[PATCH net-next 1/3] net: lwtunnel: Handle fragmentation

[David Ahern]

From: Roopa Prabhu 

Today mpls iptunnel lwtunnel_output redirect expects the tunnel
output function to handle fragmentation. This is ok but can be
avoided if we did not do the mpls output redirect too early.
ie we could wait until ip fragmentation is done and then call
mpls output for each ip fragment.

To make this work we will need,
1) the lwtunnel state to carry encap headroom
2) and do the redirect to the encap output handler on the ip fragment
(essentially do the output redirect after fragmentation)

This patch adds tunnel headroom in lwtstate to make sure we
account for tunnel data in mtu calculations during fragmentation
and adds new xmit redirect handler to redirect to lwtunnel xmit func
after ip fragmentation.

This includes IPV6 and some mtu fixes and testing from David Ahern.

Signed-off-by: Roopa Prabhu 
Signed-off-by: David Ahern 
---
 include/net/lwtunnel.h   | 44 
 net/core/lwtunnel.c  | 35 +++
 net/ipv4/ip_output.c |  8 
 net/ipv4/route.c |  4 +++-
 net/ipv6/ip6_output.c|  8 
 net/ipv6/route.c |  4 +++-
 net/mpls/mpls_iptunnel.c |  9 +
 7 files changed, 106 insertions(+), 6 deletions(-)

diff --git a/include/net/lwtunnel.h b/include/net/lwtunnel.h
index e9f116e29c22..ea3f80f58fd6 100644
--- a/include/net/lwtunnel.h
+++ b/include/net/lwtunnel.h
@@ -13,6 +13,13 @@
 /* lw tunnel state flags */
 #define LWTUNNEL_STATE_OUTPUT_REDIRECT BIT(0)
 #define LWTUNNEL_STATE_INPUT_REDIRECT  BIT(1)
+#define LWTUNNEL_STATE_XMIT_REDIRECT   BIT(2)
+
+enum {
+   LWTUNNEL_XMIT_DONE,
+   LWTUNNEL_XMIT_CONTINUE,
+};
+
 
 struct lwtunnel_state {
__u16   type;
@@ -21,6 +28,7 @@ struct lwtunnel_state {
int (*orig_output)(struct net *net, struct sock *sk, struct 
sk_buff *skb);
int (*orig_input)(struct sk_buff *);
int len;
+   __u16   headroom;
__u8data[0];
 };
 
@@ -34,6 +42,7 @@ struct lwtunnel_encap_ops {
  struct lwtunnel_state *lwtstate);
int (*get_encap_size)(struct lwtunnel_state *lwtstate);
int (*cmp_encap)(struct lwtunnel_state *a, struct lwtunnel_state *b);
+   int (*xmit)(struct sk_buff *skb);
 };
 
 #ifdef CONFIG_LWTUNNEL
@@ -75,6 +84,24 @@ static inline bool lwtunnel_input_redirect(struct 
lwtunnel_state *lwtstate)
 
return false;
 }
+
+static inline bool lwtunnel_xmit_redirect(struct lwtunnel_state *lwtstate)
+{
+   if (lwtstate && (lwtstate->flags & LWTUNNEL_STATE_XMIT_REDIRECT))
+   return true;
+
+   return false;
+}
+
+static inline unsigned int lwtunnel_headroom(struct lwtunnel_state *lwtstate,
+unsigned int mtu)
+{
+   if (lwtunnel_xmit_redirect(lwtstate) && lwtstate->headroom < mtu)
+   return lwtstate->headroom;
+
+   return 0;
+}
+
 int lwtunnel_encap_add_ops(const struct lwtunnel_encap_ops *op,
   unsigned int num);
 int lwtunnel_encap_del_ops(const struct lwtunnel_encap_ops *op,
@@ -90,6 +117,7 @@ struct lwtunnel_state *lwtunnel_state_alloc(int hdr_len);
 int lwtunnel_cmp_encap(struct lwtunnel_state *a, struct lwtunnel_state *b);
 int lwtunnel_output(struct net *net, struct sock *sk, struct sk_buff *skb);
 int lwtunnel_input(struct sk_buff *skb);
+int lwtunnel_xmit(struct sk_buff *skb);
 
 #else
 
@@ -117,6 +145,17 @@ static inline bool lwtunnel_input_redirect(struct 
lwtunnel_state *lwtstate)
return false;
 }
 
+static inline bool lwtunnel_xmit_redirect(struct lwtunnel_state *lwtstate)
+{
+   return false;
+}
+
+static inline unsigned int lwtunnel_headroom(struct lwtunnel_state *lwtstate,
+unsigned int mtu)
+{
+   return 0;
+}
+
 static inline int lwtunnel_encap_add_ops(const struct lwtunnel_encap_ops *op,
 unsigned int num)
 {
@@ -170,6 +209,11 @@ static inline int lwtunnel_input(struct sk_buff *skb)
return -EOPNOTSUPP;
 }
 
+static inline int lwtunnel_xmit(struct sk_buff *skb)
+{
+   return -EOPNOTSUPP;
+}
+
 #endif /* CONFIG_LWTUNNEL */
 
 #define MODULE_ALIAS_RTNL_LWT(encap_type) MODULE_ALIAS("rtnl-lwt-" 
__stringify(encap_type))
diff --git a/net/core/lwtunnel.c b/net/core/lwtunnel.c
index 669ecc9f884e..e5f84c26ba1a 100644
--- a/net/core/lwtunnel.c
+++ b/net/core/lwtunnel.c
@@ -251,6 +251,41 @@ int lwtunnel_output(struct net *net, struct sock *sk, 
struct sk_buff *skb)
 }
 EXPORT_SYMBOL(lwtunnel_output);
 
+int lwtunnel_xmit(struct sk_buff *skb)
+{
+   struct dst_entry *dst = skb_dst(skb);
+   const struct lwtunnel_encap_ops *ops;
+   struct lwtunnel_state *lwtstate;
+   int ret = -EINVAL;
+
+   if (!dst)
+   goto drop;
+
+   lwtstate = dst->lwtstate;
+
+   if 

[PATCH net-next 1/3] net: lwtunnel: Handle fragmentation

[David Ahern]

From: Roopa Prabhu 

Today mpls iptunnel lwtunnel_output redirect expects the tunnel
output function to handle fragmentation. This is ok but can be
avoided if we did not do the mpls output redirect too early.
ie we could wait until ip fragmentation is done and then call
mpls output for each ip fragment.

To make this work we will need,
1) the lwtunnel state to carry encap headroom
2) and do the redirect to the encap output handler on the ip fragment
(essentially do the output redirect after fragmentation)

This patch adds tunnel headroom in lwtstate to make sure we
account for tunnel data in mtu calculations during fragmentation
and adds new xmit redirect handler to redirect to lwtunnel xmit func
after ip fragmentation.

This includes IPV6 and some mtu fixes and testing from David Ahern.

Signed-off-by: Roopa Prabhu 
Signed-off-by: David Ahern 
---
 include/net/lwtunnel.h   | 44 
 net/core/lwtunnel.c  | 35 +++
 net/ipv4/ip_output.c |  8 
 net/ipv4/route.c |  4 +++-
 net/ipv6/ip6_output.c|  8 
 net/ipv6/route.c |  4 +++-
 net/mpls/mpls_iptunnel.c |  9 +
 7 files changed, 106 insertions(+), 6 deletions(-)

diff --git a/include/net/lwtunnel.h b/include/net/lwtunnel.h
index e9f116e29c22..ea3f80f58fd6 100644
--- a/include/net/lwtunnel.h
+++ b/include/net/lwtunnel.h
@@ -13,6 +13,13 @@
 /* lw tunnel state flags */
 #define LWTUNNEL_STATE_OUTPUT_REDIRECT BIT(0)
 #define LWTUNNEL_STATE_INPUT_REDIRECT  BIT(1)
+#define LWTUNNEL_STATE_XMIT_REDIRECT   BIT(2)
+
+enum {
+   LWTUNNEL_XMIT_DONE,
+   LWTUNNEL_XMIT_CONTINUE,
+};
+
 
 struct lwtunnel_state {
__u16   type;
@@ -21,6 +28,7 @@ struct lwtunnel_state {
int (*orig_output)(struct net *net, struct sock *sk, struct 
sk_buff *skb);
int (*orig_input)(struct sk_buff *);
int len;
+   __u16   headroom;
__u8data[0];
 };
 
@@ -34,6 +42,7 @@ struct lwtunnel_encap_ops {
  struct lwtunnel_state *lwtstate);
int (*get_encap_size)(struct lwtunnel_state *lwtstate);
int (*cmp_encap)(struct lwtunnel_state *a, struct lwtunnel_state *b);
+   int (*xmit)(struct sk_buff *skb);
 };
 
 #ifdef CONFIG_LWTUNNEL
@@ -75,6 +84,24 @@ static inline bool lwtunnel_input_redirect(struct 
lwtunnel_state *lwtstate)
 
return false;
 }
+
+static inline bool lwtunnel_xmit_redirect(struct lwtunnel_state *lwtstate)
+{
+   if (lwtstate && (lwtstate->flags & LWTUNNEL_STATE_XMIT_REDIRECT))
+   return true;
+
+   return false;
+}
+
+static inline unsigned int lwtunnel_headroom(struct lwtunnel_state *lwtstate,
+unsigned int mtu)
+{
+   if (lwtunnel_xmit_redirect(lwtstate) && lwtstate->headroom < mtu)
+   return lwtstate->headroom;
+
+   return 0;
+}
+
 int lwtunnel_encap_add_ops(const struct lwtunnel_encap_ops *op,
   unsigned int num);
 int lwtunnel_encap_del_ops(const struct lwtunnel_encap_ops *op,
@@ -90,6 +117,7 @@ struct lwtunnel_state *lwtunnel_state_alloc(int hdr_len);
 int lwtunnel_cmp_encap(struct lwtunnel_state *a, struct lwtunnel_state *b);
 int lwtunnel_output(struct net *net, struct sock *sk, struct sk_buff *skb);
 int lwtunnel_input(struct sk_buff *skb);
+int lwtunnel_xmit(struct sk_buff *skb);
 
 #else
 
@@ -117,6 +145,17 @@ static inline bool lwtunnel_input_redirect(struct 
lwtunnel_state *lwtstate)
return false;
 }
 
+static inline bool lwtunnel_xmit_redirect(struct lwtunnel_state *lwtstate)
+{
+   return false;
+}
+
+static inline unsigned int lwtunnel_headroom(struct lwtunnel_state *lwtstate,
+unsigned int mtu)
+{
+   return 0;
+}
+
 static inline int lwtunnel_encap_add_ops(const struct lwtunnel_encap_ops *op,
 unsigned int num)
 {
@@ -170,6 +209,11 @@ static inline int lwtunnel_input(struct sk_buff *skb)
return -EOPNOTSUPP;
 }
 
+static inline int lwtunnel_xmit(struct sk_buff *skb)
+{
+   return -EOPNOTSUPP;
+}
+
 #endif /* CONFIG_LWTUNNEL */
 
 #define MODULE_ALIAS_RTNL_LWT(encap_type) MODULE_ALIAS("rtnl-lwt-" 
__stringify(encap_type))
diff --git a/net/core/lwtunnel.c b/net/core/lwtunnel.c
index 669ecc9f884e..e5f84c26ba1a 100644
--- a/net/core/lwtunnel.c
+++ b/net/core/lwtunnel.c
@@ -251,6 +251,41 @@ int lwtunnel_output(struct net *net, struct sock *sk, 
struct sk_buff *skb)
 }
 EXPORT_SYMBOL(lwtunnel_output);
 
+int lwtunnel_xmit(struct sk_buff *skb)
+{
+   struct dst_entry *dst = skb_dst(skb);
+   const struct lwtunnel_encap_ops *ops;
+   struct lwtunnel_state *lwtstate;
+   int ret = -EINVAL;
+
+   if (!dst)
+   goto drop;
+
+   lwtstate = dst->lwtstate;
+
+   if