Merge branch 'perf/core' of git://git.kernel.org/pub/scm/linux/kernel/git/frederic/random-tracing into perf/core

35 files changed, 130 insertions, 1309 deletions

diff --git a/Documentation/ABI/testing/debugfs-kmemtrace b/Documentation/ABI/testing/debugfs-kmemtrace
deleted file mode 100644
index 5e6a92a02d85..000000000000
--- a/Documentation/ABI/testing/debugfs-kmemtrace
+++ /dev/null
@@ -1,71 +0,0 @@
-What:		/sys/kernel/debug/kmemtrace/
-Date:		July 2008
-Contact:	Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro>
-Description:
-
-In kmemtrace-enabled kernels, the following files are created:
-
-/sys/kernel/debug/kmemtrace/
-	cpu<n>		(0400)	Per-CPU tracing data, see below. (binary)
-	total_overruns	(0400)	Total number of bytes which were dropped from
-				cpu<n> files because of full buffer condition,
-				non-binary. (text)
-	abi_version	(0400)	Kernel's kmemtrace ABI version. (text)
-
-Each per-CPU file should be read according to the relay interface. That is,
-the reader should set affinity to that specific CPU and, as currently done by
-the userspace application (though there are other methods), use poll() with
-an infinite timeout before every read(). Otherwise, erroneous data may be
-read. The binary data has the following _core_ format:
-
-	Event ID	(1 byte)	Unsigned integer, one of:
-		0 - represents an allocation (KMEMTRACE_EVENT_ALLOC)
-		1 - represents a freeing of previously allocated memory
-		    (KMEMTRACE_EVENT_FREE)
-	Type ID		(1 byte)	Unsigned integer, one of:
-		0 - this is a kmalloc() / kfree()
-		1 - this is a kmem_cache_alloc() / kmem_cache_free()
-		2 - this is a __get_free_pages() et al.
-	Event size	(2 bytes)	Unsigned integer representing the
-					size of this event. Used to extend
-					kmemtrace. Discard the bytes you
-					don't know about.
-	Sequence number	(4 bytes)	Signed integer used to reorder data
-					logged on SMP machines. Wraparound
-					must be taken into account, although
-					it is unlikely.
-	Caller address	(8 bytes)	Return address to the caller.
-	Pointer to mem	(8 bytes)	Pointer to target memory area. Can be
-					NULL, but not all such calls might be
-					recorded.
-
-In case of KMEMTRACE_EVENT_ALLOC events, the next fields follow:
-
-	Requested bytes	(8 bytes)	Total number of requested bytes,
-					unsigned, must not be zero.
-	Allocated bytes (8 bytes)	Total number of actually allocated
-					bytes, unsigned, must not be lower
-					than requested bytes.
-	Requested flags	(4 bytes)	GFP flags supplied by the caller.
-	Target CPU	(4 bytes)	Signed integer, valid for event id 1.
-					If equal to -1, target CPU is the same
-					as origin CPU, but the reverse might
-					not be true.
-
-The data is made available in the same endianness the machine has.
-
-Other event ids and type ids may be defined and added. Other fields may be
-added by increasing event size, but see below for details.
-Every modification to the ABI, including new id definitions, are followed
-by bumping the ABI version by one.
-
-Adding new data to the packet (features) is done at the end of the mandatory
-data:
-	Feature size	(2 byte)
-	Feature ID	(1 byte)
-	Feature data	(Feature size - 3 bytes)
-
-
-Users:
-	kmemtrace-user - git://repo.or.cz/kmemtrace-user.git
-
diff --git a/Documentation/trace/kmemtrace.txt b/Documentation/trace/kmemtrace.txt
deleted file mode 100644
index 6308735e58ca..000000000000
--- a/Documentation/trace/kmemtrace.txt
+++ /dev/null
@@ -1,126 +0,0 @@
-			kmemtrace - Kernel Memory Tracer
-
-			  by Eduard - Gabriel Munteanu
-			     <eduard.munteanu@linux360.ro>
-
-I. Introduction
-===============
-
-kmemtrace helps kernel developers figure out two things:
-1) how different allocators (SLAB, SLUB etc.) perform
-2) how kernel code allocates memory and how much
-
-To do this, we trace every allocation and export information to the userspace
-through the relay interface. We export things such as the number of requested
-bytes, the number of bytes actually allocated (i.e. including internal
-fragmentation), whether this is a slab allocation or a plain kmalloc() and so
-on.
-
-The actual analysis is performed by a userspace tool (see section III for
-details on where to get it from). It logs the data exported by the kernel,
-processes it and (as of writing this) can provide the following information:
-- the total amount of memory allocated and fragmentation per call-site
-- the amount of memory allocated and fragmentation per allocation
-- total memory allocated and fragmentation in the collected dataset
-- number of cross-CPU allocation and frees (makes sense in NUMA environments)
-
-Moreover, it can potentially find inconsistent and erroneous behavior in
-kernel code, such as using slab free functions on kmalloc'ed memory or
-allocating less memory than requested (but not truly failed allocations).
-
-kmemtrace also makes provisions for tracing on some arch and analysing the
-data on another.
-
-II. Design and goals
-====================
-
-kmemtrace was designed to handle rather large amounts of data. Thus, it uses
-the relay interface to export whatever is logged to userspace, which then
-stores it. Analysis and reporting is done asynchronously, that is, after the
-data is collected and stored. By design, it allows one to log and analyse
-on different machines and different arches.
-
-As of writing this, the ABI is not considered stable, though it might not
-change much. However, no guarantees are made about compatibility yet. When
-deemed stable, the ABI should still allow easy extension while maintaining
-backward compatibility. This is described further in Documentation/ABI.
-
-Summary of design goals:
-	- allow logging and analysis to be done across different machines
-	- be fast and anticipate usage in high-load environments (*)
-	- be reasonably extensible
-	- make it possible for GNU/Linux distributions to have kmemtrace
-	included in their repositories
-
-(*) - one of the reasons Pekka Enberg's original userspace data analysis
-    tool's code was rewritten from Perl to C (although this is more than a
-    simple conversion)
-
-
-III. Quick usage guide
-======================
-
-1) Get a kernel that supports kmemtrace and build it accordingly (i.e. enable
-CONFIG_KMEMTRACE).
-
-2) Get the userspace tool and build it:
-$ git clone git://repo.or.cz/kmemtrace-user.git		# current repository
-$ cd kmemtrace-user/
-$ ./autogen.sh
-$ ./configure
-$ make
-
-3) Boot the kmemtrace-enabled kernel if you haven't, preferably in the
-'single' runlevel (so that relay buffers don't fill up easily), and run
-kmemtrace:
-# '$' does not mean user, but root here.
-$ mount -t debugfs none /sys/kernel/debug
-$ mount -t proc none /proc
-$ cd path/to/kmemtrace-user/
-$ ./kmemtraced
-Wait a bit, then stop it with CTRL+C.
-$ cat /sys/kernel/debug/kmemtrace/total_overruns	# Check if we didn't
-							# overrun, should
-							# be zero.
-$ (Optionally) [Run kmemtrace_check separately on each cpu[0-9]*.out file to
-		check its correctness]
-$ ./kmemtrace-report
-
-Now you should have a nice and short summary of how the allocator performs.
-
-IV. FAQ and known issues
-========================
-
-Q: 'cat /sys/kernel/debug/kmemtrace/total_overruns' is non-zero, how do I fix
-this? Should I worry?
-A: If it's non-zero, this affects kmemtrace's accuracy, depending on how
-large the number is. You can fix it by supplying a higher
-'kmemtrace.subbufs=N' kernel parameter.
----
-
-Q: kmemtrace_check reports errors, how do I fix this? Should I worry?
-A: This is a bug and should be reported. It can occur for a variety of
-reasons:
-	- possible bugs in relay code
-	- possible misuse of relay by kmemtrace
-	- timestamps being collected unorderly
-Or you may fix it yourself and send us a patch.
----
-
-Q: kmemtrace_report shows many errors, how do I fix this? Should I worry?
-A: This is a known issue and I'm working on it. These might be true errors
-in kernel code, which may have inconsistent behavior (e.g. allocating memory
-with kmem_cache_alloc() and freeing it with kfree()). Pekka Enberg pointed
-out this behavior may work with SLAB, but may fail with other allocators.
-
-It may also be due to lack of tracing in some unusual allocator functions.
-
-We don't want bug reports regarding this issue yet.
----
-
-V. See also
-===========
-
-Documentation/kernel-parameters.txt
-Documentation/ABI/testing/debugfs-kmemtrace
-
diff --git a/MAINTAINERS b/MAINTAINERS
index 13608bd2e791..26da7313055e 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -3368,13 +3368,6 @@ F:	include/linux/kmemleak.h
 F:	mm/kmemleak.c
 F:	mm/kmemleak-test.c
 
-KMEMTRACE
-M:	Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro>
-S:	Maintained
-F:	Documentation/trace/kmemtrace.txt
-F:	include/linux/kmemtrace.h
-F:	kernel/trace/kmemtrace.c
-
 KPROBES
 M:	Ananth N Mavinakayanahalli <ananth@in.ibm.com>
 M:	Anil S Keshavamurthy <anil.s.keshavamurthy@intel.com>
diff --git a/arch/powerpc/include/asm/perf_event.h b/arch/powerpc/include/asm/perf_event.h
index e6d4ce69b126..5c16b891d501 100644
--- a/arch/powerpc/include/asm/perf_event.h
+++ b/arch/powerpc/include/asm/perf_event.h
@@ -21,3 +21,15 @@
 #ifdef CONFIG_FSL_EMB_PERF_EVENT
 #include <asm/perf_event_fsl_emb.h>
 #endif
+
+#ifdef CONFIG_PERF_EVENTS
+#include <asm/ptrace.h>
+#include <asm/reg.h>
+
+#define perf_arch_fetch_caller_regs(regs, __ip)			\
+	do {							\
+		(regs)->nip = __ip;				\
+		(regs)->gpr[1] = *(unsigned long *)__get_SP();	\
+		asm volatile("mfmsr %0" : "=r" ((regs)->msr));	\
+	} while (0)
+#endif
diff --git a/arch/powerpc/kernel/misc.S b/arch/powerpc/kernel/misc.S
index 22e507c8a556..2d29752cbe16 100644
--- a/arch/powerpc/kernel/misc.S
+++ b/arch/powerpc/kernel/misc.S
@@ -127,29 +127,3 @@ _GLOBAL(__setup_cpu_power7)
 _GLOBAL(__restore_cpu_power7)
 	/* place holder */
 	blr
-
-/*
- * Get a minimal set of registers for our caller's nth caller.
- * r3 = regs pointer, r5 = n.
- *
- * We only get R1 (stack pointer), NIP (next instruction pointer)
- * and LR (link register).  These are all we can get in the
- * general case without doing complicated stack unwinding, but
- * fortunately they are enough to do a stack backtrace, which
- * is all we need them for.
- */
-_GLOBAL(perf_arch_fetch_caller_regs)
-	mr	r6,r1
-	cmpwi	r5,0
-	mflr	r4
-	ble	2f
-	mtctr	r5
-1:	PPC_LL	r6,0(r6)
-	bdnz	1b
-	PPC_LL	r4,PPC_LR_STKOFF(r6)
-2:	PPC_LL	r7,0(r6)
-	PPC_LL	r7,PPC_LR_STKOFF(r7)
-	PPC_STL	r6,GPR1-STACK_FRAME_OVERHEAD(r3)
-	PPC_STL	r4,_NIP-STACK_FRAME_OVERHEAD(r3)
-	PPC_STL	r7,_LINK-STACK_FRAME_OVERHEAD(r3)
-	blr
diff --git a/arch/sparc/include/asm/perf_event.h b/arch/sparc/include/asm/perf_event.h
index 7e2669894ce8..74c4e0cd889c 100644
--- a/arch/sparc/include/asm/perf_event.h
+++ b/arch/sparc/include/asm/perf_event.h
@@ -6,7 +6,15 @@ extern void set_perf_event_pending(void);
 #define	PERF_EVENT_INDEX_OFFSET	0
 
 #ifdef CONFIG_PERF_EVENTS
+#include <asm/ptrace.h>
+
 extern void init_hw_perf_events(void);
+
+extern void
+__perf_arch_fetch_caller_regs(struct pt_regs *regs, unsigned long ip, int skip);
+
+#define perf_arch_fetch_caller_regs(pt_regs, ip)	\
+	__perf_arch_fetch_caller_regs(pt_regs, ip, 1);
 #else
 static inline void init_hw_perf_events(void)	{ }
 #endif
diff --git a/arch/sparc/kernel/helpers.S b/arch/sparc/kernel/helpers.S
index 92090cc9e829..682fee06a16b 100644
--- a/arch/sparc/kernel/helpers.S
+++ b/arch/sparc/kernel/helpers.S
@@ -47,9 +47,9 @@ stack_trace_flush:
 	.size		stack_trace_flush,.-stack_trace_flush
 
 #ifdef CONFIG_PERF_EVENTS
-	.globl		perf_arch_fetch_caller_regs
-	.type		perf_arch_fetch_caller_regs,#function
-perf_arch_fetch_caller_regs:
+	.globl		__perf_arch_fetch_caller_regs
+	.type		__perf_arch_fetch_caller_regs,#function
+__perf_arch_fetch_caller_regs:
 	/* We always read the %pstate into %o5 since we will use
 	 * that to construct a fake %tstate to store into the regs.
 	 */
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index 6ed3ae4f5482..6e742cc4251b 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -141,6 +141,19 @@ extern unsigned long perf_instruction_pointer(struct pt_regs *regs);
 extern unsigned long perf_misc_flags(struct pt_regs *regs);
 #define perf_misc_flags(regs)	perf_misc_flags(regs)
 
+#include <asm/stacktrace.h>
+
+/*
+ * We abuse bit 3 from flags to pass exact information, see perf_misc_flags
+ * and the comment with PERF_EFLAGS_EXACT.
+ */
+#define perf_arch_fetch_caller_regs(regs, __ip)		{	\
+	(regs)->ip = (__ip);					\
+	(regs)->bp = caller_frame_pointer();			\
+	(regs)->cs = __KERNEL_CS;				\
+	regs->flags = 0;					\
+}
+
 #else
 static inline void init_hw_perf_events(void)		{ }
 static inline void perf_events_lapic_init(void)	{ }
diff --git a/arch/x86/include/asm/stacktrace.h b/arch/x86/include/asm/stacktrace.h
index 4dab78edbad9..2b16a2ad23dc 100644
--- a/arch/x86/include/asm/stacktrace.h
+++ b/arch/x86/include/asm/stacktrace.h
@@ -1,6 +1,13 @@
+/*
+ *  Copyright (C) 1991, 1992  Linus Torvalds
+ *  Copyright (C) 2000, 2001, 2002 Andi Kleen, SuSE Labs
+ */
+
 #ifndef _ASM_X86_STACKTRACE_H
 #define _ASM_X86_STACKTRACE_H
 
+#include <linux/uaccess.h>
+
 extern int kstack_depth_to_print;
 
 struct thread_info;
@@ -42,4 +49,46 @@ void dump_trace(struct task_struct *tsk, struct pt_regs *regs,
 		unsigned long *stack, unsigned long bp,
 		const struct stacktrace_ops *ops, void *data);
 
+#ifdef CONFIG_X86_32
+#define STACKSLOTS_PER_LINE 8
+#define get_bp(bp) asm("movl %%ebp, %0" : "=r" (bp) :)
+#else
+#define STACKSLOTS_PER_LINE 4
+#define get_bp(bp) asm("movq %%rbp, %0" : "=r" (bp) :)
+#endif
+
+extern void
+show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs,
+		unsigned long *stack, unsigned long bp, char *log_lvl);
+
+extern void
+show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs,
+		unsigned long *sp, unsigned long bp, char *log_lvl);
+
+extern unsigned int code_bytes;
+
+/* The form of the top of the frame on the stack */
+struct stack_frame {
+	struct stack_frame *next_frame;
+	unsigned long return_address;
+};
+
+struct stack_frame_ia32 {
+    u32 next_frame;
+    u32 return_address;
+};
+
+static inline unsigned long caller_frame_pointer(void)
+{
+	struct stack_frame *frame;
+
+	get_bp(frame);
+
+#ifdef CONFIG_FRAME_POINTER
+	frame = frame->next_frame;
+#endif
+
+	return (unsigned long)frame;
+}
+
 #endif /* _ASM_X86_STACKTRACE_H */
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 2d0d29069275..f2da20fda02d 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -1613,8 +1613,6 @@ static const struct stacktrace_ops backtrace_ops = {
 	.walk_stack		= print_context_stack_bp,
 };
 
-#include "../dumpstack.h"
-
 static void
 perf_callchain_kernel(struct pt_regs *regs, struct perf_callchain_entry *entry)
 {
@@ -1736,22 +1734,6 @@ struct perf_callchain_entry *perf_callchain(struct pt_regs *regs)
 	return entry;
 }
 
-void perf_arch_fetch_caller_regs(struct pt_regs *regs, unsigned long ip, int skip)
-{
-	regs->ip = ip;
-	/*
-	 * perf_arch_fetch_caller_regs adds another call, we need to increment
-	 * the skip level
-	 */
-	regs->bp = rewind_frame_pointer(skip + 1);
-	regs->cs = __KERNEL_CS;
-	/*
-	 * We abuse bit 3 to pass exact information, see perf_misc_flags
-	 * and the comment with PERF_EFLAGS_EXACT.
-	 */
-	regs->flags = 0;
-}
-
 unsigned long perf_instruction_pointer(struct pt_regs *regs)
 {
 	unsigned long ip;
diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c
index c89a386930b7..6e8752c1bd52 100644
--- a/arch/x86/kernel/dumpstack.c
+++ b/arch/x86/kernel/dumpstack.c
@@ -18,7 +18,6 @@
 
 #include <asm/stacktrace.h>
 
-#include "dumpstack.h"
 
 int panic_on_unrecovered_nmi;
 int panic_on_io_nmi;
diff --git a/arch/x86/kernel/dumpstack.h b/arch/x86/kernel/dumpstack.h
deleted file mode 100644
index e1a93be4fd44..000000000000
--- a/arch/x86/kernel/dumpstack.h
+++ /dev/null
@@ -1,56 +0,0 @@
-/*
- *  Copyright (C) 1991, 1992  Linus Torvalds
- *  Copyright (C) 2000, 2001, 2002 Andi Kleen, SuSE Labs
- */
-
-#ifndef DUMPSTACK_H
-#define DUMPSTACK_H
-
-#ifdef CONFIG_X86_32
-#define STACKSLOTS_PER_LINE 8
-#define get_bp(bp) asm("movl %%ebp, %0" : "=r" (bp) :)
-#else
-#define STACKSLOTS_PER_LINE 4
-#define get_bp(bp) asm("movq %%rbp, %0" : "=r" (bp) :)
-#endif
-
-#include <linux/uaccess.h>
-
-extern void
-show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs,
-		unsigned long *stack, unsigned long bp, char *log_lvl);
-
-extern void
-show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs,
-		unsigned long *sp, unsigned long bp, char *log_lvl);
-
-extern unsigned int code_bytes;
-
-/* The form of the top of the frame on the stack */
-struct stack_frame {
-	struct stack_frame *next_frame;
-	unsigned long return_address;
-};
-
-struct stack_frame_ia32 {
-    u32 next_frame;
-    u32 return_address;
-};
-
-static inline unsigned long rewind_frame_pointer(int n)
-{
-	struct stack_frame *frame;
-
-	get_bp(frame);
-
-#ifdef CONFIG_FRAME_POINTER
-	while (n--) {
-		if (probe_kernel_address(&frame->next_frame, frame))
-			break;
-	}
-#endif
-
-	return (unsigned long)frame;
-}
-
-#endif /* DUMPSTACK_H */
diff --git a/arch/x86/kernel/dumpstack_32.c b/arch/x86/kernel/dumpstack_32.c
index 11540a189d93..0f6376ffa2d9 100644
--- a/arch/x86/kernel/dumpstack_32.c
+++ b/arch/x86/kernel/dumpstack_32.c
@@ -16,8 +16,6 @@
 
 #include <asm/stacktrace.h>
 
-#include "dumpstack.h"
-
 
 void dump_trace(struct task_struct *task, struct pt_regs *regs,
 		unsigned long *stack, unsigned long bp,
diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c
index 272c9f1f05f3..57a21f11c791 100644
--- a/arch/x86/kernel/dumpstack_64.c
+++ b/arch/x86/kernel/dumpstack_64.c
@@ -16,7 +16,6 @@
 
 #include <asm/stacktrace.h>
 
-#include "dumpstack.h"
 
 #define N_EXCEPTION_STACKS_END \
 		(N_EXCEPTION_STACKS + DEBUG_STKSZ/EXCEPTION_STKSZ - 2)
diff --git a/arch/x86/kernel/stacktrace.c b/arch/x86/kernel/stacktrace.c
index 922eefbb3f6c..b53c525368a7 100644
--- a/arch/x86/kernel/stacktrace.c
+++ b/arch/x86/kernel/stacktrace.c
@@ -23,11 +23,16 @@ static int save_stack_stack(void *data, char *name)
 	return 0;
 }
 
-static void save_stack_address(void *data, unsigned long addr, int reliable)
+static void
+__save_stack_address(void *data, unsigned long addr, bool reliable, bool nosched)
 {
 	struct stack_trace *trace = data;
+#ifdef CONFIG_FRAME_POINTER
 	if (!reliable)
 		return;
+#endif
+	if (nosched && in_sched_functions(addr))
+		return;
 	if (trace->skip > 0) {
 		trace->skip--;
 		return;
@@ -36,20 +41,15 @@ static void save_stack_address(void *data, unsigned long addr, int reliable)
 		trace->entries[trace->nr_entries++] = addr;
 }
 
+static void save_stack_address(void *data, unsigned long addr, int reliable)
+{
+	return __save_stack_address(data, addr, reliable, false);
+}
+
 static void
 save_stack_address_nosched(void *data, unsigned long addr, int reliable)
 {
-	struct stack_trace *trace = (struct stack_trace *)data;
-	if (!reliable)
-		return;
-	if (in_sched_functions(addr))
-		return;
-	if (trace->skip > 0) {
-		trace->skip--;
-		return;
-	}
-	if (trace->nr_entries < trace->max_entries)
-		trace->entries[trace->nr_entries++] = addr;
+	return __save_stack_address(data, addr, reliable, true);
 }
 
 static const struct stacktrace_ops save_stack_ops = {
@@ -96,12 +96,13 @@ EXPORT_SYMBOL_GPL(save_stack_trace_tsk);
 
 /* Userspace stacktrace - based on kernel/trace/trace_sysprof.c */
 
-struct stack_frame {
+struct stack_frame_user {
 	const void __user	*next_fp;
 	unsigned long		ret_addr;
 };
 
-static int copy_stack_frame(const void __user *fp, struct stack_frame *frame)
+static int
+copy_stack_frame(const void __user *fp, struct stack_frame_user *frame)
 {
 	int ret;
 
@@ -126,7 +127,7 @@ static inline void __save_stack_trace_user(struct stack_trace *trace)
 		trace->entries[trace->nr_entries++] = regs->ip;
 
 	while (trace->nr_entries < trace->max_entries) {
-		struct stack_frame frame;
+		struct stack_frame_user frame;
 
 		frame.next_fp = NULL;
 		frame.ret_addr = 0;
diff --git a/include/linux/kmemtrace.h b/include/linux/kmemtrace.h
deleted file mode 100644
index b616d3930c3b..000000000000
--- a/include/linux/kmemtrace.h
+++ /dev/null
@@ -1,25 +0,0 @@
-/*
- * Copyright (C) 2008 Eduard - Gabriel Munteanu
- *
- * This file is released under GPL version 2.
- */
-
-#ifndef _LINUX_KMEMTRACE_H
-#define _LINUX_KMEMTRACE_H
-
-#ifdef __KERNEL__
-
-#include <trace/events/kmem.h>
-
-#ifdef CONFIG_KMEMTRACE
-extern void kmemtrace_init(void);
-#else
-static inline void kmemtrace_init(void)
-{
-}
-#endif
-
-#endif /* __KERNEL__ */
-
-#endif /* _LINUX_KMEMTRACE_H */
-
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 1218d05728b9..63b5aa5dce69 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -932,8 +932,10 @@ extern atomic_t perf_swevent_enabled[PERF_COUNT_SW_MAX];
 
 extern void __perf_sw_event(u32, u64, int, struct pt_regs *, u64);
 
-extern void
-perf_arch_fetch_caller_regs(struct pt_regs *regs, unsigned long ip, int skip);
+#ifndef perf_arch_fetch_caller_regs
+static inline void
+perf_arch_fetch_caller_regs(struct regs *regs, unsigned long ip) { }
+#endif
 
 /*
  * Take a snapshot of the regs. Skip ip and frame pointer to
@@ -943,31 +945,11 @@ perf_arch_fetch_caller_regs(struct pt_regs *regs, unsigned long ip, int skip);
  * - bp for callchains
  * - eflags, for future purposes, just in case
  */
-static inline void perf_fetch_caller_regs(struct pt_regs *regs, int skip)
+static inline void perf_fetch_caller_regs(struct pt_regs *regs)
 {
-	unsigned long ip;
-
 	memset(regs, 0, sizeof(*regs));
 
-	switch (skip) {
-	case 1 :
-		ip = CALLER_ADDR0;
-		break;
-	case 2 :
-		ip = CALLER_ADDR1;
-		break;
-	case 3 :
-		ip = CALLER_ADDR2;
-		break;
-	case 4:
-		ip = CALLER_ADDR3;
-		break;
-	/* No need to support further for now */
-	default:
-		ip = 0;
-	}
-
-	return perf_arch_fetch_caller_regs(regs, ip, skip);
+	perf_arch_fetch_caller_regs(regs, CALLER_ADDR0);
 }
 
 static inline void
@@ -977,7 +959,7 @@ perf_sw_event(u32 event_id, u64 nr, int nmi, struct pt_regs *regs, u64 addr)
 		struct pt_regs hot_regs;
 
 		if (!regs) {
-			perf_fetch_caller_regs(&hot_regs, 1);
+			perf_fetch_caller_regs(&hot_regs);
 			regs = &hot_regs;
 		}
 		__perf_sw_event(event_id, nr, nmi, regs, addr);
diff --git a/include/linux/slab_def.h b/include/linux/slab_def.h
index 1812dac8c496..1acfa73ce2ac 100644
--- a/include/linux/slab_def.h
+++ b/include/linux/slab_def.h
@@ -14,7 +14,8 @@
 #include <asm/page.h>		/* kmalloc_sizes.h needs PAGE_SIZE */
 #include <asm/cache.h>		/* kmalloc_sizes.h needs L1_CACHE_BYTES */
 #include <linux/compiler.h>
-#include <linux/kmemtrace.h>
+
+#include <trace/events/kmem.h>
 
 #ifndef ARCH_KMALLOC_MINALIGN
 /*
diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h
index 4ba59cfc1f75..6447a723ecb1 100644
--- a/include/linux/slub_def.h
+++ b/include/linux/slub_def.h
@@ -10,9 +10,10 @@
 #include <linux/gfp.h>
 #include <linux/workqueue.h>
 #include <linux/kobject.h>
-#include <linux/kmemtrace.h>
 #include <linux/kmemleak.h>
 
+#include <trace/events/kmem.h>
+
 enum stat_item {
 	ALLOC_FASTPATH,		/* Allocation from cpu slab */
 	ALLOC_SLOWPATH,		/* Allocation by getting a new cpu slab */
diff --git a/include/trace/boot.h b/include/trace/boot.h
deleted file mode 100644
index 088ea089e31d..000000000000
--- a/include/trace/boot.h
+++ /dev/null
@@ -1,60 +0,0 @@
-#ifndef _LINUX_TRACE_BOOT_H
-#define _LINUX_TRACE_BOOT_H
-
-#include <linux/module.h>
-#include <linux/kallsyms.h>
-#include <linux/init.h>
-
-/*
- * Structure which defines the trace of an initcall
- * while it is called.
- * You don't have to fill the func field since it is
- * only used internally by the tracer.
- */
-struct boot_trace_call {
-	pid_t			caller;
-	char			func[KSYM_SYMBOL_LEN];
-};
-
-/*
- * Structure which defines the trace of an initcall
- * while it returns.
- */
-struct boot_trace_ret {
-	char			func[KSYM_SYMBOL_LEN];
-	int				result;
-	unsigned long long	duration;		/* nsecs */
-};
-
-#ifdef CONFIG_BOOT_TRACER
-/* Append the traces on the ring-buffer */
-extern void trace_boot_call(struct boot_trace_call *bt, initcall_t fn);
-extern void trace_boot_ret(struct boot_trace_ret *bt, initcall_t fn);
-
-/* Tells the tracer that smp_pre_initcall is finished.
- * So we can start the tracing
- */
-extern void start_boot_trace(void);
-
-/* Resume the tracing of other necessary events
- * such as sched switches
- */
-extern void enable_boot_trace(void);
-
-/* Suspend this tracing. Actually, only sched_switches tracing have
- * to be suspended. Initcalls doesn't need it.)
- */
-extern void disable_boot_trace(void);
-#else
-static inline
-void trace_boot_call(struct boot_trace_call *bt, initcall_t fn) { }
-
-static inline
-void trace_boot_ret(struct boot_trace_ret *bt, initcall_t fn) { }
-
-static inline void start_boot_trace(void) { }
-static inline void enable_boot_trace(void) { }
-static inline void disable_boot_trace(void) { }
-#endif /* CONFIG_BOOT_TRACER */
-
-#endif /* __LINUX_TRACE_BOOT_H */
diff --git a/include/trace/ftrace.h b/include/trace/ftrace.h
index 5a64905d7278..fc013a8201e9 100644
--- a/include/trace/