linux_dsm_epyc7002/arch/tile/mm/elf.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

159 lines
3.9 KiB
C

/*
* Copyright 2010 Tilera Corporation. All Rights Reserved.
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation, version 2.
*
* This program 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, GOOD TITLE or
* NON INFRINGEMENT. See the GNU General Public License for
* more details.
*/
#include <linux/mm.h>
#include <linux/pagemap.h>
#include <linux/binfmts.h>
#include <linux/compat.h>
#include <linux/mman.h>
#include <linux/elf.h>
#include <asm/pgtable.h>
#include <asm/pgalloc.h>
#include <asm/sections.h>
/* Notify a running simulator, if any, that an exec just occurred. */
static void sim_notify_exec(const char *binary_name)
{
unsigned char c;
do {
c = *binary_name++;
__insn_mtspr(SPR_SIM_CONTROL,
(SIM_CONTROL_OS_EXEC
| (c << _SIM_CONTROL_OPERATOR_BITS)));
} while (c);
}
static int notify_exec(void)
{
int retval = 0; /* failure */
struct vm_area_struct *vma = current->mm->mmap;
while (vma) {
if ((vma->vm_flags & VM_EXECUTABLE) && vma->vm_file)
break;
vma = vma->vm_next;
}
if (vma) {
char *buf = (char *) __get_free_page(GFP_KERNEL);
if (buf) {
char *path = d_path(&vma->vm_file->f_path,
buf, PAGE_SIZE);
if (!IS_ERR(path)) {
sim_notify_exec(path);
retval = 1;
}
free_page((unsigned long)buf);
}
}
return retval;
}
/* Notify a running simulator, if any, that we loaded an interpreter. */
static void sim_notify_interp(unsigned long load_addr)
{
size_t i;
for (i = 0; i < sizeof(load_addr); i++) {
unsigned char c = load_addr >> (i * 8);
__insn_mtspr(SPR_SIM_CONTROL,
(SIM_CONTROL_OS_INTERP
| (c << _SIM_CONTROL_OPERATOR_BITS)));
}
}
/* Kernel address of page used to map read-only kernel data into userspace. */
static void *vdso_page;
/* One-entry array used for install_special_mapping. */
static struct page *vdso_pages[1];
static int __init vdso_setup(void)
{
vdso_page = (void *)get_zeroed_page(GFP_ATOMIC);
memcpy(vdso_page, __rt_sigreturn, __rt_sigreturn_end - __rt_sigreturn);
vdso_pages[0] = virt_to_page(vdso_page);
return 0;
}
device_initcall(vdso_setup);
const char *arch_vma_name(struct vm_area_struct *vma)
{
if (vma->vm_private_data == vdso_pages)
return "[vdso]";
#ifndef __tilegx__
if (vma->vm_start == MEM_USER_INTRPT)
return "[intrpt]";
#endif
return NULL;
}
int arch_setup_additional_pages(struct linux_binprm *bprm,
int executable_stack)
{
struct mm_struct *mm = current->mm;
unsigned long vdso_base;
int retval = 0;
/*
* Notify the simulator that an exec just occurred.
* If we can't find the filename of the mapping, just use
* whatever was passed as the linux_binprm filename.
*/
if (!notify_exec())
sim_notify_exec(bprm->filename);
down_write(&mm->mmap_sem);
/*
* MAYWRITE to allow gdb to COW and set breakpoints
*/
vdso_base = VDSO_BASE;
retval = install_special_mapping(mm, vdso_base, PAGE_SIZE,
VM_READ|VM_EXEC|
VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC,
vdso_pages);
#ifndef __tilegx__
/*
* Set up a user-interrupt mapping here; the user can't
* create one themselves since it is above TASK_SIZE.
* We make it unwritable by default, so the model for adding
* interrupt vectors always involves an mprotect.
*/
if (!retval) {
unsigned long addr = MEM_USER_INTRPT;
addr = mmap_region(NULL, addr, INTRPT_SIZE,
MAP_FIXED|MAP_ANONYMOUS|MAP_PRIVATE,
VM_READ|VM_EXEC|
VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC, 0);
if (addr > (unsigned long) -PAGE_SIZE)
retval = (int) addr;
}
#endif
up_write(&mm->mmap_sem);
return retval;
}
void elf_plat_init(struct pt_regs *regs, unsigned long load_addr)
{
/* Zero all registers. */
memset(regs, 0, sizeof(*regs));
/* Report the interpreter's load address. */
sim_notify_interp(load_addr);
}