kvm: Add KVM_GET_EMULATED_CPUID (9c15bb1d) · Commits · 戴 / test

Documentation/virtual/kvm/api.txt

+74 −3

Original line number	Diff line number	Diff line
		@@ -1122,9 +1122,9 @@ struct kvm_cpuid2 {
		struct kvm_cpuid_entry2 entries[0];
		};

		#define KVM_CPUID_FLAG_SIGNIFCANT_INDEX 1
		#define KVM_CPUID_FLAG_STATEFUL_FUNC 2
		#define KVM_CPUID_FLAG_STATE_READ_NEXT 4
		#define KVM_CPUID_FLAG_SIGNIFCANT_INDEX BIT(0)
		#define KVM_CPUID_FLAG_STATEFUL_FUNC BIT(1)
		#define KVM_CPUID_FLAG_STATE_READ_NEXT BIT(2)

		struct kvm_cpuid_entry2 {
		__u32 function;
		@@ -2684,6 +2684,77 @@ and usually define the validity of a groups of registers. (e.g. one bit
		};


		4.81 KVM_GET_EMULATED_CPUID

		Capability: KVM_CAP_EXT_EMUL_CPUID
		Architectures: x86
		Type: system ioctl
		Parameters: struct kvm_cpuid2 (in/out)
		Returns: 0 on success, -1 on error

		struct kvm_cpuid2 {
		__u32 nent;
		__u32 flags;
		struct kvm_cpuid_entry2 entries[0];
		};

		The member 'flags' is used for passing flags from userspace.

		#define KVM_CPUID_FLAG_SIGNIFCANT_INDEX BIT(0)
		#define KVM_CPUID_FLAG_STATEFUL_FUNC BIT(1)
		#define KVM_CPUID_FLAG_STATE_READ_NEXT BIT(2)

		struct kvm_cpuid_entry2 {
		__u32 function;
		__u32 index;
		__u32 flags;
		__u32 eax;
		__u32 ebx;
		__u32 ecx;
		__u32 edx;
		__u32 padding[3];
		};

		This ioctl returns x86 cpuid features which are emulated by
		kvm.Userspace can use the information returned by this ioctl to query
		which features are emulated by kvm instead of being present natively.

		Userspace invokes KVM_GET_EMULATED_CPUID by passing a kvm_cpuid2
		structure with the 'nent' field indicating the number of entries in
		the variable-size array 'entries'. If the number of entries is too low
		to describe the cpu capabilities, an error (E2BIG) is returned. If the
		number is too high, the 'nent' field is adjusted and an error (ENOMEM)
		is returned. If the number is just right, the 'nent' field is adjusted
		to the number of valid entries in the 'entries' array, which is then
		filled.

		The entries returned are the set CPUID bits of the respective features
		which kvm emulates, as returned by the CPUID instruction, with unknown
		or unsupported feature bits cleared.

		Features like x2apic, for example, may not be present in the host cpu
		but are exposed by kvm in KVM_GET_SUPPORTED_CPUID because they can be
		emulated efficiently and thus not included here.

		The fields in each entry are defined as follows:

		function: the eax value used to obtain the entry
		index: the ecx value used to obtain the entry (for entries that are
		affected by ecx)
		flags: an OR of zero or more of the following:
		KVM_CPUID_FLAG_SIGNIFCANT_INDEX:
		if the index field is valid
		KVM_CPUID_FLAG_STATEFUL_FUNC:
		if cpuid for this function returns different values for successive
		invocations; there will be several entries with the same function,
		all with this flag set
		KVM_CPUID_FLAG_STATE_READ_NEXT:
		for KVM_CPUID_FLAG_STATEFUL_FUNC entries, set if this entry is
		the first entry to be read by a cpu
		eax, ebx, ecx, edx: the values returned by the cpuid instruction for
		this function/index combination


		6. Capabilities that can be enabled
		-----------------------------------

arch/x86/include/uapi/asm/kvm.h

+3 −3

Original line number	Diff line number	Diff line
		@@ -211,9 +211,9 @@ struct kvm_cpuid_entry2 {
		__u32 padding[3];
		};

		#define KVM_CPUID_FLAG_SIGNIFCANT_INDEX 1
		#define KVM_CPUID_FLAG_STATEFUL_FUNC 2
		#define KVM_CPUID_FLAG_STATE_READ_NEXT 4
		#define KVM_CPUID_FLAG_SIGNIFCANT_INDEX BIT(0)
		#define KVM_CPUID_FLAG_STATEFUL_FUNC BIT(1)
		#define KVM_CPUID_FLAG_STATE_READ_NEXT BIT(2)

		/* for KVM_SET_CPUID2 */
		struct kvm_cpuid2 {

arch/x86/kvm/cpuid.c

+51 −6

Original line number	Diff line number	Diff line
		@@ -219,7 +219,13 @@ static bool supported_xcr0_bit(unsigned bit)

		#define F(x) bit(X86_FEATURE_##x)

		static int do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
		static int __do_cpuid_ent_emulated(struct kvm_cpuid_entry2 *entry,
		u32 func, u32 index, int *nent, int maxnent)
		{
		return 0;
		}

		static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
		u32 index, int *nent, int maxnent)
		{
		int r;
		@@ -515,6 +521,15 @@ out:
		return r;
		}

		static int do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 func,
		u32 idx, int *nent, int maxnent, unsigned int type)
		{
		if (type == KVM_GET_EMULATED_CPUID)
		return __do_cpuid_ent_emulated(entry, func, idx, nent, maxnent);

		return __do_cpuid_ent(entry, func, idx, nent, maxnent);
		}

		#undef F

		struct kvm_cpuid_param {
		@@ -529,8 +544,34 @@ static bool is_centaur_cpu(const struct kvm_cpuid_param *param)
		return boot_cpu_data.x86_vendor == X86_VENDOR_CENTAUR;
		}

		int kvm_dev_ioctl_get_supported_cpuid(struct kvm_cpuid2 *cpuid,
		struct kvm_cpuid_entry2 __user *entries)
		static bool sanity_check_entries(struct kvm_cpuid_entry2 __user *entries,
		__u32 num_entries, unsigned int ioctl_type)
		{
		int i;

		if (ioctl_type != KVM_GET_EMULATED_CPUID)
		return false;

		/*
		* We want to make sure that ->padding is being passed clean from
		* userspace in case we want to use it for something in the future.
		*
		* Sadly, this wasn't enforced for KVM_GET_SUPPORTED_CPUID and so we
		* have to give ourselves satisfied only with the emulated side. /me
		* sheds a tear.
		*/
		for (i = 0; i < num_entries; i++) {
		if (entries[i].padding[0] \|\|
		entries[i].padding[1] \|\|
		entries[i].padding[2])
		return true;
		}
		return false;
		}

		int kvm_dev_ioctl_get_cpuid(struct kvm_cpuid2 *cpuid,
		struct kvm_cpuid_entry2 __user *entries,
		unsigned int type)
		{
		struct kvm_cpuid_entry2 *cpuid_entries;
		int limit, nent = 0, r = -E2BIG, i;
		@@ -547,6 +588,10 @@ int kvm_dev_ioctl_get_supported_cpuid(struct kvm_cpuid2 *cpuid,
		goto out;
		if (cpuid->nent > KVM_MAX_CPUID_ENTRIES)
		cpuid->nent = KVM_MAX_CPUID_ENTRIES;

		if (sanity_check_entries(entries, cpuid->nent, type))
		return -EINVAL;

		r = -ENOMEM;
		cpuid_entries = vmalloc(sizeof(struct kvm_cpuid_entry2) * cpuid->nent);
		if (!cpuid_entries)
		@@ -560,7 +605,7 @@ int kvm_dev_ioctl_get_supported_cpuid(struct kvm_cpuid2 *cpuid,
		continue;

		r = do_cpuid_ent(&cpuid_entries[nent], ent->func, ent->idx,
		&nent, cpuid->nent);
		&nent, cpuid->nent, type);

		if (r)
		goto out_free;
		@@ -571,7 +616,7 @@ int kvm_dev_ioctl_get_supported_cpuid(struct kvm_cpuid2 *cpuid,
		limit = cpuid_entries[nent - 1].eax;
		for (func = ent->func + 1; func <= limit && nent < cpuid->nent && r == 0; ++func)
		r = do_cpuid_ent(&cpuid_entries[nent], func, ent->idx,
		&nent, cpuid->nent);
		&nent, cpuid->nent, type);

		if (r)
		goto out_free;

arch/x86/kvm/cpuid.h

+3 −2

Original line number	Diff line number	Diff line
		@@ -6,8 +6,9 @@
		void kvm_update_cpuid(struct kvm_vcpu *vcpu);
		struct kvm_cpuid_entry2 kvm_find_cpuid_entry(struct kvm_vcpu vcpu,
		u32 function, u32 index);
		int kvm_dev_ioctl_get_supported_cpuid(struct kvm_cpuid2 *cpuid,
		struct kvm_cpuid_entry2 __user *entries);
		int kvm_dev_ioctl_get_cpuid(struct kvm_cpuid2 *cpuid,
		struct kvm_cpuid_entry2 __user *entries,
		unsigned int type);
		int kvm_vcpu_ioctl_set_cpuid(struct kvm_vcpu *vcpu,
		struct kvm_cpuid *cpuid,
		struct kvm_cpuid_entry __user *entries);

arch/x86/kvm/x86.c

+6 −3

Original line number	Diff line number	Diff line
		@@ -2564,6 +2564,7 @@ int kvm_dev_ioctl_check_extension(long ext)
		case KVM_CAP_MMU_SHADOW_CACHE_CONTROL:
		case KVM_CAP_SET_TSS_ADDR:
		case KVM_CAP_EXT_CPUID:
		case KVM_CAP_EXT_EMUL_CPUID:
		case KVM_CAP_CLOCKSOURCE:
		case KVM_CAP_PIT:
		case KVM_CAP_NOP_IO_DELAY:
		@@ -2673,15 +2674,17 @@ long kvm_arch_dev_ioctl(struct file *filp,
		r = 0;
		break;
		}
		case KVM_GET_SUPPORTED_CPUID: {
		case KVM_GET_SUPPORTED_CPUID:
		case KVM_GET_EMULATED_CPUID: {
		struct kvm_cpuid2 __user *cpuid_arg = argp;
		struct kvm_cpuid2 cpuid;

		r = -EFAULT;
		if (copy_from_user(&cpuid, cpuid_arg, sizeof cpuid))
		goto out;
		r = kvm_dev_ioctl_get_supported_cpuid(&cpuid,
		cpuid_arg->entries);

		r = kvm_dev_ioctl_get_cpuid(&cpuid, cpuid_arg->entries,
		ioctl);
		if (r)
		goto out;

Admin message