On Sun, 2022-08-07 at 15:00 -0700, isaku.yamahata@xxxxxxxxx wrote:
> From: Isaku Yamahata <isaku.yamahata@xxxxxxxxx>
>
> TDX requires several initialization steps for KVM to create guest TDs.
> Detect CPU feature, enable VMX (TDX is based on VMX), detect the TDX module
> availability, and initialize it. This patch implements those steps.
>
> 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 actually not. So A.) is better than B.).
>
> Introduce a module parameter, enable_tdx, to explicitly enable TDX KVM
> support. It's off by default to keep same behavior for those who don't use
> TDX. Implement hardware_setup method to detect TDX feature of CPU.
> Because TDX requires all present CPUs to enable VMX (VMXON). The x86
> specific kvm_arch_post_hardware_enable_setup overrides the existing weak
> symbol of kvm_arch_post_hardware_enable_setup which is called at the KVM
> module initialization.
>
> Suggested-by: Sean Christopherson <seanjc@xxxxxxxxxx>
> Signed-off-by: Isaku Yamahata <isaku.yamahata@xxxxxxxxx>
> ---
> arch/x86/include/asm/kvm_host.h | 1 +
> arch/x86/kvm/Makefile | 1 +
> arch/x86/kvm/vmx/main.c | 29 ++++++++++-
> arch/x86/kvm/vmx/tdx.c | 89 +++++++++++++++++++++++++++++++++
> arch/x86/kvm/vmx/tdx.h | 4 ++
> arch/x86/kvm/vmx/x86_ops.h | 6 +++
> arch/x86/kvm/x86.c | 8 +++
> arch/x86/virt/vmx/tdx/tdx.c | 1 +
> 8 files changed, 138 insertions(+), 1 deletion(-)
> create mode 100644 arch/x86/kvm/vmx/tdx.c
>
> diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
> index 3d000f060077..f432ad32515c 100644
> --- a/arch/x86/include/asm/kvm_host.h
> +++ b/arch/x86/include/asm/kvm_host.h
> @@ -1659,6 +1659,7 @@ struct kvm_x86_init_ops {
> int (*cpu_has_kvm_support)(void);
> int (*disabled_by_bios)(void);
> int (*hardware_setup)(void);
> + int (*post_hardware_enable_setup)(void);
> unsigned int (*handle_intel_pt_intr)(void);
>
> struct kvm_x86_ops *runtime_ops;
> diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile
> index ee4d0999f20f..e2c05195cb95 100644
> --- a/arch/x86/kvm/Makefile
> +++ b/arch/x86/kvm/Makefile
> @@ -24,6 +24,7 @@ kvm-$(CONFIG_KVM_XEN) += xen.o
> kvm-intel-y += vmx/vmx.o vmx/vmenter.o vmx/pmu_intel.o vmx/vmcs12.o \
> vmx/evmcs.o vmx/nested.o vmx/posted_intr.o vmx/main.o
> kvm-intel-$(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
>
> diff --git a/arch/x86/kvm/vmx/main.c b/arch/x86/kvm/vmx/main.c
> index a0252cc0b48d..ac788af17d92 100644
> --- a/arch/x86/kvm/vmx/main.c
> +++ b/arch/x86/kvm/vmx/main.c
> @@ -7,6 +7,32 @@
> #include "pmu.h"
> #include "tdx.h"
>
> +static bool __read_mostly enable_tdx = IS_ENABLED(CONFIG_INTEL_TDX_HOST);
> +module_param_named(tdx, enable_tdx, bool, 0444);
> +
> +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;
> +}
> +
> +static int __init vt_post_hardware_enable_setup(void)
> +{
> + enable_tdx = enable_tdx && !tdx_module_setup();
> + /*
> + * Even if it failed to initialize TDX module, conventional VMX is
> + * available. Keep VMX usable.
> + */
> + return 0;
> +}
> +
> struct kvm_x86_ops vt_x86_ops __initdata = {
> .name = "kvm_intel",
>
> @@ -148,7 +174,8 @@ struct kvm_x86_ops vt_x86_ops __initdata = {
> struct kvm_x86_init_ops vt_init_ops __initdata = {
> .cpu_has_kvm_support = vmx_cpu_has_kvm_support,
> .disabled_by_bios = vmx_disabled_by_bios,
> - .hardware_setup = vmx_hardware_setup,
> + .hardware_setup = vt_hardware_setup,
> + .post_hardware_enable_setup = vt_post_hardware_enable_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..e9a17f3666de
> --- /dev/null
> +++ b/arch/x86/kvm/vmx/tdx.c
> @@ -0,0 +1,89 @@
> +// SPDX-License-Identifier: GPL-2.0
> +#include <linux/cpu.h>
> +
> +#include <asm/tdx.h>
> +
> +#include "capabilities.h"
> +#include "x86_ops.h"
> +#include "tdx.h"
> +
> +#undef pr_fmt
> +#define pr_fmt(fmt) "tdx: " fmt
> +
> +#define TDX_MAX_NR_CPUID_CONFIGS \
> + ((sizeof(struct tdsysinfo_struct) - \
> + offsetof(struct tdsysinfo_struct, cpuid_configs)) \
> + / sizeof(struct tdx_cpuid_config))
> +
> +struct tdx_capabilities {
> + u8 tdcs_nr_pages;
> + u8 tdvpx_nr_pages;
> +
> + u64 attrs_fixed0;
> + u64 attrs_fixed1;
> + u64 xfam_fixed0;
> + u64 xfam_fixed1;
> +
> + u32 nr_cpuid_configs;
> + struct tdx_cpuid_config cpuid_configs[TDX_MAX_NR_CPUID_CONFIGS];
> +};
> +
> +/* Capabilities of KVM + the TDX module. */
> +static struct tdx_capabilities tdx_caps;
> +
> +int __init tdx_module_setup(void)
> +{
> + const struct tdsysinfo_struct *tdsysinfo;
> + int ret = 0;
> +
> + BUILD_BUG_ON(sizeof(*tdsysinfo) != 1024);
> + BUILD_BUG_ON(TDX_MAX_NR_CPUID_CONFIGS != 37);
> +
> + ret = tdx_init();
> + if (ret) {
> + pr_info("Failed to initialize TDX module.\n");
> + return ret;
> + }
> +
> + tdsysinfo = tdx_get_sysinfo();
> + if (tdsysinfo->num_cpuid_config > TDX_MAX_NR_CPUID_CONFIGS)
> + return -EIO;
> +
> + tdx_caps = (struct tdx_capabilities) {
> + .tdcs_nr_pages = tdsysinfo->tdcs_base_size / PAGE_SIZE,
> + /*
> + * TDVPS = TDVPR(4K page) + TDVPX(multiple 4K pages).
> + * -1 for TDVPR.
> + */
> + .tdvpx_nr_pages = tdsysinfo->tdvps_base_size / PAGE_SIZE - 1,
> + .attrs_fixed0 = tdsysinfo->attributes_fixed0,
> + .attrs_fixed1 = tdsysinfo->attributes_fixed1,
> + .xfam_fixed0 = tdsysinfo->xfam_fixed0,
> + .xfam_fixed1 = tdsysinfo->xfam_fixed1,
> + .nr_cpuid_configs = tdsysinfo->num_cpuid_config,
> + };
> + if (!memcpy(tdx_caps.cpuid_configs, tdsysinfo->cpuid_configs,
> + tdsysinfo->num_cpuid_config *
> + sizeof(struct tdx_cpuid_config)))
> + return -EIO;
> +
> + return 0;
> +}
> +
> +int __init tdx_hardware_setup(struct kvm_x86_ops *x86_ops)
Function argument isn't used.
> +{
> + if (!enable_ept) {
> + pr_warn("Cannot enable TDX with EPT disabled\n");
> + return -EINVAL;
> + }
> +
> + if (!platform_tdx_enabled()) {
> + pr_warn("Cannot enable TDX on TDX disabled platform\n");
> + return -ENODEV;
> + }
I am not sure whether this is necessary, as tdx_init() will call it internally
anyway.
> +
> + pr_info("kvm: TDX is supported. x86 phys bits %d\n",
> + boot_cpu_data.x86_phys_bits);
Is it a little early to say "TDX is supported" before tdx_init() is called?
I don't think the whole tdx_hardware_setup() is even necessary? Looks nothing
is serious here anyway, and all staff can be done in tdx_module_setup().
> +
> + return 0;
> +}
> diff --git a/arch/x86/kvm/vmx/tdx.h b/arch/x86/kvm/vmx/tdx.h
> index 060bf48ec3d6..54d7a26ed9ee 100644
> --- a/arch/x86/kvm/vmx/tdx.h
> +++ b/arch/x86/kvm/vmx/tdx.h
> @@ -3,6 +3,8 @@
> #define __KVM_X86_TDX_H
>
> #ifdef CONFIG_INTEL_TDX_HOST
> +int tdx_module_setup(void);
> +
> struct kvm_tdx {
> struct kvm kvm;
> /* TDX specific members follow. */
> @@ -37,6 +39,8 @@ static inline struct vcpu_tdx *to_tdx(struct kvm_vcpu *vcpu)
> return container_of(vcpu, struct vcpu_tdx, vcpu);
> }
> #else
> +static inline int tdx_module_setup(void) { return -ENODEV; };
> +
> struct kvm_tdx {
> struct kvm kvm;
> };
> diff --git a/arch/x86/kvm/vmx/x86_ops.h b/arch/x86/kvm/vmx/x86_ops.h
> index 90a8c6824833..f318a6258a24 100644
> --- a/arch/x86/kvm/vmx/x86_ops.h
> +++ b/arch/x86/kvm/vmx/x86_ops.h
> @@ -128,4 +128,10 @@ 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 0; }
> +#endif
> +
> #endif /* __KVM_X86_VMX_X86_OPS_H */
> diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
> index e533cce7a70b..32a2ef718112 100644
> --- a/arch/x86/kvm/x86.c
> +++ b/arch/x86/kvm/x86.c
> @@ -11983,6 +11983,14 @@ int kvm_arch_hardware_setup(void *opaque)
> return 0;
> }
>
> +int kvm_arch_post_hardware_enable_setup(void *opaque)
> +{
> + struct kvm_x86_init_ops *ops = opaque;
> + if (ops->post_hardware_enable_setup)
> + return ops->post_hardware_enable_setup();
> + return 0;
> +}
> +
> void kvm_arch_hardware_unsetup(void)
> {
> kvm_unregister_perf_callbacks();
> diff --git a/arch/x86/virt/vmx/tdx/tdx.c b/arch/x86/virt/vmx/tdx/tdx.c
> index b9567a2217df..918e79159bbf 100644
> --- a/arch/x86/virt/vmx/tdx/tdx.c
> +++ b/arch/x86/virt/vmx/tdx/tdx.c
> @@ -1283,6 +1283,7 @@ bool platform_tdx_enabled(void)
> {
> return tdx_keyid_num >= 2;
> }
> +EXPORT_SYMBOL_GPL(platform_tdx_enabled);
>
> /**
> * tdx_init - Initialize the TDX module
