Linux-mm Archive on lore.kernel.org
 help / color / Atom feed
* [PATCH 1/4] mm/thp: move lru_add_page_tail func to huge_memory.c
@ 2020-08-01  4:09 Alex Shi
  2020-08-01  4:09 ` [PATCH 2/4] mm/thp: clean up lru_add_page_tail Alex Shi
                   ` (3 more replies)
  0 siblings, 4 replies; 7+ messages in thread
From: Alex Shi @ 2020-08-01  4:09 UTC (permalink / raw)
  To: Andrew Morton
  Cc: Johannes Weiner, Matthew Wilcox, Hugh Dickins, linux-kernel, linux-mm

The func is only used in huge_memory.c, defining it in other file with a
CONFIG_TRANSPARENT_HUGEPAGE macro restrict just looks weird.

Let's move it THP. And make it static as Hugh Dickin suggested.

Signed-off-by: Alex Shi <alex.shi@linux.alibaba.com>
Reviewed-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Hugh Dickins <hughd@google.com>
Cc: linux-kernel@vger.kernel.org
Cc: linux-mm@kvack.org
---
 include/linux/swap.h |  2 --
 mm/huge_memory.c     | 30 ++++++++++++++++++++++++++++++
 mm/swap.c            | 33 ---------------------------------
 3 files changed, 30 insertions(+), 35 deletions(-)

diff --git a/include/linux/swap.h b/include/linux/swap.h
index 661046994db4..43e6b3458f58 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -338,8 +338,6 @@ extern void lru_note_cost(struct lruvec *lruvec, bool file,
 			  unsigned int nr_pages);
 extern void lru_note_cost_page(struct page *);
 extern void lru_cache_add(struct page *);
-extern void lru_add_page_tail(struct page *page, struct page *page_tail,
-			 struct lruvec *lruvec, struct list_head *head);
 extern void activate_page(struct page *);
 extern void mark_page_accessed(struct page *);
 extern void lru_add_drain(void);
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 90733cefa528..bc905e7079bf 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -2315,6 +2315,36 @@ static void remap_page(struct page *page)
 	}
 }
 
+static void lru_add_page_tail(struct page *page, struct page *page_tail,
+				struct lruvec *lruvec, struct list_head *list)
+{
+	VM_BUG_ON_PAGE(!PageHead(page), page);
+	VM_BUG_ON_PAGE(PageCompound(page_tail), page);
+	VM_BUG_ON_PAGE(PageLRU(page_tail), page);
+	lockdep_assert_held(&lruvec_pgdat(lruvec)->lru_lock);
+
+	if (!list)
+		SetPageLRU(page_tail);
+
+	if (likely(PageLRU(page)))
+		list_add_tail(&page_tail->lru, &page->lru);
+	else if (list) {
+		/* page reclaim is reclaiming a huge page */
+		get_page(page_tail);
+		list_add_tail(&page_tail->lru, list);
+	} else {
+		/*
+		 * Head page has not yet been counted, as an hpage,
+		 * so we must account for each subpage individually.
+		 *
+		 * Put page_tail on the list at the correct position
+		 * so they all end up in order.
+		 */
+		add_page_to_lru_list_tail(page_tail, lruvec,
+					  page_lru(page_tail));
+	}
+}
+
 static void __split_huge_page_tail(struct page *head, int tail,
 		struct lruvec *lruvec, struct list_head *list)
 {
diff --git a/mm/swap.c b/mm/swap.c
index d16d65d9b4e0..c674fb441fe9 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -935,39 +935,6 @@ void __pagevec_release(struct pagevec *pvec)
 }
 EXPORT_SYMBOL(__pagevec_release);
 
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-/* used by __split_huge_page_refcount() */
-void lru_add_page_tail(struct page *page, struct page *page_tail,
-		       struct lruvec *lruvec, struct list_head *list)
-{
-	VM_BUG_ON_PAGE(!PageHead(page), page);
-	VM_BUG_ON_PAGE(PageCompound(page_tail), page);
-	VM_BUG_ON_PAGE(PageLRU(page_tail), page);
-	lockdep_assert_held(&lruvec_pgdat(lruvec)->lru_lock);
-
-	if (!list)
-		SetPageLRU(page_tail);
-
-	if (likely(PageLRU(page)))
-		list_add_tail(&page_tail->lru, &page->lru);
-	else if (list) {
-		/* page reclaim is reclaiming a huge page */
-		get_page(page_tail);
-		list_add_tail(&page_tail->lru, list);
-	} else {
-		/*
-		 * Head page has not yet been counted, as an hpage,
-		 * so we must account for each subpage individually.
-		 *
-		 * Put page_tail on the list at the correct position
-		 * so they all end up in order.
-		 */
-		add_page_to_lru_list_tail(page_tail, lruvec,
-					  page_lru(page_tail));
-	}
-}
-#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
-
 static void __pagevec_lru_add_fn(struct page *page, struct lruvec *lruvec,
 				 void *arg)
 {
-- 
1.8.3.1



^ permalink raw reply	[flat|nested] 7+ messages in thread

* [PATCH 2/4] mm/thp: clean up lru_add_page_tail
  2020-08-01  4:09 [PATCH 1/4] mm/thp: move lru_add_page_tail func to huge_memory.c Alex Shi
@ 2020-08-01  4:09 ` Alex Shi
  2020-08-01  4:09 ` [PATCH 3/4] mm/thp: remove code path which never got into Alex Shi
                   ` (2 subsequent siblings)
  3 siblings, 0 replies; 7+ messages in thread
From: Alex Shi @ 2020-08-01  4:09 UTC (permalink / raw)
  To: Andrew Morton
  Cc: Johannes Weiner, Matthew Wilcox, Hugh Dickins, linux-mm, linux-kernel

Since the first parameter is only used by head page, it's better to make
it explicit.

Signed-off-by: Alex Shi <alex.shi@linux.alibaba.com>
Reviewed-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Hugh Dickins <hughd@google.com>
Cc: linux-mm@kvack.org
Cc: linux-kernel@vger.kernel.org
---
 mm/huge_memory.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index bc905e7079bf..8cecd39bd8b7 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -2315,19 +2315,19 @@ static void remap_page(struct page *page)
 	}
 }
 
-static void lru_add_page_tail(struct page *page, struct page *page_tail,
+static void lru_add_page_tail(struct page *head, struct page *page_tail,
 				struct lruvec *lruvec, struct list_head *list)
 {
-	VM_BUG_ON_PAGE(!PageHead(page), page);
-	VM_BUG_ON_PAGE(PageCompound(page_tail), page);
-	VM_BUG_ON_PAGE(PageLRU(page_tail), page);
+	VM_BUG_ON_PAGE(!PageHead(head), head);
+	VM_BUG_ON_PAGE(PageCompound(page_tail), head);
+	VM_BUG_ON_PAGE(PageLRU(page_tail), head);
 	lockdep_assert_held(&lruvec_pgdat(lruvec)->lru_lock);
 
 	if (!list)
 		SetPageLRU(page_tail);
 
-	if (likely(PageLRU(page)))
-		list_add_tail(&page_tail->lru, &page->lru);
+	if (likely(PageLRU(head)))
+		list_add_tail(&page_tail->lru, &head->lru);
 	else if (list) {
 		/* page reclaim is reclaiming a huge page */
 		get_page(page_tail);
-- 
1.8.3.1



^ permalink raw reply	[flat|nested] 7+ messages in thread

* [PATCH 3/4] mm/thp: remove code path which never got into
  2020-08-01  4:09 [PATCH 1/4] mm/thp: move lru_add_page_tail func to huge_memory.c Alex Shi
  2020-08-01  4:09 ` [PATCH 2/4] mm/thp: clean up lru_add_page_tail Alex Shi
@ 2020-08-01  4:09 ` Alex Shi
  2020-08-01  4:09 ` [PATCH 4/4] mm/thp: narrow lru locking Alex Shi
  2020-08-01  4:11 ` [PATCH 1/4] mm/thp: move lru_add_page_tail func to huge_memory.c Alex Shi
  3 siblings, 0 replies; 7+ messages in thread
From: Alex Shi @ 2020-08-01  4:09 UTC (permalink / raw)
  To: Andrew Morton
  Cc: Kirill A. Shutemov, Johannes Weiner, Matthew Wilcox,
	Hugh Dickins, linux-mm, linux-kernel

split_huge_page() will never call on a page which isn't on lru list, so
this code never got a chance to run, and should not be run, to add tail
pages on a lru list which head page isn't there.

Although the bug was never triggered, it'better be removed for code
correctness.

BTW, it looks better to have a WARN() set in the wrong path, but the
path will be changed in incoming new page isolation func. So just save
it now.

Signed-off-by: Alex Shi <alex.shi@linux.alibaba.com>
Reviewed-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Kirill A. Shutemov <kirill@shutemov.name>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Hugh Dickins <hughd@google.com>
Cc: linux-mm@kvack.org
Cc: linux-kernel@vger.kernel.org
---
 mm/huge_memory.c | 10 ----------
 1 file changed, 10 deletions(-)

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 8cecd39bd8b7..dfe7378ab4be 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -2332,16 +2332,6 @@ static void lru_add_page_tail(struct page *head, struct page *page_tail,
 		/* page reclaim is reclaiming a huge page */
 		get_page(page_tail);
 		list_add_tail(&page_tail->lru, list);
-	} else {
-		/*
-		 * Head page has not yet been counted, as an hpage,
-		 * so we must account for each subpage individually.
-		 *
-		 * Put page_tail on the list at the correct position
-		 * so they all end up in order.
-		 */
-		add_page_to_lru_list_tail(page_tail, lruvec,
-					  page_lru(page_tail));
 	}
 }
 
-- 
1.8.3.1



^ permalink raw reply	[flat|nested] 7+ messages in thread

* [PATCH 4/4] mm/thp: narrow lru locking
  2020-08-01  4:09 [PATCH 1/4] mm/thp: move lru_add_page_tail func to huge_memory.c Alex Shi
  2020-08-01  4:09 ` [PATCH 2/4] mm/thp: clean up lru_add_page_tail Alex Shi
  2020-08-01  4:09 ` [PATCH 3/4] mm/thp: remove code path which never got into Alex Shi
@ 2020-08-01  4:09 ` Alex Shi
  2020-08-02 11:09   ` Matthew Wilcox
  2020-08-01  4:11 ` [PATCH 1/4] mm/thp: move lru_add_page_tail func to huge_memory.c Alex Shi
  3 siblings, 1 reply; 7+ messages in thread
From: Alex Shi @ 2020-08-01  4:09 UTC (permalink / raw)
  To: Andrew Morton
  Cc: Wei Yang, Hugh Dickins, Kirill A. Shutemov, Andrea Arcangeli,
	Johannes Weiner, Matthew Wilcox, linux-mm, linux-kernel

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@linux.alibaba.com>
Signed-off-by: Wei Yang <richard.weiyang@gmail.com>
Reviewed-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Kirill A. Shutemov <kirill@shutemov.name>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: linux-mm@kvack.org
Cc: linux-kernel@vger.kernel.org
---
 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



^ permalink raw reply	[flat|nested] 7+ messages in thread

* Re: [PATCH 1/4] mm/thp: move lru_add_page_tail func to huge_memory.c
  2020-08-01  4:09 [PATCH 1/4] mm/thp: move lru_add_page_tail func to huge_memory.c Alex Shi
                   ` (2 preceding siblings ...)
  2020-08-01  4:09 ` [PATCH 4/4] mm/thp: narrow lru locking Alex Shi
@ 2020-08-01  4:11 ` Alex Shi
  3 siblings, 0 replies; 7+ messages in thread
From: Alex Shi @ 2020-08-01  4:11 UTC (permalink / raw)
  To: Andrew Morton
  Cc: Johannes Weiner, Matthew Wilcox, Hugh Dickins, linux-kernel, linux-mm

Hi Andrew,

This patchset is just cleanup and get reviewed by Kirill, is it cath up 5.9?

Thanks
Alex

在 2020/8/1 下午12:09, Alex Shi 写道:
> The func is only used in huge_memory.c, defining it in other file with a
> CONFIG_TRANSPARENT_HUGEPAGE macro restrict just looks weird.
> 
> Let's move it THP. And make it static as Hugh Dickin suggested.
> 
> Signed-off-by: Alex Shi <alex.shi@linux.alibaba.com>
> Reviewed-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
> Cc: Andrew Morton <akpm@linux-foundation.org>
> Cc: Johannes Weiner <hannes@cmpxchg.org>
> Cc: Matthew Wilcox <willy@infradead.org>
> Cc: Hugh Dickins <hughd@google.com>
> Cc: linux-kernel@vger.kernel.org
> Cc: linux-mm@kvack.org
> ---
>  include/linux/swap.h |  2 --
>  mm/huge_memory.c     | 30 ++++++++++++++++++++++++++++++
>  mm/swap.c            | 33 ---------------------------------
>  3 files changed, 30 insertions(+), 35 deletions(-)
> 
> diff --git a/include/linux/swap.h b/include/linux/swap.h
> index 661046994db4..43e6b3458f58 100644
> --- a/include/linux/swap.h
> +++ b/include/linux/swap.h
> @@ -338,8 +338,6 @@ extern void lru_note_cost(struct lruvec *lruvec, bool file,
>  			  unsigned int nr_pages);
>  extern void lru_note_cost_page(struct page *);
>  extern void lru_cache_add(struct page *);
> -extern void lru_add_page_tail(struct page *page, struct page *page_tail,
> -			 struct lruvec *lruvec, struct list_head *head);
>  extern void activate_page(struct page *);
>  extern void mark_page_accessed(struct page *);
>  extern void lru_add_drain(void);
> diff --git a/mm/huge_memory.c b/mm/huge_memory.c
> index 90733cefa528..bc905e7079bf 100644
> --- a/mm/huge_memory.c
> +++ b/mm/huge_memory.c
> @@ -2315,6 +2315,36 @@ static void remap_page(struct page *page)
>  	}
>  }
>  
> +static void lru_add_page_tail(struct page *page, struct page *page_tail,
> +				struct lruvec *lruvec, struct list_head *list)
> +{
> +	VM_BUG_ON_PAGE(!PageHead(page), page);
> +	VM_BUG_ON_PAGE(PageCompound(page_tail), page);
> +	VM_BUG_ON_PAGE(PageLRU(page_tail), page);
> +	lockdep_assert_held(&lruvec_pgdat(lruvec)->lru_lock);
> +
> +	if (!list)
> +		SetPageLRU(page_tail);
> +
> +	if (likely(PageLRU(page)))
> +		list_add_tail(&page_tail->lru, &page->lru);
> +	else if (list) {
> +		/* page reclaim is reclaiming a huge page */
> +		get_page(page_tail);
> +		list_add_tail(&page_tail->lru, list);
> +	} else {
> +		/*
> +		 * Head page has not yet been counted, as an hpage,
> +		 * so we must account for each subpage individually.
> +		 *
> +		 * Put page_tail on the list at the correct position
> +		 * so they all end up in order.
> +		 */
> +		add_page_to_lru_list_tail(page_tail, lruvec,
> +					  page_lru(page_tail));
> +	}
> +}
> +
>  static void __split_huge_page_tail(struct page *head, int tail,
>  		struct lruvec *lruvec, struct list_head *list)
>  {
> diff --git a/mm/swap.c b/mm/swap.c
> index d16d65d9b4e0..c674fb441fe9 100644
> --- a/mm/swap.c
> +++ b/mm/swap.c
> @@ -935,39 +935,6 @@ void __pagevec_release(struct pagevec *pvec)
>  }
>  EXPORT_SYMBOL(__pagevec_release);
>  
> -#ifdef CONFIG_TRANSPARENT_HUGEPAGE
> -/* used by __split_huge_page_refcount() */
> -void lru_add_page_tail(struct page *page, struct page *page_tail,
> -		       struct lruvec *lruvec, struct list_head *list)
> -{
> -	VM_BUG_ON_PAGE(!PageHead(page), page);
> -	VM_BUG_ON_PAGE(PageCompound(page_tail), page);
> -	VM_BUG_ON_PAGE(PageLRU(page_tail), page);
> -	lockdep_assert_held(&lruvec_pgdat(lruvec)->lru_lock);
> -
> -	if (!list)
> -		SetPageLRU(page_tail);
> -
> -	if (likely(PageLRU(page)))
> -		list_add_tail(&page_tail->lru, &page->lru);
> -	else if (list) {
> -		/* page reclaim is reclaiming a huge page */
> -		get_page(page_tail);
> -		list_add_tail(&page_tail->lru, list);
> -	} else {
> -		/*
> -		 * Head page has not yet been counted, as an hpage,
> -		 * so we must account for each subpage individually.
> -		 *
> -		 * Put page_tail on the list at the correct position
> -		 * so they all end up in order.
> -		 */
> -		add_page_to_lru_list_tail(page_tail, lruvec,
> -					  page_lru(page_tail));
> -	}
> -}
> -#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
> -
>  static void __pagevec_lru_add_fn(struct page *page, struct lruvec *lruvec,
>  				 void *arg)
>  {
> 


^ permalink raw reply	[flat|nested] 7+ messages in thread

* Re: [PATCH 4/4] mm/thp: narrow lru locking
  2020-08-01  4:09 ` [PATCH 4/4] mm/thp: narrow lru locking Alex Shi
@ 2020-08-02 11:09   ` Matthew Wilcox
  2020-08-02 13:24     ` Alex Shi
  0 siblings, 1 reply; 7+ messages in thread
From: Matthew Wilcox @ 2020-08-02 11:09 UTC (permalink / raw)
  To: Alex Shi
  Cc: Andrew Morton, Wei Yang, Hugh Dickins, Kirill A. Shutemov,
	Andrea Arcangeli, Johannes Weiner, linux-mm, linux-kernel,
	Thomas Gleixner, Sebastian Andrzej Siewior, Peter Zijlstra


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@linux.alibaba.com>
> Signed-off-by: Wei Yang <richard.weiyang@gmail.com>
> Reviewed-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
> Cc: Hugh Dickins <hughd@google.com>
> Cc: Kirill A. Shutemov <kirill@shutemov.name>
> Cc: Andrea Arcangeli <aarcange@redhat.com>
> Cc: Johannes Weiner <hannes@cmpxchg.org>
> Cc: Matthew Wilcox <willy@infradead.org>
> Cc: Andrew Morton <akpm@linux-foundation.org>
> Cc: linux-mm@kvack.org
> Cc: linux-kernel@vger.kernel.org
> ---
>  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
> 


^ permalink raw reply	[flat|nested] 7+ messages in thread

* Re: [PATCH 4/4] mm/thp: narrow lru locking
  2020-08-02 11:09   ` Matthew Wilcox
@ 2020-08-02 13:24     ` Alex Shi
  0 siblings, 0 replies; 7+ messages in thread
From: Alex Shi @ 2020-08-02 13:24 UTC (permalink / raw)
  To: Matthew Wilcox
  Cc: Andrew Morton, Wei Yang, Hugh Dickins, Kirill A. Shutemov,
	Andrea Arcangeli, Johannes Weiner, linux-mm, linux-kernel,
	Thomas Gleixner, Sebastian Andrzej Siewior, Peter Zijlstra



在 2020/8/2 下午7:09, Matthew Wilcox 写道:
> You're playing games with separating interrupt disabling from spinlocks.
> Have you got any feedback from -rt people on this?

Is there other suggestions to remove local_irq_disable?

Just check again on kernel/mm directory on linux-next. there are still
much local_irq_disable there.

Guess we need a final solution instead of block new one.

Thanks
Alex


^ permalink raw reply	[flat|nested] 7+ messages in thread

end of thread, back to index

Thread overview: 7+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2020-08-01  4:09 [PATCH 1/4] mm/thp: move lru_add_page_tail func to huge_memory.c Alex Shi
2020-08-01  4:09 ` [PATCH 2/4] mm/thp: clean up lru_add_page_tail Alex Shi
2020-08-01  4:09 ` [PATCH 3/4] mm/thp: remove code path which never got into Alex Shi
2020-08-01  4:09 ` [PATCH 4/4] mm/thp: narrow lru locking Alex Shi
2020-08-02 11:09   ` Matthew Wilcox
2020-08-02 13:24     ` Alex Shi
2020-08-01  4:11 ` [PATCH 1/4] mm/thp: move lru_add_page_tail func to huge_memory.c Alex Shi

Linux-mm Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/linux-mm/0 linux-mm/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 linux-mm linux-mm/ https://lore.kernel.org/linux-mm \
		linux-mm@kvack.org
	public-inbox-index linux-mm

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kvack.linux-mm


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git