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.
2026-09-21 14:15:21 -07:00 · 2008-10-20 13:35:07 -07:00
parent b9d7ccf56b 98d9c66ab0
commit 92b29b86fe
65 changed files with 6137 additions and 1614 deletions
@@ -50,10 +50,12 @@ Connecting a function (probe) to a marker is done by providing a probe (function
 to call) for the specific marker through marker_probe_register() and can be
 activated by calling marker_arm(). Marker deactivation can be done by calling
 marker_disarm() as many times as marker_arm() has been called. Removing a probe
-is done through marker_probe_unregister(); it will disarm the probe and make
-sure there is no caller left using the probe when it returns. Probe removal is
-preempt-safe because preemption is disabled around the probe call. See the
-"Probe example" section below for a sample probe module.
+is done through marker_probe_unregister(); it will disarm the probe.
+marker_synchronize_unregister() must be called before the end of the module exit
+function to make sure there is no caller left using the probe. This, and the
+fact that preemption is disabled around the probe call, make sure that probe
+removal and module unload are safe. See the "Probe example" section below for a
+sample probe module.

 The marker mechanism supports inserting multiple instances of the same marker.
 Markers can be put in inline functions, inlined static functions, and
@@ -0,0 +1,101 @@
+	             Using the Linux Kernel Tracepoints
+
+			    Mathieu Desnoyers
+
+
+This document introduces Linux Kernel Tracepoints and their use. It provides
+examples of how to insert tracepoints in the kernel and connect probe functions
+to them and provides some examples of probe functions.
+
+
+* Purpose of tracepoints
+
+A tracepoint placed in code provides a hook to call a function (probe) that you
+can provide at runtime. A tracepoint can be "on" (a probe is connected to it) or
+"off" (no probe is attached). When a tracepoint is "off" it has no effect,
+except for adding a tiny time penalty (checking a condition for a branch) and
+space penalty (adding a few bytes for the function call at the end of the
+instrumented function and adds a data structure in a separate section).  When a
+tracepoint is "on", the function you provide is called each time the tracepoint
+is executed, in the execution context of the caller. When the function provided
+ends its execution, it returns to the caller (continuing from the tracepoint
+site).
+
+You can put tracepoints at important locations in the code. They are
+lightweight hooks that can pass an arbitrary number of parameters,
+which prototypes are described in a tracepoint declaration placed in a header
+file.
+
+They can be used for tracing and performance accounting.
+
+
+* Usage
+
+Two elements are required for tracepoints :
+
+- A tracepoint definition, placed in a header file.
+- The tracepoint statement, in C code.
+
+In order to use tracepoints, you should include linux/tracepoint.h.
+
+In include/trace/subsys.h :
+
+#include <linux/tracepoint.h>
+
+DEFINE_TRACE(subsys_eventname,
+	TPPTOTO(int firstarg, struct task_struct *p),
+	TPARGS(firstarg, p));
+
+In subsys/file.c (where the tracing statement must be added) :
+
+#include <trace/subsys.h>
+
+void somefct(void)
+{
+	...
+	trace_subsys_eventname(arg, task);
+	...
+}
+
+Where :
+- subsys_eventname is an identifier unique to your event
+    - subsys is the name of your subsystem.
+    - eventname is the name of the event to trace.
+- TPPTOTO(int firstarg, struct task_struct *p) is the prototype of the function
+  called by this tracepoint.
+- TPARGS(firstarg, p) are the parameters names, same as found in the prototype.
+
+Connecting a function (probe) to a tracepoint is done by providing a probe
+(function to call) for the specific tracepoint through
+register_trace_subsys_eventname().  Removing a probe is done through
+unregister_trace_subsys_eventname(); it will remove the probe sure there is no
+caller left using the probe when it returns. Probe removal is preempt-safe
+because preemption is disabled around the probe call. See the "Probe example"
+section below for a sample probe module.
+
+The tracepoint mechanism supports inserting multiple instances of the same
+tracepoint, but a single definition must be made of a given tracepoint name over
+all the kernel to make sure no type conflict will occur. Name mangling of the
+tracepoints is done using the prototypes to make sure typing is correct.
+Verification of probe type correctness is done at the registration site by the
+compiler. Tracepoints can be put in inline functions, inlined static functions,
+and unrolled loops as well as regular functions.
+
+The naming scheme "subsys_event" is suggested here as a convention intended
+to limit collisions. Tracepoint names are global to the kernel: they are
+considered as being the same whether they are in the core kernel image or in
+modules.
+
+
+* Probe / tracepoint example
+
+See the example provided in samples/tracepoints/src
+
+Compile them with your kernel.
+
+Run, as root :
+modprobe tracepoint-example (insmod order is not important)
+modprobe tracepoint-probe-example
+cat /proc/tracepoint-example (returns an expected error)
+rmmod tracepoint-example tracepoint-probe-example
+dmesg
@@ -36,7 +36,7 @@ $ mount -t debugfs debugfs /debug
 $ echo mmiotrace > /debug/tracing/current_tracer
 $ cat /debug/tracing/trace_pipe > mydump.txt &
 Start X or whatever.
-$ echo "X is up" > /debug/tracing/marker
+$ echo "X is up" > /debug/tracing/trace_marker
 $ echo none > /debug/tracing/current_tracer
 Check for lost events.

@@ -59,9 +59,8 @@ The 'cat' process should stay running (sleeping) in the background.
 Load the driver you want to trace and use it. Mmiotrace will only catch MMIO
 accesses to areas that are ioremapped while mmiotrace is active.

-[Unimplemented feature:]
 During tracing you can place comments (markers) into the trace by
-$ echo "X is up" > /debug/tracing/marker
+$ echo "X is up" > /debug/tracing/trace_marker
 This makes it easier to see which part of the (huge) trace corresponds to
 which action. It is recommended to place descriptive markers about what you
 do.
@@ -232,6 +232,7 @@ static void __exit sputrace_exit(void)

 	remove_proc_entry("sputrace", NULL);
 	kfree(sputrace_log);
+	marker_synchronize_unregister();
 }

 module_init(sputrace_init);
@@ -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)
@@ -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;
@@ -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)

@@ -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)

@@ -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");
+	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;
+
+	WARN_ON_ONCE(__copy_to_user_inatomic((char __user *)ip, new_code,
+				    MCOUNT_INSN_SIZE));
+
 	sync_core();

-	if (replaced != old && replaced != new)
-		faulted = 2;
-
-	return faulted;
+	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();
+	extern const unsigned char ftrace_test_p6nop[];
+	extern const unsigned char ftrace_test_nop5[];
+	extern const unsigned char ftrace_test_jmp[];
+	int faulted = 0;

-	/* This is running in kstop_machine */
+	/*
+	 * 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));

-	ftrace_mcount_set(data);
+	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;
+	}

-	ftrace_nop = (unsigned long *)noptable[MCOUNT_INSN_SIZE];
+	/* The return code is retured via data */
+	*(unsigned long *)data = 0;

 	return 0;
 }
@@ -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);
@@ -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) {
@@ -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);
@@ -37,6 +37,13 @@
 #define MEM_DISCARD(sec) *(.mem##sec)
 #endif

+#ifdef CONFIG_FTRACE_MCOUNT_RECORD
+#define MCOUNT_REC()	VMLINUX_SYMBOL(__start_mcount_loc) = .; \
+			*(__mcount_loc)				\
+			VMLINUX_SYMBOL(__stop_mcount_loc) = .;
+#else
+#define MCOUNT_REC()
+#endif

 /* .data section */
 #define DATA_DATA							\
@@ -52,7 +59,10 @@
 	. = ALIGN(8);							\
 	VMLINUX_SYMBOL(__start___markers) = .;				\
 	*(__markers)							\
-	VMLINUX_SYMBOL(__stop___markers) = .;
+	VMLINUX_SYMBOL(__stop___markers) = .;				\
+	VMLINUX_SYMBOL(__start___tracepoints) = .;			\
+	*(__tracepoints)						\
+	VMLINUX_SYMBOL(__stop___tracepoints) = .;

 #define RO_DATA(align)							\
 	. = ALIGN((align));						\
@@ -61,6 +71,7 @@
 		*(.rodata) *(.rodata.*)					\
 		*(__vermagic)		/* Kernel version magic */	\
 		*(__markers_strings)	/* Markers: strings */		\
+		*(__tracepoints_strings)/* Tracepoints: strings */	\
 	}								\
 									\
 	.rodata1          : AT(ADDR(.rodata1) - LOAD_OFFSET) {		\
@@ -188,6 +199,7 @@
 	/* __*init sections */						\
 	__init_rodata : AT(ADDR(__init_rodata) - LOAD_OFFSET) {		\
 		*(.ref.rodata)						\
+		MCOUNT_REC()						\
 		DEV_KEEP(init.rodata)					\
 		DEV_KEEP(exit.rodata)					\
 		CPU_KEEP(init.rodata)					\
@@ -7,6 +7,16 @@

 #ifndef __ASSEMBLY__
 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.
+	 */
+	return addr - 1;
+}
 #endif

 #endif /* CONFIG_FTRACE */
@@ -44,6 +44,8 @@ extern void __chk_io_ptr(const volatile void __iomem *);
 # error Sorry, your compiler is too old/not recognized.
 #endif

+#define notrace __attribute__((no_instrument_function))
+
 /* Intel compiler defines __GNUC__. So we will overwrite implementations
 * coming from above header files here
 */
@@ -1,10 +1,14 @@
 #ifndef _LINUX_FTRACE_H
 #define _LINUX_FTRACE_H

-#ifdef CONFIG_FTRACE
-
 #include <linux/linkage.h>
 #include <linux/fs.h>
+#include <linux/ktime.h>
+#include <linux/init.h>
+#include <linux/types.h>
+#include <linux/kallsyms.h>
+
+#ifdef CONFIG_FTRACE

 extern int ftrace_enabled;
 extern int
@@ -36,6 +40,7 @@ extern void ftrace_stub(unsigned long a0, unsigned long a1);
 # define register_ftrace_function(ops) do { } while (0)
 # define unregister_ftrace_function(ops) do { } while (0)
 # define clear_ftrace_function(ops) do { } while (0)
+static inline void ftrace_kill_atomic(void) { }
 #endif /* CONFIG_FTRACE */

 #ifdef CONFIG_DYNAMIC_FTRACE
@@ -76,8 +81,10 @@ extern void mcount_call(void);

 extern int skip_trace(unsigned long ip);

-void ftrace_disable_daemon(void);
-void ftrace_enable_daemon(void);
+extern void ftrace_release(void *start, unsigned long size);
+
+extern void ftrace_disable_daemon(void);
+extern void ftrace_enable_daemon(void);

 #else
 # define skip_trace(ip)				({ 0; })
@@ -85,6 +92,7 @@ void ftrace_enable_daemon(void);
 # define ftrace_set_filter(buf, len, reset)	do { } while (0)
 # define ftrace_disable_daemon()		do { } while (0)
 # define ftrace_enable_daemon()			do { } while (0)
+static inline void ftrace_release(void *start, unsigned long size) { }
 #endif /* CONFIG_DYNAMIC_FTRACE */

 /* totally disable ftrace - can not re-enable after this */
@@ -98,9 +106,11 @@ static inline void tracer_disable(void)
 #endif
 }

-/* Ftrace disable/restore without lock. Some synchronization mechanism
+/*
+ * Ftrace disable/restore without lock. Some synchronization mechanism
 * must be used to prevent ftrace_enabled to be changed between
- * disable/restore. */
+ * disable/restore.
+ */
 static inline int __ftrace_enabled_save(void)
 {
 #ifdef CONFIG_FTRACE
@@ -157,9 +167,71 @@ static inline void __ftrace_enabled_restore(int enabled)
 #ifdef CONFIG_TRACING
 extern void
 ftrace_special(unsigned long arg1, unsigned long arg2, unsigned long arg3);
+
+/**
+ * ftrace_printk - printf formatting in the ftrace buffer
+ * @fmt: the printf format for printing
+ *
+ * Note: __ftrace_printk is an internal function for ftrace_printk and
+ *       the @ip is passed in via the ftrace_printk macro.
+ *
+ * This function allows a kernel developer to debug fast path sections
+ * that printk is not appropriate for. By scattering in various
+ * printk like tracing in the code, a developer can quickly see
+ * where problems are occurring.
+ *
+ * This is intended as a debugging tool for the developer only.
+ * Please refrain from leaving ftrace_printks scattered around in
+ * your code.
+ */
+# define ftrace_printk(fmt...) __ftrace_printk(_THIS_IP_, fmt)
+extern int
+__ftrace_printk(unsigned long ip, const char *fmt, ...)
+	__attribute__ ((format (printf, 2, 3)));
+extern void ftrace_dump(void);
 #else
 static inline void
 ftrace_special(unsigned long arg1, unsigned long arg2, unsigned long arg3) { }
+static inline int
+ftrace_printk(const char *fmt, ...) __attribute__ ((format (printf, 1, 0)));
+
+static inline int
+ftrace_printk(const char *fmt, ...)
+{
+	return 0;
+}
+static inline void ftrace_dump(void) { }
 #endif

+#ifdef CONFIG_FTRACE_MCOUNT_RECORD
+extern void ftrace_init(void);
+extern void ftrace_init_module(unsigned long *start, unsigned long *end);
+#else
+static inline void ftrace_init(void) { }
+static inline void
+ftrace_init_module(unsigned long *start, unsigned long *end) { }
+#endif
+
+
+struct boot_trace {
+	pid_t			caller;
+	char			func[KSYM_NAME_LEN];
+	int			result;
+	unsigned long long	duration;		/* usecs */
+	ktime_t			calltime;
+	ktime_t			rettime;
+};
+
+#ifdef CONFIG_BOOT_TRACER
+extern void trace_boot(struct boot_trace *it, initcall_t fn);
+extern void start_boot_trace(void);
+extern void stop_boot_trace(void);
+#else
+static inline void trace_boot(struct boot_trace *it, initcall_t fn) { }
+static inline void start_boot_trace(void) { }
+static inline void stop_boot_trace(void) { }
+#endif
+
+
+
 #endif /* _LINUX_FTRACE_H */
@@ -40,7 +40,7 @@

 /* These are for everybody (although not all archs will actually
   discard it in modules) */
-#define __init		__section(.init.text) __cold
+#define __init		__section(.init.text) __cold notrace
 #define __initdata	__section(.init.data)
 #define __initconst	__section(.init.rodata)
 #define __exitdata	__section(.exit.data)
@@ -496,4 +496,9 @@ struct sysinfo {
 #define NUMA_BUILD 0
 #endif

+/* Rebuild everything on CONFIG_FTRACE_MCOUNT_RECORD */
+#ifdef CONFIG_FTRACE_MCOUNT_RECORD
+# define REBUILD_DUE_TO_FTRACE_MCOUNT_RECORD
+#endif
+
 #endif
@@ -29,6 +29,7 @@
 *		<jkenisto@us.ibm.com>  and Prasanna S Panchamukhi
 *		<prasanna@in.ibm.com> added function-return probes.
 */
+#include <linux/linkage.h>
 #include <linux/list.h>
 #include <linux/notifier.h>
 #include <linux/smp.h>
@@ -47,7 +48,7 @@
 #define KPROBE_HIT_SSDONE	0x00000008

 /* Attach to insert probes on any functions which should be ignored*/
-#define __kprobes	__attribute__((__section__(".kprobes.text")))
+#define __kprobes	__attribute__((__section__(".kprobes.text"))) notrace

 struct kprobe;
 struct pt_regs;
@@ -256,7 +257,7 @@ void recycle_rp_inst(struct kretprobe_instance *ri, struct hlist_head *head);

 #else /* CONFIG_KPROBES */

-#define __kprobes	/**/
+#define __kprobes	notrace
 struct jprobe;
 struct kretprobe;

@@ -4,8 +4,6 @@
 #include <linux/compiler.h>
 #include <asm/linkage.h>

-#define notrace __attribute__((no_instrument_function))
-
 #ifdef __cplusplus
 #define CPP_ASMLINKAGE extern "C"
 #else
--- a/Show More
+++ b/Show More