Commit c1f6925e authored by Matthew Wilcox (Oracle)'s avatar Matthew Wilcox (Oracle) Committed by Linus Torvalds

mm: put readahead pages in cache earlier

When populating the page cache for readahead, mappings that use
->readpages must populate the page cache themselves as the pages are
passed on a linked list which would normally be used for the page
cache's LRU.  For mappings that use ->readpage or the upcoming
->readahead method, we can put the pages into the page cache as soon as
they're allocated, which solves a race between readahead and direct IO.
It also lets us remove the gfp argument from read_pages().

Use the new readahead_page() API to implement the repeated calls to
->readpage(), just like most filesystems will.
Signed-off-by: default avatarMatthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: default avatarAndrew Morton <akpm@linux-foundation.org>
Reviewed-by: default avatarChristoph Hellwig <hch@lst.de>
Reviewed-by: default avatarWilliam Kucharski <william.kucharski@oracle.com>
Cc: Chao Yu <yuchao0@huawei.com>
Cc: Cong Wang <xiyou.wangcong@gmail.com>
Cc: Darrick J. Wong <darrick.wong@oracle.com>
Cc: Dave Chinner <dchinner@redhat.com>
Cc: Eric Biggers <ebiggers@google.com>
Cc: Gao Xiang <gaoxiang25@huawei.com>
Cc: Jaegeuk Kim <jaegeuk@kernel.org>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: Joseph Qi <joseph.qi@linux.alibaba.com>
Cc: Junxiao Bi <junxiao.bi@oracle.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Zi Yan <ziy@nvidia.com>
Cc: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Cc: Miklos Szeredi <mszeredi@redhat.com>
Link: http://lkml.kernel.org/r/20200414150233.24495-11-willy@infradead.orgSigned-off-by: default avatarLinus Torvalds <torvalds@linux-foundation.org>
parent ef8153b6
...@@ -114,14 +114,14 @@ int read_cache_pages(struct address_space *mapping, struct list_head *pages, ...@@ -114,14 +114,14 @@ int read_cache_pages(struct address_space *mapping, struct list_head *pages,
EXPORT_SYMBOL(read_cache_pages); EXPORT_SYMBOL(read_cache_pages);
static void read_pages(struct readahead_control *rac, struct list_head *pages, static void read_pages(struct readahead_control *rac, struct list_head *pages,
gfp_t gfp) bool skip_page)
{ {
const struct address_space_operations *aops = rac->mapping->a_ops; const struct address_space_operations *aops = rac->mapping->a_ops;
struct page *page;
struct blk_plug plug; struct blk_plug plug;
unsigned page_idx;
if (!readahead_count(rac)) if (!readahead_count(rac))
return; goto out;
blk_start_plug(&plug); blk_start_plug(&plug);
...@@ -130,23 +130,23 @@ static void read_pages(struct readahead_control *rac, struct list_head *pages, ...@@ -130,23 +130,23 @@ static void read_pages(struct readahead_control *rac, struct list_head *pages,
readahead_count(rac)); readahead_count(rac));
/* Clean up the remaining pages */ /* Clean up the remaining pages */
put_pages_list(pages); put_pages_list(pages);
goto out; rac->_index += rac->_nr_pages;
} rac->_nr_pages = 0;
} else {
for (page_idx = 0; page_idx < readahead_count(rac); page_idx++) { while ((page = readahead_page(rac))) {
struct page *page = lru_to_page(pages);
list_del(&page->lru);
if (!add_to_page_cache_lru(page, rac->mapping, page->index,
gfp))
aops->readpage(rac->file, page); aops->readpage(rac->file, page);
put_page(page); put_page(page);
} }
}
out:
blk_finish_plug(&plug); blk_finish_plug(&plug);
BUG_ON(!list_empty(pages)); BUG_ON(!list_empty(pages));
rac->_nr_pages = 0; BUG_ON(readahead_count(rac));
out:
if (skip_page)
rac->_index++;
} }
/* /*
...@@ -168,6 +168,7 @@ void __do_page_cache_readahead(struct address_space *mapping, ...@@ -168,6 +168,7 @@ void __do_page_cache_readahead(struct address_space *mapping,
struct readahead_control rac = { struct readahead_control rac = {
.mapping = mapping, .mapping = mapping,
.file = filp, .file = filp,
._index = index,
}; };
unsigned long i; unsigned long i;
...@@ -183,6 +184,8 @@ void __do_page_cache_readahead(struct address_space *mapping, ...@@ -183,6 +184,8 @@ void __do_page_cache_readahead(struct address_space *mapping,
if (index + i > end_index) if (index + i > end_index)
break; break;
BUG_ON(index + i != rac._index + rac._nr_pages);
page = xa_load(&mapping->i_pages, index + i); page = xa_load(&mapping->i_pages, index + i);
if (page && !xa_is_value(page)) { if (page && !xa_is_value(page)) {
/* /*
...@@ -190,15 +193,22 @@ void __do_page_cache_readahead(struct address_space *mapping, ...@@ -190,15 +193,22 @@ void __do_page_cache_readahead(struct address_space *mapping,
* contiguous pages before continuing with the next * contiguous pages before continuing with the next
* batch. * batch.
*/ */
read_pages(&rac, &page_pool, gfp_mask); read_pages(&rac, &page_pool, true);
continue; continue;
} }
page = __page_cache_alloc(gfp_mask); page = __page_cache_alloc(gfp_mask);
if (!page) if (!page)
break; break;
if (mapping->a_ops->readpages) {
page->index = index + i; page->index = index + i;
list_add(&page->lru, &page_pool); list_add(&page->lru, &page_pool);
} else if (add_to_page_cache_lru(page, mapping, index + i,
gfp_mask) < 0) {
put_page(page);
read_pages(&rac, &page_pool, true);
continue;
}
if (i == nr_to_read - lookahead_size) if (i == nr_to_read - lookahead_size)
SetPageReadahead(page); SetPageReadahead(page);
rac._nr_pages++; rac._nr_pages++;
...@@ -209,7 +219,7 @@ void __do_page_cache_readahead(struct address_space *mapping, ...@@ -209,7 +219,7 @@ void __do_page_cache_readahead(struct address_space *mapping,
* uptodate then the caller will launch readpage again, and * uptodate then the caller will launch readpage again, and
* will then handle the error. * will then handle the error.
*/ */
read_pages(&rac, &page_pool, gfp_mask); read_pages(&rac, &page_pool, false);
} }
/* /*
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment