From ff042f4a9b050895a42cae893cc01fa2ca81b95c Mon Sep 17 00:00:00 2001 From: Marcelo Tosatti Date: Tue, 22 Mar 2022 14:45:47 -0700 Subject: mm: lru_cache_disable: replace work queue synchronization with synchronize_rcu On systems that run FIFO:1 applications that busy loop, any SCHED_OTHER task that attempts to execute on such a CPU (such as work threads) will not be scheduled, which leads to system hangs. Commit d479960e44f27e0e5 ("mm: disable LRU pagevec during the migration temporarily") relies on queueing work items on all online CPUs to ensure visibility of lru_disable_count. To fix this, replace the usage of work items with synchronize_rcu, which provides the same guarantees. Readers of lru_disable_count are protected by either disabling preemption or rcu_read_lock: preempt_disable, local_irq_disable [bh_lru_lock()] rcu_read_lock [rt_spin_lock CONFIG_PREEMPT_RT] preempt_disable [local_lock !CONFIG_PREEMPT_RT] Since v5.1 kernel, synchronize_rcu() is guaranteed to wait on preempt_disable() regions of code. So any CPU which sees lru_disable_count = 0 will have exited the critical section when synchronize_rcu() returns. Link: https://lkml.kernel.org/r/Yin7hDxdt0s/x+fp@fuller.cnet Signed-off-by: Marcelo Tosatti Reviewed-by: Nicolas Saenz Julienne Acked-by: Minchan Kim Cc: Matthew Wilcox Cc: Mel Gorman Cc: Juri Lelli Cc: Thomas Gleixner Cc: Sebastian Andrzej Siewior Cc: Paul E. McKenney Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/swap.c | 23 ++++++++++++++--------- 1 file changed, 14 insertions(+), 9 deletions(-) (limited to 'mm/swap.c') diff --git a/mm/swap.c b/mm/swap.c index e9786c4f36d8..754520bab299 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -831,8 +831,7 @@ inline void __lru_add_drain_all(bool force_all_cpus) for_each_online_cpu(cpu) { struct work_struct *work = &per_cpu(lru_add_drain_work, cpu); - if (force_all_cpus || - pagevec_count(&per_cpu(lru_pvecs.lru_add, cpu)) || + if (pagevec_count(&per_cpu(lru_pvecs.lru_add, cpu)) || data_race(pagevec_count(&per_cpu(lru_rotate.pvec, cpu))) || pagevec_count(&per_cpu(lru_pvecs.lru_deactivate_file, cpu)) || pagevec_count(&per_cpu(lru_pvecs.lru_deactivate, cpu)) || @@ -876,15 +875,21 @@ atomic_t lru_disable_count = ATOMIC_INIT(0); void lru_cache_disable(void) { atomic_inc(&lru_disable_count); -#ifdef CONFIG_SMP /* - * lru_add_drain_all in the force mode will schedule draining on - * all online CPUs so any calls of lru_cache_disabled wrapped by - * local_lock or preemption disabled would be ordered by that. - * The atomic operation doesn't need to have stronger ordering - * requirements because that is enforced by the scheduling - * guarantees. + * Readers of lru_disable_count are protected by either disabling + * preemption or rcu_read_lock: + * + * preempt_disable, local_irq_disable [bh_lru_lock()] + * rcu_read_lock [rt_spin_lock CONFIG_PREEMPT_RT] + * preempt_disable [local_lock !CONFIG_PREEMPT_RT] + * + * Since v5.1 kernel, synchronize_rcu() is guaranteed to wait on + * preempt_disable() regions of code. So any CPU which sees + * lru_disable_count = 0 will have exited the critical + * section when synchronize_rcu() returns. */ + synchronize_rcu(); +#ifdef CONFIG_SMP __lru_add_drain_all(true); #else lru_add_and_bh_lrus_drain(); -- cgit v1.2.3