Merge tag 'sysctl-6.4-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/mcgrof/linux

Pull sysctl updates from Luis Chamberlain:
 "This only does a few sysctl moves from the kernel/sysctl.c file, the
  rest of the work has been put towards deprecating two API calls which
  incur recursion and prevent us from simplifying the registration
  process / saving memory per move. Most of the changes have been
  soaking on linux-next since v6.3-rc3.

  I've slowed down the kernel/sysctl.c moves due to Matthew Wilcox's
  feedback that we should see if we could *save* memory with these moves
  instead of incurring more memory. We currently incur more memory since
  when we move a syctl from kernel/sysclt.c out to its own file we end
  up having to add a new empty sysctl used to register it. To achieve
  saving memory we want to allow syctls to be passed without requiring
  the end element being empty, and just have our registration process
  rely on ARRAY_SIZE(). Without this, supporting both styles of sysctls
  would make the sysctl registration pretty brittle, hard to read and
  maintain as can be seen from Meng Tang's efforts to do just this [0].
  Fortunately, in order to use ARRAY_SIZE() for all sysctl registrations
  also implies doing the work to deprecate two API calls which use
  recursion in order to support sysctl declarations with subdirectories.

  And so during this development cycle quite a bit of effort went into
  this deprecation effort. I've annotated the following two APIs are
  deprecated and in few kernel releases we should be good to remove
  them:

   - register_sysctl_table()
   - register_sysctl_paths()

  During this merge window we should be able to deprecate and unexport
  register_sysctl_paths(), we can probably do that towards the end of
  this merge window.

  Deprecating register_sysctl_table() will take a bit more time but this
  pull request goes with a few example of how to do this.

  As it turns out each of the conversions to move away from either of
  these two API calls *also* saves memory. And so long term, all these
  changes *will* prove to have saved a bit of memory on boot.

  The way I see it then is if remove a user of one deprecated call, it
  gives us enough savings to move one kernel/sysctl.c out from the
  generic arrays as we end up with about the same amount of bytes.

  Since deprecating register_sysctl_table() and register_sysctl_paths()
  does not require maintainer coordination except the final unexport
  you'll see quite a bit of these changes from other pull requests, I've
  just kept the stragglers after rc3"

Link: https://lkml.kernel.org/r/ZAD+cpbrqlc5vmry@bombadil.infradead.org [0]

* tag 'sysctl-6.4-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/mcgrof/linux: (29 commits)
  fs: fix sysctls.c built
  mm: compaction: remove incorrect #ifdef checks
  mm: compaction: move compaction sysctl to its own file
  mm: memory-failure: Move memory failure sysctls to its own file
  arm: simplify two-level sysctl registration for ctl_isa_vars
  ia64: simplify one-level sysctl registration for kdump_ctl_table
  utsname: simplify one-level sysctl registration for uts_kern_table
  ntfs: simplfy one-level sysctl registration for ntfs_sysctls
  coda: simplify one-level sysctl registration for coda_table
  fs/cachefiles: simplify one-level sysctl registration for cachefiles_sysctls
  xfs: simplify two-level sysctl registration for xfs_table
  nfs: simplify two-level sysctl registration for nfs_cb_sysctls
  nfs: simplify two-level sysctl registration for nfs4_cb_sysctls
  lockd: simplify two-level sysctl registration for nlm_sysctls
  proc_sysctl: enhance documentation
  xen: simplify sysctl registration for balloon
  md: simplify sysctl registration
  hv: simplify sysctl registration
  scsi: simplify sysctl registration with register_sysctl()
  csky: simplify alignment sysctl registration
  ...

3 files changed, 2 insertions, 146 deletions

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;
 }