[TCP] tcp_cubic: faster cube root

The Newton-Raphson method is quadratically convergent so
only a small fixed number of steps are necessary.
Therefore it is faster to unroll the loop. Since div64_64 is no longer
inline it won't cause code explosion.

Also fixes a bug that can occur if x^2 was bigger than 32 bits.

Signed-off-by: Stephen Hemminger <shemminger@linux-foundation.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c
index 6f08adbda54e3e198b86632152bb53b01d8b6cef..0e6cdfeb207a15af1f9c51453f35cd8df8cd586a 100644 (file)
--- a/net/ipv4/tcp_cubic.c
+++ b/net/ipv4/tcp_cubic.c
@@ -96,23 +96,17 @@ static void bictcp_init(struct sock *sk)
  */
 static u32 cubic_root(u64 a)
 {
-       u32 x, x1;
+       u32 x;
 
        /* Initial estimate is based on:
         * cbrt(x) = exp(log(x) / 3)
         */
        x = 1u << (fls64(a)/3);
 
-       /*
-        * Iteration based on:
-        *                         2
-        * x    = ( 2 * x  +  a / x  ) / 3
-        *  k+1          k         k
-        */
-       do {
-               x1 = x;
-               x = (2 * x + (uint32_t) div64_64(a, x*x)) / 3;
-       } while (abs(x1 - x) > 1);
+       /* converges to 32 bits in 3 iterations */
+       x = (2 * x + (u32)div64_64(a, (u64)x*(u64)x)) / 3;
+       x = (2 * x + (u32)div64_64(a, (u64)x*(u64)x)) / 3;
+       x = (2 * x + (u32)div64_64(a, (u64)x*(u64)x)) / 3;
 
        return x;
 }