* [PATCH net-next 01/13] gso: Remove arbitrary checks for unsupported GSO
2016-05-11 16:47 [PATCH net-next 00/13] ipv6: Enable GUEoIPv6 and more fixes for v6 tunneling Tom Herbert
@ 2016-05-11 16:47 ` Tom Herbert
2016-05-11 16:47 ` [PATCH net-next 02/13] net: define gso types for IPx over IPv4 and IPv6 Tom Herbert
` (11 subsequent siblings)
12 siblings, 0 replies; 22+ messages in thread
From: Tom Herbert @ 2016-05-11 16:47 UTC (permalink / raw)
To: davem, netdev; +Cc: kernel-team
In several gso_segment functions there are checks of gso_type against
a seemingly arbitrary list of SKB_GSO_* flags. This seems like an
attempt to identify unsupported GSO types, but since the stack is
the one that set these GSO types in the first place this seems
unnecessary to do. If a combination isn't valid in the first
place that stack should not allow setting it.
This is a code simplication especially for add new GSO types.
Signed-off-by: Tom Herbert <tom@herbertland.com>
---
net/ipv4/af_inet.c | 18 ------------------
net/ipv4/gre_offload.c | 14 --------------
net/ipv4/tcp_offload.c | 19 -------------------
net/ipv4/udp_offload.c | 10 ----------
net/ipv6/ip6_offload.c | 18 ------------------
net/ipv6/udp_offload.c | 13 -------------
net/mpls/mpls_gso.c | 9 ---------
7 files changed, 101 deletions(-)
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 2e6e65f..7f08d45 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1205,24 +1205,6 @@ static struct sk_buff *inet_gso_segment(struct sk_buff *skb,
int ihl;
int id;
- if (unlikely(skb_shinfo(skb)->gso_type &
- ~(SKB_GSO_TCPV4 |
- SKB_GSO_UDP |
- SKB_GSO_DODGY |
- SKB_GSO_TCP_ECN |
- SKB_GSO_GRE |
- SKB_GSO_GRE_CSUM |
- SKB_GSO_IPIP |
- SKB_GSO_SIT |
- SKB_GSO_TCPV6 |
- SKB_GSO_UDP_TUNNEL |
- SKB_GSO_UDP_TUNNEL_CSUM |
- SKB_GSO_TCP_FIXEDID |
- SKB_GSO_TUNNEL_REMCSUM |
- SKB_GSO_PARTIAL |
- 0)))
- goto out;
-
skb_reset_network_header(skb);
nhoff = skb_network_header(skb) - skb_mac_header(skb);
if (unlikely(!pskb_may_pull(skb, sizeof(*iph))))
diff --git a/net/ipv4/gre_offload.c b/net/ipv4/gre_offload.c
index e88190a..ecd1e09 100644
--- a/net/ipv4/gre_offload.c
+++ b/net/ipv4/gre_offload.c
@@ -26,20 +26,6 @@ static struct sk_buff *gre_gso_segment(struct sk_buff *skb,
int gre_offset, outer_hlen;
bool need_csum, ufo;
- if (unlikely(skb_shinfo(skb)->gso_type &
- ~(SKB_GSO_TCPV4 |
- SKB_GSO_TCPV6 |
- SKB_GSO_UDP |
- SKB_GSO_DODGY |
- SKB_GSO_TCP_ECN |
- SKB_GSO_TCP_FIXEDID |
- SKB_GSO_GRE |
- SKB_GSO_GRE_CSUM |
- SKB_GSO_IPIP |
- SKB_GSO_SIT |
- SKB_GSO_PARTIAL)))
- goto out;
-
if (!skb->encapsulation)
goto out;
diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c
index 02737b6..5c59649 100644
--- a/net/ipv4/tcp_offload.c
+++ b/net/ipv4/tcp_offload.c
@@ -83,25 +83,6 @@ struct sk_buff *tcp_gso_segment(struct sk_buff *skb,
if (skb_gso_ok(skb, features | NETIF_F_GSO_ROBUST)) {
/* Packet is from an untrusted source, reset gso_segs. */
- int type = skb_shinfo(skb)->gso_type;
-
- if (unlikely(type &
- ~(SKB_GSO_TCPV4 |
- SKB_GSO_DODGY |
- SKB_GSO_TCP_ECN |
- SKB_GSO_TCP_FIXEDID |
- SKB_GSO_TCPV6 |
- SKB_GSO_GRE |
- SKB_GSO_GRE_CSUM |
- SKB_GSO_IPIP |
- SKB_GSO_SIT |
- SKB_GSO_UDP_TUNNEL |
- SKB_GSO_UDP_TUNNEL_CSUM |
- SKB_GSO_TUNNEL_REMCSUM |
- 0) ||
- !(type & (SKB_GSO_TCPV4 |
- SKB_GSO_TCPV6))))
- goto out;
skb_shinfo(skb)->gso_segs = DIV_ROUND_UP(skb->len, mss);
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index 6b7459c..81f253b 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -209,16 +209,6 @@ static struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb,
if (skb_gso_ok(skb, features | NETIF_F_GSO_ROBUST)) {
/* Packet is from an untrusted source, reset gso_segs. */
- int type = skb_shinfo(skb)->gso_type;
-
- if (unlikely(type & ~(SKB_GSO_UDP | SKB_GSO_DODGY |
- SKB_GSO_UDP_TUNNEL |
- SKB_GSO_UDP_TUNNEL_CSUM |
- SKB_GSO_TUNNEL_REMCSUM |
- SKB_GSO_IPIP |
- SKB_GSO_GRE | SKB_GSO_GRE_CSUM) ||
- !(type & (SKB_GSO_UDP))))
- goto out;
skb_shinfo(skb)->gso_segs = DIV_ROUND_UP(skb->len, mss);
diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c
index f5eb184..9ad743b 100644
--- a/net/ipv6/ip6_offload.c
+++ b/net/ipv6/ip6_offload.c
@@ -69,24 +69,6 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb,
bool encap, udpfrag;
int nhoff;
- if (unlikely(skb_shinfo(skb)->gso_type &
- ~(SKB_GSO_TCPV4 |
- SKB_GSO_UDP |
- SKB_GSO_DODGY |
- SKB_GSO_TCP_ECN |
- SKB_GSO_TCP_FIXEDID |
- SKB_GSO_TCPV6 |
- SKB_GSO_GRE |
- SKB_GSO_GRE_CSUM |
- SKB_GSO_IPIP |
- SKB_GSO_SIT |
- SKB_GSO_UDP_TUNNEL |
- SKB_GSO_UDP_TUNNEL_CSUM |
- SKB_GSO_TUNNEL_REMCSUM |
- SKB_GSO_PARTIAL |
- 0)))
- goto out;
-
skb_reset_network_header(skb);
nhoff = skb_network_header(skb) - skb_mac_header(skb);
if (unlikely(!pskb_may_pull(skb, sizeof(*ipv6h))))
diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c
index 5429f6b..ac858c4 100644
--- a/net/ipv6/udp_offload.c
+++ b/net/ipv6/udp_offload.c
@@ -36,19 +36,6 @@ static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb,
if (skb_gso_ok(skb, features | NETIF_F_GSO_ROBUST)) {
/* Packet is from an untrusted source, reset gso_segs. */
- int type = skb_shinfo(skb)->gso_type;
-
- if (unlikely(type & ~(SKB_GSO_UDP |
- SKB_GSO_DODGY |
- SKB_GSO_UDP_TUNNEL |
- SKB_GSO_UDP_TUNNEL_CSUM |
- SKB_GSO_TUNNEL_REMCSUM |
- SKB_GSO_GRE |
- SKB_GSO_GRE_CSUM |
- SKB_GSO_IPIP |
- SKB_GSO_SIT) ||
- !(type & (SKB_GSO_UDP))))
- goto out;
skb_shinfo(skb)->gso_segs = DIV_ROUND_UP(skb->len, mss);
diff --git a/net/mpls/mpls_gso.c b/net/mpls/mpls_gso.c
index bbcf604..6de1e13 100644
--- a/net/mpls/mpls_gso.c
+++ b/net/mpls/mpls_gso.c
@@ -26,15 +26,6 @@ static struct sk_buff *mpls_gso_segment(struct sk_buff *skb,
netdev_features_t mpls_features;
__be16 mpls_protocol;
- if (unlikely(skb_shinfo(skb)->gso_type &
- ~(SKB_GSO_TCPV4 |
- SKB_GSO_TCPV6 |
- SKB_GSO_UDP |
- SKB_GSO_DODGY |
- SKB_GSO_TCP_FIXEDID |
- SKB_GSO_TCP_ECN)))
- goto out;
-
/* Setup inner SKB. */
mpls_protocol = skb->protocol;
skb->protocol = skb->inner_protocol;
--
2.8.0.rc2
^ permalink raw reply related [flat|nested] 22+ messages in thread* [PATCH net-next 02/13] net: define gso types for IPx over IPv4 and IPv6
2016-05-11 16:47 [PATCH net-next 00/13] ipv6: Enable GUEoIPv6 and more fixes for v6 tunneling Tom Herbert
2016-05-11 16:47 ` [PATCH net-next 01/13] gso: Remove arbitrary checks for unsupported GSO Tom Herbert
@ 2016-05-11 16:47 ` Tom Herbert
2016-05-11 16:47 ` [PATCH net-next 03/13] fou: Call setup_udp_tunnel_sock Tom Herbert
` (10 subsequent siblings)
12 siblings, 0 replies; 22+ messages in thread
From: Tom Herbert @ 2016-05-11 16:47 UTC (permalink / raw)
To: davem, netdev; +Cc: kernel-team
This patch defines two new GSO definitions SKB_GSO_IPXIP4 and
SKB_GSO_IPXIP6 along with corresponding NETIF_F_GSO_IPXIP4 and
NETIF_F_GSO_IPXIP6. These are used to described IP in IP
tunnel and what the outer protocol is. The inner protocol
can be deduced from other GSO types (e.g. SKB_GSO_TCPV4 and
SKB_GSO_TCPV6). The GSO types of SKB_GSO_IPIP and SKB_GSO_SIT
are removed (these are both instances of SKB_GSO_IPXIP4).
SKB_GSO_IPXIP6 will be used when support for GSO with IP
encapsulation over IPv6 is added.
Signed-off-by: Tom Herbert <tom@herbertland.com>
---
drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c | 5 ++---
drivers/net/ethernet/broadcom/bnxt/bnxt.c | 4 ++--
drivers/net/ethernet/intel/i40e/i40e_main.c | 3 +--
drivers/net/ethernet/intel/i40e/i40e_txrx.c | 3 +--
drivers/net/ethernet/intel/i40evf/i40e_txrx.c | 3 +--
drivers/net/ethernet/intel/i40evf/i40evf_main.c | 3 +--
drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 3 +--
drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c | 3 +--
include/linux/netdev_features.h | 12 ++++++------
include/linux/netdevice.h | 4 ++--
include/linux/skbuff.h | 4 ++--
net/core/ethtool.c | 4 ++--
net/ipv4/af_inet.c | 2 +-
net/ipv4/ipip.c | 2 +-
net/ipv6/ip6_offload.c | 4 ++--
net/ipv6/sit.c | 4 ++--
net/netfilter/ipvs/ip_vs_xmit.c | 17 +++++++----------
17 files changed, 35 insertions(+), 45 deletions(-)
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
index d465bd7..0a5b770 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
@@ -13259,12 +13259,11 @@ static int bnx2x_init_dev(struct bnx2x *bp, struct pci_dev *pdev,
NETIF_F_RXHASH | NETIF_F_HW_VLAN_CTAG_TX;
if (!chip_is_e1x) {
dev->hw_features |= NETIF_F_GSO_GRE | NETIF_F_GSO_UDP_TUNNEL |
- NETIF_F_GSO_IPIP | NETIF_F_GSO_SIT;
+ NETIF_F_GSO_IPXIP4;
dev->hw_enc_features =
NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | NETIF_F_SG |
NETIF_F_TSO | NETIF_F_TSO_ECN | NETIF_F_TSO6 |
- NETIF_F_GSO_IPIP |
- NETIF_F_GSO_SIT |
+ NETIF_F_GSO_IPXIP4 |
NETIF_F_GSO_GRE | NETIF_F_GSO_UDP_TUNNEL;
}
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 6a5a717..85adcb0 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -6233,7 +6233,7 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
dev->hw_features = NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | NETIF_F_SG |
NETIF_F_TSO | NETIF_F_TSO6 |
NETIF_F_GSO_UDP_TUNNEL | NETIF_F_GSO_GRE |
- NETIF_F_GSO_IPIP | NETIF_F_GSO_SIT |
+ NETIF_F_GSO_IPXIP4 |
NETIF_F_GSO_UDP_TUNNEL_CSUM | NETIF_F_GSO_GRE_CSUM |
NETIF_F_GSO_PARTIAL | NETIF_F_RXHASH |
NETIF_F_RXCSUM | NETIF_F_LRO | NETIF_F_GRO;
@@ -6243,7 +6243,7 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
NETIF_F_TSO | NETIF_F_TSO6 |
NETIF_F_GSO_UDP_TUNNEL | NETIF_F_GSO_GRE |
NETIF_F_GSO_UDP_TUNNEL_CSUM | NETIF_F_GSO_GRE_CSUM |
- NETIF_F_GSO_IPIP | NETIF_F_GSO_SIT |
+ NETIF_F_GSO_IPXIP4;
NETIF_F_GSO_PARTIAL;
dev->gso_partial_features = NETIF_F_GSO_UDP_TUNNEL_CSUM |
NETIF_F_GSO_GRE_CSUM;
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 46a3a67..e4284b5 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -9082,8 +9082,7 @@ static int i40e_config_netdev(struct i40e_vsi *vsi)
NETIF_F_TSO6 |
NETIF_F_GSO_GRE |
NETIF_F_GSO_GRE_CSUM |
- NETIF_F_GSO_IPIP |
- NETIF_F_GSO_SIT |
+ NETIF_F_GSO_IPXIP4 |
NETIF_F_GSO_UDP_TUNNEL |
NETIF_F_GSO_UDP_TUNNEL_CSUM |
NETIF_F_GSO_PARTIAL |
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index b0edffe..5f3f97b 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -2284,8 +2284,7 @@ static int i40e_tso(struct sk_buff *skb, u8 *hdr_len, u64 *cd_type_cmd_tso_mss)
if (skb_shinfo(skb)->gso_type & (SKB_GSO_GRE |
SKB_GSO_GRE_CSUM |
- SKB_GSO_IPIP |
- SKB_GSO_SIT |
+ SKB_GSO_IPXIP4 |
SKB_GSO_UDP_TUNNEL |
SKB_GSO_UDP_TUNNEL_CSUM)) {
if (!(skb_shinfo(skb)->gso_type & SKB_GSO_PARTIAL) &&
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
index fd7dae46..2bbbbd0 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
@@ -1559,8 +1559,7 @@ static int i40e_tso(struct sk_buff *skb, u8 *hdr_len, u64 *cd_type_cmd_tso_mss)
if (skb_shinfo(skb)->gso_type & (SKB_GSO_GRE |
SKB_GSO_GRE_CSUM |
- SKB_GSO_IPIP |
- SKB_GSO_SIT |
+ SKB_GSO_IPXIP4 |
SKB_GSO_UDP_TUNNEL |
SKB_GSO_UDP_TUNNEL_CSUM)) {
if (!(skb_shinfo(skb)->gso_type & SKB_GSO_PARTIAL) &&
diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_main.c b/drivers/net/ethernet/intel/i40evf/i40evf_main.c
index b548dbe..32cdf28 100644
--- a/drivers/net/ethernet/intel/i40evf/i40evf_main.c
+++ b/drivers/net/ethernet/intel/i40evf/i40evf_main.c
@@ -2217,8 +2217,7 @@ int i40evf_process_config(struct i40evf_adapter *adapter)
NETIF_F_TSO6 |
NETIF_F_GSO_GRE |
NETIF_F_GSO_GRE_CSUM |
- NETIF_F_GSO_IPIP |
- NETIF_F_GSO_SIT |
+ NETIF_F_GSO_IPXIP4 |
NETIF_F_GSO_UDP_TUNNEL |
NETIF_F_GSO_UDP_TUNNEL_CSUM |
NETIF_F_GSO_PARTIAL |
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index d08fbcf..28e3b5a 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -9482,8 +9482,7 @@ skip_sriov:
#define IXGBE_GSO_PARTIAL_FEATURES (NETIF_F_GSO_GRE | \
NETIF_F_GSO_GRE_CSUM | \
- NETIF_F_GSO_IPIP | \
- NETIF_F_GSO_SIT | \
+ NETIF_F_GSO_IPXIP4 | \
NETIF_F_GSO_UDP_TUNNEL | \
NETIF_F_GSO_UDP_TUNNEL_CSUM)
diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
index 5e348b1..d86e511 100644
--- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
+++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
@@ -4062,8 +4062,7 @@ static int ixgbevf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
#define IXGBEVF_GSO_PARTIAL_FEATURES (NETIF_F_GSO_GRE | \
NETIF_F_GSO_GRE_CSUM | \
- NETIF_F_GSO_IPIP | \
- NETIF_F_GSO_SIT | \
+ NETIF_F_GSO_IPXIP4 | \
NETIF_F_GSO_UDP_TUNNEL | \
NETIF_F_GSO_UDP_TUNNEL_CSUM)
diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h
index bc87362..aa7b240 100644
--- a/include/linux/netdev_features.h
+++ b/include/linux/netdev_features.h
@@ -44,8 +44,8 @@ enum {
NETIF_F_FSO_BIT, /* ... FCoE segmentation */
NETIF_F_GSO_GRE_BIT, /* ... GRE with TSO */
NETIF_F_GSO_GRE_CSUM_BIT, /* ... GRE with csum with TSO */
- NETIF_F_GSO_IPIP_BIT, /* ... IPIP tunnel with TSO */
- NETIF_F_GSO_SIT_BIT, /* ... SIT tunnel with TSO */
+ NETIF_F_GSO_IPXIP4_BIT, /* ... IP4 or IP6 over IP4 with TSO */
+ NETIF_F_GSO_IPXIP6_BIT, /* ... IP4 or IP6 over IP6 with TSO */
NETIF_F_GSO_UDP_TUNNEL_BIT, /* ... UDP TUNNEL with TSO */
NETIF_F_GSO_UDP_TUNNEL_CSUM_BIT,/* ... UDP TUNNEL with TSO & CSUM */
NETIF_F_GSO_PARTIAL_BIT, /* ... Only segment inner-most L4
@@ -121,8 +121,8 @@ enum {
#define NETIF_F_RXALL __NETIF_F(RXALL)
#define NETIF_F_GSO_GRE __NETIF_F(GSO_GRE)
#define NETIF_F_GSO_GRE_CSUM __NETIF_F(GSO_GRE_CSUM)
-#define NETIF_F_GSO_IPIP __NETIF_F(GSO_IPIP)
-#define NETIF_F_GSO_SIT __NETIF_F(GSO_SIT)
+#define NETIF_F_GSO_IPXIP4 __NETIF_F(GSO_IPXIP4)
+#define NETIF_F_GSO_IPXIP6 __NETIF_F(GSO_IPXIP6)
#define NETIF_F_GSO_UDP_TUNNEL __NETIF_F(GSO_UDP_TUNNEL)
#define NETIF_F_GSO_UDP_TUNNEL_CSUM __NETIF_F(GSO_UDP_TUNNEL_CSUM)
#define NETIF_F_TSO_MANGLEID __NETIF_F(TSO_MANGLEID)
@@ -200,8 +200,8 @@ enum {
#define NETIF_F_GSO_ENCAP_ALL (NETIF_F_GSO_GRE | \
NETIF_F_GSO_GRE_CSUM | \
- NETIF_F_GSO_IPIP | \
- NETIF_F_GSO_SIT | \
+ NETIF_F_GSO_IPXIP4 | \
+ NETIF_F_GSO_IPXIP6 | \
NETIF_F_GSO_UDP_TUNNEL | \
NETIF_F_GSO_UDP_TUNNEL_CSUM)
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 63580e6..8b1eedc 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -4005,8 +4005,8 @@ static inline bool net_gso_ok(netdev_features_t features, int gso_type)
BUILD_BUG_ON(SKB_GSO_FCOE != (NETIF_F_FSO >> NETIF_F_GSO_SHIFT));
BUILD_BUG_ON(SKB_GSO_GRE != (NETIF_F_GSO_GRE >> NETIF_F_GSO_SHIFT));
BUILD_BUG_ON(SKB_GSO_GRE_CSUM != (NETIF_F_GSO_GRE_CSUM >> NETIF_F_GSO_SHIFT));
- BUILD_BUG_ON(SKB_GSO_IPIP != (NETIF_F_GSO_IPIP >> NETIF_F_GSO_SHIFT));
- BUILD_BUG_ON(SKB_GSO_SIT != (NETIF_F_GSO_SIT >> NETIF_F_GSO_SHIFT));
+ BUILD_BUG_ON(SKB_GSO_IPXIP4 != (NETIF_F_GSO_IPXIP4 >> NETIF_F_GSO_SHIFT));
+ BUILD_BUG_ON(SKB_GSO_IPXIP6 != (NETIF_F_GSO_IPXIP6 >> NETIF_F_GSO_SHIFT));
BUILD_BUG_ON(SKB_GSO_UDP_TUNNEL != (NETIF_F_GSO_UDP_TUNNEL >> NETIF_F_GSO_SHIFT));
BUILD_BUG_ON(SKB_GSO_UDP_TUNNEL_CSUM != (NETIF_F_GSO_UDP_TUNNEL_CSUM >> NETIF_F_GSO_SHIFT));
BUILD_BUG_ON(SKB_GSO_PARTIAL != (NETIF_F_GSO_PARTIAL >> NETIF_F_GSO_SHIFT));
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index c413c58..65968a9 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -471,9 +471,9 @@ enum {
SKB_GSO_GRE_CSUM = 1 << 8,
- SKB_GSO_IPIP = 1 << 9,
+ SKB_GSO_IPXIP4 = 1 << 9,
- SKB_GSO_SIT = 1 << 10,
+ SKB_GSO_IPXIP6 = 1 << 10,
SKB_GSO_UDP_TUNNEL = 1 << 11,
diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index bdb4013..f403481 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -84,8 +84,8 @@ static const char netdev_features_strings[NETDEV_FEATURE_COUNT][ETH_GSTRING_LEN]
[NETIF_F_FSO_BIT] = "tx-fcoe-segmentation",
[NETIF_F_GSO_GRE_BIT] = "tx-gre-segmentation",
[NETIF_F_GSO_GRE_CSUM_BIT] = "tx-gre-csum-segmentation",
- [NETIF_F_GSO_IPIP_BIT] = "tx-ipip-segmentation",
- [NETIF_F_GSO_SIT_BIT] = "tx-sit-segmentation",
+ [NETIF_F_GSO_IPXIP4_BIT] = "tx-ipxip4-segmentation",
+ [NETIF_F_GSO_IPXIP6_BIT] = "tx-ipxip6-segmentation",
[NETIF_F_GSO_UDP_TUNNEL_BIT] = "tx-udp_tnl-segmentation",
[NETIF_F_GSO_UDP_TUNNEL_CSUM_BIT] = "tx-udp_tnl-csum-segmentation",
[NETIF_F_GSO_PARTIAL_BIT] = "tx-gso-partial",
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 7f08d45..25040b1 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1483,7 +1483,7 @@ out_unlock:
static int ipip_gro_complete(struct sk_buff *skb, int nhoff)
{
skb->encapsulation = 1;
- skb_shinfo(skb)->gso_type |= SKB_GSO_IPIP;
+ skb_shinfo(skb)->gso_type |= SKB_GSO_IPXIP4;
return inet_gro_complete(skb, nhoff);
}
diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c
index 9282748..9783701 100644
--- a/net/ipv4/ipip.c
+++ b/net/ipv4/ipip.c
@@ -219,7 +219,7 @@ static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
if (unlikely(skb->protocol != htons(ETH_P_IP)))
goto tx_error;
- if (iptunnel_handle_offloads(skb, SKB_GSO_IPIP))
+ if (iptunnel_handle_offloads(skb, SKB_GSO_IPXIP4))
goto tx_error;
skb_set_inner_ipproto(skb, IPPROTO_IPIP);
diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c
index 9ad743b..787e55f 100644
--- a/net/ipv6/ip6_offload.c
+++ b/net/ipv6/ip6_offload.c
@@ -86,7 +86,7 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb,
proto = ipv6_gso_pull_exthdrs(skb, ipv6h->nexthdr);
if (skb->encapsulation &&
- skb_shinfo(skb)->gso_type & (SKB_GSO_SIT|SKB_GSO_IPIP))
+ skb_shinfo(skb)->gso_type & (SKB_GSO_IPXIP4 | SKB_GSO_IPXIP6))
udpfrag = proto == IPPROTO_UDP && encap;
else
udpfrag = proto == IPPROTO_UDP && !skb->encapsulation;
@@ -294,7 +294,7 @@ out_unlock:
static int sit_gro_complete(struct sk_buff *skb, int nhoff)
{
skb->encapsulation = 1;
- skb_shinfo(skb)->gso_type |= SKB_GSO_SIT;
+ skb_shinfo(skb)->gso_type |= SKB_GSO_IPXIP4;
return ipv6_gro_complete(skb, nhoff);
}
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index a13d8c1..0a5a255 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -913,7 +913,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb,
goto tx_error;
}
- if (iptunnel_handle_offloads(skb, SKB_GSO_SIT)) {
+ if (iptunnel_handle_offloads(skb, SKB_GSO_IPXIP4)) {
ip_rt_put(rt);
goto tx_error;
}
@@ -1000,7 +1000,7 @@ static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
struct ip_tunnel *tunnel = netdev_priv(dev);
const struct iphdr *tiph = &tunnel->parms.iph;
- if (iptunnel_handle_offloads(skb, SKB_GSO_IPIP))
+ if (iptunnel_handle_offloads(skb, SKB_GSO_IPXIP4))
goto tx_error;
skb_set_inner_ipproto(skb, IPPROTO_IPIP);
diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c
index 6d19d2e..01d3d89 100644
--- a/net/netfilter/ipvs/ip_vs_xmit.c
+++ b/net/netfilter/ipvs/ip_vs_xmit.c
@@ -932,17 +932,14 @@ error:
static inline int __tun_gso_type_mask(int encaps_af, int orig_af)
{
- if (encaps_af == AF_INET) {
- if (orig_af == AF_INET)
- return SKB_GSO_IPIP;
-
- return SKB_GSO_SIT;
+ switch (encaps_af) {
+ case AF_INET:
+ return SKB_GSO_IPXIP4;
+ case AF_INET6:
+ return SKB_GSO_IPXIP6;
+ default:
+ return 0;
}
-
- /* GSO: we need to provide proper SKB_GSO_ value for IPv6:
- * SKB_GSO_SIT/IPV6
- */
- return 0;
}
/*
--
2.8.0.rc2
^ permalink raw reply related [flat|nested] 22+ messages in thread* [PATCH net-next 03/13] fou: Call setup_udp_tunnel_sock
2016-05-11 16:47 [PATCH net-next 00/13] ipv6: Enable GUEoIPv6 and more fixes for v6 tunneling Tom Herbert
2016-05-11 16:47 ` [PATCH net-next 01/13] gso: Remove arbitrary checks for unsupported GSO Tom Herbert
2016-05-11 16:47 ` [PATCH net-next 02/13] net: define gso types for IPx over IPv4 and IPv6 Tom Herbert
@ 2016-05-11 16:47 ` Tom Herbert
2016-05-11 16:47 ` [PATCH net-next 04/13] fou: Split out {fou,gue}_build_header Tom Herbert
` (9 subsequent siblings)
12 siblings, 0 replies; 22+ messages in thread
From: Tom Herbert @ 2016-05-11 16:47 UTC (permalink / raw)
To: davem, netdev; +Cc: kernel-team
Use helper function to set up UDP tunnel related information for a fou
socket.
Signed-off-by: Tom Herbert <tom@herbertland.com>
---
net/ipv4/fou.c | 50 ++++++++++++++++----------------------------------
1 file changed, 16 insertions(+), 34 deletions(-)
diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c
index eeec7d6..6cbc725 100644
--- a/net/ipv4/fou.c
+++ b/net/ipv4/fou.c
@@ -448,31 +448,13 @@ static void fou_release(struct fou *fou)
kfree_rcu(fou, rcu);
}
-static int fou_encap_init(struct sock *sk, struct fou *fou, struct fou_cfg *cfg)
-{
- udp_sk(sk)->encap_rcv = fou_udp_recv;
- udp_sk(sk)->gro_receive = fou_gro_receive;
- udp_sk(sk)->gro_complete = fou_gro_complete;
- fou_from_sock(sk)->protocol = cfg->protocol;
-
- return 0;
-}
-
-static int gue_encap_init(struct sock *sk, struct fou *fou, struct fou_cfg *cfg)
-{
- udp_sk(sk)->encap_rcv = gue_udp_recv;
- udp_sk(sk)->gro_receive = gue_gro_receive;
- udp_sk(sk)->gro_complete = gue_gro_complete;
-
- return 0;
-}
-
static int fou_create(struct net *net, struct fou_cfg *cfg,
struct socket **sockp)
{
struct socket *sock = NULL;
struct fou *fou = NULL;
struct sock *sk;
+ struct udp_tunnel_sock_cfg tunnel_cfg;
int err;
/* Open UDP socket */
@@ -491,33 +473,33 @@ static int fou_create(struct net *net, struct fou_cfg *cfg,
fou->flags = cfg->flags;
fou->port = cfg->udp_config.local_udp_port;
+ fou->type = cfg->type;
+ fou->sock = sock;
+
+ memset(&tunnel_cfg, 0, sizeof(tunnel_cfg));
+ tunnel_cfg.encap_type = 1;
+ tunnel_cfg.sk_user_data = fou;
+ tunnel_cfg.encap_destroy = NULL;
/* Initial for fou type */
switch (cfg->type) {
case FOU_ENCAP_DIRECT:
- err = fou_encap_init(sk, fou, cfg);
- if (err)
- goto error;
+ tunnel_cfg.encap_rcv = fou_udp_recv;
+ tunnel_cfg.gro_receive = fou_gro_receive;
+ tunnel_cfg.gro_complete = fou_gro_complete;
+ fou->protocol = cfg->protocol;
break;
case FOU_ENCAP_GUE:
- err = gue_encap_init(sk, fou, cfg);
- if (err)
- goto error;
+ tunnel_cfg.encap_rcv = gue_udp_recv;
+ tunnel_cfg.gro_receive = gue_gro_receive;
+ tunnel_cfg.gro_complete = gue_gro_complete;
break;
default:
err = -EINVAL;
goto error;
}
- fou->type = cfg->type;
-
- udp_sk(sk)->encap_type = 1;
- udp_encap_enable();
-
- sk->sk_user_data = fou;
- fou->sock = sock;
-
- inet_inc_convert_csum(sk);
+ setup_udp_tunnel_sock(net, sock, &tunnel_cfg);
sk->sk_allocation = GFP_ATOMIC;
--
2.8.0.rc2
^ permalink raw reply related [flat|nested] 22+ messages in thread* [PATCH net-next 04/13] fou: Split out {fou,gue}_build_header
2016-05-11 16:47 [PATCH net-next 00/13] ipv6: Enable GUEoIPv6 and more fixes for v6 tunneling Tom Herbert
` (2 preceding siblings ...)
2016-05-11 16:47 ` [PATCH net-next 03/13] fou: Call setup_udp_tunnel_sock Tom Herbert
@ 2016-05-11 16:47 ` Tom Herbert
2016-05-12 18:55 ` Shmulik Ladkani
2016-05-11 16:47 ` [PATCH net-next 05/13] fou: Add encap ops for IPv6 tunnels Tom Herbert
` (8 subsequent siblings)
12 siblings, 1 reply; 22+ messages in thread
From: Tom Herbert @ 2016-05-11 16:47 UTC (permalink / raw)
To: davem, netdev; +Cc: kernel-team
Create __fou_build_header and __gue_build_header. These implement the
protocol generic parts of building the fou and gue header.
fou_build_header and gue_build_header implement the IPv4 specific
functions and call the __*_build_header functions.
Signed-off-by: Tom Herbert <tom@herbertland.com>
---
include/net/fou.h | 8 ++++----
net/ipv4/fou.c | 47 +++++++++++++++++++++++++++++++++++++----------
2 files changed, 41 insertions(+), 14 deletions(-)
diff --git a/include/net/fou.h b/include/net/fou.h
index 19b8a0c..7d2fda2 100644
--- a/include/net/fou.h
+++ b/include/net/fou.h
@@ -11,9 +11,9 @@
size_t fou_encap_hlen(struct ip_tunnel_encap *e);
static size_t gue_encap_hlen(struct ip_tunnel_encap *e);
-int fou_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e,
- u8 *protocol, struct flowi4 *fl4);
-int gue_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e,
- u8 *protocol, struct flowi4 *fl4);
+int __fou_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e,
+ u8 *protocol, __be16 *sport, int type);
+int __gue_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e,
+ u8 *protocol, __be16 *sport, int type);
#endif
diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c
index 6cbc725..f4f2ddd 100644
--- a/net/ipv4/fou.c
+++ b/net/ipv4/fou.c
@@ -780,6 +780,22 @@ static void fou_build_udp(struct sk_buff *skb, struct ip_tunnel_encap *e,
*protocol = IPPROTO_UDP;
}
+int __fou_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e,
+ u8 *protocol, __be16 *sport, int type)
+{
+ int err;
+
+ err = iptunnel_handle_offloads(skb, type);
+ if (err)
+ return err;
+
+ *sport = e->sport ? : udp_flow_src_port(dev_net(skb->dev),
+ skb, 0, 0, false);
+
+ return 0;
+}
+EXPORT_SYMBOL(__fou_build_header);
+
int fou_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e,
u8 *protocol, struct flowi4 *fl4)
{
@@ -788,26 +804,21 @@ int fou_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e,
__be16 sport;
int err;
- err = iptunnel_handle_offloads(skb, type);
+ err = __fou_build_header(skb, e, protocol, &sport, type);
if (err)
return err;
- sport = e->sport ? : udp_flow_src_port(dev_net(skb->dev),
- skb, 0, 0, false);
fou_build_udp(skb, e, fl4, protocol, sport);
return 0;
}
EXPORT_SYMBOL(fou_build_header);
-int gue_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e,
- u8 *protocol, struct flowi4 *fl4)
+int __gue_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e,
+ u8 *protocol, __be16 *sport, int type)
{
- int type = e->flags & TUNNEL_ENCAP_FLAG_CSUM ? SKB_GSO_UDP_TUNNEL_CSUM :
- SKB_GSO_UDP_TUNNEL;
struct guehdr *guehdr;
size_t hdrlen, optlen = 0;
- __be16 sport;
void *data;
bool need_priv = false;
int err;
@@ -826,8 +837,8 @@ int gue_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e,
return err;
/* Get source port (based on flow hash) before skb_push */
- sport = e->sport ? : udp_flow_src_port(dev_net(skb->dev),
- skb, 0, 0, false);
+ *sport = e->sport ? : udp_flow_src_port(dev_net(skb->dev),
+ skb, 0, 0, false);
hdrlen = sizeof(struct guehdr) + optlen;
@@ -872,6 +883,22 @@ int gue_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e,
}
+ return 0;
+}
+EXPORT_SYMBOL(__gue_build_header);
+
+int gue_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e,
+ u8 *protocol, struct flowi4 *fl4)
+{
+ int type = e->flags & TUNNEL_ENCAP_FLAG_CSUM ? SKB_GSO_UDP_TUNNEL_CSUM :
+ SKB_GSO_UDP_TUNNEL;
+ __be16 sport;
+ int err;
+
+ err = __gue_build_header(skb, e, protocol, &sport, type);
+ if (err)
+ return err;
+
fou_build_udp(skb, e, fl4, protocol, sport);
return 0;
--
2.8.0.rc2
^ permalink raw reply related [flat|nested] 22+ messages in thread* Re: [PATCH net-next 04/13] fou: Split out {fou,gue}_build_header
2016-05-11 16:47 ` [PATCH net-next 04/13] fou: Split out {fou,gue}_build_header Tom Herbert
@ 2016-05-12 18:55 ` Shmulik Ladkani
0 siblings, 0 replies; 22+ messages in thread
From: Shmulik Ladkani @ 2016-05-12 18:55 UTC (permalink / raw)
To: Tom Herbert; +Cc: davem, netdev, kernel-team
Hi Tom,
On Wed, 11 May 2016 09:47:24 -0700 Tom Herbert <tom@herbertland.com> wrote:
>
> -int fou_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e,
> - u8 *protocol, struct flowi4 *fl4);
> -int gue_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e,
> - u8 *protocol, struct flowi4 *fl4);
> +int __fou_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e,
> + u8 *protocol, __be16 *sport, int type);
> +int __gue_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e,
> + u8 *protocol, __be16 *sport, int type);
[snip]
> +EXPORT_SYMBOL(__fou_build_header);
> +
> int fou_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e,
> u8 *protocol, struct flowi4 *fl4)
Assuming 'fou_build_header' is no longer part of the interface, why
not kill the existing EXPORT_SYMBOL(fou_build_header) and make it
static?
Same for 'gue_build_header'.
Regards,
Shmulik
^ permalink raw reply [flat|nested] 22+ messages in thread
* [PATCH net-next 05/13] fou: Add encap ops for IPv6 tunnels
2016-05-11 16:47 [PATCH net-next 00/13] ipv6: Enable GUEoIPv6 and more fixes for v6 tunneling Tom Herbert
` (3 preceding siblings ...)
2016-05-11 16:47 ` [PATCH net-next 04/13] fou: Split out {fou,gue}_build_header Tom Herbert
@ 2016-05-11 16:47 ` Tom Herbert
2016-05-12 19:26 ` Shmulik Ladkani
2016-05-11 16:47 ` [PATCH net-next 06/13] ipv6: Fix nexthdr for reinjection Tom Herbert
` (7 subsequent siblings)
12 siblings, 1 reply; 22+ messages in thread
From: Tom Herbert @ 2016-05-11 16:47 UTC (permalink / raw)
To: davem, netdev; +Cc: kernel-team
This patch adds IP tunnel encapsulation operations for IPv6. This
includes the infrastructure to add and delete operations. IPv6 variants
of fou6_build_header and gue6_build_header are added in a new
fou6 module. These encapsulation operations for fou and gue are
automatically added when the fou6 module loads.
Signed-off-by: Tom Herbert <tom@herbertland.com>
---
include/net/fou.h | 2 +-
include/net/ip6_tunnel.h | 14 +++++
net/ipv6/Makefile | 4 +-
net/ipv6/fou6.c | 140 +++++++++++++++++++++++++++++++++++++++++++++
net/ipv6/ip6_tunnel_core.c | 44 ++++++++++++++
5 files changed, 202 insertions(+), 2 deletions(-)
create mode 100644 net/ipv6/fou6.c
create mode 100644 net/ipv6/ip6_tunnel_core.c
diff --git a/include/net/fou.h b/include/net/fou.h
index 7d2fda2..f5cc691 100644
--- a/include/net/fou.h
+++ b/include/net/fou.h
@@ -9,7 +9,7 @@
#include <net/udp.h>
size_t fou_encap_hlen(struct ip_tunnel_encap *e);
-static size_t gue_encap_hlen(struct ip_tunnel_encap *e);
+size_t gue_encap_hlen(struct ip_tunnel_encap *e);
int __fou_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e,
u8 *protocol, __be16 *sport, int type);
diff --git a/include/net/ip6_tunnel.h b/include/net/ip6_tunnel.h
index fb9e015..1c14c27 100644
--- a/include/net/ip6_tunnel.h
+++ b/include/net/ip6_tunnel.h
@@ -34,6 +34,20 @@ struct __ip6_tnl_parm {
__be32 o_key;
};
+struct ip6_tnl_encap_ops {
+ size_t (*encap_hlen)(struct ip_tunnel_encap *e);
+ int (*build_header)(struct sk_buff *skb, struct ip_tunnel_encap *e,
+ u8 *protocol, struct flowi6 *fl6);
+};
+
+extern const struct ip6_tnl_encap_ops __rcu *
+ ip6tun_encaps[MAX_IPTUN_ENCAP_OPS];
+
+int ip6_tnl_encap_add_ops(const struct ip6_tnl_encap_ops *op,
+ unsigned int num);
+int ip6_tnl_encap_del_ops(const struct ip6_tnl_encap_ops *op,
+ unsigned int num);
+
/* IPv6 tunnel */
struct ip6_tnl {
struct ip6_tnl __rcu *next; /* next tunnel in list */
diff --git a/net/ipv6/Makefile b/net/ipv6/Makefile
index 5e9d6bf..5cf4a1f 100644
--- a/net/ipv6/Makefile
+++ b/net/ipv6/Makefile
@@ -9,7 +9,7 @@ ipv6-objs := af_inet6.o anycast.o ip6_output.o ip6_input.o addrconf.o \
route.o ip6_fib.o ipv6_sockglue.o ndisc.o udp.o udplite.o \
raw.o icmp.o mcast.o reassembly.o tcp_ipv6.o ping.o \
exthdrs.o datagram.o ip6_flowlabel.o inet6_connection_sock.o \
- udp_offload.o
+ udp_offload.o ip6_tunnel_core.o
ipv6-offload := ip6_offload.o tcpv6_offload.o exthdrs_offload.o
@@ -43,6 +43,8 @@ obj-$(CONFIG_IPV6_SIT) += sit.o
obj-$(CONFIG_IPV6_TUNNEL) += ip6_tunnel.o
obj-$(CONFIG_IPV6_GRE) += ip6_gre.o
+obj-$(CONFIG_NET_FOU) += fou6.o
+
obj-y += addrconf_core.o exthdrs_core.o ip6_checksum.o ip6_icmp.o
obj-$(CONFIG_INET) += output_core.o protocol.o $(ipv6-offload)
diff --git a/net/ipv6/fou6.c b/net/ipv6/fou6.c
new file mode 100644
index 0000000..c972d0b
--- /dev/null
+++ b/net/ipv6/fou6.c
@@ -0,0 +1,140 @@
+#include <linux/module.h>
+#include <linux/errno.h>
+#include <linux/socket.h>
+#include <linux/skbuff.h>
+#include <linux/ip.h>
+#include <linux/udp.h>
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <net/fou.h>
+#include <net/ip.h>
+#include <net/ip6_tunnel.h>
+#include <net/ip6_checksum.h>
+#include <net/protocol.h>
+#include <net/udp.h>
+#include <net/udp_tunnel.h>
+
+static void fou6_build_udp(struct sk_buff *skb, struct ip_tunnel_encap *e,
+ struct flowi6 *fl6, u8 *protocol, __be16 sport)
+{
+ struct udphdr *uh;
+
+ skb_push(skb, sizeof(struct udphdr));
+ skb_reset_transport_header(skb);
+
+ uh = udp_hdr(skb);
+
+ uh->dest = e->dport;
+ uh->source = sport;
+ uh->len = htons(skb->len);
+ udp6_set_csum(!(e->flags & TUNNEL_ENCAP_FLAG_CSUM6), skb,
+ &fl6->saddr, &fl6->daddr, skb->len);
+
+ *protocol = IPPROTO_UDP;
+}
+
+int fou6_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e,
+ u8 *protocol, struct flowi6 *fl6)
+{
+ __be16 sport;
+ int err;
+ int type = e->flags & TUNNEL_ENCAP_FLAG_CSUM6 ?
+ SKB_GSO_UDP_TUNNEL_CSUM : SKB_GSO_UDP_TUNNEL;
+
+ err = __fou_build_header(skb, e, protocol, &sport, type);
+ if (err)
+ return err;
+
+ fou6_build_udp(skb, e, fl6, protocol, sport);
+
+ return 0;
+}
+EXPORT_SYMBOL(fou6_build_header);
+
+int gue6_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e,
+ u8 *protocol, struct flowi6 *fl6)
+{
+ __be16 sport;
+ int err;
+ int type = e->flags & TUNNEL_ENCAP_FLAG_CSUM6 ?
+ SKB_GSO_UDP_TUNNEL_CSUM : SKB_GSO_UDP_TUNNEL;
+
+ err = __gue_build_header(skb, e, protocol, &sport, type);
+ if (err)
+ return err;
+
+ fou6_build_udp(skb, e, fl6, protocol, sport);
+
+ return 0;
+}
+EXPORT_SYMBOL(gue6_build_header);
+
+#ifdef CONFIG_NET_FOU_IP_TUNNELS
+
+static const struct ip6_tnl_encap_ops fou_ip6tun_ops = {
+ .encap_hlen = fou_encap_hlen,
+ .build_header = fou6_build_header,
+};
+
+static const struct ip6_tnl_encap_ops gue_ip6tun_ops = {
+ .encap_hlen = gue_encap_hlen,
+ .build_header = gue6_build_header,
+};
+
+static int ip6_tnl_encap_add_fou_ops(void)
+{
+ int ret;
+
+ ret = ip6_tnl_encap_add_ops(&fou_ip6tun_ops, TUNNEL_ENCAP_FOU);
+ if (ret < 0) {
+ pr_err("can't add fou6 ops\n");
+ return ret;
+ }
+
+ ret = ip6_tnl_encap_add_ops(&gue_ip6tun_ops, TUNNEL_ENCAP_GUE);
+ if (ret < 0) {
+ pr_err("can't add gue6 ops\n");
+ ip6_tnl_encap_del_ops(&fou_ip6tun_ops, TUNNEL_ENCAP_FOU);
+ return ret;
+ }
+
+ return 0;
+}
+
+static void ip6_tnl_encap_del_fou_ops(void)
+{
+ ip6_tnl_encap_del_ops(&fou_ip6tun_ops, TUNNEL_ENCAP_FOU);
+ ip6_tnl_encap_del_ops(&gue_ip6tun_ops, TUNNEL_ENCAP_GUE);
+}
+
+#else
+
+static int ip6_tnl_encap_add_fou_ops(void)
+{
+ return 0;
+}
+
+static void ip6_tnl_encap_del_fou_ops(void)
+{
+}
+
+#endif
+
+static int __init fou6_init(void)
+{
+ int ret;
+
+ ret = ip6_tnl_encap_add_fou_ops();
+
+ return ret;
+}
+
+static void __exit fou6_fini(void)
+{
+ ip6_tnl_encap_del_fou_ops();
+}
+
+module_init(fou6_init);
+module_exit(fou6_fini);
+MODULE_AUTHOR("Tom Herbert <therbert@google.com>");
+MODULE_LICENSE("GPL");
diff --git a/net/ipv6/ip6_tunnel_core.c b/net/ipv6/ip6_tunnel_core.c
new file mode 100644
index 0000000..5f5b79e
--- /dev/null
+++ b/net/ipv6/ip6_tunnel_core.c
@@ -0,0 +1,44 @@
+#include <linux/module.h>
+#include <linux/errno.h>
+#include <linux/types.h>
+#include <linux/if.h>
+#include <linux/in.h>
+#include <linux/ip.h>
+#include <linux/net.h>
+#include <linux/in6.h>
+#include <net/ip6_tunnel.h>
+
+const struct ip6_tnl_encap_ops __rcu *
+ ip6tun_encaps[MAX_IPTUN_ENCAP_OPS] __read_mostly;
+EXPORT_SYMBOL(ip6tun_encaps);
+
+int ip6_tnl_encap_add_ops(const struct ip6_tnl_encap_ops *ops,
+ unsigned int num)
+{
+ if (num >= MAX_IPTUN_ENCAP_OPS)
+ return -ERANGE;
+
+ return !cmpxchg((const struct ip6_tnl_encap_ops **)
+ &ip6tun_encaps[num],
+ NULL, ops) ? 0 : -1;
+}
+EXPORT_SYMBOL(ip6_tnl_encap_add_ops);
+
+int ip6_tnl_encap_del_ops(const struct ip6_tnl_encap_ops *ops,
+ unsigned int num)
+{
+ int ret;
+
+ if (num >= MAX_IPTUN_ENCAP_OPS)
+ return -ERANGE;
+
+ ret = (cmpxchg((const struct ip6_tnl_encap_ops **)
+ &ip6tun_encaps[num],
+ ops, NULL) == ops) ? 0 : -1;
+
+ synchronize_net();
+
+ return ret;
+}
+EXPORT_SYMBOL(ip6_tnl_encap_del_ops);
+
--
2.8.0.rc2
^ permalink raw reply related [flat|nested] 22+ messages in thread* Re: [PATCH net-next 05/13] fou: Add encap ops for IPv6 tunnels
2016-05-11 16:47 ` [PATCH net-next 05/13] fou: Add encap ops for IPv6 tunnels Tom Herbert
@ 2016-05-12 19:26 ` Shmulik Ladkani
0 siblings, 0 replies; 22+ messages in thread
From: Shmulik Ladkani @ 2016-05-12 19:26 UTC (permalink / raw)
To: Tom Herbert; +Cc: davem, netdev, kernel-team
Hi,
On Wed, 11 May 2016 09:47:25 -0700 Tom Herbert <tom@herbertland.com> wrote:
> This patch adds IP tunnel encapsulation operations for IPv6. This
> includes the infrastructure to add and delete operations. IPv6 variants
> of fou6_build_header and gue6_build_header are added in a new
> fou6 module. These encapsulation operations for fou and gue are
> automatically added when the fou6 module loads.
One small nit:
> +EXPORT_SYMBOL(fou6_build_header);
[snip]
> +EXPORT_SYMBOL(gue6_build_header);
As with previous patch, seems these needn't be exported. Am I missing
something here?
Reviewed-by: Shmulik Ladkani <shmulik.ladkani@gmail.com>
Regards,
Shmulik
^ permalink raw reply [flat|nested] 22+ messages in thread
* [PATCH net-next 06/13] ipv6: Fix nexthdr for reinjection
2016-05-11 16:47 [PATCH net-next 00/13] ipv6: Enable GUEoIPv6 and more fixes for v6 tunneling Tom Herbert
` (4 preceding siblings ...)
2016-05-11 16:47 ` [PATCH net-next 05/13] fou: Add encap ops for IPv6 tunnels Tom Herbert
@ 2016-05-11 16:47 ` Tom Herbert
2016-05-12 20:23 ` Shmulik Ladkani
2016-05-11 16:47 ` [PATCH net-next 07/13] ipv6: Change "final" protocol processing for encapsulation Tom Herbert
` (6 subsequent siblings)
12 siblings, 1 reply; 22+ messages in thread
From: Tom Herbert @ 2016-05-11 16:47 UTC (permalink / raw)
To: davem, netdev; +Cc: kernel-team
In ip6_input_finish the protocol handle returns a value greater than
zero the packet needs to be resubmitted using the returned protocol.
The returned protocol is being ignored and each time through resubmit
nexthdr is taken from an offest in the packet. This patch fixes that
so that nexthdr is taken from return value of the protocol handler.
Signed-off-by: Tom Herbert <tom@herbertland.com>
---
net/ipv6/ip6_input.c | 9 ++++++---
1 file changed, 6 insertions(+), 3 deletions(-)
diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c
index 6ed5601..2a0258a 100644
--- a/net/ipv6/ip6_input.c
+++ b/net/ipv6/ip6_input.c
@@ -222,13 +222,14 @@ static int ip6_input_finish(struct net *net, struct sock *sk, struct sk_buff *sk
*/
rcu_read_lock();
-resubmit:
+
idev = ip6_dst_idev(skb_dst(skb));
if (!pskb_pull(skb, skb_transport_offset(skb)))
goto discard;
nhoff = IP6CB(skb)->nhoff;
nexthdr = skb_network_header(skb)[nhoff];
+resubmit:
raw = raw6_local_deliver(skb, nexthdr);
ipprot = rcu_dereference(inet6_protos[nexthdr]);
if (ipprot) {
@@ -256,10 +257,12 @@ resubmit:
goto discard;
ret = ipprot->handler(skb);
- if (ret > 0)
+ if (ret > 0) {
+ nexthdr = ret;
goto resubmit;
- else if (ret == 0)
+ } else if (ret == 0) {
__IP6_INC_STATS(net, idev, IPSTATS_MIB_INDELIVERS);
+ }
} else {
if (!raw) {
if (xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) {
--
2.8.0.rc2
^ permalink raw reply related [flat|nested] 22+ messages in thread* Re: [PATCH net-next 06/13] ipv6: Fix nexthdr for reinjection
2016-05-11 16:47 ` [PATCH net-next 06/13] ipv6: Fix nexthdr for reinjection Tom Herbert
@ 2016-05-12 20:23 ` Shmulik Ladkani
2016-05-12 21:45 ` Tom Herbert
0 siblings, 1 reply; 22+ messages in thread
From: Shmulik Ladkani @ 2016-05-12 20:23 UTC (permalink / raw)
To: Tom Herbert; +Cc: davem, netdev, kernel-team
Hi Tom,
On Wed, 11 May 2016 09:47:26 -0700 Tom Herbert <tom@herbertland.com> wrote:
> In ip6_input_finish the protocol handle returns a value greater than
> zero the packet needs to be resubmitted using the returned protocol.
> The returned protocol is being ignored and each time through resubmit
> nexthdr is taken from an offest in the packet. This patch fixes that
> so that nexthdr is taken from return value of the protocol handler.
>
> Signed-off-by: Tom Herbert <tom@herbertland.com>
> ---
> net/ipv6/ip6_input.c | 9 ++++++---
> 1 file changed, 6 insertions(+), 3 deletions(-)
>
> diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c
> index 6ed5601..2a0258a 100644
> --- a/net/ipv6/ip6_input.c
> +++ b/net/ipv6/ip6_input.c
> @@ -222,13 +222,14 @@ static int ip6_input_finish(struct net *net, struct sock *sk, struct sk_buff *sk
> */
>
> rcu_read_lock();
> -resubmit:
> +
> idev = ip6_dst_idev(skb_dst(skb));
> if (!pskb_pull(skb, skb_transport_offset(skb)))
> goto discard;
> nhoff = IP6CB(skb)->nhoff;
> nexthdr = skb_network_header(skb)[nhoff];
>
> +resubmit:
This has already been attempted in 0243508edd "ipv6: Fix protocol
resubmission" and reverted in 1b0ccfe54a.
It looks that in some genuine extension header handling cases of ipv6
(not related to encapsulation), the original resubmission code REALLY
requires one to re-read IP6CB(skb)->nhoff and refetch the nexthdr.
See ipv6_rthdr_rcv and ipv6_destopt_rcv for example:
Snip from ipv6_rthdr_rcv:
struct inet6_skb_parm *opt = IP6CB(skb);
opt->lastopt = opt->srcrt = skb_network_header_len(skb);
skb->transport_header += (hdr->hdrlen + 1) << 3;
opt->dst0 = opt->dst1;
opt->dst1 = 0;
opt->nhoff = (&hdr->nexthdr) - skb_network_header(skb);
return 1;
Snip from ipv6_destopt_rcv:
opt = IP6CB(skb);
#if IS_ENABLED(CONFIG_IPV6_MIP6)
opt->nhoff = dstbuf;
#else
opt->nhoff = opt->dst1;
#endif
return 1;
I think there are two "resubmission" cases:
1. original ipv6 extension header handling, which seem to require
nexthdr re-read (after IP6CB(skb)->nhoff re-assigned), as seen above
2. encapsulation resubmission (e.g. fou)
One suggestion: we may identify the encapsulation case by returning the
negative of the proto number.
Another suggestion: we can take your approach, but execute the nexthdr
re-read within ipv6_rthdr_rcv and ipv6_destopt_rcv (and similar
inet6_protocol.handler functions).
Regards,
Shmulik
^ permalink raw reply [flat|nested] 22+ messages in thread* Re: [PATCH net-next 06/13] ipv6: Fix nexthdr for reinjection
2016-05-12 20:23 ` Shmulik Ladkani
@ 2016-05-12 21:45 ` Tom Herbert
2016-05-13 4:16 ` Shmulik Ladkani
2016-05-13 6:28 ` Shmulik Ladkani
0 siblings, 2 replies; 22+ messages in thread
From: Tom Herbert @ 2016-05-12 21:45 UTC (permalink / raw)
To: Shmulik Ladkani
Cc: David S. Miller, Linux Kernel Network Developers, Kernel Team
On Thu, May 12, 2016 at 1:23 PM, Shmulik Ladkani
<shmulik.ladkani@gmail.com> wrote:
> Hi Tom,
>
> On Wed, 11 May 2016 09:47:26 -0700 Tom Herbert <tom@herbertland.com> wrote:
>> In ip6_input_finish the protocol handle returns a value greater than
>> zero the packet needs to be resubmitted using the returned protocol.
>> The returned protocol is being ignored and each time through resubmit
>> nexthdr is taken from an offest in the packet. This patch fixes that
>> so that nexthdr is taken from return value of the protocol handler.
>>
>> Signed-off-by: Tom Herbert <tom@herbertland.com>
>> ---
>> net/ipv6/ip6_input.c | 9 ++++++---
>> 1 file changed, 6 insertions(+), 3 deletions(-)
>>
>> diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c
>> index 6ed5601..2a0258a 100644
>> --- a/net/ipv6/ip6_input.c
>> +++ b/net/ipv6/ip6_input.c
>> @@ -222,13 +222,14 @@ static int ip6_input_finish(struct net *net, struct sock *sk, struct sk_buff *sk
>> */
>>
>> rcu_read_lock();
>> -resubmit:
>> +
>> idev = ip6_dst_idev(skb_dst(skb));
>> if (!pskb_pull(skb, skb_transport_offset(skb)))
>> goto discard;
>> nhoff = IP6CB(skb)->nhoff;
>> nexthdr = skb_network_header(skb)[nhoff];
>>
>> +resubmit:
>
> This has already been attempted in 0243508edd "ipv6: Fix protocol
> resubmission" and reverted in 1b0ccfe54a.
>
> It looks that in some genuine extension header handling cases of ipv6
> (not related to encapsulation), the original resubmission code REALLY
> requires one to re-read IP6CB(skb)->nhoff and refetch the nexthdr.
>
Is there any reason why the EH handlers can't read the nexthdr and return that?
Tom
> See ipv6_rthdr_rcv and ipv6_destopt_rcv for example:
>
> Snip from ipv6_rthdr_rcv:
>
> struct inet6_skb_parm *opt = IP6CB(skb);
>
> opt->lastopt = opt->srcrt = skb_network_header_len(skb);
> skb->transport_header += (hdr->hdrlen + 1) << 3;
> opt->dst0 = opt->dst1;
> opt->dst1 = 0;
> opt->nhoff = (&hdr->nexthdr) - skb_network_header(skb);
> return 1;
>
> Snip from ipv6_destopt_rcv:
>
> opt = IP6CB(skb);
> #if IS_ENABLED(CONFIG_IPV6_MIP6)
> opt->nhoff = dstbuf;
> #else
> opt->nhoff = opt->dst1;
> #endif
> return 1;
>
> I think there are two "resubmission" cases:
> 1. original ipv6 extension header handling, which seem to require
> nexthdr re-read (after IP6CB(skb)->nhoff re-assigned), as seen above
> 2. encapsulation resubmission (e.g. fou)
>
> One suggestion: we may identify the encapsulation case by returning the
> negative of the proto number.
>
> Another suggestion: we can take your approach, but execute the nexthdr
> re-read within ipv6_rthdr_rcv and ipv6_destopt_rcv (and similar
> inet6_protocol.handler functions).
>
> Regards,
> Shmulik
^ permalink raw reply [flat|nested] 22+ messages in thread
* Re: [PATCH net-next 06/13] ipv6: Fix nexthdr for reinjection
2016-05-12 21:45 ` Tom Herbert
@ 2016-05-13 4:16 ` Shmulik Ladkani
2016-05-13 6:28 ` Shmulik Ladkani
1 sibling, 0 replies; 22+ messages in thread
From: Shmulik Ladkani @ 2016-05-13 4:16 UTC (permalink / raw)
To: Tom Herbert; +Cc: David S. Miller, Linux Kernel Network Developers, Kernel Team
Hi Tom,
On Thu, 12 May 2016 14:45:36 -0700 Tom Herbert <tom@herbertland.com> wrote:
> On Thu, May 12, 2016 at 1:23 PM, Shmulik Ladkani
> <shmulik.ladkani@gmail.com> wrote:
> > On Wed, 11 May 2016 09:47:26 -0700 Tom Herbert <tom@herbertland.com> wrote:
> >> In ip6_input_finish the protocol handle returns a value greater than
> >> zero the packet needs to be resubmitted using the returned protocol.
> >> The returned protocol is being ignored and each time through resubmit
> >> nexthdr is taken from an offest in the packet. This patch fixes that
> >> so that nexthdr is taken from return value of the protocol handler.
> >>
> >> Signed-off-by: Tom Herbert <tom@herbertland.com>
> >> ---
> >> net/ipv6/ip6_input.c | 9 ++++++---
> >> 1 file changed, 6 insertions(+), 3 deletions(-)
> >>
> >> diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c
> >> index 6ed5601..2a0258a 100644
> >> --- a/net/ipv6/ip6_input.c
> >> +++ b/net/ipv6/ip6_input.c
> >> @@ -222,13 +222,14 @@ static int ip6_input_finish(struct net *net, struct sock *sk, struct sk_buff *sk
> >> */
> >>
> >> rcu_read_lock();
> >> -resubmit:
> >> +
> >> idev = ip6_dst_idev(skb_dst(skb));
> >> if (!pskb_pull(skb, skb_transport_offset(skb)))
> >> goto discard;
> >> nhoff = IP6CB(skb)->nhoff;
> >> nexthdr = skb_network_header(skb)[nhoff];
> >>
> >> +resubmit:
> >
> > This has already been attempted in 0243508edd "ipv6: Fix protocol
> > resubmission" and reverted in 1b0ccfe54a.
> >
> > It looks that in some genuine extension header handling cases of ipv6
> > (not related to encapsulation), the original resubmission code REALLY
> > requires one to re-read IP6CB(skb)->nhoff and refetch the nexthdr.
> >
> Is there any reason why the EH handlers can't read the nexthdr and return
> that?
Unaware of any reason; It does looks like we can simply do so for the EH
handlers (this was my 2nd suggestion).
Note also, that after resubmission, if the new nexthdr proto isn't found
at inet6_protos, there's a later:
icmpv6_send(skb, ICMPV6_PARAMPROB,
ICMPV6_UNK_NEXTHDR, nhoff);
whose purpose is to send icmpv6 "Parameter Problem, Unrecognized Next
Header", with the "Pointer info" field set to value of 'nhoff'.
Thus for the EH handlers case we need to pass the updated
'IP6CB(skb)->nhoff' as the last argument.
OTOH, if the nexthdr proto was due to encapsulation resubmission, I'm
not sure what's the right "pointer info" value to specify :)
Regards,
Shmulik
^ permalink raw reply [flat|nested] 22+ messages in thread
* Re: [PATCH net-next 06/13] ipv6: Fix nexthdr for reinjection
2016-05-12 21:45 ` Tom Herbert
2016-05-13 4:16 ` Shmulik Ladkani
@ 2016-05-13 6:28 ` Shmulik Ladkani
2016-05-13 11:00 ` Shmulik Ladkani
1 sibling, 1 reply; 22+ messages in thread
From: Shmulik Ladkani @ 2016-05-13 6:28 UTC (permalink / raw)
To: Tom Herbert; +Cc: David S. Miller, Linux Kernel Network Developers, Kernel Team
Hi,
On Thu, 12 May 2016 14:45:36 -0700 Tom Herbert <tom@herbertland.com> wrote:
> On Thu, May 12, 2016 at 1:23 PM, Shmulik Ladkani
> <shmulik.ladkani@gmail.com> wrote:
> >> @@ -222,13 +222,14 @@ static int ip6_input_finish(struct net *net, struct sock *sk, struct sk_buff *sk
> >> */
> >>
> >> rcu_read_lock();
> >> -resubmit:
> >> +
> >> idev = ip6_dst_idev(skb_dst(skb));
> >> if (!pskb_pull(skb, skb_transport_offset(skb)))
> >> goto discard;
> >> nhoff = IP6CB(skb)->nhoff;
> >> nexthdr = skb_network_header(skb)[nhoff];
> >>
> >> +resubmit:
> >
> > This has already been attempted in 0243508edd "ipv6: Fix protocol
> > resubmission" and reverted in 1b0ccfe54a.
> >
> > It looks that in some genuine extension header handling cases of ipv6
> > (not related to encapsulation), the original resubmission code REALLY
> > requires one to re-read IP6CB(skb)->nhoff and refetch the nexthdr.
> >
> Is there any reason why the EH handlers can't read the nexthdr and return that?
One additional thing:
Seems the
if (!pskb_pull(skb, skb_transport_offset(skb)))
located at the original resubmit label was also necessary, as the EH
handlers may increment skb->transport_header (both ipv6_destopt_rcv and
ipv6_rthdr_rcv do so).
So if we'd like to read the nexthdr at the EH handlers we should repeat
the "skb pull; read nexthdr from skb_network_header(skb)[new nhoff];
return nexhdr;" prior each positive return from EH handlers.
Thanks
Shmulik
^ permalink raw reply [flat|nested] 22+ messages in thread* Re: [PATCH net-next 06/13] ipv6: Fix nexthdr for reinjection
2016-05-13 6:28 ` Shmulik Ladkani
@ 2016-05-13 11:00 ` Shmulik Ladkani
0 siblings, 0 replies; 22+ messages in thread
From: Shmulik Ladkani @ 2016-05-13 11:00 UTC (permalink / raw)
To: Tom Herbert; +Cc: David S. Miller, Linux Kernel Network Developers, Kernel Team
Hi,
On Fri, 13 May 2016 09:28:50 +0300 Shmulik Ladkani <shmulik.ladkani@gmail.com> wrote:
> On Thu, 12 May 2016 14:45:36 -0700 Tom Herbert <tom@herbertland.com> wrote:
> > Is there any reason why the EH handlers can't read the nexthdr and return that?
>
> One additional thing:
>
> Seems the
>
> if (!pskb_pull(skb, skb_transport_offset(skb)))
>
> located at the original resubmit label was also necessary, as the EH
> handlers may increment skb->transport_header (both ipv6_destopt_rcv and
> ipv6_rthdr_rcv do so).
>
> So if we'd like to read the nexthdr at the EH handlers we should repeat
> the "skb pull; read nexthdr from skb_network_header(skb)[new nhoff];
> return nexhdr;" prior each positive return from EH handlers.
Alternatively, instead of modifying EH handlers adding this repeated
logic, we can rearrange ip6_input_finish code, under the premise that
"EH handling iff !INET6_PROTO_FINAL", as follows:
@@ -229,13 +229,14 @@ static int ip6_input_finish(struct net *net, struct sock *sk, struct sk_buff *sk
*/
rcu_read_lock();
-resubmit:
+nexthdr_read:
idev = ip6_dst_idev(skb_dst(skb));
if (!pskb_pull(skb, skb_transport_offset(skb)))
goto discard;
nhoff = IP6CB(skb)->nhoff;
nexthdr = skb_network_header(skb)[nhoff];
+resubmit:
raw = raw6_local_deliver(skb, nexthdr);
ipprot = rcu_dereference(inet6_protos[nexthdr]);
if (ipprot) {
@@ -263,8 +264,12 @@ resubmit:
goto discard;
ret = ipprot->handler(skb);
- if (ret > 0)
+ if (ret > 0) {
+ if (!(ipprot->flags & INET6_PROTO_FINAL))
+ goto nexthdr_read;
+ nexthdr = ret;
goto resubmit;
+ }
else if (ret == 0)
__IP6_INC_STATS(net, idev, IPSTATS_MIB_INDELIVERS);
Meaning, for EH (identified by !INET6_PROTO_FINAL), act as originally
was (skbpull and refetch nexthdr); For non INET6_PROTO_FINAL, ret code
is the proto itself, so go directly to resubmit.
Less modifications, but (1) creates a coupling (wasn't there already?)
between EH handlers and the !INET6_PROTO_FINAL flag, (2) anchors the
dual semantics WRT ret code of inet6_protocol->handler.
Regards,
Shmulik
^ permalink raw reply [flat|nested] 22+ messages in thread
* [PATCH net-next 07/13] ipv6: Change "final" protocol processing for encapsulation
2016-05-11 16:47 [PATCH net-next 00/13] ipv6: Enable GUEoIPv6 and more fixes for v6 tunneling Tom Herbert
` (5 preceding siblings ...)
2016-05-11 16:47 ` [PATCH net-next 06/13] ipv6: Fix nexthdr for reinjection Tom Herbert
@ 2016-05-11 16:47 ` Tom Herbert
2016-05-13 6:51 ` Shmulik Ladkani
2016-05-11 16:47 ` [PATCH net-next 08/13] fou: Support IPv6 in fou Tom Herbert
` (5 subsequent siblings)
12 siblings, 1 reply; 22+ messages in thread
From: Tom Herbert @ 2016-05-11 16:47 UTC (permalink / raw)
To: davem, netdev; +Cc: kernel-team
When performing foo-over-UDP, UDP packets are processed by the
encapsulation handler which returns another protocol to process.
This may result in processing two (or more) protocols in the
loop that are marked as INET6_PROTO_FINAL. The actions taken
for hitting a final protocol, in particular the skb_postpull_rcsum
can only be performed once.
This patch set adds a check of a final protocol has been seen. The
rules are:
- If the final protocol has not been seen any protocol is processed
(final and non-final). In the case of a final protocol, the final
actions are taken (like the skb_postpull_rcsum)
- If a final protocol has been seen (e.g. an encapsulating UDP
header) then no further non-final protocols are allowed
(e.g. extension headers). For more final protocols the
final actions are not taken (e.g. skb_postpull_rcsum).
Signed-off-by: Tom Herbert <tom@herbertland.com>
---
net/ipv6/ip6_input.c | 15 ++++++++++++++-
1 file changed, 14 insertions(+), 1 deletion(-)
diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c
index 2a0258a..7d98d01 100644
--- a/net/ipv6/ip6_input.c
+++ b/net/ipv6/ip6_input.c
@@ -216,6 +216,7 @@ static int ip6_input_finish(struct net *net, struct sock *sk, struct sk_buff *sk
unsigned int nhoff;
int nexthdr;
bool raw;
+ bool have_final = false;
/*
* Parse extension headers
@@ -235,9 +236,21 @@ resubmit:
if (ipprot) {
int ret;
- if (ipprot->flags & INET6_PROTO_FINAL) {
+ if (have_final) {
+ if (!(ipprot->flags & INET6_PROTO_FINAL)) {
+ /* Once we've seen a final protocol don't
+ * allow encapsulation on any non-final
+ * ones. This allows foo in UDP encapsulation
+ * to work.
+ */
+ goto discard;
+ }
+ } else if (ipprot->flags & INET6_PROTO_FINAL) {
const struct ipv6hdr *hdr;
+ /* Only do this once for first final protocol */
+ have_final = true;
+
/* Free reference early: we don't need it any more,
and it may hold ip_conntrack module loaded
indefinitely. */
--
2.8.0.rc2
^ permalink raw reply related [flat|nested] 22+ messages in thread* Re: [PATCH net-next 07/13] ipv6: Change "final" protocol processing for encapsulation
2016-05-11 16:47 ` [PATCH net-next 07/13] ipv6: Change "final" protocol processing for encapsulation Tom Herbert
@ 2016-05-13 6:51 ` Shmulik Ladkani
0 siblings, 0 replies; 22+ messages in thread
From: Shmulik Ladkani @ 2016-05-13 6:51 UTC (permalink / raw)
To: Tom Herbert; +Cc: davem, netdev, kernel-team
Hi,
On Wed, 11 May 2016 09:47:27 -0700 Tom Herbert <tom@herbertland.com> wrote:
> When performing foo-over-UDP, UDP packets are processed by the
> encapsulation handler which returns another protocol to process.
> This may result in processing two (or more) protocols in the
> loop that are marked as INET6_PROTO_FINAL. The actions taken
> for hitting a final protocol, in particular the skb_postpull_rcsum
> can only be performed once.
>
> This patch set adds a check of a final protocol has been seen. The
> rules are:
> - If the final protocol has not been seen any protocol is processed
> (final and non-final). In the case of a final protocol, the final
> actions are taken (like the skb_postpull_rcsum)
> - If a final protocol has been seen (e.g. an encapsulating UDP
> header) then no further non-final protocols are allowed
> (e.g. extension headers). For more final protocols the
> final actions are not taken (e.g. skb_postpull_rcsum).
>
> Signed-off-by: Tom Herbert <tom@herbertland.com>
Reviewed-by: Shmulik Ladkani <shmulik.ladkani@gmail.com>
Out of curiousity, you execute the "final actions" on the first
INET6_PROTO_FINAL occurence. Would it make any sense to defer the
actions and do them upon the last INET6_PROTO_FINAL occurence?
Or must them get executed once we encounter the first INET6_PROTO_FINAL
proto handler?
Also, just a nit, seems better if commit title is
'Ensure "final" protocol processing is performed once'
Thanks
Shmulik
^ permalink raw reply [flat|nested] 22+ messages in thread
* [PATCH net-next 08/13] fou: Support IPv6 in fou
2016-05-11 16:47 [PATCH net-next 00/13] ipv6: Enable GUEoIPv6 and more fixes for v6 tunneling Tom Herbert
` (6 preceding siblings ...)
2016-05-11 16:47 ` [PATCH net-next 07/13] ipv6: Change "final" protocol processing for encapsulation Tom Herbert
@ 2016-05-11 16:47 ` Tom Herbert
2016-05-11 16:47 ` [PATCH net-next 09/13] ip6_tun: Add infrastructure for doing encapsulation Tom Herbert
` (4 subsequent siblings)
12 siblings, 0 replies; 22+ messages in thread
From: Tom Herbert @ 2016-05-11 16:47 UTC (permalink / raw)
To: davem, netdev; +Cc: kernel-team
This patch adds receive path support for IPv6 with fou.
- Add address family to fou structure for open sockets. This supports
AF_INET and AF_INET6. Lookups for fou ports are performed on both the
port number and family.
- In fou and gue receive adjust tot_len in IPv4 header or payload_len
based on address family.
- Allow AF_INET6 in FOU_ATTR_AF netlink attribute.
Signed-off-by: Tom Herbert <tom@herbertland.com>
---
net/ipv4/fou.c | 47 +++++++++++++++++++++++++++++++++++------------
1 file changed, 35 insertions(+), 12 deletions(-)
diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c
index f4f2ddd..5f9207c 100644
--- a/net/ipv4/fou.c
+++ b/net/ipv4/fou.c
@@ -21,6 +21,7 @@ struct fou {
u8 protocol;
u8 flags;
__be16 port;
+ u8 family;
u16 type;
struct list_head list;
struct rcu_head rcu;
@@ -47,14 +48,17 @@ static inline struct fou *fou_from_sock(struct sock *sk)
return sk->sk_user_data;
}
-static int fou_recv_pull(struct sk_buff *skb, size_t len)
+static int fou_recv_pull(struct sk_buff *skb, struct fou *fou, size_t len)
{
- struct iphdr *iph = ip_hdr(skb);
-
/* Remove 'len' bytes from the packet (UDP header and
* FOU header if present).
*/
- iph->tot_len = htons(ntohs(iph->tot_len) - len);
+ if (fou->family == AF_INET)
+ ip_hdr(skb)->tot_len = htons(ntohs(ip_hdr(skb)->tot_len) - len);
+ else
+ ipv6_hdr(skb)->payload_len =
+ htons(ntohs(ipv6_hdr(skb)->payload_len) - len);
+
__skb_pull(skb, len);
skb_postpull_rcsum(skb, udp_hdr(skb), len);
skb_reset_transport_header(skb);
@@ -68,7 +72,7 @@ static int fou_udp_recv(struct sock *sk, struct sk_buff *skb)
if (!fou)
return 1;
- if (fou_recv_pull(skb, sizeof(struct udphdr)))
+ if (fou_recv_pull(skb, fou, sizeof(struct udphdr)))
goto drop;
return -fou->protocol;
@@ -141,7 +145,11 @@ static int gue_udp_recv(struct sock *sk, struct sk_buff *skb)
hdrlen = sizeof(struct guehdr) + optlen;
- ip_hdr(skb)->tot_len = htons(ntohs(ip_hdr(skb)->tot_len) - len);
+ if (fou->family == AF_INET)
+ ip_hdr(skb)->tot_len = htons(ntohs(ip_hdr(skb)->tot_len) - len);
+ else
+ ipv6_hdr(skb)->payload_len =
+ htons(ntohs(ipv6_hdr(skb)->payload_len) - len);
/* Pull csum through the guehdr now . This can be used if
* there is a remote checksum offload.
@@ -426,7 +434,8 @@ static int fou_add_to_port_list(struct net *net, struct fou *fou)
mutex_lock(&fn->fou_lock);
list_for_each_entry(fout, &fn->fou_list, list) {
- if (fou->port == fout->port) {
+ if (fou->port == fout->port &&
+ fou->family == fout->family) {
mutex_unlock(&fn->fou_lock);
return -EALREADY;
}
@@ -471,8 +480,9 @@ static int fou_create(struct net *net, struct fou_cfg *cfg,
sk = sock->sk;
- fou->flags = cfg->flags;
fou->port = cfg->udp_config.local_udp_port;
+ fou->family = cfg->udp_config.family;
+ fou->flags = cfg->flags;
fou->type = cfg->type;
fou->sock = sock;
@@ -524,12 +534,13 @@ static int fou_destroy(struct net *net, struct fou_cfg *cfg)
{
struct fou_net *fn = net_generic(net, fou_net_id);
__be16 port = cfg->udp_config.local_udp_port;
+ u8 family = cfg->udp_config.family;
int err = -EINVAL;
struct fou *fou;
mutex_lock(&fn->fou_lock);
list_for_each_entry(fou, &fn->fou_list, list) {
- if (fou->port == port) {
+ if (fou->port == port && fou->family == family) {
fou_release(fou);
err = 0;
break;
@@ -567,8 +578,15 @@ static int parse_nl_config(struct genl_info *info,
if (info->attrs[FOU_ATTR_AF]) {
u8 family = nla_get_u8(info->attrs[FOU_ATTR_AF]);
- if (family != AF_INET)
- return -EINVAL;
+ switch (family) {
+ case AF_INET:
+ break;
+ case AF_INET6:
+ cfg->udp_config.ipv6_v6only = 1;
+ break;
+ default:
+ return -EAFNOSUPPORT;
+ }
cfg->udp_config.family = family;
}
@@ -659,6 +677,7 @@ static int fou_nl_cmd_get_port(struct sk_buff *skb, struct genl_info *info)
struct fou_cfg cfg;
struct fou *fout;
__be16 port;
+ u8 family;
int ret;
ret = parse_nl_config(info, &cfg);
@@ -668,6 +687,10 @@ static int fou_nl_cmd_get_port(struct sk_buff *skb, struct genl_info *info)
if (port == 0)
return -EINVAL;
+ family = cfg.udp_config.family;
+ if (family != AF_INET && family != AF_INET6)
+ return -EINVAL;
+
msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
if (!msg)
return -ENOMEM;
@@ -675,7 +698,7 @@ static int fou_nl_cmd_get_port(struct sk_buff *skb, struct genl_info *info)
ret = -ESRCH;
mutex_lock(&fn->fou_lock);
list_for_each_entry(fout, &fn->fou_list, list) {
- if (port == fout->port) {
+ if (port == fout->port && family == fout->family) {
ret = fou_dump_info(fout, info->snd_portid,
info->snd_seq, 0, msg,
info->genlhdr->cmd);
--
2.8.0.rc2
^ permalink raw reply related [flat|nested] 22+ messages in thread* [PATCH net-next 09/13] ip6_tun: Add infrastructure for doing encapsulation
2016-05-11 16:47 [PATCH net-next 00/13] ipv6: Enable GUEoIPv6 and more fixes for v6 tunneling Tom Herbert
` (7 preceding siblings ...)
2016-05-11 16:47 ` [PATCH net-next 08/13] fou: Support IPv6 in fou Tom Herbert
@ 2016-05-11 16:47 ` Tom Herbert
2016-05-11 16:47 ` [PATCH net-next 10/13] ip6_gre: Add support for fou/gue encapsulation Tom Herbert
` (3 subsequent siblings)
12 siblings, 0 replies; 22+ messages in thread
From: Tom Herbert @ 2016-05-11 16:47 UTC (permalink / raw)
To: davem, netdev; +Cc: kernel-team
Add encap_hlen and ip_tunnel_encap structure to ip6_tnl. Add functions
for getting encap hlen, setting up encap on a tunnel, performing
encapsulation operation.
Signed-off-by: Tom Herbert <tom@herbertland.com>
---
include/net/ip6_tunnel.h | 8 +++++-
net/ipv6/ip6_tunnel.c | 36 ++++++++++++++++++--------
net/ipv6/ip6_tunnel_core.c | 64 ++++++++++++++++++++++++++++++++++++++++++++++
3 files changed, 96 insertions(+), 12 deletions(-)
diff --git a/include/net/ip6_tunnel.h b/include/net/ip6_tunnel.h
index 1c14c27..1b8db86 100644
--- a/include/net/ip6_tunnel.h
+++ b/include/net/ip6_tunnel.h
@@ -66,10 +66,16 @@ struct ip6_tnl {
__u32 o_seqno; /* The last output seqno */
int hlen; /* tun_hlen + encap_hlen */
int tun_hlen; /* Precalculated header length */
+ int encap_hlen; /* Encap header length (FOU,GUE) */
+ struct ip_tunnel_encap encap;
int mlink;
-
};
+int ip6_tnl_encap_setup(struct ip6_tnl *t,
+ struct ip_tunnel_encap *ipencap);
+int ip6_tnl_encap(struct sk_buff *skb, struct ip6_tnl *t,
+ u8 *protocol, struct flowi6 *fl6);
+
/* Tunnel encapsulation limit destination sub-option */
struct ipv6_tlv_tnl_enc_lim {
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 50af706..66e3a63 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -1010,7 +1010,7 @@ int ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev, __u8 dsfield,
struct dst_entry *dst = NULL, *ndst = NULL;
struct net_device *tdev;
int mtu;
- unsigned int max_headroom = sizeof(struct ipv6hdr);
+ unsigned int max_headroom = sizeof(struct ipv6hdr) + t->hlen;
int err = -1;
/* NBMA tunnel */
@@ -1063,7 +1063,7 @@ int ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev, __u8 dsfield,
t->parms.name);
goto tx_err_dst_release;
}
- mtu = dst_mtu(dst) - sizeof(*ipv6h);
+ mtu = dst_mtu(dst) - sizeof(*ipv6h) - t->hlen;
if (encap_limit >= 0) {
max_headroom += 8;
mtu -= 8;
@@ -1125,10 +1125,14 @@ int ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev, __u8 dsfield,
}
max_headroom = LL_RESERVED_SPACE(dst->dev) + sizeof(struct ipv6hdr)
- + dst->header_len;
+ + dst->header_len + t->hlen;
if (max_headroom > dev->needed_headroom)
dev->needed_headroom = max_headroom;
+ err = ip6_tnl_encap(skb, t, &proto, fl6);
+ if (err)
+ return err;
+
skb_push(skb, sizeof(struct ipv6hdr));
skb_reset_network_header(skb);
ipv6h = ipv6_hdr(skb);
@@ -1280,6 +1284,7 @@ static void ip6_tnl_link_config(struct ip6_tnl *t)
struct net_device *dev = t->dev;
struct __ip6_tnl_parm *p = &t->parms;
struct flowi6 *fl6 = &t->fl.u.ip6;
+ int t_hlen;
memcpy(dev->dev_addr, &p->laddr, sizeof(struct in6_addr));
memcpy(dev->broadcast, &p->raddr, sizeof(struct in6_addr));
@@ -1303,6 +1308,10 @@ static void ip6_tnl_link_config(struct ip6_tnl *t)
else
dev->flags &= ~IFF_POINTOPOINT;
+ t->tun_hlen = 0;
+ t->hlen = t->encap_hlen + t->tun_hlen;
+ t_hlen = t->hlen + sizeof(struct ipv6hdr);
+
if (p->flags & IP6_TNL_F_CAP_XMIT) {
int strict = (ipv6_addr_type(&p->raddr) &
(IPV6_ADDR_MULTICAST|IPV6_ADDR_LINKLOCAL));
@@ -1316,9 +1325,9 @@ static void ip6_tnl_link_config(struct ip6_tnl *t)
if (rt->dst.dev) {
dev->hard_header_len = rt->dst.dev->hard_header_len +
- sizeof(struct ipv6hdr);
+ sizeof(struct ipv6hdr) + t->encap_hlen;
- dev->mtu = rt->dst.dev->mtu - sizeof(struct ipv6hdr);
+ dev->mtu = rt->dst.dev->mtu - t_hlen;
if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT))
dev->mtu -= 8;
@@ -1590,14 +1599,11 @@ static void ip6_tnl_dev_setup(struct net_device *dev)
dev->netdev_ops = &ip6_tnl_netdev_ops;
dev->destructor = ip6_dev_free;
- dev->type = ARPHRD_TUNNEL6;
- dev->hard_header_len = LL_MAX_HEADER + sizeof(struct ipv6hdr);
- dev->mtu = ETH_DATA_LEN - sizeof(struct ipv6hdr);
t = netdev_priv(dev);
- if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT))
- dev->mtu -= 8;
+ dev->type = ARPHRD_TUNNEL6;
dev->flags |= IFF_NOARP;
dev->addr_len = sizeof(struct in6_addr);
+ dev->features |= NETIF_F_LLTX;
netif_keep_dst(dev);
/* This perm addr will be used as interface identifier by IPv6 */
dev->addr_assign_type = NET_ADDR_RANDOM;
@@ -1615,6 +1621,7 @@ ip6_tnl_dev_init_gen(struct net_device *dev)
{
struct ip6_tnl *t = netdev_priv(dev);
int ret;
+ int t_hlen;
t->dev = dev;
t->net = dev_net(dev);
@@ -1630,8 +1637,15 @@ ip6_tnl_dev_init_gen(struct net_device *dev)
if (ret)
goto destroy_dst;
- t->hlen = 0;
t->tun_hlen = 0;
+ t->hlen = t->encap_hlen + t->tun_hlen;
+ t_hlen = t->hlen + sizeof(struct ipv6hdr);
+
+ dev->type = ARPHRD_TUNNEL6;
+ dev->hard_header_len = LL_MAX_HEADER + t_hlen;
+ dev->mtu = ETH_DATA_LEN - t_hlen;
+ if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT))
+ dev->mtu -= 8;
return 0;
diff --git a/net/ipv6/ip6_tunnel_core.c b/net/ipv6/ip6_tunnel_core.c
index 5f5b79e..94aa414 100644
--- a/net/ipv6/ip6_tunnel_core.c
+++ b/net/ipv6/ip6_tunnel_core.c
@@ -42,3 +42,67 @@ int ip6_tnl_encap_del_ops(const struct ip6_tnl_encap_ops *ops,
}
EXPORT_SYMBOL(ip6_tnl_encap_del_ops);
+static int ip6_encap_hlen(struct ip_tunnel_encap *e)
+{
+ const struct ip6_tnl_encap_ops *ops;
+ int hlen = -EINVAL;
+
+ if (e->type == TUNNEL_ENCAP_NONE)
+ return 0;
+
+ if (e->type >= MAX_IPTUN_ENCAP_OPS)
+ return -EINVAL;
+
+ rcu_read_lock();
+ ops = rcu_dereference(ip6tun_encaps[e->type]);
+ if (likely(ops && ops->encap_hlen))
+ hlen = ops->encap_hlen(e);
+ rcu_read_unlock();
+
+ return hlen;
+}
+
+int ip6_tnl_encap_setup(struct ip6_tnl *t,
+ struct ip_tunnel_encap *ipencap)
+{
+ int hlen;
+
+ memset(&t->encap, 0, sizeof(t->encap));
+
+ hlen = ip6_encap_hlen(ipencap);
+ if (hlen < 0)
+ return hlen;
+
+ t->encap.type = ipencap->type;
+ t->encap.sport = ipencap->sport;
+ t->encap.dport = ipencap->dport;
+ t->encap.flags = ipencap->flags;
+
+ t->encap_hlen = hlen;
+ t->hlen = t->encap_hlen + t->tun_hlen;
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(ip6_tnl_encap_setup);
+
+int ip6_tnl_encap(struct sk_buff *skb, struct ip6_tnl *t,
+ u8 *protocol, struct flowi6 *fl6)
+{
+ const struct ip6_tnl_encap_ops *ops;
+ int ret = -EINVAL;
+
+ if (t->encap.type == TUNNEL_ENCAP_NONE)
+ return 0;
+
+ if (t->encap.type >= MAX_IPTUN_ENCAP_OPS)
+ return -EINVAL;
+
+ rcu_read_lock();
+ ops = rcu_dereference(ip6tun_encaps[t->encap.type]);
+ if (likely(ops && ops->build_header))
+ ret = ops->build_header(skb, &t->encap, protocol, fl6);
+ rcu_read_unlock();
+
+ return ret;
+}
+EXPORT_SYMBOL(ip6_tnl_encap);
--
2.8.0.rc2
^ permalink raw reply related [flat|nested] 22+ messages in thread* [PATCH net-next 10/13] ip6_gre: Add support for fou/gue encapsulation
2016-05-11 16:47 [PATCH net-next 00/13] ipv6: Enable GUEoIPv6 and more fixes for v6 tunneling Tom Herbert
` (8 preceding siblings ...)
2016-05-11 16:47 ` [PATCH net-next 09/13] ip6_tun: Add infrastructure for doing encapsulation Tom Herbert
@ 2016-05-11 16:47 ` Tom Herbert
2016-05-11 16:47 ` [PATCH net-next 11/13] ip6_tunnel: " Tom Herbert
` (2 subsequent siblings)
12 siblings, 0 replies; 22+ messages in thread
From: Tom Herbert @ 2016-05-11 16:47 UTC (permalink / raw)
To: davem, netdev; +Cc: kernel-team
Add netlink and setup for encapsulation
Signed-off-by: Tom Herbert <tom@herbertland.com>
---
net/ipv6/ip6_gre.c | 77 +++++++++++++++++++++++++++++++++++++++++++++++++++---
1 file changed, 74 insertions(+), 3 deletions(-)
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index ee62ec4..4110189 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -1022,9 +1022,7 @@ static int ip6gre_tunnel_init_common(struct net_device *dev)
}
tunnel->tun_hlen = gre_calc_hlen(tunnel->parms.o_flags);
-
- tunnel->hlen = tunnel->tun_hlen;
-
+ tunnel->hlen = tunnel->tun_hlen + tunnel->encap_hlen;
t_hlen = tunnel->hlen + sizeof(struct ipv6hdr);
dev->hard_header_len = LL_MAX_HEADER + t_hlen;
@@ -1290,15 +1288,57 @@ static void ip6gre_tap_setup(struct net_device *dev)
dev->priv_flags &= ~IFF_TX_SKB_SHARING;
}
+static bool ip6gre_netlink_encap_parms(struct nlattr *data[],
+ struct ip_tunnel_encap *ipencap)
+{
+ bool ret = false;
+
+ memset(ipencap, 0, sizeof(*ipencap));
+
+ if (!data)
+ return ret;
+
+ if (data[IFLA_GRE_ENCAP_TYPE]) {
+ ret = true;
+ ipencap->type = nla_get_u16(data[IFLA_GRE_ENCAP_TYPE]);
+ }
+
+ if (data[IFLA_GRE_ENCAP_FLAGS]) {
+ ret = true;
+ ipencap->flags = nla_get_u16(data[IFLA_GRE_ENCAP_FLAGS]);
+ }
+
+ if (data[IFLA_GRE_ENCAP_SPORT]) {
+ ret = true;
+ ipencap->sport = nla_get_be16(data[IFLA_GRE_ENCAP_SPORT]);
+ }
+
+ if (data[IFLA_GRE_ENCAP_DPORT]) {
+ ret = true;
+ ipencap->dport = nla_get_be16(data[IFLA_GRE_ENCAP_DPORT]);
+ }
+
+ return ret;
+}
+
static int ip6gre_newlink(struct net *src_net, struct net_device *dev,
struct nlattr *tb[], struct nlattr *data[])
{
struct ip6_tnl *nt;
struct net *net = dev_net(dev);
struct ip6gre_net *ign = net_generic(net, ip6gre_net_id);
+ struct ip_tunnel_encap ipencap;
int err;
nt = netdev_priv(dev);
+
+ if (ip6gre_netlink_encap_parms(data, &ipencap)) {
+ int err = ip6_tnl_encap_setup(nt, &ipencap);
+
+ if (err < 0)
+ return err;
+ }
+
ip6gre_netlink_parms(data, &nt->parms);
if (ip6gre_tunnel_find(net, &nt->parms, dev->type))
@@ -1345,10 +1385,18 @@ static int ip6gre_changelink(struct net_device *dev, struct nlattr *tb[],
struct net *net = nt->net;
struct ip6gre_net *ign = net_generic(net, ip6gre_net_id);
struct __ip6_tnl_parm p;
+ struct ip_tunnel_encap ipencap;
if (dev == ign->fb_tunnel_dev)
return -EINVAL;
+ if (ip6gre_netlink_encap_parms(data, &ipencap)) {
+ int err = ip6_tnl_encap_setup(nt, &ipencap);
+
+ if (err < 0)
+ return err;
+ }
+
ip6gre_netlink_parms(data, &p);
t = ip6gre_tunnel_locate(net, &p, 0);
@@ -1402,6 +1450,14 @@ static size_t ip6gre_get_size(const struct net_device *dev)
nla_total_size(4) +
/* IFLA_GRE_FLAGS */
nla_total_size(4) +
+ /* IFLA_GRE_ENCAP_TYPE */
+ nla_total_size(2) +
+ /* IFLA_GRE_ENCAP_FLAGS */
+ nla_total_size(2) +
+ /* IFLA_GRE_ENCAP_SPORT */
+ nla_total_size(2) +
+ /* IFLA_GRE_ENCAP_DPORT */
+ nla_total_size(2) +
0;
}
@@ -1425,6 +1481,17 @@ static int ip6gre_fill_info(struct sk_buff *skb, const struct net_device *dev)
nla_put_be32(skb, IFLA_GRE_FLOWINFO, p->flowinfo) ||
nla_put_u32(skb, IFLA_GRE_FLAGS, p->flags))
goto nla_put_failure;
+
+ if (nla_put_u16(skb, IFLA_GRE_ENCAP_TYPE,
+ t->encap.type) ||
+ nla_put_be16(skb, IFLA_GRE_ENCAP_SPORT,
+ t->encap.sport) ||
+ nla_put_be16(skb, IFLA_GRE_ENCAP_DPORT,
+ t->encap.dport) ||
+ nla_put_u16(skb, IFLA_GRE_ENCAP_FLAGS,
+ t->encap.flags))
+ goto nla_put_failure;
+
return 0;
nla_put_failure:
@@ -1443,6 +1510,10 @@ static const struct nla_policy ip6gre_policy[IFLA_GRE_MAX + 1] = {
[IFLA_GRE_ENCAP_LIMIT] = { .type = NLA_U8 },
[IFLA_GRE_FLOWINFO] = { .type = NLA_U32 },
[IFLA_GRE_FLAGS] = { .type = NLA_U32 },
+ [IFLA_GRE_ENCAP_TYPE] = { .type = NLA_U16 },
+ [IFLA_GRE_ENCAP_FLAGS] = { .type = NLA_U16 },
+ [IFLA_GRE_ENCAP_SPORT] = { .type = NLA_U16 },
+ [IFLA_GRE_ENCAP_DPORT] = { .type = NLA_U16 },
};
static struct rtnl_link_ops ip6gre_link_ops __read_mostly = {
--
2.8.0.rc2
^ permalink raw reply related [flat|nested] 22+ messages in thread* [PATCH net-next 11/13] ip6_tunnel: Add support for fou/gue encapsulation
2016-05-11 16:47 [PATCH net-next 00/13] ipv6: Enable GUEoIPv6 and more fixes for v6 tunneling Tom Herbert
` (9 preceding siblings ...)
2016-05-11 16:47 ` [PATCH net-next 10/13] ip6_gre: Add support for fou/gue encapsulation Tom Herbert
@ 2016-05-11 16:47 ` Tom Herbert
2016-05-11 16:47 ` [PATCH net-next 12/13] ip6ip6: Support for GSO/GRO Tom Herbert
2016-05-11 16:47 ` [PATCH net-next 13/13] ip4ip6: " Tom Herbert
12 siblings, 0 replies; 22+ messages in thread
From: Tom Herbert @ 2016-05-11 16:47 UTC (permalink / raw)
To: davem, netdev; +Cc: kernel-team
Add netlink and setup for encapsulation
Signed-off-by: Tom Herbert <tom@herbertland.com>
---
net/ipv6/ip6_tunnel.c | 72 +++++++++++++++++++++++++++++++++++++++++++++++++++
1 file changed, 72 insertions(+)
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 66e3a63..52792f9 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -1743,13 +1743,55 @@ static void ip6_tnl_netlink_parms(struct nlattr *data[],
parms->proto = nla_get_u8(data[IFLA_IPTUN_PROTO]);
}
+static bool ip6_tnl_netlink_encap_parms(struct nlattr *data[],
+ struct ip_tunnel_encap *ipencap)
+{
+ bool ret = false;
+
+ memset(ipencap, 0, sizeof(*ipencap));
+
+ if (!data)
+ return ret;
+
+ if (data[IFLA_IPTUN_ENCAP_TYPE]) {
+ ret = true;
+ ipencap->type = nla_get_u16(data[IFLA_IPTUN_ENCAP_TYPE]);
+ }
+
+ if (data[IFLA_IPTUN_ENCAP_FLAGS]) {
+ ret = true;
+ ipencap->flags = nla_get_u16(data[IFLA_IPTUN_ENCAP_FLAGS]);
+ }
+
+ if (data[IFLA_IPTUN_ENCAP_SPORT]) {
+ ret = true;
+ ipencap->sport = nla_get_be16(data[IFLA_IPTUN_ENCAP_SPORT]);
+ }
+
+ if (data[IFLA_IPTUN_ENCAP_DPORT]) {
+ ret = true;
+ ipencap->dport = nla_get_be16(data[IFLA_IPTUN_ENCAP_DPORT]);
+ }
+
+ return ret;
+}
+
static int ip6_tnl_newlink(struct net *src_net, struct net_device *dev,
struct nlattr *tb[], struct nlattr *data[])
{
struct net *net = dev_net(dev);
struct ip6_tnl *nt, *t;
+ struct ip_tunnel_encap ipencap;
nt = netdev_priv(dev);
+
+ if (ip6_tnl_netlink_encap_parms(data, &ipencap)) {
+ int err = ip6_tnl_encap_setup(nt, &ipencap);
+
+ if (err < 0)
+ return err;
+ }
+
ip6_tnl_netlink_parms(data, &nt->parms);
t = ip6_tnl_locate(net, &nt->parms, 0);
@@ -1766,10 +1808,17 @@ static int ip6_tnl_changelink(struct net_device *dev, struct nlattr *tb[],
struct __ip6_tnl_parm p;
struct net *net = t->net;
struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id);
+ struct ip_tunnel_encap ipencap;
if (dev == ip6n->fb_tnl_dev)
return -EINVAL;
+ if (ip6_tnl_netlink_encap_parms(data, &ipencap)) {
+ int err = ip6_tnl_encap_setup(t, &ipencap);
+
+ if (err < 0)
+ return err;
+ }
ip6_tnl_netlink_parms(data, &p);
t = ip6_tnl_locate(net, &p, 0);
@@ -1810,6 +1859,14 @@ static size_t ip6_tnl_get_size(const struct net_device *dev)
nla_total_size(4) +
/* IFLA_IPTUN_PROTO */
nla_total_size(1) +
+ /* IFLA_IPTUN_ENCAP_TYPE */
+ nla_total_size(2) +
+ /* IFLA_IPTUN_ENCAP_FLAGS */
+ nla_total_size(2) +
+ /* IFLA_IPTUN_ENCAP_SPORT */
+ nla_total_size(2) +
+ /* IFLA_IPTUN_ENCAP_DPORT */
+ nla_total_size(2) +
0;
}
@@ -1827,6 +1884,17 @@ static int ip6_tnl_fill_info(struct sk_buff *skb, const struct net_device *dev)
nla_put_u32(skb, IFLA_IPTUN_FLAGS, parm->flags) ||
nla_put_u8(skb, IFLA_IPTUN_PROTO, parm->proto))
goto nla_put_failure;
+
+ if (nla_put_u16(skb, IFLA_IPTUN_ENCAP_TYPE,
+ tunnel->encap.type) ||
+ nla_put_be16(skb, IFLA_IPTUN_ENCAP_SPORT,
+ tunnel->encap.sport) ||
+ nla_put_be16(skb, IFLA_IPTUN_ENCAP_DPORT,
+ tunnel->encap.dport) ||
+ nla_put_u16(skb, IFLA_IPTUN_ENCAP_FLAGS,
+ tunnel->encap.flags))
+ goto nla_put_failure;
+
return 0;
nla_put_failure:
@@ -1850,6 +1918,10 @@ static const struct nla_policy ip6_tnl_policy[IFLA_IPTUN_MAX + 1] = {
[IFLA_IPTUN_FLOWINFO] = { .type = NLA_U32 },
[IFLA_IPTUN_FLAGS] = { .type = NLA_U32 },
[IFLA_IPTUN_PROTO] = { .type = NLA_U8 },
+ [IFLA_IPTUN_ENCAP_TYPE] = { .type = NLA_U16 },
+ [IFLA_IPTUN_ENCAP_FLAGS] = { .type = NLA_U16 },
+ [IFLA_IPTUN_ENCAP_SPORT] = { .type = NLA_U16 },
+ [IFLA_IPTUN_ENCAP_DPORT] = { .type = NLA_U16 },
};
static struct rtnl_link_ops ip6_link_ops __read_mostly = {
--
2.8.0.rc2
^ permalink raw reply related [flat|nested] 22+ messages in thread* [PATCH net-next 12/13] ip6ip6: Support for GSO/GRO
2016-05-11 16:47 [PATCH net-next 00/13] ipv6: Enable GUEoIPv6 and more fixes for v6 tunneling Tom Herbert
` (10 preceding siblings ...)
2016-05-11 16:47 ` [PATCH net-next 11/13] ip6_tunnel: " Tom Herbert
@ 2016-05-11 16:47 ` Tom Herbert
2016-05-11 16:47 ` [PATCH net-next 13/13] ip4ip6: " Tom Herbert
12 siblings, 0 replies; 22+ messages in thread
From: Tom Herbert @ 2016-05-11 16:47 UTC (permalink / raw)
To: davem, netdev; +Cc: kernel-team
Signed-off-by: Tom Herbert <tom@herbertland.com>
---
net/ipv6/ip6_offload.c | 24 +++++++++++++++++++++---
net/ipv6/ip6_tunnel.c | 3 +++
2 files changed, 24 insertions(+), 3 deletions(-)
diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c
index 787e55f..332d6a0 100644
--- a/net/ipv6/ip6_offload.c
+++ b/net/ipv6/ip6_offload.c
@@ -253,9 +253,11 @@ out:
return pp;
}
-static struct sk_buff **sit_gro_receive(struct sk_buff **head,
- struct sk_buff *skb)
+static struct sk_buff **sit_ip6ip6_gro_receive(struct sk_buff **head,
+ struct sk_buff *skb)
{
+ /* Common GRO receive for SIT and IP6IP6 */
+
if (NAPI_GRO_CB(skb)->encap_mark) {
NAPI_GRO_CB(skb)->flush = 1;
return NULL;
@@ -298,6 +300,13 @@ static int sit_gro_complete(struct sk_buff *skb, int nhoff)
return ipv6_gro_complete(skb, nhoff);
}
+static int ip6ip6_gro_complete(struct sk_buff *skb, int nhoff)
+{
+ skb->encapsulation = 1;
+ skb_shinfo(skb)->gso_type |= SKB_GSO_IPXIP6;
+ return ipv6_gro_complete(skb, nhoff);
+}
+
static struct packet_offload ipv6_packet_offload __read_mostly = {
.type = cpu_to_be16(ETH_P_IPV6),
.callbacks = {
@@ -310,11 +319,19 @@ static struct packet_offload ipv6_packet_offload __read_mostly = {
static const struct net_offload sit_offload = {
.callbacks = {
.gso_segment = ipv6_gso_segment,
- .gro_receive = sit_gro_receive,
+ .gro_receive = sit_ip6ip6_gro_receive,
.gro_complete = sit_gro_complete,
},
};
+static const struct net_offload ip6ip6_offload = {
+ .callbacks = {
+ .gso_segment = ipv6_gso_segment,
+ .gro_receive = sit_ip6ip6_gro_receive,
+ .gro_complete = ip6ip6_gro_complete,
+ },
+};
+
static int __init ipv6_offload_init(void)
{
@@ -326,6 +343,7 @@ static int __init ipv6_offload_init(void)
dev_add_offload(&ipv6_packet_offload);
inet_add_offload(&sit_offload, IPPROTO_IPV6);
+ inet6_add_offload(&ip6ip6_offload, IPPROTO_IPV6);
return 0;
}
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 52792f9..0fab341 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -1238,6 +1238,9 @@ ip6ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
if (t->parms.flags & IP6_TNL_F_USE_ORIG_FWMARK)
fl6.flowi6_mark = skb->mark;
+ if (iptunnel_handle_offloads(skb, SKB_GSO_IPXIP6))
+ return -1;
+
err = ip6_tnl_xmit(skb, dev, dsfield, &fl6, encap_limit, &mtu,
IPPROTO_IPV6);
if (err != 0) {
--
2.8.0.rc2
^ permalink raw reply related [flat|nested] 22+ messages in thread* [PATCH net-next 13/13] ip4ip6: Support for GSO/GRO
2016-05-11 16:47 [PATCH net-next 00/13] ipv6: Enable GUEoIPv6 and more fixes for v6 tunneling Tom Herbert
` (11 preceding siblings ...)
2016-05-11 16:47 ` [PATCH net-next 12/13] ip6ip6: Support for GSO/GRO Tom Herbert
@ 2016-05-11 16:47 ` Tom Herbert
12 siblings, 0 replies; 22+ messages in thread
From: Tom Herbert @ 2016-05-11 16:47 UTC (permalink / raw)
To: davem, netdev; +Cc: kernel-team
Signed-off-by: Tom Herbert <tom@herbertland.com>
---
include/net/inet_common.h | 5 +++++
net/ipv4/af_inet.c | 12 +++++++-----
net/ipv6/ip6_offload.c | 33 ++++++++++++++++++++++++++++++++-
net/ipv6/ip6_tunnel.c | 5 ++++-
4 files changed, 48 insertions(+), 7 deletions(-)
diff --git a/include/net/inet_common.h b/include/net/inet_common.h
index 109e3ee..5d68342 100644
--- a/include/net/inet_common.h
+++ b/include/net/inet_common.h
@@ -39,6 +39,11 @@ int inet_ctl_sock_create(struct sock **sk, unsigned short family,
int inet_recv_error(struct sock *sk, struct msghdr *msg, int len,
int *addr_len);
+struct sk_buff **inet_gro_receive(struct sk_buff **head, struct sk_buff *skb);
+int inet_gro_complete(struct sk_buff *skb, int nhoff);
+struct sk_buff *inet_gso_segment(struct sk_buff *skb,
+ netdev_features_t features);
+
static inline void inet_ctl_sock_destroy(struct sock *sk)
{
if (sk)
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 25040b1..377424e 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1192,8 +1192,8 @@ int inet_sk_rebuild_header(struct sock *sk)
}
EXPORT_SYMBOL(inet_sk_rebuild_header);
-static struct sk_buff *inet_gso_segment(struct sk_buff *skb,
- netdev_features_t features)
+struct sk_buff *inet_gso_segment(struct sk_buff *skb,
+ netdev_features_t features)
{
bool udpfrag = false, fixedid = false, encap;
struct sk_buff *segs = ERR_PTR(-EINVAL);
@@ -1280,9 +1280,9 @@ static struct sk_buff *inet_gso_segment(struct sk_buff *skb,
out:
return segs;
}
+EXPORT_SYMBOL(inet_gso_segment);
-static struct sk_buff **inet_gro_receive(struct sk_buff **head,
- struct sk_buff *skb)
+struct sk_buff **inet_gro_receive(struct sk_buff **head, struct sk_buff *skb)
{
const struct net_offload *ops;
struct sk_buff **pp = NULL;
@@ -1398,6 +1398,7 @@ out:
return pp;
}
+EXPORT_SYMBOL(inet_gro_receive);
static struct sk_buff **ipip_gro_receive(struct sk_buff **head,
struct sk_buff *skb)
@@ -1449,7 +1450,7 @@ int inet_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len)
return -EINVAL;
}
-static int inet_gro_complete(struct sk_buff *skb, int nhoff)
+int inet_gro_complete(struct sk_buff *skb, int nhoff)
{
__be16 newlen = htons(skb->len - nhoff);
struct iphdr *iph = (struct iphdr *)(skb->data + nhoff);
@@ -1479,6 +1480,7 @@ out_unlock:
return err;
}
+EXPORT_SYMBOL(inet_gro_complete);
static int ipip_gro_complete(struct sk_buff *skb, int nhoff)
{
diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c
index 332d6a0..22e90e5 100644
--- a/net/ipv6/ip6_offload.c
+++ b/net/ipv6/ip6_offload.c
@@ -16,6 +16,7 @@
#include <net/protocol.h>
#include <net/ipv6.h>
+#include <net/inet_common.h>
#include "ip6_offload.h"
@@ -268,6 +269,21 @@ static struct sk_buff **sit_ip6ip6_gro_receive(struct sk_buff **head,
return ipv6_gro_receive(head, skb);
}
+static struct sk_buff **ip4ip6_gro_receive(struct sk_buff **head,
+ struct sk_buff *skb)
+{
+ /* Common GRO receive for SIT and IP6IP6 */
+
+ if (NAPI_GRO_CB(skb)->encap_mark) {
+ NAPI_GRO_CB(skb)->flush = 1;
+ return NULL;
+ }
+
+ NAPI_GRO_CB(skb)->encap_mark = 1;
+
+ return inet_gro_receive(head, skb);
+}
+
static int ipv6_gro_complete(struct sk_buff *skb, int nhoff)
{
const struct net_offload *ops;
@@ -307,6 +323,13 @@ static int ip6ip6_gro_complete(struct sk_buff *skb, int nhoff)
return ipv6_gro_complete(skb, nhoff);
}
+static int ip4ip6_gro_complete(struct sk_buff *skb, int nhoff)
+{
+ skb->encapsulation = 1;
+ skb_shinfo(skb)->gso_type |= SKB_GSO_IPXIP6;
+ return inet_gro_complete(skb, nhoff);
+}
+
static struct packet_offload ipv6_packet_offload __read_mostly = {
.type = cpu_to_be16(ETH_P_IPV6),
.callbacks = {
@@ -324,6 +347,14 @@ static const struct net_offload sit_offload = {
},
};
+static const struct net_offload ip4ip6_offload = {
+ .callbacks = {
+ .gso_segment = inet_gso_segment,
+ .gro_receive = ip4ip6_gro_receive,
+ .gro_complete = ip4ip6_gro_complete,
+ },
+};
+
static const struct net_offload ip6ip6_offload = {
.callbacks = {
.gso_segment = ipv6_gso_segment,
@@ -331,7 +362,6 @@ static const struct net_offload ip6ip6_offload = {
.gro_complete = ip6ip6_gro_complete,
},
};
-
static int __init ipv6_offload_init(void)
{
@@ -344,6 +374,7 @@ static int __init ipv6_offload_init(void)
inet_add_offload(&sit_offload, IPPROTO_IPV6);
inet6_add_offload(&ip6ip6_offload, IPPROTO_IPV6);
+ inet6_add_offload(&ip4ip6_offload, IPPROTO_IPIP);
return 0;
}
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 0fab341..9a53fd1 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -897,7 +897,7 @@ drop:
static int ip4ip6_rcv(struct sk_buff *skb)
{
- return ipxip6_rcv(skb, IPPROTO_IP, &tpi_v4,
+ return ipxip6_rcv(skb, IPPROTO_IPIP, &tpi_v4,
ip4ip6_dscp_ecn_decapsulate);
}
@@ -1184,6 +1184,9 @@ ip4ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
if (t->parms.flags & IP6_TNL_F_USE_ORIG_FWMARK)
fl6.flowi6_mark = skb->mark;
+ if (iptunnel_handle_offloads(skb, SKB_GSO_IPXIP6))
+ return -1;
+
err = ip6_tnl_xmit(skb, dev, dsfield, &fl6, encap_limit, &mtu,
IPPROTO_IPIP);
if (err != 0) {
--
2.8.0.rc2
^ permalink raw reply related [flat|nested] 22+ messages in thread