sysctl: Infrastructure for per namespace sysctls

This patch implements the basic infrastructure for per namespace sysctls.

A list of lists of sysctl headers is added, allowing each namespace to have
it's own list of sysctl headers.

Each list of sysctl headers has a lookup function to find the first
sysctl header in the list, allowing the lists to have a per namespace
instance.

register_sysct_root is added to tell sysctl.c about additional
lists of sysctl_headers.  As all of the users are expected to be in
kernel no unregister function is provided.

sysctl_head_next is updated to walk through the list of lists.

__register_sysctl_paths is added to add a new sysctl table on
a non-default sysctl list.

The only intrusive part of this patch is propagating the information
to decided which list of sysctls to use for sysctl_check_table.

Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>
Cc: Serge Hallyn <serue@us.ibm.com>
Cc: Daniel Lezcano <dlezcano@fr.ibm.com>
Cc: Cedric Le Goater <clg@fr.ibm.com>
Cc: Pavel Emelyanov <xemul@openvz.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>

3 files changed, 112 insertions, 23 deletions

diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h
index 77de3bf..89faebf 100644
--- a/include/linux/sysctl.h
+++ b/include/linux/sysctl.h
@@ -945,7 +945,10 @@ enum
 
 /* For the /proc/sys support */
 struct ctl_table;
+struct nsproxy;
 extern struct ctl_table_header *sysctl_head_next(struct ctl_table_header *prev);
+extern struct ctl_table_header *__sysctl_head_next(struct nsproxy *namespaces,
+						struct ctl_table_header *prev);
 extern void sysctl_head_finish(struct ctl_table_header *prev);
 extern int sysctl_perm(struct ctl_table *table, int op);
 
@@ -1049,6 +1052,13 @@ struct ctl_table
 	void *extra2;
 };
 
+struct ctl_table_root {
+	struct list_head root_list;
+	struct list_head header_list;
+	struct list_head *(*lookup)(struct ctl_table_root *root,
+					   struct nsproxy *namespaces);
+};
+
 /* struct ctl_table_header is used to maintain dynamic lists of
    struct ctl_table trees. */
 struct ctl_table_header
@@ -1058,6 +1068,7 @@ struct ctl_table_header
 	int used;
 	struct completion *unregistering;
 	struct ctl_table *ctl_table_arg;
+	struct ctl_table_root *root;
 };
 
 /* struct ctl_path describes where in the hierarchy a table is added */
@@ -1066,12 +1077,16 @@ struct ctl_path {
 	int ctl_name;
 };
 
+void register_sysctl_root(struct ctl_table_root *root);
+struct ctl_table_header *__register_sysctl_paths(
+	struct ctl_table_root *root, struct nsproxy *namespaces,
+	const struct ctl_path *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);
 
 void unregister_sysctl_table(struct ctl_table_header * table);
-int sysctl_check_table(struct ctl_table *table);
+int sysctl_check_table(struct nsproxy *namespaces, struct ctl_table *table);
 
 #else /* __KERNEL__ */
 
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 89b7d95..45e76f2 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -157,8 +157,16 @@ static int proc_dointvec_taint(struct ctl_table *table, int write, struct file *
 #endif
 
 static struct ctl_table root_table[];
-static struct ctl_table_header root_table_header =
-	{ root_table, LIST_HEAD_INIT(root_table_header.ctl_entry) };
+static struct ctl_table_root sysctl_table_root;
+static struct ctl_table_header root_table_header = {
+	.ctl_table = root_table,
+	.ctl_entry = LIST_HEAD_INIT(sysctl_table_root.header_list),
+	.root = &sysctl_table_root,
+};
+static struct ctl_table_root sysctl_table_root = {
+	.root_list = LIST_HEAD_INIT(sysctl_table_root.root_list),
+	.header_list = LIST_HEAD_INIT(root_table_header.ctl_entry),
+};
 
 static struct ctl_table kern_table[];
 static struct ctl_table vm_table[];
@@ -1371,12 +1379,27 @@ void sysctl_head_finish(struct ctl_table_header *head)
 	spin_unlock(&sysctl_lock);
 }
 
-struct ctl_table_header *sysctl_head_next(struct ctl_table_header *prev)
+static struct list_head *
+lookup_header_list(struct ctl_table_root *root, struct nsproxy *namespaces)
 {
+	struct list_head *header_list;
+	header_list = &root->header_list;
+	if (root->lookup)
+		header_list = root->lookup(root, namespaces);
+	return header_list;
+}
+
+struct ctl_table_header *__sysctl_head_next(struct nsproxy *namespaces,
+					    struct ctl_table_header *prev)
+{
+	struct ctl_table_root *root;
+	struct list_head *header_list;
 	struct ctl_table_header *head;
 	struct list_head *tmp;
+
 	spin_lock(&sysctl_lock);
 	if (prev) {
+		head = prev;
 		tmp = &prev->ctl_entry;
 		unuse_table(prev);
 		goto next;
@@ -1390,14 +1413,38 @@ struct ctl_table_header *sysctl_head_next(struct ctl_table_header *prev)
 		spin_unlock(&sysctl_lock);
 		return head;
 	next:
+		root = head->root;
 		tmp = tmp->next;
-		if (tmp == &root_table_header.ctl_entry)
-			break;
+		header_list = lookup_header_list(root, namespaces);
+		if (tmp != header_list)
+			continue;
+
+		do {
+			root = list_entry(root->root_list.next,
+					struct ctl_table_root, root_list);
+			if (root == &sysctl_table_root)
+				goto out;
+			header_list = lookup_header_list(root, namespaces);
+		} while (list_empty(header_list));
+		tmp = header_list->next;
 	}
+out:
 	spin_unlock(&sysctl_lock);
 	return NULL;
 }
 
+struct ctl_table_header *sysctl_head_next(struct ctl_table_header *prev)
+{
+	return __sysctl_head_next(current->nsproxy, prev);
+}
+
+void register_sysctl_root(struct ctl_table_root *root)
+{
+	spin_lock(&sysctl_lock);
+	list_add_tail(&root->root_list, &sysctl_table_root.root_list);
+	spin_unlock(&sysctl_lock);
+}
+
 #ifdef CONFIG_SYSCTL_SYSCALL
 int do_sysctl(int __user *name, int nlen, void __user *oldval, size_t __user *oldlenp,
 	       void __user *newval, size_t newlen)
@@ -1554,14 +1601,16 @@ static __init int sysctl_init(void)
 {
 	int err;
 	sysctl_set_parent(NULL, root_table);
-	err = sysctl_check_table(root_table);
+	err = sysctl_check_table(current->nsproxy, root_table);
 	return 0;
 }
 
 core_initcall(sysctl_init);
 
 /**
- * register_sysctl_paths - register a sysctl hierarchy
+ * __register_sysctl_paths - register a sysctl hierarchy
+ * @root: List of sysctl headers to register on
+ * @namespaces: Data to compute which lists of sysctl entries are visible
  * @path: The path to the directory the sysctl table is in.
  * @table: the top-level table structure
  *
@@ -1629,9 +1678,12 @@ core_initcall(sysctl_init);
  * This routine returns %NULL on a failure to register, and a pointer
  * to the table header on success.
  */
-struct ctl_table_header *register_sysctl_paths(const struct ctl_path *path,
-						struct ctl_table *table)
+struct ctl_table_header *__register_sysctl_paths(
+	struct ctl_table_root *root,
+	struct nsproxy *namespaces,
+	const struct ctl_path *path, struct ctl_table *table)
 {
+	struct list_head *header_list;
 	struct ctl_table_header *header;
 	struct ctl_table *new, **prevp;
 	unsigned int n, npath;
@@ -1674,19 +1726,38 @@ struct ctl_table_header *register_sysctl_paths(const struct ctl_path *path,
 	INIT_LIST_HEAD(&header->ctl_entry);
 	header->used = 0;
 	header->unregistering = NULL;
+	header->root = root;
 	sysctl_set_parent(NULL, header->ctl_table);
-	if (sysctl_check_table(header->ctl_table)) {
+	if (sysctl_check_table(namespaces, header->ctl_table)) {
 		kfree(header);
 		return NULL;
 	}
 	spin_lock(&sysctl_lock);
-	list_add_tail(&header->ctl_entry, &root_table_header.ctl_entry);
+	header_list = lookup_header_list(root, namespaces);
+	list_add_tail(&header->ctl_entry, header_list);
 	spin_unlock(&sysctl_lock);
 
 	return header;
 }
 
 /**
+ * register_sysctl_table_path - register a sysctl table hierarchy
+ * @path: The path to the directory the sysctl table is in.
+ * @table: the top-level table structure
+ *
+ * Register a sysctl table hierarchy. @table should be a filled in ctl_table
+ * array. A completely 0 filled entry terminates the table.
+ *
+ * See __register_sysctl_paths for more details.
+ */
+struct ctl_table_header *register_sysctl_paths(const struct ctl_path *path,
+						struct ctl_table *table)
+{
+	return __register_sysctl_paths(&sysctl_table_root, current->nsproxy,
+					path, table);
+}
+
+/**
  * register_sysctl_table - register a sysctl table hierarchy
  * @table: the top-level table structure
  *
diff --git a/kernel/sysctl_check.c b/kernel/sysctl_check.c
index d8a5558..c3206fa 100644
--- a/kernel/sysctl_check.c
+++ b/kernel/sysctl_check.c
@@ -1342,7 +1342,8 @@ static void sysctl_repair_table(struct ctl_table *table)
 	}
 }
 
-static struct ctl_table *sysctl_check_lookup(struct ctl_table *table)
+static struct ctl_table *sysctl_check_lookup(struct nsproxy *namespaces,
+						struct ctl_table *table)
 {
 	struct ctl_table_header *head;
 	struct ctl_table *ref, *test;
@@ -1350,8 +1351,8 @@ static struct ctl_table *sysctl_check_lookup(struct ctl_table *table)
 
 	depth = sysctl_depth(table);
 
-	for (head = sysctl_head_next(NULL); head;
-	     head = sysctl_head_next(head)) {
+	for (head = __sysctl_head_next(namespaces, NULL); head;
+	     head = __sysctl_head_next(namespaces, head)) {
 		cur_depth = depth;
 		ref = head->ctl_table;
 repeat:
@@ -1396,13 +1397,14 @@ static void set_fail(const char **fail, struct ctl_table *table, const char *str
 	*fail = str;
 }
 
-static int sysctl_check_dir(struct ctl_table *table)
+static int sysctl_check_dir(struct nsproxy *namespaces,
+				struct ctl_table *table)
 {
 	struct ctl_table *ref;
 	int error;
 
 	error = 0;
-	ref = sysctl_check_lookup(table);
+	ref = sysctl_check_lookup(namespaces, table);
 	if (ref) {
 		int match = 0;
 		if ((!table->procname && !ref->procname) ||
@@ -1427,11 +1429,12 @@ static int sysctl_check_dir(struct ctl_table *table)
 	return error;
 }
 
-static void sysctl_check_leaf(struct ctl_table *table, const char **fail)
+static void sysctl_check_leaf(struct nsproxy *namespaces,
+				struct ctl_table *table, const char **fail)
 {
 	struct ctl_table *ref;
 
-	ref = sysctl_check_lookup(table);
+	ref = sysctl_check_lookup(namespaces, table);
 	if (ref && (ref != table))
 		set_fail(fail, table, "Sysctl already exists");
 }
@@ -1455,7 +1458,7 @@ static void sysctl_check_bin_path(struct ctl_table *table, const char **fail)
 	}
 }
 
-int sysctl_check_table(struct ctl_table *table)
+int sysctl_check_table(struct nsproxy *namespaces, struct ctl_table *table)
 {
 	int error = 0;
 	for (; table->ctl_name || table->procname; table++) {
@@ -1485,7 +1488,7 @@ int sysctl_check_table(struct ctl_table *table)
 				set_fail(&fail, table, "Directory with extra1");
 			if (table->extra2)
 				set_fail(&fail, table, "Directory with extra2");
-			if (sysctl_check_dir(table))
+			if (sysctl_check_dir(namespaces, table))
 				set_fail(&fail, table, "Inconsistent directory names");
 		} else {
 			if ((table->strategy == sysctl_data) ||
@@ -1534,7 +1537,7 @@ int sysctl_check_table(struct ctl_table *table)
 			if (!table->procname && table->proc_handler)
 				set_fail(&fail, table, "proc_handler without procname");
 #endif
-			sysctl_check_leaf(table, &fail);
+			sysctl_check_leaf(namespaces, table, &fail);
 		}
 		sysctl_check_bin_path(table, &fail);
 		if (fail) {
@@ -1542,7 +1545,7 @@ int sysctl_check_table(struct ctl_table *table)
 			error = -EINVAL;
 		}
 		if (table->child)
-			error |= sysctl_check_table(table->child);
+			error |= sysctl_check_table(namespaces, table->child);
 	}
 	return error;
 }