linux/arch/mips/kernel/vdso.c
Jason Baron 909af768e8 coredump: remove VM_ALWAYSDUMP flag
The motivation for this patchset was that I was looking at a way for a
qemu-kvm process, to exclude the guest memory from its core dump, which
can be quite large.  There are already a number of filter flags in
/proc/<pid>/coredump_filter, however, these allow one to specify 'types'
of kernel memory, not specific address ranges (which is needed in this
case).

Since there are no more vma flags available, the first patch eliminates
the need for the 'VM_ALWAYSDUMP' flag.  The flag is used internally by
the kernel to mark vdso and vsyscall pages.  However, it is simple
enough to check if a vma covers a vdso or vsyscall page without the need
for this flag.

The second patch then replaces the 'VM_ALWAYSDUMP' flag with a new
'VM_NODUMP' flag, which can be set by userspace using new madvise flags:
'MADV_DONTDUMP', and unset via 'MADV_DODUMP'.  The core dump filters
continue to work the same as before unless 'MADV_DONTDUMP' is set on the
region.

The qemu code which implements this features is at:

  http://people.redhat.com/~jbaron/qemu-dump/qemu-dump.patch

In my testing the qemu core dump shrunk from 383MB -> 13MB with this
patch.

I also believe that the 'MADV_DONTDUMP' flag might be useful for
security sensitive apps, which might want to select which areas are
dumped.

This patch:

The VM_ALWAYSDUMP flag is currently used by the coredump code to
indicate that a vma is part of a vsyscall or vdso section.  However, we
can determine if a vma is in one these sections by checking it against
the gate_vma and checking for a non-NULL return value from
arch_vma_name().  Thus, freeing a valuable vma bit.

Signed-off-by: Jason Baron <jbaron@redhat.com>
Acked-by: Roland McGrath <roland@hack.frob.com>
Cc: Chris Metcalf <cmetcalf@tilera.com>
Cc: Avi Kivity <avi@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-03-23 16:58:42 -07:00

109 lines
2.4 KiB
C

/*
* This file is subject to the terms and conditions of the GNU General Public
* License. See the file "COPYING" in the main directory of this archive
* for more details.
*
* Copyright (C) 2009, 2010 Cavium Networks, Inc.
*/
#include <linux/kernel.h>
#include <linux/err.h>
#include <linux/sched.h>
#include <linux/mm.h>
#include <linux/init.h>
#include <linux/binfmts.h>
#include <linux/elf.h>
#include <linux/vmalloc.h>
#include <linux/unistd.h>
#include <asm/vdso.h>
#include <asm/uasm.h>
/*
* Including <asm/unistd.h> would give use the 64-bit syscall numbers ...
*/
#define __NR_O32_sigreturn 4119
#define __NR_O32_rt_sigreturn 4193
#define __NR_N32_rt_sigreturn 6211
static struct page *vdso_page;
static void __init install_trampoline(u32 *tramp, unsigned int sigreturn)
{
uasm_i_addiu(&tramp, 2, 0, sigreturn); /* li v0, sigreturn */
uasm_i_syscall(&tramp, 0);
}
static int __init init_vdso(void)
{
struct mips_vdso *vdso;
vdso_page = alloc_page(GFP_KERNEL);
if (!vdso_page)
panic("Cannot allocate vdso");
vdso = vmap(&vdso_page, 1, 0, PAGE_KERNEL);
if (!vdso)
panic("Cannot map vdso");
clear_page(vdso);
install_trampoline(vdso->rt_signal_trampoline, __NR_rt_sigreturn);
#ifdef CONFIG_32BIT
install_trampoline(vdso->signal_trampoline, __NR_sigreturn);
#else
install_trampoline(vdso->n32_rt_signal_trampoline,
__NR_N32_rt_sigreturn);
install_trampoline(vdso->o32_signal_trampoline, __NR_O32_sigreturn);
install_trampoline(vdso->o32_rt_signal_trampoline,
__NR_O32_rt_sigreturn);
#endif
vunmap(vdso);
return 0;
}
subsys_initcall(init_vdso);
static unsigned long vdso_addr(unsigned long start)
{
return STACK_TOP;
}
int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
{
int ret;
unsigned long addr;
struct mm_struct *mm = current->mm;
down_write(&mm->mmap_sem);
addr = vdso_addr(mm->start_stack);
addr = get_unmapped_area(NULL, addr, PAGE_SIZE, 0, 0);
if (IS_ERR_VALUE(addr)) {
ret = addr;
goto up_fail;
}
ret = install_special_mapping(mm, addr, PAGE_SIZE,
VM_READ|VM_EXEC|
VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC,
&vdso_page);
if (ret)
goto up_fail;
mm->context.vdso = (void *)addr;
up_fail:
up_write(&mm->mmap_sem);
return ret;
}
const char *arch_vma_name(struct vm_area_struct *vma)
{
if (vma->vm_mm && vma->vm_start == (long)vma->vm_mm->context.vdso)
return "[vdso]";
return NULL;
}