diff --git a/include/linux/bpf-netns.h b/include/linux/bpf-netns.h new file mode 100644 index 000000000000..f3aec3d79824 --- /dev/null +++ b/include/linux/bpf-netns.h @@ -0,0 +1,56 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _BPF_NETNS_H +#define _BPF_NETNS_H + +#include +#include + +enum netns_bpf_attach_type { + NETNS_BPF_INVALID = -1, + NETNS_BPF_FLOW_DISSECTOR = 0, + MAX_NETNS_BPF_ATTACH_TYPE +}; + +static inline enum netns_bpf_attach_type +to_netns_bpf_attach_type(enum bpf_attach_type attach_type) +{ + switch (attach_type) { + case BPF_FLOW_DISSECTOR: + return NETNS_BPF_FLOW_DISSECTOR; + default: + return NETNS_BPF_INVALID; + } +} + +/* Protects updates to netns_bpf */ +extern struct mutex netns_bpf_mutex; + +union bpf_attr; +struct bpf_prog; + +#ifdef CONFIG_NET +int netns_bpf_prog_query(const union bpf_attr *attr, + union bpf_attr __user *uattr); +int netns_bpf_prog_attach(const union bpf_attr *attr, + struct bpf_prog *prog); +int netns_bpf_prog_detach(const union bpf_attr *attr); +#else +static inline int netns_bpf_prog_query(const union bpf_attr *attr, + union bpf_attr __user *uattr) +{ + return -EOPNOTSUPP; +} + +static inline int netns_bpf_prog_attach(const union bpf_attr *attr, + struct bpf_prog *prog) +{ + return -EOPNOTSUPP; +} + +static inline int netns_bpf_prog_detach(const union bpf_attr *attr) +{ + return -EOPNOTSUPP; +} +#endif + +#endif /* _BPF_NETNS_H */ diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 531843952809..a0d5c2760103 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1283,32 +1283,6 @@ void skb_flow_dissector_init(struct flow_dissector *flow_dissector, const struct flow_dissector_key *key, unsigned int key_count); -#ifdef CONFIG_NET -int skb_flow_dissector_prog_query(const union bpf_attr *attr, - union bpf_attr __user *uattr); -int skb_flow_dissector_bpf_prog_attach(const union bpf_attr *attr, - struct bpf_prog *prog); - -int skb_flow_dissector_bpf_prog_detach(const union bpf_attr *attr); -#else -static inline int skb_flow_dissector_prog_query(const union bpf_attr *attr, - union bpf_attr __user *uattr) -{ - return -EOPNOTSUPP; -} - -static inline int skb_flow_dissector_bpf_prog_attach(const union bpf_attr *attr, - struct bpf_prog *prog) -{ - return -EOPNOTSUPP; -} - -static inline int skb_flow_dissector_bpf_prog_detach(const union bpf_attr *attr) -{ - return -EOPNOTSUPP; -} -#endif - struct bpf_flow_dissector; bool bpf_flow_dissect(struct bpf_prog *prog, struct bpf_flow_dissector *ctx, __be16 proto, int nhoff, int hlen, unsigned int flags); diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index 8e001e049497..2ee5901bec7a 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -33,6 +33,7 @@ #include #include #include +#include #include #include #include @@ -162,7 +163,8 @@ struct net { #endif struct net_generic __rcu *gen; - struct bpf_prog __rcu *flow_dissector_prog; + /* Used to store attached BPF programs */ + struct netns_bpf bpf; /* Note : following structs are cache line aligned */ #ifdef CONFIG_XFRM diff --git a/include/net/netns/bpf.h b/include/net/netns/bpf.h new file mode 100644 index 000000000000..a858d1c5b166 --- /dev/null +++ b/include/net/netns/bpf.h @@ -0,0 +1,17 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * BPF programs attached to network namespace + */ + +#ifndef __NETNS_BPF_H__ +#define __NETNS_BPF_H__ + +#include + +struct bpf_prog; + +struct netns_bpf { + struct bpf_prog __rcu *progs[MAX_NETNS_BPF_ATTACH_TYPE]; +}; + +#endif /* __NETNS_BPF_H__ */ diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index e83b0818b529..c77ab9c76f7b 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -27,6 +27,7 @@ #include #include #include +#include #define IS_FD_ARRAY(map) ((map)->map_type == BPF_MAP_TYPE_PERF_EVENT_ARRAY || \ (map)->map_type == BPF_MAP_TYPE_CGROUP_ARRAY || \ @@ -2868,7 +2869,7 @@ static int bpf_prog_attach(const union bpf_attr *attr) ret = lirc_prog_attach(attr, prog); break; case BPF_PROG_TYPE_FLOW_DISSECTOR: - ret = skb_flow_dissector_bpf_prog_attach(attr, prog); + ret = netns_bpf_prog_attach(attr, prog); break; case BPF_PROG_TYPE_CGROUP_DEVICE: case BPF_PROG_TYPE_CGROUP_SKB: @@ -2908,7 +2909,7 @@ static int bpf_prog_detach(const union bpf_attr *attr) case BPF_PROG_TYPE_FLOW_DISSECTOR: if (!capable(CAP_NET_ADMIN)) return -EPERM; - return skb_flow_dissector_bpf_prog_detach(attr); + return netns_bpf_prog_detach(attr); case BPF_PROG_TYPE_CGROUP_DEVICE: case BPF_PROG_TYPE_CGROUP_SKB: case BPF_PROG_TYPE_CGROUP_SOCK: @@ -2961,7 +2962,7 @@ static int bpf_prog_query(const union bpf_attr *attr, case BPF_LIRC_MODE2: return lirc_prog_query(attr, uattr); case BPF_FLOW_DISSECTOR: - return skb_flow_dissector_prog_query(attr, uattr); + return netns_bpf_prog_query(attr, uattr); default: return -EINVAL; } diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index b64a44a083fd..6c1b8e43d611 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -31,8 +31,10 @@ #include #include #endif +#include -static DEFINE_MUTEX(flow_dissector_mutex); +/* Protects updates to netns_bpf */ +DEFINE_MUTEX(netns_bpf_mutex); static void dissector_set_key(struct flow_dissector *flow_dissector, enum flow_dissector_key_id key_id) @@ -70,23 +72,28 @@ void skb_flow_dissector_init(struct flow_dissector *flow_dissector, } EXPORT_SYMBOL(skb_flow_dissector_init); -int skb_flow_dissector_prog_query(const union bpf_attr *attr, - union bpf_attr __user *uattr) +int netns_bpf_prog_query(const union bpf_attr *attr, + union bpf_attr __user *uattr) { __u32 __user *prog_ids = u64_to_user_ptr(attr->query.prog_ids); u32 prog_id, prog_cnt = 0, flags = 0; + enum netns_bpf_attach_type type; struct bpf_prog *attached; struct net *net; if (attr->query.query_flags) return -EINVAL; + type = to_netns_bpf_attach_type(attr->query.attach_type); + if (type < 0) + return -EINVAL; + net = get_net_ns_by_fd(attr->query.target_fd); if (IS_ERR(net)) return PTR_ERR(net); rcu_read_lock(); - attached = rcu_dereference(net->flow_dissector_prog); + attached = rcu_dereference(net->bpf.progs[type]); if (attached) { prog_cnt = 1; prog_id = attached->aux->id; @@ -112,6 +119,7 @@ int skb_flow_dissector_prog_query(const union bpf_attr *attr, static int flow_dissector_bpf_prog_attach(struct net *net, struct bpf_prog *prog) { + enum netns_bpf_attach_type type = NETNS_BPF_FLOW_DISSECTOR; struct bpf_prog *attached; if (net == &init_net) { @@ -125,74 +133,97 @@ static int flow_dissector_bpf_prog_attach(struct net *net, for_each_net(ns) { if (ns == &init_net) continue; - if (rcu_access_pointer(ns->flow_dissector_prog)) + if (rcu_access_pointer(ns->bpf.progs[type])) return -EEXIST; } } else { /* Make sure root flow dissector is not attached * when attaching to the non-root namespace. */ - if (rcu_access_pointer(init_net.flow_dissector_prog)) + if (rcu_access_pointer(init_net.bpf.progs[type])) return -EEXIST; } - attached = rcu_dereference_protected(net->flow_dissector_prog, - lockdep_is_held(&flow_dissector_mutex)); + attached = rcu_dereference_protected(net->bpf.progs[type], + lockdep_is_held(&netns_bpf_mutex)); if (attached == prog) /* The same program cannot be attached twice */ return -EINVAL; - rcu_assign_pointer(net->flow_dissector_prog, prog); + rcu_assign_pointer(net->bpf.progs[type], prog); if (attached) bpf_prog_put(attached); return 0; } -int skb_flow_dissector_bpf_prog_attach(const union bpf_attr *attr, - struct bpf_prog *prog) +int netns_bpf_prog_attach(const union bpf_attr *attr, struct bpf_prog *prog) { + enum netns_bpf_attach_type type; + struct net *net; int ret; - mutex_lock(&flow_dissector_mutex); - ret = flow_dissector_bpf_prog_attach(current->nsproxy->net_ns, prog); - mutex_unlock(&flow_dissector_mutex); + type = to_netns_bpf_attach_type(attr->attach_type); + if (type < 0) + return -EINVAL; + + net = current->nsproxy->net_ns; + mutex_lock(&netns_bpf_mutex); + switch (type) { + case NETNS_BPF_FLOW_DISSECTOR: + ret = flow_dissector_bpf_prog_attach(net, prog); + break; + default: + ret = -EINVAL; + break; + } + mutex_unlock(&netns_bpf_mutex); return ret; } -static int flow_dissector_bpf_prog_detach(struct net *net) +/* Must be called with netns_bpf_mutex held. */ +static int __netns_bpf_prog_detach(struct net *net, + enum netns_bpf_attach_type type) { struct bpf_prog *attached; - mutex_lock(&flow_dissector_mutex); - attached = rcu_dereference_protected(net->flow_dissector_prog, - lockdep_is_held(&flow_dissector_mutex)); - if (!attached) { - mutex_unlock(&flow_dissector_mutex); + attached = rcu_dereference_protected(net->bpf.progs[type], + lockdep_is_held(&netns_bpf_mutex)); + if (!attached) return -ENOENT; - } - RCU_INIT_POINTER(net->flow_dissector_prog, NULL); + RCU_INIT_POINTER(net->bpf.progs[type], NULL); bpf_prog_put(attached); - mutex_unlock(&flow_dissector_mutex); return 0; } -int skb_flow_dissector_bpf_prog_detach(const union bpf_attr *attr) +int netns_bpf_prog_detach(const union bpf_attr *attr) { - return flow_dissector_bpf_prog_detach(current->nsproxy->net_ns); + enum netns_bpf_attach_type type; + int ret; + + type = to_netns_bpf_attach_type(attr->attach_type); + if (type < 0) + return -EINVAL; + + mutex_lock(&netns_bpf_mutex); + ret = __netns_bpf_prog_detach(current->nsproxy->net_ns, type); + mutex_unlock(&netns_bpf_mutex); + + return ret; } -static void __net_exit flow_dissector_pernet_pre_exit(struct net *net) +static void __net_exit netns_bpf_pernet_pre_exit(struct net *net) { - /* We're not racing with attach/detach because there are no - * references to netns left when pre_exit gets called. - */ - if (rcu_access_pointer(net->flow_dissector_prog)) - flow_dissector_bpf_prog_detach(net); + enum netns_bpf_attach_type type; + + mutex_lock(&netns_bpf_mutex); + for (type = 0; type < MAX_NETNS_BPF_ATTACH_TYPE; type++) + __netns_bpf_prog_detach(net, type); + mutex_unlock(&netns_bpf_mutex); } -static struct pernet_operations flow_dissector_pernet_ops __net_initdata = { - .pre_exit = flow_dissector_pernet_pre_exit, +static struct pernet_operations netns_bpf_pernet_ops __net_initdata = { + .pre_exit = netns_bpf_pernet_pre_exit, }; /** @@ -1044,11 +1075,13 @@ bool __skb_flow_dissect(const struct net *net, WARN_ON_ONCE(!net); if (net) { + enum netns_bpf_attach_type type = NETNS_BPF_FLOW_DISSECTOR; + rcu_read_lock(); - attached = rcu_dereference(init_net.flow_dissector_prog); + attached = rcu_dereference(init_net.bpf.progs[type]); if (!attached) - attached = rcu_dereference(net->flow_dissector_prog); + attached = rcu_dereference(net->bpf.progs[type]); if (attached) { struct bpf_flow_keys flow_keys; @@ -1870,6 +1903,6 @@ static int __init init_default_flow_dissectors(void) flow_keys_basic_dissector_keys, ARRAY_SIZE(flow_keys_basic_dissector_keys)); - return register_pernet_subsys(&flow_dissector_pernet_ops); + return register_pernet_subsys(&netns_bpf_pernet_ops); } core_initcall(init_default_flow_dissectors);