[PATCH 3.8 102/152] mm: Only flush TLBs if a transhuge PMD is modified for NUMA pte scanning

[Kamal Mostafa]

3.8.13.14 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Mel Gorman <mgorman at suse.de>

commit f123d74abf91574837d14e5ea58f6a779a387bf5 upstream.

NUMA PTE scanning is expensive both in terms of the scanning itself and
the TLB flush if there are any updates. The TLB flush is avoided if no
PTEs are updated but there is a bug where transhuge PMDs are considered
to be updated even if they were already pmd_numa. This patch addresses
the problem and TLB flushes should be reduced.

Cc: Andrea Arcangeli <aarcange at redhat.com>
Cc: Johannes Weiner <hannes at cmpxchg.org>
Cc: Srikar Dronamraju <srikar at linux.vnet.ibm.com>
Reviewed-by: Rik van Riel <riel at redhat.com>
Signed-off-by: Mel Gorman <mgorman at suse.de>
Signed-off-by: Peter Zijlstra <peterz at infradead.org>
Link: http://lkml.kernel.org/r/1381141781-10992-12-git-send-email-mgorman@suse.de
Signed-off-by: Ingo Molnar <mingo at kernel.org>
[ kamal: 3.8 stable prereq for
  72403b4 mm: numa: return the number of base pages altered by protection changes ]
Signed-off-by: Kamal Mostafa <kamal at canonical.com>
---
 mm/huge_memory.c | 19 ++++++++++++++++---
 mm/mprotect.c    | 14 ++++++++++----
 2 files changed, 26 insertions(+), 7 deletions(-)

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 9c37776..9d0b5f5 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1472,6 +1472,12 @@ out:
 	return ret;
 }
 
+/*
+ * Returns
+ *  - 0 if PMD could not be locked
+ *  - 1 if PMD was locked but protections unchange and TLB flush unnecessary
+ *  - HPAGE_PMD_NR is protections changed and TLB flush necessary
+ */
 int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
 		unsigned long addr, pgprot_t newprot, int prot_numa)
 {
@@ -1480,9 +1486,11 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
 
 	if (__pmd_trans_huge_lock(pmd, vma) == 1) {
 		pmd_t entry;
-		entry = pmdp_get_and_clear(mm, addr, pmd);
+		ret = 1;
 		if (!prot_numa) {
+			entry = pmdp_get_and_clear(mm, addr, pmd);
 			entry = pmd_modify(entry, newprot);
+			ret = HPAGE_PMD_NR;
 			BUG_ON(pmd_write(entry));
 		} else {
 			struct page *page = pmd_page(*pmd);
@@ -1490,12 +1498,17 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
 			/* only check non-shared pages */
 			if (page_mapcount(page) == 1 &&
 			    !pmd_numa(*pmd)) {
+				entry = pmdp_get_and_clear(mm, addr, pmd);
 				entry = pmd_mknuma(entry);
+				ret = HPAGE_PMD_NR;
 			}
 		}
-		set_pmd_at(mm, addr, pmd, entry);
+
+		/* Set PMD if cleared earlier */
+		if (ret == HPAGE_PMD_NR)
+			set_pmd_at(mm, addr, pmd, entry);
+
 		spin_unlock(&vma->vm_mm->page_table_lock);
-		ret = 1;
 	}
 
 	return ret;
diff --git a/mm/mprotect.c b/mm/mprotect.c
index 2bbb648..16a42b2 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -143,10 +143,16 @@ static inline unsigned long change_pmd_range(struct vm_area_struct *vma,
 		if (pmd_trans_huge(*pmd)) {
 			if (next - addr != HPAGE_PMD_SIZE)
 				split_huge_page_pmd(vma, addr, pmd);
-			else if (change_huge_pmd(vma, pmd, addr, newprot,
-						 prot_numa)) {
-				pages++;
-				continue;
+			else {
+				int nr_ptes = change_huge_pmd(vma, pmd, addr,
+						newprot, prot_numa);
+
+				if (nr_ptes) {
+					if (nr_ptes == HPAGE_PMD_NR)
+						pages++;
+
+					continue;
+				}
 			}
 			/* fall through */
 		}
-- 
1.8.3.2