linux.git/kernel/sched/deadline.c, branch v6.8

sched/deadline: Introduce deadline servers

2023-11-15T08:57:51+00:00

Low priority tasks (e.g., SCHED_OTHER) can suffer starvation if tasks
with higher priority (e.g., SCHED_FIFO) monopolize CPU(s).

RT Throttling has been introduced a while ago as a (mostly debug)
countermeasure one can utilize to reserve some CPU time for low priority
tasks (usually background type of work, e.g. workqueues, timers, etc.).
It however has its own problems (see documentation) and the undesired
effect of unconditionally throttling FIFO tasks even when no lower
priority activity needs to run (there are mechanisms to fix this issue
as well, but, again, with their own problems).

Introduce deadline servers to service low priority tasks needs under
starvation conditions. Deadline servers are built extending SCHED_DEADLINE
implementation to allow 2-level scheduling (a sched_deadline entity
becomes a container for lower priority scheduling entities).

Signed-off-by: Peter Zijlstra (Intel) 
Signed-off-by: Daniel Bristot de Oliveira 
Signed-off-by: Peter Zijlstra (Intel) 
Link: https://lkml.kernel.org/r/4968601859d920335cf85822eb573a5f179f04b8.1699095159.git.bristot@kernel.org

sched/deadline: Move bandwidth accounting into {en,de}queue_dl_entity

2023-11-15T08:57:50+00:00

In preparation of introducing !task sched_dl_entity; move the
bandwidth accounting into {en.de}queue_dl_entity().

Signed-off-by: Peter Zijlstra (Intel) 
Signed-off-by: Daniel Bristot de Oliveira 
Signed-off-by: Peter Zijlstra (Intel) 
Reviewed-by: Phil Auld 
Reviewed-by: Valentin Schneider 
Link: https://lkml.kernel.org/r/a86dccbbe44e021b8771627e1dae01a69b73466d.1699095159.git.bristot@kernel.org

sched/deadline: Collect sched_dl_entity initialization

2023-11-15T08:57:50+00:00

Create a single function that initializes a sched_dl_entity.

Signed-off-by: Peter Zijlstra (Intel) 
Signed-off-by: Daniel Bristot de Oliveira 
Signed-off-by: Peter Zijlstra (Intel) 
Reviewed-by: Phil Auld 
Reviewed-by: Valentin Schneider 
Link: https://lkml.kernel.org/r/51acc695eecf0a1a2f78f9a044e11ffd9b316bcf.1699095159.git.bristot@kernel.org

sched: Unify runtime accounting across classes

2023-11-15T08:57:48+00:00

All classes use sched_entity::exec_start to track runtime and have
copies of the exact same code around to compute runtime.

Collapse all that.

Signed-off-by: Peter Zijlstra (Intel) 
Signed-off-by: Daniel Bristot de Oliveira 
Signed-off-by: Peter Zijlstra (Intel) 
Reviewed-by: Phil Auld 
Reviewed-by: Valentin Schneider 
Reviewed-by: Steven Rostedt (Google) 
Link: https://lkml.kernel.org/r/54d148a144f26d9559698c4dd82d8859038a7380.1699095159.git.bristot@kernel.org

sched: Fix stop_one_cpu_nowait() vs hotplug

2023-10-13T07:56:29+00:00

Kuyo reported sporadic failures on a sched_setaffinity() vs CPU
hotplug stress-test -- notably affine_move_task() remains stuck in
wait_for_completion(), leading to a hung-task detector warning.

Specifically, it was reported that stop_one_cpu_nowait(.fn =
migration_cpu_stop) returns false -- this stopper is responsible for
the matching complete().

The race scenario is:

	CPU0					CPU1

					// doing _cpu_down()

  __set_cpus_allowed_ptr()
    task_rq_lock();
					takedown_cpu()
					  stop_machine_cpuslocked(take_cpu_down..)

					
    ack_state()
					  MULTI_STOP_RUN
					    take_cpu_down()
					      __cpu_disable();
					      stop_machine_park();
						stopper->enabled = false;
					 />
   />
	stop_one_cpu_nowait(.fn = migration_cpu_stop);
          if (stopper->enabled) // false!!!

That is, by doing stop_one_cpu_nowait() after dropping rq-lock, the
stopper thread gets a chance to preempt and allows the cpu-down for
the target CPU to complete.

OTOH, since stop_one_cpu_nowait() / cpu_stop_queue_work() needs to
issue a wakeup, it must not be ran under the scheduler locks.

Solve this apparent contradiction by keeping preemption disabled over
the unlock + queue_stopper combination:

	preempt_disable();
	task_rq_unlock(...);
	if (!stop_pending)
	  stop_one_cpu_nowait(...)
	preempt_enable();

This respects the lock ordering contraints while still avoiding the
above race. That is, if we find the CPU is online under rq-lock, the
targeted stop_one_cpu_nowait() must succeed.

Apply this pattern to all similar stop_one_cpu_nowait() invocations.

Fixes: 6d337eab041d ("sched: Fix migrate_disable() vs set_cpus_allowed_ptr()")
Reported-by: "Kuyo Chang (張建文)" 
Signed-off-by: Peter Zijlstra (Intel) 
Tested-by: "Kuyo Chang (張建文)" 
Link: https://lkml.kernel.org/r/20231010200442.GA16515@noisy.programming.kicks-ass.net

sched/topology: Consolidate and clean up access to a CPU's max compute capacity

2023-10-09T10:59:48+00:00

Remove the rq::cpu_capacity_orig field and use arch_scale_cpu_capacity()
instead.

The scheduler uses 3 methods to get access to a CPU's max compute capacity:

 - arch_scale_cpu_capacity(cpu) which is the default way to get a CPU's capacity.

 - cpu_capacity_orig field which is periodically updated with
   arch_scale_cpu_capacity().

 - capacity_orig_of(cpu) which encapsulates rq->cpu_capacity_orig.

There is no real need to save the value returned by arch_scale_cpu_capacity()
in struct rq. arch_scale_cpu_capacity() returns:

 - either a per_cpu variable.

 - or a const value for systems which have only one capacity.

Remove rq::cpu_capacity_orig and use arch_scale_cpu_capacity() everywhere.

No functional changes.

Some performance tests on Arm64:

  - small SMP device (hikey): no noticeable changes
  - HMP device (RB5):         hackbench shows minor improvement (1-2%)
  - large smp (thx2):         hackbench and tbench shows minor improvement (1%)

Signed-off-by: Vincent Guittot 
Signed-off-by: Ingo Molnar 
Reviewed-by: Dietmar Eggemann 
Link: https://lore.kernel.org/r/20231009103621.374412-2-vincent.guittot@linaro.org

sched/deadline: Make dl_rq->pushable_dl_tasks update drive dl_rq->overloaded

2023-09-29T08:20:21+00:00

dl_rq->dl_nr_migratory is increased whenever a DL entity is enqueued and it has
nr_cpus_allowed > 1. Unlike the pushable_dl_tasks tree, dl_rq->dl_nr_migratory
includes a dl_rq's current task. This means a dl_rq can have a migratable
current, N non-migratable queued tasks, and be flagged as overloaded and have
its CPU set in the dlo_mask, despite having an empty pushable_tasks tree.

Make an dl_rq's overload logic be driven by {enqueue,dequeue}_pushable_dl_task(),
in other words make DL RQs only be flagged as overloaded if they have at
least one runnable-but-not-current migratable task.

 o push_dl_task() is unaffected, as it is a no-op if there are no pushable
   tasks.

 o pull_dl_task() now no longer scans runqueues whose sole migratable task is
   their current one, which it can't do anything about anyway.
   It may also now pull tasks to a DL RQ with dl_nr_running > 1 if only its
   current task is migratable.

Since dl_rq->dl_nr_migratory becomes unused, remove it.

RT had the exact same mechanism (rt_rq->rt_nr_migratory) which was dropped
in favour of relying on rt_rq->pushable_tasks, see:

  612f769edd06 ("sched/rt: Make rt_rq->pushable_tasks updates drive rto_mask")

Signed-off-by: Valentin Schneider 
Signed-off-by: Ingo Molnar 
Acked-by: Juri Lelli 
Link: https://lore.kernel.org/r/20230928150251.463109-1-vschneid@redhat.com

sched/fair: Rename check_preempt_curr() to wakeup_preempt()

2023-09-19T08:40:10+00:00

The name is a bit opaque - make it clear that this is about wakeup
preemption.

Also rename the ->check_preempt_curr() methods similarly.

Signed-off-by: Ingo Molnar 
Acked-by: Peter Zijlstra (Intel)

Merge tag 'cgroup-for-6.5' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup

2023-06-27T23:54:21+00:00

Pull cgroup updates from Tejun Heo:

 - Whenever cpuset needs to rebuild sched_domain, it walked all tasks
   looking for DEADLINE tasks as they need to be accounted on the new
   domain. Walking all tasks can be expensive and there may not be any
   DEADLINE tasks at all. Task iteration is now omitted if there are no
   DEADLINE tasks

 - Fixes DEADLINE bandwidth misaccounting after task migration failures

 - When no controller is enabled, -Wstringop-overflow warning is
   triggered. The fix patch added an early exit which is too eager and
   got reverted for now. Will fix later

 - Everything else is minor cleanups

* tag 'cgroup-for-6.5' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup:
  Revert "cgroup: Avoid -Wstringop-overflow warnings"
  cgroup/misc: Expose misc.current on cgroup v2 root
  cgroup: Avoid -Wstringop-overflow warnings
  cgroup: remove obsolete comment on cgroup_on_dfl()
  cgroup: remove unused task_cgroup_path()
  cgroup/cpuset: remove unneeded header files
  cgroup: make cgroup_is_threaded() and cgroup_is_thread_root() static
  rdmacg: fix kernel-doc warnings in rdmacg
  cgroup: Replace the css_set call with cgroup_get
  cgroup: remove unused macro for_each_e_css()
  cgroup: Update out-of-date comment in cgroup_migrate()
  cgroup: Replace all non-returning strlcpy with strscpy
  cgroup/cpuset: remove unneeded header files
  cgroup/cpuset: Free DL BW in case can_attach() fails
  sched/deadline: Create DL BW alloc, free & check overflow interface
  cgroup/cpuset: Iterate only if DEADLINE tasks are present
  sched/cpuset: Keep track of SCHED_DEADLINE task in cpusets
  sched/cpuset: Bring back cpuset_mutex
  cgroup/cpuset: Rename functions dealing with DEADLINE accounting

sched/deadline: Fix bandwidth reclaim equation in GRUB

2023-06-16T20:08:11+00:00

According to the GRUB[1] rule, the runtime is depreciated as:
  "dq = -max{u, (1 - Uinact - Uextra)} dt" (1)

To guarantee that deadline tasks doesn't starve lower class tasks,
we do not allocate the full bandwidth of the cpu to deadline tasks.
Maximum bandwidth usable by deadline tasks is denoted by "Umax".
Considering Umax, equation (1) becomes:
  "dq = -(max{u, (Umax - Uinact - Uextra)} / Umax) dt" (2)

Current implementation has a minor bug in equation (2), which this
patch fixes.

The reclamation logic is verified by a sample program which creates
multiple deadline threads and observing their utilization. The tests
were run on an isolated cpu(isolcpus=3) on a 4 cpu system.

Tests on 6.3.0
==============

RUN 1: runtime=7ms, deadline=period=10ms, RT capacity = 95%
TID[693]: RECLAIM=1, (r=7ms, d=10ms, p=10ms), Util: 93.33
TID[693]: RECLAIM=1, (r=7ms, d=10ms, p=10ms), Util: 93.35

RUN 2: runtime=1ms, deadline=period=100ms, RT capacity = 95%
TID[708]: RECLAIM=1, (r=1ms, d=100ms, p=100ms), Util: 16.69
TID[708]: RECLAIM=1, (r=1ms, d=100ms, p=100ms), Util: 16.69

RUN 3: 2 tasks
  Task 1: runtime=1ms, deadline=period=10ms
  Task 2: runtime=1ms, deadline=period=100ms
TID[631]: RECLAIM=1, (r=1ms, d=10ms, p=10ms), Util: 62.67
TID[632]: RECLAIM=1, (r=1ms, d=100ms, p=100ms), Util: 6.37
TID[631]: RECLAIM=1, (r=1ms, d=10ms, p=10ms), Util: 62.38
TID[632]: RECLAIM=1, (r=1ms, d=100ms, p=100ms), Util: 6.23

As seen above, the reclamation doesn't reclaim the maximum allowed
bandwidth and as the bandwidth of tasks gets smaller, the reclaimed
bandwidth also comes down.

Tests with this patch applied
=============================

RUN 1: runtime=7ms, deadline=period=10ms, RT capacity = 95%
TID[608]: RECLAIM=1, (r=7ms, d=10ms, p=10ms), Util: 95.19
TID[608]: RECLAIM=1, (r=7ms, d=10ms, p=10ms), Util: 95.16

RUN 2: runtime=1ms, deadline=period=100ms, RT capacity = 95%
TID[616]: RECLAIM=1, (r=1ms, d=100ms, p=100ms), Util: 95.27
TID[616]: RECLAIM=1, (r=1ms, d=100ms, p=100ms), Util: 95.21

RUN 3: 2 tasks
  Task 1: runtime=1ms, deadline=period=10ms
  Task 2: runtime=1ms, deadline=period=100ms
TID[620]: RECLAIM=1, (r=1ms, d=10ms, p=10ms), Util: 86.64
TID[621]: RECLAIM=1, (r=1ms, d=100ms, p=100ms), Util: 8.66
TID[620]: RECLAIM=1, (r=1ms, d=10ms, p=10ms), Util: 86.45
TID[621]: RECLAIM=1, (r=1ms, d=100ms, p=100ms), Util: 8.73

Running tasks on all cpus allowing for migration also showed that
the utilization is reclaimed to the maximum. Running 10 tasks on
3 cpus SCHED_FLAG_RECLAIM - top shows:
%Cpu0  : 94.6 us,  0.0 sy,  0.0 ni,  5.4 id,  0.0 wa
%Cpu1  : 95.2 us,  0.0 sy,  0.0 ni,  4.8 id,  0.0 wa
%Cpu2  : 95.8 us,  0.0 sy,  0.0 ni,  4.2 id,  0.0 wa

[1]: Abeni, Luca & Lipari, Giuseppe & Parri, Andrea & Sun, Youcheng.
     (2015). Parallel and sequential reclaiming in multicore
     real-time global scheduling.

Signed-off-by: Vineeth Pillai (Google) 
Signed-off-by: Peter Zijlstra (Intel) 
Reviewed-by: Daniel Bristot de Oliveira 
Acked-by: Juri Lelli 
Link: https://lore.kernel.org/r/20230530135526.2385378-1-vineeth@bitbyteword.org