summaryrefslogtreecommitdiffstats
path: root/mm
diff options
context:
space:
mode:
authorKirill A. Shutemov <kirill.shutemov@linux.intel.com>2016-04-28 16:18:27 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2016-04-28 19:34:04 -0700
commitaa88b68c3b1dce8bc3fd54c8a7372a777ff265cd (patch)
tree98ad92a044b6a2f39a8fa4c1c24df001108bd1a8 /mm
parent66ee95d16a7f1b7b4f1dd74a2d81c6e19dc29a14 (diff)
downloadlinux-stable-aa88b68c3b1dce8bc3fd54c8a7372a777ff265cd.tar.gz
linux-stable-aa88b68c3b1dce8bc3fd54c8a7372a777ff265cd.tar.bz2
linux-stable-aa88b68c3b1dce8bc3fd54c8a7372a777ff265cd.zip
thp: keep huge zero page pinned until tlb flush
Andrea has found[1] a race condition on MMU-gather based TLB flush vs split_huge_page() or shrinker which frees huge zero under us (patch 1/2 and 2/2 respectively). With new THP refcounting, we don't need patch 1/2: mmu_gather keeps the page pinned until flush is complete and the pin prevents the page from being split under us. We still need patch 2/2. This is simplified version of Andrea's patch. We don't need fancy encoding. [1] http://lkml.kernel.org/r/1447938052-22165-1-git-send-email-aarcange@redhat.com Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Reported-by: Andrea Arcangeli <aarcange@redhat.com> Reviewed-by: Andrea Arcangeli <aarcange@redhat.com> Cc: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com> Cc: Mel Gorman <mgorman@techsingularity.net> Cc: Hugh Dickins <hughd@google.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Vlastimil Babka <vbabka@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'mm')
-rw-r--r--mm/huge_memory.c6
-rw-r--r--mm/swap.c5
2 files changed, 8 insertions, 3 deletions
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 86f9f8b82f8e..5346de05f471 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -232,7 +232,7 @@ retry:
return READ_ONCE(huge_zero_page);
}
-static void put_huge_zero_page(void)
+void put_huge_zero_page(void)
{
/*
* Counter should never go to zero here. Only shrinker can put
@@ -1684,12 +1684,12 @@ int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
if (vma_is_dax(vma)) {
spin_unlock(ptl);
if (is_huge_zero_pmd(orig_pmd))
- put_huge_zero_page();
+ tlb_remove_page(tlb, pmd_page(orig_pmd));
} else if (is_huge_zero_pmd(orig_pmd)) {
pte_free(tlb->mm, pgtable_trans_huge_withdraw(tlb->mm, pmd));
atomic_long_dec(&tlb->mm->nr_ptes);
spin_unlock(ptl);
- put_huge_zero_page();
+ tlb_remove_page(tlb, pmd_page(orig_pmd));
} else {
struct page *page = pmd_page(orig_pmd);
page_remove_rmap(page, true);
diff --git a/mm/swap.c b/mm/swap.c
index a0bc206b4ac6..03aacbcb013f 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -728,6 +728,11 @@ void release_pages(struct page **pages, int nr, bool cold)
zone = NULL;
}
+ if (is_huge_zero_page(page)) {
+ put_huge_zero_page();
+ continue;
+ }
+
page = compound_head(page);
if (!put_page_testzero(page))
continue;