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>

1 files changed, 29 insertions, 29 deletions

diff --git a/kernel/lockdep_proc.c b/kernel/lockdep_proc.c
index d4aba4f..59b76c8 100644
--- a/kernel/lockdep_proc.c
+++ b/kernel/lockdep_proc.c
@@ -184,34 +184,34 @@ static const struct file_operations proc_lockdep_chains_operations = {
 static void lockdep_stats_debug_show(struct seq_file *m)
 {
 #ifdef CONFIG_DEBUG_LOCKDEP
-	unsigned int hi1 = debug_atomic_read(&hardirqs_on_events),
-		     hi2 = debug_atomic_read(&hardirqs_off_events),
-		     hr1 = debug_atomic_read(&redundant_hardirqs_on),
-		     hr2 = debug_atomic_read(&redundant_hardirqs_off),
-		     si1 = debug_atomic_read(&softirqs_on_events),
-		     si2 = debug_atomic_read(&softirqs_off_events),
-		     sr1 = debug_atomic_read(&redundant_softirqs_on),
-		     sr2 = debug_atomic_read(&redundant_softirqs_off);
-
-	seq_printf(m, " chain lookup misses:           %11u\n",
-		debug_atomic_read(&chain_lookup_misses));
-	seq_printf(m, " chain lookup hits:             %11u\n",
-		debug_atomic_read(&chain_lookup_hits));
-	seq_printf(m, " cyclic checks:                 %11u\n",
-		debug_atomic_read(&nr_cyclic_checks));
-	seq_printf(m, " find-mask forwards checks:     %11u\n",
-		debug_atomic_read(&nr_find_usage_forwards_checks));
-	seq_printf(m, " find-mask backwards checks:    %11u\n",
-		debug_atomic_read(&nr_find_usage_backwards_checks));
-
-	seq_printf(m, " hardirq on events:             %11u\n", hi1);
-	seq_printf(m, " hardirq off events:            %11u\n", hi2);
-	seq_printf(m, " redundant hardirq ons:         %11u\n", hr1);
-	seq_printf(m, " redundant hardirq offs:        %11u\n", hr2);
-	seq_printf(m, " softirq on events:             %11u\n", si1);
-	seq_printf(m, " softirq off events:            %11u\n", si2);
-	seq_printf(m, " redundant softirq ons:         %11u\n", sr1);
-	seq_printf(m, " redundant softirq offs:        %11u\n", sr2);
+	unsigned long long hi1 = debug_atomic_read(hardirqs_on_events),
+			   hi2 = debug_atomic_read(hardirqs_off_events),
+			   hr1 = debug_atomic_read(redundant_hardirqs_on),
+			   hr2 = debug_atomic_read(redundant_hardirqs_off),
+			   si1 = debug_atomic_read(softirqs_on_events),
+			   si2 = debug_atomic_read(softirqs_off_events),
+			   sr1 = debug_atomic_read(redundant_softirqs_on),
+			   sr2 = debug_atomic_read(redundant_softirqs_off);
+
+	seq_printf(m, " chain lookup misses:           %11llu\n",
+		debug_atomic_read(chain_lookup_misses));
+	seq_printf(m, " chain lookup hits:             %11llu\n",
+		debug_atomic_read(chain_lookup_hits));
+	seq_printf(m, " cyclic checks:                 %11llu\n",
+		debug_atomic_read(nr_cyclic_checks));
+	seq_printf(m, " find-mask forwards checks:     %11llu\n",
+		debug_atomic_read(nr_find_usage_forwards_checks));
+	seq_printf(m, " find-mask backwards checks:    %11llu\n",
+		debug_atomic_read(nr_find_usage_backwards_checks));
+
+	seq_printf(m, " hardirq on events:             %11llu\n", hi1);
+	seq_printf(m, " hardirq off events:            %11llu\n", hi2);
+	seq_printf(m, " redundant hardirq ons:         %11llu\n", hr1);
+	seq_printf(m, " redundant hardirq offs:        %11llu\n", hr2);
+	seq_printf(m, " softirq on events:             %11llu\n", si1);
+	seq_printf(m, " softirq off events:            %11llu\n", si2);
+	seq_printf(m, " redundant softirq ons:         %11llu\n", sr1);
+	seq_printf(m, " redundant softirq offs:        %11llu\n", sr2);
 #endif
 }
 
@@ -263,7 +263,7 @@ static int lockdep_stats_show(struct seq_file *m, void *v)
 #endif
 	}
 #ifdef CONFIG_DEBUG_LOCKDEP
-	DEBUG_LOCKS_WARN_ON(debug_atomic_read(&nr_unused_locks) != nr_unused);
+	DEBUG_LOCKS_WARN_ON(debug_atomic_read(nr_unused_locks) != nr_unused);
 #endif
 	seq_printf(m, " lock-classes:                  %11lu [max: %lu]\n",
 			nr_lock_classes, MAX_LOCKDEP_KEYS);