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

…nel/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
  ...

MAINTAINERS

@@ -19081,9 +19081,10 @@ S:	Maintained
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/sysctl/sysctl.git sysctl-next
 F:	fs/proc/proc_sysctl.c
 F:	include/linux/sysctl.h
-F:	kernel/sysctl-test.c
-F:	kernel/sysctl.c
-F:	tools/testing/selftests/sysctl/
+F:	kernel/sysctl*
+F:	tools/testing/selftests/sysctl/*
+F:	lib/test_sysctl.c
+F:	scripts/check-sysctl-docs
 
 PS3 NETWORK SUPPORT
 M:	Geoff Levand <geoff@infradead.org>

arch/csky/abiv1/alignment.c

@@ -300,7 +300,7 @@ void csky_alignment(struct pt_regs *regs)
 	force_sig_fault(SIGBUS, BUS_ADRALN, (void __user *)addr);
 }
 
-static struct ctl_table alignment_tbl[5] = {
+static const struct ctl_table alignment_tbl[] = {
 	{
 		.procname = "kernel_enable",
 		.data = &align_kern_enable,

arch/sh/kernel/vsyscall/vsyscall.c

@@ -14,6 +14,7 @@
 #include <linux/module.h>
 #include <linux/elf.h>
 #include <linux/sched.h>
+#include <linux/sysctl.h>
 #include <linux/err.h>
 
 /*
@@ -30,6 +31,18 @@ static int __init vdso_setup(char *s)
 }
 __setup("vdso=", vdso_setup);
 
+static const struct ctl_table vdso_table[] = {
+	{
+		.procname	= "vdso_enabled",
+		.data		= &vdso_enabled,
+		.maxlen		= sizeof(vdso_enabled),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= SYSCTL_ONE,
+	},
+};
+
 /*
  * These symbols are defined by vsyscall.o to mark the bounds
  * of the ELF DSO images included therein.
@@ -58,6 +71,14 @@ int __init vsyscall_init(void)
 	return 0;
 }
 
+static int __init vm_sysctl_init(void)
+{
+       register_sysctl_init("vm", vdso_table);
+       return 0;
+}
+
+fs_initcall(vm_sysctl_init);
+
 /* Setup a VMA at program startup for the vsyscall page */
 int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
 {

arch/x86/entry/vdso/vdso32-setup.c

@@ -51,15 +51,17 @@ __setup("vdso32=", vdso32_setup);
 __setup_param("vdso=", vdso_setup, vdso32_setup, 0);
 #endif
 
-#ifdef CONFIG_X86_64
 
 #ifdef CONFIG_SYSCTL
-/* Register vsyscall32 into the ABI table */
 #include <linux/sysctl.h>
 
-static const struct ctl_table abi_table2[] = {
+static const struct ctl_table vdso_table[] = {
 	{
+#ifdef CONFIG_X86_64
 		.procname	= "vsyscall32",
+#else
+		.procname	= "vdso_enabled",
+#endif
 		.data		= &vdso32_enabled,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
@@ -71,10 +73,14 @@ static const struct ctl_table abi_table2[] = {
 
 static __init int ia32_binfmt_init(void)
 {
-	register_sysctl("abi", abi_table2);
+#ifdef CONFIG_X86_64
+	/* Register vsyscall32 into the ABI table */
+	register_sysctl("abi", vdso_table);
+#else
+	register_sysctl_init("vm", vdso_table);
+#endif
 	return 0;
 }
 __initcall(ia32_binfmt_init);
 #endif /* CONFIG_SYSCTL */
 
-#endif	/* CONFIG_X86_64 */

fs/coredump.c

@@ -1042,7 +1042,9 @@ static const struct ctl_table coredump_sysctls[] = {
 		.data		= &core_pipe_limit,
 		.maxlen		= sizeof(unsigned int),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= SYSCTL_INT_MAX,
 	},
 	{
 		.procname       = "core_file_note_size_limit",

fs/dcache.c

@@ -73,8 +73,13 @@
  * If no ancestor relationship:
  * arbitrary, since it's serialized on rename_lock
  */
-int sysctl_vfs_cache_pressure __read_mostly = 100;
-EXPORT_SYMBOL_GPL(sysctl_vfs_cache_pressure);
+static int sysctl_vfs_cache_pressure __read_mostly = 100;
+
+unsigned long vfs_pressure_ratio(unsigned long val)
+{
+	return mult_frac(val, sysctl_vfs_cache_pressure, 100);
+}
+EXPORT_SYMBOL_GPL(vfs_pressure_ratio);
 
 __cacheline_aligned_in_smp DEFINE_SEQLOCK(rename_lock);
 
@@ -211,8 +216,20 @@ static const struct ctl_table fs_dcache_sysctls[] = {
 	},
 };
 
+static const struct ctl_table vm_dcache_sysctls[] = {
+	{
+		.procname	= "vfs_cache_pressure",
+		.data		= &sysctl_vfs_cache_pressure,
+		.maxlen		= sizeof(sysctl_vfs_cache_pressure),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= SYSCTL_ZERO,
+	},
+};
+
 static int __init init_fs_dcache_sysctls(void)
 {
+	register_sysctl_init("vm", vm_dcache_sysctls);
 	register_sysctl_init("fs", fs_dcache_sysctls);
 	return 0;
 }

fs/drop_caches.c

@@ -14,7 +14,7 @@
 #include "internal.h"
 
 /* A global variable is a bit ugly, but it keeps the code simple */
-int sysctl_drop_caches;
+static int sysctl_drop_caches;
 
 static void drop_pagecache_sb(struct super_block *sb, void *unused)
 {
@@ -48,7 +48,7 @@ static void drop_pagecache_sb(struct super_block *sb, void *unused)
 	iput(toput_inode);
 }
 
-int drop_caches_sysctl_handler(const struct ctl_table *table, int write,
+static int drop_caches_sysctl_handler(const struct ctl_table *table, int write,
 		void *buffer, size_t *length, loff_t *ppos)
 {
 	int ret;
@@ -77,3 +77,22 @@ int drop_caches_sysctl_handler(const struct ctl_table *table, int write,
 	}
 	return 0;
 }
+
+static const struct ctl_table drop_caches_table[] = {
+	{
+		.procname	= "drop_caches",
+		.data		= &sysctl_drop_caches,
+		.maxlen		= sizeof(int),
+		.mode		= 0200,
+		.proc_handler	= drop_caches_sysctl_handler,
+		.extra1		= SYSCTL_ONE,
+		.extra2		= SYSCTL_FOUR,
+	},
+};
+
+static int __init init_vm_drop_caches_sysctls(void)
+{
+	register_sysctl_init("vm", drop_caches_table);
+	return 0;
+}
+fs_initcall(init_vm_drop_caches_sysctls);

fs/fs-writeback.c

@@ -65,7 +65,7 @@ struct wb_writeback_work {
  * timestamps written to disk after 12 hours, but in the worst case a
  * few inodes might not their timestamps updated for 24 hours.
  */
-unsigned int dirtytime_expire_interval = 12 * 60 * 60;
+static unsigned int dirtytime_expire_interval = 12 * 60 * 60;
 
 static inline struct inode *wb_inode(struct list_head *head)
 {
@@ -2435,14 +2435,7 @@ static void wakeup_dirtytime_writeback(struct work_struct *w)
 	schedule_delayed_work(&dirtytime_work, dirtytime_expire_interval * HZ);
 }
 
-static int __init start_dirtytime_writeback(void)
-{
-	schedule_delayed_work(&dirtytime_work, dirtytime_expire_interval * HZ);
-	return 0;
-}
-__initcall(start_dirtytime_writeback);
-
-int dirtytime_interval_handler(const struct ctl_table *table, int write,
+static int dirtytime_interval_handler(const struct ctl_table *table, int write,
 			       void *buffer, size_t *lenp, loff_t *ppos)
 {
 	int ret;
@@ -2453,6 +2446,25 @@ int dirtytime_interval_handler(const struct ctl_table *table, int write,
 	return ret;
 }
 
+static const struct ctl_table vm_fs_writeback_table[] = {
+	{
+		.procname	= "dirtytime_expire_seconds",
+		.data		= &dirtytime_expire_interval,
+		.maxlen		= sizeof(dirtytime_expire_interval),
+		.mode		= 0644,
+		.proc_handler	= dirtytime_interval_handler,
+		.extra1		= SYSCTL_ZERO,
+	},
+};
+
+static int __init start_dirtytime_writeback(void)
+{
+	schedule_delayed_work(&dirtytime_work, dirtytime_expire_interval * HZ);
+	register_sysctl_init("vm", vm_fs_writeback_table);
+	return 0;
+}
+__initcall(start_dirtytime_writeback);
+
 /**
  * __mark_inode_dirty -	internal function to mark an inode dirty
  *

include/linux/dcache.h

@@ -519,12 +519,7 @@ static inline int simple_positive(const struct dentry *dentry)
 	return d_really_is_positive(dentry) && !d_unhashed(dentry);
 }
 
-extern int sysctl_vfs_cache_pressure;
-
-static inline unsigned long vfs_pressure_ratio(unsigned long val)
-{
-	return mult_frac(val, sysctl_vfs_cache_pressure, 100);
-}
+unsigned long vfs_pressure_ratio(unsigned long val);
 
 /**
  * d_inode - Get the actual inode of this dentry

include/linux/mm.h

@@ -40,8 +40,6 @@ struct user_struct;
 struct pt_regs;
 struct folio_batch;
 
-extern int sysctl_page_lock_unfairness;
-
 void mm_core_init(void);
 void init_mm_internals(void);
 
@@ -78,8 +76,6 @@ static inline void totalram_pages_add(long count)
 }
 
 extern void * high_memory;
-extern int page_cluster;
-extern const int page_cluster_max;
 
 #ifdef CONFIG_SYSCTL
 extern int sysctl_legacy_va_layout;
@@ -209,17 +205,6 @@ extern int sysctl_max_map_count;
 extern unsigned long sysctl_user_reserve_kbytes;
 extern unsigned long sysctl_admin_reserve_kbytes;
 
-extern int sysctl_overcommit_memory;
-extern int sysctl_overcommit_ratio;
-extern unsigned long sysctl_overcommit_kbytes;
-
-int overcommit_ratio_handler(const struct ctl_table *, int, void *, size_t *,
-		loff_t *);
-int overcommit_kbytes_handler(const struct ctl_table *, int, void *, size_t *,
-		loff_t *);
-int overcommit_policy_handler(const struct ctl_table *, int, void *, size_t *,
-		loff_t *);
-
 #if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP)
 #define nth_page(page,n) pfn_to_page(page_to_pfn((page)) + (n))
 #define folio_page_idx(folio, p)	(page_to_pfn(p) - folio_pfn(folio))
@@ -3809,12 +3794,6 @@ static inline int in_gate_area(struct mm_struct *mm, unsigned long addr)
 
 extern bool process_shares_mm(struct task_struct *p, struct mm_struct *mm);
 
-#ifdef CONFIG_SYSCTL
-extern int sysctl_drop_caches;
-int drop_caches_sysctl_handler(const struct ctl_table *, int, void *, size_t *,
-		loff_t *);
-#endif
-
 void drop_slab(void);
 
 #ifndef CONFIG_MMU
@@ -4086,8 +4065,6 @@ unsigned long wp_shared_mapping_range(struct address_space *mapping,
 				      pgoff_t first_index, pgoff_t nr);
 #endif
 
-extern int sysctl_nr_trim_pages;
-
 #ifdef CONFIG_ANON_VMA_NAME
 int madvise_set_anon_name(struct mm_struct *mm, unsigned long start,
 			  unsigned long len_in,

include/linux/mman.h

@@ -59,8 +59,6 @@
 		| MAP_HUGE_1GB)
 
 extern int sysctl_overcommit_memory;
-extern int sysctl_overcommit_ratio;
-extern unsigned long sysctl_overcommit_kbytes;
 extern struct percpu_counter vm_committed_as;
 
 #ifdef CONFIG_SMP

include/linux/swap.h

@@ -433,19 +433,10 @@ extern int vm_swappiness;
 long remove_mapping(struct address_space *mapping, struct folio *folio);
 
 #ifdef CONFIG_NUMA
-extern int node_reclaim_mode;
 extern int sysctl_min_unmapped_ratio;
 extern int sysctl_min_slab_ratio;
-#else
-#define node_reclaim_mode 0
 #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);
-}
-
 void check_move_unevictable_folios(struct folio_batch *fbatch);
 
 extern void __meminit kswapd_run(int nid);

include/linux/vmstat.h

@@ -10,15 +10,8 @@
 #include <linux/static_key.h>
 #include <linux/mmdebug.h>
 
-extern int sysctl_stat_interval;
-
 #ifdef CONFIG_NUMA
-#define ENABLE_NUMA_STAT   1
-#define DISABLE_NUMA_STAT   0
-extern int sysctl_vm_numa_stat;
 DECLARE_STATIC_KEY_TRUE(vm_numa_stat_key);
-int sysctl_vm_numa_stat_handler(const struct ctl_table *table, int write,
-		void *buffer, size_t *length, loff_t *ppos);
 #endif
 
 struct reclaim_stat {
@@ -304,10 +297,6 @@ void quiet_vmstat(void);
 void cpu_vm_stats_fold(int cpu);
 void refresh_zone_stat_thresholds(void);
 
-struct ctl_table;
-int vmstat_refresh(const struct ctl_table *, int write, void *buffer, size_t *lenp,
-		loff_t *ppos);
-
 void drain_zonestat(struct zone *zone, struct per_cpu_zonestat *);
 
 int calculate_pressure_threshold(struct zone *zone);

include/linux/writeback.h

@@ -327,12 +327,8 @@ extern struct wb_domain global_wb_domain;
 /* These are exported to sysctl. */
 extern unsigned int dirty_writeback_interval;
 extern unsigned int dirty_expire_interval;
-extern unsigned int dirtytime_expire_interval;
 extern int laptop_mode;
 
-int dirtytime_interval_handler(const struct ctl_table *table, int write,
-		void *buffer, size_t *lenp, loff_t *ppos);
-
 void global_dirty_limits(unsigned long *pbackground, unsigned long *pdirty);
 unsigned long wb_calc_thresh(struct bdi_writeback *wb, unsigned long thresh);
 unsigned long cgwb_calc_thresh(struct bdi_writeback *wb);