Merge tag 'sysctl-6.15-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/sysctl/sysctl

Pull sysctl updates from Joel Granados:

 - Move vm_table members out of kernel/sysctl.c

   All vm_table array members have moved to their respective subsystems
   leading to the removal of vm_table from kernel/sysctl.c. This
   increases modularity by placing the ctl_tables closer to where they
   are actually used and at the same time reducing the chances of merge
   conflicts in kernel/sysctl.c.

 - ctl_table range fixes

   Replace the proc_handler function that checks variable ranges in
   coredump_sysctls and vdso_table with the one that actually uses the
   extra{1,2} pointers as min/max values. This tightens the range of the
   values that users can pass into the kernel effectively preventing
   {under,over}flows.

 - Misc fixes

   Correct grammar errors and typos in test messages. Update sysctl
   files in MAINTAINERS. Constified and removed array size in
   declaration for alignment_tbl

* tag 'sysctl-6.15-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/sysctl/sysctl: (22 commits)
  selftests/sysctl: fix wording of help messages
  selftests: fix spelling/grammar errors in sysctl/sysctl.sh
  MAINTAINERS: Update sysctl file list in MAINTAINERS
  sysctl: Fix underflow value setting risk in vm_table
  coredump: Fixes core_pipe_limit sysctl proc_handler
  sysctl: remove unneeded include
  sysctl: remove the vm_table
  sh: vdso: move the sysctl to arch/sh/kernel/vsyscall/vsyscall.c
  x86: vdso: move the sysctl to arch/x86/entry/vdso/vdso32-setup.c
  fs: dcache: move the sysctl to fs/dcache.c
  sunrpc: simplify rpcauth_cache_shrink_count()
  fs: drop_caches: move sysctl to fs/drop_caches.c
  fs: fs-writeback: move sysctl to fs/fs-writeback.c
  mm: nommu: move sysctl to mm/nommu.c
  security: min_addr: move sysctl to security/min_addr.c
  mm: mmap: move sysctl to mm/mmap.c
  mm: util: move sysctls to mm/util.c
  mm: vmscan: move vmscan sysctls to mm/vmscan.c
  mm: swap: move sysctl to mm/swap.c
  mm: filemap: move sysctl to mm/filemap.c
  ...

9 files changed, 231 insertions, 17 deletions

diff --git a/mm/filemap.c b/mm/filemap.c
index e9404290f2c6..27dbfc1193b4 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -47,6 +47,7 @@
 #include <linux/splice.h>
 #include <linux/rcupdate_wait.h>
 #include <linux/sched/mm.h>
+#include <linux/sysctl.h>
 #include <asm/pgalloc.h>
 #include <asm/tlbflush.h>
 #include "internal.h"
@@ -1077,6 +1078,19 @@ static wait_queue_head_t *folio_waitqueue(struct folio *folio)
 	return &folio_wait_table[hash_ptr(folio, PAGE_WAIT_TABLE_BITS)];
 }
 
+/* How many times do we accept lock stealing from under a waiter? */
+static int sysctl_page_lock_unfairness = 5;
+static const struct ctl_table filemap_sysctl_table[] = {
+	{
+		.procname	= "page_lock_unfairness",
+		.data		= &sysctl_page_lock_unfairness,
+		.maxlen		= sizeof(sysctl_page_lock_unfairness),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= SYSCTL_ZERO,
+	}
+};
+
 void __init pagecache_init(void)
 {
 	int i;
@@ -1085,6 +1099,7 @@ void __init pagecache_init(void)
 		init_waitqueue_head(&folio_wait_table[i]);
 
 	page_writeback_init();
+	register_sysctl_init("vm", filemap_sysctl_table);
 }
 
 /*
@@ -1232,9 +1247,6 @@ static inline bool folio_trylock_flag(struct folio *folio, int bit_nr,
 	return true;
 }
 
-/* How many times do we accept lock stealing from under a waiter? */
-int sysctl_page_lock_unfairness = 5;
-
 static inline int folio_wait_bit_common(struct folio *folio, int bit_nr,
 		int state, enum behavior behavior)
 {
diff --git a/mm/internal.h b/mm/internal.h
index 20b3535935a3..7eb27ab83ed7 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -1097,9 +1097,13 @@ static inline void mminit_verify_zonelist(void)
 #define NODE_RECLAIM_SUCCESS	1
 
 #ifdef CONFIG_NUMA
+extern int node_reclaim_mode;
+
 extern int node_reclaim(struct pglist_data *, gfp_t, unsigned int);
 extern int find_next_best_node(int node, nodemask_t *used_node_mask);
 #else
+#define node_reclaim_mode 0
+
 static inline int node_reclaim(struct pglist_data *pgdat, gfp_t mask,
 				unsigned int order)
 {
@@ -1111,6 +1115,12 @@ static inline int find_next_best_node(int node, nodemask_t *used_node_mask)
 }
 #endif
 
+static inline bool node_reclaim_enabled(void)
+{
+	/* Is any node_reclaim_mode bit set? */
+	return node_reclaim_mode & (RECLAIM_ZONE|RECLAIM_WRITE|RECLAIM_UNMAP);
+}
+
 /*
  * mm/memory-failure.c
  */
diff --git a/mm/mmap.c b/mm/mmap.c
index cda01071c7b1..d6bbe435bd99 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -1543,6 +1543,57 @@ struct vm_area_struct *_install_special_mapping(
 					&special_mapping_vmops);
 }
 
+#ifdef CONFIG_SYSCTL
+#if defined(HAVE_ARCH_PICK_MMAP_LAYOUT) || \
+		defined(CONFIG_ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT)
+int sysctl_legacy_va_layout;
+#endif
+
+static const struct ctl_table mmap_table[] = {
+		{
+				.procname       = "max_map_count",
+				.data           = &sysctl_max_map_count,
+				.maxlen         = sizeof(sysctl_max_map_count),
+				.mode           = 0644,
+				.proc_handler   = proc_dointvec_minmax,
+				.extra1         = SYSCTL_ZERO,
+		},
+#if defined(HAVE_ARCH_PICK_MMAP_LAYOUT) || \
+		defined(CONFIG_ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT)
+		{
+				.procname       = "legacy_va_layout",
+				.data           = &sysctl_legacy_va_layout,
+				.maxlen         = sizeof(sysctl_legacy_va_layout),
+				.mode           = 0644,
+				.proc_handler   = proc_dointvec_minmax,
+				.extra1         = SYSCTL_ZERO,
+		},
+#endif
+#ifdef CONFIG_HAVE_ARCH_MMAP_RND_BITS
+		{
+				.procname       = "mmap_rnd_bits",
+				.data           = &mmap_rnd_bits,
+				.maxlen         = sizeof(mmap_rnd_bits),
+				.mode           = 0600,
+				.proc_handler   = proc_dointvec_minmax,
+				.extra1         = (void *)&mmap_rnd_bits_min,
+				.extra2         = (void *)&mmap_rnd_bits_max,
+		},
+#endif
+#ifdef CONFIG_HAVE_ARCH_MMAP_RND_COMPAT_BITS
+		{
+				.procname       = "mmap_rnd_compat_bits",
+				.data           = &mmap_rnd_compat_bits,
+				.maxlen         = sizeof(mmap_rnd_compat_bits),
+				.mode           = 0600,
+				.proc_handler   = proc_dointvec_minmax,
+				.extra1         = (void *)&mmap_rnd_compat_bits_min,
+				.extra2         = (void *)&mmap_rnd_compat_bits_max,
+		},
+#endif
+};
+#endif /* CONFIG_SYSCTL */
+
 /*
  * initialise the percpu counter for VM
  */
@@ -1552,6 +1603,9 @@ void __init mmap_init(void)
 
 	ret = percpu_counter_init(&vm_committed_as, 0, GFP_KERNEL);
 	VM_BUG_ON(ret);
+#ifdef CONFIG_SYSCTL
+	register_sysctl_init("vm", mmap_table);
+#endif
 }
 
 /*
diff --git a/mm/nommu.c b/mm/nommu.c
index 9cb6e99215e2..acc18ce611ed 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -48,7 +48,6 @@ struct page *mem_map;
 unsigned long max_mapnr;
 EXPORT_SYMBOL(max_mapnr);
 unsigned long highest_memmap_pfn;
-int sysctl_nr_trim_pages = CONFIG_NOMMU_INITIAL_TRIM_EXCESS;
 int heap_stack_gap = 0;
 
 atomic_long_t mmap_pages_allocated;
@@ -392,6 +391,19 @@ SYSCALL_DEFINE1(brk, unsigned long, brk)
 	return mm->brk = brk;
 }
 
+static int sysctl_nr_trim_pages = CONFIG_NOMMU_INITIAL_TRIM_EXCESS;
+
+static const struct ctl_table nommu_table[] = {
+	{
+		.procname	= "nr_trim_pages",
+		.data		= &sysctl_nr_trim_pages,
+		.maxlen		= sizeof(sysctl_nr_trim_pages),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= SYSCTL_ZERO,
+	},
+};
+
 /*
  * initialise the percpu counter for VM and region record slabs
  */
@@ -402,6 +414,7 @@ void __init mmap_init(void)
 	ret = percpu_counter_init(&vm_committed_as, 0, GFP_KERNEL);
 	VM_BUG_ON(ret);
 	vm_region_jar = KMEM_CACHE(vm_region, SLAB_PANIC|SLAB_ACCOUNT);
+	register_sysctl_init("vm", nommu_table);
 }
 
 /*
diff --git a/mm/swap.c b/mm/swap.c
index fc8281ef4241..b81cce146eb2 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -45,7 +45,7 @@
 
 /* How many pages do we try to swap or page in/out together? As a power of 2 */
 int page_cluster;
-const int page_cluster_max = 31;
+static const int page_cluster_max = 31;
 
 struct cpu_fbatches {
 	/*
@@ -1076,6 +1076,18 @@ void folio_batch_remove_exceptionals(struct folio_batch *fbatch)
 	fbatch->nr = j;
 }
 
+static const struct ctl_table swap_sysctl_table[] = {
+	{
+		.procname	= "page-cluster",
+		.data		= &page_cluster,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= (void *)&page_cluster_max,
+	}
+};
+
 /*
  * Perform any setup for the swap system
  */
@@ -1092,4 +1104,6 @@ void __init swap_setup(void)
 	 * Right now other parts of the system means that we
 	 * _really_ don't want to cluster much more
 	 */
+
+	register_sysctl_init("vm", swap_sysctl_table);
 }
diff --git a/mm/swap.h b/mm/swap.h
index ad2f121de970..274dcc6219a0 100644
--- a/mm/swap.h
+++ b/mm/swap.h
@@ -3,6 +3,7 @@
 #define _MM_SWAP_H
 
 struct mempolicy;
+extern int page_cluster;
 
 #ifdef CONFIG_SWAP
 #include <linux/swapops.h> /* for swp_offset */
diff --git a/mm/util.c b/mm/util.c
index e7d81371032b..448117da071f 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -12,6 +12,7 @@
 #include <linux/security.h>
 #include <linux/swap.h>
 #include <linux/swapops.h>
+#include <linux/sysctl.h>
 #include <linux/mman.h>
 #include <linux/hugetlb.h>
 #include <linux/vmalloc.h>
@@ -747,14 +748,16 @@ int folio_mc_copy(struct folio *dst, struct folio *src)
 EXPORT_SYMBOL(folio_mc_copy);
 
 int sysctl_overcommit_memory __read_mostly = OVERCOMMIT_GUESS;
-int sysctl_overcommit_ratio __read_mostly = 50;
-unsigned long sysctl_overcommit_kbytes __read_mostly;
+static int sysctl_overcommit_ratio __read_mostly = 50;
+static unsigned long sysctl_overcommit_kbytes __read_mostly;
 int sysctl_max_map_count __read_mostly = DEFAULT_MAX_MAP_COUNT;
 unsigned long sysctl_user_reserve_kbytes __read_mostly = 1UL << 17; /* 128MB */
 unsigned long sysctl_admin_reserve_kbytes __read_mostly = 1UL << 13; /* 8MB */
 
-int overcommit_ratio_handler(const struct ctl_table *table, int write, void *buffer,
-		size_t *lenp, loff_t *ppos)
+#ifdef CONFIG_SYSCTL
+
+static int overcommit_ratio_handler(const struct ctl_table *table, int write,
+				void *buffer, size_t *lenp, loff_t *ppos)
 {
 	int ret;
 
@@ -769,8 +772,8 @@ static void sync_overcommit_as(struct work_struct *dummy)
 	percpu_counter_sync(&vm_committed_as);
 }
 
-int overcommit_policy_handler(const struct ctl_table *table, int write, void *buffer,
-		size_t *lenp, loff_t *ppos)
+static int overcommit_policy_handler(const struct ctl_table *table, int write,
+				void *buffer, size_t *lenp, loff_t *ppos)
 {
 	struct ctl_table t;
 	int new_policy = -1;
@@ -805,8 +808,8 @@ int overcommit_policy_handler(const struct ctl_table *table, int write, void *bu
 	return ret;
 }
 
-int overcommit_kbytes_handler(const struct ctl_table *table, int write, void *buffer,
-		size_t *lenp, loff_t *ppos)
+static int overcommit_kbytes_handler(const struct ctl_table *table, int write,
+				void *buffer, size_t *lenp, loff_t *ppos)
 {
 	int ret;
 
@@ -816,6 +819,54 @@ int overcommit_kbytes_handler(const struct ctl_table *table, int write, void *bu
 	return ret;
 }
 
+static const struct ctl_table util_sysctl_table[] = {
+	{
+		.procname	= "overcommit_memory",
+		.data		= &sysctl_overcommit_memory,
+		.maxlen		= sizeof(sysctl_overcommit_memory),
+		.mode		= 0644,
+		.proc_handler	= overcommit_policy_handler,
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= SYSCTL_TWO,
+	},
+	{
+		.procname	= "overcommit_ratio",
+		.data		= &sysctl_overcommit_ratio,
+		.maxlen		= sizeof(sysctl_overcommit_ratio),
+		.mode		= 0644,
+		.proc_handler	= overcommit_ratio_handler,
+	},
+	{
+		.procname	= "overcommit_kbytes",
+		.data		= &sysctl_overcommit_kbytes,
+		.maxlen		= sizeof(sysctl_overcommit_kbytes),
+		.mode		= 0644,
+		.proc_handler	= overcommit_kbytes_handler,
+	},
+	{
+		.procname	= "user_reserve_kbytes",
+		.data		= &sysctl_user_reserve_kbytes,
+		.maxlen		= sizeof(sysctl_user_reserve_kbytes),
+		.mode		= 0644,
+		.proc_handler	= proc_doulongvec_minmax,
+	},
+	{
+		.procname	= "admin_reserve_kbytes",
+		.data		= &sysctl_admin_reserve_kbytes,
+		.maxlen		= sizeof(sysctl_admin_reserve_kbytes),
+		.mode		= 0644,
+		.proc_handler	= proc_doulongvec_minmax,
+	},
+};
+
+static int __init init_vm_util_sysctls(void)
+{
+	register_sysctl_init("vm", util_sysctl_table);
+	return 0;
+}
+subsys_initcall(init_vm_util_sysctls);
+#endif /* CONFIG_SYSCTL */
+
 /*
  * Committed memory limit enforced when OVERCOMMIT_NEVER policy is used
  */
diff --git a/mm/vmscan.c b/mm/vmscan.c
index c767d71c43d7..eb228a8cd769 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -7404,6 +7404,28 @@ void __meminit kswapd_stop(int nid)
 	pgdat_kswapd_unlock(pgdat);
 }
 
+static const struct ctl_table vmscan_sysctl_table[] = {
+	{
+		.procname	= "swappiness",
+		.data		= &vm_swappiness,
+		.maxlen		= sizeof(vm_swappiness),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= SYSCTL_TWO_HUNDRED,
+	},
+#ifdef CONFIG_NUMA
+	{
+		.procname	= "zone_reclaim_mode",
+		.data		= &node_reclaim_mode,
+		.maxlen		= sizeof(node_reclaim_mode),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= SYSCTL_ZERO,
+	}
+#endif
+};
+
 static int __init kswapd_init(void)
 {
 	int nid;
@@ -7411,6 +7433,7 @@ static int __init kswapd_init(void)
 	swap_setup();
 	for_each_node_state(nid, N_MEMORY)
  		kswapd_run(nid);
+	register_sysctl_init("vm", vmscan_sysctl_table);
 	return 0;
 }
 
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 88998725f1c5..651318765ebf 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -31,8 +31,10 @@
 
 #include "internal.h"
 
+#ifdef CONFIG_PROC_FS
 #ifdef CONFIG_NUMA
-int sysctl_vm_numa_stat = ENABLE_NUMA_STAT;
+#define ENABLE_NUMA_STAT 1
+static int sysctl_vm_numa_stat = ENABLE_NUMA_STAT;
 
 /* zero numa counters within a zone */
 static void zero_zone_numa_counters(struct zone *zone)
@@ -74,7 +76,7 @@ static void invalid_numa_statistics(void)
 
 static DEFINE_MUTEX(vm_numa_stat_lock);
 
-int sysctl_vm_numa_stat_handler(const struct ctl_table *table, int write,
+static int sysctl_vm_numa_stat_handler(const struct ctl_table *table, int write,
 		void *buffer, size_t *length, loff_t *ppos)
 {
 	int ret, oldval;
@@ -102,6 +104,7 @@ out:
 	return ret;
 }
 #endif
+#endif /* CONFIG_PROC_FS */
 
 #ifdef CONFIG_VM_EVENT_COUNTERS
 DEFINE_PER_CPU(struct vm_event_state, vm_event_states) = {{0}};
@@ -1940,7 +1943,7 @@ static const struct seq_operations vmstat_op = {
 
 #ifdef CONFIG_SMP
 static DEFINE_PER_CPU(struct delayed_work, vmstat_work);
-int sysctl_stat_interval __read_mostly = HZ;
+static int sysctl_stat_interval __read_mostly = HZ;
 static int vmstat_late_init_done;
 
 #ifdef CONFIG_PROC_FS
@@ -1949,7 +1952,7 @@ static void refresh_vm_stats(struct work_struct *work)
 	refresh_cpu_vm_stats(true);
 }
 
-int vmstat_refresh(const struct ctl_table *table, int write,
+static int vmstat_refresh(const struct ctl_table *table, int write,
 		   void *buffer, size_t *lenp, loff_t *ppos)
 {
 	long val;
@@ -2198,6 +2201,38 @@ static int __init vmstat_late_init(void)
 late_initcall(vmstat_late_init);
 #endif
 
+#ifdef CONFIG_PROC_FS
+static const struct ctl_table vmstat_table[] = {
+#ifdef CONFIG_SMP
+	{
+		.procname	= "stat_interval",
+		.data		= &sysctl_stat_interval,
+		.maxlen		= sizeof(sysctl_stat_interval),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_jiffies,
+	},
+	{
+		.procname	= "stat_refresh",
+		.data		= NULL,
+		.maxlen		= 0,
+		.mode		= 0600,
+		.proc_handler	= vmstat_refresh,
+	},
+#endif
+#ifdef CONFIG_NUMA
+	{
+		.procname	= "numa_stat",
+		.data		= &sysctl_vm_numa_stat,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= sysctl_vm_numa_stat_handler,
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= SYSCTL_ONE,
+	},
+#endif
+};
+#endif
+
 struct workqueue_struct *mm_percpu_wq;
 
 void __init init_mm_internals(void)
@@ -2229,6 +2264,7 @@ void __init init_mm_internals(void)
 	proc_create_seq("pagetypeinfo", 0400, NULL, &pagetypeinfo_op);
 	proc_create_seq("vmstat", 0444, NULL, &vmstat_op);
 	proc_create_seq("zoneinfo", 0444, NULL, &zoneinfo_op);
+	register_sysctl_init("vm", vmstat_table);
 #endif
 }