tracing: Convert the per CPU "disabled" counter to local from atomic

The per CPU "disabled" counter is used for the latency tracers and stack
tracers to make sure that their accounting isn't messed up by an NMI or
interrupt coming in and affecting the same CPU data. But the counter is an
atomic_t type. As it only needs to synchronize against the current CPU,
switch it over to local_t type.

Cc: Masami Hiramatsu <[email protected]>
Cc: Mark Rutland <[email protected]>
Cc: Mathieu Desnoyers <[email protected]>
Cc: Andrew Morton <[email protected]>
Link: https://lore.kernel.org/[email protected]
Signed-off-by: Steven Rostedt (Google) <[email protected]>

Author: rostedt

kernel/trace/trace.h

@@ -183,7 +183,7 @@ struct trace_array;
  * the trace, etc.)
  */
 struct trace_array_cpu {
-	atomic_t		disabled;
+	local_t			disabled;
 	void			*buffer_page;	/* ring buffer spare */
 
 	unsigned long		entries;

kernel/trace/trace_functions.c

@@ -291,7 +291,7 @@ function_stack_trace_call(unsigned long ip, unsigned long parent_ip,
 	parent_ip = function_get_true_parent_ip(parent_ip, fregs);
 	cpu = raw_smp_processor_id();
 	data = per_cpu_ptr(tr->array_buffer.data, cpu);
-	disabled = atomic_inc_return(&data->disabled);
+	disabled = local_inc_return(&data->disabled);
 
 	if (likely(disabled == 1)) {
 		trace_ctx = tracing_gen_ctx_flags(flags);
@@ -303,7 +303,7 @@ function_stack_trace_call(unsigned long ip, unsigned long parent_ip,
 		__trace_stack(tr, trace_ctx, skip);
 	}
 
-	atomic_dec(&data->disabled);
+	local_dec(&data->disabled);
 	local_irq_restore(flags);
 }
 
@@ -402,7 +402,7 @@ function_stack_no_repeats_trace_call(unsigned long ip, unsigned long parent_ip,
 	parent_ip = function_get_true_parent_ip(parent_ip, fregs);
 	cpu = raw_smp_processor_id();
 	data = per_cpu_ptr(tr->array_buffer.data, cpu);
-	disabled = atomic_inc_return(&data->disabled);
+	disabled = local_inc_return(&data->disabled);
 
 	if (likely(disabled == 1)) {
 		last_info = per_cpu_ptr(tr->last_func_repeats, cpu);
@@ -417,7 +417,7 @@ function_stack_no_repeats_trace_call(unsigned long ip, unsigned long parent_ip,
 	}
 
  out:
-	atomic_dec(&data->disabled);
+	local_dec(&data->disabled);
 	local_irq_restore(flags);
 }
 

kernel/trace/trace_irqsoff.c

@@ -123,12 +123,12 @@ static int func_prolog_dec(struct trace_array *tr,
 		return 0;
 
 	*data = per_cpu_ptr(tr->array_buffer.data, cpu);
-	disabled = atomic_inc_return(&(*data)->disabled);
+	disabled = local_inc_return(&(*data)->disabled);
 
 	if (likely(disabled == 1))
 		return 1;
 
-	atomic_dec(&(*data)->disabled);
+	local_dec(&(*data)->disabled);
 
 	return 0;
 }
@@ -152,7 +152,7 @@ irqsoff_tracer_call(unsigned long ip, unsigned long parent_ip,
 
 	trace_function(tr, ip, parent_ip, trace_ctx, fregs);
 
-	atomic_dec(&data->disabled);
+	local_dec(&data->disabled);
 }
 #endif /* CONFIG_FUNCTION_TRACER */
 
@@ -209,7 +209,7 @@ static int irqsoff_graph_entry(struct ftrace_graph_ent *trace,
 
 	trace_ctx = tracing_gen_ctx_flags(flags);
 	ret = __trace_graph_entry(tr, trace, trace_ctx);
-	atomic_dec(&data->disabled);
+	local_dec(&data->disabled);
 
 	return ret;
 }
@@ -238,7 +238,7 @@ static void irqsoff_graph_return(struct ftrace_graph_ret *trace,
 
 	trace_ctx = tracing_gen_ctx_flags(flags);
 	__trace_graph_return(tr, trace, trace_ctx, *calltime, rettime);
-	atomic_dec(&data->disabled);
+	local_dec(&data->disabled);
 }
 
 static struct fgraph_ops fgraph_ops = {
@@ -408,10 +408,10 @@ start_critical_timing(unsigned long ip, unsigned long parent_ip)
 
 	data = per_cpu_ptr(tr->array_buffer.data, cpu);
 
-	if (unlikely(!data) || atomic_read(&data->disabled))
+	if (unlikely(!data) || local_read(&data->disabled))
 		return;
 
-	atomic_inc(&data->disabled);
+	local_inc(&data->disabled);
 
 	data->critical_sequence = max_sequence;
 	data->preempt_timestamp = ftrace_now(cpu);
@@ -421,7 +421,7 @@ start_critical_timing(unsigned long ip, unsigned long parent_ip)
 
 	per_cpu(tracing_cpu, cpu) = 1;
 
-	atomic_dec(&data->disabled);
+	local_dec(&data->disabled);
 }
 
 static nokprobe_inline void
@@ -445,16 +445,16 @@ stop_critical_timing(unsigned long ip, unsigned long parent_ip)
 	data = per_cpu_ptr(tr->array_buffer.data, cpu);
 
 	if (unlikely(!data) ||
-	    !data->critical_start || atomic_read(&data->disabled))
+	    !data->critical_start || local_read(&data->disabled))
 		return;
 
-	atomic_inc(&data->disabled);
+	local_inc(&data->disabled);
 
 	trace_ctx = tracing_gen_ctx();
 	__trace_function(tr, ip, parent_ip, trace_ctx);
 	check_critical_timing(tr, data, parent_ip ? : ip, cpu);
 	data->critical_start = 0;
-	atomic_dec(&data->disabled);
+	local_dec(&data->disabled);
 }
 
 /* start and stop critical timings used to for stoppage (in idle) */

kernel/trace/trace_sched_wakeup.c

@@ -83,14 +83,14 @@ func_prolog_preempt_disable(struct trace_array *tr,
 		goto out_enable;
 
 	*data = per_cpu_ptr(tr->array_buffer.data, cpu);
-	disabled = atomic_inc_return(&(*data)->disabled);
+	disabled = local_inc_return(&(*data)->disabled);
 	if (unlikely(disabled != 1))
 		goto out;
 
 	return 1;
 
 out:
-	atomic_dec(&(*data)->disabled);
+	local_dec(&(*data)->disabled);
 
 out_enable:
 	preempt_enable_notrace();
@@ -144,7 +144,7 @@ static int wakeup_graph_entry(struct ftrace_graph_ent *trace,
 	*calltime = trace_clock_local();
 
 	ret = __trace_graph_entry(tr, trace, trace_ctx);
-	atomic_dec(&data->disabled);
+	local_dec(&data->disabled);
 	preempt_enable_notrace();
 
 	return ret;
@@ -173,7 +173,7 @@ static void wakeup_graph_return(struct ftrace_graph_ret *trace,
 		return;
 
 	__trace_graph_return(tr, trace, trace_ctx, *calltime, rettime);
-	atomic_dec(&data->disabled);
+	local_dec(&data->disabled);
 
 	preempt_enable_notrace();
 	return;
@@ -243,7 +243,7 @@ wakeup_tracer_call(unsigned long ip, unsigned long parent_ip,
 	trace_function(tr, ip, parent_ip, trace_ctx, fregs);
 	local_irq_restore(flags);
 
-	atomic_dec(&data->disabled);
+	local_dec(&data->disabled);
 	preempt_enable_notrace();
 }
 
@@ -471,7 +471,7 @@ probe_wakeup_sched_switch(void *ignore, bool preempt,
 
 	/* disable local data, not wakeup_cpu data */
 	cpu = raw_smp_processor_id();
-	disabled = atomic_inc_return(&per_cpu_ptr(wakeup_trace->array_buffer.data, cpu)->disabled);
+	disabled = local_inc_return(&per_cpu_ptr(wakeup_trace->array_buffer.data, cpu)->disabled);
 	if (likely(disabled != 1))
 		goto out;
 
@@ -508,7 +508,7 @@ probe_wakeup_sched_switch(void *ignore, bool preempt,
 	arch_spin_unlock(&wakeup_lock);
 	local_irq_restore(flags);
 out:
-	atomic_dec(&per_cpu_ptr(wakeup_trace->array_buffer.data, cpu)->disabled);
+	local_dec(&per_cpu_ptr(wakeup_trace->array_buffer.data, cpu)->disabled);
 }
 
 static void __wakeup_reset(struct trace_array *tr)
@@ -563,7 +563,7 @@ probe_wakeup(void *ignore, struct task_struct *p)
 	    (!dl_task(p) && (p->prio >= wakeup_prio || p->prio >= current->prio)))
 		return;
 
-	disabled = atomic_inc_return(&per_cpu_ptr(wakeup_trace->array_buffer.data, cpu)->disabled);
+	disabled = local_inc_return(&per_cpu_ptr(wakeup_trace->array_buffer.data, cpu)->disabled);
 	if (unlikely(disabled != 1))
 		goto out;
 
@@ -610,7 +610,7 @@ probe_wakeup(void *ignore, struct task_struct *p)
 out_locked:
 	arch_spin_unlock(&wakeup_lock);
 out:
-	atomic_dec(&per_cpu_ptr(wakeup_trace->array_buffer.data, cpu)->disabled);
+	local_dec(&per_cpu_ptr(wakeup_trace->array_buffer.data, cpu)->disabled);
 }
 
 static void start_wakeup_tracer(struct trace_array *tr)