RE: [PATCH v2 1/8] mm/cma: change cma mutex to irq safe spinlock

[Song Bao Hua (Barry Song)]

> -----Original Message-----
> From: Mike Kravetz [mailto:mike.kravetz@xxxxxxxxxx]
> Sent: Tuesday, March 30, 2021 12:24 PM
> To: linux-mm@xxxxxxxxx; linux-kernel@xxxxxxxxxxxxxxx
> Cc: Roman Gushchin <guro@xxxxxx>; Michal Hocko <mhocko@xxxxxxxx>; Shakeel Butt
> <shakeelb@xxxxxxxxxx>; Oscar Salvador <osalvador@xxxxxxx>; David Hildenbrand
> <david@xxxxxxxxxx>; Muchun Song <songmuchun@xxxxxxxxxxxxx>; David Rientjes
> <rientjes@xxxxxxxxxx>; linmiaohe <linmiaohe@xxxxxxxxxx>; Peter Zijlstra
> <peterz@xxxxxxxxxxxxx>; Matthew Wilcox <willy@xxxxxxxxxxxxx>; HORIGUCHI NAOYA
> <naoya.horiguchi@xxxxxxx>; Aneesh Kumar K . V <aneesh.kumar@xxxxxxxxxxxxx>;
> Waiman Long <longman@xxxxxxxxxx>; Peter Xu <peterx@xxxxxxxxxx>; Mina Almasry
> <almasrymina@xxxxxxxxxx>; Hillf Danton <hdanton@xxxxxxxx>; Joonsoo Kim
> <iamjoonsoo.kim@xxxxxxx>; Song Bao Hua (Barry Song)
> <song.bao.hua@xxxxxxxxxxxxx>; Will Deacon <will@xxxxxxxxxx>; Andrew Morton
> <akpm@xxxxxxxxxxxxxxxxxxxx>; Mike Kravetz <mike.kravetz@xxxxxxxxxx>
> Subject: [PATCH v2 1/8] mm/cma: change cma mutex to irq safe spinlock
> 
> Ideally, cma_release could be called from any context.  However, that is
> not possible because a mutex is used to protect the per-area bitmap.
> Change the bitmap to an irq safe spinlock.
> 
> Signed-off-by: Mike Kravetz <mike.kravetz@xxxxxxxxxx>

It seems mutex_lock is locking some areas with bitmap operations which
should be safe to atomic context.

Reviewed-by: Barry Song <song.bao.hua@xxxxxxxxxxxxx>

> ---
>  mm/cma.c       | 20 +++++++++++---------
>  mm/cma.h       |  2 +-
>  mm/cma_debug.c | 10 ++++++----
>  3 files changed, 18 insertions(+), 14 deletions(-)
> 
> diff --git a/mm/cma.c b/mm/cma.c
> index b2393b892d3b..80875fd4487b 100644
> --- a/mm/cma.c
> +++ b/mm/cma.c
> @@ -24,7 +24,6 @@
>  #include <linux/memblock.h>
>  #include <linux/err.h>
>  #include <linux/mm.h>
> -#include <linux/mutex.h>
>  #include <linux/sizes.h>
>  #include <linux/slab.h>
>  #include <linux/log2.h>
> @@ -83,13 +82,14 @@ static void cma_clear_bitmap(struct cma *cma, unsigned long
> pfn,
>  			     unsigned int count)
>  {
>  	unsigned long bitmap_no, bitmap_count;
> +	unsigned long flags;
> 
>  	bitmap_no = (pfn - cma->base_pfn) >> cma->order_per_bit;
>  	bitmap_count = cma_bitmap_pages_to_bits(cma, count);
> 
> -	mutex_lock(&cma->lock);
> +	spin_lock_irqsave(&cma->lock, flags);
>  	bitmap_clear(cma->bitmap, bitmap_no, bitmap_count);
> -	mutex_unlock(&cma->lock);
> +	spin_unlock_irqrestore(&cma->lock, flags);
>  }
> 
>  static void __init cma_activate_area(struct cma *cma)
> @@ -118,7 +118,7 @@ static void __init cma_activate_area(struct cma *cma)
>  	     pfn += pageblock_nr_pages)
>  		init_cma_reserved_pageblock(pfn_to_page(pfn));
> 
> -	mutex_init(&cma->lock);
> +	spin_lock_init(&cma->lock);
> 
>  #ifdef CONFIG_CMA_DEBUGFS
>  	INIT_HLIST_HEAD(&cma->mem_head);
> @@ -391,8 +391,9 @@ static void cma_debug_show_areas(struct cma *cma)
>  	unsigned long start = 0;
>  	unsigned long nr_part, nr_total = 0;
>  	unsigned long nbits = cma_bitmap_maxno(cma);
> +	unsigned long flags;
> 
> -	mutex_lock(&cma->lock);
> +	spin_lock_irqsave(&cma->lock, flags);
>  	pr_info("number of available pages: ");
>  	for (;;) {
>  		next_zero_bit = find_next_zero_bit(cma->bitmap, nbits, start);
> @@ -407,7 +408,7 @@ static void cma_debug_show_areas(struct cma *cma)
>  		start = next_zero_bit + nr_zero;
>  	}
>  	pr_cont("=> %lu free of %lu total pages\n", nr_total, cma->count);
> -	mutex_unlock(&cma->lock);
> +	spin_unlock_irqrestore(&cma->lock, flags);
>  }
>  #else
>  static inline void cma_debug_show_areas(struct cma *cma) { }
> @@ -430,6 +431,7 @@ struct page *cma_alloc(struct cma *cma, size_t count,
> unsigned int align,
>  	unsigned long pfn = -1;
>  	unsigned long start = 0;
>  	unsigned long bitmap_maxno, bitmap_no, bitmap_count;
> +	unsigned long flags;
>  	size_t i;
>  	struct page *page = NULL;
>  	int ret = -ENOMEM;
> @@ -454,12 +456,12 @@ struct page *cma_alloc(struct cma *cma, size_t count,
> unsigned int align,
>  		goto out;
> 
>  	for (;;) {
> -		mutex_lock(&cma->lock);
> +		spin_lock_irqsave(&cma->lock, flags);
>  		bitmap_no = bitmap_find_next_zero_area_off(cma->bitmap,
>  				bitmap_maxno, start, bitmap_count, mask,
>  				offset);
>  		if (bitmap_no >= bitmap_maxno) {
> -			mutex_unlock(&cma->lock);
> +			spin_unlock_irqrestore(&cma->lock, flags);
>  			break;
>  		}
>  		bitmap_set(cma->bitmap, bitmap_no, bitmap_count);
> @@ -468,7 +470,7 @@ struct page *cma_alloc(struct cma *cma, size_t count,
> unsigned int align,
>  		 * our exclusive use. If the migration fails we will take the
>  		 * lock again and unmark it.
>  		 */
> -		mutex_unlock(&cma->lock);
> +		spin_unlock_irqrestore(&cma->lock, flags);
> 
>  		pfn = cma->base_pfn + (bitmap_no << cma->order_per_bit);
>  		ret = alloc_contig_range(pfn, pfn + count, MIGRATE_CMA,
> diff --git a/mm/cma.h b/mm/cma.h
> index 68ffad4e430d..2c775877eae2 100644
> --- a/mm/cma.h
> +++ b/mm/cma.h
> @@ -15,7 +15,7 @@ struct cma {
>  	unsigned long   count;
>  	unsigned long   *bitmap;
>  	unsigned int order_per_bit; /* Order of pages represented by one bit */
> -	struct mutex    lock;
> +	spinlock_t	lock;
>  #ifdef CONFIG_CMA_DEBUGFS
>  	struct hlist_head mem_head;
>  	spinlock_t mem_head_lock;
> diff --git a/mm/cma_debug.c b/mm/cma_debug.c
> index d5bf8aa34fdc..6379cfbfd568 100644
> --- a/mm/cma_debug.c
> +++ b/mm/cma_debug.c
> @@ -35,11 +35,12 @@ static int cma_used_get(void *data, u64 *val)
>  {
>  	struct cma *cma = data;
>  	unsigned long used;
> +	unsigned long flags;
> 
> -	mutex_lock(&cma->lock);
> +	spin_lock_irqsave(&cma->lock, flags);
>  	/* pages counter is smaller than sizeof(int) */
>  	used = bitmap_weight(cma->bitmap, (int)cma_bitmap_maxno(cma));
> -	mutex_unlock(&cma->lock);
> +	spin_unlock_irqrestore(&cma->lock, flags);
>  	*val = (u64)used << cma->order_per_bit;
> 
>  	return 0;
> @@ -52,8 +53,9 @@ static int cma_maxchunk_get(void *data, u64 *val)
>  	unsigned long maxchunk = 0;
>  	unsigned long start, end = 0;
>  	unsigned long bitmap_maxno = cma_bitmap_maxno(cma);
> +	unsigned long flags;
> 
> -	mutex_lock(&cma->lock);
> +	spin_lock_irqsave(&cma->lock, flags);
>  	for (;;) {
>  		start = find_next_zero_bit(cma->bitmap, bitmap_maxno, end);
>  		if (start >= bitmap_maxno)
> @@ -61,7 +63,7 @@ static int cma_maxchunk_get(void *data, u64 *val)
>  		end = find_next_bit(cma->bitmap, bitmap_maxno, start);
>  		maxchunk = max(end - start, maxchunk);
>  	}
> -	mutex_unlock(&cma->lock);
> +	spin_unlock_irqrestore(&cma->lock, flags);
>  	*val = (u64)maxchunk << cma->order_per_bit;
> 
>  	return 0;
> --
> 2.30.2