linux_dsm_epyc7002/drivers/cpufreq/cpufreq_opp.c
Stephen Boyd 3c5445ce3a cpufreq: OPP: Avoid sleeping while atomic
We allocate the cpufreq table after calling rcu_read_lock(),
which disables preemption. This causes scheduling while atomic
warnings. Use GFP_ATOMIC instead of GFP_KERNEL and update for
kcalloc while we're here.

BUG: sleeping function called from invalid context at mm/slub.c:1246
in_atomic(): 0, irqs_disabled(): 0, pid: 80, name: modprobe
5 locks held by modprobe/80:
 #0:  (&dev->mutex){......}, at: [<c050d484>] __driver_attach+0x48/0x98
 #1:  (&dev->mutex){......}, at: [<c050d494>] __driver_attach+0x58/0x98
 #2:  (subsys mutex#5){+.+.+.}, at: [<c050c114>] subsys_interface_register+0x38/0xc8
 #3:  (cpufreq_rwsem){.+.+.+}, at: [<c05a9c8c>] __cpufreq_add_dev.isra.22+0x84/0x92c
 #4:  (rcu_read_lock){......}, at: [<c05ab24c>] dev_pm_opp_init_cpufreq_table+0x18/0x10c
Preemption disabled at:[<  (null)>]   (null)

CPU: 2 PID: 80 Comm: modprobe Not tainted 3.16.0-rc3-next-20140701-00035-g286857f216aa-dirty #217
[<c0214da8>] (unwind_backtrace) from [<c02123f8>] (show_stack+0x10/0x14)
[<c02123f8>] (show_stack) from [<c070141c>] (dump_stack+0x70/0xbc)
[<c070141c>] (dump_stack) from [<c02f4cb0>] (__kmalloc+0x124/0x250)
[<c02f4cb0>] (__kmalloc) from [<c05ab270>] (dev_pm_opp_init_cpufreq_table+0x3c/0x10c)
[<c05ab270>] (dev_pm_opp_init_cpufreq_table) from [<bf000508>] (cpufreq_init+0x48/0x378 [cpufreq_generic])
[<bf000508>] (cpufreq_init [cpufreq_generic]) from [<c05a9e08>] (__cpufreq_add_dev.isra.22+0x200/0x92c)
[<c05a9e08>] (__cpufreq_add_dev.isra.22) from [<c050c160>] (subsys_interface_register+0x84/0xc8)
[<c050c160>] (subsys_interface_register) from [<c05a9494>] (cpufreq_register_driver+0x108/0x2d8)
[<c05a9494>] (cpufreq_register_driver) from [<bf000888>] (generic_cpufreq_probe+0x50/0x74 [cpufreq_generic])
[<bf000888>] (generic_cpufreq_probe [cpufreq_generic]) from [<c050e994>] (platform_drv_probe+0x18/0x48)
[<c050e994>] (platform_drv_probe) from [<c050d1f4>] (driver_probe_device+0x128/0x370)
[<c050d1f4>] (driver_probe_device) from [<c050d4d0>] (__driver_attach+0x94/0x98)
[<c050d4d0>] (__driver_attach) from [<c050b778>] (bus_for_each_dev+0x54/0x88)
[<c050b778>] (bus_for_each_dev) from [<c050c894>] (bus_add_driver+0xe8/0x204)
[<c050c894>] (bus_add_driver) from [<c050dd48>] (driver_register+0x78/0xf4)
[<c050dd48>] (driver_register) from [<c0208870>] (do_one_initcall+0xac/0x1d8)
[<c0208870>] (do_one_initcall) from [<c028b6b4>] (load_module+0x190c/0x21e8)
[<c028b6b4>] (load_module) from [<c028c034>] (SyS_init_module+0xa4/0x110)
[<c028c034>] (SyS_init_module) from [<c020f0c0>] (ret_fast_syscall+0x0/0x48)

Fixes: a0dd7b7965 (PM / OPP: Move cpufreq specific OPP functions out of generic OPP library)
Signed-off-by: Stephen Boyd <sboyd@codeaurora.org>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
Cc: 3.16+ <stable@vger.kernel.org> # 3.16+
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2014-08-07 00:23:23 +02:00

111 lines
3.1 KiB
C

/*
* Generic OPP helper interface for CPUFreq drivers
*
* Copyright (C) 2009-2014 Texas Instruments Incorporated.
* Nishanth Menon
* Romit Dasgupta
* Kevin Hilman
*
* 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.
*/
#include <linux/cpufreq.h>
#include <linux/device.h>
#include <linux/err.h>
#include <linux/errno.h>
#include <linux/export.h>
#include <linux/kernel.h>
#include <linux/pm_opp.h>
#include <linux/rcupdate.h>
#include <linux/slab.h>
/**
* dev_pm_opp_init_cpufreq_table() - create a cpufreq table for a device
* @dev: device for which we do this operation
* @table: Cpufreq table returned back to caller
*
* Generate a cpufreq table for a provided device- this assumes that the
* opp list is already initialized and ready for usage.
*
* This function allocates required memory for the cpufreq table. It is
* expected that the caller does the required maintenance such as freeing
* the table as required.
*
* Returns -EINVAL for bad pointers, -ENODEV if the device is not found, -ENOMEM
* if no memory available for the operation (table is not populated), returns 0
* if successful and table is populated.
*
* WARNING: It is important for the callers to ensure refreshing their copy of
* the table if any of the mentioned functions have been invoked in the interim.
*
* Locking: The internal device_opp and opp structures are RCU protected.
* Since we just use the regular accessor functions to access the internal data
* structures, we use RCU read lock inside this function. As a result, users of
* this function DONOT need to use explicit locks for invoking.
*/
int dev_pm_opp_init_cpufreq_table(struct device *dev,
struct cpufreq_frequency_table **table)
{
struct dev_pm_opp *opp;
struct cpufreq_frequency_table *freq_table = NULL;
int i, max_opps, ret = 0;
unsigned long rate;
rcu_read_lock();
max_opps = dev_pm_opp_get_opp_count(dev);
if (max_opps <= 0) {
ret = max_opps ? max_opps : -ENODATA;
goto out;
}
freq_table = kcalloc(sizeof(*freq_table), (max_opps + 1), GFP_ATOMIC);
if (!freq_table) {
ret = -ENOMEM;
goto out;
}
for (i = 0, rate = 0; i < max_opps; i++, rate++) {
/* find next rate */
opp = dev_pm_opp_find_freq_ceil(dev, &rate);
if (IS_ERR(opp)) {
ret = PTR_ERR(opp);
goto out;
}
freq_table[i].driver_data = i;
freq_table[i].frequency = rate / 1000;
}
freq_table[i].driver_data = i;
freq_table[i].frequency = CPUFREQ_TABLE_END;
*table = &freq_table[0];
out:
rcu_read_unlock();
if (ret)
kfree(freq_table);
return ret;
}
EXPORT_SYMBOL_GPL(dev_pm_opp_init_cpufreq_table);
/**
* dev_pm_opp_free_cpufreq_table() - free the cpufreq table
* @dev: device for which we do this operation
* @table: table to free
*
* Free up the table allocated by dev_pm_opp_init_cpufreq_table
*/
void dev_pm_opp_free_cpufreq_table(struct device *dev,
struct cpufreq_frequency_table **table)
{
if (!table)
return;
kfree(*table);
*table = NULL;
}
EXPORT_SYMBOL_GPL(dev_pm_opp_free_cpufreq_table);