Merge branch 'akpm' (patches from Andrew)

Merge updates from Andrew Morton:

 - A few misc subsystems: kthread, scripts, ntfs, ocfs2, block, and vfs

 - Most the MM patches which precede the patches in Willy's tree: kasan,
   pagecache, gup, swap, shmem, memcg, selftests, pagemap, mremap,
   sparsemem, vmalloc, pagealloc, memory-failure, mlock, hugetlb,
   userfaultfd, vmscan, compaction, mempolicy, oom-kill, migration, thp,
   cma, autonuma, psi, ksm, page-poison, madvise, memory-hotplug, rmap,
   zswap, uaccess, ioremap, highmem, cleanups, kfence, hmm, and damon.

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (227 commits)
  mm/damon/sysfs: remove repeat container_of() in damon_sysfs_kdamond_release()
  Docs/ABI/testing: add DAMON sysfs interface ABI document
  Docs/admin-guide/mm/damon/usage: document DAMON sysfs interface
  selftests/damon: add a test for DAMON sysfs interface
  mm/damon/sysfs: support DAMOS stats
  mm/damon/sysfs: support DAMOS watermarks
  mm/damon/sysfs: support schemes prioritization
  mm/damon/sysfs: support DAMOS quotas
  mm/damon/sysfs: support DAMON-based Operation Schemes
  mm/damon/sysfs: support the physical address space monitoring
  mm/damon/sysfs: link DAMON for virtual address spaces monitoring
  mm/damon: implement a minimal stub for sysfs-based DAMON interface
  mm/damon/core: add number of each enum type values
  mm/damon/core: allow non-exclusive DAMON start/stop
  Docs/damon: update outdated term 'regions update interval'
  Docs/vm/damon/design: update DAMON-Idle Page Tracking interference handling
  Docs/vm/damon: call low level monitoring primitives the operations
  mm/damon: remove unnecessary CONFIG_DAMON option
  mm/damon/paddr,vaddr: remove damon_{p,v}a_{target_valid,set_operations}()
  mm/damon/dbgfs-test: fix is_target_id() change
  ...

23 files changed, 41 insertions, 114 deletions

diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index a7a09eef1852..49652ef9eff4 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -38,6 +38,7 @@ config ARM
 	select ARCH_USE_CMPXCHG_LOCKREF
 	select ARCH_USE_MEMTEST
 	select ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT if MMU
+	select ARCH_WANT_GENERAL_HUGETLB
 	select ARCH_WANT_IPC_PARSE_VERSION
 	select ARCH_WANT_LD_ORPHAN_WARN
 	select BINFMT_FLAT_ARGVP_ENVP_ON_STACK
@@ -1509,9 +1510,6 @@ config HW_PERF_EVENTS
 	def_bool y
 	depends on ARM_PMU
 
-config ARCH_WANT_GENERAL_HUGETLB
-	def_bool y
-
 config ARM_MODULE_PLTS
 	bool "Use PLTs to allow module memory to spill over into vmalloc area"
 	depends on MODULES
diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c
index f70573928f1b..3505789cf4bd 100644
--- a/arch/arm64/kernel/setup.c
+++ b/arch/arm64/kernel/setup.c
@@ -406,9 +406,6 @@ static int __init topology_init(void)
 {
 	int i;
 
-	for_each_online_node(i)
-		register_one_node(i);
-
 	for_each_possible_cpu(i) {
 		struct cpu *cpu = &per_cpu(cpu_data.cpu, i);
 		cpu->hotpluggable = cpu_can_disable(i);
diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c
index a33aba91ad89..cbace1c9e137 100644
--- a/arch/arm64/mm/hugetlbpage.c
+++ b/arch/arm64/mm/hugetlbpage.c
@@ -356,6 +356,7 @@ pte_t arch_make_huge_pte(pte_t entry, unsigned int shift, vm_flags_t flags)
 {
 	size_t pagesize = 1UL << shift;
 
+	entry = pte_mkhuge(entry);
 	if (pagesize == CONT_PTE_SIZE) {
 		entry = pte_mkcont(entry);
 	} else if (pagesize == CONT_PMD_SIZE) {
diff --git a/arch/hexagon/mm/init.c b/arch/hexagon/mm/init.c
index f01e91e10d95..3167a3b5c97b 100644
--- a/arch/hexagon/mm/init.c
+++ b/arch/hexagon/mm/init.c
@@ -29,8 +29,6 @@ int max_kernel_seg = 0x303;
 /*  indicate pfn's of high memory  */
 unsigned long highstart_pfn, highend_pfn;
 
-DEFINE_PER_CPU(struct mmu_gather, mmu_gathers);
-
 /* Default cache attribute for newly created page tables */
 unsigned long _dflt_cache_att = CACHEDEF;
 
diff --git a/arch/ia64/kernel/topology.c b/arch/ia64/kernel/topology.c
index e4992917a24b..94a848b06f15 100644
--- a/arch/ia64/kernel/topology.c
+++ b/arch/ia64/kernel/topology.c
@@ -70,16 +70,6 @@ static int __init topology_init(void)
 {
 	int i, err = 0;
 
-#ifdef CONFIG_NUMA
-	/*
-	 * MCD - Do we want to register all ONLINE nodes, or all POSSIBLE nodes?
-	 */
-	for_each_online_node(i) {
-		if ((err = register_one_node(i)))
-			goto out;
-	}
-#endif
-
 	sysfs_cpus = kcalloc(NR_CPUS, sizeof(struct ia64_cpu), GFP_KERNEL);
 	if (!sysfs_cpus)
 		panic("kzalloc in topology_init failed - NR_CPUS too big?");
diff --git a/arch/ia64/mm/discontig.c b/arch/ia64/mm/discontig.c
index 791d4176e4a6..73d0db36edb6 100644
--- a/arch/ia64/mm/discontig.c
+++ b/arch/ia64/mm/discontig.c
@@ -608,17 +608,11 @@ void __init paging_init(void)
 	zero_page_memmap_ptr = virt_to_page(ia64_imva(empty_zero_page));
 }
 
-#ifdef CONFIG_MEMORY_HOTPLUG
-pg_data_t *arch_alloc_nodedata(int nid)
+pg_data_t * __init arch_alloc_nodedata(int nid)
 {
 	unsigned long size = compute_pernodesize(nid);
 
-	return kzalloc(size, GFP_KERNEL);
-}
-
-void arch_free_nodedata(pg_data_t *pgdat)
-{
-	kfree(pgdat);
+	return memblock_alloc(size, SMP_CACHE_BYTES);
 }
 
 void arch_refresh_nodedata(int update_node, pg_data_t *update_pgdat)
@@ -626,7 +620,6 @@ void arch_refresh_nodedata(int update_node, pg_data_t *update_pgdat)
 	pgdat_list[update_node] = update_pgdat;
 	scatter_node_data();
 }
-#endif
 
 #ifdef CONFIG_SPARSEMEM_VMEMMAP
 int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node,
diff --git a/arch/mips/kernel/topology.c b/arch/mips/kernel/topology.c
index 08ad6371fbe0..9429d85a4703 100644
--- a/arch/mips/kernel/topology.c
+++ b/arch/mips/kernel/topology.c
@@ -12,11 +12,6 @@ static int __init topology_init(void)
 {
 	int i, ret;
 
-#ifdef CONFIG_NUMA
-	for_each_online_node(i)
-		register_one_node(i);
-#endif /* CONFIG_NUMA */
-
 	for_each_present_cpu(i) {
 		struct cpu *c = &per_cpu(cpu_devices, i);
 
diff --git a/arch/nds32/mm/init.c b/arch/nds32/mm/init.c
index f63f839738c4..825c85cab1a1 100644
--- a/arch/nds32/mm/init.c
+++ b/arch/nds32/mm/init.c
@@ -18,7 +18,6 @@
 #include <asm/tlb.h>
 #include <asm/page.h>
 
-DEFINE_PER_CPU(struct mmu_gather, mmu_gathers);
 DEFINE_SPINLOCK(anon_alias_lock);
 extern pgd_t swapper_pg_dir[PTRS_PER_PGD];
 
diff --git a/arch/openrisc/mm/init.c b/arch/openrisc/mm/init.c
index 97305bde1b16..3a021ab6f1ae 100644
--- a/arch/openrisc/mm/init.c
+++ b/arch/openrisc/mm/init.c
@@ -38,8 +38,6 @@
 
 int mem_init_done;
 
-DEFINE_PER_CPU(struct mmu_gather, mmu_gathers);
-
 static void __init zone_sizes_init(void)
 {
 	unsigned long max_zone_pfn[MAX_NR_ZONES] = { 0 };
diff --git a/arch/powerpc/include/asm/fadump-internal.h b/arch/powerpc/include/asm/fadump-internal.h
index 52189928ec08..81bcb9abb371 100644
--- a/arch/powerpc/include/asm/fadump-internal.h
+++ b/arch/powerpc/include/asm/fadump-internal.h
@@ -19,11 +19,6 @@
 
 #define memblock_num_regions(memblock_type)	(memblock.memblock_type.cnt)
 
-/* Alignment per CMA requirement. */
-#define FADUMP_CMA_ALIGNMENT	(PAGE_SIZE <<				\
-				 max_t(unsigned long, MAX_ORDER - 1,	\
-				 pageblock_order))
-
 /* FAD commands */
 #define FADUMP_REGISTER			1
 #define FADUMP_UNREGISTER		2
diff --git a/arch/powerpc/include/asm/nohash/32/hugetlb-8xx.h b/arch/powerpc/include/asm/nohash/32/hugetlb-8xx.h
index 64b6c608eca4..de092b04ee1a 100644
--- a/arch/powerpc/include/asm/nohash/32/hugetlb-8xx.h
+++ b/arch/powerpc/include/asm/nohash/32/hugetlb-8xx.h
@@ -71,9 +71,9 @@ static inline pte_t arch_make_huge_pte(pte_t entry, unsigned int shift, vm_flags
 	size_t size = 1UL << shift;
 
 	if (size == SZ_16K)
-		return __pte(pte_val(entry) & ~_PAGE_HUGE);
+		return __pte(pte_val(entry) | _PAGE_SPS);
 	else
-		return entry;
+		return __pte(pte_val(entry) | _PAGE_SPS | _PAGE_HUGE);
 }
 #define arch_make_huge_pte arch_make_huge_pte
 #endif
diff --git a/arch/powerpc/kernel/fadump.c b/arch/powerpc/kernel/fadump.c
index d03e488cfe9c..4fdb7c77fda1 100644
--- a/arch/powerpc/kernel/fadump.c
+++ b/arch/powerpc/kernel/fadump.c
@@ -113,6 +113,12 @@ static int __init fadump_cma_init(void)
 	}
 
 	/*
+	 *  If CMA activation fails, keep the pages reserved, instead of
+	 *  exposing them to buddy allocator. Same as 'fadump=nocma' case.
+	 */
+	cma_reserve_pages_on_error(fadump_cma);
+
+	/*
 	 * So we now have successfully initialized cma area for fadump.
 	 */
 	pr_info("Initialized 0x%lx bytes cma area at %ldMB from 0x%lx "
@@ -544,7 +550,7 @@ int __init fadump_reserve_mem(void)
 		if (!fw_dump.nocma) {
 			fw_dump.boot_memory_size =
 				ALIGN(fw_dump.boot_memory_size,
-				      FADUMP_CMA_ALIGNMENT);
+				      CMA_MIN_ALIGNMENT_BYTES);
 		}
 #endif
 
diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c
index d45a415d5374..2069bbb90a9a 100644
--- a/arch/powerpc/kernel/sysfs.c
+++ b/arch/powerpc/kernel/sysfs.c
@@ -1110,14 +1110,6 @@ EXPORT_SYMBOL_GPL(cpu_remove_dev_attr_group);
 /* NUMA stuff */
 
 #ifdef CONFIG_NUMA
-static void __init register_nodes(void)
-{
-	int i;
-
-	for (i = 0; i < MAX_NUMNODES; i++)
-		register_one_node(i);
-}
-
 int sysfs_add_device_to_node(struct device *dev, int nid)
 {
 	struct node *node = node_devices[nid];
@@ -1132,13 +1124,6 @@ void sysfs_remove_device_from_node(struct device *dev, int nid)
 	sysfs_remove_link(&node->dev.kobj, kobject_name(&dev->kobj));
 }
 EXPORT_SYMBOL_GPL(sysfs_remove_device_from_node);
-
-#else
-static void __init register_nodes(void)
-{
-	return;
-}
-
 #endif
 
 /* Only valid if CPU is present. */
@@ -1155,8 +1140,6 @@ static int __init topology_init(void)
 {
 	int cpu, r;
 
-	register_nodes();
-
 	for_each_possible_cpu(cpu) {
 		struct cpu *c = &per_cpu(cpu_devices, cpu);
 
diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index 5adcbd9b5e88..0804b9a11934 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -40,6 +40,7 @@ config RISCV
 	select ARCH_USE_MEMTEST
 	select ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT if MMU
 	select ARCH_WANT_FRAME_POINTERS
+	select ARCH_WANT_GENERAL_HUGETLB
 	select ARCH_WANT_HUGE_PMD_SHARE if 64BIT
 	select BINFMT_FLAT_NO_DATA_START_OFFSET if !MMU
 	select BUILDTIME_TABLE_SORT if MMU
@@ -171,9 +172,6 @@ config ARCH_SPARSEMEM_ENABLE
 config ARCH_SELECT_MEMORY_MODEL
 	def_bool ARCH_SPARSEMEM_ENABLE
 
-config ARCH_WANT_GENERAL_HUGETLB
-	def_bool y
-
 config ARCH_SUPPORTS_UPROBES
 	def_bool y
 
diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c
index b42bfdc67482..834eb652a7b9 100644
--- a/arch/riscv/kernel/setup.c
+++ b/arch/riscv/kernel/setup.c
@@ -301,9 +301,6 @@ static int __init topology_init(void)
 {
 	int i, ret;
 
-	for_each_online_node(i)
-		register_one_node(i);
-
 	for_each_possible_cpu(i) {
 		struct cpu *cpu = &per_cpu(cpu_devices, i);
 
diff --git a/arch/s390/kernel/numa.c b/arch/s390/kernel/numa.c
index 51c5a9f6e525..23ab9f02f278 100644
--- a/arch/s390/kernel/numa.c
+++ b/arch/s390/kernel/numa.c
@@ -33,10 +33,3 @@ void __init numa_setup(void)
 	NODE_DATA(0)->node_spanned_pages = memblock_end_of_DRAM() >> PAGE_SHIFT;
 	NODE_DATA(0)->node_id = 0;
 }
-
-static int __init numa_init_late(void)
-{
-	register_one_node(0);
-	return 0;
-}
-arch_initcall(numa_init_late);
diff --git a/arch/sh/kernel/topology.c b/arch/sh/kernel/topology.c
index 76af6db9daa2..2d2a7509b565 100644
--- a/arch/sh/kernel/topology.c
+++ b/arch/sh/kernel/topology.c
@@ -46,11 +46,6 @@ static int __init topology_init(void)
 {
 	int i, ret;
 
-#ifdef CONFIG_NUMA
-	for_each_online_node(i)
-		register_one_node(i);
-#endif
-
 	for_each_present_cpu(i) {
 		struct cpu *c = &per_cpu(cpu_devices, i);
 
diff --git a/arch/sparc/kernel/sysfs.c b/arch/sparc/kernel/sysfs.c
index 6d60d416f0dd..f19487e4cc71 100644
--- a/arch/sparc/kernel/sysfs.c
+++ b/arch/sparc/kernel/sysfs.c
@@ -244,22 +244,10 @@ static void __init check_mmu_stats(void)
 		mmu_stats_supported = 1;
 }
 
-static void register_nodes(void)
-{
-#ifdef CONFIG_NUMA
-	int i;
-
-	for (i = 0; i < MAX_NUMNODES; i++)
-		register_one_node(i);
-#endif
-}
-
 static int __init topology_init(void)
 {
 	int cpu, ret;
 
-	register_nodes();
-
 	check_mmu_stats();
 
 	for_each_possible_cpu(cpu) {
diff --git a/arch/sparc/mm/hugetlbpage.c b/arch/sparc/mm/hugetlbpage.c
index 0f49fada2093..d8e0e3c7038d 100644
--- a/arch/sparc/mm/hugetlbpage.c
+++ b/arch/sparc/mm/hugetlbpage.c
@@ -181,6 +181,7 @@ pte_t arch_make_huge_pte(pte_t entry, unsigned int shift, vm_flags_t flags)
 {
 	pte_t pte;
 
+	entry = pte_mkhuge(entry);
 	pte = hugepage_shift_to_tte(entry, shift);
 
 #ifdef CONFIG_SPARC64
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 42a3a736436f..61e511c51890 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -119,6 +119,7 @@ config X86
 	select ARCH_WANT_DEFAULT_BPF_JIT	if X86_64
 	select ARCH_WANTS_DYNAMIC_TASK_STRUCT
 	select ARCH_WANTS_NO_INSTR
+	select ARCH_WANT_GENERAL_HUGETLB
 	select ARCH_WANT_HUGE_PMD_SHARE
 	select ARCH_WANT_LD_ORPHAN_WARN
 	select ARCH_WANTS_RT_DELAYED_SIGNALS
@@ -349,9 +350,6 @@ config ARCH_NR_GPIO
 config ARCH_SUSPEND_POSSIBLE
 	def_bool y
 
-config ARCH_WANT_GENERAL_HUGETLB
-	def_bool y
-
 config AUDIT_ARCH
 	def_bool y if X86_64
 
diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index 4f1e825033ce..e53d3e6096fb 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -1299,10 +1299,12 @@ static void kill_me_maybe(struct callback_head *cb)
 
 	/*
 	 * -EHWPOISON from memory_failure() means that it already sent SIGBUS
-	 * to the current process with the proper error info, so no need to
-	 * send SIGBUS here again.
+	 * to the current process with the proper error info,
+	 * -EOPNOTSUPP means hwpoison_filter() filtered the error event,
+	 *
+	 * In both cases, no further processing is required.
 	 */
-	if (ret == -EHWPOISON)
+	if (ret == -EHWPOISON || ret == -EOPNOTSUPP)
 		return;
 
 	pr_err("Memory error not recovered");
diff --git a/arch/x86/kernel/topology.c b/arch/x86/kernel/topology.c
index bd83748e2bde..8617d1ed9d31 100644
--- a/arch/x86/kernel/topology.c
+++ b/arch/x86/kernel/topology.c
@@ -154,11 +154,6 @@ static int __init topology_init(void)
 {
 	int i;
 
-#ifdef CONFIG_NUMA
-	for_each_online_node(i)
-		register_one_node(i);
-#endif
-
 	for_each_present_cpu(i)
 		arch_register_cpu(i);
 
diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c
index c6b1213086d6..e8b061557887 100644
--- a/arch/x86/mm/numa.c
+++ b/arch/x86/mm/numa.c
@@ -738,17 +738,6 @@ void __init x86_numa_init(void)
 	numa_init(dummy_numa_init);
 }
 
-static void __init init_memory_less_node(int nid)
-{
-	/* Allocate and initialize node data. Memory-less node is now online.*/
-	alloc_node_data(nid);
-	free_area_init_memoryless_node(nid);
-
-	/*
-	 * All zonelists will be built later in start_kernel() after per cpu
-	 * areas are initialized.
-	 */
-}
 
 /*
  * A node may exist which has one or more Generic Initiators but no CPUs and no
@@ -766,9 +755,18 @@ void __init init_gi_nodes(void)
 {
 	int nid;
 
+	/*
+	 * Exclude this node from
+	 * bringup_nonboot_cpus
+	 *  cpu_up
+	 *   __try_online_node
+	 *    register_one_node
+	 * because node_subsys is not initialized yet.
+	 * TODO remove dependency on node_online
+	 */
 	for_each_node_state(nid, N_GENERIC_INITIATOR)
 		if (!node_online(nid))
-			init_memory_less_node(nid);
+			node_set_online(nid);
 }
 
 /*
@@ -798,8 +796,17 @@ void __init init_cpu_to_node(void)
 		if (node == NUMA_NO_NODE)
 			continue;
 
+		/*
+		 * Exclude this node from
+		 * bringup_nonboot_cpus
+		 *  cpu_up
+		 *   __try_online_node
+		 *    register_one_node
+		 * because node_subsys is not initialized yet.
+		 * TODO remove dependency on node_online
+		 */
 		if (!node_online(node))
-			init_memory_less_node(node);
+			node_set_online(node);
 
 		numa_set_node(cpu, node);
 	}