Bugzilla: 1074235 Upstream-status: 3.15 and CC'd to stable From e39435ce68bb4685288f78b1a7e24311f7ef939f Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 8 Apr 2014 16:04:12 -0700 Subject: [PATCH] lib/percpu_counter.c: fix bad percpu counter state during suspend I got a bug report yesterday from Laszlo Ersek in which he states that his kvm instance fails to suspend. Laszlo bisected it down to this commit 1cf7e9c68fe8 ("virtio_blk: blk-mq support") where virtio-blk is converted to use the blk-mq infrastructure. After digging a bit, it became clear that the issue was with the queue drain. blk-mq tracks queue usage in a percpu counter, which is incremented on request alloc and decremented when the request is freed. The initial hunt was for an inconsistency in blk-mq, but everything seemed fine. In fact, the counter only returned crazy values when suspend was in progress. When a CPU is unplugged, the percpu counters merges that CPU state with the general state. blk-mq takes care to register a hotcpu notifier with the appropriate priority, so we know it runs after the percpu counter notifier. However, the percpu counter notifier only merges the state when the CPU is fully gone. This leaves a state transition where the CPU going away is no longer in the online mask, yet it still holds private values. This means that in this state, percpu_counter_sum() returns invalid results, and the suspend then hangs waiting for abs(dead-cpu-value) requests to complete which of course will never happen. Fix this by clearing the state earlier, so we never have a case where the CPU isn't in online mask but still holds private state. This bug has been there since forever, I guess we don't have a lot of users where percpu counters needs to be reliable during the suspend cycle. Signed-off-by: Jens Axboe Reported-by: Laszlo Ersek Tested-by: Laszlo Ersek Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- lib/percpu_counter.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/lib/percpu_counter.c b/lib/percpu_counter.c index 8280a5dd1727..7dd33577b905 100644 --- a/lib/percpu_counter.c +++ b/lib/percpu_counter.c @@ -169,7 +169,7 @@ static int percpu_counter_hotcpu_callback(struct notifier_block *nb, struct percpu_counter *fbc; compute_batch_value(); - if (action != CPU_DEAD) + if (action != CPU_DEAD && action != CPU_DEAD_FROZEN) return NOTIFY_OK; cpu = (unsigned long)hcpu; -- 1.8.5.3