Merge branch 'sysctl-next' of git://git.kernel.org/pub/scm/linux/kernel/git/mcgrof/linux.git

29 files changed, 247 insertions, 447 deletions

diff --git a/arch/arm/kernel/isa.c b/arch/arm/kernel/isa.c
index d8a509c5d5bd..20218876bef2 100644
--- a/arch/arm/kernel/isa.c
+++ b/arch/arm/kernel/isa.c
@@ -40,27 +40,11 @@ static struct ctl_table ctl_isa_vars[4] = {
 
 static struct ctl_table_header *isa_sysctl_header;
 
-static struct ctl_table ctl_isa[2] = {
-	{
-		.procname	= "isa",
-		.mode		= 0555,
-		.child		= ctl_isa_vars,
-	}, {}
-};
-
-static struct ctl_table ctl_bus[2] = {
-	{
-		.procname	= "bus",
-		.mode		= 0555,
-		.child		= ctl_isa,
-	}, {}
-};
-
 void __init
 register_isa_ports(unsigned int membase, unsigned int portbase, unsigned int portshift)
 {
 	isa_membase = membase;
 	isa_portbase = portbase;
 	isa_portshift = portshift;
-	isa_sysctl_header = register_sysctl_table(ctl_bus);
+	isa_sysctl_header = register_sysctl("bus/isa", ctl_isa_vars);
 }
diff --git a/arch/csky/abiv1/alignment.c b/arch/csky/abiv1/alignment.c
index 2df115d0e210..b60259daed1b 100644
--- a/arch/csky/abiv1/alignment.c
+++ b/arch/csky/abiv1/alignment.c
@@ -332,22 +332,9 @@ static struct ctl_table alignment_tbl[5] = {
 	{}
 };
 
-static struct ctl_table sysctl_table[2] = {
-	{
-	 .procname = "csky_alignment",
-	 .mode = 0555,
-	 .child = alignment_tbl},
-	{}
-};
-
-static struct ctl_path sysctl_path[2] = {
-	{.procname = "csky"},
-	{}
-};
-
 static int __init csky_alignment_init(void)
 {
-	register_sysctl_paths(sysctl_path, sysctl_table);
+	register_sysctl_init("csky/csky_alignment", alignment_tbl);
 	return 0;
 }
 
diff --git a/arch/ia64/kernel/crash.c b/arch/ia64/kernel/crash.c
index 76730f34685c..88b3ce3e66cd 100644
--- a/arch/ia64/kernel/crash.c
+++ b/arch/ia64/kernel/crash.c
@@ -234,15 +234,6 @@ static struct ctl_table kdump_ctl_table[] = {
 	},
 	{ }
 };
-
-static struct ctl_table sys_table[] = {
-	{
-	  .procname = "kernel",
-	  .mode = 0555,
-	  .child = kdump_ctl_table,
-	},
-	{ }
-};
 #endif
 
 static int
@@ -257,7 +248,7 @@ machine_crash_setup(void)
 	if((ret = register_die_notifier(&kdump_init_notifier_nb)) != 0)
 		return ret;
 #ifdef CONFIG_SYSCTL
-	register_sysctl_table(sys_table);
+	register_sysctl("kernel", kdump_ctl_table);
 #endif
 	return 0;
 }
diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
index ad4e4896086a..9a63a0d9f596 100644
--- a/drivers/hv/vmbus_drv.c
+++ b/drivers/hv/vmbus_drv.c
@@ -1462,15 +1462,6 @@ static struct ctl_table hv_ctl_table[] = {
 	{}
 };
 
-static struct ctl_table hv_root_table[] = {
-	{
-		.procname	= "kernel",
-		.mode		= 0555,
-		.child		= hv_ctl_table
-	},
-	{}
-};
-
 /*
  * vmbus_bus_init -Main vmbus driver initialization routine.
  *
@@ -1549,7 +1540,7 @@ static int vmbus_bus_init(void)
 		 * message recording won't be available in isolated
 		 * guests should the following registration fail.
 		 */
-		hv_ctl_table_hdr = register_sysctl_table(hv_root_table);
+		hv_ctl_table_hdr = register_sysctl("kernel", hv_ctl_table);
 		if (!hv_ctl_table_hdr)
 			pr_err("Hyper-V: sysctl table register error");
 
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 13321dbb5fbc..9bc05f451d42 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -322,26 +322,6 @@ static struct ctl_table raid_table[] = {
 	{ }
 };
 
-static struct ctl_table raid_dir_table[] = {
-	{
-		.procname	= "raid",
-		.maxlen		= 0,
-		.mode		= S_IRUGO|S_IXUGO,
-		.child		= raid_table,
-	},
-	{ }
-};
-
-static struct ctl_table raid_root_table[] = {
-	{
-		.procname	= "dev",
-		.maxlen		= 0,
-		.mode		= 0555,
-		.child		= raid_dir_table,
-	},
-	{  }
-};
-
 static int start_readonly;
 
 /*
@@ -9650,7 +9630,7 @@ static int __init md_init(void)
 	mdp_major = ret;
 
 	register_reboot_notifier(&md_notifier);
-	raid_table_header = register_sysctl_table(raid_root_table);
+	raid_table_header = register_sysctl("dev/raid", raid_table);
 
 	md_geninit();
 	return 0;
diff --git a/drivers/scsi/scsi_sysctl.c b/drivers/scsi/scsi_sysctl.c
index 7259704a7f52..7f0914ea168f 100644
--- a/drivers/scsi/scsi_sysctl.c
+++ b/drivers/scsi/scsi_sysctl.c
@@ -21,25 +21,11 @@ static struct ctl_table scsi_table[] = {
 	{ }
 };
 
-static struct ctl_table scsi_dir_table[] = {
-	{ .procname	= "scsi",
-	  .mode		= 0555,
-	  .child	= scsi_table },
-	{ }
-};
-
-static struct ctl_table scsi_root_table[] = {
-	{ .procname	= "dev",
-	  .mode		= 0555,
-	  .child	= scsi_dir_table },
-	{ }
-};
-
 static struct ctl_table_header *scsi_table_header;
 
 int __init scsi_init_sysctl(void)
 {
-	scsi_table_header = register_sysctl_table(scsi_root_table);
+	scsi_table_header = register_sysctl("dev/scsi", scsi_table);
 	if (!scsi_table_header)
 		return -ENOMEM;
 	return 0;
diff --git a/drivers/xen/balloon.c b/drivers/xen/balloon.c
index 617a7f4f07a8..586a1673459e 100644
--- a/drivers/xen/balloon.c
+++ b/drivers/xen/balloon.c
@@ -97,24 +97,6 @@ static struct ctl_table balloon_table[] = {
 	{ }
 };
 
-static struct ctl_table balloon_root[] = {
-	{
-		.procname	= "balloon",
-		.mode		= 0555,
-		.child		= balloon_table,
-	},
-	{ }
-};
-
-static struct ctl_table xen_root[] = {
-	{
-		.procname	= "xen",
-		.mode		= 0555,
-		.child		= balloon_root,
-	},
-	{ }
-};
-
 #else
 #define xen_hotplug_unpopulated 0
 #endif
@@ -747,7 +729,7 @@ static int __init balloon_init(void)
 #ifdef CONFIG_XEN_BALLOON_MEMORY_HOTPLUG
 	set_online_page_callback(&xen_online_page);
 	register_memory_notifier(&xen_memory_nb);
-	register_sysctl_table(xen_root);
+	register_sysctl_init("xen/balloon", balloon_table);
 #endif
 
 	balloon_add_regions();
diff --git a/fs/cachefiles/error_inject.c b/fs/cachefiles/error_inject.c
index 58f8aec964e4..18de8a876b02 100644
--- a/fs/cachefiles/error_inject.c
+++ b/fs/cachefiles/error_inject.c
@@ -22,18 +22,9 @@ static struct ctl_table cachefiles_sysctls[] = {
 	{}
 };
 
-static struct ctl_table cachefiles_sysctls_root[] = {
-	{
-		.procname	= "cachefiles",
-		.mode		= 0555,
-		.child		= cachefiles_sysctls,
-	},
-	{}
-};
-
 int __init cachefiles_register_error_injection(void)
 {
-	cachefiles_sysctl = register_sysctl_table(cachefiles_sysctls_root);
+	cachefiles_sysctl = register_sysctl("cachefiles", cachefiles_sysctls);
 	if (!cachefiles_sysctl)
 		return -ENOMEM;
 	return 0;
diff --git a/fs/coda/sysctl.c b/fs/coda/sysctl.c
index fda3b702b1c5..a247c14aaab7 100644
--- a/fs/coda/sysctl.c
+++ b/fs/coda/sysctl.c
@@ -39,19 +39,10 @@ static struct ctl_table coda_table[] = {
 	{}
 };
 
-static struct ctl_table fs_table[] = {
-	{
-		.procname	= "coda",
-		.mode		= 0555,
-		.child		= coda_table
-	},
-	{}
-};
-
 void coda_sysctl_init(void)
 {
 	if ( !fs_table_header )
-		fs_table_header = register_sysctl_table(fs_table);
+		fs_table_header = register_sysctl("coda", coda_table);
 }
 
 void coda_sysctl_clean(void)
diff --git a/fs/lockd/svc.c b/fs/lockd/svc.c
index 9a47303b2cba..bb94949bc223 100644
--- a/fs/lockd/svc.c
+++ b/fs/lockd/svc.c
@@ -510,24 +510,6 @@ static struct ctl_table nlm_sysctls[] = {
 	{ }
 };
 
-static struct ctl_table nlm_sysctl_dir[] = {
-	{
-		.procname	= "nfs",
-		.mode		= 0555,
-		.child		= nlm_sysctls,
-	},
-	{ }
-};
-
-static struct ctl_table nlm_sysctl_root[] = {
-	{
-		.procname	= "fs",
-		.mode		= 0555,
-		.child		= nlm_sysctl_dir,
-	},
-	{ }
-};
-
 #endif	/* CONFIG_SYSCTL */
 
 /*
@@ -644,7 +626,7 @@ static int __init init_nlm(void)
 
 #ifdef CONFIG_SYSCTL
 	err = -ENOMEM;
-	nlm_sysctl_table = register_sysctl_table(nlm_sysctl_root);
+	nlm_sysctl_table = register_sysctl("fs/nfs", nlm_sysctls);
 	if (nlm_sysctl_table == NULL)
 		goto err_sysctl;
 #endif
diff --git a/fs/nfs/nfs4sysctl.c b/fs/nfs/nfs4sysctl.c
index c394e4447100..e776200e9a11 100644
--- a/fs/nfs/nfs4sysctl.c
+++ b/fs/nfs/nfs4sysctl.c
@@ -37,27 +37,10 @@ static struct ctl_table nfs4_cb_sysctls[] = {
 	{ }
 };
 
-static struct ctl_table nfs4_cb_sysctl_dir[] = {
-	{
-		.procname = "nfs",
-		.mode = 0555,
-		.child = nfs4_cb_sysctls,
-	},
-	{ }
-};
-
-static struct ctl_table nfs4_cb_sysctl_root[] = {
-	{
-		.procname = "fs",
-		.mode = 0555,
-		.child = nfs4_cb_sysctl_dir,
-	},
-	{ }
-};
-
 int nfs4_register_sysctl(void)
 {
-	nfs4_callback_sysctl_table = register_sysctl_table(nfs4_cb_sysctl_root);
+	nfs4_callback_sysctl_table = register_sysctl("fs/nfs",
+						     nfs4_cb_sysctls);
 	if (nfs4_callback_sysctl_table == NULL)
 		return -ENOMEM;
 	return 0;
diff --git a/fs/nfs/sysctl.c b/fs/nfs/sysctl.c
index 7aea195ddb35..f39e2089bc4c 100644
--- a/fs/nfs/sysctl.c
+++ b/fs/nfs/sysctl.c
@@ -32,27 +32,9 @@ static struct ctl_table nfs_cb_sysctls[] = {
 	{ }
 };
 
-static struct ctl_table nfs_cb_sysctl_dir[] = {
-	{
-		.procname = "nfs",
-		.mode = 0555,
-		.child = nfs_cb_sysctls,
-	},
-	{ }
-};
-
-static struct ctl_table nfs_cb_sysctl_root[] = {
-	{
-		.procname = "fs",
-		.mode = 0555,
-		.child = nfs_cb_sysctl_dir,
-	},
-	{ }
-};
-
 int nfs_register_sysctl(void)
 {
-	nfs_callback_sysctl_table = register_sysctl_table(nfs_cb_sysctl_root);
+	nfs_callback_sysctl_table = register_sysctl("fs/nfs", nfs_cb_sysctls);
 	if (nfs_callback_sysctl_table == NULL)
 		return -ENOMEM;
 	return 0;
diff --git a/fs/ntfs/sysctl.c b/fs/ntfs/sysctl.c
index a030d00af90c..174fe536a1c0 100644
--- a/fs/ntfs/sysctl.c
+++ b/fs/ntfs/sysctl.c
@@ -31,16 +31,6 @@ static struct ctl_table ntfs_sysctls[] = {
 	{}
 };
 
-/* Define the parent directory /proc/sys/fs. */
-static struct ctl_table sysctls_root[] = {
-	{
-		.procname	= "fs",
-		.mode		= 0555,
-		.child		= ntfs_sysctls
-	},
-	{}
-};
-
 /* Storage for the sysctls header. */
 static struct ctl_table_header *sysctls_root_table;
 
@@ -54,7 +44,7 @@ int ntfs_sysctl(int add)
 {
 	if (add) {
 		BUG_ON(sysctls_root_table);
-		sysctls_root_table = register_sysctl_table(sysctls_root);
+		sysctls_root_table = register_sysctl("fs", ntfs_sysctls);
 		if (!sysctls_root_table)
 			return -ENOMEM;
 	} else {
diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c
index ff88a5da6840..bfe0473bb61f 100644
--- a/fs/proc/proc_sysctl.c
+++ b/fs/proc/proc_sysctl.c
@@ -1282,11 +1282,43 @@ out:
 	return err;
 }
 
+/* Find the directory for the ctl_table. If one is not found create it. */
+static struct ctl_dir *sysctl_mkdir_p(struct ctl_dir *dir, const char *path)
+{
+	const char *name, *nextname;
+
+	for (name = path; name; name = nextname) {
+		int namelen;
+		nextname = strchr(name, '/');
+		if (nextname) {
+			namelen = nextname - name;
+			nextname++;
+		} else {
+			namelen = strlen(name);
+		}
+		if (namelen == 0)
+			continue;
+
+		/*
+		 * namelen ensures if name is "foo/bar/yay" only foo is
+		 * registered first. We traverse as if using mkdir -p and
+		 * return a ctl_dir for the last directory entry.
+		 */
+		dir = get_subdir(dir, name, namelen);
+		if (IS_ERR(dir))
+			break;
+	}
+	return dir;
+}
+
 /**
  * __register_sysctl_table - register a leaf sysctl table
  * @set: Sysctl tree to register on
  * @path: The path to the directory the sysctl table is in.
- * @table: the top-level table structure
+ * @table: the top-level table structure without any child. This table
+ * 	 should not be free'd after registration. So it should not be
+ * 	 used on stack. It can either be a global or dynamically allocated
+ * 	 by the caller and free'd later after sysctl unregistration.
  *
  * Register a sysctl table hierarchy. @table should be a filled in ctl_table
  * array. A completely 0 filled entry terminates the table.
@@ -1307,9 +1339,12 @@ out:
  * proc_handler - the text handler routine (described below)
  *
  * extra1, extra2 - extra pointers usable by the proc handler routines
+ * XXX: we should eventually modify these to use long min / max [0]
+ * [0] https://lkml.kernel.org/87zgpte9o4.fsf@email.froward.int.ebiederm.org
  *
  * Leaf nodes in the sysctl tree will be represented by a single file
- * under /proc; non-leaf nodes will be represented by directories.
+ * under /proc; non-leaf nodes (where child is not NULL) are not allowed,
+ * sysctl_check_table() verifies this.
  *
  * There must be a proc_handler routine for any terminal nodes.
  * Several default handlers are available to cover common cases -
@@ -1330,7 +1365,6 @@ struct ctl_table_header *__register_sysctl_table(
 {
 	struct ctl_table_root *root = set->dir.header.root;
 	struct ctl_table_header *header;
-	const char *name, *nextname;
 	struct ctl_dir *dir;
 	struct ctl_table *entry;
 	struct ctl_node *node;
@@ -1351,28 +1385,13 @@ struct ctl_table_header *__register_sysctl_table(
 
 	spin_lock(&sysctl_lock);
 	dir = &set->dir;
-	/* Reference moved down the diretory tree get_subdir */
+	/* Reference moved down the directory tree get_subdir */
 	dir->header.nreg++;
 	spin_unlock(&sysctl_lock);
 
-	/* Find the directory for the ctl_table */
-	for (name = path; name; name = nextname) {
-		int namelen;
-		nextname = strchr(name, '/');
-		if (nextname) {
-			namelen = nextname - name;
-			nextname++;
-		} else {
-			namelen = strlen(name);
-		}
-		if (namelen == 0)
-			continue;
-
-		dir = get_subdir(dir, name, namelen);
-		if (IS_ERR(dir))
-			goto fail;
-	}
-
+	dir = sysctl_mkdir_p(dir, path);
+	if (IS_ERR(dir))
+		goto fail;
 	spin_lock(&sysctl_lock);
 	if (insert_header(dir, header))
 		goto fail_put_dir_locked;
@@ -1393,8 +1412,15 @@ fail:
 
 /**
  * register_sysctl - register a sysctl table
- * @path: The path to the directory the sysctl table is in.
- * @table: the table structure
+ * @path: The path to the directory the sysctl table is in. If the path
+ * 	doesn't exist we will create it for you.
+ * @table: the table structure. The calller must ensure the life of the @table
+ * 	will be kept during the lifetime use of the syctl. It must not be freed
+ * 	until unregister_sysctl_table() is called with the given returned table
+ * 	with this registration. If your code is non modular then you don't need
+ * 	to call unregister_sysctl_table() and can instead use something like
+ * 	register_sysctl_init() which does not care for the result of the syctl
+ * 	registration.
  *
  * Register a sysctl table. @table should be a filled in ctl_table
  * array. A completely 0 filled entry terminates the table.
@@ -1410,8 +1436,11 @@ EXPORT_SYMBOL(register_sysctl);
 
 /**
  * __register_sysctl_init() - register sysctl table to path
- * @path: path name for sysctl base
- * @table: This is the sysctl table that needs to be registered to the path
+ * @path: path name for sysctl base. If that path doesn't exist we will create
+ * 	it for you.
+ * @table: This is the sysctl table that needs to be registered to the path.
+ * 	The caller must ensure the life of the @table will be kept during the
+ * 	lifetime use of the sysctl.
  * @table_name: The name of sysctl table, only used for log printing when
  *              registration fails
  *
@@ -1423,10 +1452,7 @@ EXPORT_SYMBOL(register_sysctl);
  * register_sysctl() failing on init are extremely low, and so for both reasons
  * this function does not return any error as it is used by initialization code.
  *
- * Context: Can only be called after your respective sysctl base path has been
- * registered. So for instance, most base directories are registered early on
- * init before init levels are processed through proc_sys_init() and
- * sysctl_init_bases().
+ * Context: if your base directory does not exist it will be created for you.
  */
 void __init __register_sysctl_init(const char *path, struct ctl_table *table,
 				 const char *table_name)
@@ -1556,6 +1582,7 @@ out:
  *
  * Register a sysctl table hierarchy. @table should be a filled in ctl_table
  * array. A completely 0 filled entry terminates the table.
+ * We are slowly deprecating this call so avoid its use.
  *
  * See __register_sysctl_table for more details.
  */
@@ -1627,6 +1654,7 @@ err_register_leaves:
  *
  * Register a sysctl table hierarchy. @table should be a filled in ctl_table
  * array. A completely 0 filled entry terminates the table.
+ * We are slowly deprecating this caller so avoid future uses of it.
  *
  * See __register_sysctl_paths for more details.
  */
diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index 8395605790f6..359c8d1e590d 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -32,7 +32,22 @@
 #include <linux/swapops.h>
 #include <linux/miscdevice.h>
 
-int sysctl_unprivileged_userfaultfd __read_mostly;
+static int sysctl_unprivileged_userfaultfd __read_mostly;
+
+#ifdef CONFIG_SYSCTL
+static struct ctl_table vm_userfaultfd_table[] = {
+	{
+		.procname	= "unprivileged_userfaultfd",
+		.data		= &sysctl_unprivileged_userfaultfd,
+		.maxlen		= sizeof(sysctl_unprivileged_userfaultfd),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= SYSCTL_ONE,
+	},
+	{ }
+};
+#endif
 
 static struct kmem_cache *userfaultfd_ctx_cachep __read_mostly;
 
@@ -2201,6 +2216,9 @@ static int __init userfaultfd_init(void)
 						0,
 						SLAB_HWCACHE_ALIGN|SLAB_PANIC,
 						init_once_userfaultfd_ctx);
+#ifdef CONFIG_SYSCTL
+	register_sysctl_init("vm", vm_userfaultfd_table);
+#endif
 	return 0;
 }
 __initcall(userfaultfd_init);
diff --git a/fs/xfs/xfs_sysctl.c b/fs/xfs/xfs_sysctl.c
index 546a6cd96729..fade33735393 100644
--- a/fs/xfs/xfs_sysctl.c
+++ b/fs/xfs/xfs_sysctl.c
@@ -210,28 +210,10 @@ static struct ctl_table xfs_table[] = {
 	{}
 };
 
-static struct ctl_table xfs_dir_table[] = {
-	{
-		.procname	= "xfs",
-		.mode		= 0555,
-		.child		= xfs_table
-	},
-	{}
-};
-
-static struct ctl_table xfs_root_table[] = {
-	{
-		.procname	= "fs",
-		.mode		= 0555,
-		.child		= xfs_dir_table
-	},
-	{}
-};
-
 int
 xfs_sysctl_register(void)
 {
-	xfs_table_header = register_sysctl_table(xfs_root_table);
+	xfs_table_header = register_sysctl("fs/xfs", xfs_table);
 	if (!xfs_table_header)
 		return -ENOMEM;
 	return 0;
diff --git a/include/linux/compaction.h b/include/linux/compaction.h
index 52a9ff65faee..a6e512cfb670 100644
--- a/include/linux/compaction.h
+++ b/include/linux/compaction.h
@@ -81,13 +81,6 @@ static inline unsigned long compact_gap(unsigned int order)
 }
 
 #ifdef CONFIG_COMPACTION
-extern unsigned int sysctl_compaction_proactiveness;
-extern int sysctl_compaction_handler(struct ctl_table *table, int write,
-			void *buffer, size_t *length, loff_t *ppos);
-extern int compaction_proactiveness_sysctl_handler(struct ctl_table *table,
-		int write, void *buffer, size_t *length, loff_t *ppos);
-extern int sysctl_extfrag_threshold;
-extern int sysctl_compact_unevictable_allowed;
 
 extern unsigned int extfrag_for_order(struct zone *zone, unsigned int order);
 extern int fragmentation_index(struct zone *zone, unsigned int order);
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 28703fe22386..13e8504457a1 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -124,14 +124,6 @@ void hugepage_put_subpool(struct hugepage_subpool *spool);
 
 void hugetlb_dup_vma_private(struct vm_area_struct *vma);
 void clear_vma_resv_huge_pages(struct vm_area_struct *vma);
-int hugetlb_sysctl_handler(struct ctl_table *, int, void *, size_t *, loff_t *);
-int hugetlb_overcommit_handler(struct ctl_table *, int, void *, size_t *,
-		loff_t *);
-int hugetlb_treat_movable_handler(struct ctl_table *, int, void *, size_t *,
-		loff_t *);
-int hugetlb_mempolicy_sysctl_handler(struct ctl_table *, int, void *, size_t *,
-		loff_t *);
-
 int move_hugetlb_page_tables(struct vm_area_struct *vma,
 			     struct vm_area_struct *new_vma,
 			     unsigned long old_addr, unsigned long new_addr,
diff --git a/include/linux/mm.h b/include/linux/mm.h
index daa25506b853..02e3ec3881e5 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -3632,8 +3632,6 @@ int mf_dax_kill_procs(struct address_space *mapping, pgoff_t index,
 extern int memory_failure(unsigned long pfn, int flags);
 extern void memory_failure_queue_kick(int cpu);
 extern int unpoison_memory(unsigned long pfn);
-extern int sysctl_memory_failure_early_kill;
-extern int sysctl_memory_failure_recovery;
 extern void shake_page(struct page *p);
 extern atomic_long_t num_poisoned_pages __read_mostly;
 extern int soft_offline_page(unsigned long pfn, int flags);
diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h
index a2c53e98dfd6..d78b01524349 100644
--- a/include/linux/userfaultfd_k.h
+++ b/include/linux/userfaultfd_k.h
@@ -36,8 +36,6 @@
 #define UFFD_SHARED_FCNTL_FLAGS (O_CLOEXEC | O_NONBLOCK)
 #define UFFD_FLAGS_SET (EFD_SHARED_FCNTL_FLAGS)
 
-extern int sysctl_unprivileged_userfaultfd;
-
 extern vm_fault_t handle_userfault(struct vm_fault *vmf, unsigned long reason);
 
 /* A combined operation mode + behavior flags. */
diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index cebf26445f9e..d3e584065c7f 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -2368,12 +2368,6 @@ static int seccomp_actions_logged_handler(struct ctl_table *ro_table, int write,
 	return ret;
 }
 
-static struct ctl_path seccomp_sysctl_path[] = {
-	{ .procname = "kernel", },
-	{ .procname = "seccomp", },
-	{ }
-};
-
 static struct ctl_table seccomp_sysctl_table[] = {
 	{
 		.procname	= "actions_avail",
@@ -2392,14 +2386,7 @@ static struct ctl_table seccomp_sysctl_table[] = {
 
 static int __init seccomp_sysctl_init(void)
 {
-	struct ctl_table_header *hdr;
-
-	hdr = register_sysctl_paths(seccomp_sysctl_path, seccomp_sysctl_table);
-	if (!hdr)
-		pr_warn("sysctl registration failed\n");
-	else
-		kmemleak_not_leak(hdr);
-
+	register_sysctl_init("kernel/seccomp", seccomp_sysctl_table);
 	return 0;
 }
 
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 1c240d2c99bc..bfe53e835524 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -42,7 +42,6 @@
 #include <linux/highuid.h>
 #include <linux/writeback.h>
 #include <linux/ratelimit.h>
-#include <linux/compaction.h>
 #include <linux/hugetlb.h>
 #include <linux/initrd.h>
 #include <linux/key.h>
@@ -746,27 +745,6 @@ int proc_dointvec(struct ctl_table *table, int write, void *buffer,
 	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 *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
@@ -2141,38 +2119,6 @@ static struct ctl_table vm_table[] = {
 		.extra2		= SYSCTL_ONE,
 	},
 #endif
-#ifdef CONFIG_HUGETLB_PAGE
-	{
-		.procname	= "nr_hugepages",
-		.data		= NULL,
-		.maxlen		= sizeof(unsigned long),
-		.mode		= 0644,
-		.proc_handler	= hugetlb_sysctl_handler,
-	},
-#ifdef CONFIG_NUMA
-	{
-		.procname       = "nr_hugepages_mempolicy",
-		.data           = NULL,
-		.maxlen         = sizeof(unsigned long),
-		.mode           = 0644,
-		.proc_handler   = &hugetlb_mempolicy_sysctl_handler,
-	},
-#endif
-	 {
-		.procname	= "hugetlb_shm_group",
-		.data		= &sysctl_hugetlb_shm_group,
-		.maxlen		= sizeof(gid_t),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
-	 },
-	{
-		.procname	= "nr_overcommit_hugepages",
-		.data		= NULL,
-		.maxlen		= sizeof(unsigned long),
-		.mode		= 0644,
-		.proc_handler	= hugetlb_overcommit_handler,
-	},
-#endif
 	{
 		.procname	= "lowmem_reserve_ratio",
 		.data		= &sysctl_lowmem_reserve_ratio,
@@ -2189,43 +2135,6 @@ static struct ctl_table vm_table[] = {
 		.extra1		= SYSCTL_ONE,
 		.extra2		= SYSCTL_FOUR,
 	},
-#ifdef CONFIG_COMPACTION
-	{
-		.procname	= "compact_memory",
-		.data		= NULL,
-		.maxlen		= sizeof(int),
-		.mode		= 0200,
-		.proc_handler	= sysctl_compaction_handler,
-	},
-	{
-		.procname	= "compaction_proactiveness",
-		.data		= &sysctl_compaction_proactiveness,
-		.maxlen		= sizeof(sysctl_compaction_proactiveness),
-		.mode		= 0644,
-		.proc_handler	= compaction_proactiveness_sysctl_handler,
-		.extra1		= SYSCTL_ZERO,
-		.extra2		= SYSCTL_ONE_HUNDRED,
-	},
-	{
-		.procname	= "extfrag_threshold",
-		.data		= &sysctl_extfrag_threshold,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= SYSCTL_ZERO,
-		.extra2		= SYSCTL_ONE_THOUSAND,
-	},
-	{
-		.procname	= "compact_unevictable_allowed",
-		.data		= &sysctl_compact_unevictable_allowed,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec_minmax_warn_RT_change,
-		.extra1		= SYSCTL_ZERO,
-		.extra2		= SYSCTL_ONE,
-	},
-
-#endif /* CONFIG_COMPACTION */
 	{
 		.procname	= "min_free_kbytes",
 		.data		= &min_free_kbytes,
@@ -2383,26 +2292,6 @@ static struct ctl_table vm_table[] = {
 		.extra1		= SYSCTL_ZERO,
 	},
 #endif
-#ifdef CONFIG_MEMORY_FAILURE
-	{
-		.procname	= "memory_failure_early_kill",
-		.data		= &sysctl_memory_failure_early_kill,
-		.maxlen		= sizeof(sysctl_memory_failure_early_kill),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= SYSCTL_ZERO,
-		.extra2		= SYSCTL_ONE,
-	},
-	{
-		.procname	= "memory_failure_recovery",
-		.data		= &sysctl_memory_failure_recovery,
-		.maxlen		= sizeof(sysctl_memory_failure_recovery),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= SYSCTL_ZERO,
-		.extra2		= SYSCTL_ONE,
-	},
-#endif
 	{
 		.procname	= "user_reserve_kbytes",
 		.data		= &sysctl_user_reserve_kbytes,
@@ -2439,17 +2328,6 @@ static struct ctl_table vm_table[] = {
 		.extra2		= (void *)&mmap_rnd_compat_bits_max,
 	},
 #endif
-#ifdef CONFIG_USERFAULTFD
-	{
-		.procname	= "unprivileged_userfaultfd",
-		.data		= &sysctl_unprivileged_userfaultfd,
-		.maxlen		= sizeof(sysctl_unprivileged_userfaultfd),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= SYSCTL_ZERO,
-		.extra2		= SYSCTL_ONE,
-	},
-#endif
 	{ }
 };
 
diff --git a/kernel/utsname_sysctl.c b/kernel/utsname_sysctl.c
index f50398cb790d..019e3a1566cf 100644
--- a/kernel/utsname_sysctl.c
+++ b/kernel/utsname_sysctl.c
@@ -123,15 +123,6 @@ static struct ctl_table uts_kern_table[] = {
 	{}
 };
 
-static struct ctl_table uts_root_table[] = {
-	{
-		.procname	= "kernel",
-		.mode		= 0555,
-		.child		= uts_kern_table,
-	},
-	{}
-};
-
 #ifdef CONFIG_PROC_SYSCTL
 /*
  * Notify userspace about a change in a certain entry of uts_kern_table,
@@ -147,7 +138,7 @@ void uts_proc_notify(enum uts_proc proc)
 
 static int __init utsname_sysctl_init(void)
 {
-	register_sysctl_table(uts_root_table);
+	register_sysctl("kernel", uts_kern_table);
 	return 0;
 }
 
diff --git a/mm/compaction.c b/mm/compaction.c
index e689d66cedf4..c8bcdea15f5f 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -1728,7 +1728,14 @@ typedef enum {
  * Allow userspace to control policy on scanning the unevictable LRU for
  * compactable pages.
  */
-int sysctl_compact_unevictable_allowed __read_mostly = CONFIG_COMPACT_UNEVICTABLE_DEFAULT;
+static int sysctl_compact_unevictable_allowed __read_mostly = CONFIG_COMPACT_UNEVICTABLE_DEFAULT;
+/*
+ * Tunable for proactive compaction. It determines how
+ * aggressively the kernel should compact memory in the
+ * background. It takes values in the range [0, 100].
+ */
+static unsigned int __read_mostly sysctl_compaction_proactiveness = 20;
+static int sysctl_extfrag_threshold = 500;
 
 static inline void
 update_fast_start_pfn(struct compact_control *cc, unsigned long pfn)
@@ -2584,8 +2591,6 @@ static enum compact_result compact_zone_order(struct zone *zone, int order,
 	return ret;
 }
 
-int sysctl_extfrag_threshold = 500;
-
 /**
  * try_to_compact_pages - Direct compact to satisfy a high-order allocation
  * @gfp_mask: The GFP mask of the current allocation
@@ -2742,14 +2747,7 @@ static void compact_nodes(void)
 		compact_node(nid);
 }
 
-/*
- * Tunable for proactive compaction. It determines how
- * aggressively the kernel should compact memory in the
- * background. It takes values in the range [0, 100].
- */
-unsigned int __read_mostly sysctl_compaction_proactiveness = 20;
-
-int compaction_proactiveness_sysctl_handler(struct ctl_table *table, int write,
+static int compaction_proactiveness_sysctl_handler(struct ctl_table *table, int write,
 		void *buffer, size_t *length, loff_t *ppos)
 {
 	int rc, nid;
@@ -2779,7 +2777,7 @@ int compaction_proactiveness_sysctl_handler(struct ctl_table *table, int write,
  * This is the entry point for compacting all nodes via
  * /proc/sys/vm/compact_memory
  */
-int sysctl_compaction_handler(struct ctl_table *table, int write,
+static int sysctl_compaction_handler(struct ctl_table *table, int write,
 			void *buffer, size_t *length, loff_t *ppos)
 {
 	if (write)
@@ -3075,6 +3073,63 @@ static int kcompactd_cpu_online(unsigned int cpu)
 	return 0;
 }
 
+static int proc_dointvec_minmax_warn_RT_change(struct ctl_table *table,
+		int write, void *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;
+}
+
+static struct ctl_table vm_compaction[] = {
+	{
+		.procname	= "compact_memory",
+		.data		= NULL,
+		.maxlen		= sizeof(int),
+		.mode		= 0200,
+		.proc_handler	= sysctl_compaction_handler,
+	},
+	{
+		.procname	= "compaction_proactiveness",
+		.data		= &sysctl_compaction_proactiveness,
+		.maxlen		= sizeof(sysctl_compaction_proactiveness),
+		.mode		= 0644,
+		.proc_handler	= compaction_proactiveness_sysctl_handler,
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= SYSCTL_ONE_HUNDRED,
+	},
+	{
+		.procname	= "extfrag_threshold",
+		.data		= &sysctl_extfrag_threshold,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= SYSCTL_ONE_THOUSAND,
+	},
+	{
+		.procname	= "compact_unevictable_allowed",
+		.data		= &sysctl_compact_unevictable_allowed,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax_warn_RT_change,
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= SYSCTL_ONE,
+	},
+	{ }
+};
+
 static int __init kcompactd_init(void)
 {
 	int nid;
@@ -3090,6 +3145,7 @@ static int __init kcompactd_init(void)
 
 	for_each_node_state(nid, N_MEMORY)
 		kcompactd_run(nid);
+	register_sysctl_init("vm", vm_compaction);
 	return 0;
 }
 subsys_initcall(kcompactd_init)
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 870238ccd662..efc443a906fa 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -4206,6 +4206,12 @@ static void __init hugetlb_sysfs_init(void)
 	hugetlb_register_all_nodes();
 }
 
+#ifdef CONFIG_SYSCTL
+static void hugetlb_sysctl_init(void);
+#else
+static inline void hugetlb_sysctl_init(void) { }
+#endif
+
 static int __init hugetlb_init(void)
 {
 	int i;
@@ -4261,6 +4267,7 @@ static int __init hugetlb_init(void)
 
 	hugetlb_sysfs_init();
 	hugetlb_cgroup_file_init();
+	hugetlb_sysctl_init();
 
 #ifdef CONFIG_SMP
 	num_fault_mutexes = roundup_pow_of_two(8 * num_possible_cpus());
@@ -4592,7 +4599,7 @@ out:
 	return ret;
 }
 
-int hugetlb_sysctl_handler(struct ctl_table *table, int write,
+static int hugetlb_sysctl_handler(struct ctl_table *table, int write,
 			  void *buffer, size_t *length, loff_t *ppos)
 {
 
@@ -4601,7 +4608,7 @@ int hugetlb_sysctl_handler(struct ctl_table *table, int write,
 }
 
 #ifdef CONFIG_NUMA
-int hugetlb_mempolicy_sysctl_handler(struct ctl_table *table, int write,
+static int hugetlb_mempolicy_sysctl_handler(struct ctl_table *table, int write,
 			  void *buffer, size_t *length, loff_t *ppos)
 {
 	return hugetlb_sysctl_handler_common(true, table, write,
@@ -4609,7 +4616,7 @@ int hugetlb_mempolicy_sysctl_handler(struct ctl_table *table, int write,
 }
 #endif /* CONFIG_NUMA */
 
-int hugetlb_overcommit_handler(struct ctl_table *table, int write,
+static int hugetlb_overcommit_handler(struct ctl_table *table, int write,
 		void *buffer, size_t *length, loff_t *ppos)
 {
 	struct hstate *h = &default_hstate;
@@ -4638,6 +4645,44 @@ out:
 	return ret;
 }
 
+static struct ctl_table hugetlb_table[] = {
+	{
+		.procname	= "nr_hugepages",
+		.data		= NULL,
+		.maxlen		= sizeof(unsigned long),
+		.mode		= 0644,
+		.proc_handler	= hugetlb_sysctl_handler,
+	},
+#ifdef CONFIG_NUMA
+	{
+		.procname       = "nr_hugepages_mempolicy",
+		.data           = NULL,
+		.maxlen         = sizeof(unsigned long),
+		.mode           = 0644,
+		.proc_handler   = &hugetlb_mempolicy_sysctl_handler,
+	},
+#endif
+	{
+		.procname	= "hugetlb_shm_group",
+		.data		= &sysctl_hugetlb_shm_group,
+		.maxlen		= sizeof(gid_t),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
+	{
+		.procname	= "nr_overcommit_hugepages",
+		.data		= NULL,
+		.maxlen		= sizeof(unsigned long),
+		.mode		= 0644,
+		.proc_handler	= hugetlb_overcommit_handler,
+	},
+	{ }
+};
+
+static void hugetlb_sysctl_init(void)
+{
+	register_sysctl_init("vm", hugetlb_table);
+}
 #endif /* CONFIG_SYSCTL */
 
 void hugetlb_report_meminfo(struct seq_file *m)
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index f761704d27d7..b2377f12f062 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -62,13 +62,14 @@
 #include <linux/page-isolation.h>
 #include <linux/pagewalk.h>
 #include <linux/shmem_fs.h>
+#include <linux/sysctl.h>
 #include "swap.h"
 #include "internal.h"
 #include "ras/ras_event.h"
 
-int sysctl_memory_failure_early_kill __read_mostly = 0;
+static int sysctl_memory_failure_early_kill __read_mostly;
 
-int sysctl_memory_failure_recovery __read_mostly = 1;
+static int sysctl_memory_failure_recovery __read_mostly = 1;
 
 atomic_long_t num_poisoned_pages __read_mostly = ATOMIC_LONG_INIT(0);
 
@@ -122,6 +123,37 @@ const struct attribute_group memory_failure_attr_group = {
 	.attrs = memory_failure_attr,
 };
 
+#ifdef CONFIG_SYSCTL
+static struct ctl_table memory_failure_table[] = {
+	{
+		.procname	= "memory_failure_early_kill",
+		.data		= &sysctl_memory_failure_early_kill,
+		.maxlen		= sizeof(sysctl_memory_failure_early_kill),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= SYSCTL_ONE,
+	},
+	{
+		.procname	= "memory_failure_recovery",
+		.data		= &sysctl_memory_failure_recovery,
+		.maxlen		= sizeof(sysctl_memory_failure_recovery),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= SYSCTL_ONE,
+	},
+	{ }
+};
+
+static int __init memory_failure_sysctl_init(void)
+{
+	register_sysctl_init("vm", memory_failure_table);
+	return 0;
+}
+late_initcall(memory_failure_sysctl_init);
+#endif /* CONFIG_SYSCTL */
+
 /*
  * Return values:
  *   1:   the page is dissolved (if needed) and taken off from buddy,
diff --git a/security/apparmor/lsm.c b/security/apparmor/lsm.c
index cebba4824e60..f431251ffb91 100644
--- a/security/apparmor/lsm.c
+++ b/security/apparmor/lsm.c
@@ -1764,11 +1764,6 @@ static int apparmor_dointvec(struct ctl_table *table, int write,
 	return proc_dointvec(table, write, buffer, lenp, ppos);
 }
 
-static struct ctl_path apparmor_sysctl_path[] = {
-	{ .procname = "kernel", },
-	{ }
-};
-
 static struct ctl_table apparmor_sysctl_table[] = {
 	{
 		.procname       = "unprivileged_userns_apparmor_policy",
@@ -1790,8 +1785,7 @@ static struct ctl_table apparmor_sysctl_table[] = {
 
 static int __init apparmor_init_sysctl(void)
 {
-	return register_sysctl_paths(apparmor_sysctl_path,
-				     apparmor_sysctl_table) ? 0 : -ENOMEM;
+	return register_sysctl("kernel", apparmor_sysctl_table) ? 0 : -ENOMEM;
 }
 #else
 static inline int apparmor_init_sysctl(void)
diff --git a/security/loadpin/loadpin.c b/security/loadpin/loadpin.c
index b9d773f11232..ebae964f7cc9 100644
--- a/security/loadpin/loadpin.c
+++ b/security/loadpin/loadpin.c
@@ -52,12 +52,6 @@ static bool deny_reading_verity_digests;
 #endif
 
 #ifdef CONFIG_SYSCTL
-static struct ctl_path loadpin_sysctl_path[] = {
-	{ .procname = "kernel", },
-	{ .procname = "loadpin", },
-	{ }
-};
-
 static struct ctl_table loadpin_sysctl_table[] = {
 	{
 		.procname       = "enforce",
@@ -262,7 +256,7 @@ static int __init loadpin_init(void)
 		enforce ? "" : "not ");
 	parse_exclude();
 #ifdef CONFIG_SYSCTL
-	if (!register_sysctl_paths(loadpin_sysctl_path, loadpin_sysctl_table))
+	if (!register_sysctl("kernel/loadpin", loadpin_sysctl_table))
 		pr_notice("sysctl registration failed!\n");
 #endif
 	security_add_hooks(loadpin_hooks, ARRAY_SIZE(loadpin_hooks), "loadpin");
diff --git a/security/yama/yama_lsm.c b/security/yama/yama_lsm.c
index 478be269571a..2503cf153d4a 100644
--- a/security/yama/yama_lsm.c
+++ b/security/yama/yama_lsm.c
@@ -447,12 +447,6 @@ static int yama_dointvec_minmax(struct ctl_table *table, int write,
 
 static int max_scope = YAMA_SCOPE_NO_ATTACH;
 
-static struct ctl_path yama_sysctl_path[] = {
-	{ .procname = "kernel", },
-	{ .procname = "yama", },
-	{ }
-};
-
 static struct ctl_table yama_sysctl_table[] = {
 	{
 		.procname       = "ptrace_scope",
@@ -467,7 +461,7 @@ static struct ctl_table yama_sysctl_table[] = {
 };
 static void __init yama_init_sysctl(void)
 {
-	if (!register_sysctl_paths(yama_sysctl_path, yama_sysctl_table))
+	if (!register_sysctl("kernel/yama", yama_sysctl_table))
 		panic("Yama: sysctl registration failed.\n");
 }
 #else