Hi Andre,
On 4/15/19 1:15 PM, Andre Przywara wrote:
> KVM implements the firmware interface for mitigating cache speculation
> vulnerabilities. Guests may use this interface to ensure mitigation is
> active.
> If we want to migrate such a guest to a host with a different support
> level for those workarounds, migration might need to fail, to ensure that
> critical guests don't loose their protection.
>
> Introduce a way for userland to save and restore the workarounds state.
> On restoring we do checks that make sure we don't downgrade our
> mitigation level.
Reviewed-by: Eric Auger <eric.auger@xxxxxxxxxx>
Thanks
Eric
>
> Signed-off-by: Andre Przywara <andre.przywara@xxxxxxx>
> ---
> arch/arm/include/asm/kvm_emulate.h | 10 ++
> arch/arm/include/uapi/asm/kvm.h | 12 +++
> arch/arm64/include/asm/kvm_emulate.h | 14 +++
> arch/arm64/include/uapi/asm/kvm.h | 10 ++
> virt/kvm/arm/psci.c | 139 ++++++++++++++++++++++++---
> 5 files changed, 170 insertions(+), 15 deletions(-)
>
> diff --git a/arch/arm/include/asm/kvm_emulate.h b/arch/arm/include/asm/kvm_emulate.h
> index 8927cae7c966..663a02d7e6f4 100644
> --- a/arch/arm/include/asm/kvm_emulate.h
> +++ b/arch/arm/include/asm/kvm_emulate.h
> @@ -283,6 +283,16 @@ static inline unsigned long kvm_vcpu_get_mpidr_aff(struct kvm_vcpu *vcpu)
> return vcpu_cp15(vcpu, c0_MPIDR) & MPIDR_HWID_BITMASK;
> }
>
> +static inline bool kvm_arm_get_vcpu_workaround_2_flag(struct kvm_vcpu *vcpu)
> +{
> + return false;
> +}
> +
> +static inline void kvm_arm_set_vcpu_workaround_2_flag(struct kvm_vcpu *vcpu,
> + bool flag)
> +{
> +}
> +
> static inline void kvm_vcpu_set_be(struct kvm_vcpu *vcpu)
> {
> *vcpu_cpsr(vcpu) |= PSR_E_BIT;
> diff --git a/arch/arm/include/uapi/asm/kvm.h b/arch/arm/include/uapi/asm/kvm.h
> index 4602464ebdfb..dfce6fdbd03b 100644
> --- a/arch/arm/include/uapi/asm/kvm.h
> +++ b/arch/arm/include/uapi/asm/kvm.h
> @@ -214,6 +214,18 @@ struct kvm_vcpu_events {
> #define KVM_REG_ARM_FW_REG(r) (KVM_REG_ARM | KVM_REG_SIZE_U64 | \
> KVM_REG_ARM_FW | ((r) & 0xffff))
> #define KVM_REG_ARM_PSCI_VERSION KVM_REG_ARM_FW_REG(0)
> +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1 KVM_REG_ARM_FW_REG(1)
> + /* Higher values mean better protection. */
> +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_AVAIL 0
> +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_AVAIL 1
> +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_UNAFFECTED 2
> +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2 KVM_REG_ARM_FW_REG(2)
> + /* Higher values mean better protection. */
> +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_AVAIL 0
> +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_UNKNOWN 1
> +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_AVAIL 2
> +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_UNAFFECTED 3
> +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_ENABLED (1U << 4)
>
> /* Device Control API: ARM VGIC */
> #define KVM_DEV_ARM_VGIC_GRP_ADDR 0
> diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
> index d3842791e1c4..c00c17c9adb6 100644
> --- a/arch/arm64/include/asm/kvm_emulate.h
> +++ b/arch/arm64/include/asm/kvm_emulate.h
> @@ -348,6 +348,20 @@ static inline unsigned long kvm_vcpu_get_mpidr_aff(struct kvm_vcpu *vcpu)
> return vcpu_read_sys_reg(vcpu, MPIDR_EL1) & MPIDR_HWID_BITMASK;
> }
>
> +static inline bool kvm_arm_get_vcpu_workaround_2_flag(struct kvm_vcpu *vcpu)
> +{
> + return vcpu->arch.workaround_flags & VCPU_WORKAROUND_2_FLAG;
> +}
> +
> +static inline void kvm_arm_set_vcpu_workaround_2_flag(struct kvm_vcpu *vcpu,
> + bool flag)
> +{
> + if (flag)
> + vcpu->arch.workaround_flags |= VCPU_WORKAROUND_2_FLAG;
> + else
> + vcpu->arch.workaround_flags &= ~VCPU_WORKAROUND_2_FLAG;
> +}
> +
> static inline void kvm_vcpu_set_be(struct kvm_vcpu *vcpu)
> {
> if (vcpu_mode_is_32bit(vcpu)) {
> diff --git a/arch/arm64/include/uapi/asm/kvm.h b/arch/arm64/include/uapi/asm/kvm.h
> index 97c3478ee6e7..e75a81a7716f 100644
> --- a/arch/arm64/include/uapi/asm/kvm.h
> +++ b/arch/arm64/include/uapi/asm/kvm.h
> @@ -225,6 +225,16 @@ struct kvm_vcpu_events {
> #define KVM_REG_ARM_FW_REG(r) (KVM_REG_ARM64 | KVM_REG_SIZE_U64 | \
> KVM_REG_ARM_FW | ((r) & 0xffff))
> #define KVM_REG_ARM_PSCI_VERSION KVM_REG_ARM_FW_REG(0)
> +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1 KVM_REG_ARM_FW_REG(1)
> +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_AVAIL 0
> +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_AVAIL 1
> +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_UNAFFECTED 2
> +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2 KVM_REG_ARM_FW_REG(2)
> +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_AVAIL 0
> +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_UNKNOWN 1
> +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_AVAIL 2
> +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_UNAFFECTED 3
> +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_ENABLED (1U << 4)
>
> /* Device Control API: ARM VGIC */
> #define KVM_DEV_ARM_VGIC_GRP_ADDR 0
> diff --git a/virt/kvm/arm/psci.c b/virt/kvm/arm/psci.c
> index 1da53e0e38f7..c82d90aad3ea 100644
> --- a/virt/kvm/arm/psci.c
> +++ b/virt/kvm/arm/psci.c
> @@ -449,42 +449,103 @@ int kvm_hvc_call_handler(struct kvm_vcpu *vcpu)
>
> int kvm_arm_get_fw_num_regs(struct kvm_vcpu *vcpu)
> {
> - return 1; /* PSCI version */
> + return 3; /* PSCI version and two workaround registers */
> }
>
> int kvm_arm_copy_fw_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices)
> {
> - if (put_user(KVM_REG_ARM_PSCI_VERSION, uindices))
> + if (put_user(KVM_REG_ARM_PSCI_VERSION, uindices++))
> + return -EFAULT;
> +
> + if (put_user(KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1, uindices++))
> + return -EFAULT;
> +
> + if (put_user(KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2, uindices++))
> return -EFAULT;
>
> return 0;
> }
>
> +#define KVM_REG_FEATURE_LEVEL_WIDTH 4
> +#define KVM_REG_FEATURE_LEVEL_MASK (BIT(KVM_REG_FEATURE_LEVEL_WIDTH) - 1)
> +
> +/*
> + * Convert the workaround level into an easy-to-compare number, where higher
> + * values mean better protection.
> + */
> +static int get_kernel_wa_level(u64 regid)
> +{
> + switch (regid) {
> + case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1:
> + switch (kvm_arm_harden_branch_predictor()) {
> + case KVM_BP_HARDEN_UNKNOWN:
> + return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_AVAIL;
> + case KVM_BP_HARDEN_NEEDED:
> + return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_AVAIL;
> + case KVM_BP_HARDEN_MITIGATED:
> + return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_UNAFFECTED;
> + }
> + return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_AVAIL;
> + case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2:
> + switch (kvm_arm_have_ssbd()) {
> + case KVM_SSBD_FORCE_DISABLE:
> + return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_AVAIL;
> + case KVM_SSBD_KERNEL:
> + return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_AVAIL;
> + case KVM_SSBD_FORCE_ENABLE:
> + case KVM_SSBD_MITIGATED:
> + return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_UNAFFECTED;
> + case KVM_SSBD_UNKNOWN:
> + default:
> + return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_UNKNOWN;
> + }
> + }
> +
> + return -EINVAL;
> +}
> +
> int kvm_arm_get_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
> {
> - if (reg->id == KVM_REG_ARM_PSCI_VERSION) {
> - void __user *uaddr = (void __user *)(long)reg->addr;
> - u64 val;
> + void __user *uaddr = (void __user *)(long)reg->addr;
> + u64 val;
>
> + switch (reg->id) {
> + case KVM_REG_ARM_PSCI_VERSION:
> val = kvm_psci_version(vcpu, vcpu->kvm);
> - if (copy_to_user(uaddr, &val, KVM_REG_SIZE(reg->id)))
> - return -EFAULT;
> + break;
> + case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1:
> + val = get_kernel_wa_level(reg->id) & KVM_REG_FEATURE_LEVEL_MASK;
> + break;
> + case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2:
> + val = get_kernel_wa_level(reg->id) & KVM_REG_FEATURE_LEVEL_MASK;
>
> - return 0;
> + if (val == KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_AVAIL &&
> + kvm_arm_get_vcpu_workaround_2_flag(vcpu))
> + val |= KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_ENABLED;
> + break;
> + default:
> + return -ENOENT;
> }
>
> - return -EINVAL;
> + if (copy_to_user(uaddr, &val, KVM_REG_SIZE(reg->id)))
> + return -EFAULT;
> +
> + return 0;
> }
>
> int kvm_arm_set_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
> {
> - if (reg->id == KVM_REG_ARM_PSCI_VERSION) {
> - void __user *uaddr = (void __user *)(long)reg->addr;
> - bool wants_02;
> - u64 val;
> + void __user *uaddr = (void __user *)(long)reg->addr;
> + u64 val;
> + int wa_level;> +
> + if (copy_from_user(&val, uaddr, KVM_REG_SIZE(reg->id)))
> + return -EFAULT;
>
> - if (copy_from_user(&val, uaddr, KVM_REG_SIZE(reg->id)))
> - return -EFAULT;
> + switch (reg->id) {
> + case KVM_REG_ARM_PSCI_VERSION:
> + {
> + bool wants_02;
>
> wants_02 = test_bit(KVM_ARM_VCPU_PSCI_0_2, vcpu->arch.features);
>
> @@ -501,6 +562,54 @@ int kvm_arm_set_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
> vcpu->kvm->arch.psci_version = val;
> return 0;
> }
> + break;
> + }
> +
> + case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1:
> + if (val & ~KVM_REG_FEATURE_LEVEL_MASK)
> + return -EINVAL;
> +
> + if (get_kernel_wa_level(reg->id) < val)
> + return -EINVAL;
> +
> + return 0;
> +
> + case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2:
> + if (val & ~(KVM_REG_FEATURE_LEVEL_MASK |
> + KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_ENABLED))
> + return -EINVAL;
> +
> + wa_level = val & KVM_REG_FEATURE_LEVEL_MASK;
> +
> + if (get_kernel_wa_level(reg->id) < wa_level)
> + return -EINVAL;
> +
> + /* The enabled bit must not be set unless the level is AVAIL. */
> + if (wa_level != KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_AVAIL &&
> + wa_level != val)
> + return -EINVAL;
> +
> + /* Are we finished or do we need to check the enable bit ? */
> + if (kvm_arm_have_ssbd() != KVM_SSBD_KERNEL)> + return 0;
> +
> + /*
> + * If this kernel supports the workaround to be switched on
> + * or off, make sure it matches the requested setting.
> + */
> + switch (wa_level) {
> + case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_AVAIL:
> + kvm_arm_set_vcpu_workaround_2_flag(vcpu,
> + val & KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_ENABLED);
> + break;
> + case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_UNAFFECTED:
> + kvm_arm_set_vcpu_workaround_2_flag(vcpu, true);
> + break;
> + }
> +
> + return 0;
> + default:
> + return -ENOENT;
> }
>
> return -EINVAL;
>
