[NET]: Convert hh_lock to seqlock.

The hard header cache is in the main output path, so using
seqlock instead of reader/writer lock should reduce overhead.

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

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index c57088f..631cec4 100644 (file)
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -199,7 +199,7 @@ struct hh_cache
                                          */
        u16             hh_len;         /* length of header */
        int             (*hh_output)(struct sk_buff *skb);
-       rwlock_t        hh_lock;
+       seqlock_t       hh_lock;
 
        /* cached hardware header; allow for machine alignment needs.        */
 #define HH_DATA_MOD    16

diff --git a/include/net/neighbour.h b/include/net/neighbour.h
index 2396703..3725b93 100644 (file)
--- a/include/net/neighbour.h
+++ b/include/net/neighbour.h
@@ -309,6 +309,24 @@ static inline int neigh_event_send(struct neighbour *neigh, struct sk_buff *skb)
        return 0;
 }
 
+static inline int neigh_hh_output(struct hh_cache *hh, struct sk_buff *skb)
+{
+       unsigned seq;
+       int hh_len;
+
+       do {
+               int hh_alen;
+
+               seq = read_seqbegin(&hh->hh_lock);
+               hh_len = hh->hh_len;
+               hh_alen = HH_DATA_ALIGN(hh_len);
+               memcpy(skb->data - hh_alen, hh->hh_data, hh_alen);
+       } while (read_seqretry(&hh->hh_lock, seq));
+
+       skb_push(skb, hh_len);
+       return hh->hh_output(skb);
+}
+
 static inline struct neighbour *
 __neigh_lookup(struct neigh_table *tbl, const void *pkey, struct net_device *dev, int creat)
 {

diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 0ab1987..e7300b6 100644 (file)
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -577,9 +577,10 @@ void neigh_destroy(struct neighbour *neigh)
        while ((hh = neigh->hh) != NULL) {
                neigh->hh = hh->hh_next;
                hh->hh_next = NULL;
-               write_lock_bh(&hh->hh_lock);
+
+               write_seqlock_bh(&hh->hh_lock);
                hh->hh_output = neigh_blackhole;
-               write_unlock_bh(&hh->hh_lock);
+               write_sequnlock_bh(&hh->hh_lock);
                if (atomic_dec_and_test(&hh->hh_refcnt))
                        kfree(hh);
        }
@@ -897,9 +898,9 @@ static void neigh_update_hhs(struct neighbour *neigh)
 
        if (update) {
                for (hh = neigh->hh; hh; hh = hh->hh_next) {
-                       write_lock_bh(&hh->hh_lock);
+                       write_seqlock_bh(&hh->hh_lock);
                        update(hh, neigh->dev, neigh->ha);
-                       write_unlock_bh(&hh->hh_lock);
+                       write_sequnlock_bh(&hh->hh_lock);
                }
        }
 }
@@ -1089,7 +1090,7 @@ static void neigh_hh_init(struct neighbour *n, struct dst_entry *dst,
                        break;
 
        if (!hh && (hh = kzalloc(sizeof(*hh), GFP_ATOMIC)) != NULL) {
-               rwlock_init(&hh->hh_lock);
+               seqlock_init(&hh->hh_lock);
                hh->hh_type = protocol;
                atomic_set(&hh->hh_refcnt, 0);
                hh->hh_next = NULL;

diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index a35209d..f071f84 100644 (file)
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -164,7 +164,6 @@ EXPORT_SYMBOL_GPL(ip_build_and_send_pkt);
 static inline int ip_finish_output2(struct sk_buff *skb)
 {
        struct dst_entry *dst = skb->dst;
-       struct hh_cache *hh = dst->hh;
        struct net_device *dev = dst->dev;
        int hh_len = LL_RESERVED_SPACE(dev);
 
@@ -183,16 +182,9 @@ static inline int ip_finish_output2(struct sk_buff *skb)
                skb = skb2;
        }
 
-       if (hh) {
-               int hh_alen;
-
-               read_lock_bh(&hh->hh_lock);
-               hh_alen = HH_DATA_ALIGN(hh->hh_len);
-               memcpy(skb->data - hh_alen, hh->hh_data, hh_alen);
-               read_unlock_bh(&hh->hh_lock);
-               skb_push(skb, hh->hh_len);
-               return hh->hh_output(skb);
-       } else if (dst->neighbour)
+       if (dst->hh)
+               return neigh_hh_output(dst->hh, skb);
+       else if (dst->neighbour)
                return dst->neighbour->output(skb);
 
        if (net_ratelimit())

diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index e9212c7..7b7bd44 100644 (file)
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -72,20 +72,11 @@ static __inline__ void ipv6_select_ident(struct sk_buff *skb, struct frag_hdr *f
 
 static inline int ip6_output_finish(struct sk_buff *skb)
 {
-
        struct dst_entry *dst = skb->dst;
-       struct hh_cache *hh = dst->hh;
-
-       if (hh) {
-               int hh_alen;
-
-               read_lock_bh(&hh->hh_lock);
-               hh_alen = HH_DATA_ALIGN(hh->hh_len);
-               memcpy(skb->data - hh_alen, hh->hh_data, hh_alen);
-               read_unlock_bh(&hh->hh_lock);
-               skb_push(skb, hh->hh_len);
-               return hh->hh_output(skb);
-       } else if (dst->neighbour)
+
+       if (dst->hh)
+               return neigh_hh_output(dst->hh, skb);
+       else if (dst->neighbour)
                return dst->neighbour->output(skb);
 
        IP6_INC_STATS_BH(ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES);