linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
To: linux-kernel@vger.kernel.org, stable@vger.kernel.org
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
	alan@lxorguk.ukuu.org.uk, Vincent Palatin <vpalatin@chromium.org>,
	Duncan Laurie <dlaurie@chromium.org>,
	Olof Johansson <olofj@chromium.org>,
	"H. Peter Anvin" <hpa@linux.intel.com>
Subject: [ 09/20] x86, fpu: Avoid FPU lazy restore after suspend
Date: Thu,  6 Dec 2012 16:54:24 -0800	[thread overview]
Message-ID: <20121207005235.381635650@linuxfoundation.org> (raw)
In-Reply-To: <20121207005232.756641002@linuxfoundation.org>

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

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

From: Vincent Palatin <vpalatin@chromium.org>

commit 644c154186386bb1fa6446bc5e037b9ed098db46 upstream.

When a cpu enters S3 state, the FPU state is lost.
After resuming for S3, if we try to lazy restore the FPU for a process running
on the same CPU, this will result in a corrupted FPU context.

Ensure that "fpu_owner_task" is properly invalided when (re-)initializing a CPU,
so nobody will try to lazy restore a state which doesn't exist in the hardware.

Tested with a 64-bit kernel on a 4-core Ivybridge CPU with eagerfpu=off,
by doing thousands of suspend/resume cycles with 4 processes doing FPU
operations running. Without the patch, a process is killed after a
few hundreds cycles by a SIGFPE.

Signed-off-by: Vincent Palatin <vpalatin@chromium.org>
Cc: Duncan Laurie <dlaurie@chromium.org>
Cc: Olof Johansson <olofj@chromium.org>
Link: http://lkml.kernel.org/r/1354306532-1014-1-git-send-email-vpalatin@chromium.org
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

---
 arch/x86/include/asm/fpu-internal.h |   15 +++++++++------
 arch/x86/kernel/smpboot.c           |    5 +++++
 2 files changed, 14 insertions(+), 6 deletions(-)

--- a/arch/x86/include/asm/fpu-internal.h
+++ b/arch/x86/include/asm/fpu-internal.h
@@ -334,14 +334,17 @@ static inline void __thread_fpu_begin(st
 typedef struct { int preload; } fpu_switch_t;
 
 /*
- * FIXME! We could do a totally lazy restore, but we need to
- * add a per-cpu "this was the task that last touched the FPU
- * on this CPU" variable, and the task needs to have a "I last
- * touched the FPU on this CPU" and check them.
+ * Must be run with preemption disabled: this clears the fpu_owner_task,
+ * on this CPU.
  *
- * We don't do that yet, so "fpu_lazy_restore()" always returns
- * false, but some day..
+ * This will disable any lazy FPU state restore of the current FPU state,
+ * but if the current thread owns the FPU, it will still be saved by.
  */
+static inline void __cpu_disable_lazy_restore(unsigned int cpu)
+{
+	per_cpu(fpu_owner_task, cpu) = NULL;
+}
+
 static inline int fpu_lazy_restore(struct task_struct *new, unsigned int cpu)
 {
 	return new == percpu_read_stable(fpu_owner_task) &&
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -66,6 +66,8 @@
 #include <asm/mwait.h>
 #include <asm/apic.h>
 #include <asm/io_apic.h>
+#include <asm/i387.h>
+#include <asm/fpu-internal.h>
 #include <asm/setup.h>
 #include <asm/uv/uv.h>
 #include <linux/mc146818rtc.h>
@@ -851,6 +853,9 @@ int __cpuinit native_cpu_up(unsigned int
 
 	per_cpu(cpu_state, cpu) = CPU_UP_PREPARE;
 
+	/* the FPU context is blank, nobody can own it */
+	__cpu_disable_lazy_restore(cpu);
+
 	err = do_boot_cpu(apicid, cpu);
 	if (err) {
 		pr_debug("do_boot_cpu failed %d\n", err);



  parent reply	other threads:[~2012-12-07  0:55 UTC|newest]

Thread overview: 28+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2012-12-07  0:54 [ 00/20] 3.4.23-stable review Greg Kroah-Hartman
2012-12-07  0:54 ` [ 01/20] Dove: Attempt to fix PMU/RTC interrupts Greg Kroah-Hartman
2012-12-07  0:54 ` [ 02/20] Dove: Fix irq_to_pmu() Greg Kroah-Hartman
2012-12-07  0:54 ` [ 03/20] drm/radeon/dce4+: dont use radeon_crtc for vblank callback Greg Kroah-Hartman
2012-12-07  0:54 ` [ 04/20] drm/radeon: properly handle mc_stop/mc_resume on evergreen+ (v2) Greg Kroah-Hartman
2012-12-07  0:54 ` [ 05/20] drm/radeon: properly track the crtc not_enabled case evergreen_mc_stop() Greg Kroah-Hartman
2012-12-07  0:54 ` [ 06/20] mm/vmemmap: fix wrong use of virt_to_page Greg Kroah-Hartman
2012-12-07  0:54 ` [ 07/20] mm: soft offline: split thp at the beginning of soft_offline_page() Greg Kroah-Hartman
2012-12-07  0:54 ` [ 08/20] ARM: Kirkwood: Update PCI-E fixup Greg Kroah-Hartman
2012-12-07  0:54 ` Greg Kroah-Hartman [this message]
2012-12-07  0:54 ` [ 10/20] workqueue: exit rescuer_thread() as TASK_RUNNING Greg Kroah-Hartman
2012-12-07  0:54 ` [ 11/20] md/raid10: close race that lose writes lost when replacement completes Greg Kroah-Hartman
2012-12-07  0:54 ` [ 12/20] i7300_edac: Fix error flag testing Greg Kroah-Hartman
2012-12-07  0:54 ` [ 13/20] Revert "sched, autogroup: Stop going ahead if autogroup is disabled" Greg Kroah-Hartman
2012-12-07  0:54 ` [ 14/20] bnx2x: remove redundant warning log Greg Kroah-Hartman
2012-12-07  0:54 ` [ 15/20] s390/mm: have 16 byte aligned struct pages Greg Kroah-Hartman
2012-12-07  9:59   ` Heiko Carstens
2012-12-07  0:54 ` [ 16/20] ACPI: missing break Greg Kroah-Hartman
2012-12-07  0:54 ` [ 17/20] i915: Quirk no_lvds on Gigabyte GA-D525TUD ITX motherboard Greg Kroah-Hartman
2012-12-07  0:54 ` [ 18/20] drm/i915: Add no-lvds quirk for Supermicro X7SPA-H Greg Kroah-Hartman
2012-12-07  0:54 ` [ 19/20] pnfsblock: fix partial page buffer wirte Greg Kroah-Hartman
2012-12-07  0:54 ` [ 20/20] kbuild: Do not package /boot and /lib in make tar-pkg Greg Kroah-Hartman
2012-12-08  0:49 ` [ 00/20] 3.4.23-stable review Shuah Khan
2012-12-08  0:52   ` Shuah Khan
2012-12-08  0:59     ` Shuah Khan
2012-12-08 19:46       ` Greg Kroah-Hartman
2012-12-09  1:15         ` Shuah Khan
2012-12-08  5:10 ` satoru takeuchi

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=20121207005235.381635650@linuxfoundation.org \
    --to=gregkh@linuxfoundation.org \
    --cc=alan@lxorguk.ukuu.org.uk \
    --cc=dlaurie@chromium.org \
    --cc=hpa@linux.intel.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=olofj@chromium.org \
    --cc=stable@vger.kernel.org \
    --cc=vpalatin@chromium.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).