*
* Rewritten to use page cache, (C) 1998 Stephen Tweedie
*/
-#include <linux/module.h>
#include <linux/mm.h>
#include <linux/gfp.h>
#include <linux/kernel_stat.h>
#include <linux/swapops.h>
#include <linux/init.h>
#include <linux/pagemap.h>
-#include <linux/buffer_head.h>
#include <linux/backing-dev.h>
+#include <linux/blkdev.h>
#include <linux/pagevec.h>
#include <linux/migrate.h>
#include <linux/page_cgroup.h>
*/
static const struct address_space_operations swap_aops = {
.writepage = swap_writepage,
- .set_page_dirty = __set_page_dirty_nobuffers,
+ .set_page_dirty = swap_set_page_dirty,
.migratepage = migrate_page,
};
.capabilities = BDI_CAP_NO_ACCT_AND_WRITEBACK | BDI_CAP_SWAP_BACKED,
};
-struct address_space swapper_space = {
- .page_tree = RADIX_TREE_INIT(GFP_ATOMIC|__GFP_NOWARN),
- .tree_lock = __SPIN_LOCK_UNLOCKED(swapper_space.tree_lock),
- .a_ops = &swap_aops,
- .i_mmap_nonlinear = LIST_HEAD_INIT(swapper_space.i_mmap_nonlinear),
- .backing_dev_info = &swap_backing_dev_info,
+struct address_space swapper_spaces[MAX_SWAPFILES] = {
+ [0 ... MAX_SWAPFILES - 1] = {
+ .page_tree = RADIX_TREE_INIT(GFP_ATOMIC|__GFP_NOWARN),
+ .a_ops = &swap_aops,
+ .backing_dev_info = &swap_backing_dev_info,
+ }
};
#define INC_CACHE_INFO(x) do { swap_cache_info.x++; } while (0)
unsigned long find_total;
} swap_cache_info;
+unsigned long total_swapcache_pages(void)
+{
+ int i;
+ unsigned long ret = 0;
+
+ for (i = 0; i < MAX_SWAPFILES; i++)
+ ret += swapper_spaces[i].nrpages;
+ return ret;
+}
+
void show_swap_cache_info(void)
{
- printk("%lu pages in swap cache\n", total_swapcache_pages);
+ printk("%lu pages in swap cache\n", total_swapcache_pages());
printk("Swap cache stats: add %lu, delete %lu, find %lu/%lu\n",
swap_cache_info.add_total, swap_cache_info.del_total,
swap_cache_info.find_success, swap_cache_info.find_total);
- printk("Free swap = %ldkB\n", nr_swap_pages << (PAGE_SHIFT - 10));
+ printk("Free swap = %ldkB\n",
+ get_nr_swap_pages() << (PAGE_SHIFT - 10));
printk("Total swap = %lukB\n", total_swap_pages << (PAGE_SHIFT - 10));
}
* __add_to_swap_cache resembles add_to_page_cache_locked on swapper_space,
* but sets SwapCache flag and private instead of mapping and index.
*/
-static int __add_to_swap_cache(struct page *page, swp_entry_t entry)
+int __add_to_swap_cache(struct page *page, swp_entry_t entry)
{
int error;
+ struct address_space *address_space;
VM_BUG_ON(!PageLocked(page));
VM_BUG_ON(PageSwapCache(page));
SetPageSwapCache(page);
set_page_private(page, entry.val);
- spin_lock_irq(&swapper_space.tree_lock);
- error = radix_tree_insert(&swapper_space.page_tree, entry.val, page);
+ address_space = swap_address_space(entry);
+ spin_lock_irq(&address_space->tree_lock);
+ error = radix_tree_insert(&address_space->page_tree,
+ entry.val, page);
if (likely(!error)) {
- total_swapcache_pages++;
+ address_space->nrpages++;
__inc_zone_page_state(page, NR_FILE_PAGES);
INC_CACHE_INFO(add_total);
}
- spin_unlock_irq(&swapper_space.tree_lock);
+ spin_unlock_irq(&address_space->tree_lock);
if (unlikely(error)) {
/*
*/
void __delete_from_swap_cache(struct page *page)
{
+ swp_entry_t entry;
+ struct address_space *address_space;
+
VM_BUG_ON(!PageLocked(page));
VM_BUG_ON(!PageSwapCache(page));
VM_BUG_ON(PageWriteback(page));
- radix_tree_delete(&swapper_space.page_tree, page_private(page));
+ entry.val = page_private(page);
+ address_space = swap_address_space(entry);
+ radix_tree_delete(&address_space->page_tree, page_private(page));
set_page_private(page, 0);
ClearPageSwapCache(page);
- total_swapcache_pages--;
+ address_space->nrpages--;
__dec_zone_page_state(page, NR_FILE_PAGES);
INC_CACHE_INFO(del_total);
}
* 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)
+int add_to_swap(struct page *page, struct list_head *list)
{
swp_entry_t entry;
int err;
return 0;
if (unlikely(PageTransHuge(page)))
- if (unlikely(split_huge_page(page))) {
+ if (unlikely(split_huge_page_to_list(page, list))) {
swapcache_free(entry, NULL);
return 0;
}
void delete_from_swap_cache(struct page *page)
{
swp_entry_t entry;
+ struct address_space *address_space;
entry.val = page_private(page);
- spin_lock_irq(&swapper_space.tree_lock);
+ address_space = swap_address_space(entry);
+ spin_lock_irq(&address_space->tree_lock);
__delete_from_swap_cache(page);
- spin_unlock_irq(&swapper_space.tree_lock);
+ spin_unlock_irq(&address_space->tree_lock);
swapcache_free(entry, page);
page_cache_release(page);
{
struct page *page;
- page = find_get_page(&swapper_space, entry.val);
+ page = find_get_page(swap_address_space(entry), entry.val);
if (page)
INC_CACHE_INFO(find_success);
* called after lookup_swap_cache() failed, re-calling
* that would confuse statistics.
*/
- found_page = find_get_page(&swapper_space, entry.val);
+ found_page = find_get_page(swap_address_space(entry),
+ entry.val);
if (found_page)
break;
* Swap entry may have been freed since our caller observed it.
*/
err = swapcache_prepare(entry);
- if (err == -EEXIST) { /* seems racy */
+ if (err == -EEXIST) {
radix_tree_preload_end();
+ /*
+ * We might race against get_swap_page() and stumble
+ * across a SWAP_HAS_CACHE swap_map entry whose page
+ * has not been brought into the swapcache yet, while
+ * the other end is scheduled away waiting on discard
+ * I/O completion at scan_swap_map().
+ *
+ * In order to avoid turning this transitory state
+ * into a permanent loop around this -EEXIST case
+ * if !CONFIG_PREEMPT and the I/O completion happens
+ * to be waiting on the CPU waitqueue where we are now
+ * busy looping, we just conditionally invoke the
+ * scheduler here, if there are some more important
+ * tasks to run.
+ */
+ cond_resched();
continue;
}
if (err) { /* swp entry is obsolete ? */
struct page *swapin_readahead(swp_entry_t entry, gfp_t gfp_mask,
struct vm_area_struct *vma, unsigned long addr)
{
- int nr_pages;
struct page *page;
- unsigned long offset;
- unsigned long end_offset;
-
- /*
- * Get starting offset for readaround, and number of pages to read.
- * Adjust starting address by readbehind (for NUMA interleave case)?
- * No, it's very unlikely that swap layout would follow vma layout,
- * more likely that neighbouring swap pages came from the same node:
- * so use the same "addr" to choose the same node for each swap read.
- */
- nr_pages = valid_swaphandles(entry, &offset);
- for (end_offset = offset + nr_pages; offset < end_offset; offset++) {
+ unsigned long offset = swp_offset(entry);
+ unsigned long start_offset, end_offset;
+ unsigned long mask = (1UL << page_cluster) - 1;
+ struct blk_plug plug;
+
+ /* Read a page_cluster sized and aligned cluster around offset. */
+ start_offset = offset & ~mask;
+ end_offset = offset | mask;
+ if (!start_offset) /* First page is swap header. */
+ start_offset++;
+
+ blk_start_plug(&plug);
+ for (offset = start_offset; offset <= end_offset ; offset++) {
/* Ok, do the async read-ahead now */
page = read_swap_cache_async(swp_entry(swp_type(entry), offset),
gfp_mask, vma, addr);
if (!page)
- break;
+ continue;
page_cache_release(page);
}
+ blk_finish_plug(&plug);
+
lru_add_drain(); /* Push any new pages onto the LRU now */
return read_swap_cache_async(entry, gfp_mask, vma, addr);
}