summaryrefslogtreecommitdiffstats
path: root/kernel
diff options
context:
space:
mode:
authorPavel Emelyanov <xemul@openvz.org>2007-10-18 23:39:54 -0700
committerLinus Torvalds <torvalds@woody.linux-foundation.org>2007-10-19 11:53:37 -0700
commitcf7b708c8d1d7a27736771bcf4c457b332b0f818 (patch)
tree10f80257b052313b283f18ddfe35145882e0b47f /kernel
parenta6f5e06378970a2687332c2d54046245fcff1e7e (diff)
downloadop-kernel-dev-cf7b708c8d1d7a27736771bcf4c457b332b0f818.zip
op-kernel-dev-cf7b708c8d1d7a27736771bcf4c457b332b0f818.tar.gz
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>
Diffstat (limited to 'kernel')
-rw-r--r--kernel/exit.c7
-rw-r--r--kernel/fork.c11
-rw-r--r--kernel/nsproxy.c40
3 files changed, 36 insertions, 22 deletions
diff --git a/kernel/exit.c b/kernel/exit.c
index d22aefa..db97641 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 2deaf48..d2f4a42 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 e981c61..c8ef7c2 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);
OpenPOWER on IntegriCloud