[PATCH v2 0/5] mm: batch TLB flushing for dirty folios in vmscan

Zhang Peng posted 5 patches 1 week ago
Only 1 patches received!
There is a newer version of this series
include/linux/vmstat.h |   1 +
mm/vmscan.c            | 456 +++++++++++++++++++++++++++++++------------------
2 files changed, 287 insertions(+), 170 deletions(-)
[PATCH v2 0/5] mm: batch TLB flushing for dirty folios in vmscan
Posted by Zhang Peng 1 week ago
This series introduces batch TLB flushing optimization for dirty folios
during memory reclaim, aiming to reduce IPI overhead on multi-core systems.

Background
----------
Currently, when performing pageout in memory reclaim, try_to_unmap_flush_dirty()
is called for each dirty folio individually. On multi-core systems, this causes
frequent IPIs which can significantly impact performance.

Approach
--------
This patch series accumulates dirty folios into batches and performs a single
TLB flush for the entire batch, rather than flushing for each individual folio.

Changes
-------
Patch 1: Add nr_reclaimed to reclaim_stat so shrink_folio_list() can be changed
         to void, giving a consistent interface where all per-pass statistics
         are reported through reclaim_stat.
Patch 2: Extract the folio activation block at activate_locked into
         folio_active_bounce().
Patch 3: Extract the pageout() dispatch state machine and the folio-freeing path
         into pageout_one() and folio_free() respectively.
Patch 4: Extract the TTU setup and try_to_unmap() block into folio_try_unmap().
Patch 5: Implement batch TLB flushing logic. Dirty folios are accumulated in
         batches and a single TLB flush is performed for each batch before
         calling pageout.

Testing
-------
The benchmark script uses stress-ng to compare TLB shootdown behavior before and
after this patch. It constrains a stress-ng workload via memcg to force reclaim
through shrink_folio_list(), reporting TLB shootdowns and IPIs.

Core benchmark command: stress-ng --vm 16 --vm-bytes 2G --vm-keep --timeout 60

==========================================================================
                 batch_dirty_tlb_flush Benchmark Results
==========================================================================
  Kernel: 7.0.0-rc1+   CPUs: 16
  MemTotal: 31834M   SwapTotal: 8191M
  memcg limit: 512M   alloc: 2G   workers: 16   duration: 60s
--------------------------------------------------------------------------
Metric                 Before        After             Delta (abs / %)
--------------------------------------------------------------------------
bogo ops/s             28238.63      35833.97          +7595.34 (+26.9%)
TLB shootdowns         55428953      17621697          -37807256 (-68.2%)
Function call IPIs     34073695      14498768          -19574927 (-57.4%)
pgscan_anon (pages)    52856224      60252894          7396670 (+14.0%)
pgsteal_anon (pages)   29004962      34054753          5049791 (+17.4%)
--------------------------------------------------------------------------

Suggested-by: Kairui Song <kasong@tencent.com>
Signed-off-by: Zhang Peng <bruzzhang@tencent.com>
---
Changes in v2:
- Fix incorrect comment about page_ref_freeze
- Add folio_maybe_dma_pinned() check in pageout_batch()
- Link to v1: https://lore.kernel.org/r/20260309-batch-tlb-flush-v1-0-eb8fed7d1a9e@icloud.com

---
Zhang Peng (5):
      mm/vmscan: track reclaimed pages in reclaim_stat
      mm/vmscan: extract folio activation into folio_active_bounce()
      mm/vmscan: extract folio_free() and pageout_one()
      mm/vmscan: extract folio unmap logic into folio_try_unmap()
      mm/vmscan: flush TLB for every 31 folios evictions

 include/linux/vmstat.h |   1 +
 mm/vmscan.c            | 456 +++++++++++++++++++++++++++++++------------------
 2 files changed, 287 insertions(+), 170 deletions(-)
---
base-commit: 7c5507fca017a80ece36f34e36c77e2bee267517
change-id: 20260309-batch-tlb-flush-893f0e56b496

Best regards,
-- 
Zhang Peng <zippermonkey@icloud.com>