| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <a5e09e93-106d-0527-5b1e-48dbf3b48b4e@virtuozzo.com>
Date: Mon, 28 Feb 2022 10:17:16 +0300
From: Vasily Averin <vvs@...tuozzo.com>
To: Roman Gushchin <roman.gushchin@...ux.dev>,
Linux MM <linux-mm@...ck.org>
Cc: netdev@...r.kernel.org, "David S. Miller" <davem@...emloft.net>,
Jakub Kicinski <kuba@...nel.org>, Tejun Heo <tj@...nel.org>,
Greg Kroah-Hartman <gregkh@...uxfoundation.org>,
Eric Dumazet <edumazet@...gle.com>,
Luis Chamberlain <mcgrof@...nel.org>,
Kees Cook <keescook@...omium.org>,
Hideaki YOSHIFUJI <yoshfuji@...ux-ipv6.org>,
David Ahern <dsahern@...nel.org>, linux-kernel@...r.kernel.org,
kernel@...nvz.org
Subject: [PATCH RFC] net: memcg accounting for veth devices
Following one-liner running inside memcg-limited container consumes
huge number of host memory and can trigger global OOM.
for i in `seq 1 xxx` ; do ip l a v$i type veth peer name vp$i ; done
Patch accounts most part of these allocations and can protect host.
---[cut]---
It is not polished, and perhaps should be splitted.
obviously it affects other kind of netdevices too.
Unfortunately I'm not sure that I will have enough time to handle it properly
and decided to publish current patch version as is.
OpenVz workaround it by using per-container limit for number of
available netdevices, but upstream does not have any kind of
per-container configuration.
------
Signed-off-by: Vasily Averin <vvs@...tuozzo.com>
---
drivers/net/veth.c | 2 +-
fs/kernfs/mount.c | 2 +-
fs/proc/proc_sysctl.c | 3 ++-
net/core/neighbour.c | 4 ++--
net/ipv4/devinet.c | 2 +-
net/ipv6/addrconf.c | 6 +++---
6 files changed, 10 insertions(+), 9 deletions(-)
diff --git a/drivers/net/veth.c b/drivers/net/veth.c
index 354a963075c5..6e0b4a9d0843 100644
--- a/drivers/net/veth.c
+++ b/drivers/net/veth.c
@@ -1307,7 +1307,7 @@ static int veth_alloc_queues(struct net_device *dev)
struct veth_priv *priv = netdev_priv(dev);
int i;
- priv->rq = kcalloc(dev->num_rx_queues, sizeof(*priv->rq), GFP_KERNEL);
+ priv->rq = kcalloc(dev->num_rx_queues, sizeof(*priv->rq), GFP_KERNEL_ACCOUNT);
if (!priv->rq)
return -ENOMEM;
diff --git a/fs/kernfs/mount.c b/fs/kernfs/mount.c
index cfa79715fc1a..2881aeeaa880 100644
--- a/fs/kernfs/mount.c
+++ b/fs/kernfs/mount.c
@@ -391,7 +391,7 @@ void __init kernfs_init(void)
{
kernfs_node_cache = kmem_cache_create("kernfs_node_cache",
sizeof(struct kernfs_node),
- 0, SLAB_PANIC, NULL);
+ 0, SLAB_PANIC | SLAB_ACCOUNT, NULL);
/* Creates slab cache for kernfs inode attributes */
kernfs_iattrs_cache = kmem_cache_create("kernfs_iattrs_cache",
diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c
index 7d9cfc730bd4..e20ce8198a44 100644
--- a/fs/proc/proc_sysctl.c
+++ b/fs/proc/proc_sysctl.c
@@ -1333,7 +1333,8 @@ 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 ec0bf737b076..66a4445421f1 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -1665,7 +1665,7 @@ struct neigh_parms *neigh_parms_alloc(struct net_device *dev,
struct net *net = dev_net(dev);
const struct net_device_ops *ops = dev->netdev_ops;
- p = kmemdup(&tbl->parms, sizeof(*p), GFP_KERNEL);
+ p = kmemdup(&tbl->parms, sizeof(*p), GFP_KERNEL_ACCOUNT);
if (p) {
p->tbl = tbl;
refcount_set(&p->refcnt, 1);
@@ -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 fba2bffd65f7..47523fe5b891 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -2566,7 +2566,7 @@ 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 f927c199a93c..9d903342bc41 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -358,7 +358,7 @@ 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;
@@ -382,7 +382,7 @@ static struct inet6_dev *ipv6_add_dev(struct net_device *dev)
if (dev->mtu < IPV6_MIN_MTU)
return ERR_PTR(-EINVAL);
- ndev = kzalloc(sizeof(struct inet6_dev), GFP_KERNEL);
+ ndev = kzalloc(sizeof(struct inet6_dev), GFP_KERNEL_ACCOUNT);
if (!ndev)
return ERR_PTR(err);
@@ -7023,7 +7023,7 @@ 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;
--
2.25.1
Powered by blists - more mailing lists