summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorDavid Howells <dhowells@redhat.com>2015-02-24 11:05:28 +0100
committerDavid Howells <dhowells@redhat.com>2015-04-02 15:28:53 +0200
commitf09b443d0e09f37121c55d7f83056f6ebff6ab4f (patch)
tree00f17a9fb68c2007b1b58ae4e80bddcebcfbd50b
parentFS-Cache: Handle a new operation submitted against a killed object (diff)
downloadlinux-f09b443d0e09f37121c55d7f83056f6ebff6ab4f.tar.xz
linux-f09b443d0e09f37121c55d7f83056f6ebff6ab4f.zip
FS-Cache: Synchronise object death state change vs operation submission
When an object is being marked as no longer live, do this under the object spinlock to prevent a race with operation submission targeted on that object. The problem occurs due to the following pair of intertwined sequences when the cache tries to create an object that would take it over the hard available space limit: NETFS INTERFACE =============== (A) The netfs calls fscache_acquire_cookie(). object creation is deferred to the object state machine and the netfs is allowed to continue. OBJECT STATE MACHINE KTHREAD ============================ (1) The object is looked up on disk by fscache_look_up_object() calling cachefiles_walk_to_object(). The latter finds that the object is not yet represented on disk and calls fscache_object_lookup_negative(). (2) fscache_object_lookup_negative() sets FSCACHE_COOKIE_NO_DATA_YET and clears FSCACHE_COOKIE_LOOKING_UP, thus allowing the netfs to start queuing read operations. (B) The netfs calls fscache_read_or_alloc_pages(). This calls fscache_wait_for_deferred_lookup() which sees FSCACHE_COOKIE_LOOKING_UP become clear, allowing the read to begin. (C) A read operation is set up and passed to fscache_submit_op() to deal with. (3) cachefiles_walk_to_object() calls cachefiles_has_space(), which fails (or one of the file operations to create stuff fails). cachefiles returns an error to fscache. (4) fscache_look_up_object() transits to the LOOKUP_FAILURE state, (5) fscache_lookup_failure() sets FSCACHE_OBJECT_LOOKED_UP and FSCACHE_COOKIE_UNAVAILABLE and clears FSCACHE_COOKIE_LOOKING_UP then transits to the KILL_OBJECT state. (6) fscache_kill_object() clears FSCACHE_OBJECT_IS_LIVE in an attempt to reject any further requests from the netfs. (7) object->n_ops is examined and found to be 0. fscache_kill_object() transits to the DROP_OBJECT state. (D) fscache_submit_op() locks the object spinlock, sees if it can dispatch the op immediately by calling fscache_object_is_active() - which fails since FSCACHE_OBJECT_IS_AVAILABLE has not yet been set. (E) fscache_submit_op() then tests FSCACHE_OBJECT_LOOKED_UP - which is set. It then queues the object and increments object->n_ops. (8) fscache_drop_object() releases the object and eventually fscache_put_object() calls cachefiles_put_object() which suffers an assertion failure here: ASSERTCMP(object->fscache.n_ops, ==, 0); Locking the object spinlock in step (6) around the clearance of FSCACHE_OBJECT_IS_LIVE ensures that the the decision trees in fscache_submit_op() and fscache_submit_exclusive_op() don't see the IS_LIVE flag being cleared mid-decision: either the op is queued before step (7) - in which case fscache_kill_object() will see n_ops>0 and will deal with the op - or the op will be rejected. This, combined with rejecting op submission if the target object is dying, fix the problem. The problem shows up as the following oops: CacheFiles: Assertion failed CacheFiles: 1 == 0 is false ------------[ cut here ]------------ kernel BUG at ../fs/cachefiles/interface.c:339! ... RIP: 0010:[<ffffffffa014fd9c>] [<ffffffffa014fd9c>] cachefiles_put_object+0x2a4/0x301 [cachefiles] ... Call Trace: [<ffffffffa008674b>] fscache_put_object+0x18/0x21 [fscache] [<ffffffffa00883e6>] fscache_object_work_func+0x3ba/0x3c9 [fscache] [<ffffffff81054dad>] process_one_work+0x226/0x441 [<ffffffff81055d91>] worker_thread+0x273/0x36b [<ffffffff81055b1e>] ? rescuer_thread+0x2e1/0x2e1 [<ffffffff81059b9d>] kthread+0x10e/0x116 [<ffffffff81059a8f>] ? kthread_create_on_node+0x1bb/0x1bb [<ffffffff815579ac>] ret_from_fork+0x7c/0xb0 [<ffffffff81059a8f>] ? kthread_create_on_node+0x1bb/0x1bb Signed-off-by: David Howells <dhowells@redhat.com> Reviewed-by: Steve Dickson <steved@redhat.com> Acked-by: Jeff Layton <jeff.layton@primarydata.com>
-rw-r--r--fs/fscache/object.c17
1 files changed, 14 insertions, 3 deletions
diff --git a/fs/fscache/object.c b/fs/fscache/object.c
index 9b79fc9a1464..40049f7505f0 100644
--- a/fs/fscache/object.c
+++ b/fs/fscache/object.c
@@ -328,6 +328,17 @@ void fscache_object_init(struct fscache_object *object,
EXPORT_SYMBOL(fscache_object_init);
/*
+ * Mark the object as no longer being live, making sure that we synchronise
+ * against op submission.
+ */
+static inline void fscache_mark_object_dead(struct fscache_object *object)
+{
+ spin_lock(&object->lock);
+ clear_bit(FSCACHE_OBJECT_IS_LIVE, &object->flags);
+ spin_unlock(&object->lock);
+}
+
+/*
* Abort object initialisation before we start it.
*/
static const struct fscache_state *fscache_abort_initialisation(struct fscache_object *object,
@@ -631,7 +642,7 @@ static const struct fscache_state *fscache_kill_object(struct fscache_object *ob
_enter("{OBJ%x,%d,%d},%d",
object->debug_id, object->n_ops, object->n_children, event);
- clear_bit(FSCACHE_OBJECT_IS_LIVE, &object->flags);
+ fscache_mark_object_dead(object);
object->oob_event_mask = 0;
if (list_empty(&object->dependents) &&
@@ -976,13 +987,13 @@ static const struct fscache_state *_fscache_invalidate_object(struct fscache_obj
return transit_to(UPDATE_OBJECT);
nomem:
- clear_bit(FSCACHE_OBJECT_IS_LIVE, &object->flags);
+ fscache_mark_object_dead(object);
fscache_unuse_cookie(object);
_leave(" [ENOMEM]");
return transit_to(KILL_OBJECT);
submit_op_failed:
- clear_bit(FSCACHE_OBJECT_IS_LIVE, &object->flags);
+ fscache_mark_object_dead(object);
spin_unlock(&cookie->lock);
fscache_unuse_cookie(object);
kfree(op);