mm: numa: do not trap faults on the huge zero page

Faults on the huge zero page are pointless and there is a BUG_ON to catch
them during fault time.  This patch reintroduces a check that avoids
marking the zero page PAGE_NONE.

Signed-off-by: Mel Gorman <mgorman@suse.de>
Cc: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Dave Jones <davej@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Kirill Shutemov <kirill.shutemov@linux.intel.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Rik van Riel <riel@redhat.com>
Cc: Sasha Levin <sasha.levin@oracle.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

3 files changed, 25 insertions, 3 deletions

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index cb9b3e847dac..8e791a3db6b6 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1471,7 +1471,7 @@ out:
  *  - 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)
+                unsigned long addr, pgprot_t newprot, int prot_numa)
 {
         struct mm_struct *mm = vma->vm_mm;
         spinlock_t *ptl;
@@ -1479,6 +1479,17 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
 
         if (__pmd_trans_huge_lock(pmd, vma, &ptl) == 1) {
                 pmd_t entry;
+
+                /*
+                 * Avoid trapping faults against the zero page. The read-only
+                 * data is likely to be read-cached on the local CPU and
+                 * local/remote hits to the zero page are not interesting.
+                 */
+                if (prot_numa && is_huge_zero_pmd(*pmd)) {
+                        spin_unlock(ptl);
+                        return 0;
+                }
+
                 ret = 1;
                 entry = pmdp_get_and_clear_notify(mm, addr, pmd);
                 entry = pmd_modify(entry, newprot);
diff --git a/mm/memory.c b/mm/memory.c
index d7921760cf79..bf244f56b05a 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3040,7 +3040,6 @@ static int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
                 pte_unmap_unlock(ptep, ptl);
                 return 0;
         }
-        BUG_ON(is_zero_pfn(page_to_pfn(page)));
 
         /*
          * Avoid grouping on DSO/COW pages in specific and RO pages
diff --git a/mm/mprotect.c b/mm/mprotect.c
index 76824d73380d..dd599fc235c2 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -76,6 +76,18 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
                 if (pte_present(oldpte)) {
                         pte_t ptent;
 
+                        /*
+                         * Avoid trapping faults against the zero or KSM
+                         * pages. See similar comment in change_huge_pmd.
+                         */
+                        if (prot_numa) {
+                                struct page *page;
+
+                                page = vm_normal_page(vma, addr, oldpte);
+                                if (!page || PageKsm(page))
+                                        continue;
+                        }
+
                         ptent = ptep_modify_prot_start(mm, addr, pte);
                         ptent = pte_modify(ptent, newprot);
 
@@ -142,7 +154,7 @@ static inline unsigned long change_pmd_range(struct vm_area_struct *vma,
                                 split_huge_page_pmd(vma, addr, pmd);
                         else {
                                 int nr_ptes = change_huge_pmd(vma, pmd, addr,
-                                                newprot);
+                                                newprot, prot_numa);
 
                                 if (nr_ptes) {
                                         if (nr_ptes == HPAGE_PMD_NR) {