Merge branch 'tip/perf/jump-label-2' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-2.6-trace into perf/urgent

96 files changed, 4425 insertions, 2389 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index dfabfefc21c4..299fbc86f570 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -347,6 +347,7 @@ endif
 
 config X86_VSMP
 	bool "ScaleMP vSMP"
+	select PARAVIRT_GUEST
 	select PARAVIRT
 	depends on X86_64 && PCI
 	depends on X86_EXTENDED_PLATFORM
diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug
index e5bb96b10f1a..b59ee765414e 100644
--- a/arch/x86/Kconfig.debug
+++ b/arch/x86/Kconfig.debug
@@ -125,16 +125,6 @@ config DEBUG_NX_TEST
 	  and the software setup of this feature.
 	  If in doubt, say "N"
 
-config 4KSTACKS
-	bool "Use 4Kb for kernel stacks instead of 8Kb"
-	depends on X86_32
-	---help---
-	  If you say Y here the kernel will use a 4Kb stacksize for the
-	  kernel stack attached to each process/thread. This facilitates
-	  running more threads on a system and also reduces the pressure
-	  on the VM subsystem for higher order allocations. This option
-	  will also use IRQ stacks to compensate for the reduced stackspace.
-
 config DOUBLEFAULT
 	default y
 	bool "Enable doublefault exception handler" if EMBEDDED
diff --git a/arch/x86/Makefile_32.cpu b/arch/x86/Makefile_32.cpu
index 1255d953c65d..f2ee1abb1df9 100644
--- a/arch/x86/Makefile_32.cpu
+++ b/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.
diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c
index 8f7bef8e9fff..23f315c9f215 100644
--- a/arch/x86/boot/compressed/misc.c
+++ b/arch/x86/boot/compressed/misc.c
@@ -229,18 +229,35 @@ void *memset(void *s, int c, size_t n)
 		ss[i] = c;
 	return s;
 }
-
+#ifdef CONFIG_X86_32
 void *memcpy(void *dest, const void *src, size_t n)
 {
-	int i;
-	const char *s = src;
-	char *d = dest;
+	int d0, d1, d2;
+	asm volatile(
+		"rep ; movsl\n\t"
+		"movl %4,%%ecx\n\t"
+		"rep ; movsb\n\t"
+		: "=&c" (d0), "=&D" (d1), "=&S" (d2)
+		: "0" (n >> 2), "g" (n & 3), "1" (dest), "2" (src)
+		: "memory");
 
-	for (i = 0; i < n; i++)
-		d[i] = s[i];
 	return dest;
 }
+#else
+void *memcpy(void *dest, const void *src, size_t n)
+{
+	long d0, d1, d2;
+	asm volatile(
+		"rep ; movsq\n\t"
+		"movq %4,%%rcx\n\t"
+		"rep ; movsb\n\t"
+		: "=&c" (d0), "=&D" (d1), "=&S" (d2)
+		: "0" (n >> 3), "g" (n & 7), "1" (dest), "2" (src)
+		: "memory");
 
+	return dest;
+}
+#endif
 
 static void error(char *x)
 {
diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h
index bafd80defa43..903683b07e42 100644
--- a/arch/x86/include/asm/bitops.h
+++ b/arch/x86/include/asm/bitops.h
@@ -440,6 +440,8 @@ static inline int fls(int x)
 
 #ifdef __KERNEL__
 
+#include <asm-generic/bitops/find.h>
+
 #include <asm-generic/bitops/sched.h>
 
 #define ARCH_HAS_FAST_MULTIPLIER 1
diff --git a/arch/x86/include/asm/calling.h b/arch/x86/include/asm/calling.h
index 0e63c9a2a8d0..30af5a832163 100644
--- a/arch/x86/include/asm/calling.h
+++ b/arch/x86/include/asm/calling.h
@@ -48,36 +48,38 @@ For 32-bit we have the following conventions - kernel is built with
 
 
 /*
- * 64-bit system call stack frame layout defines and helpers,
- * for assembly code:
+ * 64-bit system call stack frame layout defines and helpers, for
+ * assembly code (note that the seemingly unnecessary parentheses
+ * are to prevent cpp from inserting spaces in expressions that get
+ * passed to macros):
  */
 
-#define R15		  0
-#define R14		  8
-#define R13		 16
-#define R12		 24
-#define RBP		 32
-#define RBX		 40
+#define R15		  (0)
+#define R14		  (8)
+#define R13		 (16)
+#define R12		 (24)
+#define RBP		 (32)
+#define RBX		 (40)
 
 /* arguments: interrupts/non tracing syscalls only save up to here: */
-#define R11		 48
-#define R10		 56
-#define R9		 64
-#define R8		 72
-#define RAX		 80
-#define RCX		 88
-#define RDX		 96
-#define RSI		104
-#define RDI		112
-#define ORIG_RAX	120       /* + error_code */
+#define R11		 (48)
+#define R10		 (56)
+#define R9		 (64)
+#define R8		 (72)
+#define RAX		 (80)
+#define RCX		 (88)
+#define RDX		 (96)
+#define RSI		(104)
+#define RDI		(112)
+#define ORIG_RAX	(120)       /* + error_code */
 /* end of arguments */
 
 /* cpu exception frame or undefined in case of fast syscall: */
-#define RIP		128
-#define CS		136
-#define EFLAGS		144
-#define RSP		152
-#define SS		160
+#define RIP		(128)
+#define CS		(136)
+#define EFLAGS		(144)
+#define RSP		(152)
+#define SS		(160)
 
 #define ARGOFFSET	R11
 #define SWFRAME		ORIG_RAX
@@ -111,7 +113,7 @@ For 32-bit we have the following conventions - kernel is built with
 	.endif
 	.endm
 
-#define ARG_SKIP	9*8
+#define ARG_SKIP	(9*8)
 
 	.macro RESTORE_ARGS skiprax=0, addskip=0, skiprcx=0, skipr11=0, \
 			    skipr8910=0, skiprdx=0
@@ -169,7 +171,7 @@ For 32-bit we have the following conventions - kernel is built with
 	.endif
 	.endm
 
-#define REST_SKIP	6*8
+#define REST_SKIP	(6*8)
 
 	.macro SAVE_REST
 	subq $REST_SKIP, %rsp
diff --git a/arch/x86/include/asm/entry_arch.h b/arch/x86/include/asm/entry_arch.h
index b8e96a18676b..57650ab4a5f5 100644
--- a/arch/x86/include/asm/entry_arch.h
+++ b/arch/x86/include/asm/entry_arch.h
@@ -16,22 +16,11 @@ BUILD_INTERRUPT(call_function_single_interrupt,CALL_FUNCTION_SINGLE_VECTOR)
 BUILD_INTERRUPT(irq_move_cleanup_interrupt,IRQ_MOVE_CLEANUP_VECTOR)
 BUILD_INTERRUPT(reboot_interrupt,REBOOT_VECTOR)
 
-BUILD_INTERRUPT3(invalidate_interrupt0,INVALIDATE_TLB_VECTOR_START+0,
-		 smp_invalidate_interrupt)
-BUILD_INTERRUPT3(invalidate_interrupt1,INVALIDATE_TLB_VECTOR_START+1,
-		 smp_invalidate_interrupt)
-BUILD_INTERRUPT3(invalidate_interrupt2,INVALIDATE_TLB_VECTOR_START+2,
-		 smp_invalidate_interrupt)
-BUILD_INTERRUPT3(invalidate_interrupt3,INVALIDATE_TLB_VECTOR_START+3,
-		 smp_invalidate_interrupt)
-BUILD_INTERRUPT3(invalidate_interrupt4,INVALIDATE_TLB_VECTOR_START+4,
-		 smp_invalidate_interrupt)
-BUILD_INTERRUPT3(invalidate_interrupt5,INVALIDATE_TLB_VECTOR_START+5,
-		 smp_invalidate_interrupt)
-BUILD_INTERRUPT3(invalidate_interrupt6,INVALIDATE_TLB_VECTOR_START+6,
-		 smp_invalidate_interrupt)
-BUILD_INTERRUPT3(invalidate_interrupt7,INVALIDATE_TLB_VECTOR_START+7,
+.irpc idx, "01234567"
+BUILD_INTERRUPT3(invalidate_interrupt\idx,
+		 (INVALIDATE_TLB_VECTOR_START)+\idx,
 		 smp_invalidate_interrupt)
+.endr
 #endif
 
 BUILD_INTERRUPT(x86_platform_ipi, X86_PLATFORM_IPI_VECTOR)
diff --git a/arch/x86/include/asm/highmem.h b/arch/x86/include/asm/highmem.h
index 8caac76ac324..3bd04022fd0c 100644
--- a/arch/x86/include/asm/highmem.h
+++ b/arch/x86/include/asm/highmem.h
@@ -59,11 +59,12 @@ extern void kunmap_high(struct page *page);
 
 void *kmap(struct page *page);
 void kunmap(struct page *page);
-void *kmap_atomic_prot(struct page *page, enum km_type type, pgprot_t prot);
-void *kmap_atomic(struct page *page, enum km_type type);
-void kunmap_atomic_notypecheck(void *kvaddr, enum km_type type);
-void *kmap_atomic_pfn(unsigned long pfn, enum km_type type);
-void *kmap_atomic_prot_pfn(unsigned long pfn, enum km_type type, pgprot_t prot);
+
+void *kmap_atomic_prot(struct page *page, pgprot_t prot);
+void *__kmap_atomic(struct page *page);
+void __kunmap_atomic(void *kvaddr);
+void *kmap_atomic_pfn(unsigned long pfn);
+void *kmap_atomic_prot_pfn(unsigned long pfn, pgprot_t prot);
 struct page *kmap_atomic_to_page(void *ptr);
 
 #define flush_cache_kmaps()	do { } while (0)
diff --git a/arch/x86/include/asm/iomap.h b/arch/x86/include/asm/iomap.h
index c4191b3b7056..363e33eb6ec1 100644
--- a/arch/x86/include/asm/iomap.h
+++ b/arch/x86/include/asm/iomap.h
@@ -27,10 +27,10 @@
 #include <asm/tlbflush.h>
 
 void __iomem *
-iomap_atomic_prot_pfn(unsigned long pfn, enum km_type type, pgprot_t prot);
+iomap_atomic_prot_pfn(unsigned long pfn, pgprot_t prot);
 
 void
-iounmap_atomic(void __iomem *kvaddr, enum km_type type);
+iounmap_atomic(void __iomem *kvaddr);
 
 int
 iomap_create_wc(resource_size_t base, unsigned long size, pgprot_t *prot);
diff --git a/arch/x86/include/asm/irq.h b/arch/x86/include/asm/irq.h
index 5458380b6ef8..13b0ebaa512f 100644
--- a/arch/x86/include/asm/irq.h
+++ b/arch/x86/include/asm/irq.h
@@ -19,18 +19,14 @@ static inline int irq_canonicalize(int irq)
 # define ARCH_HAS_NMI_WATCHDOG
 #endif
 
-#ifdef CONFIG_4KSTACKS
-  extern void irq_ctx_init(int cpu);
-  extern void irq_ctx_exit(int cpu);
-# define __ARCH_HAS_DO_SOFTIRQ
+#ifdef CONFIG_X86_32
+extern void irq_ctx_init(int cpu);
 #else
 # define irq_ctx_init(cpu) do { } while (0)
-# define irq_ctx_exit(cpu) do { } while (0)
-# ifdef CONFIG_X86_64
-#  define __ARCH_HAS_DO_SOFTIRQ
-# endif
 #endif
 
+#define __ARCH_HAS_DO_SOFTIRQ
+
 #ifdef CONFIG_HOTPLUG_CPU
 #include <linux/cpumask.h>
 extern void fixup_irqs(void);
diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h
index 1f99ecfc48e1..b36c6b3fe144 100644
--- a/