Merge branch 'kvm-tdx-finish-initial' into HEAD

This patch ties the remaining loose ends and finally enables TDX guests to
run inside KVM.  It implements handling of EPT violation/misconfig and of
several TDVMCALL leaves that are handled in the kernel (CPUID, HLT, RDMSR/WRMSR,
GetTdVmCallInfo); it also adds a bunch of wrappers in vmx/main.c to
ignore operations not supported by TDX guests(*)

Finally, it introduces documentation for the new APIs that have been
added along the way.

(*) access to CPU state, VMX preemption timer, accesses to TSC offset or
    multiplier, LMCE enable/disable, hypercall patching.

Author: bonzini

Documentation/virt/kvm/api.rst

@@ -1407,6 +1407,9 @@ the memory region are automatically reflected into the guest.  For example, an
 mmap() that affects the region will be made visible immediately.  Another
 example is madvise(MADV_DROP).
 
+For TDX guest, deleting/moving memory region loses guest memory contents.
+Read only region isn't supported.  Only as-id 0 is supported.
+
 Note: On arm64, a write generated by the page-table walker (to update
 the Access and Dirty flags, for example) never results in a
 KVM_EXIT_MMIO exit when the slot has the KVM_MEM_READONLY flag. This
@@ -4764,17 +4767,19 @@ H_GET_CPU_CHARACTERISTICS hypercall.
 
 :Capability: basic
 :Architectures: x86
-:Type: vm
+:Type: vm ioctl, vcpu ioctl
 :Parameters: an opaque platform specific structure (in/out)
 :Returns: 0 on success; -1 on error
 
 If the platform supports creating encrypted VMs then this ioctl can be used
 for issuing platform-specific memory encryption commands to manage those
 encrypted VMs.
 
-Currently, this ioctl is used for issuing Secure Encrypted Virtualization
-(SEV) commands on AMD Processors. The SEV commands are defined in
-Documentation/virt/kvm/x86/amd-memory-encryption.rst.
+Currently, this ioctl is used for issuing both Secure Encrypted Virtualization
+(SEV) commands on AMD Processors and Trusted Domain Extensions (TDX) commands
+on Intel Processors.  The detailed commands are defined in
+Documentation/virt/kvm/x86/amd-memory-encryption.rst and
+Documentation/virt/kvm/x86/intel-tdx.rst.
 
 4.111 KVM_MEMORY_ENCRYPT_REG_REGION
 -----------------------------------
@@ -8160,6 +8165,28 @@ KVM_X86_QUIRK_STUFF_FEATURE_MSRS    By default, at vCPU creation, KVM sets the
                                     and 0x489), as KVM does now allow them to
                                     be set by userspace (KVM sets them based on
                                     guest CPUID, for safety purposes).
+
+KVM_X86_QUIRK_IGNORE_GUEST_PAT      By default, on Intel platforms, KVM ignores
+                                    guest PAT and forces the effective memory
+                                    type to WB in EPT.  The quirk is not available
+                                    on Intel platforms which are incapable of
+                                    safely honoring guest PAT (i.e., without CPU
+                                    self-snoop, KVM always ignores guest PAT and
+                                    forces effective memory type to WB).  It is
+                                    also ignored on AMD platforms or, on Intel,
+                                    when a VM has non-coherent DMA devices
+                                    assigned; KVM always honors guest PAT in
+                                    such case. The quirk is needed to avoid
+                                    slowdowns on certain Intel Xeon platforms
+                                    (e.g. ICX, SPR) where self-snoop feature is
+                                    supported but UC is slow enough to cause
+                                    issues with some older guests that use
+                                    UC instead of WC to map the video RAM.
+                                    Userspace can disable the quirk to honor
+                                    guest PAT if it knows that there is no such
+                                    guest software, for example if it does not
+                                    expose a bochs graphics device (which is
+                                    known to have had a buggy driver).
 =================================== ============================================
 
 7.32 KVM_CAP_MAX_VCPU_ID

Documentation/virt/kvm/x86/index.rst

@@ -11,6 +11,7 @@ KVM for x86 systems
    cpuid
    errata
    hypercalls
+   intel-tdx
    mmu
    msr
    nested-vmx

Documentation/virt/kvm/x86/intel-tdx.rst

@@ -0,0 +1,255 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+===================================
+Intel Trust Domain Extensions (TDX)
+===================================
+
+Overview
+========
+Intel's Trust Domain Extensions (TDX) protect confidential guest VMs from the
+host and physical attacks.  A CPU-attested software module called 'the TDX
+module' runs inside a new CPU isolated range to provide the functionalities to
+manage and run protected VMs, a.k.a, TDX guests or TDs.
+
+Please refer to [1] for the whitepaper, specifications and other resources.
+
+This documentation describes TDX-specific KVM ABIs.  The TDX module needs to be
+initialized before it can be used by KVM to run any TDX guests.  The host
+core-kernel provides the support of initializing the TDX module, which is
+described in the Documentation/arch/x86/tdx.rst.
+
+API description
+===============
+
+KVM_MEMORY_ENCRYPT_OP
+---------------------
+:Type: vm ioctl, vcpu ioctl
+
+For TDX operations, KVM_MEMORY_ENCRYPT_OP is re-purposed to be generic
+ioctl with TDX specific sub-ioctl() commands.
+
+::
+
+  /* Trust Domain Extensions sub-ioctl() commands. */
+  enum kvm_tdx_cmd_id {
+          KVM_TDX_CAPABILITIES = 0,
+          KVM_TDX_INIT_VM,
+          KVM_TDX_INIT_VCPU,
+          KVM_TDX_INIT_MEM_REGION,
+          KVM_TDX_FINALIZE_VM,
+          KVM_TDX_GET_CPUID,
+
+          KVM_TDX_CMD_NR_MAX,
+  };
+
+  struct kvm_tdx_cmd {
+        /* enum kvm_tdx_cmd_id */
+        __u32 id;
+        /* flags for sub-command. 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;
+  };
+
+KVM_TDX_CAPABILITIES
+--------------------
+:Type: vm ioctl
+:Returns: 0 on success, <0 on error
+
+Return the TDX capabilities that current KVM supports with the specific TDX
+module loaded in the system.  It reports what features/capabilities are allowed
+to be configured to the TDX guest.
+
+- id: KVM_TDX_CAPABILITIES
+- flags: must be 0
+- data: pointer to struct kvm_tdx_capabilities
+- hw_error: must be 0
+
+::
+
+  struct kvm_tdx_capabilities {
+        __u64 supported_attrs;
+        __u64 supported_xfam;
+        __u64 reserved[254];
+
+        /* Configurable CPUID bits for userspace */
+        struct kvm_cpuid2 cpuid;
+  };
+
+
+KVM_TDX_INIT_VM
+---------------
+:Type: vm ioctl
+:Returns: 0 on success, <0 on error
+
+Perform TDX specific VM initialization.  This needs to be called after
+KVM_CREATE_VM and before creating any VCPUs.
+
+- id: KVM_TDX_INIT_VM
+- flags: must be 0
+- data: pointer to struct kvm_tdx_init_vm
+- hw_error: must be 0
+
+::
+
+  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;
+  };
+
+
+KVM_TDX_INIT_VCPU
+-----------------
+:Type: vcpu ioctl
+:Returns: 0 on success, <0 on error
+
+Perform TDX specific VCPU initialization.
+
+- id: KVM_TDX_INIT_VCPU
+- flags: must be 0
+- data: initial value of the guest TD VCPU RCX
+- hw_error: must be 0
+
+KVM_TDX_INIT_MEM_REGION
+-----------------------
+:Type: vcpu ioctl
+:Returns: 0 on success, <0 on error
+
+Initialize @nr_pages TDX guest private memory starting from @gpa with userspace
+provided data from @source_addr.
+
+Note, before calling this sub command, memory attribute of the range
+[gpa, gpa + nr_pages] needs to be private.  Userspace can use
+KVM_SET_MEMORY_ATTRIBUTES to set the attribute.
+
+If KVM_TDX_MEASURE_MEMORY_REGION flag is specified, it also extends measurement.
+
+- id: KVM_TDX_INIT_MEM_REGION
+- flags: currently only KVM_TDX_MEASURE_MEMORY_REGION is defined
+- data: pointer to struct kvm_tdx_init_mem_region
+- hw_error: must be 0
+
+::
+
+  #define KVM_TDX_MEASURE_MEMORY_REGION   (1UL << 0)
+
+  struct kvm_tdx_init_mem_region {
+          __u64 source_addr;
+          __u64 gpa;
+          __u64 nr_pages;
+  };
+
+
+KVM_TDX_FINALIZE_VM
+-------------------
+:Type: vm ioctl
+:Returns: 0 on success, <0 on error
+
+Complete measurement of the initial TD contents and mark it ready to run.
+
+- id: KVM_TDX_FINALIZE_VM
+- flags: must be 0
+- data: must be 0
+- hw_error: must be 0
+
+
+KVM_TDX_GET_CPUID
+-----------------
+:Type: vcpu ioctl
+:Returns: 0 on success, <0 on error
+
+Get the CPUID values that the TDX module virtualizes for the TD guest.
+When it returns -E2BIG, the user space should allocate a larger buffer and
+retry. The minimum buffer size is updated in the nent field of the
+struct kvm_cpuid2.
+
+- id: KVM_TDX_GET_CPUID
+- flags: must be 0
+- data: pointer to struct kvm_cpuid2 (in/out)
+- hw_error: must be 0 (out)
+
+::
+
+  struct kvm_cpuid2 {
+	  __u32 nent;
+	  __u32 padding;
+	  struct kvm_cpuid_entry2 entries[0];
+  };
+
+  struct kvm_cpuid_entry2 {
+	  __u32 function;
+	  __u32 index;
+	  __u32 flags;
+	  __u32 eax;
+	  __u32 ebx;
+	  __u32 ecx;
+	  __u32 edx;
+	  __u32 padding[3];
+  };
+
+KVM TDX creation flow
+=====================
+In addition to the standard KVM flow, new TDX ioctls need to be called.  The
+control flow is as follows:
+
+#. Check system wide capability
+
+   * KVM_CAP_VM_TYPES: Check if VM type is supported and if KVM_X86_TDX_VM
+     is supported.
+
+#. Create VM
+
+   * KVM_CREATE_VM
+   * KVM_TDX_CAPABILITIES: Query TDX capabilities for creating TDX guests.
+   * KVM_CHECK_EXTENSION(KVM_CAP_MAX_VCPUS): Query maximum VCPUs the TD can
+     support at VM level (TDX has its own limitation on this).
+   * KVM_SET_TSC_KHZ: Configure TD's TSC frequency if a different TSC frequency
+     than host is desired.  This is Optional.
+   * KVM_TDX_INIT_VM: Pass TDX specific VM parameters.
+
+#. Create VCPU
+
+   * KVM_CREATE_VCPU
+   * KVM_TDX_INIT_VCPU: Pass TDX specific VCPU parameters.
+   * KVM_SET_CPUID2: Configure TD's CPUIDs.
+   * KVM_SET_MSRS: Configure TD's MSRs.
+
+#. Initialize initial guest memory
+
+   * Prepare content of initial guest memory.
+   * KVM_TDX_INIT_MEM_REGION: Add initial guest memory.
+   * KVM_TDX_FINALIZE_VM: Finalize the measurement of the TDX guest.
+
+#. Run VCPU
+
+References
+==========
+
+.. [1] https://www.intel.com/content/www/us/en/developer/tools/trust-domain-extensions/documentation.html

arch/x86/include/asm/kvm_host.h

@@ -2420,7 +2420,12 @@ int memslot_rmap_alloc(struct kvm_memory_slot *slot, unsigned long npages);
 	 KVM_X86_QUIRK_FIX_HYPERCALL_INSN |	\
 	 KVM_X86_QUIRK_MWAIT_NEVER_UD_FAULTS |	\
 	 KVM_X86_QUIRK_SLOT_ZAP_ALL |		\
-	 KVM_X86_QUIRK_STUFF_FEATURE_MSRS)
+	 KVM_X86_QUIRK_STUFF_FEATURE_MSRS |	\
+	 KVM_X86_QUIRK_IGNORE_GUEST_PAT)
+
+#define KVM_X86_CONDITIONAL_QUIRKS		\
+	(KVM_X86_QUIRK_CD_NW_CLEARED |		\
+	 KVM_X86_QUIRK_IGNORE_GUEST_PAT)
 
 /*
  * KVM previously used a u32 field in kvm_run to indicate the hypercall was

arch/x86/include/asm/shared/tdx.h

@@ -67,6 +67,7 @@
 #define TD_CTLS_LOCK			BIT_ULL(TD_CTLS_LOCK_BIT)
 
 /* TDX hypercall Leaf IDs */
+#define TDVMCALL_GET_TD_VM_CALL_INFO	0x10000
 #define TDVMCALL_MAP_GPA		0x10001
 #define TDVMCALL_GET_QUOTE		0x10002
 #define TDVMCALL_REPORT_FATAL_ERROR	0x10003

arch/x86/include/asm/vmx.h

@@ -585,12 +585,14 @@ enum vm_entry_failure_code {
 #define EPT_VIOLATION_ACC_WRITE_BIT	1
 #define EPT_VIOLATION_ACC_INSTR_BIT	2
 #define EPT_VIOLATION_RWX_SHIFT		3
+#define EPT_VIOLATION_EXEC_R3_LIN_BIT	6
 #define EPT_VIOLATION_GVA_IS_VALID_BIT	7
 #define EPT_VIOLATION_GVA_TRANSLATED_BIT 8
 #define EPT_VIOLATION_ACC_READ		(1 << EPT_VIOLATION_ACC_READ_BIT)
 #define EPT_VIOLATION_ACC_WRITE		(1 << EPT_VIOLATION_ACC_WRITE_BIT)
 #define EPT_VIOLATION_ACC_INSTR		(1 << EPT_VIOLATION_ACC_INSTR_BIT)
 #define EPT_VIOLATION_RWX_MASK		(VMX_EPT_RWX_MASK << EPT_VIOLATION_RWX_SHIFT)
+#define EPT_VIOLATION_EXEC_FOR_RING3_LIN (1 << EPT_VIOLATION_EXEC_R3_LIN_BIT)
 #define EPT_VIOLATION_GVA_IS_VALID	(1 << EPT_VIOLATION_GVA_IS_VALID_BIT)
 #define EPT_VIOLATION_GVA_TRANSLATED	(1 << EPT_VIOLATION_GVA_TRANSLATED_BIT)
 

arch/x86/include/uapi/asm/kvm.h

@@ -441,6 +441,7 @@ struct kvm_sync_regs {
 #define KVM_X86_QUIRK_MWAIT_NEVER_UD_FAULTS	(1 << 6)
 #define KVM_X86_QUIRK_SLOT_ZAP_ALL		(1 << 7)
 #define KVM_X86_QUIRK_STUFF_FEATURE_MSRS	(1 << 8)
+#define KVM_X86_QUIRK_IGNORE_GUEST_PAT		(1 << 9)
 
 #define KVM_STATE_NESTED_FORMAT_VMX	0
 #define KVM_STATE_NESTED_FORMAT_SVM	1

arch/x86/kvm/mmu.h

@@ -232,7 +232,7 @@ static inline u8 permission_fault(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
 	return -(u32)fault & errcode;
 }
 
-bool kvm_mmu_may_ignore_guest_pat(void);
+bool kvm_mmu_may_ignore_guest_pat(struct kvm *kvm);
 
 int kvm_mmu_post_init_vm(struct kvm *kvm);
 void kvm_mmu_pre_destroy_vm(struct kvm *kvm);