mm: numa: avoid unnecessary TLB flushes when setting NUMA hinting entries

If a PTE or PMD is already marked NUMA when scanning to mark entries for
NUMA hinting then it is not necessary to update the entry and incur a TLB
flush penalty.  Avoid the avoidhead where possible.

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>

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 8e07342b52c0406982e3cdd2e747c4f18a9efe01..fc00c8cb5a82ee89addf4d2ee8983894bf6aa5d1 100644 (file)
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1493,12 +1493,14 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
                        return 0;
                }
 
-               ret = 1;
-               entry = pmdp_get_and_clear_notify(mm, addr, pmd);
-               entry = pmd_modify(entry, newprot);
-               ret = HPAGE_PMD_NR;
-               set_pmd_at(mm, addr, pmd, entry);
-               BUG_ON(pmd_write(entry));
+               if (!prot_numa || !pmd_protnone(*pmd)) {
+                       ret = 1;
+                       entry = pmdp_get_and_clear_notify(mm, addr, pmd);
+                       entry = pmd_modify(entry, newprot);
+                       ret = HPAGE_PMD_NR;
+                       set_pmd_at(mm, addr, pmd, entry);
+                       BUG_ON(pmd_write(entry));
+               }
                spin_unlock(ptl);
        }
 

diff --git a/mm/mprotect.c b/mm/mprotect.c
index dd599fc235c2fe5ce483128bb89dfad29dc104cd..44727811bf4cf62e3579261ee9699a37fab78b3d 100644 (file)
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -86,6 +86,10 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
                                page = vm_normal_page(vma, addr, oldpte);
                                if (!page || PageKsm(page))
                                        continue;
+
+                               /* Avoid TLB flush if possible */
+                               if (pte_protnone(oldpte))
+                                       continue;
                        }
 
                        ptent = ptep_modify_prot_start(mm, addr, pte);