Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]

Groups > linux.kernel > #1377216

[PATCH 3.19.y-ckt 53/56] perf/x86/intel: Fix PEBS data source interpretation on Nehalem/Westmere

From Kamal Mostafa <kamal@canonical.com>
Newsgroups linux.kernel
Subject [PATCH 3.19.y-ckt 53/56] perf/x86/intel: Fix PEBS data source interpretation on Nehalem/Westmere
Date 2016-04-12 23:10 +0200
Message-ID <rndJn-5Cv-9@gated-at.bofh.it> (permalink)
References <rndzI-5be-21@gated-at.bofh.it>
Organization linux.* mail to news gateway

Show all headers | View raw

3.19.8-ckt19 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Andi Kleen <ak@linux.intel.com>

commit e17dc65328057c00db7e1bfea249c8771a78b30b upstream.

Jiri reported some time ago that some entries in the PEBS data source table
in perf do not agree with the SDM. We investigated and the bits
changed for Sandy Bridge, but the SDM was not updated.

perf already implements the bits correctly for Sandy Bridge
and later. This patch patches it up for Nehalem and Westmere.

Signed-off-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: jolsa@kernel.org
Link: http://lkml.kernel.org/r/1456871124-15985-1-git-send-email-andi@firstfloor.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
[ luis: backported to 3.16:
  - file rename:
    arch/x86/events/intel/core.c -> arch/x86/kernel/cpu/perf_event_intel.c
    arch/x86/events/intel/ds.c -> arch/x86/kernel/cpu/perf_event_intel_ds.c
    arch/x86/events/perf_event.h -> arch/x86/kernel/cpu/perf_event.h ]
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>

Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 arch/x86/kernel/cpu/perf_event.h          |  2 ++
 arch/x86/kernel/cpu/perf_event_intel.c    |  2 ++
 arch/x86/kernel/cpu/perf_event_intel_ds.c | 11 ++++++++++-
 3 files changed, 14 insertions(+), 1 deletion(-)

diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index 5959a0c..f2d3dfc 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -746,6 +746,8 @@ void intel_pmu_lbr_init_atom(void);
 
 void intel_pmu_lbr_init_snb(void);
 
+void intel_pmu_pebs_data_source_nhm(void);
+
 int intel_pmu_setup_lbr_filter(struct perf_event *event);
 
 int p4_pmu_init(void);
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 498b6d9..bd0ec1a 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -2410,6 +2410,7 @@ __init int intel_pmu_init(void)
 		intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_BACKEND] =
 			X86_CONFIG(.event=0xb1, .umask=0x3f, .inv=1, .cmask=1);
 
+		intel_pmu_pebs_data_source_nhm();
 		x86_add_quirk(intel_nehalem_quirk);
 
 		pr_cont("Nehalem events, ");
@@ -2472,6 +2473,7 @@ __init int intel_pmu_init(void)
 		intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_BACKEND] =
 			X86_CONFIG(.event=0xb1, .umask=0x3f, .inv=1, .cmask=1);
 
+		intel_pmu_pebs_data_source_nhm();
 		pr_cont("Westmere events, ");
 		break;
 
diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c
index ae3accf..4b4bd1b 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_ds.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c
@@ -51,7 +51,8 @@ union intel_x86_pebs_dse {
 #define OP_LH (P(OP, LOAD) | P(LVL, HIT))
 #define SNOOP_NONE_MISS (P(SNOOP, NONE) | P(SNOOP, MISS))
 
-static const u64 pebs_data_source[] = {
+/* Version for Sandy Bridge and later */
+static u64 pebs_data_source[] = {
 	P(OP, LOAD) | P(LVL, MISS) | P(LVL, L3) | P(SNOOP, NA),/* 0x00:ukn L3 */
 	OP_LH | P(LVL, L1)  | P(SNOOP, NONE),	/* 0x01: L1 local */
 	OP_LH | P(LVL, LFB) | P(SNOOP, NONE),	/* 0x02: LFB hit */
@@ -70,6 +71,14 @@ static const u64 pebs_data_source[] = {
 	OP_LH | P(LVL, UNC) | P(SNOOP, NONE), /* 0x0f: uncached */
 };
 
+/* Patch up minor differences in the bits */
+void __init intel_pmu_pebs_data_source_nhm(void)
+{
+	pebs_data_source[0x05] = OP_LH | P(LVL, L3)  | P(SNOOP, HIT);
+	pebs_data_source[0x06] = OP_LH | P(LVL, L3)  | P(SNOOP, HITM);
+	pebs_data_source[0x07] = OP_LH | P(LVL, L3)  | P(SNOOP, HITM);
+}
+
 static u64 precise_store_data(u64 status)
 {
 	union intel_x86_pebs_dse dse;
-- 
2.7.4

Back to linux.kernel | Previous | Next — Previous in thread | Next in thread | Find similar | Unroll thread

Thread

[3.19.y-ckt stable] Linux 3.19.8-ckt19 stable review Kamal Mostafa <kamal@canonical.com> - 2016-04-12 23:00 +0200
  [PATCH 3.19.y-ckt 04/56] ALSA: hda - Fix white noise on Asus N750JV headphone Kamal Mostafa <kamal@canonical.com> - 2016-04-12 23:00 +0200
  [PATCH 3.19.y-ckt 01/56] [stable-only] Revert "spi: rockchip: modify DMA max burst to 1" Kamal Mostafa <kamal@canonical.com> - 2016-04-12 23:00 +0200
  [PATCH 3.19.y-ckt 10/56] pinctrl: sh-pfc: only use dummy states for non-DT platforms Kamal Mostafa <kamal@canonical.com> - 2016-04-12 23:00 +0200
  [PATCH 3.19.y-ckt 47/56] efi: Make our variable validation list include the guid Kamal Mostafa <kamal@canonical.com> - 2016-04-12 23:10 +0200
  [PATCH 3.19.y-ckt 55/56] mwifiex: fix corner case association failure Kamal Mostafa <kamal@canonical.com> - 2016-04-12 23:10 +0200
  [PATCH 3.19.y-ckt 53/56] perf/x86/intel: Fix PEBS data source interpretation on Nehalem/Westmere Kamal Mostafa <kamal@canonical.com> - 2016-04-12 23:10 +0200
  [PATCH 3.19.y-ckt 42/56] Drivers: hv: vmbus: prevent cpu offlining on newer hypervisors Kamal Mostafa <kamal@canonical.com> - 2016-04-12 23:10 +0200
  [PATCH 3.19.y-ckt 50/56] lib/ucs2_string: Correct ucs2 -> utf8 conversion Kamal Mostafa <kamal@canonical.com> - 2016-04-12 23:10 +0200
  [PATCH 3.19.y-ckt 40/56] pinctrl: nomadik: fix pull debug print inversion Kamal Mostafa <kamal@canonical.com> - 2016-04-12 23:10 +0200
  [PATCH 3.19.y-ckt 54/56] ALSA: hda - Add new GPU codec ID 0x10de0082 to snd-hda Kamal Mostafa <kamal@canonical.com> - 2016-04-12 23:10 +0200
  [PATCH 3.19.y-ckt 27/56] ALSA: usb-audio: Minor code cleanup in create_fixed_stream_quirk() Kamal Mostafa <kamal@canonical.com> - 2016-04-12 23:10 +0200
  [PATCH 3.19.y-ckt 15/56] USB: digi_acceleport: do sanity checking for the number of ports Kamal Mostafa <kamal@canonical.com> - 2016-04-12 23:10 +0200
  [PATCH 3.19.y-ckt 44/56] lib/ucs2_string: Add ucs2 -> utf8 helper functions Kamal Mostafa <kamal@canonical.com> - 2016-04-12 23:10 +0200
  [PATCH 3.19.y-ckt 51/56] ipr: Fix out-of-bounds null overwrite Kamal Mostafa <kamal@canonical.com> - 2016-04-12 23:10 +0200
  [PATCH 3.19.y-ckt 43/56] KVM: x86: move steal time initialization to vcpu entry time Kamal Mostafa <kamal@canonical.com> - 2016-04-12 23:10 +0200
  [PATCH 3.19.y-ckt 30/56] drm/dp: move hw_mutex up the call stack Kamal Mostafa <kamal@canonical.com> - 2016-04-12 23:10 +0200
  [PATCH 3.19.y-ckt 49/56] efi: Add pstore variables to the deletion whitelist Kamal Mostafa <kamal@canonical.com> - 2016-04-12 23:10 +0200
  [PATCH 3.19.y-ckt 45/56] efi: Use ucs2_as_utf8 in efivarfs instead of open coding a bad version Kamal Mostafa <kamal@canonical.com> - 2016-04-12 23:10 +0200
  [PATCH 3.19.y-ckt 41/56] ipv6: udp: fix UDP_MIB_IGNOREDMULTI updates Kamal Mostafa <kamal@canonical.com> - 2016-04-12 23:10 +0200
  [PATCH 3.19.y-ckt 14/56] USB: cypress_m8: add endpoint sanity check Kamal Mostafa <kamal@canonical.com> - 2016-04-12 23:10 +0200
  [PATCH 3.19.y-ckt 52/56] ipr: Fix regression when loading firmware Kamal Mostafa <kamal@canonical.com> - 2016-04-12 23:10 +0200
  [PATCH 3.19.y-ckt 48/56] efi: Make efivarfs entries immutable by default Kamal Mostafa <kamal@canonical.com> - 2016-04-12 23:10 +0200
  [PATCH 3.19.y-ckt 56/56] net: phy: at803x: Request 'reset' GPIO only for AT8030 PHY Kamal Mostafa <kamal@canonical.com> - 2016-04-12 23:10 +0200
  [PATCH 3.19.y-ckt 46/56] efi: Do variable name validation tests in utf8 Kamal Mostafa <kamal@canonical.com> - 2016-04-12 23:10 +0200
  [PATCH 3.19.y-ckt 38/56] ip6_tunnel: set rtnl_link_ops before calling register_netdevice Kamal Mostafa <kamal@canonical.com> - 2016-04-12 23:10 +0200
  [PATCH 3.19.y-ckt 28/56] ALSA: usb-audio: Fix double-free in error paths after snd_usb_add_audio_stream() call Kamal Mostafa <kamal@canonical.com> - 2016-04-12 23:10 +0200
  [PATCH 3.19.y-ckt 12/56] usb: renesas_usbhs: disable TX IRQ before starting TX DMAC transfer Kamal Mostafa <kamal@canonical.com> - 2016-04-12 23:20 +0200
  [PATCH 3.19.y-ckt 16/56] ext4: add lockdep annotations for i_data_sem Kamal Mostafa <kamal@canonical.com> - 2016-04-12 23:20 +0200
  [PATCH 3.19.y-ckt 25/56] parisc: Avoid function pointers for kernel exception routines Kamal Mostafa <kamal@canonical.com> - 2016-04-12 23:20 +0200
  [PATCH 3.19.y-ckt 18/56] mm: fix invalid node in alloc_migrate_target() Kamal Mostafa <kamal@canonical.com> - 2016-04-12 23:20 +0200
  [PATCH 3.19.y-ckt 19/56] iio: st_magn: always define ST_MAGN_TRIGGER_SET_STATE Kamal Mostafa <kamal@canonical.com> - 2016-04-12 23:20 +0200
  [PATCH 3.19.y-ckt 35/56] gpio: pca953x: Use correct u16 value for register word write Kamal Mostafa <kamal@canonical.com> - 2016-04-12 23:20 +0200
  [PATCH 3.19.y-ckt 23/56] USB: serial: cp210x: Adding GE Healthcare Device ID Kamal Mostafa <kamal@canonical.com> - 2016-04-12 23:20 +0200
  [PATCH 3.19.y-ckt 22/56] USB: serial: ftdi_sio: Add support for ICP DAS I-756xU devices Kamal Mostafa <kamal@canonical.com> - 2016-04-12 23:20 +0200
  [PATCH 3.19.y-ckt 34/56] ext4: ignore quota mount options if the quota feature is enabled Kamal Mostafa <kamal@canonical.com> - 2016-04-12 23:20 +0200
  [PATCH 3.19.y-ckt 13/56] USB: mct_u232: add sanity checking in probe Kamal Mostafa <kamal@canonical.com> - 2016-04-12 23:20 +0200
  [PATCH 3.19.y-ckt 29/56] sd: Fix excessive capacity printing on devices with blocks bigger than 512 bytes Kamal Mostafa <kamal@canonical.com> - 2016-04-12 23:20 +0200
  [PATCH 3.19.y-ckt 20/56] xen/events: Mask a moving irq Kamal Mostafa <kamal@canonical.com> - 2016-04-12 23:20 +0200
  [PATCH 3.19.y-ckt 17/56] ALSA: timer: Use mod_timer() for rearming the system timer Kamal Mostafa <kamal@canonical.com> - 2016-04-12 23:20 +0200
  [PATCH 3.19.y-ckt 26/56] drm/radeon: add a dpm quirk for all R7 370 parts Kamal Mostafa <kamal@canonical.com> - 2016-04-12 23:20 +0200
  [PATCH 3.19.y-ckt 37/56] parisc: Unbreak handling exceptions from kernel modules Kamal Mostafa <kamal@canonical.com> - 2016-04-12 23:20 +0200
  [PATCH 3.19.y-ckt 32/56] ALSA: hda - fix front mic problem for a HP desktop Kamal Mostafa <kamal@canonical.com> - 2016-04-12 23:20 +0200
  [PATCH 3.19.y-ckt 39/56] net: bcmgenet: fix skb_len in bcmgenet_xmit_single() Kamal Mostafa <kamal@canonical.com> - 2016-04-12 23:20 +0200
  [PATCH 3.19.y-ckt 09/56] powerpc/mm: Fixup preempt underflow with huge pages Kamal Mostafa <kamal@canonical.com> - 2016-04-12 23:20 +0200
  [PATCH 3.19.y-ckt 33/56] KVM: x86: Inject pending interrupt even if pending nmi exist Kamal Mostafa <kamal@canonical.com> - 2016-04-12 23:20 +0200
  [PATCH 3.19.y-ckt 21/56] rbd: use GFP_NOIO consistently for request allocations Kamal Mostafa <kamal@canonical.com> - 2016-04-12 23:20 +0200
  [PATCH 3.19.y-ckt 24/56] USB: option: add "D-Link DWM-221 B1" device id Kamal Mostafa <kamal@canonical.com> - 2016-04-12 23:20 +0200
  [PATCH 3.19.y-ckt 31/56] drm/udl: Use unlocked gem unreferencing Kamal Mostafa <kamal@canonical.com> - 2016-04-12 23:20 +0200
  [PATCH 3.19.y-ckt 36/56] parisc: Fix kernel crash with reversed copy_from_user() Kamal Mostafa <kamal@canonical.com> - 2016-04-12 23:20 +0200
  [PATCH 3.19.y-ckt 11/56] usb: renesas_usbhs: avoid NULL pointer derefernce in usbhsf_pkt_handler() Kamal Mostafa <kamal@canonical.com> - 2016-04-12 23:20 +0200
  [PATCH 3.19.y-ckt 05/56] ALSA: hda - Apply fix for white noise on Asus N550JV, too Kamal Mostafa <kamal@canonical.com> - 2016-04-12 23:30 +0200
  [PATCH 3.19.y-ckt 07/56] hwmon: (max1111) Return -ENODEV from max1111_read_channel if not instantiated Kamal Mostafa <kamal@canonical.com> - 2016-04-12 23:30 +0200
  [PATCH 3.19.y-ckt 02/56] PKCS#7: pkcs7_validate_trust(): initialize the _trusted output argument Kamal Mostafa <kamal@canonical.com> - 2016-04-12 23:30 +0200
  [PATCH 3.19.y-ckt 08/56] drm/radeon: add another R7 370 quirk Kamal Mostafa <kamal@canonical.com> - 2016-04-12 23:30 +0200
  [PATCH 3.19.y-ckt 06/56] drm/radeon: add a dpm quirk for sapphire Dual-X R7 370 2G D5 Kamal Mostafa <kamal@canonical.com> - 2016-04-12 23:30 +0200
  [PATCH 3.19.y-ckt 03/56] ALSA: hda - Asus N750JV external subwoofer fixup Kamal Mostafa <kamal@canonical.com> - 2016-04-12 23:30 +0200

csiph-web