/* * SLUB: A slab allocator that limits cache line use instead of queuing * objects in per cpu and per node lists. * * The allocator synchronizes using per slab locks and only * uses a centralized lock to manage a pool of partial slabs. * * (C) 2007 SGI, Christoph Lameter */ #include #include /* struct reclaim_state */ #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include /* * Lock order: * 1. slab_lock(page) * 2. slab->list_lock * * The slab_lock protects operations on the object of a particular * slab and its metadata in the page struct. If the slab lock * has been taken then no allocations nor frees can be performed * on the objects in the slab nor can the slab be added or removed * from the partial or full lists since this would mean modifying * the page_struct of the slab. * * The list_lock protects the partial and full list on each node and * the partial slab counter. If taken then no new slabs may be added or * removed from the lists nor make the number of partial slabs be modified. * (Note that the total number of slabs is an atomic value that may be * modified without taking the list lock). * * The list_lock is a centralized lock and thus we avoid taking it as * much as possible. As long as SLUB does not have to handle partial * slabs, operations can continue without any centralized lock. F.e. * allocating a long series of objects that fill up slabs does not require * the list lock. * * The lock order is sometimes inverted when we are trying to get a slab * off a list. We take the list_lock and then look for a page on the list * to use. While we do that objects in the slabs may be freed. We can * only operate on the slab if we have also taken the slab_lock. So we use * a slab_trylock() on the slab. If trylock was successful then no frees * can occur anymore and we can use the slab for allocations etc. If the * slab_trylock() does not succeed then frees are in progress in the slab and * we must stay away from it for a while since we may cause a bouncing * cacheline if we try to acquire the lock. So go onto the next slab. * If all pages are busy then we may allocate a new slab instead of reusing * a partial slab. A new slab has noone operating on it and thus there is * no danger of cacheline contention. * * Interrupts are disabled during allocation and deallocation in order to * make the slab allocator safe to use in the context of an irq. In addition * interrupts are disabled to ensure that the processor does not change * while handling per_cpu slabs, due to kernel preemption. * * SLUB assigns one slab for allocation to each processor. * Allocations only occur from these slabs called cpu slabs. * * Slabs with free elements are kept on a partial list and during regular * operations no list for full slabs is used. If an object in a full slab is * freed then the slab will show up again on the partial lists. * We track full slabs for debugging purposes though because otherwise we * cannot scan all objects. * * Slabs are freed when they become empty. Teardown and setup is * minimal so we rely on the page allocators per cpu caches for * fast frees and allocs. * * Overloading of page flags that are otherwise used for LRU management. * * PageActive The slab is frozen and exempt from list processing. * This means that the slab is dedicated to a purpose * such as satisfying allocations for a specific * processor. Objects may be freed in the slab while * it is frozen but slab_free will then skip the usual * list operations. It is up to the processor holding * the slab to integrate the slab into the slab lists * when the slab is no longer needed. * * One use of this flag is to mark slabs that are * used for allocations. Then such a slab becomes a cpu * slab. The cpu slab may be equipped with an additional * freelist that allows lockless access to * free objects in addition to the regular freelist * that requires the slab lock. * * PageError Slab requires special handling due to debug * options set. This moves slab handling out of * the fast path and disables lockless freelists. */ #ifdef CONFIG_SLUB_DEBUG #define SLABDEBUG 1 #else #define SLABDEBUG 0 #endif /* * Issues still to be resolved: * * - Support PAGE_ALLOC_DEBUG. Should be easy to do. * * - Variable sizing of the per node arrays */ /* Enable to test recovery from slab corruption on boot */ #undef SLUB_RESILIENCY_TEST /* * Mininum number of partial slabs. These will be left on the partial * lists even if they are empty. kmem_cache_shrink may reclaim them. */ #define MIN_PARTIAL 5 /* * Maximum number of desirable partial slabs. * The existence of more partial slabs makes kmem_cache_shrink * sort the partial list by the number of objects in the. */ #define MAX_PARTIAL 10 #define DEBUG_DEFAULT_FLAGS (SLAB_DEBUG_FREE | SLAB_RED_ZONE | \ SLAB_POISON | SLAB_STORE_USER) /* * Debugging flags that require metadata to be stored in the slab. These get * disabled when slub_debug=O is used and a cache's min order increases with * metadata. */ #define DEBUG_METADATA_FLAGS (SLAB_RED_ZONE | SLAB_POISON | SLAB_STORE_USER) /* * Set of flags that will prevent slab merging */ #define SLUB_NEVER_MERGE (SLAB_RED_ZONE | SLAB_POISON | SLAB_STORE_USER | \ SLAB_TRACE | SLAB_DESTROY_BY_RCU | SLAB_NOLEAKTRACE) #define SLUB_MERGE_SAME (SLAB_DEBUG_FREE | SLAB_RECLAIM_ACCOUNT | \ SLAB_CACHE_DMA | SLAB_NOTRACK) #ifndef ARCH_KMALLOC_MINALIGN #define ARCH_KMALLOC_MINALIGN __alignof__(unsigned long long) #endif #ifndef ARCH_SLAB_MINALIGN #define ARCH_SLAB_MINALIGN __alignof__(unsigned long long) #endif #define OO_SHIFT 16 #define OO_MASK ((1 << OO_SHIFT) - 1) #define MAX_OBJS_PER_PAGE 65535 /* since page.objects is u16 */ /* Internal SLUB flags */ #define __OBJECT_POISON 0x80000000 /* Poison object */ #define __SYSFS_ADD_DEFERRED 0x40000000 /* Not yet visible via sysfs */ static int kmem_size = sizeof(struct kmem_cache); #ifdef CONFIG_SMP static struct notifier_block slab_notifier; #endif static enum { DOWN, /* No slab functionality available */ PARTIAL, /* kmem_cache_open() works but kmalloc does not */ UP, /* Everything works but does not show up in sysfs */ SYSFS /* Sysfs up */ } slab_state = DOWN; /* A list of all slab caches on the system */ static DECLARE_RWSEM(slub_lock); static LIST_HEAD(slab_caches); /* * Tracking user of a slab. */ struct track { unsigned long addr; /* Called from address */ int cpu; /* Was running on cpu */ int pid; /* Pid context */ unsigned long when; /* When did the operation occur */ }; enum track_item { TRACK_ALLOC, TRACK_FREE }; #ifdef CONFIG_SLUB_DEBUG static int sysfs_slab_add(struct kmem_cache *); static int sysfs_slab_alias(struct kmem_cache *, const char *); static void sysfs_slab_remove(struct kmem_cache *); #else static inline int sysfs_slab_add(struct kmem_cache *s) { return 0; } static inline int sysfs_slab_alias(struct kmem_cache *s, const char *p) { return 0; } static inline void sysfs_slab_remove(struct kmem_cache *s) { kfree(s); } #endif static inline void stat(struct kmem_cache_cpu *c, enum stat_item si) { #ifdef CONFIG_SLUB_STATS c->stat[si]++; #endif } /******************************************************************** * Core slab cache functions *******************************************************************/ int slab_is_available(void) { return slab_state >= UP; } static inline struct kmem_cache_node *get_node(struct kmem_cache *s, int node) { #ifdef CONFIG_NUMA return s->node[node]; #else return &s->local_node; #endif } static inline struct kmem_cache_cpu *get_cpu_slab(struct kmem_cache *s, int cpu) { #ifdef CONFIG_SMP return s->cpu_slab[cpu]; #else return &s->cpu_slab; #endif } /* Verify that a pointer has an address that is valid within a slab page */ static inline int check_valid_pointer(struct kmem_cache *s, struct page *page, const void *object) { void *base; if (!object) return 1; base = page_address(page); if (object < base || object >= base + page->objects * s->size || (object - base) % s->size) { return 0; } return 1; } /* * Slow version of get and set free pointer. * * This version requires touching the cache lines of kmem_cache which * we avoid to do in the fast alloc free paths. There we obtain the offset * from the page struct. */ static inline void *get_freepointer(struct kmem_cache *s, void *object) { return *(void **)(object + s->offset); } static inline void set_freepointer(struct kmem_cache *s, void *object, void *fp) { *(void **)(object + s->offset) = fp; } /* Loop over all objects in a slab */ #define for_each_object(__p, __s, __addr, __objects) \ for (__p = (__addr); __p < (__addr) + (__objects) * (__s)->size;\ __p += (__s)->size) /* Scan freelist */ #define for_each_free_object(__p, __s, __free) \ for (__p = (__free); __p; __p = get_freepointer((__s), __p)) /* Determine object index from a given position */ static inline int slab_index(void *p, struct kmem_cache *s, void *addr) { return (p - addr) / s->size; } static inline struct kmem_cache_order_objects oo_make(int order, unsigned long size) { struct kmem_cache_order_objects x = { (order << OO_SHIFT) + (PAGE_SIZE << order) / size }; return x; } static inline int oo_order(struct kmem_cache_order_objects x) { return x.x >> OO_SHIFT; } static inline int oo_objects(struct kmem_cache_order_objects x) { return x.x & OO_MASK; } #ifdef CONFIG_SLUB_DEBUG /* * Debug settings: */ #ifdef CONFIG_SLUB_DEBUG_ON static int slub_debug = DEBUG_DEFAULT_FLAGS; #else static int slub_debug; #endif static char *slub_debug_slabs; static int disable_higher_order_debug; /* * Object debugging */ static void print_section(char *text, u8 *addr, unsigned int length) { int i, offset; int newline = 1; char ascii[17]; ascii[16] = 0; for (i = 0; i < length; i++) { if (newline) { printk(KERN_ERR "%8s 0x%p: ", text, addr + i); newline = 0; } printk(KERN_CONT " %02x", addr[i]); offset = i % 16; ascii[offset] = isgraph(addr[i]) ? addr[i] : '.'; if (offset == 15) { printk(KERN_CONT " %s\n", ascii); newline = 1; } } if (!newline) { i %= 16; while (i < 16) { printk(KERN_CONT " "); ascii[i] = ' '; i++; } printk(KERN_CONT " %s\n", ascii); } } static struct track *get_track(struct kmem_cache *s, void *object, enum track_item alloc) { struct track *p; if (s->offset) p = object + s->offset + sizeof(void *); else p = object + s->inuse; return p + alloc; } static void set_track(struct kmem_cache *s, void *object, enum track_item alloc, unsigned long addr) { struct track *p = get_track(s, object, alloc); if (addr) { p->addr = addr; p->cpu = smp_processor_id(); p->pid = current->pid; p->when = jiffies; } else memset(p, 0, sizeof(struct track)); } static void init_tracking(struct kmem_cache *s, void *object) { if (!(s->flags & SLAB_STORE_USER)) return; set_track(s, object, TRACK_FREE, 0UL); set_track(s, object, TRACK_ALLOC, 0UL); } static void print_track(const char *s, struct track *t) { if (!t->addr) return; 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); } static void print_tracking(struct kmem_cache *s, void *object) { if (!(s->flags & SLAB_STORE_USER)) return; print_track("Allocated", get_track(s, object, TRACK_ALLOC)); print_track("Freed", get_track(s, object, TRACK_FREE)); } static void print_page_info(struct page *page) { printk(KERN_ERR "INFO: Slab 0x%p objects=%u used=%u fp=0x%p flags=0x%04lx\n", page, page->objects, page->inuse, page->freelist, page->flags); } static void slab_bug(struct kmem_cache *s, char *fmt, ...) { va_list args; char buf[100]; va_start(args, fmt); vsnprintf(buf, sizeof(buf), fmt, args); va_end(args); printk(KERN_ERR "========================================" "=====================================\n"); printk(KERN_ERR "BUG %s: %s\n", s->name, buf); printk(KERN_ERR "----------------------------------------" "-------------------------------------\n\n"); } static void slab_fix(struct kmem_cache *s, char *fmt, ...) { va_list args; char buf[100]; va_start(args, fmt); vsnprintf(buf, sizeof(buf), fmt, args); va_end(args); printk(KERN_ERR "FIX %s: %s\n", s->name, buf); } static void print_trailer(struct kmem_cache *s, struct page *page, u8 *p) { unsigned int off; /* Offset of last byte */ u8 *addr = page_address(page); print_tracking(s, p); print_page_info(page); printk(KERN_ERR "INFO: Object 0x%p @offset=%tu fp=0x%p\n\n", p, p - addr, get_freepointer(s, p)); if (p > addr + 16) print_section("Bytes b4", p - 16, 16); print_section("Object", p, min_t(unsigned long, s->objsize, PAGE_SIZE)); if (s->flags & SLAB_RED_ZONE) print_section("Redzone", p + s->objsize, s->inuse - s->objsize); if (s->offset) off = s->offset + sizeof(void *); else off = s->inuse; if (s->flags & SLAB_STORE_USER) off += 2 * sizeof(struct track); if (off != s->size) /* Beginning of the filler is the free pointer */ print_section("Padding", p + off, s->size - off); dump_stack(); } static void object_err(struct kmem_cache *s, struct page *page, u8 *object, char *reason) { slab_bug(s, "%s", reason); print_trailer(s, page, object); } static void slab_err(struct kmem_cache *s, struct page *page, char *fmt, ...) { va_list args; char buf[100]; va_start(args, fmt); vsnprintf(buf, sizeof(buf), fmt, args); va_end(args); slab_bug(s, "%s", buf); print_page_info(page); dump_stack(); } static void init_object(struct kmem_cache *s, void *object, int active) { u8 *p = object; if (s->flags & __OBJECT_POISON) { memset(p, POISON_FREE, s->objsize - 1); p[s->objsize - 1] = POISON_END; } if (s->flags & SLAB_RED_ZONE) memset(p + s->objsize, active ? SLUB_RED_ACTIVE : SLUB_RED_INACTIVE, s->inuse - s->objsize); } static u8 *check_bytes(u8 *start, unsigned int value, unsigned int bytes) { while (bytes) { if (*start != (u8)value) return start; start++; bytes--; } return NULL; } static void restore_bytes(struct kmem_cache *s, char *message, u8 data, void *from, void *to) { slab_fix(s, "Restoring 0x%p-0x%p=0x%x\n", from, to - 1, data); memset(from, data, to - from); } static int check_bytes_and_report(struct kmem_cache *s, struct page *page, u8 *object, char *what, u8 *start, unsigned int value, unsigned int bytes) { u8 *fault; u8 *end; fault = check_bytes(start, value, bytes); if (!fault) return 1; end = start + bytes; while (end > fault && end[-1] == value) end--; slab_bug(s, "%s overwritten", what); printk(KERN_ERR "INFO: 0x%p-0x%p. First byte 0x%x instead of 0x%x\n", fault, end - 1, fault[0], value); print_trailer(s, page, object); restore_bytes(s, what, value, fault, end); return 0; } /* * Object layout: * * object address * Bytes of the object to be managed. * If the freepointer may overlay the object then the free * pointer is the first word of the object. * * Poisoning uses 0x6b (POISON_FREE) and the last byte is * 0xa5 (POISON_END) * * object + s->objsize * Padding to reach word boundary. This is also used for Redzoning. * Padding is extended by another word if Redzoning is enabled and * objsize == inuse. * * We fill with 0xbb (RED_INACTIVE) for inactive objects and with * 0xcc (RED_ACTIVE) for objects in use. * * object + s->inuse * Meta data starts here. * * A. Free pointer (if we cannot overwrite object on free) * B. Tracking data for SLAB_STORE_USER * C. Padding to reach required alignment boundary or at mininum * one word if debugging is on to be able to detect writes * before the word boundary. * * Padding is done using 0x5a (POISON_INUSE) * * object + s->size * Nothing is used beyond s->size. * * If slabcaches are merged then the objsize and inuse boundaries are mostly * ignored. And therefore no slab options that rely on these boundaries * may be used with merged slabcaches. */ static int check_pad_bytes(struct kmem_cache *s, struct page *page, u8 *p) { unsigned long off = s->inuse; /* The end of info */ if (s->offset) /* Freepointer is placed after the object. */ off += sizeof(void *); if (s->flags & SLAB_STORE_USER) /* We also have user information there */ off += 2 * sizeof(struct track); if (s->size == off) return 1; return check_bytes_and_report(s, page, p, "Object padding", p + off, POISON_INUSE, s->size - off); } /* Check the pad bytes at the end of a slab page */ static int slab_pad_check(struct kmem_cache *s, struct page *page) { u8 *start; u8 *fault; u8 *end; int length; int remainder; if (!(s->flags & SLAB_POISON)) return 1; start = page_address(page); length = (PAGE_SIZE << compound_order(page)); end = start + length; remainder = length % s->size; if (!remainder) return 1; fault = check_bytes(end - remainder, POISON_INUSE, remainder); if (!fault) return 1; while (end > fault && end[-1] == POISON_INUSE) end--; slab_err(s, page, "Padding overwritten. 0x%p-0x%p", fault, end - 1); print_section("Padding", end - remainder, remainder); restore_bytes(s, "slab padding", POISON_INUSE, end - remainder, end); return 0; } static int check_object(struct kmem_cache *s, struct page *page, void *object, int active) { u8 *p = object; u8 *endobject = object + s->objsize; if (s->flags & SLAB_RED_ZONE) { unsigned int red = active ? SLUB_RED_ACTIVE : SLUB_RED_INACTIVE; if (!check_bytes_and_report(s, page, object, "Redzone", endobject, red, s->inuse - s->objsize)) return 0; } else { if ((s->flags & SLAB_POISON) && s->objsize < s->inuse) { check_bytes_and_report(s, page, p, "Alignment padding", endobject, POISON_INUSE, s->inuse - s->objsize); } } if (s->flags & SLAB_POISON) { if (!active && (s->flags & __OBJECT_POISON) && (!check_bytes_and_report(s, page, p, "Poison", p, POISON_FREE, s->objsize - 1) || !check_bytes_and_report(s, page, p, "Poison", p + s->objsize - 1, POISON_END, 1))) return 0; /* * check_pad_bytes cleans up on its own. */ check_pad_bytes(s, page, p); } if (!s->offset && active) /* * Object and freepointer overlap. Cannot check * freepointer while object is allocated. */ return 1; /* Check free pointer validity */ if (!check_valid_pointer(s, page, get_freepointer(s, p))) { object_err(s, page, p, "Freepointer corrupt"); /* * No choice but to zap it and thus lose the remainder * of the free objects in this slab. May cause * another error because the object count is now wrong. */ set_freepointer(s, p, NULL); return 0; } return 1; } static int check_slab(struct kmem_cache *s, struct page *page) { int maxobj; VM_BUG_ON(!irqs_disabled()); if (!PageSlab(page)) { slab_err(s, page, "Not a valid slab page"); return 0; } maxobj = (PAGE_SIZE << compound_order(page)) / s->size; if (page->objects > maxobj) { slab_err(s, page, "objects %u > max %u", s->name, page->objects, maxobj); return 0; } if (page->inuse > page->objects) { slab_err(s, page, "inuse %u > max %u", s->name, page->inuse, page->objects); return 0; } /* Slab_pad_check fixes things up after itself */ slab_pad_check(s, page); return 1; } /* * Determine if a certain object on a page is on the freelist. Must hold the * slab lock to guarantee that the chains are in a consistent state. */ static int on_freelist(struct kmem_cache *s, struct page *page, void *search) { int nr = 0; void *fp = page->freelist; void *object = NULL; unsigned long max_objects; while (fp && nr <= page->objects) { if (fp == search) return 1; if (!check_valid_pointer(s, page, fp)) { if (object) { object_err(s, page, object, "Freechain corrupt"); set_freepointer(s, object, NULL); break; } else { slab_err(s, page, "Freepointer corrupt"); page->freelist = NULL; page->inuse = page->objects; slab_fix(s, "Freelist cleared"); return 0; } break; } object = fp; fp = get_freepointer(s, object); nr++; } max_objects = (PAGE_SIZE << compound_order(page)) / s->size; if (max_objects > MAX_OBJS_PER_PAGE) max_objects = MAX_OBJS_PER_PAGE; if (page->objects != max_objects) { slab_err(s, page, "Wrong number of objects. Found %d but " "should be %d", page->objects, max_objects); page->objects = max_objects; slab_fix(s, "Number of objects adjusted."); } if (page->inuse != page->objects - nr) { slab_err(s, page, "Wrong object count. Counter is %d but " "counted were %d", page->inuse, page->objects - nr); page->inuse = page->objects - nr; slab_fix(s, "Object count adjusted."); } return search == NULL; } static void trace(struct kmem_cache *s, struct page *page, void *object, int alloc) { if (s->flags & SLAB_TRACE) { printk(KERN_INFO "TRACE %s %s 0x%p inuse=%d fp=0x%p\n", s->name, alloc ? "alloc" : "free", object, page->inuse, page->freelist); if (!alloc) print_section("Object", (void *)object, s->objsize); dump_stack(); } } /* * Tracking of fully allocated slabs for debugging purposes. */ static void add_full(struct kmem_cache_node *n, struct page *page) { spin_lock(&n->list_lock); list_add(&page->lru, &n->full); spin_unlock(&n->list_lock); } static void remove_full(struct kmem_cache *s, struct page *page) { struct kmem_cache_node *n; if (!(s->flags & SLAB_STORE_USER)) return; n = get_node(s, page_to_nid(page)); spin_lock(&n->list_lock); list_del(&page->lru); spin_unlock(&n->list_lock); } /* Tracking of the number of slabs for debugging purposes */ static inline unsigned long slabs_node(struct kmem_cache *s, int node) { struct kmem_cache_node *n = get_node(s, node); return atomic_long_read(&n->nr_slabs); } static inline unsigned long node_nr_slabs(struct kmem_cache_node *n) { return atomic_long_read(&n->nr_slabs); } static inline void inc_slabs_node(struct kmem_cache *s, int node, int objects) { struct kmem_cache_node *n = get_node(s, node); /* * May be called early in order to allocate a slab for the * kmem_cache_node structure. Solve the chicken-egg * dilemma by deferring the increment of the count during * bootstrap (see early_kmem_cache_node_alloc). */ if (!NUMA_BUILD || n) { atomic_long_inc(&n->nr_slabs); atomic_long_add(objects, &n->total_objects); } } static inline void dec_slabs_node(struct kmem_cache *s, int node, int objects) { struct kmem_cache_node *n = get_node(s, node); atomic_long_dec(&n->nr_slabs); atomic_long_sub(objects, &n->total_objects); } /* Object debug checks for alloc/free paths */ static void setup_object_debug(struct kmem_cache *s, struct page *page, void *object) { if (!(s->flags & (SLAB_STORE_USER|SLAB_RED_ZONE|__OBJECT_POISON))) return; init_object(s, object, 0); init_tracking(s, object); } static int alloc_debug_processing(struct kmem_cache *s, struct page *page, void *object, unsigned long addr) { if (!check_slab(s, page)) goto bad; if (!on_freelist(s, page, object)) { object_err(s, page, object, "Object already allocated"); goto bad; } if (!check_valid_pointer(s, page, object)) { object_err(s, page, object, "Freelist Pointer check fails"); goto bad; } if (!check_object(s, page, object, 0)) goto bad; /* Success perform special debug activities for allocs */ if (s->flags & SLAB_STORE_USER) set_track(s, object, TRACK_ALLOC, addr); trace(s, page, object, 1); init_object(s, object, 1); return 1; bad: if (PageSlab(page)) { /* * If this is a slab page then lets do the best we can * to avoid issues in the future. Marking all objects * as used avoids touching the remaining objects. */ slab_fix(s, "Marking all objects used"); page->inuse = page->objects; page->freelist = NULL; } return 0; } static int free_debug_processing(struct kmem_cache *s, struct page *page, void *object, unsigned long addr) { if (!check_slab(s, page)) goto fail; if (!check_valid_pointer(s, page, object)) { slab_err(s, page, "Invalid object pointer 0x%p", object); goto fail; } if (on_freelist(s, page, object)) { object_err(s, page, object, "Object already free"); goto fail; } if (!check_object(s, page, object, 1)) return 0; if (unlikely(s != page->slab)) { if (!PageSlab(page)) { slab_err(s, page, "Attempt to free object(0x%p) " "outside of slab", object); } else if (!page->slab) { printk(KERN_ERR "SLUB : no slab for object 0x%p.\n", object); dump_stack(); } else object_err(s, page, object, "page slab pointer corrupt."); goto fail; } /* Special debug activities for freeing objects */ if (!PageSlubFrozen(page) && !page->freelist) remove_full(s, page); if (s->flags & SLAB_STORE_USER) set_track(s, object, TRACK_FREE, addr); trace(s, page, object, 0); init_object(s, object, 0); return 1; fail: slab_fix(s, "Object at 0x%p not freed", object); return 0; } static int __init setup_slub_debug(char *str) { slub_debug = DEBUG_DEFAULT_FLAGS; if (*str++ != '=' || !*str) /* * No options specified. Switch on full debugging. */ goto out; if (*str == ',') /* * No options but restriction on slabs. This means full * debugging for slabs matching a pattern. */ goto check_slabs; if (tolower(*str) == 'o') { /* * Avoid enabling debugging on caches if its minimum order * would increase as a result. */ disable_higher_order_debug = 1; goto out; } slub_debug = 0; if (*str == '-') /* * Switch off all debugging measures. */ goto out; /* * Determine which debug features should be switched on */ for (; *str && *str != ','; str++) { switch (tolower(*str)) { case 'f': slub_debug |= SLAB_DEBUG_FREE; break; case 'z': slub_debug |= SLAB_RED_ZONE; break; case 'p': slub_debug |= SLAB_POISON; break; case 'u': slub_debug |= SLAB_STORE_USER; break; case 't': slub_debug |= SLAB_TRACE; break; default: printk(KERN_ERR "slub_debug option '%c' " "unknown. skipped\n", *str); } } check_slabs: if (*str == ',') slub_debug_slabs = str + 1; out: return 1; } __setup("slub_debug", setup_slub_debug); static unsigned long kmem_cache_flags(unsigned long objsize, unsigned long flags, const char *name, void (*ctor)(void *)) { /* * Enable debugging if selected on the kernel commandline. */ if (slub_debug && (!slub_debug_slabs || !strncmp(slub_debug_slabs, name, strlen(slub_debug_slabs)))) flags |= slub_debug; return flags; } #else static inline void setup_object_debug(struct kmem_cache *s, struct page *page, void *object) {} static inline int alloc_debug_processing(struct kmem_cache *s, struct page *page, void *object, unsigned long addr) { return 0; } static inline int free_debug_processing(struct kmem_cache *s, struct page *page, void *object, unsigned long addr) { return 0; } static inline int slab_pad_check(struct kmem_cache *s, struct page *page) { return 1; } static inline int check_object(struct kmem_cache *s, struct page *page, void *object, int active) { return 1; } static inline void add_full(struct kmem_cache_node *n, struct page *page) {} static inline unsigned long kmem_cache_flags(unsigned long objsize, unsigned long flags, const char *name, void (*ctor)(void *)) { return flags; } #define slub_debug 0 #define disable_higher_order_debug 0 static inline unsigned long slabs_node(struct kmem_cache *s, int node) { return 0; } static inline unsigned long node_nr_slabs(struct kmem_cache_node *n) { return 0; } static inline void inc_slabs_node(struct kmem_cache *s, int node, int objects) {} static inline void dec_slabs_node(struct kmem_cache *s, int node, int objects) {} #endif /* * Slab allocation and freeing */ static inline struct page *alloc_slab_page(gfp_t flags, int node, struct kmem_cache_order_objects oo) { int order = oo_order(oo); flags |= __GFP_NOTRACK; if (node == -1) return alloc_pages(flags, order); else return alloc_pages_node(node, flags, order); } static struct page *allocate_slab(struct kmem_cache *s, gfp_t flags, int node) { struct page *page; struct kmem_cache_order_objects oo = s->oo; gfp_t alloc_gfp; flags |= s->allocflags; /* * Let the initial higher-order allocation fail under memory pressure * so we fall-back to the minimum order allocation. */ alloc_gfp = (flags | __GFP_NOWARN | __GFP_NORETRY) & ~__GFP_NOFAIL; page = alloc_slab_page(alloc_gfp, node, oo); if (unlikely(!page)) { oo = s->min; /* * Allocation may have failed due to fragmentation. * Try a lower order alloc if possible */ page = alloc_slab_page(flags, node, oo); if (!page) return NULL; stat(get_cpu_slab(s, raw_smp_processor_id()), ORDER_FALLBACK); } if (kmemcheck_enabled && !(s->flags & (SLAB_NOTRACK | DEBUG_DEFAULT_FLAGS))) { int pages = 1 << oo_order(oo); kmemcheck_alloc_shadow(page, oo_order(oo), flags, node); /* * Objects from caches that have a constructor don't get * cleared when they're allocated, so we need to do it here. */ if (s->ctor) kmemcheck_mark_uninitialized_pages(page, pages); else kmemcheck_mark_unallocated_pages(page, pages); } page->objects = oo_objects(oo); mod_zone_page_state(page_zone(page), (s->flags & SLAB_RECLAIM_ACCOUNT) ? NR_SLAB_RECLAIMABLE : NR_SLAB_UNRECLAIMABLE, 1 << oo_order(oo)); return page; } static void setup_object(struct kmem_cache *s, struct page *page, void *object) { setup_object_debug(s, page, object); if (unlikely(s->ctor)) s->ctor(object); } static struct page *new_slab(struct kmem_cache *s, gfp_t flags, int node) { struct page *page; void *start; void *last; void *p; BUG_ON(flags & GFP_SLAB_BUG_MASK); page = allocate_slab(s, flags & (GFP_RECLAIM_MASK | GFP_CONSTRAINT_MASK), node); if (!page) goto out; inc_slabs_node(s, page_to_nid(page), page->objects); page->slab = s; page->flags |= 1 << PG_slab; if (s->flags & (SLAB_DEBUG_FREE | SLAB_RED_ZONE | SLAB_POISON | SLAB_STORE_USER | SLAB_TRACE)) __SetPageSlubDebug(page); start = page_address(page); if (unlikely(s->flags & SLAB_POISON)) memset(start, POISON_INUSE, PAGE_SIZE << compound_order(page)); last = start; for_each_object(p, s, start, page->objects) { setup_object(s, page, last); set_freepointer(s, last, p); last = p; } setup_object(s, page, last); set_freepointer(s, last, NULL); page->freelist = start; page->inuse = 0; out: return page; } static void __free_slab(struct kmem_cache *s, struct page *page) { int order = compound_order(page); int pages = 1 << order; if (unlikely(SLABDEBUG && PageSlubDebug(page))) { void *p; slab_pad_check(s, page); for_each_object(p, s, page_address(page), page->objects) check_object(s, page, p, 0); __ClearPageSlubDebug(page); } kmemcheck_free_shadow(page, compound_order(page)); mod_zone_page_state(page_zone(page), (s->flags & SLAB_RECLAIM_ACCOUNT) ? NR_SLAB_RECLAIMABLE : NR_SLAB_UNRECLAIMABLE, -pages); __ClearPageSlab(page); reset_page_mapcount(page); if (current->reclaim_state) current->reclaim_state->reclaimed_slab += pages; __free_pages(page, order); } static void rcu_free_slab(struct rcu_head *h) { struct page *page; page = container_of((struct list_head *)h, struct page, lru); __free_slab(page->slab, page); } static void free_slab(struct kmem_cache *s, struct page *page) { if (unlikely(s->flags & SLAB_DESTROY_BY_RCU)) { /* * RCU free overloads the RCU head over the LRU */ struct rcu_head *head = (void *)&page->lru; call_rcu(head, rcu_free_slab); } else __free_slab(s, page); } static void discard_slab(struct kmem_cache *s, struct page *page) { dec_slabs_node(s, page_to_nid(page), page->objects); free_slab(s, page); } /* * Per slab locking using the pagelock */ static __always_inline void slab_lock(struct page *page) { bit_spin_lock(PG_locked, &page->flags); } static __always_inline void slab_unlock(struct page *page) { __bit_spin_unlock(PG_locked, &page->flags); } static __always_inline int slab_trylock(struct page *page) { int rc = 1; rc = bit_spin_trylock(PG_locked, &page->flags); return rc; } /* * Management of partially allocated slabs */ static void add_partial(struct kmem_cache_node *n, struct page *page, int tail) { spin_lock(&n->list_lock); n->nr_partial++; if (tail) list_add_tail(&page->lru, &n->partial); else list_add(&page->lru, &n->partial); spin_unlock(&n->list_lock); } static void remove_partial(struct kmem_cache *s, struct page *page) { struct kmem_cache_node *n = get_node(s, page_to_nid(page)); spin_lock(&n->list_lock); list_del(&page->lru); n->nr_partial--; spin_unlock(&n->list_lock); } /* * Lock slab and remove from the partial list. * * Must hold list_lock. */ static inline int lock_and_freeze_slab(struct kmem_cache_node *n, struct page *page) { if (slab_trylock(page)) { list_del(&page->lru); n->nr_partial--; __SetPageSlubFrozen(page); return 1; } return 0; } /* * Try to allocate a partial slab from a specific node. */ static struct page *get_partial_node(struct kmem_cache_node *n) { struct page *page; /* * Racy check. If we mistakenly see no partial slabs then we * just allocate an empty slab. If we mistakenly try to get a * partial slab and there is none available then get_partials() * will return NULL. */ if (!n || !n->nr_partial) return NULL; spin_lock(&n->list_lock); list_for_each_entry(page, &n->partial, lru) if (lock_and_freeze_slab(n, page)) goto out; page = NULL; out: spin_unlock(&n->list_lock); return page; } /* * Get a page from somewhere. Search in increasing NUMA distances. */ static struct page *get_any_partial(struct kmem_cache *s, gfp_t flags) { #ifdef CONFIG_NUMA struct zonelist *zonelist; struct zoneref *z; struct zone *zone; enum zone_type high_zoneidx = gfp_zone(flags); struct page *page; /* * The defrag ratio allows a configuration of the tradeoffs between * inter node defragmentation and node local allocations. A lower * defrag_ratio increases the tendency to do local allocations * instead of attempting to obtain partial slabs from other nodes. * * If the defrag_ratio is set to 0 then kmalloc() always * returns node local objects. If the ratio is higher then kmalloc() * may return off node objects because partial slabs are obtained * from other nodes and filled up. * * If /sys/kernel/slab/xx/defrag_ratio is set to 100 (which makes * defrag_ratio = 1000) then every (well almost) allocation will * first attempt to defrag slab caches on other nodes. This means * scanning over all nodes to look for partial slabs which may be * expensive if we do it every time we are trying to find a slab * with available objects. */ if (!s->remote_node_defrag_ratio || get_cycles() % 1024 > s->remote_node_defrag_ratio) return NULL; zonelist = node_zonelist(slab_node(current->mempolicy), flags); for_each_zone_zonelist(zone, z, zonelist, high_zoneidx) { struct kmem_cache_node *n; n = get_node(s, zone_to_nid(zone)); if (n && cpuset_zone_allowed_hardwall(zone, flags) && n->nr_partial > s->min_partial) { page = get_partial_node(n); if (page) return page; } } #endif return NULL; } /* * Get a partial page, lock it and return it. */ static struct page *get_partial(struct kmem_cache *s, gfp_t flags, int node) { struct page *page; int searchnode = (node == -1) ? numa_node_id() : node; page = get_partial_node(get_node(s, searchnode)); if (page || (flags & __GFP_THISNODE)) return page; return get_any_partial(s, flags); } /* * Move a page back to the lists. * * Must be called with the slab lock held. * * On exit the slab lock will have been dropped. */ static void unfreeze_slab(struct kmem_cache *s, struct page *page, int tail) { struct kmem_cache_node *n = get_node(s, page_to_nid(page)); struct kmem_cache_cpu *c = get_cpu_slab(s, smp_processor_id()); __ClearPageSlubFrozen(page); if (page->inuse) { if (page->freelist) { add_partial(n, page, tail); stat(c, tail ? DEACTIVATE_TO_TAIL : DEACTIVATE_TO_HEAD); } else { stat(c, DEACTIVATE_FULL); if (SLABDEBUG && PageSlubDebug(page) && (s->flags & SLAB_STORE_USER)) add_full(n, page); } slab_unlock(page); } else { stat(c, DEACTIVATE_EMPTY); if (n->nr_partial < s->min_partial) { /* * Adding an empty slab to the partial slabs in order * to avoid page allocator overhead. This slab needs * to come after the other slabs with objects in * so that the others get filled first. That way the * size of the partial list stays small. * * kmem_cache_shrink can reclaim any empty slabs from * the partial list. */ add_partial(n, page, 1); slab_unlock(page); } else { slab_unlock(page); stat(get_cpu_slab(s, raw_smp_processor_id()), FREE_SLAB); discard_slab(s, page); } } } /* * Remove the cpu slab */ static void deactivate_slab(struct kmem_cache *s, struct kmem_cache_cpu *c) { struct page *page = c->page; int tail = 1; if (page->freelist) stat(c, DEACTIVATE_REMOTE_FREES); /* * Merge cpu freelist into slab freelist. Typically we get here * because both freelists are empty. So this is unlikely * to occur. */ while (unlikely(c->freelist)) { void **object; tail = 0; /* Hot objects. Put the slab first */ /* Retrieve object from cpu_freelist */ object = c->freelist; c->freelist = c->freelist[c->offset]; /* And put onto the regular freelist */ object[c->offset] = page->freelist; page->freelist = object; page->inuse--; } c->page = NULL; unfreeze_slab(s, page, tail); } static inline void flush_slab(struct kmem_cache *s, struct kmem_cache_cpu *c) { stat(c, CPUSLAB_FLUSH); slab_lock(c->page); deactivate_slab(s, c); } /* * Flush cpu slab. * * Called from IPI handler with interrupts disabled. */ static inline void __flush_cpu_slab(struct kmem_cache *s, int cpu) { struct kmem_cache_cpu *c = get_cpu_slab(s, cpu); if (likely(c && c->page)) flush_slab(s, c); } static void flush_cpu_slab(void *d) { struct kmem_cache *s = d; __flush_cpu_slab(s, smp_processor_id()); } static void flush_all(struct kmem_cache *s) { on_each_cpu(flush_cpu_slab, s, 1); } /* * Check if the objects in a per cpu structure fit numa * locality expectations. */ static inline int node_match(struct kmem_cache_cpu *c, int node) { #ifdef CONFIG_NUMA if (node != -1 && c->node != node) return 0; #endif return 1; } static int count_free(struct page *page) { return page->objects - page->inuse; } static unsigned long count_partial(struct kmem_cache_node *n, int (*get_count)(struct page *)) { unsigned long flags; unsigned long x = 0; struct page *page; spin_lock_irqsave(&n->list_lock, flags); list_for_each_entry(page, &n->partial, lru) x += get_count(page); spin_unlock_irqrestore(&n->list_lock, flags); return x; } static inline unsigned long node_nr_objs(struct kmem_cache_node *n) { #ifdef CONFIG_SLUB_DEBUG return atomic_long_read(&n->total_objects); #else return 0; #endif } static noinline void slab_out_of_memory(struct kmem_cache *s, gfp_t gfpflags, int nid) { int node; printk(KERN_WARNING "SLUB: Unable to allocate memory on node %d (gfp=0x%x)\n", nid, gfpflags); printk(KERN_WARNING " cache: %s, object size: %d, buffer size: %d, " "default order: %d, min order: %d\n", s->name, s->objsize, s->size, oo_order(s->oo), oo_order(s->min)); if (oo_order(s->min) > get_order(s->objsize)) printk(KERN_WARNING " %s debugging increased min order, use " "slub_debug=O to disable.\n", s->name); for_each_online_node(node) { struct kmem_cache_node *n = get_node(s, node); unsigned long nr_slabs; unsigned long nr_objs; unsigned long nr_free; if (!n) continue; nr_free = count_partial(n, count_free); nr_slabs = node_nr_slabs(n); nr_objs = node_nr_objs(n); printk(KERN_WARNING " node %d: slabs: %ld, objs: %ld, free: %ld\n", node, nr_slabs, nr_objs, nr_free); } } /* * Slow path. The lockless freelist is empty or we need to perform * debugging duties. * * Interrupts are disabled. * * Processing is still very fast if new objects have been freed to the * regular freelist. In that case we simply take over the regular freelist * as the lockless freelist and zap the regular freelist. * * If that is not working then we fall back to the partial lists. We take the * first element of the freelist as the object to allocate now and move the * rest of the freelist to the lockless freelist. * * And if we were unable to get a new slab from the partial slab lists then * we need to allocate a new slab. This is the slowest path since it involves * a call to the page allocator and the setup of a new slab. */ static void *__slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node, unsigned long addr, struct kmem_cache_cpu *c) { void **object; struct page *new; /* We handle __GFP_ZERO in the caller */ gfpflags &= ~__GFP_ZERO; if (!c->page) goto new_slab; slab_lock(c->page); if (unlikely(!node_match(c, node))) goto another_slab; stat(c, ALLOC_REFILL); load_freelist: object = c->page->freelist; if (unlikely(!object)) goto another_slab; if (unlikely(SLABDEBUG && PageSlubDebug(c->page))) goto debug; c->freelist = object[c->offset]; c->page->inuse = c->page->objects; c->page->freelist = NULL; c->node = page_to_nid(c->page); unlock_out: slab_unlock(c->page); stat(c, ALLOC_SLOWPATH); return object; another_slab: deactivate_slab(s, c); new_slab: new = get_partial(s, gfpflags, node); if (new) { c->page = new; stat(c, ALLOC_FROM_PARTIAL); goto load_freelist; } if (gfpflags & __GFP_WAIT) local_irq_enable(); new = new_slab(s, gfpflags, node); if (gfpflags & __GFP_WAIT) local_irq_disable(); if (new) { c = get_cpu_slab(s, smp_processor_id()); stat(c, ALLOC_SLAB); if (c->page) flush_slab(s, c); slab_lock(new); __SetPageSlubFrozen(new); c->page = new; goto load_freelist; } if (!(gfpflags & __GFP_NOWARN) && printk_ratelimit()) slab_out_of_memory(s, gfpflags, node); return NULL; debug: if (!alloc_debug_processing(s, c->page, object, addr)) goto another_slab; c->page->inuse++; c->page->freelist = object[c->offset]; c->node = -1; goto unlock_out; } /* * Inlined fastpath so that allocation functions (kmalloc, kmem_cache_alloc) * have the fastpath folded into their functions. So no function call * overhead for requests that can be satisfied on the fastpath. * * The fastpath works by first checking if the lockless freelist can be used. * If not then __slab_alloc is called for slow processing. * * Otherwise we can simply pick the next object from the lockless free list. */ static __always_inline void *slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node, unsigned long addr) { void **object; struct kmem_cache_cpu *c; unsigned long flags; unsigned int objsize; gfpflags &= gfp_allowed_mask; lockdep_trace_alloc(gfpflags); might_sleep_if(gfpflags & __GFP_WAIT); if (should_failslab(s->objsize, gfpflags)) return NULL; local_irq_save(flags); c = get_cpu_slab(s, smp_processor_id()); objsize = c->objsize; if (unlikely(!c->freelist || !node_match(c, node))) object = __slab_alloc(s, gfpflags, node, addr, c); else { object = c->freelist; c->freelist = object[c->offset]; stat(c, ALLOC_FASTPATH); } local_irq_restore(flags); if (unlikely((gfpflags & __GFP_ZERO) && object)) memset(object, 0, objsize); kmemcheck_slab_alloc(s, gfpflags, object, c->objsize); kmemleak_alloc_recursive(object, objsize, 1, s->flags, gfpflags); return object; } void *kmem_cache_alloc(struct kmem_cache *s, gfp_t gfpflags) { void *ret = slab_alloc(s, gfpflags, -1, _RET_IP_); trace_kmem_cache_alloc(_RET_IP_, ret, s->objsize, s->size, gfpflags); return ret; } EXPORT_SYMBOL(kmem_cache_alloc); #ifdef CONFIG_KMEMTRACE void *kmem_cache_alloc_notrace(struct kmem_cache *s, gfp_t gfpflags) { return slab_alloc(s, gfpflags, -1, _RET_IP_); } EXPORT_SYMBOL(kmem_cache_alloc_notrace); #endif #ifdef CONFIG_NUMA void *kmem_cache_alloc_node(struct kmem_cache *s, gfp_t gfpflags, int node) { void *ret = slab_alloc(s, gfpflags, node, _RET_IP_); trace_kmem_cache_alloc_node(_RET_IP_, ret, s->objsize, s->size, gfpflags, node); return ret; } EXPORT_SYMBOL(kmem_cache_alloc_node); #endif #ifdef CONFIG_KMEMTRACE void *kmem_cache_alloc_node_notrace(struct kmem_cache *s, gfp_t gfpflags, int node) { return slab_alloc(s, gfpflags, node, _RET_IP_); } EXPORT_SYMBOL(kmem_cache_alloc_node_notrace); #endif /* * Slow patch handling. This may still be called frequently since objects * have a longer lifetime than the cpu slabs in most processing loads. * * So we still attempt to reduce cache line usage. Just take the slab * lock and free the item. If there is no additional partial page * handling required then we can return immediately. */ static void __slab_free(struct kmem_cache *s, struct page *page, void *x, unsigned long addr, unsigned int offset) { void *prior; void **object = (void *)x; struct kmem_cache_cpu *c; c = get_cpu_slab(s, raw_smp_processor_id()); stat(c, FREE_SLOWPATH); slab_lock(page); if (unlikely(SLABDEBUG && PageSlubDebug(page))) goto debug; checks_ok: prior = object[offset] = page->freelist; page->freelist = object; page->inuse--; if (unlikely(PageSlubFrozen(page))) { stat(c, FREE_FROZEN); goto out_unlock; } if (unlikely(!page->inuse)) goto slab_empty; /* * Objects left in the slab. If it was not on the partial list before * then add it. */ if (unlikely(!prior)) { add_partial(get_node(s, page_to_nid(page)), page, 1); stat(c, FREE_ADD_PARTIAL); } out_unlock: slab_unlock(page); return; slab_empty: if (prior) { /* * Slab still on the partial list. */ remove_partial(s, page); stat(c, FREE_REMOVE_PARTIAL); } slab_unlock(page); stat(c, FREE_SLAB); discard_slab(s, page); return; debug: if (!free_debug_processing(s, page, x, addr)) goto out_unlock; goto checks_ok; } /* * Fastpath with forced inlining to produce a kfree and kmem_cache_free that * can perform fastpath freeing without additional function calls. * * The fastpath is only possible if we are freeing to the current cpu slab * of this processor. This typically the case if we have just allocated * the item before. * * If fastpath is not possible then fall back to __slab_free where we deal * with all sorts of special processing. */ static __always_inline void slab_free(struct kmem_cache *s, struct page *page, void *x, unsigned long addr) { void **object = (void *)x; struct kmem_cache_cpu *c; unsigned long flags; kmemleak_free_recursive(x, s->flags); local_irq_save(flags); c = get_cpu_slab(s, smp_processor_id()); kmemcheck_slab_free(s, object, c->objsize); debug_check_no_locks_freed(object, c->objsize); if (!(s->flags & SLAB_DEBUG_OBJECTS)) debug_check_no_obj_freed(object, c->objsize); if (likely(page == c->page && c->node >= 0)) { object[c->offset] = c->freelist; c->freelist = object; stat(c, FREE_FASTPATH); } else __slab_free(s, page, x, addr, c->offset); local_irq_restore(flags); } void kmem_cache_free(struct kmem_cache *s, void *x) { struct page *page; page = virt_to_head_page(x); slab_free(s, page, x, _RET_IP_); trace_kmem_cache_free(_RET_IP_, x); } EXPORT_SYMBOL(kmem_cache_free); /* Figure out on which slab page the object resides */ static struct page *get_object_page(const void *x) { struct page *page = virt_to_head_page(x); if (!PageSlab(page)) return NULL; return page; } /* * Object placement in a slab is made very easy because we always start at * offset 0. If we tune the size of the object to the alignment then we can * get the required alignment by putting one properly sized object after * another. * * Notice that the allocation order determines the sizes of the per cpu * caches. Each processor has always one slab available for allocations. * Increasing the allocation order reduces the number of times that slabs * must be moved on and off the partial lists and is therefore a factor in * locking overhead. */ /* * Mininum / Maximum order of slab pages. This influences locking overhead * and slab fragmentation. A higher order reduces the number of partial slabs * and increases the number of allocations possible without having to * take the list_lock. */ static int slub_min_order; static int slub_max_order = PAGE_ALLOC_COSTLY_ORDER; static int slub_min_objects; /* * Merge control. If this is set then no merging of slab caches will occur. * (Could be removed. This was introduced to pacify the merge skeptics.) */ static int slub_nomerge; /* * Calculate the order of allocation given an slab object size. * * The order of allocation has significant impact on performance and other * system components. Generally order 0 allocations should be preferred since * order 0 does not cause fragmentation in the page allocator. Larger objects * be problematic to put into order 0 slabs because there may be too much * unused space left. We go to a higher order if more than 1/16th of the slab * would be wasted. * * In order to reach satisfactory performance we must ensure that a minimum * number of objects is in one slab. Otherwise we may generate too much * activity on the partial lists which requires taking the list_lock. This is * less a concern for large slabs though which are rarely used. * * slub_max_order specifies the order where we begin to stop considering the * number of objects in a slab as critical. If we reach slub_max_order then * we try to keep the page order as low as possible. So we accept more waste * of space in favor of a small page order. * * Higher order allocations also allow the placement of more objects in a * slab and thereby reduce object handling overhead. If the user has * requested a higher mininum order then we start with that one instead of * the smallest order which will fit the object. */ static inline int slab_order(int size, int min_objects, int max_order, int fract_leftover) { int order; int rem; int min_order = slub_min_order; if ((PAGE_SIZE << min_order) / size > MAX_OBJS_PER_PAGE) return get_order(size * MAX_OBJS_PER_PAGE) - 1; for (order = max(min_order, fls(min_objects * size - 1) - PAGE_SHIFT); order <= max_order; order++) { unsigned long slab_size = PAGE_SIZE << order; if (slab_size < min_objects * size) continue; rem = slab_size % size; if (rem <= slab_size / fract_leftover) break; } return order; } static inline int calculate_order(int size) { int order; int min_objects; int fraction; int max_objects; /* * Attempt to find best configuration for a slab. This * works by first attempting to generate a layout with * the best configuration and backing off gradually. * * First we reduce the acceptable waste in a slab. Then * we reduce the minimum objects required in a slab. */ min_objects = slub_min_objects; if (!min_objects) min_objects = 4 * (fls(nr_cpu_ids) + 1); max_objects = (PAGE_SIZE << slub_max_order)/size; min_objects = min(min_objects, max_objects); while (min_objects > 1) { fraction = 16; while (fraction >= 4) { order = slab_order(size, min_objects, slub_max_order, fraction); if (order <= slub_max_order) return order; fraction /= 2; } min_objects--; } /* * We were unable to place multiple objects in a slab. Now * lets see if we can place a single object there. */ order = slab_order(size, 1, slub_max_order, 1); if (order <= slub_max_order) return order; /* * Doh this slab cannot be placed using slub_max_order. */ order = slab_order(size, 1, MAX_ORDER, 1); if (order < MAX_ORDER) return order; return -ENOSYS; } /* * Figure out what the alignment of the objects will be. */ static unsigned long calculate_alignment(unsigned long flags, unsigned long align, unsigned long size) { /* * If the user wants hardware cache aligned objects then follow that * suggestion if the object is sufficiently large. * * The hardware cache alignment cannot override the specified * alignment though. If that is greater then use it. */ if (flags & SLAB_HWCACHE_ALIGN) { unsigned long ralign = cache_line_size(); while (size <= ralign / 2) ralign /= 2; align = max(align, ralign); } if (align < ARCH_SLAB_MINALIGN) align = ARCH_SLAB_MINALIGN; return ALIGN(align, sizeof(void *)); } static void init_kmem_cache_cpu(struct kmem_cache *s, struct kmem_cache_cpu *c) { c->page = NULL; c->freelist = NULL; c->node = 0; c->offset = s->offset / sizeof(void *); c->objsize = s->objsize; #ifdef CONFIG_SLUB_STATS memset(c->stat, 0, NR_SLUB_STAT_ITEMS * sizeof(unsigned)); #endif } static void init_kmem_cache_node(struct kmem_cache_node *n, struct kmem_cache *s) { n->nr_partial = 0; spin_lock_init(&n->list_lock); INIT_LIST_HEAD(&n->partial); #ifdef CONFIG_SLUB_DEBUG atomic_long_set(&n->nr_slabs, 0); atomic_long_set(&n->total_objects, 0); INIT_LIST_HEAD(&n->full); #endif } #ifdef CONFIG_SMP /* * Per cpu array for per cpu structures. * * The per cpu array places all kmem_cache_cpu structures from one processor * close together meaning that it becomes possible that multiple per cpu * structures are contained in one cacheline. This may be particularly * beneficial for the kmalloc caches. * * A desktop system typically has around 60-80 slabs. With 100 here we are * likely able to get per cpu structures for all caches from the array defined * here. We must be able to cover all kmalloc caches during bootstrap. * * If the per cpu array is exhausted then fall back to kmalloc * of individual cachelines. No sharing is possible then. */ #define NR_KMEM_CACHE_CPU 100 static DEFINE_PER_CPU(struct kmem_cache_cpu [NR_KMEM_CACHE_CPU], kmem_cache_cpu); static DEFINE_PER_CPU(struct kmem_cache_cpu *, kmem_cache_cpu_free); static DECLARE_BITMAP(kmem_cach_cpu_free_init_once, CONFIG_NR_CPUS); static struct kmem_cache_cpu *alloc_kmem_cache_cpu(struct kmem_cache *s, int cpu, gfp_t flags) { struct kmem_cache_cpu *c = per_cpu(kmem_cache_cpu_free, cpu); if (c) per_cpu(kmem_cache_cpu_free, cpu) = (void *)c->freelist; else { /* Table overflow: So allocate ourselves */ c = kmalloc_node( ALIGN(sizeof(struct kmem_cache_cpu), cache_line_size()), flags, cpu_to_node(cpu)); if (!c) return NULL; } init_kmem_cache_cpu(s, c); return c; } static void free_kmem_cache_cpu(struct kmem_cache_cpu *c, int cpu) { if (c < per_cpu(kmem_cache_cpu, cpu) || c >= per_cpu(kmem_cache_cpu, cpu) + NR_KMEM_CACHE_CPU) { kfree(c); return; } c->freelist = (void *)per_cpu(kmem_cache_cpu_free, cpu); per_cpu(kmem_cache_cpu_free, cpu) = c; } static void free_kmem_cache_cpus(struct kmem_cache *s) { int cpu; for_each_online_cpu(cpu) { struct kmem_cache_cpu *c = get_cpu_slab(s, cpu); if (c) { s->cpu_slab[cpu] = NULL; free_kmem_cache_cpu(c, cpu); } } } static int alloc_kmem_cache_cpus(struct kmem_cache *s, gfp_t flags) { int cpu; for_each_online_cpu(cpu) { struct kmem_cache_cpu *c = get_cpu_slab(s, cpu); if (c) continue; c = alloc_kmem_cache_cpu(s, cpu, flags); if (!c) { free_kmem_cache_cpus(s); return 0; } s->cpu_slab[cpu] = c; } return 1; } /* * Initialize the per cpu array. */ static void init_alloc_cpu_cpu(int cpu) { int i; if (cpumask_test_cpu(cpu, to_cpumask(kmem_cach_cpu_free_init_once))) return; for (i = NR_KMEM_CACHE_CPU - 1; i >= 0; i--) free_kmem_cache_cpu(&per_cpu(kmem_cache_cpu, cpu)[i], cpu); cpumask_set_cpu(cpu, to_cpumask(kmem_cach_cpu_free_init_once)); } static void __init init_alloc_cpu(void) { int cpu; for_each_online_cpu(cpu) init_alloc_cpu_cpu(cpu); } #else static inline void free_kmem_cache_cpus(struct kmem_cache *s) {} static inline void init_alloc_cpu(void) {} static inline int alloc_kmem_cache_cpus(struct kmem_cache *s, gfp_t flags) { init_kmem_cache_cpu(s, &s->cpu_slab); return 1; } #endif #ifdef CONFIG_NUMA /* * No kmalloc_node yet so do it by hand. We know that this is the first * slab on the node for this slabcache. There are no concurrent accesses * possible. * * Note that this function only works on the kmalloc_node_cache * when allocating for the kmalloc_node_cache. This is used for bootstrapping * memory on a fresh node that has no slab structures yet. */ static void early_kmem_cache_node_alloc(gfp_t gfpflags, int node) { struct page *page; struct kmem_cache_node *n; unsigned long flags; BUG_ON(kmalloc_caches->size < sizeof(struct kmem_cache_node)); page = new_slab(kmalloc_caches, gfpflags, node); BUG_ON(!page); if (page_to_nid(page) != node) { printk(KERN_ERR "SLUB: Unable to allocate memory from " "node %d\n", node); printk(KERN_ERR "SLUB: Allocating a useless per node structure " "in order to be able to continue\n"); } n = page->freelist; BUG_ON(!n); page->freelist = get_freepointer(kmalloc_caches, n); page->inuse++; kmalloc_caches->node[node] = n; #ifdef CONFIG_SLUB_DEBUG init_object(kmalloc_caches, n, 1); init_tracking(kmalloc_caches, n); #endif init_kmem_cache_node(n, kmalloc_caches); inc_slabs_node(kmalloc_caches, node, page->objects); /* * lockdep requires consistent irq usage for each lock * so even though there cannot be a race this early in * the boot sequence, we still disable irqs. */ local_irq_save(flags); add_partial(n, page, 0); local_irq_restore(flags); } static void free_kmem_cache_nodes(struct kmem_cache *s) { int node; for_each_node_state(node, N_NORMAL_MEMORY) { struct kmem_cache_node *n = s->node[node]; if (n && n != &s->local_node) kmem_cache_free(kmalloc_caches, n); s->node[node] = NULL; } } static int init_kmem_cache_nodes(struct kmem_cache *s, gfp_t gfpflags) { int node; int local_node; if (slab_state >= UP) local_node = page_to_nid(virt_to_page(s)); else local_node = 0; for_each_node_state(node, N_NORMAL_MEMORY) { struct kmem_cache_node *n; if (local_node == node) n = &s->local_node; else { if (slab_state == DOWN) { early_kmem_cache_node_alloc(gfpflags, node); continue; } n = kmem_cache_alloc_node(kmalloc_caches, gfpflags, node); if (!n) { free_kmem_cache_nodes(s); return 0; } } s->node[node] = n; init_kmem_cache_node(n, s); } return 1; } #else static void free_kmem_cache_nodes(struct kmem_cache *s) { } static int init_kmem_cache_nodes(struct kmem_cache *s, gfp_t gfpflags) { init_kmem_cache_node(&s->local_node, s); return 1; } #endif static void set_min_partial(struct kmem_cache *s, unsigned long min) { if (min < MIN_PARTIAL) min = MIN_PARTIAL; else if (min > MAX_PARTIAL) min = MAX_PARTIAL; s->min_partial = min; } /* * calculate_sizes() determines the order and the distribution of data within * a slab object. */ static int calculate_sizes(struct kmem_cache *s, int forced_order) { unsigned long flags = s->flags; unsigned long size = s->objsize; unsigned long align = s->align; int order; /* * Round up object size to the next word boundary. We can only * place the free pointer at word boundaries and this determines * the possible location of the free pointer. */ size = ALIGN(size, sizeof(void *)); #ifdef CONFIG_SLUB_DEBUG /* * Determine if we can poison the object itself. If the user of * the slab may touch the object after free or before allocation * then we should never poison the object itself. */ if ((flags & SLAB_POISON) && !(flags & SLAB_DESTROY_BY_RCU) && !s->ctor) s->flags |= __OBJECT_POISON; else s->flags &= ~__OBJECT_POISON; /* * If we are Redzoning then check if there is some space between the * end of the object and the free pointer. If not then add an * additional word to have some bytes to store Redzone information. */ if ((flags & SLAB_RED_ZONE) && size == s->objsize) size += sizeof(void *); #endif /* * With that we have determined the number of bytes in actual use * by the object. This is the potential offset to the free pointer. */ s->inuse = size; if (((flags & (SLAB_DESTROY_BY_RCU | SLAB_POISON)) || s->ctor)) { /* * Relocate free pointer after the object if it is not * permitted to overwrite the first word of the object on * kmem_cache_free. * * This is the case if we do RCU, have a constructor or * destructor or are poisoning the objects. */ s->offset = size; size += sizeof(void *); } #ifdef CONFIG_SLUB_DEBUG if (flags & SLAB_STORE_USER) /* * Need to store information about allocs and frees after * the object. */ size += 2 * sizeof(struct track); if (flags & SLAB_RED_ZONE) /* * Add some empty padding so that we can catch * overwrites from earlier objects rather than let * tracking information or the free pointer be * corrupted if a user writes before the start * of the object. */ size += sizeof(void *); #endif /* * Determine the alignment based on various parameters that the * user specified and the dynamic determination of cache line size * on bootup. */ align = calculate_alignment(flags, align, s->objsize); s->align = align; /* * SLUB stores one object immediately after another beginning from * offset 0. In order to align the objects we have to simply size * each object to conform to the alignment. */ size = ALIGN(size, align); s->size = size; if (forced_order >= 0) order = forced_order; else order = calculate_order(size); if (order < 0) return 0; s->allocflags = 0; if (order) s->allocflags |= __GFP_COMP; if (s->flags & SLAB_CACHE_DMA) s->allocflags |= SLUB_DMA; if (s->flags & SLAB_RECLAIM_ACCOUNT) s->allocflags |= __GFP_RECLAIMABLE; /* * Determine the number of objects per slab */ s->oo = oo_make(order, size); s->min = oo_make(get_order(size), size); if (oo_objects(s->oo) > oo_objects(s->max)) s->max = s->oo; return !!oo_objects(s->oo); } static int kmem_cache_open(struct kmem_cache *s, gfp_t gfpflags, const char *name, size_t size, size_t align, unsigned long flags, void (*ctor)(void *)) { memset(s, 0, kmem_size); s->name = name; s->ctor = ctor; s->objsize = size; s->align = align; s->flags = kmem_cache_flags(size, flags, name, ctor); if (!calculate_sizes(s, -1)) goto error; if (disable_higher_order_debug) { /* * Disable debugging flags that store metadata if the min slab * order increased. */ if (get_order(s->size) > get_order(s->objsize)) { s->flags &= ~DEBUG_METADATA_FLAGS; s->offset = 0; if (!calculate_sizes(s, -1)) goto error; } } /* * The larger the object size is, the more pages we want on the partial * list to avoid pounding the page allocator excessively. */ set_min_partial(s, ilog2(s->size)); s->refcount = 1; #ifdef CONFIG_NUMA s->remote_node_defrag_ratio = 1000; #endif if (!init_kmem_cache_nodes(s, gfpflags & ~SLUB_DMA)) goto error; if (alloc_kmem_cache_cpus(s, gfpflags & ~SLUB_DMA)) return 1; free_kmem_cache_nodes(s); error: if (flags & SLAB_PANIC) panic("Cannot create slab %s size=%lu realsize=%u " "order=%u offset=%u flags=%lx\n", s->name, (unsigned long)size, s->size, oo_order(s->oo), s->offset, flags); return 0; } /* * Check if a given pointer is valid */ int kmem_ptr_validate(struct kmem_cache *s, const void *object) { struct page *page; page = get_object_page(object); if (!page || s != page->slab) /* No slab or wrong slab */ return 0; if (!check_valid_pointer(s, page, object)) return 0; /* * We could also check if the object is on the slabs freelist. * But this would be too expensive and it seems that the main * purpose of kmem_ptr_valid() is to check if the object belongs * to a certain slab. */ return 1; } EXPORT_SYMBOL(kmem_ptr_validate); /* * Determine the size of a slab object */ unsigned int kmem_cache_size(struct kmem_cache *s) { return s->objsize; } EXPORT_SYMBOL(kmem_cache_size); const char *kmem_cache_name(struct kmem_cache *s) { return s->name; } EXPORT_SYMBOL(kmem_cache_name); static void list_slab_objects(struct kmem_cache *s, struct page *page, const char *text) { #ifdef CONFIG_SLUB_DEBUG