[{"id":1767972,"web_url":"http://patchwork.ozlabs.org/comment/1767972/","msgid":"<87mv5ya9qb.fsf@linaro.org>","list_archive_url":null,"date":"2017-09-13T15:39:40","subject":"Re: [PATCH v2 07/28] arm64/sve: Low-level SVE architectural state\n\tmanipulation functions","submitter":{"id":39532,"url":"http://patchwork.ozlabs.org/api/people/39532/","name":"Alex Bennée","email":"alex.bennee@linaro.org"},"content":"Dave Martin <Dave.Martin@arm.com> writes:\n\n> Manipulating the SVE architectural state, including the vector and\n> predicate registers, first-fault register and the vector length,\n> requires the use of dedicated instructions added by SVE.\n>\n> This patch adds suitable assembly functions for saving and\n> restoring the SVE registers and querying the vector length.\n> Setting of the vector length is done as part of register restore.\n>\n> Since people building kernels may not all get an SVE-enabled\n> toolchain for a while, this patch uses macros that generate\n> explicit opcodes in place of assembler mnemonics.\n>\n> Signed-off-by: Dave Martin <Dave.Martin@arm.com>\n> Cc: Alex Bennée <alex.bennee@linaro.org>\n\nIt took me a while to find a way to properly dissemble the resulting\nbinaries, in the end needing to run a native objdump in Stretch. I'd\nhopped my gdb-multiarch was bleeding edge enough but no ;-)\n\nReviewed-by: Alex Bennée <alex.bennee@linaro.org>\n\n>\n> ---\n>\n> Changes since v1\n> ----------------\n>\n> Requested by Alex Bennée:\n>\n> * Annotate instruction generation macros with the canonical\n> architectural syntax so that people can cross-reference more easily\n> against the architectural documentation.\n> ---\n>  arch/arm64/include/asm/fpsimd.h       |   5 ++\n>  arch/arm64/include/asm/fpsimdmacros.h | 148 ++++++++++++++++++++++++++++++++++\n>  arch/arm64/kernel/entry-fpsimd.S      |  17 ++++\n>  3 files changed, 170 insertions(+)\n>\n> diff --git a/arch/arm64/include/asm/fpsimd.h b/arch/arm64/include/asm/fpsimd.h\n> index 410c481..026a7c7 100644\n> --- a/arch/arm64/include/asm/fpsimd.h\n> +++ b/arch/arm64/include/asm/fpsimd.h\n> @@ -67,6 +67,11 @@ extern void fpsimd_update_current_state(struct fpsimd_state *state);\n>\n>  extern void fpsimd_flush_task_state(struct task_struct *target);\n>\n> +extern void sve_save_state(void *state, u32 *pfpsr);\n> +extern void sve_load_state(void const *state, u32 const *pfpsr,\n> +\t\t\t   unsigned long vq_minus_1);\n> +extern unsigned int sve_get_vl(void);\n> +\n>  /* For use by EFI runtime services calls only */\n>  extern void __efi_fpsimd_begin(void);\n>  extern void __efi_fpsimd_end(void);\n> diff --git a/arch/arm64/include/asm/fpsimdmacros.h b/arch/arm64/include/asm/fpsimdmacros.h\n> index 0f5fdd3..e050d76 100644\n> --- a/arch/arm64/include/asm/fpsimdmacros.h\n> +++ b/arch/arm64/include/asm/fpsimdmacros.h\n> @@ -75,3 +75,151 @@\n>  \tldr\tw\\tmpnr, [\\state, #16 * 2 + 4]\n>  \tfpsimd_restore_fpcr x\\tmpnr, \\state\n>  .endm\n> +\n> +/* Sanity-check macros to help avoid encoding garbage instructions */\n> +\n> +.macro _check_general_reg nr\n> +\t.if (\\nr) < 0 || (\\nr) > 30\n> +\t\t.error \"Bad register number \\nr.\"\n> +\t.endif\n> +.endm\n> +\n> +.macro _sve_check_zreg znr\n> +\t.if (\\znr) < 0 || (\\znr) > 31\n> +\t\t.error \"Bad Scalable Vector Extension vector register number \\znr.\"\n> +\t.endif\n> +.endm\n> +\n> +.macro _sve_check_preg pnr\n> +\t.if (\\pnr) < 0 || (\\pnr) > 15\n> +\t\t.error \"Bad Scalable Vector Extension predicate register number \\pnr.\"\n> +\t.endif\n> +.endm\n> +\n> +.macro _check_num n, min, max\n> +\t.if (\\n) < (\\min) || (\\n) > (\\max)\n> +\t\t.error \"Number \\n out of range [\\min,\\max]\"\n> +\t.endif\n> +.endm\n> +\n> +/* SVE instruction encodings for non-SVE-capable assemblers */\n> +\n> +/* STR (vector): STR Z\\nz, [X\\nxbase, #\\offset, MUL VL] */\n> +.macro _sve_str_v nz, nxbase, offset=0\n> +\t_sve_check_zreg \\nz\n> +\t_check_general_reg \\nxbase\n> +\t_check_num (\\offset), -0x100, 0xff\n> +\t.inst\t0xe5804000\t\t\t\\\n> +\t\t| (\\nz)\t\t\t\t\\\n> +\t\t| ((\\nxbase) << 5)\t\t\\\n> +\t\t| (((\\offset) & 7) << 10)\t\\\n> +\t\t| (((\\offset) & 0x1f8) << 13)\n> +.endm\n> +\n> +/* LDR (vector): LDR Z\\nz, [X\\nxbase, #\\offset, MUL VL] */\n> +.macro _sve_ldr_v nz, nxbase, offset=0\n> +\t_sve_check_zreg \\nz\n> +\t_check_general_reg \\nxbase\n> +\t_check_num (\\offset), -0x100, 0xff\n> +\t.inst\t0x85804000\t\t\t\\\n> +\t\t| (\\nz)\t\t\t\t\\\n> +\t\t| ((\\nxbase) << 5)\t\t\\\n> +\t\t| (((\\offset) & 7) << 10)\t\\\n> +\t\t| (((\\offset) & 0x1f8) << 13)\n> +.endm\n> +\n> +/* STR (predicate): STR P\\np, [X\\nxbase, #\\offset, MUL VL] */\n> +.macro _sve_str_p np, nxbase, offset=0\n> +\t_sve_check_preg \\np\n> +\t_check_general_reg \\nxbase\n> +\t_check_num (\\offset), -0x100, 0xff\n> +\t.inst\t0xe5800000\t\t\t\\\n> +\t\t| (\\np)\t\t\t\t\\\n> +\t\t| ((\\nxbase) << 5)\t\t\\\n> +\t\t| (((\\offset) & 7) << 10)\t\\\n> +\t\t| (((\\offset) & 0x1f8) << 13)\n> +.endm\n> +\n> +/* LDR (predicate): LDR P\\np, [X\\nxbase, #\\offset, MUL VL] */\n> +.macro _sve_ldr_p np, nxbase, offset=0\n> +\t_sve_check_preg \\np\n> +\t_check_general_reg \\nxbase\n> +\t_check_num (\\offset), -0x100, 0xff\n> +\t.inst\t0x85800000\t\t\t\\\n> +\t\t| (\\np)\t\t\t\t\\\n> +\t\t| ((\\nxbase) << 5)\t\t\\\n> +\t\t| (((\\offset) & 7) << 10)\t\\\n> +\t\t| (((\\offset) & 0x1f8) << 13)\n> +.endm\n> +\n> +/* RDVL X\\nx, #\\imm */\n> +.macro _sve_rdvl nx, imm\n> +\t_check_general_reg \\nx\n> +\t_check_num (\\imm), -0x20, 0x1f\n> +\t.inst\t0x04bf5000\t\t\t\\\n> +\t\t| (\\nx)\t\t\t\t\\\n> +\t\t| (((\\imm) & 0x3f) << 5)\n> +.endm\n> +\n> +/* RDFFR (unpredicated): RDFFR P\\np.B */\n> +.macro _sve_rdffr np\n> +\t_sve_check_preg \\np\n> +\t.inst\t0x2519f000\t\t\t\\\n> +\t\t| (\\np)\n> +.endm\n> +\n> +/* WRFFR P\\np.B */\n> +.macro _sve_wrffr np\n> +\t_sve_check_preg \\np\n> +\t.inst\t0x25289000\t\t\t\\\n> +\t\t| ((\\np) << 5)\n> +.endm\n> +\n> +.macro __for from:req, to:req\n> +\t.if (\\from) == (\\to)\n> +\t\t_for__body \\from\n> +\t.else\n> +\t\t__for \\from, (\\from) + ((\\to) - (\\from)) / 2\n> +\t\t__for (\\from) + ((\\to) - (\\from)) / 2 + 1, \\to\n> +\t.endif\n> +.endm\n> +\n> +.macro _for var:req, from:req, to:req, insn:vararg\n> +\t.macro _for__body \\var:req\n> +\t\t\\insn\n> +\t.endm\n> +\n> +\t__for \\from, \\to\n> +\n> +\t.purgem _for__body\n> +.endm\n> +\n> +.macro sve_save nxbase, xpfpsr, nxtmp\n> + _for n, 0, 31,\t_sve_str_v\t\\n, \\nxbase, \\n - 34\n> + _for n, 0, 15,\t_sve_str_p\t\\n, \\nxbase, \\n - 16\n> +\t\t_sve_rdffr\t0\n> +\t\t_sve_str_p\t0, \\nxbase\n> +\t\t_sve_ldr_p\t0, \\nxbase, -16\n> +\n> +\t\tmrs\t\tx\\nxtmp, fpsr\n> +\t\tstr\t\tw\\nxtmp, [\\xpfpsr]\n> +\t\tmrs\t\tx\\nxtmp, fpcr\n> +\t\tstr\t\tw\\nxtmp, [\\xpfpsr, #4]\n> +.endm\n> +\n> +.macro sve_load nxbase, xpfpsr, xvqminus1, nxtmp\n> +\t\tmrs_s\t\tx\\nxtmp, SYS_ZCR_EL1\n> +\t\tbic\t\tx\\nxtmp, x\\nxtmp, ZCR_ELx_LEN_MASK\n> +\t\torr\t\tx\\nxtmp, x\\nxtmp, \\xvqminus1\n> +\t\tmsr_s\t\tSYS_ZCR_EL1, x\\nxtmp\t// self-synchronising\n> +\n> + _for n, 0, 31,\t_sve_ldr_v\t\\n, \\nxbase, \\n - 34\n> +\t\t_sve_ldr_p\t0, \\nxbase\n> +\t\t_sve_wrffr\t0\n> + _for n, 0, 15,\t_sve_ldr_p\t\\n, \\nxbase, \\n - 16\n> +\n> +\t\tldr\t\tw\\nxtmp, [\\xpfpsr]\n> +\t\tmsr\t\tfpsr, x\\nxtmp\n> +\t\tldr\t\tw\\nxtmp, [\\xpfpsr, #4]\n> +\t\tmsr\t\tfpcr, x\\nxtmp\n> +.endm\n> diff --git a/arch/arm64/kernel/entry-fpsimd.S b/arch/arm64/kernel/entry-fpsimd.S\n> index 6a27cd6..73f17bf 100644\n> --- a/arch/arm64/kernel/entry-fpsimd.S\n> +++ b/arch/arm64/kernel/entry-fpsimd.S\n> @@ -41,3 +41,20 @@ ENTRY(fpsimd_load_state)\n>  \tfpsimd_restore x0, 8\n>  \tret\n>  ENDPROC(fpsimd_load_state)\n> +\n> +#ifdef CONFIG_ARM64_SVE\n> +ENTRY(sve_save_state)\n> +\tsve_save 0, x1, 2\n> +\tret\n> +ENDPROC(sve_save_state)\n> +\n> +ENTRY(sve_load_state)\n> +\tsve_load 0, x1, x2, 3\n> +\tret\n> +ENDPROC(sve_load_state)\n> +\n> +ENTRY(sve_get_vl)\n> +\t_sve_rdvl\t0, 1\n> +\tret\n> +ENDPROC(sve_get_vl)\n> +#endif /* CONFIG_ARM64_SVE */\n\n\n--\nAlex Bennée","headers":{"Return-Path":"<linux-arm-kernel-bounces+incoming-imx=patchwork.ozlabs.org@lists.infradead.org>","X-Original-To":"incoming-imx@patchwork.ozlabs.org","Delivered-To":"patchwork-incoming-imx@bilbo.ozlabs.org","Authentication-Results":["ozlabs.org;\n\tspf=none (mailfrom) smtp.mailfrom=lists.infradead.org\n\t(client-ip=65.50.211.133; helo=bombadil.infradead.org;\n\tenvelope-from=linux-arm-kernel-bounces+incoming-imx=patchwork.ozlabs.org@lists.infradead.org;\n\treceiver=<UNKNOWN>)","ozlabs.org; dkim=pass (2048-bit key;\n\tunprotected) header.d=lists.infradead.org\n\theader.i=@lists.infradead.org header.b=\"gey/P2Wh\"; \n\tdkim=fail reason=\"signature verification failed\" (1024-bit key;\n\tunprotected) header.d=linaro.org header.i=@linaro.org\n\theader.b=\"jzxJ+iWI\"; dkim-atps=neutral"],"Received":["from bombadil.infradead.org (bombadil.infradead.org\n\t[65.50.211.133])\n\t(using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256\n\tbits)) (No client certificate requested)\n\tby ozlabs.org (Postfix) with ESMTPS id 3xsm7w1nCfz9s7g\n\tfor <incoming-imx@patchwork.ozlabs.org>;\n\tThu, 14 Sep 2017 01:40:12 +1000 (AEST)","from localhost ([127.0.0.1] helo=bombadil.infradead.org)\n\tby bombadil.infradead.org with esmtp (Exim 4.87 #1 (Red Hat Linux))\n\tid 1ds9lo-0006Xg-DQ; Wed, 13 Sep 2017 15:40:08 +0000","from mail-wr0-x236.google.com ([2a00:1450:400c:c0c::236])\n\tby bombadil.infradead.org with esmtps (Exim 4.87 #1 (Red Hat Linux))\n\tid 1ds9lk-0005cS-6V for linux-arm-kernel@lists.infradead.org;\n\tWed, 13 Sep 2017 15:40:06 +0000","by mail-wr0-x236.google.com with SMTP id o42so1400955wrb.3\n\tfor <linux-arm-kernel@lists.infradead.org>;\n\tWed, 13 Sep 2017 08:39:43 -0700 (PDT)","from zen.linaro.local ([81.128.185.34])\n\tby smtp.gmail.com with ESMTPSA id\n\t110sm8077960wra.39.2017.09.13.08.39.40\n\t(version=TLS1_2 cipher=ECDHE-RSA-AES128-GCM-SHA256 bits=128/128);\n\tWed, 13 Sep 2017 08:39:40 -0700 (PDT)","from zen (localhost [127.0.0.1])\n\tby zen.linaro.local (Postfix) with ESMTPS id 2158C3E009F;\n\tWed, 13 Sep 2017 16:39:40 +0100 (BST)"],"DKIM-Signature":["v=1; a=rsa-sha256; q=dns/txt; c=relaxed/relaxed;\n\td=lists.infradead.org; s=bombadil.20170209; h=Sender:\n\tContent-Transfer-Encoding:Content-Type:Cc:List-Subscribe:List-Help:List-Post:\n\tList-Archive:List-Unsubscribe:List-Id:MIME-Version:Message-ID:Date:\n\tIn-reply-to:Subject:To:From:References:Reply-To:Content-ID:\n\tContent-Description:Resent-Date:Resent-From:Resent-Sender:Resent-To:Resent-Cc\n\t:Resent-Message-ID:List-Owner;\n\tbh=T5JLTVZAqV8RoWPMlz7l8e7bwH2dZPFFNTuzkMd8XNU=;\n\tb=gey/P2WhVrlaYdpZOBWHJ9AyVm\n\tdxhZ3t6W/7Uhe77qUd0ItNqX01RUqviAO3rL4SyodL+0oxmX/JhlDhoRuaAi/IlQ76QBtQ8PkRTPl\n\tDbPtPR2bLFMO9tO5yPZwWrDERBsgEksNKi3weiR66CgqW1JzQze3kBkx5Ju3RerkM+iMgzGCA4m/B\n\t4QcuuVOEE9i2rl3+nTsBl21eb0jAK4hnhKNaRTAShvyFoBr9v+YHoTnfRK/+jcY4EUtnHMPdUeYfC\n\t5aKFReKwe5zM80UH279KvogDASfRqIEdWmGzs7YQnQu2k/76beKrqLFEu8aSPROk0WKJnaza++Vki\n\t4EGOOzdA==;","v=1; a=rsa-sha256; c=relaxed/relaxed; d=linaro.org; s=google;\n\th=references:user-agent:from:to:cc:subject:in-reply-to:date\n\t:message-id:mime-version:content-transfer-encoding;\n\tbh=A9taivPhXeEsm+oc9z5v09BgI3d45ts2hml0OP6XgPg=;\n\tb=jzxJ+iWIiZjOxbASE/Jbt2Pcn69JXnwOmmh1QtchRrQMYPXFWwLMrBCL+/yaxFP76t\n\t1XAvkgFzY8uj7pXMeum53eaLj70R+YELLXpP1ymK7URUjcb7NJ6Iq9Iue84fOLO30H8z\n\t5k7kZ0AZIV7+vw7cb2p4ZerGYApaCSrbrIOy0="],"X-Google-DKIM-Signature":"v=1; a=rsa-sha256; c=relaxed/relaxed;\n\td=1e100.net; s=20161025;\n\th=x-gm-message-state:references:user-agent:from:to:cc:subject\n\t:in-reply-to:date:message-id:mime-version:content-transfer-encoding; \n\tbh=A9taivPhXeEsm+oc9z5v09BgI3d45ts2hml0OP6XgPg=;\n\tb=izwCrgYsd2/Tzubgg7b5J/cI2rEhRVZUiHnju18OPbAG3gbLYbOCiIzIaZH5axTwzp\n\trV/JVa+eC6ql0swB3ScGFQVMImFsa8wZOi5Pyxu9vEm29fT4uHjogmEW8jFVzrIRxmfH\n\tGJfaokXGsvdjsl7XNRfW3yfiIGuBGxac0YSC1dG5+IZPi8deXaDi5eTDCCTKUX27ZA8r\n\t2qsLSumG+jgynhrfF1Jvncm1yGXH7B11R10FNwfApBHz0OzgWn4Q82DvgT7gtzQLXeID\n\t7yTatMJCkOejf0xmeC2xN714JSaYqMZnzDopJJ94ydYfkV4dEXxwFLP8XD9coomFnvxc\n\tj7hw==","X-Gm-Message-State":"AHPjjUit3OhFS7OZpFBaablvbPQzA536csMniseckaYK98hFHtNQ3G5v\n\ticiy+u4jASVPSp4R","X-Google-Smtp-Source":"ADKCNb7VcLxhvbcw1xW2H1WlKqEYkvVhBcf/v0i8DUN5ME4dMzx99+lop/V0XGDmLY4RSB9D19Hlwg==","X-Received":"by 10.223.134.174 with SMTP id 43mr17447017wrx.173.1505317181415;\n\tWed, 13 Sep 2017 08:39:41 -0700 (PDT)","References":"<1504198860-12951-1-git-send-email-Dave.Martin@arm.com>\n\t<1504198860-12951-8-git-send-email-Dave.Martin@arm.com>","User-agent":"mu4e 0.9.19; emacs 25.2.50.3","From":"Alex =?utf-8?q?Benn=C3=A9e?= <alex.bennee@linaro.org>","To":"Dave Martin <Dave.Martin@arm.com>","Subject":"Re: [PATCH v2 07/28] arm64/sve: Low-level SVE architectural state\n\tmanipulation functions","In-reply-to":"<1504198860-12951-8-git-send-email-Dave.Martin@arm.com>","Date":"Wed, 13 Sep 2017 16:39:40 +0100","Message-ID":"<87mv5ya9qb.fsf@linaro.org>","MIME-Version":"1.0","X-CRM114-Version":"20100106-BlameMichelson ( TRE 0.8.0 (BSD) ) MR-646709E3 ","X-CRM114-CacheID":"sfid-20170913_084004_401017_DF72701B ","X-CRM114-Status":"GOOD (  14.25  )","X-Spam-Score":"-2.0 (--)","X-Spam-Report":"SpamAssassin version 3.4.1 on bombadil.infradead.org summary:\n\tContent analysis details:   (-2.0 points)\n\tpts rule name              description\n\t---- ----------------------\n\t--------------------------------------------------\n\t-0.0 RCVD_IN_DNSWL_NONE RBL: Sender listed at http://www.dnswl.org/,\n\tno\n\ttrust [2a00:1450:400c:c0c:0:0:0:236 listed in] [list.dnswl.org]\n\t-0.0 SPF_PASS               SPF: sender matches SPF record\n\t-1.9 BAYES_00               BODY: Bayes spam probability is 0 to 1%\n\t[score: 0.0000]\n\t-0.1 DKIM_VALID Message has at least one valid DKIM or DK signature\n\t0.1 DKIM_SIGNED            Message has a DKIM or DK signature,\n\tnot necessarily valid\n\t-0.1 DKIM_VALID_AU Message has a valid DKIM or DK signature from\n\tauthor's domain","X-BeenThere":"linux-arm-kernel@lists.infradead.org","X-Mailman-Version":"2.1.21","Precedence":"list","List-Unsubscribe":"<http://lists.infradead.org/mailman/options/linux-arm-kernel>,\n\t<mailto:linux-arm-kernel-request@lists.infradead.org?subject=unsubscribe>","List-Archive":"<http://lists.infradead.org/pipermail/linux-arm-kernel/>","List-Post":"<mailto:linux-arm-kernel@lists.infradead.org>","List-Help":"<mailto:linux-arm-kernel-request@lists.infradead.org?subject=help>","List-Subscribe":"<http://lists.infradead.org/mailman/listinfo/linux-arm-kernel>,\n\t<mailto:linux-arm-kernel-request@lists.infradead.org?subject=subscribe>","Cc":"linux-arch@vger.kernel.org, libc-alpha@sourceware.org,\n\tArd Biesheuvel <ard.biesheuvel@linaro.org>,\n\tSzabolcs Nagy <szabolcs.nagy@arm.com>,\n\tCatalin Marinas <catalin.marinas@arm.com>,\n\tWill Deacon <will.deacon@arm.com>, \n\tRichard Sandiford <richard.sandiford@arm.com>,\n\tkvmarm@lists.cs.columbia.edu, linux-arm-kernel@lists.infradead.org","Content-Type":"text/plain; charset=\"utf-8\"","Content-Transfer-Encoding":"base64","Sender":"\"linux-arm-kernel\" <linux-arm-kernel-bounces@lists.infradead.org>","Errors-To":"linux-arm-kernel-bounces+incoming-imx=patchwork.ozlabs.org@lists.infradead.org","List-Id":"linux-imx-kernel.lists.patchwork.ozlabs.org"}}]