glibc/sysdeps/unix/sysv/linux/tile/clone.S

195 lines
4.6 KiB
ArmAsm
Raw Normal View History

/* Copyright (C) 2011-2016 Free Software Foundation, Inc.
This file is part of the GNU C Library.
Contributed by Chris Metcalf <cmetcalf@tilera.com>, 2011.
The GNU C Library is free software; you can redistribute it and/or
modify it under the terms of the GNU Lesser General Public
License as published by the Free Software Foundation; either
version 2.1 of the License, or (at your option) any later version.
The GNU C Library is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
Lesser General Public License for more details.
You should have received a copy of the GNU Lesser General Public
2012-03-09 23:56:38 +00:00
License along with the GNU C Library. If not, see
<http://www.gnu.org/licenses/>. */
/* clone() is even more special than fork() as it mucks with stacks
and invokes a function in the right context after it's all over. */
#include <sysdep.h>
#define _ERRNO_H 1
#include <bits/errno.h>
#include <asm/unistd.h>
#include <arch/abi.h>
#include <tls.h>
#include <linux/sched.h>
/* What we save where in the stack frame; must include all callee-saves. */
#define FRAME_NEXT_LR (0 * REGSIZE) /* reserved by ABI; not used here */
#define FRAME_SP (1 * REGSIZE)
#define FRAME_R30 (2 * REGSIZE)
#define FRAME_R31 (3 * REGSIZE)
#define FRAME_R32 (4 * REGSIZE)
#define FRAME_SIZE (5 * REGSIZE)
/* int clone(int (*fn)(void *arg), void *child_stack, int flags, void *arg,
pid_t *ptid, struct user_desc *tls, pid_t *ctid); */
.text
ENTRY (__clone)
/* Create a stack frame so we can pass callee-saves to new task. */
{
move r10, sp
ST sp, lr
ADDI_PTR sp, sp, -FRAME_SIZE
}
cfi_offset (lr, 0)
cfi_def_cfa_offset (FRAME_SIZE)
ADDI_PTR r11, sp, FRAME_SP
{
ST r11, r10
ADDI_PTR r11, sp, FRAME_R30
}
{
ST r11, r30
ADDI_PTR r11, sp, FRAME_R31
}
cfi_offset (r30, FRAME_R30 - FRAME_SIZE)
{
ST r11, r31
ADDI_PTR r11, sp, FRAME_R32
}
cfi_offset (r31, FRAME_R31 - FRAME_SIZE)
ST r11, r32
cfi_offset (r32, FRAME_R32 - FRAME_SIZE)
/* sanity check arguments */
BEQZ r0, .Linvalid
BEQZ r1, .Linvalid
/* Make sure child stack is properly aligned, and set up the
top frame so that we can call out of it immediately in the
child. Setting it up here means we fault in the parent if
it's bogus, which is probably cleaner than faulting first
thing in the child. */
ADDI_PTR r1, r1, -C_ABI_SAVE_AREA_SIZE
andi r1, r1, -C_ABI_SAVE_AREA_SIZE
ADDI_PTR r9, r1, REGSIZE /* sp of this frame on entry, i.e. zero */
ST r9, zero
/* We need to switch the argument convention around from
libc to kernel:
2013-06-05 20:26:40 +00:00
libc:
r0 fn
r1 child_stack
r2 flags
r3 arg
r4 ptid
r5 tls
r6 ctid
2013-06-05 20:26:40 +00:00
kernel:
r0 flags
r1 child_stack [same as libc]
r2 ptid
r3 ctid
r4 tls
2013-06-05 20:26:40 +00:00
Plus the callee-saves as described at .Lthread_start, below. */
{
move r32, r0
move r0, r2
}
{
move r31, r3
move r3, r6
}
{
move r30, r2
move r2, r4
}
{
move r4, r5
moveli TREG_SYSCALL_NR_NAME, __NR_clone
}
swint1
BEQZ r0, .Lthread_start /* If in child task. */
.Ldone:
/* Restore the callee-saved registers and return. */
ADDLI_PTR lr, sp, FRAME_SIZE
{
LD lr, lr
ADDLI_PTR r30, sp, FRAME_R30
}
{
LD r30, r30
ADDLI_PTR r31, sp, FRAME_R31
}
{
LD r31, r31
ADDLI_PTR r32, sp, FRAME_R32
}
{
LD r32, r32
ADDI_PTR sp, sp, FRAME_SIZE
}
cfi_def_cfa_offset (0)
BNEZ r1, .Lerror
jrp lr
.Lerror:
j SYSCALL_ERROR_NAME
.Linvalid:
{
movei r1, EINVAL
j .Ldone
}
2013-06-05 20:26:40 +00:00
/* This function expects to receive:
2013-06-05 20:26:40 +00:00
sp: the top of a valid stack area
r30: clone() flags
r31: the argument to pass to the user function
r32: the user function pointer */
.Lthread_start:
cfi_def_cfa_offset (FRAME_SIZE)
cfi_undefined (lr)
/* Check and see if we need to reset the PID, which we do if
Fix clone (CLONE_VM) pid/tid reset (BZ#19957) As discussed in libc-alpha [1] current clone with CLONE_VM (without CLONE_THREAD set) will reset the pthread pid/tid fields to -1. The issue is since memory is shared between the parent and child it will clobber parent's cached pid/tid leading to internal inconsistencies if the value is not restored. And even it is restored it may lead to racy conditions when between set/restore a thread might invoke pthread function that validate the pthread with INVALID_TD_P/INVALID_NOT_TERMINATED_TD_P and thus get wrong results. As stated in BZ19957, previously reports of this behaviour was close with EWONTFIX due the fact usage of clone outside glibc is tricky since glibc requires consistent internal pthread, while using clone directly may not provide it. However since now posix_spawn uses clone (CLONE_VM) to fixes various issues related to previous vfork usage this issue requires fixing. The vfork implementation also does something similar, but instead it negates and restores only the *pid* field and functions that might access its value know to handle such case (getpid, raise and pthread ones that uses INVALID_TD_P/INVALID_NOT_TERMINATED_TD_P macros that check only *tid* field). Also vfork does not call __clone directly, instead calling either __NR_vfork or __NR_clone directly. So this patch removes this clone behavior by avoiding setting the pthread pid/tid field for CLONE_VM. There is no need to check for CLONE_THREAD, since the minimum supported kernel in all architecture implies that CLONE_VM must be used with CLONE_THREAD, otherwise clone returns EINVAL. Instead of current approach of: int clone(int (*fn)(void *), void *child_stack, int flags, ...) [...] if (flags & CLONE_THREAD) goto do_syscall; pid_t new_value; if (flags & CLONE_VM) new_value = -1; else new_value = getpid (); THREAD_SETMEM (THREAD_SELF, pid, new_value); THREAD_SETMEM (THREAD_SELF, tid, new_value); do_syscall: [...] The new approach uses: int clone(int (*fn)(void *), void *child_stack, int flags, ...) [...] if (flags & CLONE_VM) goto do_syscall; pid_t new_value = getpid (); THREAD_SETMEM (THREAD_SELF, pid, new_value); THREAD_SETMEM (THREAD_SELF, tid, new_value); do_syscall: [...] It also removes the linux tst-getpid2.c test which expects the previous behavior and instead add another clone test. Tested on x86_64, i686, x32, powerpc64le, aarch64, armhf, s390, and s390x. I also did limited check on mips32 and sparc64 (using the new added test). I also got reviews from both m68k, hppa, and tile. So I presume for these architecture the patch works. The fixes for alpha, microblaze, sh, ia64, and nio2 have not been tested. [1] https://sourceware.org/ml/libc-alpha/2016-04/msg00307.html * sysdeps/unix/sysv/linux/Makefile [$(subdir) == nptl] (test): Remove tst-getpid2. (test): Add tst-clone2. * sysdeps/unix/sysv/linux/tst-clone2.c: New file. * sysdeps/unix/sysv/linux/aarch64/clone.S (__clone): Do not change pid/tid fields for CLONE_VM. * sysdeps/unix/sysv/linux/arm/clone.S: Likewise. * sysdeps/unix/sysv/linux/i386/clone.S: Likewise. * sysdeps/unix/sysv/linux/mips/clone.S: Likewise. * sysdeps/unix/sysv/linux/powerpc/powerpc32/clone.S: Likewise. * sysdeps/unix/sysv/linux/powerpc/powerpc64/clone.S: Likewise. * sysdeps/unix/sysv/linux/s390/s390-32/clone.S: Likewise. * sysdeps/unix/sysv/linux/s390/s390-64/clone.S: Likewise. * sysdeps/unix/sysv/linux/sparc/sparc32/clone.S: Likewise. * sysdeps/unix/sysv/linux/sparc/sparc64/clone.S: Likewise. * sysdeps/unix/sysv/linux/x86_64/clone.S: Likewise. * sysdeps/unix/sysv/linux/tst-getpid2.c: Remove file.
2016-04-15 19:42:38 +00:00
CLONE_VM isn't set, i.e. it's a fork-like clone with a new
address space. In that case we update the cached values
from the true system pid (retrieved via __NR_getpid syscall). */
Fix clone (CLONE_VM) pid/tid reset (BZ#19957) As discussed in libc-alpha [1] current clone with CLONE_VM (without CLONE_THREAD set) will reset the pthread pid/tid fields to -1. The issue is since memory is shared between the parent and child it will clobber parent's cached pid/tid leading to internal inconsistencies if the value is not restored. And even it is restored it may lead to racy conditions when between set/restore a thread might invoke pthread function that validate the pthread with INVALID_TD_P/INVALID_NOT_TERMINATED_TD_P and thus get wrong results. As stated in BZ19957, previously reports of this behaviour was close with EWONTFIX due the fact usage of clone outside glibc is tricky since glibc requires consistent internal pthread, while using clone directly may not provide it. However since now posix_spawn uses clone (CLONE_VM) to fixes various issues related to previous vfork usage this issue requires fixing. The vfork implementation also does something similar, but instead it negates and restores only the *pid* field and functions that might access its value know to handle such case (getpid, raise and pthread ones that uses INVALID_TD_P/INVALID_NOT_TERMINATED_TD_P macros that check only *tid* field). Also vfork does not call __clone directly, instead calling either __NR_vfork or __NR_clone directly. So this patch removes this clone behavior by avoiding setting the pthread pid/tid field for CLONE_VM. There is no need to check for CLONE_THREAD, since the minimum supported kernel in all architecture implies that CLONE_VM must be used with CLONE_THREAD, otherwise clone returns EINVAL. Instead of current approach of: int clone(int (*fn)(void *), void *child_stack, int flags, ...) [...] if (flags & CLONE_THREAD) goto do_syscall; pid_t new_value; if (flags & CLONE_VM) new_value = -1; else new_value = getpid (); THREAD_SETMEM (THREAD_SELF, pid, new_value); THREAD_SETMEM (THREAD_SELF, tid, new_value); do_syscall: [...] The new approach uses: int clone(int (*fn)(void *), void *child_stack, int flags, ...) [...] if (flags & CLONE_VM) goto do_syscall; pid_t new_value = getpid (); THREAD_SETMEM (THREAD_SELF, pid, new_value); THREAD_SETMEM (THREAD_SELF, tid, new_value); do_syscall: [...] It also removes the linux tst-getpid2.c test which expects the previous behavior and instead add another clone test. Tested on x86_64, i686, x32, powerpc64le, aarch64, armhf, s390, and s390x. I also did limited check on mips32 and sparc64 (using the new added test). I also got reviews from both m68k, hppa, and tile. So I presume for these architecture the patch works. The fixes for alpha, microblaze, sh, ia64, and nio2 have not been tested. [1] https://sourceware.org/ml/libc-alpha/2016-04/msg00307.html * sysdeps/unix/sysv/linux/Makefile [$(subdir) == nptl] (test): Remove tst-getpid2. (test): Add tst-clone2. * sysdeps/unix/sysv/linux/tst-clone2.c: New file. * sysdeps/unix/sysv/linux/aarch64/clone.S (__clone): Do not change pid/tid fields for CLONE_VM. * sysdeps/unix/sysv/linux/arm/clone.S: Likewise. * sysdeps/unix/sysv/linux/i386/clone.S: Likewise. * sysdeps/unix/sysv/linux/mips/clone.S: Likewise. * sysdeps/unix/sysv/linux/powerpc/powerpc32/clone.S: Likewise. * sysdeps/unix/sysv/linux/powerpc/powerpc64/clone.S: Likewise. * sysdeps/unix/sysv/linux/s390/s390-32/clone.S: Likewise. * sysdeps/unix/sysv/linux/s390/s390-64/clone.S: Likewise. * sysdeps/unix/sysv/linux/sparc/sparc32/clone.S: Likewise. * sysdeps/unix/sysv/linux/sparc/sparc64/clone.S: Likewise. * sysdeps/unix/sysv/linux/x86_64/clone.S: Likewise. * sysdeps/unix/sysv/linux/tst-getpid2.c: Remove file.
2016-04-15 19:42:38 +00:00
moveli r0, CLONE_VM
and r0, r30, r0
BNEZ r0, .Lno_reset_pid /* CLONE_VM is set */
moveli TREG_SYSCALL_NR_NAME, __NR_getpid
swint1
ADDLI_PTR r2, tp, PID_OFFSET
{
ST4 r2, r0
ADDLI_PTR r2, tp, TID_OFFSET
}
ST4 r2, r0
.Lno_reset_pid:
{
/* Invoke user function with specified argument. */
move r0, r31
jalr r32
}
{
j HIDDEN_JUMPTARGET(_exit)
info INFO_OP_CANNOT_BACKTRACE /* Notify backtracer to stop. */
}
PSEUDO_END (__clone)
posix: New Linux posix_spawn{p} implementation This patch implements a new posix_spawn{p} implementation for Linux. The main difference is it uses the clone syscall directly with CLONE_VM and CLONE_VFORK flags and a direct allocated stack. The new stack and start function solves most the vfork limitation (possible parent clobber due stack spilling). The remaning issue are related to signal handling: 1. That no signal handlers must run in child context, to avoid corrupt parent's state. 2. Child must synchronize with parent to enforce stack deallocation and to possible return execv issues. The first one is solved by blocking all signals in child, even NPTL-internal ones (SIGCANCEL and SIGSETXID). The second issue is done by a stack allocation in parent and a synchronization with using a pipe or waitpid (in case or error). The pipe has the advantage of allowing the child signal an exec error (checked with new tst-spawn2 test). There is an inherent race condition in pipe2 usage for architectures that do not support the syscall directly. In such cases the a pipe plus fctnl is used instead and it may lead to file descriptor leak in parent (as decribed by fcntl documentation). The child process stack is allocate with a mmap with MAP_STACK flag using default architecture stack size. Although it is slower than use a stack buffer from parent, it allows some slack for the compatibility code to run scripts with no shebang (which may use a buffer with size depending of argument list count). Performance should be similar to the vfork default posix implementation and way faster than fork path (vfork on mostly linux ports are basically clone with CLONE_VM plus CLONE_VFORK). The only difference is the syscalls required for the stack allocation/deallocation. It fixes BZ#10354, BZ#14750, and BZ#18433. Tested on i386, x86_64, powerpc64le, and aarch64. [BZ #14750] [BZ #10354] [BZ #18433] * include/sched.h (__clone): Add hidden prototype. (__clone2): Likewise. * include/unistd.h (__dup): Likewise. * posix/Makefile (tests): Add tst-spawn2. * posix/tst-spawn2.c: New file. * sysdeps/posix/dup.c (__dup): Add hidden definition. * sysdeps/unix/sysv/linux/aarch64/clone.S (__clone): Likewise. * sysdeps/unix/sysv/linux/alpha/clone.S (__clone): Likewise. * sysdeps/unix/sysv/linux/arm/clone.S (__clone): Likewise. * sysdeps/unix/sysv/linux/hppa/clone.S (__clone): Likewise. * sysdeps/unix/sysv/linux/i386/clone.S (__clone): Likewise. * sysdeps/unix/sysv/linux/ia64/clone2.S (__clone): Likewise. * sysdeps/unix/sysv/linux/m68k/clone.S (__clone): Likewise. * sysdeps/unix/sysv/linux/microblaze/clone.S (__clone): Likewise. * sysdeps/unix/sysv/linux/mips/clone.S (__clone): Likewise. * sysdeps/unix/sysv/linux/nios2/clone.S (__clone): Likewise. * sysdeps/unix/sysv/linux/powerpc/powerpc32/clone.S (__clone): Likewise. * sysdeps/unix/sysv/linux/powerpc/powerpc64/clone.S (__clone): Likewise. * sysdeps/unix/sysv/linux/s390/s390-32/clone.S (__clone): Likewise. * sysdeps/unix/sysv/linux/s390/s390-64/clone.S (__clone): Likewise. * sysdeps/unix/sysv/linux/sh/clone.S (__clone): Likewise. * sysdeps/unix/sysv/linux/sparc/sparc32/clone.S (__clone): Likewise. * sysdeps/unix/sysv/linux/sparc/sparc64/clone.S (__clone): Likewise. * sysdeps/unix/sysv/linux/tile/clone.S (__clone): Likewise. * sysdeps/unix/sysv/linux/x86_64/clone.S (__clone): Likewise. * sysdeps/unix/sysv/linux/nptl-signals.h (____nptl_is_internal_signal): New function. * sysdeps/unix/sysv/linux/spawni.c: New file.
2016-01-19 19:33:32 +00:00
libc_hidden_def (__clone)
weak_alias (__clone, clone)