[PATCH v8 4/4] arm64: switch to irq_stack during softirq

[Jungseok Lee]

On Dec 4, 2015, at 11:39 PM, James Morse wrote:

Hi James,

> Hi Catalin,
> 
> On 04/12/15 14:01, Catalin Marinas wrote:
>> On Fri, Dec 04, 2015 at 11:02:28AM +0000, James Morse wrote:
>>> +ENTRY(__do_softirq_on_irqstack)
>>> +	push	x19, lr
>>> +	push	x25, x26
>>> +
>>> +	irq_stack_entry lr
>>> +
>>> +	/* irq_stack_entry leaves irq_count in x25 */
>>> +	ldr	x1, [x25]
>>> +	add	x1, x1, #1
>>> +	str	x1, [x25]
>>> +
>>> +	bl	__do_softirq
>>> +
>>> +	ldr	x1, [x25]
>>> +	sub	x1, x1, #1
>>> +	str	x1, [x25]
>>> +
>>> +	irq_stack_exit
>>> +
>>> +	pop x25, x26
>>> +	pop x19, lr
>>> +	ret
>>> +ENDPROC(__do_softirq_on_irqstack)
>> 
>> I was thinking of doing do_softirq_own_stack() entirely in assembly
>> without the need to check for on_irq_stack() check in C, just a test of
>> the irq_count value.
> 
> I tried that, but couldn't get it to work - maybe I'm missing a trick:
> 
> There are at least two ways into do_softirq_own_stack():
> el1_irq() -> __irq_exit() -> do_softirq_own_stack(),
> as well as:
> cpu_switch_to(ksoftirqd) -> do_softirq_own_stack()
> 
> In both cases irq_count == 0 because do_softirq_own_stack() is where we
> update irq_count [0]. I can only see two ways to tell them apart,
> increment irq_count in el1_irq(), (which we don't like), or have that
> bounds checking.
> 
> 
> (We could increase hardirq_count() in el?_irq(), which would mean
> in_irq()/in_interrupt() always returns true when on the irq_stack, which
> would stop softirqs being processed here... but that is a fairly
> significant change in behavior.)

It is not simple to utilize preempt_count which is based on task for stack
switching based on core. Unluckily, I cannot give a specific challenge I've
experienced.

From implementation perspective, I think it is an advantage to use tpidr_el1
for percpu variables. But, preempt_count based approach might not utilize it.

Best Regards
Jungseok Lee