This patch hooks the IPsec GSO code into the generic
network stack.
Signed-off-by: Steffen Klassert <[email protected]>
---
include/linux/netdevice.h | 2 +-
include/net/xfrm.h | 1 +
net/core/dev.c | 40 +++++++++++++++++++++++++++++++++++-----
net/ipv4/ip_output.c | 8 +++++---
net/ipv4/xfrm4_output.c | 2 +-
net/sched/sch_generic.c | 2 +-
net/xfrm/xfrm_output.c | 14 +++++++++++++-
7 files changed, 57 insertions(+), 12 deletions(-)
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index d049c02..659eeec 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -3192,7 +3192,7 @@ int dev_get_phys_port_id(struct net_device *dev,
int dev_get_phys_port_name(struct net_device *dev,
char *name, size_t len);
int dev_change_proto_down(struct net_device *dev, bool proto_down);
-struct sk_buff *validate_xmit_skb_list(struct sk_buff *skb, struct net_device
*dev);
+struct sk_buff *validate_xmit_skb_list(struct sk_buff *skb, struct net_device
*dev, int *ret);
struct sk_buff *dev_hard_start_xmit(struct sk_buff *skb, struct net_device
*dev,
struct netdev_queue *txq, int *ret);
int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb);
diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index 7939c39..3a69883 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -1505,6 +1505,7 @@ struct xfrmk_spdinfo {
u32 spdhmcnt;
};
+void xfrm_dev_backlog(struct sk_buff_head *xfrm_backlog);
struct xfrm_state *xfrm_find_acq_byseq(struct net *net, u32 mark, u32 seq);
int xfrm_state_delete(struct xfrm_state *x);
int xfrm_state_flush(struct net *net, u8 proto, bool task_valid);
diff --git a/net/core/dev.c b/net/core/dev.c
index f083cbb..611e93c 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2911,9 +2911,10 @@ static struct sk_buff *validate_xmit_vlan(struct sk_buff
*skb,
return skb;
}
-static struct sk_buff *validate_xmit_skb(struct sk_buff *skb, struct
net_device *dev)
+static struct sk_buff *validate_xmit_skb(struct sk_buff *skb, struct
net_device *dev, int *ret)
{
netdev_features_t features;
+ int err = 0;
if (skb->next)
return skb;
@@ -2925,6 +2926,7 @@ static struct sk_buff *validate_xmit_skb(struct sk_buff
*skb, struct net_device
if (netif_needs_gso(skb, features)) {
struct sk_buff *segs;
+ struct sk_buff *skb2;
segs = skb_gso_segment(skb, features);
if (IS_ERR(segs)) {
@@ -2932,7 +2934,25 @@ static struct sk_buff *validate_xmit_skb(struct sk_buff
*skb, struct net_device
} else if (segs) {
consume_skb(skb);
skb = segs;
+
+ if (skb->hw_xfrm) {
+ do {
+ skb2 = segs->next;
+ segs->next = NULL;
+
+ err =
dev->xfrmdev_ops->xdo_dev_validate(segs);
+ if (!err)
+ segs->next = skb2;
+ else if (err != -EINPROGRESS)
+ kfree_skb(segs);
+ else if (skb == segs)
+ skb = skb2;
+
+ segs = skb2;
+ } while (segs);
+ }
}
+
} else {
if (skb_needs_linearize(skb, features) &&
__skb_linearize(skb))
@@ -2955,6 +2975,9 @@ static struct sk_buff *validate_xmit_skb(struct sk_buff
*skb, struct net_device
}
}
+ if ((err == -EINPROGRESS) && !skb)
+ *ret = NETDEV_TX_OK;
+
return skb;
out_kfree_skb:
@@ -2963,7 +2986,7 @@ out_null:
return NULL;
}
-struct sk_buff *validate_xmit_skb_list(struct sk_buff *skb, struct net_device
*dev)
+struct sk_buff *validate_xmit_skb_list(struct sk_buff *skb, struct net_device
*dev, int *ret)
{
struct sk_buff *next, *head = NULL, *tail;
@@ -2974,7 +2997,7 @@ struct sk_buff *validate_xmit_skb_list(struct sk_buff
*skb, struct net_device *d
/* in case skb wont be segmented, point to itself */
skb->prev = skb;
- skb = validate_xmit_skb(skb, dev);
+ skb = validate_xmit_skb(skb, dev, ret);
if (!skb)
continue;
@@ -3347,8 +3370,10 @@ static int __dev_queue_xmit(struct sk_buff *skb, void
*accel_priv)
if (__this_cpu_read(xmit_recursion) > RECURSION_LIMIT)
goto recursion_alert;
- skb = validate_xmit_skb(skb, dev);
- if (!skb)
+ skb = validate_xmit_skb(skb, dev, &rc);
+ if (!skb && rc == NETDEV_TX_OK)
+ goto out;
+ else if (!skb)
goto drop;
HARD_TX_LOCK(dev, txq, cpu);
@@ -3867,6 +3892,11 @@ static void net_tx_action(struct softirq_action *h)
}
}
}
+
+#ifdef CONFIG_XFRM
+ if (!skb_queue_empty(&sd->xfrm_backlog))
+ xfrm_dev_backlog(&sd->xfrm_backlog);
+#endif
}
#if (defined(CONFIG_BRIDGE) || defined(CONFIG_BRIDGE_MODULE)) && \
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 64878ef..0d75161 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -173,7 +173,7 @@ EXPORT_SYMBOL_GPL(ip_build_and_send_pkt);
static int ip_finish_output2(struct net *net, struct sock *sk, struct sk_buff
*skb)
{
- struct dst_entry *dst = skb_dst(skb);
+ struct dst_entry *dst = skb_dst(skb)->path;
struct rtable *rt = (struct rtable *)dst;
struct net_device *dev = dst->dev;
unsigned int hh_len = LL_RESERVED_SPACE(dev);
@@ -269,7 +269,9 @@ static int ip_finish_output(struct net *net, struct sock
*sk, struct sk_buff *sk
#if defined(CONFIG_NETFILTER) && defined(CONFIG_XFRM)
/* Policy lookup after SNAT yielded a new policy */
- if (skb_dst(skb)->xfrm) {
+ if (skb_dst(skb)->xfrm &&
+ !((skb_dst(skb)->dev->features & NETIF_F_ESP_OFFLOAD) ||
+ (skb_shinfo(skb)->gso_type & SKB_GSO_ESP))) {
IPCB(skb)->flags |= IPSKB_REROUTED;
return dst_output(net, sk, skb);
}
@@ -348,7 +350,7 @@ int ip_mc_output(struct net *net, struct sock *sk, struct
sk_buff *skb)
int ip_output(struct net *net, struct sock *sk, struct sk_buff *skb)
{
- struct net_device *dev = skb_dst(skb)->dev;
+ struct net_device *dev = skb_dst(skb)->path->dev;
IP_UPD_PO_STATS(net, IPSTATS_MIB_OUT, skb->len);
diff --git a/net/ipv4/xfrm4_output.c b/net/ipv4/xfrm4_output.c
index 7ee6518..14e42ba 100644
--- a/net/ipv4/xfrm4_output.c
+++ b/net/ipv4/xfrm4_output.c
@@ -29,7 +29,7 @@ static int xfrm4_tunnel_check_size(struct sk_buff *skb)
goto out;
mtu = dst_mtu(skb_dst(skb));
- if (skb->len > mtu) {
+ if ((!skb_is_gso(skb) && skb->len > mtu) || (skb_is_gso(skb) &&
skb_gso_network_seglen(skb) > ip_skb_dst_mtu(skb))) {
skb->protocol = htons(ETH_P_IP);
if (skb->sk)
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index 16bc83b..5b11424 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -157,7 +157,7 @@ int sch_direct_xmit(struct sk_buff *skb, struct Qdisc *q,
/* Note that we validate skb (GSO, checksum, ...) outside of locks */
if (validate)
- skb = validate_xmit_skb_list(skb, dev);
+ skb = validate_xmit_skb_list(skb, dev, &ret);
if (skb) {
HARD_TX_LOCK(dev, txq, smp_processor_id());
diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c
index ff4a91f..ad452e0 100644
--- a/net/xfrm/xfrm_output.c
+++ b/net/xfrm/xfrm_output.c
@@ -196,9 +196,21 @@ static int xfrm_output_gso(struct net *net, struct sock
*sk, struct sk_buff *skb
int xfrm_output(struct sock *sk, struct sk_buff *skb)
{
- struct net *net = dev_net(skb_dst(skb)->dev);
+ struct net_device *dev = skb_dst(skb)->dev;
+ struct net *net = dev_net(dev);
int err;
+ if ((dev->features & NETIF_F_ESP_OFFLOAD) || skb_is_gso(skb)) {
+ err = skb_dst(skb)->ops->local_out(net, skb->sk, skb);
+ if (unlikely(err != 1))
+ return err;
+
+ if (skb_is_gso(skb))
+ skb_shinfo(skb)->gso_type |= SKB_GSO_ESP;
+
+ return dev->xfrmdev_ops->xdo_dev_encap(skb);
+ }
+
if (skb_is_gso(skb))
return xfrm_output_gso(net, sk, skb);
--
1.9.1
