Merge branch 'kvm-updates/2.6.37' of git://git.kernel.org/pub/scm/virt/kvm/kvm

* 'kvm-updates/2.6.37' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (321 commits)
  KVM: Drop CONFIG_DMAR dependency around kvm_iommu_map_pages
  KVM: Fix signature of kvm_iommu_map_pages stub
  KVM: MCE: Send SRAR SIGBUS directly
  KVM: MCE: Add MCG_SER_P into KVM_MCE_CAP_SUPPORTED
  KVM: fix typo in copyright notice
  KVM: Disable interrupts around get_kernel_ns()
  KVM: MMU: Avoid sign extension in mmu_alloc_direct_roots() pae root address
  KVM: MMU: move access code parsing to FNAME(walk_addr) function
  KVM: MMU: audit: check whether have unsync sps after root sync
  KVM: MMU: audit: introduce audit_printk to cleanup audit code
  KVM: MMU: audit: unregister audit tracepoints before module unloaded
  KVM: MMU: audit: fix vcpu's spte walking
  KVM: MMU: set access bit for direct mapping
  KVM: MMU: cleanup for error mask set while walk guest page table
  KVM: MMU: update 'root_hpa' out of loop in PAE shadow path
  KVM: x86 emulator: Eliminate compilation warning in x86_decode_insn()
  KVM: x86: Fix constant type in kvm_get_time_scale
  KVM: VMX: Add AX to list of registers clobbered by guest switch
  KVM guest: Move a printk that's using the clock before it's ready
  KVM: x86: TSC catchup mode
  ...

virt/kvm/irq_comm.c

@@ -17,7 +17,7 @@
  * Authors:
  *   Yaozu (Eddie) Dong <Eddie.dong@intel.com>
  *
- * Copyright 2010 Red Hat, Inc. and/or its affilates.
+ * Copyright 2010 Red Hat, Inc. and/or its affiliates.
  */
 
 #include <linux/kvm_host.h>

virt/kvm/kvm_main.c

@@ -5,7 +5,7 @@
  * machines without emulation or binary translation.
  *
  * Copyright (C) 2006 Qumranet, Inc.
- * Copyright 2010 Red Hat, Inc. and/or its affilates.
+ * Copyright 2010 Red Hat, Inc. and/or its affiliates.
  *
  * Authors:
  *   Avi Kivity   <avi@qumranet.com>
@@ -705,14 +705,12 @@ skip_lpage:
 	if (r)
 		goto out_free;
 
-#ifdef CONFIG_DMAR
 	/* map the pages in iommu page table */
 	if (npages) {
 		r = kvm_iommu_map_pages(kvm, &new);
 		if (r)
 			goto out_free;
 	}
-#endif
 
 	r = -ENOMEM;
 	slots = kzalloc(sizeof(struct kvm_memslots), GFP_KERNEL);
@@ -927,35 +925,46 @@ int memslot_id(struct kvm *kvm, gfn_t gfn)
 	return memslot - slots->memslots;
 }
 
-static unsigned long gfn_to_hva_memslot(struct kvm_memory_slot *slot, gfn_t gfn)
-{
-	return slot->userspace_addr + (gfn - slot->base_gfn) * PAGE_SIZE;
-}
-
-unsigned long gfn_to_hva(struct kvm *kvm, gfn_t gfn)
+static unsigned long gfn_to_hva_many(struct kvm *kvm, gfn_t gfn,
+				     gfn_t *nr_pages)
 {
 	struct kvm_memory_slot *slot;
 
 	slot = gfn_to_memslot(kvm, gfn);
 	if (!slot || slot->flags & KVM_MEMSLOT_INVALID)
 		return bad_hva();
+
+	if (nr_pages)
+		*nr_pages = slot->npages - (gfn - slot->base_gfn);
+
 	return gfn_to_hva_memslot(slot, gfn);
 }
+
+unsigned long gfn_to_hva(struct kvm *kvm, gfn_t gfn)
+{
+	return gfn_to_hva_many(kvm, gfn, NULL);
+}
 EXPORT_SYMBOL_GPL(gfn_to_hva);
 
-static pfn_t hva_to_pfn(struct kvm *kvm, unsigned long addr)
+static pfn_t hva_to_pfn(struct kvm *kvm, unsigned long addr, bool atomic)
 {
 	struct page *page[1];
 	int npages;
 	pfn_t pfn;
 
-	might_sleep();
-
-	npages = get_user_pages_fast(addr, 1, 1, page);
+	if (atomic)
+		npages = __get_user_pages_fast(addr, 1, 1, page);
+	else {
+		might_sleep();
+		npages = get_user_pages_fast(addr, 1, 1, page);
+	}
 
 	if (unlikely(npages != 1)) {
 		struct vm_area_struct *vma;
 
+		if (atomic)
+			goto return_fault_page;
+
 		down_read(&current->mm->mmap_sem);
 		if (is_hwpoison_address(addr)) {
 			up_read(&current->mm->mmap_sem);
@@ -968,6 +977,7 @@ static pfn_t hva_to_pfn(struct kvm *kvm, unsigned long addr)
 		if (vma == NULL || addr < vma->vm_start ||
 		    !(vma->vm_flags & VM_PFNMAP)) {
 			up_read(&current->mm->mmap_sem);
+return_fault_page:
 			get_page(fault_page);
 			return page_to_pfn(fault_page);
 		}
@@ -981,7 +991,13 @@ static pfn_t hva_to_pfn(struct kvm *kvm, unsigned long addr)
 	return pfn;
 }
 
-pfn_t gfn_to_pfn(struct kvm *kvm, gfn_t gfn)
+pfn_t hva_to_pfn_atomic(struct kvm *kvm, unsigned long addr)
+{
+	return hva_to_pfn(kvm, addr, true);
+}
+EXPORT_SYMBOL_GPL(hva_to_pfn_atomic);
+
+static pfn_t __gfn_to_pfn(struct kvm *kvm, gfn_t gfn, bool atomic)
 {
 	unsigned long addr;
 
@@ -991,7 +1007,18 @@ pfn_t gfn_to_pfn(struct kvm *kvm, gfn_t gfn)
 		return page_to_pfn(bad_page);
 	}
 
-	return hva_to_pfn(kvm, addr);
+	return hva_to_pfn(kvm, addr, atomic);
+}
+
+pfn_t gfn_to_pfn_atomic(struct kvm *kvm, gfn_t gfn)
+{
+	return __gfn_to_pfn(kvm, gfn, true);
+}
+EXPORT_SYMBOL_GPL(gfn_to_pfn_atomic);
+
+pfn_t gfn_to_pfn(struct kvm *kvm, gfn_t gfn)
+{
+	return __gfn_to_pfn(kvm, gfn, false);
 }
 EXPORT_SYMBOL_GPL(gfn_to_pfn);
 
@@ -999,9 +1026,26 @@ pfn_t gfn_to_pfn_memslot(struct kvm *kvm,
 			 struct kvm_memory_slot *slot, gfn_t gfn)
 {
 	unsigned long addr = gfn_to_hva_memslot(slot, gfn);
-	return hva_to_pfn(kvm, addr);
+	return hva_to_pfn(kvm, addr, false);
 }
 
+int gfn_to_page_many_atomic(struct kvm *kvm, gfn_t gfn, struct page **pages,
+								  int nr_pages)
+{
+	unsigned long addr;
+	gfn_t entry;
+
+	addr = gfn_to_hva_many(kvm, gfn, &entry);
+	if (kvm_is_error_hva(addr))
+		return -1;
+
+	if (entry < nr_pages)
+		return 0;
+
+	return __get_user_pages_fast(addr, nr_pages, 1, pages);
+}
+EXPORT_SYMBOL_GPL(gfn_to_page_many_atomic);
+
 struct page *gfn_to_page(struct kvm *kvm, gfn_t gfn)
 {
 	pfn_t pfn;
@@ -1964,7 +2008,9 @@ static int kvm_cpu_hotplug(struct notifier_block *notifier, unsigned long val,
 	case CPU_STARTING:
 		printk(KERN_INFO "kvm: enabling virtualization on CPU%d\n",
 		       cpu);
+		spin_lock(&kvm_lock);
 		hardware_enable(NULL);
+		spin_unlock(&kvm_lock);
 		break;
 	}
 	return NOTIFY_OK;
@@ -1977,7 +2023,7 @@ asmlinkage void kvm_handle_fault_on_reboot(void)
 		/* spin while reset goes on */
 		local_irq_enable();
 		while (true)
-			;
+			cpu_relax();
 	}
 	/* Fault while not rebooting.  We want the trace. */
 	BUG();
@@ -2171,8 +2217,10 @@ static int kvm_suspend(struct sys_device *dev, pm_message_t state)
 
 static int kvm_resume(struct sys_device *dev)
 {
-	if (kvm_usage_count)
+	if (kvm_usage_count) {
+		WARN_ON(spin_is_locked(&kvm_lock));
 		hardware_enable(NULL);
+	}
 	return 0;
 }