The crtools produces not only dump in its internal format (i.e. -- pb),
but also may call other tools to create files with some state (e.g.
ip tool dumps route and ifaddr info, tmpfs will be tar-ed, iptables
utility will produce the iptables-save file, etc.).

The show functionality cannot read these images, but we can guess what
can be in the file provided by its magic.
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>

"init" in LXC opens /dev/null and then mounts devtmpfs in /dev,
so crtools can not resolve the path to the origin /dev/null.

crtools with the option --evasive-devices will check the origin
device and a new device are the same and if it's true, crtools will
dump a new path.

v2: add a description for the option
Signed-off-by: Andrey Vagin <avagin@openvz.org>
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>

This aptch replaces BUG_ON's by return of error code.
Signed-off-by: Stanislav Kinsbursky <skinsbursky@openvz.org>
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>

Signed-off-by: Pavel Emelyanov <xemul@parallels.com>

The pb_show things are no longer macros.
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>

The pb_read thing is no longer a macros. This will allow to
factor out objects collecting on restore.
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>

The pb_write thing is no longer a macros.
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>

The protobuf-c generate plain routines for entries manipulations, but
we want to have some "generic" way of working with messages. Collect them
all in an array of descriptors (similar to image files descriptions) and
do full typechecking while this.

Such thing will allow to simplfy code later.
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>

Signed-off-by: Andrey Vagin <avagin@openvz.org>
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>

In addition it fixes error handling.
Signed-off-by: Andrey Vagin <avagin@openvz.org>
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>

[xemul: Added explicit braces into ifs]
Signed-off-by: Andrey Vagin <avagin@openvz.org>
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>

When processes are restored in PIDNS, the controll process (crtools)
don't know a real pid of processes, but it knows a pid of init.

crtools can kill init and all other processes will be killed too.
Signed-off-by: Andrey Vagin <avagin@openvz.org>
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>

When a child exited, SIGCHLD is sent to parent,
if SIGCHLD has handler without SA_RESTART, the current
syscall will be interrupted.
Signed-off-by: Andrey Vagin <avagin@openvz.org>
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>

Signed-off-by: Cyrill Gorcunov <gorcunov@openvz.org>
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>

Signed-off-by: Cyrill Gorcunov <gorcunov@openvz.org>
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>

Signed-off-by: Cyrill Gorcunov <gorcunov@openvz.org>
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>

 - Use sizeof instead of PATH_MAX constant
 - Place EOS exactly after read data end
Signed-off-by: Cyrill Gorcunov <gorcunov@openvz.org>
Acked-by: Andrew Vagin <avagin@parallels.com>
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>

Revert and tune 9eda83b7. Andrey reminded me that we have
global instance of cr_options.
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>

On this stage crtools unlink old socket files, create ghost files and etc,
so we should be in a correct namespace.
Signed-off-by: Andrey Vagin <avagin@openvz.org>
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>

The option is -r|--pivot-root and an argument is a path to new root.
A root task will make pivot_root. LXC CT does that, so we need that
for restoring.

v2: s/pivot-root/root/
Signed-off-by: Andrey Vagin <avagin@openvz.org>
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>

The pstree_item for helpers is allocated without rst_info.
Before this patch prepare_fd_pid was executed for such items and
touched rst_info.
Signed-off-by: Andrey Vagin <avagin@openvz.org>
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>

The kernel patch is in 3.5 branch, so we can make this test
run automatically.
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>

It's not in zdtm.sh yet, since kernel patch is not yet
committed. When kernel is updated, the zdtm.sh will be too.
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>

Signed-off-by: Pavel Emelyanov <xemul@parallels.com>

Only the fact of the fd presence, its flags and fown and the sigmask.
The sigpending state is tightly coupled with the task's sigpending
state which is not yet supported.
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>

Signed-off-by: Pavel Emelyanov <xemul@parallels.com>

Signed-off-by: Pavel Emelyanov <xemul@parallels.com>

The list of mounts is used by inotify to restore a watch with open-by-handle. The problem
is that after the clean_mnt_ns is done the mntinfo list is no longer relevant.

Fix it by freeing the old one and initializing the new with the read-from-image stuff.
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>

Only checks for lo, one simple ifaddr and two routes are handled. Sanity
test and nothing more.
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>

Same here -- run ip tool and that's it.
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>

Just run the ip addr save and ip addr restore respectively.
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>

The thing is that the ip utililty is very likely to have support
for ifaddrs and routes dumping and restore (rtnl messages are
symmetrical wrt dump/restore and this can be easily dump in there).

Thus, the best we can do it just use this tool for that and carry
the "raw" images with ifaddrs and routes dump.
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>

Only support the lo device. This is not final yet (much more
stuff is to be handled for a link) but is rather a skeleton
showing how to do it and letting us check the LXC container
early.
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>

If the target task sits in another netns the sockets will
not be able to interconnect unless we create the host-side
one in the same netns. Thus do it and then roll back the
namespace.
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>

Signed-off-by: Pavel Emelyanov <xemul@parallels.com>

This will be required for parasite transport socket creation -- it will
have to be created in a net ns we're putting parasite in and then we'll
have to restore it back to original to go on dumping.
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>

We'll need to check whether the socket is to be created in a net
namespace (since we can't detect this automatically yet). Thus the
namespaces flags are required there.
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>

Raw images are supposed to be files with non-crtools contents.
E.g. tarballs with tmpfs contents or iptables-save output. Another
example is -- ip tool addr and route dumps we're about to merge
soon.

Having these type of images allows to use the open_image and the
cr_fdset engine easily.
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>

This type of message is also reported for NLM_F_ACK is requested
and no necessarilly indicates an error. The error code is in the
message body.
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>

Will need it int netns dumping callbacks later.
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>