From f318903c0bf42448b4c884732df2bbb0ef7a2284 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Fri, 27 Mar 2020 16:58:52 +0100 Subject: bpf: Add netns cookie and enable it for bpf cgroup hooks In Cilium we're mainly using BPF cgroup hooks today in order to implement kube-proxy free Kubernetes service translation for ClusterIP, NodePort (*), ExternalIP, and LoadBalancer as well as HostPort mapping [0] for all traffic between Cilium managed nodes. While this works in its current shape and avoids packet-level NAT for inter Cilium managed node traffic, there is one major limitation we're facing today, that is, lack of netns awareness. In Kubernetes, the concept of Pods (which hold one or multiple containers) has been built around network namespaces, so while we can use the global scope of attaching to root BPF cgroup hooks also to our advantage (e.g. for exposing NodePort ports on loopback addresses), we also have the need to differentiate between initial network namespaces and non-initial one. For example, ExternalIP services mandate that non-local service IPs are not to be translated from the host (initial) network namespace as one example. Right now, we have an ugly work-around in place where non-local service IPs for ExternalIP services are not xlated from connect() and friends BPF hooks but instead via less efficient packet-level NAT on the veth tc ingress hook for Pod traffic. On top of determining whether we're in initial or non-initial network namespace we also have a need for a socket-cookie like mechanism for network namespaces scope. Socket cookies have the nice property that they can be combined as part of the key structure e.g. for BPF LRU maps without having to worry that the cookie could be recycled. We are planning to use this for our sessionAffinity implementation for services. Therefore, add a new bpf_get_netns_cookie() helper which would resolve both use cases at once: bpf_get_netns_cookie(NULL) would provide the cookie for the initial network namespace while passing the context instead of NULL would provide the cookie from the application's network namespace. We're using a hole, so no size increase; the assignment happens only once. Therefore this allows for a comparison on initial namespace as well as regular cookie usage as we have today with socket cookies. We could later on enable this helper for other program types as well as we would see need. (*) Both externalTrafficPolicy={Local|Cluster} types [0] https://github.com/cilium/cilium/blob/master/bpf/bpf_sock.c Signed-off-by: Daniel Borkmann Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/c47d2346982693a9cf9da0e12690453aded4c788.1585323121.git.daniel@iogearbox.net --- include/linux/bpf.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index bdb981c204fa..78046c570596 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -233,6 +233,7 @@ enum bpf_arg_type { ARG_CONST_SIZE_OR_ZERO, /* number of bytes accessed from memory or 0 */ ARG_PTR_TO_CTX, /* pointer to context */ + ARG_PTR_TO_CTX_OR_NULL, /* pointer to context or NULL */ ARG_ANYTHING, /* any (initialized) argument is ok */ ARG_PTR_TO_SPIN_LOCK, /* pointer to bpf_spin_lock */ ARG_PTR_TO_SOCK_COMMON, /* pointer to sock_common */ -- cgit v1.2.3-71-gd317 From 0f09abd105da6c37713d2b253730a86cb45e127a Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Fri, 27 Mar 2020 16:58:54 +0100 Subject: bpf: Enable bpf cgroup hooks to retrieve cgroup v2 and ancestor id Enable the bpf_get_current_cgroup_id() helper for connect(), sendmsg(), recvmsg() and bind-related hooks in order to retrieve the cgroup v2 context which can then be used as part of the key for BPF map lookups, for example. Given these hooks operate in process context 'current' is always valid and pointing to the app that is performing mentioned syscalls if it's subject to a v2 cgroup. Also with same motivation of commit 7723628101aa ("bpf: Introduce bpf_skb_ancestor_cgroup_id helper") enable retrieval of ancestor from current so the cgroup id can be used for policy lookups which can then forbid connect() / bind(), for example. Signed-off-by: Daniel Borkmann Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/d2a7ef42530ad299e3cbb245e6c12374b72145ef.1585323121.git.daniel@iogearbox.net --- include/linux/bpf.h | 1 + include/uapi/linux/bpf.h | 21 ++++++++++++++++++++- kernel/bpf/core.c | 1 + kernel/bpf/helpers.c | 18 ++++++++++++++++++ net/core/filter.c | 12 ++++++++++++ tools/include/uapi/linux/bpf.h | 21 ++++++++++++++++++++- 6 files changed, 72 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 78046c570596..372708eeaecd 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1501,6 +1501,7 @@ extern const struct bpf_func_proto bpf_get_stack_proto; extern const struct bpf_func_proto bpf_sock_map_update_proto; extern const struct bpf_func_proto bpf_sock_hash_update_proto; extern const struct bpf_func_proto bpf_get_current_cgroup_id_proto; +extern const struct bpf_func_proto bpf_get_current_ancestor_cgroup_id_proto; extern const struct bpf_func_proto bpf_msg_redirect_hash_proto; extern const struct bpf_func_proto bpf_msg_redirect_map_proto; extern const struct bpf_func_proto bpf_sk_redirect_hash_proto; diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index bd81c4555206..222ba11966e3 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -2963,6 +2963,24 @@ union bpf_attr { * instead of sockets. * Return * A 8-byte long opaque number. + * + * u64 bpf_get_current_ancestor_cgroup_id(int ancestor_level) + * Description + * Return id of cgroup v2 that is ancestor of the cgroup associated + * with the current task at the *ancestor_level*. The root cgroup + * is at *ancestor_level* zero and each step down the hierarchy + * increments the level. If *ancestor_level* == level of cgroup + * associated with the current task, then return value will be the + * same as that of **bpf_get_current_cgroup_id**\ (). + * + * The helper is useful to implement policies based on cgroups + * that are upper in hierarchy than immediate cgroup associated + * with the current task. + * + * The format of returned id and helper limitations are same as in + * **bpf_get_current_cgroup_id**\ (). + * Return + * The id is returned or 0 in case the id could not be retrieved. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -3087,7 +3105,8 @@ union bpf_attr { FN(read_branch_records), \ FN(get_ns_current_pid_tgid), \ FN(xdp_output), \ - FN(get_netns_cookie), + FN(get_netns_cookie), \ + FN(get_current_ancestor_cgroup_id), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 914f3463aa41..916f5132a984 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -2156,6 +2156,7 @@ const struct bpf_func_proto bpf_get_current_pid_tgid_proto __weak; const struct bpf_func_proto bpf_get_current_uid_gid_proto __weak; const struct bpf_func_proto bpf_get_current_comm_proto __weak; const struct bpf_func_proto bpf_get_current_cgroup_id_proto __weak; +const struct bpf_func_proto bpf_get_current_ancestor_cgroup_id_proto __weak; const struct bpf_func_proto bpf_get_local_storage_proto __weak; const struct bpf_func_proto bpf_get_ns_current_pid_tgid_proto __weak; diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 01878db15eaf..bafc53ddd350 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -340,6 +340,24 @@ const struct bpf_func_proto bpf_get_current_cgroup_id_proto = { .ret_type = RET_INTEGER, }; +BPF_CALL_1(bpf_get_current_ancestor_cgroup_id, int, ancestor_level) +{ + struct cgroup *cgrp = task_dfl_cgroup(current); + struct cgroup *ancestor; + + ancestor = cgroup_ancestor(cgrp, ancestor_level); + if (!ancestor) + return 0; + return cgroup_id(ancestor); +} + +const struct bpf_func_proto bpf_get_current_ancestor_cgroup_id_proto = { + .func = bpf_get_current_ancestor_cgroup_id, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_ANYTHING, +}; + #ifdef CONFIG_CGROUP_BPF DECLARE_PER_CPU(struct bpf_cgroup_storage*, bpf_cgroup_storage[MAX_BPF_CGROUP_STORAGE_TYPE]); diff --git a/net/core/filter.c b/net/core/filter.c index 3083c7746ee0..5cec3ac9e3dd 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -6018,6 +6018,12 @@ sock_filter_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_get_netns_cookie_sock_proto; case BPF_FUNC_perf_event_output: return &bpf_event_output_data_proto; +#ifdef CONFIG_CGROUPS + case BPF_FUNC_get_current_cgroup_id: + return &bpf_get_current_cgroup_id_proto; + case BPF_FUNC_get_current_ancestor_cgroup_id: + return &bpf_get_current_ancestor_cgroup_id_proto; +#endif #ifdef CONFIG_CGROUP_NET_CLASSID case BPF_FUNC_get_cgroup_classid: return &bpf_get_cgroup_classid_curr_proto; @@ -6052,6 +6058,12 @@ sock_addr_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_get_local_storage_proto; case BPF_FUNC_perf_event_output: return &bpf_event_output_data_proto; +#ifdef CONFIG_CGROUPS + case BPF_FUNC_get_current_cgroup_id: + return &bpf_get_current_cgroup_id_proto; + case BPF_FUNC_get_current_ancestor_cgroup_id: + return &bpf_get_current_ancestor_cgroup_id_proto; +#endif #ifdef CONFIG_CGROUP_NET_CLASSID case BPF_FUNC_get_cgroup_classid: return &bpf_get_cgroup_classid_curr_proto; diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index bd81c4555206..222ba11966e3 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -2963,6 +2963,24 @@ union bpf_attr { * instead of sockets. * Return * A 8-byte long opaque number. + * + * u64 bpf_get_current_ancestor_cgroup_id(int ancestor_level) + * Description + * Return id of cgroup v2 that is ancestor of the cgroup associated + * with the current task at the *ancestor_level*. The root cgroup + * is at *ancestor_level* zero and each step down the hierarchy + * increments the level. If *ancestor_level* == level of cgroup + * associated with the current task, then return value will be the + * same as that of **bpf_get_current_cgroup_id**\ (). + * + * The helper is useful to implement policies based on cgroups + * that are upper in hierarchy than immediate cgroup associated + * with the current task. + * + * The format of returned id and helper limitations are same as in + * **bpf_get_current_cgroup_id**\ (). + * Return + * The id is returned or 0 in case the id could not be retrieved. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -3087,7 +3105,8 @@ union bpf_attr { FN(read_branch_records), \ FN(get_ns_current_pid_tgid), \ FN(xdp_output), \ - FN(get_netns_cookie), + FN(get_netns_cookie), \ + FN(get_current_ancestor_cgroup_id), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call -- cgit v1.2.3-71-gd317