mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-28 11:18:45 +07:00
909af768e8
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>
110 lines
2.4 KiB
C
110 lines
2.4 KiB
C
/*
|
|
* arch/sh/kernel/vsyscall/vsyscall.c
|
|
*
|
|
* Copyright (C) 2006 Paul Mundt
|
|
*
|
|
* vDSO randomization
|
|
* Copyright(C) 2005-2006, Red Hat, Inc., Ingo Molnar
|
|
*
|
|
* 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.
|
|
*/
|
|
#include <linux/mm.h>
|
|
#include <linux/kernel.h>
|
|
#include <linux/init.h>
|
|
#include <linux/gfp.h>
|
|
#include <linux/module.h>
|
|
#include <linux/elf.h>
|
|
#include <linux/sched.h>
|
|
#include <linux/err.h>
|
|
|
|
/*
|
|
* Should the kernel map a VDSO page into processes and pass its
|
|
* address down to glibc upon exec()?
|
|
*/
|
|
unsigned int __read_mostly vdso_enabled = 1;
|
|
EXPORT_SYMBOL_GPL(vdso_enabled);
|
|
|
|
static int __init vdso_setup(char *s)
|
|
{
|
|
vdso_enabled = simple_strtoul(s, NULL, 0);
|
|
return 1;
|
|
}
|
|
__setup("vdso=", vdso_setup);
|
|
|
|
/*
|
|
* These symbols are defined by vsyscall.o to mark the bounds
|
|
* of the ELF DSO images included therein.
|
|
*/
|
|
extern const char vsyscall_trapa_start, vsyscall_trapa_end;
|
|
static struct page *syscall_pages[1];
|
|
|
|
int __init vsyscall_init(void)
|
|
{
|
|
void *syscall_page = (void *)get_zeroed_page(GFP_ATOMIC);
|
|
syscall_pages[0] = virt_to_page(syscall_page);
|
|
|
|
/*
|
|
* XXX: Map this page to a fixmap entry if we get around
|
|
* to adding the page to ELF core dumps
|
|
*/
|
|
|
|
memcpy(syscall_page,
|
|
&vsyscall_trapa_start,
|
|
&vsyscall_trapa_end - &vsyscall_trapa_start);
|
|
|
|
return 0;
|
|
}
|
|
|
|
/* Setup a VMA at program startup for the vsyscall page */
|
|
int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
|
|
{
|
|
struct mm_struct *mm = current->mm;
|
|
unsigned long addr;
|
|
int ret;
|
|
|
|
down_write(&mm->mmap_sem);
|
|
addr = get_unmapped_area(NULL, 0, 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,
|
|
syscall_pages);
|
|
if (unlikely(ret))
|
|
goto up_fail;
|
|
|
|
current->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;
|
|
}
|
|
|
|
struct vm_area_struct *get_gate_vma(struct mm_struct *mm)
|
|
{
|
|
return NULL;
|
|
}
|
|
|
|
int in_gate_area(struct mm_struct *mm, unsigned long address)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
int in_gate_area_no_mm(unsigned long address)
|
|
{
|
|
return 0;
|
|
}
|