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

Pull kvm updates from Paolo Bonzini:
 "ARM:
   - Proper emulation of the OSLock feature of the debug architecture

   - Scalibility improvements for the MMU lock when dirty logging is on

   - New VMID allocator, which will eventually help with SVA in VMs

   - Better support for PMUs in heterogenous systems

   - PSCI 1.1 support, enabling support for SYSTEM_RESET2

   - Implement CONFIG_DEBUG_LIST at EL2

   - Make CONFIG_ARM64_ERRATUM_2077057 default y

   - Reduce the overhead of VM exit when no interrupt is pending

   - Remove traces of 32bit ARM host support from the documentation

   - Updated vgic selftests

   - Various cleanups, doc updates and spelling fixes

  RISC-V:
   - Prevent KVM_COMPAT from being selected

   - Optimize __kvm_riscv_switch_to() implementation

   - RISC-V SBI v0.3 support

  s390:
   - memop selftest

   - fix SCK locking

   - adapter interruptions virtualization for secure guests

   - add Claudio Imbrenda as maintainer

   - first step to do proper storage key checking

  x86:
   - Continue switching kvm_x86_ops to static_call(); introduce
     static_call_cond() and __static_call_ret0 when applicable.

   - Cleanup unused arguments in several functions

   - Synthesize AMD 0x80000021 leaf

   - Fixes and optimization for Hyper-V sparse-bank hypercalls

   - Implement Hyper-V's enlightened MSR bitmap for nested SVM

   - Remove MMU auditing

   - Eager splitting of page tables (new aka "TDP" MMU only) when dirty
     page tracking is enabled

   - Cleanup the implementation of the guest PGD cache

   - Preparation for the implementation of Intel IPI virtualization

   - Fix some segment descriptor checks in the emulator

   - Allow AMD AVIC support on systems with physical APIC ID above 255

   - Better API to disable virtualization quirks

   - Fixes and optimizations for the zapping of page tables:

      - Zap roots in two passes, avoiding RCU read-side critical
        sections that last too long for very large guests backed by 4
        KiB SPTEs.

      - Zap invalid and defunct roots asynchronously via
        concurrency-managed work queue.

      - Allowing yielding when zapping TDP MMU roots in response to the
        root's last reference being put.

      - Batch more TLB flushes with an RCU trick. Whoever frees the
        paging structure now holds RCU as a proxy for all vCPUs running
        in the guest, i.e. to prolongs the grace period on their behalf.
        It then kicks the the vCPUs out of guest mode before doing
        rcu_read_unlock().

  Generic:
   - Introduce __vcalloc and use it for very large allocations that need
     memcg accounting"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (246 commits)
  KVM: use kvcalloc for array allocations
  KVM: x86: Introduce KVM_CAP_DISABLE_QUIRKS2
  kvm: x86: Require const tsc for RT
  KVM: x86: synthesize CPUID leaf 0x80000021h if useful
  KVM: x86: add support for CPUID leaf 0x80000021
  KVM: x86: do not use KVM_X86_OP_OPTIONAL_RET0 for get_mt_mask
  Revert "KVM: x86/mmu: Zap only TDP MMU leafs in kvm_zap_gfn_range()"
  kvm: x86/mmu: Flush TLB before zap_gfn_range releases RCU
  KVM: arm64: fix typos in comments
  KVM: arm64: Generalise VM features into a set of flags
  KVM: s390: selftests: Add error memop tests
  KVM: s390: selftests: Add more copy memop tests
  KVM: s390: selftests: Add named stages for memop test
  KVM: s390: selftests: Add macro as abstraction for MEM_OP
  KVM: s390: selftests: Split memop tests
  KVM: s390x: fix SCK locking
  RISC-V: KVM: Implement SBI HSM suspend call
  RISC-V: KVM: Add common kvm_riscv_vcpu_wfi() function
  RISC-V: Add SBI HSM suspend related defines
  RISC-V: KVM: Implement SBI v0.3 SRST extension
  ...

1 files changed, 36 insertions, 9 deletions

diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 031e3a2537fc..e3b25dc6c367 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -50,6 +50,8 @@
 #define KVM_DIRTY_LOG_MANUAL_CAPS   (KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE | \
 				     KVM_DIRTY_LOG_INITIALLY_SET)
 
+#define KVM_HAVE_MMU_RWLOCK
+
 /*
  * Mode of operation configurable with kvm-arm.mode early param.
  * See Documentation/admin-guide/kernel-parameters.txt for more information.
@@ -71,9 +73,7 @@ int kvm_reset_vcpu(struct kvm_vcpu *vcpu);
 void kvm_arm_vcpu_destroy(struct kvm_vcpu *vcpu);
 
 struct kvm_vmid {
-	/* The VMID generation used for the virt. memory system */
-	u64    vmid_gen;
-	u32    vmid;
+	atomic64_t id;
 };
 
 struct kvm_s2_mmu {
@@ -122,20 +122,24 @@ struct kvm_arch {
 	 * should) opt in to this feature if KVM_CAP_ARM_NISV_TO_USER is
 	 * supported.
 	 */
-	bool return_nisv_io_abort_to_user;
+#define KVM_ARCH_FLAG_RETURN_NISV_IO_ABORT_TO_USER	0
+	/* Memory Tagging Extension enabled for the guest */
+#define KVM_ARCH_FLAG_MTE_ENABLED			1
+	/* At least one vCPU has ran in the VM */
+#define KVM_ARCH_FLAG_HAS_RAN_ONCE			2
+	unsigned long flags;
 
 	/*
 	 * VM-wide PMU filter, implemented as a bitmap and big enough for
 	 * up to 2^10 events (ARMv8.0) or 2^16 events (ARMv8.1+).
 	 */
 	unsigned long *pmu_filter;
-	unsigned int pmuver;
+	struct arm_pmu *arm_pmu;
+
+	cpumask_var_t supported_cpus;
 
 	u8 pfr0_csv2;
 	u8 pfr0_csv3;
-
-	/* Memory Tagging Extension enabled for the guest */
-	bool mte_enabled;
 };
 
 struct kvm_vcpu_fault_info {
@@ -171,6 +175,7 @@ enum vcpu_sysreg {
 	PAR_EL1,	/* Physical Address Register */
 	MDSCR_EL1,	/* Monitor Debug System Control Register */
 	MDCCINT_EL1,	/* Monitor Debug Comms Channel Interrupt Enable Reg */
+	OSLSR_EL1,	/* OS Lock Status Register */
 	DISR_EL1,	/* Deferred Interrupt Status Register */
 
 	/* Performance Monitors Registers */
@@ -435,6 +440,7 @@ struct kvm_vcpu_arch {
 #define KVM_ARM64_DEBUG_STATE_SAVE_SPE	(1 << 12) /* Save SPE context if active  */
 #define KVM_ARM64_DEBUG_STATE_SAVE_TRBE	(1 << 13) /* Save TRBE context if active  */
 #define KVM_ARM64_FP_FOREIGN_FPSTATE	(1 << 14)
+#define KVM_ARM64_ON_UNSUPPORTED_CPU	(1 << 15) /* Physical CPU not in supported_cpus */
 
 #define KVM_GUESTDBG_VALID_MASK (KVM_GUESTDBG_ENABLE | \
 				 KVM_GUESTDBG_USE_SW_BP | \
@@ -453,6 +459,15 @@ struct kvm_vcpu_arch {
 #define vcpu_has_ptrauth(vcpu)		false
 #endif
 
+#define vcpu_on_unsupported_cpu(vcpu)					\
+	((vcpu)->arch.flags & KVM_ARM64_ON_UNSUPPORTED_CPU)
+
+#define vcpu_set_on_unsupported_cpu(vcpu)				\
+	((vcpu)->arch.flags |= KVM_ARM64_ON_UNSUPPORTED_CPU)
+
+#define vcpu_clear_on_unsupported_cpu(vcpu)				\
+	((vcpu)->arch.flags &= ~KVM_ARM64_ON_UNSUPPORTED_CPU)
+
 #define vcpu_gp_regs(v)		(&(v)->arch.ctxt.regs)
 
 /*
@@ -692,6 +707,12 @@ int kvm_arm_pvtime_get_attr(struct kvm_vcpu *vcpu,
 int kvm_arm_pvtime_has_attr(struct kvm_vcpu *vcpu,
 			    struct kvm_device_attr *attr);
 
+extern unsigned int kvm_arm_vmid_bits;
+int kvm_arm_vmid_alloc_init(void);
+void kvm_arm_vmid_alloc_free(void);
+void kvm_arm_vmid_update(struct kvm_vmid *kvm_vmid);
+void kvm_arm_vmid_clear_active(void);
+
 static inline void kvm_arm_pvtime_vcpu_init(struct kvm_vcpu_arch *vcpu_arch)
 {
 	vcpu_arch->steal.base = GPA_INVALID;
@@ -730,6 +751,10 @@ void kvm_arm_vcpu_init_debug(struct kvm_vcpu *vcpu);
 void kvm_arm_setup_debug(struct kvm_vcpu *vcpu);
 void kvm_arm_clear_debug(struct kvm_vcpu *vcpu);
 void kvm_arm_reset_debug_ptr(struct kvm_vcpu *vcpu);
+
+#define kvm_vcpu_os_lock_enabled(vcpu)		\
+	(!!(__vcpu_sys_reg(vcpu, OSLSR_EL1) & SYS_OSLSR_OSLK))
+
 int kvm_arm_vcpu_arch_set_attr(struct kvm_vcpu *vcpu,
 			       struct kvm_device_attr *attr);
 int kvm_arm_vcpu_arch_get_attr(struct kvm_vcpu *vcpu,
@@ -791,7 +816,9 @@ bool kvm_arm_vcpu_is_finalized(struct kvm_vcpu *vcpu);
 #define kvm_arm_vcpu_sve_finalized(vcpu) \
 	((vcpu)->arch.flags & KVM_ARM64_VCPU_SVE_FINALIZED)
 
-#define kvm_has_mte(kvm) (system_supports_mte() && (kvm)->arch.mte_enabled)
+#define kvm_has_mte(kvm)					\
+	(system_supports_mte() &&				\
+	 test_bit(KVM_ARCH_FLAG_MTE_ENABLED, &(kvm)->arch.flags))
 #define kvm_vcpu_has_pmu(vcpu)					\
 	(test_bit(KVM_ARM_VCPU_PMU_V3, (vcpu)->arch.features))