OpenCloudOS-Kernel/kernel/bpf/tnum.c

215 lines
5.1 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-only
/* tnum: tracked (or tristate) numbers
*
* A tnum tracks knowledge about the bits of a value. Each bit can be either
* known (0 or 1), or unknown (x). Arithmetic operations on tnums will
* propagate the unknown bits such that the tnum result represents all the
* possible results for possible values of the operands.
*/
#include <linux/kernel.h>
#include <linux/tnum.h>
#define TNUM(_v, _m) (struct tnum){.value = _v, .mask = _m}
/* A completely unknown value */
const struct tnum tnum_unknown = { .value = 0, .mask = -1 };
struct tnum tnum_const(u64 value)
{
return TNUM(value, 0);
}
struct tnum tnum_range(u64 min, u64 max)
{
u64 chi = min ^ max, delta;
u8 bits = fls64(chi);
/* special case, needed because 1ULL << 64 is undefined */
if (bits > 63)
return tnum_unknown;
/* e.g. if chi = 4, bits = 3, delta = (1<<3) - 1 = 7.
* if chi = 0, bits = 0, delta = (1<<0) - 1 = 0, so we return
* constant min (since min == max).
*/
delta = (1ULL << bits) - 1;
return TNUM(min & ~delta, delta);
}
struct tnum tnum_lshift(struct tnum a, u8 shift)
{
return TNUM(a.value << shift, a.mask << shift);
}
struct tnum tnum_rshift(struct tnum a, u8 shift)
{
return TNUM(a.value >> shift, a.mask >> shift);
}
bpf: Fix incorrect verifier simulation of ARSH under ALU32 Anatoly has been fuzzing with kBdysch harness and reported a hang in one of the outcomes: 0: R1=ctx(id=0,off=0,imm=0) R10=fp0 0: (85) call bpf_get_socket_cookie#46 1: R0_w=invP(id=0) R10=fp0 1: (57) r0 &= 808464432 2: R0_w=invP(id=0,umax_value=808464432,var_off=(0x0; 0x30303030)) R10=fp0 2: (14) w0 -= 810299440 3: R0_w=invP(id=0,umax_value=4294967295,var_off=(0xcf800000; 0x3077fff0)) R10=fp0 3: (c4) w0 s>>= 1 4: R0_w=invP(id=0,umin_value=1740636160,umax_value=2147221496,var_off=(0x67c00000; 0x183bfff8)) R10=fp0 4: (76) if w0 s>= 0x30303030 goto pc+216 221: R0_w=invP(id=0,umin_value=1740636160,umax_value=2147221496,var_off=(0x67c00000; 0x183bfff8)) R10=fp0 221: (95) exit processed 6 insns (limit 1000000) [...] Taking a closer look, the program was xlated as follows: # ./bpftool p d x i 12 0: (85) call bpf_get_socket_cookie#7800896 1: (bf) r6 = r0 2: (57) r6 &= 808464432 3: (14) w6 -= 810299440 4: (c4) w6 s>>= 1 5: (76) if w6 s>= 0x30303030 goto pc+216 6: (05) goto pc-1 7: (05) goto pc-1 8: (05) goto pc-1 [...] 220: (05) goto pc-1 221: (05) goto pc-1 222: (95) exit Meaning, the visible effect is very similar to f54c7898ed1c ("bpf: Fix precision tracking for unbounded scalars"), that is, the fall-through branch in the instruction 5 is considered to be never taken given the conclusion from the min/max bounds tracking in w6, and therefore the dead-code sanitation rewrites it as goto pc-1. However, real-life input disagrees with verification analysis since a soft-lockup was observed. The bug sits in the analysis of the ARSH. The definition is that we shift the target register value right by K bits through shifting in copies of its sign bit. In adjust_scalar_min_max_vals(), we do first coerce the register into 32 bit mode, same happens after simulating the operation. However, for the case of simulating the actual ARSH, we don't take the mode into account and act as if it's always 64 bit, but location of sign bit is different: dst_reg->smin_value >>= umin_val; dst_reg->smax_value >>= umin_val; dst_reg->var_off = tnum_arshift(dst_reg->var_off, umin_val); Consider an unknown R0 where bpf_get_socket_cookie() (or others) would for example return 0xffff. With the above ARSH simulation, we'd see the following results: [...] 1: R1=ctx(id=0,off=0,imm=0) R2_w=invP65535 R10=fp0 1: (85) call bpf_get_socket_cookie#46 2: R0_w=invP(id=0) R10=fp0 2: (57) r0 &= 808464432 -> R0_runtime = 0x3030 3: R0_w=invP(id=0,umax_value=808464432,var_off=(0x0; 0x30303030)) R10=fp0 3: (14) w0 -= 810299440 -> R0_runtime = 0xcfb40000 4: R0_w=invP(id=0,umax_value=4294967295,var_off=(0xcf800000; 0x3077fff0)) R10=fp0 (0xffffffff) 4: (c4) w0 s>>= 1 -> R0_runtime = 0xe7da0000 5: R0_w=invP(id=0,umin_value=1740636160,umax_value=2147221496,var_off=(0x67c00000; 0x183bfff8)) R10=fp0 (0x67c00000) (0x7ffbfff8) [...] In insn 3, we have a runtime value of 0xcfb40000, which is '1100 1111 1011 0100 0000 0000 0000 0000', the result after the shift has 0xe7da0000 that is '1110 0111 1101 1010 0000 0000 0000 0000', where the sign bit is correctly retained in 32 bit mode. In insn4, the umax was 0xffffffff, and changed into 0x7ffbfff8 after the shift, that is, '0111 1111 1111 1011 1111 1111 1111 1000' and means here that the simulation didn't retain the sign bit. With above logic, the updates happen on the 64 bit min/max bounds and given we coerced the register, the sign bits of the bounds are cleared as well, meaning, we need to force the simulation into s32 space for 32 bit alu mode. Verification after the fix below. We're first analyzing the fall-through branch on 32 bit signed >= test eventually leading to rejection of the program in this specific case: 0: R1=ctx(id=0,off=0,imm=0) R10=fp0 0: (b7) r2 = 808464432 1: R1=ctx(id=0,off=0,imm=0) R2_w=invP808464432 R10=fp0 1: (85) call bpf_get_socket_cookie#46 2: R0_w=invP(id=0) R10=fp0 2: (bf) r6 = r0 3: R0_w=invP(id=0) R6_w=invP(id=0) R10=fp0 3: (57) r6 &= 808464432 4: R0_w=invP(id=0) R6_w=invP(id=0,umax_value=808464432,var_off=(0x0; 0x30303030)) R10=fp0 4: (14) w6 -= 810299440 5: R0_w=invP(id=0) R6_w=invP(id=0,umax_value=4294967295,var_off=(0xcf800000; 0x3077fff0)) R10=fp0 5: (c4) w6 s>>= 1 6: R0_w=invP(id=0) R6_w=invP(id=0,umin_value=3888119808,umax_value=4294705144,var_off=(0xe7c00000; 0x183bfff8)) R10=fp0 (0x67c00000) (0xfffbfff8) 6: (76) if w6 s>= 0x30303030 goto pc+216 7: R0_w=invP(id=0) R6_w=invP(id=0,umin_value=3888119808,umax_value=4294705144,var_off=(0xe7c00000; 0x183bfff8)) R10=fp0 7: (30) r0 = *(u8 *)skb[808464432] BPF_LD_[ABS|IND] uses reserved fields processed 8 insns (limit 1000000) [...] Fixes: 9cbe1f5a32dc ("bpf/verifier: improve register value range tracking with ARSH") Reported-by: Anatoly Trosinenko <anatoly.trosinenko@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Yonghong Song <yhs@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Link: https://lore.kernel.org/bpf/20200115204733.16648-1-daniel@iogearbox.net
2020-01-16 04:47:33 +08:00
struct tnum tnum_arshift(struct tnum a, u8 min_shift, u8 insn_bitness)
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>
2018-04-29 13:28:11 +08:00
{
/* 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.
*/
bpf: Fix incorrect verifier simulation of ARSH under ALU32 Anatoly has been fuzzing with kBdysch harness and reported a hang in one of the outcomes: 0: R1=ctx(id=0,off=0,imm=0) R10=fp0 0: (85) call bpf_get_socket_cookie#46 1: R0_w=invP(id=0) R10=fp0 1: (57) r0 &= 808464432 2: R0_w=invP(id=0,umax_value=808464432,var_off=(0x0; 0x30303030)) R10=fp0 2: (14) w0 -= 810299440 3: R0_w=invP(id=0,umax_value=4294967295,var_off=(0xcf800000; 0x3077fff0)) R10=fp0 3: (c4) w0 s>>= 1 4: R0_w=invP(id=0,umin_value=1740636160,umax_value=2147221496,var_off=(0x67c00000; 0x183bfff8)) R10=fp0 4: (76) if w0 s>= 0x30303030 goto pc+216 221: R0_w=invP(id=0,umin_value=1740636160,umax_value=2147221496,var_off=(0x67c00000; 0x183bfff8)) R10=fp0 221: (95) exit processed 6 insns (limit 1000000) [...] Taking a closer look, the program was xlated as follows: # ./bpftool p d x i 12 0: (85) call bpf_get_socket_cookie#7800896 1: (bf) r6 = r0 2: (57) r6 &= 808464432 3: (14) w6 -= 810299440 4: (c4) w6 s>>= 1 5: (76) if w6 s>= 0x30303030 goto pc+216 6: (05) goto pc-1 7: (05) goto pc-1 8: (05) goto pc-1 [...] 220: (05) goto pc-1 221: (05) goto pc-1 222: (95) exit Meaning, the visible effect is very similar to f54c7898ed1c ("bpf: Fix precision tracking for unbounded scalars"), that is, the fall-through branch in the instruction 5 is considered to be never taken given the conclusion from the min/max bounds tracking in w6, and therefore the dead-code sanitation rewrites it as goto pc-1. However, real-life input disagrees with verification analysis since a soft-lockup was observed. The bug sits in the analysis of the ARSH. The definition is that we shift the target register value right by K bits through shifting in copies of its sign bit. In adjust_scalar_min_max_vals(), we do first coerce the register into 32 bit mode, same happens after simulating the operation. However, for the case of simulating the actual ARSH, we don't take the mode into account and act as if it's always 64 bit, but location of sign bit is different: dst_reg->smin_value >>= umin_val; dst_reg->smax_value >>= umin_val; dst_reg->var_off = tnum_arshift(dst_reg->var_off, umin_val); Consider an unknown R0 where bpf_get_socket_cookie() (or others) would for example return 0xffff. With the above ARSH simulation, we'd see the following results: [...] 1: R1=ctx(id=0,off=0,imm=0) R2_w=invP65535 R10=fp0 1: (85) call bpf_get_socket_cookie#46 2: R0_w=invP(id=0) R10=fp0 2: (57) r0 &= 808464432 -> R0_runtime = 0x3030 3: R0_w=invP(id=0,umax_value=808464432,var_off=(0x0; 0x30303030)) R10=fp0 3: (14) w0 -= 810299440 -> R0_runtime = 0xcfb40000 4: R0_w=invP(id=0,umax_value=4294967295,var_off=(0xcf800000; 0x3077fff0)) R10=fp0 (0xffffffff) 4: (c4) w0 s>>= 1 -> R0_runtime = 0xe7da0000 5: R0_w=invP(id=0,umin_value=1740636160,umax_value=2147221496,var_off=(0x67c00000; 0x183bfff8)) R10=fp0 (0x67c00000) (0x7ffbfff8) [...] In insn 3, we have a runtime value of 0xcfb40000, which is '1100 1111 1011 0100 0000 0000 0000 0000', the result after the shift has 0xe7da0000 that is '1110 0111 1101 1010 0000 0000 0000 0000', where the sign bit is correctly retained in 32 bit mode. In insn4, the umax was 0xffffffff, and changed into 0x7ffbfff8 after the shift, that is, '0111 1111 1111 1011 1111 1111 1111 1000' and means here that the simulation didn't retain the sign bit. With above logic, the updates happen on the 64 bit min/max bounds and given we coerced the register, the sign bits of the bounds are cleared as well, meaning, we need to force the simulation into s32 space for 32 bit alu mode. Verification after the fix below. We're first analyzing the fall-through branch on 32 bit signed >= test eventually leading to rejection of the program in this specific case: 0: R1=ctx(id=0,off=0,imm=0) R10=fp0 0: (b7) r2 = 808464432 1: R1=ctx(id=0,off=0,imm=0) R2_w=invP808464432 R10=fp0 1: (85) call bpf_get_socket_cookie#46 2: R0_w=invP(id=0) R10=fp0 2: (bf) r6 = r0 3: R0_w=invP(id=0) R6_w=invP(id=0) R10=fp0 3: (57) r6 &= 808464432 4: R0_w=invP(id=0) R6_w=invP(id=0,umax_value=808464432,var_off=(0x0; 0x30303030)) R10=fp0 4: (14) w6 -= 810299440 5: R0_w=invP(id=0) R6_w=invP(id=0,umax_value=4294967295,var_off=(0xcf800000; 0x3077fff0)) R10=fp0 5: (c4) w6 s>>= 1 6: R0_w=invP(id=0) R6_w=invP(id=0,umin_value=3888119808,umax_value=4294705144,var_off=(0xe7c00000; 0x183bfff8)) R10=fp0 (0x67c00000) (0xfffbfff8) 6: (76) if w6 s>= 0x30303030 goto pc+216 7: R0_w=invP(id=0) R6_w=invP(id=0,umin_value=3888119808,umax_value=4294705144,var_off=(0xe7c00000; 0x183bfff8)) R10=fp0 7: (30) r0 = *(u8 *)skb[808464432] BPF_LD_[ABS|IND] uses reserved fields processed 8 insns (limit 1000000) [...] Fixes: 9cbe1f5a32dc ("bpf/verifier: improve register value range tracking with ARSH") Reported-by: Anatoly Trosinenko <anatoly.trosinenko@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Yonghong Song <yhs@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Link: https://lore.kernel.org/bpf/20200115204733.16648-1-daniel@iogearbox.net
2020-01-16 04:47:33 +08:00
if (insn_bitness == 32)
return TNUM((u32)(((s32)a.value) >> min_shift),
(u32)(((s32)a.mask) >> min_shift));
else
return TNUM((s64)a.value >> min_shift,
(s64)a.mask >> min_shift);
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>
2018-04-29 13:28:11 +08:00
}
struct tnum tnum_add(struct tnum a, struct tnum b)
{
u64 sm, sv, sigma, chi, mu;
sm = a.mask + b.mask;
sv = a.value + b.value;
sigma = sm + sv;
chi = sigma ^ sv;
mu = chi | a.mask | b.mask;
return TNUM(sv & ~mu, mu);
}
struct tnum tnum_sub(struct tnum a, struct tnum b)
{
u64 dv, alpha, beta, chi, mu;
dv = a.value - b.value;
alpha = dv + a.mask;
beta = dv - b.mask;
chi = alpha ^ beta;
mu = chi | a.mask | b.mask;
return TNUM(dv & ~mu, mu);
}
struct tnum tnum_and(struct tnum a, struct tnum b)
{
u64 alpha, beta, v;
alpha = a.value | a.mask;
beta = b.value | b.mask;
v = a.value & b.value;
return TNUM(v, alpha & beta & ~v);
}
struct tnum tnum_or(struct tnum a, struct tnum b)
{
u64 v, mu;
v = a.value | b.value;
mu = a.mask | b.mask;
return TNUM(v, mu & ~v);
}
struct tnum tnum_xor(struct tnum a, struct tnum b)
{
u64 v, mu;
v = a.value ^ b.value;
mu = a.mask | b.mask;
return TNUM(v & ~mu, mu);
}
bpf, tnums: Provably sound, faster, and more precise algorithm for tnum_mul This patch introduces a new algorithm for multiplication of tristate numbers (tnums) that is provably sound. It is faster and more precise when compared to the existing method. Like the existing method, this new algorithm follows the long multiplication algorithm. The idea is to generate partial products by multiplying each bit in the multiplier (tnum a) with the multiplicand (tnum b), and adding the partial products after appropriately bit-shifting them. The new algorithm, however, uses just a single loop over the bits of the multiplier (tnum a) and accumulates only the uncertain components of the multiplicand (tnum b) into a mask-only tnum. The following paper explains the algorithm in more detail: https://arxiv.org/abs/2105.05398. A natural way to construct the tnum product is by performing a tnum addition on all the partial products. This algorithm presents another method of doing this: decompose each partial product into two tnums, consisting of the values and the masks separately. The mask-sum is accumulated within the loop in acc_m. The value-sum tnum is generated using a.value * b.value. The tnum constructed by tnum addition of the value-sum and the mask-sum contains all possible summations of concrete values drawn from the partial product tnums pairwise. We prove this result in the paper. Our evaluations show that the new algorithm is overall more precise (producing tnums with less uncertain components) than the existing method. As an illustrative example, consider the input tnums A and B. The numbers in the parenthesis correspond to (value;mask). A = 000000x1 (1;2) B = 0010011x (38;1) A * B (existing) = xxxxxxxx (0;255) A * B (new) = 0x1xxxxx (32;95) Importantly, we present a proof of soundness of the new algorithm in the aforementioned paper. Additionally, we show that this new algorithm is empirically faster than the existing method. Co-developed-by: Matan Shachnai <m.shachnai@rutgers.edu> Co-developed-by: Srinivas Narayana <srinivas.narayana@rutgers.edu> Co-developed-by: Santosh Nagarakatte <santosh.nagarakatte@rutgers.edu> Signed-off-by: Matan Shachnai <m.shachnai@rutgers.edu> Signed-off-by: Srinivas Narayana <srinivas.narayana@rutgers.edu> Signed-off-by: Santosh Nagarakatte <santosh.nagarakatte@rutgers.edu> Signed-off-by: Harishankar Vishwanathan <harishankar.vishwanathan@rutgers.edu> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Reviewed-by: Edward Cree <ecree.xilinx@gmail.com> Link: https://arxiv.org/abs/2105.05398 Link: https://lore.kernel.org/bpf/20210531020157.7386-1-harishankar.vishwanathan@rutgers.edu
2021-05-31 10:01:57 +08:00
/* Generate partial products by multiplying each bit in the multiplier (tnum a)
* with the multiplicand (tnum b), and add the partial products after
* appropriately bit-shifting them. Instead of directly performing tnum addition
* on the generated partial products, equivalenty, decompose each partial
* product into two tnums, consisting of the value-sum (acc_v) and the
* mask-sum (acc_m) and then perform tnum addition on them. The following paper
* explains the algorithm in more detail: https://arxiv.org/abs/2105.05398.
*/
struct tnum tnum_mul(struct tnum a, struct tnum b)
{
bpf, tnums: Provably sound, faster, and more precise algorithm for tnum_mul This patch introduces a new algorithm for multiplication of tristate numbers (tnums) that is provably sound. It is faster and more precise when compared to the existing method. Like the existing method, this new algorithm follows the long multiplication algorithm. The idea is to generate partial products by multiplying each bit in the multiplier (tnum a) with the multiplicand (tnum b), and adding the partial products after appropriately bit-shifting them. The new algorithm, however, uses just a single loop over the bits of the multiplier (tnum a) and accumulates only the uncertain components of the multiplicand (tnum b) into a mask-only tnum. The following paper explains the algorithm in more detail: https://arxiv.org/abs/2105.05398. A natural way to construct the tnum product is by performing a tnum addition on all the partial products. This algorithm presents another method of doing this: decompose each partial product into two tnums, consisting of the values and the masks separately. The mask-sum is accumulated within the loop in acc_m. The value-sum tnum is generated using a.value * b.value. The tnum constructed by tnum addition of the value-sum and the mask-sum contains all possible summations of concrete values drawn from the partial product tnums pairwise. We prove this result in the paper. Our evaluations show that the new algorithm is overall more precise (producing tnums with less uncertain components) than the existing method. As an illustrative example, consider the input tnums A and B. The numbers in the parenthesis correspond to (value;mask). A = 000000x1 (1;2) B = 0010011x (38;1) A * B (existing) = xxxxxxxx (0;255) A * B (new) = 0x1xxxxx (32;95) Importantly, we present a proof of soundness of the new algorithm in the aforementioned paper. Additionally, we show that this new algorithm is empirically faster than the existing method. Co-developed-by: Matan Shachnai <m.shachnai@rutgers.edu> Co-developed-by: Srinivas Narayana <srinivas.narayana@rutgers.edu> Co-developed-by: Santosh Nagarakatte <santosh.nagarakatte@rutgers.edu> Signed-off-by: Matan Shachnai <m.shachnai@rutgers.edu> Signed-off-by: Srinivas Narayana <srinivas.narayana@rutgers.edu> Signed-off-by: Santosh Nagarakatte <santosh.nagarakatte@rutgers.edu> Signed-off-by: Harishankar Vishwanathan <harishankar.vishwanathan@rutgers.edu> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Reviewed-by: Edward Cree <ecree.xilinx@gmail.com> Link: https://arxiv.org/abs/2105.05398 Link: https://lore.kernel.org/bpf/20210531020157.7386-1-harishankar.vishwanathan@rutgers.edu
2021-05-31 10:01:57 +08:00
u64 acc_v = a.value * b.value;
struct tnum acc_m = TNUM(0, 0);
while (a.value || a.mask) {
/* LSB of tnum a is a certain 1 */
if (a.value & 1)
acc_m = tnum_add(acc_m, TNUM(0, b.mask));
/* LSB of tnum a is uncertain */
else if (a.mask & 1)
acc_m = tnum_add(acc_m, TNUM(0, b.value | b.mask));
/* Note: no case for LSB is certain 0 */
a = tnum_rshift(a, 1);
b = tnum_lshift(b, 1);
}
return tnum_add(TNUM(acc_v, 0), acc_m);
}
/* Note that if a and b disagree - i.e. one has a 'known 1' where the other has
* a 'known 0' - this will return a 'known 1' for that bit.
*/
struct tnum tnum_intersect(struct tnum a, struct tnum b)
{
u64 v, mu;
v = a.value | b.value;
mu = a.mask & b.mask;
return TNUM(v & ~mu, mu);
}
struct tnum tnum_cast(struct tnum a, u8 size)
{
a.value &= (1ULL << (size * 8)) - 1;
a.mask &= (1ULL << (size * 8)) - 1;
return a;
}
bool tnum_is_aligned(struct tnum a, u64 size)
{
if (!size)
return true;
return !((a.value | a.mask) & (size - 1));
}
bool tnum_in(struct tnum a, struct tnum b)
{
if (b.mask & ~a.mask)
return false;
b.value &= ~a.mask;
return a.value == b.value;
}
int tnum_strn(char *str, size_t size, struct tnum a)
{
return snprintf(str, size, "(%#llx; %#llx)", a.value, a.mask);
}
EXPORT_SYMBOL_GPL(tnum_strn);
int tnum_sbin(char *str, size_t size, struct tnum a)
{
size_t n;
for (n = 64; n; n--) {
if (n < size) {
if (a.mask & 1)
str[n - 1] = 'x';
else if (a.value & 1)
str[n - 1] = '1';
else
str[n - 1] = '0';
}
a.mask >>= 1;
a.value >>= 1;
}
str[min(size - 1, (size_t)64)] = 0;
return 64;
}
bpf: Verifier, do explicit ALU32 bounds tracking It is not possible for the current verifier to track ALU32 and JMP ops correctly. This can result in the verifier aborting with errors even though the program should be verifiable. BPF codes that hit this can work around it by changin int variables to 64-bit types, marking variables volatile, etc. But this is all very ugly so it would be better to avoid these tricks. But, the main reason to address this now is do_refine_retval_range() was assuming return values could not be negative. Once we fixed this code that was previously working will no longer work. See do_refine_retval_range() patch for details. And we don't want to suddenly cause programs that used to work to fail. The simplest example code snippet that illustrates the problem is likely this, 53: w8 = w0 // r8 <- [0, S32_MAX], // w8 <- [-S32_MIN, X] 54: w8 <s 0 // r8 <- [0, U32_MAX] // w8 <- [0, X] The expected 64-bit and 32-bit bounds after each line are shown on the right. The current issue is without the w* bounds we are forced to use the worst case bound of [0, U32_MAX]. To resolve this type of case, jmp32 creating divergent 32-bit bounds from 64-bit bounds, we add explicit 32-bit register bounds s32_{min|max}_value and u32_{min|max}_value. Then from branch_taken logic creating new bounds we can track 32-bit bounds explicitly. The next case we observed is ALU ops after the jmp32, 53: w8 = w0 // r8 <- [0, S32_MAX], // w8 <- [-S32_MIN, X] 54: w8 <s 0 // r8 <- [0, U32_MAX] // w8 <- [0, X] 55: w8 += 1 // r8 <- [0, U32_MAX+1] // w8 <- [0, X+1] In order to keep the bounds accurate at this point we also need to track ALU32 ops. To do this we add explicit ALU32 logic for each of the ALU ops, mov, add, sub, etc. Finally there is a question of how and when to merge bounds. The cases enumerate here, 1. MOV ALU32 - zext 32-bit -> 64-bit 2. MOV ALU64 - copy 64-bit -> 32-bit 3. op ALU32 - zext 32-bit -> 64-bit 4. op ALU64 - n/a 5. jmp ALU32 - 64-bit: var32_off | upper_32_bits(var64_off) 6. jmp ALU64 - 32-bit: (>> (<< var64_off)) Details for each case, For "MOV ALU32" BPF arch zero extends so we simply copy the bounds from 32-bit into 64-bit ensuring we truncate var_off and 64-bit bounds correctly. See zext_32_to_64. For "MOV ALU64" copy all bounds including 32-bit into new register. If the src register had 32-bit bounds the dst register will as well. For "op ALU32" zero extend 32-bit into 64-bit the same as move, see zext_32_to_64. For "op ALU64" calculate both 32-bit and 64-bit bounds no merging is done here. Except we have a special case. When RSH or ARSH is done we can't simply ignore shifting bits from 64-bit reg into the 32-bit subreg. So currently just push bounds from 64-bit into 32-bit. This will be correct in the sense that they will represent a valid state of the register. However we could lose some accuracy if an ARSH is following a jmp32 operation. We can handle this special case in a follow up series. For "jmp ALU32" mark 64-bit reg unknown and recalculate 64-bit bounds from tnum by setting var_off to ((<<(>>var_off)) | var32_off). We special case if 64-bit bounds has zero'd upper 32bits at which point we can simply copy 32-bit bounds into 64-bit register. This catches a common compiler trick where upper 32-bits are zeroed and then 32-bit ops are used followed by a 64-bit compare or 64-bit op on a pointer. See __reg_combine_64_into_32(). For "jmp ALU64" cast the bounds of the 64bit to their 32-bit counterpart. For example s32_min_value = (s32)reg->smin_value. For tnum use only the lower 32bits via, (>>(<<var_off)). See __reg_combine_64_into_32(). Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Link: https://lore.kernel.org/bpf/158560419880.10843.11448220440809118343.stgit@john-Precision-5820-Tower
2020-03-31 05:36:39 +08:00
struct tnum tnum_subreg(struct tnum a)
{
return tnum_cast(a, 4);
}
struct tnum tnum_clear_subreg(struct tnum a)
{
return tnum_lshift(tnum_rshift(a, 32), 32);
}
struct tnum tnum_const_subreg(struct tnum a, u32 value)
{
return tnum_or(tnum_clear_subreg(a), tnum_const(value));
}