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.

65 files changed, 6108 insertions, 1585 deletions

diff --git a/Documentation/markers.txt b/Documentation/markers.txt
index d9f50a19fa0..089f6138fcd 100644
--- a/Documentation/markers.txt
+++ b/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
diff --git a/Documentation/tracepoints.txt b/Documentation/tracepoints.txt
new file mode 100644
index 00000000000..5d354e16749
--- /dev/null
+++ b/Documentation/tracepoints.txt
@@ -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
diff --git a/Documentation/tracers/mmiotrace.txt b/Documentation/tracers/mmiotrace.txt
index a4afb560a45..5bbbe209622 100644
--- a/Documentation/tracers/mmiotrace.txt
+++ b/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.
diff --git a/arch/powerpc/platforms/cell/spufs/sputrace.c b/arch/powerpc/platforms/cell/spufs/sputrace.c
index 92d20e993ed..2ece399f286 100644
--- a/arch/powerpc/platforms/cell/spufs/sputrace.c
+++ b/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);
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 73966896839..5b9b12321ad 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -26,6 +26,7 @@ config X86
 	select HAVE_KPROBES
 	select ARCH_WANT_OPTIONAL_GPIOLIB
 	select HAVE_KRETPROBES
+	select HAVE_FTRACE_MCOUNT_RECORD
 	select HAVE_DYNAMIC_FTRACE
 	select HAVE_FTRACE
 	select HAVE_KVM if ((X86_32 && !X86_VOYAGER && !X86_VISWS && !X86_NUMAQ) || X86_64)
diff --git a/arch/x86/kernel/cpu/perfctr-watchdog.c b/arch/x86/kernel/cpu/perfctr-watchdog.c
index 6bff382094f..9abd48b2267 100644
--- a/arch/x86/kernel/cpu/perfctr-watchdog.c
+++ b/arch/x86/kernel/cpu/perfctr-watchdog.c
@@ -17,6 +17,8 @@
 #include <linux/bitops.h>
 #include <linux/smp.h>
 #include <linux/nmi.h>
+#include <linux/kprobes.h>
+
 #include <asm/apic.h>
 #include <asm/intel_arch_perfmon.h>
 
@@ -336,7 +338,8 @@ static void single_msr_unreserve(void)
 	release_perfctr_nmi(wd_ops->perfctr);
 }
 
-static void single_msr_rearm(struct nmi_watchdog_ctlblk *wd, unsigned nmi_hz)
+static void __kprobes
+single_msr_rearm(struct nmi_watchdog_ctlblk *wd, unsigned nmi_hz)
 {
 	/* start the cycle over again */
 	write_watchdog_counter(wd->perfctr_msr, NULL, nmi_hz);
@@ -401,7 +404,7 @@ static int setup_p6_watchdog(unsigned nmi_hz)
 	return 1;
 }
 
-static void p6_rearm(struct nmi_watchdog_ctlblk *wd, unsigned nmi_hz)
+static void __kprobes p6_rearm(struct nmi_watchdog_ctlblk *wd, unsigned nmi_hz)
 {
 	/*
 	 * P6 based Pentium M need to re-unmask
@@ -605,7 +608,7 @@ static void p4_unreserve(void)
 	release_perfctr_nmi(MSR_P4_IQ_PERFCTR0);
 }
 
-static void p4_rearm(struct nmi_watchdog_ctlblk *wd, unsigned nmi_hz)
+static void __kprobes p4_rearm(struct nmi_watchdog_ctlblk *wd, unsigned nmi_hz)
 {
 	unsigned dummy;
 	/*
@@ -784,7 +787,7 @@ unsigned lapic_adjust_nmi_hz(unsigned hz)
 	return hz;
 }
 
-int lapic_wd_event(unsigned nmi_hz)
+int __kprobes lapic_wd_event(unsigned nmi_hz)
 {
 	struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk);
 	u64 ctr;
diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S
index 4d82171d0f9..c356423a602 100644
--- a/arch/x86/kernel/entry_32.S
+++ b/arch/x86/kernel/entry_32.S
@@ -1153,20 +1153,6 @@ ENDPROC(xen_failsafe_callback)
 #ifdef CONFIG_DYNAMIC_FTRACE
 
 ENTRY(mcount)
-	pushl %eax
-	pushl %ecx
-	pushl %edx
-	movl 0xc(%esp), %eax
-	subl $MCOUNT_INSN_SIZE, %eax
-
-.globl mcount_call
-mcount_call:
-	call ftrace_stub
-
-	popl %edx
-	popl %ecx
-	popl %eax
-
 	ret
 END(mcount)
 
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index 1db6ce4314e..09e7145484c 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -64,32 +64,6 @@
 #ifdef CONFIG_FTRACE
 #ifdef CONFIG_DYNAMIC_FTRACE
 ENTRY(mcount)
-
-	subq $0x38, %rsp
-	movq %rax, (%rsp)
-	movq %rcx, 8(%rsp)
-	movq %rdx, 16(%rsp)
-	movq %rsi, 24(%rsp)
-	movq %rdi, 32(%rsp)
-	movq %r8, 40(%rsp)
-	movq %r9, 48(%rsp)
-
-	movq 0x38(%rsp), %rdi
-	subq $MCOUNT_INSN_SIZE, %rdi
-
-.globl mcount_call
-mcount_call:
-	call ftrace_stub
-
-	movq 48(%rsp), %r9
-	movq 40(%rsp), %r8
-	movq 32(%rsp), %rdi
-	movq 24(%rsp), %rsi
-	movq 16(%rsp), %rdx
-	movq 8(%rsp), %rcx
-	movq (%rsp), %rax
-	addq $0x38, %rsp
-
 	retq
 END(mcount)
 
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index ab115cd15fd..d073d981a73 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -11,17 +11,18 @@
 
 #include <linux/spinlock.h>
 #include <linux/hardirq.h>
+#include <linux/uaccess.h>
 #include <linux/ftrace.h>
 #include <linux/percpu.h>
 #include <linux/init.h>
 #include <linux/list.h>
 
-#include <asm/alternative.h>
 #include <asm/ftrace.h>
+#include <asm/nops.h>
 
 
 /* Long is fine, even if it is only 4 bytes ;-) */
-static long *ftrace_nop;
+static unsigned long *ftrace_nop;
 
 union ftrace_code_union {
 	char code[MCOUNT_INSN_SIZE];
@@ -60,11 +61,7 @@ notrace int
 ftrace_modify_code(unsigned long ip, unsigned char *old_code,
 		   unsigned char *new_code)
 {
-	unsigned replaced;
-	unsigned old = *(unsigned *)old_code; /* 4 bytes */
-	unsigned new = *(unsigned *)new_code; /* 4 bytes */
-	unsigned char newch = new_code[4];
-	int faulted = 0;
+	unsigned char replaced[MCOUNT_INSN_SIZE];
 
 	/*
 	 * Note: Due to modules and __init, code can
@@ -72,29 +69,20 @@ ftrace_modify_code(unsigned long ip, unsigned char *old_code,
 	 *  as well as code changing.
 	 *
 	 * No real locking needed, this code is run through
-	 * kstop_machine.
+	 * kstop_machine, or before SMP starts.
 	 */
-	asm volatile (
-		"1: lock\n"
-		"   cmpxchg %3, (%2)\n"
-		"   jnz 2f\n"
-		"   movb %b4, 4(%2)\n"
-		"2:\n"
-		".section .fixup, \"ax\"\n"
-		"3:	movl $1, %0\n"
-		"	jmp 2b\n"
-		".previous\n"
-		_ASM_EXTABLE(1b, 3b)
-		: "=r"(faulted), "=a"(replaced)
-		: "r"(ip), "r"(new), "c"(newch),
-		  "0"(faulted), "a"(old)
-		: "memory");
-	sync_core();
+	if (__copy_from_user_inatomic(replaced, (char __user *)ip, MCOUNT_INSN_SIZE))
+		return 1;
+
+	if (memcmp(replaced, old_code, MCOUNT_INSN_SIZE) != 0)
+		return 2;
 
-	if (replaced != old && replaced != new)
-		faulted = 2;
+	WARN_ON_ONCE(__copy_to_user_inatomic((char __user *)ip, new_code,
+				    MCOUNT_INSN_SIZE));
 
-	return faulted;
+	sync_core();
+
+	return 0;
 }
 
 notrace int ftrace_update_ftrace_func(ftrace_func_t func)
@@ -112,30 +100,76 @@ notrace int ftrace_update_ftrace_func(ftrace_func_t func)
 
 notrace int ftrace_mcount_set(unsigned long *data)
 {
-	unsigned long ip = (long)(&mcount_call);
-	unsigned long *addr = data;
-	unsigned char old[MCOUNT_INSN_SIZE], *new;
-
-	/*
-	 * Replace the mcount stub with a pointer to the
-	 * ip recorder function.
-	 */
-	memcpy(old, &mcount_call, MCOUNT_INSN_SIZE);
-	new = ftrace_call_replace(ip, *addr);
-	*addr = ftrace_modify_code(ip, old, new);
-
+	/* mcount is initialized as a nop */
+	*data = 0;
 	return 0;
 }
 
 int __init ftrace_dyn_arch_init(void *data)
 {
-	const unsigned char *const *noptable = find_nop_table();
-
-	/* This is running in kstop_machine */
-
-	ftrace_mcount_set(data);
+	extern const unsigned char ftrace_test_p6nop[];
+	extern const unsigned char ftrace_test_nop5[];
+	extern const unsigned char ftrace_test_jmp[];
+	int faulted = 0;
 
-	ftrace_nop = (unsigned long *)noptable[MCOUNT_INSN_SIZE];
+	/*
+	 * There is no good nop for all x86 archs.
+	 * We will default to using the P6_NOP5, but first we
+	 * will test to make sure that the nop will actually
+	 * work on this CPU. If it faults, we will then
+	 * go to a lesser efficient 5 byte nop. If that fails
+	 * we then just use a jmp as our nop. This isn't the most
+	 * efficient nop, but we can not use a multi part nop
+	 * since we would then risk being preempted in the middle
+	 * of that nop, and if we enabled tracing then, it might
+	 * cause a system crash.
+	 *
+	 * TODO: check the cpuid to determine the best nop.
+	 */
+	asm volatile (
+		"jmp ftrace_test_jmp\n"
+		/* This code needs to stay around */
+		".section .text, \"ax\"\n"
+		"ftrace_test_jmp:"
+		"jmp ftrace_test_p6nop\n"
+		"nop\n"
+		"nop\n"
+		"nop\n"  /* 2 byte jmp + 3 bytes */
+		"ftrace_test_p6nop:"
+		P6_NOP5
+		"jmp 1f\n"
+		"ftrace_test_nop5:"
+		".byte 0x66,0x66,0x66,0x66,0x90\n"
+		"jmp 1f\n"
+		".previous\n"
+		"1:"
+		".section .fixup, \"ax\"\n"
+		"2:	movl $1, %0\n"
+		"	jmp ftrace_test_nop5\n"
+		"3:	movl $2, %0\n"
+		"	jmp 1b\n"
+		".previous\n"
+		_ASM_EXTABLE(ftrace_test_p6nop, 2b)
+		_ASM_EXTABLE(ftrace_test_nop5, 3b)
+		: "=r"(faulted) : "0" (faulted));
+
+	switch (faulted) {
+	case 0:
+		pr_info("ftrace: converting mcount calls to 0f 1f 44 00 00\n");
+		ftrace_nop = (unsigned long *)ftrace_test_p6nop;
+		break;
+	case 1:
+		pr_info("ftrace: converting mcount calls to 66 66 66 66 90\n");
+		ftrace_nop = (unsigned long *)ftrace_test_nop5;
+		break;
+	case 2:
+		pr_info("ftrace: converting mcount calls to jmp . + 5\n");
+		ftrace_nop = (unsigned long *)ftrace_test_jmp;
+		break;
+	}
+
+	/* The return code is retured via data */
+	*(unsigned long *)data = 0;
 
 	return 0;
 }
diff --git a/arch/x86/mm/mmio-mod.c b/arch/x86/mm/mmio-mod.c
index 635b50e8558..2c4baa88f2c 100644
--- a/arch/x86/mm/mmio-mod.c
+++ b/arch/x86/mm/mmio-mod.c
@@ -56,13 +56,6 @@ struct remap_trace {
 static DEFINE_PER_CPU(struct trap_reason, pf_reason);
 static DEFINE_PER_CPU(struct mmiotrace_rw, cpu_trace);
 
-#if 0 /* XXX: no way gather this info anymore */
-/* Access to this is not per-cpu. */
-static DEFINE_PER_CPU(atomic_t, dropped);
-#endif
-
-static struct dentry *marker_file;
-
 static DEFINE_MUTEX(mmiotrace_mutex);
 static DEFINE_SPINLOCK(trace_lock);
 static atomic_t mmiotrace_enabled;
@@ -75,7 +68,7 @@ static LIST_HEAD(trace_list);		/* struct remap_trace */
  *   and trace_lock.
  * - Routines depending on is_enabled() must take trace_lock.
  * - trace_list users must hold trace_lock.
- * - is_enabled() guarantees that mmio_trace_record is allowed.
+ * - is_enabled() guarantees that mmio_trace_{rw,mapping} are allowed.
  * - pre/post callbacks assume the effect of is_enabled() being true.
  */
 
@@ -97,44 +90,6 @@ static bool is_enabled(void)
 	return atomic_read(&mmiotrace_enabled);
 }
 
-#if 0 /* XXX: needs rewrite */
-/*
- * Write callback for the debugfs entry:
- * Read a marker and write it to the mmio trace log
- */
-static ssize_t write_marker(struct file *file, const char __user *buffer,
-						size_t count, loff_t *ppos)
-{
-	char *event = NULL;
-	struct mm_io_header *headp;
-	ssize_t len = (count > 65535) ? 65535 : count;
-
-	event = kzalloc(sizeof(*headp) + len, GFP_KERNEL);
-	if (!event)
-		return -ENOMEM;
-
-	headp = (struct mm_io_header *)event;
-	headp->type = MMIO_MAGIC | (MMIO_MARKER << MMIO_OPCODE_SHIFT);
-	headp->data_len = len;
-
-	if (copy_from_user(event + sizeof(*headp), buffer, len)) {
-		kfree(event);
-		return -EFAULT;
-	}
-
-	spin_lock_irq(&trace_lock);
-#if 0 /* XXX: convert this to use tracing */
-	if (is_enabled())
-		relay_write(chan, event, sizeof(*headp) + len);
-	else
-#endif
-		len = -EINVAL;
-	spin_unlock_irq(&trace_lock);
-	kfree(event);
-	return len;
-}
-#endif
-
 static void print_pte(unsigned long address)
 {
 	unsigned int level;
@@ -307,8 +262,10 @@ static void ioremap_trace_core(resource_size_t offset, unsigned long size,
 	map.map_id = trace->id;
 
 	spin_lock_irq(&trace_lock);
-	if (!is_enabled())
+	if (!is_enabled()) {
+		kfree(trace);
 		goto not_enabled;