mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-22 22:39:20 +07:00
b185cd0dc6
The bitmap allocator must keep metadata consistent. The easiest way is to scan after every allocation for each affected block and the entire chunk. This is rather expensive. The free path can take advantage of current contig hints to prevent scanning within the start and end block. If a scan is needed, it can be done by scanning backwards from the start and forwards from the end to identify the entire free area this can be combined with. The blocks can then be updated by some basic checks rather than complete block scans. A chunk scan happens when the freed area makes a page free, a block free, or spans across blocks. This is necessary as the contig hint at this point could span across blocks. The check uses the minimum of page size and the block size to allow for variable sized blocks. There is a tradeoff here with not updating after every free. It is possible a contig hint in one block can be merged with the contig hint in the next block. This means the contig hint can be off by up to a page. However, if the chunk's contig hint is contained in one block, the contig hint will be accurate. Signed-off-by: Dennis Zhou <dennisszhou@gmail.com> Reviewed-by: Josef Bacik <jbacik@fb.com> Signed-off-by: Tejun Heo <tj@kernel.org>
152 lines
5.0 KiB
C
152 lines
5.0 KiB
C
#ifndef __LINUX_PERCPU_H
|
|
#define __LINUX_PERCPU_H
|
|
|
|
#include <linux/mmdebug.h>
|
|
#include <linux/preempt.h>
|
|
#include <linux/smp.h>
|
|
#include <linux/cpumask.h>
|
|
#include <linux/printk.h>
|
|
#include <linux/pfn.h>
|
|
#include <linux/init.h>
|
|
|
|
#include <asm/percpu.h>
|
|
|
|
/* enough to cover all DEFINE_PER_CPUs in modules */
|
|
#ifdef CONFIG_MODULES
|
|
#define PERCPU_MODULE_RESERVE (8 << 10)
|
|
#else
|
|
#define PERCPU_MODULE_RESERVE 0
|
|
#endif
|
|
|
|
/* minimum unit size, also is the maximum supported allocation size */
|
|
#define PCPU_MIN_UNIT_SIZE PFN_ALIGN(32 << 10)
|
|
|
|
/* minimum allocation size and shift in bytes */
|
|
#define PCPU_MIN_ALLOC_SHIFT 2
|
|
#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
|
|
* constraints around this constant. The reserved region must be a multiple of
|
|
* PCPU_BITMAP_BLOCK_SIZE. Additionally, PCPU_BITMAP_BLOCK_SIZE must be a
|
|
* 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_BITS (PCPU_BITMAP_BLOCK_SIZE >> \
|
|
PCPU_MIN_ALLOC_SHIFT)
|
|
|
|
/*
|
|
* Percpu allocator can serve percpu allocations before slab is
|
|
* initialized which allows slab to depend on the percpu allocator.
|
|
* The following two parameters decide how much resource to
|
|
* preallocate for this. Keep PERCPU_DYNAMIC_RESERVE equal to or
|
|
* larger than PERCPU_DYNAMIC_EARLY_SIZE.
|
|
*/
|
|
#define PERCPU_DYNAMIC_EARLY_SLOTS 128
|
|
#define PERCPU_DYNAMIC_EARLY_SIZE (12 << 10)
|
|
|
|
/*
|
|
* PERCPU_DYNAMIC_RESERVE indicates the amount of free area to piggy
|
|
* back on the first chunk for dynamic percpu allocation if arch is
|
|
* manually allocating and mapping it for faster access (as a part of
|
|
* large page mapping for example).
|
|
*
|
|
* The following values give between one and two pages of free space
|
|
* after typical minimal boot (2-way SMP, single disk and NIC) with
|
|
* both defconfig and a distro config on x86_64 and 32. More
|
|
* intelligent way to determine this would be nice.
|
|
*/
|
|
#if BITS_PER_LONG > 32
|
|
#define PERCPU_DYNAMIC_RESERVE (28 << 10)
|
|
#else
|
|
#define PERCPU_DYNAMIC_RESERVE (20 << 10)
|
|
#endif
|
|
|
|
extern void *pcpu_base_addr;
|
|
extern const unsigned long *pcpu_unit_offsets;
|
|
|
|
struct pcpu_group_info {
|
|
int nr_units; /* aligned # of units */
|
|
unsigned long base_offset; /* base address offset */
|
|
unsigned int *cpu_map; /* unit->cpu map, empty
|
|
* entries contain NR_CPUS */
|
|
};
|
|
|
|
struct pcpu_alloc_info {
|
|
size_t static_size;
|
|
size_t reserved_size;
|
|
size_t dyn_size;
|
|
size_t unit_size;
|
|
size_t atom_size;
|
|
size_t alloc_size;
|
|
size_t __ai_size; /* internal, don't use */
|
|
int nr_groups; /* 0 if grouping unnecessary */
|
|
struct pcpu_group_info groups[];
|
|
};
|
|
|
|
enum pcpu_fc {
|
|
PCPU_FC_AUTO,
|
|
PCPU_FC_EMBED,
|
|
PCPU_FC_PAGE,
|
|
|
|
PCPU_FC_NR,
|
|
};
|
|
extern const char * const pcpu_fc_names[PCPU_FC_NR];
|
|
|
|
extern enum pcpu_fc pcpu_chosen_fc;
|
|
|
|
typedef void * (*pcpu_fc_alloc_fn_t)(unsigned int cpu, size_t size,
|
|
size_t align);
|
|
typedef void (*pcpu_fc_free_fn_t)(void *ptr, size_t size);
|
|
typedef void (*pcpu_fc_populate_pte_fn_t)(unsigned long addr);
|
|
typedef int (pcpu_fc_cpu_distance_fn_t)(unsigned int from, unsigned int to);
|
|
|
|
extern struct pcpu_alloc_info * __init pcpu_alloc_alloc_info(int nr_groups,
|
|
int nr_units);
|
|
extern void __init pcpu_free_alloc_info(struct pcpu_alloc_info *ai);
|
|
|
|
extern int __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai,
|
|
void *base_addr);
|
|
|
|
#ifdef CONFIG_NEED_PER_CPU_EMBED_FIRST_CHUNK
|
|
extern int __init pcpu_embed_first_chunk(size_t reserved_size, size_t dyn_size,
|
|
size_t atom_size,
|
|
pcpu_fc_cpu_distance_fn_t cpu_distance_fn,
|
|
pcpu_fc_alloc_fn_t alloc_fn,
|
|
pcpu_fc_free_fn_t free_fn);
|
|
#endif
|
|
|
|
#ifdef CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK
|
|
extern int __init pcpu_page_first_chunk(size_t reserved_size,
|
|
pcpu_fc_alloc_fn_t alloc_fn,
|
|
pcpu_fc_free_fn_t free_fn,
|
|
pcpu_fc_populate_pte_fn_t populate_pte_fn);
|
|
#endif
|
|
|
|
extern void __percpu *__alloc_reserved_percpu(size_t size, size_t align);
|
|
extern bool __is_kernel_percpu_address(unsigned long addr, unsigned long *can_addr);
|
|
extern bool is_kernel_percpu_address(unsigned long addr);
|
|
|
|
#if !defined(CONFIG_SMP) || !defined(CONFIG_HAVE_SETUP_PER_CPU_AREA)
|
|
extern void __init setup_per_cpu_areas(void);
|
|
#endif
|
|
|
|
extern void __percpu *__alloc_percpu_gfp(size_t size, size_t align, gfp_t gfp);
|
|
extern void __percpu *__alloc_percpu(size_t size, size_t align);
|
|
extern void free_percpu(void __percpu *__pdata);
|
|
extern phys_addr_t per_cpu_ptr_to_phys(void *addr);
|
|
|
|
#define alloc_percpu_gfp(type, gfp) \
|
|
(typeof(type) __percpu *)__alloc_percpu_gfp(sizeof(type), \
|
|
__alignof__(type), gfp)
|
|
#define alloc_percpu(type) \
|
|
(typeof(type) __percpu *)__alloc_percpu(sizeof(type), \
|
|
__alignof__(type))
|
|
|
|
#endif /* __LINUX_PERCPU_H */
|