From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail.linutronix.de (146.0.238.70:993) by crypto-ml.lab.linutronix.de with IMAP4-SSL for ; 19 Feb 2019 18:50:05 -0000 Received: from mail-lj1-x22b.google.com ([2a00:1450:4864:20::22b]) by Galois.linutronix.de with esmtps (TLS1.2:RSA_AES_128_CBC_SHA1:128) (Exim 4.80) (envelope-from ) id 1gwASx-0005pE-LJ for speck@linutronix.de; Tue, 19 Feb 2019 19:50:04 +0100 Received: by mail-lj1-x22b.google.com with SMTP id z20so17368992ljj.10 for ; Tue, 19 Feb 2019 10:50:03 -0800 (PST) References: <20190219155807.878855982@infradead.org> <20190219155859.834625575@infradead.org> In-Reply-To: <20190219155859.834625575@infradead.org> From: Linus Torvalds Date: Tue, 19 Feb 2019 10:49:41 -0800 Message-ID: Subject: [MODERATED] Re: Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: 7bit MIME-Version: 1.0 To: speck@linutronix.de List-ID: On Tue, Feb 19, 2019 at 8:03 AM speck for Peter Zijlstra wrote: > > When TFA is allowed (default); the MSR gets set when PMC3 gets > scheduled and cleared when, after scheduling, PMC3 is unused. > > When TFA is not allowed; clear PMC3 from all constraints such that it > will not get used. I wonder if somebody wants a "abort always" mode for testing? IOW, have a mode where even if PCM3 is not used, set the TSX_FORCE_ABORT bit. That way people can actually verify that their code works even if it sees TSX enabled and uses it (but it always aborts). Basically verifying their fallback code. Linus