[ Upstream commit 79f3f9bedd ]
Basically, from the constraint that the sum of lag is zero, you can
infer that the 0-lag point is the weighted average of the individual
vruntime, which is what we're trying to compute:
\Sum w_i * v_i
avg = --------------
\Sum w_i
Now, since vruntime takes the whole u64 (worse, it wraps), this
multiplication term in the numerator is not something we can compute;
instead we do the min_vruntime (v0 henceforth) thing like:
v_i = (v_i - v0) + v0
This does two things:
- it keeps the key: (v_i - v0) 'small';
- it creates a relative 0-point in the modular space.
If you do that subtitution and work it all out, you end up with:
\Sum w_i * (v_i - v0)
avg = --------------------- + v0
\Sum w_i
Since you cannot very well track a ratio like that (and not suffer
terrible numerical problems) we simpy track the numerator and
denominator individually and only perform the division when strictly
needed.
Notably, the numerator lives in cfs_rq->avg_vruntime and the denominator
lives in cfs_rq->avg_load.
The one extra 'funny' is that these numbers track the entities in the
tree, and current is typically outside of the tree, so avg_vruntime()
adds current when needed before doing the division.
(vruntime_eligible() elides the division by cross-wise multiplication)
Anyway, as mentioned above, we currently use the CFS era min_vruntime
for this purpose. However, this thing can only move forward, while the
above avg can in fact move backward (when a non-eligible task leaves,
the average becomes smaller), this can cause trouble when through
happenstance (or construction) these values drift far enough apart to
wreck the game.
Replace cfs_rq::min_vruntime with cfs_rq::zero_vruntime which is kept
near/at avg_vruntime, following its motion.
The down-side is that this requires computing the avg more often.
Fixes: 147f3efaa2 ("sched/fair: Implement an EEVDF-like scheduling policy")
Reported-by: Zicheng Qu <quzicheng@huawei.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://patch.msgid.link/20251106111741.GC4068168@noisy.programming.kicks-ass.net
Cc: stable@vger.kernel.org
[ Adjust context in comments + init_cfs_rq ]
Signed-off-by: Sasha Levin <sashal@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Upstream commit ca125231dd ]
When a task is migrated out, there is a probability that the tg->load_avg
value will become abnormal. The reason is as follows:
1. Due to the 1ms update period limitation in update_tg_load_avg(), there
is a possibility that the reduced load_avg is not updated to tg->load_avg
when a task migrates out.
2. Even though __update_blocked_fair() traverses the leaf_cfs_rq_list and
calls update_tg_load_avg() for cfs_rqs that are not fully decayed, the key
function cfs_rq_is_decayed() does not check whether
cfs->tg_load_avg_contrib is null. Consequently, in some cases,
__update_blocked_fair() removes cfs_rqs whose avg.load_avg has not been
updated to tg->load_avg.
Add a check of cfs_rq->tg_load_avg_contrib in cfs_rq_is_decayed(),
which fixes the case (2.) mentioned above.
Fixes: 1528c661c2 ("sched/fair: Ratelimit update to tg->load_avg")
Signed-off-by: xupengbo <xupengbo@oppo.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Aaron Lu <ziqianlu@bytedance.com>
Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
Tested-by: Aaron Lu <ziqianlu@bytedance.com>
Link: https://patch.msgid.link/20250827022208.14487-1-xupengbo@oppo.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit 79104becf4 ]
If a task yields, the scheduler may decide to pick it again. The task in
turn may decide to yield immediately or shortly after, leading to a tight
loop of yields.
If there's another runnable task as this point, the deadline will be
increased by the slice at each loop. This can cause the deadline to runaway
pretty quickly, and subsequent elevated run delays later on as the task
doesn't get picked again. The reason the scheduler can pick the same task
again and again despite its deadline increasing is because it may be the
only eligible task at that point.
Fix this by making the task forfeiting its remaining vruntime and pushing
the deadline one slice ahead. This implements yield behavior more
authentically.
We limit the forfeiting to eligible tasks. This is because core scheduling
prefers running ineligible tasks rather than force idling. As such, without
the condition, we can end up on a yield loop which makes the vruntime
increase rapidly, leading to anomalous run delays later down the line.
Fixes: 147f3efaa2 ("sched/fair: Implement an EEVDF-like scheduling policy")
Signed-off-by: Fernand Sieber <sieberf@amazon.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20250401123622.584018-1-sieberf@amazon.com
Link: https://lore.kernel.org/r/20250911095113.203439-1-sieberf@amazon.com
Link: https://lore.kernel.org/r/20250916140228.452231-1-sieberf@amazon.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit 17e3e88ed0 ]
The check for some lost idle pelt time should be always done when
pick_next_task_fair() fails to pick a task and not only when we call it
from the fair fast-path.
The case happens when the last running task on rq is a RT or DL task. When
the latter goes to sleep and the /Sum of util_sum of the rq is at the max
value, we don't account the lost of idle time whereas we should.
Fixes: 67692435c4 ("sched: Rework pick_next_task() slow-path")
Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
Dequeuing a fair task on a throttled hierarchy returns early on
encountering a throttled cfs_rq since the throttle path has already
dequeued the hierarchy above and has adjusted the h_nr_* accounting till
the root cfs_rq.
dequeue_entities() crucially misses calling __block_task() for delayed
tasks being dequeued on the throttled hierarchies, but this was mostly
harmless until commit b7ca5743a2 ("sched/core: Tweak
wait_task_inactive() to force dequeue sched_delayed tasks") since all
existing cases would re-enqueue the task if task_on_rq_queued() returned
true and the task would eventually be blocked at pick after the
hierarchy was unthrottled.
wait_task_inactive() is special as it expects the delayed task on
throttled hierarchy to reach the blocked state on dequeue but since
__block_task() is never called, task_on_rq_queued() continues to return
true. Furthermore, since the task is now off the hierarchy, the pick
never reaches it to fully block the task even after unthrottle leading
to wait_task_inactive() looping endlessly.
Remedy this by calling __block_task() if a delayed task is being
dequeued on a throttled hierarchy.
This fix is only required for stabled kernels implementing delay dequeue
(>= v6.12) before v6.18 since upstream commit e1fad12dcb ("sched/fair:
Switch to task based throttle model") indirectly fixes this by removing
the early return conditions in dequeue_entities() as part of the per-task
throttle feature.
Cc: stable@vger.kernel.org
Reported-by: Matt Fleming <matt@readmodwrite.com>
Closes: https://lore.kernel.org/all/20250925133310.1843863-1-matt@readmodwrite.com/
Fixes: b7ca5743a2 ("sched/core: Tweak wait_task_inactive() to force dequeue sched_delayed tasks")
Tested-by: Matt Fleming <mfleming@cloudflare.com>
Signed-off-by: K Prateek Nayak <kprateek.nayak@amd.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Upstream commit 155213a2ae ]
schbench (https://github.com/masoncl/schbench.git) is showing a
regression from previous production kernels that bisected down to:
sched/fair: Remove sysctl_sched_migration_cost condition (c5b0a7eefc)
The schbench command line was:
schbench -L -m 4 -M auto -t 256 -n 0 -r 0 -s 0
This creates 4 message threads pinned to CPUs 0-3, and 256x4 worker
threads spread across the rest of the CPUs. Neither the worker threads
or the message threads do any work, they just wake each other up and go
back to sleep as soon as possible.
The end result is the first 4 CPUs are pegged waking up those 1024
workers, and the rest of the CPUs are constantly banging in and out of
idle. If I take a v6.9 Linus kernel and revert that one commit,
performance goes from 3.4M RPS to 5.4M RPS.
schedstat shows there are ~100x more new idle balance operations, and
profiling shows the worker threads are spending ~20% of their CPU time
on new idle balance. schedstats also shows that almost all of these new
idle balance attemps are failing to find busy groups.
The fix used here is to crank up the cost of the newidle balance whenever it
fails. Since we don't want sd->max_newidle_lb_cost to grow out of
control, this also changes update_newidle_cost() to use
sysctl_sched_migration_cost as the upper limit on max_newidle_lb_cost.
Signed-off-by: Chris Mason <clm@fb.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Vincent Guittot <vincent.guittot@linaro.org>
Link: https://lkml.kernel.org/r/20250626144017.1510594-2-clm@fb.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit aa3ee4f0b7 ]
Delayed dequeued feature keeps a sleeping task enqueued until its
lag has elapsed. As a result, it stays also visible in rq->nr_running.
So when in wake_affine_idle(), we should use the real running-tasks
in rq to check whether we should place the wake-up task to
current cpu.
On the other hand, add a helper function to return the nr-delayed.
Fixes: 152e11f6df ("sched/fair: Implement delayed dequeue")
Signed-off-by: Xuewen Yan <xuewen.yan@unisoc.com>
Reviewed-and-tested-by: Tianchen Ding <dtcccc@linux.alibaba.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
Link: https://lore.kernel.org/r/20250303105241.17251-2-xuewen.yan@unisoc.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit c2a295bffe ]
With delayed dequeued feature, a sleeping sched_entity remains queued in
the rq until its lag has elapsed. As a result, it stays also visible
in the statistics that are used to balance the system and in particular
the field cfs.h_nr_queued when the sched_entity is associated to a task.
Create a new h_nr_runnable that tracks only queued and runnable tasks.
Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Link: https://lore.kernel.org/r/20241202174606.4074512-5-vincent.guittot@linaro.org
Stable-dep-of: aa3ee4f0b7 ("sched/fair: Fixup wake_up_sync() vs DELAYED_DEQUEUE")
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit 2ae891b826 ]
The old default value for slice is 0.75 msec * (1 + ilog(ncpus)) which
means that we have a default slice of:
0.75 for 1 cpu
1.50 up to 3 cpus
2.25 up to 7 cpus
3.00 for 8 cpus and above.
For HZ=250 and HZ=100, because of the tick accuracy, the runtime of
tasks is far higher than their slice.
For HZ=1000 with 8 cpus or more, the accuracy of tick is already
satisfactory, but there is still an issue that tasks will get an extra
tick because the tick often arrives a little faster than expected. In
this case, the task can only wait until the next tick to consider that it
has reached its deadline, and will run 1ms longer.
vruntime + sysctl_sched_base_slice = deadline
|-----------|-----------|-----------|-----------|
1ms 1ms 1ms 1ms
^ ^ ^ ^
tick1 tick2 tick3 tick4(nearly 4ms)
There are two reasons for tick error: clockevent precision and the
CONFIG_IRQ_TIME_ACCOUNTING/CONFIG_PARAVIRT_TIME_ACCOUNTING. with
CONFIG_IRQ_TIME_ACCOUNTING every tick will be less than 1ms, but even
without it, because of clockevent precision, tick still often less than
1ms.
In order to make scheduling more precise, we changed 0.75 to 0.70,
Using 0.70 instead of 0.75 should not change much for other configs
and would fix this issue:
0.70 for 1 cpu
1.40 up to 3 cpus
2.10 up to 7 cpus
2.8 for 8 cpus and above.
This does not guarantee that tasks can run the slice time accurately
every time, but occasionally running an extra tick has little impact.
Signed-off-by: zihan zhou <15645113830zzh@gmail.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
Link: https://lkml.kernel.org/r/20250208075322.13139-1-15645113830zzh@gmail.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
commit bbce3de72b upstream.
There is a code path in dequeue_entities() that can set the slice of a
sched_entity to U64_MAX, which sometimes results in a crash.
The offending case is when dequeue_entities() is called to dequeue a
delayed group entity, and then the entity's parent's dequeue is delayed.
In that case:
1. In the if (entity_is_task(se)) else block at the beginning of
dequeue_entities(), slice is set to
cfs_rq_min_slice(group_cfs_rq(se)). If the entity was delayed, then
it has no queued tasks, so cfs_rq_min_slice() returns U64_MAX.
2. The first for_each_sched_entity() loop dequeues the entity.
3. If the entity was its parent's only child, then the next iteration
tries to dequeue the parent.
4. If the parent's dequeue needs to be delayed, then it breaks from the
first for_each_sched_entity() loop _without updating slice_.
5. The second for_each_sched_entity() loop sets the parent's ->slice to
the saved slice, which is still U64_MAX.
This throws off subsequent calculations with potentially catastrophic
results. A manifestation we saw in production was:
6. In update_entity_lag(), se->slice is used to calculate limit, which
ends up as a huge negative number.
7. limit is used in se->vlag = clamp(vlag, -limit, limit). Because limit
is negative, vlag > limit, so se->vlag is set to the same huge
negative number.
8. In place_entity(), se->vlag is scaled, which overflows and results in
another huge (positive or negative) number.
9. The adjusted lag is subtracted from se->vruntime, which increases or
decreases se->vruntime by a huge number.
10. pick_eevdf() calls entity_eligible()/vruntime_eligible(), which
incorrectly returns false because the vruntime is so far from the
other vruntimes on the queue, causing the
(vruntime - cfs_rq->min_vruntime) * load calulation to overflow.
11. Nothing appears to be eligible, so pick_eevdf() returns NULL.
12. pick_next_entity() tries to dereference the return value of
pick_eevdf() and crashes.
Dumping the cfs_rq states from the core dumps with drgn showed tell-tale
huge vruntime ranges and bogus vlag values, and I also traced se->slice
being set to U64_MAX on live systems (which was usually "benign" since
the rest of the runqueue needed to be in a particular state to crash).
Fix it in dequeue_entities() by always setting slice from the first
non-empty cfs_rq.
Fixes: aef6987d89 ("sched/eevdf: Propagate min_slice up the cgroup hierarchy")
Signed-off-by: Omar Sandoval <osandov@fb.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lkml.kernel.org/r/f0c2d1072be229e1bdddc73c0703919a8b00c652.1745570998.git.osandov@fb.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Upstream commit 563bc2161b ]
When a task is enqueued and its parent cgroup se is already on_rq, this
parent cgroup se will not be enqueued again, and hence the root->min_slice
leaves unchanged. The same issue happens when a task is dequeued and its
parent cgroup se has other runnable entities, and the parent cgroup se
will not be dequeued.
Force propagating min_slice when se doesn't need to be enqueued or
dequeued. Ensure the se hierarchy always get the latest min_slice.
Fixes: aef6987d89 ("sched/eevdf: Propagate min_slice up the cgroup hierarchy")
Signed-off-by: Tianchen Ding <dtcccc@linux.alibaba.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20250211063659.7180-1-dtcccc@linux.alibaba.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit f553741ac8 ]
A wakeup non-idle entity should preempt idle entity at any time,
but because of the slice protection of the idle entity, the non-idle
entity has to wait, so just cancel it.
This patch is aimed at minimizing the impact of SCHED_IDLE on
SCHED_NORMAL. For example, a task with SCHED_IDLE policy that sleeps for
1s and then runs for 3 ms, running cyclictest on the same cpu, has a
maximum latency of 3 ms, which is caused by the slice protection of the
idle entity. It is unreasonable. With this patch, the cyclictest latency
under the same conditions is basically the same on the cpu with idle
processes and on empty cpu.
[peterz: add helpers]
Fixes: 63304558ba ("sched/eevdf: Curb wakeup-preemption")
Signed-off-by: zihan zhou <15645113830zzh@gmail.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
Tested-by: Vincent Guittot <vincent.guittot@linaro.org>
Link: https://lkml.kernel.org/r/20250208080850.16300-1-15645113830zzh@gmail.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit 3b4035ddbf ]
child_cfs_rq_on_list attempts to convert a 'prev' pointer to a cfs_rq.
This 'prev' pointer can originate from struct rq's leaf_cfs_rq_list,
making the conversion invalid and potentially leading to memory
corruption. Depending on the relative positions of leaf_cfs_rq_list and
the task group (tg) pointer within the struct, this can cause a memory
fault or access garbage data.
The issue arises in list_add_leaf_cfs_rq, where both
cfs_rq->leaf_cfs_rq_list and rq->leaf_cfs_rq_list are added to the same
leaf list. Also, rq->tmp_alone_branch can be set to rq->leaf_cfs_rq_list.
This adds a check `if (prev == &rq->leaf_cfs_rq_list)` after the main
conditional in child_cfs_rq_on_list. This ensures that the container_of
operation will convert a correct cfs_rq struct.
This check is sufficient because only cfs_rqs on the same CPU are added
to the list, so verifying the 'prev' pointer against the current rq's list
head is enough.
Fixes a potential memory corruption issue that due to current struct
layout might not be manifesting as a crash but could lead to unpredictable
behavior when the layout changes.
Fixes: fdaba61ef8 ("sched/fair: Ensure that the CFS parent is added after unthrottling")
Signed-off-by: Zecheng Li <zecheng@google.com>
Reviewed-and-tested-by: K Prateek Nayak <kprateek.nayak@amd.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
Link: https://lore.kernel.org/r/20250304214031.2882646-1-zecheng@google.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit 3429dd57f0 ]
set_delayed() adjusts cfs_rq->h_nr_runnable for the hierarchy when an
entity is delayed irrespective of whether the entity corresponds to a
task or a cfs_rq.
Consider the following scenario:
root
/ \
A B (*) delayed since B is no longer eligible on root
| |
Task0 Task1 <--- dequeue_task_fair() - task blocks
When Task1 blocks (dequeue_entity() for task's se returns true),
dequeue_entities() will continue adjusting cfs_rq->h_nr_* for the
hierarchy of Task1. However, when the sched_entity corresponding to
cfs_rq B is delayed, set_delayed() will adjust the h_nr_runnable for the
hierarchy too leading to both dequeue_entity() and set_delayed()
decrementing h_nr_runnable for the dequeue of the same task.
A SCHED_WARN_ON() to inspect h_nr_runnable post its update in
dequeue_entities() like below:
cfs_rq->h_nr_runnable -= h_nr_runnable;
SCHED_WARN_ON(((int) cfs_rq->h_nr_runnable) < 0);
is consistently tripped when running wakeup intensive workloads like
hackbench in a cgroup.
This error is self correcting since cfs_rq are per-cpu and cannot
migrate. The entitiy is either picked for full dequeue or is requeued
when a task wakes up below it. Both those paths call clear_delayed()
which again increments h_nr_runnable of the hierarchy without
considering if the entity corresponds to a task or not.
h_nr_runnable will eventually reflect the correct value however in the
interim, the incorrect values can still influence PELT calculation which
uses se->runnable_weight or cfs_rq->h_nr_runnable.
Since only delayed tasks take the early return path in
dequeue_entities() and enqueue_task_fair(), adjust the
h_nr_runnable in {set,clear}_delayed() only when a task is delayed as
this path skips the h_nr_* update loops and returns early.
For entities corresponding to cfs_rq, the h_nr_* update loop in the
caller will do the right thing.
Fixes: 76f2f78329 ("sched/eevdf: More PELT vs DELAYED_DEQUEUE")
Signed-off-by: K Prateek Nayak <kprateek.nayak@amd.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Gautham R. Shenoy <gautham.shenoy@amd.com>
Tested-by: Swapnil Sapkal <swapnil.sapkal@amd.com>
Link: https://lkml.kernel.org/r/20250117105852.23908-1-kprateek.nayak@amd.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit a430d99e34 ]
In /proc/schedstat, lb_hot_gained reports the number hot tasks pulled
during load balance. This value is incremented in can_migrate_task()
if the task is migratable and hot. After incrementing the value,
load balancer can still decide not to migrate this task leading to wrong
accounting. Fix this by incrementing stats when hot tasks are detached.
This issue only exists in detach_tasks() where we can decide to not
migrate hot task even if it is migratable. However, in detach_one_task(),
we migrate it unconditionally.
[Swapnil: Handled the case where nr_failed_migrations_hot was not accounted properly and wrote commit log]
Fixes: d31980846f ("sched: Move up affinity check to mitigate useless redoing overhead")
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reported-by: "Gautham R. Shenoy" <gautham.shenoy@amd.com>
Not-yet-signed-off-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Swapnil Sapkal <swapnil.sapkal@amd.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20241220063224.17767-2-swapnil.sapkal@amd.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit 2a77e4be12 ]
There are 3 sites using set_next_buddy() and only one is conditional
on NEXT_BUDDY, the other two sites are unconditional; to note:
- yield_to_task()
- cgroup dequeue / pick optimization
However, having NEXT_BUDDY control both the wakeup-preemption and the
picking side of things means its near useless.
Fixes: 147f3efaa2 ("sched/fair: Implement an EEVDF-like scheduling policy")
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20241129101541.GA33464@noisy.programming.kicks-ass.net
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit 66951e4860 ]
Normally dequeue_entities() will continue to dequeue an empty group entity;
except DELAY_DEQUEUE changes things -- it retains empty entities such that they
might continue to compete and burn off some lag.
However, doing this results in update_cfs_group() re-computing the cgroup
weight 'slice' for an empty group, which it (rightly) figures isn't much at
all. This in turn means that the delayed entity is not competing at the
expected weight. Worse, the very low weight causes its lag to be inflated,
which combined with avg_vruntime() using scale_load_down(), leads to artifacts.
As such, don't adjust the weight for empty group entities and let them compete
at their original weight.
Fixes: 152e11f6df ("sched/fair: Implement delayed dequeue")
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20250110115720.GA17405@noisy.programming.kicks-ass.net
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit c7f7e9c731 ]
dlserver time is accounted when:
- dlserver is active and the dlserver proxies the cfs task.
- dlserver is active but deferred and cfs task runs after being picked
through the normal fair class pick.
dl_server_update is called in two places to make sure that both the
above times are accounted for. But it doesn't check if dlserver is
active or not. Now that we have this dl_server_active flag, we can
consolidate dl_server_update into one place and all we need to check is
whether dlserver is active or not. When dlserver is active there is only
two possible conditions:
- dlserver is deferred.
- cfs task is running on behalf of dlserver.
Fixes: a110a81c52 ("sched/deadline: Deferrable dl server")
Signed-off-by: "Vineeth Pillai (Google)" <vineeth@bitbyteword.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: Marcel Ziswiler <marcel.ziswiler@codethink.co.uk> # ROCK 5B
Link: https://lore.kernel.org/r/20241213032244.877029-2-vineeth@bitbyteword.org
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit ff47a0acfc ]
Commit b2a02fc43a ("smp: Optimize send_call_function_single_ipi()")
optimizes IPIs to idle CPUs in TIF_POLLING_NRFLAG mode by setting the
TIF_NEED_RESCHED flag in idle task's thread info and relying on
flush_smp_call_function_queue() in idle exit path to run the
call-function. A softirq raised by the call-function is handled shortly
after in do_softirq_post_smp_call_flush() but the TIF_NEED_RESCHED flag
remains set and is only cleared later when schedule_idle() calls
__schedule().
need_resched() check in _nohz_idle_balance() exists to bail out of load
balancing if another task has woken up on the CPU currently in-charge of
idle load balancing which is being processed in SCHED_SOFTIRQ context.
Since the optimization mentioned above overloads the interpretation of
TIF_NEED_RESCHED, check for idle_cpu() before going with the existing
need_resched() check which can catch a genuine task wakeup on an idle
CPU processing SCHED_SOFTIRQ from do_softirq_post_smp_call_flush(), as
well as the case where ksoftirqd needs to be preempted as a result of
new task wakeup or slice expiry.
In case of PREEMPT_RT or threadirqs, although the idle load balancing
may be inhibited in some cases on the ilb CPU, the fact that ksoftirqd
is the only fair task going back to sleep will trigger a newidle balance
on the CPU which will alleviate some imbalance if it exists if idle
balance fails to do so.
Fixes: b2a02fc43a ("smp: Optimize send_call_function_single_ipi()")
Signed-off-by: K Prateek Nayak <kprateek.nayak@amd.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20241119054432.6405-4-kprateek.nayak@amd.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
commit 5f1b64e9a9 upstream.
[Problem Description]
When running the hackbench program of LTP, the following memory leak is
reported by kmemleak.
# /opt/ltp/testcases/bin/hackbench 20 thread 1000
Running with 20*40 (== 800) tasks.
# dmesg | grep kmemleak
...
kmemleak: 480 new suspected memory leaks (see /sys/kernel/debug/kmemleak)
kmemleak: 665 new suspected memory leaks (see /sys/kernel/debug/kmemleak)
# cat /sys/kernel/debug/kmemleak
unreferenced object 0xffff888cd8ca2c40 (size 64):
comm "hackbench", pid 17142, jiffies 4299780315
hex dump (first 32 bytes):
ac 74 49 00 01 00 00 00 4c 84 49 00 01 00 00 00 .tI.....L.I.....
00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................
backtrace (crc bff18fd4):
[<ffffffff81419a89>] __kmalloc_cache_noprof+0x2f9/0x3f0
[<ffffffff8113f715>] task_numa_work+0x725/0xa00
[<ffffffff8110f878>] task_work_run+0x58/0x90
[<ffffffff81ddd9f8>] syscall_exit_to_user_mode+0x1c8/0x1e0
[<ffffffff81dd78d5>] do_syscall_64+0x85/0x150
[<ffffffff81e0012b>] entry_SYSCALL_64_after_hwframe+0x76/0x7e
...
This issue can be consistently reproduced on three different servers:
* a 448-core server
* a 256-core server
* a 192-core server
[Root Cause]
Since multiple threads are created by the hackbench program (along with
the command argument 'thread'), a shared vma might be accessed by two or
more cores simultaneously. When two or more cores observe that
vma->numab_state is NULL at the same time, vma->numab_state will be
overwritten.
Although current code ensures that only one thread scans the VMAs in a
single 'numa_scan_period', there might be a chance for another thread
to enter in the next 'numa_scan_period' while we have not gotten till
numab_state allocation [1].
Note that the command `/opt/ltp/testcases/bin/hackbench 50 process 1000`
cannot the reproduce the issue. It is verified with 200+ test runs.
[Solution]
Use the cmpxchg atomic operation to ensure that only one thread executes
the vma->numab_state assignment.
[1] https://lore.kernel.org/lkml/1794be3c-358c-4cdc-a43d-a1f841d91ef7@amd.com/
Link: https://lkml.kernel.org/r/20241113102146.2384-1-ahuang12@lenovo.com
Fixes: ef6a22b70f ("sched/numa: apply the scan delay to every new vma")
Signed-off-by: Adrian Huang <ahuang12@lenovo.com>
Reported-by: Jiwei Sun <sunjw10@lenovo.com>
Reviewed-by: Raghavendra K T <raghavendra.kt@amd.com>
Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Ben Segall <bsegall@google.com>
Cc: Dietmar Eggemann <dietmar.eggemann@arm.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Juri Lelli <juri.lelli@redhat.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Valentin Schneider <vschneid@redhat.com>
Cc: Vincent Guittot <vincent.guittot@linaro.org>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
When running stress-ng-vm-segv test, we found a null pointer dereference
error in task_numa_work(). Here is the backtrace:
[323676.066985] Unable to handle kernel NULL pointer dereference at virtual address 0000000000000020
......
[323676.067108] CPU: 35 PID: 2694524 Comm: stress-ng-vm-se
......
[323676.067113] pstate: 23401009 (nzCv daif +PAN -UAO +TCO +DIT +SSBS BTYPE=--)
[323676.067115] pc : vma_migratable+0x1c/0xd0
[323676.067122] lr : task_numa_work+0x1ec/0x4e0
[323676.067127] sp : ffff8000ada73d20
[323676.067128] x29: ffff8000ada73d20 x28: 0000000000000000 x27: 000000003e89f010
[323676.067130] x26: 0000000000080000 x25: ffff800081b5c0d8 x24: ffff800081b27000
[323676.067133] x23: 0000000000010000 x22: 0000000104d18cc0 x21: ffff0009f7158000
[323676.067135] x20: 0000000000000000 x19: 0000000000000000 x18: ffff8000ada73db8
[323676.067138] x17: 0001400000000000 x16: ffff800080df40b0 x15: 0000000000000035
[323676.067140] x14: ffff8000ada73cc8 x13: 1fffe0017cc72001 x12: ffff8000ada73cc8
[323676.067142] x11: ffff80008001160c x10: ffff000be639000c x9 : ffff8000800f4ba4
[323676.067145] x8 : ffff000810375000 x7 : ffff8000ada73974 x6 : 0000000000000001
[323676.067147] x5 : 0068000b33e26707 x4 : 0000000000000001 x3 : ffff0009f7158000
[323676.067149] x2 : 0000000000000041 x1 : 0000000000004400 x0 : 0000000000000000
[323676.067152] Call trace:
[323676.067153] vma_migratable+0x1c/0xd0
[323676.067155] task_numa_work+0x1ec/0x4e0
[323676.067157] task_work_run+0x78/0xd8
[323676.067161] do_notify_resume+0x1ec/0x290
[323676.067163] el0_svc+0x150/0x160
[323676.067167] el0t_64_sync_handler+0xf8/0x128
[323676.067170] el0t_64_sync+0x17c/0x180
[323676.067173] Code: d2888001 910003fd f9000bf3 aa0003f3 (f9401000)
[323676.067177] SMP: stopping secondary CPUs
[323676.070184] Starting crashdump kernel...
stress-ng-vm-segv in stress-ng is used to stress test the SIGSEGV error
handling function of the system, which tries to cause a SIGSEGV error on
return from unmapping the whole address space of the child process.
Normally this program will not cause kernel crashes. But before the
munmap system call returns to user mode, a potential task_numa_work()
for numa balancing could be added and executed. In this scenario, since the
child process has no vma after munmap, the vma_next() in task_numa_work()
will return a null pointer even if the vma iterator restarts from 0.
Recheck the vma pointer before dereferencing it in task_numa_work().
Fixes: 214dbc4281 ("sched: convert to vma iterator")
Signed-off-by: Shawn Wang <shawnwang@linux.alibaba.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: stable@vger.kernel.org # v6.2+
Link: https://lkml.kernel.org/r/20241025022208.125527-1-shawnwang@linux.alibaba.com
Syzkaller robot reported KCSAN tripping over the
ASSERT_EXCLUSIVE_WRITER(p->on_rq) in __block_task().
The report noted that both pick_next_task_fair() and try_to_wake_up()
were concurrently trying to write to the same p->on_rq, violating the
assertion -- even though both paths hold rq->__lock.
The logical consequence is that both code paths end up holding a
different rq->__lock. And looking through ttwu(), this is possible
when the __block_task() 'p->on_rq = 0' store is visible to the ttwu()
'p->on_rq' load, which then assumes the task is not queued and
continues to migrate it.
Rearrange things such that __block_task() releases @p with the store
and no code thereafter will use @p again.
Fixes: 152e11f6df ("sched/fair: Implement delayed dequeue")
Reported-by: syzbot+0ec1e96c2cdf5c0e512a@syzkaller.appspotmail.com
Reported-by: Kent Overstreet <kent.overstreet@linux.dev>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: Marco Elver <elver@google.com>
Link: https://lkml.kernel.org/r/20241023093641.GE16066@noisy.programming.kicks-ass.net
Commit 2e0199df25 ("sched/fair: Prepare exit/cleanup paths for delayed_dequeue")
and its follow up fixes try to deal with a rather unfortunate
situation where is task is enqueued in a new class, even though it
shouldn't have been. Mostly because the existing ->switched_to/from()
hooks are in the wrong place for this case.
This all led to Paul being able to trigger failures at something like
once per 10k CPU hours of RCU torture.
For now, do the ugly thing and move the code to the right place by
ignoring the switch hooks.
Note: Clean up the whole sched_class::switch*_{to,from}() thing.
Fixes: 2e0199df25 ("sched/fair: Prepare exit/cleanup paths for delayed_dequeue")
Reported-by: Paul E. McKenney <paulmck@kernel.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20241003185037.GA5594@noisy.programming.kicks-ass.net
Commit 85e511df3c ("sched/eevdf: Allow shorter slices to wakeup-preempt")
introduced a mechanism that a wakee with shorter slice could preempt
the current running task. It also lower the bar for the current task
to be preempted, by checking the rq->nr_running instead of cfs_rq->nr_running
when the current task has ran out of time slice. But there is a scenario
that is problematic. Say, if there is 1 cfs task and 1 rt task, before
85e511df3c, update_deadline() will not trigger a reschedule, and after
85e511df3c, since rq->nr_running is 2 and resched is true, a resched_curr()
would happen.
Some workloads (like the hackbench reported by lkp) do not like
over-scheduling. We can see that the preemption rate has been
increased by 2.2%:
1.654e+08 +2.2% 1.69e+08 hackbench.time.involuntary_context_switches
Restore its previous check criterion.
Fixes: 85e511df3c ("sched/eevdf: Allow shorter slices to wakeup-preempt")
Closes: https://lore.kernel.org/oe-lkp/202409231416.9403c2e9-oliver.sang@intel.com
Reported-by: kernel test robot <oliver.sang@intel.com>
Suggested-by: K Prateek Nayak <kprateek.nayak@amd.com>
Signed-off-by: Chen Yu <yu.c.chen@intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Honglei Wang <jameshongleiwang@126.com>
Tested-by: K Prateek Nayak <kprateek.nayak@amd.com>
Link: https://lore.kernel.org/r/20240925085440.358138-1-yu.c.chen@intel.com
Pull sched_ext support from Tejun Heo:
"This implements a new scheduler class called ‘ext_sched_class’, or
sched_ext, which allows scheduling policies to be implemented as BPF
programs.
The goals of this are:
- Ease of experimentation and exploration: Enabling rapid iteration
of new scheduling policies.
- Customization: Building application-specific schedulers which
implement policies that are not applicable to general-purpose
schedulers.
- Rapid scheduler deployments: Non-disruptive swap outs of scheduling
policies in production environments"
See individual commits for more documentation, but also the cover letter
for the latest series:
Link: https://lore.kernel.org/all/20240618212056.2833381-1-tj@kernel.org/
* tag 'sched_ext-for-6.12' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/sched_ext: (110 commits)
sched: Move update_other_load_avgs() to kernel/sched/pelt.c
sched_ext: Don't trigger ops.quiescent/runnable() on migrations
sched_ext: Synchronize bypass state changes with rq lock
scx_qmap: Implement highpri boosting
sched_ext: Implement scx_bpf_dispatch[_vtime]_from_dsq()
sched_ext: Compact struct bpf_iter_scx_dsq_kern
sched_ext: Replace consume_local_task() with move_local_task_to_local_dsq()
sched_ext: Move consume_local_task() upward
sched_ext: Move sanity check and dsq_mod_nr() into task_unlink_from_dsq()
sched_ext: Reorder args for consume_local/remote_task()
sched_ext: Restructure dispatch_to_local_dsq()
sched_ext: Fix processs_ddsp_deferred_locals() by unifying DTL_INVALID handling
sched_ext: Make find_dsq_for_dispatch() handle SCX_DSQ_LOCAL_ON
sched_ext: Refactor consume_remote_task()
sched_ext: Rename scx_kfunc_set_sleepable to unlocked and relocate
sched_ext: Add missing static to scx_dump_data
sched_ext: Add missing static to scx_has_op[]
sched_ext: Temporarily work around pick_task_scx() being called without balance_scx()
sched_ext: Add a cgroup scheduler which uses flattened hierarchy
sched_ext: Add cgroup support
...
Pull MM updates from Andrew Morton:
"Along with the usual shower of singleton patches, notable patch series
in this pull request are:
- "Align kvrealloc() with krealloc()" from Danilo Krummrich. Adds
consistency to the APIs and behaviour of these two core allocation
functions. This also simplifies/enables Rustification.
- "Some cleanups for shmem" from Baolin Wang. No functional changes -
mode code reuse, better function naming, logic simplifications.
- "mm: some small page fault cleanups" from Josef Bacik. No
functional changes - code cleanups only.
- "Various memory tiering fixes" from Zi Yan. A small fix and a
little cleanup.
- "mm/swap: remove boilerplate" from Yu Zhao. Code cleanups and
simplifications and .text shrinkage.
- "Kernel stack usage histogram" from Pasha Tatashin and Shakeel
Butt. This is a feature, it adds new feilds to /proc/vmstat such as
$ grep kstack /proc/vmstat
kstack_1k 3
kstack_2k 188
kstack_4k 11391
kstack_8k 243
kstack_16k 0
which tells us that 11391 processes used 4k of stack while none at
all used 16k. Useful for some system tuning things, but
partivularly useful for "the dynamic kernel stack project".
- "kmemleak: support for percpu memory leak detect" from Pavel
Tikhomirov. Teaches kmemleak to detect leaksage of percpu memory.
- "mm: memcg: page counters optimizations" from Roman Gushchin. "3
independent small optimizations of page counters".
- "mm: split PTE/PMD PT table Kconfig cleanups+clarifications" from
David Hildenbrand. Improves PTE/PMD splitlock detection, makes
powerpc/8xx work correctly by design rather than by accident.
- "mm: remove arch_make_page_accessible()" from David Hildenbrand.
Some folio conversions which make arch_make_page_accessible()
unneeded.
- "mm, memcg: cg2 memory{.swap,}.peak write handlers" fro David
Finkel. Cleans up and fixes our handling of the resetting of the
cgroup/process peak-memory-use detector.
- "Make core VMA operations internal and testable" from Lorenzo
Stoakes. Rationalizaion and encapsulation of the VMA manipulation
APIs. With a view to better enable testing of the VMA functions,
even from a userspace-only harness.
- "mm: zswap: fixes for global shrinker" from Takero Funaki. Fix
issues in the zswap global shrinker, resulting in improved
performance.
- "mm: print the promo watermark in zoneinfo" from Kaiyang Zhao. Fill
in some missing info in /proc/zoneinfo.
- "mm: replace follow_page() by folio_walk" from David Hildenbrand.
Code cleanups and rationalizations (conversion to folio_walk())
resulting in the removal of follow_page().
- "improving dynamic zswap shrinker protection scheme" from Nhat
Pham. Some tuning to improve zswap's dynamic shrinker. Significant
reductions in swapin and improvements in performance are shown.
- "mm: Fix several issues with unaccepted memory" from Kirill
Shutemov. Improvements to the new unaccepted memory feature,
- "mm/mprotect: Fix dax puds" from Peter Xu. Implements mprotect on
DAX PUDs. This was missing, although nobody seems to have notied
yet.
- "Introduce a store type enum for the Maple tree" from Sidhartha
Kumar. Cleanups and modest performance improvements for the maple
tree library code.
- "memcg: further decouple v1 code from v2" from Shakeel Butt. Move
more cgroup v1 remnants away from the v2 memcg code.
- "memcg: initiate deprecation of v1 features" from Shakeel Butt.
Adds various warnings telling users that memcg v1 features are
deprecated.
- "mm: swap: mTHP swap allocator base on swap cluster order" from
Chris Li. Greatly improves the success rate of the mTHP swap
allocation.
- "mm: introduce numa_memblks" from Mike Rapoport. Moves various
disparate per-arch implementations of numa_memblk code into generic
code.
- "mm: batch free swaps for zap_pte_range()" from Barry Song. Greatly
improves the performance of munmap() of swap-filled ptes.
- "support large folio swap-out and swap-in for shmem" from Baolin
Wang. With this series we no longer split shmem large folios into
simgle-page folios when swapping out shmem.
- "mm/hugetlb: alloc/free gigantic folios" from Yu Zhao. Nice
performance improvements and code reductions for gigantic folios.
- "support shmem mTHP collapse" from Baolin Wang. Adds support for
khugepaged's collapsing of shmem mTHP folios.
- "mm: Optimize mseal checks" from Pedro Falcato. Fixes an mprotect()
performance regression due to the addition of mseal().
- "Increase the number of bits available in page_type" from Matthew
Wilcox. Increases the number of bits available in page_type!
- "Simplify the page flags a little" from Matthew Wilcox. Many legacy
page flags are now folio flags, so the page-based flags and their
accessors/mutators can be removed.
- "mm: store zero pages to be swapped out in a bitmap" from Usama
Arif. An optimization which permits us to avoid writing/reading
zero-filled zswap pages to backing store.
- "Avoid MAP_FIXED gap exposure" from Liam Howlett. Fixes a race
window which occurs when a MAP_FIXED operqtion is occurring during
an unrelated vma tree walk.
- "mm: remove vma_merge()" from Lorenzo Stoakes. Major rotorooting of
the vma_merge() functionality, making ot cleaner, more testable and
better tested.
- "misc fixups for DAMON {self,kunit} tests" from SeongJae Park.
Minor fixups of DAMON selftests and kunit tests.
- "mm: memory_hotplug: improve do_migrate_range()" from Kefeng Wang.
Code cleanups and folio conversions.
- "Shmem mTHP controls and stats improvements" from Ryan Roberts.
Cleanups for shmem controls and stats.
- "mm: count the number of anonymous THPs per size" from Barry Song.
Expose additional anon THP stats to userspace for improved tuning.
- "mm: finish isolate/putback_lru_page()" from Kefeng Wang: more
folio conversions and removal of now-unused page-based APIs.
- "replace per-quota region priorities histogram buffer with
per-context one" from SeongJae Park. DAMON histogram
rationalization.
- "Docs/damon: update GitHub repo URLs and maintainer-profile" from
SeongJae Park. DAMON documentation updates.
- "mm/vdpa: correct misuse of non-direct-reclaim __GFP_NOFAIL and
improve related doc and warn" from Jason Wang: fixes usage of page
allocator __GFP_NOFAIL and GFP_ATOMIC flags.
- "mm: split underused THPs" from Yu Zhao. Improve THP=always policy.
This was overprovisioning THPs in sparsely accessed memory areas.
- "zram: introduce custom comp backends API" frm Sergey Senozhatsky.
Add support for zram run-time compression algorithm tuning.
- "mm: Care about shadow stack guard gap when getting an unmapped
area" from Mark Brown. Fix up the various arch_get_unmapped_area()
implementations to better respect guard areas.
- "Improve mem_cgroup_iter()" from Kinsey Ho. Improve the reliability
of mem_cgroup_iter() and various code cleanups.
- "mm: Support huge pfnmaps" from Peter Xu. Extends the usage of huge
pfnmap support.
- "resource: Fix region_intersects() vs add_memory_driver_managed()"
from Huang Ying. Fix a bug in region_intersects() for systems with
CXL memory.
- "mm: hwpoison: two more poison recovery" from Kefeng Wang. Teaches
a couple more code paths to correctly recover from the encountering
of poisoned memry.
- "mm: enable large folios swap-in support" from Barry Song. Support
the swapin of mTHP memory into appropriately-sized folios, rather
than into single-page folios"
* tag 'mm-stable-2024-09-20-02-31' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (416 commits)
zram: free secondary algorithms names
uprobes: turn xol_area->pages[2] into xol_area->page
uprobes: introduce the global struct vm_special_mapping xol_mapping
Revert "uprobes: use vm_special_mapping close() functionality"
mm: support large folios swap-in for sync io devices
mm: add nr argument in mem_cgroup_swapin_uncharge_swap() helper to support large folios
mm: fix swap_read_folio_zeromap() for large folios with partial zeromap
mm/debug_vm_pgtable: Use pxdp_get() for accessing page table entries
set_memory: add __must_check to generic stubs
mm/vma: return the exact errno in vms_gather_munmap_vmas()
memcg: cleanup with !CONFIG_MEMCG_V1
mm/show_mem.c: report alloc tags in human readable units
mm: support poison recovery from copy_present_page()
mm: support poison recovery from do_cow_fault()
resource, kunit: add test case for region_intersects()
resource: make alloc_free_mem_region() works for iomem_resource
mm: z3fold: deprecate CONFIG_Z3FOLD
vfio/pci: implement huge_fault support
mm/arm64: support large pfn mappings
mm/x86: support large pfn mappings
...
Pull scheduler updates from Ingo Molnar:
- Implement the SCHED_DEADLINE server infrastructure - Daniel Bristot
de Oliveira's last major contribution to the kernel:
"SCHED_DEADLINE servers can help fixing starvation issues of low
priority tasks (e.g., SCHED_OTHER) when higher priority tasks
monopolize CPU cycles. Today we have RT Throttling; DEADLINE
servers should be able to replace and improve that."
(Daniel Bristot de Oliveira, Peter Zijlstra, Joel Fernandes, Youssef
Esmat, Huang Shijie)
- Preparatory changes for sched_ext integration:
- Use set_next_task(.first) where required
- Fix up set_next_task() implementations
- Clean up DL server vs. core sched
- Split up put_prev_task_balance()
- Rework pick_next_task()
- Combine the last put_prev_task() and the first set_next_task()
- Rework dl_server
- Add put_prev_task(.next)
(Peter Zijlstra, with a fix by Tejun Heo)
- Complete the EEVDF transition and refine EEVDF scheduling:
- Implement delayed dequeue
- Allow shorter slices to wakeup-preempt
- Use sched_attr::sched_runtime to set request/slice suggestion
- Document the new feature flags
- Remove unused and duplicate-functionality fields
- Simplify & unify pick_next_task_fair()
- Misc debuggability enhancements
(Peter Zijlstra, with fixes/cleanups by Dietmar Eggemann, Valentin
Schneider and Chuyi Zhou)
- Initialize the vruntime of a new task when it is first enqueued,
resulting in significant decrease in latency of newly woken tasks
(Zhang Qiao)
- Introduce SM_IDLE and an idle re-entry fast-path in __schedule()
(K Prateek Nayak, Peter Zijlstra)
- Clean up and clarify the usage of Clean up usage of rt_task()
(Qais Yousef)
- Preempt SCHED_IDLE entities in strict cgroup hierarchies
(Tianchen Ding)
- Clarify the documentation of time units for deadline scheduler
parameters (Christian Loehle)
- Remove the HZ_BW chicken-bit feature flag introduced a year ago,
the original change seems to be working fine (Phil Auld)
- Misc fixes and cleanups (Chen Yu, Dan Carpenter, Huang Shijie,
Peilin He, Qais Yousefm and Vincent Guittot)
* tag 'sched-core-2024-09-19' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (64 commits)
sched/cpufreq: Use NSEC_PER_MSEC for deadline task
cpufreq/cppc: Use NSEC_PER_MSEC for deadline task
sched/deadline: Clarify nanoseconds in uapi
sched/deadline: Convert schedtool example to chrt
sched/debug: Fix the runnable tasks output
sched: Fix sched_delayed vs sched_core
kernel/sched: Fix util_est accounting for DELAY_DEQUEUE
kthread: Fix task state in kthread worker if being frozen
sched/pelt: Use rq_clock_task() for hw_pressure
sched/fair: Move effective_cpu_util() and effective_cpu_util() in fair.c
sched/core: Introduce SM_IDLE and an idle re-entry fast-path in __schedule()
sched: Add put_prev_task(.next)
sched: Rework dl_server
sched: Combine the last put_prev_task() and the first set_next_task()
sched: Rework pick_next_task()
sched: Split up put_prev_task_balance()
sched: Clean up DL server vs core sched
sched: Fixup set_next_task() implementations
sched: Use set_next_task(.first) where required
sched/fair: Properly deactivate sched_delayed task upon class change
...
Pull in tip/sched/core to resolve two merge conflicts:
- 96fd6c65ef ("sched: Factor out update_other_load_avgs() from __update_blocked_others()")
5d871a6399 ("sched/fair: Move effective_cpu_util() and effective_cpu_util() in fair.c")
A simple context conflict. The former added __update_blocked_others() in
the same #ifdef CONFIG_SMP block that effective_cpu_util() and
sched_cpu_util() are in and the latter moved those functions to fair.c.
This makes __update_blocked_others() more out of place. Will follow up
with a patch to relocate.
- 96fd6c65ef ("sched: Factor out update_other_load_avgs() from __update_blocked_others()")
84d265281d ("sched/pelt: Use rq_clock_task() for hw_pressure")
The former factored out the body of __update_blocked_others() into
update_other_load_avgs(). The latter changed how update_hw_load_avg() is
called in the body. Resolved by applying the change to
update_other_load_avgs() instead.
Signed-off-by: Tejun Heo <tj@kernel.org>
commit 97450eb909 ("sched/pelt: Remove shift of thermal clock")
removed the decay_shift for hw_pressure. This commit uses the
sched_clock_task() in sched_tick() while it replaces the
sched_clock_task() with rq_clock_pelt() in __update_blocked_others().
This could bring inconsistence. One possible scenario I can think of
is in ___update_load_sum():
u64 delta = now - sa->last_update_time
'now' could be calculated by rq_clock_pelt() from
__update_blocked_others(), and last_update_time was calculated by
rq_clock_task() previously from sched_tick(). Usually the former
chases after the latter, it cause a very large 'delta' and brings
unexpected behavior.
Fixes: 97450eb909 ("sched/pelt: Remove shift of thermal clock")
Signed-off-by: Chen Yu <yu.c.chen@intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Hongyan Xia <hongyan.xia2@arm.com>
Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
Link: https://lkml.kernel.org/r/20240827112607.181206-1-yu.c.chen@intel.com
Problem statement:
Since commit fc137c0dda ("sched/numa: enhance vma scanning logic"), the
Numa vma scan overhead has been reduced a lot. Meanwhile, the reducing of
the vma scan might create less Numa page fault information. The
insufficient information makes it harder for the Numa balancer to make
decision. Later, commit b7a5b537c5 ("sched/numa: Complete scanning of
partial VMAs regardless of PID activity") and commit 84db47ca71
("sched/numa: Fix mm numa_scan_seq based unconditional scan") are found to
bring back part of the performance.
Recently when running SPECcpu omnetpp_r on a 320 CPUs/2 Sockets system, a
long duration of remote Numa node read was observed by PMU events: A few
cores having ~500MB/s remote memory access for ~20 seconds. It causes
high core-to-core variance and performance penalty. After the
investigation, it is found that many vmas are skipped due to the active
PID check. According to the trace events, in most cases,
vma_is_accessed() returns false because the history access info stored in
pids_active array has been cleared.
Proposal:
The main idea is to adjust vma_is_accessed() to let it return true easier.
Thus compare the diff between mm->numa_scan_seq and
vma->numab_state->prev_scan_seq. If the diff has exceeded the threshold,
scan the vma.
This patch especially helps the cases where there are small number of
threads, like the process-based SPECcpu. Without this patch, if the
SPECcpu process access the vma at the beginning, then sleeps for a long
time, the pid_active array will be cleared. A a result, if this process
is woken up again, it never has a chance to set prot_none anymore.
Because only the first 2 times of access is granted for vma scan:
(current->mm->numa_scan_seq) - vma->numab_state->start_scan_seq) < 2 to be
worse, no other threads within the task can help set the prot_none. This
causes information lost.
Raghavendra helped test current patch and got the positive result
on the AMD platform:
autonumabench NUMA01
base patched
Amean syst-NUMA01 194.05 ( 0.00%) 165.11 * 14.92%*
Amean elsp-NUMA01 324.86 ( 0.00%) 315.58 * 2.86%*
Duration User 380345.36 368252.04
Duration System 1358.89 1156.23
Duration Elapsed 2277.45 2213.25
autonumabench NUMA02
Amean syst-NUMA02 1.12 ( 0.00%) 1.09 * 2.93%*
Amean elsp-NUMA02 3.50 ( 0.00%) 3.56 * -1.84%*
Duration User 1513.23 1575.48
Duration System 8.33 8.13
Duration Elapsed 28.59 29.71
kernbench
Amean user-256 22935.42 ( 0.00%) 22535.19 * 1.75%*
Amean syst-256 7284.16 ( 0.00%) 7608.72 * -4.46%*
Amean elsp-256 159.01 ( 0.00%) 158.17 * 0.53%*
Duration User 68816.41 67615.74
Duration System 21873.94 22848.08
Duration Elapsed 506.66 504.55
Intel 256 CPUs/2 Sockets:
autonuma benchmark also shows improvements:
v6.10-rc5 v6.10-rc5
+patch
Amean syst-NUMA01 245.85 ( 0.00%) 230.84 * 6.11%*
Amean syst-NUMA01_THREADLOCAL 205.27 ( 0.00%) 191.86 * 6.53%*
Amean syst-NUMA02 18.57 ( 0.00%) 18.09 * 2.58%*
Amean syst-NUMA02_SMT 2.63 ( 0.00%) 2.54 * 3.47%*
Amean elsp-NUMA01 517.17 ( 0.00%) 526.34 * -1.77%*
Amean elsp-NUMA01_THREADLOCAL 99.92 ( 0.00%) 100.59 * -0.67%*
Amean elsp-NUMA02 15.81 ( 0.00%) 15.72 * 0.59%*
Amean elsp-NUMA02_SMT 13.23 ( 0.00%) 12.89 * 2.53%*
v6.10-rc5 v6.10-rc5
+patch
Duration User 1064010.16 1075416.23
Duration System 3307.64 3104.66
Duration Elapsed 4537.54 4604.73
The SPECcpu remote node access issue disappears with the patch applied.
Link: https://lkml.kernel.org/r/20240827112958.181388-1-yu.c.chen@intel.com
Fixes: fc137c0dda ("sched/numa: enhance vma scanning logic")
Signed-off-by: Chen Yu <yu.c.chen@intel.com>
Co-developed-by: Chen Yu <yu.c.chen@intel.com>
Signed-off-by: Yujie Liu <yujie.liu@intel.com>
Reported-by: Xiaoping Zhou <xiaoping.zhou@intel.com>
Reviewed-and-tested-by: Raghavendra K T <raghavendra.kt@amd.com>
Acked-by: Mel Gorman <mgorman@techsingularity.net>
Cc: "Chen, Tim C" <tim.c.chen@intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Juri Lelli <juri.lelli@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Raghavendra K T <raghavendra.kt@amd.com>
Cc: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
- Resolve trivial context conflicts from dl_server clearing being moved
around.
- Add @next to put_prev_task_scx() and @prev to pick_next_task_scx() to
match sched/core.
- Merge sched_class->switch_class() addition from sched_ext with
tip/sched/core changes in __pick_next_task().
- Make pick_next_task_scx() call put_prev_task_scx() to emulate the previous
behavior where sched_class->put_prev_task() was called before
sched_class->pick_next_task().
While this makes sched_ext build and function, the behavior is not in line
with other sched classes. The follow-up patches will address the
discrepancies and remove sched_class->switch_class().
Signed-off-by: Tejun Heo <tj@kernel.org>
In order to tell the previous sched_class what the next task is, add
put_prev_task(.next).
Notable SCX will use this to:
1) determine the next task will leave the SCX sched class and push
the current task to another CPU if possible.
2) statistics on how often and which other classes preempt it
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20240813224016.367421076@infradead.org
When a task is selected through a dl_server, it will have p->dl_server
set, such that it can account runtime to the dl_server, see
update_curr_task().
Currently p->dl_server is set in pick*task() whenever it goes through
the dl_server, clearing it is a bit of a mess though. The trivial
solution is clearing it on the final put (now that we have this
location).
However, this gives a problem when:
p = pick_task(rq);
if (p)
put_prev_set_next_task(rq, prev, next);
picks the same task but through a different path, notably when it goes
from picking through the dl_server to a direct pick or vice-versa. In
that case we cannot readily determine wether we should clear or
preserve p->dl_server.
An additional complication is pick_*task() setting p->dl_server for a
remote pick, it might still need to update runtime before it schedules
the core_pick.
Close all these holes and remove all the random clearing of
p->dl_server by:
- having pick_*task() manage rq->dl_server
- having the final put_prev_task() clear p->dl_server
- having the first set_next_task() set p->dl_server = rq->dl_server
- complicate the core_sched code to save/restore rq->dl_server where
appropriate.
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20240813224016.259853414@infradead.org
The current rule is that:
pick_next_task() := pick_task() + set_next_task(.first = true)
And many classes implement it directly as such. Change things around
to make pick_next_task() optional while also changing the definition to:
pick_next_task(prev) := pick_task() + put_prev_task() + set_next_task(.first = true)
The reason is that sched_ext would like to have a 'final' call that
knows the next task. By placing put_prev_task() right next to
set_next_task() (as it already is for sched_core) this becomes
trivial.
As a bonus, this is a nice cleanup on its own.
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20240813224016.051225657@infradead.org
__sched_setscheduler() goes through an enqueue/dequeue cycle like so:
flags := DEQUEUE_SAVE | DEQUEUE_MOVE | DEQUEUE_NOCLOCK;
prev_class->dequeue_task(rq, p, flags);
new_class->enqueue_task(rq, p, flags);
when prev_class := fair_sched_class, this is followed by:
dequeue_task(rq, p, DEQUEUE_NOCLOCK | DEQUEUE_SLEEP);
the idea being that since the task has switched classes, we need to drop
the sched_delayed logic and have that task be deactivated per its previous
dequeue_task(..., DEQUEUE_SLEEP).
Unfortunately, this leaves the task on_rq. This is missing the tail end of
dequeue_entities() that issues __block_task(), which __sched_setscheduler()
won't have done due to not using DEQUEUE_DELAYED - not that it should, as
it is pretty much a fair_sched_class specific thing.
Make switched_from_fair() properly deactivate sched_delayed tasks upon
class changes via __block_task(), as if a
dequeue_task(..., DEQUEUE_DELAYED)
had been issued.
Fixes: 2e0199df25 ("sched/fair: Prepare exit/cleanup paths for delayed_dequeue")
Reported-by: "Paul E. McKenney" <paulmck@kernel.org>
Reported-by: Chen Yu <yu.c.chen@intel.com>
Signed-off-by: Valentin Schneider <vschneid@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20240829135353.1524260-1-vschneid@redhat.com
