mm/swap_slots.c: fix race conditions in swap_slots cache init

Memory allocations can happen before the swap_slots cache initialization
is completed during cpu bring up.  If we are low on memory, we could
call get_swap_page() and access swap_slots_cache before it is fully
initialized.

Add a check in get_swap_page() for initialized swap_slots_cache to
prevent this condition.  Similar check already exists in free_swap_slot.
Also annotate the checks to indicate the likely condition.

We also added a memory barrier to make sure that the locks
initialization are done before the assignment of cache->slots and
cache->slots_ret pointers.  This ensures the assumption that it is safe
to acquire the slots cache locks and use the slots cache when the
corresponding cache->slots or cache->slots_ret pointers are non null.

[akpm@linux-foundation.org: tidy up comment]
[akpm@linux-foundation.org: fix spello in comment]
Link: http://lkml.kernel.org/r/65a9d0f133f63e66bba37b53b2fd0464b7cae771.1500677066.git.tim.c.chen@linux....

mm/swap_slots.c

@@ -149,6 +149,13 @@ static int alloc_swap_slot_cache(unsigned int cpu)
 	cache->nr = 0;
 	cache->cur = 0;
 	cache->n_ret = 0;
+	/*
+	 * We initialized alloc_lock and free_lock earlier.  We use
+	 * !cache->slots or !cache->slots_ret to know if it is safe to acquire
+	 * the corresponding lock and use the cache.  Memory barrier below
+	 * ensures the assumption.
+	 */
+	mb();
 	cache->slots = slots;
 	slots = NULL;
 	cache->slots_ret = slots_ret;
@@ -275,7 +282,7 @@ int free_swap_slot(swp_entry_t entry)
 	struct swap_slots_cache *cache;
 
 	cache = raw_cpu_ptr(&swp_slots);
-	if (use_swap_slot_cache && cache->slots_ret) {
+	if (likely(use_swap_slot_cache && cache->slots_ret)) {
 		spin_lock_irq(&cache->free_lock);
 		/* Swap slots cache may be deactivated before acquiring lock */
 		if (!use_swap_slot_cache || !cache->slots_ret) {
@@ -326,7 +333,7 @@ swp_entry_t get_swap_page(struct page *page)
 	 */
 	cache = raw_cpu_ptr(&swp_slots);
 
-	if (check_cache_active()) {
+	if (likely(check_cache_active() && cache->slots)) {
 		mutex_lock(&cache->alloc_lock);
 		if (cache->slots) {
 repeat: