Skip to content

ext4: allow more DIO writes under shared i_rwsem

Baokun Li linux-ext4 4 versions – Applied

Status from this message: Applied, thanks!

Get series with b4
b4 am [email protected]

Versions newest first · linked by author and title

  1. v4 Latest6 patches 2 repliesApplied
  2. v39 patches 2 repliesSuperseded
  3. v28 patches 12 repliesSuperseded
Earlier versions · 1
VersionPostedPatchesRepliesStatus
v12 patches11 repliesSuperseded

Changes in v4 from the cover letter

* Collect RVB from Honza. (Thank you for your review!)
* Dropped Patches 6-8 (EXT4_GET_BLOCKS_CACHED_NOWAIT handling, cache-only lookup in ext4_iomap_begin, and cache-only lookup in ext4_dio_needs_zeroing). The NOWAIT support in ext4_map_blocks() and the i_size anomaly reported by Sashiko are pre-existing issues, not introduced by the lock relaxation in this series. They will be addressed in a separate patchset.
* Patches 1-5 and 9 from v3 are unchanged (renumbered to 1-6).

Patches in v4 Applied

#Subject and filesSizeRepliesApplied
1/6ext4: prevent sleeping allocation in NOWAIT write pathfs/ext4/inode.c+3 -00 replies
2/6ext4: drain in-flight DIO before buffered write fallbackfs/ext4/file.c+7 -00 replies
3/6ext4: skip overwrite check for aligned non-extending DIO writesfs/ext4/file.c+30 -220 replies
4/6ext4: base unaligned DIO lock decision on partial block zeroingfs/ext4/file.c+73 -350 replies
5/6ext4: use kiocb_modified instead of file_modified in DIO/DAX write pathfs/ext4/file.c+3 -30 replies
6/6ext4: fix NOWAIT semantic violation in DAX extending writesfs/ext4/file.c+5 -01 reply

Reviews trailers per patch

All 6 patches have a Reviewed-by or Acked-by.

PatchZhang YiJan Kara
1/6R-b R-b
2/6R-b R-b
3/6R-b R-b
4/6R-b R-b
5/6R-b R-b
6/6R-b R-b

Trailers given in replies are filled; those carried in the patches from earlier versions are outlined with dashes.

Read the v4 thread

Cover letter [PATCH v4 0/6] ext4: allow more DIO writes under shared i_rwsem

Changes since v3:
* Collect RVB from Honza. (Thank you for your review!)
* Dropped Patches 6-8 (EXT4_GET_BLOCKS_CACHED_NOWAIT handling, cache-only lookup in ext4_iomap_begin, and cache-only lookup in ext4_dio_needs_zeroing). The NOWAIT support in ext4_map_blocks() and the i_size anomaly reported by Sashiko are pre-existing issues, not introduced by the lock relaxation in this series. They will be addressed in a separate patchset.
* Patches 1-5 and 9 from v3 are unchanged (renumbered to 1-6).

Changes since v2:
* Collect RVB from Honza and Yi. (Thank you for your review!)
* Patch 6: improved EXT4_GET_BLOCKS_CACHED_NOWAIT handling - cache-hit path now uses "goto found" to run check_block_validity(), closing a security bypass for malicious extents from crafted filesystem images.
* Added Patch 9 to fix NOWAIT semantic violation in DAX extending writes reported by Sashiko.

Changes since v1:
* Collect RVB from Honza and Yi. (Thank you for your review!)
* Added Patch 1 to fix NOWAIT issues reported by Sashiko.
* Added Patch 2 to fix ext3 DIO and DIO fallback data race issue. (Patch 4 increases the probability of this race)
* Added Patches 5-8 to fix other NOWAIT issues discovered during investigation.

v1: https://lore.kernel.org/linux-ext4/[email protected]/
v2: https://lore.kernel.org/linux-ext4/[email protected]/
v3: https://lore.kernel.org/linux-ext4/[email protected]/

======

Hi all,

This series relaxes the i_rwsem requirements of ext4_dio_write_iter() so that more direct I/O writes can proceed under the shared lock.

It continues the work started by Peng Wang's RFC [1]; I'm taking over this effort going forward.

ext4_dio_write_checks() currently calls ext4_overwrite_io() to decide whether the shared lock is sufficient. Its single ext4_map_blocks() lookup only sees the first contiguous extent of the same type, which forces the exclusive lock for two cases that are actually safe under the shared lock (see individual patches for the full safety argument):

1. Aligned writes spanning multiple already-allocated extents (e.g. written + unwritten, or two discontiguous written extents).

2. Unaligned writes whose head/tail partial blocks land on written extents but the fully-covered middle blocks include hole or unwritten extents.

Patch 1 fixes a NOWAIT issue where ext4_iomap_alloc() may sleep when IOMAP_NOWAIT is set.

Patch 2 fixes a data race between DIO completion and buffered I/O fallback on ext3 (no-extent inodes). This race was made more likely by Patch 4.

Patch 3 skips the ext4_overwrite_io() pre-check entirely for aligned non-extending writes, letting them proceed under the shared lock regardless of extent state.

Patch 4 replaces ext4_overwrite_io() with ext4_dio_needs_zeroing(), which directly answers the question driving the lock decision. It checks only the head and tail partial blocks (at most two ext4_map_blocks() calls), and ignores the state of middle blocks.

Patch 5 fixes a NOWAIT issue by using kiocb_modified instead of file_modified in DIO/DAX write paths.

Patch 6 fixes a NOWAIT semantic violation in DAX extending writes where ext4_journal_start() could sleep when the write extends past i_disksize.

Testing
=======

"kvm-xfstests -c ext4/all -g auto" passes with no new failures.

Performance
===========

Hardware: /dev/sda (rotational disk, ~1 GB/s sustained write)
Filesystem: ext4 default mkfs

Test 1: aligned 8K DIO writes spanning written+unwritten extent boundaries. Each thread writes its own 1G region sequentially; the file is rebuilt between runs so every block is written exactly once.
Metric: IOPS.

  JOBS         base    +patch 3    +patch 3+4    speedup
  ----    ---------    --------    ----------    -------
     1       42,322      43,329        43,087      1.02x
     2       68,516      70,677        66,958      1.03x
     4       62,489      97,072       101,468      1.62x
     8       58,701     110,819       113,679      1.94x
    16       58,569     116,392       115,272      1.97x
    32       60,860     117,244       119,621      1.97x

Wall time at JOBS=32: 69.2s (base) -> 35.4s (patched), 1.96x faster.

Test 2: unaligned DIO writes (14336 bytes at +512 within each 16K stripe). Each stripe is laid out as [written][unwritten][unwritten] [written], so the head and tail partial blocks land on written extents but the middle is unwritten. Metric: IOPS.

  JOBS         base    +patch 3    +patch 3+4    speedup
  ----    ---------    --------    ----------    -------
     1       15,547      15,975        17,381      1.12x
     2       15,910      14,808        34,172      2.15x
     4       15,014      14,828        57,567      3.83x
     8       15,022      14,648        81,947      5.46x
    16       14,586      14,262        99,126      6.80x
    32       14,047      13,809        92,519      6.59x

Wall time at JOBS=32: 149.3s (base) -> 22.7s (patched), 6.58x faster.

In test 2, patch 3 alone has no effect (slight noise) because patch 3 only touches the aligned write path. Patch 4 introduces ext4_dio_needs_zeroing() which precisely identifies when partial block zeroing is required, allowing the shared lock for the much larger set of unaligned writes that don't actually trigger zeroing.

Comments and questions are, as always, welcome.

Thanks,
Baokun

[1]: https://lore.kernel.org/linux-ext4/[email protected]/

Baokun Li (6):
ext4: prevent sleeping allocation in NOWAIT write path
ext4: drain in-flight DIO before buffered write fallback
ext4: skip overwrite check for aligned non-extending DIO writes
ext4: base unaligned DIO lock decision on partial block zeroing
ext4: use kiocb_modified instead of file_modified in DIO/DAX write
path
ext4: fix NOWAIT semantic violation in DAX extending writes

 fs/ext4/file.c  | 148 +++++++++++++++++++++++++++++++++---------------
 fs/ext4/inode.c |   3 +
 2 files changed, 106 insertions(+), 45 deletions(-)

--
2.43.7