net: convert gro_count to bitmask

gro_hash size is 192 bytes, and uses 3 cache lines, if there is few
flows, gro_hash may be not fully used, so it is unnecessary to iterate
all gro_hash in napi_gro_flush(), to occupy unnecessary cacheline.

convert gro_count to a bitmask, and rename it as gro_bitmask, each bit
represents a element of gro_hash, only flush a gro_hash element if the
related bit is set, to speed up napi_gro_flush().

and update gro_bitmask only if it will be changed, to reduce cache
update

Suggested-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Li RongQing <lirongqing@baidu.com>
Cc: Stefano Brivio <sbrivio@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 7 insertions, 2 deletions

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 3514d67112b3..c1295c7a452e 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -308,9 +308,14 @@ struct gro_list {
 };
 
 /*
- * Structure for NAPI scheduling similar to tasklet but with weighting
+ * size of gro hash buckets, must less than bit number of
+ * napi_struct::gro_bitmask
  */
 #define GRO_HASH_BUCKETS	8
+
+/*
+ * Structure for NAPI scheduling similar to tasklet but with weighting
+ */
 struct napi_struct {
 	/* The poll_list must only be managed by the entity which
 	 * changes the state of the NAPI_STATE_SCHED bit.  This means
@@ -322,7 +327,7 @@ struct napi_struct {
 
 	unsigned long		state;
 	int			weight;
-	unsigned int		gro_count;
+	unsigned long		gro_bitmask;
 	int			(*poll)(struct napi_struct *, int);
 #ifdef CONFIG_NETPOLL
 	int			poll_owner;