- 23 May, 2014 2 commits
-
-
Andrey Vagin authored
vmsplice doesn't work for such VMA-s. This flags is set in a kernel function remap_pfn_range() (remap kernel memory to userspace), which is widely used by device drivers to provide direct access to a device memory. Reported-by:
J F <jgmb45@gmail.com> Cc: Cyrill Gorcunov <gorcunov@openvz.org> Signed-off-by:
Andrey Vagin <avagin@openvz.org> Acked-by:
Cyrill Gorcunov <gorcunov@openvz.org> Signed-off-by:
Pavel Emelyanov <xemul@parallels.com>
-
Cyrill Gorcunov authored
When there is a bind mount present on same mountpoint where mark is laying the device of both mountpoints is the same so we might end up getting wrong mountpoint. Instead we should used mount id which is unique among all mounpoints. Note it's a fast fix, I need to review fsnotify code more and make sure all corner cases are covered. https://bugzilla.openvz.org/show_bug.cgi?id=2974Reported-by:
Andrew Vagin <avagin@parallels.com> Signed-off-by:
-
- 20 May, 2014 1 commit
-
-
Filipe Brandenburger authored
Add extra troubleshooting messages for errors and failures so that the output can help troubleshoot the issue. Make error handling more uniform by using -1 for errors (e.g. opening files, reading from pagemap, etc.) and 1 for failures (data mismatch, pages not COWed when expected to be, etc.) Tested: Ran this test with criu versions known to have problems with COW and with problems to read from pagemap due to the dumpable flag not being preserved. Signed-off-by:
Filipe Brandenburger <filbranden@google.com> Acked-by:
-
- 14 May, 2014 3 commits
-
-
Andrey Vagin authored
The test proces opens master and slave points. The slave point becomes the control terminal for this process. Then the test process forks a second process and the first process closes the master point. So when a master point is closed in a second process, the first one will be killed by SIGHUP. Reported-by:
Victor Konyashkin <vkonyashkin@parallels.com> Signed-off-by:
-
Andrey Vagin authored
test/Makefile knows better how to execute tests. For example it allows to execute tests simultaneously Signed-off-by:
-
Andrey Vagin authored
Signed-off-by:
-
- 13 May, 2014 4 commits
-
-
Filipe Brandenburger authored
Preserve the dumpable flag, which affects whether a core dump will be generated, but also affects the ownership of the virtual files under /proc/$pid after restoring a process. Tested: Restored a process with a criu including this patch and looked at /proc/$pid to confirm that the virtual files were no longer all owned by root:root. zdtm tests pass except for cow01 which seems to be broken. (see https://bugzilla.openvz.org/show_bug.cgi?id=2967 for details.) This patch fixes https://bugzilla.openvz.org/show_bug.cgi?id=2968Signed-off-by:
-
Andrey Vagin authored
We stop searching if vma->start is bigger than a required one. The coursor is set on the last examined vma. When we are searching a parent vma for the next vma, we start examine vma-s starting from coursor->next, so we don't examine the vma, which is pointed by cursor. This patch replaces list_for_each_entry_continue on list_for_each_entry_from. Reported-by:
-
Andrey Vagin authored
A parent vma can be only one. Fixes: 57d25e7c ("mm: fix expression to determine which vma-s can be shared") Reported-by:
-
Andrey Vagin authored
Look at this hunk from 7659c995: - paddr = decode_pointer(vma_premmaped_start(&p->vma)); + paddr = decode_pointer(vma->premmaped_addr); Obviously we want to use p->premmaped_addr instead of vma->premmaped_addr. Fixes: 7659c995 ("vm: don't overwrite vma->shmid for private mappings") Reported-by:
-
- 12 May, 2014 5 commits
-
-
Cyrill Gorcunov authored
Here we test a big number of small VMAs to survive c/r. The main idea is to use a big number of IOVs needed for page transferring. Signed-off-by:
-
Cyrill Gorcunov authored
In a worst scenario we need one IOV for every page we're transferring from the parasite, thus don't divide by two here. Signed-off-by:
-
Andrey Vagin authored
* VDSO is never mapped with MAP_GROWSDOWN * The first page of growsdown vma may be a guard page, so any attempt to read it is suppressed by SIGBUS. Signed-off-by:
-
Cyrill Gorcunov authored
Useful for debugging. Signed-off-by:
-
Pavel Emelyanov authored
We explicitly setns() every single task by hands when restoring mount namespaces, they can be created without the NEWNS flag. Signed-off-by:
-
- 07 May, 2014 4 commits
-
-
Andrey Vagin authored
This test case creates two consecutive grows down vmas with a hole between them. Signed-off-by:
-
Andrey Vagin authored
Currently we don't add a guard page to a second consecutive growsdonw vma, even if here is enough space for it. It's wrong. Look at the following test output: Execute zdtm/live/static/grow_map03 ./grow_map03 --pidfile=grow_map03.pid --outfile=grow_map03.out Dump 3888 Restore Test: zdtm/live/static/grow_map03, Result: FAIL ==================================== ERROR ==================================== Test: zdtm/live/static/grow_map03, Namespace: Dump log : /root/git/criu/test/dump/grow_map03/3888/1/dump.log --------------------------------- grep Error --------------------------------- ------------------------------------- END ------------------------------------- Restore log: /root/git/criu/test/dump/grow_map03/3888/1/restore.log --------------------------------- grep Error --------------------------------- pie: Error (pie/restorer.c:465): Unable to remap 0x7f0da2c99000 -> 0x7f46425fc000 pie: Error (pie/restorer.c:969): Restorer fail 3888 (00.035621) Error (cr-restore.c:1590): Restoring FAILED. ------------------------------------- END ------------------------------------- ================================= ERROR OVER ================================= strace: mremap(0x7fc3de5b6000, 0, 0, MREMAP_MAYMOVE|MREMAP_FIXED, 0x7f38dd4e0000) = -1 EINVAL (Invalid argument) Signed-off-by:
-
Andrey Vagin authored
Our version of macroses are worng. Our macros: #define MINOR(dev) ((dev) & 0xff) Glibc function: return (__dev & 0xff) | ((unsigned int) (__dev >> 12) & ~0xff); Reported-by:
Amey Deshpande <ameyd@google.com> Signed-off-by:
-
Cyrill Gorcunov authored
The page-pipe buffers may be reused once queued pages are dumped, but we happen to increase page_pipe::nr_pipes all the timer, regardless the fact where page buffer came from. In worst scenario this may lead to incorrect -EAGAIN returned from page_pipe_grow forcing calling code to create new pipes. This is not critical but should be fixed. In other words page_pipe::nr_pipes must track _really_ created pipes. Signed-off-by:
-
- 25 Apr, 2014 4 commits
-
-
Pavel Emelyanov authored
We have made big step towards C/R of LXC containers -- made support for nested mount namespaces and addressed the re-attach issue. Also we have AArch64 support merged. Some work is still to be done, but it's good time to show what we have so far, thus -- the 1.3-rc1. Signed-off-by: -
Christopher Covington authored
It's possible that a procfs mounted somewhere other than /proc is in use. Signed-off-by:
Christopher Covington <cov@codeaurora.org> Signed-off-by:
-
Cyrill Gorcunov authored
https://bugzilla.openvz.org/show_bug.cgi?id=2949Signed-off-by:
-
Andrey Vagin authored
v2: s/tun/mnt_id Signed-off-by:
-
- 24 Apr, 2014 1 commit
-
-
Andrey Vagin authored
Nested mount namespaces should be checked only if fdinfo contains mnt_id Signed-off-by:
-
- 23 Apr, 2014 5 commits
-
-
Pavel Emelyanov authored
Signed-off-by: -
Pavel Emelyanov authored
Signed-off-by: -
Andrey Vagin authored
Execute zdtm/live/static/pipe00 ./pipe00 --pidfile=pipe00.pid --outfile=pipe00.out Dump 3158 Restore test/zdtm.sh: line 472: 3173 Segmentation fault (core dumped) setsid restore --file-locks --tcp-established -x -D -o Reported-by: Jenkins Criuovich Signed-off-by:
-
Pavel Emelyanov authored
Signed-off-by: -
Pavel Emelyanov authored
Signed-off-by:
-
- 22 Apr, 2014 11 commits
-
-
Pavel Emelyanov authored
The nsid lookup will search for mount in case mnt_id is given. No need to do it twice (the 2nd time for sanity check). Signed-off-by: -
Pavel Emelyanov authored
This makes mntns_get_root_fd usage more natural. Signed-off-by: -
Pavel Emelyanov authored
Signed-off-by: -
Pavel Emelyanov authored
Signed-off-by: -
Pavel Emelyanov authored
The only exception (for now) is the irmap -- it should operate on ns as well. Signed-off-by: -
Pavel Emelyanov authored
This is more logical -- we should remap file in namespace, not in pid. Also this would help to clean the code further. Signed-off-by: -
Pavel Emelyanov authored
This reverts commit f55a0b91. The collected mounts list a) points to nsid and b) should be put on nsid's mntinfo_tree. Thus is _should_ be done by separate calls.
-
Pavel Emelyanov authored
Nowadays this routine is mainly used for getting an fd, rather than keeping one for future reference. Signed-off-by: -
Andrey Vagin authored
Now mntns_collect_root() should be called each time when we need to get a root of a specified namespace and we don't need to call it for initializing the global variable. Signed-off-by:
-
Pavel Emelyanov authored
Acked-by:
-
Pavel Emelyanov authored
Acked-by:
-
