- 30 Oct, 2018 40 commits
-
-
Adrian Reber authored
Signed-off-by:
Adrian Reber <areber@redhat.com> Signed-off-by:
Andrei Vagin <avagin@virtuozzo.com>
-
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:
-
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:
-
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:
-
