percpu: introduce bitmap metadata blocks

This patch introduces the bitmap metadata blocks and adds the skeleton
of the code that will be used to maintain these blocks.  Each chunk's
bitmap is made up of full metadata blocks. These blocks maintain basic
metadata to help prevent scanning unnecssarily to update hints. Full
scanning methods are used for the skeleton and will be replaced in the
coming patches. A number of helper functions are added as well to do
conversion of pages to blocks and manage offsets. Comments will be
updated as the final version of each function is added.

There exists a relationship between PAGE_SIZE, PCPU_BITMAP_BLOCK_SIZE,
the region size, and unit_size. Every chunk's region (including offsets)
is page aligned at the beginning to preserve alignment. The end is
aligned to LCM(PAGE_SIZE, PCPU_BITMAP_BLOCK_SIZE) to ensure that the end
can fit with the populated page map which is by page and every metadata
block is fully accounted for. The unit_size is already page aligned, but
must also be aligned with PCPU_BITMAP_BLOCK_SIZE to ensure full metadata
blocks.
Signed-off-by: Dennis Zhou <dennisszhou@gmail.com>
Reviewed-by: Josef Bacik <jbacik@fb.com>
Signed-off-by: Tejun Heo <tj@kernel.org>

include/linux/percpu.h

@@ -25,6 +25,18 @@
 #define PCPU_MIN_ALLOC_SHIFT		2
 #define PCPU_MIN_ALLOC_SIZE		(1 << PCPU_MIN_ALLOC_SHIFT)
 
+/*
+ * This determines the size of each metadata block.  There are several subtle
+ * constraints around this constant.  The reserved region must be a multiple of
+ * PCPU_BITMAP_BLOCK_SIZE.  Additionally, PCPU_BITMAP_BLOCK_SIZE must be a
+ * multiple of PAGE_SIZE or PAGE_SIZE must be a multiple of
+ * PCPU_BITMAP_BLOCK_SIZE to align with the populated page map. The unit_size
+ * also has to be a multiple of PCPU_BITMAP_BLOCK_SIZE to ensure full blocks.
+ */
+#define PCPU_BITMAP_BLOCK_SIZE		PAGE_SIZE
+#define PCPU_BITMAP_BLOCK_BITS		(PCPU_BITMAP_BLOCK_SIZE >>	\
+					 PCPU_MIN_ALLOC_SHIFT)
+
 /*
  * Percpu allocator can serve percpu allocations before slab is
  * initialized which allows slab to depend on the percpu allocator.

mm/percpu-internal.h

@@ -4,6 +4,22 @@
 #include <linux/types.h>
 #include <linux/percpu.h>
 
+/*
+ * pcpu_block_md is the metadata block struct.
+ * Each chunk's bitmap is split into a number of full blocks.
+ * All units are in terms of bits.
+ */
+struct pcpu_block_md {
+	int                     contig_hint;    /* contig hint for block */
+	int                     contig_hint_start; /* block relative starting
+						      position of the contig hint */
+	int                     left_free;      /* size of free space along
+						   the left side of the block */
+	int                     right_free;     /* size of free space along
+						   the right side of the block */
+	int                     first_free;     /* block position of first free */
+};
+
 struct pcpu_chunk {
 #ifdef CONFIG_PERCPU_STATS
 	int			nr_alloc;	/* # of allocations */
@@ -17,6 +33,7 @@ struct pcpu_chunk {
 
 	unsigned long		*alloc_map;	/* allocation map */
 	unsigned long		*bound_map;	/* boundary map */
+	struct pcpu_block_md	*md_blocks;	/* metadata blocks */
 
 	void			*data;		/* chunk data */
 	int			first_free;	/* no free below this */
@@ -43,6 +60,18 @@ extern int pcpu_nr_empty_pop_pages;
 extern struct pcpu_chunk *pcpu_first_chunk;
 extern struct pcpu_chunk *pcpu_reserved_chunk;
 
+/**
+ * pcpu_chunk_nr_blocks - converts nr_pages to # of md_blocks
+ * @chunk: chunk of interest
+ *
+ * This conversion is from the number of physical pages that the chunk
+ * serves to the number of bitmap blocks used.
+ */
+static inline int pcpu_chunk_nr_blocks(struct pcpu_chunk *chunk)
+{
+	return chunk->nr_pages * PAGE_SIZE / PCPU_BITMAP_BLOCK_SIZE;
+}
+
 /**
  * pcpu_nr_pages_to_map_bits - converts the pages to size of bitmap
  * @pages: number of physical pages