Merge tag 'sysctl-6.11-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/sysctl/sysctl

Pull sysctl updates from Joel Granados:

 - Remove "->procname == NULL" check when iterating through sysctl table
   arrays

   Removing sentinels in ctl_table arrays reduces the build time size
   and runtime memory consumed by ~64 bytes per array. With all
   ctl_table sentinels gone, the additional check for ->procname == NULL
   that worked in tandem with the ARRAY_SIZE to calculate the size of
   the ctl_table arrays is no longer needed and has been removed. The
   sysctl register functions now returns an error if a sentinel is used.

 - Preparation patches for sysctl constification

   Constifying ctl_table structs prevents the modification of
   proc_handler function pointers as they would reside in .rodata. The
   ctl_table arguments in sysctl utility functions are const qualified
   in preparation for a future treewide proc_handler argument
   constification commit.

 - Misc fixes

   Increase robustness of set_ownership by providing sane default
   ownership values in case the callee doesn't set them. Bound check
   proc_dou8vec_minmax to avoid loading buggy modules and give sysctl
   testing module a name to avoid compiler complaints.

* tag 'sysctl-6.11-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/sysctl/sysctl:
  sysctl: Warn on an empty procname element
  sysctl: Remove ctl_table sentinel code comments
  sysctl: Remove "child" sysctl code comments
  sysctl: Remove superfluous empty allocations from sysctl internals
  sysctl: Replace nr_entries with ctl_table_size in new_links
  sysctl: Remove check for sentinel element in ctl_table arrays
  mm profiling: Remove superfluous sentinel element from ctl_table
  locking: Remove superfluous sentinel element from kern_lockdep_table
  sysctl: Add module description to sysctl-testing
  sysctl: constify ctl_table arguments of utility function
  utsname: constify ctl_table arguments of utility function
  sysctl: move the extra1/2 boundary check of u8 to sysctl_check_table_array
  sysctl: always initialize i_uid/i_gid

Author: torvalds

fs/proc/proc_sysctl.c

@@ -21,7 +21,7 @@
 
 #define list_for_each_table_entry(entry, header)	\
 	entry = header->ctl_table;			\
-	for (size_t i = 0 ; i < header->ctl_table_size && entry->procname; ++i, entry++)
+	for (size_t i = 0 ; i < header->ctl_table_size; ++i, entry++)
 
 static const struct dentry_operations proc_sys_dentry_operations;
 static const struct file_operations proc_sys_file_operations;
@@ -476,12 +476,10 @@ static struct inode *proc_sys_make_inode(struct super_block *sb,
 			make_empty_dir_inode(inode);
 	}
 
+	inode->i_uid = GLOBAL_ROOT_UID;
+	inode->i_gid = GLOBAL_ROOT_GID;
 	if (root->set_ownership)
 		root->set_ownership(head, &inode->i_uid, &inode->i_gid);
-	else {
-		inode->i_uid = GLOBAL_ROOT_UID;
-		inode->i_gid = GLOBAL_ROOT_GID;
-	}
 
 	return inode;
 }
@@ -951,14 +949,14 @@ static struct ctl_dir *new_dir(struct ctl_table_set *set,
 	char *new_name;
 
 	new = kzalloc(sizeof(*new) + sizeof(struct ctl_node) +
-		      sizeof(struct ctl_table)*2 +  namelen + 1,
+		      sizeof(struct ctl_table) +  namelen + 1,
 		      GFP_KERNEL);
 	if (!new)
 		return NULL;
 
 	node = (struct ctl_node *)(new + 1);
 	table = (struct ctl_table *)(node + 1);
-	new_name = (char *)(table + 2);
+	new_name = (char *)(table + 1);
 	memcpy(new_name, name, namelen);
 	table[0].procname = new_name;
 	table[0].mode = S_IFDIR|S_IRUGO|S_IXUGO;
@@ -1093,6 +1091,7 @@ static int sysctl_err(const char *path, struct ctl_table *table, char *fmt, ...)
 
 static int sysctl_check_table_array(const char *path, struct ctl_table *table)
 {
+	unsigned int extra;
 	int err = 0;
 
 	if ((table->proc_handler == proc_douintvec) ||
@@ -1104,6 +1103,19 @@ static int sysctl_check_table_array(const char *path, struct ctl_table *table)
 	if (table->proc_handler == proc_dou8vec_minmax) {
 		if (table->maxlen != sizeof(u8))
 			err |= sysctl_err(path, table, "array not allowed");
+
+		if (table->extra1) {
+			extra = *(unsigned int *) table->extra1;
+			if (extra > 255U)
+				err |= sysctl_err(path, table,
+						"range value too large for proc_dou8vec_minmax");
+		}
+		if (table->extra2) {
+			extra = *(unsigned int *) table->extra2;
+			if (extra > 255U)
+				err |= sysctl_err(path, table,
+						"range value too large for proc_dou8vec_minmax");
+		}
 	}
 
 	if (table->proc_handler == proc_dobool) {
@@ -1119,6 +1131,8 @@ static int sysctl_check_table(const char *path, struct ctl_table_header *header)
 	struct ctl_table *entry;
 	int err = 0;
 	list_for_each_table_entry(entry, header) {
+		if (!entry->procname)
+			err |= sysctl_err(path, entry, "procname is null");
 		if ((entry->proc_handler == proc_dostring) ||
 		    (entry->proc_handler == proc_dobool) ||
 		    (entry->proc_handler == proc_dointvec) ||
@@ -1154,27 +1168,25 @@ static struct ctl_table_header *new_links(struct ctl_dir *dir, struct ctl_table_
 	struct ctl_table_header *links;
 	struct ctl_node *node;
 	char *link_name;
-	int nr_entries, name_bytes;
+	int name_bytes;
 
 	name_bytes = 0;
-	nr_entries = 0;
 	list_for_each_table_entry(entry, head) {
-		nr_entries++;
 		name_bytes += strlen(entry->procname) + 1;
 	}
 
 	links = kzalloc(sizeof(struct ctl_table_header) +
-			sizeof(struct ctl_node)*nr_entries +
-			sizeof(struct ctl_table)*(nr_entries + 1) +
+			sizeof(struct ctl_node)*head->ctl_table_size +
+			sizeof(struct ctl_table)*head->ctl_table_size +
 			name_bytes,
 			GFP_KERNEL);
 
 	if (!links)
 		return NULL;
 
 	node = (struct ctl_node *)(links + 1);
-	link_table = (struct ctl_table *)(node + nr_entries);
-	link_name = (char *)&link_table[nr_entries + 1];
+	link_table = (struct ctl_table *)(node + head->ctl_table_size);
+	link_name = (char *)(link_table + head->ctl_table_size);
 	link = link_table;
 
 	list_for_each_table_entry(entry, head) {
@@ -1188,7 +1200,7 @@ static struct ctl_table_header *new_links(struct ctl_dir *dir, struct ctl_table_
 	}
 	init_header(links, dir->header.root, dir->header.set, node, link_table,
 		    head->ctl_table_size);
-	links->nreg = nr_entries;
+	links->nreg = head->ctl_table_size;
 
 	return links;
 }
@@ -1300,37 +1312,31 @@ static struct ctl_dir *sysctl_mkdir_p(struct ctl_dir *dir, const char *path)
  * __register_sysctl_table - register a leaf sysctl table
  * @set: Sysctl tree to register on
  * @path: The path to the directory the sysctl table is in.
- * @table: the top-level table structure without any child. This table
- * 	 should not be free'd after registration. So it should not be
- * 	 used on stack. It can either be a global or dynamically allocated
- * 	 by the caller and free'd later after sysctl unregistration.
+ *
+ * @table: the top-level table structure. This table should not be free'd
+ *         after registration. So it should not be used on stack. It can either
+ *         be a global or dynamically allocated by the caller and free'd later
+ *         after sysctl unregistration.
  * @table_size : The number of elements in table
  *
  * Register a sysctl table hierarchy. @table should be a filled in ctl_table
- * array. A completely 0 filled entry terminates the table.
+ * array.
  *
  * The members of the &struct ctl_table structure are used as follows:
- *
  * procname - the name of the sysctl file under /proc/sys. Set to %NULL to not
  *            enter a sysctl file
- *
- * data - a pointer to data for use by proc_handler
- *
- * maxlen - the maximum size in bytes of the data
- *
- * mode - the file permissions for the /proc/sys file
- *
- * child - must be %NULL.
- *
+ * data     - a pointer to data for use by proc_handler
+ * maxlen   - the maximum size in bytes of the data
+ * mode     - the file permissions for the /proc/sys file
+ * type     - Defines the target type (described in struct definition)
  * proc_handler - the text handler routine (described below)
  *
  * extra1, extra2 - extra pointers usable by the proc handler routines
  * XXX: we should eventually modify these to use long min / max [0]
  * [0] https://lkml.kernel.org/[email protected]
  *
  * Leaf nodes in the sysctl tree will be represented by a single file
- * under /proc; non-leaf nodes (where child is not NULL) are not allowed,
- * sysctl_check_table() verifies this.
+ * under /proc; non-leaf nodes are not allowed.
  *
  * There must be a proc_handler routine for any terminal nodes.
  * Several default handlers are available to cover common cases -

include/linux/sysctl.h

@@ -237,7 +237,7 @@ extern struct ctl_table_header *register_sysctl_mount_point(const char *path);
 
 void do_sysctl_args(void);
 bool sysctl_is_alias(char *param);
-int do_proc_douintvec(struct ctl_table *table, int write,
+int do_proc_douintvec(const struct ctl_table *table, int write,
 		      void *buffer, size_t *lenp, loff_t *ppos,
 		      int (*conv)(unsigned long *lvalp,
 				  unsigned int *valp,

kernel/locking/lockdep.c

@@ -97,7 +97,6 @@ static struct ctl_table kern_lockdep_table[] = {
 		.proc_handler   = proc_dointvec,
 	},
 #endif /* CONFIG_LOCK_STAT */
-	{ }
 };
 
 static __init int kernel_lockdep_sysctls_init(void)

kernel/sysctl-test.c

@@ -367,6 +367,54 @@ static void sysctl_test_api_dointvec_write_single_greater_int_max(
 	KUNIT_EXPECT_EQ(test, 0, *((int *)table.data));
 }
 
+/*
+ * Test that registering an invalid extra value is not allowed.
+ */
+static void sysctl_test_register_sysctl_sz_invalid_extra_value(
+		struct kunit *test)
+{
+	unsigned char data = 0;
+	struct ctl_table table_foo[] = {
+		{
+			.procname	= "foo",
+			.data		= &data,
+			.maxlen		= sizeof(u8),
+			.mode		= 0644,
+			.proc_handler	= proc_dou8vec_minmax,
+			.extra1		= SYSCTL_FOUR,
+			.extra2		= SYSCTL_ONE_THOUSAND,
+		},
+	};
+
+	struct ctl_table table_bar[] = {
+		{
+			.procname	= "bar",
+			.data		= &data,
+			.maxlen		= sizeof(u8),
+			.mode		= 0644,
+			.proc_handler	= proc_dou8vec_minmax,
+			.extra1		= SYSCTL_NEG_ONE,
+			.extra2		= SYSCTL_ONE_HUNDRED,
+		},
+	};
+
+	struct ctl_table table_qux[] = {
+		{
+			.procname	= "qux",
+			.data		= &data,
+			.maxlen		= sizeof(u8),
+			.mode		= 0644,
+			.proc_handler	= proc_dou8vec_minmax,
+			.extra1		= SYSCTL_ZERO,
+			.extra2		= SYSCTL_TWO_HUNDRED,
+		},
+	};
+
+	KUNIT_EXPECT_NULL(test, register_sysctl("foo", table_foo));
+	KUNIT_EXPECT_NULL(test, register_sysctl("foo", table_bar));
+	KUNIT_EXPECT_NOT_NULL(test, register_sysctl("foo", table_qux));
+}
+
 static struct kunit_case sysctl_test_cases[] = {
 	KUNIT_CASE(sysctl_test_api_dointvec_null_tbl_data),
 	KUNIT_CASE(sysctl_test_api_dointvec_table_maxlen_unset),
@@ -378,6 +426,7 @@ static struct kunit_case sysctl_test_cases[] = {
 	KUNIT_CASE(sysctl_test_dointvec_write_happy_single_negative),
 	KUNIT_CASE(sysctl_test_api_dointvec_write_single_less_int_min),
 	KUNIT_CASE(sysctl_test_api_dointvec_write_single_greater_int_max),
+	KUNIT_CASE(sysctl_test_register_sysctl_sz_invalid_extra_value),
 	{}
 };
 
@@ -388,4 +437,5 @@ static struct kunit_suite sysctl_test_suite = {
 
 kunit_test_suites(&sysctl_test_suite);
 
+MODULE_DESCRIPTION("KUnit test of proc sysctl");
 MODULE_LICENSE("GPL v2");

kernel/sysctl.c

@@ -205,7 +205,7 @@ static int _proc_do_string(char *data, int maxlen, int write,
 	return 0;
 }
 
-static void warn_sysctl_write(struct ctl_table *table)
+static void warn_sysctl_write(const struct ctl_table *table)
 {
 	pr_warn_once("%s wrote to %s when file position was not 0!\n"
 		"This will not be supported in the future. To silence this\n"
@@ -223,7 +223,7 @@ static void warn_sysctl_write(struct ctl_table *table)
  * handlers can ignore the return value.
  */
 static bool proc_first_pos_non_zero_ignore(loff_t *ppos,
-					   struct ctl_table *table)
+					   const struct ctl_table *table)
 {
 	if (!*ppos)
 		return false;
@@ -468,7 +468,7 @@ static int do_proc_douintvec_conv(unsigned long *lvalp,
 
 static const char proc_wspace_sep[] = { ' ', '\t', '\n' };
 
-static int __do_proc_dointvec(void *tbl_data, struct ctl_table *table,
+static int __do_proc_dointvec(void *tbl_data, const struct ctl_table *table,
 		  int write, void *buffer,
 		  size_t *lenp, loff_t *ppos,
 		  int (*conv)(bool *negp, unsigned long *lvalp, int *valp,
@@ -541,7 +541,7 @@ static int __do_proc_dointvec(void *tbl_data, struct ctl_table *table,
 	return err;
 }
 
-static int do_proc_dointvec(struct ctl_table *table, int write,
+static int do_proc_dointvec(const struct ctl_table *table, int write,
 		  void *buffer, size_t *lenp, loff_t *ppos,
 		  int (*conv)(bool *negp, unsigned long *lvalp, int *valp,
 			      int write, void *data),
@@ -552,7 +552,7 @@ static int do_proc_dointvec(struct ctl_table *table, int write,
 }
 
 static int do_proc_douintvec_w(unsigned int *tbl_data,
-			       struct ctl_table *table,
+			       const struct ctl_table *table,
 			       void *buffer,
 			       size_t *lenp, loff_t *ppos,
 			       int (*conv)(unsigned long *lvalp,
@@ -639,7 +639,7 @@ static int do_proc_douintvec_r(unsigned int *tbl_data, void *buffer,
 	return err;
 }
 
-static int __do_proc_douintvec(void *tbl_data, struct ctl_table *table,
+static int __do_proc_douintvec(void *tbl_data, const struct ctl_table *table,
 			       int write, void *buffer,
 			       size_t *lenp, loff_t *ppos,
 			       int (*conv)(unsigned long *lvalp,
@@ -675,7 +675,7 @@ static int __do_proc_douintvec(void *tbl_data, struct ctl_table *table,
 	return do_proc_douintvec_r(i, buffer, lenp, ppos, conv, data);
 }
 
-int do_proc_douintvec(struct ctl_table *table, int write,
+int do_proc_douintvec(const struct ctl_table *table, int write,
 		      void *buffer, size_t *lenp, loff_t *ppos,
 		      int (*conv)(unsigned long *lvalp,
 				  unsigned int *valp,
@@ -977,16 +977,10 @@ int proc_dou8vec_minmax(struct ctl_table *table, int write,
 	if (table->maxlen != sizeof(u8))
 		return -EINVAL;
 
-	if (table->extra1) {
+	if (table->extra1)
 		min = *(unsigned int *) table->extra1;
-		if (min > 255U)
-			return -EINVAL;
-	}
-	if (table->extra2) {
+	if (table->extra2)
 		max = *(unsigned int *) table->extra2;
-		if (max > 255U)
-			return -EINVAL;
-	}
 
 	tmp = *table;
 
@@ -1023,8 +1017,9 @@ static int sysrq_sysctl_handler(struct ctl_table *table, int write,
 }
 #endif
 
-static int __do_proc_doulongvec_minmax(void *data, struct ctl_table *table,
-		int write, void *buffer, size_t *lenp, loff_t *ppos,
+static int __do_proc_doulongvec_minmax(void *data,
+		const struct ctl_table *table, int write,
+		void *buffer, size_t *lenp, loff_t *ppos,
 		unsigned long convmul, unsigned long convdiv)
 {
 	unsigned long *i, *min, *max;
@@ -1096,7 +1091,7 @@ static int __do_proc_doulongvec_minmax(void *data, struct ctl_table *table,
 	return err;
 }
 
-static int do_proc_doulongvec_minmax(struct ctl_table *table, int write,
+static int do_proc_doulongvec_minmax(const struct ctl_table *table, int write,
 		void *buffer, size_t *lenp, loff_t *ppos, unsigned long convmul,
 		unsigned long convdiv)
 {

kernel/utsname_sysctl.c

@@ -15,7 +15,7 @@
 
 #ifdef CONFIG_PROC_SYSCTL
 
-static void *get_uts(struct ctl_table *table)
+static void *get_uts(const struct ctl_table *table)
 {
 	char *which = table->data;
 	struct uts_namespace *uts_ns;

lib/alloc_tag.c

@@ -239,7 +239,6 @@ static struct ctl_table memory_allocation_profiling_sysctls[] = {
 #endif
 		.proc_handler	= proc_do_static_key,
 	},
-	{ }
 };
 
 static void __init sysctl_init(void)