Merge branch 'bpf_link-observability'

Andrii Nakryiko says:

====================
This patch series adds various observability APIs to bpf_link:
  - each bpf_link now gets ID, similar to bpf_map and bpf_prog, by which
    user-space can iterate over all existing bpf_links and create limited FD
    from ID;
  - allows to get extra object information with bpf_link general and
    type-specific information;
  - implements `bpf link show` command which lists all active bpf_links in the
    system;
  - implements `bpf link pin` allowing to pin bpf_link by ID or from other
    pinned path.

v2->v3:
  - improve spin locking around bpf_link ID (Alexei);
  - simplify bpf_link_info handling and fix compilation error on sh arch;
v1->v2:
  - simplified `bpftool link show` implementation (Quentin);
  - fixed formatting of bpftool-link.rst (Quentin);
  - fixed attach type printing logic (Quentin);
rfc->v1:
  - dropped read-only bpf_links (Alexei);
  - fixed bug in bpf_link_cleanup() not removing ID;
  - fixed bpftool link pinning search logic;
  - added bash-completion and man page.
====================

Signed-off-by: Alexei Starovoitov <[email protected]>

4 files changed, 58 insertions, 19 deletions

diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h
index 0b41fd5fc96b..272626cc3fc9 100644
--- a/include/linux/bpf-cgroup.h
+++ b/include/linux/bpf-cgroup.h
@@ -57,8 +57,6 @@ struct bpf_cgroup_link {
 	enum bpf_attach_type type;
 };
 
-extern const struct bpf_link_ops bpf_cgroup_link_lops;
-
 struct bpf_prog_list {
 	struct list_head node;
 	struct bpf_prog *prog;
@@ -100,8 +98,6 @@ int __cgroup_bpf_attach(struct cgroup *cgrp,
 int __cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog,
 			struct bpf_cgroup_link *link,
 			enum bpf_attach_type type);
-int __cgroup_bpf_replace(struct cgroup *cgrp, struct bpf_cgroup_link *link,
-			 struct bpf_prog *new_prog);
 int __cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr,
 		       union bpf_attr __user *uattr);
 
@@ -112,8 +108,6 @@ int cgroup_bpf_attach(struct cgroup *cgrp,
 		      u32 flags);
 int cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog,
 		      enum bpf_attach_type type);
-int cgroup_bpf_replace(struct bpf_link *link, struct bpf_prog *old_prog,
-		       struct bpf_prog *new_prog);
 int cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr,
 		     union bpf_attr __user *uattr);
 
@@ -353,7 +347,6 @@ int cgroup_bpf_prog_query(const union bpf_attr *attr,
 #else
 
 struct bpf_prog;
-struct bpf_link;
 struct cgroup_bpf {};
 static inline int cgroup_bpf_inherit(struct cgroup *cgrp) { return 0; }
 static inline void cgroup_bpf_offline(struct cgroup *cgrp) {}
@@ -377,13 +370,6 @@ static inline int cgroup_bpf_link_attach(const union bpf_attr *attr,
 	return -EINVAL;
 }
 
-static inline int cgroup_bpf_replace(struct bpf_link *link,
-				     struct bpf_prog *old_prog,
-				     struct bpf_prog *new_prog)
-{
-	return -EINVAL;
-}
-
 static inline int cgroup_bpf_prog_query(const union bpf_attr *attr,
 					union bpf_attr __user *uattr)
 {
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 10960cfabea4..c07b1d2f3824 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1026,9 +1026,11 @@ extern const struct file_operations bpf_prog_fops;
 	extern const struct bpf_verifier_ops _name ## _verifier_ops;
 #define BPF_MAP_TYPE(_id, _ops) \
 	extern const struct bpf_map_ops _ops;
+#define BPF_LINK_TYPE(_id, _name)
 #include <linux/bpf_types.h>
 #undef BPF_PROG_TYPE
 #undef BPF_MAP_TYPE
+#undef BPF_LINK_TYPE
 
 extern const struct bpf_prog_ops bpf_offload_prog_ops;
 extern const struct bpf_verifier_ops tc_cls_act_analyzer_ops;
@@ -1085,21 +1087,35 @@ int bpf_prog_new_fd(struct bpf_prog *prog);
 
 struct bpf_link {
 	atomic64_t refcnt;
+	u32 id;
+	enum bpf_link_type type;
 	const struct bpf_link_ops *ops;
 	struct bpf_prog *prog;
 	struct work_struct work;
 };
 
+struct bpf_link_primer {
+	struct bpf_link *link;
+	struct file *file;
+	int fd;
+	u32 id;
+};
+
 struct bpf_link_ops {
 	void (*release)(struct bpf_link *link);
 	void (*dealloc)(struct bpf_link *link);
-
+	int (*update_prog)(struct bpf_link *link, struct bpf_prog *new_prog,
+			   struct bpf_prog *old_prog);
+	void (*show_fdinfo)(const struct bpf_link *link, struct seq_file *seq);
+	int (*fill_link_info)(const struct bpf_link *link,
+			      struct bpf_link_info *info);
 };
 
-void bpf_link_init(struct bpf_link *link, const struct bpf_link_ops *ops,
-		   struct bpf_prog *prog);
-void bpf_link_cleanup(struct bpf_link *link, struct file *link_file,
-		      int link_fd);
+void bpf_link_init(struct bpf_link *link, enum bpf_link_type type,
+		   const struct bpf_link_ops *ops, struct bpf_prog *prog);
+int bpf_link_prime(struct bpf_link *link, struct bpf_link_primer *primer);
+int bpf_link_settle(struct bpf_link_primer *primer);
+void bpf_link_cleanup(struct bpf_link_primer *primer);
 void bpf_link_inc(struct bpf_link *link);
 void bpf_link_put(struct bpf_link *link);
 int bpf_link_new_fd(struct bpf_link *link);
diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h
index ba0c2d56f8a3..8345cdf553b8 100644
--- a/include/linux/bpf_types.h
+++ b/include/linux/bpf_types.h
@@ -118,3 +118,9 @@ BPF_MAP_TYPE(BPF_MAP_TYPE_STACK, stack_map_ops)
 #if defined(CONFIG_BPF_JIT)
 BPF_MAP_TYPE(BPF_MAP_TYPE_STRUCT_OPS, bpf_struct_ops_map_ops)
 #endif
+
+BPF_LINK_TYPE(BPF_LINK_TYPE_RAW_TRACEPOINT, raw_tracepoint)
+BPF_LINK_TYPE(BPF_LINK_TYPE_TRACING, tracing)
+#ifdef CONFIG_CGROUP_BPF
+BPF_LINK_TYPE(BPF_LINK_TYPE_CGROUP, cgroup)
+#endif
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 4a6c47f3febe..0eccafae55bb 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -113,6 +113,8 @@ enum bpf_cmd {
 	BPF_MAP_DELETE_BATCH,
 	BPF_LINK_CREATE,
 	BPF_LINK_UPDATE,
+	BPF_LINK_GET_FD_BY_ID,
+	BPF_LINK_GET_NEXT_ID,
 };
 
 enum bpf_map_type {
@@ -220,6 +222,15 @@ enum bpf_attach_type {
 
 #define MAX_BPF_ATTACH_TYPE __MAX_BPF_ATTACH_TYPE
 
+enum bpf_link_type {
+	BPF_LINK_TYPE_UNSPEC = 0,
+	BPF_LINK_TYPE_RAW_TRACEPOINT = 1,
+	BPF_LINK_TYPE_TRACING = 2,
+	BPF_LINK_TYPE_CGROUP = 3,
+
+	MAX_BPF_LINK_TYPE,
+};
+
 /* cgroup-bpf attach flags used in BPF_PROG_ATTACH command
  *
  * NONE(default): No further bpf programs allowed in the subtree.
@@ -523,6 +534,7 @@ union bpf_attr {
 			__u32		prog_id;
 			__u32		map_id;
 			__u32		btf_id;
+			__u32		link_id;
 		};
 		__u32		next_id;
 		__u32		open_flags;
@@ -3609,6 +3621,25 @@ struct bpf_btf_info {
 	__u32 id;
 } __attribute__((aligned(8)));
 
+struct bpf_link_info {
+	__u32 type;
+	__u32 id;
+	__u32 prog_id;
+	union {
+		struct {
+			__aligned_u64 tp_name; /* in/out: tp_name buffer ptr */
+			__u32 tp_name_len;     /* in/out: tp_name buffer len */
+		} raw_tracepoint;
+		struct {
+			__u32 attach_type;
+		} tracing;
+		struct {
+			__u64 cgroup_id;
+			__u32 attach_type;
+		} cgroup;
+	};
+} __attribute__((aligned(8)));
+
 /* User bpf_sock_addr struct to access socket fields and sockaddr struct passed
  * by user and intended to be used by socket (e.g. to bind to, depends on
  * attach attach type).