@@ -4272,6 +4272,7 @@ 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);
@@ -4286,12 +4287,6 @@ 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 */
@@ -4317,10 +4312,17 @@ 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;
@@ -4343,15 +4345,22 @@ 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;
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. [1] https://github.com/lxc/lxc/issues/4278 [2] https://github.com/kubernetes/kubernetes/blob/b722d017a34b300a2284b890448e5a605f21d01e/pkg/proxy/ipvs/proxier.go#L103 [3] https://github.com/moby/libnetwork/blob/3797618f9a38372e8107d8c06f6ae199e1133ae8/osl/namespace_linux.go#L682 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(-)