Files
linux-stable-mirror/kernel/power/swap.c
T
Linus Torvalds a552c81ff4 Merge tag 'mm-stable-2026-06-18-09-26' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
Pull MM updates from Andrew Morton:

 - "selftests/mm: clean up build output and verbosity" (Li Wang)

   Remove some noise from the MM selftests build

 - "mm: Free contiguous order-0 pages efficiently" (Ryan Roberts)

   Speed up the freeing of a batch of 0-order pages by first scanning
   them for coalescing opportunities. This is applicable to vfree() and
   to the releasing of frozen pages

 - "mm/damon: introduce DAMOS failed region quota charge ratio"
   (SeongJae Park)

   Address a DAMOS usability issue: The DAMOS quota often exhausts
   prematurely because it charges for all memory attempted, causing slow
   and inconsistent performance when actions fail on unreclaimable
   memory.

   To fix this, a new feature lets users set a smaller, flexible quota
   charge ratio (via a numerator and denominator) for failed regions.
   Since failed actions cause less overhead, reducing their quota cost
   ensures more predictable and efficient DAMOS processing

 - "selftests/cgroup: improve zswap tests robustness and support large
   page sizes" (Li Wang)

   Fix various spurious failures and improves the overall robustness of
   the cgroup zswap selftests

 - "fix MAP_DROPPABLE not supported errno" (Anthony Yznaga)

   Fix an issue in the mlock selftests on arm32

 - "mm: huge_memory: clean up defrag sysfs with shared" (Breno Leitao)

   Some maintenance work in the huge_memory code

 - "treewide: fixup gfp_t printks" (Brendan Jackman)

   Use the special vprintf() gfp_t conversion in various places

 - "mm: Fix vmemmap optimization accounting and initialization" (Muchun
   Song)

   Fix several bugs in the vmemmap optimization, mainly around incorrect
   page accounting and memmap initialization in the DAX and memory
   hotplug paths. It also fixes pageblock migratetype initialization and
   struct page initialization for ZONE_DEVICE compound pages

 - "mm/damon: repost non-hotfix reviewed patches in damon/next tree"

   A sprinkle of unrelated minor bugfixes for DAMON

 - "mm: remove page_mapped()" (David Hildenbrand)

   Remove this function from the tree, replacing it with folio_mapped()

 - "mm/damon: let DAMON be paused and resumed" (SeongJae Park)

   Allow DAMON to be paused and resumed without losing its current state

 - "kasan: hw_tags: Disable tagging for stack and page-tables" (Muhammad
   Usama Anjum)

   Simplify and speed up kasan by removing its ineffective tagging of
   stacks and page tables

 - "mm/damon/reclaim,lru_sort: monitor all system rams by default"
   (SeongJae Park)

   Simplify deployment on diverse hardware like NUMA systems by updating
   DAMON_RECLAIM and DAMON_LRU_SORT to automatically monitor the
   physical address range covering all System RAM areas by default,
   replacing the overly restrictive behavior that only targeted the
   single largest memory block to save on negligible overhead

 - "mm/damon/sysfs: document filters/ directory as deprecated" (SeongJae
   Park)

   Update some DAMON docs

 - "mm: use spinlock guards for zone lock" (Dmitry Ilvokhin)

   Switch zone->lock handling over to using the guard() mechanisms

 - "mm/filemap: tighten mmap_miss hit accounting" (fujunjie)

   Fix a flaw where the mmap_miss counter over-credited page cache hits
   during fault-arounds and page-fault retries. This results in
   significant reduction of redundant synchronous mmap readahead I/O,
   drastically cutting down execution time and gigabytes read for sparse
   random or strided memory access workloads

 - "selftests/cgroup: Fix false positive failures in test_percpu_basic"
   (Li Wang)

   Fix a couple of false-positives in the cgroup kmem selftests

 - "mm/damon/reclaim: support monitoring intervals auto-tuning"
   (SeongJae Park)

   Add a new parameter to DAMON permitting DAMON_RECLAIM to
   automatically tune DAMON's sampling and aggregation intervals

 - "mm/damon/stat: add kdamond_pid parameter" (SeongJae Park)

   Change DAMON_STAT to provide the pid of its kdamond

 - "mm/kmemleak: dedupe verbose scan output" (Breno Leitao)

   Remove large amounts of duplicated backtraces from the verbose-mode
   kmemleak output

 - "mm: remove CONFIG_HAVE_BOOTMEM_INFO_NODE (Part 1)" (David
   Hildenbrand)

   Reduce our use of CONFIG_HAVE_BOOTMEM_INFO_NODE, with a view to
   removing it entirely in a later series

 - "mm/damon: validate min_region_size to be power of 2" (Liew Rui Yan)

   Prevent users from passing a non-power-of-2 value of `addr_unit', as
   this later results in undesirable behavior

 - "mm: document read_pages and simplify usage" (Frederick Mayle)

 - "tools/mm/page-types: Fix misc bugs" (Ye Liu)

   Fix three issues in tools/mm/page-types.c

 - "mm: misc cleanups from __GFP_UNMAPPED series" (Brendan Jackman)

   Implement several cleanups in the page allocator and related code

 - "mm, swap: swap table phase IV: unify allocation" (Kairui Song)

   Unify the allocation and charging of anon and shmem swap in folios,
   provides better synchronization, consolidates the metadata
   management, hence dropping the static array and map, and improves
   performance

 - "mm/damon: introduce data attributes monitoring" (SeongJae Park(

   Extend DAMON to monitor general data attributes other than accesses

 - "mm/vmalloc: free unused pages on vrealloc() shrink" (Shivam Kalra)

   Implement the TODO in vrealloc() to unmap and free unused pages when
   shrinking across a page boundary

 - "mm/damon: documentation and comment fixes" (niecheng)

 - "remove mmap_action success, error hooks" (Lorenzo Stoakes)

   Eliminate custom hooks from mmap_action by removing the problematic
   success_hook which allowed drivers to improperly access uninitialized
   VMAs. It replaces the error_hook with a simple error-code field and
   updates the memory char driver accordingly

 - "mm/damon: minor improvements for code readability and tests"
   (SeongJae Park)

 - "mm/damon: fix macro arguments and clarify quota goals doc" (Maksym
   Shcherba)

 - "userfaultfd: merge fs/userfaultfd.c into mm/userfaultfd.c" (Mike
   Rapoport)

 - "mm/mglru: improve reclaim loop and dirty folio" (Kairui Song and
   others)

   Clean up and slightly improves MGLRU's reclaim loop and dirty
   writeback handling. Large performance improvements are measured

 - "use vma locks for proc/pid/{smaps|numa_maps} reads" (Suren
   Baghdasaryan)

   Use per-vma locks when reading /proc/pid/smaps and numa_maps similar
   to reduce contention on central mmap_lock

 - "refactors thpsize_shmem_enabled_store() and thpsize_shmem_enabled_show()"
   (Ran Xiaokai)

   Some cleanup work in the THP code

 - "selftests/memfd: fix compilation warnings" (Konstantin Khorenko)

   Fix a few build glitches in the memfd selftest code.

 - "memcg: shrink obj_stock_pcp and cache multiple objcgs" (Shakeel
   Butt)

   Resolve a 68% performance regression caused by NUMA-node cache
   thrashing around struct obj_stock_pcp by shrinking its existing
   fields and expanding it into a multi-slot array that caches up to
   five obj_cgroup pointers per CPU, allowing per-node variants of the
   same memcg to coexist within a single 64-byte cache line.

 - "zram: writeback fixes" (Sergey Senozhatsky)

   address a couple of unrelated zram writeback issues

 - "mm: switch THP shrinker to list_lru" (Johannes Weiner)

   Resolve NUMA-awareness issues and streamlines callsite interaction by
   refactoring and extending the list_lru API to completely replace the
   complex, open-coded deferred split queue for Transparent Huge Pages

 - "mm: improve large folio readahead for exec memory" (Usama Arif)

   Improve large-folio readahead on systems like 64K-page arm64 by
   preventing the mmap_miss check from permanently disabling
   target-oriented VM_EXEC readahead, and by generalizing the
   force_thp_readahead gate to support mappings with any usefully large
   maximum folio order under the cache cap.

 - "userfaultfd/pagemap: pre-existing fixes" (Kiryl Shutsemau)

   Fix a bunch of minor issues in the userfaultfd/pagemap, all of which
   were flagged by Sashiko review of proposed new material

 - "mm/sparse-vmemmap: Provide generic vmemmap_set_pmd() and
   vmemmap_check_pmd()" (Muchun Song)

   Provide generic versions of these two functions so the four
   arch-specific implementations can be removed.

 - "mm/swap, PM: hibernate: fix swapoff race in uswsusp by pinning swap
   device" (Youngjun Park)

   Address a uswsusp-vs-swapoff race and reduces the swap device
   reference taking/releasing frequency.

 - "mm/hmm: A fix and a selftest" (Dev Jain)

* tag 'mm-stable-2026-06-18-09-26' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (321 commits)
  selftests/mm/hmm-tests: test pagemap reads of PMD device-private entries
  fs/proc/task_mmu: do not warn on seeing non-migration pmd entry
  lib/test_hmm: check alloc_page_vma() return value and handle OOM
  mm/compaction: cap compact_gap() at COMPACT_CLUSTER_MAX
  mm/swap: remove redundant swap device reference in alloc/free
  mm/swap, PM: hibernate: fix swapoff race in uswsusp by pinning swap device
  mm/filemap: use folio_next_index() for start
  vmalloc: fix NULL pointer dereference in is_vm_area_hugepages()
  sparc/mm: drop vmemmap_check_pmd helper and use generic code
  loongarch/mm: drop vmemmap_check_pmd helper and use generic code
  riscv/mm: drop vmemmap_pmd helpers and use generic code
  arm64/mm: drop vmemmap_pmd helpers and use generic code
  mm/sparse-vmemmap: provide generic vmemmap_set_pmd() and vmemmap_check_pmd()
  rust: page: mark Page::nid as inline
  userfaultfd: build __VMA_UFFD_FLAGS from config-gated masks
  userfaultfd: gate must_wait writability check on pte_present()
  mm/huge_memory: preserve pmd_swp_uffd_wp on device-private PMD downgrade
  fs/proc/task_mmu: fix hugetlb self-deadlock in pagemap_scan_pte_hole()
  fs/proc/task_mmu: use huge_page_size() in pagemap_scan_hugetlb_entry()
  fs/proc/task_mmu: fix make_uffd_wp_huge_pte() prot-update race
  ...
2026-06-19 10:14:34 -07:00

1711 lines
40 KiB
C

// SPDX-License-Identifier: GPL-2.0-only
/*
* linux/kernel/power/swap.c
*
* This file provides functions for reading the suspend image from
* and writing it to a swap partition.
*
* Copyright (C) 1998,2001-2005 Pavel Machek <pavel@ucw.cz>
* Copyright (C) 2006 Rafael J. Wysocki <rjw@sisk.pl>
* Copyright (C) 2010-2012 Bojan Smojver <bojan@rexursive.com>
*/
#define pr_fmt(fmt) "PM: " fmt
#include <crypto/acompress.h>
#include <linux/module.h>
#include <linux/file.h>
#include <linux/delay.h>
#include <linux/bitops.h>
#include <linux/device.h>
#include <linux/bio.h>
#include <linux/blkdev.h>
#include <linux/swap.h>
#include <linux/swapops.h>
#include <linux/pm.h>
#include <linux/slab.h>
#include <linux/vmalloc.h>
#include <linux/cpumask.h>
#include <linux/atomic.h>
#include <linux/kthread.h>
#include <linux/crc32.h>
#include <linux/ktime.h>
#include "power.h"
#define HIBERNATE_SIG "S1SUSPEND"
u32 swsusp_hardware_signature;
/*
* When reading an {un,}compressed image, we may restore pages in place,
* in which case some architectures need these pages cleaning before they
* can be executed. We don't know which pages these may be, so clean the lot.
*/
static bool clean_pages_on_read;
static bool clean_pages_on_decompress;
/*
* The swap map is a data structure used for keeping track of each page
* written to a swap partition. It consists of many swap_map_page structures
* that contain each an array of MAP_PAGE_ENTRIES swap entries. These
* structures are stored on the swap and linked together with the help of the
* .next_swap member.
*
* The swap map is created during suspend. The swap map pages are allocated and
* populated one at a time, so we only need one memory page to set up the entire
* structure.
*
* During resume we pick up all swap_map_page structures into a list.
*/
#define MAP_PAGE_ENTRIES (PAGE_SIZE / sizeof(sector_t) - 1)
/*
* Number of free pages that are not high.
*/
static inline unsigned long low_free_pages(void)
{
return nr_free_pages() - nr_free_highpages();
}
/*
* Number of pages required to be kept free while writing the image. Always
* half of all available low pages before the writing starts.
*/
static inline unsigned long reqd_free_pages(void)
{
return low_free_pages() / 2;
}
struct swap_map_page {
sector_t entries[MAP_PAGE_ENTRIES];
sector_t next_swap;
};
struct swap_map_page_list {
struct swap_map_page *map;
struct swap_map_page_list *next;
};
/*
* The swap_map_handle structure is used for handling swap in a file-alike way.
*/
struct swap_map_handle {
struct swap_map_page *cur;
struct swap_map_page_list *maps;
sector_t cur_swap;
sector_t first_sector;
unsigned int k;
unsigned long reqd_free_pages;
u32 crc32;
};
struct swsusp_header {
char reserved[PAGE_SIZE - 20 - sizeof(sector_t) - sizeof(int) -
sizeof(u32) - sizeof(u32)];
u32 hw_sig;
u32 crc32;
sector_t image;
unsigned int flags; /* Flags to pass to the "boot" kernel */
char orig_sig[10];
char sig[10];
} __packed;
static struct swsusp_header *swsusp_header;
/*
* The following functions are used for tracing the allocated swap pages, so
* that they can be freed in case of an error.
*/
struct swsusp_extent {
struct rb_node node;
unsigned long start;
unsigned long end;
};
static struct rb_root swsusp_extents = RB_ROOT;
static int swsusp_extents_insert(unsigned long swap_offset)
{
struct rb_node **new = &(swsusp_extents.rb_node);
struct rb_node *parent = NULL;
struct swsusp_extent *ext;
/* Figure out where to put the new node */
while (*new) {
ext = rb_entry(*new, struct swsusp_extent, node);
parent = *new;
if (swap_offset < ext->start) {
/* Try to merge */
if (swap_offset == ext->start - 1) {
ext->start--;
return 0;
}
new = &((*new)->rb_left);
} else if (swap_offset > ext->end) {
/* Try to merge */
if (swap_offset == ext->end + 1) {
ext->end++;
return 0;
}
new = &((*new)->rb_right);
} else {
/* It already is in the tree */
return -EINVAL;
}
}
/* Add the new node and rebalance the tree. */
ext = kzalloc_obj(struct swsusp_extent);
if (!ext)
return -ENOMEM;
ext->start = swap_offset;
ext->end = swap_offset;
rb_link_node(&ext->node, parent, new);
rb_insert_color(&ext->node, &swsusp_extents);
return 0;
}
sector_t alloc_swapdev_block(int swap)
{
unsigned long offset;
/*
* Allocate a swap page and register that it has been allocated, so that
* it can be freed in case of an error.
*/
offset = swp_offset(swap_alloc_hibernation_slot(swap));
if (offset) {
if (swsusp_extents_insert(offset))
swap_free_hibernation_slot(swp_entry(swap, offset));
else
return swapdev_block(swap, offset);
}
return 0;
}
void free_all_swap_pages(int swap)
{
unsigned long offset;
struct rb_node *node;
/*
* Free swap pages allocated for saving image data. It also frees the
* extents used to register which swap entries had been allocated.
*/
while ((node = swsusp_extents.rb_node)) {
struct swsusp_extent *ext;
ext = rb_entry(node, struct swsusp_extent, node);
rb_erase(node, &swsusp_extents);
for (offset = ext->start; offset <= ext->end; offset++)
swap_free_hibernation_slot(swp_entry(swap, offset));
kfree(ext);
}
}
int swsusp_swap_in_use(void)
{
return (swsusp_extents.rb_node != NULL);
}
/*
* General things
*/
static unsigned short root_swap = 0xffff;
static struct file *hib_resume_bdev_file;
struct hib_bio_batch {
atomic_t count;
wait_queue_head_t wait;
blk_status_t error;
struct blk_plug plug;
};
static void hib_init_batch(struct hib_bio_batch *hb)
{
atomic_set(&hb->count, 0);
init_waitqueue_head(&hb->wait);
hb->error = BLK_STS_OK;
blk_start_plug(&hb->plug);
}
static void hib_finish_batch(struct hib_bio_batch *hb)
{
blk_finish_plug(&hb->plug);
}
static void hib_end_io(struct bio *bio)
{
struct hib_bio_batch *hb = bio->bi_private;
struct page *page = bio_first_page_all(bio);
if (bio->bi_status) {
pr_alert("Read-error on swap-device (%u:%u:%Lu)\n",
MAJOR(bio_dev(bio)), MINOR(bio_dev(bio)),
(unsigned long long)bio->bi_iter.bi_sector);
}
if (bio_data_dir(bio) == WRITE)
put_page(page);
else if (clean_pages_on_read)
flush_icache_range((unsigned long)page_address(page),
(unsigned long)page_address(page) + PAGE_SIZE);
if (bio->bi_status && !hb->error)
hb->error = bio->bi_status;
if (atomic_dec_and_test(&hb->count))
wake_up(&hb->wait);
bio_put(bio);
}
static int hib_submit_io_sync(blk_opf_t opf, pgoff_t page_off, void *addr)
{
return bdev_rw_virt(file_bdev(hib_resume_bdev_file),
page_off * (PAGE_SIZE >> 9), addr, PAGE_SIZE, opf);
}
static int hib_submit_io_async(blk_opf_t opf, pgoff_t page_off, void *addr,
struct hib_bio_batch *hb)
{
struct bio *bio;
bio = bio_alloc(file_bdev(hib_resume_bdev_file), 1, opf,
GFP_NOIO | __GFP_HIGH);
bio->bi_iter.bi_sector = page_off * (PAGE_SIZE >> 9);
bio_add_virt_nofail(bio, addr, PAGE_SIZE);
bio->bi_end_io = hib_end_io;
bio->bi_private = hb;
atomic_inc(&hb->count);
submit_bio(bio);
return 0;
}
static int hib_wait_io(struct hib_bio_batch *hb)
{
/*
* We are relying on the behavior of blk_plug that a thread with
* a plug will flush the plug list before sleeping.
*/
wait_event(hb->wait, atomic_read(&hb->count) == 0);
return blk_status_to_errno(hb->error);
}
/*
* Saving part
*/
static int mark_swapfiles(struct swap_map_handle *handle, unsigned int flags)
{
int error;
hib_submit_io_sync(REQ_OP_READ, swsusp_resume_block, swsusp_header);
if (!memcmp("SWAP-SPACE",swsusp_header->sig, 10) ||
!memcmp("SWAPSPACE2",swsusp_header->sig, 10)) {
memcpy(swsusp_header->orig_sig,swsusp_header->sig, 10);
memcpy(swsusp_header->sig, HIBERNATE_SIG, 10);
swsusp_header->image = handle->first_sector;
if (swsusp_hardware_signature) {
swsusp_header->hw_sig = swsusp_hardware_signature;
flags |= SF_HW_SIG;
}
swsusp_header->flags = flags;
if (flags & SF_CRC32_MODE)
swsusp_header->crc32 = handle->crc32;
error = hib_submit_io_sync(REQ_OP_WRITE | REQ_SYNC,
swsusp_resume_block, swsusp_header);
} else {
pr_err("Swap header not found!\n");
error = -ENODEV;
}
return error;
}
/*
* Hold the swsusp_header flag. This is used in software_resume() in
* 'kernel/power/hibernate' to check if the image is compressed and query
* for the compression algorithm support(if so).
*/
unsigned int swsusp_header_flags;
static int swsusp_swap_check(void)
{
int res;
/*
* Check if the resume device is a swap device and get its index (if so).
* This is called before saving the image.
*/
if (swsusp_resume_device)
res = find_hibernation_swap_type(swsusp_resume_device, swsusp_resume_block);
else
res = find_first_swap(&swsusp_resume_device);
if (res < 0)
return res;
root_swap = res;
hib_resume_bdev_file = bdev_file_open_by_dev(swsusp_resume_device,
BLK_OPEN_WRITE, NULL, NULL);
if (IS_ERR(hib_resume_bdev_file))
return PTR_ERR(hib_resume_bdev_file);
return 0;
}
static int write_page(void *buf, sector_t offset, struct hib_bio_batch *hb)
{
gfp_t gfp = GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY;
void *src;
int ret;
if (!offset)
return -ENOSPC;
if (!hb)
goto sync_io;
src = (void *)__get_free_page(gfp);
if (!src) {
ret = hib_wait_io(hb); /* Free pages */
if (ret)
return ret;
src = (void *)__get_free_page(gfp);
if (WARN_ON_ONCE(!src))
goto sync_io;
}
copy_page(src, buf);
return hib_submit_io_async(REQ_OP_WRITE | REQ_SYNC, offset, src, hb);
sync_io:
return hib_submit_io_sync(REQ_OP_WRITE | REQ_SYNC, offset, buf);
}
static void release_swap_writer(struct swap_map_handle *handle)
{
if (handle->cur)
free_page((unsigned long)handle->cur);
handle->cur = NULL;
}
static int get_swap_writer(struct swap_map_handle *handle)
{
int ret;
ret = swsusp_swap_check();
if (ret) {
if (ret != -ENOSPC)
pr_err("Cannot find swap device, try swapon -a\n");
return ret;
}
handle->cur = (struct swap_map_page *)get_zeroed_page(GFP_KERNEL);
if (!handle->cur) {
ret = -ENOMEM;
goto err_close;
}
handle->cur_swap = alloc_swapdev_block(root_swap);
if (!handle->cur_swap) {
ret = -ENOSPC;
goto err_rel;
}
handle->k = 0;
handle->reqd_free_pages = reqd_free_pages();
handle->first_sector = handle->cur_swap;
return 0;
err_rel:
release_swap_writer(handle);
err_close:
swsusp_close();
return ret;
}
static int swap_write_page(struct swap_map_handle *handle, void *buf,
struct hib_bio_batch *hb)
{
int error;
sector_t offset;
if (!handle->cur)
return -EINVAL;
offset = alloc_swapdev_block(root_swap);
error = write_page(buf, offset, hb);
if (error)
return error;
handle->cur->entries[handle->k++] = offset;
if (handle->k >= MAP_PAGE_ENTRIES) {
offset = alloc_swapdev_block(root_swap);
if (!offset)
return -ENOSPC;
handle->cur->next_swap = offset;
error = write_page(handle->cur, handle->cur_swap, hb);
if (error)
goto out;
clear_page(handle->cur);
handle->cur_swap = offset;
handle->k = 0;
if (hb && low_free_pages() <= handle->reqd_free_pages) {
error = hib_wait_io(hb);
if (error)
goto out;
/*
* Recalculate the number of required free pages, to
* make sure we never take more than half.
*/
handle->reqd_free_pages = reqd_free_pages();
}
}
out:
return error;
}
static int flush_swap_writer(struct swap_map_handle *handle)
{
if (handle->cur && handle->cur_swap)
return write_page(handle->cur, handle->cur_swap, NULL);
else
return -EINVAL;
}
static int swap_writer_finish(struct swap_map_handle *handle,
unsigned int flags, int error)
{
if (!error) {
pr_info("S");
error = mark_swapfiles(handle, flags);
pr_cont("|\n");
flush_swap_writer(handle);
}
if (error)
free_all_swap_pages(root_swap);
release_swap_writer(handle);
swsusp_close();
return error;
}
/*
* Bytes we need for compressed data in worst case. We assume(limitation)
* this is the worst of all the compression algorithms.
*/
#define bytes_worst_compress(x) ((x) + ((x) / 16) + 64 + 3 + 2)
/* We need to remember how much compressed data we need to read. */
#define CMP_HEADER sizeof(size_t)
/* Number of pages/bytes we'll compress at one time. */
#define UNC_PAGES 32
#define UNC_SIZE (UNC_PAGES * PAGE_SIZE)
/* Number of pages we need for compressed data (worst case). */
#define CMP_PAGES DIV_ROUND_UP(bytes_worst_compress(UNC_SIZE) + \
CMP_HEADER, PAGE_SIZE)
#define CMP_SIZE (CMP_PAGES * PAGE_SIZE)
/* Default number of threads for compression/decompression. */
#define CMP_THREADS 3
static unsigned int hibernate_compression_threads = CMP_THREADS;
/* Minimum/maximum number of pages for read buffering. */
#define CMP_MIN_RD_PAGES 1024
#define CMP_MAX_RD_PAGES 8192
static int save_image(struct swap_map_handle *handle,
struct snapshot_handle *snapshot,
unsigned int nr_to_write)
{
unsigned int m;
int ret;
int nr_pages;
int err2;
struct hib_bio_batch hb;
ktime_t start;
ktime_t stop;
hib_init_batch(&hb);
pr_info("Saving image data pages (%u pages)...\n",
nr_to_write);
m = nr_to_write / 10;
if (!m)
m = 1;
nr_pages = 0;
start = ktime_get();
while (1) {
ret = snapshot_read_next(snapshot);
if (ret <= 0)
break;
ret = swap_write_page(handle, data_of(*snapshot), &hb);
if (ret)
break;
if (!(nr_pages % m))
pr_info("Image saving progress: %3d%%\n",
nr_pages / m * 10);
nr_pages++;
}
err2 = hib_wait_io(&hb);
hib_finish_batch(&hb);
stop = ktime_get();
if (!ret)
ret = err2;
if (!ret)
pr_info("Image saving done\n");
swsusp_show_speed(start, stop, nr_to_write, "Wrote");
return ret;
}
/*
* Structure used for CRC32.
*/
struct crc_data {
struct task_struct *thr; /* thread */
atomic_t ready; /* ready to start flag */
atomic_t stop; /* ready to stop flag */
unsigned run_threads; /* nr current threads */
wait_queue_head_t go; /* start crc update */
wait_queue_head_t done; /* crc update done */
u32 *crc32; /* points to handle's crc32 */
size_t **unc_len; /* uncompressed lengths */
unsigned char *unc[]; /* uncompressed data */
};
static struct crc_data *alloc_crc_data(int nr_threads)
{
struct crc_data *crc;
crc = kzalloc_flex(*crc, unc, nr_threads);
if (!crc)
return NULL;
crc->unc_len = kzalloc_objs(*crc->unc_len, nr_threads);
if (!crc->unc_len)
goto err_free_crc;
return crc;
err_free_crc:
kfree(crc);
return NULL;
}
static void free_crc_data(struct crc_data *crc)
{
if (!crc)
return;
if (crc->thr)
kthread_stop(crc->thr);
kfree(crc->unc_len);
kfree(crc);
}
static int crc32_threadfn(void *data)
{
struct crc_data *d = data;
unsigned i;
while (1) {
wait_event(d->go, atomic_read_acquire(&d->ready) ||
kthread_should_stop());
if (kthread_should_stop()) {
d->thr = NULL;
atomic_set_release(&d->stop, 1);
wake_up(&d->done);
break;
}
atomic_set(&d->ready, 0);
for (i = 0; i < d->run_threads; i++)
*d->crc32 = crc32_le(*d->crc32,
d->unc[i], *d->unc_len[i]);
atomic_set_release(&d->stop, 1);
wake_up(&d->done);
}
return 0;
}
/*
* Structure used for data compression.
*/
struct cmp_data {
struct task_struct *thr; /* thread */
struct crypto_acomp *cc; /* crypto compressor */
struct acomp_req *cr; /* crypto request */
atomic_t ready; /* ready to start flag */
atomic_t stop; /* ready to stop flag */
int ret; /* return code */
wait_queue_head_t go; /* start compression */
wait_queue_head_t done; /* compression done */
size_t unc_len; /* uncompressed length */
size_t cmp_len; /* compressed length */
unsigned char unc[UNC_SIZE]; /* uncompressed buffer */
unsigned char cmp[CMP_SIZE]; /* compressed buffer */
};
/* Indicates the image size after compression */
static atomic64_t compressed_size = ATOMIC_INIT(0);
static int compress_threadfn(void *data)
{
struct cmp_data *d = data;
while (1) {
wait_event(d->go, atomic_read_acquire(&d->ready) ||
kthread_should_stop());
if (kthread_should_stop()) {
d->thr = NULL;
d->ret = -1;
atomic_set_release(&d->stop, 1);
wake_up(&d->done);
break;
}
atomic_set(&d->ready, 0);
acomp_request_set_callback(d->cr, CRYPTO_TFM_REQ_MAY_SLEEP,
NULL, NULL);
acomp_request_set_src_nondma(d->cr, d->unc, d->unc_len);
acomp_request_set_dst_nondma(d->cr, d->cmp + CMP_HEADER,
CMP_SIZE - CMP_HEADER);
d->ret = crypto_acomp_compress(d->cr);
d->cmp_len = d->cr->dlen;
atomic64_add(d->cmp_len, &compressed_size);
atomic_set_release(&d->stop, 1);
wake_up(&d->done);
}
return 0;
}
static int save_compressed_image(struct swap_map_handle *handle,
struct snapshot_handle *snapshot,
unsigned int nr_to_write)
{
unsigned int m;
int ret = 0;
int nr_pages;
int err2;
struct hib_bio_batch hb;
ktime_t start;
ktime_t stop;
size_t off;
unsigned int thr, run_threads, nr_threads;
unsigned char *page = NULL;
struct cmp_data *data = NULL;
struct crc_data *crc = NULL;
hib_init_batch(&hb);
atomic64_set(&compressed_size, 0);
/*
* We'll limit the number of threads for compression to limit memory
* footprint.
*/
nr_threads = num_online_cpus() - 1;
nr_threads = clamp_val(nr_threads, 1, hibernate_compression_threads);
page = (void *)__get_free_page(GFP_NOIO | __GFP_HIGH);
if (!page) {
pr_err("Failed to allocate %s page\n", hib_comp_algo);
ret = -ENOMEM;
goto out_clean;
}
data = vcalloc(nr_threads, sizeof(*data));
if (!data) {
pr_err("Failed to allocate %s data\n", hib_comp_algo);
ret = -ENOMEM;
goto out_clean;
}
crc = alloc_crc_data(nr_threads);
if (!crc) {
pr_err("Failed to allocate crc\n");
ret = -ENOMEM;
goto out_clean;
}
/*
* Start the compression threads.
*/
for (thr = 0; thr < nr_threads; thr++) {
init_waitqueue_head(&data[thr].go);
init_waitqueue_head(&data[thr].done);
data[thr].cc = crypto_alloc_acomp(hib_comp_algo, 0, CRYPTO_ALG_ASYNC);
if (IS_ERR_OR_NULL(data[thr].cc)) {
pr_err("Could not allocate comp stream %ld\n", PTR_ERR(data[thr].cc));
ret = -EFAULT;
goto out_clean;
}
data[thr].cr = acomp_request_alloc(data[thr].cc);
if (!data[thr].cr) {
pr_err("Could not allocate comp request\n");
ret = -ENOMEM;
goto out_clean;
}
data[thr].thr = kthread_run(compress_threadfn,
&data[thr],
"image_compress/%u", thr);
if (IS_ERR(data[thr].thr)) {
data[thr].thr = NULL;
pr_err("Cannot start compression threads\n");
ret = -ENOMEM;
goto out_clean;
}
}
/*
* Start the CRC32 thread.
*/
init_waitqueue_head(&crc->go);
init_waitqueue_head(&crc->done);
handle->crc32 = 0;
crc->crc32 = &handle->crc32;
for (thr = 0; thr < nr_threads; thr++) {
crc->unc[thr] = data[thr].unc;
crc->unc_len[thr] = &data[thr].unc_len;
}
crc->thr = kthread_run(crc32_threadfn, crc, "image_crc32");
if (IS_ERR(crc->thr)) {
crc->thr = NULL;
pr_err("Cannot start CRC32 thread\n");
ret = -ENOMEM;
goto out_clean;
}
/*
* Adjust the number of required free pages after all allocations have
* been done. We don't want to run out of pages when writing.
*/
handle->reqd_free_pages = reqd_free_pages();
pr_info("Using %u thread(s) for %s compression\n", nr_threads, hib_comp_algo);
pr_info("Compressing and saving image data (%u pages)...\n",
nr_to_write);
m = nr_to_write / 10;
if (!m)
m = 1;
nr_pages = 0;
start = ktime_get();
for (;;) {
for (thr = 0; thr < nr_threads; thr++) {
for (off = 0; off < UNC_SIZE; off += PAGE_SIZE) {
ret = snapshot_read_next(snapshot);
if (ret < 0)
goto out_finish;
if (!ret)
break;
memcpy(data[thr].unc + off,
data_of(*snapshot), PAGE_SIZE);
if (!(nr_pages % m))
pr_info("Image saving progress: %3d%%\n",
nr_pages / m * 10);
nr_pages++;
}
if (!off)
break;
data[thr].unc_len = off;
atomic_set_release(&data[thr].ready, 1);
wake_up(&data[thr].go);
}
if (!thr)
break;
crc->run_threads = thr;
atomic_set_release(&crc->ready, 1);
wake_up(&crc->go);
for (run_threads = thr, thr = 0; thr < run_threads; thr++) {
wait_event(data[thr].done,
atomic_read_acquire(&data[thr].stop));
atomic_set(&data[thr].stop, 0);
ret = data[thr].ret;
if (ret < 0) {
pr_err("%s compression failed\n", hib_comp_algo);
goto out_finish;
}
if (unlikely(!data[thr].cmp_len ||
data[thr].cmp_len >
bytes_worst_compress(data[thr].unc_len))) {
pr_err("Invalid %s compressed length\n", hib_comp_algo);
ret = -1;
goto out_finish;
}
*(size_t *)data[thr].cmp = data[thr].cmp_len;
/*
* Given we are writing one page at a time to disk, we
* copy that much from the buffer, although the last
* bit will likely be smaller than full page. This is
* OK - we saved the length of the compressed data, so
* any garbage at the end will be discarded when we
* read it.
*/
for (off = 0;
off < CMP_HEADER + data[thr].cmp_len;
off += PAGE_SIZE) {
memcpy(page, data[thr].cmp + off, PAGE_SIZE);
ret = swap_write_page(handle, page, &hb);
if (ret)
goto out_finish;
}
}
wait_event(crc->done, atomic_read_acquire(&crc->stop));
atomic_set(&crc->stop, 0);
}
out_finish:
err2 = hib_wait_io(&hb);
stop = ktime_get();
if (!ret)
ret = err2;
if (!ret) {
swsusp_show_speed(start, stop, nr_to_write, "Wrote");
pr_info("Image size after compression: %lld kbytes\n",
(atomic64_read(&compressed_size) / 1024));
pr_info("Image saving done\n");
} else {
pr_err("Image saving failed: %d\n", ret);
}
out_clean:
hib_finish_batch(&hb);
free_crc_data(crc);
if (data) {
for (thr = 0; thr < nr_threads; thr++) {
if (data[thr].thr)
kthread_stop(data[thr].thr);
acomp_request_free(data[thr].cr);
if (!IS_ERR_OR_NULL(data[thr].cc))
crypto_free_acomp(data[thr].cc);
}
vfree(data);
}
if (page)
free_page((unsigned long)page);
return ret;
}
static int enough_swap(unsigned int nr_pages)
{
unsigned int free_swap = count_swap_pages(root_swap, 1);
unsigned int required;
pr_debug("Free swap pages: %u\n", free_swap);
required = PAGES_FOR_IO + nr_pages;
return free_swap > required;
}
/**
* swsusp_write - Write entire image and metadata.
* @flags: flags to pass to the "boot" kernel in the image header
*
* It is important _NOT_ to umount filesystems at this point. We want them
* synced (in case something goes wrong) but we DO not want to mark filesystem
* clean: it is not. (And it does not matter, if we resume correctly, we'll mark
* system clean, anyway.)
*
* Return: 0 on success, negative error code on failure.
*/
int swsusp_write(unsigned int flags)
{
struct swap_map_handle handle;
struct snapshot_handle snapshot;
struct swsusp_info *header;
unsigned long pages;
int error;
pages = snapshot_get_image_size();
error = get_swap_writer(&handle);
if (error) {
pr_err("Cannot get swap writer\n");
return error;
}
if (flags & SF_NOCOMPRESS_MODE) {
if (!enough_swap(pages)) {
pr_err("Not enough free swap\n");
error = -ENOSPC;
goto out_finish;
}
}
memset(&snapshot, 0, sizeof(struct snapshot_handle));
error = snapshot_read_next(&snapshot);
if (error < (int)PAGE_SIZE) {
if (error >= 0)
error = -EFAULT;
goto out_finish;
}
header = (struct swsusp_info *)data_of(snapshot);
error = swap_write_page(&handle, header, NULL);
if (!error) {
error = (flags & SF_NOCOMPRESS_MODE) ?
save_image(&handle, &snapshot, pages - 1) :
save_compressed_image(&handle, &snapshot, pages - 1);
}
out_finish:
error = swap_writer_finish(&handle, flags, error);
return error;
}
/*
* The following functions allow us to read data using a swap map in a file-like
* way.
*/
static void release_swap_reader(struct swap_map_handle *handle)
{
struct swap_map_page_list *tmp;
while (handle->maps) {
if (handle->maps->map)
free_page((unsigned long)handle->maps->map);
tmp = handle->maps;
handle->maps = handle->maps->next;
kfree(tmp);
}
handle->cur = NULL;
}
static int get_swap_reader(struct swap_map_handle *handle,
unsigned int *flags_p)
{
int error;
struct swap_map_page_list *tmp, *last;
sector_t offset;
*flags_p = swsusp_header->flags;
if (!swsusp_header->image) /* how can this happen? */
return -EINVAL;
handle->cur = NULL;
last = handle->maps = NULL;
offset = swsusp_header->image;
while (offset) {
tmp = kzalloc_obj(*handle->maps);
if (!tmp) {
release_swap_reader(handle);
return -ENOMEM;
}
if (!handle->maps)
handle->maps = tmp;
if (last)
last->next = tmp;
last = tmp;
tmp->map = (struct swap_map_page *)
__get_free_page(GFP_NOIO | __GFP_HIGH);
if (!tmp->map) {
release_swap_reader(handle);
return -ENOMEM;
}
error = hib_submit_io_sync(REQ_OP_READ, offset, tmp->map);
if (error) {
release_swap_reader(handle);
return error;
}
offset = tmp->map->next_swap;
}
handle->k = 0;
handle->cur = handle->maps->map;
return 0;
}
static int swap_read_page(struct swap_map_handle *handle, void *buf,
struct hib_bio_batch *hb)
{
sector_t offset;
int error;
struct swap_map_page_list *tmp;
if (!handle->cur)
return -EINVAL;
offset = handle->cur->entries[handle->k];
if (!offset)
return -EFAULT;
if (hb)
error = hib_submit_io_async(REQ_OP_READ, offset, buf, hb);
else
error = hib_submit_io_sync(REQ_OP_READ, offset, buf);
if (error)
return error;
if (++handle->k >= MAP_PAGE_ENTRIES) {
handle->k = 0;
free_page((unsigned long)handle->maps->map);
tmp = handle->maps;
handle->maps = handle->maps->next;
kfree(tmp);
if (!handle->maps)
release_swap_reader(handle);
else
handle->cur = handle->maps->map;
}
return error;
}
static int swap_reader_finish(struct swap_map_handle *handle)
{
release_swap_reader(handle);
return 0;
}
static int load_image(struct swap_map_handle *handle,
struct snapshot_handle *snapshot,
unsigned int nr_to_read)
{
unsigned int m;
int ret = 0;
ktime_t start;
ktime_t stop;
struct hib_bio_batch hb;
int err2;
unsigned nr_pages;
hib_init_batch(&hb);
clean_pages_on_read = true;
pr_info("Loading image data pages (%u pages)...\n", nr_to_read);
m = nr_to_read / 10;
if (!m)
m = 1;
nr_pages = 0;
start = ktime_get();
for ( ; ; ) {
ret = snapshot_write_next(snapshot);
if (ret <= 0)
break;
ret = swap_read_page(handle, data_of(*snapshot), &hb);
if (ret)
break;
if (snapshot->sync_read)
ret = hib_wait_io(&hb);
if (ret)
break;
if (!(nr_pages % m))
pr_info("Image loading progress: %3d%%\n",
nr_pages / m * 10);
nr_pages++;
}
err2 = hib_wait_io(&hb);
hib_finish_batch(&hb);
stop = ktime_get();
if (!ret)
ret = err2;
if (!ret) {
pr_info("Image loading done\n");
ret = snapshot_write_finalize(snapshot);
if (!ret && !snapshot_image_loaded(snapshot))
ret = -ENODATA;
}
swsusp_show_speed(start, stop, nr_to_read, "Read");
return ret;
}
/*
* Structure used for data decompression.
*/
struct dec_data {
struct task_struct *thr; /* thread */
struct crypto_acomp *cc; /* crypto compressor */
struct acomp_req *cr; /* crypto request */
atomic_t ready; /* ready to start flag */
atomic_t stop; /* ready to stop flag */
int ret; /* return code */
wait_queue_head_t go; /* start decompression */
wait_queue_head_t done; /* decompression done */
size_t unc_len; /* uncompressed length */
size_t cmp_len; /* compressed length */
unsigned char unc[UNC_SIZE]; /* uncompressed buffer */
unsigned char cmp[CMP_SIZE]; /* compressed buffer */
};
static int decompress_threadfn(void *data)
{
struct dec_data *d = data;
while (1) {
wait_event(d->go, atomic_read_acquire(&d->ready) ||
kthread_should_stop());
if (kthread_should_stop()) {
d->thr = NULL;
d->ret = -1;
atomic_set_release(&d->stop, 1);
wake_up(&d->done);
break;
}
atomic_set(&d->ready, 0);
acomp_request_set_callback(d->cr, CRYPTO_TFM_REQ_MAY_SLEEP,
NULL, NULL);
acomp_request_set_src_nondma(d->cr, d->cmp + CMP_HEADER,
d->cmp_len);
acomp_request_set_dst_nondma(d->cr, d->unc, UNC_SIZE);
d->ret = crypto_acomp_decompress(d->cr);
d->unc_len = d->cr->dlen;
if (clean_pages_on_decompress)
flush_icache_range((unsigned long)d->unc,
(unsigned long)d->unc + d->unc_len);
atomic_set_release(&d->stop, 1);
wake_up(&d->done);
}
return 0;
}
static int load_compressed_image(struct swap_map_handle *handle,
struct snapshot_handle *snapshot,
unsigned int nr_to_read)
{
unsigned int m;
int ret = 0;
int eof = 0;
struct hib_bio_batch hb;
ktime_t start;
ktime_t stop;
unsigned nr_pages;
size_t off;
unsigned i, thr, run_threads, nr_threads;
unsigned ring = 0, pg = 0, ring_size = 0,
have = 0, want, need, asked = 0;
unsigned long read_pages = 0;
unsigned char **page = NULL;
struct dec_data *data = NULL;
struct crc_data *crc = NULL;
hib_init_batch(&hb);
/*
* We'll limit the number of threads for decompression to limit memory
* footprint.
*/
nr_threads = num_online_cpus() - 1;
nr_threads = clamp_val(nr_threads, 1, hibernate_compression_threads);
page = vmalloc_array(CMP_MAX_RD_PAGES, sizeof(*page));
if (!page) {
pr_err("Failed to allocate %s page\n", hib_comp_algo);
ret = -ENOMEM;
goto out_clean;
}
data = vcalloc(nr_threads, sizeof(*data));
if (!data) {
pr_err("Failed to allocate %s data\n", hib_comp_algo);
ret = -ENOMEM;
goto out_clean;
}
crc = alloc_crc_data(nr_threads);
if (!crc) {
pr_err("Failed to allocate crc\n");
ret = -ENOMEM;
goto out_clean;
}
clean_pages_on_decompress = true;
/*
* Start the decompression threads.
*/
for (thr = 0; thr < nr_threads; thr++) {
init_waitqueue_head(&data[thr].go);
init_waitqueue_head(&data[thr].done);
data[thr].cc = crypto_alloc_acomp(hib_comp_algo, 0, CRYPTO_ALG_ASYNC);
if (IS_ERR_OR_NULL(data[thr].cc)) {
pr_err("Could not allocate comp stream %ld\n", PTR_ERR(data[thr].cc));
ret = -EFAULT;
goto out_clean;
}
data[thr].cr = acomp_request_alloc(data[thr].cc);
if (!data[thr].cr) {
pr_err("Could not allocate comp request\n");
ret = -ENOMEM;
goto out_clean;
}
data[thr].thr = kthread_run(decompress_threadfn,
&data[thr],
"image_decompress/%u", thr);
if (IS_ERR(data[thr].thr)) {
data[thr].thr = NULL;
pr_err("Cannot start decompression threads\n");
ret = -ENOMEM;
goto out_clean;
}
}
/*
* Start the CRC32 thread.
*/
init_waitqueue_head(&crc->go);
init_waitqueue_head(&crc->done);
handle->crc32 = 0;
crc->crc32 = &handle->crc32;
for (thr = 0; thr < nr_threads; thr++) {
crc->unc[thr] = data[thr].unc;
crc->unc_len[thr] = &data[thr].unc_len;
}
crc->thr = kthread_run(crc32_threadfn, crc, "image_crc32");
if (IS_ERR(crc->thr)) {
crc->thr = NULL;
pr_err("Cannot start CRC32 thread\n");
ret = -ENOMEM;
goto out_clean;
}
/*
* Set the number of pages for read buffering.
* This is complete guesswork, because we'll only know the real
* picture once prepare_image() is called, which is much later on
* during the image load phase. We'll assume the worst case and
* say that none of the image pages are from high memory.
*/
if (low_free_pages() > snapshot_get_image_size())
read_pages = (low_free_pages() - snapshot_get_image_size()) / 2;
read_pages = clamp_val(read_pages, CMP_MIN_RD_PAGES, CMP_MAX_RD_PAGES);
for (i = 0; i < read_pages; i++) {
page[i] = (void *)__get_free_page(i < CMP_PAGES ?
GFP_NOIO | __GFP_HIGH :
GFP_NOIO | __GFP_NOWARN |
__GFP_NORETRY);
if (!page[i]) {
if (i < CMP_PAGES) {
ring_size = i;
pr_err("Failed to allocate %s pages\n", hib_comp_algo);
ret = -ENOMEM;
goto out_clean;
} else {
break;
}
}
}
want = ring_size = i;
pr_info("Using %u thread(s) for %s decompression\n", nr_threads, hib_comp_algo);
pr_info("Loading and decompressing image data (%u pages)...\n",
nr_to_read);
m = nr_to_read / 10;
if (!m)
m = 1;
nr_pages = 0;
start = ktime_get();
ret = snapshot_write_next(snapshot);
if (ret <= 0)
goto out_finish;
for(;;) {
for (i = 0; !eof && i < want; i++) {
ret = swap_read_page(handle, page[ring], &hb);
if (ret) {
/*
* On real read error, finish. On end of data,
* set EOF flag and just exit the read loop.
*/
if (handle->cur &&
handle->cur->entries[handle->k]) {
goto out_finish;
} else {
eof = 1;
break;
}
}
if (++ring >= ring_size)
ring = 0;
}
asked += i;
want -= i;
/*
* We are out of data, wait for some more.
*/
if (!have) {
if (!asked)
break;
ret = hib_wait_io(&hb);
if (ret)
goto out_finish;
have += asked;
asked = 0;
if (eof)
eof = 2;
}
if (crc->run_threads) {
wait_event(crc->done, atomic_read_acquire(&crc->stop));
atomic_set(&crc->stop, 0);
crc->run_threads = 0;
}
for (thr = 0; have && thr < nr_threads; thr++) {
data[thr].cmp_len = *(size_t *)page[pg];
if (unlikely(!data[thr].cmp_len ||
data[thr].cmp_len >
bytes_worst_compress(UNC_SIZE))) {
pr_err("Invalid %s compressed length\n", hib_comp_algo);
ret = -1;
goto out_finish;
}
need = DIV_ROUND_UP(data[thr].cmp_len + CMP_HEADER,
PAGE_SIZE);
if (need > have) {
if (eof > 1) {
ret = -1;
goto out_finish;
}
break;
}
for (off = 0;
off < CMP_HEADER + data[thr].cmp_len;
off += PAGE_SIZE) {
memcpy(data[thr].cmp + off,
page[pg], PAGE_SIZE);
have--;
want++;
if (++pg >= ring_size)
pg = 0;
}
atomic_set_release(&data[thr].ready, 1);
wake_up(&data[thr].go);
}
/*
* Wait for more data while we are decompressing.
*/
if (have < CMP_PAGES && asked) {
ret = hib_wait_io(&hb);
if (ret)
goto out_finish;
have += asked;
asked = 0;
if (eof)
eof = 2;
}
for (run_threads = thr, thr = 0; thr < run_threads; thr++) {
wait_event(data[thr].done,
atomic_read_acquire(&data[thr].stop));
atomic_set(&data[thr].stop, 0);
ret = data[thr].ret;
if (ret < 0) {
pr_err("%s decompression failed\n", hib_comp_algo);
goto out_finish;
}
if (unlikely(!data[thr].unc_len ||
data[thr].unc_len > UNC_SIZE ||
data[thr].unc_len & (PAGE_SIZE - 1))) {
pr_err("Invalid %s uncompressed length\n", hib_comp_algo);
ret = -1;
goto out_finish;
}
for (off = 0;
off < data[thr].unc_len; off += PAGE_SIZE) {
memcpy(data_of(*snapshot),
data[thr].unc + off, PAGE_SIZE);
if (!(nr_pages % m))
pr_info("Image loading progress: %3d%%\n",
nr_pages / m * 10);
nr_pages++;
ret = snapshot_write_next(snapshot);
if (ret <= 0) {
crc->run_threads = thr + 1;
atomic_set_release(&crc->ready, 1);
wake_up(&crc->go);
goto out_finish;
}
}
}
crc->run_threads = thr;
atomic_set_release(&crc->ready, 1);
wake_up(&crc->go);
}
out_finish:
if (crc->run_threads) {
wait_event(crc->done, atomic_read_acquire(&crc->stop));
atomic_set(&crc->stop, 0);
}
stop = ktime_get();
if (!ret) {
pr_info("Image loading done\n");
ret = snapshot_write_finalize(snapshot);
if (!ret && !snapshot_image_loaded(snapshot))
ret = -ENODATA;
if (!ret) {
if (swsusp_header->flags & SF_CRC32_MODE) {
if(handle->crc32 != swsusp_header->crc32) {
pr_err("Invalid image CRC32!\n");
ret = -ENODATA;
}
}
}
}
swsusp_show_speed(start, stop, nr_to_read, "Read");
out_clean:
hib_finish_batch(&hb);
for (i = 0; i < ring_size; i++)
free_page((unsigned long)page[i]);
free_crc_data(crc);
if (data) {
for (thr = 0; thr < nr_threads; thr++) {
if (data[thr].thr)
kthread_stop(data[thr].thr);
acomp_request_free(data[thr].cr);
if (!IS_ERR_OR_NULL(data[thr].cc))
crypto_free_acomp(data[thr].cc);
}
vfree(data);
}
vfree(page);
return ret;
}
/**
* swsusp_read - read the hibernation image.
* @flags_p: flags passed by the "frozen" kernel in the image header should
* be written into this memory location
*
* Return: 0 on success, negative error code on failure.
*/
int swsusp_read(unsigned int *flags_p)
{
int error;
struct swap_map_handle handle;
struct snapshot_handle snapshot;
struct swsusp_info *header;
memset(&snapshot, 0, sizeof(struct snapshot_handle));
error = snapshot_write_next(&snapshot);
if (error < (int)PAGE_SIZE)
return error < 0 ? error : -EFAULT;
header = (struct swsusp_info *)data_of(snapshot);
error = get_swap_reader(&handle, flags_p);
if (error)
goto end;
if (!error)
error = swap_read_page(&handle, header, NULL);
if (!error) {
error = (*flags_p & SF_NOCOMPRESS_MODE) ?
load_image(&handle, &snapshot, header->pages - 1) :
load_compressed_image(&handle, &snapshot, header->pages - 1);
}
swap_reader_finish(&handle);
end:
if (!error)
pr_debug("Image successfully loaded\n");
else
pr_debug("Error %d resuming\n", error);
return error;
}
static void *swsusp_holder;
/**
* swsusp_check - Open the resume device and check for the swsusp signature.
* @exclusive: Open the resume device exclusively.
*
* Return: 0 if a valid image is found, negative error code otherwise.
*/
int swsusp_check(bool exclusive)
{
void *holder = exclusive ? &swsusp_holder : NULL;
int error;
hib_resume_bdev_file = bdev_file_open_by_dev(swsusp_resume_device,
BLK_OPEN_READ, holder, NULL);
if (!IS_ERR(hib_resume_bdev_file)) {
clear_page(swsusp_header);
error = hib_submit_io_sync(REQ_OP_READ, swsusp_resume_block,
swsusp_header);
if (error)
goto put;
if (!memcmp(HIBERNATE_SIG, swsusp_header->sig, 10)) {
memcpy(swsusp_header->sig, swsusp_header->orig_sig, 10);
swsusp_header_flags = swsusp_header->flags;
/* Reset swap signature now */
error = hib_submit_io_sync(REQ_OP_WRITE | REQ_SYNC,
swsusp_resume_block,
swsusp_header);
} else {
error = -EINVAL;
}
if (!error && swsusp_header->flags & SF_HW_SIG &&
swsusp_header->hw_sig != swsusp_hardware_signature) {
pr_info("Suspend image hardware signature mismatch (%08x now %08x); aborting resume.\n",
swsusp_header->hw_sig, swsusp_hardware_signature);
error = -EINVAL;
}
put:
if (error)
bdev_fput(hib_resume_bdev_file);
else
pr_debug("Image signature found, resuming\n");
} else {
error = PTR_ERR(hib_resume_bdev_file);
}
if (error)
pr_debug("Image not found (code %d)\n", error);
return error;
}
/**
* swsusp_close - close resume device.
*/
void swsusp_close(void)
{
if (IS_ERR(hib_resume_bdev_file)) {
pr_debug("Image device not initialised\n");
return;
}
fput(hib_resume_bdev_file);
}
/**
* swsusp_unmark - Unmark swsusp signature in the resume device
*
* Return: 0 on success, negative error code on failure.
*/
#ifdef CONFIG_SUSPEND
int swsusp_unmark(void)
{
int error;
hib_submit_io_sync(REQ_OP_READ, swsusp_resume_block, swsusp_header);
if (!memcmp(HIBERNATE_SIG,swsusp_header->sig, 10)) {
memcpy(swsusp_header->sig,swsusp_header->orig_sig, 10);
error = hib_submit_io_sync(REQ_OP_WRITE | REQ_SYNC,
swsusp_resume_block,
swsusp_header);
} else {
pr_err("Cannot find swsusp signature!\n");
error = -ENODEV;
}
/*
* We just returned from suspend, we don't need the image any more.
*/
free_all_swap_pages(root_swap);
return error;
}
#endif
static ssize_t hibernate_compression_threads_show(struct kobject *kobj,
struct kobj_attribute *attr, char *buf)
{
return sysfs_emit(buf, "%d\n", hibernate_compression_threads);
}
static ssize_t hibernate_compression_threads_store(struct kobject *kobj,
struct kobj_attribute *attr,
const char *buf, size_t n)
{
unsigned long val;
if (kstrtoul(buf, 0, &val))
return -EINVAL;
if (val < 1)
return -EINVAL;
hibernate_compression_threads = val;
return n;
}
power_attr(hibernate_compression_threads);
static struct attribute *g[] = {
&hibernate_compression_threads_attr.attr,
NULL,
};
static const struct attribute_group attr_group = {
.attrs = g,
};
static int __init swsusp_header_init(void)
{
int error;
error = sysfs_create_group(power_kobj, &attr_group);
if (error)
return -ENOMEM;
swsusp_header = (struct swsusp_header*) __get_free_page(GFP_KERNEL);
if (!swsusp_header)
panic("Could not allocate memory for swsusp_header\n");
return 0;
}
core_initcall(swsusp_header_init);
static int __init hibernate_compression_threads_setup(char *str)
{
int rc = kstrtouint(str, 0, &hibernate_compression_threads);
if (rc)
return rc;
if (hibernate_compression_threads < 1)
hibernate_compression_threads = CMP_THREADS;
return 1;
}
__setup("hibernate_compression_threads=", hibernate_compression_threads_setup);