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>
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>
CFLAGS can be overriden, we need own flags here.
Signed-off-by: Cyrill Gorcunov <gorcunov@openvz.org>
Tested-by: Alexander Kartashov <alekskartashov@parallels.com>
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>
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 $(deps-after) feature
provided by our make engine making sure the header is generated
before the deps are started to build.
Reported-by: Andrey Vagin <avagin@openvz.org>
Signed-off-by: Cyrill Gorcunov <gorcunov@openvz.org>
Tested-by: Andrew Vagin <avagin@parallels.com>
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>
The FPU data is quite CPU-type oriented,
thus move it to asm/fpu.h.
Signed-off-by: Cyrill Gorcunov <gorcunov@openvz.org>
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>
No need to propagate special flags we use for syscalls library
to all arch specific objects. Make them syscalls local.
Signed-off-by: Cyrill Gorcunov <gorcunov@openvz.org>
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>
They are really depends on CPU we're running on.
Signed-off-by: Cyrill Gorcunov <gorcunov@openvz.org>
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>
No need to walk up the directories if we need
to include protobuf file. This was always a bad
use of ability to walk the filesystem from other
headers.
Same time we don't need -I$(SRC_DIR)/protobuf/
in general makefile anymore.
[xemul: Small fixlet in head Makefile, since patch
it out-of-order]
Signed-off-by: Cyrill Gorcunov <gorcunov@openvz.org>
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>
It's been reported that we do not test if the tracee is 32bit
task running kn 64bit kernel. This patch adds such test.
https://bugzilla.openvz.org/show_bug.cgi?id=2505
Signed-off-by: Cyrill Gorcunov <gorcunov@openvz.org>
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>
We do check for proper architectrue in a makefile,
no need for additional guards.
After all porting the project for x86-32 is a far more
bigger than "just implement proper core for parts covered
by #else /* CONFIG_X86_64 */".
Signed-off-by: Cyrill Gorcunov <gorcunov@openvz.org>
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>
These functions are designated to convert a native pointer
to uint64_t used to store a virtual address in protobuf messages
and vice versa in a machine-independent way.
Signed-off-by: Alexander Kartashov <alekskartashov@parallels.com>
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>
The macro specifies the size of the machine pointer explicitly.
Signed-off-by: Alexander Kartashov <alekskartashov@parallels.com>
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>
The layout of the struct rlimit depends on the value
of the macro FILE_OFFSET_BITS. If FILE_OFFSET_BITS is 64
the userspace and kernel definitions becomes incoherent
on a 32-bit platform.
The struct krlimit representing the kernel version of
the struct rlimit is introduced to address the issue:
the function restore_rlims() is fixed to convert between
the userspace and kernel representations of the struct.
Signed-off-by: Alexander Kartashov <alekskartashov@parallels.com>
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>
This makes it possible to use TASK_SIZE instead of TASK_SIZE_MAX.
Signed-off-by: Alexander Kartashov <alekskartashov@parallels.com>
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>
This is the merge and a slight rework (no TI_SP macro) of Alexander's patches
about the subj.
Signed-off-by: Alexander Kartashov <alekskartashov@parallels.com>
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>
The macro is designated to tune the beginning of a sigframe on different architectures.
Signed-off-by: Alexander Kartashov <alekskartashov@parallels.com>
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>
The macro REG_RES is to be used to access the syscall return value register
in the struct user_regs_struct_t.
The macro REG_IP is to be used to access the program counter register
in the struct user_regs_struct_t.
Signed-off-by: Alexander Kartashov <alekskartashov@parallels.com>
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>
The macro is introduced to abstract from behavior of breakpoints:
they generate different values of the field siginfo.si_code on different architectures.
Signed-off-by: Alexander Kartashov <alekskartashov@parallels.com>
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>
Dump the with "new" prlimit syscall that works on arbitrary pid.
Restore is done in restorer _after_ mappings mixup and _before_
caps drop to make it set any max value.
The RLIM_INFINITY is handled explicitly to help future 64<->32
bits migration.
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>
* The routine sigreturn_prep_xsave_frame() is renamed to sigreturn_prep_fpu_frame().
* Moved the routines sigreturn_prep_fpu_frame(), show_rt_xsave_frame(), and
valid_xsave_frame() to the file crtools.c.
* Introduced the structure fpu_state_t to pass the FPU state to the restorer
in a machine-independent way.
Signed-off-by: Alexander Kartashov <alekskartashov@parallels.com>
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>
The size of an auxv is the machine pointer but a 64-bit integer is reserved
in a MmEntry protobuf message to store an auxv. Moreover the number of auxv's
varies from one architecture to another. So the following is proposed
to alleviate the issue.
* Introduced the type auxv_t representing a machine-pointer sized integer.
* The size of auxv array is extracted from a MmEntry message instead of using
the value of the macro AT_VECTOR_SIZE.
Signed-off-by: Alexander Kartashov <alekskartashov@parallels.com>
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>
