[PATCH AUTOSEL 4.14 06/21] kvm: x86: Improve emulation of CPUID leaves 0BH and 1FH

[PATCH AUTOSEL 4.14 06/21] kvm: x86: Improve emulation of CPUID leaves 0BH and 1FH

[Sasha Levin]

From: Jim Mattson <jmattson@google.com>

[ Upstream commit 43561123ab3759eb6ff47693aec1a307af0aef83 ]

For these CPUID leaves, the EDX output is not dependent on the ECX
input (i.e. the SIGNIFCANT_INDEX flag doesn't apply to
EDX). Furthermore, the low byte of the ECX output is always identical
to the low byte of the ECX input. KVM does not produce the correct ECX
and EDX outputs for any undefined subleaves beyond the first.

Special-case these CPUID leaves in kvm_cpuid, so that the ECX and EDX
outputs are properly generated for all undefined subleaves.

Fixes: 0771671749b59a ("KVM: Enhance guest cpuid management")
Fixes: a87f2d3a6eadab ("KVM: x86: Add Intel CPUID.1F cpuid emulation support")
Signed-off-by: Jim Mattson <jmattson@google.com>
Reviewed-by: Marc Orr <marcorr@google.com>
Reviewed-by: Peter Shier <pshier@google.com>
Reviewed-by: Jacob Xu <jacobhxu@google.com>
Cc: Sean Christopherson <sean.j.christopherson@intel.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 arch/x86/kvm/cpuid.c | 83 +++++++++++++++++++++++++-------------------
 1 file changed, 47 insertions(+), 36 deletions(-)

diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 5c82b4bc4a68a..f3c49dc423895 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -868,53 +868,64 @@ struct kvm_cpuid_entry2 *kvm_find_cpuid_entry(struct kvm_vcpu *vcpu,
 EXPORT_SYMBOL_GPL(kvm_find_cpuid_entry);
 
 /*
- * If no match is found, check whether we exceed the vCPU's limit
- * and return the content of the highest valid _standard_ leaf instead.
- * This is to satisfy the CPUID specification.
+ * If the basic or extended CPUID leaf requested is higher than the
+ * maximum supported basic or extended leaf, respectively, then it is
+ * out of range.
  */
-static struct kvm_cpuid_entry2* check_cpuid_limit(struct kvm_vcpu *vcpu,
-                                                  u32 function, u32 index)
+static bool cpuid_function_in_range(struct kvm_vcpu *vcpu, u32 function)
 {
-	struct kvm_cpuid_entry2 *maxlevel;
-
-	maxlevel = kvm_find_cpuid_entry(vcpu, function & 0x80000000, 0);
-	if (!maxlevel || maxlevel->eax >= function)
-		return NULL;
-	if (function & 0x80000000) {
-		maxlevel = kvm_find_cpuid_entry(vcpu, 0, 0);
-		if (!maxlevel)
-			return NULL;
-	}
-	return kvm_find_cpuid_entry(vcpu, maxlevel->eax, index);
+	struct kvm_cpuid_entry2 *max;
+
+	max = kvm_find_cpuid_entry(vcpu, function & 0x80000000, 0);
+	return max && function <= max->eax;
 }
 
 bool kvm_cpuid(struct kvm_vcpu *vcpu, u32 *eax, u32 *ebx,
 	       u32 *ecx, u32 *edx, bool check_limit)
 {
 	u32 function = *eax, index = *ecx;
-	struct kvm_cpuid_entry2 *best;
-	bool entry_found = true;
-
-	best = kvm_find_cpuid_entry(vcpu, function, index);
-
-	if (!best) {
-		entry_found = false;
-		if (!check_limit)
-			goto out;
+	struct kvm_cpuid_entry2 *entry;
+	struct kvm_cpuid_entry2 *max;
+	bool found;
 
-		best = check_cpuid_limit(vcpu, function, index);
+	entry = kvm_find_cpuid_entry(vcpu, function, index);
+	found = entry;
+	/*
+	 * Intel CPUID semantics treats any query for an out-of-range
+	 * leaf as if the highest basic leaf (i.e. CPUID.0H:EAX) were
+	 * requested.
+	 */
+	if (!entry && check_limit && !cpuid_function_in_range(vcpu, function)) {
+		max = kvm_find_cpuid_entry(vcpu, 0, 0);
+		if (max) {
+			function = max->eax;
+			entry = kvm_find_cpuid_entry(vcpu, function, index);
+		}
 	}
-
-out:
-	if (best) {
-		*eax = best->eax;
-		*ebx = best->ebx;
-		*ecx = best->ecx;
-		*edx = best->edx;
-	} else
+	if (entry) {
+		*eax = entry->eax;
+		*ebx = entry->ebx;
+		*ecx = entry->ecx;
+		*edx = entry->edx;
+	} else {
 		*eax = *ebx = *ecx = *edx = 0;
-	trace_kvm_cpuid(function, *eax, *ebx, *ecx, *edx, entry_found);
-	return entry_found;
+		/*
+		 * When leaf 0BH or 1FH is defined, CL is pass-through
+		 * and EDX is always the x2APIC ID, even for undefined
+		 * subleaves. Index 1 will exist iff the leaf is
+		 * implemented, so we pass through CL iff leaf 1
+		 * exists. EDX can be copied from any existing index.
+		 */
+		if (function == 0xb || function == 0x1f) {
+			entry = kvm_find_cpuid_entry(vcpu, function, 1);
+			if (entry) {
+				*ecx = index & 0xff;
+				*edx = entry->edx;
+			}
+		}
+	}
+	trace_kvm_cpuid(function, *eax, *ebx, *ecx, *edx, found);
+	return found;
 }
 EXPORT_SYMBOL_GPL(kvm_cpuid);
 
-- 
2.20.1

[PATCH AUTOSEL 4.14 07/21] kvm: x86: Use AMD CPUID semantics for AMD vCPUs

[Sasha Levin]

From: Jim Mattson <jmattson@google.com>

[ Upstream commit 5f41a37b151f6459e0b650a2f4d1d59b6c02d1ab ]

When the guest CPUID information represents an AMD vCPU, return all
zeroes for queries of undefined CPUID leaves, whether or not they are
in range.

Signed-off-by: Jim Mattson <jmattson@google.com>
Fixes: bd22f5cfcfe8f6 ("KVM: move and fix substitue search for missing CPUID entries")
Reviewed-by: Marc Orr <marcorr@google.com>
Reviewed-by: Peter Shier <pshier@google.com>
Reviewed-by: Jacob Xu <jacobhxu@google.com>
Cc: Sean Christopherson <sean.j.christopherson@intel.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 arch/x86/kvm/cpuid.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index f3c49dc423895..3d480ec143284 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -893,9 +893,11 @@ bool kvm_cpuid(struct kvm_vcpu *vcpu, u32 *eax, u32 *ebx,
 	/*
 	 * Intel CPUID semantics treats any query for an out-of-range
 	 * leaf as if the highest basic leaf (i.e. CPUID.0H:EAX) were
-	 * requested.
+	 * requested. AMD CPUID semantics returns all zeroes for any
+	 * undefined leaf, whether or not the leaf is in range.
 	 */
-	if (!entry && check_limit && !cpuid_function_in_range(vcpu, function)) {
+	if (!entry && check_limit && !guest_cpuid_is_amd(vcpu) &&
+	    !cpuid_function_in_range(vcpu, function)) {
 		max = kvm_find_cpuid_entry(vcpu, 0, 0);
 		if (max) {
 			function = max->eax;
-- 
2.20.1

[PATCH AUTOSEL 4.14 13/21] kvm: vmx: Limit guest PMCs to those supported on the host

[Sasha Levin]

From: Jim Mattson <jmattson@google.com>

[ Upstream commit e1fba49cc1e965a3dacd897367ba1e7b340cf0f4 ]

KVM can only virtualize as many PMCs as the host supports.

Limit the number of generic counters and fixed counters to the number
of corresponding counters supported on the host, rather than to
INTEL_PMC_MAX_GENERIC and INTEL_PMC_MAX_FIXED, respectively.

Note that INTEL_PMC_MAX_GENERIC is currently 32, which exceeds the 18
contiguous MSR indices reserved by Intel for event selectors. Since
the existing code relies on a contiguous range of MSR indices for
event selectors, it can't possibly work for more than 18 general
purpose counters.

Fixes: f5132b01386b5a ("KVM: Expose a version 2 architectural PMU to a guests")
Signed-off-by: Jim Mattson <jmattson@google.com>
Reviewed-by: Marc Orr <marcorr@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 arch/x86/kvm/pmu_intel.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/arch/x86/kvm/pmu_intel.c b/arch/x86/kvm/pmu_intel.c
index 2729131fe9bfc..170ca7eeb15b7 100644
--- a/arch/x86/kvm/pmu_intel.c
+++ b/arch/x86/kvm/pmu_intel.c
@@ -260,6 +260,7 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 static void intel_pmu_refresh(struct kvm_vcpu *vcpu)
 {
 	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
+	struct x86_pmu_capability x86_pmu;
 	struct kvm_cpuid_entry2 *entry;
 	union cpuid10_eax eax;
 	union cpuid10_edx edx;
@@ -281,8 +282,10 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu)
 	if (!pmu->version)
 		return;
 
+	perf_get_x86_pmu_capability(&x86_pmu);
+
 	pmu->nr_arch_gp_counters = min_t(int, eax.split.num_counters,
-					INTEL_PMC_MAX_GENERIC);
+					 x86_pmu.num_counters_gp);
 	pmu->counter_bitmask[KVM_PMC_GP] = ((u64)1 << eax.split.bit_width) - 1;
 	pmu->available_event_types = ~entry->ebx &
 					((1ull << eax.split.mask_length) - 1);
@@ -292,7 +295,7 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu)
 	} else {
 		pmu->nr_arch_fixed_counters =
 			min_t(int, edx.split.num_counters_fixed,
-				INTEL_PMC_MAX_FIXED);
+			      x86_pmu.num_counters_fixed);
 		pmu->counter_bitmask[KVM_PMC_FIXED] =
 			((u64)1 << edx.split.bit_width_fixed) - 1;
 	}
-- 
2.20.1