Re: [PATCH v6 7/7] KVM: TDX: Explicitly do WBINVD when no more TDX SEAMCALLs

[Sean Christopherson <seanjc@google.com>]

On Thu, Aug 14, 2025, Kai Huang wrote:
>  arch/x86/include/asm/tdx.h  |  2 ++
>  arch/x86/kvm/vmx/tdx.c      | 12 ++++++++++++
>  arch/x86/virt/vmx/tdx/tdx.c | 12 ++++++++++++
>  3 files changed, 26 insertions(+)
> 
> diff --git a/arch/x86/include/asm/tdx.h b/arch/x86/include/asm/tdx.h
> index 0922265c6bdc..e9a213582f03 100644
> --- a/arch/x86/include/asm/tdx.h
> +++ b/arch/x86/include/asm/tdx.h
> @@ -217,6 +217,7 @@ u64 tdh_mem_page_remove(struct tdx_td *td, u64 gpa, u64 level, u64 *ext_err1, u6
>  u64 tdh_phymem_cache_wb(bool resume);
>  u64 tdh_phymem_page_wbinvd_tdr(struct tdx_td *td);
>  u64 tdh_phymem_page_wbinvd_hkid(u64 hkid, struct page *page);
> +void tdx_cpu_flush_cache(void);
>  #else
>  static inline void tdx_init(void) { }
>  static inline int tdx_cpu_enable(void) { return -ENODEV; }
> @@ -224,6 +225,7 @@ static inline int tdx_enable(void)  { return -ENODEV; }
>  static inline u32 tdx_get_nr_guest_keyids(void) { return 0; }
>  static inline const char *tdx_dump_mce_info(struct mce *m) { return NULL; }
>  static inline const struct tdx_sys_info *tdx_get_sysinfo(void) { return NULL; }
> +static inline void tdx_cpu_flush_cache(void) { }

Stub is unnecessary.  tdx.c is built iff KVM_INTEL_TDX=y, and that depends on
INTEL_TDX_HOST.

At a glance, some of the existing stubs are useless as well.

>  #endif	/* CONFIG_INTEL_TDX_HOST */
>  
>  #endif /* !__ASSEMBLER__ */
> diff --git a/arch/x86/kvm/vmx/tdx.c b/arch/x86/kvm/vmx/tdx.c
> index 66744f5768c8..1bc6f52e0cd7 100644
> --- a/arch/x86/kvm/vmx/tdx.c
> +++ b/arch/x86/kvm/vmx/tdx.c
> @@ -442,6 +442,18 @@ void tdx_disable_virtualization_cpu(void)
>  		tdx_flush_vp(&arg);
>  	}
>  	local_irq_restore(flags);
> +
> +	/*
> +	 * No more TDX activity on this CPU from here.  Flush cache to
> +	 * avoid having to do WBINVD in stop_this_cpu() during kexec.
> +	 *
> +	 * Kexec calls native_stop_other_cpus() to stop remote CPUs
> +	 * before booting to new kernel, but that code has a "race"
> +	 * when the normal REBOOT IPI times out and NMIs are sent to
> +	 * remote CPUs to stop them.  Doing WBINVD in stop_this_cpu()
> +	 * could potentially increase the possibility of the "race".
> +	 */
> +	tdx_cpu_flush_cache();

IIUC, this can be:

	if (IS_ENABLED(CONFIG_KEXEC))
		tdx_cpu_flush_cache();

>  }
>  
>  #define TDX_SEAMCALL_RETRIES 10000
> diff --git a/arch/x86/virt/vmx/tdx/tdx.c b/arch/x86/virt/vmx/tdx/tdx.c
> index 3ea6f587c81a..c26e2e07ff6b 100644
> --- a/arch/x86/virt/vmx/tdx/tdx.c
> +++ b/arch/x86/virt/vmx/tdx/tdx.c
> @@ -1870,3 +1870,15 @@ u64 tdh_phymem_page_wbinvd_hkid(u64 hkid, struct page *page)
>  	return seamcall(TDH_PHYMEM_PAGE_WBINVD, &args);
>  }
>  EXPORT_SYMBOL_GPL(tdh_phymem_page_wbinvd_hkid);
> +
> +void tdx_cpu_flush_cache(void)
> +{
> +	lockdep_assert_preemption_disabled();
> +
> +	if (!this_cpu_read(cache_state_incoherent))
> +		return;
> +
> +	wbinvd();
> +	this_cpu_write(cache_state_incoherent, false);
> +}
> +EXPORT_SYMBOL_GPL(tdx_cpu_flush_cache);
> -- 
> 2.50.1
>