From: David Ahern <dsahern@gmail.com>
To: Robert Richter <robert.richter@amd.com>,
Peter Zijlstra <peterz@infradead.org>,
Avi Kivity <avi@redhat.com>
Cc: Arnaldo Carvalho de Melo <acme@ghostprotocols.net>,
linux-kernel@vger.kernel.org, Ingo Molnar <mingo@kernel.org>,
Jiri Olsa <jolsa@redhat.com>, Namhyung Kim <namhyung@kernel.org>,
Frederic Weisbecker <fweisbec@gmail.com>,
Gleb Natapov <gleb@redhat.com>
Subject: Re: [PATCH 08/11] perf tool: precise mode requires exclude_guest
Date: Wed, 05 Sep 2012 09:43:46 -0600 [thread overview]
Message-ID: <50477332.1000902@gmail.com> (raw)
In-Reply-To: <20120803135117.GC3732@erda.amd.com>
In an attempt to jump start this thread...
On 8/3/12 7:51 AM, Robert Richter wrote:
> On 26.07.12 10:08:29, Peter Zijlstra wrote:
>> On Wed, 2012-07-25 at 23:16 -0600, David Ahern wrote:
>>
>>> Peter's patch (see https://lkml.org/lkml/2012/7/9/298) changes kernel
>>> side to require the use of exclude_guest if the precise modifier is
>>> used, returning -EOPNOTSUPP if exclude_guest is not set. This patch goes
>>> after the user experience: Today if a user specifies -e <event>:p all
>>> other modifiers are reset - including exclude_guest. Going forward we
>>> need :p to imply :pH if a user has not specified a GH modifer.
>>>
>>> We could do nothing and handle the unsupported error and try setting the
>>> exclude_guest option - like perf handles other new parameters. But
>>> EOPNOTSUPP is not uniquely tied to this error -- e.g., it could be the
>>> BTS is not supported (:pp). Also, we have no easy way to discriminate :p
>>> from :pG or :pGH. It seems to me perf should not silently undo a user
>>> request on the modifier, but inform the user the request is wrong. For
>>> example if a user request -e cycles:pG it should not be silently turned
>>> into :pH.
>>>
>>> And then yesterday, Robert stated that none of the exclude_xxxx
>>> modifiers can be set for the AMD if the precise modifier is used, so we
>>> cannot blindly set exclude_guest if precise_ip is set.
>>>
>>> So, seems to me perf need's one action for Intel processors and another
>>> for AMD.
>>
>> No, we just need to teach the IBS code about SVM enter/exit.
>
> I aggree that this could be emulated in software by enabling/disabling
> the event with a guest/host switch. And, even better, we add this for
> every pmu in a generic way. E.g. northbridge counter and I guess also
> Intel uncore events do not support G/H counting in hardware. Same to
> other pmus that could be imaginable in the future like counters for
> IOMMUs or other hardware devices.
>
> But, as some pmus are not related to virtualization or other features
> they simply do not need to support those attributes, or we want other
> defaults, e.g. enable it system wide. Detecting features with syscall
> error checking and then falling back to other defaults does not seem
> the right approach to me, because it may require several syscalls to
> check *combinations* of supported attributes, makes error logging and
> detection more difficult due to noisy log messages and because there
> is no strict attribute flag checking in current and older kernels.
>
> I better would like to see a pmu feature flag in the same style as
> with /proc/cpuinfo, e.g.:
>
> $ cat /sys/bus/event_source/devices/cpu/flags
> exclude_host exclude_guest
>
> We also need stricter attribute flag checking, esp. of reseved flags
> and for unsupported features in some pmus (I already work on some
> patches for this). Userland then checks flags and sets up syscalls
> according to the reported flags. The goal should be to avoid syscall
> errors at all. Thus, we are able to improve dmesg logging in case of
> errors, currently we do not see any message if a syscall fails.
>
> And finally, if a feature could be emulated, we could provide this
> emulation of an attr flag to all pmus.
>
> Does this make sense?
We need to require exclude_guest when using precise attribute with perf
else all running VMs on Intel-based servers will crash. I do not have an
AMD based server to even attempt the preferred solution. Best I can do
is to attempt to keep this thread alive until someone with one can
tackle the problem.
David
next prev parent reply other threads:[~2012-09-05 15:44 UTC|newest]
Thread overview: 66+ messages / expand[flat|nested] mbox.gz Atom feed top
2012-07-20 23:25 [PATCH 00/11] perf tool: assorted cleanups and bug fixes David Ahern
2012-07-20 23:25 ` [PATCH 01/11] perf tool: add machine id to modules debug message David Ahern
2012-07-25 19:16 ` [tip:perf/core] perf symbols: Add " tip-bot for David Ahern
2012-07-20 23:25 ` [PATCH 02/11] perf kvm: set name for VM process in guest machine David Ahern
2012-07-25 12:12 ` Jiri Olsa
2012-07-25 19:17 ` [tip:perf/core] perf kvm: Set " tip-bot for David Ahern
2012-07-20 23:25 ` [PATCH 03/11] perf kvm: guest userspace samples should not be lumped with host uspace David Ahern
2012-07-25 12:13 ` Jiri Olsa
2012-07-25 19:18 ` [tip:perf/core] perf kvm: Guest " tip-bot for David Ahern
2012-07-20 23:25 ` [PATCH 04/11] perf kvm: fix bug resolving guest kernel syms - v2 David Ahern
2012-07-25 12:11 ` Jiri Olsa
2012-07-25 19:19 ` [tip:perf/core] perf kvm: Fix bug resolving guest kernel syms tip-bot for David Ahern
2012-07-20 23:25 ` [PATCH 05/11] perf kvm: use strtol for walking guestmount directory David Ahern
2012-07-23 18:09 ` Arnaldo Carvalho de Melo
2012-07-20 23:25 ` [PATCH 06/11] perf kvm: limit repetitive guestmount message to once per directory David Ahern
2012-07-23 18:11 ` Arnaldo Carvalho de Melo
2012-07-25 19:20 ` [tip:perf/core] perf kvm: Limit " tip-bot for David Ahern
2012-07-20 23:25 ` [PATCH 07/11] perf tools: dump exclude_{guest,host}, precise_ip header info too David Ahern
2012-07-25 19:20 ` [tip:perf/core] perf tools: Dump " tip-bot for David Ahern
2012-07-20 23:25 ` [PATCH 08/11] perf tool: precise mode requires exclude_guest David Ahern
2012-07-23 18:13 ` Arnaldo Carvalho de Melo
2012-07-24 14:20 ` David Ahern
2012-07-24 16:15 ` Robert Richter
2012-07-24 17:28 ` David Ahern
2012-07-24 18:03 ` Arnaldo Carvalho de Melo
2012-07-26 5:16 ` David Ahern
2012-07-26 8:08 ` Peter Zijlstra
2012-08-03 13:51 ` Robert Richter
2012-08-15 15:22 ` David Ahern
2012-09-05 15:43 ` David Ahern [this message]
2012-09-05 22:07 ` Peter Zijlstra
2012-09-06 17:44 ` Robert Richter
2012-09-06 18:19 ` David Ahern
2012-07-25 20:35 ` Peter Zijlstra
2012-07-26 5:50 ` Gleb Natapov
2012-07-26 8:07 ` Peter Zijlstra
2012-07-26 8:10 ` Gleb Natapov
2012-07-26 9:07 ` Robert Richter
2012-08-02 16:06 ` David Ahern
2012-09-06 19:02 ` Robert Richter
2012-09-06 19:17 ` David Ahern
2012-09-06 19:56 ` Robert Richter
2012-09-07 16:41 ` [PATCH] perf, ibs: Check syscall attribute flags Robert Richter
2012-09-07 16:50 ` David Ahern
2012-09-07 17:07 ` Robert Richter
2012-09-07 17:11 ` David Ahern
2012-09-07 17:20 ` David Ahern
2012-09-10 13:07 ` Robert Richter
2012-09-10 15:37 ` Arnaldo Carvalho de Melo
2012-09-07 17:25 ` Robert Richter
2012-09-07 16:56 ` Peter Zijlstra
2012-09-07 17:18 ` Robert Richter
2012-09-07 19:11 ` Peter Zijlstra
2012-09-10 9:30 ` [PATCH -v2] " Robert Richter
2012-09-14 6:17 ` [tip:perf/urgent] perf/x86/ibs: " tip-bot for Robert Richter
2012-07-20 23:25 ` [PATCH 09/11] perf top: error handling for counter creation should parallel perf-record David Ahern
2012-07-23 18:15 ` Arnaldo Carvalho de Melo
2012-07-24 14:01 ` David Ahern
2012-07-24 14:39 ` Arnaldo Carvalho de Melo
2012-07-20 23:25 ` [PATCH 10/11] perf tool: give user better message if precise is not supported David Ahern
2012-07-21 10:40 ` Namhyung Kim
2012-07-22 2:28 ` David Ahern
2012-07-20 23:25 ` [PATCH 11/11] perf kvm top: limit guest kernel info message to once David Ahern
2012-07-23 18:17 ` Arnaldo Carvalho de Melo
2012-07-24 14:02 ` David Ahern
2012-07-24 14:40 ` Arnaldo Carvalho de Melo
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=50477332.1000902@gmail.com \
--to=dsahern@gmail.com \
--cc=acme@ghostprotocols.net \
--cc=avi@redhat.com \
--cc=fweisbec@gmail.com \
--cc=gleb@redhat.com \
--cc=jolsa@redhat.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@kernel.org \
--cc=namhyung@kernel.org \
--cc=peterz@infradead.org \
--cc=robert.richter@amd.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: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).