* [PATCH 2/5] ipvs: generalize app registration in netns
2012-07-23 23:28 [GIT PULL nf-next] IPVS Simon Horman
2012-07-23 23:28 ` [PATCH 1/5] ipvs: ip_vs_ftp depends on nf_conntrack_ftp helper Simon Horman
@ 2012-07-23 23:28 ` Simon Horman
2012-07-23 23:28 ` [PATCH 3/5] ipvs: fixed sparse warning Simon Horman
` (3 subsequent siblings)
5 siblings, 0 replies; 10+ messages in thread
From: Simon Horman @ 2012-07-23 23:28 UTC (permalink / raw)
To: Pablo Neira Ayuso
Cc: lvs-devel, netdev, netfilter-devel, Wensong Zhang,
Julian Anastasov, Simon Horman
From: Julian Anastasov <ja@ssi.bg>
Get rid of the ftp_app pointer and allow applications
to be registered without adding fields in the netns_ipvs structure.
v2: fix coding style as suggested by Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
include/net/ip_vs.h | 5 ++--
net/netfilter/ipvs/ip_vs_app.c | 58 ++++++++++++++++++++++++++++++------------
net/netfilter/ipvs/ip_vs_ftp.c | 21 ++++-----------
3 files changed, 49 insertions(+), 35 deletions(-)
diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index 95374d1..4b8f18f 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -808,8 +808,6 @@ struct netns_ipvs {
struct list_head rs_table[IP_VS_RTAB_SIZE];
/* ip_vs_app */
struct list_head app_list;
- /* ip_vs_ftp */
- struct ip_vs_app *ftp_app;
/* ip_vs_proto */
#define IP_VS_PROTO_TAB_SIZE 32 /* must be power of 2 */
struct ip_vs_proto_data *proto_data_table[IP_VS_PROTO_TAB_SIZE];
@@ -1179,7 +1177,8 @@ extern void ip_vs_service_net_cleanup(struct net *net);
* (from ip_vs_app.c)
*/
#define IP_VS_APP_MAX_PORTS 8
-extern int register_ip_vs_app(struct net *net, struct ip_vs_app *app);
+extern struct ip_vs_app *register_ip_vs_app(struct net *net,
+ struct ip_vs_app *app);
extern void unregister_ip_vs_app(struct net *net, struct ip_vs_app *app);
extern int ip_vs_bind_app(struct ip_vs_conn *cp, struct ip_vs_protocol *pp);
extern void ip_vs_unbind_app(struct ip_vs_conn *cp);
diff --git a/net/netfilter/ipvs/ip_vs_app.c b/net/netfilter/ipvs/ip_vs_app.c
index 64f9e8f..9713e6e 100644
--- a/net/netfilter/ipvs/ip_vs_app.c
+++ b/net/netfilter/ipvs/ip_vs_app.c
@@ -180,22 +180,38 @@ register_ip_vs_app_inc(struct net *net, struct ip_vs_app *app, __u16 proto,
}
-/*
- * ip_vs_app registration routine
- */
-int register_ip_vs_app(struct net *net, struct ip_vs_app *app)
+/* Register application for netns */
+struct ip_vs_app *register_ip_vs_app(struct net *net, struct ip_vs_app *app)
{
struct netns_ipvs *ipvs = net_ipvs(net);
- /* increase the module use count */
- ip_vs_use_count_inc();
+ struct ip_vs_app *a;
+ int err = 0;
+
+ if (!ipvs)
+ return ERR_PTR(-ENOENT);
mutex_lock(&__ip_vs_app_mutex);
- list_add(&app->a_list, &ipvs->app_list);
+ list_for_each_entry(a, &ipvs->app_list, a_list) {
+ if (!strcmp(app->name, a->name)) {
+ err = -EEXIST;
+ goto out_unlock;
+ }
+ }
+ a = kmemdup(app, sizeof(*app), GFP_KERNEL);
+ if (!a) {
+ err = -ENOMEM;
+ goto out_unlock;
+ }
+ INIT_LIST_HEAD(&a->incs_list);
+ list_add(&a->a_list, &ipvs->app_list);
+ /* increase the module use count */
+ ip_vs_use_count_inc();
+out_unlock:
mutex_unlock(&__ip_vs_app_mutex);
- return 0;
+ return err ? ERR_PTR(err) : a;
}
@@ -205,20 +221,29 @@ int register_ip_vs_app(struct net *net, struct ip_vs_app *app)
*/
void unregister_ip_vs_app(struct net *net, struct ip_vs_app *app)
{
- struct ip_vs_app *inc, *nxt;
+ struct netns_ipvs *ipvs = net_ipvs(net);
+ struct ip_vs_app *a, *anxt, *inc, *nxt;
+
+ if (!ipvs)
+ return;
mutex_lock(&__ip_vs_app_mutex);
- list_for_each_entry_safe(inc, nxt, &app->incs_list, a_list) {
- ip_vs_app_inc_release(net, inc);
- }
+ list_for_each_entry_safe(a, anxt, &ipvs->app_list, a_list) {
+ if (app && strcmp(app->name, a->name))
+ continue;
+ list_for_each_entry_safe(inc, nxt, &a->incs_list, a_list) {
+ ip_vs_app_inc_release(net, inc);
+ }
- list_del(&app->a_list);
+ list_del(&a->a_list);
+ kfree(a);
- mutex_unlock(&__ip_vs_app_mutex);
+ /* decrease the module use count */
+ ip_vs_use_count_dec();
+ }
- /* decrease the module use count */
- ip_vs_use_count_dec();
+ mutex_unlock(&__ip_vs_app_mutex);
}
@@ -586,5 +611,6 @@ int __net_init ip_vs_app_net_init(struct net *net)
void __net_exit ip_vs_app_net_cleanup(struct net *net)
{
+ unregister_ip_vs_app(net, NULL /* all */);
proc_net_remove(net, "ip_vs_app");
}
diff --git a/net/netfilter/ipvs/ip_vs_ftp.c b/net/netfilter/ipvs/ip_vs_ftp.c
index b20b29c..ad70b7e 100644
--- a/net/netfilter/ipvs/ip_vs_ftp.c
+++ b/net/netfilter/ipvs/ip_vs_ftp.c
@@ -441,16 +441,10 @@ static int __net_init __ip_vs_ftp_init(struct net *net)
if (!ipvs)
return -ENOENT;
- app = kmemdup(&ip_vs_ftp, sizeof(struct ip_vs_app), GFP_KERNEL);
- if (!app)
- return -ENOMEM;
- INIT_LIST_HEAD(&app->a_list);
- INIT_LIST_HEAD(&app->incs_list);
- ipvs->ftp_app = app;
- ret = register_ip_vs_app(net, app);
- if (ret)
- goto err_exit;
+ app = register_ip_vs_app(net, &ip_vs_ftp);
+ if (IS_ERR(app))
+ return PTR_ERR(app);
for (i = 0; i < ports_count; i++) {
if (!ports[i])
@@ -464,9 +458,7 @@ static int __net_init __ip_vs_ftp_init(struct net *net)
return 0;
err_unreg:
- unregister_ip_vs_app(net, app);
-err_exit:
- kfree(ipvs->ftp_app);
+ unregister_ip_vs_app(net, &ip_vs_ftp);
return ret;
}
/*
@@ -474,10 +466,7 @@ err_exit:
*/
static void __ip_vs_ftp_exit(struct net *net)
{
- struct netns_ipvs *ipvs = net_ipvs(net);
-
- unregister_ip_vs_app(net, ipvs->ftp_app);
- kfree(ipvs->ftp_app);
+ unregister_ip_vs_app(net, &ip_vs_ftp);
}
static struct pernet_operations ip_vs_ftp_ops = {
--
1.7.10.2.484.gcd07cc5
^ permalink raw reply related [flat|nested] 10+ messages in thread* [PATCH 4/5] ipvs: implement passive PMTUD for IPIP packets
2012-07-23 23:28 [GIT PULL nf-next] IPVS Simon Horman
` (2 preceding siblings ...)
2012-07-23 23:28 ` [PATCH 3/5] ipvs: fixed sparse warning Simon Horman
@ 2012-07-23 23:28 ` Simon Horman
2012-07-23 23:29 ` [PATCH 5/5] ipvs: add pmtu_disc option to disable IP DF for TUN packets Simon Horman
2012-07-23 23:35 ` [GIT PULL nf-next] IPVS David Miller
5 siblings, 0 replies; 10+ messages in thread
From: Simon Horman @ 2012-07-23 23:28 UTC (permalink / raw)
To: Pablo Neira Ayuso
Cc: lvs-devel, netdev, netfilter-devel, Wensong Zhang,
Julian Anastasov, Simon Horman
From: Julian Anastasov <ja@ssi.bg>
IPVS is missing the logic to update PMTU in routing
for its IPIP packets. We monitor the dst_mtu and can return
FRAG_NEEDED messages but if the tunneled packets get ICMP
error we can not rely on other traffic to save the lowest
MTU.
The following patch adds ICMP handling for IPIP
packets in incoming direction, from some remote host to
our local IP used as saddr in the outer header. By this
way we can forward any related ICMP traffic if it is for IPVS
TUN connection. For the special case of PMTUD we update the
routing and if client requested DF we can forward the
error.
To properly update the routing we have to bind
the cached route (dest->dst_cache) to the selected saddr
because ipv4_update_pmtu uses saddr for dst lookup.
Add IP_VS_RT_MODE_CONNECT flag to force such binding with
second route.
Update ip_vs_tunnel_xmit to provide IP_VS_RT_MODE_CONNECT
and change the code to copy DF. For now we prefer not to
force PMTU discovery (outer DF=1) because we don't have
configuration option to enable or disable PMTUD. As we
do not keep any packets to resend, we prefer not to
play games with packets without DF bit because the sender
is not informed when they are rejected.
Also, change ops->update_pmtu to be called only
for local clients because there is no point to update
MTU for input routes, in our case skb->dst->dev is lo.
It seems the code is copied from ipip.c where the skb
dst points to tunnel device.
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
net/netfilter/ipvs/ip_vs_core.c | 76 +++++++++++++++++++++++++++++++++++++--
net/netfilter/ipvs/ip_vs_xmit.c | 79 ++++++++++++++++++++++++++++-------------
2 files changed, 128 insertions(+), 27 deletions(-)
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index b54ecce..58918e2 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -1303,7 +1303,8 @@ ip_vs_in_icmp(struct sk_buff *skb, int *related, unsigned int hooknum)
struct ip_vs_conn *cp;
struct ip_vs_protocol *pp;
struct ip_vs_proto_data *pd;
- unsigned int offset, ihl, verdict;
+ unsigned int offset, offset2, ihl, verdict;
+ bool ipip;
*related = 1;
@@ -1345,6 +1346,21 @@ ip_vs_in_icmp(struct sk_buff *skb, int *related, unsigned int hooknum)
net = skb_net(skb);
+ /* Special case for errors for IPIP packets */
+ ipip = false;
+ if (cih->protocol == IPPROTO_IPIP) {
+ if (unlikely(cih->frag_off & htons(IP_OFFSET)))
+ return NF_ACCEPT;
+ /* Error for our IPIP must arrive at LOCAL_IN */
+ if (!(skb_rtable(skb)->rt_flags & RTCF_LOCAL))
+ return NF_ACCEPT;
+ offset += cih->ihl * 4;
+ cih = skb_header_pointer(skb, offset, sizeof(_ciph), &_ciph);
+ if (cih == NULL)
+ return NF_ACCEPT; /* The packet looks wrong, ignore */
+ ipip = true;
+ }
+
pd = ip_vs_proto_data_get(net, cih->protocol);
if (!pd)
return NF_ACCEPT;
@@ -1358,11 +1374,14 @@ ip_vs_in_icmp(struct sk_buff *skb, int *related, unsigned int hooknum)
IP_VS_DBG_PKT(11, AF_INET, pp, skb, offset,
"Checking incoming ICMP for");
+ offset2 = offset;
offset += cih->ihl * 4;
ip_vs_fill_iphdr(AF_INET, cih, &ciph);
- /* The embedded headers contain source and dest in reverse order */
- cp = pp->conn_in_get(AF_INET, skb, &ciph, offset, 1);
+ /* The embedded headers contain source and dest in reverse order.
+ * For IPIP this is error for request, not for reply.
+ */
+ cp = pp->conn_in_get(AF_INET, skb, &ciph, offset, ipip ? 0 : 1);
if (!cp)
return NF_ACCEPT;
@@ -1376,6 +1395,57 @@ ip_vs_in_icmp(struct sk_buff *skb, int *related, unsigned int hooknum)
goto out;
}
+ if (ipip) {
+ __be32 info = ic->un.gateway;
+
+ /* Update the MTU */
+ if (ic->type == ICMP_DEST_UNREACH &&
+ ic->code == ICMP_FRAG_NEEDED) {
+ struct ip_vs_dest *dest = cp->dest;
+ u32 mtu = ntohs(ic->un.frag.mtu);
+
+ /* Strip outer IP and ICMP, go to IPIP header */
+ __skb_pull(skb, ihl + sizeof(_icmph));
+ offset2 -= ihl + sizeof(_icmph);
+ skb_reset_network_header(skb);
+ IP_VS_DBG(12, "ICMP for IPIP %pI4->%pI4: mtu=%u\n",
+ &ip_hdr(skb)->saddr, &ip_hdr(skb)->daddr, mtu);
+ rcu_read_lock();
+ ipv4_update_pmtu(skb, dev_net(skb->dev),
+ mtu, 0, 0, 0, 0);
+ rcu_read_unlock();
+ /* Client uses PMTUD? */
+ if (!(cih->frag_off & htons(IP_DF)))
+ goto ignore_ipip;
+ /* Prefer the resulting PMTU */
+ if (dest) {
+ spin_lock(&dest->dst_lock);
+ if (dest->dst_cache)
+ mtu = dst_mtu(dest->dst_cache);
+ spin_unlock(&dest->dst_lock);
+ }
+ if (mtu > 68 + sizeof(struct iphdr))
+ mtu -= sizeof(struct iphdr);
+ info = htonl(mtu);
+ }
+ /* Strip outer IP, ICMP and IPIP, go to IP header of
+ * original request.
+ */
+ __skb_pull(skb, offset2);
+ skb_reset_network_header(skb);
+ IP_VS_DBG(12, "Sending ICMP for %pI4->%pI4: t=%u, c=%u, i=%u\n",
+ &ip_hdr(skb)->saddr, &ip_hdr(skb)->daddr,
+ ic->type, ic->code, ntohl(info));
+ icmp_send(skb, ic->type, ic->code, info);
+ /* ICMP can be shorter but anyways, account it */
+ ip_vs_out_stats(cp, skb);
+
+ignore_ipip:
+ consume_skb(skb);
+ verdict = NF_STOLEN;
+ goto out;
+ }
+
/* do the statistics and put it back */
ip_vs_in_stats(cp, skb);
if (IPPROTO_TCP == cih->protocol || IPPROTO_UDP == cih->protocol)
diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c
index 65b616a..c2275ba 100644
--- a/net/netfilter/ipvs/ip_vs_xmit.c
+++ b/net/netfilter/ipvs/ip_vs_xmit.c
@@ -49,6 +49,7 @@ enum {
IP_VS_RT_MODE_RDR = 4, /* Allow redirect from remote daddr to
* local
*/
+ IP_VS_RT_MODE_CONNECT = 8, /* Always bind route to saddr */
};
/*
@@ -84,6 +85,42 @@ __ip_vs_dst_check(struct ip_vs_dest *dest, u32 rtos)
return dst;
}
+/* Get route to daddr, update *saddr, optionally bind route to saddr */
+static struct rtable *do_output_route4(struct net *net, __be32 daddr,
+ u32 rtos, int rt_mode, __be32 *saddr)
+{
+ struct flowi4 fl4;
+ struct rtable *rt;
+ int loop = 0;
+
+ memset(&fl4, 0, sizeof(fl4));
+ fl4.daddr = daddr;
+ fl4.saddr = (rt_mode & IP_VS_RT_MODE_CONNECT) ? *saddr : 0;
+ fl4.flowi4_tos = rtos;
+
+retry:
+ rt = ip_route_output_key(net, &fl4);
+ if (IS_ERR(rt)) {
+ /* Invalid saddr ? */
+ if (PTR_ERR(rt) == -EINVAL && *saddr &&
+ rt_mode & IP_VS_RT_MODE_CONNECT && !loop) {
+ *saddr = 0;
+ flowi4_update_output(&fl4, 0, rtos, daddr, 0);
+ goto retry;
+ }
+ IP_VS_DBG_RL("ip_route_output error, dest: %pI4\n", &daddr);
+ return NULL;
+ } else if (!*saddr && rt_mode & IP_VS_RT_MODE_CONNECT && fl4.saddr) {
+ ip_rt_put(rt);
+ *saddr = fl4.saddr;
+ flowi4_update_output(&fl4, 0, rtos, daddr, fl4.saddr);
+ loop++;
+ goto retry;
+ }
+ *saddr = fl4.saddr;
+ return rt;
+}
+
/* Get route to destination or remote server */
static struct rtable *
__ip_vs_get_out_rt(struct sk_buff *skb, struct ip_vs_dest *dest,
@@ -98,20 +135,13 @@ __ip_vs_get_out_rt(struct sk_buff *skb, struct ip_vs_dest *dest,
spin_lock(&dest->dst_lock);
if (!(rt = (struct rtable *)
__ip_vs_dst_check(dest, rtos))) {
- struct flowi4 fl4;
-
- memset(&fl4, 0, sizeof(fl4));
- fl4.daddr = dest->addr.ip;
- fl4.flowi4_tos = rtos;
- rt = ip_route_output_key(net, &fl4);
- if (IS_ERR(rt)) {
+ rt = do_output_route4(net, dest->addr.ip, rtos,
+ rt_mode, &dest->dst_saddr.ip);
+ if (!rt) {
spin_unlock(&dest->dst_lock);
- IP_VS_DBG_RL("ip_route_output error, dest: %pI4\n",
- &dest->addr.ip);
return NULL;
}
__ip_vs_dst_set(dest, rtos, dst_clone(&rt->dst), 0);
- dest->dst_saddr.ip = fl4.saddr;
IP_VS_DBG(10, "new dst %pI4, src %pI4, refcnt=%d, "
"rtos=%X\n",
&dest->addr.ip, &dest->dst_saddr.ip,
@@ -122,19 +152,17 @@ __ip_vs_get_out_rt(struct sk_buff *skb, struct ip_vs_dest *dest,
*ret_saddr = dest->dst_saddr.ip;
spin_unlock(&dest->dst_lock);
} else {
- struct flowi4 fl4;
+ __be32 saddr = htonl(INADDR_ANY);
- memset(&fl4, 0, sizeof(fl4));
- fl4.daddr = daddr;
- fl4.flowi4_tos = rtos;
- rt = ip_route_output_key(net, &fl4);
- if (IS_ERR(rt)) {
- IP_VS_DBG_RL("ip_route_output error, dest: %pI4\n",
- &daddr);
+ /* For such unconfigured boxes avoid many route lookups
+ * for performance reasons because we do not remember saddr
+ */
+ rt_mode &= ~IP_VS_RT_MODE_CONNECT;
+ rt = do_output_route4(net, daddr, rtos, rt_mode, &saddr);
+ if (!rt)
return NULL;
- }
if (ret_saddr)
- *ret_saddr = fl4.saddr;
+ *ret_saddr = saddr;
}
local = rt->rt_flags & RTCF_LOCAL;
@@ -331,6 +359,7 @@ ip_vs_dst_reset(struct ip_vs_dest *dest)
old_dst = dest->dst_cache;
dest->dst_cache = NULL;
dst_release(old_dst);
+ dest->dst_saddr.ip = 0;
}
#define IP_VS_XMIT_TUNNEL(skb, cp) \
@@ -771,7 +800,7 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
struct net_device *tdev; /* Device to other host */
struct iphdr *old_iph = ip_hdr(skb);
u8 tos = old_iph->tos;
- __be16 df = old_iph->frag_off;
+ __be16 df;
struct iphdr *iph; /* Our new IP header */
unsigned int max_headroom; /* The extra header space needed */
int mtu;
@@ -781,7 +810,8 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
if (!(rt = __ip_vs_get_out_rt(skb, cp->dest, cp->daddr.ip,
RT_TOS(tos), IP_VS_RT_MODE_LOCAL |
- IP_VS_RT_MODE_NON_LOCAL,
+ IP_VS_RT_MODE_NON_LOCAL |
+ IP_VS_RT_MODE_CONNECT,
&saddr)))
goto tx_error_icmp;
if (rt->rt_flags & RTCF_LOCAL) {
@@ -796,10 +826,11 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
IP_VS_DBG_RL("%s(): mtu less than 68\n", __func__);
goto tx_error_put;
}
- if (skb_dst(skb))
+ if (rt_is_output_route(skb_rtable(skb)))
skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, skb, mtu);
- df |= (old_iph->frag_off & htons(IP_DF));
+ /* Copy DF, reset fragment offset and MF */
+ df = old_iph->frag_off & htons(IP_DF);
if ((old_iph->frag_off & htons(IP_DF) &&
mtu < ntohs(old_iph->tot_len) && !skb_is_gso(skb))) {
--
1.7.10.2.484.gcd07cc5
^ permalink raw reply related [flat|nested] 10+ messages in thread* [PATCH 5/5] ipvs: add pmtu_disc option to disable IP DF for TUN packets
2012-07-23 23:28 [GIT PULL nf-next] IPVS Simon Horman
` (3 preceding siblings ...)
2012-07-23 23:28 ` [PATCH 4/5] ipvs: implement passive PMTUD for IPIP packets Simon Horman
@ 2012-07-23 23:29 ` Simon Horman
2012-07-23 23:35 ` [GIT PULL nf-next] IPVS David Miller
5 siblings, 0 replies; 10+ messages in thread
From: Simon Horman @ 2012-07-23 23:29 UTC (permalink / raw)
To: Pablo Neira Ayuso
Cc: lvs-devel, netdev, netfilter-devel, Wensong Zhang,
Julian Anastasov, Simon Horman
From: Julian Anastasov <ja@ssi.bg>
Disabling PMTU discovery can increase the output packet
rate but some users have enough resources and prefer to fragment
than to drop traffic. By default, we copy the DF bit but if
pmtu_disc is disabled we do not send FRAG_NEEDED messages anymore.
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
include/net/ip_vs.h | 11 +++++++++++
net/netfilter/ipvs/ip_vs_ctl.c | 8 ++++++++
net/netfilter/ipvs/ip_vs_xmit.c | 6 +++---
3 files changed, 22 insertions(+), 3 deletions(-)
diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index 4b8f18f..ee75ccd 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -888,6 +888,7 @@ struct netns_ipvs {
unsigned int sysctl_sync_refresh_period;
int sysctl_sync_retries;
int sysctl_nat_icmp_send;
+ int sysctl_pmtu_disc;
/* ip_vs_lblc */
int sysctl_lblc_expiration;
@@ -974,6 +975,11 @@ static inline int sysctl_sync_sock_size(struct netns_ipvs *ipvs)
return ipvs->sysctl_sync_sock_size;
}
+static inline int sysctl_pmtu_disc(struct netns_ipvs *ipvs)
+{
+ return ipvs->sysctl_pmtu_disc;
+}
+
#else
static inline int sysctl_sync_threshold(struct netns_ipvs *ipvs)
@@ -1016,6 +1022,11 @@ static inline int sysctl_sync_sock_size(struct netns_ipvs *ipvs)
return 0;
}
+static inline int sysctl_pmtu_disc(struct netns_ipvs *ipvs)
+{
+ return 1;
+}
+
#endif
/*
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index d6d5cca..03d3fc6 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -1801,6 +1801,12 @@ static struct ctl_table vs_vars[] = {
.mode = 0644,
.proc_handler = proc_dointvec,
},
+ {
+ .procname = "pmtu_disc",
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec,
+ },
#ifdef CONFIG_IP_VS_DEBUG
{
.procname = "debug_level",
@@ -3726,6 +3732,8 @@ static int __net_init ip_vs_control_net_init_sysctl(struct net *net)
ipvs->sysctl_sync_retries = clamp_t(int, DEFAULT_SYNC_RETRIES, 0, 3);
tbl[idx++].data = &ipvs->sysctl_sync_retries;
tbl[idx++].data = &ipvs->sysctl_nat_icmp_send;
+ ipvs->sysctl_pmtu_disc = 1;
+ tbl[idx++].data = &ipvs->sysctl_pmtu_disc;
ipvs->sysctl_hdr = register_net_sysctl(net, "net/ipv4/vs", tbl);
diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c
index c2275ba..543a554 100644
--- a/net/netfilter/ipvs/ip_vs_xmit.c
+++ b/net/netfilter/ipvs/ip_vs_xmit.c
@@ -795,6 +795,7 @@ int
ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
struct ip_vs_protocol *pp)
{
+ struct netns_ipvs *ipvs = net_ipvs(skb_net(skb));
struct rtable *rt; /* Route to the other host */
__be32 saddr; /* Source for tunnel */
struct net_device *tdev; /* Device to other host */
@@ -830,10 +831,9 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, skb, mtu);
/* Copy DF, reset fragment offset and MF */
- df = old_iph->frag_off & htons(IP_DF);
+ df = sysctl_pmtu_disc(ipvs) ? old_iph->frag_off & htons(IP_DF) : 0;
- if ((old_iph->frag_off & htons(IP_DF) &&
- mtu < ntohs(old_iph->tot_len) && !skb_is_gso(skb))) {
+ if (df && mtu < ntohs(old_iph->tot_len) && !skb_is_gso(skb)) {
icmp_send(skb, ICMP_DEST_UNREACH,ICMP_FRAG_NEEDED, htonl(mtu));
IP_VS_DBG_RL("%s(): frag needed\n", __func__);
goto tx_error_put;
--
1.7.10.2.484.gcd07cc5
^ permalink raw reply related [flat|nested] 10+ messages in thread