*
* Started by Ingo Molnar:
*
- * Copyright (C) 2006 Red Hat, Inc., Ingo Molnar <mingo@redhat.com>
+ * Copyright (C) 2006,2007 Red Hat, Inc., Ingo Molnar <mingo@redhat.com>
+ * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
*
* this code maps all the lock dependencies as they occur in a live kernel
* and will warn about the following classes of locking bugs:
#include <linux/debug_locks.h>
#include <linux/irqflags.h>
#include <linux/utsname.h>
+#include <linux/hash.h>
#include <asm/sections.h>
#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
+
/*
* lockdep_lock: protects the lockdep graph, the hashes and the
* class/list/hash allocators.
unsigned long nr_lock_classes;
static struct lock_class lock_classes[MAX_LOCKDEP_KEYS];
+#ifdef CONFIG_LOCK_STAT
+static DEFINE_PER_CPU(struct lock_class_stats[MAX_LOCKDEP_KEYS], lock_stats);
+
+static int lock_contention_point(struct lock_class *class, unsigned long ip)
+{
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(class->contention_point); i++) {
+ if (class->contention_point[i] == 0) {
+ class->contention_point[i] = ip;
+ break;
+ }
+ if (class->contention_point[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];
+
+ 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));
+}
+
+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);
+ 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
*/
#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];
*/
#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];
* 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:
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);
if (unlikely(!lockdep_initialized)) {
lockdep_init();
lockdep_init_error = 1;
+ save_stack_trace(&lockdep_init_trace);
}
#endif
* (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 lock_class));
+ BUILD_BUG_ON(sizeof(struct lock_class_key) >
+ sizeof(struct lockdep_map));
key = lock->key->subkeys + subclass;
* 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)
+ list_for_each_entry(class, hash_head, hash_entry) {
+ if (class->key == key) {
+ WARN_ON_ONCE(class->name != lock->name);
return class;
+ }
+ }
return NULL;
}
* 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();
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);
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,
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);
}
static int validate_chain(struct task_struct *curr, struct lockdep_map *lock,
- struct held_lock *hlock, int chain_head)
+ struct held_lock *hlock, int chain_head, u64 chain_key)
{
/*
* Trylock needs to maintain the stack of held locks, but it
* graph_lock for us)
*/
if (!hlock->trylock && (hlock->check == 2) &&
- lookup_chain_cache(curr->curr_chain_key, hlock->class)) {
+ lookup_chain_cache(chain_key, hlock->class)) {
/*
* Check whether last held lock:
*
#else
static inline int validate_chain(struct task_struct *curr,
struct lockdep_map *lock, struct held_lock *hlock,
- int chain_head)
+ int chain_head, u64 chain_key)
{
return 1;
}
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,
+ 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),
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);
return 0;
break;
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);
break;
default:
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);
}
int chain_head = 0;
u64 chain_key;
+ if (!prove_locking)
+ check = 1;
+
if (unlikely(!debug_locks))
return 0;
hlock->read = read;
hlock->check = check;
hlock->hardirqs_off = hardirqs_off;
+#ifdef CONFIG_LOCK_STAT
+ hlock->waittime_stamp = 0;
+ hlock->holdtime_stamp = sched_clock();
+#endif
if (check == 2 && !mark_irqflags(curr, hlock))
return 0;
return 0;
/*
- * Calculate the chain hash: it's the combined has of all the
+ * 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
chain_head = 1;
}
chain_key = iterate_chain_key(chain_key, id);
- curr->curr_chain_key = chain_key;
- if (!validate_chain(curr, lock, hlock, chain_head))
+ 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
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);
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
curr->curr_chain_key = hlock->prev_chain_key;
+ lock_release_holdtime(hlock);
+
#ifdef CONFIG_DEBUG_LOCKDEP
hlock->prev_chain_key = 0;
hlock->class = NULL;
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.
{
unsigned long flags;
+ if (unlikely(!lock_stat && !prove_locking))
+ return;
+
if (unlikely(current->lockdep_recursion))
return;
{
unsigned long flags;
+ if (unlikely(!lock_stat && !prove_locking))
+ return;
+
if (unlikely(current->lockdep_recursion))
return;
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, 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();
+
+ point = lock_contention_point(hlock->class, ip);
+
+ stats = get_lock_stats(hlock->class);
+ if (point < ARRAY_SIZE(stats->contention_point))
+ stats->contention_point[i]++;
+ if (lock->cpu != smp_processor_id())
+ stats->bounces[bounce_contended + !!hlock->read]++;
+ put_lock_stats(stats);
+}
+
+static void
+__lock_acquired(struct lockdep_map *lock)
+{
+ 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);
+ 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;
+}
+
+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 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);
+ 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:
}
-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;
}
struct list_head *head;
unsigned long flags;
int i;
+ int locked;
raw_local_irq_save(flags);
- graph_lock();
+ locked = graph_lock();
/*
* Unhash all classes that were created by this module:
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);
+ }
}
- graph_unlock();
+ if (locked)
+ graph_unlock();
raw_local_irq_restore(flags);
}
struct list_head *head;
unsigned long flags;
int i, j;
+ int locked;
raw_local_irq_save(flags);
* Debug check: in the end all mapped classes should
* be gone.
*/
- graph_lock();
+ locked = graph_lock();
for (i = 0; i < CLASSHASH_SIZE; i++) {
head = classhash_table + i;
if (list_empty(head))
}
}
}
- graph_unlock();
+ if (locked)
+ graph_unlock();
out_restore:
raw_local_irq_restore(flags);
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)
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);
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
*/
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;
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);
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");
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)
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");
}
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);
+ }
+}