From: Sean Christopherson <seanjc@google.com>
To: Sean Christopherson <seanjc@google.com>,
Paolo Bonzini <pbonzini@redhat.com>
Cc: kvm@vger.kernel.org, linux-kernel@vger.kernel.org,
Binbin Wu <binbin.wu@linux.intel.com>,
Chao Gao <chao.gao@intel.com>, Jim Mattson <jmattson@google.com>
Subject: [PATCH v7 1/2] KVM: VMX: Bury all of the VMX preemption timer code under CONFIG_X86_64=y
Date: Fri, 31 Jul 2026 10:19:25 -0700 [thread overview]
Message-ID: <20260731171926.2629627-2-seanjc@google.com> (raw)
In-Reply-To: <20260731171926.2629627-1-seanjc@google.com>
Double down on using the VMX preemption timer only for 64-bit kernels, and
bury the setup and runtime adjustment code, and all global variables, under
CONFIG_X86_64=y. This will allow addressing a widespread Intel erratum
without running afoul of unused-but-set-variable and __udivdi3() errors on
32-bit kernels.
No functional change intended.
Reviewed-by: Binbin Wu <binbin.wu@linux.intel.com>
Reviewed-by: Chao Gao <chao.gao@intel.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
arch/x86/kvm/vmx/vmx.c | 122 +++++++++++++++++++++++------------------
1 file changed, 69 insertions(+), 53 deletions(-)
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index e4b9ac7fed9f..a07faa066ef0 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -150,10 +150,12 @@ module_param(dump_invalid_vmcs, bool, 0644);
#define KVM_VMX_TSC_MULTIPLIER_MAX 0xffffffffffffffffULL
/* Guest_tsc -> host_tsc conversion requires 64-bit division. */
+#ifdef CONFIG_X86_64
static int __read_mostly cpu_preemption_timer_multi;
static bool __read_mostly enable_preemption_timer = 1;
-#ifdef CONFIG_X86_64
module_param_named(preemption_timer, enable_preemption_timer, bool, S_IRUGO);
+#else
+#define enable_preemption_timer false
#endif
extern bool __read_mostly allow_smaller_maxphyaddr;
@@ -7408,32 +7410,6 @@ static void vmx_refresh_guest_perf_global_control(struct kvm_vcpu *vcpu)
pmu->global_ctrl = vmcs_read64(GUEST_IA32_PERF_GLOBAL_CTRL);
}
-static void vmx_update_hv_timer(struct kvm_vcpu *vcpu, bool force_immediate_exit)
-{
- struct vcpu_vmx *vmx = to_vmx(vcpu);
- u64 tscl;
- u32 delta_tsc;
-
- if (force_immediate_exit) {
- vmcs_write32(VMX_PREEMPTION_TIMER_VALUE, 0);
- vmx->loaded_vmcs->hv_timer_soft_disabled = false;
- } else if (vmx->hv_deadline_tsc != -1) {
- tscl = rdtsc();
- if (vmx->hv_deadline_tsc > tscl)
- /* set_hv_timer ensures the delta fits in 32-bits */
- delta_tsc = (u32)((vmx->hv_deadline_tsc - tscl) >>
- cpu_preemption_timer_multi);
- else
- delta_tsc = 0;
-
- vmcs_write32(VMX_PREEMPTION_TIMER_VALUE, delta_tsc);
- vmx->loaded_vmcs->hv_timer_soft_disabled = false;
- } else if (!vmx->loaded_vmcs->hv_timer_soft_disabled) {
- vmcs_write32(VMX_PREEMPTION_TIMER_VALUE, -1);
- vmx->loaded_vmcs->hv_timer_soft_disabled = true;
- }
-}
-
void noinstr vmx_update_host_rsp(struct vcpu_vmx *vmx, unsigned long host_rsp)
{
if (unlikely(host_rsp != vmx->loaded_vmcs->host_state.rsp)) {
@@ -7519,6 +7495,8 @@ static noinstr void vmx_vcpu_enter_exit(struct kvm_vcpu *vcpu,
guest_state_exit_irqoff();
}
+static void vmx_update_hv_timer(struct kvm_vcpu *vcpu, bool force_immediate_exit);
+
fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu, u64 run_flags)
{
bool force_immediate_exit = run_flags & KVM_RUN_FORCE_IMMEDIATE_EXIT;
@@ -8328,6 +8306,36 @@ static inline int u64_shl_div_u64(u64 a, unsigned int shift,
return 0;
}
+static __init void vmx_setup_preemption_timer(void)
+{
+ if (!cpu_has_vmx_preemption_timer())
+ enable_preemption_timer = false;
+
+ if (enable_preemption_timer) {
+ u64 use_timer_freq = 5000ULL * 1000 * 1000;
+
+ cpu_preemption_timer_multi =
+ vmx_misc_preemption_timer_rate(vmcs_config.misc);
+
+ if (tsc_khz)
+ use_timer_freq = (u64)tsc_khz * 1000;
+ use_timer_freq >>= cpu_preemption_timer_multi;
+
+ /*
+ * KVM "disables" the preemption timer by setting it to its max
+ * value. Don't use the timer if it might cause spurious exits
+ * at a rate faster than 0.1 Hz (of uninterrupted guest time).
+ */
+ if (use_timer_freq > 0xffffffffu / 10)
+ enable_preemption_timer = false;
+ }
+
+ if (!enable_preemption_timer) {
+ vt_x86_ops.set_hv_timer = NULL;
+ vt_x86_ops.cancel_hv_timer = NULL;
+ }
+}
+
int vmx_set_hv_timer(struct kvm_vcpu *vcpu, u64 guest_deadline_tsc,
bool *expired)
{
@@ -8372,6 +8380,39 @@ void vmx_cancel_hv_timer(struct kvm_vcpu *vcpu)
{
to_vmx(vcpu)->hv_deadline_tsc = -1;
}
+
+static void vmx_update_hv_timer(struct kvm_vcpu *vcpu, bool force_immediate_exit)
+{
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
+ u64 tscl;
+ u32 delta_tsc;
+
+ if (force_immediate_exit) {
+ vmcs_write32(VMX_PREEMPTION_TIMER_VALUE, 0);
+ vmx->loaded_vmcs->hv_timer_soft_disabled = false;
+ } else if (vmx->hv_deadline_tsc != -1) {
+ tscl = rdtsc();
+ if (vmx->hv_deadline_tsc > tscl)
+ /* set_hv_timer ensures the delta fits in 32-bits */
+ delta_tsc = (u32)((vmx->hv_deadline_tsc - tscl) >>
+ cpu_preemption_timer_multi);
+ else
+ delta_tsc = 0;
+
+ vmcs_write32(VMX_PREEMPTION_TIMER_VALUE, delta_tsc);
+ vmx->loaded_vmcs->hv_timer_soft_disabled = false;
+ } else if (!vmx->loaded_vmcs->hv_timer_soft_disabled) {
+ vmcs_write32(VMX_PREEMPTION_TIMER_VALUE, -1);
+ vmx->loaded_vmcs->hv_timer_soft_disabled = true;
+ }
+}
+#else
+static __init void vmx_setup_preemption_timer(void) { }
+
+static void vmx_update_hv_timer(struct kvm_vcpu *vcpu, bool force_immediate_exit)
+{
+ BUILD_BUG_ON(1);
+}
#endif
void vmx_update_cpu_dirty_logging(struct kvm_vcpu *vcpu)
@@ -8734,32 +8775,7 @@ __init int vmx_hardware_setup(void)
if (!enable_ept || !enable_ept_ad_bits || !cpu_has_vmx_pml())
enable_pml = 0;
- if (!cpu_has_vmx_preemption_timer())
- enable_preemption_timer = false;
-
- if (enable_preemption_timer) {
- u64 use_timer_freq = 5000ULL * 1000 * 1000;
-
- cpu_preemption_timer_multi =
- vmx_misc_preemption_timer_rate(vmcs_config.misc);
-
- if (tsc_khz)
- use_timer_freq = (u64)tsc_khz * 1000;
- use_timer_freq >>= cpu_preemption_timer_multi;
-
- /*
- * KVM "disables" the preemption timer by setting it to its max
- * value. Don't use the timer if it might cause spurious exits
- * at a rate faster than 0.1 Hz (of uninterrupted guest time).
- */
- if (use_timer_freq > 0xffffffffu / 10)
- enable_preemption_timer = false;
- }
-
- if (!enable_preemption_timer) {
- vt_x86_ops.set_hv_timer = NULL;
- vt_x86_ops.cancel_hv_timer = NULL;
- }
+ vmx_setup_preemption_timer();
kvm_caps.supported_mce_cap |= MCG_LMCE_P;
kvm_caps.supported_mce_cap |= MCG_CMCI_P;
--
2.55.0.508.g3f0d502094-goog
next prev parent reply other threads:[~2026-07-31 17:19 UTC|newest]
Thread overview: 3+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-07-31 17:19 [PATCH v7 0/2] KVM: VMX: Workaround VMX preemption timer erratum Sean Christopherson
2026-07-31 17:19 ` Sean Christopherson [this message]
2026-07-31 17:19 ` [PATCH v7 2/2] KVM: VMX: Cap VMX preemption timer to work around Intel erratum Sean Christopherson
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=20260731171926.2629627-2-seanjc@google.com \
--to=seanjc@google.com \
--cc=binbin.wu@linux.intel.com \
--cc=chao.gao@intel.com \
--cc=jmattson@google.com \
--cc=kvm@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=pbonzini@redhat.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