On 08/07/2017 06:10 PM, Paul E. McKenney wrote:
On Mon, Aug 07, 2017 at 11:20:10AM +0530, Neeraj Upadhyay wrote:Pending cbs check in rcu_prepare_for_idle is inversed in the sense that, it should accelerate if there are pending cbs; but, the check does the opposite. So, fix it. Fixes: 15fecf89e46a ("srcu: Abstract multi-tail callback list handling") Signed-off-by: Neeraj Upadhyay <neer...@codeaurora.org>Good catch! Queued for review and testing. Just out of curiosity, how did you find this one? Thanx, Paul
Hi Paul, found the issue while reading the code.
--- kernel/rcu/tree_plugin.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index 908b309..b8f51df 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -1493,7 +1493,7 @@ static void rcu_prepare_for_idle(void) rdtp->last_accelerate = jiffies; for_each_rcu_flavor(rsp) { rdp = this_cpu_ptr(rsp->rda); - if (rcu_segcblist_pend_cbs(&rdp->cblist)) + if (!rcu_segcblist_pend_cbs(&rdp->cblist)) continue; rnp = rdp->mynode; raw_spin_lock_rcu_node(rnp); /* irqs already disabled. */ -- QUALCOMM INDIA, on behalf of Qualcomm Innovation Center, Inc. is a member of the Code Aurora Forum, hosted by The Linux Foundation
-- QUALCOMM INDIA, on behalf of Qualcomm Innovation Center, Inc. is a member of the Code Aurora Forum, hosted by The Linux Foundation
