mm/page_alloc: fix memalloc_nocma_{save/restore} APIs

Currently, memalloc_nocma_{save/restore} API that prevents CMA area
in page allocation is implemented by using current_gfp_context(). However,
there are two problems of this implementation.

First, this doesn't work for allocation fastpath. In the fastpath,
original gfp_mask is used since current_gfp_context() is introduced in
order to control reclaim and it is on slowpath. So, CMA area can be
allocated through the allocation fastpath even if
memalloc_nocma_{save/restore} APIs are used. Currently, there is just
one user for these APIs and it has a fallback method to prevent actual
problem.
Second, clearing __GFP_MOVABLE in current_gfp_context() has a side effect
to exclude the memory on the ZONE_MOVABLE for allocation target.

To fix these problems, this patch changes the implementation to exclude
CMA area in page allocation. Main point of this change is using the
alloc_flags. alloc_flags is mainly used to control allocation so it fits
for excluding CMA area in allocation.

Fixes: d7fefcc (mm/cma: add PF flag to force non cma alloc)
Signed-off-by: Joonsoo Kim <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Reviewed-by: Vlastimil Babka <[email protected]>
Cc: Christoph Hellwig <[email protected]>
Cc: Roman Gushchin <[email protected]>
Cc: Mike Kravetz <[email protected]>
Cc: Naoya Horiguchi <[email protected]>
Cc: Michal Hocko <[email protected]>
Cc: "Aneesh Kumar K . V" <[email protected]>
Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: Linus Torvalds <[email protected]>

Author: JoonsooKim

include/linux/sched/mm.h

@@ -175,12 +175,10 @@ static inline bool in_vfork(struct task_struct *tsk)
  * Applies per-task gfp context to the given allocation flags.
  * PF_MEMALLOC_NOIO implies GFP_NOIO
  * PF_MEMALLOC_NOFS implies GFP_NOFS
- * PF_MEMALLOC_NOCMA implies no allocation from CMA region.
  */
 static inline gfp_t current_gfp_context(gfp_t flags)
 {
-	if (unlikely(current->flags &
-		     (PF_MEMALLOC_NOIO | PF_MEMALLOC_NOFS | PF_MEMALLOC_NOCMA))) {
+	if (unlikely(current->flags & (PF_MEMALLOC_NOIO | PF_MEMALLOC_NOFS))) {
 		/*
 		 * NOIO implies both NOIO and NOFS and it is a weaker context
 		 * so always make sure it makes precedence
@@ -189,10 +187,6 @@ static inline gfp_t current_gfp_context(gfp_t flags)
 			flags &= ~(__GFP_IO | __GFP_FS);
 		else if (current->flags & PF_MEMALLOC_NOFS)
 			flags &= ~__GFP_FS;
-#ifdef CONFIG_CMA
-		if (current->flags & PF_MEMALLOC_NOCMA)
-			flags &= ~__GFP_MOVABLE;
-#endif
 	}
 	return flags;
 }

mm/page_alloc.c

@@ -2785,7 +2785,7 @@ __rmqueue(struct zone *zone, unsigned int order, int migratetype,
 	 * allocating from CMA when over half of the zone's free memory
 	 * is in the CMA area.
 	 */
-	if (migratetype == MIGRATE_MOVABLE &&
+	if (alloc_flags & ALLOC_CMA &&
 	    zone_page_state(zone, NR_FREE_CMA_PAGES) >
 	    zone_page_state(zone, NR_FREE_PAGES) / 2) {
 		page = __rmqueue_cma_fallback(zone, order);
@@ -2796,7 +2796,7 @@ __rmqueue(struct zone *zone, unsigned int order, int migratetype,
 retry:
 	page = __rmqueue_smallest(zone, order, migratetype);
 	if (unlikely(!page)) {
-		if (migratetype == MIGRATE_MOVABLE)
+		if (alloc_flags & ALLOC_CMA)
 			page = __rmqueue_cma_fallback(zone, order);
 
 		if (!page && __rmqueue_fallback(zone, order, migratetype,
@@ -3687,6 +3687,20 @@ alloc_flags_nofragment(struct zone *zone, gfp_t gfp_mask)
 	return alloc_flags;
 }
 
+static inline unsigned int current_alloc_flags(gfp_t gfp_mask,
+					unsigned int alloc_flags)
+{
+#ifdef CONFIG_CMA
+	unsigned int pflags = current->flags;
+
+	if (!(pflags & PF_MEMALLOC_NOCMA) &&
+			gfp_migratetype(gfp_mask) == MIGRATE_MOVABLE)
+		alloc_flags |= ALLOC_CMA;
+
+#endif
+	return alloc_flags;
+}
+
 /*
  * get_page_from_freelist goes through the zonelist trying to allocate
  * a page.
@@ -4333,10 +4347,8 @@ gfp_to_alloc_flags(gfp_t gfp_mask)
 	} else if (unlikely(rt_task(current)) && !in_interrupt())
 		alloc_flags |= ALLOC_HARDER;
 
-#ifdef CONFIG_CMA
-	if (gfp_migratetype(gfp_mask) == MIGRATE_MOVABLE)
-		alloc_flags |= ALLOC_CMA;
-#endif
+	alloc_flags = current_alloc_flags(gfp_mask, alloc_flags);
+
 	return alloc_flags;
 }
 
@@ -4637,7 +4649,7 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
 
 	reserve_flags = __gfp_pfmemalloc_flags(gfp_mask);
 	if (reserve_flags)
-		alloc_flags = reserve_flags;
+		alloc_flags = current_alloc_flags(gfp_mask, reserve_flags);
 
 	/*
 	 * Reset the nodemask and zonelist iterators if memory policies can be
@@ -4714,7 +4726,7 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
 
 	/* Avoid allocations with no watermarks from looping endlessly */
 	if (tsk_is_oom_victim(current) &&
-	    (alloc_flags == ALLOC_OOM ||
+	    (alloc_flags & ALLOC_OOM ||
 	     (gfp_mask & __GFP_NOMEMALLOC)))
 		goto nopage;
 
@@ -4806,8 +4818,7 @@ static inline bool prepare_alloc_pages(gfp_t gfp_mask, unsigned int order,
 	if (should_fail_alloc_page(gfp_mask, order))
 		return false;
 
-	if (IS_ENABLED(CONFIG_CMA) && ac->migratetype == MIGRATE_MOVABLE)
-		*alloc_flags |= ALLOC_CMA;
+	*alloc_flags = current_alloc_flags(gfp_mask, *alloc_flags);
 
 	return true;
 }