[PATCH bpf-next v3 08/11] libbpf: support subprog address relocation

[Yonghong Song <yhs@fb.com>]

A new relocation RELO_SUBPROG_ADDR is added to capture
subprog addresses loaded with ld_imm64 insns. Such ld_imm64
insns are marked with BPF_PSEUDO_FUNC and will be passed to
kernel. For bpf_for_each_map_elem() case, kernel will
check that the to-be-used subprog address must be a static
function and replace it with proper actual jited func address.

Signed-off-by: Yonghong Song <yhs@fb.com>
---
 tools/lib/bpf/libbpf.c | 64 ++++++++++++++++++++++++++++++++++++++++--
 1 file changed, 61 insertions(+), 3 deletions(-)

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 21a3eedf070d..62d9ed56b081 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -188,6 +188,7 @@ enum reloc_type {
 	RELO_CALL,
 	RELO_DATA,
 	RELO_EXTERN,
+	RELO_SUBPROG_ADDR,
 };
 
 struct reloc_desc {
@@ -579,6 +580,11 @@ static bool is_ldimm64(struct bpf_insn *insn)
 	return insn->code == (BPF_LD | BPF_IMM | BPF_DW);
 }
 
+static bool insn_is_pseudo_func(struct bpf_insn *insn)
+{
+	return is_ldimm64(insn) && insn->src_reg == BPF_PSEUDO_FUNC;
+}
+
 static int
 bpf_object__init_prog(struct bpf_object *obj, struct bpf_program *prog,
 		      const char *name, size_t sec_idx, const char *sec_name,
@@ -2979,6 +2985,23 @@ static bool sym_is_extern(const GElf_Sym *sym)
 	       GELF_ST_TYPE(sym->st_info) == STT_NOTYPE;
 }
 
+static bool sym_is_subprog(const GElf_Sym *sym, int text_shndx)
+{
+	int bind = GELF_ST_BIND(sym->st_info);
+	int type = GELF_ST_TYPE(sym->st_info);
+
+	/* in .text section */
+	if (sym->st_shndx != text_shndx)
+		return false;
+
+	/* local function */
+	if (bind == STB_LOCAL && type == STT_SECTION)
+		return true;
+
+	/* global function */
+	return bind == STB_GLOBAL && type == STT_FUNC;
+}
+
 static int find_extern_btf_id(const struct btf *btf, const char *ext_name)
 {
 	const struct btf_type *t;
@@ -3435,6 +3458,23 @@ static int bpf_program__record_reloc(struct bpf_program *prog,
 		return -LIBBPF_ERRNO__RELOC;
 	}
 
+	/* loading subprog addresses */
+	if (sym_is_subprog(sym, obj->efile.text_shndx)) {
+		/* global_func: sym->st_value = offset in the section, insn->imm = 0.
+		 * local_func: sym->st_value = 0, insn->imm = offset in the section.
+		 */
+		if ((sym->st_value % BPF_INSN_SZ) || (insn->imm % BPF_INSN_SZ)) {
+			pr_warn("prog '%s': bad subprog addr relo against '%s' at offset %zu+%d\n",
+				prog->name, sym_name, (size_t)sym->st_value, insn->imm);
+			return -LIBBPF_ERRNO__RELOC;
+		}
+
+		reloc_desc->type = RELO_SUBPROG_ADDR;
+		reloc_desc->insn_idx = insn_idx;
+		reloc_desc->sym_off = sym->st_value;
+		return 0;
+	}
+
 	type = bpf_object__section_to_libbpf_map_type(obj, shdr_idx);
 	sym_sec_name = elf_sec_name(obj, elf_sec_by_idx(obj, shdr_idx));
 
@@ -6172,6 +6212,10 @@ bpf_object__relocate_data(struct bpf_object *obj, struct bpf_program *prog)
 			}
 			relo->processed = true;
 			break;
+		case RELO_SUBPROG_ADDR:
+			insn[0].src_reg = BPF_PSEUDO_FUNC;
+			/* will be handled as a follow up pass */
+			break;
 		case RELO_CALL:
 			/* will be handled as a follow up pass */
 			break;
@@ -6358,11 +6402,11 @@ bpf_object__reloc_code(struct bpf_object *obj, struct bpf_program *main_prog,
 
 	for (insn_idx = 0; insn_idx < prog->sec_insn_cnt; insn_idx++) {
 		insn = &main_prog->insns[prog->sub_insn_off + insn_idx];
-		if (!insn_is_subprog_call(insn))
+		if (!insn_is_subprog_call(insn) && !insn_is_pseudo_func(insn))
 			continue;
 
 		relo = find_prog_insn_relo(prog, insn_idx);
-		if (relo && relo->type != RELO_CALL) {
+		if (relo && relo->type != RELO_CALL && relo->type != RELO_SUBPROG_ADDR) {
 			pr_warn("prog '%s': unexpected relo for insn #%zu, type %d\n",
 				prog->name, insn_idx, relo->type);
 			return -LIBBPF_ERRNO__RELOC;
@@ -6374,8 +6418,22 @@ bpf_object__reloc_code(struct bpf_object *obj, struct bpf_program *main_prog,
 			 * call always has imm = -1, but for static functions
 			 * relocation is against STT_SECTION and insn->imm
 			 * points to a start of a static function
+			 *
+			 * for subprog addr relocation, the relo->sym_off + insn->imm is
+			 * the byte offset in the corresponding section.
 			 */
-			sub_insn_idx = relo->sym_off / BPF_INSN_SZ + insn->imm + 1;
+			if (relo->type == RELO_CALL)
+				sub_insn_idx = relo->sym_off / BPF_INSN_SZ + insn->imm + 1;
+			else
+				sub_insn_idx = (relo->sym_off + insn->imm) / BPF_INSN_SZ;
+		} else if (insn_is_pseudo_func(insn)) {
+			/*
+			 * RELO_SUBPROG_ADDR relo is always emitted even if both
+			 * functions are in the same section, so it shouldn't reach here.
+			 */
+			pr_warn("prog '%s': missing subprog addr relo for insn #%zu\n",
+				prog->name, insn_idx);
+			return -LIBBPF_ERRNO__RELOC;
 		} else {
 			/* if subprogram call is to a static function within
 			 * the same ELF section, there won't be any relocation
-- 
2.24.1