From 1001d9886f25a88c3b6a097bea98572c1f9b9380 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Wed, 30 Oct 2024 12:00:26 -0700 Subject: [PATCH 01/16] KVM: TDX: Add TDX "architectural" error codes Add error codes for the TDX SEAMCALLs both for TDX VMM side for TDH SEAMCALL and TDX guest side for TDG.VP.VMCALL. KVM issues the TDX SEAMCALLs and checks its error code. KVM handles hypercall from the TDX guest and may return an error. So error code for the TDX guest is also needed. TDX SEAMCALL uses bits 31:0 to return more information, so these error codes will only exactly match RAX[63:32]. Error codes for TDG.VP.VMCALL is defined by TDX Guest-Host-Communication interface spec. Signed-off-by: Sean Christopherson Signed-off-by: Isaku Yamahata Signed-off-by: Rick Edgecombe Reviewed-by: Paolo Bonzini Reviewed-by: Yuan Yao Reviewed-by: Xiaoyao Li Message-ID: <20241030190039.77971-14-rick.p.edgecombe@intel.com> Signed-off-by: Paolo Bonzini --- arch/x86/include/asm/shared/tdx.h | 7 +++++- arch/x86/kvm/vmx/tdx.h | 1 + arch/x86/kvm/vmx/tdx_errno.h | 36 +++++++++++++++++++++++++++++++ 3 files changed, 43 insertions(+), 1 deletion(-) create mode 100644 arch/x86/kvm/vmx/tdx_errno.h diff --git a/arch/x86/include/asm/shared/tdx.h b/arch/x86/include/asm/shared/tdx.h index fcbbef484a78..4aedab1f2a1a 100644 --- a/arch/x86/include/asm/shared/tdx.h +++ b/arch/x86/include/asm/shared/tdx.h @@ -71,7 +71,12 @@ #define TDVMCALL_GET_QUOTE 0x10002 #define TDVMCALL_REPORT_FATAL_ERROR 0x10003 -#define TDVMCALL_STATUS_RETRY 1 +/* + * TDG.VP.VMCALL Status Codes (returned in R10) + */ +#define TDVMCALL_STATUS_SUCCESS 0x0000000000000000ULL +#define TDVMCALL_STATUS_RETRY 0x0000000000000001ULL +#define TDVMCALL_STATUS_INVALID_OPERAND 0x8000000000000000ULL /* * Bitmasks of exposed registers (with VMM). diff --git a/arch/x86/kvm/vmx/tdx.h b/arch/x86/kvm/vmx/tdx.h index cf050c78ad65..f1e861cbee3b 100644 --- a/arch/x86/kvm/vmx/tdx.h +++ b/arch/x86/kvm/vmx/tdx.h @@ -3,6 +3,7 @@ #define __KVM_X86_VMX_TDX_H #include "tdx_arch.h" +#include "tdx_errno.h" #ifdef CONFIG_KVM_INTEL_TDX int tdx_bringup(void); diff --git a/arch/x86/kvm/vmx/tdx_errno.h b/arch/x86/kvm/vmx/tdx_errno.h new file mode 100644 index 000000000000..dc3fa2a58c2c --- /dev/null +++ b/arch/x86/kvm/vmx/tdx_errno.h @@ -0,0 +1,36 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* architectural status code for SEAMCALL */ + +#ifndef __KVM_X86_TDX_ERRNO_H +#define __KVM_X86_TDX_ERRNO_H + +#define TDX_SEAMCALL_STATUS_MASK 0xFFFFFFFF00000000ULL + +/* + * TDX SEAMCALL Status Codes (returned in RAX) + */ +#define TDX_NON_RECOVERABLE_VCPU 0x4000000100000000ULL +#define TDX_INTERRUPTED_RESUMABLE 0x8000000300000000ULL +#define TDX_OPERAND_INVALID 0xC000010000000000ULL +#define TDX_OPERAND_BUSY 0x8000020000000000ULL +#define TDX_PREVIOUS_TLB_EPOCH_BUSY 0x8000020100000000ULL +#define TDX_PAGE_METADATA_INCORRECT 0xC000030000000000ULL +#define TDX_VCPU_NOT_ASSOCIATED 0x8000070200000000ULL +#define TDX_KEY_GENERATION_FAILED 0x8000080000000000ULL +#define TDX_KEY_STATE_INCORRECT 0xC000081100000000ULL +#define TDX_KEY_CONFIGURED 0x0000081500000000ULL +#define TDX_NO_HKID_READY_TO_WBCACHE 0x0000082100000000ULL +#define TDX_FLUSHVP_NOT_DONE 0x8000082400000000ULL +#define TDX_EPT_WALK_FAILED 0xC0000B0000000000ULL +#define TDX_EPT_ENTRY_STATE_INCORRECT 0xC0000B0D00000000ULL + +/* + * TDX module operand ID, appears in 31:0 part of error code as + * detail information + */ +#define TDX_OPERAND_ID_RCX 0x01 +#define TDX_OPERAND_ID_TDR 0x80 +#define TDX_OPERAND_ID_SEPT 0x92 +#define TDX_OPERAND_ID_TD_EPOCH 0xa9 + +#endif /* __KVM_X86_TDX_ERRNO_H */ -- 2.51.0 From e4aa6f6961f40249df9923acc4921c75036af3fc Mon Sep 17 00:00:00 2001 From: Isaku Yamahata Date: Wed, 30 Oct 2024 12:00:27 -0700 Subject: [PATCH 02/16] KVM: TDX: Add helper functions to print TDX SEAMCALL error Add helper functions to print out errors from the TDX module in a uniform manner. Signed-off-by: Isaku Yamahata Co-developed-by: Tony Lindgren Signed-off-by: Tony Lindgren Signed-off-by: Rick Edgecombe Reviewed-by: Binbin Wu Reviewed-by: Yuan Yao Signed-off-by: Paolo Bonzini --- arch/x86/kvm/vmx/tdx.c | 15 +++++++++++++++ 1 file changed, 15 insertions(+) diff --git a/arch/x86/kvm/vmx/tdx.c b/arch/x86/kvm/vmx/tdx.c index c319eb44d9f9..8928b27547c1 100644 --- a/arch/x86/kvm/vmx/tdx.c +++ b/arch/x86/kvm/vmx/tdx.c @@ -10,6 +10,21 @@ #undef pr_fmt #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt +#define pr_tdx_error(__fn, __err) \ + pr_err_ratelimited("SEAMCALL %s failed: 0x%llx\n", #__fn, __err) + +#define __pr_tdx_error_N(__fn_str, __err, __fmt, ...) \ + pr_err_ratelimited("SEAMCALL " __fn_str " failed: 0x%llx, " __fmt, __err, __VA_ARGS__) + +#define pr_tdx_error_1(__fn, __err, __rcx) \ + __pr_tdx_error_N(#__fn, __err, "rcx 0x%llx\n", __rcx) + +#define pr_tdx_error_2(__fn, __err, __rcx, __rdx) \ + __pr_tdx_error_N(#__fn, __err, "rcx 0x%llx, rdx 0x%llx\n", __rcx, __rdx) + +#define pr_tdx_error_3(__fn, __err, __rcx, __rdx, __r8) \ + __pr_tdx_error_N(#__fn, __err, "rcx 0x%llx, rdx 0x%llx, r8 0x%llx\n", __rcx, __rdx, __r8) + bool enable_tdx __ro_after_init; module_param_named(tdx, enable_tdx, bool, 0444); -- 2.51.0 From b2aaf38ced6905b812109915e6a94ed1a9c5bb0e Mon Sep 17 00:00:00 2001 From: Isaku Yamahata Date: Wed, 30 Oct 2024 12:00:28 -0700 Subject: [PATCH 03/16] KVM: TDX: Add place holder for TDX VM specific mem_enc_op ioctl KVM_MEMORY_ENCRYPT_OP was introduced for VM-scoped operations specific for guest state-protected VM. It defined subcommands for technology-specific operations under KVM_MEMORY_ENCRYPT_OP. Despite its name, the subcommands are not limited to memory encryption, but various technology-specific operations are defined. It's natural to repurpose KVM_MEMORY_ENCRYPT_OP for TDX specific operations and define subcommands. Add a place holder function for TDX specific VM-scoped ioctl as mem_enc_op. TDX specific sub-commands will be added to retrieve/pass TDX specific parameters. Make mem_enc_ioctl non-optional as it's always filled. Signed-off-by: Isaku Yamahata Co-developed-by: Tony Lindgren Signed-off-by: Tony Lindgren Signed-off-by: Rick Edgecombe --- - Drop the misleading "defined for consistency" line. It's a copy-paste error introduced in the earlier patches. Earlier there was padding at the end to match struct kvm_sev_cmd size. (Tony) Signed-off-by: Paolo Bonzini --- arch/x86/include/asm/kvm-x86-ops.h | 2 +- arch/x86/include/uapi/asm/kvm.h | 23 +++++++++++++++++++++ arch/x86/kvm/vmx/main.c | 10 ++++++++++ arch/x86/kvm/vmx/tdx.c | 32 ++++++++++++++++++++++++++++++ arch/x86/kvm/vmx/x86_ops.h | 6 ++++++ arch/x86/kvm/x86.c | 4 ---- 6 files changed, 72 insertions(+), 5 deletions(-) diff --git a/arch/x86/include/asm/kvm-x86-ops.h b/arch/x86/include/asm/kvm-x86-ops.h index 823c0434bbad..1eca04087cf4 100644 --- a/arch/x86/include/asm/kvm-x86-ops.h +++ b/arch/x86/include/asm/kvm-x86-ops.h @@ -125,7 +125,7 @@ KVM_X86_OP(leave_smm) KVM_X86_OP(enable_smi_window) #endif KVM_X86_OP_OPTIONAL(dev_get_attr) -KVM_X86_OP_OPTIONAL(mem_enc_ioctl) +KVM_X86_OP(mem_enc_ioctl) KVM_X86_OP_OPTIONAL(mem_enc_register_region) KVM_X86_OP_OPTIONAL(mem_enc_unregister_region) KVM_X86_OP_OPTIONAL(vm_copy_enc_context_from) diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h index 9e75da97bce0..2b0317b47e47 100644 --- a/arch/x86/include/uapi/asm/kvm.h +++ b/arch/x86/include/uapi/asm/kvm.h @@ -927,4 +927,27 @@ struct kvm_hyperv_eventfd { #define KVM_X86_SNP_VM 4 #define KVM_X86_TDX_VM 5 +/* Trust Domain eXtension sub-ioctl() commands. */ +enum kvm_tdx_cmd_id { + KVM_TDX_CMD_NR_MAX, +}; + +struct kvm_tdx_cmd { + /* enum kvm_tdx_cmd_id */ + __u32 id; + /* flags for sub-commend. If sub-command doesn't use this, set zero. */ + __u32 flags; + /* + * data for each sub-command. An immediate or a pointer to the actual + * data in process virtual address. If sub-command doesn't use it, + * set zero. + */ + __u64 data; + /* + * Auxiliary error code. The sub-command may return TDX SEAMCALL + * status code in addition to -Exxx. + */ + __u64 hw_error; +}; + #endif /* _ASM_X86_KVM_H */ diff --git a/arch/x86/kvm/vmx/main.c b/arch/x86/kvm/vmx/main.c index 5c1acc88feef..69c65085f81a 100644 --- a/arch/x86/kvm/vmx/main.c +++ b/arch/x86/kvm/vmx/main.c @@ -41,6 +41,14 @@ static __init int vt_hardware_setup(void) return 0; } +static int vt_mem_enc_ioctl(struct kvm *kvm, void __user *argp) +{ + if (!is_td(kvm)) + return -ENOTTY; + + return tdx_vm_ioctl(kvm, argp); +} + #define VMX_REQUIRED_APICV_INHIBITS \ (BIT(APICV_INHIBIT_REASON_DISABLED) | \ BIT(APICV_INHIBIT_REASON_ABSENT) | \ @@ -193,6 +201,8 @@ struct kvm_x86_ops vt_x86_ops __initdata = { .vcpu_deliver_sipi_vector = kvm_vcpu_deliver_sipi_vector, .get_untagged_addr = vmx_get_untagged_addr, + + .mem_enc_ioctl = vt_mem_enc_ioctl, }; struct kvm_x86_init_ops vt_init_ops __initdata = { diff --git a/arch/x86/kvm/vmx/tdx.c b/arch/x86/kvm/vmx/tdx.c index 8928b27547c1..a20de9db315f 100644 --- a/arch/x86/kvm/vmx/tdx.c +++ b/arch/x86/kvm/vmx/tdx.c @@ -3,6 +3,7 @@ #include #include #include "capabilities.h" +#include "x86_ops.h" #include "tdx.h" #pragma GCC poison to_vmx @@ -42,6 +43,37 @@ static __always_inline struct vcpu_tdx *to_tdx(struct kvm_vcpu *vcpu) return container_of(vcpu, struct vcpu_tdx, vcpu); } +int tdx_vm_ioctl(struct kvm *kvm, void __user *argp) +{ + struct kvm_tdx_cmd tdx_cmd; + int r; + + if (copy_from_user(&tdx_cmd, argp, sizeof(struct kvm_tdx_cmd))) + return -EFAULT; + + /* + * Userspace should never set hw_error. It is used to fill + * hardware-defined error by the kernel. + */ + if (tdx_cmd.hw_error) + return -EINVAL; + + mutex_lock(&kvm->lock); + + switch (tdx_cmd.id) { + default: + r = -EINVAL; + goto out; + } + + if (copy_to_user(argp, &tdx_cmd, sizeof(struct kvm_tdx_cmd))) + r = -EFAULT; + +out: + mutex_unlock(&kvm->lock); + return r; +} + static int tdx_online_cpu(unsigned int cpu) { unsigned long flags; diff --git a/arch/x86/kvm/vmx/x86_ops.h b/arch/x86/kvm/vmx/x86_ops.h index 430773a5ef8e..75e0ca29a39e 100644 --- a/arch/x86/kvm/vmx/x86_ops.h +++ b/arch/x86/kvm/vmx/x86_ops.h @@ -121,4 +121,10 @@ void vmx_cancel_hv_timer(struct kvm_vcpu *vcpu); #endif void vmx_setup_mce(struct kvm_vcpu *vcpu); +#ifdef CONFIG_KVM_INTEL_TDX +int tdx_vm_ioctl(struct kvm *kvm, void __user *argp); +#else +static inline int tdx_vm_ioctl(struct kvm *kvm, void __user *argp) { return -EOPNOTSUPP; } +#endif + #endif /* __KVM_X86_VMX_X86_OPS_H */ diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index eceb97734646..2434da7ac973 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -7289,10 +7289,6 @@ set_pit2_out: goto out; } case KVM_MEMORY_ENCRYPT_OP: { - r = -ENOTTY; - if (!kvm_x86_ops.mem_enc_ioctl) - goto out; - r = kvm_x86_call(mem_enc_ioctl)(kvm, argp); break; } -- 2.51.0 From 61bb28279623b636bb368ca37dc6c93a414170a3 Mon Sep 17 00:00:00 2001 From: Isaku Yamahata Date: Wed, 30 Oct 2024 12:00:29 -0700 Subject: [PATCH 04/16] KVM: TDX: Get system-wide info about TDX module on initialization TDX KVM needs system-wide information about the TDX module. Generate the data based on tdx_sysinfo td_conf CPUID data. Signed-off-by: Isaku Yamahata Co-developed-by: Xiaoyao Li Signed-off-by: Xiaoyao Li Co-developed-by: Tony Lindgren Signed-off-by: Tony Lindgren Signed-off-by: Rick Edgecombe Reviewed-by: Binbin Wu --- - Clarify comment about EAX[23:16] in td_init_cpuid_entry2() (Xiaoyao) - Add comment for configurable CPUID bits (Xiaoyao) Signed-off-by: Paolo Bonzini --- arch/x86/include/uapi/asm/kvm.h | 11 +++ arch/x86/kvm/vmx/tdx.c | 137 ++++++++++++++++++++++++++++++++ arch/x86/kvm/vmx/tdx_arch.h | 2 + 3 files changed, 150 insertions(+) diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h index 2b0317b47e47..8a4633cdb247 100644 --- a/arch/x86/include/uapi/asm/kvm.h +++ b/arch/x86/include/uapi/asm/kvm.h @@ -929,6 +929,8 @@ struct kvm_hyperv_eventfd { /* Trust Domain eXtension sub-ioctl() commands. */ enum kvm_tdx_cmd_id { + KVM_TDX_CAPABILITIES = 0, + KVM_TDX_CMD_NR_MAX, }; @@ -950,4 +952,13 @@ struct kvm_tdx_cmd { __u64 hw_error; }; +struct kvm_tdx_capabilities { + __u64 supported_attrs; + __u64 supported_xfam; + __u64 reserved[254]; + + /* Configurable CPUID bits for userspace */ + struct kvm_cpuid2 cpuid; +}; + #endif /* _ASM_X86_KVM_H */ diff --git a/arch/x86/kvm/vmx/tdx.c b/arch/x86/kvm/vmx/tdx.c index a20de9db315f..3e7dc251e5e0 100644 --- a/arch/x86/kvm/vmx/tdx.c +++ b/arch/x86/kvm/vmx/tdx.c @@ -33,6 +33,8 @@ static enum cpuhp_state tdx_cpuhp_state; static const struct tdx_sys_info *tdx_sysinfo; +#define KVM_SUPPORTED_TD_ATTRS (TDX_TD_ATTR_SEPT_VE_DISABLE) + static __always_inline struct kvm_tdx *to_kvm_tdx(struct kvm *kvm) { return container_of(kvm, struct kvm_tdx, kvm); @@ -43,6 +45,129 @@ static __always_inline struct vcpu_tdx *to_tdx(struct kvm_vcpu *vcpu) return container_of(vcpu, struct vcpu_tdx, vcpu); } +static u64 tdx_get_supported_attrs(const struct tdx_sys_info_td_conf *td_conf) +{ + u64 val = KVM_SUPPORTED_TD_ATTRS; + + if ((val & td_conf->attributes_fixed1) != td_conf->attributes_fixed1) + return 0; + + val &= td_conf->attributes_fixed0; + + return val; +} + +static u64 tdx_get_supported_xfam(const struct tdx_sys_info_td_conf *td_conf) +{ + u64 val = kvm_caps.supported_xcr0 | kvm_caps.supported_xss; + + if ((val & td_conf->xfam_fixed1) != td_conf->xfam_fixed1) + return 0; + + val &= td_conf->xfam_fixed0; + + return val; +} + +static u32 tdx_set_guest_phys_addr_bits(const u32 eax, int addr_bits) +{ + return (eax & ~GENMASK(23, 16)) | (addr_bits & 0xff) << 16; +} + +#define KVM_TDX_CPUID_NO_SUBLEAF ((__u32)-1) + +static void td_init_cpuid_entry2(struct kvm_cpuid_entry2 *entry, unsigned char idx) +{ + const struct tdx_sys_info_td_conf *td_conf = &tdx_sysinfo->td_conf; + + entry->function = (u32)td_conf->cpuid_config_leaves[idx]; + entry->index = td_conf->cpuid_config_leaves[idx] >> 32; + entry->eax = (u32)td_conf->cpuid_config_values[idx][0]; + entry->ebx = td_conf->cpuid_config_values[idx][0] >> 32; + entry->ecx = (u32)td_conf->cpuid_config_values[idx][1]; + entry->edx = td_conf->cpuid_config_values[idx][1] >> 32; + + if (entry->index == KVM_TDX_CPUID_NO_SUBLEAF) + entry->index = 0; + + /* + * The TDX module doesn't allow configuring the guest phys addr bits + * (EAX[23:16]). However, KVM uses it as an interface to the userspace + * to configure the GPAW. Report these bits as configurable. + */ + if (entry->function == 0x80000008) + entry->eax = tdx_set_guest_phys_addr_bits(entry->eax, 0xff); +} + +static int init_kvm_tdx_caps(const struct tdx_sys_info_td_conf *td_conf, + struct kvm_tdx_capabilities *caps) +{ + int i; + + caps->supported_attrs = tdx_get_supported_attrs(td_conf); + if (!caps->supported_attrs) + return -EIO; + + caps->supported_xfam = tdx_get_supported_xfam(td_conf); + if (!caps->supported_xfam) + return -EIO; + + caps->cpuid.nent = td_conf->num_cpuid_config; + + for (i = 0; i < td_conf->num_cpuid_config; i++) + td_init_cpuid_entry2(&caps->cpuid.entries[i], i); + + return 0; +} + +static int tdx_get_capabilities(struct kvm_tdx_cmd *cmd) +{ + const struct tdx_sys_info_td_conf *td_conf = &tdx_sysinfo->td_conf; + struct kvm_tdx_capabilities __user *user_caps; + struct kvm_tdx_capabilities *caps = NULL; + int ret = 0; + + /* flags is reserved for future use */ + if (cmd->flags) + return -EINVAL; + + caps = kmalloc(sizeof(*caps) + + sizeof(struct kvm_cpuid_entry2) * td_conf->num_cpuid_config, + GFP_KERNEL); + if (!caps) + return -ENOMEM; + + user_caps = u64_to_user_ptr(cmd->data); + if (copy_from_user(caps, user_caps, sizeof(*caps))) { + ret = -EFAULT; + goto out; + } + + if (caps->cpuid.nent < td_conf->num_cpuid_config) { + ret = -E2BIG; + goto out; + } + + ret = init_kvm_tdx_caps(td_conf, caps); + if (ret) + goto out; + + if (copy_to_user(user_caps, caps, sizeof(*caps))) { + ret = -EFAULT; + goto out; + } + + if (copy_to_user(user_caps->cpuid.entries, caps->cpuid.entries, + caps->cpuid.nent * + sizeof(caps->cpuid.entries[0]))) + ret = -EFAULT; + +out: + /* kfree() accepts NULL. */ + kfree(caps); + return ret; +} + int tdx_vm_ioctl(struct kvm *kvm, void __user *argp) { struct kvm_tdx_cmd tdx_cmd; @@ -61,6 +186,9 @@ int tdx_vm_ioctl(struct kvm *kvm, void __user *argp) mutex_lock(&kvm->lock); switch (tdx_cmd.id) { + case KVM_TDX_CAPABILITIES: + r = tdx_get_capabilities(&tdx_cmd); + break; default: r = -EINVAL; goto out; @@ -160,11 +288,20 @@ static int __init __tdx_bringup(void) goto get_sysinfo_err; } + /* Check TDX module and KVM capabilities */ + if (!tdx_get_supported_attrs(&tdx_sysinfo->td_conf) || + !tdx_get_supported_xfam(&tdx_sysinfo->td_conf)) + goto get_sysinfo_err; + + if (!(tdx_sysinfo->features.tdx_features0 & MD_FIELD_ID_FEATURES0_TOPOLOGY_ENUM)) + goto get_sysinfo_err; + /* * Leave hardware virtualization enabled after TDX is enabled * successfully. TDX CPU hotplug depends on this. */ return 0; + get_sysinfo_err: __tdx_cleanup(); tdx_bringup_err: diff --git a/arch/x86/kvm/vmx/tdx_arch.h b/arch/x86/kvm/vmx/tdx_arch.h index f092d8e7e6f5..0e09188a8785 100644 --- a/arch/x86/kvm/vmx/tdx_arch.h +++ b/arch/x86/kvm/vmx/tdx_arch.h @@ -121,4 +121,6 @@ struct td_params { #define TDX_MIN_TSC_FREQUENCY_KHZ (100 * 1000) #define TDX_MAX_TSC_FREQUENCY_KHZ (10 * 1000 * 1000) +#define MD_FIELD_ID_FEATURES0_TOPOLOGY_ENUM BIT_ULL(20) + #endif /* __KVM_X86_TDX_ARCH_H */ -- 2.51.0 From 8d032b683c299302aa8b5fbce17b9b87a138a5f5 Mon Sep 17 00:00:00 2001 From: Isaku Yamahata Date: Tue, 25 Feb 2025 12:45:13 -0500 Subject: [PATCH 05/16] KVM: TDX: create/destroy VM structure Implement managing the TDX private KeyID to implement, create, destroy and free for a TDX guest. When creating at TDX guest, assign a TDX private KeyID for the TDX guest for memory encryption, and allocate pages for the guest. These are used for the Trust Domain Root (TDR) and Trust Domain Control Structure (TDCS). On destruction, free the allocated pages, and the KeyID. Before tearing down the private page tables, TDX requires the guest TD to be destroyed by reclaiming the KeyID. Do it in the vm_pre_destroy() kvm_x86_ops hook. The TDR control structures can be freed in the vm_destroy() hook, which runs last. Co-developed-by: Tony Lindgren Signed-off-by: Tony Lindgren Signed-off-by: Isaku Yamahata Co-developed-by: Sean Christopherson Signed-off-by: Sean Christopherson Co-developed-by: Kai Huang Signed-off-by: Kai Huang Co-developed-by: Yan Zhao Signed-off-by: Yan Zhao Co-developed-by: Rick Edgecombe Signed-off-by: Rick Edgecombe --- - Fix build issue in kvm-coco-queue - Init ret earlier to fix __tdx_td_init() error handling. (Chao) - Standardize -EAGAIN for __tdx_td_init() retry errors (Rick) Signed-off-by: Paolo Bonzini --- arch/x86/include/asm/kvm-x86-ops.h | 1 + arch/x86/include/asm/kvm_host.h | 1 + arch/x86/kvm/Kconfig | 2 + arch/x86/kvm/vmx/main.c | 28 +- arch/x86/kvm/vmx/tdx.c | 436 +++++++++++++++++++++++++++++ arch/x86/kvm/vmx/tdx.h | 4 +- arch/x86/kvm/vmx/x86_ops.h | 6 + arch/x86/kvm/x86.c | 1 + 8 files changed, 476 insertions(+), 3 deletions(-) diff --git a/arch/x86/include/asm/kvm-x86-ops.h b/arch/x86/include/asm/kvm-x86-ops.h index 1eca04087cf4..e6cb89ced1fd 100644 --- a/arch/x86/include/asm/kvm-x86-ops.h +++ b/arch/x86/include/asm/kvm-x86-ops.h @@ -21,6 +21,7 @@ KVM_X86_OP(has_emulated_msr) KVM_X86_OP(vcpu_after_set_cpuid) KVM_X86_OP(vm_init) KVM_X86_OP_OPTIONAL(vm_destroy) +KVM_X86_OP_OPTIONAL(vm_pre_destroy) KVM_X86_OP_OPTIONAL_RET0(vcpu_precreate) KVM_X86_OP(vcpu_create) KVM_X86_OP(vcpu_free) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index ee55d1f753e8..405d38924279 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -1665,6 +1665,7 @@ struct kvm_x86_ops { unsigned int vm_size; int (*vm_init)(struct kvm *kvm); void (*vm_destroy)(struct kvm *kvm); + void (*vm_pre_destroy)(struct kvm *kvm); /* Create, but do not attach this VCPU */ int (*vcpu_precreate)(struct kvm *kvm); diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig index fe8cbee6f614..0d445a317f61 100644 --- a/arch/x86/kvm/Kconfig +++ b/arch/x86/kvm/Kconfig @@ -94,6 +94,8 @@ config KVM_SW_PROTECTED_VM config KVM_INTEL tristate "KVM for Intel (and compatible) processors support" depends on KVM && IA32_FEAT_CTL + select KVM_GENERIC_PRIVATE_MEM if INTEL_TDX_HOST + select KVM_GENERIC_MEMORY_ATTRIBUTES if INTEL_TDX_HOST help Provides support for KVM on processors equipped with Intel's VT extensions, a.k.a. Virtual Machine Extensions (VMX). diff --git a/arch/x86/kvm/vmx/main.c b/arch/x86/kvm/vmx/main.c index 69c65085f81a..97737948774a 100644 --- a/arch/x86/kvm/vmx/main.c +++ b/arch/x86/kvm/vmx/main.c @@ -41,6 +41,28 @@ static __init int vt_hardware_setup(void) return 0; } +static int vt_vm_init(struct kvm *kvm) +{ + if (is_td(kvm)) + return tdx_vm_init(kvm); + + return vmx_vm_init(kvm); +} + +static void vt_vm_pre_destroy(struct kvm *kvm) +{ + if (is_td(kvm)) + return tdx_mmu_release_hkid(kvm); +} + +static void vt_vm_destroy(struct kvm *kvm) +{ + if (is_td(kvm)) + return tdx_vm_destroy(kvm); + + vmx_vm_destroy(kvm); +} + static int vt_mem_enc_ioctl(struct kvm *kvm, void __user *argp) { if (!is_td(kvm)) @@ -72,8 +94,10 @@ struct kvm_x86_ops vt_x86_ops __initdata = { .has_emulated_msr = vmx_has_emulated_msr, .vm_size = sizeof(struct kvm_vmx), - .vm_init = vmx_vm_init, - .vm_destroy = vmx_vm_destroy, + + .vm_init = vt_vm_init, + .vm_pre_destroy = vt_vm_pre_destroy, + .vm_destroy = vt_vm_destroy, .vcpu_precreate = vmx_vcpu_precreate, .vcpu_create = vmx_vcpu_create, diff --git a/arch/x86/kvm/vmx/tdx.c b/arch/x86/kvm/vmx/tdx.c index 3e7dc251e5e0..57eab6fc9f89 100644 --- a/arch/x86/kvm/vmx/tdx.c +++ b/arch/x86/kvm/vmx/tdx.c @@ -120,6 +120,266 @@ static int init_kvm_tdx_caps(const struct tdx_sys_info_td_conf *td_conf, return 0; } +/* + * Some SEAMCALLs acquire the TDX module globally, and can fail with + * TDX_OPERAND_BUSY. Use a global mutex to serialize these SEAMCALLs. + */ +static DEFINE_MUTEX(tdx_lock); + +static inline void tdx_hkid_free(struct kvm_tdx *kvm_tdx) +{ + tdx_guest_keyid_free(kvm_tdx->hkid); + kvm_tdx->hkid = -1; +} + +static inline bool is_hkid_assigned(struct kvm_tdx *kvm_tdx) +{ + return kvm_tdx->hkid > 0; +} + +static void tdx_clear_page(struct page *page) +{ + const void *zero_page = (const void *) page_to_virt(ZERO_PAGE(0)); + void *dest = page_to_virt(page); + unsigned long i; + + /* + * The page could have been poisoned. MOVDIR64B also clears + * the poison bit so the kernel can safely use the page again. + */ + for (i = 0; i < PAGE_SIZE; i += 64) + movdir64b(dest + i, zero_page); + /* + * MOVDIR64B store uses WC buffer. Prevent following memory reads + * from seeing potentially poisoned cache. + */ + __mb(); +} + +/* TDH.PHYMEM.PAGE.RECLAIM is allowed only when destroying the TD. */ +static int __tdx_reclaim_page(struct page *page) +{ + u64 err, rcx, rdx, r8; + + err = tdh_phymem_page_reclaim(page, &rcx, &rdx, &r8); + + /* + * No need to check for TDX_OPERAND_BUSY; all TD pages are freed + * before the HKID is released and control pages have also been + * released at this point, so there is no possibility of contention. + */ + if (WARN_ON_ONCE(err)) { + pr_tdx_error_3(TDH_PHYMEM_PAGE_RECLAIM, err, rcx, rdx, r8); + return -EIO; + } + return 0; +} + +static int tdx_reclaim_page(struct page *page) +{ + int r; + + r = __tdx_reclaim_page(page); + if (!r) + tdx_clear_page(page); + return r; +} + + +/* + * Reclaim the TD control page(s) which are crypto-protected by TDX guest's + * private KeyID. Assume the cache associated with the TDX private KeyID has + * been flushed. + */ +static void tdx_reclaim_control_page(struct page *ctrl_page) +{ + /* + * Leak the page if the kernel failed to reclaim the page. + * The kernel cannot use it safely anymore. + */ + if (tdx_reclaim_page(ctrl_page)) + return; + + __free_page(ctrl_page); +} + +#define TDX_SEAMCALL_RETRIES 10000 + +static void smp_func_do_phymem_cache_wb(void *unused) +{ + u64 err = 0; + bool resume; + int i; + + /* + * TDH.PHYMEM.CACHE.WB flushes caches associated with any TDX private + * KeyID on the package or core. The TDX module may not finish the + * cache flush but return TDX_INTERRUPTED_RESUMEABLE instead. The + * kernel should retry it until it returns success w/o rescheduling. + */ + for (i = TDX_SEAMCALL_RETRIES; i > 0; i--) { + resume = !!err; + err = tdh_phymem_cache_wb(resume); + switch (err) { + case TDX_INTERRUPTED_RESUMABLE: + continue; + case TDX_NO_HKID_READY_TO_WBCACHE: + err = TDX_SUCCESS; /* Already done by other thread */ + fallthrough; + default: + goto out; + } + } + +out: + if (WARN_ON_ONCE(err)) + pr_tdx_error(TDH_PHYMEM_CACHE_WB, err); +} + +void tdx_mmu_release_hkid(struct kvm *kvm) +{ + bool packages_allocated, targets_allocated; + struct kvm_tdx *kvm_tdx = to_kvm_tdx(kvm); + cpumask_var_t packages, targets; + u64 err; + int i; + + if (!is_hkid_assigned(kvm_tdx)) + return; + + /* KeyID has been allocated but guest is not yet configured */ + if (!kvm_tdx->td.tdr_page) { + tdx_hkid_free(kvm_tdx); + return; + } + + packages_allocated = zalloc_cpumask_var(&packages, GFP_KERNEL); + targets_allocated = zalloc_cpumask_var(&targets, GFP_KERNEL); + cpus_read_lock(); + + /* + * TDH.PHYMEM.CACHE.WB tries to acquire the TDX module global lock + * and can fail with TDX_OPERAND_BUSY when it fails to get the lock. + * Multiple TDX guests can be destroyed simultaneously. Take the + * mutex to prevent it from getting error. + */ + mutex_lock(&tdx_lock); + + /* + * Releasing HKID is in vm_destroy(). + * After the above flushing vps, there should be no more vCPU + * associations, as all vCPU fds have been released at this stage. + */ + for_each_online_cpu(i) { + if (packages_allocated && + cpumask_test_and_set_cpu(topology_physical_package_id(i), + packages)) + continue; + if (targets_allocated) + cpumask_set_cpu(i, targets); + } + if (targets_allocated) + on_each_cpu_mask(targets, smp_func_do_phymem_cache_wb, NULL, true); + else + on_each_cpu(smp_func_do_phymem_cache_wb, NULL, true); + /* + * In the case of error in smp_func_do_phymem_cache_wb(), the following + * tdh_mng_key_freeid() will fail. + */ + err = tdh_mng_key_freeid(&kvm_tdx->td); + if (KVM_BUG_ON(err, kvm)) { + pr_tdx_error(TDH_MNG_KEY_FREEID, err); + pr_err("tdh_mng_key_freeid() failed. HKID %d is leaked.\n", + kvm_tdx->hkid); + } else { + tdx_hkid_free(kvm_tdx); + } + + mutex_unlock(&tdx_lock); + cpus_read_unlock(); + free_cpumask_var(targets); + free_cpumask_var(packages); +} + +static void tdx_reclaim_td_control_pages(struct kvm *kvm) +{ + struct kvm_tdx *kvm_tdx = to_kvm_tdx(kvm); + u64 err; + int i; + + /* + * tdx_mmu_release_hkid() failed to reclaim HKID. Something went wrong + * heavily with TDX module. Give up freeing TD pages. As the function + * already warned, don't warn it again. + */ + if (is_hkid_assigned(kvm_tdx)) + return; + + if (kvm_tdx->td.tdcs_pages) { + for (i = 0; i < kvm_tdx->td.tdcs_nr_pages; i++) { + if (!kvm_tdx->td.tdcs_pages[i]) + continue; + + tdx_reclaim_control_page(kvm_tdx->td.tdcs_pages[i]); + } + kfree(kvm_tdx->td.tdcs_pages); + kvm_tdx->td.tdcs_pages = NULL; + } + + if (!kvm_tdx->td.tdr_page) + return; + + if (__tdx_reclaim_page(kvm_tdx->td.tdr_page)) + return; + + /* + * Use a SEAMCALL to ask the TDX module to flush the cache based on the + * KeyID. TDX module may access TDR while operating on TD (Especially + * when it is reclaiming TDCS). + */ + err = tdh_phymem_page_wbinvd_tdr(&kvm_tdx->td); + if (KVM_BUG_ON(err, kvm)) { + pr_tdx_error(TDH_PHYMEM_PAGE_WBINVD, err); + return; + } + tdx_clear_page(kvm_tdx->td.tdr_page); + + __free_page(kvm_tdx->td.tdr_page); + kvm_tdx->td.tdr_page = NULL; +} + +void tdx_vm_destroy(struct kvm *kvm) +{ + tdx_reclaim_td_control_pages(kvm); +} + +static int tdx_do_tdh_mng_key_config(void *param) +{ + struct kvm_tdx *kvm_tdx = param; + u64 err; + + /* TDX_RND_NO_ENTROPY related retries are handled by sc_retry() */ + err = tdh_mng_key_config(&kvm_tdx->td); + + if (KVM_BUG_ON(err, &kvm_tdx->kvm)) { + pr_tdx_error(TDH_MNG_KEY_CONFIG, err); + return -EIO; + } + + return 0; +} + +static int __tdx_td_init(struct kvm *kvm); + +int tdx_vm_init(struct kvm *kvm) +{ + kvm->arch.has_protected_state = true; + kvm->arch.has_private_mem = true; + + /* Place holder for TDX specific logic. */ + return __tdx_td_init(kvm); +} + static int tdx_get_capabilities(struct kvm_tdx_cmd *cmd) { const struct tdx_sys_info_td_conf *td_conf = &tdx_sysinfo->td_conf; @@ -168,6 +428,177 @@ out: return ret; } +static int __tdx_td_init(struct kvm *kvm) +{ + struct kvm_tdx *kvm_tdx = to_kvm_tdx(kvm); + cpumask_var_t packages; + struct page **tdcs_pages = NULL; + struct page *tdr_page; + int ret, i; + u64 err; + + ret = tdx_guest_keyid_alloc(); + if (ret < 0) + return ret; + kvm_tdx->hkid = ret; + + ret = -ENOMEM; + + tdr_page = alloc_page(GFP_KERNEL); + if (!tdr_page) + goto free_hkid; + + kvm_tdx->td.tdcs_nr_pages = tdx_sysinfo->td_ctrl.tdcs_base_size / PAGE_SIZE; + tdcs_pages = kcalloc(kvm_tdx->td.tdcs_nr_pages, sizeof(*kvm_tdx->td.tdcs_pages), + GFP_KERNEL | __GFP_ZERO); + if (!tdcs_pages) + goto free_tdr; + + for (i = 0; i < kvm_tdx->td.tdcs_nr_pages; i++) { + tdcs_pages[i] = alloc_page(GFP_KERNEL); + if (!tdcs_pages[i]) + goto free_tdcs; + } + + if (!zalloc_cpumask_var(&packages, GFP_KERNEL)) + goto free_tdcs; + + cpus_read_lock(); + + /* + * Need at least one CPU of the package to be online in order to + * program all packages for host key id. Check it. + */ + for_each_present_cpu(i) + cpumask_set_cpu(topology_physical_package_id(i), packages); + for_each_online_cpu(i) + cpumask_clear_cpu(topology_physical_package_id(i), packages); + if (!cpumask_empty(packages)) { + ret = -EIO; + /* + * Because it's hard for human operator to figure out the + * reason, warn it. + */ +#define MSG_ALLPKG "All packages need to have online CPU to create TD. Online CPU and retry.\n" + pr_warn_ratelimited(MSG_ALLPKG); + goto free_packages; + } + + /* + * TDH.MNG.CREATE tries to grab the global TDX module and fails + * with TDX_OPERAND_BUSY when it fails to grab. Take the global + * lock to prevent it from failure. + */ + mutex_lock(&tdx_lock); + kvm_tdx->td.tdr_page = tdr_page; + err = tdh_mng_create(&kvm_tdx->td, kvm_tdx->hkid); + mutex_unlock(&tdx_lock); + + if (err == TDX_RND_NO_ENTROPY) { + ret = -EAGAIN; + goto free_packages; + } + + if (WARN_ON_ONCE(err)) { + pr_tdx_error(TDH_MNG_CREATE, err); + ret = -EIO; + goto free_packages; + } + + for_each_online_cpu(i) { + int pkg = topology_physical_package_id(i); + + if (cpumask_test_and_set_cpu(pkg, packages)) + continue; + + /* + * Program the memory controller in the package with an + * encryption key associated to a TDX private host key id + * assigned to this TDR. Concurrent operations on same memory + * controller results in TDX_OPERAND_BUSY. No locking needed + * beyond the cpus_read_lock() above as it serializes against + * hotplug and the first online CPU of the package is always + * used. We never have two CPUs in the same socket trying to + * program the key. + */ + ret = smp_call_on_cpu(i, tdx_do_tdh_mng_key_config, + kvm_tdx, true); + if (ret) + break; + } + cpus_read_unlock(); + free_cpumask_var(packages); + if (ret) { + i = 0; + goto teardown; + } + + kvm_tdx->td.tdcs_pages = tdcs_pages; + for (i = 0; i < kvm_tdx->td.tdcs_nr_pages; i++) { + err = tdh_mng_addcx(&kvm_tdx->td, tdcs_pages[i]); + if (err == TDX_RND_NO_ENTROPY) { + /* Here it's hard to allow userspace to retry. */ + ret = -EAGAIN; + goto teardown; + } + if (WARN_ON_ONCE(err)) { + pr_tdx_error(TDH_MNG_ADDCX, err); + ret = -EIO; + goto teardown; + } + } + + /* + * Note, TDH_MNG_INIT cannot be invoked here. TDH_MNG_INIT requires a dedicated + * ioctl() to define the configure CPUID values for the TD. + */ + return 0; + + /* + * The sequence for freeing resources from a partially initialized TD + * varies based on where in the initialization flow failure occurred. + * Simply use the full teardown and destroy, which naturally play nice + * with partial initialization. + */ +teardown: + /* Only free pages not yet added, so start at 'i' */ + for (; i < kvm_tdx->td.tdcs_nr_pages; i++) { + if (tdcs_pages[i]) { + __free_page(tdcs_pages[i]); + tdcs_pages[i] = NULL; + } + } + if (!kvm_tdx->td.tdcs_pages) + kfree(tdcs_pages); + + tdx_mmu_release_hkid(kvm); + tdx_reclaim_td_control_pages(kvm); + + return ret; + +free_packages: + cpus_read_unlock(); + free_cpumask_var(packages); + +free_tdcs: + for (i = 0; i < kvm_tdx->td.tdcs_nr_pages; i++) { + if (tdcs_pages[i]) + __free_page(tdcs_pages[i]); + } + kfree(tdcs_pages); + kvm_tdx->td.tdcs_pages = NULL; + +free_tdr: + if (tdr_page) + __free_page(tdr_page); + kvm_tdx->td.tdr_page = 0; + +free_hkid: + tdx_hkid_free(kvm_tdx); + + return ret; +} + int tdx_vm_ioctl(struct kvm *kvm, void __user *argp) { struct kvm_tdx_cmd tdx_cmd; @@ -324,6 +755,11 @@ int __init tdx_bringup(void) if (!enable_tdx) return 0; + if (!cpu_feature_enabled(X86_FEATURE_MOVDIR64B)) { + pr_err("tdx: MOVDIR64B is required for TDX\n"); + goto success_disable_tdx; + } + if (!cpu_feature_enabled(X86_FEATURE_TDX_HOST_PLATFORM)) { pr_err("tdx: no TDX private KeyIDs available\n"); goto success_disable_tdx; diff --git a/arch/x86/kvm/vmx/tdx.h b/arch/x86/kvm/vmx/tdx.h index f1e861cbee3b..afa4e2242311 100644 --- a/arch/x86/kvm/vmx/tdx.h +++ b/arch/x86/kvm/vmx/tdx.h @@ -13,7 +13,9 @@ extern bool enable_tdx; struct kvm_tdx { struct kvm kvm; - /* TDX specific members follow. */ + int hkid; + + struct tdx_td td; }; struct vcpu_tdx { diff --git a/arch/x86/kvm/vmx/x86_ops.h b/arch/x86/kvm/vmx/x86_ops.h index 75e0ca29a39e..85c78639d476 100644 --- a/arch/x86/kvm/vmx/x86_ops.h +++ b/arch/x86/kvm/vmx/x86_ops.h @@ -122,8 +122,14 @@ void vmx_cancel_hv_timer(struct kvm_vcpu *vcpu); void vmx_setup_mce(struct kvm_vcpu *vcpu); #ifdef CONFIG_KVM_INTEL_TDX +int tdx_vm_init(struct kvm *kvm); +void tdx_mmu_release_hkid(struct kvm *kvm); +void tdx_vm_destroy(struct kvm *kvm); int tdx_vm_ioctl(struct kvm *kvm, void __user *argp); #else +static inline int tdx_vm_init(struct kvm *kvm) { return -EOPNOTSUPP; } +static inline void tdx_mmu_release_hkid(struct kvm *kvm) {} +static inline void tdx_vm_destroy(struct kvm *kvm) {} static inline int tdx_vm_ioctl(struct kvm *kvm, void __user *argp) { return -EOPNOTSUPP; } #endif diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 2434da7ac973..2a2d2b6c283e 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -12870,6 +12870,7 @@ EXPORT_SYMBOL_GPL(__x86_set_memory_region); void kvm_arch_pre_destroy_vm(struct kvm *kvm) { kvm_mmu_pre_destroy_vm(kvm); + static_call_cond(kvm_x86_vm_pre_destroy)(kvm); } void kvm_arch_destroy_vm(struct kvm *kvm) -- 2.51.0 From f94f4a97e66543bd51d86b4216cc5945041d11c3 Mon Sep 17 00:00:00 2001 From: Isaku Yamahata Date: Wed, 30 Oct 2024 12:00:31 -0700 Subject: [PATCH 06/16] KVM: TDX: Support per-VM KVM_CAP_MAX_VCPUS extension check Change to report the KVM_CAP_MAX_VCPUS extension from globally to per-VM to allow userspace to be able to query maximum vCPUs for TDX guest via checking the KVM_CAP_MAX_VCPU extension on per-VM basis. Today KVM x86 reports KVM_MAX_VCPUS as guest's maximum vCPUs for all guests globally, and userspace, i.e. Qemu, queries the KVM_MAX_VCPUS extension globally but not on per-VM basis. TDX has its own limit of maximum vCPUs it can support for all TDX guests in addition to KVM_MAX_VCPUS. TDX module reports this limit via the MAX_VCPU_PER_TD global metadata. Different modules may report different values. In practice, the reported value reflects the maximum logical CPUs that ALL the platforms that the module supports can possibly have. Note some old modules may also not support this metadata, in which case the limit is U16_MAX. The current way to always report KVM_MAX_VCPUS in the KVM_CAP_MAX_VCPUS extension is not enough for TDX. To accommodate TDX, change to report the KVM_CAP_MAX_VCPUS extension on per-VM basis. Specifically, override kvm->max_vcpus in tdx_vm_init() for TDX guest, and report kvm->max_vcpus in the KVM_CAP_MAX_VCPUS extension check. Change to report "the number of logical CPUs the platform has" as the maximum vCPUs for TDX guest. Simply forwarding the MAX_VCPU_PER_TD reported by the TDX module would result in an unpredictable ABI because the reported value to userspace would be depending on whims of TDX modules. This works in practice because of the MAX_VCPU_PER_TD reported by the TDX module will never be smaller than the one reported to userspace. But to make sure KVM never reports an unsupported value, sanity check the MAX_VCPU_PER_TD reported by TDX module is not smaller than the number of logical CPUs the platform has, otherwise refuse to use TDX. Note, when creating a TDX guest, TDX actually requires the "maximum vCPUs for _this_ TDX guest" as an input to initialize the TDX guest. But TDX guest's maximum vCPUs is not part of TDREPORT thus not part of attestation, thus there's no need to allow userspace to explicitly _configure_ the maximum vCPUs on per-VM basis. KVM will simply use kvm->max_vcpus as input when initializing the TDX guest. Signed-off-by: Isaku Yamahata Signed-off-by: Rick Edgecombe Signed-off-by: Paolo Bonzini --- arch/x86/kvm/vmx/main.c | 1 + arch/x86/kvm/vmx/tdx.c | 51 +++++++++++++++++++++++++++++++++++++++++ arch/x86/kvm/x86.c | 2 ++ 3 files changed, 54 insertions(+) diff --git a/arch/x86/kvm/vmx/main.c b/arch/x86/kvm/vmx/main.c index 97737948774a..e0806dbe7b87 100644 --- a/arch/x86/kvm/vmx/main.c +++ b/arch/x86/kvm/vmx/main.c @@ -7,6 +7,7 @@ #include "pmu.h" #include "posted_intr.h" #include "tdx.h" +#include "tdx_arch.h" static __init int vt_hardware_setup(void) { diff --git a/arch/x86/kvm/vmx/tdx.c b/arch/x86/kvm/vmx/tdx.c index 57eab6fc9f89..cebe570f2002 100644 --- a/arch/x86/kvm/vmx/tdx.c +++ b/arch/x86/kvm/vmx/tdx.c @@ -376,6 +376,19 @@ int tdx_vm_init(struct kvm *kvm) kvm->arch.has_protected_state = true; kvm->arch.has_private_mem = true; + /* + * TDX has its own limit of maximum vCPUs it can support for all + * TDX guests in addition to KVM_MAX_VCPUS. TDX module reports + * such limit via the MAX_VCPU_PER_TD global metadata. In + * practice, it reflects the number of logical CPUs that ALL + * platforms that the TDX module supports can possibly have. + * + * Limit TDX guest's maximum vCPUs to the number of logical CPUs + * the platform has. Simply forwarding the MAX_VCPU_PER_TD to + * userspace would result in an unpredictable ABI. + */ + kvm->max_vcpus = min_t(int, kvm->max_vcpus, num_present_cpus()); + /* Place holder for TDX specific logic. */ return __tdx_td_init(kvm); } @@ -695,6 +708,7 @@ static int __init __do_tdx_bringup(void) static int __init __tdx_bringup(void) { + const struct tdx_sys_info_td_conf *td_conf; int r; /* @@ -727,6 +741,43 @@ static int __init __tdx_bringup(void) if (!(tdx_sysinfo->features.tdx_features0 & MD_FIELD_ID_FEATURES0_TOPOLOGY_ENUM)) goto get_sysinfo_err; + /* + * TDX has its own limit of maximum vCPUs it can support for all + * TDX guests in addition to KVM_MAX_VCPUS. Userspace needs to + * query TDX guest's maximum vCPUs by checking KVM_CAP_MAX_VCPU + * extension on per-VM basis. + * + * TDX module reports such limit via the MAX_VCPU_PER_TD global + * metadata. Different modules may report different values. + * Some old module may also not support this metadata (in which + * case this limit is U16_MAX). + * + * In practice, the reported value reflects the maximum logical + * CPUs that ALL the platforms that the module supports can + * possibly have. + * + * Simply forwarding the MAX_VCPU_PER_TD to userspace could + * result in an unpredictable ABI. KVM instead always advertise + * the number of logical CPUs the platform has as the maximum + * vCPUs for TDX guests. + * + * Make sure MAX_VCPU_PER_TD reported by TDX module is not + * smaller than the number of logical CPUs, otherwise KVM will + * report an unsupported value to userspace. + * + * Note, a platform with TDX enabled in the BIOS cannot support + * physical CPU hotplug, and TDX requires the BIOS has marked + * all logical CPUs in MADT table as enabled. Just use + * num_present_cpus() for the number of logical CPUs. + */ + td_conf = &tdx_sysinfo->td_conf; + if (td_conf->max_vcpus_per_td < num_present_cpus()) { + pr_err("Disable TDX: MAX_VCPU_PER_TD (%u) smaller than number of logical CPUs (%u).\n", + td_conf->max_vcpus_per_td, num_present_cpus()); + r = -EINVAL; + goto get_sysinfo_err; + } + /* * Leave hardware virtualization enabled after TDX is enabled * successfully. TDX CPU hotplug depends on this. diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 2a2d2b6c283e..a4d1f3319a5b 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -4720,6 +4720,8 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) break; case KVM_CAP_MAX_VCPUS: r = KVM_MAX_VCPUS; + if (kvm) + r = kvm->max_vcpus; break; case KVM_CAP_MAX_VCPU_ID: r = KVM_MAX_VCPU_IDS; -- 2.51.0 From a656dac80078def3dd7784e2bd5e6edc1c36e11c Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Wed, 22 Jan 2025 06:31:31 -0500 Subject: [PATCH 07/16] KVM: x86: expose cpuid_entry2_find for TDX CPUID values are provided for TDX virtual machines as part of the KVM_TDX_INIT_VM ioctl. Unlike KVM_SET_CPUID2, TDX will need to examine the leaves, either to validate against the CPUIDs listed in the TDX modules configuration or to fill other controls with matching values. Since there is an existing function to look up a leaf/index pair into a given list of CPUID entries, export it as kvm_find_cpuid_entry2(). Reviewed-by: Kai Huang Signed-off-by: Paolo Bonzini --- arch/x86/kvm/cpuid.c | 38 +++++--------------------------------- arch/x86/kvm/cpuid.h | 32 ++++++++++++++++++++++++++++---- 2 files changed, 33 insertions(+), 37 deletions(-) diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 121edf1f2a79..45392cf42dbc 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -82,17 +82,8 @@ u32 xstate_required_size(u64 xstate_bv, bool compacted) return ret; } -/* - * Magic value used by KVM when querying userspace-provided CPUID entries and - * doesn't care about the CPIUD index because the index of the function in - * question is not significant. Note, this magic value must have at least one - * bit set in bits[63:32] and must be consumed as a u64 by cpuid_entry2_find() - * to avoid false positives when processing guest CPUID input. - */ -#define KVM_CPUID_INDEX_NOT_SIGNIFICANT -1ull - -static struct kvm_cpuid_entry2 *cpuid_entry2_find(struct kvm_vcpu *vcpu, - u32 function, u64 index) +struct kvm_cpuid_entry2 *kvm_find_cpuid_entry2( + struct kvm_cpuid_entry2 *entries, int nent, u32 function, u64 index) { struct kvm_cpuid_entry2 *e; int i; @@ -109,8 +100,8 @@ static struct kvm_cpuid_entry2 *cpuid_entry2_find(struct kvm_vcpu *vcpu, */ lockdep_assert_irqs_enabled(); - for (i = 0; i < vcpu->arch.cpuid_nent; i++) { - e = &vcpu->arch.cpuid_entries[i]; + for (i = 0; i < nent; i++) { + e = &entries[i]; if (e->function != function) continue; @@ -141,26 +132,7 @@ static struct kvm_cpuid_entry2 *cpuid_entry2_find(struct kvm_vcpu *vcpu, return NULL; } - -struct kvm_cpuid_entry2 *kvm_find_cpuid_entry_index(struct kvm_vcpu *vcpu, - u32 function, u32 index) -{ - return cpuid_entry2_find(vcpu, function, index); -} -EXPORT_SYMBOL_GPL(kvm_find_cpuid_entry_index); - -struct kvm_cpuid_entry2 *kvm_find_cpuid_entry(struct kvm_vcpu *vcpu, - u32 function) -{ - return cpuid_entry2_find(vcpu, function, KVM_CPUID_INDEX_NOT_SIGNIFICANT); -} -EXPORT_SYMBOL_GPL(kvm_find_cpuid_entry); - -/* - * cpuid_entry2_find() and KVM_CPUID_INDEX_NOT_SIGNIFICANT should never be used - * directly outside of kvm_find_cpuid_entry() and kvm_find_cpuid_entry_index(). - */ -#undef KVM_CPUID_INDEX_NOT_SIGNIFICANT +EXPORT_SYMBOL_GPL(kvm_find_cpuid_entry2); static int kvm_check_cpuid(struct kvm_vcpu *vcpu) { diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h index 67d80aa72d50..69ae6768e830 100644 --- a/arch/x86/kvm/cpuid.h +++ b/arch/x86/kvm/cpuid.h @@ -12,10 +12,34 @@ void kvm_set_cpu_caps(void); void kvm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu); void kvm_update_cpuid_runtime(struct kvm_vcpu *vcpu); -struct kvm_cpuid_entry2 *kvm_find_cpuid_entry_index(struct kvm_vcpu *vcpu, - u32 function, u32 index); -struct kvm_cpuid_entry2 *kvm_find_cpuid_entry(struct kvm_vcpu *vcpu, - u32 function); +struct kvm_cpuid_entry2 *kvm_find_cpuid_entry2(struct kvm_cpuid_entry2 *entries, + int nent, u32 function, u64 index); +/* + * Magic value used by KVM when querying userspace-provided CPUID entries and + * doesn't care about the CPIUD index because the index of the function in + * question is not significant. Note, this magic value must have at least one + * bit set in bits[63:32] and must be consumed as a u64 by kvm_find_cpuid_entry2() + * to avoid false positives when processing guest CPUID input. + * + * KVM_CPUID_INDEX_NOT_SIGNIFICANT should never be used directly outside of + * kvm_find_cpuid_entry2() and kvm_find_cpuid_entry(). + */ +#define KVM_CPUID_INDEX_NOT_SIGNIFICANT -1ull + +static inline struct kvm_cpuid_entry2 *kvm_find_cpuid_entry_index(struct kvm_vcpu *vcpu, + u32 function, u32 index) +{ + return kvm_find_cpuid_entry2(vcpu->arch.cpuid_entries, vcpu->arch.cpuid_nent, + function, index); +} + +static inline struct kvm_cpuid_entry2 *kvm_find_cpuid_entry(struct kvm_vcpu *vcpu, + u32 function) +{ + return kvm_find_cpuid_entry2(vcpu->arch.cpuid_entries, vcpu->arch.cpuid_nent, + function, KVM_CPUID_INDEX_NOT_SIGNIFICANT); +} + int kvm_dev_ioctl_get_cpuid(struct kvm_cpuid2 *cpuid, struct kvm_cpuid_entry2 __user *entries, unsigned int type); -- 2.51.0 From 0186dd29a251866d9b69064006a5da36f7ae070e Mon Sep 17 00:00:00 2001 From: Isaku Yamahata Date: Tue, 14 Jan 2025 12:34:46 -0500 Subject: [PATCH 08/16] KVM: TDX: add ioctl to initialize VM with TDX specific parameters After the crypto-protection key has been configured, TDX requires a VM-scope initialization as a step of creating the TDX guest. This "per-VM" TDX initialization does the global configurations/features that the TDX guest can support, such as guest's CPUIDs (emulated by the TDX module), the maximum number of vcpus etc. Because there is no room in KVM_CREATE_VM to pass all the required parameters, introduce a new ioctl KVM_TDX_INIT_VM and mark the VM as TD_STATE_UNINITIALIZED until it is invoked. This "per-VM" TDX initialization must be done before any "vcpu-scope" TDX initialization; KVM_TDX_INIT_VM IOCTL must be invoked before the creation of vCPUs. Co-developed-by: Xiaoyao Li Signed-off-by: Xiaoyao Li Signed-off-by: Isaku Yamahata Signed-off-by: Rick Edgecombe Signed-off-by: Paolo Bonzini --- arch/x86/include/uapi/asm/kvm.h | 24 +++ arch/x86/kvm/vmx/tdx.c | 259 ++++++++++++++++++++++++++++++-- arch/x86/kvm/vmx/tdx.h | 26 ++++ 3 files changed, 299 insertions(+), 10 deletions(-) diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h index 8a4633cdb247..b64351076f2a 100644 --- a/arch/x86/include/uapi/asm/kvm.h +++ b/arch/x86/include/uapi/asm/kvm.h @@ -930,6 +930,7 @@ struct kvm_hyperv_eventfd { /* Trust Domain eXtension sub-ioctl() commands. */ enum kvm_tdx_cmd_id { KVM_TDX_CAPABILITIES = 0, + KVM_TDX_INIT_VM, KVM_TDX_CMD_NR_MAX, }; @@ -961,4 +962,27 @@ struct kvm_tdx_capabilities { struct kvm_cpuid2 cpuid; }; +struct kvm_tdx_init_vm { + __u64 attributes; + __u64 xfam; + __u64 mrconfigid[6]; /* sha384 digest */ + __u64 mrowner[6]; /* sha384 digest */ + __u64 mrownerconfig[6]; /* sha384 digest */ + + /* The total space for TD_PARAMS before the CPUIDs is 256 bytes */ + __u64 reserved[12]; + + /* + * Call KVM_TDX_INIT_VM before vcpu creation, thus before + * KVM_SET_CPUID2. + * This configuration supersedes KVM_SET_CPUID2s for VCPUs because the + * TDX module directly virtualizes those CPUIDs without VMM. The user + * space VMM, e.g. qemu, should make KVM_SET_CPUID2 consistent with + * those values. If it doesn't, KVM may have wrong idea of vCPUIDs of + * the guest, and KVM may wrongly emulate CPUIDs or MSRs that the TDX + * module doesn't virtualize. + */ + struct kvm_cpuid2 cpuid; +}; + #endif /* _ASM_X86_KVM_H */ diff --git a/arch/x86/kvm/vmx/tdx.c b/arch/x86/kvm/vmx/tdx.c index cebe570f2002..b58a542fdf51 100644 --- a/arch/x86/kvm/vmx/tdx.c +++ b/arch/x86/kvm/vmx/tdx.c @@ -69,6 +69,11 @@ static u64 tdx_get_supported_xfam(const struct tdx_sys_info_td_conf *td_conf) return val; } +static int tdx_get_guest_phys_addr_bits(const u32 eax) +{ + return (eax & GENMASK(23, 16)) >> 16; +} + static u32 tdx_set_guest_phys_addr_bits(const u32 eax, int addr_bits) { return (eax & ~GENMASK(23, 16)) | (addr_bits & 0xff) << 16; @@ -350,7 +355,11 @@ static void tdx_reclaim_td_control_pages(struct kvm *kvm) void tdx_vm_destroy(struct kvm *kvm) { + struct kvm_tdx *kvm_tdx = to_kvm_tdx(kvm); + tdx_reclaim_td_control_pages(kvm); + + kvm_tdx->state = TD_STATE_UNINITIALIZED; } static int tdx_do_tdh_mng_key_config(void *param) @@ -369,10 +378,10 @@ static int tdx_do_tdh_mng_key_config(void *param) return 0; } -static int __tdx_td_init(struct kvm *kvm); - int tdx_vm_init(struct kvm *kvm) { + struct kvm_tdx *kvm_tdx = to_kvm_tdx(kvm); + kvm->arch.has_protected_state = true; kvm->arch.has_private_mem = true; @@ -389,8 +398,9 @@ int tdx_vm_init(struct kvm *kvm) */ kvm->max_vcpus = min_t(int, kvm->max_vcpus, num_present_cpus()); - /* Place holder for TDX specific logic. */ - return __tdx_td_init(kvm); + kvm_tdx->state = TD_STATE_UNINITIALIZED; + + return 0; } static int tdx_get_capabilities(struct kvm_tdx_cmd *cmd) @@ -441,15 +451,151 @@ out: return ret; } -static int __tdx_td_init(struct kvm *kvm) +/* + * KVM reports guest physical address in CPUID.0x800000008.EAX[23:16], which is + * similar to TDX's GPAW. Use this field as the interface for userspace to + * configure the GPAW and EPT level for TDs. + * + * Only values 48 and 52 are supported. Value 52 means GPAW-52 and EPT level + * 5, Value 48 means GPAW-48 and EPT level 4. For value 48, GPAW-48 is always + * supported. Value 52 is only supported when the platform supports 5 level + * EPT. + */ +static int setup_tdparams_eptp_controls(struct kvm_cpuid2 *cpuid, + struct td_params *td_params) +{ + const struct kvm_cpuid_entry2 *entry; + int guest_pa; + + entry = kvm_find_cpuid_entry2(cpuid->entries, cpuid->nent, 0x80000008, 0); + if (!entry) + return -EINVAL; + + guest_pa = tdx_get_guest_phys_addr_bits(entry->eax); + + if (guest_pa != 48 && guest_pa != 52) + return -EINVAL; + + if (guest_pa == 52 && !cpu_has_vmx_ept_5levels()) + return -EINVAL; + + td_params->eptp_controls = VMX_EPTP_MT_WB; + if (guest_pa == 52) { + td_params->eptp_controls |= VMX_EPTP_PWL_5; + td_params->config_flags |= TDX_CONFIG_FLAGS_MAX_GPAW; + } else { + td_params->eptp_controls |= VMX_EPTP_PWL_4; + } + + return 0; +} + +static int setup_tdparams_cpuids(struct kvm_cpuid2 *cpuid, + struct td_params *td_params) +{ + const struct tdx_sys_info_td_conf *td_conf = &tdx_sysinfo->td_conf; + const struct kvm_cpuid_entry2 *entry; + struct tdx_cpuid_value *value; + int i, copy_cnt = 0; + + /* + * td_params.cpuid_values: The number and the order of cpuid_value must + * be same to the one of struct tdsysinfo.{num_cpuid_config, cpuid_configs} + * It's assumed that td_params was zeroed. + */ + for (i = 0; i < td_conf->num_cpuid_config; i++) { + struct kvm_cpuid_entry2 tmp; + + td_init_cpuid_entry2(&tmp, i); + + entry = kvm_find_cpuid_entry2(cpuid->entries, cpuid->nent, + tmp.function, tmp.index); + if (!entry) + continue; + + copy_cnt++; + + value = &td_params->cpuid_values[i]; + value->eax = entry->eax; + value->ebx = entry->ebx; + value->ecx = entry->ecx; + value->edx = entry->edx; + + /* + * TDX module does not accept nonzero bits 16..23 for the + * CPUID[0x80000008].EAX, see setup_tdparams_eptp_controls(). + */ + if (tmp.function == 0x80000008) + value->eax = tdx_set_guest_phys_addr_bits(value->eax, 0); + } + + /* + * Rely on the TDX module to reject invalid configuration, but it can't + * check of leafs that don't have a proper slot in td_params->cpuid_values + * to stick then. So fail if there were entries that didn't get copied to + * td_params. + */ + if (copy_cnt != cpuid->nent) + return -EINVAL; + + return 0; +} + +static int setup_tdparams(struct kvm *kvm, struct td_params *td_params, + struct kvm_tdx_init_vm *init_vm) +{ + const struct tdx_sys_info_td_conf *td_conf = &tdx_sysinfo->td_conf; + struct kvm_cpuid2 *cpuid = &init_vm->cpuid; + int ret; + + if (kvm->created_vcpus) + return -EBUSY; + + if (init_vm->attributes & ~tdx_get_supported_attrs(td_conf)) + return -EINVAL; + + if (init_vm->xfam & ~tdx_get_supported_xfam(td_conf)) + return -EINVAL; + + td_params->max_vcpus = kvm->max_vcpus; + td_params->attributes = init_vm->attributes | td_conf->attributes_fixed1; + td_params->xfam = init_vm->xfam | td_conf->xfam_fixed1; + + td_params->config_flags = TDX_CONFIG_FLAGS_NO_RBP_MOD; + td_params->tsc_frequency = TDX_TSC_KHZ_TO_25MHZ(kvm->arch.default_tsc_khz); + + ret = setup_tdparams_eptp_controls(cpuid, td_params); + if (ret) + return ret; + + ret = setup_tdparams_cpuids(cpuid, td_params); + if (ret) + return ret; + +#define MEMCPY_SAME_SIZE(dst, src) \ + do { \ + BUILD_BUG_ON(sizeof(dst) != sizeof(src)); \ + memcpy((dst), (src), sizeof(dst)); \ + } while (0) + + MEMCPY_SAME_SIZE(td_params->mrconfigid, init_vm->mrconfigid); + MEMCPY_SAME_SIZE(td_params->mrowner, init_vm->mrowner); + MEMCPY_SAME_SIZE(td_params->mrownerconfig, init_vm->mrownerconfig); + + return 0; +} + +static int __tdx_td_init(struct kvm *kvm, struct td_params *td_params, + u64 *seamcall_err) { struct kvm_tdx *kvm_tdx = to_kvm_tdx(kvm); cpumask_var_t packages; struct page **tdcs_pages = NULL; struct page *tdr_page; int ret, i; - u64 err; + u64 err, rcx; + *seamcall_err = 0; ret = tdx_guest_keyid_alloc(); if (ret < 0) return ret; @@ -561,10 +707,23 @@ static int __tdx_td_init(struct kvm *kvm) } } - /* - * Note, TDH_MNG_INIT cannot be invoked here. TDH_MNG_INIT requires a dedicated - * ioctl() to define the configure CPUID values for the TD. - */ + err = tdh_mng_init(&kvm_tdx->td, __pa(td_params), &rcx); + if ((err & TDX_SEAMCALL_STATUS_MASK) == TDX_OPERAND_INVALID) { + /* + * Because a user gives operands, don't warn. + * Return a hint to the user because it's sometimes hard for the + * user to figure out which operand is invalid. SEAMCALL status + * code includes which operand caused invalid operand error. + */ + *seamcall_err = err; + ret = -EINVAL; + goto teardown; + } else if (WARN_ON_ONCE(err)) { + pr_tdx_error_1(TDH_MNG_INIT, err, rcx); + ret = -EIO; + goto teardown; + } + return 0; /* @@ -612,6 +771,83 @@ free_hkid: return ret; } +static int tdx_td_init(struct kvm *kvm, struct kvm_tdx_cmd *cmd) +{ + struct kvm_tdx *kvm_tdx = to_kvm_tdx(kvm); + struct kvm_tdx_init_vm *init_vm; + struct td_params *td_params = NULL; + int ret; + + BUILD_BUG_ON(sizeof(*init_vm) != 256 + sizeof_field(struct kvm_tdx_init_vm, cpuid)); + BUILD_BUG_ON(sizeof(struct td_params) != 1024); + + if (kvm_tdx->state != TD_STATE_UNINITIALIZED) + return -EINVAL; + + if (cmd->flags) + return -EINVAL; + + init_vm = kmalloc(sizeof(*init_vm) + + sizeof(init_vm->cpuid.entries[0]) * KVM_MAX_CPUID_ENTRIES, + GFP_KERNEL); + if (!init_vm) + return -ENOMEM; + + if (copy_from_user(init_vm, u64_to_user_ptr(cmd->data), sizeof(*init_vm))) { + ret = -EFAULT; + goto out; + } + + if (init_vm->cpuid.nent > KVM_MAX_CPUID_ENTRIES) { + ret = -E2BIG; + goto out; + } + + if (copy_from_user(init_vm->cpuid.entries, + u64_to_user_ptr(cmd->data) + sizeof(*init_vm), + flex_array_size(init_vm, cpuid.entries, init_vm->cpuid.nent))) { + ret = -EFAULT; + goto out; + } + + if (memchr_inv(init_vm->reserved, 0, sizeof(init_vm->reserved))) { + ret = -EINVAL; + goto out; + } + + if (init_vm->cpuid.padding) { + ret = -EINVAL; + goto out; + } + + td_params = kzalloc(sizeof(struct td_params), GFP_KERNEL); + if (!td_params) { + ret = -ENOMEM; + goto out; + } + + ret = setup_tdparams(kvm, td_params, init_vm); + if (ret) + goto out; + + ret = __tdx_td_init(kvm, td_params, &cmd->hw_error); + if (ret) + goto out; + + kvm_tdx->tsc_offset = td_tdcs_exec_read64(kvm_tdx, TD_TDCS_EXEC_TSC_OFFSET); + kvm_tdx->tsc_multiplier = td_tdcs_exec_read64(kvm_tdx, TD_TDCS_EXEC_TSC_MULTIPLIER); + kvm_tdx->attributes = td_params->attributes; + kvm_tdx->xfam = td_params->xfam; + + kvm_tdx->state = TD_STATE_INITIALIZED; +out: + /* kfree() accepts NULL. */ + kfree(init_vm); + kfree(td_params); + + return ret; +} + int tdx_vm_ioctl(struct kvm *kvm, void __user *argp) { struct kvm_tdx_cmd tdx_cmd; @@ -633,6 +869,9 @@ int tdx_vm_ioctl(struct kvm *kvm, void __user *argp) case KVM_TDX_CAPABILITIES: r = tdx_get_capabilities(&tdx_cmd); break; + case KVM_TDX_INIT_VM: + r = tdx_td_init(kvm, &tdx_cmd); + break; default: r = -EINVAL; goto out; diff --git a/arch/x86/kvm/vmx/tdx.h b/arch/x86/kvm/vmx/tdx.h index afa4e2242311..6e23f78c2713 100644 --- a/arch/x86/kvm/vmx/tdx.h +++ b/arch/x86/kvm/vmx/tdx.h @@ -11,9 +11,24 @@ void tdx_cleanup(void); extern bool enable_tdx; +/* TDX module hardware states. These follow the TDX module OP_STATEs. */ +enum kvm_tdx_state { + TD_STATE_UNINITIALIZED = 0, + TD_STATE_INITIALIZED, + TD_STATE_RUNNABLE, +}; + struct kvm_tdx { struct kvm kvm; + int hkid; + enum kvm_tdx_state state; + + u64 attributes; + u64 xfam; + + u64 tsc_offset; + u64 tsc_multiplier; struct tdx_td td; }; @@ -33,6 +48,17 @@ static inline bool is_td_vcpu(struct kvm_vcpu *vcpu) return is_td(vcpu->kvm); } +static __always_inline u64 td_tdcs_exec_read64(struct kvm_tdx *kvm_tdx, u32 field) +{ + u64 err, data; + + err = tdh_mng_rd(&kvm_tdx->td, TDCS_EXEC(field), &data); + if (unlikely(err)) { + pr_err("TDH_MNG_RD[EXEC.0x%x] failed: 0x%llx\n", field, err); + return 0; + } + return data; +} #else static inline int tdx_bringup(void) { return 0; } static inline void tdx_cleanup(void) {} -- 2.51.0 From ffb6fc84134ba60bac41b77b65747407fe6e69d9 Mon Sep 17 00:00:00 2001 From: Isaku Yamahata Date: Wed, 30 Oct 2024 12:00:33 -0700 Subject: [PATCH 09/16] KVM: TDX: Make pmu_intel.c ignore guest TD case TDX KVM doesn't support PMU yet, it's future work of TDX KVM support as another patch series. For now, handle TDX by updating vcpu_to_lbr_desc() and vcpu_to_lbr_records() to return NULL. Signed-off-by: Isaku Yamahata Co-developed-by: Tony Lindgren Signed-off-by: Tony Lindgren Signed-off-by: Rick Edgecombe --- - Add pragma poison for to_vmx() (Paolo) Signed-off-by: Paolo Bonzini --- arch/x86/kvm/vmx/pmu_intel.c | 52 +++++++++++++++++++++++++++++++++++- arch/x86/kvm/vmx/pmu_intel.h | 28 +++++++++++++++++++ arch/x86/kvm/vmx/vmx.h | 34 +---------------------- 3 files changed, 80 insertions(+), 34 deletions(-) create mode 100644 arch/x86/kvm/vmx/pmu_intel.h diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c index 77012b2eca0e..8a94b52c5731 100644 --- a/arch/x86/kvm/vmx/pmu_intel.c +++ b/arch/x86/kvm/vmx/pmu_intel.c @@ -19,6 +19,7 @@ #include "lapic.h" #include "nested.h" #include "pmu.h" +#include "tdx.h" /* * Perf's "BASE" is wildly misleading, architectural PMUs use bits 31:16 of ECX @@ -34,6 +35,24 @@ #define MSR_PMC_FULL_WIDTH_BIT (MSR_IA32_PMC0 - MSR_IA32_PERFCTR0) +static struct lbr_desc *vcpu_to_lbr_desc(struct kvm_vcpu *vcpu) +{ + if (is_td_vcpu(vcpu)) + return NULL; + + return &to_vmx(vcpu)->lbr_desc; +} + +static struct x86_pmu_lbr *vcpu_to_lbr_records(struct kvm_vcpu *vcpu) +{ + if (is_td_vcpu(vcpu)) + return NULL; + + return &to_vmx(vcpu)->lbr_desc.records; +} + +#pragma GCC poison to_vmx + static void reprogram_fixed_counters(struct kvm_pmu *pmu, u64 data) { struct kvm_pmc *pmc; @@ -129,6 +148,22 @@ static inline struct kvm_pmc *get_fw_gp_pmc(struct kvm_pmu *pmu, u32 msr) return get_gp_pmc(pmu, msr, MSR_IA32_PMC0); } +static bool intel_pmu_lbr_is_compatible(struct kvm_vcpu *vcpu) +{ + if (is_td_vcpu(vcpu)) + return false; + + return cpuid_model_is_consistent(vcpu); +} + +bool intel_pmu_lbr_is_enabled(struct kvm_vcpu *vcpu) +{ + if (is_td_vcpu(vcpu)) + return false; + + return !!vcpu_to_lbr_records(vcpu)->nr; +} + static bool intel_pmu_is_valid_lbr_msr(struct kvm_vcpu *vcpu, u32 index) { struct x86_pmu_lbr *records = vcpu_to_lbr_records(vcpu); @@ -194,6 +229,9 @@ static inline void intel_pmu_release_guest_lbr_event(struct kvm_vcpu *vcpu) { struct lbr_desc *lbr_desc = vcpu_to_lbr_desc(vcpu); + if (!lbr_desc) + return; + if (lbr_desc->event) { perf_event_release_kernel(lbr_desc->event); lbr_desc->event = NULL; @@ -235,6 +273,9 @@ int intel_pmu_create_guest_lbr_event(struct kvm_vcpu *vcpu) PERF_SAMPLE_BRANCH_USER, }; + if (WARN_ON_ONCE(!lbr_desc)) + return 0; + if (unlikely(lbr_desc->event)) { __set_bit(INTEL_PMC_IDX_FIXED_VLBR, pmu->pmc_in_use); return 0; @@ -466,6 +507,9 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu) u64 perf_capabilities; u64 counter_rsvd; + if (!lbr_desc) + return; + memset(&lbr_desc->records, 0, sizeof(lbr_desc->records)); /* @@ -542,7 +586,7 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu) INTEL_PMC_MAX_GENERIC, pmu->nr_arch_fixed_counters); perf_capabilities = vcpu_get_perf_capabilities(vcpu); - if (cpuid_model_is_consistent(vcpu) && + if (intel_pmu_lbr_is_compatible(vcpu) && (perf_capabilities & PMU_CAP_LBR_FMT)) memcpy(&lbr_desc->records, &vmx_lbr_caps, sizeof(vmx_lbr_caps)); else @@ -570,6 +614,9 @@ static void intel_pmu_init(struct kvm_vcpu *vcpu) struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); struct lbr_desc *lbr_desc = vcpu_to_lbr_desc(vcpu); + if (!lbr_desc) + return; + for (i = 0; i < KVM_MAX_NR_INTEL_GP_COUNTERS; i++) { pmu->gp_counters[i].type = KVM_PMC_GP; pmu->gp_counters[i].vcpu = vcpu; @@ -677,6 +724,9 @@ void vmx_passthrough_lbr_msrs(struct kvm_vcpu *vcpu) struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); struct lbr_desc *lbr_desc = vcpu_to_lbr_desc(vcpu); + if (WARN_ON_ONCE(!lbr_desc)) + return; + if (!lbr_desc->event) { vmx_disable_lbr_msrs_passthrough(vcpu); if (vmcs_read64(GUEST_IA32_DEBUGCTL) & DEBUGCTLMSR_LBR) diff --git a/arch/x86/kvm/vmx/pmu_intel.h b/arch/x86/kvm/vmx/pmu_intel.h new file mode 100644 index 000000000000..5620d0882cdc --- /dev/null +++ b/arch/x86/kvm/vmx/pmu_intel.h @@ -0,0 +1,28 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __KVM_X86_VMX_PMU_INTEL_H +#define __KVM_X86_VMX_PMU_INTEL_H + +#include + +bool intel_pmu_lbr_is_enabled(struct kvm_vcpu *vcpu); +int intel_pmu_create_guest_lbr_event(struct kvm_vcpu *vcpu); + +struct lbr_desc { + /* Basic info about guest LBR records. */ + struct x86_pmu_lbr records; + + /* + * Emulate LBR feature via passthrough LBR registers when the + * per-vcpu guest LBR event is scheduled on the current pcpu. + * + * The records may be inaccurate if the host reclaims the LBR. + */ + struct perf_event *event; + + /* True if LBRs are marked as not intercepted in the MSR bitmap */ + bool msr_passthrough; +}; + +extern struct x86_pmu_lbr vmx_lbr_caps; + +#endif /* __KVM_X86_VMX_PMU_INTEL_H */ diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index ec8483311d00..a4ee44ffaede 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -11,6 +11,7 @@ #include "capabilities.h" #include "../kvm_cache_regs.h" +#include "pmu_intel.h" #include "vmcs.h" #include "vmx_ops.h" #include "../cpuid.h" @@ -90,24 +91,6 @@ union vmx_exit_reason { u32 full; }; -struct lbr_desc { - /* Basic info about guest LBR records. */ - struct x86_pmu_lbr records; - - /* - * Emulate LBR feature via passthrough LBR registers when the - * per-vcpu guest LBR event is scheduled on the current pcpu. - * - * The records may be inaccurate if the host reclaims the LBR. - */ - struct perf_event *event; - - /* True if LBRs are marked as not intercepted in the MSR bitmap */ - bool msr_passthrough; -}; - -extern struct x86_pmu_lbr vmx_lbr_caps; - /* * The nested_vmx structure is part of vcpu_vmx, and holds information we need * for correct emulation of VMX (i.e., nested VMX) on this vcpu. @@ -662,21 +645,6 @@ static __always_inline struct vcpu_vmx *to_vmx(struct kvm_vcpu *vcpu) return container_of(vcpu, struct vcpu_vmx, vcpu); } -static inline struct lbr_desc *vcpu_to_lbr_desc(struct kvm_vcpu *vcpu) -{ - return &to_vmx(vcpu)->lbr_desc; -} - -static inline struct x86_pmu_lbr *vcpu_to_lbr_records(struct kvm_vcpu *vcpu) -{ - return &vcpu_to_lbr_desc(vcpu)->records; -} - -static inline bool intel_pmu_lbr_is_enabled(struct kvm_vcpu *vcpu) -{ - return !!vcpu_to_lbr_records(vcpu)->nr; -} - void intel_pmu_cross_mapped_check(struct kvm_pmu *pmu); int intel_pmu_create_guest_lbr_event(struct kvm_vcpu *vcpu); void vmx_passthrough_lbr_msrs(struct kvm_vcpu *vcpu); -- 2.51.0 From 9934d7e529334d4671f96c1cab9fb1dec6ea219a Mon Sep 17 00:00:00 2001 From: Isaku Yamahata Date: Wed, 30 Oct 2024 12:00:34 -0700 Subject: [PATCH 10/16] KVM: TDX: Don't offline the last cpu of one package when there's TDX guest Destroying TDX guest requires there's at least one cpu online for each package, because reclaiming the TDX KeyID of the guest (as part of the teardown process) requires to call some SEAMCALL (on any cpu) on all packages. Do not offline the last cpu of one package when there's any TDX guest running, otherwise KVM may not be able to teardown TDX guest resulting in leaking of TDX KeyID and other resources like TDX guest control structure pages. Implement the TDX version 'offline_cpu()' to prevent the cpu from going offline if it is the last cpu on the package. Co-developed-by: Kai Huang Signed-off-by: Kai Huang Suggested-by: Sean Christopherson Signed-off-by: Isaku Yamahata Signed-off-by: Rick Edgecombe Reviewed-by: Binbin Wu Signed-off-by: Paolo Bonzini --- arch/x86/kvm/vmx/tdx.c | 43 +++++++++++++++++++++++++++++++++++++++++- 1 file changed, 42 insertions(+), 1 deletion(-) diff --git a/arch/x86/kvm/vmx/tdx.c b/arch/x86/kvm/vmx/tdx.c index b58a542fdf51..303ecd30b8e2 100644 --- a/arch/x86/kvm/vmx/tdx.c +++ b/arch/x86/kvm/vmx/tdx.c @@ -131,10 +131,13 @@ static int init_kvm_tdx_caps(const struct tdx_sys_info_td_conf *td_conf, */ static DEFINE_MUTEX(tdx_lock); +static atomic_t nr_configured_hkid; + static inline void tdx_hkid_free(struct kvm_tdx *kvm_tdx) { tdx_guest_keyid_free(kvm_tdx->hkid); kvm_tdx->hkid = -1; + atomic_dec(&nr_configured_hkid); } static inline bool is_hkid_assigned(struct kvm_tdx *kvm_tdx) @@ -603,6 +606,8 @@ static int __tdx_td_init(struct kvm *kvm, struct td_params *td_params, ret = -ENOMEM; + atomic_inc(&nr_configured_hkid); + tdr_page = alloc_page(GFP_KERNEL); if (!tdr_page) goto free_hkid; @@ -900,6 +905,42 @@ static int tdx_online_cpu(unsigned int cpu) return r; } +static int tdx_offline_cpu(unsigned int cpu) +{ + int i; + + /* No TD is running. Allow any cpu to be offline. */ + if (!atomic_read(&nr_configured_hkid)) + return 0; + + /* + * In order to reclaim TDX HKID, (i.e. when deleting guest TD), need to + * call TDH.PHYMEM.PAGE.WBINVD on all packages to program all memory + * controller with pconfig. If we have active TDX HKID, refuse to + * offline the last online cpu. + */ + for_each_online_cpu(i) { + /* + * Found another online cpu on the same package. + * Allow to offline. + */ + if (i != cpu && topology_physical_package_id(i) == + topology_physical_package_id(cpu)) + return 0; + } + + /* + * This is the last cpu of this package. Don't offline it. + * + * Because it's hard for human operator to understand the + * reason, warn it. + */ +#define MSG_ALLPKG_ONLINE \ + "TDX requires all packages to have an online CPU. Delete all TDs in order to offline all CPUs of a package.\n" + pr_warn_ratelimited(MSG_ALLPKG_ONLINE); + return -EBUSY; +} + static void __do_tdx_cleanup(void) { /* @@ -932,7 +973,7 @@ static int __init __do_tdx_bringup(void) */ r = cpuhp_setup_state_cpuslocked(CPUHP_AP_ONLINE_DYN, "kvm/cpu/tdx:online", - tdx_online_cpu, NULL); + tdx_online_cpu, tdx_offline_cpu); if (r < 0) return r; -- 2.51.0 From 9002f8cf5295218eefdd54111e8f8930ce25d0ad Mon Sep 17 00:00:00 2001 From: Isaku Yamahata Date: Wed, 30 Oct 2024 12:00:35 -0700 Subject: [PATCH 11/16] KVM: TDX: create/free TDX vcpu structure Implement vcpu related stubs for TDX for create, reset and free. For now, create only the features that do not require the TDX SEAMCALL. The TDX specific vcpu initialization will be handled by KVM_TDX_INIT_VCPU. Signed-off-by: Isaku Yamahata Signed-off-by: Rick Edgecombe --- - Use lapic_in_kernel() (Nikolay Borisov) Signed-off-by: Paolo Bonzini --- arch/x86/kvm/vmx/main.c | 42 ++++++++++++++++++++++++++++++++++---- arch/x86/kvm/vmx/tdx.c | 40 ++++++++++++++++++++++++++++++++++++ arch/x86/kvm/vmx/x86_ops.h | 6 ++++++ 3 files changed, 84 insertions(+), 4 deletions(-) diff --git a/arch/x86/kvm/vmx/main.c b/arch/x86/kvm/vmx/main.c index e0806dbe7b87..a840a8481589 100644 --- a/arch/x86/kvm/vmx/main.c +++ b/arch/x86/kvm/vmx/main.c @@ -64,6 +64,40 @@ static void vt_vm_destroy(struct kvm *kvm) vmx_vm_destroy(kvm); } +static int vt_vcpu_precreate(struct kvm *kvm) +{ + if (is_td(kvm)) + return 0; + + return vmx_vcpu_precreate(kvm); +} + +static int vt_vcpu_create(struct kvm_vcpu *vcpu) +{ + if (is_td_vcpu(vcpu)) + return tdx_vcpu_create(vcpu); + + return vmx_vcpu_create(vcpu); +} + +static void vt_vcpu_free(struct kvm_vcpu *vcpu) +{ + if (is_td_vcpu(vcpu)) { + tdx_vcpu_free(vcpu); + return; + } + + vmx_vcpu_free(vcpu); +} + +static void vt_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) +{ + if (is_td_vcpu(vcpu)) + return; + + vmx_vcpu_reset(vcpu, init_event); +} + static int vt_mem_enc_ioctl(struct kvm *kvm, void __user *argp) { if (!is_td(kvm)) @@ -100,10 +134,10 @@ struct kvm_x86_ops vt_x86_ops __initdata = { .vm_pre_destroy = vt_vm_pre_destroy, .vm_destroy = vt_vm_destroy, - .vcpu_precreate = vmx_vcpu_precreate, - .vcpu_create = vmx_vcpu_create, - .vcpu_free = vmx_vcpu_free, - .vcpu_reset = vmx_vcpu_reset, + .vcpu_precreate = vt_vcpu_precreate, + .vcpu_create = vt_vcpu_create, + .vcpu_free = vt_vcpu_free, + .vcpu_reset = vt_vcpu_reset, .prepare_switch_to_guest = vmx_prepare_switch_to_guest, .vcpu_load = vmx_vcpu_load, diff --git a/arch/x86/kvm/vmx/tdx.c b/arch/x86/kvm/vmx/tdx.c index 303ecd30b8e2..e7bcea016f64 100644 --- a/arch/x86/kvm/vmx/tdx.c +++ b/arch/x86/kvm/vmx/tdx.c @@ -4,6 +4,7 @@ #include #include "capabilities.h" #include "x86_ops.h" +#include "lapic.h" #include "tdx.h" #pragma GCC poison to_vmx @@ -406,6 +407,45 @@ int tdx_vm_init(struct kvm *kvm) return 0; } +int tdx_vcpu_create(struct kvm_vcpu *vcpu) +{ + struct kvm_tdx *kvm_tdx = to_kvm_tdx(vcpu->kvm); + + if (kvm_tdx->state != TD_STATE_INITIALIZED) + return -EIO; + + /* TDX module mandates APICv, which requires an in-kernel local APIC. */ + if (!lapic_in_kernel(vcpu)) + return -EINVAL; + + fpstate_set_confidential(&vcpu->arch.guest_fpu); + + vcpu->arch.efer = EFER_SCE | EFER_LME | EFER_LMA | EFER_NX; + + vcpu->arch.cr0_guest_owned_bits = -1ul; + vcpu->arch.cr4_guest_owned_bits = -1ul; + + /* KVM can't change TSC offset/multiplier as TDX module manages them. */ + vcpu->arch.guest_tsc_protected = true; + vcpu->arch.tsc_offset = kvm_tdx->tsc_offset; + vcpu->arch.l1_tsc_offset = vcpu->arch.tsc_offset; + vcpu->arch.tsc_scaling_ratio = kvm_tdx->tsc_multiplier; + vcpu->arch.l1_tsc_scaling_ratio = kvm_tdx->tsc_multiplier; + + vcpu->arch.guest_state_protected = + !(to_kvm_tdx(vcpu->kvm)->attributes & TDX_TD_ATTR_DEBUG); + + if ((kvm_tdx->xfam & XFEATURE_MASK_XTILE) == XFEATURE_MASK_XTILE) + vcpu->arch.xfd_no_write_intercept = true; + + return 0; +} + +void tdx_vcpu_free(struct kvm_vcpu *vcpu) +{ + /* This is stub for now. More logic will come. */ +} + static int tdx_get_capabilities(struct kvm_tdx_cmd *cmd) { const struct tdx_sys_info_td_conf *td_conf = &tdx_sysinfo->td_conf; diff --git a/arch/x86/kvm/vmx/x86_ops.h b/arch/x86/kvm/vmx/x86_ops.h index 85c78639d476..c57a69a9c7d0 100644 --- a/arch/x86/kvm/vmx/x86_ops.h +++ b/arch/x86/kvm/vmx/x86_ops.h @@ -126,11 +126,17 @@ int tdx_vm_init(struct kvm *kvm); void tdx_mmu_release_hkid(struct kvm *kvm); void tdx_vm_destroy(struct kvm *kvm); int tdx_vm_ioctl(struct kvm *kvm, void __user *argp); + +int tdx_vcpu_create(struct kvm_vcpu *vcpu); +void tdx_vcpu_free(struct kvm_vcpu *vcpu); #else static inline int tdx_vm_init(struct kvm *kvm) { return -EOPNOTSUPP; } static inline void tdx_mmu_release_hkid(struct kvm *kvm) {} static inline void tdx_vm_destroy(struct kvm *kvm) {} static inline int tdx_vm_ioctl(struct kvm *kvm, void __user *argp) { return -EOPNOTSUPP; } + +static inline int tdx_vcpu_create(struct kvm_vcpu *vcpu) { return -EOPNOTSUPP; } +static inline void tdx_vcpu_free(struct kvm_vcpu *vcpu) {} #endif #endif /* __KVM_X86_VMX_X86_OPS_H */ -- 2.51.0 From a50f673f25e0ba2b594d94efe235f4eb57d0e784 Mon Sep 17 00:00:00 2001 From: Isaku Yamahata Date: Wed, 30 Oct 2024 12:00:36 -0700 Subject: [PATCH 12/16] KVM: TDX: Do TDX specific vcpu initialization TD guest vcpu needs TDX specific initialization before running. Repurpose KVM_MEMORY_ENCRYPT_OP to vcpu-scope, add a new sub-command KVM_TDX_INIT_VCPU, and implement the callback for it. Signed-off-by: Sean Christopherson Signed-off-by: Isaku Yamahata Co-developed-by: Tony Lindgren Signed-off-by: Tony Lindgren Co-developed-by: Adrian Hunter Signed-off-by: Adrian Hunter Signed-off-by: Rick Edgecombe --- - Fix comment: https://lore.kernel.org/kvm/Z36OYfRW9oPjW8be@google.com/ (Sean) Signed-off-by: Paolo Bonzini --- arch/x86/include/asm/kvm-x86-ops.h | 1 + arch/x86/include/asm/kvm_host.h | 1 + arch/x86/include/uapi/asm/kvm.h | 1 + arch/x86/kvm/lapic.c | 1 + arch/x86/kvm/vmx/main.c | 9 ++ arch/x86/kvm/vmx/tdx.c | 172 ++++++++++++++++++++++++++++- arch/x86/kvm/vmx/tdx.h | 11 +- arch/x86/kvm/vmx/x86_ops.h | 4 + arch/x86/kvm/x86.c | 7 ++ 9 files changed, 205 insertions(+), 2 deletions(-) diff --git a/arch/x86/include/asm/kvm-x86-ops.h b/arch/x86/include/asm/kvm-x86-ops.h index e6cb89ced1fd..aae4193f80e3 100644 --- a/arch/x86/include/asm/kvm-x86-ops.h +++ b/arch/x86/include/asm/kvm-x86-ops.h @@ -127,6 +127,7 @@ KVM_X86_OP(enable_smi_window) #endif KVM_X86_OP_OPTIONAL(dev_get_attr) KVM_X86_OP(mem_enc_ioctl) +KVM_X86_OP_OPTIONAL(vcpu_mem_enc_ioctl) KVM_X86_OP_OPTIONAL(mem_enc_register_region) KVM_X86_OP_OPTIONAL(mem_enc_unregister_region) KVM_X86_OP_OPTIONAL(vm_copy_enc_context_from) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 405d38924279..6800d3956ab1 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -1849,6 +1849,7 @@ struct kvm_x86_ops { int (*dev_get_attr)(u32 group, u64 attr, u64 *val); int (*mem_enc_ioctl)(struct kvm *kvm, void __user *argp); + int (*vcpu_mem_enc_ioctl)(struct kvm_vcpu *vcpu, void __user *argp); int (*mem_enc_register_region)(struct kvm *kvm, struct kvm_enc_region *argp); int (*mem_enc_unregister_region)(struct kvm *kvm, struct kvm_enc_region *argp); int (*vm_copy_enc_context_from)(struct kvm *kvm, unsigned int source_fd); diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h index b64351076f2a..9316afbd4a88 100644 --- a/arch/x86/include/uapi/asm/kvm.h +++ b/arch/x86/include/uapi/asm/kvm.h @@ -931,6 +931,7 @@ struct kvm_hyperv_eventfd { enum kvm_tdx_cmd_id { KVM_TDX_CAPABILITIES = 0, KVM_TDX_INIT_VM, + KVM_TDX_INIT_VCPU, KVM_TDX_CMD_NR_MAX, }; diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index a009c94c26c2..a1cbca31ec30 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -2657,6 +2657,7 @@ int kvm_apic_set_base(struct kvm_vcpu *vcpu, u64 value, bool host_initiated) kvm_recalculate_apic_map(vcpu->kvm); return 0; } +EXPORT_SYMBOL_GPL(kvm_apic_set_base); void kvm_apic_update_apicv(struct kvm_vcpu *vcpu) { diff --git a/arch/x86/kvm/vmx/main.c b/arch/x86/kvm/vmx/main.c index a840a8481589..e7d402b3a90d 100644 --- a/arch/x86/kvm/vmx/main.c +++ b/arch/x86/kvm/vmx/main.c @@ -106,6 +106,14 @@ static int vt_mem_enc_ioctl(struct kvm *kvm, void __user *argp) return tdx_vm_ioctl(kvm, argp); } +static int vt_vcpu_mem_enc_ioctl(struct kvm_vcpu *vcpu, void __user *argp) +{ + if (!is_td_vcpu(vcpu)) + return -EINVAL; + + return tdx_vcpu_ioctl(vcpu, argp); +} + #define VMX_REQUIRED_APICV_INHIBITS \ (BIT(APICV_INHIBIT_REASON_DISABLED) | \ BIT(APICV_INHIBIT_REASON_ABSENT) | \ @@ -262,6 +270,7 @@ struct kvm_x86_ops vt_x86_ops __initdata = { .get_untagged_addr = vmx_get_untagged_addr, .mem_enc_ioctl = vt_mem_enc_ioctl, + .vcpu_mem_enc_ioctl = vt_vcpu_mem_enc_ioctl, }; struct kvm_x86_init_ops vt_init_ops __initdata = { diff --git a/arch/x86/kvm/vmx/tdx.c b/arch/x86/kvm/vmx/tdx.c index e7bcea016f64..4ba46ac3b9af 100644 --- a/arch/x86/kvm/vmx/tdx.c +++ b/arch/x86/kvm/vmx/tdx.c @@ -410,6 +410,7 @@ int tdx_vm_init(struct kvm *kvm) int tdx_vcpu_create(struct kvm_vcpu *vcpu) { struct kvm_tdx *kvm_tdx = to_kvm_tdx(vcpu->kvm); + struct vcpu_tdx *tdx = to_tdx(vcpu); if (kvm_tdx->state != TD_STATE_INITIALIZED) return -EIO; @@ -438,12 +439,42 @@ int tdx_vcpu_create(struct kvm_vcpu *vcpu) if ((kvm_tdx->xfam & XFEATURE_MASK_XTILE) == XFEATURE_MASK_XTILE) vcpu->arch.xfd_no_write_intercept = true; + tdx->state = VCPU_TD_STATE_UNINITIALIZED; + return 0; } void tdx_vcpu_free(struct kvm_vcpu *vcpu) { - /* This is stub for now. More logic will come. */ + struct kvm_tdx *kvm_tdx = to_kvm_tdx(vcpu->kvm); + struct vcpu_tdx *tdx = to_tdx(vcpu); + int i; + + /* + * It is not possible to reclaim pages while hkid is assigned. It might + * be assigned if: + * 1. the TD VM is being destroyed but freeing hkid failed, in which + * case the pages are leaked + * 2. TD VCPU creation failed and this on the error path, in which case + * there is nothing to do anyway + */ + if (is_hkid_assigned(kvm_tdx)) + return; + + if (tdx->vp.tdcx_pages) { + for (i = 0; i < kvm_tdx->td.tdcx_nr_pages; i++) { + if (tdx->vp.tdcx_pages[i]) + tdx_reclaim_control_page(tdx->vp.tdcx_pages[i]); + } + kfree(tdx->vp.tdcx_pages); + tdx->vp.tdcx_pages = NULL; + } + if (tdx->vp.tdvpr_page) { + tdx_reclaim_control_page(tdx->vp.tdvpr_page); + tdx->vp.tdvpr_page = 0; + } + + tdx->state = VCPU_TD_STATE_UNINITIALIZED; } static int tdx_get_capabilities(struct kvm_tdx_cmd *cmd) @@ -653,6 +684,8 @@ static int __tdx_td_init(struct kvm *kvm, struct td_params *td_params, goto free_hkid; kvm_tdx->td.tdcs_nr_pages = tdx_sysinfo->td_ctrl.tdcs_base_size / PAGE_SIZE; + /* TDVPS = TDVPR(4K page) + TDCX(multiple 4K pages), -1 for TDVPR. */ + kvm_tdx->td.tdcx_nr_pages = tdx_sysinfo->td_ctrl.tdvps_base_size / PAGE_SIZE - 1; tdcs_pages = kcalloc(kvm_tdx->td.tdcs_nr_pages, sizeof(*kvm_tdx->td.tdcs_pages), GFP_KERNEL | __GFP_ZERO); if (!tdcs_pages) @@ -930,6 +963,143 @@ out: return r; } +/* VMM can pass one 64bit auxiliary data to vcpu via RCX for guest BIOS. */ +static int tdx_td_vcpu_init(struct kvm_vcpu *vcpu, u64 vcpu_rcx) +{ + struct kvm_tdx *kvm_tdx = to_kvm_tdx(vcpu->kvm); + struct vcpu_tdx *tdx = to_tdx(vcpu); + struct page *page; + int ret, i; + u64 err; + + page = alloc_page(GFP_KERNEL); + if (!page) + return -ENOMEM; + tdx->vp.tdvpr_page = page; + + tdx->vp.tdcx_pages = kcalloc(kvm_tdx->td.tdcx_nr_pages, sizeof(*tdx->vp.tdcx_pages), + GFP_KERNEL); + if (!tdx->vp.tdcx_pages) { + ret = -ENOMEM; + goto free_tdvpr; + } + + for (i = 0; i < kvm_tdx->td.tdcx_nr_pages; i++) { + page = alloc_page(GFP_KERNEL); + if (!page) { + ret = -ENOMEM; + goto free_tdcx; + } + tdx->vp.tdcx_pages[i] = page; + } + + err = tdh_vp_create(&kvm_tdx->td, &tdx->vp); + if (KVM_BUG_ON(err, vcpu->kvm)) { + ret = -EIO; + pr_tdx_error(TDH_VP_CREATE, err); + goto free_tdcx; + } + + for (i = 0; i < kvm_tdx->td.tdcx_nr_pages; i++) { + err = tdh_vp_addcx(&tdx->vp, tdx->vp.tdcx_pages[i]); + if (KVM_BUG_ON(err, vcpu->kvm)) { + pr_tdx_error(TDH_VP_ADDCX, err); + /* + * Pages already added are reclaimed by the vcpu_free + * method, but the rest are freed here. + */ + for (; i < kvm_tdx->td.tdcx_nr_pages; i++) { + __free_page(tdx->vp.tdcx_pages[i]); + tdx->vp.tdcx_pages[i] = NULL; + } + return -EIO; + } + } + + err = tdh_vp_init(&tdx->vp, vcpu_rcx, vcpu->vcpu_id); + if (KVM_BUG_ON(err, vcpu->kvm)) { + pr_tdx_error(TDH_VP_INIT, err); + return -EIO; + } + + vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; + + return 0; + +free_tdcx: + for (i = 0; i < kvm_tdx->td.tdcx_nr_pages; i++) { + if (tdx->vp.tdcx_pages[i]) + __free_page(tdx->vp.tdcx_pages[i]); + tdx->vp.tdcx_pages[i] = NULL; + } + kfree(tdx->vp.tdcx_pages); + tdx->vp.tdcx_pages = NULL; + +free_tdvpr: + if (tdx->vp.tdvpr_page) + __free_page(tdx->vp.tdvpr_page); + tdx->vp.tdvpr_page = 0; + + return ret; +} + +static int tdx_vcpu_init(struct kvm_vcpu *vcpu, struct kvm_tdx_cmd *cmd) +{ + u64 apic_base; + struct vcpu_tdx *tdx = to_tdx(vcpu); + int ret; + + if (cmd->flags) + return -EINVAL; + + if (tdx->state != VCPU_TD_STATE_UNINITIALIZED) + return -EINVAL; + + /* + * TDX requires X2APIC, userspace is responsible for configuring guest + * CPUID accordingly. + */ + apic_base = APIC_DEFAULT_PHYS_BASE | LAPIC_MODE_X2APIC | + (kvm_vcpu_is_reset_bsp(vcpu) ? MSR_IA32_APICBASE_BSP : 0); + if (kvm_apic_set_base(vcpu, apic_base, true)) + return -EINVAL; + + ret = tdx_td_vcpu_init(vcpu, (u64)cmd->data); + if (ret) + return ret; + + tdx->state = VCPU_TD_STATE_INITIALIZED; + + return 0; +} + +int tdx_vcpu_ioctl(struct kvm_vcpu *vcpu, void __user *argp) +{ + struct kvm_tdx *kvm_tdx = to_kvm_tdx(vcpu->kvm); + struct kvm_tdx_cmd cmd; + int ret; + + if (!is_hkid_assigned(kvm_tdx) || kvm_tdx->state == TD_STATE_RUNNABLE) + return -EINVAL; + + if (copy_from_user(&cmd, argp, sizeof(cmd))) + return -EFAULT; + + if (cmd.hw_error) + return -EINVAL; + + switch (cmd.id) { + case KVM_TDX_INIT_VCPU: + ret = tdx_vcpu_init(vcpu, &cmd); + break; + default: + ret = -EINVAL; + break; + } + + return ret; +} + static int tdx_online_cpu(unsigned int cpu) { unsigned long flags; diff --git a/arch/x86/kvm/vmx/tdx.h b/arch/x86/kvm/vmx/tdx.h index 6e23f78c2713..6ec7ac1d91e3 100644 --- a/arch/x86/kvm/vmx/tdx.h +++ b/arch/x86/kvm/vmx/tdx.h @@ -33,9 +33,18 @@ struct kvm_tdx { struct tdx_td td; }; +/* TDX module vCPU states */ +enum vcpu_tdx_state { + VCPU_TD_STATE_UNINITIALIZED = 0, + VCPU_TD_STATE_INITIALIZED, +}; + struct vcpu_tdx { struct kvm_vcpu vcpu; - /* TDX specific members follow. */ + + struct tdx_vp vp; + + enum vcpu_tdx_state state; }; static inline bool is_td(struct kvm *kvm) diff --git a/arch/x86/kvm/vmx/x86_ops.h b/arch/x86/kvm/vmx/x86_ops.h index c57a69a9c7d0..89bb7785bd09 100644 --- a/arch/x86/kvm/vmx/x86_ops.h +++ b/arch/x86/kvm/vmx/x86_ops.h @@ -129,6 +129,8 @@ int tdx_vm_ioctl(struct kvm *kvm, void __user *argp); int tdx_vcpu_create(struct kvm_vcpu *vcpu); void tdx_vcpu_free(struct kvm_vcpu *vcpu); + +int tdx_vcpu_ioctl(struct kvm_vcpu *vcpu, void __user *argp); #else static inline int tdx_vm_init(struct kvm *kvm) { return -EOPNOTSUPP; } static inline void tdx_mmu_release_hkid(struct kvm *kvm) {} @@ -137,6 +139,8 @@ static inline int tdx_vm_ioctl(struct kvm *kvm, void __user *argp) { return -EOP static inline int tdx_vcpu_create(struct kvm_vcpu *vcpu) { return -EOPNOTSUPP; } static inline void tdx_vcpu_free(struct kvm_vcpu *vcpu) {} + +static inline int tdx_vcpu_ioctl(struct kvm_vcpu *vcpu, void __user *argp) { return -EOPNOTSUPP; } #endif #endif /* __KVM_X86_VMX_X86_OPS_H */ diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index a4d1f3319a5b..9f92170226e5 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -6287,6 +6287,12 @@ long kvm_arch_vcpu_ioctl(struct file *filp, case KVM_SET_DEVICE_ATTR: r = kvm_vcpu_ioctl_device_attr(vcpu, ioctl, argp); break; + case KVM_MEMORY_ENCRYPT_OP: + r = -ENOTTY; + if (!kvm_x86_ops.vcpu_mem_enc_ioctl) + goto out; + r = kvm_x86_ops.vcpu_mem_enc_ioctl(vcpu, argp); + break; default: r = -EINVAL; } @@ -12676,6 +12682,7 @@ bool kvm_vcpu_is_reset_bsp(struct kvm_vcpu *vcpu) { return vcpu->kvm->arch.bsp_vcpu_id == vcpu->vcpu_id; } +EXPORT_SYMBOL_GPL(kvm_vcpu_is_reset_bsp); bool kvm_vcpu_is_bsp(struct kvm_vcpu *vcpu) { -- 2.51.0 From 488808e682e72bdb15a579d61f5b90ece92ba83c Mon Sep 17 00:00:00 2001 From: Xiaoyao Li Date: Wed, 30 Oct 2024 12:00:37 -0700 Subject: [PATCH 13/16] KVM: x86: Introduce KVM_TDX_GET_CPUID Implement an IOCTL to allow userspace to read the CPUID bit values for a configured TD. The TDX module doesn't provide the ability to set all CPUID bits. Instead some are configured indirectly, or have fixed values. But it does allow for the final resulting CPUID bits to be read. This information will be useful for userspace to understand the configuration of the TD, and set KVM's copy via KVM_SET_CPUID2. Signed-off-by: Xiaoyao Li Co-developed-by: Tony Lindgren Signed-off-by: Tony Lindgren Signed-off-by: Rick Edgecombe --- - Fix subleaf mask check (Binbin) - Search all possible sub-leafs (Francesco Lavra) - Reduce off-by-one error sensitve code (Francesco, Xiaoyao) - Handle buffers too small from userspace (Xiaoyao) - Read max CPUID from TD instead of using fixed values (Xiaoyao) Signed-off-by: Paolo Bonzini --- arch/x86/include/uapi/asm/kvm.h | 1 + arch/x86/kvm/vmx/tdx.c | 191 ++++++++++++++++++++++++++++++++ arch/x86/kvm/vmx/tdx_arch.h | 5 + arch/x86/kvm/vmx/tdx_errno.h | 1 + 4 files changed, 198 insertions(+) diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h index 9316afbd4a88..cd55484e3f0c 100644 --- a/arch/x86/include/uapi/asm/kvm.h +++ b/arch/x86/include/uapi/asm/kvm.h @@ -932,6 +932,7 @@ enum kvm_tdx_cmd_id { KVM_TDX_CAPABILITIES = 0, KVM_TDX_INIT_VM, KVM_TDX_INIT_VCPU, + KVM_TDX_GET_CPUID, KVM_TDX_CMD_NR_MAX, }; diff --git a/arch/x86/kvm/vmx/tdx.c b/arch/x86/kvm/vmx/tdx.c index 4ba46ac3b9af..2ac925ecccd5 100644 --- a/arch/x86/kvm/vmx/tdx.c +++ b/arch/x86/kvm/vmx/tdx.c @@ -3,6 +3,7 @@ #include #include #include "capabilities.h" +#include "mmu.h" #include "x86_ops.h" #include "lapic.h" #include "tdx.h" @@ -849,6 +850,103 @@ free_hkid: return ret; } +static u64 tdx_td_metadata_field_read(struct kvm_tdx *tdx, u64 field_id, + u64 *data) +{ + u64 err; + + err = tdh_mng_rd(&tdx->td, field_id, data); + + return err; +} + +#define TDX_MD_UNREADABLE_LEAF_MASK GENMASK(30, 7) +#define TDX_MD_UNREADABLE_SUBLEAF_MASK GENMASK(31, 7) + +static int tdx_read_cpuid(struct kvm_vcpu *vcpu, u32 leaf, u32 sub_leaf, + bool sub_leaf_set, int *entry_index, + struct kvm_cpuid_entry2 *out) +{ + struct kvm_tdx *kvm_tdx = to_kvm_tdx(vcpu->kvm); + u64 field_id = TD_MD_FIELD_ID_CPUID_VALUES; + u64 ebx_eax, edx_ecx; + u64 err = 0; + + if (sub_leaf > 0b1111111) + return -EINVAL; + + if (*entry_index >= KVM_MAX_CPUID_ENTRIES) + return -EINVAL; + + if (leaf & TDX_MD_UNREADABLE_LEAF_MASK || + sub_leaf & TDX_MD_UNREADABLE_SUBLEAF_MASK) + return -EINVAL; + + /* + * bit 23:17, REVSERVED: reserved, must be 0; + * bit 16, LEAF_31: leaf number bit 31; + * bit 15:9, LEAF_6_0: leaf number bits 6:0, leaf bits 30:7 are + * implicitly 0; + * bit 8, SUBLEAF_NA: sub-leaf not applicable flag; + * bit 7:1, SUBLEAF_6_0: sub-leaf number bits 6:0. If SUBLEAF_NA is 1, + * the SUBLEAF_6_0 is all-1. + * sub-leaf bits 31:7 are implicitly 0; + * bit 0, ELEMENT_I: Element index within field; + */ + field_id |= ((leaf & 0x80000000) ? 1 : 0) << 16; + field_id |= (leaf & 0x7f) << 9; + if (sub_leaf_set) + field_id |= (sub_leaf & 0x7f) << 1; + else + field_id |= 0x1fe; + + err = tdx_td_metadata_field_read(kvm_tdx, field_id, &ebx_eax); + if (err) //TODO check for specific errors + goto err_out; + + out->eax = (u32) ebx_eax; + out->ebx = (u32) (ebx_eax >> 32); + + field_id++; + err = tdx_td_metadata_field_read(kvm_tdx, field_id, &edx_ecx); + /* + * It's weird that reading edx_ecx fails while reading ebx_eax + * succeeded. + */ + if (WARN_ON_ONCE(err)) + goto err_out; + + out->ecx = (u32) edx_ecx; + out->edx = (u32) (edx_ecx >> 32); + + out->function = leaf; + out->index = sub_leaf; + out->flags |= sub_leaf_set ? KVM_CPUID_FLAG_SIGNIFCANT_INDEX : 0; + + /* + * Work around missing support on old TDX modules, fetch + * guest maxpa from gfn_direct_bits. + */ + if (leaf == 0x80000008) { + gpa_t gpa_bits = gfn_to_gpa(kvm_gfn_direct_bits(vcpu->kvm)); + unsigned int g_maxpa = __ffs(gpa_bits) + 1; + + out->eax = tdx_set_guest_phys_addr_bits(out->eax, g_maxpa); + } + + (*entry_index)++; + + return 0; + +err_out: + out->eax = 0; + out->ebx = 0; + out->ecx = 0; + out->edx = 0; + + return -EIO; +} + static int tdx_td_init(struct kvm *kvm, struct kvm_tdx_cmd *cmd) { struct kvm_tdx *kvm_tdx = to_kvm_tdx(kvm); @@ -1043,6 +1141,96 @@ free_tdvpr: return ret; } +/* Sometimes reads multipple subleafs. Return how many enties were written. */ +static int tdx_vcpu_get_cpuid_leaf(struct kvm_vcpu *vcpu, u32 leaf, int *entry_index, + struct kvm_cpuid_entry2 *output_e) +{ + int sub_leaf = 0; + int ret; + + /* First try without a subleaf */ + ret = tdx_read_cpuid(vcpu, leaf, 0, false, entry_index, output_e); + + /* If success, or invalid leaf, just give up */ + if (ret != -EIO) + return ret; + + /* + * If the try without a subleaf failed, try reading subleafs until + * failure. The TDX module only supports 6 bits of subleaf index. + */ + while (1) { + /* Keep reading subleafs until there is a failure. */ + if (tdx_read_cpuid(vcpu, leaf, sub_leaf, true, entry_index, output_e)) + return !sub_leaf; + + sub_leaf++; + output_e++; + } + + return 0; +} + +static int tdx_vcpu_get_cpuid(struct kvm_vcpu *vcpu, struct kvm_tdx_cmd *cmd) +{ + struct kvm_cpuid2 __user *output, *td_cpuid; + int r = 0, i = 0, leaf; + u32 level; + + output = u64_to_user_ptr(cmd->data); + td_cpuid = kzalloc(sizeof(*td_cpuid) + + sizeof(output->entries[0]) * KVM_MAX_CPUID_ENTRIES, + GFP_KERNEL); + if (!td_cpuid) + return -ENOMEM; + + if (copy_from_user(td_cpuid, output, sizeof(*output))) { + r = -EFAULT; + goto out; + } + + /* Read max CPUID for normal range */ + if (tdx_vcpu_get_cpuid_leaf(vcpu, 0, &i, &td_cpuid->entries[i])) { + r = -EIO; + goto out; + } + level = td_cpuid->entries[0].eax; + + for (leaf = 1; leaf <= level; leaf++) + tdx_vcpu_get_cpuid_leaf(vcpu, leaf, &i, &td_cpuid->entries[i]); + + /* Read max CPUID for extended range */ + if (tdx_vcpu_get_cpuid_leaf(vcpu, 0x80000000, &i, &td_cpuid->entries[i])) { + r = -EIO; + goto out; + } + level = td_cpuid->entries[i - 1].eax; + + for (leaf = 0x80000001; leaf <= level; leaf++) + tdx_vcpu_get_cpuid_leaf(vcpu, leaf, &i, &td_cpuid->entries[i]); + + if (td_cpuid->nent < i) + r = -E2BIG; + td_cpuid->nent = i; + + if (copy_to_user(output, td_cpuid, sizeof(*output))) { + r = -EFAULT; + goto out; + } + + if (r == -E2BIG) + goto out; + + if (copy_to_user(output->entries, td_cpuid->entries, + td_cpuid->nent * sizeof(struct kvm_cpuid_entry2))) + r = -EFAULT; + +out: + kfree(td_cpuid); + + return r; +} + static int tdx_vcpu_init(struct kvm_vcpu *vcpu, struct kvm_tdx_cmd *cmd) { u64 apic_base; @@ -1092,6 +1280,9 @@ int tdx_vcpu_ioctl(struct kvm_vcpu *vcpu, void __user *argp) case KVM_TDX_INIT_VCPU: ret = tdx_vcpu_init(vcpu, &cmd); break; + case KVM_TDX_GET_CPUID: + ret = tdx_vcpu_get_cpuid(vcpu, &cmd); + break; default: ret = -EINVAL; break; diff --git a/arch/x86/kvm/vmx/tdx_arch.h b/arch/x86/kvm/vmx/tdx_arch.h index 0e09188a8785..55a740f90e67 100644 --- a/arch/x86/kvm/vmx/tdx_arch.h +++ b/arch/x86/kvm/vmx/tdx_arch.h @@ -123,4 +123,9 @@ struct td_params { #define MD_FIELD_ID_FEATURES0_TOPOLOGY_ENUM BIT_ULL(20) +/* + * TD scope metadata field ID. + */ +#define TD_MD_FIELD_ID_CPUID_VALUES 0x9410000300000000ULL + #endif /* __KVM_X86_TDX_ARCH_H */ diff --git a/arch/x86/kvm/vmx/tdx_errno.h b/arch/x86/kvm/vmx/tdx_errno.h index dc3fa2a58c2c..f9dbb3a065cc 100644 --- a/arch/x86/kvm/vmx/tdx_errno.h +++ b/arch/x86/kvm/vmx/tdx_errno.h @@ -23,6 +23,7 @@ #define TDX_FLUSHVP_NOT_DONE 0x8000082400000000ULL #define TDX_EPT_WALK_FAILED 0xC0000B0000000000ULL #define TDX_EPT_ENTRY_STATE_INCORRECT 0xC0000B0D00000000ULL +#define TDX_METADATA_FIELD_NOT_READABLE 0xC0000C0200000000ULL /* * TDX module operand ID, appears in 31:0 part of error code as -- 2.51.0 From 20d913729c116a43119de76d346e0d3da0dc856b Mon Sep 17 00:00:00 2001 From: Xiaoyao Li Date: Wed, 30 Oct 2024 12:00:38 -0700 Subject: [PATCH 14/16] KVM: x86/mmu: Taking guest pa into consideration when calculate tdp level For TDX, the maxpa (CPUID.0x80000008.EAX[7:0]) is fixed as native and the max_gpa (CPUID.0x80000008.EAX[23:16]) is configurable and used to configure the EPT level and GPAW. Use max_gpa to determine the TDP level. Signed-off-by: Xiaoyao Li Signed-off-by: Rick Edgecombe Signed-off-by: Paolo Bonzini --- arch/x86/kvm/cpuid.c | 14 ++++++++++++++ arch/x86/kvm/cpuid.h | 1 + arch/x86/kvm/mmu/mmu.c | 9 ++++++++- 3 files changed, 23 insertions(+), 1 deletion(-) diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 45392cf42dbc..75a2f32eb26b 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -463,6 +463,20 @@ not_found: return 36; } +int cpuid_query_maxguestphyaddr(struct kvm_vcpu *vcpu) +{ + struct kvm_cpuid_entry2 *best; + + best = kvm_find_cpuid_entry(vcpu, 0x80000000); + if (!best || best->eax < 0x80000008) + goto not_found; + best = kvm_find_cpuid_entry(vcpu, 0x80000008); + if (best) + return (best->eax >> 16) & 0xff; +not_found: + return 0; +} + /* * This "raw" version returns the reserved GPA bits without any adjustments for * encryption technologies that usurp bits. The raw mask should be used if and diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h index 69ae6768e830..5c174421a4d9 100644 --- a/arch/x86/kvm/cpuid.h +++ b/arch/x86/kvm/cpuid.h @@ -59,6 +59,7 @@ void __init kvm_init_xstate_sizes(void); u32 xstate_required_size(u64 xstate_bv, bool compacted); int cpuid_query_maxphyaddr(struct kvm_vcpu *vcpu); +int cpuid_query_maxguestphyaddr(struct kvm_vcpu *vcpu); u64 kvm_vcpu_reserved_gpa_bits_raw(struct kvm_vcpu *vcpu); static inline int cpuid_maxphyaddr(struct kvm_vcpu *vcpu) diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 8160870398b9..a79bc15f31c6 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -5416,12 +5416,19 @@ void __kvm_mmu_refresh_passthrough_bits(struct kvm_vcpu *vcpu, static inline int kvm_mmu_get_tdp_level(struct kvm_vcpu *vcpu) { + int maxpa; + + if (vcpu->kvm->arch.vm_type == KVM_X86_TDX_VM) + maxpa = cpuid_query_maxguestphyaddr(vcpu); + else + maxpa = cpuid_maxphyaddr(vcpu); + /* tdp_root_level is architecture forced level, use it if nonzero */ if (tdp_root_level) return tdp_root_level; /* Use 5-level TDP if and only if it's useful/necessary. */ - if (max_tdp_level == 5 && cpuid_maxphyaddr(vcpu) <= 48) + if (max_tdp_level == 5 && maxpa <= 48) return 4; return max_tdp_level; -- 2.51.0 From 7c035bea94074b19ed560a4f23a76c5a6c8e594f Mon Sep 17 00:00:00 2001 From: Zhiming Hu Date: Wed, 19 Feb 2025 09:02:51 -0500 Subject: [PATCH 15/16] KVM: TDX: Register TDX host key IDs to cgroup misc controller TDX host key IDs (HKID) are limit resources in a machine, and the misc cgroup lets the machine owner track their usage and limits the possibility of abusing them outside the owner's control. The cgroup v2 miscellaneous subsystem was introduced to control the resource of AMD SEV & SEV-ES ASIDs. Likewise introduce HKIDs as a misc resource. Signed-off-by: Zhiming Hu Signed-off-by: Isaku Yamahata Signed-off-by: Paolo Bonzini --- arch/x86/include/asm/tdx.h | 2 ++ arch/x86/kvm/vmx/tdx.c | 14 ++++++++++++++ arch/x86/kvm/vmx/tdx.h | 1 + arch/x86/virt/vmx/tdx/tdx.c | 6 ++++++ include/linux/misc_cgroup.h | 4 ++++ kernel/cgroup/misc.c | 4 ++++ 6 files changed, 31 insertions(+) diff --git a/arch/x86/include/asm/tdx.h b/arch/x86/include/asm/tdx.h index 1a8c687603aa..2879fc518a32 100644 --- a/arch/x86/include/asm/tdx.h +++ b/arch/x86/include/asm/tdx.h @@ -125,6 +125,7 @@ const char *tdx_dump_mce_info(struct mce *m); const struct tdx_sys_info *tdx_get_sysinfo(void); int tdx_guest_keyid_alloc(void); +u32 tdx_get_nr_guest_keyids(void); void tdx_guest_keyid_free(unsigned int keyid); struct tdx_td { @@ -180,6 +181,7 @@ u64 tdh_phymem_page_wbinvd_tdr(struct tdx_td *td); static inline void tdx_init(void) { } static inline int tdx_cpu_enable(void) { return -ENODEV; } 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; } #endif /* CONFIG_INTEL_TDX_HOST */ diff --git a/arch/x86/kvm/vmx/tdx.c b/arch/x86/kvm/vmx/tdx.c index 2ac925ecccd5..01166cb8f2e6 100644 --- a/arch/x86/kvm/vmx/tdx.c +++ b/arch/x86/kvm/vmx/tdx.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include #include +#include #include #include "capabilities.h" #include "mmu.h" @@ -140,6 +141,9 @@ static inline void tdx_hkid_free(struct kvm_tdx *kvm_tdx) tdx_guest_keyid_free(kvm_tdx->hkid); kvm_tdx->hkid = -1; atomic_dec(&nr_configured_hkid); + misc_cg_uncharge(MISC_CG_RES_TDX, kvm_tdx->misc_cg, 1); + put_misc_cg(kvm_tdx->misc_cg); + kvm_tdx->misc_cg = NULL; } static inline bool is_hkid_assigned(struct kvm_tdx *kvm_tdx) @@ -675,6 +679,10 @@ static int __tdx_td_init(struct kvm *kvm, struct td_params *td_params, if (ret < 0) return ret; kvm_tdx->hkid = ret; + kvm_tdx->misc_cg = get_current_misc_cg(); + ret = misc_cg_try_charge(MISC_CG_RES_TDX, kvm_tdx->misc_cg, 1); + if (ret) + goto free_hkid; ret = -ENOMEM; @@ -1459,6 +1467,11 @@ static int __init __tdx_bringup(void) goto get_sysinfo_err; } + if (misc_cg_set_capacity(MISC_CG_RES_TDX, tdx_get_nr_guest_keyids())) { + r = -EINVAL; + goto get_sysinfo_err; + } + /* * Leave hardware virtualization enabled after TDX is enabled * successfully. TDX CPU hotplug depends on this. @@ -1475,6 +1488,7 @@ tdx_bringup_err: void tdx_cleanup(void) { if (enable_tdx) { + misc_cg_set_capacity(MISC_CG_RES_TDX, 0); __tdx_cleanup(); kvm_disable_virtualization(); } diff --git a/arch/x86/kvm/vmx/tdx.h b/arch/x86/kvm/vmx/tdx.h index 6ec7ac1d91e3..0559126c8f9d 100644 --- a/arch/x86/kvm/vmx/tdx.h +++ b/arch/x86/kvm/vmx/tdx.h @@ -21,6 +21,7 @@ enum kvm_tdx_state { struct kvm_tdx { struct kvm kvm; + struct misc_cg *misc_cg; int hkid; enum kvm_tdx_state state; diff --git a/arch/x86/virt/vmx/tdx/tdx.c b/arch/x86/virt/vmx/tdx/tdx.c index 9f0c482c1a03..3a272e9ff2ca 100644 --- a/arch/x86/virt/vmx/tdx/tdx.c +++ b/arch/x86/virt/vmx/tdx/tdx.c @@ -1476,6 +1476,12 @@ const struct tdx_sys_info *tdx_get_sysinfo(void) } EXPORT_SYMBOL_GPL(tdx_get_sysinfo); +u32 tdx_get_nr_guest_keyids(void) +{ + return tdx_nr_guest_keyids; +} +EXPORT_SYMBOL_GPL(tdx_get_nr_guest_keyids); + int tdx_guest_keyid_alloc(void) { return ida_alloc_range(&tdx_guest_keyid_pool, tdx_guest_keyid_start, diff --git a/include/linux/misc_cgroup.h b/include/linux/misc_cgroup.h index 49eef10c8e59..8c0e4f4d71be 100644 --- a/include/linux/misc_cgroup.h +++ b/include/linux/misc_cgroup.h @@ -17,6 +17,10 @@ enum misc_res_type { MISC_CG_RES_SEV, /** @MISC_CG_RES_SEV_ES: AMD SEV-ES ASIDs resource */ MISC_CG_RES_SEV_ES, +#endif +#ifdef CONFIG_INTEL_TDX_HOST + /* Intel TDX HKIDs resource */ + MISC_CG_RES_TDX, #endif /** @MISC_CG_RES_TYPES: count of enum misc_res_type constants */ MISC_CG_RES_TYPES diff --git a/kernel/cgroup/misc.c b/kernel/cgroup/misc.c index 0e26068995a6..264aad22c967 100644 --- a/kernel/cgroup/misc.c +++ b/kernel/cgroup/misc.c @@ -24,6 +24,10 @@ static const char *const misc_res_name[] = { /* AMD SEV-ES ASIDs resource */ "sev_es", #endif +#ifdef CONFIG_INTEL_TDX_HOST + /* Intel TDX HKIDs resource */ + "tdx", +#endif }; /* Root misc cgroup */ -- 2.51.0 From 385ba3fd8d3d22d907484f9eec27d7906d48a446 Mon Sep 17 00:00:00 2001 From: Isaku Yamahata Date: Tue, 12 Nov 2024 15:36:24 +0800 Subject: [PATCH 16/16] x86/virt/tdx: Add SEAMCALL wrapper tdh_mem_sept_add() to add SEPT pages TDX architecture introduces the concept of private GPA vs shared GPA, depending on the GPA.SHARED bit. The TDX module maintains a Secure EPT (S-EPT or SEPT) tree per TD for private GPA to HPA translation. Wrap the TDH.MEM.SEPT.ADD SEAMCALL with tdh_mem_sept_add() to provide pages to the TDX module for building a TD's SEPT tree. (Refer to these pages as SEPT pages). Callers need to allocate and provide a normal page to tdh_mem_sept_add(), which then passes the page to the TDX module via the SEAMCALL TDH.MEM.SEPT.ADD. The TDX module then installs the page into SEPT tree and encrypts this SEPT page with the TD's guest keyID. The kernel cannot use the SEPT page until after reclaiming it via TDH.MEM.SEPT.REMOVE or TDH.PHYMEM.PAGE.RECLAIM. Before passing the page to the TDX module, tdh_mem_sept_add() performs a CLFLUSH on the page mapped with keyID 0 to ensure that any dirty cache lines don't write back later and clobber TD memory or control structures. Don't worry about the other MK-TME keyIDs because the kernel doesn't use them. The TDX docs specify that this flush is not needed unless the TDX module exposes the CLFLUSH_BEFORE_ALLOC feature bit. Do the CLFLUSH unconditionally for two reasons: make the solution simpler by having a single path that can handle both !CLFLUSH_BEFORE_ALLOC and CLFLUSH_BEFORE_ALLOC cases. Avoid wading into any correctness uncertainty by going with a conservative solution to start. Callers should specify "GPA" and "level" for the TDX module to install the SEPT page at the specified position in the SEPT. Do not include the root page level in "level" since TDH.MEM.SEPT.ADD can only add non-root pages to the SEPT. Ensure "level" is between 1 and 3 for a 4-level SEPT or between 1 and 4 for a 5-level SEPT. Call tdh_mem_sept_add() during the TD's build time or during the TD's runtime. Check for errors from the function return value and retrieve extended error info from the function output parameters. The TDX module has many internal locks. To avoid staying in SEAM mode for too long, SEAMCALLs returns a BUSY error code to the kernel instead of spinning on the locks. Depending on the specific SEAMCALL, the caller may need to handle this error in specific ways (e.g., retry). Therefore, return the SEAMCALL error code directly to the caller. Don't attempt to handle it in the core kernel. TDH.MEM.SEPT.ADD effectively manages two internal resources of the TDX module: it installs page table pages in the SEPT tree and also updates the TDX module's page metadata (PAMT). Don't add a wrapper for the matching SEAMCALL for removing a SEPT page (TDH.MEM.SEPT.REMOVE) because KVM, as the only in-kernel user, will only tear down the SEPT tree when the TD is being torn down. When this happens it can just do other operations that reclaim the SEPT pages for the host kernels to use, update the PAMT and let the SEPT get trashed. [Kai: Switched from generic seamcall export] [Yan: Re-wrote the changelog] Co-developed-by: Sean Christopherson Signed-off-by: Sean Christopherson Signed-off-by: Isaku Yamahata Signed-off-by: Kai Huang Signed-off-by: Rick Edgecombe Signed-off-by: Yan Zhao Message-ID: <20241112073624.22114-1-yan.y.zhao@intel.com> Acked-by: Dave Hansen Signed-off-by: Paolo Bonzini --- arch/x86/include/asm/tdx.h | 7 ++++++- arch/x86/virt/vmx/tdx/tdx.c | 19 +++++++++++++++++++ arch/x86/virt/vmx/tdx/tdx.h | 1 + 3 files changed, 26 insertions(+), 1 deletion(-) diff --git a/arch/x86/include/asm/tdx.h b/arch/x86/include/asm/tdx.h index 2879fc518a32..c3be3742f347 100644 --- a/arch/x86/include/asm/tdx.h +++ b/arch/x86/include/asm/tdx.h @@ -148,7 +148,6 @@ struct tdx_vp { struct page **tdcx_pages; }; - static inline u64 mk_keyed_paddr(u16 hkid, struct page *page) { u64 ret; @@ -158,10 +157,16 @@ static inline u64 mk_keyed_paddr(u16 hkid, struct page *page) ret |= (u64)hkid << boot_cpu_data.x86_phys_bits; return ret; +} +static inline int pg_level_to_tdx_sept_level(enum pg_level level) +{ + WARN_ON_ONCE(level == PG_LEVEL_NONE); + return level - 1; } u64 tdh_mng_addcx(struct tdx_td *td, struct page *tdcs_page); +u64 tdh_mem_sept_add(struct tdx_td *td, u64 gpa, int level, struct page *page, u64 *ext_err1, u64 *ext_err2); u64 tdh_vp_addcx(struct tdx_vp *vp, struct page *tdcx_page); u64 tdh_mng_key_config(struct tdx_td *td); u64 tdh_mng_create(struct tdx_td *td, u16 hkid); diff --git a/arch/x86/virt/vmx/tdx/tdx.c b/arch/x86/virt/vmx/tdx/tdx.c index 3a272e9ff2ca..506a75fbac0b 100644 --- a/arch/x86/virt/vmx/tdx/tdx.c +++ b/arch/x86/virt/vmx/tdx/tdx.c @@ -1529,6 +1529,25 @@ u64 tdh_mng_addcx(struct tdx_td *td, struct page *tdcs_page) } EXPORT_SYMBOL_GPL(tdh_mng_addcx); +u64 tdh_mem_sept_add(struct tdx_td *td, u64 gpa, int level, struct page *page, u64 *ext_err1, u64 *ext_err2) +{ + struct tdx_module_args args = { + .rcx = gpa | level, + .rdx = tdx_tdr_pa(td), + .r8 = page_to_phys(page), + }; + u64 ret; + + tdx_clflush_page(page); + ret = seamcall_ret(TDH_MEM_SEPT_ADD, &args); + + *ext_err1 = args.rcx; + *ext_err2 = args.rdx; + + return ret; +} +EXPORT_SYMBOL_GPL(tdh_mem_sept_add); + u64 tdh_vp_addcx(struct tdx_vp *vp, struct page *tdcx_page) { struct tdx_module_args args = { diff --git a/arch/x86/virt/vmx/tdx/tdx.h b/arch/x86/virt/vmx/tdx/tdx.h index da384387d4eb..f3e37df4c63a 100644 --- a/arch/x86/virt/vmx/tdx/tdx.h +++ b/arch/x86/virt/vmx/tdx/tdx.h @@ -15,6 +15,7 @@ * TDX module SEAMCALL leaf functions */ #define TDH_MNG_ADDCX 1 +#define TDH_MEM_SEPT_ADD 3 #define TDH_VP_ADDCX 4 #define TDH_MNG_KEY_CONFIG 8 #define TDH_MNG_CREATE 9 -- 2.51.0