linux/mm/percpu-internal.h
Dennis Zhou (Facebook) c0ebfdc3fe percpu: modify base_addr to be region specific
Originally, the first chunk was served by one or two chunks, each
given a region they are responsible for. Despite this, the arithmetic
was based off of the true base_addr of the chunk making it be overly
inclusive.

This patch moves the base_addr of chunks that are responsible for the
first chunk. The base_addr must remain page aligned to keep the
address alignment correct, so it is the beginning of the region served
page aligned down. start_offset holds where the region served begins
from this new base_addr.

The corresponding percpu address checks are modified to be more specific
as a result. The first chunk considers only the dynamic region and both
first chunk and reserved chunk checks ignore the static region. The
static region addresses should never be passed into the allocator. There
is no impact here besides distinguishing the first chunk and making the
checks specific.

The percpu pointer to physical address is left intact as addresses are
not given out in the non-allocated portion of percpu memory.

nr_pages is added to pcpu_chunk to keep track of the size of the entire
region served containing both start_offset and end_offset. This variable
will be used to manage the bitmap allocator.

Signed-off-by: Dennis Zhou <dennisszhou@gmail.com>
Reviewed-by: Josef Bacik <jbacik@fb.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
2017-07-26 10:23:52 -04:00

171 lines
4.2 KiB
C

#ifndef _MM_PERCPU_INTERNAL_H
#define _MM_PERCPU_INTERNAL_H
#include <linux/types.h>
#include <linux/percpu.h>
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_size; /* free bytes in the chunk */
int contig_hint; /* max contiguous size hint */
void *base_addr; /* base address of this chunk */
int map_used; /* # of map entries used before the sentry */
int map_alloc; /* # of map entries allocated */
int *map; /* allocation map */
struct list_head map_extend_list;/* on pcpu_map_extend_chunks */
void *data; /* chunk data */
int first_free; /* no free below this */
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 */
int nr_pages; /* # of pages served by this chunk */
int nr_populated; /* # of populated pages */
unsigned long populated[]; /* populated bitmap */
};
extern spinlock_t pcpu_lock;
extern struct list_head *pcpu_slot;
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;
#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