Return-Path: Received: from mail.linutronix.de (146.0.238.70:993) by crypto-ml.lab.linutronix.de with IMAP4-SSL for ; 05 Feb 2019 15:32:27 -0000 Received: from merlin.infradead.org ([2001:8b0:10b:1231::1]) by Galois.linutronix.de with esmtps (TLS1.2:RSA_AES_256_CBC_SHA256:256) (Exim 4.80) (envelope-from ) id 1gr2i1-0000VD-99 for speck@linutronix.de; Tue, 05 Feb 2019 16:32:26 +0100 Received: from j217100.upc-j.chello.nl ([24.132.217.100] helo=hirez.programming.kicks-ass.net) by merlin.infradead.org with esmtpsa (Exim 4.90_1 #2 (Red Hat Linux)) id 1gr2i0-0004aI-1q for speck@linutronix.de; Tue, 05 Feb 2019 15:32:24 +0000 Date: Tue, 5 Feb 2019 16:32:22 +0100 From: Peter Zijlstra Subject: [MODERATED] Re: [PATCH v1 0/9] PERFv1 0 Message-ID: <20190205153222.GZ17528@hirez.programming.kicks-ass.net> References: MIME-Version: 1.0 In-Reply-To: Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: 7bit To: speck@linutronix.de List-ID: On Mon, Feb 04, 2019 at 05:14:01PM -0800, speck for Andi Kleen wrote: > From: Andi Kleen > Subject: PERFv1 > > Walnut is an functional (not security) issue with TSX. The upcoming > microcode updates on Skylake may corrupt perfmon counter 3 > when RTM transactions are used. > > There is a new MSR that allows to force abort RTM, and free > counter 3. > > The following patchkit adds the support to perf to avoid > using counter 3, or disabling TSX when counter 3 is needed > for perf. > > There are per perf event and global options to set the > default. > > This patch sets the default to TSX enabled, but > that could be easily changed. > > We can have a discussion on the trade offs of the default > setting. I suspect it's a decision that should be made by Linus, > as it may impact user programs either way. > > The trade offs for setting the option default are: > > Using 4 (or 8 with HT off) events in perf versus > allowing RTM usage while perf is active. > > - Existing programs that use perf groups with 4 counters > may not retrieve perfmon data anymore. Perf usages > that use less than four (or 7 with HT off) counters > are not impacted. Perf usages that don't use group > will still work, but will see increase multiplexing. > > - TSX programs should not functionally break from > forcing RTM to abort because they always need a valid > fall back path. However they will see significantly > lower performance if they rely on TSX for performance > (all RTM transactions will run and only abort at the end), > potentially slowing them down so much that it is > equivalent to functional breakage. Like said; I absolutely _hate_ all of this. But I think the very worst of it is that this PMC3 corruption is on-by-default in the ucode. This means that people who update their ucode but don't update their kernel are utterly screwed.