mm: numa: Migrate pages handled during a pmd_numa hinting fault

To say that the PMD handling code was incorrectly transferred from autonuma
is an understatement. The intention was to handle a PMDs worth of pages
in the same fault and effectively batch the taking of the PTL and page
migration. The copied version instead has the impact of clearing a number
of pte_numa PTE entries and whether any page migration takes place depends
on racing. This just happens to work in some cases.

This patch handles pte_numa faults in batch when a pmd_numa fault is
handled. The pages are migrated if they are currently misplaced.
Essentially this is making an assumption that NUMA locality is
on a PMD boundary but that could be addressed by only setting
pmd_numa if all the pages within that PMD are on the same node
if necessary.

Signed-off-by: Mel Gorman <mgorman@suse.de>

1 files changed, 20 insertions, 5 deletions

diff --git a/mm/mprotect.c b/mm/mprotect.c
index 7ef6ae964e8f..dce6fb48edc4 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -37,12 +37,14 @@ static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot)
 
 static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
 		unsigned long addr, unsigned long end, pgprot_t newprot,
-		int dirty_accountable, int prot_numa)
+		int dirty_accountable, int prot_numa, bool *ret_all_same_node)
 {
 	struct mm_struct *mm = vma->vm_mm;
 	pte_t *pte, oldpte;
 	spinlock_t *ptl;
 	unsigned long pages = 0;
+	bool all_same_node = true;
+	int last_nid = -1;
 
 	pte = pte_offset_map_lock(mm, pmd, addr, &ptl);
 	arch_enter_lazy_mmu_mode();
@@ -61,6 +63,12 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
 
 				page = vm_normal_page(vma, addr, oldpte);
 				if (page) {
+					int this_nid = page_to_nid(page);
+					if (last_nid == -1)
+						last_nid = this_nid;
+					if (last_nid != this_nid)
+						all_same_node = false;
+
 					/* only check non-shared pages */
 					if (!pte_numa(oldpte) &&
 					    page_mapcount(page) == 1) {
@@ -81,7 +89,6 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
 
 			if (updated)
 				pages++;
-
 			ptep_modify_prot_commit(mm, addr, pte, ptent);
 		} else if (IS_ENABLED(CONFIG_MIGRATION) && !pte_file(oldpte)) {
 			swp_entry_t entry = pte_to_swp_entry(oldpte);
@@ -101,6 +108,7 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
 	arch_leave_lazy_mmu_mode();
 	pte_unmap_unlock(pte - 1, ptl);
 
+	*ret_all_same_node = all_same_node;
 	return pages;
 }
 
@@ -127,6 +135,7 @@ static inline unsigned long change_pmd_range(struct vm_area_struct *vma, pud_t *
 	pmd_t *pmd;
 	unsigned long next;
 	unsigned long pages = 0;
+	bool all_same_node;
 
 	pmd = pmd_offset(pud, addr);
 	do {
@@ -143,9 +152,15 @@ static inline unsigned long change_pmd_range(struct vm_area_struct *vma, pud_t *
 		if (pmd_none_or_clear_bad(pmd))
 			continue;
 		pages += change_pte_range(vma, pmd, addr, next, newprot,
-				 dirty_accountable, prot_numa);
-
-		if (prot_numa)
+				 dirty_accountable, prot_numa, &all_same_node);
+
+		/*
+		 * If we are changing protections for NUMA hinting faults then
+		 * set pmd_numa if the examined pages were all on the same
+		 * node. This allows a regular PMD to be handled as one fault
+		 * and effectively batches the taking of the PTL
+		 */
+		if (prot_numa && all_same_node)
 			change_pmd_protnuma(vma->vm_mm, addr, pmd);
 	} while (pmd++, addr = next, addr != end);