aboutsummaryrefslogtreecommitdiff
path: root/mm/swap_state.c
diff options
context:
space:
mode:
Diffstat (limited to 'mm/swap_state.c')
-rw-r--r--mm/swap_state.c109
1 files changed, 91 insertions, 18 deletions
diff --git a/mm/swap_state.c b/mm/swap_state.c
index 7efcf152592..2972eee184a 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -63,6 +63,8 @@ unsigned long total_swapcache_pages(void)
return ret;
}
+static atomic_t swapin_readahead_hits = ATOMIC_INIT(4);
+
void show_swap_cache_info(void)
{
printk("%lu pages in swap cache\n", total_swapcache_pages());
@@ -78,14 +80,14 @@ void show_swap_cache_info(void)
* __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));
- VM_BUG_ON(!PageSwapBacked(page));
+ VM_BUG_ON_PAGE(!PageLocked(page), page);
+ VM_BUG_ON_PAGE(PageSwapCache(page), page);
+ VM_BUG_ON_PAGE(!PageSwapBacked(page), page);
page_cache_get(page);
SetPageSwapCache(page);
@@ -122,7 +124,7 @@ int add_to_swap_cache(struct page *page, swp_entry_t entry, gfp_t gfp_mask)
{
int error;
- error = radix_tree_preload(gfp_mask);
+ error = radix_tree_maybe_preload(gfp_mask);
if (!error) {
error = __add_to_swap_cache(page, entry);
radix_tree_preload_end();
@@ -139,9 +141,9 @@ 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));
+ VM_BUG_ON_PAGE(!PageLocked(page), page);
+ VM_BUG_ON_PAGE(!PageSwapCache(page), page);
+ VM_BUG_ON_PAGE(PageWriteback(page), page);
entry.val = page_private(page);
address_space = swap_address_space(entry);
@@ -160,20 +162,20 @@ void __delete_from_swap_cache(struct page *page)
* 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;
- VM_BUG_ON(!PageLocked(page));
- VM_BUG_ON(!PageUptodate(page));
+ VM_BUG_ON_PAGE(!PageLocked(page), page);
+ VM_BUG_ON_PAGE(!PageUptodate(page), page);
entry = get_swap_page();
if (!entry.val)
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;
}
@@ -268,7 +270,7 @@ void free_pages_and_swap_cache(struct page **pages, int nr)
for (i = 0; i < todo; i++)
free_swap_cache(pagep[i]);
- release_pages(pagep, todo, 0);
+ release_pages(pagep, todo, false);
pagep += todo;
nr -= todo;
}
@@ -286,8 +288,11 @@ struct page * lookup_swap_cache(swp_entry_t entry)
page = find_get_page(swap_address_space(entry), entry.val);
- if (page)
+ if (page) {
INC_CACHE_INFO(find_success);
+ if (TestClearPageReadahead(page))
+ atomic_inc(&swapin_readahead_hits);
+ }
INC_CACHE_INFO(find_total);
return page;
@@ -328,7 +333,7 @@ struct page *read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
/*
* call radix_tree_preload() while we can wait.
*/
- err = radix_tree_preload(gfp_mask & GFP_KERNEL);
+ err = radix_tree_maybe_preload(gfp_mask & GFP_KERNEL);
if (err)
break;
@@ -336,8 +341,24 @@ struct page *read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
* 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 ? */
@@ -373,6 +394,50 @@ struct page *read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
return found_page;
}
+static unsigned long swapin_nr_pages(unsigned long offset)
+{
+ static unsigned long prev_offset;
+ unsigned int pages, max_pages, last_ra;
+ static atomic_t last_readahead_pages;
+
+ max_pages = 1 << ACCESS_ONCE(page_cluster);
+ if (max_pages <= 1)
+ return 1;
+
+ /*
+ * This heuristic has been found to work well on both sequential and
+ * random loads, swapping to hard disk or to SSD: please don't ask
+ * what the "+ 2" means, it just happens to work well, that's all.
+ */
+ pages = atomic_xchg(&swapin_readahead_hits, 0) + 2;
+ if (pages == 2) {
+ /*
+ * We can have no readahead hits to judge by: but must not get
+ * stuck here forever, so check for an adjacent offset instead
+ * (and don't even bother to check whether swap type is same).
+ */
+ if (offset != prev_offset + 1 && offset != prev_offset - 1)
+ pages = 1;
+ prev_offset = offset;
+ } else {
+ unsigned int roundup = 4;
+ while (roundup < pages)
+ roundup <<= 1;
+ pages = roundup;
+ }
+
+ if (pages > max_pages)
+ pages = max_pages;
+
+ /* Don't shrink readahead too fast */
+ last_ra = atomic_read(&last_readahead_pages) / 2;
+ if (pages < last_ra)
+ pages = last_ra;
+ atomic_set(&last_readahead_pages, pages);
+
+ return pages;
+}
+
/**
* swapin_readahead - swap in pages in hope we need them soon
* @entry: swap entry of this memory
@@ -396,11 +461,16 @@ struct page *swapin_readahead(swp_entry_t entry, gfp_t gfp_mask,
struct vm_area_struct *vma, unsigned long addr)
{
struct page *page;
- unsigned long offset = swp_offset(entry);
+ unsigned long entry_offset = swp_offset(entry);
+ unsigned long offset = entry_offset;
unsigned long start_offset, end_offset;
- unsigned long mask = (1UL << page_cluster) - 1;
+ unsigned long mask;
struct blk_plug plug;
+ mask = swapin_nr_pages(offset) - 1;
+ if (!mask)
+ goto skip;
+
/* Read a page_cluster sized and aligned cluster around offset. */
start_offset = offset & ~mask;
end_offset = offset | mask;
@@ -414,10 +484,13 @@ struct page *swapin_readahead(swp_entry_t entry, gfp_t gfp_mask,
gfp_mask, vma, addr);
if (!page)
continue;
+ if (offset != entry_offset)
+ SetPageReadahead(page);
page_cache_release(page);
}
blk_finish_plug(&plug);
lru_add_drain(); /* Push any new pages onto the LRU now */
+skip:
return read_swap_cache_async(entry, gfp_mask, vma, addr);
}
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2025-11-10 19:09:37 +0000