Re: [RFC 1/6] mm, thp: introduce thp zero subpages reclaim

[Matthew Wilcox <willy@infradead.org>]

On Thu, Oct 28, 2021 at 07:56:50PM +0800, Ning Zhang wrote:
> +++ b/include/linux/huge_mm.h
> @@ -185,6 +185,15 @@ unsigned long thp_get_unmapped_area(struct file *filp, unsigned long addr,
>  void free_transhuge_page(struct page *page);
>  bool is_transparent_hugepage(struct page *page);
>  
> +#ifdef CONFIG_MEMCG
> +int zsr_get_hpage(struct hpage_reclaim *hr_queue, struct page **reclaim_page);
> +unsigned long zsr_reclaim_hpage(struct lruvec *lruvec, struct page *page);
> +static inline struct list_head *hpage_reclaim_list(struct page *page)
> +{
> +	return &page[3].hpage_reclaim_list;
> +}
> +#endif

I don't think any of this needs to be under an ifdef.  That goes for a
lot of your other additions to header files.

> @@ -1110,6 +1121,10 @@ unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order,
>  						gfp_t gfp_mask,
>  						unsigned long *total_scanned);
>  
> +#ifdef CONFIG_TRANSPARENT_HUGEPAGE
> +void del_hpage_from_queue(struct page *page);
> +#endif

That name is too generic.  Also, to avoid ifdefs in code, it should be:

#ifdef CONFIG_TRANSPARENT_HUGEPAGE
void del_hpage_from_queue(struct page *page);
#else
static inline void del_hpage_from_queue(struct page *page) { }
#endif

> @@ -159,6 +159,12 @@ struct page {
>  			/* For both global and memcg */
>  			struct list_head deferred_list;
>  		};
> +		struct {	 /* Third tail page of compound page */
> +			unsigned long _compound_pad_2;
> +			unsigned long _compound_pad_3;
> +			/* For zero subpages reclaim */
> +			struct list_head hpage_reclaim_list;

Why do you need _compound_pad_3 here?

> +++ b/include/linux/mmzone.h
> @@ -787,6 +787,12 @@ struct deferred_split {
>  	struct list_head split_queue;
>  	unsigned long split_queue_len;
>  };
> +
> +struct hpage_reclaim {
> +	spinlock_t reclaim_queue_lock;
> +	struct list_head reclaim_queue;
> +	unsigned long reclaim_queue_len;
> +};

Have you considered using an XArray instead of a linked list?

> +static bool hpage_estimate_zero(struct page *page)
> +{
> +	unsigned int i, maybe_zero_pages = 0, offset = 0;
> +	void *addr;
> +
> +#define BYTES_PER_LONG (BITS_PER_LONG / BITS_PER_BYTE)

BYTES_PER_LONG is simply sizeof(long).
Also, I'd check the entire cacheline rather than just one word; it's
essentially free.

> +#ifdef CONFIG_MMU
> +#define ZSR_PG_MLOCK(flag)	(1UL << flag)
> +#else
> +#define ZSR_PG_MLOCK(flag)	0
> +#endif

Or use __PG_MLOCKED ?

> +#ifdef CONFIG_ARCH_USES_PG_UNCACHED
> +#define ZSR_PG_UNCACHED(flag)	(1UL << flag)
> +#else
> +#define ZSR_PG_UNCACHED(flag)	0
> +#endif

Define __PG_UNCACHED in page-flags.h?

> +#ifdef CONFIG_MEMORY_FAILURE
> +#define ZSR_PG_HWPOISON(flag)	(1UL << flag)
> +#else
> +#define ZSR_PG_HWPOISON(flag)	0
> +#endif

__PG_HWPOISON

> +#define hr_queue_list_to_page(head) \
> +	compound_head(list_entry((head)->prev, struct page,\
> +		      hpage_reclaim_list))

I think you're better off subtracting 3*sizeof(struct page) than
loading from compound_head.

> +#ifdef CONFIG_TRANSPARENT_HUGEPAGE
> +/* Need the page lock if the page is not a newly allocated page. */
> +static void add_hpage_to_queue(struct page *page, struct mem_cgroup *memcg)
> +{
> +	struct hpage_reclaim *hr_queue;
> +	unsigned long flags;
> +
> +	if (READ_ONCE(memcg->thp_reclaim) == THP_RECLAIM_DISABLE)
> +		return;
> +
> +	page = compound_head(page);

Why do you think the caller might be passing in a tail page here?