From: Anshuman Khandual <khandual@linux.vnet.ibm.com>
To: Stephane Eranian <eranian@google.com>
Cc: linux-kernel@vger.kernel.org, peterz@infradead.org,
mingo@elte.hu, acme@infradead.org, robert.richter@amd.com,
ming.m.lin@intel.com, andi@firstfloor.org, asharma@fb.com,
ravitillo@lbl.gov, vweaver1@eecs.utk.edu
Subject: Re: [PATCH 04/13] perf_events: sync branch stack sampling with X86 precise_sampling (v3)
Date: Fri, 27 Jan 2012 10:56:09 +0530 [thread overview]
Message-ID: <4F223571.8090300@linux.vnet.ibm.com> (raw)
In-Reply-To: <1326127761-2723-5-git-send-email-eranian@google.com>
On Monday 09 January 2012 10:19 PM, Stephane Eranian wrote:
> If precise sampling is enabled on Intel X86, then perf_event uses PEBS.
> To correct for the off-by-one error of PEBS, perf_event uses LBR when
> precise_sample > 1.
>
> On Intel X86 PERF_SAMPLE_BRANCH_STACK is implemented using LBR,
> therefore both features must be coordinated as they may not
> configure LBR the same way.
>
> For PEBS, LBR needs to capture all branches at all priv levels.
> This patch sets this up.
>
> The configuration of PERF_SAMPLE_BRANCH_STACK may not be compatible
> in which case an error must be returned.
>
> Signed-off-by: Stephane Eranian <eranian@google.com>
Reviewed by: Anshuman Khandual<khandual@linux.vnet.ibm.com>
> ---
> arch/x86/kernel/cpu/perf_event.c | 22 ++++++++++++++++++++++
> 1 files changed, 22 insertions(+), 0 deletions(-)
>
> diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
> index 3779313..710ec93 100644
> --- a/arch/x86/kernel/cpu/perf_event.c
> +++ b/arch/x86/kernel/cpu/perf_event.c
> @@ -356,6 +356,7 @@ int x86_setup_perfctr(struct perf_event *event)
> int x86_pmu_hw_config(struct perf_event *event)
> {
> if (event->attr.precise_ip) {
> + u64 *br_type, br_sel;
> int precise = 0;
>
> /* Support for constant skid */
> @@ -369,6 +370,27 @@ int x86_pmu_hw_config(struct perf_event *event)
>
> if (event->attr.precise_ip > precise)
> return -EOPNOTSUPP;
> + /*
> + * check that PEBS LBR correction does not conflict with
> + * whatever the user is asking with attr->branch_sample_type
> + */
> + if (event->attr.precise_ip > 1) {
> +
> + br_type = &event->attr.branch_sample_type;
> +
> + if (has_branch_stack(event)) {
> + br_sel = *br_type & PERF_SAMPLE_BRANCH_ANY;
> + if (br_sel != PERF_SAMPLE_BRANCH_ANY)
> + return -EOPNOTSUPP;
> + } else {
> + /*
> + * For PEBS fixups, we capture all
> + * the branches at all priv levels
> + */
> + *br_type = PERF_SAMPLE_BRANCH_ANY
> + | PERF_SAMPLE_BRANCH_PLM_ALL;
> + }
> + }
> }
>
> /*
--
Linux Technology Centre
IBM Systems and Technology Group
Bangalore India
next prev parent reply other threads:[~2012-01-27 5:26 UTC|newest]
Thread overview: 36+ messages / expand[flat|nested] mbox.gz Atom feed top
2012-01-09 16:49 [PATCH 00/13] perf_events: add support for sampling taken branches (v3) Stephane Eranian
2012-01-09 16:49 ` [PATCH 01/13] perf_events: add generic taken branch sampling support (v3) Stephane Eranian
2012-01-27 4:46 ` Anshuman Khandual
2012-01-27 9:57 ` Stephane Eranian
2012-01-09 16:49 ` [PATCH 02/13] perf_events: add Intel LBR MSR definitions (v3) Stephane Eranian
2012-01-27 5:03 ` Anshuman Khandual
2012-01-09 16:49 ` [PATCH 03/13] perf_events: add Intel X86 LBR sharing logic (v3) Stephane Eranian
2012-01-09 16:49 ` [PATCH 04/13] perf_events: sync branch stack sampling with X86 precise_sampling (v3) Stephane Eranian
2012-01-27 5:26 ` Anshuman Khandual [this message]
2012-01-09 16:49 ` [PATCH 05/13] perf_events: add LBR mappings for PERF_SAMPLE_BRANCH filters (v3) Stephane Eranian
2012-01-27 5:41 ` Anshuman Khandual
2012-01-09 16:49 ` [PATCH 06/13] perf_events: disable LBR support for older Intel Atom processors (v3) Stephane Eranian
2012-01-27 5:43 ` Anshuman Khandual
2012-01-09 16:49 ` [PATCH 07/13] perf_events: implement PERF_SAMPLE_BRANCH for Intel X86 (v3) Stephane Eranian
2012-01-27 6:14 ` Anshuman Khandual
2012-01-09 16:49 ` [PATCH 08/13] perf_events: add LBR software filter support " Stephane Eranian
2012-01-09 16:49 ` [PATCH 09/13] perf_events: disable PERF_SAMPLE_BRANCH_* when not supported (v3) Stephane Eranian
2012-01-27 7:15 ` Anshuman Khandual
2012-01-27 9:56 ` Stephane Eranian
2012-01-09 16:49 ` [PATCH 10/13] perf_events: add hook to flush branch_stack on context switch (v3) Stephane Eranian
2012-01-09 16:49 ` [PATCH 11/13] perf: add code to support PERF_SAMPLE_BRANCH_STACK (v3) Stephane Eranian
2012-01-10 1:25 ` Arun Sharma
2012-01-10 15:43 ` Stephane Eranian
2012-01-09 16:49 ` [PATCH 12/13] perf: add support for sampling taken branch to perf record (v3) Stephane Eranian
2012-01-09 16:49 ` [PATCH 13/13] perf: add support for taken branch sampling to perf report (v3) Stephane Eranian
2012-01-23 10:14 ` [PATCH 00/13] perf_events: add support for sampling taken branches (v3) Stephane Eranian
2012-01-23 12:25 ` Peter Zijlstra
2012-01-23 15:07 ` Stephane Eranian
2012-01-23 15:47 ` Andi Kleen
2012-01-23 17:14 ` Stephane Eranian
2012-01-24 15:39 ` Stephane Eranian
2012-01-24 16:08 ` David Ahern
2012-01-24 17:42 ` Stephane Eranian
2012-01-26 16:21 ` Stephane Eranian
2012-01-27 12:09 ` Peter Zijlstra
2012-01-27 18:20 ` Arun Sharma
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=4F223571.8090300@linux.vnet.ibm.com \
--to=khandual@linux.vnet.ibm.com \
--cc=acme@infradead.org \
--cc=andi@firstfloor.org \
--cc=asharma@fb.com \
--cc=eranian@google.com \
--cc=linux-kernel@vger.kernel.org \
--cc=ming.m.lin@intel.com \
--cc=mingo@elte.hu \
--cc=peterz@infradead.org \
--cc=ravitillo@lbl.gov \
--cc=robert.richter@amd.com \
--cc=vweaver1@eecs.utk.edu \
/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).