From: David Daney <ddaney@caviumnetworks.com> To: Will Deacon <will.deacon@arm.com> Cc: David Daney <ddaney.cavm@gmail.com>, <linux-arm-kernel@lists.infradead.org>, Mark Rutland <mark.rutland@arm.com>, Catalin Marinas <catalin.marinas@arm.com>, Marc Zyngier <marc.zyngier@arm.com>, <linux-kernel@vger.kernel.org>, Andrew Pinski <apinski@cavium.com>, David Daney <david.daney@cavium.com> Subject: Re: [PATCH] arm64: Add workaround for Cavium erratum 27456 Date: Wed, 10 Feb 2016 10:08:17 -0800 [thread overview] Message-ID: <56BB7C91.5010205@caviumnetworks.com> (raw) In-Reply-To: <20160210092822.GA1052@arm.com> On 02/10/2016 01:28 AM, Will Deacon wrote: > On Tue, Feb 09, 2016 at 11:29:16AM -0800, David Daney wrote: >> From: Andrew Pinski <apinski@cavium.com> >> >> On ThunderX T88 pass 1.x through 2.1 parts, broadcast TLBI >> instructions may cause the icache to become invalid if it contains >> data for a non-current ASID. >> >> This patch implements the workaround (which flushes the local icache >> when switching the mm) by using code patching. > > So, to be clear, is this "just" a performance problem as opposed to a > correctness issue? No. It is a correctness issue. Without this workaround in place, userspace programs end up executing the wrong instructions, which leads to unpredictable behavior and program crashes. > If so, do you have any numbers with and without this > change? We tried to measure it, but the impact is not measurable in the tests we have done. Switching the mm is not often done so the extra ICache invalidation is rare. Also note that for the non-workaround case, the code path is unchanged. Since the following function (__cpu_setup()) is not on the hot path of anything, any extra ICache pressure from the three NOPs is unlikely to matter. > > Will >
WARNING: multiple messages have this Message-ID (diff)
From: ddaney@caviumnetworks.com (David Daney) To: linux-arm-kernel@lists.infradead.org Subject: [PATCH] arm64: Add workaround for Cavium erratum 27456 Date: Wed, 10 Feb 2016 10:08:17 -0800 [thread overview] Message-ID: <56BB7C91.5010205@caviumnetworks.com> (raw) In-Reply-To: <20160210092822.GA1052@arm.com> On 02/10/2016 01:28 AM, Will Deacon wrote: > On Tue, Feb 09, 2016 at 11:29:16AM -0800, David Daney wrote: >> From: Andrew Pinski <apinski@cavium.com> >> >> On ThunderX T88 pass 1.x through 2.1 parts, broadcast TLBI >> instructions may cause the icache to become invalid if it contains >> data for a non-current ASID. >> >> This patch implements the workaround (which flushes the local icache >> when switching the mm) by using code patching. > > So, to be clear, is this "just" a performance problem as opposed to a > correctness issue? No. It is a correctness issue. Without this workaround in place, userspace programs end up executing the wrong instructions, which leads to unpredictable behavior and program crashes. > If so, do you have any numbers with and without this > change? We tried to measure it, but the impact is not measurable in the tests we have done. Switching the mm is not often done so the extra ICache invalidation is rare. Also note that for the non-workaround case, the code path is unchanged. Since the following function (__cpu_setup()) is not on the hot path of anything, any extra ICache pressure from the three NOPs is unlikely to matter. > > Will >
next prev parent reply other threads:[~2016-02-10 18:08 UTC|newest] Thread overview: 18+ messages / expand[flat|nested] mbox.gz Atom feed top 2016-02-09 19:29 [PATCH] arm64: Add workaround for Cavium erratum 27456 David Daney 2016-02-09 19:29 ` David Daney 2016-02-09 19:52 ` Marc Zyngier 2016-02-09 19:52 ` Marc Zyngier 2016-02-09 19:59 ` David Daney 2016-02-09 19:59 ` David Daney 2016-02-09 20:07 ` Marc Zyngier 2016-02-09 20:07 ` Marc Zyngier 2016-02-10 9:28 ` Will Deacon 2016-02-10 9:28 ` Will Deacon 2016-02-10 18:08 ` David Daney [this message] 2016-02-10 18:08 ` David Daney 2016-02-10 18:15 ` Will Deacon 2016-02-10 18:15 ` Will Deacon 2016-02-10 18:42 ` David Daney 2016-02-10 18:42 ` David Daney 2016-02-11 13:07 ` Will Deacon 2016-02-11 13:07 ` Will Deacon
Reply instructions: You may reply publicly to this message via plain-text email using any one of the following methods: * Save the following mbox file, import it into your mail client, and reply-to-all from there: mbox Avoid top-posting and favor interleaved quoting: https://en.wikipedia.org/wiki/Posting_style#Interleaved_style * Reply using the --to, --cc, and --in-reply-to switches of git-send-email(1): git send-email \ --in-reply-to=56BB7C91.5010205@caviumnetworks.com \ --to=ddaney@caviumnetworks.com \ --cc=apinski@cavium.com \ --cc=catalin.marinas@arm.com \ --cc=david.daney@cavium.com \ --cc=ddaney.cavm@gmail.com \ --cc=linux-arm-kernel@lists.infradead.org \ --cc=linux-kernel@vger.kernel.org \ --cc=marc.zyngier@arm.com \ --cc=mark.rutland@arm.com \ --cc=will.deacon@arm.com \ /path/to/YOUR_REPLY https://kernel.org/pub/software/scm/git/docs/git-send-email.html * If your mail client supports setting the In-Reply-To header via mailto: links, try the mailto: linkBe sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes, see mirroring instructions on how to clone and mirror all data and code used by this external index.