net-gro: Prepare GRO stack for the upcoming tunneling support

This patch modifies the GRO stack to avoid the use of "network_header"
and associated macros like ip_hdr() and ipv6_hdr() in order to allow
an arbitary number of IP hdrs (v4 or v6) to be used in the
encapsulation chain. This lays the foundation for various IP
tunneling support (IP-in-IP, GRE, VXLAN, SIT,...) to be added later.

With this patch, the GRO stack traversing now is mostly based on
skb_gro_offset rather than special hdr offsets saved in skb (e.g.,
skb->network_header). As a result all but the top layer (i.e., the
the transport layer) must have hdrs of the same length in order for
a pkt to be considered for aggregation. Therefore when adding a new
encap layer (e.g., for tunneling), one must check and skip flows
(e.g., by setting NAPI_GRO_CB(p)->same_flow to 0) that have a
different hdr length.

Note that unlike the network header, the transport header can and
will continue to be set by the GRO code since there will be at
most one "transport layer" in the encap chain.

Signed-off-by: H.K. Jerry Chu <hkchu@google.com>
Suggested-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 25 insertions, 51 deletions

diff --git a/net/core/dev.c b/net/core/dev.c
index 355df36360b4..c95d664b2b42 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3752,7 +3752,7 @@ static int napi_gro_complete(struct sk_buff *skb)
                 if (ptype->type != type || !ptype->callbacks.gro_complete)
                         continue;
 
-                err = ptype->callbacks.gro_complete(skb);
+                err = ptype->callbacks.gro_complete(skb, 0);
                 break;
         }
         rcu_read_unlock();
@@ -3818,6 +3818,23 @@ static void gro_list_prepare(struct napi_struct *napi, struct sk_buff *skb)
         }
 }
 
+static void skb_gro_reset_offset(struct sk_buff *skb)
+{
+        const struct skb_shared_info *pinfo = skb_shinfo(skb);
+        const skb_frag_t *frag0 = &pinfo->frags[0];
+
+        NAPI_GRO_CB(skb)->data_offset = 0;
+        NAPI_GRO_CB(skb)->frag0 = NULL;
+        NAPI_GRO_CB(skb)->frag0_len = 0;
+
+        if (skb_mac_header(skb) == skb_tail_pointer(skb) &&
+            pinfo->nr_frags &&
+            !PageHighMem(skb_frag_page(frag0))) {
+                NAPI_GRO_CB(skb)->frag0 = skb_frag_address(frag0);
+                NAPI_GRO_CB(skb)->frag0_len = skb_frag_size(frag0);
+        }
+}
+
 static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
 {
         struct sk_buff **pp = NULL;
@@ -3833,6 +3850,7 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff
         if (skb_is_gso(skb) || skb_has_frag_list(skb))
                 goto normal;
 
+        skb_gro_reset_offset(skb);
         gro_list_prepare(napi, skb);
 
         rcu_read_lock();
@@ -3938,27 +3956,8 @@ static gro_result_t napi_skb_finish(gro_result_t ret, struct sk_buff *skb)
         return ret;
 }
 
-static void skb_gro_reset_offset(struct sk_buff *skb)
-{
-        const struct skb_shared_info *pinfo = skb_shinfo(skb);
-        const skb_frag_t *frag0 = &pinfo->frags[0];
-
-        NAPI_GRO_CB(skb)->data_offset = 0;
-        NAPI_GRO_CB(skb)->frag0 = NULL;
-        NAPI_GRO_CB(skb)->frag0_len = 0;
-
-        if (skb_mac_header(skb) == skb_tail_pointer(skb) &&
-            pinfo->nr_frags &&
-            !PageHighMem(skb_frag_page(frag0))) {
-                NAPI_GRO_CB(skb)->frag0 = skb_frag_address(frag0);
-                NAPI_GRO_CB(skb)->frag0_len = skb_frag_size(frag0);
-        }
-}
-
 gro_result_t napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
 {
-        skb_gro_reset_offset(skb);
-
         return napi_skb_finish(dev_gro_receive(napi, skb), skb);
 }
 EXPORT_SYMBOL(napi_gro_receive);
@@ -3992,12 +3991,7 @@ static gro_result_t napi_frags_finish(struct napi_struct *napi, struct sk_buff *
 {
         switch (ret) {
         case GRO_NORMAL:
-        case GRO_HELD:
-                skb->protocol = eth_type_trans(skb, skb->dev);
-
-                if (ret == GRO_HELD)
-                        skb_gro_pull(skb, -ETH_HLEN);
-                else if (netif_receive_skb(skb))
+                if (netif_receive_skb(skb))
                         ret = GRO_DROP;
                 break;
 
@@ -4006,6 +4000,7 @@ static gro_result_t napi_frags_finish(struct napi_struct *napi, struct sk_buff *
                 napi_reuse_skb(napi, skb);
                 break;
 
+        case GRO_HELD:
         case GRO_MERGED:
                 break;
         }
@@ -4016,36 +4011,15 @@ static gro_result_t napi_frags_finish(struct napi_struct *napi, struct sk_buff *
 static struct sk_buff *napi_frags_skb(struct napi_struct *napi)
 {
         struct sk_buff *skb = napi->skb;
-        struct ethhdr *eth;
-        unsigned int hlen;
-        unsigned int off;
 
         napi->skb = NULL;
 
-        skb_reset_mac_header(skb);
-        skb_gro_reset_offset(skb);
-
-        off = skb_gro_offset(skb);
-        hlen = off + sizeof(*eth);
-        eth = skb_gro_header_fast(skb, off);
-        if (skb_gro_header_hard(skb, hlen)) {
-                eth = skb_gro_header_slow(skb, hlen, off);
-                if (unlikely(!eth)) {
-                        napi_reuse_skb(napi, skb);
-                        skb = NULL;
-                        goto out;
-                }
+        if (unlikely(!pskb_may_pull(skb, sizeof(struct ethhdr)))) {
+                napi_reuse_skb(napi, skb);
+                return NULL;
         }
+        skb->protocol = eth_type_trans(skb, skb->dev);
 
-        skb_gro_pull(skb, sizeof(*eth));
-
-        /*
-         * This works because the only protocols we care about don't require
-         * special handling.  We'll fix it up properly at the end.
-         */
-        skb->protocol = eth->h_proto;
-
-out:
         return skb;
 }