2
0
mirror of git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git synced 2025-09-04 20:19:47 +08:00
linux/kernel/power/power.h
Linus Torvalds c89756bcf4 Power management updates for 6.16-rc1
- Fix potential division-by-zero error in em_compute_costs() (Yaxiong
    Tian).
 
  - Fix typos in energy model documentation and example driver code (Moon
    Hee Lee, Atul Kumar Pant).
 
  - Rearrange the energy model management code and add a new function for
    adjusting a CPU energy model after adjusting the capacity of the
    given CPU to it (Rafael Wysocki).
 
  - Refactor cpufreq_online(), add and use cpufreq policy locking guards,
    use __free() in policy reference counting, and clean up core cpufreq
    code on top of that (Rafael Wysocki).
 
  - Fix boost handling on CPU suspend/resume and sysfs updates (Viresh
    Kumar).
 
  - Fix des_perf clamping with max_perf in amd_pstate_update() (Dhananjay
    Ugwekar).
 
  - Add offline, online and suspend callbacks to the amd-pstate driver,
    rename and use the existing amd_pstate_epp callbacks in it (Dhananjay
    Ugwekar).
 
  - Add support for the "Requested CPU Min frequency" BIOS option to the
    amd-pstate driver (Dhananjay Ugwekar).
 
  - Reset amd-pstate driver mode after running selftests (Swapnil
    Sapkal).
 
  - Avoid shadowing ret in amd_pstate_ut_check_driver() (Nathan
    Chancellor).
 
  - Add helper for governor checks to the schedutil cpufreq governor and
    move cpufreq-specific EAS checks to cpufreq (Rafael Wysocki).
 
  - Populate the cpu_capacity sysfs entries from the intel_pstate driver
    after registering asym capacity support (Ricardo Neri).
 
  - Add support for enabling Energy-aware scheduling (EAS) to the
    intel_pstate driver when operating in the passive mode on a hybrid
    platform (Rafael Wysocki).
 
  - Drop redundant cpus_read_lock() from store_local_boost() in the
    cpufreq core (Seyediman Seyedarab).
 
  - Replace sscanf() with kstrtouint() in the cpufreq code and use a
    symbol instead of a raw number in it (Bowen Yu).
 
  - Add support for autonomous CPU performance state selection to the
    CPPC cpufreq driver (Lifeng Zheng).
 
  - OPP: Add dev_pm_opp_set_level() (Praveen Talari).
 
  - Introduce scope-based cleanup headers and mutex locking guards in OPP
    core (Viresh Kumar).
 
  - Switch OPP to use kmemdup_array() (Zhang Enpei).
 
  - Optimize bucket assignment when next_timer_ns equals KTIME_MAX in the
    menu cpuidle governor (Zhongqiu Han).
 
  - Convert the cpuidle PSCI driver to a faux device one (Sudeep Holla).
 
  - Add C1 demotion on/off sysfs knob to the intel_idle driver (Artem
    Bityutskiy).
 
  - Fix typos in two comments in the teo cpuidle governor (Atul Kumar
    Pant).
 
  - Fix denying of auto suspend in pm_suspend_timer_fn() (Charan Teja
    Kalla).
 
  - Move debug runtime PM attributes to runtime_attrs[] (Rafael Wysocki).
 
  - Add new devm_ functions for enabling runtime PM and runtime PM
    reference counting (Bence Csókás).
 
  - Remove size arguments from strscpy() calls in the hibernation core
    code (Thorsten Blum).
 
  - Adjust the handling of devices with asynchronous suspend enabled
    during system suspend and resume to start resuming them immediately
    after resuming their parents and to start suspending such a device
    immediately after suspending its first child (Rafael Wysocki).
 
  - Adjust messages printed during tasks freezing to avoid using
    pr_cont() (Andrew Sayers, Paul Menzel).
 
  - Clean up unnecessary usage of !! in pm_print_times_init() (Zihuan
    Zhang).
 
  - Add missing wakeup source attribute relax_count to sysfs and
    remove the space character at the end ofi the string produced by
    pm_show_wakelocks() (Zijun Hu).
 
  - Add configurable pm_test delay for hibernation (Zihuan Zhang).
 
  - Disable asynchronous suspend in ucsi_ccg_probe() to prevent the
    cypd4226 device on Tegra boards from suspending prematurely (Jon
    Hunter).
 
  - Unbreak printing PM debug messages during hibernation and clean up
    some related code (Rafael Wysocki).
 
  - Add a systemd service to run cpupower and change cpupower binding's
    Makefile to use -lcpupower (John B. Wyatt IV, Francesco Poli).
 -----BEGIN PGP SIGNATURE-----
 
 iQFGBAABCAAwFiEEcM8Aw/RY0dgsiRUR7l+9nS/U47UFAmg0xS0SHHJqd0Byand5
 c29ja2kubmV0AAoJEO5fvZ0v1OO1AwwH/Rvgza5YBPb9JZqWJT/ZiBw7HcEWHhP1
 fNfcVU1gXPZiF0yoPfjfJua6BcLj6lyQ3d/+zWqqAcWfmRSD6HPe8yYz8qALUAqj
 RWhDa04aGj6B9bQuOjejatznYlQlkwCRT7zec+75D+dAHVMqR/Vt2LFAetCadgHe
 MQibAQmVFXu3RFkBjReTAdGzVoTXkwoZDrzdfA2aFAfMJNtJpOW4atUZvnucuctv
 VK3ZratrctCIw7yXEoB1nWSmlY7R5JlslplBfndjmmOnky3YxNr7C6paqwtbTWoF
 MiX48qkmLOGeO6gS8s/lVCDQ4oZ+UNFQvXRsM5NGjycBikhHX/dp/w4=
 =dIqJ
 -----END PGP SIGNATURE-----

Merge tag 'pm-6.16-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm

Pull power management updates from Rafael Wysocki:
 "Once again, the changes are dominated by cpufreq updates, but this
  time the majority of them are cpufreq core changes, mostly related to
  the introduction of policy locking guards and __free() usage, and
  fixes related to boost handling.

  Still, there is also a significant update of the intel_pstate driver
  making it register an energy model when running on a hybrid platform
  which is used for enabling energy-aware scheduling (EAS) if the driver
  operates in the passive mode (and schedutil is used as the cpufreq
  governor for all CPUs which is the passive mode default).

  There are some amd-pstate driver updates too, for a good measure,
  including the "Requested CPU Min frequency" BIOS option support and
  new online/offline callbacks.

  In the cpuidle space, the most significant change is the addition of a
  C1 demotion on/off sysfs knob to intel_idle which should help some
  users to configure their systems more precisely. There is also the
  conversion of the PSCI cpuidle driver to a faux device one and there
  are two small updates of cpuidle governors.

  Device power management is also modified quite a bit, especially the
  handling of devices with asynchronous suspend and resume enabled
  during system transitions. They are now going to be handled more
  asynchronously during suspend transitions and somewhat less
  aggressively during resume transitions.

  Apart from the above, the operating performance points (OPP) library
  is now going to use mutex locking guards and scope-based cleanup
  helpers and there is the usual bunch of assorted fixes and code
  cleanups.

  Specifics:

   - Fix potential division-by-zero error in em_compute_costs() (Yaxiong
     Tian)

   - Fix typos in energy model documentation and example driver code
     (Moon Hee Lee, Atul Kumar Pant)

   - Rearrange the energy model management code and add a new function
     for adjusting a CPU energy model after adjusting the capacity of
     the given CPU to it (Rafael Wysocki)

   - Refactor cpufreq_online(), add and use cpufreq policy locking
     guards, use __free() in policy reference counting, and clean up
     core cpufreq code on top of that (Rafael Wysocki)

   - Fix boost handling on CPU suspend/resume and sysfs updates (Viresh
     Kumar)

   - Fix des_perf clamping with max_perf in amd_pstate_update()
     (Dhananjay Ugwekar)

   - Add offline, online and suspend callbacks to the amd-pstate driver,
     rename and use the existing amd_pstate_epp callbacks in it
     (Dhananjay Ugwekar)

   - Add support for the "Requested CPU Min frequency" BIOS option to
     the amd-pstate driver (Dhananjay Ugwekar)

   - Reset amd-pstate driver mode after running selftests (Swapnil
     Sapkal)

   - Avoid shadowing ret in amd_pstate_ut_check_driver() (Nathan
     Chancellor)

   - Add helper for governor checks to the schedutil cpufreq governor
     and move cpufreq-specific EAS checks to cpufreq (Rafael Wysocki)

   - Populate the cpu_capacity sysfs entries from the intel_pstate
     driver after registering asym capacity support (Ricardo Neri)

   - Add support for enabling Energy-aware scheduling (EAS) to the
     intel_pstate driver when operating in the passive mode on a hybrid
     platform (Rafael Wysocki)

   - Drop redundant cpus_read_lock() from store_local_boost() in the
     cpufreq core (Seyediman Seyedarab)

   - Replace sscanf() with kstrtouint() in the cpufreq code and use a
     symbol instead of a raw number in it (Bowen Yu)

   - Add support for autonomous CPU performance state selection to the
     CPPC cpufreq driver (Lifeng Zheng)

   - OPP: Add dev_pm_opp_set_level() (Praveen Talari)

   - Introduce scope-based cleanup headers and mutex locking guards in
     OPP core (Viresh Kumar)

   - Switch OPP to use kmemdup_array() (Zhang Enpei)

   - Optimize bucket assignment when next_timer_ns equals KTIME_MAX in
     the menu cpuidle governor (Zhongqiu Han)

   - Convert the cpuidle PSCI driver to a faux device one (Sudeep Holla)

   - Add C1 demotion on/off sysfs knob to the intel_idle driver (Artem
     Bityutskiy)

   - Fix typos in two comments in the teo cpuidle governor (Atul Kumar
     Pant)

   - Fix denying of auto suspend in pm_suspend_timer_fn() (Charan Teja
     Kalla)

   - Move debug runtime PM attributes to runtime_attrs[] (Rafael
     Wysocki)

   - Add new devm_ functions for enabling runtime PM and runtime PM
     reference counting (Bence Csókás)

   - Remove size arguments from strscpy() calls in the hibernation core
     code (Thorsten Blum)

   - Adjust the handling of devices with asynchronous suspend enabled
     during system suspend and resume to start resuming them immediately
     after resuming their parents and to start suspending such a device
     immediately after suspending its first child (Rafael Wysocki)

   - Adjust messages printed during tasks freezing to avoid using
     pr_cont() (Andrew Sayers, Paul Menzel)

   - Clean up unnecessary usage of !! in pm_print_times_init() (Zihuan
     Zhang)

   - Add missing wakeup source attribute relax_count to sysfs and remove
     the space character at the end ofi the string produced by
     pm_show_wakelocks() (Zijun Hu)

   - Add configurable pm_test delay for hibernation (Zihuan Zhang)

   - Disable asynchronous suspend in ucsi_ccg_probe() to prevent the
     cypd4226 device on Tegra boards from suspending prematurely (Jon
     Hunter)

   - Unbreak printing PM debug messages during hibernation and clean up
     some related code (Rafael Wysocki)

   - Add a systemd service to run cpupower and change cpupower binding's
     Makefile to use -lcpupower (John B. Wyatt IV, Francesco Poli)"

* tag 'pm-6.16-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm: (72 commits)
  cpufreq: CPPC: Add support for autonomous selection
  cpufreq: Update sscanf() to kstrtouint()
  cpufreq: Replace magic number
  OPP: switch to use kmemdup_array()
  PM: freezer: Rewrite restarting tasks log to remove stray *done.*
  PM: runtime: fix denying of auto suspend in pm_suspend_timer_fn()
  cpufreq: drop redundant cpus_read_lock() from store_local_boost()
  cpupower: do not install files to /etc/default/
  cpupower: do not call systemctl at install time
  cpupower: do not write DESTDIR to cpupower.service
  PM: sleep: Introduce pm_sleep_transition_in_progress()
  cpufreq/amd-pstate: Avoid shadowing ret in amd_pstate_ut_check_driver()
  cpufreq: intel_pstate: Document hybrid processor support
  cpufreq: intel_pstate: EAS: Increase cost for CPUs using L3 cache
  cpufreq: intel_pstate: EAS support for hybrid platforms
  PM: EM: Introduce em_adjust_cpu_capacity()
  PM: EM: Move CPU capacity check to em_adjust_new_capacity()
  PM: EM: Documentation: Fix typos in example driver code
  cpufreq: Drop policy locking from cpufreq_policy_is_good_for_eas()
  PM: sleep: Introduce pm_suspend_in_progress()
  ...
2025-05-27 16:48:47 -07:00

359 lines
9.9 KiB
C

/* SPDX-License-Identifier: GPL-2.0 */
#include <linux/suspend.h>
#include <linux/suspend_ioctls.h>
#include <linux/utsname.h>
#include <linux/freezer.h>
#include <linux/compiler.h>
#include <linux/cpu.h>
#include <linux/cpuidle.h>
#include <linux/crypto.h>
struct swsusp_info {
struct new_utsname uts;
u32 version_code;
unsigned long num_physpages;
int cpus;
unsigned long image_pages;
unsigned long pages;
unsigned long size;
} __aligned(PAGE_SIZE);
#if defined(CONFIG_SUSPEND) || defined(CONFIG_HIBERNATION)
extern bool filesystem_freeze_enabled;
#endif
#ifdef CONFIG_HIBERNATION
/* kernel/power/snapshot.c */
extern void __init hibernate_reserved_size_init(void);
extern void __init hibernate_image_size_init(void);
#ifdef CONFIG_ARCH_HIBERNATION_HEADER
/* Maximum size of architecture specific data in a hibernation header */
#define MAX_ARCH_HEADER_SIZE (sizeof(struct new_utsname) + 4)
static inline int init_header_complete(struct swsusp_info *info)
{
return arch_hibernation_header_save(info, MAX_ARCH_HEADER_SIZE);
}
static inline const char *check_image_kernel(struct swsusp_info *info)
{
return arch_hibernation_header_restore(info) ?
"architecture specific data" : NULL;
}
#endif /* CONFIG_ARCH_HIBERNATION_HEADER */
/*
* Keep some memory free so that I/O operations can succeed without paging
* [Might this be more than 4 MB?]
*/
#define PAGES_FOR_IO ((4096 * 1024) >> PAGE_SHIFT)
/*
* Keep 1 MB of memory free so that device drivers can allocate some pages in
* their .suspend() routines without breaking the suspend to disk.
*/
#define SPARE_PAGES ((1024 * 1024) >> PAGE_SHIFT)
asmlinkage int swsusp_save(void);
/* kernel/power/hibernate.c */
extern bool freezer_test_done;
extern char hib_comp_algo[CRYPTO_MAX_ALG_NAME];
/* kernel/power/swap.c */
extern unsigned int swsusp_header_flags;
extern int hibernation_snapshot(int platform_mode);
extern int hibernation_restore(int platform_mode);
extern int hibernation_platform_enter(void);
#ifdef CONFIG_STRICT_KERNEL_RWX
/* kernel/power/snapshot.c */
extern void enable_restore_image_protection(void);
#else
static inline void enable_restore_image_protection(void) {}
#endif /* CONFIG_STRICT_KERNEL_RWX */
extern bool hibernation_in_progress(void);
#else /* !CONFIG_HIBERNATION */
static inline void hibernate_reserved_size_init(void) {}
static inline void hibernate_image_size_init(void) {}
static inline bool hibernation_in_progress(void) { return false; }
#endif /* !CONFIG_HIBERNATION */
#define power_attr(_name) \
static struct kobj_attribute _name##_attr = { \
.attr = { \
.name = __stringify(_name), \
.mode = 0644, \
}, \
.show = _name##_show, \
.store = _name##_store, \
}
#define power_attr_ro(_name) \
static struct kobj_attribute _name##_attr = { \
.attr = { \
.name = __stringify(_name), \
.mode = S_IRUGO, \
}, \
.show = _name##_show, \
}
/* Preferred image size in bytes (default 500 MB) */
extern unsigned long image_size;
/* Size of memory reserved for drivers (default SPARE_PAGES x PAGE_SIZE) */
extern unsigned long reserved_size;
extern int in_suspend;
extern dev_t swsusp_resume_device;
extern sector_t swsusp_resume_block;
extern int create_basic_memory_bitmaps(void);
extern void free_basic_memory_bitmaps(void);
extern int hibernate_preallocate_memory(void);
extern void clear_or_poison_free_pages(void);
/*
* Auxiliary structure used for reading the snapshot image data and
* metadata from and writing them to the list of page backup entries
* (PBEs) which is the main data structure of swsusp.
*
* Using struct snapshot_handle we can transfer the image, including its
* metadata, as a continuous sequence of bytes with the help of
* snapshot_read_next() and snapshot_write_next().
*
* The code that writes the image to a storage or transfers it to
* the user land is required to use snapshot_read_next() for this
* purpose and it should not make any assumptions regarding the internal
* structure of the image. Similarly, the code that reads the image from
* a storage or transfers it from the user land is required to use
* snapshot_write_next().
*
* This may allow us to change the internal structure of the image
* in the future with considerably less effort.
*/
struct snapshot_handle {
unsigned int cur; /* number of the block of PAGE_SIZE bytes the
* next operation will refer to (ie. current)
*/
void *buffer; /* address of the block to read from
* or write to
*/
int sync_read; /* Set to one to notify the caller of
* snapshot_write_next() that it may
* need to call wait_on_bio_chain()
*/
};
/* This macro returns the address from/to which the caller of
* snapshot_read_next()/snapshot_write_next() is allowed to
* read/write data after the function returns
*/
#define data_of(handle) ((handle).buffer)
extern unsigned int snapshot_additional_pages(struct zone *zone);
extern unsigned long snapshot_get_image_size(void);
extern int snapshot_read_next(struct snapshot_handle *handle);
extern int snapshot_write_next(struct snapshot_handle *handle);
int snapshot_write_finalize(struct snapshot_handle *handle);
extern int snapshot_image_loaded(struct snapshot_handle *handle);
extern bool hibernate_acquire(void);
extern void hibernate_release(void);
extern sector_t alloc_swapdev_block(int swap);
extern void free_all_swap_pages(int swap);
extern int swsusp_swap_in_use(void);
/*
* Flags that can be passed from the hibernatig hernel to the "boot" kernel in
* the image header.
*/
#define SF_COMPRESSION_ALG_LZO 0 /* dummy, details given below */
#define SF_PLATFORM_MODE 1
#define SF_NOCOMPRESS_MODE 2
#define SF_CRC32_MODE 4
#define SF_HW_SIG 8
/*
* Bit to indicate the compression algorithm to be used(for LZ4). The same
* could be checked while saving/loading image to/from disk to use the
* corresponding algorithms.
*
* By default, LZO compression is enabled if SF_CRC32_MODE is set. Use
* SF_COMPRESSION_ALG_LZ4 to override this behaviour and use LZ4.
*
* SF_CRC32_MODE, SF_COMPRESSION_ALG_LZO(dummy) -> Compression, LZO
* SF_CRC32_MODE, SF_COMPRESSION_ALG_LZ4 -> Compression, LZ4
*/
#define SF_COMPRESSION_ALG_LZ4 16
/* kernel/power/hibernate.c */
int swsusp_check(bool exclusive);
extern void swsusp_free(void);
extern int swsusp_read(unsigned int *flags_p);
extern int swsusp_write(unsigned int flags);
void swsusp_close(void);
#ifdef CONFIG_SUSPEND
extern int swsusp_unmark(void);
#else
static inline int swsusp_unmark(void) { return 0; }
#endif
struct __kernel_old_timeval;
/* kernel/power/swsusp.c */
extern void swsusp_show_speed(ktime_t, ktime_t, unsigned int, char *);
#ifdef CONFIG_SUSPEND
/* kernel/power/suspend.c */
extern const char * const pm_labels[];
extern const char *pm_states[];
extern const char *mem_sleep_states[];
extern int suspend_devices_and_enter(suspend_state_t state);
#else /* !CONFIG_SUSPEND */
#define mem_sleep_current PM_SUSPEND_ON
static inline int suspend_devices_and_enter(suspend_state_t state)
{
return -ENOSYS;
}
#endif /* !CONFIG_SUSPEND */
#ifdef CONFIG_PM_TEST_SUSPEND
/* kernel/power/suspend_test.c */
extern void suspend_test_start(void);
extern void suspend_test_finish(const char *label);
#else /* !CONFIG_PM_TEST_SUSPEND */
static inline void suspend_test_start(void) {}
static inline void suspend_test_finish(const char *label) {}
#endif /* !CONFIG_PM_TEST_SUSPEND */
#ifdef CONFIG_PM_SLEEP
/* kernel/power/main.c */
extern int pm_notifier_call_chain_robust(unsigned long val_up, unsigned long val_down);
extern int pm_notifier_call_chain(unsigned long val);
void pm_restrict_gfp_mask(void);
void pm_restore_gfp_mask(void);
#else
static inline void pm_restrict_gfp_mask(void) {}
static inline void pm_restore_gfp_mask(void) {}
#endif
#ifdef CONFIG_HIGHMEM
int restore_highmem(void);
#else
static inline unsigned int count_highmem_pages(void) { return 0; }
static inline int restore_highmem(void) { return 0; }
#endif
/*
* Suspend test levels
*/
enum {
/* keep first */
TEST_NONE,
TEST_CORE,
TEST_CPUS,
TEST_PLATFORM,
TEST_DEVICES,
TEST_FREEZER,
/* keep last */
__TEST_AFTER_LAST
};
#define TEST_FIRST TEST_NONE
#define TEST_MAX (__TEST_AFTER_LAST - 1)
#ifdef CONFIG_PM_SLEEP_DEBUG
extern int pm_test_level;
#else
#define pm_test_level (TEST_NONE)
#endif
#ifdef CONFIG_SUSPEND_FREEZER
static inline int suspend_freeze_processes(void)
{
int error;
error = freeze_processes();
/*
* freeze_processes() automatically thaws every task if freezing
* fails. So we need not do anything extra upon error.
*/
if (error)
return error;
error = freeze_kernel_threads();
/*
* freeze_kernel_threads() thaws only kernel threads upon freezing
* failure. So we have to thaw the userspace tasks ourselves.
*/
if (error)
thaw_processes();
return error;
}
static inline void suspend_thaw_processes(void)
{
thaw_processes();
}
#else
static inline int suspend_freeze_processes(void)
{
return 0;
}
static inline void suspend_thaw_processes(void)
{
}
#endif
#ifdef CONFIG_PM_AUTOSLEEP
/* kernel/power/autosleep.c */
extern int pm_autosleep_init(void);
extern int pm_autosleep_lock(void);
extern void pm_autosleep_unlock(void);
extern suspend_state_t pm_autosleep_state(void);
extern int pm_autosleep_set_state(suspend_state_t state);
#else /* !CONFIG_PM_AUTOSLEEP */
static inline int pm_autosleep_init(void) { return 0; }
static inline int pm_autosleep_lock(void) { return 0; }
static inline void pm_autosleep_unlock(void) {}
static inline suspend_state_t pm_autosleep_state(void) { return PM_SUSPEND_ON; }
#endif /* !CONFIG_PM_AUTOSLEEP */
#ifdef CONFIG_PM_WAKELOCKS
/* kernel/power/wakelock.c */
extern ssize_t pm_show_wakelocks(char *buf, bool show_active);
extern int pm_wake_lock(const char *buf);
extern int pm_wake_unlock(const char *buf);
#endif /* !CONFIG_PM_WAKELOCKS */
static inline int pm_sleep_disable_secondary_cpus(void)
{
cpuidle_pause();
return suspend_disable_secondary_cpus();
}
static inline void pm_sleep_enable_secondary_cpus(void)
{
suspend_enable_secondary_cpus();
cpuidle_resume();
}
void dpm_save_errno(int err);