Received: by 2002:a05:6a10:f347:0:0:0:0 with SMTP id d7csp5968823pxu; Wed, 23 Dec 2020 09:47:23 -0800 (PST) X-Google-Smtp-Source: ABdhPJxGMG5Yya0FEOCu0PAIuOtWBevshtH4R0aqc8C7vrbdX/HtYcSIQEg2GCj80WWFNhB8pjRA X-Received: by 2002:a17:906:924a:: with SMTP id c10mr24496738ejx.113.1608745642798; Wed, 23 Dec 2020 09:47:22 -0800 (PST) ARC-Seal: i=1; a=rsa-sha256; t=1608745642; cv=none; d=google.com; s=arc-20160816; b=ygNxXYu6L5i8CZP3QhHQ8EKIcBEfYOSPhH8BPXRc19Aj5o23TN8+34HMazhQksDAhm ATrULGsX8uNPpEMW4606oD00c9HnXexzw+iT8UzMbt5Y8G0taJ7jKKwvt8Hwhk37G3xy daGNN1iniHIma27xCE6IC1D2fPk2stzuMARyLEV1qtPeNSS7e1UmR1HlSiB6XeFxP7XS 7WkrkZlZ4IrTyZHp1NX7QNRHNOncKv7wd1GZsGJpm/lrCgpqgugdi9Se9xoSPSXrA5sA XaVttUZRgursxKE0bY0LMSw5mIbPvj6U0/YvAdR5F0IXNtxS/1wEIo3wzn1o9kE2KVT0 EFwQ== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=arc-20160816; h=list-id:precedence:content-transfer-encoding:mime-version :references:in-reply-to:message-id:date:subject:cc:to:from :dkim-signature; bh=lNnqBx8IedT513qvFyHDkcAQApmZvzPCwT9K8oR6vTY=; b=FSGeQ4PnkNtHkEVFchYJw69Wj7Qyym5y12prvKl91mONT7h7r/yaQ3cVowU2+LYzDq CAk3PWHIvZx4k+bTaNia1yuGL7brxXqr8qomM0sgsdqRaTJ4JqEK01ewIDfPwgQiqkEk DSSPbt1cIRwVXTBXjxYgC/0/IxlKyxOuYTWPZ82CYoHox8G8Ov7cXlsqKUxJKZrWlMZD FQh7qySNo31qmDhIYj91ZNTAiZ0lRsTwolp02cb49LFP9+VbGXfARwVaDTO4Nh0ElUIy hrkz2ncOTMKQi8yVXu1Yl8iEJ7xRoQmC0BqA83QZK2gBMmthArGzT4x+3RkU+cvl8Zo7 3C2Q== ARC-Authentication-Results: i=1; mx.google.com; dkim=pass header.i=@alien8.de header.s=dkim header.b=nBuT5Th3; spf=pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) smtp.mailfrom=linux-kernel-owner@vger.kernel.org; dmarc=pass (p=NONE sp=NONE dis=NONE) header.from=alien8.de Return-Path: Received: from vger.kernel.org (vger.kernel.org. [23.128.96.18]) by mx.google.com with ESMTP id m7si11450581eji.498.2020.12.23.09.46.59; Wed, 23 Dec 2020 09:47:22 -0800 (PST) Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18; Authentication-Results: mx.google.com; dkim=pass header.i=@alien8.de header.s=dkim header.b=nBuT5Th3; spf=pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) smtp.mailfrom=linux-kernel-owner@vger.kernel.org; dmarc=pass (p=NONE sp=NONE dis=NONE) header.from=alien8.de Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1728927AbgLWRoe (ORCPT + 99 others); Wed, 23 Dec 2020 12:44:34 -0500 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:36374 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1727591AbgLWRnY (ORCPT ); Wed, 23 Dec 2020 12:43:24 -0500 Received: from mail.skyhub.de (mail.skyhub.de [IPv6:2a01:4f8:190:11c2::b:1457]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 42651C06179C for ; Wed, 23 Dec 2020 09:42:44 -0800 (PST) Received: from zn.tnic (p200300ec2f0de600b74d534b1676c98b.dip0.t-ipconnect.de [IPv6:2003:ec:2f0d:e600:b74d:534b:1676:c98b]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by mail.skyhub.de (SuperMail on ZX Spectrum 128k) with ESMTPSA id 8D14D1EC04B9; Wed, 23 Dec 2020 18:42:42 +0100 (CET) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=alien8.de; s=dkim; t=1608745362; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version:content-type: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=lNnqBx8IedT513qvFyHDkcAQApmZvzPCwT9K8oR6vTY=; b=nBuT5Th3EfFOtctHmvwi2P4ChfazPYMvPpDso0wYntoNOwhG2ZRP3tfRMQ+MHRQ9ltVl4L wXfVh2evdOw0SgXIFOsh0wd9QYAuS08P7Ma2LHdo9qdEa8UcD7hMTnQzilpCFg3Z5zMHL4 2pa0PD1u0BlnP4Jv8eWwPXz6bzCOqo0= From: Borislav Petkov To: Andy Lutomirski , Masami Hiramatsu Cc: X86 ML , LKML Subject: [PATCH v1 03/19] x86/insn: Add an insn_decode() API Date: Wed, 23 Dec 2020 18:42:17 +0100 Message-Id: <20201223174233.28638-4-bp@alien8.de> X-Mailer: git-send-email 2.29.2 In-Reply-To: <20201223174233.28638-1-bp@alien8.de> References: <20201223174233.28638-1-bp@alien8.de> MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org From: Borislav Petkov Users of the instruction decoder should use this to decode instruction bytes. For that, have insn*() helpers return an int value to denote success/failure. When there's an error fetching the next insn byte and the insn falls short, return -ENODATA to denote that. While at it, make insn_get_opcode() more stricter as to whether what has seen so far is a valid insn and if not. Copy linux/kconfig.h for the tools-version of the decoder so that it can use IS_ENABLED(). Signed-off-by: Borislav Petkov --- arch/x86/include/asm/insn.h | 24 ++- arch/x86/lib/insn.c | 239 +++++++++++++++++++++++------- tools/arch/x86/include/asm/insn.h | 24 ++- tools/arch/x86/lib/insn.c | 239 +++++++++++++++++++++++------- tools/include/linux/kconfig.h | 73 +++++++++ 5 files changed, 475 insertions(+), 124 deletions(-) create mode 100644 tools/include/linux/kconfig.h diff --git a/arch/x86/include/asm/insn.h b/arch/x86/include/asm/insn.h index a8c3d284fa46..088aa90e9158 100644 --- a/arch/x86/include/asm/insn.h +++ b/arch/x86/include/asm/insn.h @@ -87,13 +87,23 @@ struct insn { #define X86_VEX_M_MAX 0x1f /* VEX3.M Maximum value */ extern void insn_init(struct insn *insn, const void *kaddr, int buf_len, int x86_64); -extern void insn_get_prefixes(struct insn *insn); -extern void insn_get_opcode(struct insn *insn); -extern void insn_get_modrm(struct insn *insn); -extern void insn_get_sib(struct insn *insn); -extern void insn_get_displacement(struct insn *insn); -extern void insn_get_immediate(struct insn *insn); -extern void insn_get_length(struct insn *insn); +extern int insn_get_prefixes(struct insn *insn); +extern int insn_get_opcode(struct insn *insn); +extern int insn_get_modrm(struct insn *insn); +extern int insn_get_sib(struct insn *insn); +extern int insn_get_displacement(struct insn *insn); +extern int insn_get_immediate(struct insn *insn); +extern int insn_get_length(struct insn *insn); + +enum insn_mode { + INSN_MODE_32, + INSN_MODE_64, + /* Mode is determined by the current kernel build. */ + INSN_MODE_KERN, + INSN_NUM_MODES, +}; + +extern int insn_decode(struct insn *insn, const void *kaddr, int buf_len, enum insn_mode m); /* Attribute will be determined after getting ModRM (for opcode groups) */ static inline void insn_get_attribute(struct insn *insn) diff --git a/arch/x86/lib/insn.c b/arch/x86/lib/insn.c index 1ba994862b56..b373aadcdd02 100644 --- a/arch/x86/lib/insn.c +++ b/arch/x86/lib/insn.c @@ -13,6 +13,9 @@ #include #include +#include +#include + #include /* Verify next sizeof(t) bytes can be on the same instruction */ @@ -80,12 +83,15 @@ static int __insn_get_emulate_prefix(struct insn *insn, return 1; err_out: - return 0; + return -ENODATA; } static void insn_get_emulate_prefix(struct insn *insn) { - if (__insn_get_emulate_prefix(insn, xen_prefix, sizeof(xen_prefix))) + int ret; + + ret = __insn_get_emulate_prefix(insn, xen_prefix, sizeof(xen_prefix)); + if (ret > 0) return; __insn_get_emulate_prefix(insn, kvm_prefix, sizeof(kvm_prefix)); @@ -98,8 +104,12 @@ static void insn_get_emulate_prefix(struct insn *insn) * Populates the @insn->prefixes bitmap, and updates @insn->next_byte * to point to the (first) opcode. No effect if @insn->prefixes.got * is already set. + * + * * Returns: + * 0: on success + * < 0: on error */ -void insn_get_prefixes(struct insn *insn) +int insn_get_prefixes(struct insn *insn) { struct insn_field *prefixes = &insn->prefixes; insn_attr_t attr; @@ -107,7 +117,7 @@ void insn_get_prefixes(struct insn *insn) int i, nb; if (prefixes->got) - return; + return 0; insn_get_emulate_prefix(insn); @@ -218,8 +228,10 @@ void insn_get_prefixes(struct insn *insn) prefixes->got = 1; + return 0; + err_out: - return; + return -ENODATA; } /** @@ -231,16 +243,25 @@ void insn_get_prefixes(struct insn *insn) * If necessary, first collects any preceding (prefix) bytes. * Sets @insn->opcode.value = opcode1. No effect if @insn->opcode.got * is already 1. + * + * Returns: + * 0: on success + * < 0: on error */ -void insn_get_opcode(struct insn *insn) +int insn_get_opcode(struct insn *insn) { struct insn_field *opcode = &insn->opcode; + int pfx_id, ret; insn_byte_t op; - int pfx_id; + if (opcode->got) - return; - if (!insn->prefixes.got) - insn_get_prefixes(insn); + return 0; + + if (!insn->prefixes.got) { + ret = insn_get_prefixes(insn); + if (ret) + return ret; + } /* Get first opcode */ op = get_next(insn_byte_t, insn); @@ -255,9 +276,13 @@ void insn_get_opcode(struct insn *insn) insn->attr = inat_get_avx_attribute(op, m, p); if ((inat_must_evex(insn->attr) && !insn_is_evex(insn)) || (!inat_accept_vex(insn->attr) && - !inat_is_group(insn->attr))) - insn->attr = 0; /* This instruction is bad */ - goto end; /* VEX has only 1 byte for opcode */ + !inat_is_group(insn->attr))) { + /* This instruction is bad */ + insn->attr = 0; + return 1; + } + /* VEX has only 1 byte for opcode */ + goto end; } insn->attr = inat_get_opcode_attribute(op); @@ -268,13 +293,18 @@ void insn_get_opcode(struct insn *insn) pfx_id = insn_last_prefix_id(insn); insn->attr = inat_get_escape_attribute(op, pfx_id, insn->attr); } - if (inat_must_vex(insn->attr)) - insn->attr = 0; /* This instruction is bad */ + + if (inat_must_vex(insn->attr)) { + /* This instruction is bad */ + insn->attr = 0; + return 1; + } end: opcode->got = 1; + return 0; err_out: - return; + return -ENODATA; } /** @@ -284,15 +314,25 @@ void insn_get_opcode(struct insn *insn) * Populates @insn->modrm and updates @insn->next_byte to point past the * ModRM byte, if any. If necessary, first collects the preceding bytes * (prefixes and opcode(s)). No effect if @insn->modrm.got is already 1. + * + * Returns: + * 0: on success + * < 0: on error */ -void insn_get_modrm(struct insn *insn) +int insn_get_modrm(struct insn *insn) { struct insn_field *modrm = &insn->modrm; insn_byte_t pfx_id, mod; + int ret; + if (modrm->got) - return; - if (!insn->opcode.got) - insn_get_opcode(insn); + return 0; + + if (!insn->opcode.got) { + ret = insn_get_opcode(insn); + if (ret) + return ret; + } if (inat_has_modrm(insn->attr)) { mod = get_next(insn_byte_t, insn); @@ -302,17 +342,22 @@ void insn_get_modrm(struct insn *insn) pfx_id = insn_last_prefix_id(insn); insn->attr = inat_get_group_attribute(mod, pfx_id, insn->attr); - if (insn_is_avx(insn) && !inat_accept_vex(insn->attr)) - insn->attr = 0; /* This is bad */ + if (insn_is_avx(insn) && !inat_accept_vex(insn->attr)) { + /* Bad insn */ + insn->attr = 0; + return 1; + } } } if (insn->x86_64 && inat_is_force64(insn->attr)) insn->opnd_bytes = 8; + modrm->got = 1; + return 0; err_out: - return; + return -ENODATA; } @@ -326,11 +371,16 @@ void insn_get_modrm(struct insn *insn) int insn_rip_relative(struct insn *insn) { struct insn_field *modrm = &insn->modrm; + int ret; if (!insn->x86_64) return 0; - if (!modrm->got) - insn_get_modrm(insn); + + if (!modrm->got) { + ret = insn_get_modrm(insn); + if (ret) + return ret; + } /* * For rip-relative instructions, the mod field (top 2 bits) * is zero and the r/m field (bottom 3 bits) is 0x5. @@ -344,15 +394,25 @@ int insn_rip_relative(struct insn *insn) * * If necessary, first collects the instruction up to and including the * ModRM byte. + * + * Returns: + * 0: if decoding succeeded + * < 0: otherwise. */ -void insn_get_sib(struct insn *insn) +int insn_get_sib(struct insn *insn) { insn_byte_t modrm; + int ret; if (insn->sib.got) - return; - if (!insn->modrm.got) - insn_get_modrm(insn); + return 0; + + if (!insn->modrm.got) { + ret = insn_get_modrm(insn); + if (ret) + return ret; + } + if (insn->modrm.nbytes) { modrm = (insn_byte_t)insn->modrm.value; if (insn->addr_bytes != 2 && @@ -363,8 +423,10 @@ void insn_get_sib(struct insn *insn) } insn->sib.got = 1; + return 0; + err_out: - return; + return -ENODATA; } @@ -375,15 +437,25 @@ void insn_get_sib(struct insn *insn) * If necessary, first collects the instruction up to and including the * SIB byte. * Displacement value is sign-expanded. + * + * * Returns: + * 0: if decoding succeeded + * < 0: otherwise. */ -void insn_get_displacement(struct insn *insn) +int insn_get_displacement(struct insn *insn) { insn_byte_t mod, rm, base; + int ret; if (insn->displacement.got) - return; - if (!insn->sib.got) - insn_get_sib(insn); + return 0; + + if (!insn->sib.got) { + ret = insn_get_sib(insn); + if (ret) + return ret; + } + if (insn->modrm.nbytes) { /* * Interpreting the modrm byte: @@ -426,12 +498,13 @@ void insn_get_displacement(struct insn *insn) } out: insn->displacement.got = 1; + return 0; err_out: - return; + return -ENODATA; } -/* Decode moffset16/32/64. Return 0 if failed */ +/* Decode moffset16/32/64. Return a negative value if failed. */ static int __get_moffset(struct insn *insn) { switch (insn->addr_bytes) { @@ -457,10 +530,10 @@ static int __get_moffset(struct insn *insn) return 1; err_out: - return 0; + return -ENODATA; } -/* Decode imm v32(Iz). Return 0 if failed */ +/* Decode imm v32(Iz). Return a negative value if failed. */ static int __get_immv32(struct insn *insn) { switch (insn->opnd_bytes) { @@ -480,10 +553,10 @@ static int __get_immv32(struct insn *insn) return 1; err_out: - return 0; + return -ENODATA; } -/* Decode imm v64(Iv/Ov), Return 0 if failed */ +/* Decode imm v64(Iv/Ov). Return a negative value if failed. */ static int __get_immv(struct insn *insn) { switch (insn->opnd_bytes) { @@ -507,11 +580,12 @@ static int __get_immv(struct insn *insn) insn->immediate1.got = insn->immediate2.got = 1; return 1; + err_out: - return 0; + return -ENODATA; } -/* Decode ptr16:16/32(Ap) */ +/* Decode ptr16:16/32(Ap). Return a negative value if failed. */ static int __get_immptr(struct insn *insn) { switch (insn->opnd_bytes) { @@ -534,25 +608,36 @@ static int __get_immptr(struct insn *insn) insn->immediate1.got = insn->immediate2.got = 1; return 1; + err_out: - return 0; + return -ENODATA; } /** - * insn_get_immediate() - Get the immediates of instruction + * insn_get_immediate() - Get the immediate in an instruction * @insn: &struct insn containing instruction * * If necessary, first collects the instruction up to and including the * displacement bytes. * Basically, most of immediates are sign-expanded. Unsigned-value can be - * get by bit masking with ((1 << (nbytes * 8)) - 1) + * computed by bit masking with ((1 << (nbytes * 8)) - 1) + * + * Returns: + * 0: on success + * < 0: on error */ -void insn_get_immediate(struct insn *insn) +int insn_get_immediate(struct insn *insn) { + int ret; + if (insn->immediate.got) - return; - if (!insn->displacement.got) - insn_get_displacement(insn); + return 0; + + if (!insn->displacement.got) { + ret = insn_get_displacement(insn); + if (ret) + return ret; + } if (inat_has_moffset(insn->attr)) { if (!__get_moffset(insn)) @@ -605,9 +690,10 @@ void insn_get_immediate(struct insn *insn) } done: insn->immediate.got = 1; + return 0; err_out: - return; + return -ENODATA; } /** @@ -616,13 +702,56 @@ void insn_get_immediate(struct insn *insn) * * If necessary, first collects the instruction up to and including the * immediates bytes. - */ -void insn_get_length(struct insn *insn) + * + * Returns: + * - 0 on success + * - < 0 on error +*/ +int insn_get_length(struct insn *insn) { + int ret; + if (insn->length) - return; - if (!insn->immediate.got) - insn_get_immediate(insn); + return 0; + + if (!insn->immediate.got) { + ret = insn_get_immediate(insn); + if (ret) + return ret; + } + insn->length = (unsigned char)((unsigned long)insn->next_byte - (unsigned long)insn->kaddr); + + return 0; +} + +/** + * insn_decode() - Decode an x86 instruction + * @insn: &struct insn to be initialized + * @kaddr: address (in kernel memory) of instruction (or copy thereof) + * @buf_len: length of the insn buffer at @kaddr + * @m: insn mode, see enum insn_mode + * + * Returns: + * 0: if decoding succeeded + * < 0: otherwise. + */ +int insn_decode(struct insn *insn, const void *kaddr, int buf_len, enum insn_mode m) +{ + int ret; + + if (m == INSN_MODE_KERN) + insn_init(insn, kaddr, buf_len, IS_ENABLED(CONFIG_X86_64)); + else + insn_init(insn, kaddr, buf_len, m == INSN_MODE_64); + + ret = insn_get_length(insn); + if (ret) + return ret; + + if (insn_complete(insn)) + return 0; + + return -EINVAL; } diff --git a/tools/arch/x86/include/asm/insn.h b/tools/arch/x86/include/asm/insn.h index 52c6262e6bfd..ed43bf01ebcc 100644 --- a/tools/arch/x86/include/asm/insn.h +++ b/tools/arch/x86/include/asm/insn.h @@ -87,13 +87,23 @@ struct insn { #define X86_VEX_M_MAX 0x1f /* VEX3.M Maximum value */ extern void insn_init(struct insn *insn, const void *kaddr, int buf_len, int x86_64); -extern void insn_get_prefixes(struct insn *insn); -extern void insn_get_opcode(struct insn *insn); -extern void insn_get_modrm(struct insn *insn); -extern void insn_get_sib(struct insn *insn); -extern void insn_get_displacement(struct insn *insn); -extern void insn_get_immediate(struct insn *insn); -extern void insn_get_length(struct insn *insn); +extern int insn_get_prefixes(struct insn *insn); +extern int insn_get_opcode(struct insn *insn); +extern int insn_get_modrm(struct insn *insn); +extern int insn_get_sib(struct insn *insn); +extern int insn_get_displacement(struct insn *insn); +extern int insn_get_immediate(struct insn *insn); +extern int insn_get_length(struct insn *insn); + +enum insn_mode { + INSN_MODE_32, + INSN_MODE_64, + /* Mode is determined by the current kernel build. */ + INSN_MODE_KERN, + INSN_NUM_MODES, +}; + +extern int insn_decode(struct insn *insn, const void *kaddr, int buf_len, enum insn_mode m); /* Attribute will be determined after getting ModRM (for opcode groups) */ static inline void insn_get_attribute(struct insn *insn) diff --git a/tools/arch/x86/lib/insn.c b/tools/arch/x86/lib/insn.c index f3277d6e4ef2..a2f9d9e177f2 100644 --- a/tools/arch/x86/lib/insn.c +++ b/tools/arch/x86/lib/insn.c @@ -13,6 +13,9 @@ #include "../include/asm/inat.h" #include "../include/asm/insn.h" +#include +#include + #include "../include/asm/emulate_prefix.h" /* Verify next sizeof(t) bytes can be on the same instruction */ @@ -80,12 +83,15 @@ static int __insn_get_emulate_prefix(struct insn *insn, return 1; err_out: - return 0; + return -ENODATA; } static void insn_get_emulate_prefix(struct insn *insn) { - if (__insn_get_emulate_prefix(insn, xen_prefix, sizeof(xen_prefix))) + int ret; + + ret = __insn_get_emulate_prefix(insn, xen_prefix, sizeof(xen_prefix)); + if (ret > 0) return; __insn_get_emulate_prefix(insn, kvm_prefix, sizeof(kvm_prefix)); @@ -98,8 +104,12 @@ static void insn_get_emulate_prefix(struct insn *insn) * Populates the @insn->prefixes bitmap, and updates @insn->next_byte * to point to the (first) opcode. No effect if @insn->prefixes.got * is already set. + * + * * Returns: + * 0: on success + * < 0: on error */ -void insn_get_prefixes(struct insn *insn) +int insn_get_prefixes(struct insn *insn) { struct insn_field *prefixes = &insn->prefixes; insn_attr_t attr; @@ -107,7 +117,7 @@ void insn_get_prefixes(struct insn *insn) int i, nb; if (prefixes->got) - return; + return 0; insn_get_emulate_prefix(insn); @@ -218,8 +228,10 @@ void insn_get_prefixes(struct insn *insn) prefixes->got = 1; + return 0; + err_out: - return; + return -ENODATA; } /** @@ -231,16 +243,25 @@ void insn_get_prefixes(struct insn *insn) * If necessary, first collects any preceding (prefix) bytes. * Sets @insn->opcode.value = opcode1. No effect if @insn->opcode.got * is already 1. + * + * Returns: + * 0: on success + * < 0: on error */ -void insn_get_opcode(struct insn *insn) +int insn_get_opcode(struct insn *insn) { struct insn_field *opcode = &insn->opcode; + int pfx_id, ret; insn_byte_t op; - int pfx_id; + if (opcode->got) - return; - if (!insn->prefixes.got) - insn_get_prefixes(insn); + return 0; + + if (!insn->prefixes.got) { + ret = insn_get_prefixes(insn); + if (ret) + return ret; + } /* Get first opcode */ op = get_next(insn_byte_t, insn); @@ -255,9 +276,13 @@ void insn_get_opcode(struct insn *insn) insn->attr = inat_get_avx_attribute(op, m, p); if ((inat_must_evex(insn->attr) && !insn_is_evex(insn)) || (!inat_accept_vex(insn->attr) && - !inat_is_group(insn->attr))) - insn->attr = 0; /* This instruction is bad */ - goto end; /* VEX has only 1 byte for opcode */ + !inat_is_group(insn->attr))) { + /* This instruction is bad */ + insn->attr = 0; + return 1; + } + /* VEX has only 1 byte for opcode */ + goto end; } insn->attr = inat_get_opcode_attribute(op); @@ -268,13 +293,18 @@ void insn_get_opcode(struct insn *insn) pfx_id = insn_last_prefix_id(insn); insn->attr = inat_get_escape_attribute(op, pfx_id, insn->attr); } - if (inat_must_vex(insn->attr)) - insn->attr = 0; /* This instruction is bad */ + + if (inat_must_vex(insn->attr)) { + /* This instruction is bad */ + insn->attr = 0; + return 1; + } end: opcode->got = 1; + return 0; err_out: - return; + return -ENODATA; } /** @@ -284,15 +314,25 @@ void insn_get_opcode(struct insn *insn) * Populates @insn->modrm and updates @insn->next_byte to point past the * ModRM byte, if any. If necessary, first collects the preceding bytes * (prefixes and opcode(s)). No effect if @insn->modrm.got is already 1. + * + * Returns: + * 0: on success + * < 0: on error */ -void insn_get_modrm(struct insn *insn) +int insn_get_modrm(struct insn *insn) { struct insn_field *modrm = &insn->modrm; insn_byte_t pfx_id, mod; + int ret; + if (modrm->got) - return; - if (!insn->opcode.got) - insn_get_opcode(insn); + return 0; + + if (!insn->opcode.got) { + ret = insn_get_opcode(insn); + if (ret) + return ret; + } if (inat_has_modrm(insn->attr)) { mod = get_next(insn_byte_t, insn); @@ -302,17 +342,22 @@ void insn_get_modrm(struct insn *insn) pfx_id = insn_last_prefix_id(insn); insn->attr = inat_get_group_attribute(mod, pfx_id, insn->attr); - if (insn_is_avx(insn) && !inat_accept_vex(insn->attr)) - insn->attr = 0; /* This is bad */ + if (insn_is_avx(insn) && !inat_accept_vex(insn->attr)) { + /* Bad insn */ + insn->attr = 0; + return 1; + } } } if (insn->x86_64 && inat_is_force64(insn->attr)) insn->opnd_bytes = 8; + modrm->got = 1; + return 0; err_out: - return; + return -ENODATA; } @@ -326,11 +371,16 @@ void insn_get_modrm(struct insn *insn) int insn_rip_relative(struct insn *insn) { struct insn_field *modrm = &insn->modrm; + int ret; if (!insn->x86_64) return 0; - if (!modrm->got) - insn_get_modrm(insn); + + if (!modrm->got) { + ret = insn_get_modrm(insn); + if (ret) + return ret; + } /* * For rip-relative instructions, the mod field (top 2 bits) * is zero and the r/m field (bottom 3 bits) is 0x5. @@ -344,15 +394,25 @@ int insn_rip_relative(struct insn *insn) * * If necessary, first collects the instruction up to and including the * ModRM byte. + * + * Returns: + * 0: if decoding succeeded + * < 0: otherwise. */ -void insn_get_sib(struct insn *insn) +int insn_get_sib(struct insn *insn) { insn_byte_t modrm; + int ret; if (insn->sib.got) - return; - if (!insn->modrm.got) - insn_get_modrm(insn); + return 0; + + if (!insn->modrm.got) { + ret = insn_get_modrm(insn); + if (ret) + return ret; + } + if (insn->modrm.nbytes) { modrm = (insn_byte_t)insn->modrm.value; if (insn->addr_bytes != 2 && @@ -363,8 +423,10 @@ void insn_get_sib(struct insn *insn) } insn->sib.got = 1; + return 0; + err_out: - return; + return -ENODATA; } @@ -375,15 +437,25 @@ void insn_get_sib(struct insn *insn) * If necessary, first collects the instruction up to and including the * SIB byte. * Displacement value is sign-expanded. + * + * * Returns: + * 0: if decoding succeeded + * < 0: otherwise. */ -void insn_get_displacement(struct insn *insn) +int insn_get_displacement(struct insn *insn) { insn_byte_t mod, rm, base; + int ret; if (insn->displacement.got) - return; - if (!insn->sib.got) - insn_get_sib(insn); + return 0; + + if (!insn->sib.got) { + ret = insn_get_sib(insn); + if (ret) + return ret; + } + if (insn->modrm.nbytes) { /* * Interpreting the modrm byte: @@ -426,12 +498,13 @@ void insn_get_displacement(struct insn *insn) } out: insn->displacement.got = 1; + return 0; err_out: - return; + return -ENODATA; } -/* Decode moffset16/32/64. Return 0 if failed */ +/* Decode moffset16/32/64. Return a negative value if failed. */ static int __get_moffset(struct insn *insn) { switch (insn->addr_bytes) { @@ -457,10 +530,10 @@ static int __get_moffset(struct insn *insn) return 1; err_out: - return 0; + return -ENODATA; } -/* Decode imm v32(Iz). Return 0 if failed */ +/* Decode imm v32(Iz). Return a negative value if failed. */ static int __get_immv32(struct insn *insn) { switch (insn->opnd_bytes) { @@ -480,10 +553,10 @@ static int __get_immv32(struct insn *insn) return 1; err_out: - return 0; + return -ENODATA; } -/* Decode imm v64(Iv/Ov), Return 0 if failed */ +/* Decode imm v64(Iv/Ov). Return a negative value if failed. */ static int __get_immv(struct insn *insn) { switch (insn->opnd_bytes) { @@ -507,11 +580,12 @@ static int __get_immv(struct insn *insn) insn->immediate1.got = insn->immediate2.got = 1; return 1; + err_out: - return 0; + return -ENODATA; } -/* Decode ptr16:16/32(Ap) */ +/* Decode ptr16:16/32(Ap). Return a negative value if failed. */ static int __get_immptr(struct insn *insn) { switch (insn->opnd_bytes) { @@ -534,25 +608,36 @@ static int __get_immptr(struct insn *insn) insn->immediate1.got = insn->immediate2.got = 1; return 1; + err_out: - return 0; + return -ENODATA; } /** - * insn_get_immediate() - Get the immediates of instruction + * insn_get_immediate() - Get the immediate in an instruction * @insn: &struct insn containing instruction * * If necessary, first collects the instruction up to and including the * displacement bytes. * Basically, most of immediates are sign-expanded. Unsigned-value can be - * get by bit masking with ((1 << (nbytes * 8)) - 1) + * computed by bit masking with ((1 << (nbytes * 8)) - 1) + * + * Returns: + * 0: on success + * < 0: on error */ -void insn_get_immediate(struct insn *insn) +int insn_get_immediate(struct insn *insn) { + int ret; + if (insn->immediate.got) - return; - if (!insn->displacement.got) - insn_get_displacement(insn); + return 0; + + if (!insn->displacement.got) { + ret = insn_get_displacement(insn); + if (ret) + return ret; + } if (inat_has_moffset(insn->attr)) { if (!__get_moffset(insn)) @@ -605,9 +690,10 @@ void insn_get_immediate(struct insn *insn) } done: insn->immediate.got = 1; + return 0; err_out: - return; + return -ENODATA; } /** @@ -616,13 +702,56 @@ void insn_get_immediate(struct insn *insn) * * If necessary, first collects the instruction up to and including the * immediates bytes. - */ -void insn_get_length(struct insn *insn) + * + * Returns: + * - 0 on success + * - < 0 on error +*/ +int insn_get_length(struct insn *insn) { + int ret; + if (insn->length) - return; - if (!insn->immediate.got) - insn_get_immediate(insn); + return 0; + + if (!insn->immediate.got) { + ret = insn_get_immediate(insn); + if (ret) + return ret; + } + insn->length = (unsigned char)((unsigned long)insn->next_byte - (unsigned long)insn->kaddr); + + return 0; +} + +/** + * insn_decode() - Decode an x86 instruction + * @insn: &struct insn to be initialized + * @kaddr: address (in kernel memory) of instruction (or copy thereof) + * @buf_len: length of the insn buffer at @kaddr + * @m: insn mode, see enum insn_mode + * + * Returns: + * 0: if decoding succeeded + * < 0: otherwise. + */ +int insn_decode(struct insn *insn, const void *kaddr, int buf_len, enum insn_mode m) +{ + int ret; + + if (m == INSN_MODE_KERN) + insn_init(insn, kaddr, buf_len, IS_ENABLED(CONFIG_X86_64)); + else + insn_init(insn, kaddr, buf_len, m == INSN_MODE_64); + + ret = insn_get_length(insn); + if (ret) + return ret; + + if (insn_complete(insn)) + return 0; + + return -EINVAL; } diff --git a/tools/include/linux/kconfig.h b/tools/include/linux/kconfig.h new file mode 100644 index 000000000000..1555a0c4f345 --- /dev/null +++ b/tools/include/linux/kconfig.h @@ -0,0 +1,73 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _TOOLS_LINUX_KCONFIG_H +#define _TOOLS_LINUX_KCONFIG_H + +/* CONFIG_CC_VERSION_TEXT (Do not delete this comment. See help in Kconfig) */ + +#ifdef CONFIG_CPU_BIG_ENDIAN +#define __BIG_ENDIAN 4321 +#else +#define __LITTLE_ENDIAN 1234 +#endif + +#define __ARG_PLACEHOLDER_1 0, +#define __take_second_arg(__ignored, val, ...) val + +/* + * The use of "&&" / "||" is limited in certain expressions. + * The following enable to calculate "and" / "or" with macro expansion only. + */ +#define __and(x, y) ___and(x, y) +#define ___and(x, y) ____and(__ARG_PLACEHOLDER_##x, y) +#define ____and(arg1_or_junk, y) __take_second_arg(arg1_or_junk y, 0) + +#define __or(x, y) ___or(x, y) +#define ___or(x, y) ____or(__ARG_PLACEHOLDER_##x, y) +#define ____or(arg1_or_junk, y) __take_second_arg(arg1_or_junk 1, y) + +/* + * Helper macros to use CONFIG_ options in C/CPP expressions. Note that + * these only work with boolean and tristate options. + */ + +/* + * Getting something that works in C and CPP for an arg that may or may + * not be defined is tricky. Here, if we have "#define CONFIG_BOOGER 1" + * we match on the placeholder define, insert the "0," for arg1 and generate + * the triplet (0, 1, 0). Then the last step cherry picks the 2nd arg (a one). + * When CONFIG_BOOGER is not defined, we generate a (... 1, 0) pair, and when + * the last step cherry picks the 2nd arg, we get a zero. + */ +#define __is_defined(x) ___is_defined(x) +#define ___is_defined(val) ____is_defined(__ARG_PLACEHOLDER_##val) +#define ____is_defined(arg1_or_junk) __take_second_arg(arg1_or_junk 1, 0) + +/* + * IS_BUILTIN(CONFIG_FOO) evaluates to 1 if CONFIG_FOO is set to 'y', 0 + * otherwise. For boolean options, this is equivalent to + * IS_ENABLED(CONFIG_FOO). + */ +#define IS_BUILTIN(option) __is_defined(option) + +/* + * IS_MODULE(CONFIG_FOO) evaluates to 1 if CONFIG_FOO is set to 'm', 0 + * otherwise. + */ +#define IS_MODULE(option) __is_defined(option##_MODULE) + +/* + * IS_REACHABLE(CONFIG_FOO) evaluates to 1 if the currently compiled + * code can call a function defined in code compiled based on CONFIG_FOO. + * This is similar to IS_ENABLED(), but returns false when invoked from + * built-in code when CONFIG_FOO is set to 'm'. + */ +#define IS_REACHABLE(option) __or(IS_BUILTIN(option), \ + __and(IS_MODULE(option), __is_defined(MODULE))) + +/* + * IS_ENABLED(CONFIG_FOO) evaluates to 1 if CONFIG_FOO is set to 'y' or 'm', + * 0 otherwise. + */ +#define IS_ENABLED(option) __or(IS_BUILTIN(option), IS_MODULE(option)) + +#endif /* _TOOLS_LINUX_KCONFIG_H */ -- 2.29.2