1 files changed, 92 insertions, 28 deletions

diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c
index d4e37acd4821..8f479229b349 100644
--- a/fs/proc/proc_sysctl.c
+++ b/fs/proc/proc_sysctl.c
@@ -8,6 +8,7 @@
 #include <linux/printk.h>
 #include <linux/security.h>
 #include <linux/sched.h>
+#include <linux/cred.h>
 #include <linux/namei.h>
 #include <linux/mm.h>
 #include <linux/module.h>
@@ -190,6 +191,7 @@ static void init_header(struct ctl_table_header *head,
 	head->set = set;
 	head->parent = NULL;
 	head->node = node;
+	INIT_HLIST_HEAD(&head->inodes);
 	if (node) {
 		struct ctl_table *entry;
 		for (entry = table; entry->procname; entry++, node++)
@@ -259,6 +261,44 @@ static void unuse_table(struct ctl_table_header *p)
 			complete(p->unregistering);
 }
 
+static void proc_sys_prune_dcache(struct ctl_table_header *head)
+{
+	struct inode *inode;
+	struct proc_inode *ei;
+	struct hlist_node *node;
+	struct super_block *sb;
+
+	rcu_read_lock();
+	for (;;) {
+		node = hlist_first_rcu(&head->inodes);
+		if (!node)
+			break;
+		ei = hlist_entry(node, struct proc_inode, sysctl_inodes);
+		spin_lock(&sysctl_lock);
+		hlist_del_init_rcu(&ei->sysctl_inodes);
+		spin_unlock(&sysctl_lock);
+
+		inode = &ei->vfs_inode;
+		sb = inode->i_sb;
+		if (!atomic_inc_not_zero(&sb->s_active))
+			continue;
+		inode = igrab(inode);
+		rcu_read_unlock();
+		if (unlikely(!inode)) {
+			deactivate_super(sb);
+			rcu_read_lock();
+			continue;
+		}
+
+		d_prune_aliases(inode);
+		iput(inode);
+		deactivate_super(sb);
+
+		rcu_read_lock();
+	}
+	rcu_read_unlock();
+}
+
 /* called under sysctl_lock, will reacquire if has to wait */
 static void start_unregistering(struct ctl_table_header *p)
 {
@@ -272,31 +312,22 @@ static void start_unregistering(struct ctl_table_header *p)
 		p->unregistering = &wait;
 		spin_unlock(&sysctl_lock);
 		wait_for_completion(&wait);
-		spin_lock(&sysctl_lock);
 	} else {
 		/* anything non-NULL; we'll never dereference it */
 		p->unregistering = ERR_PTR(-EINVAL);
+		spin_unlock(&sysctl_lock);
 	}
 	/*
+	 * Prune dentries for unregistered sysctls: namespaced sysctls
+	 * can have duplicate names and contaminate dcache very badly.
+	 */
+	proc_sys_prune_dcache(p);
+	/*
 	 * do not remove from the list until nobody holds it; walking the
 	 * list in do_sysctl() relies on that.
 	 */
-	erase_header(p);
-}
-
-static void sysctl_head_get(struct ctl_table_header *head)
-{
-	spin_lock(&sysctl_lock);
-	head->count++;
-	spin_unlock(&sysctl_lock);
-}
-
-void sysctl_head_put(struct ctl_table_header *head)
-{
 	spin_lock(&sysctl_lock);
-	if (!--head->count)
-		kfree_rcu(head, rcu);
-	spin_unlock(&sysctl_lock);
+	erase_header(p);
 }
 
 static struct ctl_table_header *sysctl_head_grab(struct ctl_table_header *head)
@@ -394,10 +425,6 @@ static void next_entry(struct ctl_table_header **phead, struct ctl_table **pentr
 	*pentry = entry;
 }
 
-void register_sysctl_root(struct ctl_table_root *root)
-{
-}
-
 /*
  * sysctl_perm does NOT grant the superuser all rights automatically, because
  * some sysctl variables are readonly even to root.
@@ -440,10 +467,20 @@ static struct inode *proc_sys_make_inode(struct super_block *sb,
 
 	inode->i_ino = get_next_ino();
 
-	sysctl_head_get(head);
 	ei = PROC_I(inode);
+
+	spin_lock(&sysctl_lock);
+	if (unlikely(head->unregistering)) {
+		spin_unlock(&sysctl_lock);
+		iput(inode);
+		inode = NULL;
+		goto out;
+	}
 	ei->sysctl = head;
 	ei->sysctl_entry = table;
+	hlist_add_head_rcu(&ei->sysctl_inodes, &head->inodes);
+	head->count++;
+	spin_unlock(&sysctl_lock);
 
 	inode->i_mtime = inode->i_atime = inode->i_ctime = current_time(inode);
 	inode->i_mode = table->mode;
@@ -466,6 +503,15 @@ out:
 	return inode;
 }
 
+void proc_sys_evict_inode(struct inode *inode, struct ctl_table_header *head)
+{
+	spin_lock(&sysctl_lock);
+	hlist_del_init_rcu(&PROC_I(inode)->sysctl_inodes);
+	if (!--head->count)
+		kfree_rcu(head, rcu);
+	spin_unlock(&sysctl_lock);
+}
+
 static struct ctl_table_header *grab_header(struct inode *inode)
 {
 	struct ctl_table_header *head = PROC_I(inode)->sysctl;
@@ -769,9 +815,10 @@ static int proc_sys_setattr(struct dentry *dentry, struct iattr *attr)
 	return 0;
 }
 
-static int proc_sys_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat)
+static int proc_sys_getattr(const struct path *path, struct kstat *stat,
+			    u32 request_mask, unsigned int query_flags)
 {
-	struct inode *inode = d_inode(dentry);
+	struct inode *inode = d_inode(path->dentry);
 	struct ctl_table_header *head = grab_header(inode);
 	struct ctl_table *table = PROC_I(inode)->sysctl_entry;
 
@@ -1031,15 +1078,30 @@ static int sysctl_err(const char *path, struct ctl_table *table, char *fmt, ...)
 	return -EINVAL;
 }
 
+static int sysctl_check_table_array(const char *path, struct ctl_table *table)
+{
+	int err = 0;
+
+	if ((table->proc_handler == proc_douintvec) ||
+	    (table->proc_handler == proc_douintvec_minmax)) {
+		if (table->maxlen != sizeof(unsigned int))
+			err |= sysctl_err(path, table, "array now allowed");
+	}
+
+	return err;
+}
+
 static int sysctl_check_table(const char *path, struct ctl_table *table)
 {
 	int err = 0;
 	for (; table->procname; table++) {
 		if (table->child)
-			err = sysctl_err(path, table, "Not a file");
+			err |= sysctl_err(path, table, "Not a file");
 
 		if ((table->proc_handler == proc_dostring) ||
 		    (table->proc_handler == proc_dointvec) ||
+		    (table->proc_handler == proc_douintvec) ||
+		    (table->proc_handler == proc_douintvec_minmax) ||
 		    (table->proc_handler == proc_dointvec_minmax) ||
 		    (table->proc_handler == proc_dointvec_jiffies) ||
 		    (table->proc_handler == proc_dointvec_userhz_jiffies) ||
@@ -1047,15 +1109,17 @@ static int sysctl_check_table(const char *path, struct ctl_table *table)
 		    (table->proc_handler == proc_doulongvec_minmax) ||
 		    (table->proc_handler == proc_doulongvec_ms_jiffies_minmax)) {
 			if (!table->data)
-				err = sysctl_err(path, table, "No data");
+				err |= sysctl_err(path, table, "No data");
 			if (!table->maxlen)
-				err = sysctl_err(path, table, "No maxlen");
+				err |= sysctl_err(path, table, "No maxlen");
+			else
+				err |= sysctl_check_table_array(path, table);
 		}
 		if (!table->proc_handler)
-			err = sysctl_err(path, table, "No proc_handler");
+			err |= sysctl_err(path, table, "No proc_handler");
 
 		if ((table->mode & (S_IRUGO|S_IWUGO)) != table->mode)
-			err = sysctl_err(path, table, "bogus .mode 0%o",
+			err |= sysctl_err(path, table, "bogus .mode 0%o",
 				table->mode);
 	}
 	return err;