FS type is required to distinguish between local files and remove ones, which
will be restored via SPFS and thus has to be created first.
Signed-off-by: Stanislav Kinsburskiy <skinsbursky@virtuozzo.com>
Signed-off-by: Pavel Emelyanov <xemul@virtuozzo.com>

Signed-off-by: Andrew Vagin <avagin@virtuozzo.com>
Signed-off-by: Pavel Emelyanov <xemul@virtuozzo.com>

It isn't required, __NR_memfd_create is defined in syscall-codes.h.

With this patch, we can run all tests in travis-ci, because there
a kernel has support of memfd, but __NR_memfd_create isn't defined
in installed headers
Signed-off-by: Andrew Vagin <avagin@virtuozzo.com>
Signed-off-by: Pavel Emelyanov <xemul@virtuozzo.com>

Signed-off-by: Eugene Batalov <eabatalov89@gmail.com>
Signed-off-by: Pavel Emelyanov <xemul@virtuozzo.com>

sys/syscall.h only defines syscall number constants but
not syscall function.
Signed-off-by: Eugene Batalov <eabatalov89@gmail.com>
Signed-off-by: Pavel Emelyanov <xemul@virtuozzo.com>

The package libcap-dev(el) was listed as required to run the tests. It
is, however, also required to build CRIU. Move the package to the right
place to fix the printed information.
Signed-off-by: Adrian Reber <areber@redhat.com>
Signed-off-by: Pavel Emelyanov <xemul@virtuozzo.com>

.. to address protobuf 3.x proto-c warnings
Signed-off-by: Pavel Emelyanov <xemul@virtuozzo.com>

s/batch/bunch/
Signed-off-by: Pavel Tikhomirov <ptikhomirov@virtuozzo.com>
Signed-off-by: Pavel Emelyanov <xemul@virtuozzo.com>

Instead of doing this crazy thing where we pass the number of zombies back
from the restorer blob to the main restore thread, let's just calculate the
number in the main restore thread when we need it.

Also, note that this patch shifts the location of this calculation: we used
to do a decrement of nr_in_progress when we waited() on a zombie, to sort
of lie about the fact that they did go through CR_STATE_RESTORE_SIGCHLD,
but since we're waiting on them anyway explicitly, there's no reason to do
all this hackery. Let's just calculate the number once in the right place
and be done with it.
Signed-off-by: Tycho Andersen <tycho.andersen@canonical.com>
Signed-off-by: Pavel Emelyanov <xemul@virtuozzo.com>

this avoids:

===================== Run zdtm/static/socket-tcpbuf6 in h ======================
Makefile:295: target 'mnt_enablefs.pid' given more than once in the same rule
Start test
Makefile:295: target 'mnt_enablefs.pid' given more than once in the same rule
./socket-tcpbuf6 --pidfile=socket-tcpbuf6.pid --outfile=socket-tcpbuf6.out
Run criu dump
Run criu restore
Wait for zdtm/static/socket-tcpbuf6 to die for 0.100000
Wait for zdtm/static/socket-tcpbuf6 to die for 0.200000
Removing dump/zdtm/static/socket-tcpbuf6/27
===================== Test zdtm/static/socket-tcpbuf6 PASS =====================

in every test.
Signed-off-by: Tycho Andersen <tycho.andersen@canonical.com>
Signed-off-by: Pavel Emelyanov <xemul@virtuozzo.com>

Signed-off-by: Andrew Vagin <avagin@virtuozzo.com>
Signed-off-by: Pavel Emelyanov <xemul@virtuozzo.com>

Signed-off-by: Stanislav Kinsburskiy <skinsbursky@virtuozzo.com>
Signed-off-by: Pavel Emelyanov <xemul@virtuozzo.com>

restore_mountpoint() should never be called without saved mountpoint.
If this happens, this is bug in script logic, which needs fixing.
https://jira.sw.ru/browse/PSBM-44207Signed-off-by: Eugene Kolomeetz <klm@virtuozzo.com>
Signed-off-by: Pavel Emelyanov <xemul@virtuozzo.com>

In such case, we must not proceed: without saved mountpoint, we risk
losing data when restarting automount service (think about tmpfs).
Currently, zero will be returned as exit status of preceeding echo.
https://jira.sw.ru/browse/PSBM-44207Signed-off-by: Eugene Kolomeetz <klm@virtuozzo.com>
Signed-off-by: Pavel Emelyanov <xemul@virtuozzo.com>

When we want to just execute command (without capturing output), we must
not do it via $(cmd). With such form, shell first gets output of 'cmd',
and then evaluates it. If this is empty string, it is successfully
executed. If not empty, all breaks down.
https://jira.sw.ru/browse/PSBM-44207Signed-off-by: Eugene Kolomeetz <klm@virtuozzo.com>
Signed-off-by: Pavel Emelyanov <xemul@virtuozzo.com>

When read bultin detects EOF, it sets empty string as value of specified
variable, and returns non-zero exit code. So we can rely just on exit
code, and not check variable value. This is standard approach.
https://jira.sw.ru/browse/PSBM-44207Signed-off-by: Eugene Kolomeetz <klm@virtuozzo.com>
Signed-off-by: Pavel Emelyanov <xemul@virtuozzo.com>

Signed-off-by: Kirill Tkhai <ktkhai@virtuozzo.com>
Signed-off-by: Pavel Emelyanov <xemul@virtuozzo.com>

This function may catch overflow near INT_MAX, so
it becomes return strange fd, like fd = -2147483648.
Fix that.
Signed-off-by: Kirill Tkhai <ktkhai@virtuozzo.com>
Signed-off-by: Pavel Emelyanov <xemul@virtuozzo.com>

v2: fix compilation warning for snprintf
v3: check iptables has xtables locks support once on init
v4: switch opts to kdat
Signed-off-by: Pavel Tikhomirov <ptikhomirov@virtuozzo.com>
Acked-by: Cyrill Gorcunov <gorcunov@openvz.org>
Signed-off-by: Pavel Emelyanov <xemul@virtuozzo.com>

when run several tests simultaneousely it seem that some iptables
commands can intersect and if we do not wait xtables lock criu fails:

(00.009263)     Running iptables [iptables -t filter -A INPUT --protocol tcp --source 127.0.0.1 --sport 55074 --destination 127.0.0.1 --dport 8880 -j DROP]
Another app is currently holding the xtables lock. Perhaps you want to use the -w option?
(00.014367) Error (util.c:660): exited, status=4
(00.014416) Error (netfilter.c:88): Iptables configuration failed: Success
(00.014432) ----------------------------------------
(00.014461) Error (cr-dump.c:1297): Dump files (pid: 24) failed with -1

https://ci.openvz.org/job/CRIU/job/CRIU-virtuozzo/branch/criu-dev/3/Signed-off-by: Pavel Tikhomirov <ptikhomirov@virtuozzo.com>
Acked-by: Andrew Vagin <avagin@virtuozzo.com>
Signed-off-by: Pavel Emelyanov <xemul@virtuozzo.com>

Now readlink is called in host context, this is obviously wrong.
Signed-off-by: Eugene Kolomeetz <klm@virtuozzo.com>
Signed-off-by: Pavel Emelyanov <xemul@virtuozzo.com>

Let's use $(...) form, it is more readable, and used in other places.
Signed-off-by: Eugene Kolomeetz <klm@virtuozzo.com>
Signed-off-by: Pavel Emelyanov <xemul@virtuozzo.com>

Otherwise the following errors can be triggered:

/usr/libexec/criu/scripts/systemd-autofs-restart.sh: line 64: [: =: unary
operator expected
/usr/libexec/criu/scripts/systemd-autofs-restart.sh: line 77: [: =: unary
operator expected
Signed-off-by: Stanislav Kinsburskiy <skinsbursky@virtuozzo.com>
Signed-off-by: Pavel Emelyanov <xemul@virtuozzo.com>

Signed-off-by: Stanislav Kinsburskiy <skinsbursky@virtuozzo.com>
Signed-off-by: Pavel Emelyanov <xemul@virtuozzo.com>

Restore_ns helper closes passed namepsace fd unconditionally.
Thus new_pid_ns must be invalidated in any case after calling for it.
Signed-off-by: Stanislav Kinsburskiy <skinsbursky@virtuozzo.com>
Signed-off-by: Pavel Emelyanov <xemul@virtuozzo.com>

Fily system type is not necessarily located in the column number 9.
But look like we can rely on " - " pattern: it's always located immediately
after dash.
Signed-off-by: Stanislav Kinsburskiy <skinsbursky@virtuozzo.com>
Signed-off-by: Pavel Emelyanov <xemul@virtuozzo.com>

There can be a situation, when autofs mount is catatonic, but doesn't know
about it yet.
It wasn't possible to distinguish between such mounts and others, which are
active, but not accessible for some reason. And all of such mounts were
threated as undumpable.
Such "hidden" catatonic mounts can appear if:

1) autofs master process has exited without switching
   the mount to catatonic mode (or was killed).

2) mount point was unmounted, but not propagated to
   nested mount namespace with private mounts.

These mounts can be handled by accessing the mount point. If it's catatonic,
it will update it's internals on first failed request to the autofs master.
Then we can read options again and dump the mountpoint as catatonic.
Signed-off-by: Stanislav Kinsburskiy <skinsbursky@virtuozzo.com>
Signed-off-by: Pavel Emelyanov <xemul@virtuozzo.com>

No not return error from autofs_find_pipe_read_end, if pipe end wasn't found,
because read_fd remains negative.
There is another explicit check in the caller of this function for read_fd and
proper messages are printed in such a case.
Return -ENOENT in case of read end of the pipe doesn't exist to distinguish
with other error types (will be used later).
Signed-off-by: Stanislav Kinsburskiy <skinsbursky@virtuozzo.com>
Signed-off-by: Pavel Emelyanov <xemul@virtuozzo.com>

Unfortunatelly, autofs doesn't allow to discover it's type. At least without
accessing master process. That means, that stat can be used to determine
whether some other file system is mounted on top of autofs (which we need to
take a decision whether to move restore fs aside or not), because it simply
stuck.
This patch does fs type discovering by parsing CTs mountinfo.
Signed-off-by: Stanislav Kinsburskiy <skinsbursky@virtuozzo.com>
Signed-off-by: Pavel Emelyanov <xemul@virtuozzo.com>

This patch slightly changes the logic on systemd autofs service restart script:

1) It tries to bind-mount the mountpoint on top of autofs (if any) somewhere
before service restart, and replace new mount point on top of autofs (if any)
by the saved one after.

2) It doesn't exit in case of error, trying to recover as much as
possible in case of failure instead and then continue services restarting.

The reason for introducing new logic is that there can be some other,
stateful, file system on top of autofs (say, tmpfs), which state was restore
during migration.
With current script this state will be lost, while this patch allows to
preserve restored mount point after service restart.
Signed-off-by: Stanislav Kinsburskiy <skinsbursky@virtuozzo.com>
Signed-off-by: Pavel Emelyanov <xemul@virtuozzo.com>

This was a silly mistake: bind-mounts share the same superblock, thus dentry
creation on a bind-monut will fail with EEXIST.
Signed-off-by: Stanislav Kinsburskiy <skinsbursky@virtuozzo.com>
Tested-by: Cyrill Gorcunov <gorcunov@openvz.org>
Signed-off-by: Pavel Emelyanov <xemul@virtuozzo.com>

This is essential to make sure, that we won't use the same pipe descriptor for
different pipes.
Otherwise we can run into problem with fd send via unix sockets.
Signed-off-by: Stanislav Kinsburskiy <skinsbursky@virtuozzo.com>
Tested-by: Cyrill Gorcunov <gorcunov@openvz.org>
Signed-off-by: Pavel Emelyanov <xemul@virtuozzo.com>

Signed-off-by: Cyrill Gorcunov <gorcunov@openvz.org>
Reviewed-by: Dmitry Safonov <dsafonov@virtuozzo.com>
Signed-off-by: Pavel Emelyanov <xemul@virtuozzo.com>

This is log cleanup patch.
Pr_perror prints new line by itself.
Signed-off-by: Stanislav Kinsburskiy <skinsbursky@virtuozzo.com>
Signed-off-by: Pavel Emelyanov <xemul@virtuozzo.com>

Otherwise information about real pid is lost in case of pid_to_virt returned
zero. This is required to output the real pid in error message instead of
always outputting zero (result of pid_to_virt).
IOW, would be nice to know the process pid we failed to find in the tree.
Signed-off-by: Stanislav Kinsburskiy <skinsbursky@virtuozzo.com>
Signed-off-by: Pavel Emelyanov <xemul@virtuozzo.com>

Without correct pid namespace systemctl is not able to determine whether
autofs is active or not.
The reason is unaccessible proc due to mount namespace change without pid
namespace change.
Signed-off-by: Stanislav Kinsburskiy <skinsbursky@virtuozzo.com>
Signed-off-by: Pavel Emelyanov <xemul@virtuozzo.com>

This will be installed into $(prefix)/libexec/criu/scripts.
Signed-off-by: Cyrill Gorcunov <gorcunov@virtuozzo.com>
Signed-off-by: Pavel Emelyanov <xemul@virtuozzo.com>

This script restarts systemd autofs services to workaround a problem, when
systemd doesn't consider autofs mount as own after restore (alien device ID
problem)

v4:
Environment variable NS_PID was renamed to CRTOOLS_INIT_PID

v2:
1) Added different checks: for process with pid, active service, systemd based
container.
Signed-off-by: Stanislav Kinsburskiy <skinsbursky@virtuozzo.com>
Signed-off-by: Pavel Emelyanov <xemul@virtuozzo.com>

Signed-off-by: Stanislav Kinsburskiy <skinsbursky@virtuozzo.com>
Signed-off-by: Pavel Emelyanov <xemul@virtuozzo.com>

Signed-off-by: Stanislav Kinsburskiy <skinsbursky@virtuozzo.com>
Signed-off-by: Pavel Emelyanov <xemul@virtuozzo.com>