linux-stable/mm/page_vma_mapped.c
Will Deacon a7b100953a mm: page_vma_mapped: ensure pmd is loaded with READ_ONCE outside of lock
Loading the pmd without holding the pmd_lock exposes us to races with
concurrent updaters of the page tables but, worse still, it also allows
the compiler to cache the pmd value in a register and reuse it later on,
even if we've performed a READ_ONCE in between and seen a more recent
value.

In the case of page_vma_mapped_walk, this leads to the following crash
when the pmd loaded for the initial pmd_trans_huge check is all zeroes
and a subsequent valid table entry is loaded by check_pmd.  We then
proceed into map_pte, but the compiler re-uses the zero entry inside
pte_offset_map, resulting in a junk pointer being installed in
pvmw->pte:

  PC is at check_pte+0x20/0x170
  LR is at page_vma_mapped_walk+0x2e0/0x540
  [...]
  Process doio (pid: 2463, stack limit = 0xffff00000f2e8000)
  Call trace:
    check_pte+0x20/0x170
    page_vma_mapped_walk+0x2e0/0x540
    page_mkclean_one+0xac/0x278
    rmap_walk_file+0xf0/0x238
    rmap_walk+0x64/0xa0
    page_mkclean+0x90/0xa8
    clear_page_dirty_for_io+0x84/0x2a8
    mpage_submit_page+0x34/0x98
    mpage_process_page_bufs+0x164/0x170
    mpage_prepare_extent_to_map+0x134/0x2b8
    ext4_writepages+0x484/0xe30
    do_writepages+0x44/0xe8
    __filemap_fdatawrite_range+0xbc/0x110
    file_write_and_wait_range+0x48/0xd8
    ext4_sync_file+0x80/0x4b8
    vfs_fsync_range+0x64/0xc0
    SyS_msync+0x194/0x1e8

This patch fixes the problem by ensuring that READ_ONCE is used before
the initial checks on the pmd, and this value is subsequently used when
checking whether or not the pmd is present.  pmd_check is removed and
the pmd_present check is inlined directly.

Link: http://lkml.kernel.org/r/1507222630-5839-1-git-send-email-will.deacon@arm.com
Fixes: f27176cfc3 ("mm: convert page_mkclean_one() to use page_vma_mapped_walk()")
Signed-off-by: Will Deacon <will.deacon@arm.com>
Tested-by: Yury Norov <ynorov@caviumnetworks.com>
Tested-by: Richard Ruigrok <rruigrok@codeaurora.org>
Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-10-13 16:18:33 -07:00

240 lines
6.3 KiB
C

#include <linux/mm.h>
#include <linux/rmap.h>
#include <linux/hugetlb.h>
#include <linux/swap.h>
#include <linux/swapops.h>
#include "internal.h"
static inline bool not_found(struct page_vma_mapped_walk *pvmw)
{
page_vma_mapped_walk_done(pvmw);
return false;
}
static bool map_pte(struct page_vma_mapped_walk *pvmw)
{
pvmw->pte = pte_offset_map(pvmw->pmd, pvmw->address);
if (!(pvmw->flags & PVMW_SYNC)) {
if (pvmw->flags & PVMW_MIGRATION) {
if (!is_swap_pte(*pvmw->pte))
return false;
} else {
if (!pte_present(*pvmw->pte))
return false;
}
}
pvmw->ptl = pte_lockptr(pvmw->vma->vm_mm, pvmw->pmd);
spin_lock(pvmw->ptl);
return true;
}
static bool check_pte(struct page_vma_mapped_walk *pvmw)
{
if (pvmw->flags & PVMW_MIGRATION) {
#ifdef CONFIG_MIGRATION
swp_entry_t entry;
if (!is_swap_pte(*pvmw->pte))
return false;
entry = pte_to_swp_entry(*pvmw->pte);
if (!is_migration_entry(entry))
return false;
if (migration_entry_to_page(entry) - pvmw->page >=
hpage_nr_pages(pvmw->page)) {
return false;
}
if (migration_entry_to_page(entry) < pvmw->page)
return false;
#else
WARN_ON_ONCE(1);
#endif
} else {
if (is_swap_pte(*pvmw->pte)) {
swp_entry_t entry;
entry = pte_to_swp_entry(*pvmw->pte);
if (is_device_private_entry(entry) &&
device_private_entry_to_page(entry) == pvmw->page)
return true;
}
if (!pte_present(*pvmw->pte))
return false;
/* THP can be referenced by any subpage */
if (pte_page(*pvmw->pte) - pvmw->page >=
hpage_nr_pages(pvmw->page)) {
return false;
}
if (pte_page(*pvmw->pte) < pvmw->page)
return false;
}
return true;
}
/**
* page_vma_mapped_walk - check if @pvmw->page is mapped in @pvmw->vma at
* @pvmw->address
* @pvmw: pointer to struct page_vma_mapped_walk. page, vma, address and flags
* must be set. pmd, pte and ptl must be NULL.
*
* Returns true if the page is mapped in the vma. @pvmw->pmd and @pvmw->pte point
* to relevant page table entries. @pvmw->ptl is locked. @pvmw->address is
* adjusted if needed (for PTE-mapped THPs).
*
* If @pvmw->pmd is set but @pvmw->pte is not, you have found PMD-mapped page
* (usually THP). For PTE-mapped THP, you should run page_vma_mapped_walk() in
* a loop to find all PTEs that map the THP.
*
* For HugeTLB pages, @pvmw->pte is set to the relevant page table entry
* regardless of which page table level the page is mapped at. @pvmw->pmd is
* NULL.
*
* Retruns false if there are no more page table entries for the page in
* the vma. @pvmw->ptl is unlocked and @pvmw->pte is unmapped.
*
* If you need to stop the walk before page_vma_mapped_walk() returned false,
* use page_vma_mapped_walk_done(). It will do the housekeeping.
*/
bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw)
{
struct mm_struct *mm = pvmw->vma->vm_mm;
struct page *page = pvmw->page;
pgd_t *pgd;
p4d_t *p4d;
pud_t *pud;
pmd_t pmde;
/* The only possible pmd mapping has been handled on last iteration */
if (pvmw->pmd && !pvmw->pte)
return not_found(pvmw);
if (pvmw->pte)
goto next_pte;
if (unlikely(PageHuge(pvmw->page))) {
/* when pud is not present, pte will be NULL */
pvmw->pte = huge_pte_offset(mm, pvmw->address,
PAGE_SIZE << compound_order(page));
if (!pvmw->pte)
return false;
pvmw->ptl = huge_pte_lockptr(page_hstate(page), mm, pvmw->pte);
spin_lock(pvmw->ptl);
if (!check_pte(pvmw))
return not_found(pvmw);
return true;
}
restart:
pgd = pgd_offset(mm, pvmw->address);
if (!pgd_present(*pgd))
return false;
p4d = p4d_offset(pgd, pvmw->address);
if (!p4d_present(*p4d))
return false;
pud = pud_offset(p4d, pvmw->address);
if (!pud_present(*pud))
return false;
pvmw->pmd = pmd_offset(pud, pvmw->address);
/*
* Make sure the pmd value isn't cached in a register by the
* compiler and used as a stale value after we've observed a
* subsequent update.
*/
pmde = READ_ONCE(*pvmw->pmd);
if (pmd_trans_huge(pmde) || is_pmd_migration_entry(pmde)) {
pvmw->ptl = pmd_lock(mm, pvmw->pmd);
if (likely(pmd_trans_huge(*pvmw->pmd))) {
if (pvmw->flags & PVMW_MIGRATION)
return not_found(pvmw);
if (pmd_page(*pvmw->pmd) != page)
return not_found(pvmw);
return true;
} else if (!pmd_present(*pvmw->pmd)) {
if (thp_migration_supported()) {
if (!(pvmw->flags & PVMW_MIGRATION))
return not_found(pvmw);
if (is_migration_entry(pmd_to_swp_entry(*pvmw->pmd))) {
swp_entry_t entry = pmd_to_swp_entry(*pvmw->pmd);
if (migration_entry_to_page(entry) != page)
return not_found(pvmw);
return true;
}
}
return not_found(pvmw);
} else {
/* THP pmd was split under us: handle on pte level */
spin_unlock(pvmw->ptl);
pvmw->ptl = NULL;
}
} else if (!pmd_present(pmde)) {
return false;
}
if (!map_pte(pvmw))
goto next_pte;
while (1) {
if (check_pte(pvmw))
return true;
next_pte:
/* Seek to next pte only makes sense for THP */
if (!PageTransHuge(pvmw->page) || PageHuge(pvmw->page))
return not_found(pvmw);
do {
pvmw->address += PAGE_SIZE;
if (pvmw->address >= pvmw->vma->vm_end ||
pvmw->address >=
__vma_address(pvmw->page, pvmw->vma) +
hpage_nr_pages(pvmw->page) * PAGE_SIZE)
return not_found(pvmw);
/* Did we cross page table boundary? */
if (pvmw->address % PMD_SIZE == 0) {
pte_unmap(pvmw->pte);
if (pvmw->ptl) {
spin_unlock(pvmw->ptl);
pvmw->ptl = NULL;
}
goto restart;
} else {
pvmw->pte++;
}
} while (pte_none(*pvmw->pte));
if (!pvmw->ptl) {
pvmw->ptl = pte_lockptr(mm, pvmw->pmd);
spin_lock(pvmw->ptl);
}
}
}
/**
* page_mapped_in_vma - check whether a page is really mapped in a VMA
* @page: the page to test
* @vma: the VMA to test
*
* Returns 1 if the page is mapped into the page tables of the VMA, 0
* if the page is not mapped into the page tables of this VMA. Only
* valid for normal file or anonymous VMAs.
*/
int page_mapped_in_vma(struct page *page, struct vm_area_struct *vma)
{
struct page_vma_mapped_walk pvmw = {
.page = page,
.vma = vma,
.flags = PVMW_SYNC,
};
unsigned long start, end;
start = __vma_address(page, vma);
end = start + PAGE_SIZE * (hpage_nr_pages(page) - 1);
if (unlikely(end < vma->vm_start || start >= vma->vm_end))
return 0;
pvmw.address = max(start, vma->vm_start);
if (!page_vma_mapped_walk(&pvmw))
return 0;
page_vma_mapped_walk_done(&pvmw);
return 1;
}