[PATCH 0/3] CMA: Handle the issues of aggressively allocate the

[PATCH 0/3] CMA: Handle the issues of aggressively allocate the

[Hui Zhu]

I tried the Joonsoo's CMA patches [1] in my part and found that they works
better than mine [2] about handle LRU and other issues even if they
don't shrink the memory before cma_alloc.  So I began to test it in my
part.
But my colleague Weixing found some issues around it.  So we make 2 patches to
handle the issues.
And I merged cma_alloc_counter from [2] to cma_alloc work better.

This patchset is based on aa39477b5692611b91ac9455ae588738852b3f60 and [1].

[1] https://lkml.org/lkml/2014/5/28/64
[2] https://lkml.org/lkml/2014/10/15/623

Hui Zhu (3):
CMA: Fix the bug that CMA's page number is substructed twice
CMA: Fix the issue that nr_try_movable just count MIGRATE_MOVABLE memory
CMA: Add cma_alloc_counter to make cma_alloc work better if it meet busy range

 include/linux/cma.h    |    2 +
 include/linux/mmzone.h |    3 +
 mm/cma.c               |    6 +++
 mm/page_alloc.c        |   76 ++++++++++++++++++++++++++++++++++---------------
 4 files changed, 65 insertions(+), 22 deletions(-)

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

[PATCH 1/3] CMA: Fix the bug that CMA's page number is substructed twice

[Hui Zhu]

In Joonsoo's CMA patch "CMA: always treat free cma pages as non-free on
watermark checking" [1], it changes __zone_watermark_ok to substruct CMA
pages number from free_pages if system use CMA:
	if (IS_ENABLED(CONFIG_CMA) && z->managed_cma_pages)
		free_pages -= zone_page_state(z, NR_FREE_CMA_PAGES);

But after this part of code
	for (o = 0; o < order; o++) {
		/* At the next order, this order's pages become unavailable */
		free_pages -= z->free_area[o].nr_free << o;
CMA memory in each order is part of z->free_area[o].nr_free, then the CMA
page number of this order is substructed twice.  This bug will make
__zone_watermark_ok return more false.

This patch add cma_free_area to struct free_area that just record the number
of CMA pages.  And add it back in the order loop to handle the substruct
twice issue.

[1] https://lkml.org/lkml/2014/5/28/110

Signed-off-by: Hui Zhu <zhuhui@xiaomi.com>
Signed-off-by: Weixing Liu <liuweixing@xiaomi.com>
---
 include/linux/mmzone.h |  3 +++
 mm/page_alloc.c        | 29 ++++++++++++++++++++++++++++-
 2 files changed, 31 insertions(+), 1 deletion(-)

diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index ee1ce1f..7ccad93 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -92,6 +92,9 @@ static inline int get_pfnblock_migratetype(struct page *page, unsigned long pfn)
 struct free_area {
 	struct list_head	free_list[MIGRATE_TYPES];
 	unsigned long		nr_free;
+#ifdef CONFIG_CMA
+	unsigned long		cma_nr_free;
+#endif
 };
 
 struct pglist_data;
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 1b6c82c..a8d9f03 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -650,6 +650,8 @@ static inline void __free_one_page(struct page *page,
 		} else {
 			list_del(&buddy->lru);
 			zone->free_area[order].nr_free--;
+			if (is_migrate_cma(migratetype))
+				zone->free_area[order].cma_nr_free--;
 			rmv_page_order(buddy);
 		}
 		combined_idx = buddy_idx & page_idx;
@@ -683,6 +685,8 @@ static inline void __free_one_page(struct page *page,
 	list_add(&page->lru, &zone->free_area[order].free_list[migratetype]);
 out:
 	zone->free_area[order].nr_free++;
+	if (is_migrate_cma(migratetype))
+		zone->free_area[order].cma_nr_free++;
 }
 
 static inline int free_pages_check(struct page *page)
@@ -987,6 +991,8 @@ static inline void expand(struct zone *zone, struct page *page,
 		}
 		list_add(&page[size].lru, &area->free_list[migratetype]);
 		area->nr_free++;
+		if (is_migrate_cma(migratetype))
+			area->cma_nr_free++;
 		set_page_order(&page[size], high);
 	}
 }
@@ -1070,6 +1076,8 @@ struct page *__rmqueue_smallest(struct zone *zone, unsigned int order,
 		list_del(&page->lru);
 		rmv_page_order(page);
 		area->nr_free--;
+		if (is_migrate_cma(migratetype))
+			area->cma_nr_free--;
 		expand(zone, page, order, current_order, area, migratetype);
 		set_freepage_migratetype(page, migratetype);
 		return page;
@@ -1258,6 +1266,8 @@ __rmqueue_fallback(struct zone *zone, unsigned int order, int start_migratetype)
 			page = list_entry(area->free_list[migratetype].next,
 					struct page, lru);
 			area->nr_free--;
+			if (is_migrate_cma(migratetype))
+				area->cma_nr_free--;
 
 			new_type = try_to_steal_freepages(zone, page,
 							  start_migratetype,
@@ -1682,6 +1692,8 @@ int __isolate_free_page(struct page *page, unsigned int order)
 	/* Remove page from free list */
 	list_del(&page->lru);
 	zone->free_area[order].nr_free--;
+	if (is_migrate_cma(mt))
+		zone->free_area[order].cma_nr_free--;
 	rmv_page_order(page);
 
 	/* Set the pageblock if the isolated page is at least a pageblock */
@@ -1893,6 +1905,9 @@ static bool __zone_watermark_ok(struct zone *z, unsigned int order,
 	/* free_pages may go negative - that's OK */
 	long min = mark;
 	int o;
+#ifdef CONFIG_CMA
+	bool cma_is_subbed = false;
+#endif
 
 	free_pages -= (1 << order) - 1;
 	if (alloc_flags & ALLOC_HIGH)
@@ -1905,8 +1920,10 @@ static bool __zone_watermark_ok(struct zone *z, unsigned int order,
 	 * unmovable/reclaimable allocation and they can suddenly
 	 * vanish through CMA allocation
 	 */
-	if (IS_ENABLED(CONFIG_CMA) && z->managed_cma_pages)
+	if (IS_ENABLED(CONFIG_CMA) && z->managed_cma_pages) {
 		free_pages -= zone_page_state(z, NR_FREE_CMA_PAGES);
+		cma_is_subbed = true;
+	}
 
 	if (free_pages <= min + z->lowmem_reserve[classzone_idx])
 		return false;
@@ -1914,6 +1931,13 @@ static bool __zone_watermark_ok(struct zone *z, unsigned int order,
 		/* At the next order, this order's pages become unavailable */
 		free_pages -= z->free_area[o].nr_free << o;
 
+		/* If CMA's page number of this order was substructed as part
+		   of "zone_page_state(z, NR_FREE_CMA_PAGES)", subtracting
+		   "z->free_area[o].nr_free << o" substructed CMA's page
+		   number of this order again.  So add it back.  */
+		if (IS_ENABLED(CONFIG_CMA) && cma_is_subbed)
+			free_pages += z->free_area[o].cma_nr_free << o;
+
 		/* Require fewer higher order pages to be free */
 		min >>= 1;
 
@@ -4318,6 +4342,7 @@ static void __meminit zone_init_free_lists(struct zone *zone)
 	for_each_migratetype_order(order, t) {
 		INIT_LIST_HEAD(&zone->free_area[order].free_list[t]);
 		zone->free_area[order].nr_free = 0;
+		zone->free_area[order].cma_nr_free = 0;
 	}
 }
 
@@ -6691,6 +6716,8 @@ __offline_isolated_pages(unsigned long start_pfn, unsigned long end_pfn)
 		list_del(&page->lru);
 		rmv_page_order(page);
 		zone->free_area[order].nr_free--;
+		if (is_migrate_cma(get_pageblock_migratetype(page)))
+			zone->free_area[order].cma_nr_free--;
 		for (i = 0; i < (1 << order); i++)
 			SetPageReserved((page+i));
 		pfn += (1 << order);
-- 
1.9.1

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

Re: [PATCH 1/3] CMA: Fix the bug that CMA's page number is substructed twice

[Joonsoo Kim]

On Thu, Dec 25, 2014 at 05:43:26PM +0800, Hui Zhu wrote:
> In Joonsoo's CMA patch "CMA: always treat free cma pages as non-free on
> watermark checking" [1], it changes __zone_watermark_ok to substruct CMA
> pages number from free_pages if system use CMA:
> 	if (IS_ENABLED(CONFIG_CMA) && z->managed_cma_pages)
> 		free_pages -= zone_page_state(z, NR_FREE_CMA_PAGES);

Hello, 

In fact, without that patch, watermark checking has a problem in current kernel.
If there is reserved CMA region, watermark check for high order
allocation is done loosly. See following thread.

https://lkml.org/lkml/2014/5/30/320

Your patch can fix this situation, so, how about submitting this patch
separately?

Thanks.

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

Re: [PATCH 1/3] CMA: Fix the bug that CMA's page number is substructed twice

[Hui Zhu]

On Tue, Dec 30, 2014 at 12:48 PM, Joonsoo Kim <iamjoonsoo.kim@lge.com> wrote:
> On Thu, Dec 25, 2014 at 05:43:26PM +0800, Hui Zhu wrote:
>> In Joonsoo's CMA patch "CMA: always treat free cma pages as non-free on
>> watermark checking" [1], it changes __zone_watermark_ok to substruct CMA
>> pages number from free_pages if system use CMA:
>>       if (IS_ENABLED(CONFIG_CMA) && z->managed_cma_pages)
>>               free_pages -= zone_page_state(z, NR_FREE_CMA_PAGES);
>
> Hello,
>
> In fact, without that patch, watermark checking has a problem in current kernel.
> If there is reserved CMA region, watermark check for high order
> allocation is done loosly. See following thread.
>
> https://lkml.org/lkml/2014/5/30/320
>
> Your patch can fix this situation, so, how about submitting this patch
> separately?
>
> Thanks.
>

Hi Joonsoo,

Thanks for your remind.  I will post a separate patch for current kernel.

Thanks,
Hui

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

[PATCH 2/3] CMA: Fix the issue that nr_try_movable just count MIGRATE_MOVABLE memory

[Hui Zhu]

One of my plotform that use Joonsoo's CMA patch [1] has a device that
will alloc a lot of MIGRATE_UNMOVABLE memory when it works in a zone.
When this device works, the memory status of this zone is not OK.  Most of
CMA is not allocated but most normal memory is allocated.
This issue is because in __rmqueue:
	if (IS_ENABLED(CONFIG_CMA) &&
		migratetype == MIGRATE_MOVABLE && zone->managed_cma_pages)
		page = __rmqueue_cma(zone, order);
Just allocated MIGRATE_MOVABLE will be record in nr_try_movable in function
__rmqueue_cma but not the others.  This device allocated a lot of
MIGRATE_UNMOVABLE memory affect the behavior of this zone memory allocation.

This patch change __rmqueue to let nr_try_movable record all the memory
allocation of normal memory.

[1] https://lkml.org/lkml/2014/5/28/64

Signed-off-by: Hui Zhu <zhuhui@xiaomi.com>
Signed-off-by: Weixing Liu <liuweixing@xiaomi.com>
---
 mm/page_alloc.c | 41 ++++++++++++++++++++---------------------
 1 file changed, 20 insertions(+), 21 deletions(-)

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index a8d9f03..a5bbc38 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1301,28 +1301,23 @@ static struct page *__rmqueue_cma(struct zone *zone, unsigned int order)
 {
 	struct page *page;
 
-	if (zone->nr_try_movable > 0)
-		goto alloc_movable;
+	if (zone->nr_try_cma <= 0) {
+		/* Reset counter */
+		zone->nr_try_movable = zone->max_try_movable;
+		zone->nr_try_cma = zone->max_try_cma;
 
-	if (zone->nr_try_cma > 0) {
-		/* Okay. Now, we can try to allocate the page from cma region */
-		zone->nr_try_cma -= 1 << order;
-		page = __rmqueue_smallest(zone, order, MIGRATE_CMA);
-
-		/* CMA pages can vanish through CMA allocation */
-		if (unlikely(!page && order == 0))
-			zone->nr_try_cma = 0;
-
-		return page;
+		return NULL;
 	}
 
-	/* Reset counter */
-	zone->nr_try_movable = zone->max_try_movable;
-	zone->nr_try_cma = zone->max_try_cma;
+	/* Okay. Now, we can try to allocate the page from cma region */
+	zone->nr_try_cma -= 1 << order;
+	page = __rmqueue_smallest(zone, order, MIGRATE_CMA);
 
-alloc_movable:
-	zone->nr_try_movable -= 1 << order;
-	return NULL;
+	/* CMA pages can vanish through CMA allocation */
+	if (unlikely(!page && order == 0))
+		zone->nr_try_cma = 0;
+
+	return page;
 }
 #endif
 
@@ -1335,9 +1330,13 @@ static struct page *__rmqueue(struct zone *zone, unsigned int order,
 {
 	struct page *page = NULL;
 
-	if (IS_ENABLED(CONFIG_CMA) &&
-		migratetype == MIGRATE_MOVABLE && zone->managed_cma_pages)
-		page = __rmqueue_cma(zone, order);
+	if (IS_ENABLED(CONFIG_CMA) && zone->managed_cma_pages) {
+		if (migratetype == MIGRATE_MOVABLE
+		    && zone->nr_try_movable <= 0)
+			page = __rmqueue_cma(zone, order);
+		else
+			zone->nr_try_movable -= 1 << order;
+	}
 
 retry_reserve:
 	if (!page)
-- 
1.9.1

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

[PATCH 3/3] CMA: Add cma_alloc_counter to make cma_alloc work better if it meet busy range

[Hui Zhu]

In [1], Joonsoo said that cma_alloc_counter is useless because pageblock
is isolated.
But if alloc_contig_range meet a busy range, it will undo_isolate_page_range
before goto try next range. At this time, __rmqueue_cma can begin allocd
CMA memory from the range.

So I add cma_alloc_counter let __rmqueue doesn't call __rmqueue_cma when
cma_alloc works.

[1] https://lkml.org/lkml/2014/10/24/26

Signed-off-by: Hui Zhu <zhuhui@xiaomi.com>
---
 include/linux/cma.h | 2 ++
 mm/cma.c            | 6 ++++++
 mm/page_alloc.c     | 8 +++++++-
 3 files changed, 15 insertions(+), 1 deletion(-)

diff --git a/include/linux/cma.h b/include/linux/cma.h
index 9384ba6..155158f 100644
--- a/include/linux/cma.h
+++ b/include/linux/cma.h
@@ -26,6 +26,8 @@ extern int __init cma_declare_contiguous(phys_addr_t base,
 extern int cma_init_reserved_mem(phys_addr_t base,
 					phys_addr_t size, int order_per_bit,
 					struct cma **res_cma);
+
+extern atomic_t cma_alloc_counter;
 extern struct page *cma_alloc(struct cma *cma, int count, unsigned int align);
 extern bool cma_release(struct cma *cma, struct page *pages, int count);
 #endif
diff --git a/mm/cma.c b/mm/cma.c
index 6707b5d..b63f6be 100644
--- a/mm/cma.c
+++ b/mm/cma.c
@@ -348,6 +348,8 @@ err:
 	return ret;
 }
 
+atomic_t cma_alloc_counter = ATOMIC_INIT(0);
+
 /**
  * cma_alloc() - allocate pages from contiguous area
  * @cma:   Contiguous memory region for which the allocation is performed.
@@ -378,6 +380,8 @@ struct page *cma_alloc(struct cma *cma, int count, unsigned int align)
 	bitmap_maxno = cma_bitmap_maxno(cma);
 	bitmap_count = cma_bitmap_pages_to_bits(cma, count);
 
+	atomic_inc(&cma_alloc_counter);
+
 	for (;;) {
 		mutex_lock(&cma->lock);
 		bitmap_no = bitmap_find_next_zero_area_off(cma->bitmap,
@@ -415,6 +419,8 @@ struct page *cma_alloc(struct cma *cma, int count, unsigned int align)
 		start = bitmap_no + mask + 1;
 	}
 
+	atomic_dec(&cma_alloc_counter);
+
 	pr_debug("%s(): returned %p\n", __func__, page);
 	return page;
 }
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index a5bbc38..0622c4c 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -66,6 +66,10 @@
 #include <asm/div64.h>
 #include "internal.h"
 
+#ifdef CONFIG_CMA
+#include <linux/cma.h>
+#endif
+
 /* prevent >1 _updater_ of zone percpu pageset ->high and ->batch fields */
 static DEFINE_MUTEX(pcp_batch_high_lock);
 #define MIN_PERCPU_PAGELIST_FRACTION	(8)
@@ -1330,7 +1334,9 @@ static struct page *__rmqueue(struct zone *zone, unsigned int order,
 {
 	struct page *page = NULL;
 
-	if (IS_ENABLED(CONFIG_CMA) && zone->managed_cma_pages) {
+	if (IS_ENABLED(CONFIG_CMA)
+	    && zone->managed_cma_pages
+	    && atomic_read(&cma_alloc_counter) == 0) {
 		if (migratetype == MIGRATE_MOVABLE
 		    && zone->nr_try_movable <= 0)
 			page = __rmqueue_cma(zone, order);
-- 
1.9.1

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

Re: [PATCH 3/3] CMA: Add cma_alloc_counter to make cma_alloc work better if it meet busy range

[Joonsoo Kim]

On Thu, Dec 25, 2014 at 05:43:28PM +0800, Hui Zhu wrote:
> In [1], Joonsoo said that cma_alloc_counter is useless because pageblock
> is isolated.
> But if alloc_contig_range meet a busy range, it will undo_isolate_page_range
> before goto try next range. At this time, __rmqueue_cma can begin allocd
> CMA memory from the range.

Is there any real issue from this?
When failed, we will quickly re-isolate pageblock for adjacent page
so there is no big problem I guess.

If there is real issue, how about doing start_isolation/undo_isolation
in cma_alloc()? It would reduce useless do/undo isolation due to
failed trial.

Thanks.

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>