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>
This commit is contained in:
parent
ca18255185
commit
a7b100953a
|
@ -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)
|
||||
{
|
||||
page_vma_mapped_walk_done(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:
|
|||
spin_unlock(pvmw->ptl);
|
||||
pvmw->ptl = NULL;
|
||||
}
|
||||
} else {
|
||||
if (!check_pmd(pvmw))
|
||||
return false;
|
||||
} else if (!pmd_present(pmde)) {
|
||||
return false;
|
||||
}
|
||||
if (!map_pte(pvmw))
|
||||
goto next_pte;
|
||||
|
|
Loading…
Reference in New Issue