22 files changed, 796 insertions, 219 deletions
diff --git a/Makefile b/Makefile
index 41ea6fb..e7d01ada 100644
--- a/Makefile
+++ b/Makefile
@@ -1268,6 +1268,7 @@ help:
 	@echo  '  make C=1   [targets] Check all c source with $$CHECK (sparse by default)'
 	@echo  '  make C=2   [targets] Force check of all c source with $$CHECK'
 	@echo  '  make W=1   [targets] Enable extra gcc checks'
+	@echo  '  make RECORDMCOUNT_WARN=1 [targets] Warn about ignored mcount sections'
 	@echo  ''
 	@echo  'Execute "make" or "make all" to build all targets marked with [*] '
 	@echo  'For further info see the ./README file'
diff --git a/arch/s390/include/asm/ftrace.h b/arch/s390/include/asm/ftrace.h
index 3c29be4..b7931fa 100644
--- a/arch/s390/include/asm/ftrace.h
+++ b/arch/s390/include/asm/ftrace.h
@@ -11,15 +11,13 @@ struct dyn_arch_ftrace { };
 
 #ifdef CONFIG_64BIT
 #define MCOUNT_INSN_SIZE  12
-#define MCOUNT_OFFSET	   8
 #else
 #define MCOUNT_INSN_SIZE  20
-#define MCOUNT_OFFSET	   4
 #endif
 
 static inline unsigned long ftrace_call_adjust(unsigned long addr)
 {
-	return addr - MCOUNT_OFFSET;
+	return addr;
 }
 
 #endif /* __ASSEMBLY__ */
diff --git a/arch/x86/include/asm/alternative-asm.h b/arch/x86/include/asm/alternative-asm.h
index a63a68b..94d420b 100644
--- a/arch/x86/include/asm/alternative-asm.h
+++ b/arch/x86/include/asm/alternative-asm.h
@@ -15,4 +15,13 @@
 	.endm
 #endif
 
+.macro altinstruction_entry orig alt feature orig_len alt_len
+	.align 8
+	.quad \orig
+	.quad \alt
+	.word \feature
+	.byte \orig_len
+	.byte \alt_len
+.endm
+
 #endif  /*  __ASSEMBLY__  */
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index 91f3e087..7f2f7b1 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -195,6 +195,7 @@
 
 /* Intel-defined CPU features, CPUID level 0x00000007:0 (ebx), word 9 */
 #define X86_FEATURE_FSGSBASE	(9*32+ 0) /* {RD/WR}{FS/GS}BASE instructions*/
+#define X86_FEATURE_ERMS	(9*32+ 9) /* Enhanced REP MOVSB/STOSB */
 
 #if defined(__KERNEL__) && !defined(__ASSEMBLY__)
 
diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h
index db24c22..268c783 100644
--- a/arch/x86/include/asm/ftrace.h
+++ b/arch/x86/include/asm/ftrace.h
@@ -38,11 +38,10 @@ extern void mcount(void);
 static inline unsigned long ftrace_call_adjust(unsigned long addr)
 {
 	/*
-	 * call mcount is "e8 <4 byte offset>"
-	 * The addr points to the 4 byte offset and the caller of this
-	 * function wants the pointer to e8. Simply subtract one.
+	 * addr is the address of the mcount call instruction.
+	 * recordmcount does the necessary offset calculation.
 	 */
-	return addr - 1;
+	return addr;
 }
 
 #ifdef CONFIG_DYNAMIC_FTRACE
diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h
index db8aa19..647d8a0 100644
--- a/arch/x86/include/asm/setup.h
+++ b/arch/x86/include/asm/setup.h
@@ -88,7 +88,7 @@ void *extend_brk(size_t size, size_t align);
  * executable.)
  */
 #define RESERVE_BRK(name,sz)						\
-	static void __section(.discard.text) __used			\
+	static void __section(.discard.text) __used notrace		\
 	__brk_reservation_fn_##name##__(void) {				\
 		asm volatile (						\
 			".pushsection .brk_reservation,\"aw\",@nobits;" \
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index abd3e0e..99f0ad7 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -42,7 +42,7 @@
  * Returns 0 if the range is valid, nonzero otherwise.
  *
  * This is equivalent to the following test:
- * (u33)addr + (u33)size >= (u33)current->addr_limit.seg (u65 for x86_64)
+ * (u33)addr + (u33)size > (u33)current->addr_limit.seg (u65 for x86_64)
  *
  * This needs 33-bit (65-bit for x86_64) arithmetic. We have a carry...
  */
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index 651454b..1eeeafc 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -210,6 +210,15 @@ void __init_or_module apply_alternatives(struct alt_instr *start,
 	u8 insnbuf[MAX_PATCH_LEN];
 
 	DPRINTK("%s: alt table %p -> %p\n", __func__, start, end);
+	/*
+	 * The scan order should be from start to end. A later scanned
+	 * alternative code can overwrite a previous scanned alternative code.
+	 * Some kernel functions (e.g. memcpy, memset, etc) use this order to
+	 * patch code.
+	 *
+	 * So be careful if you want to change the scan order to any other
+	 * order.
+	 */
 	for (a = start; a < end; a++) {
 		u8 *instr = a->instr;
 		BUG_ON(a->replacementlen > a->instrlen);
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index e2ced00..173f3a3 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -565,8 +565,7 @@ void __cpuinit get_cpu_cap(struct cpuinfo_x86 *c)
 
 		cpuid_count(0x00000007, 0, &eax, &ebx, &ecx, &edx);
 
-		if (eax > 0)
-			c->x86_capability[9] = ebx;
+		c->x86_capability[9] = ebx;
 	}
 
 	/* AMD-defined flags: level 0x80000001 */
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index df86bc8..fc73a34 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -29,10 +29,10 @@
 
 static void __cpuinit early_init_intel(struct cpuinfo_x86 *c)
 {
+	u64 misc_enable;
+
 	/* Unmask CPUID levels if masked: */
 	if (c->x86 > 6 || (c->x86 == 6 && c->x86_model >= 0xd)) {
-		u64 misc_enable;
-
 		rdmsrl(MSR_IA32_MISC_ENABLE, misc_enable);
 
 		if (misc_enable & MSR_IA32_MISC_ENABLE_LIMIT_CPUID) {
@@ -118,8 +118,6 @@ static void __cpuinit early_init_intel(struct cpuinfo_x86 *c)
 	 * (model 2) with the same problem.
 	 */
 	if (c->x86 == 15) {
-		u64 misc_enable;
-
 		rdmsrl(MSR_IA32_MISC_ENABLE, misc_enable);
 
 		if (misc_enable & MSR_IA32_MISC_ENABLE_FAST_STRING) {
@@ -130,6 +128,19 @@ static void __cpuinit early_init_intel(struct cpuinfo_x86 *c)
 		}
 	}
 #endif
+
+	/*
+	 * If fast string is not enabled in IA32_MISC_ENABLE for any reason,
+	 * clear the fast string and enhanced fast string CPU capabilities.
+	 */
+	if (c->x86 > 6 || (c->x86 == 6 && c->x86_model >= 0xd)) {
+		rdmsrl(MSR_IA32_MISC_ENABLE, misc_enable);
+		if (!(misc_enable & MSR_IA32_MISC_ENABLE_FAST_STRING)) {
+			printk(KERN_INFO "Disabled fast string operations\n");
+			setup_clear_cpu_cap(X86_FEATURE_REP_GOOD);
+			setup_clear_cpu_cap(X86_FEATURE_ERMS);
+		}
+	}
 }
 
 #ifdef CONFIG_X86_32
diff --git a/arch/x86/lib/clear_page_64.S b/arch/x86/lib/clear_page_64.S
index aa4326b..f2145cf 100644
--- a/arch/x86/lib/clear_page_64.S
+++ b/arch/x86/lib/clear_page_64.S
@@ -1,5 +1,6 @@
 #include <linux/linkage.h>
 #include <asm/dwarf2.h>
+#include <asm/alternative-asm.h>
 
 /*
  * Zero a page. 	
@@ -14,6 +15,15 @@ ENTRY(clear_page_c)
 	CFI_ENDPROC
 ENDPROC(clear_page_c)
 
+ENTRY(clear_page_c_e)
+	CFI_STARTPROC
+	movl $4096,%ecx
+	xorl %eax,%eax
+	rep stosb
+	ret
+	CFI_ENDPROC
+ENDPROC(clear_page_c_e)
+
 ENTRY(clear_page)
 	CFI_STARTPROC
 	xorl   %eax,%eax
@@ -38,21 +48,26 @@ ENTRY(clear_page)
 .Lclear_page_end:
 ENDPROC(clear_page)
 
-	/* Some CPUs run faster using the string instructions.
-	   It is also a lot simpler. Use this when possible */
+	/*
+	 * Some CPUs support enhanced REP MOVSB/STOSB instructions.
+	 * It is recommended to use this when possible.
+	 * If enhanced REP MOVSB/STOSB is not available, try to use fast string.
+	 * Otherwise, use original function.
+	 *
+	 */
 
 #include <asm/cpufeature.h>
 
 	.section .altinstr_replacement,"ax"
 1:	.byte 0xeb					/* jmp <disp8> */
 	.byte (clear_page_c - clear_page) - (2f - 1b)	/* offset */
-2:
+2:	.byte 0xeb					/* jmp <disp8> */
+	.byte (clear_page_c_e - clear_page) - (3f - 2b)	/* offset */
+3:
 	.previous
 	.section .altinstructions,"a"
-	.align 8
-	.quad clear_page
-	.quad 1b
-	.word X86_FEATURE_REP_GOOD
-	.byte .Lclear_page_end - clear_page
-	.byte 2b - 1b
+	altinstruction_entry clear_page,1b,X86_FEATURE_REP_GOOD,\
+			     .Lclear_page_end-clear_page, 2b-1b
+	altinstruction_entry clear_page,2b,X86_FEATURE_ERMS,   \
+			     .Lclear_page_end-clear_page,3b-2b
 	.previous
diff --git a/arch/x86/lib/copy_user_64.S b/arch/x86/lib/copy_user_64.S
index 99e4826..0248402 100644
--- a/arch/x86/lib/copy_user_64.S
+++ b/arch/x86/lib/copy_user_64.S
@@ -15,23 +15,30 @@
 #include <asm/asm-offsets.h>
 #include <asm/thread_info.h>
 #include <asm/cpufeature.h>
+#include <asm/alternative-asm.h>
 
-	.macro ALTERNATIVE_JUMP feature,orig,alt
+/*
+ * By placing feature2 after feature1 in altinstructions section, we logically
+ * implement:
+ * If CPU has feature2, jmp to alt2 is used
+ * else if CPU has feature1, jmp to alt1 is used
+ * else jmp to orig is used.
+ */
+	.macro ALTERNATIVE_JUMP feature1,feature2,orig,alt1,alt2
 0:
 	.byte 0xe9	/* 32bit jump */
 	.long \orig-1f	/* by default jump to orig */
 1:
 	.section .altinstr_replacement,"ax"
 2:	.byte 0xe9			/* near jump with 32bit immediate */
-	.long \alt-1b /* offset */   /* or alternatively to alt */
+	.long \alt1-1b /* offset */   /* or alternatively to alt1 */
+3:	.byte 0xe9			/* near jump with 32bit immediate */
+	.long \alt2-1b /* offset */   /* or alternatively to alt2 */
 	.previous
+
 	.section .altinstructions,"a"
-	.align 8
-	.quad  0b
-	.quad  2b
-	.word  \feature			/* when feature is set */
-	.byte  5
-	.byte  5
+	altinstruction_entry 0b,2b,\feature1,5,5
+	altinstruction_entry 0b,3b,\feature2,5,5
 	.previous
 	.endm
 
@@ -72,8 +79,10 @@ ENTRY(_copy_to_user)
 	addq %rdx,%rcx
 	jc bad_to_user
 	cmpq TI_addr_limit(%rax),%rcx
-	jae bad_to_user
-	ALTERNATIVE_JUMP X86_FEATURE_REP_GOOD,copy_user_generic_unrolled,copy_user_generic_string
+	ja bad_to_user
+	ALTERNATIVE_JUMP X86_FEATURE_REP_GOOD,X86_FEATURE_ERMS,	\
+		copy_user_generic_unrolled,copy_user_generic_string,	\
+		copy_user_enhanced_fast_string
 	CFI_ENDPROC
 ENDPROC(_copy_to_user)
 
@@ -85,8 +94,10 @@ ENTRY(_copy_from_user)
 	addq %rdx,%rcx
 	jc bad_from_user
 	cmpq TI_addr_limit(%rax),%rcx
-	jae bad_from_user
-	ALTERNATIVE_JUMP X86_FEATURE_REP_GOOD,copy_user_generic_unrolled,copy_user_generic_string
+	ja bad_from_user
+	ALTERNATIVE_JUMP X86_FEATURE_REP_GOOD,X86_FEATURE_ERMS,	\
+		copy_user_generic_unrolled,copy_user_generic_string,	\
+		copy_user_enhanced_fast_string
 	CFI_ENDPROC
 ENDPROC(_copy_from_user)
 
@@ -255,3 +266,37 @@ ENTRY(copy_user_generic_string)
 	.previous
 	CFI_ENDPROC
 ENDPROC(copy_user_generic_string)
+
+/*
+ * Some CPUs are adding enhanced REP MOVSB/STOSB instructions.
+ * It's recommended to use enhanced REP MOVSB/STOSB if it's enabled.
+ *
+ * Input:
+ * rdi destination
+ * rsi source
+ * rdx count
+ *
+ * Output:
+ * eax uncopied bytes or 0 if successful.
+ */
+ENTRY(copy_user_enhanced_fast_string)
+	CFI_STARTPROC
+	andl %edx,%edx
+	jz 2f
+	movl %edx,%ecx
+1:	rep
+	movsb
+2:	xorl %eax,%eax
+	ret
+
+	.section .fixup,"ax"
+12:	movl %ecx,%edx		/* ecx is zerorest also */
+	jmp copy_user_handle_tail
+	.previous
+
+	.section __ex_table,"a"
+	.align 8
+	.quad 1b,12b
+	.previous
+	CFI_ENDPROC
+ENDPROC(copy_user_enhanced_fast_string)
diff --git a/arch/x86/lib/memcpy_64.S b/arch/x86/lib/memcpy_64.S
index 75ef61e..daab21d 100644
--- a/arch/x86/lib/memcpy_64.S
+++ b/arch/x86/lib/memcpy_64.S
@@ -4,6 +4,7 @@
 
 #include <asm/cpufeature.h>
 #include <asm/dwarf2.h>
+#include <asm/alternative-asm.h>
 
 /*
  * memcpy - Copy a memory block.
@@ -37,6 +38,23 @@
 .Lmemcpy_e:
 	.previous
 
+/*
+ * memcpy_c_e() - enhanced fast string memcpy. This is faster and simpler than
+ * memcpy_c. Use memcpy_c_e when possible.
+ *
+ * This gets patched over the unrolled variant (below) via the
+ * alternative instructions framework:
+ */
+	.section .altinstr_replacement, "ax", @progbits
+.Lmemcpy_c_e:
+	movq %rdi, %rax
+
+	movl %edx, %ecx
+	rep movsb
+	ret
+.Lmemcpy_e_e:
+	.previous
+
 ENTRY(__memcpy)
 ENTRY(memcpy)
 	CFI_STARTPROC
@@ -171,21 +189,22 @@ ENDPROC(memcpy)
 ENDPROC(__memcpy)
 
 	/*
-	 * Some CPUs run faster using the string copy instructions.
-	 * It is also a lot simpler. Use this when possible:
-	 */
-
-	.section .altinstructions, "a"
-	.align 8
-	.quad memcpy
-	.quad .Lmemcpy_c
-	.word X86_FEATURE_REP_GOOD
-
-	/*
+	 * Some CPUs are adding enhanced REP MOVSB/STOSB feature
+	 * If the feature is supported, memcpy_c_e() is the first choice.
+	 * If enhanced rep movsb copy is not available, use fast string copy
+	 * memcpy_c() when possible. This is faster and code is simpler than
+	 * original memcpy().
+	 * Otherwise, original memcpy() is used.
+	 * In .altinstructions section, ERMS feature is placed after REG_GOOD
+         * feature to implement the right patch order.
+	 *
 	 * Replace only beginning, memcpy is used to apply alternatives,
 	 * so it is silly to overwrite itself with nops - reboot is the
 	 * only outcome...
 	 */
-	.byte .Lmemcpy_e - .Lmemcpy_c
-	.byte .Lmemcpy_e - .Lmemcpy_c
+	.section .altinstructions, "a"
+	altinstruction_entry memcpy,.Lmemcpy_c,X86_FEATURE_REP_GOOD,\
+			     .Lmemcpy_e-.Lmemcpy_c,.Lmemcpy_e-.Lmemcpy_c
+	altinstruction_entry memcpy,.Lmemcpy_c_e,X86_FEATURE_ERMS, \
+			     .Lmemcpy_e_e-.Lmemcpy_c_e,.Lmemcpy_e_e-.Lmemcpy_c_e
 	.previous
diff --git a/arch/x86/lib/memmove_64.S b/arch/x86/lib/memmove_64.S
index 0ecb843..d0ec9c2 100644
--- a/arch/x86/lib/memmove_64.S
+++ b/arch/x86/lib/memmove_64.S
@@ -8,6 +8,7 @@
 #define _STRING_C
 #include <linux/linkage.h>
 #include <asm/dwarf2.h>
+#include <asm/cpufeature.h>
 
 #undef memmove
 
@@ -24,6 +25,7 @@
  */
 ENTRY(memmove)
 	CFI_STARTPROC
+
 	/* Handle more 32bytes in loop */
 	mov %rdi, %rax
 	cmp $0x20, %rdx
@@ -31,8 +33,13 @@ ENTRY(memmove)
 
 	/* Decide forward/backward copy mode */
 	cmp %rdi, %rsi
-	jb	2f
+	jge .Lmemmove_begin_forward
+	mov %rsi, %r8
+	add %rdx, %r8
+	cmp %rdi, %r8
+	jg 2f
 
+.Lmemmove_begin_forward:
 	/*
 	 * movsq instruction have many startup latency
 	 * so we handle small size by general register.
@@ -78,6 +85,8 @@ ENTRY(memmove)
 	rep movsq
 	movq %r11, (%r10)
 	jmp 13f
+.Lmemmove_end_forward:
+
 	/*
 	 * Handle data backward by movsq.
 	 */
@@ -194,4 +203,22 @@ ENTRY(memmove)
 13:
 	retq
 	CFI_ENDPROC
+
+	.section .altinstr_replacement,"ax"
+.Lmemmove_begin_forward_efs:
+	/* Forward moving data. */
+	movq %rdx, %rcx
+	rep movsb
+	retq
+.Lmemmove_end_forward_efs:
+	.previous
+
+	.section .altinstructions,"a"
+	.align 8
+	.quad .Lmemmove_begin_forward
+	.quad .Lmemmove_begin_forward_efs
+	.word X86_FEATURE_ERMS
+	.byte .Lmemmove_end_forward-.Lmemmove_begin_forward
+	.byte .Lmemmove_end_forward_efs-.Lmemmove_begin_forward_efs
+	.previous
 ENDPROC(memmove)
diff --git a/arch/x86/lib/memset_64.S b/arch/x86/lib/memset_64.S
index 09d3442..79bd454 100644
--- a/arch/x86/lib/memset_64.S
+++ b/arch/x86/lib/memset_64.S
@@ -2,9 +2,13 @@
 
 #include <linux/linkage.h>
 #include <asm/dwarf2.h>
+#include <asm/cpufeature.h>
+#include <asm/alternative-asm.h>
 
 /*
- * ISO C memset - set a memory block to a byte value.
+ * ISO C memset - set a memory block to a byte value. This function uses fast
+ * string to get better performance than the original function. The code is
+ * simpler and shorter than the orignal function as well.
  *	
  * rdi   destination
  * rsi   value (char) 
@@ -31,6 +35,28 @@
 .Lmemset_e:
 	.previous
 
+/*
+ * ISO C memset - set a memory block to a byte value. This function uses
+ * enhanced rep stosb to override the fast string function.
+ * The code is simpler and shorter than the fast string function as well.
+ *
+ * rdi   destination
+ * rsi   value (char)
+ * rdx   count (bytes)
+ *
+ * rax   original destination
+ */
+	.section .altinstr_replacement, "ax", @progbits
+.Lmemset_c_e:
+	movq %rdi,%r9
+	movb %sil,%al
+	movl %edx,%ecx
+	rep stosb
+	movq %r9,%rax
+	ret
+.Lmemset_e_e:
+	.previous
+
 ENTRY(memset)
 ENTRY(__memset)
 	CFI_STARTPROC
@@ -112,16 +138,20 @@ ENTRY(__memset)
 ENDPROC(memset)
 ENDPROC(__memset)
 
-	/* Some CPUs run faster using the string instructions.
-	   It is also a lot simpler. Use this when possible */
-
-#include <asm/cpufeature.h>
-
+	/* Some CPUs support enhanced REP MOVSB/STOSB feature.
+	 * It is recommended to use this when possible.
+	 *
+	 * If enhanced REP MOVSB/STOSB feature is not available, use fast string
+	 * instructions.
+	 *
+	 * Otherwise, use original memset function.
+	 *
+	 * In .altinstructions section, ERMS feature is placed after REG_GOOD
+         * feature to implement the right patch order.
+	 */
 	.section .altinstructions,"a"
-	.align 8
-	.quad memset
-	.quad .Lmemset_c
-	.word X86_FEATURE_REP_GOOD
-	.byte .Lfinal - memset
-	.byte .Lmemset_e - .Lmemset_c
+	altinstruction_entry memset,.Lmemset_c,X86_FEATURE_REP_GOOD,\
+			     .Lfinal-memset,.Lmemset_e-.Lmemset_c
+	altinstruction_entry memset,.Lmemset_c_e,X86_FEATURE_ERMS, \
+			     .Lfinal-memset,.Lmemset_e_e-.Lmemset_c_e
 	.previous
diff --git a/include/linux/init.h b/include/linux/init.h
index 577671c..9146f39 100644
--- a/include/linux/init.h
+++ b/include/linux/init.h
@@ -79,29 +79,29 @@
 #define __exitused  __used
 #endif
 
-#define __exit          __section(.exit.text) __exitused __cold
+#define __exit          __section(.exit.text) __exitused __cold notrace
 
 /* Used for HOTPLUG */
-#define __devinit        __section(.devinit.text) __cold
+#define __devinit        __section(.devinit.text) __cold notrace
 #define __devinitdata    __section(.devinit.data)
 #define __devinitconst   __section(.devinit.rodata)
-#define __devexit        __section(.devexit.text) __exitused __cold
+#define __devexit        __section(.devexit.text) __exitused __cold notrace
 #define __devexitdata    __section(.devexit.data)
 #define __devexitconst   __section(.devexit.rodata)
 
 /* Used for HOTPLUG_CPU */
-#define __cpuinit        __section(.cpuinit.text) __cold
+#define __cpuinit        __section(.cpuinit.text) __cold notrace
 #define __cpuinitdata    __section(.cpuinit.data)
 #define __cpuinitconst   __section(.cpuinit.rodata)
-#define __cpuexit        __section(.cpuexit.text) __exitused __cold
+#define __cpuexit        __section(.cpuexit.text) __exitused __cold notrace
 #define __cpuexitdata    __section(.cpuexit.data)
 #define __cpuexitconst   __section(.cpuexit.rodata)
 
 /* Used for MEMORY_HOTPLUG */
-#define __meminit        __section(.meminit.text) __cold
+#define __meminit        __section(.meminit.text) __cold notrace
 #define __meminitdata    __section(.meminit.data)
 #define __meminitconst   __section(.meminit.rodata)
-#define __memexit        __section(.memexit.text) __exitused __cold
+#define __memexit        __section(.memexit.text) __exitused __cold notrace
 #define __memexitdata    __section(.memexit.data)
 #define __memexitconst   __section(.memexit.rodata)
 
diff --git a/scripts/Makefile.build b/scripts/Makefile.build
index d5f925a..6165622 100644
--- a/scripts/Makefile.build
+++ b/scripts/Makefile.build
@@ -244,14 +244,19 @@ endif
 
 ifdef CONFIG_FTRACE_MCOUNT_RECORD
 ifdef BUILD_C_RECORDMCOUNT
+ifeq ("$(origin RECORDMCOUNT_WARN)", "command line")
+  RECORDMCOUNT_FLAGS = -w
+endif
 # Due to recursion, we must skip empty.o.
 # The empty.o file is created in the make process in order to determine
 #  the target endianness and word size. It is made before all other C
 #  files, including recordmcount.
 sub_cmd_record_mcount =					\
 	if [ $(@) != "scripts/mod/empty.o" ]; then	\
-		$(objtree)/scripts/recordmcount "$(@)";	\
+		$(objtree)/scripts/recordmcount $(RECORDMCOUNT_FLAGS) "$(@)";	\
 	fi;
+recordmcount_source := $(srctree)/scripts/recordmcount.c \
+		    $(srctree)/scripts/recordmcount.h
 else
 sub_cmd_record_mcount = set -e ; perl $(srctree)/scripts/recordmcount.pl "$(ARCH)" \
 	"$(if $(CONFIG_CPU_BIG_ENDIAN),big,little)" \
@@ -259,6 +264,7 @@ sub_cmd_record_mcount = set -e ; perl $(srctree)/scripts/recordmcount.pl "$(ARCH
 	"$(OBJDUMP)" "$(OBJCOPY)" "$(CC) $(KBUILD_CFLAGS)" \
 	"$(LD)" "$(NM)" "$(RM)" "$(MV)" \
 	"$(if $(part-of-module),1,0)" "$(@)";
+recordmcount_source := $(srctree)/scripts/recordmcount.pl
 endif
 cmd_record_mcount = 						\
 	if [ "$(findstring -pg,$(_c_flags))" = "-pg" ]; then	\
@@ -279,13 +285,13 @@ define rule_cc_o_c
 endef
 
 # Built-in and composite module parts
-$(obj)/%.o: $(src)/%.c FORCE
+$(obj)/%.o: $(src)/%.c $(recordmcount_source) FORCE
 	$(call cmd,force_checksrc)
 	$(call if_changed_rule,cc_o_c)
 
 # Single-part modules are special since we need to mark them in $(MODVERDIR)
 
-$(single-used-m): $(obj)/%.o: $(src)/%.c FORCE
+$(single-used-m): $(obj)/%.o: $(src)/%.c $(recordmcount_source) FORCE
 	$(call cmd,force_checksrc)
 	$(call if_changed_rule,cc_o_c)
 	@{ echo $(@:.o=.ko); echo $@; } > $(MODVERDIR)/$(@F:.o=.mod)
diff --git a/scripts/recordmcount.c b/scripts/recordmcount.c
index f9f6f52..ee52cb8 100644
--- a/scripts/recordmcount.c
+++ b/scripts/recordmcount.c
@@ -24,6 +24,7 @@
 #include <sys/types.h>
 #include <sys/mman.h>
 #include <sys/stat.h>
+#include <getopt.h>
 #include <elf.h>
 #include <fcntl.h>
 #include <setjmp.h>
@@ -39,6 +40,7 @@ static char gpfx;	/* prefix for global symbol name (sometimes '_') */
 static struct stat sb;	/* Remember .st_size, etc. */
 static jmp_buf jmpenv;	/* setjmp/longjmp per-file error escape */
 static const char *altmcount;	/* alternate mcount symbol name */
+static int warn_on_notrace_sect; /* warn when section has mcount not being recorded */
 
 /* setjmp() return values */
 enum {
@@ -78,7 +80,7 @@ static off_t
 ulseek(int const fd, off_t const offset, int const whence)
 {
 	off_t const w = lseek(fd, offset, whence);
-	if ((off_t)-1 == w) {
+	if (w == (off_t)-1) {
 		perror("lseek");
 		fail_file();
 	}
@@ -111,13 +113,41 @@ static void *
 umalloc(size_t size)
 {
 	void *const addr = malloc(size);
-	if (0 == addr) {
+	if (addr == 0) {
 		fprintf(stderr, "malloc failed: %zu bytes\n", size);
 		fail_file();
 	}
 	return addr;
 }
 
+static unsigned char ideal_nop5_x86_64[5] = { 0x0f, 0x1f, 0x44, 0x00, 0x00 };
+static unsigned char ideal_nop5_x86_32[5] = { 0x3e, 0x8d, 0x74, 0x26, 0x00 };
+static unsigned char *ideal_nop;
+
+static char rel_type_nop;
+
+static int (*make_nop)(void *map, size_t const offset);
+
+static int make_nop_x86(void *map, size_t const offset)
+{
+	uint32_t *ptr;
+	unsigned char *op;
+
+	/* Confirm we have 0xe8 0x0 0x0 0x0 0x0 */
+	ptr = map + offset;
+	if (*ptr != 0)
+		return -1;
+
+	op = map + offset - 1;
+	if (*op != 0xe8)
+		return -1;
+
+	/* convert to nop */
+	ulseek(fd_map, offset - 1, SEEK_SET);
+	uwrite(fd_map, ideal_nop, 5);
+	return 0;
+}
+
 /*
  * Get the whole file as a programming convenience in order to avoid
  * malloc+lseek+read+free of many pieces.  If successful, then mmap
@@ -136,7 +166,7 @@ static void *mmap_file(char const *fname)
 	void *addr;
 
 	fd_map = open(fname, O_RDWR);
-	if (0 > fd_map || 0 > fstat(fd_map, &sb)) {
+	if (fd_map < 0 || fstat(fd_map, &sb) < 0) {
 		perror(fname);
 		fail_file();
 	}
@@ -147,7 +177,7 @@ static void *mmap_file(char const *fname)
 	addr = mmap(0, sb.st_size, PROT_READ|PROT_WRITE, MAP_PRIVATE,
 		    fd_map, 0);
 	mmap_failed = 0;
-	if (MAP_FAILED == addr) {
+	if (addr == MAP_FAILED) {
 		mmap_failed = 1;
 		addr = umalloc(sb.st_size);
 		uread(fd_map, addr, sb.st_size);
@@ -206,12 +236,13 @@ static uint32_t (*w2)(uint16_t);
 static int
 is_mcounted_section_name(char const *const txtname)
 {
-	return 0 == strcmp(".text",           txtname) ||
-		0 == strcmp(".ref.text",      txtname) ||
-		0 == strcmp(".sched.text",    txtname) ||
-		0 == strcmp(".spinlock.text", txtname) ||
-		0 == strcmp(".irqentry.text", txtname) ||
-		0 == strcmp(".text.unlikely", txtname);
+	return strcmp(".text",           txtname) == 0 ||
+		strcmp(".ref.text",      txtname) == 0 ||
+		strcmp(".sched.text",    txtname) == 0 ||
+		strcmp(".spinlock.text", txtname) == 0 ||
+		strcmp(".irqentry.text", txtname) == 0 ||
+		strcmp(".kprobes.text", txtname) == 0 ||
+		strcmp(".text.unlikely", txtname) == 0;
 }
 
 /* 32 bit and 64 bit are very similar */
@@ -264,43 +295,48 @@ do_file(char const *const fname)
 	w8 = w8nat;
 	switch (ehdr->e_ident[EI_DATA]) {
 		static unsigned int const endian = 1;
-	default: {
+	default:
 		fprintf(stderr, "unrecognized ELF data encoding %d: %s\n",
 			ehdr->e_ident[EI_DATA], fname);
 		fail_file();
-	} break;
-	case ELFDATA2LSB: {
-		if (1 != *(unsigned char const *)&endian) {
+		break;
+	case ELFDATA2LSB:
+		if (*(unsigned char const *)&endian != 1) {
 			/* main() is big endian, file.o is little endian. */
 			w = w4rev;
 			w2 = w2rev;
 			w8 = w8rev;
 		}
-	} break;
-	case ELFDATA2MSB: {
-		if (0 != *(unsigned char const *)&endian) {
+		break;
+	case ELFDATA2MSB:
+		if (*(unsigned char const *)&endian != 0) {
 			/* main() is little endian, file.o is big endian. */
 			w = w4rev;
 			w2 = w2rev;
 			w8 = w8rev;
 		}
-	} break;
+		break;
 	}  /* end switch */
-	if (0 != memcmp(ELFMAG, ehdr->e_ident, SELFMAG)
-	||  ET_REL != w2(ehdr->e_type)
-	||  EV_CURRENT != ehdr->e_ident[EI_VERSION]) {
+	if (memcmp(ELFMAG, ehdr->e_ident, SELFMAG) != 0
+	||  w2(ehdr->e_type) != ET_REL
+	||  ehdr->e_ident[EI_VERSION] != EV_CURRENT) {
 		fprintf(stderr, "unrecognized ET_REL file %s\n", fname);
 		fail_file();
 	}
 
 	gpfx = 0;
 	switch (w2(ehdr->e_machine)) {
-	default: {
+	default:
 		fprintf(stderr, "unrecognized e_machine %d %s\n",
 			w2(ehdr->e_machine), fname);
 		fail_file();
-	} break;
-	case EM_386:	 reltype = R_386_32;                   break;
+		break;
+	case EM_386:
+		reltype = R_386_32;
+		make_nop = make_nop_x86;
+		ideal_nop = ideal_nop5_x86_32;
+		mcount_adjust_32 = -1;
+		break;
 	case EM_ARM:	 reltype = R_ARM_ABS32;
 			 altmcount = "__gnu_mcount_nc";
 			 break;
@@ -311,67 +347,91 @@ do_file(char const *const fname)
 	case EM_S390:    /* reltype: e_class    */ gpfx = '_'; break;
 	case EM_SH:	 reltype = R_SH_DIR32;                 break;
 	case EM_SPARCV9: reltype = R_SPARC_64;     gpfx = '_'; break;
-	case EM_X86_64:	 reltype = R_X86_64_64;                break;
+	case EM_X86_64:
+		make_nop = make_nop_x86;
+		ideal_nop = ideal_nop5_x86_64;
+		reltype = R_X86_64_64;
+		mcount_adjust_64 = -1;
+		break;
 	}  /* end switch */
 
 	switch (ehdr->e_ident[EI_CLASS]) {
-	default: {
+	default:
 		fprintf(stderr, "unrecognized ELF class %d %s\n",
 			ehdr->e_ident[EI_CLASS], fname);
 		fail_file();
-	} break;
-	case ELFCLASS32: {
-		if (sizeof(Elf32_Ehdr) != w2(ehdr->e_ehsize)
-		||  sizeof(Elf32_Shdr) != w2(ehdr->e_shentsize)) {
+		break;
+	case ELFCLASS32:
+		if (w2(ehdr->e_ehsize) != sizeof(Elf32_Ehdr)
+		||  w2(ehdr->e_shentsize) != sizeof(Elf32_Shdr)) {
 			fprintf(stderr,
 				"unrecognized ET_REL file: %s\n", fname);
 			fail_file();
 		}
-		if (EM_S390 == w2(ehdr->e_machine))
+		if (w2(ehdr->e_machine) == EM_S390) {
 			reltype = R_390_32;
-		if (EM_MIPS == w2(ehdr->e_machine)) {
+			mcount_adjust_32 = -4;
+		}
+		if (w2(ehdr->e_machine) == EM_MIPS) {
 			reltype = R_MIPS_32;
 			is_fake_mcount32 = MIPS32_is_fake_mcount;
 		}
 		do32(ehdr, fname, reltype);
-	} break;
+		break;
 	case ELFCLASS64: {
 		Elf64_Ehdr *const ghdr = (Elf64_Ehdr *)ehdr;
-		if (sizeof(Elf64_Ehdr) != w2(ghdr->e_ehsize)
-		||  sizeof(Elf64_Shdr) != w2(ghdr->e_shentsize)) {
+		if (w2(ghdr->e_ehsize) != sizeof(Elf64_Ehdr)
+		||  w2(ghdr->e_shentsize) != sizeof(Elf64_Shdr)) {
 			fprintf(stderr,
 				"unrecognized ET_REL file: %s\n", fname);
 			fail_file();
 		}
-		if (EM_S390 == w2(ghdr->e_machine))
+		if (w2(ghdr->e_machine) == EM_S390) {
 			reltype = R_390_64;
-		if (EM_MIPS == w2(ghdr->e_machine)) {
+			mcount_adjust_64 = -8;
+		}
+		if (w2(ghdr->e_machine) == EM_MIPS) {
 			reltype = R_MIPS_64;
 			Elf64_r_sym = MIPS64_r_sym;
 			Elf64_r_info = MIPS64_r_info;
 			is_fake_mcount64 = MIPS64_is_fake_mcount;
 		}
 		do64(ghdr, fname, reltype);
-	} break;
+		break;
+	}
 	}  /* end switch */
 
 	cleanup();
 }
 
 int
-main(int argc, char const *argv[])
+main(int argc, char *argv[])
 {
 	const char ftrace[] = "/ftrace.o";
 	int ftrace_size = sizeof(ftrace) - 1;
 	int n_error = 0;  /* gcc-4.3.0 false positive complaint */
+	int c;
+	int i;
+
+	while ((c = getopt(argc, argv, "w")) >= 0) {
+		switch (c) {
+		case 'w':
+			warn_on_notrace_sect = 1;
+			break;
+		default:
+			fprintf(stderr, "usage: recordmcount [-w] file.o...\n");
+			return 0;
+		}
+	}
 
-	if (argc <= 1) {
-		fprintf(stderr, "usage: recordmcount file.o...\n");
+	if ((argc - optind) < 1) {
+		fprintf(stderr, "usage: recordmcount [-w] file.o...\n");
 		return 0;
 	}
 
 	/* Process each file in turn, allowing deep failure. */
-	for (--argc, ++argv; 0 < argc; --argc, ++argv) {
+	for (i = optind; i < argc; i++) {
+		char *file = argv[i];
 		int const sjval = setjmp(jmpenv);
 		int len;
 
@@ -380,29 +440,29 @@ main(int argc, char const *argv[])
 		 * function but does not call it. Since ftrace.o should
 		 * not be traced anyway, we just skip it.
 		 */
-		len = strlen(argv[0]);
+		len = strlen(file);
 		if (len >= ftrace_size &&
-		    strcmp(argv[0] + (len - ftrace_size), ftrace) == 0)
+		    strcmp(file + (len - ftrace_size), ftrace) == 0)
 			continue;
 
 		switch (sjval) {
-		default: {
-			fprintf(stderr, "internal error: %s\n", argv[0]);
+		default:
+			fprintf(stderr, "internal error: %s\n", file);
 			exit(1);
-		} break;
-		case SJ_SETJMP: {  /* normal sequence */
+			break;
+		case SJ_SETJMP:    /* normal sequence */
 			/* Avoid problems if early cleanup() */
 			fd_map = -1;
 			ehdr_curr = NULL;
 			mmap_failed = 1;
-			do_file(argv[0]);
-		} break;
-		case SJ_FAIL: {  /* error in do_file or below */
+			do_file(file);
+			break;
+		case SJ_FAIL:    /* error in do_file or below */
 			++n_error;
-		} break;
-		case SJ_SUCCEED: {  /* premature success */
+			break;
+		case SJ_SUCCEED:    /* premature success */
 			/* do nothing */
-		} break;
+			break;
 		}  /* end switch */
 	}
 	return !!n_error;
diff --git a/scripts/recordmcount.h b/scripts/recordmcount.h
index baf187b..4be6036 100644
--- a/scripts/recordmcount.h
+++ b/scripts/recordmcount.h
@@ -22,11 +22,15 @@
 #undef is_fake_mcount
 #undef fn_is_fake_mcount
 #undef MIPS_is_fake_mcount
+#undef mcount_adjust
 #undef sift_rel_mcount
+#undef nop_mcount
 #undef find_secsym_ndx
 #undef __has_rel_mcount
 #undef has_rel_mcount
 #undef tot_relsize
+#undef get_mcountsym
+#undef get_sym_str_and_relp
 #undef do_func
 #undef Elf_Addr
 #undef Elf_Ehdr
@@ -49,14 +53,18 @@
 #ifdef RECORD_MCOUNT_64
 # define append_func		append64
 # define sift_rel_mcount	sift64_rel_mcount
+# define nop_mcount		nop_mcount_64
 # define find_secsym_ndx	find64_secsym_ndx
 # define __has_rel_mcount	__has64_rel_mcount
 # define has_rel_mcount		has64_rel_mcount
 # define tot_relsize		tot64_relsize
+# define get_sym_str_and_relp	get_sym_str_and_relp_64
 # define do_func		do64
+# define get_mcountsym		get_mcountsym_64
 # define is_fake_mcount		is_fake_mcount64
 # define fn_is_fake_mcount	fn_is_fake_mcount64
 # define MIPS_is_fake_mcount	MIPS64_is_fake_mcount
+# define mcount_adjust		mcount_adjust_64
 # define Elf_Addr		Elf64_Addr
 # define Elf_Ehdr		Elf64_Ehdr
 # define Elf_Shdr		Elf64_Shdr
@@ -77,14 +85,18 @@
 #else
 # define append_func		append32
 # define sift_rel_mcount	sift32_rel_mcount
+# define nop_mcount		nop_mcount_32
 # define find_secsym_ndx	find32_secsym_ndx
 # define __has_rel_mcount	__has32_rel_mcount
 # define has_rel_mcount		has32_rel_mcount
 # define tot_relsize		tot32_relsize
+# define get_sym_str_and_relp	get_sym_str_and_relp_32
 # define do_func		do32
+# define get_mcountsym		get_mcountsym_32
 # define is_fake_mcount		is_fake_mcount32
 # define fn_is_fake_mcount	fn_is_fake_mcount32
 # define MIPS_is_fake_mcount	MIPS32_is_fake_mcount
+# define mcount_adjust		mcount_adjust_32
 # define Elf_Addr		Elf32_Addr
 # define Elf_Ehdr		Elf32_Ehdr
 # define Elf_Shdr		Elf32_Shdr
@@ -123,6 +135,8 @@ static void fn_ELF_R_INFO(Elf_Rel *const rp, unsigned sym, unsigned type)
 }
 static void (*Elf_r_info)(Elf_Rel *const rp, unsigned sym, unsigned type) = fn_ELF_R_INFO;
 
+static int mcount_adjust = 0;
+
 /*
  * MIPS mcount long call has 2 _mcount symbols, only the position of the 1st
  * _mcount symbol is needed for dynamic function tracer, with it, to disable
@@ -234,6 +248,49 @@ static void append_func(Elf_Ehdr *const ehdr,
 	uwrite(fd_map, ehdr, sizeof(*ehdr));
 }
 
+static unsigned get_mcountsym(Elf_Sym const *const sym0,
+			      Elf_Rel const *relp,
+			      char const *const str0)
+{
+	unsigned mcountsym = 0;
+
+	Elf_Sym const *const symp =
+		&sym0[Elf_r_sym(relp)];
+	char const *symname = &str0[w(symp->st_name)];
+	char const *mcount = gpfx == '_' ? "_mcount" : "mcount";
+
+	if (symname[0] == '.')
+		++symname;  /* ppc64 hack */
+	if (strcmp(mcount, symname) == 0 ||
+	    (altmcount && strcmp(altmcount, symname) == 0))
+		mcountsym = Elf_r_sym(relp);
+
+	return mcountsym;
+}
+
+static void get_sym_str_and_relp(Elf_Shdr const *const relhdr,
+				 Elf_Ehdr const *const ehdr,
+				 Elf_Sym const **sym0,
+				 char const **str0,
+				 Elf_Rel const **relp)
+{
+	Elf_Shdr *const shdr0 = (Elf_Shdr *)(_w(ehdr->e_shoff)
+		+ (void *)ehdr);
+	unsigned const symsec_sh_link = w(relhdr->sh_link);
+	Elf_Shdr const *const symsec = &shdr0[symsec_sh_link];
+	Elf_Shdr const *const strsec = &shdr0[w(symsec->sh_link)];
+	Elf_Rel const *const rel0 = (Elf_Rel const *)(_w(relhdr->sh_offset)
+		+ (void *)ehdr);
+
+	*sym0 = (Elf_Sym const *)(_w(symsec->sh_offset)
+				  + (void *)ehdr);
+
+	*str0 = (char const *)(_w(strsec->sh_offset)
+			       + (void *)ehdr);
+
+	*relp = rel0;
+}
+
 /*
  * Look at the relocations in order to find the calls to mcount.
  * Accumulate the section offsets that are found, and their relocation info,
@@ -250,47 +307,27 @@ static uint_t *sift_rel_mcount(uint_t *mlocp,
 {
 	uint_t *const mloc0 = mlocp;
 	Elf_Rel *mrelp = *mrelpp;
-	Elf_Shdr *const shdr0 = (Elf_Shdr *)(_w(ehdr->e_shoff)
-		+ (void *)ehdr);
-	unsigned const symsec_sh_link = w(relhdr->sh_link);
-	Elf_Shdr const *const symsec = &shdr0[symsec_sh_link];
-	Elf_Sym const *const sym0 = (Elf_Sym const *)(_w(symsec->sh_offset)
-		+ (void *)ehdr);
-
-	Elf_Shdr const *const strsec = &shdr0[w(symsec->sh_link)];
-	char const *const str0 = (char const *)(_w(strsec->sh_offset)
-		+ (void *)ehdr);
-
-	Elf_Rel const *const rel0 = (Elf_Rel const *)(_w(relhdr->sh_offset)
-		+ (void *)ehdr);
+	Elf_Sym const *sym0;
+	char const *str0;
+	Elf_Rel const *relp;
 	unsigned rel_entsize = _w(relhdr->sh_entsize);
 	unsigned const nrel = _w(relhdr->sh_size) / rel_entsize;
-	Elf_Rel const *relp = rel0;
-
 	unsigned mcountsym = 0;
 	unsigned t;
 
+	get_sym_str_and_relp(relhdr, ehdr, &sym0, &str0, &relp);
+
 	for (t = nrel; t; --t) {
-		if (!mcountsym) {
-			Elf_Sym const *const symp =
-				&sym0[Elf_r_sym(relp)];
-			char const *symname = &str0[w(symp->st_name)];
-			char const *mcount = '_' == gpfx ? "_mcount" : "mcount";
-
-			if ('.' == symname[0])
-				++symname;  /* ppc64 hack */
-			if (0 == strcmp(mcount, symname) ||
-			    (altmcount && 0 == strcmp(altmcount, symname)))
-				mcountsym = Elf_r_sym(relp);
-		}
+		if (!mcountsym)
+			mcountsym = get_mcountsym(sym0, relp, str0);
 
 		if (mcountsym == Elf_r_sym(relp) && !is_fake_mcount(relp)) {
-			uint_t const addend = _w(_w(relp->r_offset) - recval);
-
+			uint_t const addend =
+				_w(_w(relp->r_offset) - recval + mcount_adjust);
 			mrelp->r_offset = _w(offbase
 				+ ((void *)mlocp - (void *)mloc0));
 			Elf_r_info(mrelp, recsym, reltype);
-			if (sizeof(Elf_Rela) == rel_entsize) {
+			if (rel_entsize == sizeof(Elf_Rela)) {
 				((Elf_Rela *)mrelp)->r_addend = addend;
 				*mlocp++ = 0;
 			} else
@@ -304,6 +341,63 @@ static uint_t *sift_rel_mcount(uint_t *mlocp,
 	return mlocp;
 }
 
+/*
+ * Read the relocation table again, but this time its called on sections
+ * that are not going to be traced. The mcount calls here will be converted
+ * into nops.
+ */
+static void nop_mcount(Elf_Shdr const *const relhdr,
+		       Elf_Ehdr const *const ehdr,
+		       const char *const txtname)
+{
+	Elf_Shdr *const shdr0 = (Elf_Shdr *)(_w(ehdr->e_shoff)
+		+ (void *)ehdr);
+	Elf_Sym const *sym0;
+	char const *str0;
+	Elf_Rel const *relp;
+	Elf_Shdr const *const shdr = &shdr0[w(relhdr->sh_info)];
+	unsigned rel_entsize = _w(relhdr->sh_entsize);
+	unsigned const nrel = _w(relhdr->sh_size) / rel_entsize;
+	unsigned mcountsym = 0;
+	unsigned t;
+	int once = 0;
+
+	get_sym_str_and_relp(relhdr, ehdr, &sym0, &str0, &relp);
+
+	for (t = nrel; t; --t) {
+		int ret = -1;
+
+		if (!mcountsym)
+			mcountsym = get_mcountsym(sym0, relp, str0);
+
+		if (mcountsym == Elf_r_sym(relp) && !is_fake_mcount(relp)) {
+			if (make_nop)
+				ret = make_nop((void *)ehdr, shdr->sh_offset + relp->r_offset);
+			if (warn_on_notrace_sect && !once) {
+				printf("Section %s has mcount callers being ignored\n",
+				       txtname);
+				once = 1;
+				/* just warn? */
+				if (!make_nop)
+					return;
+			}
+		}
+
+		/*
+		 * If we successfully removed the mcount, mark the relocation
+		 * as a nop (don't do anything with it).
+		 */
+		if (!ret) {
+			Elf_Rel rel;
+			rel = *(Elf_Rel *)relp;
+			Elf_r_info(&rel, Elf_r_sym(relp), rel_type_nop);
+			ulseek(fd_map, (void *)relp - (void *)ehdr, SEEK_SET);
+			uwrite(fd_map, &rel, sizeof(rel));
+		}
+		relp = (Elf_Rel const *)(rel_entsize + (void *)relp);
+	}
+}
+
 
 /*
  * Find a symbol in the given section, to be used as the base for relocating
@@ -354,13 +448,13 @@ __has_rel_mcount(Elf_Shdr const *const relhdr,  /* is SHT_REL or SHT_RELA */
 	Elf_Shdr const *const txthdr = &shdr0[w(relhdr->sh_info)];
 	char const *const txtname = &shstrtab[w(txthdr->sh_name)];
 
-	if (0 == strcmp("__mcount_loc", txtname)) {
+	if (strcmp("__mcount_loc", txtname) == 0) {
 		fprintf(stderr, "warning: __mcount_loc already exists: %s\n",
 			fname);
 		succeed_file();
 	}
-	if (SHT_PROGBITS != w(txthdr->sh_type) ||
-	    !is_mcounted_section_name(txtname))
+	if (w(txthdr->sh_type) != SHT_PROGBITS ||
+	    !(w(txthdr->sh_flags) & SHF_EXECINSTR))
 		return NULL;
 	return txtname;
 }
@@ -370,7 +464,7 @@ static char const *has_rel_mcount(Elf_Shdr const *const relhdr,
 				  char const *const shstrtab,
 				  char const *const fname)
 {
-	if (SHT_REL  != w(relhdr->sh_type) && SHT_RELA != w(relhdr->sh_type))
+	if (w(relhdr->sh_type) != SHT_REL && w(relhdr->sh_type) != SHT_RELA)
 		return NULL;
 	return __has_rel_mcount(relhdr, shdr0, shstrtab, fname);
 }
@@ -383,9 +477,11 @@ static unsigned tot_relsize(Elf_Shdr const *const shdr0,
 {
 	unsigned totrelsz = 0;
 	Elf_Shdr const *shdrp = shdr0;
+	char const *txtname;
 
 	for (; nhdr; --nhdr, ++shdrp) {
-		if (has_rel_mcount(shdrp, shdr0, shstrtab, fname))
+		txtname = has_rel_mcount(shdrp, shdr0, shstrtab, fname);
+		if (txtname && is_mcounted_section_name(txtname))
 			totrelsz += _w(shdrp->sh_size);
 	}
 	return totrelsz;
@@ -421,7 +517,7 @@ do_func(Elf_Ehdr *const ehdr, char const *const fname, unsigned const reltype)
 	for (relhdr = shdr0, k = nhdr; k; --k, ++relhdr) {
 		char const *const txtname = has_rel_mcount(relhdr, shdr0,
 			shstrtab, fname);
-		if (txtname) {
+		if (txtname && is_mcounted_section_name(txtname)) {
 			uint_t recval = 0;
 			unsigned const recsym = find_secsym_ndx(
 				w(relhdr->sh_info), txtname, &recval,
@@ -432,6 +528,12 @@ do_func(Elf_Ehdr *const ehdr, char const *const fname, unsigned const reltype)
 			mlocp = sift_rel_mcount(mlocp,
 				(void *)mlocp - (void *)mloc0, &mrelp,
 				relhdr, ehdr, recsym, recval, reltype);
+		} else if (txtname && (warn_on_notrace_sect || make_nop)) {
+			/*
+			 * This section is ignored by ftrace, but still
+			 * has mcount calls. Convert them to nops now.
+			 */
+			nop_mcount(relhdr, ehdr, txtname);
 		}
 	}
 	if (mloc0 != mlocp) {
diff --git a/scripts/recordmcount.pl b/scripts/recordmcount.pl
index 4be0dee..858966a 100755
--- a/scripts/recordmcount.pl
+++ b/scripts/recordmcount.pl
@@ -134,6 +134,7 @@ my %text_sections = (
      ".sched.text" => 1,
      ".spinlock.text" => 1,
      ".irqentry.text" => 1,
+     ".kprobes.text" => 1,
      ".text.unlikely" => 1,
 );
 
@@ -222,6 +223,7 @@ if ($arch eq "x86_64") {
     $mcount_regex = "^\\s*([0-9a-fA-F]+):.*\\smcount([+-]0x[0-9a-zA-Z]+)?\$";
     $type = ".quad";
     $alignment = 8;
+    $mcount_adjust = -1;
 
     # force flags for this arch
     $ld .= " -m elf_x86_64";
@@ -231,6 +233,7 @@ if ($arch eq "x86_64") {
 
 } elsif ($arch eq "i386") {
     $alignment = 4;
+    $mcount_adjust = -1;
 
     # force flags for this arch
     $ld .= " -m elf_i386";
@@ -240,12 +243,14 @@ if ($arch eq "x86_64") {
 
 } elsif ($arch eq "s390" && $bits == 32) {
     $mcount_regex = "^\\s*([0-9a-fA-F]+):\\s*R_390_32\\s+_mcount\$";
+    $mcount_adjust = -4;
     $alignment = 4;
     $ld .= " -m elf_s390";
     $cc .= " -m31";
 
 } elsif ($arch eq "s390" && $bits == 64) {
     $mcount_regex = "^\\s*([0-9a-fA-F]+):\\s*R_390_(PC|PLT)32DBL\\s+_mcount\\+0x2\$";
+    $mcount_adjust = -8;
     $alignment = 8;
     $type = ".quad";
     $ld .= " -m elf64_s390";
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 602c3c9..a9f0671 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -6,24 +6,28 @@
  *
  * Sample output:
 
-   $ perf stat ~/hackbench 10
-   Time: 0.104
+   $ perf stat ./hackbench 10
 
-    Performance counter stats for '/home/mingo/hackbench':
+  Time: 0.118
 
-       1255.538611  task clock ticks     #      10.143 CPU utilization factor
-             54011  context switches     #       0.043 M/sec
-               385  CPU migrations       #       0.000 M/sec
-             17755  pagefaults           #       0.014 M/sec
-        3808323185  CPU cycles           #    3033.219 M/sec
-        1575111190  instructions         #    1254.530 M/sec
-          17367895  cache references     #      13.833 M/sec
-           7674421  cache misses         #       6.112 M/sec
+  Performance counter stats for './hackbench 10':
 
-    Wall-clock time elapsed:   123.786620 msecs
+       1708.761321 task-clock                #   11.037 CPUs utilized
+            41,190 context-switches          #    0.024 M/sec
+             6,735 CPU-migrations            #    0.004 M/sec
+            17,318 page-faults               #    0.010 M/sec
+     5,205,202,243 cycles                    #    3.046 GHz
+     3,856,436,920 stalled-cycles-frontend   #   74.09% frontend cycles idle
+     1,600,790,871 stalled-cycles-backend    #   30.75% backend  cycles idle
+     2,603,501,247 instructions              #    0.50  insns per cycle
+                                             #    1.48  stalled cycles per insn
+       484,357,498 branches                  #  283.455 M/sec
+         6,388,934 branch-misses             #    1.32% of all branches
+
+        0.154822978  seconds time elapsed
 
  *
- * Copyright (C) 2008, Red Hat Inc, Ingo Molnar <mingo@redhat.com>
+ * Copyright (C) 2008-2011, Red Hat Inc, Ingo Molnar <mingo@redhat.com>
  *
  * Improvements and fixes by:
  *
@@ -75,22 +79,10 @@ static struct perf_event_attr default_attrs[] = {
 };
 
 /*
- * Detailed stats:
+ * Detailed stats (-d), covering the L1 and last level data caches:
  */
 static struct perf_event_attr detailed_attrs[] = {
 
-  { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_TASK_CLOCK		},
-  { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_CONTEXT_SWITCHES	},
-  { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_CPU_MIGRATIONS		},
-  { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_PAGE_FAULTS		},
-
-  { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_CPU_CYCLES		},
-  { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_STALLED_CYCLES_FRONTEND	},
-  { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_STALLED_CYCLES_BACKEND	},
-  { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_INSTRUCTIONS		},
-  { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_BRANCH_INSTRUCTIONS	},
-  { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_BRANCH_MISSES		},
-
   { .type = PERF_TYPE_HW_CACHE,
     .config =
 	 PERF_COUNT_HW_CACHE_L1D		<<  0  |
@@ -116,6 +108,69 @@ static struct perf_event_attr detailed_attrs[] = {
 	(PERF_COUNT_HW_CACHE_RESULT_MISS	<< 16)				},
 };
 
+/*
+ * Very detailed stats (-d -d), covering the instruction cache and the TLB caches:
+ */
+static struct perf_event_attr very_detailed_attrs[] = {
+
+  { .type = PERF_TYPE_HW_CACHE,
+    .config =
+	 PERF_COUNT_HW_CACHE_L1I		<<  0  |
+	(PERF_COUNT_HW_CACHE_OP_READ		<<  8) |
+	(PERF_COUNT_HW_CACHE_RESULT_ACCESS	<< 16)				},
+
+  { .type = PERF_TYPE_HW_CACHE,
+    .config =
+	 PERF_COUNT_HW_CACHE_L1I		<<  0  |
+	(PERF_COUNT_HW_CACHE_OP_READ		<<  8) |
+	(PERF_COUNT_HW_CACHE_RESULT_MISS	<< 16)				},
+
+  { .type = PERF_TYPE_HW_CACHE,
+    .config =
+	 PERF_COUNT_HW_CACHE_DTLB		<<  0  |
+	(PERF_COUNT_HW_CACHE_OP_READ		<<  8) |
+	(PERF_COUNT_HW_CACHE_RESULT_ACCESS	<< 16)				},
+
+  { .type = PERF_TYPE_HW_CACHE,
+    .config =
+	 PERF_COUNT_HW_CACHE_DTLB		<<  0  |
+	(PERF_COUNT_HW_CACHE_OP_READ		<<  8) |
+	(PERF_COUNT_HW_CACHE_RESULT_MISS	<< 16)				},
+
+  { .type = PERF_TYPE_HW_CACHE,
+    .config =
+	 PERF_COUNT_HW_CACHE_ITLB		<<  0  |
+	(PERF_COUNT_HW_CACHE_OP_READ		<<  8) |
+	(PERF_COUNT_HW_CACHE_RESULT_ACCESS	<< 16)				},
+
+  { .type = PERF_TYPE_HW_CACHE,
+    .config =
+	 PERF_COUNT_HW_CACHE_ITLB		<<  0  |
+	(PERF_COUNT_HW_CACHE_OP_READ		<<  8) |
+	(PERF_COUNT_HW_CACHE_RESULT_MISS	<< 16)				},
+
+};
+
+/*
+ * Very, very detailed stats (-d -d -d), adding prefetch events:
+ */
+static struct perf_event_attr very_very_detailed_attrs[] = {
+
+  { .type = PERF_TYPE_HW_CACHE,
+    .config =
+	 PERF_COUNT_HW_CACHE_L1D		<<  0  |
+	(PERF_COUNT_HW_CACHE_OP_PREFETCH	<<  8) |
+	(PERF_COUNT_HW_CACHE_RESULT_ACCESS	<< 16)				},
+
+  { .type = PERF_TYPE_HW_CACHE,
+    .config =
+	 PERF_COUNT_HW_CACHE_L1D		<<  0  |
+	(PERF_COUNT_HW_CACHE_OP_PREFETCH	<<  8) |
+	(PERF_COUNT_HW_CACHE_RESULT_MISS	<< 16)				},
+};
+
+
+
 struct perf_evlist		*evsel_list;
 
 static bool			system_wide			=  false;
@@ -129,7 +184,7 @@ static pid_t			target_pid			= -1;
 static pid_t			target_tid			= -1;
 static pid_t			child_pid			= -1;
 static bool			null_run			=  false;
-static bool			detailed_run			=  false;
+static int			detailed_run			=  0;
 static bool			sync_run			=  false;
 static bool			big_num				=  true;
 static int			big_num_opt			=  -1;
@@ -206,6 +261,10 @@ struct stats			runtime_stalled_cycles_back_stats[MAX_NR_CPUS];
 struct stats			runtime_branches_stats[MAX_NR_CPUS];
 struct stats			runtime_cacherefs_stats[MAX_NR_CPUS];
 struct stats			runtime_l1_dcache_stats[MAX_NR_CPUS];
+struct stats			runtime_l1_icache_stats[MAX_NR_CPUS];
+struct stats			runtime_ll_cache_stats[MAX_NR_CPUS];
+struct stats			runtime_itlb_cache_stats[MAX_NR_CPUS];
+struct stats			runtime_dtlb_cache_stats[MAX_NR_CPUS];
 struct stats			walltime_nsecs_stats;
 
 static int create_perf_stat_counter(struct perf_evsel *evsel)
@@ -262,6 +321,14 @@ static void update_shadow_stats(struct perf_evsel *counter, u64 *count)
 		update_stats(&runtime_cacherefs_stats[0], count[0]);
 	else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_L1D))
 		update_stats(&runtime_l1_dcache_stats[0], count[0]);
+	else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_L1I))
+		update_stats(&runtime_l1_icache_stats[0], count[0]);
+	else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_LL))
+		update_stats(&runtime_ll_cache_stats[0], count[0]);
+	else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_DTLB))
+		update_stats(&runtime_dtlb_cache_stats[0], count[0]);
+	else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_ITLB))
+		update_stats(&runtime_itlb_cache_stats[0], count[0]);
 }
 
 /*
@@ -464,7 +531,7 @@ static void nsec_printout(int cpu, struct perf_evsel *evsel, double avg)
 {
 	double msecs = avg / 1e6;
 	char cpustr[16] = { '\0', };
-	const char *fmt = csv_output ? "%s%.6f%s%s" : "%s%18.6f%s%-24s";
+	const char *fmt = csv_output ? "%s%.6f%s%s" : "%s%18.6f%s%-25s";
 
 	if (no_aggr)
 		sprintf(cpustr, "CPU%*d%s",
@@ -575,6 +642,98 @@ static void print_l1_dcache_misses(int cpu, struct perf_evsel *evsel __used, dou
 	fprintf(stderr, " of all L1-dcache hits  ");
 }
 
+static void print_l1_icache_misses(int cpu, struct perf_evsel *evsel __used, double avg)
+{
+	double total, ratio = 0.0;
+	const char *color;
+
+	total = avg_stats(&runtime_l1_icache_stats[cpu]);
+
+	if (total)
+		ratio = avg / total * 100.0;
+
+	color = PERF_COLOR_NORMAL;
+	if (ratio > 20.0)
+		color = PERF_COLOR_RED;
+	else if (ratio > 10.0)
+		color = PERF_COLOR_MAGENTA;
+	else if (ratio > 5.0)
+		color = PERF_COLOR_YELLOW;
+
+	fprintf(stderr, " #  ");
+	color_fprintf(stderr, color, "%6.2f%%", ratio);
+	fprintf(stderr, " of all L1-icache hits  ");
+}
+
+static void print_dtlb_cache_misses(int cpu, struct perf_evsel *evsel __used, double avg)
+{
+	double total, ratio = 0.0;
+	const char *color;
+
+	total = avg_stats(&runtime_dtlb_cache_stats[cpu]);
+
+	if (total)
+		ratio = avg / total * 100.0;
+
+	color = PERF_COLOR_NORMAL;
+	if (ratio > 20.0)
+		color = PERF_COLOR_RED;
+	else if (ratio > 10.0)
+		color = PERF_COLOR_MAGENTA;
+	else if (ratio > 5.0)
+		color = PERF_COLOR_YELLOW;
+
+	fprintf(stderr, " #  ");
+	color_fprintf(stderr, color, "%6.2f%%", ratio);
+	fprintf(stderr, " of all dTLB cache hits ");
+}
+
+static void print_itlb_cache_misses(int cpu, struct perf_evsel *evsel __used, double avg)
+{
+	double total, ratio = 0.0;
+	const char *color;
+
+	total = avg_stats(&runtime_itlb_cache_stats[cpu]);
+
+	if (total)
+		ratio = avg / total * 100.0;
+
+	color = PERF_COLOR_NORMAL;
+	if (ratio > 20.0)
+		color = PERF_COLOR_RED;
+	else if (ratio > 10.0)
+		color = PERF_COLOR_MAGENTA;
+	else if (ratio > 5.0)
+		color = PERF_COLOR_YELLOW;
+
+	fprintf(stderr, " #  ");
+	color_fprintf(stderr, color, "%6.2f%%", ratio);
+	fprintf(stderr, " of all iTLB cache hits ");
+}
+
+static void print_ll_cache_misses(int cpu, struct perf_evsel *evsel __used, double avg)
+{
+	double total, ratio = 0.0;
+	const char *color;
+
+	total = avg_stats(&runtime_ll_cache_stats[cpu]);
+
+	if (total)
+		ratio = avg / total * 100.0;
+
+	color = PERF_COLOR_NORMAL;
+	if (ratio > 20.0)
+		color = PERF_COLOR_RED;
+	else if (ratio > 10.0)
+		color = PERF_COLOR_MAGENTA;
+	else if (ratio > 5.0)
+		color = PERF_COLOR_YELLOW;
+
+	fprintf(stderr, " #  ");
+	color_fprintf(stderr, color, "%6.2f%%", ratio);
+	fprintf(stderr, " of all LL-cache hits   ");
+}
+
 static void abs_printout(int cpu, struct perf_evsel *evsel, double avg)
 {
 	double total, ratio = 0.0;
@@ -584,9 +743,9 @@ static void abs_printout(int cpu, struct perf_evsel *evsel, double avg)
 	if (csv_output)
 		fmt = "%s%.0f%s%s";
 	else if (big_num)
-		fmt = "%s%'18.0f%s%-24s";
+		fmt = "%s%'18.0f%s%-25s";
 	else
-		fmt = "%s%18.0f%s%-24s";
+		fmt = "%s%18.0f%s%-25s";
 
 	if (no_aggr)
 		sprintf(cpustr, "CPU%*d%s",
@@ -616,7 +775,7 @@ static void abs_printout(int cpu, struct perf_evsel *evsel, double avg)
 
 		if (total && avg) {
 			ratio = total / avg;
-			fprintf(stderr, "\n                                            #   %5.2f  stalled cycles per insn", ratio);
+			fprintf(stderr, "\n                                             #   %5.2f  stalled cycles per insn", ratio);
 		}
 
 	} else if (perf_evsel__match(evsel, HARDWARE, HW_BRANCH_MISSES) &&
@@ -629,6 +788,34 @@ static void abs_printout(int cpu, struct perf_evsel *evsel, double avg)
 					((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
 			runtime_l1_dcache_stats[cpu].n != 0) {
 		print_l1_dcache_misses(cpu, evsel, avg);
+	} else if (
+		evsel->attr.type == PERF_TYPE_HW_CACHE &&
+		evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_L1I |
+					((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
+					((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
+			runtime_l1_icache_stats[cpu].n != 0) {
+		print_l1_icache_misses(cpu, evsel, avg);
+	} else if (
+		evsel->attr.type == PERF_TYPE_HW_CACHE &&
+		evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_DTLB |
+					((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
+					((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
+			runtime_dtlb_cache_stats[cpu].n != 0) {
+		print_dtlb_cache_misses(cpu, evsel, avg);
+	} else if (
+		evsel->attr.type == PERF_TYPE_HW_CACHE &&
+		evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_ITLB |
+					((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
+					((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
+			runtime_itlb_cache_stats[cpu].n != 0) {
+		print_itlb_cache_misses(cpu, evsel, avg);
+	} else if (
+		evsel->attr.type == PERF_TYPE_HW_CACHE &&
+		evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_LL |
+					((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
+					((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
+			runtime_ll_cache_stats[cpu].n != 0) {
+		print_ll_cache_misses(cpu, evsel, avg);
 	} else if (perf_evsel__match(evsel, HARDWARE, HW_CACHE_MISSES) &&
 			runtime_cacherefs_stats[cpu].n != 0) {
 		total = avg_stats(&runtime_cacherefs_stats[cpu]);
@@ -704,7 +891,7 @@ static void print_counter_aggr(struct perf_evsel *counter)
 		avg_enabled = avg_stats(&ps->res_stats[1]);
 		avg_running = avg_stats(&ps->res_stats[2]);
 
-		fprintf(stderr, "  (%.2f%%)", 100 * avg_running / avg_enabled);
+		fprintf(stderr, " [%5.2f%%]", 100 * avg_running / avg_enabled);
 	}
 	fprintf(stderr, "\n");
 }
@@ -787,10 +974,12 @@ static void print_stat(int argc, const char **argv)
 	}
 
 	if (!csv_output) {
-		fprintf(stderr, "\n");
-		fprintf(stderr, " %18.9f  seconds time elapsed",
+		if (!null_run)
+			fprintf(stderr, "\n");
+		fprintf(stderr, " %17.9f seconds time elapsed",
 				avg_stats(&walltime_nsecs_stats)/1e9);
 		if (run_count > 1) {
+			fprintf(stderr, "                                        ");
 			print_noise_pct(stddev_stats(&walltime_nsecs_stats),
 					avg_stats(&walltime_nsecs_stats));
 		}
@@ -854,7 +1043,7 @@ static const struct option options[] = {
 		    "repeat command and print average + stddev (max: 100)"),
 	OPT_BOOLEAN('n', "null", &null_run,
 		    "null run - dont start any counters"),
-	OPT_BOOLEAN('d', "detailed", &detailed_run,
+	OPT_INCR('d', "detailed", &detailed_run,
 		    "detailed run - start a lot of events"),
 	OPT_BOOLEAN('S', "sync", &sync_run,
 		    "call sync() before starting a run"),
@@ -873,6 +1062,70 @@ static const struct option options[] = {
 	OPT_END()
 };
 
+/*
+ * Add default attributes, if there were no attributes specified or
+ * if -d/--detailed, -d -d or -d -d -d is used:
+ */
+static int add_default_attributes(void)
+{
+	struct perf_evsel *pos;
+	size_t attr_nr = 0;
+	size_t c;
+
+	/* Set attrs if no event is selected and !null_run: */
+	if (null_run)
+		return 0;
+
+	if (!evsel_list->nr_entries) {
+		for (c = 0; c < ARRAY_SIZE(default_attrs); c++) {
+			pos = perf_evsel__new(default_attrs + c, c + attr_nr);
+			if (pos == NULL)
+				return -1;
+			perf_evlist__add(evsel_list, pos);
+		}
+		attr_nr += c;
+	}
+
+	/* Detailed events get appended to the event list: */
+
+	if (detailed_run <  1)
+		return 0;
+
+	/* Append detailed run extra attributes: */
+	for (c = 0; c < ARRAY_SIZE(detailed_attrs); c++) {
+		pos = perf_evsel__new(detailed_attrs + c, c + attr_nr);
+		if (pos == NULL)
+			return -1;
+		perf_evlist__add(evsel_list, pos);
+	}
+	attr_nr += c;
+
+	if (detailed_run < 2)
+		return 0;
+
+	/* Append very detailed run extra attributes: */
+	for (c = 0; c < ARRAY_SIZE(very_detailed_attrs); c++) {
+		pos = perf_evsel__new(very_detailed_attrs + c, c + attr_nr);
+		if (pos == NULL)
+			return -1;
+		perf_evlist__add(evsel_list, pos);
+	}
+
+	if (detailed_run < 3)
+		return 0;
+
+	/* Append very, very detailed run extra attributes: */
+	for (c = 0; c < ARRAY_SIZE(very_very_detailed_attrs); c++) {
+		pos = perf_evsel__new(very_very_detailed_attrs + c, c + attr_nr);
+		if (pos == NULL)
+			return -1;
+		perf_evlist__add(evsel_list, pos);
+	}
+
+
+	return 0;
+}
+
 int cmd_stat(int argc, const char **argv, const char *prefix __used)
 {
 	struct perf_evsel *pos;
@@ -918,28 +1171,8 @@ int cmd_stat(int argc, const char **argv, const char *prefix __used)
 		usage_with_options(stat_usage, options);
 	}
 
-	/* Set attrs and nr_counters if no event is selected and !null_run */
-	if (detailed_run) {
-		size_t c;
-
-		for (c = 0; c < ARRAY_SIZE(detailed_attrs); ++c) {
-			pos = perf_evsel__new(&detailed_attrs[c], c);
-			if (pos == NULL)
-				goto out;
-			perf_evlist__add(evsel_list, pos);
-		}
-	}
-	/* Set attrs and nr_counters if no event is selected and !null_run */
-	if (!detailed_run && !null_run && !evsel_list->nr_entries) {
-		size_t c;
-
-		for (c = 0; c < ARRAY_SIZE(default_attrs); ++c) {
-			pos = perf_evsel__new(&default_attrs[c], c);
-			if (pos == NULL)
-				goto out;
-			perf_evlist__add(evsel_list, pos);
-		}
-	}
+	if (add_default_attributes())
+		goto out;
 
 	if (target_pid != -1)
 		target_tid = target_pid;
diff --git a/tools/perf/util/include/asm/alternative-asm.h b/tools/perf/util/include/asm/alternative-asm.h
new file mode 100644
index 0000000..6789d78
--- /dev/null
+++ b/tools/perf/util/include/asm/alternative-asm.h
@@ -0,0 +1,8 @@
+#ifndef _PERF_ASM_ALTERNATIVE_ASM_H
+#define _PERF_ASM_ALTERNATIVE_ASM_H
+
+/* Just disable it so we can build arch/x86/lib/memcpy_64.S for perf bench: */
+
+#define altinstruction_entry #
+
+#endif