[PATCH] lockdep: irqtrace subsystem, core

Accurate hard-IRQ-flags and softirq-flags state tracing.

This allows us to attach extra functionality to IRQ flags on/off
events (such as trace-on/off).

Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Arjan van de Ven <arjan@linux.intel.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

10 files changed, 313 insertions, 30 deletions

diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index 525baab..027728b 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -429,7 +429,7 @@ void do_softirq(void)
 		local_bh_disable();
 		do_softirq_onstack();
 		account_system_vtime(current);
-		__local_bh_enable();
+		_local_bh_enable();
 	}
 
 	local_irq_restore(flags);
diff --git a/include/asm-powerpc/irqflags.h b/include/asm-powerpc/irqflags.h
new file mode 100644
index 0000000..7970cba
--- /dev/null
+++ b/include/asm-powerpc/irqflags.h
@@ -0,0 +1,31 @@
+/*
+ * include/asm-powerpc/irqflags.h
+ *
+ * IRQ flags handling
+ *
+ * This file gets included from lowlevel asm headers too, to provide
+ * wrapped versions of the local_irq_*() APIs, based on the
+ * raw_local_irq_*() macros from the lowlevel headers.
+ */
+#ifndef _ASM_IRQFLAGS_H
+#define _ASM_IRQFLAGS_H
+
+/*
+ * Get definitions for raw_local_save_flags(x), etc.
+ */
+#include <asm-powerpc/hw_irq.h>
+
+/*
+ * Do the CPU's IRQ-state tracing from assembly code. We call a
+ * C function, so save all the C-clobbered registers:
+ */
+#ifdef CONFIG_TRACE_IRQFLAGS
+
+#error No support on PowerPC yet for CONFIG_TRACE_IRQFLAGS
+
+#else
+# define TRACE_IRQS_ON
+# define TRACE_IRQS_OFF
+#endif
+
+#endif
diff --git a/include/linux/hardirq.h b/include/linux/hardirq.h
index 114ae58..b1d4332 100644
--- a/include/linux/hardirq.h
+++ b/include/linux/hardirq.h
@@ -86,9 +86,6 @@ extern void synchronize_irq(unsigned int irq);
 # define synchronize_irq(irq)	barrier()
 #endif
 
-#define nmi_enter()		irq_enter()
-#define nmi_exit()		sub_preempt_count(HARDIRQ_OFFSET)
-
 struct task_struct;
 
 #ifndef CONFIG_VIRT_CPU_ACCOUNTING
@@ -97,12 +94,35 @@ static inline void account_system_vtime(struct task_struct *tsk)
 }
 #endif
 
+/*
+ * It is safe to do non-atomic ops on ->hardirq_context,
+ * because NMI handlers may not preempt and the ops are
+ * always balanced, so the interrupted value of ->hardirq_context
+ * will always be restored.
+ */
 #define irq_enter()					\
 	do {						\
 		account_system_vtime(current);		\
 		add_preempt_count(HARDIRQ_OFFSET);	\
+		trace_hardirq_enter();			\
+	} while (0)
+
+/*
+ * Exit irq context without processing softirqs:
+ */
+#define __irq_exit()					\
+	do {						\
+		trace_hardirq_exit();			\
+		account_system_vtime(current);		\
+		sub_preempt_count(HARDIRQ_OFFSET);	\
 	} while (0)
 
+/*
+ * Exit irq context and process softirqs if needed:
+ */
 extern void irq_exit(void);
 
+#define nmi_enter()		irq_enter()
+#define nmi_exit()		__irq_exit()
+
 #endif /* LINUX_HARDIRQ_H */
diff --git a/include/linux/init_task.h b/include/linux/init_task.h
index 1b7bb37..444a3ae 100644
--- a/include/linux/init_task.h
+++ b/include/linux/init_task.h
@@ -3,6 +3,7 @@
 
 #include <linux/file.h>
 #include <linux/rcupdate.h>
+#include <linux/irqflags.h>
 
 #define INIT_FDTABLE \
 {							\
@@ -124,6 +125,7 @@ extern struct group_info init_groups;
 	.cpu_timers	= INIT_CPU_TIMERS(tsk.cpu_timers),		\
 	.fs_excl	= ATOMIC_INIT(0),				\
 	.pi_lock	= SPIN_LOCK_UNLOCKED,				\
+	INIT_TRACE_IRQFLAGS						\
 }
 
 
diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
index 73463fb..d5afee9 100644
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -10,6 +10,7 @@
 #include <linux/irqreturn.h>
 #include <linux/hardirq.h>
 #include <linux/sched.h>
+#include <linux/irqflags.h>
 #include <asm/atomic.h>
 #include <asm/ptrace.h>
 #include <asm/system.h>
@@ -199,13 +200,11 @@ static inline void __deprecated save_and_cli(unsigned long *x)
 #define save_and_cli(x)	save_and_cli(&x)
 #endif /* CONFIG_SMP */
 
-/* SoftIRQ primitives.  */
-#define local_bh_disable() \
-		do { add_preempt_count(SOFTIRQ_OFFSET); barrier(); } while (0)
-#define __local_bh_enable() \
-		do { barrier(); sub_preempt_count(SOFTIRQ_OFFSET); } while (0)
-
+extern void local_bh_disable(void);
+extern void __local_bh_enable(void);
+extern void _local_bh_enable(void);
 extern void local_bh_enable(void);
+extern void local_bh_enable_ip(unsigned long ip);
 
 /* PLEASE, avoid to allocate new softirqs, if you need not _really_ high
    frequency threaded job scheduling. For almost all the purposes
diff --git a/include/linux/irqflags.h b/include/linux/irqflags.h
new file mode 100644
index 0000000..412e025
--- /dev/null
+++ b/include/linux/irqflags.h
@@ -0,0 +1,96 @@
+/*
+ * include/linux/irqflags.h
+ *
+ * IRQ flags tracing: follow the state of the hardirq and softirq flags and
+ * provide callbacks for transitions between ON and OFF states.
+ *
+ * This file gets included from lowlevel asm headers too, to provide
+ * wrapped versions of the local_irq_*() APIs, based on the
+ * raw_local_irq_*() macros from the lowlevel headers.
+ */
+#ifndef _LINUX_TRACE_IRQFLAGS_H
+#define _LINUX_TRACE_IRQFLAGS_H
+
+#ifdef CONFIG_TRACE_IRQFLAGS
+  extern void trace_hardirqs_on(void);
+  extern void trace_hardirqs_off(void);
+  extern void trace_softirqs_on(unsigned long ip);
+  extern void trace_softirqs_off(unsigned long ip);
+# define trace_hardirq_context(p)	((p)->hardirq_context)
+# define trace_softirq_context(p)	((p)->softirq_context)
+# define trace_hardirqs_enabled(p)	((p)->hardirqs_enabled)
+# define trace_softirqs_enabled(p)	((p)->softirqs_enabled)
+# define trace_hardirq_enter()	do { current->hardirq_context++; } while (0)
+# define trace_hardirq_exit()	do { current->hardirq_context--; } while (0)
+# define trace_softirq_enter()	do { current->softirq_context++; } while (0)
+# define trace_softirq_exit()	do { current->softirq_context--; } while (0)
+# define INIT_TRACE_IRQFLAGS	.softirqs_enabled = 1,
+#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
+# define trace_softirqs_enabled(p)	0
+# define trace_hardirq_enter()		do { } while (0)
+# define trace_hardirq_exit()		do { } while (0)
+# define trace_softirq_enter()		do { } while (0)
+# define trace_softirq_exit()		do { } while (0)
+# define INIT_TRACE_IRQFLAGS
+#endif
+
+#ifdef CONFIG_TRACE_IRQFLAGS_SUPPORT
+
+#include <asm/irqflags.h>
+
+#define local_irq_enable() \
+	do { trace_hardirqs_on(); raw_local_irq_enable(); } while (0)
+#define local_irq_disable() \
+	do { raw_local_irq_disable(); trace_hardirqs_off(); } while (0)
+#define local_irq_save(flags) \
+	do { raw_local_irq_save(flags); trace_hardirqs_off(); } while (0)
+
+#define local_irq_restore(flags)				\
+	do {							\
+		if (raw_irqs_disabled_flags(flags)) {		\
+			raw_local_irq_restore(flags);		\
+			trace_hardirqs_off();			\
+		} else {					\
+			trace_hardirqs_on();			\
+			raw_local_irq_restore(flags);		\
+		}						\
+	} while (0)
+#else /* !CONFIG_TRACE_IRQFLAGS_SUPPORT */
+/*
+ * The local_irq_*() APIs are equal to the raw_local_irq*()
+ * if !TRACE_IRQFLAGS.
+ */
+# define raw_local_irq_disable()	local_irq_disable()
+# define raw_local_irq_enable()		local_irq_enable()
+# define raw_local_irq_save(flags)	local_irq_save(flags)
+# define raw_local_irq_restore(flags)	local_irq_restore(flags)
+#endif /* CONFIG_TRACE_IRQFLAGS_SUPPORT */
+
+#ifdef CONFIG_TRACE_IRQFLAGS_SUPPORT
+#define safe_halt()						\
+	do {							\
+		trace_hardirqs_on();				\
+		raw_safe_halt();				\
+	} while (0)
+
+#define local_save_flags(flags)		raw_local_save_flags(flags)
+
+#define irqs_disabled()						\
+({								\
+	unsigned long flags;					\
+								\
+	raw_local_save_flags(flags);				\
+	raw_irqs_disabled_flags(flags);				\
+})
+
+#define irqs_disabled_flags(flags)	raw_irqs_disabled_flags(flags)
+#endif		/* CONFIG_X86 */
+
+#endif
diff --git a/include/linux/sched.h b/include/linux/sched.h
index bdabeee..ad7a890 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -871,6 +871,21 @@ struct task_struct {
 	/* mutex deadlock detection */
 	struct mutex_waiter *blocked_on;
 #endif
+#ifdef CONFIG_TRACE_IRQFLAGS
+	unsigned int irq_events;
+	int hardirqs_enabled;
+	unsigned long hardirq_enable_ip;
+	unsigned int hardirq_enable_event;
+	unsigned long hardirq_disable_ip;
+	unsigned int hardirq_disable_event;
+	int softirqs_enabled;
+	unsigned long softirq_disable_ip;
+	unsigned int softirq_disable_event;
+	unsigned long softirq_enable_ip;
+	unsigned int softirq_enable_event;
+	int hardirq_context;
+	int softirq_context;
+#endif
 
 /* journalling filesystem info */
 	void *journal_info;
diff --git a/kernel/fork.c b/kernel/fork.c
index 1cd46a4..b7db7fb 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -968,6 +968,10 @@ static task_t *copy_process(unsigned long clone_flags,
 	if (!p)
 		goto fork_out;
 
+#ifdef CONFIG_TRACE_IRQFLAGS
+	DEBUG_LOCKS_WARN_ON(!p->hardirqs_enabled);
+	DEBUG_LOCKS_WARN_ON(!p->softirqs_enabled);
+#endif
 	retval = -EAGAIN;
 	if (atomic_read(&p->user->processes) >=
 			p->signal->rlim[RLIMIT_NPROC].rlim_cur) {
@@ -1042,6 +1046,21 @@ static task_t *copy_process(unsigned long clone_flags,
  	}
 	mpol_fix_fork_child_flag(p);
 #endif
+#ifdef CONFIG_TRACE_IRQFLAGS
+	p->irq_events = 0;
+	p->hardirqs_enabled = 0;
+	p->hardirq_enable_ip = 0;
+	p->hardirq_enable_event = 0;
+	p->hardirq_disable_ip = _THIS_IP_;
+	p->hardirq_disable_event = 0;
+	p->softirqs_enabled = 1;
+	p->softirq_enable_ip = _THIS_IP_;
+	p->softirq_enable_event = 0;
+	p->softirq_disable_ip = 0;
+	p->softirq_disable_event = 0;
+	p->hardirq_context = 0;
+	p->softirq_context = 0;
+#endif
 
 	rt_mutex_init_task(p);
 
diff --git a/kernel/sched.c b/kernel/sched.c
index 48c1faa..9118299 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -4462,7 +4462,9 @@ int __sched cond_resched_softirq(void)
 	BUG_ON(!in_softirq());
 
 	if (need_resched() && __resched_legal()) {
-		__local_bh_enable();
+		raw_local_irq_disable();
+		_local_bh_enable();
+		raw_local_irq_enable();
 		__cond_resched();
 		local_bh_disable();
 		return 1;
diff --git a/kernel/softirq.c b/kernel/softirq.c
index 8f03e3b..584609b 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -62,6 +62,119 @@ static inline void wakeup_softirqd(void)
 }
 
 /*
+ * This one is for softirq.c-internal use,
+ * where hardirqs are disabled legitimately:
+ */
+static void __local_bh_disable(unsigned long ip)
+{
+	unsigned long flags;
+
+	WARN_ON_ONCE(in_irq());
+
+	raw_local_irq_save(flags);
+	add_preempt_count(SOFTIRQ_OFFSET);
+	/*
+	 * Were softirqs turned off above:
+	 */
+	if (softirq_count() == SOFTIRQ_OFFSET)
+		trace_softirqs_off(ip);
+	raw_local_irq_restore(flags);
+}
+
+void local_bh_disable(void)
+{
+	__local_bh_disable((unsigned long)__builtin_return_address(0));
+}
+
+EXPORT_SYMBOL(local_bh_disable);
+
+void __local_bh_enable(void)
+{
+	WARN_ON_ONCE(in_irq());
+
+	/*
+	 * softirqs should never be enabled by __local_bh_enable(),
+	 * it always nests inside local_bh_enable() sections:
+	 */
+	WARN_ON_ONCE(softirq_count() == SOFTIRQ_OFFSET);
+
+	sub_preempt_count(SOFTIRQ_OFFSET);
+}
+EXPORT_SYMBOL_GPL(__local_bh_enable);
+
+/*
+ * Special-case - softirqs can safely be enabled in
+ * cond_resched_softirq(), or by __do_softirq(),
+ * without processing still-pending softirqs:
+ */
+void _local_bh_enable(void)
+{
+	WARN_ON_ONCE(in_irq());
+	WARN_ON_ONCE(!irqs_disabled());
+
+	if (softirq_count() == SOFTIRQ_OFFSET)
+		trace_softirqs_on((unsigned long)__builtin_return_address(0));
+	sub_preempt_count(SOFTIRQ_OFFSET);
+}
+
+EXPORT_SYMBOL(_local_bh_enable);
+
+void local_bh_enable(void)
+{
+	unsigned long flags;
+
+	WARN_ON_ONCE(in_irq());
+	WARN_ON_ONCE(irqs_disabled());
+
+	local_irq_save(flags);
+	/*
+	 * Are softirqs going to be turned on now:
+	 */
+	if (softirq_count() == SOFTIRQ_OFFSET)
+		trace_softirqs_on((unsigned long)__builtin_return_address(0));
+	/*
+	 * Keep preemption disabled until we are done with
+	 * softirq processing:
+ 	 */
+ 	sub_preempt_count(SOFTIRQ_OFFSET - 1);
+
+	if (unlikely(!in_interrupt() && local_softirq_pending()))
+		do_softirq();
+
+	dec_preempt_count();
+	local_irq_restore(flags);
+	preempt_check_resched();
+}
+EXPORT_SYMBOL(local_bh_enable);
+
+void local_bh_enable_ip(unsigned long ip)
+{
+	unsigned long flags;
+
+	WARN_ON_ONCE(in_irq());
+
+	local_irq_save(flags);
+	/*
+	 * Are softirqs going to be turned on now:
+	 */
+	if (softirq_count() == SOFTIRQ_OFFSET)
+		trace_softirqs_on(ip);
+	/*
+	 * Keep preemption disabled until we are done with
+	 * softirq processing:
+ 	 */
+ 	sub_preempt_count(SOFTIRQ_OFFSET - 1);
+
+	if (unlikely(!in_interrupt() && local_softirq_pending()))
+		do_softirq();
+
+	dec_preempt_count();
+	local_irq_restore(flags);
+	preempt_check_resched();
+}
+EXPORT_SYMBOL(local_bh_enable_ip);
+
+/*
  * We restart softirq processing MAX_SOFTIRQ_RESTART times,
  * and we fall back to softirqd after that.
  *
@@ -80,8 +193,9 @@ asmlinkage void __do_softirq(void)
 	int cpu;
 
 	pending = local_softirq_pending();
+	__local_bh_disable((unsigned long)__builtin_return_address(0));
+	trace_softirq_enter();
 
-	local_bh_disable();
 	cpu = smp_processor_id();
 restart:
 	/* Reset the pending bitmask before enabling irqs */
@@ -109,7 +223,8 @@ restart:
 	if (pending)
 		wakeup_softirqd();
 
-	__local_bh_enable();
+	trace_softirq_exit();
+	_local_bh_enable();
 }
 
 #ifndef __ARCH_HAS_DO_SOFTIRQ
@@ -136,23 +251,6 @@ EXPORT_SYMBOL(do_softirq);
 
 #endif
 
-void local_bh_enable(void)
-{
-	WARN_ON(irqs_disabled());
-	/*
-	 * Keep preemption disabled until we are done with
-	 * softirq processing:
- 	 */
- 	sub_preempt_count(SOFTIRQ_OFFSET - 1);
-
-	if (unlikely(!in_interrupt() && local_softirq_pending()))
-		do_softirq();
-
-	dec_preempt_count();
-	preempt_check_resched();
-}
-EXPORT_SYMBOL(local_bh_enable);
-
 #ifdef __ARCH_IRQ_EXIT_IRQS_DISABLED
 # define invoke_softirq()	__do_softirq()
 #else
@@ -165,6 +263,7 @@ EXPORT_SYMBOL(local_bh_enable);
 void irq_exit(void)
 {
 	account_system_vtime(current);
+	trace_hardirq_exit();
 	sub_preempt_count(IRQ_EXIT_OFFSET);
 	if (!in_interrupt() && local_softirq_pending())
 		invoke_softirq();