net: ipv6: seg6_iptunnel: mitigate 2-realloc issue

This patch mitigates the two-reallocations issue with seg6_iptunnel by
providing the dst_entry (in the cache) to the first call to
skb_cow_head(). As a result, the very first iteration would still
trigger two reallocations (i.e., empty cache), while next iterations
would only trigger a single reallocation.

Performance tests before/after applying this patch, which clearly shows
the improvement:
- before: https://ibb.co/3Cg4sNH
- after: https://ibb.co/8rQ350r

Signed-off-by: Justin Iurman <justin.iurman@uliege.be>
Cc: David Lebrun <dlebrun@google.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>

diff --git a/net/ipv6/seg6_iptunnel.c b/net/ipv6/seg6_iptunnel.c
index 098632adc9b5afa69e4b65439ee54c3fc0a8d668..4bf937bfc2633c6abad8249e6ffae6c67070d7a9 100644 (file)
--- a/net/ipv6/seg6_iptunnel.c
+++ b/net/ipv6/seg6_iptunnel.c
@@ -124,8 +124,8 @@ static __be32 seg6_make_flowlabel(struct net *net, struct sk_buff *skb,
        return flowlabel;
 }
 
-/* encapsulate an IPv6 packet within an outer IPv6 header with a given SRH */
-int seg6_do_srh_encap(struct sk_buff *skb, struct ipv6_sr_hdr *osrh, int proto)
+static int __seg6_do_srh_encap(struct sk_buff *skb, struct ipv6_sr_hdr *osrh,
+                              int proto, struct dst_entry *cache_dst)
 {
        struct dst_entry *dst = skb_dst(skb);
        struct net *net = dev_net(dst->dev);
@@ -137,7 +137,7 @@ int seg6_do_srh_encap(struct sk_buff *skb, struct ipv6_sr_hdr *osrh, int proto)
        hdrlen = (osrh->hdrlen + 1) << 3;
        tot_len = hdrlen + sizeof(*hdr);
 
-       err = skb_cow_head(skb, tot_len + skb->mac_len);
+       err = skb_cow_head(skb, tot_len + dst_dev_overhead(cache_dst, skb));
        if (unlikely(err))
                return err;
 
@@ -197,11 +197,18 @@ int seg6_do_srh_encap(struct sk_buff *skb, struct ipv6_sr_hdr *osrh, int proto)
 
        return 0;
 }
+
+/* encapsulate an IPv6 packet within an outer IPv6 header with a given SRH */
+int seg6_do_srh_encap(struct sk_buff *skb, struct ipv6_sr_hdr *osrh, int proto)
+{
+       return __seg6_do_srh_encap(skb, osrh, proto, NULL);
+}
 EXPORT_SYMBOL_GPL(seg6_do_srh_encap);
 
 /* encapsulate an IPv6 packet within an outer IPv6 header with reduced SRH */
 static int seg6_do_srh_encap_red(struct sk_buff *skb,
-                                struct ipv6_sr_hdr *osrh, int proto)
+                                struct ipv6_sr_hdr *osrh, int proto,
+                                struct dst_entry *cache_dst)
 {
        __u8 first_seg = osrh->first_segment;
        struct dst_entry *dst = skb_dst(skb);
@@ -230,7 +237,7 @@ static int seg6_do_srh_encap_red(struct sk_buff *skb,
 
        tot_len = red_hdrlen + sizeof(struct ipv6hdr);
 
-       err = skb_cow_head(skb, tot_len + skb->mac_len);
+       err = skb_cow_head(skb, tot_len + dst_dev_overhead(cache_dst, skb));
        if (unlikely(err))
                return err;
 
@@ -317,8 +324,8 @@ out:
        return 0;
 }
 
-/* insert an SRH within an IPv6 packet, just after the IPv6 header */
-int seg6_do_srh_inline(struct sk_buff *skb, struct ipv6_sr_hdr *osrh)
+static int __seg6_do_srh_inline(struct sk_buff *skb, struct ipv6_sr_hdr *osrh,
+                               struct dst_entry *cache_dst)
 {
        struct ipv6hdr *hdr, *oldhdr;
        struct ipv6_sr_hdr *isrh;
@@ -326,7 +333,7 @@ int seg6_do_srh_inline(struct sk_buff *skb, struct ipv6_sr_hdr *osrh)
 
        hdrlen = (osrh->hdrlen + 1) << 3;
 
-       err = skb_cow_head(skb, hdrlen + skb->mac_len);
+       err = skb_cow_head(skb, hdrlen + dst_dev_overhead(cache_dst, skb));
        if (unlikely(err))
                return err;
 
@@ -369,9 +376,8 @@ int seg6_do_srh_inline(struct sk_buff *skb, struct ipv6_sr_hdr *osrh)
 
        return 0;
 }
-EXPORT_SYMBOL_GPL(seg6_do_srh_inline);
 
-static int seg6_do_srh(struct sk_buff *skb)
+static int seg6_do_srh(struct sk_buff *skb, struct dst_entry *cache_dst)
 {
        struct dst_entry *dst = skb_dst(skb);
        struct seg6_iptunnel_encap *tinfo;
@@ -384,7 +390,7 @@ static int seg6_do_srh(struct sk_buff *skb)
                if (skb->protocol != htons(ETH_P_IPV6))
                        return -EINVAL;
 
-               err = seg6_do_srh_inline(skb, tinfo->srh);
+               err = __seg6_do_srh_inline(skb, tinfo->srh, cache_dst);
                if (err)
                        return err;
                break;
@@ -402,9 +408,11 @@ static int seg6_do_srh(struct sk_buff *skb)
                        return -EINVAL;
 
                if (tinfo->mode == SEG6_IPTUN_MODE_ENCAP)
-                       err = seg6_do_srh_encap(skb, tinfo->srh, proto);
+                       err = __seg6_do_srh_encap(skb, tinfo->srh,
+                                                 proto, cache_dst);
                else
-                       err = seg6_do_srh_encap_red(skb, tinfo->srh, proto);
+                       err = seg6_do_srh_encap_red(skb, tinfo->srh,
+                                                   proto, cache_dst);
 
                if (err)
                        return err;
@@ -425,11 +433,13 @@ static int seg6_do_srh(struct sk_buff *skb)
                skb_push(skb, skb->mac_len);
 
                if (tinfo->mode == SEG6_IPTUN_MODE_L2ENCAP)
-                       err = seg6_do_srh_encap(skb, tinfo->srh,
-                                               IPPROTO_ETHERNET);
+                       err = __seg6_do_srh_encap(skb, tinfo->srh,
+                                                 IPPROTO_ETHERNET,
+                                                 cache_dst);
                else
                        err = seg6_do_srh_encap_red(skb, tinfo->srh,
-                                                   IPPROTO_ETHERNET);
+                                                   IPPROTO_ETHERNET,
+                                                   cache_dst);
 
                if (err)
                        return err;
@@ -444,6 +454,13 @@ static int seg6_do_srh(struct sk_buff *skb)
        return 0;
 }
 
+/* insert an SRH within an IPv6 packet, just after the IPv6 header */
+int seg6_do_srh_inline(struct sk_buff *skb, struct ipv6_sr_hdr *osrh)
+{
+       return __seg6_do_srh_inline(skb, osrh, NULL);
+}
+EXPORT_SYMBOL_GPL(seg6_do_srh_inline);
+
 static int seg6_input_finish(struct net *net, struct sock *sk,
                             struct sk_buff *skb)
 {
@@ -458,31 +475,33 @@ static int seg6_input_core(struct net *net, struct sock *sk,
        struct seg6_lwt *slwt;
        int err;
 
-       err = seg6_do_srh(skb);
-       if (unlikely(err))
-               goto drop;
-
        slwt = seg6_lwt_lwtunnel(orig_dst->lwtstate);
 
        local_bh_disable();
        dst = dst_cache_get(&slwt->cache);
+       local_bh_enable();
+
+       err = seg6_do_srh(skb, dst);
+       if (unlikely(err))
+               goto drop;
 
        if (!dst) {
                ip6_route_input(skb);
                dst = skb_dst(skb);
                if (!dst->error) {
+                       local_bh_disable();
                        dst_cache_set_ip6(&slwt->cache, dst,
                                          &ipv6_hdr(skb)->saddr);
+                       local_bh_enable();
                }
+
+               err = skb_cow_head(skb, LL_RESERVED_SPACE(dst->dev));
+               if (unlikely(err))
+                       goto drop;
        } else {
                skb_dst_drop(skb);
                skb_dst_set(skb, dst);
        }
-       local_bh_enable();
-
-       err = skb_cow_head(skb, LL_RESERVED_SPACE(dst->dev));
-       if (unlikely(err))
-               goto drop;
 
        if (static_branch_unlikely(&nf_hooks_lwtunnel_enabled))
                return NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT,
@@ -528,16 +547,16 @@ static int seg6_output_core(struct net *net, struct sock *sk,
        struct seg6_lwt *slwt;
        int err;
 
-       err = seg6_do_srh(skb);
-       if (unlikely(err))
-               goto drop;
-
        slwt = seg6_lwt_lwtunnel(orig_dst->lwtstate);
 
        local_bh_disable();
        dst = dst_cache_get(&slwt->cache);
        local_bh_enable();
 
+       err = seg6_do_srh(skb, dst);
+       if (unlikely(err))
+               goto drop;
+
        if (unlikely(!dst)) {
                struct ipv6hdr *hdr = ipv6_hdr(skb);
                struct flowi6 fl6;
@@ -559,15 +578,15 @@ static int seg6_output_core(struct net *net, struct sock *sk,
                local_bh_disable();
                dst_cache_set_ip6(&slwt->cache, dst, &fl6.saddr);
                local_bh_enable();
+
+               err = skb_cow_head(skb, LL_RESERVED_SPACE(dst->dev));
+               if (unlikely(err))
+                       goto drop;
        }
 
        skb_dst_drop(skb);
        skb_dst_set(skb, dst);
 
-       err = skb_cow_head(skb, LL_RESERVED_SPACE(dst->dev));
-       if (unlikely(err))
-               goto drop;
-
        if (static_branch_unlikely(&nf_hooks_lwtunnel_enabled))
                return NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, net, sk, skb,
                               NULL, skb_dst(skb)->dev, dst_output);