3c7be18ac9
Percpu memory is becoming more and more widely used by various subsystems, and the total amount of memory controlled by the percpu allocator can make a good part of the total memory. As an example, bpf maps can consume a lot of percpu memory, and they are created by a user. Also, some cgroup internals (e.g. memory controller statistics) can be quite large. On a machine with many CPUs and big number of cgroups they can consume hundreds of megabytes. So the lack of memcg accounting is creating a breach in the memory isolation. Similar to the slab memory, percpu memory should be accounted by default. To implement the perpcu accounting it's possible to take the slab memory accounting as a model to follow. Let's introduce two types of percpu chunks: root and memcg. What makes memcg chunks different is an additional space allocated to store memcg membership information. If __GFP_ACCOUNT is passed on allocation, a memcg chunk should be be used. If it's possible to charge the corresponding size to the target memory cgroup, allocation is performed, and the memcg ownership data is recorded. System-wide allocations are performed using root chunks, so there is no additional memory overhead. To implement a fast reparenting of percpu memory on memcg removal, we don't store mem_cgroup pointers directly: instead we use obj_cgroup API, introduced for slab accounting. [akpm@linux-foundation.org: fix CONFIG_MEMCG_KMEM=n build errors and warning] [akpm@linux-foundation.org: move unreachable code, per Roman] [cuibixuan@huawei.com: mm/percpu: fix 'defined but not used' warning] Link: http://lkml.kernel.org/r/6d41b939-a741-b521-a7a2-e7296ec16219@huawei.com Signed-off-by: Roman Gushchin <guro@fb.com> Signed-off-by: Bixuan Cui <cuibixuan@huawei.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Shakeel Butt <shakeelb@google.com> Acked-by: Dennis Zhou <dennis@kernel.org> Cc: Christoph Lameter <cl@linux.com> Cc: David Rientjes <rientjes@google.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Mel Gorman <mgorman@techsingularity.net> Cc: Michal Hocko <mhocko@kernel.org> Cc: Pekka Enberg <penberg@kernel.org> Cc: Tejun Heo <tj@kernel.org> Cc: Tobin C. Harding <tobin@kernel.org> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Waiman Long <longman@redhat.com> Cc: Bixuan Cui <cuibixuan@huawei.com> Cc: Michal Koutný <mkoutny@suse.com> Cc: Stephen Rothwell <sfr@canb.auug.org.au> Link: http://lkml.kernel.org/r/20200623184515.4132564-3-guro@fb.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
286 lines
7.7 KiB
C
286 lines
7.7 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>
|
|
|
|
/*
|
|
* There are two chunk types: root and memcg-aware.
|
|
* Chunks of each type have separate slots list.
|
|
*
|
|
* Memcg-aware chunks have an attached vector of obj_cgroup pointers, which is
|
|
* used to store memcg membership data of a percpu object. Obj_cgroups are
|
|
* ref-counted pointers to a memory cgroup with an ability to switch dynamically
|
|
* to the parent memory cgroup. This allows to reclaim a deleted memory cgroup
|
|
* without reclaiming of all outstanding objects, which hold a reference at it.
|
|
*/
|
|
enum pcpu_chunk_type {
|
|
PCPU_CHUNK_ROOT,
|
|
#ifdef CONFIG_MEMCG_KMEM
|
|
PCPU_CHUNK_MEMCG,
|
|
#endif
|
|
PCPU_NR_CHUNK_TYPES,
|
|
PCPU_FAIL_ALLOC = PCPU_NR_CHUNK_TYPES
|
|
};
|
|
|
|
/*
|
|
* 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 */
|
|
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_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_MEMCG_KMEM
|
|
static inline enum pcpu_chunk_type pcpu_chunk_type(struct pcpu_chunk *chunk)
|
|
{
|
|
if (chunk->obj_cgroups)
|
|
return PCPU_CHUNK_MEMCG;
|
|
return PCPU_CHUNK_ROOT;
|
|
}
|
|
|
|
static inline bool pcpu_is_memcg_chunk(enum pcpu_chunk_type chunk_type)
|
|
{
|
|
return chunk_type == PCPU_CHUNK_MEMCG;
|
|
}
|
|
|
|
#else
|
|
static inline enum pcpu_chunk_type pcpu_chunk_type(struct pcpu_chunk *chunk)
|
|
{
|
|
return PCPU_CHUNK_ROOT;
|
|
}
|
|
|
|
static inline bool pcpu_is_memcg_chunk(enum pcpu_chunk_type chunk_type)
|
|
{
|
|
return false;
|
|
}
|
|
#endif
|
|
|
|
static inline struct list_head *pcpu_chunk_list(enum pcpu_chunk_type chunk_type)
|
|
{
|
|
return &pcpu_chunk_lists[pcpu_nr_slots *
|
|
pcpu_is_memcg_chunk(chunk_type)];
|
|
}
|
|
|
|
#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
|