Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull kvm updates from Paolo Bonzini:
 "This is a large update by KVM standards, including AMD PSP (Platform
  Security Processor, aka "AMD Secure Technology") and ARM CoreSight
  (debug and trace) changes.

  ARM:

   - CoreSight: Add support for ETE and TRBE

   - Stage-2 isolation for the host kernel when running in protected
     mode

   - Guest SVE support when running in nVHE mode

   - Force W^X hypervisor mappings in nVHE mode

   - ITS save/restore for guests using direct injection with GICv4.1

   - nVHE panics now produce readable backtraces

   - Guest support for PTP using the ptp_kvm driver

   - Performance improvements in the S2 fault handler

  x86:

   - AMD PSP driver changes

   - Optimizations and cleanup of nested SVM code

   - AMD: Support for virtual SPEC_CTRL

   - Optimizations of the new MMU code: fast invalidation, zap under
     read lock, enable/disably dirty page logging under read lock

   - /dev/kvm API for AMD SEV live migration (guest API coming soon)

   - support SEV virtual machines sharing the same encryption context

   - support SGX in virtual machines

   - add a few more statistics

   - improved directed yield heuristics

   - Lots and lots of cleanups

  Generic:

   - Rework of MMU notifier interface, simplifying and optimizing the
     architecture-specific code

   - a handful of "Get rid of oprofile leftovers" patches

   - Some selftests improvements"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (379 commits)
  KVM: selftests: Speed up set_memory_region_test
  selftests: kvm: Fix the check of return value
  KVM: x86: Take advantage of kvm_arch_dy_has_pending_interrupt()
  KVM: SVM: Skip SEV cache flush if no ASIDs have been used
  KVM: SVM: Remove an unnecessary prototype declaration of sev_flush_asids()
  KVM: SVM: Drop redundant svm_sev_enabled() helper
  KVM: SVM: Move SEV VMCB tracking allocation to sev.c
  KVM: SVM: Explicitly check max SEV ASID during sev_hardware_setup()
  KVM: SVM: Unconditionally invoke sev_hardware_teardown()
  KVM: SVM: Enable SEV/SEV-ES functionality by default (when supported)
  KVM: SVM: Condition sev_enabled and sev_es_enabled on CONFIG_KVM_AMD_SEV=y
  KVM: SVM: Append "_enabled" to module-scoped SEV/SEV-ES control variables
  KVM: SEV: Mask CPUID[0x8000001F].eax according to supported features
  KVM: SVM: Move SEV module params/variables to sev.c
  KVM: SVM: Disable SEV/SEV-ES if NPT is disabled
  KVM: SVM: Free sev_asid_bitmap during init if SEV setup fails
  KVM: SVM: Zero out the VMCB array used to track SEV ASID association
  x86/sev: Drop redundant and potentially misleading 'sev_enabled'
  KVM: x86: Move reverse CPUID helpers to separate header file
  KVM: x86: Rename GPR accessors to make mode-aware variants the defaults
  ...

1 files changed, 90 insertions, 8 deletions

diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index c02466a1410b..19606a341888 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -18,6 +18,7 @@
 #include <asm/processor.h>
 #include <asm/user.h>
 #include <asm/fpu/xstate.h>
+#include <asm/sgx.h>
 #include "cpuid.h"
 #include "lapic.h"
 #include "mmu.h"
@@ -28,7 +29,7 @@
  * Unlike "struct cpuinfo_x86.x86_capability", kvm_cpu_caps doesn't need to be
  * aligned to sizeof(unsigned long) because it's not accessed via bitops.
  */
-u32 kvm_cpu_caps[NCAPINTS] __read_mostly;
+u32 kvm_cpu_caps[NR_KVM_CPU_CAPS] __read_mostly;
 EXPORT_SYMBOL_GPL(kvm_cpu_caps);
 
 static u32 xstate_required_size(u64 xstate_bv, bool compacted)
@@ -53,6 +54,7 @@ static u32 xstate_required_size(u64 xstate_bv, bool compacted)
 }
 
 #define F feature_bit
+#define SF(name) (boot_cpu_has(X86_FEATURE_##name) ? F(name) : 0)
 
 static inline struct kvm_cpuid_entry2 *cpuid_entry2_find(
 	struct kvm_cpuid_entry2 *entries, int nent, u32 function, u32 index)
@@ -170,6 +172,21 @@ static void kvm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu)
 		vcpu->arch.guest_supported_xcr0 =
 			(best->eax | ((u64)best->edx << 32)) & supported_xcr0;
 
+	/*
+	 * Bits 127:0 of the allowed SECS.ATTRIBUTES (CPUID.0x12.0x1) enumerate
+	 * the supported XSAVE Feature Request Mask (XFRM), i.e. the enclave's
+	 * requested XCR0 value.  The enclave's XFRM must be a subset of XCRO
+	 * at the time of EENTER, thus adjust the allowed XFRM by the guest's
+	 * supported XCR0.  Similar to XCR0 handling, FP and SSE are forced to
+	 * '1' even on CPUs that don't support XSAVE.
+	 */
+	best = kvm_find_cpuid_entry(vcpu, 0x12, 0x1);
+	if (best) {
+		best->ecx &= vcpu->arch.guest_supported_xcr0 & 0xffffffff;
+		best->edx &= vcpu->arch.guest_supported_xcr0 >> 32;
+		best->ecx |= XFEATURE_MASK_FPSSE;
+	}
+
 	kvm_update_pv_runtime(vcpu);
 
 	vcpu->arch.maxphyaddr = cpuid_query_maxphyaddr(vcpu);
@@ -347,13 +364,13 @@ out:
 	return r;
 }
 
-static __always_inline void kvm_cpu_cap_mask(enum cpuid_leafs leaf, u32 mask)
+/* Mask kvm_cpu_caps for @leaf with the raw CPUID capabilities of this CPU. */
+static __always_inline void __kvm_cpu_cap_mask(unsigned int leaf)
 {
 	const struct cpuid_reg cpuid = x86_feature_cpuid(leaf * 32);
 	struct kvm_cpuid_entry2 entry;
 
 	reverse_cpuid_check(leaf);
-	kvm_cpu_caps[leaf] &= mask;
 
 	cpuid_count(cpuid.function, cpuid.index,
 		    &entry.eax, &entry.ebx, &entry.ecx, &entry.edx);
@@ -361,6 +378,27 @@ static __always_inline void kvm_cpu_cap_mask(enum cpuid_leafs leaf, u32 mask)
 	kvm_cpu_caps[leaf] &= *__cpuid_entry_get_reg(&entry, cpuid.reg);
 }
 
+static __always_inline
+void kvm_cpu_cap_init_scattered(enum kvm_only_cpuid_leafs leaf, u32 mask)
+{
+	/* Use kvm_cpu_cap_mask for non-scattered leafs. */
+	BUILD_BUG_ON(leaf < NCAPINTS);
+
+	kvm_cpu_caps[leaf] = mask;
+
+	__kvm_cpu_cap_mask(leaf);
+}
+
+static __always_inline void kvm_cpu_cap_mask(enum cpuid_leafs leaf, u32 mask)
+{
+	/* Use kvm_cpu_cap_init_scattered for scattered leafs. */
+	BUILD_BUG_ON(leaf >= NCAPINTS);
+
+	kvm_cpu_caps[leaf] &= mask;
+
+	__kvm_cpu_cap_mask(leaf);
+}
+
 void kvm_set_cpu_caps(void)
 {
 	unsigned int f_nx = is_efer_nx() ? F(NX) : 0;
@@ -371,12 +409,13 @@ void kvm_set_cpu_caps(void)
 	unsigned int f_gbpages = 0;
 	unsigned int f_lm = 0;
 #endif
+	memset(kvm_cpu_caps, 0, sizeof(kvm_cpu_caps));
 
-	BUILD_BUG_ON(sizeof(kvm_cpu_caps) >
+	BUILD_BUG_ON(sizeof(kvm_cpu_caps) - (NKVMCAPINTS * sizeof(*kvm_cpu_caps)) >
 		     sizeof(boot_cpu_data.x86_capability));
 
 	memcpy(&kvm_cpu_caps, &boot_cpu_data.x86_capability,
-	       sizeof(kvm_cpu_caps));
+	       sizeof(kvm_cpu_caps) - (NKVMCAPINTS * sizeof(*kvm_cpu_caps)));
 
 	kvm_cpu_cap_mask(CPUID_1_ECX,
 		/*
@@ -407,7 +446,7 @@ void kvm_set_cpu_caps(void)
 	);
 
 	kvm_cpu_cap_mask(CPUID_7_0_EBX,
-		F(FSGSBASE) | F(BMI1) | F(HLE) | F(AVX2) | F(SMEP) |
+		F(FSGSBASE) | F(SGX) | F(BMI1) | F(HLE) | F(AVX2) | F(SMEP) |
 		F(BMI2) | F(ERMS) | F(INVPCID) | F(RTM) | 0 /*MPX*/ | F(RDSEED) |
 		F(ADX) | F(SMAP) | F(AVX512IFMA) | F(AVX512F) | F(AVX512PF) |
 		F(AVX512ER) | F(AVX512CD) | F(CLFLUSHOPT) | F(CLWB) | F(AVX512DQ) |
@@ -418,7 +457,8 @@ void kvm_set_cpu_caps(void)
 		F(AVX512VBMI) | F(LA57) | F(PKU) | 0 /*OSPKE*/ | F(RDPID) |
 		F(AVX512_VPOPCNTDQ) | F(UMIP) | F(AVX512_VBMI2) | F(GFNI) |
 		F(VAES) | F(VPCLMULQDQ) | F(AVX512_VNNI) | F(AVX512_BITALG) |
-		F(CLDEMOTE) | F(MOVDIRI) | F(MOVDIR64B) | 0 /*WAITPKG*/
+		F(CLDEMOTE) | F(MOVDIRI) | F(MOVDIR64B) | 0 /*WAITPKG*/ |
+		F(SGX_LC)
 	);
 	/* Set LA57 based on hardware capability. */
 	if (cpuid_ecx(7) & F(LA57))
@@ -457,6 +497,10 @@ void kvm_set_cpu_caps(void)
 		F(XSAVEOPT) | F(XSAVEC) | F(XGETBV1) | F(XSAVES)
 	);
 
+	kvm_cpu_cap_init_scattered(CPUID_12_EAX,
+		SF(SGX1) | SF(SGX2)
+	);
+
 	kvm_cpu_cap_mask(CPUID_8000_0001_ECX,
 		F(LAHF_LM) | F(CMP_LEGACY) | 0 /*SVM*/ | 0 /* ExtApicSpace */ |
 		F(CR8_LEGACY) | F(ABM) | F(SSE4A) | F(MISALIGNSSE) |
@@ -514,6 +558,10 @@ void kvm_set_cpu_caps(void)
 	 */
 	kvm_cpu_cap_mask(CPUID_8000_000A_EDX, 0);
 
+	kvm_cpu_cap_mask(CPUID_8000_001F_EAX,
+		0 /* SME */ | F(SEV) | 0 /* VM_PAGE_FLUSH */ | F(SEV_ES) |
+		F(SME_COHERENT));
+
 	kvm_cpu_cap_mask(CPUID_C000_0001_EDX,
 		F(XSTORE) | F(XSTORE_EN) | F(XCRYPT) | F(XCRYPT_EN) |
 		F(ACE2) | F(ACE2_EN) | F(PHE) | F(PHE_EN) |
@@ -778,6 +826,38 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function)
 			entry->edx = 0;
 		}
 		break;
+	case 0x12:
+		/* Intel SGX */
+		if (!kvm_cpu_cap_has(X86_FEATURE_SGX)) {
+			entry->eax = entry->ebx = entry->ecx = entry->edx = 0;
+			break;
+		}
+
+		/*
+		 * Index 0: Sub-features, MISCSELECT (a.k.a extended features)
+		 * and max enclave sizes.   The SGX sub-features and MISCSELECT
+		 * are restricted by kernel and KVM capabilities (like most
+		 * feature flags), while enclave size is unrestricted.
+		 */
+		cpuid_entry_override(entry, CPUID_12_EAX);
+		entry->ebx &= SGX_MISC_EXINFO;
+
+		entry = do_host_cpuid(array, function, 1);
+		if (!entry)
+			goto out;
+
+		/*
+		 * Index 1: SECS.ATTRIBUTES.  ATTRIBUTES are restricted a la
+		 * feature flags.  Advertise all supported flags, including
+		 * privileged attributes that require explicit opt-in from
+		 * userspace.  ATTRIBUTES.XFRM is not adjusted as userspace is
+		 * expected to derive it from supported XCR0.
+		 */
+		entry->eax &= SGX_ATTR_DEBUG | SGX_ATTR_MODE64BIT |
+			      SGX_ATTR_PROVISIONKEY | SGX_ATTR_EINITTOKENKEY |
+			      SGX_ATTR_KSS;
+		entry->ebx &= 0;
+		break;
 	/* Intel PT */
 	case 0x14:
 		if (!kvm_cpu_cap_has(X86_FEATURE_INTEL_PT)) {
@@ -869,8 +949,10 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function)
 		break;
 	/* Support memory encryption cpuid if host supports it */
 	case 0x8000001F:
-		if (!boot_cpu_has(X86_FEATURE_SEV))
+		if (!kvm_cpu_cap_has(X86_FEATURE_SEV))
 			entry->eax = entry->ebx = entry->ecx = entry->edx = 0;
+		else
+			cpuid_entry_override(entry, CPUID_8000_001F_EAX);
 		break;
 	/*Add support for Centaur's CPUID instruction*/
 	case 0xC0000000: