19 files changed, 463 insertions, 182 deletions

diff --git a/arch/alpha/include/asm/hardirq.h b/arch/alpha/include/asm/hardirq.h
index d953e234daa..88971460fa6 100644
--- a/arch/alpha/include/asm/hardirq.h
+++ b/arch/alpha/include/asm/hardirq.h
@@ -14,17 +14,4 @@ typedef struct {
 
 void ack_bad_irq(unsigned int irq);
 
-#define HARDIRQ_BITS	12
-
-/*
- * The hardirq mask has to be large enough to have
- * space for potentially nestable IRQ sources in the system
- * to nest on a single CPU. On Alpha, interrupts are masked at the CPU
- * by IPL as well as at the system level. We only have 8 IPLs (UNIX PALcode)
- * so we really only have 8 nestable IRQs, but allow some overhead
- */
-#if (1 << HARDIRQ_BITS) < 16
-#error HARDIRQ_BITS is too low!
-#endif
-
 #endif /* _ALPHA_HARDIRQ_H */
diff --git a/arch/avr32/include/asm/hardirq.h b/arch/avr32/include/asm/hardirq.h
index 267354356f6..015bc75ea79 100644
--- a/arch/avr32/include/asm/hardirq.h
+++ b/arch/avr32/include/asm/hardirq.h
@@ -20,15 +20,4 @@ void ack_bad_irq(unsigned int irq);
 
 #endif /* __ASSEMBLY__ */
 
-#define HARDIRQ_BITS	12
-
-/*
- * 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) < NR_IRQS
-# error HARDIRQ_BITS is too low!
-#endif
-
 #endif /* __ASM_AVR32_HARDIRQ_H */
diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig
index 4eb45c01249..5b2a2379a43 100644
--- a/arch/ia64/Kconfig
+++ b/arch/ia64/Kconfig
@@ -22,6 +22,9 @@ config IA64
 	select HAVE_OPROFILE
 	select HAVE_KPROBES
 	select HAVE_KRETPROBES
+	select HAVE_FTRACE_MCOUNT_RECORD
+	select HAVE_DYNAMIC_FTRACE if (!ITANIUM)
+	select HAVE_FUNCTION_TRACER
 	select HAVE_DMA_ATTRS
 	select HAVE_KVM
 	select HAVE_ARCH_TRACEHOOK
diff --git a/arch/ia64/include/asm/ftrace.h b/arch/ia64/include/asm/ftrace.h
new file mode 100644
index 00000000000..d20db3c2a65
--- /dev/null
+++ b/arch/ia64/include/asm/ftrace.h
@@ -0,0 +1,28 @@
+#ifndef _ASM_IA64_FTRACE_H
+#define _ASM_IA64_FTRACE_H
+
+#ifdef CONFIG_FUNCTION_TRACER
+#define MCOUNT_INSN_SIZE        32 /* sizeof mcount call */
+
+#ifndef __ASSEMBLY__
+extern void _mcount(unsigned long pfs, unsigned long r1, unsigned long b0, unsigned long r0);
+#define mcount _mcount
+
+#include <asm/kprobes.h>
+/* In IA64, MCOUNT_ADDR is set in link time, so it's not a constant at compile time */
+#define MCOUNT_ADDR (((struct fnptr *)mcount)->ip)
+#define FTRACE_ADDR (((struct fnptr *)ftrace_caller)->ip)
+
+static inline unsigned long ftrace_call_adjust(unsigned long addr)
+{
+	/* second bundle, insn 2 */
+	return addr - 0x12;
+}
+
+struct dyn_arch_ftrace {
+};
+#endif
+
+#endif /* CONFIG_FUNCTION_TRACER */
+
+#endif /* _ASM_IA64_FTRACE_H */
diff --git a/arch/ia64/include/asm/hardirq.h b/arch/ia64/include/asm/hardirq.h
index 140e495b8e0..d514cd9edb4 100644
--- a/arch/ia64/include/asm/hardirq.h
+++ b/arch/ia64/include/asm/hardirq.h
@@ -20,16 +20,6 @@
 
 #define local_softirq_pending()		(local_cpu_data->softirq_pending)
 
-#define HARDIRQ_BITS	14
-
-/*
- * 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) < NR_IRQS
-# error HARDIRQ_BITS is too low!
-#endif
-
 extern void __iomem *ipi_base_addr;
 
 void ack_bad_irq(unsigned int irq);
diff --git a/arch/ia64/kernel/Makefile b/arch/ia64/kernel/Makefile
index c381ea95489..ab6e7ec0bba 100644
--- a/arch/ia64/kernel/Makefile
+++ b/arch/ia64/kernel/Makefile
@@ -2,6 +2,10 @@
 # Makefile for the linux kernel.
 #
 
+ifdef CONFIG_DYNAMIC_FTRACE
+CFLAGS_REMOVE_ftrace.o = -pg
+endif
+
 extra-y	:= head.o init_task.o vmlinux.lds
 
 obj-y := acpi.o entry.o efi.o efi_stub.o gate-data.o fsys.o ia64_ksyms.o irq.o irq_ia64.o	\
@@ -28,6 +32,7 @@ obj-$(CONFIG_IA64_CYCLONE)	+= cyclone.o
 obj-$(CONFIG_CPU_FREQ)		+= cpufreq/
 obj-$(CONFIG_IA64_MCA_RECOVERY)	+= mca_recovery.o
 obj-$(CONFIG_KPROBES)		+= kprobes.o jprobes.o
+obj-$(CONFIG_DYNAMIC_FTRACE)	+= ftrace.o
 obj-$(CONFIG_KEXEC)		+= machine_kexec.o relocate_kernel.o crash.o
 obj-$(CONFIG_CRASH_DUMP)	+= crash_dump.o
 obj-$(CONFIG_IA64_UNCACHED_ALLOCATOR)	+= uncached.o
diff --git a/arch/ia64/kernel/entry.S b/arch/ia64/kernel/entry.S
index e5341e2c117..7e3382b06d5 100644
--- a/arch/ia64/kernel/entry.S
+++ b/arch/ia64/kernel/entry.S
@@ -47,6 +47,7 @@
 #include <asm/processor.h>
 #include <asm/thread_info.h>
 #include <asm/unistd.h>
+#include <asm/ftrace.h>
 
 #include "minstate.h"
 
@@ -1404,6 +1405,105 @@ GLOBAL_ENTRY(unw_init_running)
 	br.ret.sptk.many rp
 END(unw_init_running)
 
+#ifdef CONFIG_FUNCTION_TRACER
+#ifdef CONFIG_DYNAMIC_FTRACE
+GLOBAL_ENTRY(_mcount)
+	br ftrace_stub
+END(_mcount)
+
+.here:
+	br.ret.sptk.many b0
+
+GLOBAL_ENTRY(ftrace_caller)
+	alloc out0 = ar.pfs, 8, 0, 4, 0
+	mov out3 = r0
+	;;
+	mov out2 = b0
+	add r3 = 0x20, r3
+	mov out1 = r1;
+	br.call.sptk.many b0 = ftrace_patch_gp
+	//this might be called from module, so we must patch gp
+ftrace_patch_gp:
+	movl gp=__gp
+	mov b0 = r3
+	;;
+.global ftrace_call;
+ftrace_call:
+{
+	.mlx
+	nop.m 0x0
+	movl r3 = .here;;
+}
+	alloc loc0 = ar.pfs, 4, 4, 2, 0
+	;;
+	mov loc1 = b0
+	mov out0 = b0
+	mov loc2 = r8
+	mov loc3 = r15
+	;;
+	adds out0 = -MCOUNT_INSN_SIZE, out0
+	mov out1 = in2
+	mov b6 = r3
+
+	br.call.sptk.many b0 = b6
+	;;
+	mov ar.pfs = loc0
+	mov b0 = loc1
+	mov r8 = loc2
+	mov r15 = loc3
+	br ftrace_stub
+	;;
+END(ftrace_caller)
+
+#else
+GLOBAL_ENTRY(_mcount)
+	movl r2 = ftrace_stub
+	movl r3 = ftrace_trace_function;;
+	ld8 r3 = [r3];;
+	ld8 r3 = [r3];;
+	cmp.eq p7,p0 = r2, r3
+(p7)	br.sptk.many ftrace_stub
+	;;
+
+	alloc loc0 = ar.pfs, 4, 4, 2, 0
+	;;
+	mov loc1 = b0
+	mov out0 = b0
+	mov loc2 = r8
+	mov loc3 = r15
+	;;
+	adds out0 = -MCOUNT_INSN_SIZE, out0
+	mov out1 = in2
+	mov b6 = r3
+
+	br.call.sptk.many b0 = b6
+	;;
+	mov ar.pfs = loc0
+	mov b0 = loc1
+	mov r8 = loc2
+	mov r15 = loc3
+	br ftrace_stub
+	;;
+END(_mcount)
+#endif
+
+GLOBAL_ENTRY(ftrace_stub)
+	mov r3 = b0
+	movl r2 = _mcount_ret_helper
+	;;
+	mov b6 = r2
+	mov b7 = r3
+	br.ret.sptk.many b6
+
+_mcount_ret_helper:
+	mov b0 = r42
+	mov r1 = r41
+	mov ar.pfs = r40
+	br b7
+END(ftrace_stub)
+
+#endif /* CONFIG_FUNCTION_TRACER */
+
 	.rodata
 	.align 8
 	.globl sys_call_table
diff --git a/arch/ia64/kernel/ftrace.c b/arch/ia64/kernel/ftrace.c
new file mode 100644
index 00000000000..7fc8c961b1f
--- /dev/null
+++ b/arch/ia64/kernel/ftrace.c
@@ -0,0 +1,206 @@
+/*
+ * Dynamic function tracing support.
+ *
+ * Copyright (C) 2008 Shaohua Li <shaohua.li@intel.com>
+ *
+ * For licencing details, see COPYING.
+ *
+ * Defines low-level handling of mcount calls when the kernel
+ * is compiled with the -pg flag. When using dynamic ftrace, the
+ * mcount call-sites get patched lazily with NOP till they are
+ * enabled. All code mutation routines here take effect atomically.
+ */
+
+#include <linux/uaccess.h>
+#include <linux/ftrace.h>
+
+#include <asm/cacheflush.h>
+#include <asm/patch.h>
+
+/* In IA64, each function will be added below two bundles with -pg option */
+static unsigned char __attribute__((aligned(8)))
+ftrace_orig_code[MCOUNT_INSN_SIZE] = {
+	0x02, 0x40, 0x31, 0x10, 0x80, 0x05, /* alloc r40=ar.pfs,12,8,0 */
+	0xb0, 0x02, 0x00, 0x00, 0x42, 0x40, /* mov r43=r0;; */
+	0x05, 0x00, 0xc4, 0x00,             /* mov r42=b0 */
+	0x11, 0x48, 0x01, 0x02, 0x00, 0x21, /* mov r41=r1 */
+	0x00, 0x00, 0x00, 0x02, 0x00, 0x00, /* nop.i 0x0 */
+	0x08, 0x00, 0x00, 0x50              /* br.call.sptk.many b0 = _mcount;; */
+};
+
+struct ftrace_orig_insn {
+	u64 dummy1, dummy2, dummy3;
+	u64 dummy4:64-41+13;
+	u64 imm20:20;
+	u64 dummy5:3;
+	u64 sign:1;
+	u64 dummy6:4;
+};
+
+/* mcount stub will be converted below for nop */
+static unsigned char ftrace_nop_code[MCOUNT_INSN_SIZE] = {
+	0x00, 0x00, 0x00, 0x00, 0x01, 0x00, /* [MII] nop.m 0x0 */
+	0x30, 0x00, 0x00, 0x60, 0x00, 0x00, /* mov r3=ip */
+	0x00, 0x00, 0x04, 0x00,             /* nop.i 0x0 */
+	0x05, 0x00, 0x00, 0x00, 0x01, 0x00, /* [MLX] nop.m 0x0 */
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* nop.x 0x0;; */
+	0x00, 0x00, 0x04, 0x00
+};
+
+static unsigned char *ftrace_nop_replace(void)
+{
+	return ftrace_nop_code;
+}
+
+/*
+ * mcount stub will be converted below for call
+ * Note: Just the last instruction is changed against nop
+ * */
+static unsigned char __attribute__((aligned(8)))
+ftrace_call_code[MCOUNT_INSN_SIZE] = {
+	0x00, 0x00, 0x00, 0x00, 0x01, 0x00, /* [MII] nop.m 0x0 */
+	0x30, 0x00, 0x00, 0x60, 0x00, 0x00, /* mov r3=ip */
+	0x00, 0x00, 0x04, 0x00,             /* nop.i 0x0 */
+	0x05, 0x00, 0x00, 0x00, 0x01, 0x00, /* [MLX] nop.m 0x0 */
+	0xff, 0xff, 0xff, 0xff, 0x7f, 0x00, /* brl.many .;;*/
+	0xf8, 0xff, 0xff, 0xc8
+};
+
+struct ftrace_call_insn {
+	u64 dummy1, dummy2;
+	u64 dummy3:48;
+	u64 imm39_l:16;
+	u64 imm39_h:23;
+	u64 dummy4:13;
+	u64 imm20:20;
+	u64 dummy5:3;
+	u64 i:1;
+	u64 dummy6:4;
+};
+
+static unsigned char *ftrace_call_replace(unsigned long ip, unsigned long addr)
+{
+	struct ftrace_call_insn *code = (void *)ftrace_call_code;
+	unsigned long offset = addr - (ip + 0x10);
+
+	code->imm39_l = offset >> 24;
+	code->imm39_h = offset >> 40;
+	code->imm20 = offset >> 4;
+	code->i = offset >> 63;
+	return ftrace_call_code;
+}
+
+static int
+ftrace_modify_code(unsigned long ip, unsigned char *old_code,
+		   unsigned char *new_code, int do_check)
+{
+	unsigned char replaced[MCOUNT_INSN_SIZE];
+
+	/*
+	 * Note: Due to modules and __init, code can
+	 *  disappear and change, we need to protect against faulting
+	 *  as well as code changing. We do this by using the
+	 *  probe_kernel_* functions.
+	 *
+	 * No real locking needed, this code is run through
+	 * kstop_machine, or before SMP starts.
+	 */
+
+	if (!do_check)
+		goto skip_check;
+
+	/* read the text we want to modify */
+	if (probe_kernel_read(replaced, (void *)ip, MCOUNT_INSN_SIZE))
+		return -EFAULT;
+
+	/* Make sure it is what we expect it to be */
+	if (memcmp(replaced, old_code, MCOUNT_INSN_SIZE) != 0)
+		return -EINVAL;
+
+skip_check:
+	/* replace the text with the new text */
+	if (probe_kernel_write(((void *)ip), new_code, MCOUNT_INSN_SIZE))
+		return -EPERM;
+	flush_icache_range(ip, ip + MCOUNT_INSN_SIZE);
+
+	return 0;
+}
+
+static int ftrace_make_nop_check(struct dyn_ftrace *rec, unsigned long addr)
+{
+	unsigned char __attribute__((aligned(8))) replaced[MCOUNT_INSN_SIZE];
+	unsigned long ip = rec->ip;
+
+	if (probe_kernel_read(replaced, (void *)ip, MCOUNT_INSN_SIZE))
+		return -EFAULT;
+	if (rec->flags & FTRACE_FL_CONVERTED) {
+		struct ftrace_call_insn *call_insn, *tmp_call;
+
+		call_insn = (void *)ftrace_call_code;
+		tmp_call = (void *)replaced;
+		call_insn->imm39_l = tmp_call->imm39_l;
+		call_insn->imm39_h = tmp_call->imm39_h;
+		call_insn->imm20 = tmp_call->imm20;
+		call_insn->i = tmp_call->i;
+		if (memcmp(replaced, ftrace_call_code, MCOUNT_INSN_SIZE) != 0)
+			return -EINVAL;
+		return 0;
+	} else {
+		struct ftrace_orig_insn *call_insn, *tmp_call;
+
+		call_insn = (void *)ftrace_orig_code;
+		tmp_call = (void *)replaced;
+		call_insn->sign = tmp_call->sign;
+		call_insn->imm20 = tmp_call->imm20;
+		if (memcmp(replaced, ftrace_orig_code, MCOUNT_INSN_SIZE) != 0)
+			return -EINVAL;
+		return 0;
+	}
+}
+
+int ftrace_make_nop(struct module *mod,
+		    struct dyn_ftrace *rec, unsigned long addr)
+{
+	int ret;
+	char *new;
+
+	ret = ftrace_make_nop_check(rec, addr);
+	if (ret)
+		return ret;
+	new = ftrace_nop_replace();
+	return ftrace_modify_code(rec->ip, NULL, new, 0);
+}
+
+int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
+{
+	unsigned long ip = rec->ip;
+	unsigned char *old, *new;
+
+	old=  ftrace_nop_replace();
+	new = ftrace_call_replace(ip, addr);
+	return ftrace_modify_code(ip, old, new, 1);
+}
+
+/* in IA64, _mcount can't directly call ftrace_stub. Only jump is ok */
+int ftrace_update_ftrace_func(ftrace_func_t func)
+{
+	unsigned long ip;
+	unsigned long addr = ((struct fnptr *)ftrace_call)->ip;
+
+	if (func == ftrace_stub)
+		return 0;
+	ip = ((struct fnptr *)func)->ip;
+
+	ia64_patch_imm64(addr + 2, ip);
+
+	flush_icache_range(addr, addr + 16);
+	return 0;
+}
+
+/* run from kstop_machine */
+int __init ftrace_dyn_arch_init(void *data)
+{
+	*(unsigned long *)data = 0;
+
+	return 0;
+}
diff --git a/arch/ia64/kernel/ia64_ksyms.c b/arch/ia64/kernel/ia64_ksyms.c
index 6da1f20d737..2d311864e35 100644
--- a/arch/ia64/kernel/ia64_ksyms.c
+++ b/arch/ia64/kernel/ia64_ksyms.c
@@ -112,3 +112,9 @@ EXPORT_SYMBOL_GPL(esi_call_phys);
 #endif
 extern char ia64_ivt[];
 EXPORT_SYMBOL(ia64_ivt);
+
+#include <asm/ftrace.h>
+#ifdef CONFIG_FUNCTION_TRACER
+/* mcount is defined in assembly */
+EXPORT_SYMBOL(_mcount);
+#endif
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 9c39095b33f..8fc9a847cf4 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -34,6 +34,7 @@ config X86
 	select HAVE_FUNCTION_TRACER
 	select HAVE_FUNCTION_GRAPH_TRACER
 	select HAVE_FUNCTION_TRACE_MCOUNT_TEST
+	select HAVE_FTRACE_NMI_ENTER if DYNAMIC_FTRACE
 	select HAVE_KVM if ((X86_32 && !X86_VOYAGER && !X86_VISWS && !X86_NUMAQ) || X86_64)
 	select HAVE_ARCH_KGDB if !X86_VOYAGER
 	select HAVE_ARCH_TRACEHOOK
diff --git a/arch/x86/include/asm/cacheflush.h b/arch/x86/include/asm/cacheflush.h
index 2f8466540fb..6145063cfe0 100644
--- a/arch/x86/include/asm/cacheflush.h
+++ b/arch/x86/include/asm/cacheflush.h
@@ -104,6 +104,11 @@ void clflush_cache_range(void *addr, unsigned int size);
 #ifdef CONFIG_DEBUG_RODATA
 void mark_rodata_ro(void);
 extern const int rodata_test_data;
+void set_kernel_text_rw(void);
+void set_kernel_text_ro(void);
+#else
+static inline void set_kernel_text_rw(void) { }
+static inline void set_kernel_text_ro(void) { }
 #endif
 
 #ifdef CONFIG_DEBUG_RODATA_TEST
diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h
index b55b4a7fbef..db24c2278be 100644
--- a/arch/x86/include/asm/ftrace.h
+++ b/arch/x86/include/asm/ftrace.h
@@ -55,29 +55,4 @@ struct dyn_arch_ftrace {
 #endif /* __ASSEMBLY__ */
 #endif /* CONFIG_FUNCTION_TRACER */
 
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-
-#ifndef __ASSEMBLY__
-
-/*
- * Stack of return addresses for functions
- * of a thread.
- * Used in struct thread_info
- */
-struct ftrace_ret_stack {
-	unsigned long ret;
-	unsigned long func;
-	unsigned long long calltime;
-};
-
-/*
- * Primary handler of a function return.
- * It relays on ftrace_return_to_handler.
- * Defined in entry_32/64.S
- */
-extern void return_to_handler(void);
-
-#endif /* __ASSEMBLY__ */
-#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
-
 #endif /* _ASM_X86_FTRACE_H */
diff --git a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
index 4b1c319d30c..c5d737cdb36 100644
--- a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
+++ b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
@@ -33,7 +33,7 @@
 #include <linux/cpufreq.h>
 #include <linux/compiler.h>
 #include <linux/dmi.h>
-#include <linux/ftrace.h>
+#include <trace/power.h>
 
 #include <linux/acpi.h>
 #include <acpi/processor.h>
@@ -70,6 +70,8 @@ struct acpi_cpufreq_data {
 
 static DEFINE_PER_CPU(struct acpi_cpufreq_data *, drv_data);
 
+DEFINE_TRACE(power_mark);
+
 /* acpi_perf_data is a pointer to percpu data. */
 static struct acpi_processor_performance *acpi_perf_data;
 
diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c
index 6b1f6f6f866..4325165753d 100644
--- a/arch/x86/kernel/dumpstack.c
+++ b/arch/x86/kernel/dumpstack.c
@@ -10,10 +10,12 @@
 #include <linux/kdebug.h>
 #include <linux/module.h>
 #include <linux/ptrace.h>
+#include <linux/ftrace.h>
 #include <linux/kexec.h>
 #include <linux/bug.h>
 #include <linux/nmi.h>
 #include <linux/sysfs.h>
+#include <linux/ftrace.h>
 
 #include <asm/stacktrace.h>
 
@@ -195,6 +197,11 @@ unsigned __kprobes long oops_begin(void)
 	int cpu;
 	unsigned long flags;
 
+	/* notify the hw-branch tracer so it may disable tracing and
+	   add the last trace to the trace buffer -
+	   the earlier this happens, the more useful the trace. */
+	trace_hw_branch_oops();
+
 	oops_enter();
 
 	/* racy, but better than risking deadlock. */
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index 231bdd3c5b1..3925ec0184b 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -18,6 +18,7 @@
 #include <linux/init.h>
 #include <linux/list.h>
 
+#include <asm/cacheflush.h>
 #include <asm/ftrace.h>
 #include <linux/ftrace.h>
 #include <asm/nops.h>
@@ -26,6 +27,18 @@
 
 #ifdef CONFIG_DYNAMIC_FTRACE
 
+int ftrace_arch_code_modify_prepare(void)
+{
+	set_kernel_text_rw();
+	return 0;
+}
+
+int ftrace_arch_code_modify_post_process(void)
+{
+	set_kernel_text_ro();
+	return 0;
+}
+
 union ftrace_code_union {
 	char code[MCOUNT_INSN_SIZE];
 	struct {
@@ -82,7 +95,7 @@ static unsigned char *ftrace_call_replace(unsigned long ip, unsigned long addr)
  * are the same as what exists.
  */
 
-static atomic_t in_nmi = ATOMIC_INIT(0);
+static atomic_t nmi_running = ATOMIC_INIT(0);
 static int mod_code_status;		/* holds return value of text write */
 static int mod_code_write;		/* set when NMI should do the write */
 static void *mod_code_ip;		/* holds the IP to write to */
@@ -111,12 +124,16 @@ static void ftrace_mod_code(void)
 	 */
 	mod_code_status = probe_kernel_write(mod_code_ip, mod_code_newcode,
 					     MCOUNT_INSN_SIZE);
+
+	/* if we fail, then kill any new writers */
+	if (mod_code_status)
+		mod_code_write = 0;
 }
 
 void ftrace_nmi_enter(void)
 {
-	atomic_inc(&in_nmi);
-	/* Must have in_nmi seen before reading write flag */
+	atomic_inc(&nmi_running);
+	/* Must have nmi_running seen before reading write flag */
 	smp_mb();
 	if (mod_code_write) {
 		ftrace_mod_code();
@@ -126,22 +143,21 @@ void ftrace_nmi_enter(void)
 
 void ftrace_nmi_exit(void)
 {
-	/* Finish all executions before clearing in_nmi */
+	/* Finish all executions before clearing nmi_running */
 	smp_wmb();
-	atomic_dec(&in_nmi);
+	atomic_dec(&nmi_running);
 }
 
 static void wait_for_nmi(void)
 {
-	int waited = 0;
+	if (!atomic_read(&nmi_running))
+		return;
 
-	while (atomic_read(&in_nmi)) {
-		waited = 1;
+	do {
 		cpu_relax();
-	}
+	} while (atomic_read(&nmi_running));
 
-	if (waited)
-		nmi_wait_count++;
+	nmi_wait_count++;
 }
 
 static int
@@ -368,100 +384,8 @@ int ftrace_disable_ftrace_graph_caller(void)
 	return ftrace_mod_jmp(ip, old_offset, new_offset);
 }
 
-#else /* CONFIG_DYNAMIC_FTRACE */
-
-/*
- * These functions are picked from those used on
- * this page for dynamic ftrace. They have been
- * simplified to ignore all traces in NMI context.
- */
-static atomic_t in_nmi;
-
-void ftrace_nmi_enter(void)
-{
-	atomic_inc(&in_nmi);
-}
-
-void ftrace_nmi_exit(void)
-{
-	atomic_dec(&in_nmi);
-}
-
 #endif /* !CONFIG_DYNAMIC_FTRACE */
 
-/* Add a function return address to the trace stack on thread info.*/
-static int push_return_trace(unsigned long ret, unsigned long long time,
-				unsigned long func, int *depth)
-{
-	int index;
-
-	if (!current->ret_stack)
-		return -EBUSY;
-
-	/* The return trace stack is full */
-	if (current->curr_ret_stack == FTRACE_RETFUNC_DEPTH - 1) {
-		atomic_inc(&current->trace_overrun);
-		return -EBUSY;
-	}
-
-	index = ++current->curr_ret_stack;
-	barrier();
-	current->ret_stack[index].ret = ret;
-	current->ret_stack[index].func = func;
-	current->ret_stack[index].calltime = time;
-	*depth = index;
-
-	return 0;
-}
-
-/* Retrieve a function return address to the trace stack on thread info.*/
-static void pop_return_trace(struct ftrace_graph_ret *trace, unsigned long *ret)
-{
-	int index;
-
-	index = current->curr_ret_stack;
-
-	if (unlikely(index < 0)) {
-		ftrace_graph_stop();
-		WARN_ON(1);
-		/* Might as well panic, otherwise we have no where to go */
-		*ret = (unsigned long)panic;
-		return;
-	}
-
-	*ret = current->ret_stack[index].ret;
-	trace->func = current->ret_stack[index].func;
-	trace->calltime = current->ret_stack[index].calltime;
-	trace->overrun = atomic_read(&current->trace_overrun);
-	trace->depth = index;
-	barrier();
-	current->curr_ret_stack--;
-
-}
-
-/*
- * Send the trace to the ring-buffer.
- * @return the original return address.
- */
-unsigned long ftrace_return_to_handler(void)
-{
-	struct ftrace_graph_ret trace;
-	unsigned long ret;
-
-	pop_return_trace(&trace, &ret);
-	trace.rettime = cpu_clock(raw_smp_processor_id());
-	ftrace_graph_return(&trace);
-
-	if (unlikely(!ret)) {
-		ftrace_graph_stop();
-		WARN_ON(1);
-		/* Might as well panic. What else to do? */
-		ret = (unsigned long)panic;
-	}
-
-	return ret;
-}
-
 /*
  * Hook the return address and push it in the stack of return addrs
  * in current thread info.
@@ -476,7 +400,7 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr)
 				&return_to_handler;
 
 	/* Nmi's are currently unsupported */
-	if (unlikely(atomic_read(&in_nmi)))
+	if (unlikely(in_nmi()))
 		return;
 
 	if (unlikely(atomic_read(&current->tracing_graph_pause)))
@@ -512,16 +436,9 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr)
 		return;
 	}
 
-	if (unlikely(!__kernel_text_address(old))) {
-		ftrace_graph_stop();
-		*parent = old;
-		WARN_ON(1);
-		return;
-	}
-
 	calltime = cpu_clock(raw_smp_processor_id());
 
-	if (push_return_trace(old, calltime,
+	if (ftrace_push_return_trace(old, calltime,
 				self_addr, &trace.depth) == -EBUSY) {
 		*parent = old;
 		return;
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 6d12f7e37f8..23b328edc2b 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -8,7 +8,7 @@
 #include <linux/module.h>
 #include <linux/pm.h>
 #include <linux/clockchips.h>
-#include <linux/ftrace.h>
+#include <trace/power.h>
 #include <asm/system.h>
 #include <asm/apic.h>
 
@@ -19,6 +19,9 @@ EXPORT_SYMBOL(idle_nomwait);
 
 struct kmem_cache *task_xstate_cachep;
 
+DEFINE_TRACE(power_start);
+DEFINE_TRACE(power_end);
+
 int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
 {
 	*dst = *src;
diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig
index b81125f0bde..c7da3683f4c 100644
--- a/arch/x86/kvm/Kconfig
+++ b/arch/x86/kvm/Kconfig
@@ -55,7 +55,8 @@ config KVM_AMD
 
 config KVM_TRACE
 	bool "KVM trace support"
-	depends on KVM && MARKERS && SYSFS
+	depends on KVM && SYSFS
+	select MARKERS
 	select RELAY
 	select DEBUG_FS
 	default n
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index 2cef0507441..3eb2ed188a4 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -1155,17 +1155,47 @@ static noinline int do_test_wp_bit(void)
 const int rodata_test_data = 0xC3;
 EXPORT_SYMBOL_GPL(rodata_test_data);
 
+static int kernel_set_to_readonly;
+
+void set_kernel_text_rw(void)
+{
+	unsigned long start = PFN_ALIGN(_text);
+	unsigned long size = PFN_ALIGN(_etext) - start;
+
+	if (!kernel_set_to_readonly)
+		return;
+
+	pr_debug("Set kernel text: %lx - %lx for read write\n",
+		 start, start+size);
+
+	set_pages_rw(virt_to_page(start), size >> PAGE_SHIFT);
+}
+
+void set_kernel_text_ro(void)
+{
+	unsigned long start = PFN_ALIGN(_text);
+	unsigned long size = PFN_ALIGN(_etext) - start;
+
+	if (!kernel_set_to_readonly)
+		return;
+
+	pr_debug("Set kernel text: %lx - %lx for read only\n",
+		 start, start+size);
+
+	set_pages_ro(virt_to_page(start), size >> PAGE_SHIFT);
+}
+
 void mark_rodata_ro(void)
 {
 	unsigned long start = PFN_ALIGN(_text);
 	unsigned long size = PFN_ALIGN(_etext) - start;
 
-#ifndef CONFIG_DYNAMIC_FTRACE
-	/* Dynamic tracing modifies the kernel text section */
 	set_pages_ro(virt_to_page(start), size >> PAGE_SHIFT);
 	printk(KERN_INFO "Write protecting the kernel text: %luk\n",
 		size >> 10);
 
+	kernel_set_to_readonly = 1;
+
 #ifdef CONFIG_CPA_DEBUG
 	printk(KERN_INFO "Testing CPA: Reverting %lx-%lx\n",
 		start, start+size);
@@ -1174,7 +1204,6 @@ void mark_rodata_ro(void)
 	printk(KERN_INFO "Testing CPA: write protecting again\n");
 	set_pages_ro(virt_to_page(start), size>>PAGE_SHIFT);
 #endif
-#endif /* CONFIG_DYNAMIC_FTRACE */
 
 	start += size;
 	size = (unsigned long)__end_rodata - start;
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index e6d36b49025..63fdc531601 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -986,21 +986,48 @@ void free_initmem(void)
 const int rodata_test_data = 0xC3;
 EXPORT_SYMBOL_GPL(rodata_test_data);
 
+static int kernel_set_to_readonly;
+
+void set_kernel_text_rw(void)
+{
+	unsigned long start = PFN_ALIGN(_stext);
+	unsigned long end = PFN_ALIGN(__start_rodata);
+
+	if (!kernel_set_to_readonly)
+		return;
+
+	pr_debug("Set kernel text: %lx - %lx for read write\n",
+		 start, end);
+
+	set_memory_rw(start, (end - start) >> PAGE_SHIFT);
+}
+
+void set_kernel_text_ro(void)
+{
+	unsigned long start = PFN_ALIGN(_stext);
+	unsigned long end = PFN_ALIGN(__start_rodata);
+
+	if (!kernel_set_to_readonly)
+		return;
+
+	pr_debug("Set kernel text: %lx - %lx for read only\n",
+		 start, end);
+
+	set_memory_ro(start, (end - start) >> PAGE_SHIFT);
+}
+
 void mark_rodata_ro(void)
 {
 	unsigned long start = PFN_ALIGN(_stext), end = PFN_ALIGN(__end_rodata);
 	unsigned long rodata_start =
 		((unsigned long)__start_rodata + PAGE_SIZE - 1) & PAGE_MASK;
 
-#ifdef CONFIG_DYNAMIC_FTRACE
-	/* Dynamic tracing modifies the kernel text section */
-	start = rodata_start;
-#endif
-
 	printk(KERN_INFO "Write protecting the kernel read-only data: %luk\n",
 	       (end - start) >> 10);
 	set_memory_ro(start, (end - start) >> PAGE_SHIFT);
 
+	kernel_set_to_readonly = 1;
+
 	/*
 	 * The rodata section (but not the kernel text!) should also be
 	 * not-executable.