A workaround for AMD CPU family 11h erratum 311 might cause that the
P-state Status Register shows a "current P-state" which is larger than
the "current P-state limit" in P-state Current Limit Register. For the
wrong P-state value there is no ACPI _PSS object defined and
powernow-k8/cpufreq can't determine the proper CPU frequency for that
state.
As a consequence this can cause a panic during boot (potentially with
all recent kernel versions -- at least I have reproduced it with
various 2.6.27 kernels and with the current .28 series), as an
example:
powernow-k8: Found 1 AMD Turion(tm)X2 Ultra DualCore Mobile ZM-82 processors (2 \
)
powernow-k8: 0 : pstate 0 (2200 MHz)
powernow-k8: 1 : pstate 1 (1100 MHz)
powernow-k8: 2 : pstate 2 (600 MHz)
BUG: unable to handle kernel paging request at ffff88086e7528b8
IP: [<ffffffff80486361>] cpufreq_stats_update+0x4a/0x5f
PGD 202063 PUD 0
Oops: 0002 [#1] SMP
last sysfs file:
CPU 1
Modules linked in:
Pid: 1, comm: swapper Not tainted 2.6.28-rc3-dirty #16
RIP: 0010:[<ffffffff80486361>] [<ffffffff80486361>] cpufreq_stats_update+0x4a/0\
f
Synaptics claims to have extended capabilities, but I'm not able to read them.<6\
6
RAX: 0000000000000000 RBX: 0000000000000001 RCX: ffff88006e7528c0
RDX: 00000000ffffffff RSI: ffff88006e54af00 RDI: ffffffff808f056c
RBP: 00000000fffee697 R08: 0000000000000003 R09: ffff88006e73f080
R10: 0000000000000001 R11: 00000000002191c0 R12: ffff88006fb83c10
R13: 00000000ffffffff R14: 0000000000000001 R15: 0000000000000000
FS: 0000000000000000(0000) GS:ffff88006fb50740(0000) knlGS:0000000000000000
Unable to initialize Synaptics hardware.
CS: 0010 DS: 0018 ES: 0018 CR0: 000000008005003b
CR2: ffff88086e7528b8 CR3: 0000000000201000 CR4: 00000000000006e0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400
Process swapper (pid: 1, threadinfo ffff88006fb82000, task ffff88006fb816d0)
Stack:
ffff88006e74da50 0000000000000000 ffff88006e54af00 ffffffff804863c7
ffff88006e74da50 0000000000000000 00000000ffffffff 0000000000000000
ffff88006fb83c10 ffffffff8024b46c ffffffff808f0560 ffff88006fb83c10
Call Trace:
[<ffffffff804863c7>] ? cpufreq_stat_notifier_trans+0x51/0x83
[<ffffffff8024b46c>] ? notifier_call_chain+0x29/0x4c
[<ffffffff8024b561>] ? __srcu_notifier_call_chain+0x46/0x61
[<ffffffff8048496d>] ? cpufreq_notify_transition+0x93/0xa9
[<ffffffff8021ab8d>] ? powernowk8_target+0x1e8/0x5f3
[<ffffffff80486687>] ? cpufreq_governor_performance+0x1b/0x20
[<ffffffff80484886>] ? __cpufreq_governor+0x71/0xa8
[<ffffffff80484b21>] ? __cpufreq_set_policy+0x101/0x13e
[<ffffffff80485bcd>] ? cpufreq_add_dev+0x3f0/0x4cd
[<ffffffff8048577a>] ? handle_update+0x0/0x8
[<ffffffff803c2062>] ? sysdev_driver_register+0xb6/0x10d
[<ffffffff8056592c>] ? powernowk8_init+0x0/0x7e
[<ffffffff8048604c>] ? cpufreq_register_driver+0x8f/0x140
[<ffffffff80209056>] ? _stext+0x56/0x14f
[<ffffffff802c2234>] ? proc_register+0x122/0x17d
[<ffffffff802c23a0>] ? create_proc_entry+0x73/0x8a
[<ffffffff8025c259>] ? register_irq_proc+0x92/0xaa
[<ffffffff8025c2c8>] ? init_irq_proc+0x57/0x69
[<ffffffff807fc85f>] ? kernel_init+0x116/0x169
[<ffffffff8020cc79>] ? child_rip+0xa/0x11
[<ffffffff807fc749>] ? kernel_init+0x0/0x169
[<ffffffff8020cc6f>] ? child_rip+0x0/0x11
Code: 05 c5 83 36 00 48 c7 c2 48 5d 86 80 48 8b 04 d8 48 8b 40 08 48 8b 34 02 48\
RIP [<ffffffff80486361>] cpufreq_stats_update+0x4a/0x5f
RSP <ffff88006fb83b20>
CR2: ffff88086e7528b8
---[ end trace 0678bac75e67a2f7 ]---
Kernel panic - not syncing: Attempted to kill init!
In short, aftereffect of the wrong P-state is that
cpufreq_stats_update() uses "-1" as index for some array in
cpufreq_stats_update (unsigned int cpu)
{
...
if (stat->time_in_state)
stat->time_in_state[stat->last_index] =
cputime64_add(stat->time_in_state[stat->last_index],
cputime_sub(cur_time, stat->last_time));
...
}
Fortunately, the wrong P-state value is returned only if the core is
in P-state 0. This fix solves the problem by detecting the
out-of-range P-state, ignoring it, and using "0" instead.
Cc: Mark Langsdorf <mark.langsdorf@xxxxxxx>
Signed-off-by: Andreas Herrmann <andreas.herrmann3@xxxxxxx>
---
arch/x86/kernel/cpu/cpufreq/powernow-k8.c | 18 +++++++++++++++---
arch/x86/kernel/cpu/cpufreq/powernow-k8.h | 17 ++++++++++++++++-
2 files changed, 31 insertions(+), 4 deletions(-)
Ingo,
New patch -- addressing your comments.
Will you apply it, or will Linus do it?
(In the end it's important that it goes into .28.)
Thanks,
Andreas
diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
index d3dcd58..7f05f44 100644
--- a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
+++ b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
@@ -115,9 +115,20 @@ static int query_current_values_with_pending_wait(struct powernow_k8_data *data)
u32 i = 0;
if (cpu_family == CPU_HW_PSTATE) {
- rdmsr(MSR_PSTATE_STATUS, lo, hi);
- i = lo & HW_PSTATE_MASK;
- data->currpstate = i;
+ if (data->currpstate == HW_PSTATE_INVALID) {
+ /* read (initial) hw pstate if not yet set */
+ rdmsr(MSR_PSTATE_STATUS, lo, hi);
+ i = lo & HW_PSTATE_MASK;
+
+ /*
+ * a workaround for family 11h erratum 311 might cause
+ * an "out-of-range Pstate if the core is in Pstate-0
+ */
+ if (i >= data->numps)
+ data->currpstate = HW_PSTATE_0;
+ else
+ data->currpstate = i;
+ }
return 0;
}
do {
@@ -1121,6 +1132,7 @@ static int __cpuinit powernowk8_cpu_init(struct cpufreq_policy *pol)
}
data->cpu = pol->cpu;
+ data->currpstate = HW_PSTATE_INVALID;
if (powernow_k8_cpu_init_acpi(data)) {
/*
diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k8.h b/arch/x86/kernel/cpu/cpufreq/powernow-k8.h
index ab48cfe..65cfb5d 100644
--- a/arch/x86/kernel/cpu/cpufreq/powernow-k8.h
+++ b/arch/x86/kernel/cpu/cpufreq/powernow-k8.h
@@ -5,6 +5,19 @@
* http://www.gnu.org/licenses/gpl.html
*/
+
+enum pstate {
+ HW_PSTATE_INVALID = 0xff,
+ HW_PSTATE_0 = 0,
+ HW_PSTATE_1 = 1,
+ HW_PSTATE_2 = 2,
+ HW_PSTATE_3 = 3,
+ HW_PSTATE_4 = 4,
+ HW_PSTATE_5 = 5,
+ HW_PSTATE_6 = 6,
+ HW_PSTATE_7 = 7,
+};
+
struct powernow_k8_data {
unsigned int cpu;
@@ -23,7 +36,9 @@ struct powernow_k8_data {
u32 exttype; /* extended interface = 1 */
/* keep track of the current fid / vid or pstate */
- u32 currvid, currfid, currpstate;
+ u32 currvid;
+ u32 currfid;
+ enum pstate currpstate;
/* the powernow_table includes all frequency and vid/fid pairings:
* fid are the lower 8 bits of the index, vid are the upper 8 bits.
--
1.6.0.4
--
To unsubscribe from this list: send the line "unsubscribe cpufreq" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
