mm: numa: Add fault driven placement and migration

NOTE: This patch is based on "sched, numa, mm: Add fault driven
	placement and migration policy" but as it throws away all the policy
	to just leave a basic foundation I had to drop the signed-offs-by.

This patch creates a bare-bones method for setting PTEs pte_numa in the
context of the scheduler that when faulted later will be faulted onto the
node the CPU is running on.  In itself this does nothing useful but any
placement policy will fundamentally depend on receiving hints on placement
from fault context and doing something intelligent about it.

Signed-off-by: Mel Gorman <mgorman@suse.de>
Acked-by: Rik van Riel <riel@redhat.com>

2 files changed, 17 insertions, 2 deletions

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index d79f7a55bf6f..ee8133794a56 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1046,6 +1046,7 @@ int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
          */
         split_huge_page(page);
         put_page(page);
+
         return 0;
 
 clear_pmdnuma:
@@ -1060,8 +1061,10 @@ clear_pmdnuma:
 
 out_unlock:
         spin_unlock(&mm->page_table_lock);
-        if (page)
+        if (page) {
                 put_page(page);
+                task_numa_fault(numa_node_id(), HPAGE_PMD_NR);
+        }
         return 0;
 }
 
diff --git a/mm/memory.c b/mm/memory.c
index d52542680e10..8012c1907895 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3454,7 +3454,8 @@ int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 {
         struct page *page = NULL;
         spinlock_t *ptl;
-        int current_nid, target_nid;
+        int current_nid = -1;
+        int target_nid;
 
         /*
         * The "pte" at this point cannot be used safely without
@@ -3501,6 +3502,7 @@ int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
                 current_nid = target_nid;
 
 out:
+        task_numa_fault(current_nid, 1);
         return 0;
 }
 
@@ -3537,6 +3539,7 @@ static int do_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
         for (addr = _addr + offset; addr < _addr + PMD_SIZE; pte++, addr += PAGE_SIZE) {
                 pte_t pteval = *pte;
                 struct page *page;
+                int curr_nid;
                 if (!pte_present(pteval))
                         continue;
                 if (!pte_numa(pteval))
@@ -3554,6 +3557,15 @@ static int do_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
                 page = vm_normal_page(vma, addr, pteval);
                 if (unlikely(!page))
                         continue;
+                /* only check non-shared pages */
+                if (unlikely(page_mapcount(page) != 1))
+                        continue;
+                pte_unmap_unlock(pte, ptl);
+
+                curr_nid = page_to_nid(page);
+                task_numa_fault(curr_nid, 1);
+
+                pte = pte_offset_map_lock(mm, pmdp, addr, &ptl);
         }
         pte_unmap_unlock(orig_pte, ptl);