percpu: expose statistics about percpu memory via debugfs

There is limited visibility into the use of percpu memory leaving us
unable to reason about correctness of parameters and overall use of
percpu memory. These counters and statistics aim to help understand
basic statistics about percpu memory such as number of allocations over
the lifetime, allocation sizes, and fragmentation.

New Config: PERCPU_STATS

Signed-off-by: Dennis Zhou <dennisz@fb.com>
Signed-off-by: Tejun Heo <tj@kernel.org>

1 files changed, 131 insertions, 0 deletions

diff --git a/mm/percpu-internal.h b/mm/percpu-internal.h
index 68bf18522a6d..d030fce745a2 100644
--- a/mm/percpu-internal.h
+++ b/mm/percpu-internal.h
@@ -5,6 +5,11 @@
 #include <linux/percpu.h>
 
 struct pcpu_chunk {
+#ifdef CONFIG_PERCPU_STATS
+	int			nr_alloc;	/* # of allocations */
+	size_t			max_alloc_size; /* largest allocation size */
+#endif
+
 	struct list_head	list;		/* linked to pcpu_slot lists */
 	int			free_size;	/* free bytes in the chunk */
 	int			contig_hint;	/* max contiguous size hint */
@@ -18,6 +23,11 @@ struct pcpu_chunk {
 	void			*data;		/* chunk data */
 	int			first_free;	/* no free below this */
 	bool			immutable;	/* no [de]population allowed */
+	bool			has_reserved;	/* Indicates if chunk has reserved space
+						   at the beginning. Reserved chunk will
+						   contain reservation for static chunk.
+						   Dynamic chunk will contain reservation
+						   for static and reserved chunks. */
 	int			nr_populated;	/* # of populated pages */
 	unsigned long		populated[];	/* populated bitmap */
 };
@@ -30,4 +40,125 @@ extern int pcpu_nr_slots;
 extern struct pcpu_chunk *pcpu_first_chunk;
 extern struct pcpu_chunk *pcpu_reserved_chunk;
 
+#ifdef CONFIG_PERCPU_STATS
+
+#include <linux/spinlock.h>
+
+struct percpu_stats {
+	u64 nr_alloc;		/* lifetime # of allocations */
+	u64 nr_dealloc;		/* lifetime # of deallocations */
+	u64 nr_cur_alloc;	/* current # of allocations */
+	u64 nr_max_alloc;	/* max # of live allocations */
+	u32 nr_chunks;		/* current # of live chunks */
+	u32 nr_max_chunks;	/* max # of live chunks */
+	size_t min_alloc_size;	/* min allocaiton size */
+	size_t max_alloc_size;	/* max allocation size */
+};
+
+extern struct percpu_stats pcpu_stats;
+extern struct pcpu_alloc_info pcpu_stats_ai;
+
+/*
+ * For debug purposes. We don't care about the flexible array.
+ */
+static inline void pcpu_stats_save_ai(const struct pcpu_alloc_info *ai)
+{
+	memcpy(&pcpu_stats_ai, ai, sizeof(struct pcpu_alloc_info));
+
+	/* initialize min_alloc_size to unit_size */
+	pcpu_stats.min_alloc_size = pcpu_stats_ai.unit_size;
+}
+
+/*
+ * pcpu_stats_area_alloc - increment area allocation stats
+ * @chunk: the location of the area being allocated
+ * @size: size of area to allocate in bytes
+ *
+ * CONTEXT:
+ * pcpu_lock.
+ */
+static inline void pcpu_stats_area_alloc(struct pcpu_chunk *chunk, size_t size)
+{
+	lockdep_assert_held(&pcpu_lock);
+
+	pcpu_stats.nr_alloc++;
+	pcpu_stats.nr_cur_alloc++;
+	pcpu_stats.nr_max_alloc =
+		max(pcpu_stats.nr_max_alloc, pcpu_stats.nr_cur_alloc);
+	pcpu_stats.min_alloc_size =
+		min(pcpu_stats.min_alloc_size, size);
+	pcpu_stats.max_alloc_size =
+		max(pcpu_stats.max_alloc_size, size);
+
+	chunk->nr_alloc++;
+	chunk->max_alloc_size = max(chunk->max_alloc_size, size);
+}
+
+/*
+ * pcpu_stats_area_dealloc - decrement allocation stats
+ * @chunk: the location of the area being deallocated
+ *
+ * CONTEXT:
+ * pcpu_lock.
+ */
+static inline void pcpu_stats_area_dealloc(struct pcpu_chunk *chunk)
+{
+	lockdep_assert_held(&pcpu_lock);
+
+	pcpu_stats.nr_dealloc++;
+	pcpu_stats.nr_cur_alloc--;
+
+	chunk->nr_alloc--;
+}
+
+/*
+ * pcpu_stats_chunk_alloc - increment chunk stats
+ */
+static inline void pcpu_stats_chunk_alloc(void)
+{
+	spin_lock_irq(&pcpu_lock);
+
+	pcpu_stats.nr_chunks++;
+	pcpu_stats.nr_max_chunks =
+		max(pcpu_stats.nr_max_chunks, pcpu_stats.nr_chunks);
+
+	spin_unlock_irq(&pcpu_lock);
+}
+
+/*
+ * pcpu_stats_chunk_dealloc - decrement chunk stats
+ */
+static inline void pcpu_stats_chunk_dealloc(void)
+{
+	spin_lock_irq(&pcpu_lock);
+
+	pcpu_stats.nr_chunks--;
+
+	spin_unlock_irq(&pcpu_lock);
+}
+
+#else
+
+static inline void pcpu_stats_save_ai(const struct pcpu_alloc_info *ai)
+{
+}
+
+static inline void pcpu_stats_area_alloc(struct pcpu_chunk *chunk, size_t size)
+{
+}
+
+static inline void pcpu_stats_area_dealloc(struct pcpu_chunk *chunk)
+{
+}
+
+static inline void pcpu_stats_chunk_alloc(void)
+{
+}
+
+static inline void pcpu_stats_chunk_dealloc(void)
+{
+}
+
+#endif /* !CONFIG_PERCPU_STATS */
+
 #endif