percpu: use metadata blocks to update the chunk contig hint

The largest free region will either be a block level contig hint or an
aggregate over the left_free and right_free areas of blocks. This is a
much smaller set of free areas that need to be checked than a full
traverse.

Signed-off-by: Dennis Zhou <dennisszhou@gmail.com>
Reviewed-by: Josef Bacik <jbacik@fb.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
This commit is contained in:
Dennis Zhou (Facebook) 2017-07-24 19:02:18 -04:00 committed by Tejun Heo
parent b185cd0dc6
commit 525ca84dae

View File

@ -305,6 +305,67 @@ static unsigned long pcpu_block_off_to_off(int index, int off)
return index * PCPU_BITMAP_BLOCK_BITS + off;
}
/**
* pcpu_next_md_free_region - finds the next hint free area
* @chunk: chunk of interest
* @bit_off: chunk offset
* @bits: size of free area
*
* Helper function for pcpu_for_each_md_free_region. It checks
* block->contig_hint and performs aggregation across blocks to find the
* next hint. It modifies bit_off and bits in-place to be consumed in the
* loop.
*/
static void pcpu_next_md_free_region(struct pcpu_chunk *chunk, int *bit_off,
int *bits)
{
int i = pcpu_off_to_block_index(*bit_off);
int block_off = pcpu_off_to_block_off(*bit_off);
struct pcpu_block_md *block;
*bits = 0;
for (block = chunk->md_blocks + i; i < pcpu_chunk_nr_blocks(chunk);
block++, i++) {
/* handles contig area across blocks */
if (*bits) {
*bits += block->left_free;
if (block->left_free == PCPU_BITMAP_BLOCK_BITS)
continue;
return;
}
/*
* This checks three things. First is there a contig_hint to
* check. Second, have we checked this hint before by
* comparing the block_off. Third, is this the same as the
* right contig hint. In the last case, it spills over into
* the next block and should be handled by the contig area
* across blocks code.
*/
*bits = block->contig_hint;
if (*bits && block->contig_hint_start >= block_off &&
*bits + block->contig_hint_start < PCPU_BITMAP_BLOCK_BITS) {
*bit_off = pcpu_block_off_to_off(i,
block->contig_hint_start);
return;
}
*bits = block->right_free;
*bit_off = (i + 1) * PCPU_BITMAP_BLOCK_BITS - block->right_free;
}
}
/*
* Metadata free area iterators. These perform aggregation of free areas
* based on the metadata blocks and return the offset @bit_off and size in
* bits of the free area @bits.
*/
#define pcpu_for_each_md_free_region(chunk, bit_off, bits) \
for (pcpu_next_md_free_region((chunk), &(bit_off), &(bits)); \
(bit_off) < pcpu_chunk_map_bits((chunk)); \
(bit_off) += (bits) + 1, \
pcpu_next_md_free_region((chunk), &(bit_off), &(bits)))
/**
* pcpu_mem_zalloc - allocate memory
* @size: bytes to allocate
@ -425,29 +486,28 @@ static void pcpu_chunk_update(struct pcpu_chunk *chunk, int bit_off, int bits)
* pcpu_chunk_refresh_hint - updates metadata about a chunk
* @chunk: chunk of interest
*
* Iterates over the chunk to find the largest free area.
* Iterates over the metadata blocks to find the largest contig area.
* It also counts the populated pages and uses the delta to update the
* global count.
*
* Updates:
* chunk->contig_bits
* chunk->contig_bits_start
* nr_empty_pop_pages
* nr_empty_pop_pages (chunk and global)
*/
static void pcpu_chunk_refresh_hint(struct pcpu_chunk *chunk)
{
int bits, nr_empty_pop_pages;
int rs, re; /* region start, region end */
int bit_off, bits, nr_empty_pop_pages;
/* clear metadata */
chunk->contig_bits = 0;
bit_off = chunk->first_bit;
bits = nr_empty_pop_pages = 0;
pcpu_for_each_unpop_region(chunk->alloc_map, rs, re, chunk->first_bit,
pcpu_chunk_map_bits(chunk)) {
bits = re - rs;
pcpu_for_each_md_free_region(chunk, bit_off, bits) {
pcpu_chunk_update(chunk, bit_off, bits);
pcpu_chunk_update(chunk, rs, bits);
nr_empty_pop_pages += pcpu_cnt_pop_pages(chunk, rs, bits);
nr_empty_pop_pages += pcpu_cnt_pop_pages(chunk, bit_off, bits);
}
/*