Merge branch 'tracing-v28-for-linus' of...

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.

Documentation/markers.txt

@@ -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

Documentation/tracepoints.txt

+	             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

Documentation/tracers/mmiotrace.txt

@@ -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.

arch/powerpc/platforms/cell/spufs/sputrace.c

@@ -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);

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)

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;

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)
 

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)
 

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;
 }

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);

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) {

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);

include/asm-generic/vmlinux.lds.h

@@ -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)					\

include/asm-x86/ftrace.h

@@ -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 */

include/linux/compiler.h

@@ -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
  */

include/linux/ftrace.h

 #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 */

include/linux/init.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)

include/linux/kernel.h

@@ -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

include/linux/kprobes.h

@@ -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;
 

include/linux/linkage.h

@@ -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

include/linux/marker.h

@@ -160,4 +160,11 @@ extern int marker_probe_unregister_private_data(marker_probe_func *probe,
 extern void *marker_get_private_data(const char *name, marker_probe_func *probe,
 	int num);
 
+/*
+ * marker_synchronize_unregister must be called between the last marker probe
+ * unregistration and the end of module exit to make sure there is no caller
+ * executing a probe when it is freed.
+ */
+#define marker_synchronize_unregister() synchronize_sched()
+
 #endif

include/linux/mmiotrace.h

@@ -34,11 +34,15 @@ extern void unregister_kmmio_probe(struct kmmio_probe *p);
 /* Called from page fault handler. */
 extern int kmmio_handler(struct pt_regs *regs, unsigned long addr);
 
-/* Called from ioremap.c */
 #ifdef CONFIG_MMIOTRACE
+/* Called from ioremap.c */
 extern void mmiotrace_ioremap(resource_size_t offset, unsigned long size,
 							void __iomem *addr);
 extern void mmiotrace_iounmap(volatile void __iomem *addr);
+
+/* For anyone to insert markers. Remember trailing newline. */
+extern int mmiotrace_printk(const char *fmt, ...)
+				__attribute__ ((format (printf, 1, 2)));
 #else
 static inline void mmiotrace_ioremap(resource_size_t offset,
 					unsigned long size, void __iomem *addr)
@@ -48,15 +52,22 @@ static inline void mmiotrace_ioremap(resource_size_t offset,
 static inline void mmiotrace_iounmap(volatile void __iomem *addr)
 {
 }
-#endif /* CONFIG_MMIOTRACE_HOOKS */
+
+static inline int mmiotrace_printk(const char *fmt, ...)
+				__attribute__ ((format (printf, 1, 0)));
+
+static inline int mmiotrace_printk(const char *fmt, ...)
+{
+	return 0;
+}
+#endif /* CONFIG_MMIOTRACE */
 
 enum mm_io_opcode {
 	MMIO_READ = 0x1,     /* struct mmiotrace_rw */
 	MMIO_WRITE = 0x2,    /* struct mmiotrace_rw */
 	MMIO_PROBE = 0x3,    /* struct mmiotrace_map */
 	MMIO_UNPROBE = 0x4,  /* struct mmiotrace_map */
-	MMIO_MARKER = 0x5,   /* raw char data */
-	MMIO_UNKNOWN_OP = 0x6, /* struct mmiotrace_rw */
+	MMIO_UNKNOWN_OP = 0x5, /* struct mmiotrace_rw */
 };
 
 struct mmiotrace_rw {
@@ -81,5 +92,6 @@ extern void enable_mmiotrace(void);
 extern void disable_mmiotrace(void);
 extern void mmio_trace_rw(struct mmiotrace_rw *rw);
 extern void mmio_trace_mapping(struct mmiotrace_map *map);
+extern int mmio_trace_printk(const char *fmt, va_list args);
 
 #endif /* MMIOTRACE_H */

include/linux/module.h

@@ -16,6 +16,7 @@
 #include <linux/kobject.h>
 #include <linux/moduleparam.h>
 #include <linux/marker.h>
+#include <linux/tracepoint.h>
 #include <asm/local.h>
 
 #include <asm/module.h>
@@ -331,6 +332,10 @@ struct module
 	struct marker *markers;
 	unsigned int num_markers;
 #endif
+#ifdef CONFIG_TRACEPOINTS
+	struct tracepoint *tracepoints;
+	unsigned int num_tracepoints;
+#endif
 
 #ifdef CONFIG_MODULE_UNLOAD
 	/* What modules depend on me? */
@@ -453,6 +458,9 @@ extern void print_modules(void);
 
 extern void module_update_markers(void);
 
+extern void module_update_tracepoints(void);
+extern int module_get_iter_tracepoints(struct tracepoint_iter *iter);
+
 #else /* !CONFIG_MODULES... */
 #define EXPORT_SYMBOL(sym)
 #define EXPORT_SYMBOL_GPL(sym)
@@ -557,6 +565,15 @@ static inline void module_update_markers(void)
 {
 }
 
+static inline void module_update_tracepoints(void)
+{
+}
+
+static inline int module_get_iter_tracepoints(struct tracepoint_iter *iter)
+{
+	return 0;
+}
+
 #endif /* CONFIG_MODULES */
 
 struct device_driver;

include/linux/ring_buffer.h

+#ifndef _LINUX_RING_BUFFER_H
+#define _LINUX_RING_BUFFER_H
+
+#include <linux/mm.h>
+#include <linux/seq_file.h>
+
+struct ring_buffer;
+struct ring_buffer_iter;
+
+/*
+ * Don't reference this struct directly, use functions below.
+ */
+struct ring_buffer_event {
+	u32		type:2, len:3, time_delta:27;
+	u32		array[];
+};
+
+/**
+ * enum ring_buffer_type - internal ring buffer types
+ *
+ * @RINGBUF_TYPE_PADDING:	Left over page padding
+ *				 array is ignored
+ *				 size is variable depending on how much
+ *				  padding is needed
+ *
+ * @RINGBUF_TYPE_TIME_EXTEND:	Extend the time delta
+ *				 array[0] = time delta (28 .. 59)
+ *				 size = 8 bytes
+ *
+ * @RINGBUF_TYPE_TIME_STAMP:	Sync time stamp with external clock
+ *				 array[0] = tv_nsec
+ *				 array[1] = tv_sec
+ *				 size = 16 bytes
+ *
+ * @RINGBUF_TYPE_DATA:		Data record
+ *				 If len is zero:
+ *				  array[0] holds the actual length
+ *				  array[1..(length+3)/4-1] holds data
+ *				 else
+ *				  length = len << 2
+ *				  array[0..(length+3)/4] holds data
+ */
+enum ring_buffer_type {
+	RINGBUF_TYPE_PADDING,
+	RINGBUF_TYPE_TIME_EXTEND,
+	/* FIXME: RINGBUF_TYPE_TIME_STAMP not implemented */
+	RINGBUF_TYPE_TIME_STAMP,
+	RINGBUF_TYPE_DATA,
+};
+
+unsigned ring_buffer_event_length(struct ring_buffer_event *event);
+void *ring_buffer_event_data(struct ring_buffer_event *event);
+
+/**
+ * ring_buffer_event_time_delta - return the delta timestamp of the event
+ * @event: the event to get the delta timestamp of
+ *
+ * The delta timestamp is the 27 bit timestamp since the last event.
+ */
+static inline unsigned
+ring_buffer_event_time_delta(struct ring_buffer_event *event)
+{
+	return event->time_delta;
+}
+
+/*
+ * size is in bytes for each per CPU buffer.
+ */
+struct ring_buffer *
+ring_buffer_alloc(unsigned long size, unsigned flags);
+void ring_buffer_free(struct ring_buffer *buffer);
+
+int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size);
+
+struct ring_buffer_event *
+ring_buffer_lock_reserve(struct ring_buffer *buffer,
+			 unsigned long length,
+			 unsigned long *flags);
+int ring_buffer_unlock_commit(struct ring_buffer *buffer,
+			      struct ring_buffer_event *event,
+			      unsigned long flags);
+int ring_buffer_write(struct ring_buffer *buffer,
+		      unsigned long length, void *data);
+
+struct ring_buffer_event *
+ring_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts);
+struct ring_buffer_event *
+ring_buffer_consume(struct ring_buffer *buffer, int cpu, u64 *ts);
+
+struct ring_buffer_iter *
+ring_buffer_read_start(struct ring_buffer *buffer, int cpu);
+void ring_buffer_read_finish(struct ring_buffer_iter *iter);
+
+struct ring_buffer_event *
+ring_buffer_iter_peek(struct ring_buffer_iter *iter, u64 *ts);
+struct ring_buffer_event *
+ring_buffer_read(struct ring_buffer_iter *iter, u64 *ts);
+void ring_buffer_iter_reset(struct ring_buffer_iter *iter);
+int ring_buffer_iter_empty(struct ring_buffer_iter *iter);
+
+unsigned long ring_buffer_size(struct ring_buffer *buffer);
+
+void ring_buffer_reset_cpu(struct ring_buffer *buffer, int cpu);
+void ring_buffer_reset(struct ring_buffer *buffer);
+
+int ring_buffer_swap_cpu(struct ring_buffer *buffer_a,
+			 struct ring_buffer *buffer_b, int cpu);
+
+int ring_buffer_empty(struct ring_buffer *buffer);
+int ring_buffer_empty_cpu(struct ring_buffer *buffer, int cpu);
+
+void ring_buffer_record_disable(struct ring_buffer *buffer);
+void ring_buffer_record_enable(struct ring_buffer *buffer);
+void ring_buffer_record_disable_cpu(struct ring_buffer *buffer, int cpu);
+void ring_buffer_record_enable_cpu(struct ring_buffer *buffer, int cpu);
+
+unsigned long ring_buffer_entries(struct ring_buffer *buffer);
+unsigned long ring_buffer_overruns(struct ring_buffer *buffer);
+
+u64 ring_buffer_time_stamp(int cpu);
+void ring_buffer_normalize_time_stamp(int cpu, u64 *ts);
+
+enum ring_buffer_flags {
+	RB_FL_OVERWRITE		= 1 << 0,
+};
+
+#endif /* _LINUX_RING_BUFFER_H */

include/linux/tracepoint.h

+#ifndef _LINUX_TRACEPOINT_H
+#define _LINUX_TRACEPOINT_H
+
+/*
+ * Kernel Tracepoint API.
+ *
+ * See Documentation/tracepoint.txt.
+ *
+ * (C) Copyright 2008 Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>
+ *
+ * Heavily inspired from the Linux Kernel Markers.
+ *
+ * This file is released under the GPLv2.
+ * See the file COPYING for more details.
+ */
+
+#include <linux/types.h>
+#include <linux/rcupdate.h>
+
+struct module;
+struct tracepoint;
+
+struct tracepoint {
+	const char *name;		/* Tracepoint name */
+	int state;			/* State. */
+	void **funcs;
+} __attribute__((aligned(8)));
+
+
+#define TPPROTO(args...)	args
+#define TPARGS(args...)		args
+
+#ifdef CONFIG_TRACEPOINTS
+
+/*
+ * it_func[0] is never NULL because there is at least one element in the array
+ * when the array itself is non NULL.
+ */
+#define __DO_TRACE(tp, proto, args)					\
+	do {								\
+		void **it_func;						\
+									\
+		rcu_read_lock_sched();					\
+		it_func = rcu_dereference((tp)->funcs);			\
+		if (it_func) {						\
+			do {						\
+				((void(*)(proto))(*it_func))(args);	\
+			} while (*(++it_func));				\
+		}							\
+		rcu_read_unlock_sched();				\
+	} while (0)
+
+/*
+ * Make sure the alignment of the structure in the __tracepoints section will
+ * not add unwanted padding between the beginning of the section and the
+ * structure. Force alignment to the same alignment as the section start.
+ */
+#define DEFINE_TRACE(name, proto, args)					\
+	static inline void trace_##name(proto)				\
+	{								\
+		static const char __tpstrtab_##name[]			\
+		__attribute__((section("__tracepoints_strings")))	\
+		= #name ":" #proto;					\
+		static struct tracepoint __tracepoint_##name		\
+		__attribute__((section("__tracepoints"), aligned(8))) =	\
+		{ __tpstrtab_##name, 0, NULL };				\
+		if (unlikely(__tracepoint_##name.state))		\
+			__DO_TRACE(&__tracepoint_##name,		\
+				TPPROTO(proto), TPARGS(args));		\
+	}								\
+	static inline int register_trace_##name(void (*probe)(proto))	\
+	{								\
+		return tracepoint_probe_register(#name ":" #proto,	\
+			(void *)probe);					\
+	}								\
+	static inline void unregister_trace_##name(void (*probe)(proto))\
+	{								\
+		tracepoint_probe_unregister(#name ":" #proto,		\
+			(void *)probe);					\
+	}
+
+extern void tracepoint_update_probe_range(struct tracepoint *begin,
+	struct tracepoint *end);
+
+#else /* !CONFIG_TRACEPOINTS */
+#define DEFINE_TRACE(name, proto, args)			\
+	static inline void _do_trace_##name(struct tracepoint *tp, proto) \
+	{ }								\
+	static inline void trace_##name(proto)				\
+	{ }								\
+	static inline int register_trace_##name(void (*probe)(proto))	\
+	{								\
+		return -ENOSYS;						\
+	}								\
+	static inline void unregister_trace_##name(void (*probe)(proto))\
+	{ }
+
+static inline void tracepoint_update_probe_range(struct tracepoint *begin,
+	struct tracepoint *end)
+{ }
+#endif /* CONFIG_TRACEPOINTS */
+
+/*
+ * Connect a probe to a tracepoint.
+ * Internal API, should not be used directly.
+ */
+extern int tracepoint_probe_register(const char *name, void *probe);
+
+/*
+ * Disconnect a probe from a tracepoint.
+ * Internal API, should not be used directly.
+ */
+extern int tracepoint_probe_unregister(const char *name, void *probe);
+
+struct tracepoint_iter {
+	struct module *module;
+	struct tracepoint *tracepoint;
+};
+
+extern void tracepoint_iter_start(struct tracepoint_iter *iter);
+extern void tracepoint_iter_next(struct tracepoint_iter *iter);
+extern void tracepoint_iter_stop(struct tracepoint_iter *iter);
+extern void tracepoint_iter_reset(struct tracepoint_iter *iter);
+extern int tracepoint_get_iter_range(struct tracepoint **tracepoint,
+	struct tracepoint *begin, struct tracepoint *end);
+
+/*
+ * tracepoint_synchronize_unregister must be called between the last tracepoint
+ * probe unregistration and the end of module exit to make sure there is no
+ * caller executing a probe when it is freed.
+ */
+static inline void tracepoint_synchronize_unregister(void)
+{
+	synchronize_sched();
+}
+
+#endif

include/trace/sched.h

+#ifndef _TRACE_SCHED_H
+#define _TRACE_SCHED_H
+
+#include <linux/sched.h>
+#include <linux/tracepoint.h>
+
+DEFINE_TRACE(sched_kthread_stop,
+	TPPROTO(struct task_struct *t),
+		TPARGS(t));
+
+DEFINE_TRACE(sched_kthread_stop_ret,
+	TPPROTO(int ret),
+		TPARGS(ret));
+
+DEFINE_TRACE(sched_wait_task,
+	TPPROTO(struct rq *rq, struct task_struct *p),
+		TPARGS(rq, p));
+
+DEFINE_TRACE(sched_wakeup,
+	TPPROTO(struct rq *rq, struct task_struct *p),
+		TPARGS(rq, p));
+
+DEFINE_TRACE(sched_wakeup_new,
+	TPPROTO(struct rq *rq, struct task_struct *p),
+		TPARGS(rq, p));
+
+DEFINE_TRACE(sched_switch,
+	TPPROTO(struct rq *rq, struct task_struct *prev,
+		struct task_struct *next),
+		TPARGS(rq, prev, next));
+
+DEFINE_TRACE(sched_migrate_task,
+	TPPROTO(struct rq *rq, struct task_struct *p, int dest_cpu),
+		TPARGS(rq, p, dest_cpu));
+
+DEFINE_TRACE(sched_process_free,
+	TPPROTO(struct task_struct *p),
+		TPARGS(p));
+
+DEFINE_TRACE(sched_process_exit,
+	TPPROTO(struct task_struct *p),
+		TPARGS(p));
+
+DEFINE_TRACE(sched_process_wait,
+	TPPROTO(struct pid *pid),
+		TPARGS(pid));
+
+DEFINE_TRACE(sched_process_fork,
+	TPPROTO(struct task_struct *parent, struct task_struct *child),
+		TPARGS(parent, child));
+
+DEFINE_TRACE(sched_signal_send,
+	TPPROTO(int sig, struct task_struct *p),
+		TPARGS(sig, p));
+
+#endif

init/Kconfig

@@ -786,6 +786,13 @@ config PROFILING
 	  Say Y here to enable the extended profiling support mechanisms used
 	  by profilers such as OProfile.
 
+#
+# Place an empty function call at each tracepoint site. Can be
+# dynamically changed for a probe function.
+#
+config TRACEPOINTS
+	bool
+
 config MARKERS
 	bool "Activate markers"
 	help

init/main.c

@@ -61,6 +61,7 @@
 #include <linux/sched.h>
 #include <linux/signal.h>
 #include <linux/idr.h>
+#include <linux/ftrace.h>
 
 #include <asm/io.h>
 #include <asm/bugs.h>
@@ -689,6 +690,8 @@ asmlinkage void __init start_kernel(void)
 
 	acpi_early_init(); /* before LAPIC and SMP init */
 
+	ftrace_init();
+
 	/* Do the rest non-__init'ed, we're now alive */
 	rest_init();
 }
@@ -705,30 +708,31 @@ __setup("initcall_debug", initcall_debug_setup);
 int do_one_initcall(initcall_t fn)
 {
 	int count = preempt_count();
-	ktime_t t0, t1, delta;
+	ktime_t delta;
 	char msgbuf[64];
-	int result;
+	struct boot_trace it;
 
 	if (initcall_debug) {
-		printk("calling  %pF @ %i\n", fn, task_pid_nr(current));
-		t0 = ktime_get();
+		it.caller = task_pid_nr(current);
+		printk("calling  %pF @ %i\n", fn, it.caller);
+		it.calltime = ktime_get();
 	}
 
-	result = fn();
+	it.result = fn();
 
 	if (initcall_debug) {
-		t1 = ktime_get();
-		delta = ktime_sub(t1, t0);
-
-		printk("initcall %pF returned %d after %Ld msecs\n",
-			fn, result,
-			(unsigned long long) delta.tv64 >> 20);
+		it.rettime = ktime_get();
+		delta = ktime_sub(it.rettime, it.calltime);
+		it.duration = (unsigned long long) delta.tv64 >> 10;
+		printk("initcall %pF returned %d after %Ld usecs\n", fn,
+			it.result, it.duration);
+		trace_boot(&it, fn);
 	}
 
 	msgbuf[0] = 0;
 
-	if (result && result != -ENODEV && initcall_debug)
-		sprintf(msgbuf, "error code %d ", result);
+	if (it.result && it.result != -ENODEV && initcall_debug)
+		sprintf(msgbuf, "error code %d ", it.result);
 
 	if (preempt_count() != count) {
 		strlcat(msgbuf, "preemption imbalance ", sizeof(msgbuf));
@@ -742,7 +746,7 @@ int do_one_initcall(initcall_t fn)
 		printk("initcall %pF returned with %s\n", fn, msgbuf);
 	}
 
-	return result;
+	return it.result;
 }
 
 
@@ -857,6 +861,7 @@ static int __init kernel_init(void * unused)
 	smp_prepare_cpus(setup_max_cpus);
 
 	do_pre_smp_initcalls();
+	start_boot_trace();
 
 	smp_init();
 	sched_init_smp();
@@ -883,6 +888,7 @@ static int __init kernel_init(void * unused)
 	 * we're essentially up and running. Get rid of the
 	 * initmem segments and start the user-mode stuff..
 	 */
+	stop_boot_trace();
 	init_post();
 	return 0;
 }

kernel/Makefile

@@ -85,6 +85,7 @@ obj-$(CONFIG_SYSCTL) += utsname_sysctl.o
 obj-$(CONFIG_TASK_DELAY_ACCT) += delayacct.o
 obj-$(CONFIG_TASKSTATS) += taskstats.o tsacct.o
 obj-$(CONFIG_MARKERS) += marker.o
+obj-$(CONFIG_TRACEPOINTS) += tracepoint.o
 obj-$(CONFIG_LATENCYTOP) += latencytop.o
 obj-$(CONFIG_HAVE_GENERIC_DMA_COHERENT) += dma-coherent.o
 obj-$(CONFIG_FTRACE) += trace/

kernel/exit.c

@@ -47,6 +47,7 @@
 #include <linux/blkdev.h>
 #include <linux/task_io_accounting_ops.h>
 #include <linux/tracehook.h>
+#include <trace/sched.h>
 
 #include <asm/uaccess.h>
 #include <asm/unistd.h>
@@ -146,7 +147,10 @@ static void __exit_signal(struct task_struct *tsk)
 
 static void delayed_put_task_struct(struct rcu_head *rhp)
 {
-	put_task_struct(container_of(rhp, struct task_struct, rcu));
+	struct task_struct *tsk = container_of(rhp, struct task_struct, rcu);
+
+	trace_sched_process_free(tsk);
+	put_task_struct(tsk);
 }
 
 
@@ -1070,6 +1074,8 @@ NORET_TYPE void do_exit(long code)
 
 	if (group_dead)
 		acct_process();
+	trace_sched_process_exit(tsk);
+
 	exit_sem(tsk);
 	exit_files(tsk);
 	exit_fs(tsk);
@@ -1675,6 +1681,8 @@ static long do_wait(enum pid_type type, struct pid *pid, int options,
 	struct task_struct *tsk;
 	int retval;
 
+	trace_sched_process_wait(pid);
+
 	add_wait_queue(&current->signal->wait_chldexit,&wait);
 repeat:
 	/*

kernel/fork.c

@@ -58,6 +58,7 @@
 #include <linux/tty.h>
 #include <linux/proc_fs.h>
 #include <linux/blkdev.h>
+#include <trace/sched.h>
 
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>
@@ -1372,6 +1373,8 @@ long do_fork(unsigned long clone_flags,
 	if (!IS_ERR(p)) {
 		struct completion vfork;
 
+		trace_sched_process_fork(current, p);
+
 		nr = task_pid_vnr(p);
 
 		if (clone_flags & CLONE_PARENT_SETTID)

kernel/kthread.c

@@ -13,6 +13,7 @@
 #include <linux/file.h>
 #include <linux/module.h>
 #include <linux/mutex.h>
+#include <trace/sched.h>
 
 #define KTHREAD_NICE_LEVEL (-5)
 
@@ -205,6 +206,8 @@ int kthread_stop(struct task_struct *k)
 	/* It could exit after stop_info.k set, but before wake_up_process. */
 	get_task_struct(k);
 
+	trace_sched_kthread_stop(k);
+
 	/* Must init completion *before* thread sees kthread_stop_info.k */
 	init_completion(&kthread_stop_info.done);
 	smp_wmb();
@@ -220,6 +223,8 @@ int kthread_stop(struct task_struct *k)
 	ret = kthread_stop_info.err;
 	mutex_unlock(&kthread_stop_lock);
 
+	trace_sched_kthread_stop_ret(ret);
+
 	return ret;
 }
 EXPORT_SYMBOL(kthread_stop);

kernel/marker.c

@@ -62,7 +62,7 @@ struct marker_entry {
 	int refcount;	/* Number of times armed. 0 if disarmed. */
 	struct rcu_head rcu;
 	void *oldptr;
-	unsigned char rcu_pending:1;
+	int rcu_pending;
 	unsigned char ptype:1;
 	char name[0];	/* Contains name'\0'format'\0' */
 };
@@ -103,11 +103,11 @@ void marker_probe_cb(const struct marker *mdata, void *call_private, ...)
 	char ptype;
 
 	/*
-	 * preempt_disable does two things : disabling preemption to make sure
-	 * the teardown of the callbacks can be done correctly when they are in
-	 * modules and they insure RCU read coherency.
+	 * rcu_read_lock_sched does two things : disabling preemption to make
+	 * sure the teardown of the callbacks can be done correctly when they
+	 * are in modules and they insure RCU read coherency.
 	 */
-	preempt_disable();
+	rcu_read_lock_sched();
 	ptype = mdata->ptype;
 	if (likely(!ptype)) {
 		marker_probe_func *func;
@@ -145,7 +145,7 @@ void marker_probe_cb(const struct marker *mdata, void *call_private, ...)
 			va_end(args);
 		}
 	}
-	preempt_enable();
+	rcu_read_unlock_sched();
 }
 EXPORT_SYMBOL_GPL(marker_probe_cb);
 
@@ -162,7 +162,7 @@ void marker_probe_cb_noarg(const struct marker *mdata, void *call_private, ...)
 	va_list args;	/* not initialized */
 	char ptype;
 
-	preempt_disable();
+	rcu_read_lock_sched();
 	ptype = mdata->ptype;
 	if (likely(!ptype)) {
 		marker_probe_func *func;
@@ -195,7 +195,7 @@ void marker_probe_cb_noarg(const struct marker *mdata, void *call_private, ...)
 			multi[i].func(multi[i].probe_private, call_private,
 				mdata->format, &args);
 	}
-	preempt_enable();
+	rcu_read_unlock_sched();
 }
 EXPORT_SYMBOL_GPL(marker_probe_cb_noarg);
 
@@ -560,7 +560,7 @@ static int set_marker(struct marker_entry **entry, struct marker *elem,
  * Disable a marker and its probe callback.
  * Note: only waiting an RCU period after setting elem->call to the empty
  * function insures that the original callback is not used anymore. This insured
- * by preempt_disable around the call site.
+ * by rcu_read_lock_sched around the call site.
  */
 static void disable_marker(struct marker *elem)
 {
@@ -653,11 +653,17 @@ int marker_probe_register(const char *name, const char *format,
 	entry = get_marker(name);
 	if (!entry) {
 		entry = add_marker(name, format);
-		if (IS_ERR(entry)) {
+		if (IS_ERR(entry))
 			ret = PTR_ERR(entry);
-			goto end;
-		}
+	} else if (format) {
+		if (!entry->format)
+			ret = marker_set_format(&entry, format);
+		else if (strcmp(entry->format, format))
+			ret = -EPERM;
 	}
+	if (ret)
+		goto end;
+
 	/*
 	 * If we detect that a call_rcu is pending for this marker,
 	 * make sure it's executed now.
@@ -674,6 +680,8 @@ int marker_probe_register(const char *name, const char *format,
 	mutex_lock(&markers_mutex);
 	entry = get_marker(name);
 	WARN_ON(!entry);
+	if (entry->rcu_pending)
+		rcu_barrier_sched();
 	entry->oldptr = old;
 	entry->rcu_pending = 1;
 	/* write rcu_pending before calling the RCU callback */
@@ -717,6 +725,8 @@ int marker_probe_unregister(const char *name,
 	entry = get_marker(name);
 	if (!entry)
 		goto end;
+	if (entry->rcu_pending)
+		rcu_barrier_sched();
 	entry->oldptr = old;
 	entry->rcu_pending = 1;
 	/* write rcu_pending before calling the RCU callback */
@@ -795,6 +805,8 @@ int marker_probe_unregister_private_data(marker_probe_func *probe,
 	mutex_lock(&markers_mutex);
 	entry = get_marker_from_private_data(probe, probe_private);
 	WARN_ON(!entry);
+	if (entry->rcu_pending)
+		rcu_barrier_sched();
 	entry->oldptr = old;
 	entry->rcu_pending = 1;
 	/* write rcu_pending before calling the RCU callback */

kernel/module.c

@@ -46,6 +46,8 @@
 #include <asm/cacheflush.h>
 #include <linux/license.h>
 #include <asm/sections.h>
+#include <linux/tracepoint.h>
+#include <linux/ftrace.h>
 
 #if 0
 #define DEBUGP printk
@@ -1430,6 +1432,9 @@ static void free_module(struct module *mod)
 	/* Module unload stuff */
 	module_unload_free(mod);
 
+	/* release any pointers to mcount in this module */
+	ftrace_release(mod->module_core, mod->core_size);
+
 	/* This may be NULL, but that's OK */
 	module_free(mod, mod->module_init);
 	kfree(mod->args);
@@ -1861,9 +1866,13 @@ static noinline struct module *load_module(void __user *umod,
 	unsigned int markersindex;
 	unsigned int markersstringsindex;
 	unsigned int verboseindex;
+	unsigned int tracepointsindex;
+	unsigned int tracepointsstringsindex;
+	unsigned int mcountindex;
 	struct module *mod;
 	long err = 0;
 	void *percpu = NULL, *ptr = NULL; /* Stops spurious gcc warning */
+	void *mseg;
 	struct exception_table_entry *extable;
 	mm_segment_t old_fs;
 
@@ -2156,6 +2165,12 @@ static noinline struct module *load_module(void __user *umod,
  	markersstringsindex = find_sec(hdr, sechdrs, secstrings,
 					"__markers_strings");
 	verboseindex = find_sec(hdr, sechdrs, secstrings, "__verbose");
+	tracepointsindex = find_sec(hdr, sechdrs, secstrings, "__tracepoints");
+	tracepointsstringsindex = find_sec(hdr, sechdrs, secstrings,
+					"__tracepoints_strings");
+
+	mcountindex = find_sec(hdr, sechdrs, secstrings,
+			       "__mcount_loc");
 
 	/* Now do relocations. */
 	for (i = 1; i < hdr->e_shnum; i++) {
@@ -2183,6 +2198,12 @@ static noinline struct module *load_module(void __user *umod,
 	mod->num_markers =
 		sechdrs[markersindex].sh_size / sizeof(*mod->markers);
 #endif
+#ifdef CONFIG_TRACEPOINTS
+	mod->tracepoints = (void *)sechdrs[tracepointsindex].sh_addr;
+	mod->num_tracepoints =
+		sechdrs[tracepointsindex].sh_size / sizeof(*mod->tracepoints);
+#endif
+
 
         /* Find duplicate symbols */
 	err = verify_export_symbols(mod);
@@ -2201,12 +2222,22 @@ static noinline struct module *load_module(void __user *umod,
 
 	add_kallsyms(mod, sechdrs, symindex, strindex, secstrings);
 
+	if (!mod->taints) {
 #ifdef CONFIG_MARKERS
-	if (!mod->taints)
 		marker_update_probe_range(mod->markers,
 			mod->markers + mod->num_markers);
 #endif
 	dynamic_printk_setup(sechdrs, verboseindex);
+#ifdef CONFIG_TRACEPOINTS
+		tracepoint_update_probe_range(mod->tracepoints,
+			mod->tracepoints + mod->num_tracepoints);
+#endif
+	}
+
+	/* sechdrs[0].sh_size is always zero */
+	mseg = (void *)sechdrs[mcountindex].sh_addr;
+	ftrace_init_module(mseg, mseg + sechdrs[mcountindex].sh_size);
+
 	err = module_finalize(hdr, sechdrs, mod);
 	if (err < 0)
 		goto cleanup;
@@ -2276,6 +2307,7 @@ static noinline struct module *load_module(void __user *umod,
  cleanup:
 	kobject_del(&mod->mkobj.kobj);
 	kobject_put(&mod->mkobj.kobj);
+	ftrace_release(mod->module_core, mod->core_size);
  free_unload:
 	module_unload_free(mod);
 	module_free(mod, mod->module_init);
@@ -2759,3 +2791,50 @@ void module_update_markers(void)
 	mutex_unlock(&module_mutex);
 }
 #endif
+
+#ifdef CONFIG_TRACEPOINTS
+void module_update_tracepoints(void)
+{
+	struct module *mod;
+
+	mutex_lock(&module_mutex);
+	list_for_each_entry(mod, &modules, list)
+		if (!mod->taints)
+			tracepoint_update_probe_range(mod->tracepoints,
+				mod->tracepoints + mod->num_tracepoints);
+	mutex_unlock(&module_mutex);
+}
+
+/*
+ * Returns 0 if current not found.
+ * Returns 1 if current found.
+ */
+int module_get_iter_tracepoints(struct tracepoint_iter *iter)
+{
+	struct module *iter_mod;
+	int found = 0;
+
+	mutex_lock(&module_mutex);
+	list_for_each_entry(iter_mod, &modules, list) {
+		if (!iter_mod->taints) {
+			/*
+			 * Sorted module list
+			 */
+			if (iter_mod < iter->module)
+				continue;
+			else if (iter_mod > iter->module)
+				iter->tracepoint = NULL;
+			found = tracepoint_get_iter_range(&iter->tracepoint,
+				iter_mod->tracepoints,
+				iter_mod->tracepoints
+					+ iter_mod->num_tracepoints);
+			if (found) {
+				iter->module = iter_mod;
+				break;
+			}
+		}
+	}
+	mutex_unlock(&module_mutex);
+	return found;
+}
+#endif

kernel/notifier.c

@@ -550,7 +550,7 @@ EXPORT_SYMBOL(unregister_reboot_notifier);
 
 static ATOMIC_NOTIFIER_HEAD(die_chain);
 
-int notify_die(enum die_val val, const char *str,
+int notrace notify_die(enum die_val val, const char *str,
 	       struct pt_regs *regs, long err, int trap, int sig)
 {
 	struct die_args args = {

kernel/sched.c

@@ -71,6 +71,7 @@
 #include <linux/debugfs.h>
 #include <linux/ctype.h>
 #include <linux/ftrace.h>
+#include <trace/sched.h>
 
 #include <asm/tlb.h>
 #include <asm/irq_regs.h>
@@ -1936,6 +1937,7 @@ unsigned long wait_task_inactive(struct task_struct *p, long match_state)
 		 * just go back and repeat.
 		 */
 		rq = task_rq_lock(p, &flags);
+		trace_sched_wait_task(rq, p);
 		running = task_running(rq, p);
 		on_rq = p->se.on_rq;
 		ncsw = 0;
@@ -2297,9 +2299,7 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state, int sync)
 	success = 1;
 
 out_running:
-	trace_mark(kernel_sched_wakeup,
-		"pid %d state %ld ## rq %p task %p rq->curr %p",
-		p->pid, p->state, rq, p, rq->curr);
+	trace_sched_wakeup(rq, p);
 	check_preempt_curr(rq, p, sync);
 
 	p->state = TASK_RUNNING;
@@ -2432,9 +2432,7 @@ void wake_up_new_task(struct task_struct *p, unsigned long clone_flags)
 		p->sched_class->task_new(rq, p);
 		inc_nr_running(rq);
 	}
-	trace_mark(kernel_sched_wakeup_new,
-		"pid %d state %ld ## rq %p task %p rq->curr %p",
-		p->pid, p->state, rq, p, rq->curr);
+	trace_sched_wakeup_new(rq, p);
 	check_preempt_curr(rq, p, 0);
 #ifdef CONFIG_SMP
 	if (p->sched_class->task_wake_up)
@@ -2607,11 +2605,7 @@ context_switch(struct rq *rq, struct task_struct *prev,
 	struct mm_struct *mm, *oldmm;
 
 	prepare_task_switch(rq, prev, next);
-	trace_mark(kernel_sched_schedule,
-		"prev_pid %d next_pid %d prev_state %ld "
-		"## rq %p prev %p next %p",
-		prev->pid, next->pid, prev->state,
-		rq, prev, next);
+	trace_sched_switch(rq, prev, next);
 	mm = next->mm;
 	oldmm = prev->active_mm;
 	/*
@@ -2851,6 +2845,7 @@ static void sched_migrate_task(struct task_struct *p, int dest_cpu)
 	    || unlikely(!cpu_active(dest_cpu)))
 		goto out;
 
+	trace_sched_migrate_task(rq, p, dest_cpu);
 	/* force the process onto the specified CPU */
 	if (migrate_task(p, dest_cpu, &req)) {
 		/* Need to wait for migration thread (might exit: take ref). */

kernel/signal.c

@@ -27,6 +27,7 @@
 #include <linux/freezer.h>
 #include <linux/pid_namespace.h>
 #include <linux/nsproxy.h>
+#include <trace/sched.h>
 
 #include <asm/param.h>
 #include <asm/uaccess.h>
@@ -803,6 +804,8 @@ static int send_signal(int sig, struct siginfo *info, struct task_struct *t,
 	struct sigpending *pending;
 	struct sigqueue *q;
 
+	trace_sched_signal_send(sig, t);
+
 	assert_spin_locked(&t->sighand->siglock);
 	if (!prepare_signal(sig, t))
 		return 0;

kernel/trace/Kconfig

 #
 # Architectures that offer an FTRACE implementation should select HAVE_FTRACE:
 #
+
+config NOP_TRACER
+	bool
+
 config HAVE_FTRACE
 	bool
+	select NOP_TRACER
 
 config HAVE_DYNAMIC_FTRACE
 	bool
 
+config HAVE_FTRACE_MCOUNT_RECORD
+	bool
+
 config TRACER_MAX_TRACE
 	bool
 
+config RING_BUFFER
+	bool
+
 config TRACING
 	bool
 	select DEBUG_FS
+	select RING_BUFFER
 	select STACKTRACE
+	select TRACEPOINTS
 
 config FTRACE
 	bool "Kernel Function Tracer"
 	depends on HAVE_FTRACE
+	depends on DEBUG_KERNEL
 	select FRAME_POINTER
 	select TRACING
 	select CONTEXT_SWITCH_TRACER
@@ -36,6 +50,7 @@ config IRQSOFF_TRACER
 	depends on TRACE_IRQFLAGS_SUPPORT
 	depends on GENERIC_TIME
 	depends on HAVE_FTRACE
+	depends on DEBUG_KERNEL
 	select TRACE_IRQFLAGS
 	select TRACING
 	select TRACER_MAX_TRACE
@@ -59,6 +74,7 @@ config PREEMPT_TRACER
 	depends on GENERIC_TIME
 	depends on PREEMPT
 	depends on HAVE_FTRACE
+	depends on DEBUG_KERNEL
 	select TRACING
 	select TRACER_MAX_TRACE
 	help
@@ -86,6 +102,7 @@ config SYSPROF_TRACER
 config SCHED_TRACER
 	bool "Scheduling Latency Tracer"
 	depends on HAVE_FTRACE
+	depends on DEBUG_KERNEL
 	select TRACING
 	select CONTEXT_SWITCH_TRACER
 	select TRACER_MAX_TRACE
@@ -96,16 +113,56 @@ config SCHED_TRACER
 config CONTEXT_SWITCH_TRACER
 	bool "Trace process context switches"
 	depends on HAVE_FTRACE
+	depends on DEBUG_KERNEL
 	select TRACING
 	select MARKERS
 	help
 	  This tracer gets called from the context switch and records
 	  all switching of tasks.
 
+config BOOT_TRACER
+	bool "Trace boot initcalls"
+	depends on HAVE_FTRACE
+	depends on DEBUG_KERNEL
+	select TRACING
+	help
+	  This tracer helps developers to optimize boot times: it records
+	  the timings of the initcalls and traces key events and the identity
+	  of tasks that can cause boot delays, such as context-switches.
+
+	  Its aim is to be parsed by the /scripts/bootgraph.pl tool to
+	  produce pretty graphics about boot inefficiencies, giving a visual
+	  representation of the delays during initcalls - but the raw
+	  /debug/tracing/trace text output is readable too.
+
+	  ( Note that tracing self tests can't be enabled if this tracer is
+	    selected, because the self-tests are an initcall as well and that
+	    would invalidate the boot trace. )
+
+config STACK_TRACER
+	bool "Trace max stack"
+	depends on HAVE_FTRACE
+	depends on DEBUG_KERNEL
+	select FTRACE
+	select STACKTRACE
+	help
+	  This special tracer records the maximum stack footprint of the
+	  kernel and displays it in debugfs/tracing/stack_trace.
+
+	  This tracer works by hooking into every function call that the
+	  kernel executes, and keeping a maximum stack depth value and
+	  stack-trace saved. Because this logic has to execute in every
+	  kernel function, all the time, this option can slow down the
+	  kernel measurably and is generally intended for kernel
+	  developers only.
+
+	  Say N if unsure.
+
 config DYNAMIC_FTRACE
 	bool "enable/disable ftrace tracepoints dynamically"
 	depends on FTRACE
 	depends on HAVE_DYNAMIC_FTRACE
+	depends on DEBUG_KERNEL
 	default y
 	help
          This option will modify all the calls to ftrace dynamically
@@ -121,12 +178,17 @@ config DYNAMIC_FTRACE
 	 were made. If so, it runs stop_machine (stops all CPUS)
 	 and modifies the code to jump over the call to ftrace.
 
+config FTRACE_MCOUNT_RECORD
+	def_bool y
+	depends on DYNAMIC_FTRACE
+	depends on HAVE_FTRACE_MCOUNT_RECORD
+
 config FTRACE_SELFTEST
 	bool
 
 config FTRACE_STARTUP_TEST
 	bool "Perform a startup test on ftrace"
-	depends on TRACING
+	depends on TRACING && DEBUG_KERNEL && !BOOT_TRACER
 	select FTRACE_SELFTEST
 	help
 	  This option performs a series of startup tests on ftrace. On bootup

kernel/trace/Makefile

@@ -11,6 +11,7 @@ obj-y += trace_selftest_dynamic.o
 endif
 
 obj-$(CONFIG_FTRACE) += libftrace.o
+obj-$(CONFIG_RING_BUFFER) += ring_buffer.o
 
 obj-$(CONFIG_TRACING) += trace.o
 obj-$(CONFIG_CONTEXT_SWITCH_TRACER) += trace_sched_switch.o
@@ -19,6 +20,9 @@ obj-$(CONFIG_FTRACE) += trace_functions.o
 obj-$(CONFIG_IRQSOFF_TRACER) += trace_irqsoff.o
 obj-$(CONFIG_PREEMPT_TRACER) += trace_irqsoff.o
 obj-$(CONFIG_SCHED_TRACER) += trace_sched_wakeup.o
+obj-$(CONFIG_NOP_TRACER) += trace_nop.o
+obj-$(CONFIG_STACK_TRACER) += trace_stack.o
 obj-$(CONFIG_MMIOTRACE) += trace_mmiotrace.o
+obj-$(CONFIG_BOOT_TRACER) += trace_boot.o
 
 libftrace-y := ftrace.o

kernel/trace/trace_functions.c

@@ -23,7 +23,7 @@ static void function_reset(struct trace_array *tr)
 	tr->time_start = ftrace_now(tr->cpu);
 
 	for_each_online_cpu(cpu)
-		tracing_reset(tr->data[cpu]);
+		tracing_reset(tr, cpu);
 }
 
 static void start_function_trace(struct trace_array *tr)

kernel/trace/trace_irqsoff.c

@@ -95,7 +95,7 @@ irqsoff_tracer_call(unsigned long ip, unsigned long parent_ip)
 	disabled = atomic_inc_return(&data->disabled);
 
 	if (likely(disabled == 1))
-		trace_function(tr, data, ip, parent_ip, flags);
+		trace_function(tr, data, ip, parent_ip, flags, preempt_count());
 
 	atomic_dec(&data->disabled);
 }
@@ -130,6 +130,7 @@ check_critical_timing(struct trace_array *tr,
 	unsigned long latency, t0, t1;
 	cycle_t T0, T1, delta;
 	unsigned long flags;
+	int pc;
 
 	/*
 	 * usecs conversion is slow so we try to delay the conversion
@@ -141,6 +142,8 @@ check_critical_timing(struct trace_array *tr,
 
 	local_save_flags(flags);
 
+	pc = preempt_count();
+
 	if (!report_latency(delta))
 		goto out;
 
@@ -150,7 +153,7 @@ check_critical_timing(struct trace_array *tr,
 	if (!report_latency(delta))
 		goto out_unlock;
 
-	trace_function(tr, data, CALLER_ADDR0, parent_ip, flags);
+	trace_function(tr, data, CALLER_ADDR0, parent_ip, flags, pc);
 
 	latency = nsecs_to_usecs(delta);
 
@@ -173,8 +176,8 @@ check_critical_timing(struct trace_array *tr,
 out:
 	data->critical_sequence = max_sequence;
 	data->preempt_timestamp = ftrace_now(cpu);
-	tracing_reset(data);
-	trace_function(tr, data, CALLER_ADDR0, parent_ip, flags);
+	tracing_reset(tr, cpu);
+	trace_function(tr, data, CALLER_ADDR0, parent_ip, flags, pc);
 }
 
 static inline void
@@ -203,11 +206,11 @@ start_critical_timing(unsigned long ip, unsigned long parent_ip)
 	data->critical_sequence = max_sequence;
 	data->preempt_timestamp = ftrace_now(cpu);
 	data->critical_start = parent_ip ? : ip;
-	tracing_reset(data);
+	tracing_reset(tr, cpu);
 
 	local_save_flags(flags);
 
-	trace_function(tr, data, ip, parent_ip, flags);
+	trace_function(tr, data, ip, parent_ip, flags, preempt_count());
 
 	per_cpu(tracing_cpu, cpu) = 1;
 
@@ -234,14 +237,14 @@ stop_critical_timing(unsigned long ip, unsigned long parent_ip)
 
 	data = tr->data[cpu];
 
-	if (unlikely(!data) || unlikely(!head_page(data)) ||
+	if (unlikely(!data) ||
 	    !data->critical_start || atomic_read(&data->disabled))
 		return;
 
 	atomic_inc(&data->disabled);
 
 	local_save_flags(flags);
-	trace_function(tr, data, ip, parent_ip, flags);
+	trace_function(tr, data, ip, parent_ip, flags, preempt_count());
 	check_critical_timing(tr, data, parent_ip ? : ip, cpu);
 	data->critical_start = 0;
 	atomic_dec(&data->disabled);

kernel/trace/trace_sysprof.c

@@ -241,7 +241,7 @@ static void stack_reset(struct trace_array *tr)
 	tr->time_start = ftrace_now(tr->cpu);
 
 	for_each_online_cpu(cpu)
-		tracing_reset(tr->data[cpu]);
+		tracing_reset(tr, cpu);
 }
 
 static void start_stack_trace(struct trace_array *tr)

samples/Kconfig

@@ -13,6 +13,12 @@ config SAMPLE_MARKERS
 	help
 	  This build markers example modules.
 
+config SAMPLE_TRACEPOINTS
+	tristate "Build tracepoints examples -- loadable modules only"
+	depends on TRACEPOINTS && m
+	help
+	  This build tracepoints example modules.
+
 config SAMPLE_KOBJECT
 	tristate "Build kobject examples"
 	help

samples/Makefile

 # Makefile for Linux samples code
 
-obj-$(CONFIG_SAMPLES)	+= markers/ kobject/ kprobes/
+obj-$(CONFIG_SAMPLES)	+= markers/ kobject/ kprobes/ tracepoints/

samples/markers/probe-example.c

@@ -81,6 +81,7 @@ static void __exit probe_fini(void)
 			probe_array[i].probe_func, &probe_array[i]);
 	printk(KERN_INFO "Number of event b : %u\n",
 			atomic_read(&eventb_count));
+	marker_synchronize_unregister();
 }
 
 module_init(probe_init);