From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail-pf1-x441.google.com (mail-pf1-x441.google.com [IPv6:2607:f8b0:4864:20::441]) by sourceware.org (Postfix) with ESMTPS id 4A2E1386F835 for ; Wed, 15 Apr 2020 21:45:31 +0000 (GMT) DMARC-Filter: OpenDMARC Filter v1.3.2 sourceware.org 4A2E1386F835 Received: by mail-pf1-x441.google.com with SMTP id d1so648796pfh.1 for ; Wed, 15 Apr 2020 14:45:31 -0700 (PDT) X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20161025; h=x-gm-message-state:date:from:subject:to:cc:mime-version:message-id :content-transfer-encoding; bh=AEaYw32qnHlvF+/j3/Jvpgo3bfQkRcMMSHiXyI3G7Uw=; b=HXUyl4ST8dQCBHrJDdLGpkr+guqHFF9sxaMMDCQ2AaQUXqzaPqERibrK823Ap/Zn9l rN9A71jOw3B1yuWxu6YMptwi9RT1Vwhk7SmNNQXgBqHsWPwCmO18XcVo2WIIzL0MaDGk MRQJDc9w3gI4DYO0zS/y6Xlgm4kB+fUejyjfPATDq+E2CNTJfxq3E8tr7fPrIgs4uFFg LSP6HRfh3brs0V4Zps0horl6Y5F+1eTpRMkglvfBtgzILas4o7NZ1rOGpN4y+YbYhrcn pNeO1xnHSP54ULIKp2y5mnZv9C2chp/eOSjUGTkdoVvGBnhrE5rRX72iDi2vZ30l2ARD DeZQ== X-Gm-Message-State: AGi0PuZB+d7Vd69V5Q7Igt95unrEIhiHO/SiypY5wRQhz5QVd06iBavQ sMS8SrGUwPh3KEo6mJj8Z1U= X-Google-Smtp-Source: APiQypJWoBYoWAm7oki13Exmax+mrhiZhgvqqJoR2FMRTLGjgFCJvvugMY5vDPvbr1AOSRrFApd/Vw== X-Received: by 2002:a63:c007:: with SMTP id h7mr28169254pgg.428.1586987130406; Wed, 15 Apr 2020 14:45:30 -0700 (PDT) Received: from localhost ([203.18.28.220]) by smtp.gmail.com with ESMTPSA id g11sm505015pjs.17.2020.04.15.14.45.28 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Wed, 15 Apr 2020 14:45:29 -0700 (PDT) Date: Thu, 16 Apr 2020 07:45:09 +1000 From: Nicholas Piggin Subject: Powerpc Linux 'scv' system call ABI proposal take 2 To: linuxppc-dev@lists.ozlabs.org Cc: libc-alpha@sourceware.org, libc-dev@lists.llvm.org, musl@lists.openwall.com, Segher Boessenkool MIME-Version: 1.0 Message-Id: <1586931450.ub4c8cq8dj.astroid@bobo.none> Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: quoted-printable X-Spam-Status: No, score=-1.4 required=5.0 tests=BAYES_00, DKIM_SIGNED, DKIM_VALID, DKIM_VALID_AU, DKIM_VALID_EF, FREEMAIL_FROM, KAM_NUMSUBJECT, RCVD_IN_DNSWL_NONE, SPF_HELO_NONE, SPF_PASS, TXREP autolearn=no autolearn_force=no version=3.4.2 X-Spam-Checker-Version: SpamAssassin 3.4.2 (2018-09-13) on server2.sourceware.org X-BeenThere: libc-alpha@sourceware.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: Libc-alpha mailing list List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 15 Apr 2020 21:45:34 -0000 I would like to enable Linux support for the powerpc 'scv' instruction, as a faster system call instruction. This requires two things to be defined: Firstly a way to advertise to=20 userspace that kernel supports scv, and a way to allocate and advertise support for individual scv vectors. Secondly, a calling convention ABI for this new instruction. Thanks to those who commented last time, since then I have removed my answered questions and unpopular alternatives but you can find them here https://lists.ozlabs.org/pipermail/linuxppc-dev/2020-January/203545.html Let me try one more with a wider cc list, and then we'll get something merged. Any questions or counter-opinions are welcome. System Call Vectored (scv) ABI =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D= =3D=3D=3D=3D=3D The scv instruction is introduced with POWER9 / ISA3, it comes with an rfscv counter-part. The benefit of these instructions is performance (trading slower SRR0/1 with faster LR/CTR registers, and entering the kernel with MSR[EE] and MSR[RI] left enabled, which can reduce MSR=20 updates. The scv instruction has 128 interrupt entry points (not enough=20 to cover the Linux system call space). The proposal is to assign scv numbers very conservatively and allocate=20 them as individual HWCAP features as we add support for more. The zero=20 vector ('scv 0') will be used for normal system calls, equivalent to 'sc'. Advertisement Linux has not enabled FSCR[SCV] yet, so the instruction will cause a SIGILL in current environments. Linux has defined a HWCAP2 bit=20 PPC_FEATURE2_SCV for SCV support, but does not set it. When scv instruction support and the scv 0 vector for system calls are=20 added, PPC_FEATURE2_SCV will indicate support for these. Other vectors=20 should not be used without future HWCAP bits indicating support, which is how we will allocate them. (Should unallocated ones generate SIGILL, or return -ENOSYS in r3?) Calling convention The proposal is for scv 0 to provide the standard Linux system call ABI=20 with the following differences from sc convention[1]: - LR is to be volatile across scv calls. This is necessary because the=20 scv instruction clobbers LR. From previous discussion, this should be=20 possible to deal with in GCC clobbers and CFI. - CR1 and CR5-CR7 are volatile. This matches the C ABI and would allow the kernel system call exit to avoid restoring the CR register (although=20 we probably still would anyway to avoid information leak). - Error handling: I think the consensus has been to move to using negative return value in r3 rather than CR0[SO]=3D1 to indicate error, which match= es most other architectures and is closer to a function call. The number of scratch registers (r9-r12) at kernel entry seems=20 sufficient that we don't have any costly spilling, patch is here[2]. =20 [1] https://github.com/torvalds/linux/blob/master/Documentation/powerpc/sys= call64-abi.rst [2] https://lists.ozlabs.org/pipermail/linuxppc-dev/2020-February/204840.ht= ml