Re: [PATCH 5/7] mm: move zone iterator outside of deferred_init_maxorder()

[Alexander Duyck]

On 4/30/2020 1:11 PM, Daniel Jordan wrote:
> padata will soon divide up pfn ranges between threads when parallelizing
> deferred init, and deferred_init_maxorder() complicates that by using an
> opaque index in addition to start and end pfns.  Move the index outside
> the function to make splitting the job easier, and simplify the code
> while at it.
>
> deferred_init_maxorder() now always iterates within a single pfn range
> instead of potentially multiple ranges, and advances start_pfn to the
> end of that range instead of the max-order block so partial pfn ranges
> in the block aren't skipped in a later iteration.  The section alignment
> check in deferred_grow_zone() is removed as well since this alignment is
> no longer guaranteed.  It's not clear what value the alignment provided
> originally.
>
> Signed-off-by: Daniel Jordan <daniel.m.jordan@xxxxxxxxxx>

So part of the reason for splitting it up along section aligned 
boundaries was because we already had an existing functionality in 
deferred_grow_zone that was going in and pulling out a section aligned 
chunk and processing it to prepare enough memory for other threads to 
keep running. I suspect that the section alignment was done because 
normally I believe that is also the alignment for memory onlining.

With this already breaking things up over multiple threads how does this 
work with deferred_grow_zone? Which thread is it trying to allocate from 
if it needs to allocate some memory for itself?

Also what is to prevent a worker from stop deferred_grow_zone from 
bailing out in the middle of a max order page block if there is a hole 
in the middle of the block?

> ---
>   mm/page_alloc.c | 88 +++++++++++++++----------------------------------
>   1 file changed, 27 insertions(+), 61 deletions(-)
>
> diff --git a/mm/page_alloc.c b/mm/page_alloc.c
> index 68669d3a5a665..990514d8f0d94 100644
> --- a/mm/page_alloc.c
> +++ b/mm/page_alloc.c
> @@ -1708,55 +1708,23 @@ deferred_init_mem_pfn_range_in_zone(u64 *i, struct zone *zone,
>   }
>   
>   /*
> - * Initialize and free pages. We do it in two loops: first we initialize
> - * struct page, then free to buddy allocator, because while we are
> - * freeing pages we can access pages that are ahead (computing buddy
> - * page in __free_one_page()).
> - *
> - * In order to try and keep some memory in the cache we have the loop
> - * broken along max page order boundaries. This way we will not cause
> - * any issues with the buddy page computation.
> + * Initialize the struct pages and then free them to the buddy allocator at
> + * most a max order block at a time because while we are freeing pages we can
> + * access pages that are ahead (computing buddy page in __free_one_page()).
> + * It's also cache friendly.
>    */
>   static unsigned long __init
> -deferred_init_maxorder(u64 *i, struct zone *zone, unsigned long *start_pfn,
> -		       unsigned long *end_pfn)
> +deferred_init_maxorder(struct zone *zone, unsigned long *start_pfn,
> +		       unsigned long end_pfn)
>   {
> -	unsigned long mo_pfn = ALIGN(*start_pfn + 1, MAX_ORDER_NR_PAGES);
> -	unsigned long spfn = *start_pfn, epfn = *end_pfn;
> -	unsigned long nr_pages = 0;
> -	u64 j = *i;
> -
> -	/* First we loop through and initialize the page values */
> -	for_each_free_mem_pfn_range_in_zone_from(j, zone, start_pfn, end_pfn) {
> -		unsigned long t;
> -
> -		if (mo_pfn <= *start_pfn)
> -			break;
> -
> -		t = min(mo_pfn, *end_pfn);
> -		nr_pages += deferred_init_pages(zone, *start_pfn, t);
> -
> -		if (mo_pfn < *end_pfn) {
> -			*start_pfn = mo_pfn;
> -			break;
> -		}
> -	}
> -
> -	/* Reset values and now loop through freeing pages as needed */
> -	swap(j, *i);
> -
> -	for_each_free_mem_pfn_range_in_zone_from(j, zone, &spfn, &epfn) {
> -		unsigned long t;
> -
> -		if (mo_pfn <= spfn)
> -			break;
> +	unsigned long nr_pages, pfn;
>   
> -		t = min(mo_pfn, epfn);
> -		deferred_free_pages(spfn, t);
> +	pfn = ALIGN(*start_pfn + 1, MAX_ORDER_NR_PAGES);
> +	pfn = min(pfn, end_pfn);
>   
> -		if (mo_pfn <= epfn)
> -			break;
> -	}
> +	nr_pages = deferred_init_pages(zone, *start_pfn, pfn);
> +	deferred_free_pages(*start_pfn, pfn);
> +	*start_pfn = pfn;
>   
>   	return nr_pages;
>   }
> @@ -1814,9 +1782,11 @@ static int __init deferred_init_memmap(void *data)
>   	 * that we can avoid introducing any issues with the buddy
>   	 * allocator.
>   	 */
> -	while (spfn < epfn) {
> -		nr_pages += deferred_init_maxorder(&i, zone, &spfn, &epfn);
> -		cond_resched();
> +	for_each_free_mem_pfn_range_in_zone_from(i, zone, &spfn, &epfn) {
> +		while (spfn < epfn) {
> +			nr_pages += deferred_init_maxorder(zone, &spfn, epfn);
> +			cond_resched();
> +		}
>   	}
>   zone_empty:
>   	/* Sanity check that the next zone really is unpopulated */
> @@ -1883,22 +1853,18 @@ deferred_grow_zone(struct zone *zone, unsigned int order)
>   	 * that we can avoid introducing any issues with the buddy
>   	 * allocator.
>   	 */
> -	while (spfn < epfn) {
> -		/* update our first deferred PFN for this section */
> -		first_deferred_pfn = spfn;
> -
> -		nr_pages += deferred_init_maxorder(&i, zone, &spfn, &epfn);
> -		touch_nmi_watchdog();
> -
> -		/* We should only stop along section boundaries */
> -		if ((first_deferred_pfn ^ spfn) < PAGES_PER_SECTION)
> -			continue;
> -
> -		/* If our quota has been met we can stop here */
> -		if (nr_pages >= nr_pages_needed)
> -			break;
> +	for_each_free_mem_pfn_range_in_zone_from(i, zone, &spfn, &epfn) {
> +		while (spfn < epfn) {
> +			nr_pages += deferred_init_maxorder(zone, &spfn, epfn);
> +			touch_nmi_watchdog();
> +
> +			/* If our quota has been met we can stop here */
> +			if (nr_pages >= nr_pages_needed)
> +				goto out;
> +		}
>   	}
>   
> +out:
>   	pgdat->first_deferred_pfn = spfn;
>   	pgdat_resize_unlock(pgdat, &flags);
>