Merge branch 'akpm' (patches from Andrew)

Merge more updates from Andrew Morton:
 "190 patches.

  Subsystems affected by this patch series: mm (hugetlb, userfaultfd,
  vmscan, kconfig, proc, z3fold, zbud, ras, mempolicy, memblock,
  migration, thp, nommu, kconfig, madvise, memory-hotplug, zswap,
  zsmalloc, zram, cleanups, kfence, and hmm), procfs, sysctl, misc,
  core-kernel, lib, lz4, checkpatch, init, kprobes, nilfs2, hfs,
  signals, exec, kcov, selftests, compress/decompress, and ipc"

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (190 commits)
  ipc/util.c: use binary search for max_idx
  ipc/sem.c: use READ_ONCE()/WRITE_ONCE() for use_global_lock
  ipc: use kmalloc for msg_queue and shmid_kernel
  ipc sem: use kvmalloc for sem_undo allocation
  lib/decompressors: remove set but not used variabled 'level'
  selftests/vm/pkeys: exercise x86 XSAVE init state
  selftests/vm/pkeys: refill shadow register after implicit kernel write
  selftests/vm/pkeys: handle negative sys_pkey_alloc() return code
  selftests/vm/pkeys: fix alloc_random_pkey() to make it really, really random
  kcov: add __no_sanitize_coverage to fix noinstr for all architectures
  exec: remove checks in __register_bimfmt()
  x86: signal: don't do sas_ss_reset() until we are certain that sigframe won't be abandoned
  hfsplus: report create_date to kstat.btime
  hfsplus: remove unnecessary oom message
  nilfs2: remove redundant continue statement in a while-loop
  kprobes: remove duplicated strong free_insn_page in x86 and s390
  init: print out unknown kernel parameters
  checkpatch: do not complain about positive return values starting with EPOLL
  checkpatch: improve the indented label test
  checkpatch: scripts/spdxcheck.py now requires python3
  ...

1 files changed, 85 insertions, 183 deletions

diff --git a/mm/migrate.c b/mm/migrate.c
index 380ca57b9031..23cbd9de030b 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -210,13 +210,18 @@ static bool remove_migration_pte(struct page *page, struct vm_area_struct *vma,
 		 * Recheck VMA as permissions can change since migration started
 		 */
 		entry = pte_to_swp_entry(*pvmw.pte);
-		if (is_write_migration_entry(entry))
+		if (is_writable_migration_entry(entry))
 			pte = maybe_mkwrite(pte, vma);
 		else if (pte_swp_uffd_wp(*pvmw.pte))
 			pte = pte_mkuffd_wp(pte);
 
 		if (unlikely(is_device_private_page(new))) {
-			entry = make_device_private_entry(new, pte_write(pte));
+			if (pte_write(pte))
+				entry = make_writable_device_private_entry(
+							page_to_pfn(new));
+			else
+				entry = make_readable_device_private_entry(
+							page_to_pfn(new));
 			pte = swp_entry_to_pte(entry);
 			if (pte_swp_soft_dirty(*pvmw.pte))
 				pte = pte_swp_mksoft_dirty(pte);
@@ -226,8 +231,10 @@ static bool remove_migration_pte(struct page *page, struct vm_area_struct *vma,
 
 #ifdef CONFIG_HUGETLB_PAGE
 		if (PageHuge(new)) {
+			unsigned int shift = huge_page_shift(hstate_vma(vma));
+
 			pte = pte_mkhuge(pte);
-			pte = arch_make_huge_pte(pte, vma, new, 0);
+			pte = arch_make_huge_pte(pte, shift, vma->vm_flags);
 			set_huge_pte_at(vma->vm_mm, pvmw.address, pvmw.pte, pte);
 			if (PageAnon(new))
 				hugepage_add_anon_rmap(new, vma, pvmw.address);
@@ -294,7 +301,7 @@ void __migration_entry_wait(struct mm_struct *mm, pte_t *ptep,
 	if (!is_migration_entry(entry))
 		goto out;
 
-	page = migration_entry_to_page(entry);
+	page = pfn_swap_entry_to_page(entry);
 	page = compound_head(page);
 
 	/*
@@ -335,7 +342,7 @@ void pmd_migration_entry_wait(struct mm_struct *mm, pmd_t *pmd)
 	ptl = pmd_lock(mm, pmd);
 	if (!is_pmd_migration_entry(*pmd))
 		goto unlock;
-	page = migration_entry_to_page(pmd_to_swp_entry(*pmd));
+	page = pfn_swap_entry_to_page(pmd_to_swp_entry(*pmd));
 	if (!get_page_unless_zero(page))
 		goto unlock;
 	spin_unlock(ptl);
@@ -551,7 +558,7 @@ static void __copy_gigantic_page(struct page *dst, struct page *src,
 	}
 }
 
-static void copy_huge_page(struct page *dst, struct page *src)
+void copy_huge_page(struct page *dst, struct page *src)
 {
 	int i;
 	int nr_pages;
@@ -626,7 +633,10 @@ void migrate_page_states(struct page *newpage, struct page *page)
 	if (PageSwapCache(page))
 		ClearPageSwapCache(page);
 	ClearPagePrivate(page);
-	set_page_private(page, 0);
+
+	/* page->private contains hugetlb specific flags */
+	if (!PageHuge(page))
+		set_page_private(page, 0);
 
 	/*
 	 * If any waiters have accumulated on the new page then
@@ -1099,7 +1109,7 @@ static int __unmap_and_move(struct page *page, struct page *newpage,
 		/* Establish migration ptes */
 		VM_BUG_ON_PAGE(PageAnon(page) && !PageKsm(page) && !anon_vma,
 				page);
-		try_to_unmap(page, TTU_MIGRATION|TTU_IGNORE_MLOCK);
+		try_to_migrate(page, 0);
 		page_was_mapped = 1;
 	}
 
@@ -1288,7 +1298,7 @@ static int unmap_and_move_huge_page(new_page_t get_new_page,
 	 * page_mapping() set, hugetlbfs specific move page routine will not
 	 * be called and we could leak usage counts for subpools.
 	 */
-	if (page_private(hpage) && !page_mapping(hpage)) {
+	if (hugetlb_page_subpool(hpage) && !page_mapping(hpage)) {
 		rc = -EBUSY;
 		goto out_unlock;
 	}
@@ -1301,7 +1311,7 @@ static int unmap_and_move_huge_page(new_page_t get_new_page,
 
 	if (page_mapped(hpage)) {
 		bool mapping_locked = false;
-		enum ttu_flags ttu = TTU_MIGRATION|TTU_IGNORE_MLOCK;
+		enum ttu_flags ttu = 0;
 
 		if (!PageAnon(hpage)) {
 			/*
@@ -1318,7 +1328,7 @@ static int unmap_and_move_huge_page(new_page_t get_new_page,
 			ttu |= TTU_RMAP_LOCKED;
 		}
 
-		try_to_unmap(hpage, ttu);
+		try_to_migrate(hpage, ttu);
 		page_was_mapped = 1;
 
 		if (mapping_locked)
@@ -1418,6 +1428,7 @@ int migrate_pages(struct list_head *from, new_page_t get_new_page,
 	int swapwrite = current->flags & PF_SWAPWRITE;
 	int rc, nr_subpages;
 	LIST_HEAD(ret_pages);
+	bool nosplit = (reason == MR_NUMA_MISPLACED);
 
 	trace_mm_migrate_pages_start(mode, reason);
 
@@ -1489,8 +1500,9 @@ retry:
 				/*
 				 * When memory is low, don't bother to try to migrate
 				 * other pages, just exit.
+				 * THP NUMA faulting doesn't split THP to retry.
 				 */
-				if (is_thp) {
+				if (is_thp && !nosplit) {
 					if (!try_split_thp(page, &page2, from)) {
 						nr_thp_split++;
 						goto retry;
@@ -2043,12 +2055,33 @@ static struct page *alloc_misplaced_dst_page(struct page *page,
 	return newpage;
 }
 
+static struct page *alloc_misplaced_dst_page_thp(struct page *page,
+						 unsigned long data)
+{
+	int nid = (int) data;
+	struct page *newpage;
+
+	newpage = alloc_pages_node(nid, (GFP_TRANSHUGE_LIGHT | __GFP_THISNODE),
+				   HPAGE_PMD_ORDER);
+	if (!newpage)
+		goto out;
+
+	prep_transhuge_page(newpage);
+
+out:
+	return newpage;
+}
+
 static int numamigrate_isolate_page(pg_data_t *pgdat, struct page *page)
 {
 	int page_lru;
 
 	VM_BUG_ON_PAGE(compound_order(page) && !PageTransHuge(page), page);
 
+	/* Do not migrate THP mapped by multiple processes */
+	if (PageTransHuge(page) && total_mapcount(page) > 1)
+		return 0;
+
 	/* Avoid migrating to a node that is nearly full */
 	if (!migrate_balanced_pgdat(pgdat, compound_nr(page)))
 		return 0;
@@ -2056,18 +2089,6 @@ static int numamigrate_isolate_page(pg_data_t *pgdat, struct page *page)
 	if (isolate_lru_page(page))
 		return 0;
 
-	/*
-	 * migrate_misplaced_transhuge_page() skips page migration's usual
-	 * check on page_count(), so we must do it here, now that the page
-	 * has been isolated: a GUP pin, or any other pin, prevents migration.
-	 * The expected page count is 3: 1 for page's mapcount and 1 for the
-	 * caller's pin and 1 for the reference taken by isolate_lru_page().
-	 */
-	if (PageTransHuge(page) && page_count(page) != 3) {
-		putback_lru_page(page);
-		return 0;
-	}
-
 	page_lru = page_is_file_lru(page);
 	mod_node_page_state(page_pgdat(page), NR_ISOLATED_ANON + page_lru,
 				thp_nr_pages(page));
@@ -2081,12 +2102,6 @@ static int numamigrate_isolate_page(pg_data_t *pgdat, struct page *page)
 	return 1;
 }
 
-bool pmd_trans_migrating(pmd_t pmd)
-{
-	struct page *page = pmd_page(pmd);
-	return PageLocked(page);
-}
-
 /*
  * Attempt to migrate a misplaced page to the specified destination
  * node. Caller is expected to have an elevated reference count on
@@ -2099,6 +2114,21 @@ int migrate_misplaced_page(struct page *page, struct vm_area_struct *vma,
 	int isolated;
 	int nr_remaining;
 	LIST_HEAD(migratepages);
+	new_page_t *new;
+	bool compound;
+	unsigned int nr_pages = thp_nr_pages(page);
+
+	/*
+	 * PTE mapped THP or HugeTLB page can't reach here so the page could
+	 * be either base page or THP.  And it must be head page if it is
+	 * THP.
+	 */
+	compound = PageTransHuge(page);
+
+	if (compound)
+		new = alloc_misplaced_dst_page_thp;
+	else
+		new = alloc_misplaced_dst_page;
 
 	/*
 	 * Don't migrate file pages that are mapped in multiple processes
@@ -2120,19 +2150,18 @@ int migrate_misplaced_page(struct page *page, struct vm_area_struct *vma,
 		goto out;
 
 	list_add(&page->lru, &migratepages);
-	nr_remaining = migrate_pages(&migratepages, alloc_misplaced_dst_page,
-				     NULL, node, MIGRATE_ASYNC,
-				     MR_NUMA_MISPLACED);
+	nr_remaining = migrate_pages(&migratepages, *new, NULL, node,
+				     MIGRATE_ASYNC, MR_NUMA_MISPLACED);
 	if (nr_remaining) {
 		if (!list_empty(&migratepages)) {
 			list_del(&page->lru);
-			dec_node_page_state(page, NR_ISOLATED_ANON +
-					page_is_file_lru(page));
+			mod_node_page_state(page_pgdat(page), NR_ISOLATED_ANON +
+					page_is_file_lru(page), -nr_pages);
 			putback_lru_page(page);
 		}
 		isolated = 0;
 	} else
-		count_vm_numa_event(NUMA_PAGE_MIGRATE);
+		count_vm_numa_events(NUMA_PAGE_MIGRATE, nr_pages);
 	BUG_ON(!list_empty(&migratepages));
 	return isolated;
 
@@ -2141,141 +2170,6 @@ out:
 	return 0;
 }
 #endif /* CONFIG_NUMA_BALANCING */
-
-#if defined(CONFIG_NUMA_BALANCING) && defined(CONFIG_TRANSPARENT_HUGEPAGE)
-/*
- * Migrates a THP to a given target node. page must be locked and is unlocked
- * before returning.
- */
-int migrate_misplaced_transhuge_page(struct mm_struct *mm,
-				struct vm_area_struct *vma,
-				pmd_t *pmd, pmd_t entry,
-				unsigned long address,
-				struct page *page, int node)
-{
-	spinlock_t *ptl;
-	pg_data_t *pgdat = NODE_DATA(node);
-	int isolated = 0;
-	struct page *new_page = NULL;
-	int page_lru = page_is_file_lru(page);
-	unsigned long start = address & HPAGE_PMD_MASK;
-
-	new_page = alloc_pages_node(node,
-		(GFP_TRANSHUGE_LIGHT | __GFP_THISNODE),
-		HPAGE_PMD_ORDER);
-	if (!new_page)
-		goto out_fail;
-	prep_transhuge_page(new_page);
-
-	isolated = numamigrate_isolate_page(pgdat, page);
-	if (!isolated) {
-		put_page(new_page);
-		goto out_fail;
-	}
-
-	/* Prepare a page as a migration target */
-	__SetPageLocked(new_page);
-	if (PageSwapBacked(page))
-		__SetPageSwapBacked(new_page);
-
-	/* anon mapping, we can simply copy page->mapping to the new page: */
-	new_page->mapping = page->mapping;
-	new_page->index = page->index;
-	/* flush the cache before copying using the kernel virtual address */
-	flush_cache_range(vma, start, start + HPAGE_PMD_SIZE);
-	migrate_page_copy(new_page, page);
-	WARN_ON(PageLRU(new_page));
-
-	/* Recheck the target PMD */
-	ptl = pmd_lock(mm, pmd);
-	if (unlikely(!pmd_same(*pmd, entry) || !page_ref_freeze(page, 2))) {
-		spin_unlock(ptl);
-
-		/* Reverse changes made by migrate_page_copy() */
-		if (TestClearPageActive(new_page))
-			SetPageActive(page);
-		if (TestClearPageUnevictable(new_page))
-			SetPageUnevictable(page);
-
-		unlock_page(new_page);
-		put_page(new_page);		/* Free it */
-
-		/* Retake the callers reference and putback on LRU */
-		get_page(page);
-		putback_lru_page(page);
-		mod_node_page_state(page_pgdat(page),
-			 NR_ISOLATED_ANON + page_lru, -HPAGE_PMD_NR);
-
-		goto out_unlock;
-	}
-
-	entry = mk_huge_pmd(new_page, vma->vm_page_prot);
-	entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
-
-	/*
-	 * Overwrite the old entry under pagetable lock and establish
-	 * the new PTE. Any parallel GUP will either observe the old
-	 * page blocking on the page lock, block on the page table
-	 * lock or observe the new page. The SetPageUptodate on the
-	 * new page and page_add_new_anon_rmap guarantee the copy is
-	 * visible before the pagetable update.
-	 */
-	page_add_anon_rmap(new_page, vma, start, true);
-	/*
-	 * At this point the pmd is numa/protnone (i.e. non present) and the TLB
-	 * has already been flushed globally.  So no TLB can be currently
-	 * caching this non present pmd mapping.  There's no need to clear the
-	 * pmd before doing set_pmd_at(), nor to flush the TLB after
-	 * set_pmd_at().  Clearing the pmd here would introduce a race
-	 * condition against MADV_DONTNEED, because MADV_DONTNEED only holds the
-	 * mmap_lock for reading.  If the pmd is set to NULL at any given time,
-	 * MADV_DONTNEED won't wait on the pmd lock and it'll skip clearing this
-	 * pmd.
-	 */
-	set_pmd_at(mm, start, pmd, entry);
-	update_mmu_cache_pmd(vma, address, &entry);
-
-	page_ref_unfreeze(page, 2);
-	mlock_migrate_page(new_page, page);
-	page_remove_rmap(page, true);
-	set_page_owner_migrate_reason(new_page, MR_NUMA_MISPLACED);
-
-	spin_unlock(ptl);
-
-	/* Take an "isolate" reference and put new page on the LRU. */
-	get_page(new_page);
-	putback_lru_page(new_page);
-
-	unlock_page(new_page);
-	unlock_page(page);
-	put_page(page);			/* Drop the rmap reference */
-	put_page(page);			/* Drop the LRU isolation reference */
-
-	count_vm_events(PGMIGRATE_SUCCESS, HPAGE_PMD_NR);
-	count_vm_numa_events(NUMA_PAGE_MIGRATE, HPAGE_PMD_NR);
-
-	mod_node_page_state(page_pgdat(page),
-			NR_ISOLATED_ANON + page_lru,
-			-HPAGE_PMD_NR);
-	return isolated;
-
-out_fail:
-	count_vm_events(PGMIGRATE_FAIL, HPAGE_PMD_NR);
-	ptl = pmd_lock(mm, pmd);
-	if (pmd_same(*pmd, entry)) {
-		entry = pmd_modify(entry, vma->vm_page_prot);
-		set_pmd_at(mm, start, pmd, entry);
-		update_mmu_cache_pmd(vma, address, &entry);
-	}
-	spin_unlock(ptl);
-
-out_unlock:
-	unlock_page(page);
-	put_page(page);
-	return 0;
-}
-#endif /* CONFIG_NUMA_BALANCING */
-
 #endif /* CONFIG_NUMA */
 
 #ifdef CONFIG_DEVICE_PRIVATE
@@ -2400,7 +2294,7 @@ again:
 			if (!is_device_private_entry(entry))
 				goto next;
 
-			page = device_private_entry_to_page(entry);
+			page = pfn_swap_entry_to_page(entry);
 			if (!(migrate->flags &
 				MIGRATE_VMA_SELECT_DEVICE_PRIVATE) ||
 			    page->pgmap->owner != migrate->pgmap_owner)
@@ -2408,7 +2302,7 @@ again:
 
 			mpfn = migrate_pfn(page_to_pfn(page)) |
 					MIGRATE_PFN_MIGRATE;
-			if (is_write_device_private_entry(entry))
+			if (is_writable_device_private_entry(entry))
 				mpfn |= MIGRATE_PFN_WRITE;
 		} else {
 			if (!(migrate->flags & MIGRATE_VMA_SELECT_SYSTEM))
@@ -2454,8 +2348,12 @@ again:
 			ptep_get_and_clear(mm, addr, ptep);
 
 			/* Setup special migration page table entry */
-			entry = make_migration_entry(page, mpfn &
-						     MIGRATE_PFN_WRITE);
+			if (mpfn & MIGRATE_PFN_WRITE)
+				entry = make_writable_migration_entry(
+							page_to_pfn(page));
+			else
+				entry = make_readable_migration_entry(
+							page_to_pfn(page));
 			swp_pte = swp_entry_to_pte(entry);
 			if (pte_present(pte)) {
 				if (pte_soft_dirty(pte))
@@ -2518,8 +2416,8 @@ static void migrate_vma_collect(struct migrate_vma *migrate)
 	 * that the registered device driver can skip invalidating device
 	 * private page mappings that won't be migrated.
 	 */
-	mmu_notifier_range_init_migrate(&range, 0, migrate->vma,
-		migrate->vma->vm_mm, migrate->start, migrate->end,
+	mmu_notifier_range_init_owner(&range, MMU_NOTIFY_MIGRATE, 0,
+		migrate->vma, migrate->vma->vm_mm, migrate->start, migrate->end,
 		migrate->pgmap_owner);
 	mmu_notifier_invalidate_range_start(&range);
 
@@ -2704,7 +2602,6 @@ static void migrate_vma_prepare(struct migrate_vma *migrate)
  */
 static void migrate_vma_unmap(struct migrate_vma *migrate)
 {
-	int flags = TTU_MIGRATION | TTU_IGNORE_MLOCK;
 	const unsigned long npages = migrate->npages;
 	const unsigned long start = migrate->start;
 	unsigned long addr, i, restore = 0;
@@ -2716,7 +2613,7 @@ static void migrate_vma_unmap(struct migrate_vma *migrate)
 			continue;
 
 		if (page_mapped(page)) {
-			try_to_unmap(page, flags);
+			try_to_migrate(page, 0);
 			if (page_mapped(page))
 				goto restore;
 		}
@@ -2928,7 +2825,12 @@ static void migrate_vma_insert_page(struct migrate_vma *migrate,
 		if (is_device_private_page(page)) {
 			swp_entry_t swp_entry;
 
-			swp_entry = make_device_private_entry(page, vma->vm_flags & VM_WRITE);
+			if (vma->vm_flags & VM_WRITE)
+				swp_entry = make_writable_device_private_entry(
+							page_to_pfn(page));
+			else
+				swp_entry = make_readable_device_private_entry(
+							page_to_pfn(page));
 			entry = swp_entry_to_pte(swp_entry);
 		} else {
 			/*
@@ -3025,9 +2927,9 @@ void migrate_vma_pages(struct migrate_vma *migrate)
 			if (!notified) {
 				notified = true;
 
-				mmu_notifier_range_init_migrate(&range, 0,
-					migrate->vma, migrate->vma->vm_mm,
-					addr, migrate->end,
+				mmu_notifier_range_init_owner(&range,
+					MMU_NOTIFY_MIGRATE, 0, migrate->vma,
+					migrate->vma->vm_mm, addr, migrate->end,
 					migrate->pgmap_owner);
 				mmu_notifier_invalidate_range_start(&range);
 			}