bpf: Add bpf_current_task_under_cgroup helper

This adds a bpf helper that's similar to the skb_in_cgroup helper to check
whether the probe is currently executing in the context of a specific
subset of the cgroupsv2 hierarchy. It does this based on membership test
for a cgroup arraymap. It is invalid to call this in an interrupt, and
it'll return an error. The helper is primarily to be used in debugging
activities for containers, where you may have multiple programs running in
a given top-level "container".

Signed-off-by: Sargun Dhillon <sargun@sargun.me>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Tejun Heo <tj@kernel.org>
Acked-by: Tejun Heo <tj@kernel.org>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index da218fec605657ee415f8ad71a95d8851330a9de..bea0c4e2830a48a3596a2d70de234824e59d0e35 100644 (file)
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -375,6 +375,17 @@ enum bpf_func_id {
         */
        BPF_FUNC_probe_write_user,
 
+       /**
+        * bpf_current_task_under_cgroup(map, index) - Check cgroup2 membership of current task
+        * @map: pointer to bpf_map in BPF_MAP_TYPE_CGROUP_ARRAY type
+        * @index: index of the cgroup in the bpf_map
+        * Return:
+        *   == 0 current failed the cgroup2 descendant test
+        *   == 1 current succeeded the cgroup2 descendant test
+        *    < 0 error
+        */
+       BPF_FUNC_current_task_under_cgroup,
+
        __BPF_FUNC_MAX_ID,
 };
 

diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index 633a650d7aeb74ff2e6ebc2e4134950cf94bd288..a2ac051c342f87b1372a7aeb33ba816327ee1a43 100644 (file)
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -538,7 +538,7 @@ static int __init register_perf_event_array_map(void)
 }
 late_initcall(register_perf_event_array_map);
 
-#ifdef CONFIG_SOCK_CGROUP_DATA
+#ifdef CONFIG_CGROUPS
 static void *cgroup_fd_array_get_ptr(struct bpf_map *map,
                                     struct file *map_file /* not used */,
                                     int fd)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 7094c69ac1995892c5cfa31c061cf9f3a59232de..d504722ebfa446561789750441df6c0dbc2ae1b7 100644 (file)
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -1053,7 +1053,8 @@ static int check_map_func_compatibility(struct bpf_map *map, int func_id)
                        goto error;
                break;
        case BPF_MAP_TYPE_CGROUP_ARRAY:
-               if (func_id != BPF_FUNC_skb_in_cgroup)
+               if (func_id != BPF_FUNC_skb_in_cgroup &&
+                   func_id != BPF_FUNC_current_task_under_cgroup)
                        goto error;
                break;
        default:
@@ -1075,6 +1076,7 @@ static int check_map_func_compatibility(struct bpf_map *map, int func_id)
                if (map->map_type != BPF_MAP_TYPE_STACK_TRACE)
                        goto error;
                break;
+       case BPF_FUNC_current_task_under_cgroup:
        case BPF_FUNC_skb_in_cgroup:
                if (map->map_type != BPF_MAP_TYPE_CGROUP_ARRAY)
                        goto error;

diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index b20438fdb0295a5fdedee44b6c1ae4b8cf229200..6b794d6669a7d0016472d8970020f23842bcbd56 100644 (file)
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -376,6 +376,34 @@ static const struct bpf_func_proto bpf_get_current_task_proto = {
        .ret_type       = RET_INTEGER,
 };
 
+static u64 bpf_current_task_under_cgroup(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5)
+{
+       struct bpf_map *map = (struct bpf_map *)(long)r1;
+       struct bpf_array *array = container_of(map, struct bpf_array, map);
+       struct cgroup *cgrp;
+       u32 idx = (u32)r2;
+
+       if (unlikely(in_interrupt()))
+               return -EINVAL;
+
+       if (unlikely(idx >= array->map.max_entries))
+               return -E2BIG;
+
+       cgrp = READ_ONCE(array->ptrs[idx]);
+       if (unlikely(!cgrp))
+               return -EAGAIN;
+
+       return task_under_cgroup_hierarchy(current, cgrp);
+}
+
+static const struct bpf_func_proto bpf_current_task_under_cgroup_proto = {
+       .func           = bpf_current_task_under_cgroup,
+       .gpl_only       = false,
+       .ret_type       = RET_INTEGER,
+       .arg1_type      = ARG_CONST_MAP_PTR,
+       .arg2_type      = ARG_ANYTHING,
+};
+
 static const struct bpf_func_proto *tracing_func_proto(enum bpf_func_id func_id)
 {
        switch (func_id) {
@@ -407,6 +435,8 @@ static const struct bpf_func_proto *tracing_func_proto(enum bpf_func_id func_id)
                return &bpf_perf_event_read_proto;
        case BPF_FUNC_probe_write_user:
                return bpf_get_probe_write_proto();
+       case BPF_FUNC_current_task_under_cgroup:
+               return &bpf_current_task_under_cgroup_proto;
        default:
                return NULL;
        }