/**
* add_to_swap - allocate swap space for a page
* @page: page we want to move to swap
*
* Allocate swap space for the page and add the page to the
* swap cache. Caller needs to hold the page lock.
*/
int add_to_swap(struct page *page)
{
swp_entry_t entry;
int err;
VM_BUG_ON(!PageLocked(page));
VM_BUG_ON(!PageUptodate(page));
entry = get_swap_page();
if (!entry.val)
return 0;
if (unlikely(PageTransHuge(page)))
if (unlikely(split_huge_page(page))) {
swapcache_free(entry, NULL);
return 0;
}
/*
* Radix-tree node allocations from PF_MEMALLOC contexts could
* completely exhaust the page allocator. __GFP_NOMEMALLOC
* stops emergency reserves from being allocated.
*
* TODO: this could cause a theoretical memory reclaim
* deadlock in the swap out path.
*/
/*
* Add it to the swap cache and mark it dirty
*/
err = add_to_swap_cache(page, entry,
__GFP_HIGH|__GFP_NOMEMALLOC|__GFP_NOWARN);
if (!err) { /* Success */
SetPageDirty(page);
return 1;
} else { /* -ENOMEM radix-tree allocation failure */
/*
* add_to_swap_cache() doesn't return -EEXIST, so we can safely
* clear SWAP_HAS_CACHE flag.
*/
swapcache_free(entry, NULL);
return 0;
}
}
/**
* add_to_swap - allocate swap space for a page
* @page: page we want to move to swap
*
* Allocate swap space for the page and add the page to the
* swap cache. Caller needs to hold the page lock.
*/
int add_to_swap(struct page * page, gfp_t gfp_mask)
{
swp_entry_t entry;
int err;
BUG_ON(!PageLocked(page));
for (;;) {
entry = get_swap_page();
if (!entry.val)
return 0;
/*
* Radix-tree node allocations from PF_MEMALLOC contexts could
* completely exhaust the page allocator. __GFP_NOMEMALLOC
* stops emergency reserves from being allocated.
*
* TODO: this could cause a theoretical memory reclaim
* deadlock in the swap out path.
*/
/*
* Add it to the swap cache and mark it dirty
*/
err = __add_to_swap_cache(page, entry,
gfp_mask|__GFP_NOMEMALLOC|__GFP_NOWARN);
switch (err) {
case 0: /* Success */
SetPageUptodate(page);
SetPageDirty(page);
INC_CACHE_INFO(add_total);
return 1;
case -EEXIST:
/* Raced with "speculative" read_swap_cache_async */
INC_CACHE_INFO(exist_race);
swap_free(entry);
continue;
default:
/* -ENOMEM radix-tree allocation failure */
swap_free(entry);
return 0;
}
}
}
/**
* add_to_swap - allocate swap space for a page
* @page: page we want to move to swap
*
* Allocate swap space for the page and add the page to the
* swap cache. Caller needs to hold the page lock.
*/
int add_to_swap(struct page *page)
{
swp_entry_t entry;
int err;
VM_BUG_ON_PAGE(!PageLocked(page), page);
VM_BUG_ON_PAGE(!PageUptodate(page), page);
entry = get_swap_page(page);
if (!entry.val)
return 0;
if (mem_cgroup_try_charge_swap(page, entry))
goto fail;
/*
* Radix-tree node allocations from PF_MEMALLOC contexts could
* completely exhaust the page allocator. __GFP_NOMEMALLOC
* stops emergency reserves from being allocated.
*
* TODO: this could cause a theoretical memory reclaim
* deadlock in the swap out path.
*/
/*
* Add it to the swap cache.
*/
err = add_to_swap_cache(page, entry,
__GFP_HIGH|__GFP_NOMEMALLOC|__GFP_NOWARN);
/* -ENOMEM radix-tree allocation failure */
if (err)
/*
* add_to_swap_cache() doesn't return -EEXIST, so we can safely
* clear SWAP_HAS_CACHE flag.
*/
goto fail;
return 1;
fail:
put_swap_page(page, entry);
return 0;
}
/* mm->page_table_lock is held. mmap_sem is not held */
static inline int try_to_swap_out(struct mm_struct * mm, struct vm_area_struct* vma, unsigned long address, pte_t * page_table, struct page *page, zone_t * classzone)
{
pte_t pte;
swp_entry_t entry;
/* Don't look at this pte if it's been accessed recently. */
if ((vma->vm_flags & VM_LOCKED) || ptep_test_and_clear_young(page_table)) {
mark_page_accessed(page);
return 0;
}
/* Don't bother unmapping pages that are active */
if (PageActive(page))
return 0;
/* Don't bother replenishing zones not under pressure.. */
if (!memclass(page->zone, classzone))
return 0;
if (TryLockPage(page))
return 0;
/* From this point on, the odds are that we're going to
* nuke this pte, so read and clear the pte. This hook
* is needed on CPUs which update the accessed and dirty
* bits in hardware.
*/
flush_cache_page(vma, address);
pte = ptep_get_and_clear(page_table);
flush_tlb_page(vma, address);
if (pte_dirty(pte))
set_page_dirty(page);
/*
* Is the page already in the swap cache? If so, then
* we can just drop our reference to it without doing
* any IO - it's already up-to-date on disk.
*/
if (PageSwapCache(page)) {
entry.val = page->index;
swap_duplicate(entry);
set_swap_pte:
set_pte(page_table, swp_entry_to_pte(entry));
drop_pte:
mm->rss--;
UnlockPage(page);
{
int freeable = page_count(page) - !!page->buffers <= 2;
page_cache_release(page);
return freeable;
}
}
/*
* Is it a clean page? Then it must be recoverable
* by just paging it in again, and we can just drop
* it.. or if it's dirty but has backing store,
* just mark the page dirty and drop it.
*
* However, this won't actually free any real
* memory, as the page will just be in the page cache
* somewhere, and as such we should just continue
* our scan.
*
* Basically, this just makes it possible for us to do
* some real work in the future in "refill_inactive()".
*/
if (page->mapping)
goto drop_pte;
if (!PageDirty(page))
goto drop_pte;
/*
* Anonymous buffercache pages can be left behind by
* concurrent truncate and pagefault.
*/
if (page->buffers)
goto preserve;
/*
* This is a dirty, swappable page. First of all,
* get a suitable swap entry for it, and make sure
* we have the swap cache set up to associate the
* page with that swap entry.
*/
for (;;) {
entry = get_swap_page();
if (!entry.val)
break;
/* Add it to the swap cache and mark it dirty
* (adding to the page cache will clear the dirty
* and uptodate bits, so we need to do it again)
*/
if (add_to_swap_cache(page, entry) == 0) {
SetPageUptodate(page);
set_page_dirty(page);
goto set_swap_pte;
}
/* Raced with "speculative" read_swap_cache_async */
swap_free(entry);
}
/* No swap space left */
preserve:
set_pte(page_table, pte);
UnlockPage(page);
return 0;
}
/*
* The swap-out functions return 1 if they successfully
* threw something out, and we got a free page. It returns
* zero if it couldn't do anything, and any other value
* indicates it decreased rss, but the page was shared.
*
* NOTE! If it sleeps, it *must* return 1 to make sure we
* don't continue with the swap-out. Otherwise we may be
* using a process that no longer actually exists (it might
* have died while we slept).
*/
static int try_to_swap_out(struct mm_struct * mm, struct vm_area_struct* vma, unsigned long address, pte_t * page_table, int gfp_mask)
{
pte_t pte;
swp_entry_t entry;
struct page * page;
int onlist;
pte = *page_table;
if (!pte_present(pte))
goto out_failed;
page = pte_page(pte);
if ((!VALID_PAGE(page)) || PageReserved(page))
goto out_failed;
if (mm->swap_cnt)
mm->swap_cnt--;
onlist = PageActive(page);
/* Don't look at this pte if it's been accessed recently. */
if (ptep_test_and_clear_young(page_table)) {
age_page_up(page);
goto out_failed;
}
if (!onlist)
/* The page is still mapped, so it can't be freeable... */
age_page_down_ageonly(page);
/*
* If the page is in active use by us, or if the page
* is in active use by others, don't unmap it or
* (worse) start unneeded IO.
*/
if (page->age > 0)
goto out_failed;
if (TryLockPage(page))
goto out_failed;
/* From this point on, the odds are that we're going to
* nuke this pte, so read and clear the pte. This hook
* is needed on CPUs which update the accessed and dirty
* bits in hardware.
*/
pte = ptep_get_and_clear(page_table);
/*
* Is the page already in the swap cache? If so, then
* we can just drop our reference to it without doing
* any IO - it's already up-to-date on disk.
*
* Return 0, as we didn't actually free any real
* memory, and we should just continue our scan.
*/
if (PageSwapCache(page)) {
entry.val = page->index;
if (pte_dirty(pte))
set_page_dirty(page);
set_swap_pte:
swap_duplicate(entry);
set_pte(page_table, swp_entry_to_pte(entry));
drop_pte:
UnlockPage(page);
mm->rss--;
flush_tlb_page(vma, address);
deactivate_page(page);
page_cache_release(page);
out_failed:
return 0;
}
/*
* Is it a clean page? Then it must be recoverable
* by just paging it in again, and we can just drop
* it..
*
* However, this won't actually free any real
* memory, as the page will just be in the page cache
* somewhere, and as such we should just continue
* our scan.
*
* Basically, this just makes it possible for us to do
* some real work in the future in "refill_inactive()".
*/
flush_cache_page(vma, address);
if (!pte_dirty(pte))
goto drop_pte;
/*
* Ok, it's really dirty. That means that
* we should either create a new swap cache
* entry for it, or we should write it back
* to its own backing store.
*/
if (page->mapping) {
set_page_dirty(page);
goto drop_pte;
}
/*
* This is a dirty, swappable page. First of all,
* get a suitable swap entry for it, and make sure
* we have the swap cache set up to associate the
* page with that swap entry.
*/
entry = get_swap_page();
if (!entry.val)
goto out_unlock_restore; /* No swap space left */
/* Add it to the swap cache and mark it dirty */
add_to_swap_cache(page, entry);
set_page_dirty(page);
goto set_swap_pte;
out_unlock_restore:
set_pte(page_table, pte);
UnlockPage(page);
return 0;
}
/**
* write_suspend_image - Write entire image to disk.
*
* After writing suspend signature to the disk, suspend may no
* longer fail: we have ready-to-run image in swap, and rollback
* would happen on next reboot -- corrupting data.
*
* Note: The buffer we allocate to use to write the suspend header is
* not freed; its not needed since system is going down anyway
* (plus it causes oops and I'm lazy^H^H^H^Htoo busy).
*/
static int write_suspend_image(void)
{
int i;
swp_entry_t entry, prev = { 0 };
int nr_pgdir_pages = SUSPEND_PD_PAGES(nr_copy_pages);
union diskpage *cur, *buffer = (union diskpage *)get_zeroed_page(GFP_ATOMIC);
unsigned long address;
struct page *page;
if (!buffer)
return -ENOMEM;
printk( "Writing data to swap (%d pages): ", nr_copy_pages );
for (i=0; i<nr_copy_pages; i++) {
if (!(i%100))
printk( "." );
if (!(entry = get_swap_page()).val)
panic("\nNot enough swapspace when writing data" );
if (swapfile_used[swp_type(entry)] != SWAPFILE_SUSPEND)
panic("\nPage %d: not enough swapspace on suspend device", i );
address = (pagedir_nosave+i)->address;
page = virt_to_page(address);
rw_swap_page_sync(WRITE, entry, page);
(pagedir_nosave+i)->swap_address = entry;
}
printk( "|\n" );
printk( "Writing pagedir (%d pages): ", nr_pgdir_pages);
for (i=0; i<nr_pgdir_pages; i++) {
cur = (union diskpage *)((char *) pagedir_nosave)+i;
BUG_ON ((char *) cur != (((char *) pagedir_nosave) + i*PAGE_SIZE));
printk( "." );
if (!(entry = get_swap_page()).val) {
printk(KERN_CRIT "Not enough swapspace when writing pgdir\n" );
panic("Don't know how to recover");
free_page((unsigned long) buffer);
return -ENOSPC;
}
if(swapfile_used[swp_type(entry)] != SWAPFILE_SUSPEND)
panic("\nNot enough swapspace for pagedir on suspend device" );
BUG_ON (sizeof(swp_entry_t) != sizeof(long));
BUG_ON (PAGE_SIZE % sizeof(struct pbe));
cur->link.next = prev;
page = virt_to_page((unsigned long)cur);
rw_swap_page_sync(WRITE, entry, page);
prev = entry;
}
printk("H");
BUG_ON (sizeof(struct suspend_header) > PAGE_SIZE-sizeof(swp_entry_t));
BUG_ON (sizeof(union diskpage) != PAGE_SIZE);
if (!(entry = get_swap_page()).val)
panic( "\nNot enough swapspace when writing header" );
if (swapfile_used[swp_type(entry)] != SWAPFILE_SUSPEND)
panic("\nNot enough swapspace for header on suspend device" );
cur = (void *) buffer;
if (fill_suspend_header(&cur->sh))
panic("\nOut of memory while writing header");
cur->link.next = prev;
page = virt_to_page((unsigned long)cur);
rw_swap_page_sync(WRITE, entry, page);
prev = entry;
printk( "S" );
mark_swapfiles(prev, MARK_SWAP_SUSPEND);
printk( "|\n" );
MDELAY(1000);
return 0;
}