Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
Date:   Tue, 30 May 2023 22:35:52 +0800
From:   Zhi Wang <zhi.wang.linux@gmail.com>
To:     isaku.yamahata@intel.com
Cc:     kvm@vger.kernel.org, linux-kernel@vger.kernel.org,
        isaku.yamahata@gmail.com, Paolo Bonzini <pbonzini@redhat.com>,
        erdemaktas@google.com, Sean Christopherson <seanjc@google.com>,
        Sagi Shahar <sagis@google.com>,
        David Matlack <dmatlack@google.com>,
        Kai Huang <kai.huang@intel.com>, chen.bo@intel.com
Subject: Re: [PATCH v14 004/113] KVM: TDX: Initialize the TDX module when
 loading the KVM intel kernel module
Message-ID: <20230530215036.000066d9.zhi.wang.linux@gmail.com>
In-Reply-To: <e628e2d235d9b6c00b9bd5d81bb69136b77d13c4.1685333727.git.isaku.yamahata@intel.com>
References: <cover.1685333727.git.isaku.yamahata@intel.com>
 <e628e2d235d9b6c00b9bd5d81bb69136b77d13c4.1685333727.git.isaku.yamahata@intel.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=US-ASCII
Content-Transfer-Encoding: 7bit
Precedence: bulk

On Sun, 28 May 2023 21:18:46 -0700
isaku.yamahata@intel.com wrote:

> From: Isaku Yamahata <isaku.yamahata@intel.com>
> 
> TDX requires several initialization steps for KVM to create guest TDs.
> Detect CPU feature, enable VMX (TDX is based on VMX) on all online CPUs,
> detect the TDX module availability, initialize it and disable VMX.
> 
> To enable/disable VMX on all online CPUs, utilize
> vmx_hardware_enable/disable().  The method also initializes each CPU for
> TDX.  TDX requires calling a TDX initialization function per logical
> processor (LP) before the LP uses TDX.  When the CPU is becoming online,
> call the TDX LP initialization API.  If it fails to initialize TDX, refuse
> CPU online for simplicity instead of TDX avoiding the failed LP.
> 
> There are several options on when to initialize the TDX module.  A.) kernel
> module loading time, B.) the first guest TD creation time.  A.) was chosen.
> With B.), a user may hit an error of the TDX initialization when trying to
> create the first guest TD.  The machine that fails to initialize the TDX
> module can't boot any guest TD further.  Such failure is undesirable and a
> surprise because the user expects that the machine can accommodate guest
> TD, but not.  So A.) is better than B.).
> 
> Introduce a module parameter, kvm_intel.tdx, to explicitly enable TDX KVM
> support.  It's off by default to keep the same behavior for those who don't
> use TDX.  Implement hardware_setup method to detect TDX feature of CPU and
> initialize TDX module.
> 
> Suggested-by: Sean Christopherson <seanjc@google.com>
> Signed-off-by: Isaku Yamahata <isaku.yamahata@intel.com>
> 
> ---
> Changes v13 -> v14:
> - Use on_each_cpu(vmx_hardware_enable)
> ---
>  arch/x86/kvm/Makefile      |  1 +
>  arch/x86/kvm/vmx/main.c    | 34 ++++++++++++++++++--
>  arch/x86/kvm/vmx/tdx.c     | 63 ++++++++++++++++++++++++++++++++++++++
>  arch/x86/kvm/vmx/x86_ops.h |  8 +++++
>  4 files changed, 104 insertions(+), 2 deletions(-)
>  create mode 100644 arch/x86/kvm/vmx/tdx.c
> 
> diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile
> index 0e894ae23cbc..4b01ab842ab7 100644
> --- a/arch/x86/kvm/Makefile
> +++ b/arch/x86/kvm/Makefile
> @@ -25,6 +25,7 @@ kvm-$(CONFIG_KVM_SMM)	+= smm.o
>  kvm-intel-y		+= vmx/vmx.o vmx/vmenter.o vmx/pmu_intel.o vmx/vmcs12.o \
>  			   vmx/hyperv.o vmx/nested.o vmx/posted_intr.o vmx/main.o
>  kvm-intel-$(CONFIG_X86_SGX_KVM)	+= vmx/sgx.o
> +kvm-intel-$(CONFIG_INTEL_TDX_HOST)	+= vmx/tdx.o
>  
>  kvm-amd-y		+= svm/svm.o svm/vmenter.o svm/pmu.o svm/nested.o svm/avic.o \
>  			   svm/sev.o svm/hyperv.o
> diff --git a/arch/x86/kvm/vmx/main.c b/arch/x86/kvm/vmx/main.c
> index 791ee271393d..2638b344864c 100644
> --- a/arch/x86/kvm/vmx/main.c
> +++ b/arch/x86/kvm/vmx/main.c
> @@ -6,6 +6,36 @@
>  #include "nested.h"
>  #include "pmu.h"
>  
> +static bool enable_tdx __ro_after_init;
> +module_param_named(tdx, enable_tdx, bool, 0444);
> +
> +static int vt_hardware_enable(void)
> +{
> +	int ret;
> +
> +	ret = vmx_hardware_enable();
> +	if (ret || !enable_tdx)
> +		return ret;
> +
> +	ret = tdx_cpu_enable();
> +	if (ret)
> +		vmx_hardware_disable();
> +	return ret;
> +}
> +
> +static __init int vt_hardware_setup(void)
> +{
> +	int ret;
> +
> +	ret = vmx_hardware_setup();
> +	if (ret)
> +		return ret;
> +
> +	enable_tdx = enable_tdx && !tdx_hardware_setup(&vt_x86_ops);
> +
> +	return 0;
> +}
> +
>  #define VMX_REQUIRED_APICV_INHIBITS		       \
>  (						       \
>         BIT(APICV_INHIBIT_REASON_DISABLE)|	       \
> @@ -24,7 +54,7 @@ struct kvm_x86_ops vt_x86_ops __initdata = {
>  
>  	.hardware_unsetup = vmx_hardware_unsetup,
>  
> -	.hardware_enable = vmx_hardware_enable,
> +	.hardware_enable = vt_hardware_enable,
>  	.hardware_disable = vmx_hardware_disable,
>  	.has_emulated_msr = vmx_has_emulated_msr,
>  
> @@ -159,7 +189,7 @@ struct kvm_x86_ops vt_x86_ops __initdata = {
>  };
>  
>  struct kvm_x86_init_ops vt_init_ops __initdata = {
> -	.hardware_setup = vmx_hardware_setup,
> +	.hardware_setup = vt_hardware_setup,
>  	.handle_intel_pt_intr = NULL,
>  
>  	.runtime_ops = &vt_x86_ops,
> diff --git a/arch/x86/kvm/vmx/tdx.c b/arch/x86/kvm/vmx/tdx.c
> new file mode 100644
> index 000000000000..965545a308ad
> --- /dev/null
> +++ b/arch/x86/kvm/vmx/tdx.c
> @@ -0,0 +1,63 @@
> +// SPDX-License-Identifier: GPL-2.0
> +#include <linux/cpu.h>
> +
> +#include <asm/tdx.h>
> +
> +#include "capabilities.h"
> +#include "x86_ops.h"
> +#include "x86.h"
> +
> +#undef pr_fmt
> +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
> +
> +static int __init tdx_module_setup(void)
> +{
> +	int ret;
> +
> +	ret = tdx_enable();
> +	if (ret) {
> +		pr_info("Failed to initialize TDX module.\n");
> +		return ret;
> +	}
> +
> +	return 0;
> +}
> +
> +static void __init vmx_tdx_on(void *info)
> +{
> +       atomic_t *err = info;
> +       int r;
> +
> +       r = vmx_hardware_enable();
> +       if (!r)
> +	       r = tdx_cpu_enable();
> +       if (r)
> +	       atomic_set(err, r);
> +}
> +
> +static void __init vmx_off(void *unused)
> +{
> +       vmx_hardware_disable();
> +}
> +
> +int __init tdx_hardware_setup(struct kvm_x86_ops *x86_ops)
> +{
> +	atomic_t err = ATOMIC_INIT(0);
> +	int r = 0;
> +
> +	if (!enable_ept) {
> +		pr_warn("Cannot enable TDX with EPT disabled\n");
> +		return -EINVAL;
> +	}
> +
> +	/* tdx_enable() in tdx_module_setup() requires cpus lock. */
> +	cpus_read_lock();
> +	on_each_cpu(vmx_tdx_on, &err, true);	/* TDX requires vmxon. */
> +	r = atomic_read(&err);
> +	if (!r)
> +		r = tdx_module_setup();
> +	on_each_cpu(vmx_off, NULL, true);

Out of curiosity, why VMX has to be turned off after tdx_module_setup()?

> +	cpus_read_unlock();
> +
> +	return r;
> +}
> diff --git a/arch/x86/kvm/vmx/x86_ops.h b/arch/x86/kvm/vmx/x86_ops.h
> index 051b5c4b5c2f..f59e5197836a 100644
> --- a/arch/x86/kvm/vmx/x86_ops.h
> +++ b/arch/x86/kvm/vmx/x86_ops.h
> @@ -20,6 +20,8 @@ bool kvm_is_vmx_supported(void);
>  int __init vmx_init(void);
>  void vmx_exit(void);
>  
> +__init int vmx_hardware_setup(void);
> +
>  extern struct kvm_x86_ops vt_x86_ops __initdata;
>  extern struct kvm_x86_init_ops vt_init_ops __initdata;
>  
> @@ -133,4 +135,10 @@ void vmx_cancel_hv_timer(struct kvm_vcpu *vcpu);
>  #endif
>  void vmx_setup_mce(struct kvm_vcpu *vcpu);
>  
> +#ifdef CONFIG_INTEL_TDX_HOST
> +int __init tdx_hardware_setup(struct kvm_x86_ops *x86_ops);
> +#else
> +static inline int tdx_hardware_setup(struct kvm_x86_ops *x86_ops) { return -ENOSYS; }
> +#endif
> +
>  #endif /* __KVM_X86_VMX_X86_OPS_H */