From: "Matthew Wilcox (Oracle)" <willy@xxxxxxxxxxxxx>
At allocation time, put the pages in the cache unless we're using
->readpages.
Signed-off-by: Matthew Wilcox (Oracle) <willy@xxxxxxxxxxxxx>
Cc: linux-btrfs@xxxxxxxxxxxxxxx
Cc: linux-erofs@xxxxxxxxxxxxxxxx
Cc: linux-ext4@xxxxxxxxxxxxxxx
Cc: linux-f2fs-devel@xxxxxxxxxxxxxxxxxxxxx
Cc: linux-xfs@xxxxxxxxxxxxxxx
Cc: cluster-devel@xxxxxxxxxx
Cc: ocfs2-devel@xxxxxxxxxxxxxx
---
mm/readahead.c | 64 ++++++++++++++++++++++++++++++++++----------------
1 file changed, 44 insertions(+), 20 deletions(-)
diff --git a/mm/readahead.c b/mm/readahead.c
index fc77d13af556..7daef0038b14 100644
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -114,10 +114,10 @@ int read_cache_pages(struct address_space *mapping, struct list_head *pages,
EXPORT_SYMBOL(read_cache_pages);
static void read_pages(struct address_space *mapping, struct file *filp,
- struct list_head *pages, unsigned int nr_pages, gfp_t gfp)
+ struct list_head *pages, pgoff_t start,
+ unsigned int nr_pages)
{
struct blk_plug plug;
- unsigned page_idx;
blk_start_plug(&plug);
@@ -125,18 +125,17 @@ static void read_pages(struct address_space *mapping, struct file *filp,
mapping->a_ops->readpages(filp, mapping, pages, nr_pages);
/* Clean up the remaining pages */
put_pages_list(pages);
- goto out;
- }
+ } else {
+ struct page *page;
+ unsigned long index;
- for (page_idx = 0; page_idx < nr_pages; page_idx++) {
- struct page *page = lru_to_page(pages);
- list_del(&page->lru);
- if (!add_to_page_cache_lru(page, mapping, page->index, gfp))
+ xa_for_each_range(&mapping->i_pages, index, page, start,
+ start + nr_pages - 1) {
mapping->a_ops->readpage(filp, page);
- put_page(page);
+ put_page(page);
+ }
}
-out:
blk_finish_plug(&plug);
}
@@ -153,13 +152,14 @@ unsigned long __do_page_cache_readahead(struct address_space *mapping,
unsigned long lookahead_size)
{
struct inode *inode = mapping->host;
- struct page *page;
unsigned long end_index; /* The last page we want to read */
LIST_HEAD(page_pool);
int page_idx;
+ pgoff_t page_offset;
unsigned long nr_pages = 0;
loff_t isize = i_size_read(inode);
gfp_t gfp_mask = readahead_gfp_mask(mapping);
+ bool use_list = mapping->a_ops->readpages;
if (isize == 0)
goto out;
@@ -170,21 +170,32 @@ unsigned long __do_page_cache_readahead(struct address_space *mapping,
* Preallocate as many pages as we will need.
*/
for (page_idx = 0; page_idx < nr_to_read; page_idx++) {
- pgoff_t page_offset = offset + page_idx;
+ struct page *page;
+ page_offset = offset + page_idx;
if (page_offset > end_index)
break;
page = xa_load(&mapping->i_pages, page_offset);
if (page && !xa_is_value(page)) {
/*
- * Page already present? Kick off the current batch of
- * contiguous pages before continuing with the next
- * batch.
+ * Page already present? Kick off the current batch
+ * of contiguous pages before continuing with the
+ * next batch.
*/
if (nr_pages)
- read_pages(mapping, filp, &page_pool, nr_pages,
- gfp_mask);
+ read_pages(mapping, filp, &page_pool,
+ page_offset - nr_pages,
+ nr_pages);
+ /*
+ * It's possible this page is the page we should
+ * be marking with PageReadahead. However, we
+ * don't have a stable ref to this page so it might
+ * be reallocated to another user before we can set
+ * the bit. There's probably another page in the
+ * cache marked with PageReadahead from the other
+ * process which accessed this file.
+ */
nr_pages = 0;
continue;
}
@@ -192,8 +203,20 @@ unsigned long __do_page_cache_readahead(struct address_space *mapping,
page = __page_cache_alloc(gfp_mask);
if (!page)
break;
- page->index = page_offset;
- list_add(&page->lru, &page_pool);
+ if (use_list) {
+ page->index = page_offset;
+ list_add(&page->lru, &page_pool);
+ } else if (add_to_page_cache_lru(page, mapping, page_offset,
+ gfp_mask) < 0) {
+ if (nr_pages)
+ read_pages(mapping, filp, &page_pool,
+ page_offset - nr_pages,
+ nr_pages);
+ put_page(page);
+ nr_pages = 0;
+ continue;
+ }
+
if (page_idx == nr_to_read - lookahead_size)
SetPageReadahead(page);
nr_pages++;
@@ -205,7 +228,8 @@ unsigned long __do_page_cache_readahead(struct address_space *mapping,
* will then handle the error.
*/
if (nr_pages)
- read_pages(mapping, filp, &page_pool, nr_pages, gfp_mask);
+ read_pages(mapping, filp, &page_pool, page_offset - nr_pages,
+ nr_pages);
BUG_ON(!list_empty(&page_pool));
out:
return nr_pages;
--
2.24.1
