From mboxrd@z Thu Jan 1 00:00:00 1970 From: Sebastian Andrzej Siewior Subject: Re: [PATCH RT] arm*: disable NEON in kernel mode Date: Mon, 4 Dec 2017 10:21:46 +0100 Message-ID: <20171204092145.GE2255@linutronix.de> References: <20171130142216.GB12606@linutronix.de> <20171130143028.GA1351@linutronix.de> <20171201104331.GB1612@linutronix.de> <20171201134506.GF1612@linutronix.de> <20171201141827.yip6pl3tt7kxzek7@lakrids.cambridge.arm.com> <20171201143648.GK1612@linutronix.de> <24FDBFF1-8351-46FC-885A-6B6F972F4C6C@linaro.org> <20171201175844.GT22781@e103592.cambridge.arm.com> <20171201180828.GN10595@n2100.armlinux.org.uk> <20171201182410.GU22781@e103592.cambridge.arm.com> Mime-Version: 1.0 Content-Type: text/plain; charset=utf-8 Cc: Russell King - ARM Linux , Mark Rutland , linux-rt-users@vger.kernel.org, Ard Biesheuvel , Peter Zijlstra , Catalin Marinas , Will Deacon , linux-kernel@vger.kernel.org, Steven Rostedt , tglx@linutronix.de, linux-arm-kernel@lists.infradead.org To: Dave Martin Return-path: Content-Disposition: inline In-Reply-To: <20171201182410.GU22781@e103592.cambridge.arm.com> Sender: linux-kernel-owner@vger.kernel.org List-Id: linux-rt-users.vger.kernel.org On 2017-12-01 18:24:10 [+0000], Dave Martin wrote: > > diff --git a/arch/arm64/crypto/Kconfig b/arch/arm64/crypto/Kconfig > > index 70c517aa4501..2a5f05b5a19a 100644 > > --- a/arch/arm64/crypto/Kconfig > > +++ b/arch/arm64/crypto/Kconfig > > @@ -19,19 +19,19 @@ config CRYPTO_SHA512_ARM64 > > > > config CRYPTO_SHA1_ARM64_CE > > tristate "SHA-1 digest algorithm (ARMv8 Crypto Extensions)" > > - depends on KERNEL_MODE_NEON > > + depends on KERNEL_MODE_NEON && !PREEMPT_RT_BASE > > select CRYPTO_HASH > > select CRYPTO_SHA1 > > Sebastian, can you piont to where sha1 (say) hits this issue? > I wonder whether this is really a sign that some refactoring is needed. I disabled all NEON in one go. Looking at this, it shouldn't be a issue with the block-walk. The only thing that might be a problem is that it can do multiple blocks in one go. > Cheers > ---Dave Sebastian From mboxrd@z Thu Jan 1 00:00:00 1970 From: bigeasy@linutronix.de (Sebastian Andrzej Siewior) Date: Mon, 4 Dec 2017 10:21:46 +0100 Subject: [PATCH RT] arm*: disable NEON in kernel mode In-Reply-To: <20171201182410.GU22781@e103592.cambridge.arm.com> References: <20171130142216.GB12606@linutronix.de> <20171130143028.GA1351@linutronix.de> <20171201104331.GB1612@linutronix.de> <20171201134506.GF1612@linutronix.de> <20171201141827.yip6pl3tt7kxzek7@lakrids.cambridge.arm.com> <20171201143648.GK1612@linutronix.de> <24FDBFF1-8351-46FC-885A-6B6F972F4C6C@linaro.org> <20171201175844.GT22781@e103592.cambridge.arm.com> <20171201180828.GN10595@n2100.armlinux.org.uk> <20171201182410.GU22781@e103592.cambridge.arm.com> Message-ID: <20171204092145.GE2255@linutronix.de> To: linux-arm-kernel@lists.infradead.org List-Id: linux-arm-kernel.lists.infradead.org On 2017-12-01 18:24:10 [+0000], Dave Martin wrote: > > diff --git a/arch/arm64/crypto/Kconfig b/arch/arm64/crypto/Kconfig > > index 70c517aa4501..2a5f05b5a19a 100644 > > --- a/arch/arm64/crypto/Kconfig > > +++ b/arch/arm64/crypto/Kconfig > > @@ -19,19 +19,19 @@ config CRYPTO_SHA512_ARM64 > > > > config CRYPTO_SHA1_ARM64_CE > > tristate "SHA-1 digest algorithm (ARMv8 Crypto Extensions)" > > - depends on KERNEL_MODE_NEON > > + depends on KERNEL_MODE_NEON && !PREEMPT_RT_BASE > > select CRYPTO_HASH > > select CRYPTO_SHA1 > > Sebastian, can you piont to where sha1 (say) hits this issue? > I wonder whether this is really a sign that some refactoring is needed. I disabled all NEON in one go. Looking at this, it shouldn't be a issue with the block-walk. The only thing that might be a problem is that it can do multiple blocks in one go. > Cheers > ---Dave Sebastian