mbox series

[4.14,0/5] memcontrol follow-up patches

Message ID 20210330181910.15378-1-fllinden@amazon.com
Headers show
Series memcontrol follow-up patches | expand

Message

Frank van der Linden March 30, 2021, 6:19 p.m. UTC 
During the 4.14.214 timeframe, we submitted the following
cherry-picks/backports:

mm: memcontrol: eliminate raw access to stat and event counters
mm: memcontrol: implement lruvec stat functions on top of each other
mm: memcontrol: fix excessive complexity in memory.stat reporting

They were accepted and part of linux-4.14.y since 4.14.214.

These were valid fixes, but needed a few follow-ups, or regressions
could occur. The regressions are described in the follow-up commits.

This 4.14 series adds these follow-ups, fixing these regressions.

Apologies for missing these commits. Two of them even
had the proper Fixes tags. The other two didn't, but still
mentioned the original commit in the description, so we should
have caught them.

They are all clean cherry-picks, with the exception of
"mm: fix oom_kill event handling", which needed minor
contextual massaging.

----

Aaron Lu (1):
  mem_cgroup: make sure moving_account, move_lock_task and stat_cpu in
    the same cacheline

Greg Thelen (1):
  mm: writeback: use exact memcg dirty counts

Johannes Weiner (2):
  mm: memcontrol: fix NR_WRITEBACK leak in memcg and system stats
  mm: memcg: make sure memory.events is uptodate when waking pollers

Roman Gushchin (1):
  mm: fix oom_kill event handling

 include/linux/memcontrol.h | 111 ++++++++++++++++++++++++++-----------
 mm/memcontrol.c            |  54 ++++++++++++------
 mm/oom_kill.c              |   2 +-
 mm/vmscan.c                |   2 +-
 4 files changed, 118 insertions(+), 51 deletions(-)