A mirror of the official Linux kernel repository just in case
Go to file
Johannes Weiner d583d360a6 psi: Fix psi state corruption when schedule() races with cgroup move
4117cebf1a ("psi: Optimize task switch inside shared cgroups")
introduced a race condition that corrupts internal psi state. This
manifests as kernel warnings, sometimes followed by bogusly high IO
pressure:

  psi: task underflow! cpu=1 t=2 tasks=[0 0 0 0] clear=c set=0
  (schedule() decreasing RUNNING and ONCPU, both of which are 0)

  psi: incosistent task state! task=2412744:systemd cpu=17 psi_flags=e clear=3 set=0
  (cgroup_move_task() clearing MEMSTALL and IOWAIT, but task is MEMSTALL | RUNNING | ONCPU)

What the offending commit does is batch the two psi callbacks in
schedule() to reduce the number of cgroup tree updates. When prev is
deactivated and removed from the runqueue, nothing is done in psi at
first; when the task switch completes, TSK_RUNNING and TSK_IOWAIT are
updated along with TSK_ONCPU.

However, the deactivation and the task switch inside schedule() aren't
atomic: pick_next_task() may drop the rq lock for load balancing. When
this happens, cgroup_move_task() can run after the task has been
physically dequeued, but the psi updates are still pending. Since it
looks at the task's scheduler state, it doesn't move everything to the
new cgroup that the task switch that follows is about to clear from
it. cgroup_move_task() will leak the TSK_RUNNING count in the old
cgroup, and psi_sched_switch() will underflow it in the new cgroup.

A similar thing can happen for iowait. TSK_IOWAIT is usually set when
a p->in_iowait task is dequeued, but again this update is deferred to
the switch. cgroup_move_task() can see an unqueued p->in_iowait task
and move a non-existent TSK_IOWAIT. This results in the inconsistent
task state warning, as well as a counter underflow that will result in
permanent IO ghost pressure being reported.

Fix this bug by making cgroup_move_task() use task->psi_flags instead
of looking at the potentially mismatching scheduler state.

[ We used the scheduler state historically in order to not rely on
  task->psi_flags for anything but debugging. But that ship has sailed
  anyway, and this is simpler and more robust.

  We previously already batched TSK_ONCPU clearing with the
  TSK_RUNNING update inside the deactivation call from schedule(). But
  that ordering was safe and didn't result in TSK_ONCPU corruption:
  unlike most places in the scheduler, cgroup_move_task() only checked
  task_current() and handled TSK_ONCPU if the task was still queued. ]

Fixes: 4117cebf1a ("psi: Optimize task switch inside shared cgroups")
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20210503174917.38579-1-hannes@cmpxchg.org
2021-05-06 15:33:26 +02:00
arch The x86 MM changes in this cycle were: 2021-04-29 11:41:43 -07:00
block SCSI misc on 20210428 2021-04-28 17:22:10 -07:00
certs certs: add 'x509_revocation_list' to gitignore 2021-04-26 10:48:07 -07:00
crypto for-5.13/drivers-2021-04-27 2021-04-28 14:39:37 -07:00
Documentation sched,doc: sched_debug_verbose cmdline should be sched_verbose 2021-05-06 15:33:26 +02:00
drivers - removed get_fs/set_fs 2021-04-29 11:28:08 -07:00
fs \n 2021-04-29 11:06:13 -07:00
include The x86 MM changes in this cycle were: 2021-04-29 11:41:43 -07:00
init Merge branch 'for-5.13' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup 2021-04-27 18:47:42 -07:00
ipc fs: make helpers idmap mount aware 2021-01-24 14:27:20 +01:00
kernel psi: Fix psi state corruption when schedule() races with cgroup move 2021-05-06 15:33:26 +02:00
lib - removed get_fs/set_fs 2021-04-29 11:28:08 -07:00
LICENSES LICENSES: Add the CC-BY-4.0 license 2020-12-08 10:33:27 -07:00
mm \n 2021-04-29 11:06:13 -07:00
net Scheduler updates for this cycle are: 2021-04-28 13:33:57 -07:00
samples vfio/mdev: Correct the function signatures for the mdev_type_attributes 2021-04-12 10:36:00 -06:00
scripts Devicetree updates for v5.13: 2021-04-28 15:50:24 -07:00
security Devicetree updates for v5.13: 2021-04-28 15:50:24 -07:00
sound - Core Frameworks 2021-04-28 15:59:13 -07:00
tools Perf events changes in this cycle were: 2021-04-28 13:03:44 -07:00
usr Kbuild updates for v5.12 2021-02-25 10:17:31 -08:00
virt KVM: x86/mmu: Consider the hva in mmu_notifier retry 2021-02-22 13:16:53 -05:00
.clang-format cxl for 5.12 2021-02-24 09:38:36 -08:00
.cocciconfig
.get_maintainer.ignore
.gitattributes .gitattributes: use 'dts' diff driver for dts files 2019-12-04 19:44:11 -08:00
.gitignore clang-lto series for v5.12-rc1 2021-02-23 09:28:51 -08:00
.mailmap It's been a relatively busy cycle in docsland, though more than usually 2021-04-26 13:22:43 -07:00
COPYING COPYING: state that all contributions really are covered by this file 2020-02-10 13:32:20 -08:00
CREDITS - Core Frameworks 2021-04-28 15:59:13 -07:00
Kbuild kbuild: rename hostprogs-y/always to hostprogs/always-y 2020-02-04 01:53:07 +09:00
Kconfig kbuild: ensure full rebuild when the compiler is updated 2020-05-12 13:28:33 +09:00
MAINTAINERS Here's a collection of largely clk driver updates for the merge window. The 2021-04-28 17:13:56 -07:00
Makefile CFI on arm64 series for v5.13-rc1 2021-04-27 10:16:46 -07:00
README

Linux kernel
============

There are several guides for kernel developers and users. These guides can
be rendered in a number of formats, like HTML and PDF. Please read
Documentation/admin-guide/README.rst first.

In order to build the documentation, use ``make htmldocs`` or
``make pdfdocs``.  The formatted documentation can also be read online at:

    https://www.kernel.org/doc/html/latest/

There are various text files in the Documentation/ subdirectory,
several of them using the Restructured Text markup notation.

Please read the Documentation/process/changes.rst file, as it contains the
requirements for building and running the kernel, and information about
the problems which may result by upgrading your kernel.