1 files changed, 34 insertions, 48 deletions

diff --git a/mm/mprotect.c b/mm/mprotect.c
index 412ba2b7326..bb53a6591ae 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -37,14 +37,12 @@ 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, bool *ret_all_same_node)
+		int dirty_accountable, int prot_numa)
 {
 	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();
@@ -54,25 +52,21 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
 			pte_t ptent;
 			bool updated = false;
 
-			ptent = ptep_modify_prot_start(mm, addr, pte);
 			if (!prot_numa) {
+				ptent = ptep_modify_prot_start(mm, addr, pte);
+				if (pte_numa(ptent))
+					ptent = pte_mknonnuma(ptent);
 				ptent = pte_modify(ptent, newprot);
 				updated = true;
 			} else {
 				struct page *page;
 
+				ptent = *pte;
 				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) {
+					if (!pte_numa(oldpte)) {
 						ptent = pte_mknuma(ptent);
+						set_pte_at(mm, addr, pte, ptent);
 						updated = true;
 					}
 				}
@@ -89,7 +83,10 @@ 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);
+
+			/* Only !prot_numa always clears the pte */
+			if (!prot_numa)
+				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);
 
@@ -104,33 +101,17 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
 				if (pte_swp_soft_dirty(oldpte))
 					newpte = pte_swp_mksoft_dirty(newpte);
 				set_pte_at(mm, addr, pte, newpte);
+
+				pages++;
 			}
-			pages++;
 		}
 	} while (pte++, addr += PAGE_SIZE, addr != end);
 	arch_leave_lazy_mmu_mode();
 	pte_unmap_unlock(pte - 1, ptl);
 
-	*ret_all_same_node = all_same_node;
 	return pages;
 }
 
-#ifdef CONFIG_NUMA_BALANCING
-static inline void change_pmd_protnuma(struct mm_struct *mm, unsigned long addr,
-				       pmd_t *pmd)
-{
-	spin_lock(&mm->page_table_lock);
-	set_pmd_at(mm, addr & PMD_MASK, pmd, pmd_mknuma(*pmd));
-	spin_unlock(&mm->page_table_lock);
-}
-#else
-static inline void change_pmd_protnuma(struct mm_struct *mm, unsigned long addr,
-				       pmd_t *pmd)
-{
-	BUG();
-}
-#endif /* CONFIG_NUMA_BALANCING */
-
 static inline unsigned long change_pmd_range(struct vm_area_struct *vma,
 		pud_t *pud, unsigned long addr, unsigned long end,
 		pgprot_t newprot, int dirty_accountable, int prot_numa)
@@ -138,36 +119,39 @@ static inline unsigned long change_pmd_range(struct vm_area_struct *vma,
 	pmd_t *pmd;
 	unsigned long next;
 	unsigned long pages = 0;
-	bool all_same_node;
+	unsigned long nr_huge_updates = 0;
 
 	pmd = pmd_offset(pud, addr);
 	do {
+		unsigned long this_pages;
+
 		next = pmd_addr_end(addr, end);
 		if (pmd_trans_huge(*pmd)) {
 			if (next - addr != HPAGE_PMD_SIZE)
 				split_huge_page_pmd(vma, addr, pmd);
-			else if (change_huge_pmd(vma, pmd, addr, newprot,
-						 prot_numa)) {
-				pages++;
-				continue;
+			else {
+				int nr_ptes = change_huge_pmd(vma, pmd, addr,
+						newprot, prot_numa);
+
+				if (nr_ptes) {
+					if (nr_ptes == HPAGE_PMD_NR) {
+						pages += HPAGE_PMD_NR;
+						nr_huge_updates++;
+					}
+					continue;
+				}
 			}
 			/* fall through */
 		}
 		if (pmd_none_or_clear_bad(pmd))
 			continue;
-		pages += change_pte_range(vma, pmd, addr, next, newprot,
-				 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);
+		this_pages = change_pte_range(vma, pmd, addr, next, newprot,
+				 dirty_accountable, prot_numa);
+		pages += this_pages;
 	} while (pmd++, addr = next, addr != end);
 
+	if (nr_huge_updates)
+		count_vm_numa_events(NUMA_HUGE_PTE_UPDATES, nr_huge_updates);
 	return pages;
 }
 
@@ -204,6 +188,7 @@ static unsigned long change_protection_range(struct vm_area_struct *vma,
 	BUG_ON(addr >= end);
 	pgd = pgd_offset(mm, addr);
 	flush_cache_range(vma, addr, end);
+	set_tlb_flush_pending(mm);
 	do {
 		next = pgd_addr_end(addr, end);
 		if (pgd_none_or_clear_bad(pgd))
@@ -215,6 +200,7 @@ static unsigned long change_protection_range(struct vm_area_struct *vma,
 	/* Only flush the TLB if we actually modified any entries: */
 	if (pages)
 		flush_tlb_range(vma, start, end);
+	clear_tlb_flush_pending(mm);
 
 	return pages;
 }