diff mbox series

[4/7] fuse: Move prefaulting out of hot write path

Message ID 20250129181756.44C9597C@davehans-spike.ostc.intel.com (mailing list archive)
State New
Headers show
Series Move prefaulting into write slow paths | expand

Commit Message

Dave Hansen Jan. 29, 2025, 6:17 p.m. UTC 
From: Dave Hansen <dave.hansen@linux.intel.com>

Prefaulting the write source buffer incurs an extra userspace access
in the common fast path. Make fuse_fill_write_pages() consistent with
generic_perform_write(): only touch userspace an extra time when
copy_folio_from_iter_atomic() has failed to make progress.

Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Miklos Szeredi <miklos@szeredi.hu>
---

 b/fs/fuse/file.c |   14 ++++++++++----
 1 file changed, 10 insertions(+), 4 deletions(-)
diff mbox series

Patch

diff -puN fs/fuse/file.c~fuse-postfault fs/fuse/file.c
--- a/fs/fuse/file.c~fuse-postfault	2025-01-29 09:03:34.515555724 -0800
+++ b/fs/fuse/file.c	2025-01-29 09:03:34.523556390 -0800
@@ -1234,10 +1234,6 @@  static ssize_t fuse_fill_write_pages(str
 		bytes = min_t(size_t, bytes, fc->max_write - count);
 
  again:
-		err = -EFAULT;
-		if (fault_in_iov_iter_readable(ii, bytes))
-			break;
-
 		folio = __filemap_get_folio(mapping, index, FGP_WRITEBEGIN,
 					    mapping_gfp_mask(mapping));
 		if (IS_ERR(folio)) {
@@ -1254,6 +1250,16 @@  static ssize_t fuse_fill_write_pages(str
 		if (!tmp) {
 			folio_unlock(folio);
 			folio_put(folio);
+
+			/*
+			 * Ensure forward progress by faulting in
+			 * while not holding the folio lock:
+			 */
+			if (fault_in_iov_iter_readable(ii, bytes)) {
+				err = -EFAULT;
+				break;
+			}
+
 			goto again;
 		}