Avi Kivity wrote:
On 02/24/2010 11:41 AM, Jan Kiszka wrote:Yep.
Thomas Gleixner wrote:So what's the core issue? Is the lock_t in the wait_queue a sleeping mutex?
On Tue, 23 Feb 2010, Jan Kiszka wrote:Yes, it's a wake queue.
Thomas Gleixner wrote:Hmm, a wakeup itself is fine. Is that code waking a wake queue ?
The i8254/i8259 locks need to be real spinlocks on preempt-rt. ConvertDoesn't fly for -rt anymore: pic_irq_update runs under this raw lock and
them to raw_spinlock. No change for !RT kernels.
calls kvm_vcpu_kick which tries to wake_up some thread -> scheduling
while atomic.