23 files changed, 160 insertions, 303 deletions

diff --git a/arch/x86_64/Kconfig b/arch/x86_64/Kconfig
index 40242c61e90a..e63323e03ea9 100644
--- a/arch/x86_64/Kconfig
+++ b/arch/x86_64/Kconfig
@@ -24,6 +24,10 @@ config X86
 	bool
 	default y
 
+config SEMAPHORE_SLEEPERS
+	bool
+	default y
+
 config MMU
 	bool
 	default y
@@ -61,6 +65,10 @@ config GENERIC_IOMAP
 	bool
 	default y
 
+config ARCH_MAY_HAVE_PC_FDC
+	bool
+	default y
+
 source "init/Kconfig"
 
 
@@ -436,6 +444,11 @@ config ISA_DMA_API
 	bool
 	default y
 
+config GENERIC_PENDING_IRQ
+	bool
+	depends on GENERIC_HARDIRQS && SMP
+	default y
+
 menu "Power management options"
 
 source kernel/power/Kconfig
diff --git a/arch/x86_64/boot/setup.S b/arch/x86_64/boot/setup.S
index ff58b2832b75..12ea0b6c52e2 100644
--- a/arch/x86_64/boot/setup.S
+++ b/arch/x86_64/boot/setup.S
@@ -81,7 +81,7 @@ start:
 # This is the setup header, and it must start at %cs:2 (old 0x9020:2)
 
 		.ascii	"HdrS"		# header signature
-		.word	0x0203		# header version number (>= 0x0105)
+		.word	0x0204		# header version number (>= 0x0105)
 					# or else old loadlin-1.5 will fail)
 realmode_swtch:	.word	0, 0		# default_switch, SETUPSEG
 start_sys_seg:	.word	SYSSEG
diff --git a/arch/x86_64/boot/tools/build.c b/arch/x86_64/boot/tools/build.c
index 18b5bac1c428..c44f5e2ec100 100644
--- a/arch/x86_64/boot/tools/build.c
+++ b/arch/x86_64/boot/tools/build.c
@@ -178,7 +178,9 @@ int main(int argc, char ** argv)
 		die("Output: seek failed");
 	buf[0] = (sys_size & 0xff);
 	buf[1] = ((sys_size >> 8) & 0xff);
-	if (write(1, buf, 2) != 2)
+	buf[2] = ((sys_size >> 16) & 0xff);
+	buf[3] = ((sys_size >> 24) & 0xff);
+	if (write(1, buf, 4) != 4)
 		die("Write of image length failed");
 
 	return 0;					    /* Everything is OK */
diff --git a/arch/x86_64/ia32/ia32entry.S b/arch/x86_64/ia32/ia32entry.S
index c45d6a05b984..f174083d5567 100644
--- a/arch/x86_64/ia32/ia32entry.S
+++ b/arch/x86_64/ia32/ia32entry.S
@@ -307,7 +307,7 @@ ia32_sys_call_table:
 	.quad stub32_fork
 	.quad sys_read
 	.quad sys_write
-	.quad sys32_open		/* 5 */
+	.quad compat_sys_open		/* 5 */
 	.quad sys_close
 	.quad sys32_waitpid
 	.quad sys_creat
diff --git a/arch/x86_64/ia32/sys_ia32.c b/arch/x86_64/ia32/sys_ia32.c
index be996d1b691e..04d80406ce4f 100644
--- a/arch/x86_64/ia32/sys_ia32.c
+++ b/arch/x86_64/ia32/sys_ia32.c
@@ -969,32 +969,6 @@ long sys32_kill(int pid, int sig)
 	return sys_kill(pid, sig);
 }
  
-asmlinkage long sys32_open(const char __user * filename, int flags, int mode)
-{
-	char * tmp;
-	int fd, error;
-
-	/* don't force O_LARGEFILE */
-	tmp = getname(filename);
-	fd = PTR_ERR(tmp);
-	if (!IS_ERR(tmp)) {
-		fd = get_unused_fd();
-		if (fd >= 0) {
-			struct file *f = filp_open(tmp, flags, mode);
-			error = PTR_ERR(f);
-			if (IS_ERR(f)) {
-				put_unused_fd(fd); 
-				fd = error;
-			} else {
-				fsnotify_open(f->f_dentry);
-				fd_install(fd, f);
-			}
-		}
-		putname(tmp);
-	}
-	return fd;
-}
-
 extern asmlinkage long
 sys_timer_create(clockid_t which_clock,
 		 struct sigevent __user *timer_event_spec,
diff --git a/arch/x86_64/kernel/Makefile b/arch/x86_64/kernel/Makefile
index 0296ca6cbfa3..1579bdd0adcd 100644
--- a/arch/x86_64/kernel/Makefile
+++ b/arch/x86_64/kernel/Makefile
@@ -4,10 +4,10 @@
 
 extra-y 	:= head.o head64.o init_task.o vmlinux.lds
 EXTRA_AFLAGS	:= -traditional
-obj-y	:= process.o semaphore.o signal.o entry.o traps.o irq.o \
+obj-y	:= process.o signal.o entry.o traps.o irq.o \
 		ptrace.o time.o ioport.o ldt.o setup.o i8259.o sys_x86_64.o \
 		x8664_ksyms.o i387.o syscall.o vsyscall.o \
-		setup64.o bootflag.o e820.o reboot.o quirks.o
+		setup64.o bootflag.o e820.o reboot.o quirks.o i8237.o
 
 obj-$(CONFIG_X86_MCE)         += mce.o
 obj-$(CONFIG_X86_MCE_INTEL)	+= mce_intel.o
@@ -45,3 +45,4 @@ swiotlb-$(CONFIG_SWIOTLB)      += ../../ia64/lib/swiotlb.o
 microcode-$(subst m,y,$(CONFIG_MICROCODE))  += ../../i386/kernel/microcode.o
 intel_cacheinfo-y		+= ../../i386/kernel/cpu/intel_cacheinfo.o
 quirks-y			+= ../../i386/kernel/quirks.o
+i8237-y				+= ../../i386/kernel/i8237.o
diff --git a/arch/x86_64/kernel/e820.c b/arch/x86_64/kernel/e820.c
index b548dea4e5b9..116ac5f53dce 100644
--- a/arch/x86_64/kernel/e820.c
+++ b/arch/x86_64/kernel/e820.c
@@ -85,7 +85,7 @@ int __init e820_mapped(unsigned long start, unsigned long end, unsigned type)
 		struct e820entry *ei = &e820.map[i]; 
 		if (type && ei->type != type) 
 			continue;
-		if (ei->addr >= end || ei->addr + ei->size < start) 
+		if (ei->addr >= end || ei->addr + ei->size <= start)
 			continue; 
 		return 1; 
 	} 
diff --git a/arch/x86_64/kernel/entry.S b/arch/x86_64/kernel/entry.S
index 096d470e280f..be51dbe1f75e 100644
--- a/arch/x86_64/kernel/entry.S
+++ b/arch/x86_64/kernel/entry.S
@@ -784,8 +784,9 @@ ENTRY(execve)
 	ret
 	CFI_ENDPROC
 
-ENTRY(page_fault)
+KPROBE_ENTRY(page_fault)
 	errorentry do_page_fault
+	.previous .text
 
 ENTRY(coprocessor_error)
 	zeroentry do_coprocessor_error
@@ -797,13 +798,14 @@ ENTRY(device_not_available)
 	zeroentry math_state_restore
 
 	/* runs on exception stack */
-ENTRY(debug)
+KPROBE_ENTRY(debug)
 	CFI_STARTPROC
 	pushq $0
 	CFI_ADJUST_CFA_OFFSET 8		
 	paranoidentry do_debug
 	jmp paranoid_exit
 	CFI_ENDPROC
+	.previous .text
 
 	/* runs on exception stack */	
 ENTRY(nmi)
@@ -854,8 +856,9 @@ paranoid_schedule:
 	jmp paranoid_userspace
 	CFI_ENDPROC
 
-ENTRY(int3)
+KPROBE_ENTRY(int3)
 	zeroentry do_int3	
+	.previous .text
 
 ENTRY(overflow)
 	zeroentry do_overflow
@@ -892,8 +895,9 @@ ENTRY(stack_segment)
 	jmp paranoid_exit
 	CFI_ENDPROC
 
-ENTRY(general_protection)
+KPROBE_ENTRY(general_protection)
 	errorentry do_general_protection
+	.previous .text
 
 ENTRY(alignment_check)
 	errorentry do_alignment_check
diff --git a/arch/x86_64/kernel/genapic.c b/arch/x86_64/kernel/genapic.c
index f031358906f5..b1c144f73149 100644
--- a/arch/x86_64/kernel/genapic.c
+++ b/arch/x86_64/kernel/genapic.c
@@ -25,7 +25,7 @@
 #endif
 
 /* which logical CPU number maps to which CPU (physical APIC ID) */
-u8 x86_cpu_to_apicid[NR_CPUS] = { [0 ... NR_CPUS-1] = BAD_APICID };
+u8 x86_cpu_to_apicid[NR_CPUS] __read_mostly = { [0 ... NR_CPUS-1] = BAD_APICID };
 EXPORT_SYMBOL(x86_cpu_to_apicid);
 u8 x86_cpu_to_log_apicid[NR_CPUS] = { [0 ... NR_CPUS-1] = BAD_APICID };
 
diff --git a/arch/x86_64/kernel/genapic_cluster.c b/arch/x86_64/kernel/genapic_cluster.c
index 9703da7202e3..f6523dd1bc09 100644
--- a/arch/x86_64/kernel/genapic_cluster.c
+++ b/arch/x86_64/kernel/genapic_cluster.c
@@ -72,10 +72,14 @@ static void cluster_send_IPI_mask(cpumask_t mask, int vector)
 static void cluster_send_IPI_allbutself(int vector)
 {
 	cpumask_t mask = cpu_online_map;
-	cpu_clear(smp_processor_id(), mask);
+	int me = get_cpu(); /* Ensure we are not preempted when we clear */
+
+	cpu_clear(me, mask);
 
 	if (!cpus_empty(mask))
 		cluster_send_IPI_mask(mask, vector);
+
+	put_cpu();
 }
 
 static void cluster_send_IPI_all(int vector)
diff --git a/arch/x86_64/kernel/io_apic.c b/arch/x86_64/kernel/io_apic.c
index 1013a8fe44d7..40e0aca088fb 100644
--- a/arch/x86_64/kernel/io_apic.c
+++ b/arch/x86_64/kernel/io_apic.c
@@ -70,7 +70,7 @@ static struct irq_pin_list {
 	short apic, pin, next;
 } irq_2_pin[PIN_MAP_SIZE];
 
-int vector_irq[NR_VECTORS] = { [0 ... NR_VECTORS - 1] = -1};
+int vector_irq[NR_VECTORS] __read_mostly = { [0 ... NR_VECTORS - 1] = -1};
 #ifdef CONFIG_PCI_MSI
 #define vector_to_irq(vector) 	\
 	(platform_legacy_irq(vector) ? vector : vector_irq[vector])
@@ -78,6 +78,54 @@ int vector_irq[NR_VECTORS] = { [0 ... NR_VECTORS - 1] = -1};
 #define vector_to_irq(vector)	(vector)
 #endif
 
+#define __DO_ACTION(R, ACTION, FINAL)					\
+									\
+{									\
+	int pin;							\
+	struct irq_pin_list *entry = irq_2_pin + irq;			\
+									\
+	for (;;) {							\
+		unsigned int reg;					\
+		pin = entry->pin;					\
+		if (pin == -1)						\
+			break;						\
+		reg = io_apic_read(entry->apic, 0x10 + R + pin*2);	\
+		reg ACTION;						\
+		io_apic_modify(entry->apic, reg);			\
+		if (!entry->next)					\
+			break;						\
+		entry = irq_2_pin + entry->next;			\
+	}								\
+	FINAL;								\
+}
+
+#ifdef CONFIG_SMP
+static void set_ioapic_affinity_irq(unsigned int irq, cpumask_t mask)
+{
+	unsigned long flags;
+	unsigned int dest;
+	cpumask_t tmp;
+
+	cpus_and(tmp, mask, cpu_online_map);
+	if (cpus_empty(tmp))
+		tmp = TARGET_CPUS;
+
+	cpus_and(mask, tmp, CPU_MASK_ALL);
+
+	dest = cpu_mask_to_apicid(mask);
+
+	/*
+	 * Only the high 8 bits are valid.
+	 */
+	dest = SET_APIC_LOGICAL_ID(dest);
+
+	spin_lock_irqsave(&ioapic_lock, flags);
+	__DO_ACTION(1, = dest, )
+	set_irq_info(irq, mask);
+	spin_unlock_irqrestore(&ioapic_lock, flags);
+}
+#endif
+
 /*
  * The common case is 1:1 IRQ<->pin mappings. Sometimes there are
  * shared ISA-space IRQs, so we have to support them. We are super
@@ -101,26 +149,6 @@ static void add_pin_to_irq(unsigned int irq, int apic, int pin)
 	entry->pin = pin;
 }
 
-#define __DO_ACTION(R, ACTION, FINAL)					\
-									\
-{									\
-	int pin;							\
-	struct irq_pin_list *entry = irq_2_pin + irq;			\
-									\
-	for (;;) {							\
-		unsigned int reg;					\
-		pin = entry->pin;					\
-		if (pin == -1)						\
-			break;						\
-		reg = io_apic_read(entry->apic, 0x10 + R + pin*2);	\
-		reg ACTION;						\
-		io_apic_modify(entry->apic, reg);			\
-		if (!entry->next)					\
-			break;						\
-		entry = irq_2_pin + entry->next;			\
-	}								\
-	FINAL;								\
-}
 
 #define DO_ACTION(name,R,ACTION, FINAL)					\
 									\
@@ -655,7 +683,7 @@ static inline int IO_APIC_irq_trigger(int irq)
 }
 
 /* irq_vectors is indexed by the sum of all RTEs in all I/O APICs. */
-u8 irq_vector[NR_IRQ_VECTORS] = { FIRST_DEVICE_VECTOR , 0 };
+u8 irq_vector[NR_IRQ_VECTORS] __read_mostly = { FIRST_DEVICE_VECTOR , 0 };
 
 int assign_irq_vector(int irq)
 {
@@ -767,6 +795,7 @@ static void __init setup_IO_APIC_irqs(void)
 		spin_lock_irqsave(&ioapic_lock, flags);
 		io_apic_write(apic, 0x11+2*pin, *(((int *)&entry)+1));
 		io_apic_write(apic, 0x10+2*pin, *(((int *)&entry)+0));
+		set_native_irq_info(irq, TARGET_CPUS);
 		spin_unlock_irqrestore(&ioapic_lock, flags);
 	}
 	}
@@ -1314,6 +1343,7 @@ static unsigned int startup_edge_ioapic_irq(unsigned int irq)
  */
 static void ack_edge_ioapic_irq(unsigned int irq)
 {
+	move_irq(irq);
 	if ((irq_desc[irq].status & (IRQ_PENDING | IRQ_DISABLED))
 					== (IRQ_PENDING | IRQ_DISABLED))
 		mask_IO_APIC_irq(irq);
@@ -1343,26 +1373,10 @@ static unsigned int startup_level_ioapic_irq (unsigned int irq)
 
 static void end_level_ioapic_irq (unsigned int irq)
 {
+	move_irq(irq);
 	ack_APIC_irq();
 }
 
-static void set_ioapic_affinity_irq(unsigned int irq, cpumask_t mask)
-{
-	unsigned long flags;
-	unsigned int dest;
-
-	dest = cpu_mask_to_apicid(mask);
-
-	/*
-	 * Only the high 8 bits are valid.
-	 */
-	dest = SET_APIC_LOGICAL_ID(dest);
-
-	spin_lock_irqsave(&ioapic_lock, flags);
-	__DO_ACTION(1, = dest, )
-	spin_unlock_irqrestore(&ioapic_lock, flags);
-}
-
 #ifdef CONFIG_PCI_MSI
 static unsigned int startup_edge_ioapic_vector(unsigned int vector)
 {
@@ -1375,6 +1389,7 @@ static void ack_edge_ioapic_vector(unsigned int vector)
 {
 	int irq = vector_to_irq(vector);
 
+	move_native_irq(vector);
 	ack_edge_ioapic_irq(irq);
 }
 
@@ -1389,6 +1404,7 @@ static void end_level_ioapic_vector (unsigned int vector)
 {
 	int irq = vector_to_irq(vector);
 
+	move_native_irq(vector);
 	end_level_ioapic_irq(irq);
 }
 
@@ -1406,14 +1422,17 @@ static void unmask_IO_APIC_vector (unsigned int vector)
 	unmask_IO_APIC_irq(irq);
 }
 
+#ifdef CONFIG_SMP
 static void set_ioapic_affinity_vector (unsigned int vector,
 					cpumask_t cpu_mask)
 {
 	int irq = vector_to_irq(vector);
 
+	set_native_irq_info(vector, cpu_mask);
 	set_ioapic_affinity_irq(irq, cpu_mask);
 }
-#endif
+#endif // CONFIG_SMP
+#endif // CONFIG_PCI_MSI
 
 /*
  * Level and edge triggered IO-APIC interrupts need different handling,
@@ -1424,7 +1443,7 @@ static void set_ioapic_affinity_vector (unsigned int vector,
  * races.
  */
 
-static struct hw_interrupt_type ioapic_edge_type = {
+static struct hw_interrupt_type ioapic_edge_type __read_mostly = {
 	.typename = "IO-APIC-edge",
 	.startup 	= startup_edge_ioapic,
 	.shutdown 	= shutdown_edge_ioapic,
@@ -1432,10 +1451,12 @@ static struct hw_interrupt_type ioapic_edge_type = {
 	.disable 	= disable_edge_ioapic,
 	.ack 		= ack_edge_ioapic,
 	.end 		= end_edge_ioapic,
+#ifdef CONFIG_SMP
 	.set_affinity = set_ioapic_affinity,
+#endif
 };
 
-static struct hw_interrupt_type ioapic_level_type = {
+static struct hw_interrupt_type ioapic_level_type __read_mostly = {
 	.typename = "IO-APIC-level",
 	.startup 	= startup_level_ioapic,
 	.shutdown 	= shutdown_level_ioapic,
@@ -1443,7 +1464,9 @@ static struct hw_interrupt_type ioapic_level_type = {
 	.disable 	= disable_level_ioapic,
 	.ack 		= mask_and_ack_level_ioapic,
 	.end 		= end_level_ioapic,
+#ifdef CONFIG_SMP
 	.set_affinity = set_ioapic_affinity,
+#endif
 };
 
 static inline void init_IO_APIC_traps(void)
@@ -1506,7 +1529,7 @@ static void ack_lapic_irq (unsigned int irq)
 
 static void end_lapic_irq (unsigned int i) { /* nothing */ }
 
-static struct hw_interrupt_type lapic_irq_type = {
+static struct hw_interrupt_type lapic_irq_type __read_mostly = {
 	.typename = "local-APIC-edge",
 	.startup = NULL, /* startup_irq() not used for IRQ0 */
 	.shutdown = NULL, /* shutdown_irq() not used for IRQ0 */
@@ -1918,6 +1941,7 @@ int io_apic_set_pci_routing (int ioapic, int pin, int irq, int edge_level, int a
 	spin_lock_irqsave(&ioapic_lock, flags);
 	io_apic_write(ioapic, 0x11+2*pin, *(((int *)&entry)+1));
 	io_apic_write(ioapic, 0x10+2*pin, *(((int *)&entry)+0));
+	set_native_irq_info(use_pci_vector() ?  entry.vector : irq, TARGET_CPUS);
 	spin_unlock_irqrestore(&ioapic_lock, flags);
 
 	return 0;
@@ -1931,6 +1955,7 @@ int io_apic_set_pci_routing (int ioapic, int pin, int irq, int edge_level, int a
  * we need to reprogram the ioredtbls to cater for the cpus which have come online
  * so mask in all cases should simply be TARGET_CPUS
  */
+#ifdef CONFIG_SMP
 void __init setup_ioapic_dest(void)
 {
 	int pin, ioapic, irq, irq_entry;
@@ -1949,3 +1974,4 @@ void __init setup_ioapic_dest(void)
 
 	}
 }
+#endif
diff --git a/arch/x86_64/kernel/kprobes.c b/arch/x86_64/kernel/kprobes.c
index 5c6dc7051482..df08c43276a0 100644
--- a/arch/x86_64/kernel/kprobes.c
+++ b/arch/x86_64/kernel/kprobes.c
@@ -74,7 +74,7 @@ static inline int is_IF_modifier(kprobe_opcode_t *insn)
 	return 0;
 }
 
-int arch_prepare_kprobe(struct kprobe *p)
+int __kprobes arch_prepare_kprobe(struct kprobe *p)
 {
 	/* insn: must be on special executable page on x86_64. */
 	up(&kprobe_mutex);
@@ -189,7 +189,7 @@ static inline s32 *is_riprel(u8 *insn)
 	return NULL;
 }
 
-void arch_copy_kprobe(struct kprobe *p)
+void __kprobes arch_copy_kprobe(struct kprobe *p)
 {
 	s32 *ripdisp;
 	memcpy(p->ainsn.insn, p->addr, MAX_INSN_SIZE);
@@ -215,21 +215,21 @@ void arch_copy_kprobe(struct kprobe *p)
 	p->opcode = *p->addr;
 }
 
-void arch_arm_kprobe(struct kprobe *p)
+void __kprobes arch_arm_kprobe(struct kprobe *p)
 {
 	*p->addr = BREAKPOINT_INSTRUCTION;
 	flush_icache_range((unsigned long) p->addr,
 			   (unsigned long) p->addr + sizeof(kprobe_opcode_t));
 }
 
-void arch_disarm_kprobe(struct kprobe *p)
+void __kprobes arch_disarm_kprobe(struct kprobe *p)
 {
 	*p->addr = p->opcode;
 	flush_icache_range((unsigned long) p->addr,
 			   (unsigned long) p->addr + sizeof(kprobe_opcode_t));
 }
 
-void arch_remove_kprobe(struct kprobe *p)
+void __kprobes arch_remove_kprobe(struct kprobe *p)
 {
 	up(&kprobe_mutex);
 	free_insn_slot(p->ainsn.insn);
@@ -261,7 +261,7 @@ static inline void set_current_kprobe(struct kprobe *p, struct pt_regs *regs)
 		kprobe_saved_rflags &= ~IF_MASK;
 }
 
-static void prepare_singlestep(struct kprobe *p, struct pt_regs *regs)
+static void __kprobes prepare_singlestep(struct kprobe *p, struct pt_regs *regs)
 {
 	regs->eflags |= TF_MASK;
 	regs->eflags &= ~IF_MASK;
@@ -272,7 +272,8 @@ static void prepare_singlestep(struct kprobe *p, struct pt_regs *regs)
 		regs->rip = (unsigned long)p->ainsn.insn;
 }
 
-void arch_prepare_kretprobe(struct kretprobe *rp, struct pt_regs *regs)
+void __kprobes arch_prepare_kretprobe(struct kretprobe *rp,
+				      struct pt_regs *regs)
 {
 	unsigned long *sara = (unsigned long *)regs->rsp;
         struct kretprobe_instance *ri;
@@ -295,7 +296,7 @@ void arch_prepare_kretprobe(struct kretprobe *rp, struct pt_regs *regs)
  * Interrupts are disabled on entry as trap3 is an interrupt gate and they
  * remain disabled thorough out this function.
  */
-int kprobe_handler(struct pt_regs *regs)
+int __kprobes kprobe_handler(struct pt_regs *regs)
 {
 	struct kprobe *p;
 	int ret = 0;
@@ -310,7 +311,8 @@ int kprobe_handler(struct pt_regs *regs)
 		   Disarm the probe we just hit, and ignore it. */
 		p = get_kprobe(addr);
 		if (p) {
-			if (kprobe_status == KPROBE_HIT_SS) {
+			if (kprobe_status == KPROBE_HIT_SS &&
+				*p->ainsn.insn == BREAKPOINT_INSTRUCTION) {
 				regs->eflags &= ~TF_MASK;
 				regs->eflags |= kprobe_saved_rflags;
 				unlock_kprobes();
@@ -360,7 +362,10 @@ int kprobe_handler(struct pt_regs *regs)
 			 * either a probepoint or a debugger breakpoint
 			 * at this address.  In either case, no further
 			 * handling of this interrupt is appropriate.
+			 * Back up over the (now missing) int3 and run
+			 * the original instruction.
 			 */
+			regs->rip = (unsigned long)addr;
 			ret = 1;
 		}
 		/* Not one of ours: let kernel handle it */
@@ -399,7 +404,7 @@ no_kprobe:
 /*
  * Called when we hit the probe point at kretprobe_trampoline
  */
-int trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs)
+int __kprobes trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs)
 {
         struct kretprobe_instance *ri = NULL;
         struct hlist_head *head;
@@ -478,7 +483,7 @@ int trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs)
  * that is atop the stack is the address following the copied instruction.
  * We need to make it the address following the original instruction.
  */
-static void resume_execution(struct kprobe *p, struct pt_regs *regs)
+static void __kprobes resume_execution(struct kprobe *p, struct pt_regs *regs)
 {
 	unsigned long *tos = (unsigned long *)regs->rsp;
 	unsigned long next_rip = 0;
@@ -536,7 +541,7 @@ static void resume_execution(struct kprobe *p, struct pt_regs *regs)
  * Interrupts are disabled on entry as trap1 is an interrupt gate and they
  * remain disabled thoroughout this function.  And we hold kprobe lock.
  */
-int post_kprobe_handler(struct pt_regs *regs)
+int __kprobes post_kprobe_handler(struct pt_regs *regs)
 {
 	if (!kprobe_running())
 		return 0;
@@ -571,7 +576,7 @@ out:
 }
 
 /* Interrupts disabled, kprobe_lock held. */
-int kprobe_fault_handler(struct pt_regs *regs, int trapnr)
+int __kprobes kprobe_fault_handler(struct pt_regs *regs, int trapnr)
 {
 	if (current_kprobe->fault_handler
 	    && current_kprobe->fault_handler(current_kprobe, regs, trapnr))
@@ -590,8 +595,8 @@ int kprobe_fault_handler(struct pt_regs *regs, int trapnr)
 /*
  * Wrapper routine for handling exceptions.
  */
-int kprobe_exceptions_notify(struct notifier_block *self, unsigned long val,
-			     void *data)
+int __kprobes kprobe_exceptions_notify(struct notifier_block *self,
+				       unsigned long val, void *data)
 {
 	struct die_args *args = (struct die_args *)data;
 	switch (val) {
@@ -619,7 +624,7 @@ int kprobe_exceptions_notify(struct notifier_block *self, unsigned long val,
 	return NOTIFY_DONE;
 }
 
-int setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs)
+int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs)
 {
 	struct jprobe *jp = container_of(p, struct jprobe, kp);
 	unsigned long addr;
@@ -640,7 +645,7 @@ int setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs)
 	return 1;
 }
 
-void jprobe_return(void)
+void __kprobes jprobe_return(void)
 {
 	preempt_enable_no_resched();
 	asm volatile ("       xchg   %%rbx,%%rsp     \n"
@@ -651,7 +656,7 @@ void jprobe_return(void)
 		      (jprobe_saved_rsp):"memory");
 }
 
-int longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
+int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
 {
 	u8 *addr = (u8 *) (regs->rip - 1);
 	unsigned long stack_addr = (unsigned long)jprobe_saved_rsp;
diff --git a/arch/x86_64/kernel/nmi.c b/arch/x86_64/kernel/nmi.c
index 4e44d6e6b7e5..caf164959e19 100644
--- a/arch/x86_64/kernel/nmi.c
+++ b/arch/x86_64/kernel/nmi.c
@@ -290,7 +290,7 @@ void enable_timer_nmi_watchdog(void)
 
 static int nmi_pm_active; /* nmi_active before suspend */
 
-static int lapic_nmi_suspend(struct sys_device *dev, u32 state)
+static int lapic_nmi_suspend(struct sys_device *dev, pm_message_t state)
 {
 	nmi_pm_active = nmi_active;
 	disable_lapic_nmi_watchdog();
@@ -463,6 +463,8 @@ void touch_nmi_watchdog (void)
 	 */
 	for (i = 0; i < NR_CPUS; i++)
 		per_cpu(nmi_touch, i) = 1;
+
+ 	touch_softlockup_watchdog();
 }
 
 void nmi_watchdog_tick (struct pt_regs * regs, unsigned reason)
@@ -522,14 +524,14 @@ asmlinkage void do_nmi(struct pt_regs * regs, long error_code)
 
 	nmi_enter();
 	add_pda(__nmi_count,1);
-	if (!nmi_callback(regs, cpu))
+	if (!rcu_dereference(nmi_callback)(regs, cpu))
 		default_do_nmi(regs);
 	nmi_exit();
 }
 
 void set_nmi_callback(nmi_callback_t callback)
 {
-	nmi_callback = callback;
+	rcu_assign_pointer(nmi_callback, callback);
 }
 
 void unset_nmi_callback(void)
diff --git a/arch/x86_64/kernel/process.c b/arch/x86_64/kernel/process.c
index 7577f9d7a75d..8661f82ac70b 100644
--- a/arch/x86_64/kernel/process.c
+++ b/arch/x86_64/kernel/process.c
@@ -310,6 +310,7 @@ void __show_regs(struct pt_regs * regs)
 
 void show_regs(struct pt_regs *regs)
 {
+	printk("CPU %d:", smp_processor_id());
 	__show_regs(regs);
 	show_trace(&regs->rsp);
 }
diff --git a/arch/x86_64/kernel/semaphore.c b/arch/x86_64/kernel/semaphore.c
deleted file mode 100644
index 48f7c18172b9..000000000000
--- a/arch/x86_64/kernel/semaphore.c
+++ /dev/null
@@ -1,180 +0,0 @@
-/*
- * x86_64 semaphore implementation.
- *
- * (C) Copyright 1999 Linus Torvalds
- *
- * Portions Copyright 1999 Red Hat, Inc.
- *
- *	This program is free software; you can redistribute it and/or
- *	modify it under the terms of the GNU General Public License
- *	as published by the Free Software Foundation; either version
- *	2 of the License, or (at your option) any later version.
- *
- * rw semaphores implemented November 1999 by Benjamin LaHaise <bcrl@kvack.org>
- */
-#include <linux/config.h>
-#include <linux/sched.h>
-#include <linux/init.h>
-#include <asm/errno.h>
-
-#include <asm/semaphore.h>
-
-/*
- * Semaphores are implemented using a two-way counter:
- * The "count" variable is decremented for each process
- * that tries to acquire the semaphore, while the "sleeping"
- * variable is a count of such acquires.
- *
- * Notably, the inline "up()" and "down()" functions can
- * efficiently test if they need to do any extra work (up
- * needs to do something only if count was negative before
- * the increment operation.
- *
- * "sleeping" and the contention routine ordering is protected
- * by the spinlock in the semaphore's waitqueue head.
- *
- * Note that these functions are only called when there is
- * contention on the lock, and as such all this is the
- * "non-critical" part of the whole semaphore business. The
- * critical part is the inline stuff in <asm/semaphore.h>
- * where we want to avoid any extra jumps and calls.
- */
-
-/*
- * Logic:
- *  - only on a boundary condition do we need to care. When we go
- *    from a negative count to a non-negative, we wake people up.
- *  - when we go from a non-negative count to a negative do we
- *    (a) synchronize with the "sleeper" count and (b) make sure
- *    that we're on the wakeup list before we synchronize so that
- *    we cannot lose wakeup events.
- */
-
-void __up(struct semaphore *sem)
-{
-	wake_up(&sem->wait);
-}
-
-void __sched __down(struct semaphore * sem)
-{
-	struct task_struct *tsk = current;
-	DECLARE_WAITQUEUE(wait, tsk);
-	unsigned long flags;
-
-	tsk->state = TASK_UNINTERRUPTIBLE;
-	spin_lock_irqsave(&sem->wait.lock, flags);
-	add_wait_queue_exclusive_locked(&sem->wait, &wait);
-
-	sem->sleepers++;
-	for (;;) {
-		int sleepers = sem->sleepers;
-
-		/*
-		 * Add "everybody else" into it. They aren't
-		 * playing, because we own the spinlock in
-		 * the wait_queue_head.
-		 */
-		if (!atomic_add_negative(sleepers - 1, &sem->count)) {
-			sem->sleepers = 0;
-			break;
-		}
-		sem->sleepers = 1;	/* us - see -1 above */
-		spin_unlock_irqrestore(&sem->wait.lock, flags);
-
-		schedule();
-
-		spin_lock_irqsave(&sem->wait.lock, flags);
-		tsk->state = TASK_UNINTERRUPTIBLE;
-	}
-	remove_wait_queue_locked(&sem->wait, &wait);
-	wake_up_locked(&sem->wait);
-	spin_unlock_irqrestore(&sem->wait.lock, flags);
-	tsk->state = TASK_RUNNING;
-}
-
-int __sched __down_interruptible(struct semaphore * sem)
-{
-	int retval = 0;
-	struct task_struct *tsk = current;
-	DECLARE_WAITQUEUE(wait, tsk);
-	unsigned long flags;
-
-	tsk->state = TASK_INTERRUPTIBLE;
-	spin_lock_irqsave(&sem->wait.lock, flags);
-	add_wait_queue_exclusive_locked(&sem->wait, &wait);
-
-	sem->sleepers++;
-	for (;;) {
-		int sleepers = sem->sleepers;
-
-		/*
-		 * With signals pending, this turns into
-		 * the trylock failure case - we won't be
-		 * sleeping, and we* can't get the lock as
-		 * it has contention. Just correct the count
-		 * and exit.
-		 */
-		if (signal_pending(current)) {
-			retval = -EINTR;
-			sem->sleepers = 0;
-			atomic_add(sleepers, &sem->count);
-			break;
-		}
-
-		/*
-		 * Add "everybody else" into it. They aren't
-		 * playing, because we own the spinlock in
-		 * wait_queue_head. The "-1" is because we're
-		 * still hoping to get the semaphore.
-		 */
-		if (!atomic_add_negative(sleepers - 1, &sem->count)) {
-			sem->sleepers = 0;
-			break;
-		}
-		sem->sleepers = 1;	/* us - see -1 above */
-		spin_unlock_irqrestore(&sem->wait.lock, flags);
-
-		schedule();
-
-		spin_lock_irqsave(&sem->wait.lock, flags);
-		tsk->state = TASK_INTERRUPTIBLE;
-	}
-	remove_wait_queue_locked(&sem->wait, &wait);
-	wake_up_locked(&sem->wait);
-	spin_unlock_irqrestore(&sem->wait.lock, flags);
-
-	tsk->state = TASK_RUNNING;
-	return retval;
-}
-
-/*
- * Trylock failed - make sure we correct for
- * having decremented the count.
- *
- * We could have done the trylock with a
- * single "cmpxchg" without failure cases,
- * but then it wouldn't work on a 386.
- */
-int __down_trylock(struct semaphore * sem)
-{
-	int sleepers;
-	unsigned long flags;
-
-	spin_lock_irqsave(&sem->wait.lock, flags);
-	sleepers = sem->sleepers + 1;
-	sem->sleepers = 0;
-
-	/*
-	 * Add "everybody else" and us into it. They aren't
-	 * playing, because we own the spinlock in the
-	 * wait_queue_head.
-	 */
-	if (!atomic_add_negative(sleepers, &sem->count)) {
-		wake_up_locked(&sem->wait);
-	}
-
-	spin_unlock_irqrestore(&sem->wait.lock, flags);
-	return 1;
-}
-
-
diff --git a/arch/x86_64/kernel/setup.c b/arch/x86_64/kernel/setup.c
index cfcebc8ab7b4..0511d8087910 100644
--- a/arch/x86_64/kernel/setup.c
+++ b/arch/x86_64/kernel/setup.c
@@ -65,7 +65,7 @@
  * Machine setup..
  */
 
-struct cpuinfo_x86 boot_cpu_data;
+struct cpuinfo_x86 boot_cpu_data __read_mostly;
 
 unsigned long mmu_cr4_features;
 
diff --git a/arch/x86_64/kernel/setup64.c b/arch/x86_64/kernel/setup64.c
index 34082c1cc41e..e3ffcacc8c90 100644
--- a/arch/x86_64/kernel/setup64.c
+++ b/arch/x86_64/kernel/setup64.c
@@ -36,7 +36,7 @@ struct desc_ptr idt_descr = { 256 * 16, (unsigned long) idt_table };
 
 char boot_cpu_stack[IRQSTACKSIZE] __attribute__((section(".bss.page_aligned")));
 
-unsigned long __supported_pte_mask = ~0UL;
+unsigned long __supported_pte_mask __read_mostly = ~0UL;
 static int do_not_nx __initdata = 0;
 
 /* noexec=on|off
diff --git a/arch/x86_64/kernel/smpboot.c b/arch/x86_64/kernel/smpboot.c
index fa25e39fe54d..90aeccd15190 100644
--- a/arch/x86_64/kernel/smpboot.c
+++ b/arch/x86_64/kernel/smpboot.c
@@ -62,13 +62,13 @@
 /* Number of siblings per CPU package */
 int smp_num_siblings = 1;
 /* Package ID of each logical CPU */
-u8 phys_proc_id[NR_CPUS] = { [0 ... NR_CPUS-1] = BAD_APICID };
-u8 cpu_core_id[NR_CPUS] = { [0 ... NR_CPUS-1] = BAD_APICID };
+u8 phys_proc_id[NR_CPUS] __read_mostly = { [0 ... NR_CPUS-1] = BAD_APICID };
+u8 cpu_core_id[NR_CPUS] __read_mostly = { [0 ... NR_CPUS-1] = BAD_APICID };
 EXPORT_SYMBOL(phys_proc_id);
 EXPORT_SYMBOL(cpu_core_id);
 
 /* Bitmask of currently online CPUs */
-cpumask_t cpu_online_map;
+cpumask_t cpu_online_map __read_mostly;
 
 EXPORT_SYMBOL(cpu_online_map);
 
@@ -88,8 +88,8 @@ struct cpuinfo_x86 cpu_data[NR_CPUS] __cacheline_aligned;
 /* Set when the idlers are all forked */
 int smp_threads_ready;
 
-cpumask_t cpu_sibling_map[NR_CPUS] __cacheline_aligned;
-cpumask_t cpu_core_map[NR_CPUS] __cacheline_aligned;
+cpumask_t cpu_sibling_map[NR_CPUS] __read_mostly;
+cpumask_t cpu_core_map[NR_CPUS] __read_mostly;
 EXPORT_SYMBOL(cpu_core_map);
 
 /*
diff --git a/arch/x86_64/kernel/time.c b/arch/x86_64/kernel/time.c
index 66bf6ddeb0c3..7b6abe058253 100644
--- a/arch/x86_64/kernel/time.c
+++ b/arch/x86_64/kernel/time.c
@@ -176,10 +176,7 @@ int do_settimeofday(struct timespec *tv)
 	set_normalized_timespec(&xtime, sec, nsec);
 	set_normalized_timespec(&wall_to_monotonic, wtm_sec, wtm_nsec);
 
-	time_adjust = 0;		/* stop active adjtime() */
-	time_status |= STA_UNSYNC;
-	time_maxerror = NTP_PHASE_LIMIT;
-	time_esterror = NTP_PHASE_LIMIT;
+	ntp_clear();
 
 	write_sequnlock_irq(&xtime_lock);
 	clock_was_set();
@@ -471,7 +468,7 @@ static irqreturn_t timer_interrupt(int irq, void *dev_id, struct pt_regs *regs)
  * off) isn't likely to go away much sooner anyway.
  */
 
-	if ((~time_status & STA_UNSYNC) && xtime.tv_sec > rtc_update &&
+	if (ntp_synced() && xtime.tv_sec > rtc_update &&
 		abs(xtime.tv_nsec - 500000000) <= tick_nsec / 2) {
 		set_rtc_mmss(xtime.tv_sec);
 		rtc_update = xtime.tv_sec + 660;
@@ -1041,6 +1038,7 @@ static int timer_resume(struct sys_device *dev)
 	write_sequnlock_irqrestore(&xtime_lock,flags);
 	jiffies += sleep_length;
 	wall_jiffies += sleep_length;
+	touch_softlockup_watchdog();
 	return 0;
 }
 
diff --git a/arch/x86_64/kernel/traps.c b/arch/x86_64/kernel/traps.c
index 6ead433a3885..f238d6078a5a 100644
--- a/arch/x86_64/kernel/traps.c
+++ b/arch/x86_64/kernel/traps.c
@@ -29,6 +29,7 @@
 #include <linux/module.h>
 #include <linux/moduleparam.h>
 #include <linux/nmi.h>
+#include <linux/kprobes.h>
 
 #include <asm/system.h>
 #include <asm/uaccess.h>
@@ -419,8 +420,9 @@ void die_nmi(char *str, struct pt_regs *regs)
 	do_exit(SIGSEGV);
 }
 
-static void do_trap(int trapnr, int signr, char *str, 
-			   struct pt_regs * regs, long error_code, siginfo_t *info)
+static void __kprobes do_trap(int trapnr, int signr, char *str,
+			      struct pt_regs * regs, long error_code,
+			      siginfo_t *info)
 {
 	conditional_sti(regs);
 
@@ -504,7 +506,8 @@ DO_ERROR(18, SIGSEGV, "reserved", reserved)
 DO_ERROR(12, SIGBUS,  "stack segment", stack_segment)
 DO_ERROR( 8, SIGSEGV, "double fault", double_fault)
 
-asmlinkage void do_general_protection(struct pt_regs * regs, long error_code)
+asmlinkage void __kprobes do_general_protection(struct pt_regs * regs,
+						long error_code)
 {
 	conditional_sti(regs);
 
@@ -622,7 +625,7 @@ asmlinkage void default_do_nmi(struct pt_regs *regs)
 		io_check_error(reason, regs);
 }
 
-asmlinkage void do_int3(struct pt_regs * regs, long error_code)
+asmlinkage void __kprobes do_int3(struct pt_regs * regs, long error_code)
 {
 	if (notify_die(DIE_INT3, "int3", regs, error_code, 3, SIGTRAP) == NOTIFY_STOP) {
 		return;
@@ -653,7 +656,8 @@ asmlinkage struct pt_regs *sync_regs(struct pt_regs *eregs)
 }
 
 /* runs on IST stack. */
-asmlinkage void do_debug(struct pt_regs * regs, unsigned long error_code)
+asmlinkage void __kprobes do_debug(struct pt_regs * regs,
+				   unsigned long error_code)
 {
 	unsigned long condition;
 	struct task_struct *tsk = current;
diff --git a/arch/x86_64/kernel/vmlinux.lds.S b/arch/x86_64/kernel/vmlinux.lds.S
index 2a94f9b60b2d..d4abb07af52d 100644
--- a/arch/x86_64/kernel/vmlinux.lds.S
+++ b/arch/x86_64/kernel/vmlinux.lds.S
@@ -21,6 +21,7 @@ SECTIONS
 	*(.text)
 	SCHED_TEXT
 	LOCK_TEXT
+	KPROBES_TEXT
 	*(.fixup)
 	*(.gnu.warning)
 	} = 0x9090
diff --git a/arch/x86_64/mm/fault.c b/arch/x86_64/mm/fault.c
index ca914c3bd49c..816732d8858c 100644
--- a/arch/x86_64/mm/fault.c
+++ b/arch/x86_64/mm/fault.c
@@ -23,6 +23,7 @@
 #include <linux/vt_kern.h>		/* For unblank_screen() */
 #include <linux/compiler.h>
 #include <linux/module.h>
+#include <linux/kprobes.h>
 
 #include <asm/system.h>
 #include <asm/uaccess.h>
@@ -294,7 +295,8 @@ int exception_trace = 1;
  *	bit 2 == 0 means kernel, 1 means user-mode
  *      bit 3 == 1 means fault was an instruction fetch
  */
-asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long error_code)
+asmlinkage void __kprobes do_page_fault(struct pt_regs *regs,
+					unsigned long error_code)
 {
 	struct task_struct *tsk;
 	struct mm_struct *mm;
diff --git a/arch/x86_64/mm/numa.c b/arch/x86_64/mm/numa.c
index 6a156f5692ae..04f7a33e144c 100644
--- a/arch/x86_64/mm/numa.c
+++ b/arch/x86_64/mm/numa.c
@@ -22,14 +22,14 @@
 #define Dprintk(x...)
 #endif
 
-struct pglist_data *node_data[MAX_NUMNODES];
+struct pglist_data *node_data[MAX_NUMNODES] __read_mostly;
 bootmem_data_t plat_node_bdata[MAX_NUMNODES];
 
 int memnode_shift;
 u8  memnodemap[NODEMAPSIZE];
 
-unsigned char cpu_to_node[NR_CPUS] = { [0 ... NR_CPUS-1] = NUMA_NO_NODE };
-cpumask_t     node_to_cpumask[MAX_NUMNODES];
+unsigned char cpu_to_node[NR_CPUS] __read_mostly = { [0 ... NR_CPUS-1] = NUMA_NO_NODE };
+cpumask_t     node_to_cpumask[MAX_NUMNODES] __read_mostly;
 
 int numa_off __initdata;