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

[deliverable/linux.git] / mm / huge_memory.c

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index cb9b3e847dac65ad9d0695c42e606a2ae74df743..8e791a3db6b6804987ae587feff95c79ac940480 100644 (file)
--- 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);