[PATCH 4.9 158/264] random: do crng pre-init loading in worker rather than irq

[Greg Kroah-Hartman]

From: "Jason A. Donenfeld" <Jason@xxxxxxxxx>

commit c2a7de4feb6e09f23af7accc0f882a8fa92e7ae5 upstream.

Taking spinlocks from IRQ context is generally problematic for
PREEMPT_RT. That is, in part, why we take trylocks instead. However, a
spin_try_lock() is also problematic since another spin_lock() invocation
can potentially PI-boost the wrong task, as the spin_try_lock() is
invoked from an IRQ-context, so the task on CPU (random task or idle) is
not the actual owner.

Additionally, by deferring the crng pre-init loading to the worker, we
can use the cryptographic hash function rather than xor, which is
perhaps a meaningful difference when considering this data has only been
through the relatively weak fast_mix() function.

The biggest downside of this approach is that the pre-init loading is
now deferred until later, which means things that need random numbers
after interrupts are enabled, but before workqueues are running -- or
before this particular worker manages to run -- are going to get into
trouble. Hopefully in the real world, this window is rather small,
especially since this code won't run until 64 interrupts had occurred.

Cc: Sultan Alsawaf <sultan@xxxxxxxxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Eric Biggers <ebiggers@xxxxxxxxxx>
Cc: Theodore Ts'o <tytso@xxxxxxx>
Acked-by: Sebastian Andrzej Siewior <bigeasy@xxxxxxxxxxxxx>
Reviewed-by: Dominik Brodowski <linux@xxxxxxxxxxxxxxxxxxxx>
Signed-off-by: Jason A. Donenfeld <Jason@xxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
---
 drivers/char/random.c |   65 ++++++++++++++------------------------------------
 1 file changed, 19 insertions(+), 46 deletions(-)

--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@@ -442,10 +442,6 @@ static void crng_make_state(u32 chacha_s
  * boot time when it's better to have something there rather than
  * nothing.
  *
- * There are two paths, a slow one and a fast one. The slow one
- * hashes the input along with the current key. The fast one simply
- * xors it in, and should only be used from interrupt context.
- *
  * If account is set, then the crng_init_cnt counter is incremented.
  * This shouldn't be set by functions like add_device_randomness(),
  * where we can't trust the buffer passed to it is guaranteed to be
@@ -454,19 +450,15 @@ static void crng_make_state(u32 chacha_s
  * Returns the number of bytes processed from input, which is bounded
  * by CRNG_INIT_CNT_THRESH if account is true.
  */
-static size_t crng_pre_init_inject(const void *input, size_t len,
-				   bool fast, bool account)
+static size_t crng_pre_init_inject(const void *input, size_t len, bool account)
 {
 	static int crng_init_cnt = 0;
+	struct blake2s_state hash;
 	unsigned long flags;
 
-	if (fast) {
-		if (!spin_trylock_irqsave(&base_crng.lock, flags))
-			return 0;
-	} else {
-		spin_lock_irqsave(&base_crng.lock, flags);
-	}
+	blake2s_init(&hash, sizeof(base_crng.key));
 
+	spin_lock_irqsave(&base_crng.lock, flags);
 	if (crng_init != 0) {
 		spin_unlock_irqrestore(&base_crng.lock, flags);
 		return 0;
@@ -475,21 +467,9 @@ static size_t crng_pre_init_inject(const
 	if (account)
 		len = min_t(size_t, len, CRNG_INIT_CNT_THRESH - crng_init_cnt);
 
-	if (fast) {
-		const u8 *src = input;
-		size_t i;
-
-		for (i = 0; i < len; ++i)
-			base_crng.key[(crng_init_cnt + i) %
-				      sizeof(base_crng.key)] ^= src[i];
-	} else {
-		struct blake2s_state hash;
-
-		blake2s_init(&hash, sizeof(base_crng.key));
-		blake2s_update(&hash, base_crng.key, sizeof(base_crng.key));
-		blake2s_update(&hash, input, len);
-		blake2s_final(&hash, base_crng.key);
-	}
+	blake2s_update(&hash, base_crng.key, sizeof(base_crng.key));
+	blake2s_update(&hash, input, len);
+	blake2s_final(&hash, base_crng.key);
 
 	if (account) {
 		crng_init_cnt += len;
@@ -1030,7 +1010,7 @@ void add_device_randomness(const void *b
 	unsigned long flags, now = jiffies;
 
 	if (crng_init == 0 && size)
-		crng_pre_init_inject(buf, size, false, false);
+		crng_pre_init_inject(buf, size, false);
 
 	spin_lock_irqsave(&input_pool.lock, flags);
 	_mix_pool_bytes(&cycles, sizeof(cycles));
@@ -1151,7 +1131,7 @@ void add_hwgenerator_randomness(const vo
 				size_t entropy)
 {
 	if (unlikely(crng_init == 0)) {
-		size_t ret = crng_pre_init_inject(buffer, count, false, true);
+		size_t ret = crng_pre_init_inject(buffer, count, true);
 		mix_pool_bytes(buffer, ret);
 		count -= ret;
 		buffer += ret;
@@ -1291,8 +1271,14 @@ static void mix_interrupt_randomness(str
 	fast_pool->last = jiffies;
 	local_irq_enable();
 
-	mix_pool_bytes(pool, sizeof(pool));
-	credit_entropy_bits(1);
+	if (unlikely(crng_init == 0)) {
+		crng_pre_init_inject(pool, sizeof(pool), true);
+		mix_pool_bytes(pool, sizeof(pool));
+	} else {
+		mix_pool_bytes(pool, sizeof(pool));
+		credit_entropy_bits(1);
+	}
+
 	memzero_explicit(pool, sizeof(pool));
 }
 
@@ -1325,24 +1311,11 @@ void add_interrupt_randomness(int irq)
 	fast_mix(fast_pool->pool32);
 	new_count = ++fast_pool->count;
 
-	if (unlikely(crng_init == 0)) {
-		if (new_count >= 64 &&
-		    crng_pre_init_inject(fast_pool->pool32, sizeof(fast_pool->pool32),
-					 true, true) > 0) {
-			fast_pool->count = 0;
-			fast_pool->last = now;
-			if (spin_trylock(&input_pool.lock)) {
-				_mix_pool_bytes(&fast_pool->pool32, sizeof(fast_pool->pool32));
-				spin_unlock(&input_pool.lock);
-			}
-		}
-		return;
-	}
-
 	if (new_count & MIX_INFLIGHT)
 		return;
 
-	if (new_count < 64 && !time_after(now, fast_pool->last + HZ))
+	if (new_count < 64 && (!time_after(now, fast_pool->last + HZ) ||
+			       unlikely(crng_init == 0)))
 		return;
 
 	if (unlikely(!fast_pool->mix.func))