Re: [Patch v4 2/4] KVM: SVM: Add host support for Enhanced SMT Protection

[sashiko-bot@kernel.org]

Thank you for your contribution! Sashiko AI review found 2 potential
issues to consider:
- [Medium] KVM: SVM: spurious LAPIC timer interrupts from
  sev_esmtp_enable_wakeup_icr()
- [Low] KVM: SVM: 32-bit truncation breaks SVM_EXIT_ESMTP_* in
  trace_kvm_exit()
--

commit 3f8afd82427b162ada6d9e482a251e8b54f02146
Author: Pratik R. Sampat <prsampat@amd.com>

KVM: SVM: Add host support for Enhanced SMT Protection

This commit adds KVM host support for AMD Enhanced SMT Protection (ESMTP)
for SEV-SNP guests, including feature detection, VMSA and VMCB setup, idle
wakeup ICR configuration, and handling of the new ESMTP VMEXITs.

> diff --git a/arch/x86/include/uapi/asm/svm.h b/arch/x86/include/uapi/asm/svm.h
> index e806761850921..141386d680a04 100644
> --- a/arch/x86/include/uapi/asm/svm.h
> +++ b/arch/x86/include/uapi/asm/svm.h
> @@ -136,6 +136,10 @@
>  #define SVM_EXIT_SW				0xf0000000ull
>  
>  #define SVM_EXIT_ERR           -1ull
> +/* Enhanced SMT Protection VM exits taken during VMRUN sibling sync */
> +#define SVM_EXIT_ESMTP_ILLSIB  -5ull	/* Illegal ESMTP sibling */
> +#define SVM_EXIT_ESMTP_TIMEOUT -6ull	/* ESMTP_TIMEOUT expired */
> +#define SVM_EXIT_ESMTP_RETRY   -7ull	/* Internal event; retry VMRUN */
>  
>  #define SVM_EXIT_REASONS \
>  	{ SVM_EXIT_READ_CR0,    "read_cr0" }, \
> @@ -248,7 +252,10 @@
>  	{ SVM_VMGEXIT_EXT_GUEST_REQUEST, "vmgexit_ext_guest_request" }, \
>  	{ SVM_VMGEXIT_AP_CREATION,	"vmgexit_ap_creation" }, \
>  	{ SVM_VMGEXIT_HV_FEATURES,	"vmgexit_hypervisor_feature" }, \
> -	{ SVM_EXIT_ERR,         "invalid_guest_state" }
> +	{ SVM_EXIT_ERR,         "invalid_guest_state" }, \
> +	{ SVM_EXIT_ESMTP_ILLSIB,	"esmtp_illsib" }, \
> +	{ SVM_EXIT_ESMTP_TIMEOUT,	"esmtp_timeout" }, \
> +	{ SVM_EXIT_ESMTP_RETRY,		"esmtp_retry" }

[Severity: Low]
Will trace_kvm_exit() ever match these 64-bit SVM_EXIT_ESMTP_* values in
SVM_EXIT_REASONS?

svm_get_exit_info() truncates the 64-bit control->exit_code into a u32
*reason, and TRACE_EVENT_KVM_EXIT stores exit_reason as an unsigned int.
When kvm_print_exit_reason() passes that 32-bit field to
__print_symbolic_u64(exit_reason, SVM_EXIT_REASONS), it zero-extends to
0x00000000fffffffbULL instead of matching -5ull (0xfffffffffffffffbULL),
so ftrace prints raw hex values instead of the symbolic names.

> diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
> index fad72cab76cf4..4748be617134f 100644
> --- a/arch/x86/kvm/svm/sev.c
> +++ b/arch/x86/kvm/svm/sev.c
[ ... ]
> @@ -3312,6 +3329,31 @@ int sev_cpu_init(struct svm_cpu_data *sd)
>  	return 0;
>  }
>  
> +void sev_esmtp_enable_wakeup_icr(void)
> +{
> +	unsigned int cpu, sibling, shift;
> +	u32 core;
> +
> +	if (!(sev_supported_vmsa_features & SVM_SEV_FEAT_ESMTP))
> +		return;
> +
> +	cpu = raw_smp_processor_id();
> +	shift = topology_get_domain_shift(TOPO_CORE_DOMAIN);
> +	core = per_cpu(x86_cpu_to_apicid, cpu) >> shift;
> +
> +	for_each_present_cpu(sibling) {
> +		u32 apicid = per_cpu(x86_cpu_to_apicid, sibling);
> +		u64 icr;
> +
> +		if (sibling == cpu || (apicid >> shift) != core)
> +			continue;
> +
> +		icr = (u64)apicid << 32;
> +		icr |= LOCAL_TIMER_VECTOR;
> +		WARN_ON_ONCE(wrmsrq_safe(MSR_AMD64_IDLE_WAKEUP_ICR, icr));
> +	}
> +}

[Severity: Medium]
Does programming MSR_AMD64_IDLE_WAKEUP_ICR with LOCAL_TIMER_VECTOR inject
spurious local APIC timer interrupts on the sibling CPU whenever this
thread wakes from idle while the sibling is running an ESMTP vCPU?

When the sibling exits guest mode and enables interrupts,
LOCAL_TIMER_VECTOR runs sysvec_apic_timer_interrupt() ->
local_apic_timer_interrupt(), which unconditionally increments APIC_TIMER
IRQ stats and calls evt->event_handler(evt).  When high-resolution timers
are disabled, tick_handle_periodic() and tick_nohz_lowres_handler() do not
check whether dev->next_event has been reached, so every ESMTP wakeup IPI
prematurely advances jiffies and charges a full tick of CPU time via
update_process_times().

Using RESCHEDULE_VECTOR (which KVM already uses to kick CPUs out of guest
mode) would avoid invoking the clockevent handler.

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/cover.1794244450.git.prsampat@amd.com?part=2