bpf: smarter verifier log number printing logic

Instead of always printing numbers as either decimals (and in some
cases, like for "imm=%llx", in hexadecimals), decide the form based on
actual values. For numbers in a reasonably small range (currently,
[0, U16_MAX] for unsigned values, and [S16_MIN, S16_MAX] for signed ones),
emit them as decimals. In all other cases, even for signed values,
emit them in hexadecimals.

For large values hex form is often times way more useful: it's easier to
see an exact difference between 0xffffffff80000000 and 0xffffffff7fffffff,
than between 18446744071562067966 and 18446744071562067967, as one
particular example.

Small values representing small pointer offsets or application
constants, on the other hand, are way more useful to be represented in
decimal notation.

Adjust reg_bounds register state parsing logic to take into account this
change.

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/20231118034623.3320920-8-andrii@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

2 files changed, 50 insertions, 35 deletions

diff --git a/tools/testing/selftests/bpf/prog_tests/reg_bounds.c b/tools/testing/selftests/bpf/prog_tests/reg_bounds.c
index 7a8b0bf0a7f8..fd4ab23e6f54 100644
--- a/tools/testing/selftests/bpf/prog_tests/reg_bounds.c
+++ b/tools/testing/selftests/bpf/prog_tests/reg_bounds.c
@@ -13,10 +13,13 @@
  */
 #define U64_MAX ((u64)UINT64_MAX)
 #define U32_MAX ((u32)UINT_MAX)
+#define U16_MAX ((u32)UINT_MAX)
 #define S64_MIN ((s64)INT64_MIN)
 #define S64_MAX ((s64)INT64_MAX)
 #define S32_MIN ((s32)INT_MIN)
 #define S32_MAX ((s32)INT_MAX)
+#define S16_MIN ((s16)0x80000000)
+#define S16_MAX ((s16)0x7fffffff)
 
 typedef unsigned long long ___u64;
 typedef unsigned int ___u32;
@@ -138,13 +141,17 @@ static enum num_t t_unsigned(enum num_t t)
 	}
 }
 
+#define UNUM_MAX_DECIMAL U16_MAX
+#define SNUM_MAX_DECIMAL S16_MAX
+#define SNUM_MIN_DECIMAL S16_MIN
+
 static bool num_is_small(enum num_t t, u64 x)
 {
 	switch (t) {
-	case U64: return (u64)x <= 256;
-	case U32: return (u32)x <= 256;
-	case S64: return (s64)x >= -256 && (s64)x <= 256;
-	case S32: return (s32)x >= -256 && (s32)x <= 256;
+	case U64: return (u64)x <= UNUM_MAX_DECIMAL;
+	case U32: return (u32)x <= UNUM_MAX_DECIMAL;
+	case S64: return (s64)x >= SNUM_MIN_DECIMAL && (s64)x <= SNUM_MAX_DECIMAL;
+	case S32: return (s32)x >= SNUM_MIN_DECIMAL && (s32)x <= SNUM_MAX_DECIMAL;
 	default: printf("num_is_small!\n"); exit(1);
 	}
 }
@@ -1023,20 +1030,19 @@ static int parse_reg_state(const char *s, struct reg_state *reg)
 	 */
 	struct {
 		const char *pfx;
-		const char *fmt;
 		u64 *dst, def;
 		bool is_32, is_set;
 	} *f, fields[8] = {
-		{"smin=", "%lld", &reg->r[S64].a, S64_MIN},
-		{"smax=", "%lld", &reg->r[S64].b, S64_MAX},
-		{"umin=", "%llu", &reg->r[U64].a, 0},
-		{"umax=", "%llu", &reg->r[U64].b, U64_MAX},
-		{"smin32=", "%lld", &reg->r[S32].a, (u32)S32_MIN, true},
-		{"smax32=", "%lld", &reg->r[S32].b, (u32)S32_MAX, true},
-		{"umin32=", "%llu", &reg->r[U32].a, 0,            true},
-		{"umax32=", "%llu", &reg->r[U32].b, U32_MAX,      true},
+		{"smin=", &reg->r[S64].a, S64_MIN},
+		{"smax=", &reg->r[S64].b, S64_MAX},
+		{"umin=", &reg->r[U64].a, 0},
+		{"umax=", &reg->r[U64].b, U64_MAX},
+		{"smin32=", &reg->r[S32].a, (u32)S32_MIN, true},
+		{"smax32=", &reg->r[S32].b, (u32)S32_MAX, true},
+		{"umin32=", &reg->r[U32].a, 0,            true},
+		{"umax32=", &reg->r[U32].b, U32_MAX,      true},
 	};
-	const char *p, *fmt;
+	const char *p;
 	int i;
 
 	p = strchr(s, '=');
@@ -1050,8 +1056,13 @@ static int parse_reg_state(const char *s, struct reg_state *reg)
 		long long sval;
 		enum num_t t;
 
-		if (sscanf(p, "%lld", &sval) != 1)
-			return -EINVAL;
+		if (p[0] == '0' && p[1] == 'x') {
+			if (sscanf(p, "%llx", &sval) != 1)
+				return -EINVAL;
+		} else {
+			if (sscanf(p, "%lld", &sval) != 1)
+				return -EINVAL;
+		}
 
 		reg->valid = true;
 		for (t = first_t; t <= last_t; t++) {
@@ -1075,9 +1086,13 @@ static int parse_reg_state(const char *s, struct reg_state *reg)
 
 		if (mcnt) {
 			/* populate all matched fields */
-			fmt = fields[midxs[0]].fmt;
-			if (sscanf(p, fmt, &val) != 1)
-				return -EINVAL;
+			if (p[0] == '0' && p[1] == 'x') {
+				if (sscanf(p, "%llx", &val) != 1)
+					return -EINVAL;
+			} else {
+				if (sscanf(p, "%lld", &val) != 1)
+					return -EINVAL;
+			}
 
 			for (i = 0; i < mcnt; i++) {
 				f = &fields[midxs[i]];
diff --git a/tools/testing/selftests/bpf/progs/exceptions_assert.c b/tools/testing/selftests/bpf/progs/exceptions_assert.c
index 26f7d67432cc..49efaed143fc 100644
--- a/tools/testing/selftests/bpf/progs/exceptions_assert.c
+++ b/tools/testing/selftests/bpf/progs/exceptions_assert.c
@@ -18,48 +18,48 @@
 		return *(u64 *)num;					\
 	}
 
-__msg(": R0_w=-2147483648 R10=fp0")
+__msg(": R0_w=0xffffffff80000000 R10=fp0")
 check_assert(s64, eq, int_min, INT_MIN);
-__msg(": R0_w=2147483647 R10=fp0")
+__msg(": R0_w=0x7fffffff R10=fp0")
 check_assert(s64, eq, int_max, INT_MAX);
 __msg(": R0_w=0 R10=fp0")
 check_assert(s64, eq, zero, 0);
-__msg(": R0_w=-9223372036854775808 R1_w=-9223372036854775808 R10=fp0")
+__msg(": R0_w=0x8000000000000000 R1_w=0x8000000000000000 R10=fp0")
 check_assert(s64, eq, llong_min, LLONG_MIN);
-__msg(": R0_w=9223372036854775807 R1_w=9223372036854775807 R10=fp0")
+__msg(": R0_w=0x7fffffffffffffff R1_w=0x7fffffffffffffff R10=fp0")
 check_assert(s64, eq, llong_max, LLONG_MAX);
 
-__msg(": R0_w=scalar(smax=2147483646) R10=fp0")
+__msg(": R0_w=scalar(smax=0x7ffffffe) R10=fp0")
 check_assert(s64, lt, pos, INT_MAX);
-__msg(": R0_w=scalar(smax=-1,umin=9223372036854775808,var_off=(0x8000000000000000; 0x7fffffffffffffff))")
+__msg(": R0_w=scalar(smax=-1,umin=0x8000000000000000,var_off=(0x8000000000000000; 0x7fffffffffffffff))")
 check_assert(s64, lt, zero, 0);
-__msg(": R0_w=scalar(smax=-2147483649,umin=9223372036854775808,umax=18446744071562067967,var_off=(0x8000000000000000; 0x7fffffffffffffff))")
+__msg(": R0_w=scalar(smax=0xffffffff7fffffff,umin=0x8000000000000000,umax=0xffffffff7fffffff,var_off=(0x8000000000000000; 0x7fffffffffffffff))")
 check_assert(s64, lt, neg, INT_MIN);
 
-__msg(": R0_w=scalar(smax=2147483647) R10=fp0")
+__msg(": R0_w=scalar(smax=0x7fffffff) R10=fp0")
 check_assert(s64, le, pos, INT_MAX);
 __msg(": R0_w=scalar(smax=0) R10=fp0")
 check_assert(s64, le, zero, 0);
-__msg(": R0_w=scalar(smax=-2147483648,umin=9223372036854775808,umax=18446744071562067968,var_off=(0x8000000000000000; 0x7fffffffffffffff))")
+__msg(": R0_w=scalar(smax=0xffffffff80000000,umin=0x8000000000000000,umax=0xffffffff80000000,var_off=(0x8000000000000000; 0x7fffffffffffffff))")
 check_assert(s64, le, neg, INT_MIN);
 
-__msg(": R0_w=scalar(smin=umin=2147483648,umax=9223372036854775807,var_off=(0x0; 0x7fffffffffffffff))")
+__msg(": R0_w=scalar(smin=umin=0x80000000,umax=0x7fffffffffffffff,var_off=(0x0; 0x7fffffffffffffff))")
 check_assert(s64, gt, pos, INT_MAX);
-__msg(": R0_w=scalar(smin=umin=1,umax=9223372036854775807,var_off=(0x0; 0x7fffffffffffffff))")
+__msg(": R0_w=scalar(smin=umin=1,umax=0x7fffffffffffffff,var_off=(0x0; 0x7fffffffffffffff))")
 check_assert(s64, gt, zero, 0);
-__msg(": R0_w=scalar(smin=-2147483647) R10=fp0")
+__msg(": R0_w=scalar(smin=0xffffffff80000001) R10=fp0")
 check_assert(s64, gt, neg, INT_MIN);
 
-__msg(": R0_w=scalar(smin=umin=2147483647,umax=9223372036854775807,var_off=(0x0; 0x7fffffffffffffff))")
+__msg(": R0_w=scalar(smin=umin=0x7fffffff,umax=0x7fffffffffffffff,var_off=(0x0; 0x7fffffffffffffff))")
 check_assert(s64, ge, pos, INT_MAX);
-__msg(": R0_w=scalar(smin=0,umax=9223372036854775807,var_off=(0x0; 0x7fffffffffffffff)) R10=fp0")
+__msg(": R0_w=scalar(smin=0,umax=0x7fffffffffffffff,var_off=(0x0; 0x7fffffffffffffff)) R10=fp0")
 check_assert(s64, ge, zero, 0);
-__msg(": R0_w=scalar(smin=-2147483648) R10=fp0")
+__msg(": R0_w=scalar(smin=0xffffffff80000000) R10=fp0")
 check_assert(s64, ge, neg, INT_MIN);
 
 SEC("?tc")
 __log_level(2) __failure
-__msg(": R0=0 R1=ctx() R2=scalar(smin=smin32=-2147483646,smax=smax32=2147483645) R10=fp0")
+__msg(": R0=0 R1=ctx() R2=scalar(smin=0xffffffff80000002,smax=smax32=0x7ffffffd,smin32=0x80000002) R10=fp0")
 int check_assert_range_s64(struct __sk_buff *ctx)
 {
 	struct bpf_sock *sk = ctx->sk;