From: Sean Christopherson <seanjc@google.com>
To: Kiryl Shutsemau <kas@kernel.org>,
Paolo Bonzini <pbonzini@redhat.com>,
Sean Christopherson <seanjc@google.com>,
"K. Y. Srinivasan" <kys@microsoft.com>,
Haiyang Zhang <haiyangz@microsoft.com>,
Wei Liu <wei.liu@kernel.org>, Dexuan Cui <decui@microsoft.com>,
Long Li <longli@microsoft.com>,
Ajay Kaher <ajay.kaher@broadcom.com>,
Alexey Makhalov <alexey.makhalov@broadcom.com>,
Jan Kiszka <jan.kiszka@siemens.com>,
Dave Hansen <dave.hansen@linux.intel.com>,
Andy Lutomirski <luto@kernel.org>,
Peter Zijlstra <peterz@infradead.org>,
Juergen Gross <jgross@suse.com>,
Daniel Lezcano <daniel.lezcano@kernel.org>,
Thomas Gleixner <tglx@kernel.org>,
John Stultz <jstultz@google.com>
Cc: Rick Edgecombe <rick.p.edgecombe@intel.com>,
Vitaly Kuznetsov <vkuznets@redhat.com>,
Broadcom internal kernel review list
<bcm-kernel-feedback-list@broadcom.com>,
Boris Ostrovsky <boris.ostrovsky@oracle.com>,
Stephen Boyd <sboyd@kernel.org>,
x86@kernel.org, linux-coco@lists.linux.dev, kvm@vger.kernel.org,
linux-hyperv@vger.kernel.org, virtualization@lists.linux.dev,
linux-kernel@vger.kernel.org, xen-devel@lists.xenproject.org,
Michael Kelley <mhklinux@outlook.com>,
Tom Lendacky <thomas.lendacky@amd.com>,
Nikunj A Dadhania <nikunj@amd.com>,
Thomas Gleixner <tglx@linutronix.de>,
David Woodhouse <dwmw@amazon.co.uk>
Subject: [PATCH v3 05/41] x86/tdx: Override PV calibration routines with CPUID-based calibration
Date: Fri, 15 May 2026 12:19:06 -0700 [thread overview]
Message-ID: <20260515191942.1892718-6-seanjc@google.com> (raw)
In-Reply-To: <20260515191942.1892718-1-seanjc@google.com>
When running as a TDX guest, explicitly override the TSC frequency
calibration routine with CPUID-based calibration instead of potentially
relying on a hypervisor-controlled PV routine. For TDX guests, CPUID.0x15
is always emulated by the TDX-Module, i.e. the information from CPUID is
more trustworthy than the information provided by the hypervisor.
To maintain backwards compatibility with TDX guest kernels that use native
calibration, and because it's the least awful option, retain
native_calibrate_tsc()'s stuffing of the local APIC bus period using the
core crystal frequency. While it's entirely possible for the hypervisor
to emulate the APIC timer at a different frequency than the core crystal
frequency, the commonly accepted interpretation of Intel's SDM is that APIC
timer runs at the core crystal frequency when that latter is enumerated via
CPUID:
The APIC timer frequency will be the processor’s bus clock or core
crystal clock frequency (when TSC/core crystal clock ratio is enumerated
in CPUID leaf 0x15).
If the hypervisor is malicious and deliberately runs the APIC timer at the
wrong frequency, nothing would stop the hypervisor from modifying the
frequency at any time, i.e. attempting to manually calibrate the frequency
out of paranoia would be futile.
Deliberately leave the CPU frequency calibration routine as is, since the
TDX-Module doesn't provide any guarantees with respect to CPUID.0x16.
Opportunistically add a comment explaining that CoCo TSC initialization
needs to come after hypervisor specific initialization.
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
arch/x86/coco/tdx/tdx.c | 30 +++++++++++++++++++++++++++---
arch/x86/include/asm/tdx.h | 2 ++
arch/x86/kernel/tsc.c | 8 ++++++++
3 files changed, 37 insertions(+), 3 deletions(-)
diff --git a/arch/x86/coco/tdx/tdx.c b/arch/x86/coco/tdx/tdx.c
index 29b6f1ed59ec..26890cea790b 100644
--- a/arch/x86/coco/tdx/tdx.c
+++ b/arch/x86/coco/tdx/tdx.c
@@ -8,6 +8,7 @@
#include <linux/export.h>
#include <linux/io.h>
#include <linux/kexec.h>
+#include <asm/apic.h>
#include <asm/coco.h>
#include <asm/tdx.h>
#include <asm/vmx.h>
@@ -1123,9 +1124,6 @@ void __init tdx_early_init(void)
setup_force_cpu_cap(X86_FEATURE_TDX_GUEST);
- /* TSC is the only reliable clock in TDX guest */
- setup_force_cpu_cap(X86_FEATURE_TSC_RELIABLE);
-
cc_vendor = CC_VENDOR_INTEL;
/* Configure the TD */
@@ -1195,3 +1193,29 @@ void __init tdx_early_init(void)
tdx_announce();
}
+
+static unsigned long tdx_get_tsc_khz(void)
+{
+ struct cpuid_tsc_info info;
+
+ if (WARN_ON_ONCE(cpuid_get_tsc_freq(&info)))
+ return 0;
+
+ lapic_timer_period = info.crystal_khz * 1000 / HZ;
+
+ return info.tsc_khz;
+}
+
+void __init tdx_tsc_init(void)
+{
+ /* TSC is the only reliable clock in TDX guest */
+ setup_force_cpu_cap(X86_FEATURE_TSC_RELIABLE);
+ setup_force_cpu_cap(X86_FEATURE_TSC_KNOWN_FREQ);
+
+ /*
+ * Override the PV calibration routines (if set) with more trustworthy
+ * CPUID-based calibration. The TDX module emulates CPUID, whereas any
+ * PV information is provided by the hypervisor.
+ */
+ tsc_register_calibration_routines(tdx_get_tsc_khz, NULL);
+}
diff --git a/arch/x86/include/asm/tdx.h b/arch/x86/include/asm/tdx.h
index 15eac89b0afb..60deab0ed979 100644
--- a/arch/x86/include/asm/tdx.h
+++ b/arch/x86/include/asm/tdx.h
@@ -57,6 +57,7 @@ struct ve_info {
#ifdef CONFIG_INTEL_TDX_GUEST
void __init tdx_early_init(void);
+void __init tdx_tsc_init(void);
void tdx_get_ve_info(struct ve_info *ve);
@@ -78,6 +79,7 @@ void __init tdx_dump_td_ctls(u64 td_ctls);
#else
static inline void tdx_early_init(void) { };
+static inline void tdx_tsc_init(void) { }
static inline void tdx_halt(void) { };
static inline bool tdx_early_handle_ve(struct pt_regs *regs) { return false; }
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 243999692aea..e00f53e3dd8d 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -34,6 +34,7 @@
#include <asm/topology.h>
#include <asm/uv/uv.h>
#include <asm/sev.h>
+#include <asm/tdx.h>
unsigned int __read_mostly cpu_khz; /* TSC clocks / usec, not used here */
EXPORT_SYMBOL(cpu_khz);
@@ -1559,8 +1560,15 @@ void __init tsc_early_init(void)
if (is_early_uv_system())
return;
+ /*
+ * Do CoCo specific "secure" TSC initialization *after* hypervisor
+ * platform initialization so that the secure variant can override the
+ * hypervisor's PV calibration routine with a more trusted method.
+ */
if (cc_platform_has(CC_ATTR_GUEST_SNP_SECURE_TSC))
snp_secure_tsc_init();
+ else if (boot_cpu_has(X86_FEATURE_TDX_GUEST))
+ tdx_tsc_init();
if (!determine_cpu_tsc_frequencies(true))
return;
--
2.54.0.563.g4f69b47b94-goog
next prev parent reply other threads:[~2026-05-15 19:20 UTC|newest]
Thread overview: 42+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-05-15 19:19 [PATCH v3 00/41] x86: Try to wrangle PV clocks vs. TSC Sean Christopherson
2026-05-15 19:19 ` [PATCH v3 01/41] x86/tsc: Add a standalone helpers for getting TSC info from CPUID.0x15 Sean Christopherson
2026-05-15 19:19 ` [PATCH v3 02/41] x86/tsc: Add helper to register CPU and TSC freq calibration routines Sean Christopherson
2026-05-15 19:19 ` [PATCH v3 03/41] x86/sev: Mark TSC as reliable when configuring Secure TSC Sean Christopherson
2026-05-15 19:19 ` [PATCH v3 04/41] x86/sev: Move check for SNP Secure TSC support to tsc_early_init() Sean Christopherson
2026-05-15 19:19 ` Sean Christopherson [this message]
2026-05-15 19:19 ` [PATCH v3 06/41] x86/acrn: Mark TSC frequency as known when using ACRN for calibration Sean Christopherson
2026-05-15 19:19 ` [PATCH v3 07/41] clocksource: hyper-v: Register sched_clock save/restore iff it's necessary Sean Christopherson
2026-05-15 19:19 ` [PATCH v3 08/41] clocksource: hyper-v: Drop wrappers to sched_clock save/restore helpers Sean Christopherson
2026-05-15 19:19 ` [PATCH v3 09/41] clocksource: hyper-v: Don't save/restore TSC offset when using HV sched_clock Sean Christopherson
2026-05-15 19:19 ` [PATCH v3 10/41] x86/kvmclock: Setup kvmclock for secondary CPUs iff CONFIG_SMP=y Sean Christopherson
2026-05-15 19:19 ` [PATCH v3 11/41] x86/kvm: Don't disable kvmclock on BSP in syscore_suspend() Sean Christopherson
2026-05-15 19:19 ` [PATCH v3 12/41] x86/paravirt: Remove unnecessary PARAVIRT=n stub for paravirt_set_sched_clock() Sean Christopherson
2026-05-15 19:19 ` [PATCH v3 13/41] x86/paravirt: Move handling of unstable PV clocks into paravirt_set_sched_clock() Sean Christopherson
2026-05-15 19:19 ` [PATCH v3 14/41] x86/kvmclock: Move sched_clock save/restore helpers up in kvmclock.c Sean Christopherson
2026-05-15 19:19 ` [PATCH v3 15/41] x86/xen/time: Nullify x86_platform's sched_clock save/restore hooks Sean Christopherson
2026-05-15 19:19 ` [PATCH v3 16/41] x86/vmware: Nullify save/restore hooks when using VMware's sched_clock Sean Christopherson
2026-05-15 19:19 ` [PATCH v3 17/41] x86/tsc: WARN if TSC sched_clock save/restore used with PV sched_clock Sean Christopherson
2026-05-15 19:19 ` [PATCH v3 18/41] x86/paravirt: Pass sched_clock save/restore helpers during registration Sean Christopherson
2026-05-15 19:19 ` [PATCH v3 19/41] x86/kvmclock: Move kvm_sched_clock_init() down in kvmclock.c Sean Christopherson
2026-05-15 19:19 ` [PATCH v3 20/41] x86/xen/time: Mark xen_setup_vsyscall_time_info() as __init Sean Christopherson
2026-05-15 19:19 ` [PATCH v3 21/41] x86/pvclock: Mark setup helpers and related various as __init/__ro_after_init Sean Christopherson
2026-05-15 19:19 ` [PATCH v3 22/41] x86/pvclock: WARN if pvclock's valid_flags are overwritten Sean Christopherson
2026-05-15 19:19 ` [PATCH v3 23/41] x86/kvmclock: Refactor handling of PVCLOCK_TSC_STABLE_BIT during kvmclock_init() Sean Christopherson
2026-05-15 19:19 ` [PATCH v3 24/41] timekeeping: Resume clocksources before reading persistent clock Sean Christopherson
2026-05-15 19:19 ` [PATCH v3 25/41] x86/kvmclock: Hook clocksource.suspend/resume when kvmclock isn't sched_clock Sean Christopherson
2026-05-15 19:19 ` [PATCH v3 26/41] x86/kvmclock: WARN if wall clock is read while kvmclock is suspended Sean Christopherson
2026-05-15 19:19 ` [PATCH v3 27/41] x86/kvmclock: Enable kvmclock on APs during onlining if kvmclock isn't sched_clock Sean Christopherson
2026-05-15 19:19 ` [PATCH v3 28/41] x86/paravirt: Mark __paravirt_set_sched_clock() as __init Sean Christopherson
2026-05-15 19:19 ` [PATCH v3 29/41] x86/paravirt: Plumb a return code into __paravirt_set_sched_clock() Sean Christopherson
2026-05-15 19:19 ` [PATCH v3 30/41] x86/paravirt: Don't use a PV sched_clock in CoCo guests with trusted TSC Sean Christopherson
2026-05-15 19:19 ` [PATCH v3 31/41] x86/tsc: Pass KNOWN_FREQ and RELIABLE as params to registration Sean Christopherson
2026-05-15 19:19 ` [PATCH v3 32/41] x86/tsc: Rejects attempts to override TSC calibration with lesser routine Sean Christopherson
2026-05-15 19:19 ` [PATCH v3 33/41] x86/kvmclock: Mark TSC as reliable when it's constant and nonstop Sean Christopherson
2026-05-15 19:19 ` [PATCH v3 34/41] KVM: x86: Officially define CPUID 0x40000010 as PV Timing Info (TSC and Bus) Sean Christopherson
2026-05-15 19:19 ` [PATCH v3 35/41] x86/kvmclock: Obtain TSC frequency from CPUID if present Sean Christopherson
2026-05-15 19:19 ` [PATCH v3 36/41] x86/kvmclock: Get local APIC bus frequency from PV CPUID Timing Info Sean Christopherson
2026-05-15 19:19 ` [PATCH v3 37/41] x86/kvmclock: Use TSC for sched_clock if it's constant and non-stop Sean Christopherson
2026-05-15 19:19 ` [PATCH v3 38/41] x86/paravirt: kvmclock: Setup kvmclock early iff it's sched_clock Sean Christopherson
2026-05-15 19:19 ` [PATCH v3 39/41] x86/paravirt: Move using_native_sched_clock() stub into timer.h Sean Christopherson
2026-05-15 19:19 ` [PATCH v3 40/41] x86/tsc: Add standalone helper for getting CPU frequency from CPUID Sean Christopherson
2026-05-15 19:19 ` [PATCH v3 41/41] x86/kvmclock: Get CPU base frequency from CPUID when it's available 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=20260515191942.1892718-6-seanjc@google.com \
--to=seanjc@google.com \
--cc=ajay.kaher@broadcom.com \
--cc=alexey.makhalov@broadcom.com \
--cc=bcm-kernel-feedback-list@broadcom.com \
--cc=boris.ostrovsky@oracle.com \
--cc=daniel.lezcano@kernel.org \
--cc=dave.hansen@linux.intel.com \
--cc=decui@microsoft.com \
--cc=dwmw@amazon.co.uk \
--cc=haiyangz@microsoft.com \
--cc=jan.kiszka@siemens.com \
--cc=jgross@suse.com \
--cc=jstultz@google.com \
--cc=kas@kernel.org \
--cc=kvm@vger.kernel.org \
--cc=kys@microsoft.com \
--cc=linux-coco@lists.linux.dev \
--cc=linux-hyperv@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=longli@microsoft.com \
--cc=luto@kernel.org \
--cc=mhklinux@outlook.com \
--cc=nikunj@amd.com \
--cc=pbonzini@redhat.com \
--cc=peterz@infradead.org \
--cc=rick.p.edgecombe@intel.com \
--cc=sboyd@kernel.org \
--cc=tglx@kernel.org \
--cc=tglx@linutronix.de \
--cc=thomas.lendacky@amd.com \
--cc=virtualization@lists.linux.dev \
--cc=vkuznets@redhat.com \
--cc=wei.liu@kernel.org \
--cc=x86@kernel.org \
--cc=xen-devel@lists.xenproject.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