tracing: Centralize preemptirq tracepoints and unify their usage

joelagnel · rostedt · commit c3bc8fd637a9 · 2018-07-31T11:32:27.000-04:00
This patch detaches the preemptirq tracepoints from the tracers and keeps it separate. Advantages: * Lockdep and irqsoff event can now run in parallel since they no longer have their own calls. * This unifies the usecase of adding hooks to an irqsoff and irqson event, and a preemptoff and preempton event. 3 users of the events exist: - Lockdep - irqsoff and preemptoff tracers - irqs and preempt trace events The unification cleans up several ifdefs and makes the code in preempt tracer and irqsoff tracers simpler. It gets rid of all the horrific ifdeferry around PROVE_LOCKING and makes configuration of the different users of the tracepoints more easy and understandable. It also gets rid of the time_* function calls from the lockdep hooks used to call into the preemptirq tracer which is not needed anymore. The negative delta in lines of code in this patch is quite large too. In the patch we introduce a new CONFIG option PREEMPTIRQ_TRACEPOINTS as a single point for registering probes onto the tracepoints. With this, the web of config options for preempt/irq toggle tracepoints and its users becomes: PREEMPT_TRACER PREEMPTIRQ_EVENTS IRQSOFF_TRACER PROVE_LOCKING | | \ | | \ (selects) / \ \ (selects) / TRACE_PREEMPT_TOGGLE ----> TRACE_IRQFLAGS \ / \ (depends on) / PREEMPTIRQ_TRACEPOINTS Other than the performance tests mentioned in the previous patch, I also ran the locking API test suite. I verified that all tests cases are passing. I also injected issues by not registering lockdep probes onto the tracepoints and I see failures to confirm that the probes are indeed working. This series + lockdep probes not registered (just to inject errors): [ 0.000000] hard-irqs-on + irq-safe-A/21: ok | ok | ok | [ 0.000000] soft-irqs-on + irq-safe-A/21: ok | ok | ok | [ 0.000000] sirq-safe-A => hirqs-on/12:FAILED|FAILED| ok | [ 0.000000] sirq-safe-A => hirqs-on/21:FAILED|FAILED| ok | [ 0.000000] hard-safe-A + irqs-on/12:FAILED|FAILED| ok | [ 0.000000] soft-safe-A + irqs-on/12:FAILED|FAILED| ok | [ 0.000000] hard-safe-A + irqs-on/21:FAILED|FAILED| ok | [ 0.000000] soft-safe-A + irqs-on/21:FAILED|FAILED| ok | [ 0.000000] hard-safe-A + unsafe-B #1/123: ok | ok | ok | [ 0.000000] soft-safe-A + unsafe-B #1/123: ok | ok | ok | With this series + lockdep probes registered, all locking tests pass: [ 0.000000] hard-irqs-on + irq-safe-A/21: ok | ok | ok | [ 0.000000] soft-irqs-on + irq-safe-A/21: ok | ok | ok | [ 0.000000] sirq-safe-A => hirqs-on/12: ok | ok | ok | [ 0.000000] sirq-safe-A => hirqs-on/21: ok | ok | ok | [ 0.000000] hard-safe-A + irqs-on/12: ok | ok | ok | [ 0.000000] soft-safe-A + irqs-on/12: ok | ok | ok | [ 0.000000] hard-safe-A + irqs-on/21: ok | ok | ok | [ 0.000000] soft-safe-A + irqs-on/21: ok | ok | ok | [ 0.000000] hard-safe-A + unsafe-B #1/123: ok | ok | ok | [ 0.000000] soft-safe-A + unsafe-B #1/123: ok | ok | ok | Link: http://lkml.kernel.org/r/20180730222423.196630-4-joel@joelfernandes.org Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Reviewed-by: Namhyung Kim <namhyung@kernel.org> Signed-off-by: Joel Fernandes (Google) <joel@joelfernandes.org> Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
@@ -701,16 +701,7 @@ static inline unsigned long get_lock_parent_ip(void)
 	return CALLER_ADDR2;
 }
 
-#ifdef CONFIG_IRQSOFF_TRACER
-  extern void time_hardirqs_on(unsigned long a0, unsigned long a1);
-  extern void time_hardirqs_off(unsigned long a0, unsigned long a1);
-#else
-  static inline void time_hardirqs_on(unsigned long a0, unsigned long a1) { }
-  static inline void time_hardirqs_off(unsigned long a0, unsigned long a1) { }
-#endif
-
-#if defined(CONFIG_PREEMPT_TRACER) || \
-	(defined(CONFIG_DEBUG_PREEMPT) && defined(CONFIG_PREEMPTIRQ_EVENTS))
+#ifdef CONFIG_TRACE_PREEMPT_TOGGLE
   extern void trace_preempt_on(unsigned long a0, unsigned long a1);
   extern void trace_preempt_off(unsigned long a0, unsigned long a1);
 #else
diff --git a/include/linux/irqflags.h b/include/linux/irqflags.h
@@ -15,9 +15,16 @@
 #include <linux/typecheck.h>
 #include <asm/irqflags.h>
 
-#ifdef CONFIG_TRACE_IRQFLAGS
+/* Currently trace_softirqs_on/off is used only by lockdep */
+#ifdef CONFIG_PROVE_LOCKING
   extern void trace_softirqs_on(unsigned long ip);
   extern void trace_softirqs_off(unsigned long ip);
+#else
+# define trace_softirqs_on(ip)	do { } while (0)
+# define trace_softirqs_off(ip)	do { } while (0)
+#endif
+
+#ifdef CONFIG_TRACE_IRQFLAGS
   extern void trace_hardirqs_on(void);
   extern void trace_hardirqs_off(void);
 # define trace_hardirq_context(p)	((p)->hardirq_context)
@@ -43,8 +50,6 @@ do {						\
 #else
 # define trace_hardirqs_on()		do { } while (0)
 # define trace_hardirqs_off()		do { } while (0)
-# define trace_softirqs_on(ip)		do { } while (0)
-# define trace_softirqs_off(ip)		do { } while (0)
 # define trace_hardirq_context(p)	0
 # define trace_softirq_context(p)	0
 # define trace_hardirqs_enabled(p)	0
diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h
@@ -266,7 +266,8 @@ struct held_lock {
 /*
  * Initialization, self-test and debugging-output methods:
  */
-extern void lockdep_info(void);
+extern void lockdep_init(void);
+extern void lockdep_init_early(void);
 extern void lockdep_reset(void);
 extern void lockdep_reset_lock(struct lockdep_map *lock);
 extern void lockdep_free_key_range(void *start, unsigned long size);
@@ -406,7 +407,8 @@ static inline void lockdep_on(void)
 # define lock_downgrade(l, i)			do { } while (0)
 # define lock_set_class(l, n, k, s, i)		do { } while (0)
 # define lock_set_subclass(l, s, i)		do { } while (0)
-# define lockdep_info()				do { } while (0)
+# define lockdep_init()				do { } while (0)
+# define lockdep_init_early()			do { } while (0)
 # define lockdep_init_map(lock, name, key, sub) \
 		do { (void)(name); (void)(key); } while (0)
 # define lockdep_set_class(lock, key)		do { (void)(key); } while (0)
@@ -532,7 +534,7 @@ do {								\
 
 #endif /* CONFIG_LOCKDEP */
 
-#ifdef CONFIG_TRACE_IRQFLAGS
+#ifdef CONFIG_PROVE_LOCKING
 extern void print_irqtrace_events(struct task_struct *curr);
 #else
 static inline void print_irqtrace_events(struct task_struct *curr)
diff --git a/include/linux/preempt.h b/include/linux/preempt.h
@@ -150,7 +150,7 @@
  */
 #define in_atomic_preempt_off() (preempt_count() != PREEMPT_DISABLE_OFFSET)
 
-#if defined(CONFIG_DEBUG_PREEMPT) || defined(CONFIG_PREEMPT_TRACER)
+#if defined(CONFIG_DEBUG_PREEMPT) || defined(CONFIG_TRACE_PREEMPT_TOGGLE)
 extern void preempt_count_add(int val);
 extern void preempt_count_sub(int val);
 #define preempt_count_dec_and_test() \
diff --git a/include/trace/events/preemptirq.h b/include/trace/events/preemptirq.h
@@ -1,4 +1,4 @@
-#ifdef CONFIG_PREEMPTIRQ_EVENTS
+#ifdef CONFIG_PREEMPTIRQ_TRACEPOINTS
 
 #undef TRACE_SYSTEM
 #define TRACE_SYSTEM preemptirq
@@ -32,40 +32,45 @@ DECLARE_EVENT_CLASS(preemptirq_template,
 		  (void *)((unsigned long)(_stext) + __entry->parent_offs))
 );
 
-#ifndef CONFIG_PROVE_LOCKING
+#ifdef CONFIG_TRACE_IRQFLAGS
 DEFINE_EVENT(preemptirq_template, irq_disable,
 	     TP_PROTO(unsigned long ip, unsigned long parent_ip),
 	     TP_ARGS(ip, parent_ip));
 
 DEFINE_EVENT(preemptirq_template, irq_enable,
 	     TP_PROTO(unsigned long ip, unsigned long parent_ip),
 	     TP_ARGS(ip, parent_ip));
+#else
+#define trace_irq_enable(...)
+#define trace_irq_disable(...)
+#define trace_irq_enable_rcuidle(...)
+#define trace_irq_disable_rcuidle(...)
 #endif
 
-#ifdef CONFIG_DEBUG_PREEMPT
+#ifdef CONFIG_TRACE_PREEMPT_TOGGLE
 DEFINE_EVENT(preemptirq_template, preempt_disable,
 	     TP_PROTO(unsigned long ip, unsigned long parent_ip),
 	     TP_ARGS(ip, parent_ip));
 
 DEFINE_EVENT(preemptirq_template, preempt_enable,
 	     TP_PROTO(unsigned long ip, unsigned long parent_ip),
 	     TP_ARGS(ip, parent_ip));
+#else
+#define trace_preempt_enable(...)
+#define trace_preempt_disable(...)
+#define trace_preempt_enable_rcuidle(...)
+#define trace_preempt_disable_rcuidle(...)
 #endif
 
 #endif /* _TRACE_PREEMPTIRQ_H */
 
 #include <trace/define_trace.h>
 
-#endif /* !CONFIG_PREEMPTIRQ_EVENTS */
-
-#if !defined(CONFIG_PREEMPTIRQ_EVENTS) || defined(CONFIG_PROVE_LOCKING)
+#else /* !CONFIG_PREEMPTIRQ_TRACEPOINTS */
 #define trace_irq_enable(...)
 #define trace_irq_disable(...)
 #define trace_irq_enable_rcuidle(...)
 #define trace_irq_disable_rcuidle(...)
-#endif
-
-#if !defined(CONFIG_PREEMPTIRQ_EVENTS) || !defined(CONFIG_DEBUG_PREEMPT)
 #define trace_preempt_enable(...)
 #define trace_preempt_disable(...)
 #define trace_preempt_enable_rcuidle(...)
diff --git a/init/main.c b/init/main.c
@@ -648,6 +648,9 @@ asmlinkage __visible void __init start_kernel(void)
 	profile_init();
 	call_function_init();
 	WARN(!irqs_disabled(), "Interrupts were enabled early\n");
+
+	lockdep_init_early();
+
 	early_boot_irqs_disabled = false;
 	local_irq_enable();
 
@@ -663,7 +666,7 @@ asmlinkage __visible void __init start_kernel(void)
 		panic("Too many boot %s vars at `%s'", panic_later,
 		      panic_param);
 
-	lockdep_info();
+	lockdep_init();
 
 	/*
 	 * Need to run this when irqs are enabled, because it wants
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
@@ -55,6 +55,7 @@
 
 #include "lockdep_internals.h"
 
+#include <trace/events/preemptirq.h>
 #define CREATE_TRACE_POINTS
 #include <trace/events/lock.h>
 
@@ -2839,10 +2840,9 @@ static void __trace_hardirqs_on_caller(unsigned long ip)
 	debug_atomic_inc(hardirqs_on_events);
 }
 
-__visible void trace_hardirqs_on_caller(unsigned long ip)
+static void lockdep_hardirqs_on(void *none, unsigned long ignore,
+				unsigned long ip)
 {
-	time_hardirqs_on(CALLER_ADDR0, ip);
-
 	if (unlikely(!debug_locks || current->lockdep_recursion))
 		return;
 
@@ -2881,23 +2881,15 @@ __visible void trace_hardirqs_on_caller(unsigned long ip)
 	__trace_hardirqs_on_caller(ip);
 	current->lockdep_recursion = 0;
 }
-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:
  */
-__visible void trace_hardirqs_off_caller(unsigned long ip)
+static void lockdep_hardirqs_off(void *none, unsigned long ignore,
+				 unsigned long ip)
 {
 	struct task_struct *curr = current;
 
-	time_hardirqs_off(CALLER_ADDR0, ip);
-
 	if (unlikely(!debug_locks || current->lockdep_recursion))
 		return;
 
@@ -2919,13 +2911,6 @@ __visible void trace_hardirqs_off_caller(unsigned long ip)
 	} 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);
 
 /*
  * Softirqs will be enabled:
@@ -4330,7 +4315,15 @@ void lockdep_reset_lock(struct lockdep_map *lock)
 	raw_local_irq_restore(flags);
 }
 
-void __init lockdep_info(void)
+void __init lockdep_init_early(void)
+{
+#ifdef CONFIG_PROVE_LOCKING
+	register_trace_prio_irq_disable(lockdep_hardirqs_off, NULL, INT_MAX);
+	register_trace_prio_irq_enable(lockdep_hardirqs_on, NULL, INT_MIN);
+#endif
+}
+
+void __init lockdep_init(void)
 {
 	printk("Lock dependency validator: Copyright (c) 2006 Red Hat, Inc., Ingo Molnar\n");
 
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
@@ -3189,7 +3189,7 @@ static inline void sched_tick_stop(int cpu) { }
 #endif
 
 #if defined(CONFIG_PREEMPT) && (defined(CONFIG_DEBUG_PREEMPT) || \
-				defined(CONFIG_PREEMPT_TRACER))
+				defined(CONFIG_TRACE_PREEMPT_TOGGLE))
 /*
  * If the value passed in is equal to the current preempt count
  * then we just disabled preemption. Start timing the latency.
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
@@ -82,6 +82,15 @@ config RING_BUFFER_ALLOW_SWAP
 	 Allow the use of ring_buffer_swap_cpu.
 	 Adds a very slight overhead to tracing when enabled.
 
+config PREEMPTIRQ_TRACEPOINTS
+	bool
+	depends on TRACE_PREEMPT_TOGGLE || TRACE_IRQFLAGS
+	select TRACING
+	default y
+	help
+	  Create preempt/irq toggle tracepoints if needed, so that other parts
+	  of the kernel can use them to generate or add hooks to them.
+
 # All tracer options should select GENERIC_TRACER. For those options that are
 # enabled by all tracers (context switch and event tracer) they select TRACING.
 # This allows those options to appear when no other tracer is selected. But the
@@ -155,18 +164,20 @@ config FUNCTION_GRAPH_TRACER
 	  the return value. This is done by setting the current return
 	  address on the current task structure into a stack of calls.
 
+config TRACE_PREEMPT_TOGGLE
+	bool
+	help
+	  Enables hooks which will be called when preemption is first disabled,
+	  and last enabled.
 
 config PREEMPTIRQ_EVENTS
 	bool "Enable trace events for preempt and irq disable/enable"
 	select TRACE_IRQFLAGS
-	depends on DEBUG_PREEMPT || !PROVE_LOCKING
-	depends on TRACING
+	select TRACE_PREEMPT_TOGGLE if PREEMPT
+	select GENERIC_TRACER
 	default n
 	help
 	  Enable tracing of disable and enable events for preemption and irqs.
-	  For tracing preempt disable/enable events, DEBUG_PREEMPT must be
-	  enabled. For tracing irq disable/enable events, PROVE_LOCKING must
-	  be disabled.
 
 config IRQSOFF_TRACER
 	bool "Interrupts-off Latency Tracer"
@@ -203,6 +214,7 @@ config PREEMPT_TRACER
 	select RING_BUFFER_ALLOW_SWAP
 	select TRACER_SNAPSHOT
 	select TRACER_SNAPSHOT_PER_CPU_SWAP
+	select TRACE_PREEMPT_TOGGLE
 	help
 	  This option measures the time spent in preemption-off critical
 	  sections, with microsecond accuracy.
diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile
@@ -41,7 +41,7 @@ obj-$(CONFIG_TRACING_MAP) += tracing_map.o
 obj-$(CONFIG_PREEMPTIRQ_DELAY_TEST) += preemptirq_delay_test.o
 obj-$(CONFIG_CONTEXT_SWITCH_TRACER) += trace_sched_switch.o
 obj-$(CONFIG_FUNCTION_TRACER) += trace_functions.o
-obj-$(CONFIG_PREEMPTIRQ_EVENTS) += trace_irqsoff.o
+obj-$(CONFIG_PREEMPTIRQ_TRACEPOINTS) += trace_preemptirq.o
 obj-$(CONFIG_IRQSOFF_TRACER) += trace_irqsoff.o
 obj-$(CONFIG_PREEMPT_TRACER) += trace_irqsoff.o
 obj-$(CONFIG_SCHED_TRACER) += trace_sched_wakeup.o
diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c
diff --git a/kernel/trace/trace_preemptirq.c b/kernel/trace/trace_preemptirq.c
