Messages in this thread | | | Date | Tue, 21 Jan 2014 15:51:05 +0100 | From | Peter Zijlstra <> | Subject | Re: x86: Inconsistent xAPIC synchronization in arch_irq_work_raise? |
| |
On Tue, Jan 21, 2014 at 03:01:13PM +0100, Peter Zijlstra wrote: > On Tue, Jan 21, 2014 at 02:02:06PM +0100, Jan Kiszka wrote: > > Hi all, > > > > while trying to plug a race in the CPU hotplug code on xAPIC systems, I > > was analyzing IPI transmission patterns. The handlers in > > arch/x86/include/asm/ipi.h first wait for ICR, then send. In contrast, > > arch_irq_work_raise sends the self-IPI directly and then waits. This > > looks inconsistent. Is it intended? > > > > BTW, the races are in wakeup_secondary_cpu_via_init and > > wakeup_secondary_cpu_via_nmi (lacking IRQ disable around ICR accesses). > > There we also send first, then wait for completion. But I guess that is > > due to the code originally only being used during boot. Will send fixes > > for those once the sync pattern is clear to me. > > Could be I had no clue what I was doing and copy/pasted the code until > it compiled and ran. > > In fact, I've got no clue what an ICR is.
I dug about a bit, I borrowed that code from:
lkml.kernel.org/r/1277348698-17311-3-git-send-email-ying.huang@intel.com
Huang Ying, can you explain to Jan why you do the wait afterwards?
| |