- 30 Oct, 2018 40 commits
-
-
Andrei Vagin authored
CC criu/cr-restore.o criu/cr-restore.c:3470:22: error: address of array 'thread_args[i].comm' will always evaluate to 'true' [-Werror,-Wpointer-bool-conversion] if (thread_args[i].comm) ~~ ~~~~~~~~~~~~~~~^~~~ 1 error generated. Signed-off-by:Andrei Vagin <avagin@virtuozzo.com>
-
Andrei Vagin authored
This reverts commit 8f1ba5892dd2b137a24e144febed2464f245ed1a. This test doesn't work right now: =[log]=> dump/zdtm/transition/maps007/174/3/restore.log ------------------------ grep Error ------------------------ (00.237564) 1: `- FD 2 pid 6 (00.237566) 1: `- type 1 ID 0xa (00.237567) 1: `- FD 3 pid 5 (00.237568) 1: `- FD 3 pid 6 (00.240025) 1: Error (criu/image.c:432): Unable to open pages-3.img: Permission denied (00.270600) uns: calling exit_usernsd (-1, 1) (00.270640) uns: daemon calls 0x469f80 (199, -1, 1) (00.270648) uns: `- daemon exits w/ 0 (00.271193) uns: daemon stopped (00.271199) Error (criu/cr-restore.c:2308): Restoring FAILED. ------------------------ ERROR OVER ------------------------ Signed-off-by: -
Andrei Vagin authored
Fixes: e8f913fbfd9d ("unix: check that a length of a socket is less than UNIX_PATH_MAX") Signed-off-by: -
Andrei Vagin authored
Reported-by:
志平 林 <larry.lin@outlook.com> Signed-off-by:
-
Andrei Vagin authored
CID 190774 (#1 of 1): Out-of-bounds access (OVERRUN) 5. overrun-buffer-arg: Overrunning array addr.sun_path of 108 bytes by passing it to a function which accesses it at byte offset 4094 using argument ui->ue->name.len (which evaluates to 4095). Signed-off-by: -
Andrei Vagin authored
CID 190775 (#1 of 1): Dereference before null check (REVERSE_INULL) check_after_deref: Null-checking m->parent suggests that it may be null, but it has already been dereferenced on all paths leading to the check. Signed-off-by: -
Andrei Vagin authored
CID 190777 (#1 of 1): Resource leak (RESOURCE_LEAK) 15. leaked_handle: Handle variable server_fd going out of scope leaks the handle. Signed-off-by: -
Adrian Reber authored
Signed-off-by:
Adrian Reber <areber@redhat.com> Signed-off-by:
-
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:
-
