From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
To: linux-kernel@vger.kernel.org
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
stable@vger.kernel.org, John McCalpin <mccalpin@tacc.utexas.edu>,
Vince Weaver <vincent.weaver@maine.edu>,
Peter Zijlstra <peterz@infradead.org>,
Arnaldo Carvalho de Melo <acme@ghostprotocols.net>,
Paul Mackerras <paulus@samba.org>, Ingo Molnar <mingo@kernel.org>,
zheng.z.yan@intel.com
Subject: [ 01/45] perf/x86: Fix intel QPI uncore event definitions
Date: Sun, 18 Aug 2013 13:35:50 -0700 [thread overview]
Message-ID: <20130818203621.098555466@linuxfoundation.org> (raw)
In-Reply-To: <20130818203620.996166594@linuxfoundation.org>
3.10-stable review patch. If anyone has any objections, please let me know.
------------------
From: Vince Weaver <vincent.weaver@maine.edu>
commit c9601247f8f3fdc18aed7ed7e490e8dfcd07f122 upstream.
John McCalpin reports that the "drs_data" and "ncb_data" QPI
uncore events are missing the "extra bit" and always return zero
values unless the bit is properly set.
More details from him:
According to the Xeon E5-2600 Product Family Uncore Performance
Monitoring Guide, Table 2-94, about 1/2 of the QPI Link Layer events
(including the ones that "perf" calls "drs_data" and "ncb_data") require
that the "extra bit" be set.
This was confusing for a while -- a note at the bottom of page 94 says
that the "extra bit" is bit 16 of the control register.
Unfortunately, Table 2-86 clearly says that bit 16 is reserved and must
be zero. Looking around a bit, I found that bit 21 appears to be the
correct "extra bit", and further investigation shows that "perf" actually
agrees with me:
[root@c560-003.stampede]# cat /sys/bus/event_source/devices/uncore_qpi_0/format/event
config:0-7,21
So the command
# perf -e "uncore_qpi_0/event=drs_data/"
Is the same as
# perf -e "uncore_qpi_0/event=0x02,umask=0x08/"
While it should be
# perf -e "uncore_qpi_0/event=0x102,umask=0x08/"
I confirmed that this last version gives results that agree with the
amount of data that I expected the STREAM benchmark to move across the QPI
link in the second (cross-chip) test of the original script.
Reported-by: John McCalpin <mccalpin@tacc.utexas.edu>
Signed-off-by: Vince Weaver <vincent.weaver@maine.edu>
Cc: zheng.z.yan@intel.com
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
Cc: Paul Mackerras <paulus@samba.org>
Link: http://lkml.kernel.org/r/alpine.DEB.2.10.1308021037280.26119@vincent-weaver-1.um.maine.edu
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
arch/x86/kernel/cpu/perf_event_intel_uncore.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
@@ -314,8 +314,8 @@ static struct uncore_event_desc snbep_un
static struct uncore_event_desc snbep_uncore_qpi_events[] = {
INTEL_UNCORE_EVENT_DESC(clockticks, "event=0x14"),
INTEL_UNCORE_EVENT_DESC(txl_flits_active, "event=0x00,umask=0x06"),
- INTEL_UNCORE_EVENT_DESC(drs_data, "event=0x02,umask=0x08"),
- INTEL_UNCORE_EVENT_DESC(ncb_data, "event=0x03,umask=0x04"),
+ INTEL_UNCORE_EVENT_DESC(drs_data, "event=0x102,umask=0x08"),
+ INTEL_UNCORE_EVENT_DESC(ncb_data, "event=0x103,umask=0x04"),
{ /* end: all zeroes */ },
};
next prev parent reply other threads:[~2013-08-18 20:35 UTC|newest]
Thread overview: 55+ messages / expand[flat|nested] mbox.gz Atom feed top
2013-08-18 20:35 [ 00/45] 3.10.8-stable review Greg Kroah-Hartman
2013-08-18 20:35 ` Greg Kroah-Hartman [this message]
2013-08-18 20:35 ` [ 02/45] perf/arm: Fix armpmu_map_hw_event() Greg Kroah-Hartman
2013-08-18 20:35 ` [ 03/45] memcg: dont initialize kmem-cache destroying work for root caches Greg Kroah-Hartman
2013-08-18 20:35 ` [ 04/45] microblaze: fix clone syscall Greg Kroah-Hartman
2013-08-18 20:35 ` [ 05/45] x86 get_unmapped_area(): use proper mmap base for bottom-up direction Greg Kroah-Hartman
2013-08-18 20:35 ` [ 06/45] fs/proc/task_mmu.c: fix buffer overflow in add_page_map() Greg Kroah-Hartman
2013-08-18 20:35 ` [ 07/45] sched: Ensure update_cfs_shares() is called for parents of continuously-running tasks Greg Kroah-Hartman
2013-08-18 20:35 ` [ 08/45] elevator: Fix a race in elevator switching Greg Kroah-Hartman
2013-08-18 20:35 ` [ 09/45] ARM: KVM: perform save/restore of PAR Greg Kroah-Hartman
2013-08-18 20:35 ` [ 10/45] ARM: KVM: add missing dsb before invalidating Stage-2 TLBs Greg Kroah-Hartman
2013-08-18 20:36 ` [ 11/45] ARM: KVM: clear exclusive monitor on all exception returns Greg Kroah-Hartman
2013-08-18 20:36 ` [ 12/45] iwl4965: set power mode early Greg Kroah-Hartman
2013-08-18 20:36 ` [ 13/45] iwl4965: reset firmware after rfkill off Greg Kroah-Hartman
2013-08-18 20:36 ` [ 14/45] mac80211: ignore HT primary channel while connected Greg Kroah-Hartman
2013-08-18 20:36 ` [ 15/45] mac80211: fix infinite loop in ieee80211_determine_chantype Greg Kroah-Hartman
2013-08-18 20:36 ` [ 16/45] mac80211: continue using disabled channels while connected Greg Kroah-Hartman
2013-08-18 20:36 ` [ 17/45] can: pcan_usb: fix wrong memcpy() bytes length Greg Kroah-Hartman
2013-08-18 20:36 ` [ 18/45] genetlink: fix family dump race Greg Kroah-Hartman
2013-08-18 20:36 ` [ 19/45] cfg80211: fix P2P GO interface teardown Greg Kroah-Hartman
2013-08-18 20:36 ` [ 20/45] ASoC: dapm: Fix empty list check in dapm_new_mux() Greg Kroah-Hartman
2013-08-18 20:36 ` [ 21/45] ASoC: cs42l52: Reorder Min/Max and update to SX_TLV for Beep Volume Greg Kroah-Hartman
2013-08-18 20:36 ` [ 22/45] ASoC: tegra: fix Tegra30 I2S capture parameter setup Greg Kroah-Hartman
2013-08-18 20:36 ` [ 23/45] ALSA: usb-audio: Fix invalid volume resolution for Logitech HD Webcam C525 Greg Kroah-Hartman
2013-08-18 20:36 ` [ 24/45] ALSA: 6fire: make buffers DMA-able (pcm) Greg Kroah-Hartman
2013-08-18 20:36 ` [ 25/45] ALSA: 6fire: make buffers DMA-able (midi) Greg Kroah-Hartman
2013-08-18 20:36 ` [ 26/45] ALSA: hda - Fix missing mute controls for CX5051 Greg Kroah-Hartman
2013-08-18 20:36 ` [ 27/45] ALSA: hda - Add pinfix for LG LW25 laptop Greg Kroah-Hartman
2013-08-18 20:36 ` [ 28/45] ALSA: hda - Add a fixup for Gateway LT27 Greg Kroah-Hartman
2013-08-19 17:42 ` Nathanael D. Noblet
2013-08-19 17:48 ` Greg Kroah-Hartman
2013-08-19 18:10 ` Takashi Iwai
2013-08-18 20:36 ` [ 29/45] nl80211: fix another nl80211_fam.attrbuf race Greg Kroah-Hartman
2013-08-18 20:36 ` [ 30/45] usb: add two quirky touchscreen Greg Kroah-Hartman
2013-08-18 20:36 ` [ 31/45] USB: ti_usb_3410_5052: fix big-endian firmware handling Greg Kroah-Hartman
2013-08-18 20:36 ` [ 32/45] USB: mos7840: fix big-endian probe Greg Kroah-Hartman
2013-08-18 20:36 ` [ 33/45] USB: mos7720: fix broken control requests Greg Kroah-Hartman
2013-08-18 20:36 ` [ 34/45] USB: keyspan: fix null-deref at disconnect and release Greg Kroah-Hartman
2013-08-18 20:36 ` [ 35/45] USB: EHCI: accept very late isochronous URBs Greg Kroah-Hartman
2013-08-18 20:36 ` [ 36/45] USB-Serial: Fix error handling of usb_wwan Greg Kroah-Hartman
2013-08-18 20:36 ` [ 37/45] PM / QoS: Fix workqueue deadlock when using pm_qos_update_request_timeout() Greg Kroah-Hartman
2013-08-18 20:36 ` [ 38/45] wusbcore: fix kernel panic when disconnecting a wireless USB->serial device Greg Kroah-Hartman
2013-08-18 20:36 ` [ 39/45] Fix TLB gather virtual address range invalidation corner cases Greg Kroah-Hartman
2013-08-18 20:36 ` [ 40/45] ARM: 7809/1: perf: fix event validation for software group leaders Greg Kroah-Hartman
2013-08-18 20:36 ` [ 41/45] m68k: Truncate base in do_div() Greg Kroah-Hartman
2013-08-18 20:39 ` Geert Uytterhoeven
2013-08-18 20:50 ` Greg Kroah-Hartman
2013-08-18 20:36 ` [ 42/45] m68k/atari: ARAnyM - Fix NatFeat module support Greg Kroah-Hartman
2013-08-18 20:36 ` [ 43/45] s390: Fix broken build Greg Kroah-Hartman
2013-08-18 20:36 ` [ 44/45] jbd2: Fix use after free after error in jbd2_journal_dirty_metadata() Greg Kroah-Hartman
2013-08-18 20:36 ` [ 45/45] cpuset: fix the return value of cpuset_write_u64() Greg Kroah-Hartman
2013-08-19 1:43 ` [ 00/45] 3.10.8-stable review Guenter Roeck
2013-08-19 3:30 ` Greg Kroah-Hartman
2013-08-19 22:48 ` Shuah Khan
2013-08-19 23:11 ` Greg Kroah-Hartman
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=20130818203621.098555466@linuxfoundation.org \
--to=gregkh@linuxfoundation.org \
--cc=acme@ghostprotocols.net \
--cc=linux-kernel@vger.kernel.org \
--cc=mccalpin@tacc.utexas.edu \
--cc=mingo@kernel.org \
--cc=paulus@samba.org \
--cc=peterz@infradead.org \
--cc=stable@vger.kernel.org \
--cc=vincent.weaver@maine.edu \
--cc=zheng.z.yan@intel.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).