Cc: Julian Anastasov <[email protected]>
Cc: Simon Horman <[email protected]>
Cc: Pablo Neira Ayuso <[email protected]>
Cc: Jozsef Kadlecsik <[email protected]>
Cc: Florian Westphal <[email protected]>
Suggested-by: Julian Anastasov <[email protected]>
Signed-off-by: Alexander Mikhalitsyn <[email protected]>
---
net/netfilter/ipvs/ip_vs_ctl.c | 12 +++++++-----
1 file changed, 7 insertions(+), 5 deletions(-)
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index 143a341bbc0a..daa62b8b2dd1 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();
@@ -146,8 +148,8 @@ static void update_defense_level(struct netns_ipvs *ipvs)
case 1:
if (nomem) {
ipvs->drop_rate = ipvs->drop_counter
- = ipvs->sysctl_amemthresh /
- (ipvs->sysctl_amemthresh-availmem);
+ = amemthresh /
+ (amemthresh-availmem);
ipvs->sysctl_drop_packet = 2;
} else {
ipvs->drop_rate = 0;
@@ -156,8 +158,8 @@ static void update_defense_level(struct netns_ipvs *ipvs)
case 2:
if (nomem) {
ipvs->drop_rate = ipvs->drop_counter
- = ipvs->sysctl_amemthresh /
- (ipvs->sysctl_amemthresh-availmem);
+ = amemthresh /
+ (amemthresh-availmem);
} else {
ipvs->drop_rate = 0;
ipvs->sysctl_drop_packet = 1;
--
2.34.1
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 <[email protected]>
Cc: Christian Brauner <[email protected]>
Cc: Julian Anastasov <[email protected]>
Cc: Simon Horman <[email protected]>
Cc: Pablo Neira Ayuso <[email protected]>
Cc: Jozsef Kadlecsik <[email protected]>
Cc: Florian Westphal <[email protected]>
Signed-off-by: Alexander Mikhalitsyn <[email protected]>
---
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 daa62b8b2dd1..f84f091626ef 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -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;
--
2.34.1
Hello,
On Thu, 18 Apr 2024, Alexander Mikhalitsyn wrote:
> Cc: Julian Anastasov <[email protected]>
> Cc: Simon Horman <[email protected]>
> Cc: Pablo Neira Ayuso <[email protected]>
> Cc: Jozsef Kadlecsik <[email protected]>
> Cc: Florian Westphal <[email protected]>
> Suggested-by: Julian Anastasov <[email protected]>
> Signed-off-by: Alexander Mikhalitsyn <[email protected]>
> ---
> net/netfilter/ipvs/ip_vs_ctl.c | 12 +++++++-----
> 1 file changed, 7 insertions(+), 5 deletions(-)
>
> diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
> index 143a341bbc0a..daa62b8b2dd1 100644
> --- a/net/netfilter/ipvs/ip_vs_ctl.c
> +++ b/net/netfilter/ipvs/ip_vs_ctl.c
> @@ -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();
>
> @@ -146,8 +148,8 @@ static void update_defense_level(struct netns_ipvs *ipvs)
> case 1:
> if (nomem) {
> ipvs->drop_rate = ipvs->drop_counter
> - = ipvs->sysctl_amemthresh /
> - (ipvs->sysctl_amemthresh-availmem);
> + = amemthresh /
> + (amemthresh-availmem);
Thanks, both patches look ok except that the old styling
is showing warnings for this patch:
scripts/checkpatch.pl --strict /tmp/file1.patch
It would be great if you silence them somehow in v3...
BTW, est_cpulist is masked with current->cpus_mask of the
sysctl writer process, if that is of any help. That is why I skipped
it but lets keep it read-only for now...
> ipvs->sysctl_drop_packet = 2;
> } else {
> ipvs->drop_rate = 0;
> @@ -156,8 +158,8 @@ static void update_defense_level(struct netns_ipvs *ipvs)
> case 2:
> if (nomem) {
> ipvs->drop_rate = ipvs->drop_counter
> - = ipvs->sysctl_amemthresh /
> - (ipvs->sysctl_amemthresh-availmem);
> + = amemthresh /
> + (amemthresh-availmem);
> } else {
> ipvs->drop_rate = 0;
> ipvs->sysctl_drop_packet = 1;
Regards
--
Julian Anastasov <[email protected]>
On Thu, Apr 18, 2024 at 3:23 PM Julian Anastasov <[email protected]> wrote:
>
>
> Hello,
Dear Julian,
>
> On Thu, 18 Apr 2024, Alexander Mikhalitsyn wrote:
>
> > Cc: Julian Anastasov <[email protected]>
> > Cc: Simon Horman <[email protected]>
> > Cc: Pablo Neira Ayuso <[email protected]>
> > Cc: Jozsef Kadlecsik <[email protected]>
> > Cc: Florian Westphal <[email protected]>
> > Suggested-by: Julian Anastasov <[email protected]>
> > Signed-off-by: Alexander Mikhalitsyn <[email protected]>
> > ---
> > net/netfilter/ipvs/ip_vs_ctl.c | 12 +++++++-----
> > 1 file changed, 7 insertions(+), 5 deletions(-)
> >
> > diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
> > index 143a341bbc0a..daa62b8b2dd1 100644
> > --- a/net/netfilter/ipvs/ip_vs_ctl.c
> > +++ b/net/netfilter/ipvs/ip_vs_ctl.c
>
> > @@ -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();
> >
> > @@ -146,8 +148,8 @@ static void update_defense_level(struct netns_ipvs *ipvs)
> > case 1:
> > if (nomem) {
> > ipvs->drop_rate = ipvs->drop_counter
> > - = ipvs->sysctl_amemthresh /
> > - (ipvs->sysctl_amemthresh-availmem);
> > + = amemthresh /
> > + (amemthresh-availmem);
>
> Thanks, both patches look ok except that the old styling
> is showing warnings for this patch:
>
> scripts/checkpatch.pl --strict /tmp/file1.patch
>
> It would be great if you silence them somehow in v3...
Yeah, I have fixed this in v3. Also, I had to split multiple
assignments into different
lines because of:
>CHECK: multiple assignments should be avoided
Now everything looks fine.
>
> BTW, est_cpulist is masked with current->cpus_mask of the
> sysctl writer process, if that is of any help. That is why I skipped
> it but lets keep it read-only for now...
That's a good point! Probably I'm too conservative ;-)
>
> > ipvs->sysctl_drop_packet = 2;
> > } else {
> > ipvs->drop_rate = 0;
> > @@ -156,8 +158,8 @@ static void update_defense_level(struct netns_ipvs *ipvs)
> > case 2:
> > if (nomem) {
> > ipvs->drop_rate = ipvs->drop_counter
> > - = ipvs->sysctl_amemthresh /
> > - (ipvs->sysctl_amemthresh-availmem);
> > + = amemthresh /
> > + (amemthresh-availmem);
> > } else {
> > ipvs->drop_rate = 0;
> > ipvs->sysctl_drop_packet = 1;
>
> Regards
Kind regards,
Alex
>
> --
> Julian Anastasov <[email protected]>
>