Merge tag 'percpu-for-6.6' of git://git.kernel.org/pub/scm/linux/kernel/git/dennis/percpu

Pull percpu updates from Dennis Zhou:
 "One bigger change to percpu_counter's api allowing for init and
  destroy of multiple counters via percpu_counter_init_many() and
  percpu_counter_destroy_many(). This is used to help begin remediating
  a performance regression with percpu rss stats.

  Additionally, it seems larger core count machines are feeling the
  burden of the single threaded allocation of percpu. Mateusz is
  thinking about it and I will spend some time on it too.

  percpu:

   - A couple cleanups by Baoquan He and Bibo Mao. The only behavior
     change is to start printing messages if we're under the warn limit
     for failed atomic allocations.

  percpu_counter:

   - Shakeel introduced percpu counters into mm_struct which caused
     percpu allocations be on the hot path [1]. Originally I spent some
     time trying to improve the percpu allocator, but instead preferred
     what Mateusz Guzik proposed grouping at the allocation site,
     percpu_counter_init_many(). This allows a single percpu allocation
     to be shared by the counters. I like this approach because it
     creates a shared lifetime by the allocations. Additionally, I
     believe many inits have higher level synchronization requirements,
     like percpu_counter does against HOTPLUG_CPU. Therefore we can
     group these optimizations together"

Link: https://lore.kernel.org/linux-mm/20221024052841.3291983-1-shakeelb@google.com/ [1]

* tag 'percpu-for-6.6' of git://git.kernel.org/pub/scm/linux/kernel/git/dennis/percpu:
  kernel/fork: group allocation/free of per-cpu counters for mm struct
  pcpcntr: add group allocation/free
  mm/percpu.c: print error message too if atomic alloc failed
  mm/percpu.c: optimize the code in pcpu_setup_first_chunk() a little bit
  mm/percpu.c: remove redundant check
  mm/percpu: Remove some local variables in pcpu_populate_pte

include/linux/percpu_counter.h

@@ -30,17 +30,28 @@ struct percpu_counter {
 
 extern int percpu_counter_batch;
 
-int __percpu_counter_init(struct percpu_counter *fbc, s64 amount, gfp_t gfp,
-			  struct lock_class_key *key);
+int __percpu_counter_init_many(struct percpu_counter *fbc, s64 amount,
+			       gfp_t gfp, u32 nr_counters,
+			       struct lock_class_key *key);
 
-#define percpu_counter_init(fbc, value, gfp)				\
+#define percpu_counter_init_many(fbc, value, gfp, nr_counters)		\
 	({								\
 		static struct lock_class_key __key;			\
 									\
-		__percpu_counter_init(fbc, value, gfp, &__key);		\
+		__percpu_counter_init_many(fbc, value, gfp, nr_counters,\
+					   &__key);			\
 	})
 
-void percpu_counter_destroy(struct percpu_counter *fbc);
+
+#define percpu_counter_init(fbc, value, gfp)				\
+	percpu_counter_init_many(fbc, value, gfp, 1)
+
+void percpu_counter_destroy_many(struct percpu_counter *fbc, u32 nr_counters);
+static inline void percpu_counter_destroy(struct percpu_counter *fbc)
+{
+	percpu_counter_destroy_many(fbc, 1);
+}
+
 void percpu_counter_set(struct percpu_counter *fbc, s64 amount);
 void percpu_counter_add_batch(struct percpu_counter *fbc, s64 amount,
 			      s32 batch);
@@ -116,11 +127,27 @@ struct percpu_counter {
 	s64 count;
 };
 
+static inline int percpu_counter_init_many(struct percpu_counter *fbc,
+					   s64 amount, gfp_t gfp,
+					   u32 nr_counters)
+{
+	u32 i;
+
+	for (i = 0; i < nr_counters; i++)
+		fbc[i].count = amount;
+
+	return 0;
+}
+
 static inline int percpu_counter_init(struct percpu_counter *fbc, s64 amount,
 				      gfp_t gfp)
 {
-	fbc->count = amount;
-	return 0;
+	return percpu_counter_init_many(fbc, amount, gfp, 1);
+}
+
+static inline void percpu_counter_destroy_many(struct percpu_counter *fbc,
+					       u32 nr_counters)
+{
 }
 
 static inline void percpu_counter_destroy(struct percpu_counter *fbc)