Files
linux_media/mm/percpu-internal.h
Roman Gushchin faf65dde84 percpu: rework memcg accounting
The current implementation of the memcg accounting of the percpu
memory is based on the idea of having two separate sets of chunks for
accounted and non-accounted memory. This approach has an advantage
of not wasting any extra memory for memcg data for non-accounted
chunks, however it complicates the code and leads to a higher chunks
number due to a lower chunk utilization.

Instead of having two chunk types it's possible to declare all* chunks
memcg-aware unless the kernel memory accounting is disabled globally
by a boot option. The size of objcg_array is usually small in
comparison to chunks themselves (it obviously depends on the number of
CPUs), so even if some chunk will have no accounted allocations, the
memory waste isn't significant and will likely be compensated by
a higher chunk utilization. Also, with time more and more percpu
allocations will likely become accounted.

* The first chunk is initialized before the memory cgroup subsystem,
  so we don't know for sure whether we need to allocate obj_cgroups.
  Because it's small, let's make it free for use. Then we don't need
  to allocate obj_cgroups for it.

Signed-off-by: Roman Gushchin <guro@fb.com>
Signed-off-by: Dennis Zhou <dennis@kernel.org>
2021-06-05 20:43:15 +00:00

240 lines
6.6 KiB
C

/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _MM_PERCPU_INTERNAL_H
#define _MM_PERCPU_INTERNAL_H
#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.
*
* The scan hint is the largest known contiguous area before the contig hint.
* It is not necessarily the actual largest contig hint though. There is an
* invariant that the scan_hint_start > contig_hint_start iff
* scan_hint == contig_hint. This is necessary because when scanning forward,
* we don't know if a new contig hint would be better than the current one.
*/
struct pcpu_block_md {
int scan_hint; /* scan hint for block */
int scan_hint_start; /* block relative starting
position of the scan hint */
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 */
int nr_bits; /* total bits responsible for */
};
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_bytes; /* free bytes in the chunk */
struct pcpu_block_md chunk_md;
void *base_addr; /* base address of this 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 */
bool immutable; /* no [de]population allowed */
bool isolated; /* isolated from active chunk
slots */
int start_offset; /* the overlap with the previous
region to have a page aligned
base_addr */
int end_offset; /* additional area required to
have the region end page
aligned */
#ifdef CONFIG_MEMCG_KMEM
struct obj_cgroup **obj_cgroups; /* vector of object cgroups */
#endif
int nr_pages; /* # of pages served by this chunk */
int nr_populated; /* # of populated pages */
int nr_empty_pop_pages; /* # of empty populated pages */
unsigned long populated[]; /* populated bitmap */
};
extern spinlock_t pcpu_lock;
extern struct list_head *pcpu_chunk_lists;
extern int pcpu_nr_slots;
extern int pcpu_sidelined_slot;
extern int pcpu_to_depopulate_slot;
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
*
* This conversion is from physical pages to the number of bits
* required in the bitmap.
*/
static inline int pcpu_nr_pages_to_map_bits(int pages)
{
return pages * PAGE_SIZE / PCPU_MIN_ALLOC_SIZE;
}
/**
* pcpu_chunk_map_bits - helper to convert nr_pages to size of bitmap
* @chunk: chunk of interest
*
* This conversion is from the number of physical pages that the chunk
* serves to the number of bits in the bitmap.
*/
static inline int pcpu_chunk_map_bits(struct pcpu_chunk *chunk)
{
return pcpu_nr_pages_to_map_bits(chunk->nr_pages);
}
#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)
{
unsigned long flags;
spin_lock_irqsave(&pcpu_lock, flags);
pcpu_stats.nr_chunks++;
pcpu_stats.nr_max_chunks =
max(pcpu_stats.nr_max_chunks, pcpu_stats.nr_chunks);
spin_unlock_irqrestore(&pcpu_lock, flags);
}
/*
* pcpu_stats_chunk_dealloc - decrement chunk stats
*/
static inline void pcpu_stats_chunk_dealloc(void)
{
unsigned long flags;
spin_lock_irqsave(&pcpu_lock, flags);
pcpu_stats.nr_chunks--;
spin_unlock_irqrestore(&pcpu_lock, flags);
}
#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