Merge branch 'work.namespace' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs

Pull ipc namespace update from Al Viro:
 "Rik's patches reducing the amount of synchronize_rcu() triggered by
  ipc namespace destruction.

  I've some pending stuff reducing that on the normal umount side, but
  it's nowhere near ready and Rik's stuff shouldn't be held back due to
  conflicts - I'll just redo the parts of my series that stray into
  ipc/*"

* 'work.namespace' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs:
  ipc,namespace: batch free ipc_namespace structures
  ipc,namespace: make ipc namespace allocation wait for pending free

1 files changed, 26 insertions, 9 deletions

diff --git a/ipc/namespace.c b/ipc/namespace.c
index 8316ea585733..6ecc30effd3e 100644
--- a/ipc/namespace.c
+++ b/ipc/namespace.c
@@ -19,6 +19,12 @@
 
 #include "util.h"
 
+/*
+ * The work queue is used to avoid the cost of synchronize_rcu in kern_unmount.
+ */
+static void free_ipc(struct work_struct *unused);
+static DECLARE_WORK(free_ipc_work, free_ipc);
+
 static struct ucounts *inc_ipc_namespaces(struct user_namespace *ns)
 {
 	return inc_ucount(ns, current_euid(), UCOUNT_IPC_NAMESPACES);
@@ -37,9 +43,18 @@ static struct ipc_namespace *create_ipc_ns(struct user_namespace *user_ns,
 	int err;
 
 	err = -ENOSPC;
+ again:
 	ucounts = inc_ipc_namespaces(user_ns);
-	if (!ucounts)
+	if (!ucounts) {
+		/*
+		 * IPC namespaces are freed asynchronously, by free_ipc_work.
+		 * If frees were pending, flush_work will wait, and
+		 * return true. Fail the allocation if no frees are pending.
+		 */
+		if (flush_work(&free_ipc_work))
+			goto again;
 		goto fail;
+	}
 
 	err = -ENOMEM;
 	ns = kzalloc(sizeof(struct ipc_namespace), GFP_KERNEL_ACCOUNT);
@@ -130,10 +145,11 @@ void free_ipcs(struct ipc_namespace *ns, struct ipc_ids *ids,
 
 static void free_ipc_ns(struct ipc_namespace *ns)
 {
-	/* mq_put_mnt() waits for a grace period as kern_unmount()
-	 * uses synchronize_rcu().
+	/*
+	 * Caller needs to wait for an RCU grace period to have passed
+	 * after making the mount point inaccessible to new accesses.
 	 */
-	mq_put_mnt(ns);
+	mntput(ns->mq_mnt);
 	sem_exit_ns(ns);
 	msg_exit_ns(ns);
 	shm_exit_ns(ns);
@@ -154,15 +170,16 @@ static void free_ipc(struct work_struct *unused)
 	struct ipc_namespace *n, *t;
 
 	llist_for_each_entry_safe(n, t, node, mnt_llist)
+		mnt_make_shortterm(n->mq_mnt);
+
+	/* Wait for any last users to have gone away. */
+	synchronize_rcu();
+
+	llist_for_each_entry_safe(n, t, node, mnt_llist)
 		free_ipc_ns(n);
 }
 
 /*
- * The work queue is used to avoid the cost of synchronize_rcu in kern_unmount.
- */
-static DECLARE_WORK(free_ipc_work, free_ipc);
-
-/*
  * put_ipc_ns - drop a reference to an ipc namespace.
  * @ns: the namespace to put
  *