All of lore.kernel.org
 help / color / mirror / Atom feed
From: "Mauricio Vásquez" <mauricio@kinvolk.io>
To: netdev@vger.kernel.org, bpf@vger.kernel.org
Cc: Alexei Starovoitov <ast@kernel.org>,
	Daniel Borkmann <daniel@iogearbox.net>,
	Andrii Nakryiko <andrii@kernel.org>,
	Quentin Monnet <quentin@isovalent.com>,
	Rafael David Tinoco <rafaeldtinoco@gmail.com>,
	Lorenzo Fontana <lorenzo.fontana@elastic.co>,
	Leonardo Di Donato <leonardo.didonato@elastic.co>
Subject: [PATCH bpf-next v5 5/9] bpftool: Implement btfgen()
Date: Fri, 28 Jan 2022 17:33:08 -0500	[thread overview]
Message-ID: <20220128223312.1253169-6-mauricio@kinvolk.io> (raw)
In-Reply-To: <20220128223312.1253169-1-mauricio@kinvolk.io>

btfgen() receives the path of a source and destination BTF files and a
list of BPF objects. This function records the relocations for all
objects and then generates the BTF file by calling btfgen_get_btf()
(implemented in the following commits).

btfgen_record_obj() loads the BTF and BTF.ext sections of the BPF
objects and loops through all CO-RE relocations. It uses
bpf_core_calc_relo_insn() from libbpf and passes the target spec to
btfgen_record_reloc() that saves the types involved in such relocation.

Signed-off-by: Mauricio Vásquez <mauricio@kinvolk.io>
Signed-off-by: Rafael David Tinoco <rafael.tinoco@aquasec.com>
Signed-off-by: Lorenzo Fontana <lorenzo.fontana@elastic.co>
Signed-off-by: Leonardo Di Donato <leonardo.didonato@elastic.co>
---
 tools/bpf/bpftool/Makefile |   8 +-
 tools/bpf/bpftool/gen.c    | 221 ++++++++++++++++++++++++++++++++++++-
 2 files changed, 223 insertions(+), 6 deletions(-)

diff --git a/tools/bpf/bpftool/Makefile b/tools/bpf/bpftool/Makefile
index 83369f55df61..97d447135536 100644
--- a/tools/bpf/bpftool/Makefile
+++ b/tools/bpf/bpftool/Makefile
@@ -34,10 +34,10 @@ LIBBPF_BOOTSTRAP_INCLUDE := $(LIBBPF_BOOTSTRAP_DESTDIR)/include
 LIBBPF_BOOTSTRAP_HDRS_DIR := $(LIBBPF_BOOTSTRAP_INCLUDE)/bpf
 LIBBPF_BOOTSTRAP := $(LIBBPF_BOOTSTRAP_OUTPUT)libbpf.a
 
-# We need to copy hashmap.h and nlattr.h which is not otherwise exported by
-# libbpf, but still required by bpftool.
-LIBBPF_INTERNAL_HDRS := $(addprefix $(LIBBPF_HDRS_DIR)/,hashmap.h nlattr.h)
-LIBBPF_BOOTSTRAP_INTERNAL_HDRS := $(addprefix $(LIBBPF_BOOTSTRAP_HDRS_DIR)/,hashmap.h)
+# We need to copy hashmap.h, nlattr.h, relo_core.h and libbpf_internal.h
+# which are not otherwise exported by libbpf, but still required by bpftool.
+LIBBPF_INTERNAL_HDRS := $(addprefix $(LIBBPF_HDRS_DIR)/,hashmap.h nlattr.h relo_core.h libbpf_internal.h)
+LIBBPF_BOOTSTRAP_INTERNAL_HDRS := $(addprefix $(LIBBPF_BOOTSTRAP_HDRS_DIR)/,hashmap.h relo_core.h libbpf_internal.h)
 
 ifeq ($(BPFTOOL_VERSION),)
 BPFTOOL_VERSION := $(shell make -rR --no-print-directory -sC ../../.. kernelversion)
diff --git a/tools/bpf/bpftool/gen.c b/tools/bpf/bpftool/gen.c
index 68bb88e86b27..bb9c56401ee5 100644
--- a/tools/bpf/bpftool/gen.c
+++ b/tools/bpf/bpftool/gen.c
@@ -15,6 +15,7 @@
 #include <unistd.h>
 #include <bpf/bpf.h>
 #include <bpf/libbpf.h>
+#include <bpf/libbpf_internal.h>
 #include <sys/types.h>
 #include <sys/stat.h>
 #include <sys/mman.h>
@@ -1143,6 +1144,11 @@ static void *uint_as_hash_key(int x)
 	return (void *)(uintptr_t)x;
 }
 
+static void *u32_as_hash_key(__u32 x)
+{
+	return (void *)(uintptr_t)x;
+}
+
 static void btfgen_free_type(struct btfgen_type *type)
 {
 	free(type);
@@ -1193,12 +1199,223 @@ btfgen_new_info(const char *targ_btf_path)
 	return info;
 }
 
-/* Create BTF file for a set of BPF objects */
-static int btfgen(const char *src_btf, const char *dst_btf, const char *objspaths[])
+static int btfgen_record_field_relo(struct btfgen_info *info, struct bpf_core_spec *targ_spec)
+{
+	return -EOPNOTSUPP;
+}
+
+static int btfgen_record_type_relo(struct btfgen_info *info, struct bpf_core_spec *targ_spec)
+{
+	return -EOPNOTSUPP;
+}
+
+static int btfgen_record_enumval_relo(struct btfgen_info *info, struct bpf_core_spec *targ_spec)
 {
 	return -EOPNOTSUPP;
 }
 
+static int btfgen_record_reloc(struct btfgen_info *info, struct bpf_core_spec *res)
+{
+	switch (res->relo_kind) {
+	case BPF_CORE_FIELD_BYTE_OFFSET:
+	case BPF_CORE_FIELD_BYTE_SIZE:
+	case BPF_CORE_FIELD_EXISTS:
+	case BPF_CORE_FIELD_SIGNED:
+	case BPF_CORE_FIELD_LSHIFT_U64:
+	case BPF_CORE_FIELD_RSHIFT_U64:
+		return btfgen_record_field_relo(info, res);
+	case BPF_CORE_TYPE_ID_LOCAL:
+	case BPF_CORE_TYPE_ID_TARGET:
+	case BPF_CORE_TYPE_EXISTS:
+	case BPF_CORE_TYPE_SIZE:
+		return btfgen_record_type_relo(info, res);
+	case BPF_CORE_ENUMVAL_EXISTS:
+	case BPF_CORE_ENUMVAL_VALUE:
+		return btfgen_record_enumval_relo(info, res);
+	default:
+		return -EINVAL;
+	}
+}
+
+static struct bpf_core_cand_list *
+btfgen_find_cands(const struct btf *local_btf, const struct btf *targ_btf, __u32 local_id)
+{
+	const struct btf_type *local_type;
+	struct bpf_core_cand_list *cands = NULL;
+	struct bpf_core_cand local_cand = {};
+	size_t local_essent_len;
+	const char *local_name;
+	int err;
+
+	local_cand.btf = local_btf;
+	local_cand.id = local_id;
+
+	local_type = btf__type_by_id(local_btf, local_id);
+	if (!local_type) {
+		err = -EINVAL;
+		goto err_out;
+	}
+
+	local_name = btf__name_by_offset(local_btf, local_type->name_off);
+	if (!local_name) {
+		err = -EINVAL;
+		goto err_out;
+	}
+	local_essent_len = bpf_core_essential_name_len(local_name);
+
+	cands = calloc(1, sizeof(*cands));
+	if (!cands)
+		return NULL;
+
+	err = bpf_core_add_cands(&local_cand, local_essent_len, targ_btf, "vmlinux", 1, cands);
+	if (err)
+		goto err_out;
+
+	return cands;
+
+err_out:
+	if (cands)
+		bpf_core_free_cands(cands);
+	errno = -err;
+	return NULL;
+}
+
+/* Record relocation information for a single BPF object*/
+static int btfgen_record_obj(struct btfgen_info *info, const char *obj_path)
+{
+	const struct btf_ext_info_sec *sec;
+	const struct bpf_core_relo *relo;
+	const struct btf_ext_info *seg;
+	struct hashmap *cand_cache;
+	struct btf_ext *btf_ext;
+	unsigned int relo_idx;
+	struct btf *btf;
+	int err;
+
+	btf = btf__parse(obj_path, &btf_ext);
+	err = libbpf_get_error(btf);
+	if (err) {
+		p_err("failed to parse bpf object '%s': %s", obj_path, strerror(errno));
+		return err;
+	}
+
+	if (btf_ext->core_relo_info.len == 0)
+		return 0;
+
+	cand_cache = bpf_core_create_cand_cache();
+	if (IS_ERR(cand_cache))
+		return PTR_ERR(cand_cache);
+
+	seg = &btf_ext->core_relo_info;
+	for_each_btf_ext_sec(seg, sec) {
+		for_each_btf_ext_rec(seg, sec, relo_idx, relo) {
+			struct bpf_core_spec specs_scratch[3] = {};
+			struct bpf_core_relo_res targ_res = {};
+			struct bpf_core_cand_list *cands = NULL;
+			const void *type_key = u32_as_hash_key(relo->type_id);
+			const char *sec_name = btf__name_by_offset(btf, sec->sec_name_off);
+
+			if (relo->kind != BPF_CORE_TYPE_ID_LOCAL &&
+			    !hashmap__find(cand_cache, type_key, (void **)&cands)) {
+				cands = btfgen_find_cands(btf, info->src_btf, relo->type_id);
+				if (!cands) {
+					err = -errno;
+					goto out;
+				}
+
+				err = hashmap__set(cand_cache, type_key, cands, NULL, NULL);
+				if (err)
+					goto out;
+			}
+
+			err = bpf_core_calc_relo_insn(sec_name, relo, relo_idx, btf, cands,
+						      specs_scratch, &targ_res);
+			if (err)
+				goto out;
+
+			err = btfgen_record_reloc(info, &specs_scratch[2]);
+			if (err)
+				goto out;
+		}
+	}
+
+out:
+	bpf_core_free_cand_cache(cand_cache);
+
+	return err;
+}
+
+/* Generate BTF from relocation information previously recorded */
+static struct btf *btfgen_get_btf(struct btfgen_info *info)
+{
+	return ERR_PTR(-EOPNOTSUPP);
+}
+
+/* Create BTF file for a set of BPF objects.
+ *
+ * The BTFGen algorithm is divided in two main parts: (1) collect the
+ * BTF types that are involved in relocations and (2) generate the BTF
+ * object using the collected types.
+ *
+ * In order to collect the types involved in the relocations, we parse
+ * the BTF and BTF.ext sections of the BPF objects and use
+ * bpf_core_calc_relo_insn() to get the target specification, this
+ * indicates how the types and fields are used in a relocation.
+ *
+ * Types are recorded in different ways according to the kind of the
+ * relocation. For field-based relocations only the members that are
+ * actually used are saved in order to reduce the size of the generated
+ * BTF file. For type-based and enum-based relocations the whole type is
+ * saved.
+ *
+ * The second part of the algorithm generates the BTF object. It creates
+ * an empty BTF object and fills it with the types recorded in the
+ * previous step. This function takes care of only adding the structure
+ * and union members that were marked as used and it also fixes up the
+ * type IDs on the generated BTF object.
+ */
+static int btfgen(const char *src_btf, const char *dst_btf, const char *objspaths[])
+{
+	struct btfgen_info *info;
+	struct btf *btf_new = NULL;
+	int err;
+
+	info = btfgen_new_info(src_btf);
+	if (!info) {
+		p_err("failed to allocate info structure: %s", strerror(errno));
+		err = -errno;
+		goto out;
+	}
+
+	for (int i = 0; objspaths[i] != NULL; i++) {
+		p_info("Processing BPF object: %s", objspaths[i]);
+
+		err = btfgen_record_obj(info, objspaths[i]);
+		if (err)
+			goto out;
+	}
+
+	btf_new = btfgen_get_btf(info);
+	if (!btf_new) {
+		err = -errno;
+		p_err("error generating btf: %s", strerror(errno));
+		goto out;
+	}
+
+	p_info("Creating BTF file: %s", dst_btf);
+	err = btf_save_raw(btf_new, dst_btf);
+	if (err) {
+		p_err("error saving btf file: %s", strerror(errno));
+		goto out;
+	}
+
+out:
+	btf__free(btf_new);
+	btfgen_free_info(info);
+
+	return err;
+}
+
 static int do_min_core_btf(int argc, char **argv)
 {
 	char src_btf_path[PATH_MAX], dst_btf_path[PATH_MAX];
-- 
2.25.1


  parent reply	other threads:[~2022-01-28 22:33 UTC|newest]

Thread overview: 45+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-01-28 22:33 [PATCH bpf-next v5 0/9] libbpf: Implement BTFGen Mauricio Vásquez
2022-01-28 22:33 ` [PATCH bpf-next v5 1/9] libbpf: Implement changes needed for BTFGen in bpftool Mauricio Vásquez
2022-02-01 20:57   ` Quentin Monnet
2022-02-03 16:08     ` Mauricio Vásquez Bernal
2022-02-02 18:54   ` Andrii Nakryiko
2022-02-02 19:02     ` Andrii Nakryiko
2022-02-03 16:09     ` Mauricio Vásquez Bernal
2022-01-28 22:33 ` [PATCH bpf-next v5 2/9] bpftool: Add gen min_core_btf command Mauricio Vásquez
2022-02-02 17:58   ` Andrii Nakryiko
2022-02-03 16:07     ` Mauricio Vásquez Bernal
2022-02-03 17:21       ` Andrii Nakryiko
2022-01-28 22:33 ` [PATCH bpf-next v5 3/9] bpftool: Implement btf_save_raw() Mauricio Vásquez
2022-02-02 18:48   ` Andrii Nakryiko
2022-02-03 16:07     ` Mauricio Vásquez Bernal
2022-02-03 17:23       ` Andrii Nakryiko
2022-01-28 22:33 ` [PATCH bpf-next v5 4/9] bpftool: Add struct definitions and helpers for BTFGen Mauricio Vásquez
2022-02-02 18:54   ` Andrii Nakryiko
2022-02-03 16:08     ` Mauricio Vásquez Bernal
2022-02-03 17:24       ` Andrii Nakryiko
2022-01-28 22:33 ` Mauricio Vásquez [this message]
2022-02-01 20:57   ` [PATCH bpf-next v5 5/9] bpftool: Implement btfgen() Quentin Monnet
2022-02-03 19:10     ` Mauricio Vásquez Bernal
2022-02-02 19:14   ` Andrii Nakryiko
2022-02-03 16:09     ` Mauricio Vásquez Bernal
2022-01-28 22:33 ` [PATCH bpf-next v5 6/9] bpftool: Implement relocations recording for BTFGen Mauricio Vásquez
2022-02-02 19:31   ` Andrii Nakryiko
2022-02-03 16:40     ` Mauricio Vásquez Bernal
2022-02-03 17:30       ` Andrii Nakryiko
2022-02-04  6:20         ` Rafael David Tinoco
2022-02-04 18:41           ` Andrii Nakryiko
2022-02-02 22:55   ` Andrii Nakryiko
2022-02-04 19:44     ` Mauricio Vásquez Bernal
2022-01-28 22:33 ` [PATCH bpf-next v5 7/9] bpftool: Implement btfgen_get_btf() Mauricio Vásquez
2022-02-02 19:36   ` Andrii Nakryiko
2022-02-03 16:10     ` Mauricio Vásquez Bernal
2022-02-03 17:31       ` Andrii Nakryiko
2022-01-28 22:33 ` [PATCH bpf-next v5 8/9] bpftool: gen min_core_btf explanation and examples Mauricio Vásquez
2022-02-01 20:57   ` Quentin Monnet
2022-01-28 22:33 ` [PATCH bpf-next v5 9/9] selftest/bpf: Implement tests for bpftool gen min_core_btf Mauricio Vásquez
2022-01-28 23:23   ` Mauricio Vásquez Bernal
2022-02-01 20:58     ` Quentin Monnet
2022-02-02 19:50     ` Andrii Nakryiko
2022-02-03 21:17       ` Mauricio Vásquez Bernal
2022-02-04 20:05         ` Andrii Nakryiko
2022-02-01 20:57   ` Quentin Monnet

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20220128223312.1253169-6-mauricio@kinvolk.io \
    --to=mauricio@kinvolk.io \
    --cc=andrii@kernel.org \
    --cc=ast@kernel.org \
    --cc=bpf@vger.kernel.org \
    --cc=daniel@iogearbox.net \
    --cc=leonardo.didonato@elastic.co \
    --cc=lorenzo.fontana@elastic.co \
    --cc=netdev@vger.kernel.org \
    --cc=quentin@isovalent.com \
    --cc=rafaeldtinoco@gmail.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.