393a1aa421
commit 8782fb61cc848364e1e1599d76d3c9dd58a1cc06 upstream.
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>
[manually backported. backport note: walk_page_range_novma() does not exist in
5.4, so I'm omitting it from the backport]
Signed-off-by: Jann Horn <jannh@google.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
382 lines
9.3 KiB
C
382 lines
9.3 KiB
C
// SPDX-License-Identifier: GPL-2.0
|
|
#include <linux/pagewalk.h>
|
|
#include <linux/highmem.h>
|
|
#include <linux/sched.h>
|
|
#include <linux/hugetlb.h>
|
|
|
|
static int walk_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
|
|
struct mm_walk *walk)
|
|
{
|
|
pte_t *pte;
|
|
int err = 0;
|
|
const struct mm_walk_ops *ops = walk->ops;
|
|
|
|
pte = pte_offset_map(pmd, addr);
|
|
for (;;) {
|
|
err = ops->pte_entry(pte, addr, addr + PAGE_SIZE, walk);
|
|
if (err)
|
|
break;
|
|
if (addr >= end - PAGE_SIZE)
|
|
break;
|
|
addr += PAGE_SIZE;
|
|
pte++;
|
|
}
|
|
|
|
pte_unmap(pte);
|
|
return err;
|
|
}
|
|
|
|
static int walk_pmd_range(pud_t *pud, unsigned long addr, unsigned long end,
|
|
struct mm_walk *walk)
|
|
{
|
|
pmd_t *pmd;
|
|
unsigned long next;
|
|
const struct mm_walk_ops *ops = walk->ops;
|
|
int err = 0;
|
|
|
|
pmd = pmd_offset(pud, addr);
|
|
do {
|
|
again:
|
|
next = pmd_addr_end(addr, end);
|
|
if (pmd_none(*pmd)) {
|
|
if (ops->pte_hole)
|
|
err = ops->pte_hole(addr, next, walk);
|
|
if (err)
|
|
break;
|
|
continue;
|
|
}
|
|
/*
|
|
* This implies that each ->pmd_entry() handler
|
|
* needs to know about pmd_trans_huge() pmds
|
|
*/
|
|
if (ops->pmd_entry)
|
|
err = ops->pmd_entry(pmd, addr, next, walk);
|
|
if (err)
|
|
break;
|
|
|
|
/*
|
|
* Check this here so we only break down trans_huge
|
|
* pages when we _need_ to
|
|
*/
|
|
if (!ops->pte_entry)
|
|
continue;
|
|
|
|
split_huge_pmd(walk->vma, pmd, addr);
|
|
if (pmd_trans_unstable(pmd))
|
|
goto again;
|
|
err = walk_pte_range(pmd, addr, next, walk);
|
|
if (err)
|
|
break;
|
|
} while (pmd++, addr = next, addr != end);
|
|
|
|
return err;
|
|
}
|
|
|
|
static int walk_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end,
|
|
struct mm_walk *walk)
|
|
{
|
|
pud_t *pud;
|
|
unsigned long next;
|
|
const struct mm_walk_ops *ops = walk->ops;
|
|
int err = 0;
|
|
|
|
pud = pud_offset(p4d, addr);
|
|
do {
|
|
again:
|
|
next = pud_addr_end(addr, end);
|
|
if (pud_none(*pud)) {
|
|
if (ops->pte_hole)
|
|
err = ops->pte_hole(addr, next, walk);
|
|
if (err)
|
|
break;
|
|
continue;
|
|
}
|
|
|
|
if (ops->pud_entry) {
|
|
spinlock_t *ptl = pud_trans_huge_lock(pud, walk->vma);
|
|
|
|
if (ptl) {
|
|
err = ops->pud_entry(pud, addr, next, walk);
|
|
spin_unlock(ptl);
|
|
if (err)
|
|
break;
|
|
continue;
|
|
}
|
|
}
|
|
|
|
split_huge_pud(walk->vma, pud, addr);
|
|
if (pud_none(*pud))
|
|
goto again;
|
|
|
|
if (ops->pmd_entry || ops->pte_entry)
|
|
err = walk_pmd_range(pud, addr, next, walk);
|
|
if (err)
|
|
break;
|
|
} while (pud++, addr = next, addr != end);
|
|
|
|
return err;
|
|
}
|
|
|
|
static int walk_p4d_range(pgd_t *pgd, unsigned long addr, unsigned long end,
|
|
struct mm_walk *walk)
|
|
{
|
|
p4d_t *p4d;
|
|
unsigned long next;
|
|
const struct mm_walk_ops *ops = walk->ops;
|
|
int err = 0;
|
|
|
|
p4d = p4d_offset(pgd, addr);
|
|
do {
|
|
next = p4d_addr_end(addr, end);
|
|
if (p4d_none_or_clear_bad(p4d)) {
|
|
if (ops->pte_hole)
|
|
err = ops->pte_hole(addr, next, walk);
|
|
if (err)
|
|
break;
|
|
continue;
|
|
}
|
|
if (ops->pmd_entry || ops->pte_entry)
|
|
err = walk_pud_range(p4d, addr, next, walk);
|
|
if (err)
|
|
break;
|
|
} while (p4d++, addr = next, addr != end);
|
|
|
|
return err;
|
|
}
|
|
|
|
static int walk_pgd_range(unsigned long addr, unsigned long end,
|
|
struct mm_walk *walk)
|
|
{
|
|
pgd_t *pgd;
|
|
unsigned long next;
|
|
const struct mm_walk_ops *ops = walk->ops;
|
|
int err = 0;
|
|
|
|
pgd = pgd_offset(walk->mm, addr);
|
|
do {
|
|
next = pgd_addr_end(addr, end);
|
|
if (pgd_none_or_clear_bad(pgd)) {
|
|
if (ops->pte_hole)
|
|
err = ops->pte_hole(addr, next, walk);
|
|
if (err)
|
|
break;
|
|
continue;
|
|
}
|
|
if (ops->pmd_entry || ops->pte_entry)
|
|
err = walk_p4d_range(pgd, addr, next, walk);
|
|
if (err)
|
|
break;
|
|
} while (pgd++, addr = next, addr != end);
|
|
|
|
return err;
|
|
}
|
|
|
|
#ifdef CONFIG_HUGETLB_PAGE
|
|
static unsigned long hugetlb_entry_end(struct hstate *h, unsigned long addr,
|
|
unsigned long end)
|
|
{
|
|
unsigned long boundary = (addr & huge_page_mask(h)) + huge_page_size(h);
|
|
return boundary < end ? boundary : end;
|
|
}
|
|
|
|
static int walk_hugetlb_range(unsigned long addr, unsigned long end,
|
|
struct mm_walk *walk)
|
|
{
|
|
struct vm_area_struct *vma = walk->vma;
|
|
struct hstate *h = hstate_vma(vma);
|
|
unsigned long next;
|
|
unsigned long hmask = huge_page_mask(h);
|
|
unsigned long sz = huge_page_size(h);
|
|
pte_t *pte;
|
|
const struct mm_walk_ops *ops = walk->ops;
|
|
int err = 0;
|
|
|
|
do {
|
|
next = hugetlb_entry_end(h, addr, end);
|
|
pte = huge_pte_offset(walk->mm, addr & hmask, sz);
|
|
|
|
if (pte)
|
|
err = ops->hugetlb_entry(pte, hmask, addr, next, walk);
|
|
else if (ops->pte_hole)
|
|
err = ops->pte_hole(addr, next, walk);
|
|
|
|
if (err)
|
|
break;
|
|
} while (addr = next, addr != end);
|
|
|
|
return err;
|
|
}
|
|
|
|
#else /* CONFIG_HUGETLB_PAGE */
|
|
static int walk_hugetlb_range(unsigned long addr, unsigned long end,
|
|
struct mm_walk *walk)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
#endif /* CONFIG_HUGETLB_PAGE */
|
|
|
|
/*
|
|
* Decide whether we really walk over the current vma on [@start, @end)
|
|
* or skip it via the returned value. Return 0 if we do walk over the
|
|
* current vma, and return 1 if we skip the vma. Negative values means
|
|
* error, where we abort the current walk.
|
|
*/
|
|
static int walk_page_test(unsigned long start, unsigned long end,
|
|
struct mm_walk *walk)
|
|
{
|
|
struct vm_area_struct *vma = walk->vma;
|
|
const struct mm_walk_ops *ops = walk->ops;
|
|
|
|
if (ops->test_walk)
|
|
return ops->test_walk(start, end, walk);
|
|
|
|
/*
|
|
* vma(VM_PFNMAP) doesn't have any valid struct pages behind VM_PFNMAP
|
|
* range, so we don't walk over it as we do for normal vmas. However,
|
|
* Some callers are interested in handling hole range and they don't
|
|
* want to just ignore any single address range. Such users certainly
|
|
* define their ->pte_hole() callbacks, so let's delegate them to handle
|
|
* vma(VM_PFNMAP).
|
|
*/
|
|
if (vma->vm_flags & VM_PFNMAP) {
|
|
int err = 1;
|
|
if (ops->pte_hole)
|
|
err = ops->pte_hole(start, end, walk);
|
|
return err ? err : 1;
|
|
}
|
|
return 0;
|
|
}
|
|
|
|
static int __walk_page_range(unsigned long start, unsigned long end,
|
|
struct mm_walk *walk)
|
|
{
|
|
int err = 0;
|
|
struct vm_area_struct *vma = walk->vma;
|
|
|
|
if (is_vm_hugetlb_page(vma)) {
|
|
if (walk->ops->hugetlb_entry)
|
|
err = walk_hugetlb_range(start, end, walk);
|
|
} else
|
|
err = walk_pgd_range(start, end, walk);
|
|
|
|
return err;
|
|
}
|
|
|
|
/**
|
|
* walk_page_range - walk page table with caller specific callbacks
|
|
* @mm: mm_struct representing the target process of page table walk
|
|
* @start: start address of the virtual address range
|
|
* @end: end address of the virtual address range
|
|
* @ops: operation to call during the walk
|
|
* @private: private data for callbacks' usage
|
|
*
|
|
* Recursively walk the page table tree of the process represented by @mm
|
|
* within the virtual address range [@start, @end). During walking, we can do
|
|
* some caller-specific works for each entry, by setting up pmd_entry(),
|
|
* pte_entry(), and/or hugetlb_entry(). If you don't set up for some of these
|
|
* callbacks, the associated entries/pages are just ignored.
|
|
* The return values of these callbacks are commonly defined like below:
|
|
*
|
|
* - 0 : succeeded to handle the current entry, and if you don't reach the
|
|
* end address yet, continue to walk.
|
|
* - >0 : succeeded to handle the current entry, and return to the caller
|
|
* with caller specific value.
|
|
* - <0 : failed to handle the current entry, and return to the caller
|
|
* with error code.
|
|
*
|
|
* Before starting to walk page table, some callers want to check whether
|
|
* they really want to walk over the current vma, typically by checking
|
|
* its vm_flags. walk_page_test() and @ops->test_walk() are used for this
|
|
* purpose.
|
|
*
|
|
* struct mm_walk keeps current values of some common data like vma and pmd,
|
|
* which are useful for the access from callbacks. If you want to pass some
|
|
* caller-specific data to callbacks, @private should be helpful.
|
|
*
|
|
* Locking:
|
|
* Callers of walk_page_range() and walk_page_vma() should hold @mm->mmap_sem,
|
|
* because these function traverse vma list and/or access to vma's data.
|
|
*/
|
|
int walk_page_range(struct mm_struct *mm, unsigned long start,
|
|
unsigned long end, const struct mm_walk_ops *ops,
|
|
void *private)
|
|
{
|
|
int err = 0;
|
|
unsigned long next;
|
|
struct vm_area_struct *vma;
|
|
struct mm_walk walk = {
|
|
.ops = ops,
|
|
.mm = mm,
|
|
.private = private,
|
|
};
|
|
|
|
if (start >= end)
|
|
return -EINVAL;
|
|
|
|
if (!walk.mm)
|
|
return -EINVAL;
|
|
|
|
lockdep_assert_held(&walk.mm->mmap_sem);
|
|
|
|
vma = find_vma(walk.mm, start);
|
|
do {
|
|
if (!vma) { /* after the last vma */
|
|
walk.vma = NULL;
|
|
next = end;
|
|
if (ops->pte_hole)
|
|
err = ops->pte_hole(start, next, &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, &walk);
|
|
} else { /* inside vma */
|
|
walk.vma = vma;
|
|
next = min(end, vma->vm_end);
|
|
vma = vma->vm_next;
|
|
|
|
err = walk_page_test(start, next, &walk);
|
|
if (err > 0) {
|
|
/*
|
|
* positive return values are purely for
|
|
* controlling the pagewalk, so should never
|
|
* be passed to the callers.
|
|
*/
|
|
err = 0;
|
|
continue;
|
|
}
|
|
if (err < 0)
|
|
break;
|
|
err = __walk_page_range(start, next, &walk);
|
|
}
|
|
if (err)
|
|
break;
|
|
} while (start = next, start < end);
|
|
return err;
|
|
}
|
|
|
|
int walk_page_vma(struct vm_area_struct *vma, const struct mm_walk_ops *ops,
|
|
void *private)
|
|
{
|
|
struct mm_walk walk = {
|
|
.ops = ops,
|
|
.mm = vma->vm_mm,
|
|
.vma = vma,
|
|
.private = private,
|
|
};
|
|
int err;
|
|
|
|
if (!walk.mm)
|
|
return -EINVAL;
|
|
|
|
lockdep_assert_held(&walk.mm->mmap_sem);
|
|
|
|
err = walk_page_test(vma->vm_start, vma->vm_end, &walk);
|
|
if (err > 0)
|
|
return 0;
|
|
if (err < 0)
|
|
return err;
|
|
return __walk_page_range(vma->vm_start, vma->vm_end, &walk);
|
|
}
|