At the moment we are using 4K pages all the time,
so instead of copying code over all archs we're
supporting -- add asm-generic/page.h header.
Signed-off-by: Cyrill Gorcunov <gorcunov@openvz.org>
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>
We have #define BUG() BUG_ON(true) here, where 'true'
is defined in stdbool header, so to be able to include
bug.h on its own -- include needed header inplace.
Signed-off-by: Cyrill Gorcunov <gorcunov@openvz.org>
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>
These are needed to compile project on CentOS 6.
Signed-off-by: Cyrill Gorcunov <gorcunov@openvz.org>
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>
Pavel reported that in case if there a big number
of small vmas present in the dumpee we're reading
/proc/pid/pagemap too frequently.
To speedup this procedue we inroduce pagemap cache.
The interface is:
- pmc_init/pmc_fini for cache initialization and freeing
- pmc_get_map to retrieve specific PMEs array for VMA area
v2:
- Move internal constants to pagemap-cache.c
- Make PAGEMAP_LEN to accept virtual address/size
- Don't adjust low bound in caching mode to save a couple of code bytes
Reported-by: Pavel Emelyanov <xemul@parallels.com>
Signed-off-by: Cyrill Gorcunov <gorcunov@openvz.org>
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>
We want to write into empty image files, so we
unlink them before dumping into. Let's O_TRUNC
it instead.
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>
Acked-by: Andrew Vagin <avagin@parallels.com>
PIPE_MAX_SIZE is calculated according with the kernel code.
PPB_IOV_BATCH has been taken from my mind.
Signed-off-by: Andrey Vagin <avagin@openvz.org>
Acked-by: Cyrill Gorcunov <gorcunov@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 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>
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>
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>
If a file mmaped or pointed by exe link is unlinked, we will
generate a ghost file for it. On restore the ghost file will
be created with the users counter 1 and the very first open
(e.g. for mmap) will unlink the file.
Handle this by bumping up user counter for every mapping
pointing on the file.
This appeared after previous patches that packed the reg-files
image. Before it each vma and exe link created separate entry
in the reg-files image.
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>
For unlinked opened and mmaped files we'd need to
care about remaps, for this the callback with both
file_desc and fdinfo_list_entry will be required.
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>
If we specify log level to none (0) the result is LOG_INFO (2).
Acked-by: Andrew Vagin <avagin@parallels.com>
Acked-by: Kir Kolyshkin <kir@openvz.org>
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>
When writing VMAs we perform too many small writes into vma-.img files.
This can be easily fixed by moving the vma-s into mm-s, all the more
so they cannot be splitted from each other.
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>
On restore we will read all VmaEntries in one big MmEntry object,
so to avoif copying them all into vma_areas, make them be pointable.
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>
Currently we check PTRACE_PEEKSIGINFO and if it's defined in a system
header, we suppose that ptrace_peeksiginfo_args is defined there too.
But due to a bug in glibc, this check doesn't work. Now we have F20,
where ptrace_peeksiginfo_args is defined in sys/ptrace and F21 where
it isn't defined.
commit 9341dde4d56ca71b61b47c8b87a06e6d5813ed0e
Author: Mike Frysinger <vapier@gentoo.org>
Date: Sun Jan 5 16:07:13 2014 -0500
ptrace.h: add __ prefix to ptrace_peeksiginfo_args
Signed-off-by: Andrey Vagin <avagin@openvz.org>
Acked-by: Cyrill Gorcunov <gorcunov@openvz.org>
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>
Right now we do it two times -- on shmem prepare and
on the restore itself. Make collection only once as
we do for fdinfo-s -- root task reads all stuff in and
populates tasks' rst_info with it.
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>
When parsing mappings in proc, we fstat vm file, later,
when dumping it, we stat it again to fill fd_parms.
The 2nd stat is not required, we can keep the stat in
vma_area.
This removed 35% of all stat calls on dump of basic container.
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>
The is_foo_link readlinks the lfd to check. This makes
anon-inodes dumping readlink several times to find proper
dump ops. Optimize this thing.
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>
Quite a lot of VMAs in tasks map the same file with different
perms. In that case we may skip opening all these files, but
"borrow" one from the previous VMA parsed.
There's little sense in seeking more that just previous VMA,
as same files are rarely (can be though) mapped in different
locations.
After this on a basic Centos6 container the number of opens and
stats in this function drops from ~1500 to ~500.
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>
It's useful to know this value.
W/o cache (first pre-dump) on minimal container the irmap
resolve time is ~0.2 sec. With cache (next pre-dumps or
final dump) on the same container the irmap resolve time
is 10 times less.
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>
When dumping fsnotifies we may go to irmap to get inode->path
mapping. The irmap engine scans FS (in hinted locations) to
get one and it is slow even though we scan only part of the FS.
Since the above scanning is done while tasks are frozen the
freeze time goes up :(
Improve the situation by generating irmap cache in working dir
at pre-dump when tasks get unfrozen.
The on-disk irmap cache is PB file, it sits in -W directory
and can be loaded on dump/pre-dump start in memory. When
resolving the inode->path mapping irmap may meet these entries,
revalidate them and potentially save time.
After pre-dump the (re-)collected irmap data is written back
to irmap cache image. Typically entries written back are the
same read in on cache load.
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>
We will generate some info about file-descriptors at that
stage. For now these pre-dumped ones would be fsnotifies,
so the pre-dump of a single fd is written as simple as
possible, but enough for that type of FDs pre-dump.
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>
Well, we want to pre-dump files (fsnotifies), for that we
will need mountinfo-s and root, and for the latter -- the
current ns mask.
The problem with current ns mask is that its generation is
incorporated into ns IDs generation and dumping. And since
the ids dumping is not performed on pre-dump, let's just
provide a helper for ns-mask generation.
Strictly speaking, the whole ns-mask idea is not great, but
it's to be fixed later.
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>
The existing code opens "self" and parses what's in there,
just twist the code a little to accept generic pid.
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>
Service shouldn't call client provided scripts, as it
creates a security issue (client may be unpriviledged,
while the service is).
In order to let caller do what it would normally do with
criu-scripts, make criu notify it about scripts. Caller
then do whatever it needs and responds back.
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>
RPC will start page-server daemon and needs to get the
controll back to report back to caller, but the glibc's
daemon() does exit() in parent context preventing it.
Thus -- introduce own daemonizing routine.
Strictly speaking, this is not pure daemon() clone, as the
parent process has to exit himself. But this is OK for now.
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>
If someone reads untouched page, the kernel maps the zero page
to this address. This page will not have the SOFT_DIRTY bit and it must
not be dumped.
Signed-off-by: Andrey Vagin <avagin@openvz.org>
Acked-by: Cyrill Gorcunov <gorcunov@openvz.org>
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>
For inotify/fanotifies we cannot always open inodes by a
handle and have to scan directories searching for the inode
path :(
Fortunately, in most of the containers' cases fsnotifies are
put in "typical" places. These are used as hints for scanner.
The best way to go is use openvz's ploop over such filesystems.
Long term solution is to fix NFS to provide opening by handle.
Acked-by: Cyrill Gorcunov <gorcunov@openvz.org>
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>
We will need to special-care NFS silly-rename files, thus
we need to know which FS a file belongs to.
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>
The -F|--fields option specifies which fields (by name, comma
separated) should be printed.
For nested fields all names in path should be specified.
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>
