net-gro: use ffs() to speedup napi_gro_flush()

We very often have few flows/chains to look at, and we
might increase GRO_HASH_BUCKETS to 32 or 64 in the future.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
diff --git a/net/core/dev.c b/net/core/dev.c
index f2bfd2e..d835826 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -5364,11 +5364,13 @@ static void __napi_gro_flush_chain(struct napi_struct *napi, u32 index,
  */
 void napi_gro_flush(struct napi_struct *napi, bool flush_old)
 {
-	u32 i;
+	unsigned long bitmask = napi->gro_bitmask;
+	unsigned int i, base = ~0U;
 
-	for (i = 0; i < GRO_HASH_BUCKETS; i++) {
-		if (test_bit(i, &napi->gro_bitmask))
-			__napi_gro_flush_chain(napi, i, flush_old);
+	while ((i = ffs(bitmask)) != 0) {
+		bitmask >>= i;
+		base += i;
+		__napi_gro_flush_chain(napi, base, flush_old);
 	}
 }
 EXPORT_SYMBOL(napi_gro_flush);