[PATCH] mm/readahead: no PG_readahead on EOF

[Frederick Mayle]

When readahead pulls in all the remaining pages for a file, setting the
readahead bit is counter productive. The async readahead it would
trigger would almost certainly be a no-op. Additionally, for mmap'd file
IO, the readahead bit limits the fault around [0], causing an extra
minor fault when the page is accessed.

This was discovered when looking at /sys/kernel/tracing/events/readahead
traces for a simple program. With the patch applied, fewer
page_cache_ra_unbounded calls are observed.

[1] do_fault_around calls filemap_map_pages, which finds eligible pages
    by calling next_uptodate_folio [2]. next_uptodate_folio skips pages
    with PG_readahead set [3].

Link: https://github.com/torvalds/linux/blob/v7.0/mm/filemap.c#L3921-L3939 [2]
Link: https://github.com/torvalds/linux/blob/v7.0/mm/filemap.c#L3721-L3722 [3]
Cc: Kalesh Singh <kaleshsingh@xxxxxxxxxx>
Cc: Suren Baghdasaryan <surenb@xxxxxxxxxx>
Signed-off-by: Frederick Mayle <fmayle@xxxxxxxxxx>
---
 mm/readahead.c | 15 ++++++++++++---
 1 file changed, 12 insertions(+), 3 deletions(-)

diff --git a/mm/readahead.c b/mm/readahead.c
index 8c12b63ccd4a..784a3bde82be 100644
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -329,8 +329,11 @@ static void do_page_cache_ra(struct readahead_control *ractl,
 	if (index > end_index)
 		return;
 	/* Don't read past the page containing the last byte of the file */
-	if (nr_to_read > end_index - index)
+	if (nr_to_read > end_index - index) {
 		nr_to_read = end_index - index + 1;
+		/* We've reached the end, so don't set a readahead marker. */
+		lookahead_size = 0;
+	}
 
 	filemap_invalidate_lock_shared(mapping);
 	page_cache_ra_unbounded(ractl, nr_to_read, lookahead_size);
@@ -474,7 +477,7 @@ void page_cache_ra_order(struct readahead_control *ractl,
 	pgoff_t index = start;
 	unsigned int min_order = mapping_min_folio_order(mapping);
 	pgoff_t limit;
-	pgoff_t mark = index + ra->size - ra->async_size;
+	pgoff_t mark;
 	unsigned int nofs;
 	int err = 0;
 	gfp_t gfp = readahead_gfp_mask(mapping);
@@ -488,7 +491,13 @@ void page_cache_ra_order(struct readahead_control *ractl,
 
 	limit = (i_size_read(mapping->host) - 1) >> PAGE_SHIFT;
 	limit = min(limit, ractl->_max_index);
-	limit = min(limit, index + ra->size - 1);
+	if (limit > index + ra->size - 1) {
+		limit = index + ra->size - 1;
+		mark = index + ra->size - ra->async_size;
+	} else {
+		/* We've reached the end, so don't set a readahead marker. */
+		mark = ULONG_MAX;
+	}
 
 	new_order = min(mapping_max_folio_order(mapping), new_order);
 	new_order = min_t(unsigned int, new_order, ilog2(ra->size));

base-commit: 2d565cbaafd43b10b75da56e43e5db9852a56afd
-- 
2.54.0.563.g4f69b47b94-goog