diff --git a/include/linux/slab.h b/include/linux/slab.h index ad4dd1c8d30a..573c809c33d9 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -133,6 +133,26 @@ unsigned int kmem_cache_size(struct kmem_cache *); #define KMALLOC_MAX_SIZE (1UL << KMALLOC_SHIFT_HIGH) #define KMALLOC_MAX_ORDER (KMALLOC_SHIFT_HIGH - PAGE_SHIFT) +/* + * Some archs want to perform DMA into kmalloc caches and need a guaranteed + * alignment larger than the alignment of a 64-bit integer. + * Setting ARCH_KMALLOC_MINALIGN in arch headers allows that. + */ +#ifdef ARCH_DMA_MINALIGN +#define ARCH_KMALLOC_MINALIGN ARCH_DMA_MINALIGN +#else +#define ARCH_KMALLOC_MINALIGN __alignof__(unsigned long long) +#endif + +/* + * Setting ARCH_SLAB_MINALIGN in arch headers allows a different alignment. + * Intended for arches that get misalignment faults even for 64 bit integer + * aligned buffers. + */ +#ifndef ARCH_SLAB_MINALIGN +#define ARCH_SLAB_MINALIGN __alignof__(unsigned long long) +#endif + /* * Common kmalloc functions provided by all allocators */ diff --git a/include/linux/slab_def.h b/include/linux/slab_def.h index 83203ae9390b..d00e0bacda93 100644 --- a/include/linux/slab_def.h +++ b/include/linux/slab_def.h @@ -17,32 +17,6 @@ #include -/* - * Enforce a minimum alignment for the kmalloc caches. - * Usually, the kmalloc caches are cache_line_size() aligned, except when - * DEBUG and FORCED_DEBUG are enabled, then they are BYTES_PER_WORD aligned. - * Some archs want to perform DMA into kmalloc caches and need a guaranteed - * alignment larger than the alignment of a 64-bit integer. - * ARCH_KMALLOC_MINALIGN allows that. - * Note that increasing this value may disable some debug features. - */ -#ifdef ARCH_DMA_MINALIGN -#define ARCH_KMALLOC_MINALIGN ARCH_DMA_MINALIGN -#else -#define ARCH_KMALLOC_MINALIGN __alignof__(unsigned long long) -#endif - -#ifndef ARCH_SLAB_MINALIGN -/* - * Enforce a minimum alignment for all caches. - * Intended for archs that get misalignment faults even for BYTES_PER_WORD - * aligned buffers. Includes ARCH_KMALLOC_MINALIGN. - * If possible: Do not enable this flag for CONFIG_DEBUG_SLAB, it disables - * some debug features. - */ -#define ARCH_SLAB_MINALIGN 0 -#endif - /* * struct kmem_cache * @@ -50,21 +24,19 @@ */ struct kmem_cache { -/* 1) per-cpu data, touched during every alloc/free */ - struct array_cache *array[NR_CPUS]; -/* 2) Cache tunables. Protected by cache_chain_mutex */ +/* 1) Cache tunables. Protected by cache_chain_mutex */ unsigned int batchcount; unsigned int limit; unsigned int shared; unsigned int buffer_size; u32 reciprocal_buffer_size; -/* 3) touched by every alloc & free from the backend */ +/* 2) touched by every alloc & free from the backend */ unsigned int flags; /* constant flags */ unsigned int num; /* # of objs per slab */ -/* 4) cache_grow/shrink */ +/* 3) cache_grow/shrink */ /* order of pgs per slab (2^n) */ unsigned int gfporder; @@ -80,11 +52,11 @@ struct kmem_cache { /* constructor func */ void (*ctor)(void *obj); -/* 5) cache creation/removal */ +/* 4) cache creation/removal */ const char *name; struct list_head next; -/* 6) statistics */ +/* 5) statistics */ #ifdef CONFIG_DEBUG_SLAB unsigned long num_active; unsigned long num_allocations; @@ -111,16 +83,18 @@ struct kmem_cache { int obj_size; #endif /* CONFIG_DEBUG_SLAB */ +/* 6) per-cpu/per-node data, touched during every alloc/free */ /* - * We put nodelists[] at the end of kmem_cache, because we want to size - * this array to nr_node_ids slots instead of MAX_NUMNODES + * We put array[] at the end of kmem_cache, because we want to size + * this array to nr_cpu_ids slots instead of NR_CPUS * (see kmem_cache_init()) - * We still use [MAX_NUMNODES] and not [1] or [0] because cache_cache - * is statically defined, so we reserve the max number of nodes. + * We still use [NR_CPUS] and not [1] or [0] because cache_cache + * is statically defined, so we reserve the max number of cpus. */ - struct kmem_list3 *nodelists[MAX_NUMNODES]; + struct kmem_list3 **nodelists; + struct array_cache *array[NR_CPUS]; /* - * Do not add fields after nodelists[] + * Do not add fields after array[] */ }; diff --git a/include/linux/slob_def.h b/include/linux/slob_def.h index 4382db09df4f..0ec00b39d006 100644 --- a/include/linux/slob_def.h +++ b/include/linux/slob_def.h @@ -1,16 +1,6 @@ #ifndef __LINUX_SLOB_DEF_H #define __LINUX_SLOB_DEF_H -#ifdef ARCH_DMA_MINALIGN -#define ARCH_KMALLOC_MINALIGN ARCH_DMA_MINALIGN -#else -#define ARCH_KMALLOC_MINALIGN __alignof__(unsigned long) -#endif - -#ifndef ARCH_SLAB_MINALIGN -#define ARCH_SLAB_MINALIGN __alignof__(unsigned long) -#endif - void *kmem_cache_alloc_node(struct kmem_cache *, gfp_t flags, int node); static __always_inline void *kmem_cache_alloc(struct kmem_cache *cachep, diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h index c8668d161dd8..4b35c06dfbc5 100644 --- a/include/linux/slub_def.h +++ b/include/linux/slub_def.h @@ -113,16 +113,6 @@ struct kmem_cache { #define KMALLOC_SHIFT_LOW ilog2(KMALLOC_MIN_SIZE) -#ifdef ARCH_DMA_MINALIGN -#define ARCH_KMALLOC_MINALIGN ARCH_DMA_MINALIGN -#else -#define ARCH_KMALLOC_MINALIGN __alignof__(unsigned long long) -#endif - -#ifndef ARCH_SLAB_MINALIGN -#define ARCH_SLAB_MINALIGN __alignof__(unsigned long long) -#endif - /* * Maximum kmalloc object size handled by SLUB. Larger object allocations * are passed through to the page allocator. The page allocator "fastpath" @@ -228,6 +218,19 @@ kmalloc_order(size_t size, gfp_t flags, unsigned int order) return ret; } +/** + * Calling this on allocated memory will check that the memory + * is expected to be in use, and print warnings if not. + */ +#ifdef CONFIG_SLUB_DEBUG +extern bool verify_mem_not_deleted(const void *x); +#else +static inline bool verify_mem_not_deleted(const void *x) +{ + return true; +} +#endif + #ifdef CONFIG_TRACING extern void * kmem_cache_alloc_trace(struct kmem_cache *s, gfp_t gfpflags, size_t size); diff --git a/mm/slab.c b/mm/slab.c index d96e223de775..1e523ed47c61 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -574,7 +574,9 @@ static struct arraycache_init initarray_generic = { {0, BOOT_CPUCACHE_ENTRIES, 1, 0} }; /* internal cache of cache description objs */ +static struct kmem_list3 *cache_cache_nodelists[MAX_NUMNODES]; static struct kmem_cache cache_cache = { + .nodelists = cache_cache_nodelists, .batchcount = 1, .limit = BOOT_CPUCACHE_ENTRIES, .shared = 1, @@ -1492,11 +1494,10 @@ void __init kmem_cache_init(void) cache_cache.nodelists[node] = &initkmem_list3[CACHE_CACHE + node]; /* - * struct kmem_cache size depends on nr_node_ids, which - * can be less than MAX_NUMNODES. + * struct kmem_cache size depends on nr_node_ids & nr_cpu_ids */ - cache_cache.buffer_size = offsetof(struct kmem_cache, nodelists) + - nr_node_ids * sizeof(struct kmem_list3 *); + cache_cache.buffer_size = offsetof(struct kmem_cache, array[nr_cpu_ids]) + + nr_node_ids * sizeof(struct kmem_list3 *); #if DEBUG cache_cache.obj_size = cache_cache.buffer_size; #endif @@ -2308,6 +2309,7 @@ kmem_cache_create (const char *name, size_t size, size_t align, if (!cachep) goto oops; + cachep->nodelists = (struct kmem_list3 **)&cachep->array[nr_cpu_ids]; #if DEBUG cachep->obj_size = size; @@ -3153,12 +3155,11 @@ static void *cache_alloc_debugcheck_after(struct kmem_cache *cachep, objp += obj_offset(cachep); if (cachep->ctor && cachep->flags & SLAB_POISON) cachep->ctor(objp); -#if ARCH_SLAB_MINALIGN - if ((u32)objp & (ARCH_SLAB_MINALIGN-1)) { + if (ARCH_SLAB_MINALIGN && + ((unsigned long)objp & (ARCH_SLAB_MINALIGN-1))) { printk(KERN_ERR "0x%p: not aligned to ARCH_SLAB_MINALIGN=%d\n", - objp, ARCH_SLAB_MINALIGN); + objp, (int)ARCH_SLAB_MINALIGN); } -#endif return objp; } #else diff --git a/mm/slob.c b/mm/slob.c index 46e0aee33a23..0ae881831ae2 100644 --- a/mm/slob.c +++ b/mm/slob.c @@ -482,6 +482,8 @@ void *__kmalloc_node(size_t size, gfp_t gfp, int node) int align = max(ARCH_KMALLOC_MINALIGN, ARCH_SLAB_MINALIGN); void *ret; + gfp &= gfp_allowed_mask; + lockdep_trace_alloc(gfp); if (size < PAGE_SIZE - align) { @@ -608,6 +610,10 @@ void *kmem_cache_alloc_node(struct kmem_cache *c, gfp_t flags, int node) { void *b; + flags &= gfp_allowed_mask; + + lockdep_trace_alloc(flags); + if (c->size < PAGE_SIZE) { b = slob_alloc(c->size, flags, c->align, node); trace_kmem_cache_alloc_node(_RET_IP_, b, c->size, diff --git a/mm/slub.c b/mm/slub.c index 35f351f26193..ba83f3fd0757 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -27,6 +27,7 @@ #include #include #include +#include #include @@ -191,8 +192,12 @@ static LIST_HEAD(slab_caches); /* * Tracking user of a slab. */ +#define TRACK_ADDRS_COUNT 16 struct track { unsigned long addr; /* Called from address */ +#ifdef CONFIG_STACKTRACE + unsigned long addrs[TRACK_ADDRS_COUNT]; /* Called from address */ +#endif int cpu; /* Was running on cpu */ int pid; /* Pid context */ unsigned long when; /* When did the operation occur */ @@ -420,6 +425,24 @@ static void set_track(struct kmem_cache *s, void *object, struct track *p = get_track(s, object, alloc); if (addr) { +#ifdef CONFIG_STACKTRACE + struct stack_trace trace; + int i; + + trace.nr_entries = 0; + trace.max_entries = TRACK_ADDRS_COUNT; + trace.entries = p->addrs; + trace.skip = 3; + save_stack_trace(&trace); + + /* See rant in lockdep.c */ + if (trace.nr_entries != 0 && + trace.entries[trace.nr_entries - 1] == ULONG_MAX) + trace.nr_entries--; + + for (i = trace.nr_entries; i < TRACK_ADDRS_COUNT; i++) + p->addrs[i] = 0; +#endif p->addr = addr; p->cpu = smp_processor_id(); p->pid = current->pid; @@ -444,6 +467,16 @@ static void print_track(const char *s, struct track *t) printk(KERN_ERR "INFO: %s in %pS age=%lu cpu=%u pid=%d\n", s, (void *)t->addr, jiffies - t->when, t->cpu, t->pid); +#ifdef CONFIG_STACKTRACE + { + int i; + for (i = 0; i < TRACK_ADDRS_COUNT; i++) + if (t->addrs[i]) + printk(KERN_ERR "\t%pS\n", (void *)t->addrs[i]); + else + break; + } +#endif } static void print_tracking(struct kmem_cache *s, void *object) @@ -557,10 +590,10 @@ static void init_object(struct kmem_cache *s, void *object, u8 val) memset(p + s->objsize, val, s->inuse - s->objsize); } -static u8 *check_bytes(u8 *start, unsigned int value, unsigned int bytes) +static u8 *check_bytes8(u8 *start, u8 value, unsigned int bytes) { while (bytes) { - if (*start != (u8)value) + if (*start != value) return start; start++; bytes--; @@ -568,6 +601,38 @@ static u8 *check_bytes(u8 *start, unsigned int value, unsigned int bytes) return NULL; } +static u8 *check_bytes(u8 *start, u8 value, unsigned int bytes) +{ + u64 value64; + unsigned int words, prefix; + + if (bytes <= 16) + return check_bytes8(start, value, bytes); + + value64 = value | value << 8 | value << 16 | value << 24; + value64 = value64 | value64 << 32; + prefix = 8 - ((unsigned long)start) % 8; + + if (prefix) { + u8 *r = check_bytes8(start, value, prefix); + if (r) + return r; + start += prefix; + bytes -= prefix; + } + + words = bytes / 8; + + while (words) { + if (*(u64 *)start != value64) + return check_bytes8(start, value, 8); + start += 8; + words--; + } + + return check_bytes8(start, value, bytes % 8); +} + static void restore_bytes(struct kmem_cache *s, char *message, u8 data, void *from, void *to) { @@ -2928,6 +2993,42 @@ size_t ksize(const void *object) } EXPORT_SYMBOL(ksize); +#ifdef CONFIG_SLUB_DEBUG +bool verify_mem_not_deleted(const void *x) +{ + struct page *page; + void *object = (void *)x; + unsigned long flags; + bool rv; + + if (unlikely(ZERO_OR_NULL_PTR(x))) + return false; + + local_irq_save(flags); + + page = virt_to_head_page(x); + if (unlikely(!PageSlab(page))) { + /* maybe it was from stack? */ + rv = true; + goto out_unlock; + } + + slab_lock(page); + if (on_freelist(page->slab, page, object)) { + object_err(page->slab, page, object, "Object is on free-list"); + rv = false; + } else { + rv = true; + } + slab_unlock(page); + +out_unlock: + local_irq_restore(flags); + return rv; +} +EXPORT_SYMBOL(verify_mem_not_deleted); +#endif + void kfree(const void *x) { struct page *page;