/* * The calls to set_direct_map_*() should not fail because remapping a page * here means that we only update protection bits in an existing PTE. * It is still worth to have a warning here if something changes and this * will no longer be the case.
*/ staticinlinevoid hibernate_map_page(struct page *page)
{ if (IS_ENABLED(CONFIG_ARCH_HAS_SET_DIRECT_MAP)) { int ret = set_direct_map_default_noflush(page);
if (ret)
pr_warn_once("Failed to remap page\n");
} else {
debug_pagealloc_map_pages(page, 1);
}
}
staticinlinevoid hibernate_unmap_page(struct page *page)
{ if (IS_ENABLED(CONFIG_ARCH_HAS_SET_DIRECT_MAP)) { unsignedlong addr = (unsignedlong)page_address(page); int ret = set_direct_map_invalid_noflush(page);
/* * Number of bytes to reserve for memory allocations made by device drivers * from their ->freeze() and ->freeze_noirq() callbacks so that they don't * cause image creation to fail (tunable via /sys/power/reserved_size).
*/ unsignedlong reserved_size;
/* * Preferred image size in bytes (tunable via /sys/power/image_size). * When it is set to N, swsusp will do its best to ensure the image * size will not exceed N bytes, but if that is impossible, it will * try to create the smallest image possible.
*/ unsignedlong image_size;
/* * List of PBEs needed for restoring the pages that were allocated before * the suspend and included in the suspend image, but have also been * allocated by the "resume" kernel, so their contents cannot be written * directly to their "original" page frames.
*/ struct pbe *restore_pblist;
/* struct linked_page is used to build chains of pages */
/* * List of "safe" pages (ie. pages that were not used by the image kernel * before hibernation) that may be used as temporary storage for image kernel * memory contents.
*/ staticstruct linked_page *safe_pages_list;
/* Pointer to an auxiliary buffer (1 page) */ staticvoid *buffer;
/** * get_image_page - Allocate a page for a hibernation image. * @gfp_mask: GFP mask for the allocation. * @safe_needed: Get pages that were not used before hibernation (restore only) * * During image restoration, for storing the PBE list and the image data, we can * only use memory pages that do not conflict with the pages used before * hibernation. The "unsafe" pages have PageNosaveFree set and we count them * using allocated_unsafe_pages. * * Each allocated image page is marked as PageNosave and PageNosaveFree so that * swsusp_free() can release it.
*/ staticvoid *get_image_page(gfp_t gfp_mask, int safe_needed)
{ void *res;
res = (void *)get_zeroed_page(gfp_mask); if (safe_needed) while (res && swsusp_page_is_free(virt_to_page(res))) { /* The page is unsafe, mark it for swsusp_free() */
swsusp_set_page_forbidden(virt_to_page(res));
allocated_unsafe_pages++;
res = (void *)get_zeroed_page(gfp_mask);
} if (res) {
swsusp_set_page_forbidden(virt_to_page(res));
swsusp_set_page_free(virt_to_page(res));
} return res;
}
/** * free_image_page - Free a page allocated for hibernation image. * @addr: Address of the page to free. * @clear_nosave_free: If set, clear the PageNosaveFree bit for the page. * * The page to free should have been allocated by get_image_page() (page flags * set by it are affected).
*/ staticinlinevoid free_image_page(void *addr, int clear_nosave_free)
{ struct page *page;
BUG_ON(!virt_addr_valid(addr));
page = virt_to_page(addr);
swsusp_unset_page_forbidden(page); if (clear_nosave_free)
swsusp_unset_page_free(page);
__free_page(page);
}
staticinlinevoid free_list_of_pages(struct linked_page *list, int clear_page_nosave)
{ while (list) { struct linked_page *lp = list->next;
free_image_page(list, clear_page_nosave);
list = lp;
}
}
/* * struct chain_allocator is used for allocating small objects out of * a linked list of pages called 'the chain'. * * The chain grows each time when there is no room for a new object in * the current page. The allocated objects cannot be freed individually. * It is only possible to free them all at once, by freeing the entire * chain. * * NOTE: The chain allocator may be inefficient if the allocated objects * are not much smaller than PAGE_SIZE.
*/ struct chain_allocator { struct linked_page *chain; /* the chain */ unsignedint used_space; /* total size of objects allocated out
of the current page */
gfp_t gfp_mask; /* mask for allocating pages */ int safe_needed; /* if set, only "safe" pages are allocated */
};
/* * Data types related to memory bitmaps. * * Memory bitmap is a structure consisting of many linked lists of * objects. The main list's elements are of type struct zone_bitmap * and each of them corresponds to one zone. For each zone bitmap * object there is a list of objects of type struct bm_block that * represent each blocks of bitmap in which information is stored. * * struct memory_bitmap contains a pointer to the main list of zone * bitmap objects, a struct bm_position used for browsing the bitmap, * and a pointer to the list of pages used for allocating all of the * zone bitmap objects and bitmap block objects. * * NOTE: It has to be possible to lay out the bitmap in memory * using only allocations of order 0. Additionally, the bitmap is * designed to work with arbitrary number of zones (this is over the * top for now, but let's avoid making unnecessary assumptions ;-). * * struct zone_bitmap contains a pointer to a list of bitmap block * objects and a pointer to the bitmap block object that has been * most recently used for setting bits. Additionally, it contains the * PFNs that correspond to the start and end of the represented zone. * * struct bm_block contains a pointer to the memory page in which * information is stored (in the form of a block of bitmap) * It also contains the pfns that correspond to the start and end of * the represented memory area. * * The memory bitmap is organized as a radix tree to guarantee fast random * access to the bits. There is one radix tree for each zone (as returned * from create_mem_extents). * * One radix tree is represented by one struct mem_zone_bm_rtree. There are * two linked lists for the nodes of the tree, one for the inner nodes and * one for the leave nodes. The linked leave nodes are used for fast linear * access of the memory bitmap. * * The struct rtree_node represents one node of the radix tree.
*/
/* * struct rtree_node is a wrapper struct to link the nodes * of the rtree together for easy linear iteration over * bits and easy freeing
*/ struct rtree_node { struct list_head list; unsignedlong *data;
};
/* * struct mem_zone_bm_rtree represents a bitmap used for one * populated memory zone.
*/ struct mem_zone_bm_rtree { struct list_head list; /* Link Zones together */ struct list_head nodes; /* Radix Tree inner nodes */ struct list_head leaves; /* Radix Tree leaves */ unsignedlong start_pfn; /* Zone start page frame */ unsignedlong end_pfn; /* Zone end page frame + 1 */ struct rtree_node *rtree; /* Radix Tree Root */ int levels; /* Number of Radix Tree Levels */ unsignedint blocks; /* Number of Bitmap Blocks */
};
/* struct bm_position is used for browsing memory bitmaps */
struct memory_bitmap { struct list_head zones; struct linked_page *p_list; /* list of pages used to store zone bitmap objects and bitmap block
objects */ struct bm_position cur; /* most recently used bit position */
};
/** * alloc_rtree_node - Allocate a new node and add it to the radix tree. * @gfp_mask: GFP mask for the allocation. * @safe_needed: Get pages not used before hibernation (restore only) * @ca: Pointer to a linked list of pages ("a chain") to allocate from * @list: Radix Tree node to add. * * This function is used to allocate inner nodes as well as the * leave nodes of the radix tree. It also adds the node to the * corresponding linked list passed in by the *list parameter.
*/ staticstruct rtree_node *alloc_rtree_node(gfp_t gfp_mask, int safe_needed, struct chain_allocator *ca, struct list_head *list)
{ struct rtree_node *node;
node = chain_alloc(ca, sizeof(struct rtree_node)); if (!node) return NULL;
node->data = get_image_page(gfp_mask, safe_needed); if (!node->data) return NULL;
list_add_tail(&node->list, list);
return node;
}
/** * add_rtree_block - Add a new leave node to the radix tree. * * The leave nodes need to be allocated in order to keep the leaves * linked list in order. This is guaranteed by the zone->blocks * counter.
*/ staticint add_rtree_block(struct mem_zone_bm_rtree *zone, gfp_t gfp_mask, int safe_needed, struct chain_allocator *ca)
{ struct rtree_node *node, *block, **dst; unsignedint levels_needed, block_nr; int i;
block_nr = zone->blocks;
levels_needed = 0;
/* How many levels do we need for this block nr? */ while (block_nr) {
levels_needed += 1;
block_nr >>= BM_RTREE_LEVEL_SHIFT;
}
/* Make sure the rtree has enough levels */ for (i = zone->levels; i < levels_needed; i++) {
node = alloc_rtree_node(gfp_mask, safe_needed, ca,
&zone->nodes); if (!node) return -ENOMEM;
/* Allocate new block */
block = alloc_rtree_node(gfp_mask, safe_needed, ca, &zone->leaves); if (!block) return -ENOMEM;
/* Now walk the rtree to insert the block */
node = zone->rtree;
dst = &zone->rtree;
block_nr = zone->blocks; for (i = zone->levels; i > 0; i--) { int index;
if (!node) {
node = alloc_rtree_node(gfp_mask, safe_needed, ca,
&zone->nodes); if (!node) return -ENOMEM;
*dst = node;
}
staticvoid free_zone_bm_rtree(struct mem_zone_bm_rtree *zone, int clear_nosave_free);
/** * create_zone_bm_rtree - Create a radix tree for one zone. * * Allocated the mem_zone_bm_rtree structure and initializes it. * This function also allocated and builds the radix tree for the * zone.
*/ staticstruct mem_zone_bm_rtree *create_zone_bm_rtree(gfp_t gfp_mask, int safe_needed, struct chain_allocator *ca, unsignedlong start, unsignedlong end)
{ struct mem_zone_bm_rtree *zone; unsignedint i, nr_blocks; unsignedlong pages;
pages = end - start;
zone = chain_alloc(ca, sizeof(struct mem_zone_bm_rtree)); if (!zone) return NULL;
for (i = 0; i < nr_blocks; i++) { if (add_rtree_block(zone, gfp_mask, safe_needed, ca)) {
free_zone_bm_rtree(zone, PG_UNSAFE_CLEAR); return NULL;
}
}
return zone;
}
/** * free_zone_bm_rtree - Free the memory of the radix tree. * * Free all node pages of the radix tree. The mem_zone_bm_rtree * structure itself is not freed here nor are the rtree_node * structs.
*/ staticvoid free_zone_bm_rtree(struct mem_zone_bm_rtree *zone, int clear_nosave_free)
{ struct rtree_node *node;
/** * free_mem_extents - Free a list of memory extents. * @list: List of extents to free.
*/ staticvoid free_mem_extents(struct list_head *list)
{ struct mem_extent *ext, *aux;
/** * create_mem_extents - Create a list of memory extents. * @list: List to put the extents into. * @gfp_mask: Mask to use for memory allocations. * * The extents represent contiguous ranges of PFNs.
*/ staticint create_mem_extents(struct list_head *list, gfp_t gfp_mask)
{ struct zone *zone;
/* Merge this zone's range of PFNs with the existing one */ if (zone_start < ext->start)
ext->start = zone_start; if (zone_end > ext->end)
ext->end = zone_end;
/* More merging may be possible */
cur = ext;
list_for_each_entry_safe_continue(cur, aux, list, hook) { if (zone_end < cur->start) break; if (zone_end < cur->end)
ext->end = cur->end;
list_del(&cur->hook);
kfree(cur);
}
}
return 0;
}
/** * memory_bm_create - Allocate memory for a memory bitmap.
*/ staticint memory_bm_create(struct memory_bitmap *bm, gfp_t gfp_mask, int safe_needed)
{ struct chain_allocator ca; struct list_head mem_extents; struct mem_extent *ext; int error;
/** * memory_bm_find_bit - Find the bit for a given PFN in a memory bitmap. * * Find the bit in memory bitmap @bm that corresponds to the given PFN. * The cur.zone, cur.block and cur.node_pfn members of @bm are updated. * * Walk the radix tree to find the page containing the bit that represents @pfn * and return the position of the bit in @addr and @bit_nr.
*/ staticint memory_bm_find_bit(struct memory_bitmap *bm, unsignedlong pfn, void **addr, unsignedint *bit_nr)
{ struct mem_zone_bm_rtree *curr, *zone; struct rtree_node *node; int i, block_nr;
zone = bm->cur.zone;
if (pfn >= zone->start_pfn && pfn < zone->end_pfn) goto zone_found;
zone = NULL;
/* Find the right zone */
list_for_each_entry(curr, &bm->zones, list) { if (pfn >= curr->start_pfn && pfn < curr->end_pfn) {
zone = curr; break;
}
}
if (!zone) return -EFAULT;
zone_found: /* * We have found the zone. Now walk the radix tree to find the leaf node * for our PFN.
*/
/* * If the zone we wish to scan is the current zone and the * pfn falls into the current node then we do not need to walk * the tree.
*/
node = bm->cur.node; if (zone == bm->cur.zone &&
((pfn - zone->start_pfn) & ~BM_BLOCK_MASK) == bm->cur.node_pfn) goto node_found;
/* * rtree_next_node - Jump to the next leaf node. * * Set the position to the beginning of the next node in the * memory bitmap. This is either the next node in the current * zone's radix tree or the first node in the radix tree of the * next zone. * * Return true if there is a next node, false otherwise.
*/ staticbool rtree_next_node(struct memory_bitmap *bm)
{ if (!list_is_last(&bm->cur.node->list, &bm->cur.zone->leaves)) {
bm->cur.node = list_entry(bm->cur.node->list.next, struct rtree_node, list);
bm->cur.node_pfn += BM_BITS_PER_BLOCK;
bm->cur.node_bit = 0;
touch_softlockup_watchdog(); returntrue;
}
/* No more nodes, goto next zone */ if (!list_is_last(&bm->cur.zone->list, &bm->zones)) {
bm->cur.zone = list_entry(bm->cur.zone->list.next, struct mem_zone_bm_rtree, list);
bm->cur.node = list_entry(bm->cur.zone->leaves.next, struct rtree_node, list);
bm->cur.node_pfn = 0;
bm->cur.node_bit = 0; returntrue;
}
/* No more zones */ returnfalse;
}
/** * memory_bm_next_pfn - Find the next set bit in a memory bitmap. * @bm: Memory bitmap. * * Starting from the last returned position this function searches for the next * set bit in @bm and returns the PFN represented by it. If no more bits are * set, BM_END_OF_MAP is returned. * * It is required to run memory_bm_position_reset() before the first call to * this function for the given memory bitmap.
*/ staticunsignedlong memory_bm_next_pfn(struct memory_bitmap *bm)
{ unsignedlong bits, pfn, pages; int bit;
do {
pages = bm->cur.zone->end_pfn - bm->cur.zone->start_pfn;
bits = min(pages - bm->cur.node_pfn, BM_BITS_PER_BLOCK);
bit = find_next_bit(bm->cur.node->data, bits,
bm->cur.node_bit); if (bit < bits) {
pfn = bm->cur.zone->start_pfn + bm->cur.node_pfn + bit;
bm->cur.node_bit = bit + 1;
bm->cur.cur_pfn = pfn; return pfn;
}
} while (rtree_next_node(bm));
/* * This structure represents a range of page frames the contents of which * should not be saved during hibernation.
*/ struct nosave_region { struct list_head list; unsignedlong start_pfn; unsignedlong end_pfn;
};
/** * register_nosave_region - Register a region of unsaveable memory. * * Register a range of page frames the contents of which should not be saved * during hibernation (to be used in the early initialization code).
*/ void __init register_nosave_region(unsignedlong start_pfn, unsignedlong end_pfn)
{ struct nosave_region *region;
if (start_pfn >= end_pfn) return;
if (!list_empty(&nosave_regions)) { /* Try to extend the previous region (they should be sorted) */
region = list_entry(nosave_regions.prev, struct nosave_region, list); if (region->end_pfn == start_pfn) {
region->end_pfn = end_pfn; goto Report;
}
} /* This allocation cannot fail */
region = memblock_alloc_or_panic(sizeof(struct nosave_region),
SMP_CACHE_BYTES);
region->start_pfn = start_pfn;
region->end_pfn = end_pfn;
list_add_tail(®ion->list, &nosave_regions);
Report:
pr_info("Registered nosave memory: [mem %#010llx-%#010llx]\n",
(unsignedlonglong) start_pfn << PAGE_SHIFT,
((unsignedlonglong) end_pfn << PAGE_SHIFT) - 1);
}
/* * Set bits in this map correspond to the page frames the contents of which * should not be saved during the suspend.
*/ staticstruct memory_bitmap *forbidden_pages_map;
/* Set bits in this map correspond to free page frames. */ staticstruct memory_bitmap *free_pages_map;
/* * Each page frame allocated for creating the image is marked by setting the * corresponding bits in forbidden_pages_map and free_pages_map simultaneously
*/
void swsusp_set_page_free(struct page *page)
{ if (free_pages_map)
memory_bm_set_bit(free_pages_map, page_to_pfn(page));
}
staticvoid swsusp_unset_page_forbidden(struct page *page)
{ if (forbidden_pages_map)
memory_bm_clear_bit(forbidden_pages_map, page_to_pfn(page));
}
/** * mark_nosave_pages - Mark pages that should not be saved. * @bm: Memory bitmap. * * Set the bits in @bm that correspond to the page frames the contents of which * should not be saved.
*/ staticvoid mark_nosave_pages(struct memory_bitmap *bm)
{ struct nosave_region *region;
for_each_valid_pfn(pfn, region->start_pfn, region->end_pfn) { /* * It is safe to ignore the result of * mem_bm_set_bit_check() here, since we won't * touch the PFNs for which the error is * returned anyway.
*/
mem_bm_set_bit_check(bm, pfn);
}
}
}
/** * create_basic_memory_bitmaps - Create bitmaps to hold basic page information. * * Create bitmaps needed for marking page frames that should not be saved and * free page frames. The forbidden_pages_map and free_pages_map pointers are * only modified if everything goes well, because we don't want the bits to be * touched before both bitmaps are set up.
*/ int create_basic_memory_bitmaps(void)
{ struct memory_bitmap *bm1, *bm2; int error;
if (forbidden_pages_map && free_pages_map) return 0; else
BUG_ON(forbidden_pages_map || free_pages_map);
bm1 = kzalloc(sizeof(struct memory_bitmap), GFP_KERNEL); if (!bm1) return -ENOMEM;
error = memory_bm_create(bm1, GFP_KERNEL, PG_ANY); if (error) goto Free_first_object;
bm2 = kzalloc(sizeof(struct memory_bitmap), GFP_KERNEL); if (!bm2) goto Free_first_bitmap;
error = memory_bm_create(bm2, GFP_KERNEL, PG_ANY); if (error) goto Free_second_object;
/** * free_basic_memory_bitmaps - Free memory bitmaps holding basic information. * * Free memory bitmaps allocated by create_basic_memory_bitmaps(). The * auxiliary pointers are necessary so that the bitmaps themselves are not * referred to while they are being freed.
*/ void free_basic_memory_bitmaps(void)
{ struct memory_bitmap *bm1, *bm2;
if (WARN_ON(!(forbidden_pages_map && free_pages_map))) return;
/** * snapshot_additional_pages - Estimate the number of extra pages needed. * @zone: Memory zone to carry out the computation for. * * Estimate the number of additional pages needed for setting up a hibernation * image data structures for @zone (usually, the returned value is greater than * the exact number).
*/ unsignedint snapshot_additional_pages(struct zone *zone)
{ unsignedint rtree, nodes;
pfn = page_to_pfn(page); for (i = 0; i < (1UL << order); i++) { if (!--page_count) {
touch_nmi_watchdog();
page_count = WD_PAGE_COUNT;
}
swsusp_set_page_free(pfn_to_page(pfn + i));
}
}
}
spin_unlock_irqrestore(&zone->lock, flags);
}
#ifdef CONFIG_HIGHMEM /** * count_free_highmem_pages - Compute the total number of free highmem pages. * * The returned number is system-wide.
*/ staticunsignedint count_free_highmem_pages(void)
{ struct zone *zone; unsignedint cnt = 0;
for_each_populated_zone(zone) if (is_highmem(zone))
cnt += zone_page_state(zone, NR_FREE_PAGES);
return cnt;
}
/** * saveable_highmem_page - Check if a highmem page is saveable. * * Determine whether a highmem page should be included in a hibernation image. * * We should save the page if it isn't Nosave or NosaveFree, or Reserved, * and it isn't part of a free chunk of pages.
*/ staticstruct page *saveable_highmem_page(struct zone *zone, unsignedlong pfn)
{ struct page *page;
if (swsusp_page_is_forbidden(page) || swsusp_page_is_free(page)) return NULL;
if (PageReserved(page) || PageOffline(page)) return NULL;
if (page_is_guard(page)) return NULL;
return page;
}
/** * count_highmem_pages - Compute the total number of saveable highmem pages.
*/ staticunsignedint count_highmem_pages(void)
{ struct zone *zone; unsignedint n = 0;
/** * saveable_page - Check if the given page is saveable. * * Determine whether a non-highmem page should be included in a hibernation * image. * * We should save the page if it isn't Nosave, and is not in the range * of pages statically defined as 'unsaveable', and it isn't part of * a free chunk of pages.
*/ staticstruct page *saveable_page(struct zone *zone, unsignedlong pfn)
{ struct page *page;
if (swsusp_page_is_forbidden(page) || swsusp_page_is_free(page)) return NULL;
if (PageOffline(page)) return NULL;
if (PageReserved(page)
&& (!kernel_page_present(page) || pfn_is_nosave(pfn))) return NULL;
if (page_is_guard(page)) return NULL;
return page;
}
/** * count_data_pages - Compute the total number of saveable non-highmem pages.
*/ staticunsignedint count_data_pages(void)
{ struct zone *zone; unsignedlong pfn, max_zone_pfn; unsignedint n = 0;
for_each_populated_zone(zone) { if (is_highmem(zone)) continue;
mark_free_pages(zone);
max_zone_pfn = zone_end_pfn(zone); for (pfn = zone->zone_start_pfn; pfn < max_zone_pfn; pfn++) if (saveable_page(zone, pfn))
n++;
} return n;
}
/* * This is needed, because copy_page and memcpy are not usable for copying * task structs. Returns true if the page was filled with only zeros, * otherwise false.
*/ staticinlinebool do_copy_page(long *dst, long *src)
{ long z = 0; int n;
for (n = PAGE_SIZE / sizeof(long); n; n--) {
z |= *src;
*dst++ = *src++;
} return !z;
}
/** * safe_copy_page - Copy a page in a safe way. * * Check if the page we are going to copy is marked as present in the kernel * page tables. This always is the case if CONFIG_DEBUG_PAGEALLOC or * CONFIG_ARCH_HAS_SET_DIRECT_MAP is not set. In that case kernel_page_present() * always returns 'true'. Returns true if the page was entirely composed of * zeros, otherwise it will return false.
*/ staticbool safe_copy_page(void *dst, struct page *s_page)
{ bool zeros_only;
/* * Copy data pages will copy all pages into pages pulled from the copy_bm. * If a page was entirely filled with zeros it will be marked in the zero_bm. * * Returns the number of pages copied.
*/ staticunsignedlong copy_data_pages(struct memory_bitmap *copy_bm, struct memory_bitmap *orig_bm, struct memory_bitmap *zero_bm)
{ unsignedlong copied_pages = 0; struct zone *zone; unsignedlong pfn, copy_pfn;
mark_free_pages(zone);
max_zone_pfn = zone_end_pfn(zone); for (pfn = zone->zone_start_pfn; pfn < max_zone_pfn; pfn++) if (page_is_saveable(zone, pfn))
memory_bm_set_bit(orig_bm, pfn);
}
memory_bm_position_reset(orig_bm);
memory_bm_position_reset(copy_bm);
copy_pfn = memory_bm_next_pfn(copy_bm); for (;;) {
pfn = memory_bm_next_pfn(orig_bm); if (unlikely(pfn == BM_END_OF_MAP)) break; if (copy_data_page(copy_pfn, pfn)) {
memory_bm_set_bit(zero_bm, pfn); /* Use this copy_pfn for a page that is not full of zeros */ continue;
}
copied_pages++;
copy_pfn = memory_bm_next_pfn(copy_bm);
} return copied_pages;
}
/* Total number of image pages */ staticunsignedint nr_copy_pages; /* Number of pages needed for saving the original pfns of the image pages */ staticunsignedint nr_meta_pages; /* Number of zero pages */ staticunsignedint nr_zero_pages;
/* * Numbers of normal and highmem page frames allocated for hibernation image * before suspending devices.
*/ staticunsignedint alloc_normal, alloc_highmem; /* * Memory bitmap used for marking saveable pages (during hibernation) or * hibernation image pages (during restore)
*/ staticstruct memory_bitmap orig_bm; /* * Memory bitmap used during hibernation for marking allocated page frames that * will contain copies of saveable pages. During restore it is initially used * for marking hibernation image pages, but then the set bits from it are * duplicated in @orig_bm and it is released. On highmem systems it is next * used for marking "safe" highmem pages, but it has to be reinitialized for * this purpose.
*/ staticstruct memory_bitmap copy_bm;
/* Memory bitmap which tracks which saveable pages were zero filled. */ staticstruct memory_bitmap zero_bm;
/** * swsusp_free - Free pages allocated for hibernation image. * * Image pages are allocated before snapshot creation, so they need to be * released after resume.
*/ void swsusp_free(void)
{ unsignedlong fb_pfn, fr_pfn;
if (!forbidden_pages_map || !free_pages_map) goto out;
/* * Find the next bit set in both bitmaps. This is guaranteed to * terminate when fb_pfn == fr_pfn == BM_END_OF_MAP.
*/ do { if (fb_pfn < fr_pfn)
fb_pfn = memory_bm_next_pfn(forbidden_pages_map); if (fr_pfn < fb_pfn)
fr_pfn = memory_bm_next_pfn(free_pages_map);
} while (fb_pfn != fr_pfn);
/* Helper functions used for the shrinking of memory. */
#define GFP_IMAGE (GFP_KERNEL | __GFP_NOWARN)
/** * preallocate_image_pages - Allocate a number of pages for hibernation image. * @nr_pages: Number of page frames to allocate. * @mask: GFP flags to use for the allocation. * * Return value: Number of page frames actually allocated
*/ staticunsignedlong preallocate_image_pages(unsignedlong nr_pages, gfp_t mask)
{ unsignedlong nr_alloc = 0;
/** * minimum_image_size - Estimate the minimum acceptable size of an image. * @saveable: Number of saveable pages in the system. * * We want to avoid attempting to free too much memory too hard, so estimate the * minimum acceptable size of a hibernation image to use as the lower limit for * preallocating memory. * * We assume that the minimum image size should be proportional to * * [number of saveable pages] - [number of pages that can be freed in theory] * * where the second term is the sum of (1) reclaimable slab pages, (2) active * and (3) inactive anonymous pages, (4) active and (5) inactive file pages.
*/ staticunsignedlong minimum_image_size(unsignedlong saveable)
{ unsignedlong size;
/** * hibernate_preallocate_memory - Preallocate memory for hibernation image. * * To create a hibernation image it is necessary to make a copy of every page * frame in use. We also need a number of page frames to be free during * hibernation for allocations made while saving the image and for device * drivers, in case they need to allocate memory from their hibernation * callbacks (these two numbers are given by PAGES_FOR_IO (which is a rough * estimate) and reserved_size divided by PAGE_SIZE (which is tunable through * /sys/power/reserved_size, respectively). To make this happen, we compute the * total number of available page frames and allocate at least * * ([page frames total] - PAGES_FOR_IO - [metadata pages]) / 2 * - 2 * DIV_ROUND_UP(reserved_size, PAGE_SIZE) * * of them, which corresponds to the maximum size of a hibernation image. * * If image_size is set below the number following from the above formula, * the preallocation of memory is continued until the total number of saveable * pages in the system is below the requested image size or the minimum * acceptable image size returned by minimum_image_size(), whichever is greater.
*/ int hibernate_preallocate_memory(void)
{ struct zone *zone; unsignedlong saveable, size, max_size, count, highmem, pages = 0; unsignedlong alloc, save_highmem, pages_highmem, avail_normal;
ktime_t start, stop; int error;
/* Count the number of saveable data pages. */
save_highmem = count_highmem_pages();
saveable = count_data_pages();
/* * Compute the total number of page frames we can use (count) and the * number of pages needed for image metadata (size).
*/
count = saveable;
saveable += save_highmem;
highmem = save_highmem;
size = 0;
for_each_populated_zone(zone) {
size += snapshot_additional_pages(zone); if (is_highmem(zone))
highmem += zone_page_state(zone, NR_FREE_PAGES); else
count += zone_page_state(zone, NR_FREE_PAGES);
}
avail_normal = count;
count += highmem;
count -= totalreserve_pages;
/* Compute the maximum number of saveable pages to leave in memory. */
max_size = (count - (size + PAGES_FOR_IO)) / 2
- 2 * DIV_ROUND_UP(reserved_size, PAGE_SIZE); /* Compute the desired number of image pages specified by image_size. */
size = DIV_ROUND_UP(image_size, PAGE_SIZE); if (size > max_size)
size = max_size; /* * If the desired number of image pages is at least as large as the * current number of saveable pages in memory, allocate page frames for * the image and we're done.
*/ if (size >= saveable) {
pages = preallocate_image_highmem(save_highmem);
pages += preallocate_image_memory(saveable - pages, avail_normal); goto out;
}
/* Estimate the minimum size of the image. */
pages = minimum_image_size(saveable); /* * To avoid excessive pressure on the normal zone, leave room in it to * accommodate an image of the minimum size (unless it's already too * small, in which case don't preallocate pages from it at all).
*/ if (avail_normal > pages)
avail_normal -= pages; else
avail_normal = 0; if (size < pages)
size = min_t(unsignedlong, pages, max_size);
/* * Let the memory management subsystem know that we're going to need a * large number of page frames to allocate and make it free some memory. * NOTE: If this is not done, performance will be hurt badly in some * test cases.
*/
shrink_all_memory(saveable - size);
/* * The number of saveable pages in memory was too high, so apply some * pressure to decrease it. First, make room for the largest possible * image and fail if that doesn't work. Next, try to decrease the size * of the image as much as indicated by 'size' using allocations from * highmem and non-highmem zones separately.
*/
pages_highmem = preallocate_image_highmem(highmem / 2);
alloc = count - max_size; if (alloc > pages_highmem)
alloc -= pages_highmem; else
alloc = 0;
pages = preallocate_image_memory(alloc, avail_normal); if (pages < alloc) { /* We have exhausted non-highmem pages, try highmem. */
alloc -= pages;
pages += pages_highmem;
pages_highmem = preallocate_image_highmem(alloc); if (pages_highmem < alloc) {
pr_err("Image allocation is %lu pages short\n",
alloc - pages_highmem); goto err_out;
}
pages += pages_highmem; /* * size is the desired number of saveable pages to leave in * memory, so try to preallocate (all memory - size) pages.
*/
alloc = (count - pages) - size;
pages += preallocate_image_highmem(alloc);
} else { /* * There are approximately max_size saveable pages at this point * and we want to reduce this number down to size.
*/
alloc = max_size - size;
size = preallocate_highmem_fraction(alloc, highmem, count);
pages_highmem += size;
alloc -= size;
size = preallocate_image_memory(alloc, avail_normal);
pages_highmem += preallocate_image_highmem(alloc - size);
pages += pages_highmem + size;
}
/* * We only need as many page frames for the image as there are saveable * pages in memory, but we have allocated more. Release the excessive * ones now.
*/
pages -= free_unnecessary_pages();
#ifdef CONFIG_HIGHMEM /** * count_pages_for_highmem - Count non-highmem pages needed for copying highmem. * * Compute the number of non-highmem pages that will be necessary for creating * copies of highmem pages.
*/ staticunsignedint count_pages_for_highmem(unsignedint nr_highmem)
{ unsignedint free_highmem = count_free_highmem_pages() + alloc_highmem;
/** * enough_free_mem - Check if there is enough free memory for the image.
*/ staticint enough_free_mem(unsignedint nr_pages, unsignedint nr_highmem)
{ struct zone *zone; unsignedint free = alloc_normal;
for_each_populated_zone(zone) if (!is_highmem(zone))
free += zone_page_state(zone, NR_FREE_PAGES);
#ifdef CONFIG_HIGHMEM /** * get_highmem_buffer - Allocate a buffer for highmem pages. * * If there are some highmem pages in the hibernation image, we may need a * buffer to copy them and/or load their data.
*/ staticinlineint get_highmem_buffer(int safe_needed)
{
buffer = get_image_page(GFP_ATOMIC, safe_needed); return buffer ? 0 : -ENOMEM;
}
/** * alloc_highmem_pages - Allocate some highmem pages for the image. * * Try to allocate as many pages as needed, but if the number of free highmem * pages is less than that, allocate them all.
*/ staticinlineunsignedint alloc_highmem_pages(struct memory_bitmap *bm, unsignedint nr_highmem)
{ unsignedint to_alloc = count_free_highmem_pages();
/** * swsusp_alloc - Allocate memory for hibernation image. * * We first try to allocate as many highmem pages as there are * saveable highmem pages in the system. If that fails, we allocate * non-highmem pages for the copies of the remaining highmem ones. * * In this approach it is likely that the copies of highmem pages will * also be located in the high memory, because of the way in which * copy_data_pages() works.
*/ staticint swsusp_alloc(struct memory_bitmap *copy_bm, unsignedint nr_pages, unsignedint nr_highmem)
{ if (nr_highmem > 0) { if (get_highmem_buffer(PG_ANY)) goto err_out; if (nr_highmem > alloc_highmem) {
nr_highmem -= alloc_highmem;
nr_pages += alloc_highmem_pages(copy_bm, nr_highmem);
}
} if (nr_pages > alloc_normal) {
nr_pages -= alloc_normal; while (nr_pages-- > 0) { struct page *page;
/* * End of critical section. From now on, we can write to memory, * but we should not touch disk. This specially means we must _not_ * touch swap space! Except we must write out our image of course.
*/
nr_pages += nr_highmem; /* We don't actually copy the zero pages */
nr_zero_pages = nr_pages - nr_copy_pages;
nr_meta_pages = DIV_ROUND_UP(nr_pages * sizeof(long), PAGE_SIZE);
pr_info("Image created (%d pages copied, %d zero pages)\n", nr_copy_pages, nr_zero_pages);
/** * pack_pfns - Prepare PFNs for saving. * @bm: Memory bitmap. * @buf: Memory buffer to store the PFNs in. * @zero_bm: Memory bitmap containing PFNs of zero pages. * * PFNs corresponding to set bits in @bm are stored in the area of memory * pointed to by @buf (1 page at a time). Pages which were filled with only * zeros will have the highest bit set in the packed format to distinguish * them from PFNs which will be contained in the image file.
*/ staticinlinevoid pack_pfns(unsignedlong *buf, struct memory_bitmap *bm, struct memory_bitmap *zero_bm)
{ int j;
for (j = 0; j < PAGE_SIZE / sizeof(long); j++) {
buf[j] = memory_bm_next_pfn(bm); if (unlikely(buf[j] == BM_END_OF_MAP)) break; if (memory_bm_test_bit(zero_bm, buf[j]))
buf[j] |= ENCODED_PFN_ZERO_FLAG;
}
}
/** * snapshot_read_next - Get the address to read the next image page from. * @handle: Snapshot handle to be used for the reading. * * On the first call, @handle should point to a zeroed snapshot_handle * structure. The structure gets populated then and a pointer to it should be * passed to this function every next time. * * On success, the function returns a positive number. Then, the caller * is allowed to read up to the returned number of bytes from the memory * location computed by the data_of() macro. * * The function returns 0 to indicate the end of the data stream condition, * and negative numbers are returned on errors. If that happens, the structure * pointed to by @handle is not updated and should not be used any more.
*/ int snapshot_read_next(struct snapshot_handle *handle)
{ if (handle->cur > nr_meta_pages + nr_copy_pages) return 0;
if (!buffer) { /* This makes the buffer be freed by swsusp_free() */
buffer = get_image_page(GFP_ATOMIC, PG_ANY); if (!buffer) return -ENOMEM;
} if (!handle->cur) { int error;
/** * mark_unsafe_pages - Mark pages that were used before hibernation. * * Mark the pages that cannot be used for storing the image during restoration, * because they conflict with the pages that had been used before hibernation.
*/ staticvoid mark_unsafe_pages(struct memory_bitmap *bm)
{ unsignedlong pfn;
/* Clear the "free"/"unsafe" bit for all PFNs */
memory_bm_position_reset(free_pages_map);
pfn = memory_bm_next_pfn(free_pages_map); while (pfn != BM_END_OF_MAP) {
memory_bm_clear_current(free_pages_map);
pfn = memory_bm_next_pfn(free_pages_map);
}
/* Mark pages that correspond to the "original" PFNs as "unsafe" */
duplicate_memory_bitmap(free_pages_map, bm);
/** * unpack_orig_pfns - Set bits corresponding to given PFNs in a memory bitmap. * @bm: Memory bitmap. * @buf: Area of memory containing the PFNs. * @zero_bm: Memory bitmap with the zero PFNs marked. * * For each element of the array pointed to by @buf (1 page at a time), set the * corresponding bit in @bm. If the page was originally populated with only * zeros then a corresponding bit will also be set in @zero_bm.
*/ staticint unpack_orig_pfns(unsignedlong *buf, struct memory_bitmap *bm, struct memory_bitmap *zero_bm)
{ unsignedlong decoded_pfn; bool zero; int j;
for (j = 0; j < PAGE_SIZE / sizeof(long); j++) { if (unlikely(buf[j] == BM_END_OF_MAP)) break;
zero = !!(buf[j] & ENCODED_PFN_ZERO_FLAG);
decoded_pfn = buf[j] & ENCODED_PFN_MASK; if (pfn_valid(decoded_pfn) && memory_bm_pfn_present(bm, decoded_pfn)) {
memory_bm_set_bit(bm, decoded_pfn); if (zero) {
memory_bm_set_bit(zero_bm, decoded_pfn);
nr_zero_pages++;
}
} else { if (!pfn_valid(decoded_pfn))
pr_err(FW_BUG "Memory map mismatch at 0x%llx after hibernation\n",
(unsignedlonglong)PFN_PHYS(decoded_pfn)); return -EFAULT;
}
}
return 0;
}
#ifdef CONFIG_HIGHMEM /* * struct highmem_pbe is used for creating the list of highmem pages that * should be restored atomically during the resume from disk, because the page * frames they have occupied before the suspend are in use.
*/ struct highmem_pbe { struct page *copy_page; /* data is here now */ struct page *orig_page; /* data was here before the suspend */ struct highmem_pbe *next;
};
/* * List of highmem PBEs needed for restoring the highmem pages that were * allocated before the suspend and included in the suspend image, but have * also been allocated by the "resume" kernel, so their contents cannot be * written directly to their "original" page frames.
*/ staticstruct highmem_pbe *highmem_pblist;
/** * count_highmem_image_pages - Compute the number of highmem pages in the image. * @bm: Memory bitmap. * * The bits in @bm that correspond to image pages are assumed to be set.
*/ staticunsignedint count_highmem_image_pages(struct memory_bitmap *bm)
{ unsignedlong pfn; unsignedint cnt = 0;
memory_bm_position_reset(bm);
pfn = memory_bm_next_pfn(bm); while (pfn != BM_END_OF_MAP) { if (PageHighMem(pfn_to_page(pfn)))
cnt++;
pfn = memory_bm_next_pfn(bm);
} return cnt;
}
staticunsignedint safe_highmem_pages;
staticstruct memory_bitmap *safe_highmem_bm;
/** * prepare_highmem_image - Allocate memory for loading highmem data from image. * @bm: Pointer to an uninitialized memory bitmap structure. * @nr_highmem_p: Pointer to the number of highmem image pages. * * Try to allocate as many highmem pages as there are highmem image pages * (@nr_highmem_p points to the variable containing the number of highmem image
--> --------------------
--> maximum size reached
--> --------------------
Messung V0.5
¤ Dauer der Verarbeitung: 0.12 Sekunden
(vorverarbeitet)
¤
Die Informationen auf dieser Webseite wurden
nach bestem Wissen sorgfältig zusammengestellt. Es wird jedoch weder Vollständigkeit, noch Richtigkeit,
noch Qualität der bereit gestellten Informationen zugesichert.
Bemerkung:
Die farbliche Syntaxdarstellung und die Messung sind noch experimentell.