Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull kvm updates from Paolo Bonzini:
 "As far as x86 goes this pull request "only" includes TDX host support.

  Quotes are appropriate because (at 6k lines and 100+ commits) it is
  much bigger than the rest, which will come later this week and
  consists mostly of bugfixes and selftests. s390 changes will also come
  in the second batch.

  ARM:

   - Add large stage-2 mapping (THP) support for non-protected guests
     when pKVM is enabled, clawing back some performance.

   - Enable nested virtualisation support on systems that support it,
     though it is disabled by default.

   - Add UBSAN support to the standalone EL2 object used in nVHE/hVHE
     and protected modes.

   - Large rework of the way KVM tracks architecture features and links
     them with the effects of control bits. While this has no functional
     impact, it ensures correctness of emulation (the data is
     automatically extracted from the published JSON files), and helps
     dealing with the evolution of the architecture.

   - Significant changes to the way pKVM tracks ownership of pages,
     avoiding page table walks by storing the state in the hypervisor's
     vmemmap. This in turn enables the THP support described above.

   - New selftest checking the pKVM ownership transition rules

   - Fixes for FEAT_MTE_ASYNC being accidentally advertised to guests
     even if the host didn't have it.

   - Fixes for the address translation emulation, which happened to be
     rather buggy in some specific contexts.

   - Fixes for the PMU emulation in NV contexts, decoupling PMCR_EL0.N
     from the number of counters exposed to a guest and addressing a
     number of issues in the process.

   - Add a new selftest for the SVE host state being corrupted by a
     guest.

   - Keep HCR_EL2.xMO set at all times for systems running with the
     kernel at EL2, ensuring that the window for interrupts is slightly
     bigger, and avoiding a pretty bad erratum on the AmpereOne HW.

   - Add workaround for AmpereOne's erratum AC04_CPU_23, which suffers
     from a pretty bad case of TLB corruption unless accesses to HCR_EL2
     are heavily synchronised.

   - Add a per-VM, per-ITS debugfs entry to dump the state of the ITS
     tables in a human-friendly fashion.

   - and the usual random cleanups.

  LoongArch:

   - Don't flush tlb if the host supports hardware page table walks.

   - Add KVM selftests support.

  RISC-V:

   - Add vector registers to get-reg-list selftest

   - VCPU reset related improvements

   - Remove scounteren initialization from VCPU reset

   - Support VCPU reset from userspace using set_mpstate() ioctl

  x86:

   - Initial support for TDX in KVM.

     This finally makes it possible to use the TDX module to run
     confidential guests on Intel processors. This is quite a large
     series, including support for private page tables (managed by the
     TDX module and mirrored in KVM for efficiency), forwarding some
     TDVMCALLs to userspace, and handling several special VM exits from
     the TDX module.

     This has been in the works for literally years and it's not really
     possible to describe everything here, so I'll defer to the various
     merge commits up to and including commit 7bcf7246c42a ('Merge
     branch 'kvm-tdx-finish-initial' into HEAD')"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (248 commits)
  x86/tdx: mark tdh_vp_enter() as __flatten
  Documentation: virt/kvm: remove unreferenced footnote
  RISC-V: KVM: lock the correct mp_state during reset
  KVM: arm64: Fix documentation for vgic_its_iter_next()
  KVM: arm64: np-guest CMOs with PMD_SIZE fixmap
  KVM: arm64: Stage-2 huge mappings for np-guests
  KVM: arm64: Add a range to pkvm_mappings
  KVM: arm64: Convert pkvm_mappings to interval tree
  KVM: arm64: Add a range to __pkvm_host_test_clear_young_guest()
  KVM: arm64: Add a range to __pkvm_host_wrprotect_guest()
  KVM: arm64: Add a range to __pkvm_host_unshare_guest()
  KVM: arm64: Add a range to __pkvm_host_share_guest()
  KVM: arm64: Introduce for_each_hyp_page
  KVM: arm64: Handle huge mappings for np-guest CMOs
  KVM: arm64: nv: Release faulted-in VNCR page from mmu_lock critical section
  KVM: arm64: nv: Handle TLBI S1E2 for VNCR invalidation with mmu_lock held
  KVM: arm64: nv: Hold mmu_lock when invalidating VNCR SW-TLB before translating
  RISC-V: KVM: add KVM_CAP_RISCV_MP_STATE_RESET
  RISC-V: KVM: Remove scounteren initialization
  KVM: RISC-V: remove unnecessary SBI reset state
  ...

4 files changed, 16 insertions, 13 deletions

diff --git a/arch/riscv/include/asm/kvm_aia.h b/arch/riscv/include/asm/kvm_aia.h
index 1f37b600ca47..3b643b9efc07 100644
--- a/arch/riscv/include/asm/kvm_aia.h
+++ b/arch/riscv/include/asm/kvm_aia.h
@@ -63,9 +63,6 @@ struct kvm_vcpu_aia {
 	/* CPU AIA CSR context of Guest VCPU */
 	struct kvm_vcpu_aia_csr guest_csr;
 
-	/* CPU AIA CSR context upon Guest VCPU reset */
-	struct kvm_vcpu_aia_csr guest_reset_csr;
-
 	/* Guest physical address of IMSIC for this VCPU */
 	gpa_t		imsic_addr;
 
diff --git a/arch/riscv/include/asm/kvm_host.h b/arch/riscv/include/asm/kvm_host.h
index 0e9c2fab6378..85cfebc32e4c 100644
--- a/arch/riscv/include/asm/kvm_host.h
+++ b/arch/riscv/include/asm/kvm_host.h
@@ -119,6 +119,9 @@ struct kvm_arch {
 
 	/* AIA Guest/VM context */
 	struct kvm_aia aia;
+
+	/* KVM_CAP_RISCV_MP_STATE_RESET */
+	bool mp_state_reset;
 };
 
 struct kvm_cpu_trap {
@@ -193,6 +196,12 @@ struct kvm_vcpu_smstateen_csr {
 	unsigned long sstateen0;
 };
 
+struct kvm_vcpu_reset_state {
+	spinlock_t lock;
+	unsigned long pc;
+	unsigned long a1;
+};
+
 struct kvm_vcpu_arch {
 	/* VCPU ran at least once */
 	bool ran_atleast_once;
@@ -227,12 +236,8 @@ struct kvm_vcpu_arch {
 	/* CPU Smstateen CSR context of Guest VCPU */
 	struct kvm_vcpu_smstateen_csr smstateen_csr;
 
-	/* CPU context upon Guest VCPU reset */
-	struct kvm_cpu_context guest_reset_context;
-	spinlock_t reset_cntx_lock;
-
-	/* CPU CSR context upon Guest VCPU reset */
-	struct kvm_vcpu_csr guest_reset_csr;
+	/* CPU reset state of Guest VCPU */
+	struct kvm_vcpu_reset_state reset_state;
 
 	/*
 	 * VCPU interrupts
diff --git a/arch/riscv/include/asm/kvm_vcpu_sbi.h b/arch/riscv/include/asm/kvm_vcpu_sbi.h
index 4ed6203cdd30..439ab2b3534f 100644
--- a/arch/riscv/include/asm/kvm_vcpu_sbi.h
+++ b/arch/riscv/include/asm/kvm_vcpu_sbi.h
@@ -55,6 +55,9 @@ void kvm_riscv_vcpu_sbi_forward(struct kvm_vcpu *vcpu, struct kvm_run *run);
 void kvm_riscv_vcpu_sbi_system_reset(struct kvm_vcpu *vcpu,
 				     struct kvm_run *run,
 				     u32 type, u64 flags);
+void kvm_riscv_vcpu_sbi_request_reset(struct kvm_vcpu *vcpu,
+				      unsigned long pc, unsigned long a1);
+void kvm_riscv_vcpu_sbi_load_reset_state(struct kvm_vcpu *vcpu);
 int kvm_riscv_vcpu_sbi_return(struct kvm_vcpu *vcpu, struct kvm_run *run);
 int kvm_riscv_vcpu_set_reg_sbi_ext(struct kvm_vcpu *vcpu,
 				   const struct kvm_one_reg *reg);
diff --git a/arch/riscv/include/asm/kvm_vcpu_vector.h b/arch/riscv/include/asm/kvm_vcpu_vector.h
index 27f5bccdd8b0..57a798a4cb0d 100644
--- a/arch/riscv/include/asm/kvm_vcpu_vector.h
+++ b/arch/riscv/include/asm/kvm_vcpu_vector.h
@@ -33,8 +33,7 @@ void kvm_riscv_vcpu_guest_vector_restore(struct kvm_cpu_context *cntx,
 					 unsigned long *isa);
 void kvm_riscv_vcpu_host_vector_save(struct kvm_cpu_context *cntx);
 void kvm_riscv_vcpu_host_vector_restore(struct kvm_cpu_context *cntx);
-int kvm_riscv_vcpu_alloc_vector_context(struct kvm_vcpu *vcpu,
-					struct kvm_cpu_context *cntx);
+int kvm_riscv_vcpu_alloc_vector_context(struct kvm_vcpu *vcpu);
 void kvm_riscv_vcpu_free_vector_context(struct kvm_vcpu *vcpu);
 #else
 
@@ -62,8 +61,7 @@ static inline void kvm_riscv_vcpu_host_vector_restore(struct kvm_cpu_context *cn
 {
 }
 
-static inline int kvm_riscv_vcpu_alloc_vector_context(struct kvm_vcpu *vcpu,
-						      struct kvm_cpu_context *cntx)
+static inline int kvm_riscv_vcpu_alloc_vector_context(struct kvm_vcpu *vcpu)
 {
 	return 0;
 }