Merge branch 'tracing-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'tracing-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (413 commits)
  tracing, net: fix net tree and tracing tree merge interaction
  tracing, powerpc: fix powerpc tree and tracing tree interaction
  ring-buffer: do not remove reader page from list on ring buffer free
  function-graph: allow unregistering twice
  trace: make argument 'mem' of trace_seq_putmem() const
  tracing: add missing 'extern' keywords to trace_output.h
  tracing: provide trace_seq_reserve()
  blktrace: print out BLK_TN_MESSAGE properly
  blktrace: extract duplidate code
  blktrace: fix memory leak when freeing struct blk_io_trace
  blktrace: fix blk_probes_ref chaos
  blktrace: make classic output more classic
  blktrace: fix off-by-one bug
  blktrace: fix the original blktrace
  blktrace: fix a race when creating blk_tree_root in debugfs
  blktrace: fix timestamp in binary output
  tracing, Text Edit Lock: cleanup
  tracing: filter fix for TRACE_EVENT_FORMAT events
  ftrace: Using FTRACE_WARN_ON() to check "freed record" in ftrace_release()
  x86: kretprobe-booster interrupt emulation code fix
  ...

Fix up trivial conflicts in
 arch/parisc/include/asm/ftrace.h
 include/linux/memory.h
 kernel/extable.c
 kernel/module.c

35 files changed, 1335 insertions, 270 deletions

diff --git a/include/asm-frv/ftrace.h b/include/asm-frv/ftrace.h
new file mode 100644
index 00000000000..40a8c178f10
--- /dev/null
+++ b/include/asm-frv/ftrace.h
@@ -0,0 +1 @@
+/* empty */
diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index a654d724d3b..7fa660fd449 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -61,6 +61,30 @@
 #define BRANCH_PROFILE()
 #endif
 
+#ifdef CONFIG_EVENT_TRACER
+#define FTRACE_EVENTS()	VMLINUX_SYMBOL(__start_ftrace_events) = .;	\
+			*(_ftrace_events)				\
+			VMLINUX_SYMBOL(__stop_ftrace_events) = .;
+#else
+#define FTRACE_EVENTS()
+#endif
+
+#ifdef CONFIG_TRACING
+#define TRACE_PRINTKS() VMLINUX_SYMBOL(__start___trace_bprintk_fmt) = .;      \
+			 *(__trace_printk_fmt) /* Trace_printk fmt' pointer */ \
+			 VMLINUX_SYMBOL(__stop___trace_bprintk_fmt) = .;
+#else
+#define TRACE_PRINTKS()
+#endif
+
+#ifdef CONFIG_FTRACE_SYSCALLS
+#define TRACE_SYSCALLS() VMLINUX_SYMBOL(__start_syscalls_metadata) = .;	\
+			 *(__syscalls_metadata)				\
+			 VMLINUX_SYMBOL(__stop_syscalls_metadata) = .;
+#else
+#define TRACE_SYSCALLS()
+#endif
+
 /* .data section */
 #define DATA_DATA							\
 	*(.data)							\
@@ -86,7 +110,10 @@
 	*(__verbose)                                                    \
 	VMLINUX_SYMBOL(__stop___verbose) = .;				\
 	LIKELY_PROFILE()		       				\
-	BRANCH_PROFILE()
+	BRANCH_PROFILE()						\
+	TRACE_PRINTKS()							\
+	FTRACE_EVENTS()							\
+	TRACE_SYSCALLS()
 
 #define RO_DATA(align)							\
 	. = ALIGN((align));						\
diff --git a/include/asm-m32r/ftrace.h b/include/asm-m32r/ftrace.h
new file mode 100644
index 00000000000..40a8c178f10
--- /dev/null
+++ b/include/asm-m32r/ftrace.h
@@ -0,0 +1 @@
+/* empty */
diff --git a/include/asm-mn10300/ftrace.h b/include/asm-mn10300/ftrace.h
new file mode 100644
index 00000000000..40a8c178f10
--- /dev/null
+++ b/include/asm-mn10300/ftrace.h
@@ -0,0 +1 @@
+/* empty */
diff --git a/include/linux/blktrace_api.h b/include/linux/blktrace_api.h
index 6e915878e88..d960889e92e 100644
--- a/include/linux/blktrace_api.h
+++ b/include/linux/blktrace_api.h
@@ -144,6 +144,9 @@ struct blk_user_trace_setup {
 
 #ifdef __KERNEL__
 #if defined(CONFIG_BLK_DEV_IO_TRACE)
+
+#include <linux/sysfs.h>
+
 struct blk_trace {
 	int trace_state;
 	struct rchan *rchan;
@@ -194,6 +197,8 @@ extern int blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
 extern int blk_trace_startstop(struct request_queue *q, int start);
 extern int blk_trace_remove(struct request_queue *q);
 
+extern struct attribute_group blk_trace_attr_group;
+
 #else /* !CONFIG_BLK_DEV_IO_TRACE */
 #define blk_trace_ioctl(bdev, cmd, arg)		(-ENOTTY)
 #define blk_trace_shutdown(q)			do { } while (0)
diff --git a/include/linux/compiler.h b/include/linux/compiler.h
index d95da1020f1..6faa7e549de 100644
--- a/include/linux/compiler.h
+++ b/include/linux/compiler.h
@@ -68,6 +68,7 @@ struct ftrace_branch_data {
 			unsigned long miss;
 			unsigned long hit;
 		};
+		unsigned long miss_hit[2];
 	};
 };
 
@@ -125,10 +126,7 @@ void ftrace_likely_update(struct ftrace_branch_data *f, int val, int expect);
 				.line = __LINE__,			\
 			};						\
 		______r = !!(cond);					\
-		if (______r)						\
-			______f.hit++;					\
-		else							\
-			______f.miss++;					\
+		______f.miss_hit[______r]++;					\
 		______r;						\
 	}))
 #endif /* CONFIG_PROFILE_ALL_BRANCHES */
diff --git a/include/linux/debugfs.h b/include/linux/debugfs.h
index af0e01d4c66..eb5c2ba2f81 100644
--- a/include/linux/debugfs.h
+++ b/include/linux/debugfs.h
@@ -71,6 +71,9 @@ struct dentry *debugfs_create_bool(const char *name, mode_t mode,
 struct dentry *debugfs_create_blob(const char *name, mode_t mode,
 				  struct dentry *parent,
 				  struct debugfs_blob_wrapper *blob);
+
+bool debugfs_initialized(void);
+
 #else
 
 #include <linux/err.h>
@@ -183,6 +186,11 @@ static inline struct dentry *debugfs_create_blob(const char *name, mode_t mode,
 	return ERR_PTR(-ENODEV);
 }
 
+static inline bool debugfs_initialized(void)
+{
+	return false;
+}
+
 #endif
 
 #endif
diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index a7f8134c594..015a3d22cf7 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -1,15 +1,18 @@
 #ifndef _LINUX_FTRACE_H
 #define _LINUX_FTRACE_H
 
-#include <linux/linkage.h>
-#include <linux/fs.h>
-#include <linux/ktime.h>
-#include <linux/init.h>
-#include <linux/types.h>
-#include <linux/module.h>
+#include <linux/trace_clock.h>
 #include <linux/kallsyms.h>
+#include <linux/linkage.h>
 #include <linux/bitops.h>
+#include <linux/module.h>
+#include <linux/ktime.h>
 #include <linux/sched.h>
+#include <linux/types.h>
+#include <linux/init.h>
+#include <linux/fs.h>
+
+#include <asm/ftrace.h>
 
 #ifdef CONFIG_FUNCTION_TRACER
 
@@ -95,9 +98,41 @@ stack_trace_sysctl(struct ctl_table *table, int write,
 		   loff_t *ppos);
 #endif
 
+struct ftrace_func_command {
+	struct list_head	list;
+	char			*name;
+	int			(*func)(char *func, char *cmd,
+					char *params, int enable);
+};
+
 #ifdef CONFIG_DYNAMIC_FTRACE
-/* asm/ftrace.h must be defined for archs supporting dynamic ftrace */
-#include <asm/ftrace.h>
+
+int ftrace_arch_code_modify_prepare(void);
+int ftrace_arch_code_modify_post_process(void);
+
+struct seq_file;
+
+struct ftrace_probe_ops {
+	void			(*func)(unsigned long ip,
+					unsigned long parent_ip,
+					void **data);
+	int			(*callback)(unsigned long ip, void **data);
+	void			(*free)(void **data);
+	int			(*print)(struct seq_file *m,
+					 unsigned long ip,
+					 struct ftrace_probe_ops *ops,
+					 void *data);
+};
+
+extern int
+register_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
+			      void *data);
+extern void
+unregister_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
+				void *data);
+extern void
+unregister_ftrace_function_probe_func(char *glob, struct ftrace_probe_ops *ops);
+extern void unregister_ftrace_function_probe_all(char *glob);
 
 enum {
 	FTRACE_FL_FREE		= (1 << 0),
@@ -110,15 +145,23 @@ enum {
 };
 
 struct dyn_ftrace {
-	struct list_head	list;
-	unsigned long		ip; /* address of mcount call-site */
-	unsigned long		flags;
-	struct dyn_arch_ftrace	arch;
+	union {
+		unsigned long		ip; /* address of mcount call-site */
+		struct dyn_ftrace	*freelist;
+	};
+	union {
+		unsigned long		flags;
+		struct dyn_ftrace	*newlist;
+	};
+	struct dyn_arch_ftrace		arch;
 };
 
 int ftrace_force_update(void);
 void ftrace_set_filter(unsigned char *buf, int len, int reset);
 
+int register_ftrace_command(struct ftrace_func_command *cmd);
+int unregister_ftrace_command(struct ftrace_func_command *cmd);
+
 /* defined in arch */
 extern int ftrace_ip_converted(unsigned long ip);
 extern int ftrace_dyn_arch_init(void *data);
@@ -126,6 +169,10 @@ extern int ftrace_update_ftrace_func(ftrace_func_t func);
 extern void ftrace_caller(void);
 extern void ftrace_call(void);
 extern void mcount_call(void);
+
+#ifndef FTRACE_ADDR
+#define FTRACE_ADDR ((unsigned long)ftrace_caller)
+#endif
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 extern void ftrace_graph_caller(void);
 extern int ftrace_enable_ftrace_graph_caller(void);
@@ -136,7 +183,7 @@ static inline int ftrace_disable_ftrace_graph_caller(void) { return 0; }
 #endif
 
 /**
- * ftrace_make_nop - convert code into top
+ * ftrace_make_nop - convert code into nop
  * @mod: module structure if called by module load initialization
  * @rec: the mcount call site record
  * @addr: the address that the call site should be calling
@@ -181,7 +228,6 @@ extern int ftrace_make_nop(struct module *mod,
  */
 extern int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr);
 
-
 /* May be defined in arch */
 extern int ftrace_arch_read_dyn_info(char *buf, int size);
 
@@ -198,6 +244,14 @@ extern void ftrace_enable_daemon(void);
 # define ftrace_disable_daemon()		do { } while (0)
 # define ftrace_enable_daemon()			do { } while (0)
 static inline void ftrace_release(void *start, unsigned long size) { }
+static inline int register_ftrace_command(struct ftrace_func_command *cmd)
+{
+	return -EINVAL;
+}
+static inline int unregister_ftrace_command(char *cmd_name)
+{
+	return -EINVAL;
+}
 #endif /* CONFIG_DYNAMIC_FTRACE */
 
 /* totally disable ftrace - can not re-enable after this */
@@ -233,24 +287,25 @@ static inline void __ftrace_enabled_restore(int enabled)
 #endif
 }
 
-#ifdef CONFIG_FRAME_POINTER
-/* TODO: need to fix this for ARM */
-# define CALLER_ADDR0 ((unsigned long)__builtin_return_address(0))
-# define CALLER_ADDR1 ((unsigned long)__builtin_return_address(1))
-# define CALLER_ADDR2 ((unsigned long)__builtin_return_address(2))
-# define CALLER_ADDR3 ((unsigned long)__builtin_return_address(3))
-# define CALLER_ADDR4 ((unsigned long)__builtin_return_address(4))
-# define CALLER_ADDR5 ((unsigned long)__builtin_return_address(5))
-# define CALLER_ADDR6 ((unsigned long)__builtin_return_address(6))
-#else
-# define CALLER_ADDR0 ((unsigned long)__builtin_return_address(0))
-# define CALLER_ADDR1 0UL
-# define CALLER_ADDR2 0UL
-# define CALLER_ADDR3 0UL
-# define CALLER_ADDR4 0UL
-# define CALLER_ADDR5 0UL
-# define CALLER_ADDR6 0UL
-#endif
+#ifndef HAVE_ARCH_CALLER_ADDR
+# ifdef CONFIG_FRAME_POINTER
+#  define CALLER_ADDR0 ((unsigned long)__builtin_return_address(0))
+#  define CALLER_ADDR1 ((unsigned long)__builtin_return_address(1))
+#  define CALLER_ADDR2 ((unsigned long)__builtin_return_address(2))
+#  define CALLER_ADDR3 ((unsigned long)__builtin_return_address(3))
+#  define CALLER_ADDR4 ((unsigned long)__builtin_return_address(4))
+#  define CALLER_ADDR5 ((unsigned long)__builtin_return_address(5))
+#  define CALLER_ADDR6 ((unsigned long)__builtin_return_address(6))
+# else
+#  define CALLER_ADDR0 ((unsigned long)__builtin_return_address(0))
+#  define CALLER_ADDR1 0UL
+#  define CALLER_ADDR2 0UL
+#  define CALLER_ADDR3 0UL
+#  define CALLER_ADDR4 0UL
+#  define CALLER_ADDR5 0UL
+#  define CALLER_ADDR6 0UL
+# endif
+#endif /* ifndef HAVE_ARCH_CALLER_ADDR */
 
 #ifdef CONFIG_IRQSOFF_TRACER
   extern void time_hardirqs_on(unsigned long a0, unsigned long a1);
@@ -268,54 +323,6 @@ static inline void __ftrace_enabled_restore(int enabled)
 # define trace_preempt_off(a0, a1)		do { } while (0)
 #endif
 
-#ifdef CONFIG_TRACING
-extern int ftrace_dump_on_oops;
-
-extern void tracing_start(void);
-extern void tracing_stop(void);
-extern void ftrace_off_permanent(void);
-
-extern void
-ftrace_special(unsigned long arg1, unsigned long arg2, unsigned long arg3);
-
-/**
- * ftrace_printk - printf formatting in the ftrace buffer
- * @fmt: the printf format for printing
- *
- * Note: __ftrace_printk is an internal function for ftrace_printk and
- *       the @ip is passed in via the ftrace_printk macro.
- *
- * This function allows a kernel developer to debug fast path sections
- * that printk is not appropriate for. By scattering in various
- * printk like tracing in the code, a developer can quickly see
- * where problems are occurring.
- *
- * This is intended as a debugging tool for the developer only.
- * Please refrain from leaving ftrace_printks scattered around in
- * your code.
- */
-# define ftrace_printk(fmt...) __ftrace_printk(_THIS_IP_, fmt)
-extern int
-__ftrace_printk(unsigned long ip, const char *fmt, ...)
-	__attribute__ ((format (printf, 2, 3)));
-extern void ftrace_dump(void);
-#else
-static inline void
-ftrace_special(unsigned long arg1, unsigned long arg2, unsigned long arg3) { }
-static inline int
-ftrace_printk(const char *fmt, ...) __attribute__ ((format (printf, 1, 2)));
-
-static inline void tracing_start(void) { }
-static inline void tracing_stop(void) { }
-static inline void ftrace_off_permanent(void) { }
-static inline int
-ftrace_printk(const char *fmt, ...)
-{
-	return 0;
-}
-static inline void ftrace_dump(void) { }
-#endif
-
 #ifdef CONFIG_FTRACE_MCOUNT_RECORD
 extern void ftrace_init(void);
 extern void ftrace_init_module(struct module *mod,
@@ -327,36 +334,6 @@ ftrace_init_module(struct module *mod,
 		   unsigned long *start, unsigned long *end) { }
 #endif
 
-enum {
-	POWER_NONE = 0,
-	POWER_CSTATE = 1,
-	POWER_PSTATE = 2,
-};
-
-struct power_trace {
-#ifdef CONFIG_POWER_TRACER
-	ktime_t			stamp;
-	ktime_t			end;
-	int			type;
-	int			state;
-#endif
-};
-
-#ifdef CONFIG_POWER_TRACER
-extern void trace_power_start(struct power_trace *it, unsigned int type,
-					unsigned int state);
-extern void trace_power_mark(struct power_trace *it, unsigned int type,
-					unsigned int state);
-extern void trace_power_end(struct power_trace *it);
-#else
-static inline void trace_power_start(struct power_trace *it, unsigned int type,
-					unsigned int state) { }
-static inline void trace_power_mark(struct power_trace *it, unsigned int type,
-					unsigned int state) { }
-static inline void trace_power_end(struct power_trace *it) { }
-#endif
-
-
 /*
  * Structure that defines an entry function trace.
  */
@@ -398,8 +375,7 @@ struct ftrace_ret_stack {
 extern void return_to_handler(void);
 
 extern int
-ftrace_push_return_trace(unsigned long ret, unsigned long long time,
-			 unsigned long func, int *depth);
+ftrace_push_return_trace(unsigned long ret, unsigned long func, int *depth);
 extern void
 ftrace_pop_return_trace(struct ftrace_graph_ret *trace, unsigned long *ret);
 
@@ -514,6 +490,50 @@ static inline int test_tsk_trace_graph(struct task_struct *tsk)
 	return tsk->trace & TSK_TRACE_FL_GRAPH;
 }
 
+extern int ftrace_dump_on_oops;
+
 #endif /* CONFIG_TRACING */
 
+
+#ifdef CONFIG_HW_BRANCH_TRACER
+
+void trace_hw_branch(u64 from, u64 to);
+void trace_hw_branch_oops(void);
+
+#else /* CONFIG_HW_BRANCH_TRACER */
+
+static inline void trace_hw_branch(u64 from, u64 to) {}
+static inline void trace_hw_branch_oops(void) {}
+
+#endif /* CONFIG_HW_BRANCH_TRACER */
+
+/*
+ * A syscall entry in the ftrace syscalls array.
+ *
+ * @name: name of the syscall
+ * @nb_args: number of parameters it takes
+ * @types: list of types as strings
+ * @args: list of args as strings (args[i] matches types[i])
+ */
+struct syscall_metadata {
+	const char	*name;
+	int		nb_args;
+	const char	**types;
+	const char	**args;
+};
+
+#ifdef CONFIG_FTRACE_SYSCALLS
+extern void arch_init_ftrace_syscalls(void);
+extern struct syscall_metadata *syscall_nr_to_meta(int nr);
+extern void start_ftrace_syscalls(void);
+extern void stop_ftrace_syscalls(void);
+extern void ftrace_syscall_enter(struct pt_regs *regs);
+extern void ftrace_syscall_exit(struct pt_regs *regs);
+#else
+static inline void start_ftrace_syscalls(void) { }
+static inline void stop_ftrace_syscalls(void) { }
+static inline void ftrace_syscall_enter(struct pt_regs *regs) { }
+static inline void ftrace_syscall_exit(struct pt_regs *regs) { }
+#endif
+
 #endif /* _LINUX_FTRACE_H */
diff --git a/include/linux/ftrace_irq.h b/include/linux/ftrace_irq.h
index 366a054d0b0..dca7bf8cffe 100644
--- a/include/linux/ftrace_irq.h
+++ b/include/linux/ftrace_irq.h
@@ -2,7 +2,7 @@
 #define _LINUX_FTRACE_IRQ_H
 
 
-#if defined(CONFIG_DYNAMIC_FTRACE) || defined(CONFIG_FUNCTION_GRAPH_TRACER)
+#ifdef CONFIG_FTRACE_NMI_ENTER
 extern void ftrace_nmi_enter(void);
 extern void ftrace_nmi_exit(void);
 #else
diff --git a/include/linux/hardirq.h b/include/linux/hardirq.h
index f83288347dd..faa1cf848bc 100644
--- a/include/linux/hardirq.h
+++ b/include/linux/hardirq.h
@@ -15,55 +15,61 @@
  * - bits 0-7 are the preemption count (max preemption depth: 256)
  * - bits 8-15 are the softirq count (max # of softirqs: 256)
  *
- * The hardirq count can be overridden per architecture, the default is:
+ * The hardirq count can in theory reach the same as NR_IRQS.
+ * In reality, the number of nested IRQS is limited to the stack
+ * size as well. For archs with over 1000 IRQS it is not practical
+ * to expect that they will all nest. We give a max of 10 bits for
+ * hardirq nesting. An arch may choose to give less than 10 bits.
+ * m68k expects it to be 8.
  *
- * - bits 16-27 are the hardirq count (max # of hardirqs: 4096)
- * - ( bit 28 is the PREEMPT_ACTIVE flag. )
+ * - bits 16-25 are the hardirq count (max # of nested hardirqs: 1024)
+ * - bit 26 is the NMI_MASK
+ * - bit 28 is the PREEMPT_ACTIVE flag
  *
  * PREEMPT_MASK: 0x000000ff
  * SOFTIRQ_MASK: 0x0000ff00
- * HARDIRQ_MASK: 0x0fff0000
+ * HARDIRQ_MASK: 0x03ff0000
+ *     NMI_MASK: 0x04000000
  */
 #define PREEMPT_BITS	8
 #define SOFTIRQ_BITS	8
+#define NMI_BITS	1
 
-#ifndef HARDIRQ_BITS
-#define HARDIRQ_BITS	12
+#define MAX_HARDIRQ_BITS 10
 
-#ifndef MAX_HARDIRQS_PER_CPU
-#define MAX_HARDIRQS_PER_CPU NR_IRQS
+#ifndef HARDIRQ_BITS
+# define HARDIRQ_BITS	MAX_HARDIRQ_BITS
 #endif
 
-/*
- * The hardirq mask has to be large enough to have space for potentially
- * all IRQ sources in the system nesting on a single CPU.
- */
-#if (1 << HARDIRQ_BITS) < MAX_HARDIRQS_PER_CPU
-# error HARDIRQ_BITS is too low!
-#endif
+#if HARDIRQ_BITS > MAX_HARDIRQ_BITS
+#error HARDIRQ_BITS too high!
 #endif
 
 #define PREEMPT_SHIFT	0
 #define SOFTIRQ_SHIFT	(PREEMPT_SHIFT + PREEMPT_BITS)
 #define HARDIRQ_SHIFT	(SOFTIRQ_SHIFT + SOFTIRQ_BITS)
+#define NMI_SHIFT	(HARDIRQ_SHIFT + HARDIRQ_BITS)
 
 #define __IRQ_MASK(x)	((1UL << (x))-1)
 
 #define PREEMPT_MASK	(__IRQ_MASK(PREEMPT_BITS) << PREEMPT_SHIFT)
 #define SOFTIRQ_MASK	(__IRQ_MASK(SOFTIRQ_BITS) << SOFTIRQ_SHIFT)
 #define HARDIRQ_MASK	(__IRQ_MASK(HARDIRQ_BITS) << HARDIRQ_SHIFT)
+#define NMI_MASK	(__IRQ_MASK(NMI_BITS)     << NMI_SHIFT)
 
 #define PREEMPT_OFFSET	(1UL << PREEMPT_SHIFT)
 #define SOFTIRQ_OFFSET	(1UL << SOFTIRQ_SHIFT)
 #define HARDIRQ_OFFSET	(1UL << HARDIRQ_SHIFT)
+#define NMI_OFFSET	(1UL << NMI_SHIFT)
 
-#if PREEMPT_ACTIVE < (1 << (HARDIRQ_SHIFT + HARDIRQ_BITS))
+#if PREEMPT_ACTIVE < (1 << (NMI_SHIFT + NMI_BITS))
 #error PREEMPT_ACTIVE is too low!
 #endif
 
 #define hardirq_count()	(preempt_count() & HARDIRQ_MASK)
 #define softirq_count()	(preempt_count() & SOFTIRQ_MASK)
-#define irq_count()	(preempt_count() & (HARDIRQ_MASK | SOFTIRQ_MASK))
+#define irq_count()	(preempt_count() & (HARDIRQ_MASK | SOFTIRQ_MASK \
+				 | NMI_MASK))
 
 /*
  * Are we doing bottom half or hardware interrupt processing?
@@ -73,6 +79,11 @@
 #define in_softirq()		(softirq_count())
 #define in_interrupt()		(irq_count())
 
+/*
+ * Are we in NMI context?
+ */
+#define in_nmi()	(preempt_count() & NMI_MASK)
+
 #if defined(CONFIG_PREEMPT)
 # define PREEMPT_INATOMIC_BASE kernel_locked()
 # define PREEMPT_CHECK_OFFSET 1
@@ -164,20 +175,24 @@ extern void irq_enter(void);
  */
 extern void irq_exit(void);
 
-#define nmi_enter()				\
-	do {					\
-		ftrace_nmi_enter();		\
-		lockdep_off();			\
-		rcu_nmi_enter();		\
-		__irq_enter();			\
+#define nmi_enter()						\
+	do {							\
+		ftrace_nmi_enter();				\
+		BUG_ON(in_nmi());				\
+		add_preempt_count(NMI_OFFSET + HARDIRQ_OFFSET);	\
+		lockdep_off();					\
+		rcu_nmi_enter();				\
+		trace_hardirq_enter();				\
 	} while (0)
 
-#define nmi_exit()				\
-	do {					\
-		__irq_exit();			\
-		rcu_nmi_exit();			\
-		lockdep_on();			\
-		ftrace_nmi_exit();		\
+#define nmi_exit()						\
+	do {							\
+		trace_hardirq_exit();				\
+		rcu_nmi_exit();					\
+		lockdep_on();					\
+		BUG_ON(!in_nmi());				\
+		sub_preempt_count(NMI_OFFSET + HARDIRQ_OFFSET);	\
+		ftrace_nmi_exit();				\
 	} while (0)
 
 #endif /* LINUX_HARDIRQ_H */
diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
index c68bffd182b..ce2c07d99fc 100644
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -278,6 +278,11 @@ enum
 	NR_SOFTIRQS
 };
 
+/* map softirq index to softirq name. update 'softirq_to_name' in
+ * kernel/softirq.c when adding a new softirq.
+ */
+extern char *softirq_to_name[NR_SOFTIRQS];
+
 /* softirq mask and active fields moved to irq_cpustat_t in
  * asm/hardirq.h to get better cache usage.  KAO
  */
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index cff58e288a2..d9e75ec7def 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -392,6 +392,139 @@ static inline char *pack_hex_byte(char *buf, u8 byte)
 #endif
 
 /*
+ * General tracing related utility functions - trace_printk(),
+ * tracing_on/tracing_off and tracing_start()/tracing_stop
+ *
+ * Use tracing_on/tracing_off when you want to quickly turn on or off
+ * tracing. It simply enables or disables the recording of the trace events.
+ * This also corresponds to the user space debugfs/tracing/tracing_on
+ * file, which gives a means for the kernel and userspace to interact.
+ * Place a tracing_off() in the kernel where you want tracing to end.
+ * From user space, examine the trace, and then echo 1 > tracing_on
+ * to continue tracing.
+ *
+ * tracing_stop/tracing_start has slightly more overhead. It is used
+ * by things like suspend to ram where disabling the recording of the
+ * trace is not enough, but tracing must actually stop because things
+ * like calling smp_processor_id() may crash the system.
+ *
+ * Most likely, you want to use tracing_on/tracing_off.
+ */
+#ifdef CONFIG_RING_BUFFER
+void tracing_on(void);
+void tracing_off(void);
+/* trace_off_permanent stops recording with no way to bring it back */
+void tracing_off_permanent(void);
+int tracing_is_on(void);
+#else
+static inline void tracing_on(void) { }
+static inline void tracing_off(void) { }
+static inline void tracing_off_permanent(void) { }
+static inline int tracing_is_on(void) { return 0; }
+#endif
+#ifdef CONFIG_TRACING
+extern void tracing_start(void);
+extern void tracing_stop(void);
+extern void ftrace_off_permanent(void);
+
+extern void
+ftrace_special(unsigned long arg1, unsigned long arg2, unsigned long arg3);
+
+static inline void __attribute__ ((format (printf, 1, 2)))
+____trace_printk_check_format(const char *fmt, ...)
+{
+}
+#define __trace_printk_check_format(fmt, args...)			\
+do {									\
+	if (0)								\
+		____trace_printk_check_format(fmt, ##args);		\
+} while (0)
+
+/**
+ * trace_printk - printf formatting in the ftrace buffer
+ * @fmt: the printf format for printing
+ *
+ * Note: __trace_printk is an internal function for trace_printk and
+ *       the @ip is passed in via the trace_printk macro.
+ *
+ * This function allows a kernel developer to debug fast path sections
+ * that printk is not appropriate for. By scattering in various
+ * printk like tracing in the code, a developer can quickly see
+ * where problems are occurring.
+ *
+ * This is intended as a debugging tool for the developer only.
+ * Please refrain from leaving trace_printks scattered around in
+ * your code.
+ */
+
+#define trace_printk(fmt, args...)					\
+do {									\
+	__trace_printk_check_format(fmt, ##args);			\
+	if (__builtin_constant_p(fmt)) {				\
+		static const char *trace_printk_fmt			\
+		  __attribute__((section("__trace_printk_fmt"))) =	\
+			__builtin_constant_p(fmt) ? fmt : NULL;		\
+									\
+		__trace_bprintk(_THIS_IP_, trace_printk_fmt, ##args);	\
+	} else								\
+		__trace_printk(_THIS_IP_, fmt, ##args);		\
+} while (0)
+
+extern int
+__trace_bprintk(unsigned long ip, const char *fmt, ...)
+	__attribute__ ((format (printf, 2, 3)));
+
+extern int
+__trace_printk(unsigned long ip, const char *fmt, ...)
+	__attribute__ ((format (printf, 2, 3)));
+
+/*
+ * The double __builtin_constant_p is because gcc will give us an error
+ * if we try to allocate the static variable to fmt if it is not a
+ * constant. Even with the outer if statement.
+ */
+#define ftrace_vprintk(fmt, vargs)					\
+do {									\
+	if (__builtin_constant_p(fmt)) {				\
+		static const char *trace_printk_fmt			\
+		  __attribute__((section("__trace_printk_fmt"))) =	\
+			__builtin_constant_p(fmt) ? fmt : NULL;		\
+									\
+		__ftrace_vbprintk(_THIS_IP_, trace_printk_fmt, vargs);	\
+	} else								\
+		__ftrace_vprintk(_THIS_IP_, fmt, vargs);		\
+} while (0)
+
+extern int
+__ftrace_vbprintk(unsigned long ip, const char *fmt, va_list ap);
+
+extern int
+__ftrace_vprintk(unsigned long ip, const char *fmt, va_list ap);
+
+extern void ftrace_dump(void);
+#else
+static inline void
+ftrace_special(unsigned long arg1, unsigned long arg2, unsigned long arg3) { }
+static inline int
+trace_printk(const char *fmt, ...) __attribute__ ((format (printf, 1, 2)));
+
+static inline void tracing_start(void) { }
+static inline void tracing_stop(void) { }
+static inline void ftrace_off_permanent(void) { }
+static inline int
+trace_printk(const char *fmt, ...)
+{
+	return 0;
+}