Re: [PATCH v7 09/12] mm/demotion: Demote pages according to allocation fallback order

[Alistair Popple <apopple@nvidia.com>]

"Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com> writes:

> From: Jagdish Gediya <jvgediya@linux.ibm.com>

[...]

> -static struct page *alloc_demote_page(struct page *page, unsigned long node)
> +static struct page *alloc_demote_page(struct page *page, unsigned long private)
>  {
> -	struct migration_target_control mtc = {
> -		/*
> -		 * Allocate from 'node', or fail quickly and quietly.
> -		 * When this happens, 'page' will likely just be discarded
> -		 * instead of migrated.
> -		 */
> -		.gfp_mask = (GFP_HIGHUSER_MOVABLE & ~__GFP_RECLAIM) |
> -			    __GFP_THISNODE  | __GFP_NOWARN |
> -			    __GFP_NOMEMALLOC | GFP_NOWAIT,
> -		.nid = node
> -	};
> +	struct page *target_page;
> +	nodemask_t *allowed_mask;
> +	struct migration_target_control *mtc;
> +
> +	mtc = (struct migration_target_control *)private;
> +
> +	allowed_mask = mtc->nmask;
> +	/*
> +	 * make sure we allocate from the target node first also trying to
> +	 * reclaim pages from the target node via kswapd if we are low on
> +	 * free memory on target node. If we don't do this and if we have low
> +	 * free memory on the target memtier, we would start allocating pages
> +	 * from higher memory tiers without even forcing a demotion of cold
> +	 * pages from the target memtier. This can result in the kernel placing
> +	 * hotpages in higher memory tiers.
> +	 */
> +	mtc->nmask = NULL;
> +	mtc->gfp_mask |= __GFP_THISNODE;
> +	target_page = alloc_migration_target(page, (unsigned long)&mtc);

I finally managed to get a system setup to start testing some of this
out. However it quickly crashed due to the bad pointer in the above call
- you need mtc not &mtc here.

> +	if (target_page)
> +		return target_page;
> +
> +	mtc->gfp_mask &= ~__GFP_THISNODE;
> +	mtc->nmask = allowed_mask;
>
>  	return alloc_migration_target(page, (unsigned long)&mtc);

And here.

>  }
> @@ -1487,6 +1500,19 @@ static unsigned int demote_page_list(struct list_head *demote_pages,
>  {
>  	int target_nid = next_demotion_node(pgdat->node_id);
>  	unsigned int nr_succeeded;
> +	nodemask_t allowed_mask;
> +
> +	struct migration_target_control mtc = {
> +		/*
> +		 * Allocate from 'node', or fail quickly and quietly.
> +		 * When this happens, 'page' will likely just be discarded
> +		 * instead of migrated.
> +		 */
> +		.gfp_mask = (GFP_HIGHUSER_MOVABLE & ~__GFP_RECLAIM) | __GFP_NOWARN |
> +			__GFP_NOMEMALLOC | GFP_NOWAIT,
> +		.nid = target_nid,
> +		.nmask = &allowed_mask
> +	};
>
>  	if (list_empty(demote_pages))
>  		return 0;
> @@ -1494,10 +1520,12 @@ static unsigned int demote_page_list(struct list_head *demote_pages,
>  	if (target_nid == NUMA_NO_NODE)
>  		return 0;
>
> +	node_get_allowed_targets(pgdat, &allowed_mask);
> +
>  	/* Demotion ignores all cpuset and mempolicy settings */
>  	migrate_pages(demote_pages, alloc_demote_page, NULL,
> -			    target_nid, MIGRATE_ASYNC, MR_DEMOTION,
> -			    &nr_succeeded);
> +		      (unsigned long)&mtc, MIGRATE_ASYNC, MR_DEMOTION,
> +		      &nr_succeeded);
>
>  	if (current_is_kswapd())
>  		__count_vm_events(PGDEMOTE_KSWAPD, nr_succeeded);