Merge commit 'v2.6.35-rc3' into perf/core

Merge reason: Go from -rc1 base to -rc3 base, merge in fixes.

23 files changed, 189 insertions, 52 deletions

diff --git a/arch/x86/.gitignore b/arch/x86/.gitignore
new file mode 100644
index 000000000000..028079065af6
--- /dev/null
+++ b/arch/x86/.gitignore
@@ -0,0 +1,3 @@
+boot/compressed/vmlinux
+tools/test_get_len
+
diff --git a/arch/x86/boot/compressed/mkpiggy.c b/arch/x86/boot/compressed/mkpiggy.c
index bcbd36c41432..5c228129d175 100644
--- a/arch/x86/boot/compressed/mkpiggy.c
+++ b/arch/x86/boot/compressed/mkpiggy.c
@@ -77,7 +77,7 @@ int main(int argc, char *argv[])
 	offs += 32*1024 + 18;	/* Add 32K + 18 bytes slack */
 	offs = (offs+4095) & ~4095; /* Round to a 4K boundary */
 
-	printf(".section \".rodata.compressed\",\"a\",@progbits\n");
+	printf(".section \".rodata..compressed\",\"a\",@progbits\n");
 	printf(".globl z_input_len\n");
 	printf("z_input_len = %lu\n", ilen);
 	printf(".globl z_output_len\n");
diff --git a/arch/x86/boot/compressed/vmlinux.lds.S b/arch/x86/boot/compressed/vmlinux.lds.S
index a6f1a59a5b0c..5ddabceee124 100644
--- a/arch/x86/boot/compressed/vmlinux.lds.S
+++ b/arch/x86/boot/compressed/vmlinux.lds.S
@@ -26,8 +26,8 @@ SECTIONS
 		HEAD_TEXT
 		_ehead = . ;
 	}
-	.rodata.compressed : {
-		*(.rodata.compressed)
+	.rodata..compressed : {
+		*(.rodata..compressed)
 	}
 	.text :	{
 		_text = .; 	/* Text */
diff --git a/arch/x86/include/asm/cache.h b/arch/x86/include/asm/cache.h
index 2f9047cfaaca..48f99f15452e 100644
--- a/arch/x86/include/asm/cache.h
+++ b/arch/x86/include/asm/cache.h
@@ -7,7 +7,7 @@
 #define L1_CACHE_SHIFT	(CONFIG_X86_L1_CACHE_SHIFT)
 #define L1_CACHE_BYTES	(1 << L1_CACHE_SHIFT)
 
-#define __read_mostly __attribute__((__section__(".data.read_mostly")))
+#define __read_mostly __attribute__((__section__(".data..read_mostly")))
 
 #define INTERNODE_CACHE_SHIFT CONFIG_X86_INTERNODE_CACHE_SHIFT
 #define INTERNODE_CACHE_BYTES (1 << INTERNODE_CACHE_SHIFT)
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index b49d8ca228f6..8c7ae4318629 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -110,6 +110,7 @@
 #define MSR_AMD64_PATCH_LOADER		0xc0010020
 #define MSR_AMD64_OSVW_ID_LENGTH	0xc0010140
 #define MSR_AMD64_OSVW_STATUS		0xc0010141
+#define MSR_AMD64_DC_CFG		0xc0011022
 #define MSR_AMD64_IBSFETCHCTL		0xc0011030
 #define MSR_AMD64_IBSFETCHLINAD		0xc0011031
 #define MSR_AMD64_IBSFETCHPHYSAD	0xc0011032
diff --git a/arch/x86/include/asm/pci_x86.h b/arch/x86/include/asm/pci_x86.h
index 8d8797eae5d7..cd2a31dc5fb8 100644
--- a/arch/x86/include/asm/pci_x86.h
+++ b/arch/x86/include/asm/pci_x86.h
@@ -53,6 +53,8 @@ extern int pcibios_last_bus;
 extern struct pci_bus *pci_root_bus;
 extern struct pci_ops pci_root_ops;
 
+void pcibios_scan_specific_bus(int busn);
+
 /* pci-irq.c */
 
 struct irq_info {
diff --git a/arch/x86/include/asm/suspend_32.h b/arch/x86/include/asm/suspend_32.h
index 48dcfa62ea07..fd921c3a6841 100644
--- a/arch/x86/include/asm/suspend_32.h
+++ b/arch/x86/include/asm/suspend_32.h
@@ -15,6 +15,8 @@ static inline int arch_prepare_suspend(void) { return 0; }
 struct saved_context {
 	u16 es, fs, gs, ss;
 	unsigned long cr0, cr2, cr3, cr4;
+	u64 misc_enable;
+	bool misc_enable_saved;
 	struct desc_ptr gdt;
 	struct desc_ptr idt;
 	u16 ldt;
diff --git a/arch/x86/include/asm/suspend_64.h b/arch/x86/include/asm/suspend_64.h
index 06284f42b759..8d942afae681 100644
--- a/arch/x86/include/asm/suspend_64.h
+++ b/arch/x86/include/asm/suspend_64.h
@@ -27,6 +27,8 @@ struct saved_context {
 	u16 ds, es, fs, gs, ss;
 	unsigned long gs_base, gs_kernel_base, fs_base;
 	unsigned long cr0, cr2, cr3, cr4, cr8;
+	u64 misc_enable;
+	bool misc_enable_saved;
 	unsigned long efer;
 	u16 gdt_pad;
 	u16 gdt_limit;
diff --git a/arch/x86/kernel/acpi/wakeup_32.S b/arch/x86/kernel/acpi/wakeup_32.S
index 8ded418b0593..13ab720573e3 100644
--- a/arch/x86/kernel/acpi/wakeup_32.S
+++ b/arch/x86/kernel/acpi/wakeup_32.S
@@ -1,4 +1,4 @@
-	.section .text.page_aligned
+	.section .text..page_aligned
 #include <linux/linkage.h>
 #include <asm/segment.h>
 #include <asm/page_types.h>
diff --git a/arch/x86/kernel/amd_iommu.c b/arch/x86/kernel/amd_iommu.c
index fa5a1474cd18..0d20286d78c6 100644
--- a/arch/x86/kernel/amd_iommu.c
+++ b/arch/x86/kernel/amd_iommu.c
@@ -1487,6 +1487,7 @@ static int __attach_device(struct device *dev,
 			   struct protection_domain *domain)
 {
 	struct iommu_dev_data *dev_data, *alias_data;
+	int ret;
 
 	dev_data   = get_dev_data(dev);
 	alias_data = get_dev_data(dev_data->alias);
@@ -1498,13 +1499,14 @@ static int __attach_device(struct device *dev,
 	spin_lock(&domain->lock);
 
 	/* Some sanity checks */
+	ret = -EBUSY;
 	if (alias_data->domain != NULL &&
 	    alias_data->domain != domain)
-		return -EBUSY;
+		goto out_unlock;
 
 	if (dev_data->domain != NULL &&
 	    dev_data->domain != domain)
-		return -EBUSY;
+		goto out_unlock;
 
 	/* Do real assignment */
 	if (dev_data->alias != dev) {
@@ -1520,10 +1522,14 @@ static int __attach_device(struct device *dev,
 
 	atomic_inc(&dev_data->bind);
 
+	ret = 0;
+
+out_unlock:
+
 	/* ready */
 	spin_unlock(&domain->lock);
 
-	return 0;
+	return ret;
 }
 
 /*
@@ -2324,10 +2330,6 @@ int __init amd_iommu_init_dma_ops(void)
 
 	iommu_detected = 1;
 	swiotlb = 0;
-#ifdef CONFIG_GART_IOMMU
-	gart_iommu_aperture_disabled = 1;
-	gart_iommu_aperture = 0;
-#endif
 
 	/* Make the driver finally visible to the drivers */
 	dma_ops = &amd_iommu_dma_ops;
diff --git a/arch/x86/kernel/amd_iommu_init.c b/arch/x86/kernel/amd_iommu_init.c
index 3bacb4d0844c..3cc63e2b8dd4 100644
--- a/arch/x86/kernel/amd_iommu_init.c
+++ b/arch/x86/kernel/amd_iommu_init.c
@@ -287,8 +287,12 @@ static u8 * __init iommu_map_mmio_space(u64 address)
 {
 	u8 *ret;
 
-	if (!request_mem_region(address, MMIO_REGION_LENGTH, "amd_iommu"))
+	if (!request_mem_region(address, MMIO_REGION_LENGTH, "amd_iommu")) {
+		pr_err("AMD-Vi: Can not reserve memory region %llx for mmio\n",
+			address);
+		pr_err("AMD-Vi: This is a BIOS bug. Please contact your hardware vendor\n");
 		return NULL;
+	}
 
 	ret = ioremap_nocache(address, MMIO_REGION_LENGTH);
 	if (ret != NULL)
@@ -1314,7 +1318,7 @@ static int __init amd_iommu_init(void)
 		ret = amd_iommu_init_dma_ops();
 
 	if (ret)
-		goto free;
+		goto free_disable;
 
 	amd_iommu_init_api();
 
@@ -1332,9 +1336,10 @@ static int __init amd_iommu_init(void)
 out:
 	return ret;
 
-free:
+free_disable:
 	disable_iommus();
 
+free:
 	amd_iommu_uninit_devices();
 
 	free_pages((unsigned long)amd_iommu_pd_alloc_bitmap,
@@ -1353,6 +1358,15 @@ free:
 
 	free_unity_maps();
 
+#ifdef CONFIG_GART_IOMMU
+	/*
+	 * We failed to initialize the AMD IOMMU - try fallback to GART
+	 * if possible.
+	 */
+	gart_iommu_init();
+
+#endif
+
 	goto out;
 }
 
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 707165dbc203..18cc42562250 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -36,6 +36,7 @@
 #include <linux/fs.h>
 #include <linux/mm.h>
 #include <linux/debugfs.h>
+#include <linux/edac_mce.h>
 
 #include <asm/processor.h>
 #include <asm/hw_irq.h>
@@ -169,6 +170,15 @@ void mce_log(struct mce *mce)
 		entry = rcu_dereference_check_mce(mcelog.next);
 		for (;;) {
 			/*
+			 * If edac_mce is enabled, it will check the error type
+			 * and will process it, if it is a known error.
+			 * Otherwise, the error will be sent through mcelog
+			 * interface
+			 */
+			if (edac_mce_parse(mce))
+				return;
+
+			/*
 			 * When the buffer fills up discard new entries.
 			 * Assume that the earlier errors are the more
 			 * interesting ones:
diff --git a/arch/x86/kernel/init_task.c b/arch/x86/kernel/init_task.c
index 3a54dcb9cd0e..43e9ccf44947 100644
--- a/arch/x86/kernel/init_task.c
+++ b/arch/x86/kernel/init_task.c
@@ -34,7 +34,7 @@ EXPORT_SYMBOL(init_task);
 /*
  * per-CPU TSS segments. Threads are completely 'soft' on Linux,
  * no more per-task TSS's. The TSS size is kept cacheline-aligned
- * so they are allowed to end up in the .data.cacheline_aligned
+ * so they are allowed to end up in the .data..cacheline_aligned
  * section. Since TSS's are completely CPU-local, we want them
  * on exact cacheline boundaries, to eliminate cacheline ping-pong.
  */
diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c
index a867940a6dfc..de3b63ae3da2 100644
--- a/arch/x86/kernel/setup_percpu.c
+++ b/arch/x86/kernel/setup_percpu.c
@@ -21,12 +21,6 @@
 #include <asm/cpu.h>
 #include <asm/stackprotector.h>
 
-#ifdef CONFIG_DEBUG_PER_CPU_MAPS
-# define DBG(fmt, ...) pr_dbg(fmt, ##__VA_ARGS__)
-#else
-# define DBG(fmt, ...) do { if (0) pr_dbg(fmt, ##__VA_ARGS__); } while (0)
-#endif
-
 DEFINE_PER_CPU(int, cpu_number);
 EXPORT_PER_CPU_SYMBOL(cpu_number);
 
@@ -247,7 +241,7 @@ void __init setup_per_cpu_areas(void)
 #endif
 #endif
 		/*
-		 * Up to this point, the boot CPU has been using .data.init
+		 * Up to this point, the boot CPU has been using .init.data
 		 * area.  Reload any changed state for the boot CPU.
 		 */
 		if (cpu == boot_cpu_id)
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 37462f1ddba5..c4f33b2e77d6 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -686,7 +686,7 @@ static void __cpuinit do_fork_idle(struct work_struct *work)
 static void __cpuinit announce_cpu(int cpu, int apicid)
 {
 	static int current_node = -1;
-	int node = cpu_to_node(cpu);
+	int node = early_cpu_to_node(cpu);
 
 	if (system_state == SYSTEM_BOOTING) {
 		if (node != current_node) {
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index 2cc249718c46..d0bb52296fa3 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -97,7 +97,7 @@ SECTIONS
 		HEAD_TEXT
 #ifdef CONFIG_X86_32
 		. = ALIGN(PAGE_SIZE);
-		*(.text.page_aligned)
+		*(.text..page_aligned)
 #endif
 		. = ALIGN(8);
 		_stext = .;
@@ -305,7 +305,7 @@ SECTIONS
 	. = ALIGN(PAGE_SIZE);
 	.bss : AT(ADDR(.bss) - LOAD_OFFSET) {
 		__bss_start = .;
-		*(.bss.page_aligned)
+		*(.bss..page_aligned)
 		*(.bss)
 		. = ALIGN(4);
 		__bss_stop = .;
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 81563e76e28f..a6f695d76928 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -1815,6 +1815,9 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
 
 		spte |= PT_WRITABLE_MASK;
 
+		if (!tdp_enabled && !(pte_access & ACC_WRITE_MASK))
+			spte &= ~PT_USER_MASK;
+
 		/*
 		 * Optimization: for pte sync, if spte was writable the hash
 		 * lookup is unnecessary (and expensive). Write protection
@@ -1870,6 +1873,8 @@ static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
 
 			child = page_header(pte & PT64_BASE_ADDR_MASK);
 			mmu_page_remove_parent_pte(child, sptep);
+			__set_spte(sptep, shadow_trap_nonpresent_pte);
+			kvm_flush_remote_tlbs(vcpu->kvm);
 		} else if (pfn != spte_to_pfn(*sptep)) {
 			pgprintk("hfn old %lx new %lx\n",
 				 spte_to_pfn(*sptep), pfn);
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 96dc232bfc56..ce438e0fdd26 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -28,6 +28,7 @@
 #include <linux/ftrace_event.h>
 #include <linux/slab.h>
 
+#include <asm/tlbflush.h>
 #include <asm/desc.h>
 
 #include <asm/virtext.h>
@@ -56,6 +57,8 @@ MODULE_LICENSE("GPL");
 
 #define DEBUGCTL_RESERVED_BITS (~(0x3fULL))
 
+static bool erratum_383_found __read_mostly;
+
 static const u32 host_save_user_msrs[] = {
 #ifdef CONFIG_X86_64
 	MSR_STAR, MSR_LSTAR, MSR_CSTAR, MSR_SYSCALL_MASK, MSR_KERNEL_GS_BASE,
@@ -374,6 +377,31 @@ static void svm_queue_exception(struct kvm_vcpu *vcpu, unsigned nr,
 	svm->vmcb->control.event_inj_err = error_code;
 }
 
+static void svm_init_erratum_383(void)
+{
+	u32 low, high;
+	int err;
+	u64 val;
+
+	/* Only Fam10h is affected */
+	if (boot_cpu_data.x86 != 0x10)
+		return;
+
+	/* Use _safe variants to not break nested virtualization */
+	val = native_read_msr_safe(MSR_AMD64_DC_CFG, &err);
+	if (err)
+		return;
+
+	val |= (1ULL << 47);
+
+	low  = lower_32_bits(val);
+	high = upper_32_bits(val);
+
+	native_write_msr_safe(MSR_AMD64_DC_CFG, low, high);
+
+	erratum_383_found = true;
+}
+
 static int has_svm(void)
 {
 	const char *msg;
@@ -429,6 +457,8 @@ static int svm_hardware_enable(void *garbage)
 
 	wrmsrl(MSR_VM_HSAVE_PA, page_to_pfn(sd->save_area) << PAGE_SHIFT);
 
+	svm_init_erratum_383();
+
 	return 0;
 }
 
@@ -1410,8 +1440,59 @@ static int nm_interception(struct vcpu_svm *svm)
 	return 1;
 }
 
-static int mc_interception(struct vcpu_svm *svm)
+static bool is_erratum_383(void)
 {
+	int err, i;
+	u64 value;
+
+	if (!erratum_383_found)
+		return false;
+
+	value = native_read_msr_safe(MSR_IA32_MC0_STATUS, &err);
+	if (err)
+		return false;
+
+	/* Bit 62 may or may not be set for this mce */
+	value &= ~(1ULL << 62);
+
+	if (value != 0xb600000000010015ULL)
+		return false;
+
+	/* Clear MCi_STATUS registers */
+	for (i = 0; i < 6; ++i)
+		native_write_msr_safe(MSR_IA32_MCx_STATUS(i), 0, 0);
+
+	value = native_read_msr_safe(MSR_IA32_MCG_STATUS, &err);
+	if (!err) {
+		u32 low, high;
+
+		value &= ~(1ULL << 2);
+		low    = lower_32_bits(value);
+		high   = upper_32_bits(value);
+
+		native_write_msr_safe(MSR_IA32_MCG_STATUS, low, high);
+	}
+
+	/* Flush tlb to evict multi-match entries */
+	__flush_tlb_all();
+
+	return true;
+}
+
+static void svm_handle_mce(struct vcpu_svm *svm)
+{
+	if (is_erratum_383()) {
+		/*
+		 * Erratum 383 triggered. Guest state is corrupt so kill the
+		 * guest.
+		 */
+		pr_err("KVM: Guest triggered AMD Erratum 383\n");
+
+		set_bit(KVM_REQ_TRIPLE_FAULT, &svm->vcpu.requests);
+
+		return;
+	}
+
 	/*
 	 * On an #MC intercept the MCE handler is not called automatically in
 	 * the host. So do it by hand here.
@@ -1420,6 +1501,11 @@ static int mc_interception(struct vcpu_svm *svm)
 		"int $0x12\n");
 	/* not sure if we ever come back to this point */
 
+	return;
+}
+
+static int mc_interception(struct vcpu_svm *svm)
+{
 	return 1;
 }
 
@@ -3088,6 +3174,14 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu)
 		vcpu->arch.regs_avail &= ~(1 << VCPU_EXREG_PDPTR);
 		vcpu->arch.regs_dirty &= ~(1 << VCPU_EXREG_PDPTR);
 	}
+
+	/*
+	 * We need to handle MC intercepts here before the vcpu has a chance to
+	 * change the physical cpu
+	 */
+	if (unlikely(svm->vmcb->control.exit_code ==
+		     SVM_EXIT_EXCP_BASE + MC_VECTOR))
+		svm_handle_mce(svm);
 }
 
 #undef R
diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c
index 550df481accd..787c52ca49c3 100644
--- a/arch/x86/mm/numa.c
+++ b/arch/x86/mm/numa.c
@@ -3,12 +3,6 @@
 #include <linux/module.h>
 #include <linux/bootmem.h>
 
-#ifdef CONFIG_DEBUG_PER_CPU_MAPS
-# define DBG(x...) printk(KERN_DEBUG x)
-#else
-# define DBG(x...)
-#endif
-
 /*
  * Which logical CPUs are on which nodes
  */
diff --git a/arch/x86/pci/i386.c b/arch/x86/pci/i386.c
index 97da2ba9344b..6fdb3ec30c31 100644
--- a/arch/x86/pci/i386.c
+++ b/arch/x86/pci/i386.c
@@ -96,6 +96,7 @@ EXPORT_SYMBOL(pcibios_align_resource);
  *	  the fact the PCI specs explicitly allow address decoders to be
  *	  shared between expansion ROMs and other resource regions, it's
  *	  at least dangerous)
+ *	- bad resource sizes or overlaps with other regions
  *
  *  Our solution:
  *	(1) Allocate resources for all buses behind PCI-to-PCI bridges.
@@ -136,6 +137,7 @@ static void __init pcibios_allocate_bus_resources(struct list_head *bus_list)
 					 * child resource allocations in this
 					 * range.
 					 */
+					r->start = r->end = 0;
 					r->flags = 0;
 				}
 			}
diff --git a/arch/x86/pci/legacy.c b/arch/x86/pci/legacy.c
index 0db5eaf54560..8d460eaf524f 100644
--- a/arch/x86/pci/legacy.c
+++ b/arch/x86/pci/legacy.c
@@ -11,28 +11,14 @@
  */
 static void __devinit pcibios_fixup_peer_bridges(void)
 {
-	int n, devfn;
-	long node;
+	int n;
 
 	if (pcibios_last_bus <= 0 || pcibios_last_bus > 0xff)
 		return;
 	DBG("PCI: Peer bridge fixup\n");
 
-	for (n=0; n <= pcibios_last_bus; n++) {
-		u32 l;
-		if (pci_find_bus(0, n))
-			continue;
-		node = get_mp_bus_to_node(n);
-		for (devfn = 0; devfn < 256; devfn += 8) {
-			if (!raw_pci_read(0, n, devfn, PCI_VENDOR_ID, 2, &l) &&
-			    l != 0x0000 && l != 0xffff) {
-				DBG("Found device at %02x:%02x [%04x]\n", n, devfn, l);
-				printk(KERN_INFO "PCI: Discovered peer bus %02x\n", n);
-				pci_scan_bus_on_node(n, &pci_root_ops, node);
-				break;
-			}
-		}
-	}
+	for (n=0; n <= pcibios_last_bus; n++)
+		pcibios_scan_specific_bus(n);
 }
 
 int __init pci_legacy_init(void)
@@ -50,6 +36,28 @@ int __init pci_legacy_init(void)
 	return 0;
 }
 
+void pcibios_scan_specific_bus(int busn)
+{
+	int devfn;
+	long node;
+	u32 l;
+
+	if (pci_find_bus(0, busn))
+		return;
+
+	node = get_mp_bus_to_node(busn);
+	for (devfn = 0; devfn < 256; devfn += 8) {
+		if (!raw_pci_read(0, busn, devfn, PCI_VENDOR_ID, 2, &l) &&
+		    l != 0x0000 && l != 0xffff) {
+			DBG("Found device at %02x:%02x [%04x]\n", busn, devfn, l);
+			printk(KERN_INFO "PCI: Discovered peer bus %02x\n", busn);
+			pci_scan_bus_on_node(busn, &pci_root_ops, node);
+			return;
+		}
+	}
+}
+EXPORT_SYMBOL_GPL(pcibios_scan_specific_bus);
+
 int __init pci_subsys_init(void)
 {
 	/*
diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c
index 0a979f3e5b8a..1290ba54b350 100644
--- a/arch/x86/power/cpu.c
+++ b/arch/x86/power/cpu.c
@@ -105,6 +105,8 @@ static void __save_processor_state(struct saved_context *ctxt)
 	ctxt->cr4 = read_cr4();
 	ctxt->cr8 = read_cr8();
 #endif
+	ctxt->misc_enable_saved = !rdmsrl_safe(MSR_IA32_MISC_ENABLE,
+					       &ctxt->misc_enable);
 }
 
 /* Needed by apm.c */
@@ -152,6 +154,8 @@ static void fix_processor_context(void)
  */
 static void __restore_processor_state(struct saved_context *ctxt)
 {
+	if (ctxt->misc_enable_saved)
+		wrmsrl(MSR_IA32_MISC_ENABLE, ctxt->misc_enable);
 	/*
 	 * control registers
 	 */
diff --git a/arch/x86/xen/suspend.c b/arch/x86/xen/suspend.c
index 987267f79bf5..a9c661108034 100644
--- a/arch/x86/xen/suspend.c
+++ b/arch/x86/xen/suspend.c
@@ -60,6 +60,6 @@ static void xen_vcpu_notify_restore(void *data)
 
 void xen_arch_resume(void)
 {
-	smp_call_function(xen_vcpu_notify_restore,
-			       (void *)CLOCK_EVT_NOTIFY_RESUME, 1);
+	on_each_cpu(xen_vcpu_notify_restore,
+		    (void *)CLOCK_EVT_NOTIFY_RESUME, 1);
 }