Merge branch 'perf-core-for-linus' of git://git.kernel.org/pub/scm/li…

…nux/kernel/git/tip/linux-2.6-tip

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (107 commits)
  perf stat: Add more cache-miss percentage printouts
  perf stat: Add -d -d and -d -d -d options to show more CPU events
  ftrace/kbuild: Add recordmcount files to force full build
  ftrace: Add self-tests for multiple function trace users
  ftrace: Modify ftrace_set_filter/notrace to take ops
  ftrace: Allow dynamically allocated function tracers
  ftrace: Implement separate user function filtering
  ftrace: Free hash with call_rcu_sched()
  ftrace: Have global_ops store the functions that are to be traced
  ftrace: Add ops parameter to ftrace_startup/shutdown functions
  ftrace: Add enabled_functions file
  ftrace: Use counters to enable functions to trace
  ftrace: Separate hash allocation and assignment
  ftrace: Create a global_ops to hold the filter and notrace hashes
  ftrace: Use hash instead for FTRACE_FL_FILTER
  ftrace: Replace FTRACE_FL_NOTRACE flag with a hash of ignored functions
  perf bench, x86: Add alternatives-asm.h wrapper
  x86, 64-bit: Fix copy_[to/from]_user() checks for the userspace address limit
  x86, mem: memset_64.S: Optimize memset by enhanced REP MOVSB/STOSB
  x86, mem: memmove_64.S: Optimize memmove by enhanced REP MOVSB/STOSB
  ...

Makefile

@@ -1268,6 +1268,7 @@ help:
 	@echo  '  make C=1   [targets] Check all c source with $$CHECK (sparse by default)'
 	@echo  '  make C=2   [targets] Force check of all c source with $$CHECK'
 	@echo  '  make W=1   [targets] Enable extra gcc checks'
+	@echo  '  make RECORDMCOUNT_WARN=1 [targets] Warn about ignored mcount sections'
 	@echo  ''
 	@echo  'Execute "make" or "make all" to build all targets marked with [*] '
 	@echo  'For further info see the ./README file'

arch/mips/include/asm/jump_label.h

@@ -20,16 +20,18 @@
 #define WORD_INSN ".word"
 #endif
 
-#define JUMP_LABEL(key, label)						\
-	do {								\
-		asm goto("1:\tnop\n\t"					\
-			"nop\n\t"					\
-			".pushsection __jump_table,  \"a\"\n\t"		\
-			WORD_INSN " 1b, %l[" #label "], %0\n\t"		\
-			".popsection\n\t"				\
-			: :  "i" (key) :  : label);			\
-	} while (0)
-
+static __always_inline bool arch_static_branch(struct jump_label_key *key)
+{
+	asm goto("1:\tnop\n\t"
+		"nop\n\t"
+		".pushsection __jump_table,  \"aw\"\n\t"
+		WORD_INSN " 1b, %l[l_yes], %0\n\t"
+		".popsection\n\t"
+		: :  "i" (key) : : l_yes);
+	return false;
+l_yes:
+	return true;
+}
 
 #endif /* __KERNEL__ */
 

arch/s390/Kconfig

@@ -88,6 +88,7 @@ config S390
 	select HAVE_KERNEL_XZ
 	select HAVE_GET_USER_PAGES_FAST
 	select HAVE_ARCH_MUTEX_CPU_RELAX
+	select HAVE_ARCH_JUMP_LABEL if !MARCH_G5
 	select ARCH_INLINE_SPIN_TRYLOCK
 	select ARCH_INLINE_SPIN_TRYLOCK_BH
 	select ARCH_INLINE_SPIN_LOCK

arch/s390/include/asm/ftrace.h

@@ -11,15 +11,13 @@ struct dyn_arch_ftrace { };
 
 #ifdef CONFIG_64BIT
 #define MCOUNT_INSN_SIZE  12
-#define MCOUNT_OFFSET	   8
 #else
 #define MCOUNT_INSN_SIZE  20
-#define MCOUNT_OFFSET	   4
 #endif
 
 static inline unsigned long ftrace_call_adjust(unsigned long addr)
 {
-	return addr - MCOUNT_OFFSET;
+	return addr;
 }
 
 #endif /* __ASSEMBLY__ */

arch/s390/include/asm/jump_label.h

@@ -0,0 +1,37 @@
+#ifndef _ASM_S390_JUMP_LABEL_H
+#define _ASM_S390_JUMP_LABEL_H
+
+#include <linux/types.h>
+
+#define JUMP_LABEL_NOP_SIZE 6
+
+#ifdef CONFIG_64BIT
+#define ASM_PTR ".quad"
+#define ASM_ALIGN ".balign 8"
+#else
+#define ASM_PTR ".long"
+#define ASM_ALIGN ".balign 4"
+#endif
+
+static __always_inline bool arch_static_branch(struct jump_label_key *key)
+{
+	asm goto("0:	brcl 0,0\n"
+		".pushsection __jump_table, \"aw\"\n"
+		ASM_ALIGN "\n"
+		ASM_PTR " 0b, %l[label], %0\n"
+		".popsection\n"
+		: : "X" (key) : : label);
+	return false;
+label:
+	return true;
+}
+
+typedef unsigned long jump_label_t;
+
+struct jump_entry {
+	jump_label_t code;
+	jump_label_t target;
+	jump_label_t key;
+};
+
+#endif

arch/s390/kernel/Makefile

@@ -23,7 +23,7 @@ CFLAGS_sysinfo.o += -Iinclude/math-emu -Iarch/s390/math-emu -w
 obj-y	:=  bitmap.o traps.o time.o process.o base.o early.o setup.o \
 	    processor.o sys_s390.o ptrace.o signal.o cpcmd.o ebcdic.o \
 	    s390_ext.o debug.o irq.o ipl.o dis.o diag.o mem_detect.o \
-	    vdso.o vtime.o sysinfo.o nmi.o sclp.o
+	    vdso.o vtime.o sysinfo.o nmi.o sclp.o jump_label.o
 
 obj-y	+= $(if $(CONFIG_64BIT),entry64.o,entry.o)
 obj-y	+= $(if $(CONFIG_64BIT),reipl64.o,reipl.o)

arch/s390/kernel/jump_label.c

@@ -0,0 +1,59 @@
+/*
+ * Jump label s390 support
+ *
+ * Copyright IBM Corp. 2011
+ * Author(s): Jan Glauber <[email protected]>
+ */
+#include <linux/module.h>
+#include <linux/uaccess.h>
+#include <linux/stop_machine.h>
+#include <linux/jump_label.h>
+#include <asm/ipl.h>
+
+#ifdef HAVE_JUMP_LABEL
+
+struct insn {
+	u16 opcode;
+	s32 offset;
+} __packed;
+
+struct insn_args {
+	unsigned long *target;
+	struct insn *insn;
+	ssize_t size;
+};
+
+static int __arch_jump_label_transform(void *data)
+{
+	struct insn_args *args = data;
+	int rc;
+
+	rc = probe_kernel_write(args->target, args->insn, args->size);
+	WARN_ON_ONCE(rc < 0);
+	return 0;
+}
+
+void arch_jump_label_transform(struct jump_entry *entry,
+			       enum jump_label_type type)
+{
+	struct insn_args args;
+	struct insn insn;
+
+	if (type == JUMP_LABEL_ENABLE) {
+		/* brcl 15,offset */
+		insn.opcode = 0xc0f4;
+		insn.offset = (entry->target - entry->code) >> 1;
+	} else {
+		/* brcl 0,0 */
+		insn.opcode = 0xc004;
+		insn.offset = 0;
+	}
+
+	args.target = (void *) entry->code;
+	args.insn = &insn;
+	args.size = JUMP_LABEL_NOP_SIZE;
+
+	stop_machine(__arch_jump_label_transform, &args, NULL);
+}
+
+#endif

arch/sparc/include/asm/jump_label.h

@@ -7,17 +7,20 @@
 
 #define JUMP_LABEL_NOP_SIZE 4
 
-#define JUMP_LABEL(key, label)					\
-	do {							\
-		asm goto("1:\n\t"				\
-			 "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);\
-	} while (0)
+static __always_inline bool arch_static_branch(struct jump_label_key *key)
+{
+		asm goto("1:\n\t"
+			 "nop\n\t"
+			 "nop\n\t"
+			 ".pushsection __jump_table,  \"aw\"\n\t"
+			 ".align 4\n\t"
+			 ".word 1b, %l[l_yes], %c0\n\t"
+			 ".popsection \n\t"
+			 : :  "i" (key) : : l_yes);
+	return false;
+l_yes:
+	return true;
+}
 
 #endif /* __KERNEL__ */
 

arch/x86/include/asm/alternative-asm.h

@@ -15,4 +15,13 @@
 	.endm
 #endif
 
+.macro altinstruction_entry orig alt feature orig_len alt_len
+	.align 8
+	.quad \orig
+	.quad \alt
+	.word \feature
+	.byte \orig_len
+	.byte \alt_len
+.endm
+
 #endif  /*  __ASSEMBLY__  */

arch/x86/include/asm/alternative.h

@@ -4,7 +4,6 @@
 #include <linux/types.h>
 #include <linux/stddef.h>
 #include <linux/stringify.h>
-#include <linux/jump_label.h>
 #include <asm/asm.h>
 
 /*
@@ -191,7 +190,7 @@ extern void *text_poke(void *addr, const void *opcode, size_t len);
 extern void *text_poke_smp(void *addr, const void *opcode, size_t len);
 extern void text_poke_smp_batch(struct text_poke_param *params, int n);
 
-#if defined(CONFIG_DYNAMIC_FTRACE) || defined(HAVE_JUMP_LABEL)
+#if defined(CONFIG_DYNAMIC_FTRACE) || defined(CONFIG_JUMP_LABEL)
 #define IDEAL_NOP_SIZE_5 5
 extern unsigned char ideal_nop5[IDEAL_NOP_SIZE_5];
 extern void arch_init_ideal_nop5(void);

arch/x86/include/asm/cpufeature.h

@@ -195,6 +195,7 @@
 
 /* Intel-defined CPU features, CPUID level 0x00000007:0 (ebx), word 9 */
 #define X86_FEATURE_FSGSBASE	(9*32+ 0) /* {RD/WR}{FS/GS}BASE instructions*/
+#define X86_FEATURE_ERMS	(9*32+ 9) /* Enhanced REP MOVSB/STOSB */
 
 #if defined(__KERNEL__) && !defined(__ASSEMBLY__)
 

arch/x86/include/asm/ftrace.h

@@ -38,11 +38,10 @@ 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.
+	 * addr is the address of the mcount call instruction.
+	 * recordmcount does the necessary offset calculation.
 	 */
-	return addr - 1;
+	return addr;
 }
 
 #ifdef CONFIG_DYNAMIC_FTRACE

arch/x86/include/asm/jump_label.h

@@ -5,20 +5,25 @@
 
 #include <linux/types.h>
 #include <asm/nops.h>
+#include <asm/asm.h>
 
 #define JUMP_LABEL_NOP_SIZE 5
 
-# define JUMP_LABEL_INITIAL_NOP ".byte 0xe9 \n\t .long 0\n\t"
-
-# define JUMP_LABEL(key, label)					\
-	do {							\
-		asm goto("1:"					\
-			JUMP_LABEL_INITIAL_NOP			\
-			".pushsection __jump_table,  \"aw\" \n\t"\
-			_ASM_PTR "1b, %l[" #label "], %c0 \n\t" \
-			".popsection \n\t"			\
-			: :  "i" (key) :  : label);		\
-	} while (0)
+#define JUMP_LABEL_INITIAL_NOP ".byte 0xe9 \n\t .long 0\n\t"
+
+static __always_inline bool arch_static_branch(struct jump_label_key *key)
+{
+	asm goto("1:"
+		JUMP_LABEL_INITIAL_NOP
+		".pushsection __jump_table,  \"aw\" \n\t"
+		_ASM_ALIGN "\n\t"
+		_ASM_PTR "1b, %l[l_yes], %c0 \n\t"
+		".popsection \n\t"
+		: :  "i" (key) : : l_yes);
+	return false;
+l_yes:
+	return true;
+}
 
 #endif /* __KERNEL__ */
 

arch/x86/include/asm/setup.h

@@ -88,7 +88,7 @@ void *extend_brk(size_t size, size_t align);
  * executable.)
  */
 #define RESERVE_BRK(name,sz)						\
-	static void __section(.discard.text) __used			\
+	static void __section(.discard.text) __used notrace		\
 	__brk_reservation_fn_##name##__(void) {				\
 		asm volatile (						\
 			".pushsection .brk_reservation,\"aw\",@nobits;" \

arch/x86/include/asm/stacktrace.h

@@ -37,9 +37,6 @@ print_context_stack_bp(struct thread_info *tinfo,
 /* Generic stack tracer with callbacks */
 
 struct stacktrace_ops {
-	void (*warning)(void *data, char *msg);
-	/* msg must contain %s for the symbol */
-	void (*warning_symbol)(void *data, char *msg, unsigned long symbol);
 	void (*address)(void *data, unsigned long address, int reliable);
 	/* On negative return stop dumping */
 	int (*stack)(void *data, char *name);

arch/x86/include/asm/uaccess.h

@@ -42,7 +42,7 @@
  * Returns 0 if the range is valid, nonzero otherwise.
  *
  * This is equivalent to the following test:
- * (u33)addr + (u33)size >= (u33)current->addr_limit.seg (u65 for x86_64)
+ * (u33)addr + (u33)size > (u33)current->addr_limit.seg (u65 for x86_64)
  *
  * This needs 33-bit (65-bit for x86_64) arithmetic. We have a carry...
  */

arch/x86/kernel/alternative.c

@@ -210,6 +210,15 @@ void __init_or_module apply_alternatives(struct alt_instr *start,
 	u8 insnbuf[MAX_PATCH_LEN];
 
 	DPRINTK("%s: alt table %p -> %p\n", __func__, start, end);
+	/*
+	 * The scan order should be from start to end. A later scanned
+	 * alternative code can overwrite a previous scanned alternative code.
+	 * Some kernel functions (e.g. memcpy, memset, etc) use this order to
+	 * patch code.
+	 *
+	 * So be careful if you want to change the scan order to any other
+	 * order.
+	 */
 	for (a = start; a < end; a++) {
 		u8 *instr = a->instr;
 		BUG_ON(a->replacementlen > a->instrlen);
@@ -679,7 +688,7 @@ void __kprobes text_poke_smp_batch(struct text_poke_param *params, int n)
 	__stop_machine(stop_machine_text_poke, (void *)&tpp, NULL);
 }
 
-#if defined(CONFIG_DYNAMIC_FTRACE) || defined(HAVE_JUMP_LABEL)
+#if defined(CONFIG_DYNAMIC_FTRACE) || defined(CONFIG_JUMP_LABEL)
 
 #ifdef CONFIG_X86_64
 unsigned char ideal_nop5[5] = { 0x66, 0x66, 0x66, 0x66, 0x90 };

arch/x86/kernel/cpu/common.c

@@ -565,8 +565,7 @@ void __cpuinit get_cpu_cap(struct cpuinfo_x86 *c)
 
 		cpuid_count(0x00000007, 0, &eax, &ebx, &ecx, &edx);
 
-		if (eax > 0)
-			c->x86_capability[9] = ebx;
+		c->x86_capability[9] = ebx;
 	}
 
 	/* AMD-defined flags: level 0x80000001 */

arch/x86/kernel/cpu/intel.c

@@ -29,10 +29,10 @@
 
 static void __cpuinit early_init_intel(struct cpuinfo_x86 *c)
 {
+	u64 misc_enable;
+
 	/* Unmask CPUID levels if masked: */
 	if (c->x86 > 6 || (c->x86 == 6 && c->x86_model >= 0xd)) {
-		u64 misc_enable;
-
 		rdmsrl(MSR_IA32_MISC_ENABLE, misc_enable);
 
 		if (misc_enable & MSR_IA32_MISC_ENABLE_LIMIT_CPUID) {
@@ -118,8 +118,6 @@ static void __cpuinit early_init_intel(struct cpuinfo_x86 *c)
 	 * (model 2) with the same problem.
 	 */
 	if (c->x86 == 15) {
-		u64 misc_enable;
-
 		rdmsrl(MSR_IA32_MISC_ENABLE, misc_enable);
 
 		if (misc_enable & MSR_IA32_MISC_ENABLE_FAST_STRING) {
@@ -130,6 +128,19 @@ static void __cpuinit early_init_intel(struct cpuinfo_x86 *c)
 		}
 	}
 #endif
+
+	/*
+	 * If fast string is not enabled in IA32_MISC_ENABLE for any reason,
+	 * clear the fast string and enhanced fast string CPU capabilities.
+	 */
+	if (c->x86 > 6 || (c->x86 == 6 && c->x86_model >= 0xd)) {
+		rdmsrl(MSR_IA32_MISC_ENABLE, misc_enable);
+		if (!(misc_enable & MSR_IA32_MISC_ENABLE_FAST_STRING)) {
+			printk(KERN_INFO "Disabled fast string operations\n");
+			setup_clear_cpu_cap(X86_FEATURE_REP_GOOD);
+			setup_clear_cpu_cap(X86_FEATURE_ERMS);
+		}
+	}
 }
 
 #ifdef CONFIG_X86_32