tools: bpftool: Add "inner_map" to "bpftool map create" outer maps

There is no support for creating maps of types array-of-map or
hash-of-map in bpftool. This is because the kernel needs an inner_map_fd
to collect metadata on the inner maps to be supported by the new map,
but bpftool does not provide a way to pass this file descriptor.

Add a new optional "inner_map" keyword that can be used to pass a
reference to a map, retrieve a fd to that map, and pass it as the
inner_map_fd.

Add related documentation and bash completion. Note that we can
reference the inner map by its name, meaning we can have several times
the keyword "name" with different meanings (mandatory outer map name,
and possibly a name to use to find the inner_map_fd). The bash
completion will offer it just once, and will not suggest "name" on the
following command:

    # bpftool map create /sys/fs/bpf/my_outer_map type hash_of_maps \
        inner_map name my_inner_map [TAB]

Fixing that specific case seems too convoluted. Completion will work as
expected, however, if the outer map name comes first and the "inner_map
name ..." is passed second.

Signed-off-by: Quentin Monnet <quentin@isovalent.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Link: https://lore.kernel.org/bpf/20200910102652.10509-4-quentin@isovalent.com

1 files changed, 33 insertions, 15 deletions

diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c
index d8581d5e98a1..a7efbd84fbcc 100644
--- a/tools/bpf/bpftool/map.c
+++ b/tools/bpf/bpftool/map.c
@@ -1250,7 +1250,7 @@ static int do_create(int argc, char **argv)
 {
 	struct bpf_create_map_attr attr = { NULL, };
 	const char *pinfile;
-	int err, fd;
+	int err = -1, fd;
 
 	if (!REQ_ARGS(7))
 		return -1;
@@ -1265,13 +1265,13 @@ static int do_create(int argc, char **argv)
 
 			if (attr.map_type) {
 				p_err("map type already specified");
-				return -1;
+				goto exit;
 			}
 
 			attr.map_type = map_type_from_str(*argv);
 			if ((int)attr.map_type < 0) {
 				p_err("unrecognized map type: %s", *argv);
-				return -1;
+				goto exit;
 			}
 			NEXT_ARG();
 		} else if (is_prefix(*argv, "name")) {
@@ -1280,43 +1280,56 @@ static int do_create(int argc, char **argv)
 		} else if (is_prefix(*argv, "key")) {
 			if (parse_u32_arg(&argc, &argv, &attr.key_size,
 					  "key size"))
-				return -1;
+				goto exit;
 		} else if (is_prefix(*argv, "value")) {
 			if (parse_u32_arg(&argc, &argv, &attr.value_size,
 					  "value size"))
-				return -1;
+				goto exit;
 		} else if (is_prefix(*argv, "entries")) {
 			if (parse_u32_arg(&argc, &argv, &attr.max_entries,
 					  "max entries"))
-				return -1;
+				goto exit;
 		} else if (is_prefix(*argv, "flags")) {
 			if (parse_u32_arg(&argc, &argv, &attr.map_flags,
 					  "flags"))
-				return -1;
+				goto exit;
 		} else if (is_prefix(*argv, "dev")) {
 			NEXT_ARG();
 
 			if (attr.map_ifindex) {
 				p_err("offload device already specified");
-				return -1;
+				goto exit;
 			}
 
 			attr.map_ifindex = if_nametoindex(*argv);
 			if (!attr.map_ifindex) {
 				p_err("unrecognized netdevice '%s': %s",
 				      *argv, strerror(errno));
-				return -1;
+				goto exit;
 			}
 			NEXT_ARG();
+		} else if (is_prefix(*argv, "inner_map")) {
+			struct bpf_map_info info = {};
+			__u32 len = sizeof(info);
+			int inner_map_fd;
+
+			NEXT_ARG();
+			if (!REQ_ARGS(2))
+				usage();
+			inner_map_fd = map_parse_fd_and_info(&argc, &argv,
+							     &info, &len);
+			if (inner_map_fd < 0)
+				return -1;
+			attr.inner_map_fd = inner_map_fd;
 		} else {
 			p_err("unknown arg %s", *argv);
-			return -1;
+			goto exit;
 		}
 	}
 
 	if (!attr.name) {
 		p_err("map name not specified");
-		return -1;
+		goto exit;
 	}
 
 	set_max_rlimit();
@@ -1324,17 +1337,22 @@ static int do_create(int argc, char **argv)
 	fd = bpf_create_map_xattr(&attr);
 	if (fd < 0) {
 		p_err("map create failed: %s", strerror(errno));
-		return -1;
+		goto exit;
 	}
 
 	err = do_pin_fd(fd, pinfile);
 	close(fd);
 	if (err)
-		return err;
+		goto exit;
 
 	if (json_output)
 		jsonw_null(json_wtr);
-	return 0;
+
+exit:
+	if (attr.inner_map_fd > 0)
+		close(attr.inner_map_fd);
+
+	return err;
 }
 
 static int do_pop_dequeue(int argc, char **argv)
@@ -1420,7 +1438,7 @@ static int do_help(int argc, char **argv)
 		"Usage: %1$s %2$s { show | list }   [MAP]\n"
 		"       %1$s %2$s create     FILE type TYPE key KEY_SIZE value VALUE_SIZE \\\n"
 		"                                  entries MAX_ENTRIES name NAME [flags FLAGS] \\\n"
-		"                                  [dev NAME]\n"
+		"                                  [inner_map MAP] [dev NAME]\n"
 		"       %1$s %2$s dump       MAP\n"
 		"       %1$s %2$s update     MAP [key DATA] [value VALUE] [UPDATE_FLAGS]\n"
 		"       %1$s %2$s lookup     MAP [key DATA]\n"