bpf: introduce BPF_PROG_QUERY command

introduce BPF_PROG_QUERY command to retrieve a set of either
attached programs to given cgroup or a set of effective programs
that will execute for events within a cgroup

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Martin KaFai Lau <kafai@fb.com>
for cgroup bits
Acked-by: Tejun Heo <tj@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

7 files changed, 148 insertions, 0 deletions

diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h
index 102e56fbb6de..359b6f5d3d90 100644
--- a/include/linux/bpf-cgroup.h
+++ b/include/linux/bpf-cgroup.h
@@ -44,12 +44,16 @@ int __cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog,
                         enum bpf_attach_type type, u32 flags);
 int __cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog,
                         enum bpf_attach_type type, u32 flags);
+int __cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr,
+                       union bpf_attr __user *uattr);
 
 /* Wrapper for __cgroup_bpf_*() protected by cgroup_mutex */
 int cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog,
                       enum bpf_attach_type type, u32 flags);
 int cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog,
                       enum bpf_attach_type type, u32 flags);
+int cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr,
+                     union bpf_attr __user *uattr);
 
 int __cgroup_bpf_run_filter_skb(struct sock *sk,
                                 struct sk_buff *skb,
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index a6964b75f070..a67daea731ab 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -260,6 +260,9 @@ struct bpf_prog_array {
 
 struct bpf_prog_array __rcu *bpf_prog_array_alloc(u32 prog_cnt, gfp_t flags);
 void bpf_prog_array_free(struct bpf_prog_array __rcu *progs);
+int bpf_prog_array_length(struct bpf_prog_array __rcu *progs);
+int bpf_prog_array_copy_to_user(struct bpf_prog_array __rcu *progs,
+                                __u32 __user *prog_ids, u32 cnt);
 
 #define BPF_PROG_RUN_ARRAY(array, ctx, func)            \
         ({                                              \
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 762f74bc6c47..cb2b9f95160a 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -92,6 +92,7 @@ enum bpf_cmd {
         BPF_PROG_GET_FD_BY_ID,
         BPF_MAP_GET_FD_BY_ID,
         BPF_OBJ_GET_INFO_BY_FD,
+        BPF_PROG_QUERY,
 };
 
 enum bpf_map_type {
@@ -211,6 +212,9 @@ enum bpf_attach_type {
 /* Specify numa node during map creation */
 #define BPF_F_NUMA_NODE         (1U << 2)
 
+/* flags for BPF_PROG_QUERY */
+#define BPF_F_QUERY_EFFECTIVE   (1U << 0)
+
 #define BPF_OBJ_NAME_LEN 16U
 
 union bpf_attr {
@@ -289,6 +293,15 @@ union bpf_attr {
                 __u32           info_len;
                 __aligned_u64   info;
         } info;
+
+        struct { /* anonymous struct used by BPF_PROG_QUERY command */
+                __u32           target_fd;      /* container object to query */
+                __u32           attach_type;
+                __u32           query_flags;
+                __u32           attach_flags;
+                __aligned_u64   prog_ids;
+                __u32           prog_cnt;
+        } query;
 } __attribute__((aligned(8)));
 
 /* BPF helper function descriptions:
diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index 6b7500bbdb53..e88abc0865d5 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -384,6 +384,52 @@ cleanup:
         return err;
 }
 
+/* Must be called with cgroup_mutex held to avoid races. */
+int __cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr,
+                       union bpf_attr __user *uattr)
+{
+        __u32 __user *prog_ids = u64_to_user_ptr(attr->query.prog_ids);
+        enum bpf_attach_type type = attr->query.attach_type;
+        struct list_head *progs = &cgrp->bpf.progs[type];
+        u32 flags = cgrp->bpf.flags[type];
+        int cnt, ret = 0, i;
+
+        if (attr->query.query_flags & BPF_F_QUERY_EFFECTIVE)
+                cnt = bpf_prog_array_length(cgrp->bpf.effective[type]);
+        else
+                cnt = prog_list_length(progs);
+
+        if (copy_to_user(&uattr->query.attach_flags, &flags, sizeof(flags)))
+                return -EFAULT;
+        if (copy_to_user(&uattr->query.prog_cnt, &cnt, sizeof(cnt)))
+                return -EFAULT;
+        if (attr->query.prog_cnt == 0 || !prog_ids || !cnt)
+                /* return early if user requested only program count + flags */
+                return 0;
+        if (attr->query.prog_cnt < cnt) {
+                cnt = attr->query.prog_cnt;
+                ret = -ENOSPC;
+        }
+
+        if (attr->query.query_flags & BPF_F_QUERY_EFFECTIVE) {
+                return bpf_prog_array_copy_to_user(cgrp->bpf.effective[type],
+                                                   prog_ids, cnt);
+        } else {
+                struct bpf_prog_list *pl;
+                u32 id;
+
+                i = 0;
+                list_for_each_entry(pl, progs, node) {
+                        id = pl->prog->aux->id;
+                        if (copy_to_user(prog_ids + i, &id, sizeof(id)))
+                                return -EFAULT;
+                        if (++i == cnt)
+                                break;
+                }
+        }
+        return ret;
+}
+
 /**
  * __cgroup_bpf_run_filter_skb() - Run a program for packet filtering
  * @sk: The socket sending or receiving traffic
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 6b49e1991ae7..eba966c09053 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -1412,6 +1412,44 @@ void bpf_prog_array_free(struct bpf_prog_array __rcu *progs)
         kfree_rcu(progs, rcu);
 }
 
+int bpf_prog_array_length(struct bpf_prog_array __rcu *progs)
+{
+        struct bpf_prog **prog;
+        u32 cnt = 0;
+
+        rcu_read_lock();
+        prog = rcu_dereference(progs)->progs;
+        for (; *prog; prog++)
+                cnt++;
+        rcu_read_unlock();
+        return cnt;
+}
+
+int bpf_prog_array_copy_to_user(struct bpf_prog_array __rcu *progs,
+                                __u32 __user *prog_ids, u32 cnt)
+{
+        struct bpf_prog **prog;
+        u32 i = 0, id;
+
+        rcu_read_lock();
+        prog = rcu_dereference(progs)->progs;
+        for (; *prog; prog++) {
+                id = (*prog)->aux->id;
+                if (copy_to_user(prog_ids + i, &id, sizeof(id))) {
+                        rcu_read_unlock();
+                        return -EFAULT;
+                }
+                if (++i == cnt) {
+                        prog++;
+                        break;
+                }
+        }
+        rcu_read_unlock();
+        if (*prog)
+                return -ENOSPC;
+        return 0;
+}
+
 static void bpf_prog_free_deferred(struct work_struct *work)
 {
         struct bpf_prog_aux *aux;
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 51bee695d32c..0048cb24ba7b 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -1272,6 +1272,37 @@ static int bpf_prog_detach(const union bpf_attr *attr)
         return ret;
 }
 
+#define BPF_PROG_QUERY_LAST_FIELD query.prog_cnt
+
+static int bpf_prog_query(const union bpf_attr *attr,
+                          union bpf_attr __user *uattr)
+{
+        struct cgroup *cgrp;
+        int ret;
+
+        if (!capable(CAP_NET_ADMIN))
+                return -EPERM;
+        if (CHECK_ATTR(BPF_PROG_QUERY))
+                return -EINVAL;
+        if (attr->query.query_flags & ~BPF_F_QUERY_EFFECTIVE)
+                return -EINVAL;
+
+        switch (attr->query.attach_type) {
+        case BPF_CGROUP_INET_INGRESS:
+        case BPF_CGROUP_INET_EGRESS:
+        case BPF_CGROUP_INET_SOCK_CREATE:
+        case BPF_CGROUP_SOCK_OPS:
+                break;
+        default:
+                return -EINVAL;
+        }
+        cgrp = cgroup_get_from_fd(attr->query.target_fd);
+        if (IS_ERR(cgrp))
+                return PTR_ERR(cgrp);
+        ret = cgroup_bpf_query(cgrp, attr, uattr);
+        cgroup_put(cgrp);
+        return ret;
+}
 #endif /* CONFIG_CGROUP_BPF */
 
 #define BPF_PROG_TEST_RUN_LAST_FIELD test.duration
@@ -1568,6 +1599,9 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz
         case BPF_PROG_DETACH:
                 err = bpf_prog_detach(&attr);
                 break;
+        case BPF_PROG_QUERY:
+                err = bpf_prog_query(&attr, uattr);
+                break;
 #endif
         case BPF_PROG_TEST_RUN:
                 err = bpf_prog_test_run(&attr, uattr);
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 57eb866ae78d..269512b94a94 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -5761,4 +5761,14 @@ int cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog,
         mutex_unlock(&cgroup_mutex);
         return ret;
 }
+int cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr,
+                     union bpf_attr __user *uattr)
+{
+        int ret;
+
+        mutex_lock(&cgroup_mutex);
+        ret = __cgroup_bpf_query(cgrp, attr, uattr);
+        mutex_unlock(&cgroup_mutex);
+        return ret;
+}
 #endif /* CONFIG_CGROUP_BPF */