- 30 Oct, 2018 40 commits
-
-
Cyrill Gorcunov authored
The host compel-host-bin must be built before criu, same time the criu itself should not depend on libcompel or plugins because they are the part of the compel package. Signed-off-by:
Cyrill Gorcunov <gorcunov@gmail.com> Reviewed-by:
Dmitry Safonov <0x7f454c46@gmail.com> Signed-off-by:
Andrei Vagin <avagin@virtuozzo.com>
-
Cyrill Gorcunov authored
They were occasionally kept in obj-y. Signed-off-by:
-
Cyrill Gorcunov authored
Thus to choose which deps to include, for example if only particular file is being build there is no need to include any other deps. Signed-off-by:
-
Cyrill Gorcunov authored
Signed-off-by:
-
Cyrill Gorcunov authored
Signed-off-by:
-
Cyrill Gorcunov authored
Thus will include hostprogs deps only if requested. Signed-off-by:
-
Cyrill Gorcunov authored
Signed-off-by:
-
Cyrill Gorcunov authored
Signed-off-by:
-
Cyrill Gorcunov authored
Signed-off-by:
-
Cyrill Gorcunov authored
Signed-off-by:
-
Cyrill Gorcunov authored
mrproper doesn't require inclusion of deps similar as clean target. Signed-off-by:
-
Cyrill Gorcunov authored
We fully support xsaves, so no need for noxsaves temporary option anymore. This reverts commit ba93feb5f0f017f2ee498f6ee2db58bcaf817501. Signed-off-by:
-
Cyrill Gorcunov authored
We fully support xsaves now, so no need for warning or any other message. Signed-off-by:
-
Cyrill Gorcunov authored
Signed-off-by:
-
Cyrill Gorcunov authored
Signed-off-by:
-
Cyrill Gorcunov authored
arm's cpu code is the same as aarch64, so use the symlink. Signed-off-by:
-
Cyrill Gorcunov authored
Signed-off-by:
-
Cyrill Gorcunov authored
Signed-off-by:
-
Cyrill Gorcunov authored
For debug sake Signed-off-by:
-
Cyrill Gorcunov authored
cpu extensions (such as avx-512) require bigger xsave area to keep fpu registers set, so we allocate a page per process to keep them all. On checkpoint we parse runtime fpu features and dump them into an image and do reverse on restore procedure. Signed-off-by:
-
Cyrill Gorcunov authored
Signed-off-by:
-
Cyrill Gorcunov authored
Signed-off-by:
-
Cyrill Gorcunov authored
Signed-off-by:
-
Cyrill Gorcunov authored
Signed-off-by:
-
Cyrill Gorcunov authored
This feature will allow to catch incapability early if present in image. Signed-off-by:
-
Cyrill Gorcunov authored
- externd compel_cpuinfo_t to keep all fpu information neded for xsaves mode - fetch xsaves data in compel_cpuid All this will allow us to extend criu to support avx-512 intructions. Signed-off-by:
-
Cyrill Gorcunov authored
Signed-off-by:
-
Cyrill Gorcunov authored
Signed-off-by:
-
Cyrill Gorcunov authored
We're printing messages before the log file is set up, so instead of keeping silence lets print data in default outputs. Signed-off-by:
-
Andrei Vagin authored
Signed-off-by: -
Pawel Stradomski authored
This reduces memory usage if image files are stored on tmpfs. Signed-off-by:
Pawel Stradomski <pstradomski@google.com> Signed-off-by:
-
Pavel Tikhomirov authored
In resolve_shared_mounts there are cases when we have m->master_id > 0 but m->mnt_master is not set, it happens for cases where we have no access to master mount, for instance CT root m->parent==NULL or when mount is external. In can_mount_now for such master mounts we don't need to check mounted state also, so just use "if(mi->mnt_master)" condition instead of "if(mi->master_id > 0)" to fix segfault. https://jira.sw.ru/browse/PSBM-86978 Program terminated with signal 11, Segmentation fault. 0x000000000046328b in can_mount_now (mi=0x2155970) at criu/mount.c:2699 2699 list_for_each_entry(c, &mi->mnt_master->children, siblings) (gdb) p mi->mnt_master $2 = (struct mount_info *) 0x0 Fixes commit 3a02362c5be1 ("mount: fix can_mount_now to wait children of master's share properly") Signed-off-by:
Pavel Tikhomirov <ptikhomirov@virtuozzo.com> Signed-off-by:
-
Adrian Reber authored
Running 'criu dump -t <PID>' with a configuration file under valgrind where <PID> does not exist, gives: ==14336== 600 bytes in 5 blocks are definitely lost in loss record 5 of 5 ==14336== at 0x4C29BC3: malloc (vg_replace_malloc.c:299) ==14336== by 0x5D387A4: getdelim (in /usr/lib64/libc-2.17.so) ==14336== by 0x439829: getline (stdio.h:117) ==14336== by 0x439829: parse_config (config.c:69) ==14336== by 0x439CB2: init_configuration.isra.1 (config.c:159) ==14336== by 0x439F75: init_config (config.c:212) ==14336== by 0x439F75: parse_options (config.c:487) ==14336== by 0x42499F: main (crtools.c:140) ==14336== LEAK SUMMARY: ==14336== definitely lost: 600 bytes in 5 blocks With this patch: ==17892== LEAK SUMMARY: ==17892== definitely lost: 0 bytes in 0 blocks Signed-off-by:
Adrian Reber <areber@redhat.com> Signed-off-by:
-
Andrei Vagin authored
Acked-by:
-
Andrei Vagin authored
It works like other external resources. A user specify which namespaces are external and have not to be dumped. On restore, the user gives file descriptors to preconfigured namespaces. How to use: dump: --external net[INO]:KEY restore: --inherit-fd fd[NSFD]:KEY The test script contains more details how to use this: test/others/netns_ext/run.sh Acked-by: -
Andrei Vagin authored
We need to know which namespaces are external to restore them properly. Acked-by:
-
Pavel Tikhomirov authored
1150 1371 0:169 / /zdtm/static/private_bind_propagation.test rw,relatime shared:920 - tmpfs zdtm_fs rw 1151 1150 0:170 / /zdtm/static/private_bind_propagation.test/share1 rw,relatime shared:921 - tmpfs share rw 1152 1150 0:170 / /zdtm/static/private_bind_propagation.test/share2 rw,relatime shared:921 - tmpfs share rw 1153 1151 0:169 /source /zdtm/static/private_bind_propagation.test/share1/child rw,relatime - tmpfs zdtm_fs rw 1154 1152 0:169 /source /zdtm/static/private_bind_propagation.test/share2/child rw,relatime - tmpfs zdtm_fs rw Signed-off-by: -
Pavel Tikhomirov authored
We already check (root, mountpoint) pairs preserve, do the same for (root, mountpoint, shared, slave) fours. Signed-off-by:
-
Radostin Stoyanov authored
When CRIU is called for a first time and the /run/criu.kdat file does not exists, the following warning is shown: Warn (criu/kerndat.c:847): Can't load /run/criu.kdat This patch is replacing this warning with a more appropriate debug message. File /run/criu.kdat does not exist Signed-off-by:Radostin Stoyanov <rstoyanov1@gmail.com> Signed-off-by:
-
Pavel Tikhomirov authored
If we fail to create temporary directory for doing a clean mount we can make mount clean reusing the code which enters new mountns to umount overmounts. As when last process exits mntns all mounts are implicitly cleaned from children, see in kernel source - sys_exit->do_exit ->exit_task_namespaces->switch_task_namespaces->free_nsproxy ->put_mnt_ns->umount_tree->drop_collected_mounts->umount_tree: /* Hide the mounts from mnt_mounts */ list_for_each_entry(p, &tmp_list, mnt_list) { list_del_init(&p->mnt_child); } Fixes commit b6cfb1ce2948 ("mount: make open_mountpoint handle overmouts properly") https://github.com/checkpoint-restore/criu/issues/520Signed-off-by:
-
