pmd_trans_unstable()/pmd_none_or_trans_huge_or_clear_bad() were introduced to locklessy (but atomically) detect when a pmd is a regular (stable) pmd or when the pmd is unstable and can infinitely transition from pmd_none() and pmd_trans_huge() from under us, while only holding the mmap_sem for reading (for writing not). While holding the mmap_sem only for reading, MADV_DONTNEED can run from under us and so before we can assume the pmd to be a regular stable pmd we need to compare it against pmd_none() and pmd_trans_huge() in an atomic way, with pmd_trans_unstable(). The old pmd_trans_huge() left a tiny window for a race. Useful applications are unlikely to notice the difference as doing MADV_DONTNEED concurrently with a page fault would lead to undefined behavior. [akpm@linux-foundation.org: tidy up comment grammar/layout] Signed-off-by: Andrea Arcangeli <aarcange@redhat.com> Reported-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Unified · Split
| @@ -3404,8 +3404,18 @@ static int __handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma, · 3403 unmodified lines | |||
| 3404 | if (unlikely(pmd_none(*pmd)) && | 3404 | if (unlikely(pmd_none(*pmd)) && |
| 3405 | unlikely(__pte_alloc(mm, vma, pmd, address))) | 3405 | unlikely(__pte_alloc(mm, vma, pmd, address))) |
| 3406 | return VM_FAULT_OOM; | 3406 | return VM_FAULT_OOM; |
| 3407 | /* if an huge pmd materialized from under us just retry later */ | 3407 | /* |
| 3408 | if (unlikely(pmd_trans_huge(*pmd) || pmd_devmap(*pmd))) | 3408 | * If a huge pmd materialized under us just retry later. Use |
| 3409 | * pmd_trans_unstable() instead of pmd_trans_huge() to ensure the pmd | ||
| 3410 | * didn't become pmd_trans_huge under us and then back to pmd_none, as | ||
| 3411 | * a result of MADV_DONTNEED running immediately after a huge pmd fault | ||
| 3412 | * in a different thread of this mm, in turn leading to a misleading | ||
| 3413 | * pmd_trans_huge() retval. All we have to ensure is that it is a | ||
| 3414 | * regular pmd that we can walk with pte_offset_map() and we can do that | ||
| 3415 | * through an atomic read in C, which is what pmd_trans_unstable() | ||
| 3416 | * provides. | ||
| 3417 | */ | ||
| 3418 | if (unlikely(pmd_trans_unstable(pmd) || pmd_devmap(*pmd))) | ||
| 3409 | return 0; | 3419 | return 0; |
| 3410 | /* | 3420 | /* |
| 3411 | * A regular pmd is established and it can't morph into a huge pmd | 3421 | * A regular pmd is established and it can't morph into a huge pmd |