Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
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>,
        David Matlack <dmatlack@google.com>,
        Kai Huang <kai.huang@intel.com>,
        Zhi Wang <zhi.wang.linux@gmail.com>, chen.bo@intel.com,
        hang.yuan@intel.com, tina.zhang@intel.com,
        Yang Weijiang <weijiang.yang@intel.com>
Subject: [PATCH v15 068/115] KVM: TDX: Add TSX_CTRL msr into uret_msrs list
Date:   Tue, 25 Jul 2023 15:14:19 -0700
Message-Id: <6c2d9c76d58cd511e2a271014d6e04eecea45cca.1690322424.git.isaku.yamahata@intel.com>
In-Reply-To: <cover.1690322424.git.isaku.yamahata@intel.com>
References: <cover.1690322424.git.isaku.yamahata@intel.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

From: Yang Weijiang <weijiang.yang@intel.com>

TDX module resets the TSX_CTRL MSR to 0 at TD exit if TSX is enabled for
TD. Or it preserves the TSX_CTRL MSR if TSX is disabled for TD.  VMM can
rely on uret_msrs mechanism to defer the reload of host value until exiting
to user space.

Signed-off-by: Yang Weijiang <weijiang.yang@intel.com>
Signed-off-by: Isaku Yamahata <isaku.yamahata@intel.com>
---
 arch/x86/kvm/vmx/tdx.c | 33 +++++++++++++++++++++++++++++++--
 arch/x86/kvm/vmx/tdx.h |  8 ++++++++
 2 files changed, 39 insertions(+), 2 deletions(-)

diff --git a/arch/x86/kvm/vmx/tdx.c b/arch/x86/kvm/vmx/tdx.c
index 05657e51406a..1ae72c84d40e 100644
--- a/arch/x86/kvm/vmx/tdx.c
+++ b/arch/x86/kvm/vmx/tdx.c
@@ -496,14 +496,21 @@ static struct tdx_uret_msr tdx_uret_msrs[] = {
 	{.msr = MSR_LSTAR,},
 	{.msr = MSR_TSC_AUX,},
 };
+static unsigned int tdx_uret_tsx_ctrl_slot;
 
-static void tdx_user_return_update_cache(void)
+static void tdx_user_return_update_cache(struct kvm_vcpu *vcpu)
 {
 	int i;
 
 	for (i = 0; i < ARRAY_SIZE(tdx_uret_msrs); i++)
 		kvm_user_return_update_cache(tdx_uret_msrs[i].slot,
 					     tdx_uret_msrs[i].defval);
+	/*
+	 * TSX_CTRL is reset to 0 if guest TSX is supported. Otherwise
+	 * preserved.
+	 */
+	if (to_kvm_tdx(vcpu->kvm)->tsx_supported && tdx_uret_tsx_ctrl_slot != -1)
+		kvm_user_return_update_cache(tdx_uret_tsx_ctrl_slot, 0);
 }
 
 static void tdx_restore_host_xsave_state(struct kvm_vcpu *vcpu)
@@ -547,7 +554,7 @@ fastpath_t tdx_vcpu_run(struct kvm_vcpu *vcpu)
 
 	tdx_vcpu_enter_exit(vcpu, tdx);
 
-	tdx_user_return_update_cache();
+	tdx_user_return_update_cache(vcpu);
 	tdx_restore_host_xsave_state(vcpu);
 	tdx->host_state_need_restore = true;
 
@@ -1050,6 +1057,22 @@ static int setup_tdparams_xfam(struct kvm_cpuid2 *cpuid, struct td_params *td_pa
 	return 0;
 }
 
+static bool tdparams_tsx_supported(struct kvm_cpuid2 *cpuid)
+{
+	const struct kvm_cpuid_entry2 *entry;
+	u64 mask;
+	u32 ebx;
+
+	entry = kvm_find_cpuid_entry2(cpuid->entries, cpuid->nent, 0x7, 0);
+	if (entry)
+		ebx = entry->ebx;
+	else
+		ebx = 0;
+
+	mask = __feature_bit(X86_FEATURE_HLE) | __feature_bit(X86_FEATURE_RTM);
+	return ebx & mask;
+}
+
 static int setup_tdparams(struct kvm *kvm, struct td_params *td_params,
 			struct kvm_tdx_init_vm *init_vm)
 {
@@ -1095,6 +1118,7 @@ static int setup_tdparams(struct kvm *kvm, struct td_params *td_params,
 	MEMCPY_SAME_SIZE(td_params->mrowner, init_vm->mrowner);
 	MEMCPY_SAME_SIZE(td_params->mrownerconfig, init_vm->mrownerconfig);
 
+	to_kvm_tdx(kvm)->tsx_supported = tdparams_tsx_supported(cpuid);
 	return 0;
 }
 
@@ -1760,6 +1784,11 @@ int __init tdx_hardware_setup(struct kvm_x86_ops *x86_ops)
 			return -EIO;
 		}
 	}
+	tdx_uret_tsx_ctrl_slot = kvm_find_user_return_msr(MSR_IA32_TSX_CTRL);
+	if (tdx_uret_tsx_ctrl_slot == -1 && boot_cpu_has(X86_FEATURE_MSR_TSX_CTRL)) {
+		pr_err("MSR_IA32_TSX_CTRL isn't included by kvm_find_user_return_msr\n");
+		return -EIO;
+	}
 
 	max_pkgs = topology_max_packages();
 	tdx_mng_key_config_lock = kcalloc(max_pkgs, sizeof(*tdx_mng_key_config_lock),
diff --git a/arch/x86/kvm/vmx/tdx.h b/arch/x86/kvm/vmx/tdx.h
index a3c64a2ec9e0..98c8d07723a1 100644
--- a/arch/x86/kvm/vmx/tdx.h
+++ b/arch/x86/kvm/vmx/tdx.h
@@ -17,6 +17,14 @@ struct kvm_tdx {
 	u64 xfam;
 	int hkid;
 
+	/*
+	 * Used on each TD-exit, see tdx_user_return_update_cache().
+	 * TSX_CTRL value on TD exit
+	 * - set 0     if guest TSX enabled
+	 * - preserved if guest TSX disabled
+	 */
+	bool tsx_supported;
+
 	hpa_t source_pa;
 
 	bool finalized;
-- 
2.25.1