On Mon, May 20, 2013 at 05:24:05PM +0800, Michael Wang wrote:
> >> diff --git a/drivers/cpufreq/cpufreq_governor.c
> >> b/drivers/cpufreq/cpufreq_governor.c
> >> index 443442d..449be88 100644
> >> --- a/drivers/cpufreq/cpufreq_governor.c
> >> +++ b/drivers/cpufreq/cpufreq_governor.c
> >> @@ -26,6 +26,7 @@
> >> #include <linux/tick.h>
> >> #include <linux/types.h>
> >> #include <linux/workqueue.h>
> >> +#include <linux/cpu.h>
> >>
> >> #include "cpufreq_governor.h"
> >>
> >> @@ -180,8 +181,10 @@ void gov_queue_work(struct dbs_data *dbs_data,
> >> struct cpufreq_policy *policy,
> >> if (!all_cpus) {
> >> __gov_queue_work(smp_processor_id(), dbs_data, delay);
> >> } else {
> >> + get_online_cpus();
> >> for_each_cpu(i, policy->cpus)
> >> __gov_queue_work(i, dbs_data, delay);
> >> + put_online_cpus();
> >> }
> >> }
> >> EXPORT_SYMBOL_GPL(gov_queue_work);
> >>
> >> This is supposed to make WARN disappear, if it works, then BINGO :)
> >
> > Let people test it and then we can talk :)
>
> Agree :)
>
> Borislav, would you like to take a try?
>
> If this fix cause other troubles, you could try get_cpu() or disable irq
> also.
I just confirmed that policy->cpus contains offlined cores with this:
diff --git a/drivers/cpufreq/cpufreq_governor.c b/drivers/cpufreq/cpufreq_governor.c
index 5af40ad82d23..e8c25f71e9b6 100644
--- a/drivers/cpufreq/cpufreq_governor.c
+++ b/drivers/cpufreq/cpufreq_governor.c
@@ -169,6 +169,9 @@ static inline void __gov_queue_work(int cpu, struct dbs_data *dbs_data,
{
struct cpu_dbs_common_info *cdbs = dbs_data->cdata->get_cpu_cdbs(cpu);
+ if (WARN_ON(!cpu_online(cpu)))
+ return;
+
mod_delayed_work_on(cpu, system_wq, &cdbs->work, delay);
}
see splats collection below.
And I don't think your fix above addresses the issue for the simple
reason that if cpus go offline *before* you do get_online_cpus(), then
policy->cpus will already contain offlined cpus.
Rather, a better fix would be, IMHO, to do this (it works here, of course):
---
diff --git a/drivers/cpufreq/cpufreq_governor.c b/drivers/cpufreq/cpufreq_governor.c
index 5af40ad82d23..58541b164494 100644
--- a/drivers/cpufreq/cpufreq_governor.c
+++ b/drivers/cpufreq/cpufreq_governor.c
@@ -17,6 +17,7 @@
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <asm/cputime.h>
+#include <linux/cpu.h>
#include <linux/cpufreq.h>
#include <linux/cpumask.h>
#include <linux/export.h>
@@ -169,7 +170,15 @@ static inline void __gov_queue_work(int cpu, struct dbs_data *dbs_data,
{
struct cpu_dbs_common_info *cdbs = dbs_data->cdata->get_cpu_cdbs(cpu);
+ get_online_cpus();
+
+ if (!cpu_online(cpu))
+ goto out;
+
mod_delayed_work_on(cpu, system_wq, &cdbs->work, delay);
+
+ out:
+ put_online_cpus();
}
void gov_queue_work(struct dbs_data *dbs_data, struct cpufreq_policy *policy,
--
[ 94.386340] EXT4-fs (sda7): re-mounted. Opts: (null)
[ 96.520362] kvm: exiting hardware virtualization
[ 96.637687] ACPI: Preparing to enter system sleep state S5
[ 96.643506] Disabling non-boot CPUs ...
[ 96.855499] ------------[ cut here ]------------
[ 96.860172] WARNING: at drivers/cpufreq/cpufreq_governor.c:172 gov_queue_work+0xf0/0x110()
[ 96.868501] Modules linked in: ext2 vfat fat loop usbhid snd_hda_codec_hdmi coretemp kvm_intel kvm snd_hda_codec_realtek snd_hda_intel snd_hda_codec ehci_pci xhci_hcd ehci_hcd usbcore crc32_pclmul crc32c_intel snd_hwdep snd_pcm snd_page_alloc snd_timer ghash_clmulni_intel snd aesni_intel aes_x86_64 glue_helper sb_edac edac_core acpi_cpufreq mperf pcspkr lrw gf128mul ablk_helper cryptd iTCO_wdt iTCO_vendor_support evdev soundcore lpc_ich mfd_core processor dcdbas i2c_i801 usb_common button microcode
[ 96.914238] CPU: 0 PID: 315 Comm: kworker/1:2 Tainted: G W 3.10.0-rc1+ #2
[ 96.921969] Hardware name: Dell Inc. Precision T3600/0PTTT9, BIOS A08 01/24/2013
[ 96.929424] Workqueue: events od_dbs_timer
[ 96.933574] 0000000000000009 ffff88043a08bc78 ffffffff8161445c ffff88043a08bcb8
[ 96.941085] ffffffff8103e540 ffff88043b712a80 0000000000000001 ffff88043a296400
[ 96.948602] ffff88043b712a80 ffffffff81cdc910 0000000000000001 ffff88043a08bcc8
[ 96.956123] Call Trace:
[ 96.958602] [<ffffffff8161445c>] dump_stack+0x19/0x1b
[ 96.963801] [<ffffffff8103e540>] warn_slowpath_common+0x70/0xa0
[ 96.969858] [<ffffffff8103e58a>] warn_slowpath_null+0x1a/0x20
[ 96.975735] [<ffffffff814f6bf0>] gov_queue_work+0xf0/0x110
[ 96.981359] [<ffffffff814f60bb>] od_dbs_timer+0xcb/0x170
[ 96.986808] [<ffffffff8105e75d>] process_one_work+0x1fd/0x540
[ 96.992691] [<ffffffff8105e6f2>] ? process_one_work+0x192/0x540
[ 96.998756] [<ffffffff8105ef22>] worker_thread+0x122/0x380
[ 97.004371] [<ffffffff8105ee00>] ? rescuer_thread+0x320/0x320
[ 97.010256] [<ffffffff8106634a>] kthread+0xea/0xf0
[ 97.015185] [<ffffffff81066260>] ? flush_kthread_worker+0x150/0x150
[ 97.021605] [<ffffffff81623d9c>] ret_from_fork+0x7c/0xb0
[ 97.027049] [<ffffffff81066260>] ? flush_kthread_worker+0x150/0x150
[ 97.033457] ---[ end trace d36d91c626ac81a0 ]---
[ 97.039221] ------------[ cut here ]------------
[ 97.039227] ------------[ cut here ]------------
[ 97.039229] WARNING: at drivers/cpufreq/cpufreq_governor.c:172 gov_queue_work+0xf0/0x110()
[ 97.039243] Modules linked in: ext2 vfat fat loop usbhid snd_hda_codec_hdmi coretemp kvm_intel kvm snd_hda_codec_realtek snd_hda_intel snd_hda_codec ehci_pci xhci_hcd ehci_hcd usbcore crc32_pclmul crc32c_intel snd_hwdep snd_pcm snd_page_alloc snd_timer ghash_clmulni_intel snd aesni_intel aes_x86_64 glue_helper sb_edac edac_core acpi_cpufreq mperf pcspkr lrw gf128mul ablk_helper cryptd iTCO_wdt iTCO_vendor_support evdev soundcore lpc_ich mfd_core processor dcdbas i2c_i801 usb_common button microcode
[ 97.039245] CPU: 4 PID: 82 Comm: kworker/2:1 Tainted: G W 3.10.0-rc1+ #2
[ 97.039245] Hardware name: Dell Inc. Precision T3600/0PTTT9, BIOS A08 01/24/2013
[ 97.039248] Workqueue: events od_dbs_timer
[ 97.039250] 0000000000000009 ffff88043b5cfc78 ffffffff8161445c ffff88043b5cfcb8
[ 97.039251] ffffffff8103e540 ffff88043b712a80 0000000000000002 ffff88043a295e00
[ 97.039253] ffff88043b712a80 ffffffff81cdc910 0000000000000002 ffff88043b5cfcc8
[ 97.039253] Call Trace:
[ 97.039255] [<ffffffff8161445c>] dump_stack+0x19/0x1b
[ 97.039257] [<ffffffff8103e540>] warn_slowpath_common+0x70/0xa0
[ 97.039258] [<ffffffff8103e58a>] warn_slowpath_null+0x1a/0x20
[ 97.039259] [<ffffffff814f6bf0>] gov_queue_work+0xf0/0x110
[ 97.039261] [<ffffffff814f60bb>] od_dbs_timer+0xcb/0x170
[ 97.039263] [<ffffffff8105e75d>] process_one_work+0x1fd/0x540
[ 97.039264] [<ffffffff8105e6f2>] ? process_one_work+0x192/0x540
[ 97.039265] [<ffffffff8105ef22>] worker_thread+0x122/0x380
[ 97.039267] [<ffffffff8105ee00>] ? rescuer_thread+0x320/0x320
[ 97.039268] [<ffffffff8106634a>] kthread+0xea/0xf0
[ 97.039269] [<ffffffff81066260>] ? flush_kthread_worker+0x150/0x150
[ 97.039270] [<ffffffff81623d9c>] ret_from_fork+0x7c/0xb0
[ 97.039272] [<ffffffff81066260>] ? flush_kthread_worker+0x150/0x150
[ 97.039272] ---[ end trace d36d91c626ac81a1 ]---
[ 97.143214] nouveau E[ DRM] GPU lockup - switching to software fbcon
[ 97.318430] WARNING: at drivers/cpufreq/cpufreq_governor.c:172 gov_queue_work+0xf0/0x110()
[ 97.326804] Modules linked in: ext2 vfat fat loop usbhid snd_hda_codec_hdmi coretemp kvm_intel kvm snd_hda_codec_realtek snd_hda_intel snd_hda_codec ehci_pci xhci_hcd ehci_hcd usbcore crc32_pclmul crc32c_intel snd_hwdep snd_pcm snd_page_alloc snd_timer ghash_clmulni_intel snd aesni_intel aes_x86_64 glue_helper sb_edac edac_core acpi_cpufreq mperf pcspkr lrw gf128mul ablk_helper cryptd iTCO_wdt iTCO_vendor_support evdev soundcore lpc_ich mfd_core processor dcdbas i2c_i801 usb_common button microcode
[ 97.374578] CPU: 0 PID: 98 Comm: kworker/3:1 Tainted: G W 3.10.0-rc1+ #2
[ 97.384154] Hardware name: Dell Inc. Precision T3600/0PTTT9, BIOS A08 01/24/2013
[ 97.393566] Workqueue: events od_dbs_timer
[ 97.399675] 0000000000000009 ffff88043b179c78 ffffffff8161445c ffff88043b179cb8
[ 97.409153] ffffffff8103e540 ffff88043b712a80 0000000000000003 ffff88043a295a00
[ 97.418623] ffff88043b712a80 ffffffff81cdc910 0000000000000003 ffff88043b179cc8
[ 97.428103] Call Trace:
[ 97.432520] [<ffffffff8161445c>] dump_stack+0x19/0x1b
[ 97.439678] [<ffffffff8103e540>] warn_slowpath_common+0x70/0xa0
[ 97.447694] [<ffffffff8103e58a>] warn_slowpath_null+0x1a/0x20
[ 97.455512] [<ffffffff814f6bf0>] gov_queue_work+0xf0/0x110
[ 97.462993] [<ffffffff814f60bb>] od_dbs_timer+0xcb/0x170
[ 97.470259] [<ffffffff8105e75d>] process_one_work+0x1fd/0x540
[ 97.477878] [<ffffffff8105e6f2>] ? process_one_work+0x192/0x540
[ 97.485652] [<ffffffff8105ef22>] worker_thread+0x122/0x380
[ 97.492969] [<ffffffff8105ee00>] ? rescuer_thread+0x320/0x320
[ 97.500565] [<ffffffff8106634a>] kthread+0xea/0xf0
[ 97.507167] [<ffffffff81066260>] ? flush_kthread_worker+0x150/0x150
[ 97.515255] [<ffffffff81623d9c>] ret_from_fork+0x7c/0xb0
[ 97.522389] [<ffffffff81066260>] ? flush_kthread_worker+0x150/0x150
[ 97.530472] ---[ end trace d36d91c626ac81a2 ]---
[ 97.543176] ------------[ cut here ]------------
[ 97.547172] ------------[ cut here ]------------
[ 97.547178] WARNING: at drivers/cpufreq/cpufreq_governor.c:172 gov_queue_work+0xf0/0x110()
[ 97.547197] Modules linked in: ext2 vfat fat loop usbhid snd_hda_codec_hdmi coretemp kvm_intel kvm snd_hda_codec_realtek snd_hda_intel snd_hda_codec ehci_pci xhci_hcd ehci_hcd usbcore crc32_pclmul crc32c_intel snd_hwdep snd_pcm snd_page_alloc snd_timer ghash_clmulni_intel snd aesni_intel aes_x86_64 glue_helper sb_edac edac_core acpi_cpufreq mperf pcspkr lrw gf128mul ablk_helper cryptd iTCO_wdt iTCO_vendor_support evdev soundcore lpc_ich mfd_core processor dcdbas i2c_i801 usb_common button microcode
[ 97.547199] CPU: 7 PID: 316 Comm: kworker/5:1 Tainted: G W 3.10.0-rc1+ #2
[ 97.547200] Hardware name: Dell Inc. Precision T3600/0PTTT9, BIOS A08 01/24/2013
[ 97.547202] Workqueue: events od_dbs_timer
[ 97.547204] 0000000000000009 ffff88043905dc78 ffffffff8161445c ffff88043905dcb8
[ 97.547205] ffffffff8103e540 ffff88043b712a80 0000000000000005 ffff88043a295800
[ 97.547206] ffff88043b712a80 ffffffff81cdc910 0000000000000005 ffff88043905dcc8
[ 97.547207] Call Trace:
[ 97.547211] [<ffffffff8161445c>] dump_stack+0x19/0x1b
[ 97.547214] [<ffffffff8103e540>] warn_slowpath_common+0x70/0xa0
[ 97.547215] [<ffffffff8103e58a>] warn_slowpath_null+0x1a/0x20
[ 97.547216] [<ffffffff814f6bf0>] gov_queue_work+0xf0/0x110
[ 97.547218] [<ffffffff814f60bb>] od_dbs_timer+0xcb/0x170
[ 97.547220] [<ffffffff8105e75d>] process_one_work+0x1fd/0x540
[ 97.547221] [<ffffffff8105e6f2>] ? process_one_work+0x192/0x540
[ 97.547222] [<ffffffff8105ef22>] worker_thread+0x122/0x380
[ 97.547224] [<ffffffff8105ee00>] ? rescuer_thread+0x320/0x320
[ 97.547225] [<ffffffff8106634a>] kthread+0xea/0xf0
[ 97.547226] [<ffffffff81066260>] ? flush_kthread_worker+0x150/0x150
[ 97.547228] [<ffffffff81623d9c>] ret_from_fork+0x7c/0xb0
[ 97.547229] [<ffffffff81066260>] ? flush_kthread_worker+0x150/0x150
[ 97.547230] ---[ end trace d36d91c626ac81a3 ]---
[ 97.761326] WARNING: at drivers/cpufreq/cpufreq_governor.c:172 gov_queue_work+0xf0/0x110()
[ 97.770798] Modules linked in: ext2 vfat fat loop usbhid snd_hda_codec_hdmi coretemp kvm_intel kvm snd_hda_codec_realtek snd_hda_intel snd_hda_codec ehci_pci xhci_hcd ehci_hcd usbcore crc32_pclmul crc32c_intel snd_hwdep snd_pcm snd_page_alloc snd_timer ghash_clmulni_intel snd aesni_intel aes_x86_64 glue_helper sb_edac edac_core acpi_cpufreq mperf pcspkr lrw gf128mul ablk_helper cryptd iTCO_wdt iTCO_vendor_support evdev soundcore lpc_ich mfd_core processor dcdbas i2c_i801 usb_common button microcode
[ 97.819617] CPU: 0 PID: 253 Comm: kworker/4:1 Tainted: G W 3.10.0-rc1+ #2
[ 97.828623] Hardware name: Dell Inc. Precision T3600/0PTTT9, BIOS A08 01/24/2013
[ 97.837372] Workqueue: events od_dbs_timer
[ 97.842805] 0000000000000009 ffff880439529c78 ffffffff8161445c ffff880439529cb8
[ 97.851628] ffffffff8103e540 ffff88043b712a80 0000000000000004 ffff88043a295c00
[ 97.860445] ffff88043b712a80 ffffffff81cdc910 0000000000000004 ffff880439529cc8
[ 97.869249] Call Trace:
[ 97.873041] [<ffffffff8161445c>] dump_stack+0x19/0x1b
[ 97.879533] [<ffffffff8103e540>] warn_slowpath_common+0x70/0xa0
[ 97.886912] [<ffffffff8103e58a>] warn_slowpath_null+0x1a/0x20
[ 97.894100] [<ffffffff814f6bf0>] gov_queue_work+0xf0/0x110
[ 97.901002] [<ffffffff814f60bb>] od_dbs_timer+0xcb/0x170
[ 97.907706] [<ffffffff8105e75d>] process_one_work+0x1fd/0x540
[ 97.914797] [<ffffffff8105e6f2>] ? process_one_work+0x192/0x540
[ 97.922016] [<ffffffff8105ef22>] worker_thread+0x122/0x380
[ 97.928803] [<ffffffff8105ee00>] ? rescuer_thread+0x320/0x320
[ 97.935837] [<ffffffff8106634a>] kthread+0xea/0xf0
[ 97.941900] [<ffffffff81066260>] ? flush_kthread_worker+0x150/0x150
[ 97.949443] [<ffffffff81623d9c>] ret_from_fork+0x7c/0xb0
[ 97.956027] [<ffffffff81066260>] ? flush_kthread_worker+0x150/0x150
[ 97.963563] ---[ end trace d36d91c626ac81a4 ]---
[ 97.970449] ------------[ cut here ]------------
[ 97.976277] WARNING: at drivers/cpufreq/cpufreq_governor.c:172 gov_queue_work+0xf0/0x110()
[ 97.985762] Modules linked in: ext2 vfat fat loop usbhid snd_hda_codec_hdmi coretemp kvm_intel kvm snd_hda_codec_realtek snd_hda_intel snd_hda_codec ehci_pci xhci_hcd ehci_hcd usbcore crc32_pclmul crc32c_intel snd_hwdep snd_pcm snd_page_alloc snd_timer ghash_clmulni_intel snd aesni_intel aes_x86_64 glue_helper sb_edac edac_core acpi_cpufreq mperf pcspkr lrw gf128mul ablk_helper cryptd iTCO_wdt iTCO_vendor_support evdev soundcore lpc_ich mfd_core processor dcdbas i2c_i801 usb_common button microcode
[ 98.035051] CPU: 0 PID: 102 Comm: kworker/6:1 Tainted: G W 3.10.0-rc1+ #2
[ 98.044067] Hardware name: Dell Inc. Precision T3600/0PTTT9, BIOS A08 01/24/2013
[ 98.052834] Workqueue: events od_dbs_timer
[ 98.058285] 0000000000000009 ffff88043b6f3c78 ffffffff8161445c ffff88043b6f3cb8
[ 98.067114] ffffffff8103e540 ffff88043b712a80 0000000000000006 ffff88043a295600
[ 98.075924] ffff88043b712a80 ffffffff81cdc910 0000000000000006 ffff88043b6f3cc8
[ 98.084735] Call Trace:
[ 98.088518] [<ffffffff8161445c>] dump_stack+0x19/0x1b
[ 98.095024] [<ffffffff8103e540>] warn_slowpath_common+0x70/0xa0
[ 98.102386] [<ffffffff8103e58a>] warn_slowpath_null+0x1a/0x20
[ 98.109565] [<ffffffff814f6bf0>] gov_queue_work+0xf0/0x110
[ 98.116502] [<ffffffff814f60bb>] od_dbs_timer+0xcb/0x170
[ 98.123253] [<ffffffff8105e75d>] process_one_work+0x1fd/0x540
[ 98.130394] [<ffffffff8105e6f2>] ? process_one_work+0x192/0x540
[ 98.137667] [<ffffffff8105ef22>] worker_thread+0x122/0x380
[ 98.144456] [<ffffffff8105ee00>] ? rescuer_thread+0x320/0x320
[ 98.151510] [<ffffffff8106634a>] kthread+0xea/0xf0
[ 98.157583] [<ffffffff81066260>] ? flush_kthread_worker+0x150/0x150
[ 98.165143] [<ffffffff81623d9c>] ret_from_fork+0x7c/0xb0
[ 98.171730] [<ffffffff81066260>] ? flush_kthread_worker+0x150/0x150
[ 98.179282] ---[ end trace d36d91c626ac81a5 ]---
[ 98.185098] ------------[ cut here ]------------
[ 98.190903] WARNING: at drivers/cpufreq/cpufreq_governor.c:172 gov_queue_work+0xf0/0x110()
[ 98.200387] Modules linked in: ext2 vfat fat loop
[ 98.205029] nouveau W[ PFIFO][0000:03:00.0] unknown intr 0x00400000, ch 1
[ 98.214563] usbhid snd_hda_codec_hdmi coretemp kvm_intel kvm snd_hda_codec_realtek snd_hda_intel snd_hda_codec ehci_pci xhci_hcd ehci_hcd usbcore crc32_pclmul crc32c_intel snd_hwdep snd_pcm snd_page_alloc snd_timer ghash_clmulni_intel snd aesni_intel aes_x86_64 glue_helper sb_edac edac_core acpi_cpufreq mperf pcspkr lrw gf128mul ablk_helper cryptd iTCO_wdt iTCO_vendor_support evdev soundcore lpc_ich mfd_core processor dcdbas i2c_i801 usb_common button microcode
[ 98.258886] CPU: 0 PID: 318 Comm: kworker/7:1 Tainted: G W 3.10.0-rc1+ #2
[ 98.267919] Hardware name: Dell Inc. Precision T3600/0PTTT9, BIOS A08 01/24/2013
[ 98.276689] Workqueue: events od_dbs_timer
[ 98.282147] 0000000000000009 ffff88043969dc78 ffffffff8161445c ffff88043969dcb8
[ 98.290991] ffffffff8103e540 ffff88043b712a80 0000000000000007 ffff88043a295200
[ 98.299832] ffff88043b712a80 ffffffff81cdc910 0000000000000007 ffff88043969dcc8
[ 98.308671] Call Trace:
[ 98.312471] [<ffffffff8161445c>] dump_stack+0x19/0x1b
[ 98.318982] [<ffffffff8103e540>] warn_slowpath_common+0x70/0xa0
[ 98.326376] [<ffffffff8103e58a>] warn_slowpath_null+0x1a/0x20
[ 98.333577] [<ffffffff814f6bf0>] gov_queue_work+0xf0/0x110
[ 98.340482] [<ffffffff814f60bb>] od_dbs_timer+0xcb/0x170
[ 98.347160] [<ffffffff8105e75d>] process_one_work+0x1fd/0x540
[ 98.354232] [<ffffffff8105e6f2>] ? process_one_work+0x192/0x540
[ 98.361471] [<ffffffff8105ef22>] worker_thread+0x122/0x380
[ 98.368260] [<ffffffff8105ee00>] ? rescuer_thread+0x320/0x320
[ 98.375309] [<ffffffff8106634a>] kthread+0xea/0xf0
[ 98.381385] [<ffffffff81066260>] ? flush_kthread_worker+0x150/0x150
[ 98.388951] [<ffffffff81623d9c>] ret_from_fork+0x7c/0xb0
[ 98.395546] [<ffffffff81066260>] ? flush_kthread_worker+0x150/0x150
[ 98.403097] ---[ end trace d36d91c626ac81a6 ]---
[ 98.409180] Power down.
[ 98.413109] acpi_power_off called
--
Regards/Gruss,
Boris.
Sent from a fat crate under my desk. Formatting is fine.
--
--
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
