bpf/verifier: improve register value range tracking with ARSH

When helpers like bpf_get_stack returns an int value
and later on used for arithmetic computation, the LSH and ARSH
operations are often required to get proper sign extension into
64-bit. For example, without this patch:
    54: R0=inv(id=0,umax_value=800)
    54: (bf) r8 = r0
    55: R0=inv(id=0,umax_value=800) R8_w=inv(id=0,umax_value=800)
    55: (67) r8 <<= 32
    56: R8_w=inv(id=0,umax_value=3435973836800,var_off=(0x0; 0x3ff00000000))
    56: (c7) r8 s>>= 32
    57: R8=inv(id=0)
With this patch:
    54: R0=inv(id=0,umax_value=800)
    54: (bf) r8 = r0
    55: R0=inv(id=0,umax_value=800) R8_w=inv(id=0,umax_value=800)
    55: (67) r8 <<= 32
    56: R8_w=inv(id=0,umax_value=3435973836800,var_off=(0x0; 0x3ff00000000))
    56: (c7) r8 s>>= 32
    57: R8=inv(id=0, umax_value=800,var_off=(0x0; 0x3ff))
With better range of "R8", later on when "R8" is added to other register,
e.g., a map pointer or scalar-value register, the better register
range can be derived and verifier failure may be avoided.

In our later example,
    ......
    usize = bpf_get_stack(ctx, raw_data, max_len, BPF_F_USER_STACK);
    if (usize < 0)
        return 0;
    ksize = bpf_get_stack(ctx, raw_data + usize, max_len - usize, 0);
    ......
Without improving ARSH value range tracking, the register representing
"max_len - usize" will have smin_value equal to S64_MIN and will be
rejected by verifier.

Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

3 files changed, 36 insertions, 1 deletions

diff --git a/include/linux/tnum.h b/include/linux/tnum.h
index 0d2d3da46139..c7dc2b5902c0 100644
--- a/include/linux/tnum.h
+++ b/include/linux/tnum.h
@@ -23,8 +23,10 @@ struct tnum tnum_range(u64 min, u64 max);
 /* Arithmetic and logical ops */
 /* Shift a tnum left (by a fixed shift) */
 struct tnum tnum_lshift(struct tnum a, u8 shift);
-/* Shift a tnum right (by a fixed shift) */
+/* Shift (rsh) a tnum right (by a fixed shift) */
 struct tnum tnum_rshift(struct tnum a, u8 shift);
+/* Shift (arsh) a tnum right (by a fixed min_shift) */
+struct tnum tnum_arshift(struct tnum a, u8 min_shift);
 /* Add two tnums, return @a + @b */
 struct tnum tnum_add(struct tnum a, struct tnum b);
 /* Subtract two tnums, return @a - @b */
diff --git a/kernel/bpf/tnum.c b/kernel/bpf/tnum.c
index 1f4bf68c12db..938d41211be7 100644
--- a/kernel/bpf/tnum.c
+++ b/kernel/bpf/tnum.c
@@ -43,6 +43,16 @@ struct tnum tnum_rshift(struct tnum a, u8 shift)
 	return TNUM(a.value >> shift, a.mask >> shift);
 }
 
+struct tnum tnum_arshift(struct tnum a, u8 min_shift)
+{
+	/* if a.value is negative, arithmetic shifting by minimum shift
+	 * will have larger negative offset compared to more shifting.
+	 * If a.value is nonnegative, arithmetic shifting by minimum shift
+	 * will have larger positive offset compare to more shifting.
+	 */
+	return TNUM((s64)a.value >> min_shift, (s64)a.mask >> min_shift);
+}
+
 struct tnum tnum_add(struct tnum a, struct tnum b)
 {
 	u64 sm, sv, sigma, chi, mu;
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 6e3f859b3abf..712d8655e916 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -2974,6 +2974,29 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env,
 		/* We may learn something more from the var_off */
 		__update_reg_bounds(dst_reg);
 		break;
+	case BPF_ARSH:
+		if (umax_val >= insn_bitness) {
+			/* Shifts greater than 31 or 63 are undefined.
+			 * This includes shifts by a negative number.
+			 */
+			mark_reg_unknown(env, regs, insn->dst_reg);
+			break;
+		}
+
+		/* Upon reaching here, src_known is true and
+		 * umax_val is equal to umin_val.
+		 */
+		dst_reg->smin_value >>= umin_val;
+		dst_reg->smax_value >>= umin_val;
+		dst_reg->var_off = tnum_arshift(dst_reg->var_off, umin_val);
+
+		/* blow away the dst_reg umin_value/umax_value and rely on
+		 * dst_reg var_off to refine the result.
+		 */
+		dst_reg->umin_value = 0;
+		dst_reg->umax_value = U64_MAX;
+		__update_reg_bounds(dst_reg);
+		break;
 	default:
 		mark_reg_unknown(env, regs, insn->dst_reg);
 		break;