kernel_optimize_test/include/linux/slab.h

224 lines
7.1 KiB
C
Raw Normal View History

/*
* Written by Mark Hemment, 1996 (markhe@nextd.demon.co.uk).
*
* (C) SGI 2006, Christoph Lameter <clameter@sgi.com>
* Cleaned up and restructured to ease the addition of alternative
* implementations of SLAB allocators.
*/
#ifndef _LINUX_SLAB_H
#define _LINUX_SLAB_H
#ifdef __KERNEL__
#include <linux/gfp.h>
#include <linux/types.h>
typedef struct kmem_cache kmem_cache_t __deprecated;
/*
* Flags to pass to kmem_cache_create().
* The ones marked DEBUG are only valid if CONFIG_SLAB_DEBUG is set.
*/
#define SLAB_DEBUG_FREE 0x00000100UL /* DEBUG: Perform (expensive) checks on free */
#define SLAB_DEBUG_INITIAL 0x00000200UL /* DEBUG: Call constructor (as verifier) */
#define SLAB_RED_ZONE 0x00000400UL /* DEBUG: Red zone objs in a cache */
#define SLAB_POISON 0x00000800UL /* DEBUG: Poison objects */
#define SLAB_HWCACHE_ALIGN 0x00002000UL /* Align objs on cache lines */
#define SLAB_CACHE_DMA 0x00004000UL /* Use GFP_DMA memory */
#define SLAB_MUST_HWCACHE_ALIGN 0x00008000UL /* Force alignment even if debuggin is active */
#define SLAB_STORE_USER 0x00010000UL /* DEBUG: Store the last owner for bug hunting */
#define SLAB_RECLAIM_ACCOUNT 0x00020000UL /* Objects are reclaimable */
#define SLAB_PANIC 0x00040000UL /* Panic if kmem_cache_create() fails */
#define SLAB_DESTROY_BY_RCU 0x00080000UL /* Defer freeing slabs to RCU */
[PATCH] cpuset memory spread slab cache implementation Provide the slab cache infrastructure to support cpuset memory spreading. See the previous patches, cpuset_mem_spread, for an explanation of cpuset memory spreading. This patch provides a slab cache SLAB_MEM_SPREAD flag. If set in the kmem_cache_create() call defining a slab cache, then any task marked with the process state flag PF_MEMSPREAD will spread memory page allocations for that cache over all the allowed nodes, instead of preferring the local (faulting) node. On systems not configured with CONFIG_NUMA, this results in no change to the page allocation code path for slab caches. On systems with cpusets configured in the kernel, but the "memory_spread" cpuset option not enabled for the current tasks cpuset, this adds a call to a cpuset routine and failed bit test of the processor state flag PF_SPREAD_SLAB. For tasks so marked, a second inline test is done for the slab cache flag SLAB_MEM_SPREAD, and if that is set and if the allocation is not in_interrupt(), this adds a call to to a cpuset routine that computes which of the tasks mems_allowed nodes should be preferred for this allocation. ==> This patch adds another hook into the performance critical code path to allocating objects from the slab cache, in the ____cache_alloc() chunk, below. The next patch optimizes this hook, reducing the impact of the combined mempolicy plus memory spreading hooks on this critical code path to a single check against the tasks task_struct flags word. This patch provides the generic slab flags and logic needed to apply memory spreading to a particular slab. A subsequent patch will mark a few specific slab caches for this placement policy. Signed-off-by: Paul Jackson <pj@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-03-24 19:16:07 +08:00
#define SLAB_MEM_SPREAD 0x00100000UL /* Spread some memory over cpuset */
/* Flags passed to a constructor functions */
#define SLAB_CTOR_CONSTRUCTOR 0x001UL /* If not set, then deconstructor */
#define SLAB_CTOR_ATOMIC 0x002UL /* Tell constructor it can't sleep */
#define SLAB_CTOR_VERIFY 0x004UL /* Tell constructor it's a verify call */
/*
* struct kmem_cache related prototypes
*/
void __init kmem_cache_init(void);
extern int slab_is_available(void);
struct kmem_cache *kmem_cache_create(const char *, size_t, size_t,
unsigned long,
void (*)(void *, struct kmem_cache *, unsigned long),
void (*)(void *, struct kmem_cache *, unsigned long));
void kmem_cache_destroy(struct kmem_cache *);
int kmem_cache_shrink(struct kmem_cache *);
void *kmem_cache_alloc(struct kmem_cache *, gfp_t);
void *kmem_cache_zalloc(struct kmem_cache *, gfp_t);
void kmem_cache_free(struct kmem_cache *, void *);
unsigned int kmem_cache_size(struct kmem_cache *);
const char *kmem_cache_name(struct kmem_cache *);
int kmem_ptr_validate(struct kmem_cache *cachep, const void *ptr);
#ifdef CONFIG_NUMA
extern void *kmem_cache_alloc_node(struct kmem_cache *, gfp_t flags, int node);
#else
static inline void *kmem_cache_alloc_node(struct kmem_cache *cachep,
gfp_t flags, int node)
{
return kmem_cache_alloc(cachep, flags);
}
#endif
/*
* Common kmalloc functions provided by all allocators
*/
void *__kmalloc(size_t, gfp_t);
void *__kzalloc(size_t, gfp_t);
void kfree(const void *);
unsigned int ksize(const void *);
/**
* kcalloc - allocate memory for an array. The memory is set to zero.
* @n: number of elements.
* @size: element size.
* @flags: the type of memory to allocate.
*/
static inline void *kcalloc(size_t n, size_t size, gfp_t flags)
{
if (n != 0 && size > ULONG_MAX / n)
return NULL;
return __kzalloc(n * size, flags);
}
/*
* Allocator specific definitions. These are mainly used to establish optimized
* ways to convert kmalloc() calls to kmem_cache_alloc() invocations by selecting
* the appropriate general cache at compile time.
*/
#ifdef CONFIG_SLAB
#include <linux/slab_def.h>
#else
/*
* Fallback definitions for an allocator not wanting to provide
* its own optimized kmalloc definitions (like SLOB).
*/
/**
* kmalloc - allocate memory
* @size: how many bytes of memory are required.
* @flags: the type of memory to allocate.
*
* kmalloc is the normal method of allocating memory
* in the kernel.
*
* The @flags argument may be one of:
*
* %GFP_USER - Allocate memory on behalf of user. May sleep.
*
* %GFP_KERNEL - Allocate normal kernel ram. May sleep.
*
* %GFP_ATOMIC - Allocation will not sleep.
* For example, use this inside interrupt handlers.
*
* %GFP_HIGHUSER - Allocate pages from high memory.
*
* %GFP_NOIO - Do not do any I/O at all while trying to get memory.
*
* %GFP_NOFS - Do not make any fs calls while trying to get memory.
*
* Also it is possible to set different flags by OR'ing
* in one or more of the following additional @flags:
*
* %__GFP_COLD - Request cache-cold pages instead of
* trying to return cache-warm pages.
*
* %__GFP_DMA - Request memory from the DMA-capable zone.
*
* %__GFP_HIGH - This allocation has high priority and may use emergency pools.
*
* %__GFP_HIGHMEM - Allocated memory may be from highmem.
*
* %__GFP_NOFAIL - Indicate that this allocation is in no way allowed to fail
* (think twice before using).
*
* %__GFP_NORETRY - If memory is not immediately available,
* then give up at once.
*
* %__GFP_NOWARN - If allocation fails, don't issue any warnings.
*
* %__GFP_REPEAT - If allocation fails initially, try once more before failing.
*/
static inline void *kmalloc(size_t size, gfp_t flags)
{
return __kmalloc(size, flags);
}
/**
* kzalloc - allocate memory. The memory is set to zero.
* @size: how many bytes of memory are required.
* @flags: the type of memory to allocate (see kmalloc).
*/
static inline void *kzalloc(size_t size, gfp_t flags)
{
return __kzalloc(size, flags);
}
#endif
#ifndef CONFIG_NUMA
static inline void *kmalloc_node(size_t size, gfp_t flags, int node)
{
return kmalloc(size, flags);
}
static inline void *__kmalloc_node(size_t size, gfp_t flags, int node)
{
return __kmalloc(size, flags);
}
#endif /* !CONFIG_NUMA */
/*
* kmalloc_track_caller is a special version of kmalloc that records the
* calling function of the routine calling it for slab leak tracking instead
* of just the calling function (confusing, eh?).
* It's useful when the call to kmalloc comes from a widely-used standard
* allocator where we care about the real place the memory allocation
* request comes from.
*/
#ifdef CONFIG_DEBUG_SLAB
extern void *__kmalloc_track_caller(size_t, gfp_t, void*);
#define kmalloc_track_caller(size, flags) \
__kmalloc_track_caller(size, flags, __builtin_return_address(0))
#else
#define kmalloc_track_caller(size, flags) \
__kmalloc(size, flags)
#endif /* DEBUG_SLAB */
[PATCH] add kmalloc_node, inline cleanup The patch makes the following function calls available to allocate memory on a specific node without changing the basic operation of the slab allocator: kmem_cache_alloc_node(kmem_cache_t *cachep, unsigned int flags, int node); kmalloc_node(size_t size, unsigned int flags, int node); in a similar way to the existing node-blind functions: kmem_cache_alloc(kmem_cache_t *cachep, unsigned int flags); kmalloc(size, flags); kmem_cache_alloc_node was changed to pass flags and the node information through the existing layers of the slab allocator (which lead to some minor rearrangements). The functions at the lowest layer (kmem_getpages, cache_grow) are already node aware. Also __alloc_percpu can call kmalloc_node now. Performance measurements (using the pageset localization patch) yields: w/o patches: Tasks jobs/min jti jobs/min/task real cpu 1 484.27 100 484.2736 12.02 1.97 Wed Mar 30 20:50:43 2005 100 25170.83 91 251.7083 23.12 150.10 Wed Mar 30 20:51:06 2005 200 34601.66 84 173.0083 33.64 294.14 Wed Mar 30 20:51:40 2005 300 37154.47 86 123.8482 46.99 436.56 Wed Mar 30 20:52:28 2005 400 39839.82 80 99.5995 58.43 580.46 Wed Mar 30 20:53:27 2005 500 40036.32 79 80.0726 72.68 728.60 Wed Mar 30 20:54:40 2005 600 44074.21 79 73.4570 79.23 872.10 Wed Mar 30 20:55:59 2005 700 44016.60 78 62.8809 92.56 1015.84 Wed Mar 30 20:57:32 2005 800 40411.05 80 50.5138 115.22 1161.13 Wed Mar 30 20:59:28 2005 900 42298.56 79 46.9984 123.83 1303.42 Wed Mar 30 21:01:33 2005 1000 40955.05 80 40.9551 142.11 1441.92 Wed Mar 30 21:03:55 2005 with pageset localization and slab API patches: Tasks jobs/min jti jobs/min/task real cpu 1 484.19 100 484.1930 12.02 1.98 Wed Mar 30 21:10:18 2005 100 27428.25 92 274.2825 21.22 149.79 Wed Mar 30 21:10:40 2005 200 37228.94 86 186.1447 31.27 293.49 Wed Mar 30 21:11:12 2005 300 41725.42 85 139.0847 41.84 434.10 Wed Mar 30 21:11:54 2005 400 43032.22 82 107.5805 54.10 582.06 Wed Mar 30 21:12:48 2005 500 42211.23 83 84.4225 68.94 722.61 Wed Mar 30 21:13:58 2005 600 40084.49 82 66.8075 87.12 873.11 Wed Mar 30 21:15:25 2005 700 44169.30 79 63.0990 92.24 1008.77 Wed Mar 30 21:16:58 2005 800 43097.94 79 53.8724 108.03 1155.88 Wed Mar 30 21:18:47 2005 900 41846.75 79 46.4964 125.17 1303.38 Wed Mar 30 21:20:52 2005 1000 40247.85 79 40.2478 144.60 1442.21 Wed Mar 30 21:23:17 2005 Signed-off-by: Christoph Lameter <christoph@lameter.com> Signed-off-by: Manfred Spraul <manfred@colorfullife.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-05-01 23:58:38 +08:00
#ifdef CONFIG_NUMA
/*
* kmalloc_node_track_caller is a special version of kmalloc_node that
* records the calling function of the routine calling it for slab leak
* tracking instead of just the calling function (confusing, eh?).
* It's useful when the call to kmalloc_node comes from a widely-used
* standard allocator where we care about the real place the memory
* allocation request comes from.
*/
#ifdef CONFIG_DEBUG_SLAB
extern void *__kmalloc_node_track_caller(size_t, gfp_t, int, void *);
#define kmalloc_node_track_caller(size, flags, node) \
__kmalloc_node_track_caller(size, flags, node, \
__builtin_return_address(0))
#else
#define kmalloc_node_track_caller(size, flags, node) \
__kmalloc_node(size, flags, node)
#endif
#else /* CONFIG_NUMA */
#define kmalloc_node_track_caller(size, flags, node) \
kmalloc_track_caller(size, flags)
[PATCH] add kmalloc_node, inline cleanup The patch makes the following function calls available to allocate memory on a specific node without changing the basic operation of the slab allocator: kmem_cache_alloc_node(kmem_cache_t *cachep, unsigned int flags, int node); kmalloc_node(size_t size, unsigned int flags, int node); in a similar way to the existing node-blind functions: kmem_cache_alloc(kmem_cache_t *cachep, unsigned int flags); kmalloc(size, flags); kmem_cache_alloc_node was changed to pass flags and the node information through the existing layers of the slab allocator (which lead to some minor rearrangements). The functions at the lowest layer (kmem_getpages, cache_grow) are already node aware. Also __alloc_percpu can call kmalloc_node now. Performance measurements (using the pageset localization patch) yields: w/o patches: Tasks jobs/min jti jobs/min/task real cpu 1 484.27 100 484.2736 12.02 1.97 Wed Mar 30 20:50:43 2005 100 25170.83 91 251.7083 23.12 150.10 Wed Mar 30 20:51:06 2005 200 34601.66 84 173.0083 33.64 294.14 Wed Mar 30 20:51:40 2005 300 37154.47 86 123.8482 46.99 436.56 Wed Mar 30 20:52:28 2005 400 39839.82 80 99.5995 58.43 580.46 Wed Mar 30 20:53:27 2005 500 40036.32 79 80.0726 72.68 728.60 Wed Mar 30 20:54:40 2005 600 44074.21 79 73.4570 79.23 872.10 Wed Mar 30 20:55:59 2005 700 44016.60 78 62.8809 92.56 1015.84 Wed Mar 30 20:57:32 2005 800 40411.05 80 50.5138 115.22 1161.13 Wed Mar 30 20:59:28 2005 900 42298.56 79 46.9984 123.83 1303.42 Wed Mar 30 21:01:33 2005 1000 40955.05 80 40.9551 142.11 1441.92 Wed Mar 30 21:03:55 2005 with pageset localization and slab API patches: Tasks jobs/min jti jobs/min/task real cpu 1 484.19 100 484.1930 12.02 1.98 Wed Mar 30 21:10:18 2005 100 27428.25 92 274.2825 21.22 149.79 Wed Mar 30 21:10:40 2005 200 37228.94 86 186.1447 31.27 293.49 Wed Mar 30 21:11:12 2005 300 41725.42 85 139.0847 41.84 434.10 Wed Mar 30 21:11:54 2005 400 43032.22 82 107.5805 54.10 582.06 Wed Mar 30 21:12:48 2005 500 42211.23 83 84.4225 68.94 722.61 Wed Mar 30 21:13:58 2005 600 40084.49 82 66.8075 87.12 873.11 Wed Mar 30 21:15:25 2005 700 44169.30 79 63.0990 92.24 1008.77 Wed Mar 30 21:16:58 2005 800 43097.94 79 53.8724 108.03 1155.88 Wed Mar 30 21:18:47 2005 900 41846.75 79 46.4964 125.17 1303.38 Wed Mar 30 21:20:52 2005 1000 40247.85 79 40.2478 144.60 1442.21 Wed Mar 30 21:23:17 2005 Signed-off-by: Christoph Lameter <christoph@lameter.com> Signed-off-by: Manfred Spraul <manfred@colorfullife.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-05-01 23:58:38 +08:00
#endif /* DEBUG_SLAB */
[PATCH] slob: introduce the SLOB allocator configurable replacement for slab allocator This adds a CONFIG_SLAB option under CONFIG_EMBEDDED. When CONFIG_SLAB is disabled, the kernel falls back to using the 'SLOB' allocator. SLOB is a traditional K&R/UNIX allocator with a SLAB emulation layer, similar to the original Linux kmalloc allocator that SLAB replaced. It's signicantly smaller code and is more memory efficient. But like all similar allocators, it scales poorly and suffers from fragmentation more than SLAB, so it's only appropriate for small systems. It's been tested extensively in the Linux-tiny tree. I've also stress-tested it with make -j 8 compiles on a 3G SMP+PREEMPT box (not recommended). Here's a comparison for otherwise identical builds, showing SLOB saving nearly half a megabyte of RAM: $ size vmlinux* text data bss dec hex filename 3336372 529360 190812 4056544 3de5e0 vmlinux-slab 3323208 527948 190684 4041840 3dac70 vmlinux-slob $ size mm/{slab,slob}.o text data bss dec hex filename 13221 752 48 14021 36c5 mm/slab.o 1896 52 8 1956 7a4 mm/slob.o /proc/meminfo: SLAB SLOB delta MemTotal: 27964 kB 27980 kB +16 kB MemFree: 24596 kB 25092 kB +496 kB Buffers: 36 kB 36 kB 0 kB Cached: 1188 kB 1188 kB 0 kB SwapCached: 0 kB 0 kB 0 kB Active: 608 kB 600 kB -8 kB Inactive: 808 kB 812 kB +4 kB HighTotal: 0 kB 0 kB 0 kB HighFree: 0 kB 0 kB 0 kB LowTotal: 27964 kB 27980 kB +16 kB LowFree: 24596 kB 25092 kB +496 kB SwapTotal: 0 kB 0 kB 0 kB SwapFree: 0 kB 0 kB 0 kB Dirty: 4 kB 12 kB +8 kB Writeback: 0 kB 0 kB 0 kB Mapped: 560 kB 556 kB -4 kB Slab: 1756 kB 0 kB -1756 kB CommitLimit: 13980 kB 13988 kB +8 kB Committed_AS: 4208 kB 4208 kB 0 kB PageTables: 28 kB 28 kB 0 kB VmallocTotal: 1007312 kB 1007312 kB 0 kB VmallocUsed: 48 kB 48 kB 0 kB VmallocChunk: 1007264 kB 1007264 kB 0 kB (this work has been sponsored in part by CELF) From: Ingo Molnar <mingo@elte.hu> Fix 32-bitness bugs in mm/slob.c. Signed-off-by: Matt Mackall <mpm@selenic.com> Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-08 17:01:45 +08:00
#endif /* __KERNEL__ */
#endif /* _LINUX_SLAB_H */