Merge branch 'x86/cleanups' into x86/irq

[ merged x86/cleanups into x86/irq to enable a wider IRQ entry code
  patch to be applied, which depends on a cleanup patch in x86/cleanups. ]

25 files changed, 233 insertions, 207 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 93224b5..3cf457f 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -167,9 +167,12 @@ config GENERIC_PENDING_IRQ
 config X86_SMP
 	bool
 	depends on SMP && ((X86_32 && !X86_VOYAGER) || X86_64)
-	select USE_GENERIC_SMP_HELPERS
 	default y
 
+config USE_GENERIC_SMP_HELPERS
+	def_bool y
+	depends on SMP
+
 config X86_32_SMP
 	def_bool y
 	depends on X86_32 && SMP
@@ -239,21 +242,13 @@ config X86_FIND_SMP_CONFIG
 	def_bool y
 	depends on X86_MPPARSE || X86_VOYAGER
 
-if ACPI
 config X86_MPPARSE
-	def_bool y
-	bool "Enable MPS table"
+	bool "Enable MPS table" if ACPI
+	default y
 	depends on X86_LOCAL_APIC
 	help
 	  For old smp systems that do not have proper acpi support. Newer systems
 	  (esp with 64bit cpus) with acpi support, MADT and DSDT will override it
-endif
-
-if !ACPI
-config X86_MPPARSE
-	def_bool y
-	depends on X86_LOCAL_APIC
-endif
 
 choice
 	prompt "Subarchitecture Type"
diff --git a/arch/x86/ia32/ia32_signal.c b/arch/x86/ia32/ia32_signal.c
index 4bc02b2..e82ebd6 100644
--- a/arch/x86/ia32/ia32_signal.c
+++ b/arch/x86/ia32/ia32_signal.c
@@ -572,11 +572,6 @@ int ia32_setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
 	regs->dx = (unsigned long) &frame->info;
 	regs->cx = (unsigned long) &frame->uc;
 
-	/* Make -mregparm=3 work */
-	regs->ax = sig;
-	regs->dx = (unsigned long) &frame->info;
-	regs->cx = (unsigned long) &frame->uc;
-
 	loadsegment(ds, __USER32_DS);
 	loadsegment(es, __USER32_DS);
 
diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h
index 8d676d8..9830681 100644
--- a/arch/x86/include/asm/acpi.h
+++ b/arch/x86/include/asm/acpi.h
@@ -113,7 +113,6 @@ static inline void acpi_disable_pci(void)
 	acpi_pci_disabled = 1;
 	acpi_noirq_set();
 }
-extern int acpi_irq_balance_set(char *str);
 
 /* routines for saving/restoring kernel state */
 extern int acpi_save_state_mem(void);
diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h
index 3600103..9fa9dcd 100644
--- a/arch/x86/include/asm/bitops.h
+++ b/arch/x86/include/asm/bitops.h
@@ -168,7 +168,15 @@ static inline void __change_bit(int nr, volatile unsigned long *addr)
  */
 static inline void change_bit(int nr, volatile unsigned long *addr)
 {
-	asm volatile(LOCK_PREFIX "btc %1,%0" : ADDR : "Ir" (nr));
+	if (IS_IMMEDIATE(nr)) {
+		asm volatile(LOCK_PREFIX "xorb %1,%0"
+			: CONST_MASK_ADDR(nr, addr)
+			: "iq" ((u8)CONST_MASK(nr)));
+	} else {
+		asm volatile(LOCK_PREFIX "btc %1,%0"
+			: BITOP_ADDR(addr)
+			: "Ir" (nr));
+	}
 }
 
 /**
diff --git a/arch/x86/include/asm/byteorder.h b/arch/x86/include/asm/byteorder.h
index e02ae2d..f110ad4 100644
--- a/arch/x86/include/asm/byteorder.h
+++ b/arch/x86/include/asm/byteorder.h
@@ -4,26 +4,33 @@
 #include <asm/types.h>
 #include <linux/compiler.h>
 
-#ifdef __GNUC__
+#define __LITTLE_ENDIAN
 
-#ifdef __i386__
-
-static inline __attribute_const__ __u32 ___arch__swab32(__u32 x)
+static inline __attribute_const__ __u32 __arch_swab32(__u32 val)
 {
-#ifdef CONFIG_X86_BSWAP
-	asm("bswap %0" : "=r" (x) : "0" (x));
-#else
+#ifdef __i386__
+# ifdef CONFIG_X86_BSWAP
+	asm("bswap %0" : "=r" (val) : "0" (val));
+# else
 	asm("xchgb %b0,%h0\n\t"	/* swap lower bytes	*/
 	    "rorl $16,%0\n\t"	/* swap words		*/
 	    "xchgb %b0,%h0"	/* swap higher bytes	*/
-	    : "=q" (x)
-	    : "0" (x));
+	    : "=q" (val)
+	    : "0" (val));
+# endif
+
+#else /* __i386__ */
+	asm("bswapl %0"
+	    : "=r" (val)
+	    : "0" (val));
 #endif
-	return x;
+	return val;
 }
+#define __arch_swab32 __arch_swab32
 
-static inline __attribute_const__ __u64 ___arch__swab64(__u64 val)
+static inline __attribute_const__ __u64 __arch_swab64(__u64 val)
 {
+#ifdef __i386__
 	union {
 		struct {
 			__u32 a;
@@ -32,50 +39,27 @@ static inline __attribute_const__ __u64 ___arch__swab64(__u64 val)
 		__u64 u;
 	} v;
 	v.u = val;
-#ifdef CONFIG_X86_BSWAP
+# ifdef CONFIG_X86_BSWAP
 	asm("bswapl %0 ; bswapl %1 ; xchgl %0,%1"
 	    : "=r" (v.s.a), "=r" (v.s.b)
 	    : "0" (v.s.a), "1" (v.s.b));
-#else
-	v.s.a = ___arch__swab32(v.s.a);
-	v.s.b = ___arch__swab32(v.s.b);
+# else
+	v.s.a = __arch_swab32(v.s.a);
+	v.s.b = __arch_swab32(v.s.b);
 	asm("xchgl %0,%1"
 	    : "=r" (v.s.a), "=r" (v.s.b)
 	    : "0" (v.s.a), "1" (v.s.b));
-#endif
+# endif
 	return v.u;
-}
-
 #else /* __i386__ */
-
-static inline __attribute_const__ __u64 ___arch__swab64(__u64 x)
-{
 	asm("bswapq %0"
-	    : "=r" (x)
-	    : "0" (x));
-	return x;
-}
-
-static inline __attribute_const__ __u32 ___arch__swab32(__u32 x)
-{
-	asm("bswapl %0"
-	    : "=r" (x)
-	    : "0" (x));
-	return x;
-}
-
+	    : "=r" (val)
+	    : "0" (val));
+	return val;
 #endif
+}
+#define __arch_swab64 __arch_swab64
 
-/* Do not define swab16.  Gcc is smart enough to recognize "C" version and
-   convert it into rotation or exhange.  */
-
-#define __arch__swab64(x) ___arch__swab64(x)
-#define __arch__swab32(x) ___arch__swab32(x)
-
-#define __BYTEORDER_HAS_U64__
-
-#endif /* __GNUC__ */
-
-#include <linux/byteorder/little_endian.h>
+#include <linux/byteorder.h>
 
 #endif /* _ASM_X86_BYTEORDER_H */
diff --git a/arch/x86/include/asm/iomap.h b/arch/x86/include/asm/iomap.h
new file mode 100644
index 0000000..c1f0628
--- /dev/null
+++ b/arch/x86/include/asm/iomap.h
@@ -0,0 +1,30 @@
+/*
+ * Copyright © 2008 Ingo Molnar
+ *
+ * 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.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License along
+ * with this program; if not, write to the Free Software Foundation, Inc.,
+ * 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA.
+ */
+
+#include <linux/fs.h>
+#include <linux/mm.h>
+#include <linux/uaccess.h>
+#include <asm/cacheflush.h>
+#include <asm/pgtable.h>
+#include <asm/tlbflush.h>
+
+void *
+iomap_atomic_prot_pfn(unsigned long pfn, enum km_type type, pgprot_t prot);
+
+void
+iounmap_atomic(void *kvaddr, enum km_type type);
diff --git a/arch/x86/include/asm/iommu.h b/arch/x86/include/asm/iommu.h
index e4a552d..0b500c5 100644
--- a/arch/x86/include/asm/iommu.h
+++ b/arch/x86/include/asm/iommu.h
@@ -6,7 +6,6 @@ extern void no_iommu_init(void);
 extern struct dma_mapping_ops nommu_dma_ops;
 extern int force_iommu, no_iommu;
 extern int iommu_detected;
-extern int dmar_disabled;
 
 extern unsigned long iommu_nr_pages(unsigned long addr, unsigned long len);
 
diff --git a/arch/x86/include/asm/irq.h b/arch/x86/include/asm/irq.h
index bae0eda..28e409f 100644
--- a/arch/x86/include/asm/irq.h
+++ b/arch/x86/include/asm/irq.h
@@ -31,10 +31,6 @@ static inline int irq_canonicalize(int irq)
 # endif
 #endif
 
-#ifdef CONFIG_IRQBALANCE
-extern int irqbalance_disable(char *str);
-#endif
-
 #ifdef CONFIG_HOTPLUG_CPU
 #include <linux/cpumask.h>
 extern void fixup_irqs(cpumask_t map);
diff --git a/arch/x86/include/asm/irq_regs_32.h b/arch/x86/include/asm/irq_regs_32.h
index af2f02d..86afd74 100644
--- a/arch/x86/include/asm/irq_regs_32.h
+++ b/arch/x86/include/asm/irq_regs_32.h
@@ -9,6 +9,8 @@
 
 #include <asm/percpu.h>
 
+#define ARCH_HAS_OWN_IRQ_REGS
+
 DECLARE_PER_CPU(struct pt_regs *, irq_regs);
 
 static inline struct pt_regs *get_irq_regs(void)
diff --git a/arch/x86/include/asm/tsc.h b/arch/x86/include/asm/tsc.h
index 9cd83a8..38ae163 100644
--- a/arch/x86/include/asm/tsc.h
+++ b/arch/x86/include/asm/tsc.h
@@ -34,8 +34,6 @@ static inline cycles_t get_cycles(void)
 
 static __always_inline cycles_t vget_cycles(void)
 {
-	cycles_t cycles;
-
 	/*
 	 * We only do VDSOs on TSC capable CPUs, so this shouldnt
 	 * access boot_cpu_data (which is not VDSO-safe):
@@ -44,11 +42,7 @@ static __always_inline cycles_t vget_cycles(void)
 	if (!cpu_has_tsc)
 		return 0;
 #endif
-	rdtsc_barrier();
-	cycles = (cycles_t)__native_read_tsc();
-	rdtsc_barrier();
-
-	return cycles;
+	return (cycles_t)__native_read_tsc();
 }
 
 extern void tsc_init(void);
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index 8c1f76a..4c51a2f 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -1343,7 +1343,6 @@ static void __init acpi_process_madt(void)
 			error = acpi_parse_madt_ioapic_entries();
 			if (!error) {
 				acpi_irq_model = ACPI_IRQ_MODEL_IOAPIC;
-				acpi_irq_balance_set(NULL);
 				acpi_ioapic = 1;
 
 				smp_found_config = 1;
diff --git a/arch/x86/kernel/ds.c b/arch/x86/kernel/ds.c
index 2b69994..d1a1214 100644
--- a/arch/x86/kernel/ds.c
+++ b/arch/x86/kernel/ds.c
@@ -236,17 +236,33 @@ static inline struct ds_context *ds_alloc_context(struct task_struct *task)
 	struct ds_context *context = *p_context;
 
 	if (!context) {
+		spin_unlock(&ds_lock);
+
 		context = kzalloc(sizeof(*context), GFP_KERNEL);
 
-		if (!context)
+		if (!context) {
+			spin_lock(&ds_lock);
 			return NULL;
+		}
 
 		context->ds = kzalloc(ds_cfg.sizeof_ds, GFP_KERNEL);
 		if (!context->ds) {
 			kfree(context);
+			spin_lock(&ds_lock);
 			return NULL;
 		}
 
+		spin_lock(&ds_lock);
+		/*
+		 * Check for race - another CPU could have allocated
+		 * it meanwhile:
+		 */
+		if (*p_context) {
+			kfree(context->ds);
+			kfree(context);
+			return *p_context;
+		}
+
 		*p_context = context;
 
 		context->this = p_context;
@@ -384,14 +400,15 @@ static int ds_request(struct task_struct *task, void *base, size_t size,
 
 	spin_lock(&ds_lock);
 
-	if (!check_tracer(task))
-		return -EPERM;
-
 	error = -ENOMEM;
 	context = ds_alloc_context(task);
 	if (!context)
 		goto out_unlock;
 
+	error = -EPERM;
+	if (!check_tracer(task))
+		goto out_unlock;
+
 	error = -EALREADY;
 	if (context->owner[qual] == current)
 		goto out_unlock;
diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c
index 3ce029f..1b894b7 100644
--- a/arch/x86/kernel/early-quirks.c
+++ b/arch/x86/kernel/early-quirks.c
@@ -188,20 +188,6 @@ static void __init ati_bugs_contd(int num, int slot, int func)
 }
 #endif
 
-#ifdef CONFIG_DMAR
-static void __init intel_g33_dmar(int num, int slot, int func)
-{
-	struct acpi_table_header *dmar_tbl;
-	acpi_status status;
-
-	status = acpi_get_table(ACPI_SIG_DMAR, 0, &dmar_tbl);
-	if (ACPI_SUCCESS(status)) {
-		printk(KERN_INFO "BIOS BUG: DMAR advertised on Intel G31/G33 chipset -- ignoring\n");
-		dmar_disabled = 1;
-	}
-}
-#endif
-
 #define QFLAG_APPLY_ONCE 	0x1
 #define QFLAG_APPLIED		0x2
 #define QFLAG_DONE		(QFLAG_APPLY_ONCE|QFLAG_APPLIED)
@@ -225,10 +211,6 @@ static struct chipset early_qrk[] __initdata = {
 	  PCI_CLASS_SERIAL_SMBUS, PCI_ANY_ID, 0, ati_bugs },
 	{ PCI_VENDOR_ID_ATI, PCI_DEVICE_ID_ATI_SBX00_SMBUS,
 	  PCI_CLASS_SERIAL_SMBUS, PCI_ANY_ID, 0, ati_bugs_contd },
-#ifdef CONFIG_DMAR
-	{ PCI_VENDOR_ID_INTEL, 0x29c0,
-	  PCI_CLASS_BRIDGE_HOST, PCI_ANY_ID, 0, intel_g33_dmar },
-#endif
 	{}
 };
 
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index 369de69..dbf06a0 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -11,15 +11,15 @@
  *
  * NOTE: This code handles signal-recognition, which happens every time
  * after an interrupt and after each system call.
- * 
- * Normal syscalls and interrupts don't save a full stack frame, this is 
+ *
+ * Normal syscalls and interrupts don't save a full stack frame, this is
  * only done for syscall tracing, signals or fork/exec et.al.
- * 
- * A note on terminology:	 
- * - top of stack: Architecture defined interrupt frame from SS to RIP 
- * at the top of the kernel process stack.	
+ *
+ * A note on terminology:
+ * - top of stack: Architecture defined interrupt frame from SS to RIP
+ * at the top of the kernel process stack.
  * - partial stack frame: partially saved registers upto R11.
- * - full stack frame: Like partial stack frame, but all register saved. 
+ * - full stack frame: Like partial stack frame, but all register saved.
  *
  * Some macro usage:
  * - CFI macros are used to generate dwarf2 unwind information for better
@@ -142,7 +142,7 @@ END(mcount)
 
 #ifndef CONFIG_PREEMPT
 #define retint_kernel retint_restore_args
-#endif	
+#endif
 
 #ifdef CONFIG_PARAVIRT
 ENTRY(native_usergs_sysret64)
@@ -161,14 +161,14 @@ ENTRY(native_usergs_sysret64)
 .endm
 
 /*
- * C code is not supposed to know about undefined top of stack. Every time 
- * a C function with an pt_regs argument is called from the SYSCALL based 
+ * C code is not supposed to know about undefined top of stack. Every time
+ * a C function with an pt_regs argument is called from the SYSCALL based
  * fast path FIXUP_TOP_OF_STACK is needed.
  * RESTORE_TOP_OF_STACK syncs the syscall state after any possible ptregs
  * manipulation.
- */        	
-		
-	/* %rsp:at FRAMEEND */ 
+ */
+
+	/* %rsp:at FRAMEEND */
 	.macro FIXUP_TOP_OF_STACK tmp
 	movq	%gs:pda_oldrsp,\tmp
 	movq  	\tmp,RSP(%rsp)
@@ -244,8 +244,8 @@ ENTRY(native_usergs_sysret64)
 	.endm
 /*
  * A newly forked process directly context switches into this.
- */ 	
-/* rdi:	prev */	
+ */
+/* rdi:	prev */
 ENTRY(ret_from_fork)
 	CFI_DEFAULT_STACK
 	push kernel_eflags(%rip)
@@ -256,7 +256,7 @@ ENTRY(ret_from_fork)
 	GET_THREAD_INFO(%rcx)
 	testl $(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT),TI_flags(%rcx)
 	jnz rff_trace
-rff_action:	
+rff_action:
 	RESTORE_REST
 	testl $3,CS-ARGOFFSET(%rsp)	# from kernel_thread?
 	je   int_ret_from_sys_call
@@ -267,7 +267,7 @@ rff_action:
 rff_trace:
 	movq %rsp,%rdi
 	call syscall_trace_leave
-	GET_THREAD_INFO(%rcx)	
+	GET_THREAD_INFO(%rcx)
 	jmp rff_action
 	CFI_ENDPROC
 END(ret_from_fork)
@@ -278,20 +278,20 @@ END(ret_from_fork)
  * SYSCALL does not save anything on the stack and does not change the
  * stack pointer.
  */
-		
+
 /*
- * Register setup:	
+ * Register setup:
  * rax  system call number
  * rdi  arg0
- * rcx  return address for syscall/sysret, C arg3 
+ * rcx  return address for syscall/sysret, C arg3
  * rsi  arg1
- * rdx  arg2	
+ * rdx  arg2
  * r10  arg3 	(--> moved to rcx for C)
  * r8   arg4
  * r9   arg5
  * r11  eflags for syscall/sysret, temporary for C
- * r12-r15,rbp,rbx saved by C code, not touched. 		
- * 
+ * r12-r15,rbp,rbx saved by C code, not touched.
+ *
  * Interrupts are off on entry.
  * Only called from user space.
  *
@@ -301,7 +301,7 @@ END(ret_from_fork)
  * When user can change the frames always force IRET. That is because
  * it deals with uncanonical addresses better. SYSRET has trouble
  * with them due to bugs in both AMD and Intel CPUs.
- */ 			 		
+ */
 
 ENTRY(system_call)
 	CFI_STARTPROC	simple
@@ -317,7 +317,7 @@ ENTRY(system_call)
 	 */
 ENTRY(system_call_after_swapgs)
 
-	movq	%rsp,%gs:pda_oldrsp 
+	movq	%rsp,%gs:pda_oldrsp
 	movq	%gs:pda_kernelstack,%rsp
 	/*
 	 * No need to follow this irqs off/on section - it's straight
@@ -325,7 +325,7 @@ ENTRY(system_call_after_swapgs)
 	 */
 	ENABLE_INTERRUPTS(CLBR_NONE)
 	SAVE_ARGS 8,1
-	movq  %rax,ORIG_RAX-ARGOFFSET(%rsp) 
+	movq  %rax,ORIG_RAX-ARGOFFSET(%rsp)
 	movq  %rcx,RIP-ARGOFFSET(%rsp)
 	CFI_REL_OFFSET rip,RIP-ARGOFFSET
 	GET_THREAD_INFO(%rcx)
@@ -339,19 +339,19 @@ system_call_fastpath:
 	movq %rax,RAX-ARGOFFSET(%rsp)
 /*
  * Syscall return path ending with SYSRET (fast path)
- * Has incomplete stack frame and undefined top of stack. 
- */		
+ * Has incomplete stack frame and undefined top of stack.
+ */
 ret_from_sys_call:
 	movl $_TIF_ALLWORK_MASK,%edi
 	/* edi:	flagmask */
-sysret_check:		
+sysret_check:
 	LOCKDEP_SYS_EXIT
 	GET_THREAD_INFO(%rcx)
 	DISABLE_INTERRUPTS(CLBR_NONE)
 	TRACE_IRQS_OFF
 	movl TI_flags(%rcx),%edx
 	andl %edi,%edx
-	jnz  sysret_careful 
+	jnz  sysret_careful
 	CFI_REMEMBER_STATE
 	/*
 	 * sysretq will re-enable interrupts:
@@ -366,7 +366,7 @@ sysret_check:
 
 	CFI_RESTORE_STATE
 	/* Handle reschedules */
-	/* edx:	work, edi: workmask */	
+	/* edx:	work, edi: workmask */
 sysret_careful:
 	bt $TIF_NEED_RESCHED,%edx
 	jnc sysret_signal
@@ -379,7 +379,7 @@ sysret_careful:
 	CFI_ADJUST_CFA_OFFSET -8
 	jmp sysret_check
 
-	/* Handle a signal */ 
+	/* Handle a signal */
 sysret_signal:
 	TRACE_IRQS_ON
 	ENABLE_INTERRUPTS(CLBR_NONE)
@@ -398,7 +398,7 @@ sysret_signal:
 	DISABLE_INTERRUPTS(CLBR_NONE)
 	TRACE_IRQS_OFF
 	jmp int_with_check
-	
+
 badsys:
 	movq $-ENOSYS,RAX-ARGOFFSET(%rsp)
 	jmp ret_from_sys_call
@@ -437,7 +437,7 @@ sysret_audit:
 #endif	/* CONFIG_AUDITSYSCALL */
 
 	/* Do syscall tracing */
-tracesys:			 
+tracesys:
 #ifdef CONFIG_AUDITSYSCALL
 	testl $(_TIF_WORK_SYSCALL_ENTRY & ~_TIF_SYSCALL_AUDIT),TI_flags(%rcx)
 	jz auditsys
@@ -460,8 +460,8 @@ tracesys:
 	call *sys_call_table(,%rax,8)
 	movq %rax,RAX-ARGOFFSET(%rsp)
 	/* Use IRET because user could have changed frame */
-		
-/* 
+
+/*
  * Syscall return path ending with IRET.
  * Has correct top of stack, but partial stack frame.
  */
@@ -505,18 +505,18 @@ int_very_careful:
 	TRACE_IRQS_ON
 	ENABLE_INTERRUPTS(CLBR_NONE)
 	SAVE_REST
-	/* Check for syscall exit trace */	
+	/* Check for syscall exit trace */
 	testl $_TIF_WORK_SYSCALL_EXIT,%edx
 	jz int_signal
 	pushq %rdi
 	CFI_ADJUST_CFA_OFFSET 8
-	leaq 8(%rsp),%rdi	# &ptregs -> arg1	
+	leaq 8(%rsp),%rdi	# &ptregs -> arg1
 	call syscall_trace_leave
 	popq %rdi
 	CFI_ADJUST_CFA_OFFSET -8
 	andl $~(_TIF_WORK_SYSCALL_EXIT|_TIF_SYSCALL_EMU),%edi
 	jmp int_restore_rest
-	
+
 int_signal:
 	testl $_TIF_DO_NOTIFY_MASK,%edx
 	jz 1f
@@ -531,11 +531,11 @@ int_restore_rest:
 	jmp int_with_check
 	CFI_ENDPROC
 END(system_call)
-		
-/* 
+
+/*
  * Certain special system calls that need to save a complete full stack frame.
- */ 								
-	
+ */
+
 	.macro PTREGSCALL label,func,arg
 	.globl \label
 \label:
@@ -572,7 +572,7 @@ ENTRY(ptregscall_common)
 	ret
 	CFI_ENDPROC
 END(ptregscall_common)
-	
+
 ENTRY(stub_execve)
 	CFI_STARTPROC
 	popq %r11
@@ -588,11 +588,11 @@ ENTRY(stub_execve)
 	jmp int_ret_from_sys_call
 	CFI_ENDPROC
 END(stub_execve)
-	
+
 /*
  * sigreturn is special because it needs to restore all registers on return.
  * This cannot be done with SYSRET, so use the IRET return path instead.
- */                
+ */
 ENTRY(stub_rt_sigreturn)
 	CFI_STARTPROC
 	addq $8, %rsp
@@ -731,12 +731,12 @@ exit_intr:
 	GET_THREAD_INFO(%rcx)
 	testl $3,CS-ARGOFFSET(%rsp)
 	je retint_kernel
-	
+
 	/* Interrupt came from user space */
 	/*
 	 * Has a correct top of stack, but a partial stack frame
 	 * %rcx: thread info. Interrupts off.
-	 */		
+	 */
 retint_with_reschedule:
 	movl $_TIF_WORK_MASK,%edi
 retint_check:
@@ -809,20 +809,20 @@ retint_careful:
 	pushq %rdi
 	CFI_ADJUST_CFA_OFFSET	8
 	call  schedule
-	popq %rdi		
+	popq %rdi
 	CFI_ADJUST_CFA_OFFSET	-8
 	GET_THREAD_INFO(%rcx)
 	DISABLE_INTERRUPTS(CLBR_NONE)
 	TRACE_IRQS_OFF
 	jmp retint_check
-	
+
 retint_signal:
 	testl $_TIF_DO_NOTIFY_MASK,%edx
 	jz    retint_swapgs
 	TRACE_IRQS_ON
 	ENABLE_INTERRUPTS(CLBR_NONE)
 	SAVE_REST
-	movq $-1,ORIG_RAX(%rsp) 			
+	movq $-1,ORIG_RAX(%rsp)
 	xorl %esi,%esi		# oldset
 	movq %rsp,%rdi		# &pt_regs
 	call do_notify_resume
@@ -844,14 +844,14 @@ ENTRY(retint_kernel)
 	jnc  retint_restore_args
 	call preempt_schedule_irq
 	jmp exit_intr
-#endif	
+#endif
 
 	CFI_ENDPROC
 END(common_interrupt)
-	
+
 /*
  * APIC interrupts.
- */		
+ */
 	.macro apicinterrupt num,func
 	INTR_FRAME
 	pushq $~(\num)
@@ -869,14 +869,14 @@ ENTRY(threshold_interrupt)
 	apicinterrupt THRESHOLD_APIC_VECTOR,mce_threshold_interrupt
 END(threshold_interrupt)
 
-#ifdef CONFIG_SMP	
+#ifdef CONFIG_SMP
 ENTRY(reschedule_interrupt)
 	apicinterrupt RESCHEDULE_VECTOR,smp_reschedule_interrupt
 END(reschedule_interrupt)
 
 	.macro INVALIDATE_ENTRY num
 ENTRY(invalidate_interrupt\num)
-	apicinterrupt INVALIDATE_TLB_VECTOR_START+\num,smp_invalidate_interrupt	
+	apicinterrupt INVALIDATE_TLB_VECTOR_START+\num,smp_invalidate_interrupt
 END(invalidate_interrupt\num)
 	.endm
 
@@ -915,22 +915,22 @@ END(error_interrupt)
 ENTRY(spurious_interrupt)
 	apicinterrupt SPURIOUS_APIC_VECTOR,smp_spurious_interrupt
 END(spurious_interrupt)
-				
+
 /*
  * Exception entry points.
- */ 		
+ */
 	.macro zeroentry sym
 	INTR_FRAME
 	PARAVIRT_ADJUST_EXCEPTION_FRAME
-	pushq $0	/* push error code/oldrax */ 
+	pushq $0	/* push error code/oldrax */
 	CFI_ADJUST_CFA_OFFSET 8
-	pushq %rax	/* push real oldrax to the rdi slot */ 
+	pushq %rax	/* push real oldrax to the rdi slot */
 	CFI_ADJUST_CFA_OFFSET 8
 	CFI_REL_OFFSET rax,0
 	leaq  \sym(%rip),%rax
 	jmp error_entry
 	CFI_ENDPROC
-	.endm	
+	.endm
 
 	.macro errorentry sym
 	XCPT_FRAME
@@ -1044,13 +1044,13 @@ paranoid_schedule\trace:
 
 /*
  * Exception entry point. This expects an error code/orig_rax on the stack
- * and the exception handler in %rax.	
- */ 		  				
+ * and the exception handler in %rax.
+ */
 KPROBE_ENTRY(error_entry)
 	_frame RDI
 	CFI_REL_OFFSET rax,0
 	/* rdi slot contains rax, oldrax contains error code */
-	cld	
+	cld
 	subq  $14*8,%rsp
 	CFI_ADJUST_CFA_OFFSET	(14*8)
 	movq %rsi,13*8(%rsp)
@@ -1061,7 +1061,7 @@ KPROBE_ENTRY(error_entry)
 	CFI_REL_OFFSET	rdx,RDX
 	movq %rcx,11*8(%rsp)
 	CFI_REL_OFFSET	rcx,RCX
-	movq %rsi,10*8(%rsp)	/* store rax */ 
+	movq %rsi,10*8(%rsp)	/* store rax */
 	CFI_REL_OFFSET	rax,RAX
 	movq %r8, 9*8(%rsp)
 	CFI_REL_OFFSET	r8,R8
@@ -1071,29 +1071,29 @@ KPROBE_ENTRY(error_entry)
 	CFI_REL_OFFSET	r10,R10
 	movq %r11,6*8(%rsp)
 	CFI_REL_OFFSET	r11,R11
-	movq %rbx,5*8(%rsp) 
+	movq %rbx,5*8(%rsp)
 	CFI_REL_OFFSET	rbx,RBX
-	movq %rbp,4*8(%rsp) 
+	movq %rbp,4*8(%rsp)
 	CFI_REL_OFFSET	rbp,RBP
-	movq %r12,3*8(%rsp) 
+	movq %r12,3*8(%rsp)
 	CFI_REL_OFFSET	r12,R12
-	movq %r13,2*8(%rsp) 
+	movq %r13,2*8(%rsp)
 	CFI_REL_OFFSET	r13,R13
-	movq %r14,1*8(%rsp) 
+	movq %r14,1*8(%rsp)
 	CFI_REL_OFFSET	r14,R14
-	movq %r15,(%rsp) 
+	movq %r15,(%rsp)
 	CFI_REL_OFFSET	r15,R15
-	xorl %ebx,%ebx	
+	xorl %ebx,%ebx
 	testl $3,CS(%rsp)
 	je  error_kernelspace
-error_swapgs:	
+error_swapgs:
 	SWAPGS
 error_sti:
 	TRACE_IRQS_OFF
-	movq %rdi,RDI(%rsp) 	
+	movq %rdi,RDI(%rsp)
 	CFI_REL_OFFSET	rdi,RDI
 	movq %rsp,%rdi
-	movq ORIG_RAX(%rsp),%rsi	/* get error code */ 
+	movq ORIG_RAX(%rsp),%rsi	/* get error code */
 	movq $-1,ORIG_RAX(%rsp)
 	call *%rax
 	/* ebx:	no swapgs flag (1: don't need swapgs, 0: need it) */
@@ -1102,7 +1102,7 @@ error_exit:
 	RESTORE_REST
 	DISABLE_INTERRUPTS(CLBR_NONE)
 	TRACE_IRQS_OFF
-	GET_THREAD_INFO(%rcx)	
+	GET_THREAD_INFO(%rcx)
 	testl %eax,%eax
 	jne  retint_kernel
 	LOCKDEP_SYS_EXIT_IRQ
@@ -1118,7 +1118,7 @@ error_kernelspace:
        /* There are two places in the kernel that can potentially fault with
           usergs. Handle them here. The exception handlers after
 	   iret run with kernel gs again, so don't set the user space flag.
-	   B stepping K8s sometimes report an truncated RIP for IRET 
+	   B stepping K8s sometimes report an truncated RIP for IRET
 	   exceptions returning to compat mode. Check for these here too. */
 	leaq irq_return(%rip),%rcx
 	cmpq %rcx,RIP(%rsp)
@@ -1130,17 +1130,17 @@ error_kernelspace:
         je   error_swapgs
 	jmp  error_sti
 KPROBE_END(error_entry)
-	
+
        /* Reload gs selector with exception handling */
-       /* edi:  new selector */ 
+       /* edi:  new selector */
 ENTRY(native_load_gs_index)
 	CFI_STARTPROC
 	pushf
 	CFI_ADJUST_CFA_OFFSET 8
 	DISABLE_INTERRUPTS(CLBR_ANY | ~(CLBR_RDI))
         SWAPGS
-gs_change:     
-        movl %edi,%gs   
+gs_change:
+        movl %edi,%gs
 2:	mfence		/* workaround */
 	SWAPGS
         popf
@@ -1148,20 +1148,20 @@ gs_change:
         ret
 	CFI_ENDPROC
 ENDPROC(native_load_gs_index)
-       
+
         .section __ex_table,"a"
         .align 8
         .quad gs_change,bad_gs
         .previous
         .section .fixup,"ax"
 	/* running with kernelgs */
-bad_gs: 
+bad_gs:
 	SWAPGS			/* switch back to user gs */
 	xorl %eax,%eax
         movl %eax,%gs
         jmp  2b
-        .previous       
-	
+        .previous
+
 /*
  * Create a kernel thread.
  *
@@ -1184,7 +1184,7 @@ ENTRY(kernel_thread)
 
 	xorl %r8d,%r8d
 	xorl %r9d,%r9d
-	
+
 	# clone now
 	call do_fork
 	movq %rax,RAX(%rsp)
@@ -1195,14 +1195,14 @@ ENTRY(kernel_thread)
 	 * so internally to the x86_64 port you can rely on kernel_thread()
 	 * not to reschedule the child before returning, this avoids the need
 	 * of hacks for example to fork off the per-CPU idle tasks.
-         * [Hopefully no generic code relies on the reschedule -AK]	
+         * [Hopefully no generic code relies on the reschedule -AK]
 	 */
 	RESTORE_ALL
 	UNFAKE_STACK_FRAME
 	ret
 	CFI_ENDPROC
 ENDPROC(kernel_thread)
-	
+
 child_rip:
 	pushq $0		# fake return address
 	CFI_STARTPROC
@@ -1237,10 +1237,10 @@ ENDPROC(child_rip)
 ENTRY(kernel_execve)
 	CFI_STARTPROC
 	FAKE_STACK_FRAME $0
-	SAVE_ALL	
+	SAVE_ALL
 	movq %rsp,%rcx
 	call sys_execve
-	movq %rax, RAX(%rsp)	
+	movq %rax, RAX(%rsp)
 	RESTORE_REST
 	testq %rax,%rax
 	je int_ret_from_sys_call
@@ -1259,7 +1259,7 @@ ENTRY(coprocessor_error)
 END(coprocessor_error)
 
 ENTRY(simd_coprocessor_error)
-	zeroentry do_simd_coprocessor_error	
+	zeroentry do_simd_coprocessor_error
 END(simd_coprocessor_error)
 
 ENTRY(device_not_available)
@@ -1271,12 +1271,12 @@ KPROBE_ENTRY(debug)
  	INTR_FRAME
 	PARAVIRT_ADJUST_EXCEPTION_FRAME
 	pushq $0
-	CFI_ADJUST_CFA_OFFSET 8		
+	CFI_ADJUST_CFA_OFFSET 8
 	paranoidentry do_debug, DEBUG_STACK
 	paranoidexit
 KPROBE_END(debug)
 
-	/* runs on exception stack */	
+	/* runs on exception stack */
 KPROBE_ENTRY(nmi)
 	INTR_FRAME
 	PARAVIRT_ADJUST_EXCEPTION_FRAME
@@ -1310,7 +1310,7 @@ ENTRY(bounds)
 END(bounds)
 
 ENTRY(invalid_op)
-	zeroentry do_invalid_op	
+	zeroentry do_invalid_op
 END(invalid_op)
 
 ENTRY(coprocessor_segment_overrun)
@@ -1365,7 +1365,7 @@ ENTRY(machine_check)
 	INTR_FRAME
 	PARAVIRT_ADJUST_EXCEPTION_FRAME
 	pushq $0
-	CFI_ADJUST_CFA_OFFSET 8	
+	CFI_ADJUST_CFA_OFFSET 8
 	paranoidentry do_machine_check
 	jmp paranoid_exit1
 	CFI_ENDPROC
diff --git a/arch/x86/kernel/es7000_32.c b/arch/x86/kernel/es7000_32.c
index f454c78f..0aa2c44 100644
--- a/arch/x86/kernel/es7000_32.c
+++ b/arch/x86/kernel/es7000_32.c
@@ -250,31 +250,24 @@ int __init find_unisys_acpi_oem_table(unsigned long *oem_addr)
 {
 	struct acpi_table_header *header = NULL;
 	int i = 0;
-	acpi_size tbl_size;
 
-	while (ACPI_SUCCESS(acpi_get_table_with_size("OEM1", i++, &header, &tbl_size))) {
+	while (ACPI_SUCCESS(acpi_get_table("OEM1", i++, &header))) {
 		if (!memcmp((char *) &header->oem_id, "UNISYS", 6)) {
 			struct oem_table *t = (struct oem_table *)header;
 
 			oem_addrX = t->OEMTableAddr;
 			oem_size = t->OEMTableSize;
-			early_acpi_os_unmap_memory(header, tbl_size);
 
 			*oem_addr = (unsigned long)__acpi_map_table(oem_addrX,
 								    oem_size);
 			return 0;
 		}
-		early_acpi_os_unmap_memory(header, tbl_size);
 	}
 	return -1;
 }
 
 void __init unmap_unisys_acpi_oem_table(unsigned long oem_addr)
 {
-	if (!oem_addr)
-		return;
-
-	__acpi_unmap_table((char *)oem_addr, oem_size);
 }
 #endif
 
diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index 774ac49..1c9cc43 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -128,7 +128,7 @@ static int kvm_register_clock(char *txt)
 }
 
 #ifdef CONFIG_X86_LOCAL_APIC
-static void kvm_setup_secondary_clock(void)
+static void __devinit kvm_setup_secondary_clock(void)
 {
 	/*
 	 * Now that the first cpu already had this clocksource initialized,
diff --git a/arch/x86/kernel/tsc_sync.c b/arch/x86/kernel/tsc_sync.c
index 9ffb01c..1c0dfbc 100644
--- a/arch/x86/kernel/tsc_sync.c
+++ b/arch/x86/kernel/tsc_sync.c
@@ -46,7 +46,9 @@ static __cpuinit void check_tsc_warp(void)
 	cycles_t start, now, prev, end;
 	int i;
 
+	rdtsc_barrier();
 	start = get_cycles();
+	rdtsc_barrier();
 	/*
 	 * The measurement runs for 20 msecs:
 	 */
@@ -61,7 +63,9 @@ static __cpuinit void check_tsc_warp(void)
 		 */
 		__raw_spin_lock(&sync_lock);
 		prev = last_tsc;
+		rdtsc_barrier();
 		now = get_cycles();
+		rdtsc_barrier();
 		last_tsc = now;
 		__raw_spin_unlock(&sync_lock);
 
diff --git a/arch/x86/kernel/vsyscall_64.c b/arch/x86/kernel/vsyscall_64.c
index 0b8b6690..ebf2f12 100644
--- a/arch/x86/kernel/vsyscall_64.c
+++ b/arch/x86/kernel/vsyscall_64.c
@@ -128,7 +128,16 @@ static __always_inline void do_vgettimeofday(struct timeval * tv)
 			gettimeofday(tv,NULL);
 			return;
 		}
+
+		/*
+		 * Surround the RDTSC by barriers, to make sure it's not
+		 * speculated to outside the seqlock critical section and
+		 * does not cause time warps:
+		 */
+		rdtsc_barrier();
 		now = vread();
+		rdtsc_barrier();
+
 		base = __vsyscall_gtod_data.clock.cycle_last;
 		mask = __vsyscall_gtod_data.clock.mask;
 		mult = __vsyscall_gtod_data.clock.mult;
diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig
index ce3251c..b81125f 100644
--- a/arch/x86/kvm/Kconfig
+++ b/arch/x86/kvm/Kconfig
@@ -20,6 +20,8 @@ if VIRTUALIZATION
 config KVM
 	tristate "Kernel-based Virtual Machine (KVM) support"
 	depends on HAVE_KVM
+	# for device assignment:
+	depends on PCI
 	select PREEMPT_NOTIFIERS
 	select MMU_NOTIFIER
 	select ANON_INODES
diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c
index 8772dc9..59ebd37 100644
--- a/arch/x86/kvm/i8254.c
+++ b/arch/x86/kvm/i8254.c
@@ -548,8 +548,10 @@ struct kvm_pit *kvm_create_pit(struct kvm *kvm)
 	mutex_lock(&kvm->lock);
 	pit->irq_source_id = kvm_request_irq_source_id(kvm);
 	mutex_unlock(&kvm->lock);
-	if (pit->irq_source_id < 0)
+	if (pit->irq_source_id < 0) {
+		kfree(pit);
 		return NULL;
+	}
 
 	mutex_init(&pit->pit_state.lock);
 	mutex_lock(&pit->pit_state.lock);
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 2a5e648..f1983d9 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -314,7 +314,7 @@ static int mmu_topup_memory_caches(struct kvm_vcpu *vcpu)
 	if (r)
 		goto out;
 	r = mmu_topup_memory_cache(&vcpu->arch.mmu_rmap_desc_cache,
-				   rmap_desc_cache, 1);
+				   rmap_desc_cache, 4);
 	if (r)
 		goto out;
 	r = mmu_topup_memory_cache_page(&vcpu->arch.mmu_page_cache, 8);
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 2643b43..d06b4dc 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -3564,7 +3564,8 @@ static int __init vmx_init(void)
 		bypass_guest_pf = 0;
 		kvm_mmu_set_base_ptes(VMX_EPT_READABLE_MASK |
 			VMX_EPT_WRITABLE_MASK |
-			VMX_EPT_DEFAULT_MT << VMX_EPT_MT_EPTE_SHIFT);
+			VMX_EPT_DEFAULT_MT << VMX_EPT_MT_EPTE_SHIFT |
+			VMX_EPT_IGMT_BIT);
 		kvm_mmu_set_mask_ptes(0ull, 0ull, 0ull, 0ull,
 				VMX_EPT_EXECUTABLE_MASK);
 		kvm_enable_tdp();
diff --git a/arch/x86/kvm/vmx.h b/arch/x86/kvm/vmx.h
index 3e010d2..ec5edc3 100644
--- a/arch/x86/kvm/vmx.h
+++ b/arch/x86/kvm/vmx.h
@@ -352,6 +352,7 @@ enum vmcs_field {
 #define VMX_EPT_READABLE_MASK			0x1ull
 #define VMX_EPT_WRITABLE_MASK			0x2ull
 #define VMX_EPT_EXECUTABLE_MASK			0x4ull
+#define VMX_EPT_IGMT_BIT    			(1ull << 6)
 
 #define VMX_EPT_IDENTITY_PAGETABLE_ADDR		0xfffbc000ul
 
diff --git a/arch/x86/mach-voyager/voyager_smp.c b/arch/x86/mach-voyager/voyager_smp.c
index 0e33165..5214500 100644
--- a/arch/x86/mach-voyager/voyager_smp.c
+++ b/arch/x86/mach-voyager/voyager_smp.c
@@ -7,6 +7,7 @@
  * This file provides all the same external entries as smp.c but uses
  * the voyager hal to provide the functionality
  */
+#include <linux/cpu.h>
 #include <linux/module.h>
 #include <linux/mm.h>
 #include <linux/kernel_stat.h>
@@ -1790,6 +1791,17 @@ void __init smp_setup_processor_id(void)
 	x86_write_percpu(cpu_number, hard_smp_processor_id());
 }
 
+static void voyager_send_call_func(cpumask_t callmask)
+{
+	__u32 mask = cpus_addr(callmask)[0] & ~(1 << smp_processor_id());
+	send_CPI(mask, VIC_CALL_FUNCTION_CPI);
+}
+
+static void voyager_send_call_func_single(int cpu)
+{
+	send_CPI(1 << cpu, VIC_CALL_FUNCTION_SINGLE_CPI);
+}
+
 struct smp_ops smp_ops = {
 	.smp_prepare_boot_cpu = voyager_smp_prepare_boot_cpu,
 	.smp_prepare_cpus = voyager_smp_prepare_cpus,
@@ -1799,6 +1811,6 @@ struct smp_ops smp_ops = {
 	.smp_send_stop = voyager_smp_send_stop,
 	.smp_send_reschedule = voyager_smp_send_reschedule,
 
-	.send_call_func_ipi = native_send_call_func_ipi,
-	.send_call_func_single_ipi = native_send_call_func_single_ipi,
+	.send_call_func_ipi = voyager_send_call_func,
+	.send_call_func_single_ipi = voyager_send_call_func_single,
 };
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index c483f42..3ffed25 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -102,6 +102,8 @@ static pmd_t * __init one_md_table_init(pgd_t *pgd)
 		set_pgd(pgd, __pgd(__pa(pmd_table) | _PAGE_PRESENT));
 		pud = pud_offset(pgd, 0);
 		BUG_ON(pmd_table != pmd_offset(pud, 0));
+
+		return pmd_table;
 	}
 #endif
 	pud = pud_offset(pgd, 0);