From 269d599271fa604f09d5cb0093c5dd5d59964dd5 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 6 Feb 2018 17:52:13 +0100 Subject: [PATCH] sched/core: Fix DEBUG_SPINLOCK annotation for rq->lock Mark noticed that he had sporadic "spinlock recursion" warnings from the DEBUG_SPINLOCK code. Now rq->lock is special in that the owner changes in the middle of a context switch. It so happens that we fix up the lock.owner too late, @prev can run (remotely) the moment prev->on_cpu is cleared, this then allows @prev to again try and acquire this rq->lock and trigger this warning. So we have to switch lock.owner before clearing prev->on_cpu. Do this by moving the DEBUG_SPINLOCK annotation from after switch_to() to before switch_to() and collect all lockdep annotations there into prepare_lock_switch() to mirror the existing finish_lock_switch(). Debugged-by: Mark Rutland Signed-off-by: Peter Zijlstra (Intel) Acked-by: Mark Rutland Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Signed-off-by: Ingo Molnar --- kernel/sched/core.c | 27 ++++++++++++++++----------- 1 file changed, 16 insertions(+), 11 deletions(-) diff --git a/kernel/sched/core.c b/kernel/sched/core.c index bf724c1..e7c535e 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -2601,19 +2601,31 @@ static inline void finish_task(struct task_struct *prev) #endif } -static inline void finish_lock_switch(struct rq *rq) +static inline void +prepare_lock_switch(struct rq *rq, struct task_struct *next, struct rq_flags *rf) { + /* + * Since the runqueue lock will be released by the next + * task (which is an invalid locking op but in the case + * of the scheduler it's an obvious special-case), so we + * do an early lockdep release here: + */ + rq_unpin_lock(rq, rf); + spin_release(&rq->lock.dep_map, 1, _THIS_IP_); #ifdef CONFIG_DEBUG_SPINLOCK /* this is a valid case when another task releases the spinlock */ - rq->lock.owner = current; + rq->lock.owner = next; #endif +} + +static inline void finish_lock_switch(struct rq *rq) +{ /* * If we are tracking spinlock dependencies then we have to * fix up the runqueue lock - which gets 'carried over' from * prev into current: */ spin_acquire(&rq->lock.dep_map, 0, 0, _THIS_IP_); - raw_spin_unlock_irq(&rq->lock); } @@ -2844,14 +2856,7 @@ context_switch(struct rq *rq, struct task_struct *prev, rq->clock_update_flags &= ~(RQCF_ACT_SKIP|RQCF_REQ_SKIP); - /* - * Since the runqueue lock will be released by the next - * task (which is an invalid locking op but in the case - * of the scheduler it's an obvious special-case), so we - * do an early lockdep release here: - */ - rq_unpin_lock(rq, rf); - spin_release(&rq->lock.dep_map, 1, _THIS_IP_); + prepare_lock_switch(rq, next, rf); /* Here we just switch the register state and the stack. */ switch_to(prev, next, prev); -- 2.7.4