random: fix data race on crng_node_pool

extract_crng() and crng_backtrack_protect() load crng_node_pool with a
plain load, which causes undefined behavior if do_numa_crng_init()
modifies it concurrently.

Fix this by using READ_ONCE().  Note: as per the previous discussion
https://lore.kernel.org/lkml/20211219025139.31085-1-ebiggers@kernel.org/T/#u,
READ_ONCE() is believed to be sufficient here, and it was requested that
it be used here instead of smp_load_acquire().

Also change do_numa_crng_init() to set crng_node_pool using
cmpxchg_release() instead of mb() + cmpxchg(), as the former is
sufficient here but is more lightweight.

Fixes: 1e7f583 ("random: make /dev/urandom scalable for silly userspace programs")
Cc: stable@vger.kernel.org
Signed-off-by: Eric Biggers <ebiggers@google.com>
Acked-by: Paul E. McKenney <paulmck@kernel.org>
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>

Author: ebiggers

drivers/char/random.c

@@ -854,8 +854,8 @@ static void do_numa_crng_init(struct work_struct *work)
 		crng_initialize_secondary(crng);
 		pool[i] = crng;
 	}
-	mb();
-	if (cmpxchg(&crng_node_pool, NULL, pool)) {
+	/* pairs with READ_ONCE() in select_crng() */
+	if (cmpxchg_release(&crng_node_pool, NULL, pool) != NULL) {
 		for_each_node(i)
 			kfree(pool[i]);
 		kfree(pool);
@@ -868,8 +868,26 @@ static void numa_crng_init(void)
 {
 	schedule_work(&numa_crng_init_work);
 }
+
+static struct crng_state *select_crng(void)
+{
+	struct crng_state **pool;
+	int nid = numa_node_id();
+
+	/* pairs with cmpxchg_release() in do_numa_crng_init() */
+	pool = READ_ONCE(crng_node_pool);
+	if (pool && pool[nid])
+		return pool[nid];
+
+	return &primary_crng;
+}
 #else
 static void numa_crng_init(void) {}
+
+static struct crng_state *select_crng(void)
+{
+	return &primary_crng;
+}
 #endif
 
 /*
@@ -1016,15 +1034,7 @@ static void _extract_crng(struct crng_state *crng,
 
 static void extract_crng(__u8 out[CHACHA_BLOCK_SIZE])
 {
-	struct crng_state *crng = NULL;
-
-#ifdef CONFIG_NUMA
-	if (crng_node_pool)
-		crng = crng_node_pool[numa_node_id()];
-	if (crng == NULL)
-#endif
-		crng = &primary_crng;
-	_extract_crng(crng, out);
+	_extract_crng(select_crng(), out);
 }
 
 /*
@@ -1053,15 +1063,7 @@ static void _crng_backtrack_protect(struct crng_state *crng,
 
 static void crng_backtrack_protect(__u8 tmp[CHACHA_BLOCK_SIZE], int used)
 {
-	struct crng_state *crng = NULL;
-
-#ifdef CONFIG_NUMA
-	if (crng_node_pool)
-		crng = crng_node_pool[numa_node_id()];
-	if (crng == NULL)
-#endif
-		crng = &primary_crng;
-	_crng_backtrack_protect(crng, tmp, used);
+	_crng_backtrack_protect(select_crng(), tmp, used);
 }
 
 static ssize_t extract_crng_user(void __user *buf, size_t nbytes)