From patchwork Sat Jun 4 22:00:28 2016 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Zi Shen Lim X-Patchwork-Id: 9155005 Return-Path: Received: from mail.wl.linuxfoundation.org (pdx-wl-mail.web.codeaurora.org [172.30.200.125]) by pdx-korg-patchwork.web.codeaurora.org (Postfix) with ESMTP id 80C4A60221 for ; Sat, 4 Jun 2016 22:03:19 +0000 (UTC) Received: from mail.wl.linuxfoundation.org (localhost [127.0.0.1]) by mail.wl.linuxfoundation.org (Postfix) with ESMTP id 71EEB281FE for ; Sat, 4 Jun 2016 22:03:19 +0000 (UTC) Received: by mail.wl.linuxfoundation.org (Postfix, from userid 486) id 66C5028327; Sat, 4 Jun 2016 22:03:19 +0000 (UTC) X-Spam-Checker-Version: SpamAssassin 3.3.1 (2010-03-16) on pdx-wl-mail.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-4.1 required=2.0 tests=BAYES_00, DKIM_ADSP_CUSTOM_MED, DKIM_SIGNED,FREEMAIL_FROM,RCVD_IN_DNSWL_MED,T_DKIM_INVALID autolearn=unavailable version=3.3.1 Received: from bombadil.infradead.org (bombadil.infradead.org [198.137.202.9]) (using TLSv1.2 with cipher AES128-GCM-SHA256 (128/128 bits)) (No client certificate requested) by mail.wl.linuxfoundation.org (Postfix) with ESMTPS id DDBE5281FE for ; Sat, 4 Jun 2016 22:03:18 +0000 (UTC) Received: from localhost ([127.0.0.1] helo=bombadil.infradead.org) by bombadil.infradead.org with esmtp (Exim 4.80.1 #2 (Red Hat Linux)) id 1b9JdS-0000RL-6W; Sat, 04 Jun 2016 22:01:38 +0000 Received: from mail-pa0-x241.google.com ([2607:f8b0:400e:c03::241]) by bombadil.infradead.org with esmtps (Exim 4.80.1 #2 (Red Hat Linux)) id 1b9JdO-0000PW-M3 for linux-arm-kernel@lists.infradead.org; Sat, 04 Jun 2016 22:01:35 +0000 Received: by mail-pa0-x241.google.com with SMTP id fg1so8671747pad.3 for ; Sat, 04 Jun 2016 15:01:13 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20120113; h=from:to:cc:subject:date:message-id; bh=0GzrfmthXyHU6vsP+oeDPqccjRwx8QqxQd/VQdBfFYM=; b=iNveUo3QBbA8tgV9wU54YGta5ksO1rtkm9X/2XgcpYswmfXIgZeYbd1Cqe0Dr9wSPX oldKaVJTwnWnPKK5Ef1+3KGWPlZB+HA23WsD9OMd4+WPTrIFvZiFZqy7177xsnAzy2wE bfDaIhfNSDyzQHeFiTH9JqonHZ2Vcpy65ZIVzMn8hox1GNd5+bD2ghdqRE9sgREuWk7d 6sn9C0TmsmaWYgQciGo4eEkcLTEN+OMqvKicYrAXcZ0eonNNUXCVxZvjjzIpi2WPEtlj dkEYO7qSTJeSlHrPb1M5EtHqEXWzUn3sc5WyQN187AvMY9rrwaPX5z3IWMvxLfNUdf3A ru4w== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20130820; h=x-gm-message-state:from:to:cc:subject:date:message-id; bh=0GzrfmthXyHU6vsP+oeDPqccjRwx8QqxQd/VQdBfFYM=; b=ZasfVC+T5HF/Mi5ReEIH/9JUhDlraNzcLdr0i9S8VB2ncmNSIEdmELdtsjCjejw1pc B+5/eJFieO6tcyO0dC/3N1kj1i1sAlPDY+ZX2QMqT7QUDWnhmMakqBY2MaNEcXJVhQEa xQmaOvmykvCVs+QcokA3u2gb1Dg3GgSCR1U1OaNzlYHRywjdNskc5jn/zNsiO2Sjl0bM 8H4xoaKeJ7jo4DIY6oafjky6A6+pnzRIvQFkoz1u2rcWQjcq2n4zCo8ycFXE5agCgZ59 01uxUCdId9eI4TXSPxv/iApL6gXfepZQcrVuGhRCvzJTfKYD3ACY+Y3nCPVKf8TZ5LQ+ T0Hw== X-Gm-Message-State: ALyK8tL73NhLhtrH/O1i3q9+SwYCiHEc08CISrvatVScH0zfeZ1QtbXrDv6bfhjP9RlqsQ== X-Received: by 10.66.132.37 with SMTP id or5mr14133489pab.144.1465077673098; Sat, 04 Jun 2016 15:01:13 -0700 (PDT) Received: from localhost.localdomain (c-73-223-118-172.hsd1.ca.comcast.net. [73.223.118.172]) by smtp.gmail.com with ESMTPSA id y186sm17385539pfb.13.2016.06.04.15.01.11 (version=TLS1_2 cipher=ECDHE-RSA-AES128-SHA bits=128/128); Sat, 04 Jun 2016 15:01:12 -0700 (PDT) From: Zi Shen Lim To: "David S. Miller" , Catalin Marinas , Will Deacon Subject: [PATCH net-next 1/3] arm64: bpf: implement bpf_tail_call() helper Date: Sat, 4 Jun 2016 15:00:28 -0700 Message-Id: <1465077630-633-1-git-send-email-zlim.lnx@gmail.com> X-Mailer: git-send-email 1.9.1 X-CRM114-Version: 20100106-BlameMichelson ( TRE 0.8.0 (BSD) ) MR-646709E3 X-CRM114-CacheID: sfid-20160604_150134_791539_0A93BB2C X-CRM114-Status: GOOD ( 20.69 ) X-BeenThere: linux-arm-kernel@lists.infradead.org X-Mailman-Version: 2.1.20 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Cc: Yang Shi , Daniel Borkmann , Zi Shen Lim , Alexei Starovoitov , linux-kernel@vger.kernel.org, netdev@vger.kernel.org, linux-arm-kernel@lists.infradead.org MIME-Version: 1.0 Sender: "linux-arm-kernel" Errors-To: linux-arm-kernel-bounces+patchwork-linux-arm=patchwork.kernel.org@lists.infradead.org X-Virus-Scanned: ClamAV using ClamSMTP Add support for JMP_CALL_X (tail call) introduced by commit 04fd61ab36ec ("bpf: allow bpf programs to tail-call other bpf programs"). bpf_tail_call() arguments: ctx - context pointer passed to next program array - pointer to map which type is BPF_MAP_TYPE_PROG_ARRAY index - index inside array that selects specific program to run In this implementation arm64 JIT jumps into callee program after prologue, so callee program reuses the same stack. For tail_call_cnt, we use the callee-saved R26 (which was already saved/restored but previously unused by JIT). With this patch a tail call generates the following code on arm64: if (index >= array->map.max_entries) goto out; 34: mov x10, #0x10 // #16 38: ldr w10, [x1,x10] 3c: cmp w2, w10 40: b.ge 0x0000000000000074 if (tail_call_cnt > MAX_TAIL_CALL_CNT) goto out; tail_call_cnt++; 44: mov x10, #0x20 // #32 48: cmp x26, x10 4c: b.gt 0x0000000000000074 50: add x26, x26, #0x1 prog = array->ptrs[index]; if (prog == NULL) goto out; 54: mov x10, #0x68 // #104 58: ldr x10, [x1,x10] 5c: ldr x11, [x10,x2] 60: cbz x11, 0x0000000000000074 goto *(prog->bpf_func + prologue_size); 64: mov x10, #0x20 // #32 68: ldr x10, [x11,x10] 6c: add x10, x10, #0x20 70: br x10 74: Signed-off-by: Zi Shen Lim --- arch/arm64/net/bpf_jit.h | 3 +- arch/arm64/net/bpf_jit_comp.c | 105 ++++++++++++++++++++++++++++++++++++++---- 2 files changed, 98 insertions(+), 10 deletions(-) diff --git a/arch/arm64/net/bpf_jit.h b/arch/arm64/net/bpf_jit.h index aee5637..7c16e54 100644 --- a/arch/arm64/net/bpf_jit.h +++ b/arch/arm64/net/bpf_jit.h @@ -1,7 +1,7 @@ /* * BPF JIT compiler for ARM64 * - * Copyright (C) 2014-2015 Zi Shen Lim + * Copyright (C) 2014-2016 Zi Shen Lim * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -55,6 +55,7 @@ #define A64_BL(imm26) A64_BRANCH((imm26) << 2, LINK) /* Unconditional branch (register) */ +#define A64_BR(Rn) aarch64_insn_gen_branch_reg(Rn, AARCH64_INSN_BRANCH_NOLINK) #define A64_BLR(Rn) aarch64_insn_gen_branch_reg(Rn, AARCH64_INSN_BRANCH_LINK) #define A64_RET(Rn) aarch64_insn_gen_branch_reg(Rn, AARCH64_INSN_BRANCH_RETURN) diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c index 49ba37e..51abc97 100644 --- a/arch/arm64/net/bpf_jit_comp.c +++ b/arch/arm64/net/bpf_jit_comp.c @@ -18,6 +18,7 @@ #define pr_fmt(fmt) "bpf_jit: " fmt +#include #include #include #include @@ -33,6 +34,7 @@ int bpf_jit_enable __read_mostly; #define TMP_REG_1 (MAX_BPF_JIT_REG + 0) #define TMP_REG_2 (MAX_BPF_JIT_REG + 1) +#define TCALL_CNT (MAX_BPF_JIT_REG + 2) /* Map BPF registers to A64 registers */ static const int bpf2a64[] = { @@ -54,6 +56,8 @@ static const int bpf2a64[] = { /* temporary registers for internal BPF JIT */ [TMP_REG_1] = A64_R(10), [TMP_REG_2] = A64_R(11), + /* tail_call_cnt */ + [TCALL_CNT] = A64_R(26), /* temporary register for blinding constants */ [BPF_REG_AX] = A64_R(9), }; @@ -146,13 +150,18 @@ static inline int epilogue_offset(const struct jit_ctx *ctx) #define STACK_SIZE STACK_ALIGN(_STACK_SIZE) -static void build_prologue(struct jit_ctx *ctx) +#define PROLOGUE_OFFSET 8 + +static int build_prologue(struct jit_ctx *ctx) { const u8 r6 = bpf2a64[BPF_REG_6]; const u8 r7 = bpf2a64[BPF_REG_7]; const u8 r8 = bpf2a64[BPF_REG_8]; const u8 r9 = bpf2a64[BPF_REG_9]; const u8 fp = bpf2a64[BPF_REG_FP]; + const u8 tcc = bpf2a64[TCALL_CNT]; + const int idx0 = ctx->idx; + int cur_offset; /* * BPF prog stack layout @@ -162,8 +171,6 @@ static void build_prologue(struct jit_ctx *ctx) * |FP/LR| * current A64_FP => -16:+-----+ * | ... | callee saved registers - * +-----+ - * | | x25/x26 * BPF fp register => -64:+-----+ <= (BPF_FP) * | | * | ... | BPF prog stack @@ -183,18 +190,90 @@ static void build_prologue(struct jit_ctx *ctx) emit(A64_PUSH(A64_FP, A64_LR, A64_SP), ctx); emit(A64_MOV(1, A64_FP, A64_SP), ctx); - /* Save callee-saved register */ + /* Save callee-saved registers */ emit(A64_PUSH(r6, r7, A64_SP), ctx); emit(A64_PUSH(r8, r9, A64_SP), ctx); + emit(A64_PUSH(fp, tcc, A64_SP), ctx); - /* Save fp (x25) and x26. SP requires 16 bytes alignment */ - emit(A64_PUSH(fp, A64_R(26), A64_SP), ctx); - - /* Set up BPF prog stack base register (x25) */ + /* Set up BPF prog stack base register */ emit(A64_MOV(1, fp, A64_SP), ctx); + /* Initialize tail_call_cnt */ + emit(A64_MOVZ(1, tcc, 0, 0), ctx); + /* Set up function call stack */ emit(A64_SUB_I(1, A64_SP, A64_SP, STACK_SIZE), ctx); + + cur_offset = ctx->idx - idx0; + if (cur_offset != PROLOGUE_OFFSET) { + pr_err_once("PROLOGUE_OFFSET = %d, expected %d!\n", + cur_offset, PROLOGUE_OFFSET); + return -1; + } + return 0; +} + +static int out_offset = -1; /* initialized on the first pass of build_body() */ +static int emit_bpf_tail_call(struct jit_ctx *ctx) +{ + /* bpf_tail_call(void *prog_ctx, struct bpf_array *array, u64 index) */ + const u8 r2 = bpf2a64[BPF_REG_2]; + const u8 r3 = bpf2a64[BPF_REG_3]; + + const u8 tmp = bpf2a64[TMP_REG_1]; + const u8 prg = bpf2a64[TMP_REG_2]; + const u8 tcc = bpf2a64[TCALL_CNT]; + const int idx0 = ctx->idx; +#define cur_offset (ctx->idx - idx0) +#define jmp_offset (out_offset - (cur_offset)) + size_t off; + + /* if (index >= array->map.max_entries) + * goto out; + */ + off = offsetof(struct bpf_array, map.max_entries); + emit_a64_mov_i64(tmp, off, ctx); + emit(A64_LDR32(tmp, r2, tmp), ctx); + emit(A64_CMP(0, r3, tmp), ctx); + emit(A64_B_(A64_COND_GE, jmp_offset), ctx); + + /* if (tail_call_cnt > MAX_TAIL_CALL_CNT) + * goto out; + * tail_call_cnt++; + */ + emit_a64_mov_i64(tmp, MAX_TAIL_CALL_CNT, ctx); + emit(A64_CMP(1, tcc, tmp), ctx); + emit(A64_B_(A64_COND_GT, jmp_offset), ctx); + emit(A64_ADD_I(1, tcc, tcc, 1), ctx); + + /* prog = array->ptrs[index]; + * if (prog == NULL) + * goto out; + */ + off = offsetof(struct bpf_array, ptrs); + emit_a64_mov_i64(tmp, off, ctx); + emit(A64_LDR64(tmp, r2, tmp), ctx); + emit(A64_LDR64(prg, tmp, r3), ctx); + emit(A64_CBZ(1, prg, jmp_offset), ctx); + + /* goto *(prog->bpf_func + prologue_size); */ + off = offsetof(struct bpf_prog, bpf_func); + emit_a64_mov_i64(tmp, off, ctx); + emit(A64_LDR64(tmp, prg, tmp), ctx); + emit(A64_ADD_I(1, tmp, tmp, sizeof(u32) * PROLOGUE_OFFSET), ctx); + emit(A64_BR(tmp), ctx); + + /* out: */ + if (out_offset == -1) + out_offset = cur_offset; + if (cur_offset != out_offset) { + pr_err_once("tail_call out_offset = %d, expected %d!\n", + cur_offset, out_offset); + return -1; + } + return 0; +#undef cur_offset +#undef jmp_offset } static void build_epilogue(struct jit_ctx *ctx) @@ -506,6 +585,11 @@ emit_cond_jmp: emit(A64_POP(A64_FP, A64_LR, A64_SP), ctx); break; } + /* tail call */ + case BPF_JMP | BPF_CALL | BPF_X: + if (emit_bpf_tail_call(ctx)) + return -EFAULT; + break; /* function return */ case BPF_JMP | BPF_EXIT: /* Optimization: when last instruction is EXIT, @@ -780,7 +864,10 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) goto out_off; } - build_prologue(&ctx); + if (build_prologue(&ctx)) { + prog = orig_prog; + goto out_off; + } ctx.epilogue_offset = ctx.idx; build_epilogue(&ctx);