svcrpc: ensure cache_check caller sees updated entry

Supposes cache_check runs simultaneously with an update on a different
CPU:

cache_check task doing update
^^^^^^^^^^^ ^^^^^^^^^^^^^^^^^

1. test for CACHE_VALID 1'. set entry->data
& !CACHE_NEGATIVE

2. use entry->data 2'. set CACHE_VALID

If the two memory writes performed in step 1' and 2' appear misordered
with respect to the reads in step 1 and 2, then the caller could get
stale data at step 2 even though it saw CACHE_VALID set on the cache
entry.

Add memory barriers to prevent this.

Reviewed-by: NeilBrown <[e-mail]>
Signed-off-by: J. Bruce Fields <[e-mail]>

net/sunrpc/cache.c

···
 {
 	head->expiry_time = expiry;
 	head->last_refresh = seconds_since_boot();
+	smp_wmb(); /* paired with smp_rmb() in cache_is_valid() */
 	set_bit(CACHE_VALID, &head->flags);
 }
 
···
 		/* entry is valid */
 		if (test_bit(CACHE_NEGATIVE, &h->flags))
 			return -ENOENT;
-		else
+		else {
+			/*
+			 * In combination with write barrier in
+			 * sunrpc_cache_update, ensures that anyone
+			 * using the cache entry after this sees the
+			 * updated contents:
+			 */
+			smp_rmb();
 			return 0;
+		}
 	}
 }