linux/drivers/cpufreq/cpufreq_governor.c

389 lines
10 KiB
C
Raw Normal View History

/*
* drivers/cpufreq/cpufreq_governor.c
*
* CPUFREQ governors common code
*
* Copyright (C) 2001 Russell King
* (C) 2003 Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>.
* (C) 2003 Jun Nakajima <jun.nakajima@intel.com>
* (C) 2009 Alexander Clouter <alex@digriz.org.uk>
* (c) 2012 Viresh Kumar <viresh.kumar@linaro.org>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/export.h>
#include <linux/kernel_stat.h>
#include <linux/slab.h>
#include "cpufreq_governor.h"
static struct attribute_group *get_sysfs_attr(struct dbs_data *dbs_data)
{
if (have_governor_per_policy())
return dbs_data->cdata->attr_group_gov_pol;
else
return dbs_data->cdata->attr_group_gov_sys;
}
void dbs_check_cpu(struct dbs_data *dbs_data, int cpu)
{
struct cpu_dbs_common_info *cdbs = dbs_data->cdata->get_cpu_cdbs(cpu);
struct od_dbs_tuners *od_tuners = dbs_data->tuners;
struct cs_dbs_tuners *cs_tuners = dbs_data->tuners;
struct cpufreq_policy *policy;
unsigned int max_load = 0;
unsigned int ignore_nice;
unsigned int j;
if (dbs_data->cdata->governor == GOV_ONDEMAND)
ignore_nice = od_tuners->ignore_nice_load;
else
ignore_nice = cs_tuners->ignore_nice_load;
policy = cdbs->cur_policy;
cpufreq: ondemand: Change the calculation of target frequency The ondemand governor calculates load in terms of frequency and increases it only if load_freq is greater than up_threshold multiplied by the current or average frequency. This appears to produce oscillations of frequency between min and max because, for example, a relatively small load can easily saturate minimum frequency and lead the CPU to the max. Then, it will decrease back to the min due to small load_freq. Change the calculation method of load and target frequency on the basis of the following two observations: - Load computation should not depend on the current or average measured frequency. For example, absolute load of 80% at 100MHz is not necessarily equivalent to 8% at 1000MHz in the next sampling interval. - It should be possible to increase the target frequency to any value present in the frequency table proportional to the absolute load, rather than to the max only, so that: Target frequency = C * load where we take C = policy->cpuinfo.max_freq / 100. Tested on Intel i7-3770 CPU @ 3.40GHz and on Quad core 1500MHz Krait. Phoronix benchmark of Linux Kernel Compilation 3.1 test shows an increase ~1.5% in performance. cpufreq_stats (time_in_state) shows that middle frequencies are used more, with this patch. Highest and lowest frequencies were used less by ~9%. [rjw: We have run multiple other tests on kernels with this change applied and in the vast majority of cases it turns out that the resulting performance improvement also leads to reduced consumption of energy. The change is additionally justified by the overall simplification of the code in question.] Signed-off-by: Stratos Karafotis <stratosk@semaphore.gr> Acked-by: Viresh Kumar <viresh.kumar@linaro.org> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2013-06-05 16:01:25 +00:00
/* Get Absolute Load */
for_each_cpu(j, policy->cpus) {
struct cpu_dbs_common_info *j_cdbs;
u64 cur_wall_time, cur_idle_time;
unsigned int idle_time, wall_time;
unsigned int load;
int io_busy = 0;
j_cdbs = dbs_data->cdata->get_cpu_cdbs(j);
/*
* For the purpose of ondemand, waiting for disk IO is
* an indication that you're performance critical, and
* not that the system is actually idle. So do not add
* the iowait time to the cpu idle time.
*/
if (dbs_data->cdata->governor == GOV_ONDEMAND)
io_busy = od_tuners->io_is_busy;
cur_idle_time = get_cpu_idle_time(j, &cur_wall_time, io_busy);
wall_time = (unsigned int)
(cur_wall_time - j_cdbs->prev_cpu_wall);
j_cdbs->prev_cpu_wall = cur_wall_time;
idle_time = (unsigned int)
(cur_idle_time - j_cdbs->prev_cpu_idle);
j_cdbs->prev_cpu_idle = cur_idle_time;
if (ignore_nice) {
u64 cur_nice;
unsigned long cur_nice_jiffies;
cur_nice = kcpustat_cpu(j).cpustat[CPUTIME_NICE] -
cdbs->prev_cpu_nice;
/*
* Assumption: nice time between sampling periods will
* be less than 2^32 jiffies for 32 bit sys
*/
cur_nice_jiffies = (unsigned long)
cputime64_to_jiffies64(cur_nice);
cdbs->prev_cpu_nice =
kcpustat_cpu(j).cpustat[CPUTIME_NICE];
idle_time += jiffies_to_usecs(cur_nice_jiffies);
}
if (unlikely(!wall_time || wall_time < idle_time))
continue;
load = 100 * (wall_time - idle_time) / wall_time;
if (load > max_load)
max_load = load;
}
dbs_data->cdata->gov_check_cpu(cpu, max_load);
}
EXPORT_SYMBOL_GPL(dbs_check_cpu);
static inline void __gov_queue_work(int cpu, struct dbs_data *dbs_data,
unsigned int delay)
{
struct cpu_dbs_common_info *cdbs = dbs_data->cdata->get_cpu_cdbs(cpu);
mod_delayed_work_on(cpu, system_wq, &cdbs->work, delay);
}
void gov_queue_work(struct dbs_data *dbs_data, struct cpufreq_policy *policy,
unsigned int delay, bool all_cpus)
{
int i;
cpufreq: Fix timer/workqueue corruption by protecting reading governor_enabled When a CPU is hot removed we'll cancel all the delayed work items via gov_cancel_work(). Sometimes the delayed work function determines that it should adjust the delay for all other CPUs that the policy is managing. If this scenario occurs, the canceling CPU will cancel its own work but queue up the other CPUs works to run. Commit 3617f2 (cpufreq: Fix timer/workqueue corruption due to double queueing) has tried to fix this, but reading governor_enabled is not protected by cpufreq_governor_lock. Even though od_dbs_timer() checks governor_enabled before gov_queue_work(), this scenario may occur. For example: CPU0 CPU1 ---- ---- cpu_down() ... <work runs> __cpufreq_remove_dev() od_dbs_timer() __cpufreq_governor() policy->governor_enabled policy->governor_enabled = false; cpufreq_governor_dbs() case CPUFREQ_GOV_STOP: gov_cancel_work(dbs_data, policy); cpu0 work is canceled timer is canceled cpu1 work is canceled <waits for cpu1> gov_queue_work(*, *, true); cpu0 work queued cpu1 work queued cpu2 work queued ... cpu1 work is canceled cpu2 work is canceled ... At the end of the GOV_STOP case cpu0 still has a work queued to run although the code is expecting all of the works to be canceled. __cpufreq_remove_dev() will then proceed to re-initialize all the other CPUs works except for the CPU that is going down. The CPUFREQ_GOV_START case in cpufreq_governor_dbs() will trample over the queued work and debugobjects will spit out a warning: WARNING: at lib/debugobjects.c:260 debug_print_object+0x94/0xbc() ODEBUG: init active (active state 0) object type: timer_list hint: delayed_work_timer_fn+0x0/0x14 Modules linked in: CPU: 1 PID: 1205 Comm: sh Tainted: G W 3.10.0 #200 [<c01144f0>] (unwind_backtrace+0x0/0xf8) from [<c0111d98>] (show_stack+0x10/0x14) [<c0111d98>] (show_stack+0x10/0x14) from [<c01272cc>] (warn_slowpath_common+0x4c/0x68) [<c01272cc>] (warn_slowpath_common+0x4c/0x68) from [<c012737c>] (warn_slowpath_fmt+0x30/0x40) [<c012737c>] (warn_slowpath_fmt+0x30/0x40) from [<c034c640>] (debug_print_object+0x94/0xbc) [<c034c640>] (debug_print_object+0x94/0xbc) from [<c034c7f8>] (__debug_object_init+0xc8/0x3c0) [<c034c7f8>] (__debug_object_init+0xc8/0x3c0) from [<c01360e0>] (init_timer_key+0x20/0x104) [<c01360e0>] (init_timer_key+0x20/0x104) from [<c04872ac>] (cpufreq_governor_dbs+0x1dc/0x68c) [<c04872ac>] (cpufreq_governor_dbs+0x1dc/0x68c) from [<c04833a8>] (__cpufreq_governor+0x80/0x1b0) [<c04833a8>] (__cpufreq_governor+0x80/0x1b0) from [<c0483704>] (__cpufreq_remove_dev.isra.12+0x22c/0x380) [<c0483704>] (__cpufreq_remove_dev.isra.12+0x22c/0x380) from [<c0692f38>] (cpufreq_cpu_callback+0x48/0x5c) [<c0692f38>] (cpufreq_cpu_callback+0x48/0x5c) from [<c014fb40>] (notifier_call_chain+0x44/0x84) [<c014fb40>] (notifier_call_chain+0x44/0x84) from [<c012ae44>] (__cpu_notify+0x2c/0x48) [<c012ae44>] (__cpu_notify+0x2c/0x48) from [<c068dd40>] (_cpu_down+0x80/0x258) [<c068dd40>] (_cpu_down+0x80/0x258) from [<c068df40>] (cpu_down+0x28/0x3c) [<c068df40>] (cpu_down+0x28/0x3c) from [<c068e4c0>] (store_online+0x30/0x74) [<c068e4c0>] (store_online+0x30/0x74) from [<c03a7308>] (dev_attr_store+0x18/0x24) [<c03a7308>] (dev_attr_store+0x18/0x24) from [<c0256fe0>] (sysfs_write_file+0x100/0x180) [<c0256fe0>] (sysfs_write_file+0x100/0x180) from [<c01fec9c>] (vfs_write+0xbc/0x184) [<c01fec9c>] (vfs_write+0xbc/0x184) from [<c01ff034>] (SyS_write+0x40/0x68) [<c01ff034>] (SyS_write+0x40/0x68) from [<c010e200>] (ret_fast_syscall+0x0/0x48) In gov_queue_work(), lock cpufreq_governor_lock before gov_queue_work, and unlock it after __gov_queue_work(). In this way, governor_enabled is guaranteed not changed in gov_queue_work(). Signed-off-by: Jane Li <jiel@marvell.com> Acked-by: Viresh Kumar <viresh.kumar@linaro.org> Reviewed-by: Dmitry Torokhov <dmitry.torokhov@gmail.com> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2014-01-03 09:17:41 +00:00
mutex_lock(&cpufreq_governor_lock);
cpufreq: Fix timer/workqueue corruption due to double queueing When a CPU is hot removed we'll cancel all the delayed work items via gov_cancel_work(). Normally this will just cancels a delayed timer on each CPU that the policy is managing and the work won't run, but if the work is already running the workqueue code will wait for the work to finish before continuing to prevent the work items from re-queuing themselves like they normally do. This scheme will work most of the time, except for the case where the work function determines that it should adjust the delay for all other CPUs that the policy is managing. If this scenario occurs, the canceling CPU will cancel its own work but queue up the other CPUs works to run. For example: CPU0 CPU1 ---- ---- cpu_down() ... __cpufreq_remove_dev() cpufreq_governor_dbs() case CPUFREQ_GOV_STOP: gov_cancel_work(dbs_data, policy); cpu0 work is canceled timer is canceled cpu1 work is canceled <work runs> <waits for cpu1> od_dbs_timer() gov_queue_work(*, *, true); cpu0 work queued cpu1 work queued cpu2 work queued ... cpu1 work is canceled cpu2 work is canceled ... At the end of the GOV_STOP case cpu0 still has a work queued to run although the code is expecting all of the works to be canceled. __cpufreq_remove_dev() will then proceed to re-initialize all the other CPUs works except for the CPU that is going down. The CPUFREQ_GOV_START case in cpufreq_governor_dbs() will trample over the queued work and debugobjects will spit out a warning: WARNING: at lib/debugobjects.c:260 debug_print_object+0x94/0xbc() ODEBUG: init active (active state 0) object type: timer_list hint: delayed_work_timer_fn+0x0/0x10 Modules linked in: CPU: 0 PID: 1491 Comm: sh Tainted: G W 3.10.0 #19 [<c010c178>] (unwind_backtrace+0x0/0x11c) from [<c0109dec>] (show_stack+0x10/0x14) [<c0109dec>] (show_stack+0x10/0x14) from [<c01904cc>] (warn_slowpath_common+0x4c/0x6c) [<c01904cc>] (warn_slowpath_common+0x4c/0x6c) from [<c019056c>] (warn_slowpath_fmt+0x2c/0x3c) [<c019056c>] (warn_slowpath_fmt+0x2c/0x3c) from [<c0388a7c>] (debug_print_object+0x94/0xbc) [<c0388a7c>] (debug_print_object+0x94/0xbc) from [<c0388e34>] (__debug_object_init+0x2d0/0x340) [<c0388e34>] (__debug_object_init+0x2d0/0x340) from [<c019e3b0>] (init_timer_key+0x14/0xb0) [<c019e3b0>] (init_timer_key+0x14/0xb0) from [<c0635f78>] (cpufreq_governor_dbs+0x3e8/0x5f8) [<c0635f78>] (cpufreq_governor_dbs+0x3e8/0x5f8) from [<c06325a0>] (__cpufreq_governor+0xdc/0x1a4) [<c06325a0>] (__cpufreq_governor+0xdc/0x1a4) from [<c0633704>] (__cpufreq_remove_dev.isra.10+0x3b4/0x434) [<c0633704>] (__cpufreq_remove_dev.isra.10+0x3b4/0x434) from [<c08989f4>] (cpufreq_cpu_callback+0x60/0x80) [<c08989f4>] (cpufreq_cpu_callback+0x60/0x80) from [<c08a43c0>] (notifier_call_chain+0x38/0x68) [<c08a43c0>] (notifier_call_chain+0x38/0x68) from [<c01938e0>] (__cpu_notify+0x28/0x40) [<c01938e0>] (__cpu_notify+0x28/0x40) from [<c0892ad4>] (_cpu_down+0x7c/0x2c0) [<c0892ad4>] (_cpu_down+0x7c/0x2c0) from [<c0892d3c>] (cpu_down+0x24/0x40) [<c0892d3c>] (cpu_down+0x24/0x40) from [<c0893ea8>] (store_online+0x2c/0x74) [<c0893ea8>] (store_online+0x2c/0x74) from [<c04519d8>] (dev_attr_store+0x18/0x24) [<c04519d8>] (dev_attr_store+0x18/0x24) from [<c02a69d4>] (sysfs_write_file+0x100/0x148) [<c02a69d4>] (sysfs_write_file+0x100/0x148) from [<c0255c18>] (vfs_write+0xcc/0x174) [<c0255c18>] (vfs_write+0xcc/0x174) from [<c0255f70>] (SyS_write+0x38/0x64) [<c0255f70>] (SyS_write+0x38/0x64) from [<c0106120>] (ret_fast_syscall+0x0/0x30) Signed-off-by: Stephen Boyd <sboyd@codeaurora.org> Acked-by: Viresh Kumar <viresh.kumar@linaro.org> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2013-08-27 18:47:29 +00:00
if (!policy->governor_enabled)
cpufreq: Fix timer/workqueue corruption by protecting reading governor_enabled When a CPU is hot removed we'll cancel all the delayed work items via gov_cancel_work(). Sometimes the delayed work function determines that it should adjust the delay for all other CPUs that the policy is managing. If this scenario occurs, the canceling CPU will cancel its own work but queue up the other CPUs works to run. Commit 3617f2 (cpufreq: Fix timer/workqueue corruption due to double queueing) has tried to fix this, but reading governor_enabled is not protected by cpufreq_governor_lock. Even though od_dbs_timer() checks governor_enabled before gov_queue_work(), this scenario may occur. For example: CPU0 CPU1 ---- ---- cpu_down() ... <work runs> __cpufreq_remove_dev() od_dbs_timer() __cpufreq_governor() policy->governor_enabled policy->governor_enabled = false; cpufreq_governor_dbs() case CPUFREQ_GOV_STOP: gov_cancel_work(dbs_data, policy); cpu0 work is canceled timer is canceled cpu1 work is canceled <waits for cpu1> gov_queue_work(*, *, true); cpu0 work queued cpu1 work queued cpu2 work queued ... cpu1 work is canceled cpu2 work is canceled ... At the end of the GOV_STOP case cpu0 still has a work queued to run although the code is expecting all of the works to be canceled. __cpufreq_remove_dev() will then proceed to re-initialize all the other CPUs works except for the CPU that is going down. The CPUFREQ_GOV_START case in cpufreq_governor_dbs() will trample over the queued work and debugobjects will spit out a warning: WARNING: at lib/debugobjects.c:260 debug_print_object+0x94/0xbc() ODEBUG: init active (active state 0) object type: timer_list hint: delayed_work_timer_fn+0x0/0x14 Modules linked in: CPU: 1 PID: 1205 Comm: sh Tainted: G W 3.10.0 #200 [<c01144f0>] (unwind_backtrace+0x0/0xf8) from [<c0111d98>] (show_stack+0x10/0x14) [<c0111d98>] (show_stack+0x10/0x14) from [<c01272cc>] (warn_slowpath_common+0x4c/0x68) [<c01272cc>] (warn_slowpath_common+0x4c/0x68) from [<c012737c>] (warn_slowpath_fmt+0x30/0x40) [<c012737c>] (warn_slowpath_fmt+0x30/0x40) from [<c034c640>] (debug_print_object+0x94/0xbc) [<c034c640>] (debug_print_object+0x94/0xbc) from [<c034c7f8>] (__debug_object_init+0xc8/0x3c0) [<c034c7f8>] (__debug_object_init+0xc8/0x3c0) from [<c01360e0>] (init_timer_key+0x20/0x104) [<c01360e0>] (init_timer_key+0x20/0x104) from [<c04872ac>] (cpufreq_governor_dbs+0x1dc/0x68c) [<c04872ac>] (cpufreq_governor_dbs+0x1dc/0x68c) from [<c04833a8>] (__cpufreq_governor+0x80/0x1b0) [<c04833a8>] (__cpufreq_governor+0x80/0x1b0) from [<c0483704>] (__cpufreq_remove_dev.isra.12+0x22c/0x380) [<c0483704>] (__cpufreq_remove_dev.isra.12+0x22c/0x380) from [<c0692f38>] (cpufreq_cpu_callback+0x48/0x5c) [<c0692f38>] (cpufreq_cpu_callback+0x48/0x5c) from [<c014fb40>] (notifier_call_chain+0x44/0x84) [<c014fb40>] (notifier_call_chain+0x44/0x84) from [<c012ae44>] (__cpu_notify+0x2c/0x48) [<c012ae44>] (__cpu_notify+0x2c/0x48) from [<c068dd40>] (_cpu_down+0x80/0x258) [<c068dd40>] (_cpu_down+0x80/0x258) from [<c068df40>] (cpu_down+0x28/0x3c) [<c068df40>] (cpu_down+0x28/0x3c) from [<c068e4c0>] (store_online+0x30/0x74) [<c068e4c0>] (store_online+0x30/0x74) from [<c03a7308>] (dev_attr_store+0x18/0x24) [<c03a7308>] (dev_attr_store+0x18/0x24) from [<c0256fe0>] (sysfs_write_file+0x100/0x180) [<c0256fe0>] (sysfs_write_file+0x100/0x180) from [<c01fec9c>] (vfs_write+0xbc/0x184) [<c01fec9c>] (vfs_write+0xbc/0x184) from [<c01ff034>] (SyS_write+0x40/0x68) [<c01ff034>] (SyS_write+0x40/0x68) from [<c010e200>] (ret_fast_syscall+0x0/0x48) In gov_queue_work(), lock cpufreq_governor_lock before gov_queue_work, and unlock it after __gov_queue_work(). In this way, governor_enabled is guaranteed not changed in gov_queue_work(). Signed-off-by: Jane Li <jiel@marvell.com> Acked-by: Viresh Kumar <viresh.kumar@linaro.org> Reviewed-by: Dmitry Torokhov <dmitry.torokhov@gmail.com> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2014-01-03 09:17:41 +00:00
goto out_unlock;
cpufreq: Fix timer/workqueue corruption due to double queueing When a CPU is hot removed we'll cancel all the delayed work items via gov_cancel_work(). Normally this will just cancels a delayed timer on each CPU that the policy is managing and the work won't run, but if the work is already running the workqueue code will wait for the work to finish before continuing to prevent the work items from re-queuing themselves like they normally do. This scheme will work most of the time, except for the case where the work function determines that it should adjust the delay for all other CPUs that the policy is managing. If this scenario occurs, the canceling CPU will cancel its own work but queue up the other CPUs works to run. For example: CPU0 CPU1 ---- ---- cpu_down() ... __cpufreq_remove_dev() cpufreq_governor_dbs() case CPUFREQ_GOV_STOP: gov_cancel_work(dbs_data, policy); cpu0 work is canceled timer is canceled cpu1 work is canceled <work runs> <waits for cpu1> od_dbs_timer() gov_queue_work(*, *, true); cpu0 work queued cpu1 work queued cpu2 work queued ... cpu1 work is canceled cpu2 work is canceled ... At the end of the GOV_STOP case cpu0 still has a work queued to run although the code is expecting all of the works to be canceled. __cpufreq_remove_dev() will then proceed to re-initialize all the other CPUs works except for the CPU that is going down. The CPUFREQ_GOV_START case in cpufreq_governor_dbs() will trample over the queued work and debugobjects will spit out a warning: WARNING: at lib/debugobjects.c:260 debug_print_object+0x94/0xbc() ODEBUG: init active (active state 0) object type: timer_list hint: delayed_work_timer_fn+0x0/0x10 Modules linked in: CPU: 0 PID: 1491 Comm: sh Tainted: G W 3.10.0 #19 [<c010c178>] (unwind_backtrace+0x0/0x11c) from [<c0109dec>] (show_stack+0x10/0x14) [<c0109dec>] (show_stack+0x10/0x14) from [<c01904cc>] (warn_slowpath_common+0x4c/0x6c) [<c01904cc>] (warn_slowpath_common+0x4c/0x6c) from [<c019056c>] (warn_slowpath_fmt+0x2c/0x3c) [<c019056c>] (warn_slowpath_fmt+0x2c/0x3c) from [<c0388a7c>] (debug_print_object+0x94/0xbc) [<c0388a7c>] (debug_print_object+0x94/0xbc) from [<c0388e34>] (__debug_object_init+0x2d0/0x340) [<c0388e34>] (__debug_object_init+0x2d0/0x340) from [<c019e3b0>] (init_timer_key+0x14/0xb0) [<c019e3b0>] (init_timer_key+0x14/0xb0) from [<c0635f78>] (cpufreq_governor_dbs+0x3e8/0x5f8) [<c0635f78>] (cpufreq_governor_dbs+0x3e8/0x5f8) from [<c06325a0>] (__cpufreq_governor+0xdc/0x1a4) [<c06325a0>] (__cpufreq_governor+0xdc/0x1a4) from [<c0633704>] (__cpufreq_remove_dev.isra.10+0x3b4/0x434) [<c0633704>] (__cpufreq_remove_dev.isra.10+0x3b4/0x434) from [<c08989f4>] (cpufreq_cpu_callback+0x60/0x80) [<c08989f4>] (cpufreq_cpu_callback+0x60/0x80) from [<c08a43c0>] (notifier_call_chain+0x38/0x68) [<c08a43c0>] (notifier_call_chain+0x38/0x68) from [<c01938e0>] (__cpu_notify+0x28/0x40) [<c01938e0>] (__cpu_notify+0x28/0x40) from [<c0892ad4>] (_cpu_down+0x7c/0x2c0) [<c0892ad4>] (_cpu_down+0x7c/0x2c0) from [<c0892d3c>] (cpu_down+0x24/0x40) [<c0892d3c>] (cpu_down+0x24/0x40) from [<c0893ea8>] (store_online+0x2c/0x74) [<c0893ea8>] (store_online+0x2c/0x74) from [<c04519d8>] (dev_attr_store+0x18/0x24) [<c04519d8>] (dev_attr_store+0x18/0x24) from [<c02a69d4>] (sysfs_write_file+0x100/0x148) [<c02a69d4>] (sysfs_write_file+0x100/0x148) from [<c0255c18>] (vfs_write+0xcc/0x174) [<c0255c18>] (vfs_write+0xcc/0x174) from [<c0255f70>] (SyS_write+0x38/0x64) [<c0255f70>] (SyS_write+0x38/0x64) from [<c0106120>] (ret_fast_syscall+0x0/0x30) Signed-off-by: Stephen Boyd <sboyd@codeaurora.org> Acked-by: Viresh Kumar <viresh.kumar@linaro.org> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2013-08-27 18:47:29 +00:00
if (!all_cpus) {
/*
* Use raw_smp_processor_id() to avoid preemptible warnings.
* We know that this is only called with all_cpus == false from
* works that have been queued with *_work_on() functions and
* those works are canceled during CPU_DOWN_PREPARE so they
* can't possibly run on any other CPU.
*/
__gov_queue_work(raw_smp_processor_id(), dbs_data, delay);
} else {
for_each_cpu(i, policy->cpus)
__gov_queue_work(i, dbs_data, delay);
}
cpufreq: Fix timer/workqueue corruption by protecting reading governor_enabled When a CPU is hot removed we'll cancel all the delayed work items via gov_cancel_work(). Sometimes the delayed work function determines that it should adjust the delay for all other CPUs that the policy is managing. If this scenario occurs, the canceling CPU will cancel its own work but queue up the other CPUs works to run. Commit 3617f2 (cpufreq: Fix timer/workqueue corruption due to double queueing) has tried to fix this, but reading governor_enabled is not protected by cpufreq_governor_lock. Even though od_dbs_timer() checks governor_enabled before gov_queue_work(), this scenario may occur. For example: CPU0 CPU1 ---- ---- cpu_down() ... <work runs> __cpufreq_remove_dev() od_dbs_timer() __cpufreq_governor() policy->governor_enabled policy->governor_enabled = false; cpufreq_governor_dbs() case CPUFREQ_GOV_STOP: gov_cancel_work(dbs_data, policy); cpu0 work is canceled timer is canceled cpu1 work is canceled <waits for cpu1> gov_queue_work(*, *, true); cpu0 work queued cpu1 work queued cpu2 work queued ... cpu1 work is canceled cpu2 work is canceled ... At the end of the GOV_STOP case cpu0 still has a work queued to run although the code is expecting all of the works to be canceled. __cpufreq_remove_dev() will then proceed to re-initialize all the other CPUs works except for the CPU that is going down. The CPUFREQ_GOV_START case in cpufreq_governor_dbs() will trample over the queued work and debugobjects will spit out a warning: WARNING: at lib/debugobjects.c:260 debug_print_object+0x94/0xbc() ODEBUG: init active (active state 0) object type: timer_list hint: delayed_work_timer_fn+0x0/0x14 Modules linked in: CPU: 1 PID: 1205 Comm: sh Tainted: G W 3.10.0 #200 [<c01144f0>] (unwind_backtrace+0x0/0xf8) from [<c0111d98>] (show_stack+0x10/0x14) [<c0111d98>] (show_stack+0x10/0x14) from [<c01272cc>] (warn_slowpath_common+0x4c/0x68) [<c01272cc>] (warn_slowpath_common+0x4c/0x68) from [<c012737c>] (warn_slowpath_fmt+0x30/0x40) [<c012737c>] (warn_slowpath_fmt+0x30/0x40) from [<c034c640>] (debug_print_object+0x94/0xbc) [<c034c640>] (debug_print_object+0x94/0xbc) from [<c034c7f8>] (__debug_object_init+0xc8/0x3c0) [<c034c7f8>] (__debug_object_init+0xc8/0x3c0) from [<c01360e0>] (init_timer_key+0x20/0x104) [<c01360e0>] (init_timer_key+0x20/0x104) from [<c04872ac>] (cpufreq_governor_dbs+0x1dc/0x68c) [<c04872ac>] (cpufreq_governor_dbs+0x1dc/0x68c) from [<c04833a8>] (__cpufreq_governor+0x80/0x1b0) [<c04833a8>] (__cpufreq_governor+0x80/0x1b0) from [<c0483704>] (__cpufreq_remove_dev.isra.12+0x22c/0x380) [<c0483704>] (__cpufreq_remove_dev.isra.12+0x22c/0x380) from [<c0692f38>] (cpufreq_cpu_callback+0x48/0x5c) [<c0692f38>] (cpufreq_cpu_callback+0x48/0x5c) from [<c014fb40>] (notifier_call_chain+0x44/0x84) [<c014fb40>] (notifier_call_chain+0x44/0x84) from [<c012ae44>] (__cpu_notify+0x2c/0x48) [<c012ae44>] (__cpu_notify+0x2c/0x48) from [<c068dd40>] (_cpu_down+0x80/0x258) [<c068dd40>] (_cpu_down+0x80/0x258) from [<c068df40>] (cpu_down+0x28/0x3c) [<c068df40>] (cpu_down+0x28/0x3c) from [<c068e4c0>] (store_online+0x30/0x74) [<c068e4c0>] (store_online+0x30/0x74) from [<c03a7308>] (dev_attr_store+0x18/0x24) [<c03a7308>] (dev_attr_store+0x18/0x24) from [<c0256fe0>] (sysfs_write_file+0x100/0x180) [<c0256fe0>] (sysfs_write_file+0x100/0x180) from [<c01fec9c>] (vfs_write+0xbc/0x184) [<c01fec9c>] (vfs_write+0xbc/0x184) from [<c01ff034>] (SyS_write+0x40/0x68) [<c01ff034>] (SyS_write+0x40/0x68) from [<c010e200>] (ret_fast_syscall+0x0/0x48) In gov_queue_work(), lock cpufreq_governor_lock before gov_queue_work, and unlock it after __gov_queue_work(). In this way, governor_enabled is guaranteed not changed in gov_queue_work(). Signed-off-by: Jane Li <jiel@marvell.com> Acked-by: Viresh Kumar <viresh.kumar@linaro.org> Reviewed-by: Dmitry Torokhov <dmitry.torokhov@gmail.com> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2014-01-03 09:17:41 +00:00
out_unlock:
mutex_unlock(&cpufreq_governor_lock);
}
EXPORT_SYMBOL_GPL(gov_queue_work);
static inline void gov_cancel_work(struct dbs_data *dbs_data,
struct cpufreq_policy *policy)
{
struct cpu_dbs_common_info *cdbs;
int i;
for_each_cpu(i, policy->cpus) {
cdbs = dbs_data->cdata->get_cpu_cdbs(i);
cancel_delayed_work_sync(&cdbs->work);
}
}
/* Will return if we need to evaluate cpu load again or not */
bool need_load_eval(struct cpu_dbs_common_info *cdbs,
unsigned int sampling_rate)
{
if (policy_is_shared(cdbs->cur_policy)) {
ktime_t time_now = ktime_get();
s64 delta_us = ktime_us_delta(time_now, cdbs->time_stamp);
/* Do nothing if we recently have sampled */
if (delta_us < (s64)(sampling_rate / 2))
return false;
else
cdbs->time_stamp = time_now;
}
return true;
}
EXPORT_SYMBOL_GPL(need_load_eval);
static void set_sampling_rate(struct dbs_data *dbs_data,
unsigned int sampling_rate)
{
if (dbs_data->cdata->governor == GOV_CONSERVATIVE) {
struct cs_dbs_tuners *cs_tuners = dbs_data->tuners;
cs_tuners->sampling_rate = sampling_rate;
} else {
struct od_dbs_tuners *od_tuners = dbs_data->tuners;
od_tuners->sampling_rate = sampling_rate;
}
}
int cpufreq_governor_dbs(struct cpufreq_policy *policy,
struct common_dbs_data *cdata, unsigned int event)
{
struct dbs_data *dbs_data;
struct od_cpu_dbs_info_s *od_dbs_info = NULL;
struct cs_cpu_dbs_info_s *cs_dbs_info = NULL;
struct od_ops *od_ops = NULL;
struct od_dbs_tuners *od_tuners = NULL;
struct cs_dbs_tuners *cs_tuners = NULL;
struct cpu_dbs_common_info *cpu_cdbs;
unsigned int sampling_rate, latency, ignore_nice, j, cpu = policy->cpu;
int io_busy = 0;
int rc;
if (have_governor_per_policy())
dbs_data = policy->governor_data;
else
dbs_data = cdata->gdbs_data;
WARN_ON(!dbs_data && (event != CPUFREQ_GOV_POLICY_INIT));
switch (event) {
case CPUFREQ_GOV_POLICY_INIT:
if (have_governor_per_policy()) {
WARN_ON(dbs_data);
} else if (dbs_data) {
dbs_data->usage_count++;
policy->governor_data = dbs_data;
return 0;
}
dbs_data = kzalloc(sizeof(*dbs_data), GFP_KERNEL);
if (!dbs_data) {
pr_err("%s: POLICY_INIT: kzalloc failed\n", __func__);
return -ENOMEM;
}
dbs_data->cdata = cdata;
dbs_data->usage_count = 1;
rc = cdata->init(dbs_data);
if (rc) {
pr_err("%s: POLICY_INIT: init() failed\n", __func__);
kfree(dbs_data);
return rc;
}
if (!have_governor_per_policy())
WARN_ON(cpufreq_get_global_kobject());
rc = sysfs_create_group(get_governor_parent_kobj(policy),
get_sysfs_attr(dbs_data));
if (rc) {
cdata->exit(dbs_data);
kfree(dbs_data);
return rc;
}
policy->governor_data = dbs_data;
/* policy latency is in ns. Convert it to us first */
latency = policy->cpuinfo.transition_latency / 1000;
if (latency == 0)
latency = 1;
/* Bring kernel and HW constraints together */
dbs_data->min_sampling_rate = max(dbs_data->min_sampling_rate,
MIN_LATENCY_MULTIPLIER * latency);
set_sampling_rate(dbs_data, max(dbs_data->min_sampling_rate,
latency * LATENCY_MULTIPLIER));
if ((cdata->governor == GOV_CONSERVATIVE) &&
(!policy->governor->initialized)) {
struct cs_ops *cs_ops = dbs_data->cdata->gov_ops;
cpufreq_register_notifier(cs_ops->notifier_block,
CPUFREQ_TRANSITION_NOTIFIER);
}
if (!have_governor_per_policy())
cdata->gdbs_data = dbs_data;
return 0;
case CPUFREQ_GOV_POLICY_EXIT:
if (!--dbs_data->usage_count) {
sysfs_remove_group(get_governor_parent_kobj(policy),
get_sysfs_attr(dbs_data));
if (!have_governor_per_policy())
cpufreq_put_global_kobject();
if ((dbs_data->cdata->governor == GOV_CONSERVATIVE) &&
(policy->governor->initialized == 1)) {
struct cs_ops *cs_ops = dbs_data->cdata->gov_ops;
cpufreq_unregister_notifier(cs_ops->notifier_block,
CPUFREQ_TRANSITION_NOTIFIER);
}
cdata->exit(dbs_data);
kfree(dbs_data);
cdata->gdbs_data = NULL;
}
policy->governor_data = NULL;
return 0;
}
cpu_cdbs = dbs_data->cdata->get_cpu_cdbs(cpu);
if (dbs_data->cdata->governor == GOV_CONSERVATIVE) {
cs_tuners = dbs_data->tuners;
cs_dbs_info = dbs_data->cdata->get_cpu_dbs_info_s(cpu);
sampling_rate = cs_tuners->sampling_rate;
ignore_nice = cs_tuners->ignore_nice_load;
} else {
od_tuners = dbs_data->tuners;
od_dbs_info = dbs_data->cdata->get_cpu_dbs_info_s(cpu);
sampling_rate = od_tuners->sampling_rate;
ignore_nice = od_tuners->ignore_nice_load;
od_ops = dbs_data->cdata->gov_ops;
io_busy = od_tuners->io_is_busy;
}
switch (event) {
case CPUFREQ_GOV_START:
if (!policy->cur)
return -EINVAL;
mutex_lock(&dbs_data->mutex);
for_each_cpu(j, policy->cpus) {
struct cpu_dbs_common_info *j_cdbs =
dbs_data->cdata->get_cpu_cdbs(j);
j_cdbs->cpu = j;
j_cdbs->cur_policy = policy;
j_cdbs->prev_cpu_idle = get_cpu_idle_time(j,
&j_cdbs->prev_cpu_wall, io_busy);
if (ignore_nice)
j_cdbs->prev_cpu_nice =
kcpustat_cpu(j).cpustat[CPUTIME_NICE];
mutex_init(&j_cdbs->timer_mutex);
INIT_DEFERRABLE_WORK(&j_cdbs->work,
dbs_data->cdata->gov_dbs_timer);
}
if (dbs_data->cdata->governor == GOV_CONSERVATIVE) {
cs_dbs_info->down_skip = 0;
cs_dbs_info->enable = 1;
cs_dbs_info->requested_freq = policy->cur;
} else {
od_dbs_info->rate_mult = 1;
od_dbs_info->sample_type = OD_NORMAL_SAMPLE;
od_ops->powersave_bias_init_cpu(cpu);
}
mutex_unlock(&dbs_data->mutex);
/* Initiate timer time stamp */
cpu_cdbs->time_stamp = ktime_get();
gov_queue_work(dbs_data, policy,
delay_for_sampling_rate(sampling_rate), true);
break;
case CPUFREQ_GOV_STOP:
if (dbs_data->cdata->governor == GOV_CONSERVATIVE)
cs_dbs_info->enable = 0;
gov_cancel_work(dbs_data, policy);
mutex_lock(&dbs_data->mutex);
mutex_destroy(&cpu_cdbs->timer_mutex);
cpu_cdbs->cur_policy = NULL;
mutex_unlock(&dbs_data->mutex);
break;
case CPUFREQ_GOV_LIMITS:
cpufreq: remove race while accessing cur_policy While accessing cur_policy during executing events CPUFREQ_GOV_START, CPUFREQ_GOV_STOP, CPUFREQ_GOV_LIMITS, same mutex lock is not taken, dbs_data->mutex, which leads to race and data corruption while running continious suspend resume test. This is seen with ondemand governor with suspend resume test using rtcwake. Unable to handle kernel NULL pointer dereference at virtual address 00000028 pgd = ed610000 [00000028] *pgd=adf11831, *pte=00000000, *ppte=00000000 Internal error: Oops: 17 [#1] PREEMPT SMP ARM Modules linked in: nvhost_vi CPU: 1 PID: 3243 Comm: rtcwake Not tainted 3.10.24-gf5cf9e5 #1 task: ee708040 ti: ed61c000 task.ti: ed61c000 PC is at cpufreq_governor_dbs+0x400/0x634 LR is at cpufreq_governor_dbs+0x3f8/0x634 pc : [<c05652b8>] lr : [<c05652b0>] psr: 600f0013 sp : ed61dcb0 ip : 000493e0 fp : c1cc14f0 r10: 00000000 r9 : 00000000 r8 : 00000000 r7 : eb725280 r6 : c1cc1560 r5 : eb575200 r4 : ebad7740 r3 : ee708040 r2 : ed61dca8 r1 : 001ebd24 r0 : 00000000 Flags: nZCv IRQs on FIQs on Mode SVC_32 ISA ARM Segment user Control: 10c5387d Table: ad61006a DAC: 00000015 [<c05652b8>] (cpufreq_governor_dbs+0x400/0x634) from [<c055f700>] (__cpufreq_governor+0x98/0x1b4) [<c055f700>] (__cpufreq_governor+0x98/0x1b4) from [<c0560770>] (__cpufreq_set_policy+0x250/0x320) [<c0560770>] (__cpufreq_set_policy+0x250/0x320) from [<c0561dcc>] (cpufreq_update_policy+0xcc/0x168) [<c0561dcc>] (cpufreq_update_policy+0xcc/0x168) from [<c0561ed0>] (cpu_freq_notify+0x68/0xdc) [<c0561ed0>] (cpu_freq_notify+0x68/0xdc) from [<c008eff8>] (notifier_call_chain+0x4c/0x8c) [<c008eff8>] (notifier_call_chain+0x4c/0x8c) from [<c008f3d4>] (__blocking_notifier_call_chain+0x50/0x68) [<c008f3d4>] (__blocking_notifier_call_chain+0x50/0x68) from [<c008f40c>] (blocking_notifier_call_chain+0x20/0x28) [<c008f40c>] (blocking_notifier_call_chain+0x20/0x28) from [<c00aac6c>] (pm_qos_update_bounded_target+0xd8/0x310) [<c00aac6c>] (pm_qos_update_bounded_target+0xd8/0x310) from [<c00ab3b0>] (__pm_qos_update_request+0x64/0x70) [<c00ab3b0>] (__pm_qos_update_request+0x64/0x70) from [<c004b4b8>] (tegra_pm_notify+0x114/0x134) [<c004b4b8>] (tegra_pm_notify+0x114/0x134) from [<c008eff8>] (notifier_call_chain+0x4c/0x8c) [<c008eff8>] (notifier_call_chain+0x4c/0x8c) from [<c008f3d4>] (__blocking_notifier_call_chain+0x50/0x68) [<c008f3d4>] (__blocking_notifier_call_chain+0x50/0x68) from [<c008f40c>] (blocking_notifier_call_chain+0x20/0x28) [<c008f40c>] (blocking_notifier_call_chain+0x20/0x28) from [<c00ac228>] (pm_notifier_call_chain+0x1c/0x34) [<c00ac228>] (pm_notifier_call_chain+0x1c/0x34) from [<c00ad38c>] (enter_state+0xec/0x128) [<c00ad38c>] (enter_state+0xec/0x128) from [<c00ad400>] (pm_suspend+0x38/0xa4) [<c00ad400>] (pm_suspend+0x38/0xa4) from [<c00ac114>] (state_store+0x70/0xc0) [<c00ac114>] (state_store+0x70/0xc0) from [<c027b1e8>] (kobj_attr_store+0x14/0x20) [<c027b1e8>] (kobj_attr_store+0x14/0x20) from [<c019cd9c>] (sysfs_write_file+0x104/0x184) [<c019cd9c>] (sysfs_write_file+0x104/0x184) from [<c0143038>] (vfs_write+0xd0/0x19c) [<c0143038>] (vfs_write+0xd0/0x19c) from [<c0143414>] (SyS_write+0x4c/0x78) [<c0143414>] (SyS_write+0x4c/0x78) from [<c000f080>] (ret_fast_syscall+0x0/0x30) Code: e1a00006 eb084346 e59b0020 e5951024 (e5903028) ---[ end trace 0488523c8f6b0f9d ]--- Signed-off-by: Bibek Basu <bbasu@nvidia.com> Acked-by: Viresh Kumar <viresh.kumar@linaro.org> Cc: 3.11+ <stable@vger.kernel.org> # 3.11+ Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2014-05-19 04:54:01 +00:00
mutex_lock(&dbs_data->mutex);
if (!cpu_cdbs->cur_policy) {
mutex_unlock(&dbs_data->mutex);
break;
}
mutex_lock(&cpu_cdbs->timer_mutex);
if (policy->max < cpu_cdbs->cur_policy->cur)
__cpufreq_driver_target(cpu_cdbs->cur_policy,
policy->max, CPUFREQ_RELATION_H);
else if (policy->min > cpu_cdbs->cur_policy->cur)
__cpufreq_driver_target(cpu_cdbs->cur_policy,
policy->min, CPUFREQ_RELATION_L);
dbs_check_cpu(dbs_data, cpu);
mutex_unlock(&cpu_cdbs->timer_mutex);
cpufreq: remove race while accessing cur_policy While accessing cur_policy during executing events CPUFREQ_GOV_START, CPUFREQ_GOV_STOP, CPUFREQ_GOV_LIMITS, same mutex lock is not taken, dbs_data->mutex, which leads to race and data corruption while running continious suspend resume test. This is seen with ondemand governor with suspend resume test using rtcwake. Unable to handle kernel NULL pointer dereference at virtual address 00000028 pgd = ed610000 [00000028] *pgd=adf11831, *pte=00000000, *ppte=00000000 Internal error: Oops: 17 [#1] PREEMPT SMP ARM Modules linked in: nvhost_vi CPU: 1 PID: 3243 Comm: rtcwake Not tainted 3.10.24-gf5cf9e5 #1 task: ee708040 ti: ed61c000 task.ti: ed61c000 PC is at cpufreq_governor_dbs+0x400/0x634 LR is at cpufreq_governor_dbs+0x3f8/0x634 pc : [<c05652b8>] lr : [<c05652b0>] psr: 600f0013 sp : ed61dcb0 ip : 000493e0 fp : c1cc14f0 r10: 00000000 r9 : 00000000 r8 : 00000000 r7 : eb725280 r6 : c1cc1560 r5 : eb575200 r4 : ebad7740 r3 : ee708040 r2 : ed61dca8 r1 : 001ebd24 r0 : 00000000 Flags: nZCv IRQs on FIQs on Mode SVC_32 ISA ARM Segment user Control: 10c5387d Table: ad61006a DAC: 00000015 [<c05652b8>] (cpufreq_governor_dbs+0x400/0x634) from [<c055f700>] (__cpufreq_governor+0x98/0x1b4) [<c055f700>] (__cpufreq_governor+0x98/0x1b4) from [<c0560770>] (__cpufreq_set_policy+0x250/0x320) [<c0560770>] (__cpufreq_set_policy+0x250/0x320) from [<c0561dcc>] (cpufreq_update_policy+0xcc/0x168) [<c0561dcc>] (cpufreq_update_policy+0xcc/0x168) from [<c0561ed0>] (cpu_freq_notify+0x68/0xdc) [<c0561ed0>] (cpu_freq_notify+0x68/0xdc) from [<c008eff8>] (notifier_call_chain+0x4c/0x8c) [<c008eff8>] (notifier_call_chain+0x4c/0x8c) from [<c008f3d4>] (__blocking_notifier_call_chain+0x50/0x68) [<c008f3d4>] (__blocking_notifier_call_chain+0x50/0x68) from [<c008f40c>] (blocking_notifier_call_chain+0x20/0x28) [<c008f40c>] (blocking_notifier_call_chain+0x20/0x28) from [<c00aac6c>] (pm_qos_update_bounded_target+0xd8/0x310) [<c00aac6c>] (pm_qos_update_bounded_target+0xd8/0x310) from [<c00ab3b0>] (__pm_qos_update_request+0x64/0x70) [<c00ab3b0>] (__pm_qos_update_request+0x64/0x70) from [<c004b4b8>] (tegra_pm_notify+0x114/0x134) [<c004b4b8>] (tegra_pm_notify+0x114/0x134) from [<c008eff8>] (notifier_call_chain+0x4c/0x8c) [<c008eff8>] (notifier_call_chain+0x4c/0x8c) from [<c008f3d4>] (__blocking_notifier_call_chain+0x50/0x68) [<c008f3d4>] (__blocking_notifier_call_chain+0x50/0x68) from [<c008f40c>] (blocking_notifier_call_chain+0x20/0x28) [<c008f40c>] (blocking_notifier_call_chain+0x20/0x28) from [<c00ac228>] (pm_notifier_call_chain+0x1c/0x34) [<c00ac228>] (pm_notifier_call_chain+0x1c/0x34) from [<c00ad38c>] (enter_state+0xec/0x128) [<c00ad38c>] (enter_state+0xec/0x128) from [<c00ad400>] (pm_suspend+0x38/0xa4) [<c00ad400>] (pm_suspend+0x38/0xa4) from [<c00ac114>] (state_store+0x70/0xc0) [<c00ac114>] (state_store+0x70/0xc0) from [<c027b1e8>] (kobj_attr_store+0x14/0x20) [<c027b1e8>] (kobj_attr_store+0x14/0x20) from [<c019cd9c>] (sysfs_write_file+0x104/0x184) [<c019cd9c>] (sysfs_write_file+0x104/0x184) from [<c0143038>] (vfs_write+0xd0/0x19c) [<c0143038>] (vfs_write+0xd0/0x19c) from [<c0143414>] (SyS_write+0x4c/0x78) [<c0143414>] (SyS_write+0x4c/0x78) from [<c000f080>] (ret_fast_syscall+0x0/0x30) Code: e1a00006 eb084346 e59b0020 e5951024 (e5903028) ---[ end trace 0488523c8f6b0f9d ]--- Signed-off-by: Bibek Basu <bbasu@nvidia.com> Acked-by: Viresh Kumar <viresh.kumar@linaro.org> Cc: 3.11+ <stable@vger.kernel.org> # 3.11+ Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2014-05-19 04:54:01 +00:00
mutex_unlock(&dbs_data->mutex);
break;
}
return 0;
}
EXPORT_SYMBOL_GPL(cpufreq_governor_dbs);