[RFC PATCH v2 17/18] mm/shmem: read without folio references

[Kiryl Shutsemau (Meta)]

shmem_file_read_iter() takes a reference on every folio it reads, so
small reads of one tmpfs file from many CPUs bounce the folio's
refcount.

Copy with filemap_read_rcu() first, and continue with the existing loop
where it stops.  Holes, swap entries and fallocated folios that are not
uptodate all end the copy.  So does a hwpoisoned page, which shmem keeps
in the page cache and reports with -EIO.

This drops the folio lock as well as the reference.  shmem_get_folio()
held it only for the lookup, and the copy ran after folio_unlock(), so a
read was never atomic against a write or a hole punch.  Now a read also
does not wait for one that holds the lock, as filemap_read() does not.

shmem does no readahead, and on its folios the PG_readahead bit is
PG_reclaim, which drop_caches can leave set on dirty tmpfs folios.  Do
not let it end the copy there.

Signed-off-by: Kiryl Shutsemau (Meta) <kas@xxxxxxxxxx>
---
 mm/filemap.c  |  7 ++++---
 mm/internal.h |  2 ++
 mm/shmem.c    | 11 +++++++++--
 3 files changed, 15 insertions(+), 5 deletions(-)

diff --git a/mm/filemap.c b/mm/filemap.c
index 65d414ad9d85..e148490db4da 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -2831,9 +2831,10 @@ static void filemap_end_dropbehind_read(struct folio *folio)
 static bool filemap_read_rcu_can_copy(struct folio *folio, pgoff_t index,
 				      pgoff_t last_index)
 {
-	if (!folio_test_uptodate(folio))
+	if (!folio_test_uptodate(folio) || folio_test_dropbehind(folio))
 		return false;
-	if (folio_test_readahead(folio) || folio_test_dropbehind(folio))
+	/* shmem does no readahead: there the bit is PG_reclaim */
+	if (folio_test_readahead(folio) && !folio_test_swapbacked(folio))
 		return false;
 	/* A split clears PG_head before it puts the new folios in their slots */
 	if (!folio_test_large(folio) && folio->index != index)
@@ -3020,7 +3021,7 @@ static bool filemap_read_rcu_batch(struct kiocb *iocb, struct iov_iter *iter,
  * Copy from the page cache without folio references, in batches, and
  * return how much was copied.  The slow path reads the rest.
  */
-static size_t filemap_read_rcu(struct kiocb *iocb, struct iov_iter *iter,
+size_t filemap_read_rcu(struct kiocb *iocb, struct iov_iter *iter,
 		loff_t last_pos)
 {
 	/* The page the previous read ended in; ULONG_MAX if none */
diff --git a/mm/internal.h b/mm/internal.h
index 18391dc50418..ae9a4e511c82 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -1249,6 +1249,8 @@ struct migration_target_control {
 size_t splice_folio_into_pipe(struct pipe_inode_info *pipe,
 			      struct folio *folio, loff_t fpos, size_t size);
 void filemap_read_accessed(struct folio *folio, loff_t pos, loff_t last_pos);
+size_t filemap_read_rcu(struct kiocb *iocb, struct iov_iter *iter,
+			loff_t last_pos);
 
 static inline bool vma_is_single_threaded_private(struct vm_area_struct *vma)
 {
diff --git a/mm/shmem.c b/mm/shmem.c
index 1c700fa9666d..8700b03a8a5e 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -3313,7 +3313,14 @@ static ssize_t shmem_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
 	pgoff_t index;
 	unsigned long offset;
 	int error = 0;
-	ssize_t retval = 0;
+	ssize_t retval;
+
+	retval = filemap_read_rcu(iocb, to, last_pos);
+	if (retval) {
+		last_pos = iocb->ki_pos;
+		if (!iov_iter_count(to))
+			goto out;
+	}
 
 	for (;;) {
 		struct folio *folio = NULL;
@@ -3417,7 +3424,7 @@ static ssize_t shmem_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
 		}
 		cond_resched();
 	}
-
+out:
 	file_accessed(file);
 	file->f_ra.prev_pos = last_pos;
 	return retval ? retval : error;
-- 
2.54.0