sunrpc/cache: remove races with queuing an upcall.

We currently queue an upcall after setting CACHE_PENDING,
and dequeue after clearing CACHE_PENDING.
So a request should only be present when CACHE_PENDING is set.

However we don't combine the test and the enqueue/dequeue in
a protected region, so it is possible (if unlikely) for a race
to result in a request being queued without CACHE_PENDING set,
or a request to be absent despite CACHE_PENDING.

So: include a test for CACHE_PENDING inside the regions of
enqueue and dequeue where queue_lock is held, and abort
the operation if the value is not as expected.

Also remove the early 'return' from cache_dequeue() to ensure that it
always removes all entries: As there is no locking between setting
CACHE_PENDING and calling sunrpc_cache_pipe_upcall it is not
inconceivable for some other thread to clear CACHE_PENDING and then
someone else to set it and call sunrpc_cache_pipe_upcall, both before
the original threads completed the call.

With this, it perfectly safe and correct to:
 - call cache_dequeue() if and only if we have just
   cleared CACHE_PENDING
 - call sunrpc_cache_pipe_upcall() (via cache_make_upcall)
   if and only if we have just set CACHE_PENDING.

Reported-by: Bodo Stroesser <bstroesser@ts.fujitsu.com>
Signed-off-by: NeilBrown <neilb@suse.de>
Signed-off-by: Bodo Stroesser <bstroesser@ts.fujitsu.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>

diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c
index 3b3f14fc02c5eb3f475b117c7a23988712959316..8e964ae8d7b5d78cba84763b41ae726ff91d6ed0 100644 (file)
--- a/net/sunrpc/cache.c
+++ b/net/sunrpc/cache.c
@@ -1036,23 +1036,32 @@ static int cache_release(struct inode *inode, struct file *filp,
 
 static void cache_dequeue(struct cache_detail *detail, struct cache_head *ch)
 {
-       struct cache_queue *cq;
+       struct cache_queue *cq, *tmp;
+       struct cache_request *cr;
+       struct list_head dequeued;
+
+       INIT_LIST_HEAD(&dequeued);
        spin_lock(&queue_lock);
-       list_for_each_entry(cq, &detail->queue, list)
+       list_for_each_entry_safe(cq, tmp, &detail->queue, list)
                if (!cq->reader) {
-                       struct cache_request *cr = container_of(cq, struct cache_request, q);
+                       cr = container_of(cq, struct cache_request, q);
                        if (cr->item != ch)
                                continue;
+                       if (test_bit(CACHE_PENDING, &ch->flags))
+                               /* Lost a race and it is pending again */
+                               break;
                        if (cr->readers != 0)
                                continue;
-                       list_del(&cr->q.list);
-                       spin_unlock(&queue_lock);
-                       cache_put(cr->item, detail);
-                       kfree(cr->buf);
-                       kfree(cr);
-                       return;
+                       list_move(&cr->q.list, &dequeued);
                }
        spin_unlock(&queue_lock);
+       while (!list_empty(&dequeued)) {
+               cr = list_entry(dequeued.next, struct cache_request, q.list);
+               list_del(&cr->q.list);
+               cache_put(cr->item, detail);
+               kfree(cr->buf);
+               kfree(cr);
+       }
 }
 
 /*
@@ -1166,6 +1175,7 @@ int sunrpc_cache_pipe_upcall(struct cache_detail *detail, struct cache_head *h)
 
        char *buf;
        struct cache_request *crq;
+       int ret = 0;
 
        if (!detail->cache_request)
                return -EINVAL;
@@ -1191,10 +1201,18 @@ int sunrpc_cache_pipe_upcall(struct cache_detail *detail, struct cache_head *h)
        crq->len = 0;
        crq->readers = 0;
        spin_lock(&queue_lock);
-       list_add_tail(&crq->q.list, &detail->queue);
+       if (test_bit(CACHE_PENDING, &h->flags))
+               list_add_tail(&crq->q.list, &detail->queue);
+       else
+               /* Lost a race, no longer PENDING, so don't enqueue */
+               ret = -EAGAIN;
        spin_unlock(&queue_lock);
        wake_up(&queue_wait);
-       return 0;
+       if (ret == -EAGAIN) {
+               kfree(buf);
+               kfree(crq);
+       }
+       return ret;
 }
 EXPORT_SYMBOL_GPL(sunrpc_cache_pipe_upcall);