Merge tag '20201024-v4-5.10' of git://git.kernel.org/pub/scm/linux/kernel/git/wtarreau/prandom

Pull random32 updates from Willy Tarreau:
 "Make prandom_u32() less predictable.

  This is the cleanup of the latest series of prandom_u32
  experimentations consisting in using SipHash instead of Tausworthe to
  produce the randoms used by the network stack.

  The changes to the files were kept minimal, and the controversial
  commit that used to take noise from the fast_pool (f227e3ec) was
  reverted. Instead, a dedicated "net_rand_noise" per_cpu variable is
  fed from various sources of activities (networking, scheduling) to
  perturb the SipHash state using fast, non-trivially predictable data,
  instead of keeping it fully deterministic. The goal is essentially to
  make any occasional memory leakage or brute-force attempt useless.

  The resulting code was verified to be very slightly faster on x86_64
  than what is was with the controversial commit above, though this
  remains barely above measurement noise. It was also tested on i386 and
  arm, and build- tested only on arm64"

Link: https://lore.kernel.org/netdev/20200808152628.GA27941@SDF.ORG/

* tag '20201024-v4-5.10' of git://git.kernel.org/pub/scm/linux/kernel/git/wtarreau/prandom:
  random32: add a selftest for the prandom32 code
  random32: add noise from network and scheduling activity
  random32: make prandom_u32() output unpredictable

drivers/char/random.c

@@ -1277,7 +1277,6 @@ void add_interrupt_randomness(int irq, int irq_flags)
 
 	fast_mix(fast_pool);
 	add_interrupt_bench(cycles);
-	this_cpu_add(net_rand_state.s1, fast_pool->pool[cycles & 3]);
 
 	if (unlikely(crng_init == 0)) {
 		if ((fast_pool->count >= 64) &&

include/linux/prandom.h

@@ -16,12 +16,62 @@ void prandom_bytes(void *buf, size_t nbytes);
 void prandom_seed(u32 seed);
 void prandom_reseed_late(void);
 
+DECLARE_PER_CPU(unsigned long, net_rand_noise);
+
+#define PRANDOM_ADD_NOISE(a, b, c, d) \
+	prandom_u32_add_noise((unsigned long)(a), (unsigned long)(b), \
+			      (unsigned long)(c), (unsigned long)(d))
+
+#if BITS_PER_LONG == 64
+/*
+ * The core SipHash round function.  Each line can be executed in
+ * parallel given enough CPU resources.
+ */
+#define PRND_SIPROUND(v0, v1, v2, v3) ( \
+	v0 += v1, v1 = rol64(v1, 13),  v2 += v3, v3 = rol64(v3, 16), \
+	v1 ^= v0, v0 = rol64(v0, 32),  v3 ^= v2,                     \
+	v0 += v3, v3 = rol64(v3, 21),  v2 += v1, v1 = rol64(v1, 17), \
+	v3 ^= v0,                      v1 ^= v2, v2 = rol64(v2, 32)  \
+)
+
+#define PRND_K0 (0x736f6d6570736575 ^ 0x6c7967656e657261)
+#define PRND_K1 (0x646f72616e646f6d ^ 0x7465646279746573)
+
+#elif BITS_PER_LONG == 32
+/*
+ * On 32-bit machines, we use HSipHash, a reduced-width version of SipHash.
+ * This is weaker, but 32-bit machines are not used for high-traffic
+ * applications, so there is less output for an attacker to analyze.
+ */
+#define PRND_SIPROUND(v0, v1, v2, v3) ( \
+	v0 += v1, v1 = rol32(v1,  5),  v2 += v3, v3 = rol32(v3,  8), \
+	v1 ^= v0, v0 = rol32(v0, 16),  v3 ^= v2,                     \
+	v0 += v3, v3 = rol32(v3,  7),  v2 += v1, v1 = rol32(v1, 13), \
+	v3 ^= v0,                      v1 ^= v2, v2 = rol32(v2, 16)  \
+)
+#define PRND_K0 0x6c796765
+#define PRND_K1 0x74656462
+
+#else
+#error Unsupported BITS_PER_LONG
+#endif
+
+static inline void prandom_u32_add_noise(unsigned long a, unsigned long b,
+					 unsigned long c, unsigned long d)
+{
+	/*
+	 * This is not used cryptographically; it's just
+	 * a convenient 4-word hash function. (3 xor, 2 add, 2 rol)
+	 */
+	a ^= raw_cpu_read(net_rand_noise);
+	PRND_SIPROUND(a, b, c, d);
+	raw_cpu_write(net_rand_noise, d);
+}
+
 struct rnd_state {
 	__u32 s1, s2, s3, s4;
 };
 
-DECLARE_PER_CPU(struct rnd_state, net_rand_state);
-
 u32 prandom_u32_state(struct rnd_state *state);
 void prandom_bytes_state(struct rnd_state *state, void *buf, size_t nbytes);
 void prandom_seed_full_state(struct rnd_state __percpu *pcpu_state);
@@ -67,6 +117,7 @@ static inline void prandom_seed_state(struct rnd_state *state, u64 seed)
 	state->s2 = __seed(i,   8U);
 	state->s3 = __seed(i,  16U);
 	state->s4 = __seed(i, 128U);
+	PRANDOM_ADD_NOISE(state, i, 0, 0);
 }
 
 /* Pseudo random number generator from numerical recipes. */

kernel/time/timer.c

@@ -1706,6 +1706,8 @@ void update_process_times(int user_tick)
 {
 	struct task_struct *p = current;
 
+	PRANDOM_ADD_NOISE(jiffies, user_tick, p, 0);
+
 	/* Note: this timer irq context must be accounted for as well. */
 	account_process_tick(p, user_tick);
 	run_local_timers();
@@ -1717,13 +1719,6 @@ void update_process_times(int user_tick)
 	scheduler_tick();
 	if (IS_ENABLED(CONFIG_POSIX_TIMERS))
 		run_posix_cpu_timers();
-
-	/* The current CPU might make use of net randoms without receiving IRQs
-	 * to renew them often enough. Let's update the net_rand_state from a
-	 * non-constant value that's not affine to the number of calls to make
-	 * sure it's updated when there's some activity (we don't care in idle).
-	 */
-	this_cpu_add(net_rand_state.s1, rol32(jiffies, 24) + user_tick);
 }
 
 /**

net/core/dev.c

@@ -145,6 +145,7 @@
 #include <linux/indirect_call_wrapper.h>
 #include <net/devlink.h>
 #include <linux/pm_runtime.h>
+#include <linux/prandom.h>
 
 #include "net-sysfs.h"
 
@@ -3558,6 +3559,7 @@ static int xmit_one(struct sk_buff *skb, struct net_device *dev,
 		dev_queue_xmit_nit(skb, dev);
 
 	len = skb->len;
+	PRANDOM_ADD_NOISE(skb, dev, txq, len + jiffies);
 	trace_net_dev_start_xmit(skb, dev);
 	rc = netdev_start_xmit(skb, dev, txq, more);
 	trace_net_dev_xmit(skb, rc, dev, len);
@@ -4130,6 +4132,7 @@ static int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev)
 			if (!skb)
 				goto out;
 
+			PRANDOM_ADD_NOISE(skb, dev, txq, jiffies);
 			HARD_TX_LOCK(dev, txq, cpu);
 
 			if (!netif_xmit_stopped(txq)) {
@@ -4195,6 +4198,7 @@ int dev_direct_xmit(struct sk_buff *skb, u16 queue_id)
 
 	skb_set_queue_mapping(skb, queue_id);
 	txq = skb_get_tx_queue(dev, skb);
+	PRANDOM_ADD_NOISE(skb, dev, txq, jiffies);
 
 	local_bh_disable();