[patch v2 6/8] KVM: x86: Implement Intel processor trace context switch

[Luwei Kang <luwei.kang@xxxxxxxxx>]

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,
other MSRs are loaded/stored manaully.

Signed-off-by: Chao Peng <chao.p.peng@xxxxxxxxxxxxxxx>
Signed-off-by: Luwei Kang <luwei.kang@xxxxxxxxx>
---
 arch/x86/kvm/vmx.c | 75 ++++++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 75 insertions(+)

diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 7eaf774..091120e 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -2131,6 +2131,61 @@ static unsigned long segment_base(u16 selector)
 }
 #endif
 
+static inline void pt_load_msr(struct pt_ctx *ctx, unsigned int addr_num)
+{
+	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_num; i++)
+		wrmsrl(MSR_IA32_RTIT_ADDR0_A + i, ctx->addrs[i]);
+}
+
+static inline void pt_save_msr(struct pt_ctx *ctx, unsigned int addr_num)
+{
+	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_num; i++)
+		rdmsrl(MSR_IA32_RTIT_ADDR0_A + i, ctx->addrs[i]);
+}
+
+static void pt_guest_enter(struct vcpu_vmx *vmx)
+{
+	u64 ctl;
+
+	if (pt_mode == PT_MODE_HOST || pt_mode == PT_MODE_HOST_GUEST) {
+		rdmsrl(MSR_IA32_RTIT_CTL, ctl);
+		vmx->pt_desc.host.ctl = ctl;
+		if (ctl & RTIT_CTL_TRACEEN) {
+			ctl &= ~RTIT_CTL_TRACEEN;
+			wrmsrl(MSR_IA32_RTIT_CTL, ctl);
+		}
+	}
+
+	if (pt_mode == PT_MODE_HOST_GUEST) {
+		pt_save_msr(&vmx->pt_desc.host, vmx->pt_desc.addr_num);
+		pt_load_msr(&vmx->pt_desc.guest, vmx->pt_desc.addr_num);
+	}
+}
+
+static void pt_guest_exit(struct vcpu_vmx *vmx)
+{
+	if (pt_mode == PT_MODE_HOST_GUEST) {
+		pt_save_msr(&vmx->pt_desc.guest, vmx->pt_desc.addr_num);
+		pt_load_msr(&vmx->pt_desc.host, vmx->pt_desc.addr_num);
+		wrmsrl(MSR_IA32_RTIT_CTL, vmx->pt_desc.host.ctl);
+	}
+
+	if (pt_mode == PT_MODE_HOST)
+		wrmsrl(MSR_IA32_RTIT_CTL, vmx->pt_desc.host.ctl);
+}
+
 static void vmx_save_host_state(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
@@ -5618,6 +5673,13 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx)
 		vmcs_write16(GUEST_PML_INDEX, PML_ENTITY_NUM - 1);
 	}
 
+	if (pt_mode == PT_MODE_HOST_GUEST) {
+		u32 eax, ebx, ecx, edx;
+
+		cpuid_count(0x14, 1, &eax, &ebx, &ecx, &edx);
+		vmx->pt_desc.addr_num = eax & 0x7;
+	}
+
 	return 0;
 }
 
@@ -5712,6 +5774,15 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
 	update_exception_bitmap(vcpu);
 
 	vpid_sync_context(vmx->vpid);
+
+	if (pt_mode == PT_MODE_HOST_GUEST) {
+		memset(&vmx->pt_desc.host, 0, sizeof(vmx->pt_desc.host));
+		memset(&vmx->pt_desc.guest, 0, sizeof(vmx->pt_desc.guest));
+		/* Bit[6~0] are forced to 1, writes are ignored. */
+		vmx->pt_desc.guest.output_mask = 0x7F;
+		/* Clear the status of IA32_RTIT_CTL in VMCS guest state. */
+		vmcs_write32(GUEST_IA32_RTIT_CTL, 0);
+	}
 }
 
 /*
@@ -9382,6 +9453,8 @@ 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);
 	debugctlmsr = get_debugctlmsr();
 
@@ -9517,6 +9590,8 @@ 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