Received-SPF: pass (google.com: domain of linux-kernel+bounces-80801-linux.lists.archive=gmail.com@vger.kernel.org designates 2604:1380:4601:e00::3 as permitted sender) client-ip=2604:1380:4601:e00::3;
From: isaku.yamahata@intel.com
To: kvm@vger.kernel.org,
	linux-kernel@vger.kernel.org
Cc: isaku.yamahata@intel.com,
	isaku.yamahata@gmail.com,
	Paolo Bonzini <pbonzini@redhat.com>,
	erdemaktas@google.com,
	Sean Christopherson <seanjc@google.com>,
	Sagi Shahar <sagis@google.com>,
	Kai Huang <kai.huang@intel.com>,
	chen.bo@intel.com,
	hang.yuan@intel.com,
	tina.zhang@intel.com
Subject: [PATCH v19 040/130] KVM: TDX: Make pmu_intel.c ignore guest TD case
Date: Mon, 26 Feb 2024 00:25:42 -0800
Message-Id: <2eb2e7205d23ec858e6d800fee7da2306216e8f0.1708933498.git.isaku.yamahata@intel.com>
In-Reply-To: <cover.1708933498.git.isaku.yamahata@intel.com>
References: <cover.1708933498.git.isaku.yamahata@intel.com>
Precedence: bulk
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit

From: Isaku Yamahata <isaku.yamahata@intel.com>

Because TDX KVM doesn't support PMU yet (it's future work of TDX KVM
support as another patch series) and pmu_intel.c touches vmx specific
structure in vcpu initialization, as workaround add dummy structure to
struct vcpu_tdx and pmu_intel.c can ignore TDX case.

Signed-off-by: Isaku Yamahata <isaku.yamahata@intel.com>
---
v18:
- Removed unnecessary change to vmx.c which caused kernel warning.
---
 arch/x86/kvm/vmx/pmu_intel.c | 46 +++++++++++++++++++++++++++++++++++-
 arch/x86/kvm/vmx/pmu_intel.h | 28 ++++++++++++++++++++++
 arch/x86/kvm/vmx/tdx.h       |  8 ++++++-
 arch/x86/kvm/vmx/vmx.h       | 32 +------------------------
 4 files changed, 81 insertions(+), 33 deletions(-)
 create mode 100644 arch/x86/kvm/vmx/pmu_intel.h

diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c
index 315c7c2ba89b..7e6e51efd879 100644
--- a/arch/x86/kvm/vmx/pmu_intel.c
+++ b/arch/x86/kvm/vmx/pmu_intel.c
@@ -19,6 +19,7 @@
 #include "lapic.h"
 #include "nested.h"
 #include "pmu.h"
+#include "tdx.h"
 
 #define MSR_PMC_FULL_WIDTH_BIT      (MSR_IA32_PMC0 - MSR_IA32_PERFCTR0)
 
@@ -68,6 +69,26 @@ static int fixed_pmc_events[] = {
 	[2] = PSEUDO_ARCH_REFERENCE_CYCLES,
 };
 
+struct lbr_desc *vcpu_to_lbr_desc(struct kvm_vcpu *vcpu)
+{
+#ifdef CONFIG_INTEL_TDX_HOST
+	if (is_td_vcpu(vcpu))
+		return &to_tdx(vcpu)->lbr_desc;
+#endif
+
+	return &to_vmx(vcpu)->lbr_desc;
+}
+
+struct x86_pmu_lbr *vcpu_to_lbr_records(struct kvm_vcpu *vcpu)
+{
+#ifdef CONFIG_INTEL_TDX_HOST
+	if (is_td_vcpu(vcpu))
+		return &to_tdx(vcpu)->lbr_desc.records;
+#endif
+
+	return &to_vmx(vcpu)->lbr_desc.records;
+}
+
 static void reprogram_fixed_counters(struct kvm_pmu *pmu, u64 data)
 {
 	struct kvm_pmc *pmc;
@@ -179,6 +200,23 @@ static inline struct kvm_pmc *get_fw_gp_pmc(struct kvm_pmu *pmu, u32 msr)
 	return get_gp_pmc(pmu, msr, MSR_IA32_PMC0);
 }
 
+bool intel_pmu_lbr_is_compatible(struct kvm_vcpu *vcpu)
+{
+	if (is_td_vcpu(vcpu))
+		return false;
+	return cpuid_model_is_consistent(vcpu);
+}
+
+bool intel_pmu_lbr_is_enabled(struct kvm_vcpu *vcpu)
+{
+	struct x86_pmu_lbr *lbr = vcpu_to_lbr_records(vcpu);
+
+	if (is_td_vcpu(vcpu))
+		return false;
+
+	return lbr->nr && (vcpu_get_perf_capabilities(vcpu) & PMU_CAP_LBR_FMT);
+}
+
 static bool intel_pmu_is_valid_lbr_msr(struct kvm_vcpu *vcpu, u32 index)
 {
 	struct x86_pmu_lbr *records = vcpu_to_lbr_records(vcpu);
@@ -244,6 +282,9 @@ static inline void intel_pmu_release_guest_lbr_event(struct kvm_vcpu *vcpu)
 {
 	struct lbr_desc *lbr_desc = vcpu_to_lbr_desc(vcpu);
 
+	if (is_td_vcpu(vcpu))
+		return;
+
 	if (lbr_desc->event) {
 		perf_event_release_kernel(lbr_desc->event);
 		lbr_desc->event = NULL;
@@ -285,6 +326,9 @@ int intel_pmu_create_guest_lbr_event(struct kvm_vcpu *vcpu)
 					PERF_SAMPLE_BRANCH_USER,
 	};
 
+	if (WARN_ON_ONCE(is_td_vcpu(vcpu)))
+		return 0;
+
 	if (unlikely(lbr_desc->event)) {
 		__set_bit(INTEL_PMC_IDX_FIXED_VLBR, pmu->pmc_in_use);
 		return 0;
@@ -578,7 +622,7 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu)
 		INTEL_PMC_MAX_GENERIC, pmu->nr_arch_fixed_counters);
 
 	perf_capabilities = vcpu_get_perf_capabilities(vcpu);
-	if (cpuid_model_is_consistent(vcpu) &&
+	if (intel_pmu_lbr_is_compatible(vcpu) &&
 	    (perf_capabilities & PMU_CAP_LBR_FMT))
 		x86_perf_get_lbr(&lbr_desc->records);
 	else
diff --git a/arch/x86/kvm/vmx/pmu_intel.h b/arch/x86/kvm/vmx/pmu_intel.h
new file mode 100644
index 000000000000..66bba47c1269
--- /dev/null
+++ b/arch/x86/kvm/vmx/pmu_intel.h
@@ -0,0 +1,28 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __KVM_X86_VMX_PMU_INTEL_H
+#define  __KVM_X86_VMX_PMU_INTEL_H
+
+struct lbr_desc *vcpu_to_lbr_desc(struct kvm_vcpu *vcpu);
+struct x86_pmu_lbr *vcpu_to_lbr_records(struct kvm_vcpu *vcpu);
+
+bool intel_pmu_lbr_is_compatible(struct kvm_vcpu *vcpu);
+bool intel_pmu_lbr_is_enabled(struct kvm_vcpu *vcpu);
+int intel_pmu_create_guest_lbr_event(struct kvm_vcpu *vcpu);
+
+struct lbr_desc {
+	/* Basic info about guest LBR records. */
+	struct x86_pmu_lbr records;
+
+	/*
+	 * Emulate LBR feature via passthrough LBR registers when the
+	 * per-vcpu guest LBR event is scheduled on the current pcpu.
+	 *
+	 * The records may be inaccurate if the host reclaims the LBR.
+	 */
+	struct perf_event *event;
+
+	/* True if LBRs are marked as not intercepted in the MSR bitmap */
+	bool msr_passthrough;
+};
+
+#endif /* __KVM_X86_VMX_PMU_INTEL_H */
diff --git a/arch/x86/kvm/vmx/tdx.h b/arch/x86/kvm/vmx/tdx.h
index 184fe394da86..173ed19207fb 100644
--- a/arch/x86/kvm/vmx/tdx.h
+++ b/arch/x86/kvm/vmx/tdx.h
@@ -4,6 +4,7 @@
 
 #ifdef CONFIG_INTEL_TDX_HOST
 
+#include "pmu_intel.h"
 #include "tdx_ops.h"
 
 struct kvm_tdx {
@@ -21,7 +22,12 @@ struct kvm_tdx {
 
 struct vcpu_tdx {
 	struct kvm_vcpu	vcpu;
-	/* TDX specific members follow. */
+
+	/*
+	 * Dummy to make pmu_intel not corrupt memory.
+	 * TODO: Support PMU for TDX.  Future work.
+	 */
+	struct lbr_desc lbr_desc;
 };
 
 static inline bool is_td(struct kvm *kvm)
diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h
index e3b0985bb74a..04ed2a9eada1 100644
--- a/arch/x86/kvm/vmx/vmx.h
+++ b/arch/x86/kvm/vmx/vmx.h
@@ -11,6 +11,7 @@
 #include "capabilities.h"
 #include "../kvm_cache_regs.h"
 #include "posted_intr.h"
+#include "pmu_intel.h"
 #include "vmcs.h"
 #include "vmx_ops.h"
 #include "../cpuid.h"
@@ -93,22 +94,6 @@ union vmx_exit_reason {
 	u32 full;
 };
 
-struct lbr_desc {
-	/* Basic info about guest LBR records. */
-	struct x86_pmu_lbr records;
-
-	/*
-	 * Emulate LBR feature via passthrough LBR registers when the
-	 * per-vcpu guest LBR event is scheduled on the current pcpu.
-	 *
-	 * The records may be inaccurate if the host reclaims the LBR.
-	 */
-	struct perf_event *event;
-
-	/* True if LBRs are marked as not intercepted in the MSR bitmap */
-	bool msr_passthrough;
-};
-
 /*
  * The nested_vmx structure is part of vcpu_vmx, and holds information we need
  * for correct emulation of VMX (i.e., nested VMX) on this vcpu.
@@ -659,21 +644,6 @@ static __always_inline struct vcpu_vmx *to_vmx(struct kvm_vcpu *vcpu)
 	return container_of(vcpu, struct vcpu_vmx, vcpu);
 }
 
-static inline struct lbr_desc *vcpu_to_lbr_desc(struct kvm_vcpu *vcpu)
-{
-	return &to_vmx(vcpu)->lbr_desc;
-}
-
-static inline struct x86_pmu_lbr *vcpu_to_lbr_records(struct kvm_vcpu *vcpu)
-{
-	return &vcpu_to_lbr_desc(vcpu)->records;
-}
-
-static inline bool intel_pmu_lbr_is_enabled(struct kvm_vcpu *vcpu)
-{
-	return !!vcpu_to_lbr_records(vcpu)->nr;
-}
-
 void intel_pmu_cross_mapped_check(struct kvm_pmu *pmu);
 int intel_pmu_create_guest_lbr_event(struct kvm_vcpu *vcpu);
 void vmx_passthrough_lbr_msrs(struct kvm_vcpu *vcpu);
-- 
2.25.1