Merge branch 'akpm' (patches from Andrew)

Merge misc fixes from Andrew Morton:
 "10 patches.

  Subsystems affected by this patch series: ipc, MAINTAINERS, and mm
  (vmscan, debug, pagemap, kmemleak, and selftests)"

* emailed patches from Andrew Morton <akpm@linux-foundation.org>:
  kselftest/vm: revert "tools/testing/selftests/vm/userfaultfd.c: use swap() to make code cleaner"
  MAINTAINERS: update rppt's email
  mm/kmemleak: avoid scanning potential huge holes
  ipc/sem: do not sleep with a spin lock held
  mm/pgtable: define pte_index so that preprocessor could recognize it
  mm/page_table_check: check entries at pmd levels
  mm/khugepaged: unify collapse pmd clear, flush and free
  mm/page_table_check: use unsigned long for page counters and cleanup
  mm/debug_vm_pgtable: remove pte entry from the page table
  Revert "mm/page_isolation: unset migratetype directly for non Buddy page"

10 files changed, 88 insertions, 56 deletions

diff --git a/MAINTAINERS b/MAINTAINERS
index bb83dcbcb619..ce6dff39fc14 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -12399,7 +12399,7 @@ F:	include/uapi/linux/membarrier.h
 F:	kernel/sched/membarrier.c
 
 MEMBLOCK
-M:	Mike Rapoport <rppt@linux.ibm.com>
+M:	Mike Rapoport <rppt@kernel.org>
 L:	linux-mm@kvack.org
 S:	Maintained
 F:	Documentation/core-api/boot-time-mm.rst
diff --git a/include/linux/page_table_check.h b/include/linux/page_table_check.h
index 38cace1da7b6..01e16c7696ec 100644
--- a/include/linux/page_table_check.h
+++ b/include/linux/page_table_check.h
@@ -26,6 +26,9 @@ void __page_table_check_pmd_set(struct mm_struct *mm, unsigned long addr,
 				pmd_t *pmdp, pmd_t pmd);
 void __page_table_check_pud_set(struct mm_struct *mm, unsigned long addr,
 				pud_t *pudp, pud_t pud);
+void __page_table_check_pte_clear_range(struct mm_struct *mm,
+					unsigned long addr,
+					pmd_t pmd);
 
 static inline void page_table_check_alloc(struct page *page, unsigned int order)
 {
@@ -100,6 +103,16 @@ static inline void page_table_check_pud_set(struct mm_struct *mm,
 	__page_table_check_pud_set(mm, addr, pudp, pud);
 }
 
+static inline void page_table_check_pte_clear_range(struct mm_struct *mm,
+						    unsigned long addr,
+						    pmd_t pmd)
+{
+	if (static_branch_likely(&page_table_check_disabled))
+		return;
+
+	__page_table_check_pte_clear_range(mm, addr, pmd);
+}
+
 #else
 
 static inline void page_table_check_alloc(struct page *page, unsigned int order)
@@ -143,5 +156,11 @@ static inline void page_table_check_pud_set(struct mm_struct *mm,
 {
 }
 
+static inline void page_table_check_pte_clear_range(struct mm_struct *mm,
+						    unsigned long addr,
+						    pmd_t pmd)
+{
+}
+
 #endif /* CONFIG_PAGE_TABLE_CHECK */
 #endif /* __LINUX_PAGE_TABLE_CHECK_H */
diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h
index bc8713a76e03..f4f4077b97aa 100644
--- a/include/linux/pgtable.h
+++ b/include/linux/pgtable.h
@@ -62,6 +62,7 @@ static inline unsigned long pte_index(unsigned long address)
 {
 	return (address >> PAGE_SHIFT) & (PTRS_PER_PTE - 1);
 }
+#define pte_index pte_index
 
 #ifndef pmd_index
 static inline unsigned long pmd_index(unsigned long address)
diff --git a/ipc/sem.c b/ipc/sem.c
index 6693daf4fe11..0dbdb98fdf2d 100644
--- a/ipc/sem.c
+++ b/ipc/sem.c
@@ -1964,6 +1964,7 @@ static struct sem_undo *find_alloc_undo(struct ipc_namespace *ns, int semid)
 	 */
 	un = lookup_undo(ulp, semid);
 	if (un) {
+		spin_unlock(&ulp->lock);
 		kvfree(new);
 		goto success;
 	}
@@ -1976,9 +1977,8 @@ static struct sem_undo *find_alloc_undo(struct ipc_namespace *ns, int semid)
 	ipc_assert_locked_object(&sma->sem_perm);
 	list_add(&new->list_id, &sma->list_id);
 	un = new;
-
-success:
 	spin_unlock(&ulp->lock);
+success:
 	sem_unlock(sma, -1);
 out:
 	return un;
diff --git a/mm/debug_vm_pgtable.c b/mm/debug_vm_pgtable.c
index a7ac97c76762..db2abd9e415b 100644
--- a/mm/debug_vm_pgtable.c
+++ b/mm/debug_vm_pgtable.c
@@ -171,6 +171,8 @@ static void __init pte_advanced_tests(struct pgtable_debug_args *args)
 	ptep_test_and_clear_young(args->vma, args->vaddr, args->ptep);
 	pte = ptep_get(args->ptep);
 	WARN_ON(pte_young(pte));
+
+	ptep_get_and_clear_full(args->mm, args->vaddr, args->ptep, 1);
 }
 
 static void __init pte_savedwrite_tests(struct pgtable_debug_args *args)
diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index 35f14d0a00a6..131492fd1148 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -16,6 +16,7 @@
 #include <linux/hashtable.h>
 #include <linux/userfaultfd_k.h>
 #include <linux/page_idle.h>
+#include <linux/page_table_check.h>
 #include <linux/swapops.h>
 #include <linux/shmem_fs.h>
 
@@ -1416,6 +1417,21 @@ static int khugepaged_add_pte_mapped_thp(struct mm_struct *mm,
 	return 0;
 }
 
+static void collapse_and_free_pmd(struct mm_struct *mm, struct vm_area_struct *vma,
+				  unsigned long addr, pmd_t *pmdp)
+{
+	spinlock_t *ptl;
+	pmd_t pmd;
+
+	mmap_assert_write_locked(mm);
+	ptl = pmd_lock(vma->vm_mm, pmdp);
+	pmd = pmdp_collapse_flush(vma, addr, pmdp);
+	spin_unlock(ptl);
+	mm_dec_nr_ptes(mm);
+	page_table_check_pte_clear_range(mm, addr, pmd);
+	pte_free(mm, pmd_pgtable(pmd));
+}
+
 /**
  * collapse_pte_mapped_thp - Try to collapse a pte-mapped THP for mm at
  * address haddr.
@@ -1433,7 +1449,7 @@ void collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr)
 	struct vm_area_struct *vma = find_vma(mm, haddr);
 	struct page *hpage;
 	pte_t *start_pte, *pte;
-	pmd_t *pmd, _pmd;
+	pmd_t *pmd;
 	spinlock_t *ptl;
 	int count = 0;
 	int i;
@@ -1509,12 +1525,7 @@ void collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr)
 	}
 
 	/* step 4: collapse pmd */
-	ptl = pmd_lock(vma->vm_mm, pmd);
-	_pmd = pmdp_collapse_flush(vma, haddr, pmd);
-	spin_unlock(ptl);
-	mm_dec_nr_ptes(mm);
-	pte_free(mm, pmd_pgtable(_pmd));
-
+	collapse_and_free_pmd(mm, vma, haddr, pmd);
 drop_hpage:
 	unlock_page(hpage);
 	put_page(hpage);
@@ -1552,7 +1563,7 @@ static void retract_page_tables(struct address_space *mapping, pgoff_t pgoff)
 	struct vm_area_struct *vma;
 	struct mm_struct *mm;
 	unsigned long addr;
-	pmd_t *pmd, _pmd;
+	pmd_t *pmd;
 
 	i_mmap_lock_write(mapping);
 	vma_interval_tree_foreach(vma, &mapping->i_mmap, pgoff, pgoff) {
@@ -1591,14 +1602,8 @@ static void retract_page_tables(struct address_space *mapping, pgoff_t pgoff)
 		 * reverse order. Trylock is a way to avoid deadlock.
 		 */
 		if (mmap_write_trylock(mm)) {
-			if (!khugepaged_test_exit(mm)) {
-				spinlock_t *ptl = pmd_lock(mm, pmd);
-				/* assume page table is clear */
-				_pmd = pmdp_collapse_flush(vma, addr, pmd);
-				spin_unlock(ptl);
-				mm_dec_nr_ptes(mm);
-				pte_free(mm, pmd_pgtable(_pmd));
-			}
+			if (!khugepaged_test_exit(mm))
+				collapse_and_free_pmd(mm, vma, addr, pmd);
 			mmap_write_unlock(mm);
 		} else {
 			/* Try again later */
diff --git a/mm/kmemleak.c b/mm/kmemleak.c
index dc3758fdba68..7580baa76af1 100644
--- a/mm/kmemleak.c
+++ b/mm/kmemleak.c
@@ -1410,7 +1410,8 @@ static void kmemleak_scan(void)
 {
 	unsigned long flags;
 	struct kmemleak_object *object;
-	int i;
+	struct zone *zone;
+	int __maybe_unused i;
 	int new_leaks = 0;
 
 	jiffies_last_scan = jiffies;
@@ -1450,9 +1451,9 @@ static void kmemleak_scan(void)
 	 * Struct page scanning for each node.
 	 */
 	get_online_mems();
-	for_each_online_node(i) {
-		unsigned long start_pfn = node_start_pfn(i);
-		unsigned long end_pfn = node_end_pfn(i);
+	for_each_populated_zone(zone) {
+		unsigned long start_pfn = zone->zone_start_pfn;
+		unsigned long end_pfn = zone_end_pfn(zone);
 		unsigned long pfn;
 
 		for (pfn = start_pfn; pfn < end_pfn; pfn++) {
@@ -1461,8 +1462,8 @@ static void kmemleak_scan(void)
 			if (!page)
 				continue;
 
-			/* only scan pages belonging to this node */
-			if (page_to_nid(page) != i)
+			/* only scan pages belonging to this zone */
+			if (page_zone(page) != zone)
 				continue;
 			/* only scan if page is in use */
 			if (page_count(page) == 0)
diff --git a/mm/page_isolation.c b/mm/page_isolation.c
index 6a0ddda6b3c5..f67c4c70f17f 100644
--- a/mm/page_isolation.c
+++ b/mm/page_isolation.c
@@ -115,7 +115,7 @@ static void unset_migratetype_isolate(struct page *page, unsigned migratetype)
 	 * onlining - just onlined memory won't immediately be considered for
 	 * allocation.
 	 */
-	if (!isolated_page && PageBuddy(page)) {
+	if (!isolated_page) {
 		nr_pages = move_freepages_block(zone, page, migratetype, NULL);
 		__mod_zone_freepage_state(zone, nr_pages, migratetype);
 	}
diff --git a/mm/page_table_check.c b/mm/page_table_check.c
index 7504e7caa2a1..3763bd077861 100644
--- a/mm/page_table_check.c
+++ b/mm/page_table_check.c
@@ -86,8 +86,8 @@ static void page_table_check_clear(struct mm_struct *mm, unsigned long addr,
 {
 	struct page_ext *page_ext;
 	struct page *page;
+	unsigned long i;
 	bool anon;
-	int i;
 
 	if (!pfn_valid(pfn))
 		return;
@@ -121,8 +121,8 @@ static void page_table_check_set(struct mm_struct *mm, unsigned long addr,
 {
 	struct page_ext *page_ext;
 	struct page *page;
+	unsigned long i;
 	bool anon;
-	int i;
 
 	if (!pfn_valid(pfn))
 		return;
@@ -152,10 +152,10 @@ static void page_table_check_set(struct mm_struct *mm, unsigned long addr,
 void __page_table_check_zero(struct page *page, unsigned int order)
 {
 	struct page_ext *page_ext = lookup_page_ext(page);
-	int i;
+	unsigned long i;
 
 	BUG_ON(!page_ext);
-	for (i = 0; i < (1 << order); i++) {
+	for (i = 0; i < (1ul << order); i++) {
 		struct page_table_check *ptc = get_page_table_check(page_ext);
 
 		BUG_ON(atomic_read(&ptc->anon_map_count));
@@ -206,17 +206,10 @@ EXPORT_SYMBOL(__page_table_check_pud_clear);
 void __page_table_check_pte_set(struct mm_struct *mm, unsigned long addr,
 				pte_t *ptep, pte_t pte)
 {
-	pte_t old_pte;
-
 	if (&init_mm == mm)
 		return;
 
-	old_pte = *ptep;
-	if (pte_user_accessible_page(old_pte)) {
-		page_table_check_clear(mm, addr, pte_pfn(old_pte),
-				       PAGE_SIZE >> PAGE_SHIFT);
-	}
-
+	__page_table_check_pte_clear(mm, addr, *ptep);
 	if (pte_user_accessible_page(pte)) {
 		page_table_check_set(mm, addr, pte_pfn(pte),
 				     PAGE_SIZE >> PAGE_SHIFT,
@@ -228,17 +221,10 @@ EXPORT_SYMBOL(__page_table_check_pte_set);
 void __page_table_check_pmd_set(struct mm_struct *mm, unsigned long addr,
 				pmd_t *pmdp, pmd_t pmd)
 {
-	pmd_t old_pmd;
-
 	if (&init_mm == mm)
 		return;
 
-	old_pmd = *pmdp;
-	if (pmd_user_accessible_page(old_pmd)) {
-		page_table_check_clear(mm, addr, pmd_pfn(old_pmd),
-				       PMD_PAGE_SIZE >> PAGE_SHIFT);
-	}
-
+	__page_table_check_pmd_clear(mm, addr, *pmdp);
 	if (pmd_user_accessible_page(pmd)) {
 		page_table_check_set(mm, addr, pmd_pfn(pmd),
 				     PMD_PAGE_SIZE >> PAGE_SHIFT,
@@ -250,17 +236,10 @@ EXPORT_SYMBOL(__page_table_check_pmd_set);
 void __page_table_check_pud_set(struct mm_struct *mm, unsigned long addr,
 				pud_t *pudp, pud_t pud)
 {
-	pud_t old_pud;
-
 	if (&init_mm == mm)
 		return;
 
-	old_pud = *pudp;
-	if (pud_user_accessible_page(old_pud)) {
-		page_table_check_clear(mm, addr, pud_pfn(old_pud),
-				       PUD_PAGE_SIZE >> PAGE_SHIFT);
-	}
-
+	__page_table_check_pud_clear(mm, addr, *pudp);
 	if (pud_user_accessible_page(pud)) {
 		page_table_check_set(mm, addr, pud_pfn(pud),
 				     PUD_PAGE_SIZE >> PAGE_SHIFT,
@@ -268,3 +247,23 @@ void __page_table_check_pud_set(struct mm_struct *mm, unsigned long addr,
 	}
 }
 EXPORT_SYMBOL(__page_table_check_pud_set);
+
+void __page_table_check_pte_clear_range(struct mm_struct *mm,
+					unsigned long addr,
+					pmd_t pmd)
+{
+	if (&init_mm == mm)
+		return;
+
+	if (!pmd_bad(pmd) && !pmd_leaf(pmd)) {
+		pte_t *ptep = pte_offset_map(&pmd, addr);
+		unsigned long i;
+
+		pte_unmap(ptep);
+		for (i = 0; i < PTRS_PER_PTE; i++) {
+			__page_table_check_pte_clear(mm, addr, *ptep);
+			addr += PAGE_SIZE;
+			ptep++;
+		}
+	}
+}
diff --git a/tools/testing/selftests/vm/userfaultfd.c b/tools/testing/selftests/vm/userfaultfd.c
index d3fd24f9fae8..2f49c9af1b58 100644
--- a/tools/testing/selftests/vm/userfaultfd.c
+++ b/tools/testing/selftests/vm/userfaultfd.c
@@ -1417,6 +1417,7 @@ static void userfaultfd_pagemap_test(unsigned int test_pgsize)
 static int userfaultfd_stress(void)
 {
 	void *area;
+	char *tmp_area;
 	unsigned long nr;
 	struct uffdio_register uffdio_register;
 	struct uffd_stats uffd_stats[nr_cpus];
@@ -1527,9 +1528,13 @@ static int userfaultfd_stress(void)
 					    count_verify[nr], nr);
 
 		/* prepare next bounce */
-		swap(area_src, area_dst);
+		tmp_area = area_src;
+		area_src = area_dst;
+		area_dst = tmp_area;
 
-		swap(area_src_alias, area_dst_alias);
+		tmp_area = area_src_alias;
+		area_src_alias = area_dst_alias;
+		area_dst_alias = tmp_area;
 
 		uffd_stats_report(uffd_stats, nr_cpus);
 	}