Merge branches 'perf-fixes-for-linus' and 'x86-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'perf-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
  jump label: Add work around to i386 gcc asm goto bug
  x86, ftrace: Use safe noops, drop trap test
  jump_label: Fix unaligned traps on sparc.
  jump label: Make arch_jump_label_text_poke_early() optional
  jump label: Fix error with preempt disable holding mutex
  oprofile: Remove deprecated use of flush_scheduled_work()
  oprofile: Fix the hang while taking the cpu offline
  jump label: Fix deadlock b/w jump_label_mutex vs. text_mutex
  jump label: Fix module __init section race

* 'x86-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
  x86: Check irq_remapped instead of remapping_enabled in destroy_irq()

arch/x86/Makefile_32.cpu

@@ -51,7 +51,18 @@ cflags-$(CONFIG_X86_GENERIC) 	+= $(call tune,generic,$(call tune,i686))
 # prologue (push %ebp, mov %esp, %ebp) which breaks the function graph
 # tracer assumptions. For i686, generic, core2 this is set by the
 # compiler anyway
-cflags-$(CONFIG_FUNCTION_GRAPH_TRACER) += $(call cc-option,-maccumulate-outgoing-args)
+ifeq ($(CONFIG_FUNCTION_GRAPH_TRACER), y)
+ADD_ACCUMULATE_OUTGOING_ARGS := y
+endif
+
+# Work around to a bug with asm goto with first implementations of it
+# in gcc causing gcc to mess up the push and pop of the stack in some
+# uses of asm goto.
+ifeq ($(CONFIG_JUMP_LABEL), y)
+ADD_ACCUMULATE_OUTGOING_ARGS := y
+endif
+
+cflags-$(ADD_ACCUMULATE_OUTGOING_ARGS) += $(call cc-option,-maccumulate-outgoing-args)
 
 # Bug fix for binutils: this option is required in order to keep
 # binutils from generating NOPL instructions against our will.

arch/x86/kernel/alternative.c

@@ -644,65 +644,26 @@ void *__kprobes text_poke_smp(void *addr, const void *opcode, size_t len)
 
 #if defined(CONFIG_DYNAMIC_FTRACE) || defined(HAVE_JUMP_LABEL)
 
-unsigned char ideal_nop5[IDEAL_NOP_SIZE_5];
+#ifdef CONFIG_X86_64
+unsigned char ideal_nop5[5] = { 0x66, 0x66, 0x66, 0x66, 0x90 };
+#else
+unsigned char ideal_nop5[5] = { 0x3e, 0x8d, 0x74, 0x26, 0x00 };
+#endif
 
 void __init arch_init_ideal_nop5(void)
 {
-	extern const unsigned char ftrace_test_p6nop[];
-	extern const unsigned char ftrace_test_nop5[];
-	extern const unsigned char ftrace_test_jmp[];
-	int faulted = 0;
-
 	/*
-	 * 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.
+	 * There is no good nop for all x86 archs.  This selection
+	 * algorithm should be unified with the one in find_nop_table(),
+	 * but this should be good enough for now.
 	 *
-	 * TODO: check the cpuid to determine the best nop.
+	 * For cases other than the ones below, use the safe (as in
+	 * always functional) defaults above.
 	 */
-	asm volatile (
-		"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"
-		"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("converting mcount calls to 0f 1f 44 00 00\n");
-		memcpy(ideal_nop5, ftrace_test_p6nop, IDEAL_NOP_SIZE_5);
-		break;
-	case 1:
-		pr_info("converting mcount calls to 66 66 66 66 90\n");
-		memcpy(ideal_nop5, ftrace_test_nop5, IDEAL_NOP_SIZE_5);
-		break;
-	case 2:
-		pr_info("converting mcount calls to jmp . + 5\n");
-		memcpy(ideal_nop5, ftrace_test_jmp, IDEAL_NOP_SIZE_5);
-		break;
-	}
-
+#ifdef CONFIG_X86_64
+	/* Don't use these on 32 bits due to broken virtualizers */
+	if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL)
+		memcpy(ideal_nop5, p6_nops[5], 5);
+#endif
 }
 #endif

arch/x86/kernel/apic/io_apic.c

@@ -3109,7 +3109,7 @@ void destroy_irq(unsigned int irq)
 
 	irq_set_status_flags(irq, IRQ_NOREQUEST|IRQ_NOPROBE);
 
-	if (intr_remapping_enabled)
+	if (irq_remapped(cfg))
 		free_irte(irq);
 	raw_spin_lock_irqsave(&vector_lock, flags);
 	__clear_irq_vector(irq, cfg);