[PATCH bpf-next v4] bpftool: add support for split BTF to gen min_core_btf

[Bryce Kahle <git@brycekahle.com>]

From: Bryce Kahle <bryce.kahle@datadoghq.com>

Enables a user to generate minimized kernel module BTF.

If an eBPF program probes a function within a kernel module or uses
types that come from a kernel module, split BTF is required. The split
module BTF contains only the BTF types that are unique to the module.
It will reference the base/vmlinux BTF types and always starts its type
IDs at X+1 where X is the largest type ID in the base BTF.

Minimization allows a user to ship only the types necessary to do
relocations for the program(s) in the provided eBPF object file(s). A
minimized module BTF will still not contain vmlinux BTF types, so you
should always minimize the vmlinux file first, and then minimize the
kernel module file.

Example:

bpftool gen min_core_btf vmlinux.btf vm-min.btf prog.bpf.o
bpftool -B vm-min.btf gen min_core_btf mod.btf mod-min.btf prog.bpf.o

v3->v4:
- address style nit about start_id initialization
- rename base to src_base_btf (base_btf is a global var)
- copy src_base_btf so new BTF is not modifying original vmlinux BTF

Signed-off-by: Bryce Kahle <bryce.kahle@datadoghq.com>
---
 .../bpf/bpftool/Documentation/bpftool-gen.rst | 18 ++++++++++-
 tools/bpf/bpftool/gen.c                       | 32 +++++++++++++++----
 2 files changed, 42 insertions(+), 8 deletions(-)

diff --git a/tools/bpf/bpftool/Documentation/bpftool-gen.rst b/tools/bpf/bpftool/Documentation/bpftool-gen.rst
index 5006e724d..e067d3b05 100644
--- a/tools/bpf/bpftool/Documentation/bpftool-gen.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool-gen.rst
@@ -16,7 +16,7 @@ SYNOPSIS
 
 	**bpftool** [*OPTIONS*] **gen** *COMMAND*
 
-	*OPTIONS* := { |COMMON_OPTIONS| | { **-L** | **--use-loader** } }
+	*OPTIONS* := { |COMMON_OPTIONS| | { **-B** | **--base-btf** } | { **-L** | **--use-loader** } }
 
 	*COMMAND* := { **object** | **skeleton** | **help** }
 
@@ -202,6 +202,14 @@ OPTIONS
 =======
 	.. include:: common_options.rst
 
+	-B, --base-btf *FILE*
+		  Pass a base BTF object. Base BTF objects are typically used
+		  with BTF objects for kernel modules. To avoid duplicating
+		  all kernel symbols required by modules, BTF objects for
+		  modules are "split", they are built incrementally on top of
+		  the kernel (vmlinux) BTF object. So the base BTF reference
+		  should usually point to the kernel BTF.
+
 	-L, --use-loader
 		  For skeletons, generate a "light" skeleton (also known as "loader"
 		  skeleton). A light skeleton contains a loader eBPF program. It does
@@ -444,3 +452,11 @@ ones given to min_core_btf.
   obj = bpf_object__open_file("one.bpf.o", &opts);
 
   ...
+
+Kernel module BTF may also be minimized by using the -B option:
+
+**$ bpftool -B 5.4.0-smaller.btf gen min_core_btf 5.4.0-module.btf 5.4.0-module-smaller.btf one.bpf.o**
+
+A minimized module BTF will still not contain vmlinux BTF types, so you
+should always minimize the vmlinux file first, and then minimize the
+kernel module file.
diff --git a/tools/bpf/bpftool/gen.c b/tools/bpf/bpftool/gen.c
index ee3ce2b80..57691f766 100644
--- a/tools/bpf/bpftool/gen.c
+++ b/tools/bpf/bpftool/gen.c
@@ -1630,6 +1630,7 @@ static int do_help(int argc, char **argv)
 		"       %1$s %2$s help\n"
 		"\n"
 		"       " HELP_SPEC_OPTIONS " |\n"
+		"                    {-B|--base-btf} |\n"
 		"                    {-L|--use-loader} }\n"
 		"",
 		bin_name, "gen");
@@ -1695,14 +1696,14 @@ btfgen_new_info(const char *targ_btf_path)
 	if (!info)
 		return NULL;
 
-	info->src_btf = btf__parse(targ_btf_path, NULL);
+	info->src_btf = btf__parse_split(targ_btf_path, base_btf);
 	if (!info->src_btf) {
 		err = -errno;
 		p_err("failed parsing '%s' BTF file: %s", targ_btf_path, strerror(errno));
 		goto err_out;
 	}
 
-	info->marked_btf = btf__parse(targ_btf_path, NULL);
+	info->marked_btf = btf__parse_split(targ_btf_path, base_btf);
 	if (!info->marked_btf) {
 		err = -errno;
 		p_err("failed parsing '%s' BTF file: %s", targ_btf_path, strerror(errno));
@@ -2139,12 +2140,29 @@ static int btfgen_remap_id(__u32 *type_id, void *ctx)
 /* Generate BTF from relocation information previously recorded */
 static struct btf *btfgen_get_btf(struct btfgen_info *info)
 {
-	struct btf *btf_new = NULL;
+	struct btf *btf_new = NULL, *src_base_btf_new = NULL;
 	unsigned int *ids = NULL;
+	const struct btf *src_base_btf;
 	unsigned int i, n = btf__type_cnt(info->marked_btf);
-	int err = 0;
+	int start_id, err = 0;
+
+	src_base_btf = btf__base_btf(info->src_btf);
+	start_id = src_base_btf ? btf__type_cnt(src_base_btf) : 1;
 
-	btf_new = btf__new_empty();
+	/* clone BTF to sanitize a copy and leave the original intact */
+	if (src_base_btf) {
+		const void *raw_data;
+		__u32 sz;
+
+		raw_data = btf__raw_data(src_base_btf, &sz);
+		src_base_btf_new = btf__new(raw_data, sz);
+		if (!src_base_btf_new) {
+			err = -errno;
+			goto err_out;
+		}
+	}
+
+	btf_new = btf__new_empty_split(src_base_btf_new);
 	if (!btf_new) {
 		err = -errno;
 		goto err_out;
@@ -2157,7 +2175,7 @@ static struct btf *btfgen_get_btf(struct btfgen_info *info)
 	}
 
 	/* first pass: add all marked types to btf_new and add their new ids to the ids map */
-	for (i = 1; i < n; i++) {
+	for (i = start_id; i < n; i++) {
 		const struct btf_type *cloned_type, *type;
 		const char *name;
 		int new_id;
@@ -2213,7 +2231,7 @@ static struct btf *btfgen_get_btf(struct btfgen_info *info)
 	}
 
 	/* second pass: fix up type ids */
-	for (i = 1; i < btf__type_cnt(btf_new); i++) {
+	for (i = start_id; i < btf__type_cnt(btf_new); i++) {
 		struct btf_type *btf_type = (struct btf_type *) btf__type_by_id(btf_new, i);
 
 		err = btf_type_visit_type_ids(btf_type, btfgen_remap_id, ids);
-- 
2.25.1