From: Dave Hansen <dave.hansen@xxxxxxxxxxxxxxx>
Prefaulting the write source buffer incurs an extra userspace access
in the common fast path. Make btrfs_buffered_write() 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@xxxxxxxxxxxxxxx>
Cc: Chris Mason <clm@xxxxxx>
Cc: Josef Bacik <josef@xxxxxxxxxxxxxx>
Cc: David Sterba <dsterba@xxxxxxxx>
Cc: linux-btrfs@xxxxxxxxxxxxxxx
---
b/fs/btrfs/file.c | 20 +++++++++++---------
1 file changed, 11 insertions(+), 9 deletions(-)
diff -puN fs/btrfs/file.c~btrfs-postfault fs/btrfs/file.c
--- a/fs/btrfs/file.c~btrfs-postfault 2025-01-29 09:03:36.927756510 -0800
+++ b/fs/btrfs/file.c 2025-01-29 09:03:36.935757176 -0800
@@ -1164,15 +1164,6 @@ ssize_t btrfs_buffered_write(struct kioc
int extents_locked;
bool force_page_uptodate = false;
- /*
- * Fault pages before locking them in prepare_one_folio()
- * to avoid recursive lock
- */
- if (unlikely(fault_in_iov_iter_readable(i, write_bytes))) {
- ret = -EFAULT;
- break;
- }
-
only_release_metadata = false;
sector_offset = pos & (fs_info->sectorsize - 1);
@@ -1314,6 +1305,17 @@ again:
cond_resched();
+ /*
+ * Fault pages in a slow path after dropping folio
+ * lock. This avoids the chance of deadlocking in
+ * the fault handler.
+ */
+ if (unlikely(copied == 0) &&
+ (fault_in_iov_iter_readable(i, write_bytes) == write_bytes)) {
+ ret = -EFAULT;
+ break;
+ }
+
pos += copied;
num_written += copied;
}
_
