- 09 Aug, 2017 39 commits
-
-
Michael Holzheu authored
Debian is compiled for z900 - therefore we can't use the "laa" instruction. Fix this and replace "laa" by the older "cs" (compare and swap) loop. Signed-off-by:
Michael Holzheu <holzheu@linux.vnet.ibm.com> Signed-off-by:
Andrei Vagin <avagin@virtuozzo.com>
-
Michael Holzheu authored
The flogr instruction not supported by debian jessie (z900). So replace it by the gcc built-in. Signed-off-by:
-
Michael Holzheu authored
Use the "-fno-optimize-sibling-calls" gcc option to prevent GOT relocations caused by gcc versions without the commit "S/390: Fix 64 bit sibcall": * https://gcc.gnu.org/viewcvs/gcc?view=revision&revision=233169 Otherwise we get compile errors like: GEN criu/pie/parasite-blob.h Error (compel/src/lib/handle-elf-host.c:572): Unsupported relocation of type 26 Those can be caused by the following relocation types: * R_390_GOTENT (e.g. RHEL7 based systems) * R_390_GOTPCDBL (e.g. Debian Jessie) * R_390_GOT12 (e.g. Debian Jessie) Signed-off-by:
-
Michael Holzheu authored
For kernels that don't have commit ee71d16d22 ("s390/mm: make TASK_SIZE independent from the number of page table levels") criu sets TASK_SIZE to 4 TB on s390 (see compel_task_size()). When dumping tasks >= 4 TB on such systems, we would silently loose memory >= 4TB. So add a check and refuse to dump the task in that case. When restoring tasks >= 4 TB on such systems, the remap() call for moving the vmas at the end of the restor process would fail and a very unclear error message is printed. So add a check and write a more speaking error message in that case. Reviewed-by:Alice Frosi <alice@linux.vnet.ibm.com> Signed-off-by:
-
Michael Holzheu authored
On s390 we have special console drivers with minors 64 and 65. Add support for them in criu code and in zdtm testsuite. Reviewed-by:
-
Michael Holzheu authored
If the kernel contains patch ee71d16d22 ("s390/mm: make TASK_SIZE independent from the number of page table levels") we are able to checkpoint tasks > 4TB. Add a testcase to verify this. Signed-off-by: -
Michael Holzheu authored
Reviewed-by:
Dmitry Safonov <dsafonov@virtuozzo.com> Signed-off-by:
-
Michael Holzheu authored
Reviewed-by:
-
Michael Holzheu authored
Add s390 parts to common code files. Patch history ------------- v2->v3: * Add: Fix big endian byte order checks Reviewed-by:
-
Michael Holzheu authored
Reviewed-by:
-
Michael Holzheu authored
Reviewed-by:
-
Michael Holzheu authored
Add s390 parts to common code files. Patch history ------------- v2->v3: * Add: s390: Consolidate -msoft-float into Makefile.compel Reviewed-by:
-
Michael Holzheu authored
This patch only adds the support but does not enable it for building. Reviewed-by:
-
Pavel Emelyanov authored
This completes merging files images into one. Signed-off-by:
Pavel Emelyanov <xemul@virtuozzo.com> Signed-off-by:
-
Pavel Emelyanov authored
Signed-off-by:
-
Pavel Emelyanov authored
Same here -- now when we collect info and driver at the same place late enough we can verify info once, then attach to files. Signed-off-by:
-
Pavel Emelyanov authored
Since we need tty driver for info, we may lookup the guy when collecting info, not when attaching it to a file. Signed-off-by:
-
Pavel Emelyanov authored
There are two object for TTY files -- the file itself and tty_info. The latter is effectively an inode image. Right now we collect infos before files, so that latter can find former and attach to it. In order to move tty files on generic file entry we need to collect files very early, much earlier, that infos. So here's the patch that changes the order of tty file vs info collection. The general idea is -- when collecting files put them in a list and when an info arrives it walks that list and attaches ttys to self. Next patches will also add some optimization available with that scheme. Signed-off-by:
-
Pavel Emelyanov authored
Reviewed-by:
Kirill Tkhai <ktkhai@virtuozzo.com> Signed-off-by:
-
Pavel Emelyanov authored
Reviewed-by:
-
Pavel Emelyanov authored
Reviewed-by:
-
Pavel Emelyanov authored
Reviewed-by:
-
Pavel Emelyanov authored
Reviewed-by:
-
Pavel Emelyanov authored
Reviewed-by:
-
Pavel Emelyanov authored
Reviewed-by:
-
Pavel Emelyanov authored
Reviewed-by:
-
Pavel Emelyanov authored
Reviewed-by:
-
Pavel Emelyanov authored
Reviewed-by:
-
Pavel Emelyanov authored
Reviewed-by:
-
Pavel Emelyanov authored
Reviewed-by:
-
Pavel Emelyanov authored
Reviewed-by:
-
Pavel Emelyanov authored
Reviewed-by:
-
Pavel Emelyanov authored
Reviewed-by:
-
Pavel Emelyanov authored
Reviewed-by:
-
Pavel Emelyanov authored
There are two goals of this merge. First is to reduce the amount of image files we generate and scan on restore. The latter is more importaint, as even if we have no weird stuff like signalfd, we still try to open this file. So after the merge we try to open ~15 image files (out of ~30) less %) which is nice. The 2nd goal is to simplify the C/R support for SCM messages. This becomes possible with the fact, that all files we have can be distinguished by their ID only, w/o type. This, in turn, makes image layout for SCMs much simpler. Reviewed-by:
-
Pavel Emelyanov authored
I'm about to merge all the file images into one big image, so here's the place that would read it and collect. Reviewed-by:
-
Pavel Emelyanov authored
Reviewed-by:
-
Pavel Emelyanov authored
Update README.md
-
Pavel Begunkov authored
Signed-off-by:Pavel Begunkov <asml.silence@gmail.com>
-
- 08 Aug, 2017 1 commit
-
-
Pavel Emelyanov authored
(Try to) Fix the readme problems found by the feedmereadmes guys: * Tuned up the tagline * Added info about what for, history, competitors, etc. * Put more links for potential contributors
-
