diff mbox series

[4/4] bpf powerpc: Add addr > TASK_SIZE_MAX explicit check

Message ID 20210706073211.349889-5-ravi.bangoria@linux.ibm.com (mailing list archive)
State Changes Requested
Headers show
Series bpf powerpc: Add BPF_PROBE_MEM support for 64bit JIT | expand

Checks

Context Check Description
snowpatch_ozlabs/apply_patch warning Failed to apply on branch powerpc/merge (858ea4d1f5c22aa2f8a6724c2a65458294f2ddc6)
snowpatch_ozlabs/apply_patch warning Failed to apply on branch powerpc/next (4ebbbaa4ce8524b853dd6febf0176a6efa3482d7)
snowpatch_ozlabs/apply_patch warning Failed to apply on branch linus/master (79160a603bdb51916226caf4a6616cc4e1c58a58)
snowpatch_ozlabs/apply_patch success Successfully applied on branch powerpc/fixes (60b7ed54a41b550d50caf7f2418db4a7e75b5bdc)
snowpatch_ozlabs/build-ppc64le warning Build succeeded but added 8 new sparse warnings
snowpatch_ozlabs/build-ppc64be warning Build succeeded but added 8 new sparse warnings
snowpatch_ozlabs/build-ppc64e success Build succeeded
snowpatch_ozlabs/build-pmac32 success Build succeeded
snowpatch_ozlabs/checkpatch success total: 0 errors, 0 warnings, 0 checks, 62 lines checked
snowpatch_ozlabs/needsstable success Patch has no Fixes tags

Commit Message

Ravi Bangoria July 6, 2021, 7:32 a.m. UTC 
On PowerPC with KUAP enabled, any kernel code which wants to
access userspace needs to be surrounded by disable-enable KUAP.
But that is not happening for BPF_PROBE_MEM load instruction.
So, when BPF program tries to access invalid userspace address,
page-fault handler considers it as bad KUAP fault:

  Kernel attempted to read user page (d0000000) - exploit attempt? (uid: 0)

Considering the fact that PTR_TO_BTF_ID (which uses BPF_PROBE_MEM
mode) could either be a valid kernel pointer or NULL but should
never be a pointer to userspace address, execute BPF_PROBE_MEM load
only if addr > TASK_SIZE_MAX, otherwise set dst_reg=0 and move on.

This will catch NULL, valid or invalid userspace pointers. Only bad
kernel pointer will be handled by BPF exception table.

[Alexei suggested for x86]
Suggested-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Ravi Bangoria <ravi.bangoria@linux.ibm.com>
---
 arch/powerpc/net/bpf_jit_comp64.c | 38 +++++++++++++++++++++++++++++++
 1 file changed, 38 insertions(+)

Comments

Christophe Leroy July 6, 2021, 10 a.m. UTC | #1 
Le 06/07/2021 à 09:32, Ravi Bangoria a écrit :
> On PowerPC with KUAP enabled, any kernel code which wants to
> access userspace needs to be surrounded by disable-enable KUAP.
> But that is not happening for BPF_PROBE_MEM load instruction.
> So, when BPF program tries to access invalid userspace address,
> page-fault handler considers it as bad KUAP fault:
> 
>    Kernel attempted to read user page (d0000000) - exploit attempt? (uid: 0)
> 
> Considering the fact that PTR_TO_BTF_ID (which uses BPF_PROBE_MEM
> mode) could either be a valid kernel pointer or NULL but should
> never be a pointer to userspace address, execute BPF_PROBE_MEM load
> only if addr > TASK_SIZE_MAX, otherwise set dst_reg=0 and move on.
> 
> This will catch NULL, valid or invalid userspace pointers. Only bad
> kernel pointer will be handled by BPF exception table.
> 
> [Alexei suggested for x86]
> Suggested-by: Alexei Starovoitov <ast@kernel.org>
> Signed-off-by: Ravi Bangoria <ravi.bangoria@linux.ibm.com>
> ---
>   arch/powerpc/net/bpf_jit_comp64.c | 38 +++++++++++++++++++++++++++++++
>   1 file changed, 38 insertions(+)
> 
> diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c
> index 1884c6dca89a..46becae76210 100644
> --- a/arch/powerpc/net/bpf_jit_comp64.c
> +++ b/arch/powerpc/net/bpf_jit_comp64.c
> @@ -753,6 +753,14 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context *
>   		/* dst = *(u8 *)(ul) (src + off) */
>   		case BPF_LDX | BPF_MEM | BPF_B:
>   		case BPF_LDX | BPF_PROBE_MEM | BPF_B:
> +			if (BPF_MODE(code) == BPF_PROBE_MEM) {
> +				EMIT(PPC_RAW_ADDI(b2p[TMP_REG_1], src_reg, off));
> +				PPC_LI64(b2p[TMP_REG_2], TASK_SIZE_MAX);
> +				EMIT(PPC_RAW_CMPLD(b2p[TMP_REG_1], b2p[TMP_REG_2]));
> +				PPC_BCC(COND_GT, (ctx->idx + 4) * 4);
> +				EMIT(PPC_RAW_XOR(dst_reg, dst_reg, dst_reg));

Prefered way to clear a register is to do 'li reg, 0'

> +				PPC_JMP((ctx->idx + 2) * 4);
> +			}
>   			EMIT(PPC_RAW_LBZ(dst_reg, src_reg, off));
>   			if (insn_is_zext(&insn[i + 1]))
>   				addrs[++i] = ctx->idx * 4;
> @@ -763,6 +771,14 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context *
>   		/* dst = *(u16 *)(ul) (src + off) */
>   		case BPF_LDX | BPF_MEM | BPF_H:
>   		case BPF_LDX | BPF_PROBE_MEM | BPF_H:
> +			if (BPF_MODE(code) == BPF_PROBE_MEM) {
> +				EMIT(PPC_RAW_ADDI(b2p[TMP_REG_1], src_reg, off));
> +				PPC_LI64(b2p[TMP_REG_2], TASK_SIZE_MAX);
> +				EMIT(PPC_RAW_CMPLD(b2p[TMP_REG_1], b2p[TMP_REG_2]));
> +				PPC_BCC(COND_GT, (ctx->idx + 4) * 4);
> +				EMIT(PPC_RAW_XOR(dst_reg, dst_reg, dst_reg));
> +				PPC_JMP((ctx->idx + 2) * 4);
> +			}

That code seems strictly identical to the previous one and the next one.
Can you refactor in a function ?

>   			EMIT(PPC_RAW_LHZ(dst_reg, src_reg, off));
>   			if (insn_is_zext(&insn[i + 1]))
>   				addrs[++i] = ctx->idx * 4;
> @@ -773,6 +789,14 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context *
>   		/* dst = *(u32 *)(ul) (src + off) */
>   		case BPF_LDX | BPF_MEM | BPF_W:
>   		case BPF_LDX | BPF_PROBE_MEM | BPF_W:
> +			if (BPF_MODE(code) == BPF_PROBE_MEM) {
> +				EMIT(PPC_RAW_ADDI(b2p[TMP_REG_1], src_reg, off));
> +				PPC_LI64(b2p[TMP_REG_2], TASK_SIZE_MAX);
> +				EMIT(PPC_RAW_CMPLD(b2p[TMP_REG_1], b2p[TMP_REG_2]));
> +				PPC_BCC(COND_GT, (ctx->idx + 4) * 4);
> +				EMIT(PPC_RAW_XOR(dst_reg, dst_reg, dst_reg));
> +				PPC_JMP((ctx->idx + 2) * 4);
> +			}
>   			EMIT(PPC_RAW_LWZ(dst_reg, src_reg, off));
>   			if (insn_is_zext(&insn[i + 1]))
>   				addrs[++i] = ctx->idx * 4;
> @@ -783,6 +807,20 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context *
>   		/* dst = *(u64 *)(ul) (src + off) */
>   		case BPF_LDX | BPF_MEM | BPF_DW:
>   		case BPF_LDX | BPF_PROBE_MEM | BPF_DW:
> +			if (BPF_MODE(code) == BPF_PROBE_MEM) {
> +				EMIT(PPC_RAW_ADDI(b2p[TMP_REG_1], src_reg, off));
> +				PPC_LI64(b2p[TMP_REG_2], TASK_SIZE_MAX);
> +				EMIT(PPC_RAW_CMPLD(b2p[TMP_REG_1], b2p[TMP_REG_2]));
> +				if (off % 4)

That test is worth a comment.

And I'd prefer

	if (off & 3) {
		PPC_BCC(COND_GT, (ctx->idx + 5) * 4);
		EMIT(PPC_RAW_XOR(dst_reg, dst_reg, dst_reg));
		PPC_JMP((ctx->idx + 3) * 4);
	} else {
		PPC_BCC(COND_GT, (ctx->idx + 4) * 4);
		EMIT(PPC_RAW_XOR(dst_reg, dst_reg, dst_reg));
		PPC_JMP((ctx->idx + 2) * 4);
	}

> +					PPC_BCC(COND_GT, (ctx->idx + 5) * 4);
> +				else
> +					PPC_BCC(COND_GT, (ctx->idx + 4) * 4);
> +				EMIT(PPC_RAW_XOR(dst_reg, dst_reg, dst_reg));

Use PPC_RAW_LI(dst_reg, 0);

> +				if (off % 4)
> +					PPC_JMP((ctx->idx + 3) * 4);
> +				else
> +					PPC_JMP((ctx->idx + 2) * 4);
> +			}
>   			PPC_BPF_LL(dst_reg, src_reg, off);
>   			ret = add_extable_entry(fp, image, pass, code, ctx, dst_reg);
>   			if (ret)
>
Ravi Bangoria July 7, 2021, 4:06 a.m. UTC | #2 
>> @@ -763,6 +771,14 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context *
>>           /* dst = *(u16 *)(ul) (src + off) */
>>           case BPF_LDX | BPF_MEM | BPF_H:
>>           case BPF_LDX | BPF_PROBE_MEM | BPF_H:
>> +            if (BPF_MODE(code) == BPF_PROBE_MEM) {
>> +                EMIT(PPC_RAW_ADDI(b2p[TMP_REG_1], src_reg, off));
>> +                PPC_LI64(b2p[TMP_REG_2], TASK_SIZE_MAX);
>> +                EMIT(PPC_RAW_CMPLD(b2p[TMP_REG_1], b2p[TMP_REG_2]));
>> +                PPC_BCC(COND_GT, (ctx->idx + 4) * 4);
>> +                EMIT(PPC_RAW_XOR(dst_reg, dst_reg, dst_reg));
>> +                PPC_JMP((ctx->idx + 2) * 4);
>> +            }
> 
> That code seems strictly identical to the previous one and the next one.
> Can you refactor in a function ?

I'll check this.

> 
>>               EMIT(PPC_RAW_LHZ(dst_reg, src_reg, off));
>>               if (insn_is_zext(&insn[i + 1]))
>>                   addrs[++i] = ctx->idx * 4;
>> @@ -773,6 +789,14 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context *
>>           /* dst = *(u32 *)(ul) (src + off) */
>>           case BPF_LDX | BPF_MEM | BPF_W:
>>           case BPF_LDX | BPF_PROBE_MEM | BPF_W:
>> +            if (BPF_MODE(code) == BPF_PROBE_MEM) {
>> +                EMIT(PPC_RAW_ADDI(b2p[TMP_REG_1], src_reg, off));
>> +                PPC_LI64(b2p[TMP_REG_2], TASK_SIZE_MAX);
>> +                EMIT(PPC_RAW_CMPLD(b2p[TMP_REG_1], b2p[TMP_REG_2]));
>> +                PPC_BCC(COND_GT, (ctx->idx + 4) * 4);
>> +                EMIT(PPC_RAW_XOR(dst_reg, dst_reg, dst_reg));
>> +                PPC_JMP((ctx->idx + 2) * 4);
>> +            }
>>               EMIT(PPC_RAW_LWZ(dst_reg, src_reg, off));
>>               if (insn_is_zext(&insn[i + 1]))
>>                   addrs[++i] = ctx->idx * 4;
>> @@ -783,6 +807,20 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context *
>>           /* dst = *(u64 *)(ul) (src + off) */
>>           case BPF_LDX | BPF_MEM | BPF_DW:
>>           case BPF_LDX | BPF_PROBE_MEM | BPF_DW:
>> +            if (BPF_MODE(code) == BPF_PROBE_MEM) {
>> +                EMIT(PPC_RAW_ADDI(b2p[TMP_REG_1], src_reg, off));
>> +                PPC_LI64(b2p[TMP_REG_2], TASK_SIZE_MAX);
>> +                EMIT(PPC_RAW_CMPLD(b2p[TMP_REG_1], b2p[TMP_REG_2]));
>> +                if (off % 4)
> 
> That test is worth a comment.

(off % 4) test is based on how PPC_BPF_LL() emits instruction.

> 
> And I'd prefer
> 
>      if (off & 3) {
>          PPC_BCC(COND_GT, (ctx->idx + 5) * 4);
>          EMIT(PPC_RAW_XOR(dst_reg, dst_reg, dst_reg));
>          PPC_JMP((ctx->idx + 3) * 4);
>      } else {
>          PPC_BCC(COND_GT, (ctx->idx + 4) * 4);
>          EMIT(PPC_RAW_XOR(dst_reg, dst_reg, dst_reg));
>          PPC_JMP((ctx->idx + 2) * 4);
>      }

Yes this is neat.

Thanks for the review,
Ravi
diff mbox series

Patch

diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c
index 1884c6dca89a..46becae76210 100644
--- a/arch/powerpc/net/bpf_jit_comp64.c
+++ b/arch/powerpc/net/bpf_jit_comp64.c
@@ -753,6 +753,14 @@  int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context *
 		/* dst = *(u8 *)(ul) (src + off) */
 		case BPF_LDX | BPF_MEM | BPF_B:
 		case BPF_LDX | BPF_PROBE_MEM | BPF_B:
+			if (BPF_MODE(code) == BPF_PROBE_MEM) {
+				EMIT(PPC_RAW_ADDI(b2p[TMP_REG_1], src_reg, off));
+				PPC_LI64(b2p[TMP_REG_2], TASK_SIZE_MAX);
+				EMIT(PPC_RAW_CMPLD(b2p[TMP_REG_1], b2p[TMP_REG_2]));
+				PPC_BCC(COND_GT, (ctx->idx + 4) * 4);
+				EMIT(PPC_RAW_XOR(dst_reg, dst_reg, dst_reg));
+				PPC_JMP((ctx->idx + 2) * 4);
+			}
 			EMIT(PPC_RAW_LBZ(dst_reg, src_reg, off));
 			if (insn_is_zext(&insn[i + 1]))
 				addrs[++i] = ctx->idx * 4;
@@ -763,6 +771,14 @@  int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context *
 		/* dst = *(u16 *)(ul) (src + off) */
 		case BPF_LDX | BPF_MEM | BPF_H:
 		case BPF_LDX | BPF_PROBE_MEM | BPF_H:
+			if (BPF_MODE(code) == BPF_PROBE_MEM) {
+				EMIT(PPC_RAW_ADDI(b2p[TMP_REG_1], src_reg, off));
+				PPC_LI64(b2p[TMP_REG_2], TASK_SIZE_MAX);
+				EMIT(PPC_RAW_CMPLD(b2p[TMP_REG_1], b2p[TMP_REG_2]));
+				PPC_BCC(COND_GT, (ctx->idx + 4) * 4);
+				EMIT(PPC_RAW_XOR(dst_reg, dst_reg, dst_reg));
+				PPC_JMP((ctx->idx + 2) * 4);
+			}
 			EMIT(PPC_RAW_LHZ(dst_reg, src_reg, off));
 			if (insn_is_zext(&insn[i + 1]))
 				addrs[++i] = ctx->idx * 4;
@@ -773,6 +789,14 @@  int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context *
 		/* dst = *(u32 *)(ul) (src + off) */
 		case BPF_LDX | BPF_MEM | BPF_W:
 		case BPF_LDX | BPF_PROBE_MEM | BPF_W:
+			if (BPF_MODE(code) == BPF_PROBE_MEM) {
+				EMIT(PPC_RAW_ADDI(b2p[TMP_REG_1], src_reg, off));
+				PPC_LI64(b2p[TMP_REG_2], TASK_SIZE_MAX);
+				EMIT(PPC_RAW_CMPLD(b2p[TMP_REG_1], b2p[TMP_REG_2]));
+				PPC_BCC(COND_GT, (ctx->idx + 4) * 4);
+				EMIT(PPC_RAW_XOR(dst_reg, dst_reg, dst_reg));
+				PPC_JMP((ctx->idx + 2) * 4);
+			}
 			EMIT(PPC_RAW_LWZ(dst_reg, src_reg, off));
 			if (insn_is_zext(&insn[i + 1]))
 				addrs[++i] = ctx->idx * 4;
@@ -783,6 +807,20 @@  int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context *
 		/* dst = *(u64 *)(ul) (src + off) */
 		case BPF_LDX | BPF_MEM | BPF_DW:
 		case BPF_LDX | BPF_PROBE_MEM | BPF_DW:
+			if (BPF_MODE(code) == BPF_PROBE_MEM) {
+				EMIT(PPC_RAW_ADDI(b2p[TMP_REG_1], src_reg, off));
+				PPC_LI64(b2p[TMP_REG_2], TASK_SIZE_MAX);
+				EMIT(PPC_RAW_CMPLD(b2p[TMP_REG_1], b2p[TMP_REG_2]));
+				if (off % 4)
+					PPC_BCC(COND_GT, (ctx->idx + 5) * 4);
+				else
+					PPC_BCC(COND_GT, (ctx->idx + 4) * 4);
+				EMIT(PPC_RAW_XOR(dst_reg, dst_reg, dst_reg));
+				if (off % 4)
+					PPC_JMP((ctx->idx + 3) * 4);
+				else
+					PPC_JMP((ctx->idx + 2) * 4);
+			}
 			PPC_BPF_LL(dst_reg, src_reg, off);
 			ret = add_extable_entry(fp, image, pass, code, ctx, dst_reg);
 			if (ret)