From: Benjamin Segall <bsegall@xxxxxxxxxx> commit 262de4102c7bb8e59f26a967a8ffe8cce85cc537 upstream. single_task_running() is usually more general than need_resched() but CFS_BANDWIDTH throttling will use resched_task() when there is just one task to get the task to block. This was causing long-need_resched warnings and was likely allowing VMs to overrun their quota when halt polling. Signed-off-by: Ben Segall <bsegall@xxxxxxxxxx> Signed-off-by: Venkatesh Srinivas <venkateshs@xxxxxxxxxxxx> Message-Id: <20210429162233.116849-1-venkateshs@xxxxxxxxxxxx> Signed-off-by: Paolo Bonzini <pbonzini@xxxxxxxxxx> Cc: stable@xxxxxxxxxxxxxxx Reviewed-by: Jim Mattson <jmattson@xxxxxxxxxx> Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx> --- virt/kvm/kvm_main.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -2797,7 +2797,8 @@ void kvm_vcpu_block(struct kvm_vcpu *vcp goto out; } poll_end = cur = ktime_get(); - } while (single_task_running() && ktime_before(cur, stop)); + } while (single_task_running() && !need_resched() && + ktime_before(cur, stop)); } prepare_to_rcuwait(&vcpu->wait);
