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>
144 lines
3.5 KiB
C
144 lines
3.5 KiB
C
/*
|
|
* Set up the VMAs to tell the VM about the vDSO.
|
|
* Copyright 2007 Andi Kleen, SUSE Labs.
|
|
* Subject to the GPL, v.2
|
|
*/
|
|
#include <linux/mm.h>
|
|
#include <linux/err.h>
|
|
#include <linux/sched.h>
|
|
#include <linux/slab.h>
|
|
#include <linux/init.h>
|
|
#include <linux/random.h>
|
|
#include <linux/elf.h>
|
|
#include <asm/vsyscall.h>
|
|
#include <asm/vgtod.h>
|
|
#include <asm/proto.h>
|
|
#include <asm/vdso.h>
|
|
#include <asm/page.h>
|
|
|
|
unsigned int __read_mostly vdso_enabled = 1;
|
|
|
|
extern char vdso_start[], vdso_end[];
|
|
extern unsigned short vdso_sync_cpuid;
|
|
|
|
extern struct page *vdso_pages[];
|
|
static unsigned vdso_size;
|
|
|
|
static void __init patch_vdso(void *vdso, size_t len)
|
|
{
|
|
Elf64_Ehdr *hdr = vdso;
|
|
Elf64_Shdr *sechdrs, *alt_sec = 0;
|
|
char *secstrings;
|
|
void *alt_data;
|
|
int i;
|
|
|
|
BUG_ON(len < sizeof(Elf64_Ehdr));
|
|
BUG_ON(memcmp(hdr->e_ident, ELFMAG, SELFMAG) != 0);
|
|
|
|
sechdrs = (void *)hdr + hdr->e_shoff;
|
|
secstrings = (void *)hdr + sechdrs[hdr->e_shstrndx].sh_offset;
|
|
|
|
for (i = 1; i < hdr->e_shnum; i++) {
|
|
Elf64_Shdr *shdr = &sechdrs[i];
|
|
if (!strcmp(secstrings + shdr->sh_name, ".altinstructions")) {
|
|
alt_sec = shdr;
|
|
goto found;
|
|
}
|
|
}
|
|
|
|
/* If we get here, it's probably a bug. */
|
|
pr_warning("patch_vdso: .altinstructions not found\n");
|
|
return; /* nothing to patch */
|
|
|
|
found:
|
|
alt_data = (void *)hdr + alt_sec->sh_offset;
|
|
apply_alternatives(alt_data, alt_data + alt_sec->sh_size);
|
|
}
|
|
|
|
static int __init init_vdso(void)
|
|
{
|
|
int npages = (vdso_end - vdso_start + PAGE_SIZE - 1) / PAGE_SIZE;
|
|
int i;
|
|
|
|
patch_vdso(vdso_start, vdso_end - vdso_start);
|
|
|
|
vdso_size = npages << PAGE_SHIFT;
|
|
for (i = 0; i < npages; i++)
|
|
vdso_pages[i] = virt_to_page(vdso_start + i*PAGE_SIZE);
|
|
|
|
return 0;
|
|
}
|
|
subsys_initcall(init_vdso);
|
|
|
|
struct linux_binprm;
|
|
|
|
/* Put the vdso above the (randomized) stack with another randomized offset.
|
|
This way there is no hole in the middle of address space.
|
|
To save memory make sure it is still in the same PTE as the stack top.
|
|
This doesn't give that many random bits */
|
|
static unsigned long vdso_addr(unsigned long start, unsigned len)
|
|
{
|
|
unsigned long addr, end;
|
|
unsigned offset;
|
|
end = (start + PMD_SIZE - 1) & PMD_MASK;
|
|
if (end >= TASK_SIZE_MAX)
|
|
end = TASK_SIZE_MAX;
|
|
end -= len;
|
|
/* This loses some more bits than a modulo, but is cheaper */
|
|
offset = get_random_int() & (PTRS_PER_PTE - 1);
|
|
addr = start + (offset << PAGE_SHIFT);
|
|
if (addr >= end)
|
|
addr = end;
|
|
|
|
/*
|
|
* page-align it here so that get_unmapped_area doesn't
|
|
* align it wrongfully again to the next page. addr can come in 4K
|
|
* unaligned here as a result of stack start randomization.
|
|
*/
|
|
addr = PAGE_ALIGN(addr);
|
|
addr = align_addr(addr, NULL, ALIGN_VDSO);
|
|
|
|
return addr;
|
|
}
|
|
|
|
/* Setup a VMA at program startup for the vsyscall page.
|
|
Not called for compat tasks */
|
|
int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
|
|
{
|
|
struct mm_struct *mm = current->mm;
|
|
unsigned long addr;
|
|
int ret;
|
|
|
|
if (!vdso_enabled)
|
|
return 0;
|
|
|
|
down_write(&mm->mmap_sem);
|
|
addr = vdso_addr(mm->start_stack, vdso_size);
|
|
addr = get_unmapped_area(NULL, addr, vdso_size, 0, 0);
|
|
if (IS_ERR_VALUE(addr)) {
|
|
ret = addr;
|
|
goto up_fail;
|
|
}
|
|
|
|
current->mm->context.vdso = (void *)addr;
|
|
|
|
ret = install_special_mapping(mm, addr, vdso_size,
|
|
VM_READ|VM_EXEC|
|
|
VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC,
|
|
vdso_pages);
|
|
if (ret) {
|
|
current->mm->context.vdso = NULL;
|
|
goto up_fail;
|
|
}
|
|
|
|
up_fail:
|
|
up_write(&mm->mmap_sem);
|
|
return ret;
|
|
}
|
|
|
|
static __init int vdso_setup(char *s)
|
|
{
|
|
vdso_enabled = simple_strtoul(s, NULL, 0);
|
|
return 0;
|
|
}
|
|
__setup("vdso=", vdso_setup);
|