Re: [PATCH 4/4] mm/thp: narrow lru locking

[Matthew Wilcox]

You're playing games with separating interrupt disabling from spinlocks.
Have you got any feedback from -rt people on this?

On Sat, Aug 01, 2020 at 12:09:17PM +0800, Alex Shi wrote:
> lru_lock and page cache xa_lock have no reason with current sequence,
> put them together isn't necessary. let's narrow the lru locking, but
> left the local_irq_disable to block interrupt re-entry and statistic update.
> 
> Hugh Dickins point: split_huge_page_to_list() was already silly,to be
> using the _irqsave variant: it's just been taking sleeping locks, so
> would already be broken if entered with interrupts enabled.
> so we can save passing flags argument down to __split_huge_page().
> 
> Signed-off-by: Alex Shi <alex.shi@xxxxxxxxxxxxxxxxx>
> Signed-off-by: Wei Yang <richard.weiyang@xxxxxxxxx>
> Reviewed-by: Kirill A. Shutemov <kirill.shutemov@xxxxxxxxxxxxxxx>
> Cc: Hugh Dickins <hughd@xxxxxxxxxx>
> Cc: Kirill A. Shutemov <kirill@xxxxxxxxxxxxx>
> Cc: Andrea Arcangeli <aarcange@xxxxxxxxxx>
> Cc: Johannes Weiner <hannes@xxxxxxxxxxx>
> Cc: Matthew Wilcox <willy@xxxxxxxxxxxxx>
> Cc: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
> Cc: linux-mm@xxxxxxxxx
> Cc: linux-kernel@xxxxxxxxxxxxxxx
> ---
>  mm/huge_memory.c | 25 +++++++++++++------------
>  1 file changed, 13 insertions(+), 12 deletions(-)
> 
> diff --git a/mm/huge_memory.c b/mm/huge_memory.c
> index dfe7378ab4be..070480e66bf4 100644
> --- a/mm/huge_memory.c
> +++ b/mm/huge_memory.c
> @@ -2398,7 +2398,7 @@ static void __split_huge_page_tail(struct page *head, int tail,
>  }
>  
>  static void __split_huge_page(struct page *page, struct list_head *list,
> -		pgoff_t end, unsigned long flags)
> +			      pgoff_t end)
>  {
>  	struct page *head = compound_head(page);
>  	pg_data_t *pgdat = page_pgdat(head);
> @@ -2407,8 +2407,6 @@ static void __split_huge_page(struct page *page, struct list_head *list,
>  	unsigned long offset = 0;
>  	int i;
>  
> -	lruvec = mem_cgroup_page_lruvec(head, pgdat);
> -
>  	/* complete memcg works before add pages to LRU */
>  	mem_cgroup_split_huge_fixup(head);
>  
> @@ -2420,6 +2418,11 @@ static void __split_huge_page(struct page *page, struct list_head *list,
>  		xa_lock(&swap_cache->i_pages);
>  	}
>  
> +	/* prevent PageLRU to go away from under us, and freeze lru stats */
> +	spin_lock(&pgdat->lru_lock);
> +
> +	lruvec = mem_cgroup_page_lruvec(head, pgdat);
> +
>  	for (i = HPAGE_PMD_NR - 1; i >= 1; i--) {
>  		__split_huge_page_tail(head, i, lruvec, list);
>  		/* Some pages can be beyond i_size: drop them from page cache */
> @@ -2439,6 +2442,8 @@ static void __split_huge_page(struct page *page, struct list_head *list,
>  	}
>  
>  	ClearPageCompound(head);
> +	spin_unlock(&pgdat->lru_lock);
> +	/* Caller disabled irqs, so they are still disabled here */
>  
>  	split_page_owner(head, HPAGE_PMD_ORDER);
>  
> @@ -2456,8 +2461,7 @@ static void __split_huge_page(struct page *page, struct list_head *list,
>  		page_ref_add(head, 2);
>  		xa_unlock(&head->mapping->i_pages);
>  	}
> -
> -	spin_unlock_irqrestore(&pgdat->lru_lock, flags);
> +	local_irq_enable();
>  
>  	remap_page(head);
>  
> @@ -2596,12 +2600,10 @@ bool can_split_huge_page(struct page *page, int *pextra_pins)
>  int split_huge_page_to_list(struct page *page, struct list_head *list)
>  {
>  	struct page *head = compound_head(page);
> -	struct pglist_data *pgdata = NODE_DATA(page_to_nid(head));
>  	struct deferred_split *ds_queue = get_deferred_split_queue(head);
>  	struct anon_vma *anon_vma = NULL;
>  	struct address_space *mapping = NULL;
>  	int count, mapcount, extra_pins, ret;
> -	unsigned long flags;
>  	pgoff_t end;
>  
>  	VM_BUG_ON_PAGE(is_huge_zero_page(head), head);
> @@ -2662,9 +2664,8 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
>  	unmap_page(head);
>  	VM_BUG_ON_PAGE(compound_mapcount(head), head);
>  
> -	/* prevent PageLRU to go away from under us, and freeze lru stats */
> -	spin_lock_irqsave(&pgdata->lru_lock, flags);
> -
> +	/* block interrupt reentry in xa_lock and spinlock */
> +	local_irq_disable();
>  	if (mapping) {
>  		XA_STATE(xas, &mapping->i_pages, page_index(head));
>  
> @@ -2694,7 +2695,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
>  				__dec_node_page_state(head, NR_FILE_THPS);
>  		}
>  
> -		__split_huge_page(page, list, end, flags);
> +		__split_huge_page(page, list, end);
>  		if (PageSwapCache(head)) {
>  			swp_entry_t entry = { .val = page_private(head) };
>  
> @@ -2713,7 +2714,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
>  		spin_unlock(&ds_queue->split_queue_lock);
>  fail:		if (mapping)
>  			xa_unlock(&mapping->i_pages);
> -		spin_unlock_irqrestore(&pgdata->lru_lock, flags);
> +		local_irq_enable();
>  		remap_page(head);
>  		ret = -EBUSY;
>  	}
> -- 
> 1.8.3.1
>