Merge branch 'core/urgent' into core/futexes

Merge reason: this branch was on an pre -rc1 base, merge it up to -rc6+
              to get the latest upstream fixes.

Conflicts:
	kernel/futex.c

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

31 files changed, 111 insertions, 145 deletions

diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index df8a300dfe6c..42f2f8377422 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -107,6 +107,9 @@ extern u32 native_safe_apic_wait_icr_idle(void);
 extern void native_apic_icr_write(u32 low, u32 id);
 extern u64 native_apic_icr_read(void);
 
+#define EIM_8BIT_APIC_ID	0
+#define EIM_32BIT_APIC_ID	1
+
 #ifdef CONFIG_X86_X2APIC
 /*
  * Make previous memory operations globally visible before
diff --git a/arch/x86/include/asm/cacheflush.h b/arch/x86/include/asm/cacheflush.h
index b3894bf52fcd..e55dfc1ad453 100644
--- a/arch/x86/include/asm/cacheflush.h
+++ b/arch/x86/include/asm/cacheflush.h
@@ -126,6 +126,11 @@ void clflush_cache_range(void *addr, unsigned int size);
 #ifdef CONFIG_DEBUG_RODATA
 void mark_rodata_ro(void);
 extern const int rodata_test_data;
+void set_kernel_text_rw(void);
+void set_kernel_text_ro(void);
+#else
+static inline void set_kernel_text_rw(void) { }
+static inline void set_kernel_text_ro(void) { }
 #endif
 
 #ifdef CONFIG_DEBUG_RODATA_TEST
diff --git a/arch/x86/include/asm/cpu_debug.h b/arch/x86/include/asm/cpu_debug.h
index 222802029fa6..222802029fa6 100755..100644
--- a/arch/x86/include/asm/cpu_debug.h
+++ b/arch/x86/include/asm/cpu_debug.h
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index 0beba0d1468d..bb83b1c397aa 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -154,6 +154,7 @@
  * CPUID levels like 0x6, 0xA etc
  */
 #define X86_FEATURE_IDA		(7*32+ 0) /* Intel Dynamic Acceleration */
+#define X86_FEATURE_ARAT	(7*32+ 1) /* Always Running APIC Timer */
 
 /* Virtualization flags: Linux defined */
 #define X86_FEATURE_TPR_SHADOW  (8*32+ 0) /* Intel TPR Shadow */
diff --git a/arch/x86/include/asm/cpumask.h b/arch/x86/include/asm/cpumask.h
index a7f3c75f8ad7..61c852fa346b 100644
--- a/arch/x86/include/asm/cpumask.h
+++ b/arch/x86/include/asm/cpumask.h
@@ -3,8 +3,6 @@
 #ifndef __ASSEMBLY__
 #include <linux/cpumask.h>
 
-#ifdef CONFIG_X86_64
-
 extern cpumask_var_t cpu_callin_mask;
 extern cpumask_var_t cpu_callout_mask;
 extern cpumask_var_t cpu_initialized_mask;
@@ -12,21 +10,5 @@ extern cpumask_var_t cpu_sibling_setup_mask;
 
 extern void setup_cpu_local_masks(void);
 
-#else /* CONFIG_X86_32 */
-
-extern cpumask_t cpu_callin_map;
-extern cpumask_t cpu_callout_map;
-extern cpumask_t cpu_initialized;
-extern cpumask_t cpu_sibling_setup_map;
-
-#define cpu_callin_mask		((struct cpumask *)&cpu_callin_map)
-#define cpu_callout_mask	((struct cpumask *)&cpu_callout_map)
-#define cpu_initialized_mask	((struct cpumask *)&cpu_initialized)
-#define cpu_sibling_setup_mask	((struct cpumask *)&cpu_sibling_setup_map)
-
-static inline void setup_cpu_local_masks(void) { }
-
-#endif /* CONFIG_X86_32 */
-
 #endif /* __ASSEMBLY__ */
 #endif /* _ASM_X86_CPUMASK_H */
diff --git a/arch/x86/include/asm/desc.h b/arch/x86/include/asm/desc.h
index 5623c50d67b2..c45f415ce315 100644
--- a/arch/x86/include/asm/desc.h
+++ b/arch/x86/include/asm/desc.h
@@ -37,7 +37,7 @@ extern gate_desc idt_table[];
 struct gdt_page {
 	struct desc_struct gdt[GDT_ENTRIES];
 } __attribute__((aligned(PAGE_SIZE)));
-DECLARE_PER_CPU(struct gdt_page, gdt_page);
+DECLARE_PER_CPU_PAGE_ALIGNED(struct gdt_page, gdt_page);
 
 static inline struct desc_struct *get_cpu_gdt_table(unsigned int cpu)
 {
diff --git a/arch/x86/include/asm/dma-mapping.h b/arch/x86/include/asm/dma-mapping.h
index cea7b74963e9..f82fdc412c64 100644
--- a/arch/x86/include/asm/dma-mapping.h
+++ b/arch/x86/include/asm/dma-mapping.h
@@ -238,7 +238,7 @@ static inline unsigned long dma_alloc_coherent_mask(struct device *dev,
 
 	dma_mask = dev->coherent_dma_mask;
 	if (!dma_mask)
-		dma_mask = (gfp & GFP_DMA) ? DMA_24BIT_MASK : DMA_32BIT_MASK;
+		dma_mask = (gfp & GFP_DMA) ? DMA_BIT_MASK(24) : DMA_BIT_MASK(32);
 
 	return dma_mask;
 }
@@ -247,10 +247,10 @@ static inline gfp_t dma_alloc_coherent_gfp_flags(struct device *dev, gfp_t gfp)
 {
 	unsigned long dma_mask = dma_alloc_coherent_mask(dev, gfp);
 
-	if (dma_mask <= DMA_24BIT_MASK)
+	if (dma_mask <= DMA_BIT_MASK(24))
 		gfp |= GFP_DMA;
 #ifdef CONFIG_X86_64
-	if (dma_mask <= DMA_32BIT_MASK && !(gfp & GFP_DMA))
+	if (dma_mask <= DMA_BIT_MASK(32) && !(gfp & GFP_DMA))
 		gfp |= GFP_DMA32;
 #endif
        return gfp;
diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h
index 63a79c77d220..2d81af3974a0 100644
--- a/arch/x86/include/asm/fixmap.h
+++ b/arch/x86/include/asm/fixmap.h
@@ -111,6 +111,8 @@ enum fixed_addresses {
 #ifdef CONFIG_PARAVIRT
 	FIX_PARAVIRT_BOOTMAP,
 #endif
+	FIX_TEXT_POKE0,	/* reserve 2 pages for text_poke() */
+	FIX_TEXT_POKE1,
 	__end_of_permanent_fixed_addresses,
 #ifdef CONFIG_PROVIDE_OHCI1394_DMA_INIT
 	FIX_OHCI1394_BASE,
@@ -149,11 +151,11 @@ extern pte_t *pkmap_page_table;
 
 void __native_set_fixmap(enum fixed_addresses idx, pte_t pte);
 void native_set_fixmap(enum fixed_addresses idx,
-		       unsigned long phys, pgprot_t flags);
+		       phys_addr_t phys, pgprot_t flags);
 
 #ifndef CONFIG_PARAVIRT
 static inline void __set_fixmap(enum fixed_addresses idx,
-				unsigned long phys, pgprot_t flags)
+				phys_addr_t phys, pgprot_t flags)
 {
 	native_set_fixmap(idx, phys, flags);
 }
diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h
index db24c2278be0..bd2c6511c887 100644
--- a/arch/x86/include/asm/ftrace.h
+++ b/arch/x86/include/asm/ftrace.h
@@ -28,6 +28,13 @@
 
 #endif
 
+/* FIXME: I don't want to stay hardcoded */
+#ifdef CONFIG_X86_64
+# define FTRACE_SYSCALL_MAX     296
+#else
+# define FTRACE_SYSCALL_MAX     333
+#endif
+
 #ifdef CONFIG_FUNCTION_TRACER
 #define MCOUNT_ADDR		((long)(mcount))
 #define MCOUNT_INSN_SIZE	5 /* sizeof mcount call */
diff --git a/arch/x86/include/asm/hardirq.h b/arch/x86/include/asm/hardirq.h
index 039db6aa8e02..37555e52f980 100644
--- a/arch/x86/include/asm/hardirq.h
+++ b/arch/x86/include/asm/hardirq.h
@@ -26,7 +26,7 @@ typedef struct {
 #endif
 } ____cacheline_aligned irq_cpustat_t;
 
-DECLARE_PER_CPU(irq_cpustat_t, irq_stat);
+DECLARE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat);
 
 /* We can have at most NR_VECTORS irqs routed to a cpu at a time */
 #define MAX_HARDIRQS_PER_CPU NR_VECTORS
diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h
index e5383e3d2f8c..73739322b6d0 100644
--- a/arch/x86/include/asm/io.h
+++ b/arch/x86/include/asm/io.h
@@ -193,8 +193,10 @@ extern void __iomem *ioremap_wc(resource_size_t offset, unsigned long size);
  */
 extern void early_ioremap_init(void);
 extern void early_ioremap_reset(void);
-extern void __iomem *early_ioremap(unsigned long offset, unsigned long size);
-extern void __iomem *early_memremap(unsigned long offset, unsigned long size);
+extern void __iomem *early_ioremap(resource_size_t phys_addr,
+				   unsigned long size);
+extern void __iomem *early_memremap(resource_size_t phys_addr,
+				    unsigned long size);
 extern void early_iounmap(void __iomem *addr, unsigned long size);
 
 #define IO_SPACE_LIMIT 0xffff
diff --git a/arch/x86/include/asm/io_apic.h b/arch/x86/include/asm/io_apic.h
index 373cc2bbcad2..9d826e436010 100644
--- a/arch/x86/include/asm/io_apic.h
+++ b/arch/x86/include/asm/io_apic.h
@@ -162,10 +162,13 @@ extern int (*ioapic_renumber_irq)(int ioapic, int irq);
 extern void ioapic_init_mappings(void);
 
 #ifdef CONFIG_X86_64
-extern int save_IO_APIC_setup(void);
-extern void mask_IO_APIC_setup(void);
-extern void restore_IO_APIC_setup(void);
-extern void reinit_intr_remapped_IO_APIC(int);
+extern struct IO_APIC_route_entry **alloc_ioapic_entries(void);
+extern void free_ioapic_entries(struct IO_APIC_route_entry **ioapic_entries);
+extern int save_IO_APIC_setup(struct IO_APIC_route_entry **ioapic_entries);
+extern void mask_IO_APIC_setup(struct IO_APIC_route_entry **ioapic_entries);
+extern int restore_IO_APIC_setup(struct IO_APIC_route_entry **ioapic_entries);
+extern void reinit_intr_remapped_IO_APIC(int intr_remapping,
+	struct IO_APIC_route_entry **ioapic_entries);
 #endif
 
 extern void probe_nr_irqs_gsi(void);
diff --git a/arch/x86/include/asm/lguest_hcall.h b/arch/x86/include/asm/lguest_hcall.h
index 0f4ee7148afe..faae1996487b 100644
--- a/arch/x86/include/asm/lguest_hcall.h
+++ b/arch/x86/include/asm/lguest_hcall.h
@@ -5,7 +5,6 @@
 #define LHCALL_FLUSH_ASYNC	0
 #define LHCALL_LGUEST_INIT	1
 #define LHCALL_SHUTDOWN		2
-#define LHCALL_LOAD_GDT		3
 #define LHCALL_NEW_PGTABLE	4
 #define LHCALL_FLUSH_TLB	5
 #define LHCALL_LOAD_IDT_ENTRY	6
@@ -17,6 +16,7 @@
 #define LHCALL_SET_PMD		15
 #define LHCALL_LOAD_TLS		16
 #define LHCALL_NOTIFY		17
+#define LHCALL_LOAD_GDT_ENTRY	18
 
 #define LGUEST_TRAP_ENTRY 0x1F
 
diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
index 563933e06a35..4f8c199584e7 100644
--- a/arch/x86/include/asm/mce.h
+++ b/arch/x86/include/asm/mce.h
@@ -137,6 +137,7 @@ DECLARE_PER_CPU(mce_banks_t, mce_poll_banks);
 enum mcp_flags {
 	MCP_TIMESTAMP = (1 << 0),	/* log time stamp */
 	MCP_UC = (1 << 1),		/* log uncorrected errors */
+	MCP_DONTLOG = (1 << 2),		/* only clear, don't log */
 };
 extern void machine_check_poll(enum mcp_flags flags, mce_banks_t *b);
 
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index 7727aa8b7dda..a53da004e08e 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -347,7 +347,7 @@ struct pv_mmu_ops {
 	/* Sometimes the physical address is a pfn, and sometimes its
 	   an mfn.  We can tell which is which from the index. */
 	void (*set_fixmap)(unsigned /* enum fixed_addresses */ idx,
-			   unsigned long phys, pgprot_t flags);
+			   phys_addr_t phys, pgprot_t flags);
 };
 
 struct raw_spinlock;
@@ -1432,7 +1432,7 @@ static inline void arch_leave_lazy_mmu_mode(void)
 void arch_flush_lazy_mmu_mode(void);
 
 static inline void __set_fixmap(unsigned /* enum fixed_addresses */ idx,
-				unsigned long phys, pgprot_t flags)
+				phys_addr_t phys, pgprot_t flags)
 {
 	pv_mmu_ops.set_fixmap(idx, phys, flags);
 }
@@ -1443,7 +1443,7 @@ u64 _paravirt_ident_64(u64);
 
 #define paravirt_nop	((void *)_paravirt_nop)
 
-#ifdef CONFIG_SMP
+#if defined(CONFIG_SMP) && defined(CONFIG_PARAVIRT_SPINLOCKS)
 
 static inline int __raw_spin_is_locked(struct raw_spinlock *lock)
 {
diff --git a/arch/x86/include/asm/pat.h b/arch/x86/include/asm/pat.h
index 2cd07b9422f4..7af14e512f97 100644
--- a/arch/x86/include/asm/pat.h
+++ b/arch/x86/include/asm/pat.h
@@ -18,9 +18,5 @@ extern int free_memtype(u64 start, u64 end);
 
 extern int kernel_map_sync_memtype(u64 base, unsigned long size,
 		unsigned long flag);
-extern void map_devmem(unsigned long pfn, unsigned long size,
-		       struct pgprot vma_prot);
-extern void unmap_devmem(unsigned long pfn, unsigned long size,
-			 struct pgprot vma_prot);
 
 #endif /* _ASM_X86_PAT_H */
diff --git a/arch/x86/include/asm/pci.h b/arch/x86/include/asm/pci.h
index e545ea01abcf..b51a1e8b0baf 100644
--- a/arch/x86/include/asm/pci.h
+++ b/arch/x86/include/asm/pci.h
@@ -140,11 +140,6 @@ static inline int __pcibus_to_node(const struct pci_bus *bus)
 	return sd->node;
 }
 
-static inline cpumask_t __pcibus_to_cpumask(struct pci_bus *bus)
-{
-	return node_to_cpumask(__pcibus_to_node(bus));
-}
-
 static inline const struct cpumask *
 cpumask_of_pcibus(const struct pci_bus *bus)
 {
diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
index aee103b26d01..02ecb30982a3 100644
--- a/arch/x86/include/asm/percpu.h
+++ b/arch/x86/include/asm/percpu.h
@@ -82,22 +82,22 @@ do {							\
 	case 1:						\
 		asm(op "b %1,"__percpu_arg(0)		\
 		    : "+m" (var)			\
-		    : "ri" ((T__)val));			\
+		    : "qi" ((T__)(val)));		\
 		break;					\
 	case 2:						\
 		asm(op "w %1,"__percpu_arg(0)		\
 		    : "+m" (var)			\
-		    : "ri" ((T__)val));			\
+		    : "ri" ((T__)(val)));		\
 		break;					\
 	case 4:						\
 		asm(op "l %1,"__percpu_arg(0)		\
 		    : "+m" (var)			\
-		    : "ri" ((T__)val));			\
+		    : "ri" ((T__)(val)));		\
 		break;					\
 	case 8:						\
 		asm(op "q %1,"__percpu_arg(0)		\
 		    : "+m" (var)			\
-		    : "re" ((T__)val));			\
+		    : "re" ((T__)(val)));		\
 		break;					\
 	default: __bad_percpu_size();			\
 	}						\
@@ -109,7 +109,7 @@ do {							\
 	switch (sizeof(var)) {				\
 	case 1:						\
 		asm(op "b "__percpu_arg(1)",%0"		\
-		    : "=r" (ret__)			\
+		    : "=q" (ret__)			\
 		    : "m" (var));			\
 		break;					\
 	case 2:						\
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index ae85a8d66a30..c2cceae709c8 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -94,7 +94,7 @@ struct cpuinfo_x86 {
 	unsigned long		loops_per_jiffy;
 #ifdef CONFIG_SMP
 	/* cpus sharing the last level cache: */
-	cpumask_t		llc_shared_map;
+	cpumask_var_t		llc_shared_map;
 #endif
 	/* cpuid returned max cores value: */
 	u16			 x86_max_cores;
@@ -138,7 +138,7 @@ extern struct tss_struct	doublefault_tss;
 extern __u32			cleared_cpu_caps[NCAPINTS];
 
 #ifdef CONFIG_SMP
-DECLARE_PER_CPU(struct cpuinfo_x86, cpu_info);
+DECLARE_PER_CPU_SHARED_ALIGNED(struct cpuinfo_x86, cpu_info);
 #define cpu_data(cpu)		per_cpu(cpu_info, cpu)
 #define current_cpu_data	__get_cpu_var(cpu_info)
 #else
@@ -270,7 +270,7 @@ struct tss_struct {
 
 } ____cacheline_aligned;
 
-DECLARE_PER_CPU(struct tss_struct, init_tss);
+DECLARE_PER_CPU_SHARED_ALIGNED(struct tss_struct, init_tss);
 
 /*
  * Save the original ist values for checking stack pointers during debugging
@@ -352,6 +352,11 @@ struct i387_soft_struct {
 	u32			entry_eip;
 };
 
+struct ymmh_struct {
+	/* 16 * 16 bytes for each YMMH-reg = 256 bytes */
+	u32 ymmh_space[64];
+};
+
 struct xsave_hdr_struct {
 	u64 xstate_bv;
 	u64 reserved1[2];
@@ -361,6 +366,7 @@ struct xsave_hdr_struct {
 struct xsave_struct {
 	struct i387_fxsave_struct i387;
 	struct xsave_hdr_struct xsave_hdr;
+	struct ymmh_struct ymmh;
 	/* new processor state extensions will go here */
 } __attribute__ ((packed, aligned (64)));
 
@@ -387,7 +393,7 @@ union irq_stack_union {
 	};
 };
 
-DECLARE_PER_CPU(union irq_stack_union, irq_stack_union);
+DECLARE_PER_CPU_FIRST(union irq_stack_union, irq_stack_union);
 DECLARE_INIT_PER_CPU(irq_stack_union);
 
 DECLARE_PER_CPU(char *, irq_stack_ptr);
@@ -736,6 +742,7 @@ static inline void __sti_mwait(unsigned long eax, unsigned long ecx)
 extern void mwait_idle_with_hints(unsigned long eax, unsigned long ecx);
 
 extern void select_idle_routine(const struct cpuinfo_x86 *c);
+extern void init_c1e_mask(void);
 
 extern unsigned long		boot_option_idle_override;
 extern unsigned long		idle_halt;
diff --git a/arch/x86/include/asm/ptrace-abi.h b/arch/x86/include/asm/ptrace-abi.h
index 8e0f8d199e05..86723035a515 100644
--- a/arch/x86/include/asm/ptrace-abi.h
+++ b/arch/x86/include/asm/ptrace-abi.h
@@ -80,8 +80,6 @@
 
 #define PTRACE_SINGLEBLOCK	33	/* resume execution until next branch */
 
-#ifdef CONFIG_X86_PTRACE_BTS
-
 #ifndef __ASSEMBLY__
 #include <linux/types.h>
 
@@ -140,6 +138,5 @@ struct ptrace_bts_config {
    BTS records are read from oldest to newest.
    Returns number of BTS records drained.
 */
-#endif /* CONFIG_X86_PTRACE_BTS */
 
 #endif /* _ASM_X86_PTRACE_ABI_H */
diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h
index e304b66abeea..624f133943ed 100644
--- a/arch/x86/include/asm/ptrace.h
+++ b/arch/x86/include/asm/ptrace.h
@@ -187,14 +187,15 @@ static inline int v8086_mode(struct pt_regs *regs)
 
 /*
  * X86_32 CPUs don't save ss and esp if the CPU is already in kernel mode
- * when it traps.  So regs will be the current sp.
+ * when it traps.  The previous stack will be directly underneath the saved
+ * registers, and 'sp/ss' won't even have been saved. Thus the '&regs->sp'.
  *
  * This is valid only for kernel mode traps.
  */
-static inline unsigned long kernel_trap_sp(struct pt_regs *regs)
+static inline unsigned long kernel_stack_pointer(struct pt_regs *regs)
 {
 #ifdef CONFIG_X86_32
-	return (unsigned long)regs;
+	return (unsigned long)(&regs->sp);
 #else
 	return regs->sp;
 #endif
diff --git a/arch/x86/include/asm/required-features.h b/arch/x86/include/asm/required-features.h
index d5cd6c586881..a4737dddfd58 100644
--- a/arch/x86/include/asm/required-features.h
+++ b/arch/x86/include/asm/required-features.h
@@ -50,7 +50,7 @@
 #ifdef CONFIG_X86_64
 #define NEED_PSE	0
 #define NEED_MSR	(1<<(X86_FEATURE_MSR & 31))
-#define NEED_PGE	(1<<(X86_FEATURE_PGE & 31))
+#define NEED_PGE	0
 #define NEED_FXSR	(1<<(X86_FEATURE_FXSR & 31))
 #define NEED_XMM	(1<<(X86_FEATURE_XMM & 31))
 #define NEED_XMM2	(1<<(X86_FEATURE_XMM2 & 31))
diff --git a/arch/x86/include/asm/sigcontext.h b/arch/x86/include/asm/sigcontext.h
index ec666491aaa4..72e5a4491661 100644
--- a/arch/x86/include/asm/sigcontext.h
+++ b/arch/x86/include/asm/sigcontext.h
@@ -269,6 +269,11 @@ struct _xsave_hdr {
 	__u64 reserved2[5];
 };
 
+struct _ymmh_state {
+	/* 16 * 16 bytes for each YMMH-reg */
+	__u32 ymmh_space[64];
+};
+
 /*
  * Extended state pointed by the fpstate pointer in the sigcontext.
  * In addition to the fpstate, information encoded in the xstate_hdr
@@ -278,6 +283,7 @@ struct _xsave_hdr {
 struct _xstate {
 	struct _fpstate fpstate;
 	struct _xsave_hdr xstate_hdr;
+	struct _ymmh_state ymmh;
 	/* new processor state extensions go here */
 };
 
diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h
index 47d0e21f2b9e..19e0d88b966d 100644
--- a/arch/x86/include/asm/smp.h
+++ b/arch/x86/include/asm/smp.h
@@ -21,19 +21,19 @@
 extern int smp_num_siblings;
 extern unsigned int num_processors;
 
-DECLARE_PER_CPU(cpumask_t, cpu_sibling_map);
-DECLARE_PER_CPU(cpumask_t, cpu_core_map);
+DECLARE_PER_CPU(cpumask_var_t, cpu_sibling_map);
+DECLARE_PER_CPU(cpumask_var_t, cpu_core_map);
 DECLARE_PER_CPU(u16, cpu_llc_id);
 DECLARE_PER_CPU(int, cpu_number);
 
 static inline struct cpumask *cpu_sibling_mask(int cpu)
 {
-	return &per_cpu(cpu_sibling_map, cpu);
+	return per_cpu(cpu_sibling_map, cpu);
 }
 
 static inline struct cpumask *cpu_core_mask(int cpu)
 {
-	return &per_cpu(cpu_core_map, cpu);
+	return per_cpu(cpu_core_map, cpu);
 }
 
 DECLARE_EARLY_PER_CPU(u16, x86_cpu_to_apicid);
@@ -121,9 +121,10 @@ static inline void arch_send_call_function_single_ipi(int cpu)
 	smp_ops.send_call_func_single_ipi(cpu);
 }
 
-static inline void arch_send_call_function_ipi(cpumask_t mask)
+#define arch_send_call_function_ipi_mask arch_send_call_function_ipi_mask
+static inline void arch_send_call_function_ipi_mask(const struct cpumask *mask)
 {
-	smp_ops.send_call_func_ipi(&mask);
+	smp_ops.send_call_func_ipi(mask);
 }
 
 void cpu_disable_common(void);
diff --git a/arch/x86/include/asm/spinlock.h b/arch/x86/include/asm/spinlock.h
index e5e6caffec87..b7e5db876399 100644
--- a/arch/x86/include/asm/spinlock.h
+++ b/arch/x86/include/asm/spinlock.h
@@ -172,7 +172,7 @@ static inline int __ticket_spin_is_contended(raw_spinlock_t *lock)
 	return (((tmp >> TICKET_SHIFT) - tmp) & ((1 << TICKET_SHIFT) - 1)) > 1;
 }
 
-#ifndef CONFIG_PARAVIRT
+#ifndef CONFIG_PARAVIRT_SPINLOCKS
 
 static inline int __raw_spin_is_locked(raw_spinlock_t *lock)
 {
@@ -206,7 +206,7 @@ static __always_inline void __raw_spin_lock_flags(raw_spinlock_t *lock,
 	__raw_spin_lock(lock);
 }
 
-#endif
+#endif	/* CONFIG_PARAVIRT_SPINLOCKS */
 
 static inline void __raw_spin_unlock_wait(raw_spinlock_t *lock)
 {
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index df9d5f78385e..8820a73ae090 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -94,6 +94,7 @@ struct thread_info {
 #define TIF_FORCED_TF		24	/* true if TF in eflags artificially */
 #define TIF_DEBUGCTLMSR		25	/* uses thread_struct.debugctlmsr */
 #define TIF_DS_AREA_MSR		26      /* uses thread_struct.ds_area_msr */
+#define TIF_SYSCALL_FTRACE	27	/* for ftrace syscall instrumentation */
 
 #define _TIF_SYSCALL_TRACE	(1 << TIF_SYSCALL_TRACE)
 #define _TIF_NOTIFY_RESUME	(1 << TIF_NOTIFY_RESUME)
@@ -115,15 +116,17 @@ struct thread_info {
 #define _TIF_FORCED_TF		(1 << TIF_FORCED_TF)
 #define _TIF_DEBUGCTLMSR	(1 << TIF_DEBUGCTLMSR)
 #define _TIF_DS_AREA_MSR	(1 << TIF_DS_AREA_MSR)
+#define _TIF_SYSCALL_FTRACE	(1 << TIF_SYSCALL_FTRACE)
 
 /* work to do in syscall_trace_enter() */
 #define _TIF_WORK_SYSCALL_ENTRY	\
-	(_TIF_SYSCALL_TRACE | _TIF_SYSCALL_EMU | \
+	(_TIF_SYSCALL_TRACE | _TIF_SYSCALL_EMU | _TIF_SYSCALL_FTRACE |	\
 	 _TIF_SYSCALL_AUDIT | _TIF_SECCOMP | _TIF_SINGLESTEP)
 
 /* work to do in syscall_trace_leave() */
 #define _TIF_WORK_SYSCALL_EXIT	\
-	(_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | _TIF_SINGLESTEP)
+	(_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | _TIF_SINGLESTEP |	\
+	 _TIF_SYSCALL_FTRACE)
 
 /* work to do on interrupt/exception return */
 #define _TIF_WORK_MASK							\
@@ -132,7 +135,7 @@ struct thread_info {
 	   _TIF_SINGLESTEP|_TIF_SECCOMP|_TIF_SYSCALL_EMU))
 
 /* work to do on any return to user space */
-#define _TIF_ALLWORK_MASK (0x0000FFFF & ~_TIF_SECCOMP)
+#define _TIF_ALLWORK_MASK ((0x0000FFFF & ~_TIF_SECCOMP) | _TIF_SYSCALL_FTRACE)
 
 /* Only used for 64 bit */
 #define _TIF_DO_NOTIFY_MASK						\
diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index d3539f998f88..16a5c84b0329 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -152,7 +152,7 @@ struct tlb_state {
 	struct mm_struct *active_mm;
 	int state;
 };
-DECLARE_PER_CPU(struct tlb_state, cpu_tlbstate);
+DECLARE_PER_CPU_SHARED_ALIGNED(struct tlb_state, cpu_tlbstate);
 
 static inline void reset_lazy_tlbstate(void)
 {
diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h
index 744299c0b774..f44b49abca49 100644
--- a/arch/x86/include/asm/topology.h
+++ b/arch/x86/include/asm/topology.h
@@ -44,9 +44,6 @@
 
 #ifdef CONFIG_X86_32
 
-/* Mappings between node number and cpus on that node. */
-extern cpumask_t node_to_cpumask_map[];
-
 /* Mappings between logical cpu number and node number */
 extern int cpu_to_node_map[];
 
@@ -57,30 +54,8 @@ static inline int cpu_to_node(int cpu)
 }
 #define early_cpu_to_node(cpu)	cpu_to_node(cpu)
 
-/* Returns a bitmask of CPUs on Node 'node'.
- *
- * Side note: this function creates the returned cpumask on the stack
- * so with a high NR_CPUS count, excessive stack space is used.  The
- * cpumask_of_node function should be used whenever possible.
- */
-static inline cpumask_t node_to_cpumask(int node)
-{
-	return node_to_cpumask_map[node];
-}
-
-/* Returns a bitmask of CPUs on Node 'node'. */
-static inline const struct cpumask *cpumask_of_node(int node)
-{
-	return &node_to_cpumask_map[node];
-}
-
-static inline void setup_node_to_cpumask_map(void) { }
-
 #else /* CONFIG_X86_64 */
 
-/* Mappings between node number and cpus on that node. */
-extern cpumask_t *node_to_cpumask_map;
-
 /* Mappings between logical cpu number and node number */
 DECLARE_EARLY_PER_CPU(int, x86_cpu_to_node_map);
 
@@ -91,8 +66,6 @@ DECLARE_PER_CPU(int, node_number);
 #ifdef CONFIG_DEBUG_PER_CPU_MAPS
 extern int cpu_to_node(int cpu);
 extern int early_cpu_to_node(int cpu);
-extern const cpumask_t *cpumask_of_node(int node);
-extern cpumask_t node_to_cpumask(int node);
 
 #else	/* !CONFIG_DEBUG_PER_CPU_MAPS */
 
@@ -108,42 +81,32 @@ static inline int early_cpu_to_node(int cpu)
 	return early_per_cpu(x86_cpu_to_node_map, cpu);
 }
 
-/* Returns a pointer to the cpumask of CPUs on Node 'node'. */
-static inline const cpumask_t *cpumask_of_node(int node)
-{
-	return &node_to_cpumask_map[node];
-}
+#endif /* !CONFIG_DEBUG_PER_CPU_MAPS */
+
+#endif /* CONFIG_X86_64 */
 
-/* Returns a bitmask of CPUs on Node 'node'. */
-static inline cpumask_t node_to_cpumask(int node)
+/* Mappings between node number and cpus on that node. */
+extern cpumask_var_t node_to_cpumask_map[MAX_NUMNODES];
+
+#ifdef CONFIG_DEBUG_PER_CPU_MAPS
+extern const struct cpumask *cpumask_of_node(int node);
+#else
+/* Returns a pointer to the cpumask of CPUs on Node 'node'. */
+static inline const struct cpumask *cpumask_of_node(int node)
 {
 	return node_to_cpumask_map[node];
 }
-
-#endif /* !CONFIG_DEBUG_PER_CPU_MAPS */
+#endif
 
 extern void setup_node_to_cpumask_map(void);
 
 /*
- * Replace default node_to_cpumask_ptr with optimized version
- * Deprecated: use "const struct cpumask *mask = cpumask_of_node(node)"
- */
-#define node_to_cpumask_ptr(v, node)		\
-		const cpumask_t *v = cpumask_of_node(node)
-
-#define node_to_cpumask_ptr_next(v, node)	\
-			   v = cpumask_of_node(node)
-
-#endif /* CONFIG_X86_64 */
-
-/*
  * Returns the number of the node containing Node 'node'. This
  * architecture is flat, so it is a pretty simple function!
  */
 #define parent_node(node) (node)
 
 #define pcibus_to_node(bus) __pcibus_to_node(bus)
-#define pcibus_to_cpumask(bus) __pcibus_to_cpumask(bus)
 
 #ifdef CONFIG_X86_32
 extern unsigned long node_start_pfn[];
@@ -209,40 +172,24 @@ static inline int early_cpu_to_node(int cpu)
 	return 0;
 }
 
-static inline const cpumask_t *cpumask_of_node(int node)
-{
-	return &cpu_online_map;
-}
-static inline cpumask_t node_to_cpumask(int node)
+static inline const struct cpumask *cpumask_of_node(int node)
 {
-	return cpu_online_map;
+	return cpu_online_mask;
 }
 
 static inline void setup_node_to_cpumask_map(void) { }
 
-/*
- * Replace default node_to_cpumask_ptr with optimized version
- * Deprecated: use "const struct cpumask *mask = cpumask_of_node(node)"
- */
-#define node_to_cpumask_ptr(v, node)		\
-		const cpumask_t *v = cpumask_of_node(node)
-
-#define node_to_cpumask_ptr_next(v, node)	\
-			   v = cpumask_of_node(node)
 #endif
 
 #include <asm-generic/topology.h>
 
-extern cpumask_t cpu_coregroup_map(int cpu);
 extern const struct cpumask *cpu_coregroup_mask(int cpu);
 
 #ifdef ENABLE_TOPO_DEFINES
 #define topology_physical_package_id(cpu)	(cpu_data(cpu).phys_proc_id)
 #define topology_core_id(cpu)			(cpu_data(cpu).cpu_core_id)
-#define topology_core_siblings(cpu)		(per_cpu(cpu_core_map, cpu))
-#define topology_thread_siblings(cpu)		(per_cpu(cpu_sibling_map, cpu))
-#define topology_core_cpumask(cpu)		(&per_cpu(cpu_core_map, cpu))
-#define topology_thread_cpumask(cpu)		(&per_cpu(cpu_sibling_map, cpu))
+#define topology_core_cpumask(cpu)		(per_cpu(cpu_core_map, cpu))
+#define topology_thread_cpumask(cpu)		(per_cpu(cpu_sibling_map, cpu))
 
 /* indicates that pointers to the topology cpumask_t maps are valid */
 #define arch_provides_topology_pointers		yes
@@ -253,10 +200,10 @@ static inline void arch_fix_phys_package_id(int num, u32 slot)
 }
 
 struct pci_bus;
-void set_pci_bus_resources_arch_default(struct pci_bus *b);
+void x86_pci_root_bus_res_quirks(struct pci_bus *b);
 
 #ifdef CONFIG_SMP
-#define mc_capable()	(cpus_weight(per_cpu(cpu_core_map, 0)) != nr_cpu_ids)
+#define mc_capable()	(cpumask_weight(cpu_core_mask(0)) != nr_cpu_ids)
 #define smt_capable()			(smp_num_siblings > 1)
 #endif
 
diff --git a/arch/x86/include/asm/uv/uv_mmrs.h b/arch/x86/include/asm/uv/uv_mmrs.h
index db68ac8a5ac2..2cae46c7c8a2 100644
--- a/arch/x86/include/asm/uv/uv_mmrs.h
+++ b/arch/x86/include/asm/uv/uv_mmrs.h
@@ -17,6 +17,11 @@
 /* ========================================================================= */
 /*                           UVH_BAU_DATA_CONFIG                             */
 /* ========================================================================= */
+#define UVH_LB_BAU_MISC_CONTROL 0x320170UL
+#define UV_ENABLE_INTD_SOFT_ACK_MODE_SHIFT 15
+#define UV_INTD_SOFT_ACK_TIMEOUT_PERIOD_SHIFT 16
+#define UV_INTD_SOFT_ACK_TIMEOUT_PERIOD 0x000000000bUL
+/* 1011 timebase 7 (168millisec) * 3 ticks -> 500ms */
 #define UVH_BAU_DATA_CONFIG 0x61680UL
 #define UVH_BAU_DATA_CONFIG_32 0x0438
 
diff --git a/arch/x86/include/asm/xen/page.h b/arch/x86/include/asm/xen/page.h
index 1a918dde46b5..018a0a400799 100644
--- a/arch/x86/include/asm/xen/page.h
+++ b/arch/x86/include/asm/xen/page.h
@@ -124,7 +124,8 @@ static inline unsigned long mfn_to_local_pfn(unsigned long mfn)
 
 /* VIRT <-> MACHINE conversion */
 #define virt_to_machine(v)	(phys_to_machine(XPADDR(__pa(v))))
-#define virt_to_mfn(v)		(pfn_to_mfn(PFN_DOWN(__pa(v))))
+#define virt_to_pfn(v)          (PFN_DOWN(__pa(v)))
+#define virt_to_mfn(v)		(pfn_to_mfn(virt_to_pfn(v)))
 #define mfn_to_virt(m)		(__va(mfn_to_pfn(m) << PAGE_SHIFT))
 
 static inline unsigned long pte_mfn(pte_t pte)
diff --git a/arch/x86/include/asm/xsave.h b/arch/x86/include/asm/xsave.h
index 08e9a1ac07a9..727acc152344 100644
--- a/arch/x86/include/asm/xsave.h
+++ b/arch/x86/include/asm/xsave.h
@@ -7,6 +7,7 @@
 
 #define XSTATE_FP	0x1
 #define XSTATE_SSE	0x2
+#define XSTATE_YMM	0x4
 
 #define XSTATE_FPSSE	(XSTATE_FP | XSTATE_SSE)
 
@@ -15,7 +16,7 @@
 /*
  * These are the features that the OS can handle currently.
  */
-#define XCNTXT_MASK	(XSTATE_FP | XSTATE_SSE)
+#define XCNTXT_MASK	(XSTATE_FP | XSTATE_SSE | XSTATE_YMM)
 
 #ifdef CONFIG_X86_64
 #define REX_PREFIX	"0x48, "