diff mbox series

[v18,19/32] mm/swap.c: serialize memcg changes in pagevec_lru_move_fn

Message ID 1598273705-69124-20-git-send-email-alex.shi@linux.alibaba.com (mailing list archive)
State New, archived
Headers show
Series per memcg lru_lock | expand

Commit Message

Alex Shi Aug. 24, 2020, 12:54 p.m. UTC 
Hugh Dickins' found a memcg change bug on original version:
If we want to change the pgdat->lru_lock to memcg's lruvec lock, we have
to serialize mem_cgroup_move_account during pagevec_lru_move_fn. The
possible bad scenario would like:

	cpu 0					cpu 1
lruvec = mem_cgroup_page_lruvec()
					if (!isolate_lru_page())
						mem_cgroup_move_account

spin_lock_irqsave(&lruvec->lru_lock <== wrong lock.

So we need the ClearPageLRU to block isolate_lru_page(), that serializes
the memcg change. and then removing the PageLRU check in move_fn callee
as the consequence.

Reported-by: Hugh Dickins <hughd@google.com>
Signed-off-by: Hugh Dickins <hughd@google.com>
Signed-off-by: Alex Shi <alex.shi@linux.alibaba.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: linux-mm@kvack.org
Cc: linux-kernel@vger.kernel.org
---
 mm/swap.c | 44 +++++++++++++++++++++++++++++++++++---------
 1 file changed, 35 insertions(+), 9 deletions(-)

Comments

Hugh Dickins Sept. 22, 2020, 12:42 a.m. UTC | #1 
On Mon, 24 Aug 2020, Alex Shi wrote:

> Hugh Dickins' found a memcg change bug on original version:
> If we want to change the pgdat->lru_lock to memcg's lruvec lock, we have
> to serialize mem_cgroup_move_account during pagevec_lru_move_fn. The
> possible bad scenario would like:
> 
> 	cpu 0					cpu 1
> lruvec = mem_cgroup_page_lruvec()
> 					if (!isolate_lru_page())
> 						mem_cgroup_move_account
> 
> spin_lock_irqsave(&lruvec->lru_lock <== wrong lock.
> 
> So we need the ClearPageLRU to block isolate_lru_page(), that serializes

s/the ClearPageLRU/TestClearPageLRU/

> the memcg change. and then removing the PageLRU check in move_fn callee
> as the consequence.

Deserves another paragraph about __pagevec_lru_add():
"__pagevec_lru_add_fn() is different from the others, because the pages
it deals with are, by definition, not yet on the lru.  TestClearPageLRU
is not needed and would not work, so __pagevec_lru_add() goes its own way."

> 
> Reported-by: Hugh Dickins <hughd@google.com>

True.

> Signed-off-by: Hugh Dickins <hughd@google.com>

I did provide some lines, but I think it's just
Acked-by: Hugh Dickins <hughd@google.com>
to go below your Signed-off-by.

> Signed-off-by: Alex Shi <alex.shi@linux.alibaba.com>
> Cc: Andrew Morton <akpm@linux-foundation.org>
> Cc: linux-mm@kvack.org
> Cc: linux-kernel@vger.kernel.org
> ---
>  mm/swap.c | 44 +++++++++++++++++++++++++++++++++++---------
>  1 file changed, 35 insertions(+), 9 deletions(-)

In your lruv19 branch, this patch got renamed (s/moveing/moving/):
but I think it's better with the old name used here in v18, and without
those mm/vmscan.c mods to check_move_unevictable_pages() tacked on:
please move those back to 16/32, which already makes changes to vmscan.c.

> 
> diff --git a/mm/swap.c b/mm/swap.c
> index 446ffe280809..2d9a86bf93a4 100644
> --- a/mm/swap.c
> +++ b/mm/swap.c
> @@ -221,8 +221,14 @@ static void pagevec_lru_move_fn(struct pagevec *pvec,
>  			spin_lock_irqsave(&pgdat->lru_lock, flags);
>  		}
>  
> +		/* block memcg migration during page moving between lru */
> +		if (!TestClearPageLRU(page))
> +			continue;
> +
>  		lruvec = mem_cgroup_page_lruvec(page, pgdat);
>  		(*move_fn)(page, lruvec);
> +
> +		SetPageLRU(page);
>  	}
>  	if (pgdat)
>  		spin_unlock_irqrestore(&pgdat->lru_lock, flags);
> @@ -232,7 +238,7 @@ static void pagevec_lru_move_fn(struct pagevec *pvec,
>  
>  static void pagevec_move_tail_fn(struct page *page, struct lruvec *lruvec)
>  {
> -	if (PageLRU(page) && !PageUnevictable(page)) {
> +	if (!PageUnevictable(page)) {
>  		del_page_from_lru_list(page, lruvec, page_lru(page));
>  		ClearPageActive(page);
>  		add_page_to_lru_list_tail(page, lruvec, page_lru(page));
> @@ -306,7 +312,7 @@ void lru_note_cost_page(struct page *page)
>  
>  static void __activate_page(struct page *page, struct lruvec *lruvec)
>  {
> -	if (PageLRU(page) && !PageActive(page) && !PageUnevictable(page)) {
> +	if (!PageActive(page) && !PageUnevictable(page)) {
>  		int lru = page_lru_base_type(page);
>  		int nr_pages = thp_nr_pages(page);
>  
> @@ -362,7 +368,8 @@ void activate_page(struct page *page)
>  
>  	page = compound_head(page);
>  	spin_lock_irq(&pgdat->lru_lock);
> -	__activate_page(page, mem_cgroup_page_lruvec(page, pgdat));
> +	if (PageLRU(page))
> +		__activate_page(page, mem_cgroup_page_lruvec(page, pgdat));
>  	spin_unlock_irq(&pgdat->lru_lock);
>  }
>  #endif

Every time I look at this, I wonder if that's right, or an unnecessary
optimization strayed in, or whatever.  For the benefit of others looking
at this patch, yes it is right: this is the !CONFIG_SMP alternative
version of activate_page(), and needs that PageLRU check to compensate
for the check that has now been removed from __activate_page() itself.

> @@ -521,9 +528,6 @@ static void lru_deactivate_file_fn(struct page *page, struct lruvec *lruvec)
>  	bool active;
>  	int nr_pages = thp_nr_pages(page);
>  
> -	if (!PageLRU(page))
> -		return;
> -
>  	if (PageUnevictable(page))
>  		return;
>  
> @@ -564,7 +568,7 @@ static void lru_deactivate_file_fn(struct page *page, struct lruvec *lruvec)
>  
>  static void lru_deactivate_fn(struct page *page, struct lruvec *lruvec)
>  {
> -	if (PageLRU(page) && PageActive(page) && !PageUnevictable(page)) {
> +	if (PageActive(page) && !PageUnevictable(page)) {
>  		int lru = page_lru_base_type(page);
>  		int nr_pages = thp_nr_pages(page);
>  
> @@ -581,7 +585,7 @@ static void lru_deactivate_fn(struct page *page, struct lruvec *lruvec)
>  
>  static void lru_lazyfree_fn(struct page *page, struct lruvec *lruvec)
>  {
> -	if (PageLRU(page) && PageAnon(page) && PageSwapBacked(page) &&
> +	if (PageAnon(page) && PageSwapBacked(page) &&
>  	    !PageSwapCache(page) && !PageUnevictable(page)) {
>  		bool active = PageActive(page);
>  		int nr_pages = thp_nr_pages(page);
> @@ -979,7 +983,29 @@ static void __pagevec_lru_add_fn(struct page *page, struct lruvec *lruvec)
>   */
>  void __pagevec_lru_add(struct pagevec *pvec)
>  {
> -	pagevec_lru_move_fn(pvec, __pagevec_lru_add_fn);
> +	int i;
> +	struct pglist_data *pgdat = NULL;
> +	struct lruvec *lruvec;
> +	unsigned long flags = 0;
> +
> +	for (i = 0; i < pagevec_count(pvec); i++) {
> +		struct page *page = pvec->pages[i];
> +		struct pglist_data *pagepgdat = page_pgdat(page);
> +
> +		if (pagepgdat != pgdat) {
> +			if (pgdat)
> +				spin_unlock_irqrestore(&pgdat->lru_lock, flags);
> +			pgdat = pagepgdat;
> +			spin_lock_irqsave(&pgdat->lru_lock, flags);
> +		}
> +
> +		lruvec = mem_cgroup_page_lruvec(page, pgdat);
> +		__pagevec_lru_add_fn(page, lruvec);
> +	}
> +	if (pgdat)
> +		spin_unlock_irqrestore(&pgdat->lru_lock, flags);
> +	release_pages(pvec->pages, pvec->nr);
> +	pagevec_reinit(pvec);
>  }
>  
>  /**
> -- 
> 1.8.3.1
Alex Shi Sept. 22, 2020, 5 a.m. UTC | #2 
在 2020/9/22 上午8:42, Hugh Dickins 写道:
> On Mon, 24 Aug 2020, Alex Shi wrote:
> 
>> Hugh Dickins' found a memcg change bug on original version:
>> If we want to change the pgdat->lru_lock to memcg's lruvec lock, we have
>> to serialize mem_cgroup_move_account during pagevec_lru_move_fn. The
>> possible bad scenario would like:
>>
>> 	cpu 0					cpu 1
>> lruvec = mem_cgroup_page_lruvec()
>> 					if (!isolate_lru_page())
>> 						mem_cgroup_move_account
>>
>> spin_lock_irqsave(&lruvec->lru_lock <== wrong lock.
>>
>> So we need the ClearPageLRU to block isolate_lru_page(), that serializes
> 
> s/the ClearPageLRU/TestClearPageLRU/

Thanks, will change it.

> 
>> the memcg change. and then removing the PageLRU check in move_fn callee
>> as the consequence.
> 
> Deserves another paragraph about __pagevec_lru_add():
> "__pagevec_lru_add_fn() is different from the others, because the pages
> it deals with are, by definition, not yet on the lru.  TestClearPageLRU
> is not needed and would not work, so __pagevec_lru_add() goes its own way."

Thanks for comments! will add it into new commit log.
> 
>>
>> Reported-by: Hugh Dickins <hughd@google.com>
> 
> True.
> 
>> Signed-off-by: Hugh Dickins <hughd@google.com>
> 
> I did provide some lines, but I think it's just
> Acked-by: Hugh Dickins <hughd@google.com>
> to go below your Signed-off-by.

Thanks!
> 
>> Signed-off-by: Alex Shi <alex.shi@linux.alibaba.com>
>> Cc: Andrew Morton <akpm@linux-foundation.org>
>> Cc: linux-mm@kvack.org
>> Cc: linux-kernel@vger.kernel.org
>> ---
>>  mm/swap.c | 44 +++++++++++++++++++++++++++++++++++---------
>>  1 file changed, 35 insertions(+), 9 deletions(-)
> 
> In your lruv19 branch, this patch got renamed (s/moveing/moving/):
> but I think it's better with the old name used here in v18, and without
> those mm/vmscan.c mods to check_move_unevictable_pages() tacked on:
> please move those back to 16/32, which already makes changes to vmscan.c.
> 

Yes, will move that part there.
Thanks!
Alex

>>
>> diff --git a/mm/swap.c b/mm/swap.c
>> index 446ffe280809..2d9a86bf93a4 100644
>> --- a/mm/swap.c
>> +++ b/mm/swap.c
>> @@ -221,8 +221,14 @@ static void pagevec_lru_move_fn(struct pagevec *pvec,
>>  			spin_lock_irqsave(&pgdat->lru_lock, flags);
>>  		}
>>  
>> +		/* block memcg migration during page moving between lru */
>> +		if (!TestClearPageLRU(page))
>> +			continue;
>> +
>>  		lruvec = mem_cgroup_page_lruvec(page, pgdat);
>>  		(*move_fn)(page, lruvec);
>> +
>> +		SetPageLRU(page);
>>  	}
>>  	if (pgdat)
>>  		spin_unlock_irqrestore(&pgdat->lru_lock, flags);
>> @@ -232,7 +238,7 @@ static void pagevec_lru_move_fn(struct pagevec *pvec,
>>  
>>  static void pagevec_move_tail_fn(struct page *page, struct lruvec *lruvec)
>>  {
>> -	if (PageLRU(page) && !PageUnevictable(page)) {
>> +	if (!PageUnevictable(page)) {
>>  		del_page_from_lru_list(page, lruvec, page_lru(page));
>>  		ClearPageActive(page);
>>  		add_page_to_lru_list_tail(page, lruvec, page_lru(page));
>> @@ -306,7 +312,7 @@ void lru_note_cost_page(struct page *page)
>>  
>>  static void __activate_page(struct page *page, struct lruvec *lruvec)
>>  {
>> -	if (PageLRU(page) && !PageActive(page) && !PageUnevictable(page)) {
>> +	if (!PageActive(page) && !PageUnevictable(page)) {
>>  		int lru = page_lru_base_type(page);
>>  		int nr_pages = thp_nr_pages(page);
>>  
>> @@ -362,7 +368,8 @@ void activate_page(struct page *page)
>>  
>>  	page = compound_head(page);
>>  	spin_lock_irq(&pgdat->lru_lock);
>> -	__activate_page(page, mem_cgroup_page_lruvec(page, pgdat));
>> +	if (PageLRU(page))
>> +		__activate_page(page, mem_cgroup_page_lruvec(page, pgdat));
>>  	spin_unlock_irq(&pgdat->lru_lock);
>>  }
>>  #endif
> 
> Every time I look at this, I wonder if that's right, or an unnecessary
> optimization strayed in, or whatever.  For the benefit of others looking
> at this patch, yes it is right: this is the !CONFIG_SMP alternative
> version of activate_page(), and needs that PageLRU check to compensate
> for the check that has now been removed from __activate_page() itself.
> 
>> @@ -521,9 +528,6 @@ static void lru_deactivate_file_fn(struct page *page, struct lruvec *lruvec)
>>  	bool active;
>>  	int nr_pages = thp_nr_pages(page);
>>  
>> -	if (!PageLRU(page))
>> -		return;
>> -
>>  	if (PageUnevictable(page))
>>  		return;
>>  
>> @@ -564,7 +568,7 @@ static void lru_deactivate_file_fn(struct page *page, struct lruvec *lruvec)
>>  
>>  static void lru_deactivate_fn(struct page *page, struct lruvec *lruvec)
>>  {
>> -	if (PageLRU(page) && PageActive(page) && !PageUnevictable(page)) {
>> +	if (PageActive(page) && !PageUnevictable(page)) {
>>  		int lru = page_lru_base_type(page);
>>  		int nr_pages = thp_nr_pages(page);
>>  
>> @@ -581,7 +585,7 @@ static void lru_deactivate_fn(struct page *page, struct lruvec *lruvec)
>>  
>>  static void lru_lazyfree_fn(struct page *page, struct lruvec *lruvec)
>>  {
>> -	if (PageLRU(page) && PageAnon(page) && PageSwapBacked(page) &&
>> +	if (PageAnon(page) && PageSwapBacked(page) &&
>>  	    !PageSwapCache(page) && !PageUnevictable(page)) {
>>  		bool active = PageActive(page);
>>  		int nr_pages = thp_nr_pages(page);
>> @@ -979,7 +983,29 @@ static void __pagevec_lru_add_fn(struct page *page, struct lruvec *lruvec)
>>   */
>>  void __pagevec_lru_add(struct pagevec *pvec)
>>  {
>> -	pagevec_lru_move_fn(pvec, __pagevec_lru_add_fn);
>> +	int i;
>> +	struct pglist_data *pgdat = NULL;
>> +	struct lruvec *lruvec;
>> +	unsigned long flags = 0;
>> +
>> +	for (i = 0; i < pagevec_count(pvec); i++) {
>> +		struct page *page = pvec->pages[i];
>> +		struct pglist_data *pagepgdat = page_pgdat(page);
>> +
>> +		if (pagepgdat != pgdat) {
>> +			if (pgdat)
>> +				spin_unlock_irqrestore(&pgdat->lru_lock, flags);
>> +			pgdat = pagepgdat;
>> +			spin_lock_irqsave(&pgdat->lru_lock, flags);
>> +		}
>> +
>> +		lruvec = mem_cgroup_page_lruvec(page, pgdat);
>> +		__pagevec_lru_add_fn(page, lruvec);
>> +	}
>> +	if (pgdat)
>> +		spin_unlock_irqrestore(&pgdat->lru_lock, flags);
>> +	release_pages(pvec->pages, pvec->nr);
>> +	pagevec_reinit(pvec);
>>  }
>>  
>>  /**
>> -- 
>> 1.8.3.1
diff mbox series

Patch

diff --git a/mm/swap.c b/mm/swap.c
index 446ffe280809..2d9a86bf93a4 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -221,8 +221,14 @@  static void pagevec_lru_move_fn(struct pagevec *pvec,
 			spin_lock_irqsave(&pgdat->lru_lock, flags);
 		}
 
+		/* block memcg migration during page moving between lru */
+		if (!TestClearPageLRU(page))
+			continue;
+
 		lruvec = mem_cgroup_page_lruvec(page, pgdat);
 		(*move_fn)(page, lruvec);
+
+		SetPageLRU(page);
 	}
 	if (pgdat)
 		spin_unlock_irqrestore(&pgdat->lru_lock, flags);
@@ -232,7 +238,7 @@  static void pagevec_lru_move_fn(struct pagevec *pvec,
 
 static void pagevec_move_tail_fn(struct page *page, struct lruvec *lruvec)
 {
-	if (PageLRU(page) && !PageUnevictable(page)) {
+	if (!PageUnevictable(page)) {
 		del_page_from_lru_list(page, lruvec, page_lru(page));
 		ClearPageActive(page);
 		add_page_to_lru_list_tail(page, lruvec, page_lru(page));
@@ -306,7 +312,7 @@  void lru_note_cost_page(struct page *page)
 
 static void __activate_page(struct page *page, struct lruvec *lruvec)
 {
-	if (PageLRU(page) && !PageActive(page) && !PageUnevictable(page)) {
+	if (!PageActive(page) && !PageUnevictable(page)) {
 		int lru = page_lru_base_type(page);
 		int nr_pages = thp_nr_pages(page);
 
@@ -362,7 +368,8 @@  void activate_page(struct page *page)
 
 	page = compound_head(page);
 	spin_lock_irq(&pgdat->lru_lock);
-	__activate_page(page, mem_cgroup_page_lruvec(page, pgdat));
+	if (PageLRU(page))
+		__activate_page(page, mem_cgroup_page_lruvec(page, pgdat));
 	spin_unlock_irq(&pgdat->lru_lock);
 }
 #endif
@@ -521,9 +528,6 @@  static void lru_deactivate_file_fn(struct page *page, struct lruvec *lruvec)
 	bool active;
 	int nr_pages = thp_nr_pages(page);
 
-	if (!PageLRU(page))
-		return;
-
 	if (PageUnevictable(page))
 		return;
 
@@ -564,7 +568,7 @@  static void lru_deactivate_file_fn(struct page *page, struct lruvec *lruvec)
 
 static void lru_deactivate_fn(struct page *page, struct lruvec *lruvec)
 {
-	if (PageLRU(page) && PageActive(page) && !PageUnevictable(page)) {
+	if (PageActive(page) && !PageUnevictable(page)) {
 		int lru = page_lru_base_type(page);
 		int nr_pages = thp_nr_pages(page);
 
@@ -581,7 +585,7 @@  static void lru_deactivate_fn(struct page *page, struct lruvec *lruvec)
 
 static void lru_lazyfree_fn(struct page *page, struct lruvec *lruvec)
 {
-	if (PageLRU(page) && PageAnon(page) && PageSwapBacked(page) &&
+	if (PageAnon(page) && PageSwapBacked(page) &&
 	    !PageSwapCache(page) && !PageUnevictable(page)) {
 		bool active = PageActive(page);
 		int nr_pages = thp_nr_pages(page);
@@ -979,7 +983,29 @@  static void __pagevec_lru_add_fn(struct page *page, struct lruvec *lruvec)
  */
 void __pagevec_lru_add(struct pagevec *pvec)
 {
-	pagevec_lru_move_fn(pvec, __pagevec_lru_add_fn);
+	int i;
+	struct pglist_data *pgdat = NULL;
+	struct lruvec *lruvec;
+	unsigned long flags = 0;
+
+	for (i = 0; i < pagevec_count(pvec); i++) {
+		struct page *page = pvec->pages[i];
+		struct pglist_data *pagepgdat = page_pgdat(page);
+
+		if (pagepgdat != pgdat) {
+			if (pgdat)
+				spin_unlock_irqrestore(&pgdat->lru_lock, flags);
+			pgdat = pagepgdat;
+			spin_lock_irqsave(&pgdat->lru_lock, flags);
+		}
+
+		lruvec = mem_cgroup_page_lruvec(page, pgdat);
+		__pagevec_lru_add_fn(page, lruvec);
+	}
+	if (pgdat)
+		spin_unlock_irqrestore(&pgdat->lru_lock, flags);
+	release_pages(pvec->pages, pvec->nr);
+	pagevec_reinit(pvec);
 }
 
 /**