Merge commit 'v2.6.27-rc7' into x86/microcode

26 files changed, 155 insertions, 56 deletions

diff --git a/include/asm-x86/amd_iommu_types.h b/include/asm-x86/amd_iommu_types.h
index 22aa58c..dcc8120 100644
--- a/include/asm-x86/amd_iommu_types.h
+++ b/include/asm-x86/amd_iommu_types.h
@@ -31,9 +31,6 @@
 #define ALIAS_TABLE_ENTRY_SIZE		2
 #define RLOOKUP_TABLE_ENTRY_SIZE	(sizeof(void *))
 
-/* helper macros */
-#define LOW_U32(x) ((x) & ((1ULL << 32)-1))
-
 /* Length of the MMIO region for the AMD IOMMU */
 #define MMIO_REGION_LENGTH       0x4000
 
@@ -69,6 +66,9 @@
 #define MMIO_EVT_TAIL_OFFSET	0x2018
 #define MMIO_STATUS_OFFSET	0x2020
 
+/* MMIO status bits */
+#define MMIO_STATUS_COM_WAIT_INT_MASK	0x04
+
 /* feature control bits */
 #define CONTROL_IOMMU_EN        0x00ULL
 #define CONTROL_HT_TUN_EN       0x01ULL
@@ -89,6 +89,7 @@
 #define CMD_INV_IOMMU_PAGES     0x03
 
 #define CMD_COMPL_WAIT_STORE_MASK	0x01
+#define CMD_COMPL_WAIT_INT_MASK		0x02
 #define CMD_INV_IOMMU_PAGES_SIZE_MASK	0x01
 #define CMD_INV_IOMMU_PAGES_PDE_MASK	0x02
 
@@ -99,6 +100,7 @@
 #define DEV_ENTRY_TRANSLATION   0x01
 #define DEV_ENTRY_IR            0x3d
 #define DEV_ENTRY_IW            0x3e
+#define DEV_ENTRY_NO_PAGE_FAULT	0x62
 #define DEV_ENTRY_EX            0x67
 #define DEV_ENTRY_SYSMGT1       0x68
 #define DEV_ENTRY_SYSMGT2       0x69
diff --git a/include/asm-x86/atomic_64.h b/include/asm-x86/atomic_64.h
index a009519..91c7d03 100644
--- a/include/asm-x86/atomic_64.h
+++ b/include/asm-x86/atomic_64.h
@@ -228,7 +228,7 @@ static inline void atomic64_add(long i, atomic64_t *v)
 {
 	asm volatile(LOCK_PREFIX "addq %1,%0"
 		     : "=m" (v->counter)
-		     : "ir" (i), "m" (v->counter));
+		     : "er" (i), "m" (v->counter));
 }
 
 /**
@@ -242,7 +242,7 @@ static inline void atomic64_sub(long i, atomic64_t *v)
 {
 	asm volatile(LOCK_PREFIX "subq %1,%0"
 		     : "=m" (v->counter)
-		     : "ir" (i), "m" (v->counter));
+		     : "er" (i), "m" (v->counter));
 }
 
 /**
@@ -260,7 +260,7 @@ static inline int atomic64_sub_and_test(long i, atomic64_t *v)
 
 	asm volatile(LOCK_PREFIX "subq %2,%0; sete %1"
 		     : "=m" (v->counter), "=qm" (c)
-		     : "ir" (i), "m" (v->counter) : "memory");
+		     : "er" (i), "m" (v->counter) : "memory");
 	return c;
 }
 
@@ -341,7 +341,7 @@ static inline int atomic64_add_negative(long i, atomic64_t *v)
 
 	asm volatile(LOCK_PREFIX "addq %2,%0; sets %1"
 		     : "=m" (v->counter), "=qm" (c)
-		     : "ir" (i), "m" (v->counter) : "memory");
+		     : "er" (i), "m" (v->counter) : "memory");
 	return c;
 }
 
diff --git a/include/asm-x86/cpufeature.h b/include/asm-x86/cpufeature.h
index 2f5a792..9489283 100644
--- a/include/asm-x86/cpufeature.h
+++ b/include/asm-x86/cpufeature.h
@@ -72,14 +72,15 @@
 #define X86_FEATURE_UP		(3*32+ 9) /* smp kernel running on up */
 #define X86_FEATURE_FXSAVE_LEAK (3*32+10) /* FXSAVE leaks FOP/FIP/FOP */
 #define X86_FEATURE_ARCH_PERFMON (3*32+11) /* Intel Architectural PerfMon */
-#define X86_FEATURE_PEBS	(3*32+12)  /* Precise-Event Based Sampling */
-#define X86_FEATURE_BTS		(3*32+13)  /* Branch Trace Store */
-#define X86_FEATURE_SYSCALL32	(3*32+14)  /* syscall in ia32 userspace */
-#define X86_FEATURE_SYSENTER32	(3*32+15)  /* sysenter in ia32 userspace */
+#define X86_FEATURE_PEBS	(3*32+12) /* Precise-Event Based Sampling */
+#define X86_FEATURE_BTS		(3*32+13) /* Branch Trace Store */
+#define X86_FEATURE_SYSCALL32	(3*32+14) /* syscall in ia32 userspace */
+#define X86_FEATURE_SYSENTER32	(3*32+15) /* sysenter in ia32 userspace */
 #define X86_FEATURE_REP_GOOD	(3*32+16) /* rep microcode works well on this CPU */
 #define X86_FEATURE_MFENCE_RDTSC (3*32+17) /* Mfence synchronizes RDTSC */
 #define X86_FEATURE_LFENCE_RDTSC (3*32+18) /* Lfence synchronizes RDTSC */
-#define X86_FEATURE_11AP	(3*32+19)  /* Bad local APIC aka 11AP */
+#define X86_FEATURE_11AP	(3*32+19) /* Bad local APIC aka 11AP */
+#define X86_FEATURE_NOPL	(3*32+20) /* The NOPL (0F 1F) instructions */
 
 /* Intel-defined CPU features, CPUID level 0x00000001 (ecx), word 4 */
 #define X86_FEATURE_XMM3	(4*32+ 0) /* Streaming SIMD Extensions-3 */
@@ -91,6 +92,7 @@
 #define X86_FEATURE_CX16	(4*32+13) /* CMPXCHG16B */
 #define X86_FEATURE_XTPR	(4*32+14) /* Send Task Priority Messages */
 #define X86_FEATURE_DCA		(4*32+18) /* Direct Cache Access */
+#define X86_FEATURE_XMM4_2	(4*32+20) /* Streaming SIMD Extensions-4.2 */
 
 /* VIA/Cyrix/Centaur-defined CPU features, CPUID level 0xC0000001, word 5 */
 #define X86_FEATURE_XSTORE	(5*32+ 2) /* on-CPU RNG present (xstore insn) */
@@ -189,6 +191,7 @@ extern const char * const x86_power_flags[32];
 #define cpu_has_gbpages		boot_cpu_has(X86_FEATURE_GBPAGES)
 #define cpu_has_arch_perfmon	boot_cpu_has(X86_FEATURE_ARCH_PERFMON)
 #define cpu_has_pat		boot_cpu_has(X86_FEATURE_PAT)
+#define cpu_has_xmm4_2		boot_cpu_has(X86_FEATURE_XMM4_2)
 
 #if defined(CONFIG_X86_INVLPG) || defined(CONFIG_X86_64)
 # define cpu_has_invlpg		1
diff --git a/include/asm-x86/efi.h b/include/asm-x86/efi.h
index 7ed2bd7..d4f2b0a 100644
--- a/include/asm-x86/efi.h
+++ b/include/asm-x86/efi.h
@@ -86,7 +86,7 @@ extern u64 efi_call6(void *fp, u64 arg1, u64 arg2, u64 arg3,
 	efi_call6((void *)(efi.systab->runtime->f), (u64)(a1), (u64)(a2), \
 		  (u64)(a3), (u64)(a4), (u64)(a5), (u64)(a6))
 
-extern void *efi_ioremap(unsigned long addr, unsigned long size);
+extern void __iomem *efi_ioremap(unsigned long addr, unsigned long size);
 
 #endif /* CONFIG_X86_32 */
 
diff --git a/include/asm-x86/genapic_32.h b/include/asm-x86/genapic_32.h
index b02ea6e..754d635 100644
--- a/include/asm-x86/genapic_32.h
+++ b/include/asm-x86/genapic_32.h
@@ -118,6 +118,7 @@ enum uv_system_type {UV_NONE, UV_LEGACY_APIC, UV_X2APIC, UV_NON_UNIQUE_APIC};
 #define get_uv_system_type()		UV_NONE
 #define is_uv_system()			0
 #define uv_wakeup_secondary(a, b)	1
+#define uv_system_init()		do {} while (0)
 
 
 #endif
diff --git a/include/asm-x86/genapic_64.h b/include/asm-x86/genapic_64.h
index 0f85046..a47d631 100644
--- a/include/asm-x86/genapic_64.h
+++ b/include/asm-x86/genapic_64.h
@@ -42,6 +42,7 @@ extern int is_uv_system(void);
 extern struct genapic apic_x2apic_uv_x;
 DECLARE_PER_CPU(int, x2apic_extra_bits);
 extern void uv_cpu_init(void);
+extern void uv_system_init(void);
 extern int uv_wakeup_secondary(int phys_apicid, unsigned int start_rip);
 
 extern void setup_apic_routing(void);
diff --git a/include/asm-x86/geode.h b/include/asm-x86/geode.h
index bb06027..2c1cda0 100644
--- a/include/asm-x86/geode.h
+++ b/include/asm-x86/geode.h
@@ -50,6 +50,7 @@ extern int geode_get_dev_base(unsigned int dev);
 #define MSR_PIC_YSEL_HIGH	0x51400021
 #define MSR_PIC_ZSEL_LOW	0x51400022
 #define MSR_PIC_ZSEL_HIGH	0x51400023
+#define MSR_PIC_IRQM_LPC	0x51400025
 
 #define MSR_MFGPT_IRQ		0x51400028
 #define MSR_MFGPT_NR		0x51400029
@@ -237,7 +238,7 @@ static inline u16 geode_mfgpt_read(int timer, u16 reg)
 }
 
 extern int geode_mfgpt_toggle_event(int timer, int cmp, int event, int enable);
-extern int geode_mfgpt_set_irq(int timer, int cmp, int irq, int enable);
+extern int geode_mfgpt_set_irq(int timer, int cmp, int *irq, int enable);
 extern int geode_mfgpt_alloc_timer(int timer, int domain);
 
 #define geode_mfgpt_setup_irq(t, c, i) geode_mfgpt_set_irq((t), (c), (i), 1)
diff --git a/include/asm-x86/hw_irq.h b/include/asm-x86/hw_irq.h
index 77ba51d..edd0b95 100644
--- a/include/asm-x86/hw_irq.h
+++ b/include/asm-x86/hw_irq.h
@@ -98,9 +98,17 @@ extern void (*const interrupt[NR_IRQS])(void);
 #else
 typedef int vector_irq_t[NR_VECTORS];
 DECLARE_PER_CPU(vector_irq_t, vector_irq);
-extern spinlock_t vector_lock;
 #endif
-extern void setup_vector_irq(int cpu);
+
+#if defined(CONFIG_X86_IO_APIC) && defined(CONFIG_X86_64)
+extern void lock_vector_lock(void);
+extern void unlock_vector_lock(void);
+extern void __setup_vector_irq(int cpu);
+#else
+static inline void lock_vector_lock(void) {}
+static inline void unlock_vector_lock(void) {}
+static inline void __setup_vector_irq(int cpu) {}
+#endif
 
 #endif /* !ASSEMBLY_ */
 
diff --git a/include/asm-x86/i387.h b/include/asm-x86/i387.h
index 96fa844..56d00e3 100644
--- a/include/asm-x86/i387.h
+++ b/include/asm-x86/i387.h
@@ -13,6 +13,7 @@
 #include <linux/sched.h>
 #include <linux/kernel_stat.h>
 #include <linux/regset.h>
+#include <linux/hardirq.h>
 #include <asm/asm.h>
 #include <asm/processor.h>
 #include <asm/sigcontext.h>
@@ -62,8 +63,6 @@ static inline int restore_fpu_checking(struct i387_fxsave_struct *fx)
 #else
 		     : [fx] "cdaSDb" (fx), "m" (*fx), "0" (0));
 #endif
-	if (unlikely(err))
-		init_fpu(current);
 	return err;
 }
 
@@ -236,6 +235,37 @@ static inline void kernel_fpu_end(void)
 	preempt_enable();
 }
 
+/*
+ * Some instructions like VIA's padlock instructions generate a spurious
+ * DNA fault but don't modify SSE registers. And these instructions
+ * get used from interrupt context aswell. To prevent these kernel instructions
+ * in interrupt context interact wrongly with other user/kernel fpu usage, we
+ * should use them only in the context of irq_ts_save/restore()
+ */
+static inline int irq_ts_save(void)
+{
+	/*
+	 * If we are in process context, we are ok to take a spurious DNA fault.
+	 * Otherwise, doing clts() in process context require pre-emption to
+	 * be disabled or some heavy lifting like kernel_fpu_begin()
+	 */
+	if (!in_interrupt())
+		return 0;
+
+	if (read_cr0() & X86_CR0_TS) {
+		clts();
+		return 1;
+	}
+
+	return 0;
+}
+
+static inline void irq_ts_restore(int TS_state)
+{
+	if (TS_state)
+		stts();
+}
+
 #ifdef CONFIG_X86_64
 
 static inline void save_init_fpu(struct task_struct *tsk)
diff --git a/include/asm-x86/io.h b/include/asm-x86/io.h
index bf5d629..0f954dc 100644
--- a/include/asm-x86/io.h
+++ b/include/asm-x86/io.h
@@ -21,7 +21,7 @@ extern void __iomem *fix_ioremap(unsigned idx, unsigned long phys);
 
 #define build_mmio_read(name, size, type, reg, barrier) \
 static inline type name(const volatile void __iomem *addr) \
-{ type ret; asm volatile("mov" size " %1,%0":"=" reg (ret) \
+{ type ret; asm volatile("mov" size " %1,%0":reg (ret) \
 :"m" (*(volatile type __force *)addr) barrier); return ret; }
 
 #define build_mmio_write(name, size, type, reg, barrier) \
@@ -29,13 +29,13 @@ static inline void name(type val, volatile void __iomem *addr) \
 { asm volatile("mov" size " %0,%1": :reg (val), \
 "m" (*(volatile type __force *)addr) barrier); }
 
-build_mmio_read(readb, "b", unsigned char, "q", :"memory")
-build_mmio_read(readw, "w", unsigned short, "r", :"memory")
-build_mmio_read(readl, "l", unsigned int, "r", :"memory")
+build_mmio_read(readb, "b", unsigned char, "=q", :"memory")
+build_mmio_read(readw, "w", unsigned short, "=r", :"memory")
+build_mmio_read(readl, "l", unsigned int, "=r", :"memory")
 
-build_mmio_read(__readb, "b", unsigned char, "q", )
-build_mmio_read(__readw, "w", unsigned short, "r", )
-build_mmio_read(__readl, "l", unsigned int, "r", )
+build_mmio_read(__readb, "b", unsigned char, "=q", )
+build_mmio_read(__readw, "w", unsigned short, "=r", )
+build_mmio_read(__readl, "l", unsigned int, "=r", )
 
 build_mmio_write(writeb, "b", unsigned char, "q", :"memory")
 build_mmio_write(writew, "w", unsigned short, "r", :"memory")
@@ -59,8 +59,8 @@ build_mmio_write(__writel, "l", unsigned int, "r", )
 #define mmiowb() barrier()
 
 #ifdef CONFIG_X86_64
-build_mmio_read(readq, "q", unsigned long, "r", :"memory")
-build_mmio_read(__readq, "q", unsigned long, "r", )
+build_mmio_read(readq, "q", unsigned long, "=r", :"memory")
+build_mmio_read(__readq, "q", unsigned long, "=r", )
 build_mmio_write(writeq, "q", unsigned long, "r", :"memory")
 build_mmio_write(__writeq, "q", unsigned long, "r", )
 
diff --git a/include/asm-x86/iommu.h b/include/asm-x86/iommu.h
index ecc8061..5f888cc 100644
--- a/include/asm-x86/iommu.h
+++ b/include/asm-x86/iommu.h
@@ -7,6 +7,8 @@ extern struct dma_mapping_ops nommu_dma_ops;
 extern int force_iommu, no_iommu;
 extern int iommu_detected;
 
+extern unsigned long iommu_num_pages(unsigned long addr, unsigned long len);
+
 #ifdef CONFIG_GART_IOMMU
 extern int gart_iommu_aperture;
 extern int gart_iommu_aperture_allowed;
diff --git a/include/asm-x86/irq_vectors.h b/include/asm-x86/irq_vectors.h
index 90b1d1f..a48c7f2 100644
--- a/include/asm-x86/irq_vectors.h
+++ b/include/asm-x86/irq_vectors.h
@@ -76,6 +76,7 @@
 #define CALL_FUNCTION_SINGLE_VECTOR	0xfb
 #define THERMAL_APIC_VECTOR		0xfa
 #define THRESHOLD_APIC_VECTOR		0xf9
+#define UV_BAU_MESSAGE			0xf8
 #define INVALIDATE_TLB_VECTOR_END	0xf7
 #define INVALIDATE_TLB_VECTOR_START	0xf0	/* f0-f7 used for TLB flush */
 
@@ -109,7 +110,15 @@
 #define LAST_VM86_IRQ		15
 #define invalid_vm86_irq(irq)	((irq) < 3 || (irq) > 15)
 
-#if !defined(CONFIG_X86_VOYAGER)
+#ifdef CONFIG_X86_64
+# if NR_CPUS < MAX_IO_APICS
+#  define NR_IRQS (NR_VECTORS + (32 * NR_CPUS))
+# else
+#  define NR_IRQS (NR_VECTORS + (32 * MAX_IO_APICS))
+# endif
+# define NR_IRQ_VECTORS NR_IRQS
+
+#elif !defined(CONFIG_X86_VOYAGER)
 
 # if defined(CONFIG_X86_IO_APIC) || defined(CONFIG_PARAVIRT) || defined(CONFIG_X86_VISWS)
 
diff --git a/include/asm-x86/kexec.h b/include/asm-x86/kexec.h
index c0e52a1..4246ab7 100644
--- a/include/asm-x86/kexec.h
+++ b/include/asm-x86/kexec.h
@@ -41,6 +41,10 @@
 # define PAGES_NR		17
 #endif
 
+#ifdef CONFIG_X86_32
+# define KEXEC_CONTROL_CODE_MAX_SIZE	2048
+#endif
+
 #ifndef __ASSEMBLY__
 
 #include <linux/string.h>
@@ -63,7 +67,7 @@
 /* Maximum address we can use for the control code buffer */
 # define KEXEC_CONTROL_MEMORY_LIMIT TASK_SIZE
 
-# define KEXEC_CONTROL_CODE_SIZE	4096
+# define KEXEC_CONTROL_PAGE_SIZE	4096
 
 /* The native architecture */
 # define KEXEC_ARCH KEXEC_ARCH_386
@@ -79,7 +83,7 @@
 # define KEXEC_CONTROL_MEMORY_LIMIT     (0xFFFFFFFFFFUL)
 
 /* Allocate one page for the pdp and the second for the code */
-# define KEXEC_CONTROL_CODE_SIZE  (4096UL + 4096UL)
+# define KEXEC_CONTROL_PAGE_SIZE  (4096UL + 4096UL)
 
 /* The native architecture */
 # define KEXEC_ARCH KEXEC_ARCH_X86_64
diff --git a/include/asm-x86/kvm_host.h b/include/asm-x86/kvm_host.h
index bc34dc2..c2e34c2 100644
--- a/include/asm-x86/kvm_host.h
+++ b/include/asm-x86/kvm_host.h
@@ -13,6 +13,7 @@
 
 #include <linux/types.h>
 #include <linux/mm.h>
+#include <linux/mmu_notifier.h>
 
 #include <linux/kvm.h>
 #include <linux/kvm_para.h>
@@ -251,6 +252,7 @@ struct kvm_vcpu_arch {
 		gfn_t gfn;	/* presumed gfn during guest pte update */
 		pfn_t pfn;	/* pfn corresponding to that gfn */
 		int largepage;
+		unsigned long mmu_seq;
 	} update_pte;
 
 	struct i387_fxsave_struct host_fx_image;
@@ -720,7 +722,7 @@ asmlinkage void kvm_handle_fault_on_reboot(void);
 
 #define __kvm_handle_fault_on_reboot(insn) \
 	"666: " insn "\n\t" \
-	".pushsection .text.fixup, \"ax\" \n" \
+	".pushsection .fixup, \"ax\" \n" \
 	"667: \n\t" \
 	KVM_EX_PUSH " $666b \n\t" \
 	"jmp kvm_handle_fault_on_reboot \n\t" \
@@ -729,4 +731,8 @@ asmlinkage void kvm_handle_fault_on_reboot(void);
 	KVM_EX_ENTRY " 666b, 667b \n\t" \
 	".popsection"
 
+#define KVM_ARCH_WANT_MMU_NOTIFIER
+int kvm_unmap_hva(struct kvm *kvm, unsigned long hva);
+int kvm_age_hva(struct kvm *kvm, unsigned long hva);
+
 #endif
diff --git a/include/asm-x86/mce.h b/include/asm-x86/mce.h
index 94f1fd7..531eaa5 100644
--- a/include/asm-x86/mce.h
+++ b/include/asm-x86/mce.h
@@ -92,6 +92,7 @@ extern int mce_disabled;
 
 void mce_log(struct mce *m);
 DECLARE_PER_CPU(struct sys_device, device_mce);
+extern void (*threshold_cpu_callback)(unsigned long action, unsigned int cpu);
 
 #ifdef CONFIG_X86_MCE_INTEL
 void mce_intel_feature_init(struct cpuinfo_x86 *c);
diff --git a/include/asm-x86/mman.h b/include/asm-x86/mman.h
index c1682b5..90bc410 100644
--- a/include/asm-x86/mman.h
+++ b/include/asm-x86/mman.h
@@ -12,6 +12,7 @@
 #define MAP_NORESERVE	0x4000		/* don't check for reservations */
 #define MAP_POPULATE	0x8000		/* populate (prefault) pagetables */
 #define MAP_NONBLOCK	0x10000		/* do not block on IO */
+#define MAP_STACK	0x20000		/* give out an address that is best suited for process/thread stacks */
 
 #define MCL_CURRENT	1		/* lock all current mappings */
 #define MCL_FUTURE	2		/* lock all future mappings */
diff --git a/include/asm-x86/mmconfig.h b/include/asm-x86/mmconfig.h
index 95beda0..e293ab8 100644
--- a/include/asm-x86/mmconfig.h
+++ b/include/asm-x86/mmconfig.h
@@ -3,7 +3,7 @@
 
 #ifdef CONFIG_PCI_MMCONFIG
 extern void __cpuinit fam10h_check_enable_mmcfg(void);
-extern void __init check_enable_amd_mmconf_dmi(void);
+extern void __cpuinit check_enable_amd_mmconf_dmi(void);
 #else
 static inline void fam10h_check_enable_mmcfg(void) { }
 static inline void check_enable_amd_mmconf_dmi(void) { }
diff --git a/include/asm-x86/mmzone_32.h b/include/asm-x86/mmzone_32.h
index b2298a2..5862e64 100644
--- a/include/asm-x86/mmzone_32.h
+++ b/include/asm-x86/mmzone_32.h
@@ -97,10 +97,16 @@ static inline int pfn_valid(int pfn)
 	reserve_bootmem_node(NODE_DATA(0), (addr), (size), (flags))
 #define alloc_bootmem(x) \
 	__alloc_bootmem_node(NODE_DATA(0), (x), SMP_CACHE_BYTES, __pa(MAX_DMA_ADDRESS))
+#define alloc_bootmem_nopanic(x) \
+	__alloc_bootmem_node_nopanic(NODE_DATA(0), (x), SMP_CACHE_BYTES, \
+				__pa(MAX_DMA_ADDRESS))
 #define alloc_bootmem_low(x) \
 	__alloc_bootmem_node(NODE_DATA(0), (x), SMP_CACHE_BYTES, 0)
 #define alloc_bootmem_pages(x) \
 	__alloc_bootmem_node(NODE_DATA(0), (x), PAGE_SIZE, __pa(MAX_DMA_ADDRESS))
+#define alloc_bootmem_pages_nopanic(x) \
+	__alloc_bootmem_node_nopanic(NODE_DATA(0), (x), PAGE_SIZE, \
+				__pa(MAX_DMA_ADDRESS))
 #define alloc_bootmem_low_pages(x) \
 	__alloc_bootmem_node(NODE_DATA(0), (x), PAGE_SIZE, 0)
 #define alloc_bootmem_node(pgdat, x)					\
diff --git a/include/asm-x86/msr.h b/include/asm-x86/msr.h
index ca110ee..2362cfd 100644
--- a/include/asm-x86/msr.h
+++ b/include/asm-x86/msr.h
@@ -52,14 +52,14 @@ static inline unsigned long long native_read_msr_safe(unsigned int msr,
 {
 	DECLARE_ARGS(val, low, high);
 
-	asm volatile("2: rdmsr ; xor %0,%0\n"
+	asm volatile("2: rdmsr ; xor %[err],%[err]\n"
 		     "1:\n\t"
 		     ".section .fixup,\"ax\"\n\t"
-		     "3:  mov %3,%0 ; jmp 1b\n\t"
+		     "3:  mov %[fault],%[err] ; jmp 1b\n\t"
 		     ".previous\n\t"
 		     _ASM_EXTABLE(2b, 3b)
-		     : "=r" (*err), EAX_EDX_RET(val, low, high)
-		     : "c" (msr), "i" (-EFAULT));
+		     : [err] "=r" (*err), EAX_EDX_RET(val, low, high)
+		     : "c" (msr), [fault] "i" (-EFAULT));
 	return EAX_EDX_VAL(val, low, high);
 }
 
@@ -73,15 +73,15 @@ static inline int native_write_msr_safe(unsigned int msr,
 					unsigned low, unsigned high)
 {
 	int err;
-	asm volatile("2: wrmsr ; xor %0,%0\n"
+	asm volatile("2: wrmsr ; xor %[err],%[err]\n"
 		     "1:\n\t"
 		     ".section .fixup,\"ax\"\n\t"
-		     "3:  mov %4,%0 ; jmp 1b\n\t"
+		     "3:  mov %[fault],%[err] ; jmp 1b\n\t"
 		     ".previous\n\t"
 		     _ASM_EXTABLE(2b, 3b)
-		     : "=a" (err)
+		     : [err] "=a" (err)
 		     : "c" (msr), "0" (low), "d" (high),
-		       "i" (-EFAULT)
+		       [fault] "i" (-EFAULT)
 		     : "memory");
 	return err;
 }
@@ -192,19 +192,20 @@ do {                                                            \
 #define write_rdtscp_aux(val) wrmsr(0xc0000103, (val), 0)
 
 #ifdef CONFIG_SMP
-void rdmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h);
-void wrmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h);
+int rdmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h);
+int wrmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h);
 int rdmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h);
-
 int wrmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h);
 #else  /*  CONFIG_SMP  */
-static inline void rdmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h)
+static inline int rdmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h)
 {
 	rdmsr(msr_no, *l, *h);
+	return 0;
 }
-static inline void wrmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h)
+static inline int wrmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h)
 {
 	wrmsr(msr_no, l, h);
+	return 0;
 }
 static inline int rdmsr_safe_on_cpu(unsigned int cpu, u32 msr_no,
 				    u32 *l, u32 *h)
diff --git a/include/asm-x86/percpu.h b/include/asm-x86/percpu.h
index 4e91ee1..f643a3a 100644
--- a/include/asm-x86/percpu.h
+++ b/include/asm-x86/percpu.h
@@ -182,7 +182,7 @@ do {							\
 	DEFINE_PER_CPU(_type, _name) = _initvalue;			\
 	__typeof__(_type) _name##_early_map[NR_CPUS] __initdata =	\
 				{ [0 ... NR_CPUS-1] = _initvalue };	\
-	__typeof__(_type) *_name##_early_ptr = _name##_early_map
+	__typeof__(_type) *_name##_early_ptr __refdata = _name##_early_map
 
 #define EXPORT_EARLY_PER_CPU_SYMBOL(_name)			\
 	EXPORT_PER_CPU_SYMBOL(_name)
diff --git a/include/asm-x86/pgtable_64.h b/include/asm-x86/pgtable_64.h
index ac5fff4..549144d 100644
--- a/include/asm-x86/pgtable_64.h
+++ b/include/asm-x86/pgtable_64.h
@@ -151,7 +151,7 @@ static inline void native_pgd_clear(pgd_t *pgd)
 #define VMALLOC_END      _AC(0xffffe1ffffffffff, UL)
 #define VMEMMAP_START	 _AC(0xffffe20000000000, UL)
 #define MODULES_VADDR    _AC(0xffffffffa0000000, UL)
-#define MODULES_END      _AC(0xfffffffffff00000, UL)
+#define MODULES_END      _AC(0xffffffffff000000, UL)
 #define MODULES_LEN   (MODULES_END - MODULES_VADDR)
 
 #ifndef __ASSEMBLY__
diff --git a/include/asm-x86/processor.h b/include/asm-x86/processor.h
index 58a76f6..c63a476 100644
--- a/include/asm-x86/processor.h
+++ b/include/asm-x86/processor.h
@@ -693,6 +693,29 @@ extern unsigned long		boot_option_idle_override;
 extern unsigned long		idle_halt;
 extern unsigned long		idle_nomwait;
 
+/*
+ * on systems with caches, caches must be flashed as the absolute
+ * last instruction before going into a suspended halt.  Otherwise,
+ * dirty data can linger in the cache and become stale on resume,
+ * leading to strange errors.
+ *
+ * perform a variety of operations to guarantee that the compiler
+ * will not reorder instructions.  wbinvd itself is serializing
+ * so the processor will not reorder.
+ *
+ * Systems without cache can just go into halt.
+ */
+static inline void wbinvd_halt(void)
+{
+	mb();
+	/* check for clflush to determine if wbinvd is legal */
+	if (cpu_has_clflush)
+		asm volatile("cli; wbinvd; 1: hlt; jmp 1b" : : : "memory");
+	else
+		while (1)
+			halt();
+}
+
 extern void enable_sep_cpu(void);
 extern int sysenter_setup(void);
 
diff --git a/include/asm-x86/required-features.h b/include/asm-x86/required-features.h
index adec887..5c2ff4b 100644
--- a/include/asm-x86/required-features.h
+++ b/include/asm-x86/required-features.h
@@ -41,6 +41,12 @@
 # define NEED_3DNOW	0
 #endif
 
+#if defined(CONFIG_X86_P6_NOP) || defined(CONFIG_X86_64)
+# define NEED_NOPL	(1<<(X86_FEATURE_NOPL & 31))
+#else
+# define NEED_NOPL	0
+#endif
+
 #ifdef CONFIG_X86_64
 #define NEED_PSE	0
 #define NEED_MSR	(1<<(X86_FEATURE_MSR & 31))
@@ -67,7 +73,7 @@
 #define REQUIRED_MASK1	(NEED_LM|NEED_3DNOW)
 
 #define REQUIRED_MASK2	0
-#define REQUIRED_MASK3	0
+#define REQUIRED_MASK3	(NEED_NOPL)
 #define REQUIRED_MASK4	0
 #define REQUIRED_MASK5	0
 #define REQUIRED_MASK6	0
diff --git a/include/asm-x86/spinlock.h b/include/asm-x86/spinlock.h
index 4f9a986..e39c790 100644
--- a/include/asm-x86/spinlock.h
+++ b/include/asm-x86/spinlock.h
@@ -65,7 +65,7 @@ static inline int __ticket_spin_is_contended(raw_spinlock_t *lock)
 {
 	int tmp = ACCESS_ONCE(lock->slock);
 
-	return (((tmp >> 8) & 0xff) - (tmp & 0xff)) > 1;
+	return (((tmp >> 8) - tmp) & 0xff) > 1;
 }
 
 static __always_inline void __ticket_spin_lock(raw_spinlock_t *lock)
@@ -127,7 +127,7 @@ static inline int __ticket_spin_is_contended(raw_spinlock_t *lock)
 {
 	int tmp = ACCESS_ONCE(lock->slock);
 
-	return (((tmp >> 16) & 0xffff) - (tmp & 0xffff)) > 1;
+	return (((tmp >> 16) - tmp) & 0xffff) > 1;
 }
 
 static __always_inline void __ticket_spin_lock(raw_spinlock_t *lock)
diff --git a/include/asm-x86/uv/uv_bau.h b/include/asm-x86/uv/uv_bau.h
index 91ac0df..610b6b3 100644
--- a/include/asm-x86/uv/uv_bau.h
+++ b/include/asm-x86/uv/uv_bau.h
@@ -40,11 +40,6 @@
 #define UV_ACTIVATION_DESCRIPTOR_SIZE	32
 #define UV_DISTRIBUTION_SIZE		256
 #define UV_SW_ACK_NPENDING		8
-#define UV_BAU_MESSAGE			200
-/*
- * Messaging irq; see irq_64.h and include/asm-x86/hw_irq_64.h
- * To be dynamically allocated in the future
- */
 #define UV_NET_ENDPOINT_INTD		0x38
 #define UV_DESC_BASE_PNODE_SHIFT	49
 #define UV_PAYLOADQ_PNODE_SHIFT		49
diff --git a/include/asm-x86/xen/hypervisor.h b/include/asm-x86/xen/hypervisor.h
index 8e15dd2..04ee061 100644
--- a/include/asm-x86/xen/hypervisor.h
+++ b/include/asm-x86/xen/hypervisor.h
@@ -35,7 +35,6 @@
 
 #include <linux/types.h>
 #include <linux/kernel.h>
-#include <linux/version.h>
 
 #include <xen/interface/xen.h>
 #include <xen/interface/version.h>