efHeterogeneousSynchronization main.c 庞乐 commit at 2021-04-20

efHeterogeneousSynchronization/main.c

@@ -738,3 +738,202 @@ cmp_x:
 		case BPF_S_JMP_JSET_K:
 			/* pc += (A & K) ? pc->jt : pc->jf */
 			condt  = ARM_COND_NE;
+			/* not set iff all zeroes iff Z==1 iff EQ */
+
+			imm12 = imm8m(k);
+			if (imm12 < 0) {
+				emit_mov_i_no8m(r_scratch, k, ctx);
+				emit(ARM_TST_R(r_A, r_scratch), ctx);
+			} else {
+				emit(ARM_TST_I(r_A, imm12), ctx);
+			}
+			goto cond_jump;
+		case BPF_S_JMP_JSET_X:
+			/* pc += (A & X) ? pc->jt : pc->jf */
+			update_on_xread(ctx);
+			condt  = ARM_COND_NE;
+			emit(ARM_TST_R(r_A, r_X), ctx);
+			goto cond_jump;
+		case BPF_S_RET_A:
+			emit(ARM_MOV_R(ARM_R0, r_A), ctx);
+			goto b_epilogue;
+		case BPF_S_RET_K:
+			if ((k == 0) && (ctx->ret0_fp_idx < 0))
+				ctx->ret0_fp_idx = i;
+			emit_mov_i(ARM_R0, k, ctx);
+b_epilogue:
+			if (i != ctx->skf->len - 1)
+				emit(ARM_B(b_imm(prog->len, ctx)), ctx);
+			break;
+		case BPF_S_MISC_TAX:
+			/* X = A */
+			ctx->seen |= SEEN_X;
+			emit(ARM_MOV_R(r_X, r_A), ctx);
+			break;
+		case BPF_S_MISC_TXA:
+			/* A = X */
+			update_on_xread(ctx);
+			emit(ARM_MOV_R(r_A, r_X), ctx);
+			break;
+		case BPF_S_ANC_PROTOCOL:
+			/* A = ntohs(skb->protocol) */
+			ctx->seen |= SEEN_SKB;
+			BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff,
+						  protocol) != 2);
+			off = offsetof(struct sk_buff, protocol);
+			emit(ARM_LDRH_I(r_scratch, r_skb, off), ctx);
+			emit_swap16(r_A, r_scratch, ctx);
+			break;
+		case BPF_S_ANC_CPU:
+			/* r_scratch = current_thread_info() */
+			OP_IMM3(ARM_BIC, r_scratch, ARM_SP, THREAD_SIZE - 1, ctx);
+			/* A = current_thread_info()->cpu */
+			BUILD_BUG_ON(FIELD_SIZEOF(struct thread_info, cpu) != 4);
+			off = offsetof(struct thread_info, cpu);
+			emit(ARM_LDR_I(r_A, r_scratch, off), ctx);
+			break;
+		case BPF_S_ANC_IFINDEX:
+			/* A = skb->dev->ifindex */
+			ctx->seen |= SEEN_SKB;
+			off = offsetof(struct sk_buff, dev);
+			emit(ARM_LDR_I(r_scratch, r_skb, off), ctx);
+
+			emit(ARM_CMP_I(r_scratch, 0), ctx);
+			emit_err_ret(ARM_COND_EQ, ctx);
+
+			BUILD_BUG_ON(FIELD_SIZEOF(struct net_device,
+						  ifindex) != 4);
+			off = offsetof(struct net_device, ifindex);
+			emit(ARM_LDR_I(r_A, r_scratch, off), ctx);
+			break;
+		case BPF_S_ANC_MARK:
+			ctx->seen |= SEEN_SKB;
+			BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, mark) != 4);
+			off = offsetof(struct sk_buff, mark);
+			emit(ARM_LDR_I(r_A, r_skb, off), ctx);
+			break;
+		case BPF_S_ANC_RXHASH:
+			ctx->seen |= SEEN_SKB;
+			BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, rxhash) != 4);
+			off = offsetof(struct sk_buff, rxhash);
+			emit(ARM_LDR_I(r_A, r_skb, off), ctx);
+			break;
+		case BPF_S_ANC_VLAN_TAG:
+		case BPF_S_ANC_VLAN_TAG_PRESENT:
+			ctx->seen |= SEEN_SKB;
+			BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, vlan_tci) != 2);
+			off = offsetof(struct sk_buff, vlan_tci);
+			emit(ARM_LDRH_I(r_A, r_skb, off), ctx);
+			if (inst->code == BPF_S_ANC_VLAN_TAG)
+				OP_IMM3(ARM_AND, r_A, r_A, VLAN_VID_MASK, ctx);
+			else
+				OP_IMM3(ARM_AND, r_A, r_A, VLAN_TAG_PRESENT, ctx);
+			break;
+		case BPF_S_ANC_QUEUE:
+			ctx->seen |= SEEN_SKB;
+			BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff,
+						  queue_mapping) != 2);
+			BUILD_BUG_ON(offsetof(struct sk_buff,
+					      queue_mapping) > 0xff);
+			off = offsetof(struct sk_buff, queue_mapping);
+			emit(ARM_LDRH_I(r_A, r_skb, off), ctx);
+			break;
+		default:
+			return -1;
+		}
+	}
+
+	/* compute offsets only during the first pass */
+	if (ctx->target == NULL)
+		ctx->offsets[i] = ctx->idx * 4;
+
+	return 0;
+}
+
+
+void bpf_jit_compile(struct sk_filter *fp)
+{
+	struct jit_ctx ctx;
+	unsigned tmp_idx;
+	unsigned alloc_size;
+
+	if (!bpf_jit_enable)
+		return;
+
+	memset(&ctx, 0, sizeof(ctx));
+	ctx.skf		= fp;
+	ctx.ret0_fp_idx = -1;
+
+	ctx.offsets = kzalloc(4 * (ctx.skf->len + 1), GFP_KERNEL);
+	if (ctx.offsets == NULL)
+		return;
+
+	/* fake pass to fill in the ctx->seen */
+	if (unlikely(build_body(&ctx)))
+		goto out;
+
+	tmp_idx = ctx.idx;
+	build_prologue(&ctx);
+	ctx.prologue_bytes = (ctx.idx - tmp_idx) * 4;
+
+#if __LINUX_ARM_ARCH__ < 7
+	tmp_idx = ctx.idx;
+	build_epilogue(&ctx);
+	ctx.epilogue_bytes = (ctx.idx - tmp_idx) * 4;
+
+	ctx.idx += ctx.imm_count;
+	if (ctx.imm_count) {
+		ctx.imms = kzalloc(4 * ctx.imm_count, GFP_KERNEL);
+		if (ctx.imms == NULL)
+			goto out;
+	}
+#else
+	/* there's nothing after the epilogue on ARMv7 */
+	build_epilogue(&ctx);
+#endif
+
+	alloc_size = 4 * ctx.idx;
+	ctx.target = module_alloc(max(sizeof(struct work_struct),
+				      alloc_size));
+	if (unlikely(ctx.target == NULL))
+		goto out;
+
+	ctx.idx = 0;
+	build_prologue(&ctx);
+	build_body(&ctx);
+	build_epilogue(&ctx);
+
+	flush_icache_range((u32)ctx.target, (u32)(ctx.target + ctx.idx));
+
+#if __LINUX_ARM_ARCH__ < 7
+	if (ctx.imm_count)
+		kfree(ctx.imms);
+#endif
+
+	if (bpf_jit_enable > 1)
+		print_hex_dump(KERN_INFO, "BPF JIT code: ",
+			       DUMP_PREFIX_ADDRESS, 16, 4, ctx.target,
+			       alloc_size, false);
+
+	fp->bpf_func = (void *)ctx.target;
+out:
+	kfree(ctx.offsets);
+	return;
+}
+
+static void bpf_jit_free_worker(struct work_struct *work)
+{
+	module_free(NULL, work);
+}
+
+void bpf_jit_free(struct sk_filter *fp)
+{
+	struct work_struct *work;
+
+	if (fp->bpf_func != sk_run_filter) {
+		work = (struct work_struct *)fp->bpf_func;
+
+		INIT_WORK(work, bpf_jit_free_worker);
+		schedule_work(work);
+	}
+}