summaryrefslogtreecommitdiffstats
path: root/mm/mlock.c
diff options
context:
space:
mode:
authorKirill A. Shutemov <kirill.shutemov@linux.intel.com>2016-01-15 16:52:35 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2016-01-15 17:56:32 -0800
commit7479df6da9506a624ae214588269ed42221494f9 (patch)
treee8bfc07724037bf238aa0d9d0caf6344fdfc1de5 /mm/mlock.c
parent7aef4172c7957d7e65fc172be4c99becaef855d4 (diff)
downloadlinux-stable-7479df6da9506a624ae214588269ed42221494f9.tar.gz
linux-stable-7479df6da9506a624ae214588269ed42221494f9.tar.bz2
linux-stable-7479df6da9506a624ae214588269ed42221494f9.zip
thp, mlock: do not allow huge pages in mlocked area
With new refcounting THP can belong to several VMAs. This makes tricky to track THP pages, when they partially mlocked. It can lead to leaking mlocked pages to non-VM_LOCKED vmas and other problems. With this patch we will split all pages on mlock and avoid fault-in/collapse new THP in VM_LOCKED vmas. I've tried alternative approach: do not mark THP pages mlocked and keep them on normal LRUs. This way vmscan could try to split huge pages on memory pressure and free up subpages which doesn't belong to VM_LOCKED vmas. But this is user-visible change: we screw up Mlocked accouting reported in meminfo, so I had to leave this approach aside. We can bring something better later, but this should be good enough for now. Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Tested-by: Sasha Levin <sasha.levin@oracle.com> Tested-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> Acked-by: Jerome Marchand <jmarchan@redhat.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Hugh Dickins <hughd@google.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Rik van Riel <riel@redhat.com> Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Cc: Steve Capper <steve.capper@linaro.org> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Michal Hocko <mhocko@suse.cz> Cc: Christoph Lameter <cl@linux.com> Cc: David Rientjes <rientjes@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'mm/mlock.c')
-rw-r--r--mm/mlock.c51
1 files changed, 19 insertions, 32 deletions
diff --git a/mm/mlock.c b/mm/mlock.c
index 9cb87cbc4071..c6b139ad356a 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -443,39 +443,26 @@ void munlock_vma_pages_range(struct vm_area_struct *vma,
page = follow_page_mask(vma, start, FOLL_GET | FOLL_DUMP,
&page_mask);
- if (page && !IS_ERR(page)) {
- if (PageTransHuge(page)) {
- lock_page(page);
- /*
- * Any THP page found by follow_page_mask() may
- * have gotten split before reaching
- * munlock_vma_page(), so we need to recompute
- * the page_mask here.
- */
- page_mask = munlock_vma_page(page);
- unlock_page(page);
- put_page(page); /* follow_page_mask() */
- } else {
- /*
- * Non-huge pages are handled in batches via
- * pagevec. The pin from follow_page_mask()
- * prevents them from collapsing by THP.
- */
- pagevec_add(&pvec, page);
- zone = page_zone(page);
- zoneid = page_zone_id(page);
+ if (page && !IS_ERR(page) && !PageTransCompound(page)) {
+ /*
+ * Non-huge pages are handled in batches via
+ * pagevec. The pin from follow_page_mask()
+ * prevents them from collapsing by THP.
+ */
+ pagevec_add(&pvec, page);
+ zone = page_zone(page);
+ zoneid = page_zone_id(page);
- /*
- * Try to fill the rest of pagevec using fast
- * pte walk. This will also update start to
- * the next page to process. Then munlock the
- * pagevec.
- */
- start = __munlock_pagevec_fill(&pvec, vma,
- zoneid, start, end);
- __munlock_pagevec(&pvec, zone);
- goto next;
- }
+ /*
+ * Try to fill the rest of pagevec using fast
+ * pte walk. This will also update start to
+ * the next page to process. Then munlock the
+ * pagevec.
+ */
+ start = __munlock_pagevec_fill(&pvec, vma,
+ zoneid, start, end);
+ __munlock_pagevec(&pvec, zone);
+ goto next;
}
/* It's a bug to munlock in the middle of a THP page */
VM_BUG_ON((start >> PAGE_SHIFT) & page_mask);