diff options
| author | David Rientjes <rientjes@google.com> | 2014-10-29 14:50:31 -0700 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2014-10-29 16:33:14 -0700 |
| commit | 6d50e60cd2edb5a57154db5a6f64eef5aa59b751 (patch) | |
| tree | 025056e23d57062c5e045d54613edc2e2fc4ca86 /mm/huge_memory.c | |
| parent | 47f29df7db78ee4fcdb104cf36918d987ddd0278 (diff) | |
| download | lwn-6d50e60cd2edb5a57154db5a6f64eef5aa59b751.tar.gz lwn-6d50e60cd2edb5a57154db5a6f64eef5aa59b751.zip | |
mm, thp: fix collapsing of hugepages on madvise
If an anonymous mapping is not allowed to fault thp memory and then
madvise(MADV_HUGEPAGE) is used after fault, khugepaged will never
collapse this memory into thp memory.
This occurs because the madvise(2) handler for thp, hugepage_madvise(),
clears VM_NOHUGEPAGE on the stack and it isn't stored in vma->vm_flags
until the final action of madvise_behavior(). This causes the
khugepaged_enter_vma_merge() to be a no-op in hugepage_madvise() when
the vma had previously had VM_NOHUGEPAGE set.
Fix this by passing the correct vma flags to the khugepaged mm slot
handler. There's no chance khugepaged can run on this vma until after
madvise_behavior() returns since we hold mm->mmap_sem.
It would be possible to clear VM_NOHUGEPAGE directly from vma->vm_flags
in hugepage_advise(), but I didn't want to introduce special case
behavior into madvise_behavior(). I think it's best to just let it
always set vma->vm_flags itself.
Signed-off-by: David Rientjes <rientjes@google.com>
Reported-by: Suleiman Souhlal <suleiman@google.com>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'mm/huge_memory.c')
| -rw-r--r-- | mm/huge_memory.c | 11 |
1 files changed, 6 insertions, 5 deletions
diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 780d12c000e9..de984159cf0b 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -803,7 +803,7 @@ int do_huge_pmd_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma, return VM_FAULT_FALLBACK; if (unlikely(anon_vma_prepare(vma))) return VM_FAULT_OOM; - if (unlikely(khugepaged_enter(vma))) + if (unlikely(khugepaged_enter(vma, vma->vm_flags))) return VM_FAULT_OOM; if (!(flags & FAULT_FLAG_WRITE) && transparent_hugepage_use_zero_page()) { @@ -1970,7 +1970,7 @@ int hugepage_madvise(struct vm_area_struct *vma, * register it here without waiting a page fault that * may not happen any time soon. */ - if (unlikely(khugepaged_enter_vma_merge(vma))) + if (unlikely(khugepaged_enter_vma_merge(vma, *vm_flags))) return -ENOMEM; break; case MADV_NOHUGEPAGE: @@ -2071,7 +2071,8 @@ int __khugepaged_enter(struct mm_struct *mm) return 0; } -int khugepaged_enter_vma_merge(struct vm_area_struct *vma) +int khugepaged_enter_vma_merge(struct vm_area_struct *vma, + unsigned long vm_flags) { unsigned long hstart, hend; if (!vma->anon_vma) @@ -2083,11 +2084,11 @@ int khugepaged_enter_vma_merge(struct vm_area_struct *vma) if (vma->vm_ops) /* khugepaged not yet working on file or special mappings */ return 0; - VM_BUG_ON_VMA(vma->vm_flags & VM_NO_THP, vma); + VM_BUG_ON_VMA(vm_flags & VM_NO_THP, vma); hstart = (vma->vm_start + ~HPAGE_PMD_MASK) & HPAGE_PMD_MASK; hend = vma->vm_end & HPAGE_PMD_MASK; if (hstart < hend) - return khugepaged_enter(vma); + return khugepaged_enter(vma, vm_flags); return 0; } |