X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=kernel%2Flockdep.c;h=06b0c3568f0b230a8c6b669d055c8c442a7eb790;hb=483b4ee60edbefdfbff0dd538fb81f368d9e7c0d;hp=9bad178845135fba9f6b76ac59d408b723c5b5bc;hpb=d6d897cec29252b8d0785198cfa6ca16d30c739d;p=safe%2Fjmp%2Flinux-2.6 diff --git a/kernel/lockdep.c b/kernel/lockdep.c index 9bad178..06b0c35 100644 --- a/kernel/lockdep.c +++ b/kernel/lockdep.c @@ -5,7 +5,8 @@ * * Started by Ingo Molnar: * - * Copyright (C) 2006 Red Hat, Inc., Ingo Molnar + * Copyright (C) 2006,2007 Red Hat, Inc., Ingo Molnar + * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra * * this code maps all the lock dependencies as they occur in a live kernel * and will warn about the following classes of locking bugs: @@ -24,6 +25,7 @@ * Thanks to Arjan van de Ven for coming up with the initial idea of * mapping lock dependencies runtime. */ +#define DISABLE_BRANCH_PROFILING #include #include #include @@ -36,41 +38,84 @@ #include #include #include +#include +#include +#include #include #include "lockdep_internals.h" +#ifdef CONFIG_PROVE_LOCKING +int prove_locking = 1; +module_param(prove_locking, int, 0644); +#else +#define prove_locking 0 +#endif + +#ifdef CONFIG_LOCK_STAT +int lock_stat = 1; +module_param(lock_stat, int, 0644); +#else +#define lock_stat 0 +#endif + /* - * hash_lock: protects the lockdep hashes and class/list/hash allocators. + * lockdep_lock: protects the lockdep graph, the hashes and the + * class/list/hash allocators. * * This is one of the rare exceptions where it's justified * to use a raw spinlock - we really dont want the spinlock - * code to recurse back into the lockdep code. + * code to recurse back into the lockdep code... */ -static raw_spinlock_t hash_lock = (raw_spinlock_t)__RAW_SPIN_LOCK_UNLOCKED; +static raw_spinlock_t lockdep_lock = (raw_spinlock_t)__RAW_SPIN_LOCK_UNLOCKED; -static int lockdep_initialized; +static int graph_lock(void) +{ + __raw_spin_lock(&lockdep_lock); + /* + * Make sure that if another CPU detected a bug while + * walking the graph we dont change it (while the other + * CPU is busy printing out stuff with the graph lock + * dropped already) + */ + if (!debug_locks) { + __raw_spin_unlock(&lockdep_lock); + return 0; + } + /* prevent any recursions within lockdep from causing deadlocks */ + current->lockdep_recursion++; + return 1; +} -unsigned long nr_list_entries; -static struct lock_list list_entries[MAX_LOCKDEP_ENTRIES]; +static inline int graph_unlock(void) +{ + if (debug_locks && !__raw_spin_is_locked(&lockdep_lock)) + return DEBUG_LOCKS_WARN_ON(1); + + current->lockdep_recursion--; + __raw_spin_unlock(&lockdep_lock); + return 0; +} /* - * Allocate a lockdep entry. (assumes hash_lock held, returns - * with NULL on failure) + * Turn lock debugging off and return with 0 if it was off already, + * and also release the graph lock: */ -static struct lock_list *alloc_list_entry(void) +static inline int debug_locks_off_graph_unlock(void) { - if (nr_list_entries >= MAX_LOCKDEP_ENTRIES) { - __raw_spin_unlock(&hash_lock); - debug_locks_off(); - printk("BUG: MAX_LOCKDEP_ENTRIES too low!\n"); - printk("turning off the locking correctness validator.\n"); - return NULL; - } - return list_entries + nr_list_entries++; + int ret = debug_locks_off(); + + __raw_spin_unlock(&lockdep_lock); + + return ret; } +static int lockdep_initialized; + +unsigned long nr_list_entries; +static struct lock_list list_entries[MAX_LOCKDEP_ENTRIES]; + /* * All data structures here are protected by the global debug_lock. * @@ -80,6 +125,130 @@ static struct lock_list *alloc_list_entry(void) unsigned long nr_lock_classes; static struct lock_class lock_classes[MAX_LOCKDEP_KEYS]; +static inline struct lock_class *hlock_class(struct held_lock *hlock) +{ + if (!hlock->class_idx) { + DEBUG_LOCKS_WARN_ON(1); + return NULL; + } + return lock_classes + hlock->class_idx - 1; +} + +#ifdef CONFIG_LOCK_STAT +static DEFINE_PER_CPU(struct lock_class_stats[MAX_LOCKDEP_KEYS], lock_stats); + +static int lock_point(unsigned long points[], unsigned long ip) +{ + int i; + + for (i = 0; i < LOCKSTAT_POINTS; i++) { + if (points[i] == 0) { + points[i] = ip; + break; + } + if (points[i] == ip) + break; + } + + return i; +} + +static void lock_time_inc(struct lock_time *lt, s64 time) +{ + if (time > lt->max) + lt->max = time; + + if (time < lt->min || !lt->min) + lt->min = time; + + lt->total += time; + lt->nr++; +} + +static inline void lock_time_add(struct lock_time *src, struct lock_time *dst) +{ + dst->min += src->min; + dst->max += src->max; + dst->total += src->total; + dst->nr += src->nr; +} + +struct lock_class_stats lock_stats(struct lock_class *class) +{ + struct lock_class_stats stats; + int cpu, i; + + memset(&stats, 0, sizeof(struct lock_class_stats)); + for_each_possible_cpu(cpu) { + struct lock_class_stats *pcs = + &per_cpu(lock_stats, cpu)[class - lock_classes]; + + for (i = 0; i < ARRAY_SIZE(stats.contention_point); i++) + stats.contention_point[i] += pcs->contention_point[i]; + + for (i = 0; i < ARRAY_SIZE(stats.contending_point); i++) + stats.contending_point[i] += pcs->contending_point[i]; + + lock_time_add(&pcs->read_waittime, &stats.read_waittime); + lock_time_add(&pcs->write_waittime, &stats.write_waittime); + + lock_time_add(&pcs->read_holdtime, &stats.read_holdtime); + lock_time_add(&pcs->write_holdtime, &stats.write_holdtime); + + for (i = 0; i < ARRAY_SIZE(stats.bounces); i++) + stats.bounces[i] += pcs->bounces[i]; + } + + return stats; +} + +void clear_lock_stats(struct lock_class *class) +{ + int cpu; + + for_each_possible_cpu(cpu) { + struct lock_class_stats *cpu_stats = + &per_cpu(lock_stats, cpu)[class - lock_classes]; + + memset(cpu_stats, 0, sizeof(struct lock_class_stats)); + } + memset(class->contention_point, 0, sizeof(class->contention_point)); + memset(class->contending_point, 0, sizeof(class->contending_point)); +} + +static struct lock_class_stats *get_lock_stats(struct lock_class *class) +{ + return &get_cpu_var(lock_stats)[class - lock_classes]; +} + +static void put_lock_stats(struct lock_class_stats *stats) +{ + put_cpu_var(lock_stats); +} + +static void lock_release_holdtime(struct held_lock *hlock) +{ + struct lock_class_stats *stats; + s64 holdtime; + + if (!lock_stat) + return; + + holdtime = sched_clock() - hlock->holdtime_stamp; + + stats = get_lock_stats(hlock_class(hlock)); + if (hlock->read) + lock_time_inc(&stats->read_holdtime, holdtime); + else + lock_time_inc(&stats->write_holdtime, holdtime); + put_lock_stats(stats); +} +#else +static inline void lock_release_holdtime(struct held_lock *hlock) +{ +} +#endif + /* * We keep a global list of all lock classes. The list only grows, * never shrinks. The list is only accessed with the lockdep @@ -92,24 +261,18 @@ LIST_HEAD(all_lock_classes); */ #define CLASSHASH_BITS (MAX_LOCKDEP_KEYS_BITS - 1) #define CLASSHASH_SIZE (1UL << CLASSHASH_BITS) -#define CLASSHASH_MASK (CLASSHASH_SIZE - 1) -#define __classhashfn(key) ((((unsigned long)key >> CLASSHASH_BITS) + (unsigned long)key) & CLASSHASH_MASK) +#define __classhashfn(key) hash_long((unsigned long)key, CLASSHASH_BITS) #define classhashentry(key) (classhash_table + __classhashfn((key))) static struct list_head classhash_table[CLASSHASH_SIZE]; -unsigned long nr_lock_chains; -static struct lock_chain lock_chains[MAX_LOCKDEP_CHAINS]; - /* * We put the lock dependency chains into a hash-table as well, to cache * their existence: */ #define CHAINHASH_BITS (MAX_LOCKDEP_CHAINS_BITS-1) #define CHAINHASH_SIZE (1UL << CHAINHASH_BITS) -#define CHAINHASH_MASK (CHAINHASH_SIZE - 1) -#define __chainhashfn(chain) \ - (((chain >> CHAINHASH_BITS) + chain) & CHAINHASH_MASK) +#define __chainhashfn(chain) hash_long(chain, CHAINHASH_BITS) #define chainhashentry(chain) (chainhash_table + __chainhashfn((chain))) static struct list_head chainhash_table[CHAINHASH_SIZE]; @@ -121,39 +284,28 @@ static struct list_head chainhash_table[CHAINHASH_SIZE]; * unique. */ #define iterate_chain_key(key1, key2) \ - (((key1) << MAX_LOCKDEP_KEYS_BITS/2) ^ \ - ((key1) >> (64-MAX_LOCKDEP_KEYS_BITS/2)) ^ \ + (((key1) << MAX_LOCKDEP_KEYS_BITS) ^ \ + ((key1) >> (64-MAX_LOCKDEP_KEYS_BITS)) ^ \ (key2)) void lockdep_off(void) { current->lockdep_recursion++; } - EXPORT_SYMBOL(lockdep_off); void lockdep_on(void) { current->lockdep_recursion--; } - EXPORT_SYMBOL(lockdep_on); -int lockdep_internal(void) -{ - return current->lockdep_recursion != 0; -} - -EXPORT_SYMBOL(lockdep_internal); - /* * Debugging switches: */ #define VERBOSE 0 -#ifdef VERBOSE -# define VERY_VERBOSE 0 -#endif +#define VERY_VERBOSE 0 #if VERBOSE # define HARDIRQ_VERBOSE 1 @@ -178,8 +330,8 @@ static int class_filter(struct lock_class *class) !strcmp(class->name, "&struct->lockfield")) return 1; #endif - /* Allow everything else. 0 would be filter everything else */ - return 1; + /* Filter everything else. 1 would be to allow everything else */ + return 0; } #endif @@ -191,29 +343,9 @@ static int verbose(struct lock_class *class) return 0; } -#ifdef CONFIG_TRACE_IRQFLAGS - -static int hardirq_verbose(struct lock_class *class) -{ -#if HARDIRQ_VERBOSE - return class_filter(class); -#endif - return 0; -} - -static int softirq_verbose(struct lock_class *class) -{ -#if SOFTIRQ_VERBOSE - return class_filter(class); -#endif - return 0; -} - -#endif - /* * Stack-trace: tightly packed array of stack backtrace - * addresses. Protected by the hash_lock. + * addresses. Protected by the graph_lock. */ unsigned long nr_stack_trace_entries; static unsigned long stack_trace[MAX_STACK_TRACE_ENTRIES]; @@ -224,21 +356,22 @@ static int save_trace(struct stack_trace *trace) trace->max_entries = MAX_STACK_TRACE_ENTRIES - nr_stack_trace_entries; trace->entries = stack_trace + nr_stack_trace_entries; - save_stack_trace(trace, NULL, 0, 3); + trace->skip = 3; + + save_stack_trace(trace); trace->max_entries = trace->nr_entries; nr_stack_trace_entries += trace->nr_entries; - if (DEBUG_LOCKS_WARN_ON(nr_stack_trace_entries > MAX_STACK_TRACE_ENTRIES)) - return 0; if (nr_stack_trace_entries == MAX_STACK_TRACE_ENTRIES) { - __raw_spin_unlock(&hash_lock); - if (debug_locks_off()) { - printk("BUG: MAX_STACK_TRACE_ENTRIES too low!\n"); - printk("turning off the locking correctness validator.\n"); - dump_stack(); - } + if (!debug_locks_off_graph_unlock()) + return 0; + + printk("BUG: MAX_STACK_TRACE_ENTRIES too low!\n"); + printk("turning off the locking correctness validator.\n"); + dump_stack(); + return 0; } @@ -251,6 +384,19 @@ unsigned int nr_process_chains; unsigned int max_lockdep_depth; unsigned int max_recursion_depth; +static unsigned int lockdep_dependency_gen_id; + +static bool lockdep_dependency_visit(struct lock_class *source, + unsigned int depth) +{ + if (!depth) + lockdep_dependency_gen_id++; + if (source->dep_gen_id == lockdep_dependency_gen_id) + return true; + source->dep_gen_id = lockdep_dependency_gen_id; + return false; +} + #ifdef CONFIG_DEBUG_LOCKDEP /* * We cannot printk in early bootup code. Not even early_printk() @@ -258,6 +404,11 @@ unsigned int max_recursion_depth; * about it later on, in lockdep_info(). */ static int lockdep_init_error; +static unsigned long lockdep_init_trace_data[20]; +static struct stack_trace lockdep_init_trace = { + .max_entries = ARRAY_SIZE(lockdep_init_trace_data), + .entries = lockdep_init_trace_data, +}; /* * Various lockdep statistics: @@ -307,10 +458,7 @@ static const char *usage_str[] = const char * __get_key_name(struct lockdep_subclass_key *key, char *str) { - unsigned long offs, size; - char *modname; - - return kallsyms_lookup((unsigned long)key, &size, &offs, &modname, str); + return kallsyms_lookup((unsigned long)key, NULL, NULL, NULL, str); } void @@ -349,7 +497,7 @@ get_usage_chars(struct lock_class *class, char *c1, char *c2, char *c3, char *c4 static void print_lock_name(struct lock_class *class) { - char str[128], c1, c2, c3, c4; + char str[KSYM_NAME_LEN], c1, c2, c3, c4; const char *name; get_usage_chars(class, &c1, &c2, &c3, &c4); @@ -371,7 +519,7 @@ static void print_lock_name(struct lock_class *class) static void print_lockdep_cache(struct lockdep_map *lock) { const char *name; - char str[128]; + char str[KSYM_NAME_LEN]; name = lock->name; if (!name) @@ -382,7 +530,7 @@ static void print_lockdep_cache(struct lockdep_map *lock) static void print_lock(struct held_lock *hlock) { - print_lock_name(hlock->class); + print_lock_name(hlock_class(hlock)); printk(", at: "); print_ip_sym(hlock->acquire_ip); } @@ -392,11 +540,11 @@ static void lockdep_print_held_locks(struct task_struct *curr) int i, depth = curr->lockdep_depth; if (!depth) { - printk("no locks held by %s/%d.\n", curr->comm, curr->pid); + printk("no locks held by %s/%d.\n", curr->comm, task_pid_nr(curr)); return; } printk("%d lock%s held by %s/%d:\n", - depth, depth > 1 ? "s" : "", curr->comm, curr->pid); + depth, depth > 1 ? "s" : "", curr->comm, task_pid_nr(curr)); for (i = 0; i < depth; i++) { printk(" #%d: ", i); @@ -431,17 +579,23 @@ static void print_lock_class_header(struct lock_class *class, int depth) /* * printk all lock dependencies starting at : */ -static void print_lock_dependencies(struct lock_class *class, int depth) +static void __used +print_lock_dependencies(struct lock_class *class, int depth) { struct lock_list *entry; + if (lockdep_dependency_visit(class, depth)) + return; + if (DEBUG_LOCKS_WARN_ON(depth >= 20)) return; print_lock_class_header(class, depth); list_for_each_entry(entry, &class->locks_after, entry) { - DEBUG_LOCKS_WARN_ON(!entry->class); + if (DEBUG_LOCKS_WARN_ON(!entry->class)) + return; + print_lock_dependencies(entry->class, depth + 1); printk("%*s ... acquired at:\n",depth,""); @@ -450,83 +604,344 @@ static void print_lock_dependencies(struct lock_class *class, int depth) } } +static void print_kernel_version(void) +{ + printk("%s %.*s\n", init_utsname()->release, + (int)strcspn(init_utsname()->version, " "), + init_utsname()->version); +} + +static int very_verbose(struct lock_class *class) +{ +#if VERY_VERBOSE + return class_filter(class); +#endif + return 0; +} + /* - * Add a new dependency to the head of the list: + * Is this the address of a static object: */ -static int add_lock_to_list(struct lock_class *class, struct lock_class *this, - struct list_head *head, unsigned long ip) +static int static_obj(void *obj) { - struct lock_list *entry; + unsigned long start = (unsigned long) &_stext, + end = (unsigned long) &_end, + addr = (unsigned long) obj; +#ifdef CONFIG_SMP + int i; +#endif + /* - * Lock not present yet - get a new dependency struct and - * add it to the list: + * static variable? */ - entry = alloc_list_entry(); - if (!entry) - return 0; - - entry->class = this; - save_trace(&entry->trace); + if ((addr >= start) && (addr < end)) + return 1; +#ifdef CONFIG_SMP /* - * Since we never remove from the dependency list, the list can - * be walked lockless by other CPUs, it's only allocation - * that must be protected by the spinlock. But this also means - * we must make new entries visible only once writes to the - * entry become visible - hence the RCU op: + * percpu var? */ - list_add_tail_rcu(&entry->entry, head); + for_each_possible_cpu(i) { + start = (unsigned long) &__per_cpu_start + per_cpu_offset(i); + end = (unsigned long) &__per_cpu_start + PERCPU_ENOUGH_ROOM + + per_cpu_offset(i); - return 1; -} + if ((addr >= start) && (addr < end)) + return 1; + } +#endif -/* - * Recursive, forwards-direction lock-dependency checking, used for - * both noncyclic checking and for hardirq-unsafe/softirq-unsafe - * checking. - * - * (to keep the stackframe of the recursive functions small we - * use these global variables, and we also mark various helper - * functions as noinline.) - */ -static struct held_lock *check_source, *check_target; + /* + * module var? + */ + return is_module_address(addr); +} /* - * Print a dependency chain entry (this is only done when a deadlock - * has been detected): + * To make lock name printouts unique, we calculate a unique + * class->name_version generation counter: */ -static noinline int -print_circular_bug_entry(struct lock_list *target, unsigned int depth) +static int count_matching_names(struct lock_class *new_class) { - if (debug_locks_silent) + struct lock_class *class; + int count = 0; + + if (!new_class->name) return 0; - printk("\n-> #%u", depth); - print_lock_name(target->class); - printk(":\n"); - print_stack_trace(&target->trace, 6); - return 0; + list_for_each_entry(class, &all_lock_classes, lock_entry) { + if (new_class->key - new_class->subclass == class->key) + return class->name_version; + if (class->name && !strcmp(class->name, new_class->name)) + count = max(count, class->name_version); + } + + return count + 1; } /* - * When a circular dependency is detected, print the - * header first: + * Register a lock's class in the hash-table, if the class is not present + * yet. Otherwise we look it up. We cache the result in the lock object + * itself, so actual lookup of the hash should be once per lock object. */ -static noinline int -print_circular_bug_header(struct lock_list *entry, unsigned int depth) +static inline struct lock_class * +look_up_lock_class(struct lockdep_map *lock, unsigned int subclass) { - struct task_struct *curr = current; - - __raw_spin_unlock(&hash_lock); - debug_locks_off(); - if (debug_locks_silent) - return 0; + struct lockdep_subclass_key *key; + struct list_head *hash_head; + struct lock_class *class; - printk("\n=======================================================\n"); - printk( "[ INFO: possible circular locking dependency detected ]\n"); - printk( "-------------------------------------------------------\n"); +#ifdef CONFIG_DEBUG_LOCKDEP + /* + * If the architecture calls into lockdep before initializing + * the hashes then we'll warn about it later. (we cannot printk + * right now) + */ + if (unlikely(!lockdep_initialized)) { + lockdep_init(); + lockdep_init_error = 1; + save_stack_trace(&lockdep_init_trace); + } +#endif + + /* + * Static locks do not have their class-keys yet - for them the key + * is the lock object itself: + */ + if (unlikely(!lock->key)) + lock->key = (void *)lock; + + /* + * NOTE: the class-key must be unique. For dynamic locks, a static + * lock_class_key variable is passed in through the mutex_init() + * (or spin_lock_init()) call - which acts as the key. For static + * locks we use the lock object itself as the key. + */ + BUILD_BUG_ON(sizeof(struct lock_class_key) > + sizeof(struct lockdep_map)); + + key = lock->key->subkeys + subclass; + + hash_head = classhashentry(key); + + /* + * We can walk the hash lockfree, because the hash only + * grows, and we are careful when adding entries to the end: + */ + list_for_each_entry(class, hash_head, hash_entry) { + if (class->key == key) { + WARN_ON_ONCE(class->name != lock->name); + return class; + } + } + + return NULL; +} + +/* + * Register a lock's class in the hash-table, if the class is not present + * yet. Otherwise we look it up. We cache the result in the lock object + * itself, so actual lookup of the hash should be once per lock object. + */ +static inline struct lock_class * +register_lock_class(struct lockdep_map *lock, unsigned int subclass, int force) +{ + struct lockdep_subclass_key *key; + struct list_head *hash_head; + struct lock_class *class; + unsigned long flags; + + class = look_up_lock_class(lock, subclass); + if (likely(class)) + return class; + + /* + * Debug-check: all keys must be persistent! + */ + if (!static_obj(lock->key)) { + debug_locks_off(); + printk("INFO: trying to register non-static key.\n"); + printk("the code is fine but needs lockdep annotation.\n"); + printk("turning off the locking correctness validator.\n"); + dump_stack(); + + return NULL; + } + + key = lock->key->subkeys + subclass; + hash_head = classhashentry(key); + + raw_local_irq_save(flags); + if (!graph_lock()) { + raw_local_irq_restore(flags); + return NULL; + } + /* + * We have to do the hash-walk again, to avoid races + * with another CPU: + */ + list_for_each_entry(class, hash_head, hash_entry) + if (class->key == key) + goto out_unlock_set; + /* + * Allocate a new key from the static array, and add it to + * the hash: + */ + if (nr_lock_classes >= MAX_LOCKDEP_KEYS) { + if (!debug_locks_off_graph_unlock()) { + raw_local_irq_restore(flags); + return NULL; + } + raw_local_irq_restore(flags); + + printk("BUG: MAX_LOCKDEP_KEYS too low!\n"); + printk("turning off the locking correctness validator.\n"); + return NULL; + } + class = lock_classes + nr_lock_classes++; + debug_atomic_inc(&nr_unused_locks); + class->key = key; + class->name = lock->name; + class->subclass = subclass; + INIT_LIST_HEAD(&class->lock_entry); + INIT_LIST_HEAD(&class->locks_before); + INIT_LIST_HEAD(&class->locks_after); + class->name_version = count_matching_names(class); + /* + * We use RCU's safe list-add method to make + * parallel walking of the hash-list safe: + */ + list_add_tail_rcu(&class->hash_entry, hash_head); + /* + * Add it to the global list of classes: + */ + list_add_tail_rcu(&class->lock_entry, &all_lock_classes); + + if (verbose(class)) { + graph_unlock(); + raw_local_irq_restore(flags); + + printk("\nnew class %p: %s", class->key, class->name); + if (class->name_version > 1) + printk("#%d", class->name_version); + printk("\n"); + dump_stack(); + + raw_local_irq_save(flags); + if (!graph_lock()) { + raw_local_irq_restore(flags); + return NULL; + } + } +out_unlock_set: + graph_unlock(); + raw_local_irq_restore(flags); + + if (!subclass || force) + lock->class_cache = class; + + if (DEBUG_LOCKS_WARN_ON(class->subclass != subclass)) + return NULL; + + return class; +} + +#ifdef CONFIG_PROVE_LOCKING +/* + * Allocate a lockdep entry. (assumes the graph_lock held, returns + * with NULL on failure) + */ +static struct lock_list *alloc_list_entry(void) +{ + if (nr_list_entries >= MAX_LOCKDEP_ENTRIES) { + if (!debug_locks_off_graph_unlock()) + return NULL; + + printk("BUG: MAX_LOCKDEP_ENTRIES too low!\n"); + printk("turning off the locking correctness validator.\n"); + return NULL; + } + return list_entries + nr_list_entries++; +} + +/* + * Add a new dependency to the head of the list: + */ +static int add_lock_to_list(struct lock_class *class, struct lock_class *this, + struct list_head *head, unsigned long ip, int distance) +{ + struct lock_list *entry; + /* + * Lock not present yet - get a new dependency struct and + * add it to the list: + */ + entry = alloc_list_entry(); + if (!entry) + return 0; + + if (!save_trace(&entry->trace)) + return 0; + + entry->class = this; + entry->distance = distance; + /* + * Since we never remove from the dependency list, the list can + * be walked lockless by other CPUs, it's only allocation + * that must be protected by the spinlock. But this also means + * we must make new entries visible only once writes to the + * entry become visible - hence the RCU op: + */ + list_add_tail_rcu(&entry->entry, head); + + return 1; +} + +/* + * Recursive, forwards-direction lock-dependency checking, used for + * both noncyclic checking and for hardirq-unsafe/softirq-unsafe + * checking. + * + * (to keep the stackframe of the recursive functions small we + * use these global variables, and we also mark various helper + * functions as noinline.) + */ +static struct held_lock *check_source, *check_target; + +/* + * Print a dependency chain entry (this is only done when a deadlock + * has been detected): + */ +static noinline int +print_circular_bug_entry(struct lock_list *target, unsigned int depth) +{ + if (debug_locks_silent) + return 0; + printk("\n-> #%u", depth); + print_lock_name(target->class); + printk(":\n"); + print_stack_trace(&target->trace, 6); + + return 0; +} + +/* + * When a circular dependency is detected, print the + * header first: + */ +static noinline int +print_circular_bug_header(struct lock_list *entry, unsigned int depth) +{ + struct task_struct *curr = current; + + if (!debug_locks_off_graph_unlock() || debug_locks_silent) + return 0; + + printk("\n=======================================================\n"); + printk( "[ INFO: possible circular locking dependency detected ]\n"); + print_kernel_version(); + printk( "-------------------------------------------------------\n"); printk("%s/%d is trying to acquire lock:\n", - curr->comm, curr->pid); + curr->comm, task_pid_nr(curr)); print_lock(check_source); printk("\nbut task is already holding lock:\n"); print_lock(check_target); @@ -546,8 +961,10 @@ static noinline int print_circular_bug_tail(void) if (debug_locks_silent) return 0; - this.class = check_source->class; - save_trace(&this.trace); + this.class = hlock_class(check_source); + if (!save_trace(&this.trace)) + return 0; + print_circular_bug_entry(&this, 0); printk("\nother info that might help us debug this:\n\n"); @@ -559,14 +976,79 @@ static noinline int print_circular_bug_tail(void) return 0; } +#define RECURSION_LIMIT 40 + static int noinline print_infinite_recursion_bug(void) { - __raw_spin_unlock(&hash_lock); - DEBUG_LOCKS_WARN_ON(1); + if (!debug_locks_off_graph_unlock()) + return 0; + + WARN_ON(1); return 0; } +unsigned long __lockdep_count_forward_deps(struct lock_class *class, + unsigned int depth) +{ + struct lock_list *entry; + unsigned long ret = 1; + + if (lockdep_dependency_visit(class, depth)) + return 0; + + /* + * Recurse this class's dependency list: + */ + list_for_each_entry(entry, &class->locks_after, entry) + ret += __lockdep_count_forward_deps(entry->class, depth + 1); + + return ret; +} + +unsigned long lockdep_count_forward_deps(struct lock_class *class) +{ + unsigned long ret, flags; + + local_irq_save(flags); + __raw_spin_lock(&lockdep_lock); + ret = __lockdep_count_forward_deps(class, 0); + __raw_spin_unlock(&lockdep_lock); + local_irq_restore(flags); + + return ret; +} + +unsigned long __lockdep_count_backward_deps(struct lock_class *class, + unsigned int depth) +{ + struct lock_list *entry; + unsigned long ret = 1; + + if (lockdep_dependency_visit(class, depth)) + return 0; + /* + * Recurse this class's dependency list: + */ + list_for_each_entry(entry, &class->locks_before, entry) + ret += __lockdep_count_backward_deps(entry->class, depth + 1); + + return ret; +} + +unsigned long lockdep_count_backward_deps(struct lock_class *class) +{ + unsigned long ret, flags; + + local_irq_save(flags); + __raw_spin_lock(&lockdep_lock); + ret = __lockdep_count_backward_deps(class, 0); + __raw_spin_unlock(&lockdep_lock); + local_irq_restore(flags); + + return ret; +} + /* * Prove that the dependency graph starting at can not * lead to . Print an error and return 0 if it does. @@ -576,16 +1058,19 @@ check_noncircular(struct lock_class *source, unsigned int depth) { struct lock_list *entry; + if (lockdep_dependency_visit(source, depth)) + return 1; + debug_atomic_inc(&nr_cyclic_check_recursions); if (depth > max_recursion_depth) max_recursion_depth = depth; - if (depth >= 20) + if (depth >= RECURSION_LIMIT) return print_infinite_recursion_bug(); /* * Check this lock's dependency list: */ list_for_each_entry(entry, &source->locks_after, entry) { - if (entry->class == check_target->class) + if (entry->class == hlock_class(check_target)) return print_circular_bug_header(entry, depth+1); debug_atomic_inc(&nr_cyclic_checks); if (!check_noncircular(entry->class, depth+1)) @@ -594,15 +1079,7 @@ check_noncircular(struct lock_class *source, unsigned int depth) return 1; } -static int very_verbose(struct lock_class *class) -{ -#if VERY_VERBOSE - return class_filter(class); -#endif - return 0; -} -#ifdef CONFIG_TRACE_IRQFLAGS - +#if defined(CONFIG_TRACE_IRQFLAGS) && defined(CONFIG_PROVE_LOCKING) /* * Forwards and backwards subgraph searching, for the purposes of * proving that two subgraphs can be connected by a new dependency @@ -627,9 +1104,12 @@ find_usage_forwards(struct lock_class *source, unsigned int depth) struct lock_list *entry; int ret; + if (lockdep_dependency_visit(source, depth)) + return 1; + if (depth > max_recursion_depth) max_recursion_depth = depth; - if (depth >= 20) + if (depth >= RECURSION_LIMIT) return print_infinite_recursion_bug(); debug_atomic_inc(&nr_find_usage_forwards_checks); @@ -666,9 +1146,15 @@ find_usage_backwards(struct lock_class *source, unsigned int depth) struct lock_list *entry; int ret; + if (lockdep_dependency_visit(source, depth)) + return 1; + + if (!__raw_spin_is_locked(&lockdep_lock)) + return DEBUG_LOCKS_WARN_ON(1); + if (depth > max_recursion_depth) max_recursion_depth = depth; - if (depth >= 20) + if (depth >= RECURSION_LIMIT) return print_infinite_recursion_bug(); debug_atomic_inc(&nr_find_usage_backwards_checks); @@ -677,6 +1163,11 @@ find_usage_backwards(struct lock_class *source, unsigned int depth) return 2; } + if (!source && debug_locks_off_graph_unlock()) { + WARN_ON(1); + return 0; + } + /* * Check this lock's dependency list: */ @@ -697,17 +1188,16 @@ print_bad_irq_dependency(struct task_struct *curr, enum lock_usage_bit bit2, const char *irqclass) { - __raw_spin_unlock(&hash_lock); - debug_locks_off(); - if (debug_locks_silent) + if (!debug_locks_off_graph_unlock() || debug_locks_silent) return 0; printk("\n======================================================\n"); printk( "[ INFO: %s-safe -> %s-unsafe lock order detected ]\n", irqclass, irqclass); + print_kernel_version(); printk( "------------------------------------------------------\n"); printk("%s/%d [HC%u[%lu]:SC%u[%lu]:HE%u:SE%u] is trying to acquire:\n", - curr->comm, curr->pid, + curr->comm, task_pid_nr(curr), curr->hardirq_context, hardirq_count() >> HARDIRQ_SHIFT, curr->softirq_context, softirq_count() >> SOFTIRQ_SHIFT, curr->hardirqs_enabled, @@ -717,9 +1207,9 @@ print_bad_irq_dependency(struct task_struct *curr, printk("\nand this task is already holding:\n"); print_lock(prev); printk("which would create a new lock dependency:\n"); - print_lock_name(prev->class); + print_lock_name(hlock_class(prev)); printk(" ->"); - print_lock_name(next->class); + print_lock_name(hlock_class(next)); printk("\n"); printk("\nbut this new dependency connects a %s-irq-safe lock:\n", @@ -760,12 +1250,12 @@ check_usage(struct task_struct *curr, struct held_lock *prev, find_usage_bit = bit_backwards; /* fills in */ - ret = find_usage_backwards(prev->class, 0); + ret = find_usage_backwards(hlock_class(prev), 0); if (!ret || ret == 1) return ret; find_usage_bit = bit_forwards; - ret = find_usage_forwards(next->class, 0); + ret = find_usage_forwards(hlock_class(next), 0); if (!ret || ret == 1) return ret; /* ret == 2 */ @@ -773,22 +1263,93 @@ check_usage(struct task_struct *curr, struct held_lock *prev, bit_backwards, bit_forwards, irqclass); } +static int +check_prev_add_irq(struct task_struct *curr, struct held_lock *prev, + struct held_lock *next) +{ + /* + * Prove that the new dependency does not connect a hardirq-safe + * lock with a hardirq-unsafe lock - to achieve this we search + * the backwards-subgraph starting at , and the + * forwards-subgraph starting at : + */ + if (!check_usage(curr, prev, next, LOCK_USED_IN_HARDIRQ, + LOCK_ENABLED_HARDIRQS, "hard")) + return 0; + + /* + * Prove that the new dependency does not connect a hardirq-safe-read + * lock with a hardirq-unsafe lock - to achieve this we search + * the backwards-subgraph starting at , and the + * forwards-subgraph starting at : + */ + if (!check_usage(curr, prev, next, LOCK_USED_IN_HARDIRQ_READ, + LOCK_ENABLED_HARDIRQS, "hard-read")) + return 0; + + /* + * Prove that the new dependency does not connect a softirq-safe + * lock with a softirq-unsafe lock - to achieve this we search + * the backwards-subgraph starting at , and the + * forwards-subgraph starting at : + */ + if (!check_usage(curr, prev, next, LOCK_USED_IN_SOFTIRQ, + LOCK_ENABLED_SOFTIRQS, "soft")) + return 0; + /* + * Prove that the new dependency does not connect a softirq-safe-read + * lock with a softirq-unsafe lock - to achieve this we search + * the backwards-subgraph starting at , and the + * forwards-subgraph starting at : + */ + if (!check_usage(curr, prev, next, LOCK_USED_IN_SOFTIRQ_READ, + LOCK_ENABLED_SOFTIRQS, "soft")) + return 0; + + return 1; +} + +static void inc_chains(void) +{ + if (current->hardirq_context) + nr_hardirq_chains++; + else { + if (current->softirq_context) + nr_softirq_chains++; + else + nr_process_chains++; + } +} + +#else + +static inline int +check_prev_add_irq(struct task_struct *curr, struct held_lock *prev, + struct held_lock *next) +{ + return 1; +} + +static inline void inc_chains(void) +{ + nr_process_chains++; +} + #endif static int print_deadlock_bug(struct task_struct *curr, struct held_lock *prev, struct held_lock *next) { - debug_locks_off(); - __raw_spin_unlock(&hash_lock); - if (debug_locks_silent) + if (!debug_locks_off_graph_unlock() || debug_locks_silent) return 0; printk("\n=============================================\n"); printk( "[ INFO: possible recursive locking detected ]\n"); + print_kernel_version(); printk( "---------------------------------------------\n"); printk("%s/%d is trying to acquire lock:\n", - curr->comm, curr->pid); + curr->comm, task_pid_nr(curr)); print_lock(next); printk("\nbut task is already holding lock:\n"); print_lock(prev); @@ -815,18 +1376,32 @@ check_deadlock(struct task_struct *curr, struct held_lock *next, struct lockdep_map *next_instance, int read) { struct held_lock *prev; + struct held_lock *nest = NULL; int i; for (i = 0; i < curr->lockdep_depth; i++) { prev = curr->held_locks + i; - if (prev->class != next->class) + + if (prev->instance == next->nest_lock) + nest = prev; + + if (hlock_class(prev) != hlock_class(next)) continue; + /* * Allow read-after-read recursion of the same * lock class (i.e. read_lock(lock)+read_lock(lock)): */ if ((read == 2) && prev->read) return 2; + + /* + * We're holding the nest_lock, which serializes this lock's + * nesting behaviour. + */ + if (nest) + return 2; + return print_deadlock_bug(curr, prev, next); } return 1; @@ -852,69 +1427,32 @@ check_deadlock(struct task_struct *curr, struct held_lock *next, * any of these scenarios could lead to a deadlock. * * Then if all the validations pass, we add the forwards and backwards - * dependency. - */ -static int -check_prev_add(struct task_struct *curr, struct held_lock *prev, - struct held_lock *next) -{ - struct lock_list *entry; - int ret; - - /* - * Prove that the new -> dependency would not - * create a circular dependency in the graph. (We do this by - * forward-recursing into the graph starting at , and - * checking whether we can reach .) - * - * We are using global variables to control the recursion, to - * keep the stackframe size of the recursive functions low: - */ - check_source = next; - check_target = prev; - if (!(check_noncircular(next->class, 0))) - return print_circular_bug_tail(); - -#ifdef CONFIG_TRACE_IRQFLAGS - /* - * Prove that the new dependency does not connect a hardirq-safe - * lock with a hardirq-unsafe lock - to achieve this we search - * the backwards-subgraph starting at , and the - * forwards-subgraph starting at : - */ - if (!check_usage(curr, prev, next, LOCK_USED_IN_HARDIRQ, - LOCK_ENABLED_HARDIRQS, "hard")) - return 0; - - /* - * Prove that the new dependency does not connect a hardirq-safe-read - * lock with a hardirq-unsafe lock - to achieve this we search - * the backwards-subgraph starting at , and the - * forwards-subgraph starting at : - */ - if (!check_usage(curr, prev, next, LOCK_USED_IN_HARDIRQ_READ, - LOCK_ENABLED_HARDIRQS, "hard-read")) - return 0; + * dependency. + */ +static int +check_prev_add(struct task_struct *curr, struct held_lock *prev, + struct held_lock *next, int distance) +{ + struct lock_list *entry; + int ret; /* - * Prove that the new dependency does not connect a softirq-safe - * lock with a softirq-unsafe lock - to achieve this we search - * the backwards-subgraph starting at , and the - * forwards-subgraph starting at : - */ - if (!check_usage(curr, prev, next, LOCK_USED_IN_SOFTIRQ, - LOCK_ENABLED_SOFTIRQS, "soft")) - return 0; - /* - * Prove that the new dependency does not connect a softirq-safe-read - * lock with a softirq-unsafe lock - to achieve this we search - * the backwards-subgraph starting at , and the - * forwards-subgraph starting at : + * Prove that the new -> dependency would not + * create a circular dependency in the graph. (We do this by + * forward-recursing into the graph starting at , and + * checking whether we can reach .) + * + * We are using global variables to control the recursion, to + * keep the stackframe size of the recursive functions low: */ - if (!check_usage(curr, prev, next, LOCK_USED_IN_SOFTIRQ_READ, - LOCK_ENABLED_SOFTIRQS, "soft")) + check_source = next; + check_target = prev; + if (!(check_noncircular(hlock_class(next), 0))) + return print_circular_bug_tail(); + + if (!check_prev_add_irq(curr, prev, next)) return 0; -#endif + /* * For recursive read-locks we do all the dependency checks, * but we dont store read-triggered dependencies (only @@ -933,40 +1471,43 @@ check_prev_add(struct task_struct *curr, struct held_lock *prev, * chains - the second one will be new, but L1 already has * L2 added to its dependency list, due to the first chain.) */ - list_for_each_entry(entry, &prev->class->locks_after, entry) { - if (entry->class == next->class) + list_for_each_entry(entry, &hlock_class(prev)->locks_after, entry) { + if (entry->class == hlock_class(next)) { + if (distance == 1) + entry->distance = 1; return 2; + } } /* * Ok, all validations passed, add the new lock * to the previous lock's dependency list: */ - ret = add_lock_to_list(prev->class, next->class, - &prev->class->locks_after, next->acquire_ip); + ret = add_lock_to_list(hlock_class(prev), hlock_class(next), + &hlock_class(prev)->locks_after, + next->acquire_ip, distance); + + if (!ret) + return 0; + + ret = add_lock_to_list(hlock_class(next), hlock_class(prev), + &hlock_class(next)->locks_before, + next->acquire_ip, distance); if (!ret) return 0; - /* - * Return value of 2 signals 'dependency already added', - * in that case we dont have to add the backlink either. - */ - if (ret == 2) - return 2; - ret = add_lock_to_list(next->class, prev->class, - &next->class->locks_before, next->acquire_ip); /* * Debugging printouts: */ - if (verbose(prev->class) || verbose(next->class)) { - __raw_spin_unlock(&hash_lock); + if (verbose(hlock_class(prev)) || verbose(hlock_class(next))) { + graph_unlock(); printk("\n new dependency: "); - print_lock_name(prev->class); + print_lock_name(hlock_class(prev)); printk(" => "); - print_lock_name(next->class); + print_lock_name(hlock_class(next)); printk("\n"); dump_stack(); - __raw_spin_lock(&hash_lock); + return graph_lock(); } return 1; } @@ -995,261 +1536,79 @@ check_prevs_add(struct task_struct *curr, struct held_lock *next) * to be a head: */ if (curr->held_locks[depth].irq_context != - curr->held_locks[depth-1].irq_context) - goto out_bug; - - for (;;) { - hlock = curr->held_locks + depth-1; - /* - * Only non-recursive-read entries get new dependencies - * added: - */ - if (hlock->read != 2) { - check_prev_add(curr, hlock, next); - /* - * Stop after the first non-trylock entry, - * as non-trylock entries have added their - * own direct dependencies already, so this - * lock is connected to them indirectly: - */ - if (!hlock->trylock) - break; - } - depth--; - /* - * End of lock-stack? - */ - if (!depth) - break; - /* - * Stop the search if we cross into another context: - */ - if (curr->held_locks[depth].irq_context != - curr->held_locks[depth-1].irq_context) - break; - } - return 1; -out_bug: - __raw_spin_unlock(&hash_lock); - DEBUG_LOCKS_WARN_ON(1); - - return 0; -} - - -/* - * Is this the address of a static object: - */ -static int static_obj(void *obj) -{ - unsigned long start = (unsigned long) &_stext, - end = (unsigned long) &_end, - addr = (unsigned long) obj; -#ifdef CONFIG_SMP - int i; -#endif - - /* - * static variable? - */ - if ((addr >= start) && (addr < end)) - return 1; - -#ifdef CONFIG_SMP - /* - * percpu var? - */ - for_each_possible_cpu(i) { - start = (unsigned long) &__per_cpu_start + per_cpu_offset(i); - end = (unsigned long) &__per_cpu_end + per_cpu_offset(i); - - if ((addr >= start) && (addr < end)) - return 1; - } -#endif - - /* - * module var? - */ - return is_module_address(addr); -} - -/* - * To make lock name printouts unique, we calculate a unique - * class->name_version generation counter: - */ -static int count_matching_names(struct lock_class *new_class) -{ - struct lock_class *class; - int count = 0; - - if (!new_class->name) - return 0; - - list_for_each_entry(class, &all_lock_classes, lock_entry) { - if (new_class->key - new_class->subclass == class->key) - return class->name_version; - if (class->name && !strcmp(class->name, new_class->name)) - count = max(count, class->name_version); - } - - return count + 1; -} - -extern void __error_too_big_MAX_LOCKDEP_SUBCLASSES(void); - -/* - * Register a lock's class in the hash-table, if the class is not present - * yet. Otherwise we look it up. We cache the result in the lock object - * itself, so actual lookup of the hash should be once per lock object. - */ -static inline struct lock_class * -look_up_lock_class(struct lockdep_map *lock, unsigned int subclass) -{ - struct lockdep_subclass_key *key; - struct list_head *hash_head; - struct lock_class *class; - -#ifdef CONFIG_DEBUG_LOCKDEP - /* - * If the architecture calls into lockdep before initializing - * the hashes then we'll warn about it later. (we cannot printk - * right now) - */ - if (unlikely(!lockdep_initialized)) { - lockdep_init(); - lockdep_init_error = 1; - } -#endif - - /* - * Static locks do not have their class-keys yet - for them the key - * is the lock object itself: - */ - if (unlikely(!lock->key)) - lock->key = (void *)lock; - - /* - * NOTE: the class-key must be unique. For dynamic locks, a static - * lock_class_key variable is passed in through the mutex_init() - * (or spin_lock_init()) call - which acts as the key. For static - * locks we use the lock object itself as the key. - */ - if (sizeof(struct lock_class_key) > sizeof(struct lock_class)) - __error_too_big_MAX_LOCKDEP_SUBCLASSES(); - - key = lock->key->subkeys + subclass; - - hash_head = classhashentry(key); - - /* - * We can walk the hash lockfree, because the hash only - * grows, and we are careful when adding entries to the end: - */ - list_for_each_entry(class, hash_head, hash_entry) - if (class->key == key) - return class; - - return NULL; -} - -/* - * Register a lock's class in the hash-table, if the class is not present - * yet. Otherwise we look it up. We cache the result in the lock object - * itself, so actual lookup of the hash should be once per lock object. - */ -static inline struct lock_class * -register_lock_class(struct lockdep_map *lock, unsigned int subclass) -{ - struct lockdep_subclass_key *key; - struct list_head *hash_head; - struct lock_class *class; - - class = look_up_lock_class(lock, subclass); - if (likely(class)) - return class; - - /* - * Debug-check: all keys must be persistent! - */ - if (!static_obj(lock->key)) { - debug_locks_off(); - printk("INFO: trying to register non-static key.\n"); - printk("the code is fine but needs lockdep annotation.\n"); - printk("turning off the locking correctness validator.\n"); - dump_stack(); - - return NULL; - } - - key = lock->key->subkeys + subclass; - hash_head = classhashentry(key); - - __raw_spin_lock(&hash_lock); - /* - * We have to do the hash-walk again, to avoid races - * with another CPU: - */ - list_for_each_entry(class, hash_head, hash_entry) - if (class->key == key) - goto out_unlock_set; - /* - * Allocate a new key from the static array, and add it to - * the hash: - */ - if (nr_lock_classes >= MAX_LOCKDEP_KEYS) { - __raw_spin_unlock(&hash_lock); - debug_locks_off(); - printk("BUG: MAX_LOCKDEP_KEYS too low!\n"); - printk("turning off the locking correctness validator.\n"); - return NULL; - } - class = lock_classes + nr_lock_classes++; - debug_atomic_inc(&nr_unused_locks); - class->key = key; - class->name = lock->name; - class->subclass = subclass; - INIT_LIST_HEAD(&class->lock_entry); - INIT_LIST_HEAD(&class->locks_before); - INIT_LIST_HEAD(&class->locks_after); - class->name_version = count_matching_names(class); - /* - * We use RCU's safe list-add method to make - * parallel walking of the hash-list safe: - */ - list_add_tail_rcu(&class->hash_entry, hash_head); + curr->held_locks[depth-1].irq_context) + goto out_bug; - if (verbose(class)) { - __raw_spin_unlock(&hash_lock); - printk("\nnew class %p: %s", class->key, class->name); - if (class->name_version > 1) - printk("#%d", class->name_version); - printk("\n"); - dump_stack(); - __raw_spin_lock(&hash_lock); + for (;;) { + int distance = curr->lockdep_depth - depth + 1; + hlock = curr->held_locks + depth-1; + /* + * Only non-recursive-read entries get new dependencies + * added: + */ + if (hlock->read != 2) { + if (!check_prev_add(curr, hlock, next, distance)) + return 0; + /* + * Stop after the first non-trylock entry, + * as non-trylock entries have added their + * own direct dependencies already, so this + * lock is connected to them indirectly: + */ + if (!hlock->trylock) + break; + } + depth--; + /* + * End of lock-stack? + */ + if (!depth) + break; + /* + * Stop the search if we cross into another context: + */ + if (curr->held_locks[depth].irq_context != + curr->held_locks[depth-1].irq_context) + break; } -out_unlock_set: - __raw_spin_unlock(&hash_lock); + return 1; +out_bug: + if (!debug_locks_off_graph_unlock()) + return 0; - if (!subclass) - lock->class_cache = class; + WARN_ON(1); + + return 0; +} - DEBUG_LOCKS_WARN_ON(class->subclass != subclass); +unsigned long nr_lock_chains; +struct lock_chain lock_chains[MAX_LOCKDEP_CHAINS]; +int nr_chain_hlocks; +static u16 chain_hlocks[MAX_LOCKDEP_CHAIN_HLOCKS]; - return class; +struct lock_class *lock_chain_get_class(struct lock_chain *chain, int i) +{ + return lock_classes + chain_hlocks[chain->base + i]; } /* * Look up a dependency chain. If the key is not present yet then - * add it and return 0 - in this case the new dependency chain is - * validated. If the key is already hashed, return 1. + * add it and return 1 - in this case the new dependency chain is + * validated. If the key is already hashed, return 0. + * (On return with 1 graph_lock is held.) */ -static inline int lookup_chain_cache(u64 chain_key) +static inline int lookup_chain_cache(struct task_struct *curr, + struct held_lock *hlock, + u64 chain_key) { + struct lock_class *class = hlock_class(hlock); struct list_head *hash_head = chainhashentry(chain_key); struct lock_chain *chain; + struct held_lock *hlock_curr, *hlock_next; + int i, j, n, cn; - DEBUG_LOCKS_WARN_ON(!irqs_disabled()); + if (DEBUG_LOCKS_WARN_ON(!irqs_disabled())) + return 0; /* * We can walk it lock-free, because entries only get added * to the hash: @@ -1258,57 +1617,136 @@ static inline int lookup_chain_cache(u64 chain_key) if (chain->chain_key == chain_key) { cache_hit: debug_atomic_inc(&chain_lookup_hits); - /* - * In the debugging case, force redundant checking - * by returning 1: - */ -#ifdef CONFIG_DEBUG_LOCKDEP - __raw_spin_lock(&hash_lock); - return 1; -#endif + if (very_verbose(class)) + printk("\nhash chain already cached, key: " + "%016Lx tail class: [%p] %s\n", + (unsigned long long)chain_key, + class->key, class->name); return 0; } } + if (very_verbose(class)) + printk("\nnew hash chain, key: %016Lx tail class: [%p] %s\n", + (unsigned long long)chain_key, class->key, class->name); /* * Allocate a new chain entry from the static array, and add * it to the hash: */ - __raw_spin_lock(&hash_lock); + if (!graph_lock()) + return 0; /* * We have to walk the chain again locked - to avoid duplicates: */ list_for_each_entry(chain, hash_head, entry) { if (chain->chain_key == chain_key) { - __raw_spin_unlock(&hash_lock); + graph_unlock(); goto cache_hit; } } if (unlikely(nr_lock_chains >= MAX_LOCKDEP_CHAINS)) { - __raw_spin_unlock(&hash_lock); - debug_locks_off(); + if (!debug_locks_off_graph_unlock()) + return 0; + printk("BUG: MAX_LOCKDEP_CHAINS too low!\n"); printk("turning off the locking correctness validator.\n"); return 0; } chain = lock_chains + nr_lock_chains++; chain->chain_key = chain_key; + chain->irq_context = hlock->irq_context; + /* Find the first held_lock of current chain */ + hlock_next = hlock; + for (i = curr->lockdep_depth - 1; i >= 0; i--) { + hlock_curr = curr->held_locks + i; + if (hlock_curr->irq_context != hlock_next->irq_context) + break; + hlock_next = hlock; + } + i++; + chain->depth = curr->lockdep_depth + 1 - i; + cn = nr_chain_hlocks; + while (cn + chain->depth <= MAX_LOCKDEP_CHAIN_HLOCKS) { + n = cmpxchg(&nr_chain_hlocks, cn, cn + chain->depth); + if (n == cn) + break; + cn = n; + } + if (likely(cn + chain->depth <= MAX_LOCKDEP_CHAIN_HLOCKS)) { + chain->base = cn; + for (j = 0; j < chain->depth - 1; j++, i++) { + int lock_id = curr->held_locks[i].class_idx - 1; + chain_hlocks[chain->base + j] = lock_id; + } + chain_hlocks[chain->base + j] = class - lock_classes; + } list_add_tail_rcu(&chain->entry, hash_head); debug_atomic_inc(&chain_lookup_misses); -#ifdef CONFIG_TRACE_IRQFLAGS - if (current->hardirq_context) - nr_hardirq_chains++; - else { - if (current->softirq_context) - nr_softirq_chains++; - else - nr_process_chains++; - } -#else - nr_process_chains++; -#endif + inc_chains(); + + return 1; +} + +static int validate_chain(struct task_struct *curr, struct lockdep_map *lock, + struct held_lock *hlock, int chain_head, u64 chain_key) +{ + /* + * Trylock needs to maintain the stack of held locks, but it + * does not add new dependencies, because trylock can be done + * in any order. + * + * We look up the chain_key and do the O(N^2) check and update of + * the dependencies only if this is a new dependency chain. + * (If lookup_chain_cache() returns with 1 it acquires + * graph_lock for us) + */ + if (!hlock->trylock && (hlock->check == 2) && + lookup_chain_cache(curr, hlock, chain_key)) { + /* + * Check whether last held lock: + * + * - is irq-safe, if this lock is irq-unsafe + * - is softirq-safe, if this lock is hardirq-unsafe + * + * And check whether the new lock's dependency graph + * could lead back to the previous lock. + * + * any of these scenarios could lead to a deadlock. If + * All validations + */ + int ret = check_deadlock(curr, hlock, lock, hlock->read); + + if (!ret) + return 0; + /* + * Mark recursive read, as we jump over it when + * building dependencies (just like we jump over + * trylock entries): + */ + if (ret == 2) + hlock->read = 2; + /* + * Add dependency only if this lock is not the head + * of the chain, and if it's not a secondary read-lock: + */ + if (!chain_head && ret != 2) + if (!check_prevs_add(curr, hlock)) + return 0; + graph_unlock(); + } else + /* after lookup_chain_cache(): */ + if (unlikely(!debug_locks)) + return 0; return 1; } +#else +static inline int validate_chain(struct task_struct *curr, + struct lockdep_map *lock, struct held_lock *hlock, + int chain_head, u64 chain_key) +{ + return 1; +} +#endif /* * We are building curr_chain_key incrementally, so double-check @@ -1325,15 +1763,16 @@ static void check_chain_key(struct task_struct *curr) hlock = curr->held_locks + i; if (chain_key != hlock->prev_chain_key) { debug_locks_off(); - printk("hm#1, depth: %u [%u], %016Lx != %016Lx\n", + WARN(1, "hm#1, depth: %u [%u], %016Lx != %016Lx\n", curr->lockdep_depth, i, (unsigned long long)chain_key, (unsigned long long)hlock->prev_chain_key); - WARN_ON(1); return; } - id = hlock->class - lock_classes; - DEBUG_LOCKS_WARN_ON(id >= MAX_LOCKDEP_KEYS); + id = hlock->class_idx - 1; + if (DEBUG_LOCKS_WARN_ON(id >= MAX_LOCKDEP_KEYS)) + return; + if (prev_hlock && (prev_hlock->irq_context != hlock->irq_context)) chain_key = 0; @@ -1342,16 +1781,66 @@ static void check_chain_key(struct task_struct *curr) } if (chain_key != curr->curr_chain_key) { debug_locks_off(); - printk("hm#2, depth: %u [%u], %016Lx != %016Lx\n", + WARN(1, "hm#2, depth: %u [%u], %016Lx != %016Lx\n", curr->lockdep_depth, i, (unsigned long long)chain_key, (unsigned long long)curr->curr_chain_key); - WARN_ON(1); } #endif } -#ifdef CONFIG_TRACE_IRQFLAGS +static int +print_usage_bug(struct task_struct *curr, struct held_lock *this, + enum lock_usage_bit prev_bit, enum lock_usage_bit new_bit) +{ + if (!debug_locks_off_graph_unlock() || debug_locks_silent) + return 0; + + printk("\n=================================\n"); + printk( "[ INFO: inconsistent lock state ]\n"); + print_kernel_version(); + printk( "---------------------------------\n"); + + printk("inconsistent {%s} -> {%s} usage.\n", + usage_str[prev_bit], usage_str[new_bit]); + + printk("%s/%d [HC%u[%lu]:SC%u[%lu]:HE%u:SE%u] takes:\n", + curr->comm, task_pid_nr(curr), + trace_hardirq_context(curr), hardirq_count() >> HARDIRQ_SHIFT, + trace_softirq_context(curr), softirq_count() >> SOFTIRQ_SHIFT, + trace_hardirqs_enabled(curr), + trace_softirqs_enabled(curr)); + print_lock(this); + + printk("{%s} state was registered at:\n", usage_str[prev_bit]); + print_stack_trace(hlock_class(this)->usage_traces + prev_bit, 1); + + print_irqtrace_events(curr); + printk("\nother info that might help us debug this:\n"); + lockdep_print_held_locks(curr); + + printk("\nstack backtrace:\n"); + dump_stack(); + + return 0; +} + +/* + * Print out an error if an invalid bit is set: + */ +static inline int +valid_state(struct task_struct *curr, struct held_lock *this, + enum lock_usage_bit new_bit, enum lock_usage_bit bad_bit) +{ + if (unlikely(hlock_class(this)->usage_mask & (1 << bad_bit))) + return print_usage_bug(curr, this, bad_bit, new_bit); + return 1; +} + +static int mark_lock(struct task_struct *curr, struct held_lock *this, + enum lock_usage_bit new_bit); + +#if defined(CONFIG_TRACE_IRQFLAGS) && defined(CONFIG_PROVE_LOCKING) /* * print irq inversion bug: @@ -1361,16 +1850,15 @@ print_irq_inversion_bug(struct task_struct *curr, struct lock_class *other, struct held_lock *this, int forwards, const char *irqclass) { - __raw_spin_unlock(&hash_lock); - debug_locks_off(); - if (debug_locks_silent) + if (!debug_locks_off_graph_unlock() || debug_locks_silent) return 0; printk("\n=========================================================\n"); printk( "[ INFO: possible irq lock inversion dependency detected ]\n"); + print_kernel_version(); printk( "---------------------------------------------------------\n"); printk("%s/%d just changed the state of lock:\n", - curr->comm, curr->pid); + curr->comm, task_pid_nr(curr)); print_lock(this); if (forwards) printk("but this lock took another, %s-irq-unsafe lock in the past:\n", irqclass); @@ -1383,7 +1871,7 @@ print_irq_inversion_bug(struct task_struct *curr, struct lock_class *other, lockdep_print_held_locks(curr); printk("\nthe first lock's dependencies:\n"); - print_lock_dependencies(this->class, 0); + print_lock_dependencies(hlock_class(this), 0); printk("\nthe second lock's dependencies:\n"); print_lock_dependencies(other, 0); @@ -1406,7 +1894,7 @@ check_usage_forwards(struct task_struct *curr, struct held_lock *this, find_usage_bit = bit; /* fills in */ - ret = find_usage_forwards(this->class, 0); + ret = find_usage_forwards(hlock_class(this), 0); if (!ret || ret == 1) return ret; @@ -1425,14 +1913,14 @@ check_usage_backwards(struct task_struct *curr, struct held_lock *this, find_usage_bit = bit; /* fills in */ - ret = find_usage_backwards(this->class, 0); + ret = find_usage_backwards(hlock_class(this), 0); if (!ret || ret == 1) return ret; return print_irq_inversion_bug(curr, backwards_match, this, 0, irqclass); } -static inline void print_irqtrace_events(struct task_struct *curr) +void print_irqtrace_events(struct task_struct *curr) { printk("irq event stamp: %u\n", curr->irq_events); printk("hardirqs last enabled at (%u): ", curr->hardirq_enable_event); @@ -1445,102 +1933,30 @@ static inline void print_irqtrace_events(struct task_struct *curr) print_ip_sym(curr->softirq_disable_ip); } -#else -static inline void print_irqtrace_events(struct task_struct *curr) +static int hardirq_verbose(struct lock_class *class) { -} +#if HARDIRQ_VERBOSE + return class_filter(class); #endif - -static int -print_usage_bug(struct task_struct *curr, struct held_lock *this, - enum lock_usage_bit prev_bit, enum lock_usage_bit new_bit) -{ - __raw_spin_unlock(&hash_lock); - debug_locks_off(); - if (debug_locks_silent) - return 0; - - printk("\n=================================\n"); - printk( "[ INFO: inconsistent lock state ]\n"); - printk( "---------------------------------\n"); - - printk("inconsistent {%s} -> {%s} usage.\n", - usage_str[prev_bit], usage_str[new_bit]); - - printk("%s/%d [HC%u[%lu]:SC%u[%lu]:HE%u:SE%u] takes:\n", - curr->comm, curr->pid, - trace_hardirq_context(curr), hardirq_count() >> HARDIRQ_SHIFT, - trace_softirq_context(curr), softirq_count() >> SOFTIRQ_SHIFT, - trace_hardirqs_enabled(curr), - trace_softirqs_enabled(curr)); - print_lock(this); - - printk("{%s} state was registered at:\n", usage_str[prev_bit]); - print_stack_trace(this->class->usage_traces + prev_bit, 1); - - print_irqtrace_events(curr); - printk("\nother info that might help us debug this:\n"); - lockdep_print_held_locks(curr); - - printk("\nstack backtrace:\n"); - dump_stack(); - return 0; } -/* - * Print out an error if an invalid bit is set: - */ -static inline int -valid_state(struct task_struct *curr, struct held_lock *this, - enum lock_usage_bit new_bit, enum lock_usage_bit bad_bit) +static int softirq_verbose(struct lock_class *class) { - if (unlikely(this->class->usage_mask & (1 << bad_bit))) - return print_usage_bug(curr, this, bad_bit, new_bit); - return 1; +#if SOFTIRQ_VERBOSE + return class_filter(class); +#endif + return 0; } #define STRICT_READ_CHECKS 1 -/* - * Mark a lock with a usage bit, and validate the state transition: - */ -static int mark_lock(struct task_struct *curr, struct held_lock *this, - enum lock_usage_bit new_bit, unsigned long ip) +static int mark_lock_irq(struct task_struct *curr, struct held_lock *this, + enum lock_usage_bit new_bit) { - unsigned int new_mask = 1 << new_bit, ret = 1; - - /* - * If already set then do not dirty the cacheline, - * nor do any checks: - */ - if (likely(this->class->usage_mask & new_mask)) - return 1; - - __raw_spin_lock(&hash_lock); - /* - * Make sure we didnt race: - */ - if (unlikely(this->class->usage_mask & new_mask)) { - __raw_spin_unlock(&hash_lock); - return 1; - } - - this->class->usage_mask |= new_mask; - -#ifdef CONFIG_TRACE_IRQFLAGS - if (new_bit == LOCK_ENABLED_HARDIRQS || - new_bit == LOCK_ENABLED_HARDIRQS_READ) - ip = curr->hardirq_enable_ip; - else if (new_bit == LOCK_ENABLED_SOFTIRQS || - new_bit == LOCK_ENABLED_SOFTIRQS_READ) - ip = curr->softirq_enable_ip; -#endif - if (!save_trace(this->class->usage_traces + new_bit)) - return 0; + int ret = 1; - switch (new_bit) { -#ifdef CONFIG_TRACE_IRQFLAGS + switch(new_bit) { case LOCK_USED_IN_HARDIRQ: if (!valid_state(curr, this, new_bit, LOCK_ENABLED_HARDIRQS)) return 0; @@ -1563,7 +1979,7 @@ static int mark_lock(struct task_struct *curr, struct held_lock *this, LOCK_ENABLED_HARDIRQS_READ, "hard-read")) return 0; #endif - if (hardirq_verbose(this->class)) + if (hardirq_verbose(hlock_class(this))) ret = 2; break; case LOCK_USED_IN_SOFTIRQ: @@ -1588,7 +2004,7 @@ static int mark_lock(struct task_struct *curr, struct held_lock *this, LOCK_ENABLED_SOFTIRQS_READ, "soft-read")) return 0; #endif - if (softirq_verbose(this->class)) + if (softirq_verbose(hlock_class(this))) ret = 2; break; case LOCK_USED_IN_HARDIRQ_READ: @@ -1601,7 +2017,7 @@ static int mark_lock(struct task_struct *curr, struct held_lock *this, if (!check_usage_forwards(curr, this, LOCK_ENABLED_HARDIRQS, "hard")) return 0; - if (hardirq_verbose(this->class)) + if (hardirq_verbose(hlock_class(this))) ret = 2; break; case LOCK_USED_IN_SOFTIRQ_READ: @@ -1614,7 +2030,7 @@ static int mark_lock(struct task_struct *curr, struct held_lock *this, if (!check_usage_forwards(curr, this, LOCK_ENABLED_SOFTIRQS, "soft")) return 0; - if (softirq_verbose(this->class)) + if (softirq_verbose(hlock_class(this))) ret = 2; break; case LOCK_ENABLED_HARDIRQS: @@ -1640,7 +2056,7 @@ static int mark_lock(struct task_struct *curr, struct held_lock *this, LOCK_USED_IN_HARDIRQ_READ, "hard-read")) return 0; #endif - if (hardirq_verbose(this->class)) + if (hardirq_verbose(hlock_class(this))) ret = 2; break; case LOCK_ENABLED_SOFTIRQS: @@ -1666,7 +2082,7 @@ static int mark_lock(struct task_struct *curr, struct held_lock *this, LOCK_USED_IN_SOFTIRQ_READ, "soft-read")) return 0; #endif - if (softirq_verbose(this->class)) + if (softirq_verbose(hlock_class(this))) ret = 2; break; case LOCK_ENABLED_HARDIRQS_READ: @@ -1681,7 +2097,7 @@ static int mark_lock(struct task_struct *curr, struct held_lock *this, LOCK_USED_IN_HARDIRQ, "hard")) return 0; #endif - if (hardirq_verbose(this->class)) + if (hardirq_verbose(hlock_class(this))) ret = 2; break; case LOCK_ENABLED_SOFTIRQS_READ: @@ -1694,46 +2110,24 @@ static int mark_lock(struct task_struct *curr, struct held_lock *this, */ if (!check_usage_backwards(curr, this, LOCK_USED_IN_SOFTIRQ, "soft")) - return 0; -#endif - if (softirq_verbose(this->class)) - ret = 2; - break; -#endif - case LOCK_USED: - /* - * Add it to the global list of classes: - */ - list_add_tail_rcu(&this->class->lock_entry, &all_lock_classes); - debug_atomic_dec(&nr_unused_locks); + return 0; +#endif + if (softirq_verbose(hlock_class(this))) + ret = 2; break; default: - debug_locks_off(); WARN_ON(1); - return 0; - } - - __raw_spin_unlock(&hash_lock); - - /* - * We must printk outside of the hash_lock: - */ - if (ret == 2) { - printk("\nmarked lock as {%s}:\n", usage_str[new_bit]); - print_lock(this); - print_irqtrace_events(curr); - dump_stack(); + break; } return ret; } -#ifdef CONFIG_TRACE_IRQFLAGS /* * Mark all held locks with a usage bit: */ static int -mark_held_locks(struct task_struct *curr, int hardirq, unsigned long ip) +mark_held_locks(struct task_struct *curr, int hardirq) { enum lock_usage_bit usage_bit; struct held_lock *hlock; @@ -1753,7 +2147,7 @@ mark_held_locks(struct task_struct *curr, int hardirq, unsigned long ip) else usage_bit = LOCK_ENABLED_SOFTIRQS; } - if (!mark_lock(curr, hlock, usage_bit, ip)) + if (!mark_lock(curr, hlock, usage_bit)) return 0; } @@ -1779,10 +2173,11 @@ void early_boot_irqs_on(void) /* * Hardirqs will be enabled: */ -void trace_hardirqs_on(void) +void trace_hardirqs_on_caller(unsigned long ip) { struct task_struct *curr = current; - unsigned long ip; + + time_hardirqs_on(CALLER_ADDR0, ip); if (unlikely(!debug_locks || current->lockdep_recursion)) return; @@ -1796,7 +2191,6 @@ void trace_hardirqs_on(void) } /* we'll do an OFF -> ON transition: */ curr->hardirqs_enabled = 1; - ip = (unsigned long) __builtin_return_address(0); if (DEBUG_LOCKS_WARN_ON(!irqs_disabled())) return; @@ -1806,7 +2200,7 @@ void trace_hardirqs_on(void) * We are going to turn hardirqs on, so set the * usage bit for all held locks: */ - if (!mark_held_locks(curr, 1, ip)) + if (!mark_held_locks(curr, 1)) return; /* * If we have softirqs enabled, then set the usage @@ -1814,23 +2208,30 @@ void trace_hardirqs_on(void) * this bit from being set before) */ if (curr->softirqs_enabled) - if (!mark_held_locks(curr, 0, ip)) + if (!mark_held_locks(curr, 0)) return; curr->hardirq_enable_ip = ip; curr->hardirq_enable_event = ++curr->irq_events; debug_atomic_inc(&hardirqs_on_events); } +EXPORT_SYMBOL(trace_hardirqs_on_caller); +void trace_hardirqs_on(void) +{ + trace_hardirqs_on_caller(CALLER_ADDR0); +} EXPORT_SYMBOL(trace_hardirqs_on); /* * Hardirqs were disabled: */ -void trace_hardirqs_off(void) +void trace_hardirqs_off_caller(unsigned long ip) { struct task_struct *curr = current; + time_hardirqs_off(CALLER_ADDR0, ip); + if (unlikely(!debug_locks || current->lockdep_recursion)) return; @@ -1842,13 +2243,18 @@ void trace_hardirqs_off(void) * We have done an ON -> OFF transition: */ curr->hardirqs_enabled = 0; - curr->hardirq_disable_ip = _RET_IP_; + curr->hardirq_disable_ip = ip; curr->hardirq_disable_event = ++curr->irq_events; debug_atomic_inc(&hardirqs_off_events); } else debug_atomic_inc(&redundant_hardirqs_off); } +EXPORT_SYMBOL(trace_hardirqs_off_caller); +void trace_hardirqs_off(void) +{ + trace_hardirqs_off_caller(CALLER_ADDR0); +} EXPORT_SYMBOL(trace_hardirqs_off); /* @@ -1882,7 +2288,7 @@ void trace_softirqs_on(unsigned long ip) * enabled too: */ if (curr->hardirqs_enabled) - mark_held_locks(curr, 0, ip); + mark_held_locks(curr, 0); } /* @@ -1911,13 +2317,176 @@ void trace_softirqs_off(unsigned long ip) debug_atomic_inc(&redundant_softirqs_off); } +static int mark_irqflags(struct task_struct *curr, struct held_lock *hlock) +{ + /* + * If non-trylock use in a hardirq or softirq context, then + * mark the lock as used in these contexts: + */ + if (!hlock->trylock) { + if (hlock->read) { + if (curr->hardirq_context) + if (!mark_lock(curr, hlock, + LOCK_USED_IN_HARDIRQ_READ)) + return 0; + if (curr->softirq_context) + if (!mark_lock(curr, hlock, + LOCK_USED_IN_SOFTIRQ_READ)) + return 0; + } else { + if (curr->hardirq_context) + if (!mark_lock(curr, hlock, LOCK_USED_IN_HARDIRQ)) + return 0; + if (curr->softirq_context) + if (!mark_lock(curr, hlock, LOCK_USED_IN_SOFTIRQ)) + return 0; + } + } + if (!hlock->hardirqs_off) { + if (hlock->read) { + if (!mark_lock(curr, hlock, + LOCK_ENABLED_HARDIRQS_READ)) + return 0; + if (curr->softirqs_enabled) + if (!mark_lock(curr, hlock, + LOCK_ENABLED_SOFTIRQS_READ)) + return 0; + } else { + if (!mark_lock(curr, hlock, + LOCK_ENABLED_HARDIRQS)) + return 0; + if (curr->softirqs_enabled) + if (!mark_lock(curr, hlock, + LOCK_ENABLED_SOFTIRQS)) + return 0; + } + } + + return 1; +} + +static int separate_irq_context(struct task_struct *curr, + struct held_lock *hlock) +{ + unsigned int depth = curr->lockdep_depth; + + /* + * Keep track of points where we cross into an interrupt context: + */ + hlock->irq_context = 2*(curr->hardirq_context ? 1 : 0) + + curr->softirq_context; + if (depth) { + struct held_lock *prev_hlock; + + prev_hlock = curr->held_locks + depth-1; + /* + * If we cross into another context, reset the + * hash key (this also prevents the checking and the + * adding of the dependency to 'prev'): + */ + if (prev_hlock->irq_context != hlock->irq_context) + return 1; + } + return 0; +} + +#else + +static inline +int mark_lock_irq(struct task_struct *curr, struct held_lock *this, + enum lock_usage_bit new_bit) +{ + WARN_ON(1); + return 1; +} + +static inline int mark_irqflags(struct task_struct *curr, + struct held_lock *hlock) +{ + return 1; +} + +static inline int separate_irq_context(struct task_struct *curr, + struct held_lock *hlock) +{ + return 0; +} + #endif /* + * Mark a lock with a usage bit, and validate the state transition: + */ +static int mark_lock(struct task_struct *curr, struct held_lock *this, + enum lock_usage_bit new_bit) +{ + unsigned int new_mask = 1 << new_bit, ret = 1; + + /* + * If already set then do not dirty the cacheline, + * nor do any checks: + */ + if (likely(hlock_class(this)->usage_mask & new_mask)) + return 1; + + if (!graph_lock()) + return 0; + /* + * Make sure we didnt race: + */ + if (unlikely(hlock_class(this)->usage_mask & new_mask)) { + graph_unlock(); + return 1; + } + + hlock_class(this)->usage_mask |= new_mask; + + if (!save_trace(hlock_class(this)->usage_traces + new_bit)) + return 0; + + switch (new_bit) { + case LOCK_USED_IN_HARDIRQ: + case LOCK_USED_IN_SOFTIRQ: + case LOCK_USED_IN_HARDIRQ_READ: + case LOCK_USED_IN_SOFTIRQ_READ: + case LOCK_ENABLED_HARDIRQS: + case LOCK_ENABLED_SOFTIRQS: + case LOCK_ENABLED_HARDIRQS_READ: + case LOCK_ENABLED_SOFTIRQS_READ: + ret = mark_lock_irq(curr, this, new_bit); + if (!ret) + return 0; + break; + case LOCK_USED: + debug_atomic_dec(&nr_unused_locks); + break; + default: + if (!debug_locks_off_graph_unlock()) + return 0; + WARN_ON(1); + return 0; + } + + graph_unlock(); + + /* + * We must printk outside of the graph_lock: + */ + if (ret == 2) { + printk("\nmarked lock as {%s}:\n", usage_str[new_bit]); + print_lock(this); + print_irqtrace_events(curr); + dump_stack(); + } + + return ret; +} + +/* * Initialize a lock instance's lock-class mapping info: */ void lockdep_init_map(struct lockdep_map *lock, const char *name, - struct lock_class_key *key) + struct lock_class_key *key, int subclass) { if (unlikely(!debug_locks)) return; @@ -1937,8 +2506,12 @@ void lockdep_init_map(struct lockdep_map *lock, const char *name, lock->name = name; lock->key = key; lock->class_cache = NULL; +#ifdef CONFIG_LOCK_STAT + lock->cpu = raw_smp_processor_id(); +#endif + if (subclass) + register_lock_class(lock, subclass, 1); } - EXPORT_SYMBOL_GPL(lockdep_init_map); /* @@ -1947,7 +2520,7 @@ EXPORT_SYMBOL_GPL(lockdep_init_map); */ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass, int trylock, int read, int check, int hardirqs_off, - unsigned long ip) + struct lockdep_map *nest_lock, unsigned long ip) { struct task_struct *curr = current; struct lock_class *class = NULL; @@ -1956,6 +2529,9 @@ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass, int chain_head = 0; u64 chain_key; + if (!prove_locking) + check = 1; + if (unlikely(!debug_locks)) return 0; @@ -1975,7 +2551,7 @@ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass, * Not cached yet or subclass? */ if (unlikely(!class)) { - class = register_lock_class(lock, subclass); + class = register_lock_class(lock, subclass, 0); if (!class) return 0; } @@ -1998,163 +2574,73 @@ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass, return 0; hlock = curr->held_locks + depth; - - hlock->class = class; + if (DEBUG_LOCKS_WARN_ON(!class)) + return 0; + hlock->class_idx = class - lock_classes + 1; hlock->acquire_ip = ip; hlock->instance = lock; + hlock->nest_lock = nest_lock; hlock->trylock = trylock; hlock->read = read; hlock->check = check; - hlock->hardirqs_off = hardirqs_off; - - if (check != 2) - goto out_calc_hash; -#ifdef CONFIG_TRACE_IRQFLAGS - /* - * If non-trylock use in a hardirq or softirq context, then - * mark the lock as used in these contexts: - */ - if (!trylock) { - if (read) { - if (curr->hardirq_context) - if (!mark_lock(curr, hlock, - LOCK_USED_IN_HARDIRQ_READ, ip)) - return 0; - if (curr->softirq_context) - if (!mark_lock(curr, hlock, - LOCK_USED_IN_SOFTIRQ_READ, ip)) - return 0; - } else { - if (curr->hardirq_context) - if (!mark_lock(curr, hlock, LOCK_USED_IN_HARDIRQ, ip)) - return 0; - if (curr->softirq_context) - if (!mark_lock(curr, hlock, LOCK_USED_IN_SOFTIRQ, ip)) - return 0; - } - } - if (!hardirqs_off) { - if (read) { - if (!mark_lock(curr, hlock, - LOCK_ENABLED_HARDIRQS_READ, ip)) - return 0; - if (curr->softirqs_enabled) - if (!mark_lock(curr, hlock, - LOCK_ENABLED_SOFTIRQS_READ, ip)) - return 0; - } else { - if (!mark_lock(curr, hlock, - LOCK_ENABLED_HARDIRQS, ip)) - return 0; - if (curr->softirqs_enabled) - if (!mark_lock(curr, hlock, - LOCK_ENABLED_SOFTIRQS, ip)) - return 0; - } - } + hlock->hardirqs_off = !!hardirqs_off; +#ifdef CONFIG_LOCK_STAT + hlock->waittime_stamp = 0; + hlock->holdtime_stamp = sched_clock(); #endif - /* mark it as used: */ - if (!mark_lock(curr, hlock, LOCK_USED, ip)) - return 0; -out_calc_hash: - /* - * Calculate the chain hash: it's the combined has of all the - * lock keys along the dependency chain. We save the hash value - * at every step so that we can get the current hash easily - * after unlock. The chain hash is then used to cache dependency - * results. - * - * The 'key ID' is what is the most compact key value to drive - * the hash, not class->key. - */ - id = class - lock_classes; - if (DEBUG_LOCKS_WARN_ON(id >= MAX_LOCKDEP_KEYS)) - return 0; - - chain_key = curr->curr_chain_key; - if (!depth) { - if (DEBUG_LOCKS_WARN_ON(chain_key != 0)) - return 0; - chain_head = 1; - } - - hlock->prev_chain_key = chain_key; -#ifdef CONFIG_TRACE_IRQFLAGS - /* - * Keep track of points where we cross into an interrupt context: - */ - hlock->irq_context = 2*(curr->hardirq_context ? 1 : 0) + - curr->softirq_context; - if (depth) { - struct held_lock *prev_hlock; + if (check == 2 && !mark_irqflags(curr, hlock)) + return 0; - prev_hlock = curr->held_locks + depth-1; - /* - * If we cross into another context, reset the - * hash key (this also prevents the checking and the - * adding of the dependency to 'prev'): - */ - if (prev_hlock->irq_context != hlock->irq_context) { - chain_key = 0; - chain_head = 1; - } - } -#endif - chain_key = iterate_chain_key(chain_key, id); - curr->curr_chain_key = chain_key; + /* mark it as used: */ + if (!mark_lock(curr, hlock, LOCK_USED)) + return 0; - /* - * Trylock needs to maintain the stack of held locks, but it - * does not add new dependencies, because trylock can be done - * in any order. - * - * We look up the chain_key and do the O(N^2) check and update of - * the dependencies only if this is a new dependency chain. - * (If lookup_chain_cache() returns with 1 it acquires - * hash_lock for us) - */ - if (!trylock && (check == 2) && lookup_chain_cache(chain_key)) { - /* - * Check whether last held lock: - * - * - is irq-safe, if this lock is irq-unsafe - * - is softirq-safe, if this lock is hardirq-unsafe - * - * And check whether the new lock's dependency graph - * could lead back to the previous lock. - * - * any of these scenarios could lead to a deadlock. If - * All validations - */ - int ret = check_deadlock(curr, hlock, lock, read); + /* + * Calculate the chain hash: it's the combined hash of all the + * lock keys along the dependency chain. We save the hash value + * at every step so that we can get the current hash easily + * after unlock. The chain hash is then used to cache dependency + * results. + * + * The 'key ID' is what is the most compact key value to drive + * the hash, not class->key. + */ + id = class - lock_classes; + if (DEBUG_LOCKS_WARN_ON(id >= MAX_LOCKDEP_KEYS)) + return 0; - if (!ret) + chain_key = curr->curr_chain_key; + if (!depth) { + if (DEBUG_LOCKS_WARN_ON(chain_key != 0)) return 0; - /* - * Mark recursive read, as we jump over it when - * building dependencies (just like we jump over - * trylock entries): - */ - if (ret == 2) - hlock->read = 2; - /* - * Add dependency only if this lock is not the head - * of the chain, and if it's not a secondary read-lock: - */ - if (!chain_head && ret != 2) - if (!check_prevs_add(curr, hlock)) - return 0; - __raw_spin_unlock(&hash_lock); + chain_head = 1; + } + + hlock->prev_chain_key = chain_key; + if (separate_irq_context(curr, hlock)) { + chain_key = 0; + chain_head = 1; } + chain_key = iterate_chain_key(chain_key, id); + + if (!validate_chain(curr, lock, hlock, chain_head, chain_key)) + return 0; + + curr->curr_chain_key = chain_key; curr->lockdep_depth++; check_chain_key(curr); +#ifdef CONFIG_DEBUG_LOCKDEP + if (unlikely(!debug_locks)) + return 0; +#endif if (unlikely(curr->lockdep_depth >= MAX_LOCK_DEPTH)) { debug_locks_off(); printk("BUG: MAX_LOCK_DEPTH too low!\n"); printk("turning off the locking correctness validator.\n"); return 0; } + if (unlikely(curr->lockdep_depth > max_lockdep_depth)) max_lockdep_depth = curr->lockdep_depth; @@ -2174,7 +2660,7 @@ print_unlock_inbalance_bug(struct task_struct *curr, struct lockdep_map *lock, printk( "[ BUG: bad unlock balance detected! ]\n"); printk( "-------------------------------------\n"); printk("%s/%d is trying to release lock (", - curr->comm, curr->pid); + curr->comm, task_pid_nr(curr)); print_lockdep_cache(lock); printk(") at:\n"); print_ip_sym(ip); @@ -2205,6 +2691,57 @@ static int check_unlock(struct task_struct *curr, struct lockdep_map *lock, return 1; } +static int +__lock_set_class(struct lockdep_map *lock, const char *name, + struct lock_class_key *key, unsigned int subclass, + unsigned long ip) +{ + struct task_struct *curr = current; + struct held_lock *hlock, *prev_hlock; + struct lock_class *class; + unsigned int depth; + int i; + + depth = curr->lockdep_depth; + if (DEBUG_LOCKS_WARN_ON(!depth)) + return 0; + + prev_hlock = NULL; + for (i = depth-1; i >= 0; i--) { + hlock = curr->held_locks + i; + /* + * We must not cross into another context: + */ + if (prev_hlock && prev_hlock->irq_context != hlock->irq_context) + break; + if (hlock->instance == lock) + goto found_it; + prev_hlock = hlock; + } + return print_unlock_inbalance_bug(curr, lock, ip); + +found_it: + lockdep_init_map(lock, name, key, 0); + class = register_lock_class(lock, subclass, 0); + hlock->class_idx = class - lock_classes + 1; + + curr->lockdep_depth = i; + curr->curr_chain_key = hlock->prev_chain_key; + + for (; i < depth; i++) { + hlock = curr->held_locks + i; + if (!__lock_acquire(hlock->instance, + hlock_class(hlock)->subclass, hlock->trylock, + hlock->read, hlock->check, hlock->hardirqs_off, + hlock->nest_lock, hlock->acquire_ip)) + return 0; + } + + if (DEBUG_LOCKS_WARN_ON(curr->lockdep_depth != depth)) + return 0; + return 1; +} + /* * Remove the lock to the list of currently held locks in a * potentially non-nested (out of order) manner. This is a @@ -2242,6 +2779,8 @@ lock_release_non_nested(struct task_struct *curr, return print_unlock_inbalance_bug(curr, lock, ip); found_it: + lock_release_holdtime(hlock); + /* * We have the right lock to unlock, 'hlock' points to it. * Now we remove it from the stack, and add back the other @@ -2253,9 +2792,9 @@ found_it: for (i++; i < depth; i++) { hlock = curr->held_locks + i; if (!__lock_acquire(hlock->instance, - hlock->class->subclass, hlock->trylock, + hlock_class(hlock)->subclass, hlock->trylock, hlock->read, hlock->check, hlock->hardirqs_off, - hlock->acquire_ip)) + hlock->nest_lock, hlock->acquire_ip)) return 0; } @@ -2294,9 +2833,11 @@ static int lock_release_nested(struct task_struct *curr, curr->curr_chain_key = hlock->prev_chain_key; + lock_release_holdtime(hlock); + #ifdef CONFIG_DEBUG_LOCKDEP hlock->prev_chain_key = 0; - hlock->class = NULL; + hlock->class_idx = 0; hlock->acquire_ip = 0; hlock->irq_context = 0; #endif @@ -2333,14 +2874,20 @@ __lock_release(struct lockdep_map *lock, int nested, unsigned long ip) */ static void check_flags(unsigned long flags) { -#if defined(CONFIG_DEBUG_LOCKDEP) && defined(CONFIG_TRACE_IRQFLAGS) +#if defined(CONFIG_PROVE_LOCKING) && defined(CONFIG_DEBUG_LOCKDEP) && \ + defined(CONFIG_TRACE_IRQFLAGS) if (!debug_locks) return; - if (irqs_disabled_flags(flags)) - DEBUG_LOCKS_WARN_ON(current->hardirqs_enabled); - else - DEBUG_LOCKS_WARN_ON(!current->hardirqs_enabled); + if (irqs_disabled_flags(flags)) { + if (DEBUG_LOCKS_WARN_ON(current->hardirqs_enabled)) { + printk("possible reason: unannotated irqs-off.\n"); + } + } else { + if (DEBUG_LOCKS_WARN_ON(!current->hardirqs_enabled)) { + printk("possible reason: unannotated irqs-on.\n"); + } + } /* * We dont accurately track softirq state in e.g. @@ -2359,12 +2906,32 @@ static void check_flags(unsigned long flags) #endif } +void lock_set_class(struct lockdep_map *lock, const char *name, + struct lock_class_key *key, unsigned int subclass, + unsigned long ip) +{ + unsigned long flags; + + if (unlikely(current->lockdep_recursion)) + return; + + raw_local_irq_save(flags); + current->lockdep_recursion = 1; + check_flags(flags); + if (__lock_set_class(lock, name, key, subclass, ip)) + check_chain_key(current); + current->lockdep_recursion = 0; + raw_local_irq_restore(flags); +} +EXPORT_SYMBOL_GPL(lock_set_class); + /* * We are not always called with irqs disabled - do that here, * and also avoid lockdep recursion: */ void lock_acquire(struct lockdep_map *lock, unsigned int subclass, - int trylock, int read, int check, unsigned long ip) + int trylock, int read, int check, + struct lockdep_map *nest_lock, unsigned long ip) { unsigned long flags; @@ -2376,14 +2943,14 @@ void lock_acquire(struct lockdep_map *lock, unsigned int subclass, current->lockdep_recursion = 1; __lock_acquire(lock, subclass, trylock, read, check, - irqs_disabled_flags(flags), ip); + irqs_disabled_flags(flags), nest_lock, ip); current->lockdep_recursion = 0; raw_local_irq_restore(flags); } - EXPORT_SYMBOL_GPL(lock_acquire); -void lock_release(struct lockdep_map *lock, int nested, unsigned long ip) +void lock_release(struct lockdep_map *lock, int nested, + unsigned long ip) { unsigned long flags; @@ -2397,9 +2964,173 @@ void lock_release(struct lockdep_map *lock, int nested, unsigned long ip) current->lockdep_recursion = 0; raw_local_irq_restore(flags); } - EXPORT_SYMBOL_GPL(lock_release); +#ifdef CONFIG_LOCK_STAT +static int +print_lock_contention_bug(struct task_struct *curr, struct lockdep_map *lock, + unsigned long ip) +{ + if (!debug_locks_off()) + return 0; + if (debug_locks_silent) + return 0; + + printk("\n=================================\n"); + printk( "[ BUG: bad contention detected! ]\n"); + printk( "---------------------------------\n"); + printk("%s/%d is trying to contend lock (", + curr->comm, task_pid_nr(curr)); + print_lockdep_cache(lock); + printk(") at:\n"); + print_ip_sym(ip); + printk("but there are no locks held!\n"); + printk("\nother info that might help us debug this:\n"); + lockdep_print_held_locks(curr); + + printk("\nstack backtrace:\n"); + dump_stack(); + + return 0; +} + +static void +__lock_contended(struct lockdep_map *lock, unsigned long ip) +{ + struct task_struct *curr = current; + struct held_lock *hlock, *prev_hlock; + struct lock_class_stats *stats; + unsigned int depth; + int i, contention_point, contending_point; + + depth = curr->lockdep_depth; + if (DEBUG_LOCKS_WARN_ON(!depth)) + return; + + prev_hlock = NULL; + for (i = depth-1; i >= 0; i--) { + hlock = curr->held_locks + i; + /* + * We must not cross into another context: + */ + if (prev_hlock && prev_hlock->irq_context != hlock->irq_context) + break; + if (hlock->instance == lock) + goto found_it; + prev_hlock = hlock; + } + print_lock_contention_bug(curr, lock, ip); + return; + +found_it: + hlock->waittime_stamp = sched_clock(); + + contention_point = lock_point(hlock_class(hlock)->contention_point, ip); + contending_point = lock_point(hlock_class(hlock)->contending_point, + lock->ip); + + stats = get_lock_stats(hlock_class(hlock)); + if (contention_point < LOCKSTAT_POINTS) + stats->contention_point[contention_point]++; + if (contending_point < LOCKSTAT_POINTS) + stats->contending_point[contending_point]++; + if (lock->cpu != smp_processor_id()) + stats->bounces[bounce_contended + !!hlock->read]++; + put_lock_stats(stats); +} + +static void +__lock_acquired(struct lockdep_map *lock, unsigned long ip) +{ + struct task_struct *curr = current; + struct held_lock *hlock, *prev_hlock; + struct lock_class_stats *stats; + unsigned int depth; + u64 now; + s64 waittime = 0; + int i, cpu; + + depth = curr->lockdep_depth; + if (DEBUG_LOCKS_WARN_ON(!depth)) + return; + + prev_hlock = NULL; + for (i = depth-1; i >= 0; i--) { + hlock = curr->held_locks + i; + /* + * We must not cross into another context: + */ + if (prev_hlock && prev_hlock->irq_context != hlock->irq_context) + break; + if (hlock->instance == lock) + goto found_it; + prev_hlock = hlock; + } + print_lock_contention_bug(curr, lock, _RET_IP_); + return; + +found_it: + cpu = smp_processor_id(); + if (hlock->waittime_stamp) { + now = sched_clock(); + waittime = now - hlock->waittime_stamp; + hlock->holdtime_stamp = now; + } + + stats = get_lock_stats(hlock_class(hlock)); + if (waittime) { + if (hlock->read) + lock_time_inc(&stats->read_waittime, waittime); + else + lock_time_inc(&stats->write_waittime, waittime); + } + if (lock->cpu != cpu) + stats->bounces[bounce_acquired + !!hlock->read]++; + put_lock_stats(stats); + + lock->cpu = cpu; + lock->ip = ip; +} + +void lock_contended(struct lockdep_map *lock, unsigned long ip) +{ + unsigned long flags; + + if (unlikely(!lock_stat)) + return; + + if (unlikely(current->lockdep_recursion)) + return; + + raw_local_irq_save(flags); + check_flags(flags); + current->lockdep_recursion = 1; + __lock_contended(lock, ip); + current->lockdep_recursion = 0; + raw_local_irq_restore(flags); +} +EXPORT_SYMBOL_GPL(lock_contended); + +void lock_acquired(struct lockdep_map *lock, unsigned long ip) +{ + unsigned long flags; + + if (unlikely(!lock_stat)) + return; + + if (unlikely(current->lockdep_recursion)) + return; + + raw_local_irq_save(flags); + check_flags(flags); + current->lockdep_recursion = 1; + __lock_acquired(lock, ip); + current->lockdep_recursion = 0; + raw_local_irq_restore(flags); +} +EXPORT_SYMBOL_GPL(lock_acquired); +#endif + /* * Used by the testsuite, sanitize the validator state * after a simulated failure: @@ -2408,6 +3139,7 @@ EXPORT_SYMBOL_GPL(lock_release); void lockdep_reset(void) { unsigned long flags; + int i; raw_local_irq_save(flags); current->curr_chain_key = 0; @@ -2418,6 +3150,8 @@ void lockdep_reset(void) nr_softirq_chains = 0; nr_process_chains = 0; debug_locks = 1; + for (i = 0; i < CHAINHASH_SIZE; i++) + INIT_LIST_HEAD(chainhash_table + i); raw_local_irq_restore(flags); } @@ -2439,9 +3173,10 @@ static void zap_class(struct lock_class *class) list_del_rcu(&class->hash_entry); list_del_rcu(&class->lock_entry); + class->key = NULL; } -static inline int within(void *addr, void *start, unsigned long size) +static inline int within(const void *addr, void *start, unsigned long size) { return addr >= start && addr < start + size; } @@ -2452,9 +3187,10 @@ void lockdep_free_key_range(void *start, unsigned long size) struct list_head *head; unsigned long flags; int i; + int locked; raw_local_irq_save(flags); - __raw_spin_lock(&hash_lock); + locked = graph_lock(); /* * Unhash all classes that were created by this module: @@ -2463,12 +3199,16 @@ void lockdep_free_key_range(void *start, unsigned long size) head = classhash_table + i; if (list_empty(head)) continue; - list_for_each_entry_safe(class, next, head, hash_entry) + list_for_each_entry_safe(class, next, head, hash_entry) { if (within(class->key, start, size)) zap_class(class); + else if (within(class->name, start, size)) + zap_class(class); + } } - __raw_spin_unlock(&hash_lock); + if (locked) + graph_unlock(); raw_local_irq_restore(flags); } @@ -2478,6 +3218,7 @@ void lockdep_reset_lock(struct lockdep_map *lock) struct list_head *head; unsigned long flags; int i, j; + int locked; raw_local_irq_save(flags); @@ -2496,26 +3237,27 @@ void lockdep_reset_lock(struct lockdep_map *lock) * Debug check: in the end all mapped classes should * be gone. */ - __raw_spin_lock(&hash_lock); + locked = graph_lock(); for (i = 0; i < CLASSHASH_SIZE; i++) { head = classhash_table + i; if (list_empty(head)) continue; list_for_each_entry_safe(class, next, head, hash_entry) { if (unlikely(class == lock->class_cache)) { - __raw_spin_unlock(&hash_lock); - DEBUG_LOCKS_WARN_ON(1); + if (debug_locks_off_graph_unlock()) + WARN_ON(1); goto out_restore; } } } - __raw_spin_unlock(&hash_lock); + if (locked) + graph_unlock(); out_restore: raw_local_irq_restore(flags); } -void __init lockdep_init(void) +void lockdep_init(void) { int i; @@ -2541,10 +3283,10 @@ void __init lockdep_info(void) { printk("Lock dependency validator: Copyright (c) 2006 Red Hat, Inc., Ingo Molnar\n"); - printk("... MAX_LOCKDEP_SUBCLASSES: %lu\n", MAX_LOCKDEP_SUBCLASSES); + printk("... MAX_LOCKDEP_SUBCLASSES: %lu\n", MAX_LOCKDEP_SUBCLASSES); printk("... MAX_LOCK_DEPTH: %lu\n", MAX_LOCK_DEPTH); printk("... MAX_LOCKDEP_KEYS: %lu\n", MAX_LOCKDEP_KEYS); - printk("... CLASSHASH_SIZE: %lu\n", CLASSHASH_SIZE); + printk("... CLASSHASH_SIZE: %lu\n", CLASSHASH_SIZE); printk("... MAX_LOCKDEP_ENTRIES: %lu\n", MAX_LOCKDEP_ENTRIES); printk("... MAX_LOCKDEP_CHAINS: %lu\n", MAX_LOCKDEP_CHAINS); printk("... CHAINHASH_SIZE: %lu\n", CHAINHASH_SIZE); @@ -2560,16 +3302,14 @@ void __init lockdep_info(void) sizeof(struct held_lock) * MAX_LOCK_DEPTH); #ifdef CONFIG_DEBUG_LOCKDEP - if (lockdep_init_error) - printk("WARNING: lockdep init error! Arch code didnt call lockdep_init() early enough?\n"); + if (lockdep_init_error) { + printk("WARNING: lockdep init error! Arch code didn't call lockdep_init() early enough?\n"); + printk("Call stack leading to lockdep invocation was:\n"); + print_stack_trace(&lockdep_init_trace, 0); + } #endif } -static inline int in_range(const void *start, const void *addr, const void *end) -{ - return addr >= start && addr <= end; -} - static void print_freed_lock_bug(struct task_struct *curr, const void *mem_from, const void *mem_to, struct held_lock *hlock) @@ -2583,7 +3323,7 @@ print_freed_lock_bug(struct task_struct *curr, const void *mem_from, printk( "[ BUG: held lock freed! ]\n"); printk( "-------------------------\n"); printk("%s/%d is freeing memory %p-%p, with a lock still held there!\n", - curr->comm, curr->pid, mem_from, mem_to-1); + curr->comm, task_pid_nr(curr), mem_from, mem_to-1); print_lock(hlock); lockdep_print_held_locks(curr); @@ -2591,6 +3331,13 @@ print_freed_lock_bug(struct task_struct *curr, const void *mem_from, dump_stack(); } +static inline int not_in_range(const void* mem_from, unsigned long mem_len, + const void* lock_from, unsigned long lock_len) +{ + return lock_from + lock_len <= mem_from || + mem_from + mem_len <= lock_from; +} + /* * Called when kernel memory is freed (or unmapped), or if a lock * is destroyed or reinitialized - this code checks whether there is @@ -2598,7 +3345,6 @@ print_freed_lock_bug(struct task_struct *curr, const void *mem_from, */ void debug_check_no_locks_freed(const void *mem_from, unsigned long mem_len) { - const void *mem_to = mem_from + mem_len, *lock_from, *lock_to; struct task_struct *curr = current; struct held_lock *hlock; unsigned long flags; @@ -2611,18 +3357,16 @@ void debug_check_no_locks_freed(const void *mem_from, unsigned long mem_len) for (i = 0; i < curr->lockdep_depth; i++) { hlock = curr->held_locks + i; - lock_from = (void *)hlock->instance; - lock_to = (void *)(hlock->instance + 1); - - if (!in_range(mem_from, lock_from, mem_to) && - !in_range(mem_from, lock_to, mem_to)) + if (not_in_range(mem_from, mem_len, hlock->instance, + sizeof(*hlock->instance))) continue; - print_freed_lock_bug(curr, mem_from, mem_to, hlock); + print_freed_lock_bug(curr, mem_from, mem_from + mem_len, hlock); break; } local_irq_restore(flags); } +EXPORT_SYMBOL_GPL(debug_check_no_locks_freed); static void print_held_locks_bug(struct task_struct *curr) { @@ -2635,7 +3379,7 @@ static void print_held_locks_bug(struct task_struct *curr) printk( "[ BUG: lock held at task exit time! ]\n"); printk( "-------------------------------------\n"); printk("%s/%d is exiting with locks still held!\n", - curr->comm, curr->pid); + curr->comm, task_pid_nr(curr)); lockdep_print_held_locks(curr); printk("\nstack backtrace:\n"); @@ -2654,6 +3398,10 @@ void debug_show_all_locks(void) int count = 10; int unlock = 1; + if (unlikely(!debug_locks)) { + printk("INFO: lockdep is turned off.\n"); + return; + } printk("\nShowing all locks held in the system:\n"); /* @@ -2674,11 +3422,19 @@ retry: } printk(" ignoring it.\n"); unlock = 0; + } else { + if (count != 10) + printk(KERN_CONT " locked it.\n"); } - if (count != 10) - printk(" locked it.\n"); do_each_thread(g, p) { + /* + * It's not reliable to print a task's held locks + * if it's not sleeping (or if it's not the current + * task): + */ + if (p->state == TASK_RUNNING && p != current) + continue; if (p->lockdep_depth) lockdep_print_held_locks(p); if (!unlock) @@ -2692,13 +3448,40 @@ retry: if (unlock) read_unlock(&tasklist_lock); } - EXPORT_SYMBOL_GPL(debug_show_all_locks); -void debug_show_held_locks(struct task_struct *task) +/* + * Careful: only use this function if you are sure that + * the task cannot run in parallel! + */ +void __debug_show_held_locks(struct task_struct *task) { + if (unlikely(!debug_locks)) { + printk("INFO: lockdep is turned off.\n"); + return; + } lockdep_print_held_locks(task); } +EXPORT_SYMBOL_GPL(__debug_show_held_locks); +void debug_show_held_locks(struct task_struct *task) +{ + __debug_show_held_locks(task); +} EXPORT_SYMBOL_GPL(debug_show_held_locks); +void lockdep_sys_exit(void) +{ + struct task_struct *curr = current; + + if (unlikely(curr->lockdep_depth)) { + if (!debug_locks_off()) + return; + printk("\n================================================\n"); + printk( "[ BUG: lock held when returning to user space! ]\n"); + printk( "------------------------------------------------\n"); + printk("%s/%d is leaving the kernel with locks still held!\n", + curr->comm, curr->pid); + lockdep_print_held_locks(curr); + } +}