Merge commit 'v2.6.34-rc7' into oprofile

Merge reason: Update to Linus's latest -rc.

Signed-off-by: Ingo Molnar <mingo@elte.hu>

18 files changed, 151 insertions, 108 deletions

diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S
index 59b4556a5b9..e790bc1fbfa 100644
--- a/arch/x86/ia32/ia32entry.S
+++ b/arch/x86/ia32/ia32entry.S
@@ -626,7 +626,7 @@ ia32_sys_call_table:
 	.quad stub32_sigreturn
 	.quad stub32_clone		/* 120 */
 	.quad sys_setdomainname
-	.quad sys_uname
+	.quad sys_newuname
 	.quad sys_modify_ldt
 	.quad compat_sys_adjtimex
 	.quad sys32_mprotect		/* 125 */
diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h
index a1dcfa3ab17..30a3e977612 100644
--- a/arch/x86/include/asm/io.h
+++ b/arch/x86/include/asm/io.h
@@ -347,6 +347,7 @@ extern void __iomem *early_ioremap(resource_size_t phys_addr,
 extern void __iomem *early_memremap(resource_size_t phys_addr,
 				    unsigned long size);
 extern void early_iounmap(void __iomem *addr, unsigned long size);
+extern void fixup_early_ioremap(void);
 
 #define IO_SPACE_LIMIT 0xffff
 
diff --git a/arch/x86/kernel/apb_timer.c b/arch/x86/kernel/apb_timer.c
index ff469e47005..a35347501d3 100644
--- a/arch/x86/kernel/apb_timer.c
+++ b/arch/x86/kernel/apb_timer.c
@@ -429,7 +429,7 @@ static int apbt_cpuhp_notify(struct notifier_block *n,
 
 static __init int apbt_late_init(void)
 {
-	if (disable_apbt_percpu)
+	if (disable_apbt_percpu || !apb_timer_block_enabled)
 		return 0;
 	/* This notifier should be called after workqueue is ready */
 	hotcpu_notifier(apbt_cpuhp_notify, -20);
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 127b8718abf..eb2789c3f72 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -2545,6 +2545,9 @@ void irq_force_complete_move(int irq)
 	struct irq_desc *desc = irq_to_desc(irq);
 	struct irq_cfg *cfg = desc->chip_data;
 
+	if (!cfg)
+		return;
+
 	__irq_complete_move(&desc, cfg->vector);
 }
 #else
diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
index d360b56e982..b6215b9798e 100644
--- a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
+++ b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
@@ -929,7 +929,8 @@ static int fill_powernow_table_pstate(struct powernow_k8_data *data,
 		powernow_table[i].index = index;
 
 		/* Frequency may be rounded for these */
-		if (boot_cpu_data.x86 == 0x10 || boot_cpu_data.x86 == 0x11) {
+		if ((boot_cpu_data.x86 == 0x10 && boot_cpu_data.x86_model < 10)
+				 || boot_cpu_data.x86 == 0x11) {
 			powernow_table[i].frequency =
 				freq_from_fid_did(lo & 0x3f, (lo >> 6) & 7);
 		} else
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 7e1cca13af3..1366c7cfd48 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -47,6 +47,27 @@ static void __cpuinit early_init_intel(struct cpuinfo_x86 *c)
 		(c->x86 == 0x6 && c->x86_model >= 0x0e))
 		set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
 
+	/*
+	 * Atom erratum AAE44/AAF40/AAG38/AAH41:
+	 *
+	 * A race condition between speculative fetches and invalidating
+	 * a large page.  This is worked around in microcode, but we
+	 * need the microcode to have already been loaded... so if it is
+	 * not, recommend a BIOS update and disable large pages.
+	 */
+	if (c->x86 == 6 && c->x86_model == 0x1c && c->x86_mask <= 2) {
+		u32 ucode, junk;
+
+		wrmsr(MSR_IA32_UCODE_REV, 0, 0);
+		sync_core();
+		rdmsr(MSR_IA32_UCODE_REV, junk, ucode);
+
+		if (ucode < 0x20e) {
+			printk(KERN_WARNING "Atom PSE erratum detected, BIOS microcode update recommended\n");
+			clear_cpu_cap(c, X86_FEATURE_PSE);
+		}
+	}
+
 #ifdef CONFIG_X86_64
 	set_cpu_cap(c, X86_FEATURE_SYSENTER32);
 #else
diff --git a/arch/x86/kernel/cpu/vmware.c b/arch/x86/kernel/cpu/vmware.c
index 1cbed97b59c..dfdb4dba232 100644
--- a/arch/x86/kernel/cpu/vmware.c
+++ b/arch/x86/kernel/cpu/vmware.c
@@ -22,6 +22,7 @@
  */
 
 #include <linux/dmi.h>
+#include <linux/module.h>
 #include <asm/div64.h>
 #include <asm/vmware.h>
 #include <asm/x86_init.h>
@@ -101,6 +102,7 @@ int vmware_platform(void)
 
 	return 0;
 }
+EXPORT_SYMBOL(vmware_platform);
 
 /*
  * VMware hypervisor takes care of exporting a reliable TSC to the guest.
diff --git a/arch/x86/kernel/dumpstack.h b/arch/x86/kernel/dumpstack.h
index e39e77168a3..e1a93be4fd4 100644
--- a/arch/x86/kernel/dumpstack.h
+++ b/arch/x86/kernel/dumpstack.h
@@ -14,6 +14,8 @@
 #define get_bp(bp) asm("movq %%rbp, %0" : "=r" (bp) :)
 #endif
 
+#include <linux/uaccess.h>
+
 extern void
 show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs,
 		unsigned long *stack, unsigned long bp, char *log_lvl);
@@ -42,8 +44,10 @@ static inline unsigned long rewind_frame_pointer(int n)
 	get_bp(frame);
 
 #ifdef CONFIG_FRAME_POINTER
-	while (n--)
-		frame = frame->next_frame;
+	while (n--) {
+		if (probe_kernel_address(&frame->next_frame, frame))
+			break;
+	}
 #endif
 
 	return (unsigned long)frame;
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index dc9690b4c4c..17cb3295cbf 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -276,12 +276,12 @@ int copy_thread(unsigned long clone_flags, unsigned long sp,
 
 	set_tsk_thread_flag(p, TIF_FORK);
 
-	p->thread.fs = me->thread.fs;
-	p->thread.gs = me->thread.gs;
 	p->thread.io_bitmap_ptr = NULL;
 
 	savesegment(gs, p->thread.gsindex);
+	p->thread.gs = p->thread.gsindex ? 0 : me->thread.gs;
 	savesegment(fs, p->thread.fsindex);
+	p->thread.fs = p->thread.fsindex ? 0 : me->thread.fs;
 	savesegment(es, p->thread.es);
 	savesegment(ds, p->thread.ds);
 
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 48aeee8eefb..19a8906bcaa 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -1490,8 +1490,8 @@ static int mmu_zap_unsync_children(struct kvm *kvm,
 		for_each_sp(pages, sp, parents, i) {
 			kvm_mmu_zap_page(kvm, sp);
 			mmu_pages_clear_parents(&parents);
+			zapped++;
 		}
-		zapped += pages.nr;
 		kvm_mmu_pages_init(parent, &parents, &pages);
 	}
 
@@ -1542,14 +1542,16 @@ void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned int kvm_nr_mmu_pages)
 	 */
 
 	if (used_pages > kvm_nr_mmu_pages) {
-		while (used_pages > kvm_nr_mmu_pages) {
+		while (used_pages > kvm_nr_mmu_pages &&
+			!list_empty(&kvm->arch.active_mmu_pages)) {
 			struct kvm_mmu_page *page;
 
 			page = container_of(kvm->arch.active_mmu_pages.prev,
 					    struct kvm_mmu_page, link);
-			kvm_mmu_zap_page(kvm, page);
+			used_pages -= kvm_mmu_zap_page(kvm, page);
 			used_pages--;
 		}
+		kvm_nr_mmu_pages = used_pages;
 		kvm->arch.n_free_mmu_pages = 0;
 	}
 	else
@@ -1596,7 +1598,8 @@ static void mmu_unshadow(struct kvm *kvm, gfn_t gfn)
 		    && !sp->role.invalid) {
 			pgprintk("%s: zap %lx %x\n",
 				 __func__, gfn, sp->role.word);
-			kvm_mmu_zap_page(kvm, sp);
+			if (kvm_mmu_zap_page(kvm, sp))
+				nn = bucket->first;
 		}
 	}
 }
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 445c59411ed..2ba58206812 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -706,29 +706,28 @@ static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id)
 	if (err)
 		goto free_svm;
 
+	err = -ENOMEM;
 	page = alloc_page(GFP_KERNEL);
-	if (!page) {
-		err = -ENOMEM;
+	if (!page)
 		goto uninit;
-	}
 
-	err = -ENOMEM;
 	msrpm_pages = alloc_pages(GFP_KERNEL, MSRPM_ALLOC_ORDER);
 	if (!msrpm_pages)
-		goto uninit;
+		goto free_page1;
 
 	nested_msrpm_pages = alloc_pages(GFP_KERNEL, MSRPM_ALLOC_ORDER);
 	if (!nested_msrpm_pages)
-		goto uninit;
-
-	svm->msrpm = page_address(msrpm_pages);
-	svm_vcpu_init_msrpm(svm->msrpm);
+		goto free_page2;
 
 	hsave_page = alloc_page(GFP_KERNEL);
 	if (!hsave_page)
-		goto uninit;
+		goto free_page3;
+
 	svm->nested.hsave = page_address(hsave_page);
 
+	svm->msrpm = page_address(msrpm_pages);
+	svm_vcpu_init_msrpm(svm->msrpm);
+
 	svm->nested.msrpm = page_address(nested_msrpm_pages);
 
 	svm->vmcb = page_address(page);
@@ -744,6 +743,12 @@ static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id)
 
 	return &svm->vcpu;
 
+free_page3:
+	__free_pages(nested_msrpm_pages, MSRPM_ALLOC_ORDER);
+free_page2:
+	__free_pages(msrpm_pages, MSRPM_ALLOC_ORDER);
+free_page1:
+	__free_page(page);
 uninit:
 	kvm_vcpu_uninit(&svm->vcpu);
 free_svm:
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 686492ed307..bc933cfb4e6 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -77,6 +77,8 @@ module_param(emulate_invalid_guest_state, bool, S_IRUGO);
 #define KVM_PMODE_VM_CR4_ALWAYS_ON (X86_CR4_PAE | X86_CR4_VMXE)
 #define KVM_RMODE_VM_CR4_ALWAYS_ON (X86_CR4_VME | X86_CR4_PAE | X86_CR4_VMXE)
 
+#define RMODE_GUEST_OWNED_EFLAGS_BITS (~(X86_EFLAGS_IOPL | X86_EFLAGS_VM))
+
 /*
  * These 2 parameters are used to config the controls for Pause-Loop Exiting:
  * ple_gap:    upper bound on the amount of time between two successive
@@ -131,7 +133,7 @@ struct vcpu_vmx {
 	} host_state;
 	struct {
 		int vm86_active;
-		u8 save_iopl;
+		ulong save_rflags;
 		struct kvm_save_segment {
 			u16 selector;
 			unsigned long base;
@@ -818,18 +820,23 @@ static void vmx_fpu_deactivate(struct kvm_vcpu *vcpu)
 
 static unsigned long vmx_get_rflags(struct kvm_vcpu *vcpu)
 {
-	unsigned long rflags;
+	unsigned long rflags, save_rflags;
 
 	rflags = vmcs_readl(GUEST_RFLAGS);
-	if (to_vmx(vcpu)->rmode.vm86_active)
-		rflags &= ~(unsigned long)(X86_EFLAGS_IOPL | X86_EFLAGS_VM);
+	if (to_vmx(vcpu)->rmode.vm86_active) {
+		rflags &= RMODE_GUEST_OWNED_EFLAGS_BITS;
+		save_rflags = to_vmx(vcpu)->rmode.save_rflags;
+		rflags |= save_rflags & ~RMODE_GUEST_OWNED_EFLAGS_BITS;
+	}
 	return rflags;
 }
 
 static void vmx_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags)
 {
-	if (to_vmx(vcpu)->rmode.vm86_active)
+	if (to_vmx(vcpu)->rmode.vm86_active) {
+		to_vmx(vcpu)->rmode.save_rflags = rflags;
 		rflags |= X86_EFLAGS_IOPL | X86_EFLAGS_VM;
+	}
 	vmcs_writel(GUEST_RFLAGS, rflags);
 }
 
@@ -1483,8 +1490,8 @@ static void enter_pmode(struct kvm_vcpu *vcpu)
 	vmcs_write32(GUEST_TR_AR_BYTES, vmx->rmode.tr.ar);
 
 	flags = vmcs_readl(GUEST_RFLAGS);
-	flags &= ~(X86_EFLAGS_IOPL | X86_EFLAGS_VM);
-	flags |= (vmx->rmode.save_iopl << IOPL_SHIFT);
+	flags &= RMODE_GUEST_OWNED_EFLAGS_BITS;
+	flags |= vmx->rmode.save_rflags & ~RMODE_GUEST_OWNED_EFLAGS_BITS;
 	vmcs_writel(GUEST_RFLAGS, flags);
 
 	vmcs_writel(GUEST_CR4, (vmcs_readl(GUEST_CR4) & ~X86_CR4_VME) |
@@ -1557,8 +1564,7 @@ static void enter_rmode(struct kvm_vcpu *vcpu)
 	vmcs_write32(GUEST_TR_AR_BYTES, 0x008b);
 
 	flags = vmcs_readl(GUEST_RFLAGS);
-	vmx->rmode.save_iopl
-		= (flags & X86_EFLAGS_IOPL) >> IOPL_SHIFT;
+	vmx->rmode.save_rflags = flags;
 
 	flags |= X86_EFLAGS_IOPL | X86_EFLAGS_VM;
 
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 24cd0ee896e..3c4ca98ad27 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -433,8 +433,6 @@ void kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
 
 #ifdef CONFIG_X86_64
 	if (cr0 & 0xffffffff00000000UL) {
-		printk(KERN_DEBUG "set_cr0: 0x%lx #GP, reserved bits 0x%lx\n",
-		       cr0, kvm_read_cr0(vcpu));
 		kvm_inject_gp(vcpu, 0);
 		return;
 	}
@@ -443,14 +441,11 @@ void kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
 	cr0 &= ~CR0_RESERVED_BITS;
 
 	if ((cr0 & X86_CR0_NW) && !(cr0 & X86_CR0_CD)) {
-		printk(KERN_DEBUG "set_cr0: #GP, CD == 0 && NW == 1\n");
 		kvm_inject_gp(vcpu, 0);
 		return;
 	}
 
 	if ((cr0 & X86_CR0_PG) && !(cr0 & X86_CR0_PE)) {
-		printk(KERN_DEBUG "set_cr0: #GP, set PG flag "
-		       "and a clear PE flag\n");
 		kvm_inject_gp(vcpu, 0);
 		return;
 	}
@@ -461,15 +456,11 @@ void kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
 			int cs_db, cs_l;
 
 			if (!is_pae(vcpu)) {
-				printk(KERN_DEBUG "set_cr0: #GP, start paging "
-				       "in long mode while PAE is disabled\n");
 				kvm_inject_gp(vcpu, 0);
 				return;
 			}
 			kvm_x86_ops->get_cs_db_l_bits(vcpu, &cs_db, &cs_l);
 			if (cs_l) {
-				printk(KERN_DEBUG "set_cr0: #GP, start paging "
-				       "in long mode while CS.L == 1\n");
 				kvm_inject_gp(vcpu, 0);
 				return;
 
@@ -477,8 +468,6 @@ void kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
 		} else
 #endif
 		if (is_pae(vcpu) && !load_pdptrs(vcpu, vcpu->arch.cr3)) {
-			printk(KERN_DEBUG "set_cr0: #GP, pdptrs "
-			       "reserved bits\n");
 			kvm_inject_gp(vcpu, 0);
 			return;
 		}
@@ -505,28 +494,23 @@ void kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
 	unsigned long pdptr_bits = X86_CR4_PGE | X86_CR4_PSE | X86_CR4_PAE;
 
 	if (cr4 & CR4_RESERVED_BITS) {
-		printk(KERN_DEBUG "set_cr4: #GP, reserved bits\n");
 		kvm_inject_gp(vcpu, 0);
 		return;
 	}
 
 	if (is_long_mode(vcpu)) {
 		if (!(cr4 & X86_CR4_PAE)) {
-			printk(KERN_DEBUG "set_cr4: #GP, clearing PAE while "
-			       "in long mode\n");
 			kvm_inject_gp(vcpu, 0);
 			return;
 		}
 	} else if (is_paging(vcpu) && (cr4 & X86_CR4_PAE)
 		   && ((cr4 ^ old_cr4) & pdptr_bits)
 		   && !load_pdptrs(vcpu, vcpu->arch.cr3)) {
-		printk(KERN_DEBUG "set_cr4: #GP, pdptrs reserved bits\n");
 		kvm_inject_gp(vcpu, 0);
 		return;
 	}
 
 	if (cr4 & X86_CR4_VMXE) {
-		printk(KERN_DEBUG "set_cr4: #GP, setting VMXE\n");
 		kvm_inject_gp(vcpu, 0);
 		return;
 	}
@@ -547,21 +531,16 @@ void kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3)
 
 	if (is_long_mode(vcpu)) {
 		if (cr3 & CR3_L_MODE_RESERVED_BITS) {
-			printk(KERN_DEBUG "set_cr3: #GP, reserved bits\n");
 			kvm_inject_gp(vcpu, 0);
 			return;
 		}
 	} else {
 		if (is_pae(vcpu)) {
 			if (cr3 & CR3_PAE_RESERVED_BITS) {
-				printk(KERN_DEBUG
-				       "set_cr3: #GP, reserved bits\n");
 				kvm_inject_gp(vcpu, 0);
 				return;
 			}
 			if (is_paging(vcpu) && !load_pdptrs(vcpu, cr3)) {
-				printk(KERN_DEBUG "set_cr3: #GP, pdptrs "
-				       "reserved bits\n");
 				kvm_inject_gp(vcpu, 0);
 				return;
 			}
@@ -593,7 +572,6 @@ EXPORT_SYMBOL_GPL(kvm_set_cr3);
 void kvm_set_cr8(struct kvm_vcpu *vcpu, unsigned long cr8)
 {
 	if (cr8 & CR8_RESERVED_BITS) {
-		printk(KERN_DEBUG "set_cr8: #GP, reserved bits 0x%lx\n", cr8);
 		kvm_inject_gp(vcpu, 0);
 		return;
 	}
@@ -649,15 +627,12 @@ static u32 emulated_msrs[] = {
 static void set_efer(struct kvm_vcpu *vcpu, u64 efer)
 {
 	if (efer & efer_reserved_bits) {
-		printk(KERN_DEBUG "set_efer: 0x%llx #GP, reserved bits\n",
-		       efer);
 		kvm_inject_gp(vcpu, 0);
 		return;
 	}
 
 	if (is_paging(vcpu)
 	    && (vcpu->arch.efer & EFER_LME) != (efer & EFER_LME)) {
-		printk(KERN_DEBUG "set_efer: #GP, change LME while paging\n");
 		kvm_inject_gp(vcpu, 0);
 		return;
 	}
@@ -667,7 +642,6 @@ static void set_efer(struct kvm_vcpu *vcpu, u64 efer)
 
 		feat = kvm_find_cpuid_entry(vcpu, 0x80000001, 0);
 		if (!feat || !(feat->edx & bit(X86_FEATURE_FXSR_OPT))) {
-			printk(KERN_DEBUG "set_efer: #GP, enable FFXSR w/o CPUID capability\n");
 			kvm_inject_gp(vcpu, 0);
 			return;
 		}
@@ -678,7 +652,6 @@ static void set_efer(struct kvm_vcpu *vcpu, u64 efer)
 
 		feat = kvm_find_cpuid_entry(vcpu, 0x80000001, 0);
 		if (!feat || !(feat->ecx & bit(X86_FEATURE_SVM))) {
-			printk(KERN_DEBUG "set_efer: #GP, enable SVM w/o SVM\n");
 			kvm_inject_gp(vcpu, 0);
 			return;
 		}
@@ -967,9 +940,13 @@ static int set_msr_mce(struct kvm_vcpu *vcpu, u32 msr, u64 data)
 		if (msr >= MSR_IA32_MC0_CTL &&
 		    msr < MSR_IA32_MC0_CTL + 4 * bank_num) {
 			u32 offset = msr - MSR_IA32_MC0_CTL;
-			/* only 0 or all 1s can be written to IA32_MCi_CTL */
+			/* only 0 or all 1s can be written to IA32_MCi_CTL
+			 * some Linux kernels though clear bit 10 in bank 4 to
+			 * workaround a BIOS/GART TBL issue on AMD K8s, ignore
+			 * this to avoid an uncatched #GP in the guest
+			 */
 			if ((offset & 0x3) == 0 &&
-			    data != 0 && data != ~(u64)0)
+			    data != 0 && (data | (1 << 10)) != ~(u64)0)
 				return -1;
 			vcpu->arch.mce_banks[offset] = data;
 			break;
@@ -2635,8 +2612,9 @@ static int kvm_vm_ioctl_reinject(struct kvm *kvm,
 int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm,
 				      struct kvm_dirty_log *log)
 {
-	int r, n, i;
+	int r, i;
 	struct kvm_memory_slot *memslot;
+	unsigned long n;
 	unsigned long is_dirty = 0;
 	unsigned long *dirty_bitmap = NULL;
 
@@ -2651,7 +2629,7 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm,
 	if (!memslot->dirty_bitmap)
 		goto out;
 
-	n = ALIGN(memslot->npages, BITS_PER_LONG) / 8;
+	n = kvm_dirty_bitmap_bytes(memslot);
 
 	r = -ENOMEM;
 	dirty_bitmap = vmalloc(n);
@@ -4483,7 +4461,9 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 		kvm_set_cr8(vcpu, kvm_run->cr8);
 
 	if (vcpu->arch.pio.cur_count) {
+		vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
 		r = complete_pio(vcpu);
+		srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
 		if (r)
 			goto out;
 	}
@@ -5146,6 +5126,7 @@ int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int reason)
 	int ret = 0;
 	u32 old_tss_base = get_segment_base(vcpu, VCPU_SREG_TR);
 	u16 old_tss_sel = get_segment_selector(vcpu, VCPU_SREG_TR);
+	u32 desc_limit;
 
 	old_tss_base = kvm_mmu_gva_to_gpa_write(vcpu, old_tss_base, NULL);
 
@@ -5168,7 +5149,10 @@ int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int reason)
 		}
 	}
 
-	if (!nseg_desc.p || get_desc_limit(&nseg_desc) < 0x67) {
+	desc_limit = get_desc_limit(&nseg_desc);
+	if (!nseg_desc.p ||
+	    ((desc_limit < 0x67 && (nseg_desc.type & 8)) ||
+	     desc_limit < 0x2b)) {
 		kvm_queue_exception_e(vcpu, TS_VECTOR, tss_selector & 0xfffc);
 		return 1;
 	}
diff --git a/arch/x86/lib/rwsem_64.S b/arch/x86/lib/rwsem_64.S
index 15acecf0d7a..41fcf00e49d 100644
--- a/arch/x86/lib/rwsem_64.S
+++ b/arch/x86/lib/rwsem_64.S
@@ -60,7 +60,7 @@ ENTRY(call_rwsem_down_write_failed)
 	ENDPROC(call_rwsem_down_write_failed)
 
 ENTRY(call_rwsem_wake)
-	decw %dx    /* do nothing if still outstanding active readers */
+	decl %edx	/* do nothing if still outstanding active readers */
 	jnz 1f
 	save_common_regs
 	movq %rax,%rdi
diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c
index 5eb1ba74a3a..12e4d2d3c11 100644
--- a/arch/x86/mm/ioremap.c
+++ b/arch/x86/mm/ioremap.c
@@ -448,6 +448,20 @@ static inline void __init early_clear_fixmap(enum fixed_addresses idx)
 static void __iomem *prev_map[FIX_BTMAPS_SLOTS] __initdata;
 static unsigned long prev_size[FIX_BTMAPS_SLOTS] __initdata;
 
+void __init fixup_early_ioremap(void)
+{
+	int i;
+
+	for (i = 0; i < FIX_BTMAPS_SLOTS; i++) {
+		if (prev_map[i]) {
+			WARN_ON(1);
+			break;
+		}
+	}
+
+	early_ioremap_init();
+}
+
 static int __init check_early_ioremap_leak(void)
 {
 	int count = 0;
diff --git a/arch/x86/mm/pgtable_32.c b/arch/x86/mm/pgtable_32.c
index 1a8faf09afe..792854003ed 100644
--- a/arch/x86/mm/pgtable_32.c
+++ b/arch/x86/mm/pgtable_32.c
@@ -18,6 +18,7 @@
 #include <asm/e820.h>
 #include <asm/tlb.h>
 #include <asm/tlbflush.h>
+#include <asm/io.h>
 
 unsigned int __VMALLOC_RESERVE = 128 << 20;
 
@@ -128,6 +129,7 @@ static int __init parse_reservetop(char *arg)
 
 	address = memparse(arg, &arg);
 	reserve_top_address(address);
+	fixup_early_ioremap();
 	return 0;
 }
 early_param("reservetop", parse_reservetop);
diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c
index c7b1ebfb7da..31930fd30ea 100644
--- a/arch/x86/pci/acpi.c
+++ b/arch/x86/pci/acpi.c
@@ -66,14 +66,44 @@ resource_to_addr(struct acpi_resource *resource,
 			struct acpi_resource_address64 *addr)
 {
 	acpi_status status;
-
-	status = acpi_resource_to_address64(resource, addr);
-	if (ACPI_SUCCESS(status) &&
-	    (addr->resource_type == ACPI_MEMORY_RANGE ||
-	    addr->resource_type == ACPI_IO_RANGE) &&
-	    addr->address_length > 0 &&
-	    addr->producer_consumer == ACPI_PRODUCER) {
+	struct acpi_resource_memory24 *memory24;
+	struct acpi_resource_memory32 *memory32;
+	struct acpi_resource_fixed_memory32 *fixed_memory32;
+
+	memset(addr, 0, sizeof(*addr));
+	switch (resource->type) {
+	case ACPI_RESOURCE_TYPE_MEMORY24:
+		memory24 = &resource->data.memory24;
+		addr->resource_type = ACPI_MEMORY_RANGE;
+		addr->minimum = memory24->minimum;
+		addr->address_length = memory24->address_length;
+		addr->maximum = addr->minimum + addr->address_length - 1;
+		return AE_OK;
+	case ACPI_RESOURCE_TYPE_MEMORY32:
+		memory32 = &resource->data.memory32;
+		addr->resource_type = ACPI_MEMORY_RANGE;
+		addr->minimum = memory32->minimum;
+		addr->address_length = memory32->address_length;
+		addr->maximum = addr->minimum + addr->address_length - 1;
 		return AE_OK;
+	case ACPI_RESOURCE_TYPE_FIXED_MEMORY32:
+		fixed_memory32 = &resource->data.fixed_memory32;
+		addr->resource_type = ACPI_MEMORY_RANGE;
+		addr->minimum = fixed_memory32->address;
+		addr->address_length = fixed_memory32->address_length;
+		addr->maximum = addr->minimum + addr->address_length - 1;
+		return AE_OK;
+	case ACPI_RESOURCE_TYPE_ADDRESS16:
+	case ACPI_RESOURCE_TYPE_ADDRESS32:
+	case ACPI_RESOURCE_TYPE_ADDRESS64:
+		status = acpi_resource_to_address64(resource, addr);
+		if (ACPI_SUCCESS(status) &&
+		    (addr->resource_type == ACPI_MEMORY_RANGE ||
+		    addr->resource_type == ACPI_IO_RANGE) &&
+		    addr->address_length > 0) {
+			return AE_OK;
+		}
+		break;
 	}
 	return AE_ERROR;
 }
@@ -91,30 +121,6 @@ count_resource(struct acpi_resource *acpi_res, void *data)
 	return AE_OK;
 }
 
-static void
-align_resource(struct acpi_device *bridge, struct resource *res)
-{
-	int align = (res->flags & IORESOURCE_MEM) ? 16 : 4;
-
-	/*
-	 * Host bridge windows are not BARs, but the decoders on the PCI side
-	 * that claim this address space have starting alignment and length
-	 * constraints, so fix any obvious BIOS goofs.
-	 */
-	if (!IS_ALIGNED(res->start, align)) {
-		dev_printk(KERN_DEBUG, &bridge->dev,
-			   "host bridge window %pR invalid; "
-			   "aligning start to %d-byte boundary\n", res, align);
-		res->start &= ~(align - 1);
-	}
-	if (!IS_ALIGNED(res->end + 1, align)) {
-		dev_printk(KERN_DEBUG, &bridge->dev,
-			   "host bridge window %pR invalid; "
-			   "aligning end to %d-byte boundary\n", res, align);
-		res->end = ALIGN(res->end, align) - 1;
-	}
-}
-
 static acpi_status
 setup_resource(struct acpi_resource *acpi_res, void *data)
 {
@@ -124,7 +130,7 @@ setup_resource(struct acpi_resource *acpi_res, void *data)
 	acpi_status status;
 	unsigned long flags;
 	struct resource *root, *conflict;
-	u64 start, end, max_len;
+	u64 start, end;
 
 	status = resource_to_addr(acpi_res, &addr);
 	if (!ACPI_SUCCESS(status))
@@ -141,19 +147,8 @@ setup_resource(struct acpi_resource *acpi_res, void *data)
 	} else
 		return AE_OK;
 
-	max_len = addr.maximum - addr.minimum + 1;
-	if (addr.address_length > max_len) {
-		dev_printk(KERN_DEBUG, &info->bridge->dev,
-			   "host bridge window length %#llx doesn't fit in "
-			   "%#llx-%#llx, trimming\n",
-			   (unsigned long long) addr.address_length,
-			   (unsigned long long) addr.minimum,
-			   (unsigned long long) addr.maximum);
-		addr.address_length = max_len;
-	}
-
 	start = addr.minimum + addr.translation_offset;
-	end = start + addr.address_length - 1;
+	end = addr.maximum + addr.translation_offset;
 
 	res = &info->res[info->res_num];
 	res->name = info->name;
@@ -161,7 +156,6 @@ setup_resource(struct acpi_resource *acpi_res, void *data)
 	res->start = start;
 	res->end = end;
 	res->child = NULL;
-	align_resource(info->bridge, res);
 
 	if (!pci_use_crs) {
 		dev_printk(KERN_DEBUG, &info->bridge->dev,
diff --git a/arch/x86/pci/i386.c b/arch/x86/pci/i386.c
index 46fd43f7910..97da2ba9344 100644
--- a/arch/x86/pci/i386.c
+++ b/arch/x86/pci/i386.c
@@ -72,6 +72,9 @@ pcibios_align_resource(void *data, const struct resource *res,
 			return start;
 		if (start & 0x300)
 			start = (start + 0x3ff) & ~0x3ff;
+	} else if (res->flags & IORESOURCE_MEM) {
+		if (start < BIOS_END)
+			start = BIOS_END;
 	}
 	return start;
 }