random: speed up the fast_mix function by a factor of four

By mixing the entropy in chunks of 32-bit words instead of byte by
byte, we can speed up the fast_mix function significantly.  Since it
is called on every single interrupt, on systems with a very heavy
interrupt load, this can make a noticeable difference.

Also fix a compilation warning in add_interrupt_randomness() and avoid
xor'ing cycles and jiffies together just in case we have an
architecture which tries to define random_get_entropy() by returning
jiffies.
Signed-off-by: N"Theodore Ts'o" <tytso@mit.edu>
Reported-by: NJörn Engel <joern@logfs.org>

drivers/char/random.c

@@ -584,21 +584,26 @@ struct fast_pool {
  * collector.  It's hardcoded for an 128 bit pool and assumes that any
  * locks that might be needed are taken by the caller.
  */
-static void fast_mix(struct fast_pool *f, const void *in, int nbytes)
+static void fast_mix(struct fast_pool *f, __u32 input[4])
 {
-	const char	*bytes = in;
 	__u32		w;
-	unsigned	i = f->count;
 	unsigned	input_rotate = f->rotate;
 
-	while (nbytes--) {
-		w = rol32(*bytes++, input_rotate & 31) ^ f->pool[i & 3] ^
-			f->pool[(i + 1) & 3];
-		f->pool[i & 3] = (w >> 3) ^ twist_table[w & 7];
-		input_rotate += (i++ & 3) ? 7 : 14;
-	}
-	f->count = i;
+	w = rol32(input[0], input_rotate) ^ f->pool[0] ^ f->pool[3];
+	f->pool[0] = (w >> 3) ^ twist_table[w & 7];
+	input_rotate = (input_rotate + 14) & 31;
+	w = rol32(input[1], input_rotate) ^ f->pool[1] ^ f->pool[0];
+	f->pool[1] = (w >> 3) ^ twist_table[w & 7];
+	input_rotate = (input_rotate + 7) & 31;
+	w = rol32(input[2], input_rotate) ^ f->pool[2] ^ f->pool[1];
+	f->pool[2] = (w >> 3) ^ twist_table[w & 7];
+	input_rotate = (input_rotate + 7) & 31;
+	w = rol32(input[3], input_rotate) ^ f->pool[3] ^ f->pool[2];
+	f->pool[3] = (w >> 3) ^ twist_table[w & 7];
+	input_rotate = (input_rotate + 7) & 31;
+
 	f->rotate = input_rotate;
+	f->count++;
 }
 
 /*
@@ -828,20 +833,21 @@ void add_interrupt_randomness(int irq, int irq_flags)
 	struct fast_pool	*fast_pool = &__get_cpu_var(irq_randomness);
 	struct pt_regs		*regs = get_irq_regs();
 	unsigned long		now = jiffies;
-	__u32			input[4], cycles = random_get_entropy();
-
-	input[0] = cycles ^ jiffies;
-	input[1] = irq;
-	if (regs) {
-		__u64 ip = instruction_pointer(regs);
-		input[2] = ip;
-		input[3] = ip >> 32;
-	}
+	cycles_t		cycles = random_get_entropy();
+	__u32			input[4], c_high, j_high;
+	__u64			ip;
+
+	c_high = (sizeof(cycles) > 4) ? cycles >> 32 : 0;
+	j_high = (sizeof(now) > 4) ? now >> 32 : 0;
+	input[0] = cycles ^ j_high ^ irq;
+	input[1] = now ^ c_high;
+	ip = regs ? instruction_pointer(regs) : _RET_IP_;
+	input[2] = ip;
+	input[3] = ip >> 32;
 
-	fast_mix(fast_pool, input, sizeof(input));
+	fast_mix(fast_pool, input);
 
-	if ((fast_pool->count & 1023) &&
-	    !time_after(now, fast_pool->last + HZ))
+	if ((fast_pool->count & 63) && !time_after(now, fast_pool->last + HZ))
 		return;
 
 	fast_pool->last = now;