From patchwork Tue Jan 15 08:35:18 2019 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 8bit X-Patchwork-Submitter: =?utf-8?b?QmrDtnJuIFTDtnBlbA==?= X-Patchwork-Id: 1025056 X-Patchwork-Delegate: bpf@iogearbox.net Return-Path: X-Original-To: patchwork-incoming-netdev@ozlabs.org Delivered-To: patchwork-incoming-netdev@ozlabs.org Authentication-Results: ozlabs.org; spf=none (mailfrom) smtp.mailfrom=vger.kernel.org (client-ip=209.132.180.67; helo=vger.kernel.org; envelope-from=netdev-owner@vger.kernel.org; receiver=) Authentication-Results: ozlabs.org; dmarc=pass (p=none dis=none) header.from=gmail.com Authentication-Results: ozlabs.org; dkim=pass (2048-bit key; unprotected) header.d=gmail.com header.i=@gmail.com header.b="f0In0suy"; dkim-atps=neutral Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by ozlabs.org (Postfix) with ESMTP id 43f3Zw5jjFz9rxp for ; Tue, 15 Jan 2019 19:36:08 +1100 (AEDT) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1728363AbfAOIgG (ORCPT ); Tue, 15 Jan 2019 03:36:06 -0500 Received: from mail-lj1-f193.google.com ([209.85.208.193]:38425 "EHLO mail-lj1-f193.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1725869AbfAOIgG (ORCPT ); Tue, 15 Jan 2019 03:36:06 -0500 Received: by mail-lj1-f193.google.com with SMTP id c19-v6so1576409lja.5 for ; Tue, 15 Jan 2019 00:36:01 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20161025; h=from:to:cc:subject:date:message-id:in-reply-to:references :mime-version:content-transfer-encoding; bh=uPq7ZfCSIXyIRsibTm50nWPNGbHlUnFTPFoej6YpplU=; b=f0In0suyet9+f6dKFSicK6IW6pRBb/+0+0+jVdDNwUlF5lW2Fgo8piR0k4fWMBDQdB rigD55ou/u1tj/WaXNk4dE8ljTCSBjPmd+/G5uL+9CB9sx2GTKJ5hl17UU4AvfL/N98G FLHKhMAQR7z4AfhCOluW8xzVPFG9XAj63IlLMbIbzAcHApWVvSibOcxWpVDH1HNVxKa4 7Grv4QLbkenadhZyYfsPbUm9HiJySXniOj1KB9XFgAk9UR2fWE0eKIWSuxumeONTwq2a QlJ5c5dgegn9XVGHxIKh5ArPAqTPt4VMDL7aLYidxwK5kZcXepejeXEZTaKGQ/1MvILB Ejew== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20161025; h=x-gm-message-state:from:to:cc:subject:date:message-id:in-reply-to :references:mime-version:content-transfer-encoding; bh=uPq7ZfCSIXyIRsibTm50nWPNGbHlUnFTPFoej6YpplU=; b=bR6Zl2ReqAkQBAKj/MvLZf8nZyKoTyenNgnpbJtG/A4IIrzc3398Vs3qqRnqknetMP DbBJ8AtwuWOW+2dIoX7mxn/bnvbGVT7vXWtBnAauxghi69A8SF+QqQ4hETz0bLMsFfxH GcvNoIsbSp6c9keVHhXaGR8p6on5Sd7hE0FdOR7nFplcRx+G4sKxMOXri6KZbSdIq54p I9+5NBQUh9WCdLvGyysrM9CS5SvBFmU+viO8SofzZ2Y7E7dJv07h8vqHk3QTb4Ar5yze YMy9dmKL2QFEEYH1UxNoOIWIr87GCQtGUGV/tQS9iRQ9ijV0kn3ub0iwODr5+9JbhnbB nWJg== X-Gm-Message-State: AJcUukc8nps/5T3d1S0EGqIpWuPfR/hHkKmGK+pYi3tecdMD74yfNAzy H05XozW6yDuwiu0EM8fKjx8nxjXTXXHPgg== X-Google-Smtp-Source: ALg8bN4SX1tIXo2r90GkBM1tAEmTvlcNKSFufEZtEhAXSzj79nCzA2ce04seChDcPx5Eonvcnf2k3Q== X-Received: by 2002:a2e:20c3:: with SMTP id g64-v6mr1985927lji.101.1547541359678; Tue, 15 Jan 2019 00:35:59 -0800 (PST) Received: from btopel-mobl.ger.intel.com ([213.100.199.124]) by smtp.gmail.com with ESMTPSA id e14-v6sm453004ljb.31.2019.01.15.00.35.58 (version=TLS1_2 cipher=ECDHE-RSA-AES128-GCM-SHA256 bits=128/128); Tue, 15 Jan 2019 00:35:59 -0800 (PST) From: =?utf-8?b?QmrDtnJuIFTDtnBlbA==?= To: linux-riscv@lists.infradead.org Cc: =?utf-8?b?QmrDtnJuIFTDtnBlbA==?= , daniel@iogearbox.net, palmer@sifive.com, davidlee@sifive.com, netdev@vger.kernel.org Subject: [RFC PATCH 3/3] bpf, riscv: added eBPF JIT for RV64G Date: Tue, 15 Jan 2019 09:35:18 +0100 Message-Id: <20190115083518.10149-4-bjorn.topel@gmail.com> X-Mailer: git-send-email 2.19.1 In-Reply-To: <20190115083518.10149-1-bjorn.topel@gmail.com> References: <20190115083518.10149-1-bjorn.topel@gmail.com> MIME-Version: 1.0 Sender: netdev-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: netdev@vger.kernel.org This commit adds eBPF JIT for RV64G. Codewise, it needs some refactoring. Currently there's a bit too much copy-and-paste going on, and I know some places where I could optimize the code generation a bit (mostly BPF_K type of instructions, dealing with immediates). From a features perspective, two things are missing: * tail calls * "far-branches", i.e. conditional branches that reach beyond 13b. The test_bpf.ko passes all tests. Signed-off-by: Björn Töpel --- arch/riscv/net/bpf_jit_comp.c | 1608 +++++++++++++++++++++++++++++++++ 1 file changed, 1608 insertions(+) diff --git a/arch/riscv/net/bpf_jit_comp.c b/arch/riscv/net/bpf_jit_comp.c index 7e359d3249ee..562d56eb8d23 100644 --- a/arch/riscv/net/bpf_jit_comp.c +++ b/arch/riscv/net/bpf_jit_comp.c @@ -1,4 +1,1612 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * BPF JIT compiler for RV64G + * + * Copyright(c) 2019 Björn Töpel + * + */ + +#include +#include +#include + +#define TMP_REG_0 (MAX_BPF_JIT_REG + 0) +#define TMP_REG_1 (MAX_BPF_JIT_REG + 1) +#define TAIL_CALL_REG (MAX_BPF_JIT_REG + 2) + +enum rv_register { + RV_REG_ZERO = 0, /* The constant value 0 */ + RV_REG_RA = 1, /* Return address */ + RV_REG_SP = 2, /* Stack pointer */ + RV_REG_GP = 3, /* Global pointer */ + RV_REG_TP = 4, /* Thread pointer */ + RV_REG_T0 = 5, /* Temporaries */ + RV_REG_T1 = 6, + RV_REG_T2 = 7, + RV_REG_FP = 8, + RV_REG_S1 = 9, /* Saved registers */ + RV_REG_A0 = 10, /* Function argument/return values */ + RV_REG_A1 = 11, /* Function arguments */ + RV_REG_A2 = 12, + RV_REG_A3 = 13, + RV_REG_A4 = 14, + RV_REG_A5 = 15, + RV_REG_A6 = 16, + RV_REG_A7 = 17, + RV_REG_S2 = 18, /* Saved registers */ + RV_REG_S3 = 19, + RV_REG_S4 = 20, + RV_REG_S5 = 21, + RV_REG_S6 = 22, + RV_REG_S7 = 23, + RV_REG_S8 = 24, + RV_REG_S9 = 25, + RV_REG_S10 = 26, + RV_REG_S11 = 27, + RV_REG_T3 = 28, /* Temporaries */ + RV_REG_T4 = 29, + RV_REG_T5 = 30, + RV_REG_T6 = 31, +}; + +struct rv_jit_context { + struct bpf_prog *prog; + u32 *insns; /* RV insns */ + int ninsns; + int epilogue_offset; + int *offset; /* BPF to RV */ + unsigned long seen_reg_bits; + int stack_size; +}; + +struct rv_jit_data { + struct bpf_binary_header *header; + u8 *image; + struct rv_jit_context ctx; +}; + +static u8 bpf_to_rv_reg(int bpf_reg, struct rv_jit_context *ctx) +{ + switch (bpf_reg) { + /* Return value */ + case BPF_REG_0: + __set_bit(RV_REG_A5, &ctx->seen_reg_bits); + return RV_REG_A5; + /* Function arguments */ + case BPF_REG_1: + __set_bit(RV_REG_A0, &ctx->seen_reg_bits); + return RV_REG_A0; + case BPF_REG_2: + __set_bit(RV_REG_A1, &ctx->seen_reg_bits); + return RV_REG_A1; + case BPF_REG_3: + __set_bit(RV_REG_A2, &ctx->seen_reg_bits); + return RV_REG_A2; + case BPF_REG_4: + __set_bit(RV_REG_A3, &ctx->seen_reg_bits); + return RV_REG_A3; + case BPF_REG_5: + __set_bit(RV_REG_A4, &ctx->seen_reg_bits); + return RV_REG_A4; + /* Callee saved registers */ + case BPF_REG_6: + __set_bit(RV_REG_S1, &ctx->seen_reg_bits); + return RV_REG_S1; + case BPF_REG_7: + __set_bit(RV_REG_S2, &ctx->seen_reg_bits); + return RV_REG_S2; + case BPF_REG_8: + __set_bit(RV_REG_S3, &ctx->seen_reg_bits); + return RV_REG_S3; + case BPF_REG_9: + __set_bit(RV_REG_S4, &ctx->seen_reg_bits); + return RV_REG_S4; + /* Stack read-only frame pointer to access stack */ + case BPF_REG_FP: + __set_bit(RV_REG_S5, &ctx->seen_reg_bits); + return RV_REG_S5; + /* Temporary register */ + case BPF_REG_AX: + __set_bit(RV_REG_T0, &ctx->seen_reg_bits); + return RV_REG_T0; + /* Tail call counter */ + case TAIL_CALL_REG: + __set_bit(RV_REG_S6, &ctx->seen_reg_bits); + return RV_REG_S6; + default: + return 0; + } +}; + +static void seen_call(struct rv_jit_context *ctx) +{ + __set_bit(RV_REG_RA, &ctx->seen_reg_bits); +} + +static bool seen_reg(int rv_reg, struct rv_jit_context *ctx) +{ + return test_bit(rv_reg, &ctx->seen_reg_bits); +} + +static void emit(const u32 insn, struct rv_jit_context *ctx) +{ + if (ctx->insns) + ctx->insns[ctx->ninsns] = insn; + + ctx->ninsns++; +} + +static u32 rv_r_insn(u8 funct7, u8 rs2, u8 rs1, u8 funct3, u8 rd, u8 opcode) +{ + return (funct7 << 25) | (rs2 << 20) | (rs1 << 15) | (funct3 << 12) | + (rd << 7) | opcode; +} + +static u32 rv_i_insn(u16 imm11_0, u8 rs1, u8 funct3, u8 rd, u8 opcode) +{ + return (imm11_0 << 20) | (rs1 << 15) | (funct3 << 12) | (rd << 7) | + opcode; +} + +static u32 rv_s_insn(u16 imm11_0, u8 rs2, u8 rs1, u8 funct3, u8 opcode) +{ + u8 imm11_5 = imm11_0 >> 5, imm4_0 = imm11_0 & 0x1f; + + return (imm11_5 << 25) | (rs2 << 20) | (rs1 << 15) | (funct3 << 12) | + (imm4_0 << 7) | opcode; +} + +static u32 rv_sb_insn(u16 imm12_1, u8 rs2, u8 rs1, u8 funct3, u8 opcode) +{ + u8 imm12 = ((imm12_1 & 0x800) >> 5) | ((imm12_1 & 0x3f0) >> 4); + u8 imm4_1 = ((imm12_1 & 0xf) << 1) | ((imm12_1 & 0x400) >> 10); + + return (imm12 << 25) | (rs2 << 20) | (rs1 << 15) | (funct3 << 12) | + (imm4_1 << 7) | opcode; +} + +static u32 rv_u_insn(u32 imm31_12, u8 rd, u8 opcode) +{ + return (imm31_12 << 12) | (rd << 7) | opcode; +} + +static u32 rv_uj_insn(u32 imm20_1, u8 rd, u8 opcode) +{ + u32 imm; + + imm = (imm20_1 & 0x80000) | ((imm20_1 & 0x3ff) << 9) | + ((imm20_1 & 0x400) >> 2) | ((imm20_1 & 0x7f800) >> 11); + + return (imm << 12) | (rd << 7) | opcode; +} + +static u32 rv_amo_insn(u8 funct5, u8 aq, u8 rl, u8 rs2, u8 rs1, + u8 funct3, u8 rd, u8 opcode) +{ + u8 funct7 = (funct5 << 2) | (aq << 1) | rl; + + return rv_r_insn(funct7, rs2, rs1, funct3, rd, opcode); +} + +static u32 rv_addiw(u8 rd, u8 rs1, u16 imm11_0) +{ + return rv_i_insn(imm11_0, rs1, 0, rd, 0x1b); +} + +static u32 rv_addi(u8 rd, u8 rs1, u16 imm11_0) +{ + return rv_i_insn(imm11_0, rs1, 0, rd, 0x13); +} + +static u32 rv_addw(u8 rd, u8 rs1, u8 rs2) +{ + return rv_r_insn(0, rs2, rs1, 0, rd, 0x3b); +} + +static u32 rv_add(u8 rd, u8 rs1, u8 rs2) +{ + return rv_r_insn(0, rs2, rs1, 0, rd, 0x33); +} + +static u32 rv_subw(u8 rd, u8 rs1, u8 rs2) +{ + return rv_r_insn(0x20, rs2, rs1, 0, rd, 0x3b); +} + +static u32 rv_sub(u8 rd, u8 rs1, u8 rs2) +{ + return rv_r_insn(0x20, rs2, rs1, 0, rd, 0x33); +} + +static u32 rv_and(u8 rd, u8 rs1, u8 rs2) +{ + return rv_r_insn(0, rs2, rs1, 7, rd, 0x33); +} + +static u32 rv_or(u8 rd, u8 rs1, u8 rs2) +{ + return rv_r_insn(0, rs2, rs1, 6, rd, 0x33); +} + +static u32 rv_xor(u8 rd, u8 rs1, u8 rs2) +{ + return rv_r_insn(0, rs2, rs1, 4, rd, 0x33); +} + +static u32 rv_mulw(u8 rd, u8 rs1, u8 rs2) +{ + return rv_r_insn(1, rs2, rs1, 0, rd, 0x3b); +} + +static u32 rv_mul(u8 rd, u8 rs1, u8 rs2) +{ + return rv_r_insn(1, rs2, rs1, 0, rd, 0x33); +} + +static u32 rv_divuw(u8 rd, u8 rs1, u8 rs2) +{ + return rv_r_insn(1, rs2, rs1, 5, rd, 0x3b); +} + +static u32 rv_divu(u8 rd, u8 rs1, u8 rs2) +{ + return rv_r_insn(1, rs2, rs1, 5, rd, 0x33); +} + +static u32 rv_remuw(u8 rd, u8 rs1, u8 rs2) +{ + return rv_r_insn(1, rs2, rs1, 7, rd, 0x3b); +} + +static u32 rv_remu(u8 rd, u8 rs1, u8 rs2) +{ + return rv_r_insn(1, rs2, rs1, 7, rd, 0x33); +} + +static u32 rv_sllw(u8 rd, u8 rs1, u8 rs2) +{ + return rv_r_insn(0, rs2, rs1, 1, rd, 0x3b); +} + +static u32 rv_sll(u8 rd, u8 rs1, u8 rs2) +{ + return rv_r_insn(0, rs2, rs1, 1, rd, 0x33); +} + +static u32 rv_srlw(u8 rd, u8 rs1, u8 rs2) +{ + return rv_r_insn(0, rs2, rs1, 5, rd, 0x3b); +} + +static u32 rv_srl(u8 rd, u8 rs1, u8 rs2) +{ + return rv_r_insn(0, rs2, rs1, 5, rd, 0x33); +} + +static u32 rv_sraw(u8 rd, u8 rs1, u8 rs2) +{ + return rv_r_insn(0x20, rs2, rs1, 5, rd, 0x3b); +} + +static u32 rv_sra(u8 rd, u8 rs1, u8 rs2) +{ + return rv_r_insn(0x20, rs2, rs1, 5, rd, 0x33); +} + +static u32 rv_lui(u8 rd, u32 imm31_12) +{ + return rv_u_insn(imm31_12, rd, 0x37); +} + +static u32 rv_slli(u8 rd, u8 rs1, u16 imm11_0) +{ + return rv_i_insn(imm11_0, rs1, 1, rd, 0x13); +} + +static u32 rv_andi(u8 rd, u8 rs1, u16 imm11_0) +{ + return rv_i_insn(imm11_0, rs1, 7, rd, 0x13); +} + +static u32 rv_ori(u8 rd, u8 rs1, u16 imm11_0) +{ + return rv_i_insn(imm11_0, rs1, 6, rd, 0x13); +} + +static u32 rv_xori(u8 rd, u8 rs1, u16 imm11_0) +{ + return rv_i_insn(imm11_0, rs1, 4, rd, 0x13); +} + +static u32 rv_slliw(u8 rd, u8 rs1, u16 imm11_0) +{ + return rv_i_insn(imm11_0, rs1, 1, rd, 0x1b); +} + +static u32 rv_srliw(u8 rd, u8 rs1, u16 imm11_0) +{ + return rv_i_insn(imm11_0, rs1, 5, rd, 0x1b); +} + +static u32 rv_srli(u8 rd, u8 rs1, u16 imm11_0) +{ + return rv_i_insn(imm11_0, rs1, 5, rd, 0x13); +} + +static u32 rv_sraiw(u8 rd, u8 rs1, u16 imm11_0) +{ + return rv_i_insn(0x400 | imm11_0, rs1, 5, rd, 0x1b); +} + +static u32 rv_srai(u8 rd, u8 rs1, u16 imm11_0) +{ + return rv_i_insn(0x400 | imm11_0, rs1, 5, rd, 0x13); +} + +#if 0 +static u32 rv_auipc(u8 rd, u32 imm31_12) +{ + return rv_u_insn(imm31_12, rd, 0x17); +} +#endif + +static u32 rv_jal(u8 rd, u32 imm20_1) +{ + return rv_uj_insn(imm20_1, rd, 0x6f); +} + +static u32 rv_jalr(u8 rd, u8 rs1, u16 imm11_0) +{ + return rv_i_insn(imm11_0, rs1, 0, rd, 0x67); +} + +static u32 rv_beq(u8 rs1, u8 rs2, u16 imm12_1) +{ + return rv_sb_insn(imm12_1, rs2, rs1, 0, 0x63); +} + +static u32 rv_bltu(u8 rs1, u8 rs2, u16 imm12_1) +{ + return rv_sb_insn(imm12_1, rs2, rs1, 6, 0x63); +} + +static u32 rv_bgeu(u8 rs1, u8 rs2, u16 imm12_1) +{ + return rv_sb_insn(imm12_1, rs2, rs1, 7, 0x63); +} + +static u32 rv_bne(u8 rs1, u8 rs2, u16 imm12_1) +{ + return rv_sb_insn(imm12_1, rs2, rs1, 1, 0x63); +} + +static u32 rv_blt(u8 rs1, u8 rs2, u16 imm12_1) +{ + return rv_sb_insn(imm12_1, rs2, rs1, 4, 0x63); +} + +static u32 rv_bge(u8 rs1, u8 rs2, u16 imm12_1) +{ + return rv_sb_insn(imm12_1, rs2, rs1, 5, 0x63); +} + +static u32 rv_sb(u8 rs1, u16 imm11_0, u8 rs2) +{ + return rv_s_insn(imm11_0, rs2, rs1, 0, 0x23); +} + +static u32 rv_sh(u8 rs1, u16 imm11_0, u8 rs2) +{ + return rv_s_insn(imm11_0, rs2, rs1, 1, 0x23); +} + +static u32 rv_sw(u8 rs1, u16 imm11_0, u8 rs2) +{ + return rv_s_insn(imm11_0, rs2, rs1, 2, 0x23); +} + +static u32 rv_sd(u8 rs1, u16 imm11_0, u8 rs2) +{ + return rv_s_insn(imm11_0, rs2, rs1, 3, 0x23); +} + +#if 0 +static u32 rv_lb(u8 rd, u16 imm11_0, u8 rs1) +{ + return rv_i_insn(imm11_0, rs1, 0, rd, 0x03); +} +#endif + +static u32 rv_lbu(u8 rd, u16 imm11_0, u8 rs1) +{ + return rv_i_insn(imm11_0, rs1, 4, rd, 0x03); +} + +#if 0 +static u32 rv_lh(u8 rd, u16 imm11_0, u8 rs1) +{ + return rv_i_insn(imm11_0, rs1, 1, rd, 0x03); +} +#endif + +static u32 rv_lhu(u8 rd, u16 imm11_0, u8 rs1) +{ + return rv_i_insn(imm11_0, rs1, 5, rd, 0x03); +} + +#if 0 +static u32 rv_lw(u8 rd, u16 imm11_0, u8 rs1) +{ + return rv_i_insn(imm11_0, rs1, 2, rd, 0x03); +} +#endif + +static u32 rv_lwu(u8 rd, u16 imm11_0, u8 rs1) +{ + return rv_i_insn(imm11_0, rs1, 6, rd, 0x03); +} + +static u32 rv_ld(u8 rd, u16 imm11_0, u8 rs1) +{ + return rv_i_insn(imm11_0, rs1, 3, rd, 0x03); +} + +static u32 rv_amoadd_w(u8 rd, u8 rs2, u8 rs1, u8 aq, u8 rl) +{ + return rv_amo_insn(0, aq, rl, rs2, rs1, 2, rd, 0x2f); +} + +static u32 rv_amoadd_d(u8 rd, u8 rs2, u8 rs1, u8 aq, u8 rl) +{ + return rv_amo_insn(0, aq, rl, rs2, rs1, 3, rd, 0x2f); +} + +static bool is_12b_int(s64 val) +{ + return -(1 << 11) <= val && val < (1 << 11); +} + +static bool is_32b_int(s64 val) +{ + return -(1L << 31) <= val && val < (1L << 31); +} + +/* jumps */ +static bool is_21b_int(s64 val) +{ + return -(1L << 20) <= val && val < (1L << 20); + +} + +/* conditional branches */ +static bool is_13b_int(s64 val) +{ + return -(1 << 12) <= val && val < (1 << 12); +} + +static void emit_imm(u8 rd, s64 val, struct rv_jit_context *ctx) +{ + /* Note that the immediate from the add is sign-extended, + * which means that we need to compensate this by adding 2^12, + * when the 12th bit is set. A simpler way of doing this, and + * getting rid of the check, is to just add 2**11 before the + * shift. The "Loading a 32-Bit constant" example from the + * "Computer Organization and Design, RISC-V edition" book by + * Patterson/Hennessy highlights this fact. + * + * This also means that we need to process LSB to MSB. + */ + s64 upper = (val + (1 << 11)) >> 12, lower = val & 0xfff; + int shift; + + if (is_32b_int(val)) { + if (upper) + emit(rv_lui(rd, upper), ctx); + + if (!upper) { + emit(rv_addi(rd, RV_REG_ZERO, lower), ctx); + return; + } + + emit(rv_addiw(rd, rd, lower), ctx); + return; + } + + shift = __ffs(upper); + upper >>= shift; + shift += 12; + + emit_imm(rd, upper, ctx); + + emit(rv_slli(rd, rd, shift), ctx); + if (lower) + emit(rv_addi(rd, rd, lower), ctx); +} + +static int rv_offset(int bpf_to, int bpf_from, struct rv_jit_context *ctx) +{ + int from = ctx->offset[bpf_from] - 1, to = ctx->offset[bpf_to]; + + return (to - from) << 2; +} + +static int epilogue_offset(struct rv_jit_context *ctx) +{ + int to = ctx->epilogue_offset, from = ctx->ninsns; + + return (to - from) << 2; +} + +static int emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx, + bool extra_pass) +{ + bool is64 = BPF_CLASS(insn->code) == BPF_ALU64; + int rvoff, i = insn - ctx->prog->insnsi; + u8 rd, rs, code = insn->code; + s16 off = insn->off; + s32 imm = insn->imm; + + switch (code) { + /* dst = src */ + case BPF_ALU | BPF_MOV | BPF_X: + case BPF_ALU64 | BPF_MOV | BPF_X: + rs = bpf_to_rv_reg(insn->src_reg, ctx); + rd = bpf_to_rv_reg(insn->dst_reg, ctx); + emit(is64 ? rv_addi(rd, rs, 0) : rv_addiw(rd, rs, 0), ctx); + if (!is64) { + emit(rv_slli(rd, rd, 32), ctx); + emit(rv_srli(rd, rd, 32), ctx); + } + break; + + /* dst = dst OP src */ + case BPF_ALU | BPF_ADD | BPF_X: + case BPF_ALU64 | BPF_ADD | BPF_X: + rs = bpf_to_rv_reg(insn->src_reg, ctx); + rd = bpf_to_rv_reg(insn->dst_reg, ctx); + emit(is64 ? rv_add(rd, rd, rs) : rv_addw(rd, rd, rs), ctx); + break; + case BPF_ALU | BPF_SUB | BPF_X: + case BPF_ALU64 | BPF_SUB | BPF_X: + rs = bpf_to_rv_reg(insn->src_reg, ctx); + rd = bpf_to_rv_reg(insn->dst_reg, ctx); + emit(is64 ? rv_sub(rd, rd, rs) : rv_subw(rd, rd, rs), ctx); + break; + case BPF_ALU | BPF_AND | BPF_X: + case BPF_ALU64 | BPF_AND | BPF_X: + rs = bpf_to_rv_reg(insn->src_reg, ctx); + rd = bpf_to_rv_reg(insn->dst_reg, ctx); + emit(rv_and(rd, rd, rs), ctx); + break; + case BPF_ALU | BPF_OR | BPF_X: + case BPF_ALU64 | BPF_OR | BPF_X: + rs = bpf_to_rv_reg(insn->src_reg, ctx); + rd = bpf_to_rv_reg(insn->dst_reg, ctx); + emit(rv_or(rd, rd, rs), ctx); + break; + case BPF_ALU | BPF_XOR | BPF_X: + case BPF_ALU64 | BPF_XOR | BPF_X: + rs = bpf_to_rv_reg(insn->src_reg, ctx); + rd = bpf_to_rv_reg(insn->dst_reg, ctx); + emit(rv_xor(rd, rd, rs), ctx); + break; + case BPF_ALU | BPF_MUL | BPF_X: + case BPF_ALU64 | BPF_MUL | BPF_X: + rs = bpf_to_rv_reg(insn->src_reg, ctx); + rd = bpf_to_rv_reg(insn->dst_reg, ctx); + emit(is64 ? rv_mul(rd, rd, rs) : rv_mulw(rd, rd, rs), ctx); + if (!is64) { + emit(rv_slli(rd, rd, 32), ctx); + emit(rv_srli(rd, rd, 32), ctx); + } + break; + case BPF_ALU | BPF_DIV | BPF_X: + case BPF_ALU64 | BPF_DIV | BPF_X: + rs = bpf_to_rv_reg(insn->src_reg, ctx); + rd = bpf_to_rv_reg(insn->dst_reg, ctx); + emit(is64 ? rv_divu(rd, rd, rs) : rv_divuw(rd, rd, rs), ctx); + if (!is64) { + emit(rv_slli(rd, rd, 32), ctx); + emit(rv_srli(rd, rd, 32), ctx); + } + break; + case BPF_ALU | BPF_MOD | BPF_X: + case BPF_ALU64 | BPF_MOD | BPF_X: + rs = bpf_to_rv_reg(insn->src_reg, ctx); + rd = bpf_to_rv_reg(insn->dst_reg, ctx); + emit(is64 ? rv_remu(rd, rd, rs) : rv_remuw(rd, rd, rs), ctx); + if (!is64) { + emit(rv_slli(rd, rd, 32), ctx); + emit(rv_srli(rd, rd, 32), ctx); + } + break; + case BPF_ALU | BPF_LSH | BPF_X: + case BPF_ALU64 | BPF_LSH | BPF_X: + rs = bpf_to_rv_reg(insn->src_reg, ctx); + rd = bpf_to_rv_reg(insn->dst_reg, ctx); + emit(is64 ? rv_sll(rd, rd, rs) : rv_sllw(rd, rd, rs), ctx); + break; + case BPF_ALU | BPF_RSH | BPF_X: + case BPF_ALU64 | BPF_RSH | BPF_X: + rs = bpf_to_rv_reg(insn->src_reg, ctx); + rd = bpf_to_rv_reg(insn->dst_reg, ctx); + emit(is64 ? rv_srl(rd, rd, rs) : rv_srlw(rd, rd, rs), ctx); + break; + case BPF_ALU | BPF_ARSH | BPF_X: + case BPF_ALU64 | BPF_ARSH | BPF_X: + rs = bpf_to_rv_reg(insn->src_reg, ctx); + rd = bpf_to_rv_reg(insn->dst_reg, ctx); + emit(is64 ? rv_sra(rd, rd, rs) : rv_sraw(rd, rd, rs), ctx); + break; + + /* dst = -dst */ + case BPF_ALU | BPF_NEG: + case BPF_ALU64 | BPF_NEG: + rd = bpf_to_rv_reg(insn->dst_reg, ctx); + emit(is64 ? + rv_sub(rd, RV_REG_ZERO, rd) : + rv_subw(rd, RV_REG_ZERO, rd), + ctx); + break; + + /* dst = BSWAP##imm(dst) */ + case BPF_ALU | BPF_END | BPF_FROM_LE: + { + int shift = 64 - imm; + + rd = bpf_to_rv_reg(insn->dst_reg, ctx); + emit(rv_slli(rd, rd, shift), ctx); + emit(rv_srli(rd, rd, shift), ctx); + break; + } + case BPF_ALU | BPF_END | BPF_FROM_BE: + rd = bpf_to_rv_reg(insn->dst_reg, ctx); + + emit(rv_addi(RV_REG_T2, RV_REG_ZERO, 0), ctx); + + emit(rv_andi(RV_REG_T1, rd, 0xff), ctx); + emit(rv_add(RV_REG_T2, RV_REG_T2, RV_REG_T1), ctx); + emit(rv_slli(RV_REG_T2, RV_REG_T2, 8), ctx); + emit(rv_srli(rd, rd, 8), ctx); + if (imm == 16) + goto out_be; + + emit(rv_andi(RV_REG_T1, rd, 0xff), ctx); + emit(rv_add(RV_REG_T2, RV_REG_T2, RV_REG_T1), ctx); + emit(rv_slli(RV_REG_T2, RV_REG_T2, 8), ctx); + emit(rv_srli(rd, rd, 8), ctx); + + emit(rv_andi(RV_REG_T1, rd, 0xff), ctx); + emit(rv_add(RV_REG_T2, RV_REG_T2, RV_REG_T1), ctx); + emit(rv_slli(RV_REG_T2, RV_REG_T2, 8), ctx); + emit(rv_srli(rd, rd, 8), ctx); + if (imm == 32) + goto out_be; + + emit(rv_andi(RV_REG_T1, rd, 0xff), ctx); + emit(rv_add(RV_REG_T2, RV_REG_T2, RV_REG_T1), ctx); + emit(rv_slli(RV_REG_T2, RV_REG_T2, 8), ctx); + emit(rv_srli(rd, rd, 8), ctx); + + emit(rv_andi(RV_REG_T1, rd, 0xff), ctx); + emit(rv_add(RV_REG_T2, RV_REG_T2, RV_REG_T1), ctx); + emit(rv_slli(RV_REG_T2, RV_REG_T2, 8), ctx); + emit(rv_srli(rd, rd, 8), ctx); + + emit(rv_andi(RV_REG_T1, rd, 0xff), ctx); + emit(rv_add(RV_REG_T2, RV_REG_T2, RV_REG_T1), ctx); + emit(rv_slli(RV_REG_T2, RV_REG_T2, 8), ctx); + emit(rv_srli(rd, rd, 8), ctx); + + emit(rv_andi(RV_REG_T1, rd, 0xff), ctx); + emit(rv_add(RV_REG_T2, RV_REG_T2, RV_REG_T1), ctx); + emit(rv_slli(RV_REG_T2, RV_REG_T2, 8), ctx); + emit(rv_srli(rd, rd, 8), ctx); + out_be: + emit(rv_andi(RV_REG_T1, rd, 0xff), ctx); + emit(rv_add(RV_REG_T2, RV_REG_T2, RV_REG_T1), ctx); + + emit(rv_addi(rd, RV_REG_T2, 0), ctx); + break; + + /* dst = imm */ + case BPF_ALU | BPF_MOV | BPF_K: + case BPF_ALU64 | BPF_MOV | BPF_K: + rd = bpf_to_rv_reg(insn->dst_reg, ctx); + emit_imm(rd, imm, ctx); + if (!is64) { + emit(rv_slli(rd, rd, 32), ctx); + emit(rv_srli(rd, rd, 32), ctx); + } + break; + + /* dst = dst OP imm */ + case BPF_ALU | BPF_ADD | BPF_K: + case BPF_ALU64 | BPF_ADD | BPF_K: + rd = bpf_to_rv_reg(insn->dst_reg, ctx); + if (is_12b_int(imm)) { + emit(is64 ? rv_addi(rd, rd, imm) : + rv_addiw(rd, rd, imm), ctx); + if (!is64) { + emit(rv_slli(rd, rd, 32), ctx); + emit(rv_srli(rd, rd, 32), ctx); + } + break; + } + emit_imm(RV_REG_T1, imm, ctx); + emit(is64 ? rv_add(rd, rd, RV_REG_T1) : + rv_addw(rd, rd, RV_REG_T1), ctx); + if (!is64) { + emit(rv_slli(rd, rd, 32), ctx); + emit(rv_srli(rd, rd, 32), ctx); + } + break; + case BPF_ALU | BPF_SUB | BPF_K: + case BPF_ALU64 | BPF_SUB | BPF_K: + rd = bpf_to_rv_reg(insn->dst_reg, ctx); + if (is_12b_int(-imm)) { + emit(is64 ? rv_addi(rd, rd, -imm) : + rv_addiw(rd, rd, -imm), ctx); + if (!is64) { + emit(rv_slli(rd, rd, 32), ctx); + emit(rv_srli(rd, rd, 32), ctx); + } + break; + } + emit_imm(RV_REG_T1, imm, ctx); + emit(is64 ? rv_sub(rd, rd, RV_REG_T1) : + rv_subw(rd, rd, RV_REG_T1), ctx); + if (!is64) { + emit(rv_slli(rd, rd, 32), ctx); + emit(rv_srli(rd, rd, 32), ctx); + } + break; + case BPF_ALU | BPF_AND | BPF_K: + case BPF_ALU64 | BPF_AND | BPF_K: + rd = bpf_to_rv_reg(insn->dst_reg, ctx); + if (is_12b_int(imm)) { + emit(rv_andi(rd, rd, imm), ctx); + if (!is64) { + emit(rv_slli(rd, rd, 32), ctx); + emit(rv_srli(rd, rd, 32), ctx); + } + break; + } + emit_imm(RV_REG_T1, imm, ctx); + emit(rv_and(rd, rd, RV_REG_T1), ctx); + if (!is64) { + emit(rv_slli(rd, rd, 32), ctx); + emit(rv_srli(rd, rd, 32), ctx); + } + break; + case BPF_ALU | BPF_OR | BPF_K: + case BPF_ALU64 | BPF_OR | BPF_K: + rd = bpf_to_rv_reg(insn->dst_reg, ctx); + if (is_12b_int(imm)) { + emit(rv_ori(rd, rd, imm), ctx); + if (!is64) { + emit(rv_slli(rd, rd, 32), ctx); + emit(rv_srli(rd, rd, 32), ctx); + } + break; + } + emit_imm(RV_REG_T1, imm, ctx); + emit(rv_or(rd, rd, RV_REG_T1), ctx); + if (!is64) { + emit(rv_slli(rd, rd, 32), ctx); + emit(rv_srli(rd, rd, 32), ctx); + } + break; + case BPF_ALU | BPF_XOR | BPF_K: + case BPF_ALU64 | BPF_XOR | BPF_K: + rd = bpf_to_rv_reg(insn->dst_reg, ctx); + if (is_12b_int(imm)) { + emit(rv_xori(rd, rd, imm), ctx); + if (!is64) { + emit(rv_slli(rd, rd, 32), ctx); + emit(rv_srli(rd, rd, 32), ctx); + } + break; + } + emit_imm(RV_REG_T1, imm, ctx); + emit(rv_xor(rd, rd, RV_REG_T1), ctx); + if (!is64) { + emit(rv_slli(rd, rd, 32), ctx); + emit(rv_srli(rd, rd, 32), ctx); + } + break; + case BPF_ALU | BPF_MUL | BPF_K: + case BPF_ALU64 | BPF_MUL | BPF_K: + rd = bpf_to_rv_reg(insn->dst_reg, ctx); + emit_imm(RV_REG_T1, imm, ctx); + emit(is64 ? rv_mul(rd, rd, RV_REG_T1) : + rv_mulw(rd, rd, RV_REG_T1), ctx); + if (!is64) { + emit(rv_slli(rd, rd, 32), ctx); + emit(rv_srli(rd, rd, 32), ctx); + } + break; + case BPF_ALU | BPF_DIV | BPF_K: + case BPF_ALU64 | BPF_DIV | BPF_K: + rd = bpf_to_rv_reg(insn->dst_reg, ctx); + emit_imm(RV_REG_T1, imm, ctx); + emit(is64 ? rv_divu(rd, rd, RV_REG_T1) : + rv_divuw(rd, rd, RV_REG_T1), ctx); + if (!is64) { + emit(rv_slli(rd, rd, 32), ctx); + emit(rv_srli(rd, rd, 32), ctx); + } + break; + case BPF_ALU | BPF_MOD | BPF_K: + case BPF_ALU64 | BPF_MOD | BPF_K: + rd = bpf_to_rv_reg(insn->dst_reg, ctx); + emit_imm(RV_REG_T1, imm, ctx); + emit(is64 ? rv_remu(rd, rd, RV_REG_T1) : + rv_remuw(rd, rd, RV_REG_T1), ctx); + if (!is64) { + emit(rv_slli(rd, rd, 32), ctx); + emit(rv_srli(rd, rd, 32), ctx); + } + break; + case BPF_ALU | BPF_LSH | BPF_K: + case BPF_ALU64 | BPF_LSH | BPF_K: + rd = bpf_to_rv_reg(insn->dst_reg, ctx); + emit(is64 ? rv_slli(rd, rd, imm) : + rv_slliw(rd, rd, imm), ctx); + break; + case BPF_ALU | BPF_RSH | BPF_K: + case BPF_ALU64 | BPF_RSH | BPF_K: + rd = bpf_to_rv_reg(insn->dst_reg, ctx); + emit(is64 ? rv_srli(rd, rd, imm) : + rv_srliw(rd, rd, imm), ctx); + break; + case BPF_ALU | BPF_ARSH | BPF_K: + case BPF_ALU64 | BPF_ARSH | BPF_K: + rd = bpf_to_rv_reg(insn->dst_reg, ctx); + emit(is64 ? rv_srai(rd, rd, imm) : + rv_sraiw(rd, rd, imm), ctx); + break; + + /* JUMP off */ + case BPF_JMP | BPF_JA: + rvoff = rv_offset(i + off, i, ctx); + if (!is_21b_int(rvoff)) { + pr_err("bpf-jit: %d offset=%d not supported yet!\n", + __LINE__, rvoff); + return -1; + } + + emit(rv_jal(RV_REG_ZERO, rvoff >> 1), ctx); + break; + + /* IF (dst COND src) JUMP off */ + case BPF_JMP | BPF_JEQ | BPF_X: + rvoff = rv_offset(i + off, i, ctx); + if (!is_13b_int(rvoff)) { + pr_err("bpf-jit: %d offset=%d not supported yet!\n", + __LINE__, (int)rvoff); + return -1; + } + rs = bpf_to_rv_reg(insn->src_reg, ctx); + rd = bpf_to_rv_reg(insn->dst_reg, ctx); + emit(rv_beq(rd, rs, rvoff >> 1), ctx); + break; + case BPF_JMP | BPF_JGT | BPF_X: + rvoff = rv_offset(i + off, i, ctx); + if (!is_13b_int(rvoff)) { + pr_err("bpf-jit: %d offset=%d not supported yet!\n", + __LINE__, (int)rvoff); + return -1; + } + rs = bpf_to_rv_reg(insn->src_reg, ctx); + rd = bpf_to_rv_reg(insn->dst_reg, ctx); + emit(rv_bltu(rs, rd, rvoff >> 1), ctx); + break; + case BPF_JMP | BPF_JLT | BPF_X: + rvoff = rv_offset(i + off, i, ctx); + if (!is_13b_int(rvoff)) { + pr_err("bpf-jit: %d offset=%d not supported yet!\n", + __LINE__, (int)rvoff); + return -1; + } + rs = bpf_to_rv_reg(insn->src_reg, ctx); + rd = bpf_to_rv_reg(insn->dst_reg, ctx); + emit(rv_bltu(rd, rs, rvoff >> 1), ctx); + break; + case BPF_JMP | BPF_JGE | BPF_X: + rvoff = rv_offset(i + off, i, ctx); + if (!is_13b_int(rvoff)) { + pr_err("bpf-jit: %d offset=%d not supported yet!\n", + __LINE__, (int)rvoff); + return -1; + } + rs = bpf_to_rv_reg(insn->src_reg, ctx); + rd = bpf_to_rv_reg(insn->dst_reg, ctx); + emit(rv_bgeu(rd, rs, rvoff >> 1), ctx); + break; + case BPF_JMP | BPF_JLE | BPF_X: + rvoff = rv_offset(i + off, i, ctx); + if (!is_13b_int(rvoff)) { + pr_err("bpf-jit: %d offset=%d not supported yet!\n", + __LINE__, (int)rvoff); + return -1; + } + rs = bpf_to_rv_reg(insn->src_reg, ctx); + rd = bpf_to_rv_reg(insn->dst_reg, ctx); + emit(rv_bgeu(rs, rd, rvoff >> 1), ctx); + break; + case BPF_JMP | BPF_JNE | BPF_X: + rvoff = rv_offset(i + off, i, ctx); + if (!is_13b_int(rvoff)) { + pr_err("bpf-jit: %d offset=%d not supported yet!\n", + __LINE__, (int)rvoff); + return -1; + } + rs = bpf_to_rv_reg(insn->src_reg, ctx); + rd = bpf_to_rv_reg(insn->dst_reg, ctx); + emit(rv_bne(rd, rs, rvoff >> 1), ctx); + break; + case BPF_JMP | BPF_JSGT | BPF_X: + rvoff = rv_offset(i + off, i, ctx); + if (!is_13b_int(rvoff)) { + pr_err("bpf-jit: %d offset=%d not supported yet!\n", + __LINE__, (int)rvoff); + return -1; + } + rs = bpf_to_rv_reg(insn->src_reg, ctx); + rd = bpf_to_rv_reg(insn->dst_reg, ctx); + emit(rv_blt(rs, rd, rvoff >> 1), ctx); + break; + case BPF_JMP | BPF_JSLT | BPF_X: + rvoff = rv_offset(i + off, i, ctx); + if (!is_13b_int(rvoff)) { + pr_err("bpf-jit: %d offset=%d not supported yet!\n", + __LINE__, (int)rvoff); + return -1; + } + rs = bpf_to_rv_reg(insn->src_reg, ctx); + rd = bpf_to_rv_reg(insn->dst_reg, ctx); + emit(rv_blt(rd, rs, rvoff >> 1), ctx); + break; + case BPF_JMP | BPF_JSGE | BPF_X: + rvoff = rv_offset(i + off, i, ctx); + if (!is_13b_int(rvoff)) { + pr_err("bpf-jit: %d offset=%d not supported yet!\n", + __LINE__, (int)rvoff); + return -1; + } + rs = bpf_to_rv_reg(insn->src_reg, ctx); + rd = bpf_to_rv_reg(insn->dst_reg, ctx); + emit(rv_bge(rd, rs, rvoff >> 1), ctx); + break; + case BPF_JMP | BPF_JSLE | BPF_X: + rvoff = rv_offset(i + off, i, ctx); + if (!is_13b_int(rvoff)) { + pr_err("bpf-jit: %d offset=%d not supported yet!\n", + __LINE__, (int)rvoff); + return -1; + } + rs = bpf_to_rv_reg(insn->src_reg, ctx); + rd = bpf_to_rv_reg(insn->dst_reg, ctx); + emit(rv_bge(rs, rd, rvoff >> 1), ctx); + break; + case BPF_JMP | BPF_JSET | BPF_X: + rvoff = rv_offset(i + off, i, ctx); + if (!is_13b_int(rvoff)) { + pr_err("bpf-jit: %d offset=%d not supported yet!\n", + __LINE__, (int)rvoff); + return -1; + } + rs = bpf_to_rv_reg(insn->src_reg, ctx); + rd = bpf_to_rv_reg(insn->dst_reg, ctx); + emit(rv_and(RV_REG_T1, rd, rs), ctx); + emit(rv_bne(RV_REG_T1, RV_REG_ZERO, rvoff >> 1), ctx); + break; + + /* IF (dst COND imm) JUMP off */ + case BPF_JMP | BPF_JEQ | BPF_K: + rvoff = rv_offset(i + off, i, ctx); + if (!is_13b_int(rvoff)) { + pr_err("bpf-jit: %d offset=%d not supported yet!\n", + __LINE__, (int)rvoff); + return -1; + } + rd = bpf_to_rv_reg(insn->dst_reg, ctx); + emit_imm(RV_REG_T1, imm, ctx); + emit(rv_beq(rd, RV_REG_T1, rvoff >> 1), ctx); + break; + case BPF_JMP | BPF_JGT | BPF_K: + rvoff = rv_offset(i + off, i, ctx); + if (!is_13b_int(rvoff)) { + pr_err("bpf-jit: %d offset=%d not supported yet!\n", + __LINE__, (int)rvoff); + return -1; + } + rd = bpf_to_rv_reg(insn->dst_reg, ctx); + emit_imm(RV_REG_T1, imm, ctx); + emit(rv_bltu(RV_REG_T1, rd, rvoff >> 1), ctx); + break; + case BPF_JMP | BPF_JLT | BPF_K: + rvoff = rv_offset(i + off, i, ctx); + if (!is_13b_int(rvoff)) { + pr_err("bpf-jit: %d offset=%d not supported yet!\n", + __LINE__, (int)rvoff); + return -1; + } + rd = bpf_to_rv_reg(insn->dst_reg, ctx); + emit_imm(RV_REG_T1, imm, ctx); + emit(rv_bltu(rd, RV_REG_T1, rvoff >> 1), ctx); + break; + case BPF_JMP | BPF_JGE | BPF_K: + rvoff = rv_offset(i + off, i, ctx); + if (!is_13b_int(rvoff)) { + pr_err("bpf-jit: %d offset=%d not supported yet!\n", + __LINE__, (int)rvoff); + return -1; + } + rd = bpf_to_rv_reg(insn->dst_reg, ctx); + emit_imm(RV_REG_T1, imm, ctx); + emit(rv_bgeu(rd, RV_REG_T1, rvoff >> 1), ctx); + break; + case BPF_JMP | BPF_JLE | BPF_K: + rvoff = rv_offset(i + off, i, ctx); + if (!is_13b_int(rvoff)) { + pr_err("bpf-jit: %d offset=%d not supported yet!\n", + __LINE__, (int)rvoff); + return -1; + } + rd = bpf_to_rv_reg(insn->dst_reg, ctx); + emit_imm(RV_REG_T1, imm, ctx); + emit(rv_bgeu(RV_REG_T1, rd, rvoff >> 1), ctx); + break; + case BPF_JMP | BPF_JNE | BPF_K: + rvoff = rv_offset(i + off, i, ctx); + if (!is_13b_int(rvoff)) { + pr_err("bpf-jit: %d offset=%d not supported yet!\n", + __LINE__, (int)rvoff); + return -1; + } + rd = bpf_to_rv_reg(insn->dst_reg, ctx); + emit_imm(RV_REG_T1, imm, ctx); + emit(rv_bne(rd, RV_REG_T1, rvoff >> 1), ctx); + break; + case BPF_JMP | BPF_JSGT | BPF_K: + rvoff = rv_offset(i + off, i, ctx); + if (!is_13b_int(rvoff)) { + pr_err("bpf-jit: %d offset=%d not supported yet!\n", + __LINE__, (int)rvoff); + return -1; + } + rd = bpf_to_rv_reg(insn->dst_reg, ctx); + emit_imm(RV_REG_T1, imm, ctx); + emit(rv_blt(RV_REG_T1, rd, rvoff >> 1), ctx); + break; + case BPF_JMP | BPF_JSLT | BPF_K: + rvoff = rv_offset(i + off, i, ctx); + if (!is_13b_int(rvoff)) { + pr_err("bpf-jit: %d offset=%d not supported yet!\n", + __LINE__, (int)rvoff); + return -1; + } + rd = bpf_to_rv_reg(insn->dst_reg, ctx); + emit_imm(RV_REG_T1, imm, ctx); + emit(rv_blt(rd, RV_REG_T1, rvoff >> 1), ctx); + break; + case BPF_JMP | BPF_JSGE | BPF_K: + rvoff = rv_offset(i + off, i, ctx); + if (!is_13b_int(rvoff)) { + pr_err("bpf-jit: %d offset=%d not supported yet!\n", + __LINE__, (int)rvoff); + return -1; + } + rd = bpf_to_rv_reg(insn->dst_reg, ctx); + emit_imm(RV_REG_T1, imm, ctx); + emit(rv_bge(rd, RV_REG_T1, rvoff >> 1), ctx); + break; + case BPF_JMP | BPF_JSLE | BPF_K: + rvoff = rv_offset(i + off, i, ctx); + if (!is_13b_int(rvoff)) { + pr_err("bpf-jit: %d offset=%d not supported yet!\n", + __LINE__, (int)rvoff); + return -1; + } + rd = bpf_to_rv_reg(insn->dst_reg, ctx); + emit_imm(RV_REG_T1, imm, ctx); + emit(rv_bge(RV_REG_T1, rd, rvoff >> 1), ctx); + break; + case BPF_JMP | BPF_JSET | BPF_K: + rvoff = rv_offset(i + off, i, ctx); + if (!is_13b_int(rvoff)) { + pr_err("bpf-jit: %d offset=%d not supported yet!\n", + __LINE__, (int)rvoff); + return -1; + } + rd = bpf_to_rv_reg(insn->dst_reg, ctx); + emit_imm(RV_REG_T2, imm, ctx); + emit(rv_and(RV_REG_T1, rd, RV_REG_T2), ctx); + emit(rv_bne(RV_REG_T1, RV_REG_ZERO, rvoff >> 1), ctx); + break; + + /* function call */ + case BPF_JMP | BPF_CALL: + { + bool fixed; + int i, ret; + u64 addr; + + seen_call(ctx); + ret = bpf_jit_get_func_addr(ctx->prog, insn, extra_pass, &addr, + &fixed); + if (ret < 0) + return ret; + if (fixed) { + emit_imm(RV_REG_T1, addr, ctx); + } else { + i = ctx->ninsns; + emit_imm(RV_REG_T1, addr, ctx); + for (i = ctx->ninsns - i; i < 8; i++) { + /* nop */ + emit(rv_addi(RV_REG_ZERO, RV_REG_ZERO, 0), + ctx); + } + } + emit(rv_jalr(RV_REG_RA, RV_REG_T1, 0), ctx); + rd = bpf_to_rv_reg(BPF_REG_0, ctx); + emit(rv_addi(rd, RV_REG_A0, 0), ctx); + break; + } + /* tail call */ + case BPF_JMP | BPF_TAIL_CALL: + rd = bpf_to_rv_reg(TAIL_CALL_REG, ctx); + pr_err("bpf-jit: tail call not supported yet!\n"); + return -1; + + /* function return */ + case BPF_JMP | BPF_EXIT: + if (i == ctx->prog->len - 1) + break; + + rvoff = epilogue_offset(ctx); + if (!is_21b_int(rvoff)) { + pr_err("bpf-jit: %d offset=%d not supported yet!\n", + __LINE__, rvoff); + return -1; + } + + emit(rv_jal(RV_REG_ZERO, rvoff >> 1), ctx); + break; + + /* dst = imm64 */ + case BPF_LD | BPF_IMM | BPF_DW: + { + struct bpf_insn insn1 = insn[1]; + u64 imm64; + + imm64 = (u64)insn1.imm << 32 | (u32)imm; + rd = bpf_to_rv_reg(insn->dst_reg, ctx); + emit_imm(rd, imm64, ctx); + return 1; + } + + /* LDX: dst = *(size *)(src + off) */ + case BPF_LDX | BPF_MEM | BPF_B: + rs = bpf_to_rv_reg(insn->src_reg, ctx); + rd = bpf_to_rv_reg(insn->dst_reg, ctx); + if (is_12b_int(off)) { + emit(rv_lbu(rd, off, rs), ctx); + break; + } + + emit_imm(RV_REG_T1, off, ctx); + emit(rv_add(RV_REG_T1, RV_REG_T1, rs), ctx); + emit(rv_lbu(rd, 0, RV_REG_T1), ctx); + break; + case BPF_LDX | BPF_MEM | BPF_H: + rs = bpf_to_rv_reg(insn->src_reg, ctx); + rd = bpf_to_rv_reg(insn->dst_reg, ctx); + if (is_12b_int(off)) { + emit(rv_lhu(rd, off, rs), ctx); + break; + } + + emit_imm(RV_REG_T1, off, ctx); + emit(rv_add(RV_REG_T1, RV_REG_T1, rs), ctx); + emit(rv_lhu(rd, 0, RV_REG_T1), ctx); + break; + case BPF_LDX | BPF_MEM | BPF_W: + rs = bpf_to_rv_reg(insn->src_reg, ctx); + rd = bpf_to_rv_reg(insn->dst_reg, ctx); + if (is_12b_int(off)) { + emit(rv_lwu(rd, off, rs), ctx); + break; + } + + emit_imm(RV_REG_T1, off, ctx); + emit(rv_add(RV_REG_T1, RV_REG_T1, rs), ctx); + emit(rv_lwu(rd, 0, RV_REG_T1), ctx); + break; + case BPF_LDX | BPF_MEM | BPF_DW: + rs = bpf_to_rv_reg(insn->src_reg, ctx); + rd = bpf_to_rv_reg(insn->dst_reg, ctx); + if (is_12b_int(off)) { + emit(rv_ld(rd, off, rs), ctx); + break; + } + + emit_imm(RV_REG_T1, off, ctx); + emit(rv_add(RV_REG_T1, RV_REG_T1, rs), ctx); + emit(rv_ld(rd, 0, RV_REG_T1), ctx); + break; + + /* ST: *(size *)(dst + off) = imm */ + case BPF_ST | BPF_MEM | BPF_B: + rd = bpf_to_rv_reg(insn->dst_reg, ctx); + emit_imm(RV_REG_T1, imm, ctx); + if (is_12b_int(off)) { + emit(rv_sb(rd, off, RV_REG_T1), ctx); + break; + } + + emit_imm(RV_REG_T2, off, ctx); + emit(rv_add(RV_REG_T2, RV_REG_T2, rd), ctx); + emit(rv_sb(RV_REG_T2, 0, RV_REG_T1), ctx); + break; + + case BPF_ST | BPF_MEM | BPF_H: + rd = bpf_to_rv_reg(insn->dst_reg, ctx); + emit_imm(RV_REG_T1, imm, ctx); + if (is_12b_int(off)) { + emit(rv_sh(rd, off, RV_REG_T1), ctx); + break; + } + + emit_imm(RV_REG_T2, off, ctx); + emit(rv_add(RV_REG_T2, RV_REG_T2, rd), ctx); + emit(rv_sh(RV_REG_T2, 0, RV_REG_T1), ctx); + break; + case BPF_ST | BPF_MEM | BPF_W: + rd = bpf_to_rv_reg(insn->dst_reg, ctx); + emit_imm(RV_REG_T1, imm, ctx); + if (is_12b_int(off)) { + emit(rv_sw(rd, off, RV_REG_T1), ctx); + break; + } + + emit_imm(RV_REG_T2, off, ctx); + emit(rv_add(RV_REG_T2, RV_REG_T2, rd), ctx); + emit(rv_sw(RV_REG_T2, 0, RV_REG_T1), ctx); + break; + case BPF_ST | BPF_MEM | BPF_DW: + rd = bpf_to_rv_reg(insn->dst_reg, ctx); + emit_imm(RV_REG_T1, imm, ctx); + if (is_12b_int(off)) { + emit(rv_sd(rd, off, RV_REG_T1), ctx); + break; + } + + emit_imm(RV_REG_T2, off, ctx); + emit(rv_add(RV_REG_T2, RV_REG_T2, rd), ctx); + emit(rv_sd(RV_REG_T2, 0, RV_REG_T1), ctx); + break; + + /* STX: *(size *)(dst + off) = src */ + case BPF_STX | BPF_MEM | BPF_B: + rs = bpf_to_rv_reg(insn->src_reg, ctx); + rd = bpf_to_rv_reg(insn->dst_reg, ctx); + if (is_12b_int(off)) { + emit(rv_sb(rd, off, rs), ctx); + break; + } + + emit_imm(RV_REG_T1, off, ctx); + emit(rv_add(RV_REG_T1, RV_REG_T1, rd), ctx); + emit(rv_sb(RV_REG_T1, 0, rs), ctx); + break; + case BPF_STX | BPF_MEM | BPF_H: + rs = bpf_to_rv_reg(insn->src_reg, ctx); + rd = bpf_to_rv_reg(insn->dst_reg, ctx); + if (is_12b_int(off)) { + emit(rv_sh(rd, off, rs), ctx); + break; + } + + emit_imm(RV_REG_T1, off, ctx); + emit(rv_add(RV_REG_T1, RV_REG_T1, rd), ctx); + emit(rv_sh(RV_REG_T1, 0, rs), ctx); + break; + case BPF_STX | BPF_MEM | BPF_W: + rs = bpf_to_rv_reg(insn->src_reg, ctx); + rd = bpf_to_rv_reg(insn->dst_reg, ctx); + if (is_12b_int(off)) { + emit(rv_sw(rd, off, rs), ctx); + break; + } + + emit_imm(RV_REG_T1, off, ctx); + emit(rv_add(RV_REG_T1, RV_REG_T1, rd), ctx); + emit(rv_sw(RV_REG_T1, 0, rs), ctx); + break; + case BPF_STX | BPF_MEM | BPF_DW: + rs = bpf_to_rv_reg(insn->src_reg, ctx); + rd = bpf_to_rv_reg(insn->dst_reg, ctx); + if (is_12b_int(off)) { + emit(rv_sd(rd, off, rs), ctx); + break; + } + + emit_imm(RV_REG_T1, off, ctx); + emit(rv_add(RV_REG_T1, RV_REG_T1, rd), ctx); + emit(rv_sd(RV_REG_T1, 0, rs), ctx); + break; + /* STX XADD: lock *(u32 *)(dst + off) += src */ + case BPF_STX | BPF_XADD | BPF_W: + /* STX XADD: lock *(u64 *)(dst + off) += src */ + case BPF_STX | BPF_XADD | BPF_DW: + rs = bpf_to_rv_reg(insn->src_reg, ctx); + rd = bpf_to_rv_reg(insn->dst_reg, ctx); + if (off) { + if (is_12b_int(off)) { + emit(rv_addi(RV_REG_T1, rd, off), ctx); + } else { + emit_imm(RV_REG_T1, off, ctx); + emit(rv_add(RV_REG_T1, RV_REG_T1, rd), ctx); + } + + rd = RV_REG_T1; + } + + emit(BPF_SIZE(code) == BPF_W ? + rv_amoadd_w(RV_REG_ZERO, rs, rd, 0, 0) : + rv_amoadd_d(RV_REG_ZERO, rs, rd, 0, 0), ctx); + break; + default: + pr_err("bpf-jit: unknown opcode %02x\n", code); + return -EINVAL; + } + + return 0; +} + +static void build_prologue(struct rv_jit_context *ctx) +{ + int stack_adjust = 0, store_offset, bpf_stack_adjust; + + if (seen_reg(RV_REG_RA, ctx)) + stack_adjust += 8; + stack_adjust += 8; /* RV_REG_FP */ + if (seen_reg(RV_REG_S1, ctx)) + stack_adjust += 8; + if (seen_reg(RV_REG_S2, ctx)) + stack_adjust += 8; + if (seen_reg(RV_REG_S3, ctx)) + stack_adjust += 8; + if (seen_reg(RV_REG_S4, ctx)) + stack_adjust += 8; + if (seen_reg(RV_REG_S5, ctx)) + stack_adjust += 8; + if (seen_reg(RV_REG_S6, ctx)) + stack_adjust += 8; + + stack_adjust = round_up(stack_adjust, 16); + bpf_stack_adjust = round_up(ctx->prog->aux->stack_depth, 16); + stack_adjust += bpf_stack_adjust; + + store_offset = stack_adjust - 8; + + emit(rv_addi(RV_REG_SP, RV_REG_SP, -stack_adjust), ctx); + + if (seen_reg(RV_REG_RA, ctx)) { + emit(rv_sd(RV_REG_SP, store_offset, RV_REG_RA), ctx); + store_offset -= 8; + } + emit(rv_sd(RV_REG_SP, store_offset, RV_REG_FP), ctx); + store_offset -= 8; + if (seen_reg(RV_REG_S1, ctx)) { + emit(rv_sd(RV_REG_SP, store_offset, RV_REG_S1), ctx); + store_offset -= 8; + } + if (seen_reg(RV_REG_S2, ctx)) { + emit(rv_sd(RV_REG_SP, store_offset, RV_REG_S2), ctx); + store_offset -= 8; + } + if (seen_reg(RV_REG_S3, ctx)) { + emit(rv_sd(RV_REG_SP, store_offset, RV_REG_S3), ctx); + store_offset -= 8; + } + if (seen_reg(RV_REG_S4, ctx)) { + emit(rv_sd(RV_REG_SP, store_offset, RV_REG_S4), ctx); + store_offset -= 8; + } + if (seen_reg(RV_REG_S5, ctx)) { + emit(rv_sd(RV_REG_SP, store_offset, RV_REG_S5), ctx); + store_offset -= 8; + } + if (seen_reg(RV_REG_S6, ctx)) { + emit(rv_sd(RV_REG_SP, store_offset, RV_REG_S6), ctx); + store_offset -= 8; + } + + emit(rv_addi(RV_REG_FP, RV_REG_SP, stack_adjust), ctx); + + if (bpf_stack_adjust) { + if (!seen_reg(RV_REG_S5, ctx)) + pr_warn("bpf-jit: not seen BPF_REG_FP, stack is %d\n", + bpf_stack_adjust); + emit(rv_addi(RV_REG_S5, RV_REG_SP, bpf_stack_adjust), ctx); + } + + ctx->stack_size = stack_adjust; +} + +static void build_epilogue(struct rv_jit_context *ctx) +{ + int stack_adjust = ctx->stack_size, store_offset = stack_adjust - 8; + + if (seen_reg(RV_REG_RA, ctx)) { + emit(rv_ld(RV_REG_RA, store_offset, RV_REG_SP), ctx); + store_offset -= 8; + } + emit(rv_ld(RV_REG_FP, store_offset, RV_REG_SP), ctx); + store_offset -= 8; + if (seen_reg(RV_REG_S1, ctx)) { + emit(rv_ld(RV_REG_S1, store_offset, RV_REG_SP), ctx); + store_offset -= 8; + } + if (seen_reg(RV_REG_S2, ctx)) { + emit(rv_ld(RV_REG_S2, store_offset, RV_REG_SP), ctx); + store_offset -= 8; + } + if (seen_reg(RV_REG_S3, ctx)) { + emit(rv_ld(RV_REG_S3, store_offset, RV_REG_SP), ctx); + store_offset -= 8; + } + if (seen_reg(RV_REG_S4, ctx)) { + emit(rv_ld(RV_REG_S4, store_offset, RV_REG_SP), ctx); + store_offset -= 8; + } + if (seen_reg(RV_REG_S5, ctx)) { + emit(rv_ld(RV_REG_S5, store_offset, RV_REG_SP), ctx); + store_offset -= 8; + } + if (seen_reg(RV_REG_S6, ctx)) { + emit(rv_ld(RV_REG_S6, store_offset, RV_REG_SP), ctx); + store_offset -= 8; + } + + emit(rv_addi(RV_REG_SP, RV_REG_SP, stack_adjust), ctx); + /* Set return value. */ + emit(rv_addi(RV_REG_A0, RV_REG_A5, 0), ctx); + emit(rv_jalr(RV_REG_ZERO, RV_REG_RA, 0), ctx); +} + +static int build_body(struct rv_jit_context *ctx, bool extra_pass) +{ + const struct bpf_prog *prog = ctx->prog; + int i; + + for (i = 0; i < prog->len; i++) { + const struct bpf_insn *insn = &prog->insnsi[i]; + int ret; + + ret = emit_insn(insn, ctx, extra_pass); + if (ret > 0) { + i++; + if (ctx->insns == NULL) + ctx->offset[i] = ctx->ninsns; + continue; + } + if (ctx->insns == NULL) + ctx->offset[i] = ctx->ninsns; + if (ret) + return ret; + } + return 0; +} + +static void bpf_fill_ill_insns(void *area, unsigned int size) +{ + memset(area, 0, size); +} + +static void bpf_flush_icache(void *start, void *end) +{ + flush_icache_range((unsigned long)start, (unsigned long)end); +} + struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) { + bool tmp_blinded = false, extra_pass = false; + struct bpf_prog *tmp, *orig_prog = prog; + struct rv_jit_data *jit_data; + struct rv_jit_context *ctx; + unsigned int image_size; + + if (!prog->jit_requested) + return orig_prog; + + tmp = bpf_jit_blind_constants(prog); + if (IS_ERR(tmp)) + return orig_prog; + if (tmp != prog) { + tmp_blinded = true; + prog = tmp; + } + + jit_data = prog->aux->jit_data; + if (!jit_data) { + jit_data = kzalloc(sizeof(*jit_data), GFP_KERNEL); + if (!jit_data) { + prog = orig_prog; + goto out; + } + prog->aux->jit_data = jit_data; + } + + ctx = &jit_data->ctx; + + if (ctx->offset) { + extra_pass = true; + image_size = sizeof(u32) * ctx->ninsns; + goto skip_init_ctx; + } + + ctx->prog = prog; + ctx->offset = kcalloc(prog->len, sizeof(int), GFP_KERNEL); + if (!ctx->offset) { + prog = orig_prog; + goto out_offset; + } + + /* First pass generates the ctx->offset, but does not emit an image. */ + if (build_body(ctx, extra_pass)) { + prog = orig_prog; + goto out_offset; + } + build_prologue(ctx); + ctx->epilogue_offset = ctx->ninsns; + build_epilogue(ctx); + + /* Allocate image, now that we know the size. */ + image_size = sizeof(u32) * ctx->ninsns; + jit_data->header = bpf_jit_binary_alloc(image_size, &jit_data->image, + sizeof(u32), + bpf_fill_ill_insns); + if (!jit_data->header) { + prog = orig_prog; + goto out_offset; + } + + /* Second, real pass, that acutally emits the image. */ + ctx->insns = (u32 *)jit_data->image; +skip_init_ctx: + ctx->ninsns = 0; + + build_prologue(ctx); + if (build_body(ctx, extra_pass)) { + bpf_jit_binary_free(jit_data->header); + prog = orig_prog; + goto out_offset; + } + build_epilogue(ctx); + + if (bpf_jit_enable > 1) + bpf_jit_dump(prog->len, image_size, 2, ctx->insns); + + prog->bpf_func = (void *)ctx->insns; + prog->jited = 1; + prog->jited_len = image_size; + + bpf_flush_icache(jit_data->header, (u8 *)ctx->insns + ctx->ninsns); + + if (!prog->is_func || extra_pass) { +out_offset: + kfree(ctx->offset); + kfree(jit_data); + prog->aux->jit_data = NULL; + } +out: + if (tmp_blinded) + bpf_jit_prog_release_other(prog, prog == orig_prog ? + tmp : orig_prog); return prog; }