Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::3:5 as permitted sender) client-ip=2620:137:e000::3:5;
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
Subject: [PATCH v16 063/116] KVM: TDX: vcpu_run: save/restore host state(host kernel gs)
Date:   Mon, 16 Oct 2023 09:14:15 -0700
Message-Id: <a4897b3ef5480f12ecedda3867b4a968ca4ddf6d.1697471314.git.isaku.yamahata@intel.com>
In-Reply-To: <cover.1697471314.git.isaku.yamahata@intel.com>
References: <cover.1697471314.git.isaku.yamahata@intel.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

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

On entering/exiting TDX vcpu, Preserved or clobbered CPU state is different
from VMX case.  Add TDX hooks to save/restore host/guest CPU state.
Save/restore kernel GS base MSR.

Signed-off-by: Isaku Yamahata <isaku.yamahata@intel.com>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/vmx/main.c    | 30 +++++++++++++++++++++++++--
 arch/x86/kvm/vmx/tdx.c     | 42 ++++++++++++++++++++++++++++++++++++++
 arch/x86/kvm/vmx/tdx.h     |  4 ++++
 arch/x86/kvm/vmx/x86_ops.h |  4 ++++
 4 files changed, 78 insertions(+), 2 deletions(-)

diff --git a/arch/x86/kvm/vmx/main.c b/arch/x86/kvm/vmx/main.c
index c45b8fc3e8d3..bc75ed8ff371 100644
--- a/arch/x86/kvm/vmx/main.c
+++ b/arch/x86/kvm/vmx/main.c
@@ -169,6 +169,32 @@ static void vt_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
 	vmx_vcpu_reset(vcpu, init_event);
 }
 
+static void vt_prepare_switch_to_guest(struct kvm_vcpu *vcpu)
+{
+	/*
+	 * All host state is saved/restored across SEAMCALL/SEAMRET, and the
+	 * guest state of a TD is obviously off limits.  Deferring MSRs and DRs
+	 * is pointless because the TDX module needs to load *something* so as
+	 * not to expose guest state.
+	 */
+	if (is_td_vcpu(vcpu)) {
+		tdx_prepare_switch_to_guest(vcpu);
+		return;
+	}
+
+	vmx_prepare_switch_to_guest(vcpu);
+}
+
+static void vt_vcpu_put(struct kvm_vcpu *vcpu)
+{
+	if (is_td_vcpu(vcpu)) {
+		tdx_vcpu_put(vcpu);
+		return;
+	}
+
+	vmx_vcpu_put(vcpu);
+}
+
 static int vt_vcpu_pre_run(struct kvm_vcpu *vcpu)
 {
 	if (is_td_vcpu(vcpu))
@@ -304,9 +330,9 @@ struct kvm_x86_ops vt_x86_ops __initdata = {
 	.vcpu_free = vt_vcpu_free,
 	.vcpu_reset = vt_vcpu_reset,
 
-	.prepare_switch_to_guest = vmx_prepare_switch_to_guest,
+	.prepare_switch_to_guest = vt_prepare_switch_to_guest,
 	.vcpu_load = vmx_vcpu_load,
-	.vcpu_put = vmx_vcpu_put,
+	.vcpu_put = vt_vcpu_put,
 
 	.update_exception_bitmap = vmx_update_exception_bitmap,
 	.get_msr_feature = vmx_get_msr_feature,
diff --git a/arch/x86/kvm/vmx/tdx.c b/arch/x86/kvm/vmx/tdx.c
index 7b5d0556ad95..add9a0083adb 100644
--- a/arch/x86/kvm/vmx/tdx.c
+++ b/arch/x86/kvm/vmx/tdx.c
@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/cpu.h>
+#include <linux/mmu_context.h>
 
 #include <asm/tdx.h>
 
@@ -392,6 +393,7 @@ u8 tdx_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio)
 int tdx_vcpu_create(struct kvm_vcpu *vcpu)
 {
 	struct kvm_tdx *kvm_tdx = to_kvm_tdx(vcpu->kvm);
+	struct vcpu_tdx *tdx = to_tdx(vcpu);
 
 	/*
 	 * On cpu creation, cpuid entry is blank.  Forcibly enable
@@ -420,9 +422,47 @@ int tdx_vcpu_create(struct kvm_vcpu *vcpu)
 	if ((kvm_tdx->xfam & XFEATURE_MASK_XTILE) == XFEATURE_MASK_XTILE)
 		vcpu->arch.xfd_no_write_intercept = true;
 
+	tdx->host_state_need_save = true;
+	tdx->host_state_need_restore = false;
+
 	return 0;
 }
 
+void tdx_prepare_switch_to_guest(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_tdx *tdx = to_tdx(vcpu);
+
+	if (!tdx->host_state_need_save)
+		return;
+
+	if (likely(is_64bit_mm(current->mm)))
+		tdx->msr_host_kernel_gs_base = current->thread.gsbase;
+	else
+		tdx->msr_host_kernel_gs_base = read_msr(MSR_KERNEL_GS_BASE);
+
+	tdx->host_state_need_save = false;
+}
+
+static void tdx_prepare_switch_to_host(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_tdx *tdx = to_tdx(vcpu);
+
+	tdx->host_state_need_save = true;
+	if (!tdx->host_state_need_restore)
+		return;
+
+	++vcpu->stat.host_state_reload;
+
+	wrmsrl(MSR_KERNEL_GS_BASE, tdx->msr_host_kernel_gs_base);
+	tdx->host_state_need_restore = false;
+}
+
+void tdx_vcpu_put(struct kvm_vcpu *vcpu)
+{
+	vmx_vcpu_pi_put(vcpu);
+	tdx_prepare_switch_to_host(vcpu);
+}
+
 void tdx_vcpu_free(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_tdx *tdx = to_tdx(vcpu);
@@ -543,6 +583,8 @@ fastpath_t tdx_vcpu_run(struct kvm_vcpu *vcpu)
 
 	tdx_vcpu_enter_exit(tdx);
 
+	tdx->host_state_need_restore = true;
+
 	vcpu->arch.regs_avail &= ~VMX_REGS_LAZY_LOAD_SET;
 	trace_kvm_exit(vcpu, KVM_ISA_VMX);
 
diff --git a/arch/x86/kvm/vmx/tdx.h b/arch/x86/kvm/vmx/tdx.h
index 04942488e6d1..610bd3f4e952 100644
--- a/arch/x86/kvm/vmx/tdx.h
+++ b/arch/x86/kvm/vmx/tdx.h
@@ -66,6 +66,10 @@ struct vcpu_tdx {
 
 	bool initialized;
 
+	bool host_state_need_save;
+	bool host_state_need_restore;
+	u64 msr_host_kernel_gs_base;
+
 	/*
 	 * Dummy to make pmu_intel not corrupt memory.
 	 * TODO: Support PMU for TDX.  Future work.
diff --git a/arch/x86/kvm/vmx/x86_ops.h b/arch/x86/kvm/vmx/x86_ops.h
index 87cfa1c5afa3..02da72dfb2cf 100644
--- a/arch/x86/kvm/vmx/x86_ops.h
+++ b/arch/x86/kvm/vmx/x86_ops.h
@@ -151,6 +151,8 @@ int tdx_vcpu_create(struct kvm_vcpu *vcpu);
 void tdx_vcpu_free(struct kvm_vcpu *vcpu);
 void tdx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event);
 fastpath_t tdx_vcpu_run(struct kvm_vcpu *vcpu);
+void tdx_prepare_switch_to_guest(struct kvm_vcpu *vcpu);
+void tdx_vcpu_put(struct kvm_vcpu *vcpu);
 u8 tdx_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio);
 
 int tdx_vcpu_ioctl(struct kvm_vcpu *vcpu, void __user *argp);
@@ -179,6 +181,8 @@ static inline int tdx_vcpu_create(struct kvm_vcpu *vcpu) { return -EOPNOTSUPP; }
 static inline void tdx_vcpu_free(struct kvm_vcpu *vcpu) {}
 static inline void tdx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) {}
 static inline fastpath_t tdx_vcpu_run(struct kvm_vcpu *vcpu) { return EXIT_FASTPATH_NONE; }
+static inline void tdx_prepare_switch_to_guest(struct kvm_vcpu *vcpu) {}
+static inline void tdx_vcpu_put(struct kvm_vcpu *vcpu) {}
 static inline u8 tdx_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio) { return 0; }
 
 static inline int tdx_vcpu_ioctl(struct kvm_vcpu *vcpu, void __user *argp) { return -EOPNOTSUPP; }
-- 
2.25.1