From mboxrd@z Thu Jan 1 00:00:00 1970 From: Borislav Petkov Subject: Re: [PATCH] x86/ACPI/cstate: Allow ACPI C1 FFH MWAIT use on AMD systems Date: Tue, 23 May 2017 09:59:11 +0200 Message-ID: <20170523075911.GA25383@nazgul.tnic> References: <1495030819-4347-1-git-send-email-Yazen.Ghannam@amd.com> <20170522162143.GA19781@nazgul.tnic> Mime-Version: 1.0 Content-Type: text/plain; charset=utf-8 Return-path: Received: from mail.skyhub.de ([5.9.137.197]:60516 "EHLO mail.skyhub.de" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1762002AbdEWH7P (ORCPT ); Tue, 23 May 2017 03:59:15 -0400 Content-Disposition: inline In-Reply-To: Sender: linux-pm-owner@vger.kernel.org List-Id: linux-pm@vger.kernel.org To: "Ghannam, Yazen" Cc: "linux-pm@vger.kernel.org" , "x86@kernel.org" , "linux-kernel@vger.kernel.org" , "rjw@rjwysocki.net" , "len.brown@intel.com" , "pavel@ucw.cz" On Mon, May 22, 2017 at 08:20:56PM +0000, Ghannam, Yazen wrote: > On the other hand, MWAIT on AMD limits the hardware to using only certain, > shallower Cstates. This is okay if we define individual states and use MWAIT > for some of them. But it would consume more power if used always. Let me see if I understand it correctly: Even though we used to do HLT on previous families as idling with HLT *is* the preferred method until now, with your change you're moving *every* AMD machine out there to do MWAIT now. Lemme look at the F15h BKDG: "2.5.3.2 C-state Request Interface C-states are dynamically requested by software and are exposed through ACPI objects (see 2.5.3.6 [ACPI Processor C-state Objects]). C-states can be requested on a per-core basis. Software requests a C-state change in one of two ways, either by executing the HLT instruction or by reading from an IO address specified by MSRC001_0073[CstateAddr] plus an offset of 0 through 7 (see D18F4x11[C:8])." So this doesn't say anything about using MWAIT. What's up? -- Regards/Gruss, Boris. ECO tip #101: Trim your mails when you reply. --