[PATCH nf-next v5] netfilter: ipvs: Fix reuse connection if RS weight is 0

[PATCH nf-next v5] netfilter: ipvs: Fix reuse connection if RS weight is 0

[yangxingwu]

We are changing expire_nodest_conn to work even for reused connections when
conn_reuse_mode=0, just as what was done with commit dc7b3eb900aa ("ipvs:
Fix reuse connection if real server is dead").

For controlled and persistent connections, the new connection will get the
needed real server depending on the rules in ip_vs_check_template().

Fixes: d752c3645717 ("ipvs: allow rescheduling of new connections when port reuse is detected")
Co-developed-by: Chuanqi Liu <legend050709@qq.com>
Signed-off-by: Chuanqi Liu <legend050709@qq.com>
Signed-off-by: yangxingwu <xingwu.yang@gmail.com>
---
 Documentation/networking/ipvs-sysctl.rst | 3 +--
 net/netfilter/ipvs/ip_vs_core.c          | 8 ++++----
 2 files changed, 5 insertions(+), 6 deletions(-)

diff --git a/Documentation/networking/ipvs-sysctl.rst b/Documentation/networking/ipvs-sysctl.rst
index 2afccc63856e..1cfbf1add2fc 100644
--- a/Documentation/networking/ipvs-sysctl.rst
+++ b/Documentation/networking/ipvs-sysctl.rst
@@ -37,8 +37,7 @@ conn_reuse_mode - INTEGER
 
 	0: disable any special handling on port reuse. The new
 	connection will be delivered to the same real server that was
-	servicing the previous connection. This will effectively
-	disable expire_nodest_conn.
+	servicing the previous connection.
 
 	bit 1: enable rescheduling of new connections when it is safe.
 	That is, whenever expire_nodest_conn and for TCP sockets, when
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index 128690c512df..f9d65d2c8da8 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -1964,7 +1964,6 @@ ip_vs_in(struct netns_ipvs *ipvs, unsigned int hooknum, struct sk_buff *skb, int
 	struct ip_vs_proto_data *pd;
 	struct ip_vs_conn *cp;
 	int ret, pkts;
-	int conn_reuse_mode;
 	struct sock *sk;
 
 	/* Already marked as IPVS request or reply? */
@@ -2041,15 +2040,16 @@ ip_vs_in(struct netns_ipvs *ipvs, unsigned int hooknum, struct sk_buff *skb, int
 	cp = INDIRECT_CALL_1(pp->conn_in_get, ip_vs_conn_in_get_proto,
 			     ipvs, af, skb, &iph);
 
-	conn_reuse_mode = sysctl_conn_reuse_mode(ipvs);
-	if (conn_reuse_mode && !iph.fragoffs && is_new_conn(skb, &iph) && cp) {
+	if (!iph.fragoffs && is_new_conn(skb, &iph) && cp) {
 		bool old_ct = false, resched = false;
+		int conn_reuse_mode = sysctl_conn_reuse_mode(ipvs);
 
 		if (unlikely(sysctl_expire_nodest_conn(ipvs)) && cp->dest &&
 		    unlikely(!atomic_read(&cp->dest->weight))) {
 			resched = true;
 			old_ct = ip_vs_conn_uses_old_conntrack(cp, skb);
-		} else if (is_new_conn_expected(cp, conn_reuse_mode)) {
+		} else if (conn_reuse_mode &&
+			   is_new_conn_expected(cp, conn_reuse_mode)) {
 			old_ct = ip_vs_conn_uses_old_conntrack(cp, skb);
 			if (!atomic_read(&cp->n_control)) {
 				resched = true;
-- 
2.30.2

Re: [PATCH nf-next v5] netfilter: ipvs: Fix reuse connection if RS weight is 0

[Julian Anastasov]

	Hello,

On Mon, 1 Nov 2021, yangxingwu wrote:

> We are changing expire_nodest_conn to work even for reused connections when
> conn_reuse_mode=0, just as what was done with commit dc7b3eb900aa ("ipvs:
> Fix reuse connection if real server is dead").
> 
> For controlled and persistent connections, the new connection will get the
> needed real server depending on the rules in ip_vs_check_template().
> 
> Fixes: d752c3645717 ("ipvs: allow rescheduling of new connections when port reuse is detected")
> Co-developed-by: Chuanqi Liu <legend050709@qq.com>
> Signed-off-by: Chuanqi Liu <legend050709@qq.com>
> Signed-off-by: yangxingwu <xingwu.yang@gmail.com>

	Looks good to me, thanks!

Acked-by: Julian Anastasov <ja@ssi.bg>

> ---
>  Documentation/networking/ipvs-sysctl.rst | 3 +--
>  net/netfilter/ipvs/ip_vs_core.c          | 8 ++++----
>  2 files changed, 5 insertions(+), 6 deletions(-)
> 
> diff --git a/Documentation/networking/ipvs-sysctl.rst b/Documentation/networking/ipvs-sysctl.rst
> index 2afccc63856e..1cfbf1add2fc 100644
> --- a/Documentation/networking/ipvs-sysctl.rst
> +++ b/Documentation/networking/ipvs-sysctl.rst
> @@ -37,8 +37,7 @@ conn_reuse_mode - INTEGER
>  
>  	0: disable any special handling on port reuse. The new
>  	connection will be delivered to the same real server that was
> -	servicing the previous connection. This will effectively
> -	disable expire_nodest_conn.
> +	servicing the previous connection.
>  
>  	bit 1: enable rescheduling of new connections when it is safe.
>  	That is, whenever expire_nodest_conn and for TCP sockets, when
> diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
> index 128690c512df..f9d65d2c8da8 100644
> --- a/net/netfilter/ipvs/ip_vs_core.c
> +++ b/net/netfilter/ipvs/ip_vs_core.c
> @@ -1964,7 +1964,6 @@ ip_vs_in(struct netns_ipvs *ipvs, unsigned int hooknum, struct sk_buff *skb, int
>  	struct ip_vs_proto_data *pd;
>  	struct ip_vs_conn *cp;
>  	int ret, pkts;
> -	int conn_reuse_mode;
>  	struct sock *sk;
>  
>  	/* Already marked as IPVS request or reply? */
> @@ -2041,15 +2040,16 @@ ip_vs_in(struct netns_ipvs *ipvs, unsigned int hooknum, struct sk_buff *skb, int
>  	cp = INDIRECT_CALL_1(pp->conn_in_get, ip_vs_conn_in_get_proto,
>  			     ipvs, af, skb, &iph);
>  
> -	conn_reuse_mode = sysctl_conn_reuse_mode(ipvs);
> -	if (conn_reuse_mode && !iph.fragoffs && is_new_conn(skb, &iph) && cp) {
> +	if (!iph.fragoffs && is_new_conn(skb, &iph) && cp) {
>  		bool old_ct = false, resched = false;
> +		int conn_reuse_mode = sysctl_conn_reuse_mode(ipvs);
>  
>  		if (unlikely(sysctl_expire_nodest_conn(ipvs)) && cp->dest &&
>  		    unlikely(!atomic_read(&cp->dest->weight))) {
>  			resched = true;
>  			old_ct = ip_vs_conn_uses_old_conntrack(cp, skb);
> -		} else if (is_new_conn_expected(cp, conn_reuse_mode)) {
> +		} else if (conn_reuse_mode &&
> +			   is_new_conn_expected(cp, conn_reuse_mode)) {
>  			old_ct = ip_vs_conn_uses_old_conntrack(cp, skb);
>  			if (!atomic_read(&cp->n_control)) {
>  				resched = true;
> -- 
> 2.30.2

Regards

--
Julian Anastasov <ja@ssi.bg>

Re: [PATCH nf-next v5] netfilter: ipvs: Fix reuse connection if RS weight is 0

[yangxingwu]

Julian,

thanks for your help

A big problem has been fixed :)

On Tue, Nov 2, 2021 at 2:21 AM Julian Anastasov <ja@ssi.bg> wrote:
>
>
>         Hello,
>
> On Mon, 1 Nov 2021, yangxingwu wrote:
>
> > We are changing expire_nodest_conn to work even for reused connections when
> > conn_reuse_mode=0, just as what was done with commit dc7b3eb900aa ("ipvs:
> > Fix reuse connection if real server is dead").
> >
> > For controlled and persistent connections, the new connection will get the
> > needed real server depending on the rules in ip_vs_check_template().
> >
> > Fixes: d752c3645717 ("ipvs: allow rescheduling of new connections when port reuse is detected")
> > Co-developed-by: Chuanqi Liu <legend050709@qq.com>
> > Signed-off-by: Chuanqi Liu <legend050709@qq.com>
> > Signed-off-by: yangxingwu <xingwu.yang@gmail.com>
>
>         Looks good to me, thanks!
>
> Acked-by: Julian Anastasov <ja@ssi.bg>
>
> > ---
> >  Documentation/networking/ipvs-sysctl.rst | 3 +--
> >  net/netfilter/ipvs/ip_vs_core.c          | 8 ++++----
> >  2 files changed, 5 insertions(+), 6 deletions(-)
> >
> > diff --git a/Documentation/networking/ipvs-sysctl.rst b/Documentation/networking/ipvs-sysctl.rst
> > index 2afccc63856e..1cfbf1add2fc 100644
> > --- a/Documentation/networking/ipvs-sysctl.rst
> > +++ b/Documentation/networking/ipvs-sysctl.rst
> > @@ -37,8 +37,7 @@ conn_reuse_mode - INTEGER
> >
> >       0: disable any special handling on port reuse. The new
> >       connection will be delivered to the same real server that was
> > -     servicing the previous connection. This will effectively
> > -     disable expire_nodest_conn.
> > +     servicing the previous connection.
> >
> >       bit 1: enable rescheduling of new connections when it is safe.
> >       That is, whenever expire_nodest_conn and for TCP sockets, when
> > diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
> > index 128690c512df..f9d65d2c8da8 100644
> > --- a/net/netfilter/ipvs/ip_vs_core.c
> > +++ b/net/netfilter/ipvs/ip_vs_core.c
> > @@ -1964,7 +1964,6 @@ ip_vs_in(struct netns_ipvs *ipvs, unsigned int hooknum, struct sk_buff *skb, int
> >       struct ip_vs_proto_data *pd;
> >       struct ip_vs_conn *cp;
> >       int ret, pkts;
> > -     int conn_reuse_mode;
> >       struct sock *sk;
> >
> >       /* Already marked as IPVS request or reply? */
> > @@ -2041,15 +2040,16 @@ ip_vs_in(struct netns_ipvs *ipvs, unsigned int hooknum, struct sk_buff *skb, int
> >       cp = INDIRECT_CALL_1(pp->conn_in_get, ip_vs_conn_in_get_proto,
> >                            ipvs, af, skb, &iph);
> >
> > -     conn_reuse_mode = sysctl_conn_reuse_mode(ipvs);
> > -     if (conn_reuse_mode && !iph.fragoffs && is_new_conn(skb, &iph) && cp) {
> > +     if (!iph.fragoffs && is_new_conn(skb, &iph) && cp) {
> >               bool old_ct = false, resched = false;
> > +             int conn_reuse_mode = sysctl_conn_reuse_mode(ipvs);
> >
> >               if (unlikely(sysctl_expire_nodest_conn(ipvs)) && cp->dest &&
> >                   unlikely(!atomic_read(&cp->dest->weight))) {
> >                       resched = true;
> >                       old_ct = ip_vs_conn_uses_old_conntrack(cp, skb);
> > -             } else if (is_new_conn_expected(cp, conn_reuse_mode)) {
> > +             } else if (conn_reuse_mode &&
> > +                        is_new_conn_expected(cp, conn_reuse_mode)) {
> >                       old_ct = ip_vs_conn_uses_old_conntrack(cp, skb);
> >                       if (!atomic_read(&cp->n_control)) {
> >                               resched = true;
> > --
> > 2.30.2
>
> Regards
>
> --
> Julian Anastasov <ja@ssi.bg>

Re: [PATCH nf-next v5] netfilter: ipvs: Fix reuse connection if RS weight is 0

[Simon Horman]

On Mon, Nov 01, 2021 at 10:04:16AM +0800, yangxingwu wrote:
> We are changing expire_nodest_conn to work even for reused connections when
> conn_reuse_mode=0, just as what was done with commit dc7b3eb900aa ("ipvs:
> Fix reuse connection if real server is dead").
> 
> For controlled and persistent connections, the new connection will get the
> needed real server depending on the rules in ip_vs_check_template().
> 
> Fixes: d752c3645717 ("ipvs: allow rescheduling of new connections when port reuse is detected")
> Co-developed-by: Chuanqi Liu <legend050709@qq.com>
> Signed-off-by: Chuanqi Liu <legend050709@qq.com>
> Signed-off-by: yangxingwu <xingwu.yang@gmail.com>

Thanks, and sorry but I have a few nits.

> ---
>  Documentation/networking/ipvs-sysctl.rst | 3 +--
>  net/netfilter/ipvs/ip_vs_core.c          | 8 ++++----
>  2 files changed, 5 insertions(+), 6 deletions(-)
> 
> diff --git a/Documentation/networking/ipvs-sysctl.rst b/Documentation/networking/ipvs-sysctl.rst
> index 2afccc63856e..1cfbf1add2fc 100644
> --- a/Documentation/networking/ipvs-sysctl.rst
> +++ b/Documentation/networking/ipvs-sysctl.rst
> @@ -37,8 +37,7 @@ conn_reuse_mode - INTEGER
>  
>  	0: disable any special handling on port reuse. The new
>  	connection will be delivered to the same real server that was
> -	servicing the previous connection. This will effectively
> -	disable expire_nodest_conn.
> +	servicing the previous connection.

nit: s/servicing/service/

>  
>  	bit 1: enable rescheduling of new connections when it is safe.
>  	That is, whenever expire_nodest_conn and for TCP sockets, when
> diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
> index 128690c512df..f9d65d2c8da8 100644
> --- a/net/netfilter/ipvs/ip_vs_core.c
> +++ b/net/netfilter/ipvs/ip_vs_core.c
> @@ -1964,7 +1964,6 @@ ip_vs_in(struct netns_ipvs *ipvs, unsigned int hooknum, struct sk_buff *skb, int
>  	struct ip_vs_proto_data *pd;
>  	struct ip_vs_conn *cp;
>  	int ret, pkts;
> -	int conn_reuse_mode;
>  	struct sock *sk;
>  
>  	/* Already marked as IPVS request or reply? */
> @@ -2041,15 +2040,16 @@ ip_vs_in(struct netns_ipvs *ipvs, unsigned int hooknum, struct sk_buff *skb, int
>  	cp = INDIRECT_CALL_1(pp->conn_in_get, ip_vs_conn_in_get_proto,
>  			     ipvs, af, skb, &iph);
>  
> -	conn_reuse_mode = sysctl_conn_reuse_mode(ipvs);
> -	if (conn_reuse_mode && !iph.fragoffs && is_new_conn(skb, &iph) && cp) {
> +	if (!iph.fragoffs && is_new_conn(skb, &iph) && cp) {
>  		bool old_ct = false, resched = false;
> +		int conn_reuse_mode = sysctl_conn_reuse_mode(ipvs);

We should probably try to move towards reverse xmas tree, which
is preferred for Linux network code these days.

So could you move the conn_reuse_mode line above the bool line?

>  
>  		if (unlikely(sysctl_expire_nodest_conn(ipvs)) && cp->dest &&
>  		    unlikely(!atomic_read(&cp->dest->weight))) {
>  			resched = true;
>  			old_ct = ip_vs_conn_uses_old_conntrack(cp, skb);
> -		} else if (is_new_conn_expected(cp, conn_reuse_mode)) {
> +		} else if (conn_reuse_mode &&
> +			   is_new_conn_expected(cp, conn_reuse_mode)) {
>  			old_ct = ip_vs_conn_uses_old_conntrack(cp, skb);
>  			if (!atomic_read(&cp->n_control)) {
>  				resched = true;
> -- 
> 2.30.2
> 

Re: [PATCH nf-next v5] netfilter: ipvs: Fix reuse connection if RS weight is 0

[Simon Horman]

On Wed, Nov 03, 2021 at 07:40:46PM +0800, yangxingwu wrote:
> hello Simon
> 
> I delete the "This will effectively disable expire_nodest_conn" section
> from doc, and the others remain untouched. The following is how it looks
> like after modification:
> 
> 0: disable any special handling on port reuse. The new
> connection will be delivered to the same real server that was
> servicing the previous connection.
> 
> Simon, pls help to check if it's necessary to replace servicing with
> service.

Sorry, my mistake. No need to replace servicing with service.

> And I will move the conn_reuse_mode line above the bool line
> 
> On Tue, Nov 2, 2021 at 2:21 AM Julian Anastasov <ja@ssi.bg> wrote:
> 
> >
> >         Hello,
> >
> > On Mon, 1 Nov 2021, yangxingwu wrote:
> >
> > > We are changing expire_nodest_conn to work even for reused connections
> > when
> > > conn_reuse_mode=0, just as what was done with commit dc7b3eb900aa ("ipvs:
> > > Fix reuse connection if real server is dead").
> > >
> > > For controlled and persistent connections, the new connection will get
> > the
> > > needed real server depending on the rules in ip_vs_check_template().
> > >
> > > Fixes: d752c3645717 ("ipvs: allow rescheduling of new connections when
> > port reuse is detected")
> > > Co-developed-by: Chuanqi Liu <legend050709@qq.com>
> > > Signed-off-by: Chuanqi Liu <legend050709@qq.com>
> > > Signed-off-by: yangxingwu <xingwu.yang@gmail.com>
> >
> >         Looks good to me, thanks!
> >
> > Acked-by: Julian Anastasov <ja@ssi.bg>
> >
> > > ---
> > >  Documentation/networking/ipvs-sysctl.rst | 3 +--
> > >  net/netfilter/ipvs/ip_vs_core.c          | 8 ++++----
> > >  2 files changed, 5 insertions(+), 6 deletions(-)
> > >
> > > diff --git a/Documentation/networking/ipvs-sysctl.rst
> > b/Documentation/networking/ipvs-sysctl.rst
> > > index 2afccc63856e..1cfbf1add2fc 100644
> > > --- a/Documentation/networking/ipvs-sysctl.rst
> > > +++ b/Documentation/networking/ipvs-sysctl.rst
> > > @@ -37,8 +37,7 @@ conn_reuse_mode - INTEGER
> > >
> > >       0: disable any special handling on port reuse. The new
> > >       connection will be delivered to the same real server that was
> > > -     servicing the previous connection. This will effectively
> > > -     disable expire_nodest_conn.
> > > +     servicing the previous connection.
> > >
> > >       bit 1: enable rescheduling of new connections when it is safe.
> > >       That is, whenever expire_nodest_conn and for TCP sockets, when
> > > diff --git a/net/netfilter/ipvs/ip_vs_core.c
> > b/net/netfilter/ipvs/ip_vs_core.c
> > > index 128690c512df..f9d65d2c8da8 100644
> > > --- a/net/netfilter/ipvs/ip_vs_core.c
> > > +++ b/net/netfilter/ipvs/ip_vs_core.c
> > > @@ -1964,7 +1964,6 @@ ip_vs_in(struct netns_ipvs *ipvs, unsigned int
> > hooknum, struct sk_buff *skb, int
> > >       struct ip_vs_proto_data *pd;
> > >       struct ip_vs_conn *cp;
> > >       int ret, pkts;
> > > -     int conn_reuse_mode;
> > >       struct sock *sk;
> > >
> > >       /* Already marked as IPVS request or reply? */
> > > @@ -2041,15 +2040,16 @@ ip_vs_in(struct netns_ipvs *ipvs, unsigned int
> > hooknum, struct sk_buff *skb, int
> > >       cp = INDIRECT_CALL_1(pp->conn_in_get, ip_vs_conn_in_get_proto,
> > >                            ipvs, af, skb, &iph);
> > >
> > > -     conn_reuse_mode = sysctl_conn_reuse_mode(ipvs);
> > > -     if (conn_reuse_mode && !iph.fragoffs && is_new_conn(skb, &iph) &&
> > cp) {
> > > +     if (!iph.fragoffs && is_new_conn(skb, &iph) && cp) {
> > >               bool old_ct = false, resched = false;
> > > +             int conn_reuse_mode = sysctl_conn_reuse_mode(ipvs);
> > >
> > >               if (unlikely(sysctl_expire_nodest_conn(ipvs)) && cp->dest
> > &&
> > >                   unlikely(!atomic_read(&cp->dest->weight))) {
> > >                       resched = true;
> > >                       old_ct = ip_vs_conn_uses_old_conntrack(cp, skb);
> > > -             } else if (is_new_conn_expected(cp, conn_reuse_mode)) {
> > > +             } else if (conn_reuse_mode &&
> > > +                        is_new_conn_expected(cp, conn_reuse_mode)) {
> > >                       old_ct = ip_vs_conn_uses_old_conntrack(cp, skb);
> > >                       if (!atomic_read(&cp->n_control)) {
> > >                               resched = true;
> > > --
> > > 2.30.2
> >
> > Regards
> >
> > --
> > Julian Anastasov <ja@ssi.bg>
> >