diff options
author | Benjamin Gaignard <benjamin.gaignard@linaro.org> | 2012-10-05 04:13:20 +0400 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2012-10-05 22:04:57 +0400 |
commit | ca279cf1065fb689abea1dc7d8c11787729bb185 (patch) | |
tree | fdde907d1c3198f81c9085f858ac64c7a3cc50d8 /lib/genalloc.c | |
parent | e96875677fb2b7cb739c5d7769824dff7260d31d (diff) | |
download | linux-ca279cf1065fb689abea1dc7d8c11787729bb185.tar.xz |
genalloc: make it possible to use a custom allocation algorithm
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>
Diffstat (limited to 'lib/genalloc.c')
-rw-r--r-- | lib/genalloc.c | 88 |
1 files changed, 84 insertions, 4 deletions
diff --git a/lib/genalloc.c b/lib/genalloc.c index 6bc04aab6ec7..ca208a92628c 100644 --- a/lib/genalloc.c +++ b/lib/genalloc.c @@ -152,6 +152,8 @@ struct gen_pool *gen_pool_create(int min_alloc_order, int nid) spin_lock_init(&pool->lock); INIT_LIST_HEAD(&pool->chunks); pool->min_alloc_order = min_alloc_order; + pool->algo = gen_pool_first_fit; + pool->data = NULL; } return pool; } @@ -255,8 +257,9 @@ EXPORT_SYMBOL(gen_pool_destroy); * @size: number of bytes to allocate from the pool * * Allocate the requested number of bytes from the specified pool. - * Uses a first-fit algorithm. Can not be used in NMI handler on - * architectures without NMI-safe cmpxchg implementation. + * Uses the pool allocation function (with first-fit algorithm by default). + * Can not be used in NMI handler on architectures without + * NMI-safe cmpxchg implementation. */ unsigned long gen_pool_alloc(struct gen_pool *pool, size_t size) { @@ -280,8 +283,8 @@ unsigned long gen_pool_alloc(struct gen_pool *pool, size_t size) end_bit = (chunk->end_addr - chunk->start_addr) >> order; retry: - start_bit = bitmap_find_next_zero_area(chunk->bits, end_bit, - start_bit, nbits, 0); + start_bit = pool->algo(chunk->bits, end_bit, start_bit, nbits, + pool->data); if (start_bit >= end_bit) continue; remain = bitmap_set_ll(chunk->bits, start_bit, nbits); @@ -400,3 +403,80 @@ size_t gen_pool_size(struct gen_pool *pool) return size; } EXPORT_SYMBOL_GPL(gen_pool_size); + +/** + * gen_pool_set_algo - set the allocation algorithm + * @pool: pool to change allocation algorithm + * @algo: custom algorithm function + * @data: additional data used by @algo + * + * Call @algo for each memory allocation in the pool. + * If @algo is NULL use gen_pool_first_fit as default + * memory allocation function. + */ +void gen_pool_set_algo(struct gen_pool *pool, genpool_algo_t algo, void *data) +{ + rcu_read_lock(); + + pool->algo = algo; + if (!pool->algo) + pool->algo = gen_pool_first_fit; + + pool->data = data; + + rcu_read_unlock(); +} +EXPORT_SYMBOL(gen_pool_set_algo); + +/** + * gen_pool_first_fit - find the first available region + * of memory matching the size requirement (no alignment constraint) + * @map: The address to base the search on + * @size: The bitmap size in bits + * @start: The bitnumber to start searching at + * @nr: The number of zeroed bits we're looking for + * @data: additional data - unused + */ +unsigned long gen_pool_first_fit(unsigned long *map, unsigned long size, + unsigned long start, unsigned int nr, void *data) +{ + return bitmap_find_next_zero_area(map, size, start, nr, 0); +} +EXPORT_SYMBOL(gen_pool_first_fit); + +/** + * gen_pool_best_fit - find the best fitting region of memory + * macthing the size requirement (no alignment constraint) + * @map: The address to base the search on + * @size: The bitmap size in bits + * @start: The bitnumber to start searching at + * @nr: The number of zeroed bits we're looking for + * @data: additional data - unused + * + * Iterate over the bitmap to find the smallest free region + * which we can allocate the memory. + */ +unsigned long gen_pool_best_fit(unsigned long *map, unsigned long size, + unsigned long start, unsigned int nr, void *data) +{ + unsigned long start_bit = size; + unsigned long len = size + 1; + unsigned long index; + + index = bitmap_find_next_zero_area(map, size, start, nr, 0); + + while (index < size) { + int next_bit = find_next_bit(map, size, index + nr); + if ((next_bit - index) < len) { + len = next_bit - index; + start_bit = index; + if (len == nr) + return start_bit; + } + index = bitmap_find_next_zero_area(map, size, + next_bit + 1, nr, 0); + } + + return start_bit; +} +EXPORT_SYMBOL(gen_pool_best_fit); |