stable.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
To: linux-kernel@vger.kernel.org
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
	stable@vger.kernel.org,
	Linus Torvalds <torvalds@linux-foundation.org>,
	Stephane Eranian <eranian@google.com>
Subject: [ 17/48] perf,x86: fix kernel crash with PEBS/BTS after suspend/resume
Date: Mon, 18 Mar 2013 14:08:25 -0700	[thread overview]
Message-ID: <20130318210811.466798627@linuxfoundation.org> (raw)
In-Reply-To: <20130318210810.247845918@linuxfoundation.org>

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

------------------

From: Stephane Eranian <eranian@google.com>

commit 1d9d8639c063caf6efc2447f5f26aa637f844ff6 upstream.

This patch fixes a kernel crash when using precise sampling (PEBS)
after a suspend/resume. Turns out the CPU notifier code is not invoked
on CPU0 (BP). Therefore, the DS_AREA (used by PEBS) is not restored properly
by the kernel and keeps it power-on/resume value of 0 causing any PEBS
measurement to crash when running on CPU0.

The workaround is to add a hook in the actual resume code to restore
the DS Area MSR value. It is invoked for all CPUS. So for all but CPU0,
the DS_AREA will be restored twice but this is harmless.

Reported-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Stephane Eranian <eranian@google.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

---
 arch/x86/kernel/cpu/perf_event_intel_ds.c |    8 ++++++++
 arch/x86/power/cpu.c                      |    2 ++
 include/linux/perf_event.h                |    2 ++
 3 files changed, 12 insertions(+)

--- a/arch/x86/kernel/cpu/perf_event_intel_ds.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c
@@ -723,3 +723,11 @@ void intel_ds_init(void)
 		}
 	}
 }
+
+void perf_restore_debug_store(void)
+{
+	if (!x86_pmu.bts && !x86_pmu.pebs)
+		return;
+
+	init_debug_store_on_cpu(smp_processor_id());
+}
--- a/arch/x86/power/cpu.c
+++ b/arch/x86/power/cpu.c
@@ -11,6 +11,7 @@
 #include <linux/suspend.h>
 #include <linux/export.h>
 #include <linux/smp.h>
+#include <linux/perf_event.h>
 
 #include <asm/pgtable.h>
 #include <asm/proto.h>
@@ -227,6 +228,7 @@ static void __restore_processor_state(st
 	do_fpu_end();
 	x86_platform.restore_sched_clock_state();
 	mtrr_bp_restore();
+	perf_restore_debug_store();
 }
 
 /* Needed by apm.c */
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -1290,6 +1290,7 @@ extern void perf_swevent_put_recursion_c
 extern void perf_event_enable(struct perf_event *event);
 extern void perf_event_disable(struct perf_event *event);
 extern void perf_event_task_tick(void);
+extern void perf_restore_debug_store(void);
 #else
 static inline void
 perf_event_task_sched_in(struct task_struct *prev,
@@ -1328,6 +1329,7 @@ static inline void perf_swevent_put_recu
 static inline void perf_event_enable(struct perf_event *event)		{ }
 static inline void perf_event_disable(struct perf_event *event)		{ }
 static inline void perf_event_task_tick(void)				{ }
+static inline void perf_restore_debug_store(void)			{ }
 #endif
 
 #define perf_output_put(handle, x) perf_output_copy((handle), &(x), sizeof(x))



  parent reply	other threads:[~2013-03-18 21:08 UTC|newest]

Thread overview: 51+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2013-03-18 21:08 [ 00/48] 3.4.37-stable review Greg Kroah-Hartman
2013-03-18 21:08 ` [ 01/48] qcaux: add Franklin U600 Greg Kroah-Hartman
2013-03-18 21:08 ` [ 02/48] xen/pciback: Dont disable a PCI device that is already disabled Greg Kroah-Hartman
2013-03-18 21:08 ` [ 03/48] virtio: rng: disallow multiple device registrations, fixes crashes Greg Kroah-Hartman
2013-03-18 21:08 ` [ 04/48] USB: option: add Huawei E5331 Greg Kroah-Hartman
2013-03-18 21:08 ` [ 05/48] USB: cdc-wdm: fix buffer overflow Greg Kroah-Hartman
2013-03-18 21:08 ` [ 06/48] usb: cp210x new Vendor/Device IDs Greg Kroah-Hartman
2013-03-18 21:08 ` [ 07/48] USB: added support for Cinterions products AH6 and PLS8 Greg Kroah-Hartman
2013-03-18 21:08 ` [ 08/48] usb: serial: Add Rigblaster Advantage to device table Greg Kroah-Hartman
2013-03-18 21:08 ` [ 09/48] USB: storage: fix Huawei mode switching regression Greg Kroah-Hartman
2013-03-18 21:08 ` [ 10/48] USB: EHCI: dont check DMA values in QH overlays Greg Kroah-Hartman
2013-03-18 21:08 ` [ 11/48] staging: vt6656: Fix oops on resume from suspend Greg Kroah-Hartman
2013-03-18 21:08 ` [ 12/48] signal: always clear sa_restorer on execve Greg Kroah-Hartman
2013-03-18 21:08 ` [ 13/48] ext3: Fix format string issues Greg Kroah-Hartman
2013-03-18 21:08 ` [ 14/48] serial: 8250_pci: add support for another kind of NetMos Technology PCI 9835 Multi-I/O Controller Greg Kroah-Hartman
2013-03-18 21:08 ` [ 15/48] tty: serial: fix typo "ARCH_S5P6450" Greg Kroah-Hartman
2013-03-18 21:08 ` [ 16/48] TTY: do not reset masters packet mode Greg Kroah-Hartman
2013-03-18 21:08 ` Greg Kroah-Hartman [this message]
2013-03-18 21:08 ` [ 18/48] ALSA: seq: Fix missing error handling in snd_seq_timer_open() Greg Kroah-Hartman
2013-03-18 21:08 ` [ 19/48] hwmon: (pmbus/ltc2978) Fix temperature reporting Greg Kroah-Hartman
2013-03-18 21:08 ` [ 20/48] hwmon: (lineage-pem) Add missing terminating entry for pem_[input|fan]_attributes Greg Kroah-Hartman
2013-03-18 21:08 ` [ 21/48] w1: fix oops when w1_search is called from netlink connector Greg Kroah-Hartman
2013-03-18 21:08 ` [ 22/48] powerpc: Fix STAB initialization Greg Kroah-Hartman
2013-03-18 21:08 ` [ 23/48] powerpc: Fix cputable entry for 970MP rev 1.0 Greg Kroah-Hartman
2013-03-18 21:08 ` [ 24/48] selinux: use GFP_ATOMIC under spin_lock Greg Kroah-Hartman
2013-03-18 21:08 ` [ 25/48] perf,x86: fix wrmsr_on_cpu() warning on suspend/resume Greg Kroah-Hartman
2013-03-18 21:08 ` [ 26/48] perf,x86: fix link failure for non-Intel configs Greg Kroah-Hartman
2013-03-18 21:08 ` [ 27/48] s390: critical section cleanup vs. machine checks Greg Kroah-Hartman
2013-03-18 21:08 ` [ 28/48] s390/mm: fix flush_tlb_kernel_range() Greg Kroah-Hartman
2013-03-18 21:08 ` [ 29/48] btrfs: use rcu_barrier() to wait for bdev puts at unmount Greg Kroah-Hartman
2013-03-18 21:08 ` [ 30/48] atmel_lcdfb: fix 16-bpp modes on older SOCs Greg Kroah-Hartman
2013-03-18 21:08 ` [ 31/48] drm/i915: EBUSY status handling added to i915_gem_fault() Greg Kroah-Hartman
2013-03-18 21:08 ` [ 32/48] hwmon: (sht15) Fix memory leak if regulator_enable() fails Greg Kroah-Hartman
2013-03-18 21:08 ` [ 33/48] block: use i_size_write() in bd_set_size() Greg Kroah-Hartman
2013-03-18 21:08 ` [ 34/48] loopdev: fix a deadlock Greg Kroah-Hartman
2013-03-18 21:08 ` [ 35/48] loopdev: remove an user triggerable oops Greg Kroah-Hartman
2013-03-18 21:08 ` [ 36/48] drm/i915: Increase the RC6p threshold Greg Kroah-Hartman
2013-03-18 21:08 ` [ 37/48] l2tp: Restore socket refcount when sendmsg succeeds Greg Kroah-Hartman
2013-03-18 21:08 ` [ 38/48] rds: limit the size allocated by rds_message_alloc() Greg Kroah-Hartman
2013-03-18 21:08 ` [ 39/48] net: ipv6: Dont purge default router if accept_ra=2 Greg Kroah-Hartman
2013-03-18 21:08 ` [ 40/48] tcp: fix double-counted receiver RTT when leaving receiver fast path Greg Kroah-Hartman
2013-03-18 21:08 ` [ 41/48] tun: add a missing nf_reset() in tun_net_xmit() Greg Kroah-Hartman
2013-03-18 21:08 ` [ 42/48] macvlan: Set IFF_UNICAST_FLT flag to prevent unnecessary promisc mode Greg Kroah-Hartman
2013-03-18 21:08 ` [ 43/48] netlabel: correctly list all the static label mappings Greg Kroah-Hartman
2013-03-18 21:08 ` [ 44/48] bridging: fix rx_handlers return code Greg Kroah-Hartman
2013-03-18 21:08 ` [ 45/48] ipv6: stop multicast forwarding to process interface scoped addresses Greg Kroah-Hartman
2013-03-18 21:08 ` [ 46/48] rtnl: fix info leak on RTM_GETLINK request for VF devices Greg Kroah-Hartman
2013-03-18 21:08 ` [ 47/48] dcbnl: fix various netlink info leaks Greg Kroah-Hartman
2013-03-18 21:08 ` [ 48/48] 6lowpan: Fix endianness issue in is_addr_link_local() Greg Kroah-Hartman
2013-03-19  0:50 ` [ 00/48] 3.4.37-stable review Shuah Khan
2013-03-19  0:57   ` Parag Warudkar

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=20130318210811.466798627@linuxfoundation.org \
    --to=gregkh@linuxfoundation.org \
    --cc=eranian@google.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=stable@vger.kernel.org \
    --cc=torvalds@linux-foundation.org \
    /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).