Merge branch 'tracing/ftrace' into tracing/core

Documentation/lockdep-design.txt

@@ -27,33 +27,37 @@ lock-class.
 State
 -----
 
-The validator tracks lock-class usage history into 5 separate state bits:
+The validator tracks lock-class usage history into 4n + 1 separate state bits:
 
-- 'ever held in hardirq context'                    [ == hardirq-safe   ]
-- 'ever held in softirq context'                    [ == softirq-safe   ]
-- 'ever held with hardirqs enabled'                 [ == hardirq-unsafe ]
-- 'ever held with softirqs and hardirqs enabled'    [ == softirq-unsafe ]
+- 'ever held in STATE context'
+- 'ever head as readlock in STATE context'
+- 'ever head with STATE enabled'
+- 'ever head as readlock with STATE enabled'
+
+Where STATE can be either one of (kernel/lockdep_states.h)
+ - hardirq
+ - softirq
+ - reclaim_fs
 
 - 'ever used'                                       [ == !unused        ]
 
-When locking rules are violated, these 4 state bits are presented in the
-locking error messages, inside curlies.  A contrived example:
+When locking rules are violated, these state bits are presented in the
+locking error messages, inside curlies. A contrived example:
 
    modprobe/2287 is trying to acquire lock:
-    (&sio_locks[i].lock){--..}, at: [<c02867fd>] mutex_lock+0x21/0x24
+    (&sio_locks[i].lock){-.-...}, at: [<c02867fd>] mutex_lock+0x21/0x24
 
    but task is already holding lock:
-    (&sio_locks[i].lock){--..}, at: [<c02867fd>] mutex_lock+0x21/0x24
+    (&sio_locks[i].lock){-.-...}, at: [<c02867fd>] mutex_lock+0x21/0x24
 
 
-The bit position indicates hardirq, softirq, hardirq-read,
-softirq-read respectively, and the character displayed in each
-indicates:
+The bit position indicates STATE, STATE-read, for each of the states listed
+above, and the character displayed in each indicates:
 
    '.'  acquired while irqs disabled
    '+'  acquired in irq context
    '-'  acquired with irqs enabled
-   '?' read acquired in irq context with irqs enabled.
+   '?'  acquired in irq context with irqs enabled.
 
 Unused mutexes cannot be part of the cause of an error.
 

include/linux/lockdep.h

@@ -20,43 +20,10 @@ struct lockdep_map;
 #include <linux/stacktrace.h>
 
 /*
- * Lock-class usage-state bits:
+ * We'd rather not expose kernel/lockdep_states.h this wide, but we do need
+ * the total number of states... :-(
  */
-enum lock_usage_bit
-{
-	LOCK_USED = 0,
-	LOCK_USED_IN_HARDIRQ,
-	LOCK_USED_IN_SOFTIRQ,
-	LOCK_ENABLED_SOFTIRQS,
-	LOCK_ENABLED_HARDIRQS,
-	LOCK_USED_IN_HARDIRQ_READ,
-	LOCK_USED_IN_SOFTIRQ_READ,
-	LOCK_ENABLED_SOFTIRQS_READ,
-	LOCK_ENABLED_HARDIRQS_READ,
-	LOCK_USAGE_STATES
-};
-
-/*
- * Usage-state bitmasks:
- */
-#define LOCKF_USED			(1 << LOCK_USED)
-#define LOCKF_USED_IN_HARDIRQ		(1 << LOCK_USED_IN_HARDIRQ)
-#define LOCKF_USED_IN_SOFTIRQ		(1 << LOCK_USED_IN_SOFTIRQ)
-#define LOCKF_ENABLED_HARDIRQS		(1 << LOCK_ENABLED_HARDIRQS)
-#define LOCKF_ENABLED_SOFTIRQS		(1 << LOCK_ENABLED_SOFTIRQS)
-
-#define LOCKF_ENABLED_IRQS (LOCKF_ENABLED_HARDIRQS | LOCKF_ENABLED_SOFTIRQS)
-#define LOCKF_USED_IN_IRQ (LOCKF_USED_IN_HARDIRQ | LOCKF_USED_IN_SOFTIRQ)
-
-#define LOCKF_USED_IN_HARDIRQ_READ	(1 << LOCK_USED_IN_HARDIRQ_READ)
-#define LOCKF_USED_IN_SOFTIRQ_READ	(1 << LOCK_USED_IN_SOFTIRQ_READ)
-#define LOCKF_ENABLED_HARDIRQS_READ	(1 << LOCK_ENABLED_HARDIRQS_READ)
-#define LOCKF_ENABLED_SOFTIRQS_READ	(1 << LOCK_ENABLED_SOFTIRQS_READ)
-
-#define LOCKF_ENABLED_IRQS_READ \
-		(LOCKF_ENABLED_HARDIRQS_READ | LOCKF_ENABLED_SOFTIRQS_READ)
-#define LOCKF_USED_IN_IRQ_READ \
-		(LOCKF_USED_IN_HARDIRQ_READ | LOCKF_USED_IN_SOFTIRQ_READ)
+#define XXX_LOCK_USAGE_STATES		(1+3*4)
 
 #define MAX_LOCKDEP_SUBCLASSES		8UL
 
@@ -97,7 +64,7 @@ struct lock_class {
 	 * IRQ/softirq usage tracking bits:
 	 */
 	unsigned long			usage_mask;
-	struct stack_trace		usage_traces[LOCK_USAGE_STATES];
+	struct stack_trace		usage_traces[XXX_LOCK_USAGE_STATES];
 
 	/*
 	 * These fields represent a directed graph of lock dependencies,
@@ -324,7 +291,11 @@ static inline void lock_set_subclass(struct lockdep_map *lock,
 	lock_set_class(lock, lock->name, lock->key, subclass, ip);
 }
 
-# define INIT_LOCKDEP				.lockdep_recursion = 0,
+extern void lockdep_set_current_reclaim_state(gfp_t gfp_mask);
+extern void lockdep_clear_current_reclaim_state(void);
+extern void lockdep_trace_alloc(gfp_t mask);
+
+# define INIT_LOCKDEP				.lockdep_recursion = 0, .lockdep_reclaim_gfp = 0,
 
 #define lockdep_depth(tsk)	(debug_locks ? (tsk)->lockdep_depth : 0)
 
@@ -342,6 +313,9 @@ static inline void lockdep_on(void)
 # define lock_release(l, n, 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_set_current_reclaim_state(g)	do { } while (0)
+# define lockdep_clear_current_reclaim_state()	do { } while (0)
+# define lockdep_trace_alloc(g)			do { } while (0)
 # define lockdep_init()				do { } while (0)
 # define lockdep_info()				do { } while (0)
 # define lockdep_init_map(lock, name, key, sub) \

include/linux/mutex.h

@@ -50,8 +50,10 @@ struct mutex {
 	atomic_t		count;
 	spinlock_t		wait_lock;
 	struct list_head	wait_list;
-#ifdef CONFIG_DEBUG_MUTEXES
+#if defined(CONFIG_DEBUG_MUTEXES) || defined(CONFIG_SMP)
 	struct thread_info	*owner;
+#endif
+#ifdef CONFIG_DEBUG_MUTEXES
 	const char 		*name;
 	void			*magic;
 #endif
@@ -68,7 +70,6 @@ struct mutex_waiter {
 	struct list_head	list;
 	struct task_struct	*task;
 #ifdef CONFIG_DEBUG_MUTEXES
-	struct mutex		*lock;
 	void			*magic;
 #endif
 };

include/linux/ring_buffer.h

@@ -121,6 +121,9 @@ unsigned long ring_buffer_overrun_cpu(struct ring_buffer *buffer, int cpu);
 u64 ring_buffer_time_stamp(int cpu);
 void ring_buffer_normalize_time_stamp(int cpu, u64 *ts);
 
+size_t ring_buffer_page_len(void *page);
+
+
 /*
  * The below functions are fine to use outside the tracing facility.
  */
@@ -138,8 +141,8 @@ static inline int tracing_is_on(void) { return 0; }
 
 void *ring_buffer_alloc_read_page(struct ring_buffer *buffer);
 void ring_buffer_free_read_page(struct ring_buffer *buffer, void *data);
-int ring_buffer_read_page(struct ring_buffer *buffer,
-			  void **data_page, int cpu, int full);
+int ring_buffer_read_page(struct ring_buffer *buffer, void **data_page,
+			  size_t len, int cpu, int full);
 
 enum ring_buffer_flags {
 	RB_FL_OVERWRITE		= 1 << 0,

include/linux/sched.h

@@ -333,7 +333,9 @@ extern signed long schedule_timeout(signed long timeout);
 extern signed long schedule_timeout_interruptible(signed long timeout);
 extern signed long schedule_timeout_killable(signed long timeout);
 extern signed long schedule_timeout_uninterruptible(signed long timeout);
+asmlinkage void __schedule(void);
 asmlinkage void schedule(void);
+extern int mutex_spin_on_owner(struct mutex *lock, struct thread_info *owner);
 
 struct nsproxy;
 struct user_namespace;
@@ -1330,6 +1332,7 @@ struct task_struct {
 	int lockdep_depth;
 	unsigned int lockdep_recursion;
 	struct held_lock held_locks[MAX_LOCK_DEPTH];
+	gfp_t lockdep_reclaim_gfp;
 #endif
 
 /* journalling filesystem info */

include/linux/timer.h

@@ -5,6 +5,7 @@
 #include <linux/ktime.h>
 #include <linux/stddef.h>
 #include <linux/debugobjects.h>
+#include <linux/stringify.h>
 
 struct tvec_base;
 
@@ -21,52 +22,126 @@ struct timer_list {
 	char start_comm[16];
 	int start_pid;
 #endif
+#ifdef CONFIG_LOCKDEP
+	struct lockdep_map lockdep_map;
+#endif
 };
 
 extern struct tvec_base boot_tvec_bases;
 
+#ifdef CONFIG_LOCKDEP
+/*
+ * NB: because we have to copy the lockdep_map, setting the lockdep_map key
+ * (second argument) here is required, otherwise it could be initialised to
+ * the copy of the lockdep_map later! We use the pointer to and the string
+ * "<file>:<line>" as the key resp. the name of the lockdep_map.
+ */
+#define __TIMER_LOCKDEP_MAP_INITIALIZER(_kn)				\
+	.lockdep_map = STATIC_LOCKDEP_MAP_INIT(_kn, &_kn),
+#else
+#define __TIMER_LOCKDEP_MAP_INITIALIZER(_kn)
+#endif
+
 #define TIMER_INITIALIZER(_function, _expires, _data) {		\
 		.entry = { .prev = TIMER_ENTRY_STATIC },	\
 		.function = (_function),			\
 		.expires = (_expires),				\
 		.data = (_data),				\
 		.base = &boot_tvec_bases,			\
+		__TIMER_LOCKDEP_MAP_INITIALIZER(		\
+			__FILE__ ":" __stringify(__LINE__))	\
 	}
 
 #define DEFINE_TIMER(_name, _function, _expires, _data)		\
 	struct timer_list _name =				\
 		TIMER_INITIALIZER(_function, _expires, _data)
 
-void init_timer(struct timer_list *timer);
-void init_timer_deferrable(struct timer_list *timer);
+void init_timer_key(struct timer_list *timer,
+		    const char *name,
+		    struct lock_class_key *key);
+void init_timer_deferrable_key(struct timer_list *timer,
+			       const char *name,
+			       struct lock_class_key *key);
+
+#ifdef CONFIG_LOCKDEP
+#define init_timer(timer)						\
+	do {								\
+		static struct lock_class_key __key;			\
+		init_timer_key((timer), #timer, &__key);		\
+	} while (0)
+
+#define init_timer_deferrable(timer)					\
+	do {								\
+		static struct lock_class_key __key;			\
+		init_timer_deferrable_key((timer), #timer, &__key);	\
+	} while (0)
+
+#define init_timer_on_stack(timer)					\
+	do {								\
+		static struct lock_class_key __key;			\
+		init_timer_on_stack_key((timer), #timer, &__key);	\
+	} while (0)
+
+#define setup_timer(timer, fn, data)					\
+	do {								\
+		static struct lock_class_key __key;			\
+		setup_timer_key((timer), #timer, &__key, (fn), (data));\
+	} while (0)
+
+#define setup_timer_on_stack(timer, fn, data)				\
+	do {								\
+		static struct lock_class_key __key;			\
+		setup_timer_on_stack_key((timer), #timer, &__key,	\
+					 (fn), (data));			\
+	} while (0)
+#else
+#define init_timer(timer)\
+	init_timer_key((timer), NULL, NULL)
+#define init_timer_deferrable(timer)\
+	init_timer_deferrable_key((timer), NULL, NULL)
+#define init_timer_on_stack(timer)\
+	init_timer_on_stack_key((timer), NULL, NULL)
+#define setup_timer(timer, fn, data)\
+	setup_timer_key((timer), NULL, NULL, (fn), (data))
+#define setup_timer_on_stack(timer, fn, data)\
+	setup_timer_on_stack_key((timer), NULL, NULL, (fn), (data))
+#endif
 
 #ifdef CONFIG_DEBUG_OBJECTS_TIMERS
-extern void init_timer_on_stack(struct timer_list *timer);
+extern void init_timer_on_stack_key(struct timer_list *timer,
+				    const char *name,
+				    struct lock_class_key *key);
 extern void destroy_timer_on_stack(struct timer_list *timer);
 #else
 static inline void destroy_timer_on_stack(struct timer_list *timer) { }
-static inline void init_timer_on_stack(struct timer_list *timer)
+static inline void init_timer_on_stack_key(struct timer_list *timer,
+					   const char *name,
+					   struct lock_class_key *key)
 {
-	init_timer(timer);
+	init_timer_key(timer, name, key);
 }
 #endif
 
-static inline void setup_timer(struct timer_list * timer,
+static inline void setup_timer_key(struct timer_list * timer,
+				const char *name,
+				struct lock_class_key *key,
 				void (*function)(unsigned long),
 				unsigned long data)
 {
 	timer->function = function;
 	timer->data = data;
-	init_timer(timer);
+	init_timer_key(timer, name, key);
 }
 
-static inline void setup_timer_on_stack(struct timer_list *timer,
+static inline void setup_timer_on_stack_key(struct timer_list *timer,
+					const char *name,
+					struct lock_class_key *key,
 					void (*function)(unsigned long),
 					unsigned long data)
 {
 	timer->function = function;
 	timer->data = data;
-	init_timer_on_stack(timer);
+	init_timer_on_stack_key(timer, name, key);
 }
 
 /**

include/trace/lockdep.h

@@ -0,0 +1,9 @@
+#ifndef _TRACE_LOCKDEP_H
+#define _TRACE_LOCKDEP_H
+
+#include <linux/lockdep.h>
+#include <linux/tracepoint.h>
+
+#include <trace/lockdep_event_types.h>
+
+#endif

include/trace/lockdep_event_types.h

@@ -0,0 +1,44 @@
+
+#ifndef TRACE_EVENT_FORMAT
+# error Do not include this file directly.
+# error Unless you know what you are doing.
+#endif
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM lock
+
+#ifdef CONFIG_LOCKDEP
+
+TRACE_FORMAT(lock_acquire,
+	TPPROTO(struct lockdep_map *lock, unsigned int subclass,
+		int trylock, int read, int check,
+		struct lockdep_map *next_lock, unsigned long ip),
+	TPARGS(lock, subclass, trylock, read, check, next_lock, ip),
+	TPFMT("%s%s%s", trylock ? "try " : "",
+		read ? "read " : "", lock->name)
+	);
+
+TRACE_FORMAT(lock_release,
+	TPPROTO(struct lockdep_map *lock, int nested, unsigned long ip),
+	TPARGS(lock, nested, ip),
+	TPFMT("%s", lock->name)
+	);
+
+#ifdef CONFIG_LOCK_STAT
+
+TRACE_FORMAT(lock_contended,
+	TPPROTO(struct lockdep_map *lock, unsigned long ip),
+	TPARGS(lock, ip),
+	TPFMT("%s", lock->name)
+	);
+
+TRACE_FORMAT(lock_acquired,
+	TPPROTO(struct lockdep_map *lock, unsigned long ip),
+	TPARGS(lock, ip),
+	TPFMT("%s", lock->name)
+	);
+
+#endif
+#endif
+
+#undef TRACE_SYSTEM

include/trace/trace_event_types.h

@@ -2,3 +2,4 @@
 
 #include <trace/sched_event_types.h>
 #include <trace/irq_event_types.h>
+#include <trace/lockdep_event_types.h>

include/trace/trace_events.h

@@ -2,3 +2,4 @@
 
 #include <trace/sched.h>
 #include <trace/irq.h>
+#include <trace/lockdep.h>