mm: add PSI accounting around ->read_folio and ->readahead calls

PSI tries to account for the cost of bringing back in pages discarded by
the MM LRU management.  Currently the prime place for that is hooked into
the bio submission path, which is a rather bad place:

 - it does not actually account I/O for non-block file systems, of which
   we have many
 - it adds overhead and a layering violation to the block layer

Add the accounting into the two places in the core MM code that read
pages into an address space by calling into ->read_folio and ->readahead
so that the entire file system operations are covered, to broaden
the coverage and allow removing the accounting in the block layer going
forward.

As psi_memstall_enter can deal with nested calls this will not lead to
double accounting even while the bio annotations are still present.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Link: https://lore.kernel.org/r/20220915094200.139713-2-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>

1 files changed, 18 insertions, 4 deletions

diff --git a/mm/readahead.c b/mm/readahead.c
index fdcd28cbd92d..b10f0cf81d80 100644
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -122,6 +122,7 @@
 #include <linux/task_io_accounting_ops.h>
 #include <linux/pagevec.h>
 #include <linux/pagemap.h>
+#include <linux/psi.h>
 #include <linux/syscalls.h>
 #include <linux/file.h>
 #include <linux/mm_inline.h>
@@ -152,6 +153,8 @@ static void read_pages(struct readahead_control *rac)
 	if (!readahead_count(rac))
 		return;
 
+	if (unlikely(rac->_workingset))
+		psi_memstall_enter(&rac->_pflags);
 	blk_start_plug(&plug);
 
 	if (aops->readahead) {
@@ -179,6 +182,9 @@ static void read_pages(struct readahead_control *rac)
 	}
 
 	blk_finish_plug(&plug);
+	if (unlikely(rac->_workingset))
+		psi_memstall_leave(&rac->_pflags);
+	rac->_workingset = false;
 
 	BUG_ON(readahead_count(rac));
 }
@@ -252,6 +258,7 @@ void page_cache_ra_unbounded(struct readahead_control *ractl,
 		}
 		if (i == nr_to_read - lookahead_size)
 			folio_set_readahead(folio);
+		ractl->_workingset |= folio_test_workingset(folio);
 		ractl->_nr_pages++;
 	}
 
@@ -480,11 +487,14 @@ static inline int ra_alloc_folio(struct readahead_control *ractl, pgoff_t index,
 	if (index == mark)
 		folio_set_readahead(folio);
 	err = filemap_add_folio(ractl->mapping, folio, index, gfp);
-	if (err)
+	if (err) {
 		folio_put(folio);
-	else
-		ractl->_nr_pages += 1UL << order;
-	return err;
+		return err;
+	}
+
+	ractl->_nr_pages += 1UL << order;
+	ractl->_workingset |= folio_test_workingset(folio);
+	return 0;
 }
 
 void page_cache_ra_order(struct readahead_control *ractl,
@@ -826,6 +836,10 @@ void readahead_expand(struct readahead_control *ractl,
 			put_page(page);
 			return;
 		}
+		if (unlikely(PageWorkingset(page)) && !ractl->_workingset) {
+			ractl->_workingset = true;
+			psi_memstall_enter(&ractl->_pflags);
+		}
 		ractl->_nr_pages++;
 		if (ra) {
 			ra->size++;