The ARM parasite head uses a pad of 228 bytes
to make the offset of the symbol __export_parasite_stack
representable in the ARM instruction set. This value
needs to be changed every time the value of the macro
PARASITE_STACK_SIZE changes.
This patch makes this manual interference redundant.
Signed-off-by: Alexander Kartashov <alekskartashov@parallels.com>
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>
Currently we dump pages directly from parasite into image files. This
is bad for several reasons:
1. We cannot use any more-or-less custom format for pages easily, since
parasite code cannot be linked with any libraries;
2. We will not be able to optimize migration with preliminary memory
migration (a.k.a. iterative migration) with it -- if we send pages
from parasite over network we are not able to let the task we dump
continue running.
That said, what is done is -- pages from target task are put into a
page-pipe in one go, then (not in this patch) parasite can be released
and we can do with pages whatever we want. For now pages are just
spliced from pipe into image file.
Some numbers:
In order to drain 1Gb of memory from task we need 1.5M of shared map
in args (for iovecs) and 4 pipes (8 descriptors) each referencing 128Mb
of pages, which int turn requires 4 x 640K chunks of sequential kernel
memory (for pipe_buffer). Not that big I guess.
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>
The page-pipe is an object, that can accumulate pages inside it. It
consists of list of page-pipe-bufs, which in turn has a pipa, an
array of iovecs that describe the pages' locations and some stats.
Users of it are supposed to vmsplice pages into pipes to accumulate
then for later use, and vmsplice them from pipes when required.
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>
I will have to push some sort of map of pages to dump into parasite.
For this, I need to have estimation of how much memory I'd need for
than in parasite args. These two values will help with it.
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>
Right now when we collect list of vmas we need to know the
number of elements in it. In the future I will need to know
more, so it makes sense to create a vmas-list object for it.
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>
Just make use of previous patch. The creds dumping args are tuned to
fit one page (minimal static args size).
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>
Sometimes we don't know the exact amount of data we would want
to send to parasite via args area (e.g. -- while draining fds).
Fix this, by moving the args area behind the parasite blob and
mmap-ing it with the run-time calculated size.
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>
PIE code can't use glibc helpers so instead of passing
CR_NOGLIBC macro in every source file pie code uses just
pass it in pie/Makefile.
Signed-off-by: Cyrill Gorcunov <gorcunov@openvz.org>
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>
We will need futexes to use in PIE code but futex.h
uses BUG_ON helper, so to diet inclusions move BUG_ONs
code to include/bug.h.
Signed-off-by: Cyrill Gorcunov <gorcunov@openvz.org>
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>
PIE code use own handmade stack so we need -fno-stack-protector
option to eliminate compilation warning if -fstack-protector
passed in command line CFLAGS.
Signed-off-by: Cyrill Gorcunov <gorcunov@openvz.org>
Tested-by: Alexander Kartashov <alekskartashov@parallels.com>
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>
| cr-check.c: In function ‘check_unaligned_vmsplice’:
| cr-check.c:372:2: error: ignoring return value of ‘pipe’, declared with attribute warn_unused_result [-Werror=unused-result]
Signed-off-by: Cyrill Gorcunov <gorcunov@openvz.org>
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>
This facrots out common core members freeing into pstree.c
helper. Per-arch freeing helpers are now symmetrical to the
allocating ones.
This is a merge of two Cyrill's patches.
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>
- For NT_X86_XSTATE we need a system elf.h
- Drop duplicated parasite-syscall.h
- Organize headers in the way
- system headers
- asm headers
- regular headers
- protobuf stuff
Signed-off-by: Cyrill Gorcunov <gorcunov@openvz.org>
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>
This is the first release, that actually doesn't require a custom
kernel in order to make all the tool features to work. Just take
the v3.8 (with proper config) and that's it :)
Another coolness about this release is the ARM port. In this case,
however, one does require a custom kernel, since the kcmp system
call is not wired into the ARM table in the upstream kernel :(
What else? Quite a lot, actually:
* C/R ability of a LOT of new stuff
* Remote syscall execution
* Deprecation of --namespace option
* Build system rework
* Ability to collect gcov info
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>
The constant 4294967295 isn't replaced with 0xFFFFFFFF
in a generated source.
Signed-off-by: Alexander Kartashov <alekskartashov@parallels.com>
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>
Currently the mainstream-kernel tests list is equal to cr test list.
Signed-off-by: Andrew Vagin <avagin@openvz.org>
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>
In case if here is a fast cpu and make is done in parallel
we may have the following error
| GEN arch/x86/sys-exec-tbl.c
| GEN arch/x86/syscalls.S
| CC arch/x86/crtools.o
| CC arch/x86/cpu.o
| CC arch/x86/syscalls.o
| LINK arch/x86/syscalls.built-in.o
| In file included from include/restorer.h:12:0,
| from arch/x86/crtools.c:19:
| include/lock.h: In function ‘futex_set_and_wake’:
| include/lock.h:56:2: error: implicit declaration of function ‘sys_futex’ [-Werror=implicit-function-declaration]
| cc1: all warnings being treated as errors
| make[1]: *** [arch/x86/crtools.o] Error 1
| make: *** [arch/x86] Error 2
This is because crtools.c includes syscall.h but this header
is generated by a special script. So use $(deps-after) feature
provided by our make engine making sure the header is generated
before the deps are started to build.
Reported-by: Andrey Vagin <avagin@openvz.org>
Signed-off-by: Cyrill Gorcunov <gorcunov@openvz.org>
Tested-by: Andrew Vagin <avagin@parallels.com>
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>
Since we generate some headers the deps creation may
need to be ordered, thus add deps-after variable
for this case.
Signed-off-by: Cyrill Gorcunov <gorcunov@openvz.org>
Tested-by: Andrew Vagin <avagin@parallels.com>
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>
Some of ours headers (such as syscall.h) are
clashes with system headers names. So we need
to be sure that the headers we include as
| #include "something.h"
being searched in known place. In particular on
some machines it it already produced problems.
This btw revealved a problem in cr-dump.c -- we've
had #include <parasite.h> there. Fix it.
Signed-off-by: Cyrill Gorcunov <gorcunov@openvz.org>
Tested-by: Andrew Vagin <avagin@parallels.com>
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>
The FPU data is quite CPU-type oriented,
thus move it to asm/fpu.h.
Signed-off-by: Cyrill Gorcunov <gorcunov@openvz.org>
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>
No need to propagate special flags we use for syscalls library
to all arch specific objects. Make them syscalls local.
Signed-off-by: Cyrill Gorcunov <gorcunov@openvz.org>
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>
They are really depends on CPU we're running on.
Signed-off-by: Cyrill Gorcunov <gorcunov@openvz.org>
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>
This allows to reuse the code and make rebuild to work correctly.
Signed-off-by: Cyrill Gorcunov <gorcunov@openvz.org>
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>
I occasionally used assignments instead of
appending manpages for generation. Fix it.
Signed-off-by: Cyrill Gorcunov <gorcunov@openvz.org>
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>
This is a bit tricky since the build infrastructure
we're switching to is targeted to per-directory targets
if simplified Makefiles are used.
So I did the following
- move rules to compile general sources to Makefile.crtools
- main Makefiles now simply calls for scritps/Makefile.build
help to generate built-in.o target
Also note that we clean up suffixes for implicit rules with
.SUFFIXES:
this is done on purpose to eliminate any possible side effect
in future -- all rules _must_ be described explicitly.
Because of implicit rules used in zdtm building procedure
I can't use of stict makefile mode and add
MAKEFLAGS := -r
to the top of the general Makefile. This should be done
one day latter (if ever).
Signed-off-by: Cyrill Gorcunov <gorcunov@openvz.org>
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>
We're building project from toplevel directory so
no need for absolute paths.
Signed-off-by: Cyrill Gorcunov <gorcunov@openvz.org>
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>
Because we need util-net.c for both PIE code and
a regular code, just move it to pie/ directory
and build with -fpie option, this way we can reuse
compiled file in main program without additional
compilation pass.
Signed-off-by: Cyrill Gorcunov <gorcunov@openvz.org>
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>
This script is engine for simplified Makefiles.
I tried to make it somewhat close to what is used
to build linux kernel.
Signed-off-by: Cyrill Gorcunov <gorcunov@openvz.org>
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>
