Re: [PATCH v2 07/23] sched/cache: Introduce per runqueue task LLC preference counter

[Tim Chen <tim.c.chen@linux.intel.com>]

On Tue, 2025-12-09 at 14:06 +0100, Peter Zijlstra wrote:
> On Wed, Dec 03, 2025 at 03:07:26PM -0800, Tim Chen wrote:
> 
> > +#ifdef CONFIG_SCHED_CACHE
> > +
> > +static unsigned int *alloc_new_pref_llcs(unsigned int *old, unsigned int **gc)
> > +{
> > +	unsigned int *new = NULL;
> > +
> > +	new = kcalloc(new_max_llcs, sizeof(unsigned int),
> > +		      GFP_KERNEL | __GFP_NOWARN);
> > +
> > +	if (!new) {
> > +		*gc = NULL;
> > +	} else {
> > +		/*
> > +		 * Place old entry in garbage collector
> > +		 * for later disposal.
> > +		 */
> > +		*gc = old;
> > +	}
> > +	return new;
> > +}
> > +
> > +static void populate_new_pref_llcs(unsigned int *old, unsigned int *new)
> > +{
> > +	int i;
> > +
> > +	if (!old)
> > +		return;
> > +
> > +	for (i = 0; i < max_llcs; i++)
> > +		new[i] = old[i];
> > +}
> > +
> > +static int resize_llc_pref(void)
> > +{
> > +	unsigned int *__percpu *tmp_llc_pref;
> > +	int i, ret = 0;
> > +
> > +	if (new_max_llcs <= max_llcs)
> > +		return 0;
> > +
> > +	/*
> > +	 * Allocate temp percpu pointer for old llc_pref,
> > +	 * which will be released after switching to the
> > +	 * new buffer.
> > +	 */
> > +	tmp_llc_pref = alloc_percpu_noprof(unsigned int *);
> > +	if (!tmp_llc_pref)
> > +		return -ENOMEM;
> > +
> > +	for_each_present_cpu(i)
> > +		*per_cpu_ptr(tmp_llc_pref, i) = NULL;
> > +
> > +	/*
> > +	 * Resize the per rq nr_pref_llc buffer and
> > +	 * switch to this new buffer.
> > +	 */
> > +	for_each_present_cpu(i) {
> > +		struct rq_flags rf;
> > +		unsigned int *new;
> > +		struct rq *rq;
> > +
> > +		rq = cpu_rq(i);
> > +		new = alloc_new_pref_llcs(rq->nr_pref_llc, per_cpu_ptr(tmp_llc_pref, i));
> > +		if (!new) {
> > +			ret = -ENOMEM;
> > +
> > +			goto release_old;
> > +		}
> > +
> > +		/*
> > +		 * Locking rq ensures that rq->nr_pref_llc values
> > +		 * don't change with new task enqueue/dequeue
> > +		 * when we repopulate the newly enlarged array.
> > +		 */
> 
> 		guard(rq_lock_irq)(rq);
> 
> Notably, this cannot be with IRQs disabled, as you're doing allocations.

Okay.

> 
> > +		rq_lock_irqsave(rq, &rf);
> > +		populate_new_pref_llcs(rq->nr_pref_llc, new);
> > +		rq->nr_pref_llc = new;
> > +		rq_unlock_irqrestore(rq, &rf);
> > +	}
> > +
> > +release_old:
> > +	/*
> > +	 * Load balance is done under rcu_lock.
> > +	 * Wait for load balance before and during resizing to
> > +	 * be done. They may refer to old nr_pref_llc[]
> > +	 * that hasn't been resized.
> > +	 */
> > +	synchronize_rcu();
> > +	for_each_present_cpu(i)
> > +		kfree(*per_cpu_ptr(tmp_llc_pref, i));
> > +
> > +	free_percpu(tmp_llc_pref);
> > +
> > +	/* succeed and update */
> > +	if (!ret)
> > +		max_llcs = new_max_llcs;
> > +
> > +	return ret;
> > +}
> 
> I think you need at least cpus_read_lock(), because present_cpu is
> dynamic -- but I'm not quite sure what lock is used to serialize it.

Let me check on what is the right lock for making sure present_cpu
is not chenged.  Thanks.

Tim