fixes for 4.4

Signed-off-by: Sasha Levin <sashal@kernel.org>

diff --git a/queue-4.4/ib-hfi1-avoid-hardlockup-with-flushlist_lock.patch b/queue-4.4/ib-hfi1-avoid-hardlockup-with-flushlist_lock.patch
new file mode 100644 (file)
index 0000000..24ea5e8
--- /dev/null
+++ b/queue-4.4/ib-hfi1-avoid-hardlockup-with-flushlist_lock.patch
@@ -0,0 +1,62 @@
+From 90b648b15d12e81d307027414de915852ec0b558 Mon Sep 17 00:00:00 2001
+From: Mike Marciniszyn <mike.marciniszyn@intel.com>
+Date: Mon, 24 Jun 2019 11:56:02 -0400
+Subject: IB/hfi1: Avoid hardlockup with flushlist_lock
+
+[ 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: <stable@vger.kernel.org>
+Reviewed-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
+Signed-off-by: Mike Marciniszyn <mike.marciniszyn@intel.com>
+Signed-off-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
+Signed-off-by: Doug Ledford <dledford@redhat.com>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ drivers/staging/rdma/hfi1/sdma.c | 9 +++------
+ 1 file changed, 3 insertions(+), 6 deletions(-)
+
+diff --git a/drivers/staging/rdma/hfi1/sdma.c b/drivers/staging/rdma/hfi1/sdma.c
+index 2a1da2189900..68df64b6c2e4 100644
+--- a/drivers/staging/rdma/hfi1/sdma.c
++++ b/drivers/staging/rdma/hfi1/sdma.c
+@@ -390,10 +390,7 @@ 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) {
+@@ -2103,7 +2100,7 @@ int sdma_send_txreq(struct sdma_engine *sde,
+               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:
+@@ -2196,7 +2193,7 @@ int sdma_send_txlist(struct sdma_engine *sde,
+               }
+       }
+       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:
+-- 
+2.20.1
+

diff --git a/queue-4.4/series b/queue-4.4/series
index 531057bc0b8ce1bdba4a90f815d6413facd47f3f..407a92fa43acd5622df9ec181e8b72713f1fa8f1 100644 (file)
--- a/queue-4.4/series
+++ b/queue-4.4/series
@@ -23,3 +23,4 @@ bluetooth-fix-regression-with-minimum-encryption-key-size-alignment.patch
 smb3-retry-on-status_insufficient_resources-instead-of-failing-write.patch
 cfg80211-fix-memory-leak-of-wiphy-device-name.patch
 mac80211-drop-robust-management-frames-from-unknown-ta.patch
+ib-hfi1-avoid-hardlockup-with-flushlist_lock.patch