Merge branch 'akpm' (patches from Andrew)

Merge updates from Andrew Morton:
 "A large amount of MM, plenty more to come.

  Subsystems affected by this patch series:
   - tools
   - kthread
   - kbuild
   - scripts
   - ocfs2
   - vfs
   - mm: slub, kmemleak, pagecache, gup, swap, memcg, pagemap, mremap,
         sparsemem, kasan, pagealloc, vmscan, compaction, mempolicy,
         hugetlbfs, hugetlb"

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (155 commits)
  include/linux/huge_mm.h: check PageTail in hpage_nr_pages even when !THP
  mm/hugetlb: fix build failure with HUGETLB_PAGE but not HUGEBTLBFS
  selftests/vm: fix map_hugetlb length used for testing read and write
  mm/hugetlb: remove unnecessary memory fetch in PageHeadHuge()
  mm/hugetlb.c: clean code by removing unnecessary initialization
  hugetlb_cgroup: add hugetlb_cgroup reservation docs
  hugetlb_cgroup: add hugetlb_cgroup reservation tests
  hugetlb: support file_region coalescing again
  hugetlb_cgroup: support noreserve mappings
  hugetlb_cgroup: add accounting for shared mappings
  hugetlb: disable region_add file_region coalescing
  hugetlb_cgroup: add reservation accounting for private mappings
  mm/hugetlb_cgroup: fix hugetlb_cgroup migration
  hugetlb_cgroup: add interface for charge/uncharge hugetlb reservations
  hugetlb_cgroup: add hugetlb_cgroup reservation counter
  hugetlbfs: Use i_mmap_rwsem to address page fault/truncate race
  hugetlbfs: use i_mmap_rwsem for more pmd sharing synchronization
  mm/memblock.c: remove redundant assignment to variable max_addr
  mm: mempolicy: require at least one nodeid for MPOL_PREFERRED
  mm: mempolicy: use VM_BUG_ON_VMA in queue_pages_test_walk()
  ...

3 files changed, 49 insertions, 6 deletions

diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 915dda3f7f19..755c07d845ce 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -1813,12 +1813,14 @@ int cgroup_show_path(struct seq_file *sf, struct kernfs_node *kf_node,
 enum cgroup2_param {
 	Opt_nsdelegate,
 	Opt_memory_localevents,
+	Opt_memory_recursiveprot,
 	nr__cgroup2_params
 };
 
 static const struct fs_parameter_spec cgroup2_fs_parameters[] = {
 	fsparam_flag("nsdelegate",		Opt_nsdelegate),
 	fsparam_flag("memory_localevents",	Opt_memory_localevents),
+	fsparam_flag("memory_recursiveprot",	Opt_memory_recursiveprot),
 	{}
 };
 
@@ -1839,6 +1841,9 @@ static int cgroup2_parse_param(struct fs_context *fc, struct fs_parameter *param
 	case Opt_memory_localevents:
 		ctx->flags |= CGRP_ROOT_MEMORY_LOCAL_EVENTS;
 		return 0;
+	case Opt_memory_recursiveprot:
+		ctx->flags |= CGRP_ROOT_MEMORY_RECURSIVE_PROT;
+		return 0;
 	}
 	return -EINVAL;
 }
@@ -1855,6 +1860,11 @@ static void apply_cgroup_root_flags(unsigned int root_flags)
 			cgrp_dfl_root.flags |= CGRP_ROOT_MEMORY_LOCAL_EVENTS;
 		else
 			cgrp_dfl_root.flags &= ~CGRP_ROOT_MEMORY_LOCAL_EVENTS;
+
+		if (root_flags & CGRP_ROOT_MEMORY_RECURSIVE_PROT)
+			cgrp_dfl_root.flags |= CGRP_ROOT_MEMORY_RECURSIVE_PROT;
+		else
+			cgrp_dfl_root.flags &= ~CGRP_ROOT_MEMORY_RECURSIVE_PROT;
 	}
 }
 
@@ -1864,6 +1874,8 @@ static int cgroup_show_options(struct seq_file *seq, struct kernfs_root *kf_root
 		seq_puts(seq, ",nsdelegate");
 	if (cgrp_dfl_root.flags & CGRP_ROOT_MEMORY_LOCAL_EVENTS)
 		seq_puts(seq, ",memory_localevents");
+	if (cgrp_dfl_root.flags & CGRP_ROOT_MEMORY_RECURSIVE_PROT)
+		seq_puts(seq, ",memory_recursiveprot");
 	return 0;
 }
 
@@ -6412,7 +6424,10 @@ static struct kobj_attribute cgroup_delegate_attr = __ATTR_RO(delegate);
 static ssize_t features_show(struct kobject *kobj, struct kobj_attribute *attr,
 			     char *buf)
 {
-	return snprintf(buf, PAGE_SIZE, "nsdelegate\nmemory_localevents\n");
+	return snprintf(buf, PAGE_SIZE,
+			"nsdelegate\n"
+			"memory_localevents\n"
+			"memory_recursiveprot\n");
 }
 static struct kobj_attribute cgroup_features_attr = __ATTR_RO(features);
 
diff --git a/kernel/fork.c b/kernel/fork.c
index 25f38a84dbfd..ba122d6f5127 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -281,7 +281,7 @@ static inline void free_thread_stack(struct task_struct *tsk)
 					     MEMCG_KERNEL_STACK_KB,
 					     -(int)(PAGE_SIZE / 1024));
 
-			memcg_kmem_uncharge(vm->pages[i], 0);
+			memcg_kmem_uncharge_page(vm->pages[i], 0);
 		}
 
 		for (i = 0; i < NR_CACHED_STACKS; i++) {
@@ -413,12 +413,13 @@ static int memcg_charge_kernel_stack(struct task_struct *tsk)
 
 		for (i = 0; i < THREAD_SIZE / PAGE_SIZE; i++) {
 			/*
-			 * If memcg_kmem_charge() fails, page->mem_cgroup
-			 * pointer is NULL, and both memcg_kmem_uncharge()
+			 * If memcg_kmem_charge_page() fails, page->mem_cgroup
+			 * pointer is NULL, and both memcg_kmem_uncharge_page()
 			 * and mod_memcg_page_state() in free_thread_stack()
 			 * will ignore this page. So it's safe.
 			 */
-			ret = memcg_kmem_charge(vm->pages[i], GFP_KERNEL, 0);
+			ret = memcg_kmem_charge_page(vm->pages[i], GFP_KERNEL,
+						     0);
 			if (ret)
 				return ret;
 
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 94638f695e60..8a176d8727a3 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -212,6 +212,11 @@ static int proc_do_cad_pid(struct ctl_table *table, int write,
 		  void __user *buffer, size_t *lenp, loff_t *ppos);
 static int proc_taint(struct ctl_table *table, int write,
 			       void __user *buffer, size_t *lenp, loff_t *ppos);
+#ifdef CONFIG_COMPACTION
+static int proc_dointvec_minmax_warn_RT_change(struct ctl_table *table,
+					       int write, void __user *buffer,
+					       size_t *lenp, loff_t *ppos);
+#endif
 #endif
 
 #ifdef CONFIG_PRINTK
@@ -1467,7 +1472,7 @@ static struct ctl_table vm_table[] = {
 		.data		= &sysctl_compact_unevictable_allowed,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
+		.proc_handler	= proc_dointvec_minmax_warn_RT_change,
 		.extra1		= SYSCTL_ZERO,
 		.extra2		= SYSCTL_ONE,
 	},
@@ -2555,6 +2560,28 @@ int proc_dointvec(struct ctl_table *table, int write,
 	return do_proc_dointvec(table, write, buffer, lenp, ppos, NULL, NULL);
 }
 
+#ifdef CONFIG_COMPACTION
+static int proc_dointvec_minmax_warn_RT_change(struct ctl_table *table,
+					       int write, void __user *buffer,
+					       size_t *lenp, loff_t *ppos)
+{
+	int ret, old;
+
+	if (!IS_ENABLED(CONFIG_PREEMPT_RT) || !write)
+		return proc_dointvec_minmax(table, write, buffer, lenp, ppos);
+
+	old = *(int *)table->data;
+	ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
+	if (ret)
+		return ret;
+	if (old != *(int *)table->data)
+		pr_warn_once("sysctl attribute %s changed by %s[%d]\n",
+			     table->procname, current->comm,
+			     task_pid_nr(current));
+	return ret;
+}
+#endif
+
 /**
  * proc_douintvec - read a vector of unsigned integers
  * @table: the sysctl table