diff mbox series

[bpf-next] bpf: Emit explicit NULL pointer checks for PROBE_LDX instructions.

Message ID 20210202053837.95909-1-alexei.starovoitov@gmail.com
State New
Headers show
Series [bpf-next] bpf: Emit explicit NULL pointer checks for PROBE_LDX instructions. | expand

Commit Message

Alexei Starovoitov Feb. 2, 2021, 5:38 a.m. UTC
From: Alexei Starovoitov <ast@kernel.org>

PTR_TO_BTF_ID registers contain either kernel pointer or NULL.
Emit the NULL check explicitly by JIT instead of going into
do_user_addr_fault() on NULL deference.

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 arch/x86/net/bpf_jit_comp.c | 19 +++++++++++++++++++
 1 file changed, 19 insertions(+)

Comments

Song Liu Feb. 3, 2021, 12:56 a.m. UTC | #1
> On Feb 1, 2021, at 9:38 PM, Alexei Starovoitov <alexei.starovoitov@gmail.com> wrote:

> 

> From: Alexei Starovoitov <ast@kernel.org>

> 

> PTR_TO_BTF_ID registers contain either kernel pointer or NULL.

> Emit the NULL check explicitly by JIT instead of going into

> do_user_addr_fault() on NULL deference.

> 

> Signed-off-by: Alexei Starovoitov <ast@kernel.org>

> ---

> arch/x86/net/bpf_jit_comp.c | 19 +++++++++++++++++++

> 1 file changed, 19 insertions(+)

> 

> diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c

> index b7a2911bda77..a3dc3bd154ac 100644

> --- a/arch/x86/net/bpf_jit_comp.c

> +++ b/arch/x86/net/bpf_jit_comp.c

> @@ -930,6 +930,7 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,

> 		u32 dst_reg = insn->dst_reg;

> 		u32 src_reg = insn->src_reg;

> 		u8 b2 = 0, b3 = 0;

> +		u8 *start_of_ldx;

> 		s64 jmp_offset;

> 		u8 jmp_cond;

> 		u8 *func;

> @@ -1278,12 +1279,30 @@ st:			if (is_imm8(insn->off))

> 		case BPF_LDX | BPF_PROBE_MEM | BPF_W:

> 		case BPF_LDX | BPF_MEM | BPF_DW:

> 		case BPF_LDX | BPF_PROBE_MEM | BPF_DW:

> +			if (BPF_MODE(insn->code) == BPF_PROBE_MEM) {

> +				/* test src_reg, src_reg */

> +				maybe_emit_mod(&prog, src_reg, src_reg, true); /* always 1 byte */

> +				EMIT2(0x85, add_2reg(0xC0, src_reg, src_reg));

> +				/* jne start_of_ldx */

> +				EMIT2(X86_JNE, 0);

> +				/* xor dst_reg, dst_reg */

> +				emit_mov_imm32(&prog, false, dst_reg, 0);

> +				/* jmp byte_after_ldx */

> +				EMIT2(0xEB, 0);

> +

> +				/* populate jmp_offset for JNE above */

> +				temp[4] = prog - temp - 5 /* sizeof(test + jne) */;


IIUC, this case only happens for i == 1 in the loop? If so, can we use temp[5(?)] 
instead of start_of_ldx?

Thanks,
Song

> +				start_of_ldx = prog;

> +			}

> 			emit_ldx(&prog, BPF_SIZE(insn->code), dst_reg, src_reg, insn->off);

> 			if (BPF_MODE(insn->code) == BPF_PROBE_MEM) {

> 				struct exception_table_entry *ex;

> 				u8 *_insn = image + proglen;

> 				s64 delta;

> 

> +				/* populate jmp_offset for JMP above */

> +				start_of_ldx[-1] = prog - start_of_ldx;

> +

> 				if (!bpf_prog->aux->extable)

> 					break;

> 

> -- 

> 2.24.1

>
Alexei Starovoitov Feb. 3, 2021, 2:19 a.m. UTC | #2
On Wed, Feb 03, 2021 at 12:56:39AM +0000, Song Liu wrote:
> 

> 

> > On Feb 1, 2021, at 9:38 PM, Alexei Starovoitov <alexei.starovoitov@gmail.com> wrote:

> > 

> > From: Alexei Starovoitov <ast@kernel.org>

> > 

> > PTR_TO_BTF_ID registers contain either kernel pointer or NULL.

> > Emit the NULL check explicitly by JIT instead of going into

> > do_user_addr_fault() on NULL deference.

> > 

> > Signed-off-by: Alexei Starovoitov <ast@kernel.org>

> > ---

> > arch/x86/net/bpf_jit_comp.c | 19 +++++++++++++++++++

> > 1 file changed, 19 insertions(+)

> > 

> > diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c

> > index b7a2911bda77..a3dc3bd154ac 100644

> > --- a/arch/x86/net/bpf_jit_comp.c

> > +++ b/arch/x86/net/bpf_jit_comp.c

> > @@ -930,6 +930,7 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,

> > 		u32 dst_reg = insn->dst_reg;

> > 		u32 src_reg = insn->src_reg;

> > 		u8 b2 = 0, b3 = 0;

> > +		u8 *start_of_ldx;

> > 		s64 jmp_offset;

> > 		u8 jmp_cond;

> > 		u8 *func;

> > @@ -1278,12 +1279,30 @@ st:			if (is_imm8(insn->off))

> > 		case BPF_LDX | BPF_PROBE_MEM | BPF_W:

> > 		case BPF_LDX | BPF_MEM | BPF_DW:

> > 		case BPF_LDX | BPF_PROBE_MEM | BPF_DW:

> > +			if (BPF_MODE(insn->code) == BPF_PROBE_MEM) {

> > +				/* test src_reg, src_reg */

> > +				maybe_emit_mod(&prog, src_reg, src_reg, true); /* always 1 byte */

> > +				EMIT2(0x85, add_2reg(0xC0, src_reg, src_reg));

> > +				/* jne start_of_ldx */

> > +				EMIT2(X86_JNE, 0);

> > +				/* xor dst_reg, dst_reg */

> > +				emit_mov_imm32(&prog, false, dst_reg, 0);

> > +				/* jmp byte_after_ldx */

> > +				EMIT2(0xEB, 0);

> > +

> > +				/* populate jmp_offset for JNE above */

> > +				temp[4] = prog - temp - 5 /* sizeof(test + jne) */;

> 

> IIUC, this case only happens for i == 1 in the loop? If so, can we use temp[5(?)] 

> instead of start_of_ldx?


I don't understand the question, but let me try anyway :)
temp is a buffer for single instruction.
prog=temp; for every loop iteration (not only i == 1)
temp[4] is second byte in JNE instruction as the comment says.
temp[5] is a byte after JNE. It's a first byte of XOR.
That XOR is variable length instruction. 
Hence while emitting JNE we don't know the target offset in JNE and just use 0.
So temp[4] assignment populates with actual offset, since now we know the size
of XOR.
Song Liu Feb. 3, 2021, 6:37 p.m. UTC | #3
> On Feb 2, 2021, at 6:19 PM, Alexei Starovoitov <alexei.starovoitov@gmail.com> wrote:

> 

> On Wed, Feb 03, 2021 at 12:56:39AM +0000, Song Liu wrote:

>> 

>> 

>>> On Feb 1, 2021, at 9:38 PM, Alexei Starovoitov <alexei.starovoitov@gmail.com> wrote:

>>> 

>>> From: Alexei Starovoitov <ast@kernel.org>

>>> 

>>> PTR_TO_BTF_ID registers contain either kernel pointer or NULL.

>>> Emit the NULL check explicitly by JIT instead of going into

>>> do_user_addr_fault() on NULL deference.

>>> 

>>> Signed-off-by: Alexei Starovoitov <ast@kernel.org>

>>> ---

>>> arch/x86/net/bpf_jit_comp.c | 19 +++++++++++++++++++

>>> 1 file changed, 19 insertions(+)

>>> 

>>> diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c

>>> index b7a2911bda77..a3dc3bd154ac 100644

>>> --- a/arch/x86/net/bpf_jit_comp.c

>>> +++ b/arch/x86/net/bpf_jit_comp.c

>>> @@ -930,6 +930,7 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,

>>> 		u32 dst_reg = insn->dst_reg;

>>> 		u32 src_reg = insn->src_reg;

>>> 		u8 b2 = 0, b3 = 0;

>>> +		u8 *start_of_ldx;

>>> 		s64 jmp_offset;

>>> 		u8 jmp_cond;

>>> 		u8 *func;

>>> @@ -1278,12 +1279,30 @@ st:			if (is_imm8(insn->off))

>>> 		case BPF_LDX | BPF_PROBE_MEM | BPF_W:

>>> 		case BPF_LDX | BPF_MEM | BPF_DW:

>>> 		case BPF_LDX | BPF_PROBE_MEM | BPF_DW:

>>> +			if (BPF_MODE(insn->code) == BPF_PROBE_MEM) {

>>> +				/* test src_reg, src_reg */

>>> +				maybe_emit_mod(&prog, src_reg, src_reg, true); /* always 1 byte */

>>> +				EMIT2(0x85, add_2reg(0xC0, src_reg, src_reg));

>>> +				/* jne start_of_ldx */

>>> +				EMIT2(X86_JNE, 0);

>>> +				/* xor dst_reg, dst_reg */

>>> +				emit_mov_imm32(&prog, false, dst_reg, 0);

>>> +				/* jmp byte_after_ldx */

>>> +				EMIT2(0xEB, 0);

>>> +

>>> +				/* populate jmp_offset for JNE above */

>>> +				temp[4] = prog - temp - 5 /* sizeof(test + jne) */;

>> 

>> IIUC, this case only happens for i == 1 in the loop? If so, can we use temp[5(?)] 

>> instead of start_of_ldx?

> 

> I don't understand the question, but let me try anyway :)

> temp is a buffer for single instruction.

> prog=temp; for every loop iteration (not only i == 1)


Thanks for the explanation. I misunderstood how we use prog in the loop. 

> temp[4] is second byte in JNE instruction as the comment says.

> temp[5] is a byte after JNE. It's a first byte of XOR.

> That XOR is variable length instruction. 

> Hence while emitting JNE we don't know the target offset in JNE and just use 0.

> So temp[4] assignment populates with actual offset, since now we know the size

> of XOR.


And after reading emit_ldx() more carefully, I agree that introducing 
start_of_ldx would simplify the logic here. 

Acked-by: Song Liu <songliubraving@fb.com>
patchwork-bot+netdevbpf@kernel.org Feb. 4, 2021, 4:10 p.m. UTC | #4
Hello:

This patch was applied to bpf/bpf-next.git (refs/heads/master):

On Mon,  1 Feb 2021 21:38:37 -0800 you wrote:
> From: Alexei Starovoitov <ast@kernel.org>

> 

> PTR_TO_BTF_ID registers contain either kernel pointer or NULL.

> Emit the NULL check explicitly by JIT instead of going into

> do_user_addr_fault() on NULL deference.

> 

> Signed-off-by: Alexei Starovoitov <ast@kernel.org>

> 

> [...]


Here is the summary with links:
  - [bpf-next] bpf: Emit explicit NULL pointer checks for PROBE_LDX instructions.
    https://git.kernel.org/bpf/bpf-next/c/4c5de127598e

You are awesome, thank you!
--
Deet-doot-dot, I am a bot.
https://korg.docs.kernel.org/patchwork/pwbot.html
diff mbox series

Patch

diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index b7a2911bda77..a3dc3bd154ac 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -930,6 +930,7 @@  static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 		u32 dst_reg = insn->dst_reg;
 		u32 src_reg = insn->src_reg;
 		u8 b2 = 0, b3 = 0;
+		u8 *start_of_ldx;
 		s64 jmp_offset;
 		u8 jmp_cond;
 		u8 *func;
@@ -1278,12 +1279,30 @@  st:			if (is_imm8(insn->off))
 		case BPF_LDX | BPF_PROBE_MEM | BPF_W:
 		case BPF_LDX | BPF_MEM | BPF_DW:
 		case BPF_LDX | BPF_PROBE_MEM | BPF_DW:
+			if (BPF_MODE(insn->code) == BPF_PROBE_MEM) {
+				/* test src_reg, src_reg */
+				maybe_emit_mod(&prog, src_reg, src_reg, true); /* always 1 byte */
+				EMIT2(0x85, add_2reg(0xC0, src_reg, src_reg));
+				/* jne start_of_ldx */
+				EMIT2(X86_JNE, 0);
+				/* xor dst_reg, dst_reg */
+				emit_mov_imm32(&prog, false, dst_reg, 0);
+				/* jmp byte_after_ldx */
+				EMIT2(0xEB, 0);
+
+				/* populate jmp_offset for JNE above */
+				temp[4] = prog - temp - 5 /* sizeof(test + jne) */;
+				start_of_ldx = prog;
+			}
 			emit_ldx(&prog, BPF_SIZE(insn->code), dst_reg, src_reg, insn->off);
 			if (BPF_MODE(insn->code) == BPF_PROBE_MEM) {
 				struct exception_table_entry *ex;
 				u8 *_insn = image + proglen;
 				s64 delta;
 
+				/* populate jmp_offset for JMP above */
+				start_of_ldx[-1] = prog - start_of_ldx;
+
 				if (!bpf_prog->aux->extable)
 					break;