From 6126891c6d4f6f4ef50323d2020635ee255a796e Mon Sep 17 00:00:00 2001 From: Vasily Averin Date: Mon, 19 Jul 2021 13:44:31 +0300 Subject: [PATCH] memcg: enable accounting for IP address and routing-related objects An netadmin inside container can use 'ip a a' and 'ip r a' to assign a large number of ipv4/ipv6 addresses and routing entries and force kernel to allocate megabytes of unaccounted memory for long-lived per-netdevice related kernel objects: 'struct in_ifaddr', 'struct inet6_ifaddr', 'struct fib6_node', 'struct rt6_info', 'struct fib_rules' and ip_fib caches. These objects can be manually removed, though usually they lives in memory till destroy of its net namespace. It makes sense to account for them to restrict the host's memory consumption from inside the memcg-limited container. One of such objects is the 'struct fib6_node' mostly allocated in net/ipv6/route.c::__ip6_ins_rt() inside the lock_bh()/unlock_bh() section: write_lock_bh(&table->tb6_lock); err = fib6_add(&table->tb6_root, rt, info, mxc); write_unlock_bh(&table->tb6_lock); In this case it is not enough to simply add SLAB_ACCOUNT to corresponding kmem cache. The proper memory cgroup still cannot be found due to the incorrect 'in_interrupt()' check used in memcg_kmem_bypass(). Obsoleted in_interrupt() does not describe real execution context properly. >From include/linux/preempt.h: The following macros are deprecated and should not be used in new code: in_interrupt() - We're in NMI,IRQ,SoftIRQ context or have BH disabled To verify the current execution context new macro should be used instead: in_task() - We're in task context Signed-off-by: Vasily Averin Signed-off-by: David S. Miller --- mm/memcontrol.c | 2 +- net/core/fib_rules.c | 4 ++-- net/ipv4/devinet.c | 2 +- net/ipv4/fib_trie.c | 4 ++-- net/ipv6/addrconf.c | 2 +- net/ipv6/ip6_fib.c | 4 ++-- net/ipv6/route.c | 2 +- 7 files changed, 10 insertions(+), 10 deletions(-) diff --git a/mm/memcontrol.c b/mm/memcontrol.c index ae1f5d0cb581..1bbf239b06f2 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -968,7 +968,7 @@ static __always_inline bool memcg_kmem_bypass(void) return false; /* Memcg to charge can't be determined. */ - if (in_interrupt() || !current->mm || (current->flags & PF_KTHREAD)) + if (!in_task() || !current->mm || (current->flags & PF_KTHREAD)) return true; return false; diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index a9f937975080..79df7cd9dbc1 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -57,7 +57,7 @@ int fib_default_rule_add(struct fib_rules_ops *ops, { struct fib_rule *r; - r = kzalloc(ops->rule_size, GFP_KERNEL); + r = kzalloc(ops->rule_size, GFP_KERNEL_ACCOUNT); if (r == NULL) return -ENOMEM; @@ -541,7 +541,7 @@ static int fib_nl2rule(struct sk_buff *skb, struct nlmsghdr *nlh, goto errout; } - nlrule = kzalloc(ops->rule_size, GFP_KERNEL); + nlrule = kzalloc(ops->rule_size, GFP_KERNEL_ACCOUNT); if (!nlrule) { err = -ENOMEM; goto errout; diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 73721a4448bd..d38124bd1b94 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -215,7 +215,7 @@ static void devinet_sysctl_unregister(struct in_device *idev) static struct in_ifaddr *inet_alloc_ifa(void) { - return kzalloc(sizeof(struct in_ifaddr), GFP_KERNEL); + return kzalloc(sizeof(struct in_ifaddr), GFP_KERNEL_ACCOUNT); } static void inet_rcu_free_ifa(struct rcu_head *head) diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 25cf387cca5b..8060524f4256 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -2380,11 +2380,11 @@ void __init fib_trie_init(void) { fn_alias_kmem = kmem_cache_create("ip_fib_alias", sizeof(struct fib_alias), - 0, SLAB_PANIC, NULL); + 0, SLAB_PANIC | SLAB_ACCOUNT, NULL); trie_leaf_kmem = kmem_cache_create("ip_fib_trie", LEAF_SIZE, - 0, SLAB_PANIC, NULL); + 0, SLAB_PANIC | SLAB_ACCOUNT, NULL); } struct fib_table *fib_trie_table(u32 id, struct fib_table *alias) diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index e2f625e39455..bc330fffb4a8 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -1080,7 +1080,7 @@ ipv6_add_addr(struct inet6_dev *idev, struct ifa6_config *cfg, goto out; } - ifa = kzalloc(sizeof(*ifa), gfp_flags); + ifa = kzalloc(sizeof(*ifa), gfp_flags | __GFP_ACCOUNT); if (!ifa) { err = -ENOBUFS; goto out; diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 2d650dc24349..a8f118e469b7 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -2449,8 +2449,8 @@ int __init fib6_init(void) int ret = -ENOMEM; fib6_node_kmem = kmem_cache_create("fib6_nodes", - sizeof(struct fib6_node), - 0, SLAB_HWCACHE_ALIGN, + sizeof(struct fib6_node), 0, + SLAB_HWCACHE_ALIGN | SLAB_ACCOUNT, NULL); if (!fib6_node_kmem) goto out; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 7b756a7dc036..5f7286acca33 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -6638,7 +6638,7 @@ int __init ip6_route_init(void) ret = -ENOMEM; ip6_dst_ops_template.kmem_cachep = kmem_cache_create("ip6_dst_cache", sizeof(struct rt6_info), 0, - SLAB_HWCACHE_ALIGN, NULL); + SLAB_HWCACHE_ALIGN | SLAB_ACCOUNT, NULL); if (!ip6_dst_ops_template.kmem_cachep) goto out; -- GitLab