diff options
Diffstat (limited to 'lib')
41 files changed, 1892 insertions, 418 deletions
diff --git a/lib/842/842_debugfs.h b/lib/842/842_debugfs.h index 277e403e8701..4469407c3e0d 100644 --- a/lib/842/842_debugfs.h +++ b/lib/842/842_debugfs.h @@ -22,8 +22,6 @@ static int __init sw842_debugfs_create(void) return -ENODEV; sw842_debugfs_root = debugfs_create_dir(MODULE_NAME, NULL); - if (IS_ERR(sw842_debugfs_root)) - return PTR_ERR(sw842_debugfs_root); for (i = 0; i < ARRAY_SIZE(template_count); i++) { char name[32]; @@ -46,8 +44,7 @@ static int __init sw842_debugfs_create(void) static void __exit sw842_debugfs_remove(void) { - if (sw842_debugfs_root && !IS_ERR(sw842_debugfs_root)) - debugfs_remove_recursive(sw842_debugfs_root); + debugfs_remove_recursive(sw842_debugfs_root); } #endif diff --git a/lib/Kconfig b/lib/Kconfig index 78ddb9526b62..52a7b2e6fb74 100644 --- a/lib/Kconfig +++ b/lib/Kconfig @@ -584,6 +584,11 @@ config OID_REGISTRY config UCS2_STRING tristate +# +# generic vdso +# +source "lib/vdso/Kconfig" + source "lib/fonts/Kconfig" config SG_SPLIT diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index cbdfae379896..4ac4ca21a30a 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -305,19 +305,26 @@ config DEBUG_FS If unsure, say N. -config HEADERS_CHECK - bool "Run 'make headers_check' when building vmlinux" +config HEADERS_INSTALL + bool "Install uapi headers to usr/include" depends on !UML help - This option will extract the user-visible kernel headers whenever - building the kernel, and will run basic sanity checks on them to - ensure that exported files do not attempt to include files which - were not exported, etc. + This option will install uapi headers (headers exported to user-space) + into the usr/include directory for use during the kernel build. + This is unneeded for building the kernel itself, but needed for some + user-space program samples. It is also needed by some features such + as uapi header sanity checks. + +config HEADERS_CHECK + bool "Run sanity checks on uapi headers when building 'all'" + depends on HEADERS_INSTALL + help + This option will run basic sanity checks on uapi headers when + building the 'all' target, for example, ensure that they do not + attempt to include files which were not exported, etc. If you're making modifications to header files which are - relevant for userspace, say 'Y', and check the headers - exported to $(INSTALL_HDR_PATH) (usually 'usr/include' in - your build tree), to make sure they're suitable. + relevant for userspace, say 'Y'. config OPTIMIZE_INLINING bool "Allow compiler to uninline functions marked 'inline'" @@ -1095,7 +1102,7 @@ config PROVE_LOCKING select DEBUG_SPINLOCK select DEBUG_MUTEXES select DEBUG_RT_MUTEXES if RT_MUTEXES - select DEBUG_RWSEMS if RWSEM_SPIN_ON_OWNER + select DEBUG_RWSEMS select DEBUG_WW_MUTEX_SLOWPATH select DEBUG_LOCK_ALLOC select TRACE_IRQFLAGS @@ -1199,10 +1206,10 @@ config DEBUG_WW_MUTEX_SLOWPATH config DEBUG_RWSEMS bool "RW Semaphore debugging: basic checks" - depends on DEBUG_KERNEL && RWSEM_SPIN_ON_OWNER + depends on DEBUG_KERNEL help - This debugging feature allows mismatched rw semaphore locks and unlocks - to be detected and reported. + This debugging feature allows mismatched rw semaphore locks + and unlocks to be detected and reported. config DEBUG_LOCK_ALLOC bool "Lock debugging: detect incorrect freeing of live locks" @@ -1701,7 +1708,7 @@ config LKDTM called lkdtm. Documentation on how to use the module can be found in - Documentation/fault-injection/provoke-crashes.txt + Documentation/fault-injection/provoke-crashes.rst config TEST_LIST_SORT tristate "Linked list sorting test" @@ -1754,6 +1761,18 @@ config RBTREE_TEST A benchmark measuring the performance of the rbtree library. Also includes rbtree invariant checks. +config REED_SOLOMON_TEST + tristate "Reed-Solomon library test" + depends on DEBUG_KERNEL || m + select REED_SOLOMON + select REED_SOLOMON_ENC16 + select REED_SOLOMON_DEC16 + help + This option enables the self-test function of rslib at boot, + or at module load time. + + If unsure, say N. + config INTERVAL_TREE_TEST tristate "Interval tree test" depends on DEBUG_KERNEL @@ -1858,6 +1877,14 @@ config TEST_PARMAN If unsure, say N. +config TEST_IRQ_TIMINGS + bool "IRQ timings selftest" + depends on IRQ_TIMINGS + help + Enable this option to test the irq timings code on boot. + + If unsure, say N. + config TEST_LKM tristate "Test module loading with 'hello world' module" depends on m @@ -1909,6 +1936,15 @@ config TEST_BPF If unsure, say N. +config TEST_BLACKHOLE_DEV + tristate "Test blackhole netdev functionality" + depends on m && NET + help + This builds the "test_blackhole_dev" module that validates the + data path through this blackhole netdev. + + If unsure, say N. + config FIND_BIT_BENCHMARK tristate "Test find_bit functions" help diff --git a/lib/Makefile b/lib/Makefile index dcb558c7554d..fdd56bc219b8 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -91,6 +91,7 @@ obj-$(CONFIG_TEST_DEBUG_VIRTUAL) += test_debug_virtual.o obj-$(CONFIG_TEST_MEMCAT_P) += test_memcat_p.o obj-$(CONFIG_TEST_OBJAGG) += test_objagg.o obj-$(CONFIG_TEST_STACKINIT) += test_stackinit.o +obj-$(CONFIG_TEST_BLACKHOLE_DEV) += test_blackhole_dev.o obj-$(CONFIG_TEST_LIVEPATCH) += livepatch/ @@ -102,7 +103,7 @@ endif obj-$(CONFIG_DEBUG_INFO_REDUCED) += debug_info.o CFLAGS_debug_info.o += $(call cc-option, -femit-struct-debug-detailed=any) -obj-y += math/ +obj-y += math/ crypto/ obj-$(CONFIG_GENERIC_IOMAP) += iomap.o obj-$(CONFIG_GENERIC_PCI_IOMAP) += pci_iomap.o diff --git a/lib/atomic64.c b/lib/atomic64.c index 7e6905751522..e98c85a99787 100644 --- a/lib/atomic64.c +++ b/lib/atomic64.c @@ -42,11 +42,11 @@ static inline raw_spinlock_t *lock_addr(const atomic64_t *v) return &atomic64_lock[addr & (NR_LOCKS - 1)].lock; } -long long atomic64_read(const atomic64_t *v) +s64 atomic64_read(const atomic64_t *v) { unsigned long flags; raw_spinlock_t *lock = lock_addr(v); - long long val; + s64 val; raw_spin_lock_irqsave(lock, flags); val = v->counter; @@ -55,7 +55,7 @@ long long atomic64_read(const atomic64_t *v) } EXPORT_SYMBOL(atomic64_read); -void atomic64_set(atomic64_t *v, long long i) +void atomic64_set(atomic64_t *v, s64 i) { unsigned long flags; raw_spinlock_t *lock = lock_addr(v); @@ -67,7 +67,7 @@ void atomic64_set(atomic64_t *v, long long i) EXPORT_SYMBOL(atomic64_set); #define ATOMIC64_OP(op, c_op) \ -void atomic64_##op(long long a, atomic64_t *v) \ +void atomic64_##op(s64 a, atomic64_t *v) \ { \ unsigned long flags; \ raw_spinlock_t *lock = lock_addr(v); \ @@ -79,11 +79,11 @@ void atomic64_##op(long long a, atomic64_t *v) \ EXPORT_SYMBOL(atomic64_##op); #define ATOMIC64_OP_RETURN(op, c_op) \ -long long atomic64_##op##_return(long long a, atomic64_t *v) \ +s64 atomic64_##op##_return(s64 a, atomic64_t *v) \ { \ unsigned long flags; \ raw_spinlock_t *lock = lock_addr(v); \ - long long val; \ + s64 val; \ \ raw_spin_lock_irqsave(lock, flags); \ val = (v->counter c_op a); \ @@ -93,11 +93,11 @@ long long atomic64_##op##_return(long long a, atomic64_t *v) \ EXPORT_SYMBOL(atomic64_##op##_return); #define ATOMIC64_FETCH_OP(op, c_op) \ -long long atomic64_fetch_##op(long long a, atomic64_t *v) \ +s64 atomic64_fetch_##op(s64 a, atomic64_t *v) \ { \ unsigned long flags; \ raw_spinlock_t *lock = lock_addr(v); \ - long long val; \ + s64 val; \ \ raw_spin_lock_irqsave(lock, flags); \ val = v->counter; \ @@ -130,11 +130,11 @@ ATOMIC64_OPS(xor, ^=) #undef ATOMIC64_OP_RETURN #undef ATOMIC64_OP -long long atomic64_dec_if_positive(atomic64_t *v) +s64 atomic64_dec_if_positive(atomic64_t *v) { unsigned long flags; raw_spinlock_t *lock = lock_addr(v); - long long val; + s64 val; raw_spin_lock_irqsave(lock, flags); val = v->counter - 1; @@ -145,11 +145,11 @@ long long atomic64_dec_if_positive(atomic64_t *v) } EXPORT_SYMBOL(atomic64_dec_if_positive); -long long atomic64_cmpxchg(atomic64_t *v, long long o, long long n) +s64 atomic64_cmpxchg(atomic64_t *v, s64 o, s64 n) { unsigned long flags; raw_spinlock_t *lock = lock_addr(v); - long long val; + s64 val; raw_spin_lock_irqsave(lock, flags); val = v->counter; @@ -160,11 +160,11 @@ long long atomic64_cmpxchg(atomic64_t *v, long long o, long long n) } EXPORT_SYMBOL(atomic64_cmpxchg); -long long atomic64_xchg(atomic64_t *v, long long new) +s64 atomic64_xchg(atomic64_t *v, s64 new) { unsigned long flags; raw_spinlock_t *lock = lock_addr(v); - long long val; + s64 val; raw_spin_lock_irqsave(lock, flags); val = v->counter; @@ -174,11 +174,11 @@ long long atomic64_xchg(atomic64_t *v, long long new) } EXPORT_SYMBOL(atomic64_xchg); -long long atomic64_fetch_add_unless(atomic64_t *v, long long a, long long u) +s64 atomic64_fetch_add_unless(atomic64_t *v, s64 a, s64 u) { unsigned long flags; raw_spinlock_t *lock = lock_addr(v); - long long val; + s64 val; raw_spin_lock_irqsave(lock, flags); val = v->counter; diff --git a/lib/crypto/Makefile b/lib/crypto/Makefile new file mode 100644 index 000000000000..88195c34932d --- /dev/null +++ b/lib/crypto/Makefile @@ -0,0 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0 + +obj-$(CONFIG_CRYPTO_LIB_ARC4) += libarc4.o +libarc4-y := arc4.o diff --git a/lib/crypto/arc4.c b/lib/crypto/arc4.c new file mode 100644 index 000000000000..c2020f19c652 --- /dev/null +++ b/lib/crypto/arc4.c @@ -0,0 +1,74 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Cryptographic API + * + * ARC4 Cipher Algorithm + * + * Jon Oberheide <jon@oberheide.org> + */ + +#include <crypto/arc4.h> +#include <linux/module.h> + +int arc4_setkey(struct arc4_ctx *ctx, const u8 *in_key, unsigned int key_len) +{ + int i, j = 0, k = 0; + + ctx->x = 1; + ctx->y = 0; + + for (i = 0; i < 256; i++) + ctx->S[i] = i; + + for (i = 0; i < 256; i++) { + u32 a = ctx->S[i]; + + j = (j + in_key[k] + a) & 0xff; + ctx->S[i] = ctx->S[j]; + ctx->S[j] = a; + if (++k >= key_len) + k = 0; + } + + return 0; +} +EXPORT_SYMBOL(arc4_setkey); + +void arc4_crypt(struct arc4_ctx *ctx, u8 *out, const u8 *in, unsigned int len) +{ + u32 *const S = ctx->S; + u32 x, y, a, b; + u32 ty, ta, tb; + + if (len == 0) + return; + + x = ctx->x; + y = ctx->y; + + a = S[x]; + y = (y + a) & 0xff; + b = S[y]; + + do { + S[y] = a; + a = (a + b) & 0xff; + S[x] = b; + x = (x + 1) & 0xff; + ta = S[x]; + ty = (y + ta) & 0xff; + tb = S[ty]; + *out++ = *in++ ^ S[a]; + if (--len == 0) + break; + y = ty; + a = ta; + b = tb; + } while (true); + + ctx->x = x; + ctx->y = y; +} +EXPORT_SYMBOL(arc4_crypt); + +MODULE_LICENSE("GPL"); diff --git a/lib/debugobjects.c b/lib/debugobjects.c index 55437fd5128b..61261195f5b6 100644 --- a/lib/debugobjects.c +++ b/lib/debugobjects.c @@ -25,16 +25,37 @@ #define ODEBUG_POOL_SIZE 1024 #define ODEBUG_POOL_MIN_LEVEL 256 +#define ODEBUG_POOL_PERCPU_SIZE 64 +#define ODEBUG_BATCH_SIZE 16 #define ODEBUG_CHUNK_SHIFT PAGE_SHIFT #define ODEBUG_CHUNK_SIZE (1 << ODEBUG_CHUNK_SHIFT) #define ODEBUG_CHUNK_MASK (~(ODEBUG_CHUNK_SIZE - 1)) +/* + * We limit the freeing of debug objects via workqueue at a maximum + * frequency of 10Hz and about 1024 objects for each freeing operation. + * So it is freeing at most 10k debug objects per second. + */ +#define ODEBUG_FREE_WORK_MAX 1024 +#define ODEBUG_FREE_WORK_DELAY DIV_ROUND_UP(HZ, 10) + struct debug_bucket { struct hlist_head list; raw_spinlock_t lock; }; +/* + * Debug object percpu free list + * Access is protected by disabling irq + */ +struct debug_percpu_free { + struct hlist_head free_objs; + int obj_free; +}; + +static DEFINE_PER_CPU(struct debug_percpu_free, percpu_obj_pool); + static struct debug_bucket obj_hash[ODEBUG_HASH_SIZE]; static struct debug_obj obj_static_pool[ODEBUG_POOL_SIZE] __initdata; @@ -44,13 +65,20 @@ static DEFINE_RAW_SPINLOCK(pool_lock); static HLIST_HEAD(obj_pool); static HLIST_HEAD(obj_to_free); +/* + * Because of the presence of percpu free pools, obj_pool_free will + * under-count those in the percpu free pools. Similarly, obj_pool_used + * will over-count those in the percpu free pools. Adjustments will be + * made at debug_stats_show(). Both obj_pool_min_free and obj_pool_max_used + * can be off. + */ static int obj_pool_min_free = ODEBUG_POOL_SIZE; static int obj_pool_free = ODEBUG_POOL_SIZE; static int obj_pool_used; static int obj_pool_max_used; +static bool obj_freeing; /* The number of objs on the global free list */ static int obj_nr_tofree; -static struct kmem_cache *obj_cache; static int debug_objects_maxchain __read_mostly; static int __maybe_unused debug_objects_maxchecked __read_mostly; @@ -63,6 +91,7 @@ static int debug_objects_pool_size __read_mostly static int debug_objects_pool_min_level __read_mostly = ODEBUG_POOL_MIN_LEVEL; static struct debug_obj_descr *descr_test __read_mostly; +static struct kmem_cache *obj_cache __read_mostly; /* * Track numbers of kmem_cache_alloc()/free() calls done. @@ -71,7 +100,7 @@ static int debug_objects_allocated; static int debug_objects_freed; static void free_obj_work(struct work_struct *work); -static DECLARE_WORK(debug_obj_work, free_obj_work); +static DECLARE_DELAYED_WORK(debug_obj_work, free_obj_work); static int __init enable_object_debug(char *str) { @@ -100,7 +129,7 @@ static const char *obj_states[ODEBUG_STATE_MAX] = { static void fill_pool(void) { gfp_t gfp = GFP_ATOMIC | __GFP_NORETRY | __GFP_NOWARN; - struct debug_obj *new, *obj; + struct debug_obj *obj; unsigned long flags; if (likely(obj_pool_free >= debug_objects_pool_min_level)) @@ -116,7 +145,7 @@ static void fill_pool(void) * Recheck with the lock held as the worker thread might have * won the race and freed the global free list already. */ - if (obj_nr_tofree) { + while (obj_nr_tofree && (obj_pool_free < obj_pool_min_free)) { obj = hlist_entry(obj_to_free.first, typeof(*obj), node); hlist_del(&obj->node); obj_nr_tofree--; @@ -130,15 +159,23 @@ static void fill_pool(void) return; while (obj_pool_free < debug_objects_pool_min_level) { + struct debug_obj *new[ODEBUG_BATCH_SIZE]; + int cnt; - new = kmem_cache_zalloc(obj_cache, gfp); - if (!new) + for (cnt = 0; cnt < ODEBUG_BATCH_SIZE; cnt++) { + new[cnt] = kmem_cache_zalloc(obj_cache, gfp); + if (!new[cnt]) + break; + } + if (!cnt) return; raw_spin_lock_irqsave(&pool_lock, flags); - hlist_add_head(&new->node, &obj_pool); - debug_objects_allocated++; - obj_pool_free++; + while (cnt) { + hlist_add_head(&new[--cnt]->node, &obj_pool); + debug_objects_allocated++; + obj_pool_free++; + } raw_spin_unlock_irqrestore(&pool_lock, flags); } } @@ -163,36 +200,81 @@ static struct debug_obj *lookup_object(void *addr, struct debug_bucket *b) } /* + * Allocate a new object from the hlist + */ +static struct debug_obj *__alloc_object(struct hlist_head *list) +{ + struct debug_obj *obj = NULL; + + if (list->first) { + obj = hlist_entry(list->first, typeof(*obj), node); + hlist_del(&obj->node); + } + + return obj; +} + +/* * Allocate a new object. If the pool is empty, switch off the debugger. * Must be called with interrupts disabled. */ static struct debug_obj * alloc_object(void *addr, struct debug_bucket *b, struct debug_obj_descr *descr) { - struct debug_obj *obj = NULL; + struct debug_percpu_free *percpu_pool = this_cpu_ptr(&percpu_obj_pool); + struct debug_obj *obj; - raw_spin_lock(&pool_lock); - if (obj_pool.first) { - obj = hlist_entry(obj_pool.first, typeof(*obj), node); + if (likely(obj_cache)) { + obj = __alloc_object(&percpu_pool->free_objs); + if (obj) { + percpu_pool->obj_free--; + goto init_obj; + } + } - obj->object = addr; - obj->descr = descr; - obj->state = ODEBUG_STATE_NONE; - obj->astate = 0; - hlist_del(&obj->node); + raw_spin_lock(&pool_lock); + obj = __alloc_object(&obj_pool); + if (obj) { + obj_pool_used++; + obj_pool_free--; - hlist_add_head(&obj->node, &b->list); + /* + * Looking ahead, allocate one batch of debug objects and + * put them into the percpu free pool. + */ + if (likely(obj_cache)) { + int i; + + for (i = 0; i < ODEBUG_BATCH_SIZE; i++) { + struct debug_obj *obj2; + + obj2 = __alloc_object(&obj_pool); + if (!obj2) + break; + hlist_add_head(&obj2->node, + &percpu_pool->free_objs); + percpu_pool->obj_free++; + obj_pool_used++; + obj_pool_free--; + } + } - obj_pool_used++; if (obj_pool_used > obj_pool_max_used) obj_pool_max_used = obj_pool_used; - obj_pool_free--; if (obj_pool_free < obj_pool_min_free) obj_pool_min_free = obj_pool_free; } raw_spin_unlock(&pool_lock); +init_obj: + if (obj) { + obj->object = addr; + obj->descr = descr; + obj->state = ODEBUG_STATE_NONE; + obj->astate = 0; + hlist_add_head(&obj->node, &b->list); + } return obj; } @@ -209,13 +291,19 @@ static void free_obj_work(struct work_struct *work) unsigned long flags; HLIST_HEAD(tofree); + WRITE_ONCE(obj_freeing, false); if (!raw_spin_trylock_irqsave(&pool_lock, flags)) return; + if (obj_pool_free >= debug_objects_pool_size) + goto free_objs; + /* * The objs on the pool list might be allocated before the work is * run, so recheck if pool list it full or not, if not fill pool - * list from the global free list + * list from the global free list. As it is likely that a workload + * may be gearing up to use more and more objects, don't free any + * of them until the next round. */ while (obj_nr_tofree && obj_pool_free < debug_objects_pool_size) { obj = hlist_entry(obj_to_free.first, typeof(*obj), node); @@ -224,7 +312,10 @@ static void free_obj_work(struct work_struct *work) obj_pool_free++; obj_nr_tofree--; } + raw_spin_unlock_irqrestore(&pool_lock, flags); + return; +free_objs: /* * Pool list is already full and there are still objs on the free * list. Move remaining free objs to a temporary list to free the @@ -243,24 +334,86 @@ static void free_obj_work(struct work_struct *work) } } -static bool __free_object(struct debug_obj *obj) +static void __free_object(struct debug_obj *obj) { + struct debug_obj *objs[ODEBUG_BATCH_SIZE]; + struct debug_percpu_free *percpu_pool; + int lookahead_count = 0; unsigned long flags; bool work; - raw_spin_lock_irqsave(&pool_lock, flags); - work = (obj_pool_free > debug_objects_pool_size) && obj_cache; + local_irq_save(flags); + if (!obj_cache) + goto free_to_obj_pool; + + /* + * Try to free it into the percpu pool first. + */ + percpu_pool = this_cpu_ptr(&percpu_obj_pool); + if (percpu_pool->obj_free < ODEBUG_POOL_PERCPU_SIZE) { + hlist_add_head(&obj->node, &percpu_pool->free_objs); + percpu_pool->obj_free++; + local_irq_restore(flags); + return; + } + + /* + * As the percpu pool is full, look ahead and pull out a batch + * of objects from the percpu pool and free them as well. + */ + for (; lookahead_count < ODEBUG_BATCH_SIZE; lookahead_count++) { + objs[lookahead_count] = __alloc_object(&percpu_pool->free_objs); + if (!objs[lookahead_count]) + break; + percpu_pool->obj_free--; + } + +free_to_obj_pool: + raw_spin_lock(&pool_lock); + work = (obj_pool_free > debug_objects_pool_size) && obj_cache && + (obj_nr_tofree < ODEBUG_FREE_WORK_MAX); obj_pool_used--; if (work) { obj_nr_tofree++; hlist_add_head(&obj->node, &obj_to_free); + if (lookahead_count) { + obj_nr_tofree += lookahead_count; + obj_pool_used -= lookahead_count; + while (lookahead_count) { + hlist_add_head(&objs[--lookahead_count]->node, + &obj_to_free); + } + } + + if ((obj_pool_free > debug_objects_pool_size) && + (obj_nr_tofree < ODEBUG_FREE_WORK_MAX)) { + int i; + + /* + * Free one more batch of objects from obj_pool. + */ + for (i = 0; i < ODEBUG_BATCH_SIZE; i++) { + obj = __alloc_object(&obj_pool); + hlist_add_head(&obj->node, &obj_to_free); + obj_pool_free--; + obj_nr_tofree++; + } + } } else { obj_pool_free++; hlist_add_head(&obj->node, &obj_pool); + if (lookahead_count) { + obj_pool_free += lookahead_count; + obj_pool_used -= lookahead_count; + while (lookahead_count) { + hlist_add_head(&objs[--lookahead_count]->node, + &obj_pool); + } + } } - raw_spin_unlock_irqrestore(&pool_lock, flags); - return work; + raw_spin_unlock(&pool_lock); + local_irq_restore(flags); } /* @@ -269,8 +422,11 @@ static bool __free_object(struct debug_obj *obj) */ static void free_object(struct debug_obj *obj) { - if (__free_object(obj)) - schedule_work(&debug_obj_work); + __free_object(obj); + if (!obj_freeing && obj_nr_tofree) { + WRITE_ONCE(obj_freeing, true); + schedule_delayed_work(&debug_obj_work, ODEBUG_FREE_WORK_DELAY); + } } /* @@ -372,6 +528,7 @@ static void __debug_object_init(void *addr, struct debug_obj_descr *descr, int onstack) { enum debug_obj_state state; + bool check_stack = false; struct debug_bucket *db; struct debug_obj *obj; unsigned long flags; @@ -391,7 +548,7 @@ __debug_object_init(void *addr, struct debug_obj_descr *descr, int onstack) debug_objects_oom(); return; } - debug_object_is_on_stack(addr, onstack); + check_stack = true; } switch (obj->state) { @@ -402,20 +559,23 @@ __debug_object_init(void *addr, struct debug_obj_descr *descr, int onstack) break; case ODEBUG_STATE_ACTIVE: - debug_print_object(obj, "init"); state = obj->state; raw_spin_unlock_irqrestore(&db->lock, flags); + debug_print_object(obj, "init"); debug_object_fixup(descr->fixup_init, addr, state); return; case ODEBUG_STATE_DESTROYED: + raw_spin_unlock_irqrestore(&db->lock, flags); debug_print_object(obj, "init"); - break; + return; default: break; } raw_spin_unlock_irqrestore(&db->lock, flags); + if (check_stack) + debug_object_is_on_stack(addr, onstack); } /** @@ -473,6 +633,8 @@ int debug_object_activate(void *addr, struct debug_obj_descr *descr) obj = lookup_object(addr, db); if (obj) { + bool print_object = false; + switch (obj->state) { case ODEBUG_STATE_INIT: case ODEBUG_STATE_INACTIVE: @@ -481,14 +643,14 @@ int debug_object_activate(void *addr, struct debug_obj_descr *descr) break; case ODEBUG_STATE_ACTIVE: - debug_print_object(obj, "activate"); state = obj->state; raw_spin_unlock_irqrestore(&db->lock, flags); + debug_print_object(obj, "activate"); ret = debug_object_fixup(descr->fixup_activate, addr, state); return ret ? 0 : -EINVAL; case ODEBUG_STATE_DESTROYED: - debug_print_object(obj, "activate"); + print_object = true; ret = -EINVAL; break; default: @@ -496,10 +658,13 @@ int debug_object_activate(void *addr, struct debug_obj_descr *descr) break; } raw_spin_unlock_irqrestore(&db->lock, flags); + if (print_object) + debug_print_object(obj, "activate"); return ret; } raw_spin_unlock_irqrestore(&db->lock, flags); + /* * We are here when a static object is activated. We * let the type specific code confirm whether this is @@ -531,6 +696,7 @@ void debug_object_deactivate(void *addr, struct debug_obj_descr *descr) struct debug_bucket *db; struct debug_obj *obj; unsigned long flags; + bool print_object = false; if (!debug_objects_enabled) return; @@ -548,24 +714,27 @@ void debug_object_deactivate(void *addr, struct debug_obj_descr *descr) if (!obj->astate) obj->state = ODEBUG_STATE_INACTIVE; else - debug_print_object(obj, "deactivate"); + print_object = true; break; case ODEBUG_STATE_DESTROYED: - debug_print_object(obj, "deactivate"); + print_object = true; break; default: break; } - } else { + } + + raw_spin_unlock_irqrestore(&db->lock, flags); + if (!obj) { struct debug_obj o = { .object = addr, .state = ODEBUG_STATE_NOTAVAILABLE, .descr = descr }; debug_print_object(&o, "deactivate"); + } else if (print_object) { + debug_print_object(obj, "deactivate"); } - - raw_spin_unlock_irqrestore(&db->lock, flags); } EXPORT_SYMBOL_GPL(debug_object_deactivate); @@ -580,6 +749,7 @@ void debug_object_destroy(void *addr, struct debug_obj_descr *descr) struct debug_bucket *db; struct debug_obj *obj; unsigned long flags; + bool print_object = false; if (!debug_objects_enabled) return; @@ -599,20 +769,22 @@ void debug_object_destroy(void *addr, struct debug_obj_descr *descr) obj->state = ODEBUG_STATE_DESTROYED; break; case ODEBUG_STATE_ACTIVE: - debug_print_object(obj, "destroy"); state = obj->state; raw_spin_unlock_irqrestore(&db->lock, flags); + debug_print_object(obj, "destroy"); debug_object_fixup(descr->fixup_destroy, addr, state); return; case ODEBUG_STATE_DESTROYED: - debug_print_object(obj, "destroy"); + print_object = true; break; default: break; } out_unlock: raw_spin_unlock_irqrestore(&db->lock, flags); + if (print_object) + debug_print_object(obj, "destroy"); } EXPORT_SYMBOL_GPL(debug_object_destroy); @@ -641,9 +813,9 @@ void debug_object_free(void *addr, struct debug_obj_descr *descr) switch (obj->state) { case ODEBUG_STATE_ACTIVE: - debug_print_object(obj, "free"); state = obj->state; raw_spin_unlock_irqrestore(&db->lock, flags); + debug_print_object(obj, "free"); debug_object_fixup(descr->fixup_free, addr, state); return; default: @@ -716,6 +888,7 @@ debug_object_active_state(void *addr, struct debug_obj_descr *descr, struct debug_bucket *db; struct debug_obj *obj; unsigned long flags; + bool print_object = false; if (!debug_objects_enabled) return; @@ -731,22 +904,25 @@ debug_object_active_state(void *addr, struct debug_obj_descr *descr, if (obj->astate == expect) obj->astate = next; else - debug_print_object(obj, "active_state"); + print_object = true; break; default: - debug_print_object(obj, "active_state"); + print_object = true; break; } - } else { + } + + raw_spin_unlock_irqrestore(&db->lock, flags); + if (!obj) { struct debug_obj o = { .object = addr, .state = ODEBUG_STATE_NOTAVAILABLE, .descr = descr }; debug_print_object(&o, "active_state"); + } else if (print_object) { + debug_print_object(obj, "active_state"); } - - raw_spin_unlock_irqrestore(&db->lock, flags); } EXPORT_SYMBOL_GPL(debug_object_active_state); @@ -760,7 +936,6 @@ static void __debug_check_no_obj_freed(const void *address, unsigned long size) struct hlist_node *tmp; struct debug_obj *obj; int cnt, objs_checked = 0; - bool work = false; saddr = (unsigned long) address; eaddr = saddr + size; @@ -782,16 +957,16 @@ repeat: switch (obj->state) { case ODEBUG_STATE_ACTIVE: - debug_print_object(obj, "free"); descr = obj->descr; state = obj->state; raw_spin_unlock_irqrestore(&db->lock, flags); + debug_print_object(obj, "free"); debug_object_fixup(descr->fixup_free, (void *) oaddr, state); goto repeat; default: hlist_del(&obj->node); - work |= __free_object(obj); + __free_object(obj); break; } } @@ -807,8 +982,10 @@ repeat: debug_objects_maxchecked = objs_checked; /* Schedule work to actually kmem_cache_free() objects */ - if (work) - schedule_work(&debug_obj_work); + if (!obj_freeing && obj_nr_tofree) { + WRITE_ONCE(obj_freeing, true); + schedule_delayed_work(&debug_obj_work, ODEBUG_FREE_WORK_DELAY); + } } void debug_check_no_obj_freed(const void *address, unsigned long size) @@ -822,13 +999,19 @@ void debug_check_no_obj_freed(const void *address, unsigned long size) static int debug_stats_show(struct seq_file *m, void *v) { + int cpu, obj_percpu_free = 0; + + for_each_possible_cpu(cpu) + obj_percpu_free += per_cpu(percpu_obj_pool.obj_free, cpu); + seq_printf(m, "max_chain :%d\n", debug_objects_maxchain); seq_printf(m, "max_checked :%d\n", debug_objects_maxchecked); seq_printf(m, "warnings :%d\n", debug_objects_warnings); seq_printf(m, "fixups :%d\n", debug_objects_fixups); - seq_printf(m, "pool_free :%d\n", obj_pool_free); + seq_printf(m, "pool_free :%d\n", obj_pool_free + obj_percpu_free); + seq_printf(m, "pool_pcp_free :%d\n", obj_percpu_free); seq_printf(m, "pool_min_free :%d\n", obj_pool_min_free); - seq_printf(m, "pool_used :%d\n", obj_pool_used); + seq_printf(m, "pool_used :%d\n", obj_pool_used - obj_percpu_free); seq_printf(m, "pool_max_used :%d\n", obj_pool_max_used); seq_printf(m, "on_free_list :%d\n", obj_nr_tofree); seq_printf(m, "objs_allocated:%d\n", debug_objects_allocated); @@ -850,26 +1033,16 @@ static const struct file_operations debug_stats_fops = { static int __init debug_objects_init_debugfs(void) { - struct dentry *dbgdir, *dbgstats; + struct dentry *dbgdir; if (!debug_objects_enabled) return 0; dbgdir = debugfs_create_dir("debug_objects", NULL); - if (!dbgdir) - return -ENOMEM; - dbgstats = debugfs_create_file("stats", 0444, dbgdir, NULL, - &debug_stats_fops); - if (!dbgstats) - goto err; + debugfs_create_file("stats", 0444, dbgdir, NULL, &debug_stats_fops); return 0; - -err: - debugfs_remove(dbgdir); - - return -ENOMEM; } __initcall(debug_objects_init_debugfs); @@ -1175,9 +1348,20 @@ free: */ void __init debug_objects_mem_init(void) { + int cpu, extras; + if (!debug_objects_enabled) return; + /* + * Initialize the percpu object pools + * + * Initialization is not strictly necessary, but was done for + * completeness. + */ + for_each_possible_cpu(cpu) + INIT_HLIST_HEAD(&per_cpu(percpu_obj_pool.free_objs, cpu)); + obj_cache = kmem_cache_create("debug_objects_cache", sizeof (struct debug_obj), 0, SLAB_DEBUG_OBJECTS | SLAB_NOLEAKTRACE, @@ -1194,6 +1378,7 @@ void __init debug_objects_mem_init(void) * Increase the thresholds for allocating and freeing objects * according to the number of possible CPUs available in the system. */ - debug_objects_pool_size += num_possible_cpus() * 32; - debug_objects_pool_min_level += num_possible_cpus() * 4; + extras = num_possible_cpus() * ODEBUG_BATCH_SIZE; + debug_objects_pool_size += extras; + debug_objects_pool_min_level += extras; } diff --git a/lib/devres.c b/lib/devres.c index 69bed2f38306..6a0e9bd6524a 100644 --- a/lib/devres.c +++ b/lib/devres.c @@ -131,7 +131,8 @@ EXPORT_SYMBOL(devm_iounmap); * if (IS_ERR(base)) * return PTR_ERR(base); */ -void __iomem *devm_ioremap_resource(struct device *dev, struct resource *res) +void __iomem *devm_ioremap_resource(struct device *dev, + const struct resource *res) { resource_size_t size; void __iomem *dest_ptr; diff --git a/lib/digsig.c b/lib/digsig.c index 3cf89c775ab2..e0627c3e53b2 100644 --- a/lib/digsig.c +++ b/lib/digsig.c @@ -218,7 +218,7 @@ int digsig_verify(struct key *keyring, const char *sig, int siglen, /* search in specific keyring */ key_ref_t kref; kref = keyring_search(make_key_ref(keyring, 1UL), - &key_type_user, name); + &key_type_user, name, true); if (IS_ERR(kref)) key = ERR_CAST(kref); else diff --git a/lib/dynamic_debug.c b/lib/dynamic_debug.c index 8a16c2d498e9..c60409138e13 100644 --- a/lib/dynamic_debug.c +++ b/lib/dynamic_debug.c @@ -993,20 +993,14 @@ static __initdata int ddebug_init_success; static int __init dynamic_debug_init_debugfs(void) { - struct dentry *dir, *file; + struct dentry *dir; if (!ddebug_init_success) return -ENODEV; dir = debugfs_create_dir("dynamic_debug", NULL); - if (!dir) - return -ENOMEM; - file = debugfs_create_file("control", 0644, dir, NULL, - &ddebug_proc_fops); - if (!file) { - debugfs_remove(dir); - return -ENOMEM; - } + debugfs_create_file("control", 0644, dir, NULL, &ddebug_proc_fops); + return 0; } diff --git a/lib/fault-inject.c b/lib/fault-inject.c index 3cb21b2bf088..8186ca84910b 100644 --- a/lib/fault-inject.c +++ b/lib/fault-inject.c @@ -166,10 +166,10 @@ static int debugfs_ul_get(void *data, u64 *val) DEFINE_SIMPLE_ATTRIBUTE(fops_ul, debugfs_ul_get, debugfs_ul_set, "%llu\n"); -static struct dentry *debugfs_create_ul(const char *name, umode_t mode, - struct dentry *parent, unsigned long *value) +static void debugfs_create_ul(const char *name, umode_t mode, + struct dentry *parent, unsigned long *value) { - return debugfs_create_file(name, mode, parent, value, &fops_ul); + debugfs_create_file(name, mode, parent, value, &fops_ul); } #ifdef CONFIG_FAULT_INJECTION_STACKTRACE_FILTER @@ -185,12 +185,11 @@ static int debugfs_stacktrace_depth_set(void *data, u64 val) DEFINE_SIMPLE_ATTRIBUTE(fops_stacktrace_depth, debugfs_ul_get, debugfs_stacktrace_depth_set, "%llu\n"); -static struct dentry *debugfs_create_stacktrace_depth( - const char *name, umode_t mode, - struct dentry *parent, unsigned long *value) +static void debugfs_create_stacktrace_depth(const char *name, umode_t mode, + struct dentry *parent, + unsigned long *value) { - return debugfs_create_file(name, mode, parent, value, - &fops_stacktrace_depth); + debugfs_create_file(name, mode, parent, value, &fops_stacktrace_depth); } #endif /* CONFIG_FAULT_INJECTION_STACKTRACE_FILTER */ @@ -202,51 +201,31 @@ struct dentry *fault_create_debugfs_attr(const char *name, struct dentry *dir; dir = debugfs_create_dir(name, parent); - if (!dir) - return ERR_PTR(-ENOMEM); - - if (!debugfs_create_ul("probability", mode, dir, &attr->probability)) - goto fail; - if (!debugfs_create_ul("interval", mode, dir, &attr->interval)) - goto fail; - if (!debugfs_create_atomic_t("times", mode, dir, &attr->times)) - goto fail; - if (!debugfs_create_atomic_t("space", mode, dir, &attr->space)) - goto fail; - if (!debugfs_create_ul("verbose", mode, dir, &attr->verbose)) - goto fail; - if (!debugfs_create_u32("verbose_ratelimit_interval_ms", mode, dir, - &attr->ratelimit_state.interval)) - goto fail; - if (!debugfs_create_u32("verbose_ratelimit_burst", mode, dir, - &attr->ratelimit_state.burst)) - goto fail; - if (!debugfs_create_bool("task-filter", mode, dir, &attr->task_filter)) - goto fail; + if (IS_ERR(dir)) + return dir; + + debugfs_create_ul("probability", mode, dir, &attr->probability); + debugfs_create_ul("interval", mode, dir, &attr->interval); + debugfs_create_atomic_t("times", mode, dir, &attr->times); + debugfs_create_atomic_t("space", mode, dir, &attr->space); + debugfs_create_ul("verbose", mode, dir, &attr->verbose); + debugfs_create_u32("verbose_ratelimit_interval_ms", mode, dir, + &attr->ratelimit_state.interval); + debugfs_create_u32("verbose_ratelimit_burst", mode, dir, + &attr->ratelimit_state.burst); + debugfs_create_bool("task-filter", mode, dir, &attr->task_filter); #ifdef CONFIG_FAULT_INJECTION_STACKTRACE_FILTER - - if (!debugfs_create_stacktrace_depth("stacktrace-depth", mode, dir, - &attr->stacktrace_depth)) - goto fail; - if (!debugfs_create_ul("require-start", mode, dir, - &attr->require_start)) - goto fail; - if (!debugfs_create_ul("require-end", mode, dir, &attr->require_end)) - goto fail; - if (!debugfs_create_ul("reject-start", mode, dir, &attr->reject_start)) - goto fail; - if (!debugfs_create_ul("reject-end", mode, dir, &attr->reject_end)) - goto fail; - + debugfs_create_stacktrace_depth("stacktrace-depth", mode, dir, + &attr->stacktrace_depth); + debugfs_create_ul("require-start", mode, dir, &attr->require_start); + debugfs_create_ul("require-end", mode, dir, &attr->require_end); + debugfs_create_ul("reject-start", mode, dir, &attr->reject_start); + debugfs_create_ul("reject-end", mode, dir, &attr->reject_end); #endif /* CONFIG_FAULT_INJECTION_STACKTRACE_FILTER */ attr->dname = dget(dir); return dir; -fail: - debugfs_remove_recursive(dir); - - return ERR_PTR(-ENOMEM); } EXPORT_SYMBOL_GPL(fault_create_debugfs_attr); diff --git a/lib/fonts/fonts.c b/lib/fonts/fonts.c index 9969358a7af5..e7258d8c252b 100644 --- a/lib/fonts/fonts.c +++ b/lib/fonts/fonts.c @@ -20,56 +20,42 @@ #endif #include <linux/font.h> -#define NO_FONTS - static const struct font_desc *fonts[] = { #ifdef CONFIG_FONT_8x8 -#undef NO_FONTS - &font_vga_8x8, + &font_vga_8x8, #endif #ifdef CONFIG_FONT_8x16 -#undef NO_FONTS - &font_vga_8x16, + &font_vga_8x16, #endif #ifdef CONFIG_FONT_6x11 -#undef NO_FONTS - &font_vga_6x11, + &font_vga_6x11, #endif #ifdef CONFIG_FONT_7x14 -#undef NO_FONTS - &font_7x14, + &font_7x14, #endif #ifdef CONFIG_FONT_SUN8x16 -#undef NO_FONTS - &font_sun_8x16, + &font_sun_8x16, #endif #ifdef CONFIG_FONT_SUN12x22 -#undef NO_FONTS - &font_sun_12x22, + &font_sun_12x22, #endif #ifdef CONFIG_FONT_10x18 -#undef NO_FONTS - &font_10x18, + &font_10x18, #endif #ifdef CONFIG_FONT_ACORN_8x8 -#undef NO_FONTS - &font_acorn_8x8, + &font_acorn_8x8, #endif #ifdef CONFIG_FONT_PEARL_8x8 -#undef NO_FONTS - &font_pearl_8x8, + &font_pearl_8x8, #endif #ifdef CONFIG_FONT_MINI_4x6 -#undef NO_FONTS - &font_mini_4x6, + &font_mini_4x6, #endif #ifdef CONFIG_FONT_6x10 -#undef NO_FONTS - &font_6x10, + &font_6x10, #endif #ifdef CONFIG_FONT_TER16x32 -#undef NO_FONTS - &font_ter_16x32, + &font_ter_16x32, #endif }; @@ -90,16 +76,17 @@ static const struct font_desc *fonts[] = { * specified font. * */ - const struct font_desc *find_font(const char *name) { - unsigned int i; + unsigned int i; - for (i = 0; i < num_fonts; i++) - if (!strcmp(fonts[i]->name, name)) - return fonts[i]; - return NULL; + BUILD_BUG_ON(!num_fonts); + for (i = 0; i < num_fonts; i++) + if (!strcmp(fonts[i]->name, name)) + return fonts[i]; + return NULL; } +EXPORT_SYMBOL(find_font); /** @@ -116,44 +103,46 @@ const struct font_desc *find_font(const char *name) * chosen font. * */ - const struct font_desc *get_default_font(int xres, int yres, u32 font_w, u32 font_h) { - int i, c, cc; - const struct font_desc *f, *g; - - g = NULL; - cc = -10000; - for(i=0; i<num_fonts; i++) { - f = fonts[i]; - c = f->pref; + int i, c, cc, res; + const struct font_desc *f, *g; + + g = NULL; + cc = -10000; + for (i = 0; i < num_fonts; i++) { + f = fonts[i]; + c = f->pref; #if defined(__mc68000__) #ifdef CONFIG_FONT_PEARL_8x8 - if (MACH_IS_AMIGA && f->idx == PEARL8x8_IDX) - c = 100; + if (MACH_IS_AMIGA && f->idx == PEARL8x8_IDX) + c = 100; #endif #ifdef CONFIG_FONT_6x11 - if (MACH_IS_MAC && xres < 640 && f->idx == VGA6x11_IDX) - c = 100; + if (MACH_IS_MAC && xres < 640 && f->idx == VGA6x11_IDX) + c = 100; #endif #endif - if ((yres < 400) == (f->height <= 8)) - c += 1000; + if ((yres < 400) == (f->height <= 8)) + c += 1000; + + /* prefer a bigger font for high resolution */ + res = (xres / f->width) * (yres / f->height) / 1000; + if (res > 20) + c += 20 - res; - if ((font_w & (1 << (f->width - 1))) && - (font_h & (1 << (f->height - 1)))) - c += 1000; + if ((font_w & (1 << (f->width - 1))) && + (font_h & (1 << (f->height - 1)))) + c += 1000; - if (c > cc) { - cc = c; - g = f; + if (c > cc) { + cc = c; + g = f; + } } - } - return g; + return g; } - -EXPORT_SYMBOL(find_font); EXPORT_SYMBOL(get_default_font); MODULE_AUTHOR("James Simmons <jsimmons@users.sf.net>"); diff --git a/lib/genalloc.c b/lib/genalloc.c index 5257f74fccf3..9fc31292cfa1 100644 --- a/lib/genalloc.c +++ b/lib/genalloc.c @@ -327,21 +327,45 @@ EXPORT_SYMBOL(gen_pool_alloc_algo_owner); * gen_pool_dma_alloc - allocate special memory from the pool for DMA usage * @pool: pool to allocate from * @size: number of bytes to allocate from the pool - * @dma: dma-view physical address return value. Use NULL if unneeded. + * @dma: dma-view physical address return value. Use %NULL if unneeded. * * Allocate the requested number of bytes from the specified pool. * Uses the pool allocation function (with first-fit algorithm by default). * Can not be used in NMI handler on architectures without * NMI-safe cmpxchg implementation. + * + * Return: virtual address of the allocated memory, or %NULL on failure */ void *gen_pool_dma_alloc(struct gen_pool *pool, size_t size, dma_addr_t *dma) { + return gen_pool_dma_alloc_algo(pool, size, dma, pool->algo, pool->data); +} +EXPORT_SYMBOL(gen_pool_dma_alloc); + +/** + * gen_pool_dma_alloc_algo - allocate special memory from the pool for DMA + * usage with the given pool algorithm + * @pool: pool to allocate from + * @size: number of bytes to allocate from the pool + * @dma: DMA-view physical address return value. Use %NULL if unneeded. + * @algo: algorithm passed from caller + * @data: data passed to algorithm + * + * Allocate the requested number of bytes from the specified pool. Uses the + * given pool allocation function. Can not be used in NMI handler on + * architectures without NMI-safe cmpxchg implementation. + * + * Return: virtual address of the allocated memory, or %NULL on failure + */ +void *gen_pool_dma_alloc_algo(struct gen_pool *pool, size_t size, + dma_addr_t *dma, genpool_algo_t algo, void *data) +{ unsigned long vaddr; if (!pool) return NULL; - vaddr = gen_pool_alloc(pool, size); + vaddr = gen_pool_alloc_algo(pool, size, algo, data); if (!vaddr) return NULL; @@ -350,7 +374,102 @@ void *gen_pool_dma_alloc(struct gen_pool *pool, size_t size, dma_addr_t *dma) return (void *)vaddr; } -EXPORT_SYMBOL(gen_pool_dma_alloc); +EXPORT_SYMBOL(gen_pool_dma_alloc_algo); + +/** + * gen_pool_dma_alloc_align - allocate special memory from the pool for DMA + * usage with the given alignment + * @pool: pool to allocate from + * @size: number of bytes to allocate from the pool + * @dma: DMA-view physical address return value. Use %NULL if unneeded. + * @align: alignment in bytes for starting address + * + * Allocate the requested number bytes from the specified pool, with the given + * alignment restriction. Can not be used in NMI handler on architectures + * without NMI-safe cmpxchg implementation. + * + * Return: virtual address of the allocated memory, or %NULL on failure + */ +void *gen_pool_dma_alloc_align(struct gen_pool *pool, size_t size, + dma_addr_t *dma, int align) +{ + struct genpool_data_align data = { .align = align }; + + return gen_pool_dma_alloc_algo(pool, size, dma, + gen_pool_first_fit_align, &data); +} +EXPORT_SYMBOL(gen_pool_dma_alloc_align); + +/** + * gen_pool_dma_zalloc - allocate special zeroed memory from the pool for + * DMA usage + * @pool: pool to allocate from + * @size: number of bytes to allocate from the pool + * @dma: dma-view physical address return value. Use %NULL if unneeded. + * + * Allocate the requested number of zeroed bytes from the specified pool. + * Uses the pool allocation function (with first-fit algorithm by default). + * Can not be used in NMI handler on architectures without + * NMI-safe cmpxchg implementation. + * + * Return: virtual address of the allocated zeroed memory, or %NULL on failure + */ +void *gen_pool_dma_zalloc(struct gen_pool *pool, size_t size, dma_addr_t *dma) +{ + return gen_pool_dma_zalloc_algo(pool, size, dma, pool->algo, pool->data); +} +EXPORT_SYMBOL(gen_pool_dma_zalloc); + +/** + * gen_pool_dma_zalloc_algo - allocate special zeroed memory from the pool for + * DMA usage with the given pool algorithm + * @pool: pool to allocate from + * @size: number of bytes to allocate from the pool + * @dma: DMA-view physical address return value. Use %NULL if unneeded. + * @algo: algorithm passed from caller + * @data: data passed to algorithm + * + * Allocate the requested number of zeroed bytes from the specified pool. Uses + * the given pool allocation function. Can not be used in NMI handler on + * architectures without NMI-safe cmpxchg implementation. + * + * Return: virtual address of the allocated zeroed memory, or %NULL on failure + */ +void *gen_pool_dma_zalloc_algo(struct gen_pool *pool, size_t size, + dma_addr_t *dma, genpool_algo_t algo, void *data) +{ + void *vaddr = gen_pool_dma_alloc_algo(pool, size, dma, algo, data); + + if (vaddr) + memset(vaddr, 0, size); + + return vaddr; +} +EXPORT_SYMBOL(gen_pool_dma_zalloc_algo); + +/** + * gen_pool_dma_zalloc_align - allocate special zeroed memory from the pool for + * DMA usage with the given alignment + * @pool: pool to allocate from + * @size: number of bytes to allocate from the pool + * @dma: DMA-view physical address return value. Use %NULL if unneeded. + * @align: alignment in bytes for starting address + * + * Allocate the requested number of zeroed bytes from the specified pool, + * with the given alignment restriction. Can not be used in NMI handler on + * architectures without NMI-safe cmpxchg implementation. + * + * Return: virtual address of the allocated zeroed memory, or %NULL on failure + */ +void *gen_pool_dma_zalloc_align(struct gen_pool *pool, size_t size, + dma_addr_t *dma, int align) +{ + struct genpool_data_align data = { .align = align }; + + return gen_pool_dma_zalloc_algo(pool, size, dma, + gen_pool_first_fit_align, &data); +} +EXPORT_SYMBOL(gen_pool_dma_zalloc_align); /** * gen_pool_free - free allocated special memory back to the pool diff --git a/lib/idr.c b/lib/idr.c index c34e256d2f01..66a374892482 100644 --- a/lib/idr.c +++ b/lib/idr.c @@ -228,11 +228,21 @@ void *idr_get_next(struct idr *idr, int *nextid) { struct radix_tree_iter iter; void __rcu **slot; + void *entry = NULL; unsigned long base = idr->idr_base; unsigned long id = *nextid; id = (id < base) ? 0 : id - base; - slot = radix_tree_iter_find(&idr->idr_rt, &iter, id); + radix_tree_for_each_slot(slot, &idr->idr_rt, &iter, id) { + entry = rcu_dereference_raw(*slot); + if (!entry) + continue; + if (!xa_is_internal(entry)) + break; + if (slot != &idr->idr_rt.xa_head && !xa_is_retry(entry)) + break; + slot = radix_tree_iter_retry(&iter); + } if (!slot) return NULL; id = iter.index + base; @@ -241,7 +251,7 @@ void *idr_get_next(struct idr *idr, int *nextid) return NULL; *nextid = id; - return rcu_dereference_raw(*slot); + return entry; } EXPORT_SYMBOL(idr_get_next); diff --git a/lib/iov_iter.c b/lib/iov_iter.c index f99c41d4eb54..f1e0569b4539 100644 --- a/lib/iov_iter.c +++ b/lib/iov_iter.c @@ -1634,9 +1634,9 @@ EXPORT_SYMBOL(dup_iter); * on-stack array was used or not (and regardless of whether this function * returns an error or not). * - * Return: 0 on success or negative error code on error. + * Return: Negative error code on error, bytes imported on success */ -int import_iovec(int type, const struct iovec __user * uvector, +ssize_t import_iovec(int type, const struct iovec __user * uvector, unsigned nr_segs, unsigned fast_segs, struct iovec **iov, struct iov_iter *i) { @@ -1652,16 +1652,17 @@ int import_iovec(int type, const struct iovec __user * uvector, } iov_iter_init(i, type, p, nr_segs, n); *iov = p == *iov ? NULL : p; - return 0; + return n; } EXPORT_SYMBOL(import_iovec); #ifdef CONFIG_COMPAT #include <linux/compat.h> -int compat_import_iovec(int type, const struct compat_iovec __user * uvector, - unsigned nr_segs, unsigned fast_segs, - struct iovec **iov, struct iov_iter *i) +ssize_t compat_import_iovec(int type, + const struct compat_iovec __user * uvector, + unsigned nr_segs, unsigned fast_segs, + struct iovec **iov, struct iov_iter *i) { ssize_t n; struct iovec *p; @@ -1675,7 +1676,7 @@ int compat_import_iovec(int type, const struct compat_iovec __user * uvector, } iov_iter_init(i, type, p, nr_segs, n); *iov = p == *iov ? NULL : p; - return 0; + return n; } #endif diff --git a/lib/kobject.c b/lib/kobject.c index f2ccdbac8ed9..83198cb37d8d 100644 --- a/lib/kobject.c +++ b/lib/kobject.c @@ -498,8 +498,10 @@ int kobject_rename(struct kobject *kobj, const char *new_name) kobj = kobject_get(kobj); if (!kobj) return -EINVAL; - if (!kobj->parent) + if (!kobj->parent) { + kobject_put(kobj); return -EINVAL; + } devpath = kobject_get_path(kobj, GFP_KERNEL); if (!devpath) { diff --git a/lib/list_sort.c b/lib/list_sort.c index 712ed1f4eb64..52f0c258c895 100644 --- a/lib/list_sort.c +++ b/lib/list_sort.c @@ -157,9 +157,11 @@ static void merge_final(void *priv, cmp_func cmp, struct list_head *head, * * The number of pending lists of size 2^k is determined by the * state of bit k of "count" plus two extra pieces of information: + * * - The state of bit k-1 (when k == 0, consider bit -1 always set), and * - Whether the higher-order bits are zero or non-zero (i.e. * is count >= 2^(k+1)). + * * There are six states we distinguish. "x" represents some arbitrary * bits, and "y" represents some arbitrary non-zero bits: * 0: 00x: 0 pending of size 2^k; x pending of sizes < 2^k diff --git a/lib/mpi/mpi-pow.c b/lib/mpi/mpi-pow.c index 82b19e4f1189..2fd7a46d55ec 100644 --- a/lib/mpi/mpi-pow.c +++ b/lib/mpi/mpi-pow.c @@ -24,6 +24,7 @@ int mpi_powm(MPI res, MPI base, MPI exp, MPI mod) { mpi_ptr_t mp_marker = NULL, bp_marker = NULL, ep_marker = NULL; + struct karatsuba_ctx karactx = {}; mpi_ptr_t xp_marker = NULL; mpi_ptr_t tspace = NULL; mpi_ptr_t rp, ep, mp, bp; @@ -150,13 +151,11 @@ int mpi_powm(MPI res, MPI base, MPI exp, MPI mod) int c; mpi_limb_t e; mpi_limb_t carry_limb; - struct karatsuba_ctx karactx; xp = xp_marker = mpi_alloc_limb_space(2 * (msize + 1)); if (!xp) goto enomem; - memset(&karactx, 0, sizeof karactx); negative_result = (ep[0] & 1) && base->sign; i = esize - 1; @@ -281,8 +280,6 @@ int mpi_powm(MPI res, MPI base, MPI exp, MPI mod) if (mod_shift_cnt) mpihelp_rshift(rp, rp, rsize, mod_shift_cnt); MPN_NORMALIZE(rp, rsize); - - mpihelp_release_karatsuba_ctx(&karactx); } if (negative_result && rsize) { @@ -299,6 +296,7 @@ int mpi_powm(MPI res, MPI base, MPI exp, MPI mod) leave: rc = 0; enomem: + mpihelp_release_karatsuba_ctx(&karactx); if (assign_rp) mpi_assign_limb_space(res, rp, size); if (mp_marker) diff --git a/lib/notifier-error-inject.c b/lib/notifier-error-inject.c index 3d2ba7cf83f4..21016b32d313 100644 --- a/lib/notifier-error-inject.c +++ b/lib/notifier-error-inject.c @@ -59,33 +59,22 @@ struct dentry *notifier_err_inject_init(const char *name, struct dentry *parent, err_inject->nb.priority = priority; dir = debugfs_create_dir(name, parent); - if (!dir) - return ERR_PTR(-ENOMEM); actions_dir = debugfs_create_dir("actions", dir); - if (!actions_dir) - goto fail; for (action = err_inject->actions; action->name; action++) { struct dentry *action_dir; action_dir = debugfs_create_dir(action->name, actions_dir); - if (!action_dir) - goto fail; /* * Create debugfs r/w file containing action->error. If * notifier call chain is called with action->val, it will * fail with the error code */ - if (!debugfs_create_errno("error", mode, action_dir, - &action->error)) - goto fail; + debugfs_create_errno("error", mode, action_dir, &action->error); } return dir; -fail: - debugfs_remove_recursive(dir); - return ERR_PTR(-ENOMEM); } EXPORT_SYMBOL_GPL(notifier_err_inject_init); diff --git a/lib/objagg.c b/lib/objagg.c index 576be22e86de..55621fb82e0a 100644 --- a/lib/objagg.c +++ b/lib/objagg.c @@ -605,12 +605,10 @@ const struct objagg_stats *objagg_stats_get(struct objagg *objagg) { struct objagg_stats *objagg_stats; struct objagg_obj *objagg_obj; - size_t alloc_size; int i; - alloc_size = sizeof(*objagg_stats) + - sizeof(objagg_stats->stats_info[0]) * objagg->obj_count; - objagg_stats = kzalloc(alloc_size, GFP_KERNEL); + objagg_stats = kzalloc(struct_size(objagg_stats, stats_info, + objagg->obj_count), GFP_KERNEL); if (!objagg_stats) return ERR_PTR(-ENOMEM); diff --git a/lib/percpu-refcount.c b/lib/percpu-refcount.c index 071a76c7bac0..4f6c6ebbbbde 100644 --- a/lib/percpu-refcount.c +++ b/lib/percpu-refcount.c @@ -70,11 +70,14 @@ int percpu_ref_init(struct percpu_ref *ref, percpu_ref_func_t *release, return -ENOMEM; ref->force_atomic = flags & PERCPU_REF_INIT_ATOMIC; + ref->allow_reinit = flags & PERCPU_REF_ALLOW_REINIT; - if (flags & (PERCPU_REF_INIT_ATOMIC | PERCPU_REF_INIT_DEAD)) + if (flags & (PERCPU_REF_INIT_ATOMIC | PERCPU_REF_INIT_DEAD)) { ref->percpu_count_ptr |= __PERCPU_REF_ATOMIC; - else + ref->allow_reinit = true; + } else { start_count += PERCPU_COUNT_BIAS; + } if (flags & PERCPU_REF_INIT_DEAD) ref->percpu_count_ptr |= __PERCPU_REF_DEAD; @@ -120,6 +123,9 @@ static void percpu_ref_call_confirm_rcu(struct rcu_head *rcu) ref->confirm_switch = NULL; wake_up_all(&percpu_ref_switch_waitq); + if (!ref->allow_reinit) + percpu_ref_exit(ref); + /* drop ref from percpu_ref_switch_to_atomic() */ percpu_ref_put(ref); } @@ -195,6 +201,9 @@ static void __percpu_ref_switch_to_percpu(struct percpu_ref *ref) if (!(ref->percpu_count_ptr & __PERCPU_REF_ATOMIC)) return; + if (WARN_ON_ONCE(!ref->allow_reinit)) + return; + atomic_long_add(PERCPU_COUNT_BIAS, &ref->count); /* diff --git a/lib/raid6/Makefile b/lib/raid6/Makefile index e723eacf7868..42695bc8d451 100644 --- a/lib/raid6/Makefile +++ b/lib/raid6/Makefile @@ -12,9 +12,6 @@ raid6_pq-$(CONFIG_S390) += s390vx8.o recov_s390xc.o hostprogs-y += mktables -quiet_cmd_unroll = UNROLL $@ - cmd_unroll = $(AWK) -f$(srctree)/$(src)/unroll.awk -vN=$(UNROLL) < $< > $@ - ifeq ($(CONFIG_ALTIVEC),y) altivec_flags := -maltivec $(call cc-option,-mabi=altivec) @@ -26,7 +23,6 @@ CFLAGS_REMOVE_altivec1.o += -msoft-float CFLAGS_REMOVE_altivec2.o += -msoft-float CFLAGS_REMOVE_altivec4.o += -msoft-float CFLAGS_REMOVE_altivec8.o += -msoft-float -CFLAGS_REMOVE_altivec8.o += -msoft-float CFLAGS_REMOVE_vpermxor1.o += -msoft-float CFLAGS_REMOVE_vpermxor2.o += -msoft-float CFLAGS_REMOVE_vpermxor4.o += -msoft-float @@ -51,111 +47,39 @@ CFLAGS_REMOVE_neon8.o += -mgeneral-regs-only endif endif -targets += int1.c -$(obj)/int1.c: UNROLL := 1 -$(obj)/int1.c: $(src)/int.uc $(src)/unroll.awk FORCE - $(call if_changed,unroll) - -targets += int2.c -$(obj)/int2.c: UNROLL := 2 -$(obj)/int2.c: $(src)/int.uc $(src)/unroll.awk FORCE - $(call if_changed,unroll) - -targets += int4.c -$(obj)/int4.c: UNROLL := 4 -$(obj)/int4.c: $(src)/int.uc $(src)/unroll.awk FORCE - $(call if_changed,unroll) - -targets += int8.c -$(obj)/int8.c: UNROLL := 8 -$(obj)/int8.c: $(src)/int.uc $(src)/unroll.awk FORCE - $(call if_changed,unroll) - -targets += int16.c -$(obj)/int16.c: UNROLL := 16 -$(obj)/int16.c: $(src)/int.uc $(src)/unroll.awk FORCE - $(call if_changed,unroll) +quiet_cmd_unroll = UNROLL $@ + cmd_unroll = $(AWK) -f$(srctree)/$(src)/unroll.awk -vN=$* < $< > $@ -targets += int32.c -$(obj)/int32.c: UNROLL := 32 -$(obj)/int32.c: $(src)/int.uc $(src)/unroll.awk FORCE +targets += int1.c int2.c int4.c int8.c int16.c int32.c +$(obj)/int%.c: $(src)/int.uc $(src)/unroll.awk FORCE $(call if_changed,unroll) CFLAGS_altivec1.o += $(altivec_flags) -targets += altivec1.c -$(obj)/altivec1.c: UNROLL := 1 -$(obj)/altivec1.c: $(src)/altivec.uc $(src)/unroll.awk FORCE - $(call if_changed,unroll) - CFLAGS_altivec2.o += $(altivec_flags) -targets += altivec2.c -$(obj)/altivec2.c: UNROLL := 2 -$(obj)/altivec2.c: $(src)/altivec.uc $(src)/unroll.awk FORCE - $(call if_changed,unroll) - CFLAGS_altivec4.o += $(altivec_flags) -targets += altivec4.c -$(obj)/altivec4.c: UNROLL := 4 -$(obj)/altivec4.c: $(src)/altivec.uc $(src)/unroll.awk FORCE - $(call if_changed,unroll) - CFLAGS_altivec8.o += $(altivec_flags) -targets += altivec8.c -$(obj)/altivec8.c: UNROLL := 8 -$(obj)/altivec8.c: $(src)/altivec.uc $(src)/unroll.awk FORCE +targets += altivec1.c altivec2.c altivec4.c altivec8.c +$(obj)/altivec%.c: $(src)/altivec.uc $(src)/unroll.awk FORCE $(call if_changed,unroll) CFLAGS_vpermxor1.o += $(altivec_flags) -targets += vpermxor1.c -$(obj)/vpermxor1.c: UNROLL := 1 -$(obj)/vpermxor1.c: $(src)/vpermxor.uc $(src)/unroll.awk FORCE - $(call if_changed,unroll) - CFLAGS_vpermxor2.o += $(altivec_flags) -targets += vpermxor2.c -$(obj)/vpermxor2.c: UNROLL := 2 -$(obj)/vpermxor2.c: $(src)/vpermxor.uc $(src)/unroll.awk FORCE - $(call if_changed,unroll) - CFLAGS_vpermxor4.o += $(altivec_flags) -targets += vpermxor4.c -$(obj)/vpermxor4.c: UNROLL := 4 -$(obj)/vpermxor4.c: $(src)/vpermxor.uc $(src)/unroll.awk FORCE - $(call if_changed,unroll) - CFLAGS_vpermxor8.o += $(altivec_flags) -targets += vpermxor8.c -$(obj)/vpermxor8.c: UNROLL := 8 -$(obj)/vpermxor8.c: $(src)/vpermxor.uc $(src)/unroll.awk FORCE +targets += vpermxor1.o vpermxor2.o vpermxor4.o vpermxor8.o +$(obj)/vpermxor%.c: $(src)/vpermxor.uc $(src)/unroll.awk FORCE $(call if_changed,unroll) CFLAGS_neon1.o += $(NEON_FLAGS) -targets += neon1.c -$(obj)/neon1.c: UNROLL := 1 -$(obj)/neon1.c: $(src)/neon.uc $(src)/unroll.awk FORCE - $(call if_changed,unroll) - CFLAGS_neon2.o += $(NEON_FLAGS) -targets += neon2.c -$(obj)/neon2.c: UNROLL := 2 -$(obj)/neon2.c: $(src)/neon.uc $(src)/unroll.awk FORCE - $(call if_changed,unroll) - CFLAGS_neon4.o += $(NEON_FLAGS) -targets += neon4.c -$(obj)/neon4.c: UNROLL := 4 -$(obj)/neon4.c: $(src)/neon.uc $(src)/unroll.awk FORCE - $(call if_changed,unroll) - CFLAGS_neon8.o += $(NEON_FLAGS) -targets += neon8.c -$(obj)/neon8.c: UNROLL := 8 -$(obj)/neon8.c: $(src)/neon.uc $(src)/unroll.awk FORCE +targets += neon1.c neon2.c neon4.c neon8.c +$(obj)/neon%.c: $(src)/neon.uc $(src)/unroll.awk FORCE $(call if_changed,unroll) targets += s390vx8.c -$(obj)/s390vx8.c: UNROLL := 8 -$(obj)/s390vx8.c: $(src)/s390vx.uc $(src)/unroll.awk FORCE +$(obj)/s390vx%.c: $(src)/s390vx.uc $(src)/unroll.awk FORCE $(call if_changed,unroll) quiet_cmd_mktable = TABLE $@ diff --git a/lib/raid6/s390vx.uc b/lib/raid6/s390vx.uc index 914ebe98fc21..9e597e1f91a4 100644 --- a/lib/raid6/s390vx.uc +++ b/lib/raid6/s390vx.uc @@ -60,7 +60,7 @@ static inline void LOAD_DATA(int x, u8 *ptr) typedef struct { u8 _[16 * $#]; } addrtype; register addrtype *__ptr asm("1") = (addrtype *) ptr; - asm volatile ("VLM %2,%3,0,%r1" + asm volatile ("VLM %2,%3,0,%1" : : "m" (*__ptr), "a" (__ptr), "i" (x), "i" (x + $# - 1)); } diff --git a/lib/reed_solomon/Makefile b/lib/reed_solomon/Makefile index ba9d7a3329eb..5d4fa68f26cb 100644 --- a/lib/reed_solomon/Makefile +++ b/lib/reed_solomon/Makefile @@ -4,4 +4,4 @@ # obj-$(CONFIG_REED_SOLOMON) += reed_solomon.o - +obj-$(CONFIG_REED_SOLOMON_TEST) += test_rslib.o diff --git a/lib/reed_solomon/decode_rs.c b/lib/reed_solomon/decode_rs.c index 1db74eb098d0..805de84ae83d 100644 --- a/lib/reed_solomon/decode_rs.c +++ b/lib/reed_solomon/decode_rs.c @@ -22,6 +22,7 @@ uint16_t *index_of = rs->index_of; uint16_t u, q, tmp, num1, num2, den, discr_r, syn_error; int count = 0; + int num_corrected; uint16_t msk = (uint16_t) rs->nn; /* @@ -39,11 +40,21 @@ /* Check length parameter for validity */ pad = nn - nroots - len; - BUG_ON(pad < 0 || pad >= nn); + BUG_ON(pad < 0 || pad >= nn - nroots); /* Does the caller provide the syndrome ? */ - if (s != NULL) - goto decode; + if (s != NULL) { + for (i = 0; i < nroots; i++) { + /* The syndrome is in index form, + * so nn represents zero + */ + if (s[i] != nn) + goto decode; + } + + /* syndrome is zero, no errors to correct */ + return 0; + } /* form the syndromes; i.e., evaluate data(x) at roots of * g(x) */ @@ -88,8 +99,7 @@ /* if syndrome is zero, data[] is a codeword and there are no * errors to correct. So return data[] unmodified */ - count = 0; - goto finish; + return 0; } decode: @@ -99,9 +109,9 @@ if (no_eras > 0) { /* Init lambda to be the erasure locator polynomial */ lambda[1] = alpha_to[rs_modnn(rs, - prim * (nn - 1 - eras_pos[0]))]; + prim * (nn - 1 - (eras_pos[0] + pad)))]; for (i = 1; i < no_eras; i++) { - u = rs_modnn(rs, prim * (nn - 1 - eras_pos[i])); + u = rs_modnn(rs, prim * (nn - 1 - (eras_pos[i] + pad))); for (j = i + 1; j > 0; j--) { tmp = index_of[lambda[j - 1]]; if (tmp != nn) { @@ -175,6 +185,15 @@ if (lambda[i] != nn) deg_lambda = i; } + + if (deg_lambda == 0) { + /* + * deg(lambda) is zero even though the syndrome is non-zero + * => uncorrectable error detected + */ + return -EBADMSG; + } + /* Find roots of error+erasure locator polynomial by Chien search */ memcpy(®[1], &lambda[1], nroots * sizeof(reg[0])); count = 0; /* Number of roots of lambda(x) */ @@ -188,6 +207,12 @@ } if (q != 0) continue; /* Not a root */ + + if (k < pad) { + /* Impossible error location. Uncorrectable error. */ + return -EBADMSG; + } + /* store root (index-form) and error location number */ root[count] = i; loc[count] = k; @@ -202,8 +227,7 @@ * deg(lambda) unequal to number of roots => uncorrectable * error detected */ - count = -EBADMSG; - goto finish; + return -EBADMSG; } /* * Compute err+eras evaluator poly omega(x) = s(x)*lambda(x) (modulo @@ -223,7 +247,9 @@ /* * Compute error values in poly-form. num1 = omega(inv(X(l))), num2 = * inv(X(l))**(fcr-1) and den = lambda_pr(inv(X(l))) all in poly-form + * Note: we reuse the buffer for b to store the correction pattern */ + num_corrected = 0; for (j = count - 1; j >= 0; j--) { num1 = 0; for (i = deg_omega; i >= 0; i--) { @@ -231,6 +257,13 @@ num1 ^= alpha_to[rs_modnn(rs, omega[i] + i * root[j])]; } + + if (num1 == 0) { + /* Nothing to correct at this position */ + b[j] = 0; + continue; + } + num2 = alpha_to[rs_modnn(rs, root[j] * (fcr - 1) + nn)]; den = 0; @@ -242,30 +275,52 @@ i * root[j])]; } } - /* Apply error to data */ - if (num1 != 0 && loc[j] >= pad) { - uint16_t cor = alpha_to[rs_modnn(rs,index_of[num1] + - index_of[num2] + - nn - index_of[den])]; - /* Store the error correction pattern, if a - * correction buffer is available */ - if (corr) { - corr[j] = cor; - } else { - /* If a data buffer is given and the - * error is inside the message, - * correct it */ - if (data && (loc[j] < (nn - nroots))) - data[loc[j] - pad] ^= cor; - } + + b[j] = alpha_to[rs_modnn(rs, index_of[num1] + + index_of[num2] + + nn - index_of[den])]; + num_corrected++; + } + + /* + * We compute the syndrome of the 'error' and check that it matches + * the syndrome of the received word + */ + for (i = 0; i < nroots; i++) { + tmp = 0; + for (j = 0; j < count; j++) { + if (b[j] == 0) + continue; + + k = (fcr + i) * prim * (nn-loc[j]-1); + tmp ^= alpha_to[rs_modnn(rs, index_of[b[j]] + k)]; } + + if (tmp != alpha_to[s[i]]) + return -EBADMSG; } -finish: - if (eras_pos != NULL) { - for (i = 0; i < count; i++) - eras_pos[i] = loc[i] - pad; + /* + * Store the error correction pattern, if a + * correction buffer is available + */ + if (corr && eras_pos) { + j = 0; + for (i = 0; i < count; i++) { + if (b[i]) { + corr[j] = b[i]; + eras_pos[j++] = loc[i] - pad; + } + } + } else if (data && par) { + /* Apply error to data and parity */ + for (i = 0; i < count; i++) { + if (loc[i] < (nn - nroots)) + data[loc[i] - pad] ^= b[i]; + else + par[loc[i] - pad - len] ^= b[i]; + } } - return count; + return num_corrected; } diff --git a/lib/reed_solomon/reed_solomon.c b/lib/reed_solomon/reed_solomon.c index e5fdc8b9e856..bbc01bad3053 100644 --- a/lib/reed_solomon/reed_solomon.c +++ b/lib/reed_solomon/reed_solomon.c @@ -340,7 +340,8 @@ EXPORT_SYMBOL_GPL(encode_rs8); * @data: data field of a given type * @par: received parity data field * @len: data length - * @s: syndrome data field (if NULL, syndrome is calculated) + * @s: syndrome data field, must be in index form + * (if NULL, syndrome is calculated) * @no_eras: number of erasures * @eras_pos: position of erasures, can be NULL * @invmsk: invert data mask (will be xored on data, not on parity!) @@ -354,7 +355,8 @@ EXPORT_SYMBOL_GPL(encode_rs8); * decoding, so the caller has to ensure that decoder invocations are * serialized. * - * Returns the number of corrected bits or -EBADMSG for uncorrectable errors. + * Returns the number of corrected symbols or -EBADMSG for uncorrectable + * errors. The count includes errors in the parity. */ int decode_rs8(struct rs_control *rsc, uint8_t *data, uint16_t *par, int len, uint16_t *s, int no_eras, int *eras_pos, uint16_t invmsk, @@ -391,7 +393,8 @@ EXPORT_SYMBOL_GPL(encode_rs16); * @data: data field of a given type * @par: received parity data field * @len: data length - * @s: syndrome data field (if NULL, syndrome is calculated) + * @s: syndrome data field, must be in index form + * (if NULL, syndrome is calculated) * @no_eras: number of erasures * @eras_pos: position of erasures, can be NULL * @invmsk: invert data mask (will be xored on data, not on parity!) @@ -403,7 +406,8 @@ EXPORT_SYMBOL_GPL(encode_rs16); * decoding, so the caller has to ensure that decoder invocations are * serialized. * - * Returns the number of corrected bits or -EBADMSG for uncorrectable errors. + * Returns the number of corrected symbols or -EBADMSG for uncorrectable + * errors. The count includes errors in the parity. */ int decode_rs16(struct rs_control *rsc, uint16_t *data, uint16_t *par, int len, uint16_t *s, int no_eras, int *eras_pos, uint16_t invmsk, diff --git a/lib/reed_solomon/test_rslib.c b/lib/reed_solomon/test_rslib.c new file mode 100644 index 000000000000..4eb29f365ece --- /dev/null +++ b/lib/reed_solomon/test_rslib.c @@ -0,0 +1,518 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Tests for Generic Reed Solomon encoder / decoder library + * + * Written by Ferdinand Blomqvist + * Based on previous work by Phil Karn, KA9Q + */ +#include <linux/rslib.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/moduleparam.h> +#include <linux/random.h> +#include <linux/slab.h> + +enum verbosity { + V_SILENT, + V_PROGRESS, + V_CSUMMARY +}; + +enum method { + CORR_BUFFER, + CALLER_SYNDROME, + IN_PLACE +}; + +#define __param(type, name, init, msg) \ + static type name = init; \ + module_param(name, type, 0444); \ + MODULE_PARM_DESC(name, msg) + +__param(int, v, V_PROGRESS, "Verbosity level"); +__param(int, ewsc, 1, "Erasures without symbol corruption"); +__param(int, bc, 1, "Test for correct behaviour beyond error correction capacity"); + +struct etab { + int symsize; + int genpoly; + int fcs; + int prim; + int nroots; + int ntrials; +}; + +/* List of codes to test */ +static struct etab Tab[] = { + {2, 0x7, 1, 1, 1, 100000 }, + {3, 0xb, 1, 1, 2, 100000 }, + {3, 0xb, 1, 1, 3, 100000 }, + {3, 0xb, 2, 1, 4, 100000 }, + {4, 0x13, 1, 1, 4, 10000 }, + {5, 0x25, 1, 1, 6, 1000 }, + {6, 0x43, 3, 1, 8, 1000 }, + {7, 0x89, 1, 1, 14, 500 }, + {8, 0x11d, 1, 1, 30, 100 }, + {8, 0x187, 112, 11, 32, 100 }, + {9, 0x211, 1, 1, 33, 80 }, + {0, 0, 0, 0, 0, 0}, +}; + + +struct estat { + int dwrong; + int irv; + int wepos; + int nwords; +}; + +struct bcstat { + int rfail; + int rsuccess; + int noncw; + int nwords; +}; + +struct wspace { + uint16_t *c; /* sent codeword */ + uint16_t *r; /* received word */ + uint16_t *s; /* syndrome */ + uint16_t *corr; /* correction buffer */ + int *errlocs; + int *derrlocs; +}; + +struct pad { + int mult; + int shift; +}; + +static struct pad pad_coef[] = { + { 0, 0 }, + { 1, 2 }, + { 1, 1 }, + { 3, 2 }, + { 1, 0 }, +}; + +static void free_ws(struct wspace *ws) +{ + if (!ws) + return; + + kfree(ws->errlocs); + kfree(ws->c); + kfree(ws); +} + +static struct wspace *alloc_ws(struct rs_codec *rs) +{ + int nroots = rs->nroots; + struct wspace *ws; + int nn = rs->nn; + + ws = kzalloc(sizeof(*ws), GFP_KERNEL); + if (!ws) + return NULL; + + ws->c = kmalloc_array(2 * (nn + nroots), + sizeof(uint16_t), GFP_KERNEL); + if (!ws->c) + goto err; + + ws->r = ws->c + nn; + ws->s = ws->r + nn; + ws->corr = ws->s + nroots; + + ws->errlocs = kmalloc_array(nn + nroots, sizeof(int), GFP_KERNEL); + if (!ws->errlocs) + goto err; + + ws->derrlocs = ws->errlocs + nn; + return ws; + +err: + free_ws(ws); + return NULL; +} + + +/* + * Generates a random codeword and stores it in c. Generates random errors and + * erasures, and stores the random word with errors in r. Erasure positions are + * stored in derrlocs, while errlocs has one of three values in every position: + * + * 0 if there is no error in this position; + * 1 if there is a symbol error in this position; + * 2 if there is an erasure without symbol corruption. + * + * Returns the number of corrupted symbols. + */ +static int get_rcw_we(struct rs_control *rs, struct wspace *ws, + int len, int errs, int eras) +{ + int nroots = rs->codec->nroots; + int *derrlocs = ws->derrlocs; + int *errlocs = ws->errlocs; + int dlen = len - nroots; + int nn = rs->codec->nn; + uint16_t *c = ws->c; + uint16_t *r = ws->r; + int errval; + int errloc; + int i; + + /* Load c with random data and encode */ + for (i = 0; i < dlen; i++) + c[i] = prandom_u32() & nn; + + memset(c + dlen, 0, nroots * sizeof(*c)); + encode_rs16(rs, c, dlen, c + dlen, 0); + + /* Make copyand add errors and erasures */ + memcpy(r, c, len * sizeof(*r)); + memset(errlocs, 0, len * sizeof(*errlocs)); + memset(derrlocs, 0, nroots * sizeof(*derrlocs)); + + /* Generating random errors */ + for (i = 0; i < errs; i++) { + do { + /* Error value must be nonzero */ + errval = prandom_u32() & nn; + } while (errval == 0); + + do { + /* Must not choose the same location twice */ + errloc = prandom_u32() % len; + } while (errlocs[errloc] != 0); + + errlocs[errloc] = 1; + r[errloc] ^= errval; + } + + /* Generating random erasures */ + for (i = 0; i < eras; i++) { + do { + /* Must not choose the same location twice */ + errloc = prandom_u32() % len; + } while (errlocs[errloc] != 0); + + derrlocs[i] = errloc; + + if (ewsc && (prandom_u32() & 1)) { + /* Erasure with the symbol intact */ + errlocs[errloc] = 2; + } else { + /* Erasure with corrupted symbol */ + do { + /* Error value must be nonzero */ + errval = prandom_u32() & nn; + } while (errval == 0); + + errlocs[errloc] = 1; + r[errloc] ^= errval; + errs++; + } + } + + return errs; +} + +static void fix_err(uint16_t *data, int nerrs, uint16_t *corr, int *errlocs) +{ + int i; + + for (i = 0; i < nerrs; i++) + data[errlocs[i]] ^= corr[i]; +} + +static void compute_syndrome(struct rs_control *rsc, uint16_t *data, + int len, uint16_t *syn) +{ + struct rs_codec *rs = rsc->codec; + uint16_t *alpha_to = rs->alpha_to; + uint16_t *index_of = rs->index_of; + int nroots = rs->nroots; + int prim = rs->prim; + int fcr = rs->fcr; + int i, j; + + /* Calculating syndrome */ + for (i = 0; i < nroots; i++) { + syn[i] = data[0]; + for (j = 1; j < len; j++) { + if (syn[i] == 0) { + syn[i] = data[j]; + } else { + syn[i] = data[j] ^ + alpha_to[rs_modnn(rs, index_of[syn[i]] + + (fcr + i) * prim)]; + } + } + } + + /* Convert to index form */ + for (i = 0; i < nroots; i++) + syn[i] = rs->index_of[syn[i]]; +} + +/* Test up to error correction capacity */ +static void test_uc(struct rs_control *rs, int len, int errs, + int eras, int trials, struct estat *stat, + struct wspace *ws, int method) +{ + int dlen = len - rs->codec->nroots; + int *derrlocs = ws->derrlocs; + int *errlocs = ws->errlocs; + uint16_t *corr = ws->corr; + uint16_t *c = ws->c; + uint16_t *r = ws->r; + uint16_t *s = ws->s; + int derrs, nerrs; + int i, j; + + for (j = 0; j < trials; j++) { + nerrs = get_rcw_we(rs, ws, len, errs, eras); + + switch (method) { + case CORR_BUFFER: + derrs = decode_rs16(rs, r, r + dlen, dlen, + NULL, eras, derrlocs, 0, corr); + fix_err(r, derrs, corr, derrlocs); + break; + case CALLER_SYNDROME: + compute_syndrome(rs, r, len, s); + derrs = decode_rs16(rs, NULL, NULL, dlen, + s, eras, derrlocs, 0, corr); + fix_err(r, derrs, corr, derrlocs); + break; + case IN_PLACE: + derrs = decode_rs16(rs, r, r + dlen, dlen, + NULL, eras, derrlocs, 0, NULL); + break; + default: + continue; + } + + if (derrs != nerrs) + stat->irv++; + + if (method != IN_PLACE) { + for (i = 0; i < derrs; i++) { + if (errlocs[derrlocs[i]] != 1) + stat->wepos++; + } + } + + if (memcmp(r, c, len * sizeof(*r))) + stat->dwrong++; + } + stat->nwords += trials; +} + +static int ex_rs_helper(struct rs_control *rs, struct wspace *ws, + int len, int trials, int method) +{ + static const char * const desc[] = { + "Testing correction buffer interface...", + "Testing with caller provided syndrome...", + "Testing in-place interface..." + }; + + struct estat stat = {0, 0, 0, 0}; + int nroots = rs->codec->nroots; + int errs, eras, retval; + + if (v >= V_PROGRESS) + pr_info(" %s\n", desc[method]); + + for (errs = 0; errs <= nroots / 2; errs++) + for (eras = 0; eras <= nroots - 2 * errs; eras++) + test_uc(rs, len, errs, eras, trials, &stat, ws, method); + + if (v >= V_CSUMMARY) { + pr_info(" Decodes wrong: %d / %d\n", + stat.dwrong, stat.nwords); + pr_info(" Wrong return value: %d / %d\n", + stat.irv, stat.nwords); + if (method != IN_PLACE) + pr_info(" Wrong error position: %d\n", stat.wepos); + } + + retval = stat.dwrong + stat.wepos + stat.irv; + if (retval && v >= V_PROGRESS) + pr_warn(" FAIL: %d decoding failures!\n", retval); + + return retval; +} + +static int exercise_rs(struct rs_control *rs, struct wspace *ws, + int len, int trials) +{ + + int retval = 0; + int i; + + if (v >= V_PROGRESS) + pr_info("Testing up to error correction capacity...\n"); + + for (i = 0; i <= IN_PLACE; i++) + retval |= ex_rs_helper(rs, ws, len, trials, i); + + return retval; +} + +/* Tests for correct behaviour beyond error correction capacity */ +static void test_bc(struct rs_control *rs, int len, int errs, + int eras, int trials, struct bcstat *stat, + struct wspace *ws) +{ + int nroots = rs->codec->nroots; + int dlen = len - nroots; + int *derrlocs = ws->derrlocs; + uint16_t *corr = ws->corr; + uint16_t *r = ws->r; + int derrs, j; + + for (j = 0; j < trials; j++) { + get_rcw_we(rs, ws, len, errs, eras); + derrs = decode_rs16(rs, r, r + dlen, dlen, + NULL, eras, derrlocs, 0, corr); + fix_err(r, derrs, corr, derrlocs); + + if (derrs >= 0) { + stat->rsuccess++; + + /* + * We check that the returned word is actually a + * codeword. The obious way to do this would be to + * compute the syndrome, but we don't want to replicate + * that code here. However, all the codes are in + * systematic form, and therefore we can encode the + * returned word, and see whether the parity changes or + * not. + */ + memset(corr, 0, nroots * sizeof(*corr)); + encode_rs16(rs, r, dlen, corr, 0); + + if (memcmp(r + dlen, corr, nroots * sizeof(*corr))) + stat->noncw++; + } else { + stat->rfail++; + } + } + stat->nwords += trials; +} + +static int exercise_rs_bc(struct rs_control *rs, struct wspace *ws, + int len, int trials) +{ + struct bcstat stat = {0, 0, 0, 0}; + int nroots = rs->codec->nroots; + int errs, eras, cutoff; + + if (v >= V_PROGRESS) + pr_info("Testing beyond error correction capacity...\n"); + + for (errs = 1; errs <= nroots; errs++) { + eras = nroots - 2 * errs + 1; + if (eras < 0) + eras = 0; + + cutoff = nroots <= len - errs ? nroots : len - errs; + for (; eras <= cutoff; eras++) + test_bc(rs, len, errs, eras, trials, &stat, ws); + } + + if (v >= V_CSUMMARY) { + pr_info(" decoder gives up: %d / %d\n", + stat.rfail, stat.nwords); + pr_info(" decoder returns success: %d / %d\n", + stat.rsuccess, stat.nwords); + pr_info(" not a codeword: %d / %d\n", + stat.noncw, stat.rsuccess); + } + + if (stat.noncw && v >= V_PROGRESS) + pr_warn(" FAIL: %d silent failures!\n", stat.noncw); + + return stat.noncw; +} + +static int run_exercise(struct etab *e) +{ + int nn = (1 << e->symsize) - 1; + int kk = nn - e->nroots; + struct rs_control *rsc; + int retval = -ENOMEM; + int max_pad = kk - 1; + int prev_pad = -1; + struct wspace *ws; + int i; + + rsc = init_rs(e->symsize, e->genpoly, e->fcs, e->prim, e->nroots); + if (!rsc) + return retval; + + ws = alloc_ws(rsc->codec); + if (!ws) + goto err; + + retval = 0; + for (i = 0; i < ARRAY_SIZE(pad_coef); i++) { + int pad = (pad_coef[i].mult * max_pad) >> pad_coef[i].shift; + int len = nn - pad; + + if (pad == prev_pad) + continue; + + prev_pad = pad; + if (v >= V_PROGRESS) { + pr_info("Testing (%d,%d)_%d code...\n", + len, kk - pad, nn + 1); + } + + retval |= exercise_rs(rsc, ws, len, e->ntrials); + if (bc) + retval |= exercise_rs_bc(rsc, ws, len, e->ntrials); + } + + free_ws(ws); + +err: + free_rs(rsc); + return retval; +} + +static int __init test_rslib_init(void) +{ + int i, fail = 0; + + for (i = 0; Tab[i].symsize != 0 ; i++) { + int retval; + + retval = run_exercise(Tab + i); + if (retval < 0) + return -ENOMEM; + + fail |= retval; + } + + if (fail) + pr_warn("rslib: test failed\n"); + else + pr_info("rslib: test ok\n"); + + return -EAGAIN; /* Fail will directly unload the module */ +} + +static void __exit test_rslib_exit(void) +{ +} + +module_init(test_rslib_init) +module_exit(test_rslib_exit) + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Ferdinand Blomqvist"); +MODULE_DESCRIPTION("Reed-Solomon library test"); diff --git a/lib/sbitmap.c b/lib/sbitmap.c index 54f57cd117c6..969e5400a615 100644 --- a/lib/sbitmap.c +++ b/lib/sbitmap.c @@ -26,9 +26,7 @@ static inline bool sbitmap_deferred_clear(struct sbitmap *sb, int index) /* * First get a stable cleared mask, setting the old mask to 0. */ - do { - mask = sb->map[index].cleared; - } while (cmpxchg(&sb->map[index].cleared, mask, 0) != mask); + mask = xchg(&sb->map[index].cleared, 0); /* * Now clear the masked bits in our free word @@ -516,10 +514,8 @@ static struct sbq_wait_state *sbq_wake_ptr(struct sbitmap_queue *sbq) struct sbq_wait_state *ws = &sbq->ws[wake_index]; if (waitqueue_active(&ws->wait)) { - int o = atomic_read(&sbq->wake_index); - - if (wake_index != o) - atomic_cmpxchg(&sbq->wake_index, o, wake_index); + if (wake_index != atomic_read(&sbq->wake_index)) + atomic_set(&sbq->wake_index, wake_index); return ws; } diff --git a/lib/scatterlist.c b/lib/scatterlist.c index 2882d9ba6607..c2cf2c311b7d 100644 --- a/lib/scatterlist.c +++ b/lib/scatterlist.c @@ -179,7 +179,8 @@ static void sg_kfree(struct scatterlist *sg, unsigned int nents) * __sg_free_table - Free a previously mapped sg table * @table: The sg table header to use * @max_ents: The maximum number of entries per single scatterlist - * @skip_first_chunk: don't free the (preallocated) first scatterlist chunk + * @nents_first_chunk: Number of entries int the (preallocated) first + * scatterlist chunk, 0 means no such preallocated first chunk * @free_fn: Free function * * Description: @@ -189,9 +190,10 @@ static void sg_kfree(struct scatterlist *sg, unsigned int nents) * **/ void __sg_free_table(struct sg_table *table, unsigned int max_ents, - bool skip_first_chunk, sg_free_fn *free_fn) + unsigned int nents_first_chunk, sg_free_fn *free_fn) { struct scatterlist *sgl, *next; + unsigned curr_max_ents = nents_first_chunk ?: max_ents; if (unlikely(!table->sgl)) return; @@ -207,9 +209,9 @@ void __sg_free_table(struct sg_table *table, unsigned int max_ents, * sg_size is then one less than alloc size, since the last * element is the chain pointer. */ - if (alloc_size > max_ents) { - next = sg_chain_ptr(&sgl[max_ents - 1]); - alloc_size = max_ents; + if (alloc_size > curr_max_ents) { + next = sg_chain_ptr(&sgl[curr_max_ents - 1]); + alloc_size = curr_max_ents; sg_size = alloc_size - 1; } else { sg_size = alloc_size; @@ -217,11 +219,12 @@ void __sg_free_table(struct sg_table *table, unsigned int max_ents, } table->orig_nents -= sg_size; - if (skip_first_chunk) - skip_first_chunk = false; + if (nents_first_chunk) + nents_first_chunk = 0; else free_fn(sgl, alloc_size); sgl = next; + curr_max_ents = max_ents; } table->sgl = NULL; @@ -244,6 +247,8 @@ EXPORT_SYMBOL(sg_free_table); * @table: The sg table header to use * @nents: Number of entries in sg list * @max_ents: The maximum number of entries the allocator returns per call + * @nents_first_chunk: Number of entries int the (preallocated) first + * scatterlist chunk, 0 means no such preallocated chunk provided by user * @gfp_mask: GFP allocation mask * @alloc_fn: Allocator to use * @@ -260,10 +265,13 @@ EXPORT_SYMBOL(sg_free_table); **/ int __sg_alloc_table(struct sg_table *table, unsigned int nents, unsigned int max_ents, struct scatterlist *first_chunk, - gfp_t gfp_mask, sg_alloc_fn *alloc_fn) + unsigned int nents_first_chunk, gfp_t gfp_mask, + sg_alloc_fn *alloc_fn) { struct scatterlist *sg, *prv; unsigned int left; + unsigned curr_max_ents = nents_first_chunk ?: max_ents; + unsigned prv_max_ents; memset(table, 0, sizeof(*table)); @@ -279,8 +287,8 @@ int __sg_alloc_table(struct sg_table *table, unsigned int nents, do { unsigned int sg_size, alloc_size = left; - if (alloc_size > max_ents) { - alloc_size = max_ents; + if (alloc_size > curr_max_ents) { + alloc_size = curr_max_ents; sg_size = alloc_size - 1; } else sg_size = alloc_size; @@ -314,7 +322,7 @@ int __sg_alloc_table(struct sg_table *table, unsigned int nents, * If this is not the first mapping, chain previous part. */ if (prv) - sg_chain(prv, max_ents, sg); + sg_chain(prv, prv_max_ents, sg); else table->sgl = sg; @@ -325,6 +333,8 @@ int __sg_alloc_table(struct sg_table *table, unsigned int nents, sg_mark_end(&sg[sg_size - 1]); prv = sg; + prv_max_ents = curr_max_ents; + curr_max_ents = max_ents; } while (left); return 0; @@ -347,9 +357,9 @@ int sg_alloc_table(struct sg_table *table, unsigned int nents, gfp_t gfp_mask) int ret; ret = __sg_alloc_table(table, nents, SG_MAX_SINGLE_ALLOC, - NULL, gfp_mask, sg_kmalloc); + NULL, 0, gfp_mask, sg_kmalloc); if (unlikely(ret)) - __sg_free_table(table, SG_MAX_SINGLE_ALLOC, false, sg_kfree); + __sg_free_table(table, SG_MAX_SINGLE_ALLOC, 0, sg_kfree); return ret; } @@ -676,17 +686,18 @@ static bool sg_miter_get_next_page(struct sg_mapping_iter *miter) { if (!miter->__remaining) { struct scatterlist *sg; - unsigned long pgoffset; if (!__sg_page_iter_next(&miter->piter)) return false; sg = miter->piter.sg; - pgoffset = miter->piter.sg_pgoffset; - miter->__offset = pgoffset ? 0 : sg->offset; + miter->__offset = miter->piter.sg_pgoffset ? 0 : sg->offset; + miter->piter.sg_pgoffset += miter->__offset >> PAGE_SHIFT; + miter->__offset &= PAGE_SIZE - 1; miter->__remaining = sg->offset + sg->length - - (pgoffset << PAGE_SHIFT) - miter->__offset; + (miter->piter.sg_pgoffset << PAGE_SHIFT) - + miter->__offset; miter->__remaining = min_t(unsigned long, miter->__remaining, PAGE_SIZE - miter->__offset); } diff --git a/lib/sg_pool.c b/lib/sg_pool.c index cff20df2695e..db29e5c1f790 100644 --- a/lib/sg_pool.c +++ b/lib/sg_pool.c @@ -70,18 +70,27 @@ static struct scatterlist *sg_pool_alloc(unsigned int nents, gfp_t gfp_mask) /** * sg_free_table_chained - Free a previously mapped sg table * @table: The sg table header to use - * @first_chunk: was first_chunk not NULL in sg_alloc_table_chained? + * @nents_first_chunk: size of the first_chunk SGL passed to + * sg_alloc_table_chained * * Description: * Free an sg table previously allocated and setup with * sg_alloc_table_chained(). * + * @nents_first_chunk has to be same with that same parameter passed + * to sg_alloc_table_chained(). + * **/ -void sg_free_table_chained(struct sg_table *table, bool first_chunk) +void sg_free_table_chained(struct sg_table *table, + unsigned nents_first_chunk) { - if (first_chunk && table->orig_nents <= SG_CHUNK_SIZE) + if (table->orig_nents <= nents_first_chunk) return; - __sg_free_table(table, SG_CHUNK_SIZE, first_chunk, sg_pool_free); + + if (nents_first_chunk == 1) + nents_first_chunk = 0; + + __sg_free_table(table, SG_CHUNK_SIZE, nents_first_chunk, sg_pool_free); } EXPORT_SYMBOL_GPL(sg_free_table_chained); @@ -90,31 +99,41 @@ EXPORT_SYMBOL_GPL(sg_free_table_chained); * @table: The sg table header to use * @nents: Number of entries in sg list * @first_chunk: first SGL + * @nents_first_chunk: number of the SGL of @first_chunk * * Description: * Allocate and chain SGLs in an sg table. If @nents@ is larger than - * SG_CHUNK_SIZE a chained sg table will be setup. + * @nents_first_chunk a chained sg table will be setup. @first_chunk is + * ignored if nents_first_chunk <= 1 because user expects the SGL points + * non-chain SGL. * **/ int sg_alloc_table_chained(struct sg_table *table, int nents, - struct scatterlist *first_chunk) + struct scatterlist *first_chunk, unsigned nents_first_chunk) { int ret; BUG_ON(!nents); - if (first_chunk) { - if (nents <= SG_CHUNK_SIZE) { + if (first_chunk && nents_first_chunk) { + if (nents <= nents_first_chunk) { table->nents = table->orig_nents = nents; sg_init_table(table->sgl, nents); return 0; } } + /* User supposes that the 1st SGL includes real entry */ + if (nents_first_chunk <= 1) { + first_chunk = NULL; + nents_first_chunk = 0; + } + ret = __sg_alloc_table(table, nents, SG_CHUNK_SIZE, - first_chunk, GFP_ATOMIC, sg_pool_alloc); + first_chunk, nents_first_chunk, + GFP_ATOMIC, sg_pool_alloc); if (unlikely(ret)) - sg_free_table_chained(table, (bool)first_chunk); + sg_free_table_chained(table, nents_first_chunk); return ret; } EXPORT_SYMBOL_GPL(sg_alloc_table_chained); diff --git a/lib/smp_processor_id.c b/lib/smp_processor_id.c index 157d9e31f6c2..60ba93fc42ce 100644 --- a/lib/smp_processor_id.c +++ b/lib/smp_processor_id.c @@ -23,7 +23,7 @@ unsigned int check_preemption_disabled(const char *what1, const char *what2) * Kernel threads bound to a single CPU can safely use * smp_processor_id(): */ - if (cpumask_equal(¤t->cpus_allowed, cpumask_of(this_cpu))) + if (cpumask_equal(current->cpus_ptr, cpumask_of(this_cpu))) goto out; /* diff --git a/lib/string_helpers.c b/lib/string_helpers.c index 4403e1924f73..3a90a9e2b94a 100644 --- a/lib/string_helpers.c +++ b/lib/string_helpers.c @@ -540,6 +540,25 @@ int string_escape_mem(const char *src, size_t isz, char *dst, size_t osz, } EXPORT_SYMBOL(string_escape_mem); +int string_escape_mem_ascii(const char *src, size_t isz, char *dst, + size_t osz) +{ + char *p = dst; + char *end = p + osz; + + while (isz--) { + unsigned char c = *src++; + + if (!isprint(c) || !isascii(c) || c == '"' || c == '\\') + escape_hex(c, &p, end); + else + escape_passthrough(c, &p, end); + } + + return p - dst; +} +EXPORT_SYMBOL(string_escape_mem_ascii); + /* * Return an allocated string that has been escaped of special characters * and double quotes, making it safe to log in quotes. diff --git a/lib/test_blackhole_dev.c b/lib/test_blackhole_dev.c new file mode 100644 index 000000000000..4c40580a99a3 --- /dev/null +++ b/lib/test_blackhole_dev.c @@ -0,0 +1,100 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * This module tests the blackhole_dev that is created during the + * net subsystem initialization. The test this module performs is + * by injecting an skb into the stack with skb->dev as the + * blackhole_dev and expects kernel to behave in a sane manner + * (in other words, *not crash*)! + * + * Copyright (c) 2018, Mahesh Bandewar <maheshb@google.com> + */ + +#include <linux/init.h> +#include <linux/module.h> +#include <linux/printk.h> +#include <linux/skbuff.h> +#include <linux/netdevice.h> +#include <linux/udp.h> +#include <linux/ipv6.h> + +#include <net/dst.h> + +#define SKB_SIZE 256 +#define HEAD_SIZE (14+40+8) /* Ether + IPv6 + UDP */ +#define TAIL_SIZE 32 /* random tail-room */ + +#define UDP_PORT 1234 + +static int __init test_blackholedev_init(void) +{ + struct ipv6hdr *ip6h; + struct sk_buff *skb; + struct ethhdr *ethh; + struct udphdr *uh; + int data_len; + int ret; + + skb = alloc_skb(SKB_SIZE, GFP_KERNEL); + if (!skb) + return -ENOMEM; + + /* Reserve head-room for the headers */ + skb_reserve(skb, HEAD_SIZE); + + /* Add data to the skb */ + data_len = SKB_SIZE - (HEAD_SIZE + TAIL_SIZE); + memset(__skb_put(skb, data_len), 0xf, data_len); + + /* Add protocol data */ + /* (Transport) UDP */ + uh = (struct udphdr *)skb_push(skb, sizeof(struct udphdr)); + skb_set_transport_header(skb, 0); + uh->source = uh->dest = htons(UDP_PORT); + uh->len = htons(data_len); + uh->check = 0; + /* (Network) IPv6 */ + ip6h = (struct ipv6hdr *)skb_push(skb, sizeof(struct ipv6hdr)); + skb_set_network_header(skb, 0); + ip6h->hop_limit = 32; + ip6h->payload_len = data_len + sizeof(struct udphdr); + ip6h->nexthdr = IPPROTO_UDP; + ip6h->saddr = in6addr_loopback; + ip6h->daddr = in6addr_loopback; + /* Ether */ + ethh = (struct ethhdr *)skb_push(skb, sizeof(struct ethhdr)); + skb_set_mac_header(skb, 0); + + skb->protocol = htons(ETH_P_IPV6); + skb->pkt_type = PACKET_HOST; + skb->dev = blackhole_netdev; + + /* Now attempt to send the packet */ + ret = dev_queue_xmit(skb); + + switch (ret) { + case NET_XMIT_SUCCESS: + pr_warn("dev_queue_xmit() returned NET_XMIT_SUCCESS\n"); + break; + case NET_XMIT_DROP: + pr_warn("dev_queue_xmit() returned NET_XMIT_DROP\n"); + break; + case NET_XMIT_CN: + pr_warn("dev_queue_xmit() returned NET_XMIT_CN\n"); + break; + default: + pr_err("dev_queue_xmit() returned UNKNOWN(%d)\n", ret); + } + + return 0; +} + +static void __exit test_blackholedev_exit(void) +{ + pr_warn("test_blackholedev module terminating.\n"); +} + +module_init(test_blackholedev_init); +module_exit(test_blackholedev_exit); + +MODULE_AUTHOR("Mahesh Bandewar <maheshb@google.com>"); +MODULE_LICENSE("GPL"); diff --git a/lib/test_kasan.c b/lib/test_kasan.c index e3c593c38eff..b63b367a94e8 100644 --- a/lib/test_kasan.c +++ b/lib/test_kasan.c @@ -7,16 +7,17 @@ #define pr_fmt(fmt) "kasan test: %s " fmt, __func__ +#include <linux/bitops.h> #include <linux/delay.h> +#include <linux/kasan.h> #include <linux/kernel.h> -#include <linux/mman.h> #include <linux/mm.h> +#include <linux/mman.h> +#include <linux/module.h> #include <linux/printk.h> #include <linux/slab.h> #include <linux/string.h> #include <linux/uaccess.h> -#include <linux/module.h> -#include <linux/kasan.h> /* * Note: test functions are marked noinline so that their names appear in @@ -619,6 +620,95 @@ static noinline void __init kasan_strings(void) strnlen(ptr, 1); } +static noinline void __init kasan_bitops(void) +{ + /* + * Allocate 1 more byte, which causes kzalloc to round up to 16-bytes; + * this way we do not actually corrupt other memory. + */ + long *bits = kzalloc(sizeof(*bits) + 1, GFP_KERNEL); + if (!bits) + return; + + /* + * Below calls try to access bit within allocated memory; however, the + * below accesses are still out-of-bounds, since bitops are defined to + * operate on the whole long the bit is in. + */ + pr_info("out-of-bounds in set_bit\n"); + set_bit(BITS_PER_LONG, bits); + + pr_info("out-of-bounds in __set_bit\n"); + __set_bit(BITS_PER_LONG, bits); + + pr_info("out-of-bounds in clear_bit\n"); + clear_bit(BITS_PER_LONG, bits); + + pr_info("out-of-bounds in __clear_bit\n"); + __clear_bit(BITS_PER_LONG, bits); + + pr_info("out-of-bounds in clear_bit_unlock\n"); + clear_bit_unlock(BITS_PER_LONG, bits); + + pr_info("out-of-bounds in __clear_bit_unlock\n"); + __clear_bit_unlock(BITS_PER_LONG, bits); + + pr_info("out-of-bounds in change_bit\n"); + change_bit(BITS_PER_LONG, bits); + + pr_info("out-of-bounds in __change_bit\n"); + __change_bit(BITS_PER_LONG, bits); + + /* + * Below calls try to access bit beyond allocated memory. + */ + pr_info("out-of-bounds in test_and_set_bit\n"); + test_and_set_bit(BITS_PER_LONG + BITS_PER_BYTE, bits); + + pr_info("out-of-bounds in __test_and_set_bit\n"); + __test_and_set_bit(BITS_PER_LONG + BITS_PER_BYTE, bits); + + pr_info("out-of-bounds in test_and_set_bit_lock\n"); + test_and_set_bit_lock(BITS_PER_LONG + BITS_PER_BYTE, bits); + + pr_info("out-of-bounds in test_and_clear_bit\n"); + test_and_clear_bit(BITS_PER_LONG + BITS_PER_BYTE, bits); + + pr_info("out-of-bounds in __test_and_clear_bit\n"); + __test_and_clear_bit(BITS_PER_LONG + BITS_PER_BYTE, bits); + + pr_info("out-of-bounds in test_and_change_bit\n"); + test_and_change_bit(BITS_PER_LONG + BITS_PER_BYTE, bits); + + pr_info("out-of-bounds in __test_and_change_bit\n"); + __test_and_change_bit(BITS_PER_LONG + BITS_PER_BYTE, bits); + + pr_info("out-of-bounds in test_bit\n"); + (void)test_bit(BITS_PER_LONG + BITS_PER_BYTE, bits); + +#if defined(clear_bit_unlock_is_negative_byte) + pr_info("out-of-bounds in clear_bit_unlock_is_negative_byte\n"); + clear_bit_unlock_is_negative_byte(BITS_PER_LONG + BITS_PER_BYTE, bits); +#endif + kfree(bits); +} + +static noinline void __init kmalloc_double_kzfree(void) +{ + char *ptr; + size_t size = 16; + + pr_info("double-free (kzfree)\n"); + ptr = kmalloc(size, GFP_KERNEL); + if (!ptr) { + pr_err("Allocation failed\n"); + return; + } + + kzfree(ptr); + kzfree(ptr); +} + static int __init kmalloc_tests_init(void) { /* @@ -660,6 +750,8 @@ static int __init kmalloc_tests_init(void) kasan_memchr(); kasan_memcmp(); kasan_strings(); + kasan_bitops(); + kmalloc_double_kzfree(); kasan_restore_multi_shot(multishot); diff --git a/lib/test_xarray.c b/lib/test_xarray.c index 5d4bad8bd96a..9d631a7b6a70 100644 --- a/lib/test_xarray.c +++ b/lib/test_xarray.c @@ -38,6 +38,12 @@ static void *xa_store_index(struct xarray *xa, unsigned long index, gfp_t gfp) return xa_store(xa, index, xa_mk_index(index), gfp); } +static void xa_insert_index(struct xarray *xa, unsigned long index) +{ + XA_BUG_ON(xa, xa_insert(xa, index, xa_mk_index(index), + GFP_KERNEL) != 0); +} + static void xa_alloc_index(struct xarray *xa, unsigned long index, gfp_t gfp) { u32 id; @@ -338,6 +344,37 @@ static noinline void check_xa_shrink(struct xarray *xa) } } +static noinline void check_insert(struct xarray *xa) +{ + unsigned long i; + + for (i = 0; i < 1024; i++) { + xa_insert_index(xa, i); + XA_BUG_ON(xa, xa_load(xa, i - 1) != NULL); + XA_BUG_ON(xa, xa_load(xa, i + 1) != NULL); + xa_erase_index(xa, i); + } + + for (i = 10; i < BITS_PER_LONG; i++) { + xa_insert_index(xa, 1UL << i); + XA_BUG_ON(xa, xa_load(xa, (1UL << i) - 1) != NULL); + XA_BUG_ON(xa, xa_load(xa, (1UL << i) + 1) != NULL); + xa_erase_index(xa, 1UL << i); + + xa_insert_index(xa, (1UL << i) - 1); + XA_BUG_ON(xa, xa_load(xa, (1UL << i) - 2) != NULL); + XA_BUG_ON(xa, xa_load(xa, 1UL << i) != NULL); + xa_erase_index(xa, (1UL << i) - 1); + } + + xa_insert_index(xa, ~0UL); + XA_BUG_ON(xa, xa_load(xa, 0UL) != NULL); + XA_BUG_ON(xa, xa_load(xa, ~1UL) != NULL); + xa_erase_index(xa, ~0UL); + + XA_BUG_ON(xa, !xa_empty(xa)); +} + static noinline void check_cmpxchg(struct xarray *xa) { void *FIVE = xa_mk_value(5); @@ -1527,6 +1564,7 @@ static int xarray_checks(void) check_xa_mark(&array); check_xa_shrink(&array); check_xas_erase(&array); + check_insert(&array); check_cmpxchg(&array); check_reserve(&array); check_reserve(&xa0); diff --git a/lib/vdso/Kconfig b/lib/vdso/Kconfig new file mode 100644 index 000000000000..cc00364bd2c2 --- /dev/null +++ b/lib/vdso/Kconfig @@ -0,0 +1,36 @@ +# SPDX-License-Identifier: GPL-2.0 + +config HAVE_GENERIC_VDSO + bool + +if HAVE_GENERIC_VDSO + +config GENERIC_GETTIMEOFDAY + bool + help + This is a generic implementation of gettimeofday vdso. + Each architecture that enables this feature has to + provide the fallback implementation. + +config GENERIC_VDSO_32 + bool + depends on GENERIC_GETTIMEOFDAY && !64BIT + help + This config option helps to avoid possible performance issues + in 32 bit only architectures. + +config GENERIC_COMPAT_VDSO + bool + help + This config option enables the compat VDSO layer. + +config CROSS_COMPILE_COMPAT_VDSO + string "32 bit Toolchain prefix for compat vDSO" + default "" + depends on GENERIC_COMPAT_VDSO + help + Defines the cross-compiler prefix for compiling compat vDSO. + If a 64 bit compiler (i.e. x86_64) can compile the VDSO for + 32 bit, it does not need to define this parameter. + +endif diff --git a/lib/vdso/Makefile b/lib/vdso/Makefile new file mode 100644 index 000000000000..c415a685d61b --- /dev/null +++ b/lib/vdso/Makefile @@ -0,0 +1,22 @@ +# SPDX-License-Identifier: GPL-2.0 + +GENERIC_VDSO_MK_PATH := $(abspath $(lastword $(MAKEFILE_LIST))) +GENERIC_VDSO_DIR := $(dir $(GENERIC_VDSO_MK_PATH)) + +c-gettimeofday-$(CONFIG_GENERIC_GETTIMEOFDAY) := $(addprefix $(GENERIC_VDSO_DIR), gettimeofday.c) + +# This cmd checks that the vdso library does not contain absolute relocation +# It has to be called after the linking of the vdso library and requires it +# as a parameter. +# +# $(ARCH_REL_TYPE_ABS) is defined in the arch specific makefile and corresponds +# to the absolute relocation types printed by "objdump -R" and accepted by the +# dynamic linker. +ifndef ARCH_REL_TYPE_ABS +$(error ARCH_REL_TYPE_ABS is not set) +endif + +quiet_cmd_vdso_check = VDSOCHK $@ + cmd_vdso_check = if $(OBJDUMP) -R $@ | egrep -h "$(ARCH_REL_TYPE_ABS)"; \ + then (echo >&2 "$@: dynamic relocations are not supported"; \ + rm -f $@; /bin/false); fi diff --git a/lib/vdso/gettimeofday.c b/lib/vdso/gettimeofday.c new file mode 100644 index 000000000000..2d1c1f241fd9 --- /dev/null +++ b/lib/vdso/gettimeofday.c @@ -0,0 +1,239 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Generic userspace implementations of gettimeofday() and similar. + */ +#include <linux/compiler.h> +#include <linux/math64.h> +#include <linux/time.h> +#include <linux/kernel.h> +#include <linux/hrtimer_defs.h> +#include <vdso/datapage.h> +#include <vdso/helpers.h> + +/* + * The generic vDSO implementation requires that gettimeofday.h + * provides: + * - __arch_get_vdso_data(): to get the vdso datapage. + * - __arch_get_hw_counter(): to get the hw counter based on the + * clock_mode. + * - gettimeofday_fallback(): fallback for gettimeofday. + * - clock_gettime_fallback(): fallback for clock_gettime. + * - clock_getres_fallback(): fallback for clock_getres. + */ +#ifdef ENABLE_COMPAT_VDSO +#include <asm/vdso/compat_gettimeofday.h> +#else +#include <asm/vdso/gettimeofday.h> +#endif /* ENABLE_COMPAT_VDSO */ + +#ifndef vdso_calc_delta +/* + * Default implementation which works for all sane clocksources. That + * obviously excludes x86/TSC. + */ +static __always_inline +u64 vdso_calc_delta(u64 cycles, u64 last, u64 mask, u32 mult) +{ + return ((cycles - last) & mask) * mult; +} +#endif + +static int do_hres(const struct vdso_data *vd, clockid_t clk, + struct __kernel_timespec *ts) +{ + const struct vdso_timestamp *vdso_ts = &vd->basetime[clk]; + u64 cycles, last, sec, ns; + u32 seq; + + do { + seq = vdso_read_begin(vd); + cycles = __arch_get_hw_counter(vd->clock_mode); + ns = vdso_ts->nsec; + last = vd->cycle_last; + if (unlikely((s64)cycles < 0)) + return clock_gettime_fallback(clk, ts); + + ns += vdso_calc_delta(cycles, last, vd->mask, vd->mult); + ns >>= vd->shift; + sec = vdso_ts->sec; + } while (unlikely(vdso_read_retry(vd, seq))); + + /* + * Do this outside the loop: a race inside the loop could result + * in __iter_div_u64_rem() being extremely slow. + */ + ts->tv_sec = sec + __iter_div_u64_rem(ns, NSEC_PER_SEC, &ns); + ts->tv_nsec = ns; + + return 0; +} + +static void do_coarse(const struct vdso_data *vd, clockid_t clk, + struct __kernel_timespec *ts) +{ + const struct vdso_timestamp *vdso_ts = &vd->basetime[clk]; + u32 seq; + + do { + seq = vdso_read_begin(vd); + ts->tv_sec = vdso_ts->sec; + ts->tv_nsec = vdso_ts->nsec; + } while (unlikely(vdso_read_retry(vd, seq))); +} + +static __maybe_unused int +__cvdso_clock_gettime(clockid_t clock, struct __kernel_timespec *ts) +{ + const struct vdso_data *vd = __arch_get_vdso_data(); + u32 msk; + + /* Check for negative values or invalid clocks */ + if (unlikely((u32) clock >= MAX_CLOCKS)) + goto fallback; + + /* + * Convert the clockid to a bitmask and use it to check which + * clocks are handled in the VDSO directly. + */ + msk = 1U << clock; + if (likely(msk & VDSO_HRES)) { + return do_hres(&vd[CS_HRES_COARSE], clock, ts); + } else if (msk & VDSO_COARSE) { + do_coarse(&vd[CS_HRES_COARSE], clock, ts); + return 0; + } else if (msk & VDSO_RAW) { + return do_hres(&vd[CS_RAW], clock, ts); + } + +fallback: + return clock_gettime_fallback(clock, ts); +} + +static __maybe_unused int +__cvdso_clock_gettime32(clockid_t clock, struct old_timespec32 *res) +{ + struct __kernel_timespec ts; + int ret; + + if (res == NULL) + goto fallback; + + ret = __cvdso_clock_gettime(clock, &ts); + + if (ret == 0) { + res->tv_sec = ts.tv_sec; + res->tv_nsec = ts.tv_nsec; + } + + return ret; + +fallback: + return clock_gettime_fallback(clock, (struct __kernel_timespec *)res); +} + +static __maybe_unused int +__cvdso_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz) +{ + const struct vdso_data *vd = __arch_get_vdso_data(); + + if (likely(tv != NULL)) { + struct __kernel_timespec ts; + + if (do_hres(&vd[CS_HRES_COARSE], CLOCK_REALTIME, &ts)) + return gettimeofday_fallback(tv, tz); + + tv->tv_sec = ts.tv_sec; + tv->tv_usec = (u32)ts.tv_nsec / NSEC_PER_USEC; + } + + if (unlikely(tz != NULL)) { + tz->tz_minuteswest = vd[CS_HRES_COARSE].tz_minuteswest; + tz->tz_dsttime = vd[CS_HRES_COARSE].tz_dsttime; + } + + return 0; +} + +#ifdef VDSO_HAS_TIME +static __maybe_unused time_t __cvdso_time(time_t *time) +{ + const struct vdso_data *vd = __arch_get_vdso_data(); + time_t t = READ_ONCE(vd[CS_HRES_COARSE].basetime[CLOCK_REALTIME].sec); + + if (time) + *time = t; + + return t; +} +#endif /* VDSO_HAS_TIME */ + +#ifdef VDSO_HAS_CLOCK_GETRES +static __maybe_unused +int __cvdso_clock_getres(clockid_t clock, struct __kernel_timespec *res) +{ + const struct vdso_data *vd = __arch_get_vdso_data(); + u64 ns; + u32 msk; + u64 hrtimer_res = READ_ONCE(vd[CS_HRES_COARSE].hrtimer_res); + + /* Check for negative values or invalid clocks */ + if (unlikely((u32) clock >= MAX_CLOCKS)) + goto fallback; + + /* + * Convert the clockid to a bitmask and use it to check which + * clocks are handled in the VDSO directly. + */ + msk = 1U << clock; + if (msk & VDSO_HRES) { + /* + * Preserves the behaviour of posix_get_hrtimer_res(). + */ + ns = hrtimer_res; + } else if (msk & VDSO_COARSE) { + /* + * Preserves the behaviour of posix_get_coarse_res(). + */ + ns = LOW_RES_NSEC; + } else if (msk & VDSO_RAW) { + /* + * Preserves the behaviour of posix_get_hrtimer_res(). + */ + ns = hrtimer_res; + } else { + goto fallback; + } + + if (res) { + res->tv_sec = 0; + res->tv_nsec = ns; + } + + return 0; + +fallback: + return clock_getres_fallback(clock, res); +} + +static __maybe_unused int +__cvdso_clock_getres_time32(clockid_t clock, struct old_timespec32 *res) +{ + struct __kernel_timespec ts; + int ret; + + if (res == NULL) + goto fallback; + + ret = __cvdso_clock_getres(clock, &ts); + + if (ret == 0) { + res->tv_sec = ts.tv_sec; + res->tv_nsec = ts.tv_nsec; + } + + return ret; + +fallback: + return clock_getres_fallback(clock, (struct __kernel_timespec *)res); +} +#endif /* VDSO_HAS_CLOCK_GETRES */ diff --git a/lib/vsprintf.c b/lib/vsprintf.c index 63937044c57d..b0967cf17137 100644 --- a/lib/vsprintf.c +++ b/lib/vsprintf.c @@ -599,7 +599,7 @@ static char *string_nocheck(char *buf, char *end, const char *s, struct printf_spec spec) { int len = 0; - size_t lim = spec.precision; + int lim = spec.precision; while (lim--) { char c = *s++; @@ -1799,7 +1799,7 @@ char *clock(char *buf, char *end, struct clk *clk, struct printf_spec spec, #ifdef CONFIG_COMMON_CLK return string(buf, end, __clk_get_name(clk), spec); #else - return error_string(buf, end, "(%pC?)", spec); + return ptr_to_id(buf, end, clk, spec); #endif } } diff --git a/lib/xarray.c b/lib/xarray.c index 6be3acbb861f..446b956c9188 100644 --- a/lib/xarray.c +++ b/lib/xarray.c @@ -298,6 +298,8 @@ bool xas_nomem(struct xa_state *xas, gfp_t gfp) xas_destroy(xas); return false; } + if (xas->xa->xa_flags & XA_FLAGS_ACCOUNT) + gfp |= __GFP_ACCOUNT; xas->xa_alloc = kmem_cache_alloc(radix_tree_node_cachep, gfp); if (!xas->xa_alloc) return false; @@ -325,6 +327,8 @@ static bool __xas_nomem(struct xa_state *xas, gfp_t gfp) xas_destroy(xas); return false; } + if (xas->xa->xa_flags & XA_FLAGS_ACCOUNT) + gfp |= __GFP_ACCOUNT; if (gfpflags_allow_blocking(gfp)) { xas_unlock_type(xas, lock_type); xas->xa_alloc = kmem_cache_alloc(radix_tree_node_cachep, gfp); @@ -358,8 +362,12 @@ static void *xas_alloc(struct xa_state *xas, unsigned int shift) if (node) { xas->xa_alloc = NULL; } else { - node = kmem_cache_alloc(radix_tree_node_cachep, - GFP_NOWAIT | __GFP_NOWARN); + gfp_t gfp = GFP_NOWAIT | __GFP_NOWARN; + + if (xas->xa->xa_flags & XA_FLAGS_ACCOUNT) + gfp |= __GFP_ACCOUNT; + + node = kmem_cache_alloc(radix_tree_node_cachep, gfp); if (!node) { xas_set_err(xas, -ENOMEM); return NULL; |