Make access to task's nsproxy lighter

When someone wants to deal with some other taks's namespaces it has to lock
the task and then to get the desired namespace if the one exists.  This is
slow on read-only paths and may be impossible in some cases.

E.g.  Oleg recently noticed a race between unshare() and the (sent for
review in cgroups) pid namespaces - when the task notifies the parent it
has to know the parent's namespace, but taking the task_lock() is
impossible there - the code is under write locked tasklist lock.

On the other hand switching the namespace on task (daemonize) and releasing
the namespace (after the last task exit) is rather rare operation and we
can sacrifice its speed to solve the issues above.

The access to other task namespaces is proposed to be performed
like this:

     rcu_read_lock();
     nsproxy = task_nsproxy(tsk);
     if (nsproxy != NULL) {
             / *
               * work with the namespaces here
               * e.g. get the reference on one of them
               * /
     } / *
         * NULL task_nsproxy() means that this task is
         * almost dead (zombie)
         * /
     rcu_read_unlock();

This patch has passed the review by Eric and Oleg :) and,
of course, tested.

[clg@fr.ibm.com: fix unshare()]
[ebiederm@xmission.com: Update get_net_ns_by_pid]
Signed-off-by: Pavel Emelyanov <xemul@openvz.org>
Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>
Cc: Oleg Nesterov <oleg@tv-sign.ru>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Serge Hallyn <serue@us.ibm.com>
Signed-off-by: Cedric Le Goater <clg@fr.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

6 files changed, 91 insertions, 45 deletions

diff --git a/fs/proc/base.c b/fs/proc/base.c
index fbff900fd5a..6afca09a653 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -350,18 +350,21 @@ struct proc_mounts {
 static int mounts_open(struct inode *inode, struct file *file)
 {
 	struct task_struct *task = get_proc_task(inode);
+	struct nsproxy *nsp;
 	struct mnt_namespace *ns = NULL;
 	struct proc_mounts *p;
 	int ret = -EINVAL;
 
 	if (task) {
-		task_lock(task);
-		if (task->nsproxy) {
-			ns = task->nsproxy->mnt_ns;
+		rcu_read_lock();
+		nsp = task_nsproxy(task);
+		if (nsp) {
+			ns = nsp->mnt_ns;
 			if (ns)
 				get_mnt_ns(ns);
 		}
-		task_unlock(task);
+		rcu_read_unlock();
+
 		put_task_struct(task);
 	}
 
@@ -424,16 +427,20 @@ static int mountstats_open(struct inode *inode, struct file *file)
 
 	if (!ret) {
 		struct seq_file *m = file->private_data;
+		struct nsproxy *nsp;
 		struct mnt_namespace *mnt_ns = NULL;
 		struct task_struct *task = get_proc_task(inode);
 
 		if (task) {
-			task_lock(task);
-			if (task->nsproxy)
-				mnt_ns = task->nsproxy->mnt_ns;
-			if (mnt_ns)
-				get_mnt_ns(mnt_ns);
-			task_unlock(task);
+			rcu_read_lock();
+			nsp = task_nsproxy(task);
+			if (nsp) {
+				mnt_ns = nsp->mnt_ns;
+				if (mnt_ns)
+					get_mnt_ns(mnt_ns);
+			}
+			rcu_read_unlock();
+
 			put_task_struct(task);
 		}
 
diff --git a/include/linux/nsproxy.h b/include/linux/nsproxy.h
index f1eca68751a..0e66b57631f 100644
--- a/include/linux/nsproxy.h
+++ b/include/linux/nsproxy.h
@@ -32,8 +32,39 @@ struct nsproxy {
 };
 extern struct nsproxy init_nsproxy;
 
+/*
+ * the namespaces access rules are:
+ *
+ *  1. only current task is allowed to change tsk->nsproxy pointer or
+ *     any pointer on the nsproxy itself
+ *
+ *  2. when accessing (i.e. reading) current task's namespaces - no
+ *     precautions should be taken - just dereference the pointers
+ *
+ *  3. the access to other task namespaces is performed like this
+ *     rcu_read_lock();
+ *     nsproxy = task_nsproxy(tsk);
+ *     if (nsproxy != NULL) {
+ *             / *
+ *               * work with the namespaces here
+ *               * e.g. get the reference on one of them
+ *               * /
+ *     } / *
+ *         * NULL task_nsproxy() means that this task is
+ *         * almost dead (zombie)
+ *         * /
+ *     rcu_read_unlock();
+ *
+ */
+
+static inline struct nsproxy *task_nsproxy(struct task_struct *tsk)
+{
+	return rcu_dereference(tsk->nsproxy);
+}
+
 int copy_namespaces(unsigned long flags, struct task_struct *tsk);
-void get_task_namespaces(struct task_struct *tsk);
+void exit_task_namespaces(struct task_struct *tsk);
+void switch_task_namespaces(struct task_struct *tsk, struct nsproxy *new);
 void free_nsproxy(struct nsproxy *ns);
 int unshare_nsproxy_namespaces(unsigned long, struct nsproxy **,
 	struct fs_struct *);
@@ -45,15 +76,9 @@ static inline void put_nsproxy(struct nsproxy *ns)
 	}
 }
 
-static inline void exit_task_namespaces(struct task_struct *p)
+static inline void get_nsproxy(struct nsproxy *ns)
 {
-	struct nsproxy *ns = p->nsproxy;
-	if (ns) {
-		task_lock(p);
-		p->nsproxy = NULL;
-		task_unlock(p);
-		put_nsproxy(ns);
-	}
+	atomic_inc(&ns->count);
 }
 
 #ifdef CONFIG_CGROUP_NS
diff --git a/kernel/exit.c b/kernel/exit.c
index d22aefabb12..db9764186d5 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -400,9 +400,10 @@ void daemonize(const char *name, ...)
 	current->fs = fs;
 	atomic_inc(&fs->count);
 
-	exit_task_namespaces(current);
-	current->nsproxy = init_task.nsproxy;
-	get_task_namespaces(current);
+	if (current->nsproxy != init_task.nsproxy) {
+		get_nsproxy(init_task.nsproxy);
+		switch_task_namespaces(current, init_task.nsproxy);
+	}
 
  	exit_files(current);
 	current->files = init_task.files;
diff --git a/kernel/fork.c b/kernel/fork.c
index 2deaf481efa..d2f4a420a5b 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1632,7 +1632,7 @@ asmlinkage long sys_unshare(unsigned long unshare_flags)
 	struct mm_struct *mm, *new_mm = NULL, *active_mm = NULL;
 	struct files_struct *fd, *new_fd = NULL;
 	struct sem_undo_list *new_ulist = NULL;
-	struct nsproxy *new_nsproxy = NULL, *old_nsproxy = NULL;
+	struct nsproxy *new_nsproxy = NULL;
 
 	check_unshare_flags(&unshare_flags);
 
@@ -1662,14 +1662,13 @@ asmlinkage long sys_unshare(unsigned long unshare_flags)
 
 	if (new_fs ||  new_mm || new_fd || new_ulist || new_nsproxy) {
 
-		task_lock(current);
-
 		if (new_nsproxy) {
-			old_nsproxy = current->nsproxy;
-			current->nsproxy = new_nsproxy;
-			new_nsproxy = old_nsproxy;
+			switch_task_namespaces(current, new_nsproxy);
+			new_nsproxy = NULL;
 		}
 
+		task_lock(current);
+
 		if (new_fs) {
 			fs = current->fs;
 			current->fs = new_fs;
diff --git a/kernel/nsproxy.c b/kernel/nsproxy.c
index e981c61304f..c8ef7c2992e 100644
--- a/kernel/nsproxy.c
+++ b/kernel/nsproxy.c
@@ -26,19 +26,6 @@ static struct kmem_cache *nsproxy_cachep;
 
 struct nsproxy init_nsproxy = INIT_NSPROXY(init_nsproxy);
 
-static inline void get_nsproxy(struct nsproxy *ns)
-{
-	atomic_inc(&ns->count);
-}
-
-void get_task_namespaces(struct task_struct *tsk)
-{
-	struct nsproxy *ns = tsk->nsproxy;
-	if (ns) {
-		get_nsproxy(ns);
-	}
-}
-
 /*
  * creates a copy of "orig" with refcount 1.
  */
@@ -216,6 +203,33 @@ out:
 	return err;
 }
 
+void switch_task_namespaces(struct task_struct *p, struct nsproxy *new)
+{
+	struct nsproxy *ns;
+
+	might_sleep();
+
+	ns = p->nsproxy;
+
+	rcu_assign_pointer(p->nsproxy, new);
+
+	if (ns && atomic_dec_and_test(&ns->count)) {
+		/*
+		 * wait for others to get what they want from this nsproxy.
+		 *
+		 * cannot release this nsproxy via the call_rcu() since
+		 * put_mnt_ns() will want to sleep
+		 */
+		synchronize_rcu();
+		free_nsproxy(ns);
+	}
+}
+
+void exit_task_namespaces(struct task_struct *p)
+{
+	switch_task_namespaces(p, NULL);
+}
+
 static int __init nsproxy_cache_init(void)
 {
 	nsproxy_cachep = KMEM_CACHE(nsproxy, SLAB_PANIC);
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 1072d16696c..4a2640d3826 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -744,10 +744,10 @@ static struct net *get_net_ns_by_pid(pid_t pid)
 	rcu_read_lock();
 	tsk = find_task_by_pid(pid);
 	if (tsk) {
-		task_lock(tsk);
-		if (tsk->nsproxy)
-			net = get_net(tsk->nsproxy->net_ns);
-		task_unlock(tsk);
+		struct nsproxy *nsproxy;
+		nsproxy = task_nsproxy(tsk);
+		if (nsproxy)
+			net = get_net(nsproxy->net_ns);
 	}
 	rcu_read_unlock();
 	return net;