diff mbox series

[v9,06/20] mm/thp: narrow lru locking

Message ID 1583146830-169516-7-git-send-email-alex.shi@linux.alibaba.com (mailing list archive)
State New, archived
Headers show
Series [v9,01/20] mm/vmscan: remove unnecessary lruvec adding | expand

Commit Message

Alex Shi March 2, 2020, 11 a.m. UTC 
Lru locking just guard the lru list and subpage's Mlocked. Including
other things can't give help just delay the locking release. So narrow
the locking for early lock release and better code meaning.

Signed-off-by: Alex Shi <alex.shi@linux.alibaba.com>
Cc: Kirill A. Shutemov <kirill@shutemov.name>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: linux-mm@kvack.org
Cc: linux-kernel@vger.kernel.org
---
 mm/huge_memory.c | 17 +++++++----------
 1 file changed, 7 insertions(+), 10 deletions(-)

Comments

Kirill A . Shutemov March 4, 2020, 8:02 a.m. UTC | #1 
On Mon, Mar 02, 2020 at 07:00:16PM +0800, Alex Shi wrote:
> @@ -2564,6 +2565,9 @@ static void __split_huge_page(struct page *page, struct list_head *list,
>  		xa_lock(&swap_cache->i_pages);
>  	}
>  
> +	/* Lru list would be changed, don't care head's LRU bit. */
> +	spin_lock_irqsave(&pgdat->lru_lock, flags);
> +
>  	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 */

You change locking order WRT i_pages lock. Is it safe?
Alex Shi March 4, 2020, 8:51 a.m. UTC | #2 
在 2020/3/4 下午4:02, Kirill A. Shutemov 写道:
> On Mon, Mar 02, 2020 at 07:00:16PM +0800, Alex Shi wrote:
>> @@ -2564,6 +2565,9 @@ static void __split_huge_page(struct page *page, struct list_head *list,
>>  		xa_lock(&swap_cache->i_pages);
>>  	}
>>  
>> +	/* Lru list would be changed, don't care head's LRU bit. */
>> +	spin_lock_irqsave(&pgdat->lru_lock, flags);
>> +
>>  	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 */
> 
> You change locking order WRT i_pages lock. Is it safe?
> 

Thanks Kirill,

I think so. and lock_dep/proving has no complain.

Any problem addressed?

Alex
diff mbox series

Patch

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 599367d25fca..3835f87d03fd 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -2542,13 +2542,14 @@  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);
 	struct lruvec *lruvec;
 	struct address_space *swap_cache = NULL;
 	unsigned long offset = 0;
+	unsigned long flags;
 	int i;
 
 	lruvec = mem_cgroup_page_lruvec(head, pgdat);
@@ -2564,6 +2565,9 @@  static void __split_huge_page(struct page *page, struct list_head *list,
 		xa_lock(&swap_cache->i_pages);
 	}
 
+	/* Lru list would be changed, don't care head's LRU bit. */
+	spin_lock_irqsave(&pgdat->lru_lock, flags);
+
 	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 */
@@ -2581,6 +2585,7 @@  static void __split_huge_page(struct page *page, struct list_head *list,
 					head + i, 0);
 		}
 	}
+	spin_unlock_irqrestore(&pgdat->lru_lock, flags);
 
 	ClearPageCompound(head);
 
@@ -2601,8 +2606,6 @@  static void __split_huge_page(struct page *page, struct list_head *list,
 		xa_unlock(&head->mapping->i_pages);
 	}
 
-	spin_unlock_irqrestore(&pgdat->lru_lock, flags);
-
 	remap_page(head);
 
 	for (i = 0; i < HPAGE_PMD_NR; i++) {
@@ -2740,13 +2743,11 @@  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;
 	bool mlocked;
-	unsigned long flags;
 	pgoff_t end;
 
 	VM_BUG_ON_PAGE(is_huge_zero_page(head), head);
@@ -2812,9 +2813,6 @@  int split_huge_page_to_list(struct page *page, struct list_head *list)
 	if (mlocked)
 		lru_add_drain();
 
-	/* prevent PageLRU to go away from under us, and freeze lru stats */
-	spin_lock_irqsave(&pgdata->lru_lock, flags);
-
 	if (mapping) {
 		XA_STATE(xas, &mapping->i_pages, page_index(head));
 
@@ -2844,7 +2842,7 @@  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) };
 
@@ -2863,7 +2861,6 @@  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);
 		remap_page(head);
 		ret = -EBUSY;
 	}