summaryrefslogtreecommitdiff
path: root/mm
diff options
context:
space:
mode:
authorMel Gorman <mgorman@suse.de>2014-10-02 19:47:42 +0100
committerGreg Kroah-Hartman <gregkh@linuxfoundation.org>2014-10-09 12:21:27 -0700
commit5f50c44d8a63ee6c4801cdcb372b8048ac77efcf (patch)
tree578553a467e28ab5d35bbb515c218f6bbd031d3d /mm
parent1da286ebc5a1d23d0b4b88ba0d64fc141ac4c37d (diff)
downloadlwn-5f50c44d8a63ee6c4801cdcb372b8048ac77efcf.tar.gz
lwn-5f50c44d8a63ee6c4801cdcb372b8048ac77efcf.zip
mm: numa: Do not mark PTEs pte_numa when splitting huge pages
commit abc40bd2eeb77eb7c2effcaf63154aad929a1d5f upstream. This patch reverts 1ba6e0b50b ("mm: numa: split_huge_page: transfer the NUMA type from the pmd to the pte"). If a huge page is being split due a protection change and the tail will be in a PROT_NONE vma then NUMA hinting PTEs are temporarily created in the protected VMA. VM_RW|VM_PROTNONE |-----------------| ^ split here In the specific case above, it should get fixed up by change_pte_range() but there is a window of opportunity for weirdness to happen. Similarly, if a huge page is shrunk and split during a protection update but before pmd_numa is cleared then a pte_numa can be left behind. Instead of adding complexity trying to deal with the case, this patch will not mark PTEs NUMA when splitting a huge page. NUMA hinting faults will not be triggered which is marginal in comparison to the complexity in dealing with the corner cases during THP split. Signed-off-by: Mel Gorman <mgorman@suse.de> Acked-by: Rik van Riel <riel@redhat.com> Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Diffstat (limited to 'mm')
-rw-r--r--mm/huge_memory.c7
1 files changed, 5 insertions, 2 deletions
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 4a0c99870774..718bfa16a36f 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1826,14 +1826,17 @@ static int __split_huge_page_map(struct page *page,
for (i = 0; i < HPAGE_PMD_NR; i++, haddr += PAGE_SIZE) {
pte_t *pte, entry;
BUG_ON(PageCompound(page+i));
+ /*
+ * Note that pmd_numa is not transferred deliberately
+ * to avoid any possibility that pte_numa leaks to
+ * a PROT_NONE VMA by accident.
+ */
entry = mk_pte(page + i, vma->vm_page_prot);
entry = maybe_mkwrite(pte_mkdirty(entry), vma);
if (!pmd_write(*pmd))
entry = pte_wrprotect(entry);
if (!pmd_young(*pmd))
entry = pte_mkold(entry);
- if (pmd_numa(*pmd))
- entry = pte_mknuma(entry);
pte = pte_offset_map(&_pmd, haddr);
BUG_ON(!pte_none(*pte));
set_pte_at(mm, haddr, pte, entry);