Merge branch 'linux-3.4.35' into rel-17

Bug 1243631

Change-Id: I915826047b2e20f0ad0a7d75df295c6cbf6e5b0a

47 files changed, 535 insertions, 390 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 7cbdfdac3c7c..29cf70ff6b43 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -1244,10 +1244,6 @@ config HAVE_ARCH_BOOTMEM
 	def_bool y
 	depends on X86_32 && NUMA
 
-config HAVE_ARCH_ALLOC_REMAP
-	def_bool y
-	depends on X86_32 && NUMA
-
 config ARCH_HAVE_MEMORY_PRESENT
 	def_bool y
 	depends on X86_32 && DISCONTIGMEM
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index b1c611e6da67..f1276aaeffdb 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -85,7 +85,7 @@ endif
 ifdef CONFIG_X86_X32
 	x32_ld_ok := $(call try-run,\
 			/bin/echo -e '1: .quad 1b' | \
-			$(CC) $(KBUILD_AFLAGS) -c -xassembler -o "$$TMP" - && \
+			$(CC) $(KBUILD_AFLAGS) -c -x assembler -o "$$TMP" - && \
 			$(OBJCOPY) -O elf32-x86-64 "$$TMP" "$$TMPO" && \
 			$(LD) -m elf32_x86_64 "$$TMPO" -o "$$TMP",y,n)
         ifeq ($(x32_ld_ok),y)
diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile
index e398bb5d63bb..8a84501acb1b 100644
--- a/arch/x86/boot/compressed/Makefile
+++ b/arch/x86/boot/compressed/Makefile
@@ -28,6 +28,9 @@ VMLINUX_OBJS = $(obj)/vmlinux.lds $(obj)/head_$(BITS).o $(obj)/misc.o \
 	$(obj)/string.o $(obj)/cmdline.o $(obj)/early_serial_console.o \
 	$(obj)/piggy.o
 
+$(obj)/eboot.o: KBUILD_CFLAGS += -fshort-wchar -mno-red-zone
+$(obj)/efi_stub_$(BITS).o: KBUILD_CLFAGS += -fshort-wchar -mno-red-zone
+
 ifeq ($(CONFIG_EFI_STUB), y)
 	VMLINUX_OBJS += $(obj)/eboot.o $(obj)/efi_stub_$(BITS).o
 endif
diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c
index 0cdfc0d2315e..8bb90707cb55 100644
--- a/arch/x86/boot/compressed/eboot.c
+++ b/arch/x86/boot/compressed/eboot.c
@@ -12,6 +12,8 @@
 #include <asm/setup.h>
 #include <asm/desc.h>
 
+#undef memcpy			/* Use memcpy from misc.c */
+
 #include "eboot.h"
 
 static efi_system_table_t *sys_table;
diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S
index e3e734005e19..66c4cae439c9 100644
--- a/arch/x86/ia32/ia32entry.S
+++ b/arch/x86/ia32/ia32entry.S
@@ -205,7 +205,7 @@ sysexit_from_sys_call:
 	testl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT),TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET)
 	jnz ia32_ret_from_sys_call
 	TRACE_IRQS_ON
-	sti
+	ENABLE_INTERRUPTS(CLBR_NONE)
 	movl %eax,%esi		/* second arg, syscall return value */
 	cmpl $-MAX_ERRNO,%eax	/* is it an error ? */
 	jbe 1f
@@ -215,7 +215,7 @@ sysexit_from_sys_call:
 	call __audit_syscall_exit
 	movq RAX-ARGOFFSET(%rsp),%rax	/* reload syscall return value */
 	movl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT),%edi
-	cli
+	DISABLE_INTERRUPTS(CLBR_NONE)
 	TRACE_IRQS_OFF
 	testl %edi,TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET)
 	jz \exit
diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h
index c9dcc181d4d1..da37433e3628 100644
--- a/arch/x86/include/asm/efi.h
+++ b/arch/x86/include/asm/efi.h
@@ -94,10 +94,12 @@ extern void __iomem *efi_ioremap(unsigned long addr, unsigned long size,
 #endif /* CONFIG_X86_32 */
 
 extern int add_efi_memmap;
+extern unsigned long x86_efi_facility;
 extern void efi_set_executable(efi_memory_desc_t *md, bool executable);
 extern int efi_memblock_x86_reserve_range(void);
 extern void efi_call_phys_prelog(void);
 extern void efi_call_phys_epilog(void);
+extern void efi_unmap_memmap(void);
 
 #ifndef CONFIG_EFI
 /*
diff --git a/arch/x86/include/asm/fpu-internal.h b/arch/x86/include/asm/fpu-internal.h
index 4fa88154e4de..92e05b6c84f8 100644
--- a/arch/x86/include/asm/fpu-internal.h
+++ b/arch/x86/include/asm/fpu-internal.h
@@ -334,14 +334,17 @@ static inline void __thread_fpu_begin(struct task_struct *tsk)
 typedef struct { int preload; } fpu_switch_t;
 
 /*
- * FIXME! We could do a totally lazy restore, but we need to
- * add a per-cpu "this was the task that last touched the FPU
- * on this CPU" variable, and the task needs to have a "I last
- * touched the FPU on this CPU" and check them.
+ * Must be run with preemption disabled: this clears the fpu_owner_task,
+ * on this CPU.
  *
- * We don't do that yet, so "fpu_lazy_restore()" always returns
- * false, but some day..
+ * This will disable any lazy FPU state restore of the current FPU state,
+ * but if the current thread owns the FPU, it will still be saved by.
  */
+static inline void __cpu_disable_lazy_restore(unsigned int cpu)
+{
+	per_cpu(fpu_owner_task, cpu) = NULL;
+}
+
 static inline int fpu_lazy_restore(struct task_struct *new, unsigned int cpu)
 {
 	return new == percpu_read_stable(fpu_owner_task) &&
diff --git a/arch/x86/include/asm/mmzone_32.h b/arch/x86/include/asm/mmzone_32.h
index 55728e121473..5e0286f8081a 100644
--- a/arch/x86/include/asm/mmzone_32.h
+++ b/arch/x86/include/asm/mmzone_32.h
@@ -14,12 +14,6 @@ extern struct pglist_data *node_data[];
 
 #include <asm/numaq.h>
 
-extern void resume_map_numa_kva(pgd_t *pgd);
-
-#else /* !CONFIG_NUMA */
-
-static inline void resume_map_numa_kva(pgd_t *pgd) {}
-
 #endif /* CONFIG_NUMA */
 
 #ifdef CONFIG_DISCONTIGMEM
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 49afb3f41eb6..3f3dd526b3b8 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -142,12 +142,16 @@ static inline unsigned long pmd_pfn(pmd_t pmd)
 	return (pmd_val(pmd) & PTE_PFN_MASK) >> PAGE_SHIFT;
 }
 
+static inline unsigned long pud_pfn(pud_t pud)
+{
+	return (pud_val(pud) & PTE_PFN_MASK) >> PAGE_SHIFT;
+}
+
 #define pte_page(pte)	pfn_to_page(pte_pfn(pte))
 
 static inline int pmd_large(pmd_t pte)
 {
-	return (pmd_flags(pte) & (_PAGE_PSE | _PAGE_PRESENT)) ==
-		(_PAGE_PSE | _PAGE_PRESENT);
+	return pmd_flags(pte) & _PAGE_PSE;
 }
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
@@ -415,7 +419,13 @@ static inline int pte_hidden(pte_t pte)
 
 static inline int pmd_present(pmd_t pmd)
 {
-	return pmd_flags(pmd) & _PAGE_PRESENT;
+	/*
+	 * Checking for _PAGE_PSE is needed too because
+	 * split_huge_page will temporarily clear the present bit (but
+	 * the _PAGE_PSE flag will remain set at all times while the
+	 * _PAGE_PRESENT bit is clear).
+	 */
+	return pmd_flags(pmd) & (_PAGE_PRESENT | _PAGE_PROTNONE | _PAGE_PSE);
 }
 
 static inline int pmd_none(pmd_t pmd)
diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h
index dcfde52979c3..19f16ebaf4fa 100644
--- a/arch/x86/include/asm/ptrace.h
+++ b/arch/x86/include/asm/ptrace.h
@@ -205,21 +205,14 @@ static inline bool user_64bit_mode(struct pt_regs *regs)
 }
 #endif
 
-/*
- * X86_32 CPUs don't save ss and esp if the CPU is already in kernel mode
- * 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_stack_pointer(struct pt_regs *regs)
-{
 #ifdef CONFIG_X86_32
-	return (unsigned long)(&regs->sp);
+extern unsigned long kernel_stack_pointer(struct pt_regs *regs);
 #else
+static inline unsigned long kernel_stack_pointer(struct pt_regs *regs)
+{
 	return regs->sp;
-#endif
 }
+#endif
 
 #define GET_IP(regs) ((regs)->ip)
 #define GET_FP(regs) ((regs)->bp)
diff --git a/arch/x86/include/asm/xen/page.h b/arch/x86/include/asm/xen/page.h
index c34f96c2f7a0..1bd321d00f26 100644
--- a/arch/x86/include/asm/xen/page.h
+++ b/arch/x86/include/asm/xen/page.h
@@ -50,7 +50,8 @@ extern unsigned long set_phys_range_identity(unsigned long pfn_s,
 
 extern int m2p_add_override(unsigned long mfn, struct page *page,
 			    struct gnttab_map_grant_ref *kmap_op);
-extern int m2p_remove_override(struct page *page, bool clear_pte);
+extern int m2p_remove_override(struct page *page,
+				struct gnttab_map_grant_ref *kmap_op);
 extern struct page *m2p_find_override(unsigned long mfn);
 extern unsigned long m2p_find_override_pfn(unsigned long mfn, unsigned long pfn);
 
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index 73ef56c5a8b3..bda833c5f6ce 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -160,7 +160,7 @@ static const unsigned char * const k7_nops[ASM_NOP_MAX+2] =
 #endif
 
 #ifdef P6_NOP1
-static const unsigned char  __initconst_or_module p6nops[] =
+static const unsigned char p6nops[] =
 {
 	P6_NOP1,
 	P6_NOP2,
diff --git a/arch/x86/kernel/apic/x2apic_phys.c b/arch/x86/kernel/apic/x2apic_phys.c
index 991e315f4227..db31a2cfc9a9 100644
--- a/arch/x86/kernel/apic/x2apic_phys.c
+++ b/arch/x86/kernel/apic/x2apic_phys.c
@@ -20,18 +20,19 @@ static int set_x2apic_phys_mode(char *arg)
 }
 early_param("x2apic_phys", set_x2apic_phys_mode);
 
-static int x2apic_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
+static bool x2apic_fadt_phys(void)
 {
-	if (x2apic_phys)
-		return x2apic_enabled();
-	else if ((acpi_gbl_FADT.header.revision >= FADT2_REVISION_ID) &&
-		(acpi_gbl_FADT.flags & ACPI_FADT_APIC_PHYSICAL) &&
-		x2apic_enabled()) {
+	if ((acpi_gbl_FADT.header.revision >= FADT2_REVISION_ID) &&
+		(acpi_gbl_FADT.flags & ACPI_FADT_APIC_PHYSICAL)) {
 		printk(KERN_DEBUG "System requires x2apic physical mode\n");
-		return 1;
+		return true;
 	}
-	else
-		return 0;
+	return false;
+}
+
+static int x2apic_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
+{
+	return x2apic_enabled() && (x2apic_phys || x2apic_fadt_phys());
 }
 
 static void
@@ -114,7 +115,7 @@ static void init_x2apic_ldr(void)
 
 static int x2apic_phys_probe(void)
 {
-	if (x2apic_mode && x2apic_phys)
+	if (x2apic_mode && (x2apic_phys || x2apic_fadt_phys()))
 		return 1;
 
 	return apic == &apic_x2apic_phys;
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 146bb6218eec..a9c8a46dd7d3 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -598,6 +598,34 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c)
 		}
 	}
 
+	/*
+	 * The way access filter has a performance penalty on some workloads.
+	 * Disable it on the affected CPUs.
+	 */
+	if ((c->x86 == 0x15) &&
+	    (c->x86_model >= 0x02) && (c->x86_model < 0x20)) {
+		u64 val;
+
+		if (!rdmsrl_safe(0xc0011021, &val) && !(val & 0x1E)) {
+			val |= 0x1E;
+			checking_wrmsrl(0xc0011021, val);
+		}
+	}
+
+	/*
+	 * The way access filter has a performance penalty on some workloads.
+	 * Disable it on the affected CPUs.
+	 */
+	if ((c->x86 == 0x15) &&
+	    (c->x86_model >= 0x02) && (c->x86_model < 0x20)) {
+		u64 val;
+
+		if (!rdmsrl_safe(0xc0011021, &val) && !(val & 0x1E)) {
+			val |= 0x1E;
+			checking_wrmsrl(0xc0011021, val);
+		}
+	}
+
 	cpu_detect_cache_sizes(c);
 
 	/* Multi core CPU? */
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index 0a630dd4b620..646d192b18a2 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -68,7 +68,8 @@ static void __init ms_hyperv_init_platform(void)
 	printk(KERN_INFO "HyperV: features 0x%x, hints 0x%x\n",
 	       ms_hyperv.features, ms_hyperv.hints);
 
-	clocksource_register_hz(&hyperv_cs, NSEC_PER_SEC/100);
+	if (ms_hyperv.features & HV_X64_MSR_TIME_REF_COUNT_AVAILABLE)
+		clocksource_register_hz(&hyperv_cs, NSEC_PER_SEC/100);
 }
 
 const __refconst struct hypervisor_x86 x86_hyper_ms_hyperv = {
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index 62d61e9976eb..298dc000378a 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -1076,6 +1076,9 @@ void __init memblock_x86_fill(void)
 		memblock_add(ei->addr, ei->size);
 	}
 
+	/* throw away partial pages */
+	memblock_trim_memory(PAGE_SIZE);
+
 	memblock_dump_all();
 }
 
diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S
index 7b784f4ef1e4..2af4ccd88d16 100644
--- a/arch/x86/kernel/entry_32.S
+++ b/arch/x86/kernel/entry_32.S
@@ -1025,7 +1025,7 @@ ENTRY(xen_sysenter_target)
 
 ENTRY(xen_hypervisor_callback)
 	CFI_STARTPROC
-	pushl_cfi $0
+	pushl_cfi $-1 /* orig_ax = -1 => not a system call */
 	SAVE_ALL
 	TRACE_IRQS_OFF
 
@@ -1067,14 +1067,15 @@ ENTRY(xen_failsafe_callback)
 2:	mov 8(%esp),%es
 3:	mov 12(%esp),%fs
 4:	mov 16(%esp),%gs
+	/* EAX == 0 => Category 1 (Bad segment)
+	   EAX != 0 => Category 2 (Bad IRET) */
 	testl %eax,%eax
 	popl_cfi %eax
 	lea 16(%esp),%esp
 	CFI_ADJUST_CFA_OFFSET -16
 	jz 5f
-	addl $16,%esp
-	jmp iret_exc		# EAX != 0 => Category 2 (Bad IRET)
-5:	pushl_cfi $0		# EAX == 0 => Category 1 (Bad segment)
+	jmp iret_exc
+5:	pushl_cfi $-1 /* orig_ax = -1 => not a system call */
 	SAVE_ALL
 	jmp ret_from_exception
 	CFI_ENDPROC
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index cdc79b5cfcd9..bd6f59203b5f 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -1351,7 +1351,7 @@ ENTRY(xen_failsafe_callback)
 	CFI_RESTORE r11
 	addq $0x30,%rsp
 	CFI_ADJUST_CFA_OFFSET -0x30
-	pushq_cfi $0
+	pushq_cfi $-1 /* orig_ax = -1 => not a system call */
 	SAVE_ALL
 	jmp error_exit
 	CFI_ENDPROC
diff --git a/arch/x86/kernel/head.c b/arch/x86/kernel/head.c
index 48d9d4ea1020..992f442ca155 100644
--- a/arch/x86/kernel/head.c
+++ b/arch/x86/kernel/head.c
@@ -5,8 +5,6 @@
 #include <asm/setup.h>
 #include <asm/bios_ebda.h>
 
-#define BIOS_LOWMEM_KILOBYTES 0x413
-
 /*
  * The BIOS places the EBDA/XBDA at the top of conventional
  * memory, and usually decreases the reported amount of
@@ -16,17 +14,30 @@
  * chipset: reserve a page before VGA to prevent PCI prefetch
  * into it (errata #56). Usually the page is reserved anyways,
  * unless you have no PS/2 mouse plugged in.
+ *
+ * This functions is deliberately very conservative.  Losing
+ * memory in the bottom megabyte is rarely a problem, as long
+ * as we have enough memory to install the trampoline.  Using
+ * memory that is in use by the BIOS or by some DMA device
+ * the BIOS didn't shut down *is* a big problem.
  */
+
+#define BIOS_LOWMEM_KILOBYTES	0x413
+#define LOWMEM_CAP		0x9f000U	/* Absolute maximum */
+#define INSANE_CUTOFF		0x20000U	/* Less than this = insane */
+
 void __init reserve_ebda_region(void)
 {
 	unsigned int lowmem, ebda_addr;
 
-	/* To determine the position of the EBDA and the */
-	/* end of conventional memory, we need to look at */
-	/* the BIOS data area. In a paravirtual environment */
-	/* that area is absent. We'll just have to assume */
-	/* that the paravirt case can handle memory setup */
-	/* correctly, without our help. */
+	/*
+	 * To determine the position of the EBDA and the
+	 * end of conventional memory, we need to look at
+	 * the BIOS data area. In a paravirtual environment
+	 * that area is absent. We'll just have to assume
+	 * that the paravirt case can handle memory setup
+	 * correctly, without our help.
+	 */
 	if (paravirt_enabled())
 		return;
 
@@ -37,19 +48,23 @@ void __init reserve_ebda_region(void)
 	/* start of EBDA area */
 	ebda_addr = get_bios_ebda();
 
-	/* Fixup: bios puts an EBDA in the top 64K segment */
-	/* of conventional memory, but does not adjust lowmem. */
-	if ((lowmem - ebda_addr) <= 0x10000)
-		lowmem = ebda_addr;
+	/*
+	 * Note: some old Dells seem to need 4k EBDA without
+	 * reporting so, so just consider the memory above 0x9f000
+	 * to be off limits (bugzilla 2990).
+	 */
+
+	/* If the EBDA address is below 128K, assume it is bogus */
+	if (ebda_addr < INSANE_CUTOFF)
+		ebda_addr = LOWMEM_CAP;
 
-	/* Fixup: bios does not report an EBDA at all. */
-	/* Some old Dells seem to need 4k anyhow (bugzilla 2990) */
-	if ((ebda_addr == 0) && (lowmem >= 0x9f000))
-		lowmem = 0x9f000;
+	/* If lowmem is less than 128K, assume it is bogus */
+	if (lowmem < INSANE_CUTOFF)
+		lowmem = LOWMEM_CAP;
 
-	/* Paranoia: should never happen, but... */
-	if ((lowmem == 0) || (lowmem >= 0x100000))
-		lowmem = 0x9f000;
+	/* Use the lower of the lowmem and EBDA markers as the cutoff */
+	lowmem = min(lowmem, ebda_addr);
+	lowmem = min(lowmem, LOWMEM_CAP); /* Absolute cap */
 
 	/* reserve all memory between lowmem and the 1MB mark */
 	memblock_reserve(lowmem, 0x100000 - lowmem);
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index ad0de0c2714e..2861b4cafd2e 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -431,7 +431,7 @@ void hpet_msi_unmask(struct irq_data *data)
 
 	/* unmask it */
 	cfg = hpet_readl(HPET_Tn_CFG(hdev->num));
-	cfg |= HPET_TN_FSB;
+	cfg |= HPET_TN_ENABLE | HPET_TN_FSB;
 	hpet_writel(cfg, HPET_Tn_CFG(hdev->num));
 }
 
@@ -442,7 +442,7 @@ void hpet_msi_mask(struct irq_data *data)
 
 	/* mask it */
 	cfg = hpet_readl(HPET_Tn_CFG(hdev->num));
-	cfg &= ~HPET_TN_FSB;
+	cfg &= ~(HPET_TN_ENABLE | HPET_TN_FSB);
 	hpet_writel(cfg, HPET_Tn_CFG(hdev->num));
 }
 
diff --git a/arch/x86/kernel/microcode_amd.c b/arch/x86/kernel/microcode_amd.c
index 8a2ce8fd41c0..5d8cf0d6796c 100644
--- a/arch/x86/kernel/microcode_amd.c
+++ b/arch/x86/kernel/microcode_amd.c
@@ -97,6 +97,7 @@ static unsigned int verify_ucode_size(int cpu, u32 patch_size,
 #define F1XH_MPB_MAX_SIZE 2048
 #define F14H_MPB_MAX_SIZE 1824
 #define F15H_MPB_MAX_SIZE 4096
+#define F16H_MPB_MAX_SIZE 3458
 
 	switch (c->x86) {
 	case 0x14:
@@ -105,6 +106,9 @@ static unsigned int verify_ucode_size(int cpu, u32 patch_size,
 	case 0x15:
 		max_size = F15H_MPB_MAX_SIZE;
 		break;
+	case 0x16:
+		max_size = F16H_MPB_MAX_SIZE;
+		break;
 	default:
 		max_size = F1XH_MPB_MAX_SIZE;
 		break;
@@ -143,11 +147,12 @@ static int get_matching_microcode(int cpu, const u8 *ucode_ptr,
 				  unsigned int *current_size)
 {
 	struct microcode_header_amd *mc_hdr;
-	unsigned int actual_size;
+	unsigned int actual_size, patch_size;
 	u16 equiv_cpu_id;
 
 	/* size of the current patch we're staring at */
-	*current_size = *(u32 *)(ucode_ptr + 4) + SECTION_HDR_SIZE;
+	patch_size = *(u32 *)(ucode_ptr + 4);
+	*current_size = patch_size + SECTION_HDR_SIZE;
 
 	equiv_cpu_id = find_equiv_id();
 	if (!equiv_cpu_id)
@@ -174,7 +179,7 @@ static int get_matching_microcode(int cpu, const u8 *ucode_ptr,
 	/*
 	 * now that the header looks sane, verify its size
 	 */
-	actual_size = verify_ucode_size(cpu, *current_size, leftover_size);
+	actual_size = verify_ucode_size(cpu, patch_size, leftover_size);
 	if (!actual_size)
 		return 0;
 
diff --git a/arch/x86/kernel/msr.c b/arch/x86/kernel/msr.c
index eb113693f043..8563b64e18cf 100644
--- a/arch/x86/kernel/msr.c
+++ b/arch/x86/kernel/msr.c
@@ -174,6 +174,9 @@ static int msr_open(struct inode *inode, struct file *file)
 	unsigned int cpu;
 	struct cpuinfo_x86 *c;
 
+	if (!capable(CAP_SYS_RAWIO))
+		return -EPERM;
+
 	cpu = iminor(file->f_path.dentry->d_inode);
 	if (cpu >= nr_cpu_ids || !cpu_online(cpu))
 		return -ENXIO;	/* No such CPU */
diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index cf1178332bc0..c4410fb4938f 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -21,6 +21,7 @@
 #include <linux/signal.h>
 #include <linux/perf_event.h>
 #include <linux/hw_breakpoint.h>
+#include <linux/module.h>
 
 #include <asm/uaccess.h>
 #include <asm/pgtable.h>
@@ -165,6 +166,35 @@ static inline bool invalid_selector(u16 value)
 
 #define FLAG_MASK		FLAG_MASK_32
 
+/*
+ * X86_32 CPUs don't save ss and esp if the CPU is already in kernel mode
+ * 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'.
+ *
+ * Now, if the stack is empty, '&regs->sp' is out of range. In this
+ * case we try to take the previous stack. To always return a non-null
+ * stack pointer we fall back to regs as stack if no previous stack
+ * exists.
+ *
+ * This is valid only for kernel mode traps.
+ */
+unsigned long kernel_stack_pointer(struct pt_regs *regs)
+{
+	unsigned long context = (unsigned long)regs & ~(THREAD_SIZE - 1);
+	unsigned long sp = (unsigned long)&regs->sp;
+	struct thread_info *tinfo;
+
+	if (context == (sp & ~(THREAD_SIZE - 1)))
+		return sp;
+
+	tinfo = (struct thread_info *)context;
+	if (tinfo->previous_esp)
+		return tinfo->previous_esp;
+
+	return (unsigned long)regs;
+}
+EXPORT_SYMBOL_GPL(kernel_stack_pointer);
+
 static unsigned long *pt_regs_access(struct pt_regs *regs, unsigned long regno)
 {
 	BUILD_BUG_ON(offsetof(struct pt_regs, bx) != 0);
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index 3034ee5afb0f..df1b604c0c1f 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -619,7 +619,7 @@ static void native_machine_emergency_restart(void)
 			break;
 
 		case BOOT_EFI:
-			if (efi_enabled)
+			if (efi_enabled(EFI_RUNTIME_SERVICES))
 				efi.reset_system(reboot_mode ?
 						 EFI_RESET_WARM :
 						 EFI_RESET_COLD,
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index d6c956e674cc..dc29333e1bb9 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -621,6 +621,83 @@ static __init void reserve_ibft_region(void)
 
 static unsigned reserve_low = CONFIG_X86_RESERVE_LOW << 10;
 
+static bool __init snb_gfx_workaround_needed(void)
+{
+#ifdef CONFIG_PCI
+	int i;
+	u16 vendor, devid;
+	static const u16 snb_ids[] = {
+		0x0102,
+		0x0112,
+		0x0122,
+		0x0106,
+		0x0116,
+		0x0126,
+		0x010a,
+	};
+
+	/* Assume no if something weird is going on with PCI */
+	if (!early_pci_allowed())
+		return false;
+
+	vendor = read_pci_config_16(0, 2, 0, PCI_VENDOR_ID);
+	if (vendor != 0x8086)
+		return false;
+
+	devid = read_pci_config_16(0, 2, 0, PCI_DEVICE_ID);
+	for (i = 0; i < ARRAY_SIZE(snb_ids); i++)
+		if (devid == snb_ids[i])
+			return true;
+#endif
+
+	return false;
+}
+
+/*
+ * Sandy Bridge graphics has trouble with certain ranges, exclude
+ * them from allocation.
+ */
+static void __init trim_snb_memory(void)
+{
+	static const unsigned long bad_pages[] = {
+		0x20050000,
+		0x20110000,
+		0x20130000,
+		0x20138000,
+		0x40004000,
+	};
+	int i;
+
+	if (!snb_gfx_workaround_needed())
+		return;
+
+	printk(KERN_DEBUG "reserving inaccessible SNB gfx pages\n");
+
+	/*
+	 * Reserve all memory below the 1 MB mark that has not
+	 * already been reserved.
+	 */
+	memblock_reserve(0, 1<<20);
+
+	for (i = 0; i < ARRAY_SIZE(bad_pages); i++) {
+		if (memblock_reserve(bad_pages[i], PAGE_SIZE))
+			printk(KERN_WARNING "failed to reserve 0x%08lx\n",
+			       bad_pages[i]);
+	}
+}
+
+/*
+ * Here we put platform-specific memory range workarounds, i.e.
+ * memory known to be corrupt or otherwise in need to be reserved on
+ * specific platforms.
+ *
+ * If this gets used more widely it could use a real dispatch mechanism.
+ */
+static void __init trim_platform_memory_ranges(void)
+{
+	trim_snb_memory();
+}
+
 static void __init trim_bios_range(void)
 {
 	/*
@@ -641,6 +718,7 @@ static void __init trim_bios_range(void)
 	 * take them out.
 	 */
 	e820_remove_range(BIOS_BEGIN, BIOS_END - BIOS_BEGIN, E820_RAM, 1);
+
 	sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map);
 }
 
@@ -741,15 +819,15 @@ void __init setup_arch(char **cmdline_p)
 #ifdef CONFIG_EFI
 	if (!strncmp((char *)&boot_params.efi_info.efi_loader_signature,
 		     "EL32", 4)) {
-		efi_enabled = 1;
-		efi_64bit = false;
+		set_bit(EFI_BOOT, &x86_efi_facility);
 	} else if (!strncmp((char *)&boot_params.efi_info.efi_loader_signature,
 		     "EL64", 4)) {
-		efi_enabled = 1;
-		efi_64bit = true;
+		set_bit(EFI_BOOT, &x86_efi_facility);
+		set_bit(EFI_64BIT, &x86_efi_facility);
 	}
-	if (efi_enabled && efi_memblock_x86_reserve_range())
-		efi_enabled = 0;
+
+	if (efi_enabled(EFI_BOOT))
+		efi_memblock_x86_reserve_range();
 #endif
 
 	x86_init.oem.arch_setup();
@@ -822,7 +900,7 @@ void __init setup_arch(char **cmdline_p)
 
 	finish_e820_parsing();
 
-	if (efi_enabled)
+	if (efi_enabled(EFI_BOOT))
 		efi_init();
 
 	dmi_scan_machine();
@@ -905,7 +983,7 @@ void __init setup_arch(char **cmdline_p)
 	 * The EFI specification says that boot service code won't be called
 	 * after ExitBootServices(). This is, in fact, a lie.
 	 */
-	if (efi_enabled)
+	if (efi_enabled(EFI_MEMMAP))
 		efi_reserve_boot_services();
 
 	/* preallocate 4k for mptable mpc */
@@ -920,6 +998,8 @@ void __init setup_arch(char **cmdline_p)
 
 	setup_trampolines();
 
+	trim_platform_memory_ranges();
+
 	init_gbpages();
 
 	/* max_pfn_mapped is updated here */
@@ -928,8 +1008,22 @@ void __init setup_arch(char **cmdline_p)
 
 #ifdef CONFIG_X86_64
 	if (max_pfn > max_low_pfn) {
-		max_pfn_mapped = init_memory_mapping(1UL<<32,
-						     max_pfn<<PAGE_SHIFT);
+		int i;
+		unsigned long start, end;
+		unsigned long start_pfn, end_pfn;
+
+		for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn,
+							 NULL) {
+
+			end = PFN_PHYS(end_pfn);
+			if (end <= (1UL<<32))
+				continue;
+
+			start = PFN_PHYS(start_pfn);
+			max_pfn_mapped = init_memory_mapping(
+						max((1UL<<32), start), end);
+		}
+
 		/* can we preseve max_low_pfn ?*/
 		max_low_pfn = max_pfn;
 	}
@@ -1027,7 +1121,7 @@ void __init setup_arch(char **cmdline_p)
 
 #ifdef CONFIG_VT
 #if defined(CONFIG_VGA_CONSOLE)
-	if (!efi_enabled || (efi_mem_type(0xa0000) != EFI_CONVENTIONAL_MEMORY))
+	if (!efi_enabled(EFI_BOOT) || (efi_mem_type(0xa0000) != EFI_CONVENTIONAL_MEMORY))
 		conswitchp = &vga_con;
 #elif defined(CONFIG_DUMMY_CONSOLE)
 	conswitchp = &dummy_con;
@@ -1042,6 +1136,18 @@ void __init setup_arch(char **cmdline_p)
 	mcheck_init();
 
 	arch_init_ideal_nops();
+
+#ifdef CONFIG_EFI
+	/* Once setup is done above, unmap the EFI memory map on
+	 * mismatched firmware/kernel archtectures since there is no
+	 * support for runtime services.
+	 */
+	if (efi_enabled(EFI_BOOT) &&
+	    IS_ENABLED(CONFIG_X86_64) != efi_enabled(EFI_64BIT)) {
+		pr_info("efi: Setup done, disabling due to 32/64-bit mismatch\n");
+		efi_unmap_memmap();
+	}
+#endif
 }
 
 #ifdef CONFIG_X86_32
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 6e1e406038c2..849cdcf2e76a 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -66,6 +66,8 @@
 #include <asm/mwait.h>
 #include <asm/apic.h>
 #include <asm/io_apic.h>
+#include <asm/i387.h>
+#include <asm/fpu-internal.h>
 #include <asm/setup.h>
 #include <asm/uv/uv.h>
 #include <linux/mc146818rtc.h>
@@ -851,6 +853,9 @@ int __cpuinit native_cpu_up(unsigned int cpu)
 
 	per_cpu(cpu_state, cpu) = CPU_UP_PREPARE;
 
+	/* the FPU context is blank, nobody can own it */
+	__cpu_disable_lazy_restore(cpu);
+
 	err = do_boot_cpu(apicid, cpu);
 	if (err) {
 		pr_debug("do_boot_cpu failed %d\n", err);
diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h
index 26d1fb437eb5..638de3efd7a3 100644
--- a/arch/x86/kvm/cpuid.h
+++ b/arch/x86/kvm/cpuid.h
@@ -23,6 +23,9 @@ static inline bool guest_cpuid_has_xsave(struct kvm_vcpu *vcpu)
 {
 	struct kvm_cpuid_entry2 *best;
 
+	if (!static_cpu_has(X86_FEATURE_XSAVE))
+		return 0;
+
 	best = kvm_find_cpuid_entry(vcpu, 1, 0);
 	return best && (best->ecx & bit(X86_FEATURE_XSAVE));
 }
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 185a2b823a2d..e28fb97a1a88 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -5697,6 +5697,9 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
 	int pending_vec, max_bits, idx;
 	struct desc_ptr dt;
 
+	if (!guest_cpuid_has_xsave(vcpu) && (sregs->cr4 & X86_CR4_OSXSAVE))
+		return -EINVAL;
+
 	dt.size = sregs->idt.limit;
 	dt.address = sregs->idt.base;
 	kvm_x86_ops->set_idt(vcpu, &dt);
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 3ecfd1aaf214..e922e01868fb 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -747,13 +747,15 @@ __bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code,
 				return;
 		}
 #endif
+		/* Kernel addresses are always protection faults: */
+		if (address >= TASK_SIZE)
+			error_code |= PF_PROT;
 
-		if (unlikely(show_unhandled_signals))
+		if (likely(show_unhandled_signals))
 			show_signal_msg(regs, error_code, address, tsk);
 
-		/* Kernel addresses are always protection faults: */
 		tsk->thread.cr2		= address;
-		tsk->thread.error_code	= error_code | (address >= TASK_SIZE);
+		tsk->thread.error_code	= error_code;
 		tsk->thread.trap_nr	= X86_TRAP_PF;
 
 		force_sig_info_fault(SIGSEGV, si_code, address, tsk, 0);
diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c
index f6679a7fb8ca..b91e48512425 100644
--- a/arch/x86/mm/hugetlbpage.c
+++ b/arch/x86/mm/hugetlbpage.c
@@ -56,9 +56,16 @@ static int vma_shareable(struct vm_area_struct *vma, unsigned long addr)
 }
 
 /*
- * search for a shareable pmd page for hugetlb.
+ * Search for a shareable pmd page for hugetlb. In any case calls pmd_alloc()
+ * and returns the corresponding pte. While this is not necessary for the
+ * !shared pmd case because we can allocate the pmd later as well, it makes the
+ * code much cleaner. pmd allocation is essential for the shared case because
+ * pud has to be populated inside the same i_mmap_mutex section - otherwise
+ * racing tasks could either miss the sharing (see huge_pte_offset) or select a
+ * bad pmd for sharing.
  */
-static void huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud)
+static pte_t *
+huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud)
 {
 	struct vm_area_struct *vma = find_vma(mm, addr);
 	struct address_space *mapping = vma->vm_file->f_mapping;
@@ -68,9 +75,10 @@ static void huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud)
 	struct vm_area_struct *svma;
 	unsigned long saddr;
 	pte_t *spte = NULL;
+	pte_t *pte;
 
 	if (!vma_shareable(vma, addr))
-		return;
+		return (pte_t *)pmd_alloc(mm, pud, addr);
 
 	mutex_lock(&mapping->i_mmap_mutex);
 	vma_prio_tree_foreach(svma, &iter, &mapping->i_mmap, idx, idx) {
@@ -97,7 +105,9 @@ static void huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud)
 		put_page(virt_to_page(spte));
 	spin_unlock(&mm->page_table_lock);
 out:
+	pte = (pte_t *)pmd_alloc(mm, pud, addr);
 	mutex_unlock(&mapping->i_mmap_mutex);
+	return pte;
 }
 
 /*
@@ -142,8 +152,9 @@ pte_t *huge_pte_alloc(struct mm_struct *mm,
 		} else {
 			BUG_ON(sz != PMD_SIZE);
 			if (pud_none(*pud))
-				huge_pmd_share(mm, addr, pud);
-			pte = (pte_t *) pmd_alloc(mm, pud, addr);
+				pte = huge_pmd_share(mm, addr, pud);
+			else
+				pte = (pte_t *)pmd_alloc(mm, pud, addr);
 		}
 	}
 	BUG_ON(pte && !pte_none(*pte) && !pte_huge(*pte));
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index 4f0cec7e4ffb..fae70904ed08 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -29,36 +29,50 @@ int direct_gbpages
 #endif
 ;
 
-static void __init find_early_table_space(unsigned long end, int use_pse,
-					  int use_gbpages)
+struct map_range {
+	unsigned long start;
+	unsigned long end;
+	unsigned page_size_mask;
+};
+
+/*
+ * First calculate space needed for kernel direct mapping page tables to cover
+ * mr[0].start to mr[nr_range - 1].end, while accounting for possible 2M and 1GB
+ * pages. Then find enough contiguous space for those page tables.
+ */
+static void __init find_early_table_space(struct map_range *mr, int nr_range)
 {
-	unsigned long puds, pmds, ptes, tables, start = 0, good_end = end;
+	int i;
+	unsigned long puds = 0, pmds = 0, ptes = 0, tables;
+	unsigned long start = 0, good_end;
 	phys_addr_t base;
 
-	puds = (end + PUD_SIZE - 1) >> PUD_SHIFT;
-	tables = roundup(puds * sizeof(pud_t), PAGE_SIZE);
+	for (i = 0; i < nr_range; i++) {
+		unsigned long range, extra;
 
-	if (use_gbpages) {
-		unsigned long extra;
+		range = mr[i].end - mr[i].start;
+		puds += (range + PUD_SIZE - 1) >> PUD_SHIFT;
 
-		extra = end - ((end>>PUD_SHIFT) << PUD_SHIFT);
-		pmds = (extra + PMD_SIZE - 1) >> PMD_SHIFT;
-	} else
-		pmds = (end + PMD_SIZE - 1) >> PMD_SHIFT;
-
-	tables += roundup(pmds * sizeof(pmd_t), PAGE_SIZE);
+		if (mr[i].page_size_mask & (1 << PG_LEVEL_1G)) {
+			extra = range - ((range >> PUD_SHIFT) << PUD_SHIFT);
+			pmds += (extra + PMD_SIZE - 1) >> PMD_SHIFT;
+		} else {
+			pmds += (range + PMD_SIZE - 1) >> PMD_SHIFT;
+		}
 
-	if (use_pse) {
-		unsigned long extra;
-
-		extra = end - ((end>>PMD_SHIFT) << PMD_SHIFT);
+		if (mr[i].page_size_mask & (1 << PG_LEVEL_2M)) {
+			extra = range - ((range >> PMD_SHIFT) << PMD_SHIFT);
 #ifdef CONFIG_X86_32
-		extra += PMD_SIZE;
+			extra += PMD_SIZE;
 #endif
-		ptes = (extra + PAGE_SIZE - 1) >> PAGE_SHIFT;
-	} else
-		ptes = (end + PAGE_SIZE - 1) >> PAGE_SHIFT;
+			ptes += (extra + PAGE_SIZE - 1) >> PAGE_SHIFT;
+		} else {
+			ptes += (range + PAGE_SIZE - 1) >> PAGE_SHIFT;
+		}
+	}
 
+	tables = roundup(puds * sizeof(pud_t), PAGE_SIZE);
+	tables += roundup(pmds * sizeof(pmd_t), PAGE_SIZE);
 	tables += roundup(ptes * sizeof(pte_t), PAGE_SIZE);
 
 #ifdef CONFIG_X86_32
@@ -75,8 +89,9 @@ static void __init find_early_table_space(unsigned long end, int use_pse,
 	pgt_buf_end = pgt_buf_start;
 	pgt_buf_top = pgt_buf_start + (tables >> PAGE_SHIFT);
 
-	printk(KERN_DEBUG "kernel direct mapping tables up to %lx @ %lx-%lx\n",
-		end, pgt_buf_start << PAGE_SHIFT, pgt_buf_top << PAGE_SHIFT);
+ 	printk(KERN_DEBUG "kernel direct mapping tables up to %#lx @ [mem %#010lx-%#010lx]\n",
+		mr[nr_range - 1].end - 1, pgt_buf_start << PAGE_SHIFT,
+ 		(pgt_buf_top << PAGE_SHIFT) - 1);
 }
 
 void __init native_pagetable_reserve(u64 start, u64 end)
@@ -84,12 +99,6 @@ void __init native_pagetable_reserve(u64 start, u64 end)
 	memblock_reserve(start, end - start);
 }
 
-struct map_range {
-	unsigned long start;
-	unsigned long end;
-	unsigned page_size_mask;
-};
-
 #ifdef CONFIG_X86_32
 #define NR_RANGE_MR 3
 #else /* CONFIG_X86_64 */
@@ -261,7 +270,7 @@ unsigned long __init_refok init_memory_mapping(unsigned long start,
 	 * nodes are discovered.
 	 */
 	if (!after_bootmem)
-		find_early_table_space(end, use_pse, use_gbpages);
+		find_early_table_space(mr, nr_range);
 
 	for (i = 0; i < nr_range; i++)
 		ret = kernel_physical_mapping_init(mr[i].start, mr[i].end,
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index fc18be0f6f29..faf7a6830c0b 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -821,6 +821,9 @@ int kern_addr_valid(unsigned long addr)
 	if (pud_none(*pud))
 		return 0;
 
+	if (pud_large(*pud))
+		return pfn_valid(pud_pfn(*pud));
+
 	pmd = pmd_offset(pud, addr);
 	if (pmd_none(*pmd))
 		return 0;
diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c
index 19d3fa08b119..c1e83944abfe 100644
--- a/arch/x86/mm/numa.c
+++ b/arch/x86/mm/numa.c
@@ -193,7 +193,6 @@ int __init numa_add_memblk(int nid, u64 start, u64 end)
 static void __init setup_node_data(int nid, u64 start, u64 end)
 {
 	const size_t nd_size = roundup(sizeof(pg_data_t), PAGE_SIZE);
-	bool remapped = false;
 	u64 nd_pa;
 	void *nd;
 	int tnid;
@@ -205,37 +204,28 @@ static void __init setup_node_data(int nid, u64 start, u64 end)
 	if (end && (end - start) < NODE_MIN_SIZE)
 		return;
 
-	/* initialize remap allocator before aligning to ZONE_ALIGN */
-	init_alloc_remap(nid, start, end);
-
 	start = roundup(start, ZONE_ALIGN);
 
 	printk(KERN_INFO "Initmem setup node %d %016Lx-%016Lx\n",
 	       nid, start, end);
 
 	/*
-	 * Allocate node data.  Try remap allocator first, node-local
-	 * memory and then any node.  Never allocate in DMA zone.
+	 * Allocate node data.  Try node-local memory and then any node.
+	 * Never allocate in DMA zone.
 	 */
-	nd = alloc_remap(nid, nd_size);
-	if (nd) {
-		nd_pa = __pa(nd);
-		remapped = true;
-	} else {
-		nd_pa = memblock_alloc_nid(nd_size, SMP_CACHE_BYTES, nid);
-		if (!nd_pa) {
-			pr_err("Cannot find %zu bytes in node %d\n",
-			       nd_size, nid);
-			return;
-		}
-		nd = __va(nd_pa);
+	nd_pa = memblock_alloc_nid(nd_size, SMP_CACHE_BYTES, nid);
+	if (!nd_pa) {
+		pr_err("Cannot find %zu bytes in node %d\n",
+		       nd_size, nid);
+		return;
 	}
+	nd = __va(nd_pa);
 
 	/* report and initialize */
-	printk(KERN_INFO "  NODE_DATA [%016Lx - %016Lx]%s\n",
-	       nd_pa, nd_pa + nd_size - 1, remapped ? " (remapped)" : "");
+	printk(KERN_INFO "  NODE_DATA [mem %#010Lx-%#010Lx]\n",
+	       nd_pa, nd_pa + nd_size - 1);
 	tnid = early_pfn_to_nid(nd_pa >> PAGE_SHIFT);
-	if (!remapped && tnid != nid)
+	if (tnid != nid)
 		printk(KERN_INFO "    NODE_DATA(%d) on node %d\n", nid, tnid);
 
 	node_data[nid] = nd;
diff --git a/arch/x86/mm/numa_32.c b/arch/x86/mm/numa_32.c
index 534255a36b6b..73a6d7395bd3 100644
--- a/arch/x86/mm/numa_32.c
+++ b/arch/x86/mm/numa_32.c
@@ -73,167 +73,6 @@ unsigned long node_memmap_size_bytes(int nid, unsigned long start_pfn,
 
 extern unsigned long highend_pfn, highstart_pfn;
 
-#define LARGE_PAGE_BYTES (PTRS_PER_PTE * PAGE_SIZE)
-
-static void *node_remap_start_vaddr[MAX_NUMNODES];
-void set_pmd_pfn(unsigned long vaddr, unsigned long pfn, pgprot_t flags);
-
-/*
- * Remap memory allocator
- */
-static unsigned long node_remap_start_pfn[MAX_NUMNODES];
-static void *node_remap_end_vaddr[MAX_NUMNODES];
-static void *node_remap_alloc_vaddr[MAX_NUMNODES];
-
-/**
- * alloc_remap - Allocate remapped memory
- * @nid: NUMA node to allocate memory from
- * @size: The size of allocation
- *
- * Allocate @size bytes from the remap area of NUMA node @nid.  The
- * size of the remap area is predetermined by init_alloc_remap() and
- * only the callers considered there should call this function.  For
- * more info, please read the comment on top of init_alloc_remap().
- *
- * The caller must be ready to handle allocation failure from this
- * function and fall back to regular memory allocator in such cases.
- *
- * CONTEXT:
- * Single CPU early boot context.
- *
- * RETURNS:
- * Pointer to the allocated memory on success, %NULL on failure.
- */
-void *alloc_remap(int nid, unsigned long size)
-{
-	void *allocation = node_remap_alloc_vaddr[nid];
-
-	size = ALIGN(size, L1_CACHE_BYTES);
-
-	if (!allocation || (allocation + size) > node_remap_end_vaddr[nid])
-		return NULL;
-
-	node_remap_alloc_vaddr[nid] += size;
-	memset(allocation, 0, size);
-
-	return allocation;
-}
-
-#ifdef CONFIG_HIBERNATION
-/**
- * resume_map_numa_kva - add KVA mapping to the temporary page tables created
- *                       during resume from hibernation
- * @pgd_base - temporary resume page directory
- */
-void resume_map_numa_kva(pgd_t *pgd_base)
-{
-	int node;
-
-	for_each_online_node(node) {
-		unsigned long start_va, start_pfn, nr_pages, pfn;
-
-		start_va = (unsigned long)node_remap_start_vaddr[node];
-		start_pfn = node_remap_start_pfn[node];
-		nr_pages = (node_remap_end_vaddr[node] -
-			    node_remap_start_vaddr[node]) >> PAGE_SHIFT;
-
-		printk(KERN_DEBUG "%s: node %d\n", __func__, node);
-
-		for (pfn = 0; pfn < nr_pages; pfn += PTRS_PER_PTE) {
-			unsigned long vaddr = start_va + (pfn << PAGE_SHIFT);
-			pgd_t *pgd = pgd_base + pgd_index(vaddr);
-			pud_t *pud = pud_offset(pgd, vaddr);
-			pmd_t *pmd = pmd_offset(pud, vaddr);
-
-			set_pmd(pmd, pfn_pmd(start_pfn + pfn,
-						PAGE_KERNEL_LARGE_EXEC));
-
-			printk(KERN_DEBUG "%s: %08lx -> pfn %08lx\n",
-				__func__, vaddr, start_pfn + pfn);
-		}
-	}
-}
-#endif
-
-/**
- * init_alloc_remap - Initialize remap allocator for a NUMA node
- * @nid: NUMA node to initizlie remap allocator for
- *
- * NUMA nodes may end up without any lowmem.  As allocating pgdat and
- * memmap on a different node with lowmem is inefficient, a special
- * remap allocator is implemented which can be used by alloc_remap().
- *
- * For each node, the amount of memory which will be necessary for
- * pgdat and memmap is calculated and two memory areas of the size are
- * allocated - one in the node and the other in lowmem; then, the area
- * in the node is remapped to the lowmem area.
- *
- * As pgdat and memmap must be allocated in lowmem anyway, this
- * doesn't waste lowmem address space; however, the actual lowmem
- * which gets remapped over is wasted.  The amount shouldn't be
- * problematic on machines this feature will be used.
- *
- * Initialization failure isn't fatal.  alloc_remap() is used
- * opportunistically and the callers will fall back to other memory
- * allocation mechanisms on failure.
- */
-void __init init_alloc_remap(int nid, u64 start, u64 end)
-{
-	unsigned long start_pfn = start >> PAGE_SHIFT;
-	unsigned long end_pfn = end >> PAGE_SHIFT;
-	unsigned long size, pfn;
-	u64 node_pa, remap_pa;
-	void *remap_va;
-
-	/*
-	 * The acpi/srat node info can show hot-add memroy zones where
-	 * memory could be added but not currently present.
-	 */
-	printk(KERN_DEBUG "node %d pfn: [%lx - %lx]\n",
-	       nid, start_pfn, end_pfn);
-
-	/* calculate the necessary space aligned to large page size */
-	size = node_memmap_size_bytes(nid, start_pfn, end_pfn);
-	size += ALIGN(sizeof(pg_data_t), PAGE_SIZE);
-	size = ALIGN(size, LARGE_PAGE_BYTES);
-
-	/* allocate node memory and the lowmem remap area */
-	node_pa = memblock_find_in_range(start, end, size, LARGE_PAGE_BYTES);
-	if (!node_pa) {
-		pr_warning("remap_alloc: failed to allocate %lu bytes for node %d\n",
-			   size, nid);
-		return;
-	}
-	memblock_reserve(node_pa, size);
-
-	remap_pa = memblock_find_in_range(min_low_pfn << PAGE_SHIFT,
-					  max_low_pfn << PAGE_SHIFT,
-					  size, LARGE_PAGE_BYTES);
-	if (!remap_pa) {
-		pr_warning("remap_alloc: failed to allocate %lu bytes remap area for node %d\n",
-			   size, nid);
-		memblock_free(node_pa, size);
-		return;
-	}
-	memblock_reserve(remap_pa, size);
-	remap_va = phys_to_virt(remap_pa);
-
-	/* perform actual remap */
-	for (pfn = 0; pfn < size >> PAGE_SHIFT; pfn += PTRS_PER_PTE)
-		set_pmd_pfn((unsigned long)remap_va + (pfn << PAGE_SHIFT),
-			    (node_pa >> PAGE_SHIFT) + pfn,
-			    PAGE_KERNEL_LARGE);
-
-	/* initialize remap allocator parameters */
-	node_remap_start_pfn[nid] = node_pa >> PAGE_SHIFT;
-	node_remap_start_vaddr[nid] = remap_va;
-	node_remap_end_vaddr[nid] = remap_va + size;
-	node_remap_alloc_vaddr[nid] = remap_va;
-
-	printk(KERN_DEBUG "remap_alloc: node %d [%08llx-%08llx) -> [%p-%p)\n",
-	       nid, node_pa, node_pa + size, remap_va, remap_va + size);
-}
-
 void __init initmem_init(void)
 {
 	x86_numa_init();
diff --git a/arch/x86/mm/numa_internal.h b/arch/x86/mm/numa_internal.h
index 7178c3afe05e..ad86ec91e640 100644
--- a/arch/x86/mm/numa_internal.h
+++ b/arch/x86/mm/numa_internal.h
@@ -21,12 +21,6 @@ void __init numa_reset_distance(void);
 
 void __init x86_numa_init(void);
 
-#ifdef CONFIG_X86_64
-static inline void init_alloc_remap(int nid, u64 start, u64 end)	{ }
-#else
-void __init init_alloc_remap(int nid, u64 start, u64 end);
-#endif
-
 #ifdef CONFIG_NUMA_EMU
 void __init numa_emulation(struct numa_meminfo *numa_meminfo,
 			   int numa_dist_cnt);
diff --git a/arch/x86/oprofile/nmi_int.c b/arch/x86/oprofile/nmi_int.c
index 26b8a8514ee5..48768df2471a 100644
--- a/arch/x86/oprofile/nmi_int.c
+++ b/arch/x86/oprofile/nmi_int.c
@@ -55,7 +55,7 @@ u64 op_x86_get_ctrl(struct op_x86_model_spec const *model,
 	val |= counter_config->extra;
 	event &= model->event_mask ? model->event_mask : 0xFF;
 	val |= event & 0xFF;
-	val |= (event & 0x0F00) << 24;
+	val |= (u64)(event & 0x0F00) << 24;
 
 	return val;
 }
diff --git a/arch/x86/pci/fixup.c b/arch/x86/pci/fixup.c
index d0e6e403b4f6..5dd467bd6121 100644
--- a/arch/x86/pci/fixup.c
+++ b/arch/x86/pci/fixup.c
@@ -519,3 +519,20 @@ static void sb600_disable_hpet_bar(struct pci_dev *dev)
 	}
 }
 DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_ATI, 0x4385, sb600_disable_hpet_bar);
+
+/*
+ * Twinhead H12Y needs us to block out a region otherwise we map devices
+ * there and any access kills the box.
+ *
+ *   See: https://bugzilla.kernel.org/show_bug.cgi?id=10231
+ *
+ * Match off the LPC and svid/sdid (older kernels lose the bridge subvendor)
+ */
+static void __devinit twinhead_reserve_killing_zone(struct pci_dev *dev)
+{
+        if (dev->subsystem_vendor == 0x14FF && dev->subsystem_device == 0xA003) {
+                pr_info("Reserving memory on Twinhead H12Y\n");
+                request_mem_region(0xFFB00000, 0x100000, "twinhead");
+        }
+}
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x27B9, twinhead_reserve_killing_zone);
diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
index 92660edaa1e7..1e406371a683 100644
--- a/arch/x86/platform/efi/efi.c
+++ b/arch/x86/platform/efi/efi.c
@@ -50,9 +50,6 @@
 
 #define EFI_DEBUG	1
 
-int efi_enabled;
-EXPORT_SYMBOL(efi_enabled);
-
 struct efi __read_mostly efi = {
 	.mps        = EFI_INVALID_TABLE_ADDR,
 	.acpi       = EFI_INVALID_TABLE_ADDR,
@@ -68,15 +65,29 @@ EXPORT_SYMBOL(efi);
 
 struct efi_memory_map memmap;
 
-bool efi_64bit;
-static bool efi_native;
-
 static struct efi efi_phys __initdata;
 static efi_system_table_t efi_systab __initdata;
 
+static inline bool efi_is_native(void)
+{
+	return IS_ENABLED(CONFIG_X86_64) == efi_enabled(EFI_64BIT);
+}
+
+unsigned long x86_efi_facility;
+
+/*
+ * Returns 1 if 'facility' is enabled, 0 otherwise.
+ */
+int efi_enabled(int facility)
+{
+	return test_bit(facility, &x86_efi_facility) != 0;
+}
+EXPORT_SYMBOL(efi_enabled);
+
+static bool disable_runtime = false;
 static int __init setup_noefi(char *arg)
 {
-	efi_enabled = 0;
+	disable_runtime = true;
 	return 0;
 }
 early_param("noefi", setup_noefi);
@@ -419,10 +430,22 @@ void __init efi_reserve_boot_services(void)
 	}
 }
 
-static void __init efi_free_boot_services(void)
+void __init efi_unmap_memmap(void)
+{
+	clear_bit(EFI_MEMMAP, &x86_efi_facility);
+	if (memmap.map) {
+		early_iounmap(memmap.map, memmap.nr_map * memmap.desc_size);
+		memmap.map = NULL;
+	}
+}
+
+void __init efi_free_boot_services(void)
 {
 	void *p;
 
+	if (!efi_is_native())
+		return;
+
 	for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
 		efi_memory_desc_t *md = p;
 		unsigned long long start = md->phys_addr;
@@ -438,11 +461,13 @@ static void __init efi_free_boot_services(void)
 
 		free_bootmem_late(start, size);
 	}
+
+	efi_unmap_memmap();
 }
 
 static int __init efi_systab_init(void *phys)
 {
-	if (efi_64bit) {
+	if (efi_enabled(EFI_64BIT)) {
 		efi_system_table_64_t *systab64;
 		u64 tmp = 0;
 
@@ -534,7 +559,7 @@ static int __init efi_config_init(u64 tables, int nr_tables)
 	void *config_tables, *tablep;
 	int i, sz;
 
-	if (efi_64bit)
+	if (efi_enabled(EFI_64BIT))
 		sz = sizeof(efi_config_table_64_t);
 	else
 		sz = sizeof(efi_config_table_32_t);
@@ -554,7 +579,7 @@ static int __init efi_config_init(u64 tables, int nr_tables)
 		efi_guid_t guid;
 		unsigned long table;
 
-		if (efi_64bit) {
+		if (efi_enabled(EFI_64BIT)) {
 			u64 table64;
 			guid = ((efi_config_table_64_t *)tablep)->guid;
 			table64 = ((efi_config_table_64_t *)tablep)->table;
@@ -666,22 +691,19 @@ void __init efi_init(void)
 	if (boot_params.efi_info.efi_systab_hi ||
 	    boot_params.efi_info.efi_memmap_hi) {
 		pr_info("Table located above 4GB, disabling EFI.\n");
-		efi_enabled = 0;
 		return;
 	}
 	efi_phys.systab = (efi_system_table_t *)boot_params.efi_info.efi_systab;
-	efi_native = !efi_64bit;
 #else
 	efi_phys.systab = (efi_system_table_t *)
 			  (boot_params.efi_info.efi_systab |
 			  ((__u64)boot_params.efi_info.efi_systab_hi<<32));
-	efi_native = efi_64bit;
 #endif
 
-	if (efi_systab_init(efi_phys.systab)) {
-		efi_enabled = 0;
+	if (efi_systab_init(efi_phys.systab))
 		return;
-	}
+
+	set_bit(EFI_SYSTEM_TABLES, &x86_efi_facility);
 
 	/*
 	 * Show what we know for posterity
@@ -699,29 +721,31 @@ void __init efi_init(void)
 		efi.systab->hdr.revision >> 16,
 		efi.systab->hdr.revision & 0xffff, vendor);
 
-	if (efi_config_init(efi.systab->tables, efi.systab->nr_tables)) {
-		efi_enabled = 0;
+	if (efi_config_init(efi.systab->tables, efi.systab->nr_tables))
 		return;
-	}
+
+	set_bit(EFI_CONFIG_TABLES, &x86_efi_facility);
 
 	/*
 	 * Note: We currently don't support runtime services on an EFI
 	 * that doesn't match the kernel 32/64-bit mode.
 	 */
 
-	if (!efi_native)
+	if (!efi_is_native())
 		pr_info("No EFI runtime due to 32/64-bit mismatch with kernel\n");
-	else if (efi_runtime_init()) {
-		efi_enabled = 0;
-		return;
+	else {
+		if (disable_runtime || efi_runtime_init())
+			return;
+		set_bit(EFI_RUNTIME_SERVICES, &x86_efi_facility);
 	}
 
-	if (efi_memmap_init()) {
-		efi_enabled = 0;
+	if (efi_memmap_init())
 		return;
-	}
+
+	set_bit(EFI_MEMMAP, &x86_efi_facility);
+
 #ifdef CONFIG_X86_32
-	if (efi_native) {
+	if (efi_is_native()) {
 		x86_platform.get_wallclock = efi_get_time;
 		x86_platform.set_wallclock = efi_set_rtc_mmss;
 	}
@@ -787,8 +811,10 @@ void __init efi_enter_virtual_mode(void)
 	 * non-native EFI
 	 */
 
-	if (!efi_native)
-		goto out;
+	if (!efi_is_native()) {
+		efi_unmap_memmap();
+		return;
+	}
 
 	/* Merge contiguous regions of the same type and attribute */
 	for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
@@ -878,18 +904,12 @@ void __init efi_enter_virtual_mode(void)
 	}
 
 	/*
-	 * Thankfully, it does seem that no runtime services other than
-	 * SetVirtualAddressMap() will touch boot services code, so we can
-	 * get rid of it all at this point
-	 */
-	efi_free_boot_services();
-
-	/*
 	 * Now that EFI is in virtual mode, update the function
 	 * pointers in the runtime service table to the new virtual addresses.
 	 *
 	 * Call EFI services through wrapper functions.
 	 */
+	efi.runtime_version = efi_systab.hdr.revision;
 	efi.get_time = virt_efi_get_time;
 	efi.set_time = virt_efi_set_time;
 	efi.get_wakeup_time = virt_efi_get_wakeup_time;
@@ -906,9 +926,6 @@ void __init efi_enter_virtual_mode(void)
 	if (__supported_pte_mask & _PAGE_NX)
 		runtime_code_page_mkexec();
 
-out:
-	early_iounmap(memmap.map, memmap.nr_map * memmap.desc_size);
-	memmap.map = NULL;
 	kfree(new_memmap);
 }
 
@@ -935,6 +952,9 @@ u64 efi_mem_attributes(unsigned long phys_addr)
 	efi_memory_desc_t *md;
 	void *p;
 
+	if (!efi_enabled(EFI_MEMMAP))
+		return 0;
+
 	for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
 		md = p;
 		if ((md->phys_addr <= phys_addr) &&
diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c
index ac3aa54e2654..0fba86da5895 100644
--- a/arch/x86/platform/efi/efi_64.c
+++ b/arch/x86/platform/efi/efi_64.c
@@ -38,7 +38,7 @@
 #include <asm/cacheflush.h>
 #include <asm/fixmap.h>
 
-static pgd_t save_pgd __initdata;
+static pgd_t *save_pgd __initdata;
 static unsigned long efi_flags __initdata;
 
 static void __init early_code_mapping_set_exec(int executable)
@@ -61,12 +61,20 @@ static void __init early_code_mapping_set_exec(int executable)
 void __init efi_call_phys_prelog(void)
 {
 	unsigned long vaddress;
+	int pgd;
+	int n_pgds;
 
 	early_code_mapping_set_exec(1);
 	local_irq_save(efi_flags);
-	vaddress = (unsigned long)__va(0x0UL);
-	save_pgd = *pgd_offset_k(0x0UL);
-	set_pgd(pgd_offset_k(0x0UL), *pgd_offset_k(vaddress));
+
+	n_pgds = DIV_ROUND_UP((max_pfn << PAGE_SHIFT), PGDIR_SIZE);
+	save_pgd = kmalloc(n_pgds * sizeof(pgd_t), GFP_KERNEL);
+
+	for (pgd = 0; pgd < n_pgds; pgd++) {
+		save_pgd[pgd] = *pgd_offset_k(pgd * PGDIR_SIZE);
+		vaddress = (unsigned long)__va(pgd * PGDIR_SIZE);
+		set_pgd(pgd_offset_k(pgd * PGDIR_SIZE), *pgd_offset_k(vaddress));
+	}
 	__flush_tlb_all();
 }
 
@@ -75,7 +83,11 @@ void __init efi_call_phys_epilog(void)
 	/*
 	 * After the lock is released, the original page table is restored.
 	 */
-	set_pgd(pgd_offset_k(0x0UL), save_pgd);
+	int pgd;
+	int n_pgds = DIV_ROUND_UP((max_pfn << PAGE_SHIFT) , PGDIR_SIZE);
+	for (pgd = 0; pgd < n_pgds; pgd++)
+		set_pgd(pgd_offset_k(pgd * PGDIR_SIZE), save_pgd[pgd]);
+	kfree(save_pgd);
 	__flush_tlb_all();
 	local_irq_restore(efi_flags);
 	early_code_mapping_set_exec(0);
diff --git a/arch/x86/power/hibernate_32.c b/arch/x86/power/hibernate_32.c
index 74202c1910cd..7d28c885d238 100644
--- a/arch/x86/power/hibernate_32.c
+++ b/arch/x86/power/hibernate_32.c
@@ -129,8 +129,6 @@ static int resume_physical_mapping_init(pgd_t *pgd_base)
 		}
 	}
 
-	resume_map_numa_kva(pgd_base);
-
 	return 0;
 }
 
diff --git a/arch/x86/syscalls/syscall_64.tbl b/arch/x86/syscalls/syscall_64.tbl
index dd29a9ea27c5..fd1f10348130 100644
--- a/arch/x86/syscalls/syscall_64.tbl
+++ b/arch/x86/syscalls/syscall_64.tbl
@@ -60,8 +60,8 @@
 51	common	getsockname		sys_getsockname
 52	common	getpeername		sys_getpeername
 53	common	socketpair		sys_socketpair
-54	common	setsockopt		sys_setsockopt
-55	common	getsockopt		sys_getsockopt
+54	64	setsockopt		sys_setsockopt
+55	64	getsockopt		sys_getsockopt
 56	common	clone			stub_clone
 57	common	fork			stub_fork
 58	common	vfork			stub_vfork
@@ -351,3 +351,5 @@
 538	x32	sendmmsg		compat_sys_sendmmsg
 539	x32	process_vm_readv	compat_sys_process_vm_readv
 540	x32	process_vm_writev	compat_sys_process_vm_writev
+541	x32	setsockopt		compat_sys_setsockopt
+542	x32	getsockopt		compat_sys_getsockopt
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 40edfc37a6fd..59100548cbdb 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -942,7 +942,16 @@ static void xen_write_cr4(unsigned long cr4)
 
 	native_write_cr4(cr4);
 }
-
+#ifdef CONFIG_X86_64
+static inline unsigned long xen_read_cr8(void)
+{
+	return 0;
+}
+static inline void xen_write_cr8(unsigned long val)
+{
+	BUG_ON(val);
+}
+#endif
 static int xen_write_msr_safe(unsigned int msr, unsigned low, unsigned high)
 {
 	int ret;
@@ -1111,6 +1120,11 @@ static const struct pv_cpu_ops xen_cpu_ops __initconst = {
 	.read_cr4_safe = native_read_cr4_safe,
 	.write_cr4 = xen_write_cr4,
 
+#ifdef CONFIG_X86_64
+	.read_cr8 = xen_read_cr8,
+	.write_cr8 = xen_write_cr8,
+#endif
+
 	.wbinvd = native_wbinvd,
 
 	.read_msr = native_read_msr_safe,
@@ -1121,6 +1135,8 @@ static const struct pv_cpu_ops xen_cpu_ops __initconst = {
 	.read_tsc = native_read_tsc,
 	.read_pmc = native_read_pmc,
 
+	.read_tscp = native_read_tscp,
+
 	.iret = xen_iret,
 	.irq_enable_sysexit = xen_sysexit,
 #ifdef CONFIG_X86_64
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index 69f5857660ac..5cb8e27d43d2 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -1203,6 +1203,25 @@ unsigned long xen_read_cr2_direct(void)
 	return this_cpu_read(xen_vcpu_info.arch.cr2);
 }
 
+void xen_flush_tlb_all(void)
+{
+	struct mmuext_op *op;
+	struct multicall_space mcs;
+
+	trace_xen_mmu_flush_tlb_all(0);
+
+	preempt_disable();
+
+	mcs = xen_mc_entry(sizeof(*op));
+
+	op = mcs.args;
+	op->cmd = MMUEXT_TLB_FLUSH_ALL;
+	MULTI_mmuext_op(mcs.mc, op, 1, NULL, DOMID_SELF);
+
+	xen_mc_issue(PARAVIRT_LAZY_MMU);
+
+	preempt_enable();
+}
 static void xen_flush_tlb(void)
 {
 	struct mmuext_op *op;
@@ -2364,7 +2383,7 @@ int xen_remap_domain_mfn_range(struct vm_area_struct *vma,
 	err = 0;
 out:
 
-	flush_tlb_all();
+	xen_flush_tlb_all();
 
 	return err;
 }
diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c
index 00a038540c8e..3ace81769478 100644
--- a/arch/x86/xen/p2m.c
+++ b/arch/x86/xen/p2m.c
@@ -714,9 +714,6 @@ int m2p_add_override(unsigned long mfn, struct page *page,
 
 			xen_mc_issue(PARAVIRT_LAZY_MMU);
 		}
-		/* let's use dev_bus_addr to record the old mfn instead */
-		kmap_op->dev_bus_addr = page->index;
-		page->index = (unsigned long) kmap_op;
 	}
 	spin_lock_irqsave(&m2p_override_lock, flags);
 	list_add(&page->lru,  &m2p_overrides[mfn_hash(mfn)]);
@@ -743,7 +740,8 @@ int m2p_add_override(unsigned long mfn, struct page *page,
 	return 0;
 }
 EXPORT_SYMBOL_GPL(m2p_add_override);
-int m2p_remove_override(struct page *page, bool clear_pte)
+int m2p_remove_override(struct page *page,
+		struct gnttab_map_grant_ref *kmap_op)
 {
 	unsigned long flags;
 	unsigned long mfn;
@@ -773,10 +771,8 @@ int m2p_remove_override(struct page *page, bool clear_pte)
 	WARN_ON(!PagePrivate(page));
 	ClearPagePrivate(page);
 
-	if (clear_pte) {
-		struct gnttab_map_grant_ref *map_op =
-			(struct gnttab_map_grant_ref *) page->index;
-		set_phys_to_machine(pfn, map_op->dev_bus_addr);
+	set_phys_to_machine(pfn, page->index);
+	if (kmap_op != NULL) {
 		if (!PageHighMem(page)) {
 			struct multicall_space mcs;
 			struct gnttab_unmap_grant_ref *unmap_op;
@@ -788,13 +784,13 @@ int m2p_remove_override(struct page *page, bool clear_pte)
 			 * issued. In this case handle is going to -1 because
 			 * it hasn't been modified yet.
 			 */
-			if (map_op->handle == -1)
+			if (kmap_op->handle == -1)
 				xen_mc_flush();
 			/*
-			 * Now if map_op->handle is negative it means that the
+			 * Now if kmap_op->handle is negative it means that the
 			 * hypercall actually returned an error.
 			 */
-			if (map_op->handle == GNTST_general_error) {
+			if (kmap_op->handle == GNTST_general_error) {
 				printk(KERN_WARNING "m2p_remove_override: "
 						"pfn %lx mfn %lx, failed to modify kernel mappings",
 						pfn, mfn);
@@ -804,8 +800,8 @@ int m2p_remove_override(struct page *page, bool clear_pte)
 			mcs = xen_mc_entry(
 					sizeof(struct gnttab_unmap_grant_ref));
 			unmap_op = mcs.args;
-			unmap_op->host_addr = map_op->host_addr;
-			unmap_op->handle = map_op->handle;
+			unmap_op->host_addr = kmap_op->host_addr;
+			unmap_op->handle = kmap_op->handle;
 			unmap_op->dev_bus_addr = 0;
 
 			MULTI_grant_table_op(mcs.mc,
@@ -816,10 +812,9 @@ int m2p_remove_override(struct page *page, bool clear_pte)
 			set_pte_at(&init_mm, address, ptep,
 					pfn_pte(pfn, PAGE_KERNEL));
 			__flush_tlb_single(address);
-			map_op->host_addr = 0;
+			kmap_op->host_addr = 0;
 		}
-	} else
-		set_phys_to_machine(pfn, page->index);
+	}
 
 	/* p2m(m2p(mfn)) == FOREIGN_FRAME(mfn): the mfn is already present
 	 * somewhere in this domain, even before being added to the
diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index 1ba8dff26753..017d48a26a02 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -17,6 +17,7 @@
 #include <asm/e820.h>
 #include <asm/setup.h>
 #include <asm/acpi.h>
+#include <asm/numa.h>
 #include <asm/xen/hypervisor.h>
 #include <asm/xen/hypercall.h>
 
@@ -79,9 +80,16 @@ static void __init xen_add_extra_mem(u64 start, u64 size)
 	memblock_reserve(start, size);
 
 	xen_max_p2m_pfn = PFN_DOWN(start + size);
+	for (pfn = PFN_DOWN(start); pfn < xen_max_p2m_pfn; pfn++) {
+		unsigned long mfn = pfn_to_mfn(pfn);
+
+		if (WARN(mfn == pfn, "Trying to over-write 1-1 mapping (pfn: %lx)\n", pfn))
+			continue;
+		WARN(mfn != INVALID_P2M_ENTRY, "Trying to remove %lx which has %lx mfn!\n",
+			pfn, mfn);
 
-	for (pfn = PFN_DOWN(start); pfn <= xen_max_p2m_pfn; pfn++)
 		__set_phys_to_machine(pfn, INVALID_P2M_ENTRY);
+	}
 }
 
 static unsigned long __init xen_release_chunk(unsigned long start,
@@ -424,4 +432,7 @@ void __init xen_arch_setup(void)
 	disable_cpufreq();
 	WARN_ON(set_pm_idle_to_default());
 	fiddle_vdso();
+#ifdef CONFIG_NUMA
+	numa_off = 1;
+#endif
 }
diff --git a/arch/x86/xen/spinlock.c b/arch/x86/xen/spinlock.c
index d69cc6c3f808..67bc7bae746e 100644
--- a/arch/x86/xen/spinlock.c
+++ b/arch/x86/xen/spinlock.c
@@ -328,7 +328,6 @@ static noinline void xen_spin_unlock_slow(struct xen_spinlock *xl)
 		if (per_cpu(lock_spinners, cpu) == xl) {
 			ADD_STATS(released_slow_kicked, 1);
 			xen_send_IPI_one(cpu, XEN_SPIN_UNLOCK_VECTOR);
-			break;
 		}
 	}
 }
diff --git a/arch/x86/xen/xen-asm_32.S b/arch/x86/xen/xen-asm_32.S
index b040b0e518ca..7328f71651e1 100644
--- a/arch/x86/xen/xen-asm_32.S
+++ b/arch/x86/xen/xen-asm_32.S
@@ -88,11 +88,11 @@ ENTRY(xen_iret)
 	 */
 #ifdef CONFIG_SMP
 	GET_THREAD_INFO(%eax)
-	movl TI_cpu(%eax), %eax
-	movl __per_cpu_offset(,%eax,4), %eax
-	mov xen_vcpu(%eax), %eax
+	movl %ss:TI_cpu(%eax), %eax
+	movl %ss:__per_cpu_offset(,%eax,4), %eax
+	mov %ss:xen_vcpu(%eax), %eax
 #else
-	movl xen_vcpu, %eax
+	movl %ss:xen_vcpu, %eax
 #endif
 
 	/* check IF state we're restoring */
@@ -105,11 +105,11 @@ ENTRY(xen_iret)
 	 * resuming the code, so we don't have to be worried about
 	 * being preempted to another CPU.
 	 */
-	setz XEN_vcpu_info_mask(%eax)
+	setz %ss:XEN_vcpu_info_mask(%eax)
 xen_iret_start_crit:
 
 	/* check for unmasked and pending */
-	cmpw $0x0001, XEN_vcpu_info_pending(%eax)
+	cmpw $0x0001, %ss:XEN_vcpu_info_pending(%eax)
 
 	/*
 	 * If there's something pending, mask events again so we can
@@ -117,7 +117,7 @@ xen_iret_start_crit:
 	 * touch XEN_vcpu_info_mask.
 	 */
 	jne 1f
-	movb $1, XEN_vcpu_info_mask(%eax)
+	movb $1, %ss:XEN_vcpu_info_mask(%eax)
 
 1:	popl %eax