25 files changed, 186 insertions, 81 deletions

diff --git a/arch/x86/boot/boot.h b/arch/x86/boot/boot.h
index 9011a88353de..ed1e9206f830 100644
--- a/arch/x86/boot/boot.h
+++ b/arch/x86/boot/boot.h
@@ -16,7 +16,7 @@
 #ifndef BOOT_BOOT_H
 #define BOOT_BOOT_H
 
-#define STACK_SIZE	512	/* Minimum number of bytes for stack */
+#define STACK_SIZE	1024	/* Minimum number of bytes for stack */
 
 #ifndef __ASSEMBLY__
 
diff --git a/arch/x86/entry/vdso/vdso32-setup.c b/arch/x86/entry/vdso/vdso32-setup.c
index 08a317a9ae4b..a7508d7e20b7 100644
--- a/arch/x86/entry/vdso/vdso32-setup.c
+++ b/arch/x86/entry/vdso/vdso32-setup.c
@@ -31,8 +31,10 @@ static int __init vdso32_setup(char *s)
 {
 	vdso32_enabled = simple_strtoul(s, NULL, 0);
 
-	if (vdso32_enabled > 1)
+	if (vdso32_enabled > 1) {
 		pr_warn("vdso32 values other than 0 and 1 are no longer allowed; vdso disabled\n");
+		vdso32_enabled = 0;
+	}
 
 	return 1;
 }
@@ -63,13 +65,18 @@ subsys_initcall(sysenter_setup);
 /* Register vsyscall32 into the ABI table */
 #include <linux/sysctl.h>
 
+static const int zero;
+static const int one = 1;
+
 static struct ctl_table abi_table2[] = {
 	{
 		.procname	= "vsyscall32",
 		.data		= &vdso32_enabled,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= (int *)&zero,
+		.extra2		= (int *)&one,
 	},
 	{}
 };
diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h
index 1514753fd435..d262f985bbc8 100644
--- a/arch/x86/include/asm/elf.h
+++ b/arch/x86/include/asm/elf.h
@@ -278,7 +278,7 @@ struct task_struct;
 
 #define	ARCH_DLINFO_IA32						\
 do {									\
-	if (vdso32_enabled) {						\
+	if (VDSO_CURRENT_BASE) {					\
 		NEW_AUX_ENT(AT_SYSINFO,	VDSO_ENTRY);			\
 		NEW_AUX_ENT(AT_SYSINFO_EHDR, VDSO_CURRENT_BASE);	\
 	}								\
diff --git a/arch/x86/include/asm/pmem.h b/arch/x86/include/asm/pmem.h
index d8ce3ec816ab..6503526d7b24 100644
--- a/arch/x86/include/asm/pmem.h
+++ b/arch/x86/include/asm/pmem.h
@@ -72,8 +72,8 @@ static inline void arch_wmb_pmem(void)
  * @size:	number of bytes to write back
  *
  * Write back a cache range using the CLWB (cache line write back)
- * instruction.  This function requires explicit ordering with an
- * arch_wmb_pmem() call.  This API is internal to the x86 PMEM implementation.
+ * instruction. Note that @size is internally rounded up to be cache
+ * line size aligned.
  */
 static inline void __arch_wb_cache_pmem(void *vaddr, size_t size)
 {
@@ -87,15 +87,6 @@ static inline void __arch_wb_cache_pmem(void *vaddr, size_t size)
 		clwb(p);
 }
 
-/*
- * copy_from_iter_nocache() on x86 only uses non-temporal stores for iovec
- * iterators, so for other types (bvec & kvec) we must do a cache write-back.
- */
-static inline bool __iter_needs_pmem_wb(struct iov_iter *i)
-{
-	return iter_is_iovec(i) == false;
-}
-
 /**
  * arch_copy_from_iter_pmem - copy data from an iterator to PMEM
  * @addr:	PMEM destination address
@@ -114,8 +105,36 @@ static inline size_t arch_copy_from_iter_pmem(void __pmem *addr, size_t bytes,
 	/* TODO: skip the write-back by always using non-temporal stores */
 	len = copy_from_iter_nocache(vaddr, bytes, i);
 
-	if (__iter_needs_pmem_wb(i))
-		__arch_wb_cache_pmem(vaddr, bytes);
+	/*
+	 * In the iovec case on x86_64 copy_from_iter_nocache() uses
+	 * non-temporal stores for the bulk of the transfer, but we need
+	 * to manually flush if the transfer is unaligned. A cached
+	 * memory copy is used when destination or size is not naturally
+	 * aligned. That is:
+	 *   - Require 8-byte alignment when size is 8 bytes or larger.
+	 *   - Require 4-byte alignment when size is 4 bytes.
+	 *
+	 * In the non-iovec case the entire destination needs to be
+	 * flushed.
+	 */
+	if (iter_is_iovec(i)) {
+		unsigned long flushed, dest = (unsigned long) addr;
+
+		if (bytes < 8) {
+			if (!IS_ALIGNED(dest, 4) || (bytes != 4))
+				__arch_wb_cache_pmem(addr, bytes);
+		} else {
+			if (!IS_ALIGNED(dest, 8)) {
+				dest = ALIGN(dest, boot_cpu_data.x86_clflush_size);
+				__arch_wb_cache_pmem(addr, 1);
+			}
+
+			flushed = dest - (unsigned long) addr;
+			if (bytes > flushed && !IS_ALIGNED(bytes - flushed, 8))
+				__arch_wb_cache_pmem(addr + bytes - 1, 1);
+		}
+	} else
+		__arch_wb_cache_pmem(addr, bytes);
 
 	return len;
 }
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 8ca533b8c606..1e5d2f07416b 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -1875,6 +1875,7 @@ static struct irq_chip ioapic_chip __read_mostly = {
 	.irq_ack		= irq_chip_ack_parent,
 	.irq_eoi		= ioapic_ack_level,
 	.irq_set_affinity	= ioapic_set_affinity,
+	.irq_retrigger		= irq_chip_retrigger_hierarchy,
 	.flags			= IRQCHIP_SKIP_SET_WAKE,
 };
 
@@ -1886,6 +1887,7 @@ static struct irq_chip ioapic_ir_chip __read_mostly = {
 	.irq_ack		= irq_chip_ack_parent,
 	.irq_eoi		= ioapic_ir_ack_level,
 	.irq_set_affinity	= ioapic_set_affinity,
+	.irq_retrigger		= irq_chip_retrigger_hierarchy,
 	.flags			= IRQCHIP_SKIP_SET_WAKE,
 };
 
diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c
index e99b15077e94..62aca448726a 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_amd.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c
@@ -53,7 +53,7 @@ static const char * const th_names[] = {
 	"load_store",
 	"insn_fetch",
 	"combined_unit",
-	"",
+	"decode_unit",
 	"northbridge",
 	"execution_unit",
 };
diff --git a/arch/x86/kernel/cpu/perf_event_intel_lbr.c b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
index 659f01e165d5..8900400230c6 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_lbr.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
@@ -410,6 +410,9 @@ static void intel_pmu_lbr_read_32(struct cpu_hw_events *cpuc)
 		cpuc->lbr_entries[i].to		= msr_lastbranch.to;
 		cpuc->lbr_entries[i].mispred	= 0;
 		cpuc->lbr_entries[i].predicted	= 0;
+		cpuc->lbr_entries[i].in_tx	= 0;
+		cpuc->lbr_entries[i].abort	= 0;
+		cpuc->lbr_entries[i].cycles	= 0;
 		cpuc->lbr_entries[i].reserved	= 0;
 	}
 	cpuc->lbr_stack.nr = i;
diff --git a/arch/x86/kernel/fpu/init.c b/arch/x86/kernel/fpu/init.c
index be39b5fde4b9..1011c05b1bd5 100644
--- a/arch/x86/kernel/fpu/init.c
+++ b/arch/x86/kernel/fpu/init.c
@@ -96,6 +96,7 @@ static void fpu__init_system_early_generic(struct cpuinfo_x86 *c)
  * Boot time FPU feature detection code:
  */
 unsigned int mxcsr_feature_mask __read_mostly = 0xffffffffu;
+EXPORT_SYMBOL_GPL(mxcsr_feature_mask);
 
 static void __init fpu__init_system_mxcsr(void)
 {
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index 311bcf338f07..bfc587579dc3 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -977,6 +977,18 @@ void prepare_ftrace_return(unsigned long self_addr, unsigned long *parent,
 	unsigned long return_hooker = (unsigned long)
 				&return_to_handler;
 
+	/*
+	 * When resuming from suspend-to-ram, this function can be indirectly
+	 * called from early CPU startup code while the CPU is in real mode,
+	 * which would fail miserably.  Make sure the stack pointer is a
+	 * virtual address.
+	 *
+	 * This check isn't as accurate as virt_addr_valid(), but it should be
+	 * good enough for this purpose, and it's fast.
+	 */
+	if (unlikely((long)__builtin_frame_address(0) >= 0))
+		return;
+
 	if (unlikely(ftrace_graph_is_dead()))
 		return;
 
diff --git a/arch/x86/kernel/kprobes/common.h b/arch/x86/kernel/kprobes/common.h
index c6ee63f927ab..d688826e5736 100644
--- a/arch/x86/kernel/kprobes/common.h
+++ b/arch/x86/kernel/kprobes/common.h
@@ -67,7 +67,7 @@
 #endif
 
 /* Ensure if the instruction can be boostable */
-extern int can_boost(kprobe_opcode_t *instruction);
+extern int can_boost(kprobe_opcode_t *instruction, void *addr);
 /* Recover instruction if given address is probed */
 extern unsigned long recover_probed_instruction(kprobe_opcode_t *buf,
 					 unsigned long addr);
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index 023c442c33bb..99d293ea2b49 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -163,12 +163,12 @@ NOKPROBE_SYMBOL(skip_prefixes);
  * Returns non-zero if opcode is boostable.
  * RIP relative instructions are adjusted at copying time in 64 bits mode
  */
-int can_boost(kprobe_opcode_t *opcodes)
+int can_boost(kprobe_opcode_t *opcodes, void *addr)
 {
 	kprobe_opcode_t opcode;
 	kprobe_opcode_t *orig_opcodes = opcodes;
 
-	if (search_exception_tables((unsigned long)opcodes))
+	if (search_exception_tables((unsigned long)addr))
 		return 0;	/* Page fault may occur on this address. */
 
 retry:
@@ -413,7 +413,7 @@ static int arch_copy_kprobe(struct kprobe *p)
 	 * __copy_instruction can modify the displacement of the instruction,
 	 * but it doesn't affect boostable check.
 	 */
-	if (can_boost(p->ainsn.insn))
+	if (can_boost(p->ainsn.insn, p->addr))
 		p->ainsn.boostable = 0;
 	else
 		p->ainsn.boostable = -1;
diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c
index 7b3b9d15c47a..c9d488f3e4cd 100644
--- a/arch/x86/kernel/kprobes/opt.c
+++ b/arch/x86/kernel/kprobes/opt.c
@@ -177,7 +177,7 @@ static int copy_optimized_instructions(u8 *dest, u8 *src)
 
 	while (len < RELATIVEJUMP_SIZE) {
 		ret = __copy_instruction(dest + len, src + len);
-		if (!ret || !can_boost(dest + len))
+		if (!ret || !can_boost(dest + len, src + len))
 			return -EINVAL;
 		len += ret;
 	}
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 47190bd399e7..cec49ecf5f31 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -161,8 +161,8 @@ void kvm_async_pf_task_wait(u32 token)
 			 */
 			rcu_irq_exit();
 			native_safe_halt();
-			rcu_irq_enter();
 			local_irq_disable();
+			rcu_irq_enter();
 		}
 	}
 	if (!n.halted)
diff --git a/arch/x86/kernel/pci-calgary_64.c b/arch/x86/kernel/pci-calgary_64.c
index 0497f719977d..c055e9a4e547 100644
--- a/arch/x86/kernel/pci-calgary_64.c
+++ b/arch/x86/kernel/pci-calgary_64.c
@@ -296,7 +296,7 @@ static void iommu_free(struct iommu_table *tbl, dma_addr_t dma_addr,
 
 	/* were we called with bad_dma_address? */
 	badend = DMA_ERROR_CODE + (EMERGENCY_PAGES * PAGE_SIZE);
-	if (unlikely((dma_addr >= DMA_ERROR_CODE) && (dma_addr < badend))) {
+	if (unlikely(dma_addr < badend)) {
 		WARN(1, KERN_ERR "Calgary: driver tried unmapping bad DMA "
 		       "address 0x%Lx\n", dma_addr);
 		return;
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 2e1fd586b895..9357b29de9bc 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -737,18 +737,20 @@ out:
 static int move_to_next_stateful_cpuid_entry(struct kvm_vcpu *vcpu, int i)
 {
 	struct kvm_cpuid_entry2 *e = &vcpu->arch.cpuid_entries[i];
-	int j, nent = vcpu->arch.cpuid_nent;
+	struct kvm_cpuid_entry2 *ej;
+	int j = i;
+	int nent = vcpu->arch.cpuid_nent;
 
 	e->flags &= ~KVM_CPUID_FLAG_STATE_READ_NEXT;
 	/* when no next entry is found, the current entry[i] is reselected */
-	for (j = i + 1; ; j = (j + 1) % nent) {
-		struct kvm_cpuid_entry2 *ej = &vcpu->arch.cpuid_entries[j];
-		if (ej->function == e->function) {
-			ej->flags |= KVM_CPUID_FLAG_STATE_READ_NEXT;
-			return j;
-		}
-	}
-	return 0; /* silence gcc, even though control never reaches here */
+	do {
+		j = (j + 1) % nent;
+		ej = &vcpu->arch.cpuid_entries[j];
+	} while (ej->function != e->function);
+
+	ej->flags |= KVM_CPUID_FLAG_STATE_READ_NEXT;
+
+	return j;
 }
 
 /* find an entry with matching function, matching index (if needed), and that
@@ -818,12 +820,6 @@ void kvm_cpuid(struct kvm_vcpu *vcpu, u32 *eax, u32 *ebx, u32 *ecx, u32 *edx)
 	if (!best)
 		best = check_cpuid_limit(vcpu, function, index);
 
-	/*
-	 * Perfmon not yet supported for L2 guest.
-	 */
-	if (is_guest_mode(vcpu) && function == 0xa)
-		best = NULL;
-
 	if (best) {
 		*eax = best->eax;
 		*ebx = best->ebx;
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 8eb8a934b531..1049c3c9b877 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -3433,12 +3433,15 @@ static int kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn)
 	return kvm_setup_async_pf(vcpu, gva, kvm_vcpu_gfn_to_hva(vcpu, gfn), &arch);
 }
 
-static bool can_do_async_pf(struct kvm_vcpu *vcpu)
+bool kvm_can_do_async_pf(struct kvm_vcpu *vcpu)
 {
 	if (unlikely(!lapic_in_kernel(vcpu) ||
 		     kvm_event_needs_reinjection(vcpu)))
 		return false;
 
+	if (is_guest_mode(vcpu))
+		return false;
+
 	return kvm_x86_ops->interrupt_allowed(vcpu);
 }
 
@@ -3454,7 +3457,7 @@ static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn,
 	if (!async)
 		return false; /* *pfn has correct page already */
 
-	if (!prefault && can_do_async_pf(vcpu)) {
+	if (!prefault && kvm_can_do_async_pf(vcpu)) {
 		trace_kvm_try_async_get_page(gva, gfn);
 		if (kvm_find_async_pf_gfn(vcpu, gfn)) {
 			trace_kvm_async_pf_doublefault(gva, gfn);
diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h
index 55ffb7b0f95e..e60fc80f8a9c 100644
--- a/arch/x86/kvm/mmu.h
+++ b/arch/x86/kvm/mmu.h
@@ -74,6 +74,7 @@ enum {
 int handle_mmio_page_fault(struct kvm_vcpu *vcpu, u64 addr, bool direct);
 void kvm_init_shadow_mmu(struct kvm_vcpu *vcpu);
 void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly);
+bool kvm_can_do_async_pf(struct kvm_vcpu *vcpu);
 
 static inline unsigned int kvm_mmu_available_pages(struct kvm *kvm)
 {
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 3a7ae80dc49d..50ca8f409a7c 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -6678,14 +6678,20 @@ static int nested_vmx_check_vmptr(struct kvm_vcpu *vcpu, int exit_reason,
 		}
 
 		page = nested_get_page(vcpu, vmptr);
-		if (page == NULL ||
-		    *(u32 *)kmap(page) != VMCS12_REVISION) {
+		if (page == NULL) {
 			nested_vmx_failInvalid(vcpu);
+			skip_emulated_instruction(vcpu);
+			return 1;
+		}
+		if (*(u32 *)kmap(page) != VMCS12_REVISION) {
 			kunmap(page);
+			nested_release_page_clean(page);
+			nested_vmx_failInvalid(vcpu);
 			skip_emulated_instruction(vcpu);
 			return 1;
 		}
 		kunmap(page);
+		nested_release_page_clean(page);
 		vmx->nested.vmxon_ptr = vmptr;
 		break;
 	case EXIT_REASON_VMCLEAR:
@@ -7748,8 +7754,6 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu)
 	case EXIT_REASON_TASK_SWITCH:
 		return true;
 	case EXIT_REASON_CPUID:
-		if (kvm_register_read(vcpu, VCPU_REGS_RAX) == 0xa)
-			return false;
 		return true;
 	case EXIT_REASON_HLT:
 		return nested_cpu_has(vmcs12, CPU_BASED_HLT_EXITING);
@@ -7834,6 +7838,9 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu)
 		return nested_cpu_has2(vmcs12, SECONDARY_EXEC_XSAVES);
 	case EXIT_REASON_PCOMMIT:
 		return nested_cpu_has2(vmcs12, SECONDARY_EXEC_PCOMMIT);
+	case EXIT_REASON_PML_FULL:
+		/* We don't expose PML support to L1. */
+		return false;
 	default:
 		return true;
 	}
@@ -9753,6 +9760,18 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
 
 	}
 
+	if (enable_pml) {
+		/*
+		 * Conceptually we want to copy the PML address and index from
+		 * vmcs01 here, and then back to vmcs01 on nested vmexit. But,
+		 * since we always flush the log on each vmexit, this happens
+		 * to be equivalent to simply resetting the fields in vmcs02.
+		 */
+		ASSERT(vmx->pml_pg);
+		vmcs_write64(PML_ADDRESS, page_to_phys(vmx->pml_pg));
+		vmcs_write16(GUEST_PML_INDEX, PML_ENTITY_NUM - 1);
+	}
+
 	if (nested_cpu_has_ept(vmcs12)) {
 		kvm_mmu_unload(vcpu);
 		nested_ept_init_mmu_context(vcpu);
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index e75095fa414e..6c82792487e9 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -2960,6 +2960,12 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu,
 			      | KVM_VCPUEVENT_VALID_SMM))
 		return -EINVAL;
 
+	/* INITs are latched while in SMM */
+	if (events->flags & KVM_VCPUEVENT_VALID_SMM &&
+	    (events->smi.smm || events->smi.pending) &&
+	    vcpu->arch.mp_state == KVM_MP_STATE_INIT_RECEIVED)
+		return -EINVAL;
+
 	process_nmi(vcpu);
 	vcpu->arch.exception.pending = events->exception.injected;
 	vcpu->arch.exception.nr = events->exception.nr;
@@ -3134,11 +3140,14 @@ static void kvm_vcpu_ioctl_x86_get_xsave(struct kvm_vcpu *vcpu,
 	}
 }
 
+#define XSAVE_MXCSR_OFFSET 24
+
 static int kvm_vcpu_ioctl_x86_set_xsave(struct kvm_vcpu *vcpu,
 					struct kvm_xsave *guest_xsave)
 {
 	u64 xstate_bv =
 		*(u64 *)&guest_xsave->region[XSAVE_HDR_OFFSET / sizeof(u32)];
+	u32 mxcsr = *(u32 *)&guest_xsave->region[XSAVE_MXCSR_OFFSET / sizeof(u32)];
 
 	if (cpu_has_xsave) {
 		/*
@@ -3146,11 +3155,13 @@ static int kvm_vcpu_ioctl_x86_set_xsave(struct kvm_vcpu *vcpu,
 		 * CPUID leaf 0xD, index 0, EDX:EAX.  This is for compatibility
 		 * with old userspace.
 		 */
-		if (xstate_bv & ~kvm_supported_xcr0())
+		if (xstate_bv & ~kvm_supported_xcr0() ||
+			mxcsr & ~mxcsr_feature_mask)
 			return -EINVAL;
 		load_xsave(vcpu, (u8 *)guest_xsave->region);
 	} else {
-		if (xstate_bv & ~XFEATURE_MASK_FPSSE)
+		if (xstate_bv & ~XFEATURE_MASK_FPSSE ||
+			mxcsr & ~mxcsr_feature_mask)
 			return -EINVAL;
 		memcpy(&vcpu->arch.guest_fpu.state.fxsave,
 			guest_xsave->region, sizeof(struct fxregs_state));
@@ -4597,16 +4608,20 @@ emul_write:
 
 static int kernel_pio(struct kvm_vcpu *vcpu, void *pd)
 {
-	/* TODO: String I/O for in kernel device */
-	int r;
+	int r = 0, i;
 
-	if (vcpu->arch.pio.in)
-		r = kvm_io_bus_read(vcpu, KVM_PIO_BUS, vcpu->arch.pio.port,
-				    vcpu->arch.pio.size, pd);
-	else
-		r = kvm_io_bus_write(vcpu, KVM_PIO_BUS,
-				     vcpu->arch.pio.port, vcpu->arch.pio.size,
-				     pd);
+	for (i = 0; i < vcpu->arch.pio.count; i++) {
+		if (vcpu->arch.pio.in)
+			r = kvm_io_bus_read(vcpu, KVM_PIO_BUS, vcpu->arch.pio.port,
+					    vcpu->arch.pio.size, pd);
+		else
+			r = kvm_io_bus_write(vcpu, KVM_PIO_BUS,
+					     vcpu->arch.pio.port, vcpu->arch.pio.size,
+					     pd);
+		if (r)
+			break;
+		pd += vcpu->arch.pio.size;
+	}
 	return r;
 }
 
@@ -4644,6 +4659,8 @@ static int emulator_pio_in_emulated(struct x86_emulate_ctxt *ctxt,
 	if (vcpu->arch.pio.count)
 		goto data_avail;
 
+	memset(vcpu->arch.pio_data, 0, size * count);
+
 	ret = emulator_pio_in_out(vcpu, size, port, val, count, true);
 	if (ret) {
 data_avail:
@@ -6993,6 +7010,12 @@ int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu,
 	    mp_state->mp_state != KVM_MP_STATE_RUNNABLE)
 		return -EINVAL;
 
+	/* INITs are latched while in SMM */
+	if ((is_smm(vcpu) || vcpu->arch.smi_pending) &&
+	    (mp_state->mp_state == KVM_MP_STATE_SIPI_RECEIVED ||
+	     mp_state->mp_state == KVM_MP_STATE_INIT_RECEIVED))
+		return -EINVAL;
+
 	if (mp_state->mp_state == KVM_MP_STATE_SIPI_RECEIVED) {
 		vcpu->arch.mp_state = KVM_MP_STATE_INIT_RECEIVED;
 		set_bit(KVM_APIC_SIPI, &vcpu->arch.apic->pending_events);
@@ -8222,8 +8245,7 @@ bool kvm_arch_can_inject_async_page_present(struct kvm_vcpu *vcpu)
 	if (!(vcpu->arch.apf.msr_val & KVM_ASYNC_PF_ENABLED))
 		return true;
 	else
-		return !kvm_event_needs_reinjection(vcpu) &&
-			kvm_x86_ops->interrupt_allowed(vcpu);
+		return kvm_can_do_async_pf(vcpu);
 }
 
 void kvm_arch_start_assignment(struct kvm *kvm)
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index 493f54172b4a..3aebbd6c6f5f 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -628,21 +628,40 @@ void __init init_mem_mapping(void)
  * devmem_is_allowed() checks to see if /dev/mem access to a certain address
  * is valid. The argument is a physical page number.
  *
- *
- * On x86, access has to be given to the first megabyte of ram because that area
- * contains BIOS code and data regions used by X and dosemu and similar apps.
- * Access has to be given to non-kernel-ram areas as well, these contain the PCI
- * mmio resources as well as potential bios/acpi data regions.
+ * On x86, access has to be given to the first megabyte of RAM because that
+ * area traditionally contains BIOS code and data regions used by X, dosemu,
+ * and similar apps. Since they map the entire memory range, the whole range
+ * must be allowed (for mapping), but any areas that would otherwise be
+ * disallowed are flagged as being "zero filled" instead of rejected.
+ * Access has to be given to non-kernel-ram areas as well, these contain the
+ * PCI mmio resources as well as potential bios/acpi data regions.
  */
 int devmem_is_allowed(unsigned long pagenr)
 {
-	if (pagenr < 256)
-		return 1;
-	if (iomem_is_exclusive(pagenr << PAGE_SHIFT))
+	if (page_is_ram(pagenr)) {
+		/*
+		 * For disallowed memory regions in the low 1MB range,
+		 * request that the page be shown as all zeros.
+		 */
+		if (pagenr < 256)
+			return 2;
+
+		return 0;
+	}
+
+	/*
+	 * This must follow RAM test, since System RAM is considered a
+	 * restricted resource under CONFIG_STRICT_IOMEM.
+	 */
+	if (iomem_is_exclusive(pagenr << PAGE_SHIFT)) {
+		/* Low 1MB bypasses iomem restrictions. */
+		if (pagenr < 256)
+			return 1;
+
 		return 0;
-	if (!page_is_ram(pagenr))
-		return 1;
-	return 0;
+	}
+
+	return 1;
 }
 
 void free_init_pages(char *what, unsigned long begin, unsigned long end)
diff --git a/arch/x86/platform/intel-mid/device_libs/platform_wdt.c b/arch/x86/platform/intel-mid/device_libs/platform_wdt.c
index de734134bc8d..40c616495da7 100644
--- a/arch/x86/platform/intel-mid/device_libs/platform_wdt.c
+++ b/arch/x86/platform/intel-mid/device_libs/platform_wdt.c
@@ -17,7 +17,7 @@
 #include <asm/intel-mid.h>
 #include <asm/io_apic.h>
 
-#define TANGIER_EXT_TIMER0_MSI 15
+#define TANGIER_EXT_TIMER0_MSI 12
 
 static struct platform_device wdt_dev = {
 	.name = "intel_mid_wdt",
diff --git a/arch/x86/um/ptrace_64.c b/arch/x86/um/ptrace_64.c
index a629694ee750..e14c43a2d187 100644
--- a/arch/x86/um/ptrace_64.c
+++ b/arch/x86/um/ptrace_64.c
@@ -121,7 +121,7 @@ int poke_user(struct task_struct *child, long addr, long data)
 	else if ((addr >= offsetof(struct user, u_debugreg[0])) &&
 		(addr <= offsetof(struct user, u_debugreg[7]))) {
 		addr -= offsetof(struct user, u_debugreg[0]);
-		addr = addr >> 2;
+		addr = addr >> 3;
 		if ((addr == 4) || (addr == 5))
 			return -EIO;
 		child->thread.arch.debugregs[addr] = data;
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index 1e56ff583459..63146c378f1e 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -2038,7 +2038,8 @@ static unsigned long __init xen_read_phys_ulong(phys_addr_t addr)
 
 /*
  * Translate a virtual address to a physical one without relying on mapped
- * page tables.
+ * page tables. Don't rely on big pages being aligned in (guest) physical
+ * space!
  */
 static phys_addr_t __init xen_early_virt_to_phys(unsigned long vaddr)
 {
@@ -2059,7 +2060,7 @@ static phys_addr_t __init xen_early_virt_to_phys(unsigned long vaddr)
 						       sizeof(pud)));
 	if (!pud_present(pud))
 		return 0;
-	pa = pud_pfn(pud) << PAGE_SHIFT;
+	pa = pud_val(pud) & PTE_PFN_MASK;
 	if (pud_large(pud))
 		return pa + (vaddr & ~PUD_MASK);
 
@@ -2067,7 +2068,7 @@ static phys_addr_t __init xen_early_virt_to_phys(unsigned long vaddr)
 						       sizeof(pmd)));
 	if (!pmd_present(pmd))
 		return 0;
-	pa = pmd_pfn(pmd) << PAGE_SHIFT;
+	pa = pmd_val(pmd) & PTE_PFN_MASK;
 	if (pmd_large(pmd))
 		return pa + (vaddr & ~PMD_MASK);
 
diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index e345891450c3..df8844a1853a 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -713,10 +713,9 @@ static void __init xen_reserve_xen_mfnlist(void)
 		size = PFN_PHYS(xen_start_info->nr_p2m_frames);
 	}
 
-	if (!xen_is_e820_reserved(start, size)) {
-		memblock_reserve(start, size);
+	memblock_reserve(start, size);
+	if (!xen_is_e820_reserved(start, size))
 		return;
-	}
 
 #ifdef CONFIG_X86_32
 	/*
@@ -727,6 +726,7 @@ static void __init xen_reserve_xen_mfnlist(void)
 	BUG();
 #else
 	xen_relocate_p2m();
+	memblock_free(start, size);
 #endif
 }
 
diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c
index f1ba6a092854..8846257d8792 100644
--- a/arch/x86/xen/time.c
+++ b/arch/x86/xen/time.c
@@ -343,11 +343,11 @@ static int xen_vcpuop_set_next_event(unsigned long delta,
 	WARN_ON(!clockevent_state_oneshot(evt));
 
 	single.timeout_abs_ns = get_abs_timeout(delta);
-	single.flags = VCPU_SSHOTTMR_future;
+	/* Get an event anyway, even if the timeout is already expired */
+	single.flags = 0;
 
 	ret = HYPERVISOR_vcpu_op(VCPUOP_set_singleshot_timer, cpu, &single);
-
-	BUG_ON(ret != 0 && ret != -ETIME);
+	BUG_ON(ret != 0);
 
 	return ret;
 }