In commit 459828b6 I suddenly broke backward
compatibility of auxv vector on 32bit machines.
Bring it back.
Reported-by: Andrey Vagin <avagin@openvz.org>
Signed-off-by: Cyrill Gorcunov <gorcunov@openvz.org>
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>

We call tar, ip, iptables, etc. when restoring container.
The problem is that these stuff is called from inside new
mount namespace after pivot_root(). But the execvp uses
PATH variable inherited from the host system, which may
not reflect real binaries layout.

Add "/bin" to path as temporary workaround.
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>

When live-migrating a container on NFS the link-remap cannot
create original file on target machine, since the file name
is still visible -- source CT is alive. The proper fix would
be to move file aside, then create link, then move original
file back, but since NFS changes file name anyway, we just
do the same -- generate another name for link.
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>

Before this patch, criu splices all data in pipes and then saves these
data in a image file. Here is a problem, becase creating pipes with big
buffers fails too often, because a kernel tries to allocate a big linear
chunks of memory. Now memory are dumped for a few iterations, where the
size of pipe buffers is restricted.

TODO: need to rework pre-dump, because currently dumping data from
      pipes are postponed. We are going to use sys_process_vm_readv for
      this.
Signed-off-by: Andrey Vagin <avagin@openvz.org>
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>

It's preparation to dump memory by chunks.
Signed-off-by: Andrey Vagin <avagin@openvz.org>
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>

The problem is that vmsplice() to a big pipe fails very often.

The kernel allocates a linear chunk of memory for pipe buffer
descriptos, but a big allocation in kernel can fail.

So we need to restrict maximal capacity of pipes. But the number of
pipes is restricted too, so we need to split dumping memory on chunks.

In this patch we calculates the pipe size for which vmsplice() will not
fail.

v2: s/batch/chunk and a few other small fixes
v3: Remove callbacks from page_pipes and reuse pipes
Signed-off-by: Andrey Vagin <avagin@openvz.org>
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>

The following issue is possibly caused by using busybox make.

protobuf/packet-sock.pb-c.c: In function 'packet_sock_entry__init':
protobuf/packet-sock.pb-c.c:98:3: error: this decimal constant is unsigned only in ISO C90 [-Werror]

Use a belt-and-suspenders approach to ensure it doesn't happen.
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>

The current -march settings will cause an error if the user a
conflicting flags such as -mcpu=cortex-a15. Use USERCFLAGS instead
of CFLAGS so that a default is provided but can be overridden.

Change-Id: I8ffecd6bfd7ad5794486a5d14d27bce3170898d3
Acked-by: Alexander Kartashov <alekskartashov@parallels.com>
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>

Ideally, a user could set CFLAGS on the command line to contain
compilation options and include and library paths (or maybe set
those last two with CPPFLAGS and LDFLAGS). Unfortunately, setting
CFLAGS on the command line currently short-circuits essential
logic in the makefile and breaks the build. After a first failed
attempt it appears that a monolithic overhaul or "flag day" to
fix this is a substantial undertaking, so for now just provide a
workaround in the form of a USERCFLAGS variable.
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>

Perhaps left over from when a single types.h was being used for
multiple architectures, remove the ARM definition of
AT_VECTOR_SIZE from the x86 types.h header. Also remove the
CONFIG_ARM definition since it unused.
Acked-by: Alexander Kartashov <alekskartashov@parallels.com>
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>

The current mechanism for determining ARM architecture version
breaks down when cross-compiling. Default to ARMv7 if the user
specifies ARCH=arm. Users wishing to cross-compile for ARMv6
platforms such as the Raspberry Pi should use ARCH=armv6 as
previously required.
Acked-by: Alexander Kartashov <alekskartashov@parallels.com>
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>

Without this a user may encounter the following error.

arch/arm/include/asm/atomic.h:38:2: error: implicit declaration of function ‘smp_mb’

With the #error pragma a user is a least pointed to the specific
section in the file that's causing the problem

arch/arm/include/asm/atomic.h:21:2: error: #error ARM architecture version (CONFIG_ARMV*) not set or unsupported.
Acked-by: Alexander Kartashov <alekskartashov@parallels.com>
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>

ARCH is a user-facing variable and setting it on the command line
clobbers any manipulation attempted in the makefile. Following
the example of the Linux kernel makefiles, use a SRCARCH variable
instead for the internal, potentially fixed-up, architecture name.
This fixes the following error.

make ARCH=x86_64
Makefile:69: *** "The architecture x86_64 isn't supported".  Stop.
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>

The top-level makefile defines an ARCH_DIR variable. Always use
it rather than referencing ARCH directly, since ARCH may be set
by the user on the command line and that raw input may not be
what needs to be used internally.
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>

A user may have necessary linker directories specified in CFLAGS.
Make sure to include them.

Change-Id: I76c2a7bd6e34cc282bfcd5f83cc69ae7fa2c8cc2
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>

The makefile includes need to be moved for everything to be
defined properly when the configure tests run.

The Ubuntu 12.04 x86_64 GCC and Linaro's 13.08 and newer AArch64
GCC's have the if_packet.h kernel header, but as of 13.12,
the Linaro AArch32 GCC does not.

Change-Id: I363c43fdb81b028f99aac77e15bff9462c87af4b
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>

The links to the versioned libcriu.so.* included $(DESTDIR) and
$(LIBDIR) which will generate wrong links if building criu packages.
Now the links points to the correct file without any path.

For some reason criu.8 was installed with executable permission. Use
'install' with '-m 644' to make sure this does not happen.
Signed-off-by: Adrian Reber <adrian@lisas.de>
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>

No need to read it in cycle.
Repored-by: Pavel Emelyanov <xemul@parallels.com>
Signed-off-by: Cyrill Gorcunov <gorcunov@openvz.org>
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>

Repeated custom entries are presented as an array
of pointers in the memory, so once we fetch the
first entry we are to continue iterating pointers
instead.

Before

	| vmas: {
	|         start: 0x00000000400000
	|         end: 0x00000000406000
	|         pgoff: 0000000000000000
	|         shmid: 0x0000000000000b
	|         prot: 0x5
	|         flags: 0x2
	|         status: 0x41
	|         fd: 0xffffffffffffffff
	| }
	| :{
	|         start: 0x00000000462d00
	|         end: 0000000000000000
	|         pgoff: 0000000000000000
	|         shmid: 0x00000000605000
	|         prot: 0x606000
	|         flags: 0
	|         status: 0x5000
	|         fd: 0x0000000000000b
	|         madv: 0x00000000000041
	| }

After

	| vmas: {
	|         start: 0x00000000400000
	|         end: 0x00000000406000
	|         pgoff: 0000000000000000
	|         shmid: 0x0000000000000b
	|         prot: 0x5
	|         flags: 0x2
	|         status: 0x41
	|         fd: 0xffffffffffffffff
	| }
	| :{
	|         start: 0x00000000605000
	|         end: 0x00000000606000
	|         pgoff: 0x00000000005000
	|         shmid: 0x0000000000000b
	|         prot: 0x1
	|         flags: 0x2
	|         status: 0x41
	|         fd: 0xffffffffffffffff
	| }
Signed-off-by: Cyrill Gorcunov <gorcunov@openvz.org>
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>

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

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

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

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

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

We're aligning members and number in protobuf
files from the very beginning for readability
sake. So fix up newer ones which were not.

Also use /* */ comments, not //.
Signed-off-by: Cyrill Gorcunov <gorcunov@openvz.org>
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>

setup_opts_from_req() prints an error message, so there's no need
for its caller to print another one.

While at it, simplify/unify error checking, treating any
non-zero value as an error.
Signed-off-by: Kir Kolyshkin <kir@openvz.org>
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>

Using a soname makes it easy for applications to
detect if the ABI of libcriu.so has changed.
It still creates libcriu.so as before in lib. During
'make install' additional links are created:

 libcriu.so -> libcriu.so.1.0
 libcriu.so.1 -> libcriu.so.1.0
Signed-off-by: Adrian Reber <adrian@lisas.de>
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>

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

CONFIG_HAS_PEEKSIGINFO_ARGS is used there.

Cc: Christopher Covington <cov@codeaurora.org>
Reported-by: Christopher Covington <cov@codeaurora.org>
Signed-off-by: Andrey Vagin <avagin@openvz.org>
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>

For x86_64, LIBDIR can be tricky to find out. Nevertheless, this
works for at least RedHat/CentOS/Fedora, SLES/openSUSE, Debian/Ubuntu
and Gentoo. So, while it can guess LIBDIR wrong, this is still
a good approximation for those installing criu from source.
Signed-off-by: Kir Kolyshkin <kir@openvz.org>
Acked-by: Cyrill Gorcunov <gorcunov@openvz.org>
Acked-by: Adrian Reber <adrian@lisas.de>
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>

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

After previous fixes we can merge and move a couple
of them for easier reading.
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>

Same for previous patch with vmas -- we do it on collect and
on real open. Just put the pointer on fifo_info structure.
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>

We do it first -- on collect, second -- on restore. The
2nd lookup is excessive, we can put fd pointer on vm_area
at lookup and reuse one later.
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>

On restore we only need to know currnet task mappings' start and end
to find where to put the restorer blob. And since the smaps file in
/proc/pid is up to 3 times slower, than the maps one, it makes
perfect sense just to parse the latter one.
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>

Those opened for cwd, root, exe link and vma-s do not
care about the pos value.
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>

Usefult to test restore time, for example.
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>

With new remap refcount users will get the counter
eventually as they appear.

Reported-by: Andrew Vagin <avagin@parallels.com> via Jenkins
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>

To link Open MPI against CRIU I need the header files installed.
Attached is a patch which adds the necessary Makefile rules to
install libcriu.so and the header file to compile against CRIU.
Signed-off-by: Adrian Reber <adrian@lisas.de>
Acked-by: Kir Kolyshkin <kir@openvz.org>
Acked-by: Andrew Vagin <avagin@parallels.com>
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>

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