This commit pushes the grace-period-end checks further down into rcu_dump_cpu_stacks(), and also uses lockless checks coupled with finer-grained locking.
The result is that the current leaf rcu_node structure's ->lock is acquired only if a stack backtrace might be needed from the current CPU, and is held across only that CPU's backtrace. As a result, if there are no stalled CPUs associated with a given rcu_node structure, then its ->lock will not be acquired at all. On large systems, it is usually (though not always) the case that a small number of CPUs are stalling the current grace period, which means that the ->lock need be acquired only for a small fraction of the rcu_node structures. Signed-off-by: Paul E. McKenney <paul...@kernel.org> --- kernel/rcu/tree_stall.h | 18 +++++++++++------- 1 file changed, 11 insertions(+), 7 deletions(-) diff --git a/kernel/rcu/tree_stall.h b/kernel/rcu/tree_stall.h index 9d79133377ff6..8994391b95c76 100644 --- a/kernel/rcu/tree_stall.h +++ b/kernel/rcu/tree_stall.h @@ -342,20 +342,24 @@ static void rcu_dump_cpu_stacks(unsigned long gp_seq) struct rcu_node *rnp; rcu_for_each_leaf_node(rnp) { - if (gp_seq != rcu_state.gp_seq) { - pr_err("INFO: Stall ended during stack backtracing.\n"); - return; - } printk_deferred_enter(); - raw_spin_lock_irqsave_rcu_node(rnp, flags); - for_each_leaf_node_possible_cpu(rnp, cpu) + for_each_leaf_node_possible_cpu(rnp, cpu) { + if (gp_seq != data_race(rcu_state.gp_seq)) { + printk_deferred_exit(); + pr_err("INFO: Stall ended during stack backtracing.\n"); + return; + } + if (!(data_race(rnp->qsmask) & leaf_node_cpu_bit(rnp, cpu))) + continue; + raw_spin_lock_irqsave_rcu_node(rnp, flags); if (rnp->qsmask & leaf_node_cpu_bit(rnp, cpu)) { if (cpu_is_offline(cpu)) pr_err("Offline CPU %d blocking current GP.\n", cpu); else dump_cpu_task(cpu); + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); } - raw_spin_unlock_irqrestore_rcu_node(rnp, flags); + } printk_deferred_exit(); } } -- 2.40.1