000:00:02.0/qxl.rom size 65536 max_size 65536 +fd 34 host 0x7fec18600000 +cpr_find_fd /rom@etc/acpi/tables, id 0 returns -1 +cpr_save_fd /rom@etc/acpi/tables, id 0, fd 35 +qemu_ram_alloc_shared /rom@etc/acpi/tables size 131072 max_size +2097152 fd 35 host 0x7fec18200000 +cpr_find_fd /rom@etc/table-loader, id 0 returns -1 +cpr_save_fd /rom@etc/table-loader, id 0, fd 36 +qemu_ram_alloc_shared /rom@etc/table-loader size 4096 max_size 65536 +fd 36 host 0x7feb8b600000 +cpr_find_fd /rom@etc/acpi/rsdp, id 0 returns -1 +cpr_save_fd /rom@etc/acpi/rsdp, id 0, fd 37 +qemu_ram_alloc_shared /rom@etc/acpi/rsdp size 4096 max_size 4096 fd +37 host 0x7feb8b400000 + +cpr_state_save cpr-transfer mode +cpr_transfer_output /var/run/alma8cpr-dst.sock +Target: +cpr_transfer_input /var/run/alma8cpr-dst.sock +cpr_state_load cpr-transfer mode +cpr_find_fd pc.bios, id 0 returns 20 +qemu_ram_alloc_shared pc.bios size 262144 max_size 262144 fd 20 host +0x7fcdc9800000 +cpr_find_fd pc.rom, id 0 returns 19 +qemu_ram_alloc_shared pc.rom size 131072 max_size 131072 fd 19 host +0x7fcdc9600000 +cpr_find_fd 0000:00:01.0/e1000e.rom, id 0 returns 18 +qemu_ram_alloc_shared 0000:00:01.0/e1000e.rom size 262144 max_size +262144 fd 18 host 0x7fcdc9400000 +cpr_find_fd 0000:00:02.0/vga.vram, id 0 returns 17 +qemu_ram_alloc_shared 0000:00:02.0/vga.vram size 67108864 max_size +67108864 fd 17 host 0x7fcd27e00000 +cpr_find_fd 0000:00:02.0/qxl.vrom, id 0 returns 16 +qemu_ram_alloc_shared 0000:00:02.0/qxl.vrom size 8192 max_size 8192 +fd 16 host 0x7fcdc9200000 +cpr_find_fd 0000:00:02.0/qxl.vram, id 0 returns 15 +qemu_ram_alloc_shared 0000:00:02.0/qxl.vram size 67108864 max_size +67108864 fd 15 host 0x7fcd23c00000 +cpr_find_fd 0000:00:02.0/qxl.rom, id 0 returns 14 +qemu_ram_alloc_shared 0000:00:02.0/qxl.rom size 65536 max_size 65536 +fd 14 host 0x7fcdc8800000 +cpr_find_fd /rom@etc/acpi/tables, id 0 returns 13 +qemu_ram_alloc_shared /rom@etc/acpi/tables size 131072 max_size +2097152 fd 13 host 0x7fcdc8400000 +cpr_find_fd /rom@etc/table-loader, id 0 returns 11 +qemu_ram_alloc_shared /rom@etc/table-loader size 4096 max_size 65536 +fd 11 host 0x7fcdc8200000 +cpr_find_fd /rom@etc/acpi/rsdp, id 0 returns 10 +qemu_ram_alloc_shared /rom@etc/acpi/rsdp size 4096 max_size 4096 fd +10 host 0x7fcd3be00000 +Looks like both vga.vram and qxl.vram are being preserved (with +the same +addresses), and no incompatible ram blocks are found during +migration. +Sorry, addressed are not the same, of course. However +corresponding ram +blocks do seem to be preserved and initialized. +So far, I have not reproduced the guest driver failure. + +However, I have isolated places where new QEMU improperly writes to +the qxl memory regions prior to starting the guest, by mmap'ing them +readonly after cpr: + +  qemu_ram_alloc_internal() +    if (reused && (strstr(name, "qxl") || strstr("name", "vga"))) +        ram_flags |= RAM_READONLY; +    new_block = qemu_ram_alloc_from_fd(...) + +I have attached a draft fix; try it and let me know. +My console window looks fine before and after cpr, using +-vnc $hostip:0 -vga qxl + +- Steve +Regarding the reproduce: when I launch the buggy version with the same +options as you, i.e. "-vnc 0.0.0.0:$port -vga qxl", and do cpr-transfer, +my VNC client silently hangs on the target after a while. Could it +happen on your stand as well? +cpr does not preserve the vnc connection and session. To test, I specify +port 0 for the source VM and port 1 for the dest. When the src vnc goes +dormant the dest vnc becomes active. +Could you try launching VM with +"-nographic -device qxl-vga"? That way VM's serial console is given you +directly in the shell, so when qxl driver crashes you're still able to +inspect the kernel messages. +I have been running like that, but have not reproduced the qxl driver +crash, +and I suspect my guest image+kernel is too old. However, once I +realized the +issue was post-cpr modification of qxl memory, I switched my attention +to the +fix. +As for your patch, I can report that it doesn't resolve the issue as it +is. But I was able to track down another possible memory corruption +using your approach with readonly mmap'ing: +Program terminated with signal SIGSEGV, Segmentation fault. +#0 init_qxl_ram (d=0x5638996e0e70) at ../hw/display/qxl.c:412 +412        d->ram->magic      = cpu_to_le32(QXL_RAM_MAGIC); +[Current thread is 1 (Thread 0x7f1a4f83b480 (LWP 229798))] +(gdb) bt +#0 init_qxl_ram (d=0x5638996e0e70) at ../hw/display/qxl.c:412 +#1 0x0000563896e7f467 in qxl_realize_common (qxl=0x5638996e0e70, +errp=0x7ffd3c2b8170) at ../hw/display/qxl.c:2142 +#2 0x0000563896e7fda1 in qxl_realize_primary (dev=0x5638996e0e70, +errp=0x7ffd3c2b81d0) at ../hw/display/qxl.c:2257 +#3 0x0000563896c7e8f2 in pci_qdev_realize (qdev=0x5638996e0e70, +errp=0x7ffd3c2b8250) at ../hw/pci/pci.c:2174 +#4 0x00005638970eb54b in device_set_realized (obj=0x5638996e0e70, +value=true, errp=0x7ffd3c2b84e0) at ../hw/core/qdev.c:494 +#5 0x00005638970f5e14 in property_set_bool (obj=0x5638996e0e70, +v=0x5638996f3770, name=0x56389759b141 "realized", +opaque=0x5638987893d0, errp=0x7ffd3c2b84e0) +    at ../qom/object.c:2374 +#6 0x00005638970f39f8 in object_property_set (obj=0x5638996e0e70, +name=0x56389759b141 "realized", v=0x5638996f3770, errp=0x7ffd3c2b84e0) +    at ../qom/object.c:1449 +#7 0x00005638970f8586 in object_property_set_qobject +(obj=0x5638996e0e70, name=0x56389759b141 "realized", +value=0x5638996df900, errp=0x7ffd3c2b84e0) +    at ../qom/qom-qobject.c:28 +#8 0x00005638970f3d8d in object_property_set_bool +(obj=0x5638996e0e70, name=0x56389759b141 "realized", value=true, +errp=0x7ffd3c2b84e0) +    at ../qom/object.c:1519 +#9 0x00005638970eacb0 in qdev_realize (dev=0x5638996e0e70, +bus=0x563898cf3c20, errp=0x7ffd3c2b84e0) at ../hw/core/qdev.c:276 +#10 0x0000563896dba675 in qdev_device_add_from_qdict +(opts=0x5638996dfe50, from_json=false, errp=0x7ffd3c2b84e0) at +../system/qdev-monitor.c:714 +#11 0x0000563896dba721 in qdev_device_add (opts=0x563898786150, +errp=0x56389855dc40 <error_fatal>) at ../system/qdev-monitor.c:733 +#12 0x0000563896dc48f1 in device_init_func (opaque=0x0, +opts=0x563898786150, errp=0x56389855dc40 <error_fatal>) at +../system/vl.c:1207 +#13 0x000056389737a6cc in qemu_opts_foreach +    (list=0x563898427b60 <qemu_device_opts>, func=0x563896dc48ca +<device_init_func>, opaque=0x0, errp=0x56389855dc40 <error_fatal>) +    at ../util/qemu-option.c:1135 +#14 0x0000563896dc89b5 in qemu_create_cli_devices () at +../system/vl.c:2745 +#15 0x0000563896dc8c00 in qmp_x_exit_preconfig (errp=0x56389855dc40 +<error_fatal>) at ../system/vl.c:2806 +#16 0x0000563896dcb5de in qemu_init (argc=33, argv=0x7ffd3c2b8948) +at ../system/vl.c:3838 +#17 0x0000563897297323 in main (argc=33, argv=0x7ffd3c2b8948) at +../system/main.c:72 +So the attached adjusted version of your patch does seem to help. At +least I can't reproduce the crash on my stand. +Thanks for the stack trace; the calls to SPICE_RING_INIT in +init_qxl_ram are +definitely harmful. Try V2 of the patch, attached, which skips the lines +of init_qxl_ram that modify guest memory. +I'm wondering, could it be useful to explicitly mark all the reused +memory regions readonly upon cpr-transfer, and then make them writable +back again after the migration is done? That way we will be segfaulting +early on instead of debugging tricky memory corruptions. +It's a useful debugging technique, but changing protection on a large +memory region +can be too expensive for production due to TLB shootdowns. +Good point. Though we could move this code under non-default option to +avoid re-writing. + +Den + +On 3/5/25 11:19 PM, Steven Sistare wrote: +> +On 3/5/2025 11:50 AM, Andrey Drobyshev wrote: +> +> On 3/4/25 9:05 PM, Steven Sistare wrote: +> +>> On 2/28/2025 1:37 PM, Andrey Drobyshev wrote: +> +>>> On 2/28/25 8:35 PM, Andrey Drobyshev wrote: +> +>>>> On 2/28/25 8:20 PM, Steven Sistare wrote: +> +>>>>> On 2/28/2025 1:13 PM, Steven Sistare wrote: +> +>>>>>> On 2/28/2025 12:39 PM, Andrey Drobyshev wrote: +> +>>>>>>> Hi all, +> +>>>>>>> +> +>>>>>>> We've been experimenting with cpr-transfer migration mode recently +> +>>>>>>> and +> +>>>>>>> have discovered the following issue with the guest QXL driver: +> +>>>>>>> +> +>>>>>>> Run migration source: +> +>>>>>>>> EMULATOR=/path/to/emulator +> +>>>>>>>> ROOTFS=/path/to/image +> +>>>>>>>> QMPSOCK=/var/run/alma8qmp-src.sock +> +>>>>>>>> +> +>>>>>>>> $EMULATOR -enable-kvm \ +> +>>>>>>>>       -machine q35 \ +> +>>>>>>>>       -cpu host -smp 2 -m 2G \ +> +>>>>>>>>       -object memory-backend-file,id=ram0,size=2G,mem-path=/ +> +>>>>>>>> dev/shm/ +> +>>>>>>>> ram0,share=on\ +> +>>>>>>>>       -machine memory-backend=ram0 \ +> +>>>>>>>>       -machine aux-ram-share=on \ +> +>>>>>>>>       -drive file=$ROOTFS,media=disk,if=virtio \ +> +>>>>>>>>       -qmp unix:$QMPSOCK,server=on,wait=off \ +> +>>>>>>>>       -nographic \ +> +>>>>>>>>       -device qxl-vga +> +>>>>>>> +> +>>>>>>> Run migration target: +> +>>>>>>>> EMULATOR=/path/to/emulator +> +>>>>>>>> ROOTFS=/path/to/image +> +>>>>>>>> QMPSOCK=/var/run/alma8qmp-dst.sock +> +>>>>>>>> $EMULATOR -enable-kvm \ +> +>>>>>>>>       -machine q35 \ +> +>>>>>>>>       -cpu host -smp 2 -m 2G \ +> +>>>>>>>>       -object memory-backend-file,id=ram0,size=2G,mem-path=/ +> +>>>>>>>> dev/shm/ +> +>>>>>>>> ram0,share=on\ +> +>>>>>>>>       -machine memory-backend=ram0 \ +> +>>>>>>>>       -machine aux-ram-share=on \ +> +>>>>>>>>       -drive file=$ROOTFS,media=disk,if=virtio \ +> +>>>>>>>>       -qmp unix:$QMPSOCK,server=on,wait=off \ +> +>>>>>>>>       -nographic \ +> +>>>>>>>>       -device qxl-vga \ +> +>>>>>>>>       -incoming tcp:0:44444 \ +> +>>>>>>>>       -incoming '{"channel-type": "cpr", "addr": { "transport": +> +>>>>>>>> "socket", "type": "unix", "path": "/var/run/alma8cpr-dst.sock"}}' +> +>>>>>>> +> +>>>>>>> +> +>>>>>>> Launch the migration: +> +>>>>>>>> QMPSHELL=/root/src/qemu/master/scripts/qmp/qmp-shell +> +>>>>>>>> QMPSOCK=/var/run/alma8qmp-src.sock +> +>>>>>>>> +> +>>>>>>>> $QMPSHELL -p $QMPSOCK <<EOF +> +>>>>>>>>       migrate-set-parameters mode=cpr-transfer +> +>>>>>>>>       migrate channels=[{"channel-type":"main","addr": +> +>>>>>>>> {"transport":"socket","type":"inet","host":"0","port":"44444"}}, +> +>>>>>>>> {"channel-type":"cpr","addr": +> +>>>>>>>> {"transport":"socket","type":"unix","path":"/var/run/alma8cpr- +> +>>>>>>>> dst.sock"}}] +> +>>>>>>>> EOF +> +>>>>>>> +> +>>>>>>> Then, after a while, QXL guest driver on target crashes spewing the +> +>>>>>>> following messages: +> +>>>>>>>> [  73.962002] [TTM] Buffer eviction failed +> +>>>>>>>> [  73.962072] qxl 0000:00:02.0: object_init failed for (3149824, +> +>>>>>>>> 0x00000001) +> +>>>>>>>> [  73.962081] [drm:qxl_alloc_bo_reserved [qxl]] *ERROR* failed to +> +>>>>>>>> allocate VRAM BO +> +>>>>>>> +> +>>>>>>> That seems to be a known kernel QXL driver bug: +> +>>>>>>> +> +>>>>>>> +https://lore.kernel.org/all/20220907094423.93581-1- +> +>>>>>>> min_halo@163.com/T/ +> +>>>>>>> +https://lore.kernel.org/lkml/ZTgydqRlK6WX_b29@eldamar.lan/ +> +>>>>>>> +> +>>>>>>> (the latter discussion contains that reproduce script which +> +>>>>>>> speeds up +> +>>>>>>> the crash in the guest): +> +>>>>>>>> #!/bin/bash +> +>>>>>>>> +> +>>>>>>>> chvt 3 +> +>>>>>>>> +> +>>>>>>>> for j in $(seq 80); do +> +>>>>>>>>           echo "$(date) starting round $j" +> +>>>>>>>>           if [ "$(journalctl --boot | grep "failed to allocate +> +>>>>>>>> VRAM +> +>>>>>>>> BO")" != "" ]; then +> +>>>>>>>>                   echo "bug was reproduced after $j tries" +> +>>>>>>>>                   exit 1 +> +>>>>>>>>           fi +> +>>>>>>>>           for i in $(seq 100); do +> +>>>>>>>>                   dmesg > /dev/tty3 +> +>>>>>>>>           done +> +>>>>>>>> done +> +>>>>>>>> +> +>>>>>>>> echo "bug could not be reproduced" +> +>>>>>>>> exit 0 +> +>>>>>>> +> +>>>>>>> The bug itself seems to remain unfixed, as I was able to reproduce +> +>>>>>>> that +> +>>>>>>> with Fedora 41 guest, as well as AlmaLinux 8 guest. However our +> +>>>>>>> cpr-transfer code also seems to be buggy as it triggers the crash - +> +>>>>>>> without the cpr-transfer migration the above reproduce doesn't +> +>>>>>>> lead to +> +>>>>>>> crash on the source VM. +> +>>>>>>> +> +>>>>>>> I suspect that, as cpr-transfer doesn't migrate the guest +> +>>>>>>> memory, but +> +>>>>>>> rather passes it through the memory backend object, our code might +> +>>>>>>> somehow corrupt the VRAM. However, I wasn't able to trace the +> +>>>>>>> corruption so far. +> +>>>>>>> +> +>>>>>>> Could somebody help the investigation and take a look into +> +>>>>>>> this? Any +> +>>>>>>> suggestions would be appreciated. Thanks! +> +>>>>>> +> +>>>>>> Possibly some memory region created by qxl is not being preserved. +> +>>>>>> Try adding these traces to see what is preserved: +> +>>>>>> +> +>>>>>> -trace enable='*cpr*' +> +>>>>>> -trace enable='*ram_alloc*' +> +>>>>> +> +>>>>> Also try adding this patch to see if it flags any ram blocks as not +> +>>>>> compatible with cpr. A message is printed at migration start time. +> +>>>>>    +https://lore.kernel.org/qemu-devel/1740667681-257312-1-git-send- +> +>>>>> email- +> +>>>>> steven.sistare@oracle.com/ +> +>>>>> +> +>>>>> - Steve +> +>>>>> +> +>>>> +> +>>>> With the traces enabled + the "migration: ram block cpr blockers" +> +>>>> patch +> +>>>> applied: +> +>>>> +> +>>>> Source: +> +>>>>> cpr_find_fd pc.bios, id 0 returns -1 +> +>>>>> cpr_save_fd pc.bios, id 0, fd 22 +> +>>>>> qemu_ram_alloc_shared pc.bios size 262144 max_size 262144 fd 22 host +> +>>>>> 0x7fec18e00000 +> +>>>>> cpr_find_fd pc.rom, id 0 returns -1 +> +>>>>> cpr_save_fd pc.rom, id 0, fd 23 +> +>>>>> qemu_ram_alloc_shared pc.rom size 131072 max_size 131072 fd 23 host +> +>>>>> 0x7fec18c00000 +> +>>>>> cpr_find_fd 0000:00:01.0/e1000e.rom, id 0 returns -1 +> +>>>>> cpr_save_fd 0000:00:01.0/e1000e.rom, id 0, fd 24 +> +>>>>> qemu_ram_alloc_shared 0000:00:01.0/e1000e.rom size 262144 max_size +> +>>>>> 262144 fd 24 host 0x7fec18a00000 +> +>>>>> cpr_find_fd 0000:00:02.0/vga.vram, id 0 returns -1 +> +>>>>> cpr_save_fd 0000:00:02.0/vga.vram, id 0, fd 25 +> +>>>>> qemu_ram_alloc_shared 0000:00:02.0/vga.vram size 67108864 max_size +> +>>>>> 67108864 fd 25 host 0x7feb77e00000 +> +>>>>> cpr_find_fd 0000:00:02.0/qxl.vrom, id 0 returns -1 +> +>>>>> cpr_save_fd 0000:00:02.0/qxl.vrom, id 0, fd 27 +> +>>>>> qemu_ram_alloc_shared 0000:00:02.0/qxl.vrom size 8192 max_size 8192 +> +>>>>> fd 27 host 0x7fec18800000 +> +>>>>> cpr_find_fd 0000:00:02.0/qxl.vram, id 0 returns -1 +> +>>>>> cpr_save_fd 0000:00:02.0/qxl.vram, id 0, fd 28 +> +>>>>> qemu_ram_alloc_shared 0000:00:02.0/qxl.vram size 67108864 max_size +> +>>>>> 67108864 fd 28 host 0x7feb73c00000 +> +>>>>> cpr_find_fd 0000:00:02.0/qxl.rom, id 0 returns -1 +> +>>>>> cpr_save_fd 0000:00:02.0/qxl.rom, id 0, fd 34 +> +>>>>> qemu_ram_alloc_shared 0000:00:02.0/qxl.rom size 65536 max_size 65536 +> +>>>>> fd 34 host 0x7fec18600000 +> +>>>>> cpr_find_fd /rom@etc/acpi/tables, id 0 returns -1 +> +>>>>> cpr_save_fd /rom@etc/acpi/tables, id 0, fd 35 +> +>>>>> qemu_ram_alloc_shared /rom@etc/acpi/tables size 131072 max_size +> +>>>>> 2097152 fd 35 host 0x7fec18200000 +> +>>>>> cpr_find_fd /rom@etc/table-loader, id 0 returns -1 +> +>>>>> cpr_save_fd /rom@etc/table-loader, id 0, fd 36 +> +>>>>> qemu_ram_alloc_shared /rom@etc/table-loader size 4096 max_size 65536 +> +>>>>> fd 36 host 0x7feb8b600000 +> +>>>>> cpr_find_fd /rom@etc/acpi/rsdp, id 0 returns -1 +> +>>>>> cpr_save_fd /rom@etc/acpi/rsdp, id 0, fd 37 +> +>>>>> qemu_ram_alloc_shared /rom@etc/acpi/rsdp size 4096 max_size 4096 fd +> +>>>>> 37 host 0x7feb8b400000 +> +>>>>> +> +>>>>> cpr_state_save cpr-transfer mode +> +>>>>> cpr_transfer_output /var/run/alma8cpr-dst.sock +> +>>>> +> +>>>> Target: +> +>>>>> cpr_transfer_input /var/run/alma8cpr-dst.sock +> +>>>>> cpr_state_load cpr-transfer mode +> +>>>>> cpr_find_fd pc.bios, id 0 returns 20 +> +>>>>> qemu_ram_alloc_shared pc.bios size 262144 max_size 262144 fd 20 host +> +>>>>> 0x7fcdc9800000 +> +>>>>> cpr_find_fd pc.rom, id 0 returns 19 +> +>>>>> qemu_ram_alloc_shared pc.rom size 131072 max_size 131072 fd 19 host +> +>>>>> 0x7fcdc9600000 +> +>>>>> cpr_find_fd 0000:00:01.0/e1000e.rom, id 0 returns 18 +> +>>>>> qemu_ram_alloc_shared 0000:00:01.0/e1000e.rom size 262144 max_size +> +>>>>> 262144 fd 18 host 0x7fcdc9400000 +> +>>>>> cpr_find_fd 0000:00:02.0/vga.vram, id 0 returns 17 +> +>>>>> qemu_ram_alloc_shared 0000:00:02.0/vga.vram size 67108864 max_size +> +>>>>> 67108864 fd 17 host 0x7fcd27e00000 +> +>>>>> cpr_find_fd 0000:00:02.0/qxl.vrom, id 0 returns 16 +> +>>>>> qemu_ram_alloc_shared 0000:00:02.0/qxl.vrom size 8192 max_size 8192 +> +>>>>> fd 16 host 0x7fcdc9200000 +> +>>>>> cpr_find_fd 0000:00:02.0/qxl.vram, id 0 returns 15 +> +>>>>> qemu_ram_alloc_shared 0000:00:02.0/qxl.vram size 67108864 max_size +> +>>>>> 67108864 fd 15 host 0x7fcd23c00000 +> +>>>>> cpr_find_fd 0000:00:02.0/qxl.rom, id 0 returns 14 +> +>>>>> qemu_ram_alloc_shared 0000:00:02.0/qxl.rom size 65536 max_size 65536 +> +>>>>> fd 14 host 0x7fcdc8800000 +> +>>>>> cpr_find_fd /rom@etc/acpi/tables, id 0 returns 13 +> +>>>>> qemu_ram_alloc_shared /rom@etc/acpi/tables size 131072 max_size +> +>>>>> 2097152 fd 13 host 0x7fcdc8400000 +> +>>>>> cpr_find_fd /rom@etc/table-loader, id 0 returns 11 +> +>>>>> qemu_ram_alloc_shared /rom@etc/table-loader size 4096 max_size 65536 +> +>>>>> fd 11 host 0x7fcdc8200000 +> +>>>>> cpr_find_fd /rom@etc/acpi/rsdp, id 0 returns 10 +> +>>>>> qemu_ram_alloc_shared /rom@etc/acpi/rsdp size 4096 max_size 4096 fd +> +>>>>> 10 host 0x7fcd3be00000 +> +>>>> +> +>>>> Looks like both vga.vram and qxl.vram are being preserved (with the +> +>>>> same +> +>>>> addresses), and no incompatible ram blocks are found during migration. +> +>>> +> +>>> Sorry, addressed are not the same, of course. However corresponding +> +>>> ram +> +>>> blocks do seem to be preserved and initialized. +> +>> +> +>> So far, I have not reproduced the guest driver failure. +> +>> +> +>> However, I have isolated places where new QEMU improperly writes to +> +>> the qxl memory regions prior to starting the guest, by mmap'ing them +> +>> readonly after cpr: +> +>> +> +>>   qemu_ram_alloc_internal() +> +>>     if (reused && (strstr(name, "qxl") || strstr("name", "vga"))) +> +>>         ram_flags |= RAM_READONLY; +> +>>     new_block = qemu_ram_alloc_from_fd(...) +> +>> +> +>> I have attached a draft fix; try it and let me know. +> +>> My console window looks fine before and after cpr, using +> +>> -vnc $hostip:0 -vga qxl +> +>> +> +>> - Steve +> +> +> +> Regarding the reproduce: when I launch the buggy version with the same +> +> options as you, i.e. "-vnc 0.0.0.0:$port -vga qxl", and do cpr-transfer, +> +> my VNC client silently hangs on the target after a while. Could it +> +> happen on your stand as well? +> +> +cpr does not preserve the vnc connection and session. To test, I specify +> +port 0 for the source VM and port 1 for the dest. When the src vnc goes +> +dormant the dest vnc becomes active. +> +Sure, I meant that VNC on the dest (on the port 1) works for a while +after the migration and then hangs, apparently after the guest QXL crash. + +> +> Could you try launching VM with +> +> "-nographic -device qxl-vga"? That way VM's serial console is given you +> +> directly in the shell, so when qxl driver crashes you're still able to +> +> inspect the kernel messages. +> +> +I have been running like that, but have not reproduced the qxl driver +> +crash, +> +and I suspect my guest image+kernel is too old. +Yes, that's probably the case. But the crash occurs on my Fedora 41 +guest with the 6.11.5-300.fc41.x86_64 kernel, so newer kernels seem to +be buggy. + + +> +However, once I realized the +> +issue was post-cpr modification of qxl memory, I switched my attention +> +to the +> +fix. +> +> +> As for your patch, I can report that it doesn't resolve the issue as it +> +> is. But I was able to track down another possible memory corruption +> +> using your approach with readonly mmap'ing: +> +> +> +>> Program terminated with signal SIGSEGV, Segmentation fault. +> +>> #0 init_qxl_ram (d=0x5638996e0e70) at ../hw/display/qxl.c:412 +> +>> 412        d->ram->magic      = cpu_to_le32(QXL_RAM_MAGIC); +> +>> [Current thread is 1 (Thread 0x7f1a4f83b480 (LWP 229798))] +> +>> (gdb) bt +> +>> #0 init_qxl_ram (d=0x5638996e0e70) at ../hw/display/qxl.c:412 +> +>> #1 0x0000563896e7f467 in qxl_realize_common (qxl=0x5638996e0e70, +> +>> errp=0x7ffd3c2b8170) at ../hw/display/qxl.c:2142 +> +>> #2 0x0000563896e7fda1 in qxl_realize_primary (dev=0x5638996e0e70, +> +>> errp=0x7ffd3c2b81d0) at ../hw/display/qxl.c:2257 +> +>> #3 0x0000563896c7e8f2 in pci_qdev_realize (qdev=0x5638996e0e70, +> +>> errp=0x7ffd3c2b8250) at ../hw/pci/pci.c:2174 +> +>> #4 0x00005638970eb54b in device_set_realized (obj=0x5638996e0e70, +> +>> value=true, errp=0x7ffd3c2b84e0) at ../hw/core/qdev.c:494 +> +>> #5 0x00005638970f5e14 in property_set_bool (obj=0x5638996e0e70, +> +>> v=0x5638996f3770, name=0x56389759b141 "realized", +> +>> opaque=0x5638987893d0, errp=0x7ffd3c2b84e0) +> +>>     at ../qom/object.c:2374 +> +>> #6 0x00005638970f39f8 in object_property_set (obj=0x5638996e0e70, +> +>> name=0x56389759b141 "realized", v=0x5638996f3770, errp=0x7ffd3c2b84e0) +> +>>     at ../qom/object.c:1449 +> +>> #7 0x00005638970f8586 in object_property_set_qobject +> +>> (obj=0x5638996e0e70, name=0x56389759b141 "realized", +> +>> value=0x5638996df900, errp=0x7ffd3c2b84e0) +> +>>     at ../qom/qom-qobject.c:28 +> +>> #8 0x00005638970f3d8d in object_property_set_bool +> +>> (obj=0x5638996e0e70, name=0x56389759b141 "realized", value=true, +> +>> errp=0x7ffd3c2b84e0) +> +>>     at ../qom/object.c:1519 +> +>> #9 0x00005638970eacb0 in qdev_realize (dev=0x5638996e0e70, +> +>> bus=0x563898cf3c20, errp=0x7ffd3c2b84e0) at ../hw/core/qdev.c:276 +> +>> #10 0x0000563896dba675 in qdev_device_add_from_qdict +> +>> (opts=0x5638996dfe50, from_json=false, errp=0x7ffd3c2b84e0) at ../ +> +>> system/qdev-monitor.c:714 +> +>> #11 0x0000563896dba721 in qdev_device_add (opts=0x563898786150, +> +>> errp=0x56389855dc40 <error_fatal>) at ../system/qdev-monitor.c:733 +> +>> #12 0x0000563896dc48f1 in device_init_func (opaque=0x0, +> +>> opts=0x563898786150, errp=0x56389855dc40 <error_fatal>) at ../system/ +> +>> vl.c:1207 +> +>> #13 0x000056389737a6cc in qemu_opts_foreach +> +>>     (list=0x563898427b60 <qemu_device_opts>, func=0x563896dc48ca +> +>> <device_init_func>, opaque=0x0, errp=0x56389855dc40 <error_fatal>) +> +>>     at ../util/qemu-option.c:1135 +> +>> #14 0x0000563896dc89b5 in qemu_create_cli_devices () at ../system/ +> +>> vl.c:2745 +> +>> #15 0x0000563896dc8c00 in qmp_x_exit_preconfig (errp=0x56389855dc40 +> +>> <error_fatal>) at ../system/vl.c:2806 +> +>> #16 0x0000563896dcb5de in qemu_init (argc=33, argv=0x7ffd3c2b8948) +> +>> at ../system/vl.c:3838 +> +>> #17 0x0000563897297323 in main (argc=33, argv=0x7ffd3c2b8948) at ../ +> +>> system/main.c:72 +> +> +> +> So the attached adjusted version of your patch does seem to help. At +> +> least I can't reproduce the crash on my stand. +> +> +Thanks for the stack trace; the calls to SPICE_RING_INIT in init_qxl_ram +> +are +> +definitely harmful. Try V2 of the patch, attached, which skips the lines +> +of init_qxl_ram that modify guest memory. +> +Thanks, your v2 patch does seem to prevent the crash. Would you re-send +it to the list as a proper fix? + +> +> I'm wondering, could it be useful to explicitly mark all the reused +> +> memory regions readonly upon cpr-transfer, and then make them writable +> +> back again after the migration is done? That way we will be segfaulting +> +> early on instead of debugging tricky memory corruptions. +> +> +It's a useful debugging technique, but changing protection on a large +> +memory region +> +can be too expensive for production due to TLB shootdowns. +> +> +Also, there are cases where writes are performed but the value is +> +guaranteed to +> +be the same: +> + qxl_post_load() +> +   qxl_set_mode() +> +     d->rom->mode = cpu_to_le32(modenr); +> +The value is the same because mode and shadow_rom.mode were passed in +> +vmstate +> +from old qemu. +> +There're also cases where devices' ROM might be re-initialized. E.g. +this segfault occures upon further exploration of RO mapped RAM blocks: + +> +Program terminated with signal SIGSEGV, Segmentation fault. +> +#0 __memmove_avx_unaligned_erms () at +> +../sysdeps/x86_64/multiarch/memmove-vec-unaligned-erms.S:664 +> +664 rep movsb +> +[Current thread is 1 (Thread 0x7f6e7d08b480 (LWP 310379))] +> +(gdb) bt +> +#0 __memmove_avx_unaligned_erms () at +> +../sysdeps/x86_64/multiarch/memmove-vec-unaligned-erms.S:664 +> +#1 0x000055aa1d030ecd in rom_set_mr (rom=0x55aa200ba380, +> +owner=0x55aa2019ac10, name=0x7fffb8272bc0 "/rom@etc/acpi/tables", ro=true) +> +at ../hw/core/loader.c:1032 +> +#2 0x000055aa1d031577 in rom_add_blob +> +(name=0x55aa1da51f13 "etc/acpi/tables", blob=0x55aa208a1070, len=131072, +> +max_len=2097152, addr=18446744073709551615, fw_file_name=0x55aa1da51f13 +> +"etc/acpi/tables", fw_callback=0x55aa1d441f59 <acpi_build_update>, +> +callback_opaque=0x55aa20ff0010, as=0x0, read_only=true) at +> +../hw/core/loader.c:1147 +> +#3 0x000055aa1cfd788d in acpi_add_rom_blob +> +(update=0x55aa1d441f59 <acpi_build_update>, opaque=0x55aa20ff0010, +> +blob=0x55aa1fc9aa00, name=0x55aa1da51f13 "etc/acpi/tables") at +> +../hw/acpi/utils.c:46 +> +#4 0x000055aa1d44213f in acpi_setup () at ../hw/i386/acpi-build.c:2720 +> +#5 0x000055aa1d434199 in pc_machine_done (notifier=0x55aa1ff15050, data=0x0) +> +at ../hw/i386/pc.c:638 +> +#6 0x000055aa1d876845 in notifier_list_notify (list=0x55aa1ea25c10 +> +<machine_init_done_notifiers>, data=0x0) at ../util/notify.c:39 +> +#7 0x000055aa1d039ee5 in qdev_machine_creation_done () at +> +../hw/core/machine.c:1749 +> +#8 0x000055aa1d2c7b3e in qemu_machine_creation_done (errp=0x55aa1ea5cc40 +> +<error_fatal>) at ../system/vl.c:2779 +> +#9 0x000055aa1d2c7c7d in qmp_x_exit_preconfig (errp=0x55aa1ea5cc40 +> +<error_fatal>) at ../system/vl.c:2807 +> +#10 0x000055aa1d2ca64f in qemu_init (argc=35, argv=0x7fffb82730e8) at +> +../system/vl.c:3838 +> +#11 0x000055aa1d79638c in main (argc=35, argv=0x7fffb82730e8) at +> +../system/main.c:72 +I'm not sure whether ACPI tables ROM in particular is rewritten with the +same content, but there might be cases where ROM can be read from file +system upon initialization. That is undesirable as guest kernel +certainly won't be too happy about sudden change of the device's ROM +content. + +So the issue we're dealing with here is any unwanted memory related +device initialization upon cpr. + +For now the only thing that comes to my mind is to make a test where we +put as many devices as we can into a VM, make ram blocks RO upon cpr +(and remap them as RW later after migration is done, if needed), and +catch any unwanted memory violations. As Den suggested, we might +consider adding that behaviour as a separate non-default option (or +"migrate" command flag specific to cpr-transfer), which would only be +used in the testing. + +Andrey + +On 3/6/25 16:16, Andrey Drobyshev wrote: +On 3/5/25 11:19 PM, Steven Sistare wrote: +On 3/5/2025 11:50 AM, Andrey Drobyshev wrote: +On 3/4/25 9:05 PM, Steven Sistare wrote: +On 2/28/2025 1:37 PM, Andrey Drobyshev wrote: +On 2/28/25 8:35 PM, Andrey Drobyshev wrote: +On 2/28/25 8:20 PM, Steven Sistare wrote: +On 2/28/2025 1:13 PM, Steven Sistare wrote: +On 2/28/2025 12:39 PM, Andrey Drobyshev wrote: +Hi all, + +We've been experimenting with cpr-transfer migration mode recently +and +have discovered the following issue with the guest QXL driver: + +Run migration source: +EMULATOR=/path/to/emulator +ROOTFS=/path/to/image +QMPSOCK=/var/run/alma8qmp-src.sock + +$EMULATOR -enable-kvm \ +       -machine q35 \ +       -cpu host -smp 2 -m 2G \ +       -object memory-backend-file,id=ram0,size=2G,mem-path=/ +dev/shm/ +ram0,share=on\ +       -machine memory-backend=ram0 \ +       -machine aux-ram-share=on \ +       -drive file=$ROOTFS,media=disk,if=virtio \ +       -qmp unix:$QMPSOCK,server=on,wait=off \ +       -nographic \ +       -device qxl-vga +Run migration target: +EMULATOR=/path/to/emulator +ROOTFS=/path/to/image +QMPSOCK=/var/run/alma8qmp-dst.sock +$EMULATOR -enable-kvm \ +       -machine q35 \ +       -cpu host -smp 2 -m 2G \ +       -object memory-backend-file,id=ram0,size=2G,mem-path=/ +dev/shm/ +ram0,share=on\ +       -machine memory-backend=ram0 \ +       -machine aux-ram-share=on \ +       -drive file=$ROOTFS,media=disk,if=virtio \ +       -qmp unix:$QMPSOCK,server=on,wait=off \ +       -nographic \ +       -device qxl-vga \ +       -incoming tcp:0:44444 \ +       -incoming '{"channel-type": "cpr", "addr": { "transport": +"socket", "type": "unix", "path": "/var/run/alma8cpr-dst.sock"}}' +Launch the migration: +QMPSHELL=/root/src/qemu/master/scripts/qmp/qmp-shell +QMPSOCK=/var/run/alma8qmp-src.sock + +$QMPSHELL -p $QMPSOCK <<EOF +       migrate-set-parameters mode=cpr-transfer +       migrate channels=[{"channel-type":"main","addr": +{"transport":"socket","type":"inet","host":"0","port":"44444"}}, +{"channel-type":"cpr","addr": +{"transport":"socket","type":"unix","path":"/var/run/alma8cpr- +dst.sock"}}] +EOF +Then, after a while, QXL guest driver on target crashes spewing the +following messages: +[  73.962002] [TTM] Buffer eviction failed +[  73.962072] qxl 0000:00:02.0: object_init failed for (3149824, +0x00000001) +[  73.962081] [drm:qxl_alloc_bo_reserved [qxl]] *ERROR* failed to +allocate VRAM BO +That seems to be a known kernel QXL driver bug: +https://lore.kernel.org/all/20220907094423.93581-1- +min_halo@163.com/T/ +https://lore.kernel.org/lkml/ZTgydqRlK6WX_b29@eldamar.lan/ +(the latter discussion contains that reproduce script which +speeds up +the crash in the guest): +#!/bin/bash + +chvt 3 + +for j in $(seq 80); do +           echo "$(date) starting round $j" +           if [ "$(journalctl --boot | grep "failed to allocate +VRAM +BO")" != "" ]; then +                   echo "bug was reproduced after $j tries" +                   exit 1 +           fi +           for i in $(seq 100); do +                   dmesg > /dev/tty3 +           done +done + +echo "bug could not be reproduced" +exit 0 +The bug itself seems to remain unfixed, as I was able to reproduce +that +with Fedora 41 guest, as well as AlmaLinux 8 guest. However our +cpr-transfer code also seems to be buggy as it triggers the crash - +without the cpr-transfer migration the above reproduce doesn't +lead to +crash on the source VM. + +I suspect that, as cpr-transfer doesn't migrate the guest +memory, but +rather passes it through the memory backend object, our code might +somehow corrupt the VRAM. However, I wasn't able to trace the +corruption so far. + +Could somebody help the investigation and take a look into +this? Any +suggestions would be appreciated. Thanks! +Possibly some memory region created by qxl is not being preserved. +Try adding these traces to see what is preserved: + +-trace enable='*cpr*' +-trace enable='*ram_alloc*' +Also try adding this patch to see if it flags any ram blocks as not +compatible with cpr. A message is printed at migration start time. +    +https://lore.kernel.org/qemu-devel/1740667681-257312-1-git-send- +email- +steven.sistare@oracle.com/ + +- Steve +With the traces enabled + the "migration: ram block cpr blockers" +patch +applied: + +Source: +cpr_find_fd pc.bios, id 0 returns -1 +cpr_save_fd pc.bios, id 0, fd 22 +qemu_ram_alloc_shared pc.bios size 262144 max_size 262144 fd 22 host +0x7fec18e00000 +cpr_find_fd pc.rom, id 0 returns -1 +cpr_save_fd pc.rom, id 0, fd 23 +qemu_ram_alloc_shared pc.rom size 131072 max_size 131072 fd 23 host +0x7fec18c00000 +cpr_find_fd 0000:00:01.0/e1000e.rom, id 0 returns -1 +cpr_save_fd 0000:00:01.0/e1000e.rom, id 0, fd 24 +qemu_ram_alloc_shared 0000:00:01.0/e1000e.rom size 262144 max_size +262144 fd 24 host 0x7fec18a00000 +cpr_find_fd 0000:00:02.0/vga.vram, id 0 returns -1 +cpr_save_fd 0000:00:02.0/vga.vram, id 0, fd 25 +qemu_ram_alloc_shared 0000:00:02.0/vga.vram size 67108864 max_size +67108864 fd 25 host 0x7feb77e00000 +cpr_find_fd 0000:00:02.0/qxl.vrom, id 0 returns -1 +cpr_save_fd 0000:00:02.0/qxl.vrom, id 0, fd 27 +qemu_ram_alloc_shared 0000:00:02.0/qxl.vrom size 8192 max_size 8192 +fd 27 host 0x7fec18800000 +cpr_find_fd 0000:00:02.0/qxl.vram, id 0 returns -1 +cpr_save_fd 0000:00:02.0/qxl.vram, id 0, fd 28 +qemu_ram_alloc_shared 0000:00:02.0/qxl.vram size 67108864 max_size +67108864 fd 28 host 0x7feb73c00000 +cpr_find_fd 0000:00:02.0/qxl.rom, id 0 returns -1 +cpr_save_fd 0000:00:02.0/qxl.rom, id 0, fd 34 +qemu_ram_alloc_shared 0000:00:02.0/qxl.rom size 65536 max_size 65536 +fd 34 host 0x7fec18600000 +cpr_find_fd /rom@etc/acpi/tables, id 0 returns -1 +cpr_save_fd /rom@etc/acpi/tables, id 0, fd 35 +qemu_ram_alloc_shared /rom@etc/acpi/tables size 131072 max_size +2097152 fd 35 host 0x7fec18200000 +cpr_find_fd /rom@etc/table-loader, id 0 returns -1 +cpr_save_fd /rom@etc/table-loader, id 0, fd 36 +qemu_ram_alloc_shared /rom@etc/table-loader size 4096 max_size 65536 +fd 36 host 0x7feb8b600000 +cpr_find_fd /rom@etc/acpi/rsdp, id 0 returns -1 +cpr_save_fd /rom@etc/acpi/rsdp, id 0, fd 37 +qemu_ram_alloc_shared /rom@etc/acpi/rsdp size 4096 max_size 4096 fd +37 host 0x7feb8b400000 + +cpr_state_save cpr-transfer mode +cpr_transfer_output /var/run/alma8cpr-dst.sock +Target: +cpr_transfer_input /var/run/alma8cpr-dst.sock +cpr_state_load cpr-transfer mode +cpr_find_fd pc.bios, id 0 returns 20 +qemu_ram_alloc_shared pc.bios size 262144 max_size 262144 fd 20 host +0x7fcdc9800000 +cpr_find_fd pc.rom, id 0 returns 19 +qemu_ram_alloc_shared pc.rom size 131072 max_size 131072 fd 19 host +0x7fcdc9600000 +cpr_find_fd 0000:00:01.0/e1000e.rom, id 0 returns 18 +qemu_ram_alloc_shared 0000:00:01.0/e1000e.rom size 262144 max_size +262144 fd 18 host 0x7fcdc9400000 +cpr_find_fd 0000:00:02.0/vga.vram, id 0 returns 17 +qemu_ram_alloc_shared 0000:00:02.0/vga.vram size 67108864 max_size +67108864 fd 17 host 0x7fcd27e00000 +cpr_find_fd 0000:00:02.0/qxl.vrom, id 0 returns 16 +qemu_ram_alloc_shared 0000:00:02.0/qxl.vrom size 8192 max_size 8192 +fd 16 host 0x7fcdc9200000 +cpr_find_fd 0000:00:02.0/qxl.vram, id 0 returns 15 +qemu_ram_alloc_shared 0000:00:02.0/qxl.vram size 67108864 max_size +67108864 fd 15 host 0x7fcd23c00000 +cpr_find_fd 0000:00:02.0/qxl.rom, id 0 returns 14 +qemu_ram_alloc_shared 0000:00:02.0/qxl.rom size 65536 max_size 65536 +fd 14 host 0x7fcdc8800000 +cpr_find_fd /rom@etc/acpi/tables, id 0 returns 13 +qemu_ram_alloc_shared /rom@etc/acpi/tables size 131072 max_size +2097152 fd 13 host 0x7fcdc8400000 +cpr_find_fd /rom@etc/table-loader, id 0 returns 11 +qemu_ram_alloc_shared /rom@etc/table-loader size 4096 max_size 65536 +fd 11 host 0x7fcdc8200000 +cpr_find_fd /rom@etc/acpi/rsdp, id 0 returns 10 +qemu_ram_alloc_shared /rom@etc/acpi/rsdp size 4096 max_size 4096 fd +10 host 0x7fcd3be00000 +Looks like both vga.vram and qxl.vram are being preserved (with the +same +addresses), and no incompatible ram blocks are found during migration. +Sorry, addressed are not the same, of course. However corresponding +ram +blocks do seem to be preserved and initialized. +So far, I have not reproduced the guest driver failure. + +However, I have isolated places where new QEMU improperly writes to +the qxl memory regions prior to starting the guest, by mmap'ing them +readonly after cpr: + +   qemu_ram_alloc_internal() +     if (reused && (strstr(name, "qxl") || strstr("name", "vga"))) +         ram_flags |= RAM_READONLY; +     new_block = qemu_ram_alloc_from_fd(...) + +I have attached a draft fix; try it and let me know. +My console window looks fine before and after cpr, using +-vnc $hostip:0 -vga qxl + +- Steve +Regarding the reproduce: when I launch the buggy version with the same +options as you, i.e. "-vnc 0.0.0.0:$port -vga qxl", and do cpr-transfer, +my VNC client silently hangs on the target after a while. Could it +happen on your stand as well? +cpr does not preserve the vnc connection and session. To test, I specify +port 0 for the source VM and port 1 for the dest. When the src vnc goes +dormant the dest vnc becomes active. +Sure, I meant that VNC on the dest (on the port 1) works for a while +after the migration and then hangs, apparently after the guest QXL crash. +Could you try launching VM with +"-nographic -device qxl-vga"? That way VM's serial console is given you +directly in the shell, so when qxl driver crashes you're still able to +inspect the kernel messages. +I have been running like that, but have not reproduced the qxl driver +crash, +and I suspect my guest image+kernel is too old. +Yes, that's probably the case. But the crash occurs on my Fedora 41 +guest with the 6.11.5-300.fc41.x86_64 kernel, so newer kernels seem to +be buggy. +However, once I realized the +issue was post-cpr modification of qxl memory, I switched my attention +to the +fix. +As for your patch, I can report that it doesn't resolve the issue as it +is. But I was able to track down another possible memory corruption +using your approach with readonly mmap'ing: +Program terminated with signal SIGSEGV, Segmentation fault. +#0 init_qxl_ram (d=0x5638996e0e70) at ../hw/display/qxl.c:412 +412        d->ram->magic      = cpu_to_le32(QXL_RAM_MAGIC); +[Current thread is 1 (Thread 0x7f1a4f83b480 (LWP 229798))] +(gdb) bt +#0 init_qxl_ram (d=0x5638996e0e70) at ../hw/display/qxl.c:412 +#1 0x0000563896e7f467 in qxl_realize_common (qxl=0x5638996e0e70, +errp=0x7ffd3c2b8170) at ../hw/display/qxl.c:2142 +#2 0x0000563896e7fda1 in qxl_realize_primary (dev=0x5638996e0e70, +errp=0x7ffd3c2b81d0) at ../hw/display/qxl.c:2257 +#3 0x0000563896c7e8f2 in pci_qdev_realize (qdev=0x5638996e0e70, +errp=0x7ffd3c2b8250) at ../hw/pci/pci.c:2174 +#4 0x00005638970eb54b in device_set_realized (obj=0x5638996e0e70, +value=true, errp=0x7ffd3c2b84e0) at ../hw/core/qdev.c:494 +#5 0x00005638970f5e14 in property_set_bool (obj=0x5638996e0e70, +v=0x5638996f3770, name=0x56389759b141 "realized", +opaque=0x5638987893d0, errp=0x7ffd3c2b84e0) +     at ../qom/object.c:2374 +#6 0x00005638970f39f8 in object_property_set (obj=0x5638996e0e70, +name=0x56389759b141 "realized", v=0x5638996f3770, errp=0x7ffd3c2b84e0) +     at ../qom/object.c:1449 +#7 0x00005638970f8586 in object_property_set_qobject +(obj=0x5638996e0e70, name=0x56389759b141 "realized", +value=0x5638996df900, errp=0x7ffd3c2b84e0) +     at ../qom/qom-qobject.c:28 +#8 0x00005638970f3d8d in object_property_set_bool +(obj=0x5638996e0e70, name=0x56389759b141 "realized", value=true, +errp=0x7ffd3c2b84e0) +     at ../qom/object.c:1519 +#9 0x00005638970eacb0 in qdev_realize (dev=0x5638996e0e70, +bus=0x563898cf3c20, errp=0x7ffd3c2b84e0) at ../hw/core/qdev.c:276 +#10 0x0000563896dba675 in qdev_device_add_from_qdict +(opts=0x5638996dfe50, from_json=false, errp=0x7ffd3c2b84e0) at ../ +system/qdev-monitor.c:714 +#11 0x0000563896dba721 in qdev_device_add (opts=0x563898786150, +errp=0x56389855dc40 <error_fatal>) at ../system/qdev-monitor.c:733 +#12 0x0000563896dc48f1 in device_init_func (opaque=0x0, +opts=0x563898786150, errp=0x56389855dc40 <error_fatal>) at ../system/ +vl.c:1207 +#13 0x000056389737a6cc in qemu_opts_foreach +     (list=0x563898427b60 <qemu_device_opts>, func=0x563896dc48ca +<device_init_func>, opaque=0x0, errp=0x56389855dc40 <error_fatal>) +     at ../util/qemu-option.c:1135 +#14 0x0000563896dc89b5 in qemu_create_cli_devices () at ../system/ +vl.c:2745 +#15 0x0000563896dc8c00 in qmp_x_exit_preconfig (errp=0x56389855dc40 +<error_fatal>) at ../system/vl.c:2806 +#16 0x0000563896dcb5de in qemu_init (argc=33, argv=0x7ffd3c2b8948) +at ../system/vl.c:3838 +#17 0x0000563897297323 in main (argc=33, argv=0x7ffd3c2b8948) at ../ +system/main.c:72 +So the attached adjusted version of your patch does seem to help. At +least I can't reproduce the crash on my stand. +Thanks for the stack trace; the calls to SPICE_RING_INIT in init_qxl_ram +are +definitely harmful. Try V2 of the patch, attached, which skips the lines +of init_qxl_ram that modify guest memory. +Thanks, your v2 patch does seem to prevent the crash. Would you re-send +it to the list as a proper fix? +I'm wondering, could it be useful to explicitly mark all the reused +memory regions readonly upon cpr-transfer, and then make them writable +back again after the migration is done? That way we will be segfaulting +early on instead of debugging tricky memory corruptions. +It's a useful debugging technique, but changing protection on a large +memory region +can be too expensive for production due to TLB shootdowns. + +Also, there are cases where writes are performed but the value is +guaranteed to +be the same: +  qxl_post_load() +    qxl_set_mode() +      d->rom->mode = cpu_to_le32(modenr); +The value is the same because mode and shadow_rom.mode were passed in +vmstate +from old qemu. +There're also cases where devices' ROM might be re-initialized. E.g. +this segfault occures upon further exploration of RO mapped RAM blocks: +Program terminated with signal SIGSEGV, Segmentation fault. +#0 __memmove_avx_unaligned_erms () at +../sysdeps/x86_64/multiarch/memmove-vec-unaligned-erms.S:664 +664 rep movsb +[Current thread is 1 (Thread 0x7f6e7d08b480 (LWP 310379))] +(gdb) bt +#0 __memmove_avx_unaligned_erms () at +../sysdeps/x86_64/multiarch/memmove-vec-unaligned-erms.S:664 +#1 0x000055aa1d030ecd in rom_set_mr (rom=0x55aa200ba380, owner=0x55aa2019ac10, +name=0x7fffb8272bc0 "/rom@etc/acpi/tables", ro=true) + at ../hw/core/loader.c:1032 +#2 0x000055aa1d031577 in rom_add_blob + (name=0x55aa1da51f13 "etc/acpi/tables", blob=0x55aa208a1070, len=131072, max_len=2097152, +addr=18446744073709551615, fw_file_name=0x55aa1da51f13 "etc/acpi/tables", +fw_callback=0x55aa1d441f59 <acpi_build_update>, callback_opaque=0x55aa20ff0010, as=0x0, +read_only=true) at ../hw/core/loader.c:1147 +#3 0x000055aa1cfd788d in acpi_add_rom_blob + (update=0x55aa1d441f59 <acpi_build_update>, opaque=0x55aa20ff0010, +blob=0x55aa1fc9aa00, name=0x55aa1da51f13 "etc/acpi/tables") at ../hw/acpi/utils.c:46 +#4 0x000055aa1d44213f in acpi_setup () at ../hw/i386/acpi-build.c:2720 +#5 0x000055aa1d434199 in pc_machine_done (notifier=0x55aa1ff15050, data=0x0) +at ../hw/i386/pc.c:638 +#6 0x000055aa1d876845 in notifier_list_notify (list=0x55aa1ea25c10 +<machine_init_done_notifiers>, data=0x0) at ../util/notify.c:39 +#7 0x000055aa1d039ee5 in qdev_machine_creation_done () at +../hw/core/machine.c:1749 +#8 0x000055aa1d2c7b3e in qemu_machine_creation_done (errp=0x55aa1ea5cc40 +<error_fatal>) at ../system/vl.c:2779 +#9 0x000055aa1d2c7c7d in qmp_x_exit_preconfig (errp=0x55aa1ea5cc40 +<error_fatal>) at ../system/vl.c:2807 +#10 0x000055aa1d2ca64f in qemu_init (argc=35, argv=0x7fffb82730e8) at +../system/vl.c:3838 +#11 0x000055aa1d79638c in main (argc=35, argv=0x7fffb82730e8) at +../system/main.c:72 +I'm not sure whether ACPI tables ROM in particular is rewritten with the +same content, but there might be cases where ROM can be read from file +system upon initialization. That is undesirable as guest kernel +certainly won't be too happy about sudden change of the device's ROM +content. + +So the issue we're dealing with here is any unwanted memory related +device initialization upon cpr. + +For now the only thing that comes to my mind is to make a test where we +put as many devices as we can into a VM, make ram blocks RO upon cpr +(and remap them as RW later after migration is done, if needed), and +catch any unwanted memory violations. As Den suggested, we might +consider adding that behaviour as a separate non-default option (or +"migrate" command flag specific to cpr-transfer), which would only be +used in the testing. + +Andrey +No way. ACPI with the source must be used in the same way as BIOSes +and optional ROMs. + +Den + +On 3/6/2025 10:52 AM, Denis V. Lunev wrote: +On 3/6/25 16:16, Andrey Drobyshev wrote: +On 3/5/25 11:19 PM, Steven Sistare wrote: +On 3/5/2025 11:50 AM, Andrey Drobyshev wrote: +On 3/4/25 9:05 PM, Steven Sistare wrote: +On 2/28/2025 1:37 PM, Andrey Drobyshev wrote: +On 2/28/25 8:35 PM, Andrey Drobyshev wrote: +On 2/28/25 8:20 PM, Steven Sistare wrote: +On 2/28/2025 1:13 PM, Steven Sistare wrote: +On 2/28/2025 12:39 PM, Andrey Drobyshev wrote: +Hi all, + +We've been experimenting with cpr-transfer migration mode recently +and +have discovered the following issue with the guest QXL driver: + +Run migration source: +EMULATOR=/path/to/emulator +ROOTFS=/path/to/image +QMPSOCK=/var/run/alma8qmp-src.sock + +$EMULATOR -enable-kvm \ +       -machine q35 \ +       -cpu host -smp 2 -m 2G \ +       -object memory-backend-file,id=ram0,size=2G,mem-path=/ +dev/shm/ +ram0,share=on\ +       -machine memory-backend=ram0 \ +       -machine aux-ram-share=on \ +       -drive file=$ROOTFS,media=disk,if=virtio \ +       -qmp unix:$QMPSOCK,server=on,wait=off \ +       -nographic \ +       -device qxl-vga +Run migration target: +EMULATOR=/path/to/emulator +ROOTFS=/path/to/image +QMPSOCK=/var/run/alma8qmp-dst.sock +$EMULATOR -enable-kvm \ +       -machine q35 \ +       -cpu host -smp 2 -m 2G \ +       -object memory-backend-file,id=ram0,size=2G,mem-path=/ +dev/shm/ +ram0,share=on\ +       -machine memory-backend=ram0 \ +       -machine aux-ram-share=on \ +       -drive file=$ROOTFS,media=disk,if=virtio \ +       -qmp unix:$QMPSOCK,server=on,wait=off \ +       -nographic \ +       -device qxl-vga \ +       -incoming tcp:0:44444 \ +       -incoming '{"channel-type": "cpr", "addr": { "transport": +"socket", "type": "unix", "path": "/var/run/alma8cpr-dst.sock"}}' +Launch the migration: +QMPSHELL=/root/src/qemu/master/scripts/qmp/qmp-shell +QMPSOCK=/var/run/alma8qmp-src.sock + +$QMPSHELL -p $QMPSOCK <<EOF +       migrate-set-parameters mode=cpr-transfer +       migrate channels=[{"channel-type":"main","addr": +{"transport":"socket","type":"inet","host":"0","port":"44444"}}, +{"channel-type":"cpr","addr": +{"transport":"socket","type":"unix","path":"/var/run/alma8cpr- +dst.sock"}}] +EOF +Then, after a while, QXL guest driver on target crashes spewing the +following messages: +[  73.962002] [TTM] Buffer eviction failed +[  73.962072] qxl 0000:00:02.0: object_init failed for (3149824, +0x00000001) +[  73.962081] [drm:qxl_alloc_bo_reserved [qxl]] *ERROR* failed to +allocate VRAM BO +That seems to be a known kernel QXL driver bug: +https://lore.kernel.org/all/20220907094423.93581-1- +min_halo@163.com/T/ +https://lore.kernel.org/lkml/ZTgydqRlK6WX_b29@eldamar.lan/ +(the latter discussion contains that reproduce script which +speeds up +the crash in the guest): +#!/bin/bash + +chvt 3 + +for j in $(seq 80); do +           echo "$(date) starting round $j" +           if [ "$(journalctl --boot | grep "failed to allocate +VRAM +BO")" != "" ]; then +                   echo "bug was reproduced after $j tries" +                   exit 1 +           fi +           for i in $(seq 100); do +                   dmesg > /dev/tty3 +           done +done + +echo "bug could not be reproduced" +exit 0 +The bug itself seems to remain unfixed, as I was able to reproduce +that +with Fedora 41 guest, as well as AlmaLinux 8 guest. However our +cpr-transfer code also seems to be buggy as it triggers the crash - +without the cpr-transfer migration the above reproduce doesn't +lead to +crash on the source VM. + +I suspect that, as cpr-transfer doesn't migrate the guest +memory, but +rather passes it through the memory backend object, our code might +somehow corrupt the VRAM. However, I wasn't able to trace the +corruption so far. + +Could somebody help the investigation and take a look into +this? Any +suggestions would be appreciated. Thanks! +Possibly some memory region created by qxl is not being preserved. +Try adding these traces to see what is preserved: + +-trace enable='*cpr*' +-trace enable='*ram_alloc*' +Also try adding this patch to see if it flags any ram blocks as not +compatible with cpr. A message is printed at migration start time. +    +https://lore.kernel.org/qemu-devel/1740667681-257312-1-git-send- +email- +steven.sistare@oracle.com/ + +- Steve +With the traces enabled + the "migration: ram block cpr blockers" +patch +applied: + +Source: +cpr_find_fd pc.bios, id 0 returns -1 +cpr_save_fd pc.bios, id 0, fd 22 +qemu_ram_alloc_shared pc.bios size 262144 max_size 262144 fd 22 host +0x7fec18e00000 +cpr_find_fd pc.rom, id 0 returns -1 +cpr_save_fd pc.rom, id 0, fd 23 +qemu_ram_alloc_shared pc.rom size 131072 max_size 131072 fd 23 host +0x7fec18c00000 +cpr_find_fd 0000:00:01.0/e1000e.rom, id 0 returns -1 +cpr_save_fd 0000:00:01.0/e1000e.rom, id 0, fd 24 +qemu_ram_alloc_shared 0000:00:01.0/e1000e.rom size 262144 max_size +262144 fd 24 host 0x7fec18a00000 +cpr_find_fd 0000:00:02.0/vga.vram, id 0 returns -1 +cpr_save_fd 0000:00:02.0/vga.vram, id 0, fd 25 +qemu_ram_alloc_shared 0000:00:02.0/vga.vram size 67108864 max_size +67108864 fd 25 host 0x7feb77e00000 +cpr_find_fd 0000:00:02.0/qxl.vrom, id 0 returns -1 +cpr_save_fd 0000:00:02.0/qxl.vrom, id 0, fd 27 +qemu_ram_alloc_shared 0000:00:02.0/qxl.vrom size 8192 max_size 8192 +fd 27 host 0x7fec18800000 +cpr_find_fd 0000:00:02.0/qxl.vram, id 0 returns -1 +cpr_save_fd 0000:00:02.0/qxl.vram, id 0, fd 28 +qemu_ram_alloc_shared 0000:00:02.0/qxl.vram size 67108864 max_size +67108864 fd 28 host 0x7feb73c00000 +cpr_find_fd 0000:00:02.0/qxl.rom, id 0 returns -1 +cpr_save_fd 0000:00:02.0/qxl.rom, id 0, fd 34 +qemu_ram_alloc_shared 0000:00:02.0/qxl.rom size 65536 max_size 65536 +fd 34 host 0x7fec18600000 +cpr_find_fd /rom@etc/acpi/tables, id 0 returns -1 +cpr_save_fd /rom@etc/acpi/tables, id 0, fd 35 +qemu_ram_alloc_shared /rom@etc/acpi/tables size 131072 max_size +2097152 fd 35 host 0x7fec18200000 +cpr_find_fd /rom@etc/table-loader, id 0 returns -1 +cpr_save_fd /rom@etc/table-loader, id 0, fd 36 +qemu_ram_alloc_shared /rom@etc/table-loader size 4096 max_size 65536 +fd 36 host 0x7feb8b600000 +cpr_find_fd /rom@etc/acpi/rsdp, id 0 returns -1 +cpr_save_fd /rom@etc/acpi/rsdp, id 0, fd 37 +qemu_ram_alloc_shared /rom@etc/acpi/rsdp size 4096 max_size 4096 fd +37 host 0x7feb8b400000 + +cpr_state_save cpr-transfer mode +cpr_transfer_output /var/run/alma8cpr-dst.sock +Target: +cpr_transfer_input /var/run/alma8cpr-dst.sock +cpr_state_load cpr-transfer mode +cpr_find_fd pc.bios, id 0 returns 20 +qemu_ram_alloc_shared pc.bios size 262144 max_size 262144 fd 20 host +0x7fcdc9800000 +cpr_find_fd pc.rom, id 0 returns 19 +qemu_ram_alloc_shared pc.rom size 131072 max_size 131072 fd 19 host +0x7fcdc9600000 +cpr_find_fd 0000:00:01.0/e1000e.rom, id 0 returns 18 +qemu_ram_alloc_shared 0000:00:01.0/e1000e.rom size 262144 max_size +262144 fd 18 host 0x7fcdc9400000 +cpr_find_fd 0000:00:02.0/vga.vram, id 0 returns 17 +qemu_ram_alloc_shared 0000:00:02.0/vga.vram size 67108864 max_size +67108864 fd 17 host 0x7fcd27e00000 +cpr_find_fd 0000:00:02.0/qxl.vrom, id 0 returns 16 +qemu_ram_alloc_shared 0000:00:02.0/qxl.vrom size 8192 max_size 8192 +fd 16 host 0x7fcdc9200000 +cpr_find_fd 0000:00:02.0/qxl.vram, id 0 returns 15 +qemu_ram_alloc_shared 0000:00:02.0/qxl.vram size 67108864 max_size +67108864 fd 15 host 0x7fcd23c00000 +cpr_find_fd 0000:00:02.0/qxl.rom, id 0 returns 14 +qemu_ram_alloc_shared 0000:00:02.0/qxl.rom size 65536 max_size 65536 +fd 14 host 0x7fcdc8800000 +cpr_find_fd /rom@etc/acpi/tables, id 0 returns 13 +qemu_ram_alloc_shared /rom@etc/acpi/tables size 131072 max_size +2097152 fd 13 host 0x7fcdc8400000 +cpr_find_fd /rom@etc/table-loader, id 0 returns 11 +qemu_ram_alloc_shared /rom@etc/table-loader size 4096 max_size 65536 +fd 11 host 0x7fcdc8200000 +cpr_find_fd /rom@etc/acpi/rsdp, id 0 returns 10 +qemu_ram_alloc_shared /rom@etc/acpi/rsdp size 4096 max_size 4096 fd +10 host 0x7fcd3be00000 +Looks like both vga.vram and qxl.vram are being preserved (with the +same +addresses), and no incompatible ram blocks are found during migration. +Sorry, addressed are not the same, of course. However corresponding +ram +blocks do seem to be preserved and initialized. +So far, I have not reproduced the guest driver failure. + +However, I have isolated places where new QEMU improperly writes to +the qxl memory regions prior to starting the guest, by mmap'ing them +readonly after cpr: + +   qemu_ram_alloc_internal() +     if (reused && (strstr(name, "qxl") || strstr("name", "vga"))) +         ram_flags |= RAM_READONLY; +     new_block = qemu_ram_alloc_from_fd(...) + +I have attached a draft fix; try it and let me know. +My console window looks fine before and after cpr, using +-vnc $hostip:0 -vga qxl + +- Steve +Regarding the reproduce: when I launch the buggy version with the same +options as you, i.e. "-vnc 0.0.0.0:$port -vga qxl", and do cpr-transfer, +my VNC client silently hangs on the target after a while. Could it +happen on your stand as well? +cpr does not preserve the vnc connection and session. To test, I specify +port 0 for the source VM and port 1 for the dest. When the src vnc goes +dormant the dest vnc becomes active. +Sure, I meant that VNC on the dest (on the port 1) works for a while +after the migration and then hangs, apparently after the guest QXL crash. +Could you try launching VM with +"-nographic -device qxl-vga"? That way VM's serial console is given you +directly in the shell, so when qxl driver crashes you're still able to +inspect the kernel messages. +I have been running like that, but have not reproduced the qxl driver +crash, +and I suspect my guest image+kernel is too old. +Yes, that's probably the case. But the crash occurs on my Fedora 41 +guest with the 6.11.5-300.fc41.x86_64 kernel, so newer kernels seem to +be buggy. +However, once I realized the +issue was post-cpr modification of qxl memory, I switched my attention +to the +fix. +As for your patch, I can report that it doesn't resolve the issue as it +is. But I was able to track down another possible memory corruption +using your approach with readonly mmap'ing: +Program terminated with signal SIGSEGV, Segmentation fault. +#0 init_qxl_ram (d=0x5638996e0e70) at ../hw/display/qxl.c:412 +412        d->ram->magic      = cpu_to_le32(QXL_RAM_MAGIC); +[Current thread is 1 (Thread 0x7f1a4f83b480 (LWP 229798))] +(gdb) bt +#0 init_qxl_ram (d=0x5638996e0e70) at ../hw/display/qxl.c:412 +#1 0x0000563896e7f467 in qxl_realize_common (qxl=0x5638996e0e70, +errp=0x7ffd3c2b8170) at ../hw/display/qxl.c:2142 +#2 0x0000563896e7fda1 in qxl_realize_primary (dev=0x5638996e0e70, +errp=0x7ffd3c2b81d0) at ../hw/display/qxl.c:2257 +#3 0x0000563896c7e8f2 in pci_qdev_realize (qdev=0x5638996e0e70, +errp=0x7ffd3c2b8250) at ../hw/pci/pci.c:2174 +#4 0x00005638970eb54b in device_set_realized (obj=0x5638996e0e70, +value=true, errp=0x7ffd3c2b84e0) at ../hw/core/qdev.c:494 +#5 0x00005638970f5e14 in property_set_bool (obj=0x5638996e0e70, +v=0x5638996f3770, name=0x56389759b141 "realized", +opaque=0x5638987893d0, errp=0x7ffd3c2b84e0) +     at ../qom/object.c:2374 +#6 0x00005638970f39f8 in object_property_set (obj=0x5638996e0e70, +name=0x56389759b141 "realized", v=0x5638996f3770, errp=0x7ffd3c2b84e0) +     at ../qom/object.c:1449 +#7 0x00005638970f8586 in object_property_set_qobject +(obj=0x5638996e0e70, name=0x56389759b141 "realized", +value=0x5638996df900, errp=0x7ffd3c2b84e0) +     at ../qom/qom-qobject.c:28 +#8 0x00005638970f3d8d in object_property_set_bool +(obj=0x5638996e0e70, name=0x56389759b141 "realized", value=true, +errp=0x7ffd3c2b84e0) +     at ../qom/object.c:1519 +#9 0x00005638970eacb0 in qdev_realize (dev=0x5638996e0e70, +bus=0x563898cf3c20, errp=0x7ffd3c2b84e0) at ../hw/core/qdev.c:276 +#10 0x0000563896dba675 in qdev_device_add_from_qdict +(opts=0x5638996dfe50, from_json=false, errp=0x7ffd3c2b84e0) at ../ +system/qdev-monitor.c:714 +#11 0x0000563896dba721 in qdev_device_add (opts=0x563898786150, +errp=0x56389855dc40 <error_fatal>) at ../system/qdev-monitor.c:733 +#12 0x0000563896dc48f1 in device_init_func (opaque=0x0, +opts=0x563898786150, errp=0x56389855dc40 <error_fatal>) at ../system/ +vl.c:1207 +#13 0x000056389737a6cc in qemu_opts_foreach +     (list=0x563898427b60 <qemu_device_opts>, func=0x563896dc48ca +<device_init_func>, opaque=0x0, errp=0x56389855dc40 <error_fatal>) +     at ../util/qemu-option.c:1135 +#14 0x0000563896dc89b5 in qemu_create_cli_devices () at ../system/ +vl.c:2745 +#15 0x0000563896dc8c00 in qmp_x_exit_preconfig (errp=0x56389855dc40 +<error_fatal>) at ../system/vl.c:2806 +#16 0x0000563896dcb5de in qemu_init (argc=33, argv=0x7ffd3c2b8948) +at ../system/vl.c:3838 +#17 0x0000563897297323 in main (argc=33, argv=0x7ffd3c2b8948) at ../ +system/main.c:72 +So the attached adjusted version of your patch does seem to help. At +least I can't reproduce the crash on my stand. +Thanks for the stack trace; the calls to SPICE_RING_INIT in init_qxl_ram +are +definitely harmful. Try V2 of the patch, attached, which skips the lines +of init_qxl_ram that modify guest memory. +Thanks, your v2 patch does seem to prevent the crash. Would you re-send +it to the list as a proper fix? +Yes. Was waiting for your confirmation. +I'm wondering, could it be useful to explicitly mark all the reused +memory regions readonly upon cpr-transfer, and then make them writable +back again after the migration is done? That way we will be segfaulting +early on instead of debugging tricky memory corruptions. +It's a useful debugging technique, but changing protection on a large +memory region +can be too expensive for production due to TLB shootdowns. + +Also, there are cases where writes are performed but the value is +guaranteed to +be the same: +  qxl_post_load() +    qxl_set_mode() +      d->rom->mode = cpu_to_le32(modenr); +The value is the same because mode and shadow_rom.mode were passed in +vmstate +from old qemu. +There're also cases where devices' ROM might be re-initialized. E.g. +this segfault occures upon further exploration of RO mapped RAM blocks: +Program terminated with signal SIGSEGV, Segmentation fault. +#0 __memmove_avx_unaligned_erms () at +../sysdeps/x86_64/multiarch/memmove-vec-unaligned-erms.S:664 +664            rep    movsb +[Current thread is 1 (Thread 0x7f6e7d08b480 (LWP 310379))] +(gdb) bt +#0 __memmove_avx_unaligned_erms () at +../sysdeps/x86_64/multiarch/memmove-vec-unaligned-erms.S:664 +#1 0x000055aa1d030ecd in rom_set_mr (rom=0x55aa200ba380, owner=0x55aa2019ac10, +name=0x7fffb8272bc0 "/rom@etc/acpi/tables", ro=true) +    at ../hw/core/loader.c:1032 +#2 0x000055aa1d031577 in rom_add_blob +    (name=0x55aa1da51f13 "etc/acpi/tables", blob=0x55aa208a1070, len=131072, max_len=2097152, +addr=18446744073709551615, fw_file_name=0x55aa1da51f13 "etc/acpi/tables", +fw_callback=0x55aa1d441f59 <acpi_build_update>, callback_opaque=0x55aa20ff0010, as=0x0, +read_only=true) at ../hw/core/loader.c:1147 +#3 0x000055aa1cfd788d in acpi_add_rom_blob +    (update=0x55aa1d441f59 <acpi_build_update>, opaque=0x55aa20ff0010, +blob=0x55aa1fc9aa00, name=0x55aa1da51f13 "etc/acpi/tables") at ../hw/acpi/utils.c:46 +#4 0x000055aa1d44213f in acpi_setup () at ../hw/i386/acpi-build.c:2720 +#5 0x000055aa1d434199 in pc_machine_done (notifier=0x55aa1ff15050, data=0x0) +at ../hw/i386/pc.c:638 +#6 0x000055aa1d876845 in notifier_list_notify (list=0x55aa1ea25c10 +<machine_init_done_notifiers>, data=0x0) at ../util/notify.c:39 +#7 0x000055aa1d039ee5 in qdev_machine_creation_done () at +../hw/core/machine.c:1749 +#8 0x000055aa1d2c7b3e in qemu_machine_creation_done (errp=0x55aa1ea5cc40 +<error_fatal>) at ../system/vl.c:2779 +#9 0x000055aa1d2c7c7d in qmp_x_exit_preconfig (errp=0x55aa1ea5cc40 +<error_fatal>) at ../system/vl.c:2807 +#10 0x000055aa1d2ca64f in qemu_init (argc=35, argv=0x7fffb82730e8) at +../system/vl.c:3838 +#11 0x000055aa1d79638c in main (argc=35, argv=0x7fffb82730e8) at +../system/main.c:72 +I'm not sure whether ACPI tables ROM in particular is rewritten with the +same content, but there might be cases where ROM can be read from file +system upon initialization. That is undesirable as guest kernel +certainly won't be too happy about sudden change of the device's ROM +content. + +So the issue we're dealing with here is any unwanted memory related +device initialization upon cpr. + +For now the only thing that comes to my mind is to make a test where we +put as many devices as we can into a VM, make ram blocks RO upon cpr +(and remap them as RW later after migration is done, if needed), and +catch any unwanted memory violations. As Den suggested, we might +consider adding that behaviour as a separate non-default option (or +"migrate" command flag specific to cpr-transfer), which would only be +used in the testing. +I'll look into adding an option, but there may be too many false positives, +such as the qxl_set_mode case above. And the maintainers may object to me +eliminating the false positives by adding more CPR_IN tests, due to gratuitous +(from their POV) ugliness. + +But I will use the technique to look for more write violations. +Andrey +No way. ACPI with the source must be used in the same way as BIOSes +and optional ROMs. +Yup, its a bug. Will fix. + +- Steve + +see +1741380954-341079-1-git-send-email-steven.sistare@oracle.com +/">https://lore.kernel.org/qemu-devel/ +1741380954-341079-1-git-send-email-steven.sistare@oracle.com +/ +- Steve + +On 3/6/2025 11:13 AM, Steven Sistare wrote: +On 3/6/2025 10:52 AM, Denis V. Lunev wrote: +On 3/6/25 16:16, Andrey Drobyshev wrote: +On 3/5/25 11:19 PM, Steven Sistare wrote: +On 3/5/2025 11:50 AM, Andrey Drobyshev wrote: +On 3/4/25 9:05 PM, Steven Sistare wrote: +On 2/28/2025 1:37 PM, Andrey Drobyshev wrote: +On 2/28/25 8:35 PM, Andrey Drobyshev wrote: +On 2/28/25 8:20 PM, Steven Sistare wrote: +On 2/28/2025 1:13 PM, Steven Sistare wrote: +On 2/28/2025 12:39 PM, Andrey Drobyshev wrote: +Hi all, + +We've been experimenting with cpr-transfer migration mode recently +and +have discovered the following issue with the guest QXL driver: + +Run migration source: +EMULATOR=/path/to/emulator +ROOTFS=/path/to/image +QMPSOCK=/var/run/alma8qmp-src.sock + +$EMULATOR -enable-kvm \ +       -machine q35 \ +       -cpu host -smp 2 -m 2G \ +       -object memory-backend-file,id=ram0,size=2G,mem-path=/ +dev/shm/ +ram0,share=on\ +       -machine memory-backend=ram0 \ +       -machine aux-ram-share=on \ +       -drive file=$ROOTFS,media=disk,if=virtio \ +       -qmp unix:$QMPSOCK,server=on,wait=off \ +       -nographic \ +       -device qxl-vga +Run migration target: +EMULATOR=/path/to/emulator +ROOTFS=/path/to/image +QMPSOCK=/var/run/alma8qmp-dst.sock +$EMULATOR -enable-kvm \ +       -machine q35 \ +       -cpu host -smp 2 -m 2G \ +       -object memory-backend-file,id=ram0,size=2G,mem-path=/ +dev/shm/ +ram0,share=on\ +       -machine memory-backend=ram0 \ +       -machine aux-ram-share=on \ +       -drive file=$ROOTFS,media=disk,if=virtio \ +       -qmp unix:$QMPSOCK,server=on,wait=off \ +       -nographic \ +       -device qxl-vga \ +       -incoming tcp:0:44444 \ +       -incoming '{"channel-type": "cpr", "addr": { "transport": +"socket", "type": "unix", "path": "/var/run/alma8cpr-dst.sock"}}' +Launch the migration: +QMPSHELL=/root/src/qemu/master/scripts/qmp/qmp-shell +QMPSOCK=/var/run/alma8qmp-src.sock + +$QMPSHELL -p $QMPSOCK <<EOF +       migrate-set-parameters mode=cpr-transfer +       migrate channels=[{"channel-type":"main","addr": +{"transport":"socket","type":"inet","host":"0","port":"44444"}}, +{"channel-type":"cpr","addr": +{"transport":"socket","type":"unix","path":"/var/run/alma8cpr- +dst.sock"}}] +EOF +Then, after a while, QXL guest driver on target crashes spewing the +following messages: +[  73.962002] [TTM] Buffer eviction failed +[  73.962072] qxl 0000:00:02.0: object_init failed for (3149824, +0x00000001) +[  73.962081] [drm:qxl_alloc_bo_reserved [qxl]] *ERROR* failed to +allocate VRAM BO +That seems to be a known kernel QXL driver bug: +https://lore.kernel.org/all/20220907094423.93581-1- +min_halo@163.com/T/ +https://lore.kernel.org/lkml/ZTgydqRlK6WX_b29@eldamar.lan/ +(the latter discussion contains that reproduce script which +speeds up +the crash in the guest): +#!/bin/bash + +chvt 3 + +for j in $(seq 80); do +           echo "$(date) starting round $j" +           if [ "$(journalctl --boot | grep "failed to allocate +VRAM +BO")" != "" ]; then +                   echo "bug was reproduced after $j tries" +                   exit 1 +           fi +           for i in $(seq 100); do +                   dmesg > /dev/tty3 +           done +done + +echo "bug could not be reproduced" +exit 0 +The bug itself seems to remain unfixed, as I was able to reproduce +that +with Fedora 41 guest, as well as AlmaLinux 8 guest. However our +cpr-transfer code also seems to be buggy as it triggers the crash - +without the cpr-transfer migration the above reproduce doesn't +lead to +crash on the source VM. + +I suspect that, as cpr-transfer doesn't migrate the guest +memory, but +rather passes it through the memory backend object, our code might +somehow corrupt the VRAM. However, I wasn't able to trace the +corruption so far. + +Could somebody help the investigation and take a look into +this? Any +suggestions would be appreciated. Thanks! +Possibly some memory region created by qxl is not being preserved. +Try adding these traces to see what is preserved: + +-trace enable='*cpr*' +-trace enable='*ram_alloc*' +Also try adding this patch to see if it flags any ram blocks as not +compatible with cpr. A message is printed at migration start time. +    +https://lore.kernel.org/qemu-devel/1740667681-257312-1-git-send- +email- +steven.sistare@oracle.com/ + +- Steve +With the traces enabled + the "migration: ram block cpr blockers" +patch +applied: + +Source: +cpr_find_fd pc.bios, id 0 returns -1 +cpr_save_fd pc.bios, id 0, fd 22 +qemu_ram_alloc_shared pc.bios size 262144 max_size 262144 fd 22 host +0x7fec18e00000 +cpr_find_fd pc.rom, id 0 returns -1 +cpr_save_fd pc.rom, id 0, fd 23 +qemu_ram_alloc_shared pc.rom size 131072 max_size 131072 fd 23 host +0x7fec18c00000 +cpr_find_fd 0000:00:01.0/e1000e.rom, id 0 returns -1 +cpr_save_fd 0000:00:01.0/e1000e.rom, id 0, fd 24 +qemu_ram_alloc_shared 0000:00:01.0/e1000e.rom size 262144 max_size +262144 fd 24 host 0x7fec18a00000 +cpr_find_fd 0000:00:02.0/vga.vram, id 0 returns -1 +cpr_save_fd 0000:00:02.0/vga.vram, id 0, fd 25 +qemu_ram_alloc_shared 0000:00:02.0/vga.vram size 67108864 max_size +67108864 fd 25 host 0x7feb77e00000 +cpr_find_fd 0000:00:02.0/qxl.vrom, id 0 returns -1 +cpr_save_fd 0000:00:02.0/qxl.vrom, id 0, fd 27 +qemu_ram_alloc_shared 0000:00:02.0/qxl.vrom size 8192 max_size 8192 +fd 27 host 0x7fec18800000 +cpr_find_fd 0000:00:02.0/qxl.vram, id 0 returns -1 +cpr_save_fd 0000:00:02.0/qxl.vram, id 0, fd 28 +qemu_ram_alloc_shared 0000:00:02.0/qxl.vram size 67108864 max_size +67108864 fd 28 host 0x7feb73c00000 +cpr_find_fd 0000:00:02.0/qxl.rom, id 0 returns -1 +cpr_save_fd 0000:00:02.0/qxl.rom, id 0, fd 34 +qemu_ram_alloc_shared 0000:00:02.0/qxl.rom size 65536 max_size 65536 +fd 34 host 0x7fec18600000 +cpr_find_fd /rom@etc/acpi/tables, id 0 returns -1 +cpr_save_fd /rom@etc/acpi/tables, id 0, fd 35 +qemu_ram_alloc_shared /rom@etc/acpi/tables size 131072 max_size +2097152 fd 35 host 0x7fec18200000 +cpr_find_fd /rom@etc/table-loader, id 0 returns -1 +cpr_save_fd /rom@etc/table-loader, id 0, fd 36 +qemu_ram_alloc_shared /rom@etc/table-loader size 4096 max_size 65536 +fd 36 host 0x7feb8b600000 +cpr_find_fd /rom@etc/acpi/rsdp, id 0 returns -1 +cpr_save_fd /rom@etc/acpi/rsdp, id 0, fd 37 +qemu_ram_alloc_shared /rom@etc/acpi/rsdp size 4096 max_size 4096 fd +37 host 0x7feb8b400000 + +cpr_state_save cpr-transfer mode +cpr_transfer_output /var/run/alma8cpr-dst.sock +Target: +cpr_transfer_input /var/run/alma8cpr-dst.sock +cpr_state_load cpr-transfer mode +cpr_find_fd pc.bios, id 0 returns 20 +qemu_ram_alloc_shared pc.bios size 262144 max_size 262144 fd 20 host +0x7fcdc9800000 +cpr_find_fd pc.rom, id 0 returns 19 +qemu_ram_alloc_shared pc.rom size 131072 max_size 131072 fd 19 host +0x7fcdc9600000 +cpr_find_fd 0000:00:01.0/e1000e.rom, id 0 returns 18 +qemu_ram_alloc_shared 0000:00:01.0/e1000e.rom size 262144 max_size +262144 fd 18 host 0x7fcdc9400000 +cpr_find_fd 0000:00:02.0/vga.vram, id 0 returns 17 +qemu_ram_alloc_shared 0000:00:02.0/vga.vram size 67108864 max_size +67108864 fd 17 host 0x7fcd27e00000 +cpr_find_fd 0000:00:02.0/qxl.vrom, id 0 returns 16 +qemu_ram_alloc_shared 0000:00:02.0/qxl.vrom size 8192 max_size 8192 +fd 16 host 0x7fcdc9200000 +cpr_find_fd 0000:00:02.0/qxl.vram, id 0 returns 15 +qemu_ram_alloc_shared 0000:00:02.0/qxl.vram size 67108864 max_size +67108864 fd 15 host 0x7fcd23c00000 +cpr_find_fd 0000:00:02.0/qxl.rom, id 0 returns 14 +qemu_ram_alloc_shared 0000:00:02.0/qxl.rom size 65536 max_size 65536 +fd 14 host 0x7fcdc8800000 +cpr_find_fd /rom@etc/acpi/tables, id 0 returns 13 +qemu_ram_alloc_shared /rom@etc/acpi/tables size 131072 max_size +2097152 fd 13 host 0x7fcdc8400000 +cpr_find_fd /rom@etc/table-loader, id 0 returns 11 +qemu_ram_alloc_shared /rom@etc/table-loader size 4096 max_size 65536 +fd 11 host 0x7fcdc8200000 +cpr_find_fd /rom@etc/acpi/rsdp, id 0 returns 10 +qemu_ram_alloc_shared /rom@etc/acpi/rsdp size 4096 max_size 4096 fd +10 host 0x7fcd3be00000 +Looks like both vga.vram and qxl.vram are being preserved (with the +same +addresses), and no incompatible ram blocks are found during migration. +Sorry, addressed are not the same, of course. However corresponding +ram +blocks do seem to be preserved and initialized. +So far, I have not reproduced the guest driver failure. + +However, I have isolated places where new QEMU improperly writes to +the qxl memory regions prior to starting the guest, by mmap'ing them +readonly after cpr: + +   qemu_ram_alloc_internal() +     if (reused && (strstr(name, "qxl") || strstr("name", "vga"))) +         ram_flags |= RAM_READONLY; +     new_block = qemu_ram_alloc_from_fd(...) + +I have attached a draft fix; try it and let me know. +My console window looks fine before and after cpr, using +-vnc $hostip:0 -vga qxl + +- Steve +Regarding the reproduce: when I launch the buggy version with the same +options as you, i.e. "-vnc 0.0.0.0:$port -vga qxl", and do cpr-transfer, +my VNC client silently hangs on the target after a while. Could it +happen on your stand as well? +cpr does not preserve the vnc connection and session. To test, I specify +port 0 for the source VM and port 1 for the dest. When the src vnc goes +dormant the dest vnc becomes active. +Sure, I meant that VNC on the dest (on the port 1) works for a while +after the migration and then hangs, apparently after the guest QXL crash. +Could you try launching VM with +"-nographic -device qxl-vga"? That way VM's serial console is given you +directly in the shell, so when qxl driver crashes you're still able to +inspect the kernel messages. +I have been running like that, but have not reproduced the qxl driver +crash, +and I suspect my guest image+kernel is too old. +Yes, that's probably the case. But the crash occurs on my Fedora 41 +guest with the 6.11.5-300.fc41.x86_64 kernel, so newer kernels seem to +be buggy. +However, once I realized the +issue was post-cpr modification of qxl memory, I switched my attention +to the +fix. +As for your patch, I can report that it doesn't resolve the issue as it +is. But I was able to track down another possible memory corruption +using your approach with readonly mmap'ing: +Program terminated with signal SIGSEGV, Segmentation fault. +#0 init_qxl_ram (d=0x5638996e0e70) at ../hw/display/qxl.c:412 +412        d->ram->magic      = cpu_to_le32(QXL_RAM_MAGIC); +[Current thread is 1 (Thread 0x7f1a4f83b480 (LWP 229798))] +(gdb) bt +#0 init_qxl_ram (d=0x5638996e0e70) at ../hw/display/qxl.c:412 +#1 0x0000563896e7f467 in qxl_realize_common (qxl=0x5638996e0e70, +errp=0x7ffd3c2b8170) at ../hw/display/qxl.c:2142 +#2 0x0000563896e7fda1 in qxl_realize_primary (dev=0x5638996e0e70, +errp=0x7ffd3c2b81d0) at ../hw/display/qxl.c:2257 +#3 0x0000563896c7e8f2 in pci_qdev_realize (qdev=0x5638996e0e70, +errp=0x7ffd3c2b8250) at ../hw/pci/pci.c:2174 +#4 0x00005638970eb54b in device_set_realized (obj=0x5638996e0e70, +value=true, errp=0x7ffd3c2b84e0) at ../hw/core/qdev.c:494 +#5 0x00005638970f5e14 in property_set_bool (obj=0x5638996e0e70, +v=0x5638996f3770, name=0x56389759b141 "realized", +opaque=0x5638987893d0, errp=0x7ffd3c2b84e0) +     at ../qom/object.c:2374 +#6 0x00005638970f39f8 in object_property_set (obj=0x5638996e0e70, +name=0x56389759b141 "realized", v=0x5638996f3770, errp=0x7ffd3c2b84e0) +     at ../qom/object.c:1449 +#7 0x00005638970f8586 in object_property_set_qobject +(obj=0x5638996e0e70, name=0x56389759b141 "realized", +value=0x5638996df900, errp=0x7ffd3c2b84e0) +     at ../qom/qom-qobject.c:28 +#8 0x00005638970f3d8d in object_property_set_bool +(obj=0x5638996e0e70, name=0x56389759b141 "realized", value=true, +errp=0x7ffd3c2b84e0) +     at ../qom/object.c:1519 +#9 0x00005638970eacb0 in qdev_realize (dev=0x5638996e0e70, +bus=0x563898cf3c20, errp=0x7ffd3c2b84e0) at ../hw/core/qdev.c:276 +#10 0x0000563896dba675 in qdev_device_add_from_qdict +(opts=0x5638996dfe50, from_json=false, errp=0x7ffd3c2b84e0) at ../ +system/qdev-monitor.c:714 +#11 0x0000563896dba721 in qdev_device_add (opts=0x563898786150, +errp=0x56389855dc40 <error_fatal>) at ../system/qdev-monitor.c:733 +#12 0x0000563896dc48f1 in device_init_func (opaque=0x0, +opts=0x563898786150, errp=0x56389855dc40 <error_fatal>) at ../system/ +vl.c:1207 +#13 0x000056389737a6cc in qemu_opts_foreach +     (list=0x563898427b60 <qemu_device_opts>, func=0x563896dc48ca +<device_init_func>, opaque=0x0, errp=0x56389855dc40 <error_fatal>) +     at ../util/qemu-option.c:1135 +#14 0x0000563896dc89b5 in qemu_create_cli_devices () at ../system/ +vl.c:2745 +#15 0x0000563896dc8c00 in qmp_x_exit_preconfig (errp=0x56389855dc40 +<error_fatal>) at ../system/vl.c:2806 +#16 0x0000563896dcb5de in qemu_init (argc=33, argv=0x7ffd3c2b8948) +at ../system/vl.c:3838 +#17 0x0000563897297323 in main (argc=33, argv=0x7ffd3c2b8948) at ../ +system/main.c:72 +So the attached adjusted version of your patch does seem to help. At +least I can't reproduce the crash on my stand. +Thanks for the stack trace; the calls to SPICE_RING_INIT in init_qxl_ram +are +definitely harmful. Try V2 of the patch, attached, which skips the lines +of init_qxl_ram that modify guest memory. +Thanks, your v2 patch does seem to prevent the crash. Would you re-send +it to the list as a proper fix? +Yes. Was waiting for your confirmation. +I'm wondering, could it be useful to explicitly mark all the reused +memory regions readonly upon cpr-transfer, and then make them writable +back again after the migration is done? That way we will be segfaulting +early on instead of debugging tricky memory corruptions. +It's a useful debugging technique, but changing protection on a large +memory region +can be too expensive for production due to TLB shootdowns. + +Also, there are cases where writes are performed but the value is +guaranteed to +be the same: +  qxl_post_load() +    qxl_set_mode() +      d->rom->mode = cpu_to_le32(modenr); +The value is the same because mode and shadow_rom.mode were passed in +vmstate +from old qemu. +There're also cases where devices' ROM might be re-initialized. E.g. +this segfault occures upon further exploration of RO mapped RAM blocks: +Program terminated with signal SIGSEGV, Segmentation fault. +#0 __memmove_avx_unaligned_erms () at +../sysdeps/x86_64/multiarch/memmove-vec-unaligned-erms.S:664 +664            rep    movsb +[Current thread is 1 (Thread 0x7f6e7d08b480 (LWP 310379))] +(gdb) bt +#0 __memmove_avx_unaligned_erms () at +../sysdeps/x86_64/multiarch/memmove-vec-unaligned-erms.S:664 +#1 0x000055aa1d030ecd in rom_set_mr (rom=0x55aa200ba380, owner=0x55aa2019ac10, +name=0x7fffb8272bc0 "/rom@etc/acpi/tables", ro=true) +    at ../hw/core/loader.c:1032 +#2 0x000055aa1d031577 in rom_add_blob +    (name=0x55aa1da51f13 "etc/acpi/tables", blob=0x55aa208a1070, len=131072, max_len=2097152, +addr=18446744073709551615, fw_file_name=0x55aa1da51f13 "etc/acpi/tables", +fw_callback=0x55aa1d441f59 <acpi_build_update>, callback_opaque=0x55aa20ff0010, as=0x0, +read_only=true) at ../hw/core/loader.c:1147 +#3 0x000055aa1cfd788d in acpi_add_rom_blob +    (update=0x55aa1d441f59 <acpi_build_update>, opaque=0x55aa20ff0010, +blob=0x55aa1fc9aa00, name=0x55aa1da51f13 "etc/acpi/tables") at ../hw/acpi/utils.c:46 +#4 0x000055aa1d44213f in acpi_setup () at ../hw/i386/acpi-build.c:2720 +#5 0x000055aa1d434199 in pc_machine_done (notifier=0x55aa1ff15050, data=0x0) +at ../hw/i386/pc.c:638 +#6 0x000055aa1d876845 in notifier_list_notify (list=0x55aa1ea25c10 +<machine_init_done_notifiers>, data=0x0) at ../util/notify.c:39 +#7 0x000055aa1d039ee5 in qdev_machine_creation_done () at +../hw/core/machine.c:1749 +#8 0x000055aa1d2c7b3e in qemu_machine_creation_done (errp=0x55aa1ea5cc40 +<error_fatal>) at ../system/vl.c:2779 +#9 0x000055aa1d2c7c7d in qmp_x_exit_preconfig (errp=0x55aa1ea5cc40 +<error_fatal>) at ../system/vl.c:2807 +#10 0x000055aa1d2ca64f in qemu_init (argc=35, argv=0x7fffb82730e8) at +../system/vl.c:3838 +#11 0x000055aa1d79638c in main (argc=35, argv=0x7fffb82730e8) at +../system/main.c:72 +I'm not sure whether ACPI tables ROM in particular is rewritten with the +same content, but there might be cases where ROM can be read from file +system upon initialization. That is undesirable as guest kernel +certainly won't be too happy about sudden change of the device's ROM +content. + +So the issue we're dealing with here is any unwanted memory related +device initialization upon cpr. + +For now the only thing that comes to my mind is to make a test where we +put as many devices as we can into a VM, make ram blocks RO upon cpr +(and remap them as RW later after migration is done, if needed), and +catch any unwanted memory violations. As Den suggested, we might +consider adding that behaviour as a separate non-default option (or +"migrate" command flag specific to cpr-transfer), which would only be +used in the testing. +I'll look into adding an option, but there may be too many false positives, +such as the qxl_set_mode case above. And the maintainers may object to me +eliminating the false positives by adding more CPR_IN tests, due to gratuitous +(from their POV) ugliness. + +But I will use the technique to look for more write violations. +Andrey +No way. ACPI with the source must be used in the same way as BIOSes +and optional ROMs. +Yup, its a bug. Will fix. + +- Steve + diff --git a/results/classifier/001/mistranslation/64322995 b/results/classifier/001/mistranslation/64322995 new file mode 100644 index 000000000..2f16ce872 --- /dev/null +++ b/results/classifier/001/mistranslation/64322995 @@ -0,0 +1,54 @@ +mistranslation: 0.936 +semantic: 0.906 +other: 0.881 +instruction: 0.864 + +[Qemu-devel] [BUG] trace: QEMU hangs on initialization with the "simple" backend + +While starting the softmmu version of QEMU, the simple backend waits for the +writeout thread to signal a condition variable when initializing the output file +path. But since the writeout thread has not been created, it just waits forever. + +Thanks, + Lluis + +On Tue, Feb 09, 2016 at 09:24:04PM +0100, LluÃs Vilanova wrote: +> +While starting the softmmu version of QEMU, the simple backend waits for the +> +writeout thread to signal a condition variable when initializing the output +> +file +> +path. But since the writeout thread has not been created, it just waits +> +forever. +Denis Lunev posted a fix: +https://patchwork.ozlabs.org/patch/580968/ +Stefan +signature.asc +Description: +PGP signature + +Stefan Hajnoczi writes: + +> +On Tue, Feb 09, 2016 at 09:24:04PM +0100, LluÃs Vilanova wrote: +> +> While starting the softmmu version of QEMU, the simple backend waits for the +> +> writeout thread to signal a condition variable when initializing the output +> +> file +> +> path. But since the writeout thread has not been created, it just waits +> +> forever. +> +Denis Lunev posted a fix: +> +https://patchwork.ozlabs.org/patch/580968/ +Great, thanks. + +Lluis + diff --git a/results/classifier/001/mistranslation/70294255 b/results/classifier/001/mistranslation/70294255 new file mode 100644 index 000000000..67353acda --- /dev/null +++ b/results/classifier/001/mistranslation/70294255 @@ -0,0 +1,1061 @@ +mistranslation: 0.862 +semantic: 0.858 +instruction: 0.856 +other: 0.852 + +[Qemu-devel] 答复: Re: 答复: Re: 答复: Re: 答复: Re: [BUG]COLO failover hang + +hi: + +yes.it is better. + +And should we delete + + + + +#ifdef WIN32 + + QIO_CHANNEL(cioc)-ï¼event = CreateEvent(NULL, FALSE, FALSE, NULL) + +#endif + + + + +in qio_channel_socket_acceptï¼ + +qio_channel_socket_new already have it. + + + + + + + + + + + + +åå§é®ä»¶ + + + +åä»¶äººï¼ address@hidden +æ¶ä»¶äººï¼ç广10165992 +æéäººï¼ address@hidden address@hidden address@hidden address@hidden +æ¥ æ ï¼2017å¹´03æ22æ¥ 15:03 +主 é¢ ï¼Re: [Qemu-devel] çå¤: Re: çå¤: Re: çå¤: Re: [BUG]COLO failover hang + + + + + +Hi, + +On 2017/3/22 9:42, address@hidden wrote: +ï¼ diff --git a/migration/socket.c b/migration/socket.c +ï¼ +ï¼ +ï¼ index 13966f1..d65a0ea 100644 +ï¼ +ï¼ +ï¼ --- a/migration/socket.c +ï¼ +ï¼ +ï¼ +++ b/migration/socket.c +ï¼ +ï¼ +ï¼ @@ -147,8 +147,9 @@ static gboolean +socket_accept_incoming_migration(QIOChannel *ioc, +ï¼ +ï¼ +ï¼ } +ï¼ +ï¼ +ï¼ +ï¼ +ï¼ +ï¼ trace_migration_socket_incoming_accepted() +ï¼ +ï¼ +ï¼ +ï¼ +ï¼ +ï¼ qio_channel_set_name(QIO_CHANNEL(sioc), "migration-socket-incoming") +ï¼ +ï¼ +ï¼ + qio_channel_set_feature(QIO_CHANNEL(sioc), QIO_CHANNEL_FEATURE_SHUTDOWN) +ï¼ +ï¼ +ï¼ migration_channel_process_incoming(migrate_get_current(), +ï¼ +ï¼ +ï¼ QIO_CHANNEL(sioc)) +ï¼ +ï¼ +ï¼ object_unref(OBJECT(sioc)) +ï¼ +ï¼ +ï¼ +ï¼ +ï¼ Is this patch ok? +ï¼ + +Yes, i think this works, but a better way maybe to call +qio_channel_set_feature() +in qio_channel_socket_accept(), we didn't set the SHUTDOWN feature for the +socket accept fd, +Or fix it by this: + +diff --git a/io/channel-socket.c b/io/channel-socket.c +index f546c68..ce6894c 100644 +--- a/io/channel-socket.c ++++ b/io/channel-socket.c +@@ -330,9 +330,8 @@ qio_channel_socket_accept(QIOChannelSocket *ioc, + Error **errp) + { + QIOChannelSocket *cioc +- +- cioc = QIO_CHANNEL_SOCKET(object_new(TYPE_QIO_CHANNEL_SOCKET)) +- cioc-ï¼fd = -1 ++ ++ cioc = qio_channel_socket_new() + cioc-ï¼remoteAddrLen = sizeof(ioc-ï¼remoteAddr) + cioc-ï¼localAddrLen = sizeof(ioc-ï¼localAddr) + + +Thanks, +Hailiang + +ï¼ I have test it . The test could not hang any more. +ï¼ +ï¼ +ï¼ +ï¼ +ï¼ +ï¼ +ï¼ +ï¼ +ï¼ +ï¼ +ï¼ +ï¼ +ï¼ åå§é®ä»¶ +ï¼ +ï¼ +ï¼ +ï¼ åä»¶äººï¼ address@hidden +ï¼ æ¶ä»¶äººï¼ address@hidden address@hidden +ï¼ æéäººï¼ address@hidden address@hidden address@hidden +ï¼ æ¥ æ ï¼2017å¹´03æ22æ¥ 09:11 +ï¼ ä¸» é¢ ï¼Re: [Qemu-devel] çå¤: Re: çå¤: Re: [BUG]COLO failover hang +ï¼ +ï¼ +ï¼ +ï¼ +ï¼ +ï¼ On 2017/3/21 19:56, Dr. David Alan Gilbert wrote: +ï¼ ï¼ * Hailiang Zhang (address@hidden) wrote: +ï¼ ï¼ï¼ Hi, +ï¼ ï¼ï¼ +ï¼ ï¼ï¼ Thanks for reporting this, and i confirmed it in my test, and it is a bug. +ï¼ ï¼ï¼ +ï¼ ï¼ï¼ Though we tried to call qemu_file_shutdown() to shutdown the related fd, in +ï¼ ï¼ï¼ case COLO thread/incoming thread is stuck in read/write() while do +failover, +ï¼ ï¼ï¼ but it didn't take effect, because all the fd used by COLO (also migration) +ï¼ ï¼ï¼ has been wrapped by qio channel, and it will not call the shutdown API if +ï¼ ï¼ï¼ we didn't qio_channel_set_feature(QIO_CHANNEL(sioc), +QIO_CHANNEL_FEATURE_SHUTDOWN). +ï¼ ï¼ï¼ +ï¼ ï¼ï¼ Cc: Dr. David Alan Gilbert address@hidden +ï¼ ï¼ï¼ +ï¼ ï¼ï¼ I doubted migration cancel has the same problem, it may be stuck in write() +ï¼ ï¼ï¼ if we tried to cancel migration. +ï¼ ï¼ï¼ +ï¼ ï¼ï¼ void fd_start_outgoing_migration(MigrationState *s, const char *fdname, +Error **errp) +ï¼ ï¼ï¼ { +ï¼ ï¼ï¼ qio_channel_set_name(QIO_CHANNEL(ioc), "migration-fd-outgoing") +ï¼ ï¼ï¼ migration_channel_connect(s, ioc, NULL) +ï¼ ï¼ï¼ ... ... +ï¼ ï¼ï¼ We didn't call qio_channel_set_feature(QIO_CHANNEL(sioc), +QIO_CHANNEL_FEATURE_SHUTDOWN) above, +ï¼ ï¼ï¼ and the +ï¼ ï¼ï¼ migrate_fd_cancel() +ï¼ ï¼ï¼ { +ï¼ ï¼ï¼ ... ... +ï¼ ï¼ï¼ if (s-ï¼state == MIGRATION_STATUS_CANCELLING && f) { +ï¼ ï¼ï¼ qemu_file_shutdown(f) --ï¼ This will not take effect. No ? +ï¼ ï¼ï¼ } +ï¼ ï¼ï¼ } +ï¼ ï¼ +ï¼ ï¼ (cc'd in Daniel Berrange). +ï¼ ï¼ I see that we call qio_channel_set_feature(ioc, +QIO_CHANNEL_FEATURE_SHUTDOWN) at the +ï¼ ï¼ top of qio_channel_socket_new so I think that's safe isn't it? +ï¼ ï¼ +ï¼ +ï¼ Hmm, you are right, this problem is only exist for the migration incoming fd, +thanks. +ï¼ +ï¼ ï¼ Dave +ï¼ ï¼ +ï¼ ï¼ï¼ Thanks, +ï¼ ï¼ï¼ Hailiang +ï¼ ï¼ï¼ +ï¼ ï¼ï¼ On 2017/3/21 16:10, address@hidden wrote: +ï¼ ï¼ï¼ï¼ Thank youã +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ I have test areadyã +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ When the Primary Node panic,the Secondary Node qemu hang at the same +placeã +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ Incorrding +http://wiki.qemu-project.org/Features/COLO +ï¼kill Primary Node +qemu will not produce the problem,but Primary Node panic canã +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ I think due to the feature of channel does not support +QIO_CHANNEL_FEATURE_SHUTDOWN. +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ when failover,channel_shutdown could not shut down the channel. +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ so the colo_process_incoming_thread will hang at recvmsg. +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ I test a patch: +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ diff --git a/migration/socket.c b/migration/socket.c +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ index 13966f1..d65a0ea 100644 +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ --- a/migration/socket.c +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ +++ b/migration/socket.c +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ @@ -147,8 +147,9 @@ static gboolean +socket_accept_incoming_migration(QIOChannel *ioc, +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ } +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ trace_migration_socket_incoming_accepted() +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ qio_channel_set_name(QIO_CHANNEL(sioc), +"migration-socket-incoming") +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ + qio_channel_set_feature(QIO_CHANNEL(sioc), +QIO_CHANNEL_FEATURE_SHUTDOWN) +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ migration_channel_process_incoming(migrate_get_current(), +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ QIO_CHANNEL(sioc)) +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ object_unref(OBJECT(sioc)) +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ My test will not hang any more. +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ åå§é®ä»¶ +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ åä»¶äººï¼ address@hidden +ï¼ ï¼ï¼ï¼ æ¶ä»¶äººï¼ç广10165992 address@hidden +ï¼ ï¼ï¼ï¼ æéäººï¼ address@hidden address@hidden +ï¼ ï¼ï¼ï¼ æ¥ æ ï¼2017å¹´03æ21æ¥ 15:58 +ï¼ ï¼ï¼ï¼ 主 é¢ ï¼Re: [Qemu-devel] çå¤: Re: [BUG]COLO failover hang +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ Hi,Wang. +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ You can test this branch: +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ +https://github.com/coloft/qemu/tree/colo-v5.1-developing-COLO-frame-v21-with-shared-disk +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ and please follow wiki ensure your own configuration correctly. +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ +http://wiki.qemu-project.org/Features/COLO +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ Thanks +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ Zhang Chen +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ On 03/21/2017 03:27 PM, address@hidden wrote: +ï¼ ï¼ï¼ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ hi. +ï¼ ï¼ï¼ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ I test the git qemu master have the same problem. +ï¼ ï¼ï¼ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ (gdb) bt +ï¼ ï¼ï¼ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ #0 qio_channel_socket_readv (ioc=0x7f65911b4e50, iov=0x7f64ef3fd880, +ï¼ ï¼ï¼ï¼ ï¼ niov=1, fds=0x0, nfds=0x0, errp=0x0) at io/channel-socket.c:461 +ï¼ ï¼ï¼ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ #1 0x00007f658e4aa0c2 in qio_channel_read +ï¼ ï¼ï¼ï¼ ï¼ (address@hidden, address@hidden "", +ï¼ ï¼ï¼ï¼ ï¼ address@hidden, address@hidden) at io/channel.c:114 +ï¼ ï¼ï¼ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ #2 0x00007f658e3ea990 in channel_get_buffer (opaque=ï¼optimized outï¼, +ï¼ ï¼ï¼ï¼ ï¼ buf=0x7f65907cb838 "", pos=ï¼optimized outï¼, size=32768) at +ï¼ ï¼ï¼ï¼ ï¼ migration/qemu-file-channel.c:78 +ï¼ ï¼ï¼ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ #3 0x00007f658e3e97fc in qemu_fill_buffer (f=0x7f65907cb800) at +ï¼ ï¼ï¼ï¼ ï¼ migration/qemu-file.c:295 +ï¼ ï¼ï¼ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ #4 0x00007f658e3ea2e1 in qemu_peek_byte (address@hidden, +ï¼ ï¼ï¼ï¼ ï¼ address@hidden) at migration/qemu-file.c:555 +ï¼ ï¼ï¼ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ #5 0x00007f658e3ea34b in qemu_get_byte (address@hidden) at +ï¼ ï¼ï¼ï¼ ï¼ migration/qemu-file.c:568 +ï¼ ï¼ï¼ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ #6 0x00007f658e3ea552 in qemu_get_be32 (address@hidden) at +ï¼ ï¼ï¼ï¼ ï¼ migration/qemu-file.c:648 +ï¼ ï¼ï¼ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ #7 0x00007f658e3e66e5 in colo_receive_message (f=0x7f65907cb800, +ï¼ ï¼ï¼ï¼ ï¼ address@hidden) at migration/colo.c:244 +ï¼ ï¼ï¼ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ #8 0x00007f658e3e681e in colo_receive_check_message (f=ï¼optimized +ï¼ ï¼ï¼ï¼ ï¼ outï¼, address@hidden, +ï¼ ï¼ï¼ï¼ ï¼ address@hidden) +ï¼ ï¼ï¼ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ at migration/colo.c:264 +ï¼ ï¼ï¼ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ #9 0x00007f658e3e740e in colo_process_incoming_thread +ï¼ ï¼ï¼ï¼ ï¼ (opaque=0x7f658eb30360 ï¼mis_current.31286ï¼) at migration/colo.c:577 +ï¼ ï¼ï¼ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ #10 0x00007f658be09df3 in start_thread () from /lib64/libpthread.so.0 +ï¼ ï¼ï¼ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ #11 0x00007f65881983ed in clone () from /lib64/libc.so.6 +ï¼ ï¼ï¼ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ (gdb) p ioc-ï¼name +ï¼ ï¼ï¼ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ $2 = 0x7f658ff7d5c0 "migration-socket-incoming" +ï¼ ï¼ï¼ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ (gdb) p ioc-ï¼features Do not support QIO_CHANNEL_FEATURE_SHUTDOWN +ï¼ ï¼ï¼ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ $3 = 0 +ï¼ ï¼ï¼ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ (gdb) bt +ï¼ ï¼ï¼ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ #0 socket_accept_incoming_migration (ioc=0x7fdcceeafa90, +ï¼ ï¼ï¼ï¼ ï¼ condition=G_IO_IN, opaque=0x7fdcceeafa90) at migration/socket.c:137 +ï¼ ï¼ï¼ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ #1 0x00007fdcc6966350 in g_main_dispatch (context=ï¼optimized outï¼) at +ï¼ ï¼ï¼ï¼ ï¼ gmain.c:3054 +ï¼ ï¼ï¼ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ #2 g_main_context_dispatch (context=ï¼optimized outï¼, +ï¼ ï¼ï¼ï¼ ï¼ address@hidden) at gmain.c:3630 +ï¼ ï¼ï¼ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ #3 0x00007fdccb8a6dcc in glib_pollfds_poll () at util/main-loop.c:213 +ï¼ ï¼ï¼ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ #4 os_host_main_loop_wait (timeout=ï¼optimized outï¼) at +ï¼ ï¼ï¼ï¼ ï¼ util/main-loop.c:258 +ï¼ ï¼ï¼ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ #5 main_loop_wait (address@hidden) at +ï¼ ï¼ï¼ï¼ ï¼ util/main-loop.c:506 +ï¼ ï¼ï¼ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ #6 0x00007fdccb526187 in main_loop () at vl.c:1898 +ï¼ ï¼ï¼ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ #7 main (argc=ï¼optimized outï¼, argv=ï¼optimized outï¼, envp=ï¼optimized +ï¼ ï¼ï¼ï¼ ï¼ outï¼) at vl.c:4709 +ï¼ ï¼ï¼ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ (gdb) p ioc-ï¼features +ï¼ ï¼ï¼ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ $1 = 6 +ï¼ ï¼ï¼ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ (gdb) p ioc-ï¼name +ï¼ ï¼ï¼ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ $2 = 0x7fdcce1b1ab0 "migration-socket-listener" +ï¼ ï¼ï¼ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ May be socket_accept_incoming_migration should +ï¼ ï¼ï¼ï¼ ï¼ call qio_channel_set_feature(ioc, QIO_CHANNEL_FEATURE_SHUTDOWN)?? +ï¼ ï¼ï¼ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ thank you. +ï¼ ï¼ï¼ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ åå§é®ä»¶ +ï¼ ï¼ï¼ï¼ ï¼ address@hidden +ï¼ ï¼ï¼ï¼ ï¼ address@hidden +ï¼ ï¼ï¼ï¼ ï¼ address@hidden@huawei.comï¼ +ï¼ ï¼ï¼ï¼ ï¼ *æ¥ æ ï¼*2017å¹´03æ16æ¥ 14:46 +ï¼ ï¼ï¼ï¼ ï¼ *主 é¢ ï¼**Re: [Qemu-devel] COLO failover hang* +ï¼ ï¼ï¼ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ On 03/15/2017 05:06 PM, wangguang wrote: +ï¼ ï¼ï¼ï¼ ï¼ ï¼ am testing QEMU COLO feature described here [QEMU +ï¼ ï¼ï¼ï¼ ï¼ ï¼ Wiki]( +http://wiki.qemu-project.org/Features/COLO +). +ï¼ ï¼ï¼ï¼ ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ ï¼ When the Primary Node panic,the Secondary Node qemu hang. +ï¼ ï¼ï¼ï¼ ï¼ ï¼ hang at recvmsg in qio_channel_socket_readv. +ï¼ ï¼ï¼ï¼ ï¼ ï¼ And I run { 'execute': 'nbd-server-stop' } and { "execute": +ï¼ ï¼ï¼ï¼ ï¼ ï¼ "x-colo-lost-heartbeat" } in Secondary VM's +ï¼ ï¼ï¼ï¼ ï¼ ï¼ monitor,the Secondary Node qemu still hang at recvmsg . +ï¼ ï¼ï¼ï¼ ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ ï¼ I found that the colo in qemu is not complete yet. +ï¼ ï¼ï¼ï¼ ï¼ ï¼ Do the colo have any plan for development? +ï¼ ï¼ï¼ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ Yes, We are developing. You can see some of patch we pushing. +ï¼ ï¼ï¼ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ ï¼ Has anyone ever run it successfully? Any help is appreciated! +ï¼ ï¼ï¼ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ In our internal version can run it successfully, +ï¼ ï¼ï¼ï¼ ï¼ The failover detail you can ask Zhanghailiang for help. +ï¼ ï¼ï¼ï¼ ï¼ Next time if you have some question about COLO, +ï¼ ï¼ï¼ï¼ ï¼ please cc me and zhanghailiang address@hidden +ï¼ ï¼ï¼ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ Thanks +ï¼ ï¼ï¼ï¼ ï¼ Zhang Chen +ï¼ ï¼ï¼ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ ï¼ centos7.2+qemu2.7.50 +ï¼ ï¼ï¼ï¼ ï¼ ï¼ (gdb) bt +ï¼ ï¼ï¼ï¼ ï¼ ï¼ #0 0x00007f3e00cc86ad in recvmsg () from /lib64/libpthread.so.0 +ï¼ ï¼ï¼ï¼ ï¼ ï¼ #1 0x00007f3e0332b738 in qio_channel_socket_readv (ioc=ï¼optimized +outï¼, +ï¼ ï¼ï¼ï¼ ï¼ ï¼ iov=ï¼optimized outï¼, niov=ï¼optimized outï¼, fds=0x0, nfds=0x0, +errp=0x0) at +ï¼ ï¼ï¼ï¼ ï¼ ï¼ io/channel-socket.c:497 +ï¼ ï¼ï¼ï¼ ï¼ ï¼ #2 0x00007f3e03329472 in qio_channel_read (address@hidden, +ï¼ ï¼ï¼ï¼ ï¼ ï¼ address@hidden "", address@hidden, +ï¼ ï¼ï¼ï¼ ï¼ ï¼ address@hidden) at io/channel.c:97 +ï¼ ï¼ï¼ï¼ ï¼ ï¼ #3 0x00007f3e032750e0 in channel_get_buffer (opaque=ï¼optimized outï¼, +ï¼ ï¼ï¼ï¼ ï¼ ï¼ buf=0x7f3e05910f38 "", pos=ï¼optimized outï¼, size=32768) at +ï¼ ï¼ï¼ï¼ ï¼ ï¼ migration/qemu-file-channel.c:78 +ï¼ ï¼ï¼ï¼ ï¼ ï¼ #4 0x00007f3e0327412c in qemu_fill_buffer (f=0x7f3e05910f00) at +ï¼ ï¼ï¼ï¼ ï¼ ï¼ migration/qemu-file.c:257 +ï¼ ï¼ï¼ï¼ ï¼ ï¼ #5 0x00007f3e03274a41 in qemu_peek_byte (address@hidden, +ï¼ ï¼ï¼ï¼ ï¼ ï¼ address@hidden) at migration/qemu-file.c:510 +ï¼ ï¼ï¼ï¼ ï¼ ï¼ #6 0x00007f3e03274aab in qemu_get_byte (address@hidden) at +ï¼ ï¼ï¼ï¼ ï¼ ï¼ migration/qemu-file.c:523 +ï¼ ï¼ï¼ï¼ ï¼ ï¼ #7 0x00007f3e03274cb2 in qemu_get_be32 (address@hidden) at +ï¼ ï¼ï¼ï¼ ï¼ ï¼ migration/qemu-file.c:603 +ï¼ ï¼ï¼ï¼ ï¼ ï¼ #8 0x00007f3e03271735 in colo_receive_message (f=0x7f3e05910f00, +ï¼ ï¼ï¼ï¼ ï¼ ï¼ address@hidden) at migration/colo.c:215 +ï¼ ï¼ï¼ï¼ ï¼ ï¼ #9 0x00007f3e0327250d in colo_wait_handle_message +(errp=0x7f3d62bfaa48, +ï¼ ï¼ï¼ï¼ ï¼ ï¼ checkpoint_request=ï¼synthetic pointerï¼, f=ï¼optimized outï¼) at +ï¼ ï¼ï¼ï¼ ï¼ ï¼ migration/colo.c:546 +ï¼ ï¼ï¼ï¼ ï¼ ï¼ #10 colo_process_incoming_thread (opaque=0x7f3e067245e0) at +ï¼ ï¼ï¼ï¼ ï¼ ï¼ migration/colo.c:649 +ï¼ ï¼ï¼ï¼ ï¼ ï¼ #11 0x00007f3e00cc1df3 in start_thread () from /lib64/libpthread.so.0 +ï¼ ï¼ï¼ï¼ ï¼ ï¼ #12 0x00007f3dfc9c03ed in clone () from /lib64/libc..so.6 +ï¼ ï¼ï¼ï¼ ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ ï¼ -- +ï¼ ï¼ï¼ï¼ ï¼ ï¼ View this message in context: +http://qemu.11.n7.nabble.com/COLO-failover-hang-tp473250.html +ï¼ ï¼ï¼ï¼ ï¼ ï¼ Sent from the Developer mailing list archive at Nabble.com. +ï¼ ï¼ï¼ï¼ ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ -- +ï¼ ï¼ï¼ï¼ ï¼ Thanks +ï¼ ï¼ï¼ï¼ ï¼ Zhang Chen +ï¼ ï¼ï¼ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ +ï¼ ï¼ -- +ï¼ ï¼ Dr. David Alan Gilbert / address@hidden / Manchester, UK +ï¼ ï¼ +ï¼ ï¼ . +ï¼ ï¼ +ï¼ + +On 2017/3/22 16:09, address@hidden wrote: +hi: + +yes.it is better. + +And should we delete +Yes, you are right. +#ifdef WIN32 + + QIO_CHANNEL(cioc)-ï¼event = CreateEvent(NULL, FALSE, FALSE, NULL) + +#endif + + + + +in qio_channel_socket_acceptï¼ + +qio_channel_socket_new already have it. + + + + + + + + + + + + +åå§é®ä»¶ + + + +åä»¶äººï¼ address@hidden +æ¶ä»¶äººï¼ç广10165992 +æéäººï¼ address@hidden address@hidden address@hidden address@hidden +æ¥ æ ï¼2017å¹´03æ22æ¥ 15:03 +主 é¢ ï¼Re: [Qemu-devel] çå¤: Re: çå¤: Re: çå¤: Re: [BUG]COLO failover hang + + + + + +Hi, + +On 2017/3/22 9:42, address@hidden wrote: +ï¼ diff --git a/migration/socket.c b/migration/socket.c +ï¼ +ï¼ +ï¼ index 13966f1..d65a0ea 100644 +ï¼ +ï¼ +ï¼ --- a/migration/socket.c +ï¼ +ï¼ +ï¼ +++ b/migration/socket.c +ï¼ +ï¼ +ï¼ @@ -147,8 +147,9 @@ static gboolean +socket_accept_incoming_migration(QIOChannel *ioc, +ï¼ +ï¼ +ï¼ } +ï¼ +ï¼ +ï¼ +ï¼ +ï¼ +ï¼ trace_migration_socket_incoming_accepted() +ï¼ +ï¼ +ï¼ +ï¼ +ï¼ +ï¼ qio_channel_set_name(QIO_CHANNEL(sioc), "migration-socket-incoming") +ï¼ +ï¼ +ï¼ + qio_channel_set_feature(QIO_CHANNEL(sioc), QIO_CHANNEL_FEATURE_SHUTDOWN) +ï¼ +ï¼ +ï¼ migration_channel_process_incoming(migrate_get_current(), +ï¼ +ï¼ +ï¼ QIO_CHANNEL(sioc)) +ï¼ +ï¼ +ï¼ object_unref(OBJECT(sioc)) +ï¼ +ï¼ +ï¼ +ï¼ +ï¼ Is this patch ok? +ï¼ + +Yes, i think this works, but a better way maybe to call +qio_channel_set_feature() +in qio_channel_socket_accept(), we didn't set the SHUTDOWN feature for the +socket accept fd, +Or fix it by this: + +diff --git a/io/channel-socket.c b/io/channel-socket.c +index f546c68..ce6894c 100644 +--- a/io/channel-socket.c ++++ b/io/channel-socket.c +@@ -330,9 +330,8 @@ qio_channel_socket_accept(QIOChannelSocket *ioc, + Error **errp) + { + QIOChannelSocket *cioc +- +- cioc = QIO_CHANNEL_SOCKET(object_new(TYPE_QIO_CHANNEL_SOCKET)) +- cioc-ï¼fd = -1 ++ ++ cioc = qio_channel_socket_new() + cioc-ï¼remoteAddrLen = sizeof(ioc-ï¼remoteAddr) + cioc-ï¼localAddrLen = sizeof(ioc-ï¼localAddr) + + +Thanks, +Hailiang + +ï¼ I have test it . The test could not hang any more. +ï¼ +ï¼ +ï¼ +ï¼ +ï¼ +ï¼ +ï¼ +ï¼ +ï¼ +ï¼ +ï¼ +ï¼ +ï¼ åå§é®ä»¶ +ï¼ +ï¼ +ï¼ +ï¼ åä»¶äººï¼ address@hidden +ï¼ æ¶ä»¶äººï¼ address@hidden address@hidden +ï¼ æéäººï¼ address@hidden address@hidden address@hidden +ï¼ æ¥ æ ï¼2017å¹´03æ22æ¥ 09:11 +ï¼ ä¸» é¢ ï¼Re: [Qemu-devel] çå¤: Re: çå¤: Re: [BUG]COLO failover hang +ï¼ +ï¼ +ï¼ +ï¼ +ï¼ +ï¼ On 2017/3/21 19:56, Dr. David Alan Gilbert wrote: +ï¼ ï¼ * Hailiang Zhang (address@hidden) wrote: +ï¼ ï¼ï¼ Hi, +ï¼ ï¼ï¼ +ï¼ ï¼ï¼ Thanks for reporting this, and i confirmed it in my test, and it is a bug. +ï¼ ï¼ï¼ +ï¼ ï¼ï¼ Though we tried to call qemu_file_shutdown() to shutdown the related fd, in +ï¼ ï¼ï¼ case COLO thread/incoming thread is stuck in read/write() while do +failover, +ï¼ ï¼ï¼ but it didn't take effect, because all the fd used by COLO (also migration) +ï¼ ï¼ï¼ has been wrapped by qio channel, and it will not call the shutdown API if +ï¼ ï¼ï¼ we didn't qio_channel_set_feature(QIO_CHANNEL(sioc), +QIO_CHANNEL_FEATURE_SHUTDOWN). +ï¼ ï¼ï¼ +ï¼ ï¼ï¼ Cc: Dr. David Alan Gilbert address@hidden +ï¼ ï¼ï¼ +ï¼ ï¼ï¼ I doubted migration cancel has the same problem, it may be stuck in write() +ï¼ ï¼ï¼ if we tried to cancel migration. +ï¼ ï¼ï¼ +ï¼ ï¼ï¼ void fd_start_outgoing_migration(MigrationState *s, const char *fdname, +Error **errp) +ï¼ ï¼ï¼ { +ï¼ ï¼ï¼ qio_channel_set_name(QIO_CHANNEL(ioc), "migration-fd-outgoing") +ï¼ ï¼ï¼ migration_channel_connect(s, ioc, NULL) +ï¼ ï¼ï¼ ... ... +ï¼ ï¼ï¼ We didn't call qio_channel_set_feature(QIO_CHANNEL(sioc), +QIO_CHANNEL_FEATURE_SHUTDOWN) above, +ï¼ ï¼ï¼ and the +ï¼ ï¼ï¼ migrate_fd_cancel() +ï¼ ï¼ï¼ { +ï¼ ï¼ï¼ ... ... +ï¼ ï¼ï¼ if (s-ï¼state == MIGRATION_STATUS_CANCELLING && f) { +ï¼ ï¼ï¼ qemu_file_shutdown(f) --ï¼ This will not take effect. No ? +ï¼ ï¼ï¼ } +ï¼ ï¼ï¼ } +ï¼ ï¼ +ï¼ ï¼ (cc'd in Daniel Berrange). +ï¼ ï¼ I see that we call qio_channel_set_feature(ioc, +QIO_CHANNEL_FEATURE_SHUTDOWN) at the +ï¼ ï¼ top of qio_channel_socket_new so I think that's safe isn't it? +ï¼ ï¼ +ï¼ +ï¼ Hmm, you are right, this problem is only exist for the migration incoming fd, +thanks. +ï¼ +ï¼ ï¼ Dave +ï¼ ï¼ +ï¼ ï¼ï¼ Thanks, +ï¼ ï¼ï¼ Hailiang +ï¼ ï¼ï¼ +ï¼ ï¼ï¼ On 2017/3/21 16:10, address@hidden wrote: +ï¼ ï¼ï¼ï¼ Thank youã +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ I have test areadyã +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ When the Primary Node panic,the Secondary Node qemu hang at the same +placeã +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ Incorrding +http://wiki.qemu-project.org/Features/COLO +ï¼kill Primary Node +qemu will not produce the problem,but Primary Node panic canã +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ I think due to the feature of channel does not support +QIO_CHANNEL_FEATURE_SHUTDOWN. +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ when failover,channel_shutdown could not shut down the channel. +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ so the colo_process_incoming_thread will hang at recvmsg. +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ I test a patch: +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ diff --git a/migration/socket.c b/migration/socket.c +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ index 13966f1..d65a0ea 100644 +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ --- a/migration/socket.c +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ +++ b/migration/socket.c +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ @@ -147,8 +147,9 @@ static gboolean +socket_accept_incoming_migration(QIOChannel *ioc, +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ } +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ trace_migration_socket_incoming_accepted() +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ qio_channel_set_name(QIO_CHANNEL(sioc), +"migration-socket-incoming") +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ + qio_channel_set_feature(QIO_CHANNEL(sioc), +QIO_CHANNEL_FEATURE_SHUTDOWN) +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ migration_channel_process_incoming(migrate_get_current(), +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ QIO_CHANNEL(sioc)) +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ object_unref(OBJECT(sioc)) +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ My test will not hang any more. +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ åå§é®ä»¶ +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ åä»¶äººï¼ address@hidden +ï¼ ï¼ï¼ï¼ æ¶ä»¶äººï¼ç广10165992 address@hidden +ï¼ ï¼ï¼ï¼ æéäººï¼ address@hidden address@hidden +ï¼ ï¼ï¼ï¼ æ¥ æ ï¼2017å¹´03æ21æ¥ 15:58 +ï¼ ï¼ï¼ï¼ 主 é¢ ï¼Re: [Qemu-devel] çå¤: Re: [BUG]COLO failover hang +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ Hi,Wang. +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ You can test this branch: +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ +https://github.com/coloft/qemu/tree/colo-v5.1-developing-COLO-frame-v21-with-shared-disk +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ and please follow wiki ensure your own configuration correctly. +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ +http://wiki.qemu-project.org/Features/COLO +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ Thanks +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ Zhang Chen +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ï¼ On 03/21/2017 03:27 PM, address@hidden wrote: +ï¼ ï¼ï¼ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ hi. +ï¼ ï¼ï¼ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ I test the git qemu master have the same problem. +ï¼ ï¼ï¼ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ (gdb) bt +ï¼ ï¼ï¼ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ #0 qio_channel_socket_readv (ioc=0x7f65911b4e50, iov=0x7f64ef3fd880, +ï¼ ï¼ï¼ï¼ ï¼ niov=1, fds=0x0, nfds=0x0, errp=0x0) at io/channel-socket.c:461 +ï¼ ï¼ï¼ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ #1 0x00007f658e4aa0c2 in qio_channel_read +ï¼ ï¼ï¼ï¼ ï¼ (address@hidden, address@hidden "", +ï¼ ï¼ï¼ï¼ ï¼ address@hidden, address@hidden) at io/channel.c:114 +ï¼ ï¼ï¼ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ #2 0x00007f658e3ea990 in channel_get_buffer (opaque=ï¼optimized outï¼, +ï¼ ï¼ï¼ï¼ ï¼ buf=0x7f65907cb838 "", pos=ï¼optimized outï¼, size=32768) at +ï¼ ï¼ï¼ï¼ ï¼ migration/qemu-file-channel.c:78 +ï¼ ï¼ï¼ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ #3 0x00007f658e3e97fc in qemu_fill_buffer (f=0x7f65907cb800) at +ï¼ ï¼ï¼ï¼ ï¼ migration/qemu-file.c:295 +ï¼ ï¼ï¼ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ #4 0x00007f658e3ea2e1 in qemu_peek_byte (address@hidden, +ï¼ ï¼ï¼ï¼ ï¼ address@hidden) at migration/qemu-file.c:555 +ï¼ ï¼ï¼ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ #5 0x00007f658e3ea34b in qemu_get_byte (address@hidden) at +ï¼ ï¼ï¼ï¼ ï¼ migration/qemu-file.c:568 +ï¼ ï¼ï¼ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ #6 0x00007f658e3ea552 in qemu_get_be32 (address@hidden) at +ï¼ ï¼ï¼ï¼ ï¼ migration/qemu-file.c:648 +ï¼ ï¼ï¼ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ #7 0x00007f658e3e66e5 in colo_receive_message (f=0x7f65907cb800, +ï¼ ï¼ï¼ï¼ ï¼ address@hidden) at migration/colo.c:244 +ï¼ ï¼ï¼ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ #8 0x00007f658e3e681e in colo_receive_check_message (f=ï¼optimized +ï¼ ï¼ï¼ï¼ ï¼ outï¼, address@hidden, +ï¼ ï¼ï¼ï¼ ï¼ address@hidden) +ï¼ ï¼ï¼ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ at migration/colo.c:264 +ï¼ ï¼ï¼ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ #9 0x00007f658e3e740e in colo_process_incoming_thread +ï¼ ï¼ï¼ï¼ ï¼ (opaque=0x7f658eb30360 ï¼mis_current.31286ï¼) at migration/colo.c:577 +ï¼ ï¼ï¼ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ #10 0x00007f658be09df3 in start_thread () from /lib64/libpthread.so.0 +ï¼ ï¼ï¼ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ #11 0x00007f65881983ed in clone () from /lib64/libc.so.6 +ï¼ ï¼ï¼ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ (gdb) p ioc-ï¼name +ï¼ ï¼ï¼ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ $2 = 0x7f658ff7d5c0 "migration-socket-incoming" +ï¼ ï¼ï¼ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ (gdb) p ioc-ï¼features Do not support QIO_CHANNEL_FEATURE_SHUTDOWN +ï¼ ï¼ï¼ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ $3 = 0 +ï¼ ï¼ï¼ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ (gdb) bt +ï¼ ï¼ï¼ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ #0 socket_accept_incoming_migration (ioc=0x7fdcceeafa90, +ï¼ ï¼ï¼ï¼ ï¼ condition=G_IO_IN, opaque=0x7fdcceeafa90) at migration/socket.c:137 +ï¼ ï¼ï¼ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ #1 0x00007fdcc6966350 in g_main_dispatch (context=ï¼optimized outï¼) at +ï¼ ï¼ï¼ï¼ ï¼ gmain.c:3054 +ï¼ ï¼ï¼ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ #2 g_main_context_dispatch (context=ï¼optimized outï¼, +ï¼ ï¼ï¼ï¼ ï¼ address@hidden) at gmain.c:3630 +ï¼ ï¼ï¼ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ #3 0x00007fdccb8a6dcc in glib_pollfds_poll () at util/main-loop.c:213 +ï¼ ï¼ï¼ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ #4 os_host_main_loop_wait (timeout=ï¼optimized outï¼) at +ï¼ ï¼ï¼ï¼ ï¼ util/main-loop.c:258 +ï¼ ï¼ï¼ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ #5 main_loop_wait (address@hidden) at +ï¼ ï¼ï¼ï¼ ï¼ util/main-loop.c:506 +ï¼ ï¼ï¼ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ #6 0x00007fdccb526187 in main_loop () at vl.c:1898 +ï¼ ï¼ï¼ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ #7 main (argc=ï¼optimized outï¼, argv=ï¼optimized outï¼, envp=ï¼optimized +ï¼ ï¼ï¼ï¼ ï¼ outï¼) at vl.c:4709 +ï¼ ï¼ï¼ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ (gdb) p ioc-ï¼features +ï¼ ï¼ï¼ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ $1 = 6 +ï¼ ï¼ï¼ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ (gdb) p ioc-ï¼name +ï¼ ï¼ï¼ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ $2 = 0x7fdcce1b1ab0 "migration-socket-listener" +ï¼ ï¼ï¼ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ May be socket_accept_incoming_migration should +ï¼ ï¼ï¼ï¼ ï¼ call qio_channel_set_feature(ioc, QIO_CHANNEL_FEATURE_SHUTDOWN)?? +ï¼ ï¼ï¼ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ thank you. +ï¼ ï¼ï¼ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ åå§é®ä»¶ +ï¼ ï¼ï¼ï¼ ï¼ address@hidden +ï¼ ï¼ï¼ï¼ ï¼ address@hidden +ï¼ ï¼ï¼ï¼ ï¼ address@hidden@huawei.comï¼ +ï¼ ï¼ï¼ï¼ ï¼ *æ¥ æ ï¼*2017å¹´03æ16æ¥ 14:46 +ï¼ ï¼ï¼ï¼ ï¼ *主 é¢ ï¼**Re: [Qemu-devel] COLO failover hang* +ï¼ ï¼ï¼ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ On 03/15/2017 05:06 PM, wangguang wrote: +ï¼ ï¼ï¼ï¼ ï¼ ï¼ am testing QEMU COLO feature described here [QEMU +ï¼ ï¼ï¼ï¼ ï¼ ï¼ Wiki]( +http://wiki.qemu-project.org/Features/COLO +). +ï¼ ï¼ï¼ï¼ ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ ï¼ When the Primary Node panic,the Secondary Node qemu hang. +ï¼ ï¼ï¼ï¼ ï¼ ï¼ hang at recvmsg in qio_channel_socket_readv. +ï¼ ï¼ï¼ï¼ ï¼ ï¼ And I run { 'execute': 'nbd-server-stop' } and { "execute": +ï¼ ï¼ï¼ï¼ ï¼ ï¼ "x-colo-lost-heartbeat" } in Secondary VM's +ï¼ ï¼ï¼ï¼ ï¼ ï¼ monitor,the Secondary Node qemu still hang at recvmsg . +ï¼ ï¼ï¼ï¼ ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ ï¼ I found that the colo in qemu is not complete yet. +ï¼ ï¼ï¼ï¼ ï¼ ï¼ Do the colo have any plan for development? +ï¼ ï¼ï¼ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ Yes, We are developing. You can see some of patch we pushing. +ï¼ ï¼ï¼ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ ï¼ Has anyone ever run it successfully? Any help is appreciated! +ï¼ ï¼ï¼ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ In our internal version can run it successfully, +ï¼ ï¼ï¼ï¼ ï¼ The failover detail you can ask Zhanghailiang for help. +ï¼ ï¼ï¼ï¼ ï¼ Next time if you have some question about COLO, +ï¼ ï¼ï¼ï¼ ï¼ please cc me and zhanghailiang address@hidden +ï¼ ï¼ï¼ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ Thanks +ï¼ ï¼ï¼ï¼ ï¼ Zhang Chen +ï¼ ï¼ï¼ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ ï¼ centos7.2+qemu2.7.50 +ï¼ ï¼ï¼ï¼ ï¼ ï¼ (gdb) bt +ï¼ ï¼ï¼ï¼ ï¼ ï¼ #0 0x00007f3e00cc86ad in recvmsg () from /lib64/libpthread.so.0 +ï¼ ï¼ï¼ï¼ ï¼ ï¼ #1 0x00007f3e0332b738 in qio_channel_socket_readv (ioc=ï¼optimized +outï¼, +ï¼ ï¼ï¼ï¼ ï¼ ï¼ iov=ï¼optimized outï¼, niov=ï¼optimized outï¼, fds=0x0, nfds=0x0, +errp=0x0) at +ï¼ ï¼ï¼ï¼ ï¼ ï¼ io/channel-socket.c:497 +ï¼ ï¼ï¼ï¼ ï¼ ï¼ #2 0x00007f3e03329472 in qio_channel_read (address@hidden, +ï¼ ï¼ï¼ï¼ ï¼ ï¼ address@hidden "", address@hidden, +ï¼ ï¼ï¼ï¼ ï¼ ï¼ address@hidden) at io/channel.c:97 +ï¼ ï¼ï¼ï¼ ï¼ ï¼ #3 0x00007f3e032750e0 in channel_get_buffer (opaque=ï¼optimized outï¼, +ï¼ ï¼ï¼ï¼ ï¼ ï¼ buf=0x7f3e05910f38 "", pos=ï¼optimized outï¼, size=32768) at +ï¼ ï¼ï¼ï¼ ï¼ ï¼ migration/qemu-file-channel.c:78 +ï¼ ï¼ï¼ï¼ ï¼ ï¼ #4 0x00007f3e0327412c in qemu_fill_buffer (f=0x7f3e05910f00) at +ï¼ ï¼ï¼ï¼ ï¼ ï¼ migration/qemu-file.c:257 +ï¼ ï¼ï¼ï¼ ï¼ ï¼ #5 0x00007f3e03274a41 in qemu_peek_byte (address@hidden, +ï¼ ï¼ï¼ï¼ ï¼ ï¼ address@hidden) at migration/qemu-file.c:510 +ï¼ ï¼ï¼ï¼ ï¼ ï¼ #6 0x00007f3e03274aab in qemu_get_byte (address@hidden) at +ï¼ ï¼ï¼ï¼ ï¼ ï¼ migration/qemu-file.c:523 +ï¼ ï¼ï¼ï¼ ï¼ ï¼ #7 0x00007f3e03274cb2 in qemu_get_be32 (address@hidden) at +ï¼ ï¼ï¼ï¼ ï¼ ï¼ migration/qemu-file.c:603 +ï¼ ï¼ï¼ï¼ ï¼ ï¼ #8 0x00007f3e03271735 in colo_receive_message (f=0x7f3e05910f00, +ï¼ ï¼ï¼ï¼ ï¼ ï¼ address@hidden) at migration/colo.c:215 +ï¼ ï¼ï¼ï¼ ï¼ ï¼ #9 0x00007f3e0327250d in colo_wait_handle_message +(errp=0x7f3d62bfaa48, +ï¼ ï¼ï¼ï¼ ï¼ ï¼ checkpoint_request=ï¼synthetic pointerï¼, f=ï¼optimized outï¼) at +ï¼ ï¼ï¼ï¼ ï¼ ï¼ migration/colo.c:546 +ï¼ ï¼ï¼ï¼ ï¼ ï¼ #10 colo_process_incoming_thread (opaque=0x7f3e067245e0) at +ï¼ ï¼ï¼ï¼ ï¼ ï¼ migration/colo.c:649 +ï¼ ï¼ï¼ï¼ ï¼ ï¼ #11 0x00007f3e00cc1df3 in start_thread () from /lib64/libpthread.so.0 +ï¼ ï¼ï¼ï¼ ï¼ ï¼ #12 0x00007f3dfc9c03ed in clone () from /lib64/libc..so.6 +ï¼ ï¼ï¼ï¼ ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ ï¼ -- +ï¼ ï¼ï¼ï¼ ï¼ ï¼ View this message in context: +http://qemu.11.n7.nabble.com/COLO-failover-hang-tp473250.html +ï¼ ï¼ï¼ï¼ ï¼ ï¼ Sent from the Developer mailing list archive at Nabble.com. +ï¼ ï¼ï¼ï¼ ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ -- +ï¼ ï¼ï¼ï¼ ï¼ Thanks +ï¼ ï¼ï¼ï¼ ï¼ Zhang Chen +ï¼ ï¼ï¼ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ +ï¼ ï¼ï¼ï¼ ï¼ +ï¼ ï¼ï¼ï¼ +ï¼ ï¼ï¼ +ï¼ ï¼ -- +ï¼ ï¼ Dr. David Alan Gilbert / address@hidden / Manchester, UK +ï¼ ï¼ +ï¼ ï¼ . +ï¼ ï¼ +ï¼ + diff --git a/results/classifier/001/mistranslation/71456293 b/results/classifier/001/mistranslation/71456293 new file mode 100644 index 000000000..746a624cc --- /dev/null +++ b/results/classifier/001/mistranslation/71456293 @@ -0,0 +1,1486 @@ +mistranslation: 0.659 +instruction: 0.624 +semantic: 0.600 +other: 0.598 + +[Qemu-devel][bug] qemu crash when migrate vm and vm's disks + +When migrate vm and vmâs disks target host qemu crash due to an invalid free. +#0 object_unref (obj=0x1000) at /qemu-2.12/rpmbuild/BUILD/qemu-2.12/qom/object.c:920 +#1 0x0000560434d79e79 in memory_region_unref (mr=<optimized out>) +at /qemu-2.12/rpmbuild/BUILD/qemu-2.12/memory.c:1730 +#2 flatview_destroy (view=0x560439653880) at /qemu-2.12/rpmbuild/BUILD/qemu-2.12/memory.c:292 +#3 0x000056043514dfbe in call_rcu_thread (opaque=<optimized out>) +at /qemu-2.12/rpmbuild/BUILD/qemu-2.12/util/rcu.c:284 +#4 0x00007fbc2b36fe25 in start_thread () from /lib64/libpthread.so.0 +#5 0x00007fbc2b099bad in clone () from /lib64/libc.so.6 +test base qemu-2.12.0 +ï¼ +but use lastest qemu(v6.0.0-rc2) also reproduce. +As follow patch can resolve this problem: +https://lists.gnu.org/archive/html/qemu-devel/2018-07/msg02272.html +Steps to reproduce: +(1) Create VM (virsh define) +(2) Add 64 virtio scsi disks +(3) migrate vm and vmâdisks +------------------------------------------------------------------------------------------------------------------------------------- +æ¬é®ä»¶åå ¶é件å«ææ°åä¸éå¢çä¿å¯ä¿¡æ¯ï¼ä» éäºåéç»ä¸é¢å°åä¸ååº +ç个人æ群ç»ãç¦æ¢ä»»ä½å ¶ä»äººä»¥ä»»ä½å½¢å¼ä½¿ç¨ï¼å æ¬ä½ä¸éäºå ¨é¨æé¨åå°æ³é²ãå¤å¶ã +ææ£åï¼æ¬é®ä»¶ä¸çä¿¡æ¯ãå¦ææ¨éæ¶äºæ¬é®ä»¶ï¼è¯·æ¨ç«å³çµè¯æé®ä»¶éç¥å件人并å é¤æ¬ +é®ä»¶ï¼ +This e-mail and its attachments contain confidential information from New H3C, which is +intended only for the person or entity whose address is listed above. Any use of the +information contained herein in any way (including, but not limited to, total or partial +disclosure, reproduction, or dissemination) by persons other than the intended +recipient(s) is prohibited. If you receive this e-mail in error, please notify the sender +by phone or email immediately and delete it! + +* Yuchen (yu.chen@h3c.com) wrote: +> +When migrate vm and vmâs disks target host qemu crash due to an invalid free. +> +> +#0 object_unref (obj=0x1000) at +> +/qemu-2.12/rpmbuild/BUILD/qemu-2.12/qom/object.c:920 +> +#1 0x0000560434d79e79 in memory_region_unref (mr=<optimized out>) +> +at /qemu-2.12/rpmbuild/BUILD/qemu-2.12/memory.c:1730 +> +#2 flatview_destroy (view=0x560439653880) at +> +/qemu-2.12/rpmbuild/BUILD/qemu-2.12/memory.c:292 +> +#3 0x000056043514dfbe in call_rcu_thread (opaque=<optimized out>) +> +at /qemu-2.12/rpmbuild/BUILD/qemu-2.12/util/rcu.c:284 +> +#4 0x00007fbc2b36fe25 in start_thread () from /lib64/libpthread.so.0 +> +#5 0x00007fbc2b099bad in clone () from /lib64/libc.so.6 +> +> +test base qemu-2.12.0ï¼but use lastest qemu(v6.0.0-rc2) also reproduce. +Interesting. + +> +As follow patch can resolve this problem: +> +https://lists.gnu.org/archive/html/qemu-devel/2018-07/msg02272.html +That's a pci/rcu change; ccing Paolo and Micahel. + +> +Steps to reproduce: +> +(1) Create VM (virsh define) +> +(2) Add 64 virtio scsi disks +Is that hot adding the disks later, or are they included in the VM at +creation? +Can you provide a libvirt XML example? + +> +(3) migrate vm and vmâdisks +What do you mean by 'and vm disks' - are you doing a block migration? + +Dave + +> +------------------------------------------------------------------------------------------------------------------------------------- +> +æ¬é®ä»¶åå ¶é件å«ææ°åä¸éå¢çä¿å¯ä¿¡æ¯ï¼ä» éäºåéç»ä¸é¢å°åä¸ååº +> +ç个人æ群ç»ãç¦æ¢ä»»ä½å ¶ä»äººä»¥ä»»ä½å½¢å¼ä½¿ç¨ï¼å æ¬ä½ä¸éäºå ¨é¨æé¨åå°æ³é²ãå¤å¶ã +> +ææ£åï¼æ¬é®ä»¶ä¸çä¿¡æ¯ãå¦ææ¨éæ¶äºæ¬é®ä»¶ï¼è¯·æ¨ç«å³çµè¯æé®ä»¶éç¥å件人并å é¤æ¬ +> +é®ä»¶ï¼ +> +This e-mail and its attachments contain confidential information from New +> +H3C, which is +> +intended only for the person or entity whose address is listed above. Any use +> +of the +> +information contained herein in any way (including, but not limited to, total +> +or partial +> +disclosure, reproduction, or dissemination) by persons other than the intended +> +recipient(s) is prohibited. If you receive this e-mail in error, please +> +notify the sender +> +by phone or email immediately and delete it! +-- +Dr. David Alan Gilbert / dgilbert@redhat.com / Manchester, UK + +> +-----é®ä»¶å件----- +> +å件人: Dr. David Alan Gilbert [ +mailto:dgilbert@redhat.com +] +> +åéæ¶é´: 2021å¹´4æ8æ¥ 19:27 +> +æ¶ä»¶äºº: yuchen (Cloud) <yu.chen@h3c.com>; pbonzini@redhat.com; +> +mst@redhat.com +> +æé: qemu-devel@nongnu.org +> +主é¢: Re: [Qemu-devel][bug] qemu crash when migrate vm and vm's disks +> +> +* Yuchen (yu.chen@h3c.com) wrote: +> +> When migrate vm and vmâs disks target host qemu crash due to an invalid +> +free. +> +> +> +> #0 object_unref (obj=0x1000) at +> +> /qemu-2.12/rpmbuild/BUILD/qemu-2.12/qom/object.c:920 +> +> #1 0x0000560434d79e79 in memory_region_unref (mr=<optimized out>) +> +> at /qemu-2.12/rpmbuild/BUILD/qemu-2.12/memory.c:1730 +> +> #2 flatview_destroy (view=0x560439653880) at +> +> /qemu-2.12/rpmbuild/BUILD/qemu-2.12/memory.c:292 +> +> #3 0x000056043514dfbe in call_rcu_thread (opaque=<optimized out>) +> +> at /qemu-2.12/rpmbuild/BUILD/qemu-2.12/util/rcu.c:284 +> +> #4 0x00007fbc2b36fe25 in start_thread () from /lib64/libpthread.so.0 +> +> #5 0x00007fbc2b099bad in clone () from /lib64/libc.so.6 +> +> +> +> test base qemu-2.12.0ï¼but use lastest qemu(v6.0.0-rc2) also reproduce. +> +> +Interesting. +> +> +> As follow patch can resolve this problem: +> +> +https://lists.gnu.org/archive/html/qemu-devel/2018-07/msg02272.html +> +> +That's a pci/rcu change; ccing Paolo and Micahel. +> +> +> Steps to reproduce: +> +> (1) Create VM (virsh define) +> +> (2) Add 64 virtio scsi disks +> +> +Is that hot adding the disks later, or are they included in the VM at +> +creation? +> +Can you provide a libvirt XML example? +> +Include disks in the VM at creation + +vm disks xml (only virtio scsi disks): + <devices> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native'/> + <source file='/vms/tempp/vm-os'/> + <target dev='vda' bus='virtio'/> + <address type='pci' domain='0x0000' bus='0x00' slot='0x08' +function='0x0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data1'/> + <target dev='sda' bus='scsi'/> + <address type='drive' controller='2' bus='0' target='0' unit='0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data2'/> + <target dev='sdb' bus='scsi'/> + <address type='drive' controller='3' bus='0' target='0' unit='0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data3'/> + <target dev='sdc' bus='scsi'/> + <address type='drive' controller='4' bus='0' target='0' unit='0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data4'/> + <target dev='sdd' bus='scsi'/> + <address type='drive' controller='5' bus='0' target='0' unit='0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data5'/> + <target dev='sde' bus='scsi'/> + <address type='drive' controller='6' bus='0' target='0' unit='0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data6'/> + <target dev='sdf' bus='scsi'/> + <address type='drive' controller='7' bus='0' target='0' unit='0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data7'/> + <target dev='sdg' bus='scsi'/> + <address type='drive' controller='8' bus='0' target='0' unit='0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data8'/> + <target dev='sdh' bus='scsi'/> + <address type='drive' controller='9' bus='0' target='0' unit='0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data9'/> + <target dev='sdi' bus='scsi'/> + <address type='drive' controller='10' bus='0' target='0' unit='0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data10'/> + <target dev='sdj' bus='scsi'/> + <address type='drive' controller='11' bus='0' target='0' unit='0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data11'/> + <target dev='sdk' bus='scsi'/> + <address type='drive' controller='12' bus='0' target='0' unit='0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data12'/> + <target dev='sdl' bus='scsi'/> + <address type='drive' controller='13' bus='0' target='0' unit='0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data13'/> + <target dev='sdm' bus='scsi'/> + <address type='drive' controller='14' bus='0' target='0' unit='0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data14'/> + <target dev='sdn' bus='scsi'/> + <address type='drive' controller='15' bus='0' target='0' unit='0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data15'/> + <target dev='sdo' bus='scsi'/> + <address type='drive' controller='16' bus='0' target='0' unit='0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data16'/> + <target dev='sdp' bus='scsi'/> + <address type='drive' controller='17' bus='0' target='0' unit='0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data17'/> + <target dev='sdq' bus='scsi'/> + <address type='drive' controller='18' bus='0' target='0' unit='0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data18'/> + <target dev='sdr' bus='scsi'/> + <address type='drive' controller='19' bus='0' target='0' unit='0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data19'/> + <target dev='sds' bus='scsi'/> + <address type='drive' controller='20' bus='0' target='0' unit='0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data20'/> + <target dev='sdt' bus='scsi'/> + <address type='drive' controller='21' bus='0' target='0' unit='0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data21'/> + <target dev='sdu' bus='scsi'/> + <address type='drive' controller='22' bus='0' target='0' unit='0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data22'/> + <target dev='sdv' bus='scsi'/> + <address type='drive' controller='23' bus='0' target='0' unit='0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data23'/> + <target dev='sdw' bus='scsi'/> + <address type='drive' controller='24' bus='0' target='0' unit='0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data24'/> + <target dev='sdx' bus='scsi'/> + <address type='drive' controller='25' bus='0' target='0' unit='0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data25'/> + <target dev='sdy' bus='scsi'/> + <address type='drive' controller='26' bus='0' target='0' unit='0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data26'/> + <target dev='sdz' bus='scsi'/> + <address type='drive' controller='27' bus='0' target='0' unit='0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data27'/> + <target dev='sdaa' bus='scsi'/> + <address type='drive' controller='28' bus='0' target='0' unit='0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data28'/> + <target dev='sdab' bus='scsi'/> + <address type='drive' controller='29' bus='0' target='0' unit='0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data29'/> + <target dev='sdac' bus='scsi'/> + <address type='drive' controller='30' bus='0' target='0' unit='0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data30'/> + <target dev='sdad' bus='scsi'/> + <address type='drive' controller='31' bus='0' target='0' unit='0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data31'/> + <target dev='sdae' bus='scsi'/> + <address type='drive' controller='32' bus='0' target='0' unit='0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data32'/> + <target dev='sdaf' bus='scsi'/> + <address type='drive' controller='33' bus='0' target='0' unit='0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data33'/> + <target dev='sdag' bus='scsi'/> + <address type='drive' controller='34' bus='0' target='0' unit='0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data34'/> + <target dev='sdah' bus='scsi'/> + <address type='drive' controller='35' bus='0' target='0' unit='0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data35'/> + <target dev='sdai' bus='scsi'/> + <address type='drive' controller='36' bus='0' target='0' unit='0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data36'/> + <target dev='sdaj' bus='scsi'/> + <address type='drive' controller='37' bus='0' target='0' unit='0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data37'/> + <target dev='sdak' bus='scsi'/> + <address type='drive' controller='38' bus='0' target='0' unit='0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data38'/> + <target dev='sdal' bus='scsi'/> + <address type='drive' controller='39' bus='0' target='0' unit='0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data39'/> + <target dev='sdam' bus='scsi'/> + <address type='drive' controller='40' bus='0' target='0' unit='0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data40'/> + <target dev='sdan' bus='scsi'/> + <address type='drive' controller='41' bus='0' target='0' unit='0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data41'/> + <target dev='sdao' bus='scsi'/> + <address type='drive' controller='42' bus='0' target='0' unit='0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data42'/> + <target dev='sdap' bus='scsi'/> + <address type='drive' controller='43' bus='0' target='0' unit='0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data43'/> + <target dev='sdaq' bus='scsi'/> + <address type='drive' controller='44' bus='0' target='0' unit='0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data44'/> + <target dev='sdar' bus='scsi'/> + <address type='drive' controller='45' bus='0' target='0' unit='0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data45'/> + <target dev='sdas' bus='scsi'/> + <address type='drive' controller='46' bus='0' target='0' unit='0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data46'/> + <target dev='sdat' bus='scsi'/> + <address type='drive' controller='47' bus='0' target='0' unit='0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data47'/> + <target dev='sdau' bus='scsi'/> + <address type='drive' controller='48' bus='0' target='0' unit='0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data48'/> + <target dev='sdav' bus='scsi'/> + <address type='drive' controller='49' bus='0' target='0' unit='0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data49'/> + <target dev='sdaw' bus='scsi'/> + <address type='drive' controller='50' bus='0' target='0' unit='0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data50'/> + <target dev='sdax' bus='scsi'/> + <address type='drive' controller='51' bus='0' target='0' unit='0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data51'/> + <target dev='sday' bus='scsi'/> + <address type='drive' controller='52' bus='0' target='0' unit='0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data52'/> + <target dev='sdaz' bus='scsi'/> + <address type='drive' controller='53' bus='0' target='0' unit='0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data53'/> + <target dev='sdba' bus='scsi'/> + <address type='drive' controller='54' bus='0' target='0' unit='0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data54'/> + <target dev='sdbb' bus='scsi'/> + <address type='drive' controller='55' bus='0' target='0' unit='0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data55'/> + <target dev='sdbc' bus='scsi'/> + <address type='drive' controller='56' bus='0' target='0' unit='0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data56'/> + <target dev='sdbd' bus='scsi'/> + <address type='drive' controller='57' bus='0' target='0' unit='0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data57'/> + <target dev='sdbe' bus='scsi'/> + <address type='drive' controller='58' bus='0' target='0' unit='0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data58'/> + <target dev='sdbf' bus='scsi'/> + <address type='drive' controller='59' bus='0' target='0' unit='0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data59'/> + <target dev='sdbg' bus='scsi'/> + <address type='drive' controller='60' bus='0' target='0' unit='0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data60'/> + <target dev='sdbh' bus='scsi'/> + <address type='drive' controller='61' bus='0' target='0' unit='0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data61'/> + <target dev='sdbi' bus='scsi'/> + <address type='drive' controller='62' bus='0' target='0' unit='0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data62'/> + <target dev='sdbj' bus='scsi'/> + <address type='drive' controller='63' bus='0' target='0' unit='0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data63'/> + <target dev='sdbk' bus='scsi'/> + <address type='drive' controller='64' bus='0' target='0' unit='0'/> + </disk> + <controller type='scsi' index='0'> + <address type='pci' domain='0x0000' bus='0x01' slot='0x02' +function='0x0'/> + </controller> + <controller type='scsi' index='1' model='virtio-scsi'> + <address type='pci' domain='0x0000' bus='0x00' slot='0x06' +function='0x0'/> + </controller> + <controller type='scsi' index='2' model='virtio-scsi'> + <address type='pci' domain='0x0000' bus='0x01' slot='0x01' +function='0x0'/> + </controller> + <controller type='scsi' index='3' model='virtio-scsi'> + <address type='pci' domain='0x0000' bus='0x01' slot='0x03' +function='0x0'/> + </controller> + <controller type='scsi' index='4' model='virtio-scsi'> + <address type='pci' domain='0x0000' bus='0x01' slot='0x04' +function='0x0'/> + </controller> + <controller type='scsi' index='5' model='virtio-scsi'> + <address type='pci' domain='0x0000' bus='0x01' slot='0x05' +function='0x0'/> + </controller> + <controller type='scsi' index='6' model='virtio-scsi'> + <address type='pci' domain='0x0000' bus='0x01' slot='0x06' +function='0x0'/> + </controller> + <controller type='scsi' index='7' model='virtio-scsi'> + <address type='pci' domain='0x0000' bus='0x01' slot='0x07' +function='0x0'/> + </controller> + <controller type='scsi' index='8' model='virtio-scsi'> + <address type='pci' domain='0x0000' bus='0x01' slot='0x08' +function='0x0'/> + </controller> + <controller type='scsi' index='9' model='virtio-scsi'> + <address type='pci' domain='0x0000' bus='0x01' slot='0x09' +function='0x0'/> + </controller> + <controller type='scsi' index='10' model='virtio-scsi'> + <address type='pci' domain='0x0000' bus='0x01' slot='0x0a' +function='0x0'/> + </controller> + <controller type='scsi' index='11' model='virtio-scsi'> + <address type='pci' domain='0x0000' bus='0x01' slot='0x0b' +function='0x0'/> + </controller> + <controller type='scsi' index='12' model='virtio-scsi'> + <address type='pci' domain='0x0000' bus='0x01' slot='0x0c' +function='0x0'/> + </controller> + <controller type='scsi' index='13' model='virtio-scsi'> + <address type='pci' domain='0x0000' bus='0x01' slot='0x0d' +function='0x0'/> + </controller> + <controller type='scsi' index='14' model='virtio-scsi'> + <address type='pci' domain='0x0000' bus='0x01' slot='0x0e' +function='0x0'/> + </controller> + <controller type='scsi' index='15' model='virtio-scsi'> + <address type='pci' domain='0x0000' bus='0x01' slot='0x0f' +function='0x0'/> + </controller> + <controller type='scsi' index='16' model='virtio-scsi'> + <address type='pci' domain='0x0000' bus='0x01' slot='0x10' +function='0x0'/> + </controller> + <controller type='scsi' index='17' model='virtio-scsi'> + <address type='pci' domain='0x0000' bus='0x01' slot='0x11' +function='0x0'/> + </controller> + <controller type='scsi' index='18' model='virtio-scsi'> + <address type='pci' domain='0x0000' bus='0x01' slot='0x12' +function='0x0'/> + </controller> + <controller type='scsi' index='19' model='virtio-scsi'> + <address type='pci' domain='0x0000' bus='0x01' slot='0x13' +function='0x0'/> + </controller> + <controller type='scsi' index='20' model='virtio-scsi'> + <address type='pci' domain='0x0000' bus='0x01' slot='0x14' +function='0x0'/> + </controller> + <controller type='scsi' index='21' model='virtio-scsi'> + <address type='pci' domain='0x0000' bus='0x01' slot='0x15' +function='0x0'/> + </controller> + <controller type='scsi' index='22' model='virtio-scsi'> + <address type='pci' domain='0x0000' bus='0x01' slot='0x16' +function='0x0'/> + </controller> + <controller type='scsi' index='23' model='virtio-scsi'> + <address type='pci' domain='0x0000' bus='0x01' slot='0x17' +function='0x0'/> + </controller> + <controller type='scsi' index='24' model='virtio-scsi'> + <address type='pci' domain='0x0000' bus='0x01' slot='0x18' +function='0x0'/> + </controller> + <controller type='scsi' index='25' model='virtio-scsi'> + <address type='pci' domain='0x0000' bus='0x01' slot='0x19' +function='0x0'/> + </controller> + <controller type='scsi' index='26' model='virtio-scsi'> + <address type='pci' domain='0x0000' bus='0x01' slot='0x1a' +function='0x0'/> + </controller> + <controller type='scsi' index='27' model='virtio-scsi'> + <address type='pci' domain='0x0000' bus='0x01' slot='0x1b' +function='0x0'/> + </controller> + <controller type='scsi' index='28' model='virtio-scsi'> + <address type='pci' domain='0x0000' bus='0x01' slot='0x1c' +function='0x0'/> + </controller> + <controller type='scsi' index='29' model='virtio-scsi'> + <address type='pci' domain='0x0000' bus='0x01' slot='0x1d' +function='0x0'/> + </controller> + <controller type='scsi' index='30' model='virtio-scsi'> + <address type='pci' domain='0x0000' bus='0x01' slot='0x1e' +function='0x0'/> + </controller> + <controller type='scsi' index='31' model='virtio-scsi'> + <address type='pci' domain='0x0000' bus='0x02' slot='0x01' +function='0x0'/> + </controller> + <controller type='scsi' index='32' model='virtio-scsi'> + <address type='pci' domain='0x0000' bus='0x02' slot='0x02' +function='0x0'/> + </controller> + <controller type='scsi' index='33' model='virtio-scsi'> + <address type='pci' domain='0x0000' bus='0x02' slot='0x03' +function='0x0'/> + </controller> + <controller type='scsi' index='34' model='virtio-scsi'> + <address type='pci' domain='0x0000' bus='0x02' slot='0x04' +function='0x0'/> + </controller> + <controller type='scsi' index='35' model='virtio-scsi'> + <address type='pci' domain='0x0000' bus='0x02' slot='0x05' +function='0x0'/> + </controller> + <controller type='scsi' index='36' model='virtio-scsi'> + <address type='pci' domain='0x0000' bus='0x02' slot='0x06' +function='0x0'/> + </controller> + <controller type='scsi' index='37' model='virtio-scsi'> + <address type='pci' domain='0x0000' bus='0x02' slot='0x07' +function='0x0'/> + </controller> + <controller type='scsi' index='38' model='virtio-scsi'> + <address type='pci' domain='0x0000' bus='0x02' slot='0x08' +function='0x0'/> + </controller> + <controller type='scsi' index='39' model='virtio-scsi'> + <address type='pci' domain='0x0000' bus='0x02' slot='0x09' +function='0x0'/> + </controller> + <controller type='scsi' index='40' model='virtio-scsi'> + <address type='pci' domain='0x0000' bus='0x02' slot='0x0a' +function='0x0'/> + </controller> + <controller type='scsi' index='41' model='virtio-scsi'> + <address type='pci' domain='0x0000' bus='0x02' slot='0x0b' +function='0x0'/> + </controller> + <controller type='scsi' index='42' model='virtio-scsi'> + <address type='pci' domain='0x0000' bus='0x02' slot='0x0c' +function='0x0'/> + </controller> + <controller type='scsi' index='43' model='virtio-scsi'> + <address type='pci' domain='0x0000' bus='0x02' slot='0x0d' +function='0x0'/> + </controller> + <controller type='scsi' index='44' model='virtio-scsi'> + <address type='pci' domain='0x0000' bus='0x00' slot='0x03' +function='0x0'/> + </controller> + <controller type='scsi' index='45' model='virtio-scsi'> + <address type='pci' domain='0x0000' bus='0x00' slot='0x09' +function='0x0'/> + </controller> + <controller type='scsi' index='46' model='virtio-scsi'> + <address type='pci' domain='0x0000' bus='0x00' slot='0x0b' +function='0x0'/> + </controller> + <controller type='scsi' index='47' model='virtio-scsi'> + <address type='pci' domain='0x0000' bus='0x00' slot='0x0c' +function='0x0'/> + </controller> + <controller type='scsi' index='48' model='virtio-scsi'> + <address type='pci' domain='0x0000' bus='0x00' slot='0x0d' +function='0x0'/> + </controller> + <controller type='scsi' index='49' model='virtio-scsi'> + <address type='pci' domain='0x0000' bus='0x00' slot='0x0e' +function='0x0'/> + </controller> + <controller type='scsi' index='50' model='virtio-scsi'> + <address type='pci' domain='0x0000' bus='0x00' slot='0x0f' +function='0x0'/> + </controller> + <controller type='scsi' index='51' model='virtio-scsi'> + <address type='pci' domain='0x0000' bus='0x00' slot='0x10' +function='0x0'/> + </controller> + <controller type='scsi' index='52' model='virtio-scsi'> + <address type='pci' domain='0x0000' bus='0x00' slot='0x11' +function='0x0'/> + </controller> + <controller type='scsi' index='53' model='virtio-scsi'> + <address type='pci' domain='0x0000' bus='0x00' slot='0x12' +function='0x0'/> + </controller> + <controller type='scsi' index='54' model='virtio-scsi'> + <address type='pci' domain='0x0000' bus='0x00' slot='0x13' +function='0x0'/> + </controller> + <controller type='scsi' index='55' model='virtio-scsi'> + <address type='pci' domain='0x0000' bus='0x00' slot='0x14' +function='0x0'/> + </controller> + <controller type='scsi' index='56' model='virtio-scsi'> + <address type='pci' domain='0x0000' bus='0x00' slot='0x15' +function='0x0'/> + </controller> + <controller type='scsi' index='57' model='virtio-scsi'> + <address type='pci' domain='0x0000' bus='0x00' slot='0x16' +function='0x0'/> + </controller> + <controller type='scsi' index='58' model='virtio-scsi'> + <address type='pci' domain='0x0000' bus='0x00' slot='0x17' +function='0x0'/> + </controller> + <controller type='scsi' index='59' model='virtio-scsi'> + <address type='pci' domain='0x0000' bus='0x00' slot='0x18' +function='0x0'/> + </controller> + <controller type='scsi' index='60' model='virtio-scsi'> + <address type='pci' domain='0x0000' bus='0x00' slot='0x19' +function='0x0'/> + </controller> + <controller type='scsi' index='61' model='virtio-scsi'> + <address type='pci' domain='0x0000' bus='0x00' slot='0x1a' +function='0x0'/> + </controller> + <controller type='scsi' index='62' model='virtio-scsi'> + <address type='pci' domain='0x0000' bus='0x00' slot='0x1b' +function='0x0'/> + </controller> + <controller type='scsi' index='63' model='virtio-scsi'> + <address type='pci' domain='0x0000' bus='0x00' slot='0x1c' +function='0x0'/> + </controller> + <controller type='scsi' index='64' model='virtio-scsi'> + <address type='pci' domain='0x0000' bus='0x00' slot='0x1d' +function='0x0'/> + </controller> + <controller type='pci' index='0' model='pci-root'/> + <controller type='pci' index='1' model='pci-bridge'> + <model name='pci-bridge'/> + <target chassisNr='1'/> + <address type='pci' domain='0x0000' bus='0x00' slot='0x1f' +function='0x0'/> + </controller> + <controller type='pci' index='2' model='pci-bridge'> + <model name='pci-bridge'/> + <target chassisNr='2'/> + <address type='pci' domain='0x0000' bus='0x01' slot='0x1f' +function='0x0'/> + </controller> + </devices> + +vm disks xml (only virtio disks): + <devices> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native'/> + <source file='/vms/tempp/vm-os'/> + <target dev='vda' bus='virtio'/> + <address type='pci' domain='0x0000' bus='0x00' slot='0x08' +function='0x0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data2'/> + <target dev='vdb' bus='virtio'/> + <address type='pci' domain='0x0000' bus='0x00' slot='0x06' +function='0x0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data3'/> + <target dev='vdc' bus='virtio'/> + <address type='pci' domain='0x0000' bus='0x00' slot='0x09' +function='0x0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data4'/> + <target dev='vdd' bus='virtio'/> + <address type='pci' domain='0x0000' bus='0x00' slot='0x0b' +function='0x0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data5'/> + <target dev='vde' bus='virtio'/> + <address type='pci' domain='0x0000' bus='0x00' slot='0x0c' +function='0x0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data6'/> + <target dev='vdf' bus='virtio'/> + <address type='pci' domain='0x0000' bus='0x00' slot='0x0d' +function='0x0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data7'/> + <target dev='vdg' bus='virtio'/> + <address type='pci' domain='0x0000' bus='0x00' slot='0x0e' +function='0x0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data8'/> + <target dev='vdh' bus='virtio'/> + <address type='pci' domain='0x0000' bus='0x00' slot='0x0f' +function='0x0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data9'/> + <target dev='vdi' bus='virtio'/> + <address type='pci' domain='0x0000' bus='0x00' slot='0x10' +function='0x0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data10'/> + <target dev='vdj' bus='virtio'/> + <address type='pci' domain='0x0000' bus='0x00' slot='0x11' +function='0x0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data11'/> + <target dev='vdk' bus='virtio'/> + <address type='pci' domain='0x0000' bus='0x00' slot='0x12' +function='0x0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data12'/> + <target dev='vdl' bus='virtio'/> + <address type='pci' domain='0x0000' bus='0x00' slot='0x13' +function='0x0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data13'/> + <target dev='vdm' bus='virtio'/> + <address type='pci' domain='0x0000' bus='0x00' slot='0x14' +function='0x0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data14'/> + <target dev='vdn' bus='virtio'/> + <address type='pci' domain='0x0000' bus='0x00' slot='0x15' +function='0x0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data15'/> + <target dev='vdo' bus='virtio'/> + <address type='pci' domain='0x0000' bus='0x00' slot='0x16' +function='0x0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data16'/> + <target dev='vdp' bus='virtio'/> + <address type='pci' domain='0x0000' bus='0x00' slot='0x17' +function='0x0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data17'/> + <target dev='vdq' bus='virtio'/> + <address type='pci' domain='0x0000' bus='0x00' slot='0x18' +function='0x0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data18'/> + <target dev='vdr' bus='virtio'/> + <address type='pci' domain='0x0000' bus='0x00' slot='0x19' +function='0x0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data19'/> + <target dev='vds' bus='virtio'/> + <address type='pci' domain='0x0000' bus='0x00' slot='0x1a' +function='0x0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data20'/> + <target dev='vdt' bus='virtio'/> + <address type='pci' domain='0x0000' bus='0x00' slot='0x1b' +function='0x0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data21'/> + <target dev='vdu' bus='virtio'/> + <address type='pci' domain='0x0000' bus='0x00' slot='0x1c' +function='0x0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data22'/> + <target dev='vdv' bus='virtio'/> + <address type='pci' domain='0x0000' bus='0x00' slot='0x1d' +function='0x0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data23'/> + <target dev='vdw' bus='virtio'/> + <address type='pci' domain='0x0000' bus='0x00' slot='0x1e' +function='0x0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data24'/> + <target dev='vdx' bus='virtio'/> + <address type='pci' domain='0x0000' bus='0x01' slot='0x01' +function='0x0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data25'/> + <target dev='vdy' bus='virtio'/> + <address type='pci' domain='0x0000' bus='0x01' slot='0x03' +function='0x0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data26'/> + <target dev='vdz' bus='virtio'/> + <address type='pci' domain='0x0000' bus='0x01' slot='0x04' +function='0x0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data27'/> + <target dev='vdaa' bus='virtio'/> + <address type='pci' domain='0x0000' bus='0x01' slot='0x05' +function='0x0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data28'/> + <target dev='vdab' bus='virtio'/> + <address type='pci' domain='0x0000' bus='0x01' slot='0x06' +function='0x0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data29'/> + <target dev='vdac' bus='virtio'/> + <address type='pci' domain='0x0000' bus='0x01' slot='0x07' +function='0x0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data30'/> + <target dev='vdad' bus='virtio'/> + <address type='pci' domain='0x0000' bus='0x01' slot='0x08' +function='0x0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data31'/> + <target dev='vdae' bus='virtio'/> + <address type='pci' domain='0x0000' bus='0x01' slot='0x09' +function='0x0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data32'/> + <target dev='vdaf' bus='virtio'/> + <address type='pci' domain='0x0000' bus='0x01' slot='0x0a' +function='0x0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data33'/> + <target dev='vdag' bus='virtio'/> + <address type='pci' domain='0x0000' bus='0x01' slot='0x0b' +function='0x0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data34'/> + <target dev='vdah' bus='virtio'/> + <address type='pci' domain='0x0000' bus='0x01' slot='0x0c' +function='0x0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data35'/> + <target dev='vdai' bus='virtio'/> + <address type='pci' domain='0x0000' bus='0x01' slot='0x0d' +function='0x0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data36'/> + <target dev='vdaj' bus='virtio'/> + <address type='pci' domain='0x0000' bus='0x01' slot='0x0e' +function='0x0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data37'/> + <target dev='vdak' bus='virtio'/> + <address type='pci' domain='0x0000' bus='0x01' slot='0x0f' +function='0x0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data38'/> + <target dev='vdal' bus='virtio'/> + <address type='pci' domain='0x0000' bus='0x01' slot='0x10' +function='0x0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data39'/> + <target dev='vdam' bus='virtio'/> + <address type='pci' domain='0x0000' bus='0x01' slot='0x11' +function='0x0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data40'/> + <target dev='vdan' bus='virtio'/> + <address type='pci' domain='0x0000' bus='0x01' slot='0x12' +function='0x0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data41'/> + <target dev='vdao' bus='virtio'/> + <address type='pci' domain='0x0000' bus='0x01' slot='0x13' +function='0x0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data42'/> + <target dev='vdap' bus='virtio'/> + <address type='pci' domain='0x0000' bus='0x01' slot='0x14' +function='0x0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data43'/> + <target dev='vdaq' bus='virtio'/> + <address type='pci' domain='0x0000' bus='0x01' slot='0x15' +function='0x0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data44'/> + <target dev='vdar' bus='virtio'/> + <address type='pci' domain='0x0000' bus='0x01' slot='0x16' +function='0x0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data45'/> + <target dev='vdas' bus='virtio'/> + <address type='pci' domain='0x0000' bus='0x01' slot='0x17' +function='0x0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data46'/> + <target dev='vdat' bus='virtio'/> + <address type='pci' domain='0x0000' bus='0x01' slot='0x18' +function='0x0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data47'/> + <target dev='vdau' bus='virtio'/> + <address type='pci' domain='0x0000' bus='0x01' slot='0x19' +function='0x0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data48'/> + <target dev='vdav' bus='virtio'/> + <address type='pci' domain='0x0000' bus='0x01' slot='0x1a' +function='0x0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data49'/> + <target dev='vdaw' bus='virtio'/> + <address type='pci' domain='0x0000' bus='0x01' slot='0x1b' +function='0x0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data50'/> + <target dev='vdax' bus='virtio'/> + <address type='pci' domain='0x0000' bus='0x01' slot='0x1c' +function='0x0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data51'/> + <target dev='vday' bus='virtio'/> + <address type='pci' domain='0x0000' bus='0x01' slot='0x1d' +function='0x0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data52'/> + <target dev='vdaz' bus='virtio'/> + <address type='pci' domain='0x0000' bus='0x01' slot='0x1e' +function='0x0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data53'/> + <target dev='vdba' bus='virtio'/> + <address type='pci' domain='0x0000' bus='0x02' slot='0x01' +function='0x0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data54'/> + <target dev='vdbb' bus='virtio'/> + <address type='pci' domain='0x0000' bus='0x02' slot='0x02' +function='0x0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data55'/> + <target dev='vdbc' bus='virtio'/> + <address type='pci' domain='0x0000' bus='0x02' slot='0x03' +function='0x0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data56'/> + <target dev='vdbd' bus='virtio'/> + <address type='pci' domain='0x0000' bus='0x02' slot='0x04' +function='0x0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data57'/> + <target dev='vdbe' bus='virtio'/> + <address type='pci' domain='0x0000' bus='0x02' slot='0x05' +function='0x0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data58'/> + <target dev='vdbf' bus='virtio'/> + <address type='pci' domain='0x0000' bus='0x02' slot='0x06' +function='0x0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data59'/> + <target dev='vdbg' bus='virtio'/> + <address type='pci' domain='0x0000' bus='0x02' slot='0x07' +function='0x0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data60'/> + <target dev='vdbh' bus='virtio'/> + <address type='pci' domain='0x0000' bus='0x02' slot='0x08' +function='0x0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data61'/> + <target dev='vdbi' bus='virtio'/> + <address type='pci' domain='0x0000' bus='0x02' slot='0x09' +function='0x0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data62'/> + <target dev='vdbj' bus='virtio'/> + <address type='pci' domain='0x0000' bus='0x02' slot='0x0a' +function='0x0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data63'/> + <target dev='vdbk' bus='virtio'/> + <address type='pci' domain='0x0000' bus='0x02' slot='0x0b' +function='0x0'/> + </disk> + <disk type='file' device='disk'> + <driver name='qemu' type='qcow2' cache='directsync' io='native' +discard='unmap'/> + <source file='/vms/tempp/vm-data1'/> + <target dev='vdbl' bus='virtio'/> + <address type='pci' domain='0x0000' bus='0x00' slot='0x03' +function='0x0'/> + </disk> + <controller type='pci' index='0' model='pci-root'/> + <controller type='pci' index='1' model='pci-bridge'> + <model name='pci-bridge'/> + <target chassisNr='1'/> + <address type='pci' domain='0x0000' bus='0x00' slot='0x1f' +function='0x0'/> + </controller> + <controller type='pci' index='2' model='pci-bridge'> + <model name='pci-bridge'/> + <target chassisNr='2'/> + <address type='pci' domain='0x0000' bus='0x01' slot='0x1f' +function='0x0'/> + </controller> + </devices> + +> +> (3) migrate vm and vmâdisks +> +> +What do you mean by 'and vm disks' - are you doing a block migration? +> +Yes, block migration. +In fact, only migration domain also reproduced. + +> +Dave +> +> +> ---------------------------------------------------------------------- +> +> --------------------------------------------------------------- +> +Dr. David Alan Gilbert / dgilbert@redhat.com / Manchester, UK +------------------------------------------------------------------------------------------------------------------------------------- +æ¬é®ä»¶åå ¶é件å«ææ°åä¸éå¢çä¿å¯ä¿¡æ¯ï¼ä» éäºåéç»ä¸é¢å°åä¸ååº +ç个人æ群ç»ãç¦æ¢ä»»ä½å ¶ä»äººä»¥ä»»ä½å½¢å¼ä½¿ç¨ï¼å æ¬ä½ä¸éäºå ¨é¨æé¨åå°æ³é²ãå¤å¶ã +ææ£åï¼æ¬é®ä»¶ä¸çä¿¡æ¯ãå¦ææ¨éæ¶äºæ¬é®ä»¶ï¼è¯·æ¨ç«å³çµè¯æé®ä»¶éç¥å件人并å é¤æ¬ +é®ä»¶ï¼ +This e-mail and its attachments contain confidential information from New H3C, +which is +intended only for the person or entity whose address is listed above. Any use +of the +information contained herein in any way (including, but not limited to, total +or partial +disclosure, reproduction, or dissemination) by persons other than the intended +recipient(s) is prohibited. If you receive this e-mail in error, please notify +the sender +by phone or email immediately and delete it! + diff --git a/results/classifier/001/mistranslation/74466963 b/results/classifier/001/mistranslation/74466963 new file mode 100644 index 000000000..fffafcf77 --- /dev/null +++ b/results/classifier/001/mistranslation/74466963 @@ -0,0 +1,1878 @@ +mistranslation: 0.927 +instruction: 0.903 +semantic: 0.891 +other: 0.877 + +[Qemu-devel] [TCG only][Migration Bug? ] Occasionally, the content of VM's memory is inconsistent between Source and Destination of migration + +Hi all, + +Does anyboday remember the similar issue post by hailiang months ago +http://patchwork.ozlabs.org/patch/454322/ +At least tow bugs about migration had been fixed since that. +And now we found the same issue at the tcg vm(kvm is fine), after +migration, the content VM's memory is inconsistent. +we add a patch to check memory content, you can find it from affix + +steps to reporduce: +1) apply the patch and re-build qemu +2) prepare the ubuntu guest and run memtest in grub. +soruce side: +x86_64-softmmu/qemu-system-x86_64 -netdev tap,id=hn0 -device +e1000,id=net-pci0,netdev=hn0,mac=52:54:00:12:34:65 -boot c -drive +if=none,file=/home/lizj/ubuntu.raw,id=drive-virtio-disk0 -device +virtio-blk-pci,bus=pci.0,addr=0x4,drive=drive-virtio-disk0,id=virtio-disk0 +-vnc :7 -m 128 -smp 1 -device piix3-usb-uhci -device usb-tablet -qmp +tcp::4444,server,nowait -monitor stdio -cpu qemu64 -machine +pc-i440fx-2.3,accel=tcg,usb=off +destination side: +x86_64-softmmu/qemu-system-x86_64 -netdev tap,id=hn0 -device +e1000,id=net-pci0,netdev=hn0,mac=52:54:00:12:34:65 -boot c -drive +if=none,file=/home/lizj/ubuntu.raw,id=drive-virtio-disk0 -device +virtio-blk-pci,bus=pci.0,addr=0x4,drive=drive-virtio-disk0,id=virtio-disk0 +-vnc :7 -m 128 -smp 1 -device piix3-usb-uhci -device usb-tablet -qmp +tcp::4444,server,nowait -monitor stdio -cpu qemu64 -machine +pc-i440fx-2.3,accel=tcg,usb=off -incoming tcp:0:8881 +3) start migration +with 1000M NIC, migration will finish within 3 min. + +at source: +(qemu) migrate tcp:192.168.2.66:8881 +after saving ram complete +e9e725df678d392b1a83b3a917f332bb +qemu-system-x86_64: end ram md5 +(qemu) + +at destination: +...skip... +Completed load of VM with exit code 0 seq iteration 1264 +Completed load of VM with exit code 0 seq iteration 1265 +Completed load of VM with exit code 0 seq iteration 1266 +qemu-system-x86_64: after loading state section id 2(ram) +49c2dac7bde0e5e22db7280dcb3824f9 +qemu-system-x86_64: end ram md5 +qemu-system-x86_64: qemu_loadvm_state: after cpu_synchronize_all_post_init + +49c2dac7bde0e5e22db7280dcb3824f9 +qemu-system-x86_64: end ram md5 + +This occurs occasionally and only at tcg machine. It seems that +some pages dirtied in source side don't transferred to destination. +This problem can be reproduced even if we disable virtio. +Is it OK for some pages that not transferred to destination when do +migration ? Or is it a bug? +Any idea... + +=================md5 check patch============================= + +diff --git a/Makefile.target b/Makefile.target +index 962d004..e2cb8e9 100644 +--- a/Makefile.target ++++ b/Makefile.target +@@ -139,7 +139,7 @@ obj-y += memory.o cputlb.o + obj-y += memory_mapping.o + obj-y += dump.o + obj-y += migration/ram.o migration/savevm.o +-LIBS := $(libs_softmmu) $(LIBS) ++LIBS := $(libs_softmmu) $(LIBS) -lplumb + + # xen support + obj-$(CONFIG_XEN) += xen-common.o +diff --git a/migration/ram.c b/migration/ram.c +index 1eb155a..3b7a09d 100644 +--- a/migration/ram.c ++++ b/migration/ram.c +@@ -2513,7 +2513,7 @@ static int ram_load(QEMUFile *f, void *opaque, int +version_id) +} + + rcu_read_unlock(); +- DPRINTF("Completed load of VM with exit code %d seq iteration " ++ fprintf(stderr, "Completed load of VM with exit code %d seq iteration " + "%" PRIu64 "\n", ret, seq_iter); + return ret; + } +diff --git a/migration/savevm.c b/migration/savevm.c +index 0ad1b93..3feaa61 100644 +--- a/migration/savevm.c ++++ b/migration/savevm.c +@@ -891,6 +891,29 @@ void qemu_savevm_state_header(QEMUFile *f) + + } + ++#include "exec/ram_addr.h" ++#include "qemu/rcu_queue.h" ++#include <clplumbing/md5.h> ++#ifndef MD5_DIGEST_LENGTH ++#define MD5_DIGEST_LENGTH 16 ++#endif ++ ++static void check_host_md5(void) ++{ ++ int i; ++ unsigned char md[MD5_DIGEST_LENGTH]; ++ rcu_read_lock(); ++ RAMBlock *block = QLIST_FIRST_RCU(&ram_list.blocks);/* Only check +'pc.ram' block */ ++ rcu_read_unlock(); ++ ++ MD5(block->host, block->used_length, md); ++ for(i = 0; i < MD5_DIGEST_LENGTH; i++) { ++ fprintf(stderr, "%02x", md[i]); ++ } ++ fprintf(stderr, "\n"); ++ error_report("end ram md5"); ++} ++ + void qemu_savevm_state_begin(QEMUFile *f, + const MigrationParams *params) + { +@@ -1056,6 +1079,10 @@ void qemu_savevm_state_complete_precopy(QEMUFile +*f, bool iterable_only) +save_section_header(f, se, QEMU_VM_SECTION_END); + + ret = se->ops->save_live_complete_precopy(f, se->opaque); ++ ++ fprintf(stderr, "after saving %s complete\n", se->idstr); ++ check_host_md5(); ++ + trace_savevm_section_end(se->idstr, se->section_id, ret); + save_section_footer(f, se); + if (ret < 0) { +@@ -1791,6 +1818,11 @@ static int qemu_loadvm_state_main(QEMUFile *f, +MigrationIncomingState *mis) +section_id, le->se->idstr); + return ret; + } ++ if (section_type == QEMU_VM_SECTION_END) { ++ error_report("after loading state section id %d(%s)", ++ section_id, le->se->idstr); ++ check_host_md5(); ++ } + if (!check_section_footer(f, le)) { + return -EINVAL; + } +@@ -1901,6 +1933,8 @@ int qemu_loadvm_state(QEMUFile *f) + } + + cpu_synchronize_all_post_init(); ++ error_report("%s: after cpu_synchronize_all_post_init\n", __func__); ++ check_host_md5(); + + return ret; + } + +* Li Zhijian (address@hidden) wrote: +> +Hi all, +> +> +Does anyboday remember the similar issue post by hailiang months ago +> +http://patchwork.ozlabs.org/patch/454322/ +> +At least tow bugs about migration had been fixed since that. +Yes, I wondered what happened to that. + +> +And now we found the same issue at the tcg vm(kvm is fine), after migration, +> +the content VM's memory is inconsistent. +Hmm, TCG only - I don't know much about that; but I guess something must +be accessing memory without using the proper macros/functions so +it doesn't mark it as dirty. + +> +we add a patch to check memory content, you can find it from affix +> +> +steps to reporduce: +> +1) apply the patch and re-build qemu +> +2) prepare the ubuntu guest and run memtest in grub. +> +soruce side: +> +x86_64-softmmu/qemu-system-x86_64 -netdev tap,id=hn0 -device +> +e1000,id=net-pci0,netdev=hn0,mac=52:54:00:12:34:65 -boot c -drive +> +if=none,file=/home/lizj/ubuntu.raw,id=drive-virtio-disk0 -device +> +virtio-blk-pci,bus=pci.0,addr=0x4,drive=drive-virtio-disk0,id=virtio-disk0 +> +-vnc :7 -m 128 -smp 1 -device piix3-usb-uhci -device usb-tablet -qmp +> +tcp::4444,server,nowait -monitor stdio -cpu qemu64 -machine +> +pc-i440fx-2.3,accel=tcg,usb=off +> +> +destination side: +> +x86_64-softmmu/qemu-system-x86_64 -netdev tap,id=hn0 -device +> +e1000,id=net-pci0,netdev=hn0,mac=52:54:00:12:34:65 -boot c -drive +> +if=none,file=/home/lizj/ubuntu.raw,id=drive-virtio-disk0 -device +> +virtio-blk-pci,bus=pci.0,addr=0x4,drive=drive-virtio-disk0,id=virtio-disk0 +> +-vnc :7 -m 128 -smp 1 -device piix3-usb-uhci -device usb-tablet -qmp +> +tcp::4444,server,nowait -monitor stdio -cpu qemu64 -machine +> +pc-i440fx-2.3,accel=tcg,usb=off -incoming tcp:0:8881 +> +> +3) start migration +> +with 1000M NIC, migration will finish within 3 min. +> +> +at source: +> +(qemu) migrate tcp:192.168.2.66:8881 +> +after saving ram complete +> +e9e725df678d392b1a83b3a917f332bb +> +qemu-system-x86_64: end ram md5 +> +(qemu) +> +> +at destination: +> +...skip... +> +Completed load of VM with exit code 0 seq iteration 1264 +> +Completed load of VM with exit code 0 seq iteration 1265 +> +Completed load of VM with exit code 0 seq iteration 1266 +> +qemu-system-x86_64: after loading state section id 2(ram) +> +49c2dac7bde0e5e22db7280dcb3824f9 +> +qemu-system-x86_64: end ram md5 +> +qemu-system-x86_64: qemu_loadvm_state: after cpu_synchronize_all_post_init +> +> +49c2dac7bde0e5e22db7280dcb3824f9 +> +qemu-system-x86_64: end ram md5 +> +> +This occurs occasionally and only at tcg machine. It seems that +> +some pages dirtied in source side don't transferred to destination. +> +This problem can be reproduced even if we disable virtio. +> +> +Is it OK for some pages that not transferred to destination when do +> +migration ? Or is it a bug? +I'm pretty sure that means it's a bug. Hard to find though, I guess +at least memtest is smaller than a big OS. I think I'd dump the whole +of memory on both sides, hexdump and diff them - I'd guess it would +just be one byte/word different, maybe that would offer some idea what +wrote it. + +Dave + +> +Any idea... +> +> +=================md5 check patch============================= +> +> +diff --git a/Makefile.target b/Makefile.target +> +index 962d004..e2cb8e9 100644 +> +--- a/Makefile.target +> ++++ b/Makefile.target +> +@@ -139,7 +139,7 @@ obj-y += memory.o cputlb.o +> +obj-y += memory_mapping.o +> +obj-y += dump.o +> +obj-y += migration/ram.o migration/savevm.o +> +-LIBS := $(libs_softmmu) $(LIBS) +> ++LIBS := $(libs_softmmu) $(LIBS) -lplumb +> +> +# xen support +> +obj-$(CONFIG_XEN) += xen-common.o +> +diff --git a/migration/ram.c b/migration/ram.c +> +index 1eb155a..3b7a09d 100644 +> +--- a/migration/ram.c +> ++++ b/migration/ram.c +> +@@ -2513,7 +2513,7 @@ static int ram_load(QEMUFile *f, void *opaque, int +> +version_id) +> +} +> +> +rcu_read_unlock(); +> +- DPRINTF("Completed load of VM with exit code %d seq iteration " +> ++ fprintf(stderr, "Completed load of VM with exit code %d seq iteration " +> +"%" PRIu64 "\n", ret, seq_iter); +> +return ret; +> +} +> +diff --git a/migration/savevm.c b/migration/savevm.c +> +index 0ad1b93..3feaa61 100644 +> +--- a/migration/savevm.c +> ++++ b/migration/savevm.c +> +@@ -891,6 +891,29 @@ void qemu_savevm_state_header(QEMUFile *f) +> +> +} +> +> ++#include "exec/ram_addr.h" +> ++#include "qemu/rcu_queue.h" +> ++#include <clplumbing/md5.h> +> ++#ifndef MD5_DIGEST_LENGTH +> ++#define MD5_DIGEST_LENGTH 16 +> ++#endif +> ++ +> ++static void check_host_md5(void) +> ++{ +> ++ int i; +> ++ unsigned char md[MD5_DIGEST_LENGTH]; +> ++ rcu_read_lock(); +> ++ RAMBlock *block = QLIST_FIRST_RCU(&ram_list.blocks);/* Only check +> +'pc.ram' block */ +> ++ rcu_read_unlock(); +> ++ +> ++ MD5(block->host, block->used_length, md); +> ++ for(i = 0; i < MD5_DIGEST_LENGTH; i++) { +> ++ fprintf(stderr, "%02x", md[i]); +> ++ } +> ++ fprintf(stderr, "\n"); +> ++ error_report("end ram md5"); +> ++} +> ++ +> +void qemu_savevm_state_begin(QEMUFile *f, +> +const MigrationParams *params) +> +{ +> +@@ -1056,6 +1079,10 @@ void qemu_savevm_state_complete_precopy(QEMUFile *f, +> +bool iterable_only) +> +save_section_header(f, se, QEMU_VM_SECTION_END); +> +> +ret = se->ops->save_live_complete_precopy(f, se->opaque); +> ++ +> ++ fprintf(stderr, "after saving %s complete\n", se->idstr); +> ++ check_host_md5(); +> ++ +> +trace_savevm_section_end(se->idstr, se->section_id, ret); +> +save_section_footer(f, se); +> +if (ret < 0) { +> +@@ -1791,6 +1818,11 @@ static int qemu_loadvm_state_main(QEMUFile *f, +> +MigrationIncomingState *mis) +> +section_id, le->se->idstr); +> +return ret; +> +} +> ++ if (section_type == QEMU_VM_SECTION_END) { +> ++ error_report("after loading state section id %d(%s)", +> ++ section_id, le->se->idstr); +> ++ check_host_md5(); +> ++ } +> +if (!check_section_footer(f, le)) { +> +return -EINVAL; +> +} +> +@@ -1901,6 +1933,8 @@ int qemu_loadvm_state(QEMUFile *f) +> +} +> +> +cpu_synchronize_all_post_init(); +> ++ error_report("%s: after cpu_synchronize_all_post_init\n", __func__); +> ++ check_host_md5(); +> +> +return ret; +> +} +> +> +> +-- +Dr. David Alan Gilbert / address@hidden / Manchester, UK + +On 2015/12/3 17:24, Dr. David Alan Gilbert wrote: +* Li Zhijian (address@hidden) wrote: +Hi all, + +Does anyboday remember the similar issue post by hailiang months ago +http://patchwork.ozlabs.org/patch/454322/ +At least tow bugs about migration had been fixed since that. +Yes, I wondered what happened to that. +And now we found the same issue at the tcg vm(kvm is fine), after migration, +the content VM's memory is inconsistent. +Hmm, TCG only - I don't know much about that; but I guess something must +be accessing memory without using the proper macros/functions so +it doesn't mark it as dirty. +we add a patch to check memory content, you can find it from affix + +steps to reporduce: +1) apply the patch and re-build qemu +2) prepare the ubuntu guest and run memtest in grub. +soruce side: +x86_64-softmmu/qemu-system-x86_64 -netdev tap,id=hn0 -device +e1000,id=net-pci0,netdev=hn0,mac=52:54:00:12:34:65 -boot c -drive +if=none,file=/home/lizj/ubuntu.raw,id=drive-virtio-disk0 -device +virtio-blk-pci,bus=pci.0,addr=0x4,drive=drive-virtio-disk0,id=virtio-disk0 +-vnc :7 -m 128 -smp 1 -device piix3-usb-uhci -device usb-tablet -qmp +tcp::4444,server,nowait -monitor stdio -cpu qemu64 -machine +pc-i440fx-2.3,accel=tcg,usb=off + +destination side: +x86_64-softmmu/qemu-system-x86_64 -netdev tap,id=hn0 -device +e1000,id=net-pci0,netdev=hn0,mac=52:54:00:12:34:65 -boot c -drive +if=none,file=/home/lizj/ubuntu.raw,id=drive-virtio-disk0 -device +virtio-blk-pci,bus=pci.0,addr=0x4,drive=drive-virtio-disk0,id=virtio-disk0 +-vnc :7 -m 128 -smp 1 -device piix3-usb-uhci -device usb-tablet -qmp +tcp::4444,server,nowait -monitor stdio -cpu qemu64 -machine +pc-i440fx-2.3,accel=tcg,usb=off -incoming tcp:0:8881 + +3) start migration +with 1000M NIC, migration will finish within 3 min. + +at source: +(qemu) migrate tcp:192.168.2.66:8881 +after saving ram complete +e9e725df678d392b1a83b3a917f332bb +qemu-system-x86_64: end ram md5 +(qemu) + +at destination: +...skip... +Completed load of VM with exit code 0 seq iteration 1264 +Completed load of VM with exit code 0 seq iteration 1265 +Completed load of VM with exit code 0 seq iteration 1266 +qemu-system-x86_64: after loading state section id 2(ram) +49c2dac7bde0e5e22db7280dcb3824f9 +qemu-system-x86_64: end ram md5 +qemu-system-x86_64: qemu_loadvm_state: after cpu_synchronize_all_post_init + +49c2dac7bde0e5e22db7280dcb3824f9 +qemu-system-x86_64: end ram md5 + +This occurs occasionally and only at tcg machine. It seems that +some pages dirtied in source side don't transferred to destination. +This problem can be reproduced even if we disable virtio. + +Is it OK for some pages that not transferred to destination when do +migration ? Or is it a bug? +I'm pretty sure that means it's a bug. Hard to find though, I guess +at least memtest is smaller than a big OS. I think I'd dump the whole +of memory on both sides, hexdump and diff them - I'd guess it would +just be one byte/word different, maybe that would offer some idea what +wrote it. +Maybe one better way to do that is with the help of userfaultfd's write-protect +capability. It is still in the development by Andrea Arcangeli, but there +is a RFC version available, please refer to +http://www.spinics.net/lists/linux-mm/msg97422.html +ï¼I'm developing live memory snapshot which based on it, maybe this is another +scene where we +can use userfaultfd's WP ;) ). +Dave +Any idea... + +=================md5 check patch============================= + +diff --git a/Makefile.target b/Makefile.target +index 962d004..e2cb8e9 100644 +--- a/Makefile.target ++++ b/Makefile.target +@@ -139,7 +139,7 @@ obj-y += memory.o cputlb.o + obj-y += memory_mapping.o + obj-y += dump.o + obj-y += migration/ram.o migration/savevm.o +-LIBS := $(libs_softmmu) $(LIBS) ++LIBS := $(libs_softmmu) $(LIBS) -lplumb + + # xen support + obj-$(CONFIG_XEN) += xen-common.o +diff --git a/migration/ram.c b/migration/ram.c +index 1eb155a..3b7a09d 100644 +--- a/migration/ram.c ++++ b/migration/ram.c +@@ -2513,7 +2513,7 @@ static int ram_load(QEMUFile *f, void *opaque, int +version_id) + } + + rcu_read_unlock(); +- DPRINTF("Completed load of VM with exit code %d seq iteration " ++ fprintf(stderr, "Completed load of VM with exit code %d seq iteration " + "%" PRIu64 "\n", ret, seq_iter); + return ret; + } +diff --git a/migration/savevm.c b/migration/savevm.c +index 0ad1b93..3feaa61 100644 +--- a/migration/savevm.c ++++ b/migration/savevm.c +@@ -891,6 +891,29 @@ void qemu_savevm_state_header(QEMUFile *f) + + } + ++#include "exec/ram_addr.h" ++#include "qemu/rcu_queue.h" ++#include <clplumbing/md5.h> ++#ifndef MD5_DIGEST_LENGTH ++#define MD5_DIGEST_LENGTH 16 ++#endif ++ ++static void check_host_md5(void) ++{ ++ int i; ++ unsigned char md[MD5_DIGEST_LENGTH]; ++ rcu_read_lock(); ++ RAMBlock *block = QLIST_FIRST_RCU(&ram_list.blocks);/* Only check +'pc.ram' block */ ++ rcu_read_unlock(); ++ ++ MD5(block->host, block->used_length, md); ++ for(i = 0; i < MD5_DIGEST_LENGTH; i++) { ++ fprintf(stderr, "%02x", md[i]); ++ } ++ fprintf(stderr, "\n"); ++ error_report("end ram md5"); ++} ++ + void qemu_savevm_state_begin(QEMUFile *f, + const MigrationParams *params) + { +@@ -1056,6 +1079,10 @@ void qemu_savevm_state_complete_precopy(QEMUFile *f, +bool iterable_only) + save_section_header(f, se, QEMU_VM_SECTION_END); + + ret = se->ops->save_live_complete_precopy(f, se->opaque); ++ ++ fprintf(stderr, "after saving %s complete\n", se->idstr); ++ check_host_md5(); ++ + trace_savevm_section_end(se->idstr, se->section_id, ret); + save_section_footer(f, se); + if (ret < 0) { +@@ -1791,6 +1818,11 @@ static int qemu_loadvm_state_main(QEMUFile *f, +MigrationIncomingState *mis) + section_id, le->se->idstr); + return ret; + } ++ if (section_type == QEMU_VM_SECTION_END) { ++ error_report("after loading state section id %d(%s)", ++ section_id, le->se->idstr); ++ check_host_md5(); ++ } + if (!check_section_footer(f, le)) { + return -EINVAL; + } +@@ -1901,6 +1933,8 @@ int qemu_loadvm_state(QEMUFile *f) + } + + cpu_synchronize_all_post_init(); ++ error_report("%s: after cpu_synchronize_all_post_init\n", __func__); ++ check_host_md5(); + + return ret; + } +-- +Dr. David Alan Gilbert / address@hidden / Manchester, UK + +. + +On 12/03/2015 05:37 PM, Hailiang Zhang wrote: +On 2015/12/3 17:24, Dr. David Alan Gilbert wrote: +* Li Zhijian (address@hidden) wrote: +Hi all, + +Does anyboday remember the similar issue post by hailiang months ago +http://patchwork.ozlabs.org/patch/454322/ +At least tow bugs about migration had been fixed since that. +Yes, I wondered what happened to that. +And now we found the same issue at the tcg vm(kvm is fine), after +migration, +the content VM's memory is inconsistent. +Hmm, TCG only - I don't know much about that; but I guess something must +be accessing memory without using the proper macros/functions so +it doesn't mark it as dirty. +we add a patch to check memory content, you can find it from affix + +steps to reporduce: +1) apply the patch and re-build qemu +2) prepare the ubuntu guest and run memtest in grub. +soruce side: +x86_64-softmmu/qemu-system-x86_64 -netdev tap,id=hn0 -device +e1000,id=net-pci0,netdev=hn0,mac=52:54:00:12:34:65 -boot c -drive +if=none,file=/home/lizj/ubuntu.raw,id=drive-virtio-disk0 -device +virtio-blk-pci,bus=pci.0,addr=0x4,drive=drive-virtio-disk0,id=virtio-disk0 + +-vnc :7 -m 128 -smp 1 -device piix3-usb-uhci -device usb-tablet -qmp +tcp::4444,server,nowait -monitor stdio -cpu qemu64 -machine +pc-i440fx-2.3,accel=tcg,usb=off + +destination side: +x86_64-softmmu/qemu-system-x86_64 -netdev tap,id=hn0 -device +e1000,id=net-pci0,netdev=hn0,mac=52:54:00:12:34:65 -boot c -drive +if=none,file=/home/lizj/ubuntu.raw,id=drive-virtio-disk0 -device +virtio-blk-pci,bus=pci.0,addr=0x4,drive=drive-virtio-disk0,id=virtio-disk0 + +-vnc :7 -m 128 -smp 1 -device piix3-usb-uhci -device usb-tablet -qmp +tcp::4444,server,nowait -monitor stdio -cpu qemu64 -machine +pc-i440fx-2.3,accel=tcg,usb=off -incoming tcp:0:8881 + +3) start migration +with 1000M NIC, migration will finish within 3 min. + +at source: +(qemu) migrate tcp:192.168.2.66:8881 +after saving ram complete +e9e725df678d392b1a83b3a917f332bb +qemu-system-x86_64: end ram md5 +(qemu) + +at destination: +...skip... +Completed load of VM with exit code 0 seq iteration 1264 +Completed load of VM with exit code 0 seq iteration 1265 +Completed load of VM with exit code 0 seq iteration 1266 +qemu-system-x86_64: after loading state section id 2(ram) +49c2dac7bde0e5e22db7280dcb3824f9 +qemu-system-x86_64: end ram md5 +qemu-system-x86_64: qemu_loadvm_state: after +cpu_synchronize_all_post_init + +49c2dac7bde0e5e22db7280dcb3824f9 +qemu-system-x86_64: end ram md5 + +This occurs occasionally and only at tcg machine. It seems that +some pages dirtied in source side don't transferred to destination. +This problem can be reproduced even if we disable virtio. + +Is it OK for some pages that not transferred to destination when do +migration ? Or is it a bug? +I'm pretty sure that means it's a bug. Hard to find though, I guess +at least memtest is smaller than a big OS. I think I'd dump the whole +of memory on both sides, hexdump and diff them - I'd guess it would +just be one byte/word different, maybe that would offer some idea what +wrote it. +Maybe one better way to do that is with the help of userfaultfd's +write-protect +capability. It is still in the development by Andrea Arcangeli, but there +is a RFC version available, please refer to +http://www.spinics.net/lists/linux-mm/msg97422.html +ï¼I'm developing live memory snapshot which based on it, maybe this is +another scene where we +can use userfaultfd's WP ;) ). +sounds good. + +thanks +Li +Dave +Any idea... + +=================md5 check patch============================= + +diff --git a/Makefile.target b/Makefile.target +index 962d004..e2cb8e9 100644 +--- a/Makefile.target ++++ b/Makefile.target +@@ -139,7 +139,7 @@ obj-y += memory.o cputlb.o + obj-y += memory_mapping.o + obj-y += dump.o + obj-y += migration/ram.o migration/savevm.o +-LIBS := $(libs_softmmu) $(LIBS) ++LIBS := $(libs_softmmu) $(LIBS) -lplumb + + # xen support + obj-$(CONFIG_XEN) += xen-common.o +diff --git a/migration/ram.c b/migration/ram.c +index 1eb155a..3b7a09d 100644 +--- a/migration/ram.c ++++ b/migration/ram.c +@@ -2513,7 +2513,7 @@ static int ram_load(QEMUFile *f, void *opaque, int +version_id) + } + + rcu_read_unlock(); +- DPRINTF("Completed load of VM with exit code %d seq iteration " ++ fprintf(stderr, "Completed load of VM with exit code %d seq +iteration " + "%" PRIu64 "\n", ret, seq_iter); + return ret; + } +diff --git a/migration/savevm.c b/migration/savevm.c +index 0ad1b93..3feaa61 100644 +--- a/migration/savevm.c ++++ b/migration/savevm.c +@@ -891,6 +891,29 @@ void qemu_savevm_state_header(QEMUFile *f) + + } + ++#include "exec/ram_addr.h" ++#include "qemu/rcu_queue.h" ++#include <clplumbing/md5.h> ++#ifndef MD5_DIGEST_LENGTH ++#define MD5_DIGEST_LENGTH 16 ++#endif ++ ++static void check_host_md5(void) ++{ ++ int i; ++ unsigned char md[MD5_DIGEST_LENGTH]; ++ rcu_read_lock(); ++ RAMBlock *block = QLIST_FIRST_RCU(&ram_list.blocks);/* Only check +'pc.ram' block */ ++ rcu_read_unlock(); ++ ++ MD5(block->host, block->used_length, md); ++ for(i = 0; i < MD5_DIGEST_LENGTH; i++) { ++ fprintf(stderr, "%02x", md[i]); ++ } ++ fprintf(stderr, "\n"); ++ error_report("end ram md5"); ++} ++ + void qemu_savevm_state_begin(QEMUFile *f, + const MigrationParams *params) + { +@@ -1056,6 +1079,10 @@ void +qemu_savevm_state_complete_precopy(QEMUFile *f, +bool iterable_only) + save_section_header(f, se, QEMU_VM_SECTION_END); + + ret = se->ops->save_live_complete_precopy(f, se->opaque); ++ ++ fprintf(stderr, "after saving %s complete\n", se->idstr); ++ check_host_md5(); ++ + trace_savevm_section_end(se->idstr, se->section_id, ret); + save_section_footer(f, se); + if (ret < 0) { +@@ -1791,6 +1818,11 @@ static int qemu_loadvm_state_main(QEMUFile *f, +MigrationIncomingState *mis) + section_id, le->se->idstr); + return ret; + } ++ if (section_type == QEMU_VM_SECTION_END) { ++ error_report("after loading state section id %d(%s)", ++ section_id, le->se->idstr); ++ check_host_md5(); ++ } + if (!check_section_footer(f, le)) { + return -EINVAL; + } +@@ -1901,6 +1933,8 @@ int qemu_loadvm_state(QEMUFile *f) + } + + cpu_synchronize_all_post_init(); ++ error_report("%s: after cpu_synchronize_all_post_init\n", +__func__); ++ check_host_md5(); + + return ret; + } +-- +Dr. David Alan Gilbert / address@hidden / Manchester, UK + +. +. +-- +Best regards. +Li Zhijian (8555) + +On 12/03/2015 05:24 PM, Dr. David Alan Gilbert wrote: +* Li Zhijian (address@hidden) wrote: +Hi all, + +Does anyboday remember the similar issue post by hailiang months ago +http://patchwork.ozlabs.org/patch/454322/ +At least tow bugs about migration had been fixed since that. +Yes, I wondered what happened to that. +And now we found the same issue at the tcg vm(kvm is fine), after migration, +the content VM's memory is inconsistent. +Hmm, TCG only - I don't know much about that; but I guess something must +be accessing memory without using the proper macros/functions so +it doesn't mark it as dirty. +we add a patch to check memory content, you can find it from affix + +steps to reporduce: +1) apply the patch and re-build qemu +2) prepare the ubuntu guest and run memtest in grub. +soruce side: +x86_64-softmmu/qemu-system-x86_64 -netdev tap,id=hn0 -device +e1000,id=net-pci0,netdev=hn0,mac=52:54:00:12:34:65 -boot c -drive +if=none,file=/home/lizj/ubuntu.raw,id=drive-virtio-disk0 -device +virtio-blk-pci,bus=pci.0,addr=0x4,drive=drive-virtio-disk0,id=virtio-disk0 +-vnc :7 -m 128 -smp 1 -device piix3-usb-uhci -device usb-tablet -qmp +tcp::4444,server,nowait -monitor stdio -cpu qemu64 -machine +pc-i440fx-2.3,accel=tcg,usb=off + +destination side: +x86_64-softmmu/qemu-system-x86_64 -netdev tap,id=hn0 -device +e1000,id=net-pci0,netdev=hn0,mac=52:54:00:12:34:65 -boot c -drive +if=none,file=/home/lizj/ubuntu.raw,id=drive-virtio-disk0 -device +virtio-blk-pci,bus=pci.0,addr=0x4,drive=drive-virtio-disk0,id=virtio-disk0 +-vnc :7 -m 128 -smp 1 -device piix3-usb-uhci -device usb-tablet -qmp +tcp::4444,server,nowait -monitor stdio -cpu qemu64 -machine +pc-i440fx-2.3,accel=tcg,usb=off -incoming tcp:0:8881 + +3) start migration +with 1000M NIC, migration will finish within 3 min. + +at source: +(qemu) migrate tcp:192.168.2.66:8881 +after saving ram complete +e9e725df678d392b1a83b3a917f332bb +qemu-system-x86_64: end ram md5 +(qemu) + +at destination: +...skip... +Completed load of VM with exit code 0 seq iteration 1264 +Completed load of VM with exit code 0 seq iteration 1265 +Completed load of VM with exit code 0 seq iteration 1266 +qemu-system-x86_64: after loading state section id 2(ram) +49c2dac7bde0e5e22db7280dcb3824f9 +qemu-system-x86_64: end ram md5 +qemu-system-x86_64: qemu_loadvm_state: after cpu_synchronize_all_post_init + +49c2dac7bde0e5e22db7280dcb3824f9 +qemu-system-x86_64: end ram md5 + +This occurs occasionally and only at tcg machine. It seems that +some pages dirtied in source side don't transferred to destination. +This problem can be reproduced even if we disable virtio. + +Is it OK for some pages that not transferred to destination when do +migration ? Or is it a bug? +I'm pretty sure that means it's a bug. Hard to find though, I guess +at least memtest is smaller than a big OS. I think I'd dump the whole +of memory on both sides, hexdump and diff them - I'd guess it would +just be one byte/word different, maybe that would offer some idea what +wrote it. +I try to dump and compare them, more than 10 pages are different. +in source side, they are random value rather than always 'FF' 'FB' 'EF' +'BF'... in destination. +and not all of the different pages are continuous. + +thanks +Li +Dave +Any idea... + +=================md5 check patch============================= + +diff --git a/Makefile.target b/Makefile.target +index 962d004..e2cb8e9 100644 +--- a/Makefile.target ++++ b/Makefile.target +@@ -139,7 +139,7 @@ obj-y += memory.o cputlb.o + obj-y += memory_mapping.o + obj-y += dump.o + obj-y += migration/ram.o migration/savevm.o +-LIBS := $(libs_softmmu) $(LIBS) ++LIBS := $(libs_softmmu) $(LIBS) -lplumb + + # xen support + obj-$(CONFIG_XEN) += xen-common.o +diff --git a/migration/ram.c b/migration/ram.c +index 1eb155a..3b7a09d 100644 +--- a/migration/ram.c ++++ b/migration/ram.c +@@ -2513,7 +2513,7 @@ static int ram_load(QEMUFile *f, void *opaque, int +version_id) + } + + rcu_read_unlock(); +- DPRINTF("Completed load of VM with exit code %d seq iteration " ++ fprintf(stderr, "Completed load of VM with exit code %d seq iteration " + "%" PRIu64 "\n", ret, seq_iter); + return ret; + } +diff --git a/migration/savevm.c b/migration/savevm.c +index 0ad1b93..3feaa61 100644 +--- a/migration/savevm.c ++++ b/migration/savevm.c +@@ -891,6 +891,29 @@ void qemu_savevm_state_header(QEMUFile *f) + + } + ++#include "exec/ram_addr.h" ++#include "qemu/rcu_queue.h" ++#include <clplumbing/md5.h> ++#ifndef MD5_DIGEST_LENGTH ++#define MD5_DIGEST_LENGTH 16 ++#endif ++ ++static void check_host_md5(void) ++{ ++ int i; ++ unsigned char md[MD5_DIGEST_LENGTH]; ++ rcu_read_lock(); ++ RAMBlock *block = QLIST_FIRST_RCU(&ram_list.blocks);/* Only check +'pc.ram' block */ ++ rcu_read_unlock(); ++ ++ MD5(block->host, block->used_length, md); ++ for(i = 0; i < MD5_DIGEST_LENGTH; i++) { ++ fprintf(stderr, "%02x", md[i]); ++ } ++ fprintf(stderr, "\n"); ++ error_report("end ram md5"); ++} ++ + void qemu_savevm_state_begin(QEMUFile *f, + const MigrationParams *params) + { +@@ -1056,6 +1079,10 @@ void qemu_savevm_state_complete_precopy(QEMUFile *f, +bool iterable_only) + save_section_header(f, se, QEMU_VM_SECTION_END); + + ret = se->ops->save_live_complete_precopy(f, se->opaque); ++ ++ fprintf(stderr, "after saving %s complete\n", se->idstr); ++ check_host_md5(); ++ + trace_savevm_section_end(se->idstr, se->section_id, ret); + save_section_footer(f, se); + if (ret < 0) { +@@ -1791,6 +1818,11 @@ static int qemu_loadvm_state_main(QEMUFile *f, +MigrationIncomingState *mis) + section_id, le->se->idstr); + return ret; + } ++ if (section_type == QEMU_VM_SECTION_END) { ++ error_report("after loading state section id %d(%s)", ++ section_id, le->se->idstr); ++ check_host_md5(); ++ } + if (!check_section_footer(f, le)) { + return -EINVAL; + } +@@ -1901,6 +1933,8 @@ int qemu_loadvm_state(QEMUFile *f) + } + + cpu_synchronize_all_post_init(); ++ error_report("%s: after cpu_synchronize_all_post_init\n", __func__); ++ check_host_md5(); + + return ret; + } +-- +Dr. David Alan Gilbert / address@hidden / Manchester, UK + + +. +-- +Best regards. +Li Zhijian (8555) + +* Li Zhijian (address@hidden) wrote: +> +> +> +On 12/03/2015 05:24 PM, Dr. David Alan Gilbert wrote: +> +>* Li Zhijian (address@hidden) wrote: +> +>>Hi all, +> +>> +> +>>Does anyboday remember the similar issue post by hailiang months ago +> +>> +http://patchwork.ozlabs.org/patch/454322/ +> +>>At least tow bugs about migration had been fixed since that. +> +> +> +>Yes, I wondered what happened to that. +> +> +> +>>And now we found the same issue at the tcg vm(kvm is fine), after migration, +> +>>the content VM's memory is inconsistent. +> +> +> +>Hmm, TCG only - I don't know much about that; but I guess something must +> +>be accessing memory without using the proper macros/functions so +> +>it doesn't mark it as dirty. +> +> +> +>>we add a patch to check memory content, you can find it from affix +> +>> +> +>>steps to reporduce: +> +>>1) apply the patch and re-build qemu +> +>>2) prepare the ubuntu guest and run memtest in grub. +> +>>soruce side: +> +>>x86_64-softmmu/qemu-system-x86_64 -netdev tap,id=hn0 -device +> +>>e1000,id=net-pci0,netdev=hn0,mac=52:54:00:12:34:65 -boot c -drive +> +>>if=none,file=/home/lizj/ubuntu.raw,id=drive-virtio-disk0 -device +> +>>virtio-blk-pci,bus=pci.0,addr=0x4,drive=drive-virtio-disk0,id=virtio-disk0 +> +>>-vnc :7 -m 128 -smp 1 -device piix3-usb-uhci -device usb-tablet -qmp +> +>>tcp::4444,server,nowait -monitor stdio -cpu qemu64 -machine +> +>>pc-i440fx-2.3,accel=tcg,usb=off +> +>> +> +>>destination side: +> +>>x86_64-softmmu/qemu-system-x86_64 -netdev tap,id=hn0 -device +> +>>e1000,id=net-pci0,netdev=hn0,mac=52:54:00:12:34:65 -boot c -drive +> +>>if=none,file=/home/lizj/ubuntu.raw,id=drive-virtio-disk0 -device +> +>>virtio-blk-pci,bus=pci.0,addr=0x4,drive=drive-virtio-disk0,id=virtio-disk0 +> +>>-vnc :7 -m 128 -smp 1 -device piix3-usb-uhci -device usb-tablet -qmp +> +>>tcp::4444,server,nowait -monitor stdio -cpu qemu64 -machine +> +>>pc-i440fx-2.3,accel=tcg,usb=off -incoming tcp:0:8881 +> +>> +> +>>3) start migration +> +>>with 1000M NIC, migration will finish within 3 min. +> +>> +> +>>at source: +> +>>(qemu) migrate tcp:192.168.2.66:8881 +> +>>after saving ram complete +> +>>e9e725df678d392b1a83b3a917f332bb +> +>>qemu-system-x86_64: end ram md5 +> +>>(qemu) +> +>> +> +>>at destination: +> +>>...skip... +> +>>Completed load of VM with exit code 0 seq iteration 1264 +> +>>Completed load of VM with exit code 0 seq iteration 1265 +> +>>Completed load of VM with exit code 0 seq iteration 1266 +> +>>qemu-system-x86_64: after loading state section id 2(ram) +> +>>49c2dac7bde0e5e22db7280dcb3824f9 +> +>>qemu-system-x86_64: end ram md5 +> +>>qemu-system-x86_64: qemu_loadvm_state: after cpu_synchronize_all_post_init +> +>> +> +>>49c2dac7bde0e5e22db7280dcb3824f9 +> +>>qemu-system-x86_64: end ram md5 +> +>> +> +>>This occurs occasionally and only at tcg machine. It seems that +> +>>some pages dirtied in source side don't transferred to destination. +> +>>This problem can be reproduced even if we disable virtio. +> +>> +> +>>Is it OK for some pages that not transferred to destination when do +> +>>migration ? Or is it a bug? +> +> +> +>I'm pretty sure that means it's a bug. Hard to find though, I guess +> +>at least memtest is smaller than a big OS. I think I'd dump the whole +> +>of memory on both sides, hexdump and diff them - I'd guess it would +> +>just be one byte/word different, maybe that would offer some idea what +> +>wrote it. +> +> +I try to dump and compare them, more than 10 pages are different. +> +in source side, they are random value rather than always 'FF' 'FB' 'EF' +> +'BF'... in destination. +> +> +and not all of the different pages are continuous. +I wonder if it happens on all of memtest's different test patterns, +perhaps it might be possible to narrow it down if you tell memtest +to only run one test at a time. + +Dave + +> +> +thanks +> +Li +> +> +> +> +> +>Dave +> +> +> +>>Any idea... +> +>> +> +>>=================md5 check patch============================= +> +>> +> +>>diff --git a/Makefile.target b/Makefile.target +> +>>index 962d004..e2cb8e9 100644 +> +>>--- a/Makefile.target +> +>>+++ b/Makefile.target +> +>>@@ -139,7 +139,7 @@ obj-y += memory.o cputlb.o +> +>> obj-y += memory_mapping.o +> +>> obj-y += dump.o +> +>> obj-y += migration/ram.o migration/savevm.o +> +>>-LIBS := $(libs_softmmu) $(LIBS) +> +>>+LIBS := $(libs_softmmu) $(LIBS) -lplumb +> +>> +> +>> # xen support +> +>> obj-$(CONFIG_XEN) += xen-common.o +> +>>diff --git a/migration/ram.c b/migration/ram.c +> +>>index 1eb155a..3b7a09d 100644 +> +>>--- a/migration/ram.c +> +>>+++ b/migration/ram.c +> +>>@@ -2513,7 +2513,7 @@ static int ram_load(QEMUFile *f, void *opaque, int +> +>>version_id) +> +>> } +> +>> +> +>> rcu_read_unlock(); +> +>>- DPRINTF("Completed load of VM with exit code %d seq iteration " +> +>>+ fprintf(stderr, "Completed load of VM with exit code %d seq iteration " +> +>> "%" PRIu64 "\n", ret, seq_iter); +> +>> return ret; +> +>> } +> +>>diff --git a/migration/savevm.c b/migration/savevm.c +> +>>index 0ad1b93..3feaa61 100644 +> +>>--- a/migration/savevm.c +> +>>+++ b/migration/savevm.c +> +>>@@ -891,6 +891,29 @@ void qemu_savevm_state_header(QEMUFile *f) +> +>> +> +>> } +> +>> +> +>>+#include "exec/ram_addr.h" +> +>>+#include "qemu/rcu_queue.h" +> +>>+#include <clplumbing/md5.h> +> +>>+#ifndef MD5_DIGEST_LENGTH +> +>>+#define MD5_DIGEST_LENGTH 16 +> +>>+#endif +> +>>+ +> +>>+static void check_host_md5(void) +> +>>+{ +> +>>+ int i; +> +>>+ unsigned char md[MD5_DIGEST_LENGTH]; +> +>>+ rcu_read_lock(); +> +>>+ RAMBlock *block = QLIST_FIRST_RCU(&ram_list.blocks);/* Only check +> +>>'pc.ram' block */ +> +>>+ rcu_read_unlock(); +> +>>+ +> +>>+ MD5(block->host, block->used_length, md); +> +>>+ for(i = 0; i < MD5_DIGEST_LENGTH; i++) { +> +>>+ fprintf(stderr, "%02x", md[i]); +> +>>+ } +> +>>+ fprintf(stderr, "\n"); +> +>>+ error_report("end ram md5"); +> +>>+} +> +>>+ +> +>> void qemu_savevm_state_begin(QEMUFile *f, +> +>> const MigrationParams *params) +> +>> { +> +>>@@ -1056,6 +1079,10 @@ void qemu_savevm_state_complete_precopy(QEMUFile *f, +> +>>bool iterable_only) +> +>> save_section_header(f, se, QEMU_VM_SECTION_END); +> +>> +> +>> ret = se->ops->save_live_complete_precopy(f, se->opaque); +> +>>+ +> +>>+ fprintf(stderr, "after saving %s complete\n", se->idstr); +> +>>+ check_host_md5(); +> +>>+ +> +>> trace_savevm_section_end(se->idstr, se->section_id, ret); +> +>> save_section_footer(f, se); +> +>> if (ret < 0) { +> +>>@@ -1791,6 +1818,11 @@ static int qemu_loadvm_state_main(QEMUFile *f, +> +>>MigrationIncomingState *mis) +> +>> section_id, le->se->idstr); +> +>> return ret; +> +>> } +> +>>+ if (section_type == QEMU_VM_SECTION_END) { +> +>>+ error_report("after loading state section id %d(%s)", +> +>>+ section_id, le->se->idstr); +> +>>+ check_host_md5(); +> +>>+ } +> +>> if (!check_section_footer(f, le)) { +> +>> return -EINVAL; +> +>> } +> +>>@@ -1901,6 +1933,8 @@ int qemu_loadvm_state(QEMUFile *f) +> +>> } +> +>> +> +>> cpu_synchronize_all_post_init(); +> +>>+ error_report("%s: after cpu_synchronize_all_post_init\n", __func__); +> +>>+ check_host_md5(); +> +>> +> +>> return ret; +> +>> } +> +>> +> +>> +> +>> +> +>-- +> +>Dr. David Alan Gilbert / address@hidden / Manchester, UK +> +> +> +> +> +>. +> +> +> +> +-- +> +Best regards. +> +Li Zhijian (8555) +> +> +-- +Dr. David Alan Gilbert / address@hidden / Manchester, UK + +Li Zhijian <address@hidden> wrote: +> +Hi all, +> +> +Does anyboday remember the similar issue post by hailiang months ago +> +http://patchwork.ozlabs.org/patch/454322/ +> +At least tow bugs about migration had been fixed since that. +> +> +And now we found the same issue at the tcg vm(kvm is fine), after +> +migration, the content VM's memory is inconsistent. +> +> +we add a patch to check memory content, you can find it from affix +> +> +steps to reporduce: +> +1) apply the patch and re-build qemu +> +2) prepare the ubuntu guest and run memtest in grub. +> +soruce side: +> +x86_64-softmmu/qemu-system-x86_64 -netdev tap,id=hn0 -device +> +e1000,id=net-pci0,netdev=hn0,mac=52:54:00:12:34:65 -boot c -drive +> +if=none,file=/home/lizj/ubuntu.raw,id=drive-virtio-disk0 -device +> +virtio-blk-pci,bus=pci.0,addr=0x4,drive=drive-virtio-disk0,id=virtio-disk0 +> +-vnc :7 -m 128 -smp 1 -device piix3-usb-uhci -device usb-tablet -qmp +> +tcp::4444,server,nowait -monitor stdio -cpu qemu64 -machine +> +pc-i440fx-2.3,accel=tcg,usb=off +> +> +destination side: +> +x86_64-softmmu/qemu-system-x86_64 -netdev tap,id=hn0 -device +> +e1000,id=net-pci0,netdev=hn0,mac=52:54:00:12:34:65 -boot c -drive +> +if=none,file=/home/lizj/ubuntu.raw,id=drive-virtio-disk0 -device +> +virtio-blk-pci,bus=pci.0,addr=0x4,drive=drive-virtio-disk0,id=virtio-disk0 +> +-vnc :7 -m 128 -smp 1 -device piix3-usb-uhci -device usb-tablet -qmp +> +tcp::4444,server,nowait -monitor stdio -cpu qemu64 -machine +> +pc-i440fx-2.3,accel=tcg,usb=off -incoming tcp:0:8881 +> +> +3) start migration +> +with 1000M NIC, migration will finish within 3 min. +> +> +at source: +> +(qemu) migrate tcp:192.168.2.66:8881 +> +after saving ram complete +> +e9e725df678d392b1a83b3a917f332bb +> +qemu-system-x86_64: end ram md5 +> +(qemu) +> +> +at destination: +> +...skip... +> +Completed load of VM with exit code 0 seq iteration 1264 +> +Completed load of VM with exit code 0 seq iteration 1265 +> +Completed load of VM with exit code 0 seq iteration 1266 +> +qemu-system-x86_64: after loading state section id 2(ram) +> +49c2dac7bde0e5e22db7280dcb3824f9 +> +qemu-system-x86_64: end ram md5 +> +qemu-system-x86_64: qemu_loadvm_state: after cpu_synchronize_all_post_init +> +> +49c2dac7bde0e5e22db7280dcb3824f9 +> +qemu-system-x86_64: end ram md5 +> +> +This occurs occasionally and only at tcg machine. It seems that +> +some pages dirtied in source side don't transferred to destination. +> +This problem can be reproduced even if we disable virtio. +> +> +Is it OK for some pages that not transferred to destination when do +> +migration ? Or is it a bug? +> +> +Any idea... +Thanks for describing how to reproduce the bug. +If some pages are not transferred to destination then it is a bug, so we +need to know what the problem is, notice that the problem can be that +TCG is not marking dirty some page, that Migration code "forgets" about +that page, or anything eles altogether, that is what we need to find. + +There are more posibilities, I am not sure that memtest is on 32bit +mode, and it is inside posibility that we are missing some state when we +are on real mode. + +Will try to take a look at this. + +THanks, again. + + +> +> +=================md5 check patch============================= +> +> +diff --git a/Makefile.target b/Makefile.target +> +index 962d004..e2cb8e9 100644 +> +--- a/Makefile.target +> ++++ b/Makefile.target +> +@@ -139,7 +139,7 @@ obj-y += memory.o cputlb.o +> +obj-y += memory_mapping.o +> +obj-y += dump.o +> +obj-y += migration/ram.o migration/savevm.o +> +-LIBS := $(libs_softmmu) $(LIBS) +> ++LIBS := $(libs_softmmu) $(LIBS) -lplumb +> +> +# xen support +> +obj-$(CONFIG_XEN) += xen-common.o +> +diff --git a/migration/ram.c b/migration/ram.c +> +index 1eb155a..3b7a09d 100644 +> +--- a/migration/ram.c +> ++++ b/migration/ram.c +> +@@ -2513,7 +2513,7 @@ static int ram_load(QEMUFile *f, void *opaque, +> +int version_id) +> +} +> +> +rcu_read_unlock(); +> +- DPRINTF("Completed load of VM with exit code %d seq iteration " +> ++ fprintf(stderr, "Completed load of VM with exit code %d seq iteration " +> +"%" PRIu64 "\n", ret, seq_iter); +> +return ret; +> +} +> +diff --git a/migration/savevm.c b/migration/savevm.c +> +index 0ad1b93..3feaa61 100644 +> +--- a/migration/savevm.c +> ++++ b/migration/savevm.c +> +@@ -891,6 +891,29 @@ void qemu_savevm_state_header(QEMUFile *f) +> +> +} +> +> ++#include "exec/ram_addr.h" +> ++#include "qemu/rcu_queue.h" +> ++#include <clplumbing/md5.h> +> ++#ifndef MD5_DIGEST_LENGTH +> ++#define MD5_DIGEST_LENGTH 16 +> ++#endif +> ++ +> ++static void check_host_md5(void) +> ++{ +> ++ int i; +> ++ unsigned char md[MD5_DIGEST_LENGTH]; +> ++ rcu_read_lock(); +> ++ RAMBlock *block = QLIST_FIRST_RCU(&ram_list.blocks);/* Only check +> +'pc.ram' block */ +> ++ rcu_read_unlock(); +> ++ +> ++ MD5(block->host, block->used_length, md); +> ++ for(i = 0; i < MD5_DIGEST_LENGTH; i++) { +> ++ fprintf(stderr, "%02x", md[i]); +> ++ } +> ++ fprintf(stderr, "\n"); +> ++ error_report("end ram md5"); +> ++} +> ++ +> +void qemu_savevm_state_begin(QEMUFile *f, +> +const MigrationParams *params) +> +{ +> +@@ -1056,6 +1079,10 @@ void +> +qemu_savevm_state_complete_precopy(QEMUFile *f, bool iterable_only) +> +save_section_header(f, se, QEMU_VM_SECTION_END); +> +> +ret = se->ops->save_live_complete_precopy(f, se->opaque); +> ++ +> ++ fprintf(stderr, "after saving %s complete\n", se->idstr); +> ++ check_host_md5(); +> ++ +> +trace_savevm_section_end(se->idstr, se->section_id, ret); +> +save_section_footer(f, se); +> +if (ret < 0) { +> +@@ -1791,6 +1818,11 @@ static int qemu_loadvm_state_main(QEMUFile *f, +> +MigrationIncomingState *mis) +> +section_id, le->se->idstr); +> +return ret; +> +} +> ++ if (section_type == QEMU_VM_SECTION_END) { +> ++ error_report("after loading state section id %d(%s)", +> ++ section_id, le->se->idstr); +> ++ check_host_md5(); +> ++ } +> +if (!check_section_footer(f, le)) { +> +return -EINVAL; +> +} +> +@@ -1901,6 +1933,8 @@ int qemu_loadvm_state(QEMUFile *f) +> +} +> +> +cpu_synchronize_all_post_init(); +> ++ error_report("%s: after cpu_synchronize_all_post_init\n", __func__); +> ++ check_host_md5(); +> +> +return ret; +> +} + +> +> +Thanks for describing how to reproduce the bug. +> +If some pages are not transferred to destination then it is a bug, so we need +> +to know what the problem is, notice that the problem can be that TCG is not +> +marking dirty some page, that Migration code "forgets" about that page, or +> +anything eles altogether, that is what we need to find. +> +> +There are more posibilities, I am not sure that memtest is on 32bit mode, and +> +it is inside posibility that we are missing some state when we are on real +> +mode. +> +> +Will try to take a look at this. +> +> +THanks, again. +> +Hi Juan & Amit + + Do you think we should add a mechanism to check the data integrity during LM +like Zhijian's patch did? it may be very helpful for developers. + Actually, I did the similar thing before in order to make sure that I did the +right thing we I change the code related to LM. + +Liang + +On (Fri) 04 Dec 2015 [01:43:07], Li, Liang Z wrote: +> +> +> +> Thanks for describing how to reproduce the bug. +> +> If some pages are not transferred to destination then it is a bug, so we +> +> need +> +> to know what the problem is, notice that the problem can be that TCG is not +> +> marking dirty some page, that Migration code "forgets" about that page, or +> +> anything eles altogether, that is what we need to find. +> +> +> +> There are more posibilities, I am not sure that memtest is on 32bit mode, +> +> and +> +> it is inside posibility that we are missing some state when we are on real +> +> mode. +> +> +> +> Will try to take a look at this. +> +> +> +> THanks, again. +> +> +> +> +Hi Juan & Amit +> +> +Do you think we should add a mechanism to check the data integrity during LM +> +like Zhijian's patch did? it may be very helpful for developers. +> +Actually, I did the similar thing before in order to make sure that I did +> +the right thing we I change the code related to LM. +If you mean for debugging, something that's not always on, then I'm +fine with it. + +A script that goes along that shows the result of comparison of the +diff will be helpful too, something that shows how many pages are +differnt, how many bytes in a page on average, and so on. + + Amit + diff --git a/results/classifier/001/mistranslation/74545755 b/results/classifier/001/mistranslation/74545755 new file mode 100644 index 000000000..32d247ac7 --- /dev/null +++ b/results/classifier/001/mistranslation/74545755 @@ -0,0 +1,344 @@ +mistranslation: 0.752 +instruction: 0.700 +other: 0.683 +semantic: 0.669 + +[Bug Report][RFC PATCH 0/1] block: fix failing assert on paused VM migration + +There's a bug (failing assert) which is reproduced during migration of +a paused VM. I am able to reproduce it on a stand with 2 nodes and a common +NFS share, with VM's disk on that share. + +root@fedora40-1-vm:~# virsh domblklist alma8-vm + Target Source +------------------------------------------ + sda /mnt/shared/images/alma8.qcow2 + +root@fedora40-1-vm:~# df -Th /mnt/shared +Filesystem Type Size Used Avail Use% Mounted on +127.0.0.1:/srv/nfsd nfs4 63G 16G 48G 25% /mnt/shared + +On the 1st node: + +root@fedora40-1-vm:~# virsh start alma8-vm ; virsh suspend alma8-vm +root@fedora40-1-vm:~# virsh migrate --compressed --p2p --persistent +--undefinesource --live alma8-vm qemu+ssh://fedora40-2-vm/system + +Then on the 2nd node: + +root@fedora40-2-vm:~# virsh migrate --compressed --p2p --persistent +--undefinesource --live alma8-vm qemu+ssh://fedora40-1-vm/system +error: operation failed: domain is not running + +root@fedora40-2-vm:~# tail -3 /var/log/libvirt/qemu/alma8-vm.log +2024-09-19 13:53:33.336+0000: initiating migration +qemu-system-x86_64: ../block.c:6976: int +bdrv_inactivate_recurse(BlockDriverState *): Assertion `!(bs->open_flags & +BDRV_O_INACTIVE)' failed. +2024-09-19 13:53:42.991+0000: shutting down, reason=crashed + +Backtrace: + +(gdb) bt +#0 0x00007f7eaa2f1664 in __pthread_kill_implementation () at /lib64/libc.so.6 +#1 0x00007f7eaa298c4e in raise () at /lib64/libc.so.6 +#2 0x00007f7eaa280902 in abort () at /lib64/libc.so.6 +#3 0x00007f7eaa28081e in __assert_fail_base.cold () at /lib64/libc.so.6 +#4 0x00007f7eaa290d87 in __assert_fail () at /lib64/libc.so.6 +#5 0x0000563c38b95eb8 in bdrv_inactivate_recurse (bs=0x563c3b6c60c0) at +../block.c:6976 +#6 0x0000563c38b95aeb in bdrv_inactivate_all () at ../block.c:7038 +#7 0x0000563c3884d354 in qemu_savevm_state_complete_precopy_non_iterable +(f=0x563c3b700c20, in_postcopy=false, inactivate_disks=true) + at ../migration/savevm.c:1571 +#8 0x0000563c3884dc1a in qemu_savevm_state_complete_precopy (f=0x563c3b700c20, +iterable_only=false, inactivate_disks=true) at ../migration/savevm.c:1631 +#9 0x0000563c3883a340 in migration_completion_precopy (s=0x563c3b4d51f0, +current_active_state=<optimized out>) at ../migration/migration.c:2780 +#10 migration_completion (s=0x563c3b4d51f0) at ../migration/migration.c:2844 +#11 migration_iteration_run (s=0x563c3b4d51f0) at ../migration/migration.c:3270 +#12 migration_thread (opaque=0x563c3b4d51f0) at ../migration/migration.c:3536 +#13 0x0000563c38dbcf14 in qemu_thread_start (args=0x563c3c2d5bf0) at +../util/qemu-thread-posix.c:541 +#14 0x00007f7eaa2ef6d7 in start_thread () at /lib64/libc.so.6 +#15 0x00007f7eaa373414 in clone () at /lib64/libc.so.6 + +What happens here is that after 1st migration BDS related to HDD remains +inactive as VM is still paused. Then when we initiate 2nd migration, +bdrv_inactivate_all() leads to the attempt to set BDRV_O_INACTIVE flag +on that node which is already set, thus assert fails. + +Attached patch which simply skips setting flag if it's already set is more +of a kludge than a clean solution. Should we use more sophisticated logic +which allows some of the nodes be in inactive state prior to the migration, +and takes them into account during bdrv_inactivate_all()? Comments would +be appreciated. + +Andrey + +Andrey Drobyshev (1): + block: do not fail when inactivating node which is inactive + + block.c | 10 +++++++++- + 1 file changed, 9 insertions(+), 1 deletion(-) + +-- +2.39.3 + +Instead of throwing an assert let's just ignore that flag is already set +and return. We assume that it's going to be safe to ignore. Otherwise +this assert fails when migrating a paused VM back and forth. + +Ideally we'd like to have a more sophisticated solution, e.g. not even +scan the nodes which should be inactive at this point. + +Signed-off-by: Andrey Drobyshev <andrey.drobyshev@virtuozzo.com> +--- + block.c | 10 +++++++++- + 1 file changed, 9 insertions(+), 1 deletion(-) + +diff --git a/block.c b/block.c +index 7d90007cae..c1dcf906d1 100644 +--- a/block.c ++++ b/block.c +@@ -6973,7 +6973,15 @@ static int GRAPH_RDLOCK +bdrv_inactivate_recurse(BlockDriverState *bs) + return 0; + } + +- assert(!(bs->open_flags & BDRV_O_INACTIVE)); ++ if (bs->open_flags & BDRV_O_INACTIVE) { ++ /* ++ * Return here instead of throwing assert as a workaround to ++ * prevent failure on migrating paused VM. ++ * Here we assume that if we're trying to inactivate BDS that's ++ * already inactive, it's safe to just ignore it. ++ */ ++ return 0; ++ } + + /* Inactivate this node */ + if (bs->drv->bdrv_inactivate) { +-- +2.39.3 + +[add migration maintainers] + +On 24.09.24 15:56, Andrey Drobyshev wrote: +Instead of throwing an assert let's just ignore that flag is already set +and return. We assume that it's going to be safe to ignore. Otherwise +this assert fails when migrating a paused VM back and forth. + +Ideally we'd like to have a more sophisticated solution, e.g. not even +scan the nodes which should be inactive at this point. + +Signed-off-by: Andrey Drobyshev <andrey.drobyshev@virtuozzo.com> +--- + block.c | 10 +++++++++- + 1 file changed, 9 insertions(+), 1 deletion(-) + +diff --git a/block.c b/block.c +index 7d90007cae..c1dcf906d1 100644 +--- a/block.c ++++ b/block.c +@@ -6973,7 +6973,15 @@ static int GRAPH_RDLOCK +bdrv_inactivate_recurse(BlockDriverState *bs) + return 0; + } +- assert(!(bs->open_flags & BDRV_O_INACTIVE)); ++ if (bs->open_flags & BDRV_O_INACTIVE) { ++ /* ++ * Return here instead of throwing assert as a workaround to ++ * prevent failure on migrating paused VM. ++ * Here we assume that if we're trying to inactivate BDS that's ++ * already inactive, it's safe to just ignore it. ++ */ ++ return 0; ++ } +/* Inactivate this node */ +if (bs->drv->bdrv_inactivate) { +I doubt that this a correct way to go. + +As far as I understand, "inactive" actually means that "storage is not belong to +qemu, but to someone else (another qemu process for example), and may be changed +transparently". In turn this means that Qemu should do nothing with inactive disks. So the +problem is that nobody called bdrv_activate_all on target, and we shouldn't ignore that. + +Hmm, I see in process_incoming_migration_bh() we do call bdrv_activate_all(), +but only in some scenarios. May be, the condition should be less strict here. + +Why we need any condition here at all? Don't we want to activate block-layer on +target after migration anyway? + +-- +Best regards, +Vladimir + +On 9/30/24 12:25 PM, Vladimir Sementsov-Ogievskiy wrote: +> +[add migration maintainers] +> +> +On 24.09.24 15:56, Andrey Drobyshev wrote: +> +> [...] +> +> +I doubt that this a correct way to go. +> +> +As far as I understand, "inactive" actually means that "storage is not +> +belong to qemu, but to someone else (another qemu process for example), +> +and may be changed transparently". In turn this means that Qemu should +> +do nothing with inactive disks. So the problem is that nobody called +> +bdrv_activate_all on target, and we shouldn't ignore that. +> +> +Hmm, I see in process_incoming_migration_bh() we do call +> +bdrv_activate_all(), but only in some scenarios. May be, the condition +> +should be less strict here. +> +> +Why we need any condition here at all? Don't we want to activate +> +block-layer on target after migration anyway? +> +Hmm I'm not sure about the unconditional activation, since we at least +have to honor LATE_BLOCK_ACTIVATE cap if it's set (and probably delay it +in such a case). In current libvirt upstream I see such code: + +> +/* Migration capabilities which should always be enabled as long as they +> +> +* are supported by QEMU. If the capability is supposed to be enabled on both +> +> +* sides of migration, it won't be enabled unless both sides support it. +> +> +*/ +> +> +static const qemuMigrationParamsAlwaysOnItem qemuMigrationParamsAlwaysOn[] = +> +{ +> +> +{QEMU_MIGRATION_CAP_PAUSE_BEFORE_SWITCHOVER, +> +> +QEMU_MIGRATION_SOURCE}, +> +> +> +> +{QEMU_MIGRATION_CAP_LATE_BLOCK_ACTIVATE, +> +> +QEMU_MIGRATION_DESTINATION}, +> +> +}; +which means that libvirt always wants LATE_BLOCK_ACTIVATE to be set. + +The code from process_incoming_migration_bh() you're referring to: + +> +/* If capability late_block_activate is set: +> +> +* Only fire up the block code now if we're going to restart the +> +> +* VM, else 'cont' will do it. +> +> +* This causes file locking to happen; so we don't want it to happen +> +> +* unless we really are starting the VM. +> +> +*/ +> +> +if (!migrate_late_block_activate() || +> +> +(autostart && (!global_state_received() || +> +> +runstate_is_live(global_state_get_runstate())))) { +> +> +/* Make sure all file formats throw away their mutable metadata. +> +> +> +* If we get an error here, just don't restart the VM yet. */ +> +> +bdrv_activate_all(&local_err); +> +> +if (local_err) { +> +> +error_report_err(local_err); +> +> +local_err = NULL; +> +> +autostart = false; +> +> +} +> +> +} +It states explicitly that we're either going to start VM right at this +point if (autostart == true), or we wait till "cont" command happens. +None of this is going to happen if we start another migration while +still being in PAUSED state. So I think it seems reasonable to take +such case into account. For instance, this patch does prevent the crash: + +> +diff --git a/migration/migration.c b/migration/migration.c +> +index ae2be31557..3222f6745b 100644 +> +--- a/migration/migration.c +> ++++ b/migration/migration.c +> +@@ -733,7 +733,8 @@ static void process_incoming_migration_bh(void *opaque) +> +*/ +> +if (!migrate_late_block_activate() || +> +(autostart && (!global_state_received() || +> +- runstate_is_live(global_state_get_runstate())))) { +> ++ runstate_is_live(global_state_get_runstate()))) || +> ++ (!autostart && global_state_get_runstate() == RUN_STATE_PAUSED)) { +> +/* Make sure all file formats throw away their mutable metadata. +> +* If we get an error here, just don't restart the VM yet. */ +> +bdrv_activate_all(&local_err); +What are your thoughts on it? + +Andrey + diff --git a/results/classifier/001/mistranslation/80604314 b/results/classifier/001/mistranslation/80604314 new file mode 100644 index 000000000..798c2e866 --- /dev/null +++ b/results/classifier/001/mistranslation/80604314 @@ -0,0 +1,1480 @@ +mistranslation: 0.922 +other: 0.898 +semantic: 0.890 +instruction: 0.877 + +[BUG] vhost-vdpa: qemu-system-s390x crashes with second virtio-net-ccw device + +When I start qemu with a second virtio-net-ccw device (i.e. adding +-device virtio-net-ccw in addition to the autogenerated device), I get +a segfault. gdb points to + +#0 0x000055d6ab52681d in virtio_net_get_config (vdev=<optimized out>, + config=0x55d6ad9e3f80 "RT") at /home/cohuck/git/qemu/hw/net/virtio-net.c:146 +146 if (nc->peer->info->type == NET_CLIENT_DRIVER_VHOST_VDPA) { + +(backtrace doesn't go further) + +Starting qemu with no additional "-device virtio-net-ccw" (i.e., only +the autogenerated virtio-net-ccw device is present) works. Specifying +several "-device virtio-net-pci" works as well. + +Things break with 1e0a84ea49b6 ("vhost-vdpa: introduce vhost-vdpa net +client"), 38140cc4d971 ("vhost_net: introduce set_config & get_config") +works (in-between state does not compile). + +This is reproducible with tcg as well. Same problem both with +--enable-vhost-vdpa and --disable-vhost-vdpa. + +Have not yet tried to figure out what might be special with +virtio-ccw... anyone have an idea? + +[This should probably be considered a blocker?] + +On Fri, Jul 24, 2020 at 03:27:18PM +0200, Cornelia Huck wrote: +> +When I start qemu with a second virtio-net-ccw device (i.e. adding +> +-device virtio-net-ccw in addition to the autogenerated device), I get +> +a segfault. gdb points to +> +> +#0 0x000055d6ab52681d in virtio_net_get_config (vdev=<optimized out>, +> +config=0x55d6ad9e3f80 "RT") at +> +/home/cohuck/git/qemu/hw/net/virtio-net.c:146 +> +146 if (nc->peer->info->type == NET_CLIENT_DRIVER_VHOST_VDPA) { +> +> +(backtrace doesn't go further) +> +> +Starting qemu with no additional "-device virtio-net-ccw" (i.e., only +> +the autogenerated virtio-net-ccw device is present) works. Specifying +> +several "-device virtio-net-pci" works as well. +> +> +Things break with 1e0a84ea49b6 ("vhost-vdpa: introduce vhost-vdpa net +> +client"), 38140cc4d971 ("vhost_net: introduce set_config & get_config") +> +works (in-between state does not compile). +Ouch. I didn't test all in-between states :( +But I wish we had a 0-day instrastructure like kernel has, +that catches things like that. + +> +This is reproducible with tcg as well. Same problem both with +> +--enable-vhost-vdpa and --disable-vhost-vdpa. +> +> +Have not yet tried to figure out what might be special with +> +virtio-ccw... anyone have an idea? +> +> +[This should probably be considered a blocker?] + +On Fri, 24 Jul 2020 09:30:58 -0400 +"Michael S. Tsirkin" <mst@redhat.com> wrote: + +> +On Fri, Jul 24, 2020 at 03:27:18PM +0200, Cornelia Huck wrote: +> +> When I start qemu with a second virtio-net-ccw device (i.e. adding +> +> -device virtio-net-ccw in addition to the autogenerated device), I get +> +> a segfault. gdb points to +> +> +> +> #0 0x000055d6ab52681d in virtio_net_get_config (vdev=<optimized out>, +> +> config=0x55d6ad9e3f80 "RT") at +> +> /home/cohuck/git/qemu/hw/net/virtio-net.c:146 +> +> 146 if (nc->peer->info->type == NET_CLIENT_DRIVER_VHOST_VDPA) { +> +> +> +> (backtrace doesn't go further) +The core was incomplete, but running under gdb directly shows that it +is just a bog-standard config space access (first for that device). + +The cause of the crash is that nc->peer is not set... no idea how that +can happen, not that familiar with that part of QEMU. (Should the code +check, or is that really something that should not happen?) + +What I don't understand is why it is set correctly for the first, +autogenerated virtio-net-ccw device, but not for the second one, and +why virtio-net-pci doesn't show these problems. The only difference +between -ccw and -pci that comes to my mind here is that config space +accesses for ccw are done via an asynchronous operation, so timing +might be different. + +> +> +> +> Starting qemu with no additional "-device virtio-net-ccw" (i.e., only +> +> the autogenerated virtio-net-ccw device is present) works. Specifying +> +> several "-device virtio-net-pci" works as well. +> +> +> +> Things break with 1e0a84ea49b6 ("vhost-vdpa: introduce vhost-vdpa net +> +> client"), 38140cc4d971 ("vhost_net: introduce set_config & get_config") +> +> works (in-between state does not compile). +> +> +Ouch. I didn't test all in-between states :( +> +But I wish we had a 0-day instrastructure like kernel has, +> +that catches things like that. +Yep, that would be useful... so patchew only builds the complete series? + +> +> +> This is reproducible with tcg as well. Same problem both with +> +> --enable-vhost-vdpa and --disable-vhost-vdpa. +> +> +> +> Have not yet tried to figure out what might be special with +> +> virtio-ccw... anyone have an idea? +> +> +> +> [This should probably be considered a blocker?] +I think so, as it makes s390x unusable with more that one +virtio-net-ccw device, and I don't even see a workaround. + +On Fri, Jul 24, 2020 at 04:56:27PM +0200, Cornelia Huck wrote: +> +On Fri, 24 Jul 2020 09:30:58 -0400 +> +"Michael S. Tsirkin" <mst@redhat.com> wrote: +> +> +> On Fri, Jul 24, 2020 at 03:27:18PM +0200, Cornelia Huck wrote: +> +> > When I start qemu with a second virtio-net-ccw device (i.e. adding +> +> > -device virtio-net-ccw in addition to the autogenerated device), I get +> +> > a segfault. gdb points to +> +> > +> +> > #0 0x000055d6ab52681d in virtio_net_get_config (vdev=<optimized out>, +> +> > config=0x55d6ad9e3f80 "RT") at +> +> > /home/cohuck/git/qemu/hw/net/virtio-net.c:146 +> +> > 146 if (nc->peer->info->type == NET_CLIENT_DRIVER_VHOST_VDPA) { +> +> > +> +> > (backtrace doesn't go further) +> +> +The core was incomplete, but running under gdb directly shows that it +> +is just a bog-standard config space access (first for that device). +> +> +The cause of the crash is that nc->peer is not set... no idea how that +> +can happen, not that familiar with that part of QEMU. (Should the code +> +check, or is that really something that should not happen?) +> +> +What I don't understand is why it is set correctly for the first, +> +autogenerated virtio-net-ccw device, but not for the second one, and +> +why virtio-net-pci doesn't show these problems. The only difference +> +between -ccw and -pci that comes to my mind here is that config space +> +accesses for ccw are done via an asynchronous operation, so timing +> +might be different. +Hopefully Jason has an idea. Could you post a full command line +please? Do you need a working guest to trigger this? Does this trigger +on an x86 host? + +> +> > +> +> > Starting qemu with no additional "-device virtio-net-ccw" (i.e., only +> +> > the autogenerated virtio-net-ccw device is present) works. Specifying +> +> > several "-device virtio-net-pci" works as well. +> +> > +> +> > Things break with 1e0a84ea49b6 ("vhost-vdpa: introduce vhost-vdpa net +> +> > client"), 38140cc4d971 ("vhost_net: introduce set_config & get_config") +> +> > works (in-between state does not compile). +> +> +> +> Ouch. I didn't test all in-between states :( +> +> But I wish we had a 0-day instrastructure like kernel has, +> +> that catches things like that. +> +> +Yep, that would be useful... so patchew only builds the complete series? +> +> +> +> +> > This is reproducible with tcg as well. Same problem both with +> +> > --enable-vhost-vdpa and --disable-vhost-vdpa. +> +> > +> +> > Have not yet tried to figure out what might be special with +> +> > virtio-ccw... anyone have an idea? +> +> > +> +> > [This should probably be considered a blocker?] +> +> +I think so, as it makes s390x unusable with more that one +> +virtio-net-ccw device, and I don't even see a workaround. + +On Fri, 24 Jul 2020 11:17:57 -0400 +"Michael S. Tsirkin" <mst@redhat.com> wrote: + +> +On Fri, Jul 24, 2020 at 04:56:27PM +0200, Cornelia Huck wrote: +> +> On Fri, 24 Jul 2020 09:30:58 -0400 +> +> "Michael S. Tsirkin" <mst@redhat.com> wrote: +> +> +> +> > On Fri, Jul 24, 2020 at 03:27:18PM +0200, Cornelia Huck wrote: +> +> > > When I start qemu with a second virtio-net-ccw device (i.e. adding +> +> > > -device virtio-net-ccw in addition to the autogenerated device), I get +> +> > > a segfault. gdb points to +> +> > > +> +> > > #0 0x000055d6ab52681d in virtio_net_get_config (vdev=<optimized out>, +> +> > > config=0x55d6ad9e3f80 "RT") at +> +> > > /home/cohuck/git/qemu/hw/net/virtio-net.c:146 +> +> > > 146 if (nc->peer->info->type == NET_CLIENT_DRIVER_VHOST_VDPA) { +> +> > > +> +> > > (backtrace doesn't go further) +> +> +> +> The core was incomplete, but running under gdb directly shows that it +> +> is just a bog-standard config space access (first for that device). +> +> +> +> The cause of the crash is that nc->peer is not set... no idea how that +> +> can happen, not that familiar with that part of QEMU. (Should the code +> +> check, or is that really something that should not happen?) +> +> +> +> What I don't understand is why it is set correctly for the first, +> +> autogenerated virtio-net-ccw device, but not for the second one, and +> +> why virtio-net-pci doesn't show these problems. The only difference +> +> between -ccw and -pci that comes to my mind here is that config space +> +> accesses for ccw are done via an asynchronous operation, so timing +> +> might be different. +> +> +Hopefully Jason has an idea. Could you post a full command line +> +please? Do you need a working guest to trigger this? Does this trigger +> +on an x86 host? +Yes, it does trigger with tcg-on-x86 as well. I've been using + +s390x-softmmu/qemu-system-s390x -M s390-ccw-virtio,accel=tcg -cpu qemu,zpci=on +-m 1024 -nographic -device virtio-scsi-ccw,id=scsi0,devno=fe.0.0001 +-drive file=/path/to/image,format=qcow2,if=none,id=drive-scsi0-0-0-0 +-device +scsi-hd,bus=scsi0.0,channel=0,scsi-id=0,lun=0,drive=drive-scsi0-0-0-0,id=scsi0-0-0-0,bootindex=1 + +-device virtio-net-ccw + +It seems it needs the guest actually doing something with the nics; I +cannot reproduce the crash if I use the old advent calendar moon buggy +image and just add a virtio-net-ccw device. + +(I don't think it's a problem with my local build, as I see the problem +both on my laptop and on an LPAR.) + +> +> +> > > +> +> > > Starting qemu with no additional "-device virtio-net-ccw" (i.e., only +> +> > > the autogenerated virtio-net-ccw device is present) works. Specifying +> +> > > several "-device virtio-net-pci" works as well. +> +> > > +> +> > > Things break with 1e0a84ea49b6 ("vhost-vdpa: introduce vhost-vdpa net +> +> > > client"), 38140cc4d971 ("vhost_net: introduce set_config & get_config") +> +> > > works (in-between state does not compile). +> +> > +> +> > Ouch. I didn't test all in-between states :( +> +> > But I wish we had a 0-day instrastructure like kernel has, +> +> > that catches things like that. +> +> +> +> Yep, that would be useful... so patchew only builds the complete series? +> +> +> +> > +> +> > > This is reproducible with tcg as well. Same problem both with +> +> > > --enable-vhost-vdpa and --disable-vhost-vdpa. +> +> > > +> +> > > Have not yet tried to figure out what might be special with +> +> > > virtio-ccw... anyone have an idea? +> +> > > +> +> > > [This should probably be considered a blocker?] +> +> +> +> I think so, as it makes s390x unusable with more that one +> +> virtio-net-ccw device, and I don't even see a workaround. +> + +On 2020/7/24 ä¸å11:34, Cornelia Huck wrote: +On Fri, 24 Jul 2020 11:17:57 -0400 +"Michael S. Tsirkin"<mst@redhat.com> wrote: +On Fri, Jul 24, 2020 at 04:56:27PM +0200, Cornelia Huck wrote: +On Fri, 24 Jul 2020 09:30:58 -0400 +"Michael S. Tsirkin"<mst@redhat.com> wrote: +On Fri, Jul 24, 2020 at 03:27:18PM +0200, Cornelia Huck wrote: +When I start qemu with a second virtio-net-ccw device (i.e. adding +-device virtio-net-ccw in addition to the autogenerated device), I get +a segfault. gdb points to + +#0 0x000055d6ab52681d in virtio_net_get_config (vdev=<optimized out>, + config=0x55d6ad9e3f80 "RT") at +/home/cohuck/git/qemu/hw/net/virtio-net.c:146 +146 if (nc->peer->info->type == NET_CLIENT_DRIVER_VHOST_VDPA) { + +(backtrace doesn't go further) +The core was incomplete, but running under gdb directly shows that it +is just a bog-standard config space access (first for that device). + +The cause of the crash is that nc->peer is not set... no idea how that +can happen, not that familiar with that part of QEMU. (Should the code +check, or is that really something that should not happen?) + +What I don't understand is why it is set correctly for the first, +autogenerated virtio-net-ccw device, but not for the second one, and +why virtio-net-pci doesn't show these problems. The only difference +between -ccw and -pci that comes to my mind here is that config space +accesses for ccw are done via an asynchronous operation, so timing +might be different. +Hopefully Jason has an idea. Could you post a full command line +please? Do you need a working guest to trigger this? Does this trigger +on an x86 host? +Yes, it does trigger with tcg-on-x86 as well. I've been using + +s390x-softmmu/qemu-system-s390x -M s390-ccw-virtio,accel=tcg -cpu qemu,zpci=on +-m 1024 -nographic -device virtio-scsi-ccw,id=scsi0,devno=fe.0.0001 +-drive file=/path/to/image,format=qcow2,if=none,id=drive-scsi0-0-0-0 +-device +scsi-hd,bus=scsi0.0,channel=0,scsi-id=0,lun=0,drive=drive-scsi0-0-0-0,id=scsi0-0-0-0,bootindex=1 +-device virtio-net-ccw + +It seems it needs the guest actually doing something with the nics; I +cannot reproduce the crash if I use the old advent calendar moon buggy +image and just add a virtio-net-ccw device. + +(I don't think it's a problem with my local build, as I see the problem +both on my laptop and on an LPAR.) +It looks to me we forget the check the existence of peer. + +Please try the attached patch to see if it works. + +Thanks +0001-virtio-net-check-the-existence-of-peer-before-accesi.patch +Description: +Text Data + +On Sat, 25 Jul 2020 08:40:07 +0800 +Jason Wang <jasowang@redhat.com> wrote: + +> +On 2020/7/24 ä¸å11:34, Cornelia Huck wrote: +> +> On Fri, 24 Jul 2020 11:17:57 -0400 +> +> "Michael S. Tsirkin"<mst@redhat.com> wrote: +> +> +> +>> On Fri, Jul 24, 2020 at 04:56:27PM +0200, Cornelia Huck wrote: +> +>>> On Fri, 24 Jul 2020 09:30:58 -0400 +> +>>> "Michael S. Tsirkin"<mst@redhat.com> wrote: +> +>>> +> +>>>> On Fri, Jul 24, 2020 at 03:27:18PM +0200, Cornelia Huck wrote: +> +>>>>> When I start qemu with a second virtio-net-ccw device (i.e. adding +> +>>>>> -device virtio-net-ccw in addition to the autogenerated device), I get +> +>>>>> a segfault. gdb points to +> +>>>>> +> +>>>>> #0 0x000055d6ab52681d in virtio_net_get_config (vdev=<optimized out>, +> +>>>>> config=0x55d6ad9e3f80 "RT") at +> +>>>>> /home/cohuck/git/qemu/hw/net/virtio-net.c:146 +> +>>>>> 146 if (nc->peer->info->type == NET_CLIENT_DRIVER_VHOST_VDPA) { +> +>>>>> +> +>>>>> (backtrace doesn't go further) +> +>>> The core was incomplete, but running under gdb directly shows that it +> +>>> is just a bog-standard config space access (first for that device). +> +>>> +> +>>> The cause of the crash is that nc->peer is not set... no idea how that +> +>>> can happen, not that familiar with that part of QEMU. (Should the code +> +>>> check, or is that really something that should not happen?) +> +>>> +> +>>> What I don't understand is why it is set correctly for the first, +> +>>> autogenerated virtio-net-ccw device, but not for the second one, and +> +>>> why virtio-net-pci doesn't show these problems. The only difference +> +>>> between -ccw and -pci that comes to my mind here is that config space +> +>>> accesses for ccw are done via an asynchronous operation, so timing +> +>>> might be different. +> +>> Hopefully Jason has an idea. Could you post a full command line +> +>> please? Do you need a working guest to trigger this? Does this trigger +> +>> on an x86 host? +> +> Yes, it does trigger with tcg-on-x86 as well. I've been using +> +> +> +> s390x-softmmu/qemu-system-s390x -M s390-ccw-virtio,accel=tcg -cpu +> +> qemu,zpci=on +> +> -m 1024 -nographic -device virtio-scsi-ccw,id=scsi0,devno=fe.0.0001 +> +> -drive file=/path/to/image,format=qcow2,if=none,id=drive-scsi0-0-0-0 +> +> -device +> +> scsi-hd,bus=scsi0.0,channel=0,scsi-id=0,lun=0,drive=drive-scsi0-0-0-0,id=scsi0-0-0-0,bootindex=1 +> +> -device virtio-net-ccw +> +> +> +> It seems it needs the guest actually doing something with the nics; I +> +> cannot reproduce the crash if I use the old advent calendar moon buggy +> +> image and just add a virtio-net-ccw device. +> +> +> +> (I don't think it's a problem with my local build, as I see the problem +> +> both on my laptop and on an LPAR.) +> +> +> +It looks to me we forget the check the existence of peer. +> +> +Please try the attached patch to see if it works. +Thanks, that patch gets my guest up and running again. So, FWIW, + +Tested-by: Cornelia Huck <cohuck@redhat.com> + +Any idea why this did not hit with virtio-net-pci (or the autogenerated +virtio-net-ccw device)? + +On 2020/7/27 ä¸å2:43, Cornelia Huck wrote: +On Sat, 25 Jul 2020 08:40:07 +0800 +Jason Wang <jasowang@redhat.com> wrote: +On 2020/7/24 ä¸å11:34, Cornelia Huck wrote: +On Fri, 24 Jul 2020 11:17:57 -0400 +"Michael S. Tsirkin"<mst@redhat.com> wrote: +On Fri, Jul 24, 2020 at 04:56:27PM +0200, Cornelia Huck wrote: +On Fri, 24 Jul 2020 09:30:58 -0400 +"Michael S. Tsirkin"<mst@redhat.com> wrote: +On Fri, Jul 24, 2020 at 03:27:18PM +0200, Cornelia Huck wrote: +When I start qemu with a second virtio-net-ccw device (i.e. adding +-device virtio-net-ccw in addition to the autogenerated device), I get +a segfault. gdb points to + +#0 0x000055d6ab52681d in virtio_net_get_config (vdev=<optimized out>, + config=0x55d6ad9e3f80 "RT") at +/home/cohuck/git/qemu/hw/net/virtio-net.c:146 +146 if (nc->peer->info->type == NET_CLIENT_DRIVER_VHOST_VDPA) { + +(backtrace doesn't go further) +The core was incomplete, but running under gdb directly shows that it +is just a bog-standard config space access (first for that device). + +The cause of the crash is that nc->peer is not set... no idea how that +can happen, not that familiar with that part of QEMU. (Should the code +check, or is that really something that should not happen?) + +What I don't understand is why it is set correctly for the first, +autogenerated virtio-net-ccw device, but not for the second one, and +why virtio-net-pci doesn't show these problems. The only difference +between -ccw and -pci that comes to my mind here is that config space +accesses for ccw are done via an asynchronous operation, so timing +might be different. +Hopefully Jason has an idea. Could you post a full command line +please? Do you need a working guest to trigger this? Does this trigger +on an x86 host? +Yes, it does trigger with tcg-on-x86 as well. I've been using + +s390x-softmmu/qemu-system-s390x -M s390-ccw-virtio,accel=tcg -cpu qemu,zpci=on +-m 1024 -nographic -device virtio-scsi-ccw,id=scsi0,devno=fe.0.0001 +-drive file=/path/to/image,format=qcow2,if=none,id=drive-scsi0-0-0-0 +-device +scsi-hd,bus=scsi0.0,channel=0,scsi-id=0,lun=0,drive=drive-scsi0-0-0-0,id=scsi0-0-0-0,bootindex=1 +-device virtio-net-ccw + +It seems it needs the guest actually doing something with the nics; I +cannot reproduce the crash if I use the old advent calendar moon buggy +image and just add a virtio-net-ccw device. + +(I don't think it's a problem with my local build, as I see the problem +both on my laptop and on an LPAR.) +It looks to me we forget the check the existence of peer. + +Please try the attached patch to see if it works. +Thanks, that patch gets my guest up and running again. So, FWIW, + +Tested-by: Cornelia Huck <cohuck@redhat.com> + +Any idea why this did not hit with virtio-net-pci (or the autogenerated +virtio-net-ccw device)? +It can be hit with virtio-net-pci as well (just start without peer). +For autogenerated virtio-net-cww, I think the reason is that it has +already had a peer set. +Thanks + +On Mon, 27 Jul 2020 15:38:12 +0800 +Jason Wang <jasowang@redhat.com> wrote: + +> +On 2020/7/27 ä¸å2:43, Cornelia Huck wrote: +> +> On Sat, 25 Jul 2020 08:40:07 +0800 +> +> Jason Wang <jasowang@redhat.com> wrote: +> +> +> +>> On 2020/7/24 ä¸å11:34, Cornelia Huck wrote: +> +>>> On Fri, 24 Jul 2020 11:17:57 -0400 +> +>>> "Michael S. Tsirkin"<mst@redhat.com> wrote: +> +>>> +> +>>>> On Fri, Jul 24, 2020 at 04:56:27PM +0200, Cornelia Huck wrote: +> +>>>>> On Fri, 24 Jul 2020 09:30:58 -0400 +> +>>>>> "Michael S. Tsirkin"<mst@redhat.com> wrote: +> +>>>>> +> +>>>>>> On Fri, Jul 24, 2020 at 03:27:18PM +0200, Cornelia Huck wrote: +> +>>>>>>> When I start qemu with a second virtio-net-ccw device (i.e. adding +> +>>>>>>> -device virtio-net-ccw in addition to the autogenerated device), I get +> +>>>>>>> a segfault. gdb points to +> +>>>>>>> +> +>>>>>>> #0 0x000055d6ab52681d in virtio_net_get_config (vdev=<optimized out>, +> +>>>>>>> config=0x55d6ad9e3f80 "RT") at +> +>>>>>>> /home/cohuck/git/qemu/hw/net/virtio-net.c:146 +> +>>>>>>> 146 if (nc->peer->info->type == NET_CLIENT_DRIVER_VHOST_VDPA) { +> +>>>>>>> +> +>>>>>>> (backtrace doesn't go further) +> +>>>>> The core was incomplete, but running under gdb directly shows that it +> +>>>>> is just a bog-standard config space access (first for that device). +> +>>>>> +> +>>>>> The cause of the crash is that nc->peer is not set... no idea how that +> +>>>>> can happen, not that familiar with that part of QEMU. (Should the code +> +>>>>> check, or is that really something that should not happen?) +> +>>>>> +> +>>>>> What I don't understand is why it is set correctly for the first, +> +>>>>> autogenerated virtio-net-ccw device, but not for the second one, and +> +>>>>> why virtio-net-pci doesn't show these problems. The only difference +> +>>>>> between -ccw and -pci that comes to my mind here is that config space +> +>>>>> accesses for ccw are done via an asynchronous operation, so timing +> +>>>>> might be different. +> +>>>> Hopefully Jason has an idea. Could you post a full command line +> +>>>> please? Do you need a working guest to trigger this? Does this trigger +> +>>>> on an x86 host? +> +>>> Yes, it does trigger with tcg-on-x86 as well. I've been using +> +>>> +> +>>> s390x-softmmu/qemu-system-s390x -M s390-ccw-virtio,accel=tcg -cpu +> +>>> qemu,zpci=on +> +>>> -m 1024 -nographic -device virtio-scsi-ccw,id=scsi0,devno=fe.0.0001 +> +>>> -drive file=/path/to/image,format=qcow2,if=none,id=drive-scsi0-0-0-0 +> +>>> -device +> +>>> scsi-hd,bus=scsi0.0,channel=0,scsi-id=0,lun=0,drive=drive-scsi0-0-0-0,id=scsi0-0-0-0,bootindex=1 +> +>>> -device virtio-net-ccw +> +>>> +> +>>> It seems it needs the guest actually doing something with the nics; I +> +>>> cannot reproduce the crash if I use the old advent calendar moon buggy +> +>>> image and just add a virtio-net-ccw device. +> +>>> +> +>>> (I don't think it's a problem with my local build, as I see the problem +> +>>> both on my laptop and on an LPAR.) +> +>> +> +>> It looks to me we forget the check the existence of peer. +> +>> +> +>> Please try the attached patch to see if it works. +> +> Thanks, that patch gets my guest up and running again. So, FWIW, +> +> +> +> Tested-by: Cornelia Huck <cohuck@redhat.com> +> +> +> +> Any idea why this did not hit with virtio-net-pci (or the autogenerated +> +> virtio-net-ccw device)? +> +> +> +It can be hit with virtio-net-pci as well (just start without peer). +Hm, I had not been able to reproduce the crash with a 'naked' -device +virtio-net-pci. But checking seems to be the right idea anyway. + +> +> +For autogenerated virtio-net-cww, I think the reason is that it has +> +already had a peer set. +Ok, that might well be. + +On 2020/7/27 ä¸å4:41, Cornelia Huck wrote: +On Mon, 27 Jul 2020 15:38:12 +0800 +Jason Wang <jasowang@redhat.com> wrote: +On 2020/7/27 ä¸å2:43, Cornelia Huck wrote: +On Sat, 25 Jul 2020 08:40:07 +0800 +Jason Wang <jasowang@redhat.com> wrote: +On 2020/7/24 ä¸å11:34, Cornelia Huck wrote: +On Fri, 24 Jul 2020 11:17:57 -0400 +"Michael S. Tsirkin"<mst@redhat.com> wrote: +On Fri, Jul 24, 2020 at 04:56:27PM +0200, Cornelia Huck wrote: +On Fri, 24 Jul 2020 09:30:58 -0400 +"Michael S. Tsirkin"<mst@redhat.com> wrote: +On Fri, Jul 24, 2020 at 03:27:18PM +0200, Cornelia Huck wrote: +When I start qemu with a second virtio-net-ccw device (i.e. adding +-device virtio-net-ccw in addition to the autogenerated device), I get +a segfault. gdb points to + +#0 0x000055d6ab52681d in virtio_net_get_config (vdev=<optimized out>, + config=0x55d6ad9e3f80 "RT") at +/home/cohuck/git/qemu/hw/net/virtio-net.c:146 +146 if (nc->peer->info->type == NET_CLIENT_DRIVER_VHOST_VDPA) { + +(backtrace doesn't go further) +The core was incomplete, but running under gdb directly shows that it +is just a bog-standard config space access (first for that device). + +The cause of the crash is that nc->peer is not set... no idea how that +can happen, not that familiar with that part of QEMU. (Should the code +check, or is that really something that should not happen?) + +What I don't understand is why it is set correctly for the first, +autogenerated virtio-net-ccw device, but not for the second one, and +why virtio-net-pci doesn't show these problems. The only difference +between -ccw and -pci that comes to my mind here is that config space +accesses for ccw are done via an asynchronous operation, so timing +might be different. +Hopefully Jason has an idea. Could you post a full command line +please? Do you need a working guest to trigger this? Does this trigger +on an x86 host? +Yes, it does trigger with tcg-on-x86 as well. I've been using + +s390x-softmmu/qemu-system-s390x -M s390-ccw-virtio,accel=tcg -cpu qemu,zpci=on +-m 1024 -nographic -device virtio-scsi-ccw,id=scsi0,devno=fe.0.0001 +-drive file=/path/to/image,format=qcow2,if=none,id=drive-scsi0-0-0-0 +-device +scsi-hd,bus=scsi0.0,channel=0,scsi-id=0,lun=0,drive=drive-scsi0-0-0-0,id=scsi0-0-0-0,bootindex=1 +-device virtio-net-ccw + +It seems it needs the guest actually doing something with the nics; I +cannot reproduce the crash if I use the old advent calendar moon buggy +image and just add a virtio-net-ccw device. + +(I don't think it's a problem with my local build, as I see the problem +both on my laptop and on an LPAR.) +It looks to me we forget the check the existence of peer. + +Please try the attached patch to see if it works. +Thanks, that patch gets my guest up and running again. So, FWIW, + +Tested-by: Cornelia Huck <cohuck@redhat.com> + +Any idea why this did not hit with virtio-net-pci (or the autogenerated +virtio-net-ccw device)? +It can be hit with virtio-net-pci as well (just start without peer). +Hm, I had not been able to reproduce the crash with a 'naked' -device +virtio-net-pci. But checking seems to be the right idea anyway. +Sorry for being unclear, I meant for networking part, you just need +start without peer, and you need a real guest (any Linux) that is trying +to access the config space of virtio-net. +Thanks +For autogenerated virtio-net-cww, I think the reason is that it has +already had a peer set. +Ok, that might well be. + +On Mon, Jul 27, 2020 at 04:51:23PM +0800, Jason Wang wrote: +> +> +On 2020/7/27 ä¸å4:41, Cornelia Huck wrote: +> +> On Mon, 27 Jul 2020 15:38:12 +0800 +> +> Jason Wang <jasowang@redhat.com> wrote: +> +> +> +> > On 2020/7/27 ä¸å2:43, Cornelia Huck wrote: +> +> > > On Sat, 25 Jul 2020 08:40:07 +0800 +> +> > > Jason Wang <jasowang@redhat.com> wrote: +> +> > > > On 2020/7/24 ä¸å11:34, Cornelia Huck wrote: +> +> > > > > On Fri, 24 Jul 2020 11:17:57 -0400 +> +> > > > > "Michael S. Tsirkin"<mst@redhat.com> wrote: +> +> > > > > > On Fri, Jul 24, 2020 at 04:56:27PM +0200, Cornelia Huck wrote: +> +> > > > > > > On Fri, 24 Jul 2020 09:30:58 -0400 +> +> > > > > > > "Michael S. Tsirkin"<mst@redhat.com> wrote: +> +> > > > > > > > On Fri, Jul 24, 2020 at 03:27:18PM +0200, Cornelia Huck wrote: +> +> > > > > > > > > When I start qemu with a second virtio-net-ccw device (i.e. +> +> > > > > > > > > adding +> +> > > > > > > > > -device virtio-net-ccw in addition to the autogenerated +> +> > > > > > > > > device), I get +> +> > > > > > > > > a segfault. gdb points to +> +> > > > > > > > > +> +> > > > > > > > > #0 0x000055d6ab52681d in virtio_net_get_config +> +> > > > > > > > > (vdev=<optimized out>, +> +> > > > > > > > > config=0x55d6ad9e3f80 "RT") at +> +> > > > > > > > > /home/cohuck/git/qemu/hw/net/virtio-net.c:146 +> +> > > > > > > > > 146 if (nc->peer->info->type == +> +> > > > > > > > > NET_CLIENT_DRIVER_VHOST_VDPA) { +> +> > > > > > > > > +> +> > > > > > > > > (backtrace doesn't go further) +> +> > > > > > > The core was incomplete, but running under gdb directly shows +> +> > > > > > > that it +> +> > > > > > > is just a bog-standard config space access (first for that +> +> > > > > > > device). +> +> > > > > > > +> +> > > > > > > The cause of the crash is that nc->peer is not set... no idea +> +> > > > > > > how that +> +> > > > > > > can happen, not that familiar with that part of QEMU. (Should +> +> > > > > > > the code +> +> > > > > > > check, or is that really something that should not happen?) +> +> > > > > > > +> +> > > > > > > What I don't understand is why it is set correctly for the +> +> > > > > > > first, +> +> > > > > > > autogenerated virtio-net-ccw device, but not for the second +> +> > > > > > > one, and +> +> > > > > > > why virtio-net-pci doesn't show these problems. The only +> +> > > > > > > difference +> +> > > > > > > between -ccw and -pci that comes to my mind here is that config +> +> > > > > > > space +> +> > > > > > > accesses for ccw are done via an asynchronous operation, so +> +> > > > > > > timing +> +> > > > > > > might be different. +> +> > > > > > Hopefully Jason has an idea. Could you post a full command line +> +> > > > > > please? Do you need a working guest to trigger this? Does this +> +> > > > > > trigger +> +> > > > > > on an x86 host? +> +> > > > > Yes, it does trigger with tcg-on-x86 as well. I've been using +> +> > > > > +> +> > > > > s390x-softmmu/qemu-system-s390x -M s390-ccw-virtio,accel=tcg -cpu +> +> > > > > qemu,zpci=on +> +> > > > > -m 1024 -nographic -device virtio-scsi-ccw,id=scsi0,devno=fe.0.0001 +> +> > > > > -drive file=/path/to/image,format=qcow2,if=none,id=drive-scsi0-0-0-0 +> +> > > > > -device +> +> > > > > scsi-hd,bus=scsi0.0,channel=0,scsi-id=0,lun=0,drive=drive-scsi0-0-0-0,id=scsi0-0-0-0,bootindex=1 +> +> > > > > -device virtio-net-ccw +> +> > > > > +> +> > > > > It seems it needs the guest actually doing something with the nics; +> +> > > > > I +> +> > > > > cannot reproduce the crash if I use the old advent calendar moon +> +> > > > > buggy +> +> > > > > image and just add a virtio-net-ccw device. +> +> > > > > +> +> > > > > (I don't think it's a problem with my local build, as I see the +> +> > > > > problem +> +> > > > > both on my laptop and on an LPAR.) +> +> > > > It looks to me we forget the check the existence of peer. +> +> > > > +> +> > > > Please try the attached patch to see if it works. +> +> > > Thanks, that patch gets my guest up and running again. So, FWIW, +> +> > > +> +> > > Tested-by: Cornelia Huck <cohuck@redhat.com> +> +> > > +> +> > > Any idea why this did not hit with virtio-net-pci (or the autogenerated +> +> > > virtio-net-ccw device)? +> +> > +> +> > It can be hit with virtio-net-pci as well (just start without peer). +> +> Hm, I had not been able to reproduce the crash with a 'naked' -device +> +> virtio-net-pci. But checking seems to be the right idea anyway. +> +> +> +Sorry for being unclear, I meant for networking part, you just need start +> +without peer, and you need a real guest (any Linux) that is trying to access +> +the config space of virtio-net. +> +> +Thanks +A pxe guest will do it, but that doesn't support ccw, right? + +I'm still unclear why this triggers with ccw but not pci - +any idea? + +> +> +> +> +> > For autogenerated virtio-net-cww, I think the reason is that it has +> +> > already had a peer set. +> +> Ok, that might well be. +> +> +> +> + +On 2020/7/27 ä¸å7:43, Michael S. Tsirkin wrote: +On Mon, Jul 27, 2020 at 04:51:23PM +0800, Jason Wang wrote: +On 2020/7/27 ä¸å4:41, Cornelia Huck wrote: +On Mon, 27 Jul 2020 15:38:12 +0800 +Jason Wang<jasowang@redhat.com> wrote: +On 2020/7/27 ä¸å2:43, Cornelia Huck wrote: +On Sat, 25 Jul 2020 08:40:07 +0800 +Jason Wang<jasowang@redhat.com> wrote: +On 2020/7/24 ä¸å11:34, Cornelia Huck wrote: +On Fri, 24 Jul 2020 11:17:57 -0400 +"Michael S. Tsirkin"<mst@redhat.com> wrote: +On Fri, Jul 24, 2020 at 04:56:27PM +0200, Cornelia Huck wrote: +On Fri, 24 Jul 2020 09:30:58 -0400 +"Michael S. Tsirkin"<mst@redhat.com> wrote: +On Fri, Jul 24, 2020 at 03:27:18PM +0200, Cornelia Huck wrote: +When I start qemu with a second virtio-net-ccw device (i.e. adding +-device virtio-net-ccw in addition to the autogenerated device), I get +a segfault. gdb points to + +#0 0x000055d6ab52681d in virtio_net_get_config (vdev=<optimized out>, + config=0x55d6ad9e3f80 "RT") at +/home/cohuck/git/qemu/hw/net/virtio-net.c:146 +146 if (nc->peer->info->type == NET_CLIENT_DRIVER_VHOST_VDPA) { + +(backtrace doesn't go further) +The core was incomplete, but running under gdb directly shows that it +is just a bog-standard config space access (first for that device). + +The cause of the crash is that nc->peer is not set... no idea how that +can happen, not that familiar with that part of QEMU. (Should the code +check, or is that really something that should not happen?) + +What I don't understand is why it is set correctly for the first, +autogenerated virtio-net-ccw device, but not for the second one, and +why virtio-net-pci doesn't show these problems. The only difference +between -ccw and -pci that comes to my mind here is that config space +accesses for ccw are done via an asynchronous operation, so timing +might be different. +Hopefully Jason has an idea. Could you post a full command line +please? Do you need a working guest to trigger this? Does this trigger +on an x86 host? +Yes, it does trigger with tcg-on-x86 as well. I've been using + +s390x-softmmu/qemu-system-s390x -M s390-ccw-virtio,accel=tcg -cpu qemu,zpci=on +-m 1024 -nographic -device virtio-scsi-ccw,id=scsi0,devno=fe.0.0001 +-drive file=/path/to/image,format=qcow2,if=none,id=drive-scsi0-0-0-0 +-device +scsi-hd,bus=scsi0.0,channel=0,scsi-id=0,lun=0,drive=drive-scsi0-0-0-0,id=scsi0-0-0-0,bootindex=1 +-device virtio-net-ccw + +It seems it needs the guest actually doing something with the nics; I +cannot reproduce the crash if I use the old advent calendar moon buggy +image and just add a virtio-net-ccw device. + +(I don't think it's a problem with my local build, as I see the problem +both on my laptop and on an LPAR.) +It looks to me we forget the check the existence of peer. + +Please try the attached patch to see if it works. +Thanks, that patch gets my guest up and running again. So, FWIW, + +Tested-by: Cornelia Huck<cohuck@redhat.com> + +Any idea why this did not hit with virtio-net-pci (or the autogenerated +virtio-net-ccw device)? +It can be hit with virtio-net-pci as well (just start without peer). +Hm, I had not been able to reproduce the crash with a 'naked' -device +virtio-net-pci. But checking seems to be the right idea anyway. +Sorry for being unclear, I meant for networking part, you just need start +without peer, and you need a real guest (any Linux) that is trying to access +the config space of virtio-net. + +Thanks +A pxe guest will do it, but that doesn't support ccw, right? +Yes, it depends on the cli actually. +I'm still unclear why this triggers with ccw but not pci - +any idea? +I don't test pxe but I can reproduce this with pci (just start a linux +guest without a peer). +Thanks + +On Mon, Jul 27, 2020 at 08:44:09PM +0800, Jason Wang wrote: +> +> +On 2020/7/27 ä¸å7:43, Michael S. Tsirkin wrote: +> +> On Mon, Jul 27, 2020 at 04:51:23PM +0800, Jason Wang wrote: +> +> > On 2020/7/27 ä¸å4:41, Cornelia Huck wrote: +> +> > > On Mon, 27 Jul 2020 15:38:12 +0800 +> +> > > Jason Wang<jasowang@redhat.com> wrote: +> +> > > +> +> > > > On 2020/7/27 ä¸å2:43, Cornelia Huck wrote: +> +> > > > > On Sat, 25 Jul 2020 08:40:07 +0800 +> +> > > > > Jason Wang<jasowang@redhat.com> wrote: +> +> > > > > > On 2020/7/24 ä¸å11:34, Cornelia Huck wrote: +> +> > > > > > > On Fri, 24 Jul 2020 11:17:57 -0400 +> +> > > > > > > "Michael S. Tsirkin"<mst@redhat.com> wrote: +> +> > > > > > > > On Fri, Jul 24, 2020 at 04:56:27PM +0200, Cornelia Huck wrote: +> +> > > > > > > > > On Fri, 24 Jul 2020 09:30:58 -0400 +> +> > > > > > > > > "Michael S. Tsirkin"<mst@redhat.com> wrote: +> +> > > > > > > > > > On Fri, Jul 24, 2020 at 03:27:18PM +0200, Cornelia Huck +> +> > > > > > > > > > wrote: +> +> > > > > > > > > > > When I start qemu with a second virtio-net-ccw device +> +> > > > > > > > > > > (i.e. adding +> +> > > > > > > > > > > -device virtio-net-ccw in addition to the autogenerated +> +> > > > > > > > > > > device), I get +> +> > > > > > > > > > > a segfault. gdb points to +> +> > > > > > > > > > > +> +> > > > > > > > > > > #0 0x000055d6ab52681d in virtio_net_get_config +> +> > > > > > > > > > > (vdev=<optimized out>, +> +> > > > > > > > > > > config=0x55d6ad9e3f80 "RT") at +> +> > > > > > > > > > > /home/cohuck/git/qemu/hw/net/virtio-net.c:146 +> +> > > > > > > > > > > 146 if (nc->peer->info->type == +> +> > > > > > > > > > > NET_CLIENT_DRIVER_VHOST_VDPA) { +> +> > > > > > > > > > > +> +> > > > > > > > > > > (backtrace doesn't go further) +> +> > > > > > > > > The core was incomplete, but running under gdb directly +> +> > > > > > > > > shows that it +> +> > > > > > > > > is just a bog-standard config space access (first for that +> +> > > > > > > > > device). +> +> > > > > > > > > +> +> > > > > > > > > The cause of the crash is that nc->peer is not set... no +> +> > > > > > > > > idea how that +> +> > > > > > > > > can happen, not that familiar with that part of QEMU. +> +> > > > > > > > > (Should the code +> +> > > > > > > > > check, or is that really something that should not happen?) +> +> > > > > > > > > +> +> > > > > > > > > What I don't understand is why it is set correctly for the +> +> > > > > > > > > first, +> +> > > > > > > > > autogenerated virtio-net-ccw device, but not for the second +> +> > > > > > > > > one, and +> +> > > > > > > > > why virtio-net-pci doesn't show these problems. The only +> +> > > > > > > > > difference +> +> > > > > > > > > between -ccw and -pci that comes to my mind here is that +> +> > > > > > > > > config space +> +> > > > > > > > > accesses for ccw are done via an asynchronous operation, so +> +> > > > > > > > > timing +> +> > > > > > > > > might be different. +> +> > > > > > > > Hopefully Jason has an idea. Could you post a full command +> +> > > > > > > > line +> +> > > > > > > > please? Do you need a working guest to trigger this? Does +> +> > > > > > > > this trigger +> +> > > > > > > > on an x86 host? +> +> > > > > > > Yes, it does trigger with tcg-on-x86 as well. I've been using +> +> > > > > > > +> +> > > > > > > s390x-softmmu/qemu-system-s390x -M s390-ccw-virtio,accel=tcg +> +> > > > > > > -cpu qemu,zpci=on +> +> > > > > > > -m 1024 -nographic -device +> +> > > > > > > virtio-scsi-ccw,id=scsi0,devno=fe.0.0001 +> +> > > > > > > -drive +> +> > > > > > > file=/path/to/image,format=qcow2,if=none,id=drive-scsi0-0-0-0 +> +> > > > > > > -device +> +> > > > > > > scsi-hd,bus=scsi0.0,channel=0,scsi-id=0,lun=0,drive=drive-scsi0-0-0-0,id=scsi0-0-0-0,bootindex=1 +> +> > > > > > > -device virtio-net-ccw +> +> > > > > > > +> +> > > > > > > It seems it needs the guest actually doing something with the +> +> > > > > > > nics; I +> +> > > > > > > cannot reproduce the crash if I use the old advent calendar +> +> > > > > > > moon buggy +> +> > > > > > > image and just add a virtio-net-ccw device. +> +> > > > > > > +> +> > > > > > > (I don't think it's a problem with my local build, as I see the +> +> > > > > > > problem +> +> > > > > > > both on my laptop and on an LPAR.) +> +> > > > > > It looks to me we forget the check the existence of peer. +> +> > > > > > +> +> > > > > > Please try the attached patch to see if it works. +> +> > > > > Thanks, that patch gets my guest up and running again. So, FWIW, +> +> > > > > +> +> > > > > Tested-by: Cornelia Huck<cohuck@redhat.com> +> +> > > > > +> +> > > > > Any idea why this did not hit with virtio-net-pci (or the +> +> > > > > autogenerated +> +> > > > > virtio-net-ccw device)? +> +> > > > It can be hit with virtio-net-pci as well (just start without peer). +> +> > > Hm, I had not been able to reproduce the crash with a 'naked' -device +> +> > > virtio-net-pci. But checking seems to be the right idea anyway. +> +> > Sorry for being unclear, I meant for networking part, you just need start +> +> > without peer, and you need a real guest (any Linux) that is trying to +> +> > access +> +> > the config space of virtio-net. +> +> > +> +> > Thanks +> +> A pxe guest will do it, but that doesn't support ccw, right? +> +> +> +Yes, it depends on the cli actually. +> +> +> +> +> +> I'm still unclear why this triggers with ccw but not pci - +> +> any idea? +> +> +> +I don't test pxe but I can reproduce this with pci (just start a linux guest +> +without a peer). +> +> +Thanks +> +Might be a good addition to a unit test. Not sure what would the +test do exactly: just make sure guest runs? Looks like a lot of work +for an empty test ... maybe we can poke at the guest config with +qtest commands at least. + +-- +MST + +On 2020/7/27 ä¸å9:16, Michael S. Tsirkin wrote: +On Mon, Jul 27, 2020 at 08:44:09PM +0800, Jason Wang wrote: +On 2020/7/27 ä¸å7:43, Michael S. Tsirkin wrote: +On Mon, Jul 27, 2020 at 04:51:23PM +0800, Jason Wang wrote: +On 2020/7/27 ä¸å4:41, Cornelia Huck wrote: +On Mon, 27 Jul 2020 15:38:12 +0800 +Jason Wang<jasowang@redhat.com> wrote: +On 2020/7/27 ä¸å2:43, Cornelia Huck wrote: +On Sat, 25 Jul 2020 08:40:07 +0800 +Jason Wang<jasowang@redhat.com> wrote: +On 2020/7/24 ä¸å11:34, Cornelia Huck wrote: +On Fri, 24 Jul 2020 11:17:57 -0400 +"Michael S. Tsirkin"<mst@redhat.com> wrote: +On Fri, Jul 24, 2020 at 04:56:27PM +0200, Cornelia Huck wrote: +On Fri, 24 Jul 2020 09:30:58 -0400 +"Michael S. Tsirkin"<mst@redhat.com> wrote: +On Fri, Jul 24, 2020 at 03:27:18PM +0200, Cornelia Huck wrote: +When I start qemu with a second virtio-net-ccw device (i.e. adding +-device virtio-net-ccw in addition to the autogenerated device), I get +a segfault. gdb points to + +#0 0x000055d6ab52681d in virtio_net_get_config (vdev=<optimized out>, + config=0x55d6ad9e3f80 "RT") at +/home/cohuck/git/qemu/hw/net/virtio-net.c:146 +146 if (nc->peer->info->type == NET_CLIENT_DRIVER_VHOST_VDPA) { + +(backtrace doesn't go further) +The core was incomplete, but running under gdb directly shows that it +is just a bog-standard config space access (first for that device). + +The cause of the crash is that nc->peer is not set... no idea how that +can happen, not that familiar with that part of QEMU. (Should the code +check, or is that really something that should not happen?) + +What I don't understand is why it is set correctly for the first, +autogenerated virtio-net-ccw device, but not for the second one, and +why virtio-net-pci doesn't show these problems. The only difference +between -ccw and -pci that comes to my mind here is that config space +accesses for ccw are done via an asynchronous operation, so timing +might be different. +Hopefully Jason has an idea. Could you post a full command line +please? Do you need a working guest to trigger this? Does this trigger +on an x86 host? +Yes, it does trigger with tcg-on-x86 as well. I've been using + +s390x-softmmu/qemu-system-s390x -M s390-ccw-virtio,accel=tcg -cpu qemu,zpci=on +-m 1024 -nographic -device virtio-scsi-ccw,id=scsi0,devno=fe.0.0001 +-drive file=/path/to/image,format=qcow2,if=none,id=drive-scsi0-0-0-0 +-device +scsi-hd,bus=scsi0.0,channel=0,scsi-id=0,lun=0,drive=drive-scsi0-0-0-0,id=scsi0-0-0-0,bootindex=1 +-device virtio-net-ccw + +It seems it needs the guest actually doing something with the nics; I +cannot reproduce the crash if I use the old advent calendar moon buggy +image and just add a virtio-net-ccw device. + +(I don't think it's a problem with my local build, as I see the problem +both on my laptop and on an LPAR.) +It looks to me we forget the check the existence of peer. + +Please try the attached patch to see if it works. +Thanks, that patch gets my guest up and running again. So, FWIW, + +Tested-by: Cornelia Huck<cohuck@redhat.com> + +Any idea why this did not hit with virtio-net-pci (or the autogenerated +virtio-net-ccw device)? +It can be hit with virtio-net-pci as well (just start without peer). +Hm, I had not been able to reproduce the crash with a 'naked' -device +virtio-net-pci. But checking seems to be the right idea anyway. +Sorry for being unclear, I meant for networking part, you just need start +without peer, and you need a real guest (any Linux) that is trying to access +the config space of virtio-net. + +Thanks +A pxe guest will do it, but that doesn't support ccw, right? +Yes, it depends on the cli actually. +I'm still unclear why this triggers with ccw but not pci - +any idea? +I don't test pxe but I can reproduce this with pci (just start a linux guest +without a peer). + +Thanks +Might be a good addition to a unit test. Not sure what would the +test do exactly: just make sure guest runs? Looks like a lot of work +for an empty test ... maybe we can poke at the guest config with +qtest commands at least. +That should work or we can simply extend the exist virtio-net qtest to +do that. +Thanks + diff --git a/results/classifier/001/mistranslation/80615920 b/results/classifier/001/mistranslation/80615920 new file mode 100644 index 000000000..97712c2f5 --- /dev/null +++ b/results/classifier/001/mistranslation/80615920 @@ -0,0 +1,348 @@ +mistranslation: 0.800 +other: 0.786 +instruction: 0.751 +semantic: 0.737 + +[BUG] accel/tcg: cpu_exec_longjmp_cleanup: assertion failed: (cpu == current_cpu) + +It seems there is a bug in SIGALRM handling when 486 system emulates x86_64 +code. + +This code: + +#include <stdio.h> +#include <stdlib.h> +#include <pthread.h> +#include <signal.h> +#include <unistd.h> + +pthread_t thread1, thread2; + +// Signal handler for SIGALRM +void alarm_handler(int sig) { + // Do nothing, just wake up the other thread +} + +// Thread 1 function +void* thread1_func(void* arg) { + // Set up the signal handler for SIGALRM + signal(SIGALRM, alarm_handler); + + // Wait for 5 seconds + sleep(1); + + // Send SIGALRM signal to thread 2 + pthread_kill(thread2, SIGALRM); + + return NULL; +} + +// Thread 2 function +void* thread2_func(void* arg) { + // Wait for the SIGALRM signal + pause(); + + printf("Thread 2 woke up!\n"); + + return NULL; +} + +int main() { + // Create thread 1 + if (pthread_create(&thread1, NULL, thread1_func, NULL) != 0) { + fprintf(stderr, "Failed to create thread 1\n"); + return 1; + } + + // Create thread 2 + if (pthread_create(&thread2, NULL, thread2_func, NULL) != 0) { + fprintf(stderr, "Failed to create thread 2\n"); + return 1; + } + + // Wait for both threads to finish + pthread_join(thread1, NULL); + pthread_join(thread2, NULL); + + return 0; +} + + +Fails with this -strace log (there are also unsupported syscalls 334 and 435, +but it seems it doesn't affect the code much): + +... +736 rt_sigaction(SIGALRM,0x000000001123ec20,0x000000001123ecc0) = 0 +736 clock_nanosleep(CLOCK_REALTIME,0,{tv_sec = 1,tv_nsec = 0},{tv_sec = +1,tv_nsec = 0}) +736 rt_sigprocmask(SIG_BLOCK,0x00000000109fad20,0x0000000010800b38,8) = 0 +736 Unknown syscall 435 +736 +clone(CLONE_VM|CLONE_FS|CLONE_FILES|CLONE_SIGHAND|CLONE_THREAD|CLONE_SYSVSEM|CLONE_SETTLS|CLONE_PARENT_SETTID| + ... +736 rt_sigprocmask(SIG_SETMASK,0x0000000010800b38,NULL,8) +736 set_robust_list(0x11a419a0,0) = -1 errno=38 (Function not implemented) +736 rt_sigprocmask(SIG_SETMASK,0x0000000011a41fb0,NULL,8) = 0 + = 0 +736 pause(0,0,2,277186368,0,295966400) +736 +futex(0x000000001123f990,FUTEX_CLOCK_REALTIME|FUTEX_WAIT_BITSET,738,NULL,NULL,0) + = 0 +736 rt_sigprocmask(SIG_BLOCK,0x00000000109fad20,0x000000001123ee88,8) = 0 +736 getpid() = 736 +736 tgkill(736,739,SIGALRM) = 0 + = -1 errno=4 (Interrupted system call) +--- SIGALRM {si_signo=SIGALRM, si_code=SI_TKILL, si_pid=736, si_uid=0} --- +0x48874a != 0x3c69e10 +736 rt_sigprocmask(SIG_SETMASK,0x000000001123ee88,NULL,8) = 0 +** +ERROR:../accel/tcg/cpu-exec.c:546:cpu_exec_longjmp_cleanup: assertion failed: +(cpu == current_cpu) +Bail out! ERROR:../accel/tcg/cpu-exec.c:546:cpu_exec_longjmp_cleanup: assertion +failed: (cpu == current_cpu) +0x48874a != 0x3c69e10 +** +ERROR:../accel/tcg/cpu-exec.c:546:cpu_exec_longjmp_cleanup: assertion failed: +(cpu == current_cpu) +Bail out! ERROR:../accel/tcg/cpu-exec.c:546:cpu_exec_longjmp_cleanup: assertion +failed: (cpu == current_cpu) +# + +The code fails either with or without -singlestep, the command line: + +/usr/bin/qemu-x86_64 -L /opt/x86_64 -strace -singlestep /opt/x86_64/alarm.bin + +Source code of QEMU 8.1.1 was modified with patch "[PATCH] qemu/timer: Don't +use RDTSC on i486" [1], +with added few ioctls (not relevant) and cpu_exec_longjmp_cleanup() now prints +current pointers of +cpu and current_cpu (line "0x48874a != 0x3c69e10"). + +config.log (built as a part of buildroot, basically the minimal possible +configuration for running x86_64 on 486): + +# Configured with: +'/mnt/hd_8tb_p1/p1/home/crossgen/buildroot_486_2/output/build/qemu-8.1.1/configure' + '--prefix=/usr' +'--cross-prefix=/mnt/hd_8tb_p1/p1/home/crossgen/buildroot_486_2/output/host/bin/i486-buildroot-linux-gnu-' + '--audio-drv-list=' +'--python=/mnt/hd_8tb_p1/p1/home/crossgen/buildroot_486_2/output/host/bin/python3' + +'--ninja=/mnt/hd_8tb_p1/p1/home/crossgen/buildroot_486_2/output/host/bin/ninja' +'--disable-alsa' '--disable-bpf' '--disable-brlapi' '--disable-bsd-user' +'--disable-cap-ng' '--disable-capstone' '--disable-containers' +'--disable-coreaudio' '--disable-curl' '--disable-curses' +'--disable-dbus-display' '--disable-docs' '--disable-dsound' '--disable-hvf' +'--disable-jack' '--disable-libiscsi' '--disable-linux-aio' +'--disable-linux-io-uring' '--disable-malloc-trim' '--disable-membarrier' +'--disable-mpath' '--disable-netmap' '--disable-opengl' '--disable-oss' +'--disable-pa' '--disable-rbd' '--disable-sanitizers' '--disable-selinux' +'--disable-sparse' '--disable-strip' '--disable-vde' '--disable-vhost-crypto' +'--disable-vhost-user-blk-server' '--disable-virtfs' '--disable-whpx' +'--disable-xen' '--disable-attr' '--disable-kvm' '--disable-vhost-net' +'--disable-download' '--disable-hexagon-idef-parser' '--disable-system' +'--enable-linux-user' '--target-list=x86_64-linux-user' '--disable-vhost-user' +'--disable-slirp' '--disable-sdl' '--disable-fdt' '--enable-trace-backends=nop' +'--disable-tools' '--disable-guest-agent' '--disable-fuse' +'--disable-fuse-lseek' '--disable-seccomp' '--disable-libssh' +'--disable-libusb' '--disable-vnc' '--disable-nettle' '--disable-numa' +'--disable-pipewire' '--disable-spice' '--disable-usb-redir' +'--disable-install-blobs' + +Emulation of the same x86_64 code with qemu 6.2.0 installed on another x86_64 +native machine works fine. + +[1] +https://lists.nongnu.org/archive/html/qemu-devel/2023-11/msg05387.html +Best regards, +Petr + +On Sat, 25 Nov 2023 at 13:09, Petr Cvek <petrcvekcz@gmail.com> wrote: +> +> +It seems there is a bug in SIGALRM handling when 486 system emulates x86_64 +> +code. +486 host is pretty well out of support currently. Can you reproduce +this on a less ancient host CPU type ? + +> +ERROR:../accel/tcg/cpu-exec.c:546:cpu_exec_longjmp_cleanup: assertion failed: +> +(cpu == current_cpu) +> +Bail out! ERROR:../accel/tcg/cpu-exec.c:546:cpu_exec_longjmp_cleanup: +> +assertion failed: (cpu == current_cpu) +> +0x48874a != 0x3c69e10 +> +** +> +ERROR:../accel/tcg/cpu-exec.c:546:cpu_exec_longjmp_cleanup: assertion failed: +> +(cpu == current_cpu) +> +Bail out! ERROR:../accel/tcg/cpu-exec.c:546:cpu_exec_longjmp_cleanup: +> +assertion failed: (cpu == current_cpu) +What compiler version do you build QEMU with? That +assert is there because we have seen some buggy compilers +in the past which don't correctly preserve the variable +value as the setjmp/longjmp spec requires them to. + +thanks +-- PMM + +Dne 27. 11. 23 v 10:37 Peter Maydell napsal(a): +> +On Sat, 25 Nov 2023 at 13:09, Petr Cvek <petrcvekcz@gmail.com> wrote: +> +> +> +> It seems there is a bug in SIGALRM handling when 486 system emulates x86_64 +> +> code. +> +> +486 host is pretty well out of support currently. Can you reproduce +> +this on a less ancient host CPU type ? +> +It seems it only fails when the code is compiled for i486. QEMU built with the +same compiler with -march=i586 and above runs on the same physical hardware +without a problem. All -march= variants were executed on ryzen 3600. + +> +> ERROR:../accel/tcg/cpu-exec.c:546:cpu_exec_longjmp_cleanup: assertion +> +> failed: (cpu == current_cpu) +> +> Bail out! ERROR:../accel/tcg/cpu-exec.c:546:cpu_exec_longjmp_cleanup: +> +> assertion failed: (cpu == current_cpu) +> +> 0x48874a != 0x3c69e10 +> +> ** +> +> ERROR:../accel/tcg/cpu-exec.c:546:cpu_exec_longjmp_cleanup: assertion +> +> failed: (cpu == current_cpu) +> +> Bail out! ERROR:../accel/tcg/cpu-exec.c:546:cpu_exec_longjmp_cleanup: +> +> assertion failed: (cpu == current_cpu) +> +> +What compiler version do you build QEMU with? That +> +assert is there because we have seen some buggy compilers +> +in the past which don't correctly preserve the variable +> +value as the setjmp/longjmp spec requires them to. +> +i486 and i586+ code variants were compiled with GCC 13.2.0 (more exactly, +slackware64 current multilib distribution). + +i486 binary which runs on the real 486 is also GCC 13.2.0 and installed as a +part of the buildroot crosscompiler (about two week old git snapshot). + +> +thanks +> +-- PMM +best regards, +Petr + +On 11/25/23 07:08, Petr Cvek wrote: +ERROR:../accel/tcg/cpu-exec.c:546:cpu_exec_longjmp_cleanup: assertion failed: +(cpu == current_cpu) +Bail out! ERROR:../accel/tcg/cpu-exec.c:546:cpu_exec_longjmp_cleanup: assertion +failed: (cpu == current_cpu) +# + +The code fails either with or without -singlestep, the command line: + +/usr/bin/qemu-x86_64 -L /opt/x86_64 -strace -singlestep /opt/x86_64/alarm.bin + +Source code of QEMU 8.1.1 was modified with patch "[PATCH] qemu/timer: Don't use +RDTSC on i486" [1], +with added few ioctls (not relevant) and cpu_exec_longjmp_cleanup() now prints +current pointers of +cpu and current_cpu (line "0x48874a != 0x3c69e10"). +If you try this again with 8.2-rc2, you should not see an assertion failure. +You should see instead + +QEMU internal SIGILL {code=ILLOPC, addr=0x12345678} +which I think more accurately summarizes the situation of attempting RDTSC on hardware +that does not support it. +r~ + +Dne 29. 11. 23 v 15:25 Richard Henderson napsal(a): +> +On 11/25/23 07:08, Petr Cvek wrote: +> +> ERROR:../accel/tcg/cpu-exec.c:546:cpu_exec_longjmp_cleanup: assertion +> +> failed: (cpu == current_cpu) +> +> Bail out! ERROR:../accel/tcg/cpu-exec.c:546:cpu_exec_longjmp_cleanup: +> +> assertion failed: (cpu == current_cpu) +> +> # +> +> +> +> The code fails either with or without -singlestep, the command line: +> +> +> +> /usr/bin/qemu-x86_64 -L /opt/x86_64 -strace -singlestep +> +> /opt/x86_64/alarm.bin +> +> +> +> Source code of QEMU 8.1.1 was modified with patch "[PATCH] qemu/timer: Don't +> +> use RDTSC on i486" [1], +> +> with added few ioctls (not relevant) and cpu_exec_longjmp_cleanup() now +> +> prints current pointers of +> +> cpu and current_cpu (line "0x48874a != 0x3c69e10"). +> +> +> +If you try this again with 8.2-rc2, you should not see an assertion failure. +> +You should see instead +> +> +QEMU internal SIGILL {code=ILLOPC, addr=0x12345678} +> +> +which I think more accurately summarizes the situation of attempting RDTSC on +> +hardware that does not support it. +> +> +Compilation of vanilla qemu v8.2.0-rc2 with -march=i486 by GCC 13.2.0 and +running the resulting binary on ryzen still leads to: + +** +ERROR:../accel/tcg/cpu-exec.c:533:cpu_exec_longjmp_cleanup: assertion failed: +(cpu == current_cpu) +Bail out! ERROR:../accel/tcg/cpu-exec.c:533:cpu_exec_longjmp_cleanup: assertion +failed: (cpu == current_cpu) +Aborted + +> +> +r~ +Petr + |