Merge branch 'for-5.14' of git://git.kernel.org/pub/scm/linux/kernel/git/dennis/percpu

Pull percpu updates from Dennis Zhou:

 - percpu chunk depopulation - depopulate backing pages for chunks with
   empty pages when we exceed a global threshold without those pages.
   This lets us reclaim a portion of memory that would previously be
   lost until the full chunk would be freed (possibly never).

 - memcg accounting cleanup - previously separate chunks were managed
   for normal allocations and __GFP_ACCOUNT allocations. These are now
   consolidated which cleans up the code quite a bit.

 - a few misc clean ups for clang warnings

* 'for-5.14' of git://git.kernel.org/pub/scm/linux/kernel/git/dennis/percpu:
  percpu: optimize locking in pcpu_balance_workfn()
  percpu: initialize best_upa variable
  percpu: rework memcg accounting
  mm, memcg: introduce mem_cgroup_kmem_disabled()
  mm, memcg: mark cgroup_memory_nosocket, nokmem and noswap as __ro_after_init
  percpu: make symbol 'pcpu_free_slot' static
  percpu: implement partial chunk depopulation
  percpu: use pcpu_free_slot instead of pcpu_nr_slots - 1
  percpu: factor out pcpu_check_block_hint()
  percpu: split __pcpu_balance_workfn()
  percpu: fix a comment about the chunks ordering

Author: torvalds

include/linux/memcontrol.h

@@ -1619,6 +1619,7 @@ static inline void set_shrinker_bit(struct mem_cgroup *memcg,
 #endif
 
 #ifdef CONFIG_MEMCG_KMEM
+bool mem_cgroup_kmem_disabled(void);
 int __memcg_kmem_charge_page(struct page *page, gfp_t gfp, int order);
 void __memcg_kmem_uncharge_page(struct page *page, int order);
 
@@ -1672,6 +1673,10 @@ static inline int memcg_cache_id(struct mem_cgroup *memcg)
 struct mem_cgroup *mem_cgroup_from_obj(void *p);
 
 #else
+static inline bool mem_cgroup_kmem_disabled(void)
+{
+	return true;
+}
 
 static inline int memcg_kmem_charge_page(struct page *page, gfp_t gfp,
 					 int order)

mm/memcontrol.c

@@ -81,14 +81,14 @@ DEFINE_PER_CPU(struct mem_cgroup *, int_active_memcg);
 EXPORT_PER_CPU_SYMBOL_GPL(int_active_memcg);
 
 /* Socket memory accounting disabled? */
-static bool cgroup_memory_nosocket;
+static bool cgroup_memory_nosocket __ro_after_init;
 
 /* Kernel memory accounting disabled? */
-bool cgroup_memory_nokmem;
+bool cgroup_memory_nokmem __ro_after_init;
 
 /* Whether the swap controller is active */
 #ifdef CONFIG_MEMCG_SWAP
-bool cgroup_memory_noswap __read_mostly;
+bool cgroup_memory_noswap __ro_after_init;
 #else
 #define cgroup_memory_noswap		1
 #endif
@@ -256,6 +256,11 @@ struct cgroup_subsys_state *vmpressure_to_css(struct vmpressure *vmpr)
 #ifdef CONFIG_MEMCG_KMEM
 extern spinlock_t css_set_lock;
 
+bool mem_cgroup_kmem_disabled(void)
+{
+	return cgroup_memory_nokmem;
+}
+
 static void obj_cgroup_uncharge_pages(struct obj_cgroup *objcg,
 				      unsigned int nr_pages);
 

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.
@@ -67,6 +48,8 @@ struct pcpu_chunk {
 
 	void			*data;		/* chunk data */
 	bool			immutable;	/* no [de]population allowed */
+	bool			isolated;	/* isolated from active chunk
+						   slots */
 	int			start_offset;	/* the overlap with the previous
 						   region to have a page aligned
 						   base_addr */
@@ -87,7 +70,9 @@ extern spinlock_t pcpu_lock;
 
 extern struct list_head *pcpu_chunk_lists;
 extern int pcpu_nr_slots;
-extern int pcpu_nr_empty_pop_pages[];
+extern int pcpu_sidelined_slot;
+extern int pcpu_to_depopulate_slot;
+extern int pcpu_nr_empty_pop_pages;
 
 extern struct pcpu_chunk *pcpu_first_chunk;
 extern struct pcpu_chunk *pcpu_reserved_chunk;
@@ -128,37 +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;
 
@@ -118,3 +117,8 @@ static int __init pcpu_verify_alloc_info(const struct pcpu_alloc_info *ai)
 
 	return 0;
 }
+
+static bool pcpu_should_reclaim_chunk(struct pcpu_chunk *chunk)
+{
+	return false;
+}

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
@@ -215,18 +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");
-					chunk_map_stats(m, chunk, buffer);
-				} 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

@@ -329,13 +329,12 @@ 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;
 
@@ -378,3 +377,33 @@ static int __init pcpu_verify_alloc_info(const struct pcpu_alloc_info *ai)
 	/* no extra restriction */
 	return 0;
 }
+
+/**
+ * pcpu_should_reclaim_chunk - determine if a chunk should go into reclaim
+ * @chunk: chunk of interest
+ *
+ * This is the entry point for percpu reclaim.  If a chunk qualifies, it is then
+ * isolated and managed in separate lists at the back of pcpu_slot: sidelined
+ * and to_depopulate respectively.  The to_depopulate list holds chunks slated
+ * for depopulation.  They no longer contribute to pcpu_nr_empty_pop_pages once
+ * they are on this list.  Once depopulated, they are moved onto the sidelined
+ * list which enables them to be pulled back in for allocation if no other chunk
+ * can suffice the allocation.
+ */
+static bool pcpu_should_reclaim_chunk(struct pcpu_chunk *chunk)
+{
+	/* do not reclaim either the first chunk or reserved chunk */
+	if (chunk == pcpu_first_chunk || chunk == pcpu_reserved_chunk)
+		return false;
+
+	/*
+	 * If it is isolated, it may be on the sidelined list so move it back to
+	 * the to_depopulate list.  If we hit at least 1/4 pages empty pages AND
+	 * there is no system-wide shortage of empty pages aside from this
+	 * chunk, move it to the to_depopulate list.
+	 */
+	return ((chunk->isolated && chunk->nr_empty_pop_pages) ||
+		(pcpu_nr_empty_pop_pages >
+		 (PCPU_EMPTY_POP_PAGES_HIGH + chunk->nr_empty_pop_pages) &&
+		 chunk->nr_empty_pop_pages >= chunk->nr_pages / 4));
+}