On Wed, Sep 09, 2020 at 05:09:31PM +0800, qianjun.kernel@gmail.com wrote:
> From: jun qian <qianjun.kernel@gmail.com>
> 
> When get the pending softirqs, it need to process all the pending
> softirqs in the while loop. If the processing time of each pending
> softirq is need more than 2 msec in this loop, or one of the softirq
> will running a long time, according to the original code logic, it
> will process all the pending softirqs without wakeuping ksoftirqd,
> which will cause a relatively large scheduling delay on the
> corresponding CPU, which we do not wish to see. The patch will check
> the total time to process pending softirq, if the time exceeds 2 ms
> we need to wakeup the ksofirqd to aviod large sched delay.

But what is all that unreadaable gibberish with pending_new_{flag,bit} ?

Random comments below..


> +#define MAX_SOFTIRQ_TIME_NS 2000000

	2*NSEC_PER_MSEC


> +DEFINE_PER_CPU(__u32, pending_new_flag);
> +DEFINE_PER_CPU(__u32, pending_next_bit);

__u32 is for userspace ABI, this is not it, use u32

> +#define SOFTIRQ_PENDING_MASK ((1UL << NR_SOFTIRQS) - 1)
> +
>  asmlinkage __visible void __softirq_entry __do_softirq(void)
>  {
> -	unsigned long end = jiffies + MAX_SOFTIRQ_TIME;
> +	u64 end = sched_clock() + MAX_SOFTIRQ_TIME_NS;
>  	unsigned long old_flags = current->flags;
>  	int max_restart = MAX_SOFTIRQ_RESTART;
>  	struct softirq_action *h;
>  	bool in_hardirq;
> -	__u32 pending;
> -	int softirq_bit;
> +	__u32 pending, pending_left, pending_new;
> +	int softirq_bit, next_bit;
> +	unsigned long flags;
>  
>  	/*
>  	 * Mask out PF_MEMALLOC as the current task context is borrowed for the
> @@ -277,10 +282,33 @@ asmlinkage __visible void __softirq_entry __do_softirq(void)
>  
>  	h = softirq_vec;
>  
> -	while ((softirq_bit = ffs(pending))) {
> -		unsigned int vec_nr;
> +	next_bit = per_cpu(pending_next_bit, smp_processor_id());
> +	per_cpu(pending_new_flag, smp_processor_id()) = 0;

	__this_cpu_read() / __this_cpu_write()

> +
> +	pending_left = pending &
> +		(SOFTIRQ_PENDING_MASK << next_bit);
> +	pending_new = pending &
> +		(SOFTIRQ_PENDING_MASK >> (NR_SOFTIRQS - next_bit));

The second mask is the inverse of the first.

> +	/*
> +	 * In order to be fair, we shold process the pengding bits by the
> +	 * last processing order.
> +	 */
> +	while ((softirq_bit = ffs(pending_left)) ||
> +		(softirq_bit = ffs(pending_new))) {
>  		int prev_count;
> +		unsigned int vec_nr = 0;
>  
> +		/*
> +		 * when the left pengding bits have been handled, we should
> +		 * to reset the h to softirq_vec.
> +		 */
> +		if (!ffs(pending_left)) {
> +			if (per_cpu(pending_new_flag, smp_processor_id()) == 0) {
> +				h = softirq_vec;
> +				per_cpu(pending_new_flag, smp_processor_id()) = 1;
> +			}
> +		}
>  		h += softirq_bit - 1;
>  
>  		vec_nr = h - softirq_vec;
> @@ -298,17 +326,44 @@ asmlinkage __visible void __softirq_entry __do_softirq(void)
>  			preempt_count_set(prev_count);
>  		}
>  		h++;
> -		pending >>= softirq_bit;
> +
> +		if (ffs(pending_left))

This is the _third_ ffs(pending_left), those things are _expensive_ (on
some archs, see include/asm-generic/bitops/__ffs.h).

> +			pending_left >>= softirq_bit;
> +		else
> +			pending_new >>= softirq_bit;
> +
> +		/*
> +		 * the softirq's action has been run too much time,
> +		 * so it may need to wakeup the ksoftirqd
> +		 */
> +		if (need_resched() && sched_clock() > end) {
> +			/*
> +			 * Ensure that the remaining pending bits will be
> +			 * handled.
> +			 */
> +			local_irq_save(flags);
> +			if (ffs(pending_left))

*fourth*...

> +				or_softirq_pending((pending_left << (vec_nr + 1)) |
> +							pending_new);
> +			else
> +				or_softirq_pending(pending_new << (vec_nr + 1));
> +			local_irq_restore(flags);
> +			per_cpu(pending_next_bit, smp_processor_id()) = vec_nr + 1;
> +			break;
> +		}
>  	}
>  
> +	/* reset the pending_next_bit */
> +	per_cpu(pending_next_bit, smp_processor_id()) = 0;
> +
>  	if (__this_cpu_read(ksoftirqd) == current)
>  		rcu_softirq_qs();
>  	local_irq_disable();
>  
>  	pending = local_softirq_pending();
>  	if (pending) {
> -		if (time_before(jiffies, end) && !need_resched() &&
> -		    --max_restart)
> +		if (!need_resched() && --max_restart &&
> +		    sched_clock() <= end)
>  			goto restart;
>  
>  		wakeup_softirqd();

This really wants to be a number of separate patches; and I quickly lost
the plot in your code. Instead of cleaning things up, you're making an
even bigger mess of things.

That said, I _think_ I've managed to decode what you want. See the
completely untested patches attached.