bpf: libbpf: Add STRUCT_OPS support

This patch adds BPF STRUCT_OPS support to libbpf.

The only sec_name convention is SEC(".struct_ops") to identify the
struct_ops implemented in BPF,
e.g. To implement a tcp_congestion_ops:

SEC(".struct_ops")
struct tcp_congestion_ops dctcp = {
	.init           = (void *)dctcp_init,  /* <-- a bpf_prog */
	/* ... some more func prts ... */
	.name           = "bpf_dctcp",
};

Each struct_ops is defined as a global variable under SEC(".struct_ops")
as above.  libbpf creates a map for each variable and the variable name
is the map's name.  Multiple struct_ops is supported under
SEC(".struct_ops").

In the bpf_object__open phase, libbpf will look for the SEC(".struct_ops")
section and find out what is the btf-type the struct_ops is
implementing.  Note that the btf-type here is referring to
a type in the bpf_prog.o's btf.  A "struct bpf_map" is added
by bpf_object__add_map() as other maps do.  It will then
collect (through SHT_REL) where are the bpf progs that the
func ptrs are referring to.  No btf_vmlinux is needed in
the open phase.

In the bpf_object__load phase, the map-fields, which depend
on the btf_vmlinux, are initialized (in bpf_map__init_kern_struct_ops()).
It will also set the prog->type, prog->attach_btf_id, and
prog->expected_attach_type.  Thus, the prog's properties do
not rely on its section name.
[ Currently, the bpf_prog's btf-type ==> btf_vmlinux's btf-type matching
  process is as simple as: member-name match + btf-kind match + size match.
  If these matching conditions fail, libbpf will reject.
  The current targeting support is "struct tcp_congestion_ops" which
  most of its members are function pointers.
  The member ordering of the bpf_prog's btf-type can be different from
  the btf_vmlinux's btf-type. ]

Then, all obj->maps are created as usual (in bpf_object__create_maps()).

Once the maps are created and prog's properties are all set,
the libbpf will proceed to load all the progs.

bpf_map__attach_struct_ops() is added to register a struct_ops
map to a kernel subsystem.
Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20200109003514.3856730-1-kafai@fb.com

tools/lib/bpf/bpf.c

@@ -95,7 +95,11 @@ int bpf_create_map_xattr(const struct bpf_create_map_attr *create_attr)
 	attr.btf_key_type_id = create_attr->btf_key_type_id;
 	attr.btf_value_type_id = create_attr->btf_value_type_id;
 	attr.map_ifindex = create_attr->map_ifindex;
-	attr.inner_map_fd = create_attr->inner_map_fd;
+	if (attr.map_type == BPF_MAP_TYPE_STRUCT_OPS)
+		attr.btf_vmlinux_value_type_id =
+			create_attr->btf_vmlinux_value_type_id;
+	else
+		attr.inner_map_fd = create_attr->inner_map_fd;
 
 	return sys_bpf(BPF_MAP_CREATE, &attr, sizeof(attr));
 }
@@ -228,7 +232,9 @@ int bpf_load_program_xattr(const struct bpf_load_program_attr *load_attr,
 	memset(&attr, 0, sizeof(attr));
 	attr.prog_type = load_attr->prog_type;
 	attr.expected_attach_type = load_attr->expected_attach_type;
-	if (attr.prog_type == BPF_PROG_TYPE_TRACING) {
+	if (attr.prog_type == BPF_PROG_TYPE_STRUCT_OPS) {
+		attr.attach_btf_id = load_attr->attach_btf_id;
+	} else if (attr.prog_type == BPF_PROG_TYPE_TRACING) {
 		attr.attach_btf_id = load_attr->attach_btf_id;
 		attr.attach_prog_fd = load_attr->attach_prog_fd;
 	} else {

tools/lib/bpf/bpf.h

@@ -46,7 +46,10 @@ struct bpf_create_map_attr {
 	__u32 btf_key_type_id;
 	__u32 btf_value_type_id;
 	__u32 map_ifindex;
-	__u32 inner_map_fd;
+	union {
+		__u32 inner_map_fd;
+		__u32 btf_vmlinux_value_type_id;
+	};
 };
 
 LIBBPF_API int

tools/lib/bpf/libbpf.h

@@ -239,6 +239,8 @@ bpf_program__attach_raw_tracepoint(struct bpf_program *prog,
 
 LIBBPF_API struct bpf_link *
 bpf_program__attach_trace(struct bpf_program *prog);
+struct bpf_map;
+LIBBPF_API struct bpf_link *bpf_map__attach_struct_ops(struct bpf_map *map);
 struct bpf_insn;
 
 /*
@@ -315,6 +317,7 @@ LIBBPF_API int bpf_program__set_sched_act(struct bpf_program *prog);
 LIBBPF_API int bpf_program__set_xdp(struct bpf_program *prog);
 LIBBPF_API int bpf_program__set_perf_event(struct bpf_program *prog);
 LIBBPF_API int bpf_program__set_tracing(struct bpf_program *prog);
+LIBBPF_API int bpf_program__set_struct_ops(struct bpf_program *prog);
 
 LIBBPF_API enum bpf_prog_type bpf_program__get_type(struct bpf_program *prog);
 LIBBPF_API void bpf_program__set_type(struct bpf_program *prog,
@@ -335,6 +338,7 @@ LIBBPF_API bool bpf_program__is_sched_act(const struct bpf_program *prog);
 LIBBPF_API bool bpf_program__is_xdp(const struct bpf_program *prog);
 LIBBPF_API bool bpf_program__is_perf_event(const struct bpf_program *prog);
 LIBBPF_API bool bpf_program__is_tracing(const struct bpf_program *prog);
+LIBBPF_API bool bpf_program__is_struct_ops(const struct bpf_program *prog);
 
 /*
  * No need for __attribute__((packed)), all members of 'bpf_map_def'
@@ -354,7 +358,6 @@ struct bpf_map_def {
  * The 'struct bpf_map' in include/linux/bpf.h is internal to the kernel,
  * so no need to worry about a name clash.
  */
-struct bpf_map;
 LIBBPF_API struct bpf_map *
 bpf_object__find_map_by_name(const struct bpf_object *obj, const char *name);
 

tools/lib/bpf/libbpf.map

@@ -213,6 +213,7 @@ LIBBPF_0.0.7 {
 	global:
 		btf_dump__emit_type_decl;
 		bpf_link__disconnect;
+		bpf_map__attach_struct_ops;
 		bpf_object__find_program_by_name;
 		bpf_object__attach_skeleton;
 		bpf_object__destroy_skeleton;
@@ -223,5 +224,7 @@ LIBBPF_0.0.7 {
 		bpf_prog_attach_xattr;
 		bpf_program__attach;
 		bpf_program__name;
+		bpf_program__is_struct_ops;
+		bpf_program__set_struct_ops;
 		btf__align_of;
 } LIBBPF_0.0.6;

tools/lib/bpf/libbpf_probes.c

@@ -103,6 +103,7 @@ probe_load(enum bpf_prog_type prog_type, const struct bpf_insn *insns,
 	case BPF_PROG_TYPE_CGROUP_SYSCTL:
 	case BPF_PROG_TYPE_CGROUP_SOCKOPT:
 	case BPF_PROG_TYPE_TRACING:
+	case BPF_PROG_TYPE_STRUCT_OPS:
 	default:
 		break;
 	}
@@ -251,6 +252,7 @@ bool bpf_probe_map_type(enum bpf_map_type map_type, __u32 ifindex)
 	case BPF_MAP_TYPE_XSKMAP:
 	case BPF_MAP_TYPE_SOCKHASH:
 	case BPF_MAP_TYPE_REUSEPORT_SOCKARRAY:
+	case BPF_MAP_TYPE_STRUCT_OPS:
 	default:
 		break;
 	}