On Thu, 18 Jul 2019, Peter Zijlstra wrote:
> On Thu, Jul 18, 2019 at 11:58:47AM +0200, Thomas Gleixner wrote:
>
> As we discussed on IRC, it is worse, we can only use these functions
> from task/process context. We need something like the below.
Indeed that's better defined.
Thanks,
tgl
On Thu, Jul 18, 2019 at 11:58:47AM +0200, Thomas Gleixner wrote:
> Subject: smp: Warn on function calls from softirq context
> From: Thomas Gleixner
> Date: Thu, 18 Jul 2019 11:20:09 +0200
>
> It's clearly documented that smp function calls cannot be invoked from
> softirq handling context. Unfor
On Thu, 18 Jul 2019, luferry wrote:
> At 2019-07-18 16:07:58, "Thomas Gleixner" wrote:
> >On Thu, 18 Jul 2019, lufe...@163.com wrote:
> >
> >> From: luferry
> >>
> >> The race can reproduced by sending wait enabled IPI in softirq/irq env
> >
> >Which code path is doing that?
>
> I checked kernel
At 2019-07-18 16:07:58, "Thomas Gleixner" wrote:
>On Thu, 18 Jul 2019, lufe...@163.com wrote:
>
>> From: luferry
>>
>> The race can reproduced by sending wait enabled IPI in softirq/irq env
>
>Which code path is doing that?
>
>Thanks,
>
> tglx
Thanks for your kindly reply.
I che
On Thu, 18 Jul 2019, lufe...@163.com wrote:
> From: luferry
>
> The race can reproduced by sending wait enabled IPI in softirq/irq env
Which code path is doing that?
Thanks,
tglx
From: luferry
The race can reproduced by sending wait enabled IPI in softirq/irq env
src cpu only send ipi when dst cpu with queue empty, if interrupts
disturbed between llist_add and send_ipi. Interrupt handler may raise
softirq.In irq env, if src cpu try send_ipi to same dst cpu with
wait enab
6 matches
Mail list logo