From 423873736b78f549fbfa2f715f2e4de7e6c5e1e9 Mon Sep 17 00:00:00 2001 From: Alex Williamson Date: Tue, 20 Dec 2011 21:59:03 -0700 Subject: KVM: Remove ability to assign a device without iommu support This option has no users and it exposes a security hole that we can allow devices to be assigned without iommu protection. Make KVM_DEV_ASSIGN_ENABLE_IOMMU a mandatory option. Signed-off-by: Alex Williamson Signed-off-by: Marcelo Tosatti --- Documentation/virtual/kvm/api.txt | 3 +++ 1 file changed, 3 insertions(+) (limited to 'Documentation') diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt index 7945b0bd35e2..ee2c96b3ba5a 100644 --- a/Documentation/virtual/kvm/api.txt +++ b/Documentation/virtual/kvm/api.txt @@ -1151,6 +1151,9 @@ 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. + 4.49 KVM_DEASSIGN_PCI_DEVICE Capability: KVM_CAP_DEVICE_DEASSIGNMENT -- cgit v1.2.3 From 3d27e23b17010c668db311140b17bbbb70c78fb9 Mon Sep 17 00:00:00 2001 From: Alex Williamson Date: Tue, 20 Dec 2011 21:59:09 -0700 Subject: KVM: Device assignment permission checks Only allow KVM device assignment to attach to devices which: - Are not bridges - Have BAR resources (assume others are special devices) - The user has permissions to use Assigning a bridge is a configuration error, it's not supported, and typically doesn't result in the behavior the user is expecting anyway. Devices without BAR resources are typically chipset components that also don't have host drivers. We don't want users to hold such devices captive or cause system problems by fencing them off into an iommu domain. We determine "permission to use" by testing whether the user has access to the PCI sysfs resource files. By default a normal user will not have access to these files, so it provides a good indication that an administration agent has granted the user access to the device. [Yang Bai: add missing #include] [avi: fix comment style] Signed-off-by: Alex Williamson Signed-off-by: Yang Bai Signed-off-by: Marcelo Tosatti --- Documentation/virtual/kvm/api.txt | 4 +++ virt/kvm/assigned-dev.c | 75 +++++++++++++++++++++++++++++++++++++++ 2 files changed, 79 insertions(+) (limited to 'Documentation') diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt index ee2c96b3ba5a..4df9af4f6132 100644 --- a/Documentation/virtual/kvm/api.txt +++ b/Documentation/virtual/kvm/api.txt @@ -1154,6 +1154,10 @@ following flags are specified: 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 diff --git a/virt/kvm/assigned-dev.c b/virt/kvm/assigned-dev.c index a251a28f79c7..758e3b36d4cf 100644 --- a/virt/kvm/assigned-dev.c +++ b/virt/kvm/assigned-dev.c @@ -17,6 +17,8 @@ #include #include #include +#include +#include #include "irq.h" static struct kvm_assigned_dev_kernel *kvm_find_assigned_dev(struct list_head *head, @@ -480,12 +482,73 @@ out: 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; @@ -516,6 +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; -- cgit v1.2.3 From 4d25a066b69fb749a39d0d4c610689dd765a0b0e Mon Sep 17 00:00:00 2001 From: Jan Kiszka Date: Wed, 21 Dec 2011 12:28:29 +0100 Subject: KVM: Don't automatically expose the TSC deadline timer in cpuid Unlike all of the other cpuid bits, the TSC deadline timer bit is set unconditionally, regardless of what userspace wants. This is broken in several ways: - if userspace doesn't use KVM_CREATE_IRQCHIP, and doesn't emulate the TSC deadline timer feature, a guest that uses the feature will break - live migration to older host kernels that don't support the TSC deadline timer will cause the feature to be pulled from under the guest's feet; breaking it - guests that are broken wrt the feature will fail. Fix by not enabling the feature automatically; instead report it to userspace. Because the feature depends on KVM_CREATE_IRQCHIP, which we cannot guarantee will be called, we expose it via a KVM_CAP_TSC_DEADLINE_TIMER and not KVM_GET_SUPPORTED_CPUID. Fixes the Illumos guest kernel, which uses the TSC deadline timer feature. [avi: add the KVM_CAP + documentation] Reported-by: Alexey Zaytsev Tested-by: Alexey Zaytsev Signed-off-by: Jan Kiszka Signed-off-by: Avi Kivity --- Documentation/virtual/kvm/api.txt | 9 +++++++++ arch/x86/kvm/x86.c | 19 +++++++++---------- include/linux/kvm.h | 1 + 3 files changed, 19 insertions(+), 10 deletions(-) (limited to 'Documentation') diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt index 4df9af4f6132..e2a4b5287361 100644 --- a/Documentation/virtual/kvm/api.txt +++ b/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 diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index c38efd7b792e..4c938da2ba00 100644 --- a/arch/x86/kvm/x86.c +++ b/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; diff --git a/include/linux/kvm.h b/include/linux/kvm.h index c3892fc1d538..68e67e50d028 100644 --- a/include/linux/kvm.h +++ b/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 -- cgit v1.2.3