OSDN Git Service

sched/core: Use READ_ONCE()/WRITE_ONCE() in move_queued_task()/task_rq_lock()
authorAndrea Parri <andrea.parri@amarulasolutions.com>
Mon, 21 Jan 2019 15:52:40 +0000 (16:52 +0100)
committerIngo Molnar <mingo@kernel.org>
Mon, 4 Feb 2019 08:13:21 +0000 (09:13 +0100)
commitc546951d9c9300065bad253ecdf1ac59ce9d06c8
treeb5f282be96ca33780d286e8bf07d1b01471aa0c9
parent1ca4fa3ab604734e38e2a3000c9abf788512ffa7
sched/core: Use READ_ONCE()/WRITE_ONCE() in move_queued_task()/task_rq_lock()

move_queued_task() synchronizes with task_rq_lock() as follows:

move_queued_task() task_rq_lock()

[S] ->on_rq = MIGRATING [L] rq = task_rq()
WMB (__set_task_cpu()) ACQUIRE (rq->lock);
[S] ->cpu = new_cpu [L] ->on_rq

where "[L] rq = task_rq()" is ordered before "ACQUIRE (rq->lock)" by an
address dependency and, in turn, "ACQUIRE (rq->lock)" is ordered before
"[L] ->on_rq" by the ACQUIRE itself.

Use READ_ONCE() to load ->cpu in task_rq() (c.f., task_cpu()) to honor
this address dependency.  Also, mark the accesses to ->cpu and ->on_rq
with READ_ONCE()/WRITE_ONCE() to comply with the LKMM.

Signed-off-by: Andrea Parri <andrea.parri@amarulasolutions.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Alan Stern <stern@rowland.harvard.edu>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul E. McKenney <paulmck@linux.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Will Deacon <will.deacon@arm.com>
Link: https://lkml.kernel.org/r/20190121155240.27173-1-andrea.parri@amarulasolutions.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
include/linux/sched.h
kernel/sched/core.c
kernel/sched/sched.h