summaryrefslogtreecommitdiff
path: root/kernel/bpf
diff options
context:
space:
mode:
authorDaniel Borkmann <daniel@iogearbox.net>2020-05-19 00:45:45 +0200
committerAlexei Starovoitov <ast@kernel.org>2020-05-19 11:32:04 -0700
commit1b66d253610c7f8f257103808a9460223a087469 (patch)
treee1b37c8c2f7fd3a557d51de9705dacf71f566c9f /kernel/bpf
parentd800bad67d4c21aaf11722f04e0f7547fb915ab5 (diff)
bpf: Add get{peer, sock}name attach types for sock_addr
As stated in 983695fa6765 ("bpf: fix unconnected udp hooks"), the objective for the existing cgroup connect/sendmsg/recvmsg/bind BPF hooks is to be transparent to applications. In Cilium we make use of these hooks [0] in order to enable E-W load balancing for existing Kubernetes service types for all Cilium managed nodes in the cluster. Those backends can be local or remote. The main advantage of this approach is that it operates as close as possible to the socket, and therefore allows to avoid packet-based NAT given in connect/sendmsg/recvmsg hooks we only need to xlate sock addresses. This also allows to expose NodePort services on loopback addresses in the host namespace, for example. As another advantage, this also efficiently blocks bind requests for applications in the host namespace for exposed ports. However, one missing item is that we also need to perform reverse xlation for inet{,6}_getname() hooks such that we can return the service IP/port tuple back to the application instead of the remote peer address. The vast majority of applications does not bother about getpeername(), but in a few occasions we've seen breakage when validating the peer's address since it returns unexpectedly the backend tuple instead of the service one. Therefore, this trivial patch allows to customise and adds a getpeername() as well as getsockname() BPF cgroup hook for both IPv4 and IPv6 in order to address this situation. Simple example: # ./cilium/cilium service list ID Frontend Service Type Backend 1 1.2.3.4:80 ClusterIP 1 => 10.0.0.10:80 Before; curl's verbose output example, no getpeername() reverse xlation: # curl --verbose 1.2.3.4 * Rebuilt URL to: 1.2.3.4/ * Trying 1.2.3.4... * TCP_NODELAY set * Connected to 1.2.3.4 (10.0.0.10) port 80 (#0) > GET / HTTP/1.1 > Host: 1.2.3.4 > User-Agent: curl/7.58.0 > Accept: */* [...] After; with getpeername() reverse xlation: # curl --verbose 1.2.3.4 * Rebuilt URL to: 1.2.3.4/ * Trying 1.2.3.4... * TCP_NODELAY set * Connected to 1.2.3.4 (1.2.3.4) port 80 (#0) > GET / HTTP/1.1 > Host: 1.2.3.4 > User-Agent: curl/7.58.0 > Accept: */* [...] Originally, I had both under a BPF_CGROUP_INET{4,6}_GETNAME type and exposed peer to the context similar as in inet{,6}_getname() fashion, but API-wise this is suboptimal as it always enforces programs having to test for ctx->peer which can easily be missed, hence BPF_CGROUP_INET{4,6}_GET{PEER,SOCK}NAME split. Similarly, the checked return code is on tnum_range(1, 1), but if a use case comes up in future, it can easily be changed to return an error code instead. Helper and ctx member access is the same as with connect/sendmsg/etc hooks. [0] https://github.com/cilium/cilium/blob/master/bpf/bpf_sock.c Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Andrii Nakryiko <andriin@fb.com> Acked-by: Andrey Ignatov <rdna@fb.com> Link: https://lore.kernel.org/bpf/61a479d759b2482ae3efb45546490bacd796a220.1589841594.git.daniel@iogearbox.net
Diffstat (limited to 'kernel/bpf')
-rw-r--r--kernel/bpf/syscall.c12
-rw-r--r--kernel/bpf/verifier.c6
2 files changed, 17 insertions, 1 deletions
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 57dfc98289d5..431241c74614 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -1978,6 +1978,10 @@ bpf_prog_load_check_attach(enum bpf_prog_type prog_type,
case BPF_CGROUP_INET6_BIND:
case BPF_CGROUP_INET4_CONNECT:
case BPF_CGROUP_INET6_CONNECT:
+ case BPF_CGROUP_INET4_GETPEERNAME:
+ case BPF_CGROUP_INET6_GETPEERNAME:
+ case BPF_CGROUP_INET4_GETSOCKNAME:
+ case BPF_CGROUP_INET6_GETSOCKNAME:
case BPF_CGROUP_UDP4_SENDMSG:
case BPF_CGROUP_UDP6_SENDMSG:
case BPF_CGROUP_UDP4_RECVMSG:
@@ -2767,6 +2771,10 @@ attach_type_to_prog_type(enum bpf_attach_type attach_type)
case BPF_CGROUP_INET6_BIND:
case BPF_CGROUP_INET4_CONNECT:
case BPF_CGROUP_INET6_CONNECT:
+ case BPF_CGROUP_INET4_GETPEERNAME:
+ case BPF_CGROUP_INET6_GETPEERNAME:
+ case BPF_CGROUP_INET4_GETSOCKNAME:
+ case BPF_CGROUP_INET6_GETSOCKNAME:
case BPF_CGROUP_UDP4_SENDMSG:
case BPF_CGROUP_UDP6_SENDMSG:
case BPF_CGROUP_UDP4_RECVMSG:
@@ -2912,6 +2920,10 @@ static int bpf_prog_query(const union bpf_attr *attr,
case BPF_CGROUP_INET6_POST_BIND:
case BPF_CGROUP_INET4_CONNECT:
case BPF_CGROUP_INET6_CONNECT:
+ case BPF_CGROUP_INET4_GETPEERNAME:
+ case BPF_CGROUP_INET6_GETPEERNAME:
+ case BPF_CGROUP_INET4_GETSOCKNAME:
+ case BPF_CGROUP_INET6_GETSOCKNAME:
case BPF_CGROUP_UDP4_SENDMSG:
case BPF_CGROUP_UDP6_SENDMSG:
case BPF_CGROUP_UDP4_RECVMSG:
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 9c7d67d65d8c..2ed8351f47a4 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -7094,7 +7094,11 @@ static int check_return_code(struct bpf_verifier_env *env)
switch (env->prog->type) {
case BPF_PROG_TYPE_CGROUP_SOCK_ADDR:
if (env->prog->expected_attach_type == BPF_CGROUP_UDP4_RECVMSG ||
- env->prog->expected_attach_type == BPF_CGROUP_UDP6_RECVMSG)
+ env->prog->expected_attach_type == BPF_CGROUP_UDP6_RECVMSG ||
+ env->prog->expected_attach_type == BPF_CGROUP_INET4_GETPEERNAME ||
+ env->prog->expected_attach_type == BPF_CGROUP_INET6_GETPEERNAME ||
+ env->prog->expected_attach_type == BPF_CGROUP_INET4_GETSOCKNAME ||
+ env->prog->expected_attach_type == BPF_CGROUP_INET6_GETSOCKNAME)
range = tnum_range(1, 1);
break;
case BPF_PROG_TYPE_CGROUP_SKB: