nagai/kernel
3
0
Fork 0
forked from mirrors/linux
Code Pull requests Activity

percpu: set PCPU_BITMAP_BLOCK_SIZE to PAGE_SIZE

Browse source 
Previously, block size was flexible based on the constraint that the
GCD(PCPU_BITMAP_BLOCK_SIZE, PAGE_SIZE) > 1. However, this carried the
overhead that keeping a floating number of populated free pages required
scanning over the free regions of a chunk.

Setting the block size to be fixed at PAGE_SIZE lets us know when an
empty page becomes used as we will break a full contig_hint of a block.
This means we no longer have to scan the whole chunk upon breaking a
contig_hint which empty page management piggybacked off. A later patch
takes advantage of this to optimize the allocation path by only scanning
forward using the scan_hint introduced later too.

Signed-off-by: Dennis Zhou <dennis@kernel.org>
Reviewed-by: Peng Fan <peng.fan@nxp.com>
This commit is contained in:
Dennis Zhou 2019-02-13 11:10:30 -08:00
parent 8744d85942
commit b239f7daf5
3 changed files with 48 additions and 76 deletions
repo.diff.show_diff_stats Download patch file Download diff file Expand all files Collapse all files

12
include/linux/percpu.h
View file

@ -26,16 +26,10 @@
#define PCPU_MIN_ALLOC_SHIFT 2 #define PCPU_MIN_ALLOC_SHIFT 2
#define PCPU_MIN_ALLOC_SIZE (1 << PCPU_MIN_ALLOC_SHIFT) #define PCPU_MIN_ALLOC_SIZE (1 << PCPU_MIN_ALLOC_SHIFT)
/* number of bits per page, used to trigger a scan if blocks are > PAGE_SIZE */
#define PCPU_BITS_PER_PAGE (PAGE_SIZE >> PCPU_MIN_ALLOC_SHIFT)
/* /*
* This determines the size of each metadata block. There are several subtle * The PCPU_BITMAP_BLOCK_SIZE must be the same size as PAGE_SIZE as the
* constraints around this constant. The reserved region must be a multiple of * updating of hints is used to manage the nr_empty_pop_pages in both
* PCPU_BITMAP_BLOCK_SIZE. Additionally, PCPU_BITMAP_BLOCK_SIZE must be a * the chunk and globally.
* 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_SIZE PAGE_SIZE
#define PCPU_BITMAP_BLOCK_BITS (PCPU_BITMAP_BLOCK_SIZE >> \ #define PCPU_BITMAP_BLOCK_BITS (PCPU_BITMAP_BLOCK_SIZE >> \

2
mm/percpu-km.c
View file

@ -70,7 +70,7 @@ static struct pcpu_chunk *pcpu_create_chunk(gfp_t gfp)
chunk->base_addr = page_address(pages); chunk->base_addr = page_address(pages);
spin_lock_irqsave(&pcpu_lock, flags); spin_lock_irqsave(&pcpu_lock, flags);
pcpu_chunk_populated(chunk, 0, nr_pages, false); pcpu_chunk_populated(chunk, 0, nr_pages);
spin_unlock_irqrestore(&pcpu_lock, flags); spin_unlock_irqrestore(&pcpu_lock, flags);
pcpu_stats_chunk_alloc(); pcpu_stats_chunk_alloc();

114
mm/percpu.c
View file

@ -527,37 +527,20 @@ static void pcpu_chunk_relocate(struct pcpu_chunk *chunk, int oslot)
__pcpu_chunk_move(chunk, nslot, oslot < nslot); __pcpu_chunk_move(chunk, nslot, oslot < nslot);
} }
/**
* pcpu_cnt_pop_pages- counts populated backing pages in range
* @chunk: chunk of interest
* @bit_off: start offset
* @bits: size of area to check
*
* Calculates the number of populated pages in the region
* [page_start, page_end). This keeps track of how many empty populated
* pages are available and decide if async work should be scheduled.
*
* RETURNS:
* The nr of populated pages.
*/
static inline int pcpu_cnt_pop_pages(struct pcpu_chunk *chunk, int bit_off,
int bits)
{
int page_start = PFN_UP(bit_off * PCPU_MIN_ALLOC_SIZE);
int page_end = PFN_DOWN((bit_off + bits) * PCPU_MIN_ALLOC_SIZE);
if (page_start >= page_end)
return 0;
/* /*
* bitmap_weight counts the number of bits set in a bitmap up to * pcpu_update_empty_pages - update empty page counters
* the specified number of bits. This is counting the populated * @chunk: chunk of interest
* pages up to page_end and then subtracting the populated pages * @nr: nr of empty pages
* up to page_start to count the populated pages in *
* [page_start, page_end). * This is used to keep track of the empty pages now based on the premise
* a md_block covers a page. The hint update functions recognize if a block
* is made full or broken to calculate deltas for keeping track of free pages.
*/ */
return bitmap_weight(chunk->populated, page_end) - static inline void pcpu_update_empty_pages(struct pcpu_chunk *chunk, int nr)
bitmap_weight(chunk->populated, page_start); {
chunk->nr_empty_pop_pages += nr;
if (chunk != pcpu_reserved_chunk)
pcpu_nr_empty_pop_pages += nr;
} }
/* /*
@ -608,36 +591,19 @@ static void pcpu_chunk_update(struct pcpu_chunk *chunk, int bit_off, int bits)
* Updates: * Updates:
* chunk->contig_bits * chunk->contig_bits
* chunk->contig_bits_start * chunk->contig_bits_start
* nr_empty_pop_pages (chunk and global)
*/ */
static void pcpu_chunk_refresh_hint(struct pcpu_chunk *chunk) static void pcpu_chunk_refresh_hint(struct pcpu_chunk *chunk)
{ {
int bit_off, bits, nr_empty_pop_pages; int bit_off, bits;
/* clear metadata */ /* clear metadata */
chunk->contig_bits = 0; chunk->contig_bits = 0;
bit_off = chunk->first_bit; bit_off = chunk->first_bit;
bits = nr_empty_pop_pages = 0; bits = 0;
pcpu_for_each_md_free_region(chunk, bit_off, bits) { pcpu_for_each_md_free_region(chunk, bit_off, bits) {
pcpu_chunk_update(chunk, bit_off, bits); pcpu_chunk_update(chunk, bit_off, bits);
nr_empty_pop_pages += pcpu_cnt_pop_pages(chunk, bit_off, bits);
} }
/*
* Keep track of nr_empty_pop_pages.
*
* The chunk maintains the previous number of free pages it held,
* so the delta is used to update the global counter. The reserved
* chunk is not part of the free page count as they are populated
* at init and are special to serving reserved allocations.
*/
if (chunk != pcpu_reserved_chunk)
pcpu_nr_empty_pop_pages +=
(nr_empty_pop_pages - chunk->nr_empty_pop_pages);
chunk->nr_empty_pop_pages = nr_empty_pop_pages;
} }
/** /**
@ -709,6 +675,7 @@ static void pcpu_block_refresh_hint(struct pcpu_chunk *chunk, int index)
static void pcpu_block_update_hint_alloc(struct pcpu_chunk *chunk, int bit_off, static void pcpu_block_update_hint_alloc(struct pcpu_chunk *chunk, int bit_off,
int bits) int bits)
{ {
int nr_empty_pages = 0;
struct pcpu_block_md *s_block, *e_block, *block; struct pcpu_block_md *s_block, *e_block, *block;
int s_index, e_index; /* block indexes of the freed allocation */ int s_index, e_index; /* block indexes of the freed allocation */
int s_off, e_off; /* block offsets of the freed allocation */ int s_off, e_off; /* block offsets of the freed allocation */
@ -733,6 +700,9 @@ static void pcpu_block_update_hint_alloc(struct pcpu_chunk *chunk, int bit_off,
* If the allocation breaks the contig_hint, a scan is required to * If the allocation breaks the contig_hint, a scan is required to
* restore this hint. * restore this hint.
*/ */
if (s_block->contig_hint == PCPU_BITMAP_BLOCK_BITS)
nr_empty_pages++;
if (s_off == s_block->first_free) if (s_off == s_block->first_free)
s_block->first_free = find_next_zero_bit( s_block->first_free = find_next_zero_bit(
pcpu_index_alloc_map(chunk, s_index), pcpu_index_alloc_map(chunk, s_index),
@ -760,6 +730,9 @@ static void pcpu_block_update_hint_alloc(struct pcpu_chunk *chunk, int bit_off,
* Update e_block. * Update e_block.
*/ */
if (s_index != e_index) { if (s_index != e_index) {
if (e_block->contig_hint == PCPU_BITMAP_BLOCK_BITS)
nr_empty_pages++;
/* /*
* When the allocation is across blocks, the end is along * When the allocation is across blocks, the end is along
* the left part of the e_block. * the left part of the e_block.
@ -784,6 +757,7 @@ static void pcpu_block_update_hint_alloc(struct pcpu_chunk *chunk, int bit_off,
} }
/* update in-between md_blocks */ /* update in-between md_blocks */
nr_empty_pages += (e_index - s_index - 1);
for (block = s_block + 1; block < e_block; block++) { for (block = s_block + 1; block < e_block; block++) {
block->contig_hint = 0; block->contig_hint = 0;
block->left_free = 0; block->left_free = 0;
@ -791,6 +765,9 @@ static void pcpu_block_update_hint_alloc(struct pcpu_chunk *chunk, int bit_off,
} }
} }
if (nr_empty_pages)
pcpu_update_empty_pages(chunk, -nr_empty_pages);
/* /*
* The only time a full chunk scan is required is if the chunk * The only time a full chunk scan is required is if the chunk
* contig hint is broken. Otherwise, it means a smaller space * contig hint is broken. Otherwise, it means a smaller space
@ -823,6 +800,7 @@ static void pcpu_block_update_hint_alloc(struct pcpu_chunk *chunk, int bit_off,
static void pcpu_block_update_hint_free(struct pcpu_chunk *chunk, int bit_off, static void pcpu_block_update_hint_free(struct pcpu_chunk *chunk, int bit_off,
int bits) int bits)
{ {
int nr_empty_pages = 0;
struct pcpu_block_md *s_block, *e_block, *block; struct pcpu_block_md *s_block, *e_block, *block;
int s_index, e_index; /* block indexes of the freed allocation */ int s_index, e_index; /* block indexes of the freed allocation */
int s_off, e_off; /* block offsets of the freed allocation */ int s_off, e_off; /* block offsets of the freed allocation */
@ -876,14 +854,19 @@ static void pcpu_block_update_hint_free(struct pcpu_chunk *chunk, int bit_off,
/* update s_block */ /* update s_block */
e_off = (s_index == e_index) ? end : PCPU_BITMAP_BLOCK_BITS; e_off = (s_index == e_index) ? end : PCPU_BITMAP_BLOCK_BITS;
if (!start && e_off == PCPU_BITMAP_BLOCK_BITS)
nr_empty_pages++;
pcpu_block_update(s_block, start, e_off); pcpu_block_update(s_block, start, e_off);
/* freeing in the same block */ /* freeing in the same block */
if (s_index != e_index) { if (s_index != e_index) {
/* update e_block */ /* update e_block */
if (end == PCPU_BITMAP_BLOCK_BITS)
nr_empty_pages++;
pcpu_block_update(e_block, 0, end); pcpu_block_update(e_block, 0, end);
/* reset md_blocks in the middle */ /* reset md_blocks in the middle */
nr_empty_pages += (e_index - s_index - 1);
for (block = s_block + 1; block < e_block; block++) { for (block = s_block + 1; block < e_block; block++) {
block->first_free = 0; block->first_free = 0;
block->contig_hint_start = 0; block->contig_hint_start = 0;
@ -893,15 +876,16 @@ static void pcpu_block_update_hint_free(struct pcpu_chunk *chunk, int bit_off,
} }
} }
if (nr_empty_pages)
pcpu_update_empty_pages(chunk, nr_empty_pages);
/* /*
* Refresh chunk metadata when the free makes a page free, a block * Refresh chunk metadata when the free makes a block free or spans
* free, or spans across blocks. The contig hint may be off by up to * across blocks. The contig_hint may be off by up to a page, but if
* a page, but if the hint is contained in a block, it will be accurate * the contig_hint is contained in a block, it will be accurate with
* with the else condition below. * the else condition below.
*/ */
if ((ALIGN_DOWN(end, min(PCPU_BITS_PER_PAGE, PCPU_BITMAP_BLOCK_BITS)) > if (((end - start) >= PCPU_BITMAP_BLOCK_BITS) || s_index != e_index)
ALIGN(start, min(PCPU_BITS_PER_PAGE, PCPU_BITMAP_BLOCK_BITS))) ||
s_index != e_index)
pcpu_chunk_refresh_hint(chunk); pcpu_chunk_refresh_hint(chunk);
else else
pcpu_chunk_update(chunk, pcpu_block_off_to_off(s_index, start), pcpu_chunk_update(chunk, pcpu_block_off_to_off(s_index, start),
@ -1178,9 +1162,7 @@ static struct pcpu_chunk * __init pcpu_alloc_first_chunk(unsigned long tmp_addr,
chunk->immutable = true; chunk->immutable = true;
bitmap_fill(chunk->populated, chunk->nr_pages); bitmap_fill(chunk->populated, chunk->nr_pages);
chunk->nr_populated = chunk->nr_pages; chunk->nr_populated = chunk->nr_pages;
chunk->nr_empty_pop_pages = chunk->nr_empty_pop_pages = chunk->nr_pages;
pcpu_cnt_pop_pages(chunk, start_offset / PCPU_MIN_ALLOC_SIZE,
map_size / PCPU_MIN_ALLOC_SIZE);
chunk->contig_bits = map_size / PCPU_MIN_ALLOC_SIZE; chunk->contig_bits = map_size / PCPU_MIN_ALLOC_SIZE;
chunk->free_bytes = map_size; chunk->free_bytes = map_size;
@ -1275,7 +1257,6 @@ static void pcpu_free_chunk(struct pcpu_chunk *chunk)
* @chunk: pcpu_chunk which got populated * @chunk: pcpu_chunk which got populated
* @page_start: the start page * @page_start: the start page
* @page_end: the end page * @page_end: the end page
* @for_alloc: if this is to populate for allocation
* *
* Pages in [@page_start,@page_end) have been populated to @chunk. Update * Pages in [@page_start,@page_end) have been populated to @chunk. Update
* the bookkeeping information accordingly. Must be called after each * the bookkeeping information accordingly. Must be called after each
@ -1285,7 +1266,7 @@ static void pcpu_free_chunk(struct pcpu_chunk *chunk)
* is to serve an allocation in that area. * is to serve an allocation in that area.
*/ */
static void pcpu_chunk_populated(struct pcpu_chunk *chunk, int page_start, static void pcpu_chunk_populated(struct pcpu_chunk *chunk, int page_start,
int page_end, bool for_alloc) int page_end)
{ {
int nr = page_end - page_start; int nr = page_end - page_start;
@ -1295,10 +1276,7 @@ static void pcpu_chunk_populated(struct pcpu_chunk *chunk, int page_start,
chunk->nr_populated += nr; chunk->nr_populated += nr;
pcpu_nr_populated += nr; pcpu_nr_populated += nr;
if (!for_alloc) { pcpu_update_empty_pages(chunk, nr);
chunk->nr_empty_pop_pages += nr;
pcpu_nr_empty_pop_pages += nr;
}
} }
/** /**
@ -1320,9 +1298,9 @@ static void pcpu_chunk_depopulated(struct pcpu_chunk *chunk,
bitmap_clear(chunk->populated, page_start, nr); bitmap_clear(chunk->populated, page_start, nr);
chunk->nr_populated -= nr; chunk->nr_populated -= nr;
chunk->nr_empty_pop_pages -= nr;
pcpu_nr_empty_pop_pages -= nr;
pcpu_nr_populated -= nr; pcpu_nr_populated -= nr;
pcpu_update_empty_pages(chunk, -nr);
} }
/* /*
@ -1537,7 +1515,7 @@ static void __percpu *pcpu_alloc(size_t size, size_t align, bool reserved,
err = "failed to populate"; err = "failed to populate";
goto fail_unlock; goto fail_unlock;
} }
pcpu_chunk_populated(chunk, rs, re, true); pcpu_chunk_populated(chunk, rs, re);
spin_unlock_irqrestore(&pcpu_lock, flags); spin_unlock_irqrestore(&pcpu_lock, flags);
} }
@ -1736,7 +1714,7 @@ static void pcpu_balance_workfn(struct work_struct *work)
if (!ret) { if (!ret) {
nr_to_pop -= nr; nr_to_pop -= nr;
spin_lock_irq(&pcpu_lock); spin_lock_irq(&pcpu_lock);
pcpu_chunk_populated(chunk, rs, rs + nr, false); pcpu_chunk_populated(chunk, rs, rs + nr);
spin_unlock_irq(&pcpu_lock); spin_unlock_irq(&pcpu_lock);
} else { } else {
nr_to_pop = 0; nr_to_pop = 0;