From a28ebea2adc4a2bef5989a5a181ec238f59fbcad Mon Sep 17 00:00:00 2001 From: Christoffer Dall Date: Tue, 9 Aug 2016 19:13:01 +0200 Subject: [PATCH] KVM: Protect device ops->create and list_add with kvm->lock MIME-Version: 1.0 Content-Type: text/plain; charset=utf8 Content-Transfer-Encoding: 8bit KVM devices were manipulating list data structures without any form of synchronization, and some implementations of the create operations also suffered from a lack of synchronization. Now when we've split the xics create operation into create and init, we can hold the kvm->lock mutex while calling the create operation and when manipulating the devices list. The error path in the generic code gets slightly ugly because we have to take the mutex again and delete the device from the list, but holding the mutex during anon_inode_getfd or releasing/locking the mutex in the common non-error path seemed wrong. Signed-off-by: Christoffer Dall Reviewed-by: Paolo Bonzini Acked-by: Christian Borntraeger Signed-off-by: Radim Krčmář --- arch/arm/kvm/arm.c | 6 +++++- arch/powerpc/kvm/book3s_xics.c | 2 -- include/linux/kvm_host.h | 6 ++++++ virt/kvm/arm/vgic/vgic-init.c | 17 ++++------------- virt/kvm/kvm_main.c | 13 ++++++++++++- 5 files changed, 27 insertions(+), 17 deletions(-) diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c index d94bb9093ead..75f130ef6504 100644 --- a/arch/arm/kvm/arm.c +++ b/arch/arm/kvm/arm.c @@ -1009,9 +1009,13 @@ long kvm_arch_vm_ioctl(struct file *filp, switch (ioctl) { case KVM_CREATE_IRQCHIP: { + int ret; if (!vgic_present) return -ENXIO; - return kvm_vgic_create(kvm, KVM_DEV_TYPE_ARM_VGIC_V2); + mutex_lock(&kvm->lock); + ret = kvm_vgic_create(kvm, KVM_DEV_TYPE_ARM_VGIC_V2); + mutex_unlock(&kvm->lock); + return ret; } case KVM_ARM_SET_DEVICE_ADDR: { struct kvm_arm_device_addr dev_addr; diff --git a/arch/powerpc/kvm/book3s_xics.c b/arch/powerpc/kvm/book3s_xics.c index f2def8e45fef..05aa11399a78 100644 --- a/arch/powerpc/kvm/book3s_xics.c +++ b/arch/powerpc/kvm/book3s_xics.c @@ -1329,12 +1329,10 @@ static int kvmppc_xics_create(struct kvm_device *dev, u32 type) xics->kvm = kvm; /* Already there ? */ - mutex_lock(&kvm->lock); if (kvm->arch.xics) ret = -EEXIST; else kvm->arch.xics = xics; - mutex_unlock(&kvm->lock); if (ret) { kfree(xics); diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index d3c9b82812c3..9c28b4d4c90b 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -1113,6 +1113,12 @@ struct kvm_device { /* create, destroy, and name are mandatory */ struct kvm_device_ops { const char *name; + + /* + * create is called holding kvm->lock and any operations not suitable + * to do while holding the lock should be deferred to init (see + * below). + */ int (*create)(struct kvm_device *dev, u32 type); /* diff --git a/virt/kvm/arm/vgic/vgic-init.c b/virt/kvm/arm/vgic/vgic-init.c index fb4b0a79a950..83777c1cbae0 100644 --- a/virt/kvm/arm/vgic/vgic-init.c +++ b/virt/kvm/arm/vgic/vgic-init.c @@ -73,12 +73,8 @@ int kvm_vgic_create(struct kvm *kvm, u32 type) int i, vcpu_lock_idx = -1, ret; struct kvm_vcpu *vcpu; - mutex_lock(&kvm->lock); - - if (irqchip_in_kernel(kvm)) { - ret = -EEXIST; - goto out; - } + if (irqchip_in_kernel(kvm)) + return -EEXIST; /* * This function is also called by the KVM_CREATE_IRQCHIP handler, @@ -87,10 +83,8 @@ int kvm_vgic_create(struct kvm *kvm, u32 type) * the proper checks already. */ if (type == KVM_DEV_TYPE_ARM_VGIC_V2 && - !kvm_vgic_global_state.can_emulate_gicv2) { - ret = -ENODEV; - goto out; - } + !kvm_vgic_global_state.can_emulate_gicv2) + return -ENODEV; /* * Any time a vcpu is run, vcpu_load is called which tries to grab the @@ -138,9 +132,6 @@ out_unlock: vcpu = kvm_get_vcpu(kvm, vcpu_lock_idx); mutex_unlock(&vcpu->mutex); } - -out: - mutex_unlock(&kvm->lock); return ret; } diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index ae642452e91a..195078225aa5 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -696,6 +696,11 @@ static void kvm_destroy_devices(struct kvm *kvm) { struct kvm_device *dev, *tmp; + /* + * We do not need to take the kvm->lock here, because nobody else + * has a reference to the struct kvm at this point and therefore + * cannot access the devices list anyhow. + */ list_for_each_entry_safe(dev, tmp, &kvm->devices, vm_node) { list_del(&dev->vm_node); dev->ops->destroy(dev); @@ -2832,11 +2837,15 @@ static int kvm_ioctl_create_device(struct kvm *kvm, dev->ops = ops; dev->kvm = kvm; + mutex_lock(&kvm->lock); ret = ops->create(dev, cd->type); if (ret < 0) { + mutex_unlock(&kvm->lock); kfree(dev); return ret; } + list_add(&dev->vm_node, &kvm->devices); + mutex_unlock(&kvm->lock); if (ops->init) ops->init(dev); @@ -2844,10 +2853,12 @@ static int kvm_ioctl_create_device(struct kvm *kvm, ret = anon_inode_getfd(ops->name, &kvm_device_fops, dev, O_RDWR | O_CLOEXEC); if (ret < 0) { ops->destroy(dev); + mutex_lock(&kvm->lock); + list_del(&dev->vm_node); + mutex_unlock(&kvm->lock); return ret; } - list_add(&dev->vm_node, &kvm->devices); kvm_get_kvm(kvm); cd->fd = ret; return 0; -- 2.30.2