diff options
Diffstat (limited to 'lib')
| -rw-r--r-- | lib/Kconfig | 12 | ||||
| -rw-r--r-- | lib/Kconfig.debug | 37 | ||||
| -rw-r--r-- | lib/Makefile | 3 | ||||
| -rw-r--r-- | lib/checksum.c | 11 | ||||
| -rw-r--r-- | lib/crc32.c | 4 | ||||
| -rw-r--r-- | lib/crypto/Makefile | 2 | ||||
| -rw-r--r-- | lib/crypto/mpi/mpi-bit.c | 1 | ||||
| -rw-r--r-- | lib/crypto/simd.c | 11 | ||||
| -rw-r--r-- | lib/debugobjects.c | 849 | ||||
| -rw-r--r-- | lib/dim/dim.c | 3 | ||||
| -rw-r--r-- | lib/dim/net_dim.c | 10 | ||||
| -rw-r--r-- | lib/dynamic_queue_limits.c | 2 | ||||
| -rw-r--r-- | lib/interval_tree_test.c | 2 | ||||
| -rw-r--r-- | lib/iomem_copy.c | 136 | ||||
| -rw-r--r-- | lib/iov_iter.c | 68 | ||||
| -rw-r--r-- | lib/kunit/debugfs.c | 9 | ||||
| -rw-r--r-- | lib/kunit/kunit-test.c | 2 | ||||
| -rw-r--r-- | lib/kunit/string-stream-test.c | 1 | ||||
| -rw-r--r-- | lib/locking-selftest.c | 39 | ||||
| -rw-r--r-- | lib/logic_pio.c | 4 | ||||
| -rw-r--r-- | lib/math/test_div64.c | 85 | ||||
| -rw-r--r-- | lib/packing.c | 322 | ||||
| -rw-r--r-- | lib/packing_test.c | 413 | ||||
| -rw-r--r-- | lib/random32.c | 2 | ||||
| -rw-r--r-- | lib/rbtree_test.c | 2 | ||||
| -rw-r--r-- | lib/test_bpf.c | 2 | ||||
| -rw-r--r-- | lib/test_parman.c | 2 | ||||
| -rw-r--r-- | lib/test_printf.c | 61 | ||||
| -rw-r--r-- | lib/test_scanf.c | 2 | ||||
| -rw-r--r-- | lib/vsprintf.c | 57 |
30 files changed, 1597 insertions, 557 deletions
diff --git a/lib/Kconfig b/lib/Kconfig index b38849af6f13..50d85f38b569 100644 --- a/lib/Kconfig +++ b/lib/Kconfig @@ -40,6 +40,18 @@ config PACKING When in doubt, say N. +config PACKING_KUNIT_TEST + tristate "KUnit tests for packing library" if !KUNIT_ALL_TESTS + depends on PACKING && KUNIT + default KUNIT_ALL_TESTS + help + This builds KUnit tests for the packing library. + + For more information on KUnit and unit tests in general, + please refer to the KUnit documentation in Documentation/dev-tools/kunit/. + + When in doubt, say N. + config BITREVERSE tristate diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 7312ae7c3cc5..a2fe6d5cfbd2 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -1328,19 +1328,6 @@ config SCHEDSTATS endmenu -config DEBUG_TIMEKEEPING - bool "Enable extra timekeeping sanity checking" - help - This option will enable additional timekeeping sanity checks - which may be helpful when diagnosing issues where timekeeping - problems are suspected. - - This may include checks in the timekeeping hotpaths, so this - option may have a (very small) performance impact to some - workloads. - - If unsure, say N. - config DEBUG_PREEMPT bool "Debug preemptible kernel" depends on DEBUG_KERNEL && PREEMPTION && TRACE_IRQFLAGS_SUPPORT @@ -1409,22 +1396,14 @@ config PROVE_LOCKING For more details, see Documentation/locking/lockdep-design.rst. config PROVE_RAW_LOCK_NESTING - bool "Enable raw_spinlock - spinlock nesting checks" + bool depends on PROVE_LOCKING - default n + default y help Enable the raw_spinlock vs. spinlock nesting checks which ensure that the lock nesting rules for PREEMPT_RT enabled kernels are not violated. - NOTE: There are known nesting problems. So if you enable this - option expect lockdep splats until these problems have been fully - addressed which is work in progress. This config switch allows to - identify and analyze these problems. It will be removed and the - check permanently enabled once the main issues have been fixed. - - If unsure, select N. - config LOCK_STAT bool "Lock usage statistics" depends on DEBUG_KERNEL && LOCK_DEBUGGING_SUPPORT @@ -1905,7 +1884,7 @@ config STRICT_DEVMEM bool "Filter access to /dev/mem" depends on MMU && DEVMEM depends on ARCH_HAS_DEVMEM_IS_ALLOWED || GENERIC_LIB_DEVMEM_IS_ALLOWED - default y if PPC || X86 || ARM64 + default y if PPC || X86 || ARM64 || S390 help If this option is disabled, you allow userspace (root) access to all of memory, including kernel and userspace memory. Accidental @@ -2115,6 +2094,16 @@ config FAIL_SUNRPC Provide fault-injection capability for SunRPC and its consumers. +config FAIL_SKB_REALLOC + bool "Fault-injection capability forcing skb to reallocate" + depends on FAULT_INJECTION_DEBUG_FS + help + Provide fault-injection capability that forces the skb to be + reallocated, catching possible invalid pointers to the skb. + + For more information, check + Documentation/dev-tools/fault-injection/fault-injection.rst + config FAULT_INJECTION_CONFIGFS bool "Configfs interface for fault-injection capabilities" depends on FAULT_INJECTION diff --git a/lib/Makefile b/lib/Makefile index 773adf88af41..b393dd8151e2 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -35,7 +35,7 @@ lib-y := ctype.o string.o vsprintf.o cmdline.o \ is_single_threaded.o plist.o decompress.o kobject_uevent.o \ earlycpio.o seq_buf.o siphash.o dec_and_lock.o \ nmi_backtrace.o win_minmax.o memcat_p.o \ - buildid.o objpool.o union_find.o + buildid.o objpool.o union_find.o iomem_copy.o lib-$(CONFIG_PRINTK) += dump_stack.o lib-$(CONFIG_SMP) += cpumask.o @@ -154,6 +154,7 @@ obj-$(CONFIG_DEBUG_OBJECTS) += debugobjects.o obj-$(CONFIG_BITREVERSE) += bitrev.o obj-$(CONFIG_LINEAR_RANGES) += linear_ranges.o obj-$(CONFIG_PACKING) += packing.o +obj-$(CONFIG_PACKING_KUNIT_TEST) += packing_test.o obj-$(CONFIG_CRC_CCITT) += crc-ccitt.o obj-$(CONFIG_CRC16) += crc16.o obj-$(CONFIG_CRC_T10DIF)+= crc-t10dif.o diff --git a/lib/checksum.c b/lib/checksum.c index 6860d6b05a17..025ba546e1ec 100644 --- a/lib/checksum.c +++ b/lib/checksum.c @@ -34,15 +34,6 @@ #include <asm/byteorder.h> #ifndef do_csum -static inline unsigned short from32to16(unsigned int x) -{ - /* add up 16-bit and 16-bit for 16+c bit */ - x = (x & 0xffff) + (x >> 16); - /* add up carry.. */ - x = (x & 0xffff) + (x >> 16); - return x; -} - static unsigned int do_csum(const unsigned char *buff, int len) { int odd; @@ -90,7 +81,7 @@ static unsigned int do_csum(const unsigned char *buff, int len) #else result += (*buff << 8); #endif - result = from32to16(result); + result = csum_from32to16(result); if (odd) result = ((result >> 8) & 0xff) | ((result & 0xff) << 8); out: diff --git a/lib/crc32.c b/lib/crc32.c index 5649847d0a8d..ff587fee3893 100644 --- a/lib/crc32.c +++ b/lib/crc32.c @@ -205,7 +205,11 @@ EXPORT_SYMBOL(crc32_le); EXPORT_SYMBOL(__crc32c_le); u32 __pure crc32_le_base(u32, unsigned char const *, size_t) __alias(crc32_le); +EXPORT_SYMBOL(crc32_le_base); + u32 __pure __crc32c_le_base(u32, unsigned char const *, size_t) __alias(__crc32c_le); +EXPORT_SYMBOL(__crc32c_le_base); + u32 __pure crc32_be_base(u32, unsigned char const *, size_t) __alias(crc32_be); /* diff --git a/lib/crypto/Makefile b/lib/crypto/Makefile index 969baab8c805..01fac1cd05a1 100644 --- a/lib/crypto/Makefile +++ b/lib/crypto/Makefile @@ -58,3 +58,5 @@ libcurve25519-y += curve25519-selftest.o endif obj-$(CONFIG_MPILIB) += mpi/ + +obj-$(CONFIG_CRYPTO_MANAGER_EXTRA_TESTS) += simd.o diff --git a/lib/crypto/mpi/mpi-bit.c b/lib/crypto/mpi/mpi-bit.c index 835a2f0622a0..934d81311360 100644 --- a/lib/crypto/mpi/mpi-bit.c +++ b/lib/crypto/mpi/mpi-bit.c @@ -95,6 +95,7 @@ int mpi_set_bit(MPI a, unsigned int n) a->d[limbno] |= (A_LIMB_1<<bitno); return 0; } +EXPORT_SYMBOL_GPL(mpi_set_bit); /* * Shift A by N bits to the right. diff --git a/lib/crypto/simd.c b/lib/crypto/simd.c new file mode 100644 index 000000000000..9c36cb3bb49c --- /dev/null +++ b/lib/crypto/simd.c @@ -0,0 +1,11 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * SIMD testing utility functions + * + * Copyright 2024 Google LLC + */ + +#include <crypto/internal/simd.h> + +DEFINE_PER_CPU(bool, crypto_simd_disabled_for_test); +EXPORT_PER_CPU_SYMBOL_GPL(crypto_simd_disabled_for_test); diff --git a/lib/debugobjects.c b/lib/debugobjects.c index 5ce473ad499b..7f50c4480a4e 100644 --- a/lib/debugobjects.c +++ b/lib/debugobjects.c @@ -7,25 +7,30 @@ #define pr_fmt(fmt) "ODEBUG: " fmt +#include <linux/cpu.h> #include <linux/debugobjects.h> -#include <linux/interrupt.h> +#include <linux/debugfs.h> +#include <linux/hash.h> +#include <linux/kmemleak.h> #include <linux/sched.h> +#include <linux/sched/loadavg.h> #include <linux/sched/task_stack.h> #include <linux/seq_file.h> -#include <linux/debugfs.h> #include <linux/slab.h> -#include <linux/hash.h> -#include <linux/kmemleak.h> -#include <linux/cpu.h> +#include <linux/static_key.h> #define ODEBUG_HASH_BITS 14 #define ODEBUG_HASH_SIZE (1 << ODEBUG_HASH_BITS) -#define ODEBUG_POOL_SIZE 1024 -#define ODEBUG_POOL_MIN_LEVEL 256 -#define ODEBUG_POOL_PERCPU_SIZE 64 +/* Must be power of two */ #define ODEBUG_BATCH_SIZE 16 +/* Initial values. Must all be a multiple of batch size */ +#define ODEBUG_POOL_SIZE (64 * ODEBUG_BATCH_SIZE) +#define ODEBUG_POOL_MIN_LEVEL (ODEBUG_POOL_SIZE / 4) + +#define ODEBUG_POOL_PERCPU_SIZE (8 * ODEBUG_BATCH_SIZE) + #define ODEBUG_CHUNK_SHIFT PAGE_SHIFT #define ODEBUG_CHUNK_SIZE (1 << ODEBUG_CHUNK_SHIFT) #define ODEBUG_CHUNK_MASK (~(ODEBUG_CHUNK_SIZE - 1)) @@ -35,7 +40,7 @@ * 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_MAX (1024 / ODEBUG_BATCH_SIZE) #define ODEBUG_FREE_WORK_DELAY DIV_ROUND_UP(HZ, 10) struct debug_bucket { @@ -43,16 +48,24 @@ struct debug_bucket { 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; +struct pool_stats { + unsigned int cur_used; + unsigned int max_used; + unsigned int min_fill; }; -static DEFINE_PER_CPU(struct debug_percpu_free, percpu_obj_pool); +struct obj_pool { + struct hlist_head objects; + unsigned int cnt; + unsigned int min_cnt; + unsigned int max_cnt; + struct pool_stats stats; +} ____cacheline_aligned; + + +static DEFINE_PER_CPU_ALIGNED(struct obj_pool, pool_pcpu) = { + .max_cnt = ODEBUG_POOL_PERCPU_SIZE, +}; static struct debug_bucket obj_hash[ODEBUG_HASH_SIZE]; @@ -60,37 +73,32 @@ static struct debug_obj obj_static_pool[ODEBUG_POOL_SIZE] __initdata; static DEFINE_RAW_SPINLOCK(pool_lock); -static HLIST_HEAD(obj_pool); -static HLIST_HEAD(obj_to_free); +static struct obj_pool pool_global = { + .min_cnt = ODEBUG_POOL_MIN_LEVEL, + .max_cnt = ODEBUG_POOL_SIZE, + .stats = { + .min_fill = ODEBUG_POOL_SIZE, + }, +}; -/* - * 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 __data_racy obj_pool_min_free = ODEBUG_POOL_SIZE; -static int __data_racy obj_pool_free = ODEBUG_POOL_SIZE; -static int obj_pool_used; -static int __data_racy obj_pool_max_used; +static struct obj_pool pool_to_free = { + .max_cnt = UINT_MAX, +}; + +static HLIST_HEAD(pool_boot); + +static unsigned long avg_usage; static bool obj_freeing; -/* The number of objs on the global free list */ -static int obj_nr_tofree; static int __data_racy debug_objects_maxchain __read_mostly; static int __data_racy __maybe_unused debug_objects_maxchecked __read_mostly; static int __data_racy debug_objects_fixups __read_mostly; static int __data_racy debug_objects_warnings __read_mostly; -static int __data_racy debug_objects_enabled __read_mostly +static bool __data_racy debug_objects_enabled __read_mostly = CONFIG_DEBUG_OBJECTS_ENABLE_DEFAULT; -static int debug_objects_pool_size __ro_after_init - = ODEBUG_POOL_SIZE; -static int debug_objects_pool_min_level __ro_after_init - = ODEBUG_POOL_MIN_LEVEL; -static const struct debug_obj_descr *descr_test __read_mostly; -static struct kmem_cache *obj_cache __ro_after_init; +static const struct debug_obj_descr *descr_test __read_mostly; +static struct kmem_cache *obj_cache __ro_after_init; /* * Track numbers of kmem_cache_alloc()/free() calls done. @@ -101,19 +109,20 @@ static int __data_racy debug_objects_freed; static void free_obj_work(struct work_struct *work); static DECLARE_DELAYED_WORK(debug_obj_work, free_obj_work); +static DEFINE_STATIC_KEY_FALSE(obj_cache_enabled); + static int __init enable_object_debug(char *str) { - debug_objects_enabled = 1; + debug_objects_enabled = true; return 0; } +early_param("debug_objects", enable_object_debug); static int __init disable_object_debug(char *str) { - debug_objects_enabled = 0; + debug_objects_enabled = false; return 0; } - -early_param("debug_objects", enable_object_debug); early_param("no_debug_objects", disable_object_debug); static const char *obj_states[ODEBUG_STATE_MAX] = { @@ -125,61 +134,280 @@ static const char *obj_states[ODEBUG_STATE_MAX] = { [ODEBUG_STATE_NOTAVAILABLE] = "not available", }; -static void fill_pool(void) +static __always_inline unsigned int pool_count(struct obj_pool *pool) +{ + return READ_ONCE(pool->cnt); +} + +static __always_inline bool pool_should_refill(struct obj_pool *pool) +{ + return pool_count(pool) < pool->min_cnt; +} + +static __always_inline bool pool_must_refill(struct obj_pool *pool) +{ + return pool_count(pool) < pool->min_cnt / 2; +} + +static bool pool_move_batch(struct obj_pool *dst, struct obj_pool *src) { - gfp_t gfp = __GFP_HIGH | __GFP_NOWARN; + struct hlist_node *last, *next_batch, *first_batch; struct debug_obj *obj; - unsigned long flags; - if (likely(READ_ONCE(obj_pool_free) >= debug_objects_pool_min_level)) + if (dst->cnt >= dst->max_cnt || !src->cnt) + return false; + + first_batch = src->objects.first; + obj = hlist_entry(first_batch, typeof(*obj), node); + last = obj->batch_last; + next_batch = last->next; + + /* Move the next batch to the front of the source pool */ + src->objects.first = next_batch; + if (next_batch) + next_batch->pprev = &src->objects.first; + + /* Add the extracted batch to the destination pool */ + last->next = dst->objects.first; + if (last->next) + last->next->pprev = &last->next; + first_batch->pprev = &dst->objects.first; + dst->objects.first = first_batch; + + WRITE_ONCE(src->cnt, src->cnt - ODEBUG_BATCH_SIZE); + WRITE_ONCE(dst->cnt, dst->cnt + ODEBUG_BATCH_SIZE); + return true; +} + +static bool pool_push_batch(struct obj_pool *dst, struct hlist_head *head) +{ + struct hlist_node *last; + struct debug_obj *obj; + + if (dst->cnt >= dst->max_cnt) + return false; + + obj = hlist_entry(head->first, typeof(*obj), node); + last = obj->batch_last; + + hlist_splice_init(head, last, &dst->objects); + WRITE_ONCE(dst->cnt, dst->cnt + ODEBUG_BATCH_SIZE); + return true; +} + +static bool pool_pop_batch(struct hlist_head *head, struct obj_pool *src) +{ + struct hlist_node *last, *next; + struct debug_obj *obj; + + if (!src->cnt) + return false; + + /* Move the complete list to the head */ + hlist_move_list(&src->objects, head); + + obj = hlist_entry(head->first, typeof(*obj), node); + last = obj->batch_last; + next = last->next; + /* Disconnect the batch from the list */ + last->next = NULL; + + /* Move the node after last back to the source pool. */ + src->objects.first = next; + if (next) + next->pprev = &src->objects.first; + + WRITE_ONCE(src->cnt, src->cnt - ODEBUG_BATCH_SIZE); + return true; +} + +static struct debug_obj *__alloc_object(struct hlist_head *list) +{ + struct debug_obj *obj; + + if (unlikely(!list->first)) + return NULL; + + obj = hlist_entry(list->first, typeof(*obj), node); + hlist_del(&obj->node); + return obj; +} + +static void pcpu_refill_stats(void) +{ + struct pool_stats *stats = &pool_global.stats; + + WRITE_ONCE(stats->cur_used, stats->cur_used + ODEBUG_BATCH_SIZE); + + if (stats->cur_used > stats->max_used) + stats->max_used = stats->cur_used; + + if (pool_global.cnt < stats->min_fill) + stats->min_fill = pool_global.cnt; +} + +static struct debug_obj *pcpu_alloc(void) +{ + struct obj_pool *pcp = this_cpu_ptr(&pool_pcpu); + + lockdep_assert_irqs_disabled(); + + for (;;) { + struct debug_obj *obj = __alloc_object(&pcp->objects); + + if (likely(obj)) { + pcp->cnt--; + /* + * If this emptied a batch try to refill from the + * free pool. Don't do that if this was the top-most + * batch as pcpu_free() expects the per CPU pool + * to be less than ODEBUG_POOL_PERCPU_SIZE. + */ + if (unlikely(pcp->cnt < (ODEBUG_POOL_PERCPU_SIZE - ODEBUG_BATCH_SIZE) && + !(pcp->cnt % ODEBUG_BATCH_SIZE))) { + /* + * Don't try to allocate from the regular pool here + * to not exhaust it prematurely. + */ + if (pool_count(&pool_to_free)) { + guard(raw_spinlock)(&pool_lock); + pool_move_batch(pcp, &pool_to_free); + pcpu_refill_stats(); + } + } + return obj; + } + + guard(raw_spinlock)(&pool_lock); + if (!pool_move_batch(pcp, &pool_to_free)) { + if (!pool_move_batch(pcp, &pool_global)) + return NULL; + } + pcpu_refill_stats(); + } +} + +static void pcpu_free(struct debug_obj *obj) +{ + struct obj_pool *pcp = this_cpu_ptr(&pool_pcpu); + struct debug_obj *first; + + lockdep_assert_irqs_disabled(); + + if (!(pcp->cnt % ODEBUG_BATCH_SIZE)) { + obj->batch_last = &obj->node; + } else { + first = hlist_entry(pcp->objects.first, typeof(*first), node); + obj->batch_last = first->batch_last; + } + hlist_add_head(&obj->node, &pcp->objects); + pcp->cnt++; + + /* Pool full ? */ + if (pcp->cnt < ODEBUG_POOL_PERCPU_SIZE) return; + /* Remove a batch from the per CPU pool */ + guard(raw_spinlock)(&pool_lock); + /* Try to fit the batch into the pool_global first */ + if (!pool_move_batch(&pool_global, pcp)) + pool_move_batch(&pool_to_free, pcp); + WRITE_ONCE(pool_global.stats.cur_used, pool_global.stats.cur_used - ODEBUG_BATCH_SIZE); +} + +static void free_object_list(struct hlist_head *head) +{ + struct hlist_node *tmp; + struct debug_obj *obj; + int cnt = 0; + + hlist_for_each_entry_safe(obj, tmp, head, node) { + hlist_del(&obj->node); + kmem_cache_free(obj_cache, obj); + cnt++; + } + debug_objects_freed += cnt; +} + +static void fill_pool_from_freelist(void) +{ + static unsigned long state; + /* * Reuse objs from the global obj_to_free list; they will be * reinitialized when allocating. - * - * obj_nr_tofree is checked locklessly; the READ_ONCE() pairs with - * the WRITE_ONCE() in pool_lock critical sections. */ - if (READ_ONCE(obj_nr_tofree)) { - raw_spin_lock_irqsave(&pool_lock, flags); - /* - * Recheck with the lock held as the worker thread might have - * won the race and freed the global free list already. - */ - while (obj_nr_tofree && (obj_pool_free < debug_objects_pool_min_level)) { - obj = hlist_entry(obj_to_free.first, typeof(*obj), node); - hlist_del(&obj->node); - WRITE_ONCE(obj_nr_tofree, obj_nr_tofree - 1); - hlist_add_head(&obj->node, &obj_pool); - WRITE_ONCE(obj_pool_free, obj_pool_free + 1); + if (!pool_count(&pool_to_free)) + return; + + /* + * Prevent the context from being scheduled or interrupted after + * setting the state flag; + */ + guard(irqsave)(); + + /* + * Avoid lock contention on &pool_lock and avoid making the cache + * line exclusive by testing the bit before attempting to set it. + */ + if (test_bit(0, &state) || test_and_set_bit(0, &state)) + return; + + /* Avoid taking the lock when there is no work to do */ + while (pool_should_refill(&pool_global) && pool_count(&pool_to_free)) { + guard(raw_spinlock)(&pool_lock); + /* Move a batch if possible */ + pool_move_batch(&pool_global, &pool_to_free); + } + clear_bit(0, &state); +} + +static bool kmem_alloc_batch(struct hlist_head *head, struct kmem_cache *cache, gfp_t gfp) +{ + struct hlist_node *last = NULL; + struct debug_obj *obj; + + for (int cnt = 0; cnt < ODEBUG_BATCH_SIZE; cnt++) { + obj = kmem_cache_zalloc(cache, gfp); + if (!obj) { + free_object_list(head); + return false; } - raw_spin_unlock_irqrestore(&pool_lock, flags); + debug_objects_allocated++; + + if (!last) + last = &obj->node; + obj->batch_last = last; + + hlist_add_head(&obj->node, head); } + return true; +} + +static void fill_pool(void) +{ + static atomic_t cpus_allocating; - if (unlikely(!obj_cache)) + /* + * Avoid allocation and lock contention when: + * - One other CPU is already allocating + * - the global pool has not reached the critical level yet + */ + if (!pool_must_refill(&pool_global) && atomic_read(&cpus_allocating)) return; - while (READ_ONCE(obj_pool_free) < debug_objects_pool_min_level) { - struct debug_obj *new[ODEBUG_BATCH_SIZE]; - int cnt; + atomic_inc(&cpus_allocating); + while (pool_should_refill(&pool_global)) { + HLIST_HEAD(head); - for (cnt = 0; cnt < ODEBUG_BATCH_SIZE; cnt++) { - new[cnt] = kmem_cache_zalloc(obj_cache, gfp); - if (!new[cnt]) - break; - } - if (!cnt) - return; + if (!kmem_alloc_batch(&head, obj_cache, __GFP_HIGH | __GFP_NOWARN)) + break; - raw_spin_lock_irqsave(&pool_lock, flags); - while (cnt) { - hlist_add_head(&new[--cnt]->node, &obj_pool); - debug_objects_allocated++; - WRITE_ONCE(obj_pool_free, obj_pool_free + 1); - } - raw_spin_unlock_irqrestore(&pool_lock, flags); + guard(raw_spinlock_irqsave)(&pool_lock); + if (!pool_push_batch(&pool_global, &head)) + pool_push_batch(&pool_to_free, &head); } + atomic_dec(&cpus_allocating); } /* @@ -201,72 +429,37 @@ static struct debug_obj *lookup_object(void *addr, struct debug_bucket *b) return NULL; } -/* - * Allocate a new object from the hlist - */ -static struct debug_obj *__alloc_object(struct hlist_head *list) +static void calc_usage(void) { - struct debug_obj *obj = NULL; + static DEFINE_RAW_SPINLOCK(avg_lock); + static unsigned long avg_period; + unsigned long cur, now = jiffies; - if (list->first) { - obj = hlist_entry(list->first, typeof(*obj), node); - hlist_del(&obj->node); - } + if (!time_after_eq(now, READ_ONCE(avg_period))) + return; - return obj; + if (!raw_spin_trylock(&avg_lock)) + return; + + WRITE_ONCE(avg_period, now + msecs_to_jiffies(10)); + cur = READ_ONCE(pool_global.stats.cur_used) * ODEBUG_FREE_WORK_MAX; + WRITE_ONCE(avg_usage, calc_load(avg_usage, EXP_5, cur)); + raw_spin_unlock(&avg_lock); } -static struct debug_obj * -alloc_object(void *addr, struct debug_bucket *b, const struct debug_obj_descr *descr) +static struct debug_obj *alloc_object(void *addr, struct debug_bucket *b, + const struct debug_obj_descr *descr) { - struct debug_percpu_free *percpu_pool = this_cpu_ptr(&percpu_obj_pool); struct debug_obj *obj; - if (likely(obj_cache)) { - obj = __alloc_object(&percpu_pool->free_objs); - if (obj) { - percpu_pool->obj_free--; - goto init_obj; - } - } - - raw_spin_lock(&pool_lock); - obj = __alloc_object(&obj_pool); - if (obj) { - obj_pool_used++; - WRITE_ONCE(obj_pool_free, obj_pool_free - 1); - - /* - * 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++; - WRITE_ONCE(obj_pool_free, obj_pool_free - 1); - } - } - - if (obj_pool_used > obj_pool_max_used) - obj_pool_max_used = obj_pool_used; + calc_usage(); - if (obj_pool_free < obj_pool_min_free) - obj_pool_min_free = obj_pool_free; - } - raw_spin_unlock(&pool_lock); + if (static_branch_likely(&obj_cache_enabled)) + obj = pcpu_alloc(); + else + obj = __alloc_object(&pool_boot); -init_obj: - if (obj) { + if (likely(obj)) { obj->object = addr; obj->descr = descr; obj->state = ODEBUG_STATE_NONE; @@ -276,142 +469,58 @@ init_obj: return obj; } -/* - * workqueue function to free objects. - * - * To reduce contention on the global pool_lock, the actual freeing of - * debug objects will be delayed if the pool_lock is busy. - */ +/* workqueue function to free objects. */ static void free_obj_work(struct work_struct *work) { - struct hlist_node *tmp; - struct debug_obj *obj; - unsigned long flags; - HLIST_HEAD(tofree); + static unsigned long last_use_avg; + unsigned long cur_used, last_used, delta; + unsigned int max_free = 0; 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; + /* Rate limit freeing based on current use average */ + cur_used = READ_ONCE(avg_usage); + last_used = last_use_avg; + last_use_avg = cur_used; - /* - * 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. 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); - hlist_del(&obj->node); - hlist_add_head(&obj->node, &obj_pool); - WRITE_ONCE(obj_pool_free, obj_pool_free + 1); - WRITE_ONCE(obj_nr_tofree, obj_nr_tofree - 1); - } - raw_spin_unlock_irqrestore(&pool_lock, flags); - return; + if (!pool_count(&pool_to_free)) + 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 - * memory outside the pool_lock held region. - */ - if (obj_nr_tofree) { - hlist_move_list(&obj_to_free, &tofree); - debug_objects_freed += obj_nr_tofree; - WRITE_ONCE(obj_nr_tofree, 0); + if (cur_used <= last_used) { + delta = (last_used - cur_used) / ODEBUG_FREE_WORK_MAX; + max_free = min(delta, ODEBUG_FREE_WORK_MAX); } - raw_spin_unlock_irqrestore(&pool_lock, flags); - hlist_for_each_entry_safe(obj, tmp, &tofree, node) { - hlist_del(&obj->node); - kmem_cache_free(obj_cache, obj); + for (int cnt = 0; cnt < ODEBUG_FREE_WORK_MAX; cnt++) { + HLIST_HEAD(tofree); + + /* Acquire and drop the lock for each batch */ + scoped_guard(raw_spinlock_irqsave, &pool_lock) { + if (!pool_to_free.cnt) + return; + + /* Refill the global pool if possible */ + if (pool_move_batch(&pool_global, &pool_to_free)) { + /* Don't free as there seems to be demand */ + max_free = 0; + } else if (max_free) { + pool_pop_batch(&tofree, &pool_to_free); + max_free--; + } else { + return; + } + } + free_object_list(&tofree); } } 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; - - 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) { - WRITE_ONCE(obj_nr_tofree, obj_nr_tofree + 1); - hlist_add_head(&obj->node, &obj_to_free); - if (lookahead_count) { - WRITE_ONCE(obj_nr_tofree, 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); - WRITE_ONCE(obj_pool_free, obj_pool_free - 1); - WRITE_ONCE(obj_nr_tofree, obj_nr_tofree + 1); - } - } - } else { - WRITE_ONCE(obj_pool_free, obj_pool_free + 1); - hlist_add_head(&obj->node, &obj_pool); - if (lookahead_count) { - WRITE_ONCE(obj_pool_free, 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(&pool_lock); - local_irq_restore(flags); + guard(irqsave)(); + if (static_branch_likely(&obj_cache_enabled)) + pcpu_free(obj); + else + hlist_add_head(&obj->node, &pool_boot); } /* @@ -421,63 +530,52 @@ free_to_obj_pool: static void free_object(struct debug_obj *obj) { __free_object(obj); - if (!READ_ONCE(obj_freeing) && READ_ONCE(obj_nr_tofree)) { + if (!READ_ONCE(obj_freeing) && pool_count(&pool_to_free)) { WRITE_ONCE(obj_freeing, true); schedule_delayed_work(&debug_obj_work, ODEBUG_FREE_WORK_DELAY); } } -#ifdef CONFIG_HOTPLUG_CPU -static int object_cpu_offline(unsigned int cpu) +static void put_objects(struct hlist_head *list) { - struct debug_percpu_free *percpu_pool; struct hlist_node *tmp; struct debug_obj *obj; - unsigned long flags; - /* Remote access is safe as the CPU is dead already */ - percpu_pool = per_cpu_ptr(&percpu_obj_pool, cpu); - hlist_for_each_entry_safe(obj, tmp, &percpu_pool->free_objs, node) { + /* + * Using free_object() puts the objects into reuse or schedules + * them for freeing and it get's all the accounting correct. + */ + hlist_for_each_entry_safe(obj, tmp, list, node) { hlist_del(&obj->node); - kmem_cache_free(obj_cache, obj); + free_object(obj); } +} - raw_spin_lock_irqsave(&pool_lock, flags); - obj_pool_used -= percpu_pool->obj_free; - debug_objects_freed += percpu_pool->obj_free; - raw_spin_unlock_irqrestore(&pool_lock, flags); - - percpu_pool->obj_free = 0; +#ifdef CONFIG_HOTPLUG_CPU +static int object_cpu_offline(unsigned int cpu) +{ + /* Remote access is safe as the CPU is dead already */ + struct obj_pool *pcp = per_cpu_ptr(&pool_pcpu, cpu); + put_objects(&pcp->objects); + pcp->cnt = 0; return 0; } #endif -/* - * We run out of memory. That means we probably have tons of objects - * allocated. - */ +/* Out of memory. Free all objects from hash */ static void debug_objects_oom(void) { struct debug_bucket *db = obj_hash; - struct hlist_node *tmp; HLIST_HEAD(freelist); - struct debug_obj *obj; - unsigned long flags; - int i; pr_warn("Out of memory. ODEBUG disabled\n"); - for (i = 0; i < ODEBUG_HASH_SIZE; i++, db++) { - raw_spin_lock_irqsave(&db->lock, flags); - hlist_move_list(&db->list, &freelist); - raw_spin_unlock_irqrestore(&db->lock, flags); + for (int i = 0; i < ODEBUG_HASH_SIZE; i++, db++) { + scoped_guard(raw_spinlock_irqsave, &db->lock) + hlist_move_list(&db->list, &freelist); - /* Now free them */ - hlist_for_each_entry_safe(obj, tmp, &freelist, node) { - hlist_del(&obj->node); - free_object(obj); - } + put_objects(&freelist); } } @@ -592,12 +690,24 @@ static struct debug_obj *lookup_object_or_alloc(void *addr, struct debug_bucket } /* Out of memory. Do the cleanup outside of the locked region */ - debug_objects_enabled = 0; + debug_objects_enabled = false; return NULL; } static void debug_objects_fill_pool(void) { + if (!static_branch_likely(&obj_cache_enabled)) + return; + + if (likely(!pool_should_refill(&pool_global))) + return; + + /* Try reusing objects from obj_to_free_list */ + fill_pool_from_freelist(); + + if (likely(!pool_should_refill(&pool_global))) + return; + /* * On RT enabled kernels the pool refill must happen in preemptible * context -- for !RT kernels we rely on the fact that spinlock_t and @@ -1007,7 +1117,7 @@ repeat: debug_objects_maxchecked = objs_checked; /* Schedule work to actually kmem_cache_free() objects */ - if (!READ_ONCE(obj_freeing) && READ_ONCE(obj_nr_tofree)) { + if (!READ_ONCE(obj_freeing) && pool_count(&pool_to_free)) { WRITE_ONCE(obj_freeing, true); schedule_delayed_work(&debug_obj_work, ODEBUG_FREE_WORK_DELAY); } @@ -1024,23 +1134,33 @@ 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; + unsigned int cpu, pool_used, pcp_free = 0; + /* + * pool_global.stats.cur_used is the number of batches currently + * handed out to per CPU pools. Convert it to number of objects + * and subtract the number of free objects in the per CPU pools. + * As this is lockless the number is an estimate. + */ 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", READ_ONCE(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 - obj_percpu_free); - seq_printf(m, "pool_max_used :%d\n", obj_pool_max_used); - seq_printf(m, "on_free_list :%d\n", READ_ONCE(obj_nr_tofree)); - seq_printf(m, "objs_allocated:%d\n", debug_objects_allocated); - seq_printf(m, "objs_freed :%d\n", debug_objects_freed); + pcp_free += per_cpu(pool_pcpu.cnt, cpu); + + pool_used = READ_ONCE(pool_global.stats.cur_used); + pcp_free = min(pool_used, pcp_free); + pool_used -= pcp_free; + + 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 : %u\n", pool_count(&pool_global) + pcp_free); + seq_printf(m, "pool_pcp_free : %u\n", pcp_free); + seq_printf(m, "pool_min_free : %u\n", data_race(pool_global.stats.min_fill)); + seq_printf(m, "pool_used : %u\n", pool_used); + seq_printf(m, "pool_max_used : %u\n", data_race(pool_global.stats.max_used)); + seq_printf(m, "on_free_list : %u\n", pool_count(&pool_to_free)); + seq_printf(m, "objs_allocated: %d\n", debug_objects_allocated); + seq_printf(m, "objs_freed : %d\n", debug_objects_freed); return 0; } DEFINE_SHOW_ATTRIBUTE(debug_stats); @@ -1194,7 +1314,7 @@ check_results(void *addr, enum debug_obj_state state, int fixups, int warnings) out: raw_spin_unlock_irqrestore(&db->lock, flags); if (res) - debug_objects_enabled = 0; + debug_objects_enabled = false; return res; } @@ -1209,7 +1329,7 @@ static __initconst const struct debug_obj_descr descr_type_test = { static __initdata struct self_test obj = { .static_init = 0 }; -static void __init debug_objects_selftest(void) +static bool __init debug_objects_selftest(void) { int fixups, oldfixups, warnings, oldwarnings; unsigned long flags; @@ -1278,9 +1398,10 @@ out: descr_test = NULL; local_irq_restore(flags); + return debug_objects_enabled; } #else -static inline void debug_objects_selftest(void) { } +static inline bool debug_objects_selftest(void) { return true; } #endif /* @@ -1295,65 +1416,54 @@ void __init debug_objects_early_init(void) for (i = 0; i < ODEBUG_HASH_SIZE; i++) raw_spin_lock_init(&obj_hash[i].lock); + /* Keep early boot simple and add everything to the boot list */ for (i = 0; i < ODEBUG_POOL_SIZE; i++) - hlist_add_head(&obj_static_pool[i].node, &obj_pool); + hlist_add_head(&obj_static_pool[i].node, &pool_boot); } /* - * Convert the statically allocated objects to dynamic ones: + * Convert the statically allocated objects to dynamic ones. + * debug_objects_mem_init() is called early so only one CPU is up and + * interrupts are disabled, which means it is safe to replace the active + * object references. */ -static int __init debug_objects_replace_static_objects(void) +static bool __init debug_objects_replace_static_objects(struct kmem_cache *cache) { struct debug_bucket *db = obj_hash; struct hlist_node *tmp; - struct debug_obj *obj, *new; + struct debug_obj *obj; HLIST_HEAD(objects); - int i, cnt = 0; + int i; - for (i = 0; i < ODEBUG_POOL_SIZE; i++) { - obj = kmem_cache_zalloc(obj_cache, GFP_KERNEL); - if (!obj) + for (i = 0; i < ODEBUG_POOL_SIZE; i += ODEBUG_BATCH_SIZE) { + if (!kmem_alloc_batch(&objects, cache, GFP_KERNEL)) goto free; - hlist_add_head(&obj->node, &objects); + pool_push_batch(&pool_global, &objects); } - debug_objects_allocated += i; - - /* - * debug_objects_mem_init() is now called early that only one CPU is up - * and interrupts have been disabled, so it is safe to replace the - * active object references. - */ - - /* Remove the statically allocated objects from the pool */ - hlist_for_each_entry_safe(obj, tmp, &obj_pool, node) - hlist_del(&obj->node); - /* Move the allocated objects to the pool */ - hlist_move_list(&objects, &obj_pool); + /* Disconnect the boot pool. */ + pool_boot.first = NULL; /* Replace the active object references */ for (i = 0; i < ODEBUG_HASH_SIZE; i++, db++) { hlist_move_list(&db->list, &objects); hlist_for_each_entry(obj, &objects, node) { - new = hlist_entry(obj_pool.first, typeof(*obj), node); - hlist_del(&new->node); + struct debug_obj *new = pcpu_alloc(); + /* copy object data */ *new = *obj; hlist_add_head(&new->node, &db->list); - cnt++; } } - - pr_debug("%d of %d active objects replaced\n", - cnt, obj_pool_used); - return 0; + return true; free: - hlist_for_each_entry_safe(obj, tmp, &objects, node) { + /* Can't use free_object_list() as the cache is not populated yet */ + hlist_for_each_entry_safe(obj, tmp, &pool_global.objects, node) { hlist_del(&obj->node); - kmem_cache_free(obj_cache, obj); + kmem_cache_free(cache, obj); } - return -ENOMEM; + return false; } /* @@ -1364,43 +1474,40 @@ free: */ void __init debug_objects_mem_init(void) { - int cpu, extras; + struct kmem_cache *cache; + int 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)); + if (!debug_objects_selftest()) + return; - obj_cache = kmem_cache_create("debug_objects_cache", - sizeof (struct debug_obj), 0, - SLAB_DEBUG_OBJECTS | SLAB_NOLEAKTRACE, - NULL); + cache = kmem_cache_create("debug_objects_cache", sizeof (struct debug_obj), 0, + SLAB_DEBUG_OBJECTS | SLAB_NOLEAKTRACE, NULL); - if (!obj_cache || debug_objects_replace_static_objects()) { - debug_objects_enabled = 0; - kmem_cache_destroy(obj_cache); - pr_warn("out of memory.\n"); + if (!cache || !debug_objects_replace_static_objects(cache)) { + debug_objects_enabled = false; + pr_warn("Out of memory.\n"); return; - } else - debug_objects_selftest(); - -#ifdef CONFIG_HOTPLUG_CPU - cpuhp_setup_state_nocalls(CPUHP_DEBUG_OBJ_DEAD, "object:offline", NULL, - object_cpu_offline); -#endif + } /* - * Increase the thresholds for allocating and freeing objects - * according to the number of possible CPUs available in the system. + * Adjust the thresholds for allocating and freeing objects + * according to the number of possible CPUs available in the + * system. */ extras = num_possible_cpus() * ODEBUG_BATCH_SIZE; - debug_objects_pool_size += extras; - debug_objects_pool_min_level += extras; + pool_global.max_cnt += extras; + pool_global.min_cnt += extras; + + /* Everything worked. Expose the cache */ + obj_cache = cache; + static_branch_enable(&obj_cache_enabled); + +#ifdef CONFIG_HOTPLUG_CPU + cpuhp_setup_state_nocalls(CPUHP_DEBUG_OBJ_DEAD, "object:offline", NULL, + object_cpu_offline); +#endif + return; } diff --git a/lib/dim/dim.c b/lib/dim/dim.c index 83b65ac74d73..97c3d084ebf0 100644 --- a/lib/dim/dim.c +++ b/lib/dim/dim.c @@ -54,7 +54,8 @@ void dim_park_tired(struct dim *dim) } EXPORT_SYMBOL(dim_park_tired); -bool dim_calc_stats(struct dim_sample *start, struct dim_sample *end, +bool dim_calc_stats(const struct dim_sample *start, + const struct dim_sample *end, struct dim_stats *curr_stats) { /* u32 holds up to 71 minutes, should be enough */ diff --git a/lib/dim/net_dim.c b/lib/dim/net_dim.c index d7e7028e9b19..d6aa09a979b3 100644 --- a/lib/dim/net_dim.c +++ b/lib/dim/net_dim.c @@ -347,7 +347,7 @@ static bool net_dim_decision(struct dim_stats *curr_stats, struct dim *dim) return dim->profile_ix != prev_ix; } -void net_dim(struct dim *dim, struct dim_sample end_sample) +void net_dim(struct dim *dim, const struct dim_sample *end_sample) { struct dim_stats curr_stats; u16 nevents; @@ -355,11 +355,11 @@ void net_dim(struct dim *dim, struct dim_sample end_sample) switch (dim->state) { case DIM_MEASURE_IN_PROGRESS: nevents = BIT_GAP(BITS_PER_TYPE(u16), - end_sample.event_ctr, + end_sample->event_ctr, dim->start_sample.event_ctr); if (nevents < DIM_NEVENTS) break; - if (!dim_calc_stats(&dim->start_sample, &end_sample, &curr_stats)) + if (!dim_calc_stats(&dim->start_sample, end_sample, &curr_stats)) break; if (net_dim_decision(&curr_stats, dim)) { dim->state = DIM_APPLY_NEW_PROFILE; @@ -368,8 +368,8 @@ void net_dim(struct dim *dim, struct dim_sample end_sample) } fallthrough; case DIM_START_MEASURE: - dim_update_sample(end_sample.event_ctr, end_sample.pkt_ctr, - end_sample.byte_ctr, &dim->start_sample); + dim_update_sample(end_sample->event_ctr, end_sample->pkt_ctr, + end_sample->byte_ctr, &dim->start_sample); dim->state = DIM_MEASURE_IN_PROGRESS; break; case DIM_APPLY_NEW_PROFILE: diff --git a/lib/dynamic_queue_limits.c b/lib/dynamic_queue_limits.c index e49deddd3de9..c1b7638a594a 100644 --- a/lib/dynamic_queue_limits.c +++ b/lib/dynamic_queue_limits.c @@ -179,7 +179,7 @@ void dql_completed(struct dql *dql, unsigned int count) dql->adj_limit = limit + completed; dql->prev_ovlimit = ovlimit; - dql->prev_last_obj_cnt = dql->last_obj_cnt; + dql->prev_last_obj_cnt = READ_ONCE(dql->last_obj_cnt); dql->num_completed = completed; dql->prev_num_queued = num_queued; diff --git a/lib/interval_tree_test.c b/lib/interval_tree_test.c index f37f4d44faa9..837064b83a6c 100644 --- a/lib/interval_tree_test.c +++ b/lib/interval_tree_test.c @@ -2,7 +2,7 @@ #include <linux/module.h> #include <linux/moduleparam.h> #include <linux/interval_tree.h> -#include <linux/random.h> +#include <linux/prandom.h> #include <linux/slab.h> #include <asm/timex.h> diff --git a/lib/iomem_copy.c b/lib/iomem_copy.c new file mode 100644 index 000000000000..dec7eaea60e0 --- /dev/null +++ b/lib/iomem_copy.c @@ -0,0 +1,136 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright 2024 Kalray, Inc. All Rights Reserved. + */ + +#include <linux/align.h> +#include <linux/export.h> +#include <linux/io.h> +#include <linux/types.h> +#include <linux/unaligned.h> + +#ifndef memset_io +/** + * memset_io() - Set a range of I/O memory to a constant value + * @addr: The beginning of the I/O-memory range to set + * @val: The value to set the memory to + * @count: The number of bytes to set + * + * Set a range of I/O memory to a given value. + */ +void memset_io(volatile void __iomem *addr, int val, size_t count) +{ + long qc = (u8)val; + + qc *= ~0UL / 0xff; + + while (count && !IS_ALIGNED((long)addr, sizeof(long))) { + __raw_writeb(val, addr); + addr++; + count--; + } + + while (count >= sizeof(long)) { +#ifdef CONFIG_64BIT + __raw_writeq(qc, addr); +#else + __raw_writel(qc, addr); +#endif + + addr += sizeof(long); + count -= sizeof(long); + } + + while (count) { + __raw_writeb(val, addr); + addr++; + count--; + } +} +EXPORT_SYMBOL(memset_io); +#endif + +#ifndef memcpy_fromio +/** + * memcpy_fromio() - Copy a block of data from I/O memory + * @dst: The (RAM) destination for the copy + * @src: The (I/O memory) source for the data + * @count: The number of bytes to copy + * + * Copy a block of data from I/O memory. + */ +void memcpy_fromio(void *dst, const volatile void __iomem *src, size_t count) +{ + while (count && !IS_ALIGNED((long)src, sizeof(long))) { + *(u8 *)dst = __raw_readb(src); + src++; + dst++; + count--; + } + + while (count >= sizeof(long)) { +#ifdef CONFIG_64BIT + long val = __raw_readq(src); +#else + long val = __raw_readl(src); +#endif + put_unaligned(val, (long *)dst); + + + src += sizeof(long); + dst += sizeof(long); + count -= sizeof(long); + } + + while (count) { + *(u8 *)dst = __raw_readb(src); + src++; + dst++; + count--; + } +} +EXPORT_SYMBOL(memcpy_fromio); +#endif + +#ifndef memcpy_toio +/** + * memcpy_toio() -Copy a block of data into I/O memory + * @dst: The (I/O memory) destination for the copy + * @src: The (RAM) source for the data + * @count: The number of bytes to copy + * + * Copy a block of data to I/O memory. + */ +void memcpy_toio(volatile void __iomem *dst, const void *src, size_t count) +{ + while (count && !IS_ALIGNED((long)dst, sizeof(long))) { + __raw_writeb(*(u8 *)src, dst); + src++; + dst++; + count--; + } + + while (count >= sizeof(long)) { + long val = get_unaligned((long *)src); +#ifdef CONFIG_64BIT + __raw_writeq(val, dst); +#else + __raw_writel(val, dst); +#endif + + src += sizeof(long); + dst += sizeof(long); + count -= sizeof(long); + } + + while (count) { + __raw_writeb(*(u8 *)src, dst); + src++; + dst++; + count--; + } +} +EXPORT_SYMBOL(memcpy_toio); +#endif + + diff --git a/lib/iov_iter.c b/lib/iov_iter.c index 908e75a28d90..9ec806f989f2 100644 --- a/lib/iov_iter.c +++ b/lib/iov_iter.c @@ -1682,8 +1682,8 @@ static ssize_t iov_iter_extract_xarray_pages(struct iov_iter *i, } /* - * Extract a list of contiguous pages from an ITER_BVEC iterator. This does - * not get references on the pages, nor does it get a pin on them. + * Extract a list of virtually contiguous pages from an ITER_BVEC iterator. + * This does not get references on the pages, nor does it get a pin on them. */ static ssize_t iov_iter_extract_bvec_pages(struct iov_iter *i, struct page ***pages, size_t maxsize, @@ -1691,35 +1691,59 @@ static ssize_t iov_iter_extract_bvec_pages(struct iov_iter *i, iov_iter_extraction_t extraction_flags, size_t *offset0) { - struct page **p, *page; - size_t skip = i->iov_offset, offset, size; - int k; + size_t skip = i->iov_offset, size = 0; + struct bvec_iter bi; + int k = 0; - for (;;) { - if (i->nr_segs == 0) - return 0; - size = min(maxsize, i->bvec->bv_len - skip); - if (size) - break; + if (i->nr_segs == 0) + return 0; + + if (i->iov_offset == i->bvec->bv_len) { i->iov_offset = 0; i->nr_segs--; i->bvec++; skip = 0; } + bi.bi_idx = 0; + bi.bi_size = maxsize; + bi.bi_bvec_done = skip; + + maxpages = want_pages_array(pages, maxsize, skip, maxpages); + + while (bi.bi_size && bi.bi_idx < i->nr_segs) { + struct bio_vec bv = bvec_iter_bvec(i->bvec, bi); + + /* + * The iov_iter_extract_pages interface only allows an offset + * into the first page. Break out of the loop if we see an + * offset into subsequent pages, the caller will have to call + * iov_iter_extract_pages again for the reminder. + */ + if (k) { + if (bv.bv_offset) + break; + } else { + *offset0 = bv.bv_offset; + } - skip += i->bvec->bv_offset; - page = i->bvec->bv_page + skip / PAGE_SIZE; - offset = skip % PAGE_SIZE; - *offset0 = offset; + (*pages)[k++] = bv.bv_page; + size += bv.bv_len; - maxpages = want_pages_array(pages, size, offset, maxpages); - if (!maxpages) - return -ENOMEM; - p = *pages; - for (k = 0; k < maxpages; k++) - p[k] = page + k; + if (k >= maxpages) + break; + + /* + * We are done when the end of the bvec doesn't align to a page + * boundary as that would create a hole in the returned space. + * The caller will handle this with another call to + * iov_iter_extract_pages. + */ + if (bv.bv_offset + bv.bv_len != PAGE_SIZE) + break; + + bvec_iter_advance_single(i->bvec, &bi, bv.bv_len); + } - size = min_t(size_t, size, maxpages * PAGE_SIZE - offset); iov_iter_advance(i, size); return size; } diff --git a/lib/kunit/debugfs.c b/lib/kunit/debugfs.c index d548750a325a..af71911f4a07 100644 --- a/lib/kunit/debugfs.c +++ b/lib/kunit/debugfs.c @@ -181,7 +181,7 @@ void kunit_debugfs_create_suite(struct kunit_suite *suite) * successfully. */ stream = alloc_string_stream(GFP_KERNEL); - if (IS_ERR_OR_NULL(stream)) + if (IS_ERR(stream)) return; string_stream_set_append_newlines(stream, true); @@ -189,7 +189,7 @@ void kunit_debugfs_create_suite(struct kunit_suite *suite) kunit_suite_for_each_test_case(suite, test_case) { stream = alloc_string_stream(GFP_KERNEL); - if (IS_ERR_OR_NULL(stream)) + if (IS_ERR(stream)) goto err; string_stream_set_append_newlines(stream, true); @@ -212,8 +212,11 @@ void kunit_debugfs_create_suite(struct kunit_suite *suite) err: string_stream_destroy(suite->log); - kunit_suite_for_each_test_case(suite, test_case) + suite->log = NULL; + kunit_suite_for_each_test_case(suite, test_case) { string_stream_destroy(test_case->log); + test_case->log = NULL; + } } void kunit_debugfs_destroy_suite(struct kunit_suite *suite) diff --git a/lib/kunit/kunit-test.c b/lib/kunit/kunit-test.c index 37e02be1e710..d9c781c859fd 100644 --- a/lib/kunit/kunit-test.c +++ b/lib/kunit/kunit-test.c @@ -805,6 +805,8 @@ static void kunit_device_driver_test(struct kunit *test) struct device *test_device; struct driver_test_state *test_state = kunit_kzalloc(test, sizeof(*test_state), GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, test_state); + test->priv = test_state; test_driver = kunit_driver_create(test, "my_driver"); diff --git a/lib/kunit/string-stream-test.c b/lib/kunit/string-stream-test.c index 7511442ea98f..7734e33156f9 100644 --- a/lib/kunit/string-stream-test.c +++ b/lib/kunit/string-stream-test.c @@ -9,6 +9,7 @@ #include <kunit/static_stub.h> #include <kunit/test.h> #include <linux/ktime.h> +#include <linux/prandom.h> #include <linux/slab.h> #include <linux/timekeeping.h> diff --git a/lib/locking-selftest.c b/lib/locking-selftest.c index 6f6a5fc85b42..6e0c019f71b6 100644 --- a/lib/locking-selftest.c +++ b/lib/locking-selftest.c @@ -2710,6 +2710,43 @@ static void local_lock_3B(void) } +#ifdef CONFIG_DEBUG_LOCK_ALLOC +static inline const char *rw_semaphore_lockdep_name(struct rw_semaphore *rwsem) +{ + return rwsem->dep_map.name; +} +#else +static inline const char *rw_semaphore_lockdep_name(struct rw_semaphore *rwsem) +{ + return NULL; +} +#endif + +static void test_lockdep_set_subclass_name(void) +{ + const char *name_before = rw_semaphore_lockdep_name(&rwsem_X1); + const char *name_after; + + lockdep_set_subclass(&rwsem_X1, 1); + name_after = rw_semaphore_lockdep_name(&rwsem_X1); + DEBUG_LOCKS_WARN_ON(name_before != name_after); +} + +/* + * lockdep_set_subclass() should reuse the existing lock class name instead + * of creating a new one. + */ +static void lockdep_set_subclass_name_test(void) +{ + printk(" --------------------------------------------------------------------------\n"); + printk(" | lockdep_set_subclass() name test|\n"); + printk(" -----------------------------------\n"); + + print_testname("compare name before and after"); + dotest(test_lockdep_set_subclass_name, SUCCESS, LOCKTYPE_RWSEM); + pr_cont("\n"); +} + static void local_lock_tests(void) { printk(" --------------------------------------------------------------------------\n"); @@ -2920,6 +2957,8 @@ void locking_selftest(void) dotest(hardirq_deadlock_softirq_not_deadlock, FAILURE, LOCKTYPE_SPECIAL); pr_cont("\n"); + lockdep_set_subclass_name_test(); + if (unexpected_testcase_failures) { printk("-----------------------------------------------------------------\n"); debug_locks = 0; diff --git a/lib/logic_pio.c b/lib/logic_pio.c index 2ea564a40064..e29496a38d06 100644 --- a/lib/logic_pio.c +++ b/lib/logic_pio.c @@ -122,7 +122,7 @@ void logic_pio_unregister_range(struct logic_pio_hwaddr *range) * * Traverse the io_range_list to find the registered node for @fwnode. */ -struct logic_pio_hwaddr *find_io_range_by_fwnode(struct fwnode_handle *fwnode) +struct logic_pio_hwaddr *find_io_range_by_fwnode(const struct fwnode_handle *fwnode) { struct logic_pio_hwaddr *range, *found_range = NULL; @@ -186,7 +186,7 @@ resource_size_t logic_pio_to_hwaddr(unsigned long pio) * * Returns Logical PIO value if successful, ~0UL otherwise */ -unsigned long logic_pio_trans_hwaddr(struct fwnode_handle *fwnode, +unsigned long logic_pio_trans_hwaddr(const struct fwnode_handle *fwnode, resource_size_t addr, resource_size_t size) { struct logic_pio_hwaddr *range; diff --git a/lib/math/test_div64.c b/lib/math/test_div64.c index c15edd688dd2..3cd699b654d9 100644 --- a/lib/math/test_div64.c +++ b/lib/math/test_div64.c @@ -26,6 +26,9 @@ static const u64 test_div64_dividends[] = { 0x0072db27380dd689, 0x0842f488162e2284, 0xf66745411d8ab063, + 0xfffffffffffffffb, + 0xfffffffffffffffc, + 0xffffffffffffffff, }; #define SIZE_DIV64_DIVIDENDS ARRAY_SIZE(test_div64_dividends) @@ -37,7 +40,10 @@ static const u64 test_div64_dividends[] = { #define TEST_DIV64_DIVISOR_5 0x0008a880 #define TEST_DIV64_DIVISOR_6 0x003fd3ae #define TEST_DIV64_DIVISOR_7 0x0b658fac -#define TEST_DIV64_DIVISOR_8 0xdc08b349 +#define TEST_DIV64_DIVISOR_8 0x80000001 +#define TEST_DIV64_DIVISOR_9 0xdc08b349 +#define TEST_DIV64_DIVISOR_A 0xfffffffe +#define TEST_DIV64_DIVISOR_B 0xffffffff static const u32 test_div64_divisors[] = { TEST_DIV64_DIVISOR_0, @@ -49,13 +55,16 @@ static const u32 test_div64_divisors[] = { TEST_DIV64_DIVISOR_6, TEST_DIV64_DIVISOR_7, TEST_DIV64_DIVISOR_8, + TEST_DIV64_DIVISOR_9, + TEST_DIV64_DIVISOR_A, + TEST_DIV64_DIVISOR_B, }; #define SIZE_DIV64_DIVISORS ARRAY_SIZE(test_div64_divisors) static const struct { u64 quotient; u32 remainder; -} test_div64_results[SIZE_DIV64_DIVISORS][SIZE_DIV64_DIVIDENDS] = { +} test_div64_results[SIZE_DIV64_DIVIDENDS][SIZE_DIV64_DIVISORS] = { { { 0x0000000013045e47, 0x00000001 }, { 0x000000000161596c, 0x00000030 }, @@ -65,6 +74,9 @@ static const struct { { 0x00000000000013c4, 0x0004ce80 }, { 0x00000000000002ae, 0x001e143c }, { 0x000000000000000f, 0x0033e56c }, + { 0x0000000000000001, 0x2b27507f }, + { 0x0000000000000000, 0xab275080 }, + { 0x0000000000000000, 0xab275080 }, { 0x0000000000000000, 0xab275080 }, }, { { 0x00000001c45c02d1, 0x00000000 }, @@ -75,7 +87,10 @@ static const struct { { 0x000000000001d637, 0x0004e5d9 }, { 0x0000000000003fc9, 0x000713bb }, { 0x0000000000000165, 0x029abe7d }, + { 0x000000000000001f, 0x673c193a }, { 0x0000000000000012, 0x6e9f7e37 }, + { 0x000000000000000f, 0xe73c1977 }, + { 0x000000000000000f, 0xe73c1968 }, }, { { 0x000000197a3a0cf7, 0x00000002 }, { 0x00000001d9632e5c, 0x00000021 }, @@ -85,7 +100,10 @@ static const struct { { 0x00000000001a7bb3, 0x00072331 }, { 0x00000000000397ad, 0x0002c61b }, { 0x000000000000141e, 0x06ea2e89 }, + { 0x00000000000001ca, 0x4c0a72e7 }, { 0x000000000000010a, 0xab002ad7 }, + { 0x00000000000000e5, 0x4c0a767b }, + { 0x00000000000000e5, 0x4c0a7596 }, }, { { 0x0000017949e37538, 0x00000001 }, { 0x0000001b62441f37, 0x00000055 }, @@ -95,7 +113,10 @@ static const struct { { 0x0000000001882ec6, 0x0005cbf9 }, { 0x000000000035333b, 0x0017abdf }, { 0x00000000000129f1, 0x0ab4520d }, + { 0x0000000000001a87, 0x18ff0472 }, { 0x0000000000000f6e, 0x8ac0ce9b }, + { 0x0000000000000d43, 0x98ff397f }, + { 0x0000000000000d43, 0x98ff2c3c }, }, { { 0x000011f321a74e49, 0x00000006 }, { 0x0000014d8481d211, 0x0000005b }, @@ -105,7 +126,10 @@ static const struct { { 0x0000000012a88828, 0x00036c97 }, { 0x000000000287f16f, 0x002c2a25 }, { 0x00000000000e2cc7, 0x02d581e3 }, + { 0x0000000000014318, 0x2ee07d7f }, { 0x000000000000bbf4, 0x1ba08c03 }, + { 0x000000000000a18c, 0x2ee303af }, + { 0x000000000000a18c, 0x2ee26223 }, }, { { 0x0000d8db8f72935d, 0x00000005 }, { 0x00000fbd5aed7a2e, 0x00000002 }, @@ -115,7 +139,10 @@ static const struct { { 0x00000000e16b20fa, 0x0002a14a }, { 0x000000001e940d22, 0x00353b2e }, { 0x0000000000ab40ac, 0x06fba6ba }, + { 0x00000000000f3f70, 0x0af7eeda }, { 0x000000000008debd, 0x72d98365 }, + { 0x0000000000079fb8, 0x0b166dba }, + { 0x0000000000079fb8, 0x0b0ece02 }, }, { { 0x000cc3045b8fc281, 0x00000000 }, { 0x0000ed1f48b5c9fc, 0x00000079 }, @@ -125,7 +152,10 @@ static const struct { { 0x0000000d43fce827, 0x00082b09 }, { 0x00000001ccaba11a, 0x0037e8dd }, { 0x000000000a13f729, 0x0566dffd }, + { 0x0000000000e5b64e, 0x3728203b }, { 0x000000000085a14b, 0x23d36726 }, + { 0x000000000072db27, 0x38f38cd7 }, + { 0x000000000072db27, 0x3880b1b0 }, }, { { 0x00eafeb9c993592b, 0x00000001 }, { 0x00110e5befa9a991, 0x00000048 }, @@ -135,7 +165,10 @@ static const struct { { 0x000000f4459740fc, 0x00084484 }, { 0x0000002122c47bf9, 0x002ca446 }, { 0x00000000b9936290, 0x004979c4 }, + { 0x000000001085e910, 0x05a83974 }, { 0x00000000099ca89d, 0x9db446bf }, + { 0x000000000842f488, 0x26b40b94 }, + { 0x000000000842f488, 0x1e71170c }, }, { { 0x1b60cece589da1d2, 0x00000001 }, { 0x01fcb42be1453f5b, 0x0000004f }, @@ -145,7 +178,49 @@ static const struct { { 0x00001c757dfab350, 0x00048863 }, { 0x000003dc4979c652, 0x00224ea7 }, { 0x000000159edc3144, 0x06409ab3 }, + { 0x00000001ecce8a7e, 0x30bc25e5 }, { 0x000000011eadfee3, 0xa99c48a8 }, + { 0x00000000f6674543, 0x0a593ae9 }, + { 0x00000000f6674542, 0x13f1f5a5 }, + }, { + { 0x1c71c71c71c71c71, 0x00000002 }, + { 0x0210842108421084, 0x0000000b }, + { 0x007f01fc07f01fc0, 0x000000fb }, + { 0x00014245eabf1f9a, 0x0000a63d }, + { 0x0000ffffffffffff, 0x0000fffb }, + { 0x00001d913cecc509, 0x0007937b }, + { 0x00000402c70c678f, 0x0005bfc9 }, + { 0x00000016766cb70b, 0x045edf97 }, + { 0x00000001fffffffb, 0x80000000 }, + { 0x0000000129d84b3a, 0xa2e8fe71 }, + { 0x0000000100000001, 0xfffffffd }, + { 0x0000000100000000, 0xfffffffb }, + }, { + { 0x1c71c71c71c71c71, 0x00000003 }, + { 0x0210842108421084, 0x0000000c }, + { 0x007f01fc07f01fc0, 0x000000fc }, + { 0x00014245eabf1f9a, 0x0000a63e }, + { 0x0000ffffffffffff, 0x0000fffc }, + { 0x00001d913cecc509, 0x0007937c }, + { 0x00000402c70c678f, 0x0005bfca }, + { 0x00000016766cb70b, 0x045edf98 }, + { 0x00000001fffffffc, 0x00000000 }, + { 0x0000000129d84b3a, 0xa2e8fe72 }, + { 0x0000000100000002, 0x00000000 }, + { 0x0000000100000000, 0xfffffffc }, + }, { + { 0x1c71c71c71c71c71, 0x00000006 }, + { 0x0210842108421084, 0x0000000f }, + { 0x007f01fc07f01fc0, 0x000000ff }, + { 0x00014245eabf1f9a, 0x0000a641 }, + { 0x0000ffffffffffff, 0x0000ffff }, + { 0x00001d913cecc509, 0x0007937f }, + { 0x00000402c70c678f, 0x0005bfcd }, + { 0x00000016766cb70b, 0x045edf9b }, + { 0x00000001fffffffc, 0x00000003 }, + { 0x0000000129d84b3a, 0xa2e8fe75 }, + { 0x0000000100000002, 0x00000003 }, + { 0x0000000100000001, 0x00000000 }, }, }; @@ -208,6 +283,12 @@ static bool __init test_div64(void) return false; if (!test_div64_one(dividend, TEST_DIV64_DIVISOR_8, i, 8)) return false; + if (!test_div64_one(dividend, TEST_DIV64_DIVISOR_9, i, 9)) + return false; + if (!test_div64_one(dividend, TEST_DIV64_DIVISOR_A, i, 10)) + return false; + if (!test_div64_one(dividend, TEST_DIV64_DIVISOR_B, i, 11)) + return false; for (j = 0; j < SIZE_DIV64_DIVISORS; j++) { if (!test_div64_one(dividend, test_div64_divisors[j], i, j)) diff --git a/lib/packing.c b/lib/packing.c index 3f656167c17e..793942745e34 100644 --- a/lib/packing.c +++ b/lib/packing.c @@ -9,52 +9,53 @@ #include <linux/types.h> #include <linux/bitrev.h> -static int get_le_offset(int offset) +/** + * calculate_box_addr - Determine physical location of byte in buffer + * @box: Index of byte within buffer seen as a logical big-endian big number + * @len: Size of buffer in bytes + * @quirks: mask of QUIRK_LSW32_IS_FIRST and QUIRK_LITTLE_ENDIAN + * + * Function interprets the buffer as a @len byte sized big number, and returns + * the physical offset of the @box logical octet within it. Internally, it + * treats the big number as groups of 4 bytes. If @len is not a multiple of 4, + * the last group may be shorter. + * + * @QUIRK_LSW32_IS_FIRST gives the ordering of groups of 4 octets relative to + * each other. If set, the most significant group of 4 octets is last in the + * buffer (and may be truncated if @len is not a multiple of 4). + * + * @QUIRK_LITTLE_ENDIAN gives the ordering of bytes within each group of 4. + * If set, the most significant byte is last in the group. If @len takes the + * form of 4k+3, the last group will only be able to represent 24 bits, and its + * most significant octet is byte 2. + * + * Return: the physical offset into the buffer corresponding to the logical box. + */ +static size_t calculate_box_addr(size_t box, size_t len, u8 quirks) { - int closest_multiple_of_4; + size_t offset_of_group, offset_in_group, this_group = box / 4; + size_t group_size; - closest_multiple_of_4 = (offset / 4) * 4; - offset -= closest_multiple_of_4; - return closest_multiple_of_4 + (3 - offset); -} + if (quirks & QUIRK_LSW32_IS_FIRST) + offset_of_group = this_group * 4; + else + offset_of_group = len - ((this_group + 1) * 4); -static int get_reverse_lsw32_offset(int offset, size_t len) -{ - int closest_multiple_of_4; - int word_index; - - word_index = offset / 4; - closest_multiple_of_4 = word_index * 4; - offset -= closest_multiple_of_4; - word_index = (len / 4) - word_index - 1; - return word_index * 4 + offset; -} + group_size = min(4, len - offset_of_group); -static void adjust_for_msb_right_quirk(u64 *to_write, int *box_start_bit, - int *box_end_bit, u8 *box_mask) -{ - int box_bit_width = *box_start_bit - *box_end_bit + 1; - int new_box_start_bit, new_box_end_bit; - - *to_write >>= *box_end_bit; - *to_write = bitrev8(*to_write) >> (8 - box_bit_width); - *to_write <<= *box_end_bit; - - new_box_end_bit = box_bit_width - *box_start_bit - 1; - new_box_start_bit = box_bit_width - *box_end_bit - 1; - *box_mask = GENMASK_ULL(new_box_start_bit, new_box_end_bit); - *box_start_bit = new_box_start_bit; - *box_end_bit = new_box_end_bit; + if (quirks & QUIRK_LITTLE_ENDIAN) + offset_in_group = box - this_group * 4; + else + offset_in_group = group_size - (box - this_group * 4) - 1; + + return offset_of_group + offset_in_group; } /** - * packing - Convert numbers (currently u64) between a packed and an unpacked - * format. Unpacked means laid out in memory in the CPU's native - * understanding of integers, while packed means anything else that - * requires translation. + * pack - Pack u64 number into bitfield of buffer. * * @pbuf: Pointer to a buffer holding the packed value. - * @uval: Pointer to an u64 holding the unpacked value. + * @uval: CPU-readable unpacked value to pack. * @startbit: The index (in logical notation, compensated for quirks) where * the packed value starts within pbuf. Must be larger than, or * equal to, endbit. @@ -62,79 +63,179 @@ static void adjust_for_msb_right_quirk(u64 *to_write, int *box_start_bit, * the packed value ends within pbuf. Must be smaller than, or equal * to, startbit. * @pbuflen: The length in bytes of the packed buffer pointed to by @pbuf. - * @op: If PACK, then uval will be treated as const pointer and copied (packed) - * into pbuf, between startbit and endbit. - * If UNPACK, then pbuf will be treated as const pointer and the logical - * value between startbit and endbit will be copied (unpacked) to uval. * @quirks: A bit mask of QUIRK_LITTLE_ENDIAN, QUIRK_LSW32_IS_FIRST and * QUIRK_MSB_ON_THE_RIGHT. * * Return: 0 on success, EINVAL or ERANGE if called incorrectly. Assuming - * correct usage, return code may be discarded. - * If op is PACK, pbuf is modified. - * If op is UNPACK, uval is modified. + * correct usage, return code may be discarded. The @pbuf memory will + * be modified on success. */ -int packing(void *pbuf, u64 *uval, int startbit, int endbit, size_t pbuflen, - enum packing_op op, u8 quirks) +int pack(void *pbuf, u64 uval, size_t startbit, size_t endbit, size_t pbuflen, + u8 quirks) { - /* Number of bits for storing "uval" - * also width of the field to access in the pbuf - */ - u64 value_width; /* Logical byte indices corresponding to the * start and end of the field. */ int plogical_first_u8, plogical_last_u8, box; + /* width of the field to access in the pbuf */ + u64 value_width; - /* startbit is expected to be larger than endbit */ - if (startbit < endbit) + /* startbit is expected to be larger than endbit, and both are + * expected to be within the logically addressable range of the buffer. + */ + if (unlikely(startbit < endbit || startbit >= BITS_PER_BYTE * pbuflen)) /* Invalid function call */ return -EINVAL; value_width = startbit - endbit + 1; - if (value_width > 64) + if (unlikely(value_width > 64)) return -ERANGE; /* Check if "uval" fits in "value_width" bits. * If value_width is 64, the check will fail, but any * 64-bit uval will surely fit. */ - if (op == PACK && value_width < 64 && (*uval >= (1ull << value_width))) + if (unlikely(value_width < 64 && uval >= (1ull << value_width))) /* Cannot store "uval" inside "value_width" bits. * Truncating "uval" is most certainly not desirable, * so simply erroring out is appropriate. */ return -ERANGE; + /* Iterate through an idealistic view of the pbuf as an u64 with + * no quirks, u8 by u8 (aligned at u8 boundaries), from high to low + * logical bit significance. "box" denotes the current logical u8. + */ + plogical_first_u8 = startbit / BITS_PER_BYTE; + plogical_last_u8 = endbit / BITS_PER_BYTE; + + for (box = plogical_first_u8; box >= plogical_last_u8; box--) { + /* Bit indices into the currently accessed 8-bit box */ + size_t box_start_bit, box_end_bit, box_addr; + u8 box_mask; + /* Corresponding bits from the unpacked u64 parameter */ + size_t proj_start_bit, proj_end_bit; + u64 proj_mask; + u64 pval; + + /* This u8 may need to be accessed in its entirety + * (from bit 7 to bit 0), or not, depending on the + * input arguments startbit and endbit. + */ + if (box == plogical_first_u8) + box_start_bit = startbit % BITS_PER_BYTE; + else + box_start_bit = 7; + if (box == plogical_last_u8) + box_end_bit = endbit % BITS_PER_BYTE; + else + box_end_bit = 0; + + /* We have determined the box bit start and end. + * Now we calculate where this (masked) u8 box would fit + * in the unpacked (CPU-readable) u64 - the u8 box's + * projection onto the unpacked u64. Though the + * box is u8, the projection is u64 because it may fall + * anywhere within the unpacked u64. + */ + proj_start_bit = ((box * BITS_PER_BYTE) + box_start_bit) - endbit; + proj_end_bit = ((box * BITS_PER_BYTE) + box_end_bit) - endbit; + proj_mask = GENMASK_ULL(proj_start_bit, proj_end_bit); + box_mask = GENMASK(box_start_bit, box_end_bit); + + /* Determine the offset of the u8 box inside the pbuf, + * adjusted for quirks. The adjusted box_addr will be used for + * effective addressing inside the pbuf (so it's not + * logical any longer). + */ + box_addr = calculate_box_addr(box, pbuflen, quirks); + + /* Write to pbuf, read from uval */ + pval = uval & proj_mask; + pval >>= proj_end_bit; + pval <<= box_end_bit; + + if (quirks & QUIRK_MSB_ON_THE_RIGHT) { + pval = bitrev8(pval); + box_mask = bitrev8(box_mask); + } + + ((u8 *)pbuf)[box_addr] &= ~box_mask; + ((u8 *)pbuf)[box_addr] |= pval; + } + return 0; +} +EXPORT_SYMBOL(pack); + +/** + * unpack - Unpack u64 number from packed buffer. + * + * @pbuf: Pointer to a buffer holding the packed value. + * @uval: Pointer to an u64 holding the unpacked value. + * @startbit: The index (in logical notation, compensated for quirks) where + * the packed value starts within pbuf. Must be larger than, or + * equal to, endbit. + * @endbit: The index (in logical notation, compensated for quirks) where + * the packed value ends within pbuf. Must be smaller than, or equal + * to, startbit. + * @pbuflen: The length in bytes of the packed buffer pointed to by @pbuf. + * @quirks: A bit mask of QUIRK_LITTLE_ENDIAN, QUIRK_LSW32_IS_FIRST and + * QUIRK_MSB_ON_THE_RIGHT. + * + * Return: 0 on success, EINVAL or ERANGE if called incorrectly. Assuming + * correct usage, return code may be discarded. The @uval will be + * modified on success. + */ +int unpack(const void *pbuf, u64 *uval, size_t startbit, size_t endbit, + size_t pbuflen, u8 quirks) +{ + /* Logical byte indices corresponding to the + * start and end of the field. + */ + int plogical_first_u8, plogical_last_u8, box; + /* width of the field to access in the pbuf */ + u64 value_width; + + /* startbit is expected to be larger than endbit, and both are + * expected to be within the logically addressable range of the buffer. + */ + if (unlikely(startbit < endbit || startbit >= BITS_PER_BYTE * pbuflen)) + /* Invalid function call */ + return -EINVAL; + + value_width = startbit - endbit + 1; + if (unlikely(value_width > 64)) + return -ERANGE; + /* Initialize parameter */ - if (op == UNPACK) - *uval = 0; + *uval = 0; /* Iterate through an idealistic view of the pbuf as an u64 with * no quirks, u8 by u8 (aligned at u8 boundaries), from high to low * logical bit significance. "box" denotes the current logical u8. */ - plogical_first_u8 = startbit / 8; - plogical_last_u8 = endbit / 8; + plogical_first_u8 = startbit / BITS_PER_BYTE; + plogical_last_u8 = endbit / BITS_PER_BYTE; for (box = plogical_first_u8; box >= plogical_last_u8; box--) { /* Bit indices into the currently accessed 8-bit box */ - int box_start_bit, box_end_bit, box_addr; + size_t box_start_bit, box_end_bit, box_addr; u8 box_mask; /* Corresponding bits from the unpacked u64 parameter */ - int proj_start_bit, proj_end_bit; + size_t proj_start_bit, proj_end_bit; u64 proj_mask; + u64 pval; /* This u8 may need to be accessed in its entirety * (from bit 7 to bit 0), or not, depending on the * input arguments startbit and endbit. */ if (box == plogical_first_u8) - box_start_bit = startbit % 8; + box_start_bit = startbit % BITS_PER_BYTE; else box_start_bit = 7; if (box == plogical_last_u8) - box_end_bit = endbit % 8; + box_end_bit = endbit % BITS_PER_BYTE; else box_end_bit = 0; @@ -145,57 +246,72 @@ int packing(void *pbuf, u64 *uval, int startbit, int endbit, size_t pbuflen, * box is u8, the projection is u64 because it may fall * anywhere within the unpacked u64. */ - proj_start_bit = ((box * 8) + box_start_bit) - endbit; - proj_end_bit = ((box * 8) + box_end_bit) - endbit; + proj_start_bit = ((box * BITS_PER_BYTE) + box_start_bit) - endbit; + proj_end_bit = ((box * BITS_PER_BYTE) + box_end_bit) - endbit; proj_mask = GENMASK_ULL(proj_start_bit, proj_end_bit); - box_mask = GENMASK_ULL(box_start_bit, box_end_bit); + box_mask = GENMASK(box_start_bit, box_end_bit); /* Determine the offset of the u8 box inside the pbuf, * adjusted for quirks. The adjusted box_addr will be used for * effective addressing inside the pbuf (so it's not * logical any longer). */ - box_addr = pbuflen - box - 1; - if (quirks & QUIRK_LITTLE_ENDIAN) - box_addr = get_le_offset(box_addr); - if (quirks & QUIRK_LSW32_IS_FIRST) - box_addr = get_reverse_lsw32_offset(box_addr, - pbuflen); - - if (op == UNPACK) { - u64 pval; - - /* Read from pbuf, write to uval */ - pval = ((u8 *)pbuf)[box_addr] & box_mask; - if (quirks & QUIRK_MSB_ON_THE_RIGHT) - adjust_for_msb_right_quirk(&pval, - &box_start_bit, - &box_end_bit, - &box_mask); - - pval >>= box_end_bit; - pval <<= proj_end_bit; - *uval &= ~proj_mask; - *uval |= pval; - } else { - u64 pval; - - /* Write to pbuf, read from uval */ - pval = (*uval) & proj_mask; - pval >>= proj_end_bit; - if (quirks & QUIRK_MSB_ON_THE_RIGHT) - adjust_for_msb_right_quirk(&pval, - &box_start_bit, - &box_end_bit, - &box_mask); - - pval <<= box_end_bit; - ((u8 *)pbuf)[box_addr] &= ~box_mask; - ((u8 *)pbuf)[box_addr] |= pval; - } + box_addr = calculate_box_addr(box, pbuflen, quirks); + + /* Read from pbuf, write to uval */ + pval = ((u8 *)pbuf)[box_addr]; + + if (quirks & QUIRK_MSB_ON_THE_RIGHT) + pval = bitrev8(pval); + + pval &= box_mask; + + pval >>= box_end_bit; + pval <<= proj_end_bit; + *uval &= ~proj_mask; + *uval |= pval; } return 0; } +EXPORT_SYMBOL(unpack); + +/** + * packing - Convert numbers (currently u64) between a packed and an unpacked + * format. Unpacked means laid out in memory in the CPU's native + * understanding of integers, while packed means anything else that + * requires translation. + * + * @pbuf: Pointer to a buffer holding the packed value. + * @uval: Pointer to an u64 holding the unpacked value. + * @startbit: The index (in logical notation, compensated for quirks) where + * the packed value starts within pbuf. Must be larger than, or + * equal to, endbit. + * @endbit: The index (in logical notation, compensated for quirks) where + * the packed value ends within pbuf. Must be smaller than, or equal + * to, startbit. + * @pbuflen: The length in bytes of the packed buffer pointed to by @pbuf. + * @op: If PACK, then uval will be treated as const pointer and copied (packed) + * into pbuf, between startbit and endbit. + * If UNPACK, then pbuf will be treated as const pointer and the logical + * value between startbit and endbit will be copied (unpacked) to uval. + * @quirks: A bit mask of QUIRK_LITTLE_ENDIAN, QUIRK_LSW32_IS_FIRST and + * QUIRK_MSB_ON_THE_RIGHT. + * + * Note: this is deprecated, prefer to use pack() or unpack() in new code. + * + * Return: 0 on success, EINVAL or ERANGE if called incorrectly. Assuming + * correct usage, return code may be discarded. + * If op is PACK, pbuf is modified. + * If op is UNPACK, uval is modified. + */ +int packing(void *pbuf, u64 *uval, int startbit, int endbit, size_t pbuflen, + enum packing_op op, u8 quirks) +{ + if (op == PACK) + return pack(pbuf, *uval, startbit, endbit, pbuflen, quirks); + + return unpack(pbuf, uval, startbit, endbit, pbuflen, quirks); +} EXPORT_SYMBOL(packing); MODULE_DESCRIPTION("Generic bitfield packing and unpacking"); diff --git a/lib/packing_test.c b/lib/packing_test.c new file mode 100644 index 000000000000..b38ea43c03fd --- /dev/null +++ b/lib/packing_test.c @@ -0,0 +1,413 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2024, Vladimir Oltean <olteanv@gmail.com> + * Copyright (c) 2024, Intel Corporation. + */ +#include <kunit/test.h> +#include <linux/packing.h> + +struct packing_test_case { + const char *desc; + const u8 *pbuf; + size_t pbuf_size; + u64 uval; + size_t start_bit; + size_t end_bit; + u8 quirks; +}; + +#define NO_QUIRKS 0 + +/** + * PBUF - Initialize .pbuf and .pbuf_size + * @array: elements of constant physical buffer + * + * Initializes the .pbuf and .pbuf_size fields of a struct packing_test_case + * with a constant array of the specified elements. + */ +#define PBUF(array...) \ + .pbuf = (const u8[]){ array }, \ + .pbuf_size = sizeof((const u8 []){ array }) + +static const struct packing_test_case cases[] = { + /* These tests pack and unpack a magic 64-bit value + * (0xcafedeadbeefcafe) at a fixed logical offset (32) within an + * otherwise zero array of 128 bits (16 bytes). They test all possible + * bit layouts of the 128 bit buffer. + */ + { + .desc = "no quirks, 16 bytes", + PBUF(0x00, 0x00, 0x00, 0x00, 0xca, 0xfe, 0xde, 0xad, + 0xbe, 0xef, 0xca, 0xfe, 0x00, 0x00, 0x00, 0x00), + .uval = 0xcafedeadbeefcafe, + .start_bit = 95, + .end_bit = 32, + .quirks = NO_QUIRKS, + }, + { + .desc = "lsw32 first, 16 bytes", + PBUF(0x00, 0x00, 0x00, 0x00, 0xbe, 0xef, 0xca, 0xfe, + 0xca, 0xfe, 0xde, 0xad, 0x00, 0x00, 0x00, 0x00), + .uval = 0xcafedeadbeefcafe, + .start_bit = 95, + .end_bit = 32, + .quirks = QUIRK_LSW32_IS_FIRST, + }, + { + .desc = "little endian words, 16 bytes", + PBUF(0x00, 0x00, 0x00, 0x00, 0xad, 0xde, 0xfe, 0xca, + 0xfe, 0xca, 0xef, 0xbe, 0x00, 0x00, 0x00, 0x00), + .uval = 0xcafedeadbeefcafe, + .start_bit = 95, + .end_bit = 32, + .quirks = QUIRK_LITTLE_ENDIAN, + }, + { + .desc = "lsw32 first + little endian words, 16 bytes", + PBUF(0x00, 0x00, 0x00, 0x00, 0xfe, 0xca, 0xef, 0xbe, + 0xad, 0xde, 0xfe, 0xca, 0x00, 0x00, 0x00, 0x00), + .uval = 0xcafedeadbeefcafe, + .start_bit = 95, + .end_bit = 32, + .quirks = QUIRK_LSW32_IS_FIRST | QUIRK_LITTLE_ENDIAN, + }, + { + .desc = "msb right, 16 bytes", + PBUF(0x00, 0x00, 0x00, 0x00, 0x53, 0x7f, 0x7b, 0xb5, + 0x7d, 0xf7, 0x53, 0x7f, 0x00, 0x00, 0x00, 0x00), + .uval = 0xcafedeadbeefcafe, + .start_bit = 95, + .end_bit = 32, + .quirks = QUIRK_MSB_ON_THE_RIGHT, + }, + { + .desc = "msb right + lsw32 first, 16 bytes", + PBUF(0x00, 0x00, 0x00, 0x00, 0x7d, 0xf7, 0x53, 0x7f, + 0x53, 0x7f, 0x7b, 0xb5, 0x00, 0x00, 0x00, 0x00), + .uval = 0xcafedeadbeefcafe, + .start_bit = 95, + .end_bit = 32, + .quirks = QUIRK_MSB_ON_THE_RIGHT | QUIRK_LSW32_IS_FIRST, + }, + { + .desc = "msb right + little endian words, 16 bytes", + PBUF(0x00, 0x00, 0x00, 0x00, 0xb5, 0x7b, 0x7f, 0x53, + 0x7f, 0x53, 0xf7, 0x7d, 0x00, 0x00, 0x00, 0x00), + .uval = 0xcafedeadbeefcafe, + .start_bit = 95, + .end_bit = 32, + .quirks = QUIRK_MSB_ON_THE_RIGHT | QUIRK_LITTLE_ENDIAN, + }, + { + .desc = "msb right + lsw32 first + little endian words, 16 bytes", + PBUF(0x00, 0x00, 0x00, 0x00, 0x7f, 0x53, 0xf7, 0x7d, + 0xb5, 0x7b, 0x7f, 0x53, 0x00, 0x00, 0x00, 0x00), + .uval = 0xcafedeadbeefcafe, + .start_bit = 95, + .end_bit = 32, + .quirks = QUIRK_MSB_ON_THE_RIGHT | QUIRK_LSW32_IS_FIRST | QUIRK_LITTLE_ENDIAN, + }, + /* These tests pack and unpack a magic 64-bit value + * (0xcafedeadbeefcafe) at a fixed logical offset (32) within an + * otherwise zero array of varying size from 18 bytes to 24 bytes. + */ + { + .desc = "no quirks, 18 bytes", + PBUF(0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xca, 0xfe, + 0xde, 0xad, 0xbe, 0xef, 0xca, 0xfe, 0x00, 0x00, + 0x00, 0x00), + .uval = 0xcafedeadbeefcafe, + .start_bit = 95, + .end_bit = 32, + .quirks = NO_QUIRKS, + }, + { + .desc = "no quirks, 19 bytes", + PBUF(0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xca, + 0xfe, 0xde, 0xad, 0xbe, 0xef, 0xca, 0xfe, 0x00, + 0x00, 0x00, 0x00), + .uval = 0xcafedeadbeefcafe, + .start_bit = 95, + .end_bit = 32, + .quirks = NO_QUIRKS, + }, + { + .desc = "no quirks, 20 bytes", + PBUF(0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0xca, 0xfe, 0xde, 0xad, 0xbe, 0xef, 0xca, 0xfe, + 0x00, 0x00, 0x00, 0x00), + .uval = 0xcafedeadbeefcafe, + .start_bit = 95, + .end_bit = 32, + .quirks = NO_QUIRKS, + }, + { + .desc = "no quirks, 22 bytes", + PBUF(0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0xca, 0xfe, 0xde, 0xad, 0xbe, 0xef, + 0xca, 0xfe, 0x00, 0x00, 0x00, 0x00), + .uval = 0xcafedeadbeefcafe, + .start_bit = 95, + .end_bit = 32, + .quirks = NO_QUIRKS, + }, + { + .desc = "no quirks, 24 bytes", + PBUF(0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0xca, 0xfe, 0xde, 0xad, + 0xbe, 0xef, 0xca, 0xfe, 0x00, 0x00, 0x00, 0x00), + .uval = 0xcafedeadbeefcafe, + .start_bit = 95, + .end_bit = 32, + .quirks = NO_QUIRKS, + }, + { + .desc = "lsw32 first + little endian words, 18 bytes", + PBUF(0x00, 0x00, 0x00, 0x00, 0xfe, 0xca, 0xef, 0xbe, + 0xad, 0xde, 0xfe, 0xca, 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00), + .uval = 0xcafedeadbeefcafe, + .start_bit = 95, + .end_bit = 32, + .quirks = QUIRK_LSW32_IS_FIRST | QUIRK_LITTLE_ENDIAN, + }, + { + .desc = "lsw32 first + little endian words, 19 bytes", + PBUF(0x00, 0x00, 0x00, 0x00, 0xfe, 0xca, 0xef, 0xbe, + 0xad, 0xde, 0xfe, 0xca, 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00), + .uval = 0xcafedeadbeefcafe, + .start_bit = 95, + .end_bit = 32, + .quirks = QUIRK_LSW32_IS_FIRST | QUIRK_LITTLE_ENDIAN, + }, + { + .desc = "lsw32 first + little endian words, 20 bytes", + PBUF(0x00, 0x00, 0x00, 0x00, 0xfe, 0xca, 0xef, 0xbe, + 0xad, 0xde, 0xfe, 0xca, 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00), + .uval = 0xcafedeadbeefcafe, + .start_bit = 95, + .end_bit = 32, + .quirks = QUIRK_LSW32_IS_FIRST | QUIRK_LITTLE_ENDIAN, + }, + { + .desc = "lsw32 first + little endian words, 22 bytes", + PBUF(0x00, 0x00, 0x00, 0x00, 0xfe, 0xca, 0xef, 0xbe, + 0xad, 0xde, 0xfe, 0xca, 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00), + .uval = 0xcafedeadbeefcafe, + .start_bit = 95, + .end_bit = 32, + .quirks = QUIRK_LSW32_IS_FIRST | QUIRK_LITTLE_ENDIAN, + }, + { + .desc = "lsw32 first + little endian words, 24 bytes", + PBUF(0x00, 0x00, 0x00, 0x00, 0xfe, 0xca, 0xef, 0xbe, + 0xad, 0xde, 0xfe, 0xca, 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00), + .uval = 0xcafedeadbeefcafe, + .start_bit = 95, + .end_bit = 32, + .quirks = QUIRK_LSW32_IS_FIRST | QUIRK_LITTLE_ENDIAN, + }, + /* These tests pack and unpack a magic 64-bit value + * (0x1122334455667788) at an odd starting bit (43) within an + * otherwise zero array of 128 bits (16 bytes). They test all possible + * bit layouts of the 128 bit buffer. + */ + { + .desc = "no quirks, 16 bytes, non-aligned", + PBUF(0x00, 0x00, 0x00, 0x89, 0x11, 0x9a, 0x22, 0xab, + 0x33, 0xbc, 0x40, 0x00, 0x00, 0x00, 0x00, 0x00), + .uval = 0x1122334455667788, + .start_bit = 106, + .end_bit = 43, + .quirks = NO_QUIRKS, + }, + { + .desc = "lsw32 first, 16 bytes, non-aligned", + PBUF(0x00, 0x00, 0x00, 0x00, 0x33, 0xbc, 0x40, 0x00, + 0x11, 0x9a, 0x22, 0xab, 0x00, 0x00, 0x00, 0x89), + .uval = 0x1122334455667788, + .start_bit = 106, + .end_bit = 43, + .quirks = QUIRK_LSW32_IS_FIRST, + }, + { + .desc = "little endian words, 16 bytes, non-aligned", + PBUF(0x89, 0x00, 0x00, 0x00, 0xab, 0x22, 0x9a, 0x11, + 0x00, 0x40, 0xbc, 0x33, 0x00, 0x00, 0x00, 0x00), + .uval = 0x1122334455667788, + .start_bit = 106, + .end_bit = 43, + .quirks = QUIRK_LITTLE_ENDIAN, + }, + { + .desc = "lsw32 first + little endian words, 16 bytes, non-aligned", + PBUF(0x00, 0x00, 0x00, 0x00, 0x00, 0x40, 0xbc, 0x33, + 0xab, 0x22, 0x9a, 0x11, 0x89, 0x00, 0x00, 0x00), + .uval = 0x1122334455667788, + .start_bit = 106, + .end_bit = 43, + .quirks = QUIRK_LSW32_IS_FIRST | QUIRK_LITTLE_ENDIAN, + }, + { + .desc = "msb right, 16 bytes, non-aligned", + PBUF(0x00, 0x00, 0x00, 0x91, 0x88, 0x59, 0x44, 0xd5, + 0xcc, 0x3d, 0x02, 0x00, 0x00, 0x00, 0x00, 0x00), + .uval = 0x1122334455667788, + .start_bit = 106, + .end_bit = 43, + .quirks = QUIRK_MSB_ON_THE_RIGHT, + }, + { + .desc = "msb right + lsw32 first, 16 bytes, non-aligned", + PBUF(0x00, 0x00, 0x00, 0x00, 0xcc, 0x3d, 0x02, 0x00, + 0x88, 0x59, 0x44, 0xd5, 0x00, 0x00, 0x00, 0x91), + .uval = 0x1122334455667788, + .start_bit = 106, + .end_bit = 43, + .quirks = QUIRK_MSB_ON_THE_RIGHT | QUIRK_LSW32_IS_FIRST, + }, + { + .desc = "msb right + little endian words, 16 bytes, non-aligned", + PBUF(0x91, 0x00, 0x00, 0x00, 0xd5, 0x44, 0x59, 0x88, + 0x00, 0x02, 0x3d, 0xcc, 0x00, 0x00, 0x00, 0x00), + .uval = 0x1122334455667788, + .start_bit = 106, + .end_bit = 43, + .quirks = QUIRK_MSB_ON_THE_RIGHT | QUIRK_LITTLE_ENDIAN, + }, + { + .desc = "msb right + lsw32 first + little endian words, 16 bytes, non-aligned", + PBUF(0x00, 0x00, 0x00, 0x00, 0x00, 0x02, 0x3d, 0xcc, + 0xd5, 0x44, 0x59, 0x88, 0x91, 0x00, 0x00, 0x00), + .uval = 0x1122334455667788, + .start_bit = 106, + .end_bit = 43, + .quirks = QUIRK_MSB_ON_THE_RIGHT | QUIRK_LSW32_IS_FIRST | QUIRK_LITTLE_ENDIAN, + }, + /* These tests pack and unpack a u64 with all bits set + * (0xffffffffffffffff) at an odd starting bit (43) within an + * otherwise zero array of 128 bits (16 bytes). They test all possible + * bit layouts of the 128 bit buffer. + */ + { + .desc = "no quirks, 16 bytes, non-aligned, 0xff", + PBUF(0x00, 0x00, 0x07, 0xff, 0xff, 0xff, 0xff, 0xff, + 0xff, 0xff, 0xf8, 0x00, 0x00, 0x00, 0x00, 0x00), + .uval = 0xffffffffffffffff, + .start_bit = 106, + .end_bit = 43, + .quirks = NO_QUIRKS, + }, + { + .desc = "lsw32 first, 16 bytes, non-aligned, 0xff", + PBUF(0x00, 0x00, 0x00, 0x00, 0xff, 0xff, 0xf8, 0x00, + 0xff, 0xff, 0xff, 0xff, 0x00, 0x00, 0x07, 0xff), + .uval = 0xffffffffffffffff, + .start_bit = 106, + .end_bit = 43, + .quirks = QUIRK_LSW32_IS_FIRST, + }, + { + .desc = "little endian words, 16 bytes, non-aligned, 0xff", + PBUF(0xff, 0x07, 0x00, 0x00, 0xff, 0xff, 0xff, 0xff, + 0x00, 0xf8, 0xff, 0xff, 0x00, 0x00, 0x00, 0x00), + .uval = 0xffffffffffffffff, + .start_bit = 106, + .end_bit = 43, + .quirks = QUIRK_LITTLE_ENDIAN, + }, + { + .desc = "lsw32 first + little endian words, 16 bytes, non-aligned, 0xff", + PBUF(0x00, 0x00, 0x00, 0x00, 0x00, 0xf8, 0xff, 0xff, + 0xff, 0xff, 0xff, 0xff, 0xff, 0x07, 0x00, 0x00), + .uval = 0xffffffffffffffff, + .start_bit = 106, + .end_bit = 43, + .quirks = QUIRK_LSW32_IS_FIRST | QUIRK_LITTLE_ENDIAN, + }, + { + .desc = "msb right, 16 bytes, non-aligned, 0xff", + PBUF(0x00, 0x00, 0xe0, 0xff, 0xff, 0xff, 0xff, 0xff, + 0xff, 0xff, 0x1f, 0x00, 0x00, 0x00, 0x00, 0x00), + .uval = 0xffffffffffffffff, + .start_bit = 106, + .end_bit = 43, + .quirks = QUIRK_MSB_ON_THE_RIGHT, + }, + { + .desc = "msb right + lsw32 first, 16 bytes, non-aligned, 0xff", + PBUF(0x00, 0x00, 0x00, 0x00, 0xff, 0xff, 0x1f, 0x00, + 0xff, 0xff, 0xff, 0xff, 0x00, 0x00, 0xe0, 0xff), + .uval = 0xffffffffffffffff, + .start_bit = 106, + .end_bit = 43, + .quirks = QUIRK_MSB_ON_THE_RIGHT | QUIRK_LSW32_IS_FIRST, + }, + { + .desc = "msb right + little endian words, 16 bytes, non-aligned, 0xff", + PBUF(0xff, 0xe0, 0x00, 0x00, 0xff, 0xff, 0xff, 0xff, + 0x00, 0x1f, 0xff, 0xff, 0x00, 0x00, 0x00, 0x00), + .uval = 0xffffffffffffffff, + .start_bit = 106, + .end_bit = 43, + .quirks = QUIRK_MSB_ON_THE_RIGHT | QUIRK_LITTLE_ENDIAN, + }, + { + .desc = "msb right + lsw32 first + little endian words, 16 bytes, non-aligned, 0xff", + PBUF(0x00, 0x00, 0x00, 0x00, 0x00, 0x1f, 0xff, 0xff, + 0xff, 0xff, 0xff, 0xff, 0xff, 0xe0, 0x00, 0x00), + .uval = 0xffffffffffffffff, + .start_bit = 106, + .end_bit = 43, + .quirks = QUIRK_MSB_ON_THE_RIGHT | QUIRK_LSW32_IS_FIRST | QUIRK_LITTLE_ENDIAN, + }, +}; + +KUNIT_ARRAY_PARAM_DESC(packing, cases, desc); + +static void packing_test_pack(struct kunit *test) +{ + const struct packing_test_case *params = test->param_value; + u8 *pbuf; + int err; + + pbuf = kunit_kzalloc(test, params->pbuf_size, GFP_KERNEL); + KUNIT_ASSERT_NOT_NULL(test, pbuf); + + err = pack(pbuf, params->uval, params->start_bit, params->end_bit, + params->pbuf_size, params->quirks); + + KUNIT_EXPECT_EQ_MSG(test, err, 0, "pack() returned %pe\n", ERR_PTR(err)); + KUNIT_EXPECT_MEMEQ(test, pbuf, params->pbuf, params->pbuf_size); +} + +static void packing_test_unpack(struct kunit *test) +{ + const struct packing_test_case *params = test->param_value; + u64 uval; + int err; + + err = unpack(params->pbuf, &uval, params->start_bit, params->end_bit, + params->pbuf_size, params->quirks); + KUNIT_EXPECT_EQ_MSG(test, err, 0, "unpack() returned %pe\n", ERR_PTR(err)); + KUNIT_EXPECT_EQ(test, uval, params->uval); +} + +static struct kunit_case packing_test_cases[] = { + KUNIT_CASE_PARAM(packing_test_pack, packing_gen_params), + KUNIT_CASE_PARAM(packing_test_unpack, packing_gen_params), + {}, +}; + +static struct kunit_suite packing_test_suite = { + .name = "packing", + .test_cases = packing_test_cases, +}; + +kunit_test_suite(packing_test_suite); + +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("KUnit tests for packing library"); diff --git a/lib/random32.c b/lib/random32.c index 0a5a0e3600c8..24e7acd9343f 100644 --- a/lib/random32.c +++ b/lib/random32.c @@ -36,7 +36,7 @@ #include <linux/percpu.h> #include <linux/export.h> #include <linux/jiffies.h> -#include <linux/random.h> +#include <linux/prandom.h> #include <linux/sched.h> #include <linux/bitops.h> #include <linux/slab.h> diff --git a/lib/rbtree_test.c b/lib/rbtree_test.c index 41ae3c7570d3..8655a76d29a1 100644 --- a/lib/rbtree_test.c +++ b/lib/rbtree_test.c @@ -2,7 +2,7 @@ #include <linux/module.h> #include <linux/moduleparam.h> #include <linux/rbtree_augmented.h> -#include <linux/random.h> +#include <linux/prandom.h> #include <linux/slab.h> #include <asm/timex.h> diff --git a/lib/test_bpf.c b/lib/test_bpf.c index fa5edd6ef7f7..2eed1ad958e9 100644 --- a/lib/test_bpf.c +++ b/lib/test_bpf.c @@ -14,7 +14,7 @@ #include <linux/skbuff.h> #include <linux/netdevice.h> #include <linux/if_vlan.h> -#include <linux/random.h> +#include <linux/prandom.h> #include <linux/highmem.h> #include <linux/sched.h> diff --git a/lib/test_parman.c b/lib/test_parman.c index 35e32243693c..f9b97426a337 100644 --- a/lib/test_parman.c +++ b/lib/test_parman.c @@ -39,7 +39,7 @@ #include <linux/slab.h> #include <linux/bitops.h> #include <linux/err.h> -#include <linux/random.h> +#include <linux/prandom.h> #include <linux/parman.h> #define TEST_PARMAN_PRIO_SHIFT 7 /* defines number of prios for testing */ diff --git a/lib/test_printf.c b/lib/test_printf.c index 8448b6d02bd9..59dbe4f9a4cb 100644 --- a/lib/test_printf.c +++ b/lib/test_printf.c @@ -386,6 +386,66 @@ kernel_ptr(void) static void __init struct_resource(void) { + struct resource test_resource = { + .start = 0xc0ffee00, + .end = 0xc0ffee00, + .flags = IORESOURCE_MEM, + }; + + test("[mem 0xc0ffee00 flags 0x200]", + "%pr", &test_resource); + + test_resource = (struct resource) { + .start = 0xc0ffee, + .end = 0xba5eba11, + .flags = IORESOURCE_MEM, + }; + test("[mem 0x00c0ffee-0xba5eba11 flags 0x200]", + "%pr", &test_resource); + + test_resource = (struct resource) { + .start = 0xba5eba11, + .end = 0xc0ffee, + .flags = IORESOURCE_MEM, + }; + test("[mem 0xba5eba11-0x00c0ffee flags 0x200]", + "%pr", &test_resource); + + test_resource = (struct resource) { + .start = 0xba5eba11, + .end = 0xba5eca11, + .flags = IORESOURCE_MEM, + }; + + test("[mem 0xba5eba11-0xba5eca11 flags 0x200]", + "%pr", &test_resource); + + test_resource = (struct resource) { + .start = 0xba11, + .end = 0xca10, + .flags = IORESOURCE_IO | + IORESOURCE_DISABLED | + IORESOURCE_UNSET, + }; + + test("[io size 0x1000 disabled]", + "%pR", &test_resource); +} + +static void __init +struct_range(void) +{ + struct range test_range = DEFINE_RANGE(0xc0ffee00ba5eba11, + 0xc0ffee00ba5eba11); + test("[range 0xc0ffee00ba5eba11]", "%pra", &test_range); + + test_range = DEFINE_RANGE(0xc0ffee, 0xba5eba11); + test("[range 0x0000000000c0ffee-0x00000000ba5eba11]", + "%pra", &test_range); + + test_range = DEFINE_RANGE(0xba5eba11, 0xc0ffee); + test("[range 0x00000000ba5eba11-0x0000000000c0ffee]", + "%pra", &test_range); } static void __init @@ -763,6 +823,7 @@ test_pointer(void) symbol_ptr(); kernel_ptr(); struct_resource(); + struct_range(); addr(); escaped_str(); hex_string(); diff --git a/lib/test_scanf.c b/lib/test_scanf.c index 7257b1768545..44f8508c9d88 100644 --- a/lib/test_scanf.c +++ b/lib/test_scanf.c @@ -11,7 +11,7 @@ #include <linux/module.h> #include <linux/overflow.h> #include <linux/printk.h> -#include <linux/random.h> +#include <linux/prandom.h> #include <linux/slab.h> #include <linux/string.h> diff --git a/lib/vsprintf.c b/lib/vsprintf.c index c5e2ec9303c5..6ac02bbb7df1 100644 --- a/lib/vsprintf.c +++ b/lib/vsprintf.c @@ -1040,6 +1040,20 @@ static const struct printf_spec default_dec04_spec = { }; static noinline_for_stack +char *hex_range(char *buf, char *end, u64 start_val, u64 end_val, + struct printf_spec spec) +{ + buf = number(buf, end, start_val, spec); + if (start_val == end_val) + return buf; + + if (buf < end) + *buf = '-'; + ++buf; + return number(buf, end, end_val, spec); +} + +static noinline_for_stack char *resource_string(char *buf, char *end, struct resource *res, struct printf_spec spec, const char *fmt) { @@ -1115,11 +1129,7 @@ char *resource_string(char *buf, char *end, struct resource *res, p = string_nocheck(p, pend, "size ", str_spec); p = number(p, pend, resource_size(res), *specp); } else { - p = number(p, pend, res->start, *specp); - if (res->start != res->end) { - *p++ = '-'; - p = number(p, pend, res->end, *specp); - } + p = hex_range(p, pend, res->start, res->end, *specp); } if (decode) { if (res->flags & IORESOURCE_MEM_64) @@ -1141,6 +1151,31 @@ char *resource_string(char *buf, char *end, struct resource *res, } static noinline_for_stack +char *range_string(char *buf, char *end, const struct range *range, + struct printf_spec spec, const char *fmt) +{ + char sym[sizeof("[range 0x0123456789abcdef-0x0123456789abcdef]")]; + char *p = sym, *pend = sym + sizeof(sym); + + struct printf_spec range_spec = { + .field_width = 2 + 2 * sizeof(range->start), /* 0x + 2 * 8 */ + .flags = SPECIAL | SMALL | ZEROPAD, + .base = 16, + .precision = -1, + }; + + if (check_pointer(&buf, end, range, spec)) + return buf; + + p = string_nocheck(p, pend, "[range ", default_str_spec); + p = hex_range(p, pend, range->start, range->end, range_spec); + *p++ = ']'; + *p = '\0'; + + return string_nocheck(buf, end, sym, spec); +} + +static noinline_for_stack char *hex_string(char *buf, char *end, u8 *addr, struct printf_spec spec, const char *fmt) { @@ -2229,6 +2264,15 @@ char *fwnode_string(char *buf, char *end, struct fwnode_handle *fwnode, return widen_string(buf, buf - buf_start, end, spec); } +static noinline_for_stack +char *resource_or_range(const char *fmt, char *buf, char *end, void *ptr, + struct printf_spec spec) +{ + if (*fmt == 'r' && fmt[1] == 'a') + return range_string(buf, end, ptr, spec, fmt); + return resource_string(buf, end, ptr, spec, fmt); +} + int __init no_hash_pointers_enable(char *str) { if (no_hash_pointers) @@ -2277,6 +2321,7 @@ char *rust_fmt_argument(char *buf, char *end, void *ptr); * - 'Bb' as above with module build ID (for use in backtraces) * - 'R' For decoded struct resource, e.g., [mem 0x0-0x1f 64bit pref] * - 'r' For raw struct resource, e.g., [mem 0x0-0x1f flags 0x201] + * - 'ra' For struct ranges, e.g., [range 0x0000000000000000 - 0x00000000000000ff] * - 'b[l]' For a bitmap, the number of bits is determined by the field * width which must be explicitly specified either as part of the * format string '%32b[l]' or through '%*b[l]', [l] selects @@ -2401,7 +2446,7 @@ char *pointer(const char *fmt, char *buf, char *end, void *ptr, return symbol_string(buf, end, ptr, spec, fmt); case 'R': case 'r': - return resource_string(buf, end, ptr, spec, fmt); + return resource_or_range(fmt, buf, end, ptr, spec); case 'h': return hex_string(buf, end, ptr, spec, fmt); case 'b': |