Merge branch 'tracing/core-v2' into tracing-for-linus

Conflicts:
	include/linux/slub_def.h
	lib/Kconfig.debug
	mm/slob.c
	mm/slub.c

37 files changed, 627 insertions, 132 deletions

diff --git a/arch/Kconfig b/arch/Kconfig
index 830c16a..dc81b34 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -6,6 +6,7 @@ config OPROFILE
 	tristate "OProfile system profiling (EXPERIMENTAL)"
 	depends on PROFILING
 	depends on HAVE_OPROFILE
+	depends on TRACING_SUPPORT
 	select TRACING
 	select RING_BUFFER
 	help
diff --git a/arch/alpha/include/asm/ftrace.h b/arch/alpha/include/asm/ftrace.h
new file mode 100644
index 0000000..40a8c17
--- /dev/null
+++ b/arch/alpha/include/asm/ftrace.h
@@ -0,0 +1 @@
+/* empty */
diff --git a/arch/alpha/include/asm/hardirq.h b/arch/alpha/include/asm/hardirq.h
index d953e23..8897146 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/ftrace.h b/arch/avr32/include/asm/ftrace.h
new file mode 100644
index 0000000..40a8c17
--- /dev/null
+++ b/arch/avr32/include/asm/ftrace.h
@@ -0,0 +1 @@
+/* empty */
diff --git a/arch/avr32/include/asm/hardirq.h b/arch/avr32/include/asm/hardirq.h
index 2673543..015bc75 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/blackfin/include/asm/ftrace.h b/arch/blackfin/include/asm/ftrace.h
new file mode 100644
index 0000000..40a8c17
--- /dev/null
+++ b/arch/blackfin/include/asm/ftrace.h
@@ -0,0 +1 @@
+/* empty */
diff --git a/arch/cris/include/asm/ftrace.h b/arch/cris/include/asm/ftrace.h
new file mode 100644
index 0000000..40a8c17
--- /dev/null
+++ b/arch/cris/include/asm/ftrace.h
@@ -0,0 +1 @@
+/* empty */
diff --git a/arch/h8300/include/asm/ftrace.h b/arch/h8300/include/asm/ftrace.h
new file mode 100644
index 0000000..40a8c17
--- /dev/null
+++ b/arch/h8300/include/asm/ftrace.h
@@ -0,0 +1 @@
+/* empty */
diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig
index 153e727..294a3b1 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 0000000..d20db3c
--- /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 140e495..d514cd9 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 f2778f2..dc62df0 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 e5341e2..7e3382b 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 0000000..7fc8c96
--- /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 6da1f20..2d31186 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/m68k/include/asm/ftrace.h b/arch/m68k/include/asm/ftrace.h
new file mode 100644
index 0000000..40a8c17
--- /dev/null
+++ b/arch/m68k/include/asm/ftrace.h
@@ -0,0 +1 @@
+/* empty */
diff --git a/arch/mips/include/asm/ftrace.h b/arch/mips/include/asm/ftrace.h
new file mode 100644
index 0000000..40a8c17
--- /dev/null
+++ b/arch/mips/include/asm/ftrace.h
@@ -0,0 +1 @@
+/* empty */
diff --git a/arch/parisc/include/asm/ftrace.h b/arch/parisc/include/asm/ftrace.h
new file mode 100644
index 0000000..40a8c17
--- /dev/null
+++ b/arch/parisc/include/asm/ftrace.h
@@ -0,0 +1 @@
+/* empty */
diff --git a/arch/um/include/asm/ftrace.h b/arch/um/include/asm/ftrace.h
new file mode 100644
index 0000000..40a8c17
--- /dev/null
+++ b/arch/um/include/asm/ftrace.h
@@ -0,0 +1 @@
+/* empty */
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 748e50a..0885245 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -34,6 +34,8 @@ 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_FTRACE_SYSCALLS
 	select HAVE_KVM
 	select HAVE_ARCH_KGDB
 	select HAVE_ARCH_TRACEHOOK
diff --git a/arch/x86/include/asm/cacheflush.h b/arch/x86/include/asm/cacheflush.h
index b3894bf..e55dfc1 100644
--- a/arch/x86/include/asm/cacheflush.h
+++ b/arch/x86/include/asm/cacheflush.h
@@ -126,6 +126,11 @@ 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/fixmap.h b/arch/x86/include/asm/fixmap.h
index 63a79c7..81937a5 100644
--- a/arch/x86/include/asm/fixmap.h
+++ b/arch/x86/include/asm/fixmap.h
@@ -111,6 +111,8 @@ enum fixed_addresses {
 #ifdef CONFIG_PARAVIRT
 	FIX_PARAVIRT_BOOTMAP,
 #endif
+	FIX_TEXT_POKE0,	/* reserve 2 pages for text_poke() */
+	FIX_TEXT_POKE1,
 	__end_of_permanent_fixed_addresses,
 #ifdef CONFIG_PROVIDE_OHCI1394_DMA_INIT
 	FIX_OHCI1394_BASE,
diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h
index db24c22..bd2c651 100644
--- a/arch/x86/include/asm/ftrace.h
+++ b/arch/x86/include/asm/ftrace.h
@@ -28,6 +28,13 @@
 
 #endif
 
+/* FIXME: I don't want to stay hardcoded */
+#ifdef CONFIG_X86_64
+# define FTRACE_SYSCALL_MAX     296
+#else
+# define FTRACE_SYSCALL_MAX     333
+#endif
+
 #ifdef CONFIG_FUNCTION_TRACER
 #define MCOUNT_ADDR		((long)(mcount))
 #define MCOUNT_INSN_SIZE	5 /* sizeof mcount call */
diff --git a/arch/x86/include/asm/ptrace-abi.h b/arch/x86/include/asm/ptrace-abi.h
index 8e0f8d1..8672303 100644
--- a/arch/x86/include/asm/ptrace-abi.h
+++ b/arch/x86/include/asm/ptrace-abi.h
@@ -80,8 +80,6 @@
 
 #define PTRACE_SINGLEBLOCK	33	/* resume execution until next branch */
 
-#ifdef CONFIG_X86_PTRACE_BTS
-
 #ifndef __ASSEMBLY__
 #include <linux/types.h>
 
@@ -140,6 +138,5 @@ struct ptrace_bts_config {
    BTS records are read from oldest to newest.
    Returns number of BTS records drained.
 */
-#endif /* CONFIG_X86_PTRACE_BTS */
 
 #endif /* _ASM_X86_PTRACE_ABI_H */
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index df9d5f7..8820a73 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -94,6 +94,7 @@ struct thread_info {
 #define TIF_FORCED_TF		24	/* true if TF in eflags artificially */
 #define TIF_DEBUGCTLMSR		25	/* uses thread_struct.debugctlmsr */
 #define TIF_DS_AREA_MSR		26      /* uses thread_struct.ds_area_msr */
+#define TIF_SYSCALL_FTRACE	27	/* for ftrace syscall instrumentation */
 
 #define _TIF_SYSCALL_TRACE	(1 << TIF_SYSCALL_TRACE)
 #define _TIF_NOTIFY_RESUME	(1 << TIF_NOTIFY_RESUME)
@@ -115,15 +116,17 @@ struct thread_info {
 #define _TIF_FORCED_TF		(1 << TIF_FORCED_TF)
 #define _TIF_DEBUGCTLMSR	(1 << TIF_DEBUGCTLMSR)
 #define _TIF_DS_AREA_MSR	(1 << TIF_DS_AREA_MSR)
+#define _TIF_SYSCALL_FTRACE	(1 << TIF_SYSCALL_FTRACE)
 
 /* work to do in syscall_trace_enter() */
 #define _TIF_WORK_SYSCALL_ENTRY	\
-	(_TIF_SYSCALL_TRACE | _TIF_SYSCALL_EMU | \
+	(_TIF_SYSCALL_TRACE | _TIF_SYSCALL_EMU | _TIF_SYSCALL_FTRACE |	\
 	 _TIF_SYSCALL_AUDIT | _TIF_SECCOMP | _TIF_SINGLESTEP)
 
 /* work to do in syscall_trace_leave() */
 #define _TIF_WORK_SYSCALL_EXIT	\
-	(_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | _TIF_SINGLESTEP)
+	(_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | _TIF_SINGLESTEP |	\
+	 _TIF_SYSCALL_FTRACE)
 
 /* work to do on interrupt/exception return */
 #define _TIF_WORK_MASK							\
@@ -132,7 +135,7 @@ struct thread_info {
 	   _TIF_SINGLESTEP|_TIF_SECCOMP|_TIF_SYSCALL_EMU))
 
 /* work to do on any return to user space */
-#define _TIF_ALLWORK_MASK (0x0000FFFF & ~_TIF_SECCOMP)
+#define _TIF_ALLWORK_MASK ((0x0000FFFF & ~_TIF_SECCOMP) | _TIF_SYSCALL_FTRACE)
 
 /* Only used for 64 bit */
 #define _TIF_DO_NOTIFY_MASK						\
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index c611ad6..145cce7 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -66,7 +66,8 @@ obj-$(CONFIG_X86_MPPARSE)	+= mpparse.o
 obj-y				+= apic/
 obj-$(CONFIG_X86_REBOOTFIXUPS)	+= reboot_fixups_32.o
 obj-$(CONFIG_DYNAMIC_FTRACE)	+= ftrace.o
-obj-$(CONFIG_FUNCTION_GRAPH_TRACER)	+= ftrace.o
+obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += ftrace.o
+obj-$(CONFIG_FTRACE_SYSCALLS)	+= ftrace.o
 obj-$(CONFIG_KEXEC)		+= machine_kexec_$(BITS).o
 obj-$(CONFIG_KEXEC)		+= relocate_kernel_$(BITS).o crash.o
 obj-$(CONFIG_CRASH_DUMP)	+= crash_dump_$(BITS).o
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index 4c80f15..f576587 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -5,6 +5,7 @@
 #include <linux/kprobes.h>
 #include <linux/mm.h>
 #include <linux/vmalloc.h>
+#include <linux/memory.h>
 #include <asm/alternative.h>
 #include <asm/sections.h>
 #include <asm/pgtable.h>
@@ -12,7 +13,9 @@
 #include <asm/nmi.h>
 #include <asm/vsyscall.h>
 #include <asm/cacheflush.h>
+#include <asm/tlbflush.h>
 #include <asm/io.h>
+#include <asm/fixmap.h>
 
 #define MAX_PATCH_LEN (255-1)
 
@@ -226,6 +229,7 @@ static void alternatives_smp_lock(u8 **start, u8 **end, u8 *text, u8 *text_end)
 {
 	u8 **ptr;
 
+	mutex_lock(&text_mutex);
 	for (ptr = start; ptr < end; ptr++) {
 		if (*ptr < text)
 			continue;
@@ -234,6 +238,7 @@ static void alternatives_smp_lock(u8 **start, u8 **end, u8 *text, u8 *text_end)
 		/* turn DS segment override prefix into lock prefix */
 		text_poke(*ptr, ((unsigned char []){0xf0}), 1);
 	};
+	mutex_unlock(&text_mutex);
 }
 
 static void alternatives_smp_unlock(u8 **start, u8 **end, u8 *text, u8 *text_end)
@@ -243,6 +248,7 @@ static void alternatives_smp_unlock(u8 **start, u8 **end, u8 *text, u8 *text_end
 	if (noreplace_smp)
 		return;
 
+	mutex_lock(&text_mutex);
 	for (ptr = start; ptr < end; ptr++) {
 		if (*ptr < text)
 			continue;
@@ -251,6 +257,7 @@ static void alternatives_smp_unlock(u8 **start, u8 **end, u8 *text, u8 *text_end
 		/* turn lock prefix into DS segment override prefix */
 		text_poke(*ptr, ((unsigned char []){0x3E}), 1);
 	};
+	mutex_unlock(&text_mutex);
 }
 
 struct smp_alt_module {
@@ -500,15 +507,16 @@ void *text_poke_early(void *addr, const void *opcode, size_t len)
  * It means the size must be writable atomically and the address must be aligned
  * in a way that permits an atomic write. It also makes sure we fit on a single
  * page.
+ *
+ * Note: Must be called under text_mutex.
  */
 void *__kprobes text_poke(void *addr, const void *opcode, size_t len)
 {
+	unsigned long flags;
 	char *vaddr;
-	int nr_pages = 2;
 	struct page *pages[2];
 	int i;
 
-	might_sleep();
 	if (!core_kernel_text((unsigned long)addr)) {
 		pages[0] = vmalloc_to_page(addr);
 		pages[1] = vmalloc_to_page(addr + PAGE_SIZE);
@@ -518,18 +526,21 @@ void *__kprobes text_poke(void *addr, const void *opcode, size_t len)
 		pages[1] = virt_to_page(addr + PAGE_SIZE);
 	}
 	BUG_ON(!pages[0]);
-	if (!pages[1])
-		nr_pages = 1;
-	vaddr = vmap(pages, nr_pages, VM_MAP, PAGE_KERNEL);
-	BUG_ON(!vaddr);
-	local_irq_disable();
+	local_irq_save(flags);
+	set_fixmap(FIX_TEXT_POKE0, page_to_phys(pages[0]));
+	if (pages[1])
+		set_fixmap(FIX_TEXT_POKE1, page_to_phys(pages[1]));
+	vaddr = (char *)fix_to_virt(FIX_TEXT_POKE0);
 	memcpy(&vaddr[(unsigned long)addr & ~PAGE_MASK], opcode, len);
-	local_irq_enable();
-	vunmap(vaddr);
+	clear_fixmap(FIX_TEXT_POKE0);
+	if (pages[1])
+		clear_fixmap(FIX_TEXT_POKE1);
+	local_flush_tlb();
 	sync_core();
 	/* Could also do a CLFLUSH here to speed up CPU recovery; but
 	   that causes hangs on some VIA CPUs. */
 	for (i = 0; i < len; i++)
 		BUG_ON(((char *)addr)[i] != ((char *)opcode)[i]);
+	local_irq_restore(flags);
 	return addr;
 }
diff --git a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
index 23da96e..05209b5 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 <linux/io.h>
@@ -72,6 +72,8 @@ 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 dd2130b..95ea5fa 100644
--- a/arch/x86/kernel/dumpstack.c
+++ b/arch/x86/kernel/dumpstack.c
@@ -15,6 +15,7 @@
 #include <linux/bug.h>
 #include <linux/nmi.h>
 #include <linux/sysfs.h>
+#include <linux/ftrace.h>
 
 #include <asm/stacktrace.h>
 
@@ -196,6 +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 76f7141..61df775 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 {
@@ -66,11 +79,11 @@ static unsigned char *ftrace_call_replace(unsigned long ip, unsigned long addr)
  *
  * 1) Put the instruction pointer into the IP buffer
  *    and the new code into the "code" buffer.
- * 2) Set a flag that says we are modifying code
- * 3) Wait for any running NMIs to finish.
- * 4) Write the code
- * 5) clear the flag.
- * 6) Wait for any running NMIs to finish.
+ * 2) Wait for any running NMIs to finish and set a flag that says
+ *    we are modifying code, it is done in an atomic operation.
+ * 3) Write the code
+ * 4) clear the flag.
+ * 5) Wait for any running NMIs to finish.
  *
  * If an NMI is executed, the first thing it does is to call
  * "ftrace_nmi_enter". This will check if the flag is set to write
@@ -82,9 +95,9 @@ 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);
+#define MOD_CODE_WRITE_FLAG (1 << 31)	/* set when NMI should do the write */
+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 */
 static void *mod_code_newcode;		/* holds the text to write to the IP */
 
@@ -101,6 +114,20 @@ int ftrace_arch_read_dyn_info(char *buf, int size)
 	return r;
 }
 
+static void clear_mod_flag(void)
+{
+	int old = atomic_read(&nmi_running);
+
+	for (;;) {
+		int new = old & ~MOD_CODE_WRITE_FLAG;
+
+		if (old == new)
+			break;
+
+		old = atomic_cmpxchg(&nmi_running, old, new);
+	}
+}
+
 static void ftrace_mod_code(void)
 {
 	/*
@@ -111,37 +138,52 @@ 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)
+		clear_mod_flag();
 }
 
 void ftrace_nmi_enter(void)
 {
-	atomic_inc(&in_nmi);
-	/* Must have in_nmi seen before reading write flag */
-	smp_mb();
-	if (mod_code_write) {
+	if (atomic_inc_return(&nmi_running) & MOD_CODE_WRITE_FLAG) {
+		smp_rmb();
 		ftrace_mod_code();
 		atomic_inc(&nmi_update_count);
 	}
+	/* Must have previous changes seen before executions */
+	smp_mb();
 }
 
 void ftrace_nmi_exit(void)
 {
-	/* Finish all executions before clearing in_nmi */
-	smp_wmb();
-	atomic_dec(&in_nmi);
+	/* Finish all executions before clearing nmi_running */
+	smp_mb();
+	atomic_dec(&nmi_running);
+}
+
+static void wait_for_nmi_and_set_mod_flag(void)
+{
+	if (!atomic_cmpxchg(&nmi_running, 0, MOD_CODE_WRITE_FLAG))
+		return;
+
+	do {
+		cpu_relax();
+	} while (atomic_cmpxchg(&nmi_running, 0, MOD_CODE_WRITE_FLAG));
+
+	nmi_wait_count++;
 }
 
 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
@@ -151,14 +193,9 @@ do_ftrace_mod_code(unsigned long ip, void *new_code)
 	mod_code_newcode = new_code;
 
 	/* The buffers need to be visible before we let NMIs write them */
-	smp_wmb();
-
-	mod_code_write = 1;
-
-	/* Make sure write bit is visible before we wait on NMIs */
 	smp_mb();
 
-	wait_for_nmi();
+	wait_for_nmi_and_set_mod_flag();
 
 	/* Make sure all running NMIs have finished before we write the code */
 	smp_mb();
@@ -166,13 +203,9 @@ do_ftrace_mod_code(unsigned long ip, void *new_code)
 	ftrace_mod_code();
 
 	/* Make sure the write happens before clearing the bit */
-	smp_wmb();
-
-	mod_code_write = 0;
-
-	/* make sure NMIs see the cleared bit */
 	smp_mb();
 
+	clear_mod_flag();
 	wait_for_nmi();
 
 	return mod_code_status;
@@ -368,25 +401,6 @@ 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 */
 
 /*
@@ -396,14 +410,13 @@ void ftrace_nmi_exit(void)
 void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr)
 {
 	unsigned long old;
-	unsigned long long calltime;
 	int faulted;
 	struct ftrace_graph_ent trace;
 	unsigned long return_hooker = (unsigned long)
 				&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)))
@@ -439,17 +452,7 @@ 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 (ftrace_push_return_trace(old, calltime,
-				self_addr, &trace.depth) == -EBUSY) {
+	if (ftrace_push_return_trace(old, self_addr, &trace.depth) == -EBUSY) {
 		*parent = old;
 		return;
 	}
@@ -463,3 +466,66 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr)
 	}
 }
 #endif /* CONFIG_FUNCTION_GRAPH_TRACER */
+
+#ifdef CONFIG_FTRACE_SYSCALLS
+
+extern unsigned long __start_syscalls_metadata[];
+extern unsigned long __stop_syscalls_metadata[];
+extern unsigned long *sys_call_table;
+
+static struct syscall_metadata **syscalls_metadata;
+
+static struct syscall_metadata *find_syscall_meta(unsigned long *syscall)
+{
+	struct syscall_metadata *start;
+	struct syscall_metadata *stop;
+	char str[KSYM_SYMBOL_LEN];
+
+
+	start = (struct syscall_metadata *)__start_syscalls_metadata;
+	stop = (struct syscall_metadata *)__stop_syscalls_metadata;
+	kallsyms_lookup((unsigned long) syscall, NULL, NULL, NULL, str);
+
+	for ( ; start < stop; start++) {
+		if (start->name && !strcmp(start->name, str))
+			return start;
+	}
+	return NULL;
+}
+
+struct syscall_metadata *syscall_nr_to_meta(int nr)
+{
+	if (!syscalls_metadata || nr >= FTRACE_SYSCALL_MAX || nr < 0)
+		return NULL;
+
+	return syscalls_metadata[nr];
+}
+
+void arch_init_ftrace_syscalls(void)
+{
+	int i;
+	struct syscall_metadata *meta;
+	unsigned long **psys_syscall_table = &sys_call_table;
+	static atomic_t refs;
+
+	if (atomic_inc_return(&refs) != 1)
+		goto end;
+
+	syscalls_metadata = kzalloc(sizeof(*syscalls_metadata) *
+					FTRACE_SYSCALL_MAX, GFP_KERNEL);
+	if (!syscalls_metadata) {
+		WARN_ON(1);
+		return;
+	}
+
+	for (i = 0; i < FTRACE_SYSCALL_MAX; i++) {
+		meta = find_syscall_meta(psys_syscall_table[i]);
+		syscalls_metadata[i] = meta;
+	}
+	return;
+
+	/* Paranoid: avoid overflow */
+end:
+	atomic_dec(&refs);
+}
+#endif
diff --git a/arch/x86/kernel/kprobes.c b/arch/x86/kernel/kprobes.c
index 55b9461..7b5169d 100644
--- a/arch/x86/kernel/kprobes.c
+++ b/arch/x86/kernel/kprobes.c
@@ -638,13 +638,13 @@ static void __used __kprobes kretprobe_trampoline_holder(void)
 #else
 			"	pushf\n"
 			/*
-			 * Skip cs, ip, orig_ax.
+			 * Skip cs, ip, orig_ax and gs.
 			 * trampoline_handler() will plug in these values
 			 */
-			"	subl $12, %esp\n"
+			"	subl $16, %esp\n"
 			"	pushl %fs\n"
-			"	pushl %ds\n"
 			"	pushl %es\n"
+			"	pushl %ds\n"
 			"	pushl %eax\n"
 			"	pushl %ebp\n"
 			"	pushl %edi\n"
@@ -655,10 +655,10 @@ static void __used __kprobes kretprobe_trampoline_holder(void)
 			"	movl %esp, %eax\n"
 			"	call trampoline_handler\n"
 			/* Move flags to cs */
-			"	movl 52(%esp), %edx\n"
-			"	movl %edx, 48(%esp)\n"
+			"	movl 56(%esp), %edx\n"
+			"	movl %edx, 52(%esp)\n"
 			/* Replace saved flags with true return address. */
-			"	movl %eax, 52(%esp)\n"
+			"	movl %eax, 56(%esp)\n"
 			"	popl %ebx\n"
 			"	popl %ecx\n"
 			"	popl %edx\n"
@@ -666,8 +666,8 @@ static void __used __kprobes kretprobe_trampoline_holder(void)
 			"	popl %edi\n"
 			"	popl %ebp\n"
 			"	popl %eax\n"
-			/* Skip ip, orig_ax, es, ds, fs */
-			"	addl $20, %esp\n"
+			/* Skip ds, es, fs, gs, orig_ax and ip */
+			"	addl $24, %esp\n"
 			"	popf\n"
 #endif
 			"	ret\n");
@@ -691,6 +691,7 @@ static __used __kprobes void *trampoline_handler(struct pt_regs *regs)
 	regs->cs = __KERNEL_CS;
 #else
 	regs->cs = __KERNEL_CS | get_kernel_rpl();
+	regs->gs = 0;
 #endif
 	regs->ip = trampoline_address;
 	regs->orig_ax = ~0UL;
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 156f875..62fc75b 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>
 #include <asm/idle.h>
@@ -22,6 +22,9 @@ 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/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index 1937871..5c6e463 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -21,6 +21,7 @@
 #include <linux/audit.h>
 #include <linux/seccomp.h>
 #include <linux/signal.h>
+#include <linux/ftrace.h>
 
 #include <asm/uaccess.h>
 #include <asm/pgtable.h>
@@ -1415,6 +1416,9 @@ asmregparm long syscall_trace_enter(struct pt_regs *regs)
 	    tracehook_report_syscall_entry(regs))
 		ret = -1L;
 
+	if (unlikely(test_thread_flag(TIF_SYSCALL_FTRACE)))
+		ftrace_syscall_enter(regs);
+
 	if (unlikely(current->audit_context)) {
 		if (IS_IA32)
 			audit_syscall_entry(AUDIT_ARCH_I386,
@@ -1438,6 +1442,9 @@ asmregparm void syscall_trace_leave(struct pt_regs *regs)
 	if (unlikely(current->audit_context))
 		audit_syscall_exit(AUDITSC_RESULT(regs->ax), regs->ax);
 
+	if (unlikely(test_thread_flag(TIF_SYSCALL_FTRACE)))
+		ftrace_syscall_exit(regs);
+
 	if (test_thread_flag(TIF_SYSCALL_TRACE))
 		tracehook_report_syscall_exit(regs, 0);
 
diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig
index 0a303c3..a58504e 100644
--- a/arch/x86/kvm/Kconfig
+++ b/arch/x86/kvm/Kconfig
@@ -59,7 +59,8 @@ 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 db81e9a..749559e 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -1054,17 +1054,47 @@ 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);
@@ -1073,7 +1103,6 @@ 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 54efa57d..1753e80 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -734,21 +734,48 @@ void __init mem_init(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.
diff --git a/arch/xtensa/include/asm/ftrace.h b/arch/xtensa/include/asm/ftrace.h
new file mode 100644
index 0000000..40a8c17
--- /dev/null
+++ b/arch/xtensa/include/asm/ftrace.h
@@ -0,0 +1 @@
+/* empty */