Merge branch 'akpm' (patches from Andrew)

Merge yet more updates from Andrew Morton:
 "The rest of MM and a kernel-wide procfs cleanup.

  Summary of the more significant patches:

   - Patch series "mm/memory_hotplug: Factor out memory block
     devicehandling", v3. David Hildenbrand.

     Some spring-cleaning of the memory hotplug code, notably in
     drivers/base/memory.c

   - "mm: thp: fix false negative of shmem vma's THP eligibility". Yang
     Shi.

     Fix /proc/pid/smaps output for THP pages used in shmem.

   - "resource: fix locking in find_next_iomem_res()" + 1. Nadav Amit.

     Bugfix and speedup for kernel/resource.c

   - Patch series "mm: Further memory block device cleanups", David
     Hildenbrand.

     More spring-cleaning of the memory hotplug code.

   - Patch series "mm: Sub-section memory hotplug support". Dan
     Williams.

     Generalise the memory hotplug code so that pmem can use it more
     completely. Then remove the hacks from the libnvdimm code which
     were there to work around the memory-hotplug code's constraints.

   - "proc/sysctl: add shared variables for range check", Matteo Croce.

     We have about 250 instances of

          int zero;
          ...
                  .extra1 = &zero,

     in the tree. This is a tree-wide sweep to make all those private
     "zero"s and "one"s use global variables.

     Alas, it isn't practical to make those two global integers const"

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (38 commits)
  proc/sysctl: add shared variables for range check
  mm: migrate: remove unused mode argument
  mm/sparsemem: cleanup 'section number' data types
  libnvdimm/pfn: stop padding pmem namespaces to section alignment
  libnvdimm/pfn: fix fsdax-mode namespace info-block zero-fields
  mm/devm_memremap_pages: enable sub-section remap
  mm: document ZONE_DEVICE memory-model implications
  mm/sparsemem: support sub-section hotplug
  mm/sparsemem: prepare for sub-section ranges
  mm: kill is_dev_zone() helper
  mm/hotplug: kill is_dev_zone() usage in __remove_pages()
  mm/sparsemem: convert kmalloc_section_memmap() to populate_section_memmap()
  mm/hotplug: prepare shrink_{zone, pgdat}_span for sub-section removal
  mm/sparsemem: add helpers track active portions of a section at boot
  mm/sparsemem: introduce a SECTION_IS_EARLY flag
  mm/sparsemem: introduce struct mem_section_usage
  drivers/base/memory.c: get rid of find_memory_block_hinted()
  mm/memory_hotplug: move and simplify walk_memory_blocks()
  mm/memory_hotplug: rename walk_memory_range() and pass start+size instead of pfns
  mm: make register_mem_sect_under_node() static
  ...

12 files changed, 52 insertions, 54 deletions

diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index e661469cabdd..750a69dde39b 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -1074,4 +1074,21 @@ int arch_add_memory(int nid, u64 start, u64 size,
 	return __add_pages(nid, start >> PAGE_SHIFT, size >> PAGE_SHIFT,
 			   restrictions);
 }
+void arch_remove_memory(int nid, u64 start, u64 size,
+			struct vmem_altmap *altmap)
+{
+	unsigned long start_pfn = start >> PAGE_SHIFT;
+	unsigned long nr_pages = size >> PAGE_SHIFT;
+	struct zone *zone;
+
+	/*
+	 * FIXME: Cleanup page tables (also in arch_add_memory() in case
+	 * adding fails). Until then, this function should only be used
+	 * during memory hotplug (adding memory), not for memory
+	 * unplug. ARCH_ENABLE_MEMORY_HOTREMOVE must not be
+	 * unlocked yet.
+	 */
+	zone = page_zone(pfn_to_page(start_pfn));
+	__remove_pages(zone, start_pfn, nr_pages, altmap);
+}
 #endif
diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c
index d28e29103bdb..aae75fd7b810 100644
--- a/arch/ia64/mm/init.c
+++ b/arch/ia64/mm/init.c
@@ -681,7 +681,6 @@ int arch_add_memory(int nid, u64 start, u64 size,
 	return ret;
 }
 
-#ifdef CONFIG_MEMORY_HOTREMOVE
 void arch_remove_memory(int nid, u64 start, u64 size,
 			struct vmem_altmap *altmap)
 {
@@ -693,4 +692,3 @@ void arch_remove_memory(int nid, u64 start, u64 size,
 	__remove_pages(zone, start_pfn, nr_pages, altmap);
 }
 #endif
-#endif
diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index 26a8da3723bb..9259337d7374 100644
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -125,7 +125,6 @@ int __ref arch_add_memory(int nid, u64 start, u64 size,
 	return __add_pages(nid, start_pfn, nr_pages, restrictions);
 }
 
-#ifdef CONFIG_MEMORY_HOTREMOVE
 void __ref arch_remove_memory(int nid, u64 start, u64 size,
 			     struct vmem_altmap *altmap)
 {
@@ -151,7 +150,6 @@ void __ref arch_remove_memory(int nid, u64 start, u64 size,
 		pr_warn("Hash collision while resizing HPT\n");
 }
 #endif
-#endif /* CONFIG_MEMORY_HOTPLUG */
 
 #ifndef CONFIG_NEED_MULTIPLE_NODES
 void __init mem_topology_setup(void)
diff --git a/arch/powerpc/platforms/powernv/memtrace.c b/arch/powerpc/platforms/powernv/memtrace.c
index 5e53c1392d3b..eb2e75dac369 100644
--- a/arch/powerpc/platforms/powernv/memtrace.c
+++ b/arch/powerpc/platforms/powernv/memtrace.c
@@ -70,23 +70,23 @@ static int change_memblock_state(struct memory_block *mem, void *arg)
 /* called with device_hotplug_lock held */
 static bool memtrace_offline_pages(u32 nid, u64 start_pfn, u64 nr_pages)
 {
-	u64 end_pfn = start_pfn + nr_pages - 1;
+	const unsigned long start = PFN_PHYS(start_pfn);
+	const unsigned long size = PFN_PHYS(nr_pages);
 
-	if (walk_memory_range(start_pfn, end_pfn, NULL,
-	    check_memblock_online))
+	if (walk_memory_blocks(start, size, NULL, check_memblock_online))
 		return false;
 
-	walk_memory_range(start_pfn, end_pfn, (void *)MEM_GOING_OFFLINE,
-			  change_memblock_state);
+	walk_memory_blocks(start, size, (void *)MEM_GOING_OFFLINE,
+			   change_memblock_state);
 
 	if (offline_pages(start_pfn, nr_pages)) {
-		walk_memory_range(start_pfn, end_pfn, (void *)MEM_ONLINE,
-				  change_memblock_state);
+		walk_memory_blocks(start, size, (void *)MEM_ONLINE,
+				   change_memblock_state);
 		return false;
 	}
 
-	walk_memory_range(start_pfn, end_pfn, (void *)MEM_OFFLINE,
-			  change_memblock_state);
+	walk_memory_blocks(start, size, (void *)MEM_OFFLINE,
+			   change_memblock_state);
 
 
 	return true;
@@ -242,9 +242,8 @@ static int memtrace_online(void)
 		 */
 		if (!memhp_auto_online) {
 			lock_device_hotplug();
-			walk_memory_range(PFN_DOWN(ent->start),
-					  PFN_UP(ent->start + ent->size - 1),
-					  NULL, online_mem_block);
+			walk_memory_blocks(ent->start, ent->size, NULL,
+					   online_mem_block);
 			unlock_device_hotplug();
 		}
 
diff --git a/arch/s390/appldata/appldata_base.c b/arch/s390/appldata/appldata_base.c
index e4b58240ec53..aa738cad1338 100644
--- a/arch/s390/appldata/appldata_base.c
+++ b/arch/s390/appldata/appldata_base.c
@@ -220,15 +220,13 @@ appldata_timer_handler(struct ctl_table *ctl, int write,
 			   void __user *buffer, size_t *lenp, loff_t *ppos)
 {
 	int timer_active = appldata_timer_active;
-	int zero = 0;
-	int one = 1;
 	int rc;
 	struct ctl_table ctl_entry = {
 		.procname	= ctl->procname,
 		.data		= &timer_active,
 		.maxlen		= sizeof(int),
-		.extra1		= &zero,
-		.extra2		= &one,
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= SYSCTL_ONE,
 	};
 
 	rc = proc_douintvec_minmax(&ctl_entry, write, buffer, lenp, ppos);
@@ -255,13 +253,12 @@ appldata_interval_handler(struct ctl_table *ctl, int write,
 			   void __user *buffer, size_t *lenp, loff_t *ppos)
 {
 	int interval = appldata_interval;
-	int one = 1;
 	int rc;
 	struct ctl_table ctl_entry = {
 		.procname	= ctl->procname,
 		.data		= &interval,
 		.maxlen		= sizeof(int),
-		.extra1		= &one,
+		.extra1		= SYSCTL_ONE,
 	};
 
 	rc = proc_dointvec_minmax(&ctl_entry, write, buffer, lenp, ppos);
@@ -289,13 +286,11 @@ appldata_generic_handler(struct ctl_table *ctl, int write,
 	struct list_head *lh;
 	int rc, found;
 	int active;
-	int zero = 0;
-	int one = 1;
 	struct ctl_table ctl_entry = {
 		.data		= &active,
 		.maxlen		= sizeof(int),
-		.extra1		= &zero,
-		.extra2		= &one,
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= SYSCTL_ONE,
 	};
 
 	found = 0;
diff --git a/arch/s390/kernel/topology.c b/arch/s390/kernel/topology.c
index 8964a3f60aad..2db6fb405a9a 100644
--- a/arch/s390/kernel/topology.c
+++ b/arch/s390/kernel/topology.c
@@ -587,15 +587,13 @@ static int topology_ctl_handler(struct ctl_table *ctl, int write,
 {
 	int enabled = topology_is_enabled();
 	int new_mode;
-	int zero = 0;
-	int one = 1;
 	int rc;
 	struct ctl_table ctl_entry = {
 		.procname	= ctl->procname,
 		.data		= &enabled,
 		.maxlen		= sizeof(int),
-		.extra1		= &zero,
-		.extra2		= &one,
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= SYSCTL_ONE,
 	};
 
 	rc = proc_douintvec_minmax(&ctl_entry, write, buffer, lenp, ppos);
diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c
index f0bee6af3960..4e5bbe328594 100644
--- a/arch/s390/mm/init.c
+++ b/arch/s390/mm/init.c
@@ -273,6 +273,9 @@ int arch_add_memory(int nid, u64 start, u64 size,
 	unsigned long size_pages = PFN_DOWN(size);
 	int rc;
 
+	if (WARN_ON_ONCE(restrictions->altmap))
+		return -EINVAL;
+
 	rc = vmem_add_mapping(start, size);
 	if (rc)
 		return rc;
@@ -283,16 +286,15 @@ int arch_add_memory(int nid, u64 start, u64 size,
 	return rc;
 }
 
-#ifdef CONFIG_MEMORY_HOTREMOVE
 void arch_remove_memory(int nid, u64 start, u64 size,
 			struct vmem_altmap *altmap)
 {
-	/*
-	 * There is no hardware or firmware interface which could trigger a
-	 * hot memory remove on s390. So there is nothing that needs to be
-	 * implemented.
-	 */
-	BUG();
+	unsigned long start_pfn = start >> PAGE_SHIFT;
+	unsigned long nr_pages = size >> PAGE_SHIFT;
+	struct zone *zone;
+
+	zone = page_zone(pfn_to_page(start_pfn));
+	__remove_pages(zone, start_pfn, nr_pages, altmap);
+	vmem_remove_mapping(start, size);
 }
-#endif
 #endif /* CONFIG_MEMORY_HOTPLUG */
diff --git a/arch/sh/mm/init.c b/arch/sh/mm/init.c
index 13c6a6bb5fd9..dfdbaa50946e 100644
--- a/arch/sh/mm/init.c
+++ b/arch/sh/mm/init.c
@@ -429,7 +429,6 @@ int memory_add_physaddr_to_nid(u64 addr)
 EXPORT_SYMBOL_GPL(memory_add_physaddr_to_nid);
 #endif
 
-#ifdef CONFIG_MEMORY_HOTREMOVE
 void arch_remove_memory(int nid, u64 start, u64 size,
 			struct vmem_altmap *altmap)
 {
@@ -440,5 +439,4 @@ void arch_remove_memory(int nid, u64 start, u64 size,
 	zone = page_zone(pfn_to_page(start_pfn));
 	__remove_pages(zone, start_pfn, nr_pages, altmap);
 }
-#endif
 #endif /* CONFIG_MEMORY_HOTPLUG */
diff --git a/arch/x86/entry/vdso/vdso32-setup.c b/arch/x86/entry/vdso/vdso32-setup.c
index 42d4c89f990e..240626e7f55a 100644
--- a/arch/x86/entry/vdso/vdso32-setup.c
+++ b/arch/x86/entry/vdso/vdso32-setup.c
@@ -65,9 +65,6 @@ subsys_initcall(sysenter_setup);
 /* Register vsyscall32 into the ABI table */
 #include <linux/sysctl.h>
 
-static const int zero;
-static const int one = 1;
-
 static struct ctl_table abi_table2[] = {
 	{
 		.procname	= "vsyscall32",
@@ -75,8 +72,8 @@ static struct ctl_table abi_table2[] = {
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= (int *)&zero,
-		.extra2		= (int *)&one,
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= SYSCTL_ONE,
 	},
 	{}
 };
diff --git a/arch/x86/kernel/itmt.c b/arch/x86/kernel/itmt.c
index 838cf8a32c49..1cb3ca9bba49 100644
--- a/arch/x86/kernel/itmt.c
+++ b/arch/x86/kernel/itmt.c
@@ -65,8 +65,6 @@ static int sched_itmt_update_handler(struct ctl_table *table, int write,
 	return ret;
 }
 
-static unsigned int zero;
-static unsigned int one = 1;
 static struct ctl_table itmt_kern_table[] = {
 	{
 		.procname	= "sched_itmt_enabled",
@@ -74,8 +72,8 @@ static struct ctl_table itmt_kern_table[] = {
 		.maxlen		= sizeof(unsigned int),
 		.mode		= 0644,
 		.proc_handler	= sched_itmt_update_handler,
-		.extra1		= &zero,
-		.extra2		= &one,
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= SYSCTL_ONE,
 	},
 	{}
 };
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index f265a4316179..4068abb9427f 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -860,7 +860,6 @@ int arch_add_memory(int nid, u64 start, u64 size,
 	return __add_pages(nid, start_pfn, nr_pages, restrictions);
 }
 
-#ifdef CONFIG_MEMORY_HOTREMOVE
 void arch_remove_memory(int nid, u64 start, u64 size,
 			struct vmem_altmap *altmap)
 {
@@ -872,7 +871,6 @@ void arch_remove_memory(int nid, u64 start, u64 size,
 	__remove_pages(zone, start_pfn, nr_pages, altmap);
 }
 #endif
-#endif
 
 int kernel_set_to_readonly __read_mostly;
 
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 08bbf648827b..a6b5c653727b 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -1198,7 +1198,6 @@ void __ref vmemmap_free(unsigned long start, unsigned long end,
 	remove_pagetable(start, end, false, altmap);
 }
 
-#ifdef CONFIG_MEMORY_HOTREMOVE
 static void __meminit
 kernel_physical_mapping_remove(unsigned long start, unsigned long end)
 {
@@ -1219,7 +1218,6 @@ void __ref arch_remove_memory(int nid, u64 start, u64 size,
 	__remove_pages(zone, start_pfn, nr_pages, altmap);
 	kernel_physical_mapping_remove(start, start + size);
 }
-#endif
 #endif /* CONFIG_MEMORY_HOTPLUG */
 
 static struct kcore_list kcore_vsyscall;
@@ -1520,7 +1518,9 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node,
 {
 	int err;
 
-	if (boot_cpu_has(X86_FEATURE_PSE))
+	if (end - start < PAGES_PER_SECTION * sizeof(struct page))
+		err = vmemmap_populate_basepages(start, end, node);
+	else if (boot_cpu_has(X86_FEATURE_PSE))
 		err = vmemmap_populate_hugepages(start, end, node, altmap);
 	else if (altmap) {
 		pr_err_once("%s: no cpu support for altmap allocations\n",