On 03/13/2013 10:27 AM, Changlong Xie wrote:
> Hi Len,
>
> FYI, since 3.9-rc1 our three NHM EP/EX LKP(linux kernel performance) test servers
> except SNB/IVB/WSM hung up unexpectly.
>
> We did git bisect for about 8 times on all servers, it said that the first bad commit is ac3ebafa.
>
> commit ac3ebafa81af76d65e4fb45c6388f08e90ddcc6d
> Author: Daniel Lezcano <daniel.lezcano@xxxxxxxxxx>
> Date: Mon Feb 4 22:44:43 2013 +0000
fixing patch for review:
-----------------------
>From 78a74aea386b0969909c2e4ae388024ce71fdb18 Mon Sep 17 00:00:00 2001
From: Alex Shi <alex.shi@xxxxxxxxx>
Date: Tue, 26 Mar 2013 22:57:47 +0800
Subject: [PATCH] cpuidle/acpi: recover percpu acpi processor cstate
Commit: ac3ebafa81af76d6 "ACPI / idle: remove usage of the statedata"
change the percpu processor cstate to a unify unique cstate in acpi
idle. That cause all our NHM box boot hang or panic.
2178751 Task dump for CPU 1:^M
2178752 swapper/1 R running task 6736 0 1
0x00000000^M
2178753 ffff8801e8029dc8 ffffffff8101cf96 ffff8801e8029e28
ffffffff813d294b^M
2178754 0000000000000f99 0000000000000003 00000000003cf654
0000000025c17d03^M
2178755 ffff8801e8029e38 ffff8801e74fc000 00000002590dc5c4
ffffffff8163cdb0^M
2178756 Call Trace:^M
2178757 [<ffffffff8101cf96>] ? acpi_processor_ffh_cstate_enter+0x2d/0x2f^M
2178758 [<ffffffff813d294b>] acpi_idle_enter_bm+0x1b1/0x236^M
2178759 [<ffffffff8163cdb0>] ? disable_cpuidle+0x10/0x10^M
2178760 [<ffffffff8163cdc2>] cpuidle_enter+0x12/0x14^M
2178761 [<ffffffff8163d286>] cpuidle_wrap_enter+0x2f/0x6d^M
2178762 [<ffffffff8163d2d4>] cpuidle_enter_tk+0x10/0x12^M
2178763 [<ffffffff8163cdd6>] cpuidle_enter_state+0x12/0x3a^M
2178764 [<ffffffff8163d4a7>] cpuidle_idle_call+0xe8/0x161^M
2178765 [<ffffffff81008d99>] cpu_idle+0x5e/0xa4^M
2178766 [<ffffffff8174c6c1>] start_secondary+0x1a9/0x1ad^M
2178767 Task dump for CPU 2:^M
In fact, the acpi idle bases on percpu cstate difference assumption, the
infrastructure use many percpu structures to implement self.
Just unique acpi_processor_cx is far far not enough.
This patch just is a quick fix by introducing back the percpu cstates.
And keep driver_data away.
If someone really want to unify the acpi cstates, please make sure whole
software infrastructure changed and get the grant from hardware,
include many kinds of BIOS setting.
Signed-off-by: Alex Shi <alex.shi@xxxxxxxxx>
---
drivers/acpi/processor_idle.c | 13 +++++++------
1 file changed, 7 insertions(+), 6 deletions(-)
diff --git a/drivers/acpi/processor_idle.c b/drivers/acpi/processor_idle.c
index fc95308..ee255c6 100644
--- a/drivers/acpi/processor_idle.c
+++ b/drivers/acpi/processor_idle.c
@@ -66,7 +66,8 @@ module_param(latency_factor, uint, 0644);
static DEFINE_PER_CPU(struct cpuidle_device *, acpi_cpuidle_device);
-static struct acpi_processor_cx *acpi_cstate[CPUIDLE_STATE_MAX];
+static DEFINE_PER_CPU(struct acpi_processor_cx * [CPUIDLE_STATE_MAX],
+ acpi_cstate);
static int disabled_by_idle_boot_param(void)
{
@@ -722,7 +723,7 @@ static int acpi_idle_enter_c1(struct cpuidle_device *dev,
struct cpuidle_driver *drv, int index)
{
struct acpi_processor *pr;
- struct acpi_processor_cx *cx = acpi_cstate[index];
+ struct acpi_processor_cx *cx = per_cpu(acpi_cstate[index], dev->cpu);
pr = __this_cpu_read(processors);
@@ -745,7 +746,7 @@ static int acpi_idle_enter_c1(struct cpuidle_device *dev,
*/
static int acpi_idle_play_dead(struct cpuidle_device *dev, int index)
{
- struct acpi_processor_cx *cx = acpi_cstate[index];
+ struct acpi_processor_cx *cx = per_cpu(acpi_cstate[index], dev->cpu);
ACPI_FLUSH_CPU_CACHE();
@@ -775,7 +776,7 @@ static int acpi_idle_enter_simple(struct cpuidle_device *dev,
struct cpuidle_driver *drv, int index)
{
struct acpi_processor *pr;
- struct acpi_processor_cx *cx = acpi_cstate[index];
+ struct acpi_processor_cx *cx = per_cpu(acpi_cstate[index], dev->cpu);
pr = __this_cpu_read(processors);
@@ -833,7 +834,7 @@ static int acpi_idle_enter_bm(struct cpuidle_device *dev,
struct cpuidle_driver *drv, int index)
{
struct acpi_processor *pr;
- struct acpi_processor_cx *cx = acpi_cstate[index];
+ struct acpi_processor_cx *cx = per_cpu(acpi_cstate[index], dev->cpu);
pr = __this_cpu_read(processors);
@@ -960,7 +961,7 @@ static int acpi_processor_setup_cpuidle_cx(struct acpi_processor *pr,
!(acpi_gbl_FADT.flags & ACPI_FADT_C2_MP_SUPPORTED))
continue;
#endif
- acpi_cstate[count] = cx;
+ per_cpu(acpi_cstate[count], dev->cpu) = cx;
count++;
if (count == CPUIDLE_STATE_MAX)
--
1.7.12
--
To unsubscribe from this list: send the line "unsubscribe linux-acpi" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
