[PATCH v13 08/12] KVM: x86: Add Intel PT context switch for each vcpu

[Luwei Kang]

From: Chao Peng <chao.p.peng@xxxxxxxxxxxxxxx>

Load/Store Intel Processor Trace register in context switch.
MSR IA32_RTIT_CTL is loaded/stored automatically from VMCS.
In Host-Guest mode, we need load/resore PT MSRs only when PT
is enabled in guest.

Signed-off-by: Chao Peng <chao.p.peng@xxxxxxxxxxxxxxx>
Signed-off-by: Luwei Kang <luwei.kang@xxxxxxxxx>
---
 arch/x86/include/asm/intel_pt.h |  2 +
 arch/x86/kvm/vmx.c              | 94 +++++++++++++++++++++++++++++++++++++++++
 2 files changed, 96 insertions(+)

diff --git a/arch/x86/include/asm/intel_pt.h b/arch/x86/include/asm/intel_pt.h
index 4727584..eabbdbc 100644
--- a/arch/x86/include/asm/intel_pt.h
+++ b/arch/x86/include/asm/intel_pt.h
@@ -8,6 +8,8 @@
 #define PT_MODE_SYSTEM		0
 #define PT_MODE_HOST_GUEST	1
 
+#define RTIT_ADDR_RANGE		4
+
 enum pt_capabilities {
 	PT_CAP_max_subleaf = 0,
 	PT_CAP_cr3_filtering,
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 692154c..d8480a6 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -978,6 +978,24 @@ struct vmx_msrs {
 	struct vmx_msr_entry	val[NR_AUTOLOAD_MSRS];
 };
 
+struct pt_ctx {
+	u64 ctl;
+	u64 status;
+	u64 output_base;
+	u64 output_mask;
+	u64 cr3_match;
+	u64 addr_a[RTIT_ADDR_RANGE];
+	u64 addr_b[RTIT_ADDR_RANGE];
+};
+
+struct pt_desc {
+	u64 ctl_bitmask;
+	u32 addr_range;
+	u32 caps[PT_CPUID_REGS_NUM * PT_CPUID_LEAVES];
+	struct pt_ctx host;
+	struct pt_ctx guest;
+};
+
 struct vcpu_vmx {
 	struct kvm_vcpu       vcpu;
 	unsigned long         host_rsp;
@@ -1071,6 +1089,8 @@ struct vcpu_vmx {
 	u64 msr_ia32_feature_control;
 	u64 msr_ia32_feature_control_valid_bits;
 	u64 ept_pointer;
+
+	struct pt_desc pt_desc;
 };
 
 enum segment_cache_field {
@@ -2899,6 +2919,69 @@ static unsigned long segment_base(u16 selector)
 }
 #endif
 
+static inline void pt_load_msr(struct pt_ctx *ctx, u32 addr_range)
+{
+	u32 i;
+
+	wrmsrl(MSR_IA32_RTIT_STATUS, ctx->status);
+	wrmsrl(MSR_IA32_RTIT_OUTPUT_BASE, ctx->output_base);
+	wrmsrl(MSR_IA32_RTIT_OUTPUT_MASK, ctx->output_mask);
+	wrmsrl(MSR_IA32_RTIT_CR3_MATCH, ctx->cr3_match);
+	for (i = 0; i < addr_range; i++) {
+		wrmsrl(MSR_IA32_RTIT_ADDR0_A + i * 2, ctx->addr_a[i]);
+		wrmsrl(MSR_IA32_RTIT_ADDR0_B + i * 2, ctx->addr_b[i]);
+	}
+}
+
+static inline void pt_save_msr(struct pt_ctx *ctx, u32 addr_range)
+{
+	u32 i;
+
+	rdmsrl(MSR_IA32_RTIT_STATUS, ctx->status);
+	rdmsrl(MSR_IA32_RTIT_OUTPUT_BASE, ctx->output_base);
+	rdmsrl(MSR_IA32_RTIT_OUTPUT_MASK, ctx->output_mask);
+	rdmsrl(MSR_IA32_RTIT_CR3_MATCH, ctx->cr3_match);
+	for (i = 0; i < addr_range; i++) {
+		rdmsrl(MSR_IA32_RTIT_ADDR0_A + i * 2, ctx->addr_a[i]);
+		rdmsrl(MSR_IA32_RTIT_ADDR0_B + i * 2, ctx->addr_b[i]);
+	}
+}
+
+static void pt_guest_enter(struct vcpu_vmx *vmx)
+{
+	if (pt_mode == PT_MODE_SYSTEM)
+		return;
+
+	/* Save host state before VM entry */
+	rdmsrl(MSR_IA32_RTIT_CTL, vmx->pt_desc.host.ctl);
+
+	/*
+	 * Set guest state of MSR_IA32_RTIT_CTL MSR (PT will be disabled
+	 * on VM entry when it has been disabled in guest before).
+	 */
+	vmcs_write64(GUEST_IA32_RTIT_CTL, vmx->pt_desc.guest.ctl);
+
+	if (vmx->pt_desc.guest.ctl & RTIT_CTL_TRACEEN) {
+		wrmsrl(MSR_IA32_RTIT_CTL, 0);
+		pt_save_msr(&vmx->pt_desc.host, vmx->pt_desc.addr_range);
+		pt_load_msr(&vmx->pt_desc.guest, vmx->pt_desc.addr_range);
+	}
+}
+
+static void pt_guest_exit(struct vcpu_vmx *vmx)
+{
+	if (pt_mode == PT_MODE_SYSTEM)
+		return;
+
+	if (vmx->pt_desc.guest.ctl & RTIT_CTL_TRACEEN) {
+		pt_save_msr(&vmx->pt_desc.guest, vmx->pt_desc.addr_range);
+		pt_load_msr(&vmx->pt_desc.host, vmx->pt_desc.addr_range);
+	}
+
+	/* Reload host state (IA32_RTIT_CTL will be cleared on VM exit). */
+	wrmsrl(MSR_IA32_RTIT_CTL, vmx->pt_desc.host.ctl);
+}
+
 static void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
@@ -6749,6 +6832,13 @@ static void vmx_vcpu_setup(struct vcpu_vmx *vmx)
 
 	if (cpu_has_vmx_encls_vmexit())
 		vmcs_write64(ENCLS_EXITING_BITMAP, -1ull);
+
+	if (pt_mode == PT_MODE_HOST_GUEST) {
+		memset(&vmx->pt_desc, 0, sizeof(vmx->pt_desc));
+		/* Bit[6~0] are forced to 1, writes are ignored. */
+		vmx->pt_desc.guest.output_mask = 0x7F;
+		vmcs_write64(GUEST_IA32_RTIT_CTL, 0);
+	}
 }
 
 static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
@@ -11260,6 +11350,8 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
 	    vcpu->arch.pkru != vmx->host_pkru)
 		__write_pkru(vcpu->arch.pkru);
 
+	pt_guest_enter(vmx);
+
 	atomic_switch_perf_msrs(vmx);
 
 	vmx_update_hv_timer(vcpu);
@@ -11459,6 +11551,8 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
 				  | (1 << VCPU_EXREG_CR3));
 	vcpu->arch.regs_dirty = 0;
 
+	pt_guest_exit(vmx);
+
 	/*
 	 * eager fpu is enabled if PKEY is supported and CR4 is switched
 	 * back on host, so it is safe to read guest PKRU from current
-- 
1.8.3.1