From 940d71c6462e8151c78f28e4919aa8882ff2054e Mon Sep 17 00:00:00 2001 From: Sergey Senozhatsky Date: Thu, 20 May 2021 19:14:22 +0900 Subject: [PATCH] wq: handle VM suspension in stall detection If VCPU is suspended (VM suspend) in wq_watchdog_timer_fn() then once this VCPU resumes it will see the new jiffies value, while it may take a while before IRQ detects PVCLOCK_GUEST_STOPPED on this VCPU and updates all the watchdogs via pvclock_touch_watchdogs(). There is a small chance of misreported WQ stalls in the meantime, because new jiffies is time_after() old 'ts + thresh'. wq_watchdog_timer_fn() { for_each_pool(pool, pi) { if (time_after(jiffies, ts + thresh)) { pr_emerg("BUG: workqueue lockup - pool"); } } } Save jiffies at the beginning of this function and use that value for stall detection. If VM gets suspended then we continue using "old" jiffies value and old WQ touch timestamps. If IRQ at some point restarts the stall detection cycle (pvclock_touch_watchdogs()) then old jiffies will always be before new 'ts + thresh'. Signed-off-by: Sergey Senozhatsky Signed-off-by: Tejun Heo --- 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 #include #include +#include #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); } }