mirror of
https://github.com/torvalds/linux.git
synced 2024-11-15 08:31:55 +00:00
6e17c6de3d
- Yosry has also eliminated cgroup's atomic rstat flushing. - Nhat Pham adds the new cachestat() syscall. It provides userspace with the ability to query pagecache status - a similar concept to mincore() but more powerful and with improved usability. - Mel Gorman provides more optimizations for compaction, reducing the prevalence of page rescanning. - Lorenzo Stoakes has done some maintanance work on the get_user_pages() interface. - Liam Howlett continues with cleanups and maintenance work to the maple tree code. Peng Zhang also does some work on maple tree. - Johannes Weiner has done some cleanup work on the compaction code. - David Hildenbrand has contributed additional selftests for get_user_pages(). - Thomas Gleixner has contributed some maintenance and optimization work for the vmalloc code. - Baolin Wang has provided some compaction cleanups, - SeongJae Park continues maintenance work on the DAMON code. - Huang Ying has done some maintenance on the swap code's usage of device refcounting. - Christoph Hellwig has some cleanups for the filemap/directio code. - Ryan Roberts provides two patch series which yield some rationalization of the kernel's access to pte entries - use the provided APIs rather than open-coding accesses. - Lorenzo Stoakes has some fixes to the interaction between pagecache and directio access to file mappings. - John Hubbard has a series of fixes to the MM selftesting code. - ZhangPeng continues the folio conversion campaign. - Hugh Dickins has been working on the pagetable handling code, mainly with a view to reducing the load on the mmap_lock. - Catalin Marinas has reduced the arm64 kmalloc() minimum alignment from 128 to 8. - Domenico Cerasuolo has improved the zswap reclaim mechanism by reorganizing the LRU management. - Matthew Wilcox provides some fixups to make gfs2 work better with the buffer_head code. - Vishal Moola also has done some folio conversion work. - Matthew Wilcox has removed the remnants of the pagevec code - their functionality is migrated over to struct folio_batch. -----BEGIN PGP SIGNATURE----- iHUEABYIAB0WIQTTMBEPP41GrTpTJgfdBJ7gKXxAjgUCZJejewAKCRDdBJ7gKXxA joggAPwKMfT9lvDBEUnJagY7dbDPky1cSYZdJKxxM2cApGa42gEA6Cl8HRAWqSOh J0qXCzqaaN8+BuEyLGDVPaXur9KirwY= =B7yQ -----END PGP SIGNATURE----- Merge tag 'mm-stable-2023-06-24-19-15' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm Pull mm updates from Andrew Morton: - Yosry Ahmed brought back some cgroup v1 stats in OOM logs - Yosry has also eliminated cgroup's atomic rstat flushing - Nhat Pham adds the new cachestat() syscall. It provides userspace with the ability to query pagecache status - a similar concept to mincore() but more powerful and with improved usability - Mel Gorman provides more optimizations for compaction, reducing the prevalence of page rescanning - Lorenzo Stoakes has done some maintanance work on the get_user_pages() interface - Liam Howlett continues with cleanups and maintenance work to the maple tree code. Peng Zhang also does some work on maple tree - Johannes Weiner has done some cleanup work on the compaction code - David Hildenbrand has contributed additional selftests for get_user_pages() - Thomas Gleixner has contributed some maintenance and optimization work for the vmalloc code - Baolin Wang has provided some compaction cleanups, - SeongJae Park continues maintenance work on the DAMON code - Huang Ying has done some maintenance on the swap code's usage of device refcounting - Christoph Hellwig has some cleanups for the filemap/directio code - Ryan Roberts provides two patch series which yield some rationalization of the kernel's access to pte entries - use the provided APIs rather than open-coding accesses - Lorenzo Stoakes has some fixes to the interaction between pagecache and directio access to file mappings - John Hubbard has a series of fixes to the MM selftesting code - ZhangPeng continues the folio conversion campaign - Hugh Dickins has been working on the pagetable handling code, mainly with a view to reducing the load on the mmap_lock - Catalin Marinas has reduced the arm64 kmalloc() minimum alignment from 128 to 8 - Domenico Cerasuolo has improved the zswap reclaim mechanism by reorganizing the LRU management - Matthew Wilcox provides some fixups to make gfs2 work better with the buffer_head code - Vishal Moola also has done some folio conversion work - Matthew Wilcox has removed the remnants of the pagevec code - their functionality is migrated over to struct folio_batch * tag 'mm-stable-2023-06-24-19-15' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (380 commits) mm/hugetlb: remove hugetlb_set_page_subpool() mm: nommu: correct the range of mmap_sem_read_lock in task_mem() hugetlb: revert use of page_cache_next_miss() Revert "page cache: fix page_cache_next/prev_miss off by one" mm/vmscan: fix root proactive reclaim unthrottling unbalanced node mm: memcg: rename and document global_reclaim() mm: kill [add|del]_page_to_lru_list() mm: compaction: convert to use a folio in isolate_migratepages_block() mm: zswap: fix double invalidate with exclusive loads mm: remove unnecessary pagevec includes mm: remove references to pagevec mm: rename invalidate_mapping_pagevec to mapping_try_invalidate mm: remove struct pagevec net: convert sunrpc from pagevec to folio_batch i915: convert i915_gpu_error to use a folio_batch pagevec: rename fbatch_count() mm: remove check_move_unevictable_pages() drm: convert drm_gem_put_pages() to use a folio_batch i915: convert shmem_sg_free_table() to use a folio_batch scatterlist: add sg_set_folio() ...
328 lines
8.9 KiB
C
328 lines
8.9 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>
|
|
|
|
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);
|
|
|
|
#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 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 */
|
|
|
|
#else /* !CONFIG_HIBERNATION */
|
|
|
|
static inline void hibernate_reserved_size_init(void) {}
|
|
static inline void hibernate_image_size_init(void) {}
|
|
#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);
|
|
extern void 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_PLATFORM_MODE 1
|
|
#define SF_NOCOMPRESS_MODE 2
|
|
#define SF_CRC32_MODE 4
|
|
#define SF_HW_SIG 8
|
|
|
|
/* kernel/power/hibernate.c */
|
|
int swsusp_check(bool snapshot_test);
|
|
extern void swsusp_free(void);
|
|
extern int swsusp_read(unsigned int *flags_p);
|
|
extern int swsusp_write(unsigned int flags);
|
|
void swsusp_close(bool snapshot_test);
|
|
#ifdef CONFIG_SUSPEND
|
|
extern int swsusp_unmark(void);
|
|
#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();
|
|
}
|