- 02 Apr, 2017 8 commits
-
-
Cyrill Gorcunov authored
When infecting victim we construct sigframe to be able to self-rectore it in case if something goes wrong. But in case is a targer been using alternative stack for signal handling it will be missed in sigframe since we don't fetch it. Thus add fetching sas on infection stage and put it into signal frame early. Signed-off-by:
Cyrill Gorcunov <gorcunov@openvz.org> Signed-off-by:
Andrei Vagin <avagin@virtuozzo.com>
-
Dmitry Safonov authored
We need to leave this part of restorer in restored task in case of inserted redirected calls. Jump trampolines from old vdso lead here - it would be painful to land nowhere. Signed-off-by:
Dmitry Safonov <dsafonov@virtuozzo.com> Signed-off-by:
-
Dmitry Safonov authored
Reworked this code a little and it becomes more readable. Drop those macroses under CONFIG_X86_64 define and just use boolean `compat_vdso' to check whether insert 64 or 32-bit jmp. Signed-off-by:
-
Dmitry Safonov authored
It's the same on all archs (as it's called from generic code), no need to redeclare it. <parasite-vdso.h> is included in all per-arch headers. Drop vdso_symtable forward declaration as <parasite-vdso.h> includes <util-vdso.h> header which defines the structure. Signed-off-by:
-
Cyrill Gorcunov authored
When checkpointing applications with really big memory slab (like in our vz7 test with 920G of memory) the int type get cutted, we should use long int instead, just like we do in other code pieces. Otherwise get (on vz7's criu, which s sharing the code) | pie: 756: Daemon waits for command | (01.193097) Wait for ack 12 on daemon socket | (01.193112) Fetched ack: 12 12 0 | (01.193164) 988065 fdinfo 0: pos: 0 flags: 100002/0 | (01.193201) fdinfo: type: 0xb flags: 0100002/0 pos: 0 fd: 0 | (01.193279) 988065 fdinfo 1: pos: 0 flags: 100002/0 | (01.193307) fdinfo: type: 0xb flags: 0100002/0 pos: 0 fd: 1 | (01.193341) 988065 fdinfo 2: pos: 0 flags: 100002/0 | (01.193365) fdinfo: type: 0xb flags: 0100002/0 pos: 0 fd: 2 | (01.193375) ---------------------------------------- | (01.193405) Error (criu/parasite-syscall.c:243): BUG at criu/parasite-syscall.c:243 | pie: 756: Error (criu/pie/parasite.c:676): Trimmed message received (1> Signed-off-by:
-
Cyrill Gorcunov authored
Signed-off-by:
-
Cyrill Gorcunov authored
Supporting shutdown for dgram sockets (udp and udplite) is simple -- just fetch the state from diag module and record it in the image, then upon socket creation restore this state. Signed-off-by:
-
Pavel Tikhomirov authored
To restore fsnotify's watches on files we need to find paths for each of them using handle we have in /proc/<pid>/fdinfo/<fsnotifyfd>. These handle is valid to open the file with open_by_handle_at if you have mount fd where the file lays. So we try open_by_handle_at for all possible mount fds we have. But we can not do so for 'file' bind-mounts, as the way we open mount fd opens file instead and can hang on fifos or fail on sockets. (see check_open_handle->open_handle->open_mount code path, imagine lookup_mnt_sdev() found 'file' bind-mount, open_mount() failed(hanged) in __open_mountpoint() and if irmap_lookup() also was not successful the whole dump fails too) So if we have file bindmount of fifo file, and we restore some inotify on other file on other mount with same s_dev, we hang forever on open. So just skip non-directory mounts from inotify search we will find path for them on other mount(e.g. non-bindmount) with same s_dev. v2: remove isdir hashing, improve commit message v3: make lookup_mnt_sdev handle only nondir mounts, add comment, move more expensive notdir_mountpoint check after s_dev v4: inverse notdir_mountpoint to be mnt_is_dir, now on error in mnt_is_dir mount is also skipped Signed-off-by:
Pavel Tikhomirov <ptikhomirov@virtuozzo.com> Signed-off-by:
-
- 27 Mar, 2017 2 commits
-
-
Andrei Vagin authored
External mounts are provided by an user and CRIU doesn't need to restore their content. https://github.com/xemul/criu/issues/299 Reported-by: Stéphane Graber Signed-off-by:
-
Andrei Vagin authored
Currently we collect mounts to clean up a mount namespace, but it isn't required when we are going to call pivot_root. https://github.com/docker/docker/issues/31663Signed-off-by:
-
- 15 Mar, 2017 30 commits
-
-
Pavel Emelyanov authored
An example, that steals stderr descriptor from victim task. Signed-off-by:
Pavel Emelyanov <xemul@virtuozzo.com> Signed-off-by:
-
Pavel Emelyanov authored
The same for libcompel.so user. Signed-off-by:
-
Pavel Emelyanov authored
This is just export by reasonable name of the existing code, that sends and receives FDs via compel RPC socket. v2: Rebase on recent criu-dev Fix parallel build Signed-off-by:
-
Dmitry Safonov authored
CID 73371 (#1 of 1): Big parameter passed by value (PASS_BY_VALUE) pass_by_value: Passing parameter regs of type user_regs_struct_t (size 224 bytes) by value. Suggesting to do this until compel is released and API is cut in stone. Signed-off-by:
-
Dmitry Safonov authored
Found by Coverity error: > CID 172193 (#1 of 1): Bad bit shift operation (BAD_SHIFT) > 1. large_shift: In expression 1 << sig % 64, left shifting > by more than 31 bits has undefined behavior. The shift amount, > sig % 64, is as much as 63. That is: 1. yes, UB 2. while adding a signal to mask, this has flushed all other signals from mask. Signed-off-by:
-
Dmitry Safonov authored
The purpose is to unblock previously blocked SIGCHLD, not all the signals. IIRC, this block-unblock dancing is about a race where SIGCHLD may come during switching to restorer blob, where CRIU handler function is already unmapped - which will result in segmentation violation if SIGCHLD wasn't blocked. Fixes:3a61c38a ("restore: block sigchld to remap task_entries") Cc: Andrei Vagin <avagin@virtuozzo.com> Signed-off-by:
-
Kir Kolyshkin authored
The statement like #include <compel/plugins/plugin-std.h> looks a bit tautological. I think the single "plugins" word is enough: #include <compel/plugins/std.h> Reviewed-by:
Kir Kolyshkin <kir@openvz.org> Signed-off-by:
-
Kir Kolyshkin authored
First, for building compel plugins, we already have "-I compel/include/uapi" in ccflags and asflags, so there is no need to add "-iquote include/uapi". Second, let's refer to compel plugin uapi includes in a uniform way, choosing the same way the external code does, i.e. #include <compel/...>. Third, in a few cases simplify #include statements by including compel/plugins/plugin-std.h instead of a number of plugins/std/*.h files. Reviewed-by:
-
Kir Kolyshkin authored
This header should have everything we have in std/ Reviewed-by:
-
Kir Kolyshkin authored
* install 'cp' can copy recursively, create directories, and even dereference symlinks. Everything we have in uapi/ is to be installed. NOTE we can't use -r for compel includes, as there is some extra stuff in there we don't want to take with us (in particular, plugins/ and 'compel -> .' symlinks). * uninstall rm -rf everything under compel includedir While at it, fix some minor things here and there. Reviewed-by:
-
Kir Kolyshkin authored
It is not used anywhere, so unless someone has any plans, let's kill it. Reviewed-by:
-
Kir Kolyshkin authored
A slash after a directory was missing in a number of places, that resulted in "make uninstall" leaving a number of files behind. Signed-off-by:
-
Kir Kolyshkin authored
GNU make tries to rebuild any makefiles it uses. While in general it's a good idea (and it is used e.g. in autoconf-based builds), in our case it is not necessary, as all the makefiles are static. More to say, as we have a few "match anything" rules for subdirectories, Makefiles in these subdirs are also matching these rules, which leads to excessive (re)building while a particular makefile is needed. Protect such Makefiles with explicit (or pattern) rules, so make knows it should do nothing to rebuild those. Signed-off-by:
-
Kir Kolyshkin authored
Apparently @true was used as a rule for any target which should have a non-empty rule doing nothing. For this, there's a "<target>: ;" syntax, let's use this and eliminate an unnecessary fork/exec :) Signed-off-by:
-
Kir Kolyshkin authored
Mostly this is done in order to not repeat the recursive clean lines twice. Signed-off-by:
-
Kir Kolyshkin authored
Signed-off-by:
-
Kir Kolyshkin authored
As all builds are done from top source dir, there is no need to have SRC_DIR. Reviewed-by:
-
Kir Kolyshkin authored
Our whole system of Makefiles are integrated from top to bottom, meaning: 1. The paths in sub-makefiles are relative to the top source dir. 2. Sub-makefiles are executed via make $(build)=<SUBDIR> <TARGET> For some reason, makefiles under lib/ are the exclusion. Let's fix it. Side effect: you can now build any individual target under lib/, for example, "make lib/c/libcriu.so" works. [v2: use the .FORCE, thanks to dsafonov@] Signed-off-by:
-
Kir Kolyshkin authored
As compel is an external tool now, let's treat it as such -- remove the hardcoded paths to compel files, they are now provided via compel CLI. Details: 1. The compel std plugin dependency is dropped from the intermediate criu/Makefile. It was there in order to make sure plugin is built before pie, but the top level Makefile and Makefile.compel take care about it. 2. The compel std plugin logic is simplified in criu/pie/Makefile. 3. The compel linker script dependency is kept as-is for now (except the linker script file name no longer appears in the list of objects to link). 4. Linking of compel std plugin is moved to a second linking stage in order to simplify the Makefile. Side note: we can actually avoid running the linker twice! 5. The compel binary dependency is dropped from criu/pie/Makefile as this is already there in top-level Makefile (look for criu-deps). [v2: reworked after dsafonov@ comments; keep most compel deps] Signed-off-by:
-
Dmitry Safonov authored
To check that jump trampolines to rt-vdso works. Acked-by:
-
Dmitry Safonov authored
Acked-by:
-
Dmitry Safonov authored
Reduce __export_restore_task(), which is fat and too long, drop needless parameter from vdso_proxify() and drop also that find-tuple logic, which isn't needed really. Acked-by:
-
Dmitry Safonov authored
It's always "dumpee" and is used in two pr_err() messages, put it right there. Acked-by:
-
Dmitry Safonov authored
We should log whom we're remapping, but ~5 lines upper or so we've unmapped dumpee vdso and vvar. Here we're mremapping runtime host-provided vdso/vvar blobs to the dumpee position. Correct the messages to reflect that we've remapped rt-vdso/vvar, having the same naming as in vdso_do_park(). Acked-by:
-
Dmitry Safonov authored
Acked-by:
-
Dmitry Safonov authored
Remove not needed VDSO_SYMBOL_*_NAME defines. Acked-by:
-
Dmitry Safonov authored
Acked-by:
-
Dmitry Safonov authored
For 32-bit at this moment there are follwing entries: o __vdso_clock_gettime o __vdso_gettimeofday o __vdso_time o __kernel_vsyscall o __kernel_sigreturn o __kernel_rt_sigreturn So, there isn't __vdso_getcpu(), which is present in 64-bit vDSO, and 64-bit vDSO doesn't have those __kernel_*. This is fine as two vdso blobs with the same not present symbols are considered to be the same in comparison. I didn't introduce ARCH_VDSO_SYMBOLS_32, as it would have different size and that will result in quite painful conversion of struct vdso_symtable (it's fixed size and e.g., inside parasite's parameters) Which is not needed by the described behavior of vdso blobs comparison. Acked-by:
-
Dmitry Safonov authored
Forward CRIU's log fd into helper, so it can actually print errors. This will help to debug troubles with helper, like #273. Log fd can be safely written to, as it's opened in CRIU with O_APPEND or it's line-buffered (stdout) or not buffered (stderr) stream. Anyway, it's double safe, as there is simple synchronization between helper and CRIU, so only one of them will log at a time. Also expanded the comment about a helper. Acked-by:
-
Kir Kolyshkin authored
This macro is not in use since mid-2012 (commit 4806e139 "protobuf: Convert vma_entry to PB format v3"), so I guess it is about time to retire it. Signed-off-by:
-
