lockstat: Make lockstat counting per cpu
Locking statistics are implemented using global atomic
variables. This is usually fine unless some path write them very
often.
This is the case for the function and function graph tracers
that disable irqs for each entry saved (except if the function
tracer is in preempt disabled only mode).
And calls to local_irq_save/restore() increment
hardirqs_on_events and hardirqs_off_events stats (or similar
stats for redundant versions).
Incrementing these global vars for each function ends up in too
much cache bouncing if lockstats are enabled.
To solve this, implement the debug_atomic_*() operations using
per cpu vars.
-v2: Use per_cpu() instead of get_cpu_var() to fetch the desired
cpu vars on debug_atomic_read()
-v3: Store the stats in a structure. No need for local_t as we
are NMI/irq safe.
-v4: Fix tons of build errors. I thought I had tested it but I
probably forgot to select the relevant config.
Suggested-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Steven Rostedt <rostedt@goodmis.org>
LKML-Reference: <1270505417-8144-1-git-send-regression-fweisbec@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Steven Rostedt <rostedt@goodmis.org>
diff --git a/kernel/lockdep.c b/kernel/lockdep.c
index 0c30d04..069af02 100644
--- a/kernel/lockdep.c
+++ b/kernel/lockdep.c
@@ -430,20 +430,7 @@
/*
* Various lockdep statistics:
*/
-atomic_t chain_lookup_hits;
-atomic_t chain_lookup_misses;
-atomic_t hardirqs_on_events;
-atomic_t hardirqs_off_events;
-atomic_t redundant_hardirqs_on;
-atomic_t redundant_hardirqs_off;
-atomic_t softirqs_on_events;
-atomic_t softirqs_off_events;
-atomic_t redundant_softirqs_on;
-atomic_t redundant_softirqs_off;
-atomic_t nr_unused_locks;
-atomic_t nr_cyclic_checks;
-atomic_t nr_find_usage_forwards_checks;
-atomic_t nr_find_usage_backwards_checks;
+DEFINE_PER_CPU(struct lockdep_stats, lockdep_stats);
#endif
/*
@@ -758,7 +745,7 @@
return NULL;
}
class = lock_classes + nr_lock_classes++;
- debug_atomic_inc(&nr_unused_locks);
+ debug_atomic_inc(nr_unused_locks);
class->key = key;
class->name = lock->name;
class->subclass = subclass;
@@ -1215,7 +1202,7 @@
{
int result;
- debug_atomic_inc(&nr_cyclic_checks);
+ debug_atomic_inc(nr_cyclic_checks);
result = __bfs_forwards(root, target, class_equal, target_entry);
@@ -1252,7 +1239,7 @@
{
int result;
- debug_atomic_inc(&nr_find_usage_forwards_checks);
+ debug_atomic_inc(nr_find_usage_forwards_checks);
result = __bfs_forwards(root, (void *)bit, usage_match, target_entry);
@@ -1275,7 +1262,7 @@
{
int result;
- debug_atomic_inc(&nr_find_usage_backwards_checks);
+ debug_atomic_inc(nr_find_usage_backwards_checks);
result = __bfs_backwards(root, (void *)bit, usage_match, target_entry);
@@ -1835,7 +1822,7 @@
list_for_each_entry(chain, hash_head, entry) {
if (chain->chain_key == chain_key) {
cache_hit:
- debug_atomic_inc(&chain_lookup_hits);
+ debug_atomic_inc(chain_lookup_hits);
if (very_verbose(class))
printk("\nhash chain already cached, key: "
"%016Lx tail class: [%p] %s\n",
@@ -1900,7 +1887,7 @@
chain_hlocks[chain->base + j] = class - lock_classes;
}
list_add_tail_rcu(&chain->entry, hash_head);
- debug_atomic_inc(&chain_lookup_misses);
+ debug_atomic_inc(chain_lookup_misses);
inc_chains();
return 1;
@@ -2321,7 +2308,7 @@
return;
if (unlikely(curr->hardirqs_enabled)) {
- debug_atomic_inc(&redundant_hardirqs_on);
+ debug_atomic_inc(redundant_hardirqs_on);
return;
}
/* we'll do an OFF -> ON transition: */
@@ -2348,7 +2335,7 @@
curr->hardirq_enable_ip = ip;
curr->hardirq_enable_event = ++curr->irq_events;
- debug_atomic_inc(&hardirqs_on_events);
+ debug_atomic_inc(hardirqs_on_events);
}
EXPORT_SYMBOL(trace_hardirqs_on_caller);
@@ -2380,9 +2367,9 @@
curr->hardirqs_enabled = 0;
curr->hardirq_disable_ip = ip;
curr->hardirq_disable_event = ++curr->irq_events;
- debug_atomic_inc(&hardirqs_off_events);
+ debug_atomic_inc(hardirqs_off_events);
} else
- debug_atomic_inc(&redundant_hardirqs_off);
+ debug_atomic_inc(redundant_hardirqs_off);
}
EXPORT_SYMBOL(trace_hardirqs_off_caller);
@@ -2406,7 +2393,7 @@
return;
if (curr->softirqs_enabled) {
- debug_atomic_inc(&redundant_softirqs_on);
+ debug_atomic_inc(redundant_softirqs_on);
return;
}
@@ -2416,7 +2403,7 @@
curr->softirqs_enabled = 1;
curr->softirq_enable_ip = ip;
curr->softirq_enable_event = ++curr->irq_events;
- debug_atomic_inc(&softirqs_on_events);
+ debug_atomic_inc(softirqs_on_events);
/*
* We are going to turn softirqs on, so set the
* usage bit for all held locks, if hardirqs are
@@ -2446,10 +2433,10 @@
curr->softirqs_enabled = 0;
curr->softirq_disable_ip = ip;
curr->softirq_disable_event = ++curr->irq_events;
- debug_atomic_inc(&softirqs_off_events);
+ debug_atomic_inc(softirqs_off_events);
DEBUG_LOCKS_WARN_ON(!softirq_count());
} else
- debug_atomic_inc(&redundant_softirqs_off);
+ debug_atomic_inc(redundant_softirqs_off);
}
static void __lockdep_trace_alloc(gfp_t gfp_mask, unsigned long flags)
@@ -2654,7 +2641,7 @@
return 0;
break;
case LOCK_USED:
- debug_atomic_dec(&nr_unused_locks);
+ debug_atomic_dec(nr_unused_locks);
break;
default:
if (!debug_locks_off_graph_unlock())
@@ -2760,7 +2747,7 @@
if (!class)
return 0;
}
- debug_atomic_inc((atomic_t *)&class->ops);
+ atomic_inc((atomic_t *)&class->ops);
if (very_verbose(class)) {
printk("\nacquire class [%p] %s", class->key, class->name);
if (class->name_version > 1)