libbpf: Add weak ksym support to gen_loader

This extends existing ksym relocation code to also support relocating
weak ksyms. Care needs to be taken to zero out the src_reg (currently
BPF_PSEUOD_BTF_ID, always set for gen_loader by bpf_object__relocate_data)
when the BTF ID lookup fails at runtime.  This is not a problem for
libbpf as it only sets ext->is_set when BTF ID lookup succeeds (and only
proceeds in case of failure if ext->is_weak, leading to src_reg
remaining as 0 for weak unresolved ksym).

A pattern similar to emit_relo_kfunc_btf is followed of first storing
the default values and then jumping over actual stores in case of an
error. For src_reg adjustment, we also need to perform it when copying
the populated instruction, so depending on if copied insn[0].imm is 0 or
not, we decide to jump over the adjustment.

We cannot reach that point unless the ksym was weak and resolved and
zeroed out, as the emit_check_err will cause us to jump to cleanup
label, so we do not need to recheck whether the ksym is weak before
doing the adjustment after copying BTF ID and BTF FD.

This is consistent with how libbpf relocates weak ksym. Logging
statements are added to show the relocation result and aid debugging.
Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20211028063501.2239335-4-memxor@gmail.com

tools/lib/bpf/gen_loader.c

@@ -13,6 +13,7 @@
 #include "hashmap.h"
 #include "bpf_gen_internal.h"
 #include "skel_internal.h"
+#include <asm/byteorder.h>
 
 #define MAX_USED_MAPS	64
 #define MAX_USED_PROGS	32
@@ -777,12 +778,24 @@ static void emit_relo_ksym_typeless(struct bpf_gen *gen,
 	emit_ksym_relo_log(gen, relo, kdesc->ref);
 }
 
+static __u32 src_reg_mask(void)
+{
+#if defined(__LITTLE_ENDIAN_BITFIELD)
+	return 0x0f; /* src_reg,dst_reg,... */
+#elif defined(__BIG_ENDIAN_BITFIELD)
+	return 0xf0; /* dst_reg,src_reg,... */
+#else
+#error "Unsupported bit endianness, cannot proceed"
+#endif
+}
+
 /* Expects:
  * BPF_REG_8 - pointer to instruction
  */
 static void emit_relo_ksym_btf(struct bpf_gen *gen, struct ksym_relo_desc *relo, int insn)
 {
 	struct ksym_desc *kdesc;
+	__u32 reg_mask;
 
 	kdesc = get_ksym_desc(gen, relo);
 	if (!kdesc)
@@ -793,19 +806,35 @@ static void emit_relo_ksym_btf(struct bpf_gen *gen, struct ksym_relo_desc *relo,
 			       kdesc->insn + offsetof(struct bpf_insn, imm));
 		move_blob2blob(gen, insn + sizeof(struct bpf_insn) + offsetof(struct bpf_insn, imm), 4,
 			       kdesc->insn + sizeof(struct bpf_insn) + offsetof(struct bpf_insn, imm));
-		goto log;
+		emit(gen, BPF_LDX_MEM(BPF_W, BPF_REG_9, BPF_REG_8, offsetof(struct bpf_insn, imm)));
+		/* jump over src_reg adjustment if imm is not 0 */
+		emit(gen, BPF_JMP_IMM(BPF_JNE, BPF_REG_9, 0, 3));
+		goto clear_src_reg;
 	}
 	/* remember insn offset, so we can copy BTF ID and FD later */
 	kdesc->insn = insn;
 	emit_bpf_find_by_name_kind(gen, relo);
-	emit_check_err(gen);
+	if (!relo->is_weak)
+		emit_check_err(gen);
+	/* set default values as 0 */
+	emit(gen, BPF_ST_MEM(BPF_W, BPF_REG_8, offsetof(struct bpf_insn, imm), 0));
+	emit(gen, BPF_ST_MEM(BPF_W, BPF_REG_8, sizeof(struct bpf_insn) + offsetof(struct bpf_insn, imm), 0));
+	/* skip success case stores if ret < 0 */
+	emit(gen, BPF_JMP_IMM(BPF_JSLT, BPF_REG_7, 0, 4));
 	/* store btf_id into insn[insn_idx].imm */
 	emit(gen, BPF_STX_MEM(BPF_W, BPF_REG_8, BPF_REG_7, offsetof(struct bpf_insn, imm)));
 	/* store btf_obj_fd into insn[insn_idx + 1].imm */
 	emit(gen, BPF_ALU64_IMM(BPF_RSH, BPF_REG_7, 32));
 	emit(gen, BPF_STX_MEM(BPF_W, BPF_REG_8, BPF_REG_7,
 			      sizeof(struct bpf_insn) + offsetof(struct bpf_insn, imm)));
-log:
+	emit(gen, BPF_JMP_IMM(BPF_JSGE, BPF_REG_7, 0, 3));
+clear_src_reg:
+	/* clear bpf_object__relocate_data's src_reg assignment, otherwise we get a verifier failure */
+	reg_mask = src_reg_mask();
+	emit(gen, BPF_LDX_MEM(BPF_B, BPF_REG_9, BPF_REG_8, offsetofend(struct bpf_insn, code)));
+	emit(gen, BPF_ALU32_IMM(BPF_AND, BPF_REG_9, reg_mask));
+	emit(gen, BPF_STX_MEM(BPF_B, BPF_REG_8, BPF_REG_9, offsetofend(struct bpf_insn, code)));
+
 	emit_ksym_relo_log(gen, relo, kdesc->ref);
 }