Hi Linus,
Please pull this first branch containing new code for iomap for
5.20. The most notable change in the first batch is that we no longer
schedule pages beyond i_size for writeback, preferring instead to let
truncate deal with those pages.
Next week, there may be a second pull request to remove iomap_writepage
from the other two filesystems (gfs2/zonefs) that use iomap for buffered
IO. This follows in the same vein as the recent removal of writepage
from XFS, since it hasn't been triggered in a few years; it does nothing
during direct reclaim; and as far as the people who examined the
patchset can tell, it's moving the codebase in the right direction.
However, as it was a late addition to for-next, I'm holding off on that
section for another week of testing to see if anyone can come up with a
solid reason for holding off in the meantime.
As usual, I did a test-merge with upstream master as of a few minutes
ago, and didn't see any conflicts. Please let me know if you encounter
any problems.
--D
The following changes since commit 03c765b0e3b4cb5063276b086c76f7a612856a9a:
Linux 5.19-rc4 (2022-06-26 14:22:10 -0700)
are available in the Git repository at:
git://git.kernel.org/pub/scm/fs/xfs/xfs-linux.git tags/iomap-5.20-merge-1
for you to fetch changes up to f8189d5d5fbf082786fb91c549f5127f23daec09:
dax: set did_zero to true when zeroing successfully (2022-06-30 10:05:11 -0700)
----------------------------------------------------------------
New code for 5.20:
- Skip writeback for pages that are completely beyond EOF
- Minor code cleanups
----------------------------------------------------------------
Chris Mason (1):
iomap: skip pages past eof in iomap_do_writepage()
Kaixu Xia (2):
iomap: set did_zero to true when zeroing successfully
dax: set did_zero to true when zeroing successfully
fs/dax.c | 4 ++--
fs/iomap/buffered-io.c | 15 ++++++++-------
2 files changed, 10 insertions(+), 9 deletions(-)
