Re: [PATCH v2] powerpc: Fix smp_send_stop NMI IPI handling

2018-04-26 Thread Nicholas Piggin
On Thu, 26 Apr 2018 20:30:37 +1000 Michael Ellerman wrote: > Nicholas Piggin writes: > > The NMI IPI handler for a receiving CPU increments nmi_ipi_busy_count > > over the handler function call, which causes later smp_send_nmi_ipi() > > callers to spin until the call is finished. > > > > The smp

Re: [PATCH v2] powerpc: Fix smp_send_stop NMI IPI handling

2018-04-26 Thread Michael Ellerman
Nicholas Piggin writes: > The NMI IPI handler for a receiving CPU increments nmi_ipi_busy_count > over the handler function call, which causes later smp_send_nmi_ipi() > callers to spin until the call is finished. > > The smp_send_stop function never returns, so the busy count is never > decremete

[PATCH v2] powerpc: Fix smp_send_stop NMI IPI handling

2018-04-25 Thread Nicholas Piggin
The NMI IPI handler for a receiving CPU increments nmi_ipi_busy_count over the handler function call, which causes later smp_send_nmi_ipi() callers to spin until the call is finished. The smp_send_stop function never returns, so the busy count is never decremeted, which can cause the system to han