percpu: split __pcpu_balance_workfn()

__pcpu_balance_workfn() became fairly big and hard to follow, but in
fact it consists of two fully independent parts, responsible for
the destruction of excessive free chunks and population of necessarily
amount of free pages.

In order to simplify the code and prepare for adding of a new
functionality, split it in two functions:

  1) pcpu_balance_free,
  2) pcpu_balance_populated.

Move the taking/releasing of the pcpu_alloc_mutex to an upper level
to keep the current synchronization in place.
Signed-off-by: NRoman Gushchin <guro@fb.com>
Reviewed-by: NDennis Zhou <dennis@kernel.org>
Signed-off-by: NDennis Zhou <dennis@kernel.org>

mm/percpu.c

@@ -1933,31 +1933,22 @@ void __percpu *__alloc_reserved_percpu(size_t size, size_t align)
 }
 
 /**
- * __pcpu_balance_workfn - manage the amount of free chunks and populated pages
+ * pcpu_balance_free - manage the amount of free chunks
  * @type: chunk type
  *
- * Reclaim all fully free chunks except for the first one.  This is also
- * responsible for maintaining the pool of empty populated pages.  However,
- * it is possible that this is called when physical memory is scarce causing
- * OOM killer to be triggered.  We should avoid doing so until an actual
- * allocation causes the failure as it is possible that requests can be
- * serviced from already backed regions.
+ * Reclaim all fully free chunks except for the first one.
  */
-static void __pcpu_balance_workfn(enum pcpu_chunk_type type)
+static void pcpu_balance_free(enum pcpu_chunk_type type)
 {
-	/* gfp flags passed to underlying allocators */
-	const gfp_t gfp = GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN;
 	LIST_HEAD(to_free);
 	struct list_head *pcpu_slot = pcpu_chunk_list(type);
 	struct list_head *free_head = &pcpu_slot[pcpu_nr_slots - 1];
 	struct pcpu_chunk *chunk, *next;
-	int slot, nr_to_pop, ret;
 
 	/*
 	 * There's no reason to keep around multiple unused chunks and VM
 	 * areas can be scarce.  Destroy all free chunks except for one.
 	 */
-	mutex_lock(&pcpu_alloc_mutex);
 	spin_lock_irq(&pcpu_lock);
 
 	list_for_each_entry_safe(chunk, next, free_head, list) {
@@ -1985,6 +1976,25 @@ static void __pcpu_balance_workfn(enum pcpu_chunk_type type)
 		pcpu_destroy_chunk(chunk);
 		cond_resched();
 	}
+}
+
+/**
+ * pcpu_balance_populated - manage the amount of populated pages
+ * @type: chunk type
+ *
+ * Maintain a certain amount of populated pages to satisfy atomic allocations.
+ * It is possible that this is called when physical memory is scarce causing
+ * OOM killer to be triggered.  We should avoid doing so until an actual
+ * allocation causes the failure as it is possible that requests can be
+ * serviced from already backed regions.
+ */
+static void pcpu_balance_populated(enum pcpu_chunk_type type)
+{
+	/* gfp flags passed to underlying allocators */
+	const gfp_t gfp = GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN;
+	struct list_head *pcpu_slot = pcpu_chunk_list(type);
+	struct pcpu_chunk *chunk;
+	int slot, nr_to_pop, ret;
 
 	/*
 	 * Ensure there are certain number of free populated pages for
@@ -2054,22 +2064,24 @@ static void __pcpu_balance_workfn(enum pcpu_chunk_type type)
 			goto retry_pop;
 		}
 	}
-
-	mutex_unlock(&pcpu_alloc_mutex);
 }
 
 /**
  * pcpu_balance_workfn - manage the amount of free chunks and populated pages
  * @work: unused
  *
- * Call __pcpu_balance_workfn() for each chunk type.
+ * Call pcpu_balance_free() and pcpu_balance_populated() for each chunk type.
  */
 static void pcpu_balance_workfn(struct work_struct *work)
 {
 	enum pcpu_chunk_type type;
 
-	for (type = 0; type < PCPU_NR_CHUNK_TYPES; type++)
-		__pcpu_balance_workfn(type);
+	for (type = 0; type < PCPU_NR_CHUNK_TYPES; type++) {
+		mutex_lock(&pcpu_alloc_mutex);
+		pcpu_balance_free(type);
+		pcpu_balance_populated(type);
+		mutex_unlock(&pcpu_alloc_mutex);
+	}
 }
 
 /**