memcg: accounting for objects allocated for new netdevice

Creating a new netdevice allocates at least ~50Kb of memory for various
kernel objects, but only ~5Kb of them are accounted to memcg. As a result,
creating an unlimited number of netdevice inside a memcg-limited container
does not fall within memcg restrictions, consumes a significant part
of the host's memory, can cause global OOM and lead to random kills of
host processes.

The main consumers of non-accounted memory are:
 ~10Kb   80+ kernfs nodes
 ~6Kb    ipv6_add_dev() allocations
  6Kb    __register_sysctl_table() allocations
  4Kb    neigh_sysctl_register() allocations
  4Kb    __devinet_sysctl_register() allocations
  4Kb    __addrconf_sysctl_register() allocations

Accounting of these objects allows to increase the share of memcg-related
memory up to 60-70% (~38Kb accounted vs ~54Kb total for dummy netdevice
on typical VM with default Fedora 35 kernel) and this should be enough
to somehow protect the host from misuse inside container.

Other related objects are quite small and may not be taken into account
to minimize the expected performance degradation.

It should be separately mentonied ~300 bytes of percpu allocation
of struct ipstats_mib in snmp6_alloc_dev(), on huge multi-cpu nodes
it can become the main consumer of memory.

This patch does not enables kernfs accounting as it affects
other parts of the kernel and should be discussed separately.
However, even without kernfs, this patch significantly improves the
current situation and allows to take into account more than half
of all netdevice allocations.

Signed-off-by: Vasily Averin <vvs@openvz.org>
Acked-by: Luis Chamberlain <mcgrof@kernel.org>
Link: https://lore.kernel.org/r/354a0a5f-9ec3-a25c-3215-304eab2157bc@openvz.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c
index 5851c2a..c29f39c 100644 (file)
--- a/fs/proc/proc_sysctl.c
+++ b/fs/proc/proc_sysctl.c
@@ -1333,7 +1333,7 @@ struct ctl_table_header *__register_sysctl_table(
                nr_entries++;
 
        header = kzalloc(sizeof(struct ctl_table_header) +
-                        sizeof(struct ctl_node)*nr_entries, GFP_KERNEL);
+                        sizeof(struct ctl_node)*nr_entries, GFP_KERNEL_ACCOUNT);
        if (!header)
                return NULL;
 

diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index f64ebd0..47b6c1f 100644 (file)
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -3728,7 +3728,7 @@ int neigh_sysctl_register(struct net_device *dev, struct neigh_parms *p,
        char neigh_path[ sizeof("net//neigh/") + IFNAMSIZ + IFNAMSIZ ];
        char *p_name;
 
-       t = kmemdup(&neigh_sysctl_template, sizeof(*t), GFP_KERNEL);
+       t = kmemdup(&neigh_sysctl_template, sizeof(*t), GFP_KERNEL_ACCOUNT);
        if (!t)
                goto err;
 

diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index 53a6b14..89141ba 100644 (file)
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -2573,7 +2573,7 @@ static int __devinet_sysctl_register(struct net *net, char *dev_name,
        struct devinet_sysctl_table *t;
        char path[sizeof("net/ipv4/conf/") + IFNAMSIZ];
 
-       t = kmemdup(&devinet_sysctl, sizeof(*t), GFP_KERNEL);
+       t = kmemdup(&devinet_sysctl, sizeof(*t), GFP_KERNEL_ACCOUNT);
        if (!t)
                goto out;
 

diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 7dee662..cde242d 100644 (file)
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -335,7 +335,7 @@ static int snmp6_alloc_dev(struct inet6_dev *idev)
 {
        int i;
 
-       idev->stats.ipv6 = alloc_percpu(struct ipstats_mib);
+       idev->stats.ipv6 = alloc_percpu_gfp(struct ipstats_mib, GFP_KERNEL_ACCOUNT);
        if (!idev->stats.ipv6)
                goto err_ip;
 
@@ -351,7 +351,7 @@ static int snmp6_alloc_dev(struct inet6_dev *idev)
        if (!idev->stats.icmpv6dev)
                goto err_icmp;
        idev->stats.icmpv6msgdev = kzalloc(sizeof(struct icmpv6msg_mib_device),
-                                          GFP_KERNEL);
+                                          GFP_KERNEL_ACCOUNT);
        if (!idev->stats.icmpv6msgdev)
                goto err_icmpmsg;
 
@@ -375,7 +375,7 @@ static struct inet6_dev *ipv6_add_dev(struct net_device *dev)
        if (dev->mtu < IPV6_MIN_MTU && dev != blackhole_netdev)
                return ERR_PTR(-EINVAL);
 
-       ndev = kzalloc(sizeof(struct inet6_dev), GFP_KERNEL);
+       ndev = kzalloc(sizeof(*ndev), GFP_KERNEL_ACCOUNT);
        if (!ndev)
                return ERR_PTR(err);
 
@@ -7060,7 +7060,7 @@ static int __addrconf_sysctl_register(struct net *net, char *dev_name,
        struct ctl_table *table;
        char path[sizeof("net/ipv6/conf/") + IFNAMSIZ];
 
-       table = kmemdup(addrconf_sysctl, sizeof(addrconf_sysctl), GFP_KERNEL);
+       table = kmemdup(addrconf_sysctl, sizeof(addrconf_sysctl), GFP_KERNEL_ACCOUNT);
        if (!table)
                goto out;