Merge branch 'akpm' (patches from Andrew)

Merge misc updates from Andrew Morton:
 "173 patches.

  Subsystems affected by this series: ia64, ocfs2, block, and mm (debug,
  pagecache, gup, swap, shmem, memcg, selftests, pagemap, mremap,
  bootmem, sparsemem, vmalloc, kasan, pagealloc, memory-failure,
  hugetlb, userfaultfd, vmscan, compaction, mempolicy, memblock,
  oom-kill, migration, ksm, percpu, vmstat, and madvise)"

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (173 commits)
  mm/madvise: add MADV_WILLNEED to process_madvise()
  mm/vmstat: remove unneeded return value
  mm/vmstat: simplify the array size calculation
  mm/vmstat: correct some wrong comments
  mm/percpu,c: remove obsolete comments of pcpu_chunk_populated()
  selftests: vm: add COW time test for KSM pages
  selftests: vm: add KSM merging time test
  mm: KSM: fix data type
  selftests: vm: add KSM merging across nodes test
  selftests: vm: add KSM zero page merging test
  selftests: vm: add KSM unmerge test
  selftests: vm: add KSM merge test
  mm/migrate: correct kernel-doc notation
  mm: wire up syscall process_mrelease
  mm: introduce process_mrelease system call
  memblock: make memblock_find_in_range method private
  mm/mempolicy.c: use in_task() in mempolicy_slab_node()
  mm/mempolicy: unify the create() func for bind/interleave/prefer-many policies
  mm/mempolicy: advertise new MPOL_PREFERRED_MANY
  mm/hugetlb: add support for mempolicy MPOL_PREFERRED_MANY
  ...

39 files changed, 2072 insertions, 1137 deletions

diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index cd06dca232c3..4a9d4e27d0d9 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -271,6 +271,14 @@ void wb_wakeup_delayed(struct bdi_writeback *wb)
 	spin_unlock_bh(&wb->work_lock);
 }
 
+static void wb_update_bandwidth_workfn(struct work_struct *work)
+{
+	struct bdi_writeback *wb = container_of(to_delayed_work(work),
+						struct bdi_writeback, bw_dwork);
+
+	wb_update_bandwidth(wb);
+}
+
 /*
  * Initial write bandwidth: 100 MB/s
  */
@@ -293,6 +301,7 @@ static int wb_init(struct bdi_writeback *wb, struct backing_dev_info *bdi,
 	INIT_LIST_HEAD(&wb->b_dirty_time);
 	spin_lock_init(&wb->list_lock);
 
+	atomic_set(&wb->writeback_inodes, 0);
 	wb->bw_time_stamp = jiffies;
 	wb->balanced_dirty_ratelimit = INIT_BW;
 	wb->dirty_ratelimit = INIT_BW;
@@ -302,6 +311,7 @@ static int wb_init(struct bdi_writeback *wb, struct backing_dev_info *bdi,
 	spin_lock_init(&wb->work_lock);
 	INIT_LIST_HEAD(&wb->work_list);
 	INIT_DELAYED_WORK(&wb->dwork, wb_workfn);
+	INIT_DELAYED_WORK(&wb->bw_dwork, wb_update_bandwidth_workfn);
 	wb->dirty_sleep = jiffies;
 
 	err = fprop_local_init_percpu(&wb->completions, gfp);
@@ -350,6 +360,7 @@ static void wb_shutdown(struct bdi_writeback *wb)
 	mod_delayed_work(bdi_wq, &wb->dwork, 0);
 	flush_delayed_work(&wb->dwork);
 	WARN_ON(!list_empty(&wb->work_list));
+	flush_delayed_work(&wb->bw_dwork);
 }
 
 static void wb_exit(struct bdi_writeback *wb)
diff --git a/mm/bootmem_info.c b/mm/bootmem_info.c
index 5b152dba7344..f03f42f426f6 100644
--- a/mm/bootmem_info.c
+++ b/mm/bootmem_info.c
@@ -39,7 +39,7 @@ void put_page_bootmem(struct page *page)
 }
 
 #ifndef CONFIG_SPARSEMEM_VMEMMAP
-static void register_page_bootmem_info_section(unsigned long start_pfn)
+static void __init register_page_bootmem_info_section(unsigned long start_pfn)
 {
 	unsigned long mapsize, section_nr, i;
 	struct mem_section *ms;
@@ -74,7 +74,7 @@ static void register_page_bootmem_info_section(unsigned long start_pfn)
 
 }
 #else /* CONFIG_SPARSEMEM_VMEMMAP */
-static void register_page_bootmem_info_section(unsigned long start_pfn)
+static void __init register_page_bootmem_info_section(unsigned long start_pfn)
 {
 	unsigned long mapsize, section_nr, i;
 	struct mem_section *ms;
diff --git a/mm/compaction.c b/mm/compaction.c
index 621508e0ecd5..fa9b2b598eab 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -2398,7 +2398,7 @@ compact_zone(struct compact_control *cc, struct capture_control *capc)
 
 		err = migrate_pages(&cc->migratepages, compaction_alloc,
 				compaction_free, (unsigned long)cc, cc->mode,
-				MR_COMPACTION);
+				MR_COMPACTION, NULL);
 
 		trace_mm_compaction_migratepages(cc->nr_migratepages, err,
 							&cc->migratepages);
@@ -2706,6 +2706,30 @@ static void compact_nodes(void)
  */
 unsigned int __read_mostly sysctl_compaction_proactiveness = 20;
 
+int compaction_proactiveness_sysctl_handler(struct ctl_table *table, int write,
+		void *buffer, size_t *length, loff_t *ppos)
+{
+	int rc, nid;
+
+	rc = proc_dointvec_minmax(table, write, buffer, length, ppos);
+	if (rc)
+		return rc;
+
+	if (write && sysctl_compaction_proactiveness) {
+		for_each_online_node(nid) {
+			pg_data_t *pgdat = NODE_DATA(nid);
+
+			if (pgdat->proactive_compact_trigger)
+				continue;
+
+			pgdat->proactive_compact_trigger = true;
+			wake_up_interruptible(&pgdat->kcompactd_wait);
+		}
+	}
+
+	return 0;
+}
+
 /*
  * This is the entry point for compacting all nodes via
  * /proc/sys/vm/compact_memory
@@ -2750,7 +2774,8 @@ void compaction_unregister_node(struct node *node)
 
 static inline bool kcompactd_work_requested(pg_data_t *pgdat)
 {
-	return pgdat->kcompactd_max_order > 0 || kthread_should_stop();
+	return pgdat->kcompactd_max_order > 0 || kthread_should_stop() ||
+		pgdat->proactive_compact_trigger;
 }
 
 static bool kcompactd_node_suitable(pg_data_t *pgdat)
@@ -2885,7 +2910,8 @@ static int kcompactd(void *p)
 {
 	pg_data_t *pgdat = (pg_data_t *)p;
 	struct task_struct *tsk = current;
-	unsigned int proactive_defer = 0;
+	long default_timeout = msecs_to_jiffies(HPAGE_FRAG_CHECK_INTERVAL_MSEC);
+	long timeout = default_timeout;
 
 	const struct cpumask *cpumask = cpumask_of_node(pgdat->node_id);
 
@@ -2900,25 +2926,39 @@ static int kcompactd(void *p)
 	while (!kthread_should_stop()) {
 		unsigned long pflags;
 
+		/*
+		 * Avoid the unnecessary wakeup for proactive compaction
+		 * when it is disabled.
+		 */
+		if (!sysctl_compaction_proactiveness)
+			timeout = MAX_SCHEDULE_TIMEOUT;
 		trace_mm_compaction_kcompactd_sleep(pgdat->node_id);
 		if (wait_event_freezable_timeout(pgdat->kcompactd_wait,
-			kcompactd_work_requested(pgdat),
-			msecs_to_jiffies(HPAGE_FRAG_CHECK_INTERVAL_MSEC))) {
+			kcompactd_work_requested(pgdat), timeout) &&
+			!pgdat->proactive_compact_trigger) {
 
 			psi_memstall_enter(&pflags);
 			kcompactd_do_work(pgdat);
 			psi_memstall_leave(&pflags);
+			/*
+			 * Reset the timeout value. The defer timeout from
+			 * proactive compaction is lost here but that is fine
+			 * as the condition of the zone changing substantionally
+			 * then carrying on with the previous defer interval is
+			 * not useful.
+			 */
+			timeout = default_timeout;
 			continue;
 		}
 
-		/* kcompactd wait timeout */
+		/*
+		 * Start the proactive work with default timeout. Based
+		 * on the fragmentation score, this timeout is updated.
+		 */
+		timeout = default_timeout;
 		if (should_proactive_compact_node(pgdat)) {
 			unsigned int prev_score, score;
 
-			if (proactive_defer) {
-				proactive_defer--;
-				continue;
-			}
 			prev_score = fragmentation_score_node(pgdat);
 			proactive_compact_node(pgdat);
 			score = fragmentation_score_node(pgdat);
@@ -2926,9 +2966,12 @@ static int kcompactd(void *p)
 			 * Defer proactive compaction if the fragmentation
 			 * score did not go down i.e. no progress made.
 			 */
-			proactive_defer = score < prev_score ?
-					0 : 1 << COMPACT_MAX_DEFER_SHIFT;
+			if (unlikely(score >= prev_score))
+				timeout =
+				   default_timeout << COMPACT_MAX_DEFER_SHIFT;
 		}
+		if (unlikely(pgdat->proactive_compact_trigger))
+			pgdat->proactive_compact_trigger = false;
 	}
 
 	return 0;
diff --git a/mm/debug_vm_pgtable.c b/mm/debug_vm_pgtable.c
index 1c922691aa61..1403639302e4 100644
--- a/mm/debug_vm_pgtable.c
+++ b/mm/debug_vm_pgtable.c
@@ -29,6 +29,8 @@
 #include <linux/start_kernel.h>
 #include <linux/sched/mm.h>
 #include <linux/io.h>
+
+#include <asm/cacheflush.h>
 #include <asm/pgalloc.h>
 #include <asm/tlbflush.h>
 
@@ -58,10 +60,41 @@
 #define RANDOM_ORVALUE (GENMASK(BITS_PER_LONG - 1, 0) & ~ARCH_SKIP_MASK)
 #define RANDOM_NZVALUE	GENMASK(7, 0)
 
-static void __init pte_basic_tests(unsigned long pfn, int idx)
+struct pgtable_debug_args {
+	struct mm_struct	*mm;
+	struct vm_area_struct	*vma;
+
+	pgd_t			*pgdp;
+	p4d_t			*p4dp;
+	pud_t			*pudp;
+	pmd_t			*pmdp;
+	pte_t			*ptep;
+
+	p4d_t			*start_p4dp;
+	pud_t			*start_pudp;
+	pmd_t			*start_pmdp;
+	pgtable_t		start_ptep;
+
+	unsigned long		vaddr;
+	pgprot_t		page_prot;
+	pgprot_t		page_prot_none;
+
+	bool			is_contiguous_page;
+	unsigned long		pud_pfn;
+	unsigned long		pmd_pfn;
+	unsigned long		pte_pfn;
+
+	unsigned long		fixed_pgd_pfn;
+	unsigned long		fixed_p4d_pfn;
+	unsigned long		fixed_pud_pfn;
+	unsigned long		fixed_pmd_pfn;
+	unsigned long		fixed_pte_pfn;
+};
+
+static void __init pte_basic_tests(struct pgtable_debug_args *args, int idx)
 {
 	pgprot_t prot = protection_map[idx];
-	pte_t pte = pfn_pte(pfn, prot);
+	pte_t pte = pfn_pte(args->fixed_pte_pfn, prot);
 	unsigned long val = idx, *ptr = &val;
 
 	pr_debug("Validating PTE basic (%pGv)\n", ptr);
@@ -86,53 +119,63 @@ static void __init pte_basic_tests(unsigned long pfn, int idx)
 	WARN_ON(!pte_dirty(pte_wrprotect(pte_mkdirty(pte))));
 }
 
-static void __init pte_advanced_tests(struct mm_struct *mm,
-				      struct vm_area_struct *vma, pte_t *ptep,
-				      unsigned long pfn, unsigned long vaddr,
-				      pgprot_t prot)
+static void __init pte_advanced_tests(struct pgtable_debug_args *args)
 {
+	struct page *page;
 	pte_t pte;
 
 	/*
 	 * Architectures optimize set_pte_at by avoiding TLB flush.
 	 * This requires set_pte_at to be not used to update an
 	 * existing pte entry. Clear pte before we do set_pte_at
+	 *
+	 * flush_dcache_page() is called after set_pte_at() to clear
+	 * PG_arch_1 for the page on ARM64. The page flag isn't cleared
+	 * when it's released and page allocation check will fail when
+	 * the page is allocated again. For architectures other than ARM64,
+	 * the unexpected overhead of cache flushing is acceptable.
 	 */
+	page = (args->pte_pfn != ULONG_MAX) ? pfn_to_page(args->pte_pfn) : NULL;
+	if (!page)
+		return;
 
 	pr_debug("Validating PTE advanced\n");
-	pte = pfn_pte(pfn, prot);
-	set_pte_at(mm, vaddr, ptep, pte);
-	ptep_set_wrprotect(mm, vaddr, ptep);
-	pte = ptep_get(ptep);
+	pte = pfn_pte(args->pte_pfn, args->page_prot);
+	set_pte_at(args->mm, args->vaddr, args->ptep, pte);
+	flush_dcache_page(page);
+	ptep_set_wrprotect(args->mm, args->vaddr, args->ptep);
+	pte = ptep_get(args->ptep);
 	WARN_ON(pte_write(pte));
-	ptep_get_and_clear(mm, vaddr, ptep);
-	pte = ptep_get(ptep);
+	ptep_get_and_clear(args->mm, args->vaddr, args->ptep);
+	pte = ptep_get(args->ptep);
 	WARN_ON(!pte_none(pte));
 
-	pte = pfn_pte(pfn, prot);
+	pte = pfn_pte(args->pte_pfn, args->page_prot);
 	pte = pte_wrprotect(pte);
 	pte = pte_mkclean(pte);
-	set_pte_at(mm, vaddr, ptep, pte);
+	set_pte_at(args->mm, args->vaddr, args->ptep, pte);
+	flush_dcache_page(page);
 	pte = pte_mkwrite(pte);
 	pte = pte_mkdirty(pte);
-	ptep_set_access_flags(vma, vaddr, ptep, pte, 1);
-	pte = ptep_get(ptep);
+	ptep_set_access_flags(args->vma, args->vaddr, args->ptep, pte, 1);
+	pte = ptep_get(args->ptep);
 	WARN_ON(!(pte_write(pte) && pte_dirty(pte)));
-	ptep_get_and_clear_full(mm, vaddr, ptep, 1);
-	pte = ptep_get(ptep);
+	ptep_get_and_clear_full(args->mm, args->vaddr, args->ptep, 1);
+	pte = ptep_get(args->ptep);
 	WARN_ON(!pte_none(pte));
 
-	pte = pfn_pte(pfn, prot);
+	pte = pfn_pte(args->pte_pfn, args->page_prot);
 	pte = pte_mkyoung(pte);
-	set_pte_at(mm, vaddr, ptep, pte);
-	ptep_test_and_clear_young(vma, vaddr, ptep);
-	pte = ptep_get(ptep);
+	set_pte_at(args->mm, args->vaddr, args->ptep, pte);
+	flush_dcache_page(page);
+	ptep_test_and_clear_young(args->vma, args->vaddr, args->ptep);
+	pte = ptep_get(args->ptep);
 	WARN_ON(pte_young(pte));
 }
 
-static void __init pte_savedwrite_tests(unsigned long pfn, pgprot_t prot)
+static void __init pte_savedwrite_tests(struct pgtable_debug_args *args)
 {
-	pte_t pte = pfn_pte(pfn, prot);
+	pte_t pte = pfn_pte(args->fixed_pte_pfn, args->page_prot_none);
 
 	if (!IS_ENABLED(CONFIG_NUMA_BALANCING))
 		return;
@@ -143,7 +186,7 @@ static void __init pte_savedwrite_tests(unsigned long pfn, pgprot_t prot)
 }
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
-static void __init pmd_basic_tests(unsigned long pfn, int idx)
+static void __init pmd_basic_tests(struct pgtable_debug_args *args, int idx)
 {
 	pgprot_t prot = protection_map[idx];
 	unsigned long val = idx, *ptr = &val;
@@ -153,7 +196,7 @@ static void __init pmd_basic_tests(unsigned long pfn, int idx)
 		return;
 
 	pr_debug("Validating PMD basic (%pGv)\n", ptr);
-	pmd = pfn_pmd(pfn, prot);
+	pmd = pfn_pmd(args->fixed_pmd_pfn, prot);
 
 	/*
 	 * This test needs to be executed after the given page table entry
@@ -181,57 +224,70 @@ static void __init pmd_basic_tests(unsigned long pfn, int idx)
 	WARN_ON(!pmd_bad(pmd_mkhuge(pmd)));
 }
 
-static void __init pmd_advanced_tests(struct mm_struct *mm,
-				      struct vm_area_struct *vma, pmd_t *pmdp,
-				      unsigned long pfn, unsigned long vaddr,
-				      pgprot_t prot, pgtable_t pgtable)
+static void __init pmd_advanced_tests(struct pgtable_debug_args *args)
 {
+	struct page *page;
 	pmd_t pmd;
+	unsigned long vaddr = args->vaddr;
 
 	if (!has_transparent_hugepage())
 		return;
 
+	page = (args->pmd_pfn != ULONG_MAX) ? pfn_to_page(args->pmd_pfn) : NULL;
+	if (!page)
+		return;
+
+	/*
+	 * flush_dcache_page() is called after set_pmd_at() to clear
+	 * PG_arch_1 for the page on ARM64. The page flag isn't cleared
+	 * when it's released and page allocation check will fail when
+	 * the page is allocated again. For architectures other than ARM64,
+	 * the unexpected overhead of cache flushing is acceptable.
+	 */
 	pr_debug("Validating PMD advanced\n");
 	/* Align the address wrt HPAGE_PMD_SIZE */
 	vaddr &= HPAGE_PMD_MASK;
 
-	pgtable_trans_huge_deposit(mm, pmdp, pgtable);
+	pgtable_trans_huge_deposit(args->mm, args->pmdp, args->start_ptep);
 
-	pmd = pfn_pmd(pfn, prot);
-	set_pmd_at(mm, vaddr, pmdp, pmd);
-	pmdp_set_wrprotect(mm, vaddr, pmdp);
-	pmd = READ_ONCE(*pmdp);
+	pmd = pfn_pmd(args->pmd_pfn, args->page_prot);
+	set_pmd_at(args->mm, vaddr, args->pmdp, pmd);
+	flush_dcache_page(page);
+	pmdp_set_wrprotect(args->mm, vaddr, args->pmdp);
+	pmd = READ_ONCE(*args->pmdp);
 	WARN_ON(pmd_write(pmd));
-	pmdp_huge_get_and_clear(mm, vaddr, pmdp);
-	pmd = READ_ONCE(*pmdp);
+	pmdp_huge_get_and_clear(args->mm, vaddr, args->pmdp);
+	pmd = READ_ONCE(*args->pmdp);
 	WARN_ON(!pmd_none(pmd));
 
-	pmd = pfn_pmd(pfn, prot);
+	pmd = pfn_pmd(args->pmd_pfn, args->page_prot);
 	pmd = pmd_wrprotect(pmd);
 	pmd = pmd_mkclean(pmd);
-	set_pmd_at(mm, vaddr, pmdp, pmd);
+	set_pmd_at(args->mm, vaddr, args->pmdp, pmd);
+	flush_dcache_page(page);
 	pmd = pmd_mkwrite(pmd);
 	pmd = pmd_mkdirty(pmd);
-	pmdp_set_access_flags(vma, vaddr, pmdp, pmd, 1);
-	pmd = READ_ONCE(*pmdp);
+	pmdp_set_access_flags(args->vma, vaddr, args->pmdp, pmd, 1);
+	pmd = READ_ONCE(*args->pmdp);
 	WARN_ON(!(pmd_write(pmd) && pmd_dirty(pmd)));
-	pmdp_huge_get_and_clear_full(vma, vaddr, pmdp, 1);
-	pmd = READ_ONCE(*pmdp);
+	pmdp_huge_get_and_clear_full(args->vma, vaddr, args->pmdp, 1);
+	pmd = READ_ONCE(*args->pmdp);
 	WARN_ON(!pmd_none(pmd));
 
-	pmd = pmd_mkhuge(pfn_pmd(pfn, prot));
+	pmd = pmd_mkhuge(pfn_pmd(args->pmd_pfn, args->page_prot));
 	pmd = pmd_mkyoung(pmd);
-	set_pmd_at(mm, vaddr, pmdp, pmd);
-	pmdp_test_and_clear_young(vma, vaddr, pmdp);
-	pmd = READ_ONCE(*pmdp);
+	set_pmd_at(args->mm, vaddr, args->pmdp, pmd);
+	flush_dcache_page(page);
+	pmdp_test_and_clear_young(args->vma, vaddr, args->pmdp);
+	pmd = READ_ONCE(*args->pmdp);
 	WARN_ON(pmd_young(pmd));
 
 	/*  Clear the pte entries  */
-	pmdp_huge_get_and_clear(mm, vaddr, pmdp);
-	pgtable = pgtable_trans_huge_withdraw(mm, pmdp);
+	pmdp_huge_get_and_clear(args->mm, vaddr, args->pmdp);
+	pgtable_trans_huge_withdraw(args->mm, args->pmdp);
 }
 
-static void __init pmd_leaf_tests(unsigned long pfn, pgprot_t prot)
+static void __init pmd_leaf_tests(struct pgtable_debug_args *args)
 {
 	pmd_t pmd;
 
@@ -239,7 +295,7 @@ static void __init pmd_leaf_tests(unsigned long pfn, pgprot_t prot)
 		return;
 
 	pr_debug("Validating PMD leaf\n");
-	pmd = pfn_pmd(pfn, prot);
+	pmd = pfn_pmd(args->fixed_pmd_pfn, args->page_prot);
 
 	/*
 	 * PMD based THP is a leaf entry.
@@ -248,7 +304,7 @@ static void __init pmd_leaf_tests(unsigned long pfn, pgprot_t prot)
 	WARN_ON(!pmd_leaf(pmd));
 }
 
-static void __init pmd_savedwrite_tests(unsigned long pfn, pgprot_t prot)
+static void __init pmd_savedwrite_tests(struct pgtable_debug_args *args)
 {
 	pmd_t pmd;
 
@@ -259,13 +315,13 @@ static void __init pmd_savedwrite_tests(unsigned long pfn, pgprot_t prot)
 		return;
 
 	pr_debug("Validating PMD saved write\n");
-	pmd = pfn_pmd(pfn, prot);
+	pmd = pfn_pmd(args->fixed_pmd_pfn, args->page_prot_none);
 	WARN_ON(!pmd_savedwrite(pmd_mk_savedwrite(pmd_clear_savedwrite(pmd))));
 	WARN_ON(pmd_savedwrite(pmd_clear_savedwrite(pmd_mk_savedwrite(pmd))));
 }
 
 #ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
-static void __init pud_basic_tests(struct mm_struct *mm, unsigned long pfn, int idx)
+static void __init pud_basic_tests(struct pgtable_debug_args *args, int idx)
 {
 	pgprot_t prot = protection_map[idx];
 	unsigned long val = idx, *ptr = &val;
@@ -275,7 +331,7 @@ static void __init pud_basic_tests(struct mm_struct *mm, unsigned long pfn, int
 		return;
 
 	pr_debug("Validating PUD basic (%pGv)\n", ptr);
-	pud = pfn_pud(pfn, prot);
+	pud = pfn_pud(args->fixed_pud_pfn, prot);
 
 	/*
 	 * This test needs to be executed after the given page table entry
@@ -296,7 +352,7 @@ static void __init pud_basic_tests(struct mm_struct *mm, unsigned long pfn, int
 	WARN_ON(pud_dirty(pud_wrprotect(pud_mkclean(pud))));
 	WARN_ON(!pud_dirty(pud_wrprotect(pud_mkdirty(pud))));
 
-	if (mm_pmd_folded(mm))
+	if (mm_pmd_folded(args->mm))
 		return;
 
 	/*
@@ -306,58 +362,71 @@ static void __init pud_basic_tests(struct mm_struct *mm, unsigned long pfn, int
 	WARN_ON(!pud_bad(pud_mkhuge(pud)));
 }
 
-static void __init pud_advanced_tests(struct mm_struct *mm,
-				      struct vm_area_struct *vma, pud_t *pudp,
-				      unsigned long pfn, unsigned long vaddr,
-				      pgprot_t prot)
+static void __init pud_advanced_tests(struct pgtable_debug_args *args)
 {
+	struct page *page;
+	unsigned long vaddr = args->vaddr;
 	pud_t pud;
 
 	if (!has_transparent_hugepage())
 		return;
 
+	page = (args->pud_pfn != ULONG_MAX) ? pfn_to_page(args->pud_pfn) : NULL;
+	if (!page)
+		return;
+
+	/*
+	 * flush_dcache_page() is called after set_pud_at() to clear
+	 * PG_arch_1 for the page on ARM64. The page flag isn't cleared
+	 * when it's released and page allocation check will fail when
+	 * the page is allocated again. For architectures other than ARM64,
+	 * the unexpected overhead of cache flushing is acceptable.
+	 */
 	pr_debug("Validating PUD advanced\n");
 	/* Align the address wrt HPAGE_PUD_SIZE */
 	vaddr &= HPAGE_PUD_MASK;
 
-	pud = pfn_pud(pfn, prot);
-	set_pud_at(mm, vaddr, pudp, pud);
-	pudp_set_wrprotect(mm, vaddr, pudp);
-	pud = READ_ONCE(*pudp);
+	pud = pfn_pud(args->pud_pfn, args->page_prot);
+	set_pud_at(args->mm, vaddr, args->pudp, pud);
+	flush_dcache_page(page);
+	pudp_set_wrprotect(args->mm, vaddr, args->pudp);
+	pud = READ_ONCE(*args->pudp);
 	WARN_ON(pud_write(pud));
 
 #ifndef __PAGETABLE_PMD_FOLDED
-	pudp_huge_get_and_clear(mm, vaddr, pudp);
-	pud = READ_ONCE(*pudp);
+	pudp_huge_get_and_clear(args->mm, vaddr, args->pudp);
+	pud = READ_ONCE(*args->pudp);
 	WARN_ON(!pud_none(pud));
 #endif /* __PAGETABLE_PMD_FOLDED */
-	pud = pfn_pud(pfn, prot);
+	pud = pfn_pud(args->pud_pfn, args->page_prot);
 	pud = pud_wrprotect(pud);
 	pud = pud_mkclean(pud);
-	set_pud_at(mm, vaddr, pudp, pud);
+	set_pud_at(args->mm, vaddr, args->pudp, pud);
+	flush_dcache_page(page);
 	pud = pud_mkwrite(pud);
 	pud = pud_mkdirty(pud);
-	pudp_set_access_flags(vma, vaddr, pudp, pud, 1);
-	pud = READ_ONCE(*pudp);
+	pudp_set_access_flags(args->vma, vaddr, args->pudp, pud, 1);
+	pud = READ_ONCE(*args->pudp);
 	WARN_ON(!(pud_write(pud) && pud_dirty(pud)));
 
 #ifndef __PAGETABLE_PMD_FOLDED
-	pudp_huge_get_and_clear_full(mm, vaddr, pudp, 1);
-	pud = READ_ONCE(*pudp);
+	pudp_huge_get_and_clear_full(args->mm, vaddr, args->pudp, 1);
+	pud = READ_ONCE(*args->pudp);
 	WARN_ON(!pud_none(pud));
 #endif /* __PAGETABLE_PMD_FOLDED */
 
-	pud = pfn_pud(pfn, prot);
+	pud = pfn_pud(args->pud_pfn, args->page_prot);
 	pud = pud_mkyoung(pud);
-	set_pud_at(mm, vaddr, pudp, pud);
-	pudp_test_and_clear_young(vma, vaddr, pudp);
-	pud = READ_ONCE(*pudp);
+	set_pud_at(args->mm, vaddr, args->pudp, pud);
+	flush_dcache_page(page);
+	pudp_test_and_clear_young(args->vma, vaddr, args->pudp);
+	pud = READ_ONCE(*args->pudp);
 	WARN_ON(pud_young(pud));
 
-	pudp_huge_get_and_clear(mm, vaddr, pudp);
+	pudp_huge_get_and_clear(args->mm, vaddr, args->pudp);
 }
 
-static void __init pud_leaf_tests(unsigned long pfn, pgprot_t prot)
+static void __init pud_leaf_tests(struct pgtable_debug_args *args)
 {
 	pud_t pud;
 
@@ -365,7 +434,7 @@ static void __init pud_leaf_tests(unsigned long pfn, pgprot_t prot)
 		return;
 
 	pr_debug("Validating PUD leaf\n");
-	pud = pfn_pud(pfn, prot);
+	pud = pfn_pud(args->fixed_pud_pfn, args->page_prot);
 	/*
 	 * PUD based THP is a leaf entry.
 	 */
@@ -373,41 +442,26 @@ static void __init pud_leaf_tests(unsigned long pfn, pgprot_t prot)
 	WARN_ON(!pud_leaf(pud));
 }
 #else  /* !CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */
-static void __init pud_basic_tests(struct mm_struct *mm, unsigned long pfn, int idx) { }
-static void __init pud_advanced_tests(struct mm_struct *mm,
-				      struct vm_area_struct *vma, pud_t *pudp,
-				      unsigned long pfn, unsigned long vaddr,
-				      pgprot_t prot)
-{
-}
-static void __init pud_leaf_tests(unsigned long pfn, pgprot_t prot) { }
+static void __init pud_basic_tests(struct pgtable_debug_args *args, int idx) { }
+static void __init pud_advanced_tests(struct pgtable_debug_args *args) { }
+static void __init pud_leaf_tests(struct pgtable_debug_args *args) { }
 #endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */
 #else  /* !CONFIG_TRANSPARENT_HUGEPAGE */
-static void __init pmd_basic_tests(unsigned long pfn, int idx) { }
-static void __init pud_basic_tests(struct mm_struct *mm, unsigned long pfn, int idx) { }
-static void __init pmd_advanced_tests(struct mm_struct *mm,
-				      struct vm_area_struct *vma, pmd_t *pmdp,
-				      unsigned long pfn, unsigned long vaddr,
-				      pgprot_t prot, pgtable_t pgtable)
-{
-}
-static void __init pud_advanced_tests(struct mm_struct *mm,
-				      struct vm_area_struct *vma, pud_t *pudp,
-				      unsigned long pfn, unsigned long vaddr,
-				      pgprot_t prot)
-{
-}
-static void __init pmd_leaf_tests(unsigned long pfn, pgprot_t prot) { }
-static void __init pud_leaf_tests(unsigned long pfn, pgprot_t prot) { }
-static void __init pmd_savedwrite_tests(unsigned long pfn, pgprot_t prot) { }
+static void __init pmd_basic_tests(struct pgtable_debug_args *args, int idx) { }
+static void __init pud_basic_tests(struct pgtable_debug_args *args, int idx) { }
+static void __init pmd_advanced_tests(struct pgtable_debug_args *args) { }
+static void __init pud_advanced_tests(struct pgtable_debug_args *args) { }
+static void __init pmd_leaf_tests(struct pgtable_debug_args *args) { }
+static void __init pud_leaf_tests(struct pgtable_debug_args *args) { }
+static void __init pmd_savedwrite_tests(struct pgtable_debug_args *args) { }
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 
 #ifdef CONFIG_HAVE_ARCH_HUGE_VMAP
-static void __init pmd_huge_tests(pmd_t *pmdp, unsigned long pfn, pgprot_t prot)
+static void __init pmd_huge_tests(struct pgtable_debug_args *args)
 {
 	pmd_t pmd;
 
-	if (!arch_vmap_pmd_supported(prot))
+	if (!arch_vmap_pmd_supported(args->page_prot))
 		return;
 
 	pr_debug("Validating PMD huge\n");
@@ -415,18 +469,18 @@ static void __init pmd_huge_tests(pmd_t *pmdp, unsigned long pfn, pgprot_t prot)
 	 * X86 defined pmd_set_huge() verifies that the given
 	 * PMD is not a populated non-leaf entry.
 	 */
-	WRITE_ONCE(*pmdp, __pmd(0));
-	WARN_ON(!pmd_set_huge(pmdp, __pfn_to_phys(pfn), prot));
-	WARN_ON(!pmd_clear_huge(pmdp));
-	pmd = READ_ONCE(*pmdp);
+	WRITE_ONCE(*args->pmdp, __pmd(0));
+	WARN_ON(!pmd_set_huge(args->pmdp, __pfn_to_phys(args->fixed_pmd_pfn), args->page_prot));
+	WARN_ON(!pmd_clear_huge(args->pmdp));
+	pmd = READ_ONCE(*args->pmdp);
 	WARN_ON(!pmd_none(pmd));
 }
 
-static void __init pud_huge_tests(pud_t *pudp, unsigned long pfn, pgprot_t prot)
+static void __init pud_huge_tests(struct pgtable_debug_args *args)
 {
 	pud_t pud;
 
-	if (!arch_vmap_pud_supported(prot))
+	if (!arch_vmap_pud_supported(args->page_prot))
 		return;
 
 	pr_debug("Validating PUD huge\n");
@@ -434,18 +488,18 @@ static void __init pud_huge_tests(pud_t *pudp, unsigned long pfn, pgprot_t prot)
 	 * X86 defined pud_set_huge() verifies that the given
 	 * PUD is not a populated non-leaf entry.
 	 */
-	WRITE_ONCE(*pudp, __pud(0));
-	WARN_ON(!pud_set_huge(pudp, __pfn_to_phys(pfn), prot));
-	WARN_ON(!pud_clear_huge(pudp));
-	pud = READ_ONCE(*pudp);
+	WRITE_ONCE(*args->pudp, __pud(0));
+	WARN_ON(!pud_set_huge(args->pudp, __pfn_to_phys(args->fixed_pud_pfn), args->page_prot));
+	WARN_ON(!pud_clear_huge(args->pudp));
+	pud = READ_ONCE(*args->pudp);
 	WARN_ON(!pud_none(pud));
 }
 #else /* !CONFIG_HAVE_ARCH_HUGE_VMAP */
-static void __init pmd_huge_tests(pmd_t *pmdp, unsigned long pfn, pgprot_t prot) { }
-static void __init pud_huge_tests(pud_t *pudp, unsigned long pfn, pgprot_t prot) { }
+static void __init pmd_huge_tests(struct pgtable_debug_args *args) { }
+static void __init pud_huge_tests(struct pgtable_debug_args *args) { }
 #endif /* CONFIG_HAVE_ARCH_HUGE_VMAP */
 
-static void __init p4d_basic_tests(unsigned long pfn, pgprot_t prot)
+static void __init p4d_basic_tests(struct pgtable_debug_args *args)
 {
 	p4d_t p4d;
 
@@ -454,7 +508,7 @@ static void __init p4d_basic_tests(unsigned long pfn, pgprot_t prot)
 	WARN_ON(!p4d_same(p4d, p4d));
 }
 
-static void __init pgd_basic_tests(unsigned long pfn, pgprot_t prot)
+static void __init pgd_basic_tests(struct pgtable_debug_args *args)
 {
 	pgd_t pgd;
 
@@ -464,27 +518,26 @@ static void __init pgd_basic_tests(unsigned long pfn, pgprot_t prot)
 }
 
 #ifndef __PAGETABLE_PUD_FOLDED
-static void __init pud_clear_tests(struct mm_struct *mm, pud_t *pudp)
+static void __init pud_clear_tests(struct pgtable_debug_args *args)
 {
-	pud_t pud = READ_ONCE(*pudp);
+	pud_t pud = READ_ONCE(*args->pudp);
 
-	if (mm_pmd_folded(mm))
+	if (mm_pmd_folded(args->mm))
 		return;
 
 	pr_debug("Validating PUD clear\n");
 	pud = __pud(pud_val(pud) | RANDOM_ORVALUE);
-	WRITE_ONCE(*pudp, pud);
-	pud_clear(pudp);
-	pud = READ_ONCE(*pudp);
+	WRITE_ONCE(*args->pudp, pud);
+	pud_clear(args->pudp);
+	pud = READ_ONCE(*args->pudp);
 	WARN_ON(!pud_none(pud));
 }
 
-static void __init pud_populate_tests(struct mm_struct *mm, pud_t *pudp,
-				      pmd_t *pmdp)
+static void __init pud_populate_tests(struct pgtable_debug_args *args)
 {
 	pud_t pud;
 
-	if (mm_pmd_folded(mm))
+	if (mm_pmd_folded(args->mm))
 		return;
 
 	pr_debug("Validating PUD populate\n");
@@ -492,40 +545,36 @@ static void __init pud_populate_tests(struct mm_struct *mm, pud_t *pudp,
 	 * This entry points to next level page table page.
 	 * Hence this must not qualify as pud_bad().
 	 */
-	pud_populate(mm, pudp, pmdp);
-	pud = READ_ONCE(*pudp);
+	pud_populate(args->mm, args->pudp, args->start_pmdp);
+	pud = READ_ONCE(*args->pudp);
 	WARN_ON(pud_bad(pud));
 }
 #else  /* !__PAGETABLE_PUD_FOLDED */
-static void __init pud_clear_tests(struct mm_struct *mm, pud_t *pudp) { }
-static void __init pud_populate_tests(struct mm_struct *mm, pud_t *pudp,
-				      pmd_t *pmdp)
-{
-}
+static void __init pud_clear_tests(struct pgtable_debug_args *args) { }
+static void __init pud_populate_tests(struct pgtable_debug_args *args) { }
 #endif /* PAGETABLE_PUD_FOLDED */
 
 #ifndef __PAGETABLE_P4D_FOLDED
-static void __init p4d_clear_tests(struct mm_struct *mm, p4d_t *p4dp)
+static void __init p4d_clear_tests(struct pgtable_debug_args *args)
 {
-	p4d_t p4d = READ_ONCE(*p4dp);
+	p4d_t p4d = READ_ONCE(*args->p4dp);
 
-	if (mm_pud_folded(mm))
+	if (mm_pud_folded(args->mm))
 		return;
 
 	pr_debug("Validating P4D clear\n");
 	p4d = __p4d(p4d_val(p4d) | RANDOM_ORVALUE);
-	WRITE_ONCE(*p4dp, p4d);
-	p4d_clear(p4dp);
-	p4d = READ_ONCE(*p4dp);
+	WRITE_ONCE(*args->p4dp, p4d);
+	p4d_clear(args->p4dp);
+	p4d = READ_ONCE(*args->p4dp);
 	WARN_ON(!p4d_none(p4d));
 }
 
-static void __init p4d_populate_tests(struct mm_struct *mm, p4d_t *p4dp,
-				      pud_t *pudp)
+static void __init p4d_populate_tests(struct pgtable_debug_args *args)
 {
 	p4d_t p4d;
 
-	if (mm_pud_folded(mm))
+	if (mm_pud_folded(args->mm))
 		return;
 
 	pr_debug("Validating P4D populate\n");
@@ -533,34 +582,33 @@ static void __init p4d_populate_tests(struct mm_struct *mm, p4d_t *p4dp,
 	 * This entry points to next level page table page.
 	 * Hence this must not qualify as p4d_bad().
 	 */
-	pud_clear(pudp);
-	p4d_clear(p4dp);
-	p4d_populate(mm, p4dp, pudp);
-	p4d = READ_ONCE(*p4dp);
+	pud_clear(args->pudp);
+	p4d_clear(args->p4dp);
+	p4d_populate(args->mm, args->p4dp, args->start_pudp);
+	p4d = READ_ONCE(*args->p4dp);
 	WARN_ON(p4d_bad(p4d));
 }
 
-static void __init pgd_clear_tests(struct mm_struct *mm, pgd_t *pgdp)
+static void __init pgd_clear_tests(struct pgtable_debug_args *args)
 {
-	pgd_t pgd = READ_ONCE(*pgdp);
+	pgd_t pgd = READ_ONCE(*(args->pgdp));
 
-	if (mm_p4d_folded(mm))
+	if (mm_p4d_folded(args->mm))
 		return;
 
 	pr_debug("Validating PGD clear\n");
 	pgd = __pgd(pgd_val(pgd) | RANDOM_ORVALUE);
-	WRITE_ONCE(*pgdp, pgd);
-	pgd_clear(pgdp);
-	pgd = READ_ONCE(*pgdp);
+	WRITE_ONCE(*args->pgdp, pgd);
+	pgd_clear(args->pgdp);
+	pgd = READ_ONCE(*args->pgdp);
 	WARN_ON(!pgd_none(pgd));
 }
 
-static void __init pgd_populate_tests(struct mm_struct *mm, pgd_t *pgdp,
-				      p4d_t *p4dp)
+static void __init pgd_populate_tests(struct pgtable_debug_args *args)
 {
 	pgd_t pgd;
 
-	if (mm_p4d_folded(mm))
+	if (mm_p4d_folded(args->mm))
 		return;
 
 	pr_debug("Validating PGD populate\n");
@@ -568,56 +616,60 @@ static void __init pgd_populate_tests(struct mm_struct *mm, pgd_t *pgdp,
 	 * This entry points to next level page table page.
 	 * Hence this must not qualify as pgd_bad().
 	 */
-	p4d_clear(p4dp);
-	pgd_clear(pgdp);
-	pgd_populate(mm, pgdp, p4dp);
-	pgd = READ_ONCE(*pgdp);
+	p4d_clear(args->p4dp);
+	pgd_clear(args->pgdp);
+	pgd_populate(args->mm, args->pgdp, args->start_p4dp);
+	pgd = READ_ONCE(*args->pgdp);
 	WARN_ON(pgd_bad(pgd));
 }
 #else  /* !__PAGETABLE_P4D_FOLDED */
-static void __init p4d_clear_tests(struct mm_struct *mm, p4d_t *p4dp) { }
-static void __init pgd_clear_tests(struct mm_struct *mm, pgd_t *pgdp) { }
-static void __init p4d_populate_tests(struct mm_struct *mm, p4d_t *p4dp,
-				      pud_t *pudp)
-{
-}
-static void __init pgd_populate_tests(struct mm_struct *mm, pgd_t *pgdp,
-				      p4d_t *p4dp)
-{
-}
+static void __init p4d_clear_tests(struct pgtable_debug_args *args) { }
+static void __init pgd_clear_tests(struct pgtable_debug_args *args) { }
+static void __init p4d_populate_tests(struct pgtable_debug_args *args) { }
+static void __init pgd_populate_tests(struct pgtable_debug_args *args) { }
 #endif /* PAGETABLE_P4D_FOLDED */
 
-static void __init pte_clear_tests(struct mm_struct *mm, pte_t *ptep,
-				   unsigned long pfn, unsigned long vaddr,
-				   pgprot_t prot)
+static void __init pte_clear_tests(struct pgtable_debug_args *args)
 {
-	pte_t pte = pfn_pte(pfn, prot);
+	struct page *page;
+	pte_t pte = pfn_pte(args->pte_pfn, args->page_prot);
+
+	page = (args->pte_pfn != ULONG_MAX) ? pfn_to_page(args->pte_pfn) : NULL;
+	if (!page)
+		return;
 
+	/*
+	 * flush_dcache_page() is called after set_pte_at() to clear
+	 * PG_arch_1 for the page on ARM64. The page flag isn't cleared
+	 * when it's released and page allocation check will fail when
+	 * the page is allocated again. For architectures other than ARM64,
+	 * the unexpected overhead of cache flushing is acceptable.
+	 */
 	pr_debug("Validating PTE clear\n");
 #ifndef CONFIG_RISCV
 	pte = __pte(pte_val(pte) | RANDOM_ORVALUE);
 #endif
-	set_pte_at(mm, vaddr, ptep, pte);
+	set_pte_at(args->mm, args->vaddr, args->ptep, pte);
+	flush_dcache_page(page);
 	barrier();
-	pte_clear(mm, vaddr, ptep);
-	pte = ptep_get(ptep);
+	pte_clear(args->mm, args->vaddr, args->ptep);
+	pte = ptep_get(args->ptep);
 	WARN_ON(!pte_none(pte));
 }
 
-static void __init pmd_clear_tests(struct mm_struct *mm, pmd_t *pmdp)
+static void __init pmd_clear_tests(struct pgtable_debug_args *args)
 {
-	pmd_t pmd = READ_ONCE(*pmdp);
+	pmd_t pmd = READ_ONCE(*args->pmdp);
 
 	pr_debug("Validating PMD clear\n");
 	pmd = __pmd(pmd_val(pmd) | RANDOM_ORVALUE);
-	WRITE_ONCE(*pmdp, pmd);
-	pmd_clear(pmdp);
-	pmd = READ_ONCE(*pmdp);
+	WRITE_ONCE(*args->pmdp, pmd);
+	pmd_clear(args->pmdp);
+	pmd = READ_ONCE(*args->pmdp);
 	WARN_ON(!pmd_none(pmd));
 }
 
-static void __init pmd_populate_tests(struct mm_struct *mm, pmd_t *pmdp,
-				      pgtable_t pgtable)
+static void __init pmd_populate_tests(struct pgtable_debug_args *args)
 {
 	pmd_t pmd;
 
@@ -626,14 +678,14 @@ static void __init pmd_populate_tests(struct mm_struct *mm, pmd_t *pmdp,
 	 * This entry points to next level page table page.
 	 * Hence this must not qualify as pmd_bad().
 	 */
-	pmd_populate(mm, pmdp, pgtable);
-	pmd = READ_ONCE(*pmdp);
+	pmd_populate(args->mm, args->pmdp, args->start_ptep);
+	pmd = READ_ONCE(*args->pmdp);
 	WARN_ON(pmd_bad(pmd));
 }
 
-static void __init pte_special_tests(unsigned long pfn, pgprot_t prot)
+static void __init pte_special_tests(struct pgtable_debug_args *args)
 {
-	pte_t pte = pfn_pte(pfn, prot);
+	pte_t pte = pfn_pte(args->fixed_pte_pfn, args->page_prot);
 
 	if (!IS_ENABLED(CONFIG_ARCH_HAS_PTE_SPECIAL))
 		return;
@@ -642,9 +694,9 @@ static void __init pte_special_tests(unsigned long pfn, pgprot_t prot)
 	WARN_ON(!pte_special(pte_mkspecial(pte)));
 }
 
-static void __init pte_protnone_tests(unsigned long pfn, pgprot_t prot)
+static void __init pte_protnone_tests(struct pgtable_debug_args *args)
 {
-	pte_t pte = pfn_pte(pfn, prot);
+	pte_t pte = pfn_pte(args->fixed_pte_pfn, args->page_prot_none);
 
 	if (!IS_ENABLED(CONFIG_NUMA_BALANCING))
 		return;
@@ -655,7 +707,7 @@ static void __init pte_protnone_tests(unsigned long pfn, pgprot_t prot)
 }
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
-static void __init pmd_protnone_tests(unsigned long pfn, pgprot_t prot)
+static void __init pmd_protnone_tests(struct pgtable_debug_args *args)
 {
 	pmd_t pmd;
 
@@ -666,25 +718,25 @@ static void __init pmd_protnone_tests(unsigned long pfn, pgprot_t prot)
 		return;
 
 	pr_debug("Validating PMD protnone\n");
-	pmd = pmd_mkhuge(pfn_pmd(pfn, prot));
+	pmd = pmd_mkhuge(pfn_pmd(args->fixed_pmd_pfn, args->page_prot_none));
 	WARN_ON(!pmd_protnone(pmd));
 	WARN_ON(!pmd_present(pmd));
 }
 #else  /* !CONFIG_TRANSPARENT_HUGEPAGE */
-static void __init pmd_protnone_tests(unsigned long pfn, pgprot_t prot) { }
+static void __init pmd_protnone_tests(struct pgtable_debug_args *args) { }
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 
 #ifdef CONFIG_ARCH_HAS_PTE_DEVMAP
-static void __init pte_devmap_tests(unsigned long pfn, pgprot_t prot)
+static void __init pte_devmap_tests(struct pgtable_debug_args *args)
 {
-	pte_t pte = pfn_pte(pfn, prot);
+	pte_t pte = pfn_pte(args->fixed_pte_pfn, args->page_prot);
 
 	pr_debug("Validating PTE devmap\n");
 	WARN_ON(!pte_devmap(pte_mkdevmap(pte)));
 }
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
-static void __init pmd_devmap_tests(unsigned long pfn, pgprot_t prot)
+static void __init pmd_devmap_tests(struct pgtable_debug_args *args)
 {
 	pmd_t pmd;
 
@@ -692,12 +744,12 @@ static void __init pmd_devmap_tests(unsigned long pfn, pgprot_t prot)
 		return;
 
 	pr_debug("Validating PMD devmap\n");
-	pmd = pfn_pmd(pfn, prot);
+	pmd = pfn_pmd(args->fixed_pmd_pfn, args->page_prot);
 	WARN_ON(!pmd_devmap(pmd_mkdevmap(pmd)));
 }
 
 #ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
-static void __init pud_devmap_tests(unsigned long pfn, pgprot_t prot)
+static void __init pud_devmap_tests(struct pgtable_debug_args *args)
 {
 	pud_t pud;
 
@@ -705,25 +757,25 @@ static void __init pud_devmap_tests(unsigned long pfn, pgprot_t prot)
 		return;
 
 	pr_debug("Validating PUD devmap\n");
-	pud = pfn_pud(pfn, prot);
+	pud = pfn_pud(args->fixed_pud_pfn, args->page_prot);
 	WARN_ON(!pud_devmap(pud_mkdevmap(pud)));
 }
 #else  /* !CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */
-static void __init pud_devmap_tests(unsigned long pfn, pgprot_t prot) { }
+static void __init pud_devmap_tests(struct pgtable_debug_args *args) { }
 #endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */
 #else  /* CONFIG_TRANSPARENT_HUGEPAGE */
-static void __init pmd_devmap_tests(unsigned long pfn, pgprot_t prot) { }
-static void __init pud_devmap_tests(unsigned long pfn, pgprot_t prot) { }
+static void __init pmd_devmap_tests(struct pgtable_debug_args *args) { }
+static void __init pud_devmap_tests(struct pgtable_debug_args *args) { }
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 #else
-static void __init pte_devmap_tests(unsigned long pfn, pgprot_t prot) { }
-static void __init pmd_devmap_tests(unsigned long pfn, pgprot_t prot) { }
-static void __init pud_devmap_tests(unsigned long pfn, pgprot_t prot) { }
+static void __init pte_devmap_tests(struct pgtable_debug_args *args) { }
+static void __init pmd_devmap_tests(struct pgtable_debug_args *args) { }
+static void __init pud_devmap_tests(struct pgtable_debug_args *args) { }
 #endif /* CONFIG_ARCH_HAS_PTE_DEVMAP */
 
-static void __init pte_soft_dirty_tests(unsigned long pfn, pgprot_t prot)
+static void __init pte_soft_dirty_tests(struct pgtable_debug_args *args)
 {
-	pte_t pte = pfn_pte(pfn, prot);
+	pte_t pte = pfn_pte(args->fixed_pte_pfn, args->page_prot);
 
 	if (!IS_ENABLED(CONFIG_MEM_SOFT_DIRTY))
 		return;
@@ -733,9 +785,9 @@ static void __init pte_soft_dirty_tests(unsigned long pfn, pgprot_t prot)
 	WARN_ON(pte_soft_dirty(pte_clear_soft_dirty(pte)));
 }
 
-static void __init pte_swap_soft_dirty_tests(unsigned long pfn, pgprot_t prot)
+static void __init pte_swap_soft_dirty_tests(struct pgtable_debug_args *args)
 {
-	pte_t pte = pfn_pte(pfn, prot);
+	pte_t pte = pfn_pte(args->fixed_pte_pfn, args->page_prot);
 
 	if (!IS_ENABLED(CONFIG_MEM_SOFT_DIRTY))
 		return;
@@ -746,7 +798,7 @@ static void __init pte_swap_soft_dirty_tests(unsigned long pfn, pgprot_t prot)
 }
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
-static void __init pmd_soft_dirty_tests(unsigned long pfn, pgprot_t prot)
+static void __init pmd_soft_dirty_tests(struct pgtable_debug_args *args)
 {
 	pmd_t pmd;
 
@@ -757,12 +809,12 @@ static void __init pmd_soft_dirty_tests(unsigned long pfn, pgprot_t prot)
 		return;
 
 	pr_debug("Validating PMD soft dirty\n");
-	pmd = pfn_pmd(pfn, prot);
+	pmd = pfn_pmd(args->fixed_pmd_pfn, args->page_prot);
 	WARN_ON(!pmd_soft_dirty(pmd_mksoft_dirty(pmd)));
 	WARN_ON(pmd_soft_dirty(pmd_clear_soft_dirty(pmd)));
 }
 
-static void __init pmd_swap_soft_dirty_tests(unsigned long pfn, pgprot_t prot)
+static void __init pmd_swap_soft_dirty_tests(struct pgtable_debug_args *args)
 {
 	pmd_t pmd;
 
@@ -774,31 +826,29 @@ static void __init pmd_swap_soft_dirty_tests(unsigned long pfn, pgprot_t prot)
 		return;
 
 	pr_debug("Validating PMD swap soft dirty\n");
-	pmd = pfn_pmd(pfn, prot);
+	pmd = pfn_pmd(args->fixed_pmd_pfn, args->page_prot);
 	WARN_ON(!pmd_swp_soft_dirty(pmd_swp_mksoft_dirty(pmd)));
 	WARN_ON(pmd_swp_soft_dirty(pmd_swp_clear_soft_dirty(pmd)));
 }
 #else  /* !CONFIG_TRANSPARENT_HUGEPAGE */
-static void __init pmd_soft_dirty_tests(unsigned long pfn, pgprot_t prot) { }
-static void __init pmd_swap_soft_dirty_tests(unsigned long pfn, pgprot_t prot)
-{
-}
+static void __init pmd_soft_dirty_tests(struct pgtable_debug_args *args) { }
+static void __init pmd_swap_soft_dirty_tests(struct pgtable_debug_args *args) { }
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 
-static void __init pte_swap_tests(unsigned long pfn, pgprot_t prot)
+static void __init pte_swap_tests(struct pgtable_debug_args *args)
 {
 	swp_entry_t swp;
 	pte_t pte;
 
 	pr_debug("Validating PTE swap\n");
-	pte = pfn_pte(pfn, prot);
+	pte = pfn_pte(args->fixed_pte_pfn, args->page_prot);
 	swp = __pte_to_swp_entry(pte);
 	pte = __swp_entry_to_pte(swp);
-	WARN_ON(pfn != pte_pfn(pte));
+	WARN_ON(args->fixed_pte_pfn != pte_pfn(pte));
 }
 
 #ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION
-static void __init pmd_swap_tests(unsigned long pfn, pgprot_t prot)
+static void __init pmd_swap_tests(struct pgtable_debug_args *args)
 {
 	swp_entry_t swp;
 	pmd_t pmd;
@@ -807,16 +857,16 @@ static void __init pmd_swap_tests(unsigned long pfn, pgprot_t prot)
 		return;
 
 	pr_debug("Validating PMD swap\n");
-	pmd = pfn_pmd(pfn, prot);
+	pmd = pfn_pmd(args->fixed_pmd_pfn, args->page_prot);
 	swp = __pmd_to_swp_entry(pmd);
 	pmd = __swp_entry_to_pmd(swp);
-	WARN_ON(pfn != pmd_pfn(pmd));
+	WARN_ON(args->fixed_pmd_pfn != pmd_pfn(pmd));
 }
 #else  /* !CONFIG_ARCH_ENABLE_THP_MIGRATION */
-static void __init pmd_swap_tests(unsigned long pfn, pgprot_t prot) { }
+static void __init pmd_swap_tests(struct pgtable_debug_args *args) { }
 #endif /* CONFIG_ARCH_ENABLE_THP_MIGRATION */
 
-static void __init swap_migration_tests(void)
+static void __init swap_migration_tests(struct pgtable_debug_args *args)
 {
 	struct page *page;
 	swp_entry_t swp;
@@ -824,19 +874,18 @@ static void __init swap_migration_tests(void)
 	if (!IS_ENABLED(CONFIG_MIGRATION))
 		return;
 
-	pr_debug("Validating swap migration\n");
 	/*
 	 * swap_migration_tests() requires a dedicated page as it needs to
 	 * be locked before creating a migration entry from it. Locking the
 	 * page that actually maps kernel text ('start_kernel') can be real
-	 * problematic. Lets allocate a dedicated page explicitly for this
-	 * purpose that will be freed subsequently.
+	 * problematic. Lets use the allocated page explicitly for this
+	 * purpose.
 	 */
-	page = alloc_page(GFP_KERNEL);
-	if (!page) {
-		pr_err("page allocation failed\n");
+	page = (args->pte_pfn != ULONG_MAX) ? pfn_to_page(args->pte_pfn) : NULL;
+	if (!page)
 		return;
-	}
+
+	pr_debug("Validating swap migration\n");
 
 	/*
 	 * make_migration_entry() expects given page to be
@@ -855,11 +904,10 @@ static void __init swap_migration_tests(void)
 	WARN_ON(!is_migration_entry(swp));
 	WARN_ON(is_writable_migration_entry(swp));
 	__ClearPageLocked(page);
-	__free_page(page);
 }
 
 #ifdef CONFIG_HUGETLB_PAGE
-static void __init hugetlb_basic_tests(unsigned long pfn, pgprot_t prot)
+static void __init hugetlb_basic_tests(struct pgtable_debug_args *args)
 {
 	struct page *page;
 	pte_t pte;
@@ -869,25 +917,25 @@ static void __init hugetlb_basic_tests(unsigned long pfn, pgprot_t prot)
 	 * Accessing the page associated with the pfn is safe here,
 	 * as it was previously derived from a real kernel symbol.
 	 */
-	page = pfn_to_page(pfn);
-	pte = mk_huge_pte(page, prot);
+	page = pfn_to_page(args->fixed_pmd_pfn);
+	pte = mk_huge_pte(page, args->page_prot);
 
 	WARN_ON(!huge_pte_dirty(huge_pte_mkdirty(pte)));
 	WARN_ON(!huge_pte_write(huge_pte_mkwrite(huge_pte_wrprotect(pte))));
 	WARN_ON(huge_pte_write(huge_pte_wrprotect(huge_pte_mkwrite(pte))));
 
 #ifdef CONFIG_ARCH_WANT_GENERAL_HUGETLB
-	pte = pfn_pte(pfn, prot);
+	pte = pfn_pte(args->fixed_pmd_pfn, args->page_prot);
 
 	WARN_ON(!pte_huge(pte_mkhuge(pte)));
 #endif /* CONFIG_ARCH_WANT_GENERAL_HUGETLB */
 }
 #else  /* !CONFIG_HUGETLB_PAGE */
-static void __init hugetlb_basic_tests(unsigned long pfn, pgprot_t prot) { }
+static void __init hugetlb_basic_tests(struct pgtable_debug_args *args) { }
 #endif /* CONFIG_HUGETLB_PAGE */
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
-static void __init pmd_thp_tests(unsigned long pfn, pgprot_t prot)
+static void __init pmd_thp_tests(struct pgtable_debug_args *args)
 {
 	pmd_t pmd;
 
@@ -906,7 +954,7 @@ static void __init pmd_thp_tests(unsigned long pfn, pgprot_t prot)
 	 * needs to return true. pmd_present() should be true whenever
 	 * pmd_trans_huge() returns true.
 	 */
-	pmd = pfn_pmd(pfn, prot);
+	pmd = pfn_pmd(args->fixed_pmd_pfn, args->page_prot);
 	WARN_ON(!pmd_trans_huge(pmd_mkhuge(pmd)));
 
 #ifndef __HAVE_ARCH_PMDP_INVALIDATE
@@ -916,7 +964,7 @@ static void __init pmd_thp_tests(unsigned long pfn, pgprot_t prot)
 }
 
 #ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
-static void __init pud_thp_tests(unsigned long pfn, pgprot_t prot)
+static void __init pud_thp_tests(struct pgtable_debug_args *args)
 {
 	pud_t pud;
 
@@ -924,7 +972,7 @@ static void __init pud_thp_tests(unsigned long pfn, pgprot_t prot)
 		return;
 
 	pr_debug("Validating PUD based THP\n");
-	pud = pfn_pud(pfn, prot);
+	pud = pfn_pud(args->fixed_pud_pfn, args->page_prot);
 	WARN_ON(!pud_trans_huge(pud_mkhuge(pud)));
 
 	/*
@@ -936,11 +984,11 @@ static void __init pud_thp_tests(unsigned long pfn, pgprot_t prot)
 	 */
 }
 #else  /* !CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */
-static void __init pud_thp_tests(unsigned long pfn, pgprot_t prot) { }
+static void __init pud_thp_tests(struct pgtable_debug_args *args) { }
 #endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */
 #else  /* !CONFIG_TRANSPARENT_HUGEPAGE */
-static void __init pmd_thp_tests(unsigned long pfn, pgprot_t prot) { }
-static void __init pud_thp_tests(unsigned long pfn, pgprot_t prot) { }
+static void __init pmd_thp_tests(struct pgtable_debug_args *args) { }
+static void __init pud_thp_tests(struct pgtable_debug_args *args) { }
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 
 static unsigned long __init get_random_vaddr(void)
@@ -955,43 +1003,179 @@ static unsigned long __init get_random_vaddr(void)
 	return random_vaddr;
 }
 
-static int __init debug_vm_pgtable(void)
+static void __init destroy_args(struct pgtable_debug_args *args)
 {
-	struct vm_area_struct *vma;
-	struct mm_struct *mm;
-	pgd_t *pgdp;
-	p4d_t *p4dp, *saved_p4dp;
-	pud_t *pudp, *saved_pudp;
-	pmd_t *pmdp, *saved_pmdp, pmd;
-	pte_t *ptep;
-	pgtable_t saved_ptep;
-	pgprot_t prot, protnone;
-	phys_addr_t paddr;
-	unsigned long vaddr, pte_aligned, pmd_aligned;
-	unsigned long pud_aligned, p4d_aligned, pgd_aligned;
-	spinlock_t *ptl = NULL;
-	int idx;
+	struct page *page = NULL;
+
+	/* Free (huge) page */
+	if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) &&
+	    IS_ENABLED(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD) &&
+	    has_transparent_hugepage() &&
+	    args->pud_pfn != ULONG_MAX) {
+		if (args->is_contiguous_page) {
+			free_contig_range(args->pud_pfn,
+					  (1 << (HPAGE_PUD_SHIFT - PAGE_SHIFT)));
+		} else {
+			page = pfn_to_page(args->pud_pfn);
+			__free_pages(page, HPAGE_PUD_SHIFT - PAGE_SHIFT);
+		}
+
+		args->pud_pfn = ULONG_MAX;
+		args->pmd_pfn = ULONG_MAX;
+		args->pte_pfn = ULONG_MAX;
+	}
 
-	pr_info("Validating architecture page table helpers\n");
-	prot = vm_get_page_prot(VMFLAGS);
-	vaddr = get_random_vaddr();
-	mm = mm_alloc();
-	if (!mm) {
-		pr_err("mm_struct allocation failed\n");
-		return 1;
+	if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) &&
+	    has_transparent_hugepage() &&
+	    args->pmd_pfn != ULONG_MAX) {
+		if (args->is_contiguous_page) {
+			free_contig_range(args->pmd_pfn, (1 << HPAGE_PMD_ORDER));
+		} else {
+			page = pfn_to_page(args->pmd_pfn);
+			__free_pages(page, HPAGE_PMD_ORDER);
+		}
+
+		args->pmd_pfn = ULONG_MAX;
+		args->pte_pfn = ULONG_MAX;
 	}
 
+	if (args->pte_pfn != ULONG_MAX) {
+		page = pfn_to_page(args->pte_pfn);
+		__free_pages(page, 0);
+
+		args->pte_pfn = ULONG_MAX;
+	}
+
+	/* Free page table entries */
+	if (args->start_ptep) {
+		pte_free(args->mm, args->start_ptep);
+		mm_dec_nr_ptes(args->mm);
+	}
+
+	if (args->start_pmdp) {
+		pmd_free(args->mm, args->start_pmdp);
+		mm_dec_nr_pmds(args->mm);
+	}
+
+	if (args->start_pudp) {
+		pud_free(args->mm, args->start_pudp);
+		mm_dec_nr_puds(args->mm);
+	}
+
+	if (args->start_p4dp)
+		p4d_free(args->mm, args->start_p4dp);
+
+	/* Free vma and mm struct */
+	if (args->vma)
+		vm_area_free(args->vma);
+
+	if (args->mm)
+		mmdrop(args->mm);
+}
+
+static struct page * __init
+debug_vm_pgtable_alloc_huge_page(struct pgtable_debug_args *args, int order)
+{
+	struct page *page = NULL;
+
+#ifdef CONFIG_CONTIG_ALLOC
+	if (order >= MAX_ORDER) {
+		page = alloc_contig_pages((1 << order), GFP_KERNEL,
+					  first_online_node, NULL);
+		if (page) {
+			args->is_contiguous_page = true;
+			return page;
+		}
+	}
+#endif
+
+	if (order < MAX_ORDER)
+		page = alloc_pages(GFP_KERNEL, order);
+
+	return page;
+}
+
+static int __init init_args(struct pgtable_debug_args *args)
+{
+	struct page *page = NULL;
+	phys_addr_t phys;
+	int ret = 0;
+
 	/*
+	 * Initialize the debugging data.
+	 *
 	 * __P000 (or even __S000) will help create page table entries with
 	 * PROT_NONE permission as required for pxx_protnone_tests().
 	 */
-	protnone = __P000;
+	memset(args, 0, sizeof(*args));
+	args->vaddr              = get_random_vaddr();
+	args->page_prot          = vm_get_page_prot(VMFLAGS);
+	args->page_prot_none     = __P000;
+	args->is_contiguous_page = false;
+	args->pud_pfn            = ULONG_MAX;
+	args->pmd_pfn            = ULONG_MAX;
+	args->pte_pfn            = ULONG_MAX;
+	args->fixed_pgd_pfn      = ULONG_MAX;
+	args->fixed_p4d_pfn      = ULONG_MAX;
+	args->fixed_pud_pfn      = ULONG_MAX;
+	args->fixed_pmd_pfn      = ULONG_MAX;
+	args->fixed_pte_pfn      = ULONG_MAX;
+
+	/* Allocate mm and vma */
+	args->mm = mm_alloc();
+	if (!args->mm) {
+		pr_err("Failed to allocate mm struct\n");
+		ret = -ENOMEM;
+		goto error;
+	}
+
+	args->vma = vm_area_alloc(args->mm);
+	if (!args->vma) {
+		pr_err("Failed to allocate vma\n");
+		ret = -ENOMEM;
+		goto error;
+	}
+
+	/*
+	 * Allocate page table entries. They will be modified in the tests.
+	 * Lets save the page table entries so that they can be released
+	 * when the tests are completed.
+	 */
+	args->pgdp = pgd_offset(args->mm, args->vaddr);
+	args->p4dp = p4d_alloc(args->mm, args->pgdp, args->vaddr);
+	if (!args->p4dp) {
+		pr_err("Failed to allocate p4d entries\n");
+		ret = -ENOMEM;
+		goto error;
+	}
+	args->start_p4dp = p4d_offset(args->pgdp, 0UL);
+	WARN_ON(!args->start_p4dp);
+
+	args->pudp = pud_alloc(args->mm, args->p4dp, args->vaddr);
+	if (!args->pudp) {
+		pr_err("Failed to allocate pud entries\n");
+		ret = -ENOMEM;
+		goto error;
+	}
+	args->start_pudp = pud_offset(args->p4dp, 0UL);
+	WARN_ON(!args->start_pudp);
+
+	args->pmdp = pmd_alloc(args->mm, args->pudp, args->vaddr);
+	if (!args->pmdp) {
+		pr_err("Failed to allocate pmd entries\n");
+		ret = -ENOMEM;
+		goto error;
+	}
+	args->start_pmdp = pmd_offset(args->pudp, 0UL);
+	WARN_ON(!args->start_pmdp);
 
-	vma = vm_area_alloc(mm);
-	if (!vma) {
-		pr_err("vma allocation failed\n");
-		return 1;
+	if (pte_alloc(args->mm, args->pmdp)) {
+		pr_err("Failed to allocate pte entries\n");
+		ret = -ENOMEM;
+		goto error;
 	}
+	args->start_ptep = pmd_pgtable(READ_ONCE(*args->pmdp));
+	WARN_ON(!args->start_ptep);
 
 	/*
 	 * PFN for mapping at PTE level is determined from a standard kernel
@@ -1000,40 +1184,65 @@ static int __init debug_vm_pgtable(void)
 	 * exist on the platform but that does not really matter as pfn_pxx()
 	 * helpers will still create appropriate entries for the test. This
 	 * helps avoid large memory block allocations to be used for mapping
-	 * at higher page table levels.
+	 * at higher page table levels in some of the tests.
 	 */
-	paddr = __pa_symbol(&start_kernel);
-
-	pte_aligned = (paddr & PAGE_MASK) >> PAGE_SHIFT;
-	pmd_aligned = (paddr & PMD_MASK) >> PAGE_SHIFT;
-	pud_aligned = (paddr & PUD_MASK) >> PAGE_SHIFT;
-	p4d_aligned = (paddr & P4D_MASK) >> PAGE_SHIFT;
-	pgd_aligned = (paddr & PGDIR_MASK) >> PAGE_SHIFT;
-	WARN_ON(!pfn_valid(pte_aligned));
-
-	pgdp = pgd_offset(mm, vaddr);
-	p4dp = p4d_alloc(mm, pgdp, vaddr);
-	pudp = pud_alloc(mm, p4dp, vaddr);
-	pmdp = pmd_alloc(mm, pudp, vaddr);
+	phys = __pa_symbol(&start_kernel);
+	args->fixed_pgd_pfn = __phys_to_pfn(phys & PGDIR_MASK);
+	args->fixed_p4d_pfn = __phys_to_pfn(phys & P4D_MASK);
+	args->fixed_pud_pfn = __phys_to_pfn(phys & PUD_MASK);
+	args->fixed_pmd_pfn = __phys_to_pfn(phys & PMD_MASK);
+	args->fixed_pte_pfn = __phys_to_pfn(phys & PAGE_MASK);
+	WARN_ON(!pfn_valid(args->fixed_pte_pfn));
+
 	/*
-	 * Allocate pgtable_t
+	 * Allocate (huge) pages because some of the tests need to access
+	 * the data in the pages. The corresponding tests will be skipped
+	 * if we fail to allocate (huge) pages.
 	 */
-	if (pte_alloc(mm, pmdp)) {
-		pr_err("pgtable allocation failed\n");
-		return 1;
+	if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) &&
+	    IS_ENABLED(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD) &&
+	    has_transparent_hugepage()) {
+		page = debug_vm_pgtable_alloc_huge_page(args,
+				HPAGE_PUD_SHIFT - PAGE_SHIFT);
+		if (page) {
+			args->pud_pfn = page_to_pfn(page);
+			args->pmd_pfn = args->pud_pfn;
+			args->pte_pfn = args->pud_pfn;
+			return 0;
+		}
 	}
 
-	/*
-	 * Save all the page table page addresses as the page table
-	 * entries will be used for testing with random or garbage
-	 * values. These saved addresses will be used for freeing
-	 * page table pages.
-	 */
-	pmd = READ_ONCE(*pmdp);
-	saved_p4dp = p4d_offset(pgdp, 0UL);
-	saved_pudp = pud_offset(p4dp, 0UL);
-	saved_pmdp = pmd_offset(pudp, 0UL);
-	saved_ptep = pmd_pgtable(pmd);
+	if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) &&
+	    has_transparent_hugepage()) {
+		page = debug_vm_pgtable_alloc_huge_page(args, HPAGE_PMD_ORDER);
+		if (page) {
+			args->pmd_pfn = page_to_pfn(page);
+			args->pte_pfn = args->pmd_pfn;
+			return 0;
+		}
+	}
+
+	page = alloc_pages(GFP_KERNEL, 0);
+	if (page)
+		args->pte_pfn = page_to_pfn(page);
+
+	return 0;
+
+error:
+	destroy_args(args);
+	return ret;
+}
+
+static int __init debug_vm_pgtable(void)
+{
+	struct pgtable_debug_args args;
+	spinlock_t *ptl = NULL;
+	int idx, ret;
+
+	pr_info("Validating architecture page table helpers\n");
+	ret = init_args(&args);
+	if (ret)
+		return ret;
 
 	/*
 	 * Iterate over the protection_map[] to make sure that all
@@ -1042,9 +1251,9 @@ static int __init debug_vm_pgtable(void)
 	 * given page table entry.
 	 */
 	for (idx = 0; idx < ARRAY_SIZE(protection_map); idx++) {
-		pte_basic_tests(pte_aligned, idx);
-		pmd_basic_tests(pmd_aligned, idx);
-		pud_basic_tests(mm, pud_aligned, idx);
+		pte_basic_tests(&args, idx);
+		pmd_basic_tests(&args, idx);
+		pud_basic_tests(&args, idx);
 	}
 
 	/*
@@ -1054,79 +1263,70 @@ static int __init debug_vm_pgtable(void)
 	 * the above iteration for now to save some test execution
 	 * time.
 	 */
-	p4d_basic_tests(p4d_aligned, prot);
-	pgd_basic_tests(pgd_aligned, prot);
+	p4d_basic_tests(&args);
+	pgd_basic_tests(&args);
 
-	pmd_leaf_tests(pmd_aligned, prot);
-	pud_leaf_tests(pud_aligned, prot);
+	pmd_leaf_tests(&args);
+	pud_leaf_tests(&args);
 
-	pte_savedwrite_tests(pte_aligned, protnone);
-	pmd_savedwrite_tests(pmd_aligned, protnone);
+	pte_savedwrite_tests(&args);
+	pmd_savedwrite_tests(&args);
 
-	pte_special_tests(pte_aligned, prot);
-	pte_protnone_tests(pte_aligned, protnone);
-	pmd_protnone_tests(pmd_aligned, protnone);
+	pte_special_tests(&args);
+	pte_protnone_tests(&args);
+	pmd_protnone_tests(&args);
 
-	pte_devmap_tests(pte_aligned, prot);
-	pmd_devmap_tests(pmd_aligned, prot);
-	pud_devmap_tests(pud_aligned, prot);
+	pte_devmap_tests(&args);
+	pmd_devmap_tests(&args);
+	pud_devmap_tests(&args);
 
-	pte_soft_dirty_tests(pte_aligned, prot);
-	pmd_soft_dirty_tests(pmd_aligned, prot);
-	pte_swap_soft_dirty_tests(pte_aligned, prot);
-	pmd_swap_soft_dirty_tests(pmd_aligned, prot);
+	pte_soft_dirty_tests(&args);
+	pmd_soft_dirty_tests(&args);
+	pte_swap_soft_dirty_tests(&args);
+	pmd_swap_soft_dirty_tests(&args);
 
-	pte_swap_tests(pte_aligned, prot);
-	pmd_swap_tests(pmd_aligned, prot);
+	pte_swap_tests(&args);
+	pmd_swap_tests(&args);
 
-	swap_migration_tests();
+	swap_migration_tests(&args);
 
-	pmd_thp_tests(pmd_aligned, prot);
-	pud_thp_tests(pud_aligned, prot);
+	pmd_thp_tests(&args);
+	pud_thp_tests(&args);
 
-	hugetlb_basic_tests(pte_aligned, prot);
+	hugetlb_basic_tests(&args);
 
 	/*
 	 * Page table modifying tests. They need to hold
 	 * proper page table lock.
 	 */
 
-	ptep = pte_offset_map_lock(mm, pmdp, vaddr, &ptl);
-	pte_clear_tests(mm, ptep, pte_aligned, vaddr, prot);
-	pte_advanced_tests(mm, vma, ptep, pte_aligned, vaddr, prot);
-	pte_unmap_unlock(ptep, ptl);
+	args.ptep = pte_offset_map_lock(args.mm, args.pmdp, args.vaddr, &ptl);
+	pte_clear_tests(&args);
+	pte_advanced_tests(&args);
+	pte_unmap_unlock(args.ptep, ptl);
 
-	ptl = pmd_lock(mm, pmdp);
-	pmd_clear_tests(mm, pmdp);
-	pmd_advanced_tests(mm, vma, pmdp, pmd_aligned, vaddr, prot, saved_ptep);
-	pmd_huge_tests(pmdp, pmd_aligned, prot);
-	pmd_populate_tests(mm, pmdp, saved_ptep);
+	ptl = pmd_lock(args.mm, args.pmdp);
+	pmd_clear_tests(&args);
+	pmd_advanced_tests(&args);
+	pmd_huge_tests(&args);
+	pmd_populate_tests(&args);
 	spin_unlock(ptl);
 
-	ptl = pud_lock(mm, pudp);
-	pud_clear_tests(mm, pudp);
-	pud_advanced_tests(mm, vma, pudp, pud_aligned, vaddr, prot);
-	pud_huge_tests(pudp, pud_aligned, prot);
-	pud_populate_tests(mm, pudp, saved_pmdp);
+	ptl = pud_lock(args.mm, args.pudp);
+	pud_clear_tests(&args);
+	pud_advanced_tests(&args);
+	pud_huge_tests(&args);
+	pud_populate_tests(&args);
 	spin_unlock(ptl);
 
-	spin_lock(&mm->page_table_lock);
-	p4d_clear_tests(mm, p4dp);
-	pgd_clear_tests(mm, pgdp);
-	p4d_populate_tests(mm, p4dp, saved_pudp);
-	pgd_populate_tests(mm, pgdp, saved_p4dp);
-	spin_unlock(&mm->page_table_lock);
-
-	p4d_free(mm, saved_p4dp);
-	pud_free(mm, saved_pudp);
-	pmd_free(mm, saved_pmdp);
-	pte_free(mm, saved_ptep);
-
-	vm_area_free(vma);
-	mm_dec_nr_puds(mm);
-	mm_dec_nr_pmds(mm);
-	mm_dec_nr_ptes(mm);
-	mmdrop(mm);
+	spin_lock(&(args.mm->page_table_lock));
+	p4d_clear_tests(&args);
+	pgd_clear_tests(&args);
+	p4d_populate_tests(&args);
+	pgd_populate_tests(&args);
+	spin_unlock(&(args.mm->page_table_lock));
+
+	destroy_args(&args);
 	return 0;
 }
 late_initcall(debug_vm_pgtable);
diff --git a/mm/filemap.c b/mm/filemap.c
index 920e8dc03251..dae481293b5d 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -260,12 +260,11 @@ static void page_cache_free_page(struct address_space *mapping,
 void delete_from_page_cache(struct page *page)
 {
 	struct address_space *mapping = page_mapping(page);
-	unsigned long flags;
 
 	BUG_ON(!PageLocked(page));
-	xa_lock_irqsave(&mapping->i_pages, flags);
+	xa_lock_irq(&mapping->i_pages);
 	__delete_from_page_cache(page, NULL);
-	xa_unlock_irqrestore(&mapping->i_pages, flags);
+	xa_unlock_irq(&mapping->i_pages);
 
 	page_cache_free_page(mapping, page);
 }
@@ -337,19 +336,18 @@ void delete_from_page_cache_batch(struct address_space *mapping,
 				  struct pagevec *pvec)
 {
 	int i;
-	unsigned long flags;
 
 	if (!pagevec_count(pvec))
 		return;
 
-	xa_lock_irqsave(&mapping->i_pages, flags);
+	xa_lock_irq(&mapping->i_pages);
 	for (i = 0; i < pagevec_count(pvec); i++) {
 		trace_mm_filemap_delete_from_page_cache(pvec->pages[i]);
 
 		unaccount_page_cache_page(mapping, pvec->pages[i]);
 	}
 	page_cache_delete_batch(mapping, pvec);
-	xa_unlock_irqrestore(&mapping->i_pages, flags);
+	xa_unlock_irq(&mapping->i_pages);
 
 	for (i = 0; i < pagevec_count(pvec); i++)
 		page_cache_free_page(mapping, pvec->pages[i]);
@@ -841,7 +839,6 @@ void replace_page_cache_page(struct page *old, struct page *new)
 	void (*freepage)(struct page *) = mapping->a_ops->freepage;
 	pgoff_t offset = old->index;
 	XA_STATE(xas, &mapping->i_pages, offset);
-	unsigned long flags;
 
 	VM_BUG_ON_PAGE(!PageLocked(old), old);
 	VM_BUG_ON_PAGE(!PageLocked(new), new);
@@ -853,7 +850,7 @@ void replace_page_cache_page(struct page *old, struct page *new)
 
 	mem_cgroup_migrate(old, new);
 
-	xas_lock_irqsave(&xas, flags);
+	xas_lock_irq(&xas);
 	xas_store(&xas, new);
 
 	old->mapping = NULL;
@@ -866,7 +863,7 @@ void replace_page_cache_page(struct page *old, struct page *new)
 		__dec_lruvec_page_state(old, NR_SHMEM);
 	if (PageSwapBacked(new))
 		__inc_lruvec_page_state(new, NR_SHMEM);
-	xas_unlock_irqrestore(&xas, flags);
+	xas_unlock_irq(&xas);
 	if (freepage)
 		freepage(old);
 	put_page(old);
diff --git a/mm/gup.c b/mm/gup.c
index b94717977d17..9935a4480710 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -62,11 +62,24 @@ static void put_page_refs(struct page *page, int refs)
 	put_page(page);
 }
 
-/*
- * Return the compound head page with ref appropriately incremented,
- * or NULL if that failed.
+/**
+ * try_get_compound_head() - return the compound head page with refcount
+ * appropriately incremented, or NULL if that failed.
+ *
+ * This handles potential refcount overflow correctly. It also works correctly
+ * for various lockless get_user_pages()-related callers, due to the use of
+ * page_cache_add_speculative().
+ *
+ * Even though the name includes "compound_head", this function is still
+ * appropriate for callers that have a non-compound @page to get.
+ *
+ * @page:  pointer to page to be gotten
+ * @refs:  the value to add to the page's refcount
+ *
+ * Return: head page (with refcount appropriately incremented) for success, or
+ * NULL upon failure.
  */
-static inline struct page *try_get_compound_head(struct page *page, int refs)
+struct page *try_get_compound_head(struct page *page, int refs)
 {
 	struct page *head = compound_head(page);
 
@@ -92,10 +105,17 @@ static inline struct page *try_get_compound_head(struct page *page, int refs)
 	return head;
 }
 
-/*
+/**
  * try_grab_compound_head() - attempt to elevate a page's refcount, by a
  * flags-dependent amount.
  *
+ * Even though the name includes "compound_head", this function is still
+ * appropriate for callers that have a non-compound @page to get.
+ *
+ * @page:  pointer to page to be grabbed
+ * @refs:  the value to (effectively) add to the page's refcount
+ * @flags: gup flags: these are the FOLL_* flag values.
+ *
  * "grab" names in this file mean, "look at flags to decide whether to use
  * FOLL_PIN or FOLL_GET behavior, when incrementing the page's refcount.
  *
@@ -103,22 +123,26 @@ static inline struct page *try_get_compound_head(struct page *page, int refs)
  * same time. (That's true throughout the get_user_pages*() and
  * pin_user_pages*() APIs.) Cases:
  *
- *    FOLL_GET: page's refcount will be incremented by 1.
- *    FOLL_PIN: page's refcount will be incremented by GUP_PIN_COUNTING_BIAS.
+ *    FOLL_GET: page's refcount will be incremented by @refs.
+ *
+ *    FOLL_PIN on compound pages that are > two pages long: page's refcount will
+ *    be incremented by @refs, and page[2].hpage_pinned_refcount will be
+ *    incremented by @refs * GUP_PIN_COUNTING_BIAS.
+ *
+ *    FOLL_PIN on normal pages, or compound pages that are two pages long:
+ *    page's refcount will be incremented by @refs * GUP_PIN_COUNTING_BIAS.
  *
  * Return: head page (with refcount appropriately incremented) for success, or
  * NULL upon failure. If neither FOLL_GET nor FOLL_PIN was set, that's
  * considered failure, and furthermore, a likely bug in the caller, so a warning
  * is also emitted.
  */
-__maybe_unused struct page *try_grab_compound_head(struct page *page,
-						   int refs, unsigned int flags)
+struct page *try_grab_compound_head(struct page *page,
+				    int refs, unsigned int flags)
 {
 	if (flags & FOLL_GET)
 		return try_get_compound_head(page, refs);
 	else if (flags & FOLL_PIN) {
-		int orig_refs = refs;
-
 		/*
 		 * Can't do FOLL_LONGTERM + FOLL_PIN gup fast path if not in a
 		 * right zone, so fail and let the caller fall back to the slow
@@ -143,6 +167,8 @@ __maybe_unused struct page *try_grab_compound_head(struct page *page,
 		 *
 		 * However, be sure to *also* increment the normal page refcount
 		 * field at least once, so that the page really is pinned.
+		 * That's why the refcount from the earlier
+		 * try_get_compound_head() is left intact.
 		 */
 		if (hpage_pincount_available(page))
 			hpage_pincount_add(page, refs);
@@ -150,7 +176,7 @@ __maybe_unused struct page *try_grab_compound_head(struct page *page,
 			page_ref_add(page, refs * (GUP_PIN_COUNTING_BIAS - 1));
 
 		mod_node_page_state(page_pgdat(page), NR_FOLL_PIN_ACQUIRED,
-				    orig_refs);
+				    refs);
 
 		return page;
 	}
@@ -186,10 +212,8 @@ static void put_compound_head(struct page *page, int refs, unsigned int flags)
  * @flags:   gup flags: these are the FOLL_* flag values.
  *
  * Either FOLL_PIN or FOLL_GET (or neither) may be set, but not both at the same
- * time. Cases:
- *
- *    FOLL_GET: page's refcount will be incremented by 1.
- *    FOLL_PIN: page's refcount will be incremented by GUP_PIN_COUNTING_BIAS.
+ * time. Cases: please see the try_grab_compound_head() documentation, with
+ * "refs=1".
  *
  * Return: true for success, or if no action was required (if neither FOLL_PIN
  * nor FOLL_GET was set, nothing is done). False for failure: FOLL_GET or
@@ -197,35 +221,10 @@ static void put_compound_head(struct page *page, int refs, unsigned int flags)
  */
 bool __must_check try_grab_page(struct page *page, unsigned int flags)
 {
-	WARN_ON_ONCE((flags & (FOLL_GET | FOLL_PIN)) == (FOLL_GET | FOLL_PIN));
+	if (!(flags & (FOLL_GET | FOLL_PIN)))
+		return true;
 
-	if (flags & FOLL_GET)
-		return try_get_page(page);
-	else if (flags & FOLL_PIN) {
-		int refs = 1;
-
-		page = compound_head(page);
-
-		if (WARN_ON_ONCE(page_ref_count(page) <= 0))
-			return false;
-
-		if (hpage_pincount_available(page))
-			hpage_pincount_add(page, 1);
-		else
-			refs = GUP_PIN_COUNTING_BIAS;
-
-		/*
-		 * Similar to try_grab_compound_head(): even if using the
-		 * hpage_pincount_add/_sub() routines, be sure to
-		 * *also* increment the normal page refcount field at least
-		 * once, so that the page really is pinned.
-		 */
-		page_ref_add(page, refs);
-
-		mod_node_page_state(page_pgdat(page), NR_FOLL_PIN_ACQUIRED, 1);
-	}
-
-	return true;
+	return try_grab_compound_head(page, 1, flags);
 }
 
 /**
@@ -1151,7 +1150,6 @@ static long __get_user_pages(struct mm_struct *mm,
 					 * We must stop here.
 					 */
 					BUG_ON(gup_flags & FOLL_NOWAIT);
-					BUG_ON(ret != 0);
 					goto out;
 				}
 				continue;
@@ -1276,7 +1274,7 @@ int fixup_user_fault(struct mm_struct *mm,
 		     bool *unlocked)
 {
 	struct vm_area_struct *vma;
-	vm_fault_t ret, major = 0;
+	vm_fault_t ret;
 
 	address = untagged_addr(address);
 
@@ -1296,7 +1294,6 @@ retry:
 		return -EINTR;
 
 	ret = handle_mm_fault(vma, address, fault_flags, NULL);
-	major |= ret & VM_FAULT_MAJOR;
 	if (ret & VM_FAULT_ERROR) {
 		int err = vm_fault_to_errno(ret, 0);
 
@@ -1475,8 +1472,8 @@ long populate_vma_page_range(struct vm_area_struct *vma,
 	unsigned long nr_pages = (end - start) / PAGE_SIZE;
 	int gup_flags;
 
-	VM_BUG_ON(start & ~PAGE_MASK);
-	VM_BUG_ON(end   & ~PAGE_MASK);
+	VM_BUG_ON(!PAGE_ALIGNED(start));
+	VM_BUG_ON(!PAGE_ALIGNED(end));
 	VM_BUG_ON_VMA(start < vma->vm_start, vma);
 	VM_BUG_ON_VMA(end   > vma->vm_end, vma);
 	mmap_assert_locked(mm);
@@ -1775,7 +1772,7 @@ static long check_and_migrate_movable_pages(unsigned long nr_pages,
 	if (!list_empty(&movable_page_list)) {
 		ret = migrate_pages(&movable_page_list, alloc_migration_target,
 				    NULL, (unsigned long)&mtc, MIGRATE_SYNC,
-				    MR_LONGTERM_PIN);
+				    MR_LONGTERM_PIN, NULL);
 		if (ret && !list_empty(&movable_page_list))
 			putback_movable_pages(&movable_page_list);
 	}
@@ -2244,6 +2241,7 @@ static int __gup_device_huge(unsigned long pfn, unsigned long addr,
 {
 	int nr_start = *nr;
 	struct dev_pagemap *pgmap = NULL;
+	int ret = 1;
 
 	do {
 		struct page *page = pfn_to_page(pfn);
@@ -2251,21 +2249,22 @@ static int __gup_device_huge(unsigned long pfn, unsigned long addr,
 		pgmap = get_dev_pagemap(pfn, pgmap);
 		if (unlikely(!pgmap)) {
 			undo_dev_pagemap(nr, nr_start, flags, pages);
-			return 0;
+			ret = 0;
+			break;
 		}
 		SetPageReferenced(page);
 		pages[*nr] = page;
 		if (unlikely(!try_grab_page(page, flags))) {
 			undo_dev_pagemap(nr, nr_start, flags, pages);
-			return 0;
+			ret = 0;
+			break;
 		}
 		(*nr)++;
 		pfn++;
 	} while (addr += PAGE_SIZE, addr != end);
 
-	if (pgmap)
-		put_dev_pagemap(pgmap);
-	return 1;
+	put_dev_pagemap(pgmap);
+	return ret;
 }
 
 static int __gup_device_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr,
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index afff3ac87067..5e9ef0fc261e 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1440,32 +1440,6 @@ vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf)
 		goto out;
 	}
 
-	/*
-	 * Since we took the NUMA fault, we must have observed the !accessible
-	 * bit. Make sure all other CPUs agree with that, to avoid them
-	 * modifying the page we're about to migrate.
-	 *
-	 * Must be done under PTL such that we'll observe the relevant
-	 * inc_tlb_flush_pending().
-	 *
-	 * We are not sure a pending tlb flush here is for a huge page
-	 * mapping or not. Hence use the tlb range variant
-	 */
-	if (mm_tlb_flush_pending(vma->vm_mm)) {
-		flush_tlb_range(vma, haddr, haddr + HPAGE_PMD_SIZE);
-		/*
-		 * change_huge_pmd() released the pmd lock before
-		 * invalidating the secondary MMUs sharing the primary
-		 * MMU pagetables (with ->invalidate_range()). The
-		 * mmu_notifier_invalidate_range_end() (which
-		 * internally calls ->invalidate_range()) in
-		 * change_pmd_range() will run after us, so we can't
-		 * rely on it here and we need an explicit invalidate.
-		 */
-		mmu_notifier_invalidate_range(vma->vm_mm, haddr,
-					      haddr + HPAGE_PMD_SIZE);
-	}
-
 	pmd = pmd_modify(oldpmd, vma->vm_page_prot);
 	page = vm_normal_page_pmd(vma, haddr, pmd);
 	if (!page)
@@ -2454,11 +2428,11 @@ static void __split_huge_page(struct page *page, struct list_head *list,
 
 	for (i = nr - 1; i >= 1; i--) {
 		__split_huge_page_tail(head, i, lruvec, list);
-		/* Some pages can be beyond i_size: drop them from page cache */
+		/* Some pages can be beyond EOF: drop them from page cache */
 		if (head[i].index >= end) {
 			ClearPageDirty(head + i);
 			__delete_from_page_cache(head + i, NULL);
-			if (IS_ENABLED(CONFIG_SHMEM) && PageSwapBacked(head))
+			if (shmem_mapping(head->mapping))
 				shmem_uncharge(head->mapping->host, 1);
 			put_page(head + i);
 		} else if (!PageAnon(page)) {
@@ -2686,6 +2660,8 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
 		 * head page lock is good enough to serialize the trimming.
 		 */
 		end = DIV_ROUND_UP(i_size_read(mapping->host), PAGE_SIZE);
+		if (shmem_mapping(mapping))
+			end = shmem_fallocend(mapping->host, end);
 	}
 
 	/*
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 8ea35ba6699f..95dc7b83381f 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1072,6 +1072,8 @@ static void enqueue_huge_page(struct hstate *h, struct page *page)
 	int nid = page_to_nid(page);
 
 	lockdep_assert_held(&hugetlb_lock);
+	VM_BUG_ON_PAGE(page_count(page), page);
+
 	list_move(&page->lru, &h->hugepage_freelists[nid]);
 	h->free_huge_pages++;
 	h->free_huge_pages_node[nid]++;
@@ -1143,7 +1145,7 @@ static struct page *dequeue_huge_page_vma(struct hstate *h,
 				unsigned long address, int avoid_reserve,
 				long chg)
 {
-	struct page *page;
+	struct page *page = NULL;
 	struct mempolicy *mpol;
 	gfp_t gfp_mask;
 	nodemask_t *nodemask;
@@ -1164,7 +1166,17 @@ static struct page *dequeue_huge_page_vma(struct hstate *h,
 
 	gfp_mask = htlb_alloc_mask(h);
 	nid = huge_node(vma, address, gfp_mask, &mpol, &nodemask);
-	page = dequeue_huge_page_nodemask(h, gfp_mask, nid, nodemask);
+
+	if (mpol_is_preferred_many(mpol)) {
+		page = dequeue_huge_page_nodemask(h, gfp_mask, nid, nodemask);
+
+		/* Fallback to all nodes if page==NULL */
+		nodemask = NULL;
+	}
+
+	if (!page)
+		page = dequeue_huge_page_nodemask(h, gfp_mask, nid, nodemask);
+
 	if (page && !avoid_reserve && vma_has_reserves(vma, chg)) {
 		SetHPageRestoreReserve(page);
 		h->resv_huge_pages--;
@@ -1368,8 +1380,28 @@ static void remove_hugetlb_page(struct hstate *h, struct page *page,
 		h->surplus_huge_pages_node[nid]--;
 	}
 
+	/*
+	 * Very subtle
+	 *
+	 * For non-gigantic pages set the destructor to the normal compound
+	 * page dtor.  This is needed in case someone takes an additional
+	 * temporary ref to the page, and freeing is delayed until they drop
+	 * their reference.
+	 *
+	 * For gigantic pages set the destructor to the null dtor.  This
+	 * destructor will never be called.  Before freeing the gigantic
+	 * page destroy_compound_gigantic_page will turn the compound page
+	 * into a simple group of pages.  After this the destructor does not
+	 * apply.
+	 *
+	 * This handles the case where more than one ref is held when and
+	 * after update_and_free_page is called.
+	 */
 	set_page_refcounted(page);
-	set_compound_page_dtor(page, NULL_COMPOUND_DTOR);
+	if (hstate_is_gigantic(h))
+		set_compound_page_dtor(page, NULL_COMPOUND_DTOR);
+	else
+		set_compound_page_dtor(page, COMPOUND_PAGE_DTOR);
 
 	h->nr_huge_pages--;
 	h->nr_huge_pages_node[nid]--;
@@ -1399,11 +1431,20 @@ static void add_hugetlb_page(struct hstate *h, struct page *page,
 	SetHPageVmemmapOptimized(page);
 
 	/*
-	 * This page is now managed by the hugetlb allocator and has
-	 * no users -- drop the last reference.
+	 * This page is about to be managed by the hugetlb allocator and
+	 * should have no users.  Drop our reference, and check for others
+	 * just in case.
 	 */
 	zeroed = put_page_testzero(page);
-	VM_BUG_ON_PAGE(!zeroed, page);
+	if (!zeroed)
+		/*
+		 * It is VERY unlikely soneone else has taken a ref on
+		 * the page.  In this case, we simply return as the
+		 * hugetlb destructor (free_huge_page) will be called
+		 * when this other ref is dropped.
+		 */
+		return;
+
 	arch_clear_hugepage_flags(page);
 	enqueue_huge_page(h, page);
 }
@@ -1657,16 +1698,14 @@ static bool prep_compound_gigantic_page(struct page *page, unsigned int order)
 		 * cache adding could take a ref on a 'to be' tail page.
 		 * We need to respect any increased ref count, and only set
 		 * the ref count to zero if count is currently 1.  If count
-		 * is not 1, we call synchronize_rcu in the hope that a rcu
-		 * grace period will cause ref count to drop and then retry.
-		 * If count is still inflated on retry we return an error and
-		 * must discard the pages.
+		 * is not 1, we return an error.  An error return indicates
+		 * the set of pages can not be converted to a gigantic page.
+		 * The caller who allocated the pages should then discard the
+		 * pages using the appropriate free interface.
 		 */
 		if (!page_ref_freeze(p, 1)) {
-			pr_info("HugeTLB unexpected inflated ref count on freshly allocated page\n");
-			synchronize_rcu();
-			if (!page_ref_freeze(p, 1))
-				goto out_error;
+			pr_warn("HugeTLB page can not be used due to unexpected inflated ref count\n");
+			goto out_error;
 		}
 		set_page_count(p, 0);
 		set_compound_head(p, page);
@@ -1830,7 +1869,6 @@ retry:
 				retry = true;
 				goto retry;
 			}
-			pr_warn("HugeTLB page can not be used due to unexpected inflated ref count\n");
 			return NULL;
 		}
 	}
@@ -2020,9 +2058,10 @@ int dissolve_free_huge_pages(unsigned long start_pfn, unsigned long end_pfn)
  * Allocates a fresh surplus page from the page allocator.
  */
 static struct page *alloc_surplus_huge_page(struct hstate *h, gfp_t gfp_mask,
-		int nid, nodemask_t *nmask)
+		int nid, nodemask_t *nmask, bool zero_ref)
 {
 	struct page *page = NULL;
+	bool retry = false;
 
 	if (hstate_is_gigantic(h))
 		return NULL;
@@ -2032,6 +2071,7 @@ static struct page *alloc_surplus_huge_page(struct hstate *h, gfp_t gfp_mask,
 		goto out_unlock;
 	spin_unlock_irq(&hugetlb_lock);
 
+retry:
 	page = alloc_fresh_huge_page(h, gfp_mask, nid, nmask, NULL);
 	if (!page)
 		return NULL;
@@ -2049,11 +2089,35 @@ static struct page *alloc_surplus_huge_page(struct hstate *h, gfp_t gfp_mask,
 		spin_unlock_irq(&hugetlb_lock);
 		put_page(page);
 		return NULL;
-	} else {
-		h->surplus_huge_pages++;
-		h->surplus_huge_pages_node[page_to_nid(page)]++;
 	}
 
+	if (zero_ref) {
+		/*
+		 * Caller requires a page with zero ref count.
+		 * We will drop ref count here.  If someone else is holding
+		 * a ref, the page will be freed when they drop it.  Abuse
+		 * temporary page flag to accomplish this.
+		 */
+		SetHPageTemporary(page);
+		if (!put_page_testzero(page)) {
+			/*
+			 * Unexpected inflated ref count on freshly allocated
+			 * huge.  Retry once.
+			 */
+			pr_info("HugeTLB unexpected inflated ref count on freshly allocated page\n");
+			spin_unlock_irq(&hugetlb_lock);
+			if (retry)
+				return NULL;
+
+			retry = true;
+			goto retry;
+		}
+		ClearHPageTemporary(page);
+	}
+
+	h->surplus_huge_pages++;
+	h->surplus_huge_pages_node[page_to_nid(page)]++;
+
 out_unlock:
 	spin_unlock_irq(&hugetlb_lock);
 
@@ -2088,16 +2152,26 @@ static
 struct page *alloc_buddy_huge_page_with_mpol(struct hstate *h,
 		struct vm_area_struct *vma, unsigned long addr)
 {
-	struct page *page;
+	struct page *page = NULL;
 	struct mempolicy *mpol;
 	gfp_t gfp_mask = htlb_alloc_mask(h);
 	int nid;
 	nodemask_t *nodemask;
 
 	nid = huge_node(vma, addr, gfp_mask, &mpol, &nodemask);
-	page = alloc_surplus_huge_page(h, gfp_mask, nid, nodemask);
-	mpol_cond_put(mpol);
+	if (mpol_is_preferred_many(mpol)) {
+		gfp_t gfp = gfp_mask | __GFP_NOWARN;
 
+		gfp &=  ~(__GFP_DIRECT_RECLAIM | __GFP_NOFAIL);
+		page = alloc_surplus_huge_page(h, gfp, nid, nodemask, false);
+
+		/* Fallback to all nodes if page==NULL */
+		nodemask = NULL;
+	}
+
+	if (!page)
+		page = alloc_surplus_huge_page(h, gfp_mask, nid, nodemask, false);
+	mpol_cond_put(mpol);
 	return page;
 }
 
@@ -2167,7 +2241,7 @@ retry:
 	spin_unlock_irq(&hugetlb_lock);
 	for (i = 0; i < needed; i++) {
 		page = alloc_surplus_huge_page(h, htlb_alloc_mask(h),
-				NUMA_NO_NODE, NULL);
+				NUMA_NO_NODE, NULL, true);
 		if (!page) {
 			alloc_ok = false;
 			break;
@@ -2208,24 +2282,20 @@ retry:
 
 	/* Free the needed pages to the hugetlb pool */
 	list_for_each_entry_safe(page, tmp, &surplus_list, lru) {
-		int zeroed;
-
 		if ((--needed) < 0)
 			break;
-		/*
-		 * This page is now managed by the hugetlb allocator and has
-		 * no users -- drop the buddy allocator's reference.
-		 */
-		zeroed = put_page_testzero(page);
-		VM_BUG_ON_PAGE(!zeroed, page);
+		/* Add the page to the hugetlb allocator */
 		enqueue_huge_page(h, page);
 	}
 free:
 	spin_unlock_irq(&hugetlb_lock);
 
-	/* Free unnecessary surplus pages to the buddy allocator */
+	/*
+	 * Free unnecessary surplus pages to the buddy allocator.
+	 * Pages have no ref count, call free_huge_page directly.
+	 */
 	list_for_each_entry_safe(page, tmp, &surplus_list, lru)
-		put_page(page);
+		free_huge_page(page);
 	spin_lock_irq(&hugetlb_lock);
 
 	return ret;
@@ -2534,6 +2604,7 @@ static int alloc_and_dissolve_huge_page(struct hstate *h, struct page *old_page,
 {
 	gfp_t gfp_mask = htlb_alloc_mask(h) | __GFP_THISNODE;
 	int nid = page_to_nid(old_page);
+	bool alloc_retry = false;
 	struct page *new_page;
 	int ret = 0;
 
@@ -2544,9 +2615,30 @@ static int alloc_and_dissolve_huge_page(struct hstate *h, struct page *old_page,
 	 * the pool.  This simplifies and let us do most of the processing
 	 * under the lock.
 	 */
+alloc_retry:
 	new_page = alloc_buddy_huge_page(h, gfp_mask, nid, NULL, NULL);
 	if (!new_page)
 		return -ENOMEM;
+	/*
+	 * If all goes well, this page will be directly added to the free
+	 * list in the pool.  For this the ref count needs to be zero.
+	 * Attempt to drop now, and retry once if needed.  It is VERY
+	 * unlikely there is another ref on the page.
+	 *
+	 * If someone else has a reference to the page, it will be freed
+	 * when they drop their ref.  Abuse temporary page flag to accomplish
+	 * this.  Retry once if there is an inflated ref count.
+	 */
+	SetHPageTemporary(new_page);
+	if (!put_page_testzero(new_page)) {
+		if (alloc_retry)
+			return -EBUSY;
+
+		alloc_retry = true;
+		goto alloc_retry;
+	}
+	ClearHPageTemporary(new_page);
+
 	__prep_new_huge_page(h, new_page);
 
 retry:
@@ -2586,11 +2678,10 @@ retry:
 		remove_hugetlb_page(h, old_page, false);
 
 		/*
-		 * Reference count trick is needed because allocator gives us
-		 * referenced page but the pool requires pages with 0 refcount.
+		 * Ref count on new page is already zero as it was dropped
+		 * earlier.  It can be directly added to the pool free list.
 		 */
 		__prep_account_new_huge_page(h, nid);
-		page_ref_dec(new_page);
 		enqueue_huge_page(h, new_page);
 
 		/*
@@ -2604,6 +2695,8 @@ retry:
 
 free_new:
 	spin_unlock_irq(&hugetlb_lock);
+	/* Page has a zero ref count, but needs a ref to be freed */
+	set_page_refcounted(new_page);
 	update_and_free_page(h, new_page, false);
 
 	return ret;
@@ -2828,8 +2921,8 @@ static void __init gather_bootmem_prealloc(void)
 			prep_new_huge_page(h, page, page_to_nid(page));
 			put_page(page); /* add to the hugepage allocator */
 		} else {
+			/* VERY unlikely inflated ref count on a tail page */
 			free_gigantic_page(page, huge_page_order(h));
-			pr_warn("HugeTLB page can not be used due to unexpected inflated ref count\n");
 		}
 
 		/*
@@ -4033,8 +4126,10 @@ static void hugetlb_vm_op_open(struct vm_area_struct *vma)
 	 * after this open call completes.  It is therefore safe to take a
 	 * new reference here without additional locking.
 	 */
-	if (resv && is_vma_resv_set(vma, HPAGE_RESV_OWNER))
+	if (resv && is_vma_resv_set(vma, HPAGE_RESV_OWNER)) {
+		resv_map_dup_hugetlb_cgroup_uncharge_info(resv);
 		kref_get(&resv->refs);
+	}
 }
 
 static void hugetlb_vm_op_close(struct vm_area_struct *vma)
diff --git a/mm/hwpoison-inject.c b/mm/hwpoison-inject.c
index 1ae1ebc2b9b1..aff4d27ec235 100644
--- a/mm/hwpoison-inject.c
+++ b/mm/hwpoison-inject.c
@@ -30,7 +30,7 @@ static int hwpoison_inject(void *data, u64 val)
 	if (!hwpoison_filter_enable)
 		goto inject;
 
-	shake_page(hpage, 0);
+	shake_page(hpage);
 	/*
 	 * This implies unable to support non-LRU pages.
 	 */
diff --git a/mm/internal.h b/mm/internal.h
index 31ff935b2547..cf3cb933eba3 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -211,6 +211,10 @@ extern void zone_pcp_reset(struct zone *zone);
 extern void zone_pcp_disable(struct zone *zone);
 extern void zone_pcp_enable(struct zone *zone);
 
+extern void *memmap_alloc(phys_addr_t size, phys_addr_t align,
+			  phys_addr_t min_addr,
+			  int nid, bool exact_nid);
+
 #if defined CONFIG_COMPACTION || defined CONFIG_CMA
 
 /*
@@ -539,12 +543,17 @@ static inline void mminit_validate_memmodel_limits(unsigned long *start_pfn,
 
 #ifdef CONFIG_NUMA
 extern int node_reclaim(struct pglist_data *, gfp_t, unsigned int);
+extern int find_next_best_node(int node, nodemask_t *used_node_mask);
 #else
 static inline int node_reclaim(struct pglist_data *pgdat, gfp_t mask,
 				unsigned int order)
 {
 	return NODE_RECLAIM_NOSCAN;
 }
+static inline int find_next_best_node(int node, nodemask_t *used_node_mask)
+{
+	return NUMA_NO_NODE;
+}
 #endif
 
 extern int hwpoison_filter(struct page *p);
diff --git a/mm/kasan/hw_tags.c b/mm/kasan/hw_tags.c
index e4c16f6b6680..05d1e9460e2e 100644
--- a/mm/kasan/hw_tags.c
+++ b/mm/kasan/hw_tags.c
@@ -37,16 +37,9 @@ enum kasan_arg_stacktrace {
 	KASAN_ARG_STACKTRACE_ON,
 };
 
-enum kasan_arg_fault {
-	KASAN_ARG_FAULT_DEFAULT,
-	KASAN_ARG_FAULT_REPORT,
-	KASAN_ARG_FAULT_PANIC,
-};
-
 static enum kasan_arg kasan_arg __ro_after_init;
 static enum kasan_arg_mode kasan_arg_mode __ro_after_init;
 static enum kasan_arg_stacktrace kasan_arg_stacktrace __ro_after_init;
-static enum kasan_arg_fault kasan_arg_fault __ro_after_init;
 
 /* Whether KASAN is enabled at all. */
 DEFINE_STATIC_KEY_FALSE(kasan_flag_enabled);
@@ -59,9 +52,6 @@ EXPORT_SYMBOL_GPL(kasan_flag_async);
 /* Whether to collect alloc/free stack traces. */
 DEFINE_STATIC_KEY_FALSE(kasan_flag_stacktrace);
 
-/* Whether to panic or print a report and disable tag checking on fault. */
-bool kasan_flag_panic __ro_after_init;
-
 /* kasan=off/on */
 static int __init early_kasan_flag(char *arg)
 {
@@ -113,23 +103,6 @@ static int __init early_kasan_flag_stacktrace(char *arg)
 }
 early_param("kasan.stacktrace", early_kasan_flag_stacktrace);
 
-/* kasan.fault=report/panic */
-static int __init early_kasan_fault(char *arg)
-{
-	if (!arg)
-		return -EINVAL;
-
-	if (!strcmp(arg, "report"))
-		kasan_arg_fault = KASAN_ARG_FAULT_REPORT;
-	else if (!strcmp(arg, "panic"))
-		kasan_arg_fault = KASAN_ARG_FAULT_PANIC;
-	else
-		return -EINVAL;
-
-	return 0;
-}
-early_param("kasan.fault", early_kasan_fault);
-
 /* kasan_init_hw_tags_cpu() is called for each CPU. */
 void kasan_init_hw_tags_cpu(void)
 {
@@ -195,22 +168,6 @@ void __init kasan_init_hw_tags(void)
 		break;
 	}
 
-	switch (kasan_arg_fault) {
-	case KASAN_ARG_FAULT_DEFAULT:
-		/*
-		 * Default to no panic on report.
-		 * Do nothing, kasan_flag_panic keeps its default value.
-		 */
-		break;
-	case KASAN_ARG_FAULT_REPORT:
-		/* Do nothing, kasan_flag_panic keeps its default value. */
-		break;
-	case KASAN_ARG_FAULT_PANIC:
-		/* Enable panic on report. */
-		kasan_flag_panic = true;
-		break;
-	}
-
 	pr_info("KernelAddressSanitizer initialized\n");
 }
 
diff --git a/mm/kasan/kasan.h b/mm/kasan/kasan.h
index fff93b0bcb08..8bf568a80eb8 100644
--- a/mm/kasan/kasan.h
+++ b/mm/kasan/kasan.h
@@ -38,7 +38,6 @@ static inline bool kasan_async_mode_enabled(void)
 
 #endif
 
-extern bool kasan_flag_panic __ro_after_init;
 extern bool kasan_flag_async __ro_after_init;
 
 #if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)
diff --git a/mm/kasan/report.c b/mm/kasan/report.c
index 8fff1825b22c..884a950c7026 100644
--- a/mm/kasan/report.c
+++ b/mm/kasan/report.c
@@ -39,6 +39,31 @@ static unsigned long kasan_flags;
 #define KASAN_BIT_REPORTED	0
 #define KASAN_BIT_MULTI_SHOT	1
 
+enum kasan_arg_fault {
+	KASAN_ARG_FAULT_DEFAULT,
+	KASAN_ARG_FAULT_REPORT,
+	KASAN_ARG_FAULT_PANIC,
+};
+
+static enum kasan_arg_fault kasan_arg_fault __ro_after_init = KASAN_ARG_FAULT_DEFAULT;
+
+/* kasan.fault=report/panic */
+static int __init early_kasan_fault(char *arg)
+{
+	if (!arg)
+		return -EINVAL;
+
+	if (!strcmp(arg, "report"))
+		kasan_arg_fault = KASAN_ARG_FAULT_REPORT;
+	else if (!strcmp(arg, "panic"))
+		kasan_arg_fault = KASAN_ARG_FAULT_PANIC;
+	else
+		return -EINVAL;
+
+	return 0;
+}
+early_param("kasan.fault", early_kasan_fault);
+
 bool kasan_save_enable_multi_shot(void)
 {
 	return test_and_set_bit(KASAN_BIT_MULTI_SHOT, &kasan_flags);
@@ -102,10 +127,8 @@ static void end_report(unsigned long *flags, unsigned long addr)
 		panic_on_warn = 0;
 		panic("panic_on_warn set ...\n");
 	}
-#ifdef CONFIG_KASAN_HW_TAGS
-	if (kasan_flag_panic)
+	if (kasan_arg_fault == KASAN_ARG_FAULT_PANIC)
 		panic("kasan.fault=panic set ...\n");
-#endif
 	kasan_enable_current();
 }
 
diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index b0412be08fa2..045cc579f724 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -1721,7 +1721,7 @@ static void collapse_file(struct mm_struct *mm,
 				xas_unlock_irq(&xas);
 				/* swap in or instantiate fallocated page */
 				if (shmem_getpage(mapping->host, index, &page,
-						  SGP_NOHUGE)) {
+						  SGP_NOALLOC)) {
 					result = SCAN_FAIL;
 					goto xa_unlocked;
 				}
diff --git a/mm/ksm.c b/mm/ksm.c
index 3fa9bc8a67cf..025338128cd9 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -259,7 +259,7 @@ static unsigned long ksm_stable_node_chains;
 static unsigned long ksm_stable_node_dups;
 
 /* Delay in pruning stale stable_node_dups in the stable_node_chains */
-static int ksm_stable_node_chains_prune_millisecs = 2000;
+static unsigned int ksm_stable_node_chains_prune_millisecs = 2000;
 
 /* Maximum number of page slots sharing a stable node */
 static int ksm_max_page_sharing = 256;
@@ -3105,11 +3105,11 @@ stable_node_chains_prune_millisecs_store(struct kobject *kobj,
 					 struct kobj_attribute *attr,
 					 const char *buf, size_t count)
 {
-	unsigned long msecs;
+	unsigned int msecs;
 	int err;
 
-	err = kstrtoul(buf, 10, &msecs);
-	if (err || msecs > UINT_MAX)
+	err = kstrtouint(buf, 10, &msecs);
+	if (err)
 		return -EINVAL;
 
 	ksm_stable_node_chains_prune_millisecs = msecs;
diff --git a/mm/madvise.c b/mm/madvise.c
index 56324a3dbc4e..0734db8d53a7 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -1048,6 +1048,7 @@ process_madvise_behavior_valid(int behavior)
 	switch (behavior) {
 	case MADV_COLD:
 	case MADV_PAGEOUT:
+	case MADV_WILLNEED:
 		return true;
 	default:
 		return false;
diff --git a/mm/memblock.c b/mm/memblock.c
index e2ca8ddc8ebe..0ab5a749bfa6 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -315,7 +315,7 @@ static phys_addr_t __init_memblock memblock_find_in_range_node(phys_addr_t size,
  * Return:
  * Found address on success, 0 on failure.
  */
-phys_addr_t __init_memblock memblock_find_in_range(phys_addr_t start,
+static phys_addr_t __init_memblock memblock_find_in_range(phys_addr_t start,
 					phys_addr_t end, phys_addr_t size,
 					phys_addr_t align)
 {
@@ -1496,18 +1496,12 @@ void * __init memblock_alloc_exact_nid_raw(
 			phys_addr_t min_addr, phys_addr_t max_addr,
 			int nid)
 {
-	void *ptr;
-
 	memblock_dbg("%s: %llu bytes align=0x%llx nid=%d from=%pa max_addr=%pa %pS\n",
 		     __func__, (u64)size, (u64)align, nid, &min_addr,
 		     &max_addr, (void *)_RET_IP_);
 
-	ptr = memblock_alloc_internal(size, align,
-					   min_addr, max_addr, nid, true);
-	if (ptr && size > 0)
-		page_init_poison(ptr, size);
-
-	return ptr;
+	return memblock_alloc_internal(size, align, min_addr, max_addr, nid,
+				       true);
 }
 
 /**
@@ -1534,18 +1528,12 @@ void * __init memblock_alloc_try_nid_raw(
 			phys_addr_t min_addr, phys_addr_t max_addr,
 			int nid)
 {
-	void *ptr;
-
 	memblock_dbg("%s: %llu bytes align=0x%llx nid=%d from=%pa max_addr=%pa %pS\n",
 		     __func__, (u64)size, (u64)align, nid, &min_addr,
 		     &max_addr, (void *)_RET_IP_);
 
-	ptr = memblock_alloc_internal(size, align,
-					   min_addr, max_addr, nid, false);
-	if (ptr && size > 0)
-		page_init_poison(ptr, size);
-
-	return ptr;
+	return memblock_alloc_internal(size, align, min_addr, max_addr, nid,
+				       false);
 }
 
 /**
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 389b5766e74f..b762215d73eb 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -103,6 +103,14 @@ static bool do_memsw_account(void)
 	return !cgroup_subsys_on_dfl(memory_cgrp_subsys) && !cgroup_memory_noswap;
 }
 
+/* memcg and lruvec stats flushing */
+static void flush_memcg_stats_dwork(struct work_struct *w);
+static DECLARE_DEFERRABLE_WORK(stats_flush_dwork, flush_memcg_stats_dwork);
+static void flush_memcg_stats_work(struct work_struct *w);
+static DECLARE_WORK(stats_flush_work, flush_memcg_stats_work);
+static DEFINE_PER_CPU(unsigned int, stats_flush_threshold);
+static DEFINE_SPINLOCK(stats_flush_lock);
+
 #define THRESHOLDS_EVENTS_TARGET 128
 #define SOFTLIMIT_EVENTS_TARGET 1024
 
@@ -248,9 +256,9 @@ struct vmpressure *memcg_to_vmpressure(struct mem_cgroup *memcg)
 	return &memcg->vmpressure;
 }
 
-struct cgroup_subsys_state *vmpressure_to_css(struct vmpressure *vmpr)
+struct mem_cgroup *vmpressure_to_memcg(struct vmpressure *vmpr)
 {
-	return &container_of(vmpr, struct mem_cgroup, vmpressure)->css;
+	return container_of(vmpr, struct mem_cgroup, vmpressure);
 }
 
 #ifdef CONFIG_MEMCG_KMEM
@@ -646,17 +654,6 @@ void __mod_memcg_state(struct mem_cgroup *memcg, int idx, int val)
 }
 
 /* idx can be of type enum memcg_stat_item or node_stat_item. */
-static unsigned long memcg_page_state(struct mem_cgroup *memcg, int idx)
-{
-	long x = READ_ONCE(memcg->vmstats.state[idx]);
-#ifdef CONFIG_SMP
-	if (x < 0)
-		x = 0;
-#endif
-	return x;
-}
-
-/* idx can be of type enum memcg_stat_item or node_stat_item. */
 static unsigned long memcg_page_state_local(struct mem_cgroup *memcg, int idx)
 {
 	long x = 0;
@@ -671,23 +668,11 @@ static unsigned long memcg_page_state_local(struct mem_cgroup *memcg, int idx)
 	return x;
 }
 
-static struct mem_cgroup_per_node *
-parent_nodeinfo(struct mem_cgroup_per_node *pn, int nid)
-{
-	struct mem_cgroup *parent;
-
-	parent = parent_mem_cgroup(pn->memcg);
-	if (!parent)
-		return NULL;
-	return parent->nodeinfo[nid];
-}
-
 void __mod_memcg_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx,
 			      int val)
 {
 	struct mem_cgroup_per_node *pn;
 	struct mem_cgroup *memcg;
-	long x, threshold = MEMCG_CHARGE_BATCH;
 
 	pn = container_of(lruvec, struct mem_cgroup_per_node, lruvec);
 	memcg = pn->memcg;
@@ -696,21 +681,9 @@ void __mod_memcg_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx,
 	__mod_memcg_state(memcg, idx, val);
 
 	/* Update lruvec */
-	__this_cpu_add(pn->lruvec_stat_local->count[idx], val);
-
-	if (vmstat_item_in_bytes(idx))
-		threshold <<= PAGE_SHIFT;
-
-	x = val + __this_cpu_read(pn->lruvec_stat_cpu->count[idx]);
-	if (unlikely(abs(x) > threshold)) {
-		pg_data_t *pgdat = lruvec_pgdat(lruvec);
-		struct mem_cgroup_per_node *pi;
-
-		for (pi = pn; pi; pi = parent_nodeinfo(pi, pgdat->node_id))
-			atomic_long_add(x, &pi->lruvec_stat[idx]);
-		x = 0;
-	}
-	__this_cpu_write(pn->lruvec_stat_cpu->count[idx], x);
+	__this_cpu_add(pn->lruvec_stats_percpu->state[idx], val);
+	if (!(__this_cpu_inc_return(stats_flush_threshold) % MEMCG_CHARGE_BATCH))
+		queue_work(system_unbound_wq, &stats_flush_work);
 }
 
 /**
@@ -905,7 +878,7 @@ EXPORT_SYMBOL(mem_cgroup_from_task);
 
 static __always_inline struct mem_cgroup *active_memcg(void)
 {
-	if (in_interrupt())
+	if (!in_task())
 		return this_cpu_read(int_active_memcg);
 	else
 		return current->active_memcg;
@@ -2205,8 +2178,9 @@ static void drain_local_stock(struct work_struct *dummy)
 	unsigned long flags;
 
 	/*
-	 * The only protection from memory hotplug vs. drain_stock races is
-	 * that we always operate on local CPU stock here with IRQ disabled
+	 * The only protection from cpu hotplug (memcg_hotplug_cpu_dead) vs.
+	 * drain_stock races is that we always operate on local CPU stock
+	 * here with IRQ disabled
 	 */
 	local_irq_save(flags);
 
@@ -2273,7 +2247,7 @@ static void drain_all_stock(struct mem_cgroup *root_memcg)
 		if (memcg && stock->nr_pages &&
 		    mem_cgroup_is_descendant(memcg, root_memcg))
 			flush = true;
-		if (obj_stock_flush_required(stock, root_memcg))
+		else if (obj_stock_flush_required(stock, root_memcg))
 			flush = true;
 		rcu_read_unlock();
 
@@ -2289,40 +2263,13 @@ static void drain_all_stock(struct mem_cgroup *root_memcg)
 	mutex_unlock(&percpu_charge_mutex);
 }
 
-static void memcg_flush_lruvec_page_state(struct mem_cgroup *memcg, int cpu)
-{
-	int nid;
-
-	for_each_node(nid) {
-		struct mem_cgroup_per_node *pn = memcg->nodeinfo[nid];
-		unsigned long stat[NR_VM_NODE_STAT_ITEMS];
-		struct batched_lruvec_stat *lstatc;
-		int i;
-
-		lstatc = per_cpu_ptr(pn->lruvec_stat_cpu, cpu);
-		for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++) {
-			stat[i] = lstatc->count[i];
-			lstatc->count[i] = 0;
-		}
-
-		do {
-			for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++)
-				atomic_long_add(stat[i], &pn->lruvec_stat[i]);
-		} while ((pn = parent_nodeinfo(pn, nid)));
-	}
-}
-
 static int memcg_hotplug_cpu_dead(unsigned int cpu)
 {
 	struct memcg_stock_pcp *stock;
-	struct mem_cgroup *memcg;
 
 	stock = &per_cpu(memcg_stock, cpu);
 	drain_stock(stock);
 
-	for_each_mem_cgroup(memcg)
-		memcg_flush_lruvec_page_state(memcg, cpu);
-
 	return 0;
 }
 
@@ -4116,7 +4063,7 @@ static int mem_cgroup_swappiness_write(struct cgroup_subsys_state *css,
 {
 	struct mem_cgroup *memcg = mem_cgroup_from_css(css);
 
-	if (val > 100)
+	if (val > 200)
 		return -EINVAL;
 
 	if (!mem_cgroup_is_root(memcg))
@@ -4668,7 +4615,7 @@ void mem_cgroup_flush_foreign(struct bdi_writeback *wb)
 		    atomic_read(&frn->done.cnt) == 1) {
 			frn->at = 0;
 			trace_flush_foreign(wb, frn->bdi_id, frn->memcg_id);
-			cgroup_writeback_by_id(frn->bdi_id, frn->memcg_id, 0,
+			cgroup_writeback_by_id(frn->bdi_id, frn->memcg_id,
 					       WB_REASON_FOREIGN_FLUSH,
 					       &frn->done);
 		}
@@ -4892,9 +4839,9 @@ static ssize_t memcg_write_event_control(struct kernfs_open_file *of,
 
 	vfs_poll(efile.file, &event->pt);
 
-	spin_lock(&memcg->event_list_lock);
+	spin_lock_irq(&memcg->event_list_lock);
 	list_add(&event->list, &memcg->event_list);
-	spin_unlock(&memcg->event_list_lock);
+	spin_unlock_irq(&memcg->event_list_lock);
 
 	fdput(cfile);
 	fdput(efile);
@@ -5129,17 +5076,9 @@ static int alloc_mem_cgroup_per_node_info(struct mem_cgroup *memcg, int node)
 	if (!pn)
 		return 1;
 
-	pn->lruvec_stat_local = alloc_percpu_gfp(struct lruvec_stat,
-						 GFP_KERNEL_ACCOUNT);
-	if (!pn->lruvec_stat_local) {
-		kfree(pn);
-		return 1;
-	}
-
-	pn->lruvec_stat_cpu = alloc_percpu_gfp(struct batched_lruvec_stat,
-					       GFP_KERNEL_ACCOUNT);
-	if (!pn->lruvec_stat_cpu) {
-		free_percpu(pn->lruvec_stat_local);
+	pn->lruvec_stats_percpu = alloc_percpu_gfp(struct lruvec_stats_percpu,
+						   GFP_KERNEL_ACCOUNT);
+	if (!pn->lruvec_stats_percpu) {
 		kfree(pn);
 		return 1;
 	}
@@ -5160,8 +5099,7 @@ static void free_mem_cgroup_per_node_info(struct mem_cgroup *memcg, int node)
 	if (!pn)
 		return;
 
-	free_percpu(pn->lruvec_stat_cpu);
-	free_percpu(pn->lruvec_stat_local);
+	free_percpu(pn->lruvec_stats_percpu);
 	kfree(pn);
 }
 
@@ -5177,15 +5115,7 @@ static void __mem_cgroup_free(struct mem_cgroup *memcg)
 
 static void mem_cgroup_free(struct mem_cgroup *memcg)
 {
-	int cpu;
-
 	memcg_wb_domain_exit(memcg);
-	/*
-	 * Flush percpu lruvec stats to guarantee the value
-	 * correctness on parent's and all ancestor levels.
-	 */
-	for_each_online_cpu(cpu)
-		memcg_flush_lruvec_page_state(memcg, cpu);
 	__mem_cgroup_free(memcg);
 }
 
@@ -5321,6 +5251,10 @@ static int mem_cgroup_css_online(struct cgroup_subsys_state *css)
 	/* Online state pins memcg ID, memcg ID pins CSS */
 	refcount_set(&memcg->id.ref, 1);
 	css_get(css);
+
+	if (unlikely(mem_cgroup_is_root(memcg)))
+		queue_delayed_work(system_unbound_wq, &stats_flush_dwork,
+				   2UL*HZ);
 	return 0;
 }
 
@@ -5334,12 +5268,12 @@ static void mem_cgroup_css_offline(struct cgroup_subsys_state *css)
 	 * Notify userspace about cgroup removing only after rmdir of cgroup
 	 * directory to avoid race between userspace and kernelspace.
 	 */
-	spin_lock(&memcg->event_list_lock);
+	spin_lock_irq(&memcg->event_list_lock);
 	list_for_each_entry_safe(event, tmp, &memcg->event_list, list) {
 		list_del_init(&event->list);
 		schedule_work(&event->remove);
 	}
-	spin_unlock(&memcg->event_list_lock);
+	spin_unlock_irq(&memcg->event_list_lock);
 
 	page_counter_set_min(&memcg->memory, 0);
 	page_counter_set_low(&memcg->memory, 0);
@@ -5412,13 +5346,33 @@ static void mem_cgroup_css_reset(struct cgroup_subsys_state *css)
 	memcg_wb_domain_size_changed(memcg);
 }
 
+void mem_cgroup_flush_stats(void)
+{
+	if (!spin_trylock(&stats_flush_lock))
+		return;
+
+	cgroup_rstat_flush_irqsafe(root_mem_cgroup->css.cgroup);
+	spin_unlock(&stats_flush_lock);
+}
+
+static void flush_memcg_stats_dwork(struct work_struct *w)
+{
+	mem_cgroup_flush_stats();
+	queue_delayed_work(system_unbound_wq, &stats_flush_dwork, 2UL*HZ);
+}
+
+static void flush_memcg_stats_work(struct work_struct *w)
+{
+	mem_cgroup_flush_stats();
+}
+
 static void mem_cgroup_css_rstat_flush(struct cgroup_subsys_state *css, int cpu)
 {
 	struct mem_cgroup *memcg = mem_cgroup_from_css(css);
 	struct mem_cgroup *parent = parent_mem_cgroup(memcg);
 	struct memcg_vmstats_percpu *statc;
 	long delta, v;
-	int i;
+	int i, nid;
 
 	statc = per_cpu_ptr(memcg->vmstats_percpu, cpu);
 
@@ -5466,6 +5420,36 @@ static void mem_cgroup_css_rstat_flush(struct cgroup_subsys_state *css, int cpu)
 		if (parent)
 			parent->vmstats.events_pending[i] += delta;
 	}
+
+	for_each_node_state(nid, N_MEMORY) {
+		struct mem_cgroup_per_node *pn = memcg->nodeinfo[nid];
+		struct mem_cgroup_per_node *ppn = NULL;
+		struct lruvec_stats_percpu *lstatc;
+
+		if (parent)
+			ppn = parent->nodeinfo[nid];
+
+		lstatc = per_cpu_ptr(pn->lruvec_stats_percpu, cpu);
+
+		for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++) {
+			delta = pn->lruvec_stats.state_pending[i];
+			if (delta)
+				pn->lruvec_stats.state_pending[i] = 0;
+
+			v = READ_ONCE(lstatc->state[i]);
+			if (v != lstatc->state_prev[i]) {
+				delta += v - lstatc->state_prev[i];
+				lstatc->state_prev[i] = v;
+			}
+
+			if (!delta)
+				continue;
+
+			pn->lruvec_stats.state[i] += delta;
+			if (ppn)
+				ppn->lruvec_stats.state_pending[i] += delta;
+		}
+	}
 }
 
 #ifdef CONFIG_MMU
@@ -6399,6 +6383,8 @@ static int memory_numa_stat_show(struct seq_file *m, void *v)
 	int i;
 	struct mem_cgroup *memcg = mem_cgroup_from_seq(m);
 
+	cgroup_rstat_flush(memcg->css.cgroup);
+
 	for (i = 0; i < ARRAY_SIZE(memory_stats); i++) {
 		int nid;
 
@@ -6704,8 +6690,7 @@ void mem_cgroup_calculate_protection(struct mem_cgroup *root,
 			atomic_long_read(&parent->memory.children_low_usage)));
 }
 
-static int __mem_cgroup_charge(struct page *page, struct mem_cgroup *memcg,
-			       gfp_t gfp)
+static int charge_memcg(struct page *page, struct mem_cgroup *memcg, gfp_t gfp)
 {
 	unsigned int nr_pages = thp_nr_pages(page);
 	int ret;
@@ -6726,7 +6711,7 @@ out:
 }
 
 /**
- * mem_cgroup_charge - charge a newly allocated page to a cgroup
+ * __mem_cgroup_charge - charge a newly allocated page to a cgroup
  * @page: page to charge
  * @mm: mm context of the victim
  * @gfp_mask: reclaim mode
@@ -6739,16 +6724,14 @@ out:
  *
  * Returns 0 on success. Otherwise, an error code is returned.
  */
-int mem_cgroup_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask)
+int __mem_cgroup_charge(struct page *page, struct mm_struct *mm,
+			gfp_t gfp_mask)
 {
 	struct mem_cgroup *memcg;
 	int ret;
 
-	if (mem_cgroup_disabled())
-		return 0;
-
 	memcg = get_mem_cgroup_from_mm(mm);
-	ret = __mem_cgroup_charge(page, memcg, gfp_mask);
+	ret = charge_memcg(page, memcg, gfp_mask);
 	css_put(&memcg->css);
 
 	return ret;
@@ -6783,7 +6766,7 @@ int mem_cgroup_swapin_charge_page(struct page *page, struct mm_struct *mm,
 		memcg = get_mem_cgroup_from_mm(mm);
 	rcu_read_unlock();
 
-	ret = __mem_cgroup_charge(page, memcg, gfp);
+	ret = charge_memcg(page, memcg, gfp);
 
 	css_put(&memcg->css);
 	return ret;
@@ -6919,18 +6902,15 @@ static void uncharge_page(struct page *page, struct uncharge_gather *ug)
 }
 
 /**
- * mem_cgroup_uncharge - uncharge a page
+ * __mem_cgroup_uncharge - uncharge a page
  * @page: page to uncharge
  *
- * Uncharge a page previously charged with mem_cgroup_charge().
+ * Uncharge a page previously charged with __mem_cgroup_charge().
  */
-void mem_cgroup_uncharge(struct page *page)
+void __mem_cgroup_uncharge(struct page *page)
 {
 	struct uncharge_gather ug;
 
-	if (mem_cgroup_disabled())
-		return;
-
 	/* Don't touch page->lru of any random page, pre-check: */
 	if (!page_memcg(page))
 		return;
@@ -6941,20 +6921,17 @@ void mem_cgroup_uncharge(struct page *page)
 }
 
 /**
- * mem_cgroup_uncharge_list - uncharge a list of page
+ * __mem_cgroup_uncharge_list - uncharge a list of page
  * @page_list: list of pages to uncharge
  *
  * Uncharge a list of pages previously charged with
- * mem_cgroup_charge().
+ * __mem_cgroup_charge().
  */
-void mem_cgroup_uncharge_list(struct list_head *page_list)
+void __mem_cgroup_uncharge_list(struct list_head *page_list)
 {
 	struct uncharge_gather ug;
 	struct page *page;
 
-	if (mem_cgroup_disabled())
-		return;
-
 	uncharge_gather_clear(&ug);
 	list_for_each_entry(page, page_list, lru)
 		uncharge_page(page, &ug);
@@ -7244,7 +7221,7 @@ void mem_cgroup_swapout(struct page *page, swp_entry_t entry)
 }
 
 /**
- * mem_cgroup_try_charge_swap - try charging swap space for a page
+ * __mem_cgroup_try_charge_swap - try charging swap space for a page
  * @page: page being added to swap
  * @entry: swap entry to charge
  *
@@ -7252,16 +7229,13 @@ void mem_cgroup_swapout(struct page *page, swp_entry_t entry)
  *
  * Returns 0 on success, -ENOMEM on failure.
  */
-int mem_cgroup_try_charge_swap(struct page *page, swp_entry_t entry)
+int __mem_cgroup_try_charge_swap(struct page *page, swp_entry_t entry)
 {
 	unsigned int nr_pages = thp_nr_pages(page);
 	struct page_counter *counter;
 	struct mem_cgroup *memcg;
 	unsigned short oldid;
 
-	if (mem_cgroup_disabled())
-		return 0;
-
 	if (!cgroup_subsys_on_dfl(memory_cgrp_subsys))
 		return 0;
 
@@ -7297,11 +7271,11 @@ int mem_cgroup_try_charge_swap(struct page *page, swp_entry_t entry)
 }
 
 /**
- * mem_cgroup_uncharge_swap - uncharge swap space
+ * __mem_cgroup_uncharge_swap - uncharge swap space
  * @entry: swap entry to uncharge
  * @nr_pages: the amount of swap space to uncharge
  */
-void mem_cgroup_uncharge_swap(swp_entry_t entry, unsigned int nr_pages)
+void __mem_cgroup_uncharge_swap(swp_entry_t entry, unsigned int nr_pages)
 {
 	struct mem_cgroup *memcg;
 	unsigned short id;
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index e1f87cf13235..54879c339024 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -68,7 +68,7 @@ atomic_long_t num_poisoned_pages __read_mostly = ATOMIC_LONG_INIT(0);
 
 static bool __page_handle_poison(struct page *page)
 {
-	bool ret;
+	int ret;
 
 	zone_pcp_disable(page_zone(page));
 	ret = dissolve_free_huge_page(page);
@@ -76,7 +76,7 @@ static bool __page_handle_poison(struct page *page)
 		ret = take_page_off_buddy(page);
 	zone_pcp_enable(page_zone(page));
 
-	return ret;
+	return ret > 0;
 }
 
 static bool page_handle_poison(struct page *page, bool hugepage_or_freepage, bool release)
@@ -282,9 +282,9 @@ static int kill_proc(struct to_kill *tk, unsigned long pfn, int flags)
 
 /*
  * Unknown page type encountered. Try to check whether it can turn PageLRU by
- * lru_add_drain_all, or a free page by reclaiming slabs when possible.
+ * lru_add_drain_all.
  */
-void shake_page(struct page *p, int access)
+void shake_page(struct page *p)
 {
 	if (PageHuge(p))
 		return;
@@ -296,11 +296,9 @@ void shake_page(struct page *p, int access)
 	}
 
 	/*
-	 * Only call shrink_node_slabs here (which would also shrink
-	 * other caches) if access is not potentially fatal.
+	 * TODO: Could shrink slab caches here if a lightweight range-based
+	 * shrinker will be available.
 	 */
-	if (access)
-		drop_slab_node(page_to_nid(p));
 }
 EXPORT_SYMBOL_GPL(shake_page);
 
@@ -391,8 +389,8 @@ static void add_to_kill(struct task_struct *tsk, struct page *p,
 /*
  * Kill the processes that have been collected earlier.
  *
- * Only do anything when DOIT is set, otherwise just free the list
- * (this is used for clean pages which do not need killing)
+ * Only do anything when FORCEKILL is set, otherwise just free the
+ * list (this is used for clean pages which do not need killing)
  * Also when FAIL is set do a force kill because something went
  * wrong earlier.
  */
@@ -632,7 +630,7 @@ static int hwpoison_pte_range(pmd_t *pmdp, unsigned long addr,
 {
 	struct hwp_walk *hwp = (struct hwp_walk *)walk->private;
 	int ret = 0;
-	pte_t *ptep;
+	pte_t *ptep, *mapped_pte;
 	spinlock_t *ptl;
 
 	ptl = pmd_trans_huge_lock(pmdp, walk->vma);
@@ -645,14 +643,15 @@ static int hwpoison_pte_range(pmd_t *pmdp, unsigned long addr,
 	if (pmd_trans_unstable(pmdp))
 		goto out;
 
-	ptep = pte_offset_map_lock(walk->vma->vm_mm, pmdp, addr, &ptl);
+	mapped_pte = ptep = pte_offset_map_lock(walk->vma->vm_mm, pmdp,
+						addr, &ptl);
 	for (; addr != end; ptep++, addr += PAGE_SIZE) {
 		ret = check_hwpoisoned_entry(*ptep, addr, PAGE_SHIFT,
 					     hwp->pfn, &hwp->tk);
 		if (ret == 1)
 			break;
 	}
-	pte_unmap_unlock(ptep - 1, ptl);
+	pte_unmap_unlock(mapped_pte, ptl);
 out:
 	cond_resched();
 	return ret;
@@ -1204,7 +1203,7 @@ try_again:
 			 * page, retry.
 			 */
 			if (pass++ < 3) {
-				shake_page(p, 1);
+				shake_page(p);
 				goto try_again;
 			}
 			ret = -EIO;
@@ -1221,7 +1220,7 @@ try_again:
 		 */
 		if (pass++ < 3) {
 			put_page(p);
-			shake_page(p, 1);
+			shake_page(p);
 			count_increased = false;
 			goto try_again;
 		}
@@ -1229,6 +1228,9 @@ try_again:
 		ret = -EIO;
 	}
 out:
+	if (ret == -EIO)
+		dump_page(p, "hwpoison: unhandlable page");
+
 	return ret;
 }
 
@@ -1270,14 +1272,13 @@ static int get_hwpoison_page(struct page *p, unsigned long flags)
  * the pages and send SIGBUS to the processes if the data was dirty.
  */
 static bool hwpoison_user_mappings(struct page *p, unsigned long pfn,
-				  int flags, struct page **hpagep)
+				  int flags, struct page *hpage)
 {
 	enum ttu_flags ttu = TTU_IGNORE_MLOCK | TTU_SYNC;
 	struct address_space *mapping;
 	LIST_HEAD(tokill);
 	bool unmap_success;
 	int kill = 1, forcekill;
-	struct page *hpage = *hpagep;
 	bool mlocked = PageMlocked(hpage);
 
 	/*
@@ -1369,7 +1370,7 @@ static bool hwpoison_user_mappings(struct page *p, unsigned long pfn,
 	 * shake_page() again to ensure that it's flushed.
 	 */
 	if (mlocked)
-		shake_page(hpage, 0);
+		shake_page(hpage);
 
 	/*
 	 * Now that the dirty bit has been propagated to the
@@ -1502,7 +1503,7 @@ static int memory_failure_hugetlb(unsigned long pfn, int flags)
 		goto out;
 	}
 
-	if (!hwpoison_user_mappings(p, pfn, flags, &head)) {
+	if (!hwpoison_user_mappings(p, pfn, flags, head)) {
 		action_result(pfn, MF_MSG_UNMAP_FAILED, MF_IGNORED);
 		res = -EBUSY;
 		goto out;
@@ -1518,7 +1519,6 @@ static int memory_failure_dev_pagemap(unsigned long pfn, int flags,
 		struct dev_pagemap *pgmap)
 {
 	struct page *page = pfn_to_page(pfn);
-	const bool unmap_success = true;
 	unsigned long size = 0;
 	struct to_kill *tk;
 	LIST_HEAD(tokill);
@@ -1590,7 +1590,7 @@ static int memory_failure_dev_pagemap(unsigned long pfn, int flags,
 		start = (page->index << PAGE_SHIFT) & ~(size - 1);
 		unmap_mapping_range(page->mapping, start, size, 0);
 	}
-	kill_procs(&tokill, flags & MF_MUST_KILL, !unmap_success, pfn, flags);
+	kill_procs(&tokill, flags & MF_MUST_KILL, false, pfn, flags);
 	rc = 0;
 unlock:
 	dax_unlock_page(page, cookie);
@@ -1724,7 +1724,7 @@ try_again:
 	 * The check (unnecessarily) ignores LRU pages being isolated and
 	 * walked by the page reclaim code, however that's not a big loss.
 	 */
-	shake_page(p, 0);
+	shake_page(p);
 
 	lock_page(p);
 
@@ -1783,7 +1783,7 @@ try_again:
 	 * Now take care of user space mappings.
 	 * Abort on fail: __delete_from_page_cache() assumes unmapped page.
 	 */
-	if (!hwpoison_user_mappings(p, pfn, flags, &p)) {
+	if (!hwpoison_user_mappings(p, pfn, flags, p)) {
 		action_result(pfn, MF_MSG_UNMAP_FAILED, MF_IGNORED);
 		res = -EBUSY;
 		goto unlock_page;
@@ -2099,7 +2099,7 @@ static int __soft_offline_page(struct page *page)
 
 	if (isolate_page(hpage, &pagelist)) {
 		ret = migrate_pages(&pagelist, alloc_migration_target, NULL,
-			(unsigned long)&mtc, MIGRATE_SYNC, MR_MEMORY_FAILURE);
+			(unsigned long)&mtc, MIGRATE_SYNC, MR_MEMORY_FAILURE, NULL);
 		if (!ret) {
 			bool release = !huge;
 
@@ -2208,9 +2208,6 @@ retry:
 			try_again = false;
 			goto retry;
 		}
-	} else if (ret == -EIO) {
-		pr_info("%s: %#lx: unknown page type: %lx (%pGp)\n",
-			 __func__, pfn, page->flags, &page->flags);
 	}
 
 	return ret;
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 86c3af79e874..4c527a80b6c9 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1469,7 +1469,7 @@ do_migrate_range(unsigned long start_pfn, unsigned long end_pfn)
 		if (nodes_empty(nmask))
 			node_set(mtc.nid, nmask);
 		ret = migrate_pages(&source, alloc_migration_target, NULL,
-			(unsigned long)&mtc, MIGRATE_SYNC, MR_MEMORY_HOTPLUG);
+			(unsigned long)&mtc, MIGRATE_SYNC, MR_MEMORY_HOTPLUG, NULL);
 		if (ret) {
 			list_for_each_entry(page, &source, lru) {
 				if (__ratelimit(&migrate_rs)) {
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index e32360e90274..5e90b3fb7794 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -31,6 +31,9 @@
  *                but useful to set in a VMA when you have a non default
  *                process policy.
  *
+ * preferred many Try a set of nodes first before normal fallback. This is
+ *                similar to preferred without the special case.
+ *
  * default        Allocate on the local node first, or when on a VMA
  *                use the process policy. This is what Linux always did
  *		  in a NUMA aware kernel and still does by, ahem, default.
@@ -189,7 +192,7 @@ static void mpol_relative_nodemask(nodemask_t *ret, const nodemask_t *orig,
 	nodes_onto(*ret, tmp, *rel);
 }
 
-static int mpol_new_interleave(struct mempolicy *pol, const nodemask_t *nodes)
+static int mpol_new_nodemask(struct mempolicy *pol, const nodemask_t *nodes)
 {
 	if (nodes_empty(*nodes))
 		return -EINVAL;
@@ -207,14 +210,6 @@ static int mpol_new_preferred(struct mempolicy *pol, const nodemask_t *nodes)
 	return 0;
 }
 
-static int mpol_new_bind(struct mempolicy *pol, const nodemask_t *nodes)
-{
-	if (nodes_empty(*nodes))
-		return -EINVAL;
-	pol->nodes = *nodes;
-	return 0;
-}
-
 /*
  * mpol_set_nodemask is called after mpol_new() to set up the nodemask, if
  * any, for the new policy.  mpol_new() has already validated the nodes
@@ -394,7 +389,7 @@ static const struct mempolicy_operations mpol_ops[MPOL_MAX] = {
 		.rebind = mpol_rebind_default,
 	},
 	[MPOL_INTERLEAVE] = {
-		.create = mpol_new_interleave,
+		.create = mpol_new_nodemask,
 		.rebind = mpol_rebind_nodemask,
 	},
 	[MPOL_PREFERRED] = {
@@ -402,12 +397,16 @@ static const struct mempolicy_operations mpol_ops[MPOL_MAX] = {
 		.rebind = mpol_rebind_preferred,
 	},
 	[MPOL_BIND] = {
-		.create = mpol_new_bind,
+		.create = mpol_new_nodemask,
 		.rebind = mpol_rebind_nodemask,
 	},
 	[MPOL_LOCAL] = {
 		.rebind = mpol_rebind_default,
 	},
+	[MPOL_PREFERRED_MANY] = {
+		.create = mpol_new_nodemask,
+		.rebind = mpol_rebind_preferred,
+	},
 };
 
 static int migrate_page_add(struct page *page, struct list_head *pagelist,
@@ -900,6 +899,7 @@ static void get_policy_nodemask(struct mempolicy *p, nodemask_t *nodes)
 	case MPOL_BIND:
 	case MPOL_INTERLEAVE:
 	case MPOL_PREFERRED:
+	case MPOL_PREFERRED_MANY:
 		*nodes = p->nodes;
 		break;
 	case MPOL_LOCAL:
@@ -1084,7 +1084,7 @@ static int migrate_to_node(struct mm_struct *mm, int source, int dest,
 
 	if (!list_empty(&pagelist)) {
 		err = migrate_pages(&pagelist, alloc_migration_target, NULL,
-				(unsigned long)&mtc, MIGRATE_SYNC, MR_SYSCALL);
+				(unsigned long)&mtc, MIGRATE_SYNC, MR_SYSCALL, NULL);
 		if (err)
 			putback_movable_pages(&pagelist);
 	}
@@ -1338,7 +1338,7 @@ static long do_mbind(unsigned long start, unsigned long len,
 		if (!list_empty(&pagelist)) {
 			WARN_ON_ONCE(flags & MPOL_MF_LAZY);
 			nr_failed = migrate_pages(&pagelist, new_page, NULL,
-				start, MIGRATE_SYNC, MR_MEMPOLICY_MBIND);
+				start, MIGRATE_SYNC, MR_MEMPOLICY_MBIND, NULL);
 			if (nr_failed)
 				putback_movable_pages(&pagelist);
 		}
@@ -1446,7 +1446,8 @@ static inline int sanitize_mpol_flags(int *mode, unsigned short *flags)
 {
 	*flags = *mode & MPOL_MODE_FLAGS;
 	*mode &= ~MPOL_MODE_FLAGS;
-	if ((unsigned int)(*mode) >= MPOL_MAX)
+
+	if ((unsigned int)(*mode) >=  MPOL_MAX)
 		return -EINVAL;
 	if ((*flags & MPOL_F_STATIC_NODES) && (*flags & MPOL_F_RELATIVE_NODES))
 		return -EINVAL;
@@ -1875,16 +1876,27 @@ static int apply_policy_zone(struct mempolicy *policy, enum zone_type zone)
  */
 nodemask_t *policy_nodemask(gfp_t gfp, struct mempolicy *policy)
 {
+	int mode = policy->mode;
+
 	/* Lower zones don't get a nodemask applied for MPOL_BIND */
-	if (unlikely(policy->mode == MPOL_BIND) &&
-			apply_policy_zone(policy, gfp_zone(gfp)) &&
-			cpuset_nodemask_valid_mems_allowed(&policy->nodes))
+	if (unlikely(mode == MPOL_BIND) &&
+		apply_policy_zone(policy, gfp_zone(gfp)) &&
+		cpuset_nodemask_valid_mems_allowed(&policy->nodes))
+		return &policy->nodes;
+
+	if (mode == MPOL_PREFERRED_MANY)
 		return &policy->nodes;
 
 	return NULL;
 }
 
-/* Return the node id preferred by the given mempolicy, or the given id */
+/*
+ * Return the  preferred node id for 'prefer' mempolicy, and return
+ * the given id for all other policies.
+ *
+ * policy_node() is always coupled with policy_nodemask(), which
+ * secures the nodemask limit for 'bind' and 'prefer-many' policy.
+ */
 static int policy_node(gfp_t gfp, struct mempolicy *policy, int nd)
 {
 	if (policy->mode == MPOL_PREFERRED) {
@@ -1922,7 +1934,7 @@ unsigned int mempolicy_slab_node(void)
 	struct mempolicy *policy;
 	int node = numa_mem_id();
 
-	if (in_interrupt())
+	if (!in_task())
 		return node;
 
 	policy = current->mempolicy;
@@ -1936,7 +1948,9 @@ unsigned int mempolicy_slab_node(void)
 	case MPOL_INTERLEAVE:
 		return interleave_nodes(policy);
 
-	case MPOL_BIND: {
+	case MPOL_BIND:
+	case MPOL_PREFERRED_MANY:
+	{
 		struct zoneref *z;
 
 		/*
@@ -2008,12 +2022,12 @@ static inline unsigned interleave_nid(struct mempolicy *pol,
  * @addr: address in @vma for shared policy lookup and interleave policy
  * @gfp_flags: for requested zone
  * @mpol: pointer to mempolicy pointer for reference counted mempolicy
- * @nodemask: pointer to nodemask pointer for MPOL_BIND nodemask
+ * @nodemask: pointer to nodemask pointer for 'bind' and 'prefer-many' policy
  *
  * Returns a nid suitable for a huge page allocation and a pointer
  * to the struct mempolicy for conditional unref after allocation.
- * If the effective policy is 'BIND, returns a pointer to the mempolicy's
- * @nodemask for filtering the zonelist.
+ * If the effective policy is 'bind' or 'prefer-many', returns a pointer
+ * to the mempolicy's @nodemask for filtering the zonelist.
  *
  * Must be protected by read_mems_allowed_begin()
  */
@@ -2021,16 +2035,18 @@ int huge_node(struct vm_area_struct *vma, unsigned long addr, gfp_t gfp_flags,
 				struct mempolicy **mpol, nodemask_t **nodemask)
 {
 	int nid;
+	int mode;
 
 	*mpol = get_vma_policy(vma, addr);
-	*nodemask = NULL;	/* assume !MPOL_BIND */
+	*nodemask = NULL;
+	mode = (*mpol)->mode;
 
-	if (unlikely((*mpol)->mode == MPOL_INTERLEAVE)) {
+	if (unlikely(mode == MPOL_INTERLEAVE)) {
 		nid = interleave_nid(*mpol, vma, addr,
 					huge_page_shift(hstate_vma(vma)));
 	} else {
 		nid = policy_node(gfp_flags, *mpol, numa_node_id());
-		if ((*mpol)->mode == MPOL_BIND)
+		if (mode == MPOL_BIND || mode == MPOL_PREFERRED_MANY)
 			*nodemask = &(*mpol)->nodes;
 	}
 	return nid;
@@ -2063,6 +2079,7 @@ bool init_nodemask_of_mempolicy(nodemask_t *mask)
 	mempolicy = current->mempolicy;
 	switch (mempolicy->mode) {
 	case MPOL_PREFERRED:
+	case MPOL_PREFERRED_MANY:
 	case MPOL_BIND:
 	case MPOL_INTERLEAVE:
 		*mask = mempolicy->nodes;
@@ -2128,6 +2145,27 @@ static struct page *alloc_page_interleave(gfp_t gfp, unsigned order,
 	return page;
 }
 
+static struct page *alloc_pages_preferred_many(gfp_t gfp, unsigned int order,
+						int nid, struct mempolicy *pol)
+{
+	struct page *page;
+	gfp_t preferred_gfp;
+
+	/*
+	 * This is a two pass approach. The first pass will only try the
+	 * preferred nodes but skip the direct reclaim and allow the
+	 * allocation to fail, while the second pass will try all the
+	 * nodes in system.
+	 */
+	preferred_gfp = gfp | __GFP_NOWARN;
+	preferred_gfp &= ~(__GFP_DIRECT_RECLAIM | __GFP_NOFAIL);
+	page = __alloc_pages(preferred_gfp, order, nid, &pol->nodes);
+	if (!page)
+		page = __alloc_pages(gfp, order, numa_node_id(), NULL);
+
+	return page;
+}
+
 /**
  * alloc_pages_vma - Allocate a page for a VMA.
  * @gfp: GFP flags.
@@ -2163,6 +2201,12 @@ struct page *alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma,
 		goto out;
 	}
 
+	if (pol->mode == MPOL_PREFERRED_MANY) {
+		page = alloc_pages_preferred_many(gfp, order, node, pol);
+		mpol_cond_put(pol);
+		goto out;
+	}
+
 	if (unlikely(IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) && hugepage)) {
 		int hpage_node = node;
 
@@ -2173,7 +2217,7 @@ struct page *alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma,
 		 * node and don't fall back to other nodes, as the cost of
 		 * remote accesses would likely offset THP benefits.
 		 *
-		 * If the policy is interleave, or does not allow the current
+		 * If the policy is interleave or does not allow the current
 		 * node in its nodemask, we allocate the standard way.
 		 */
 		if (pol->mode == MPOL_PREFERRED)
@@ -2240,6 +2284,9 @@ struct page *alloc_pages(gfp_t gfp, unsigned order)
 	 */
 	if (pol->mode == MPOL_INTERLEAVE)
 		page = alloc_page_interleave(gfp, order, interleave_nodes(pol));
+	else if (pol->mode == MPOL_PREFERRED_MANY)
+		page = alloc_pages_preferred_many(gfp, order,
+				numa_node_id(), pol);
 	else
 		page = __alloc_pages(gfp, order,
 				policy_node(gfp, pol, numa_node_id()),
@@ -2311,6 +2358,7 @@ bool __mpol_equal(struct mempolicy *a, struct mempolicy *b)
 	case MPOL_BIND:
 	case MPOL_INTERLEAVE:
 	case MPOL_PREFERRED:
+	case MPOL_PREFERRED_MANY:
 		return !!nodes_equal(a->nodes, b->nodes);
 	case MPOL_LOCAL:
 		return true;
@@ -2425,8 +2473,8 @@ static void sp_free(struct sp_node *n)
  * node id.  Policy determination "mimics" alloc_page_vma().
  * Called from fault path where we know the vma and faulting address.
  *
- * Return: -1 if the page is in a node that is valid for this policy, or a
- * suitable node ID to allocate a replacement page from.
+ * Return: NUMA_NO_NODE if the page is in a node that is valid for this
+ * policy, or a suitable node ID to allocate a replacement page from.
  */
 int mpol_misplaced(struct page *page, struct vm_area_struct *vma, unsigned long addr)
 {
@@ -2437,7 +2485,7 @@ int mpol_misplaced(struct page *page, struct vm_area_struct *vma, unsigned long
 	int thiscpu = raw_smp_processor_id();
 	int thisnid = cpu_to_node(thiscpu);
 	int polnid = NUMA_NO_NODE;
-	int ret = -1;
+	int ret = NUMA_NO_NODE;
 
 	pol = get_vma_policy(vma, addr);
 	if (!(pol->flags & MPOL_F_MOF))
@@ -2451,6 +2499,8 @@ int mpol_misplaced(struct page *page, struct vm_area_struct *vma, unsigned long
 		break;
 
 	case MPOL_PREFERRED:
+		if (node_isset(curnid, pol->nodes))
+			goto out;
 		polnid = first_node(pol->nodes);
 		break;
 
@@ -2465,9 +2515,10 @@ int mpol_misplaced(struct page *page, struct vm_area_struct *vma, unsigned long
 				break;
 			goto out;
 		}
+		fallthrough;
 
+	case MPOL_PREFERRED_MANY:
 		/*
-		 * allows binding to multiple nodes.
 		 * use current page if in policy nodemask,
 		 * else select nearest allowed node, if any.
 		 * If no allowed nodes, use current [!misplaced].
@@ -2829,6 +2880,7 @@ static const char * const policy_modes[] =
 	[MPOL_BIND]       = "bind",
 	[MPOL_INTERLEAVE] = "interleave",
 	[MPOL_LOCAL]      = "local",
+	[MPOL_PREFERRED_MANY]  = "prefer (many)",
 };
 
 
@@ -2907,6 +2959,7 @@ int mpol_parse_str(char *str, struct mempolicy **mpol)
 		if (!nodelist)
 			err = 0;
 		goto out;
+	case MPOL_PREFERRED_MANY:
 	case MPOL_BIND:
 		/*
 		 * Insist on a nodelist
@@ -2993,6 +3046,7 @@ void mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol)
 	case MPOL_LOCAL:
 		break;
 	case MPOL_PREFERRED:
+	case MPOL_PREFERRED_MANY:
 	case MPOL_BIND:
 	case MPOL_INTERLEAVE:
 		nodes = pol->nodes;
@@ -3021,3 +3075,64 @@ void mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol)
 		p += scnprintf(p, buffer + maxlen - p, ":%*pbl",
 			       nodemask_pr_args(&nodes));
 }
+
+bool numa_demotion_enabled = false;
+
+#ifdef CONFIG_SYSFS
+static ssize_t numa_demotion_enabled_show(struct kobject *kobj,
+					  struct kobj_attribute *attr, char *buf)
+{
+	return sysfs_emit(buf, "%s\n",
+			  numa_demotion_enabled? "true" : "false");
+}
+
+static ssize_t numa_demotion_enabled_store(struct kobject *kobj,
+					   struct kobj_attribute *attr,
+					   const char *buf, size_t count)
+{
+	if (!strncmp(buf, "true", 4) || !strncmp(buf, "1", 1))
+		numa_demotion_enabled = true;
+	else if (!strncmp(buf, "false", 5) || !strncmp(buf, "0", 1))
+		numa_demotion_enabled = false;
+	else
+		return -EINVAL;
+
+	return count;
+}
+
+static struct kobj_attribute numa_demotion_enabled_attr =
+	__ATTR(demotion_enabled, 0644, numa_demotion_enabled_show,
+	       numa_demotion_enabled_store);
+
+static struct attribute *numa_attrs[] = {
+	&numa_demotion_enabled_attr.attr,
+	NULL,
+};
+
+static const struct attribute_group numa_attr_group = {
+	.attrs = numa_attrs,
+};
+
+static int __init numa_init_sysfs(void)
+{
+	int err;
+	struct kobject *numa_kobj;
+
+	numa_kobj = kobject_create_and_add("numa", mm_kobj);
+	if (!numa_kobj) {
+		pr_err("failed to create numa kobject\n");
+		return -ENOMEM;
+	}
+	err = sysfs_create_group(numa_kobj, &numa_attr_group);
+	if (err) {
+		pr_err("failed to register numa group\n");
+		goto delete_obj;
+	}
+	return 0;
+
+delete_obj:
+	kobject_put(numa_kobj);
+	return err;
+}
+subsys_initcall(numa_init_sysfs);
+#endif
diff --git a/mm/migrate.c b/mm/migrate.c
index 7e240437e7d9..a0aeb3fe46a7 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -49,6 +49,7 @@
 #include <linux/sched/mm.h>
 #include <linux/ptrace.h>
 #include <linux/oom.h>
+#include <linux/memory.h>
 
 #include <asm/tlbflush.h>
 
@@ -1099,6 +1100,80 @@ out:
 	return rc;
 }
 
+
+/*
+ * node_demotion[] example:
+ *
+ * Consider a system with two sockets.  Each socket has
+ * three classes of memory attached: fast, medium and slow.
+ * Each memory class is placed in its own NUMA node.  The
+ * CPUs are placed in the node with the "fast" memory.  The
+ * 6 NUMA nodes (0-5) might be split among the sockets like
+ * this:
+ *
+ *	Socket A: 0, 1, 2
+ *	Socket B: 3, 4, 5
+ *
+ * When Node 0 fills up, its memory should be migrated to
+ * Node 1.  When Node 1 fills up, it should be migrated to
+ * Node 2.  The migration path start on the nodes with the
+ * processors (since allocations default to this node) and
+ * fast memory, progress through medium and end with the
+ * slow memory:
+ *
+ *	0 -> 1 -> 2 -> stop
+ *	3 -> 4 -> 5 -> stop
+ *
+ * This is represented in the node_demotion[] like this:
+ *
+ *	{  1, // Node 0 migrates to 1
+ *	   2, // Node 1 migrates to 2
+ *	  -1, // Node 2 does not migrate
+ *	   4, // Node 3 migrates to 4
+ *	   5, // Node 4 migrates to 5
+ *	  -1} // Node 5 does not migrate
+ */
+
+/*
+ * Writes to this array occur without locking.  Cycles are
+ * not allowed: Node X demotes to Y which demotes to X...
+ *
+ * If multiple reads are performed, a single rcu_read_lock()
+ * must be held over all reads to ensure that no cycles are
+ * observed.
+ */
+static int node_demotion[MAX_NUMNODES] __read_mostly =
+	{[0 ...  MAX_NUMNODES - 1] = NUMA_NO_NODE};
+
+/**
+ * next_demotion_node() - Get the next node in the demotion path
+ * @node: The starting node to lookup the next node
+ *
+ * Return: node id for next memory node in the demotion path hierarchy
+ * from @node; NUMA_NO_NODE if @node is terminal.  This does not keep
+ * @node online or guarantee that it *continues* to be the next demotion
+ * target.
+ */
+int next_demotion_node(int node)
+{
+	int target;
+
+	/*
+	 * node_demotion[] is updated without excluding this
+	 * function from running.  RCU doesn't provide any
+	 * compiler barriers, so the READ_ONCE() is required
+	 * to avoid compiler reordering or read merging.
+	 *
+	 * Make sure to use RCU over entire code blocks if
+	 * node_demotion[] reads need to be consistent.
+	 */
+	rcu_read_lock();
+	target = READ_ONCE(node_demotion[node]);
+	rcu_read_unlock();
+
+	return target;
+}
+
 /*
  * Obtain the lock on page, remove all ptes and migrate the page
  * to the newly allocated page in newpage.
@@ -1354,6 +1429,8 @@ static inline int try_split_thp(struct page *page, struct page **page2,
  * @mode:		The migration mode that specifies the constraints for
  *			page migration, if any.
  * @reason:		The reason for page migration.
+ * @ret_succeeded:	Set to the number of pages migrated successfully if
+ *			the caller passes a non-NULL pointer.
  *
  * The function returns after 10 attempts or if no pages are movable any more
  * because the list has become empty or no retryable pages exist any more.
@@ -1364,7 +1441,7 @@ static inline int try_split_thp(struct page *page, struct page **page2,
  */
 int migrate_pages(struct list_head *from, new_page_t get_new_page,
 		free_page_t put_new_page, unsigned long private,
-		enum migrate_mode mode, int reason)
+		enum migrate_mode mode, int reason, unsigned int *ret_succeeded)
 {
 	int retry = 1;
 	int thp_retry = 1;
@@ -1519,6 +1596,9 @@ out:
 	if (!swapwrite)
 		current->flags &= ~PF_SWAPWRITE;
 
+	if (ret_succeeded)
+		*ret_succeeded = nr_succeeded;
+
 	return rc;
 }
 
@@ -1588,7 +1668,7 @@ static int do_move_pages_to_node(struct mm_struct *mm,
 	};
 
 	err = migrate_pages(pagelist, alloc_migration_target, NULL,
-			(unsigned long)&mtc, MIGRATE_SYNC, MR_SYSCALL);
+		(unsigned long)&mtc, MIGRATE_SYNC, MR_SYSCALL, NULL);
 	if (err)
 		putback_movable_pages(pagelist);
 	return err;
@@ -2103,7 +2183,7 @@ int migrate_misplaced_page(struct page *page, struct vm_area_struct *vma,
 
 	list_add(&page->lru, &migratepages);
 	nr_remaining = migrate_pages(&migratepages, *new, NULL, node,
-				     MIGRATE_ASYNC, MR_NUMA_MISPLACED);
+				     MIGRATE_ASYNC, MR_NUMA_MISPLACED, NULL);
 	if (nr_remaining) {
 		if (!list_empty(&migratepages)) {
 			list_del(&page->lru);
@@ -2982,3 +3062,232 @@ void migrate_vma_finalize(struct migrate_vma *migrate)
 }
 EXPORT_SYMBOL(migrate_vma_finalize);
 #endif /* CONFIG_DEVICE_PRIVATE */
+
+#if defined(CONFIG_MEMORY_HOTPLUG)
+/* Disable reclaim-based migration. */
+static void __disable_all_migrate_targets(void)
+{
+	int node;
+
+	for_each_online_node(node)
+		node_demotion[node] = NUMA_NO_NODE;
+}
+
+static void disable_all_migrate_targets(void)
+{
+	__disable_all_migrate_targets();
+
+	/*
+	 * Ensure that the "disable" is visible across the system.
+	 * Readers will see either a combination of before+disable
+	 * state or disable+after.  They will never see before and
+	 * after state together.
+	 *
+	 * The before+after state together might have cycles and
+	 * could cause readers to do things like loop until this
+	 * function finishes.  This ensures they can only see a
+	 * single "bad" read and would, for instance, only loop
+	 * once.
+	 */
+	synchronize_rcu();
+}
+
+/*
+ * Find an automatic demotion target for 'node'.
+ * Failing here is OK.  It might just indicate
+ * being at the end of a chain.
+ */
+static int establish_migrate_target(int node, nodemask_t *used)
+{
+	int migration_target;
+
+	/*
+	 * Can not set a migration target on a
+	 * node with it already set.
+	 *
+	 * No need for READ_ONCE() here since this
+	 * in the write path for node_demotion[].
+	 * This should be the only thread writing.
+	 */
+	if (node_demotion[node] != NUMA_NO_NODE)
+		return NUMA_NO_NODE;
+
+	migration_target = find_next_best_node(node, used);
+	if (migration_target == NUMA_NO_NODE)
+		return NUMA_NO_NODE;
+
+	node_demotion[node] = migration_target;
+
+	return migration_target;
+}
+
+/*
+ * When memory fills up on a node, memory contents can be
+ * automatically migrated to another node instead of
+ * discarded at reclaim.
+ *
+ * Establish a "migration path" which will start at nodes
+ * with CPUs and will follow the priorities used to build the
+ * page allocator zonelists.
+ *
+ * The difference here is that cycles must be avoided.  If
+ * node0 migrates to node1, then neither node1, nor anything
+ * node1 migrates to can migrate to node0.
+ *
+ * This function can run simultaneously with readers of
+ * node_demotion[].  However, it can not run simultaneously
+ * with itself.  Exclusion is provided by memory hotplug events
+ * being single-threaded.
+ */
+static void __set_migration_target_nodes(void)
+{
+	nodemask_t next_pass	= NODE_MASK_NONE;
+	nodemask_t this_pass	= NODE_MASK_NONE;
+	nodemask_t used_targets = NODE_MASK_NONE;
+	int node;
+
+	/*
+	 * Avoid any oddities like cycles that could occur
+	 * from changes in the topology.  This will leave
+	 * a momentary gap when migration is disabled.
+	 */
+	disable_all_migrate_targets();
+
+	/*
+	 * Allocations go close to CPUs, first.  Assume that
+	 * the migration path starts at the nodes with CPUs.
+	 */
+	next_pass = node_states[N_CPU];
+again:
+	this_pass = next_pass;
+	next_pass = NODE_MASK_NONE;
+	/*
+	 * To avoid cycles in the migration "graph", ensure
+	 * that migration sources are not future targets by
+	 * setting them in 'used_targets'.  Do this only
+	 * once per pass so that multiple source nodes can
+	 * share a target node.
+	 *
+	 * 'used_targets' will become unavailable in future
+	 * passes.  This limits some opportunities for
+	 * multiple source nodes to share a destination.
+	 */
+	nodes_or(used_targets, used_targets, this_pass);
+	for_each_node_mask(node, this_pass) {
+		int target_node = establish_migrate_target(node, &used_targets);
+
+		if (target_node == NUMA_NO_NODE)
+			continue;
+
+		/*
+		 * Visit targets from this pass in the next pass.
+		 * Eventually, every node will have been part of
+		 * a pass, and will become set in 'used_targets'.
+		 */
+		node_set(target_node, next_pass);
+	}
+	/*
+	 * 'next_pass' contains nodes which became migration
+	 * targets in this pass.  Make additional passes until
+	 * no more migrations targets are available.
+	 */
+	if (!nodes_empty(next_pass))
+		goto again;
+}
+
+/*
+ * For callers that do not hold get_online_mems() already.
+ */
+static void set_migration_target_nodes(void)
+{
+	get_online_mems();
+	__set_migration_target_nodes();
+	put_online_mems();
+}
+
+/*
+ * React to hotplug events that might affect the migration targets
+ * like events that online or offline NUMA nodes.
+ *
+ * The ordering is also currently dependent on which nodes have
+ * CPUs.  That means we need CPU on/offline notification too.
+ */
+static int migration_online_cpu(unsigned int cpu)
+{
+	set_migration_target_nodes();
+	return 0;
+}
+
+static int migration_offline_cpu(unsigned int cpu)
+{
+	set_migration_target_nodes();
+	return 0;
+}
+
+/*
+ * This leaves migrate-on-reclaim transiently disabled between
+ * the MEM_GOING_OFFLINE and MEM_OFFLINE events.  This runs
+ * whether reclaim-based migration is enabled or not, which
+ * ensures that the user can turn reclaim-based migration at
+ * any time without needing to recalculate migration targets.
+ *
+ * These callbacks already hold get_online_mems().  That is why
+ * __set_migration_target_nodes() can be used as opposed to
+ * set_migration_target_nodes().
+ */
+static int __meminit migrate_on_reclaim_callback(struct notifier_block *self,
+						 unsigned long action, void *arg)
+{
+	switch (action) {
+	case MEM_GOING_OFFLINE:
+		/*
+		 * Make sure there are not transient states where
+		 * an offline node is a migration target.  This
+		 * will leave migration disabled until the offline
+		 * completes and the MEM_OFFLINE case below runs.
+		 */
+		disable_all_migrate_targets();
+		break;
+	case MEM_OFFLINE:
+	case MEM_ONLINE:
+		/*
+		 * Recalculate the target nodes once the node
+		 * reaches its final state (online or offline).
+		 */
+		__set_migration_target_nodes();
+		break;
+	case MEM_CANCEL_OFFLINE:
+		/*
+		 * MEM_GOING_OFFLINE disabled all the migration
+		 * targets.  Reenable them.
+		 */
+		__set_migration_target_nodes();
+		break;
+	case MEM_GOING_ONLINE:
+	case MEM_CANCEL_ONLINE:
+		break;
+	}
+
+	return notifier_from_errno(0);
+}
+
+static int __init migrate_on_reclaim_init(void)
+{
+	int ret;
+
+	ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "migrate on reclaim",
+				migration_online_cpu,
+				migration_offline_cpu);
+	/*
+	 * In the unlikely case that this fails, the automatic
+	 * migration targets may become suboptimal for nodes
+	 * where N_CPU changes.  With such a small impact in a
+	 * rare case, do not bother trying to do anything special.
+	 */
+	WARN_ON(ret < 0);
+
+	hotplug_memory_notifier(migrate_on_reclaim_callback, 100);
+	return 0;
+}
+late_initcall(migrate_on_reclaim_init);
+#endif /* CONFIG_MEMORY_HOTPLUG */
diff --git a/mm/mmap.c b/mm/mmap.c
index 181a113b545d..dce46105e3df 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -534,6 +534,7 @@ static int find_vma_links(struct mm_struct *mm, unsigned long addr,
 {
 	struct rb_node **__rb_link, *__rb_parent, *rb_prev;
 
+	mmap_assert_locked(mm);
 	__rb_link = &mm->mm_rb.rb_node;
 	rb_prev = __rb_parent = NULL;
 
@@ -2297,6 +2298,7 @@ struct vm_area_struct *find_vma(struct mm_struct *mm, unsigned long addr)
 	struct rb_node *rb_node;
 	struct vm_area_struct *vma;
 
+	mmap_assert_locked(mm);
 	/* Check the cache first. */
 	vma = vmacache_find(mm, addr);
 	if (likely(vma))
@@ -2986,14 +2988,11 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size,
 	if (mmap_write_lock_killable(mm))
 		return -EINTR;
 
-	vma = find_vma(mm, start);
+	vma = vma_lookup(mm, start);
 
 	if (!vma || !(vma->vm_flags & VM_SHARED))
 		goto out;
 
-	if (start < vma->vm_start)
-		goto out;
-
 	if (start + size > vma->vm_end) {
 		struct vm_area_struct *next;
 
diff --git a/mm/mremap.c b/mm/mremap.c
index 5989d3990020..badfe17ade1f 100644
--- a/mm/mremap.c
+++ b/mm/mremap.c
@@ -686,7 +686,7 @@ static unsigned long move_vma(struct vm_area_struct *vma,
 	if (do_munmap(mm, old_addr, old_len, uf_unmap) < 0) {
 		/* OOM: unable to split vma, just get accounts right */
 		if (vm_flags & VM_ACCOUNT && !(flags & MREMAP_DONTUNMAP))
-			vm_acct_memory(new_len >> PAGE_SHIFT);
+			vm_acct_memory(old_len >> PAGE_SHIFT);
 		excess = 0;
 	}
 
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index c729a4c4a1ac..831340e7ad8b 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -28,6 +28,7 @@
 #include <linux/sched/task.h>
 #include <linux/sched/debug.h>
 #include <linux/swap.h>
+#include <linux/syscalls.h>
 #include <linux/timex.h>
 #include <linux/jiffies.h>
 #include <linux/cpuset.h>
@@ -1141,3 +1142,72 @@ void pagefault_out_of_memory(void)
 	out_of_memory(&oc);
 	mutex_unlock(&oom_lock);
 }
+
+SYSCALL_DEFINE2(process_mrelease, int, pidfd, unsigned int, flags)
+{
+#ifdef CONFIG_MMU
+	struct mm_struct *mm = NULL;
+	struct task_struct *task;
+	struct task_struct *p;
+	unsigned int f_flags;
+	bool reap = true;
+	struct pid *pid;
+	long ret = 0;
+
+	if (flags)
+		return -EINVAL;
+
+	pid = pidfd_get_pid(pidfd, &f_flags);
+	if (IS_ERR(pid))
+		return PTR_ERR(pid);
+
+	task = get_pid_task(pid, PIDTYPE_TGID);
+	if (!task) {
+		ret = -ESRCH;
+		goto put_pid;
+	}
+
+	/*
+	 * Make sure to choose a thread which still has a reference to mm
+	 * during the group exit
+	 */
+	p = find_lock_task_mm(task);
+	if (!p) {
+		ret = -ESRCH;
+		goto put_task;
+	}
+
+	mm = p->mm;
+	mmgrab(mm);
+
+	/* If the work has been done already, just exit with success */
+	if (test_bit(MMF_OOM_SKIP, &mm->flags))
+		reap = false;
+	else if (!task_will_free_mem(p)) {
+		reap = false;
+		ret = -EINVAL;
+	}
+	task_unlock(p);
+
+	if (!reap)
+		goto drop_mm;
+
+	if (mmap_read_lock_killable(mm)) {
+		ret = -EINTR;
+		goto drop_mm;
+	}
+	if (!__oom_reap_task_mm(mm))
+		ret = -EAGAIN;
+	mmap_read_unlock(mm);
+
+drop_mm:
+	mmdrop(mm);
+put_task:
+	put_task_struct(task);
+put_pid:
+	put_pid(pid);
+	return ret;
+#else
+	return -ENOSYS;
+#endif /* CONFIG_MMU */
+}
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index c12f67cbfa19..4812a17b288c 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -183,7 +183,7 @@ static struct fprop_local_percpu *wb_memcg_completions(struct bdi_writeback *wb)
 static void wb_min_max_ratio(struct bdi_writeback *wb,
 			     unsigned long *minp, unsigned long *maxp)
 {
-	unsigned long this_bw = wb->avg_write_bandwidth;
+	unsigned long this_bw = READ_ONCE(wb->avg_write_bandwidth);
 	unsigned long tot_bw = atomic_long_read(&wb->bdi->tot_write_bandwidth);
 	unsigned long long min = wb->bdi->min_ratio;
 	unsigned long long max = wb->bdi->max_ratio;
@@ -892,7 +892,7 @@ static long long pos_ratio_polynom(unsigned long setpoint,
 static void wb_position_ratio(struct dirty_throttle_control *dtc)
 {
 	struct bdi_writeback *wb = dtc->wb;
-	unsigned long write_bw = wb->avg_write_bandwidth;
+	unsigned long write_bw = READ_ONCE(wb->avg_write_bandwidth);
 	unsigned long freerun = dirty_freerun_ceiling(dtc->thresh, dtc->bg_thresh);
 	unsigned long limit = hard_dirty_limit(dtc_dom(dtc), dtc->thresh);
 	unsigned long wb_thresh = dtc->wb_thresh;
@@ -1115,7 +1115,7 @@ out:
 					&wb->bdi->tot_write_bandwidth) <= 0);
 	}
 	wb->write_bandwidth = bw;
-	wb->avg_write_bandwidth = avg;
+	WRITE_ONCE(wb->avg_write_bandwidth, avg);
 }
 
 static void update_dirty_limit(struct dirty_throttle_control *dtc)
@@ -1147,8 +1147,8 @@ update:
 	dom->dirty_limit = limit;
 }
 
-static void domain_update_bandwidth(struct dirty_throttle_control *dtc,
-				    unsigned long now)
+static void domain_update_dirty_limit(struct dirty_throttle_control *dtc,
+				      unsigned long now)
 {
 	struct wb_domain *dom = dtc_dom(dtc);
 
@@ -1324,7 +1324,7 @@ static void wb_update_dirty_ratelimit(struct dirty_throttle_control *dtc,
 	else
 		dirty_ratelimit -= step;
 
-	wb->dirty_ratelimit = max(dirty_ratelimit, 1UL);
+	WRITE_ONCE(wb->dirty_ratelimit, max(dirty_ratelimit, 1UL));
 	wb->balanced_dirty_ratelimit = balanced_dirty_ratelimit;
 
 	trace_bdi_dirty_ratelimit(wb, dirty_rate, task_ratelimit);
@@ -1332,35 +1332,28 @@ static void wb_update_dirty_ratelimit(struct dirty_throttle_control *dtc,
 
 static void __wb_update_bandwidth(struct dirty_throttle_control *gdtc,
 				  struct dirty_throttle_control *mdtc,
-				  unsigned long start_time,
 				  bool update_ratelimit)
 {
 	struct bdi_writeback *wb = gdtc->wb;
 	unsigned long now = jiffies;
-	unsigned long elapsed = now - wb->bw_time_stamp;
+	unsigned long elapsed;
 	unsigned long dirtied;
 	unsigned long written;
 
-	lockdep_assert_held(&wb->list_lock);
+	spin_lock(&wb->list_lock);
 
 	/*
-	 * rate-limit, only update once every 200ms.
+	 * Lockless checks for elapsed time are racy and delayed update after
+	 * IO completion doesn't do it at all (to make sure written pages are
+	 * accounted reasonably quickly). Make sure elapsed >= 1 to avoid
+	 * division errors.
 	 */
-	if (elapsed < BANDWIDTH_INTERVAL)
-		return;
-
+	elapsed = max(now - wb->bw_time_stamp, 1UL);
 	dirtied = percpu_counter_read(&wb->stat[WB_DIRTIED]);
 	written = percpu_counter_read(&wb->stat[WB_WRITTEN]);
 
-	/*
-	 * Skip quiet periods when disk bandwidth is under-utilized.
-	 * (at least 1s idle time between two flusher runs)
-	 */
-	if (elapsed > HZ && time_before(wb->bw_time_stamp, start_time))
-		goto snapshot;
-
 	if (update_ratelimit) {
-		domain_update_bandwidth(gdtc, now);
+		domain_update_dirty_limit(gdtc, now);
 		wb_update_dirty_ratelimit(gdtc, dirtied, elapsed);
 
 		/*
@@ -1368,23 +1361,41 @@ static void __wb_update_bandwidth(struct dirty_throttle_control *gdtc,
 		 * compiler has no way to figure that out.  Help it.
 		 */
 		if (IS_ENABLED(CONFIG_CGROUP_WRITEBACK) && mdtc) {
-			domain_update_bandwidth(mdtc, now);
+			domain_update_dirty_limit(mdtc, now);
 			wb_update_dirty_ratelimit(mdtc, dirtied, elapsed);
 		}
 	}
 	wb_update_write_bandwidth(wb, elapsed, written);
 
-snapshot:
 	wb->dirtied_stamp = dirtied;
 	wb->written_stamp = written;
-	wb->bw_time_stamp = now;
+	WRITE_ONCE(wb->bw_time_stamp, now);
+	spin_unlock(&wb->list_lock);
 }
 
-void wb_update_bandwidth(struct bdi_writeback *wb, unsigned long start_time)
+void wb_update_bandwidth(struct bdi_writeback *wb)
 {
 	struct dirty_throttle_control gdtc = { GDTC_INIT(wb) };
 
-	__wb_update_bandwidth(&gdtc, NULL, start_time, false);
+	__wb_update_bandwidth(&gdtc, NULL, false);
+}
+
+/* Interval after which we consider wb idle and don't estimate bandwidth */
+#define WB_BANDWIDTH_IDLE_JIF (HZ)
+
+static void wb_bandwidth_estimate_start(struct bdi_writeback *wb)
+{
+	unsigned long now = jiffies;
+	unsigned long elapsed = now - READ_ONCE(wb->bw_time_stamp);
+
+	if (elapsed > WB_BANDWIDTH_IDLE_JIF &&
+	    !atomic_read(&wb->writeback_inodes)) {
+		spin_lock(&wb->list_lock);
+		wb->dirtied_stamp = wb_stat(wb, WB_DIRTIED);
+		wb->written_stamp = wb_stat(wb, WB_WRITTEN);
+		WRITE_ONCE(wb->bw_time_stamp, now);
+		spin_unlock(&wb->list_lock);
+	}
 }
 
 /*
@@ -1407,7 +1418,7 @@ static unsigned long dirty_poll_interval(unsigned long dirty,
 static unsigned long wb_max_pause(struct bdi_writeback *wb,
 				  unsigned long wb_dirty)
 {
-	unsigned long bw = wb->avg_write_bandwidth;
+	unsigned long bw = READ_ONCE(wb->avg_write_bandwidth);
 	unsigned long t;
 
 	/*
@@ -1429,8 +1440,8 @@ static long wb_min_pause(struct bdi_writeback *wb,
 			 unsigned long dirty_ratelimit,
 			 int *nr_dirtied_pause)
 {
-	long hi = ilog2(wb->avg_write_bandwidth);
-	long lo = ilog2(wb->dirty_ratelimit);
+	long hi = ilog2(READ_ONCE(wb->avg_write_bandwidth));
+	long lo = ilog2(READ_ONCE(wb->dirty_ratelimit));
 	long t;		/* target pause */
 	long pause;	/* estimated next pause */
 	int pages;	/* target nr_dirtied_pause */
@@ -1710,15 +1721,12 @@ free_running:
 		if (dirty_exceeded && !wb->dirty_exceeded)
 			wb->dirty_exceeded = 1;
 
-		if (time_is_before_jiffies(wb->bw_time_stamp +
-					   BANDWIDTH_INTERVAL)) {
-			spin_lock(&wb->list_lock);
-			__wb_update_bandwidth(gdtc, mdtc, start_time, true);
-			spin_unlock(&wb->list_lock);
-		}
+		if (time_is_before_jiffies(READ_ONCE(wb->bw_time_stamp) +
+					   BANDWIDTH_INTERVAL))
+			__wb_update_bandwidth(gdtc, mdtc, true);
 
 		/* throttle according to the chosen dtc */
-		dirty_ratelimit = wb->dirty_ratelimit;
+		dirty_ratelimit = READ_ONCE(wb->dirty_ratelimit);
 		task_ratelimit = ((u64)dirty_ratelimit * sdtc->pos_ratio) >>
 							RATELIMIT_CALC_SHIFT;
 		max_pause = wb_max_pause(wb, sdtc->wb_dirty);
@@ -2345,9 +2353,12 @@ EXPORT_SYMBOL(generic_writepages);
 int do_writepages(struct address_space *mapping, struct writeback_control *wbc)
 {
 	int ret;
+	struct bdi_writeback *wb;
 
 	if (wbc->nr_to_write <= 0)
 		return 0;
+	wb = inode_to_wb_wbc(mapping->host, wbc);
+	wb_bandwidth_estimate_start(wb);
 	while (1) {
 		if (mapping->a_ops->writepages)
 			ret = mapping->a_ops->writepages(mapping, wbc);
@@ -2358,6 +2369,14 @@ int do_writepages(struct address_space *mapping, struct writeback_control *wbc)
 		cond_resched();
 		congestion_wait(BLK_RW_ASYNC, HZ/50);
 	}
+	/*
+	 * Usually few pages are written by now from those we've just submitted
+	 * but if there's constant writeback being submitted, this makes sure
+	 * writeback bandwidth is updated once in a while.
+	 */
+	if (time_is_before_jiffies(READ_ONCE(wb->bw_time_stamp) +
+				   BANDWIDTH_INTERVAL))
+		wb_update_bandwidth(wb);
 	return ret;
 }
 
@@ -2729,6 +2748,24 @@ int clear_page_dirty_for_io(struct page *page)
 }
 EXPORT_SYMBOL(clear_page_dirty_for_io);
 
+static void wb_inode_writeback_start(struct bdi_writeback *wb)
+{
+	atomic_inc(&wb->writeback_inodes);
+}
+
+static void wb_inode_writeback_end(struct bdi_writeback *wb)
+{
+	atomic_dec(&wb->writeback_inodes);
+	/*
+	 * Make sure estimate of writeback throughput gets updated after
+	 * writeback completed. We delay the update by BANDWIDTH_INTERVAL
+	 * (which is the interval other bandwidth updates use for batching) so
+	 * that if multiple inodes end writeback at a similar time, they get
+	 * batched into one bandwidth update.
+	 */
+	queue_delayed_work(bdi_wq, &wb->bw_dwork, BANDWIDTH_INTERVAL);
+}
+
 int test_clear_page_writeback(struct page *page)
 {
 	struct address_space *mapping = page_mapping(page);
@@ -2750,6 +2787,9 @@ int test_clear_page_writeback(struct page *page)
 
 				dec_wb_stat(wb, WB_WRITEBACK);
 				__wb_writeout_inc(wb);
+				if (!mapping_tagged(mapping,
+						    PAGECACHE_TAG_WRITEBACK))
+					wb_inode_writeback_end(wb);
 			}
 		}
 
@@ -2792,8 +2832,13 @@ int __test_set_page_writeback(struct page *page, bool keep_write)
 						   PAGECACHE_TAG_WRITEBACK);
 
 			xas_set_mark(&xas, PAGECACHE_TAG_WRITEBACK);
-			if (bdi->capabilities & BDI_CAP_WRITEBACK_ACCT)
-				inc_wb_stat(inode_to_wb(inode), WB_WRITEBACK);
+			if (bdi->capabilities & BDI_CAP_WRITEBACK_ACCT) {
+				struct bdi_writeback *wb = inode_to_wb(inode);
+
+				inc_wb_stat(wb, WB_WRITEBACK);
+				if (!on_wblist)
+					wb_inode_writeback_start(wb);
+			}
 
 			/*
 			 * We can come through here when swapping anonymous
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index eeb3a9cb36bb..f95e1d2386a1 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -4211,7 +4211,7 @@ static void warn_alloc_show_mem(gfp_t gfp_mask, nodemask_t *nodemask)
 		if (tsk_is_oom_victim(current) ||
 		    (current->flags & (PF_MEMALLOC | PF_EXITING)))
 			filter &= ~SHOW_MEM_FILTER_NODES;
-	if (in_interrupt() || !(gfp_mask & __GFP_DIRECT_RECLAIM))
+	if (!in_task() || !(gfp_mask & __GFP_DIRECT_RECLAIM))
 		filter &= ~SHOW_MEM_FILTER_NODES;
 
 	show_mem(filter, nodemask);
@@ -4549,14 +4549,14 @@ static bool __need_reclaim(gfp_t gfp_mask)
 	return true;
 }
 
-void __fs_reclaim_acquire(void)
+void __fs_reclaim_acquire(unsigned long ip)
 {
-	lock_map_acquire(&__fs_reclaim_map);
+	lock_acquire_exclusive(&__fs_reclaim_map, 0, 0, NULL, ip);
 }
 
-void __fs_reclaim_release(void)
+void __fs_reclaim_release(unsigned long ip)
 {
-	lock_map_release(&__fs_reclaim_map);
+	lock_release(&__fs_reclaim_map, ip);
 }
 
 void fs_reclaim_acquire(gfp_t gfp_mask)
@@ -4565,7 +4565,7 @@ void fs_reclaim_acquire(gfp_t gfp_mask)
 
 	if (__need_reclaim(gfp_mask)) {
 		if (gfp_mask & __GFP_FS)
-			__fs_reclaim_acquire();
+			__fs_reclaim_acquire(_RET_IP_);
 
 #ifdef CONFIG_MMU_NOTIFIER
 		lock_map_acquire(&__mmu_notifier_invalidate_range_start_map);
@@ -4582,7 +4582,7 @@ void fs_reclaim_release(gfp_t gfp_mask)
 
 	if (__need_reclaim(gfp_mask)) {
 		if (gfp_mask & __GFP_FS)
-			__fs_reclaim_release();
+			__fs_reclaim_release(_RET_IP_);
 	}
 }
 EXPORT_SYMBOL_GPL(fs_reclaim_release);
@@ -4697,7 +4697,7 @@ gfp_to_alloc_flags(gfp_t gfp_mask)
 		 * comment for __cpuset_node_allowed().
 		 */
 		alloc_flags &= ~ALLOC_CPUSET;
-	} else if (unlikely(rt_task(current)) && !in_interrupt())
+	} else if (unlikely(rt_task(current)) && in_task())
 		alloc_flags |= ALLOC_HARDER;
 
 	alloc_flags = gfp_to_alloc_flags_cma(gfp_mask, alloc_flags);
@@ -5157,7 +5157,7 @@ static inline bool prepare_alloc_pages(gfp_t gfp_mask, unsigned int order,
 		 * When we are in the interrupt context, it is irrelevant
 		 * to the current task context. It means that any node ok.
 		 */
-		if (!in_interrupt() && !ac->nodemask)
+		if (in_task() && !ac->nodemask)
 			ac->nodemask = &cpuset_current_mems_allowed;
 		else
 			*alloc_flags |= ALLOC_CPUSET;
@@ -5903,6 +5903,7 @@ void show_free_areas(unsigned int filter, nodemask_t *nodemask)
 		" unevictable:%lu dirty:%lu writeback:%lu\n"
 		" slab_reclaimable:%lu slab_unreclaimable:%lu\n"
 		" mapped:%lu shmem:%lu pagetables:%lu bounce:%lu\n"
+		" kernel_misc_reclaimable:%lu\n"
 		" free:%lu free_pcp:%lu free_cma:%lu\n",
 		global_node_page_state(NR_ACTIVE_ANON),
 		global_node_page_state(NR_INACTIVE_ANON),
@@ -5919,6 +5920,7 @@ void show_free_areas(unsigned int filter, nodemask_t *nodemask)
 		global_node_page_state(NR_SHMEM),
 		global_node_page_state(NR_PAGETABLE),
 		global_zone_page_state(NR_BOUNCE),
+		global_node_page_state(NR_KERNEL_MISC_RECLAIMABLE),
 		global_zone_page_state(NR_FREE_PAGES),
 		free_pcp,
 		global_zone_page_state(NR_FREE_CMA_PAGES));
@@ -6155,7 +6157,7 @@ static int node_load[MAX_NUMNODES];
  *
  * Return: node id of the found node or %NUMA_NO_NODE if no node is found.
  */
-static int find_next_best_node(int node, nodemask_t *used_node_mask)
+int find_next_best_node(int node, nodemask_t *used_node_mask)
 {
 	int n, val;
 	int min_val = INT_MAX;
@@ -6640,7 +6642,6 @@ static void __meminit zone_init_free_lists(struct zone *zone)
 	}
 }
 
-#if !defined(CONFIG_FLATMEM)
 /*
  * Only struct pages that correspond to ranges defined by memblock.memory
  * are zeroed and initialized by going through __init_single_page() during
@@ -6685,13 +6686,6 @@ static void __init init_unavailable_range(unsigned long spfn,
 		pr_info("On node %d, zone %s: %lld pages in unavailable ranges",
 			node, zone_names[zone], pgcnt);
 }
-#else
-static inline void init_unavailable_range(unsigned long spfn,
-					  unsigned long epfn,
-					  int zone, int node)
-{
-}
-#endif
 
 static void __init memmap_init_zone_range(struct zone *zone,
 					  unsigned long start_pfn,
@@ -6721,7 +6715,7 @@ static void __init memmap_init(void)
 {
 	unsigned long start_pfn, end_pfn;
 	unsigned long hole_pfn = 0;
-	int i, j, zone_id, nid;
+	int i, j, zone_id = 0, nid;
 
 	for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, &nid) {
 		struct pglist_data *node = NODE_DATA(nid);
@@ -6754,6 +6748,26 @@ static void __init memmap_init(void)
 		init_unavailable_range(hole_pfn, end_pfn, zone_id, nid);
 }
 
+void __init *memmap_alloc(phys_addr_t size, phys_addr_t align,
+			  phys_addr_t min_addr, int nid, bool exact_nid)
+{
+	void *ptr;
+
+	if (exact_nid)
+		ptr = memblock_alloc_exact_nid_raw(size, align, min_addr,
+						   MEMBLOCK_ALLOC_ACCESSIBLE,
+						   nid);
+	else
+		ptr = memblock_alloc_try_nid_raw(size, align, min_addr,
+						 MEMBLOCK_ALLOC_ACCESSIBLE,
+						 nid);
+
+	if (ptr && size > 0)
+		page_init_poison(ptr, size);
+
+	return ptr;
+}
+
 static int zone_batchsize(struct zone *zone)
 {
 #ifdef CONFIG_MMU
@@ -7501,7 +7515,7 @@ static void __init free_area_init_core(struct pglist_data *pgdat)
 }
 
 #ifdef CONFIG_FLATMEM
-static void __ref alloc_node_mem_map(struct pglist_data *pgdat)
+static void __init alloc_node_mem_map(struct pglist_data *pgdat)
 {
 	unsigned long __maybe_unused start = 0;
 	unsigned long __maybe_unused offset = 0;
@@ -7525,8 +7539,8 @@ static void __ref alloc_node_mem_map(struct pglist_data *pgdat)
 		end = pgdat_end_pfn(pgdat);
 		end = ALIGN(end, MAX_ORDER_NR_PAGES);
 		size =  (end - start) * sizeof(struct page);
-		map = memblock_alloc_node(size, SMP_CACHE_BYTES,
-					  pgdat->node_id);
+		map = memmap_alloc(size, SMP_CACHE_BYTES, MEMBLOCK_LOW_LIMIT,
+				   pgdat->node_id, false);
 		if (!map)
 			panic("Failed to allocate %ld bytes for node %d memory map\n",
 			      size, pgdat->node_id);
@@ -7547,7 +7561,7 @@ static void __ref alloc_node_mem_map(struct pglist_data *pgdat)
 #endif
 }
 #else
-static void __ref alloc_node_mem_map(struct pglist_data *pgdat) { }
+static inline void alloc_node_mem_map(struct pglist_data *pgdat) { }
 #endif /* CONFIG_FLATMEM */
 
 #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
@@ -8976,7 +8990,7 @@ static int __alloc_contig_migrate_range(struct compact_control *cc,
 		cc->nr_migratepages -= nr_reclaimed;
 
 		ret = migrate_pages(&cc->migratepages, alloc_migration_target,
-				NULL, (unsigned long)&mtc, cc->mode, MR_CONTIG_RANGE);
+			NULL, (unsigned long)&mtc, cc->mode, MR_CONTIG_RANGE, NULL);
 
 		/*
 		 * On -ENOMEM, migrate_pages() bails out right away. It is pointless
diff --git a/mm/page_isolation.c b/mm/page_isolation.c
index bddf788f45bf..fff55bb830f9 100644
--- a/mm/page_isolation.c
+++ b/mm/page_isolation.c
@@ -287,6 +287,7 @@ int test_pages_isolated(unsigned long start_pfn, unsigned long end_pfn,
 	unsigned long pfn, flags;
 	struct page *page;
 	struct zone *zone;
+	int ret;
 
 	/*
 	 * Note: pageblock_nr_pages != MAX_ORDER. Then, chunks of free pages
@@ -299,15 +300,21 @@ int test_pages_isolated(unsigned long start_pfn, unsigned long end_pfn,
 			break;
 	}
 	page = __first_valid_page(start_pfn, end_pfn - start_pfn);
-	if ((pfn < end_pfn) || !page)
-		return -EBUSY;
+	if ((pfn < end_pfn) || !page) {
+		ret = -EBUSY;
+		goto out;
+	}
+
 	/* Check all pages are free or marked as ISOLATED */
 	zone = page_zone(page);
 	spin_lock_irqsave(&zone->lock, flags);
 	pfn = __test_page_isolated_in_pageblock(start_pfn, end_pfn, isol_flags);
 	spin_unlock_irqrestore(&zone->lock, flags);
 
+	ret = pfn < end_pfn ? -EBUSY : 0;
+
+out:
 	trace_test_pages_isolated(start_pfn, end_pfn, pfn);
 
-	return pfn < end_pfn ? -EBUSY : 0;
+	return ret;
 }
diff --git a/mm/percpu.c b/mm/percpu.c
index 7f2e0151c4e2..e1c20837a42a 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -1520,9 +1520,6 @@ static void pcpu_free_chunk(struct pcpu_chunk *chunk)
  * Pages in [@page_start,@page_end) have been populated to @chunk.  Update
  * the bookkeeping information accordingly.  Must be called after each
  * successful population.
- *
- * If this is @for_alloc, do not increment pcpu_nr_empty_pop_pages because it
- * is to serve an allocation in that area.
  */
 static void pcpu_chunk_populated(struct pcpu_chunk *chunk, int page_start,
 				 int page_end)
diff --git a/mm/shmem.c b/mm/shmem.c
index 3107acee4f71..88742953532c 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -38,8 +38,7 @@
 #include <linux/hugetlb.h>
 #include <linux/frontswap.h>
 #include <linux/fs_parser.h>
-
-#include <asm/tlbflush.h> /* for arch/microblaze update_mmu_cache() */
+#include <linux/swapfile.h>
 
 static struct vfsmount *shm_mnt;
 
@@ -137,9 +136,6 @@ static unsigned long shmem_default_max_inodes(void)
 }
 #endif
 
-static bool shmem_should_replace_page(struct page *page, gfp_t gfp);
-static int shmem_replace_page(struct page **pagep, gfp_t gfp,
-				struct shmem_inode_info *info, pgoff_t index);
 static int shmem_swapin_page(struct inode *inode, pgoff_t index,
 			     struct page **pagep, enum sgp_type sgp,
 			     gfp_t gfp, struct vm_area_struct *vma,
@@ -278,10 +274,10 @@ static int shmem_reserve_inode(struct super_block *sb, ino_t *inop)
 	ino_t ino;
 
 	if (!(sb->s_flags & SB_KERNMOUNT)) {
-		spin_lock(&sbinfo->stat_lock);
+		raw_spin_lock(&sbinfo->stat_lock);
 		if (sbinfo->max_inodes) {
 			if (!sbinfo->free_inodes) {
-				spin_unlock(&sbinfo->stat_lock);
+				raw_spin_unlock(&sbinfo->stat_lock);
 				return -ENOSPC;
 			}
 			sbinfo->free_inodes--;
@@ -304,7 +300,7 @@ static int shmem_reserve_inode(struct super_block *sb, ino_t *inop)
 			}
 			*inop = ino;
 		}
-		spin_unlock(&sbinfo->stat_lock);
+		raw_spin_unlock(&sbinfo->stat_lock);
 	} else if (inop) {
 		/*
 		 * __shmem_file_setup, one of our callers, is lock-free: it
@@ -319,13 +315,14 @@ static int shmem_reserve_inode(struct super_block *sb, ino_t *inop)
 		 * to worry about things like glibc compatibility.
 		 */
 		ino_t *next_ino;
+
 		next_ino = per_cpu_ptr(sbinfo->ino_batch, get_cpu());
 		ino = *next_ino;
 		if (unlikely(ino % SHMEM_INO_BATCH == 0)) {
-			spin_lock(&sbinfo->stat_lock);
+			raw_spin_lock(&sbinfo->stat_lock);
 			ino = sbinfo->next_ino;
 			sbinfo->next_ino += SHMEM_INO_BATCH;
-			spin_unlock(&sbinfo->stat_lock);
+			raw_spin_unlock(&sbinfo->stat_lock);
 			if (unlikely(is_zero_ino(ino)))
 				ino++;
 		}
@@ -341,9 +338,9 @@ static void shmem_free_inode(struct super_block *sb)
 {
 	struct shmem_sb_info *sbinfo = SHMEM_SB(sb);
 	if (sbinfo->max_inodes) {
-		spin_lock(&sbinfo->stat_lock);
+		raw_spin_lock(&sbinfo->stat_lock);
 		sbinfo->free_inodes++;
-		spin_unlock(&sbinfo->stat_lock);
+		raw_spin_unlock(&sbinfo->stat_lock);
 	}
 }
 
@@ -474,7 +471,38 @@ static bool shmem_confirm_swap(struct address_space *mapping,
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 /* ifdef here to avoid bloating shmem.o when not necessary */
 
-static int shmem_huge __read_mostly;
+static int shmem_huge __read_mostly = SHMEM_HUGE_NEVER;
+
+bool shmem_is_huge(struct vm_area_struct *vma,
+		   struct inode *inode, pgoff_t index)
+{
+	loff_t i_size;
+
+	if (shmem_huge == SHMEM_HUGE_DENY)
+		return false;
+	if (vma && ((vma->vm_flags & VM_NOHUGEPAGE) ||
+	    test_bit(MMF_DISABLE_THP, &vma->vm_mm->flags)))
+		return false;
+	if (shmem_huge == SHMEM_HUGE_FORCE)
+		return true;
+
+	switch (SHMEM_SB(inode->i_sb)->huge) {
+	case SHMEM_HUGE_ALWAYS:
+		return true;
+	case SHMEM_HUGE_WITHIN_SIZE:
+		index = round_up(index, HPAGE_PMD_NR);
+		i_size = round_up(i_size_read(inode), PAGE_SIZE);
+		if (i_size >= HPAGE_PMD_SIZE && (i_size >> PAGE_SHIFT) >= index)
+			return true;
+		fallthrough;
+	case SHMEM_HUGE_ADVISE:
+		if (vma && (vma->vm_flags & VM_HUGEPAGE))
+			return true;
+		fallthrough;
+	default:
+		return false;
+	}
+}
 
 #if defined(CONFIG_SYSFS)
 static int shmem_parse_huge(const char *str)
@@ -645,6 +673,12 @@ static long shmem_unused_huge_count(struct super_block *sb,
 
 #define shmem_huge SHMEM_HUGE_DENY
 
+bool shmem_is_huge(struct vm_area_struct *vma,
+		   struct inode *inode, pgoff_t index)
+{
+	return false;
+}
+
 static unsigned long shmem_unused_huge_shrink(struct shmem_sb_info *sbinfo,
 		struct shrink_control *sc, unsigned long nr_to_split)
 {
@@ -652,15 +686,6 @@ static unsigned long shmem_unused_huge_shrink(struct shmem_sb_info *sbinfo,
 }
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 
-static inline bool is_huge_enabled(struct shmem_sb_info *sbinfo)
-{
-	if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) &&
-	    (shmem_huge == SHMEM_HUGE_FORCE || sbinfo->huge) &&
-	    shmem_huge != SHMEM_HUGE_DENY)
-		return true;
-	return false;
-}
-
 /*
  * Like add_to_page_cache_locked, but error if expected item has gone.
  */
@@ -905,6 +930,9 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend,
 	if (lend == -1)
 		end = -1;	/* unsigned, so actually very big */
 
+	if (info->fallocend > start && info->fallocend <= end && !unfalloc)
+		info->fallocend = start;
+
 	pagevec_init(&pvec);
 	index = start;
 	while (index < end && find_lock_entries(mapping, index, end - 1,
@@ -1038,7 +1066,6 @@ static int shmem_getattr(struct user_namespace *mnt_userns,
 {
 	struct inode *inode = path->dentry->d_inode;
 	struct shmem_inode_info *info = SHMEM_I(inode);
-	struct shmem_sb_info *sb_info = SHMEM_SB(inode->i_sb);
 
 	if (info->alloced - info->swapped != inode->i_mapping->nrpages) {
 		spin_lock_irq(&info->lock);
@@ -1047,7 +1074,7 @@ static int shmem_getattr(struct user_namespace *mnt_userns,
 	}
 	generic_fillattr(&init_user_ns, inode, stat);
 
-	if (is_huge_enabled(sb_info))
+	if (shmem_is_huge(NULL, inode, 0))
 		stat->blksize = HPAGE_PMD_SIZE;
 
 	return 0;
@@ -1058,7 +1085,6 @@ static int shmem_setattr(struct user_namespace *mnt_userns,
 {
 	struct inode *inode = d_inode(dentry);
 	struct shmem_inode_info *info = SHMEM_I(inode);
-	struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb);
 	int error;
 
 	error = setattr_prepare(&init_user_ns, dentry, attr);
@@ -1094,24 +1120,6 @@ static int shmem_setattr(struct user_namespace *mnt_userns,
 			if (oldsize > holebegin)
 				unmap_mapping_range(inode->i_mapping,
 							holebegin, 0, 1);
-
-			/*
-			 * Part of the huge page can be beyond i_size: subject
-			 * to shrink under memory pressure.
-			 */
-			if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) {
-				spin_lock(&sbinfo->shrinklist_lock);
-				/*
-				 * _careful to defend against unlocked access to
-				 * ->shrink_list in shmem_unused_huge_shrink()
-				 */
-				if (list_empty_careful(&info->shrinklist)) {
-					list_add_tail(&info->shrinklist,
-							&sbinfo->shrinklist);
-					sbinfo->shrinklist_len++;
-				}
-				spin_unlock(&sbinfo->shrinklist_lock);
-			}
 		}
 	}
 
@@ -1156,8 +1164,6 @@ static void shmem_evict_inode(struct inode *inode)
 	clear_inode(inode);
 }
 
-extern struct swap_info_struct *swap_info[];
-
 static int shmem_find_swap_entries(struct address_space *mapping,
 				   pgoff_t start, unsigned int nr_entries,
 				   struct page **entries, pgoff_t *indices,
@@ -1338,7 +1344,19 @@ static int shmem_writepage(struct page *page, struct writeback_control *wbc)
 	swp_entry_t swap;
 	pgoff_t index;
 
-	VM_BUG_ON_PAGE(PageCompound(page), page);
+	/*
+	 * If /sys/kernel/mm/transparent_hugepage/shmem_enabled is "always" or
+	 * "force", drivers/gpu/drm/i915/gem/i915_gem_shmem.c gets huge pages,
+	 * and its shmem_writeback() needs them to be split when swapping.
+	 */
+	if (PageTransCompound(page)) {
+		/* Ensure the subpages are still dirty */
+		SetPageDirty(page);
+		if (split_huge_page(page) < 0)
+			goto redirty;
+		ClearPageDirty(page);
+	}
+
 	BUG_ON(!PageLocked(page));
 	mapping = page->mapping;
 	index = page->index;
@@ -1453,10 +1471,10 @@ static struct mempolicy *shmem_get_sbmpol(struct shmem_sb_info *sbinfo)
 {
 	struct mempolicy *mpol = NULL;
 	if (sbinfo->mpol) {
-		spin_lock(&sbinfo->stat_lock);	/* prevent replace/use races */
+		raw_spin_lock(&sbinfo->stat_lock);	/* prevent replace/use races */
 		mpol = sbinfo->mpol;
 		mpol_get(mpol);
-		spin_unlock(&sbinfo->stat_lock);
+		raw_spin_unlock(&sbinfo->stat_lock);
 	}
 	return mpol;
 }
@@ -1798,7 +1816,6 @@ static int shmem_getpage_gfp(struct inode *inode, pgoff_t index,
 	struct shmem_sb_info *sbinfo;
 	struct mm_struct *charge_mm;
 	struct page *page;
-	enum sgp_type sgp_huge = sgp;
 	pgoff_t hindex = index;
 	gfp_t huge_gfp;
 	int error;
@@ -1807,8 +1824,6 @@ static int shmem_getpage_gfp(struct inode *inode, pgoff_t index,
 
 	if (index > (MAX_LFS_FILESIZE >> PAGE_SHIFT))
 		return -EFBIG;
-	if (sgp == SGP_NOHUGE || sgp == SGP_HUGE)
-		sgp = SGP_CACHE;
 repeat:
 	if (sgp <= SGP_CACHE &&
 	    ((loff_t)index << PAGE_SHIFT) >= i_size_read(inode)) {
@@ -1840,26 +1855,31 @@ repeat:
 		return error;
 	}
 
-	if (page)
+	if (page) {
 		hindex = page->index;
-	if (page && sgp == SGP_WRITE)
-		mark_page_accessed(page);
-
-	/* fallocated page? */
-	if (page && !PageUptodate(page)) {
+		if (sgp == SGP_WRITE)
+			mark_page_accessed(page);
+		if (PageUptodate(page))
+			goto out;
+		/* fallocated page */
 		if (sgp != SGP_READ)
 			goto clear;
 		unlock_page(page);
 		put_page(page);
-		page = NULL;
-		hindex = index;
 	}
-	if (page || sgp == SGP_READ)
-		goto out;
 
 	/*
-	 * Fast cache lookup did not find it:
-	 * bring it back from swap or allocate.
+	 * SGP_READ: succeed on hole, with NULL page, letting caller zero.
+	 * SGP_NOALLOC: fail on hole, with NULL page, letting caller fail.
+	 */
+	*pagep = NULL;
+	if (sgp == SGP_READ)
+		return 0;
+	if (sgp == SGP_NOALLOC)
+		return -ENOENT;
+
+	/*
+	 * Fast cache lookup and swap lookup did not find it: allocate.
 	 */
 
 	if (vma && userfaultfd_missing(vma)) {
@@ -1867,36 +1887,12 @@ repeat:
 		return 0;
 	}
 
-	/* shmem_symlink() */
-	if (!shmem_mapping(mapping))
-		goto alloc_nohuge;
-	if (shmem_huge == SHMEM_HUGE_DENY || sgp_huge == SGP_NOHUGE)
-		goto alloc_nohuge;
-	if (shmem_huge == SHMEM_HUGE_FORCE)
-		goto alloc_huge;
-	switch (sbinfo->huge) {
-	case SHMEM_HUGE_NEVER:
+	/* Never use a huge page for shmem_symlink() */
+	if (S_ISLNK(inode->i_mode))
 		goto alloc_nohuge;
-	case SHMEM_HUGE_WITHIN_SIZE: {
-		loff_t i_size;
-		pgoff_t off;
-
-		off = round_up(index, HPAGE_PMD_NR);
-		i_size = round_up(i_size_read(inode), PAGE_SIZE);
-		if (i_size >= HPAGE_PMD_SIZE &&
-		    i_size >> PAGE_SHIFT >= off)
-			goto alloc_huge;
-
-		fallthrough;
-	}
-	case SHMEM_HUGE_ADVISE:
-		if (sgp_huge == SGP_HUGE)
-			goto alloc_huge;
-		/* TODO: implement fadvise() hints */
+	if (!shmem_is_huge(vma, inode, index))
 		goto alloc_nohuge;
-	}
 
-alloc_huge:
 	huge_gfp = vma_thp_gfp_mask(vma);
 	huge_gfp = limit_gfp_mask(huge_gfp, gfp);
 	page = shmem_alloc_and_acct_page(huge_gfp, inode, index, true);
@@ -2052,7 +2048,6 @@ static vm_fault_t shmem_fault(struct vm_fault *vmf)
 	struct vm_area_struct *vma = vmf->vma;
 	struct inode *inode = file_inode(vma->vm_file);
 	gfp_t gfp = mapping_gfp_mask(inode->i_mapping);
-	enum sgp_type sgp;
 	int err;
 	vm_fault_t ret = VM_FAULT_LOCKED;
 
@@ -2115,15 +2110,7 @@ static vm_fault_t shmem_fault(struct vm_fault *vmf)
 		spin_unlock(&inode->i_lock);
 	}
 
-	sgp = SGP_CACHE;
-
-	if ((vma->vm_flags & VM_NOHUGEPAGE) ||
-	    test_bit(MMF_DISABLE_THP, &vma->vm_mm->flags))
-		sgp = SGP_NOHUGE;
-	else if (vma->vm_flags & VM_HUGEPAGE)
-		sgp = SGP_HUGE;
-
-	err = shmem_getpage_gfp(inode, vmf->pgoff, &vmf->page, sgp,
+	err = shmem_getpage_gfp(inode, vmf->pgoff, &vmf->page, SGP_CACHE,
 				  gfp, vma, vmf, &ret);
 	if (err)
 		return vmf_error(err);
@@ -2655,7 +2642,7 @@ static long shmem_fallocate(struct file *file, int mode, loff_t offset,
 	struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb);
 	struct shmem_inode_info *info = SHMEM_I(inode);
 	struct shmem_falloc shmem_falloc;
-	pgoff_t start, index, end;
+	pgoff_t start, index, end, undo_fallocend;
 	int error;
 
 	if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE))
@@ -2724,7 +2711,16 @@ static long shmem_fallocate(struct file *file, int mode, loff_t offset,
 	inode->i_private = &shmem_falloc;
 	spin_unlock(&inode->i_lock);
 
-	for (index = start; index < end; index++) {
+	/*
+	 * info->fallocend is only relevant when huge pages might be
+	 * involved: to prevent split_huge_page() freeing fallocated
+	 * pages when FALLOC_FL_KEEP_SIZE committed beyond i_size.
+	 */
+	undo_fallocend = info->fallocend;
+	if (info->fallocend < end)
+		info->fallocend = end;
+
+	for (index = start; index < end; ) {
 		struct page *page;
 
 		/*
@@ -2738,6 +2734,7 @@ static long shmem_fallocate(struct file *file, int mode, loff_t offset,
 		else
 			error = shmem_getpage(inode, index, &page, SGP_FALLOC);
 		if (error) {
+			info->fallocend = undo_fallocend;
 			/* Remove the !PageUptodate pages we added */
 			if (index > start) {
 				shmem_undo_range(inode,
@@ -2747,13 +2744,26 @@ static long shmem_fallocate(struct file *file, int mode, loff_t offset,
 			goto undone;
 		}
 
+		index++;
+		/*
+		 * Here is a more important optimization than it appears:
+		 * a second SGP_FALLOC on the same huge page will clear it,
+		 * making it PageUptodate and un-undoable if we fail later.
+		 */
+		if (PageTransCompound(page)) {
+			index = round_up(index, HPAGE_PMD_NR);
+			/* Beware 32-bit wraparound */
+			if (!index)
+				index--;
+		}
+
 		/*
 		 * Inform shmem_writepage() how far we have reached.
 		 * No need for lock or barrier: we have the page lock.
 		 */
-		shmem_falloc.next++;
 		if (!PageUptodate(page))
-			shmem_falloc.nr_falloced++;
+			shmem_falloc.nr_falloced += index - shmem_falloc.next;
+		shmem_falloc.next = index;
 
 		/*
 		 * If !PageUptodate, leave it that way so that freeable pages
@@ -3488,9 +3498,10 @@ static int shmem_reconfigure(struct fs_context *fc)
 	struct shmem_options *ctx = fc->fs_private;
 	struct shmem_sb_info *sbinfo = SHMEM_SB(fc->root->d_sb);
 	unsigned long inodes;
+	struct mempolicy *mpol = NULL;
 	const char *err;
 
-	spin_lock(&sbinfo->stat_lock);
+	raw_spin_lock(&sbinfo->stat_lock);
 	inodes = sbinfo->max_inodes - sbinfo->free_inodes;
 	if ((ctx->seen & SHMEM_SEEN_BLOCKS) && ctx->blocks) {
 		if (!sbinfo->max_blocks) {
@@ -3535,14 +3546,15 @@ static int shmem_reconfigure(struct fs_context *fc)
 	 * Preserve previous mempolicy unless mpol remount option was specified.
 	 */
 	if (ctx->mpol) {
-		mpol_put(sbinfo->mpol);
+		mpol = sbinfo->mpol;
 		sbinfo->mpol = ctx->mpol;	/* transfers initial ref */
 		ctx->mpol = NULL;
 	}
-	spin_unlock(&sbinfo->stat_lock);
+	raw_spin_unlock(&sbinfo->stat_lock);
+	mpol_put(mpol);
 	return 0;
 out:
-	spin_unlock(&sbinfo->stat_lock);
+	raw_spin_unlock(&sbinfo->stat_lock);
 	return invalfc(fc, "%s", err);
 }
 
@@ -3613,7 +3625,6 @@ static int shmem_fill_super(struct super_block *sb, struct fs_context *fc)
 	struct shmem_options *ctx = fc->fs_private;
 	struct inode *inode;
 	struct shmem_sb_info *sbinfo;
-	int err = -ENOMEM;
 
 	/* Round up to L1_CACHE_BYTES to resist false sharing */
 	sbinfo = kzalloc(max((int)sizeof(struct shmem_sb_info),
@@ -3659,7 +3670,7 @@ static int shmem_fill_super(struct super_block *sb, struct fs_context *fc)
 	sbinfo->mpol = ctx->mpol;
 	ctx->mpol = NULL;
 
-	spin_lock_init(&sbinfo->stat_lock);
+	raw_spin_lock_init(&sbinfo->stat_lock);
 	if (percpu_counter_init(&sbinfo->used_blocks, 0, GFP_KERNEL))
 		goto failed;
 	spin_lock_init(&sbinfo->shrinklist_lock);
@@ -3691,7 +3702,7 @@ static int shmem_fill_super(struct super_block *sb, struct fs_context *fc)
 
 failed:
 	shmem_put_super(sb);
-	return err;
+	return -ENOMEM;
 }
 
 static int shmem_get_tree(struct fs_context *fc)
@@ -3907,7 +3918,7 @@ int __init shmem_init(void)
 	if (has_transparent_hugepage() && shmem_huge > SHMEM_HUGE_DENY)
 		SHMEM_SB(shm_mnt->mnt_sb)->huge = shmem_huge;
 	else
-		shmem_huge = 0; /* just in case it was patched */
+		shmem_huge = SHMEM_HUGE_NEVER; /* just in case it was patched */
 #endif
 	return 0;
 
@@ -3976,42 +3987,6 @@ struct kobj_attribute shmem_enabled_attr =
 	__ATTR(shmem_enabled, 0644, shmem_enabled_show, shmem_enabled_store);
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE && CONFIG_SYSFS */
 
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-bool shmem_huge_enabled(struct vm_area_struct *vma)
-{
-	struct inode *inode = file_inode(vma->vm_file);
-	struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb);
-	loff_t i_size;
-	pgoff_t off;
-
-	if (!transhuge_vma_enabled(vma, vma->vm_flags))
-		return false;
-	if (shmem_huge == SHMEM_HUGE_FORCE)
-		return true;
-	if (shmem_huge == SHMEM_HUGE_DENY)
-		return false;
-	switch (sbinfo->huge) {
-		case SHMEM_HUGE_NEVER:
-			return false;
-		case SHMEM_HUGE_ALWAYS:
-			return true;
-		case SHMEM_HUGE_WITHIN_SIZE:
-			off = round_up(vma->vm_pgoff, HPAGE_PMD_NR);
-			i_size = round_up(i_size_read(inode), PAGE_SIZE);
-			if (i_size >= HPAGE_PMD_SIZE &&
-					i_size >> PAGE_SHIFT >= off)
-				return true;
-			fallthrough;
-		case SHMEM_HUGE_ADVISE:
-			/* TODO: implement fadvise() hints */
-			return (vma->vm_flags & VM_HUGEPAGE);
-		default:
-			VM_BUG_ON(1);
-			return false;
-	}
-}
-#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
-
 #else /* !CONFIG_SHMEM */
 
 /*
diff --git a/mm/sparse.c b/mm/sparse.c
index 6326cdf36c4f..120bc8ea5293 100644
--- a/mm/sparse.c
+++ b/mm/sparse.c
@@ -109,32 +109,6 @@ static inline int sparse_index_init(unsigned long section_nr, int nid)
 }
 #endif
 
-#ifdef CONFIG_SPARSEMEM_EXTREME
-unsigned long __section_nr(struct mem_section *ms)
-{
-	unsigned long root_nr;
-	struct mem_section *root = NULL;
-
-	for (root_nr = 0; root_nr < NR_SECTION_ROOTS; root_nr++) {
-		root = __nr_to_section(root_nr * SECTIONS_PER_ROOT);
-		if (!root)
-			continue;
-
-		if ((ms >= root) && (ms < (root + SECTIONS_PER_ROOT)))
-		     break;
-	}
-
-	VM_BUG_ON(!root);
-
-	return (root_nr * SECTIONS_PER_ROOT) + (ms - root);
-}
-#else
-unsigned long __section_nr(struct mem_section *ms)
-{
-	return (unsigned long)(ms - mem_section[0]);
-}
-#endif
-
 /*
  * During early boot, before section_mem_map is used for an actual
  * mem_map, we use section_mem_map to store the section's NUMA
@@ -143,7 +117,7 @@ unsigned long __section_nr(struct mem_section *ms)
  */
 static inline unsigned long sparse_encode_early_nid(int nid)
 {
-	return (nid << SECTION_NID_SHIFT);
+	return ((unsigned long)nid << SECTION_NID_SHIFT);
 }
 
 static inline int sparse_early_nid(struct mem_section *section)
@@ -187,10 +161,9 @@ void __meminit mminit_validate_memmodel_limits(unsigned long *start_pfn,
  * those loops early.
  */
 unsigned long __highest_present_section_nr;
-static void section_mark_present(struct mem_section *ms)
+static void __section_mark_present(struct mem_section *ms,
+		unsigned long section_nr)
 {
-	unsigned long section_nr = __section_nr(ms);
-
 	if (section_nr > __highest_present_section_nr)
 		__highest_present_section_nr = section_nr;
 
@@ -280,7 +253,7 @@ static void __init memory_present(int nid, unsigned long start, unsigned long en
 		if (!ms->section_mem_map) {
 			ms->section_mem_map = sparse_encode_early_nid(nid) |
 							SECTION_IS_ONLINE;
-			section_mark_present(ms);
+			__section_mark_present(ms, section);
 		}
 	}
 }
@@ -348,7 +321,8 @@ size_t mem_section_usage_size(void)
 static inline phys_addr_t pgdat_to_phys(struct pglist_data *pgdat)
 {
 #ifndef CONFIG_NUMA
-	return __pa_symbol(pgdat);
+	VM_BUG_ON(pgdat != &contig_page_data);
+	return __pa_symbol(&contig_page_data);
 #else
 	return __pa(pgdat);
 #endif
@@ -462,8 +436,7 @@ struct page __init *__populate_section_memmap(unsigned long pfn,
 	if (map)
 		return map;
 
-	map = memblock_alloc_try_nid_raw(size, size, addr,
-					  MEMBLOCK_ALLOC_ACCESSIBLE, nid);
+	map = memmap_alloc(size, size, addr, nid, false);
 	if (!map)
 		panic("%s: Failed to allocate %lu bytes align=0x%lx nid=%d from=%pa\n",
 		      __func__, size, PAGE_SIZE, nid, &addr);
@@ -490,8 +463,7 @@ static void __init sparse_buffer_init(unsigned long size, int nid)
 	 * and we want it to be properly aligned to the section size - this is
 	 * especially the case for VMEMMAP which maps memmap to PMDs
 	 */
-	sparsemap_buf = memblock_alloc_exact_nid_raw(size, section_map_size(),
-					addr, MEMBLOCK_ALLOC_ACCESSIBLE, nid);
+	sparsemap_buf = memmap_alloc(size, section_map_size(), addr, nid, true);
 	sparsemap_buf_end = sparsemap_buf + size;
 }
 
@@ -934,7 +906,7 @@ int __meminit sparse_add_section(int nid, unsigned long start_pfn,
 
 	ms = __nr_to_section(section_nr);
 	set_section_nid(section_nr, nid);
-	section_mark_present(ms);
+	__section_mark_present(ms, section_nr);
 
 	/* Align memmap to section boundary in the subsection case */
 	if (section_nr_to_pfn(section_nr) != start_pfn)
diff --git a/mm/swap.c b/mm/swap.c
index 19600430e536..897200d27dd0 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -179,28 +179,6 @@ int get_kernel_pages(const struct kvec *kiov, int nr_segs, int write,
 }
 EXPORT_SYMBOL_GPL(get_kernel_pages);
 
-/*
- * get_kernel_page() - pin a kernel page in memory
- * @start:	starting kernel address
- * @write:	pinning for read/write, currently ignored
- * @pages:	array that receives pointer to the page pinned.
- *		Must be at least nr_segs long.
- *
- * Returns 1 if page is pinned. If the page was not pinned, returns
- * -errno. The page returned must be released with a put_page() call
- * when it is finished with.
- */
-int get_kernel_page(unsigned long start, int write, struct page **pages)
-{
-	const struct kvec kiov = {
-		.iov_base = (void *)start,
-		.iov_len = PAGE_SIZE
-	};
-
-	return get_kernel_pages(&kiov, 1, write, pages);
-}
-EXPORT_SYMBOL_GPL(get_kernel_page);
-
 static void pagevec_lru_move_fn(struct pagevec *pvec,
 	void (*move_fn)(struct page *page, struct lruvec *lruvec))
 {
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 1e07d1c776f2..22d10f713848 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -3130,6 +3130,7 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
 	struct filename *name;
 	struct file *swap_file = NULL;
 	struct address_space *mapping;
+	struct dentry *dentry;
 	int prio;
 	int error;
 	union swap_header *swap_header;
@@ -3173,6 +3174,7 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
 
 	p->swap_file = swap_file;
 	mapping = swap_file->f_mapping;
+	dentry = swap_file->f_path.dentry;
 	inode = mapping->host;
 
 	error = claim_swapfile(p, inode);
@@ -3180,6 +3182,10 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
 		goto bad_swap;
 
 	inode_lock(inode);
+	if (d_unlinked(dentry) || cant_mount(dentry)) {
+		error = -ENOENT;
+		goto bad_swap_unlock_inode;
+	}
 	if (IS_SWAPFILE(inode)) {
 		error = -EBUSY;
 		goto bad_swap_unlock_inode;
@@ -3773,7 +3779,7 @@ static void free_swap_count_continuations(struct swap_info_struct *si)
 }
 
 #if defined(CONFIG_MEMCG) && defined(CONFIG_BLK_CGROUP)
-void cgroup_throttle_swaprate(struct page *page, gfp_t gfp_mask)
+void __cgroup_throttle_swaprate(struct page *page, gfp_t gfp_mask)
 {
 	struct swap_info_struct *si, *next;
 	int nid = page_to_nid(page);
diff --git a/mm/truncate.c b/mm/truncate.c
index 44ad5e515140..714eaf19821d 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -484,8 +484,9 @@ static unsigned long __invalidate_mapping_pages(struct address_space *mapping,
 			index = indices[i];
 
 			if (xa_is_value(page)) {
-				invalidate_exceptional_entry(mapping, index,
-							     page);
+				count += invalidate_exceptional_entry(mapping,
+								      index,
+								      page);
 				continue;
 			}
 			index += thp_nr_pages(page) - 1;
@@ -513,19 +514,18 @@ static unsigned long __invalidate_mapping_pages(struct address_space *mapping,
 }
 
 /**
- * invalidate_mapping_pages - Invalidate all the unlocked pages of one inode
- * @mapping: the address_space which holds the pages to invalidate
+ * invalidate_mapping_pages - Invalidate all clean, unlocked cache of one inode
+ * @mapping: the address_space which holds the cache to invalidate
  * @start: the offset 'from' which to invalidate
  * @end: the offset 'to' which to invalidate (inclusive)
  *
- * This function only removes the unlocked pages, if you want to
- * remove all the pages of one inode, you must call truncate_inode_pages.
+ * This function removes pages that are clean, unmapped and unlocked,
+ * as well as shadow entries. It will not block on IO activity.
  *
- * invalidate_mapping_pages() will not block on IO activity. It will not
- * invalidate pages which are dirty, locked, under writeback or mapped into
- * pagetables.
+ * If you want to remove all the pages of one inode, regardless of
+ * their use and writeback state, use truncate_inode_pages().
  *
- * Return: the number of the pages that were invalidated
+ * Return: the number of the cache entries that were invalidated
  */
 unsigned long invalidate_mapping_pages(struct address_space *mapping,
 		pgoff_t start, pgoff_t end)
@@ -561,21 +561,19 @@ void invalidate_mapping_pagevec(struct address_space *mapping,
 static int
 invalidate_complete_page2(struct address_space *mapping, struct page *page)
 {
-	unsigned long flags;
-
 	if (page->mapping != mapping)
 		return 0;
 
 	if (page_has_private(page) && !try_to_release_page(page, GFP_KERNEL))
 		return 0;
 
-	xa_lock_irqsave(&mapping->i_pages, flags);
+	xa_lock_irq(&mapping->i_pages);
 	if (PageDirty(page))
 		goto failed;
 
 	BUG_ON(page_has_private(page));
 	__delete_from_page_cache(page, NULL);
-	xa_unlock_irqrestore(&mapping->i_pages, flags);
+	xa_unlock_irq(&mapping->i_pages);
 
 	if (mapping->a_ops->freepage)
 		mapping->a_ops->freepage(page);
@@ -583,7 +581,7 @@ invalidate_complete_page2(struct address_space *mapping, struct page *page)
 	put_page(page);	/* pagecache ref */
 	return 1;
 failed:
-	xa_unlock_irqrestore(&mapping->i_pages, flags);
+	xa_unlock_irq(&mapping->i_pages);
 	return 0;
 }
 
diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
index 0e2132834bc7..7a9008415534 100644
--- a/mm/userfaultfd.c
+++ b/mm/userfaultfd.c
@@ -483,7 +483,7 @@ static __always_inline ssize_t __mcopy_atomic(struct mm_struct *dst_mm,
 					      unsigned long src_start,
 					      unsigned long len,
 					      enum mcopy_atomic_mode mcopy_mode,
-					      bool *mmap_changing,
+					      atomic_t *mmap_changing,
 					      __u64 mode)
 {
 	struct vm_area_struct *dst_vma;
@@ -517,7 +517,7 @@ retry:
 	 * request the user to retry later
 	 */
 	err = -EAGAIN;
-	if (mmap_changing && READ_ONCE(*mmap_changing))
+	if (mmap_changing && atomic_read(mmap_changing))
 		goto out_unlock;
 
 	/*
@@ -650,28 +650,29 @@ out:
 
 ssize_t mcopy_atomic(struct mm_struct *dst_mm, unsigned long dst_start,
 		     unsigned long src_start, unsigned long len,
-		     bool *mmap_changing, __u64 mode)
+		     atomic_t *mmap_changing, __u64 mode)
 {
 	return __mcopy_atomic(dst_mm, dst_start, src_start, len,
 			      MCOPY_ATOMIC_NORMAL, mmap_changing, mode);
 }
 
 ssize_t mfill_zeropage(struct mm_struct *dst_mm, unsigned long start,
-		       unsigned long len, bool *mmap_changing)
+		       unsigned long len, atomic_t *mmap_changing)
 {
 	return __mcopy_atomic(dst_mm, start, 0, len, MCOPY_ATOMIC_ZEROPAGE,
 			      mmap_changing, 0);
 }
 
 ssize_t mcopy_continue(struct mm_struct *dst_mm, unsigned long start,
-		       unsigned long len, bool *mmap_changing)
+		       unsigned long len, atomic_t *mmap_changing)
 {
 	return __mcopy_atomic(dst_mm, start, 0, len, MCOPY_ATOMIC_CONTINUE,
 			      mmap_changing, 0);
 }
 
 int mwriteprotect_range(struct mm_struct *dst_mm, unsigned long start,
-			unsigned long len, bool enable_wp, bool *mmap_changing)
+			unsigned long len, bool enable_wp,
+			atomic_t *mmap_changing)
 {
 	struct vm_area_struct *dst_vma;
 	pgprot_t newprot;
@@ -694,7 +695,7 @@ int mwriteprotect_range(struct mm_struct *dst_mm, unsigned long start,
 	 * request the user to retry later
 	 */
 	err = -EAGAIN;
-	if (mmap_changing && READ_ONCE(*mmap_changing))
+	if (mmap_changing && atomic_read(mmap_changing))
 		goto out_unlock;
 
 	err = -ENOENT;
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index d5cd52805149..3824dc16ce1c 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -787,6 +787,28 @@ unsigned long vmalloc_nr_pages(void)
 	return atomic_long_read(&nr_vmalloc_pages);
 }
 
+static struct vmap_area *find_vmap_area_exceed_addr(unsigned long addr)
+{
+	struct vmap_area *va = NULL;
+	struct rb_node *n = vmap_area_root.rb_node;
+
+	while (n) {
+		struct vmap_area *tmp;
+
+		tmp = rb_entry(n, struct vmap_area, rb_node);
+		if (tmp->va_end > addr) {
+			va = tmp;
+			if (tmp->va_start <= addr)
+				break;
+
+			n = n->rb_left;
+		} else
+			n = n->rb_right;
+	}
+
+	return va;
+}
+
 static struct vmap_area *__find_vmap_area(unsigned long addr)
 {
 	struct rb_node *n = vmap_area_root.rb_node;
@@ -1479,6 +1501,7 @@ static struct vmap_area *alloc_vmap_area(unsigned long size,
 				int node, gfp_t gfp_mask)
 {
 	struct vmap_area *va;
+	unsigned long freed;
 	unsigned long addr;
 	int purged = 0;
 	int ret;
@@ -1542,13 +1565,12 @@ overflow:
 		goto retry;
 	}
 
-	if (gfpflags_allow_blocking(gfp_mask)) {
-		unsigned long freed = 0;
-		blocking_notifier_call_chain(&vmap_notify_list, 0, &freed);
-		if (freed > 0) {
-			purged = 0;
-			goto retry;
-		}
+	freed = 0;
+	blocking_notifier_call_chain(&vmap_notify_list, 0, &freed);
+
+	if (freed > 0) {
+		purged = 0;
+		goto retry;
 	}
 
 	if (!(gfp_mask & __GFP_NOWARN) && printk_ratelimit())
@@ -2779,7 +2801,7 @@ EXPORT_SYMBOL_GPL(vmap_pfn);
 
 static inline unsigned int
 vm_area_alloc_pages(gfp_t gfp, int nid,
-		unsigned int order, unsigned long nr_pages, struct page **pages)
+		unsigned int order, unsigned int nr_pages, struct page **pages)
 {
 	unsigned int nr_allocated = 0;
 
@@ -2789,10 +2811,32 @@ vm_area_alloc_pages(gfp_t gfp, int nid,
 	 * to fails, fallback to a single page allocator that is
 	 * more permissive.
 	 */
-	if (!order)
-		nr_allocated = alloc_pages_bulk_array_node(
-			gfp, nid, nr_pages, pages);
-	else
+	if (!order) {
+		while (nr_allocated < nr_pages) {
+			unsigned int nr, nr_pages_request;
+
+			/*
+			 * A maximum allowed request is hard-coded and is 100
+			 * pages per call. That is done in order to prevent a
+			 * long preemption off scenario in the bulk-allocator
+			 * so the range is [1:100].
+			 */
+			nr_pages_request = min(100U, nr_pages - nr_allocated);
+
+			nr = alloc_pages_bulk_array_node(gfp, nid,
+				nr_pages_request, pages + nr_allocated);
+
+			nr_allocated += nr;
+			cond_resched();
+
+			/*
+			 * If zero or pages were obtained partly,
+			 * fallback to a single page allocator.
+			 */
+			if (nr != nr_pages_request)
+				break;
+		}
+	} else
 		/*
 		 * Compound pages required for remap_vmalloc_page if
 		 * high-order pages.
@@ -2816,9 +2860,7 @@ vm_area_alloc_pages(gfp_t gfp, int nid,
 		for (i = 0; i < (1U << order); i++)
 			pages[nr_allocated + i] = page + i;
 
-		if (gfpflags_allow_blocking(gfp))
-			cond_resched();
-
+		cond_resched();
 		nr_allocated += 1U << order;
 	}
 
@@ -3267,9 +3309,14 @@ long vread(char *buf, char *addr, unsigned long count)
 		count = -(unsigned long) addr;
 
 	spin_lock(&vmap_area_lock);
-	va = __find_vmap_area((unsigned long)addr);
+	va = find_vmap_area_exceed_addr((unsigned long)addr);
 	if (!va)
 		goto finished;
+
+	/* no intersects with alive vmap_area */
+	if ((unsigned long)addr + count <= va->va_start)
+		goto finished;
+
 	list_for_each_entry_from(va, &vmap_area_list, list) {
 		if (!count)
 			break;
diff --git a/mm/vmpressure.c b/mm/vmpressure.c
index d69019fc3789..76518e4166dc 100644
--- a/mm/vmpressure.c
+++ b/mm/vmpressure.c
@@ -74,8 +74,7 @@ static struct vmpressure *work_to_vmpressure(struct work_struct *work)
 
 static struct vmpressure *vmpressure_parent(struct vmpressure *vmpr)
 {
-	struct cgroup_subsys_state *css = vmpressure_to_css(vmpr);
-	struct mem_cgroup *memcg = mem_cgroup_from_css(css);
+	struct mem_cgroup *memcg = vmpressure_to_memcg(vmpr);
 
 	memcg = parent_mem_cgroup(memcg);
 	if (!memcg)
@@ -240,7 +239,12 @@ static void vmpressure_work_fn(struct work_struct *work)
 void vmpressure(gfp_t gfp, struct mem_cgroup *memcg, bool tree,
 		unsigned long scanned, unsigned long reclaimed)
 {
-	struct vmpressure *vmpr = memcg_to_vmpressure(memcg);
+	struct vmpressure *vmpr;
+
+	if (mem_cgroup_disabled())
+		return;
+
+	vmpr = memcg_to_vmpressure(memcg);
 
 	/*
 	 * Here we only want to account pressure that userland is able to
diff --git a/mm/vmscan.c b/mm/vmscan.c
index eeae2f6bc532..740d03e6dae2 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -41,6 +41,7 @@
 #include <linux/kthread.h>
 #include <linux/freezer.h>
 #include <linux/memcontrol.h>
+#include <linux/migrate.h>
 #include <linux/delayacct.h>
 #include <linux/sysctl.h>
 #include <linux/oom.h>
@@ -121,6 +122,9 @@ struct scan_control {
 	/* The file pages on the current node are dangerously low */
 	unsigned int file_is_tiny:1;
 
+	/* Always discard instead of demoting to lower tier memory */
+	unsigned int no_demotion:1;
+
 	/* Allocation order */
 	s8 order;
 
@@ -518,6 +522,48 @@ static long add_nr_deferred(long nr, struct shrinker *shrinker,
 	return atomic_long_add_return(nr, &shrinker->nr_deferred[nid]);
 }
 
+static bool can_demote(int nid, struct scan_control *sc)
+{
+	if (!numa_demotion_enabled)
+		return false;
+	if (sc) {
+		if (sc->no_demotion)
+			return false;
+		/* It is pointless to do demotion in memcg reclaim */
+		if (cgroup_reclaim(sc))
+			return false;
+	}
+	if (next_demotion_node(nid) == NUMA_NO_NODE)
+		return false;
+
+	return true;
+}
+
+static inline bool can_reclaim_anon_pages(struct mem_cgroup *memcg,
+					  int nid,
+					  struct scan_control *sc)
+{
+	if (memcg == NULL) {
+		/*
+		 * For non-memcg reclaim, is there
+		 * space in any swap device?
+		 */
+		if (get_nr_swap_pages() > 0)
+			return true;
+	} else {
+		/* Is the memcg below its swap limit? */
+		if (mem_cgroup_get_nr_swap_pages(memcg) > 0)
+			return true;
+	}
+
+	/*
+	 * The page can not be swapped.
+	 *
+	 * Can it be reclaimed from this node via demotion?
+	 */
+	return can_demote(nid, sc);
+}
+
 /*
  * This misses isolated pages which are not accounted for to save counters.
  * As the data only determines if reclaim or compaction continues, it is
@@ -529,7 +575,7 @@ unsigned long zone_reclaimable_pages(struct zone *zone)
 
 	nr = zone_page_state_snapshot(zone, NR_ZONE_INACTIVE_FILE) +
 		zone_page_state_snapshot(zone, NR_ZONE_ACTIVE_FILE);
-	if (get_nr_swap_pages() > 0)
+	if (can_reclaim_anon_pages(NULL, zone_to_nid(zone), NULL))
 		nr += zone_page_state_snapshot(zone, NR_ZONE_INACTIVE_ANON) +
 			zone_page_state_snapshot(zone, NR_ZONE_ACTIVE_ANON);
 
@@ -893,6 +939,7 @@ out:
 void drop_slab_node(int nid)
 {
 	unsigned long freed;
+	int shift = 0;
 
 	do {
 		struct mem_cgroup *memcg = NULL;
@@ -905,7 +952,7 @@ void drop_slab_node(int nid)
 		do {
 			freed += shrink_slab(GFP_KERNEL, nid, memcg, 0);
 		} while ((memcg = mem_cgroup_iter(NULL, memcg, NULL)) != NULL);
-	} while (freed > 10);
+	} while ((freed >> shift++) > 1);
 }
 
 void drop_slab(void)
@@ -1052,14 +1099,13 @@ static pageout_t pageout(struct page *page, struct address_space *mapping)
 static int __remove_mapping(struct address_space *mapping, struct page *page,
 			    bool reclaimed, struct mem_cgroup *target_memcg)
 {
-	unsigned long flags;
 	int refcount;
 	void *shadow = NULL;
 
 	BUG_ON(!PageLocked(page));
 	BUG_ON(mapping != page_mapping(page));
 
-	xa_lock_irqsave(&mapping->i_pages, flags);
+	xa_lock_irq(&mapping->i_pages);
 	/*
 	 * The non racy check for a busy page.
 	 *
@@ -1100,7 +1146,7 @@ static int __remove_mapping(struct address_space *mapping, struct page *page,
 		if (reclaimed && !mapping_exiting(mapping))
 			shadow = workingset_eviction(page, target_memcg);
 		__delete_from_swap_cache(page, swap, shadow);
-		xa_unlock_irqrestore(&mapping->i_pages, flags);
+		xa_unlock_irq(&mapping->i_pages);
 		put_swap_page(page, swap);
 	} else {
 		void (*freepage)(struct page *);
@@ -1126,7 +1172,7 @@ static int __remove_mapping(struct address_space *mapping, struct page *page,
 		    !mapping_exiting(mapping) && !dax_mapping(mapping))
 			shadow = workingset_eviction(page, target_memcg);
 		__delete_from_page_cache(page, shadow);
-		xa_unlock_irqrestore(&mapping->i_pages, flags);
+		xa_unlock_irq(&mapping->i_pages);
 
 		if (freepage != NULL)
 			freepage(page);
@@ -1135,7 +1181,7 @@ static int __remove_mapping(struct address_space *mapping, struct page *page,
 	return 1;
 
 cannot_free:
-	xa_unlock_irqrestore(&mapping->i_pages, flags);
+	xa_unlock_irq(&mapping->i_pages);
 	return 0;
 }
 
@@ -1264,6 +1310,54 @@ static void page_check_dirty_writeback(struct page *page,
 		mapping->a_ops->is_dirty_writeback(page, dirty, writeback);
 }
 
+static struct page *alloc_demote_page(struct page *page, unsigned long node)
+{
+	struct migration_target_control mtc = {
+		/*
+		 * Allocate from 'node', or fail quickly and quietly.
+		 * When this happens, 'page' will likely just be discarded
+		 * instead of migrated.
+		 */
+		.gfp_mask = (GFP_HIGHUSER_MOVABLE & ~__GFP_RECLAIM) |
+			    __GFP_THISNODE  | __GFP_NOWARN |
+			    __GFP_NOMEMALLOC | GFP_NOWAIT,
+		.nid = node
+	};
+
+	return alloc_migration_target(page, (unsigned long)&mtc);
+}
+
+/*
+ * Take pages on @demote_list and attempt to demote them to
+ * another node.  Pages which are not demoted are left on
+ * @demote_pages.
+ */
+static unsigned int demote_page_list(struct list_head *demote_pages,
+				     struct pglist_data *pgdat)
+{
+	int target_nid = next_demotion_node(pgdat->node_id);
+	unsigned int nr_succeeded;
+	int err;
+
+	if (list_empty(demote_pages))
+		return 0;
+
+	if (target_nid == NUMA_NO_NODE)
+		return 0;
+
+	/* Demotion ignores all cpuset and mempolicy settings */
+	err = migrate_pages(demote_pages, alloc_demote_page, NULL,
+			    target_nid, MIGRATE_ASYNC, MR_DEMOTION,
+			    &nr_succeeded);
+
+	if (current_is_kswapd())
+		__count_vm_events(PGDEMOTE_KSWAPD, nr_succeeded);
+	else
+		__count_vm_events(PGDEMOTE_DIRECT, nr_succeeded);
+
+	return nr_succeeded;
+}
+
 /*
  * shrink_page_list() returns the number of reclaimed pages
  */
@@ -1275,12 +1369,16 @@ static unsigned int shrink_page_list(struct list_head *page_list,
 {
 	LIST_HEAD(ret_pages);
 	LIST_HEAD(free_pages);
+	LIST_HEAD(demote_pages);
 	unsigned int nr_reclaimed = 0;
 	unsigned int pgactivate = 0;
+	bool do_demote_pass;
 
 	memset(stat, 0, sizeof(*stat));
 	cond_resched();
+	do_demote_pass = can_demote(pgdat->node_id, sc);
 
+retry:
 	while (!list_empty(page_list)) {
 		struct address_space *mapping;
 		struct page *page;
@@ -1430,6 +1528,17 @@ static unsigned int shrink_page_list(struct list_head *page_list,
 		}
 
 		/*
+		 * Before reclaiming the page, try to relocate
+		 * its contents to another node.
+		 */
+		if (do_demote_pass &&
+		    (thp_migration_supported() || !PageTransHuge(page))) {
+			list_add(&page->lru, &demote_pages);
+			unlock_page(page);
+			continue;
+		}
+
+		/*
 		 * Anonymous process memory has backing store?
 		 * Try to allocate it some swap space here.
 		 * Lazyfree page could be freed directly
@@ -1624,11 +1733,14 @@ static unsigned int shrink_page_list(struct list_head *page_list,
 			/* follow __remove_mapping for reference */
 			if (!page_ref_freeze(page, 1))
 				goto keep_locked;
-			if (PageDirty(page)) {
-				page_ref_unfreeze(page, 1);
-				goto keep_locked;
-			}
-
+			/*
+			 * The page has only one reference left, which is
+			 * from the isolation. After the caller puts the
+			 * page back on lru and drops the reference, the
+			 * page will be freed anyway. It doesn't matter
+			 * which lru it goes. So we don't bother checking
+			 * PageDirty here.
+			 */
 			count_vm_event(PGLAZYFREED);
 			count_memcg_page_event(page, PGLAZYFREED);
 		} else if (!mapping || !__remove_mapping(mapping, page, true,
@@ -1680,6 +1792,17 @@ keep:
 		list_add(&page->lru, &ret_pages);
 		VM_BUG_ON_PAGE(PageLRU(page) || PageUnevictable(page), page);
 	}
+	/* 'page_list' is always empty here */
+
+	/* Migrate pages selected for demotion */
+	nr_reclaimed += demote_page_list(&demote_pages, pgdat);
+	/* Pages that could not be demoted are still in @demote_pages */
+	if (!list_empty(&demote_pages)) {
+		/* Pages which failed to demoted go back on @page_list for retry: */
+		list_splice_init(&demote_pages, page_list);
+		do_demote_pass = false;
+		goto retry;
+	}
 
 	pgactivate = stat->nr_activate[0] + stat->nr_activate[1];
 
@@ -1698,7 +1821,6 @@ unsigned int reclaim_clean_pages_from_list(struct zone *zone,
 {
 	struct scan_control sc = {
 		.gfp_mask = GFP_KERNEL,
-		.priority = DEF_PRIORITY,
 		.may_unmap = 1,
 	};
 	struct reclaim_stat stat;
@@ -2323,10 +2445,10 @@ unsigned long reclaim_pages(struct list_head *page_list)
 	unsigned int noreclaim_flag;
 	struct scan_control sc = {
 		.gfp_mask = GFP_KERNEL,
-		.priority = DEF_PRIORITY,
 		.may_writepage = 1,
 		.may_unmap = 1,
 		.may_swap = 1,
+		.no_demotion = 1,
 	};
 
 	noreclaim_flag = memalloc_noreclaim_save();
@@ -2452,6 +2574,7 @@ enum scan_balance {
 static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc,
 			   unsigned long *nr)
 {
+	struct pglist_data *pgdat = lruvec_pgdat(lruvec);
 	struct mem_cgroup *memcg = lruvec_memcg(lruvec);
 	unsigned long anon_cost, file_cost, total_cost;
 	int swappiness = mem_cgroup_swappiness(memcg);
@@ -2462,7 +2585,7 @@ static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc,
 	enum lru_list lru;
 
 	/* If we have no swap space, do not bother scanning anon pages. */
-	if (!sc->may_swap || mem_cgroup_get_nr_swap_pages(memcg) <= 0) {
+	if (!sc->may_swap || !can_reclaim_anon_pages(memcg, pgdat->node_id, sc)) {
 		scan_balance = SCAN_FILE;
 		goto out;
 	}
@@ -2645,6 +2768,21 @@ out:
 	}
 }
 
+/*
+ * Anonymous LRU management is a waste if there is
+ * ultimately no way to reclaim the memory.
+ */
+static bool can_age_anon_pages(struct pglist_data *pgdat,
+			       struct scan_control *sc)
+{
+	/* Aging the anon LRU is valuable if swap is present: */
+	if (total_swap_pages > 0)
+		return true;
+
+	/* Also valuable if anon pages can be demoted: */
+	return can_demote(pgdat->node_id, sc);
+}
+
 static void shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc)
 {
 	unsigned long nr[NR_LRU_LISTS];
@@ -2754,7 +2892,8 @@ static void shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc)
 	 * Even if we did not try to evict anon pages at all, we want to
 	 * rebalance the anon lru active/inactive ratio.
 	 */
-	if (total_swap_pages && inactive_is_low(lruvec, LRU_INACTIVE_ANON))
+	if (can_age_anon_pages(lruvec_pgdat(lruvec), sc) &&
+	    inactive_is_low(lruvec, LRU_INACTIVE_ANON))
 		shrink_active_list(SWAP_CLUSTER_MAX, lruvec,
 				   sc, LRU_ACTIVE_ANON);
 }
@@ -2824,7 +2963,7 @@ static inline bool should_continue_reclaim(struct pglist_data *pgdat,
 	 */
 	pages_for_compaction = compact_gap(sc->order);
 	inactive_lru_pages = node_page_state(pgdat, NR_INACTIVE_FILE);
-	if (get_nr_swap_pages() > 0)
+	if (can_reclaim_anon_pages(NULL, pgdat->node_id, sc))
 		inactive_lru_pages += node_page_state(pgdat, NR_INACTIVE_ANON);
 
 	return inactive_lru_pages > pages_for_compaction;
@@ -2898,6 +3037,12 @@ static void shrink_node(pg_data_t *pgdat, struct scan_control *sc)
 	target_lruvec = mem_cgroup_lruvec(sc->target_mem_cgroup, pgdat);
 
 again:
+	/*
+	 * Flush the memory cgroup stats, so that we read accurate per-memcg
+	 * lruvec stats for heuristics.
+	 */
+	mem_cgroup_flush_stats();
+
 	memset(&sc->nr, 0, sizeof(sc->nr));
 
 	nr_reclaimed = sc->nr_reclaimed;
@@ -3434,18 +3579,14 @@ static bool throttle_direct_reclaim(gfp_t gfp_mask, struct zonelist *zonelist,
 	 * blocked waiting on the same lock. Instead, throttle for up to a
 	 * second before continuing.
 	 */
-	if (!(gfp_mask & __GFP_FS)) {
+	if (!(gfp_mask & __GFP_FS))
 		wait_event_interruptible_timeout(pgdat->pfmemalloc_wait,
 			allow_direct_reclaim(pgdat), HZ);
+	else
+		/* Throttle until kswapd wakes the process */
+		wait_event_killable(zone->zone_pgdat->pfmemalloc_wait,
+			allow_direct_reclaim(pgdat));
 
-		goto check_pending;
-	}
-
-	/* Throttle until kswapd wakes the process */
-	wait_event_killable(zone->zone_pgdat->pfmemalloc_wait,
-		allow_direct_reclaim(pgdat));
-
-check_pending:
 	if (fatal_signal_pending(current))
 		return true;
 
@@ -3583,7 +3724,7 @@ static void age_active_anon(struct pglist_data *pgdat,
 	struct mem_cgroup *memcg;
 	struct lruvec *lruvec;
 
-	if (!total_swap_pages)
+	if (!can_age_anon_pages(pgdat, sc))
 		return;
 
 	lruvec = mem_cgroup_lruvec(NULL, pgdat);
@@ -3812,7 +3953,7 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int highest_zoneidx)
 
 	set_task_reclaim_state(current, &sc.reclaim_state);
 	psi_memstall_enter(&pflags);
-	__fs_reclaim_acquire();
+	__fs_reclaim_acquire(_THIS_IP_);
 
 	count_vm_event(PAGEOUTRUN);
 
@@ -3938,9 +4079,9 @@ restart:
 			wake_up_all(&pgdat->pfmemalloc_wait);
 
 		/* Check if kswapd should be suspending */
-		__fs_reclaim_release();
+		__fs_reclaim_release(_THIS_IP_);
 		ret = try_to_freeze();
-		__fs_reclaim_acquire();
+		__fs_reclaim_acquire(_THIS_IP_);
 		if (ret || kthread_should_stop())
 			break;
 
@@ -3992,7 +4133,7 @@ out:
 	}
 
 	snapshot_refaults(NULL, pgdat);
-	__fs_reclaim_release();
+	__fs_reclaim_release(_THIS_IP_);
 	psi_memstall_leave(&pflags);
 	set_task_reclaim_state(current, NULL);
 
@@ -4290,23 +4431,20 @@ unsigned long shrink_all_memory(unsigned long nr_to_reclaim)
  * This kswapd start function will be called by init and node-hot-add.
  * On node-hot-add, kswapd will moved to proper cpus if cpus are hot-added.
  */
-int kswapd_run(int nid)
+void kswapd_run(int nid)
 {
 	pg_data_t *pgdat = NODE_DATA(nid);
-	int ret = 0;
 
 	if (pgdat->kswapd)
-		return 0;
+		return;
 
 	pgdat->kswapd = kthread_run(kswapd, pgdat, "kswapd%d", nid);
 	if (IS_ERR(pgdat->kswapd)) {
 		/* failure at boot is fatal */
 		BUG_ON(system_state < SYSTEM_RUNNING);
 		pr_err("Failed to start kswapd on node %d\n", nid);
-		ret = PTR_ERR(pgdat->kswapd);
 		pgdat->kswapd = NULL;
 	}
-	return ret;
 }
 
 /*
diff --git a/mm/vmstat.c b/mm/vmstat.c
index a7ed56ac4c0b..0885a34197b7 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -204,7 +204,7 @@ int calculate_normal_threshold(struct zone *zone)
 	 *
 	 * Some sample thresholds:
 	 *
-	 * Threshold	Processors	(fls)	Zonesize	fls(mem+1)
+	 * Threshold	Processors	(fls)	Zonesize	fls(mem)+1
 	 * ------------------------------------------------------------------
 	 * 8		1		1	0.9-1 GB	4
 	 * 16		2		2	0.9-1 GB	4
@@ -1217,6 +1217,8 @@ const char * const vmstat_text[] = {
 	"pgreuse",
 	"pgsteal_kswapd",
 	"pgsteal_direct",
+	"pgdemote_kswapd",
+	"pgdemote_direct",
 	"pgscan_kswapd",
 	"pgscan_direct",
 	"pgscan_direct_throttle",
@@ -1452,7 +1454,7 @@ static void pagetypeinfo_showfree_print(struct seq_file *m,
 }
 
 /* Print out the free pages at each order for each migatetype */
-static int pagetypeinfo_showfree(struct seq_file *m, void *arg)
+static void pagetypeinfo_showfree(struct seq_file *m, void *arg)
 {
 	int order;
 	pg_data_t *pgdat = (pg_data_t *)arg;
@@ -1464,8 +1466,6 @@ static int pagetypeinfo_showfree(struct seq_file *m, void *arg)
 	seq_putc(m, '\n');
 
 	walk_zones_in_node(m, pgdat, true, false, pagetypeinfo_showfree_print);
-
-	return 0;
 }
 
 static void pagetypeinfo_showblockcount_print(struct seq_file *m,
@@ -1501,7 +1501,7 @@ static void pagetypeinfo_showblockcount_print(struct seq_file *m,
 }
 
 /* Print out the number of pageblocks for each migratetype */
-static int pagetypeinfo_showblockcount(struct seq_file *m, void *arg)
+static void pagetypeinfo_showblockcount(struct seq_file *m, void *arg)
 {
 	int mtype;
 	pg_data_t *pgdat = (pg_data_t *)arg;
@@ -1512,8 +1512,6 @@ static int pagetypeinfo_showblockcount(struct seq_file *m, void *arg)
 	seq_putc(m, '\n');
 	walk_zones_in_node(m, pgdat, true, false,
 		pagetypeinfo_showblockcount_print);
-
-	return 0;
 }
 
 /*
@@ -1874,11 +1872,6 @@ static void vmstat_update(struct work_struct *w)
 }
 
 /*
- * Switch off vmstat processing and then fold all the remaining differentials
- * until the diffs stay at zero. The function is used by NOHZ and can only be
- * invoked when tick processing is not active.
- */
-/*
  * Check if the diffs for a certain cpu indicate that
  * an update is needed.
  */
@@ -1894,17 +1887,15 @@ static bool need_update(int cpu)
 		/*
 		 * The fast way of checking if there are any vmstat diffs.
 		 */
-		if (memchr_inv(pzstats->vm_stat_diff, 0, NR_VM_ZONE_STAT_ITEMS *
-			       sizeof(pzstats->vm_stat_diff[0])))
+		if (memchr_inv(pzstats->vm_stat_diff, 0, sizeof(pzstats->vm_stat_diff)))
 			return true;
 
 		if (last_pgdat == zone->zone_pgdat)
 			continue;
 		last_pgdat = zone->zone_pgdat;
 		n = per_cpu_ptr(zone->zone_pgdat->per_cpu_nodestats, cpu);
-		if (memchr_inv(n->vm_node_stat_diff, 0, NR_VM_NODE_STAT_ITEMS *
-			       sizeof(n->vm_node_stat_diff[0])))
-		    return true;
+		if (memchr_inv(n->vm_node_stat_diff, 0, sizeof(n->vm_node_stat_diff)))
+			return true;
 	}
 	return false;
 }