From: Pablo Neira Ayuso <pablo@netfilter.org>
To: netfilter-devel@vger.kernel.org
Cc: davem@davemloft.net, netdev@vger.kernel.org
Subject: [PATCH 04/15] ipvs: allow tunneling with gre encapsulation
Date: Mon, 8 Jul 2019 12:32:26 +0200 [thread overview]
Message-ID: <20190708103237.28061-5-pablo@netfilter.org> (raw)
In-Reply-To: <20190708103237.28061-1-pablo@netfilter.org>
From: Vadim Fedorenko <vfedorenko@yandex-team.ru>
windows real servers can handle gre tunnels, this patch allows
gre encapsulation with the tunneling method, thereby letting ipvs
be load balancer for windows-based services
Signed-off-by: Vadim Fedorenko <vfedorenko@yandex-team.ru>
Acked-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
include/uapi/linux/ip_vs.h | 1 +
net/netfilter/ipvs/ip_vs_ctl.c | 1 +
net/netfilter/ipvs/ip_vs_xmit.c | 66 +++++++++++++++++++++++++++++++++++++++--
3 files changed, 65 insertions(+), 3 deletions(-)
diff --git a/include/uapi/linux/ip_vs.h b/include/uapi/linux/ip_vs.h
index e4f18061a4fd..4102ddcb4e14 100644
--- a/include/uapi/linux/ip_vs.h
+++ b/include/uapi/linux/ip_vs.h
@@ -128,6 +128,7 @@
enum {
IP_VS_CONN_F_TUNNEL_TYPE_IPIP = 0, /* IPIP */
IP_VS_CONN_F_TUNNEL_TYPE_GUE, /* GUE */
+ IP_VS_CONN_F_TUNNEL_TYPE_GRE, /* GRE */
IP_VS_CONN_F_TUNNEL_TYPE_MAX,
};
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index 84384d896e29..998353bec74f 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -525,6 +525,7 @@ static void ip_vs_rs_hash(struct netns_ipvs *ipvs, struct ip_vs_dest *dest)
port = dest->tun_port;
break;
case IP_VS_CONN_F_TUNNEL_TYPE_IPIP:
+ case IP_VS_CONN_F_TUNNEL_TYPE_GRE:
port = 0;
break;
default:
diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c
index 71fc6d63a67f..9c464d24beec 100644
--- a/net/netfilter/ipvs/ip_vs_xmit.c
+++ b/net/netfilter/ipvs/ip_vs_xmit.c
@@ -29,6 +29,7 @@
#include <linux/tcp.h> /* for tcphdr */
#include <net/ip.h>
#include <net/gue.h>
+#include <net/gre.h>
#include <net/tcp.h> /* for csum_tcpudp_magic */
#include <net/udp.h>
#include <net/icmp.h> /* for icmp_send */
@@ -388,6 +389,12 @@ __ip_vs_get_out_rt(struct netns_ipvs *ipvs, int skb_af, struct sk_buff *skb,
IP_VS_TUNNEL_ENCAP_FLAG_REMCSUM) &&
skb->ip_summed == CHECKSUM_PARTIAL)
mtu -= GUE_PLEN_REMCSUM + GUE_LEN_PRIV;
+ } else if (dest->tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GRE) {
+ __be16 tflags = 0;
+
+ if (dest->tun_flags & IP_VS_TUNNEL_ENCAP_FLAG_CSUM)
+ tflags |= TUNNEL_CSUM;
+ mtu -= gre_calc_hlen(tflags);
}
if (mtu < 68) {
IP_VS_DBG_RL("%s(): mtu less than 68\n", __func__);
@@ -548,6 +555,12 @@ __ip_vs_get_out_rt_v6(struct netns_ipvs *ipvs, int skb_af, struct sk_buff *skb,
IP_VS_TUNNEL_ENCAP_FLAG_REMCSUM) &&
skb->ip_summed == CHECKSUM_PARTIAL)
mtu -= GUE_PLEN_REMCSUM + GUE_LEN_PRIV;
+ } else if (dest->tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GRE) {
+ __be16 tflags = 0;
+
+ if (dest->tun_flags & IP_VS_TUNNEL_ENCAP_FLAG_CSUM)
+ tflags |= TUNNEL_CSUM;
+ mtu -= gre_calc_hlen(tflags);
}
if (mtu < IPV6_MIN_MTU) {
IP_VS_DBG_RL("%s(): mtu less than %d\n", __func__,
@@ -1079,6 +1092,24 @@ ipvs_gue_encap(struct net *net, struct sk_buff *skb,
return 0;
}
+static void
+ipvs_gre_encap(struct net *net, struct sk_buff *skb,
+ struct ip_vs_conn *cp, __u8 *next_protocol)
+{
+ __be16 proto = *next_protocol == IPPROTO_IPIP ?
+ htons(ETH_P_IP) : htons(ETH_P_IPV6);
+ __be16 tflags = 0;
+ size_t hdrlen;
+
+ if (cp->dest->tun_flags & IP_VS_TUNNEL_ENCAP_FLAG_CSUM)
+ tflags |= TUNNEL_CSUM;
+
+ hdrlen = gre_calc_hlen(tflags);
+ gre_build_header(skb, hdrlen, tflags, proto, 0, 0);
+
+ *next_protocol = IPPROTO_GRE;
+}
+
/*
* IP Tunneling transmitter
*
@@ -1151,6 +1182,15 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
gue_hdrlen = sizeof(struct guehdr) + gue_optlen;
max_headroom += sizeof(struct udphdr) + gue_hdrlen;
+ } else if (tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GRE) {
+ size_t gre_hdrlen;
+ __be16 tflags = 0;
+
+ if (tun_flags & IP_VS_TUNNEL_ENCAP_FLAG_CSUM)
+ tflags |= TUNNEL_CSUM;
+ gre_hdrlen = gre_calc_hlen(tflags);
+
+ max_headroom += gre_hdrlen;
}
/* We only care about the df field if sysctl_pmtu_disc(ipvs) is set */
@@ -1172,6 +1212,11 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
skb->ip_summed == CHECKSUM_PARTIAL) {
gso_type |= SKB_GSO_TUNNEL_REMCSUM;
}
+ } else if (tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GRE) {
+ if (tun_flags & IP_VS_TUNNEL_ENCAP_FLAG_CSUM)
+ gso_type |= SKB_GSO_GRE_CSUM;
+ else
+ gso_type |= SKB_GSO_GRE;
}
if (iptunnel_handle_offloads(skb, gso_type))
@@ -1192,8 +1237,8 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
check = true;
udp_set_csum(!check, skb, saddr, cp->daddr.ip, skb->len);
- }
-
+ } else if (tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GRE)
+ ipvs_gre_encap(net, skb, cp, &next_protocol);
skb_push(skb, sizeof(struct iphdr));
skb_reset_network_header(skb);
@@ -1287,6 +1332,15 @@ ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
gue_hdrlen = sizeof(struct guehdr) + gue_optlen;
max_headroom += sizeof(struct udphdr) + gue_hdrlen;
+ } else if (tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GRE) {
+ size_t gre_hdrlen;
+ __be16 tflags = 0;
+
+ if (tun_flags & IP_VS_TUNNEL_ENCAP_FLAG_CSUM)
+ tflags |= TUNNEL_CSUM;
+ gre_hdrlen = gre_calc_hlen(tflags);
+
+ max_headroom += gre_hdrlen;
}
skb = ip_vs_prepare_tunneled_skb(skb, cp->af, max_headroom,
@@ -1306,6 +1360,11 @@ ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
skb->ip_summed == CHECKSUM_PARTIAL) {
gso_type |= SKB_GSO_TUNNEL_REMCSUM;
}
+ } else if (tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GRE) {
+ if (tun_flags & IP_VS_TUNNEL_ENCAP_FLAG_CSUM)
+ gso_type |= SKB_GSO_GRE_CSUM;
+ else
+ gso_type |= SKB_GSO_GRE;
}
if (iptunnel_handle_offloads(skb, gso_type))
@@ -1326,7 +1385,8 @@ ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
check = true;
udp6_set_csum(!check, skb, &saddr, &cp->daddr.in6, skb->len);
- }
+ } else if (tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GRE)
+ ipvs_gre_encap(net, skb, cp, &next_protocol);
skb_push(skb, sizeof(struct ipv6hdr));
skb_reset_network_header(skb);
--
2.11.0
next prev parent reply other threads:[~2019-07-08 10:33 UTC|newest]
Thread overview: 17+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-07-08 10:32 [PATCH 00/15] Netfilter/IPVS updates for net-next Pablo Neira Ayuso
2019-07-08 10:32 ` [PATCH 01/15] netfilter: rename nf_SYNPROXY.h to nf_synproxy.h Pablo Neira Ayuso
2019-07-08 10:32 ` [PATCH 02/15] netfilter: nf_log: Replace a seq_printf() call by seq_puts() in seq_show() Pablo Neira Ayuso
2019-07-08 10:32 ` [PATCH 03/15] netfilter: nf_queue: remove unused hook entries pointer Pablo Neira Ayuso
2019-07-08 10:32 ` Pablo Neira Ayuso [this message]
2019-07-08 10:32 ` [PATCH 05/15] netfilter: nf_tables: Add synproxy support Pablo Neira Ayuso
2019-07-08 10:32 ` [PATCH 06/15] ipvs: strip gre tunnel headers from icmp errors Pablo Neira Ayuso
2019-07-08 10:32 ` [PATCH 07/15] netfilter: nft_meta: move bridge meta keys into nft_meta_bridge Pablo Neira Ayuso
2019-07-08 10:32 ` [PATCH 08/15] netfilter: nft_meta_bridge: Remove the br_private.h header Pablo Neira Ayuso
2019-07-08 10:32 ` [PATCH 09/15] bridge: add br_vlan_get_pvid_rcu() Pablo Neira Ayuso
2019-07-08 10:32 ` [PATCH 10/15] netfilter: nft_meta_bridge: add NFT_META_BRI_IIFPVID support Pablo Neira Ayuso
2019-07-08 10:32 ` [PATCH 11/15] bridge: add br_vlan_get_proto() Pablo Neira Ayuso
2019-07-08 10:32 ` [PATCH 12/15] netfilter: nft_meta_bridge: Add NFT_META_BRI_IIFVPROTO support Pablo Neira Ayuso
2019-07-08 10:32 ` [PATCH 13/15] netfilter: nf_tables: add nft_expr_type_request_module() Pablo Neira Ayuso
2019-07-08 10:32 ` [PATCH 14/15] netfilter: nf_tables: __nft_expr_type_get() selects specific family type Pablo Neira Ayuso
2019-07-08 10:32 ` [PATCH 15/15] netfilter: nf_tables: force module load in case select_ops() returns -EAGAIN Pablo Neira Ayuso
2019-07-08 19:14 ` [PATCH 00/15] Netfilter/IPVS updates for net-next David Miller
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20190708103237.28061-5-pablo@netfilter.org \
--to=pablo@netfilter.org \
--cc=davem@davemloft.net \
--cc=netdev@vger.kernel.org \
--cc=netfilter-devel@vger.kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).