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
+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

+#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

+
+#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>

kernel/lockdep_internals.h

@@ -6,6 +6,45 @@
  * lockdep subsystem internal functions and variables.
  */
 
+/*
+ * Lock-class usage-state bits:
+ */
+enum lock_usage_bit {
+#define LOCKDEP_STATE(__STATE)		\
+	LOCK_USED_IN_##__STATE,		\
+	LOCK_USED_IN_##__STATE##_READ,	\
+	LOCK_ENABLED_##__STATE,		\
+	LOCK_ENABLED_##__STATE##_READ,
+#include "lockdep_states.h"
+#undef LOCKDEP_STATE
+	LOCK_USED,
+	LOCK_USAGE_STATES
+};
+
+/*
+ * Usage-state bitmasks:
+ */
+#define __LOCKF(__STATE)	LOCKF_##__STATE = (1 << LOCK_##__STATE),
+
+enum {
+#define LOCKDEP_STATE(__STATE)						\
+	__LOCKF(USED_IN_##__STATE)					\
+	__LOCKF(USED_IN_##__STATE##_READ)				\
+	__LOCKF(ENABLED_##__STATE)					\
+	__LOCKF(ENABLED_##__STATE##_READ)
+#include "lockdep_states.h"
+#undef LOCKDEP_STATE
+	__LOCKF(USED)
+};
+
+#define LOCKF_ENABLED_IRQ (LOCKF_ENABLED_HARDIRQ | LOCKF_ENABLED_SOFTIRQ)
+#define LOCKF_USED_IN_IRQ (LOCKF_USED_IN_HARDIRQ | LOCKF_USED_IN_SOFTIRQ)
+
+#define LOCKF_ENABLED_IRQ_READ \
+		(LOCKF_ENABLED_HARDIRQ_READ | LOCKF_ENABLED_SOFTIRQ_READ)
+#define LOCKF_USED_IN_IRQ_READ \
+		(LOCKF_USED_IN_HARDIRQ_READ | LOCKF_USED_IN_SOFTIRQ_READ)
+
 /*
  * MAX_LOCKDEP_ENTRIES is the maximum number of lock dependencies
  * we track.
@@ -31,8 +70,10 @@
 extern struct list_head all_lock_classes;
 extern struct lock_chain lock_chains[];
 
-extern void
-get_usage_chars(struct lock_class *class, char *c1, char *c2, char *c3, char *c4);
+#define LOCK_USAGE_CHARS (1+LOCK_USAGE_STATES/2)
+
+extern void get_usage_chars(struct lock_class *class,
+			    char usage[LOCK_USAGE_CHARS]);
 
 extern const char * __get_key_name(struct lockdep_subclass_key *key, char *str);
 

kernel/lockdep_proc.c

@@ -84,7 +84,7 @@ static int l_show(struct seq_file *m, void *v)
 {
 	struct lock_class *class = v;
 	struct lock_list *entry;
-	char c1, c2, c3, c4;
+	char usage[LOCK_USAGE_CHARS];
 
 	if (v == SEQ_START_TOKEN) {
 		seq_printf(m, "all lock classes:\n");
@@ -100,8 +100,8 @@ static int l_show(struct seq_file *m, void *v)
 	seq_printf(m, " BD:%5ld", lockdep_count_backward_deps(class));
 #endif
 
-	get_usage_chars(class, &c1, &c2, &c3, &c4);
-	seq_printf(m, " %c%c%c%c", c1, c2, c3, c4);
+	get_usage_chars(class, usage);
+	seq_printf(m, " %s", usage);
 
 	seq_printf(m, ": ");
 	print_name(m, class);
@@ -300,27 +300,27 @@ static int lockdep_stats_show(struct seq_file *m, void *v)
 			nr_uncategorized++;
 		if (class->usage_mask & LOCKF_USED_IN_IRQ)
 			nr_irq_safe++;
-		if (class->usage_mask & LOCKF_ENABLED_IRQS)
+		if (class->usage_mask & LOCKF_ENABLED_IRQ)
 			nr_irq_unsafe++;
 		if (class->usage_mask & LOCKF_USED_IN_SOFTIRQ)
 			nr_softirq_safe++;
-		if (class->usage_mask & LOCKF_ENABLED_SOFTIRQS)
+		if (class->usage_mask & LOCKF_ENABLED_SOFTIRQ)
 			nr_softirq_unsafe++;
 		if (class->usage_mask & LOCKF_USED_IN_HARDIRQ)
 			nr_hardirq_safe++;
-		if (class->usage_mask & LOCKF_ENABLED_HARDIRQS)
+		if (class->usage_mask & LOCKF_ENABLED_HARDIRQ)
 			nr_hardirq_unsafe++;
 		if (class->usage_mask & LOCKF_USED_IN_IRQ_READ)
 			nr_irq_read_safe++;
-		if (class->usage_mask & LOCKF_ENABLED_IRQS_READ)
+		if (class->usage_mask & LOCKF_ENABLED_IRQ_READ)
 			nr_irq_read_unsafe++;
 		if (class->usage_mask & LOCKF_USED_IN_SOFTIRQ_READ)
 			nr_softirq_read_safe++;
-		if (class->usage_mask & LOCKF_ENABLED_SOFTIRQS_READ)
+		if (class->usage_mask & LOCKF_ENABLED_SOFTIRQ_READ)
 			nr_softirq_read_unsafe++;
 		if (class->usage_mask & LOCKF_USED_IN_HARDIRQ_READ)
 			nr_hardirq_read_safe++;
-		if (class->usage_mask & LOCKF_ENABLED_HARDIRQS_READ)
+		if (class->usage_mask & LOCKF_ENABLED_HARDIRQ_READ)
 			nr_hardirq_read_unsafe++;
 
 #ifdef CONFIG_PROVE_LOCKING
@@ -601,6 +601,10 @@ static void seq_stats(struct seq_file *m, struct lock_stat_data *data)
 static void seq_header(struct seq_file *m)
 {
 	seq_printf(m, "lock_stat version 0.3\n");
+
+	if (unlikely(!debug_locks))
+		seq_printf(m, "*WARNING* lock debugging disabled!! - possibly due to a lockdep warning\n");
+
 	seq_line(m, '-', 0, 40 + 1 + 10 * (14 + 1));
 	seq_printf(m, "%40s %14s %14s %14s %14s %14s %14s %14s %14s "
 			"%14s %14s\n",

kernel/lockdep_states.h

+/*
+ * Lockdep states,
+ *
+ * please update XXX_LOCK_USAGE_STATES in include/linux/lockdep.h whenever
+ * you add one, or come up with a nice dynamic solution.
+ */
+LOCKDEP_STATE(HARDIRQ)
+LOCKDEP_STATE(SOFTIRQ)
+LOCKDEP_STATE(RECLAIM_FS)

kernel/mutex-debug.c

@@ -26,11 +26,6 @@
 /*
  * Must be called with lock->wait_lock held.
  */
-void debug_mutex_set_owner(struct mutex *lock, struct thread_info *new_owner)
-{
-	lock->owner = new_owner;
-}
-
 void debug_mutex_lock_common(struct mutex *lock, struct mutex_waiter *waiter)
 {
 	memset(waiter, MUTEX_DEBUG_INIT, sizeof(*waiter));
@@ -59,7 +54,6 @@ void debug_mutex_add_waiter(struct mutex *lock, struct mutex_waiter *waiter,
 
 	/* Mark the current thread as blocked on the lock: */
 	ti->task->blocked_on = waiter;
-	waiter->lock = lock;
 }
 
 void mutex_remove_waiter(struct mutex *lock, struct mutex_waiter *waiter,
@@ -82,7 +76,7 @@ void debug_mutex_unlock(struct mutex *lock)
 	DEBUG_LOCKS_WARN_ON(lock->magic != lock);
 	DEBUG_LOCKS_WARN_ON(lock->owner != current_thread_info());
 	DEBUG_LOCKS_WARN_ON(!lock->wait_list.prev && !lock->wait_list.next);
-	DEBUG_LOCKS_WARN_ON(lock->owner != current_thread_info());
+	mutex_clear_owner(lock);
 }
 
 void debug_mutex_init(struct mutex *lock, const char *name,
@@ -95,7 +89,6 @@ void debug_mutex_init(struct mutex *lock, const char *name,
 	debug_check_no_locks_freed((void *)lock, sizeof(*lock));
 	lockdep_init_map(&lock->dep_map, name, key, 0);
 #endif
-	lock->owner = NULL;
 	lock->magic = lock;
 }
 

kernel/mutex-debug.h

@@ -13,14 +13,6 @@
 /*
  * This must be called with lock->wait_lock held.
  */
-extern void
-debug_mutex_set_owner(struct mutex *lock, struct thread_info *new_owner);
-
-static inline void debug_mutex_clear_owner(struct mutex *lock)
-{
-	lock->owner = NULL;
-}
-
 extern void debug_mutex_lock_common(struct mutex *lock,
 				    struct mutex_waiter *waiter);
 extern void debug_mutex_wake_waiter(struct mutex *lock,
@@ -35,6 +27,16 @@ extern void debug_mutex_unlock(struct mutex *lock);
 extern void debug_mutex_init(struct mutex *lock, const char *name,
 			     struct lock_class_key *key);
 
+static inline void mutex_set_owner(struct mutex *lock)
+{
+	lock->owner = current_thread_info();
+}
+
+static inline void mutex_clear_owner(struct mutex *lock)
+{
+	lock->owner = NULL;
+}
+
 #define spin_lock_mutex(lock, flags)			\
 	do {						\
 		struct mutex *l = container_of(lock, struct mutex, wait_lock); \

kernel/mutex.c

@@ -10,6 +10,11 @@
  * Many thanks to Arjan van de Ven, Thomas Gleixner, Steven Rostedt and
  * David Howells for suggestions and improvements.
  *
+ *  - Adaptive spinning for mutexes by Peter Zijlstra. (Ported to mainline
+ *    from the -rt tree, where it was originally implemented for rtmutexes
+ *    by Steven Rostedt, based on work by Gregory Haskins, Peter Morreale
+ *    and Sven Dietrich.
+ *
  * Also see Documentation/mutex-design.txt.
  */
 #include <linux/mutex.h>
@@ -46,6 +51,7 @@ __mutex_init(struct mutex *lock, const char *name, struct lock_class_key *key)
 	atomic_set(&lock->count, 1);
 	spin_lock_init(&lock->wait_lock);
 	INIT_LIST_HEAD(&lock->wait_list);
+	mutex_clear_owner(lock);
 
 	debug_mutex_init(lock, name, key);
 }
@@ -91,6 +97,7 @@ void inline __sched mutex_lock(struct mutex *lock)
 	 * 'unlocked' into 'locked' state.
 	 */
 	__mutex_fastpath_lock(&lock->count, __mutex_lock_slowpath);
+	mutex_set_owner(lock);
 }
 
 EXPORT_SYMBOL(mutex_lock);
@@ -115,6 +122,14 @@ void __sched mutex_unlock(struct mutex *lock)
 	 * The unlocking fastpath is the 0->1 transition from 'locked'
 	 * into 'unlocked' state:
 	 */
+#ifndef CONFIG_DEBUG_MUTEXES
+	/*
+	 * When debugging is enabled we must not clear the owner before time,
+	 * the slow path will always be taken, and that clears the owner field
+	 * after verifying that it was indeed current.
+	 */
+	mutex_clear_owner(lock);
+#endif
 	__mutex_fastpath_unlock(&lock->count, __mutex_unlock_slowpath);
 }
 
@@ -129,21 +144,75 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
 {
 	struct task_struct *task = current;
 	struct mutex_waiter waiter;
-	unsigned int old_val;
 	unsigned long flags;
 
+	preempt_disable();
+	mutex_acquire(&lock->dep_map, subclass, 0, ip);
+#if defined(CONFIG_SMP) && !defined(CONFIG_DEBUG_MUTEXES)
+	/*
+	 * Optimistic spinning.
+	 *
+	 * We try to spin for acquisition when we find that there are no
+	 * pending waiters and the lock owner is currently running on a
+	 * (different) CPU.
+	 *
+	 * The rationale is that if the lock owner is running, it is likely to
+	 * release the lock soon.
+	 *
+	 * Since this needs the lock owner, and this mutex implementation
+	 * doesn't track the owner atomically in the lock field, we need to
+	 * track it non-atomically.
+	 *
+	 * We can't do this for DEBUG_MUTEXES because that relies on wait_lock
+	 * to serialize everything.
+	 */
+
+	for (;;) {
+		struct thread_info *owner;
+
+		/*
+		 * If there's an owner, wait for it to either
+		 * release the lock or go to sleep.
+		 */
+		owner = ACCESS_ONCE(lock->owner);
+		if (owner && !mutex_spin_on_owner(lock, owner))
+			break;
+
+		if (atomic_cmpxchg(&lock->count, 1, 0) == 1) {
+			lock_acquired(&lock->dep_map, ip);
+			mutex_set_owner(lock);
+			preempt_enable();
+			return 0;
+		}
+
+		/*
+		 * When there's no owner, we might have preempted between the
+		 * owner acquiring the lock and setting the owner field. If
+		 * we're an RT task that will live-lock because we won't let
+		 * the owner complete.
+		 */
+		if (!owner && (need_resched() || rt_task(task)))
+			break;
+
+		/*
+		 * The cpu_relax() call is a compiler barrier which forces
+		 * everything in this loop to be re-loaded. We don't need
+		 * memory barriers as we'll eventually observe the right
+		 * values at the cost of a few extra spins.
+		 */
+		cpu_relax();
+	}
+#endif
 	spin_lock_mutex(&lock->wait_lock, flags);
 
 	debug_mutex_lock_common(lock, &waiter);
-	mutex_acquire(&lock->dep_map, subclass, 0, ip);
 	debug_mutex_add_waiter(lock, &waiter, task_thread_info(task));
 
 	/* add waiting tasks to the end of the waitqueue (FIFO): */
 	list_add_tail(&waiter.list, &lock->wait_list);
 	waiter.task = task;
 
-	old_val = atomic_xchg(&lock->count, -1);
-	if (old_val == 1)
+	if (atomic_xchg(&lock->count, -1) == 1)
 		goto done;
 
 	lock_contended(&lock->dep_map, ip);
@@ -158,8 +227,7 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
 		 * that when we release the lock, we properly wake up the
 		 * other waiters:
 		 */
-		old_val = atomic_xchg(&lock->count, -1);
-		if (old_val == 1)
+		if (atomic_xchg(&lock->count, -1) == 1)
 			break;
 
 		/*
@@ -173,21 +241,22 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
 			spin_unlock_mutex(&lock->wait_lock, flags);
 
 			debug_mutex_free_waiter(&waiter);
+			preempt_enable();
 			return -EINTR;
 		}
 		__set_task_state(task, state);
 
 		/* didnt get the lock, go to sleep: */
 		spin_unlock_mutex(&lock->wait_lock, flags);
-		schedule();
+		__schedule();
 		spin_lock_mutex(&lock->wait_lock, flags);
 	}
 
 done:
 	lock_acquired(&lock->dep_map, ip);
 	/* got the lock - rejoice! */
-	mutex_remove_waiter(lock, &waiter, task_thread_info(task));
-	debug_mutex_set_owner(lock, task_thread_info(task));
+	mutex_remove_waiter(lock, &waiter, current_thread_info());
+	mutex_set_owner(lock);
 
 	/* set it to 0 if there are no waiters left: */
 	if (likely(list_empty(&lock->wait_list)))
@@ -196,6 +265,7 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
 	spin_unlock_mutex(&lock->wait_lock, flags);
 
 	debug_mutex_free_waiter(&waiter);
+	preempt_enable();
 
 	return 0;
 }
@@ -222,7 +292,8 @@ int __sched
 mutex_lock_interruptible_nested(struct mutex *lock, unsigned int subclass)
 {
 	might_sleep();
-	return __mutex_lock_common(lock, TASK_INTERRUPTIBLE, subclass, _RET_IP_);
+	return __mutex_lock_common(lock, TASK_INTERRUPTIBLE,
+				   subclass, _RET_IP_);
 }
 
 EXPORT_SYMBOL_GPL(mutex_lock_interruptible_nested);
@@ -260,8 +331,6 @@ __mutex_unlock_common_slowpath(atomic_t *lock_count, int nested)
 		wake_up_process(waiter->task);
 	}
 
-	debug_mutex_clear_owner(lock);
-
 	spin_unlock_mutex(&lock->wait_lock, flags);
 }
 
@@ -298,18 +367,30 @@ __mutex_lock_interruptible_slowpath(atomic_t *lock_count);
  */
 int __sched mutex_lock_interruptible(struct mutex *lock)
 {
+	int ret;
+
 	might_sleep();
-	return __mutex_fastpath_lock_retval
+	ret =  __mutex_fastpath_lock_retval
 			(&lock->count, __mutex_lock_interruptible_slowpath);
+	if (!ret)
+		mutex_set_owner(lock);
+
+	return ret;
 }
 
 EXPORT_SYMBOL(mutex_lock_interruptible);
 
 int __sched mutex_lock_killable(struct mutex *lock)
 {
+	int ret;
+
 	might_sleep();
-	return __mutex_fastpath_lock_retval
+	ret = __mutex_fastpath_lock_retval
 			(&lock->count, __mutex_lock_killable_slowpath);
+	if (!ret)
+		mutex_set_owner(lock);
+
+	return ret;
 }
 EXPORT_SYMBOL(mutex_lock_killable);
 
@@ -352,9 +433,10 @@ static inline int __mutex_trylock_slowpath(atomic_t *lock_count)
 
 	prev = atomic_xchg(&lock->count, -1);
 	if (likely(prev == 1)) {
-		debug_mutex_set_owner(lock, current_thread_info());
+		mutex_set_owner(lock);
 		mutex_acquire(&lock->dep_map, 0, 1, _RET_IP_);
 	}
+
 	/* Set it back to 0 if there are no waiters: */
 	if (likely(list_empty(&lock->wait_list)))
 		atomic_set(&lock->count, 0);
@@ -380,8 +462,13 @@ static inline int __mutex_trylock_slowpath(atomic_t *lock_count)
  */
 int __sched mutex_trylock(struct mutex *lock)
 {
-	return __mutex_fastpath_trylock(&lock->count,
-					__mutex_trylock_slowpath);
+	int ret;
+
+	ret = __mutex_fastpath_trylock(&lock->count, __mutex_trylock_slowpath);
+	if (ret)
+		mutex_set_owner(lock);
+
+	return ret;
 }
 
 EXPORT_SYMBOL(mutex_trylock);

kernel/mutex.h

@@ -16,8 +16,26 @@
 #define mutex_remove_waiter(lock, waiter, ti) \
 		__list_del((waiter)->list.prev, (waiter)->list.next)
 
-#define debug_mutex_set_owner(lock, new_owner)		do { } while (0)
-#define debug_mutex_clear_owner(lock)			do { } while (0)
+#ifdef CONFIG_SMP
+static inline void mutex_set_owner(struct mutex *lock)
+{
+	lock->owner = current_thread_info();
+}
+
+static inline void mutex_clear_owner(struct mutex *lock)
+{
+	lock->owner = NULL;
+}
+#else
+static inline void mutex_set_owner(struct mutex *lock)
+{
+}
+
+static inline void mutex_clear_owner(struct mutex *lock)
+{
+}
+#endif
+
 #define debug_mutex_wake_waiter(lock, waiter)		do { } while (0)
 #define debug_mutex_free_waiter(waiter)			do { } while (0)
 #define debug_mutex_add_waiter(lock, waiter, ti)	do { } while (0)

kernel/sched.c

@@ -4543,15 +4543,13 @@ pick_next_task(struct rq *rq, struct task_struct *prev)
 /*
  * schedule() is the main scheduler function.
  */
-asmlinkage void __sched schedule(void)
+asmlinkage void __sched __schedule(void)
 {
 	struct task_struct *prev, *next;
 	unsigned long *switch_count;
 	struct rq *rq;
 	int cpu;
 
-need_resched:
-	preempt_disable();
 	cpu = smp_processor_id();
 	rq = cpu_rq(cpu);
 	rcu_qsctr_inc(cpu);
@@ -4608,13 +4606,80 @@ asmlinkage void __sched schedule(void)
 
 	if (unlikely(reacquire_kernel_lock(current) < 0))
 		goto need_resched_nonpreemptible;
+}
 
+asmlinkage void __sched schedule(void)
+{
+need_resched:
+	preempt_disable();
+	__schedule();
 	preempt_enable_no_resched();
 	if (unlikely(test_thread_flag(TIF_NEED_RESCHED)))
 		goto need_resched;
 }
 EXPORT_SYMBOL(schedule);
 
+#ifdef CONFIG_SMP
+/*
+ * Look out! "owner" is an entirely speculative pointer
+ * access and not reliable.
+ */
+int mutex_spin_on_owner(struct mutex *lock, struct thread_info *owner)
+{
+	unsigned int cpu;
+	struct rq *rq;
+
+	if (!sched_feat(OWNER_SPIN))
+		return 0;
+
+#ifdef CONFIG_DEBUG_PAGEALLOC
+	/*
+	 * Need to access the cpu field knowing that
+	 * DEBUG_PAGEALLOC could have unmapped it if
+	 * the mutex owner just released it and exited.
+	 */
+	if (probe_kernel_address(&owner->cpu, cpu))
+		goto out;
+#else
+	cpu = owner->cpu;
+#endif
+
+	/*
+	 * Even if the access succeeded (likely case),
+	 * the cpu field may no longer be valid.
+	 */
+	if (cpu >= nr_cpumask_bits)
+		goto out;
+
+	/*
+	 * We need to validate that we can do a
+	 * get_cpu() and that we have the percpu area.
+	 */
+	if (!cpu_online(cpu))
+		goto out;
+
+	rq = cpu_rq(cpu);
+
+	for (;;) {
+		/*
+		 * Owner changed, break to re-assess state.
+		 */
+		if (lock->owner != owner)
+			break;
+
+		/*
+		 * Is that owner really running on that cpu?
+		 */
+		if (task_thread_info(rq->curr) != owner || need_resched())
+			return 0;
+
+		cpu_relax();
+	}
+out:
+	return 1;
+}
+#endif
+
 #ifdef CONFIG_PREEMPT
 /*
  * this is the entry point to schedule() from in-kernel preemption

kernel/sched_features.h

@@ -13,3 +13,4 @@ SCHED_FEAT(LB_WAKEUP_UPDATE, 1)
 SCHED_FEAT(ASYM_EFF_LOAD, 1)
 SCHED_FEAT(WAKEUP_OVERLAP, 0)
 SCHED_FEAT(LAST_BUDDY, 1)
+SCHED_FEAT(OWNER_SPIN, 1)

kernel/timer.c

@@ -491,14 +491,18 @@ static inline void debug_timer_free(struct timer_list *timer)
 	debug_object_free(timer, &timer_debug_descr);
 }
 
-static void __init_timer(struct timer_list *timer);
+static void __init_timer(struct timer_list *timer,
+			 const char *name,
+			 struct lock_class_key *key);
 
-void init_timer_on_stack(struct timer_list *timer)
+void init_timer_on_stack_key(struct timer_list *timer,
+			     const char *name,
+			     struct lock_class_key *key)
 {
 	debug_object_init_on_stack(timer, &timer_debug_descr);
-	__init_timer(timer);
+	__init_timer(timer, name, key);
 }
-EXPORT_SYMBOL_GPL(init_timer_on_stack);
+EXPORT_SYMBOL_GPL(init_timer_on_stack_key);
 
 void destroy_timer_on_stack(struct timer_list *timer)
 {
@@ -512,7 +516,9 @@ static inline void debug_timer_activate(struct timer_list *timer) { }
 static inline void debug_timer_deactivate(struct timer_list *timer) { }
 #endif
 
-static void __init_timer(struct timer_list *timer)
+static void __init_timer(struct timer_list *timer,
+			 const char *name,
+			 struct lock_class_key *key)
 {
 	timer->entry.next = NULL;
 	timer->base = __raw_get_cpu_var(tvec_bases);
@@ -521,6 +527,7 @@ static void __init_timer(struct timer_list *timer)
 	timer->start_pid = -1;
 	memset(timer->start_comm, 0, TASK_COMM_LEN);
 #endif
+	lockdep_init_map(&timer->lockdep_map, name, key, 0);
 }
 
 /**
@@ -530,19 +537,23 @@ static void __init_timer(struct timer_list *timer)
  * init_timer() must be done to a timer prior calling *any* of the
  * other timer functions.
  */
-void init_timer(struct timer_list *timer)
+void init_timer_key(struct timer_list *timer,
+		    const char *name,
+		    struct lock_class_key *key)
 {
 	debug_timer_init(timer);
-	__init_timer(timer);
+	__init_timer(timer, name, key);
 }
-EXPORT_SYMBOL(init_timer);
+EXPORT_SYMBOL(init_timer_key);
 
-void init_timer_deferrable(struct timer_list *timer)
+void init_timer_deferrable_key(struct timer_list *timer,
+			       const char *name,
+			       struct lock_class_key *key)
 {
-	init_timer(timer);
+	init_timer_key(timer, name, key);
 	timer_set_deferrable(timer);
 }
-EXPORT_SYMBOL(init_timer_deferrable);
+EXPORT_SYMBOL(init_timer_deferrable_key);
 
 static inline void detach_timer(struct timer_list *timer,
 				int clear_pending)
@@ -789,6 +800,15 @@ EXPORT_SYMBOL(try_to_del_timer_sync);
  */
 int del_timer_sync(struct timer_list *timer)
 {
+#ifdef CONFIG_LOCKDEP
+	unsigned long flags;
+
+	local_irq_save(flags);
+	lock_map_acquire(&timer->lockdep_map);
+	lock_map_release(&timer->lockdep_map);
+	local_irq_restore(flags);
+#endif
+
 	for (;;) {
 		int ret = try_to_del_timer_sync(timer);
 		if (ret >= 0)
@@ -861,10 +881,36 @@ static inline void __run_timers(struct tvec_base *base)
 
 			set_running_timer(base, timer);
 			detach_timer(timer, 1);
+
 			spin_unlock_irq(&base->lock);
 			{
 				int preempt_count = preempt_count();
+
+#ifdef CONFIG_LOCKDEP
+				/*
+				 * It is permissible to free the timer from
+				 * inside the function that is called from
+				 * it, this we need to take into account for
+				 * lockdep too. To avoid bogus "held lock
+				 * freed" warnings as well as problems when
+				 * looking into timer->lockdep_map, make a
+				 * copy and use that here.
+				 */
+				struct lockdep_map lockdep_map =
+					timer->lockdep_map;
+#endif
+				/*
+				 * Couple the lock chain with the lock chain at
+				 * del_timer_sync() by acquiring the lock_map
+				 * around the fn() call here and in
+				 * del_timer_sync().
+				 */
+				lock_map_acquire(&lockdep_map);
+
 				fn(data);
+
+				lock_map_release(&lockdep_map);
+
 				if (preempt_count != preempt_count()) {
 					printk(KERN_ERR "huh, entered %p "
 					       "with preempt_count %08x, exited"

kernel/trace/ring_buffer.c

@@ -61,6 +61,8 @@ enum {
 
 static unsigned long ring_buffer_flags __read_mostly = RB_BUFFERS_ON;
 
+#define BUF_PAGE_HDR_SIZE offsetof(struct buffer_data_page, data)
+
 /**
  * tracing_on - enable all tracing buffers
  *
@@ -132,7 +134,7 @@ void ring_buffer_normalize_time_stamp(int cpu, u64 *ts)
 }
 EXPORT_SYMBOL_GPL(ring_buffer_normalize_time_stamp);
 
-#define RB_EVNT_HDR_SIZE (sizeof(struct ring_buffer_event))
+#define RB_EVNT_HDR_SIZE (offsetof(struct ring_buffer_event, array))
 #define RB_ALIGNMENT		4U
 #define RB_MAX_SMALL_DATA	28
 
@@ -234,6 +236,18 @@ static void rb_init_page(struct buffer_data_page *bpage)
 	local_set(&bpage->commit, 0);
 }
 
+/**
+ * ring_buffer_page_len - the size of data on the page.
+ * @page: The page to read
+ *
+ * Returns the amount of data on the page, including buffer page header.
+ */
+size_t ring_buffer_page_len(void *page)
+{
+	return local_read(&((struct buffer_data_page *)page)->commit)
+		+ BUF_PAGE_HDR_SIZE;
+}
+
 /*
  * Also stolen from mm/slob.c. Thanks to Mathieu Desnoyers for pointing
  * this issue out.
@@ -254,7 +268,7 @@ static inline int test_time_stamp(u64 delta)
 	return 0;
 }
 
-#define BUF_PAGE_SIZE (PAGE_SIZE - offsetof(struct buffer_data_page, data))
+#define BUF_PAGE_SIZE (PAGE_SIZE - BUF_PAGE_HDR_SIZE)
 
 /*
  * head_page == tail_page && head == tail then buffer is empty.
@@ -2378,8 +2392,8 @@ static void rb_remove_entries(struct ring_buffer_per_cpu *cpu_buffer,
  */
 void *ring_buffer_alloc_read_page(struct ring_buffer *buffer)
 {
-	unsigned long addr;
 	struct buffer_data_page *bpage;
+	unsigned long addr;
 
 	addr = __get_free_page(GFP_KERNEL);
 	if (!addr)
@@ -2387,6 +2401,8 @@ void *ring_buffer_alloc_read_page(struct ring_buffer *buffer)
 
 	bpage = (void *)addr;
 
+	rb_init_page(bpage);
+
 	return bpage;
 }
 
@@ -2406,6 +2422,7 @@ void ring_buffer_free_read_page(struct ring_buffer *buffer, void *data)
  * ring_buffer_read_page - extract a page from the ring buffer
  * @buffer: buffer to extract from
  * @data_page: the page to use allocated from ring_buffer_alloc_read_page
+ * @len: amount to extract
  * @cpu: the cpu of the buffer to extract
  * @full: should the extraction only happen when the page is full.
  *
@@ -2418,7 +2435,7 @@ void ring_buffer_free_read_page(struct ring_buffer *buffer, void *data)
  *	rpage = ring_buffer_alloc_read_page(buffer);
  *	if (!rpage)
  *		return error;
- *	ret = ring_buffer_read_page(buffer, &rpage, cpu, 0);
+ *	ret = ring_buffer_read_page(buffer, &rpage, len, cpu, 0);
  *	if (ret >= 0)
  *		process_page(rpage, ret);
  *
@@ -2435,70 +2452,103 @@ void ring_buffer_free_read_page(struct ring_buffer *buffer, void *data)
  *  <0 if no data has been transferred.
  */
 int ring_buffer_read_page(struct ring_buffer *buffer,
-			    void **data_page, int cpu, int full)
+			  void **data_page, size_t len, int cpu, int full)
 {
 	struct ring_buffer_per_cpu *cpu_buffer = buffer->buffers[cpu];
 	struct ring_buffer_event *event;
 	struct buffer_data_page *bpage;
+	struct buffer_page *reader;
 	unsigned long flags;
+	unsigned int commit;
 	unsigned int read;
 	int ret = -1;
 
+	/*
+	 * If len is not big enough to hold the page header, then
+	 * we can not copy anything.
+	 */
+	if (len <= BUF_PAGE_HDR_SIZE)
+		return -1;
+
+	len -= BUF_PAGE_HDR_SIZE;
+
 	if (!data_page)
-		return 0;
+		return -1;
 
 	bpage = *data_page;
 	if (!bpage)
-		return 0;
+		return -1;
 
 	spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
 
-	/*
-	 * rb_buffer_peek will get the next ring buffer if
-	 * the current reader page is empty.
-	 */
-	event = rb_buffer_peek(buffer, cpu, NULL);
-	if (!event)
+	reader = rb_get_reader_page(cpu_buffer);
+	if (!reader)
 		goto out;
 
-	/* check for data */
-	if (!local_read(&cpu_buffer->reader_page->page->commit))
-		goto out;
+	event = rb_reader_event(cpu_buffer);
+
+	read = reader->read;
+	commit = rb_page_commit(reader);
 
-	read = cpu_buffer->reader_page->read;
 	/*
-	 * If the writer is already off of the read page, then simply
-	 * switch the read page with the given page. Otherwise
-	 * we need to copy the data from the reader to the writer.
-	 */
-	if (cpu_buffer->reader_page == cpu_buffer->commit_page) {
-		unsigned int commit = rb_page_commit(cpu_buffer->reader_page);
+	 * If this page has been partially read or
+	 * if len is not big enough to read the rest of the page or
+	 * a writer is still on the page, then
+	 * we must copy the data from the page to the buffer.
+	 * Otherwise, we can simply swap the page with the one passed in.
+	 */
+	if (read || (len < (commit - read)) ||
+	    cpu_buffer->reader_page == cpu_buffer->commit_page) {
 		struct buffer_data_page *rpage = cpu_buffer->reader_page->page;
+		unsigned int rpos = read;
+		unsigned int pos = 0;
+		unsigned int size;
 
 		if (full)
 			goto out;
-		/* The writer is still on the reader page, we must copy */
-		memcpy(bpage->data + read, rpage->data + read, commit - read);
 
-		/* consume what was read */
-		cpu_buffer->reader_page->read = commit;
+		if (len > (commit - read))
+			len = (commit - read);
+
+		size = rb_event_length(event);
+
+		if (len < size)
+			goto out;
+
+		/* Need to copy one event at a time */
+		do {
+			memcpy(bpage->data + pos, rpage->data + rpos, size);
+
+			len -= size;
+
+			rb_advance_reader(cpu_buffer);
+			rpos = reader->read;
+			pos += size;
+
+			event = rb_reader_event(cpu_buffer);
+			size = rb_event_length(event);
+		} while (len > size);
 
 		/* update bpage */
-		local_set(&bpage->commit, commit);
-		if (!read)
+		local_set(&bpage->commit, pos);
 		bpage->time_stamp = rpage->time_stamp;
+
+		/* we copied everything to the beginning */
+		read = 0;
 	} else {
 		/* swap the pages */
 		rb_init_page(bpage);
-		bpage = cpu_buffer->reader_page->page;
-		cpu_buffer->reader_page->page = *data_page;
-		cpu_buffer->reader_page->read = 0;
+		bpage = reader->page;
+		reader->page = *data_page;
+		local_set(&reader->write, 0);
+		reader->read = 0;
 		*data_page = bpage;
-	}
-	ret = read;
 
 		/* update the entry counter */
 		rb_remove_entries(cpu_buffer, bpage, read);
+	}
+	ret = read;
+
  out:
 	spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
 

kernel/trace/trace.c

@@ -11,31 +11,30 @@
  *  Copyright (C) 2004-2006 Ingo Molnar
  *  Copyright (C) 2004 William Lee Irwin III
  */
+#include <linux/ring_buffer.h>
 #include <linux/utsrelease.h>
+#include <linux/stacktrace.h>
+#include <linux/writeback.h>
 #include <linux/kallsyms.h>
 #include <linux/seq_file.h>
 #include <linux/notifier.h>
+#include <linux/irqflags.h>
 #include <linux/debugfs.h>
 #include <linux/pagemap.h>
 #include <linux/hardirq.h>
 #include <linux/linkage.h>
 #include <linux/uaccess.h>
+#include <linux/kprobes.h>
 #include <linux/ftrace.h>
 #include <linux/module.h>
 #include <linux/percpu.h>
+#include <linux/splice.h>
 #include <linux/kdebug.h>
 #include <linux/ctype.h>
 #include <linux/init.h>
 #include <linux/poll.h>
 #include <linux/gfp.h>
 #include <linux/fs.h>
-#include <linux/kprobes.h>
-#include <linux/writeback.h>
-#include <linux/splice.h>
-
-#include <linux/stacktrace.h>
-#include <linux/ring_buffer.h>
-#include <linux/irqflags.h>
 
 #include "trace.h"
 #include "trace_output.h"
@@ -624,7 +623,7 @@ static unsigned map_pid_to_cmdline[PID_MAX_DEFAULT+1];
 static unsigned map_cmdline_to_pid[SAVED_CMDLINES];
 static char saved_cmdlines[SAVED_CMDLINES][TASK_COMM_LEN];
 static int cmdline_idx;
-static DEFINE_SPINLOCK(trace_cmdline_lock);
+static raw_spinlock_t trace_cmdline_lock = __RAW_SPIN_LOCK_UNLOCKED;
 
 /* temporary disable recording */
 static atomic_t trace_record_cmdline_disabled __read_mostly;
@@ -736,7 +735,7 @@ static void trace_save_cmdline(struct task_struct *tsk)
 	 * nor do we want to disable interrupts,
 	 * so if we miss here, then better luck next time.
 	 */
-	if (!spin_trylock(&trace_cmdline_lock))
+	if (!__raw_spin_trylock(&trace_cmdline_lock))
 		return;
 
 	idx = map_pid_to_cmdline[tsk->pid];
@@ -754,7 +753,7 @@ static void trace_save_cmdline(struct task_struct *tsk)
 
 	memcpy(&saved_cmdlines[idx], tsk->comm, TASK_COMM_LEN);
 
-	spin_unlock(&trace_cmdline_lock);
+	__raw_spin_unlock(&trace_cmdline_lock);
 }
 
 char *trace_find_cmdline(int pid)
@@ -3005,6 +3004,246 @@ static struct file_operations tracing_mark_fops = {
 	.write		= tracing_mark_write,
 };
 
+struct ftrace_buffer_info {
+	struct trace_array	*tr;
+	void			*spare;
+	int			cpu;
+	unsigned int		read;
+};
+
+static int tracing_buffers_open(struct inode *inode, struct file *filp)
+{
+	int cpu = (int)(long)inode->i_private;
+	struct ftrace_buffer_info *info;
+
+	if (tracing_disabled)
+		return -ENODEV;
+
+	info = kzalloc(sizeof(*info), GFP_KERNEL);
+	if (!info)
+		return -ENOMEM;
+
+	info->tr	= &global_trace;
+	info->cpu	= cpu;
+	info->spare	= ring_buffer_alloc_read_page(info->tr->buffer);
+	/* Force reading ring buffer for first read */
+	info->read	= (unsigned int)-1;
+	if (!info->spare)
+		goto out;
+
+	filp->private_data = info;
+
+	return 0;
+
+ out:
+	kfree(info);
+	return -ENOMEM;
+}
+
+static ssize_t
+tracing_buffers_read(struct file *filp, char __user *ubuf,
+		     size_t count, loff_t *ppos)
+{
+	struct ftrace_buffer_info *info = filp->private_data;
+	unsigned int pos;
+	ssize_t ret;
+	size_t size;
+
+	/* Do we have previous read data to read? */
+	if (info->read < PAGE_SIZE)
+		goto read;
+
+	info->read = 0;
+
+	ret = ring_buffer_read_page(info->tr->buffer,
+				    &info->spare,
+				    count,
+				    info->cpu, 0);
+	if (ret < 0)
+		return 0;
+
+	pos = ring_buffer_page_len(info->spare);
+
+	if (pos < PAGE_SIZE)
+		memset(info->spare + pos, 0, PAGE_SIZE - pos);
+
+read:
+	size = PAGE_SIZE - info->read;
+	if (size > count)
+		size = count;
+
+	ret = copy_to_user(ubuf, info->spare + info->read, size);
+	if (ret)
+		return -EFAULT;
+	*ppos += size;
+	info->read += size;
+
+	return size;
+}
+
+static int tracing_buffers_release(struct inode *inode, struct file *file)
+{
+	struct ftrace_buffer_info *info = file->private_data;
+
+	ring_buffer_free_read_page(info->tr->buffer, info->spare);
+	kfree(info);
+
+	return 0;
+}
+
+struct buffer_ref {
+	struct ring_buffer	*buffer;
+	void			*page;
+	int			ref;
+};
+
+static void buffer_pipe_buf_release(struct pipe_inode_info *pipe,
+				    struct pipe_buffer *buf)
+{
+	struct buffer_ref *ref = (struct buffer_ref *)buf->private;
+
+	if (--ref->ref)
+		return;
+
+	ring_buffer_free_read_page(ref->buffer, ref->page);
+	kfree(ref);
+	buf->private = 0;
+}
+
+static int buffer_pipe_buf_steal(struct pipe_inode_info *pipe,
+				 struct pipe_buffer *buf)
+{
+	return 1;
+}
+
+static void buffer_pipe_buf_get(struct pipe_inode_info *pipe,
+				struct pipe_buffer *buf)
+{
+	struct buffer_ref *ref = (struct buffer_ref *)buf->private;
+
+	ref->ref++;
+}
+
+/* Pipe buffer operations for a buffer. */
+static struct pipe_buf_operations buffer_pipe_buf_ops = {
+	.can_merge		= 0,
+	.map			= generic_pipe_buf_map,
+	.unmap			= generic_pipe_buf_unmap,
+	.confirm		= generic_pipe_buf_confirm,
+	.release		= buffer_pipe_buf_release,
+	.steal			= buffer_pipe_buf_steal,
+	.get			= buffer_pipe_buf_get,
+};
+
+/*
+ * Callback from splice_to_pipe(), if we need to release some pages
+ * at the end of the spd in case we error'ed out in filling the pipe.
+ */
+static void buffer_spd_release(struct splice_pipe_desc *spd, unsigned int i)
+{
+	struct buffer_ref *ref =
+		(struct buffer_ref *)spd->partial[i].private;
+
+	if (--ref->ref)
+		return;
+
+	ring_buffer_free_read_page(ref->buffer, ref->page);
+	kfree(ref);
+	spd->partial[i].private = 0;
+}
+
+static ssize_t
+tracing_buffers_splice_read(struct file *file, loff_t *ppos,
+			    struct pipe_inode_info *pipe, size_t len,
+			    unsigned int flags)
+{
+	struct ftrace_buffer_info *info = file->private_data;
+	struct partial_page partial[PIPE_BUFFERS];
+	struct page *pages[PIPE_BUFFERS];
+	struct splice_pipe_desc spd = {
+		.pages		= pages,
+		.partial	= partial,
+		.flags		= flags,
+		.ops		= &buffer_pipe_buf_ops,
+		.spd_release	= buffer_spd_release,
+	};
+	struct buffer_ref *ref;
+	int size, i;
+	size_t ret;
+
+	/*
+	 * We can't seek on a buffer input
+	 */
+	if (unlikely(*ppos))
+		return -ESPIPE;
+
+
+	for (i = 0; i < PIPE_BUFFERS && len; i++, len -= size) {
+		struct page *page;
+		int r;
+
+		ref = kzalloc(sizeof(*ref), GFP_KERNEL);
+		if (!ref)
+			break;
+
+		ref->buffer = info->tr->buffer;
+		ref->page = ring_buffer_alloc_read_page(ref->buffer);
+		if (!ref->page) {
+			kfree(ref);
+			break;
+		}
+
+		r = ring_buffer_read_page(ref->buffer, &ref->page,
+					  len, info->cpu, 0);
+		if (r < 0) {
+			ring_buffer_free_read_page(ref->buffer,
+						   ref->page);
+			kfree(ref);
+			break;
+		}
+
+		/*
+		 * zero out any left over data, this is going to
+		 * user land.
+		 */
+		size = ring_buffer_page_len(ref->page);
+		if (size < PAGE_SIZE)
+			memset(ref->page + size, 0, PAGE_SIZE - size);
+
+		page = virt_to_page(ref->page);
+
+		spd.pages[i] = page;
+		spd.partial[i].len = PAGE_SIZE;
+		spd.partial[i].offset = 0;
+		spd.partial[i].private = (unsigned long)ref;
+		spd.nr_pages++;
+	}
+
+	spd.nr_pages = i;
+
+	/* did we read anything? */
+	if (!spd.nr_pages) {
+		if (flags & SPLICE_F_NONBLOCK)
+			ret = -EAGAIN;
+		else
+			ret = 0;
+		/* TODO: block */
+		return ret;
+	}
+
+	ret = splice_to_pipe(pipe, &spd);
+
+	return ret;
+}
+
+static const struct file_operations tracing_buffers_fops = {
+	.open		= tracing_buffers_open,
+	.read		= tracing_buffers_read,
+	.release	= tracing_buffers_release,
+	.splice_read	= tracing_buffers_splice_read,
+	.llseek		= no_llseek,
+};
+
 #ifdef CONFIG_DYNAMIC_FTRACE
 
 int __weak ftrace_arch_read_dyn_info(char *buf, int size)
@@ -3399,6 +3638,7 @@ static __init void create_trace_options_dir(void)
 static __init int tracer_init_debugfs(void)
 {
 	struct dentry *d_tracer;
+	struct dentry *buffers;
 	struct dentry *entry;
 	int cpu;
 
@@ -3471,6 +3711,26 @@ static __init int tracer_init_debugfs(void)
 		pr_warning("Could not create debugfs "
 			   "'trace_marker' entry\n");
 
+	buffers = debugfs_create_dir("binary_buffers", d_tracer);
+
+	if (!buffers)
+		pr_warning("Could not create buffers directory\n");
+	else {
+		int cpu;
+		char buf[64];
+
+		for_each_tracing_cpu(cpu) {
+			sprintf(buf, "%d", cpu);
+
+			entry = debugfs_create_file(buf, 0444, buffers,
+						    (void *)(long)cpu,
+						    &tracing_buffers_fops);
+			if (!entry)
+				pr_warning("Could not create debugfs buffers "
+					   "'%s' entry\n", buf);
+		}
+	}
+
 #ifdef CONFIG_DYNAMIC_FTRACE
 	entry = debugfs_create_file("dyn_ftrace_total_info", 0444, d_tracer,
 				    &ftrace_update_tot_cnt,
@@ -3491,7 +3751,7 @@ static __init int tracer_init_debugfs(void)
 
 int trace_vprintk(unsigned long ip, int depth, const char *fmt, va_list args)
 {
-	static DEFINE_SPINLOCK(trace_buf_lock);
+	static raw_spinlock_t trace_buf_lock = __RAW_SPIN_LOCK_UNLOCKED;
 	static char trace_buf[TRACE_BUF_SIZE];
 
 	struct ring_buffer_event *event;
@@ -3513,7 +3773,8 @@ int trace_vprintk(unsigned long ip, int depth, const char *fmt, va_list args)
 		goto out;
 
 	pause_graph_tracing();
-	spin_lock_irqsave(&trace_buf_lock, irq_flags);
+	raw_local_irq_save(irq_flags);
+	__raw_spin_lock(&trace_buf_lock);
 	len = vsnprintf(trace_buf, TRACE_BUF_SIZE, fmt, args);
 
 	len = min(len, TRACE_BUF_SIZE-1);
@@ -3532,7 +3793,8 @@ int trace_vprintk(unsigned long ip, int depth, const char *fmt, va_list args)
 	ring_buffer_unlock_commit(tr->buffer, event);
 
  out_unlock:
-	spin_unlock_irqrestore(&trace_buf_lock, irq_flags);
+	__raw_spin_unlock(&trace_buf_lock);
+	raw_local_irq_restore(irq_flags);
 	unpause_graph_tracing();
  out:
 	preempt_enable_notrace();

kernel/trace/trace.h

@@ -217,6 +217,7 @@ enum trace_flag_type {
  */
 struct trace_array_cpu {
 	atomic_t		disabled;
+	void			*buffer_page;	/* ring buffer spare */
 
 	/* these fields get copied into max-trace: */
 	unsigned long		trace_idx;

kernel/trace/trace_events_stage_3.h

@@ -5,7 +5,7 @@
  *
  * static void ftrace_event_<call>(proto)
  * {
- * 	event_trace_printk(_RET_IP_, "(<call>) " <fmt>);
+ * 	event_trace_printk(_RET_IP_, "<call>: " <fmt>);
  * }
  *
  * static int ftrace_reg_event_<call>(void)
@@ -112,7 +112,7 @@
 #define _TRACE_FORMAT(call, proto, args, fmt)				\
 static void ftrace_event_##call(proto)					\
 {									\
-	event_trace_printk(_RET_IP_, "(" #call ") " fmt);		\
+	event_trace_printk(_RET_IP_, #call ": " fmt);			\
 }									\
 									\
 static int ftrace_reg_event_##call(void)				\

lib/Kconfig.debug

@@ -402,7 +402,7 @@ config LOCKDEP
 	bool
 	depends on DEBUG_KERNEL && TRACE_IRQFLAGS_SUPPORT && STACKTRACE_SUPPORT && LOCKDEP_SUPPORT
 	select STACKTRACE
-	select FRAME_POINTER if !X86 && !MIPS && !PPC
+	select FRAME_POINTER if !MIPS && !PPC
 	select KALLSYMS
 	select KALLSYMS_ALL
 

mm/page_alloc.c

@@ -1479,6 +1479,8 @@ __alloc_pages_internal(gfp_t gfp_mask, unsigned int order,
 	unsigned long did_some_progress;
 	unsigned long pages_reclaimed = 0;
 
+	lockdep_trace_alloc(gfp_mask);
+
 	might_sleep_if(wait);
 
 	if (should_fail_alloc_page(gfp_mask, order))
@@ -1578,12 +1580,15 @@ __alloc_pages_internal(gfp_t gfp_mask, unsigned int order,
 	 */
 	cpuset_update_task_memory_state();
 	p->flags |= PF_MEMALLOC;
+
+	lockdep_set_current_reclaim_state(gfp_mask);
 	reclaim_state.reclaimed_slab = 0;
 	p->reclaim_state = &reclaim_state;
 
 	did_some_progress = try_to_free_pages(zonelist, order, gfp_mask);
 
 	p->reclaim_state = NULL;
+	lockdep_clear_current_reclaim_state();
 	p->flags &= ~PF_MEMALLOC;
 
 	cond_resched();

mm/slab.c

@@ -3327,6 +3327,8 @@ __cache_alloc_node(struct kmem_cache *cachep, gfp_t flags, int nodeid,
 	unsigned long save_flags;
 	void *ptr;
 
+	lockdep_trace_alloc(flags);
+
 	if (slab_should_failslab(cachep, flags))
 		return NULL;
 
@@ -3403,6 +3405,8 @@ __cache_alloc(struct kmem_cache *cachep, gfp_t flags, void *caller)
 	unsigned long save_flags;
 	void *objp;
 
+	lockdep_trace_alloc(flags);
+
 	if (slab_should_failslab(cachep, flags))
 		return NULL;
 

mm/slob.c

@@ -466,6 +466,8 @@ void *__kmalloc_node(size_t size, gfp_t gfp, int node)
 	int align = max(ARCH_KMALLOC_MINALIGN, ARCH_SLAB_MINALIGN);
 	void *ret;
 
+	lockdep_trace_alloc(flags);
+
 	if (size < PAGE_SIZE - align) {
 		if (!size)
 			return ZERO_SIZE_PTR;

mm/slub.c

@@ -1597,6 +1597,7 @@ static __always_inline void *slab_alloc(struct kmem_cache *s,
 	unsigned long flags;
 	unsigned int objsize;
 
+	lockdep_trace_alloc(gfpflags);
 	might_sleep_if(gfpflags & __GFP_WAIT);
 
 	if (should_failslab(s->objsize, gfpflags))

mm/vmscan.c

@@ -1965,6 +1965,8 @@ static int kswapd(void *p)
 	};
 	node_to_cpumask_ptr(cpumask, pgdat->node_id);
 
+	lockdep_set_current_reclaim_state(GFP_KERNEL);
+
 	if (!cpumask_empty(cpumask))
 		set_cpus_allowed_ptr(tsk, cpumask);
 	current->reclaim_state = &reclaim_state;