fs: move namespace sysctls and declare fs base directory20211118-sysctl-cleanups-set-04-v2

This moves the namespace sysctls to its own file as part of the
kernel/sysctl.c spring cleaning

Since we have now removed all sysctls for "fs", we now have to
declare it on the filesystem code, we do that using the new helper,
which reduces boiler plate code.

We rename init_fs_shared_sysctls() to init_fs_sysctls() to reflect
that now fs/sysctls.c is taking on the burden of being the first
to register the base directory as well.

Lastly, since init code will load in the order in which we link it
we have to move the sysctl code to be linked in early, so that its
early init routine runs prior to other fs code. This way, other
filesystem code can register their own sysctls using the helpers
after this:

  * register_sysctl_init()
  * register_sysctl()

Signed-off-by: Luis Chamberlain <mcgrof@kernel.org>

5 files changed, 30 insertions, 26 deletions

diff --git a/fs/Makefile b/fs/Makefile
index ea8770d124da2..dab324aea08f2 100644
--- a/fs/Makefile
+++ b/fs/Makefile
@@ -6,6 +6,8 @@
 # Rewritten to use lists instead of if-statements.
 # 
 
+obj-$(CONFIG_SYSCTL)		+= sysctls.o
+
 obj-y :=	open.o read_write.o file_table.o super.o \
 		char_dev.o stat.o exec.o pipe.o namei.o fcntl.o \
 		ioctl.o readdir.o select.o dcache.o inode.o \
@@ -28,7 +30,6 @@ obj-y				+= notify/
 obj-$(CONFIG_EPOLL)		+= eventpoll.o
 obj-y				+= anon_inodes.o
 obj-$(CONFIG_SIGNALFD)		+= signalfd.o
-obj-$(CONFIG_SYSCTL)		+= sysctls.o
 obj-$(CONFIG_TIMERFD)		+= timerfd.o
 obj-$(CONFIG_EVENTFD)		+= eventfd.o
 obj-$(CONFIG_USERFAULTFD)	+= userfaultfd.o
diff --git a/fs/namespace.c b/fs/namespace.c
index 659a8f39c61af..37e6e5a55622d 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -36,7 +36,7 @@
 #include "internal.h"
 
 /* Maximum number of mounts in a mount namespace */
-unsigned int sysctl_mount_max __read_mostly = 100000;
+static unsigned int sysctl_mount_max __read_mostly = 100000;
 
 static unsigned int m_hash_mask __read_mostly;
 static unsigned int m_hash_shift __read_mostly;
@@ -4596,3 +4596,25 @@ const struct proc_ns_operations mntns_operations = {
 	.install	= mntns_install,
 	.owner		= mntns_owner,
 };
+
+#ifdef CONFIG_SYSCTL
+static struct ctl_table fs_namespace_sysctls[] = {
+	{
+		.procname	= "mount-max",
+		.data		= &sysctl_mount_max,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= SYSCTL_ONE,
+	},
+	{ }
+};
+
+static int __init init_fs_namespace_sysctls(void)
+{
+	register_sysctl_init("fs", fs_namespace_sysctls, "namespace_sysctls");
+	return 0;
+}
+early_initcall(init_fs_namespace_sysctls);
+
+#endif /* CONFIG_SYSCTL */
diff --git a/fs/sysctls.c b/fs/sysctls.c
index a757cafba130d..c701273c9432b 100644
--- a/fs/sysctls.c
+++ b/fs/sysctls.c
@@ -29,10 +29,11 @@ static struct ctl_table fs_shared_sysctls[] = {
 	{ }
 };
 
-static int __init init_fs_shared_sysctls(void)
+DECLARE_SYSCTL_BASE(fs, fs_shared_sysctls);
+
+static int __init init_fs_sysctls(void)
 {
-	register_sysctl_init("fs", fs_shared_sysctls, "fs_shared_sysctls");
-	return 0;
+	return register_sysctl_base(fs);
 }
 
-early_initcall(init_fs_shared_sysctls);
+early_initcall(init_fs_sysctls);
diff --git a/include/linux/mount.h b/include/linux/mount.h
index 5d92a7e1a742d..7f18a7555dff7 100644
--- a/include/linux/mount.h
+++ b/include/linux/mount.h
@@ -113,9 +113,6 @@ extern void mnt_set_expiry(struct vfsmount *mnt, struct list_head *expiry_list);
 extern void mark_mounts_for_expiry(struct list_head *mounts);
 
 extern dev_t name_to_dev_t(const char *name);
-
-extern unsigned int sysctl_mount_max;
-
 extern bool path_is_mountpoint(const struct path *path);
 
 extern void kern_unmount_array(struct vfsmount *mnt[], unsigned int num);
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 44254aff413ee..6549a43f620a4 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -2811,18 +2811,6 @@ static struct ctl_table vm_table[] = {
 	{ }
 };
 
-static struct ctl_table fs_table[] = {
-	{
-		.procname	= "mount-max",
-		.data		= &sysctl_mount_max,
-		.maxlen		= sizeof(unsigned int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= SYSCTL_ONE,
-	},
-	{ }
-};
-
 static struct ctl_table debug_table[] = {
 #ifdef CONFIG_SYSCTL_EXCEPTION_TRACE
 	{
@@ -2863,11 +2851,6 @@ static struct ctl_table sysctl_base_table[] = {
 		.child		= vm_table,
 	},
 	{
-		.procname	= "fs",
-		.mode		= 0555,
-		.child		= fs_table,
-	},
-	{
 		.procname	= "debug",
 		.mode		= 0555,
 		.child		= debug_table,