bpf: print spilled register state in stack slot

Print the same register state representation when printing stack state,
as we do for normal registers. Note that if stack slot contains
subregister spill (1, 2, or 4 byte long), we'll still emit "m0?" mask
for those bytes that are not part of spilled register.

While means we can get something like fp-8=0000scalar() for a 4-byte
spill with other 4 bytes still being STACK_ZERO.

Some example before and after, taken from the log of
pyperf_subprogs.bpf.o:

49: (7b) *(u64 *)(r10 -256) = r1      ; frame1: R1_w=ctx(off=0,imm=0) R10=fp0 fp-256_w=ctx
49: (7b) *(u64 *)(r10 -256) = r1      ; frame1: R1_w=ctx(off=0,imm=0) R10=fp0 fp-256_w=ctx(off=0,imm=0)

150: (7b) *(u64 *)(r10 -264) = r0     ; frame1: R0_w=map_value_or_null(id=6,off=0,ks=192,vs=4,imm=0) R10=fp0 fp-264_w=map_value_or_null
150: (7b) *(u64 *)(r10 -264) = r0     ; frame1: R0_w=map_value_or_null(id=6,off=0,ks=192,vs=4,imm=0) R10=fp0 fp-264_w=map_value_or_null(id=6,off=0,ks=192,vs=4,imm=0)

5192: (61) r1 = *(u32 *)(r10 -272)    ; frame1: R1_w=scalar(smin=smin32=0,smax=umax=smax32=umax32=15,var_off=(0x0; 0xf)) R10=fp0 fp-272=
5192: (61) r1 = *(u32 *)(r10 -272)    ; frame1: R1_w=scalar(smin=smin32=0,smax=umax=smax32=umax32=15,var_off=(0x0; 0xf)) R10=fp0 fp-272=????scalar(smin=smin32=0,smax=umax=smax32=umax32=15,var_off=(0x0; 0xf))

While at it, do a few other simple clean ups:
  - skip slot if it's not scratched before detecting whether it's valid;
  - move taking spilled_reg pointer outside of switch (only DYNPTR has
    to adjust that to get to the "main" slot);
  - don't recalculate types_buf second time for MISC/ZERO/default case.

Acked-by: Eduard Zingerman <eddyz87@gmail.com>
Acked-by: Stanislav Fomichev <sdf@google.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/r/20231118034623.3320920-5-andrii@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

kernel/bpf/log.c

@@ -618,7 +618,6 @@ void print_verifier_state(struct bpf_verifier_env *env, const struct bpf_func_st
 			  bool print_all)
 {
 	const struct bpf_reg_state *reg;
-	enum bpf_reg_type t;
 	int i;
 
 	if (state->frameno)
@@ -637,32 +636,38 @@ void print_verifier_state(struct bpf_verifier_env *env, const struct bpf_func_st
 	for (i = 0; i < state->allocated_stack / BPF_REG_SIZE; i++) {
 		char types_buf[BPF_REG_SIZE + 1];
 		bool valid = false;
+		u8 slot_type;
 		int j;
 
+		if (!print_all && !stack_slot_scratched(env, i))
+			continue;
+
 		for (j = 0; j < BPF_REG_SIZE; j++) {
-			if (state->stack[i].slot_type[j] != STACK_INVALID)
+			slot_type = state->stack[i].slot_type[j];
+			if (slot_type != STACK_INVALID)
 				valid = true;
-			types_buf[j] = slot_type_char[state->stack[i].slot_type[j]];
+			types_buf[j] = slot_type_char[slot_type];
 		}
 		types_buf[BPF_REG_SIZE] = 0;
 		if (!valid)
 			continue;
-		if (!print_all && !stack_slot_scratched(env, i))
-			continue;
+
+		reg = &state->stack[i].spilled_ptr;
 		switch (state->stack[i].slot_type[BPF_REG_SIZE - 1]) {
 		case STACK_SPILL:
-			reg = &state->stack[i].spilled_ptr;
-			t = reg->type;
+			/* print MISC/ZERO/INVALID slots above subreg spill */
+			for (j = 0; j < BPF_REG_SIZE; j++)
+				if (state->stack[i].slot_type[j] == STACK_SPILL)
+					break;
+			types_buf[j] = '\0';
 
 			verbose(env, " fp%d", (-i - 1) * BPF_REG_SIZE);
 			print_liveness(env, reg->live);
-			verbose(env, "=%s", t == SCALAR_VALUE ? "" : reg_type_str(env, t));
-			if (t == SCALAR_VALUE && reg->precise)
-				verbose(env, "P");
-			if (t == SCALAR_VALUE && tnum_is_const(reg->var_off))
-				verbose(env, "%lld", reg->var_off.value + reg->off);
+			verbose(env, "=%s", types_buf);
+			print_reg_state(env, reg);
 			break;
 		case STACK_DYNPTR:
+			/* skip to main dynptr slot */
 			i += BPF_DYNPTR_NR_SLOTS - 1;
 			reg = &state->stack[i].spilled_ptr;
 
@@ -674,7 +679,6 @@ void print_verifier_state(struct bpf_verifier_env *env, const struct bpf_func_st
 			break;
 		case STACK_ITER:
 			/* only main slot has ref_obj_id set; skip others */
-			reg = &state->stack[i].spilled_ptr;
 			if (!reg->ref_obj_id)
 				continue;
 
@@ -688,12 +692,6 @@ void print_verifier_state(struct bpf_verifier_env *env, const struct bpf_func_st
 		case STACK_MISC:
 		case STACK_ZERO:
 		default:
-			reg = &state->stack[i].spilled_ptr;
-
-			for (j = 0; j < BPF_REG_SIZE; j++)
-				types_buf[j] = slot_type_char[state->stack[i].slot_type[j]];
-			types_buf[BPF_REG_SIZE] = 0;
-
 			verbose(env, " fp%d", (-i - 1) * BPF_REG_SIZE);
 			print_liveness(env, reg->live);
 			verbose(env, "=%s", types_buf);