random: remove batched entropy locking

Rather than use spinlocks to protect batched entropy, we can instead
disable interrupts locally, since we're dealing with per-cpu data, and
manage resets with a basic generation counter. At the same time, we
can't quite do this on PREEMPT_RT, where we still want spinlocks-as-
mutexes semantics. So we use a local_lock_t, which provides the right
behavior for each. Because this is a per-cpu lock, that generation
counter is still doing the necessary CPU-to-CPU communication.

This should improve performance a bit. It will also fix the linked splat
that Jonathan received with a PROVE_RAW_LOCK_NESTING=y.
Reviewed-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Reviewed-by: Dominik Brodowski <linux@dominikbrodowski.net>
Reviewed-by: Eric Biggers <ebiggers@google.com>
Suggested-by: Andy Lutomirski <luto@kernel.org>
Reported-by: Jonathan Neuschäfer <j.neuschaefer@gmx.net>
Tested-by: Jonathan Neuschäfer <j.neuschaefer@gmx.net>
Link: https://lore.kernel.org/lkml/YfMa0QgsjCVdRAvJ@latitude/Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>

drivers/char/random.c

@@ -1731,13 +1731,16 @@ static int __init random_sysctls_init(void)
 device_initcall(random_sysctls_init);
 #endif	/* CONFIG_SYSCTL */
 
+static atomic_t batch_generation = ATOMIC_INIT(0);
+
 struct batched_entropy {
 	union {
 		u64 entropy_u64[CHACHA_BLOCK_SIZE / sizeof(u64)];
 		u32 entropy_u32[CHACHA_BLOCK_SIZE / sizeof(u32)];
 	};
+	local_lock_t lock;
 	unsigned int position;
-	spinlock_t batch_lock;
+	int generation;
 };
 
 /*
@@ -1749,7 +1752,7 @@ struct batched_entropy {
  * point prior.
  */
 static DEFINE_PER_CPU(struct batched_entropy, batched_entropy_u64) = {
-	.batch_lock = __SPIN_LOCK_UNLOCKED(batched_entropy_u64.lock),
+	.lock = INIT_LOCAL_LOCK(batched_entropy_u64.lock)
 };
 
 u64 get_random_u64(void)
@@ -1758,67 +1761,65 @@ u64 get_random_u64(void)
 	unsigned long flags;
 	struct batched_entropy *batch;
 	static void *previous;
+	int next_gen;
 
 	warn_unseeded_randomness(&previous);
 
+	local_lock_irqsave(&batched_entropy_u64.lock, flags);
 	batch = raw_cpu_ptr(&batched_entropy_u64);
-	spin_lock_irqsave(&batch->batch_lock, flags);
-	if (batch->position % ARRAY_SIZE(batch->entropy_u64) == 0) {
+
+	next_gen = atomic_read(&batch_generation);
+	if (batch->position % ARRAY_SIZE(batch->entropy_u64) == 0 ||
+	    next_gen != batch->generation) {
 		extract_crng((u8 *)batch->entropy_u64);
 		batch->position = 0;
+		batch->generation = next_gen;
 	}
+
 	ret = batch->entropy_u64[batch->position++];
-	spin_unlock_irqrestore(&batch->batch_lock, flags);
+	local_unlock_irqrestore(&batched_entropy_u64.lock, flags);
 	return ret;
 }
 EXPORT_SYMBOL(get_random_u64);
 
 static DEFINE_PER_CPU(struct batched_entropy, batched_entropy_u32) = {
-	.batch_lock = __SPIN_LOCK_UNLOCKED(batched_entropy_u32.lock),
+	.lock = INIT_LOCAL_LOCK(batched_entropy_u32.lock)
 };
+
 u32 get_random_u32(void)
 {
 	u32 ret;
 	unsigned long flags;
 	struct batched_entropy *batch;
 	static void *previous;
+	int next_gen;
 
 	warn_unseeded_randomness(&previous);
 
+	local_lock_irqsave(&batched_entropy_u32.lock, flags);
 	batch = raw_cpu_ptr(&batched_entropy_u32);
-	spin_lock_irqsave(&batch->batch_lock, flags);
-	if (batch->position % ARRAY_SIZE(batch->entropy_u32) == 0) {
+
+	next_gen = atomic_read(&batch_generation);
+	if (batch->position % ARRAY_SIZE(batch->entropy_u32) == 0 ||
+	    next_gen != batch->generation) {
 		extract_crng((u8 *)batch->entropy_u32);
 		batch->position = 0;
+		batch->generation = next_gen;
 	}
+
 	ret = batch->entropy_u32[batch->position++];
-	spin_unlock_irqrestore(&batch->batch_lock, flags);
+	local_unlock_irqrestore(&batched_entropy_u32.lock, flags);
 	return ret;
 }
 EXPORT_SYMBOL(get_random_u32);
 
 /* It's important to invalidate all potential batched entropy that might
  * be stored before the crng is initialized, which we can do lazily by
- * simply resetting the counter to zero so that it's re-extracted on the
- * next usage. */
+ * bumping the generation counter.
+ */
 static void invalidate_batched_entropy(void)
 {
-	int cpu;
-	unsigned long flags;
-
-	for_each_possible_cpu(cpu) {
-		struct batched_entropy *batched_entropy;
-
-		batched_entropy = per_cpu_ptr(&batched_entropy_u32, cpu);
-		spin_lock_irqsave(&batched_entropy->batch_lock, flags);
-		batched_entropy->position = 0;
-		spin_unlock(&batched_entropy->batch_lock);
-
-		batched_entropy = per_cpu_ptr(&batched_entropy_u64, cpu);
-		spin_lock(&batched_entropy->batch_lock);
-		batched_entropy->position = 0;
-		spin_unlock_irqrestore(&batched_entropy->batch_lock, flags);
-	}
+	atomic_inc(&batch_generation);
 }
 
 /**