24 files changed, 160 insertions, 59 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 6a154a9..fe120da 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -108,7 +108,6 @@ config X86
 	select GENERIC_CLOCKEVENTS_BROADCAST if X86_64 || (X86_32 && X86_LOCAL_APIC)
 	select GENERIC_TIME_VSYSCALL if X86_64
 	select KTIME_SCALAR if X86_32
-	select ALWAYS_USE_PERSISTENT_CLOCK
 	select GENERIC_STRNCPY_FROM_USER
 	select GENERIC_STRNLEN_USER
 	select HAVE_CONTEXT_TRACKING if X86_64
@@ -2266,6 +2265,7 @@ source "fs/Kconfig.binfmt"
 config IA32_EMULATION
 	bool "IA32 Emulation"
 	depends on X86_64
+	select BINFMT_ELF
 	select COMPAT_BINFMT_ELF
 	select HAVE_UID16
 	---help---
diff --git a/arch/x86/crypto/crc32-pclmul_asm.S b/arch/x86/crypto/crc32-pclmul_asm.S
index 94c27df..f247304 100644
--- a/arch/x86/crypto/crc32-pclmul_asm.S
+++ b/arch/x86/crypto/crc32-pclmul_asm.S
@@ -240,7 +240,7 @@ fold_64:
 	pand    %xmm3, %xmm1
 	PCLMULQDQ 0x00, CONSTANT, %xmm1
 	pxor    %xmm2, %xmm1
-	pextrd  $0x01, %xmm1, %eax
+	PEXTRD  0x01, %xmm1, %eax
 
 	ret
 ENDPROC(crc32_pclmul_le_16)
diff --git a/arch/x86/crypto/sha256-avx-asm.S b/arch/x86/crypto/sha256-avx-asm.S
index 56610c4..642f156 100644
--- a/arch/x86/crypto/sha256-avx-asm.S
+++ b/arch/x86/crypto/sha256-avx-asm.S
@@ -118,7 +118,7 @@ y2 = %r15d
 
 _INP_END_SIZE = 8
 _INP_SIZE = 8
-_XFER_SIZE = 8
+_XFER_SIZE = 16
 _XMM_SAVE_SIZE = 0
 
 _INP_END = 0
diff --git a/arch/x86/crypto/sha256-ssse3-asm.S b/arch/x86/crypto/sha256-ssse3-asm.S
index 98d3c39..f833b74 100644
--- a/arch/x86/crypto/sha256-ssse3-asm.S
+++ b/arch/x86/crypto/sha256-ssse3-asm.S
@@ -111,7 +111,7 @@ y2 = %r15d
 
 _INP_END_SIZE = 8
 _INP_SIZE = 8
-_XFER_SIZE = 8
+_XFER_SIZE = 16
 _XMM_SAVE_SIZE = 0
 
 _INP_END = 0
diff --git a/arch/x86/include/asm/inst.h b/arch/x86/include/asm/inst.h
index 280bf7f..3e11527 100644
--- a/arch/x86/include/asm/inst.h
+++ b/arch/x86/include/asm/inst.h
@@ -9,12 +9,68 @@
 
 #define REG_NUM_INVALID		100
 
-#define REG_TYPE_R64		0
-#define REG_TYPE_XMM		1
+#define REG_TYPE_R32		0
+#define REG_TYPE_R64		1
+#define REG_TYPE_XMM		2
 #define REG_TYPE_INVALID	100
 
+	.macro R32_NUM opd r32
+	\opd = REG_NUM_INVALID
+	.ifc \r32,%eax
+	\opd = 0
+	.endif
+	.ifc \r32,%ecx
+	\opd = 1
+	.endif
+	.ifc \r32,%edx
+	\opd = 2
+	.endif
+	.ifc \r32,%ebx
+	\opd = 3
+	.endif
+	.ifc \r32,%esp
+	\opd = 4
+	.endif
+	.ifc \r32,%ebp
+	\opd = 5
+	.endif
+	.ifc \r32,%esi
+	\opd = 6
+	.endif
+	.ifc \r32,%edi
+	\opd = 7
+	.endif
+#ifdef CONFIG_X86_64
+	.ifc \r32,%r8d
+	\opd = 8
+	.endif
+	.ifc \r32,%r9d
+	\opd = 9
+	.endif
+	.ifc \r32,%r10d
+	\opd = 10
+	.endif
+	.ifc \r32,%r11d
+	\opd = 11
+	.endif
+	.ifc \r32,%r12d
+	\opd = 12
+	.endif
+	.ifc \r32,%r13d
+	\opd = 13
+	.endif
+	.ifc \r32,%r14d
+	\opd = 14
+	.endif
+	.ifc \r32,%r15d
+	\opd = 15
+	.endif
+#endif
+	.endm
+
 	.macro R64_NUM opd r64
 	\opd = REG_NUM_INVALID
+#ifdef CONFIG_X86_64
 	.ifc \r64,%rax
 	\opd = 0
 	.endif
@@ -63,6 +119,7 @@
 	.ifc \r64,%r15
 	\opd = 15
 	.endif
+#endif
 	.endm
 
 	.macro XMM_NUM opd xmm
@@ -118,10 +175,13 @@
 	.endm
 
 	.macro REG_TYPE type reg
+	R32_NUM reg_type_r32 \reg
 	R64_NUM reg_type_r64 \reg
 	XMM_NUM reg_type_xmm \reg
 	.if reg_type_r64 <> REG_NUM_INVALID
 	\type = REG_TYPE_R64
+	.elseif reg_type_r32 <> REG_NUM_INVALID
+	\type = REG_TYPE_R32
 	.elseif reg_type_xmm <> REG_NUM_INVALID
 	\type = REG_TYPE_XMM
 	.else
@@ -162,6 +222,16 @@
 	.byte \imm8
 	.endm
 
+	.macro PEXTRD imm8 xmm gpr
+	R32_NUM extrd_opd1 \gpr
+	XMM_NUM extrd_opd2 \xmm
+	PFX_OPD_SIZE
+	PFX_REX extrd_opd1 extrd_opd2
+	.byte 0x0f, 0x3a, 0x16
+	MODRM 0xc0 extrd_opd1 extrd_opd2
+	.byte \imm8
+	.endm
+
 	.macro AESKEYGENASSIST rcon xmm1 xmm2
 	XMM_NUM aeskeygen_opd1 \xmm1
 	XMM_NUM aeskeygen_opd2 \xmm2
diff --git a/arch/x86/include/asm/irq.h b/arch/x86/include/asm/irq.h
index ba870bb..57873be 100644
--- a/arch/x86/include/asm/irq.h
+++ b/arch/x86/include/asm/irq.h
@@ -41,4 +41,9 @@ extern int vector_used_by_percpu_irq(unsigned int vector);
 
 extern void init_ISA_irqs(void);
 
+#ifdef CONFIG_X86_LOCAL_APIC
+void arch_trigger_all_cpu_backtrace(void);
+#define arch_trigger_all_cpu_backtrace arch_trigger_all_cpu_backtrace
+#endif
+
 #endif /* _ASM_X86_IRQ_H */
diff --git a/arch/x86/include/asm/microcode.h b/arch/x86/include/asm/microcode.h
index 6825e2e..6bc3985 100644
--- a/arch/x86/include/asm/microcode.h
+++ b/arch/x86/include/asm/microcode.h
@@ -60,11 +60,11 @@ static inline void __exit exit_amd_microcode(void) {}
 #ifdef CONFIG_MICROCODE_EARLY
 #define MAX_UCODE_COUNT 128
 extern void __init load_ucode_bsp(void);
-extern __init void load_ucode_ap(void);
+extern void __cpuinit load_ucode_ap(void);
 extern int __init save_microcode_in_initrd(void);
 #else
 static inline void __init load_ucode_bsp(void) {}
-static inline __init void load_ucode_ap(void) {}
+static inline void __cpuinit load_ucode_ap(void) {}
 static inline int __init save_microcode_in_initrd(void)
 {
 	return 0;
diff --git a/arch/x86/include/asm/nmi.h b/arch/x86/include/asm/nmi.h
index c0fa356..86f9301 100644
--- a/arch/x86/include/asm/nmi.h
+++ b/arch/x86/include/asm/nmi.h
@@ -18,9 +18,7 @@ extern int proc_nmi_enabled(struct ctl_table *, int ,
 			void __user *, size_t *, loff_t *);
 extern int unknown_nmi_panic;
 
-void arch_trigger_all_cpu_backtrace(void);
-#define arch_trigger_all_cpu_backtrace arch_trigger_all_cpu_backtrace
-#endif
+#endif /* CONFIG_X86_LOCAL_APIC */
 
 #define NMI_FLAG_FIRST	1
 
diff --git a/arch/x86/kernel/apic/hw_nmi.c b/arch/x86/kernel/apic/hw_nmi.c
index 31cb9ae..a698d71 100644
--- a/arch/x86/kernel/apic/hw_nmi.c
+++ b/arch/x86/kernel/apic/hw_nmi.c
@@ -9,6 +9,7 @@
  *
  */
 #include <asm/apic.h>
+#include <asm/nmi.h>
 
 #include <linux/cpumask.h>
 #include <linux/kdebug.h>
diff --git a/arch/x86/kernel/cpu/mtrr/cleanup.c b/arch/x86/kernel/cpu/mtrr/cleanup.c
index 35ffda5..5f90b85 100644
--- a/arch/x86/kernel/cpu/mtrr/cleanup.c
+++ b/arch/x86/kernel/cpu/mtrr/cleanup.c
@@ -714,15 +714,15 @@ int __init mtrr_cleanup(unsigned address_bits)
 	if (mtrr_tom2)
 		x_remove_size = (mtrr_tom2 >> PAGE_SHIFT) - x_remove_base;
 
-	nr_range = x86_get_mtrr_mem_range(range, 0, x_remove_base, x_remove_size);
 	/*
 	 * [0, 1M) should always be covered by var mtrr with WB
 	 * and fixed mtrrs should take effect before var mtrr for it:
 	 */
-	nr_range = add_range_with_merge(range, RANGE_NUM, nr_range, 0,
+	nr_range = add_range_with_merge(range, RANGE_NUM, 0, 0,
 					1ULL<<(20 - PAGE_SHIFT));
-	/* Sort the ranges: */
-	sort_range(range, nr_range);
+	/* add from var mtrr at last */
+	nr_range = x86_get_mtrr_mem_range(range, nr_range,
+					  x_remove_base, x_remove_size);
 
 	range_sums = sum_ranges(range, nr_range);
 	printk(KERN_INFO "total RAM covered: %ldM\n",
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index dab95a8..55b6761 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -34,7 +34,7 @@
 extern pgd_t early_level4_pgt[PTRS_PER_PGD];
 extern pmd_t early_dynamic_pgts[EARLY_DYNAMIC_PAGE_TABLES][PTRS_PER_PMD];
 static unsigned int __initdata next_early_pgt = 2;
-pmdval_t __initdata early_pmd_flags = __PAGE_KERNEL_LARGE & ~(_PAGE_GLOBAL | _PAGE_NX);
+pmdval_t early_pmd_flags = __PAGE_KERNEL_LARGE & ~(_PAGE_GLOBAL | _PAGE_NX);
 
 /* Wipe all early page tables except for the kernel symbol map */
 static void __init reset_early_page_tables(void)
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index 08f7e80..321d65e 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -115,8 +115,10 @@ startup_64:
 	movq	%rdi, %rax
 	shrq	$PUD_SHIFT, %rax
 	andl	$(PTRS_PER_PUD-1), %eax
-	movq	%rdx, (4096+0)(%rbx,%rax,8)
-	movq	%rdx, (4096+8)(%rbx,%rax,8)
+	movq	%rdx, 4096(%rbx,%rax,8)
+	incl	%eax
+	andl	$(PTRS_PER_PUD-1), %eax
+	movq	%rdx, 4096(%rbx,%rax,8)
 
 	addq	$8192, %rbx
 	movq	%rdi, %rax
diff --git a/arch/x86/kernel/i387.c b/arch/x86/kernel/i387.c
index 245a71d..cb33909 100644
--- a/arch/x86/kernel/i387.c
+++ b/arch/x86/kernel/i387.c
@@ -22,23 +22,19 @@
 /*
  * Were we in an interrupt that interrupted kernel mode?
  *
- * For now, with eagerfpu we will return interrupted kernel FPU
- * state as not-idle. TBD: Ideally we can change the return value
- * to something like __thread_has_fpu(current). But we need to
- * be careful of doing __thread_clear_has_fpu() before saving
- * the FPU etc for supporting nested uses etc. For now, take
- * the simple route!
- *
  * On others, we can do a kernel_fpu_begin/end() pair *ONLY* if that
  * pair does nothing at all: the thread must not have fpu (so
  * that we don't try to save the FPU state), and TS must
  * be set (so that the clts/stts pair does nothing that is
  * visible in the interrupted kernel thread).
+ *
+ * Except for the eagerfpu case when we return 1 unless we've already
+ * been eager and saved the state in kernel_fpu_begin().
  */
 static inline bool interrupted_kernel_fpu_idle(void)
 {
 	if (use_eager_fpu())
-		return 0;
+		return __thread_has_fpu(current);
 
 	return !__thread_has_fpu(current) &&
 		(read_cr0() & X86_CR0_TS);
@@ -78,8 +74,8 @@ void __kernel_fpu_begin(void)
 	struct task_struct *me = current;
 
 	if (__thread_has_fpu(me)) {
-		__save_init_fpu(me);
 		__thread_clear_has_fpu(me);
+		__save_init_fpu(me);
 		/* We do 'stts()' in __kernel_fpu_end() */
 	} else if (!use_eager_fpu()) {
 		this_cpu_write(fpu_owner_task, NULL);
diff --git a/arch/x86/kernel/microcode_intel_early.c b/arch/x86/kernel/microcode_intel_early.c
index d893e8e..2e9e128 100644
--- a/arch/x86/kernel/microcode_intel_early.c
+++ b/arch/x86/kernel/microcode_intel_early.c
@@ -487,6 +487,7 @@ static inline void show_saved_mc(void)
 #endif
 
 #if defined(CONFIG_MICROCODE_INTEL_EARLY) && defined(CONFIG_HOTPLUG_CPU)
+static DEFINE_MUTEX(x86_cpu_microcode_mutex);
 /*
  * Save this mc into mc_saved_data. So it will be loaded early when a CPU is
  * hot added or resumes.
@@ -507,7 +508,7 @@ int save_mc_for_early(u8 *mc)
 	 * Hold hotplug lock so mc_saved_data is not accessed by a CPU in
 	 * hotplug.
 	 */
-	cpu_hotplug_driver_lock();
+	mutex_lock(&x86_cpu_microcode_mutex);
 
 	mc_saved_count_init = mc_saved_data.mc_saved_count;
 	mc_saved_count = mc_saved_data.mc_saved_count;
@@ -544,7 +545,7 @@ int save_mc_for_early(u8 *mc)
 	}
 
 out:
-	cpu_hotplug_driver_unlock();
+	mutex_unlock(&x86_cpu_microcode_mutex);
 
 	return ret;
 }
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 607af0d..4e7a37f 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -312,6 +312,8 @@ void arch_cpu_idle(void)
 {
 	if (cpuidle_idle_call())
 		x86_idle();
+	else
+		local_irq_enable();
 }
 
 /*
@@ -368,9 +370,6 @@ void amd_e400_remove_cpu(int cpu)
  */
 static void amd_e400_idle(void)
 {
-	if (need_resched())
-		return;
-
 	if (!amd_e400_c1e_detected) {
 		u32 lo, hi;
 
diff --git a/arch/x86/kernel/relocate_kernel_64.S b/arch/x86/kernel/relocate_kernel_64.S
index 7a6f3b3..f2bb9c9 100644
--- a/arch/x86/kernel/relocate_kernel_64.S
+++ b/arch/x86/kernel/relocate_kernel_64.S
@@ -160,7 +160,7 @@ identity_mapped:
 	xorq    %rbp, %rbp
 	xorq	%r8,  %r8
 	xorq	%r9,  %r9
-	xorq	%r10, %r9
+	xorq	%r10, %r10
 	xorq	%r11, %r11
 	xorq	%r12, %r12
 	xorq	%r13, %r13
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 8db0010..5953dce 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -1240,9 +1240,12 @@ static int decode_modrm(struct x86_emulate_ctxt *ctxt,
 	ctxt->modrm_seg = VCPU_SREG_DS;
 
 	if (ctxt->modrm_mod == 3) {
+		int highbyte_regs = ctxt->rex_prefix == 0;
+
 		op->type = OP_REG;
 		op->bytes = (ctxt->d & ByteOp) ? 1 : ctxt->op_bytes;
-		op->addr.reg = decode_register(ctxt, ctxt->modrm_rm, ctxt->d & ByteOp);
+		op->addr.reg = decode_register(ctxt, ctxt->modrm_rm,
+					       highbyte_regs && (ctxt->d & ByteOp));
 		if (ctxt->d & Sse) {
 			op->type = OP_XMM;
 			op->bytes = 16;
@@ -3997,7 +4000,8 @@ static const struct opcode twobyte_table[256] = {
 	DI(ImplicitOps | Priv, invd), DI(ImplicitOps | Priv, wbinvd), N, N,
 	N, D(ImplicitOps | ModRM), N, N,
 	/* 0x10 - 0x1F */
-	N, N, N, N, N, N, N, N, D(ImplicitOps | ModRM), N, N, N, N, N, N, N,
+	N, N, N, N, N, N, N, N,
+	D(ImplicitOps | ModRM), N, N, N, N, N, N, D(ImplicitOps | ModRM),
 	/* 0x20 - 0x2F */
 	DIP(ModRM | DstMem | Priv | Op3264, cr_read, check_cr_read),
 	DIP(ModRM | DstMem | Priv | Op3264, dr_read, check_dr_read),
@@ -4836,6 +4840,7 @@ twobyte_insn:
 	case 0x08:		/* invd */
 	case 0x0d:		/* GrpP (prefetch) */
 	case 0x18:		/* Grp16 (prefetch/nop) */
+	case 0x1f:		/* nop */
 		break;
 	case 0x20: /* mov cr, reg */
 		ctxt->dst.val = ops->get_cr(ctxt, ctxt->modrm_reg);
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index e1adbb4..0eee2c8 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -1861,11 +1861,14 @@ void kvm_apic_accept_events(struct kvm_vcpu *vcpu)
 {
 	struct kvm_lapic *apic = vcpu->arch.apic;
 	unsigned int sipi_vector;
+	unsigned long pe;
 
-	if (!kvm_vcpu_has_lapic(vcpu))
+	if (!kvm_vcpu_has_lapic(vcpu) || !apic->pending_events)
 		return;
 
-	if (test_and_clear_bit(KVM_APIC_INIT, &apic->pending_events)) {
+	pe = xchg(&apic->pending_events, 0);
+
+	if (test_bit(KVM_APIC_INIT, &pe)) {
 		kvm_lapic_reset(vcpu);
 		kvm_vcpu_reset(vcpu);
 		if (kvm_vcpu_is_bsp(apic->vcpu))
@@ -1873,7 +1876,7 @@ void kvm_apic_accept_events(struct kvm_vcpu *vcpu)
 		else
 			vcpu->arch.mp_state = KVM_MP_STATE_INIT_RECEIVED;
 	}
-	if (test_and_clear_bit(KVM_APIC_SIPI, &apic->pending_events) &&
+	if (test_bit(KVM_APIC_SIPI, &pe) &&
 	    vcpu->arch.mp_state == KVM_MP_STATE_INIT_RECEIVED) {
 		/* evaluate pending_events before reading the vector */
 		smp_rmb();
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index fdc5dca..1f34e92 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -277,6 +277,9 @@ static int __meminit split_mem_range(struct map_range *mr, int nr_range,
 	end_pfn = limit_pfn;
 	nr_range = save_mr(mr, nr_range, start_pfn, end_pfn, 0);
 
+	if (!after_bootmem)
+		adjust_range_page_size_mask(mr, nr_range);
+
 	/* try to merge same page size and continuous */
 	for (i = 0; nr_range > 1 && i < nr_range - 1; i++) {
 		unsigned long old_start;
@@ -291,9 +294,6 @@ static int __meminit split_mem_range(struct map_range *mr, int nr_range,
 		nr_range--;
 	}
 
-	if (!after_bootmem)
-		adjust_range_page_size_mask(mr, nr_range);
-
 	for (i = 0; i < nr_range; i++)
 		printk(KERN_DEBUG " [mem %#010lx-%#010lx] page %s\n",
 				mr[i].start, mr[i].end - 1,
@@ -359,7 +359,17 @@ unsigned long __init_refok init_memory_mapping(unsigned long start,
 }
 
 /*
- * would have hole in the middle or ends, and only ram parts will be mapped.
+ * We need to iterate through the E820 memory map and create direct mappings
+ * for only E820_RAM and E820_KERN_RESERVED regions. We cannot simply
+ * create direct mappings for all pfns from [0 to max_low_pfn) and
+ * [4GB to max_pfn) because of possible memory holes in high addresses
+ * that cannot be marked as UC by fixed/variable range MTRRs.
+ * Depending on the alignment of E820 ranges, this may possibly result
+ * in using smaller size (i.e. 4K instead of 2M or 1G) page tables.
+ *
+ * init_mem_mapping() calls init_range_memory_mapping() with big range.
+ * That range would have hole in the middle or ends, and only ram parts
+ * will be mapped in init_range_memory_mapping().
  */
 static unsigned long __init init_range_memory_mapping(
 					   unsigned long r_start,
@@ -419,6 +429,13 @@ void __init init_mem_mapping(void)
 	max_pfn_mapped = 0; /* will get exact value next */
 	min_pfn_mapped = real_end >> PAGE_SHIFT;
 	last_start = start = real_end;
+
+	/*
+	 * We start from the top (end of memory) and go to the bottom.
+	 * The memblock_find_in_range() gets us a block of RAM from the
+	 * end of RAM in [min_pfn_mapped, max_pfn_mapped) used as new pages
+	 * for page table.
+	 */
 	while (last_start > ISA_END_ADDRESS) {
 		if (last_start > step_size) {
 			start = round_down(last_start - 1, step_size);
diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c
index 305c68b..981c2db 100644
--- a/arch/x86/pci/common.c
+++ b/arch/x86/pci/common.c
@@ -628,7 +628,9 @@ int pcibios_add_device(struct pci_dev *dev)
 
 	pa_data = boot_params.hdr.setup_data;
 	while (pa_data) {
-		data = phys_to_virt(pa_data);
+		data = ioremap(pa_data, sizeof(*rom));
+		if (!data)
+			return -ENOMEM;
 
 		if (data->type == SETUP_PCI) {
 			rom = (struct pci_setup_rom *)data;
@@ -645,6 +647,7 @@ int pcibios_add_device(struct pci_dev *dev)
 			}
 		}
 		pa_data = data->next;
+		iounmap(data);
 	}
 	return 0;
 }
diff --git a/arch/x86/pci/mrst.c b/arch/x86/pci/mrst.c
index 0e0fabf..6eb18c4 100644
--- a/arch/x86/pci/mrst.c
+++ b/arch/x86/pci/mrst.c
@@ -141,11 +141,6 @@ static int pci_device_update_fixed(struct pci_bus *bus, unsigned int devfn,
  */
 static bool type1_access_ok(unsigned int bus, unsigned int devfn, int reg)
 {
-	if (bus == 0 && (devfn == PCI_DEVFN(2, 0)
-				|| devfn == PCI_DEVFN(0, 0)
-				|| devfn == PCI_DEVFN(3, 0)))
-		return 1;
-
 	/* This is a workaround for A0 LNC bug where PCI status register does
 	 * not have new CAP bit set. can not be written by SW either.
 	 *
@@ -155,7 +150,10 @@ static bool type1_access_ok(unsigned int bus, unsigned int devfn, int reg)
 	 */
 	if (reg >= 0x100 || reg == PCI_STATUS || reg == PCI_HEADER_TYPE)
 		return 0;
-
+	if (bus == 0 && (devfn == PCI_DEVFN(2, 0)
+				|| devfn == PCI_DEVFN(0, 0)
+				|| devfn == PCI_DEVFN(3, 0)))
+		return 1;
 	return 0; /* langwell on others */
 }
 
diff --git a/arch/x86/tools/relocs.c b/arch/x86/tools/relocs.c
index 590be10..f7bab68 100644
--- a/arch/x86/tools/relocs.c
+++ b/arch/x86/tools/relocs.c
@@ -42,9 +42,6 @@ static const char * const sym_regex_kernel[S_NSYMTYPES] = {
 	"^(xen_irq_disable_direct_reloc$|"
 	"xen_save_fl_direct_reloc$|"
 	"VDSO|"
-#if ELF_BITS == 64
-	"__vvar_page|"
-#endif
 	"__crc_)",
 
 /*
@@ -72,6 +69,7 @@ static const char * const sym_regex_kernel[S_NSYMTYPES] = {
 	"__per_cpu_load|"
 	"init_per_cpu__.*|"
 	"__end_rodata_hpage_align|"
+	"__vvar_page|"
 #endif
 	"_end)$"
 };
diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c
index 8ff3799..d99cae8 100644
--- a/arch/x86/xen/smp.c
+++ b/arch/x86/xen/smp.c
@@ -17,6 +17,7 @@
 #include <linux/slab.h>
 #include <linux/smp.h>
 #include <linux/irq_work.h>
+#include <linux/tick.h>
 
 #include <asm/paravirt.h>
 #include <asm/desc.h>
@@ -447,6 +448,13 @@ static void __cpuinit xen_play_dead(void) /* used only with HOTPLUG_CPU */
 	play_dead_common();
 	HYPERVISOR_vcpu_op(VCPUOP_down, smp_processor_id(), NULL);
 	cpu_bringup();
+	/*
+	 * commit 4b0c0f294 (tick: Cleanup NOHZ per cpu data on cpu down)
+	 * clears certain data that the cpu_idle loop (which called us
+	 * and that we return from) expects. The only way to get that
+	 * data back is to call:
+	 */
+	tick_nohz_idle_enter();
 }
 
 #else /* !CONFIG_HOTPLUG_CPU */
@@ -576,24 +584,22 @@ void xen_send_IPI_mask_allbutself(const struct cpumask *mask,
 {
 	unsigned cpu;
 	unsigned int this_cpu = smp_processor_id();
+	int xen_vector = xen_map_vector(vector);
 
-	if (!(num_online_cpus() > 1))
+	if (!(num_online_cpus() > 1) || (xen_vector < 0))
 		return;
 
 	for_each_cpu_and(cpu, mask, cpu_online_mask) {
 		if (this_cpu == cpu)
 			continue;
 
-		xen_smp_send_call_function_single_ipi(cpu);
+		xen_send_IPI_one(cpu, xen_vector);
 	}
 }
 
 void xen_send_IPI_allbutself(int vector)
 {
-	int xen_vector = xen_map_vector(vector);
-
-	if (xen_vector >= 0)
-		xen_send_IPI_mask_allbutself(cpu_online_mask, xen_vector);
+	xen_send_IPI_mask_allbutself(cpu_online_mask, vector);
 }
 
 static irqreturn_t xen_call_function_interrupt(int irq, void *dev_id)
diff --git a/arch/x86/xen/smp.h b/arch/x86/xen/smp.h
index 8981a76..c7c2d89 100644
--- a/arch/x86/xen/smp.h
+++ b/arch/x86/xen/smp.h
@@ -5,7 +5,6 @@ extern void xen_send_IPI_mask(const struct cpumask *mask,
 extern void xen_send_IPI_mask_allbutself(const struct cpumask *mask,
 				int vector);
 extern void xen_send_IPI_allbutself(int vector);
-extern void physflat_send_IPI_allbutself(int vector);
 extern void xen_send_IPI_all(int vector);
 extern void xen_send_IPI_self(int vector);