mm: mempolicy: Use _PAGE_NUMA to migrate pages

Note: Based on "mm/mpol: Use special PROT_NONE to migrate pages" but
	sufficiently different that the signed-off-bys were dropped

Combine our previous _PAGE_NUMA, mpol_misplaced and migrate_misplaced_page()
pieces into an effective migrate on fault scheme.

Note that (on x86) we rely on PROT_NONE pages being !present and avoid
the TLB flush from try_to_unmap(TTU_MIGRATION). This greatly improves the
page-migration performance.

Based-on-work-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Mel Gorman <mgorman@suse.de>

1 files changed, 28 insertions, 3 deletions

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index f5f3763..5723b55 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -18,6 +18,7 @@
 #include <linux/freezer.h>
 #include <linux/mman.h>
 #include <linux/pagemap.h>
+#include <linux/migrate.h>
 #include <asm/tlb.h>
 #include <asm/pgalloc.h>
 #include "internal.h"
@@ -1019,17 +1020,39 @@ out:
 }
 
 /* NUMA hinting page fault entry point for trans huge pmds */
-int do_huge_pmd_numa_page(struct mm_struct *mm, unsigned long addr,
-				pmd_t pmd, pmd_t *pmdp)
+int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
+				unsigned long addr, pmd_t pmd, pmd_t *pmdp)
 {
-	struct page *page;
+	struct page *page = NULL;
 	unsigned long haddr = addr & HPAGE_PMD_MASK;
+	int target_nid;
 
 	spin_lock(&mm->page_table_lock);
 	if (unlikely(!pmd_same(pmd, *pmdp)))
 		goto out_unlock;
 
 	page = pmd_page(pmd);
+	get_page(page);
+	spin_unlock(&mm->page_table_lock);
+
+	target_nid = mpol_misplaced(page, vma, haddr);
+	if (target_nid == -1)
+		goto clear_pmdnuma;
+
+	/*
+	 * Due to lacking code to migrate thp pages, we'll split
+	 * (which preserves the special PROT_NONE) and re-take the
+	 * fault on the normal pages.
+	 */
+	split_huge_page(page);
+	put_page(page);
+	return 0;
+
+clear_pmdnuma:
+	spin_lock(&mm->page_table_lock);
+	if (unlikely(!pmd_same(pmd, *pmdp)))
+		goto out_unlock;
+
 	pmd = pmd_mknonnuma(pmd);
 	set_pmd_at(mm, haddr, pmdp, pmd);
 	VM_BUG_ON(pmd_numa(*pmdp));
@@ -1037,6 +1060,8 @@ int do_huge_pmd_numa_page(struct mm_struct *mm, unsigned long addr,
 
 out_unlock:
 	spin_unlock(&mm->page_table_lock);
+	if (page)
+		put_page(page);
 	return 0;
 }