1 files changed, 243 insertions, 63 deletions

diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h
index 14a8ff2de11e..288fe0055cd5 100644
--- a/include/linux/sysctl.h
+++ b/include/linux/sysctl.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * sysctl.h: General linux system control interface
  *
@@ -25,57 +26,202 @@
 #include <linux/rcupdate.h>
 #include <linux/wait.h>
 #include <linux/rbtree.h>
+#include <linux/uidgid.h>
 #include <uapi/linux/sysctl.h>
 
 /* For the /proc/sys support */
+struct completion;
 struct ctl_table;
 struct nsproxy;
 struct ctl_table_root;
 struct ctl_table_header;
 struct ctl_dir;
 
-typedef struct ctl_table ctl_table;
-
-typedef int proc_handler (struct ctl_table *ctl, int write,
-			  void __user *buffer, size_t *lenp, loff_t *ppos);
-
-extern int proc_dostring(struct ctl_table *, int,
-			 void __user *, size_t *, loff_t *);
-extern int proc_dointvec(struct ctl_table *, int,
-			 void __user *, size_t *, loff_t *);
-extern int proc_dointvec_minmax(struct ctl_table *, int,
-				void __user *, size_t *, loff_t *);
-extern int proc_dointvec_jiffies(struct ctl_table *, int,
-				 void __user *, size_t *, loff_t *);
-extern int proc_dointvec_userhz_jiffies(struct ctl_table *, int,
-					void __user *, size_t *, loff_t *);
-extern int proc_dointvec_ms_jiffies(struct ctl_table *, int,
-				    void __user *, size_t *, loff_t *);
-extern int proc_doulongvec_minmax(struct ctl_table *, int,
-				  void __user *, size_t *, loff_t *);
-extern int proc_doulongvec_ms_jiffies_minmax(struct ctl_table *table, int,
-				      void __user *, size_t *, loff_t *);
-extern int proc_do_large_bitmap(struct ctl_table *, int,
-				void __user *, size_t *, loff_t *);
+/* Keep the same order as in fs/proc/proc_sysctl.c */
+#define SYSCTL_ZERO			((void *)&sysctl_vals[0])
+#define SYSCTL_ONE			((void *)&sysctl_vals[1])
+#define SYSCTL_TWO			((void *)&sysctl_vals[2])
+#define SYSCTL_THREE			((void *)&sysctl_vals[3])
+#define SYSCTL_FOUR			((void *)&sysctl_vals[4])
+#define SYSCTL_ONE_HUNDRED		((void *)&sysctl_vals[5])
+#define SYSCTL_TWO_HUNDRED		((void *)&sysctl_vals[6])
+#define SYSCTL_ONE_THOUSAND		((void *)&sysctl_vals[7])
+#define SYSCTL_THREE_THOUSAND		((void *)&sysctl_vals[8])
+#define SYSCTL_INT_MAX			((void *)&sysctl_vals[9])
+
+/* this is needed for the proc_dointvec_minmax for [fs_]overflow UID and GID */
+#define SYSCTL_MAXOLDUID		((void *)&sysctl_vals[10])
+#define SYSCTL_NEG_ONE			((void *)&sysctl_vals[11])
+
+extern const int sysctl_vals[];
+
+#define SYSCTL_LONG_ZERO	((void *)&sysctl_long_vals[0])
+#define SYSCTL_LONG_ONE		((void *)&sysctl_long_vals[1])
+#define SYSCTL_LONG_MAX		((void *)&sysctl_long_vals[2])
+
+#define SYSCTL_CONV_IDENTITY(val) (val)
+/**
+ *
+ * "dir" originates from read_iter (dir = 0) or write_iter (dir = 1)
+ * in the file_operations struct at proc/proc_sysctl.c. Its value means
+ * one of two things for sysctl:
+ * 1. SYSCTL_USER_TO_KERN(dir) Writing to an internal kernel variable from user
+ *                             space (dir > 0)
+ * 2. SYSCTL_KERN_TO_USER(dir) Writing to a user space buffer from a kernel
+ *                             variable (dir == 0).
+ */
+#define SYSCTL_USER_TO_KERN(dir) (!!(dir))
+#define SYSCTL_KERN_TO_USER(dir) (!dir)
+
+#define SYSCTL_USER_TO_KERN_INT_CONV(name, u_ptr_op)		\
+int sysctl_user_to_kern_int_conv##name(const bool *negp,	\
+				       const unsigned long *u_ptr,\
+				       int *k_ptr)		\
+{								\
+	unsigned long u = u_ptr_op(*u_ptr);			\
+	if (*negp) {						\
+		if (u > (unsigned long) INT_MAX + 1)		\
+			return -EINVAL;				\
+		WRITE_ONCE(*k_ptr, -u);				\
+	} else {						\
+		if (u > (unsigned long) INT_MAX)		\
+			return -EINVAL;				\
+		WRITE_ONCE(*k_ptr, u);				\
+	}							\
+	return 0;						\
+}
+
+#define SYSCTL_KERN_TO_USER_INT_CONV(name, k_ptr_op)		\
+int sysctl_kern_to_user_int_conv##name(bool *negp,		\
+				       unsigned long *u_ptr,	\
+				       const int *k_ptr)	\
+{								\
+	int val = READ_ONCE(*k_ptr);				\
+	if (val < 0) {						\
+		*negp = true;					\
+		*u_ptr = -k_ptr_op((unsigned long)val);		\
+	} else {						\
+		*negp = false;					\
+		*u_ptr = k_ptr_op((unsigned long)val);		\
+	}							\
+	return 0;						\
+}
+
+/**
+ * To range check on a converted value, use a temp k_ptr
+ * When checking range, value should be within (tbl->extra1, tbl->extra2)
+ */
+#define SYSCTL_INT_CONV_CUSTOM(name, user_to_kern, kern_to_user,	\
+			       k_ptr_range_check)			\
+int do_proc_int_conv##name(bool *negp, unsigned long *u_ptr, int *k_ptr,\
+			   int dir, const struct ctl_table *tbl)	\
+{									\
+	if (SYSCTL_KERN_TO_USER(dir))					\
+		return kern_to_user(negp, u_ptr, k_ptr);		\
+									\
+	if (k_ptr_range_check) {					\
+		int tmp_k, ret;						\
+		if (!tbl)						\
+			return -EINVAL;					\
+		ret = user_to_kern(negp, u_ptr, &tmp_k);		\
+		if (ret)						\
+			return ret;					\
+		if ((tbl->extra1 && *(int *)tbl->extra1 > tmp_k) ||	\
+		    (tbl->extra2 && *(int *)tbl->extra2 < tmp_k))	\
+			return -EINVAL;					\
+		WRITE_ONCE(*k_ptr, tmp_k);				\
+	} else								\
+		return user_to_kern(negp, u_ptr, k_ptr);		\
+	return 0;							\
+}
+
+#define SYSCTL_USER_TO_KERN_UINT_CONV(name, u_ptr_op)		\
+int sysctl_user_to_kern_uint_conv##name(const unsigned long *u_ptr,\
+					unsigned int *k_ptr)	\
+{								\
+	unsigned long u = u_ptr_op(*u_ptr);			\
+	if (u > UINT_MAX)					\
+		return -EINVAL;					\
+	WRITE_ONCE(*k_ptr, u);					\
+	return 0;						\
+}
+
+#define SYSCTL_UINT_CONV_CUSTOM(name, user_to_kern, kern_to_user,	\
+				k_ptr_range_check)			\
+int do_proc_uint_conv##name(unsigned long *u_ptr, unsigned int *k_ptr,	\
+			   int dir, const struct ctl_table *tbl)	\
+{									\
+	if (SYSCTL_KERN_TO_USER(dir))					\
+		return kern_to_user(u_ptr, k_ptr);			\
+									\
+	if (k_ptr_range_check) {					\
+		unsigned int tmp_k;					\
+		int ret;						\
+		if (!tbl)						\
+			return -EINVAL;					\
+		ret = user_to_kern(u_ptr, &tmp_k);			\
+		if (ret)						\
+			return ret;					\
+		if ((tbl->extra1 &&					\
+		     *(unsigned int *)tbl->extra1 > tmp_k) ||		\
+		    (tbl->extra2 &&					\
+		     *(unsigned int *)tbl->extra2 < tmp_k))		\
+			return -ERANGE;					\
+		WRITE_ONCE(*k_ptr, tmp_k);				\
+	} else								\
+		return user_to_kern(u_ptr, k_ptr);			\
+	return 0;							\
+}
+
+
+extern const unsigned long sysctl_long_vals[];
+
+typedef int proc_handler(const struct ctl_table *ctl, int write, void *buffer,
+		size_t *lenp, loff_t *ppos);
+
+int proc_dostring(const struct ctl_table *, int, void *, size_t *, loff_t *);
+int proc_dobool(const struct ctl_table *table, int write, void *buffer,
+		size_t *lenp, loff_t *ppos);
+int proc_dointvec(const struct ctl_table *, int, void *, size_t *, loff_t *);
+int proc_dointvec_minmax(const struct ctl_table *table, int dir, void *buffer,
+			 size_t *lenp, loff_t *ppos);
+int proc_dointvec_conv(const struct ctl_table *table, int dir, void *buffer,
+		       size_t *lenp, loff_t *ppos,
+		       int (*conv)(bool *negp, unsigned long *u_ptr, int *k_ptr,
+				   int dir, const struct ctl_table *table));
+int proc_douintvec(const struct ctl_table *, int, void *, size_t *, loff_t *);
+int proc_douintvec_minmax(const struct ctl_table *table, int write, void *buffer,
+		size_t *lenp, loff_t *ppos);
+int proc_douintvec_conv(const struct ctl_table *table, int write, void *buffer,
+			size_t *lenp, loff_t *ppos,
+			int (*conv)(unsigned long *lvalp, unsigned int *valp,
+				    int write, const struct ctl_table *table));
+
+int proc_dou8vec_minmax(const struct ctl_table *table, int write, void *buffer,
+			size_t *lenp, loff_t *ppos);
+int proc_doulongvec_minmax(const struct ctl_table *, int, void *, size_t *, loff_t *);
+int proc_doulongvec_minmax_conv(const struct ctl_table *table, int dir,
+				void *buffer, size_t *lenp, loff_t *ppos,
+				unsigned long convmul, unsigned long convdiv);
+int proc_do_large_bitmap(const struct ctl_table *, int, void *, size_t *, loff_t *);
+int proc_do_static_key(const struct ctl_table *table, int write, void *buffer,
+		size_t *lenp, loff_t *ppos);
+int sysctl_kern_to_user_uint_conv(unsigned long *u_ptr, const unsigned int *k_ptr);
 
 /*
- * Register a set of sysctl names by calling register_sysctl_table
- * with an initialised array of struct ctl_table's.  An entry with 
- * NULL procname terminates the table.  table->de will be
- * set up by the registration and need not be initialised in advance.
+ * Register a set of sysctl names by calling register_sysctl
+ * with an initialised array of struct ctl_table's.
  *
  * sysctl names can be mirrored automatically under /proc/sys.  The
  * procname supplied controls /proc naming.
  *
- * The table's mode will be honoured both for sys_sysctl(2) and
- * proc-fs access.
+ * The table's mode will be honoured for proc-fs access.
  *
  * Leaf nodes in the sysctl tree will be represented by a single file
  * under /proc; non-leaf nodes will be represented by directories.  A
  * null procname disables /proc mirroring at this node.
  *
- * sysctl(2) can automatically manage read and write requests through
- * the sysctl table.  The data and maxlen fields of the ctl_table
+ * The data and maxlen fields of the ctl_table
  * struct enable minimal validation of the values being written to be
  * performed, and the mode field allows minimal authentication.
  * 
@@ -104,31 +250,42 @@ static inline void *proc_sys_poll_event(struct ctl_table_poll *poll)
 	struct ctl_table_poll name = __CTL_TABLE_POLL_INITIALIZER(name)
 
 /* A sysctl table is an array of struct ctl_table: */
-struct ctl_table 
-{
-	const char *procname;		/* Text ID for /proc/sys, or zero */
+struct ctl_table {
+	const char *procname;		/* Text ID for /proc/sys */
 	void *data;
 	int maxlen;
 	umode_t mode;
-	struct ctl_table *child;	/* Deprecated */
 	proc_handler *proc_handler;	/* Callback for text formatting */
 	struct ctl_table_poll *poll;
 	void *extra1;
 	void *extra2;
-};
+} __randomize_layout;
 
 struct ctl_node {
 	struct rb_node node;
 	struct ctl_table_header *header;
 };
 
-/* struct ctl_table_header is used to maintain dynamic lists of
-   struct ctl_table trees. */
-struct ctl_table_header
-{
+/**
+ * struct ctl_table_header - maintains dynamic lists of struct ctl_table trees
+ * @ctl_table: pointer to the first element in ctl_table array
+ * @ctl_table_size: number of elements pointed by @ctl_table
+ * @used: The entry will never be touched when equal to 0.
+ * @count: Upped every time something is added to @inodes and downed every time
+ *         something is removed from inodes
+ * @nreg: When nreg drops to 0 the ctl_table_header will be unregistered.
+ * @rcu: Delays the freeing of the inode. Introduced with "unfuck proc_sysctl ->d_compare()"
+ *
+ * @type: Enumeration to differentiate between ctl target types
+ * @type.SYSCTL_TABLE_TYPE_DEFAULT: ctl target with no special considerations
+ * @type.SYSCTL_TABLE_TYPE_PERMANENTLY_EMPTY: Identifies a permanently empty dir
+ *                                            target to serve as a mount point
+ */
+struct ctl_table_header {
 	union {
 		struct {
-			struct ctl_table *ctl_table;
+			const struct ctl_table *ctl_table;
+			int ctl_table_size;
 			int used;
 			int count;
 			int nreg;
@@ -136,11 +293,16 @@ struct ctl_table_header
 		struct rcu_head rcu;
 	};
 	struct completion *unregistering;
-	struct ctl_table *ctl_table_arg;
+	const struct ctl_table *ctl_table_arg;
 	struct ctl_table_root *root;
 	struct ctl_table_set *set;
 	struct ctl_dir *parent;
 	struct ctl_node *node;
+	struct hlist_head inodes; /* head for proc_inode->sysctl_inodes */
+	enum {
+		SYSCTL_TABLE_TYPE_DEFAULT,
+		SYSCTL_TABLE_TYPE_PERMANENTLY_EMPTY,
+	} type;
 };
 
 struct ctl_dir {
@@ -156,15 +318,14 @@ struct ctl_table_set {
 
 struct ctl_table_root {
 	struct ctl_table_set default_set;
-	struct ctl_table_set *(*lookup)(struct ctl_table_root *root,
-					   struct nsproxy *namespaces);
-	int (*permissions)(struct ctl_table_header *head, struct ctl_table *table);
+	struct ctl_table_set *(*lookup)(struct ctl_table_root *root);
+	void (*set_ownership)(struct ctl_table_header *head,
+			      kuid_t *uid, kgid_t *gid);
+	int (*permissions)(struct ctl_table_header *head, const struct ctl_table *table);
 };
 
-/* struct ctl_path describes where in the hierarchy a table is added */
-struct ctl_path {
-	const char *procname;
-};
+#define register_sysctl(path, table)	\
+	register_sysctl_sz(path, table, ARRAY_SIZE(table))
 
 #ifdef CONFIG_SYSCTL
 
@@ -175,29 +336,40 @@ extern void setup_sysctl_set(struct ctl_table_set *p,
 	int (*is_seen)(struct ctl_table_set *));
 extern void retire_sysctl_set(struct ctl_table_set *set);
 
-void register_sysctl_root(struct ctl_table_root *root);
 struct ctl_table_header *__register_sysctl_table(
 	struct ctl_table_set *set,
-	const char *path, struct ctl_table *table);
-struct ctl_table_header *__register_sysctl_paths(
-	struct ctl_table_set *set,
-	const struct ctl_path *path, struct ctl_table *table);
-struct ctl_table_header *register_sysctl(const char *path, struct ctl_table *table);
-struct ctl_table_header *register_sysctl_table(struct ctl_table * table);
-struct ctl_table_header *register_sysctl_paths(const struct ctl_path *path,
-						struct ctl_table *table);
-
+	const char *path, const struct ctl_table *table, size_t table_size);
+struct ctl_table_header *register_sysctl_sz(const char *path, const struct ctl_table *table,
+					    size_t table_size);
 void unregister_sysctl_table(struct ctl_table_header * table);
 
-extern int sysctl_init(void);
+extern int sysctl_init_bases(void);
+extern void __register_sysctl_init(const char *path, const struct ctl_table *table,
+				 const char *table_name, size_t table_size);
+#define register_sysctl_init(path, table)	\
+	__register_sysctl_init(path, table, #table, ARRAY_SIZE(table))
+extern struct ctl_table_header *register_sysctl_mount_point(const char *path);
+
+void do_sysctl_args(void);
+bool sysctl_is_alias(char *param);
+
+extern int unaligned_enabled;
+extern int no_unaligned_warning;
+
 #else /* CONFIG_SYSCTL */
-static inline struct ctl_table_header *register_sysctl_table(struct ctl_table * table)
+
+static inline void register_sysctl_init(const char *path, const struct ctl_table *table)
+{
+}
+
+static inline struct ctl_table_header *register_sysctl_mount_point(const char *path)
 {
 	return NULL;
 }
 
-static inline struct ctl_table_header *register_sysctl_paths(
-			const struct ctl_path *path, struct ctl_table *table)
+static inline struct ctl_table_header *register_sysctl_sz(const char *path,
+							  const struct ctl_table *table,
+							  size_t table_size)
 {
 	return NULL;
 }
@@ -212,6 +384,14 @@ static inline void setup_sysctl_set(struct ctl_table_set *p,
 {
 }
 
+static inline void do_sysctl_args(void)
+{
+}
+
+static inline bool sysctl_is_alias(char *param)
+{
+	return false;
+}
 #endif /* CONFIG_SYSCTL */
 
 #endif /* _LINUX_SYSCTL_H */