From 102a0743326a03cd1a1202ceda21e175b7d3575c Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Tue, 20 Feb 2024 01:20:52 +0000
Subject: [PATCH] add new system file
---
kernel/mm/percpu.c | 953 +++++++++++++++++++++++++++++++++++++++++-----------------
1 files changed, 671 insertions(+), 282 deletions(-)
diff --git a/kernel/mm/percpu.c b/kernel/mm/percpu.c
index 2bbae23..b31c6df 100644
--- a/kernel/mm/percpu.c
+++ b/kernel/mm/percpu.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
/*
* mm/percpu.c - percpu memory allocator
*
@@ -5,9 +6,7 @@
* Copyright (C) 2009 Tejun Heo <tj@kernel.org>
*
* Copyright (C) 2017 Facebook Inc.
- * Copyright (C) 2017 Dennis Zhou <dennisszhou@gmail.com>
- *
- * This file is released under the GPLv2 license.
+ * Copyright (C) 2017 Dennis Zhou <dennis@kernel.org>
*
* The percpu allocator handles both static and dynamic areas. Percpu
* areas are allocated in chunks which are divided into units. There is
@@ -38,9 +37,14 @@
* takes care of normal allocations.
*
* The allocator organizes chunks into lists according to free size and
- * tries to allocate from the fullest chunk first. Each chunk is managed
- * by a bitmap with metadata blocks. The allocation map is updated on
- * every allocation and free to reflect the current state while the boundary
+ * memcg-awareness. To make a percpu allocation memcg-aware the __GFP_ACCOUNT
+ * flag should be passed. All memcg-aware allocations are sharing one set
+ * of chunks and all unaccounted allocations and allocations performed
+ * by processes belonging to the root memory cgroup are using the second set.
+ *
+ * The allocator tries to allocate from the fullest chunk first. Each chunk
+ * is managed by a bitmap with metadata blocks. The allocation map is updated
+ * on every allocation and free to reflect the current state while the boundary
* map is only updated on allocation. Each metadata block contains
* information to help mitigate the need to iterate over large portions
* of the bitmap. The reverse mapping from page to chunk is stored in
@@ -65,7 +69,7 @@
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/bitmap.h>
-#include <linux/bootmem.h>
+#include <linux/memblock.h>
#include <linux/err.h>
#include <linux/lcm.h>
#include <linux/list.h>
@@ -81,6 +85,8 @@
#include <linux/workqueue.h>
#include <linux/kmemleak.h>
#include <linux/sched.h>
+#include <linux/sched/mm.h>
+#include <linux/memcontrol.h>
#include <asm/cacheflush.h>
#include <asm/sections.h>
@@ -94,6 +100,8 @@
/* the slots are sorted by free bytes left, 1-31 bytes share the same slot */
#define PCPU_SLOT_BASE_SHIFT 5
+/* chunks in slots below this are subject to being sidelined on failed alloc */
+#define PCPU_SLOT_FAIL_THRESHOLD 3
#define PCPU_EMPTY_POP_PAGES_LOW 2
#define PCPU_EMPTY_POP_PAGES_HIGH 4
@@ -158,16 +166,16 @@
DEFINE_SPINLOCK(pcpu_lock); /* all internal data structures */
static DEFINE_MUTEX(pcpu_alloc_mutex); /* chunk create/destroy, [de]pop, map ext */
-struct list_head *pcpu_slot __ro_after_init; /* chunk list slots */
+struct list_head *pcpu_chunk_lists __ro_after_init; /* chunk list slots */
/* chunks which need their map areas extended, protected by pcpu_lock */
static LIST_HEAD(pcpu_map_extend_chunks);
/*
- * The number of empty populated pages, protected by pcpu_lock. The
- * reserved chunk doesn't contribute to the count.
+ * The number of empty populated pages by chunk type, protected by pcpu_lock.
+ * The reserved chunk doesn't contribute to the count.
*/
-int pcpu_nr_empty_pop_pages;
+int pcpu_nr_empty_pop_pages[PCPU_NR_CHUNK_TYPES];
/*
* The number of populated pages in use by the allocator, protected by
@@ -231,10 +239,13 @@
static int pcpu_chunk_slot(const struct pcpu_chunk *chunk)
{
- if (chunk->free_bytes < PCPU_MIN_ALLOC_SIZE || chunk->contig_bits == 0)
+ const struct pcpu_block_md *chunk_md = &chunk->chunk_md;
+
+ if (chunk->free_bytes < PCPU_MIN_ALLOC_SIZE ||
+ chunk_md->contig_hint == 0)
return 0;
- return pcpu_size_to_slot(chunk->free_bytes);
+ return pcpu_size_to_slot(chunk_md->contig_hint * PCPU_MIN_ALLOC_SIZE);
}
/* set the pointer to a chunk in a page struct */
@@ -266,33 +277,6 @@
pcpu_unit_page_offset(cpu, page_idx);
}
-static void pcpu_next_unpop(unsigned long *bitmap, int *rs, int *re, int end)
-{
- *rs = find_next_zero_bit(bitmap, end, *rs);
- *re = find_next_bit(bitmap, end, *rs + 1);
-}
-
-static void pcpu_next_pop(unsigned long *bitmap, int *rs, int *re, int end)
-{
- *rs = find_next_bit(bitmap, end, *rs);
- *re = find_next_zero_bit(bitmap, end, *rs + 1);
-}
-
-/*
- * Bitmap region iterators. Iterates over the bitmap between
- * [@start, @end) in @chunk. @rs and @re should be integer variables
- * and will be set to start and end index of the current free region.
- */
-#define pcpu_for_each_unpop_region(bitmap, rs, re, start, end) \
- for ((rs) = (start), pcpu_next_unpop((bitmap), &(rs), &(re), (end)); \
- (rs) < (re); \
- (rs) = (re) + 1, pcpu_next_unpop((bitmap), &(rs), &(re), (end)))
-
-#define pcpu_for_each_pop_region(bitmap, rs, re, start, end) \
- for ((rs) = (start), pcpu_next_pop((bitmap), &(rs), &(re), (end)); \
- (rs) < (re); \
- (rs) = (re) + 1, pcpu_next_pop((bitmap), &(rs), &(re), (end)))
-
/*
* The following are helper functions to help access bitmaps and convert
* between bitmap offsets to address offsets.
@@ -316,6 +300,34 @@
static unsigned long pcpu_block_off_to_off(int index, int off)
{
return index * PCPU_BITMAP_BLOCK_BITS + off;
+}
+
+/*
+ * pcpu_next_hint - determine which hint to use
+ * @block: block of interest
+ * @alloc_bits: size of allocation
+ *
+ * This determines if we should scan based on the scan_hint or first_free.
+ * In general, we want to scan from first_free to fulfill allocations by
+ * first fit. However, if we know a scan_hint at position scan_hint_start
+ * cannot fulfill an allocation, we can begin scanning from there knowing
+ * the contig_hint will be our fallback.
+ */
+static int pcpu_next_hint(struct pcpu_block_md *block, int alloc_bits)
+{
+ /*
+ * The three conditions below determine if we can skip past the
+ * scan_hint. First, does the scan hint exist. Second, is the
+ * contig_hint after the scan_hint (possibly not true iff
+ * contig_hint == scan_hint). Third, is the allocation request
+ * larger than the scan_hint.
+ */
+ if (block->scan_hint &&
+ block->contig_hint_start > block->scan_hint_start &&
+ alloc_bits > block->scan_hint)
+ return block->scan_hint_start + block->scan_hint;
+
+ return block->first_free;
}
/**
@@ -413,9 +425,11 @@
if (block->contig_hint &&
block->contig_hint_start >= block_off &&
block->contig_hint >= *bits + alloc_bits) {
+ int start = pcpu_next_hint(block, alloc_bits);
+
*bits += alloc_bits + block->contig_hint_start -
- block->first_free;
- *bit_off = pcpu_block_off_to_off(i, block->first_free);
+ start;
+ *bit_off = pcpu_block_off_to_off(i, start);
return;
}
/* reset to satisfy the second predicate above */
@@ -474,7 +488,7 @@
if (size <= PAGE_SIZE)
return kzalloc(size, gfp);
else
- return __vmalloc(size, gfp | __GFP_ZERO, PAGE_KERNEL);
+ return __vmalloc(size, gfp | __GFP_ZERO);
}
/**
@@ -486,6 +500,25 @@
static void pcpu_mem_free(void *ptr)
{
kvfree(ptr);
+}
+
+static void __pcpu_chunk_move(struct pcpu_chunk *chunk, int slot,
+ bool move_front)
+{
+ if (chunk != pcpu_reserved_chunk) {
+ struct list_head *pcpu_slot;
+
+ pcpu_slot = pcpu_chunk_list(pcpu_chunk_type(chunk));
+ if (move_front)
+ list_move(&chunk->list, &pcpu_slot[slot]);
+ else
+ list_move_tail(&chunk->list, &pcpu_slot[slot]);
+ }
+}
+
+static void pcpu_chunk_move(struct pcpu_chunk *chunk, int slot)
+{
+ __pcpu_chunk_move(chunk, slot, true);
}
/**
@@ -505,110 +538,39 @@
{
int nslot = pcpu_chunk_slot(chunk);
- if (chunk != pcpu_reserved_chunk && oslot != nslot) {
- if (oslot < nslot)
- list_move(&chunk->list, &pcpu_slot[nslot]);
- else
- list_move_tail(&chunk->list, &pcpu_slot[nslot]);
- }
+ if (oslot != nslot)
+ __pcpu_chunk_move(chunk, nslot, oslot < nslot);
}
-/**
- * pcpu_cnt_pop_pages- counts populated backing pages in range
+/*
+ * pcpu_update_empty_pages - update empty page counters
* @chunk: chunk of interest
- * @bit_off: start offset
- * @bits: size of area to check
+ * @nr: nr of empty pages
*
- * 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.
+ * 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.
*/
-static inline int pcpu_cnt_pop_pages(struct pcpu_chunk *chunk, int bit_off,
- int bits)
+static inline void pcpu_update_empty_pages(struct pcpu_chunk *chunk, int nr)
{
- 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
- * the specified number of bits. This is counting the populated
- * pages up to page_end and then subtracting the populated pages
- * up to page_start to count the populated pages in
- * [page_start, page_end).
- */
- return bitmap_weight(chunk->populated, page_end) -
- bitmap_weight(chunk->populated, page_start);
-}
-
-/**
- * pcpu_chunk_update - updates the chunk metadata given a free area
- * @chunk: chunk of interest
- * @bit_off: chunk offset
- * @bits: size of free area
- *
- * This updates the chunk's contig hint and starting offset given a free area.
- * Choose the best starting offset if the contig hint is equal.
- */
-static void pcpu_chunk_update(struct pcpu_chunk *chunk, int bit_off, int bits)
-{
- if (bits > chunk->contig_bits) {
- chunk->contig_bits_start = bit_off;
- chunk->contig_bits = bits;
- } else if (bits == chunk->contig_bits && chunk->contig_bits_start &&
- (!bit_off ||
- __ffs(bit_off) > __ffs(chunk->contig_bits_start))) {
- /* use the start with the best alignment */
- chunk->contig_bits_start = bit_off;
- }
-}
-
-/**
- * pcpu_chunk_refresh_hint - updates metadata about a chunk
- * @chunk: chunk of interest
- *
- * 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 (chunk and global)
- */
-static void pcpu_chunk_refresh_hint(struct pcpu_chunk *chunk)
-{
- 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_md_free_region(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.
- */
+ chunk->nr_empty_pop_pages += nr;
if (chunk != pcpu_reserved_chunk)
- pcpu_nr_empty_pop_pages +=
- (nr_empty_pop_pages - chunk->nr_empty_pop_pages);
+ pcpu_nr_empty_pop_pages[pcpu_chunk_type(chunk)] += nr;
+}
- chunk->nr_empty_pop_pages = nr_empty_pop_pages;
+/*
+ * pcpu_region_overlap - determines if two regions overlap
+ * @a: start of first region, inclusive
+ * @b: end of first region, exclusive
+ * @x: start of second region, inclusive
+ * @y: end of second region, exclusive
+ *
+ * This is used to determine if the hint region [a, b) overlaps with the
+ * allocated region [x, y).
+ */
+static inline bool pcpu_region_overlap(int a, int b, int x, int y)
+{
+ return (a < y) && (x < b);
}
/**
@@ -629,17 +591,132 @@
if (start == 0)
block->left_free = contig;
- if (end == PCPU_BITMAP_BLOCK_BITS)
+ if (end == block->nr_bits)
block->right_free = contig;
if (contig > block->contig_hint) {
+ /* promote the old contig_hint to be the new scan_hint */
+ if (start > block->contig_hint_start) {
+ if (block->contig_hint > block->scan_hint) {
+ block->scan_hint_start =
+ block->contig_hint_start;
+ block->scan_hint = block->contig_hint;
+ } else if (start < block->scan_hint_start) {
+ /*
+ * The old contig_hint == scan_hint. But, the
+ * new contig is larger so hold the invariant
+ * scan_hint_start < contig_hint_start.
+ */
+ block->scan_hint = 0;
+ }
+ } else {
+ block->scan_hint = 0;
+ }
block->contig_hint_start = start;
block->contig_hint = contig;
- } else if (block->contig_hint_start && contig == block->contig_hint &&
- (!start || __ffs(start) > __ffs(block->contig_hint_start))) {
- /* use the start with the best alignment */
- block->contig_hint_start = start;
+ } else if (contig == block->contig_hint) {
+ if (block->contig_hint_start &&
+ (!start ||
+ __ffs(start) > __ffs(block->contig_hint_start))) {
+ /* start has a better alignment so use it */
+ block->contig_hint_start = start;
+ if (start < block->scan_hint_start &&
+ block->contig_hint > block->scan_hint)
+ block->scan_hint = 0;
+ } else if (start > block->scan_hint_start ||
+ block->contig_hint > block->scan_hint) {
+ /*
+ * Knowing contig == contig_hint, update the scan_hint
+ * if it is farther than or larger than the current
+ * scan_hint.
+ */
+ block->scan_hint_start = start;
+ block->scan_hint = contig;
+ }
+ } else {
+ /*
+ * The region is smaller than the contig_hint. So only update
+ * the scan_hint if it is larger than or equal and farther than
+ * the current scan_hint.
+ */
+ if ((start < block->contig_hint_start &&
+ (contig > block->scan_hint ||
+ (contig == block->scan_hint &&
+ start > block->scan_hint_start)))) {
+ block->scan_hint_start = start;
+ block->scan_hint = contig;
+ }
}
+}
+
+/*
+ * pcpu_block_update_scan - update a block given a free area from a scan
+ * @chunk: chunk of interest
+ * @bit_off: chunk offset
+ * @bits: size of free area
+ *
+ * Finding the final allocation spot first goes through pcpu_find_block_fit()
+ * to find a block that can hold the allocation and then pcpu_alloc_area()
+ * where a scan is used. When allocations require specific alignments,
+ * we can inadvertently create holes which will not be seen in the alloc
+ * or free paths.
+ *
+ * This takes a given free area hole and updates a block as it may change the
+ * scan_hint. We need to scan backwards to ensure we don't miss free bits
+ * from alignment.
+ */
+static void pcpu_block_update_scan(struct pcpu_chunk *chunk, int bit_off,
+ int bits)
+{
+ int s_off = pcpu_off_to_block_off(bit_off);
+ int e_off = s_off + bits;
+ int s_index, l_bit;
+ struct pcpu_block_md *block;
+
+ if (e_off > PCPU_BITMAP_BLOCK_BITS)
+ return;
+
+ s_index = pcpu_off_to_block_index(bit_off);
+ block = chunk->md_blocks + s_index;
+
+ /* scan backwards in case of alignment skipping free bits */
+ l_bit = find_last_bit(pcpu_index_alloc_map(chunk, s_index), s_off);
+ s_off = (s_off == l_bit) ? 0 : l_bit + 1;
+
+ pcpu_block_update(block, s_off, e_off);
+}
+
+/**
+ * pcpu_chunk_refresh_hint - updates metadata about a chunk
+ * @chunk: chunk of interest
+ * @full_scan: if we should scan from the beginning
+ *
+ * Iterates over the metadata blocks to find the largest contig area.
+ * A full scan can be avoided on the allocation path as this is triggered
+ * if we broke the contig_hint. In doing so, the scan_hint will be before
+ * the contig_hint or after if the scan_hint == contig_hint. This cannot
+ * be prevented on freeing as we want to find the largest area possibly
+ * spanning blocks.
+ */
+static void pcpu_chunk_refresh_hint(struct pcpu_chunk *chunk, bool full_scan)
+{
+ struct pcpu_block_md *chunk_md = &chunk->chunk_md;
+ int bit_off, bits;
+
+ /* promote scan_hint to contig_hint */
+ if (!full_scan && chunk_md->scan_hint) {
+ bit_off = chunk_md->scan_hint_start + chunk_md->scan_hint;
+ chunk_md->contig_hint_start = chunk_md->scan_hint_start;
+ chunk_md->contig_hint = chunk_md->scan_hint;
+ chunk_md->scan_hint = 0;
+ } else {
+ bit_off = chunk_md->first_free;
+ chunk_md->contig_hint = 0;
+ }
+
+ bits = 0;
+ pcpu_for_each_md_free_region(chunk, bit_off, bits)
+ pcpu_block_update(chunk_md, bit_off, bit_off + bits);
}
/**
@@ -654,17 +731,25 @@
{
struct pcpu_block_md *block = chunk->md_blocks + index;
unsigned long *alloc_map = pcpu_index_alloc_map(chunk, index);
- int rs, re; /* region start, region end */
+ unsigned int rs, re, start; /* region start, region end */
- /* clear hints */
- block->contig_hint = 0;
- block->left_free = block->right_free = 0;
+ /* promote scan_hint to contig_hint */
+ if (block->scan_hint) {
+ start = block->scan_hint_start + block->scan_hint;
+ block->contig_hint_start = block->scan_hint_start;
+ block->contig_hint = block->scan_hint;
+ block->scan_hint = 0;
+ } else {
+ start = block->first_free;
+ block->contig_hint = 0;
+ }
+
+ block->right_free = 0;
/* iterate over free areas and update the contig hints */
- pcpu_for_each_unpop_region(alloc_map, rs, re, block->first_free,
- PCPU_BITMAP_BLOCK_BITS) {
+ bitmap_for_each_clear_region(alloc_map, rs, re, start,
+ PCPU_BITMAP_BLOCK_BITS)
pcpu_block_update(block, rs, re);
- }
}
/**
@@ -680,6 +765,8 @@
static void pcpu_block_update_hint_alloc(struct pcpu_chunk *chunk, int bit_off,
int bits)
{
+ struct pcpu_block_md *chunk_md = &chunk->chunk_md;
+ int nr_empty_pages = 0;
struct pcpu_block_md *s_block, *e_block, *block;
int s_index, e_index; /* block indexes of the freed allocation */
int s_off, e_off; /* block offsets of the freed allocation */
@@ -704,15 +791,29 @@
* If the allocation breaks the contig_hint, a scan is required to
* restore this hint.
*/
+ if (s_block->contig_hint == PCPU_BITMAP_BLOCK_BITS)
+ nr_empty_pages++;
+
if (s_off == s_block->first_free)
s_block->first_free = find_next_zero_bit(
pcpu_index_alloc_map(chunk, s_index),
PCPU_BITMAP_BLOCK_BITS,
s_off + bits);
- if (s_off >= s_block->contig_hint_start &&
- s_off < s_block->contig_hint_start + s_block->contig_hint) {
+ if (pcpu_region_overlap(s_block->scan_hint_start,
+ s_block->scan_hint_start + s_block->scan_hint,
+ s_off,
+ s_off + bits))
+ s_block->scan_hint = 0;
+
+ if (pcpu_region_overlap(s_block->contig_hint_start,
+ s_block->contig_hint_start +
+ s_block->contig_hint,
+ s_off,
+ s_off + bits)) {
/* block contig hint is broken - scan to fix it */
+ if (!s_off)
+ s_block->left_free = 0;
pcpu_block_refresh_hint(chunk, s_index);
} else {
/* update left and right contig manually */
@@ -728,6 +829,9 @@
* Update e_block.
*/
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
* the left part of the e_block.
@@ -740,11 +844,14 @@
/* reset the block */
e_block++;
} else {
+ if (e_off > e_block->scan_hint_start)
+ e_block->scan_hint = 0;
+
+ e_block->left_free = 0;
if (e_off > e_block->contig_hint_start) {
/* contig hint is broken - scan to fix it */
pcpu_block_refresh_hint(chunk, e_index);
} else {
- e_block->left_free = 0;
e_block->right_free =
min_t(int, e_block->right_free,
PCPU_BITMAP_BLOCK_BITS - e_off);
@@ -752,21 +859,36 @@
}
/* update in-between md_blocks */
+ nr_empty_pages += (e_index - s_index - 1);
for (block = s_block + 1; block < e_block; block++) {
+ block->scan_hint = 0;
block->contig_hint = 0;
block->left_free = 0;
block->right_free = 0;
}
}
+ if (nr_empty_pages)
+ pcpu_update_empty_pages(chunk, -nr_empty_pages);
+
+ if (pcpu_region_overlap(chunk_md->scan_hint_start,
+ chunk_md->scan_hint_start +
+ chunk_md->scan_hint,
+ bit_off,
+ bit_off + bits))
+ chunk_md->scan_hint = 0;
+
/*
* The only time a full chunk scan is required is if the chunk
* contig hint is broken. Otherwise, it means a smaller space
* was used and therefore the chunk contig hint is still correct.
*/
- if (bit_off >= chunk->contig_bits_start &&
- bit_off < chunk->contig_bits_start + chunk->contig_bits)
- pcpu_chunk_refresh_hint(chunk);
+ if (pcpu_region_overlap(chunk_md->contig_hint_start,
+ chunk_md->contig_hint_start +
+ chunk_md->contig_hint,
+ bit_off,
+ bit_off + bits))
+ pcpu_chunk_refresh_hint(chunk, false);
}
/**
@@ -782,13 +904,15 @@
*
* A chunk update is triggered if a page becomes free, a block becomes free,
* or the free spans across blocks. This tradeoff is to minimize iterating
- * over the block metadata to update chunk->contig_bits. chunk->contig_bits
- * may be off by up to a page, but it will never be more than the available
- * space. If the contig hint is contained in one block, it will be accurate.
+ * over the block metadata to update chunk_md->contig_hint.
+ * chunk_md->contig_hint may be off by up to a page, but it will never be more
+ * than the available space. If the contig hint is contained in one block, it
+ * will be accurate.
*/
static void pcpu_block_update_hint_free(struct pcpu_chunk *chunk, int bit_off,
int bits)
{
+ int nr_empty_pages = 0;
struct pcpu_block_md *s_block, *e_block, *block;
int s_index, e_index; /* block indexes of the freed allocation */
int s_off, e_off; /* block offsets of the freed allocation */
@@ -842,16 +966,22 @@
/* update s_block */
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);
/* freeing in the same block */
if (s_index != e_index) {
/* update e_block */
+ if (end == PCPU_BITMAP_BLOCK_BITS)
+ nr_empty_pages++;
pcpu_block_update(e_block, 0, end);
/* reset md_blocks in the middle */
+ nr_empty_pages += (e_index - s_index - 1);
for (block = s_block + 1; block < e_block; block++) {
block->first_free = 0;
+ block->scan_hint = 0;
block->contig_hint_start = 0;
block->contig_hint = PCPU_BITMAP_BLOCK_BITS;
block->left_free = PCPU_BITMAP_BLOCK_BITS;
@@ -859,19 +989,21 @@
}
}
+ if (nr_empty_pages)
+ pcpu_update_empty_pages(chunk, nr_empty_pages);
+
/*
- * Refresh chunk metadata when the free makes a page free, a block
- * free, or spans across blocks. The contig hint may be off by up to
- * a page, but if the hint is contained in a block, it will be accurate
- * with the else condition below.
+ * Refresh chunk metadata when the free makes a block free or spans
+ * across blocks. The contig_hint may be off by up to a page, but if
+ * the contig_hint is contained in a block, it will be accurate with
+ * the else condition below.
*/
- if ((ALIGN_DOWN(end, min(PCPU_BITS_PER_PAGE, PCPU_BITMAP_BLOCK_BITS)) >
- ALIGN(start, min(PCPU_BITS_PER_PAGE, PCPU_BITMAP_BLOCK_BITS))) ||
- s_index != e_index)
- pcpu_chunk_refresh_hint(chunk);
+ if (((end - start) >= PCPU_BITMAP_BLOCK_BITS) || s_index != e_index)
+ pcpu_chunk_refresh_hint(chunk, true);
else
- pcpu_chunk_update(chunk, pcpu_block_off_to_off(s_index, start),
- s_block->contig_hint);
+ pcpu_block_update(&chunk->chunk_md,
+ pcpu_block_off_to_off(s_index, start),
+ end);
}
/**
@@ -890,13 +1022,13 @@
static bool pcpu_is_populated(struct pcpu_chunk *chunk, int bit_off, int bits,
int *next_off)
{
- int page_start, page_end, rs, re;
+ unsigned int page_start, page_end, rs, re;
page_start = PFN_DOWN(bit_off * PCPU_MIN_ALLOC_SIZE);
page_end = PFN_UP((bit_off + bits) * PCPU_MIN_ALLOC_SIZE);
rs = page_start;
- pcpu_next_unpop(chunk->populated, &rs, &re, page_end);
+ bitmap_next_clear_region(chunk->populated, &rs, &re, page_end);
if (rs >= page_end)
return true;
@@ -926,6 +1058,7 @@
static int pcpu_find_block_fit(struct pcpu_chunk *chunk, int alloc_bits,
size_t align, bool pop_only)
{
+ struct pcpu_block_md *chunk_md = &chunk->chunk_md;
int bit_off, bits, next_off;
/*
@@ -934,12 +1067,12 @@
* cannot fit in the global hint, there is memory pressure and creating
* a new chunk would happen soon.
*/
- bit_off = ALIGN(chunk->contig_bits_start, align) -
- chunk->contig_bits_start;
- if (bit_off + alloc_bits > chunk->contig_bits)
+ bit_off = ALIGN(chunk_md->contig_hint_start, align) -
+ chunk_md->contig_hint_start;
+ if (bit_off + alloc_bits > chunk_md->contig_hint)
return -1;
- bit_off = chunk->first_bit;
+ bit_off = pcpu_next_hint(chunk_md, alloc_bits);
bits = 0;
pcpu_for_each_fit_region(chunk, alloc_bits, align, bit_off, bits) {
if (!pop_only || pcpu_is_populated(chunk, bit_off, bits,
@@ -954,6 +1087,62 @@
return -1;
return bit_off;
+}
+
+/*
+ * pcpu_find_zero_area - modified from bitmap_find_next_zero_area_off()
+ * @map: the address to base the search on
+ * @size: the bitmap size in bits
+ * @start: the bitnumber to start searching at
+ * @nr: the number of zeroed bits we're looking for
+ * @align_mask: alignment mask for zero area
+ * @largest_off: offset of the largest area skipped
+ * @largest_bits: size of the largest area skipped
+ *
+ * The @align_mask should be one less than a power of 2.
+ *
+ * This is a modified version of bitmap_find_next_zero_area_off() to remember
+ * the largest area that was skipped. This is imperfect, but in general is
+ * good enough. The largest remembered region is the largest failed region
+ * seen. This does not include anything we possibly skipped due to alignment.
+ * pcpu_block_update_scan() does scan backwards to try and recover what was
+ * lost to alignment. While this can cause scanning to miss earlier possible
+ * free areas, smaller allocations will eventually fill those holes.
+ */
+static unsigned long pcpu_find_zero_area(unsigned long *map,
+ unsigned long size,
+ unsigned long start,
+ unsigned long nr,
+ unsigned long align_mask,
+ unsigned long *largest_off,
+ unsigned long *largest_bits)
+{
+ unsigned long index, end, i, area_off, area_bits;
+again:
+ index = find_next_zero_bit(map, size, start);
+
+ /* Align allocation */
+ index = __ALIGN_MASK(index, align_mask);
+ area_off = index;
+
+ end = index + nr;
+ if (end > size)
+ return end;
+ i = find_next_bit(map, end, index);
+ if (i < end) {
+ area_bits = i - area_off;
+ /* remember largest unused area with best alignment */
+ if (area_bits > *largest_bits ||
+ (area_bits == *largest_bits && *largest_off &&
+ (!area_off || __ffs(area_off) > __ffs(*largest_off)))) {
+ *largest_off = area_off;
+ *largest_bits = area_bits;
+ }
+
+ start = i + 1;
+ goto again;
+ }
+ return index;
}
/**
@@ -978,7 +1167,9 @@
static int pcpu_alloc_area(struct pcpu_chunk *chunk, int alloc_bits,
size_t align, int start)
{
+ struct pcpu_block_md *chunk_md = &chunk->chunk_md;
size_t align_mask = (align) ? (align - 1) : 0;
+ unsigned long area_off = 0, area_bits = 0;
int bit_off, end, oslot;
lockdep_assert_held(&pcpu_lock);
@@ -990,10 +1181,13 @@
*/
end = min_t(int, start + alloc_bits + PCPU_BITMAP_BLOCK_BITS,
pcpu_chunk_map_bits(chunk));
- bit_off = bitmap_find_next_zero_area(chunk->alloc_map, end, start,
- alloc_bits, align_mask);
+ bit_off = pcpu_find_zero_area(chunk->alloc_map, end, start, alloc_bits,
+ align_mask, &area_off, &area_bits);
if (bit_off >= end)
return -1;
+
+ if (area_bits)
+ pcpu_block_update_scan(chunk, area_off, area_bits);
/* update alloc map */
bitmap_set(chunk->alloc_map, bit_off, alloc_bits);
@@ -1006,8 +1200,8 @@
chunk->free_bytes -= alloc_bits * PCPU_MIN_ALLOC_SIZE;
/* update first free bit */
- if (bit_off == chunk->first_bit)
- chunk->first_bit = find_next_zero_bit(
+ if (bit_off == chunk_md->first_free)
+ chunk_md->first_free = find_next_zero_bit(
chunk->alloc_map,
pcpu_chunk_map_bits(chunk),
bit_off + alloc_bits);
@@ -1026,10 +1220,14 @@
*
* This function determines the size of an allocation to free using
* the boundary bitmap and clears the allocation map.
+ *
+ * RETURNS:
+ * Number of freed bytes.
*/
-static void pcpu_free_area(struct pcpu_chunk *chunk, int off)
+static int pcpu_free_area(struct pcpu_chunk *chunk, int off)
{
- int bit_off, bits, end, oslot;
+ struct pcpu_block_md *chunk_md = &chunk->chunk_md;
+ int bit_off, bits, end, oslot, freed;
lockdep_assert_held(&pcpu_lock);
pcpu_stats_area_dealloc(chunk);
@@ -1044,28 +1242,42 @@
bits = end - bit_off;
bitmap_clear(chunk->alloc_map, bit_off, bits);
+ freed = bits * PCPU_MIN_ALLOC_SIZE;
+
/* update metadata */
- chunk->free_bytes += bits * PCPU_MIN_ALLOC_SIZE;
+ chunk->free_bytes += freed;
/* update first free bit */
- chunk->first_bit = min(chunk->first_bit, bit_off);
+ chunk_md->first_free = min(chunk_md->first_free, bit_off);
pcpu_block_update_hint_free(chunk, bit_off, bits);
pcpu_chunk_relocate(chunk, oslot);
+
+ return freed;
+}
+
+static void pcpu_init_md_block(struct pcpu_block_md *block, int nr_bits)
+{
+ block->scan_hint = 0;
+ block->contig_hint = nr_bits;
+ block->left_free = nr_bits;
+ block->right_free = nr_bits;
+ block->first_free = 0;
+ block->nr_bits = nr_bits;
}
static void pcpu_init_md_blocks(struct pcpu_chunk *chunk)
{
struct pcpu_block_md *md_block;
+ /* init the chunk's block */
+ pcpu_init_md_block(&chunk->chunk_md, pcpu_chunk_map_bits(chunk));
+
for (md_block = chunk->md_blocks;
md_block != chunk->md_blocks + pcpu_chunk_nr_blocks(chunk);
- md_block++) {
- md_block->contig_hint = PCPU_BITMAP_BLOCK_BITS;
- md_block->left_free = PCPU_BITMAP_BLOCK_BITS;
- md_block->right_free = PCPU_BITMAP_BLOCK_BITS;
- }
+ md_block++)
+ pcpu_init_md_block(md_block, PCPU_BITMAP_BLOCK_BITS);
}
/**
@@ -1087,6 +1299,7 @@
struct pcpu_chunk *chunk;
unsigned long aligned_addr, lcm_align;
int start_offset, offset_bits, region_size, region_bits;
+ size_t alloc_size;
/* region calculations */
aligned_addr = tmp_addr & PAGE_MASK;
@@ -1102,9 +1315,12 @@
region_size = ALIGN(start_offset + map_size, lcm_align);
/* allocate chunk */
- chunk = memblock_virt_alloc(sizeof(struct pcpu_chunk) +
- BITS_TO_LONGS(region_size >> PAGE_SHIFT) * sizeof(unsigned long),
- 0);
+ alloc_size = struct_size(chunk, populated,
+ BITS_TO_LONGS(region_size >> PAGE_SHIFT));
+ chunk = memblock_alloc(alloc_size, SMP_CACHE_BYTES);
+ if (!chunk)
+ panic("%s: Failed to allocate %zu bytes\n", __func__,
+ alloc_size);
INIT_LIST_HEAD(&chunk->list);
@@ -1115,23 +1331,37 @@
chunk->nr_pages = region_size >> PAGE_SHIFT;
region_bits = pcpu_chunk_map_bits(chunk);
- chunk->alloc_map = memblock_virt_alloc(BITS_TO_LONGS(region_bits) *
- sizeof(chunk->alloc_map[0]), 0);
- chunk->bound_map = memblock_virt_alloc(BITS_TO_LONGS(region_bits + 1) *
- sizeof(chunk->bound_map[0]), 0);
- chunk->md_blocks = memblock_virt_alloc(pcpu_chunk_nr_blocks(chunk) *
- sizeof(chunk->md_blocks[0]), 0);
+ alloc_size = BITS_TO_LONGS(region_bits) * sizeof(chunk->alloc_map[0]);
+ chunk->alloc_map = memblock_alloc(alloc_size, SMP_CACHE_BYTES);
+ if (!chunk->alloc_map)
+ panic("%s: Failed to allocate %zu bytes\n", __func__,
+ alloc_size);
+
+ alloc_size =
+ BITS_TO_LONGS(region_bits + 1) * sizeof(chunk->bound_map[0]);
+ chunk->bound_map = memblock_alloc(alloc_size, SMP_CACHE_BYTES);
+ if (!chunk->bound_map)
+ panic("%s: Failed to allocate %zu bytes\n", __func__,
+ alloc_size);
+
+ alloc_size = pcpu_chunk_nr_blocks(chunk) * sizeof(chunk->md_blocks[0]);
+ chunk->md_blocks = memblock_alloc(alloc_size, SMP_CACHE_BYTES);
+ if (!chunk->md_blocks)
+ panic("%s: Failed to allocate %zu bytes\n", __func__,
+ alloc_size);
+
+#ifdef CONFIG_MEMCG_KMEM
+ /* first chunk isn't memcg-aware */
+ chunk->obj_cgroups = NULL;
+#endif
pcpu_init_md_blocks(chunk);
/* manage populated page bitmap */
chunk->immutable = true;
bitmap_fill(chunk->populated, chunk->nr_pages);
chunk->nr_populated = chunk->nr_pages;
- chunk->nr_empty_pop_pages =
- pcpu_cnt_pop_pages(chunk, start_offset / PCPU_MIN_ALLOC_SIZE,
- map_size / PCPU_MIN_ALLOC_SIZE);
+ chunk->nr_empty_pop_pages = chunk->nr_pages;
- chunk->contig_bits = map_size / PCPU_MIN_ALLOC_SIZE;
chunk->free_bytes = map_size;
if (chunk->start_offset) {
@@ -1141,7 +1371,7 @@
set_bit(0, chunk->bound_map);
set_bit(offset_bits, chunk->bound_map);
- chunk->first_bit = offset_bits;
+ chunk->chunk_md.first_free = offset_bits;
pcpu_block_update_hint_alloc(chunk, 0, offset_bits);
}
@@ -1163,7 +1393,7 @@
return chunk;
}
-static struct pcpu_chunk *pcpu_alloc_chunk(gfp_t gfp)
+static struct pcpu_chunk *pcpu_alloc_chunk(enum pcpu_chunk_type type, gfp_t gfp)
{
struct pcpu_chunk *chunk;
int region_bits;
@@ -1191,14 +1421,27 @@
if (!chunk->md_blocks)
goto md_blocks_fail;
+#ifdef CONFIG_MEMCG_KMEM
+ if (pcpu_is_memcg_chunk(type)) {
+ chunk->obj_cgroups =
+ pcpu_mem_zalloc(pcpu_chunk_map_bits(chunk) *
+ sizeof(struct obj_cgroup *), gfp);
+ if (!chunk->obj_cgroups)
+ goto objcg_fail;
+ }
+#endif
+
pcpu_init_md_blocks(chunk);
/* init metadata */
- chunk->contig_bits = region_bits;
chunk->free_bytes = chunk->nr_pages * PAGE_SIZE;
return chunk;
+#ifdef CONFIG_MEMCG_KMEM
+objcg_fail:
+ pcpu_mem_free(chunk->md_blocks);
+#endif
md_blocks_fail:
pcpu_mem_free(chunk->bound_map);
bound_map_fail:
@@ -1213,6 +1456,9 @@
{
if (!chunk)
return;
+#ifdef CONFIG_MEMCG_KMEM
+ pcpu_mem_free(chunk->obj_cgroups);
+#endif
pcpu_mem_free(chunk->md_blocks);
pcpu_mem_free(chunk->bound_map);
pcpu_mem_free(chunk->alloc_map);
@@ -1224,7 +1470,6 @@
* @chunk: pcpu_chunk which got populated
* @page_start: the start 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
* the bookkeeping information accordingly. Must be called after each
@@ -1234,7 +1479,7 @@
* is to serve an allocation in that area.
*/
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;
@@ -1244,10 +1489,7 @@
chunk->nr_populated += nr;
pcpu_nr_populated += nr;
- if (!for_alloc) {
- chunk->nr_empty_pop_pages += nr;
- pcpu_nr_empty_pop_pages += nr;
- }
+ pcpu_update_empty_pages(chunk, nr);
}
/**
@@ -1269,9 +1511,9 @@
bitmap_clear(chunk->populated, page_start, nr);
chunk->nr_populated -= nr;
- chunk->nr_empty_pop_pages -= nr;
- pcpu_nr_empty_pop_pages -= nr;
pcpu_nr_populated -= nr;
+
+ pcpu_update_empty_pages(chunk, -nr);
}
/*
@@ -1293,7 +1535,8 @@
int page_start, int page_end, gfp_t gfp);
static void pcpu_depopulate_chunk(struct pcpu_chunk *chunk,
int page_start, int page_end);
-static struct pcpu_chunk *pcpu_create_chunk(gfp_t gfp);
+static struct pcpu_chunk *pcpu_create_chunk(enum pcpu_chunk_type type,
+ gfp_t gfp);
static void pcpu_destroy_chunk(struct pcpu_chunk *chunk);
static struct page *pcpu_addr_to_page(void *addr);
static int __init pcpu_verify_alloc_info(const struct pcpu_alloc_info *ai);
@@ -1335,6 +1578,86 @@
return pcpu_get_page_chunk(pcpu_addr_to_page(addr));
}
+#ifdef CONFIG_MEMCG_KMEM
+static enum pcpu_chunk_type pcpu_memcg_pre_alloc_hook(size_t size, gfp_t gfp,
+ struct obj_cgroup **objcgp)
+{
+ struct obj_cgroup *objcg;
+
+ if (!memcg_kmem_enabled() || !(gfp & __GFP_ACCOUNT))
+ return PCPU_CHUNK_ROOT;
+
+ objcg = get_obj_cgroup_from_current();
+ if (!objcg)
+ return PCPU_CHUNK_ROOT;
+
+ if (obj_cgroup_charge(objcg, gfp, size * num_possible_cpus())) {
+ obj_cgroup_put(objcg);
+ return PCPU_FAIL_ALLOC;
+ }
+
+ *objcgp = objcg;
+ return PCPU_CHUNK_MEMCG;
+}
+
+static void pcpu_memcg_post_alloc_hook(struct obj_cgroup *objcg,
+ struct pcpu_chunk *chunk, int off,
+ size_t size)
+{
+ if (!objcg)
+ return;
+
+ if (chunk) {
+ chunk->obj_cgroups[off >> PCPU_MIN_ALLOC_SHIFT] = objcg;
+
+ rcu_read_lock();
+ mod_memcg_state(obj_cgroup_memcg(objcg), MEMCG_PERCPU_B,
+ size * num_possible_cpus());
+ rcu_read_unlock();
+ } else {
+ obj_cgroup_uncharge(objcg, size * num_possible_cpus());
+ obj_cgroup_put(objcg);
+ }
+}
+
+static void pcpu_memcg_free_hook(struct pcpu_chunk *chunk, int off, size_t size)
+{
+ struct obj_cgroup *objcg;
+
+ if (!pcpu_is_memcg_chunk(pcpu_chunk_type(chunk)))
+ return;
+
+ objcg = chunk->obj_cgroups[off >> PCPU_MIN_ALLOC_SHIFT];
+ chunk->obj_cgroups[off >> PCPU_MIN_ALLOC_SHIFT] = NULL;
+
+ obj_cgroup_uncharge(objcg, size * num_possible_cpus());
+
+ rcu_read_lock();
+ mod_memcg_state(obj_cgroup_memcg(objcg), MEMCG_PERCPU_B,
+ -(size * num_possible_cpus()));
+ rcu_read_unlock();
+
+ obj_cgroup_put(objcg);
+}
+
+#else /* CONFIG_MEMCG_KMEM */
+static enum pcpu_chunk_type
+pcpu_memcg_pre_alloc_hook(size_t size, gfp_t gfp, struct obj_cgroup **objcgp)
+{
+ return PCPU_CHUNK_ROOT;
+}
+
+static void pcpu_memcg_post_alloc_hook(struct obj_cgroup *objcg,
+ struct pcpu_chunk *chunk, int off,
+ size_t size)
+{
+}
+
+static void pcpu_memcg_free_hook(struct pcpu_chunk *chunk, int off, size_t size)
+{
+}
+#endif /* CONFIG_MEMCG_KMEM */
+
/**
* pcpu_alloc - the percpu allocator
* @size: size of area to allocate in bytes
@@ -1353,17 +1676,25 @@
static void __percpu *pcpu_alloc(size_t size, size_t align, bool reserved,
gfp_t gfp)
{
- /* whitelisted flags that can be passed to the backing allocators */
- gfp_t pcpu_gfp = gfp & (GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN);
- bool is_atomic = (gfp & GFP_KERNEL) != GFP_KERNEL;
- bool do_warn = !(gfp & __GFP_NOWARN);
+ gfp_t pcpu_gfp;
+ bool is_atomic;
+ bool do_warn;
+ enum pcpu_chunk_type type;
+ struct list_head *pcpu_slot;
+ struct obj_cgroup *objcg = NULL;
static int warn_limit = 10;
- struct pcpu_chunk *chunk;
+ struct pcpu_chunk *chunk, *next;
const char *err;
int slot, off, cpu, ret;
unsigned long flags;
void __percpu *ptr;
size_t bits, bit_align;
+
+ gfp = current_gfp_context(gfp);
+ /* whitelisted flags that can be passed to the backing allocators */
+ pcpu_gfp = gfp & (GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN);
+ is_atomic = (gfp & GFP_KERNEL) != GFP_KERNEL;
+ do_warn = !(gfp & __GFP_NOWARN);
/*
* There is now a minimum allocation size of PCPU_MIN_ALLOC_SIZE,
@@ -1385,16 +1716,23 @@
return NULL;
}
+ type = pcpu_memcg_pre_alloc_hook(size, gfp, &objcg);
+ if (unlikely(type == PCPU_FAIL_ALLOC))
+ return NULL;
+ pcpu_slot = pcpu_chunk_list(type);
+
if (!is_atomic) {
/*
* pcpu_balance_workfn() allocates memory under this mutex,
* and it may wait for memory reclaim. Allow current task
* to become OOM victim, in case of memory pressure.
*/
- if (gfp & __GFP_NOFAIL)
+ if (gfp & __GFP_NOFAIL) {
mutex_lock(&pcpu_alloc_mutex);
- else if (mutex_lock_killable(&pcpu_alloc_mutex))
+ } else if (mutex_lock_killable(&pcpu_alloc_mutex)) {
+ pcpu_memcg_post_alloc_hook(objcg, NULL, 0, size);
return NULL;
+ }
}
spin_lock_irqsave(&pcpu_lock, flags);
@@ -1420,11 +1758,14 @@
restart:
/* search through normal chunks */
for (slot = pcpu_size_to_slot(size); slot < pcpu_nr_slots; slot++) {
- list_for_each_entry(chunk, &pcpu_slot[slot], list) {
+ list_for_each_entry_safe(chunk, next, &pcpu_slot[slot], list) {
off = pcpu_find_block_fit(chunk, bits, bit_align,
is_atomic);
- if (off < 0)
+ if (off < 0) {
+ if (slot < PCPU_SLOT_FAIL_THRESHOLD)
+ pcpu_chunk_move(chunk, 0);
continue;
+ }
off = pcpu_alloc_area(chunk, bits, bit_align, off);
if (off >= 0)
@@ -1446,7 +1787,7 @@
}
if (list_empty(&pcpu_slot[pcpu_nr_slots - 1])) {
- chunk = pcpu_create_chunk(pcpu_gfp);
+ chunk = pcpu_create_chunk(type, pcpu_gfp);
if (!chunk) {
err = "failed to allocate new chunk";
goto fail;
@@ -1466,13 +1807,13 @@
/* populate if not all pages are already there */
if (!is_atomic) {
- int page_start, page_end, rs, re;
+ unsigned int page_start, page_end, rs, re;
page_start = PFN_DOWN(off);
page_end = PFN_UP(off + size);
- pcpu_for_each_unpop_region(chunk->populated, rs, re,
- page_start, page_end) {
+ bitmap_for_each_clear_region(chunk->populated, rs, re,
+ page_start, page_end) {
WARN_ON(chunk->immutable);
ret = pcpu_populate_chunk(chunk, rs, re, pcpu_gfp);
@@ -1483,14 +1824,14 @@
err = "failed to populate";
goto fail_unlock;
}
- pcpu_chunk_populated(chunk, rs, re, true);
+ pcpu_chunk_populated(chunk, rs, re);
spin_unlock_irqrestore(&pcpu_lock, flags);
}
mutex_unlock(&pcpu_alloc_mutex);
}
- if (pcpu_nr_empty_pop_pages < PCPU_EMPTY_POP_PAGES_LOW)
+ if (pcpu_nr_empty_pop_pages[type] < PCPU_EMPTY_POP_PAGES_LOW)
pcpu_schedule_balance_work();
/* clear the areas and return address relative to base address */
@@ -1502,6 +1843,8 @@
trace_percpu_alloc_percpu(reserved, is_atomic, size, align,
chunk->base_addr, off, ptr);
+
+ pcpu_memcg_post_alloc_hook(objcg, chunk, off, size);
return ptr;
@@ -1524,6 +1867,9 @@
} else {
mutex_unlock(&pcpu_alloc_mutex);
}
+
+ pcpu_memcg_post_alloc_hook(objcg, NULL, 0, size);
+
return NULL;
}
@@ -1583,8 +1929,8 @@
}
/**
- * pcpu_balance_workfn - manage the amount of free chunks and populated pages
- * @work: unused
+ * __pcpu_balance_workfn - manage the amount of free chunks and populated pages
+ * @type: chunk type
*
* Reclaim all fully free chunks except for the first one. This is also
* responsible for maintaining the pool of empty populated pages. However,
@@ -1593,11 +1939,12 @@
* allocation causes the failure as it is possible that requests can be
* serviced from already backed regions.
*/
-static void pcpu_balance_workfn(struct work_struct *work)
+static void __pcpu_balance_workfn(enum pcpu_chunk_type type)
{
/* gfp flags passed to underlying allocators */
const gfp_t gfp = GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN;
LIST_HEAD(to_free);
+ struct list_head *pcpu_slot = pcpu_chunk_list(type);
struct list_head *free_head = &pcpu_slot[pcpu_nr_slots - 1];
struct pcpu_chunk *chunk, *next;
int slot, nr_to_pop, ret;
@@ -1622,10 +1969,10 @@
spin_unlock_irq(&pcpu_lock);
list_for_each_entry_safe(chunk, next, &to_free, list) {
- int rs, re;
+ unsigned int rs, re;
- pcpu_for_each_pop_region(chunk->populated, rs, re, 0,
- chunk->nr_pages) {
+ bitmap_for_each_set_region(chunk->populated, rs, re, 0,
+ chunk->nr_pages) {
pcpu_depopulate_chunk(chunk, rs, re);
spin_lock_irq(&pcpu_lock);
pcpu_chunk_depopulated(chunk, rs, re);
@@ -1652,12 +1999,12 @@
pcpu_atomic_alloc_failed = false;
} else {
nr_to_pop = clamp(PCPU_EMPTY_POP_PAGES_HIGH -
- pcpu_nr_empty_pop_pages,
+ pcpu_nr_empty_pop_pages[type],
0, PCPU_EMPTY_POP_PAGES_HIGH);
}
for (slot = pcpu_size_to_slot(PAGE_SIZE); slot < pcpu_nr_slots; slot++) {
- int nr_unpop = 0, rs, re;
+ unsigned int nr_unpop = 0, rs, re;
if (!nr_to_pop)
break;
@@ -1674,15 +2021,15 @@
continue;
/* @chunk can't go away while pcpu_alloc_mutex is held */
- pcpu_for_each_unpop_region(chunk->populated, rs, re, 0,
- chunk->nr_pages) {
- int nr = min(re - rs, nr_to_pop);
+ bitmap_for_each_clear_region(chunk->populated, rs, re, 0,
+ chunk->nr_pages) {
+ int nr = min_t(int, re - rs, nr_to_pop);
ret = pcpu_populate_chunk(chunk, rs, rs + nr, gfp);
if (!ret) {
nr_to_pop -= nr;
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);
} else {
nr_to_pop = 0;
@@ -1695,7 +2042,7 @@
if (nr_to_pop) {
/* ran out of chunks to populate, create a new one and retry */
- chunk = pcpu_create_chunk(gfp);
+ chunk = pcpu_create_chunk(type, gfp);
if (chunk) {
spin_lock_irq(&pcpu_lock);
pcpu_chunk_relocate(chunk, -1);
@@ -1705,6 +2052,20 @@
}
mutex_unlock(&pcpu_alloc_mutex);
+}
+
+/**
+ * pcpu_balance_workfn - manage the amount of free chunks and populated pages
+ * @work: unused
+ *
+ * Call __pcpu_balance_workfn() for each chunk type.
+ */
+static void pcpu_balance_workfn(struct work_struct *work)
+{
+ enum pcpu_chunk_type type;
+
+ for (type = 0; type < PCPU_NR_CHUNK_TYPES; type++)
+ __pcpu_balance_workfn(type);
}
/**
@@ -1721,8 +2082,9 @@
void *addr;
struct pcpu_chunk *chunk;
unsigned long flags;
- int off;
+ int size, off;
bool need_balance = false;
+ struct list_head *pcpu_slot;
if (!ptr)
return;
@@ -1736,7 +2098,11 @@
chunk = pcpu_chunk_addr_search(addr);
off = addr - chunk->base_addr;
- pcpu_free_area(chunk, off);
+ size = pcpu_free_area(chunk, off);
+
+ pcpu_slot = pcpu_chunk_list(pcpu_chunk_type(chunk));
+
+ pcpu_memcg_free_hook(chunk, off, size);
/* if there are more than one fully free chunks, wake up grim reaper */
if (chunk->free_bytes == pcpu_unit_size) {
@@ -1890,11 +2256,11 @@
void *ptr;
int unit;
- base_size = ALIGN(sizeof(*ai) + nr_groups * sizeof(ai->groups[0]),
+ base_size = ALIGN(struct_size(ai, groups, nr_groups),
__alignof__(ai->groups[0].cpu_map[0]));
ai_size = base_size + nr_units * sizeof(ai->groups[0].cpu_map[0]);
- ptr = memblock_virt_alloc_nopanic(PFN_ALIGN(ai_size), PAGE_SIZE);
+ ptr = memblock_alloc(PFN_ALIGN(ai_size), PAGE_SIZE);
if (!ptr)
return NULL;
ai = ptr;
@@ -1985,7 +2351,7 @@
* @base_addr: mapped address
*
* Initialize the first percpu chunk which contains the kernel static
- * perpcu area. This function is to be called from arch percpu area
+ * percpu area. This function is to be called from arch percpu area
* setup path.
*
* @ai contains all information necessary to initialize the first
@@ -2032,12 +2398,9 @@
* share the same vm, but use offset regions in the area allocation map.
* The chunk serving the dynamic region is circulated in the chunk slots
* and available for dynamic allocation like any other chunk.
- *
- * RETURNS:
- * 0 on success, -errno on failure.
*/
-int __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai,
- void *base_addr)
+void __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai,
+ void *base_addr)
{
size_t size_sum = ai->static_size + ai->reserved_size + ai->dyn_size;
size_t static_size, dyn_size;
@@ -2050,6 +2413,8 @@
int group, unit, i;
int map_size;
unsigned long tmp_addr;
+ size_t alloc_size;
+ enum pcpu_chunk_type type;
#define PCPU_SETUP_BUG_ON(cond) do { \
if (unlikely(cond)) { \
@@ -2081,12 +2446,29 @@
PCPU_SETUP_BUG_ON(pcpu_verify_alloc_info(ai) < 0);
/* process group information and build config tables accordingly */
- group_offsets = memblock_virt_alloc(ai->nr_groups *
- sizeof(group_offsets[0]), 0);
- group_sizes = memblock_virt_alloc(ai->nr_groups *
- sizeof(group_sizes[0]), 0);
- unit_map = memblock_virt_alloc(nr_cpu_ids * sizeof(unit_map[0]), 0);
- unit_off = memblock_virt_alloc(nr_cpu_ids * sizeof(unit_off[0]), 0);
+ alloc_size = ai->nr_groups * sizeof(group_offsets[0]);
+ group_offsets = memblock_alloc(alloc_size, SMP_CACHE_BYTES);
+ if (!group_offsets)
+ panic("%s: Failed to allocate %zu bytes\n", __func__,
+ alloc_size);
+
+ alloc_size = ai->nr_groups * sizeof(group_sizes[0]);
+ group_sizes = memblock_alloc(alloc_size, SMP_CACHE_BYTES);
+ if (!group_sizes)
+ panic("%s: Failed to allocate %zu bytes\n", __func__,
+ alloc_size);
+
+ alloc_size = nr_cpu_ids * sizeof(unit_map[0]);
+ unit_map = memblock_alloc(alloc_size, SMP_CACHE_BYTES);
+ if (!unit_map)
+ panic("%s: Failed to allocate %zu bytes\n", __func__,
+ alloc_size);
+
+ alloc_size = nr_cpu_ids * sizeof(unit_off[0]);
+ unit_off = memblock_alloc(alloc_size, SMP_CACHE_BYTES);
+ if (!unit_off)
+ panic("%s: Failed to allocate %zu bytes\n", __func__,
+ alloc_size);
for (cpu = 0; cpu < nr_cpu_ids; cpu++)
unit_map[cpu] = UINT_MAX;
@@ -2140,8 +2522,8 @@
pcpu_unit_pages = ai->unit_size >> PAGE_SHIFT;
pcpu_unit_size = pcpu_unit_pages << PAGE_SHIFT;
pcpu_atom_size = ai->atom_size;
- pcpu_chunk_struct_size = sizeof(struct pcpu_chunk) +
- BITS_TO_LONGS(pcpu_unit_pages) * sizeof(unsigned long);
+ pcpu_chunk_struct_size = struct_size(chunk, populated,
+ BITS_TO_LONGS(pcpu_unit_pages));
pcpu_stats_save_ai(ai);
@@ -2150,10 +2532,18 @@
* empty chunks.
*/
pcpu_nr_slots = __pcpu_size_to_slot(pcpu_unit_size) + 2;
- pcpu_slot = memblock_virt_alloc(
- pcpu_nr_slots * sizeof(pcpu_slot[0]), 0);
- for (i = 0; i < pcpu_nr_slots; i++)
- INIT_LIST_HEAD(&pcpu_slot[i]);
+ pcpu_chunk_lists = memblock_alloc(pcpu_nr_slots *
+ sizeof(pcpu_chunk_lists[0]) *
+ PCPU_NR_CHUNK_TYPES,
+ SMP_CACHE_BYTES);
+ if (!pcpu_chunk_lists)
+ panic("%s: Failed to allocate %zu bytes\n", __func__,
+ pcpu_nr_slots * sizeof(pcpu_chunk_lists[0]) *
+ PCPU_NR_CHUNK_TYPES);
+
+ for (type = 0; type < PCPU_NR_CHUNK_TYPES; type++)
+ for (i = 0; i < pcpu_nr_slots; i++)
+ INIT_LIST_HEAD(&pcpu_chunk_list(type)[i]);
/*
* The end of the static region needs to be aligned with the
@@ -2190,7 +2580,7 @@
/* link the first chunk in */
pcpu_first_chunk = chunk;
- pcpu_nr_empty_pop_pages = pcpu_first_chunk->nr_empty_pop_pages;
+ pcpu_nr_empty_pop_pages[PCPU_CHUNK_ROOT] = pcpu_first_chunk->nr_empty_pop_pages;
pcpu_chunk_relocate(pcpu_first_chunk, -1);
/* include all regions of the first chunk */
@@ -2201,7 +2591,6 @@
/* we're done */
pcpu_base_addr = base_addr;
- return 0;
}
#ifdef CONFIG_SMP
@@ -2284,7 +2673,7 @@
const size_t static_size = __per_cpu_end - __per_cpu_start;
int nr_groups = 1, nr_units = 0;
size_t size_sum, min_unit_size, alloc_size;
- int upa, max_upa, uninitialized_var(best_upa); /* units_per_alloc */
+ int upa, max_upa, best_upa; /* units_per_alloc */
int last_allocs, group, unit;
unsigned int cpu, tcpu;
struct pcpu_alloc_info *ai;
@@ -2388,7 +2777,7 @@
ai->atom_size = atom_size;
ai->alloc_size = alloc_size;
- for (group = 0, unit = 0; group_cnt[group]; group++) {
+ for (group = 0, unit = 0; group < nr_groups; group++) {
struct pcpu_group_info *gi = &ai->groups[group];
/*
@@ -2454,7 +2843,7 @@
struct pcpu_alloc_info *ai;
size_t size_sum, areas_size;
unsigned long max_distance;
- int group, i, highest_group, rc;
+ int group, i, highest_group, rc = 0;
ai = pcpu_build_alloc_info(reserved_size, dyn_size, atom_size,
cpu_distance_fn);
@@ -2464,7 +2853,7 @@
size_sum = ai->static_size + ai->reserved_size + ai->dyn_size;
areas_size = PFN_ALIGN(ai->nr_groups * sizeof(void *));
- areas = memblock_virt_alloc_nopanic(areas_size, 0);
+ areas = memblock_alloc(areas_size, SMP_CACHE_BYTES);
if (!areas) {
rc = -ENOMEM;
goto out_free;
@@ -2539,7 +2928,7 @@
PFN_DOWN(size_sum), ai->static_size, ai->reserved_size,
ai->dyn_size, ai->unit_size);
- rc = pcpu_setup_first_chunk(ai, base);
+ pcpu_setup_first_chunk(ai, base);
goto out_free;
out_free_areas:
@@ -2583,7 +2972,7 @@
int unit_pages;
size_t pages_size;
struct page **pages;
- int unit, i, j, rc;
+ int unit, i, j, rc = 0;
int upa;
int nr_g0_units;
@@ -2595,7 +2984,7 @@
BUG_ON(ai->nr_groups != 1);
upa = ai->alloc_size/ai->unit_size;
nr_g0_units = roundup(num_possible_cpus(), upa);
- if (unlikely(WARN_ON(ai->groups[0].nr_units != nr_g0_units))) {
+ if (WARN_ON(ai->groups[0].nr_units != nr_g0_units)) {
pcpu_free_alloc_info(ai);
return -EINVAL;
}
@@ -2605,7 +2994,10 @@
/* unaligned allocations can't be freed, round up to page size */
pages_size = PFN_ALIGN(unit_pages * num_possible_cpus() *
sizeof(pages[0]));
- pages = memblock_virt_alloc(pages_size, 0);
+ pages = memblock_alloc(pages_size, SMP_CACHE_BYTES);
+ if (!pages)
+ panic("%s: Failed to allocate %zu bytes\n", __func__,
+ pages_size);
/* allocate pages */
j = 0;
@@ -2661,7 +3053,7 @@
unit_pages, psize_str, ai->static_size,
ai->reserved_size, ai->dyn_size);
- rc = pcpu_setup_first_chunk(ai, vm.addr);
+ pcpu_setup_first_chunk(ai, vm.addr);
goto out_free_ar;
enomem:
@@ -2694,8 +3086,7 @@
static void * __init pcpu_dfl_fc_alloc(unsigned int cpu, size_t size,
size_t align)
{
- return memblock_virt_alloc_from_nopanic(
- size, align, __pa(MAX_DMA_ADDRESS));
+ return memblock_alloc_from(size, align, __pa(MAX_DMA_ADDRESS));
}
static void __init pcpu_dfl_fc_free(void *ptr, size_t size)
@@ -2743,9 +3134,7 @@
void *fc;
ai = pcpu_alloc_alloc_info(1, 1);
- fc = memblock_virt_alloc_from_nopanic(unit_size,
- PAGE_SIZE,
- __pa(MAX_DMA_ADDRESS));
+ fc = memblock_alloc_from(unit_size, PAGE_SIZE, __pa(MAX_DMA_ADDRESS));
if (!ai || !fc)
panic("Failed to allocate memory for percpu areas.");
/* kmemleak tracks the percpu allocations separately */
@@ -2758,8 +3147,7 @@
ai->groups[0].nr_units = 1;
ai->groups[0].cpu_map[0] = 0;
- if (pcpu_setup_first_chunk(ai, fc) < 0)
- panic("Failed to initialize percpu areas.");
+ pcpu_setup_first_chunk(ai, fc);
pcpu_free_alloc_info(ai);
}
@@ -2780,6 +3168,7 @@
{
return pcpu_nr_populated * pcpu_nr_units;
}
+EXPORT_SYMBOL_GPL(pcpu_nr_pages);
/*
* Percpu allocator is initialized early during boot when neither slab or
--
Gitblit v1.6.2