Merge branch 'akpm' (patches from Andrew)

Merge misc updates from Andrew Morton:
 "257 patches.

  Subsystems affected by this patch series: scripts, ocfs2, vfs, and
  mm (slab-generic, slab, slub, kconfig, dax, kasan, debug, pagecache,
  gup, swap, memcg, pagemap, mprotect, mremap, iomap, tracing, vmalloc,
  pagealloc, memory-failure, hugetlb, userfaultfd, vmscan, tools,
  memblock, oom-kill, hugetlbfs, migration, thp, readahead, nommu, ksm,
  vmstat, madvise, memory-hotplug, rmap, zsmalloc, highmem, zram,
  cleanups, kfence, and damon)"

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (257 commits)
  mm/damon: remove return value from before_terminate callback
  mm/damon: fix a few spelling mistakes in comments and a pr_debug message
  mm/damon: simplify stop mechanism
  Docs/admin-guide/mm/pagemap: wordsmith page flags descriptions
  Docs/admin-guide/mm/damon/start: simplify the content
  Docs/admin-guide/mm/damon/start: fix a wrong link
  Docs/admin-guide/mm/damon/start: fix wrong example commands
  mm/damon/dbgfs: add adaptive_targets list check before enable monitor_on
  mm/damon: remove unnecessary variable initialization
  Documentation/admin-guide/mm/damon: add a document for DAMON_RECLAIM
  mm/damon: introduce DAMON-based Reclamation (DAMON_RECLAIM)
  selftests/damon: support watermarks
  mm/damon/dbgfs: support watermarks
  mm/damon/schemes: activate schemes based on a watermarks mechanism
  tools/selftests/damon: update for regions prioritization of schemes
  mm/damon/dbgfs: support prioritization weights
  mm/damon/vaddr,paddr: support pageout prioritization
  mm/damon/schemes: prioritize regions within the quotas
  mm/damon/selftests: support schemes quotas
  mm/damon/dbgfs: support quotas of schemes
  ...

3 files changed, 81 insertions, 22 deletions

diff --git a/drivers/base/Makefile b/drivers/base/Makefile
index ef8e44a7d288..02f7f1358e86 100644
--- a/drivers/base/Makefile
+++ b/drivers/base/Makefile
@@ -13,7 +13,7 @@ obj-y			+= power/
 obj-$(CONFIG_ISA_BUS_API)	+= isa.o
 obj-y				+= firmware_loader/
 obj-$(CONFIG_NUMA)	+= node.o
-obj-$(CONFIG_MEMORY_HOTPLUG_SPARSE) += memory.o
+obj-$(CONFIG_MEMORY_HOTPLUG) += memory.o
 ifeq ($(CONFIG_SYSFS),y)
 obj-$(CONFIG_MODULES)	+= module.o
 endif
diff --git a/drivers/base/arch_numa.c b/drivers/base/arch_numa.c
index 00fb4120a5b3..bc1876915457 100644
--- a/drivers/base/arch_numa.c
+++ b/drivers/base/arch_numa.c
@@ -14,6 +14,7 @@
 #include <linux/of.h>
 
 #include <asm/sections.h>
+#include <asm/pgalloc.h>
 
 struct pglist_data *node_data[MAX_NUMNODES] __read_mostly;
 EXPORT_SYMBOL(node_data);
@@ -165,25 +166,86 @@ static void * __init pcpu_fc_alloc(unsigned int cpu, size_t size,
 
 static void __init pcpu_fc_free(void *ptr, size_t size)
 {
-	memblock_free_early(__pa(ptr), size);
+	memblock_free(ptr, size);
 }
 
+#ifdef CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK
+static void __init pcpu_populate_pte(unsigned long addr)
+{
+	pgd_t *pgd = pgd_offset_k(addr);
+	p4d_t *p4d;
+	pud_t *pud;
+	pmd_t *pmd;
+
+	p4d = p4d_offset(pgd, addr);
+	if (p4d_none(*p4d)) {
+		pud_t *new;
+
+		new = memblock_alloc(PAGE_SIZE, PAGE_SIZE);
+		if (!new)
+			goto err_alloc;
+		p4d_populate(&init_mm, p4d, new);
+	}
+
+	pud = pud_offset(p4d, addr);
+	if (pud_none(*pud)) {
+		pmd_t *new;
+
+		new = memblock_alloc(PAGE_SIZE, PAGE_SIZE);
+		if (!new)
+			goto err_alloc;
+		pud_populate(&init_mm, pud, new);
+	}
+
+	pmd = pmd_offset(pud, addr);
+	if (!pmd_present(*pmd)) {
+		pte_t *new;
+
+		new = memblock_alloc(PAGE_SIZE, PAGE_SIZE);
+		if (!new)
+			goto err_alloc;
+		pmd_populate_kernel(&init_mm, pmd, new);
+	}
+
+	return;
+
+err_alloc:
+	panic("%s: Failed to allocate %lu bytes align=%lx from=%lx\n",
+	      __func__, PAGE_SIZE, PAGE_SIZE, PAGE_SIZE);
+}
+#endif
+
 void __init setup_per_cpu_areas(void)
 {
 	unsigned long delta;
 	unsigned int cpu;
-	int rc;
+	int rc = -EINVAL;
+
+	if (pcpu_chosen_fc != PCPU_FC_PAGE) {
+		/*
+		 * Always reserve area for module percpu variables.  That's
+		 * what the legacy allocator did.
+		 */
+		rc = pcpu_embed_first_chunk(PERCPU_MODULE_RESERVE,
+					    PERCPU_DYNAMIC_RESERVE, PAGE_SIZE,
+					    pcpu_cpu_distance,
+					    pcpu_fc_alloc, pcpu_fc_free);
+#ifdef CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK
+		if (rc < 0)
+			pr_warn("PERCPU: %s allocator failed (%d), falling back to page size\n",
+				   pcpu_fc_names[pcpu_chosen_fc], rc);
+#endif
+	}
 
-	/*
-	 * Always reserve area for module percpu variables.  That's
-	 * what the legacy allocator did.
-	 */
-	rc = pcpu_embed_first_chunk(PERCPU_MODULE_RESERVE,
-				    PERCPU_DYNAMIC_RESERVE, PAGE_SIZE,
-				    pcpu_cpu_distance,
-				    pcpu_fc_alloc, pcpu_fc_free);
+#ifdef CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK
+	if (rc < 0)
+		rc = pcpu_page_first_chunk(PERCPU_MODULE_RESERVE,
+					   pcpu_fc_alloc,
+					   pcpu_fc_free,
+					   pcpu_populate_pte);
+#endif
 	if (rc < 0)
-		panic("Failed to initialize percpu areas.");
+		panic("Failed to initialize percpu areas (err=%d).", rc);
 
 	delta = (unsigned long)pcpu_base_addr - (unsigned long)__per_cpu_start;
 	for_each_possible_cpu(cpu)
@@ -264,7 +326,7 @@ void __init numa_free_distance(void)
 	size = numa_distance_cnt * numa_distance_cnt *
 		sizeof(numa_distance[0]);
 
-	memblock_free_ptr(numa_distance, size);
+	memblock_free(numa_distance, size);
 	numa_distance_cnt = 0;
 	numa_distance = NULL;
 }
@@ -275,15 +337,13 @@ void __init numa_free_distance(void)
 static int __init numa_alloc_distance(void)
 {
 	size_t size;
-	u64 phys;
 	int i, j;
 
 	size = nr_node_ids * nr_node_ids * sizeof(numa_distance[0]);
-	phys = memblock_phys_alloc_range(size, PAGE_SIZE, 0, PFN_PHYS(max_pfn));
-	if (WARN_ON(!phys))
+	numa_distance = memblock_alloc(size, PAGE_SIZE);
+	if (WARN_ON(!numa_distance))
 		return -ENOMEM;
 
-	numa_distance = __va(phys);
 	numa_distance_cnt = nr_node_ids;
 
 	/* fill with the default distances */
diff --git a/drivers/base/node.c b/drivers/base/node.c
index c56d34f8158f..b5a4ba18f9f9 100644
--- a/drivers/base/node.c
+++ b/drivers/base/node.c
@@ -629,7 +629,7 @@ static void node_device_release(struct device *dev)
 {
 	struct node *node = to_node(dev);
 
-#if defined(CONFIG_MEMORY_HOTPLUG_SPARSE) && defined(CONFIG_HUGETLBFS)
+#if defined(CONFIG_MEMORY_HOTPLUG) && defined(CONFIG_HUGETLBFS)
 	/*
 	 * We schedule the work only when a memory section is
 	 * onlined/offlined on this node. When we come here,
@@ -782,7 +782,7 @@ int unregister_cpu_under_node(unsigned int cpu, unsigned int nid)
 	return 0;
 }
 
-#ifdef CONFIG_MEMORY_HOTPLUG_SPARSE
+#ifdef CONFIG_MEMORY_HOTPLUG
 static int __ref get_nid_for_pfn(unsigned long pfn)
 {
 #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
@@ -958,10 +958,9 @@ static int node_memory_callback(struct notifier_block *self,
 	return NOTIFY_OK;
 }
 #endif	/* CONFIG_HUGETLBFS */
-#endif /* CONFIG_MEMORY_HOTPLUG_SPARSE */
+#endif /* CONFIG_MEMORY_HOTPLUG */
 
-#if !defined(CONFIG_MEMORY_HOTPLUG_SPARSE) || \
-    !defined(CONFIG_HUGETLBFS)
+#if !defined(CONFIG_MEMORY_HOTPLUG) || !defined(CONFIG_HUGETLBFS)
 static inline int node_memory_callback(struct notifier_block *self,
 				unsigned long action, void *arg)
 {