efHeterogeneousSynchronization main.c 庞乐 commit at 2021-03-17

efHeterogeneousSynchronization/main.c

@@ -449,3 +449,202 @@ static inline void emit_udiv(u8 rd, u8 rm, u8 rn, struct jit_ctx *ctx)
 
 	if (rd != ARM_R0)
 		emit(ARM_MOV_R(rd, ARM_R0), ctx);
+}
+
+static inline void update_on_xread(struct jit_ctx *ctx)
+{
+	if (!(ctx->seen & SEEN_X))
+		ctx->flags |= FLAG_NEED_X_RESET;
+
+	ctx->seen |= SEEN_X;
+}
+
+static int build_body(struct jit_ctx *ctx)
+{
+	void *load_func[] = {jit_get_skb_b, jit_get_skb_h, jit_get_skb_w};
+	const struct sk_filter *prog = ctx->skf;
+	const struct sock_filter *inst;
+	unsigned i, load_order, off, condt;
+	int imm12;
+	u32 k;
+
+	for (i = 0; i < prog->len; i++) {
+		inst = &(prog->insns[i]);
+		/* K as an immediate value operand */
+		k = inst->k;
+
+		/* compute offsets only in the fake pass */
+		if (ctx->target == NULL)
+			ctx->offsets[i] = ctx->idx * 4;
+
+		switch (inst->code) {
+		case BPF_S_LD_IMM:
+			emit_mov_i(r_A, k, ctx);
+			break;
+		case BPF_S_LD_W_LEN:
+			ctx->seen |= SEEN_SKB;
+			BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, len) != 4);
+			emit(ARM_LDR_I(r_A, r_skb,
+				       offsetof(struct sk_buff, len)), ctx);
+			break;
+		case BPF_S_LD_MEM:
+			/* A = scratch[k] */
+			ctx->seen |= SEEN_MEM_WORD(k);
+			emit(ARM_LDR_I(r_A, ARM_SP, SCRATCH_OFF(k)), ctx);
+			break;
+		case BPF_S_LD_W_ABS:
+			load_order = 2;
+			goto load;
+		case BPF_S_LD_H_ABS:
+			load_order = 1;
+			goto load;
+		case BPF_S_LD_B_ABS:
+			load_order = 0;
+load:
+			/* the interpreter will deal with the negative K */
+			if ((int)k < 0)
+				return -ENOTSUPP;
+			emit_mov_i(r_off, k, ctx);
+load_common:
+			ctx->seen |= SEEN_DATA | SEEN_CALL;
+
+			if (load_order > 0) {
+				emit(ARM_SUB_I(r_scratch, r_skb_hl,
+					       1 << load_order), ctx);
+				emit(ARM_CMP_R(r_scratch, r_off), ctx);
+				condt = ARM_COND_HS;
+			} else {
+				emit(ARM_CMP_R(r_skb_hl, r_off), ctx);
+				condt = ARM_COND_HI;
+			}
+
+			_emit(condt, ARM_ADD_R(r_scratch, r_off, r_skb_data),
+			      ctx);
+
+			if (load_order == 0)
+				_emit(condt, ARM_LDRB_I(r_A, r_scratch, 0),
+				      ctx);
+			else if (load_order == 1)
+				emit_load_be16(condt, r_A, r_scratch, ctx);
+			else if (load_order == 2)
+				emit_load_be32(condt, r_A, r_scratch, ctx);
+
+			_emit(condt, ARM_B(b_imm(i + 1, ctx)), ctx);
+
+			/* the slowpath */
+			emit_mov_i(ARM_R3, (u32)load_func[load_order], ctx);
+			emit(ARM_MOV_R(ARM_R0, r_skb), ctx);
+			/* the offset is already in R1 */
+			emit_blx_r(ARM_R3, ctx);
+			/* check the result of skb_copy_bits */
+			emit(ARM_CMP_I(ARM_R1, 0), ctx);
+			emit_err_ret(ARM_COND_NE, ctx);
+			emit(ARM_MOV_R(r_A, ARM_R0), ctx);
+			break;
+		case BPF_S_LD_W_IND:
+			load_order = 2;
+			goto load_ind;
+		case BPF_S_LD_H_IND:
+			load_order = 1;
+			goto load_ind;
+		case BPF_S_LD_B_IND:
+			load_order = 0;
+load_ind:
+			OP_IMM3(ARM_ADD, r_off, r_X, k, ctx);
+			goto load_common;
+		case BPF_S_LDX_IMM:
+			ctx->seen |= SEEN_X;
+			emit_mov_i(r_X, k, ctx);
+			break;
+		case BPF_S_LDX_W_LEN:
+			ctx->seen |= SEEN_X | SEEN_SKB;
+			emit(ARM_LDR_I(r_X, r_skb,
+				       offsetof(struct sk_buff, len)), ctx);
+			break;
+		case BPF_S_LDX_MEM:
+			ctx->seen |= SEEN_X | SEEN_MEM_WORD(k);
+			emit(ARM_LDR_I(r_X, ARM_SP, SCRATCH_OFF(k)), ctx);
+			break;
+		case BPF_S_LDX_B_MSH:
+			/* x = ((*(frame + k)) & 0xf) << 2; */
+			ctx->seen |= SEEN_X | SEEN_DATA | SEEN_CALL;
+			/* the interpreter should deal with the negative K */
+			if (k < 0)
+				return -1;
+			/* offset in r1: we might have to take the slow path */
+			emit_mov_i(r_off, k, ctx);
+			emit(ARM_CMP_R(r_skb_hl, r_off), ctx);
+
+			/* load in r0: common with the slowpath */
+			_emit(ARM_COND_HI, ARM_LDRB_R(ARM_R0, r_skb_data,
+						      ARM_R1), ctx);
+			/*
+			 * emit_mov_i() might generate one or two instructions,
+			 * the same holds for emit_blx_r()
+			 */
+			_emit(ARM_COND_HI, ARM_B(b_imm(i + 1, ctx) - 2), ctx);
+
+			emit(ARM_MOV_R(ARM_R0, r_skb), ctx);
+			/* r_off is r1 */
+			emit_mov_i(ARM_R3, (u32)jit_get_skb_b, ctx);
+			emit_blx_r(ARM_R3, ctx);
+			/* check the return value of skb_copy_bits */
+			emit(ARM_CMP_I(ARM_R1, 0), ctx);
+			emit_err_ret(ARM_COND_NE, ctx);
+
+			emit(ARM_AND_I(r_X, ARM_R0, 0x00f), ctx);
+			emit(ARM_LSL_I(r_X, r_X, 2), ctx);
+			break;
+		case BPF_S_ST:
+			ctx->seen |= SEEN_MEM_WORD(k);
+			emit(ARM_STR_I(r_A, ARM_SP, SCRATCH_OFF(k)), ctx);
+			break;
+		case BPF_S_STX:
+			update_on_xread(ctx);
+			ctx->seen |= SEEN_MEM_WORD(k);
+			emit(ARM_STR_I(r_X, ARM_SP, SCRATCH_OFF(k)), ctx);
+			break;
+		case BPF_S_ALU_ADD_K:
+			/* A += K */
+			OP_IMM3(ARM_ADD, r_A, r_A, k, ctx);
+			break;
+		case BPF_S_ALU_ADD_X:
+			update_on_xread(ctx);
+			emit(ARM_ADD_R(r_A, r_A, r_X), ctx);
+			break;
+		case BPF_S_ALU_SUB_K:
+			/* A -= K */
+			OP_IMM3(ARM_SUB, r_A, r_A, k, ctx);
+			break;
+		case BPF_S_ALU_SUB_X:
+			update_on_xread(ctx);
+			emit(ARM_SUB_R(r_A, r_A, r_X), ctx);
+			break;
+		case BPF_S_ALU_MUL_K:
+			/* A *= K */
+			emit_mov_i(r_scratch, k, ctx);
+			emit(ARM_MUL(r_A, r_A, r_scratch), ctx);
+			break;
+		case BPF_S_ALU_MUL_X:
+			update_on_xread(ctx);
+			emit(ARM_MUL(r_A, r_A, r_X), ctx);
+			break;
+		case BPF_S_ALU_DIV_K:
+			/* current k == reciprocal_value(userspace k) */
+			emit_mov_i(r_scratch, k, ctx);
+			/* A = top 32 bits of the product */
+			emit(ARM_UMULL(r_scratch, r_A, r_A, r_scratch), ctx);
+			break;
+		case BPF_S_ALU_DIV_X:
+			update_on_xread(ctx);
+			emit(ARM_CMP_I(r_X, 0), ctx);
+			emit_err_ret(ARM_COND_EQ, ctx);
+			emit_udiv(r_A, r_A, r_X, ctx);
+			break;
+		case BPF_S_ALU_OR_K:
+			/* A |= K */
+			OP_IMM3(ARM_ORR, r_A, r_A, k, ctx);
+			break;
+		case BPF_S_ALU_OR_X:
+			update_on_xread(ctx);
+			emit(ARM_ORR_R(r_A, r_A, r_X), ctx);