// 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 <linux/module.h>#include <linux/file.h>#include <linux/delay.h>#include <linux/bitops.h>#include <linux/genhd.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/lzo.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" /* * 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)]; 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(sizeof(struct swsusp_extent), GFP_KERNEL); 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;} /** * alloc_swapdev_block - allocate a swap page and register that it has * been allocated, so that it can be freed in case of an error. */ sector_t alloc_swapdev_block(int swap){ unsigned long offset; offset = swp_offset(get_swap_page_of_type(swap)); if (offset) { if (swsusp_extents_insert(offset)) swap_free(swp_entry(swap, offset)); else return swapdev_block(swap, offset); } return 0;} /** * free_all_swap_pages - free swap pages allocated for saving image data. * It also frees the extents used to register which swap entries had been * allocated. */ void free_all_swap_pages(int swap){ struct rb_node *node; while ((node = swsusp_extents.rb_node)) { struct swsusp_extent *ext; unsigned long offset; ext = rb_entry(node, struct swsusp_extent, node); rb_erase(node, &swsusp_extents); for (offset = ext->start; offset <= ext->end; offset++) swap_free(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 block_device *hib_resume_bdev; 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(int op, int op_flags, pgoff_t page_off, void *addr, struct hib_bio_batch *hb){ struct page *page = virt_to_page(addr); struct bio *bio; int error = 0; bio = bio_alloc(GFP_NOIO | __GFP_HIGH, 1); bio->bi_iter.bi_sector = page_off * (PAGE_SIZE >> 9); bio_set_dev(bio, hib_resume_bdev); bio_set_op_attrs(bio, op, op_flags); if (bio_add_page(bio, page, PAGE_SIZE, 0) < PAGE_SIZE) { pr_err("Adding page to bio failed at %llu\n", (unsigned long long)bio->bi_iter.bi_sector); bio_put(bio); return -EFAULT; } if (hb) { bio->bi_end_io = hib_end_io; bio->bi_private = hb; atomic_inc(&hb->count); submit_bio(bio); } else { error = submit_bio_wait(bio); bio_put(bio); } return error;} static blk_status_t 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(REQ_OP_READ, 0, swsusp_resume_block, swsusp_header, NULL); 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; swsusp_header->flags = flags; if (flags & SF_CRC32_MODE) swsusp_header->crc32 = handle->crc32; error = hib_submit_io(REQ_OP_WRITE, REQ_SYNC, swsusp_resume_block, swsusp_header, NULL); } else { pr_err("Swap header not found!\n"); error = -ENODEV; } return error;} /** * swsusp_swap_check - check if the resume device is a swap device * and get its index (if so) * * This is called before saving image */static int swsusp_swap_check(void){ int res; if (swsusp_resume_device) res = swap_type_of(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 = blkdev_get_by_dev(swsusp_resume_device, FMODE_WRITE, NULL); if (IS_ERR(hib_resume_bdev)) return PTR_ERR(hib_resume_bdev); res = set_blocksize(hib_resume_bdev, PAGE_SIZE); if (res < 0) blkdev_put(hib_resume_bdev, FMODE_WRITE); return res;} /** * write_page - Write one page to given swap location. * @buf: Address we're writing. * @offset: Offset of the swap page we're writing to. * @hb: bio completion batch */ static int write_page(void *buf, sector_t offset, struct hib_bio_batch *hb){ void *src; int ret; if (!offset) return -ENOSPC; if (hb) { src = (void *)__get_free_page(GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY); if (src) { copy_page(src, buf); } else { ret = hib_wait_io(hb); /* Free pages */ if (ret) return ret; src = (void *)__get_free_page(GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY); if (src) { copy_page(src, buf); } else { WARN_ON_ONCE(1); hb = NULL; /* Go synchronous */ src = buf; } } } else { src = buf; } return hib_submit_io(REQ_OP_WRITE, REQ_SYNC, offset, src, hb);} 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(FMODE_WRITE); return ret;} static int swap_write_page(struct swap_map_handle *handle, void *buf, struct hib_bio_batch *hb){ int error = 0; 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");Lines 1–500 of 1613. Load more
// 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 <linux/module.h> #include <linux/file.h> #include <linux/delay.h> #include <linux/bitops.h> #include <linux/genhd.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/lzo.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" /* * 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)]; 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(sizeof(struct swsusp_extent), GFP_KERNEL); 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; } /** * alloc_swapdev_block - allocate a swap page and register that it has * been allocated, so that it can be freed in case of an error. */ sector_t alloc_swapdev_block(int swap) { unsigned long offset; offset = swp_offset(get_swap_page_of_type(swap)); if (offset) { if (swsusp_extents_insert(offset)) swap_free(swp_entry(swap, offset)); else return swapdev_block(swap, offset); } return 0; } /** * free_all_swap_pages - free swap pages allocated for saving image data. * It also frees the extents used to register which swap entries had been * allocated. */ void free_all_swap_pages(int swap) { struct rb_node *node; while ((node = swsusp_extents.rb_node)) { struct swsusp_extent *ext; unsigned long offset; ext = rb_entry(node, struct swsusp_extent, node); rb_erase(node, &swsusp_extents); for (offset = ext->start; offset <= ext->end; offset++) swap_free(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 block_device *hib_resume_bdev; 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(int op, int op_flags, pgoff_t page_off, void *addr, struct hib_bio_batch *hb) { struct page *page = virt_to_page(addr); struct bio *bio; int error = 0; bio = bio_alloc(GFP_NOIO | __GFP_HIGH, 1); bio->bi_iter.bi_sector = page_off * (PAGE_SIZE >> 9); bio_set_dev(bio, hib_resume_bdev); bio_set_op_attrs(bio, op, op_flags); if (bio_add_page(bio, page, PAGE_SIZE, 0) < PAGE_SIZE) { pr_err("Adding page to bio failed at %llu\n", (unsigned long long)bio->bi_iter.bi_sector); bio_put(bio); return -EFAULT; } if (hb) { bio->bi_end_io = hib_end_io; bio->bi_private = hb; atomic_inc(&hb->count); submit_bio(bio); } else { error = submit_bio_wait(bio); bio_put(bio); } return error; } static blk_status_t 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(REQ_OP_READ, 0, swsusp_resume_block, swsusp_header, NULL); 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; swsusp_header->flags = flags; if (flags & SF_CRC32_MODE) swsusp_header->crc32 = handle->crc32; error = hib_submit_io(REQ_OP_WRITE, REQ_SYNC, swsusp_resume_block, swsusp_header, NULL); } else { pr_err("Swap header not found!\n"); error = -ENODEV; } return error; } /** * swsusp_swap_check - check if the resume device is a swap device * and get its index (if so) * * This is called before saving image */ static int swsusp_swap_check(void) { int res; if (swsusp_resume_device) res = swap_type_of(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 = blkdev_get_by_dev(swsusp_resume_device, FMODE_WRITE, NULL); if (IS_ERR(hib_resume_bdev)) return PTR_ERR(hib_resume_bdev); res = set_blocksize(hib_resume_bdev, PAGE_SIZE); if (res < 0) blkdev_put(hib_resume_bdev, FMODE_WRITE); return res; } /** * write_page - Write one page to given swap location. * @buf: Address we're writing. * @offset: Offset of the swap page we're writing to. * @hb: bio completion batch */ static int write_page(void *buf, sector_t offset, struct hib_bio_batch *hb) { void *src; int ret; if (!offset) return -ENOSPC; if (hb) { src = (void *)__get_free_page(GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY); if (src) { copy_page(src, buf); } else { ret = hib_wait_io(hb); /* Free pages */ if (ret) return ret; src = (void *)__get_free_page(GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY); if (src) { copy_page(src, buf); } else { WARN_ON_ONCE(1); hb = NULL; /* Go synchronous */ src = buf; } } } else { src = buf; } return hib_submit_io(REQ_OP_WRITE, REQ_SYNC, offset, src, hb); } 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(FMODE_WRITE); return ret; } static int swap_write_page(struct swap_map_handle *handle, void *buf, struct hib_bio_batch *hb) { int error = 0; 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");