- 06 Feb, 2017 1 commit
-
-
Kir Kolyshkin authored
C compiler might generate calls to memcpy, memset, memcmp, and memmove as it seem fit (so far we haven't seen memmove being required). That means we need to provide our own versions of it for code which is not linked to a libc. We already have a solution for that in commit bdf60512 ("pie: provide memcpy/memcmp/memset for noglibc case") but we faced another problem of compiler trying to optimize our builtin_memset() by inserting calls to memset() which is just an alias in our case and so it lead to infinite recursion. This was workarounded in commit 8ea0ba7d ("string.h: fix memset over-optimization with clang") but it's not clear that was a proper fix. This patch is considered to be the real solution. As we don't have any other implementations of memset/memcpy/memcmp in non-libc case, we can call ours without any prefixes and avoid using weak aliases. Implementation notes: 1. mem*() functions code had to be moved from .h to .c for the functions to be compatible with their prototypes declared in /usr/include/string.h (i.e. "extern"). 2. FORTIFY_SOURCE needed to be disabled for code not linked to libc, because otherwise memcpy() may be replaced with a macro that expands to __memcpy_chk() which of course can't be resolved during linking. https://travis-ci.org/kolyshkin/criu/builds/198415449Signed-off-by:
Kir Kolyshkin <kir@openvz.org> Signed-off-by:
Pavel Emelyanov <xemul@virtuozzo.com>
-
- 03 Feb, 2017 12 commits
-
-
Dmitry Safonov authored
Now changes in top-Makefile, middle-Makefile will result in a correct recompiling, as it's expected: [criu]$ touch criu/Makefile [criu]$ make <...> DEP criu/arch/x86/sigframe.d DEP criu/arch/x86/sigaction_compat.d DEP criu/arch/x86/crtools.d DEP criu/arch/x86/cpu.d DEP criu/arch/x86/call32.d CC criu/arch/x86/call32.o CC criu/arch/x86/cpu.o CC criu/arch/x86/crtools.o <...> travis-ci: success for Fix rebuild on Makefile changes Reported-by:Andrey Ryabinin <aryabinin@virtuozzo.com> Signed-off-by:
Dmitry Safonov <dsafonov@virtuozzo.com> Acked-by:
Cyrill Gorcunov <gorcunov@openvz.org> Signed-off-by:
-
Dmitry Safonov authored
Result: [japdoll@dsafonov criu]$ touch Makefile [japdoll@dsafonov criu]$ make make[1]: Entering directory '/home/japdoll/tools/criu' PBCC images/macvlan.pb-c.c DEP images/macvlan.pb-c.d PBCC images/autofs.pb-c.c DEP images/autofs.pb-c.d PBCC images/sysctl.pb-c.c DEP images/sysctl.pb-c.d <...> travis-ci: success for Fix rebuild on Makefile changes Signed-off-by: -
Kir Kolyshkin authored
We found a weird case of parasite code dying of SIGSEGV when clang is used as a compiler (see [1] for more details). Apparently, it was caused by clang optimizing our builtin_memset() by inserting a call to memset(). It is a valid compiler optimization, aside from the fact that in our code memset() is defined as a weak alias to builtin_memset(), which of course lead to infinite recursion and stack growth. This might be a bug in compiler, but there are ways to avoid it: 1. Rewrite builtin_memset() in asm (note it needs to be done for every architecture supported). 2. Disable compiler optimizations for this code (say, by using -O0). 3. Declare the pointer inside builtin_memcpy() as volatile. The last approach looks more appealing -- mostly for being simple. [1] https://github.com/xemul/criu/issues/279 travis-ci: success for string.h: fix memset over-optimization with clang Cc: Andrei Vagin <avagin@virtuozzo.com> Cc: Dmitry Safonov <dsafonov@virtuozzo.com> Cc: Cyrill Gorcunov <gorcunov@openvz.org> Signed-off-by:
-
Kirill Tkhai authored
So, after the patch struct pid will look as: struct pid { struct pstree_item *item; pid_t real; int state; struct { pid_t virt; struct rb_node node; } ns[1]; }; travis-ci: success for Make pstree_item::pid allocated dynamically Signed-off-by:Kirill Tkhai <ktkhai@virtuozzo.com> Signed-off-by:
-
Kirill Tkhai authored
Add a link from task's pid to pstree_item. Threads have this link set in NULL. travis-ci: success for Make pstree_item::pid allocated dynamically Signed-off-by:
-
Kirill Tkhai authored
The expression rb_entry(node, struct pstree_item, pid.node) may create a fake impression, that we dereferrence pstree_item for threads too, which is a BUG, but it's not so, because we are only interested in its ->pid field. But anyway, escape of pstree_item, iterate over struct pid, which are more readable. travis-ci: success for Make pstree_item::pid allocated dynamically Signed-off-by:
-
Kirill Tkhai authored
This will be used to pass MSG_DONTWAIT in next patch. Signed-off-by:
-
Kirill Tkhai authored
Replace "-1" return with errno codes. ENOMSG and EBADFD were choosen to do not cross with standard recvmsg() errors (described in its man page). This patch is need as preparation to making recv_msg() be able to be non-block, and return EAGAIN and EWOULDBLOCK in case of no data. Signed-off-by:
-
Andrei Vagin authored
cr_page_server() returns pid, if it is executed as a daemon otherwise it returns an error code. crtools returns 0 only if cr_page_server() returns a positive value, what is obviously wrong. travis-ci: success for crtools: close a signal descriptor after passing a preparation stage (rev6) Signed-off-by:
Andrei Vagin <avagin@virtuozzo.com> Signed-off-by:
-
Andrei Vagin authored
travis-ci: success for crtools: close a signal descriptor after passing a preparation stage (rev6) Cc: Mike Rapoport <rppt@linux.vnet.ibm.com> Signed-off-by:
-
Andrei Vagin authored
This patch adds the --siganl-fd FD option to specify a file descriptor. CRIU will write '\0' to this descriptor and close it after passing a preparation stage. It is alternative way to demonizing a criu process after a preparation stage. It's imposiable to get exit code, if a process has daemonized. The introduced way allows to wait a preparation stage and to get an exit code. It can be easy used from shell and other script languages. v3: fix a help message v4: Here is a sequence of actions how it can be used: * open a pipe * run a service with the pipe[1] as status_fd * read(pipe[0]) to wait a moment when the service will be ready to accept connections * do a work which requires the service * wait the service process to gets its exit status to be sure that everything okey travis-ci: success for crtools: close a signal descriptor after passing a preparation stage (rev6) Cc: Mike Rapoport <mike.rapoport@gmail.com> Cc: Kir Kolyshkin <kir@openvz.org> Signed-off-by: -
Dmitry Safonov authored
All kernel options, features that depend on kernel version should be checked with `criu check`. Cc: Pavel Emelyanov <xemul@virtuozzo.com> Signed-off-by:
-
- 01 Feb, 2017 27 commits
-
-
Pavel Begunkov authored
This is needed in cases when kernel doesn't support OFD locks. (OFD locks were added in 2014). travis-ci: success for zdtm: Add checkskip scripts for OFD locks Signed-off-by:
Pavel Begunkov <asml.silence@gmail.com> Signed-off-by:
Eugene Batalov <eabatalov89@gmail.com> Signed-off-by:
-
Andrei Vagin authored
* Don't send uninitialized data * Close descriptors more carefully * Add comments travis-ci: success for zdtm: improve socket-tcp-close-wait.c Reported-by:
-
Andrey Ryabinin authored
Some distros put 'ip' util in /bin directory. travis-ci: success for tests: add '/bin/ip' to deps in addition to '/sbin/ip' Signed-off-by:
-
Andrey Ryabinin authored
'info' array is off-by-one, nla_parse_nested() requires destination array (i.e. 'info') to have maxtype+1 (i.e. IFLA_INFO_MAX+1) elements: ERROR: AddressSanitizer: stack-buffer-overflow on address 0x7ffef823e3f8 WRITE of size 48 at 0x7ffef823e3f8 thread T0 #0 0x7f9ab7a3915b in __asan_memset (/usr/lib/gcc/x86_64-pc-linux-gnu/5.4.0/libasan.so.2+0x8d15b) #1 0x7f9ab6d4e553 in nla_parse (/usr/lib64/libnl-3.so.200+0xa553) #2 0x4acfb7 in dump_one_netdev criu/net.c:445 #3 0x4adb60 in dump_one_ethernet criu/net.c:594 #4 0x4adb60 in dump_one_link criu/net.c:665 #5 0x48af69 in nlmsg_receive criu/libnetlink.c:45 #6 0x48af69 in do_rtnl_req criu/libnetlink.c:119 #7 0x4b0e86 in dump_links criu/net.c:878 #8 0x4b0e86 in dump_net_ns criu/net.c:1651 #9 0x4a760d in do_dump_namespaces criu/namespaces.c:985 #10 0x4a760d in dump_namespaces criu/namespaces.c:1045 #11 0x451ef7 in cr_dump_tasks criu/cr-dump.c:1799 #12 0x424588 in main criu/crtools.c:736 #13 0x7f9ab67b171f in __libc_start_main (/lib64/libc.so.6+0x2071f) #14 0x4253d8 in _start (/criu/criu/criu+0x4253d8) Address 0x7ffef823e3f8 is located in stack of thread T0 at offset 264 in frame #0 0x4ac9ef in dump_one_netdev criu/net.c:364 This frame has 5 object(s): [32, 168) 'netdev' [224, 264) 'info' <== Memory access at offset 264 overflows this variable [320, 1040) 'req' [1088, 3368) 'path' [3424, 3625) 'stable_secret' Increase 'info' size to fix this. Fixes: b705dcc3 ("net: pass the struct nlattrs to dump() functions") travis-ci: success for net: fix stack out-of-bounds access in dump_one_netdev() Signed-off-by:
-
Andrey Ryabinin authored
Ghost file entry used right after it has been freed: ERROR: AddressSanitizer: heap-use-after-free on address 0x60700000dc50 READ of size 4 at 0x60700000dc50 thread T0 #0 0x46e819 in open_remap_ghost criu/files-reg.c:312 #1 0x46e819 in prepare_one_remap criu/files-reg.c:461 #2 0x46e819 in prepare_remaps criu/files-reg.c:507 #3 0x45af00 in root_prepare_shared criu/cr-restore.c:235 #4 0x45af00 in restore_task_with_children criu/cr-restore.c:1421 #5 0x7efc71e85f0c in clone (/lib64/libc.so.6+0xe7f0c) 0x60700000dc50 is located 32 bytes inside of 80-byte region [0x60700000dc30,0x60700000dc80) freed by thread T0 here: #0 0x7efc7305184a in __interceptor_free (/usr/lib/gcc/x86_64-pc-linux-gnu/5.4.0/libasan.so.2+0x9884a) #1 0x46e4df in open_remap_ghost criu/files-reg.c:309 #2 0x46e4df in prepare_one_remap criu/files-reg.c:461 #3 0x46e4df in prepare_remaps criu/files-reg.c:507 previously allocated by thread T0 here: #0 0x7efc73051b82 in malloc (/usr/lib/gcc/x86_64-pc-linux-gnu/5.4.0/libasan.so.2+0x98b82) #1 0x7efc7277a8ea in protobuf_c_message_unpack (/usr/lib64/libprotobuf-c.so.1+0x48ea) #2 0xd528232002838017 (<unknown module>) Just move freeing after the last 'gfe' usage to fix this. Fixes: d0097b2d ("files: Support ghost directories restore") travis-ci: success for files-reg: fix use-after-free in open_remap_ghost() Signed-off-by:
-
Pavel Tikhomirov authored
Opening /proc/<pid>/pagemap in userns is only available since linux v4.3 or later, after commit 1c90308e7a77 (pagemap: hide physical addresses from non-privileged users). So those tests fail on older kernels: https://ci.openvz.org/job/CRIU/job/CRIU-virtuozzo/job/criu-dev/1402 travis-ci: success for zdtm: do not run cow0x tests in userns Signed-off-by:
Pavel Tikhomirov <ptikhomirov@virtuozzo.com> Signed-off-by:
-
Cyrill Gorcunov authored
For more detailed error description. travis-ci: success for Add multiple devpts support Signed-off-by:
-
Cyrill Gorcunov authored
Always use %#x format for ID priting for better readability. travis-ci: success for Add multiple devpts support Signed-off-by:
-
Cyrill Gorcunov authored
travis-ci: success for Add "pre-resume" stage Signed-off-by:
-
Cyrill Gorcunov authored
The main idea is to be able to operate with container at the moment where its processess and resources are already restored but the processes are not yet in running state, ie just before we kick them. Beside the need of tuning up beancounters (which is vz7 specific feature) this might be useful to make some additional debug tests from the script. We can't reuse ACT_POST_RESTORE action or move it because we can kill the restored processes here and resume them on a source side as avagin@ explained. [ xemul: In between POST_RESTORE and PRE_RESUME ghost files are cleaned up (an a little bit more), so two separate stages are required and the latter one cannot fail. ] travis-ci: success for Add "pre-resume" stage Signed-off-by:
-
Andrei Vagin authored
The test has to do nothing during c/r. ======================= Run zdtm/static/socket_aio in ns ======================= Start test ./socket_aio --pidfile=socket_aio.pid --outfile=socket_aio.out Run criu dump Run criu restore 5: Old maps lost: set(["7f0a5188a000-7f0a5188f000 ['rw-p']"]) 5: New maps appeared: set(["7f0a51884000-7f0a5188f000 ['rw-p']", "7f0a51883000-7f0a51884000 ['---p']"]) Send the 9 signal to 97 Wait for zdtm/static/socket_aio(97) to die for 0.100000 Reported-by: Mr Jenkins travis-ci: success for zdtm/socket_aio: add a synchonization between processes Signed-off-by:
Andrei Vagin <avagin@openvz.org> Signed-off-by:
-
Andrei Vagin authored
CID 174800 (#1 of 1): Out-of-bounds write (OVERRUN) 5. overrun-local: Overrunning array buf of 1024 bytes at byte offset 1024 using index n (which evaluates to 1024). Signed-off-by:
-
Andrei Vagin authored
CID 174774 (#1 of 1): Logically dead code (DEADCODE) dead_error_line: Execution cannot reach this statement: return 1;. Signed-off-by:
-
Andrei Vagin authored
They pass in userns, so we can run them by default. travis-ci: success for zdtm: run more tests in userns Signed-off-by:
-
Andrei Vagin authored
If we have two sockets and send an upd message from one to another, we can't be sure that it will be delivered immediately, there is a change to get from recv(..., MSG_DONTWAIT) EGAIN. This message is handled asynchronously in a kernel space, so there may be a small timeout before we get it from another socket. v2: fix socket6_udp too Reported-by: Mr Travis Signed-off-by:
-
Cyrill Gorcunov authored
If desc is empty we should not try to eval it, otherwise it would lead to exceptio. So test for its size as well. travis-ci: success for zdtm.py: Fix eval error if empty desc file provided Signed-off-by:
-
Andrei Vagin authored
It is an rudiment of zdtm.sh. Now we don't add ps to a test root and we want to avoid forks in tests where it isn't supposed to be called. travis-ci: success for zdtm: don't call ps from tests Signed-off-by:
-
Andrei Vagin authored
The previous test uses only libsoccr_restore. This test creates a tcp connection, then it dumps and restore it. travis-ci: success for soccr: add one more test to check libsoccr_save/libsoccr_restore Signed-off-by:
-
Pavel Begunkov authored
travis-ci: success for series starting with [1/1] locks: Check syscalls return values in lock probing Signed-off-by:
-
Vitaly Ostrosablin authored
In some old distros -m state doesn't work correctly and test fails because test output diverges from expected results. Here we replace obsoleted -m state with -m conntrack. travis-ci: success for series starting with [v2,1/2] test: replace cat in Makefiles with awk Signed-off-by:
Vitaly Ostrosablin <vostrosablin@virtuozzo.com> Reviewed-by:
-
Vitaly Ostrosablin authored
cat *.pid works when we have only one running process at any moment. That's because pidfiles contain no newlines and cat will just concatenate content of all files present in directory. So, e.g., if we have pidfiles: 31338 31359 31880 31884 31889 cat will build following string from those pidfiles: 3133831359318803188431889 Obviously, kill would fail to send signals to processes, because it's now a single big number, which cannot be unambigously split back in general case. That's where awk comes in. We don't need to modify C part of tests to print newlines at end of file. We just order awk to print content of each file, which adds a newline at end - problem solved, kill can once again parse, which PIDs it get and send proper signals to them. Also, should be completely safe for zdtm.py, because it doesn't use Makefiles and sends signals on it's own. travis-ci: success for series starting with [v2,1/2] test: replace cat in Makefiles with awk Signed-off-by:
-
Pavel Emelyanov authored
This helps cleanup cr-time mounts a little bit. travis-ci: success for mount: Add ->collect callback Signed-off-by: -
Pavel Emelyanov authored
travis-ci: success for mount: Sanitize sb comparison code Signed-off-by: -
Pavel Emelyanov authored
Introduce fstype->sb_equal and move btrfs-specific checks into it. travis-ci: success for mount: Sanitize sb comparison code Signed-off-by: -
Pavel Emelyanov authored
travis-ci: success for mount: Sanitize sb comparison code Signed-off-by: -
Dmitry Safonov authored
Before: [~]# criu check lazy_pages Looks good. [~]# criu check --feature lazy_pages Error (criu/kerndat.c:588): Lazy pages are not available After: [~]# criu check lazy_pages Error: excessive parameters for command check ...skipped usage() output... Just a little improvement, not to mislead anyone. Cc: Kir Kolyshkin <kir@openvz.org> Signed-off-by:
-
Dmitry Safonov authored
O_* flags should be in event_f_flags parameter, according to fanotify_init(2). On x86_32 fanotify_mark() has second mask argument (as mask is 64-bit, the higher parts of mask shouldn't be used): > COMPAT_SYSCALL_DEFINE6(fanotify_mark, > int, fanotify_fd, unsigned int, flags, > __u32, mask0, __u32, mask1, int, dfd, > const char __user *, pathname) > { > return sys_fanotify_mark(fanotify_fd, flags, > #ifdef __BIG_ENDIAN > ((__u64)mask0 << 32) | mask1, > #else > ((__u64)mask1 << 32) | mask0, > #endif > dfd, pathname); travis-ci: success for 32-bit tests fixes Signed-off-by:
-
