mm: pagewalk: Fix race between unmap and page walker
The mmap lock protects the page walker from changes to the page tables
during the walk. However a read lock is insufficient to protect those
areas which don't have a VMA as munmap() detaches the VMAs before
downgrading to a read lock and actually tearing down PTEs/page tables.
For users of walk_page_range() the solution is to simply call pte_hole()
immediately without checking the actual page tables when a VMA is not
present. We now never call __walk_page_range() without a valid vma.
For walk_page_range_novma() the locking requirements are tightened to
require the mmap write lock to be taken, and then walking the pgd
directly with 'no_vma' set.
This in turn means that all page walkers either have a valid vma, or
it's that special 'novma' case for page table debugging. As a result,
all the odd '(!walk->vma && !walk->no_vma)' tests can be removed.
Fixes: dd2283f260
("mm: mmap: zap pages with read mmap_sem in munmap")
Reported-by: Jann Horn <jannh@google.com>
Signed-off-by: Steven Price <steven.price@arm.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Cc: Konstantin Khlebnikov <koct9i@gmail.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This commit is contained in:
parent
d895ec7938
commit
8782fb61cc
|
@ -118,10 +118,10 @@ static int __set_memory(unsigned long addr, int numpages, pgprot_t set_mask,
|
|||
if (!numpages)
|
||||
return 0;
|
||||
|
||||
mmap_read_lock(&init_mm);
|
||||
mmap_write_lock(&init_mm);
|
||||
ret = walk_page_range_novma(&init_mm, start, end, &pageattr_ops, NULL,
|
||||
&masks);
|
||||
mmap_read_unlock(&init_mm);
|
||||
mmap_write_unlock(&init_mm);
|
||||
|
||||
flush_tlb_kernel_range(start, end);
|
||||
|
||||
|
|
|
@ -110,7 +110,7 @@ static int walk_pmd_range(pud_t *pud, unsigned long addr, unsigned long end,
|
|||
do {
|
||||
again:
|
||||
next = pmd_addr_end(addr, end);
|
||||
if (pmd_none(*pmd) || (!walk->vma && !walk->no_vma)) {
|
||||
if (pmd_none(*pmd)) {
|
||||
if (ops->pte_hole)
|
||||
err = ops->pte_hole(addr, next, depth, walk);
|
||||
if (err)
|
||||
|
@ -171,7 +171,7 @@ static int walk_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end,
|
|||
do {
|
||||
again:
|
||||
next = pud_addr_end(addr, end);
|
||||
if (pud_none(*pud) || (!walk->vma && !walk->no_vma)) {
|
||||
if (pud_none(*pud)) {
|
||||
if (ops->pte_hole)
|
||||
err = ops->pte_hole(addr, next, depth, walk);
|
||||
if (err)
|
||||
|
@ -366,19 +366,19 @@ static int __walk_page_range(unsigned long start, unsigned long end,
|
|||
struct vm_area_struct *vma = walk->vma;
|
||||
const struct mm_walk_ops *ops = walk->ops;
|
||||
|
||||
if (vma && ops->pre_vma) {
|
||||
if (ops->pre_vma) {
|
||||
err = ops->pre_vma(start, end, walk);
|
||||
if (err)
|
||||
return err;
|
||||
}
|
||||
|
||||
if (vma && is_vm_hugetlb_page(vma)) {
|
||||
if (is_vm_hugetlb_page(vma)) {
|
||||
if (ops->hugetlb_entry)
|
||||
err = walk_hugetlb_range(start, end, walk);
|
||||
} else
|
||||
err = walk_pgd_range(start, end, walk);
|
||||
|
||||
if (vma && ops->post_vma)
|
||||
if (ops->post_vma)
|
||||
ops->post_vma(walk);
|
||||
|
||||
return err;
|
||||
|
@ -450,9 +450,13 @@ int walk_page_range(struct mm_struct *mm, unsigned long start,
|
|||
if (!vma) { /* after the last vma */
|
||||
walk.vma = NULL;
|
||||
next = end;
|
||||
if (ops->pte_hole)
|
||||
err = ops->pte_hole(start, next, -1, &walk);
|
||||
} else if (start < vma->vm_start) { /* outside vma */
|
||||
walk.vma = NULL;
|
||||
next = min(end, vma->vm_start);
|
||||
if (ops->pte_hole)
|
||||
err = ops->pte_hole(start, next, -1, &walk);
|
||||
} else { /* inside vma */
|
||||
walk.vma = vma;
|
||||
next = min(end, vma->vm_end);
|
||||
|
@ -470,9 +474,8 @@ int walk_page_range(struct mm_struct *mm, unsigned long start,
|
|||
}
|
||||
if (err < 0)
|
||||
break;
|
||||
}
|
||||
if (walk.vma || walk.ops->pte_hole)
|
||||
err = __walk_page_range(start, next, &walk);
|
||||
}
|
||||
if (err)
|
||||
break;
|
||||
} while (start = next, start < end);
|
||||
|
@ -501,9 +504,9 @@ int walk_page_range_novma(struct mm_struct *mm, unsigned long start,
|
|||
if (start >= end || !walk.mm)
|
||||
return -EINVAL;
|
||||
|
||||
mmap_assert_locked(walk.mm);
|
||||
mmap_assert_write_locked(walk.mm);
|
||||
|
||||
return __walk_page_range(start, end, &walk);
|
||||
return walk_pgd_range(start, end, &walk);
|
||||
}
|
||||
|
||||
int walk_page_vma(struct vm_area_struct *vma, const struct mm_walk_ops *ops,
|
||||
|
|
|
@ -152,13 +152,13 @@ void ptdump_walk_pgd(struct ptdump_state *st, struct mm_struct *mm, pgd_t *pgd)
|
|||
{
|
||||
const struct ptdump_range *range = st->range;
|
||||
|
||||
mmap_read_lock(mm);
|
||||
mmap_write_lock(mm);
|
||||
while (range->start != range->end) {
|
||||
walk_page_range_novma(mm, range->start, range->end,
|
||||
&ptdump_ops, pgd, st);
|
||||
range++;
|
||||
}
|
||||
mmap_read_unlock(mm);
|
||||
mmap_write_unlock(mm);
|
||||
|
||||
/* Flush out the last page */
|
||||
st->note_page(st, 0, -1, 0);
|
||||
|
|
Loading…
Reference in New Issue