mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-15 09:26:42 +07:00
ca279cf106
Premit use of another algorithm than the default first-fit one. For
example a custom algorithm could be used to manage alignment requirements.
As I can't predict all the possible requirements/needs for all allocation
uses cases, I add a "free" field 'void *data' to pass any needed
information to the allocation function. For example 'data' could be used
to handle a structure where you store the alignment, the expected memory
bank, the requester device, or any information that could influence the
allocation algorithm.
An usage example may look like this:
struct my_pool_constraints {
int align;
int bank;
...
};
unsigned long my_custom_algo(unsigned long *map, unsigned long size,
unsigned long start, unsigned int nr, void *data)
{
struct my_pool_constraints *constraints = data;
...
deal with allocation contraints
...
return the index in bitmap where perform the allocation
}
void create_my_pool()
{
struct my_pool_constraints c;
struct gen_pool *pool = gen_pool_create(...);
gen_pool_add(pool, ...);
gen_pool_set_algo(pool, my_custom_algo, &c);
}
Add of best-fit algorithm function:
most of the time best-fit is slower then first-fit but memory fragmentation
is lower. The random buffer allocation/free tests don't show any arithmetic
relation between the allocation time and fragmentation but the
best-fit algorithm
is sometime able to perform the allocation when the first-fit can't.
This new algorithm help to remove static allocations on ESRAM, a small but
fast on-chip RAM of few KB, used for high-performance uses cases like DMA
linked lists, graphic accelerators, encoders/decoders. On the Ux500
(in the ARM tree) we have define 5 ESRAM banks of 128 KB each and use of
static allocations becomes unmaintainable:
cd arch/arm/mach-ux500 && grep -r ESRAM .
./include/mach/db8500-regs.h:/* Base address and bank offsets for ESRAM */
./include/mach/db8500-regs.h:#define U8500_ESRAM_BASE 0x40000000
./include/mach/db8500-regs.h:#define U8500_ESRAM_BANK_SIZE 0x00020000
./include/mach/db8500-regs.h:#define U8500_ESRAM_BANK0 U8500_ESRAM_BASE
./include/mach/db8500-regs.h:#define U8500_ESRAM_BANK1 (U8500_ESRAM_BASE + U8500_ESRAM_BANK_SIZE)
./include/mach/db8500-regs.h:#define U8500_ESRAM_BANK2 (U8500_ESRAM_BANK1 + U8500_ESRAM_BANK_SIZE)
./include/mach/db8500-regs.h:#define U8500_ESRAM_BANK3 (U8500_ESRAM_BANK2 + U8500_ESRAM_BANK_SIZE)
./include/mach/db8500-regs.h:#define U8500_ESRAM_BANK4 (U8500_ESRAM_BANK3 + U8500_ESRAM_BANK_SIZE)
./include/mach/db8500-regs.h:#define U8500_ESRAM_DMA_LCPA_OFFSET 0x10000
./include/mach/db8500-regs.h:#define U8500_DMA_LCPA_BASE
(U8500_ESRAM_BANK0 + U8500_ESRAM_DMA_LCPA_OFFSET)
./include/mach/db8500-regs.h:#define U8500_DMA_LCLA_BASE U8500_ESRAM_BANK4
I want to use genalloc to do dynamic allocations but I need to be able to
fine tune the allocation algorithm. I my case best-fit algorithm give
better results than first-fit, but it will not be true for every use case.
Signed-off-by: Benjamin Gaignard <benjamin.gaignard@stericsson.com>
Cc: Huang Ying <ying.huang@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
109 lines
4.0 KiB
C
109 lines
4.0 KiB
C
/*
|
|
* Basic general purpose allocator for managing special purpose
|
|
* memory, for example, memory that is not managed by the regular
|
|
* kmalloc/kfree interface. Uses for this includes on-device special
|
|
* memory, uncached memory etc.
|
|
*
|
|
* It is safe to use the allocator in NMI handlers and other special
|
|
* unblockable contexts that could otherwise deadlock on locks. This
|
|
* is implemented by using atomic operations and retries on any
|
|
* conflicts. The disadvantage is that there may be livelocks in
|
|
* extreme cases. For better scalability, one allocator can be used
|
|
* for each CPU.
|
|
*
|
|
* The lockless operation only works if there is enough memory
|
|
* available. If new memory is added to the pool a lock has to be
|
|
* still taken. So any user relying on locklessness has to ensure
|
|
* that sufficient memory is preallocated.
|
|
*
|
|
* The basic atomic operation of this allocator is cmpxchg on long.
|
|
* On architectures that don't have NMI-safe cmpxchg implementation,
|
|
* the allocator can NOT be used in NMI handler. So code uses the
|
|
* allocator in NMI handler should depend on
|
|
* CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG.
|
|
*
|
|
* This source code is licensed under the GNU General Public License,
|
|
* Version 2. See the file COPYING for more details.
|
|
*/
|
|
|
|
|
|
#ifndef __GENALLOC_H__
|
|
#define __GENALLOC_H__
|
|
/**
|
|
* Allocation callback function type definition
|
|
* @map: Pointer to bitmap
|
|
* @size: The bitmap size in bits
|
|
* @start: The bitnumber to start searching at
|
|
* @nr: The number of zeroed bits we're looking for
|
|
* @data: optional additional data used by @genpool_algo_t
|
|
*/
|
|
typedef unsigned long (*genpool_algo_t)(unsigned long *map,
|
|
unsigned long size,
|
|
unsigned long start,
|
|
unsigned int nr,
|
|
void *data);
|
|
|
|
/*
|
|
* General purpose special memory pool descriptor.
|
|
*/
|
|
struct gen_pool {
|
|
spinlock_t lock;
|
|
struct list_head chunks; /* list of chunks in this pool */
|
|
int min_alloc_order; /* minimum allocation order */
|
|
|
|
genpool_algo_t algo; /* allocation function */
|
|
void *data;
|
|
};
|
|
|
|
/*
|
|
* General purpose special memory pool chunk descriptor.
|
|
*/
|
|
struct gen_pool_chunk {
|
|
struct list_head next_chunk; /* next chunk in pool */
|
|
atomic_t avail;
|
|
phys_addr_t phys_addr; /* physical starting address of memory chunk */
|
|
unsigned long start_addr; /* starting address of memory chunk */
|
|
unsigned long end_addr; /* ending address of memory chunk */
|
|
unsigned long bits[0]; /* bitmap for allocating memory chunk */
|
|
};
|
|
|
|
extern struct gen_pool *gen_pool_create(int, int);
|
|
extern phys_addr_t gen_pool_virt_to_phys(struct gen_pool *pool, unsigned long);
|
|
extern int gen_pool_add_virt(struct gen_pool *, unsigned long, phys_addr_t,
|
|
size_t, int);
|
|
/**
|
|
* gen_pool_add - add a new chunk of special memory to the pool
|
|
* @pool: pool to add new memory chunk to
|
|
* @addr: starting address of memory chunk to add to pool
|
|
* @size: size in bytes of the memory chunk to add to pool
|
|
* @nid: node id of the node the chunk structure and bitmap should be
|
|
* allocated on, or -1
|
|
*
|
|
* Add a new chunk of special memory to the specified pool.
|
|
*
|
|
* Returns 0 on success or a -ve errno on failure.
|
|
*/
|
|
static inline int gen_pool_add(struct gen_pool *pool, unsigned long addr,
|
|
size_t size, int nid)
|
|
{
|
|
return gen_pool_add_virt(pool, addr, -1, size, nid);
|
|
}
|
|
extern void gen_pool_destroy(struct gen_pool *);
|
|
extern unsigned long gen_pool_alloc(struct gen_pool *, size_t);
|
|
extern void gen_pool_free(struct gen_pool *, unsigned long, size_t);
|
|
extern void gen_pool_for_each_chunk(struct gen_pool *,
|
|
void (*)(struct gen_pool *, struct gen_pool_chunk *, void *), void *);
|
|
extern size_t gen_pool_avail(struct gen_pool *);
|
|
extern size_t gen_pool_size(struct gen_pool *);
|
|
|
|
extern void gen_pool_set_algo(struct gen_pool *pool, genpool_algo_t algo,
|
|
void *data);
|
|
|
|
extern unsigned long gen_pool_first_fit(unsigned long *map, unsigned long size,
|
|
unsigned long start, unsigned int nr, void *data);
|
|
|
|
extern unsigned long gen_pool_best_fit(unsigned long *map, unsigned long size,
|
|
unsigned long start, unsigned int nr, void *data);
|
|
|
|
#endif /* __GENALLOC_H__ */
|