The per cpu allocator allows dynamic allocation of memory on all processors simultaneously. A bitmap is used to track used areas. The allocator implements tight packing to reduce the cache footprint and increase speed since cacheline contention is typically not a concern for memory mainly used by a single cpu. Small objects will fill up gaps left by larger allocations that required alignments. The size of the cpu_alloc area can be changed via make menuconfig. Signed-off-by: Christoph Lameter --- include/linux/percpu.h | 46 +++++++++++++ include/linux/vmstat.h | 2 mm/Kconfig | 6 + mm/Makefile | 2 mm/cpu_alloc.c | 167 +++++++++++++++++++++++++++++++++++++++++++++++++ mm/vmstat.c | 1 6 files changed, 222 insertions(+), 2 deletions(-) Index: linux-2.6/include/linux/vmstat.h =================================================================== --- linux-2.6.orig/include/linux/vmstat.h 2008-05-29 19:41:21.000000000 -0700 +++ linux-2.6/include/linux/vmstat.h 2008-05-29 20:15:37.000000000 -0700 @@ -37,7 +37,7 @@ enum vm_event_item { PGPGIN, PGPGOUT, PS FOR_ALL_ZONES(PGSCAN_KSWAPD), FOR_ALL_ZONES(PGSCAN_DIRECT), PGINODESTEAL, SLABS_SCANNED, KSWAPD_STEAL, KSWAPD_INODESTEAL, - PAGEOUTRUN, ALLOCSTALL, PGROTATED, + PAGEOUTRUN, ALLOCSTALL, PGROTATED, CPU_BYTES, #ifdef CONFIG_HUGETLB_PAGE HTLB_BUDDY_PGALLOC, HTLB_BUDDY_PGALLOC_FAIL, #endif Index: linux-2.6/mm/Kconfig =================================================================== --- linux-2.6.orig/mm/Kconfig 2008-05-29 19:41:21.000000000 -0700 +++ linux-2.6/mm/Kconfig 2008-05-29 20:13:39.000000000 -0700 @@ -205,3 +205,9 @@ config NR_QUICK config VIRT_TO_BUS def_bool y depends on !ARCH_NO_VIRT_TO_BUS + +config CPU_ALLOC_SIZE + int "Size of cpu alloc area" + default "30000" + help + Sets the maximum amount of memory that can be allocated via cpu_alloc Index: linux-2.6/mm/Makefile =================================================================== --- linux-2.6.orig/mm/Makefile 2008-05-29 19:41:21.000000000 -0700 +++ linux-2.6/mm/Makefile 2008-05-29 20:15:41.000000000 -0700 @@ -11,7 +11,7 @@ obj-y := bootmem.o filemap.o mempool.o maccess.o page_alloc.o page-writeback.o pdflush.o \ readahead.o swap.o truncate.o vmscan.o \ prio_tree.o util.o mmzone.o vmstat.o backing-dev.o \ - page_isolation.o $(mmu-y) + page_isolation.o cpu_alloc.o $(mmu-y) obj-$(CONFIG_PROC_PAGE_MONITOR) += pagewalk.o obj-$(CONFIG_BOUNCE) += bounce.o Index: linux-2.6/mm/cpu_alloc.c =================================================================== --- /dev/null 1970-01-01 00:00:00.000000000 +0000 +++ linux-2.6/mm/cpu_alloc.c 2008-05-29 20:13:39.000000000 -0700 @@ -0,0 +1,167 @@ +/* + * Cpu allocator - Manage objects allocated for each processor + * + * (C) 2008 SGI, Christoph Lameter + * Basic implementation with allocation and free from a dedicated per + * cpu area. + * + * The per cpu allocator allows dynamic allocation of memory on all + * processor simultaneously. A bitmap is used to track used areas. + * The allocator implements tight packing to reduce the cache footprint + * and increase speed since cacheline contention is typically not a concern + * for memory mainly used by a single cpu. Small objects will fill up gaps + * left by larger allocations that required alignments. + */ +#include +#include +#include +#include +#include +#include + +/* + * Basic allocation unit. A bit map is created to track the use of each + * UNIT_SIZE element in the cpu area. + */ +#define UNIT_TYPE int +#define UNIT_SIZE sizeof(UNIT_TYPE) +#define UNITS (CONFIG_CPU_ALLOC_SIZE / UNIT_SIZE) + +static DEFINE_PER_CPU(UNIT_TYPE, area[UNITS]); + +/* + * How many units are needed for an object of a given size + */ +static int size_to_units(unsigned long size) +{ + return DIV_ROUND_UP(size, UNIT_SIZE); +} + +/* + * Lock to protect the bitmap and the meta data for the cpu allocator. + */ +static DEFINE_SPINLOCK(cpu_alloc_map_lock); +static DECLARE_BITMAP(cpu_alloc_map, UNITS); +static int first_free; /* First known free unit */ + +/* + * Mark an object as used in the cpu_alloc_map + * + * Must hold cpu_alloc_map_lock + */ +static void set_map(int start, int length) +{ + while (length-- > 0) + __set_bit(start++, cpu_alloc_map); +} + +/* + * Mark an area as freed. + * + * Must hold cpu_alloc_map_lock + */ +static void clear_map(int start, int length) +{ + while (length-- > 0) + __clear_bit(start++, cpu_alloc_map); +} + +/* + * Allocate an object of a certain size + * + * Returns a special pointer that can be used with CPU_PTR to find the + * address of the object for a certain cpu. + */ +void *cpu_alloc(unsigned long size, gfp_t gfpflags, unsigned long align) +{ + unsigned long start; + int units = size_to_units(size); + void *ptr; + int first; + unsigned long flags; + + if (!size) + return ZERO_SIZE_PTR; + + spin_lock_irqsave(&cpu_alloc_map_lock, flags); + + first = 1; + start = first_free; + + for ( ; ; ) { + + start = find_next_zero_bit(cpu_alloc_map, UNITS, start); + if (start >= UNITS) + goto out_of_memory; + + if (first) + first_free = start; + + /* + * Check alignment and that there is enough space after + * the starting unit. + */ + if (start % (align / UNIT_SIZE) == 0 && + find_next_bit(cpu_alloc_map, UNITS, start + 1) + >= start + units) + break; + start++; + first = 0; + } + + if (first) + first_free = start + units; + + if (start + units > UNITS) + goto out_of_memory; + + set_map(start, units); + __count_vm_events(CPU_BYTES, units * UNIT_SIZE); + + spin_unlock_irqrestore(&cpu_alloc_map_lock, flags); + + ptr = per_cpu_var(area) + start; + + if (gfpflags & __GFP_ZERO) { + int cpu; + + for_each_possible_cpu(cpu) + memset(CPU_PTR(ptr, cpu), 0, size); + } + + return ptr; + +out_of_memory: + spin_unlock_irqrestore(&cpu_alloc_map_lock, flags); + return NULL; +} +EXPORT_SYMBOL(cpu_alloc); + +/* + * Free an object. The pointer must be a cpu pointer allocated + * via cpu_alloc. + */ +void cpu_free(void *start, unsigned long size) +{ + unsigned long units = size_to_units(size); + unsigned long index = (int *)start - per_cpu_var(area); + unsigned long flags; + + if (!start || start == ZERO_SIZE_PTR) + return; + + BUG_ON(index >= UNITS || + !test_bit(index, cpu_alloc_map) || + !test_bit(index + units - 1, cpu_alloc_map)); + + spin_lock_irqsave(&cpu_alloc_map_lock, flags); + + clear_map(index, units); + __count_vm_events(CPU_BYTES, -units * UNIT_SIZE); + + if (index < first_free) + first_free = index; + + spin_unlock_irqrestore(&cpu_alloc_map_lock, flags); +} +EXPORT_SYMBOL(cpu_free); Index: linux-2.6/mm/vmstat.c =================================================================== --- linux-2.6.orig/mm/vmstat.c 2008-05-29 19:41:21.000000000 -0700 +++ linux-2.6/mm/vmstat.c 2008-05-29 20:13:39.000000000 -0700 @@ -653,6 +653,7 @@ static const char * const vmstat_text[] "allocstall", "pgrotated", + "cpu_bytes", #ifdef CONFIG_HUGETLB_PAGE "htlb_buddy_alloc_success", "htlb_buddy_alloc_fail", Index: linux-2.6/include/linux/percpu.h =================================================================== --- linux-2.6.orig/include/linux/percpu.h 2008-05-29 19:41:21.000000000 -0700 +++ linux-2.6/include/linux/percpu.h 2008-05-29 20:29:12.000000000 -0700 @@ -135,4 +135,50 @@ static inline void percpu_free(void *__p #define free_percpu(ptr) percpu_free((ptr)) #define per_cpu_ptr(ptr, cpu) percpu_ptr((ptr), (cpu)) + +/* + * cpu allocator definitions + * + * The cpu allocator allows allocating an instance of an object for each + * processor and the use of a single pointer to access all instances + * of the object. cpu_alloc provides optimized means for accessing the + * instance of the object belonging to the currently executing processor + * as well as special atomic operations on fields of objects of the + * currently executing processor. + * + * Cpu objects are typically small. The allocator packs them tightly + * to increase the chance on each access that a per cpu object is already + * cached. Alignments may be specified but the intent is to align the data + * properly due to cpu alignment constraints and not to avoid cacheline + * contention. Any holes left by aligning objects are filled up with smaller + * objects that are allocated later. + * + * Cpu data can be allocated using CPU_ALLOC. The resulting pointer is + * pointing to the instance of the variable in the per cpu area provided + * by the loader. It is generally an error to use the pointer directly + * unless we are booting the system. + * + * __GFP_ZERO may be passed as a flag to zero the allocated memory. + */ + +/* Return a pointer to the instance of a object for a particular processor */ +#define CPU_PTR(__p, __cpu) SHIFT_PERCPU_PTR((__p), per_cpu_offset(__cpu)) + +/* + * Return a pointer to the instance of the object belonging to the processor + * running the current code. + */ +#define THIS_CPU(__p) SHIFT_PERCPU_PTR((__p), my_cpu_offset) +#define __THIS_CPU(__p) SHIFT_PERCPU_PTR((__p), __my_cpu_offset) + +#define CPU_ALLOC(type, flags) ((typeof(type) *)cpu_alloc(sizeof(type), \ + (flags), __alignof__(type))) +#define CPU_FREE(pointer) cpu_free((pointer), sizeof(*(pointer))) + +/* + * Raw calls + */ +void *cpu_alloc(unsigned long size, gfp_t flags, unsigned long align); +void cpu_free(void *cpu_pointer, unsigned long size); + #endif /* __LINUX_PERCPU_H */ -- -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/