From mboxrd@z Thu Jan 1 00:00:00 1970 From: "Michael Kerrisk (man-pages)" Subject: Re: [patch] perf_event_open.2: Exclude_hv clarification Date: Thu, 26 Feb 2015 08:50:33 +0100 Message-ID: <54EED049.6090805@gmail.com> References: <54E2D272.1080607@gmail.com> Mime-Version: 1.0 Content-Type: text/plain; charset=windows-1252 Content-Transfer-Encoding: 7bit Return-path: In-Reply-To: <54E2D272.1080607@gmail.com> Sender: linux-kernel-owner@vger.kernel.org To: Vince Weaver Cc: mtk.manpages@gmail.com, linux-man@vger.kernel.org, linux-kernel@vger.kernel.org, Peter Zijlstra , Paul Mackerras , Ingo Molnar , Arnaldo Carvalho de Melo List-Id: linux-man@vger.kernel.org Hello Paul, Ping! Cheers, Michael On 02/17/2015 06:32 AM, Michael Kerrisk (man-pages) wrote: > Hi Paul Mackerass, > > Would you be willing to review/comment on Vince's patch, please. > > Cheers, > > Michael > > On 02/11/2015 08:04 PM, Vince Weaver wrote: >> >> This manpage patch relates to the exclude_hv bit added to the kernel >> in the following commit: >> >> exclude_hv; Linux 2.6.31 >> commit 0475f9ea8e2cc030298908949e0d5da9f2fc2cfe >> Author: Paul Mackerras >> >> perf_counters: allow users to count user, kernel and/or hypervisor events >> >> Signed-off-by: Paul Mackerras >> >> The updated manpage text points out that the exclude_hv >> "exclude hypervisor" bit only applies on hardware that >> supports this feature (such as PowerPC) >> and is silently ignored on other platforms such as x86. >> >> This is a resend of the patch; the previous time I sent it >> (http://thread.gmane.org/gmane.linux.man/7500) it did not >> receive any comments. >> >> >> Signed-off-by: Vince Weaver >> >> diff --git a/man2/perf_event_open.2 b/man2/perf_event_open.2 >> index 39c8d8c..665aa31 100644 >> --- a/man2/perf_event_open.2 >> +++ b/man2/perf_event_open.2 >> @@ -856,10 +856,9 @@ If this bit is set, the count excludes events that happen in kernel-space. >> .IR "exclude_hv" >> If this bit is set, the count excludes events that happen in the >> hypervisor. >> -This is mainly for PMUs that have built-in support for handling this >> -(such as POWER). >> -Extra support is needed for handling hypervisor measurements on most >> -machines. >> +This is mainly for PMUs that have built-in hardware support >> +for this feature (such as POWER; this setting is silently >> +ignored on x86). >> .TP >> .IR "exclude_idle" >> If set, don't count when the CPU is idle. >> > > -- Michael Kerrisk Linux man-pages maintainer; http://www.kernel.org/doc/man-pages/ Linux/UNIX System Programming Training: http://man7.org/training/