[PATCH 1/3] mm/readahead: fix the broken readahead for POSIX_FADV_WILLNEED

[Jaegeuk Kim <jaegeuk@kernel.org>]

This patch fixes the broken readahead flow for POSIX_FADV_WILLNEED, where
the problem is, in force_page_cache_ra(nr_to_read), nr_to_read is cut by
the below code.

     max_pages = max_t(unsigned long, bdi->io_pages, ra->ra_pages);
     nr_to_read = min_t(unsigned long, nr_to_read, max_pages);

IOWs, we are not able to read ahead larger than the above max_pages which
is most likely the range of 2MB and 16MB. Note, it doesn't make sense
to set ra->ra_pages to the entire file size. Instead, let's fix this logic.

Before:
f2fs_fadvise: dev = (252,16), ino = 14, i_size = 4294967296 offset:0, len:4294967296, advise:3
page_cache_ra_unbounded: dev=252:16 ino=e index=0 nr_to_read=512 lookahead_size=0
page_cache_ra_unbounded: dev=252:16 ino=e index=512 nr_to_read=512 lookahead_size=0
page_cache_ra_unbounded: dev=252:16 ino=e index=1024 nr_to_read=512 lookahead_size=0
page_cache_ra_unbounded: dev=252:16 ino=e index=1536 nr_to_read=512 lookahead_size=0

After:
f2fs_fadvise: dev = (252,16), ino = 14, i_size = 4294967296 offset:0, len:4294967296, advise:3
page_cache_ra_unbounded: dev=252:16 ino=e index=0 nr_to_read=2048 lookahead_size=0
page_cache_ra_unbounded: dev=252:16 ino=e index=2048 nr_to_read=2048 lookahead_size=0
page_cache_ra_unbounded: dev=252:16 ino=e index=4096 nr_to_read=2048 lookahead_size=0
page_cache_ra_unbounded: dev=252:16 ino=e index=6144 nr_to_read=2048 lookahead_size=0
page_cache_ra_unbounded: dev=252:16 ino=e index=8192 nr_to_read=2048 lookahead_size=0
page_cache_ra_unbounded: dev=252:16 ino=e index=10240 nr_to_read=2048 lookahead_size=0
page_cache_ra_unbounded: dev=252:16 ino=e index=12288 nr_to_read=2048 lookahead_size=0
page_cache_ra_unbounded: dev=252:16 ino=e index=14336 nr_to_read=2048 lookahead_size=0
page_cache_ra_unbounded: dev=252:16 ino=e index=16384 nr_to_read=2048 lookahead_size=0
page_cache_ra_unbounded: dev=252:16 ino=e index=18432 nr_to_read=2048 lookahead_size=0
page_cache_ra_unbounded: dev=252:16 ino=e index=20480 nr_to_read=2048 lookahead_size=0
page_cache_ra_unbounded: dev=252:16 ino=e index=22528 nr_to_read=2048 lookahead_size=0
page_cache_ra_unbounded: dev=252:16 ino=e index=24576 nr_to_read=2048 lookahead_size=0
...
page_cache_ra_unbounded: dev=252:16 ino=e index=1042432 nr_to_read=2048 lookahead_size=0
page_cache_ra_unbounded: dev=252:16 ino=e index=1044480 nr_to_read=2048 lookahead_size=0
page_cache_ra_unbounded: dev=252:16 ino=e index=1046528 nr_to_read=2048 lookahead_size=0

Cc: linux-mm@kvack.org
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 mm/readahead.c | 27 ++++++++++++---------------
 1 file changed, 12 insertions(+), 15 deletions(-)

diff --git a/mm/readahead.c b/mm/readahead.c
index 3a4b5d58eeb6..e88425ce06f7 100644
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -311,7 +311,7 @@ EXPORT_SYMBOL_GPL(page_cache_ra_unbounded);
  * behaviour which would occur if page allocations are causing VM writeback.
  * We really don't want to intermingle reads and writes like that.
  */
-static void do_page_cache_ra(struct readahead_control *ractl,
+static int do_page_cache_ra(struct readahead_control *ractl,
 		unsigned long nr_to_read, unsigned long lookahead_size)
 {
 	struct inode *inode = ractl->mapping->host;
@@ -320,45 +320,42 @@ static void do_page_cache_ra(struct readahead_control *ractl,
 	pgoff_t end_index;	/* The last page we want to read */
 
 	if (isize == 0)
-		return;
+		return -EINVAL;
 
 	end_index = (isize - 1) >> PAGE_SHIFT;
 	if (index > end_index)
-		return;
+		return -EINVAL;
 	/* Don't read past the page containing the last byte of the file */
 	if (nr_to_read > end_index - index)
 		nr_to_read = end_index - index + 1;
 
 	page_cache_ra_unbounded(ractl, nr_to_read, lookahead_size);
+	return 0;
 }
 
 /*
- * Chunk the readahead into 2 megabyte units, so that we don't pin too much
- * memory at once.
+ * Chunk the readahead per the block device capacity, and read all nr_to_read.
  */
 void force_page_cache_ra(struct readahead_control *ractl,
 		unsigned long nr_to_read)
 {
 	struct address_space *mapping = ractl->mapping;
-	struct file_ra_state *ra = ractl->ra;
 	struct backing_dev_info *bdi = inode_to_bdi(mapping->host);
-	unsigned long max_pages;
+	unsigned long this_chunk;
 
 	if (unlikely(!mapping->a_ops->read_folio && !mapping->a_ops->readahead))
 		return;
 
 	/*
-	 * If the request exceeds the readahead window, allow the read to
-	 * be up to the optimal hardware IO size
+	 * Consider the optimal hardware IO size for readahead chunk.
 	 */
-	max_pages = max_t(unsigned long, bdi->io_pages, ra->ra_pages);
-	nr_to_read = min_t(unsigned long, nr_to_read, max_pages);
+	this_chunk = max_t(unsigned long, bdi->io_pages, ractl->ra->ra_pages);
+
 	while (nr_to_read) {
-		unsigned long this_chunk = (2 * 1024 * 1024) / PAGE_SIZE;
+		this_chunk = min_t(unsigned long, this_chunk, nr_to_read);
 
-		if (this_chunk > nr_to_read)
-			this_chunk = nr_to_read;
-		do_page_cache_ra(ractl, this_chunk, 0);
+		if (do_page_cache_ra(ractl, this_chunk, 0))
+			break;
 
 		nr_to_read -= this_chunk;
 	}
-- 
2.52.0.107.ga0afd4fd5b-goog