diff options
authorWill Deacon <>2017-10-13 15:58:25 -0700
committerLinus Torvalds <>2017-10-13 16:18:33 -0700
commita7b100953aa33a5bbdc3e5e7f2241b9c0704606e (patch)
parentca182551857cc2c1e6a2b7f1e72090a137a15008 (diff)
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: Fixes: f27176cfc363 ("mm: convert page_mkclean_one() to use page_vma_mapped_walk()") Signed-off-by: Will Deacon <> Tested-by: Yury Norov <> Tested-by: Richard Ruigrok <> Acked-by: Kirill A. Shutemov <> Cc: "Paul E. McKenney" <> Cc: Peter Zijlstra <> Cc: <> Signed-off-by: Andrew Morton <> Signed-off-by: Linus Torvalds <>
1 files changed, 10 insertions, 15 deletions
diff --git a/mm/page_vma_mapped.c b/mm/page_vma_mapped.c
index eb462e7db0a9..53afbb919a1c 100644
--- a/mm/page_vma_mapped.c
+++ b/mm/page_vma_mapped.c
@@ -6,17 +6,6 @@
#include "internal.h"
-static inline bool check_pmd(struct page_vma_mapped_walk *pvmw)
- pmd_t pmde;
- /*
- * Make sure we don't re-load pmd between present and !trans_huge check.
- * We need a consistent view.
- */
- pmde = READ_ONCE(*pvmw->pmd);
- return pmd_present(pmde) && !pmd_trans_huge(pmde);
static inline bool not_found(struct page_vma_mapped_walk *pvmw)
@@ -116,6 +105,7 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw)
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)
@@ -148,7 +138,13 @@ restart:
if (!pud_present(*pud))
return false;
pvmw->pmd = pmd_offset(pud, pvmw->address);
- if (pmd_trans_huge(*pvmw->pmd) || is_pmd_migration_entry(*pvmw->pmd)) {
+ /*
+ * 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)
@@ -174,9 +170,8 @@ restart:
pvmw->ptl = NULL;
- } else {
- if (!check_pmd(pvmw))
- return false;
+ } else if (!pmd_present(pmde)) {
+ return false;
if (!map_pte(pvmw))
goto next_pte;