[GIT PULL] workqueue fixes for v5.13-rc3

[Tejun Heo]

Hello, Linus.

One commit to fix spurious workqueue stall warnings across VM suspensions.

Thanks.

The following changes since commit c3d0e3fd41b7f0f5d5d5b6022ab7e813f04ea727:

  Merge tag 'fs.idmapped.mount_setattr.v5.13-rc3' of gitolite.kernel.org:pub/scm/linux/kernel/git/brauner/linux (2021-05-19 06:12:31 -1000)

are available in the Git repository at:

  git://git.kernel.org/pub/scm/linux/kernel/git/tj/wq.git for-5.13-fixes

for you to fetch changes up to 940d71c6462e8151c78f28e4919aa8882ff2054e:

  wq: handle VM suspension in stall detection (2021-05-20 12:58:30 -0400)

----------------------------------------------------------------
Sergey Senozhatsky (1):
      wq: handle VM suspension in stall detection

 kernel/workqueue.c | 12 ++++++++++--
 1 file changed, 10 insertions(+), 2 deletions(-)

diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index b19d759e55a5..50142fc08902 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -50,6 +50,7 @@
 #include <linux/uaccess.h>
 #include <linux/sched/isolation.h>
 #include <linux/nmi.h>
+#include <linux/kvm_para.h>
 
 #include "workqueue_internal.h"
 
@@ -5772,6 +5773,7 @@ static void wq_watchdog_timer_fn(struct timer_list *unused)
 {
 	unsigned long thresh = READ_ONCE(wq_watchdog_thresh) * HZ;
 	bool lockup_detected = false;
+	unsigned long now = jiffies;
 	struct worker_pool *pool;
 	int pi;
 
@@ -5786,6 +5788,12 @@ static void wq_watchdog_timer_fn(struct timer_list *unused)
 		if (list_empty(&pool->worklist))
 			continue;
 
+		/*
+		 * If a virtual machine is stopped by the host it can look to
+		 * the watchdog like a stall.
+		 */
+		kvm_check_and_clear_guest_paused();
+
 		/* get the latest of pool and touched timestamps */
 		if (pool->cpu >= 0)
 			touched = READ_ONCE(per_cpu(wq_watchdog_touched_cpu, pool->cpu));
@@ -5799,12 +5807,12 @@ static void wq_watchdog_timer_fn(struct timer_list *unused)
 			ts = touched;
 
 		/* did we stall? */
-		if (time_after(jiffies, ts + thresh)) {
+		if (time_after(now, ts + thresh)) {
 			lockup_detected = true;
 			pr_emerg("BUG: workqueue lockup - pool");
 			pr_cont_pool_info(pool);
 			pr_cont(" stuck for %us!\n",
-				jiffies_to_msecs(jiffies - pool_ts) / 1000);
+				jiffies_to_msecs(now - pool_ts) / 1000);
 		}
 	}