bpf tools: Record map accessing instructions for each program

This patch records the indices of instructions which are needed to be
relocated. That information is saved in the 'reloc_desc' field in
'struct bpf_program'. In the loading phase (this patch takes effect in
the opening phase), the collected instructions will be replaced by map
loading instructions.

Since we are going to close the ELF file and clear all data at the end
of the 'opening' phase, the ELF information will no longer be valid in
the 'loading' phase. We have to locate the instructions before maps are
loaded, instead of directly modifying the instruction.

'struct bpf_map_def' is introduced in this patch to let us know how many
maps are defined in the object.

This is the third part of map relocation. The principle of map relocation
is described in commit message of 'bpf tools: Collect symbol table from
SHT_SYMTAB section'.

Signed-off-by: Wang Nan <wangnan0@huawei.com>
Acked-by: Alexei Starovoitov <ast@plumgrid.com>
Cc: Brendan Gregg <brendan.d.gregg@gmail.com>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: David Ahern <dsahern@gmail.com>
Cc: He Kuang <hekuang@huawei.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kaixu Xia <xiakaixu@huawei.com>
Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Zefan Li <lizefan@huawei.com>
Cc: pi3orama@163.com
Link: http://lkml.kernel.org/r/1435716878-189507-15-git-send-email-wangnan0@huawei.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

2 files changed, 137 insertions, 0 deletions

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index e8088f8214d1..ac69ae3bd628 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -9,6 +9,7 @@
 #include <stdlib.h>
 #include <stdio.h>
 #include <stdarg.h>
+#include <inttypes.h>
 #include <string.h>
 #include <unistd.h>
 #include <fcntl.h>
@@ -88,6 +89,12 @@ struct bpf_program {
 	char *section_name;
 	struct bpf_insn *insns;
 	size_t insns_cnt;
+
+	struct {
+		int insn_idx;
+		int map_idx;
+	} *reloc_desc;
+	int nr_reloc;
 };
 
 struct bpf_object {
@@ -127,6 +134,9 @@ static void bpf_program__exit(struct bpf_program *prog)
 
 	zfree(&prog->section_name);
 	zfree(&prog->insns);
+	zfree(&prog->reloc_desc);
+
+	prog->nr_reloc = 0;
 	prog->insns_cnt = 0;
 	prog->idx = -1;
 }
@@ -481,6 +491,118 @@ out:
 	return err;
 }
 
+static struct bpf_program *
+bpf_object__find_prog_by_idx(struct bpf_object *obj, int idx)
+{
+	struct bpf_program *prog;
+	size_t i;
+
+	for (i = 0; i < obj->nr_programs; i++) {
+		prog = &obj->programs[i];
+		if (prog->idx == idx)
+			return prog;
+	}
+	return NULL;
+}
+
+static int
+bpf_program__collect_reloc(struct bpf_program *prog,
+			   size_t nr_maps, GElf_Shdr *shdr,
+			   Elf_Data *data, Elf_Data *symbols)
+{
+	int i, nrels;
+
+	pr_debug("collecting relocating info for: '%s'\n",
+		 prog->section_name);
+	nrels = shdr->sh_size / shdr->sh_entsize;
+
+	prog->reloc_desc = malloc(sizeof(*prog->reloc_desc) * nrels);
+	if (!prog->reloc_desc) {
+		pr_warning("failed to alloc memory in relocation\n");
+		return -ENOMEM;
+	}
+	prog->nr_reloc = nrels;
+
+	for (i = 0; i < nrels; i++) {
+		GElf_Sym sym;
+		GElf_Rel rel;
+		unsigned int insn_idx;
+		struct bpf_insn *insns = prog->insns;
+		size_t map_idx;
+
+		if (!gelf_getrel(data, i, &rel)) {
+			pr_warning("relocation: failed to get %d reloc\n", i);
+			return -EINVAL;
+		}
+
+		insn_idx = rel.r_offset / sizeof(struct bpf_insn);
+		pr_debug("relocation: insn_idx=%u\n", insn_idx);
+
+		if (!gelf_getsym(symbols,
+				 GELF_R_SYM(rel.r_info),
+				 &sym)) {
+			pr_warning("relocation: symbol %"PRIx64" not found\n",
+				   GELF_R_SYM(rel.r_info));
+			return -EINVAL;
+		}
+
+		if (insns[insn_idx].code != (BPF_LD | BPF_IMM | BPF_DW)) {
+			pr_warning("bpf: relocation: invalid relo for insns[%d].code 0x%x\n",
+				   insn_idx, insns[insn_idx].code);
+			return -EINVAL;
+		}
+
+		map_idx = sym.st_value / sizeof(struct bpf_map_def);
+		if (map_idx >= nr_maps) {
+			pr_warning("bpf relocation: map_idx %d large than %d\n",
+				   (int)map_idx, (int)nr_maps - 1);
+			return -EINVAL;
+		}
+
+		prog->reloc_desc[i].insn_idx = insn_idx;
+		prog->reloc_desc[i].map_idx = map_idx;
+	}
+	return 0;
+}
+
+static int bpf_object__collect_reloc(struct bpf_object *obj)
+{
+	int i, err;
+
+	if (!obj_elf_valid(obj)) {
+		pr_warning("Internal error: elf object is closed\n");
+		return -EINVAL;
+	}
+
+	for (i = 0; i < obj->efile.nr_reloc; i++) {
+		GElf_Shdr *shdr = &obj->efile.reloc[i].shdr;
+		Elf_Data *data = obj->efile.reloc[i].data;
+		int idx = shdr->sh_info;
+		struct bpf_program *prog;
+		size_t nr_maps = obj->maps_buf_sz /
+				 sizeof(struct bpf_map_def);
+
+		if (shdr->sh_type != SHT_REL) {
+			pr_warning("internal error at %d\n", __LINE__);
+			return -EINVAL;
+		}
+
+		prog = bpf_object__find_prog_by_idx(obj, idx);
+		if (!prog) {
+			pr_warning("relocation failed: no %d section\n",
+				   idx);
+			return -ENOENT;
+		}
+
+		err = bpf_program__collect_reloc(prog, nr_maps,
+						 shdr, data,
+						 obj->efile.symbols);
+		if (err)
+			return -EINVAL;
+	}
+	return 0;
+}
+
 static int bpf_object__validate(struct bpf_object *obj)
 {
 	if (obj->kern_version == 0) {
@@ -511,6 +633,8 @@ __bpf_object__open(const char *path, void *obj_buf, size_t obj_buf_sz)
 		goto out;
 	if (bpf_object__elf_collect(obj))
 		goto out;
+	if (bpf_object__collect_reloc(obj))
+		goto out;
 	if (bpf_object__validate(obj))
 		goto out;
 
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index dc966dd9fd75..6e75acdb9112 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -30,4 +30,17 @@ struct bpf_object *bpf_object__open_buffer(void *obj_buf,
 					   size_t obj_buf_sz);
 void bpf_object__close(struct bpf_object *object);
 
+/*
+ * We don't need __attribute__((packed)) now since it is
+ * unnecessary for 'bpf_map_def' because they are all aligned.
+ * In addition, using it will trigger -Wpacked warning message,
+ * and will be treated as an error due to -Werror.
+ */
+struct bpf_map_def {
+	unsigned int type;
+	unsigned int key_size;
+	unsigned int value_size;
+	unsigned int max_entries;
+};
+
 #endif