diff mbox series

[v3,bpf-next,03/14] bpf: Add x86-64 JIT support for PROBE_MEM32 pseudo instructions.

Message ID 20240308010812.89848-4-alexei.starovoitov@gmail.com (mailing list archive)
State New
Headers show
Series bpf: Introduce BPF arena. | expand

Commit Message

Alexei Starovoitov March 8, 2024, 1:08 a.m. UTC
From: Alexei Starovoitov <ast@kernel.org>

Add support for [LDX | STX | ST], PROBE_MEM32, [B | H | W | DW] instructions.
They are similar to PROBE_MEM instructions with the following differences:
- PROBE_MEM has to check that the address is in the kernel range with
  src_reg + insn->off >= TASK_SIZE_MAX + PAGE_SIZE check
- PROBE_MEM doesn't support store
- PROBE_MEM32 relies on the verifier to clear upper 32-bit in the register
- PROBE_MEM32 adds 64-bit kern_vm_start address (which is stored in %r12 in the prologue)
  Due to bpf_arena constructions such %r12 + %reg + off16 access is guaranteed
  to be within arena virtual range, so no address check at run-time.
- PROBE_MEM32 allows STX and ST. If they fault the store is a nop.
  When LDX faults the destination register is zeroed.

Acked-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 arch/x86/net/bpf_jit_comp.c | 191 +++++++++++++++++++++++++++++++++++-
 include/linux/bpf.h         |   1 +
 include/linux/filter.h      |   3 +
 3 files changed, 194 insertions(+), 1 deletion(-)

Comments

Andrii Nakryiko March 11, 2024, 10:05 p.m. UTC | #1
On Thu, Mar 7, 2024 at 5:08 PM Alexei Starovoitov
<alexei.starovoitov@gmail.com> wrote:
>
> From: Alexei Starovoitov <ast@kernel.org>
>
> Add support for [LDX | STX | ST], PROBE_MEM32, [B | H | W | DW] instructions.
> They are similar to PROBE_MEM instructions with the following differences:
> - PROBE_MEM has to check that the address is in the kernel range with
>   src_reg + insn->off >= TASK_SIZE_MAX + PAGE_SIZE check
> - PROBE_MEM doesn't support store
> - PROBE_MEM32 relies on the verifier to clear upper 32-bit in the register
> - PROBE_MEM32 adds 64-bit kern_vm_start address (which is stored in %r12 in the prologue)
>   Due to bpf_arena constructions such %r12 + %reg + off16 access is guaranteed
>   to be within arena virtual range, so no address check at run-time.
> - PROBE_MEM32 allows STX and ST. If they fault the store is a nop.
>   When LDX faults the destination register is zeroed.
>
> Acked-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
> ---
>  arch/x86/net/bpf_jit_comp.c | 191 +++++++++++++++++++++++++++++++++++-
>  include/linux/bpf.h         |   1 +
>  include/linux/filter.h      |   3 +
>  3 files changed, 194 insertions(+), 1 deletion(-)
>

[...]

> +static u8 add_3mod(u8 byte, u32 r1, u32 r2, u32 index)
> +{
> +       if (is_ereg(r1))
> +               byte |= 1;
> +       if (is_ereg(index))
> +               byte |= 2;
> +       if (is_ereg(r2))
> +               byte |= 4;
> +       return byte;
> +}
> +
>  /* Encode 'dst_reg' register into x86-64 opcode 'byte' */
>  static u8 add_1reg(u8 byte, u32 dst_reg)
>  {
> @@ -645,6 +659,8 @@ static void emit_bpf_tail_call_indirect(struct bpf_prog *bpf_prog,
>                 pop_r12(&prog);
>         } else {
>                 pop_callee_regs(&prog, callee_regs_used);
> +               if (bpf_arena_get_kern_vm_start(bpf_prog->aux->arena))

ah, I guess this is where NULL is expected?.. But isn't `if
(bpf_prog->aux->arena)` equivalent and more straightforward check?

> +                       pop_r12(&prog);
>         }
>
>         EMIT1(0x58);                              /* pop rax */
> @@ -704,6 +720,8 @@ static void emit_bpf_tail_call_direct(struct bpf_prog *bpf_prog,
>                 pop_r12(&prog);
>         } else {
>                 pop_callee_regs(&prog, callee_regs_used);
> +               if (bpf_arena_get_kern_vm_start(bpf_prog->aux->arena))
> +                       pop_r12(&prog);
>         }
>
>         EMIT1(0x58);                                  /* pop rax */

[...]

> @@ -1147,11 +1276,14 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, u8 *rw_image
>         bool tail_call_seen = false;
>         bool seen_exit = false;
>         u8 temp[BPF_MAX_INSN_SIZE + BPF_INSN_SAFETY];
> +       u64 arena_vm_start;
>         int i, excnt = 0;
>         int ilen, proglen = 0;
>         u8 *prog = temp;
>         int err;
>
> +       arena_vm_start = bpf_arena_get_kern_vm_start(bpf_prog->aux->arena);

and I'm guessing here you didn't want that check... I'd probably go
with explicit pointer checks, but ok, it's fine

> +
>         detect_reg_usage(insn, insn_cnt, callee_regs_used,
>                          &tail_call_seen);
>

[...]
Alexei Starovoitov March 11, 2024, 10:44 p.m. UTC | #2
On Mon, Mar 11, 2024 at 3:06 PM Andrii Nakryiko
<andrii.nakryiko@gmail.com> wrote:
>
>
> > +       arena_vm_start = bpf_arena_get_kern_vm_start(bpf_prog->aux->arena);
>
> and I'm guessing here you didn't want that check... I'd probably go
> with explicit pointer checks, but ok, it's fine

It's not only here. I expect all JITs will be calling it
and explicit NULL check will be replicated.
Hence I went with a NULL check inside that helper.
Another reason is:
__weak u64 bpf_arena_get_*()
{ return 0; }
So simple code overall.
diff mbox series

Patch

diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index e1390d1e331b..38705a1abe62 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -113,6 +113,7 @@  static int bpf_size_to_x86_bytes(int bpf_size)
 /* Pick a register outside of BPF range for JIT internal work */
 #define AUX_REG (MAX_BPF_JIT_REG + 1)
 #define X86_REG_R9 (MAX_BPF_JIT_REG + 2)
+#define X86_REG_R12 (MAX_BPF_JIT_REG + 3)
 
 /*
  * The following table maps BPF registers to x86-64 registers.
@@ -139,6 +140,7 @@  static const int reg2hex[] = {
 	[BPF_REG_AX] = 2, /* R10 temp register */
 	[AUX_REG] = 3,    /* R11 temp register */
 	[X86_REG_R9] = 1, /* R9 register, 6th function argument */
+	[X86_REG_R12] = 4, /* R12 callee saved */
 };
 
 static const int reg2pt_regs[] = {
@@ -167,6 +169,7 @@  static bool is_ereg(u32 reg)
 			     BIT(BPF_REG_8) |
 			     BIT(BPF_REG_9) |
 			     BIT(X86_REG_R9) |
+			     BIT(X86_REG_R12) |
 			     BIT(BPF_REG_AX));
 }
 
@@ -205,6 +208,17 @@  static u8 add_2mod(u8 byte, u32 r1, u32 r2)
 	return byte;
 }
 
+static u8 add_3mod(u8 byte, u32 r1, u32 r2, u32 index)
+{
+	if (is_ereg(r1))
+		byte |= 1;
+	if (is_ereg(index))
+		byte |= 2;
+	if (is_ereg(r2))
+		byte |= 4;
+	return byte;
+}
+
 /* Encode 'dst_reg' register into x86-64 opcode 'byte' */
 static u8 add_1reg(u8 byte, u32 dst_reg)
 {
@@ -645,6 +659,8 @@  static void emit_bpf_tail_call_indirect(struct bpf_prog *bpf_prog,
 		pop_r12(&prog);
 	} else {
 		pop_callee_regs(&prog, callee_regs_used);
+		if (bpf_arena_get_kern_vm_start(bpf_prog->aux->arena))
+			pop_r12(&prog);
 	}
 
 	EMIT1(0x58);                              /* pop rax */
@@ -704,6 +720,8 @@  static void emit_bpf_tail_call_direct(struct bpf_prog *bpf_prog,
 		pop_r12(&prog);
 	} else {
 		pop_callee_regs(&prog, callee_regs_used);
+		if (bpf_arena_get_kern_vm_start(bpf_prog->aux->arena))
+			pop_r12(&prog);
 	}
 
 	EMIT1(0x58);                                  /* pop rax */
@@ -887,6 +905,18 @@  static void emit_insn_suffix(u8 **pprog, u32 ptr_reg, u32 val_reg, int off)
 	*pprog = prog;
 }
 
+static void emit_insn_suffix_SIB(u8 **pprog, u32 ptr_reg, u32 val_reg, u32 index_reg, int off)
+{
+	u8 *prog = *pprog;
+
+	if (is_imm8(off)) {
+		EMIT3(add_2reg(0x44, BPF_REG_0, val_reg), add_2reg(0, ptr_reg, index_reg) /* SIB */, off);
+	} else {
+		EMIT2_off32(add_2reg(0x84, BPF_REG_0, val_reg), add_2reg(0, ptr_reg, index_reg) /* SIB */, off);
+	}
+	*pprog = prog;
+}
+
 /*
  * Emit a REX byte if it will be necessary to address these registers
  */
@@ -968,6 +998,37 @@  static void emit_ldsx(u8 **pprog, u32 size, u32 dst_reg, u32 src_reg, int off)
 	*pprog = prog;
 }
 
+static void emit_ldx_index(u8 **pprog, u32 size, u32 dst_reg, u32 src_reg, u32 index_reg, int off)
+{
+	u8 *prog = *pprog;
+
+	switch (size) {
+	case BPF_B:
+		/* movzx rax, byte ptr [rax + r12 + off] */
+		EMIT3(add_3mod(0x40, src_reg, dst_reg, index_reg), 0x0F, 0xB6);
+		break;
+	case BPF_H:
+		/* movzx rax, word ptr [rax + r12 + off] */
+		EMIT3(add_3mod(0x40, src_reg, dst_reg, index_reg), 0x0F, 0xB7);
+		break;
+	case BPF_W:
+		/* mov eax, dword ptr [rax + r12 + off] */
+		EMIT2(add_3mod(0x40, src_reg, dst_reg, index_reg), 0x8B);
+		break;
+	case BPF_DW:
+		/* mov rax, qword ptr [rax + r12 + off] */
+		EMIT2(add_3mod(0x48, src_reg, dst_reg, index_reg), 0x8B);
+		break;
+	}
+	emit_insn_suffix_SIB(&prog, src_reg, dst_reg, index_reg, off);
+	*pprog = prog;
+}
+
+static void emit_ldx_r12(u8 **pprog, u32 size, u32 dst_reg, u32 src_reg, int off)
+{
+	emit_ldx_index(pprog, size, dst_reg, src_reg, X86_REG_R12, off);
+}
+
 /* STX: *(u8*)(dst_reg + off) = src_reg */
 static void emit_stx(u8 **pprog, u32 size, u32 dst_reg, u32 src_reg, int off)
 {
@@ -1002,6 +1063,71 @@  static void emit_stx(u8 **pprog, u32 size, u32 dst_reg, u32 src_reg, int off)
 	*pprog = prog;
 }
 
+/* STX: *(u8*)(dst_reg + index_reg + off) = src_reg */
+static void emit_stx_index(u8 **pprog, u32 size, u32 dst_reg, u32 src_reg, u32 index_reg, int off)
+{
+	u8 *prog = *pprog;
+
+	switch (size) {
+	case BPF_B:
+		/* mov byte ptr [rax + r12 + off], al */
+		EMIT2(add_3mod(0x40, dst_reg, src_reg, index_reg), 0x88);
+		break;
+	case BPF_H:
+		/* mov word ptr [rax + r12 + off], ax */
+		EMIT3(0x66, add_3mod(0x40, dst_reg, src_reg, index_reg), 0x89);
+		break;
+	case BPF_W:
+		/* mov dword ptr [rax + r12 + 1], eax */
+		EMIT2(add_3mod(0x40, dst_reg, src_reg, index_reg), 0x89);
+		break;
+	case BPF_DW:
+		/* mov qword ptr [rax + r12 + 1], rax */
+		EMIT2(add_3mod(0x48, dst_reg, src_reg, index_reg), 0x89);
+		break;
+	}
+	emit_insn_suffix_SIB(&prog, dst_reg, src_reg, index_reg, off);
+	*pprog = prog;
+}
+
+static void emit_stx_r12(u8 **pprog, u32 size, u32 dst_reg, u32 src_reg, int off)
+{
+	emit_stx_index(pprog, size, dst_reg, src_reg, X86_REG_R12, off);
+}
+
+/* ST: *(u8*)(dst_reg + index_reg + off) = imm32 */
+static void emit_st_index(u8 **pprog, u32 size, u32 dst_reg, u32 index_reg, int off, int imm)
+{
+	u8 *prog = *pprog;
+
+	switch (size) {
+	case BPF_B:
+		/* mov byte ptr [rax + r12 + off], imm8 */
+		EMIT2(add_3mod(0x40, dst_reg, 0, index_reg), 0xC6);
+		break;
+	case BPF_H:
+		/* mov word ptr [rax + r12 + off], imm16 */
+		EMIT3(0x66, add_3mod(0x40, dst_reg, 0, index_reg), 0xC7);
+		break;
+	case BPF_W:
+		/* mov dword ptr [rax + r12 + 1], imm32 */
+		EMIT2(add_3mod(0x40, dst_reg, 0, index_reg), 0xC7);
+		break;
+	case BPF_DW:
+		/* mov qword ptr [rax + r12 + 1], imm32 */
+		EMIT2(add_3mod(0x48, dst_reg, 0, index_reg), 0xC7);
+		break;
+	}
+	emit_insn_suffix_SIB(&prog, dst_reg, 0, index_reg, off);
+	EMIT(imm, bpf_size_to_x86_bytes(size));
+	*pprog = prog;
+}
+
+static void emit_st_r12(u8 **pprog, u32 size, u32 dst_reg, int off, int imm)
+{
+	emit_st_index(pprog, size, dst_reg, X86_REG_R12, off, imm);
+}
+
 static int emit_atomic(u8 **pprog, u8 atomic_op,
 		       u32 dst_reg, u32 src_reg, s16 off, u8 bpf_size)
 {
@@ -1043,12 +1169,15 @@  static int emit_atomic(u8 **pprog, u8 atomic_op,
 	return 0;
 }
 
+#define DONT_CLEAR 1
+
 bool ex_handler_bpf(const struct exception_table_entry *x, struct pt_regs *regs)
 {
 	u32 reg = x->fixup >> 8;
 
 	/* jump over faulting load and clear dest register */
-	*(unsigned long *)((void *)regs + reg) = 0;
+	if (reg != DONT_CLEAR)
+		*(unsigned long *)((void *)regs + reg) = 0;
 	regs->ip += x->fixup & 0xff;
 	return true;
 }
@@ -1147,11 +1276,14 @@  static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, u8 *rw_image
 	bool tail_call_seen = false;
 	bool seen_exit = false;
 	u8 temp[BPF_MAX_INSN_SIZE + BPF_INSN_SAFETY];
+	u64 arena_vm_start;
 	int i, excnt = 0;
 	int ilen, proglen = 0;
 	u8 *prog = temp;
 	int err;
 
+	arena_vm_start = bpf_arena_get_kern_vm_start(bpf_prog->aux->arena);
+
 	detect_reg_usage(insn, insn_cnt, callee_regs_used,
 			 &tail_call_seen);
 
@@ -1172,8 +1304,13 @@  static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, u8 *rw_image
 		push_r12(&prog);
 		push_callee_regs(&prog, all_callee_regs_used);
 	} else {
+		if (arena_vm_start)
+			push_r12(&prog);
 		push_callee_regs(&prog, callee_regs_used);
 	}
+	if (arena_vm_start)
+		emit_mov_imm64(&prog, X86_REG_R12,
+			       arena_vm_start >> 32, (u32) arena_vm_start);
 
 	ilen = prog - temp;
 	if (rw_image)
@@ -1564,6 +1701,56 @@  st:			if (is_imm8(insn->off))
 			emit_stx(&prog, BPF_SIZE(insn->code), dst_reg, src_reg, insn->off);
 			break;
 
+		case BPF_ST | BPF_PROBE_MEM32 | BPF_B:
+		case BPF_ST | BPF_PROBE_MEM32 | BPF_H:
+		case BPF_ST | BPF_PROBE_MEM32 | BPF_W:
+		case BPF_ST | BPF_PROBE_MEM32 | BPF_DW:
+			start_of_ldx = prog;
+			emit_st_r12(&prog, BPF_SIZE(insn->code), dst_reg, insn->off, insn->imm);
+			goto populate_extable;
+
+			/* LDX: dst_reg = *(u8*)(src_reg + r12 + off) */
+		case BPF_LDX | BPF_PROBE_MEM32 | BPF_B:
+		case BPF_LDX | BPF_PROBE_MEM32 | BPF_H:
+		case BPF_LDX | BPF_PROBE_MEM32 | BPF_W:
+		case BPF_LDX | BPF_PROBE_MEM32 | BPF_DW:
+		case BPF_STX | BPF_PROBE_MEM32 | BPF_B:
+		case BPF_STX | BPF_PROBE_MEM32 | BPF_H:
+		case BPF_STX | BPF_PROBE_MEM32 | BPF_W:
+		case BPF_STX | BPF_PROBE_MEM32 | BPF_DW:
+			start_of_ldx = prog;
+			if (BPF_CLASS(insn->code) == BPF_LDX)
+				emit_ldx_r12(&prog, BPF_SIZE(insn->code), dst_reg, src_reg, insn->off);
+			else
+				emit_stx_r12(&prog, BPF_SIZE(insn->code), dst_reg, src_reg, insn->off);
+populate_extable:
+			{
+				struct exception_table_entry *ex;
+				u8 *_insn = image + proglen + (start_of_ldx - temp);
+				s64 delta;
+
+				if (!bpf_prog->aux->extable)
+					break;
+
+				if (excnt >= bpf_prog->aux->num_exentries) {
+					pr_err("mem32 extable bug\n");
+					return -EFAULT;
+				}
+				ex = &bpf_prog->aux->extable[excnt++];
+
+				delta = _insn - (u8 *)&ex->insn;
+				/* switch ex to rw buffer for writes */
+				ex = (void *)rw_image + ((void *)ex - (void *)image);
+
+				ex->insn = delta;
+
+				ex->data = EX_TYPE_BPF;
+
+				ex->fixup = (prog - start_of_ldx) |
+					((BPF_CLASS(insn->code) == BPF_LDX ? reg2pt_regs[dst_reg] : DONT_CLEAR) << 8);
+			}
+			break;
+
 			/* LDX: dst_reg = *(u8*)(src_reg + off) */
 		case BPF_LDX | BPF_MEM | BPF_B:
 		case BPF_LDX | BPF_PROBE_MEM | BPF_B:
@@ -2036,6 +2223,8 @@  st:			if (is_imm8(insn->off))
 				pop_r12(&prog);
 			} else {
 				pop_callee_regs(&prog, callee_regs_used);
+				if (arena_vm_start)
+					pop_r12(&prog);
 			}
 			EMIT1(0xC9);         /* leave */
 			emit_return(&prog, image + addrs[i - 1] + (prog - temp));
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index ea6ab6e0eef9..8904d1606125 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1458,6 +1458,7 @@  struct bpf_prog_aux {
 	bool xdp_has_frags;
 	bool exception_cb;
 	bool exception_boundary;
+	struct bpf_arena *arena;
 	/* BTF_KIND_FUNC_PROTO for valid attach_btf_id */
 	const struct btf_type *attach_func_proto;
 	/* function name for valid attach_btf_id */
diff --git a/include/linux/filter.h b/include/linux/filter.h
index 36cc29a2934c..b119f04ecb0b 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -72,6 +72,9 @@  struct ctl_table_header;
 /* unused opcode to mark special ldsx instruction. Same as BPF_IND */
 #define BPF_PROBE_MEMSX	0x40
 
+/* unused opcode to mark special load instruction. Same as BPF_MSH */
+#define BPF_PROBE_MEM32	0xa0
+
 /* unused opcode to mark call to interpreter with arguments */
 #define BPF_CALL_ARGS	0xe0