From: Xiaoyao Li <xiaoyao.li@intel.com>
To: Paolo Bonzini <pbonzini@redhat.com>,
Sean Christopherson <seanjc@google.com>,
Vitaly Kuznetsov <vkuznets@redhat.com>,
Wanpeng Li <wanpengli@tencent.com>,
Jim Mattson <jmattson@google.com>, Joerg Roedel <joro@8bytes.org>
Cc: xiaoyao.li@intel.com, erdemaktas@google.com,
Connor Kuehl <ckuehl@redhat.com>,
x86@kernel.org, linux-kernel@vger.kernel.org,
kvm@vger.kernel.org, isaku.yamahata@intel.com,
Kai Huang <kai.huang@intel.com>
Subject: [PATCH 05/11] KVM: x86: Disallow tsc manipulation for TDX
Date: Fri, 12 Nov 2021 23:37:27 +0800 [thread overview]
Message-ID: <20211112153733.2767561-6-xiaoyao.li@intel.com> (raw)
In-Reply-To: <20211112153733.2767561-1-xiaoyao.li@intel.com>
From: Sean Christopherson <sean.j.christopherson@intel.com>
The TSC for TDX guest is fixed at TD creation time.
Introduce kvm_tsc_immutable() to tell if TSC is immutable or not.
If immutable, short circuit all paths that lead to one of the myriad TSC
adjustment flows.
Suggested-by: Kai Huang <kai.huang@linux.intel.com>
Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
Signed-off-by: Xiaoyao Li <xiaoyao.li@intel.com>
---
arch/x86/kvm/x86.c | 34 ++++++++++++++++++++++++++--------
arch/x86/kvm/x86.h | 5 +++++
2 files changed, 31 insertions(+), 8 deletions(-)
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 2b21c5169f32..34dd93b29932 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -2247,7 +2247,9 @@ static int set_tsc_khz(struct kvm_vcpu *vcpu, u32 user_tsc_khz, bool scale)
u64 ratio;
/* Guest TSC same frequency as host TSC? */
- if (!scale) {
+ if (!scale || kvm_tsc_immutable(vcpu)) {
+ if (scale)
+ pr_warn_ratelimited("Guest TSC immutable, scaling not supported\n");
kvm_vcpu_write_tsc_multiplier(vcpu, kvm_default_tsc_scaling_ratio);
return 0;
}
@@ -2534,6 +2536,9 @@ static void kvm_synchronize_tsc(struct kvm_vcpu *vcpu, u64 data)
bool matched = false;
bool synchronizing = false;
+ if (WARN_ON_ONCE(kvm_tsc_immutable(vcpu)))
+ return;
+
raw_spin_lock_irqsave(&kvm->arch.tsc_write_lock, flags);
offset = kvm_compute_l1_tsc_offset(vcpu, data);
ns = get_kvmclock_base_ns();
@@ -2960,6 +2965,10 @@ static int kvm_guest_time_update(struct kvm_vcpu *v)
u8 pvclock_flags;
bool use_master_clock;
+ /* Unable to update guest time if the TSC is immutable. */
+ if (kvm_tsc_immutable(v))
+ return 0;
+
kernel_ns = 0;
host_tsc = 0;
@@ -4332,7 +4341,7 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
if (tsc_delta < 0)
mark_tsc_unstable("KVM discovered backwards TSC");
- if (kvm_check_tsc_unstable()) {
+ if (kvm_check_tsc_unstable() && !kvm_tsc_immutable(vcpu)) {
u64 offset = kvm_compute_l1_tsc_offset(vcpu,
vcpu->arch.last_guest_tsc);
kvm_vcpu_write_tsc_offset(vcpu, offset);
@@ -4346,7 +4355,8 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
* On a host with synchronized TSC, there is no need to update
* kvmclock on vcpu->cpu migration
*/
- if (!vcpu->kvm->arch.use_master_clock || vcpu->cpu == -1)
+ if ((!vcpu->kvm->arch.use_master_clock || vcpu->cpu == -1) &&
+ !kvm_tsc_immutable(vcpu))
kvm_make_request(KVM_REQ_GLOBAL_CLOCK_UPDATE, vcpu);
if (vcpu->cpu != cpu)
kvm_make_request(KVM_REQ_MIGRATE_TIMER, vcpu);
@@ -5274,10 +5284,11 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
break;
}
case KVM_SET_TSC_KHZ: {
- u32 user_tsc_khz;
+ u32 user_tsc_khz = (u32)arg;
r = -EINVAL;
- user_tsc_khz = (u32)arg;
+ if (kvm_tsc_immutable(vcpu))
+ goto out;
if (kvm_has_tsc_control &&
user_tsc_khz >= kvm_max_guest_tsc_khz)
@@ -10857,9 +10868,12 @@ void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu)
if (mutex_lock_killable(&vcpu->mutex))
return;
- vcpu_load(vcpu);
- kvm_synchronize_tsc(vcpu, 0);
- vcpu_put(vcpu);
+
+ if (!kvm_tsc_immutable(vcpu)) {
+ vcpu_load(vcpu);
+ kvm_synchronize_tsc(vcpu, 0);
+ vcpu_put(vcpu);
+ }
/* poll control enabled by default */
vcpu->arch.msr_kvm_poll_control = 1;
@@ -11119,6 +11133,10 @@ int kvm_arch_hardware_enable(void)
if (backwards_tsc) {
u64 delta_cyc = max_tsc - local_tsc;
list_for_each_entry(kvm, &vm_list, vm_list) {
+ if (kvm_tsc_immutable(vcpu)) {
+ pr_warn_ratelimited("Backwards TSC observed and guest with immutable TSC active\n");
+ continue;
+ }
kvm->arch.backwards_tsc_observed = true;
kvm_for_each_vcpu(i, vcpu, kvm) {
vcpu->arch.tsc_offset_adjustment += delta_cyc;
diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
index 69c60297bef2..0d8435b32bf5 100644
--- a/arch/x86/kvm/x86.h
+++ b/arch/x86/kvm/x86.h
@@ -446,6 +446,11 @@ static __always_inline bool kvm_guest_mce_disallowed(struct kvm *kvm)
return kvm->arch.vm_type == KVM_X86_TDX_VM;
}
+static __always_inline bool kvm_tsc_immutable(struct kvm_vcpu *vcpu)
+{
+ return vcpu->kvm->arch.vm_type == KVM_X86_TDX_VM;
+}
+
void kvm_load_guest_xsave_state(struct kvm_vcpu *vcpu);
void kvm_load_host_xsave_state(struct kvm_vcpu *vcpu);
int kvm_spec_ctrl_test_value(u64 value);
--
2.27.0
next prev parent reply other threads:[~2021-11-12 15:38 UTC|newest]
Thread overview: 22+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-11-12 15:37 [PATCH 00/11] KVM: x86: TDX preparation of introducing vm_type and blocking ioctls based on vm_type Xiaoyao Li
2021-11-12 15:37 ` [PATCH 01/11] KVM: x86: Introduce vm_type to differentiate normal VMs from confidential VMs Xiaoyao Li
2021-11-12 16:47 ` Sean Christopherson
2021-11-15 15:37 ` Xiaoyao Li
2021-11-12 15:37 ` [PATCH 02/11] KVM: x86: Disable direct IRQ injection for TDX Xiaoyao Li
2021-11-12 15:37 ` [PATCH 03/11] KVM: x86: Clean up kvm_vcpu_ioctl_x86_setup_mce() Xiaoyao Li
2021-12-02 1:19 ` Xiaoyao Li
2021-11-12 15:37 ` [PATCH 04/11] KVM: x86: Disable MCE related stuff for TDX Xiaoyao Li
2021-11-12 17:01 ` Sean Christopherson
2021-11-15 15:39 ` Xiaoyao Li
2021-11-12 15:37 ` Xiaoyao Li [this message]
2021-11-12 15:37 ` [PATCH 06/11] KVM: x86: Disable in-kernel I/O APIC and level routes " Xiaoyao Li
2021-11-12 15:37 ` [PATCH 07/11] KVM: x86: Disable SMM " Xiaoyao Li
2021-11-12 18:04 ` Sean Christopherson
2021-11-12 18:35 ` Sean Christopherson
2021-12-01 6:29 ` Xiaoyao Li
2021-11-12 15:37 ` [PATCH 08/11] KVM: x86: Disable INIT/SIPI " Xiaoyao Li
2021-11-12 15:37 ` [PATCH 09/11] KVM: x86: Block ioctls to access guest state " Xiaoyao Li
2021-11-12 15:37 ` [PATCH 10/11] KVM: Disallow read-only memory for x86 TDX Xiaoyao Li
2021-11-12 16:52 ` Sean Christopherson
2021-11-14 3:43 ` Xiaoyao Li
2021-11-12 15:37 ` [PATCH 11/11] KVM: Disallow dirty logging " Xiaoyao Li
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=20211112153733.2767561-6-xiaoyao.li@intel.com \
--to=xiaoyao.li@intel.com \
--cc=ckuehl@redhat.com \
--cc=erdemaktas@google.com \
--cc=isaku.yamahata@intel.com \
--cc=jmattson@google.com \
--cc=joro@8bytes.org \
--cc=kai.huang@intel.com \
--cc=kvm@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=pbonzini@redhat.com \
--cc=seanjc@google.com \
--cc=vkuznets@redhat.com \
--cc=wanpengli@tencent.com \
--cc=x86@kernel.org \
/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
all inboxes | Powered by JetHome®