linux/drivers/base/power/opp/opp.h

222 lines
7.1 KiB
C
Raw Normal View History

/*
* Generic OPP Interface
*
* Copyright (C) 2009-2010 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.
*/
#ifndef __DRIVER_OPP_H__
#define __DRIVER_OPP_H__
#include <linux/device.h>
#include <linux/kernel.h>
#include <linux/list.h>
#include <linux/limits.h>
#include <linux/pm_opp.h>
#include <linux/rculist.h>
#include <linux/rcupdate.h>
struct clk;
struct regulator;
PM / OPP: Protect updates to list_dev with mutex dev_opp_list_lock is used everywhere to protect device and OPP lists, but dev_pm_opp_set_sharing_cpus() is missed somehow. And instead we used rcu-lock, which wouldn't help here as we are adding a new list_dev. This also fixes a problem where we have called kzalloc(..., GFP_KERNEL) from within rcu-lock, which isn't allowed as kzalloc can sleep when called with GFP_KERNEL. With CONFIG_DEBUG_ATOMIC_SLEEP set, we get following lockdep-splat: include/linux/rcupdate.h:578 Illegal context switch in RCU read-side critical section! other info that might help us debug this: rcu_scheduler_active = 1, debug_locks = 0 5 locks held by swapper/0/1: #0: (&dev->mutex){......}, at: [<c02f68f4>] __driver_attach+0x48/0x98 #1: (&dev->mutex){......}, at: [<c02f6904>] __driver_attach+0x58/0x98 #2: (cpu_hotplug.lock){++++++}, at: [<c00249d0>] get_online_cpus+0x40/0xb0 #3: (subsys mutex#5){+.+.+.}, at: [<c02f4f8c>] subsys_interface_register+0x44/0xdc #4: (rcu_read_lock){......}, at: [<c0305c80>] dev_pm_opp_set_sharing_cpus+0x0/0x1e4 stack backtrace: CPU: 1 PID: 1 Comm: swapper/0 Tainted: G W 4.3.0-rc7-00047-g81f5932958a8 #59 Hardware name: SAMSUNG EXYNOS (Flattened Device Tree) [<c0016874>] (unwind_backtrace) from [<c001355c>] (show_stack+0x10/0x14) [<c001355c>] (show_stack) from [<c022553c>] (dump_stack+0x94/0xbc) [<c022553c>] (dump_stack) from [<c004904c>] (___might_sleep+0x24c/0x298) [<c004904c>] (___might_sleep) from [<c00f07e4>] (kmem_cache_alloc+0xe8/0x164) [<c00f07e4>] (kmem_cache_alloc) from [<c0305354>] (_add_list_dev+0x30/0x58) [<c0305354>] (_add_list_dev) from [<c0305d50>] (dev_pm_opp_set_sharing_cpus+0xd0/0x1e4) [<c0305d50>] (dev_pm_opp_set_sharing_cpus) from [<c040eda4>] (cpufreq_init+0x4cc/0x62c) [<c040eda4>] (cpufreq_init) from [<c040a964>] (cpufreq_online+0xbc/0x73c) [<c040a964>] (cpufreq_online) from [<c02f4fe0>] (subsys_interface_register+0x98/0xdc) [<c02f4fe0>] (subsys_interface_register) from [<c040a640>] (cpufreq_register_driver+0x110/0x17c) [<c040a640>] (cpufreq_register_driver) from [<c040ef64>] (dt_cpufreq_probe+0x60/0x8c) [<c040ef64>] (dt_cpufreq_probe) from [<c02f8084>] (platform_drv_probe+0x44/0xa4) [<c02f8084>] (platform_drv_probe) from [<c02f67c0>] (driver_probe_device+0x208/0x2f4) [<c02f67c0>] (driver_probe_device) from [<c02f6940>] (__driver_attach+0x94/0x98) [<c02f6940>] (__driver_attach) from [<c02f4c1c>] (bus_for_each_dev+0x68/0x9c) Reported-by: Michael Turquette <mturquette@baylibre.com> Reviewed-by: Stephen Boyd <sboyd@codeaurora.org> Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org> Cc: 4.3 <stable@vger.kernel.org> # 4.3 Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2015-11-05 16:51:19 +08:00
/* Lock to allow exclusive modification to the device and opp lists */
extern struct mutex opp_table_lock;
PM / OPP: Protect updates to list_dev with mutex dev_opp_list_lock is used everywhere to protect device and OPP lists, but dev_pm_opp_set_sharing_cpus() is missed somehow. And instead we used rcu-lock, which wouldn't help here as we are adding a new list_dev. This also fixes a problem where we have called kzalloc(..., GFP_KERNEL) from within rcu-lock, which isn't allowed as kzalloc can sleep when called with GFP_KERNEL. With CONFIG_DEBUG_ATOMIC_SLEEP set, we get following lockdep-splat: include/linux/rcupdate.h:578 Illegal context switch in RCU read-side critical section! other info that might help us debug this: rcu_scheduler_active = 1, debug_locks = 0 5 locks held by swapper/0/1: #0: (&dev->mutex){......}, at: [<c02f68f4>] __driver_attach+0x48/0x98 #1: (&dev->mutex){......}, at: [<c02f6904>] __driver_attach+0x58/0x98 #2: (cpu_hotplug.lock){++++++}, at: [<c00249d0>] get_online_cpus+0x40/0xb0 #3: (subsys mutex#5){+.+.+.}, at: [<c02f4f8c>] subsys_interface_register+0x44/0xdc #4: (rcu_read_lock){......}, at: [<c0305c80>] dev_pm_opp_set_sharing_cpus+0x0/0x1e4 stack backtrace: CPU: 1 PID: 1 Comm: swapper/0 Tainted: G W 4.3.0-rc7-00047-g81f5932958a8 #59 Hardware name: SAMSUNG EXYNOS (Flattened Device Tree) [<c0016874>] (unwind_backtrace) from [<c001355c>] (show_stack+0x10/0x14) [<c001355c>] (show_stack) from [<c022553c>] (dump_stack+0x94/0xbc) [<c022553c>] (dump_stack) from [<c004904c>] (___might_sleep+0x24c/0x298) [<c004904c>] (___might_sleep) from [<c00f07e4>] (kmem_cache_alloc+0xe8/0x164) [<c00f07e4>] (kmem_cache_alloc) from [<c0305354>] (_add_list_dev+0x30/0x58) [<c0305354>] (_add_list_dev) from [<c0305d50>] (dev_pm_opp_set_sharing_cpus+0xd0/0x1e4) [<c0305d50>] (dev_pm_opp_set_sharing_cpus) from [<c040eda4>] (cpufreq_init+0x4cc/0x62c) [<c040eda4>] (cpufreq_init) from [<c040a964>] (cpufreq_online+0xbc/0x73c) [<c040a964>] (cpufreq_online) from [<c02f4fe0>] (subsys_interface_register+0x98/0xdc) [<c02f4fe0>] (subsys_interface_register) from [<c040a640>] (cpufreq_register_driver+0x110/0x17c) [<c040a640>] (cpufreq_register_driver) from [<c040ef64>] (dt_cpufreq_probe+0x60/0x8c) [<c040ef64>] (dt_cpufreq_probe) from [<c02f8084>] (platform_drv_probe+0x44/0xa4) [<c02f8084>] (platform_drv_probe) from [<c02f67c0>] (driver_probe_device+0x208/0x2f4) [<c02f67c0>] (driver_probe_device) from [<c02f6940>] (__driver_attach+0x94/0x98) [<c02f6940>] (__driver_attach) from [<c02f4c1c>] (bus_for_each_dev+0x68/0x9c) Reported-by: Michael Turquette <mturquette@baylibre.com> Reviewed-by: Stephen Boyd <sboyd@codeaurora.org> Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org> Cc: 4.3 <stable@vger.kernel.org> # 4.3 Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2015-11-05 16:51:19 +08:00
extern struct list_head opp_tables;
/*
* Internal data structure organization with the OPP layer library is as
* follows:
* opp_tables (root)
* |- device 1 (represents voltage domain 1)
* | |- opp 1 (availability, freq, voltage)
* | |- opp 2 ..
* ... ...
* | `- opp n ..
* |- device 2 (represents the next voltage domain)
* ...
* `- device m (represents mth voltage domain)
* device 1, 2.. are represented by opp_table structure while each opp
* is represented by the opp structure.
*/
/**
* struct dev_pm_opp - Generic OPP description structure
* @node: opp table node. The nodes are maintained throughout the lifetime
* of boot. It is expected only an optimal set of OPPs are
* added to the library by the SoC framework.
* RCU usage: opp table is traversed with RCU locks. node
* modification is possible realtime, hence the modifications
* are protected by the opp_table_lock for integrity.
* IMPORTANT: the opp nodes should be maintained in increasing
* order.
* @available: true/false - marks if this OPP as available or not
* @dynamic: not-created from static DT entries.
* @turbo: true if turbo (boost) OPP
* @suspend: true if suspend OPP
* @rate: Frequency in hertz
* @supply: Power supply voltage/current values
* @clock_latency_ns: Latency (in nanoseconds) of switching to this OPP's
* frequency from any other OPP's frequency.
* @opp_table: points back to the opp_table struct this opp belongs to
* @rcu_head: RCU callback head used for deferred freeing
* @np: OPP's device node.
* @dentry: debugfs dentry pointer (per opp)
*
* This structure stores the OPP information for a given device.
*/
struct dev_pm_opp {
struct list_head node;
bool available;
bool dynamic;
bool turbo;
bool suspend;
unsigned long rate;
struct dev_pm_opp_supply supply;
unsigned long clock_latency_ns;
struct opp_table *opp_table;
struct rcu_head rcu_head;
struct device_node *np;
#ifdef CONFIG_DEBUG_FS
struct dentry *dentry;
#endif
};
/**
* struct opp_device - devices managed by 'struct opp_table'
* @node: list node
* @dev: device to which the struct object belongs
* @rcu_head: RCU callback head used for deferred freeing
* @dentry: debugfs dentry pointer (per device)
*
* This is an internal data structure maintaining the devices that are managed
* by 'struct opp_table'.
*/
struct opp_device {
struct list_head node;
const struct device *dev;
struct rcu_head rcu_head;
#ifdef CONFIG_DEBUG_FS
struct dentry *dentry;
#endif
};
enum opp_table_access {
OPP_TABLE_ACCESS_UNKNOWN = 0,
OPP_TABLE_ACCESS_EXCLUSIVE = 1,
OPP_TABLE_ACCESS_SHARED = 2,
};
/**
* struct opp_table - Device opp structure
* @node: table node - contains the devices with OPPs that
* have been registered. Nodes once added are not modified in this
* table.
* RCU usage: nodes are not modified in the table of opp_table,
* however addition is possible and is secured by opp_table_lock
* @srcu_head: notifier head to notify the OPP availability changes.
* @rcu_head: RCU callback head used for deferred freeing
* @dev_list: list of devices that share these OPPs
* @opp_list: table of opps
* @np: struct device_node pointer for opp's DT node.
* @clock_latency_ns_max: Max clock latency in nanoseconds.
* @shared_opp: OPP is shared between multiple devices.
* @suspend_opp: Pointer to OPP to be used during device suspend.
* @supported_hw: Array of version number to support.
* @supported_hw_count: Number of elements in supported_hw array.
* @prop_name: A name to postfix to many DT properties, while parsing them.
* @clk: Device's clock handle
* @regulator: Supply regulator
* @dentry: debugfs dentry pointer of the real device directory (not links).
* @dentry_name: Name of the real dentry.
*
* @voltage_tolerance_v1: In percentage, for v1 bindings only.
*
* This is an internal data structure maintaining the link to opps attached to
* a device. This structure is not meant to be shared to users as it is
* meant for book keeping and private to OPP library.
*
* Because the opp structures can be used from both rcu and srcu readers, we
* need to wait for the grace period of both of them before freeing any
* resources. And so we have used kfree_rcu() from within call_srcu() handlers.
*/
struct opp_table {
struct list_head node;
struct srcu_notifier_head srcu_head;
struct rcu_head rcu_head;
struct list_head dev_list;
struct list_head opp_list;
struct device_node *np;
unsigned long clock_latency_ns_max;
/* For backward compatibility with v1 bindings */
unsigned int voltage_tolerance_v1;
enum opp_table_access shared_opp;
struct dev_pm_opp *suspend_opp;
unsigned int *supported_hw;
unsigned int supported_hw_count;
const char *prop_name;
struct clk *clk;
struct regulator *regulator;
#ifdef CONFIG_DEBUG_FS
struct dentry *dentry;
char dentry_name[NAME_MAX];
#endif
};
/* Routines internal to opp core */
struct opp_table *_find_opp_table(struct device *dev);
struct opp_device *_add_opp_dev(const struct device *dev, struct opp_table *opp_table);
void _dev_pm_opp_remove_table(struct device *dev, bool remove_all);
struct dev_pm_opp *_allocate_opp(struct device *dev, struct opp_table **opp_table);
int _opp_add(struct device *dev, struct dev_pm_opp *new_opp, struct opp_table *opp_table);
void _opp_remove(struct opp_table *opp_table, struct dev_pm_opp *opp, bool notify);
int _opp_add_v1(struct device *dev, unsigned long freq, long u_volt, bool dynamic);
void _dev_pm_opp_cpumask_remove_table(const struct cpumask *cpumask, bool of);
#ifdef CONFIG_OF
void _of_init_opp_table(struct opp_table *opp_table, struct device *dev);
#else
static inline void _of_init_opp_table(struct opp_table *opp_table, struct device *dev) {}
#endif
#ifdef CONFIG_DEBUG_FS
void opp_debug_remove_one(struct dev_pm_opp *opp);
int opp_debug_create_one(struct dev_pm_opp *opp, struct opp_table *opp_table);
int opp_debug_register(struct opp_device *opp_dev, struct opp_table *opp_table);
void opp_debug_unregister(struct opp_device *opp_dev, struct opp_table *opp_table);
#else
static inline void opp_debug_remove_one(struct dev_pm_opp *opp) {}
static inline int opp_debug_create_one(struct dev_pm_opp *opp,
struct opp_table *opp_table)
{ return 0; }
static inline int opp_debug_register(struct opp_device *opp_dev,
struct opp_table *opp_table)
{ return 0; }
static inline void opp_debug_unregister(struct opp_device *opp_dev,
struct opp_table *opp_table)
{ }
#endif /* DEBUG_FS */
#endif /* __DRIVER_OPP_H__ */