Merge branches 'perf-fixes-for-linus' and 'x86-fixes-for-linus' of gi…

…t://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/Kconfig

@@ -42,6 +42,20 @@ config KPROBES
 	  for kernel debugging, non-intrusive instrumentation and testing.
 	  If in doubt, say "N".
 
+config JUMP_LABEL
+       bool "Optimize trace point call sites"
+       depends on HAVE_ARCH_JUMP_LABEL
+       help
+         If it is detected that the compiler has support for "asm goto",
+	 the kernel will compile trace point locations with just a
+	 nop instruction. When trace points are enabled, the nop will
+	 be converted to a jump to the trace function. This technique
+	 lowers overhead and stress on the branch prediction of the
+	 processor.
+
+	 On i386, options added to the compiler flags may increase
+	 the size of the kernel slightly.
+
 config OPTPROBES
 	def_bool y
 	depends on KPROBES && HAVE_OPTPROBES

arch/sparc/include/asm/jump_label.h

@@ -13,6 +13,7 @@
 			 "nop\n\t"				\
 			 "nop\n\t"				\
 			 ".pushsection __jump_table,  \"a\"\n\t"\
+			 ".align 4\n\t"				\
 			 ".word 1b, %l[" #label "], %c0\n\t"	\
 			 ".popsection \n\t"			\
 			 : :  "i" (key) :  : label);\

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);

drivers/oprofile/buffer_sync.c

@@ -190,7 +190,7 @@ void sync_stop(void)
 	profile_event_unregister(PROFILE_TASK_EXIT, &task_exit_nb);
 	task_handoff_unregister(&task_free_nb);
 	mutex_unlock(&buffer_mutex);
-	flush_scheduled_work();
+	flush_cpu_work();
 
 	/* make sure we don't leak task structs */
 	process_task_mortuary();

drivers/oprofile/cpu_buffer.c

@@ -111,14 +111,18 @@ void start_cpu_work(void)
 
 void end_cpu_work(void)
 {
-	int i;
-
 	work_enabled = 0;
+}
+
+void flush_cpu_work(void)
+{
+	int i;
 
 	for_each_online_cpu(i) {
 		struct oprofile_cpu_buffer *b = &per_cpu(op_cpu_buffer, i);
 
-		cancel_delayed_work(&b->work);
+		/* these works are per-cpu, no need for flush_sync */
+		flush_delayed_work(&b->work);
 	}
 }
 

drivers/oprofile/cpu_buffer.h

@@ -25,6 +25,7 @@ void free_cpu_buffers(void);
 
 void start_cpu_work(void);
 void end_cpu_work(void);
+void flush_cpu_work(void);
 
 /* CPU buffer is composed of such entries (which are
  * also used for context switch notes)

drivers/oprofile/timer_int.c

@@ -21,6 +21,7 @@
 #include "oprof.h"
 
 static DEFINE_PER_CPU(struct hrtimer, oprofile_hrtimer);
+static int ctr_running;
 
 static enum hrtimer_restart oprofile_hrtimer_notify(struct hrtimer *hrtimer)
 {
@@ -33,6 +34,9 @@ static void __oprofile_hrtimer_start(void *unused)
 {
 	struct hrtimer *hrtimer = &__get_cpu_var(oprofile_hrtimer);
 
+	if (!ctr_running)
+		return;
+
 	hrtimer_init(hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 	hrtimer->function = oprofile_hrtimer_notify;
 
@@ -42,23 +46,32 @@ static void __oprofile_hrtimer_start(void *unused)
 
 static int oprofile_hrtimer_start(void)
 {
+	get_online_cpus();
+	ctr_running = 1;
 	on_each_cpu(__oprofile_hrtimer_start, NULL, 1);
+	put_online_cpus();
 	return 0;
 }
 
 static void __oprofile_hrtimer_stop(int cpu)
 {
 	struct hrtimer *hrtimer = &per_cpu(oprofile_hrtimer, cpu);
 
+	if (!ctr_running)
+		return;
+
 	hrtimer_cancel(hrtimer);
 }
 
 static void oprofile_hrtimer_stop(void)
 {
 	int cpu;
 
+	get_online_cpus();
 	for_each_online_cpu(cpu)
 		__oprofile_hrtimer_stop(cpu);
+	ctr_running = 0;
+	put_online_cpus();
 }
 
 static int __cpuinit oprofile_cpu_notify(struct notifier_block *self,

include/linux/jump_label.h

@@ -1,7 +1,7 @@
 #ifndef _LINUX_JUMP_LABEL_H
 #define _LINUX_JUMP_LABEL_H
 
-#if defined(CC_HAVE_ASM_GOTO) && defined(CONFIG_HAVE_ARCH_JUMP_LABEL)
+#if defined(CC_HAVE_ASM_GOTO) && defined(CONFIG_JUMP_LABEL)
 # include <asm/jump_label.h>
 # define HAVE_JUMP_LABEL
 #endif
@@ -18,6 +18,8 @@ struct module;
 extern struct jump_entry __start___jump_table[];
 extern struct jump_entry __stop___jump_table[];
 
+extern void jump_label_lock(void);
+extern void jump_label_unlock(void);
 extern void arch_jump_label_transform(struct jump_entry *entry,
 				 enum jump_label_type type);
 extern void arch_jump_label_text_poke_early(jump_label_t addr);
@@ -59,6 +61,9 @@ static inline int jump_label_text_reserved(void *start, void *end)
 	return 0;
 }
 
+static inline void jump_label_lock(void) {}
+static inline void jump_label_unlock(void) {}
+
 #endif
 
 #define COND_STMT(key, stmt)					\