diff options
Diffstat (limited to 'lib')
-rw-r--r-- | lib/Kconfig.debug | 80 | ||||
-rw-r--r-- | lib/Kconfig.kgdb | 11 | ||||
-rw-r--r-- | lib/Makefile | 7 | ||||
-rw-r--r-- | lib/bitmap.c | 11 | ||||
-rw-r--r-- | lib/cmdline.c | 2 | ||||
-rw-r--r-- | lib/debug_locks.c | 2 | ||||
-rw-r--r-- | lib/debugobjects.c | 46 | ||||
-rw-r--r-- | lib/idr.c | 2 | ||||
-rw-r--r-- | lib/iomap.c | 3 | ||||
-rw-r--r-- | lib/iommu-helper.c | 5 | ||||
-rw-r--r-- | lib/klist.c | 96 | ||||
-rw-r--r-- | lib/kobject.c | 3 | ||||
-rw-r--r-- | lib/kobject_uevent.c | 6 | ||||
-rw-r--r-- | lib/lmb.c | 2 | ||||
-rw-r--r-- | lib/percpu_counter.c | 8 | ||||
-rw-r--r-- | lib/plist.c | 13 | ||||
-rw-r--r-- | lib/radix-tree.c | 180 | ||||
-rw-r--r-- | lib/random32.c | 48 | ||||
-rw-r--r-- | lib/ratelimit.c | 3 | ||||
-rw-r--r-- | lib/scatterlist.c | 4 | ||||
-rw-r--r-- | lib/show_mem.c | 63 | ||||
-rw-r--r-- | lib/smp_processor_id.c | 5 | ||||
-rw-r--r-- | lib/string_helpers.c | 64 | ||||
-rw-r--r-- | lib/swiotlb.c | 51 | ||||
-rw-r--r-- | lib/syscall.c | 75 | ||||
-rw-r--r-- | lib/vsprintf.c | 13 |
26 files changed, 634 insertions, 169 deletions
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index e1d4764435e..aa81d284844 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -394,7 +394,7 @@ config LOCKDEP bool depends on DEBUG_KERNEL && TRACE_IRQFLAGS_SUPPORT && STACKTRACE_SUPPORT && LOCKDEP_SUPPORT select STACKTRACE - select FRAME_POINTER if !X86 && !MIPS + select FRAME_POINTER if !X86 && !MIPS && !PPC select KALLSYMS select KALLSYMS_ALL @@ -495,6 +495,15 @@ config DEBUG_VM If unsure, say N. +config DEBUG_VIRTUAL + bool "Debug VM translations" + depends on DEBUG_KERNEL && X86 + help + Enable some costly sanity checks in virtual to page code. This can + catch mistakes with virt_to_page() and friends. + + If unsure, say N. + config DEBUG_WRITECOUNT bool "Debug filesystem writers count" depends on DEBUG_KERNEL @@ -597,6 +606,19 @@ config RCU_TORTURE_TEST_RUNNABLE Say N here if you want the RCU torture tests to start only after being manually enabled via /proc. +config RCU_CPU_STALL_DETECTOR + bool "Check for stalled CPUs delaying RCU grace periods" + depends on CLASSIC_RCU + default n + help + This option causes RCU to printk information on which + CPUs are delaying the current grace period, but only when + the grace period extends for excessive time periods. + + Say Y if you want RCU to perform such checks. + + Say N if you are unsure. + config KPROBES_SANITY_TEST bool "Kprobes sanity tests" depends on DEBUG_KERNEL @@ -624,6 +646,28 @@ config BACKTRACE_SELF_TEST Say N if you are unsure. +config DEBUG_BLOCK_EXT_DEVT + bool "Force extended block device numbers and spread them" + depends on DEBUG_KERNEL + depends on BLOCK + default n + help + Conventionally, block device numbers are allocated from + predetermined contiguous area. However, extended block area + may introduce non-contiguous block device numbers. This + option forces most block device numbers to be allocated from + the extended space and spreads them to discover kernel or + userland code paths which assume predetermined contiguous + device number allocation. + + Note that turning on this debug option shuffles all the + device numbers for all IDE and SCSI devices including libata + ones, so root partition specified using device number + directly (via rdev or root=MAJ:MIN) won't work anymore. + Textual device names (root=/dev/sdXn) will continue to work. + + Say N if you are unsure. + config LKDTM tristate "Linux Kernel Dump Test Tool Module" depends on DEBUG_KERNEL @@ -661,10 +705,21 @@ config FAIL_PAGE_ALLOC config FAIL_MAKE_REQUEST bool "Fault-injection capability for disk IO" - depends on FAULT_INJECTION + depends on FAULT_INJECTION && BLOCK help Provide fault-injection capability for disk IO. +config FAIL_IO_TIMEOUT + bool "Faul-injection capability for faking disk interrupts" + depends on FAULT_INJECTION && BLOCK + help + Provide fault-injection capability on end IO handling. This + will make the block layer "forget" an interrupt as configured, + thus exercising the error handling. + + Only works with drivers that use the generic timeout handling, + for others it wont do anything. + config FAULT_INJECTION_DEBUG_FS bool "Debugfs entries for fault-injection capabilities" depends on FAULT_INJECTION && SYSFS && DEBUG_FS @@ -676,13 +731,13 @@ config FAULT_INJECTION_STACKTRACE_FILTER depends on FAULT_INJECTION_DEBUG_FS && STACKTRACE_SUPPORT depends on !X86_64 select STACKTRACE - select FRAME_POINTER + select FRAME_POINTER if !PPC help Provide stacktrace filter for fault-injection capabilities config LATENCYTOP bool "Latency measuring infrastructure" - select FRAME_POINTER if !MIPS + select FRAME_POINTER if !MIPS && !PPC select KALLSYMS select KALLSYMS_ALL select STACKTRACE @@ -693,6 +748,14 @@ config LATENCYTOP Enable this option if you want to use the LatencyTOP tool to find out which userspace is blocking on what kernel operations. +config SYSCTL_SYSCALL_CHECK + bool "Sysctl checks" + depends on SYSCTL_SYSCALL + ---help--- + sys_sysctl uses binary paths that have been found challenging + to properly maintain and use. This enables checks that help + you to keep things correct. + source kernel/trace/Kconfig config PROVIDE_OHCI1394_DMA_INIT @@ -735,6 +798,15 @@ config FIREWIRE_OHCI_REMOTE_DMA If unsure, say N. +menuconfig BUILD_DOCSRC + bool "Build targets in Documentation/ tree" + depends on HEADERS_CHECK + help + This option attempts to build objects from the source files in the + kernel Documentation/ tree. + + Say N if you are unsure. + source "samples/Kconfig" source "lib/Kconfig.kgdb" diff --git a/lib/Kconfig.kgdb b/lib/Kconfig.kgdb index 2cfd2721f7e..9b5d1d7f2ef 100644 --- a/lib/Kconfig.kgdb +++ b/lib/Kconfig.kgdb @@ -4,14 +4,17 @@ config HAVE_ARCH_KGDB menuconfig KGDB bool "KGDB: kernel debugging with remote gdb" - select FRAME_POINTER depends on HAVE_ARCH_KGDB depends on DEBUG_KERNEL && EXPERIMENTAL help If you say Y here, it will be possible to remotely debug the - kernel using gdb. Documentation of kernel debugger is available - at http://kgdb.sourceforge.net as well as in DocBook form - in Documentation/DocBook/. If unsure, say N. + kernel using gdb. It is recommended but not required, that + you also turn on the kernel config option + CONFIG_FRAME_POINTER to aid in producing more reliable stack + backtraces in the external debugger. Documentation of + kernel debugger is available at http://kgdb.sourceforge.net + as well as in DocBook form in Documentation/DocBook/. If + unsure, say N. if KGDB diff --git a/lib/Makefile b/lib/Makefile index 9085ad6fa53..44001af76a7 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -11,7 +11,7 @@ lib-y := ctype.o string.o vsprintf.o cmdline.o \ rbtree.o radix-tree.o dump_stack.o \ idr.o int_sqrt.o extable.o prio_tree.o \ sha1.o irq_regs.o reciprocal_div.o argv_split.o \ - proportions.o prio_heap.o ratelimit.o + proportions.o prio_heap.o ratelimit.o show_mem.o lib-$(CONFIG_MMU) += ioremap.o lib-$(CONFIG_SMP) += cpumask.o @@ -19,7 +19,8 @@ lib-$(CONFIG_SMP) += cpumask.o lib-y += kobject.o kref.o klist.o obj-y += bcd.o div64.o sort.o parser.o halfmd4.o debug_locks.o random32.o \ - bust_spinlocks.o hexdump.o kasprintf.o bitmap.o scatterlist.o + bust_spinlocks.o hexdump.o kasprintf.o bitmap.o scatterlist.o \ + string_helpers.o ifeq ($(CONFIG_DEBUG_KOBJECT),y) CFLAGS_kobject.o += -DDEBUG @@ -78,6 +79,8 @@ lib-$(CONFIG_GENERIC_BUG) += bug.o obj-$(CONFIG_HAVE_LMB) += lmb.o +obj-$(CONFIG_HAVE_ARCH_TRACEHOOK) += syscall.o + hostprogs-y := gen_crc32table clean-files := crc32table.h diff --git a/lib/bitmap.c b/lib/bitmap.c index 482df94ea21..06fb57c86de 100644 --- a/lib/bitmap.c +++ b/lib/bitmap.c @@ -316,6 +316,17 @@ int bitmap_scnprintf(char *buf, unsigned int buflen, EXPORT_SYMBOL(bitmap_scnprintf); /** + * bitmap_scnprintf_len - return buffer length needed to convert + * bitmap to an ASCII hex string + * @nr_bits: number of bits to be converted + */ +int bitmap_scnprintf_len(unsigned int nr_bits) +{ + unsigned int nr_nibbles = ALIGN(nr_bits, 4) / 4; + return nr_nibbles + ALIGN(nr_nibbles, CHUNKSZ / 4) / (CHUNKSZ / 4) - 1; +} + +/** * __bitmap_parse - convert an ASCII hex string into a bitmap. * @buf: pointer to buffer containing string. * @buflen: buffer size in bytes. If string is smaller than this diff --git a/lib/cmdline.c b/lib/cmdline.c index 5ba8a942a47..f5f3ad8b62f 100644 --- a/lib/cmdline.c +++ b/lib/cmdline.c @@ -126,7 +126,7 @@ char *get_options(const char *str, int nints, int *ints) * megabyte, or one gigabyte, respectively. */ -unsigned long long memparse(char *ptr, char **retptr) +unsigned long long memparse(const char *ptr, char **retptr) { char *endptr; /* local pointer to end of parsed string */ diff --git a/lib/debug_locks.c b/lib/debug_locks.c index 0ef01d14727..0218b4693dd 100644 --- a/lib/debug_locks.c +++ b/lib/debug_locks.c @@ -8,6 +8,7 @@ * * Copyright (C) 2006 Red Hat, Inc., Ingo Molnar <mingo@redhat.com> */ +#include <linux/kernel.h> #include <linux/rwsem.h> #include <linux/mutex.h> #include <linux/module.h> @@ -37,6 +38,7 @@ int debug_locks_off(void) { if (xchg(&debug_locks, 0)) { if (!debug_locks_silent) { + oops_in_progress = 1; console_verbose(); return 1; } diff --git a/lib/debugobjects.c b/lib/debugobjects.c index f86196390cf..e3ab374e133 100644 --- a/lib/debugobjects.c +++ b/lib/debugobjects.c @@ -112,6 +112,7 @@ static struct debug_obj *lookup_object(void *addr, struct debug_bucket *b) /* * Allocate a new object. If the pool is empty, switch off the debugger. + * Must be called with interrupts disabled. */ static struct debug_obj * alloc_object(void *addr, struct debug_bucket *b, struct debug_obj_descr *descr) @@ -148,17 +149,18 @@ alloc_object(void *addr, struct debug_bucket *b, struct debug_obj_descr *descr) static void free_object(struct debug_obj *obj) { unsigned long idx = (unsigned long)(obj - obj_static_pool); + unsigned long flags; if (obj_pool_free < ODEBUG_POOL_SIZE || idx < ODEBUG_POOL_SIZE) { - spin_lock(&pool_lock); + spin_lock_irqsave(&pool_lock, flags); hlist_add_head(&obj->node, &obj_pool); obj_pool_free++; obj_pool_used--; - spin_unlock(&pool_lock); + spin_unlock_irqrestore(&pool_lock, flags); } else { - spin_lock(&pool_lock); + spin_lock_irqsave(&pool_lock, flags); obj_pool_used--; - spin_unlock(&pool_lock); + spin_unlock_irqrestore(&pool_lock, flags); kmem_cache_free(obj_cache, obj); } } @@ -171,6 +173,7 @@ static void debug_objects_oom(void) { struct debug_bucket *db = obj_hash; struct hlist_node *node, *tmp; + HLIST_HEAD(freelist); struct debug_obj *obj; unsigned long flags; int i; @@ -179,11 +182,14 @@ static void debug_objects_oom(void) for (i = 0; i < ODEBUG_HASH_SIZE; i++, db++) { spin_lock_irqsave(&db->lock, flags); - hlist_for_each_entry_safe(obj, node, tmp, &db->list, node) { + hlist_move_list(&db->list, &freelist); + spin_unlock_irqrestore(&db->lock, flags); + + /* Now free them */ + hlist_for_each_entry_safe(obj, node, tmp, &freelist, node) { hlist_del(&obj->node); free_object(obj); } - spin_unlock_irqrestore(&db->lock, flags); } } @@ -205,9 +211,8 @@ static void debug_print_object(struct debug_obj *obj, char *msg) if (limit < 5 && obj->descr != descr_test) { limit++; - printk(KERN_ERR "ODEBUG: %s %s object type: %s\n", msg, + WARN(1, KERN_ERR "ODEBUG: %s %s object type: %s\n", msg, obj_states[obj->state], obj->descr->name); - WARN_ON(1); } debug_objects_warnings++; } @@ -499,8 +504,9 @@ void debug_object_free(void *addr, struct debug_obj_descr *descr) return; default: hlist_del(&obj->node); + spin_unlock_irqrestore(&db->lock, flags); free_object(obj); - break; + return; } out_unlock: spin_unlock_irqrestore(&db->lock, flags); @@ -511,6 +517,7 @@ static void __debug_check_no_obj_freed(const void *address, unsigned long size) { unsigned long flags, oaddr, saddr, eaddr, paddr, chunks; struct hlist_node *node, *tmp; + HLIST_HEAD(freelist); struct debug_obj_descr *descr; enum debug_obj_state state; struct debug_bucket *db; @@ -546,11 +553,18 @@ repeat: goto repeat; default: hlist_del(&obj->node); - free_object(obj); + hlist_add_head(&obj->node, &freelist); break; } } spin_unlock_irqrestore(&db->lock, flags); + + /* Now free them */ + hlist_for_each_entry_safe(obj, node, tmp, &freelist, node) { + hlist_del(&obj->node); + free_object(obj); + } + if (cnt > debug_objects_maxchain) debug_objects_maxchain = cnt; } @@ -733,26 +747,22 @@ check_results(void *addr, enum debug_obj_state state, int fixups, int warnings) obj = lookup_object(addr, db); if (!obj && state != ODEBUG_STATE_NONE) { - printk(KERN_ERR "ODEBUG: selftest object not found\n"); - WARN_ON(1); + WARN(1, KERN_ERR "ODEBUG: selftest object not found\n"); goto out; } if (obj && obj->state != state) { - printk(KERN_ERR "ODEBUG: selftest wrong state: %d != %d\n", + WARN(1, KERN_ERR "ODEBUG: selftest wrong state: %d != %d\n", obj->state, state); - WARN_ON(1); goto out; } if (fixups != debug_objects_fixups) { - printk(KERN_ERR "ODEBUG: selftest fixups failed %d != %d\n", + WARN(1, KERN_ERR "ODEBUG: selftest fixups failed %d != %d\n", fixups, debug_objects_fixups); - WARN_ON(1); goto out; } if (warnings != debug_objects_warnings) { - printk(KERN_ERR "ODEBUG: selftest warnings failed %d != %d\n", + WARN(1, KERN_ERR "ODEBUG: selftest warnings failed %d != %d\n", warnings, debug_objects_warnings); - WARN_ON(1); goto out; } res = 0; diff --git a/lib/idr.c b/lib/idr.c index 3476f8203e9..e728c7fccc4 100644 --- a/lib/idr.c +++ b/lib/idr.c @@ -607,7 +607,7 @@ void *idr_replace(struct idr *idp, void *ptr, int id) } EXPORT_SYMBOL(idr_replace); -static void idr_cache_ctor(struct kmem_cache *idr_layer_cache, void *idr_layer) +static void idr_cache_ctor(void *idr_layer) { memset(idr_layer, 0, sizeof(struct idr_layer)); } diff --git a/lib/iomap.c b/lib/iomap.c index 37a3ea4cac9..d3222938515 100644 --- a/lib/iomap.c +++ b/lib/iomap.c @@ -40,8 +40,7 @@ static void bad_io_access(unsigned long port, const char *access) static int count = 10; if (count) { count--; - printk(KERN_ERR "Bad IO access at port %#lx (%s)\n", port, access); - WARN_ON(1); + WARN(1, KERN_ERR "Bad IO access at port %#lx (%s)\n", port, access); } } diff --git a/lib/iommu-helper.c b/lib/iommu-helper.c index a3b8d4c3f77..5d90074dca7 100644 --- a/lib/iommu-helper.c +++ b/lib/iommu-helper.c @@ -30,8 +30,7 @@ again: return index; } -static inline void set_bit_area(unsigned long *map, unsigned long i, - int len) +void iommu_area_reserve(unsigned long *map, unsigned long i, int len) { unsigned long end = i + len; while (i < end) { @@ -64,7 +63,7 @@ again: start = index + 1; goto again; } - set_bit_area(map, index, nr); + iommu_area_reserve(map, index, nr); } return index; } diff --git a/lib/klist.c b/lib/klist.c index cca37f96faa..bbdd3015c2c 100644 --- a/lib/klist.c +++ b/lib/klist.c @@ -37,6 +37,37 @@ #include <linux/klist.h> #include <linux/module.h> +/* + * Use the lowest bit of n_klist to mark deleted nodes and exclude + * dead ones from iteration. + */ +#define KNODE_DEAD 1LU +#define KNODE_KLIST_MASK ~KNODE_DEAD + +static struct klist *knode_klist(struct klist_node *knode) +{ + return (struct klist *) + ((unsigned long)knode->n_klist & KNODE_KLIST_MASK); +} + +static bool knode_dead(struct klist_node *knode) +{ + return (unsigned long)knode->n_klist & KNODE_DEAD; +} + +static void knode_set_klist(struct klist_node *knode, struct klist *klist) +{ + knode->n_klist = klist; + /* no knode deserves to start its life dead */ + WARN_ON(knode_dead(knode)); +} + +static void knode_kill(struct klist_node *knode) +{ + /* and no knode should die twice ever either, see we're very humane */ + WARN_ON(knode_dead(knode)); + *(unsigned long *)&knode->n_klist |= KNODE_DEAD; +} /** * klist_init - Initialize a klist structure. @@ -79,7 +110,7 @@ static void klist_node_init(struct klist *k, struct klist_node *n) INIT_LIST_HEAD(&n->n_node); init_completion(&n->n_removed); kref_init(&n->n_ref); - n->n_klist = k; + knode_set_klist(n, k); if (k->get) k->get(n); } @@ -115,7 +146,7 @@ EXPORT_SYMBOL_GPL(klist_add_tail); */ void klist_add_after(struct klist_node *n, struct klist_node *pos) { - struct klist *k = pos->n_klist; + struct klist *k = knode_klist(pos); klist_node_init(k, n); spin_lock(&k->k_lock); @@ -131,7 +162,7 @@ EXPORT_SYMBOL_GPL(klist_add_after); */ void klist_add_before(struct klist_node *n, struct klist_node *pos) { - struct klist *k = pos->n_klist; + struct klist *k = knode_klist(pos); klist_node_init(k, n); spin_lock(&k->k_lock); @@ -144,9 +175,10 @@ static void klist_release(struct kref *kref) { struct klist_node *n = container_of(kref, struct klist_node, n_ref); + WARN_ON(!knode_dead(n)); list_del(&n->n_node); complete(&n->n_removed); - n->n_klist = NULL; + knode_set_klist(n, NULL); } static int klist_dec_and_del(struct klist_node *n) @@ -154,22 +186,29 @@ static int klist_dec_and_del(struct klist_node *n) return kref_put(&n->n_ref, klist_release); } -/** - * klist_del - Decrement the reference count of node and try to remove. - * @n: node we're deleting. - */ -void klist_del(struct klist_node *n) +static void klist_put(struct klist_node *n, bool kill) { - struct klist *k = n->n_klist; + struct klist *k = knode_klist(n); void (*put)(struct klist_node *) = k->put; spin_lock(&k->k_lock); + if (kill) + knode_kill(n); if (!klist_dec_and_del(n)) put = NULL; spin_unlock(&k->k_lock); if (put) put(n); } + +/** + * klist_del - Decrement the reference count of node and try to remove. + * @n: node we're deleting. + */ +void klist_del(struct klist_node *n) +{ + klist_put(n, true); +} EXPORT_SYMBOL_GPL(klist_del); /** @@ -206,7 +245,6 @@ void klist_iter_init_node(struct klist *k, struct klist_iter *i, struct klist_node *n) { i->i_klist = k; - i->i_head = &k->k_list; i->i_cur = n; if (n) kref_get(&n->n_ref); @@ -237,7 +275,7 @@ EXPORT_SYMBOL_GPL(klist_iter_init); void klist_iter_exit(struct klist_iter *i) { if (i->i_cur) { - klist_del(i->i_cur); + klist_put(i->i_cur, false); i->i_cur = NULL; } } @@ -258,27 +296,33 @@ static struct klist_node *to_klist_node(struct list_head *n) */ struct klist_node *klist_next(struct klist_iter *i) { - struct list_head *next; - struct klist_node *lnode = i->i_cur; - struct klist_node *knode = NULL; void (*put)(struct klist_node *) = i->i_klist->put; + struct klist_node *last = i->i_cur; + struct klist_node *next; spin_lock(&i->i_klist->k_lock); - if (lnode) { - next = lnode->n_node.next; - if (!klist_dec_and_del(lnode)) + + if (last) { + next = to_klist_node(last->n_node.next); + if (!klist_dec_and_del(last)) put = NULL; } else - next = i->i_head->next; + next = to_klist_node(i->i_klist->k_list.next); - if (next != i->i_head) { - knode = to_klist_node(next); - kref_get(&knode->n_ref); + i->i_cur = NULL; + while (next != to_klist_node(&i->i_klist->k_list)) { + if (likely(!knode_dead(next))) { + kref_get(&next->n_ref); + i->i_cur = next; + break; + } + next = to_klist_node(next->n_node.next); } - i->i_cur = knode; + spin_unlock(&i->i_klist->k_lock); - if (put && lnode) - put(lnode); - return knode; + + if (put && last) + put(last); + return i->i_cur; } EXPORT_SYMBOL_GPL(klist_next); diff --git a/lib/kobject.c b/lib/kobject.c index bd732ffebc8..fbf0ae28237 100644 --- a/lib/kobject.c +++ b/lib/kobject.c @@ -223,8 +223,7 @@ static int kobject_set_name_vargs(struct kobject *kobj, const char *fmt, return -ENOMEM; /* ewww... some of these buggers have '/' in the name ... */ - s = strchr(kobj->name, '/'); - if (s) + while ((s = strchr(kobj->name, '/'))) s[0] = '!'; kfree(old_name); diff --git a/lib/kobject_uevent.c b/lib/kobject_uevent.c index 9f8d599459d..3f914725bda 100644 --- a/lib/kobject_uevent.c +++ b/lib/kobject_uevent.c @@ -285,8 +285,7 @@ int add_uevent_var(struct kobj_uevent_env *env, const char *format, ...) int len; if (env->envp_idx >= ARRAY_SIZE(env->envp)) { - printk(KERN_ERR "add_uevent_var: too many keys\n"); - WARN_ON(1); + WARN(1, KERN_ERR "add_uevent_var: too many keys\n"); return -ENOMEM; } @@ -297,8 +296,7 @@ int add_uevent_var(struct kobj_uevent_env *env, const char *format, ...) va_end(args); if (len >= (sizeof(env->buf) - env->buflen)) { - printk(KERN_ERR "add_uevent_var: buffer size too small\n"); - WARN_ON(1); + WARN(1, KERN_ERR "add_uevent_var: buffer size too small\n"); return -ENOMEM; } diff --git a/lib/lmb.c b/lib/lmb.c index 5d7b9286503..97e54703708 100644 --- a/lib/lmb.c +++ b/lib/lmb.c @@ -462,6 +462,8 @@ void __init lmb_enforce_memory_limit(u64 memory_limit) if (lmb.memory.region[0].size < lmb.rmo_size) lmb.rmo_size = lmb.memory.region[0].size; + memory_limit = lmb_end_of_DRAM(); + /* And truncate any reserves above the limit also. */ for (i = 0; i < lmb.reserved.cnt; i++) { p = &lmb.reserved.region[i]; diff --git a/lib/percpu_counter.c b/lib/percpu_counter.c index 4a8ba4bf5f6..a8663890a88 100644 --- a/lib/percpu_counter.c +++ b/lib/percpu_counter.c @@ -52,7 +52,7 @@ EXPORT_SYMBOL(__percpu_counter_add); * Add up all the per-cpu counts, return the result. This is a more accurate * but much slower version of percpu_counter_read_positive() */ -s64 __percpu_counter_sum(struct percpu_counter *fbc, int set) +s64 __percpu_counter_sum(struct percpu_counter *fbc) { s64 ret; int cpu; @@ -62,11 +62,9 @@ s64 __percpu_counter_sum(struct percpu_counter *fbc, int set) for_each_online_cpu(cpu) { s32 *pcount = per_cpu_ptr(fbc->counters, cpu); ret += *pcount; - if (set) - *pcount = 0; + *pcount = 0; } - if (set) - fbc->count = ret; + fbc->count = ret; spin_unlock(&fbc->lock); return ret; diff --git a/lib/plist.c b/lib/plist.c index 3074a02272f..d6c64a824e1 100644 --- a/lib/plist.c +++ b/lib/plist.c @@ -31,12 +31,13 @@ static void plist_check_prev_next(struct list_head *t, struct list_head *p, struct list_head *n) { - if (n->prev != p || p->next != n) { - printk("top: %p, n: %p, p: %p\n", t, t->next, t->prev); - printk("prev: %p, n: %p, p: %p\n", p, p->next, p->prev); - printk("next: %p, n: %p, p: %p\n", n, n->next, n->prev); - WARN_ON(1); - } + WARN(n->prev != p || p->next != n, + "top: %p, n: %p, p: %p\n" + "prev: %p, n: %p, p: %p\n" + "next: %p, n: %p, p: %p\n", + t, t->next, t->prev, + p, p->next, p->prev, + n, n->next, n->prev); } static void plist_check_list(struct list_head *top) diff --git a/lib/radix-tree.c b/lib/radix-tree.c index 56ec21a7f73..be86b32bc87 100644 --- a/lib/radix-tree.c +++ b/lib/radix-tree.c @@ -359,18 +359,17 @@ EXPORT_SYMBOL(radix_tree_insert); * Returns: the slot corresponding to the position @index in the * radix tree @root. This is useful for update-if-exists operations. * - * This function cannot be called under rcu_read_lock, it must be - * excluded from writers, as must the returned slot for subsequent - * use by radix_tree_deref_slot() and radix_tree_replace slot. - * Caller must hold tree write locked across slot lookup and - * replace. + * This function can be called under rcu_read_lock iff the slot is not + * modified by radix_tree_replace_slot, otherwise it must be called + * exclusive from other writers. Any dereference of the slot must be done + * using radix_tree_deref_slot. */ void **radix_tree_lookup_slot(struct radix_tree_root *root, unsigned long index) { unsigned int height, shift; struct radix_tree_node *node, **slot; - node = root->rnode; + node = rcu_dereference(root->rnode); if (node == NULL) return NULL; @@ -390,7 +389,7 @@ void **radix_tree_lookup_slot(struct radix_tree_root *root, unsigned long index) do { slot = (struct radix_tree_node **) (node->slots + ((index>>shift) & RADIX_TREE_MAP_MASK)); - node = *slot; + node = rcu_dereference(*slot); if (node == NULL) return NULL; @@ -667,7 +666,7 @@ unsigned long radix_tree_next_hole(struct radix_tree_root *root, EXPORT_SYMBOL(radix_tree_next_hole); static unsigned int -__lookup(struct radix_tree_node *slot, void **results, unsigned long index, +__lookup(struct radix_tree_node *slot, void ***results, unsigned long index, unsigned int max_items, unsigned long *next_index) { unsigned int nr_found = 0; @@ -701,11 +700,9 @@ __lookup(struct radix_tree_node *slot, void **results, unsigned long index, /* Bottom level: grab some items */ for (i = index & RADIX_TREE_MAP_MASK; i < RADIX_TREE_MAP_SIZE; i++) { - struct radix_tree_node *node; index++; - node = slot->slots[i]; - if (node) { - results[nr_found++] = rcu_dereference(node); + if (slot->slots[i]) { + results[nr_found++] = &(slot->slots[i]); if (nr_found == max_items) goto out; } @@ -759,13 +756,22 @@ radix_tree_gang_lookup(struct radix_tree_root *root, void **results, ret = 0; while (ret < max_items) { - unsigned int nr_found; + unsigned int nr_found, slots_found, i; unsigned long next_index; /* Index of next search */ if (cur_index > max_index) break; - nr_found = __lookup(node, results + ret, cur_index, + slots_found = __lookup(node, (void ***)results + ret, cur_index, max_items - ret, &next_index); + nr_found = 0; + for (i = 0; i < slots_found; i++) { + struct radix_tree_node *slot; + slot = *(((void ***)results)[ret + i]); + if (!slot) + continue; + results[ret + nr_found] = rcu_dereference(slot); + nr_found++; + } ret += nr_found; if (next_index == 0) break; @@ -776,12 +782,71 @@ radix_tree_gang_lookup(struct radix_tree_root *root, void **results, } EXPORT_SYMBOL(radix_tree_gang_lookup); +/** + * radix_tree_gang_lookup_slot - perform multiple slot lookup on radix tree + * @root: radix tree root + * @results: where the results of the lookup are placed + * @first_index: start the lookup from this key + * @max_items: place up to this many items at *results + * + * Performs an index-ascending scan of the tree for present items. Places + * their slots at *@results and returns the number of items which were + * placed at *@results. + * + * The implementation is naive. + * + * Like radix_tree_gang_lookup as far as RCU and locking goes. Slots must + * be dereferenced with radix_tree_deref_slot, and if using only RCU + * protection, radix_tree_deref_slot may fail requiring a retry. + */ +unsigned int +radix_tree_gang_lookup_slot(struct radix_tree_root *root, void ***results, + unsigned long first_index, unsigned int max_items) +{ + unsigned long max_index; + struct radix_tree_node *node; + unsigned long cur_index = first_index; + unsigned int ret; + + node = rcu_dereference(root->rnode); + if (!node) + return 0; + + if (!radix_tree_is_indirect_ptr(node)) { + if (first_index > 0) + return 0; + results[0] = (void **)&root->rnode; + return 1; + } + node = radix_tree_indirect_to_ptr(node); + + max_index = radix_tree_maxindex(node->height); + + ret = 0; + w |