From 7863dcc72d0f4b13a641065670426435448b3d80 Mon Sep 17 00:00:00 2001
From: Christian Brauner <christian.brauner@ubuntu.com>
Date: Fri, 22 Nov 2024 14:24:58 +0100
Subject: pid: allow pid_max to be set per pid namespace

The pid_max sysctl is a global value. For a long time the default value
has been 65535 and during the pidfd dicussions Linus proposed to bump
pid_max by default (cf. [1]). Based on this discussion systemd started
bumping pid_max to 2^22. So all new systems now run with a very high
pid_max limit with some distros having also backported that change.
The decision to bump pid_max is obviously correct. It just doesn't make
a lot of sense nowadays to enforce such a low pid number. There's
sufficient tooling to make selecting specific processes without typing
really large pid numbers available.

In any case, there are workloads that have expections about how large
pid numbers they accept. Either for historical reasons or architectural
reasons. One concreate example is the 32-bit version of Android's bionic
libc which requires pid numbers less than 65536. There are workloads
where it is run in a 32-bit container on a 64-bit kernel. If the host
has a pid_max value greater than 65535 the libc will abort thread
creation because of size assumptions of pthread_mutex_t.

That's a fairly specific use-case however, in general specific workloads
that are moved into containers running on a host with a new kernel and a
new systemd can run into issues with large pid_max values. Obviously
making assumptions about the size of the allocated pid is suboptimal but
we have userspace that does it.

Of course, giving containers the ability to restrict the number of
processes in their respective pid namespace indepent of the global limit
through pid_max is something desirable in itself and comes in handy in
general.

Independent of motivating use-cases the existence of pid namespaces
makes this also a good semantical extension and there have been prior
proposals pushing in a similar direction.
The trick here is to minimize the risk of regressions which I think is
doable. The fact that pid namespaces are hierarchical will help us here.

What we mostly care about is that when the host sets a low pid_max
limit, say (crazy number) 100 that no descendant pid namespace can
allocate a higher pid number in its namespace. Since pid allocation is
hierarchial this can be ensured by checking each pid allocation against
the pid namespace's pid_max limit. This means if the allocation in the
descendant pid namespace succeeds, the ancestor pid namespace can reject
it. If the ancestor pid namespace has a higher limit than the descendant
pid namespace the descendant pid namespace will reject the pid
allocation. The ancestor pid namespace will obviously not care about
this.
All in all this means pid_max continues to enforce a system wide limit
on the number of processes but allows pid namespaces sufficient leeway
in handling workloads with assumptions about pid values and allows
containers to restrict the number of processes in a pid namespace
through the pid_max interface.

[1]: https://lore.kernel.org/linux-api/CAHk-=wiZ40LVjnXSi9iHLE_-ZBsWFGCgdmNiYZUXn1-V5YBg2g@mail.gmail.com
- rebased from 5.14-rc1
- a few fixes (missing ns_free_inum on error path, missing initialization, etc)
- permission check changes in pid_table_root_permissions
- unsigned int pid_max -> int pid_max (keep pid_max type as it was)
- add READ_ONCE in alloc_pid() as suggested by Christian
- rebased from 6.7 and take into account:
 * sysctl: treewide: drop unused argument ctl_table_root::set_ownership(table)
 * sysctl: treewide: constify ctl_table_header::ctl_table_arg
 * pidfd: add pidfs
 * tracing: Move saved_cmdline code into trace_sched_switch.c

Signed-off-by: Alexander Mikhalitsyn <aleksandr.mikhalitsyn@canonical.com>
Link: https://lore.kernel.org/r/20241122132459.135120-2-aleksandr.mikhalitsyn@canonical.com
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 kernel/pid.c | 125 +++++++++++++++++++++++++++++++++++++++++++++++++++++++----
 1 file changed, 118 insertions(+), 7 deletions(-)

(limited to 'kernel/pid.c')

diff --git a/kernel/pid.c b/kernel/pid.c
index 115448e89c3e9..ce3e94e26a0f0 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -60,10 +60,8 @@ struct pid init_struct_pid = {
 	}, }
 };
 
-int pid_max = PID_MAX_DEFAULT;
-
-int pid_max_min = RESERVED_PIDS + 1;
-int pid_max_max = PID_MAX_LIMIT;
+static int pid_max_min = RESERVED_PIDS + 1;
+static int pid_max_max = PID_MAX_LIMIT;
 /*
  * Pseudo filesystems start inode numbering after one. We use Reserved
  * PIDs as a natural offset.
@@ -87,6 +85,7 @@ struct pid_namespace init_pid_ns = {
 #ifdef CONFIG_PID_NS
 	.ns.ops = &pidns_operations,
 #endif
+	.pid_max = PID_MAX_DEFAULT,
 #if defined(CONFIG_SYSCTL) && defined(CONFIG_MEMFD_CREATE)
 	.memfd_noexec_scope = MEMFD_NOEXEC_SCOPE_EXEC,
 #endif
@@ -193,6 +192,7 @@ struct pid *alloc_pid(struct pid_namespace *ns, pid_t *set_tid,
 
 	for (i = ns->level; i >= 0; i--) {
 		int tid = 0;
+		int pid_max = READ_ONCE(tmp->pid_max);
 
 		if (set_tid_size) {
 			tid = set_tid[ns->level - i];
@@ -644,17 +644,118 @@ SYSCALL_DEFINE2(pidfd_open, pid_t, pid, unsigned int, flags)
 	return fd;
 }
 
+#ifdef CONFIG_SYSCTL
+static struct ctl_table_set *pid_table_root_lookup(struct ctl_table_root *root)
+{
+	return &task_active_pid_ns(current)->set;
+}
+
+static int set_is_seen(struct ctl_table_set *set)
+{
+	return &task_active_pid_ns(current)->set == set;
+}
+
+static int pid_table_root_permissions(struct ctl_table_header *head,
+				      const struct ctl_table *table)
+{
+	struct pid_namespace *pidns =
+		container_of(head->set, struct pid_namespace, set);
+	int mode = table->mode;
+
+	if (ns_capable(pidns->user_ns, CAP_SYS_ADMIN) ||
+	    uid_eq(current_euid(), make_kuid(pidns->user_ns, 0)))
+		mode = (mode & S_IRWXU) >> 6;
+	else if (in_egroup_p(make_kgid(pidns->user_ns, 0)))
+		mode = (mode & S_IRWXG) >> 3;
+	else
+		mode = mode & S_IROTH;
+	return (mode << 6) | (mode << 3) | mode;
+}
+
+static void pid_table_root_set_ownership(struct ctl_table_header *head,
+					 kuid_t *uid, kgid_t *gid)
+{
+	struct pid_namespace *pidns =
+		container_of(head->set, struct pid_namespace, set);
+	kuid_t ns_root_uid;
+	kgid_t ns_root_gid;
+
+	ns_root_uid = make_kuid(pidns->user_ns, 0);
+	if (uid_valid(ns_root_uid))
+		*uid = ns_root_uid;
+
+	ns_root_gid = make_kgid(pidns->user_ns, 0);
+	if (gid_valid(ns_root_gid))
+		*gid = ns_root_gid;
+}
+
+static struct ctl_table_root pid_table_root = {
+	.lookup		= pid_table_root_lookup,
+	.permissions	= pid_table_root_permissions,
+	.set_ownership	= pid_table_root_set_ownership,
+};
+
+static struct ctl_table pid_table[] = {
+	{
+		.procname	= "pid_max",
+		.data		= &init_pid_ns.pid_max,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &pid_max_min,
+		.extra2		= &pid_max_max,
+	},
+};
+#endif
+
+int register_pidns_sysctls(struct pid_namespace *pidns)
+{
+#ifdef CONFIG_SYSCTL
+	struct ctl_table *tbl;
+
+	setup_sysctl_set(&pidns->set, &pid_table_root, set_is_seen);
+
+	tbl = kmemdup(pid_table, sizeof(pid_table), GFP_KERNEL);
+	if (!tbl)
+		return -ENOMEM;
+	tbl->data = &pidns->pid_max;
+	pidns->pid_max = min(pid_max_max, max_t(int, pidns->pid_max,
+			     PIDS_PER_CPU_DEFAULT * num_possible_cpus()));
+
+	pidns->sysctls = __register_sysctl_table(&pidns->set, "kernel", tbl,
+						 ARRAY_SIZE(pid_table));
+	if (!pidns->sysctls) {
+		kfree(tbl);
+		retire_sysctl_set(&pidns->set);
+		return -ENOMEM;
+	}
+#endif
+	return 0;
+}
+
+void unregister_pidns_sysctls(struct pid_namespace *pidns)
+{
+#ifdef CONFIG_SYSCTL
+	const struct ctl_table *tbl;
+
+	tbl = pidns->sysctls->ctl_table_arg;
+	unregister_sysctl_table(pidns->sysctls);
+	retire_sysctl_set(&pidns->set);
+	kfree(tbl);
+#endif
+}
+
 void __init pid_idr_init(void)
 {
 	/* Verify no one has done anything silly: */
 	BUILD_BUG_ON(PID_MAX_LIMIT >= PIDNS_ADDING);
 
 	/* bump default and minimum pid_max based on number of cpus */
-	pid_max = min(pid_max_max, max_t(int, pid_max,
-				PIDS_PER_CPU_DEFAULT * num_possible_cpus()));
+	init_pid_ns.pid_max = min(pid_max_max, max_t(int, init_pid_ns.pid_max,
+				  PIDS_PER_CPU_DEFAULT * num_possible_cpus()));
 	pid_max_min = max_t(int, pid_max_min,
 				PIDS_PER_CPU_MIN * num_possible_cpus());
-	pr_info("pid_max: default: %u minimum: %u\n", pid_max, pid_max_min);
+	pr_info("pid_max: default: %u minimum: %u\n", init_pid_ns.pid_max, pid_max_min);
 
 	idr_init(&init_pid_ns.idr);
 
@@ -665,6 +766,16 @@ void __init pid_idr_init(void)
 			NULL);
 }
 
+static __init int pid_namespace_sysctl_init(void)
+{
+#ifdef CONFIG_SYSCTL
+	/* "kernel" directory will have already been initialized. */
+	BUG_ON(register_pidns_sysctls(&init_pid_ns));
+#endif
+	return 0;
+}
+subsys_initcall(pid_namespace_sysctl_init);
+
 static struct file *__pidfd_fget(struct task_struct *task, int fd)
 {
 	struct file *file;
-- 
cgit v1.2.3


From 9698d5a4836549d394e6efd858b5200878c9f255 Mon Sep 17 00:00:00 2001
From: Christian Brauner <brauner@kernel.org>
Date: Fri, 29 Nov 2024 14:02:23 +0100
Subject: pidfs: rework inode number allocation

Recently we received a patchset that aims to enable file handle encoding
and decoding via name_to_handle_at(2) and open_by_handle_at(2).

A crucical step in the patch series is how to go from inode number to
struct pid without leaking information into unprivileged contexts. The
issue is that in order to find a struct pid the pid number in the
initial pid namespace must be encoded into the file handle via
name_to_handle_at(2). This can be used by containers using a separate
pid namespace to learn what the pid number of a given process in the
initial pid namespace is. While this is a weak information leak it could
be used in various exploits and in general is an ugly wart in the design.

To solve this problem a new way is needed to lookup a struct pid based
on the inode number allocated for that struct pid. The other part is to
remove the custom inode number allocation on 32bit systems that is also
an ugly wart that should go away.

So, a new scheme is used that I was discusssing with Tejun some time
back. A cyclic ida is used for the lower 32 bits and a the high 32 bits
are used for the generation number. This gives a 64 bit inode number
that is unique on both 32 bit and 64 bit. The lower 32 bit number is
recycled slowly and can be used to lookup struct pids.

Link: https://lore.kernel.org/r/20241129-work-pidfs-v2-1-61043d66fbce@kernel.org
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Reviewed-by: Amir Goldstein <amir73il@gmail.com>
Reviewed-by: Jan Kara <jack@suse.cz>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/pidfs.c            | 78 ++++++++++++++++++++++++++++++++++++++++++++++++++-
 include/linux/pidfs.h |  2 ++
 kernel/pid.c          | 14 ++++-----
 3 files changed, 86 insertions(+), 8 deletions(-)

(limited to 'kernel/pid.c')

diff --git a/fs/pidfs.c b/fs/pidfs.c
index 618abb1fa1b84..abfe96be9ffe3 100644
--- a/fs/pidfs.c
+++ b/fs/pidfs.c
@@ -23,6 +23,79 @@
 #include "internal.h"
 #include "mount.h"
 
+static DEFINE_IDR(pidfs_ino_idr);
+
+static u32 pidfs_ino_upper_32_bits = 0;
+
+#if BITS_PER_LONG == 32
+/*
+ * On 32 bit systems the lower 32 bits are the inode number and
+ * the higher 32 bits are the generation number. The starting
+ * value for the inode number and the generation number is one.
+ */
+static u32 pidfs_ino_lower_32_bits = 1;
+
+static inline unsigned long pidfs_ino(u64 ino)
+{
+	return lower_32_bits(ino);
+}
+
+/* On 32 bit the generation number are the upper 32 bits. */
+static inline u32 pidfs_gen(u64 ino)
+{
+	return upper_32_bits(ino);
+}
+
+#else
+
+static u32 pidfs_ino_lower_32_bits = 0;
+
+/* On 64 bit simply return ino. */
+static inline unsigned long pidfs_ino(u64 ino)
+{
+	return ino;
+}
+
+/* On 64 bit the generation number is 1. */
+static inline u32 pidfs_gen(u64 ino)
+{
+	return 1;
+}
+#endif
+
+/*
+ * Construct an inode number for struct pid in a way that we can use the
+ * lower 32bit to lookup struct pid independent of any pid numbers that
+ * could be leaked into userspace (e.g., via file handle encoding).
+ */
+int pidfs_add_pid(struct pid *pid)
+{
+	u32 upper;
+	int lower;
+
+        /*
+	 * Inode numbering for pidfs start at 2. This avoids collisions
+	 * with the root inode which is 1 for pseudo filesystems.
+         */
+	lower = idr_alloc_cyclic(&pidfs_ino_idr, pid, 2, 0, GFP_ATOMIC);
+	if (lower >= 0 && lower < pidfs_ino_lower_32_bits)
+		pidfs_ino_upper_32_bits++;
+	upper = pidfs_ino_upper_32_bits;
+	pidfs_ino_lower_32_bits = lower;
+	if (lower < 0)
+		return lower;
+
+	pid->ino = ((u64)upper << 32) | lower;
+	pid->stashed = NULL;
+	return 0;
+}
+
+/* The idr number to remove is the lower 32 bits of the inode. */
+void pidfs_remove_pid(struct pid *pid)
+{
+	idr_remove(&pidfs_ino_idr, lower_32_bits(pid->ino));
+}
+
 #ifdef CONFIG_PROC_FS
 /**
  * pidfd_show_fdinfo - print information about a pidfd
@@ -346,7 +419,7 @@ static inline void pidfs_free_inum(unsigned long ino)
 #else
 static inline int pidfs_inum(struct pid *pid, unsigned long *ino)
 {
-	*ino = pid->ino;
+	*ino = pidfs_ino(pid->ino);
 	return 0;
 }
 #define pidfs_free_inum(ino) ((void)(ino))
@@ -429,11 +502,14 @@ static const struct dentry_operations pidfs_dentry_operations = {
 
 static int pidfs_init_inode(struct inode *inode, void *data)
 {
+	const struct pid *pid = data;
+
 	inode->i_private = data;
 	inode->i_flags |= S_PRIVATE;
 	inode->i_mode |= S_IRWXU;
 	inode->i_op = &pidfs_inode_operations;
 	inode->i_fop = &pidfs_file_operations;
+	inode->i_generation = pidfs_gen(pid->ino);
 	/*
 	 * Inode numbering for pidfs start at RESERVED_PIDS + 1. This
 	 * avoids collisions with the root inode which is 1 for pseudo
diff --git a/include/linux/pidfs.h b/include/linux/pidfs.h
index 75bdf9807802a..2958652bb108b 100644
--- a/include/linux/pidfs.h
+++ b/include/linux/pidfs.h
@@ -4,5 +4,7 @@
 
 struct file *pidfs_alloc_file(struct pid *pid, unsigned int flags);
 void __init pidfs_init(void);
+int pidfs_add_pid(struct pid *pid);
+void pidfs_remove_pid(struct pid *pid);
 
 #endif /* _LINUX_PID_FS_H */
diff --git a/kernel/pid.c b/kernel/pid.c
index 115448e89c3e9..58567d6904b25 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -64,11 +64,6 @@ int pid_max = PID_MAX_DEFAULT;
 
 int pid_max_min = RESERVED_PIDS + 1;
 int pid_max_max = PID_MAX_LIMIT;
-/*
- * Pseudo filesystems start inode numbering after one. We use Reserved
- * PIDs as a natural offset.
- */
-static u64 pidfs_ino = RESERVED_PIDS;
 
 /*
  * PID-map pages start out as NULL, they get allocated upon
@@ -158,6 +153,7 @@ void free_pid(struct pid *pid)
 
 		idr_remove(&ns->idr, upid->nr);
 	}
+	pidfs_remove_pid(pid);
 	spin_unlock_irqrestore(&pidmap_lock, flags);
 
 	call_rcu(&pid->rcu, delayed_put_pid);
@@ -273,22 +269,26 @@ struct pid *alloc_pid(struct pid_namespace *ns, pid_t *set_tid,
 	INIT_HLIST_HEAD(&pid->inodes);
 
 	upid = pid->numbers + ns->level;
+	idr_preload(GFP_KERNEL);
 	spin_lock_irq(&pidmap_lock);
 	if (!(ns->pid_allocated & PIDNS_ADDING))
 		goto out_unlock;
-	pid->stashed = NULL;
-	pid->ino = ++pidfs_ino;
+	retval = pidfs_add_pid(pid);
+	if (retval)
+		goto out_unlock;
 	for ( ; upid >= pid->numbers; --upid) {
 		/* Make the PID visible to find_pid_ns. */
 		idr_replace(&upid->ns->idr, pid, upid->nr);
 		upid->ns->pid_allocated++;
 	}
 	spin_unlock_irq(&pidmap_lock);
+	idr_preload_end();
 
 	return pid;
 
 out_unlock:
 	spin_unlock_irq(&pidmap_lock);
+	idr_preload_end();
 	put_pid_ns(ns);
 
 out_free:
-- 
cgit v1.2.3


From 16ecd47cb0cd895c7c2f5dd5db50f6c005c51639 Mon Sep 17 00:00:00 2001
From: Christian Brauner <brauner@kernel.org>
Date: Sat, 14 Dec 2024 22:01:28 +0100
Subject: pidfs: lookup pid through rbtree

The new pid inode number allocation scheme is neat but I overlooked a
possible, even though unlikely, attack that can be used to trigger an
overflow on both 32bit and 64bit.

An unique 64 bit identifier was constructed for each struct pid by two
combining a 32 bit idr with a 32 bit generation number. A 32bit number
was allocated using the idr_alloc_cyclic() infrastructure. When the idr
wrapped around a 32 bit wraparound counter was incremented. The 32 bit
wraparound counter served as the upper 32 bits and the allocated idr
number as the lower 32 bits.

Since the idr can only allocate up to INT_MAX entries everytime a
wraparound happens INT_MAX - 1 entries are lost (Ignoring that numbering
always starts at 2 to avoid theoretical collisions with the root inode
number.).

If userspace fully populates the idr such that and puts itself into
control of two entries such that one entry is somewhere in the middle
and the other entry is the INT_MAX entry then it is possible to overflow
the wraparound counter. That is probably difficult to pull off but the
mere possibility is annoying.

The problem could be contained to 32 bit by switching to a data
structure such as the maple tree that allows allocating 64 bit numbers
on 64 bit machines. That would leave 32 bit in a lurch but that probably
doesn't matter that much. The other problem is that removing entries
form the maple tree is somewhat non-trivial because the removal code can
be called under the irq write lock of tasklist_lock and
irq{save,restore} code.

Instead, allocate unique identifiers for struct pid by simply
incrementing a 64 bit counter and insert each struct pid into the rbtree
so it can be looked up to decode file handles avoiding to leak actual
pids across pid namespaces in file handles.

On both 64 bit and 32 bit the same 64 bit identifier is used to lookup
struct pid in the rbtree. On 64 bit the unique identifier for struct pid
simply becomes the inode number. Comparing two pidfds continues to be as
simple as comparing inode numbers.

On 32 bit the 64 bit number assigned to struct pid is split into two 32
bit numbers. The lower 32 bits are used as the inode number and the
upper 32 bits are used as the inode generation number. Whenever a
wraparound happens on 32 bit the 64 bit number will be incremented by 2
so inode numbering starts at 2 again.

When a wraparound happens on 32 bit multiple pidfds with the same inode
number are likely to exist. This isn't a problem since before pidfs
pidfds used the anonymous inode meaning all pidfds had the same inode
number. On 32 bit sserspace can thus reconstruct the 64 bit identifier
by retrieving both the inode number and the inode generation number to
compare, or use file handles. This gives the same guarantees on both 32
bit and 64 bit.

Link: https://lore.kernel.org/r/20241214-gekoppelt-erdarbeiten-a1f9a982a5a6@brauner
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/pidfs.c            | 129 +++++++++++++++++++++++++++++++-------------------
 include/linux/pid.h   |   2 +
 include/linux/pidfs.h |   2 +-
 kernel/pid.c          |   6 +--
 4 files changed, 86 insertions(+), 53 deletions(-)

(limited to 'kernel/pid.c')

diff --git a/fs/pidfs.c b/fs/pidfs.c
index fe10d2a126a22..c5a51c69acc86 100644
--- a/fs/pidfs.c
+++ b/fs/pidfs.c
@@ -24,18 +24,9 @@
 #include "internal.h"
 #include "mount.h"
 
-static DEFINE_IDR(pidfs_ino_idr);
-
-static u32 pidfs_ino_upper_32_bits = 0;
+static struct rb_root pidfs_ino_tree = RB_ROOT;
 
 #if BITS_PER_LONG == 32
-/*
- * On 32 bit systems the lower 32 bits are the inode number and
- * the higher 32 bits are the generation number. The starting
- * value for the inode number and the generation number is one.
- */
-static u32 pidfs_ino_lower_32_bits = 1;
-
 static inline unsigned long pidfs_ino(u64 ino)
 {
 	return lower_32_bits(ino);
@@ -49,52 +40,79 @@ static inline u32 pidfs_gen(u64 ino)
 
 #else
 
-static u32 pidfs_ino_lower_32_bits = 0;
-
 /* On 64 bit simply return ino. */
 static inline unsigned long pidfs_ino(u64 ino)
 {
 	return ino;
 }
 
-/* On 64 bit the generation number is 1. */
+/* On 64 bit the generation number is 0. */
 static inline u32 pidfs_gen(u64 ino)
 {
-	return 1;
+	return 0;
 }
 #endif
 
-/*
- * Construct an inode number for struct pid in a way that we can use the
- * lower 32bit to lookup struct pid independent of any pid numbers that
- * could be leaked into userspace (e.g., via file handle encoding).
- */
-int pidfs_add_pid(struct pid *pid)
+static int pidfs_ino_cmp(struct rb_node *a, const struct rb_node *b)
 {
-	u32 upper;
-	int lower;
-
-        /*
-	 * Inode numbering for pidfs start at 2. This avoids collisions
-	 * with the root inode which is 1 for pseudo filesystems.
-         */
-	lower = idr_alloc_cyclic(&pidfs_ino_idr, pid, 2, 0, GFP_ATOMIC);
-	if (lower >= 0 && lower < pidfs_ino_lower_32_bits)
-		pidfs_ino_upper_32_bits++;
-	upper = pidfs_ino_upper_32_bits;
-	pidfs_ino_lower_32_bits = lower;
-	if (lower < 0)
-		return lower;
-
-	pid->ino = ((u64)upper << 32) | lower;
-	pid->stashed = NULL;
+	struct pid *pid_a = rb_entry(a, struct pid, pidfs_node);
+	struct pid *pid_b = rb_entry(b, struct pid, pidfs_node);
+	u64 pid_ino_a = pid_a->ino;
+	u64 pid_ino_b = pid_b->ino;
+
+	if (pid_ino_a < pid_ino_b)
+		return -1;
+	if (pid_ino_a > pid_ino_b)
+		return 1;
 	return 0;
 }
 
-/* The idr number to remove is the lower 32 bits of the inode. */
+void pidfs_add_pid(struct pid *pid)
+{
+	static u64 pidfs_ino_nr = 2;
+
+	/*
+	 * On 64 bit nothing special happens. The 64bit number assigned
+	 * to struct pid is the inode number.
+	 *
+	 * On 32 bit the 64 bit number assigned to struct pid is split
+	 * into two 32 bit numbers. The lower 32 bits are used as the
+	 * inode number and the upper 32 bits are used as the inode
+	 * generation number.
+	 *
+	 * On 32 bit pidfs_ino() will return the lower 32 bit. When
+	 * pidfs_ino() returns zero a wrap around happened. When a
+	 * wraparound happens the 64 bit number will be incremented by 2
+	 * so inode numbering starts at 2 again.
+	 *
+	 * On 64 bit comparing two pidfds is as simple as comparing
+	 * inode numbers.
+	 *
+	 * When a wraparound happens on 32 bit multiple pidfds with the
+	 * same inode number are likely to exist (This isn't a problem
+	 * since before pidfs pidfds used the anonymous inode meaning
+	 * all pidfds had the same inode number.). Userspace can
+	 * reconstruct the 64 bit identifier by retrieving both the
+	 * inode number and the inode generation number to compare or
+	 * use file handles.
+	 */
+	if (pidfs_ino(pidfs_ino_nr) == 0)
+		pidfs_ino_nr += 2;
+
+	pid->ino = pidfs_ino_nr;
+	pid->stashed = NULL;
+	pidfs_ino_nr++;
+
+	write_seqcount_begin(&pidmap_lock_seq);
+	rb_find_add_rcu(&pid->pidfs_node, &pidfs_ino_tree, pidfs_ino_cmp);
+	write_seqcount_end(&pidmap_lock_seq);
+}
+
 void pidfs_remove_pid(struct pid *pid)
 {
-	idr_remove(&pidfs_ino_idr, lower_32_bits(pid->ino));
+	write_seqcount_begin(&pidmap_lock_seq);
+	rb_erase(&pid->pidfs_node, &pidfs_ino_tree);
+	write_seqcount_end(&pidmap_lock_seq);
 }
 
 #ifdef CONFIG_PROC_FS
@@ -513,24 +531,37 @@ static int pidfs_encode_fh(struct inode *inode, u32 *fh, int *max_len,
 	return FILEID_KERNFS;
 }
 
+static int pidfs_ino_find(const void *key, const struct rb_node *node)
+{
+	const u64 pid_ino = *(u64 *)key;
+	const struct pid *pid = rb_entry(node, struct pid, pidfs_node);
+
+	if (pid_ino < pid->ino)
+		return -1;
+	if (pid_ino > pid->ino)
+		return 1;
+	return 0;
+}
+
 /* Find a struct pid based on the inode number. */
 static struct pid *pidfs_ino_get_pid(u64 ino)
 {
-	unsigned long pid_ino = pidfs_ino(ino);
-	u32 gen = pidfs_gen(ino);
 	struct pid *pid;
+	struct rb_node *node;
+	unsigned int seq;
 
 	guard(rcu)();
-
-	pid = idr_find(&pidfs_ino_idr, lower_32_bits(pid_ino));
-	if (!pid)
+	do {
+		seq = read_seqcount_begin(&pidmap_lock_seq);
+		node = rb_find_rcu(&ino, &pidfs_ino_tree, pidfs_ino_find);
+		if (node)
+			break;
+	} while (read_seqcount_retry(&pidmap_lock_seq, seq));
+
+	if (!node)
 		return NULL;
 
-	if (pidfs_ino(pid->ino) != pid_ino)
-		return NULL;
-
-	if (pidfs_gen(pid->ino) != gen)
-		return NULL;
+	pid = rb_entry(node, struct pid, pidfs_node);
 
 	/* Within our pid namespace hierarchy? */
 	if (pid_vnr(pid) == 0)
diff --git a/include/linux/pid.h b/include/linux/pid.h
index a3aad9b4074cb..fe575fcdb4afa 100644
--- a/include/linux/pid.h
+++ b/include/linux/pid.h
@@ -59,6 +59,7 @@ struct pid
 	spinlock_t lock;
 	struct dentry *stashed;
 	u64 ino;
+	struct rb_node pidfs_node;
 	/* lists of tasks that use this pid */
 	struct hlist_head tasks[PIDTYPE_MAX];
 	struct hlist_head inodes;
@@ -68,6 +69,7 @@ struct pid
 	struct upid numbers[];
 };
 
+extern seqcount_spinlock_t pidmap_lock_seq;
 extern struct pid init_struct_pid;
 
 struct file;
diff --git a/include/linux/pidfs.h b/include/linux/pidfs.h
index 2958652bb108b..df574d6708d42 100644
--- a/include/linux/pidfs.h
+++ b/include/linux/pidfs.h
@@ -4,7 +4,7 @@
 
 struct file *pidfs_alloc_file(struct pid *pid, unsigned int flags);
 void __init pidfs_init(void);
-int pidfs_add_pid(struct pid *pid);
+void pidfs_add_pid(struct pid *pid);
 void pidfs_remove_pid(struct pid *pid);
 
 #endif /* _LINUX_PID_FS_H */
diff --git a/kernel/pid.c b/kernel/pid.c
index 58567d6904b25..aa2a7d4da4555 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -43,6 +43,7 @@
 #include <linux/sched/task.h>
 #include <linux/idr.h>
 #include <linux/pidfs.h>
+#include <linux/seqlock.h>
 #include <net/sock.h>
 #include <uapi/linux/pidfd.h>
 
@@ -103,6 +104,7 @@ EXPORT_SYMBOL_GPL(init_pid_ns);
  */
 
 static  __cacheline_aligned_in_smp DEFINE_SPINLOCK(pidmap_lock);
+seqcount_spinlock_t pidmap_lock_seq = SEQCNT_SPINLOCK_ZERO(pidmap_lock_seq, &pidmap_lock);
 
 void put_pid(struct pid *pid)
 {
@@ -273,9 +275,7 @@ struct pid *alloc_pid(struct pid_namespace *ns, pid_t *set_tid,
 	spin_lock_irq(&pidmap_lock);
 	if (!(ns->pid_allocated & PIDNS_ADDING))
 		goto out_unlock;
-	retval = pidfs_add_pid(pid);
-	if (retval)
-		goto out_unlock;
+	pidfs_add_pid(pid);
 	for ( ; upid >= pid->numbers; --upid) {
 		/* Make the PID visible to find_pid_ns. */
 		idr_replace(&upid->ns->idr, pid, upid->nr);
-- 
cgit v1.2.3


From 1751f872cc97f992ed5c4c72c55588db1f0021e1 Mon Sep 17 00:00:00 2001
From: Joel Granados <joel.granados@kernel.org>
Date: Tue, 28 Jan 2025 13:48:37 +0100
Subject: treewide: const qualify ctl_tables where applicable

Add the const qualifier to all the ctl_tables in the tree except for
watchdog_hardlockup_sysctl, memory_allocation_profiling_sysctls,
loadpin_sysctl_table and the ones calling register_net_sysctl (./net,
drivers/inifiniband dirs). These are special cases as they use a
registration function with a non-const qualified ctl_table argument or
modify the arrays before passing them on to the registration function.

Constifying ctl_table structs will prevent the modification of
proc_handler function pointers as the arrays would reside in .rodata.
This is made possible after commit 78eb4ea25cd5 ("sysctl: treewide:
constify the ctl_table argument of proc_handlers") constified all the
proc_handlers.

Created this by running an spatch followed by a sed command:
Spatch:
    virtual patch

    @
    depends on !(file in "net")
    disable optional_qualifier
    @

    identifier table_name != {
      watchdog_hardlockup_sysctl,
      iwcm_ctl_table,
      ucma_ctl_table,
      memory_allocation_profiling_sysctls,
      loadpin_sysctl_table
    };
    @@

    + const
    struct ctl_table table_name [] = { ... };

sed:
    sed --in-place \
      -e "s/struct ctl_table .table = &uts_kern/const struct ctl_table *table = \&uts_kern/" \
      kernel/utsname_sysctl.c

Reviewed-by: Song Liu <song@kernel.org>
Acked-by: Steven Rostedt (Google) <rostedt@goodmis.org> # for kernel/trace/
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com> # SCSI
Reviewed-by: Darrick J. Wong <djwong@kernel.org> # xfs
Acked-by: Jani Nikula <jani.nikula@intel.com>
Acked-by: Corey Minyard <cminyard@mvista.com>
Acked-by: Wei Liu <wei.liu@kernel.org>
Acked-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Bill O'Donnell <bodonnel@redhat.com>
Acked-by: Baoquan He <bhe@redhat.com>
Acked-by: Ashutosh Dixit <ashutosh.dixit@intel.com>
Acked-by: Anna Schumaker <anna.schumaker@oracle.com>
Signed-off-by: Joel Granados <joel.granados@kernel.org>
---
 arch/arm/kernel/isa.c                         | 2 +-
 arch/arm64/kernel/fpsimd.c                    | 4 ++--
 arch/arm64/kernel/process.c                   | 2 +-
 arch/powerpc/kernel/idle.c                    | 2 +-
 arch/powerpc/platforms/pseries/mobility.c     | 2 +-
 arch/riscv/kernel/process.c                   | 2 +-
 arch/riscv/kernel/vector.c                    | 2 +-
 arch/s390/appldata/appldata_base.c            | 2 +-
 arch/s390/kernel/debug.c                      | 2 +-
 arch/s390/kernel/hiperdispatch.c              | 2 +-
 arch/s390/kernel/topology.c                   | 2 +-
 arch/s390/mm/cmm.c                            | 2 +-
 arch/s390/mm/pgalloc.c                        | 2 +-
 arch/x86/entry/vdso/vdso32-setup.c            | 2 +-
 arch/x86/kernel/cpu/bus_lock.c                | 2 +-
 crypto/fips.c                                 | 2 +-
 drivers/base/firmware_loader/fallback_table.c | 2 +-
 drivers/cdrom/cdrom.c                         | 2 +-
 drivers/char/hpet.c                           | 2 +-
 drivers/char/ipmi/ipmi_poweroff.c             | 2 +-
 drivers/char/random.c                         | 2 +-
 drivers/gpu/drm/i915/i915_perf.c              | 2 +-
 drivers/gpu/drm/xe/xe_observation.c           | 2 +-
 drivers/hv/hv_common.c                        | 2 +-
 drivers/md/md.c                               | 2 +-
 drivers/misc/sgi-xp/xpc_main.c                | 4 ++--
 drivers/perf/arm_pmuv3.c                      | 2 +-
 drivers/perf/riscv_pmu_sbi.c                  | 2 +-
 drivers/scsi/scsi_sysctl.c                    | 2 +-
 drivers/scsi/sg.c                             | 2 +-
 drivers/tty/tty_io.c                          | 2 +-
 drivers/xen/balloon.c                         | 2 +-
 fs/aio.c                                      | 2 +-
 fs/cachefiles/error_inject.c                  | 2 +-
 fs/coda/sysctl.c                              | 2 +-
 fs/coredump.c                                 | 2 +-
 fs/dcache.c                                   | 2 +-
 fs/devpts/inode.c                             | 2 +-
 fs/eventpoll.c                                | 2 +-
 fs/exec.c                                     | 2 +-
 fs/file_table.c                               | 2 +-
 fs/fuse/sysctl.c                              | 2 +-
 fs/inode.c                                    | 2 +-
 fs/lockd/svc.c                                | 2 +-
 fs/locks.c                                    | 2 +-
 fs/namei.c                                    | 2 +-
 fs/namespace.c                                | 2 +-
 fs/nfs/nfs4sysctl.c                           | 2 +-
 fs/nfs/sysctl.c                               | 2 +-
 fs/notify/dnotify/dnotify.c                   | 2 +-
 fs/notify/fanotify/fanotify_user.c            | 2 +-
 fs/notify/inotify/inotify_user.c              | 2 +-
 fs/ocfs2/stackglue.c                          | 2 +-
 fs/pipe.c                                     | 2 +-
 fs/quota/dquot.c                              | 2 +-
 fs/sysctls.c                                  | 2 +-
 fs/userfaultfd.c                              | 2 +-
 fs/verity/init.c                              | 2 +-
 fs/xfs/xfs_sysctl.c                           | 2 +-
 init/do_mounts_initrd.c                       | 2 +-
 io_uring/io_uring.c                           | 2 +-
 ipc/ipc_sysctl.c                              | 2 +-
 ipc/mq_sysctl.c                               | 2 +-
 kernel/acct.c                                 | 2 +-
 kernel/bpf/syscall.c                          | 2 +-
 kernel/delayacct.c                            | 2 +-
 kernel/exit.c                                 | 2 +-
 kernel/hung_task.c                            | 2 +-
 kernel/kexec_core.c                           | 2 +-
 kernel/kprobes.c                              | 2 +-
 kernel/latencytop.c                           | 2 +-
 kernel/locking/lockdep.c                      | 2 +-
 kernel/panic.c                                | 2 +-
 kernel/pid.c                                  | 2 +-
 kernel/pid_namespace.c                        | 2 +-
 kernel/pid_sysctl.h                           | 2 +-
 kernel/printk/sysctl.c                        | 2 +-
 kernel/reboot.c                               | 2 +-
 kernel/sched/autogroup.c                      | 2 +-
 kernel/sched/core.c                           | 2 +-
 kernel/sched/deadline.c                       | 2 +-
 kernel/sched/fair.c                           | 2 +-
 kernel/sched/rt.c                             | 2 +-
 kernel/sched/topology.c                       | 2 +-
 kernel/seccomp.c                              | 2 +-
 kernel/signal.c                               | 2 +-
 kernel/stackleak.c                            | 2 +-
 kernel/sysctl-test.c                          | 6 +++---
 kernel/sysctl.c                               | 4 ++--
 kernel/time/timer.c                           | 2 +-
 kernel/trace/ftrace.c                         | 2 +-
 kernel/trace/trace_events_user.c              | 2 +-
 kernel/umh.c                                  | 2 +-
 kernel/utsname_sysctl.c                       | 4 ++--
 kernel/watchdog.c                             | 2 +-
 lib/test_sysctl.c                             | 6 +++---
 mm/compaction.c                               | 2 +-
 mm/hugetlb.c                                  | 2 +-
 mm/hugetlb_vmemmap.c                          | 2 +-
 mm/memory-failure.c                           | 2 +-
 mm/oom_kill.c                                 | 2 +-
 mm/page-writeback.c                           | 2 +-
 mm/page_alloc.c                               | 2 +-
 security/apparmor/lsm.c                       | 2 +-
 security/keys/sysctl.c                        | 2 +-
 security/yama/yama_lsm.c                      | 2 +-
 106 files changed, 114 insertions(+), 114 deletions(-)

(limited to 'kernel/pid.c')

diff --git a/arch/arm/kernel/isa.c b/arch/arm/kernel/isa.c
index 905b1b1915468..db8be609fab24 100644
--- a/arch/arm/kernel/isa.c
+++ b/arch/arm/kernel/isa.c
@@ -16,7 +16,7 @@
 
 static unsigned int isa_membase, isa_portbase, isa_portshift;
 
-static struct ctl_table ctl_isa_vars[] = {
+static const struct ctl_table ctl_isa_vars[] = {
 	{
 		.procname	= "membase",
 		.data		= &isa_membase, 
diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c
index 8c4c1a2186cc5..2b601d88762d4 100644
--- a/arch/arm64/kernel/fpsimd.c
+++ b/arch/arm64/kernel/fpsimd.c
@@ -562,7 +562,7 @@ static int vec_proc_do_default_vl(const struct ctl_table *table, int write,
 	return 0;
 }
 
-static struct ctl_table sve_default_vl_table[] = {
+static const struct ctl_table sve_default_vl_table[] = {
 	{
 		.procname	= "sve_default_vector_length",
 		.mode		= 0644,
@@ -585,7 +585,7 @@ static int __init sve_sysctl_init(void) { return 0; }
 #endif /* ! (CONFIG_ARM64_SVE && CONFIG_SYSCTL) */
 
 #if defined(CONFIG_ARM64_SME) && defined(CONFIG_SYSCTL)
-static struct ctl_table sme_default_vl_table[] = {
+static const struct ctl_table sme_default_vl_table[] = {
 	{
 		.procname	= "sme_default_vector_length",
 		.mode		= 0644,
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index 2968a33bb3bc1..42faebb7b7123 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -859,7 +859,7 @@ long get_tagged_addr_ctrl(struct task_struct *task)
  * disable it for tasks that already opted in to the relaxed ABI.
  */
 
-static struct ctl_table tagged_addr_sysctl_table[] = {
+static const struct ctl_table tagged_addr_sysctl_table[] = {
 	{
 		.procname	= "tagged_addr_disabled",
 		.mode		= 0644,
diff --git a/arch/powerpc/kernel/idle.c b/arch/powerpc/kernel/idle.c
index 30b56c67fa610..e527cd3ef128b 100644
--- a/arch/powerpc/kernel/idle.c
+++ b/arch/powerpc/kernel/idle.c
@@ -97,7 +97,7 @@ void power4_idle(void)
 /*
  * Register the sysctl to set/clear powersave_nap.
  */
-static struct ctl_table powersave_nap_ctl_table[] = {
+static const struct ctl_table powersave_nap_ctl_table[] = {
 	{
 		.procname	= "powersave-nap",
 		.data		= &powersave_nap,
diff --git a/arch/powerpc/platforms/pseries/mobility.c b/arch/powerpc/platforms/pseries/mobility.c
index 1798f0f14d58a..62bd8e2d5d4c0 100644
--- a/arch/powerpc/platforms/pseries/mobility.c
+++ b/arch/powerpc/platforms/pseries/mobility.c
@@ -53,7 +53,7 @@ struct update_props_workarea {
 static unsigned int nmi_wd_lpm_factor = 200;
 
 #ifdef CONFIG_SYSCTL
-static struct ctl_table nmi_wd_lpm_factor_ctl_table[] = {
+static const struct ctl_table nmi_wd_lpm_factor_ctl_table[] = {
 	{
 		.procname	= "nmi_wd_lpm_factor",
 		.data		= &nmi_wd_lpm_factor,
diff --git a/arch/riscv/kernel/process.c b/arch/riscv/kernel/process.c
index 58b6482c2bf66..7891294abf493 100644
--- a/arch/riscv/kernel/process.c
+++ b/arch/riscv/kernel/process.c
@@ -364,7 +364,7 @@ static bool try_to_set_pmm(unsigned long value)
  * disable it for tasks that already opted in to the relaxed ABI.
  */
 
-static struct ctl_table tagged_addr_sysctl_table[] = {
+static const struct ctl_table tagged_addr_sysctl_table[] = {
 	{
 		.procname	= "tagged_addr_disabled",
 		.mode		= 0644,
diff --git a/arch/riscv/kernel/vector.c b/arch/riscv/kernel/vector.c
index 821818886fab0..d022b028ac3ff 100644
--- a/arch/riscv/kernel/vector.c
+++ b/arch/riscv/kernel/vector.c
@@ -287,7 +287,7 @@ long riscv_v_vstate_ctrl_set_current(unsigned long arg)
 
 #ifdef CONFIG_SYSCTL
 
-static struct ctl_table riscv_v_default_vstate_table[] = {
+static const struct ctl_table riscv_v_default_vstate_table[] = {
 	{
 		.procname	= "riscv_v_default_allow",
 		.data		= &riscv_v_implicit_uacc,
diff --git a/arch/s390/appldata/appldata_base.c b/arch/s390/appldata/appldata_base.c
index 91a30e017d658..dd7ba7587dd5c 100644
--- a/arch/s390/appldata/appldata_base.c
+++ b/arch/s390/appldata/appldata_base.c
@@ -52,7 +52,7 @@ static int appldata_interval_handler(const struct ctl_table *ctl, int write,
 				     void *buffer, size_t *lenp, loff_t *ppos);
 
 static struct ctl_table_header *appldata_sysctl_header;
-static struct ctl_table appldata_table[] = {
+static const struct ctl_table appldata_table[] = {
 	{
 		.procname	= "timer",
 		.mode		= S_IRUGO | S_IWUSR,
diff --git a/arch/s390/kernel/debug.c b/arch/s390/kernel/debug.c
index ba6b7329a10e9..ce038e9205f71 100644
--- a/arch/s390/kernel/debug.c
+++ b/arch/s390/kernel/debug.c
@@ -1122,7 +1122,7 @@ static int s390dbf_procactive(const struct ctl_table *table, int write,
 		return 0;
 }
 
-static struct ctl_table s390dbf_table[] = {
+static const struct ctl_table s390dbf_table[] = {
 	{
 		.procname	= "debug_stoppable",
 		.data		= &debug_stoppable,
diff --git a/arch/s390/kernel/hiperdispatch.c b/arch/s390/kernel/hiperdispatch.c
index 2a99a216ab629..7857a7e8e56cb 100644
--- a/arch/s390/kernel/hiperdispatch.c
+++ b/arch/s390/kernel/hiperdispatch.c
@@ -292,7 +292,7 @@ static int hiperdispatch_ctl_handler(const struct ctl_table *ctl, int write,
 	return 0;
 }
 
-static struct ctl_table hiperdispatch_ctl_table[] = {
+static const struct ctl_table hiperdispatch_ctl_table[] = {
 	{
 		.procname	= "hiperdispatch",
 		.mode		= 0644,
diff --git a/arch/s390/kernel/topology.c b/arch/s390/kernel/topology.c
index 3808f942a4333..211cc8382e4a9 100644
--- a/arch/s390/kernel/topology.c
+++ b/arch/s390/kernel/topology.c
@@ -667,7 +667,7 @@ static int polarization_ctl_handler(const struct ctl_table *ctl, int write,
 	return set_polarization(polarization);
 }
 
-static struct ctl_table topology_ctl_table[] = {
+static const struct ctl_table topology_ctl_table[] = {
 	{
 		.procname	= "topology",
 		.mode		= 0644,
diff --git a/arch/s390/mm/cmm.c b/arch/s390/mm/cmm.c
index 7bf0f691827b5..39f44b6256e0d 100644
--- a/arch/s390/mm/cmm.c
+++ b/arch/s390/mm/cmm.c
@@ -332,7 +332,7 @@ static int cmm_timeout_handler(const struct ctl_table *ctl, int write,
 	return 0;
 }
 
-static struct ctl_table cmm_table[] = {
+static const struct ctl_table cmm_table[] = {
 	{
 		.procname	= "cmm_pages",
 		.mode		= 0644,
diff --git a/arch/s390/mm/pgalloc.c b/arch/s390/mm/pgalloc.c
index d33f55b7ee981..cd2fef79ad2c7 100644
--- a/arch/s390/mm/pgalloc.c
+++ b/arch/s390/mm/pgalloc.c
@@ -21,7 +21,7 @@
 int page_table_allocate_pgste = 0;
 EXPORT_SYMBOL(page_table_allocate_pgste);
 
-static struct ctl_table page_table_sysctl[] = {
+static const struct ctl_table page_table_sysctl[] = {
 	{
 		.procname	= "allocate_pgste",
 		.data		= &page_table_allocate_pgste,
diff --git a/arch/x86/entry/vdso/vdso32-setup.c b/arch/x86/entry/vdso/vdso32-setup.c
index 76e4e74f35b5a..f6d2d8aba6434 100644
--- a/arch/x86/entry/vdso/vdso32-setup.c
+++ b/arch/x86/entry/vdso/vdso32-setup.c
@@ -57,7 +57,7 @@ __setup_param("vdso=", vdso_setup, vdso32_setup, 0);
 /* Register vsyscall32 into the ABI table */
 #include <linux/sysctl.h>
 
-static struct ctl_table abi_table2[] = {
+static const struct ctl_table abi_table2[] = {
 	{
 		.procname	= "vsyscall32",
 		.data		= &vdso32_enabled,
diff --git a/arch/x86/kernel/cpu/bus_lock.c b/arch/x86/kernel/cpu/bus_lock.c
index 704e9241b9640..6cba85c79d42d 100644
--- a/arch/x86/kernel/cpu/bus_lock.c
+++ b/arch/x86/kernel/cpu/bus_lock.c
@@ -49,7 +49,7 @@ static unsigned int sysctl_sld_mitigate = 1;
 static DEFINE_SEMAPHORE(buslock_sem, 1);
 
 #ifdef CONFIG_PROC_SYSCTL
-static struct ctl_table sld_sysctls[] = {
+static const struct ctl_table sld_sysctls[] = {
 	{
 		.procname       = "split_lock_mitigate",
 		.data           = &sysctl_sld_mitigate,
diff --git a/crypto/fips.c b/crypto/fips.c
index a58e7750f5329..2fa3a9ee61a15 100644
--- a/crypto/fips.c
+++ b/crypto/fips.c
@@ -41,7 +41,7 @@ __setup("fips=", fips_enable);
 static char fips_name[] = FIPS_MODULE_NAME;
 static char fips_version[] = FIPS_MODULE_VERSION;
 
-static struct ctl_table crypto_sysctl_table[] = {
+static const struct ctl_table crypto_sysctl_table[] = {
 	{
 		.procname	= "fips_enabled",
 		.data		= &fips_enabled,
diff --git a/drivers/base/firmware_loader/fallback_table.c b/drivers/base/firmware_loader/fallback_table.c
index ddb70e29eb423..c8afc501a8a47 100644
--- a/drivers/base/firmware_loader/fallback_table.c
+++ b/drivers/base/firmware_loader/fallback_table.c
@@ -25,7 +25,7 @@ struct firmware_fallback_config fw_fallback_config = {
 EXPORT_SYMBOL_NS_GPL(fw_fallback_config, "FIRMWARE_LOADER_PRIVATE");
 
 #ifdef CONFIG_SYSCTL
-static struct ctl_table firmware_config_table[] = {
+static const struct ctl_table firmware_config_table[] = {
 	{
 		.procname	= "force_sysfs_fallback",
 		.data		= &fw_fallback_config.force_sysfs_fallback,
diff --git a/drivers/cdrom/cdrom.c b/drivers/cdrom/cdrom.c
index 51745ed1bbabc..b163e043c6873 100644
--- a/drivers/cdrom/cdrom.c
+++ b/drivers/cdrom/cdrom.c
@@ -3612,7 +3612,7 @@ static int cdrom_sysctl_handler(const struct ctl_table *ctl, int write,
 }
 
 /* Place files in /proc/sys/dev/cdrom */
-static struct ctl_table cdrom_table[] = {
+static const struct ctl_table cdrom_table[] = {
 	{
 		.procname	= "info",
 		.data		= &cdrom_sysctl_settings.info, 
diff --git a/drivers/char/hpet.c b/drivers/char/hpet.c
index 48fe96ab46490..e110857824fcb 100644
--- a/drivers/char/hpet.c
+++ b/drivers/char/hpet.c
@@ -724,7 +724,7 @@ static int hpet_is_known(struct hpet_data *hdp)
 	return 0;
 }
 
-static struct ctl_table hpet_table[] = {
+static const struct ctl_table hpet_table[] = {
 	{
 	 .procname = "max-user-freq",
 	 .data = &hpet_max_freq,
diff --git a/drivers/char/ipmi/ipmi_poweroff.c b/drivers/char/ipmi/ipmi_poweroff.c
index 05f17e3e6207b..e63c316d8aaa5 100644
--- a/drivers/char/ipmi/ipmi_poweroff.c
+++ b/drivers/char/ipmi/ipmi_poweroff.c
@@ -650,7 +650,7 @@ static struct ipmi_smi_watcher smi_watcher = {
 #ifdef CONFIG_PROC_FS
 #include <linux/sysctl.h>
 
-static struct ctl_table ipmi_table[] = {
+static const struct ctl_table ipmi_table[] = {
 	{ .procname	= "poweroff_powercycle",
 	  .data		= &poweroff_powercycle,
 	  .maxlen	= sizeof(poweroff_powercycle),
diff --git a/drivers/char/random.c b/drivers/char/random.c
index 23ee76bbb4aa7..2581186fa61b7 100644
--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@@ -1665,7 +1665,7 @@ static int proc_do_rointvec(const struct ctl_table *table, int write, void *buf,
 	return write ? 0 : proc_dointvec(table, 0, buf, lenp, ppos);
 }
 
-static struct ctl_table random_table[] = {
+static const struct ctl_table random_table[] = {
 	{
 		.procname	= "poolsize",
 		.data		= &sysctl_poolsize,
diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
index 2406cda75b7b4..5384d1bb49233 100644
--- a/drivers/gpu/drm/i915/i915_perf.c
+++ b/drivers/gpu/drm/i915/i915_perf.c
@@ -4802,7 +4802,7 @@ err_unlock:
 	return ret;
 }
 
-static struct ctl_table oa_table[] = {
+static const struct ctl_table oa_table[] = {
 	{
 	 .procname = "perf_stream_paranoid",
 	 .data = &i915_perf_stream_paranoid,
diff --git a/drivers/gpu/drm/xe/xe_observation.c b/drivers/gpu/drm/xe/xe_observation.c
index 8ec1b84cbb9e4..57cf01efc07f8 100644
--- a/drivers/gpu/drm/xe/xe_observation.c
+++ b/drivers/gpu/drm/xe/xe_observation.c
@@ -56,7 +56,7 @@ int xe_observation_ioctl(struct drm_device *dev, void *data, struct drm_file *fi
 	}
 }
 
-static struct ctl_table observation_ctl_table[] = {
+static const struct ctl_table observation_ctl_table[] = {
 	{
 	 .procname = "observation_paranoid",
 	 .data = &xe_observation_paranoid,
diff --git a/drivers/hv/hv_common.c b/drivers/hv/hv_common.c
index af5d1dc451f67..f2e6f55d6ca62 100644
--- a/drivers/hv/hv_common.c
+++ b/drivers/hv/hv_common.c
@@ -141,7 +141,7 @@ static int sysctl_record_panic_msg = 1;
  * sysctl option to allow the user to control whether kmsg data should be
  * reported to Hyper-V on panic.
  */
-static struct ctl_table hv_ctl_table[] = {
+static const struct ctl_table hv_ctl_table[] = {
 	{
 		.procname	= "hyperv_record_panic_msg",
 		.data		= &sysctl_record_panic_msg,
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 866015b681af8..22f7bd3b94d58 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -294,7 +294,7 @@ void mddev_destroy_serial_pool(struct mddev *mddev, struct md_rdev *rdev)
 
 static struct ctl_table_header *raid_table_header;
 
-static struct ctl_table raid_table[] = {
+static const struct ctl_table raid_table[] = {
 	{
 		.procname	= "speed_limit_min",
 		.data		= &sysctl_speed_limit_min,
diff --git a/drivers/misc/sgi-xp/xpc_main.c b/drivers/misc/sgi-xp/xpc_main.c
index 61b66e318488c..7a3c34306de98 100644
--- a/drivers/misc/sgi-xp/xpc_main.c
+++ b/drivers/misc/sgi-xp/xpc_main.c
@@ -93,7 +93,7 @@ int xpc_disengage_timelimit = XPC_DISENGAGE_DEFAULT_TIMELIMIT;
 static int xpc_disengage_min_timelimit;	/* = 0 */
 static int xpc_disengage_max_timelimit = 120;
 
-static struct ctl_table xpc_sys_xpc_hb[] = {
+static const struct ctl_table xpc_sys_xpc_hb[] = {
 	{
 	 .procname = "hb_interval",
 	 .data = &xpc_hb_interval,
@@ -111,7 +111,7 @@ static struct ctl_table xpc_sys_xpc_hb[] = {
 	 .extra1 = &xpc_hb_check_min_interval,
 	 .extra2 = &xpc_hb_check_max_interval},
 };
-static struct ctl_table xpc_sys_xpc[] = {
+static const struct ctl_table xpc_sys_xpc[] = {
 	{
 	 .procname = "disengage_timelimit",
 	 .data = &xpc_disengage_timelimit,
diff --git a/drivers/perf/arm_pmuv3.c b/drivers/perf/arm_pmuv3.c
index b5cc11abc962c..0e360feb3432e 100644
--- a/drivers/perf/arm_pmuv3.c
+++ b/drivers/perf/arm_pmuv3.c
@@ -1279,7 +1279,7 @@ static int armv8pmu_proc_user_access_handler(const struct ctl_table *table, int
 	return 0;
 }
 
-static struct ctl_table armv8_pmu_sysctl_table[] = {
+static const struct ctl_table armv8_pmu_sysctl_table[] = {
 	{
 		.procname       = "perf_user_access",
 		.data		= &sysctl_perf_user_access,
diff --git a/drivers/perf/riscv_pmu_sbi.c b/drivers/perf/riscv_pmu_sbi.c
index 194c153e5d71c..698de8ddf895b 100644
--- a/drivers/perf/riscv_pmu_sbi.c
+++ b/drivers/perf/riscv_pmu_sbi.c
@@ -1317,7 +1317,7 @@ static int riscv_pmu_proc_user_access_handler(const struct ctl_table *table,
 	return 0;
 }
 
-static struct ctl_table sbi_pmu_sysctl_table[] = {
+static const struct ctl_table sbi_pmu_sysctl_table[] = {
 	{
 		.procname       = "perf_user_access",
 		.data		= &sysctl_perf_user_access,
diff --git a/drivers/scsi/scsi_sysctl.c b/drivers/scsi/scsi_sysctl.c
index 093774d775346..be4aef0f4f996 100644
--- a/drivers/scsi/scsi_sysctl.c
+++ b/drivers/scsi/scsi_sysctl.c
@@ -12,7 +12,7 @@
 #include "scsi_priv.h"
 
 
-static struct ctl_table scsi_table[] = {
+static const struct ctl_table scsi_table[] = {
 	{ .procname	= "logging_level",
 	  .data		= &scsi_logging_level,
 	  .maxlen	= sizeof(scsi_logging_level),
diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c
index 94127868bedf8..effb7e7681659 100644
--- a/drivers/scsi/sg.c
+++ b/drivers/scsi/sg.c
@@ -1639,7 +1639,7 @@ MODULE_PARM_DESC(allow_dio, "allow direct I/O (default: 0 (disallow))");
 #ifdef CONFIG_SYSCTL
 #include <linux/sysctl.h>
 
-static struct ctl_table sg_sysctls[] = {
+static const struct ctl_table sg_sysctls[] = {
 	{
 		.procname	= "sg-big-buff",
 		.data		= &sg_big_buff,
diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c
index 50c0c23ae6780..449dbd2164603 100644
--- a/drivers/tty/tty_io.c
+++ b/drivers/tty/tty_io.c
@@ -3617,7 +3617,7 @@ void console_sysfs_notify(void)
 		sysfs_notify(&consdev->kobj, NULL, "active");
 }
 
-static struct ctl_table tty_table[] = {
+static const struct ctl_table tty_table[] = {
 	{
 		.procname	= "legacy_tiocsti",
 		.data		= &tty_legacy_tiocsti,
diff --git a/drivers/xen/balloon.c b/drivers/xen/balloon.c
index 528395133b4f8..163f7f1d70f1b 100644
--- a/drivers/xen/balloon.c
+++ b/drivers/xen/balloon.c
@@ -84,7 +84,7 @@ module_param(balloon_boot_timeout, uint, 0444);
 #ifdef CONFIG_XEN_BALLOON_MEMORY_HOTPLUG
 static int xen_hotplug_unpopulated;
 
-static struct ctl_table balloon_table[] = {
+static const struct ctl_table balloon_table[] = {
 	{
 		.procname	= "hotplug_unpopulated",
 		.data		= &xen_hotplug_unpopulated,
diff --git a/fs/aio.c b/fs/aio.c
index 50671640b5883..7b976b564cfc4 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -224,7 +224,7 @@ static unsigned long aio_nr;		/* current system wide number of aio requests */
 static unsigned long aio_max_nr = 0x10000; /* system wide maximum number of aio requests */
 /*----end sysctl variables---*/
 #ifdef CONFIG_SYSCTL
-static struct ctl_table aio_sysctls[] = {
+static const struct ctl_table aio_sysctls[] = {
 	{
 		.procname	= "aio-nr",
 		.data		= &aio_nr,
diff --git a/fs/cachefiles/error_inject.c b/fs/cachefiles/error_inject.c
index 1715d5ca2b2d2..e341ade47dd8a 100644
--- a/fs/cachefiles/error_inject.c
+++ b/fs/cachefiles/error_inject.c
@@ -11,7 +11,7 @@
 unsigned int cachefiles_error_injection_state;
 
 static struct ctl_table_header *cachefiles_sysctl;
-static struct ctl_table cachefiles_sysctls[] = {
+static const struct ctl_table cachefiles_sysctls[] = {
 	{
 		.procname	= "error_injection",
 		.data		= &cachefiles_error_injection_state,
diff --git a/fs/coda/sysctl.c b/fs/coda/sysctl.c
index 9f2d5743e2c89..0df46f09b6cc5 100644
--- a/fs/coda/sysctl.c
+++ b/fs/coda/sysctl.c
@@ -14,7 +14,7 @@
 
 static struct ctl_table_header *fs_table_header;
 
-static struct ctl_table coda_table[] = {
+static const struct ctl_table coda_table[] = {
 	{
 		.procname	= "timeout",
 		.data		= &coda_timeout,
diff --git a/fs/coredump.c b/fs/coredump.c
index d48edb37bc35c..591700e1b2ce6 100644
--- a/fs/coredump.c
+++ b/fs/coredump.c
@@ -995,7 +995,7 @@ static int proc_dostring_coredump(const struct ctl_table *table, int write,
 static const unsigned int core_file_note_size_min = CORE_FILE_NOTE_SIZE_DEFAULT;
 static const unsigned int core_file_note_size_max = CORE_FILE_NOTE_SIZE_MAX;
 
-static struct ctl_table coredump_sysctls[] = {
+static const struct ctl_table coredump_sysctls[] = {
 	{
 		.procname	= "core_uses_pid",
 		.data		= &core_uses_pid,
diff --git a/fs/dcache.c b/fs/dcache.c
index 1a01d7a6a7a92..1cd929f17eecf 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -192,7 +192,7 @@ static int proc_nr_dentry(const struct ctl_table *table, int write, void *buffer
 	return proc_doulongvec_minmax(table, write, buffer, lenp, ppos);
 }
 
-static struct ctl_table fs_dcache_sysctls[] = {
+static const struct ctl_table fs_dcache_sysctls[] = {
 	{
 		.procname	= "dentry-state",
 		.data		= &dentry_stat,
diff --git a/fs/devpts/inode.c b/fs/devpts/inode.c
index b20e565b9c5ea..1096ff8562fa1 100644
--- a/fs/devpts/inode.c
+++ b/fs/devpts/inode.c
@@ -45,7 +45,7 @@ static int pty_limit_min;
 static int pty_limit_max = INT_MAX;
 static atomic_t pty_count = ATOMIC_INIT(0);
 
-static struct ctl_table pty_table[] = {
+static const struct ctl_table pty_table[] = {
 	{
 		.procname	= "max",
 		.maxlen		= sizeof(int),
diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index f9898e60dd8bd..7c0980db77b31 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -318,7 +318,7 @@ static void unlist_file(struct epitems_head *head)
 static long long_zero;
 static long long_max = LONG_MAX;
 
-static struct ctl_table epoll_table[] = {
+static const struct ctl_table epoll_table[] = {
 	{
 		.procname	= "max_user_watches",
 		.data		= &max_user_watches,
diff --git a/fs/exec.c b/fs/exec.c
index a498391744724..506cd411f4ac2 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -2159,7 +2159,7 @@ static int proc_dointvec_minmax_coredump(const struct ctl_table *table, int writ
 	return error;
 }
 
-static struct ctl_table fs_exec_sysctls[] = {
+static const struct ctl_table fs_exec_sysctls[] = {
 	{
 		.procname	= "suid_dumpable",
 		.data		= &suid_dumpable,
diff --git a/fs/file_table.c b/fs/file_table.c
index a32171d2b83f5..7f7c378c6e31a 100644
--- a/fs/file_table.c
+++ b/fs/file_table.c
@@ -106,7 +106,7 @@ static int proc_nr_files(const struct ctl_table *table, int write, void *buffer,
 	return proc_doulongvec_minmax(table, write, buffer, lenp, ppos);
 }
 
-static struct ctl_table fs_stat_sysctls[] = {
+static const struct ctl_table fs_stat_sysctls[] = {
 	{
 		.procname	= "file-nr",
 		.data		= &files_stat,
diff --git a/fs/fuse/sysctl.c b/fs/fuse/sysctl.c
index b272bb333005a..63fb1e5bee301 100644
--- a/fs/fuse/sysctl.c
+++ b/fs/fuse/sysctl.c
@@ -13,7 +13,7 @@ static struct ctl_table_header *fuse_table_header;
 /* Bound by fuse_init_out max_pages, which is a u16 */
 static unsigned int sysctl_fuse_max_pages_limit = 65535;
 
-static struct ctl_table fuse_sysctl_table[] = {
+static const struct ctl_table fuse_sysctl_table[] = {
 	{
 		.procname	= "max_pages_limit",
 		.data		= &fuse_max_pages_limit,
diff --git a/fs/inode.c b/fs/inode.c
index 6b4c77268fc0e..5587aabdaa5ee 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -184,7 +184,7 @@ static int proc_nr_inodes(const struct ctl_table *table, int write, void *buffer
 	return proc_doulongvec_minmax(table, write, buffer, lenp, ppos);
 }
 
-static struct ctl_table inodes_sysctls[] = {
+static const struct ctl_table inodes_sysctls[] = {
 	{
 		.procname	= "inode-nr",
 		.data		= &inodes_stat,
diff --git a/fs/lockd/svc.c b/fs/lockd/svc.c
index 7ded57ec3a603..2c8eedc6c2cc9 100644
--- a/fs/lockd/svc.c
+++ b/fs/lockd/svc.c
@@ -412,7 +412,7 @@ EXPORT_SYMBOL_GPL(lockd_down);
  * Sysctl parameters (same as module parameters, different interface).
  */
 
-static struct ctl_table nlm_sysctls[] = {
+static const struct ctl_table nlm_sysctls[] = {
 	{
 		.procname	= "nlm_grace_period",
 		.data		= &nlm_grace_period,
diff --git a/fs/locks.c b/fs/locks.c
index 25afc8d9c9d12..1619cddfa7a4d 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -97,7 +97,7 @@ static int leases_enable = 1;
 static int lease_break_time = 45;
 
 #ifdef CONFIG_SYSCTL
-static struct ctl_table locks_sysctls[] = {
+static const struct ctl_table locks_sysctls[] = {
 	{
 		.procname	= "leases-enable",
 		.data		= &leases_enable,
diff --git a/fs/namei.c b/fs/namei.c
index e56c29a22d262..8c82afddd2ad8 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -1099,7 +1099,7 @@ static int sysctl_protected_fifos __read_mostly;
 static int sysctl_protected_regular __read_mostly;
 
 #ifdef CONFIG_SYSCTL
-static struct ctl_table namei_sysctls[] = {
+static const struct ctl_table namei_sysctls[] = {
 	{
 		.procname	= "protected_symlinks",
 		.data		= &sysctl_protected_symlinks,
diff --git a/fs/namespace.c b/fs/namespace.c
index 4013fbac354a2..a3ed3f2980cba 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -5985,7 +5985,7 @@ const struct proc_ns_operations mntns_operations = {
 };
 
 #ifdef CONFIG_SYSCTL
-static struct ctl_table fs_namespace_sysctls[] = {
+static const struct ctl_table fs_namespace_sysctls[] = {
 	{
 		.procname	= "mount-max",
 		.data		= &sysctl_mount_max,
diff --git a/fs/nfs/nfs4sysctl.c b/fs/nfs/nfs4sysctl.c
index 886a7c4c60b35..d1a92d8f8ba4c 100644
--- a/fs/nfs/nfs4sysctl.c
+++ b/fs/nfs/nfs4sysctl.c
@@ -17,7 +17,7 @@ static const int nfs_set_port_min;
 static const int nfs_set_port_max = 65535;
 static struct ctl_table_header *nfs4_callback_sysctl_table;
 
-static struct ctl_table nfs4_cb_sysctls[] = {
+static const struct ctl_table nfs4_cb_sysctls[] = {
 	{
 		.procname = "nfs_callback_tcpport",
 		.data = &nfs_callback_set_tcpport,
diff --git a/fs/nfs/sysctl.c b/fs/nfs/sysctl.c
index e645be1a33817..f579df0e8d673 100644
--- a/fs/nfs/sysctl.c
+++ b/fs/nfs/sysctl.c
@@ -14,7 +14,7 @@
 
 static struct ctl_table_header *nfs_callback_sysctl_table;
 
-static struct ctl_table nfs_cb_sysctls[] = {
+static const struct ctl_table nfs_cb_sysctls[] = {
 	{
 		.procname	= "nfs_mountpoint_timeout",
 		.data		= &nfs_mountpoint_expiry_timeout,
diff --git a/fs/notify/dnotify/dnotify.c b/fs/notify/dnotify/dnotify.c
index 6004dfdfdf0f3..c4cdaf5fa7eda 100644
--- a/fs/notify/dnotify/dnotify.c
+++ b/fs/notify/dnotify/dnotify.c
@@ -20,7 +20,7 @@
 
 static int dir_notify_enable __read_mostly = 1;
 #ifdef CONFIG_SYSCTL
-static struct ctl_table dnotify_sysctls[] = {
+static const struct ctl_table dnotify_sysctls[] = {
 	{
 		.procname	= "dir-notify-enable",
 		.data		= &dir_notify_enable,
diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c
index 6ff94e3122326..ba3e2d09eb44e 100644
--- a/fs/notify/fanotify/fanotify_user.c
+++ b/fs/notify/fanotify/fanotify_user.c
@@ -58,7 +58,7 @@ static int fanotify_max_queued_events __read_mostly;
 static long ft_zero = 0;
 static long ft_int_max = INT_MAX;
 
-static struct ctl_table fanotify_table[] = {
+static const struct ctl_table fanotify_table[] = {
 	{
 		.procname	= "max_user_groups",
 		.data	= &init_user_ns.ucount_max[UCOUNT_FANOTIFY_GROUPS],
diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c
index e0c48956608a5..b372fb2c56bd1 100644
--- a/fs/notify/inotify/inotify_user.c
+++ b/fs/notify/inotify/inotify_user.c
@@ -58,7 +58,7 @@ struct kmem_cache *inotify_inode_mark_cachep __ro_after_init;
 static long it_zero = 0;
 static long it_int_max = INT_MAX;
 
-static struct ctl_table inotify_table[] = {
+static const struct ctl_table inotify_table[] = {
 	{
 		.procname	= "max_user_instances",
 		.data		= &init_user_ns.ucount_max[UCOUNT_INOTIFY_INSTANCES],
diff --git a/fs/ocfs2/stackglue.c b/fs/ocfs2/stackglue.c
index 20aa37b67cfb1..ddd761cf44c87 100644
--- a/fs/ocfs2/stackglue.c
+++ b/fs/ocfs2/stackglue.c
@@ -650,7 +650,7 @@ error:
  * and easier to preserve the name.
  */
 
-static struct ctl_table ocfs2_nm_table[] = {
+static const struct ctl_table ocfs2_nm_table[] = {
 	{
 		.procname	= "hb_ctl_path",
 		.data		= ocfs2_hb_ctl_path,
diff --git a/fs/pipe.c b/fs/pipe.c
index 82fede0f2111e..94b59045ab44b 100644
--- a/fs/pipe.c
+++ b/fs/pipe.c
@@ -1478,7 +1478,7 @@ static int proc_dopipe_max_size(const struct ctl_table *table, int write,
 				 do_proc_dopipe_max_size_conv, NULL);
 }
 
-static struct ctl_table fs_pipe_sysctls[] = {
+static const struct ctl_table fs_pipe_sysctls[] = {
 	{
 		.procname	= "pipe-max-size",
 		.data		= &pipe_max_size,
diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c
index f9578918cfb25..825c5c2e09621 100644
--- a/fs/quota/dquot.c
+++ b/fs/quota/dquot.c
@@ -2926,7 +2926,7 @@ static int do_proc_dqstats(const struct ctl_table *table, int write,
 	return proc_doulongvec_minmax(table, write, buffer, lenp, ppos);
 }
 
-static struct ctl_table fs_dqstats_table[] = {
+static const struct ctl_table fs_dqstats_table[] = {
 	{
 		.procname	= "lookups",
 		.data		= &dqstats.stat[DQST_LOOKUPS],
diff --git a/fs/sysctls.c b/fs/sysctls.c
index 8dbde9a802fa4..ad429dffeb4b7 100644
--- a/fs/sysctls.c
+++ b/fs/sysctls.c
@@ -7,7 +7,7 @@
 #include <linux/init.h>
 #include <linux/sysctl.h>
 
-static struct ctl_table fs_shared_sysctls[] = {
+static const struct ctl_table fs_shared_sysctls[] = {
 	{
 		.procname	= "overflowuid",
 		.data		= &fs_overflowuid,
diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index 7c0bd0b55f880..97c4d71115d8a 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -36,7 +36,7 @@
 static int sysctl_unprivileged_userfaultfd __read_mostly;
 
 #ifdef CONFIG_SYSCTL
-static struct ctl_table vm_userfaultfd_table[] = {
+static const struct ctl_table vm_userfaultfd_table[] = {
 	{
 		.procname	= "unprivileged_userfaultfd",
 		.data		= &sysctl_unprivileged_userfaultfd,
diff --git a/fs/verity/init.c b/fs/verity/init.c
index f440f0e61e3e6..6e8d33b50240e 100644
--- a/fs/verity/init.c
+++ b/fs/verity/init.c
@@ -10,7 +10,7 @@
 #include <linux/ratelimit.h>
 
 #ifdef CONFIG_SYSCTL
-static struct ctl_table fsverity_sysctl_table[] = {
+static const struct ctl_table fsverity_sysctl_table[] = {
 #ifdef CONFIG_FS_VERITY_BUILTIN_SIGNATURES
 	{
 		.procname       = "require_signatures",
diff --git a/fs/xfs/xfs_sysctl.c b/fs/xfs/xfs_sysctl.c
index c84df23b494d3..751dc74a30671 100644
--- a/fs/xfs/xfs_sysctl.c
+++ b/fs/xfs/xfs_sysctl.c
@@ -66,7 +66,7 @@ xfs_deprecated_dointvec_minmax(
 	return proc_dointvec_minmax(ctl, write, buffer, lenp, ppos);
 }
 
-static struct ctl_table xfs_table[] = {
+static const struct ctl_table xfs_table[] = {
 	{
 		.procname	= "irix_sgid_inherit",
 		.data		= &xfs_params.sgid_inherit.val,
diff --git a/init/do_mounts_initrd.c b/init/do_mounts_initrd.c
index f86ef92a6c461..f6867bad0d782 100644
--- a/init/do_mounts_initrd.c
+++ b/init/do_mounts_initrd.c
@@ -21,7 +21,7 @@ phys_addr_t phys_initrd_start __initdata;
 unsigned long phys_initrd_size __initdata;
 
 #ifdef CONFIG_SYSCTL
-static struct ctl_table kern_do_mounts_initrd_table[] = {
+static const struct ctl_table kern_do_mounts_initrd_table[] = {
 	{
 		.procname       = "real-root-dev",
 		.data           = &real_root_dev,
diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index 7bfbc7c223677..5a0f8a5041d66 100644
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -157,7 +157,7 @@ static int __read_mostly sysctl_io_uring_disabled;
 static int __read_mostly sysctl_io_uring_group = -1;
 
 #ifdef CONFIG_SYSCTL
-static struct ctl_table kernel_io_uring_disabled_table[] = {
+static const struct ctl_table kernel_io_uring_disabled_table[] = {
 	{
 		.procname	= "io_uring_disabled",
 		.data		= &sysctl_io_uring_disabled,
diff --git a/ipc/ipc_sysctl.c b/ipc/ipc_sysctl.c
index 54318e0b45578..15b17e86e198c 100644
--- a/ipc/ipc_sysctl.c
+++ b/ipc/ipc_sysctl.c
@@ -73,7 +73,7 @@ int ipc_mni = IPCMNI;
 int ipc_mni_shift = IPCMNI_SHIFT;
 int ipc_min_cycle = RADIX_TREE_MAP_SIZE;
 
-static struct ctl_table ipc_sysctls[] = {
+static const struct ctl_table ipc_sysctls[] = {
 	{
 		.procname	= "shmmax",
 		.data		= &init_ipc_ns.shm_ctlmax,
diff --git a/ipc/mq_sysctl.c b/ipc/mq_sysctl.c
index b70dc2ff22d84..0dd12e1c9f53e 100644
--- a/ipc/mq_sysctl.c
+++ b/ipc/mq_sysctl.c
@@ -20,7 +20,7 @@ static int msg_max_limit_max = HARD_MSGMAX;
 static int msg_maxsize_limit_min = MIN_MSGSIZEMAX;
 static int msg_maxsize_limit_max = HARD_MSGSIZEMAX;
 
-static struct ctl_table mq_sysctls[] = {
+static const struct ctl_table mq_sysctls[] = {
 	{
 		.procname	= "queues_max",
 		.data		= &init_ipc_ns.mq_queues_max,
diff --git a/kernel/acct.c b/kernel/acct.c
index 179848ad33e97..31222e8cd534f 100644
--- a/kernel/acct.c
+++ b/kernel/acct.c
@@ -76,7 +76,7 @@ static int acct_parm[3] = {4, 2, 30};
 #define ACCT_TIMEOUT	(acct_parm[2])	/* foo second timeout between checks */
 
 #ifdef CONFIG_SYSCTL
-static struct ctl_table kern_acct_table[] = {
+static const struct ctl_table kern_acct_table[] = {
 	{
 		.procname       = "acct",
 		.data           = &acct_parm,
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 0daf098e32074..c420edbfb7c87 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -6128,7 +6128,7 @@ static int bpf_unpriv_handler(const struct ctl_table *table, int write,
 	return ret;
 }
 
-static struct ctl_table bpf_syscall_table[] = {
+static const struct ctl_table bpf_syscall_table[] = {
 	{
 		.procname	= "unprivileged_bpf_disabled",
 		.data		= &sysctl_unprivileged_bpf_disabled,
diff --git a/kernel/delayacct.c b/kernel/delayacct.c
index b238eb8c6573a..eb63a021ac041 100644
--- a/kernel/delayacct.c
+++ b/kernel/delayacct.c
@@ -64,7 +64,7 @@ static int sysctl_delayacct(const struct ctl_table *table, int write, void *buff
 	return err;
 }
 
-static struct ctl_table kern_delayacct_table[] = {
+static const struct ctl_table kern_delayacct_table[] = {
 	{
 		.procname       = "task_delayacct",
 		.data           = NULL,
diff --git a/kernel/exit.c b/kernel/exit.c
index 1dcddfe537ee3..3485e5fc499e4 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -85,7 +85,7 @@
 static unsigned int oops_limit = 10000;
 
 #ifdef CONFIG_SYSCTL
-static struct ctl_table kern_exit_table[] = {
+static const struct ctl_table kern_exit_table[] = {
 	{
 		.procname       = "oops_limit",
 		.data           = &oops_limit,
diff --git a/kernel/hung_task.c b/kernel/hung_task.c
index 953169893a95e..04efa7a6e69bf 100644
--- a/kernel/hung_task.c
+++ b/kernel/hung_task.c
@@ -274,7 +274,7 @@ static int proc_dohung_task_timeout_secs(const struct ctl_table *table, int writ
  * and hung_task_check_interval_secs
  */
 static const unsigned long hung_task_timeout_max = (LONG_MAX / HZ);
-static struct ctl_table hung_task_sysctls[] = {
+static const struct ctl_table hung_task_sysctls[] = {
 #ifdef CONFIG_SMP
 	{
 		.procname	= "hung_task_all_cpu_backtrace",
diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c
index b424a5c6ae87e..c0bdc1686154d 100644
--- a/kernel/kexec_core.c
+++ b/kernel/kexec_core.c
@@ -925,7 +925,7 @@ static int kexec_limit_handler(const struct ctl_table *table, int write,
 	return proc_dointvec(&tmp, write, buffer, lenp, ppos);
 }
 
-static struct ctl_table kexec_core_sysctls[] = {
+static const struct ctl_table kexec_core_sysctls[] = {
 	{
 		.procname	= "kexec_load_disabled",
 		.data		= &kexec_load_disabled,
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 0305692106709..88aeac84e4c05 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -946,7 +946,7 @@ static int proc_kprobes_optimization_handler(const struct ctl_table *table,
 	return ret;
 }
 
-static struct ctl_table kprobe_sysctls[] = {
+static const struct ctl_table kprobe_sysctls[] = {
 	{
 		.procname	= "kprobes-optimization",
 		.data		= &sysctl_kprobes_optimization,
diff --git a/kernel/latencytop.c b/kernel/latencytop.c
index 77ee3ea8a573c..d4281d1e13a63 100644
--- a/kernel/latencytop.c
+++ b/kernel/latencytop.c
@@ -77,7 +77,7 @@ static int sysctl_latencytop(const struct ctl_table *table, int write, void *buf
 	return err;
 }
 
-static struct ctl_table latencytop_sysctl[] = {
+static const struct ctl_table latencytop_sysctl[] = {
 	{
 		.procname   = "latencytop",
 		.data       = &latencytop_enabled,
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index 29acd238dad70..4470680f02269 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -79,7 +79,7 @@ module_param(lock_stat, int, 0644);
 #endif
 
 #ifdef CONFIG_SYSCTL
-static struct ctl_table kern_lockdep_table[] = {
+static const struct ctl_table kern_lockdep_table[] = {
 #ifdef CONFIG_PROVE_LOCKING
 	{
 		.procname       = "prove_locking",
diff --git a/kernel/panic.c b/kernel/panic.c
index fbc59b3b64d0b..d8635d5cecb25 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -84,7 +84,7 @@ ATOMIC_NOTIFIER_HEAD(panic_notifier_list);
 EXPORT_SYMBOL(panic_notifier_list);
 
 #ifdef CONFIG_SYSCTL
-static struct ctl_table kern_panic_table[] = {
+static const struct ctl_table kern_panic_table[] = {
 #ifdef CONFIG_SMP
 	{
 		.procname       = "oops_all_cpu_backtrace",
diff --git a/kernel/pid.c b/kernel/pid.c
index 3a10a7b6fcf80..924084713be8b 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -695,7 +695,7 @@ static struct ctl_table_root pid_table_root = {
 	.set_ownership	= pid_table_root_set_ownership,
 };
 
-static struct ctl_table pid_table[] = {
+static const struct ctl_table pid_table[] = {
 	{
 		.procname	= "pid_max",
 		.data		= &init_pid_ns.pid_max,
diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c
index f1ffa032fc320..8f6cfec87555a 100644
--- a/kernel/pid_namespace.c
+++ b/kernel/pid_namespace.c
@@ -303,7 +303,7 @@ static int pid_ns_ctl_handler(const struct ctl_table *table, int write,
 	return ret;
 }
 
-static struct ctl_table pid_ns_ctl_table[] = {
+static const struct ctl_table pid_ns_ctl_table[] = {
 	{
 		.procname = "ns_last_pid",
 		.maxlen = sizeof(int),
diff --git a/kernel/pid_sysctl.h b/kernel/pid_sysctl.h
index 18ecaef6be416..5d8f981de7c56 100644
--- a/kernel/pid_sysctl.h
+++ b/kernel/pid_sysctl.h
@@ -31,7 +31,7 @@ static int pid_mfd_noexec_dointvec_minmax(const struct ctl_table *table,
 	return err;
 }
 
-static struct ctl_table pid_ns_ctl_table_vm[] = {
+static const struct ctl_table pid_ns_ctl_table_vm[] = {
 	{
 		.procname	= "memfd_noexec",
 		.data		= &init_pid_ns.memfd_noexec_scope,
diff --git a/kernel/printk/sysctl.c b/kernel/printk/sysctl.c
index f5072dc85f7aa..da77f3f5c1fe9 100644
--- a/kernel/printk/sysctl.c
+++ b/kernel/printk/sysctl.c
@@ -20,7 +20,7 @@ static int proc_dointvec_minmax_sysadmin(const struct ctl_table *table, int writ
 	return proc_dointvec_minmax(table, write, buffer, lenp, ppos);
 }
 
-static struct ctl_table printk_sysctls[] = {
+static const struct ctl_table printk_sysctls[] = {
 	{
 		.procname	= "printk",
 		.data		= &console_loglevel,
diff --git a/kernel/reboot.c b/kernel/reboot.c
index a701000bab347..b5a8569e5d81f 100644
--- a/kernel/reboot.c
+++ b/kernel/reboot.c
@@ -1287,7 +1287,7 @@ static struct attribute *reboot_attrs[] = {
 };
 
 #ifdef CONFIG_SYSCTL
-static struct ctl_table kern_reboot_table[] = {
+static const struct ctl_table kern_reboot_table[] = {
 	{
 		.procname       = "poweroff_cmd",
 		.data           = &poweroff_cmd,
diff --git a/kernel/sched/autogroup.c b/kernel/sched/autogroup.c
index db68a964e34e2..83d46b9b8ec8c 100644
--- a/kernel/sched/autogroup.c
+++ b/kernel/sched/autogroup.c
@@ -9,7 +9,7 @@ static struct autogroup autogroup_default;
 static atomic_t autogroup_seq_nr;
 
 #ifdef CONFIG_SYSCTL
-static struct ctl_table sched_autogroup_sysctls[] = {
+static const struct ctl_table sched_autogroup_sysctls[] = {
 	{
 		.procname       = "sched_autogroup_enabled",
 		.data           = &sysctl_sched_autogroup_enabled,
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 9142a0394d466..165c90ba64ea9 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -4654,7 +4654,7 @@ static int sysctl_schedstats(const struct ctl_table *table, int write, void *buf
 #endif /* CONFIG_SCHEDSTATS */
 
 #ifdef CONFIG_SYSCTL
-static struct ctl_table sched_core_sysctls[] = {
+static const struct ctl_table sched_core_sysctls[] = {
 #ifdef CONFIG_SCHEDSTATS
 	{
 		.procname       = "sched_schedstats",
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 62192ac79c30a..38e4537790af7 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -26,7 +26,7 @@
 static unsigned int sysctl_sched_dl_period_max = 1 << 22; /* ~4 seconds */
 static unsigned int sysctl_sched_dl_period_min = 100;     /* 100 us */
 #ifdef CONFIG_SYSCTL
-static struct ctl_table sched_dl_sysctls[] = {
+static const struct ctl_table sched_dl_sysctls[] = {
 	{
 		.procname       = "sched_deadline_period_max_us",
 		.data           = &sysctl_sched_dl_period_max,
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 1e78caa21436b..ce2e94ccad0c6 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -133,7 +133,7 @@ static unsigned int sysctl_numa_balancing_promote_rate_limit = 65536;
 #endif
 
 #ifdef CONFIG_SYSCTL
-static struct ctl_table sched_fair_sysctls[] = {
+static const struct ctl_table sched_fair_sysctls[] = {
 #ifdef CONFIG_CFS_BANDWIDTH
 	{
 		.procname       = "sched_cfs_bandwidth_slice_us",
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index bd66a46b06aca..4b8e33c615b12 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -26,7 +26,7 @@ static int sched_rt_handler(const struct ctl_table *table, int write, void *buff
 		size_t *lenp, loff_t *ppos);
 static int sched_rr_handler(const struct ctl_table *table, int write, void *buffer,
 		size_t *lenp, loff_t *ppos);
-static struct ctl_table sched_rt_sysctls[] = {
+static const struct ctl_table sched_rt_sysctls[] = {
 	{
 		.procname       = "sched_rt_period_us",
 		.data           = &sysctl_sched_rt_period,
diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index da33ec9e94ab2..c49aea8c10254 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -312,7 +312,7 @@ static int sched_energy_aware_handler(const struct ctl_table *table, int write,
 	return ret;
 }
 
-static struct ctl_table sched_energy_aware_sysctls[] = {
+static const struct ctl_table sched_energy_aware_sysctls[] = {
 	{
 		.procname       = "sched_energy_aware",
 		.data           = &sysctl_sched_energy_aware,
diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index 385d48293a5fa..f59381c4a2ffb 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -2450,7 +2450,7 @@ static int seccomp_actions_logged_handler(const struct ctl_table *ro_table, int
 	return ret;
 }
 
-static struct ctl_table seccomp_sysctl_table[] = {
+static const struct ctl_table seccomp_sysctl_table[] = {
 	{
 		.procname	= "actions_avail",
 		.data		= (void *) &seccomp_actions_avail,
diff --git a/kernel/signal.c b/kernel/signal.c
index a2afd54303f08..875e97f6205a2 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -4950,7 +4950,7 @@ static inline void siginfo_buildtime_checks(void)
 }
 
 #if defined(CONFIG_SYSCTL)
-static struct ctl_table signal_debug_table[] = {
+static const struct ctl_table signal_debug_table[] = {
 #ifdef CONFIG_SYSCTL_EXCEPTION_TRACE
 	{
 		.procname	= "exception-trace",
diff --git a/kernel/stackleak.c b/kernel/stackleak.c
index 0f4804f28c616..bb65321761b43 100644
--- a/kernel/stackleak.c
+++ b/kernel/stackleak.c
@@ -45,7 +45,7 @@ static int stack_erasing_sysctl(const struct ctl_table *table, int write,
 					str_enabled_disabled(state));
 	return ret;
 }
-static struct ctl_table stackleak_sysctls[] = {
+static const struct ctl_table stackleak_sysctls[] = {
 	{
 		.procname	= "stack_erasing",
 		.data		= NULL,
diff --git a/kernel/sysctl-test.c b/kernel/sysctl-test.c
index 3ac98bb7fb822..eb2842bd05577 100644
--- a/kernel/sysctl-test.c
+++ b/kernel/sysctl-test.c
@@ -374,7 +374,7 @@ static void sysctl_test_register_sysctl_sz_invalid_extra_value(
 		struct kunit *test)
 {
 	unsigned char data = 0;
-	struct ctl_table table_foo[] = {
+	const struct ctl_table table_foo[] = {
 		{
 			.procname	= "foo",
 			.data		= &data,
@@ -386,7 +386,7 @@ static void sysctl_test_register_sysctl_sz_invalid_extra_value(
 		},
 	};
 
-	struct ctl_table table_bar[] = {
+	const struct ctl_table table_bar[] = {
 		{
 			.procname	= "bar",
 			.data		= &data,
@@ -398,7 +398,7 @@ static void sysctl_test_register_sysctl_sz_invalid_extra_value(
 		},
 	};
 
-	struct ctl_table table_qux[] = {
+	const struct ctl_table table_qux[] = {
 		{
 			.procname	= "qux",
 			.data		= &data,
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 7ae7a41368551..cb57da499ebb1 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -1609,7 +1609,7 @@ int proc_do_static_key(const struct ctl_table *table, int write,
 	return ret;
 }
 
-static struct ctl_table kern_table[] = {
+static const struct ctl_table kern_table[] = {
 	{
 		.procname	= "panic",
 		.data		= &panic_timeout,
@@ -2021,7 +2021,7 @@ static struct ctl_table kern_table[] = {
 #endif
 };
 
-static struct ctl_table vm_table[] = {
+static const struct ctl_table vm_table[] = {
 	{
 		.procname	= "overcommit_memory",
 		.data		= &sysctl_overcommit_memory,
diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index 40706cb369205..c8f776dc6ee08 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -301,7 +301,7 @@ static int timer_migration_handler(const struct ctl_table *table, int write,
 	return ret;
 }
 
-static struct ctl_table timer_sysctl[] = {
+static const struct ctl_table timer_sysctl[] = {
 	{
 		.procname	= "timer_migration",
 		.data		= &sysctl_timer_migration,
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index f79eb9386c7fa..728ecda6e8d4d 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -8780,7 +8780,7 @@ ftrace_enable_sysctl(const struct ctl_table *table, int write,
 	return 0;
 }
 
-static struct ctl_table ftrace_sysctls[] = {
+static const struct ctl_table ftrace_sysctls[] = {
 	{
 		.procname       = "ftrace_enabled",
 		.data           = &ftrace_enabled,
diff --git a/kernel/trace/trace_events_user.c b/kernel/trace/trace_events_user.c
index 17bcad8f79de7..97325fbd62836 100644
--- a/kernel/trace/trace_events_user.c
+++ b/kernel/trace/trace_events_user.c
@@ -2899,7 +2899,7 @@ static int set_max_user_events_sysctl(const struct ctl_table *table, int write,
 	return ret;
 }
 
-static struct ctl_table user_event_sysctls[] = {
+static const struct ctl_table user_event_sysctls[] = {
 	{
 		.procname	= "user_events_max",
 		.data		= &max_user_events,
diff --git a/kernel/umh.c b/kernel/umh.c
index be92342707773..b4da45a3a7cfc 100644
--- a/kernel/umh.c
+++ b/kernel/umh.c
@@ -544,7 +544,7 @@ static int proc_cap_handler(const struct ctl_table *table, int write,
 	return 0;
 }
 
-static struct ctl_table usermodehelper_table[] = {
+static const struct ctl_table usermodehelper_table[] = {
 	{
 		.procname	= "bset",
 		.data		= &usermodehelper_bset,
diff --git a/kernel/utsname_sysctl.c b/kernel/utsname_sysctl.c
index 7282f61a8650f..bfbaaecb1dd43 100644
--- a/kernel/utsname_sysctl.c
+++ b/kernel/utsname_sysctl.c
@@ -75,7 +75,7 @@ static DEFINE_CTL_TABLE_POLL(hostname_poll);
 static DEFINE_CTL_TABLE_POLL(domainname_poll);
 
 // Note: update 'enum uts_proc' to match any changes to this table
-static struct ctl_table uts_kern_table[] = {
+static const struct ctl_table uts_kern_table[] = {
 	{
 		.procname	= "arch",
 		.data		= init_uts_ns.name.machine,
@@ -129,7 +129,7 @@ static struct ctl_table uts_kern_table[] = {
  */
 void uts_proc_notify(enum uts_proc proc)
 {
-	struct ctl_table *table = &uts_kern_table[proc];
+	const struct ctl_table *table = &uts_kern_table[proc];
 
 	proc_sys_poll_notify(table->poll);
 }
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index 177abb7d0d4e5..b2da7de39d06d 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -1094,7 +1094,7 @@ static int proc_watchdog_cpumask(const struct ctl_table *table, int write,
 
 static const int sixty = 60;
 
-static struct ctl_table watchdog_sysctls[] = {
+static const struct ctl_table watchdog_sysctls[] = {
 	{
 		.procname       = "watchdog",
 		.data		= &watchdog_user_enabled,
diff --git a/lib/test_sysctl.c b/lib/test_sysctl.c
index b6696fa1d4262..4249e0cc8aaff 100644
--- a/lib/test_sysctl.c
+++ b/lib/test_sysctl.c
@@ -71,7 +71,7 @@ static struct test_sysctl_data test_data = {
 };
 
 /* These are all under /proc/sys/debug/test_sysctl/ */
-static struct ctl_table test_table[] = {
+static const struct ctl_table test_table[] = {
 	{
 		.procname	= "int_0001",
 		.data		= &test_data.int_0001,
@@ -177,7 +177,7 @@ static int test_sysctl_setup_node_tests(void)
 }
 
 /* Used to test that unregister actually removes the directory */
-static struct ctl_table test_table_unregister[] = {
+static const struct ctl_table test_table_unregister[] = {
 	{
 		.procname	= "unregister_error",
 		.data		= &test_data.int_0001,
@@ -220,7 +220,7 @@ static int test_sysctl_run_register_mount_point(void)
 	return 0;
 }
 
-static struct ctl_table test_table_empty[] = { };
+static const struct ctl_table test_table_empty[] = { };
 
 static int test_sysctl_run_register_empty(void)
 {
diff --git a/mm/compaction.c b/mm/compaction.c
index 73e80b2fb22e5..bcc0df0066dc3 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -3272,7 +3272,7 @@ static int proc_dointvec_minmax_warn_RT_change(const struct ctl_table *table,
 	return ret;
 }
 
-static struct ctl_table vm_compaction[] = {
+static const struct ctl_table vm_compaction[] = {
 	{
 		.procname	= "compact_memory",
 		.data		= &sysctl_compact_memory,
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 87761b042ed04..3b25b69aa94f1 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -4867,7 +4867,7 @@ out:
 	return ret;
 }
 
-static struct ctl_table hugetlb_table[] = {
+static const struct ctl_table hugetlb_table[] = {
 	{
 		.procname	= "nr_hugepages",
 		.data		= NULL,
diff --git a/mm/hugetlb_vmemmap.c b/mm/hugetlb_vmemmap.c
index 57b7f591eee82..7735972add012 100644
--- a/mm/hugetlb_vmemmap.c
+++ b/mm/hugetlb_vmemmap.c
@@ -693,7 +693,7 @@ void hugetlb_vmemmap_optimize_folios(struct hstate *h, struct list_head *folio_l
 	free_vmemmap_page_list(&vmemmap_pages);
 }
 
-static struct ctl_table hugetlb_vmemmap_sysctls[] = {
+static const struct ctl_table hugetlb_vmemmap_sysctls[] = {
 	{
 		.procname	= "hugetlb_optimize_vmemmap",
 		.data		= &vmemmap_optimize_enabled,
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index a7b8ccd29b6f5..995a15eb67e2c 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -124,7 +124,7 @@ const struct attribute_group memory_failure_attr_group = {
 	.attrs = memory_failure_attr,
 };
 
-static struct ctl_table memory_failure_table[] = {
+static const struct ctl_table memory_failure_table[] = {
 	{
 		.procname	= "memory_failure_early_kill",
 		.data		= &sysctl_memory_failure_early_kill,
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 044ebab2c9411..1cf121ad7085c 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -705,7 +705,7 @@ static void queue_oom_reaper(struct task_struct *tsk)
 }
 
 #ifdef CONFIG_SYSCTL
-static struct ctl_table vm_oom_kill_table[] = {
+static const struct ctl_table vm_oom_kill_table[] = {
 	{
 		.procname	= "panic_on_oom",
 		.data		= &sysctl_panic_on_oom,
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 4f5970723cf2a..eb55ece39c565 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -2298,7 +2298,7 @@ static int page_writeback_cpu_online(unsigned int cpu)
 /* this is needed for the proc_doulongvec_minmax of vm_dirty_bytes */
 static const unsigned long dirty_bytes_min = 2 * PAGE_SIZE;
 
-static struct ctl_table vm_page_writeback_sysctls[] = {
+static const struct ctl_table vm_page_writeback_sysctls[] = {
 	{
 		.procname   = "dirty_background_ratio",
 		.data       = &dirty_background_ratio,
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 6e469c7ef9a41..579789600a3c7 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -6166,7 +6166,7 @@ out:
 	return ret;
 }
 
-static struct ctl_table page_alloc_sysctl_table[] = {
+static const struct ctl_table page_alloc_sysctl_table[] = {
 	{
 		.procname	= "min_free_kbytes",
 		.data		= &min_free_kbytes,
diff --git a/security/apparmor/lsm.c b/security/apparmor/lsm.c
index 1edc12862a7de..9b6c2f157f83e 100644
--- a/security/apparmor/lsm.c
+++ b/security/apparmor/lsm.c
@@ -2038,7 +2038,7 @@ static int apparmor_dointvec(const struct ctl_table *table, int write,
 	return proc_dointvec(table, write, buffer, lenp, ppos);
 }
 
-static struct ctl_table apparmor_sysctl_table[] = {
+static const struct ctl_table apparmor_sysctl_table[] = {
 #ifdef CONFIG_USER_NS
 	{
 		.procname       = "unprivileged_userns_apparmor_policy",
diff --git a/security/keys/sysctl.c b/security/keys/sysctl.c
index 91f000eef3ad8..cde08c478f327 100644
--- a/security/keys/sysctl.c
+++ b/security/keys/sysctl.c
@@ -9,7 +9,7 @@
 #include <linux/sysctl.h>
 #include "internal.h"
 
-static struct ctl_table key_sysctls[] = {
+static const struct ctl_table key_sysctls[] = {
 	{
 		.procname = "maxkeys",
 		.data = &key_quota_maxkeys,
diff --git a/security/yama/yama_lsm.c b/security/yama/yama_lsm.c
index 1a2d02fee09bf..1971710620c18 100644
--- a/security/yama/yama_lsm.c
+++ b/security/yama/yama_lsm.c
@@ -452,7 +452,7 @@ static int yama_dointvec_minmax(const struct ctl_table *table, int write,
 
 static int max_scope = YAMA_SCOPE_NO_ATTACH;
 
-static struct ctl_table yama_sysctl_table[] = {
+static const struct ctl_table yama_sysctl_table[] = {
 	{
 		.procname       = "ptrace_scope",
 		.data           = &ptrace_scope,
-- 
cgit v1.2.3