Merge branch 'kvm-tdx-initial' into HEAD

This large commit contains the initial support for TDX in KVM.  All x86
parts enable the host-side hypercalls that KVM uses to talk to the TDX
module, a software component that runs in a special CPU mode called SEAM
(Secure Arbitration Mode).

The series is in turn split into multiple sub-series, each with a separate
merge commit:

- Initialization: basic setup for using the TDX module from KVM, plus
  ioctls to create TDX VMs and vCPUs.

- MMU: in TDX, private and shared halves of the address space are mapped by
  different EPT roots, and the private half is managed by the TDX module.
  Using the support that was added to the generic MMU code in 6.14,
  add support for TDX's secure page tables to the Intel side of KVM.
  Generic KVM code takes care of maintaining a mirror of the secure page
  tables so that they can be queried efficiently, and ensuring that changes
  are applied to both the mirror and the secure EPT.

- vCPU enter/exit: implement the callbacks that handle the entry of a TDX
  vCPU (via the SEAMCALL TDH.VP.ENTER) and the corresponding save/restore
  of host state.

- Userspace exits: introduce support for guest TDVMCALLs that KVM forwards to
  userspace.  These correspond to the usual KVM_EXIT_* "heavyweight vmexits"
  but are triggered through a different mechanism, similar to VMGEXIT for
  SEV-ES and SEV-SNP.

- Interrupt handling: support for virtual interrupt injection as well as
  handling VM-Exits that are caused by vectored events.  Exclusive to
  TDX are machine-check SMIs, which the kernel already knows how to
  handle through the kernel machine check handler (commit 7911f145de5f,
  "x86/mce: Implement recovery for errors in TDX/SEAM non-root mode")

- Loose ends: handling of the remaining exits from the TDX module, including
  EPT violation/misconfig and several TDVMCALL leaves that are handled in
  the kernel (CPUID, HLT, RDMSR/WRMSR, GetTdVmCallInfo); plus returning
  an error or ignoring operations that are not supported by TDX guests

Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

3 files changed, 20 insertions, 5 deletions

diff --git a/include/linux/kvm_dirty_ring.h b/include/linux/kvm_dirty_ring.h
index 4862c98d80d3..da4d9b5f58f1 100644
--- a/include/linux/kvm_dirty_ring.h
+++ b/include/linux/kvm_dirty_ring.h
@@ -32,7 +32,7 @@ struct kvm_dirty_ring {
  * If CONFIG_HAVE_HVM_DIRTY_RING not defined, kvm_dirty_ring.o should
  * not be included as well, so define these nop functions for the arch.
  */
-static inline u32 kvm_dirty_ring_get_rsvd_entries(void)
+static inline u32 kvm_dirty_ring_get_rsvd_entries(struct kvm *kvm)
 {
 	return 0;
 }
@@ -42,7 +42,7 @@ static inline bool kvm_use_dirty_bitmap(struct kvm *kvm)
 	return true;
 }
 
-static inline int kvm_dirty_ring_alloc(struct kvm_dirty_ring *ring,
+static inline int kvm_dirty_ring_alloc(struct kvm *kvm, struct kvm_dirty_ring *ring,
 				       int index, u32 size)
 {
 	return 0;
@@ -71,11 +71,12 @@ static inline void kvm_dirty_ring_free(struct kvm_dirty_ring *ring)
 
 #else /* CONFIG_HAVE_KVM_DIRTY_RING */
 
-int kvm_cpu_dirty_log_size(void);
+int kvm_cpu_dirty_log_size(struct kvm *kvm);
 bool kvm_use_dirty_bitmap(struct kvm *kvm);
 bool kvm_arch_allow_write_without_running_vcpu(struct kvm *kvm);
-u32 kvm_dirty_ring_get_rsvd_entries(void);
-int kvm_dirty_ring_alloc(struct kvm_dirty_ring *ring, int index, u32 size);
+u32 kvm_dirty_ring_get_rsvd_entries(struct kvm *kvm);
+int kvm_dirty_ring_alloc(struct kvm *kvm, struct kvm_dirty_ring *ring,
+			 int index, u32 size);
 
 /*
  * called with kvm->slots_lock held, returns the number of
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 291d49b9bf05..1dedc421b3e3 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -1610,6 +1610,7 @@ void kvm_arch_disable_virtualization(void);
 int kvm_arch_enable_virtualization_cpu(void);
 void kvm_arch_disable_virtualization_cpu(void);
 #endif
+bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu);
 int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu);
 bool kvm_arch_vcpu_in_kernel(struct kvm_vcpu *vcpu);
 int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu);
@@ -2284,6 +2285,7 @@ static inline bool kvm_check_request(int req, struct kvm_vcpu *vcpu)
 }
 
 #ifdef CONFIG_KVM_GENERIC_HARDWARE_ENABLING
+extern bool enable_virt_at_load;
 extern bool kvm_rebooting;
 #endif
 
@@ -2571,4 +2573,12 @@ long kvm_arch_vcpu_pre_fault_memory(struct kvm_vcpu *vcpu,
 				    struct kvm_pre_fault_memory *range);
 #endif
 
+#ifdef CONFIG_KVM_GENERIC_HARDWARE_ENABLING
+int kvm_enable_virtualization(void);
+void kvm_disable_virtualization(void);
+#else
+static inline int kvm_enable_virtualization(void) { return 0; }
+static inline void kvm_disable_virtualization(void) { }
+#endif
+
 #endif
diff --git a/include/linux/misc_cgroup.h b/include/linux/misc_cgroup.h
index 4bf261d41a6d..71cf5bfc6349 100644
--- a/include/linux/misc_cgroup.h
+++ b/include/linux/misc_cgroup.h
@@ -18,6 +18,10 @@ enum misc_res_type {
 	/** @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
 };