From: Binbin Wu <binbin.wu@linux.intel.com>
To: pbonzini@redhat.com, seanjc@google.com, kvm@vger.kernel.org
Cc: rick.p.edgecombe@intel.com, kai.huang@intel.com,
adrian.hunter@intel.com, reinette.chatre@intel.com,
xiaoyao.li@intel.com, tony.lindgren@intel.com,
isaku.yamahata@intel.com, yan.y.zhao@intel.com,
chao.gao@intel.com, linux-kernel@vger.kernel.org,
binbin.wu@linux.intel.com
Subject: [PATCH v2 12/20] KVM: TDX: Add methods to ignore accesses to CPU state
Date: Thu, 27 Feb 2025 09:20:13 +0800 [thread overview]
Message-ID: <20250227012021.1778144-13-binbin.wu@linux.intel.com> (raw)
In-Reply-To: <20250227012021.1778144-1-binbin.wu@linux.intel.com>
From: Isaku Yamahata <isaku.yamahata@intel.com>
TDX protects TDX guest state from VMM. Implement access methods for TDX
guest state to ignore them or return zero. Because those methods can be
called by kvm ioctls to set/get cpu registers, they don't have KVM_BUG_ON.
Signed-off-by: Isaku Yamahata <isaku.yamahata@intel.com>
Co-developed-by: Adrian Hunter <adrian.hunter@intel.com>
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Co-developed-by: Binbin Wu <binbin.wu@linux.intel.com>
Signed-off-by: Binbin Wu <binbin.wu@linux.intel.com>
---
TDX "the rest" v2:
- Discard the mistakenly introduced change.
https://lore.kernel.org/kvm/67dd44fb-0211-4435-a294-b9f00dc681d8@linux.intel.com
- Drop tdx_cache_reg() (Adrian, Sean)
TDX "the rest" v1:
- Dropped KVM_BUG_ON() in vt_sync_dirty_debug_regs(). (Rick)
Since the KVM_BUG_ON() is removed, change the changlog accordingly.
---
arch/x86/kvm/vmx/main.c | 307 ++++++++++++++++++++++++++++++++++++----
1 file changed, 278 insertions(+), 29 deletions(-)
diff --git a/arch/x86/kvm/vmx/main.c b/arch/x86/kvm/vmx/main.c
index 7f3be1b65ce1..b76f39cc56fb 100644
--- a/arch/x86/kvm/vmx/main.c
+++ b/arch/x86/kvm/vmx/main.c
@@ -335,6 +335,214 @@ static void vt_deliver_interrupt(struct kvm_lapic *apic, int delivery_mode,
vmx_deliver_interrupt(apic, delivery_mode, trig_mode, vector);
}
+static void vt_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu)
+{
+ if (is_td_vcpu(vcpu))
+ return;
+
+ vmx_vcpu_after_set_cpuid(vcpu);
+}
+
+static void vt_update_exception_bitmap(struct kvm_vcpu *vcpu)
+{
+ if (is_td_vcpu(vcpu))
+ return;
+
+ vmx_update_exception_bitmap(vcpu);
+}
+
+static u64 vt_get_segment_base(struct kvm_vcpu *vcpu, int seg)
+{
+ if (is_td_vcpu(vcpu))
+ return 0;
+
+ return vmx_get_segment_base(vcpu, seg);
+}
+
+static void vt_get_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var,
+ int seg)
+{
+ if (is_td_vcpu(vcpu)) {
+ memset(var, 0, sizeof(*var));
+ return;
+ }
+
+ vmx_get_segment(vcpu, var, seg);
+}
+
+static void vt_set_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var,
+ int seg)
+{
+ if (is_td_vcpu(vcpu))
+ return;
+
+ vmx_set_segment(vcpu, var, seg);
+}
+
+static int vt_get_cpl(struct kvm_vcpu *vcpu)
+{
+ if (is_td_vcpu(vcpu))
+ return 0;
+
+ return vmx_get_cpl(vcpu);
+}
+
+static int vt_get_cpl_no_cache(struct kvm_vcpu *vcpu)
+{
+ if (is_td_vcpu(vcpu))
+ return 0;
+
+ return vmx_get_cpl_no_cache(vcpu);
+}
+
+static void vt_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l)
+{
+ if (is_td_vcpu(vcpu)) {
+ *db = 0;
+ *l = 0;
+ return;
+ }
+
+ vmx_get_cs_db_l_bits(vcpu, db, l);
+}
+
+static bool vt_is_valid_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
+{
+ if (is_td_vcpu(vcpu))
+ return true;
+
+ return vmx_is_valid_cr0(vcpu, cr0);
+}
+
+static void vt_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
+{
+ if (is_td_vcpu(vcpu))
+ return;
+
+ vmx_set_cr0(vcpu, cr0);
+}
+
+static bool vt_is_valid_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
+{
+ if (is_td_vcpu(vcpu))
+ return true;
+
+ return vmx_is_valid_cr4(vcpu, cr4);
+}
+
+static void vt_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
+{
+ if (is_td_vcpu(vcpu))
+ return;
+
+ vmx_set_cr4(vcpu, cr4);
+}
+
+static int vt_set_efer(struct kvm_vcpu *vcpu, u64 efer)
+{
+ if (is_td_vcpu(vcpu))
+ return 0;
+
+ return vmx_set_efer(vcpu, efer);
+}
+
+static void vt_get_idt(struct kvm_vcpu *vcpu, struct desc_ptr *dt)
+{
+ if (is_td_vcpu(vcpu)) {
+ memset(dt, 0, sizeof(*dt));
+ return;
+ }
+
+ vmx_get_idt(vcpu, dt);
+}
+
+static void vt_set_idt(struct kvm_vcpu *vcpu, struct desc_ptr *dt)
+{
+ if (is_td_vcpu(vcpu))
+ return;
+
+ vmx_set_idt(vcpu, dt);
+}
+
+static void vt_get_gdt(struct kvm_vcpu *vcpu, struct desc_ptr *dt)
+{
+ if (is_td_vcpu(vcpu)) {
+ memset(dt, 0, sizeof(*dt));
+ return;
+ }
+
+ vmx_get_gdt(vcpu, dt);
+}
+
+static void vt_set_gdt(struct kvm_vcpu *vcpu, struct desc_ptr *dt)
+{
+ if (is_td_vcpu(vcpu))
+ return;
+
+ vmx_set_gdt(vcpu, dt);
+}
+
+static void vt_set_dr6(struct kvm_vcpu *vcpu, unsigned long val)
+{
+ if (is_td_vcpu(vcpu))
+ return;
+
+ vmx_set_dr6(vcpu, val);
+}
+
+static void vt_set_dr7(struct kvm_vcpu *vcpu, unsigned long val)
+{
+ if (is_td_vcpu(vcpu))
+ return;
+
+ vmx_set_dr7(vcpu, val);
+}
+
+static void vt_sync_dirty_debug_regs(struct kvm_vcpu *vcpu)
+{
+ /*
+ * MOV-DR exiting is always cleared for TD guest, even in debug mode.
+ * Thus KVM_DEBUGREG_WONT_EXIT can never be set and it should never
+ * reach here for TD vcpu.
+ */
+ if (is_td_vcpu(vcpu))
+ return;
+
+ vmx_sync_dirty_debug_regs(vcpu);
+}
+
+static void vt_cache_reg(struct kvm_vcpu *vcpu, enum kvm_reg reg)
+{
+ if (WARN_ON_ONCE(is_td_vcpu(vcpu)))
+ return;
+
+ vmx_cache_reg(vcpu, reg);
+}
+
+static unsigned long vt_get_rflags(struct kvm_vcpu *vcpu)
+{
+ if (is_td_vcpu(vcpu))
+ return 0;
+
+ return vmx_get_rflags(vcpu);
+}
+
+static void vt_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags)
+{
+ if (is_td_vcpu(vcpu))
+ return;
+
+ vmx_set_rflags(vcpu, rflags);
+}
+
+static bool vt_get_if_flag(struct kvm_vcpu *vcpu)
+{
+ if (is_td_vcpu(vcpu))
+ return false;
+
+ return vmx_get_if_flag(vcpu);
+}
+
static void vt_flush_tlb_all(struct kvm_vcpu *vcpu)
{
if (is_td_vcpu(vcpu)) {
@@ -457,6 +665,14 @@ static void vt_inject_irq(struct kvm_vcpu *vcpu, bool reinjected)
vmx_inject_irq(vcpu, reinjected);
}
+static void vt_inject_exception(struct kvm_vcpu *vcpu)
+{
+ if (is_td_vcpu(vcpu))
+ return;
+
+ vmx_inject_exception(vcpu);
+}
+
static void vt_cancel_injection(struct kvm_vcpu *vcpu)
{
if (is_td_vcpu(vcpu))
@@ -504,6 +720,14 @@ static void vt_get_exit_info(struct kvm_vcpu *vcpu, u32 *reason,
vmx_get_exit_info(vcpu, reason, info1, info2, intr_info, error_code);
}
+static void vt_update_cr8_intercept(struct kvm_vcpu *vcpu, int tpr, int irr)
+{
+ if (is_td_vcpu(vcpu))
+ return;
+
+ vmx_update_cr8_intercept(vcpu, tpr, irr);
+}
+
static void vt_set_apic_access_page_addr(struct kvm_vcpu *vcpu)
{
if (is_td_vcpu(vcpu))
@@ -522,6 +746,30 @@ static void vt_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu)
vmx_refresh_apicv_exec_ctrl(vcpu);
}
+static void vt_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap)
+{
+ if (is_td_vcpu(vcpu))
+ return;
+
+ vmx_load_eoi_exitmap(vcpu, eoi_exit_bitmap);
+}
+
+static int vt_set_tss_addr(struct kvm *kvm, unsigned int addr)
+{
+ if (is_td(kvm))
+ return 0;
+
+ return vmx_set_tss_addr(kvm, addr);
+}
+
+static int vt_set_identity_map_addr(struct kvm *kvm, u64 ident_addr)
+{
+ if (is_td(kvm))
+ return 0;
+
+ return vmx_set_identity_map_addr(kvm, ident_addr);
+}
+
static int vt_mem_enc_ioctl(struct kvm *kvm, void __user *argp)
{
if (!is_td(kvm))
@@ -583,32 +831,33 @@ struct kvm_x86_ops vt_x86_ops __initdata = {
.vcpu_load = vt_vcpu_load,
.vcpu_put = vt_vcpu_put,
- .update_exception_bitmap = vmx_update_exception_bitmap,
+ .update_exception_bitmap = vt_update_exception_bitmap,
.get_feature_msr = vmx_get_feature_msr,
.get_msr = vt_get_msr,
.set_msr = vt_set_msr,
- .get_segment_base = vmx_get_segment_base,
- .get_segment = vmx_get_segment,
- .set_segment = vmx_set_segment,
- .get_cpl = vmx_get_cpl,
- .get_cpl_no_cache = vmx_get_cpl_no_cache,
- .get_cs_db_l_bits = vmx_get_cs_db_l_bits,
- .is_valid_cr0 = vmx_is_valid_cr0,
- .set_cr0 = vmx_set_cr0,
- .is_valid_cr4 = vmx_is_valid_cr4,
- .set_cr4 = vmx_set_cr4,
- .set_efer = vmx_set_efer,
- .get_idt = vmx_get_idt,
- .set_idt = vmx_set_idt,
- .get_gdt = vmx_get_gdt,
- .set_gdt = vmx_set_gdt,
- .set_dr6 = vmx_set_dr6,
- .set_dr7 = vmx_set_dr7,
- .sync_dirty_debug_regs = vmx_sync_dirty_debug_regs,
- .cache_reg = vmx_cache_reg,
- .get_rflags = vmx_get_rflags,
- .set_rflags = vmx_set_rflags,
- .get_if_flag = vmx_get_if_flag,
+
+ .get_segment_base = vt_get_segment_base,
+ .get_segment = vt_get_segment,
+ .set_segment = vt_set_segment,
+ .get_cpl = vt_get_cpl,
+ .get_cpl_no_cache = vt_get_cpl_no_cache,
+ .get_cs_db_l_bits = vt_get_cs_db_l_bits,
+ .is_valid_cr0 = vt_is_valid_cr0,
+ .set_cr0 = vt_set_cr0,
+ .is_valid_cr4 = vt_is_valid_cr4,
+ .set_cr4 = vt_set_cr4,
+ .set_efer = vt_set_efer,
+ .get_idt = vt_get_idt,
+ .set_idt = vt_set_idt,
+ .get_gdt = vt_get_gdt,
+ .set_gdt = vt_set_gdt,
+ .set_dr6 = vt_set_dr6,
+ .set_dr7 = vt_set_dr7,
+ .sync_dirty_debug_regs = vt_sync_dirty_debug_regs,
+ .cache_reg = vt_cache_reg,
+ .get_rflags = vt_get_rflags,
+ .set_rflags = vt_set_rflags,
+ .get_if_flag = vt_get_if_flag,
.flush_tlb_all = vt_flush_tlb_all,
.flush_tlb_current = vt_flush_tlb_current,
@@ -625,7 +874,7 @@ struct kvm_x86_ops vt_x86_ops __initdata = {
.patch_hypercall = vmx_patch_hypercall,
.inject_irq = vt_inject_irq,
.inject_nmi = vt_inject_nmi,
- .inject_exception = vmx_inject_exception,
+ .inject_exception = vt_inject_exception,
.cancel_injection = vt_cancel_injection,
.interrupt_allowed = vt_interrupt_allowed,
.nmi_allowed = vt_nmi_allowed,
@@ -633,13 +882,13 @@ struct kvm_x86_ops vt_x86_ops __initdata = {
.set_nmi_mask = vt_set_nmi_mask,
.enable_nmi_window = vt_enable_nmi_window,
.enable_irq_window = vt_enable_irq_window,
- .update_cr8_intercept = vmx_update_cr8_intercept,
+ .update_cr8_intercept = vt_update_cr8_intercept,
.x2apic_icr_is_split = false,
.set_virtual_apic_mode = vt_set_virtual_apic_mode,
.set_apic_access_page_addr = vt_set_apic_access_page_addr,
.refresh_apicv_exec_ctrl = vt_refresh_apicv_exec_ctrl,
- .load_eoi_exitmap = vmx_load_eoi_exitmap,
+ .load_eoi_exitmap = vt_load_eoi_exitmap,
.apicv_pre_state_restore = vt_apicv_pre_state_restore,
.required_apicv_inhibits = VMX_REQUIRED_APICV_INHIBITS,
.hwapic_isr_update = vt_hwapic_isr_update,
@@ -647,14 +896,14 @@ struct kvm_x86_ops vt_x86_ops __initdata = {
.deliver_interrupt = vt_deliver_interrupt,
.dy_apicv_has_pending_interrupt = pi_has_pending_interrupt,
- .set_tss_addr = vmx_set_tss_addr,
- .set_identity_map_addr = vmx_set_identity_map_addr,
+ .set_tss_addr = vt_set_tss_addr,
+ .set_identity_map_addr = vt_set_identity_map_addr,
.get_mt_mask = vmx_get_mt_mask,
.get_exit_info = vt_get_exit_info,
.get_entry_info = vt_get_entry_info,
- .vcpu_after_set_cpuid = vmx_vcpu_after_set_cpuid,
+ .vcpu_after_set_cpuid = vt_vcpu_after_set_cpuid,
.has_wbinvd_exit = cpu_has_vmx_wbinvd_exit,
--
2.46.0
next prev parent reply other threads:[~2025-02-27 1:19 UTC|newest]
Thread overview: 21+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-02-27 1:20 [PATCH v2 00/20] KVM: TDX: TDX "the rest" part Binbin Wu
2025-02-27 1:20 ` [PATCH v2 01/20] KVM: TDX: Handle EPT violation/misconfig exit Binbin Wu
2025-02-27 1:20 ` [PATCH v2 02/20] KVM: TDX: Detect unexpected SEPT violations due to pending SPTEs Binbin Wu
2025-02-27 1:20 ` [PATCH v2 03/20] KVM: TDX: Retry locally in TDX EPT violation handler on RET_PF_RETRY Binbin Wu
2025-02-27 1:20 ` [PATCH v2 04/20] KVM: TDX: Kick off vCPUs when SEAMCALL is busy during TD page removal Binbin Wu
2025-02-27 1:20 ` [PATCH v2 05/20] KVM: TDX: Handle TDX PV CPUID hypercall Binbin Wu
2025-02-27 1:20 ` [PATCH v2 06/20] KVM: TDX: Handle TDX PV HLT hypercall Binbin Wu
2025-02-27 1:20 ` [PATCH v2 07/20] KVM: x86: Move KVM_MAX_MCE_BANKS to header file Binbin Wu
2025-02-27 1:20 ` [PATCH v2 08/20] KVM: TDX: Implement callbacks for MSR operations Binbin Wu
2025-02-27 1:20 ` [PATCH v2 09/20] KVM: TDX: Handle TDX PV rdmsr/wrmsr hypercall Binbin Wu
2025-02-27 1:20 ` [PATCH v2 10/20] KVM: TDX: Enable guest access to LMCE related MSRs Binbin Wu
2025-02-27 1:20 ` [PATCH v2 11/20] KVM: TDX: Handle TDG.VP.VMCALL<GetTdVmCallInfo> hypercall Binbin Wu
2025-02-27 1:20 ` Binbin Wu [this message]
2025-02-27 1:20 ` [PATCH v2 13/20] KVM: TDX: Add method to ignore guest instruction emulation Binbin Wu
2025-02-27 1:20 ` [PATCH v2 14/20] KVM: TDX: Add methods to ignore VMX preemption timer Binbin Wu
2025-02-27 1:20 ` [PATCH v2 15/20] KVM: TDX: Add methods to ignore accesses to TSC Binbin Wu
2025-02-27 1:20 ` [PATCH v2 16/20] KVM: TDX: Ignore setting up mce Binbin Wu
2025-02-27 1:20 ` [PATCH v2 17/20] KVM: TDX: Add a method to ignore hypercall patching Binbin Wu
2025-02-27 1:20 ` [PATCH v2 18/20] KVM: TDX: Enable guest access to MTRR MSRs Binbin Wu
2025-02-27 1:20 ` [PATCH v2 19/20] KVM: TDX: Make TDX VM type supported Binbin Wu
2025-02-27 1:20 ` [PATCH v2 20/20] Documentation/virt/kvm: Document on Trust Domain Extensions (TDX) Binbin Wu
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20250227012021.1778144-13-binbin.wu@linux.intel.com \
--to=binbin.wu@linux.intel.com \
--cc=adrian.hunter@intel.com \
--cc=chao.gao@intel.com \
--cc=isaku.yamahata@intel.com \
--cc=kai.huang@intel.com \
--cc=kvm@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=pbonzini@redhat.com \
--cc=reinette.chatre@intel.com \
--cc=rick.p.edgecombe@intel.com \
--cc=seanjc@google.com \
--cc=tony.lindgren@intel.com \
--cc=xiaoyao.li@intel.com \
--cc=yan.y.zhao@intel.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox