Re: [PATCH] KVM: PPC: Book3S: Provide information about hardware/firmware CVE workarounds

[Paolo Bonzini <pbonzini@redhat.com>]

On 16/01/2018 01:59, Paul Mackerras wrote:
> This adds a new ioctl, KVM_PPC_GET_CPU_CHAR, that gives userspace
> information about the underlying machine's level of vulnerability
> to the recently announced vulnerabilities CVE-2017-5715,
> CVE-2017-5753 and CVE-2017-5754, and whether the machine provides
> instructions to assist software to work around the vulnerabilities.
> 
> The ioctl returns two u64 words describing characteristics of the
> CPU and required software behaviour respectively, plus two mask
> words which indicate which bits have been filled in by the kernel,
> for extensibility.  The bit definitions are the same as for the
> new H_GET_CPU_CHARACTERISTICS hypercall.
> 
> There is also a new capability, KVM_CAP_PPC_GET_CPU_CHAR, which
> indicates whether the new ioctl is available.
> 
> Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
> ---
>  Documentation/virtual/kvm/api.txt   |  46 +++++++++++++
>  arch/powerpc/include/uapi/asm/kvm.h |  22 +++++++
>  arch/powerpc/kvm/powerpc.c          | 124 ++++++++++++++++++++++++++++++++++++
>  include/uapi/linux/kvm.h            |   3 +
>  4 files changed, 195 insertions(+)
> 
> diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt
> index f670e4b..85ca84a 100644
> --- a/Documentation/virtual/kvm/api.txt
> +++ b/Documentation/virtual/kvm/api.txt
> @@ -3394,6 +3394,52 @@ invalid, if invalid pages are written to (e.g. after the end of memory)
>  or if no page table is present for the addresses (e.g. when using
>  hugepages).
>  
> +4.108 KVM_PPC_GET_CPU_CHAR
> +
> +Capability: KVM_CAP_PPC_GET_CPU_CHAR
> +Architectures: powerpc
> +Type: vm ioctl
> +Parameters: struct kvm_ppc_cpu_char (out)
> +Returns: 0 on successful completion
> +	 -EFAULT if struct kvm_ppc_cpu_char cannot be written
> +
> +This ioctl gives userspace information about certain characteristics
> +of the CPU relating to speculative execution of instructions and
> +possible information leakage resulting from speculative execution (see
> +CVE-2017-5715, CVE-2017-5753 and CVE-2017-5754).  The information is
> +returned in struct kvm_ppc_cpu_char, which looks like this:
> +
> +struct kvm_ppc_cpu_char {
> +	__u64	character;		/* characteristics of the CPU */
> +	__u64	behaviour;		/* recommended software behaviour */
> +	__u64	character_mask;		/* valid bits in character */
> +	__u64	behaviour_mask;		/* valid bits in behaviour */
> +};
> +
> +For extensibility, the character_mask and behaviour_mask fields
> +indicate which bits of character and behaviour have been filled in by
> +the kernel.  If the set of defined bits is extended in future then
> +userspace will be able to tell whether it is running on a kernel that
> +knows about the new bits.
> +
> +The character field describes attributes of the CPU which can help
> +with preventing inadvertent information disclosure - specifically,
> +whether there is an instruction to flash-invalidate the L1 data cache
> +(ori 30,30,0 or mtspr SPRN_TRIG2,rN), whether the L1 data cache is set
> +to a mode where entries can only be used by the thread that created
> +them, whether the bcctr[l] instruction prevents speculation, and
> +whether a speculation barrier instruction (ori 31,31,0) is provided.
> +
> +The behaviour field describes actions that software should take to
> +prevent inadvertent information disclosure, and thus describes which
> +vulnerabilities the hardware is subject to; specifically whether the
> +L1 data cache should be flushed when returning to user mode from the
> +kernel, and whether a speculation barrier should be placed between an
> +array bounds check and the array access.
> +
> +These fields use the same bit definitions as the new
> +H_GET_CPU_CHARACTERISTICS hypercall.
> +
>  5. The kvm_run structure
>  ------------------------
>  
> diff --git a/arch/powerpc/include/uapi/asm/kvm.h b/arch/powerpc/include/uapi/asm/kvm.h
> index 61d6049..ce74bed 100644
> --- a/arch/powerpc/include/uapi/asm/kvm.h
> +++ b/arch/powerpc/include/uapi/asm/kvm.h
> @@ -443,6 +443,28 @@ struct kvm_ppc_rmmu_info {
>  	__u32	ap_encodings[8];
>  };
>  
> +/* For KVM_PPC_GET_CPU_CHAR */
> +struct kvm_ppc_cpu_char {
> +	__u64	character;		/* characteristics of the CPU */
> +	__u64	behaviour;		/* recommended software behaviour */
> +	__u64	character_mask;		/* valid bits in character */
> +	__u64	behaviour_mask;		/* valid bits in behaviour */
> +};
> +
> +/*
> + * Values for character and character_mask.
> + * These are identical to the values used by H_GET_CPU_CHARACTERISTICS.
> + */
> +#define KVM_PPC_CPU_CHAR_SPEC_BAR_ORI31		(1ULL << 63)
> +#define KVM_PPC_CPU_CHAR_BCCTRL_SERIALISED	(1ULL << 62)
> +#define KVM_PPC_CPU_CHAR_L1D_FLUSH_ORI30	(1ULL << 61)
> +#define KVM_PPC_CPU_CHAR_L1D_FLUSH_TRIG2	(1ULL << 60)
> +#define KVM_PPC_CPU_CHAR_L1D_THREAD_PRIV	(1ULL << 59)
> +
> +#define KVM_PPC_CPU_BEHAV_FAVOUR_SECURITY	(1ULL << 63)
> +#define KVM_PPC_CPU_BEHAV_L1D_FLUSH_PR		(1ULL << 62)
> +#define KVM_PPC_CPU_BEHAV_BNDS_CHK_SPEC_BAR	(1ULL << 61)
> +
>  /* Per-vcpu XICS interrupt controller state */
>  #define KVM_REG_PPC_ICP_STATE	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x8c)
>  
> diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
> index 1915e86..c9cecff 100644
> --- a/arch/powerpc/kvm/powerpc.c
> +++ b/arch/powerpc/kvm/powerpc.c
> @@ -39,6 +39,10 @@
>  #include <asm/iommu.h>
>  #include <asm/switch_to.h>
>  #include <asm/xive.h>
> +#ifdef CONFIG_PPC_PSERIES
> +#include <asm/hvcall.h>
> +#include <asm/plpar_wrappers.h>
> +#endif
>  
>  #include "timing.h"
>  #include "irq.h"
> @@ -548,6 +552,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
>  #ifdef CONFIG_KVM_XICS
>  	case KVM_CAP_IRQ_XICS:
>  #endif
> +	case KVM_CAP_PPC_GET_CPU_CHAR:
>  		r = 1;
>  		break;
>  
> @@ -1759,6 +1764,117 @@ static int kvm_vm_ioctl_enable_cap(struct kvm *kvm,
>  	return r;
>  }
>  
> +#ifdef CONFIG_PPC_BOOK3S_64
> +/*
> + * These functions check whether the underlying hardware is safe
> + * against attacks based on observing the effects of speculatively
> + * executed instructions, and whether it supplies instructions for
> + * use in workarounds.  The information comes from firmware, either
> + * via the device tree on powernv platforms or from an hcall on
> + * pseries platforms.
> + */
> +#ifdef CONFIG_PPC_PSERIES
> +static int pseries_get_cpu_char(struct kvm_ppc_cpu_char *cp)
> +{
> +	struct h_cpu_char_result c;
> +	unsigned long rc;
> +
> +	if (!machine_is(pseries))
> +		return -ENOTTY;
> +
> +	rc = plpar_get_cpu_characteristics(&c);
> +	if (rc == H_SUCCESS) {
> +		cp->character = c.character;
> +		cp->behaviour = c.behaviour;
> +		cp->character_mask = KVM_PPC_CPU_CHAR_SPEC_BAR_ORI31 |
> +			KVM_PPC_CPU_CHAR_BCCTRL_SERIALISED |
> +			KVM_PPC_CPU_CHAR_L1D_FLUSH_ORI30 |
> +			KVM_PPC_CPU_CHAR_L1D_FLUSH_TRIG2 |
> +			KVM_PPC_CPU_CHAR_L1D_THREAD_PRIV;
> +		cp->behaviour_mask = KVM_PPC_CPU_BEHAV_FAVOUR_SECURITY |
> +			KVM_PPC_CPU_BEHAV_L1D_FLUSH_PR |
> +			KVM_PPC_CPU_BEHAV_BNDS_CHK_SPEC_BAR;
> +	}
> +	return 0;
> +}
> +#else
> +static int pseries_get_cpu_char(struct kvm_ppc_cpu_char *cp)
> +{
> +	return -ENOTTY;
> +}
> +#endif
> +
> +static inline bool have_fw_feat(struct device_node *fw_features,
> +				const char *state, const char *name)
> +{
> +	struct device_node *np;
> +	bool r = false;
> +
> +	np = of_get_child_by_name(fw_features, name);
> +	if (np) {
> +		r = of_property_read_bool(np, state);
> +		of_node_put(np);
> +	}
> +	return r;
> +}
> +
> +static int kvmppc_get_cpu_char(struct kvm_ppc_cpu_char *cp)
> +{
> +	struct device_node *np, *fw_features;
> +	int r;
> +
> +	memset(cp, 0, sizeof(*cp));
> +	r = pseries_get_cpu_char(cp);
> +	if (r != -ENOTTY)
> +		return r;
> +
> +	np = of_find_node_by_name(NULL, "ibm,opal");
> +	if (np) {
> +		fw_features = of_get_child_by_name(np, "fw-features");
> +		of_node_put(np);
> +		if (!fw_features)
> +			return 0;
> +		if (have_fw_feat(fw_features, "enabled",
> +				 "inst-spec-barrier-ori31,31,0"))
> +			cp->character |= KVM_PPC_CPU_CHAR_SPEC_BAR_ORI31;
> +		if (have_fw_feat(fw_features, "enabled",
> +				 "fw-bcctrl-serialized"))
> +			cp->character |= KVM_PPC_CPU_CHAR_BCCTRL_SERIALISED;
> +		if (have_fw_feat(fw_features, "enabled",
> +				 "inst-l1d-flush-ori30,30,0"))
> +			cp->character |= KVM_PPC_CPU_CHAR_L1D_FLUSH_ORI30;
> +		if (have_fw_feat(fw_features, "enabled",
> +				 "inst-l1d-flush-trig2"))
> +			cp->character |= KVM_PPC_CPU_CHAR_L1D_FLUSH_TRIG2;
> +		if (have_fw_feat(fw_features, "enabled",
> +				 "fw-l1d-thread-split"))
> +			cp->character |= KVM_PPC_CPU_CHAR_L1D_THREAD_PRIV;
> +		cp->character_mask = KVM_PPC_CPU_CHAR_SPEC_BAR_ORI31 |
> +			KVM_PPC_CPU_CHAR_BCCTRL_SERIALISED |
> +			KVM_PPC_CPU_CHAR_L1D_FLUSH_ORI30 |
> +			KVM_PPC_CPU_CHAR_L1D_FLUSH_TRIG2 |
> +			KVM_PPC_CPU_CHAR_L1D_THREAD_PRIV;
> +
> +		if (have_fw_feat(fw_features, "enabled",
> +				 "speculation-policy-favor-security"))
> +			cp->behaviour |= KVM_PPC_CPU_BEHAV_FAVOUR_SECURITY;
> +		if (!have_fw_feat(fw_features, "disabled",
> +				  "needs-l1d-flush-msr-pr-0-to-1"))
> +			cp->behaviour |= KVM_PPC_CPU_BEHAV_L1D_FLUSH_PR;
> +		if (!have_fw_feat(fw_features, "disabled",
> +				  "needs-spec-barrier-for-bound-checks"))
> +			cp->behaviour |= KVM_PPC_CPU_BEHAV_BNDS_CHK_SPEC_BAR;
> +		cp->behaviour_mask = KVM_PPC_CPU_BEHAV_FAVOUR_SECURITY |
> +			KVM_PPC_CPU_BEHAV_L1D_FLUSH_PR |
> +			KVM_PPC_CPU_BEHAV_BNDS_CHK_SPEC_BAR;
> +
> +		of_node_put(fw_features);
> +	}
> +
> +	return 0;
> +}
> +#endif
> +
>  long kvm_arch_vm_ioctl(struct file *filp,
>                         unsigned int ioctl, unsigned long arg)
>  {
> @@ -1861,6 +1977,14 @@ long kvm_arch_vm_ioctl(struct file *filp,
>  			r = -EFAULT;
>  		break;
>  	}
> +	case KVM_PPC_GET_CPU_CHAR: {
> +		struct kvm_ppc_cpu_char cpuchar;
> +
> +		r = kvmppc_get_cpu_char(&cpuchar);
> +		if (r >= 0 && copy_to_user(argp, &cpuchar, sizeof(cpuchar)))
> +			r = -EFAULT;
> +		break;
> +	}
>  	default: {
>  		struct kvm *kvm = filp->private_data;
>  		r = kvm->arch.kvm_ops->arch_vm_ioctl(filp, ioctl, arg);
> diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
> index 282d7613..e96e629 100644
> --- a/include/uapi/linux/kvm.h
> +++ b/include/uapi/linux/kvm.h
> @@ -932,6 +932,7 @@ struct kvm_ppc_resize_hpt {
>  #define KVM_CAP_HYPERV_SYNIC2 148
>  #define KVM_CAP_HYPERV_VP_INDEX 149
>  #define KVM_CAP_S390_AIS_MIGRATION 150
> +#define KVM_CAP_PPC_GET_CPU_CHAR 151
>  
>  #ifdef KVM_CAP_IRQ_ROUTING
>  
> @@ -1261,6 +1262,8 @@ struct kvm_s390_ucas_mapping {
>  #define KVM_PPC_CONFIGURE_V3_MMU  _IOW(KVMIO,  0xaf, struct kvm_ppc_mmuv3_cfg)
>  /* Available with KVM_CAP_PPC_RADIX_MMU */
>  #define KVM_PPC_GET_RMMU_INFO	  _IOW(KVMIO,  0xb0, struct kvm_ppc_rmmu_info)
> +/* Available with KVM_CAP_PPC_GET_CPU_CHAR */
> +#define KVM_PPC_GET_CPU_CHAR	  _IOR(KVMIO,  0xb1, struct kvm_ppc_cpu_char)
>  
>  /* ioctl for vm fd */
>  #define KVM_CREATE_DEVICE	  _IOWR(KVMIO,  0xe0, struct kvm_create_device)
> 

Thanks, looks good.  Would you like this in 4.15?

Paolo