mm: introduce memalloc_noreclaim_{save,restore}

The previous patch ("mm: prevent potential recursive reclaim due to
clearing PF_MEMALLOC") has shown that simply setting and clearing
PF_MEMALLOC in current->flags can result in wrongly clearing a
pre-existing PF_MEMALLOC flag and potentially lead to recursive reclaim.
Let's introduce helpers that support proper nesting by saving the
previous stat of the flag, similar to the existing memalloc_noio_* and
memalloc_nofs_* helpers.  Convert existing setting/clearing of
PF_MEMALLOC within mm to the new helpers.

There are no known issues with the converted code, but the change makes
it more robust.

Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: Vlastimil Babka <[email protected]>
Suggested-by: Michal Hocko <[email protected]>
Acked-by: Michal Hocko <[email protected]>
Acked-by: Hillf Danton <[email protected]>
Cc: Mel Gorman <[email protected]>
Cc: Johannes Weiner <[email protected]>
Cc: Andrey Ryabinin <[email protected]>
Cc: Boris Brezillon <[email protected]>
Cc: Chris Leech <[email protected]>
Cc: "David S. Miller" <[email protected]>
Cc: Eric Dumazet <[email protected]>
Cc: Josef Bacik <[email protected]>
Cc: Lee Duncan <[email protected]>
Cc: Michal Hocko <[email protected]>
Cc: Richard Weinberger <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>

include/linux/sched/mm.h

@@ -191,4 +191,16 @@ static inline void memalloc_nofs_restore(unsigned int flags)
 	current->flags = (current->flags & ~PF_MEMALLOC_NOFS) | flags;
 }
 
+static inline unsigned int memalloc_noreclaim_save(void)
+{
+	unsigned int flags = current->flags & PF_MEMALLOC;
+	current->flags |= PF_MEMALLOC;
+	return flags;
+}
+
+static inline void memalloc_noreclaim_restore(unsigned int flags)
+{
+	current->flags = (current->flags & ~PF_MEMALLOC) | flags;
+}
+
 #endif /* _LINUX_SCHED_MM_H */

mm/page_alloc.c

@@ -3283,15 +3283,15 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
 		enum compact_priority prio, enum compact_result *compact_result)
 {
 	struct page *page;
-	unsigned int noreclaim_flag = current->flags & PF_MEMALLOC;
+	unsigned int noreclaim_flag;
 
 	if (!order)
 		return NULL;
 
-	current->flags |= PF_MEMALLOC;
+	noreclaim_flag = memalloc_noreclaim_save();
 	*compact_result = try_to_compact_pages(gfp_mask, order, alloc_flags, ac,
 									prio);
-	current->flags = (current->flags & ~PF_MEMALLOC) | noreclaim_flag;
+	memalloc_noreclaim_restore(noreclaim_flag);
 
 	if (*compact_result <= COMPACT_INACTIVE)
 		return NULL;
@@ -3438,12 +3438,13 @@ __perform_reclaim(gfp_t gfp_mask, unsigned int order,
 {
 	struct reclaim_state reclaim_state;
 	int progress;
+	unsigned int noreclaim_flag;
 
 	cond_resched();
 
 	/* We now go into synchronous reclaim */
 	cpuset_memory_pressure_bump();
-	current->flags |= PF_MEMALLOC;
+	noreclaim_flag = memalloc_noreclaim_save();
 	lockdep_set_current_reclaim_state(gfp_mask);
 	reclaim_state.reclaimed_slab = 0;
 	current->reclaim_state = &reclaim_state;
@@ -3453,7 +3454,7 @@ __perform_reclaim(gfp_t gfp_mask, unsigned int order,
 
 	current->reclaim_state = NULL;
 	lockdep_clear_current_reclaim_state();
-	current->flags &= ~PF_MEMALLOC;
+	memalloc_noreclaim_restore(noreclaim_flag);
 
 	cond_resched();
 

mm/vmscan.c

@@ -3036,6 +3036,7 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg,
 	struct zonelist *zonelist;
 	unsigned long nr_reclaimed;
 	int nid;
+	unsigned int noreclaim_flag;
 	struct scan_control sc = {
 		.nr_to_reclaim = max(nr_pages, SWAP_CLUSTER_MAX),
 		.gfp_mask = (current_gfp_context(gfp_mask) & GFP_RECLAIM_MASK) |
@@ -3062,9 +3063,9 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg,
 					    sc.gfp_mask,
 					    sc.reclaim_idx);
 
-	current->flags |= PF_MEMALLOC;
+	noreclaim_flag = memalloc_noreclaim_save();
 	nr_reclaimed = do_try_to_free_pages(zonelist, &sc);
-	current->flags &= ~PF_MEMALLOC;
+	memalloc_noreclaim_restore(noreclaim_flag);
 
 	trace_mm_vmscan_memcg_reclaim_end(nr_reclaimed);
 
@@ -3589,8 +3590,9 @@ unsigned long shrink_all_memory(unsigned long nr_to_reclaim)
 	struct zonelist *zonelist = node_zonelist(numa_node_id(), sc.gfp_mask);
 	struct task_struct *p = current;
 	unsigned long nr_reclaimed;
+	unsigned int noreclaim_flag;
 
-	p->flags |= PF_MEMALLOC;
+	noreclaim_flag = memalloc_noreclaim_save();
 	lockdep_set_current_reclaim_state(sc.gfp_mask);
 	reclaim_state.reclaimed_slab = 0;
 	p->reclaim_state = &reclaim_state;
@@ -3599,7 +3601,7 @@ unsigned long shrink_all_memory(unsigned long nr_to_reclaim)
 
 	p->reclaim_state = NULL;
 	lockdep_clear_current_reclaim_state();
-	p->flags &= ~PF_MEMALLOC;
+	memalloc_noreclaim_restore(noreclaim_flag);
 
 	return nr_reclaimed;
 }
@@ -3764,6 +3766,7 @@ static int __node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, unsigned in
 	struct task_struct *p = current;
 	struct reclaim_state reclaim_state;
 	int classzone_idx = gfp_zone(gfp_mask);
+	unsigned int noreclaim_flag;
 	struct scan_control sc = {
 		.nr_to_reclaim = max(nr_pages, SWAP_CLUSTER_MAX),
 		.gfp_mask = (gfp_mask = current_gfp_context(gfp_mask)),
@@ -3781,7 +3784,8 @@ static int __node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, unsigned in
 	 * and we also need to be able to write out pages for RECLAIM_WRITE
 	 * and RECLAIM_UNMAP.
 	 */
-	p->flags |= PF_MEMALLOC | PF_SWAPWRITE;
+	noreclaim_flag = memalloc_noreclaim_save();
+	p->flags |= PF_SWAPWRITE;
 	lockdep_set_current_reclaim_state(gfp_mask);
 	reclaim_state.reclaimed_slab = 0;
 	p->reclaim_state = &reclaim_state;
@@ -3797,7 +3801,8 @@ static int __node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, unsigned in
 	}
 
 	p->reclaim_state = NULL;
-	current->flags &= ~(PF_MEMALLOC | PF_SWAPWRITE);
+	current->flags &= ~PF_SWAPWRITE;
+	memalloc_noreclaim_restore(noreclaim_flag);
 	lockdep_clear_current_reclaim_state();
 	return sc.nr_reclaimed >= nr_pages;
 }