Merge branch 'kvm-updates/3.2' of git://git.kernel.org/pub/scm/virt/kvm/kvm

* 'kvm-updates/3.2' of git://git.kernel.org/pub/scm/virt/kvm/kvm:
  KVM: PPC: e500: include linux/export.h
  KVM: PPC: fix kvmppc_start_thread() for CONFIG_SMP=N
  KVM: PPC: protect use of kvmppc_h_pr
  KVM: PPC: move compute_tlbie_rb to book3s_64 common header
  KVM: Don't automatically expose the TSC deadline timer in cpuid
  KVM: Device assignment permission checks
  KVM: Remove ability to assign a device without iommu support
  KVM: x86: Prevent starting PIT timers in the absence of irqchip support

Documentation/virtual/kvm/api.txt

@@ -1100,6 +1100,15 @@ emulate them efficiently. The fields in each entry are defined as follows:
    eax, ebx, ecx, edx: the values returned by the cpuid instruction for
          this function/index combination
 
+The TSC deadline timer feature (CPUID leaf 1, ecx[24]) is always returned
+as false, since the feature depends on KVM_CREATE_IRQCHIP for local APIC
+support.  Instead it is reported via
+
+  ioctl(KVM_CHECK_EXTENSION, KVM_CAP_TSC_DEADLINE_TIMER)
+
+if that returns true and you use KVM_CREATE_IRQCHIP, or if you emulate the
+feature in userspace, then you can enable the feature for KVM_SET_CPUID2.
+
 4.47 KVM_PPC_GET_PVINFO
 
 Capability: KVM_CAP_PPC_GET_PVINFO
@@ -1151,6 +1160,13 @@ following flags are specified:
 /* Depends on KVM_CAP_IOMMU */
 #define KVM_DEV_ASSIGN_ENABLE_IOMMU	(1 << 0)
 
+The KVM_DEV_ASSIGN_ENABLE_IOMMU flag is a mandatory option to ensure
+isolation of the device.  Usages not specifying this flag are deprecated.
+
+Only PCI header type 0 devices with PCI BAR resources are supported by
+device assignment.  The user requesting this ioctl must have read/write
+access to the PCI sysfs resource files associated with the device.
+
 4.49 KVM_DEASSIGN_PCI_DEVICE
 
 Capability: KVM_CAP_DEVICE_DEASSIGNMENT

arch/powerpc/include/asm/kvm_book3s.h

@@ -381,39 +381,6 @@ static inline bool kvmppc_critical_section(struct kvm_vcpu *vcpu)
 }
 #endif
 
-static inline unsigned long compute_tlbie_rb(unsigned long v, unsigned long r,
-					     unsigned long pte_index)
-{
-	unsigned long rb, va_low;
-
-	rb = (v & ~0x7fUL) << 16;		/* AVA field */
-	va_low = pte_index >> 3;
-	if (v & HPTE_V_SECONDARY)
-		va_low = ~va_low;
-	/* xor vsid from AVA */
-	if (!(v & HPTE_V_1TB_SEG))
-		va_low ^= v >> 12;
-	else
-		va_low ^= v >> 24;
-	va_low &= 0x7ff;
-	if (v & HPTE_V_LARGE) {
-		rb |= 1;			/* L field */
-		if (cpu_has_feature(CPU_FTR_ARCH_206) &&
-		    (r & 0xff000)) {
-			/* non-16MB large page, must be 64k */
-			/* (masks depend on page size) */
-			rb |= 0x1000;		/* page encoding in LP field */
-			rb |= (va_low & 0x7f) << 16; /* 7b of VA in AVA/LP field */
-			rb |= (va_low & 0xfe);	/* AVAL field (P7 doesn't seem to care) */
-		}
-	} else {
-		/* 4kB page */
-		rb |= (va_low & 0x7ff) << 12;	/* remaining 11b of VA */
-	}
-	rb |= (v >> 54) & 0x300;		/* B field */
-	return rb;
-}
-
 /* Magic register values loaded into r3 and r4 before the 'sc' assembly
  * instruction for the OSI hypercalls */
 #define OSI_SC_MAGIC_R3			0x113724FA

arch/powerpc/include/asm/kvm_book3s_64.h

@@ -29,4 +29,37 @@ static inline struct kvmppc_book3s_shadow_vcpu *to_svcpu(struct kvm_vcpu *vcpu)
 
 #define SPAPR_TCE_SHIFT		12
 
+static inline unsigned long compute_tlbie_rb(unsigned long v, unsigned long r,
+					     unsigned long pte_index)
+{
+	unsigned long rb, va_low;
+
+	rb = (v & ~0x7fUL) << 16;		/* AVA field */
+	va_low = pte_index >> 3;
+	if (v & HPTE_V_SECONDARY)
+		va_low = ~va_low;
+	/* xor vsid from AVA */
+	if (!(v & HPTE_V_1TB_SEG))
+		va_low ^= v >> 12;
+	else
+		va_low ^= v >> 24;
+	va_low &= 0x7ff;
+	if (v & HPTE_V_LARGE) {
+		rb |= 1;			/* L field */
+		if (cpu_has_feature(CPU_FTR_ARCH_206) &&
+		    (r & 0xff000)) {
+			/* non-16MB large page, must be 64k */
+			/* (masks depend on page size) */
+			rb |= 0x1000;		/* page encoding in LP field */
+			rb |= (va_low & 0x7f) << 16; /* 7b of VA in AVA/LP field */
+			rb |= (va_low & 0xfe);	/* AVAL field (P7 doesn't seem to care) */
+		}
+	} else {
+		/* 4kB page */
+		rb |= (va_low & 0x7ff) << 12;	/* remaining 11b of VA */
+	}
+	rb |= (v >> 54) & 0x300;		/* B field */
+	return rb;
+}
+
 #endif /* __ASM_KVM_BOOK3S_64_H__ */

arch/powerpc/kvm/book3s_hv.c

@@ -538,7 +538,7 @@ static void kvmppc_start_thread(struct kvm_vcpu *vcpu)
 	tpaca->kvm_hstate.napping = 0;
 	vcpu->cpu = vc->pcpu;
 	smp_wmb();
-#ifdef CONFIG_PPC_ICP_NATIVE
+#if defined(CONFIG_PPC_ICP_NATIVE) && defined(CONFIG_SMP)
 	if (vcpu->arch.ptid) {
 		tpaca->cpu_start = 0x80;
 		wmb();

arch/powerpc/kvm/book3s_pr.c

@@ -658,10 +658,12 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 			ulong cmd = kvmppc_get_gpr(vcpu, 3);
 			int i;
 
+#ifdef CONFIG_KVM_BOOK3S_64_PR
 			if (kvmppc_h_pr(vcpu, cmd) == EMULATE_DONE) {
 				r = RESUME_GUEST;
 				break;
 			}
+#endif
 
 			run->papr_hcall.nr = cmd;
 			for (i = 0; i < 9; ++i) {

arch/powerpc/kvm/e500.c

@@ -15,6 +15,7 @@
 #include <linux/kvm_host.h>
 #include <linux/slab.h>
 #include <linux/err.h>
+#include <linux/export.h>
 
 #include <asm/reg.h>
 #include <asm/cputable.h>

arch/x86/kvm/i8254.c

@@ -338,11 +338,15 @@ static enum hrtimer_restart pit_timer_fn(struct hrtimer *data)
 		return HRTIMER_NORESTART;
 }
 
-static void create_pit_timer(struct kvm_kpit_state *ps, u32 val, int is_period)
+static void create_pit_timer(struct kvm *kvm, u32 val, int is_period)
 {
+	struct kvm_kpit_state *ps = &kvm->arch.vpit->pit_state;
 	struct kvm_timer *pt = &ps->pit_timer;
 	s64 interval;
 
+	if (!irqchip_in_kernel(kvm))
+		return;
+
 	interval = muldiv64(val, NSEC_PER_SEC, KVM_PIT_FREQ);
 
 	pr_debug("create pit timer, interval is %llu nsec\n", interval);
@@ -394,13 +398,13 @@ static void pit_load_count(struct kvm *kvm, int channel, u32 val)
         /* FIXME: enhance mode 4 precision */
 	case 4:
 		if (!(ps->flags & KVM_PIT_FLAGS_HPET_LEGACY)) {
-			create_pit_timer(ps, val, 0);
+			create_pit_timer(kvm, val, 0);
 		}
 		break;
 	case 2:
 	case 3:
 		if (!(ps->flags & KVM_PIT_FLAGS_HPET_LEGACY)){
-			create_pit_timer(ps, val, 1);
+			create_pit_timer(kvm, val, 1);
 		}
 		break;
 	default:

arch/x86/kvm/x86.c

@@ -602,7 +602,6 @@ static void update_cpuid(struct kvm_vcpu *vcpu)
 {
 	struct kvm_cpuid_entry2 *best;
 	struct kvm_lapic *apic = vcpu->arch.apic;
-	u32 timer_mode_mask;
 
 	best = kvm_find_cpuid_entry(vcpu, 1, 0);
 	if (!best)
@@ -615,15 +614,12 @@ static void update_cpuid(struct kvm_vcpu *vcpu)
 			best->ecx |= bit(X86_FEATURE_OSXSAVE);
 	}
 
-	if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL &&
-		best->function == 0x1) {
-		best->ecx |= bit(X86_FEATURE_TSC_DEADLINE_TIMER);
-		timer_mode_mask = 3 << 17;
-	} else
-		timer_mode_mask = 1 << 17;
-
-	if (apic)
-		apic->lapic_timer.timer_mode_mask = timer_mode_mask;
+	if (apic) {
+		if (best->ecx & bit(X86_FEATURE_TSC_DEADLINE_TIMER))
+			apic->lapic_timer.timer_mode_mask = 3 << 17;
+		else
+			apic->lapic_timer.timer_mode_mask = 1 << 17;
+	}
 }
 
 int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
@@ -2135,6 +2131,9 @@ int kvm_dev_ioctl_check_extension(long ext)
 	case KVM_CAP_TSC_CONTROL:
 		r = kvm_has_tsc_control;
 		break;
+	case KVM_CAP_TSC_DEADLINE_TIMER:
+		r = boot_cpu_has(X86_FEATURE_TSC_DEADLINE_TIMER);
+		break;
 	default:
 		r = 0;
 		break;

include/linux/kvm.h

@@ -557,6 +557,7 @@ struct kvm_ppc_pvinfo {
 #define KVM_CAP_MAX_VCPUS 66       /* returns max vcpus per vm */
 #define KVM_CAP_PPC_PAPR 68
 #define KVM_CAP_S390_GMAP 71
+#define KVM_CAP_TSC_DEADLINE_TIMER 72
 
 #ifdef KVM_CAP_IRQ_ROUTING
 

virt/kvm/assigned-dev.c

@@ -17,6 +17,8 @@
 #include <linux/pci.h>
 #include <linux/interrupt.h>
 #include <linux/slab.h>
+#include <linux/namei.h>
+#include <linux/fs.h>
 #include "irq.h"
 
 static struct kvm_assigned_dev_kernel *kvm_find_assigned_dev(struct list_head *head,
@@ -480,12 +482,76 @@ static int kvm_vm_ioctl_deassign_dev_irq(struct kvm *kvm,
 	return r;
 }
 
+/*
+ * We want to test whether the caller has been granted permissions to
+ * use this device.  To be able to configure and control the device,
+ * the user needs access to PCI configuration space and BAR resources.
+ * These are accessed through PCI sysfs.  PCI config space is often
+ * passed to the process calling this ioctl via file descriptor, so we
+ * can't rely on access to that file.  We can check for permissions
+ * on each of the BAR resource files, which is a pretty clear
+ * indicator that the user has been granted access to the device.
+ */
+static int probe_sysfs_permissions(struct pci_dev *dev)
+{
+#ifdef CONFIG_SYSFS
+	int i;
+	bool bar_found = false;
+
+	for (i = PCI_STD_RESOURCES; i <= PCI_STD_RESOURCE_END; i++) {
+		char *kpath, *syspath;
+		struct path path;
+		struct inode *inode;
+		int r;
+
+		if (!pci_resource_len(dev, i))
+			continue;
+
+		kpath = kobject_get_path(&dev->dev.kobj, GFP_KERNEL);
+		if (!kpath)
+			return -ENOMEM;
+
+		/* Per sysfs-rules, sysfs is always at /sys */
+		syspath = kasprintf(GFP_KERNEL, "/sys%s/resource%d", kpath, i);
+		kfree(kpath);
+		if (!syspath)
+			return -ENOMEM;
+
+		r = kern_path(syspath, LOOKUP_FOLLOW, &path);
+		kfree(syspath);
+		if (r)
+			return r;
+
+		inode = path.dentry->d_inode;
+
+		r = inode_permission(inode, MAY_READ | MAY_WRITE | MAY_ACCESS);
+		path_put(&path);
+		if (r)
+			return r;
+
+		bar_found = true;
+	}
+
+	/* If no resources, probably something special */
+	if (!bar_found)
+		return -EPERM;
+
+	return 0;
+#else
+	return -EINVAL; /* No way to control the device without sysfs */
+#endif
+}
+
 static int kvm_vm_ioctl_assign_device(struct kvm *kvm,
 				      struct kvm_assigned_pci_dev *assigned_dev)
 {
 	int r = 0, idx;
 	struct kvm_assigned_dev_kernel *match;
 	struct pci_dev *dev;
+	u8 header_type;
+
+	if (!(assigned_dev->flags & KVM_DEV_ASSIGN_ENABLE_IOMMU))
+		return -EINVAL;
 
 	mutex_lock(&kvm->lock);
 	idx = srcu_read_lock(&kvm->srcu);
@@ -513,6 +579,18 @@ static int kvm_vm_ioctl_assign_device(struct kvm *kvm,
 		r = -EINVAL;
 		goto out_free;
 	}
+
+	/* Don't allow bridges to be assigned */
+	pci_read_config_byte(dev, PCI_HEADER_TYPE, &header_type);
+	if ((header_type & PCI_HEADER_TYPE) != PCI_HEADER_TYPE_NORMAL) {
+		r = -EPERM;
+		goto out_put;
+	}
+
+	r = probe_sysfs_permissions(dev);
+	if (r)
+		goto out_put;
+
 	if (pci_enable_device(dev)) {
 		printk(KERN_INFO "%s: Could not enable PCI device\n", __func__);
 		r = -EBUSY;
@@ -544,7 +622,6 @@ static int kvm_vm_ioctl_assign_device(struct kvm *kvm,
 
 	list_add(&match->list, &kvm->arch.assigned_dev_head);
 
-	if (assigned_dev->flags & KVM_DEV_ASSIGN_ENABLE_IOMMU) {
 	if (!kvm->arch.iommu_domain) {
 		r = kvm_iommu_map_guest(kvm);
 		if (r)
@@ -553,7 +630,6 @@ static int kvm_vm_ioctl_assign_device(struct kvm *kvm,
 	r = kvm_assign_device(kvm, match);
 	if (r)
 		goto out_list_del;
-	}
 
 out:
 	srcu_read_unlock(&kvm->srcu, idx);
@@ -593,7 +669,6 @@ static int kvm_vm_ioctl_deassign_device(struct kvm *kvm,
 		goto out;
 	}
 
-	if (match->flags & KVM_DEV_ASSIGN_ENABLE_IOMMU)
 	kvm_deassign_device(kvm, match);
 
 	kvm_free_assigned_device(kvm, match);