percpu: rework memcg accounting

The current implementation of the memcg accounting of the percpu
memory is based on the idea of having two separate sets of chunks for
accounted and non-accounted memory. This approach has an advantage
of not wasting any extra memory for memcg data for non-accounted
chunks, however it complicates the code and leads to a higher chunks
number due to a lower chunk utilization.

Instead of having two chunk types it's possible to declare all* chunks
memcg-aware unless the kernel memory accounting is disabled globally
by a boot option. The size of objcg_array is usually small in
comparison to chunks themselves (it obviously depends on the number of
CPUs), so even if some chunk will have no accounted allocations, the
memory waste isn't significant and will likely be compensated by
a higher chunk utilization. Also, with time more and more percpu
allocations will likely become accounted.

* The first chunk is initialized before the memory cgroup subsystem,
  so we don't know for sure whether we need to allocate obj_cgroups.
  Because it's small, let's make it free for use. Then we don't need
  to allocate obj_cgroups for it.

Signed-off-by: Roman Gushchin <[email protected]>
Signed-off-by: Dennis Zhou <[email protected]>

Author: rgushchin

mm/percpu-internal.h

@@ -5,25 +5,6 @@
 #include <linux/types.h>
 #include <linux/percpu.h>
 
-/*
- * There are two chunk types: root and memcg-aware.
- * Chunks of each type have separate slots list.
- *
- * Memcg-aware chunks have an attached vector of obj_cgroup pointers, which is
- * used to store memcg membership data of a percpu object.  Obj_cgroups are
- * ref-counted pointers to a memory cgroup with an ability to switch dynamically
- * to the parent memory cgroup.  This allows to reclaim a deleted memory cgroup
- * without reclaiming of all outstanding objects, which hold a reference at it.
- */
-enum pcpu_chunk_type {
-	PCPU_CHUNK_ROOT,
-#ifdef CONFIG_MEMCG_KMEM
-	PCPU_CHUNK_MEMCG,
-#endif
-	PCPU_NR_CHUNK_TYPES,
-	PCPU_FAIL_ALLOC = PCPU_NR_CHUNK_TYPES
-};
-
 /*
  * pcpu_block_md is the metadata block struct.
  * Each chunk's bitmap is split into a number of full blocks.
@@ -91,7 +72,7 @@ extern struct list_head *pcpu_chunk_lists;
 extern int pcpu_nr_slots;
 extern int pcpu_sidelined_slot;
 extern int pcpu_to_depopulate_slot;
-extern int pcpu_nr_empty_pop_pages[];
+extern int pcpu_nr_empty_pop_pages;
 
 extern struct pcpu_chunk *pcpu_first_chunk;
 extern struct pcpu_chunk *pcpu_reserved_chunk;
@@ -132,37 +113,6 @@ static inline int pcpu_chunk_map_bits(struct pcpu_chunk *chunk)
 	return pcpu_nr_pages_to_map_bits(chunk->nr_pages);
 }
 
-#ifdef CONFIG_MEMCG_KMEM
-static inline enum pcpu_chunk_type pcpu_chunk_type(struct pcpu_chunk *chunk)
-{
-	if (chunk->obj_cgroups)
-		return PCPU_CHUNK_MEMCG;
-	return PCPU_CHUNK_ROOT;
-}
-
-static inline bool pcpu_is_memcg_chunk(enum pcpu_chunk_type chunk_type)
-{
-	return chunk_type == PCPU_CHUNK_MEMCG;
-}
-
-#else
-static inline enum pcpu_chunk_type pcpu_chunk_type(struct pcpu_chunk *chunk)
-{
-	return PCPU_CHUNK_ROOT;
-}
-
-static inline bool pcpu_is_memcg_chunk(enum pcpu_chunk_type chunk_type)
-{
-	return false;
-}
-#endif
-
-static inline struct list_head *pcpu_chunk_list(enum pcpu_chunk_type chunk_type)
-{
-	return &pcpu_chunk_lists[pcpu_nr_slots *
-				 pcpu_is_memcg_chunk(chunk_type)];
-}
-
 #ifdef CONFIG_PERCPU_STATS
 
 #include <linux/spinlock.h>

mm/percpu-km.c

@@ -44,16 +44,15 @@ static void pcpu_depopulate_chunk(struct pcpu_chunk *chunk,
 	/* nada */
 }
 
-static struct pcpu_chunk *pcpu_create_chunk(enum pcpu_chunk_type type,
-					    gfp_t gfp)
+static struct pcpu_chunk *pcpu_create_chunk(gfp_t gfp)
 {
 	const int nr_pages = pcpu_group_sizes[0] >> PAGE_SHIFT;
 	struct pcpu_chunk *chunk;
 	struct page *pages;
 	unsigned long flags;
 	int i;
 
-	chunk = pcpu_alloc_chunk(type, gfp);
+	chunk = pcpu_alloc_chunk(gfp);
 	if (!chunk)
 		return NULL;
 

mm/percpu-stats.c

@@ -34,15 +34,11 @@ static int find_max_nr_alloc(void)
 {
 	struct pcpu_chunk *chunk;
 	int slot, max_nr_alloc;
-	enum pcpu_chunk_type type;
 
 	max_nr_alloc = 0;
-	for (type = 0; type < PCPU_NR_CHUNK_TYPES; type++)
-		for (slot = 0; slot < pcpu_nr_slots; slot++)
-			list_for_each_entry(chunk, &pcpu_chunk_list(type)[slot],
-					    list)
-				max_nr_alloc = max(max_nr_alloc,
-						   chunk->nr_alloc);
+	for (slot = 0; slot < pcpu_nr_slots; slot++)
+		list_for_each_entry(chunk, &pcpu_chunk_lists[slot], list)
+			max_nr_alloc = max(max_nr_alloc, chunk->nr_alloc);
 
 	return max_nr_alloc;
 }
@@ -133,9 +129,6 @@ static void chunk_map_stats(struct seq_file *m, struct pcpu_chunk *chunk,
 	P("cur_min_alloc", cur_min_alloc);
 	P("cur_med_alloc", cur_med_alloc);
 	P("cur_max_alloc", cur_max_alloc);
-#ifdef CONFIG_MEMCG_KMEM
-	P("memcg_aware", pcpu_is_memcg_chunk(pcpu_chunk_type(chunk)));
-#endif
 	seq_putc(m, '\n');
 }
 
@@ -144,8 +137,6 @@ static int percpu_stats_show(struct seq_file *m, void *v)
 	struct pcpu_chunk *chunk;
 	int slot, max_nr_alloc;
 	int *buffer;
-	enum pcpu_chunk_type type;
-	int nr_empty_pop_pages;
 
 alloc_buffer:
 	spin_lock_irq(&pcpu_lock);
@@ -166,10 +157,6 @@ static int percpu_stats_show(struct seq_file *m, void *v)
 		goto alloc_buffer;
 	}
 
-	nr_empty_pop_pages = 0;
-	for (type = 0; type < PCPU_NR_CHUNK_TYPES; type++)
-		nr_empty_pop_pages += pcpu_nr_empty_pop_pages[type];
-
 #define PL(X)								\
 	seq_printf(m, "  %-20s: %12lld\n", #X, (long long int)pcpu_stats_ai.X)
 
@@ -201,7 +188,7 @@ static int percpu_stats_show(struct seq_file *m, void *v)
 	PU(nr_max_chunks);
 	PU(min_alloc_size);
 	PU(max_alloc_size);
-	P("empty_pop_pages", nr_empty_pop_pages);
+	P("empty_pop_pages", pcpu_nr_empty_pop_pages);
 	seq_putc(m, '\n');
 
 #undef PU
@@ -215,20 +202,17 @@ static int percpu_stats_show(struct seq_file *m, void *v)
 		chunk_map_stats(m, pcpu_reserved_chunk, buffer);
 	}
 
-	for (type = 0; type < PCPU_NR_CHUNK_TYPES; type++) {
-		for (slot = 0; slot < pcpu_nr_slots; slot++) {
-			list_for_each_entry(chunk, &pcpu_chunk_list(type)[slot],
-					    list) {
-				if (chunk == pcpu_first_chunk)
-					seq_puts(m, "Chunk: <- First Chunk\n");
-				else if (slot == pcpu_to_depopulate_slot)
-					seq_puts(m, "Chunk (to_depopulate)\n");
-				else if (slot == pcpu_sidelined_slot)
-					seq_puts(m, "Chunk (sidelined):\n");
-				else
-					seq_puts(m, "Chunk:\n");
-				chunk_map_stats(m, chunk, buffer);
-			}
+	for (slot = 0; slot < pcpu_nr_slots; slot++) {
+		list_for_each_entry(chunk, &pcpu_chunk_lists[slot], list) {
+			if (chunk == pcpu_first_chunk)
+				seq_puts(m, "Chunk: <- First Chunk\n");
+			else if (slot == pcpu_to_depopulate_slot)
+				seq_puts(m, "Chunk (to_depopulate)\n");
+			else if (slot == pcpu_sidelined_slot)
+				seq_puts(m, "Chunk (sidelined):\n");
+			else
+				seq_puts(m, "Chunk:\n");
+			chunk_map_stats(m, chunk, buffer);
 		}
 	}
 

mm/percpu-vm.c

@@ -328,13 +328,12 @@ static void pcpu_depopulate_chunk(struct pcpu_chunk *chunk,
 	pcpu_free_pages(chunk, pages, page_start, page_end);
 }
 
-static struct pcpu_chunk *pcpu_create_chunk(enum pcpu_chunk_type type,
-					    gfp_t gfp)
+static struct pcpu_chunk *pcpu_create_chunk(gfp_t gfp)
 {
 	struct pcpu_chunk *chunk;
 	struct vm_struct **vms;
 
-	chunk = pcpu_alloc_chunk(type, gfp);
+	chunk = pcpu_alloc_chunk(gfp);
 	if (!chunk)
 		return NULL;
 
@@ -403,7 +402,7 @@ static bool pcpu_should_reclaim_chunk(struct pcpu_chunk *chunk)
 	 * chunk, move it to the to_depopulate list.
 	 */
 	return ((chunk->isolated && chunk->nr_empty_pop_pages) ||
-		(pcpu_nr_empty_pop_pages[pcpu_chunk_type(chunk)] >
-		 PCPU_EMPTY_POP_PAGES_HIGH + chunk->nr_empty_pop_pages &&
-		chunk->nr_empty_pop_pages >= chunk->nr_pages / 4));
+		(pcpu_nr_empty_pop_pages >
+		 (PCPU_EMPTY_POP_PAGES_HIGH + chunk->nr_empty_pop_pages) &&
+		 chunk->nr_empty_pop_pages >= chunk->nr_pages / 4));
 }