You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

Peter Zijlstra 9d6885c565 sched: Fix data-race in wakeup ... Mel reported that on some ARM64 platforms loadavg goes bananas and Will tracked it down to the following race: CPU0 CPU1 schedule() prev->sched_contributes_to_load = X; deactivate_task(prev); try_to_wake_up() if (p->on_rq &&) // false if (smp_load_acquire(&p->on_cpu) && // true ttwu_queue_wakelist()) p->sched_remote_wakeup = Y; smp_store_release(prev->on_cpu, 0); where both p->sched_contributes_to_load and p->sched_remote_wakeup are in the same word, and thus the stores X and Y race (and can clobber one another's data). Whereas prior to commit c6e7bd7afaeb ("sched/core: Optimize ttwu() spinning on p->on_cpu") the p->on_cpu handoff serialized access to p->sched_remote_wakeup (just as it still does with p->sched_contributes_to_load) that commit broke that by calling ttwu_queue_wakelist() with p->on_cpu != 0. However, due to p->XXX = X ttwu() schedule() if (p->on_rq && ...) // false smp_mb__after_spinlock() if (smp_load_acquire(&p->on_cpu) && deactivate_task() ttwu_queue_wakelist()) p->on_rq = 0; p->sched_remote_wakeup = Y; We can be sure any 'current' store is complete and 'current' is guaranteed asleep. Therefore we can move p->sched_remote_wakeup into the current flags word. Note: while the observed failure was loadavg accounting gone wrong due to ttwu() cobbering p->sched_contributes_to_load, the reverse problem is also possible where schedule() clobbers p->sched_remote_wakeup, this could result in enqueue_entity() wrecking ->vruntime and causing scheduling artifacts. Fixes: c6e7bd7afaeb ("sched/core: Optimize ttwu() spinning on p->on_cpu") Reported-by: Mel Gorman <mgorman@techsingularity.net> Debugged-by: Will Deacon <will@kernel.org> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Link: https://lkml.kernel.org/r/20201117083016.GK3121392@hirez.programming.kicks-ass.net Change-Id: I9a2e7ef7bfd4e3c1c8bdd49ecb4793634924b6c8 Signed-off-by: Alexander Winkowski <dereference23@outlook.com>		5 months ago
..
acpi	Import A525FXXU3AUG4	3 years ago
asm-generic	locking/barriers: Introduce smp_cond_load_relaxed() and atomic_cond_read_relaxed()	5 months ago
clocksource	arm64: use WFE for long delays	5 months ago
crypto	Import A525FXXU3AUG4	3 years ago
drm	Import A525FXXU3AUG4	3 years ago
dt-bindings	Import A525FXXU3AUG4	3 years ago
keys	Import A525FXXU3AUG4	3 years ago
kvm	Import A525FXXU3AUG4	3 years ago
linux	sched: Fix data-race in wakeup	5 months ago
math-emu	Import A525FXXU3AUG4	3 years ago
media	Import A525FXXU3AUG4	3 years ago
memory	Import A525FXXU3AUG4	3 years ago
microvisor	Import A525FXXU3AUG4	3 years ago
misc	Import A525FXXU3AUG4	3 years ago
net	BACKPORT: bpf: Hooks for sys_connect	9 months ago
pcmcia	Import A525FXXU3AUG4	3 years ago
ras	Import A525FXXU3AUG4	3 years ago
rdma	Import A525FXXU3AUG4	3 years ago
scsi	Import A525FXXU3AUG4	3 years ago
sdp	Import A525FXXU3AUG4	3 years ago
soc	Import A525FXXU3AUG4	3 years ago
sound	Revert "Revert "Revert "ANDROID: ALSA: jack: Update supported ja..."	8 months ago
target	Import A525FXXU3AUG4	3 years ago
trace	erofs: sync up with kernel 5.10	5 months ago
uapi	input: Sync switch event codes with upstream linux	8 months ago
video	Import A525FXXU3AUG4	3 years ago
vservices	Import A525FXXU3AUG4	3 years ago
xen	Import A525FXXU3AUG4	3 years ago
Kbuild	Import A525FXXU3AUG4	3 years ago