[PATCH net-next v3 1/2] ipvs: add READ_ONCE barrier for ipvs->sysctl_amemthresh

[PATCH net-next v3 1/2] ipvs: add READ_ONCE barrier for ipvs->sysctl_amemthresh

[Alexander Mikhalitsyn]

Cc: Julian Anastasov <ja@ssi.bg>
Cc: Simon Horman <horms@verge.net.au>
Cc: Pablo Neira Ayuso <pablo@netfilter.org>
Cc: Jozsef Kadlecsik <kadlec@netfilter.org>
Cc: Florian Westphal <fw@strlen.de>
Suggested-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Alexander Mikhalitsyn <aleksandr.mikhalitsyn@canonical.com>
---
 net/netfilter/ipvs/ip_vs_ctl.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index 143a341bbc0a..32be24f0d4e4 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -94,6 +94,7 @@ static void update_defense_level(struct netns_ipvs *ipvs)
 {
 	struct sysinfo i;
 	int availmem;
+	int amemthresh;
 	int nomem;
 	int to_change = -1;
 
@@ -105,7 +106,8 @@ static void update_defense_level(struct netns_ipvs *ipvs)
 	/* si_swapinfo(&i); */
 	/* availmem = availmem - (i.totalswap - i.freeswap); */
 
-	nomem = (availmem < ipvs->sysctl_amemthresh);
+	amemthresh = max(READ_ONCE(ipvs->sysctl_amemthresh), 0);
+	nomem = (availmem < amemthresh);
 
 	local_bh_disable();
 
@@ -145,9 +147,8 @@ static void update_defense_level(struct netns_ipvs *ipvs)
 		break;
 	case 1:
 		if (nomem) {
-			ipvs->drop_rate = ipvs->drop_counter
-				= ipvs->sysctl_amemthresh /
-				(ipvs->sysctl_amemthresh-availmem);
+			ipvs->drop_counter = amemthresh / (amemthresh - availmem);
+			ipvs->drop_rate = ipvs->drop_counter;
 			ipvs->sysctl_drop_packet = 2;
 		} else {
 			ipvs->drop_rate = 0;
@@ -155,9 +156,8 @@ static void update_defense_level(struct netns_ipvs *ipvs)
 		break;
 	case 2:
 		if (nomem) {
-			ipvs->drop_rate = ipvs->drop_counter
-				= ipvs->sysctl_amemthresh /
-				(ipvs->sysctl_amemthresh-availmem);
+			ipvs->drop_counter = amemthresh / (amemthresh - availmem);
+			ipvs->drop_rate = ipvs->drop_counter;
 		} else {
 			ipvs->drop_rate = 0;
 			ipvs->sysctl_drop_packet = 1;
-- 
2.34.1

[PATCH net-next v3 2/2] ipvs: allow some sysctls in non-init user namespaces

[Alexander Mikhalitsyn]

Let's make all IPVS sysctls writtable even when
network namespace is owned by non-initial user namespace.

Let's make a few sysctls to be read-only for non-privileged users:
- sync_qlen_max
- sync_sock_size
- run_estimation
- est_cpulist
- est_nice

I'm trying to be conservative with this to prevent
introducing any security issues in there. Maybe,
we can allow more sysctls to be writable, but let's
do this on-demand and when we see real use-case.

This patch is motivated by user request in the LXC
project [1]. Having this can help with running some
Kubernetes [2] or Docker Swarm [3] workloads inside the system
containers.

Link: https://github.com/lxc/lxc/issues/4278 [1]
Link: https://github.com/kubernetes/kubernetes/blob/b722d017a34b300a2284b890448e5a605f21d01e/pkg/proxy/ipvs/proxier.go#L103 [2]
Link: https://github.com/moby/libnetwork/blob/3797618f9a38372e8107d8c06f6ae199e1133ae8/osl/namespace_linux.go#L682 [3]

Cc: Stéphane Graber <stgraber@stgraber.org>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Julian Anastasov <ja@ssi.bg>
Cc: Simon Horman <horms@verge.net.au>
Cc: Pablo Neira Ayuso <pablo@netfilter.org>
Cc: Jozsef Kadlecsik <kadlec@netfilter.org>
Cc: Florian Westphal <fw@strlen.de>
Signed-off-by: Alexander Mikhalitsyn <aleksandr.mikhalitsyn@canonical.com>
---
 net/netfilter/ipvs/ip_vs_ctl.c | 21 +++++++++++++++------
 1 file changed, 15 insertions(+), 6 deletions(-)

diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index 32be24f0d4e4..c3ba71aa2654 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -4270,6 +4270,7 @@ static int __net_init ip_vs_control_net_init_sysctl(struct netns_ipvs *ipvs)
 	struct ctl_table *tbl;
 	int idx, ret;
 	size_t ctl_table_size = ARRAY_SIZE(vs_vars);
+	bool unpriv = net->user_ns != &init_user_ns;
 
 	atomic_set(&ipvs->dropentry, 0);
 	spin_lock_init(&ipvs->dropentry_lock);
@@ -4284,12 +4285,6 @@ static int __net_init ip_vs_control_net_init_sysctl(struct netns_ipvs *ipvs)
 		tbl = kmemdup(vs_vars, sizeof(vs_vars), GFP_KERNEL);
 		if (tbl == NULL)
 			return -ENOMEM;
-
-		/* Don't export sysctls to unprivileged users */
-		if (net->user_ns != &init_user_ns) {
-			tbl[0].procname = NULL;
-			ctl_table_size = 0;
-		}
 	} else
 		tbl = vs_vars;
 	/* Initialize sysctl defaults */
@@ -4315,10 +4310,17 @@ static int __net_init ip_vs_control_net_init_sysctl(struct netns_ipvs *ipvs)
 	ipvs->sysctl_sync_ports = 1;
 	tbl[idx++].data = &ipvs->sysctl_sync_ports;
 	tbl[idx++].data = &ipvs->sysctl_sync_persist_mode;
+
 	ipvs->sysctl_sync_qlen_max = nr_free_buffer_pages() / 32;
+	if (unpriv)
+		tbl[idx].mode = 0444;
 	tbl[idx++].data = &ipvs->sysctl_sync_qlen_max;
+
 	ipvs->sysctl_sync_sock_size = 0;
+	if (unpriv)
+		tbl[idx].mode = 0444;
 	tbl[idx++].data = &ipvs->sysctl_sync_sock_size;
+
 	tbl[idx++].data = &ipvs->sysctl_cache_bypass;
 	tbl[idx++].data = &ipvs->sysctl_expire_nodest_conn;
 	tbl[idx++].data = &ipvs->sysctl_sloppy_tcp;
@@ -4341,15 +4343,22 @@ static int __net_init ip_vs_control_net_init_sysctl(struct netns_ipvs *ipvs)
 	tbl[idx++].data = &ipvs->sysctl_conn_reuse_mode;
 	tbl[idx++].data = &ipvs->sysctl_schedule_icmp;
 	tbl[idx++].data = &ipvs->sysctl_ignore_tunneled;
+
 	ipvs->sysctl_run_estimation = 1;
+	if (unpriv)
+		tbl[idx].mode = 0444;
 	tbl[idx].extra2 = ipvs;
 	tbl[idx++].data = &ipvs->sysctl_run_estimation;
 
 	ipvs->est_cpulist_valid = 0;
+	if (unpriv)
+		tbl[idx].mode = 0444;
 	tbl[idx].extra2 = ipvs;
 	tbl[idx++].data = &ipvs->sysctl_est_cpulist;
 
 	ipvs->sysctl_est_nice = IPVS_EST_NICE;
+	if (unpriv)
+		tbl[idx].mode = 0444;
 	tbl[idx].extra2 = ipvs;
 	tbl[idx++].data = &ipvs->sysctl_est_nice;
 
-- 
2.34.1

Re: [PATCH net-next v3 1/2] ipvs: add READ_ONCE barrier for ipvs->sysctl_amemthresh

[Julian Anastasov]

	Hello,

On Thu, 18 Apr 2024, Alexander Mikhalitsyn wrote:

> Cc: Julian Anastasov <ja@ssi.bg>
> Cc: Simon Horman <horms@verge.net.au>
> Cc: Pablo Neira Ayuso <pablo@netfilter.org>
> Cc: Jozsef Kadlecsik <kadlec@netfilter.org>
> Cc: Florian Westphal <fw@strlen.de>
> Suggested-by: Julian Anastasov <ja@ssi.bg>
> Signed-off-by: Alexander Mikhalitsyn <aleksandr.mikhalitsyn@canonical.com>

	Looks good to me, thanks!

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

> ---
>  net/netfilter/ipvs/ip_vs_ctl.c | 14 +++++++-------
>  1 file changed, 7 insertions(+), 7 deletions(-)
> 
> diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
> index 143a341bbc0a..32be24f0d4e4 100644
> --- a/net/netfilter/ipvs/ip_vs_ctl.c
> +++ b/net/netfilter/ipvs/ip_vs_ctl.c
> @@ -94,6 +94,7 @@ static void update_defense_level(struct netns_ipvs *ipvs)
>  {
>  	struct sysinfo i;
>  	int availmem;
> +	int amemthresh;
>  	int nomem;
>  	int to_change = -1;
>  
> @@ -105,7 +106,8 @@ static void update_defense_level(struct netns_ipvs *ipvs)
>  	/* si_swapinfo(&i); */
>  	/* availmem = availmem - (i.totalswap - i.freeswap); */
>  
> -	nomem = (availmem < ipvs->sysctl_amemthresh);
> +	amemthresh = max(READ_ONCE(ipvs->sysctl_amemthresh), 0);
> +	nomem = (availmem < amemthresh);
>  
>  	local_bh_disable();
>  
> @@ -145,9 +147,8 @@ static void update_defense_level(struct netns_ipvs *ipvs)
>  		break;
>  	case 1:
>  		if (nomem) {
> -			ipvs->drop_rate = ipvs->drop_counter
> -				= ipvs->sysctl_amemthresh /
> -				(ipvs->sysctl_amemthresh-availmem);
> +			ipvs->drop_counter = amemthresh / (amemthresh - availmem);
> +			ipvs->drop_rate = ipvs->drop_counter;
>  			ipvs->sysctl_drop_packet = 2;
>  		} else {
>  			ipvs->drop_rate = 0;
> @@ -155,9 +156,8 @@ static void update_defense_level(struct netns_ipvs *ipvs)
>  		break;
>  	case 2:
>  		if (nomem) {
> -			ipvs->drop_rate = ipvs->drop_counter
> -				= ipvs->sysctl_amemthresh /
> -				(ipvs->sysctl_amemthresh-availmem);
> +			ipvs->drop_counter = amemthresh / (amemthresh - availmem);
> +			ipvs->drop_rate = ipvs->drop_counter;
>  		} else {
>  			ipvs->drop_rate = 0;
>  			ipvs->sysctl_drop_packet = 1;
> -- 
> 2.34.1

Regards

--
Julian Anastasov <ja@ssi.bg>

Re: [PATCH net-next v3 2/2] ipvs: allow some sysctls in non-init user namespaces

[Julian Anastasov]

[-- Attachment #1: Type: text/plain, Size: 4068 bytes --]


	Hello,

On Thu, 18 Apr 2024, Alexander Mikhalitsyn wrote:

> Let's make all IPVS sysctls writtable even when
> network namespace is owned by non-initial user namespace.
> 
> Let's make a few sysctls to be read-only for non-privileged users:
> - sync_qlen_max
> - sync_sock_size
> - run_estimation
> - est_cpulist
> - est_nice
> 
> I'm trying to be conservative with this to prevent
> introducing any security issues in there. Maybe,
> we can allow more sysctls to be writable, but let's
> do this on-demand and when we see real use-case.
> 
> This patch is motivated by user request in the LXC
> project [1]. Having this can help with running some
> Kubernetes [2] or Docker Swarm [3] workloads inside the system
> containers.
> 
> Link: https://github.com/lxc/lxc/issues/4278 [1]
> Link: https://github.com/kubernetes/kubernetes/blob/b722d017a34b300a2284b890448e5a605f21d01e/pkg/proxy/ipvs/proxier.go#L103 [2]
> Link: https://github.com/moby/libnetwork/blob/3797618f9a38372e8107d8c06f6ae199e1133ae8/osl/namespace_linux.go#L682 [3]
> 
> Cc: Stéphane Graber <stgraber@stgraber.org>
> Cc: Christian Brauner <brauner@kernel.org>
> Cc: Julian Anastasov <ja@ssi.bg>
> Cc: Simon Horman <horms@verge.net.au>
> Cc: Pablo Neira Ayuso <pablo@netfilter.org>
> Cc: Jozsef Kadlecsik <kadlec@netfilter.org>
> Cc: Florian Westphal <fw@strlen.de>
> Signed-off-by: Alexander Mikhalitsyn <aleksandr.mikhalitsyn@canonical.com>

	Looks good to me, thanks!

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

> ---
>  net/netfilter/ipvs/ip_vs_ctl.c | 21 +++++++++++++++------
>  1 file changed, 15 insertions(+), 6 deletions(-)
> 
> diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
> index 32be24f0d4e4..c3ba71aa2654 100644
> --- a/net/netfilter/ipvs/ip_vs_ctl.c
> +++ b/net/netfilter/ipvs/ip_vs_ctl.c
> @@ -4270,6 +4270,7 @@ static int __net_init ip_vs_control_net_init_sysctl(struct netns_ipvs *ipvs)
>  	struct ctl_table *tbl;
>  	int idx, ret;
>  	size_t ctl_table_size = ARRAY_SIZE(vs_vars);
> +	bool unpriv = net->user_ns != &init_user_ns;
>  
>  	atomic_set(&ipvs->dropentry, 0);
>  	spin_lock_init(&ipvs->dropentry_lock);
> @@ -4284,12 +4285,6 @@ static int __net_init ip_vs_control_net_init_sysctl(struct netns_ipvs *ipvs)
>  		tbl = kmemdup(vs_vars, sizeof(vs_vars), GFP_KERNEL);
>  		if (tbl == NULL)
>  			return -ENOMEM;
> -
> -		/* Don't export sysctls to unprivileged users */
> -		if (net->user_ns != &init_user_ns) {
> -			tbl[0].procname = NULL;
> -			ctl_table_size = 0;
> -		}
>  	} else
>  		tbl = vs_vars;
>  	/* Initialize sysctl defaults */
> @@ -4315,10 +4310,17 @@ static int __net_init ip_vs_control_net_init_sysctl(struct netns_ipvs *ipvs)
>  	ipvs->sysctl_sync_ports = 1;
>  	tbl[idx++].data = &ipvs->sysctl_sync_ports;
>  	tbl[idx++].data = &ipvs->sysctl_sync_persist_mode;
> +
>  	ipvs->sysctl_sync_qlen_max = nr_free_buffer_pages() / 32;
> +	if (unpriv)
> +		tbl[idx].mode = 0444;
>  	tbl[idx++].data = &ipvs->sysctl_sync_qlen_max;
> +
>  	ipvs->sysctl_sync_sock_size = 0;
> +	if (unpriv)
> +		tbl[idx].mode = 0444;
>  	tbl[idx++].data = &ipvs->sysctl_sync_sock_size;
> +
>  	tbl[idx++].data = &ipvs->sysctl_cache_bypass;
>  	tbl[idx++].data = &ipvs->sysctl_expire_nodest_conn;
>  	tbl[idx++].data = &ipvs->sysctl_sloppy_tcp;
> @@ -4341,15 +4343,22 @@ static int __net_init ip_vs_control_net_init_sysctl(struct netns_ipvs *ipvs)
>  	tbl[idx++].data = &ipvs->sysctl_conn_reuse_mode;
>  	tbl[idx++].data = &ipvs->sysctl_schedule_icmp;
>  	tbl[idx++].data = &ipvs->sysctl_ignore_tunneled;
> +
>  	ipvs->sysctl_run_estimation = 1;
> +	if (unpriv)
> +		tbl[idx].mode = 0444;
>  	tbl[idx].extra2 = ipvs;
>  	tbl[idx++].data = &ipvs->sysctl_run_estimation;
>  
>  	ipvs->est_cpulist_valid = 0;
> +	if (unpriv)
> +		tbl[idx].mode = 0444;
>  	tbl[idx].extra2 = ipvs;
>  	tbl[idx++].data = &ipvs->sysctl_est_cpulist;
>  
>  	ipvs->sysctl_est_nice = IPVS_EST_NICE;
> +	if (unpriv)
> +		tbl[idx].mode = 0444;
>  	tbl[idx].extra2 = ipvs;
>  	tbl[idx++].data = &ipvs->sysctl_est_nice;
>  
> -- 
> 2.34.1
> 
> 

Regards

--
Julian Anastasov <ja@ssi.bg>

Re: [PATCH net-next v3 1/2] ipvs: add READ_ONCE barrier for ipvs->sysctl_amemthresh

[Aleksandr Mikhalitsyn]

On Sun, Apr 21, 2024 at 1:06 PM Julian Anastasov <ja@ssi.bg> wrote:
>
>
>         Hello,

Dear Julian,

Thanks a lot for the fast review and suggestions!

Kind regards,
Alex

>
> On Thu, 18 Apr 2024, Alexander Mikhalitsyn wrote:
>
> > Cc: Julian Anastasov <ja@ssi.bg>
> > Cc: Simon Horman <horms@verge.net.au>
> > Cc: Pablo Neira Ayuso <pablo@netfilter.org>
> > Cc: Jozsef Kadlecsik <kadlec@netfilter.org>
> > Cc: Florian Westphal <fw@strlen.de>
> > Suggested-by: Julian Anastasov <ja@ssi.bg>
> > Signed-off-by: Alexander Mikhalitsyn <aleksandr.mikhalitsyn@canonical.com>
>
>         Looks good to me, thanks!
>
> Acked-by: Julian Anastasov <ja@ssi.bg>
>
> > ---
> >  net/netfilter/ipvs/ip_vs_ctl.c | 14 +++++++-------
> >  1 file changed, 7 insertions(+), 7 deletions(-)
> >
> > diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
> > index 143a341bbc0a..32be24f0d4e4 100644
> > --- a/net/netfilter/ipvs/ip_vs_ctl.c
> > +++ b/net/netfilter/ipvs/ip_vs_ctl.c
> > @@ -94,6 +94,7 @@ static void update_defense_level(struct netns_ipvs *ipvs)
> >  {
> >       struct sysinfo i;
> >       int availmem;
> > +     int amemthresh;
> >       int nomem;
> >       int to_change = -1;
> >
> > @@ -105,7 +106,8 @@ static void update_defense_level(struct netns_ipvs *ipvs)
> >       /* si_swapinfo(&i); */
> >       /* availmem = availmem - (i.totalswap - i.freeswap); */
> >
> > -     nomem = (availmem < ipvs->sysctl_amemthresh);
> > +     amemthresh = max(READ_ONCE(ipvs->sysctl_amemthresh), 0);
> > +     nomem = (availmem < amemthresh);
> >
> >       local_bh_disable();
> >
> > @@ -145,9 +147,8 @@ static void update_defense_level(struct netns_ipvs *ipvs)
> >               break;
> >       case 1:
> >               if (nomem) {
> > -                     ipvs->drop_rate = ipvs->drop_counter
> > -                             = ipvs->sysctl_amemthresh /
> > -                             (ipvs->sysctl_amemthresh-availmem);
> > +                     ipvs->drop_counter = amemthresh / (amemthresh - availmem);
> > +                     ipvs->drop_rate = ipvs->drop_counter;
> >                       ipvs->sysctl_drop_packet = 2;
> >               } else {
> >                       ipvs->drop_rate = 0;
> > @@ -155,9 +156,8 @@ static void update_defense_level(struct netns_ipvs *ipvs)
> >               break;
> >       case 2:
> >               if (nomem) {
> > -                     ipvs->drop_rate = ipvs->drop_counter
> > -                             = ipvs->sysctl_amemthresh /
> > -                             (ipvs->sysctl_amemthresh-availmem);
> > +                     ipvs->drop_counter = amemthresh / (amemthresh - availmem);
> > +                     ipvs->drop_rate = ipvs->drop_counter;
> >               } else {
> >                       ipvs->drop_rate = 0;
> >                       ipvs->sysctl_drop_packet = 1;
> > --
> > 2.34.1
>
> Regards
>
> --
> Julian Anastasov <ja@ssi.bg>
>