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.

4 files changed, 86 insertions, 89 deletions

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;
 }