From c81f94023e66b7beca81ad9e457cd434b0c37dab Mon Sep 17 00:00:00 2001 From: Mike Marciniszyn Date: Fri, 14 Jun 2019 12:32:26 -0400 Subject: [PATCH] IB/hfi1: Avoid hardlockup with flushlist_lock BugLink: https://bugs.launchpad.net/bugs/1844558 [ Upstream commit cf131a81967583ae737df6383a0893b9fee75b4e ] Heavy contention of the sde flushlist_lock can cause hard lockups at extreme scale when the flushing logic is under stress. Mitigate by replacing the item at a time copy to the local list with an O(1) list_splice_init() and using the high priority work queue to do the flushes. Fixes: 7724105686e7 ("IB/hfi1: add driver files") Cc: Reviewed-by: Dennis Dalessandro Signed-off-by: Mike Marciniszyn Signed-off-by: Dennis Dalessandro Signed-off-by: Doug Ledford Signed-off-by: Sasha Levin Signed-off-by: Kamal Mostafa Signed-off-by: Khalid Elmously --- drivers/infiniband/hw/hfi1/sdma.c | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-) diff --git a/drivers/infiniband/hw/hfi1/sdma.c b/drivers/infiniband/hw/hfi1/sdma.c index 31c8f89b5fc8..b9086144891a 100644 --- a/drivers/infiniband/hw/hfi1/sdma.c +++ b/drivers/infiniband/hw/hfi1/sdma.c @@ -410,10 +410,7 @@ static void sdma_flush(struct sdma_engine *sde) sdma_flush_descq(sde); spin_lock_irqsave(&sde->flushlist_lock, flags); /* copy flush list */ - list_for_each_entry_safe(txp, txp_next, &sde->flushlist, list) { - list_del_init(&txp->list); - list_add_tail(&txp->list, &flushlist); - } + list_splice_init(&sde->flushlist, &flushlist); spin_unlock_irqrestore(&sde->flushlist_lock, flags); /* flush from flush list */ list_for_each_entry_safe(txp, txp_next, &flushlist, list) @@ -2430,7 +2427,7 @@ unlock_noconn: wait->tx_count++; wait->count += tx->num_desc; } - schedule_work(&sde->flush_worker); + queue_work_on(sde->cpu, system_highpri_wq, &sde->flush_worker); ret = -ECOMM; goto unlock; nodesc: @@ -2530,7 +2527,7 @@ unlock_noconn: } } spin_unlock(&sde->flushlist_lock); - schedule_work(&sde->flush_worker); + queue_work_on(sde->cpu, system_highpri_wq, &sde->flush_worker); ret = -ECOMM; goto update_tail; nodesc: -- 2.39.2