[047/262] mm: don't read i_size of inode unless we need it

Commit Message

Andrew Morton Nov. 5, 2021, 8:37 p.m. UTC

From: Jens Axboe <[e-mail]>
Subject: mm: don't read i_size of inode unless we need it

We always go through i_size_read(), and we rarely end up needing it. Push
the read to down where we need to check it, which avoids it for most
cases.

It looks like we can even remove this check entirely, which might be
worth pursuing. But at least this takes it out of the hot path.

Link: https://lkml.kernel.org/r/[e-mail]
Signed-off-by: Jens Axboe <[e-mail]>
Acked-by: Chris Mason <[e-mail]>
Cc: Josef Bacik <[e-mail]>
Cc: Dave Chinner <[e-mail]>
Cc: Pavel Begunkov <[e-mail]>
Cc: Jan Kara <[e-mail]>
Signed-off-by: Andrew Morton <[e-mail]>
---

 mm/filemap.c |    7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

Patch

--- a/mm/filemap.c~mm-dont-read-i_size-of-inode-unless-we-need-it
+++ a/mm/filemap.c
@@ -2740,9 +2740,7 @@  generic_file_read_iter(struct kiocb *ioc
 		struct file *file = iocb->ki_filp;
 		struct address_space *mapping = file->f_mapping;
 		struct inode *inode = mapping->host;
-		loff_t size;
 
-		size = i_size_read(inode);
 		if (iocb->ki_flags & IOCB_NOWAIT) {
 			if (filemap_range_needs_writeback(mapping, iocb->ki_pos,
 						iocb->ki_pos + count - 1))
@@ -2774,8 +2772,9 @@  generic_file_read_iter(struct kiocb *ioc
 		 * the rest of the read.  Buffered reads will not work for
 		 * DAX files, so don't bother trying.
 		 */
-		if (retval < 0 || !count || iocb->ki_pos >= size ||
-		    IS_DAX(inode))
+		if (retval < 0 || !count || IS_DAX(inode))
+			return retval;
+		if (iocb->ki_pos >= i_size_read(inode))
 			return retval;
 	}