Merge branch 'tracing-v28-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'tracing-v28-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (131 commits)
  tracing/fastboot: improve help text
  tracing/stacktrace: improve help text
  tracing/fastboot: fix initcalls disposition in bootgraph.pl
  tracing/fastboot: fix bootgraph.pl initcall name regexp
  tracing/fastboot: fix issues and improve output of bootgraph.pl
  tracepoints: synchronize unregister static inline
  tracepoints: tracepoint_synchronize_unregister()
  ftrace: make ftrace_test_p6nop disassembler-friendly
  markers: fix synchronize marker unregister static inline
  tracing/fastboot: add better resolution to initcall debug/tracing
  trace: add build-time check to avoid overrunning hex buffer
  ftrace: fix hex output mode of ftrace
  tracing/fastboot: fix initcalls disposition in bootgraph.pl
  tracing/fastboot: fix printk format typo in boot tracer
  ftrace: return an error when setting a nonexistent tracer
  ftrace: make some tracers reentrant
  ring-buffer: make reentrant
  ring-buffer: move page indexes into page headers
  tracing/fastboot: only trace non-module initcalls
  ftrace: move pc counter in irqtrace
  ...

Manually fix conflicts:
 - init/main.c: initcall tracing
 - kernel/module.c: verbose level vs tracepoints
 - scripts/bootgraph.pl: fallout from cherry-picking commits.

8 files changed, 196 insertions, 192 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 7396689..5b9b123 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -26,6 +26,7 @@ config X86
 	select HAVE_KPROBES
 	select ARCH_WANT_OPTIONAL_GPIOLIB
 	select HAVE_KRETPROBES
+	select HAVE_FTRACE_MCOUNT_RECORD
 	select HAVE_DYNAMIC_FTRACE
 	select HAVE_FTRACE
 	select HAVE_KVM if ((X86_32 && !X86_VOYAGER && !X86_VISWS && !X86_NUMAQ) || X86_64)
diff --git a/arch/x86/kernel/cpu/perfctr-watchdog.c b/arch/x86/kernel/cpu/perfctr-watchdog.c
index 6bff382..9abd48b 100644
--- a/arch/x86/kernel/cpu/perfctr-watchdog.c
+++ b/arch/x86/kernel/cpu/perfctr-watchdog.c
@@ -17,6 +17,8 @@
 #include <linux/bitops.h>
 #include <linux/smp.h>
 #include <linux/nmi.h>
+#include <linux/kprobes.h>
+
 #include <asm/apic.h>
 #include <asm/intel_arch_perfmon.h>
 
@@ -336,7 +338,8 @@ static void single_msr_unreserve(void)
 	release_perfctr_nmi(wd_ops->perfctr);
 }
 
-static void single_msr_rearm(struct nmi_watchdog_ctlblk *wd, unsigned nmi_hz)
+static void __kprobes
+single_msr_rearm(struct nmi_watchdog_ctlblk *wd, unsigned nmi_hz)
 {
 	/* start the cycle over again */
 	write_watchdog_counter(wd->perfctr_msr, NULL, nmi_hz);
@@ -401,7 +404,7 @@ static int setup_p6_watchdog(unsigned nmi_hz)
 	return 1;
 }
 
-static void p6_rearm(struct nmi_watchdog_ctlblk *wd, unsigned nmi_hz)
+static void __kprobes p6_rearm(struct nmi_watchdog_ctlblk *wd, unsigned nmi_hz)
 {
 	/*
 	 * P6 based Pentium M need to re-unmask
@@ -605,7 +608,7 @@ static void p4_unreserve(void)
 	release_perfctr_nmi(MSR_P4_IQ_PERFCTR0);
 }
 
-static void p4_rearm(struct nmi_watchdog_ctlblk *wd, unsigned nmi_hz)
+static void __kprobes p4_rearm(struct nmi_watchdog_ctlblk *wd, unsigned nmi_hz)
 {
 	unsigned dummy;
 	/*
@@ -784,7 +787,7 @@ unsigned lapic_adjust_nmi_hz(unsigned hz)
 	return hz;
 }
 
-int lapic_wd_event(unsigned nmi_hz)
+int __kprobes lapic_wd_event(unsigned nmi_hz)
 {
 	struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk);
 	u64 ctr;
diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S
index 4d82171..c356423 100644
--- a/arch/x86/kernel/entry_32.S
+++ b/arch/x86/kernel/entry_32.S
@@ -1153,20 +1153,6 @@ ENDPROC(xen_failsafe_callback)
 #ifdef CONFIG_DYNAMIC_FTRACE
 
 ENTRY(mcount)
-	pushl %eax
-	pushl %ecx
-	pushl %edx
-	movl 0xc(%esp), %eax
-	subl $MCOUNT_INSN_SIZE, %eax
-
-.globl mcount_call
-mcount_call:
-	call ftrace_stub
-
-	popl %edx
-	popl %ecx
-	popl %eax
-
 	ret
 END(mcount)
 
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index 1db6ce4..09e7145 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -64,32 +64,6 @@
 #ifdef CONFIG_FTRACE
 #ifdef CONFIG_DYNAMIC_FTRACE
 ENTRY(mcount)
-
-	subq $0x38, %rsp
-	movq %rax, (%rsp)
-	movq %rcx, 8(%rsp)
-	movq %rdx, 16(%rsp)
-	movq %rsi, 24(%rsp)
-	movq %rdi, 32(%rsp)
-	movq %r8, 40(%rsp)
-	movq %r9, 48(%rsp)
-
-	movq 0x38(%rsp), %rdi
-	subq $MCOUNT_INSN_SIZE, %rdi
-
-.globl mcount_call
-mcount_call:
-	call ftrace_stub
-
-	movq 48(%rsp), %r9
-	movq 40(%rsp), %r8
-	movq 32(%rsp), %rdi
-	movq 24(%rsp), %rsi
-	movq 16(%rsp), %rdx
-	movq 8(%rsp), %rcx
-	movq (%rsp), %rax
-	addq $0x38, %rsp
-
 	retq
 END(mcount)
 
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index ab115cd..d073d98 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -11,17 +11,18 @@
 
 #include <linux/spinlock.h>
 #include <linux/hardirq.h>
+#include <linux/uaccess.h>
 #include <linux/ftrace.h>
 #include <linux/percpu.h>
 #include <linux/init.h>
 #include <linux/list.h>
 
-#include <asm/alternative.h>
 #include <asm/ftrace.h>
+#include <asm/nops.h>
 
 
 /* Long is fine, even if it is only 4 bytes ;-) */
-static long *ftrace_nop;
+static unsigned long *ftrace_nop;
 
 union ftrace_code_union {
 	char code[MCOUNT_INSN_SIZE];
@@ -60,11 +61,7 @@ notrace int
 ftrace_modify_code(unsigned long ip, unsigned char *old_code,
 		   unsigned char *new_code)
 {
-	unsigned replaced;
-	unsigned old = *(unsigned *)old_code; /* 4 bytes */
-	unsigned new = *(unsigned *)new_code; /* 4 bytes */
-	unsigned char newch = new_code[4];
-	int faulted = 0;
+	unsigned char replaced[MCOUNT_INSN_SIZE];
 
 	/*
 	 * Note: Due to modules and __init, code can
@@ -72,29 +69,20 @@ ftrace_modify_code(unsigned long ip, unsigned char *old_code,
 	 *  as well as code changing.
 	 *
 	 * No real locking needed, this code is run through
-	 * kstop_machine.
+	 * kstop_machine, or before SMP starts.
 	 */
-	asm volatile (
-		"1: lock\n"
-		"   cmpxchg %3, (%2)\n"
-		"   jnz 2f\n"
-		"   movb %b4, 4(%2)\n"
-		"2:\n"
-		".section .fixup, \"ax\"\n"
-		"3:	movl $1, %0\n"
-		"	jmp 2b\n"
-		".previous\n"
-		_ASM_EXTABLE(1b, 3b)
-		: "=r"(faulted), "=a"(replaced)
-		: "r"(ip), "r"(new), "c"(newch),
-		  "0"(faulted), "a"(old)
-		: "memory");
-	sync_core();
+	if (__copy_from_user_inatomic(replaced, (char __user *)ip, MCOUNT_INSN_SIZE))
+		return 1;
+
+	if (memcmp(replaced, old_code, MCOUNT_INSN_SIZE) != 0)
+		return 2;
 
-	if (replaced != old && replaced != new)
-		faulted = 2;
+	WARN_ON_ONCE(__copy_to_user_inatomic((char __user *)ip, new_code,
+				    MCOUNT_INSN_SIZE));
 
-	return faulted;
+	sync_core();
+
+	return 0;
 }
 
 notrace int ftrace_update_ftrace_func(ftrace_func_t func)
@@ -112,30 +100,76 @@ notrace int ftrace_update_ftrace_func(ftrace_func_t func)
 
 notrace int ftrace_mcount_set(unsigned long *data)
 {
-	unsigned long ip = (long)(&mcount_call);
-	unsigned long *addr = data;
-	unsigned char old[MCOUNT_INSN_SIZE], *new;
-
-	/*
-	 * Replace the mcount stub with a pointer to the
-	 * ip recorder function.
-	 */
-	memcpy(old, &mcount_call, MCOUNT_INSN_SIZE);
-	new = ftrace_call_replace(ip, *addr);
-	*addr = ftrace_modify_code(ip, old, new);
-
+	/* mcount is initialized as a nop */
+	*data = 0;
 	return 0;
 }
 
 int __init ftrace_dyn_arch_init(void *data)
 {
-	const unsigned char *const *noptable = find_nop_table();
-
-	/* This is running in kstop_machine */
-
-	ftrace_mcount_set(data);
+	extern const unsigned char ftrace_test_p6nop[];
+	extern const unsigned char ftrace_test_nop5[];
+	extern const unsigned char ftrace_test_jmp[];
+	int faulted = 0;
 
-	ftrace_nop = (unsigned long *)noptable[MCOUNT_INSN_SIZE];
+	/*
+	 * There is no good nop for all x86 archs.
+	 * We will default to using the P6_NOP5, but first we
+	 * will test to make sure that the nop will actually
+	 * work on this CPU. If it faults, we will then
+	 * go to a lesser efficient 5 byte nop. If that fails
+	 * we then just use a jmp as our nop. This isn't the most
+	 * efficient nop, but we can not use a multi part nop
+	 * since we would then risk being preempted in the middle
+	 * of that nop, and if we enabled tracing then, it might
+	 * cause a system crash.
+	 *
+	 * TODO: check the cpuid to determine the best nop.
+	 */
+	asm volatile (
+		"jmp ftrace_test_jmp\n"
+		/* This code needs to stay around */
+		".section .text, \"ax\"\n"
+		"ftrace_test_jmp:"
+		"jmp ftrace_test_p6nop\n"
+		"nop\n"
+		"nop\n"
+		"nop\n"  /* 2 byte jmp + 3 bytes */
+		"ftrace_test_p6nop:"
+		P6_NOP5
+		"jmp 1f\n"
+		"ftrace_test_nop5:"
+		".byte 0x66,0x66,0x66,0x66,0x90\n"
+		"jmp 1f\n"
+		".previous\n"
+		"1:"
+		".section .fixup, \"ax\"\n"
+		"2:	movl $1, %0\n"
+		"	jmp ftrace_test_nop5\n"
+		"3:	movl $2, %0\n"
+		"	jmp 1b\n"
+		".previous\n"
+		_ASM_EXTABLE(ftrace_test_p6nop, 2b)
+		_ASM_EXTABLE(ftrace_test_nop5, 3b)
+		: "=r"(faulted) : "0" (faulted));
+
+	switch (faulted) {
+	case 0:
+		pr_info("ftrace: converting mcount calls to 0f 1f 44 00 00\n");
+		ftrace_nop = (unsigned long *)ftrace_test_p6nop;
+		break;
+	case 1:
+		pr_info("ftrace: converting mcount calls to 66 66 66 66 90\n");
+		ftrace_nop = (unsigned long *)ftrace_test_nop5;
+		break;
+	case 2:
+		pr_info("ftrace: converting mcount calls to jmp . + 5\n");
+		ftrace_nop = (unsigned long *)ftrace_test_jmp;
+		break;
+	}
+
+	/* The return code is retured via data */
+	*(unsigned long *)data = 0;
 
 	return 0;
 }
diff --git a/arch/x86/mm/mmio-mod.c b/arch/x86/mm/mmio-mod.c
index 635b50e..2c4baa8 100644
--- a/arch/x86/mm/mmio-mod.c
+++ b/arch/x86/mm/mmio-mod.c
@@ -56,13 +56,6 @@ struct remap_trace {
 static DEFINE_PER_CPU(struct trap_reason, pf_reason);
 static DEFINE_PER_CPU(struct mmiotrace_rw, cpu_trace);
 
-#if 0 /* XXX: no way gather this info anymore */
-/* Access to this is not per-cpu. */
-static DEFINE_PER_CPU(atomic_t, dropped);
-#endif
-
-static struct dentry *marker_file;
-
 static DEFINE_MUTEX(mmiotrace_mutex);
 static DEFINE_SPINLOCK(trace_lock);
 static atomic_t mmiotrace_enabled;
@@ -75,7 +68,7 @@ static LIST_HEAD(trace_list);		/* struct remap_trace */
  *   and trace_lock.
  * - Routines depending on is_enabled() must take trace_lock.
  * - trace_list users must hold trace_lock.
- * - is_enabled() guarantees that mmio_trace_record is allowed.
+ * - is_enabled() guarantees that mmio_trace_{rw,mapping} are allowed.
  * - pre/post callbacks assume the effect of is_enabled() being true.
  */
 
@@ -97,44 +90,6 @@ static bool is_enabled(void)
 	return atomic_read(&mmiotrace_enabled);
 }
 
-#if 0 /* XXX: needs rewrite */
-/*
- * Write callback for the debugfs entry:
- * Read a marker and write it to the mmio trace log
- */
-static ssize_t write_marker(struct file *file, const char __user *buffer,
-						size_t count, loff_t *ppos)
-{
-	char *event = NULL;
-	struct mm_io_header *headp;
-	ssize_t len = (count > 65535) ? 65535 : count;
-
-	event = kzalloc(sizeof(*headp) + len, GFP_KERNEL);
-	if (!event)
-		return -ENOMEM;
-
-	headp = (struct mm_io_header *)event;
-	headp->type = MMIO_MAGIC | (MMIO_MARKER << MMIO_OPCODE_SHIFT);
-	headp->data_len = len;
-
-	if (copy_from_user(event + sizeof(*headp), buffer, len)) {
-		kfree(event);
-		return -EFAULT;
-	}
-
-	spin_lock_irq(&trace_lock);
-#if 0 /* XXX: convert this to use tracing */
-	if (is_enabled())
-		relay_write(chan, event, sizeof(*headp) + len);
-	else
-#endif
-		len = -EINVAL;
-	spin_unlock_irq(&trace_lock);
-	kfree(event);
-	return len;
-}
-#endif
-
 static void print_pte(unsigned long address)
 {
 	unsigned int level;
@@ -307,8 +262,10 @@ static void ioremap_trace_core(resource_size_t offset, unsigned long size,
 	map.map_id = trace->id;
 
 	spin_lock_irq(&trace_lock);
-	if (!is_enabled())
+	if (!is_enabled()) {
+		kfree(trace);
 		goto not_enabled;
+	}
 
 	mmio_trace_mapping(&map);
 	list_add_tail(&trace->list, &trace_list);
@@ -377,6 +334,23 @@ void mmiotrace_iounmap(volatile void __iomem *addr)
 		iounmap_trace_core(addr);
 }
 
+int mmiotrace_printk(const char *fmt, ...)
+{
+	int ret = 0;
+	va_list args;
+	unsigned long flags;
+	va_start(args, fmt);
+
+	spin_lock_irqsave(&trace_lock, flags);
+	if (is_enabled())
+		ret = mmio_trace_printk(fmt, args);
+	spin_unlock_irqrestore(&trace_lock, flags);
+
+	va_end(args);
+	return ret;
+}
+EXPORT_SYMBOL(mmiotrace_printk);
+
 static void clear_trace_list(void)
 {
 	struct remap_trace *trace;
@@ -462,26 +436,12 @@ static void leave_uniprocessor(void)
 }
 #endif
 
-#if 0 /* XXX: out of order */
-static struct file_operations fops_marker = {
-	.owner =	THIS_MODULE,
-	.write =	write_marker
-};
-#endif
-
 void enable_mmiotrace(void)
 {
 	mutex_lock(&mmiotrace_mutex);
 	if (is_enabled())
 		goto out;
 
-#if 0 /* XXX: tracing does not support text entries */
-	marker_file = debugfs_create_file("marker", 0660, dir, NULL,
-								&fops_marker);
-	if (!marker_file)
-		pr_err(NAME "marker file creation failed.\n");
-#endif
-
 	if (nommiotrace)
 		pr_info(NAME "MMIO tracing disabled.\n");
 	enter_uniprocessor();
@@ -506,11 +466,6 @@ void disable_mmiotrace(void)
 
 	clear_trace_list(); /* guarantees: no more kmmio callbacks */
 	leave_uniprocessor();
-	if (marker_file) {
-		debugfs_remove(marker_file);
-		marker_file = NULL;
-	}
-
 	pr_info(NAME "disabled.\n");
 out:
 	mutex_unlock(&mmiotrace_mutex);
diff --git a/arch/x86/mm/pf_in.c b/arch/x86/mm/pf_in.c
index efa1911..df3d5c8 100644
--- a/arch/x86/mm/pf_in.c
+++ b/arch/x86/mm/pf_in.c
@@ -79,25 +79,34 @@ static unsigned int mw32[] = { 0xC7 };
 static unsigned int mw64[] = { 0x89, 0x8B };
 #endif /* not __i386__ */
 
-static int skip_prefix(unsigned char *addr, int *shorted, int *enlarged,
-								int *rexr)
+struct prefix_bits {
+	unsigned shorted:1;
+	unsigned enlarged:1;
+	unsigned rexr:1;
+	unsigned rex:1;
+};
+
+static int skip_prefix(unsigned char *addr, struct prefix_bits *prf)
 {
 	int i;
 	unsigned char *p = addr;
-	*shorted = 0;
-	*enlarged = 0;
-	*rexr = 0;
+	prf->shorted = 0;
+	prf->enlarged = 0;
+	prf->rexr = 0;
+	prf->rex = 0;
 
 restart:
 	for (i = 0; i < ARRAY_SIZE(prefix_codes); i++) {
 		if (*p == prefix_codes[i]) {
 			if (*p == 0x66)
-				*shorted = 1;
+				prf->shorted = 1;
 #ifdef __amd64__
 			if ((*p & 0xf8) == 0x48)
-				*enlarged = 1;
+				prf->enlarged = 1;
 			if ((*p & 0xf4) == 0x44)
-				*rexr = 1;
+				prf->rexr = 1;
+			if ((*p & 0xf0) == 0x40)
+				prf->rex = 1;
 #endif
 			p++;
 			goto restart;
@@ -135,12 +144,12 @@ enum reason_type get_ins_type(unsigned long ins_addr)
 {
 	unsigned int opcode;
 	unsigned char *p;
-	int shorted, enlarged, rexr;
+	struct prefix_bits prf;
 	int i;
 	enum reason_type rv = OTHERS;
 
 	p = (unsigned char *)ins_addr;
-	p += skip_prefix(p, &shorted, &enlarged, &rexr);
+	p += skip_prefix(p, &prf);
 	p += get_opcode(p, &opcode);
 
 	CHECK_OP_TYPE(opcode, reg_rop, REG_READ);
@@ -156,10 +165,11 @@ static unsigned int get_ins_reg_width(unsigned long ins_addr)
 {
 	unsigned int opcode;
 	unsigned char *p;
-	int i, shorted, enlarged, rexr;
+	struct prefix_bits prf;
+	int i;
 
 	p = (unsigned char *)ins_addr;
-	p += skip_prefix(p, &shorted, &enlarged, &rexr);
+	p += skip_prefix(p, &prf);
 	p += get_opcode(p, &opcode);
 
 	for (i = 0; i < ARRAY_SIZE(rw8); i++)
@@ -168,7 +178,7 @@ static unsigned int get_ins_reg_width(unsigned long ins_addr)
 
 	for (i = 0; i < ARRAY_SIZE(rw32); i++)
 		if (rw32[i] == opcode)
-			return (shorted ? 2 : (enlarged ? 8 : 4));
+			return prf.shorted ? 2 : (prf.enlarged ? 8 : 4);
 
 	printk(KERN_ERR "mmiotrace: Unknown opcode 0x%02x\n", opcode);
 	return 0;
@@ -178,10 +188,11 @@ unsigned int get_ins_mem_width(unsigned long ins_addr)
 {
 	unsigned int opcode;
 	unsigned char *p;
-	int i, shorted, enlarged, rexr;
+	struct prefix_bits prf;
+	int i;
 
 	p = (unsigned char *)ins_addr;
-	p += skip_prefix(p, &shorted, &enlarged, &rexr);
+	p += skip_prefix(p, &prf);
 	p += get_opcode(p, &opcode);
 
 	for (i = 0; i < ARRAY_SIZE(mw8); i++)
@@ -194,11 +205,11 @@ unsigned int get_ins_mem_width(unsigned long ins_addr)
 
 	for (i = 0; i < ARRAY_SIZE(mw32); i++)
 		if (mw32[i] == opcode)
-			return shorted ? 2 : 4;
+			return prf.shorted ? 2 : 4;
 
 	for (i = 0; i < ARRAY_SIZE(mw64); i++)
 		if (mw64[i] == opcode)
-			return shorted ? 2 : (enlarged ? 8 : 4);
+			return prf.shorted ? 2 : (prf.enlarged ? 8 : 4);
 
 	printk(KERN_ERR "mmiotrace: Unknown opcode 0x%02x\n", opcode);
 	return 0;
@@ -238,7 +249,7 @@ enum {
 #endif
 };
 
-static unsigned char *get_reg_w8(int no, struct pt_regs *regs)
+static unsigned char *get_reg_w8(int no, int rex, struct pt_regs *regs)
 {
 	unsigned char *rv = NULL;
 
@@ -255,18 +266,6 @@ static unsigned char *get_reg_w8(int no, struct pt_regs *regs)
 	case arg_DL:
 		rv = (unsigned char *)&regs->dx;
 		break;
-	case arg_AH:
-		rv = 1 + (unsigned char *)&regs->ax;
-		break;
-	case arg_BH:
-		rv = 1 + (unsigned char *)&regs->bx;
-		break;
-	case arg_CH:
-		rv = 1 + (unsigned char *)&regs->cx;
-		break;
-	case arg_DH:
-		rv = 1 + (unsigned char *)&regs->dx;
-		break;
 #ifdef __amd64__
 	case arg_R8:
 		rv = (unsigned char *)&regs->r8;
@@ -294,9 +293,55 @@ static unsigned char *get_reg_w8(int no, struct pt_regs *regs)
 		break;
 #endif
 	default:
-		printk(KERN_ERR "mmiotrace: Error reg no# %d\n", no);
 		break;
 	}
+
+	if (rv)
+		return rv;
+
+	if (rex) {
+		/*
+		 * If REX prefix exists, access low bytes of SI etc.
+		 * instead of AH etc.
+		 */
+		switch (no) {
+		case arg_SI:
+			rv = (unsigned char *)&regs->si;
+			break;
+		case arg_DI:
+			rv = (unsigned char *)&regs->di;
+			break;
+		case arg_BP:
+			rv = (unsigned char *)&regs->bp;
+			break;
+		case arg_SP:
+			rv = (unsigned char *)&regs->sp;
+			break;
+		default:
+			break;
+		}
+	} else {
+		switch (no) {
+		case arg_AH:
+			rv = 1 + (unsigned char *)&regs->ax;
+			break;
+		case arg_BH:
+			rv = 1 + (unsigned char *)&regs->bx;
+			break;
+		case arg_CH:
+			rv = 1 + (unsigned char *)&regs->cx;
+			break;
+		case arg_DH:
+			rv = 1 + (unsigned char *)&regs->dx;
+			break;
+		default:
+			break;
+		}
+	}
+
+	if (!rv)
+		printk(KERN_ERR "mmiotrace: Error reg no# %d\n", no);
+
 	return rv;
 }
 
@@ -368,11 +413,12 @@ unsigned long get_ins_reg_val(unsigned long ins_addr, struct pt_regs *regs)
 	unsigned char mod_rm;
 	int reg;
 	unsigned char *p;
-	int i, shorted, enlarged, rexr;
+	struct prefix_bits prf;
+	int i;
 	unsigned long rv;
 
 	p = (unsigned char *)ins_addr;
-	p += skip_prefix(p, &shorted, &enlarged, &rexr);
+	p += skip_prefix(p, &prf);
 	p += get_opcode(p, &opcode);
 	for (i = 0; i < ARRAY_SIZE(reg_rop); i++)
 		if (reg_rop[i] == opcode) {
@@ -392,10 +438,10 @@ unsigned long get_ins_reg_val(unsigned long ins_addr, struct pt_regs *regs)
 
 do_work:
 	mod_rm = *p;
-	reg = ((mod_rm >> 3) & 0x7) | (rexr << 3);
+	reg = ((mod_rm >> 3) & 0x7) | (prf.rexr << 3);
 	switch (get_ins_reg_width(ins_addr)) {
 	case 1:
-		return *get_reg_w8(reg, regs);
+		return *get_reg_w8(reg, prf.rex, regs);
 
 	case 2:
 		return *(unsigned short *)get_reg_w32(reg, regs);
@@ -422,11 +468,12 @@ unsigned long get_ins_imm_val(unsigned long ins_addr)
 	unsigned char mod_rm;
 	unsigned char mod;
 	unsigned char *p;
-	int i, shorted, enlarged, rexr;
+	struct prefix_bits prf;
+	int i;
 	unsigned long rv;
 
 	p = (unsigned char *)ins_addr;
-	p += skip_prefix(p, &shorted, &enlarged, &rexr);
+	p += skip_prefix(p, &prf);
 	p += get_opcode(p, &opcode);
 	for (i = 0; i < ARRAY_SIZE(imm_wop); i++)
 		if (imm_wop[i] == opcode) {
diff --git a/arch/x86/mm/testmmiotrace.c b/arch/x86/mm/testmmiotrace.c
index d877c5b..ab50a8d 100644
--- a/arch/x86/mm/testmmiotrace.c
+++ b/arch/x86/mm/testmmiotrace.c
@@ -3,6 +3,7 @@
  */
 #include <linux/module.h>
 #include <linux/io.h>
+#include <linux/mmiotrace.h>
 
 #define MODULE_NAME "testmmiotrace"
 
@@ -13,6 +14,7 @@ MODULE_PARM_DESC(mmio_address, "Start address of the mapping of 16 kB.");
 static void do_write_test(void __iomem *p)
 {
 	unsigned int i;
+	mmiotrace_printk("Write test.\n");
 	for (i = 0; i < 256; i++)
 		iowrite8(i, p + i);
 	for (i = 1024; i < (5 * 1024); i += 2)
@@ -24,6 +26,7 @@ static void do_write_test(void __iomem *p)
 static void do_read_test(void __iomem *p)
 {
 	unsigned int i;
+	mmiotrace_printk("Read test.\n");
 	for (i = 0; i < 256; i++)
 		ioread8(p + i);
 	for (i = 1024; i < (5 * 1024); i += 2)
@@ -39,6 +42,7 @@ static void do_test(void)
 		pr_err(MODULE_NAME ": could not ioremap, aborting.\n");
 		return;
 	}
+	mmiotrace_printk("ioremap returned %p.\n", p);
 	do_write_test(p);
 	do_read_test(p);
 	iounmap(p);