Merge tag 'kvmarm-5.18' of git://git.kernel.org/pub/scm/linux/kernel/git/kvmarm/kvmarm into HEAD

KVM/arm64 updates for 5.18

- 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

Documentation/virt/kvm/devices/vcpu.rst

@@ -70,7 +70,7 @@ irqchip.
 	 -ENODEV  PMUv3 not supported or GIC not initialized
 	 -ENXIO   PMUv3 not properly configured or in-kernel irqchip not
 	 	  configured as required prior to calling this attribute
-	 -EBUSY   PMUv3 already initialized
+	 -EBUSY   PMUv3 already initialized or a VCPU has already run
 	 -EINVAL  Invalid filter range
 	 =======  ======================================================
 
@@ -104,11 +104,43 @@ hardware event. Filtering event 0x1E (CHAIN) has no effect either, as it
 isn't strictly speaking an event. Filtering the cycle counter is possible
 using event 0x11 (CPU_CYCLES).
 
+1.4 ATTRIBUTE: KVM_ARM_VCPU_PMU_V3_SET_PMU
+------------------------------------------
+
+:Parameters: in kvm_device_attr.addr the address to an int representing the PMU
+             identifier.
+
+:Returns:
+
+	 =======  ====================================================
+	 -EBUSY   PMUv3 already initialized, a VCPU has already run or
+                  an event filter has already been set
+	 -EFAULT  Error accessing the PMU identifier
+	 -ENXIO   PMU not found
+	 -ENODEV  PMUv3 not supported or GIC not initialized
+	 -ENOMEM  Could not allocate memory
+	 =======  ====================================================
+
+Request that the VCPU uses the specified hardware PMU when creating guest events
+for the purpose of PMU emulation. The PMU identifier can be read from the "type"
+file for the desired PMU instance under /sys/devices (or, equivalent,
+/sys/bus/even_source). This attribute is particularly useful on heterogeneous
+systems where there are at least two CPU PMUs on the system. The PMU that is set
+for one VCPU will be used by all the other VCPUs. It isn't possible to set a PMU
+if a PMU event filter is already present.
+
+Note that KVM will not make any attempts to run the VCPU on the physical CPUs
+associated with the PMU specified by this attribute. This is entirely left to
+userspace. However, attempting to run the VCPU on a physical CPU not supported
+by the PMU will fail and KVM_RUN will return with
+exit_reason = KVM_EXIT_FAIL_ENTRY and populate the fail_entry struct by setting
+hardare_entry_failure_reason field to KVM_EXIT_FAIL_ENTRY_CPU_UNSUPPORTED and
+the cpu field to the processor id.
 
 2. GROUP: KVM_ARM_VCPU_TIMER_CTRL
 =================================
 
-:Architectures: ARM, ARM64
+:Architectures: ARM64
 
 2.1. ATTRIBUTES: KVM_ARM_VCPU_TIMER_IRQ_VTIMER, KVM_ARM_VCPU_TIMER_IRQ_PTIMER
 -----------------------------------------------------------------------------

arch/arm64/Kconfig

@@ -682,6 +682,7 @@ config ARM64_ERRATUM_2051678
 
 config ARM64_ERRATUM_2077057
 	bool "Cortex-A510: 2077057: workaround software-step corrupting SPSR_EL2"
+	default y
 	help
 	  This option adds the workaround for ARM Cortex-A510 erratum 2077057.
 	  Affected Cortex-A510 may corrupt SPSR_EL2 when the a step exception is

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;
@@ -725,6 +746,10 @@ 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,
@@ -786,7 +811,9 @@ 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))
 

arch/arm64/include/asm/kvm_mmu.h

@@ -115,6 +115,7 @@ alternative_cb_end
 #include <asm/cache.h>
 #include <asm/cacheflush.h>
 #include <asm/mmu_context.h>
+#include <asm/kvm_host.h>
 
 void kvm_update_va_mask(struct alt_instr *alt,
 			__le32 *origptr, __le32 *updptr, int nr_inst);
@@ -266,7 +267,8 @@ static __always_inline u64 kvm_get_vttbr(struct kvm_s2_mmu *mmu)
 	u64 cnp = system_supports_cnp() ? VTTBR_CNP_BIT : 0;
 
 	baddr = mmu->pgd_phys;
-	vmid_field = (u64)READ_ONCE(vmid->vmid) << VTTBR_VMID_SHIFT;
+	vmid_field = atomic64_read(&vmid->id) << VTTBR_VMID_SHIFT;
+	vmid_field &= VTTBR_VMID_MASK(kvm_arm_vmid_bits);
 	return kvm_phys_to_vttbr(baddr) | vmid_field | cnp;
 }
 

arch/arm64/include/asm/sysreg.h

@@ -128,8 +128,16 @@
 #define SYS_DBGWVRn_EL1(n)		sys_reg(2, 0, 0, n, 6)
 #define SYS_DBGWCRn_EL1(n)		sys_reg(2, 0, 0, n, 7)
 #define SYS_MDRAR_EL1			sys_reg(2, 0, 1, 0, 0)
+
 #define SYS_OSLAR_EL1			sys_reg(2, 0, 1, 0, 4)
+#define SYS_OSLAR_OSLK			BIT(0)
+
 #define SYS_OSLSR_EL1			sys_reg(2, 0, 1, 1, 4)
+#define SYS_OSLSR_OSLM_MASK		(BIT(3) | BIT(0))
+#define SYS_OSLSR_OSLM_NI		0
+#define SYS_OSLSR_OSLM_IMPLEMENTED	BIT(3)
+#define SYS_OSLSR_OSLK			BIT(1)
+
 #define SYS_OSDLR_EL1			sys_reg(2, 0, 1, 3, 4)
 #define SYS_DBGPRCR_EL1			sys_reg(2, 0, 1, 4, 4)
 #define SYS_DBGCLAIMSET_EL1		sys_reg(2, 0, 7, 8, 6)

arch/arm64/include/uapi/asm/kvm.h

@@ -362,6 +362,7 @@ struct kvm_arm_copy_mte_tags {
 #define   KVM_ARM_VCPU_PMU_V3_IRQ	0
 #define   KVM_ARM_VCPU_PMU_V3_INIT	1
 #define   KVM_ARM_VCPU_PMU_V3_FILTER	2
+#define   KVM_ARM_VCPU_PMU_V3_SET_PMU	3
 #define KVM_ARM_VCPU_TIMER_CTRL		1
 #define   KVM_ARM_VCPU_TIMER_IRQ_VTIMER		0
 #define   KVM_ARM_VCPU_TIMER_IRQ_PTIMER		1
@@ -413,6 +414,16 @@ struct kvm_arm_copy_mte_tags {
 #define KVM_PSCI_RET_INVAL		PSCI_RET_INVALID_PARAMS
 #define KVM_PSCI_RET_DENIED		PSCI_RET_DENIED
 
+/* arm64-specific kvm_run::system_event flags */
+/*
+ * Reset caused by a PSCI v1.1 SYSTEM_RESET2 call.
+ * Valid only when the system event has a type of KVM_SYSTEM_EVENT_RESET.
+ */
+#define KVM_SYSTEM_EVENT_RESET_FLAG_PSCI_RESET2	(1ULL << 0)
+
+/* run->fail_entry.hardware_entry_failure_reason codes. */
+#define KVM_EXIT_FAIL_ENTRY_CPU_UNSUPPORTED	(1ULL << 0)
+
 #endif
 
 #endif /* __ARM_KVM_H__ */

arch/arm64/kernel/fpsimd.c

@@ -348,7 +348,13 @@ static void task_fpsimd_load(void)
 
 /*
  * Ensure FPSIMD/SVE storage in memory for the loaded context is up to
- * date with respect to the CPU registers.
+ * date with respect to the CPU registers. Note carefully that the
+ * current context is the context last bound to the CPU stored in
+ * last, if KVM is involved this may be the guest VM context rather
+ * than the host thread for the VM pointed to by current. This means
+ * that we must always reference the state storage via last rather
+ * than via current, other than the TIF_ flags which KVM will
+ * carefully maintain for us.
  */
 static void fpsimd_save(void)
 {

arch/arm64/kernel/image-vars.h

@@ -79,6 +79,9 @@ KVM_NVHE_ALIAS(__hyp_stub_vectors);
 /* Kernel symbol used by icache_is_vpipt(). */
 KVM_NVHE_ALIAS(__icache_flags);
 
+/* VMID bits set by the KVM VMID allocator */
+KVM_NVHE_ALIAS(kvm_arm_vmid_bits);
+
 /* Kernel symbols needed for cpus_have_final/const_caps checks. */
 KVM_NVHE_ALIAS(arm64_const_caps_ready);
 KVM_NVHE_ALIAS(cpu_hwcap_keys);

arch/arm64/kvm/Makefile

@@ -14,7 +14,7 @@ kvm-y += arm.o mmu.o mmio.o psci.o hypercalls.o pvtime.o \
 	 inject_fault.o va_layout.o handle_exit.o \
 	 guest.o debug.o reset.o sys_regs.o \
 	 vgic-sys-reg-v3.o fpsimd.o pmu.o pkvm.o \
-	 arch_timer.o trng.o\
+	 arch_timer.o trng.o vmid.o \
 	 vgic/vgic.o vgic/vgic-init.o \
 	 vgic/vgic-irqfd.o vgic/vgic-v2.o \
 	 vgic/vgic-v3.o vgic/vgic-v4.o \

arch/arm64/kvm/arm.c

@@ -53,11 +53,6 @@ static DEFINE_PER_CPU(unsigned long, kvm_arm_hyp_stack_page);
 unsigned long kvm_arm_hyp_percpu_base[NR_CPUS];
 DECLARE_KVM_NVHE_PER_CPU(struct kvm_nvhe_init_params, kvm_init_params);
 
-/* The VMID used in the VTTBR */
-static atomic64_t kvm_vmid_gen = ATOMIC64_INIT(1);
-static u32 kvm_next_vmid;
-static DEFINE_SPINLOCK(kvm_vmid_lock);
-
 static bool vgic_present;
 
 static DEFINE_PER_CPU(unsigned char, kvm_arm_hardware_enabled);
@@ -89,7 +84,8 @@ int kvm_vm_ioctl_enable_cap(struct kvm *kvm,
 	switch (cap->cap) {
 	case KVM_CAP_ARM_NISV_TO_USER:
 		r = 0;
-		kvm->arch.return_nisv_io_abort_to_user = true;
+		set_bit(KVM_ARCH_FLAG_RETURN_NISV_IO_ABORT_TO_USER,
+			&kvm->arch.flags);
 		break;
 	case KVM_CAP_ARM_MTE:
 		mutex_lock(&kvm->lock);
@@ -97,7 +93,7 @@ int kvm_vm_ioctl_enable_cap(struct kvm *kvm,
 			r = -EINVAL;
 		} else {
 			r = 0;
-			kvm->arch.mte_enabled = true;
+			set_bit(KVM_ARCH_FLAG_MTE_ENABLED, &kvm->arch.flags);
 		}
 		mutex_unlock(&kvm->lock);
 		break;
@@ -150,6 +146,10 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 	if (ret)
 		goto out_free_stage2_pgd;
 
+	if (!zalloc_cpumask_var(&kvm->arch.supported_cpus, GFP_KERNEL))
+		goto out_free_stage2_pgd;
+	cpumask_copy(kvm->arch.supported_cpus, cpu_possible_mask);
+
 	kvm_vgic_early_init(kvm);
 
 	/* The maximum number of VCPUs is limited by the host's GIC model */
@@ -176,6 +176,7 @@ vm_fault_t kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf)
 void kvm_arch_destroy_vm(struct kvm *kvm)
 {
 	bitmap_free(kvm->arch.pmu_filter);
+	free_cpumask_var(kvm->arch.supported_cpus);
 
 	kvm_vgic_destroy(kvm);
 
@@ -411,6 +412,9 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 	if (vcpu_has_ptrauth(vcpu))
 		vcpu_ptrauth_disable(vcpu);
 	kvm_arch_vcpu_load_debug_state_flags(vcpu);
+
+	if (!cpumask_test_cpu(smp_processor_id(), vcpu->kvm->arch.supported_cpus))
+		vcpu_set_on_unsupported_cpu(vcpu);
 }
 
 void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
@@ -422,7 +426,9 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
 	kvm_timer_vcpu_put(vcpu);
 	kvm_vgic_put(vcpu);
 	kvm_vcpu_pmu_restore_host(vcpu);
+	kvm_arm_vmid_clear_active();
 
+	vcpu_clear_on_unsupported_cpu(vcpu);
 	vcpu->cpu = -1;
 }
 
@@ -489,87 +495,6 @@ unsigned long kvm_arch_vcpu_get_ip(struct kvm_vcpu *vcpu)
 }
 #endif
 
-/* Just ensure a guest exit from a particular CPU */
-static void exit_vm_noop(void *info)
-{
-}
-
-void force_vm_exit(const cpumask_t *mask)
-{
-	preempt_disable();
-	smp_call_function_many(mask, exit_vm_noop, NULL, true);
-	preempt_enable();
-}
-
-/**
- * need_new_vmid_gen - check that the VMID is still valid
- * @vmid: The VMID to check
- *
- * return true if there is a new generation of VMIDs being used
- *
- * The hardware supports a limited set of values with the value zero reserved
- * for the host, so we check if an assigned value belongs to a previous
- * generation, which requires us to assign a new value. If we're the first to
- * use a VMID for the new generation, we must flush necessary caches and TLBs
- * on all CPUs.
- */
-static bool need_new_vmid_gen(struct kvm_vmid *vmid)
-{
-	u64 current_vmid_gen = atomic64_read(&kvm_vmid_gen);
-	smp_rmb(); /* Orders read of kvm_vmid_gen and kvm->arch.vmid */
-	return unlikely(READ_ONCE(vmid->vmid_gen) != current_vmid_gen);
-}
-
-/**
- * update_vmid - Update the vmid with a valid VMID for the current generation
- * @vmid: The stage-2 VMID information struct
- */
-static void update_vmid(struct kvm_vmid *vmid)
-{
-	if (!need_new_vmid_gen(vmid))
-		return;
-
-	spin_lock(&kvm_vmid_lock);
-
-	/*
-	 * We need to re-check the vmid_gen here to ensure that if another vcpu
-	 * already allocated a valid vmid for this vm, then this vcpu should
-	 * use the same vmid.
-	 */
-	if (!need_new_vmid_gen(vmid)) {
-		spin_unlock(&kvm_vmid_lock);
-		return;
-	}
-
-	/* First user of a new VMID generation? */
-	if (unlikely(kvm_next_vmid == 0)) {
-		atomic64_inc(&kvm_vmid_gen);
-		kvm_next_vmid = 1;
-
-		/*
-		 * On SMP we know no other CPUs can use this CPU's or each
-		 * other's VMID after force_vm_exit returns since the
-		 * kvm_vmid_lock blocks them from reentry to the guest.
-		 */
-		force_vm_exit(cpu_all_mask);
-		/*
-		 * Now broadcast TLB + ICACHE invalidation over the inner
-		 * shareable domain to make sure all data structures are
-		 * clean.
-		 */
-		kvm_call_hyp(__kvm_flush_vm_context);
-	}
-
-	WRITE_ONCE(vmid->vmid, kvm_next_vmid);
-	kvm_next_vmid++;
-	kvm_next_vmid &= (1 << kvm_get_vmid_bits()) - 1;
-
-	smp_wmb();
-	WRITE_ONCE(vmid->vmid_gen, atomic64_read(&kvm_vmid_gen));
-
-	spin_unlock(&kvm_vmid_lock);
-}
-
 static int kvm_vcpu_initialized(struct kvm_vcpu *vcpu)
 {
 	return vcpu->arch.target >= 0;
@@ -634,6 +559,10 @@ int kvm_arch_vcpu_run_pid_change(struct kvm_vcpu *vcpu)
 	if (kvm_vm_is_protected(kvm))
 		kvm_call_hyp_nvhe(__pkvm_vcpu_init_traps, vcpu);
 
+	mutex_lock(&kvm->lock);
+	set_bit(KVM_ARCH_FLAG_HAS_RAN_ONCE, &kvm->arch.flags);
+	mutex_unlock(&kvm->lock);
+
 	return ret;
 }
 
@@ -792,8 +721,15 @@ static bool kvm_vcpu_exit_request(struct kvm_vcpu *vcpu, int *ret)
 		}
 	}
 
+	if (unlikely(vcpu_on_unsupported_cpu(vcpu))) {
+		run->exit_reason = KVM_EXIT_FAIL_ENTRY;
+		run->fail_entry.hardware_entry_failure_reason = KVM_EXIT_FAIL_ENTRY_CPU_UNSUPPORTED;
+		run->fail_entry.cpu = smp_processor_id();
+		*ret = 0;
+		return true;
+	}
+
 	return kvm_request_pending(vcpu) ||
-			need_new_vmid_gen(&vcpu->arch.hw_mmu->vmid) ||
 			xfer_to_guest_mode_work_pending();
 }
 
@@ -855,8 +791,6 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 		if (!ret)
 			ret = 1;
 
-		update_vmid(&vcpu->arch.hw_mmu->vmid);
-
 		check_vcpu_requests(vcpu);
 
 		/*
@@ -866,6 +800,15 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 		 */
 		preempt_disable();
 
+		/*
+		 * The VMID allocator only tracks active VMIDs per
+		 * physical CPU, and therefore the VMID allocated may not be
+		 * preserved on VMID roll-over if the task was preempted,
+		 * making a thread's VMID inactive. So we need to call
+		 * kvm_arm_vmid_update() in non-premptible context.
+		 */
+		kvm_arm_vmid_update(&vcpu->arch.hw_mmu->vmid);
+
 		kvm_pmu_flush_hwstate(vcpu);
 
 		local_irq_disable();
@@ -945,9 +888,11 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 		 * context synchronization event) is necessary to ensure that
 		 * pending interrupts are taken.
 		 */
-		local_irq_enable();
-		isb();
-		local_irq_disable();
+		if (ARM_EXCEPTION_CODE(ret) == ARM_EXCEPTION_IRQ) {
+			local_irq_enable();
+			isb();
+			local_irq_disable();
+		}
 
 		guest_timing_exit_irqoff();
 
@@ -1745,7 +1690,7 @@ static void init_cpu_logical_map(void)
 
 	/*
 	 * Copy the MPIDR <-> logical CPU ID mapping to hyp.
-	 * Only copy the set of online CPUs whose features have been chacked
+	 * Only copy the set of online CPUs whose features have been checked
 	 * against the finalized system capabilities. The hypervisor will not
 	 * allow any other CPUs from the `possible` set to boot.
 	 */
@@ -2161,6 +2106,12 @@ int kvm_arch_init(void *opaque)
 	if (err)
 		return err;
 
+	err = kvm_arm_vmid_alloc_init();
+	if (err) {
+		kvm_err("Failed to initialize VMID allocator.\n");
+		return err;
+	}
+
 	if (!in_hyp_mode) {
 		err = init_hyp_mode();
 		if (err)
@@ -2200,6 +2151,7 @@ int kvm_arch_init(void *opaque)
 	if (!in_hyp_mode)
 		teardown_hyp_mode();
 out_err:
+	kvm_arm_vmid_alloc_free();
 	return err;
 }
 

arch/arm64/kvm/debug.c

@@ -105,9 +105,11 @@ static void kvm_arm_setup_mdcr_el2(struct kvm_vcpu *vcpu)
 	 *  - Userspace is using the hardware to debug the guest
 	 *  (KVM_GUESTDBG_USE_HW is set).
 	 *  - The guest is not using debug (KVM_ARM64_DEBUG_DIRTY is clear).
+	 *  - The guest has enabled the OS Lock (debug exceptions are blocked).
 	 */
 	if ((vcpu->guest_debug & KVM_GUESTDBG_USE_HW) ||
-	    !(vcpu->arch.flags & KVM_ARM64_DEBUG_DIRTY))
+	    !(vcpu->arch.flags & KVM_ARM64_DEBUG_DIRTY) ||
+	    kvm_vcpu_os_lock_enabled(vcpu))
 		vcpu->arch.mdcr_el2 |= MDCR_EL2_TDA;
 
 	trace_kvm_arm_set_dreg32("MDCR_EL2", vcpu->arch.mdcr_el2);
@@ -160,8 +162,8 @@ void kvm_arm_setup_debug(struct kvm_vcpu *vcpu)
 
 	kvm_arm_setup_mdcr_el2(vcpu);
 
-	/* Is Guest debugging in effect? */
-	if (vcpu->guest_debug) {
+	/* Check if we need to use the debug registers. */
+	if (vcpu->guest_debug || kvm_vcpu_os_lock_enabled(vcpu)) {
 		/* Save guest debug state */
 		save_guest_debug_regs(vcpu);
 
@@ -223,6 +225,19 @@ void kvm_arm_setup_debug(struct kvm_vcpu *vcpu)
 			trace_kvm_arm_set_regset("WAPTS", get_num_wrps(),
 						&vcpu->arch.debug_ptr->dbg_wcr[0],
 						&vcpu->arch.debug_ptr->dbg_wvr[0]);
+
+		/*
+		 * The OS Lock blocks debug exceptions in all ELs when it is
+		 * enabled. If the guest has enabled the OS Lock, constrain its
+		 * effects to the guest. Emulate the behavior by clearing
+		 * MDSCR_EL1.MDE. In so doing, we ensure that host debug
+		 * exceptions are unaffected by guest configuration of the OS
+		 * Lock.
+		 */
+		} else if (kvm_vcpu_os_lock_enabled(vcpu)) {
+			mdscr = vcpu_read_sys_reg(vcpu, MDSCR_EL1);
+			mdscr &= ~DBG_MDSCR_MDE;
+			vcpu_write_sys_reg(vcpu, mdscr, MDSCR_EL1);
 		}
 	}
 
@@ -244,7 +259,10 @@ void kvm_arm_clear_debug(struct kvm_vcpu *vcpu)
 {
 	trace_kvm_arm_clear_debug(vcpu->guest_debug);
 
-	if (vcpu->guest_debug) {
+	/*
+	 * Restore the guest's debug registers if we were using them.
+	 */
+	if (vcpu->guest_debug || kvm_vcpu_os_lock_enabled(vcpu)) {
 		restore_guest_debug_regs(vcpu);
 
 		/*

arch/arm64/kvm/fpsimd.c

@@ -84,6 +84,11 @@ void kvm_arch_vcpu_load_fp(struct kvm_vcpu *vcpu)
 		vcpu->arch.flags |= KVM_ARM64_HOST_SVE_ENABLED;
 }
 
+/*
+ * Called just before entering the guest once we are no longer
+ * preemptable. Syncs the host's TIF_FOREIGN_FPSTATE with the KVM
+ * mirror of the flag used by the hypervisor.
+ */
 void kvm_arch_vcpu_ctxflush_fp(struct kvm_vcpu *vcpu)
 {
 	if (test_thread_flag(TIF_FOREIGN_FPSTATE))
@@ -93,10 +98,11 @@ void kvm_arch_vcpu_ctxflush_fp(struct kvm_vcpu *vcpu)
 }
 
 /*
- * If the guest FPSIMD state was loaded, update the host's context
- * tracking data mark the CPU FPSIMD regs as dirty and belonging to vcpu
- * so that they will be written back if the kernel clobbers them due to
- * kernel-mode NEON before re-entry into the guest.
+ * Called just after exiting the guest. If the guest FPSIMD state
+ * was loaded, update the host's context tracking data mark the CPU
+ * FPSIMD regs as dirty and belonging to vcpu so that they will be
+ * written back if the kernel clobbers them due to kernel-mode NEON
+ * before re-entry into the guest.
  */
 void kvm_arch_vcpu_ctxsync_fp(struct kvm_vcpu *vcpu)
 {

arch/arm64/kvm/guest.c

@@ -282,7 +282,7 @@ static int set_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 			break;
 
 		/*
-		 * Otherwide, this is a priviledged mode, and *all* the
+		 * Otherwise, this is a privileged mode, and *all* the
 		 * registers must be narrowed to 32bit.
 		 */
 		default:

arch/arm64/kvm/handle_exit.c

@@ -248,7 +248,7 @@ int handle_exit(struct kvm_vcpu *vcpu, int exception_index)
 	case ARM_EXCEPTION_HYP_GONE:
 		/*
 		 * EL2 has been reset to the hyp-stub. This happens when a guest
-		 * is pre-empted by kvm_reboot()'s shutdown call.
+		 * is pre-emptied by kvm_reboot()'s shutdown call.
 		 */
 		run->exit_reason = KVM_EXIT_FAIL_ENTRY;
 		return 0;

arch/arm64/kvm/hyp/include/hyp/switch.h

@@ -173,6 +173,8 @@ static bool kvm_hyp_handle_fpsimd(struct kvm_vcpu *vcpu, u64 *exit_code)
 		return false;
 
 	/* Valid trap.  Switch the context: */
+
+	/* First disable enough traps to allow us to update the registers */
 	if (has_vhe()) {
 		reg = CPACR_EL1_FPEN;
 		if (sve_guest)
@@ -188,11 +190,13 @@ static bool kvm_hyp_handle_fpsimd(struct kvm_vcpu *vcpu, u64 *exit_code)
 	}
 	isb();
 
+	/* Write out the host state if it's in the registers */
 	if (vcpu->arch.flags & KVM_ARM64_FP_HOST) {
 		__fpsimd_save_state(vcpu->arch.host_fpsimd_state);
 		vcpu->arch.flags &= ~KVM_ARM64_FP_HOST;
 	}
 
+	/* Restore the guest state */
 	if (sve_guest)
 		__hyp_sve_restore_guest(vcpu);
 	else

arch/arm64/kvm/hyp/nvhe/Makefile

@@ -13,10 +13,11 @@ lib-objs := clear_page.o copy_page.o memcpy.o memset.o
 lib-objs := $(addprefix ../../../lib/, $(lib-objs))
 
 obj-y := timer-sr.o sysreg-sr.o debug-sr.o switch.o tlb.o hyp-init.o host.o \
-	 hyp-main.o hyp-smp.o psci-relay.o early_alloc.o stub.o page_alloc.o \
+	 hyp-main.o hyp-smp.o psci-relay.o early_alloc.o page_alloc.o \
 	 cache.o setup.o mm.o mem_protect.o sys_regs.o pkvm.o
 obj-y += ../vgic-v3-sr.o ../aarch32.o ../vgic-v2-cpuif-proxy.o ../entry.o \
 	 ../fpsimd.o ../hyp-entry.o ../exception.o ../pgtable.o
+obj-$(CONFIG_DEBUG_LIST) += list_debug.o
 obj-y += $(lib-objs)
 
 ##

arch/arm64/kvm/hyp/nvhe/list_debug.c

+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2022 - Google LLC
+ * Author: Keir Fraser <keirf@google.com>
+ */
+
+#include <linux/list.h>
+#include <linux/bug.h>
+
+static inline __must_check bool nvhe_check_data_corruption(bool v)
+{
+	return v;
+}
+
+#define NVHE_CHECK_DATA_CORRUPTION(condition)				 \
+	nvhe_check_data_corruption(({					 \
+		bool corruption = unlikely(condition);			 \
+		if (corruption) {					 \
+			if (IS_ENABLED(CONFIG_BUG_ON_DATA_CORRUPTION)) { \
+				BUG_ON(1);				 \
+			} else						 \
+				WARN_ON(1);				 \
+		}							 \
+		corruption;						 \
+	}))
+
+/* The predicates checked here are taken from lib/list_debug.c. */
+
+bool __list_add_valid(struct list_head *new, struct list_head *prev,
+		      struct list_head *next)
+{
+	if (NVHE_CHECK_DATA_CORRUPTION(next->prev != prev) ||
+	    NVHE_CHECK_DATA_CORRUPTION(prev->next != next) ||
+	    NVHE_CHECK_DATA_CORRUPTION(new == prev || new == next))
+		return false;
+
+	return true;
+}
+
+bool __list_del_entry_valid(struct list_head *entry)
+{
+	struct list_head *prev, *next;
+
+	prev = entry->prev;
+	next = entry->next;
+
+	if (NVHE_CHECK_DATA_CORRUPTION(next == LIST_POISON1) ||
+	    NVHE_CHECK_DATA_CORRUPTION(prev == LIST_POISON2) ||
+	    NVHE_CHECK_DATA_CORRUPTION(prev->next != entry) ||
+	    NVHE_CHECK_DATA_CORRUPTION(next->prev != entry))
+		return false;
+
+	return true;
+}

arch/arm64/kvm/hyp/nvhe/mem_protect.c

@@ -138,8 +138,7 @@ int kvm_host_prepare_stage2(void *pgt_pool_base)
 
 	mmu->pgd_phys = __hyp_pa(host_kvm.pgt.pgd);
 	mmu->pgt = &host_kvm.pgt;
-	WRITE_ONCE(mmu->vmid.vmid_gen, 0);
-	WRITE_ONCE(mmu->vmid.vmid, 0);
+	atomic64_set(&mmu->vmid.id, 0);
 
 	return 0;
 }

arch/arm64/kvm/hyp/nvhe/page_alloc.c

@@ -102,7 +102,7 @@ static void __hyp_attach_page(struct hyp_pool *pool,
 	 * Only the first struct hyp_page of a high-order page (otherwise known
 	 * as the 'head') should have p->order set. The non-head pages should
 	 * have p->order = HYP_NO_ORDER. Here @p may no longer be the head
-	 * after coallescing, so make sure to mark it HYP_NO_ORDER proactively.
+	 * after coalescing, so make sure to mark it HYP_NO_ORDER proactively.
 	 */
 	p->order = HYP_NO_ORDER;
 	for (; (order + 1) < pool->max_order; order++) {
@@ -110,7 +110,7 @@ static void __hyp_attach_page(struct hyp_pool *pool,
 		if (!buddy)
 			break;
 
-		/* Take the buddy out of its list, and coallesce with @p */
+		/* Take the buddy out of its list, and coalesce with @p */
 		page_remove_from_list(buddy);
 		buddy->order = HYP_NO_ORDER;
 		p = min(p, buddy);

arch/arm64/kvm/hyp/nvhe/stub.c

-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Stubs for out-of-line function calls caused by re-using kernel
- * infrastructure at EL2.
- *
- * Copyright (C) 2020 - Google LLC
- */
-
-#include <linux/list.h>
-
-#ifdef CONFIG_DEBUG_LIST
-bool __list_add_valid(struct list_head *new, struct list_head *prev,
-		      struct list_head *next)
-{
-		return true;
-}
-
-bool __list_del_entry_valid(struct list_head *entry)
-{
-		return true;
-}
-#endif

arch/arm64/kvm/mmio.c

@@ -135,7 +135,8 @@ int io_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa)
 	 * volunteered to do so, and bail out otherwise.
 	 */
 	if (!kvm_vcpu_dabt_isvalid(vcpu)) {
-		if (vcpu->kvm->arch.return_nisv_io_abort_to_user) {
+		if (test_bit(KVM_ARCH_FLAG_RETURN_NISV_IO_ABORT_TO_USER,
+			     &vcpu->kvm->arch.flags)) {
 			run->exit_reason = KVM_EXIT_ARM_NISV;
 			run->arm_nisv.esr_iss = kvm_vcpu_dabt_iss_nisv_sanitized(vcpu);
 			run->arm_nisv.fault_ipa = fault_ipa;

arch/arm64/kvm/mmu.c

@@ -58,7 +58,7 @@ static int stage2_apply_range(struct kvm *kvm, phys_addr_t addr,
 			break;
 
 		if (resched && next != end)
-			cond_resched_lock(&kvm->mmu_lock);
+			cond_resched_rwlock_write(&kvm->mmu_lock);
 	} while (addr = next, addr != end);
 
 	return ret;
@@ -179,7 +179,7 @@ static void __unmap_stage2_range(struct kvm_s2_mmu *mmu, phys_addr_t start, u64
 	struct kvm *kvm = kvm_s2_mmu_to_kvm(mmu);
 	phys_addr_t end = start + size;
 
-	assert_spin_locked(&kvm->mmu_lock);
+	lockdep_assert_held_write(&kvm->mmu_lock);
 	WARN_ON(size & ~PAGE_MASK);
 	WARN_ON(stage2_apply_range(kvm, start, end, kvm_pgtable_stage2_unmap,
 				   may_block));
@@ -213,13 +213,13 @@ static void stage2_flush_vm(struct kvm *kvm)
 	int idx, bkt;
 
 	idx = srcu_read_lock(&kvm->srcu);
-	spin_lock(&kvm->mmu_lock);
+	write_lock(&kvm->mmu_lock);
 
 	slots = kvm_memslots(kvm);
 	kvm_for_each_memslot(memslot, bkt, slots)
 		stage2_flush_memslot(kvm, memslot);
 
-	spin_unlock(&kvm->mmu_lock);
+	write_unlock(&kvm->mmu_lock);
 	srcu_read_unlock(&kvm->srcu, idx);
 }
 
@@ -615,7 +615,7 @@ static struct kvm_pgtable_mm_ops kvm_s2_mm_ops = {
 };
 
 /**
- * kvm_init_stage2_mmu - Initialise a S2 MMU strucrure
+ * kvm_init_stage2_mmu - Initialise a S2 MMU structure
  * @kvm:	The pointer to the KVM structure
  * @mmu:	The pointer to the s2 MMU structure
  *
@@ -653,7 +653,6 @@ int kvm_init_stage2_mmu(struct kvm *kvm, struct kvm_s2_mmu *mmu)
 
 	mmu->pgt = pgt;
 	mmu->pgd_phys = __pa(pgt->pgd);
-	WRITE_ONCE(mmu->vmid.vmid_gen, 0);
 	return 0;
 
 out_destroy_pgtable:
@@ -720,13 +719,13 @@ void stage2_unmap_vm(struct kvm *kvm)
 
 	idx = srcu_read_lock(&kvm->srcu);
 	mmap_read_lock(current->mm);
-	spin_lock(&kvm->mmu_lock);
+	write_lock(&kvm->mmu_lock);
 
 	slots = kvm_memslots(kvm);
 	kvm_for_each_memslot(memslot, bkt, slots)
 		stage2_unmap_memslot(kvm, memslot);
 
-	spin_unlock(&kvm->mmu_lock);
+	write_unlock(&kvm->mmu_lock);
 	mmap_read_unlock(current->mm);
 	srcu_read_unlock(&kvm->srcu, idx);
 }
@@ -736,14 +735,14 @@ void kvm_free_stage2_pgd(struct kvm_s2_mmu *mmu)
 	struct kvm *kvm = kvm_s2_mmu_to_kvm(mmu);
 	struct kvm_pgtable *pgt = NULL;
 
-	spin_lock(&kvm->mmu_lock);
+	write_lock(&kvm->mmu_lock);
 	pgt = mmu->pgt;
 	if (pgt) {
 		mmu->pgd_phys = 0;
 		mmu->pgt = NULL;
 		free_percpu(mmu->last_vcpu_ran);
 	}
-	spin_unlock(&kvm->mmu_lock);
+	write_unlock(&kvm->mmu_lock);
 
 	if (pgt) {
 		kvm_pgtable_stage2_destroy(pgt);
@@ -783,10 +782,10 @@ int kvm_phys_addr_ioremap(struct kvm *kvm, phys_addr_t guest_ipa,
 		if (ret)
 			break;
 
-		spin_lock(&kvm->mmu_lock);
+		write_lock(&kvm->mmu_lock);
 		ret = kvm_pgtable_stage2_map(pgt, addr, PAGE_SIZE, pa, prot,
 					     &cache);
-		spin_unlock(&kvm->mmu_lock);
+		write_unlock(&kvm->mmu_lock);
 		if (ret)
 			break;
 
@@ -834,9 +833,9 @@ static void kvm_mmu_wp_memory_region(struct kvm *kvm, int slot)
 	start = memslot->base_gfn << PAGE_SHIFT;
 	end = (memslot->base_gfn + memslot->npages) << PAGE_SHIFT;
 
-	spin_lock(&kvm->mmu_lock);
+	write_lock(&kvm->mmu_lock);
 	stage2_wp_range(&kvm->arch.mmu, start, end);
-	spin_unlock(&kvm->mmu_lock);
+	write_unlock(&kvm->mmu_lock);
 	kvm_flush_remote_tlbs(kvm);
 }
 
@@ -1080,6 +1079,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	gfn_t gfn;
 	kvm_pfn_t pfn;
 	bool logging_active = memslot_is_logging(memslot);
+	bool logging_perm_fault = false;
 	unsigned long fault_level = kvm_vcpu_trap_get_fault_level(vcpu);
 	unsigned long vma_pagesize, fault_granule;
 	enum kvm_pgtable_prot prot = KVM_PGTABLE_PROT_R;
@@ -1114,6 +1114,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	if (logging_active) {
 		force_pte = true;
 		vma_shift = PAGE_SHIFT;
+		logging_perm_fault = (fault_status == FSC_PERM && write_fault);
 	} else {
 		vma_shift = get_vma_page_shift(vma, hva);
 	}
@@ -1212,7 +1213,15 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	if (exec_fault && device)
 		return -ENOEXEC;
 
-	spin_lock(&kvm->mmu_lock);
+	/*
+	 * To reduce MMU contentions and enhance concurrency during dirty
+	 * logging dirty logging, only acquire read lock for permission
+	 * relaxation.
+	 */
+	if (logging_perm_fault)
+		read_lock(&kvm->mmu_lock);
+	else
+		write_lock(&kvm->mmu_lock);
 	pgt = vcpu->arch.hw_mmu->pgt;
 	if (mmu_notifier_retry(kvm, mmu_seq))
 		goto out_unlock;
@@ -1271,7 +1280,10 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	}
 
 out_unlock:
-	spin_unlock(&kvm->mmu_lock);
+	if (logging_perm_fault)
+		read_unlock(&kvm->mmu_lock);
+	else
+		write_unlock(&kvm->mmu_lock);
 	kvm_set_pfn_accessed(pfn);
 	kvm_release_pfn_clean(pfn);
 	return ret != -EAGAIN ? ret : 0;
@@ -1286,10 +1298,10 @@ static void handle_access_fault(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa)
 
 	trace_kvm_access_fault(fault_ipa);
 
-	spin_lock(&vcpu->kvm->mmu_lock);
+	write_lock(&vcpu->kvm->mmu_lock);
 	mmu = vcpu->arch.hw_mmu;
 	kpte = kvm_pgtable_stage2_mkyoung(mmu->pgt, fault_ipa);
-	spin_unlock(&vcpu->kvm->mmu_lock);
+	write_unlock(&vcpu->kvm->mmu_lock);
 
 	pte = __pte(kpte);
 	if (pte_valid(pte))
@@ -1692,9 +1704,9 @@ void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
 	gpa_t gpa = slot->base_gfn << PAGE_SHIFT;
 	phys_addr_t size = slot->npages << PAGE_SHIFT;
 
-	spin_lock(&kvm->mmu_lock);
+	write_lock(&kvm->mmu_lock);
 	unmap_stage2_range(&kvm->arch.mmu, gpa, size);
-	spin_unlock(&kvm->mmu_lock);
+	write_unlock(&kvm->mmu_lock);
 }
 
 /*

arch/arm64/kvm/pmu-emul.c

@@ -7,6 +7,7 @@
 #include <linux/cpu.h>
 #include <linux/kvm.h>
 #include <linux/kvm_host.h>
+#include <linux/list.h>
 #include <linux/perf_event.h>
 #include <linux/perf/arm_pmu.h>
 #include <linux/uaccess.h>
@@ -16,6 +17,9 @@
 
 DEFINE_STATIC_KEY_FALSE(kvm_arm_pmu_available);
 
+static LIST_HEAD(arm_pmus);
+static DEFINE_MUTEX(arm_pmus_lock);
+
 static void kvm_pmu_create_perf_event(struct kvm_vcpu *vcpu, u64 select_idx);
 static void kvm_pmu_update_pmc_chained(struct kvm_vcpu *vcpu, u64 select_idx);
 static void kvm_pmu_stop_counter(struct kvm_vcpu *vcpu, struct kvm_pmc *pmc);
@@ -24,7 +28,11 @@ static void kvm_pmu_stop_counter(struct kvm_vcpu *vcpu, struct kvm_pmc *pmc);
 
 static u32 kvm_pmu_event_mask(struct kvm *kvm)
 {
-	switch (kvm->arch.pmuver) {
+	unsigned int pmuver;
+
+	pmuver = kvm->arch.arm_pmu->pmuver;
+
+	switch (pmuver) {
 	case ID_AA64DFR0_PMUVER_8_0:
 		return GENMASK(9, 0);
 	case ID_AA64DFR0_PMUVER_8_1:
@@ -33,7 +41,7 @@ static u32 kvm_pmu_event_mask(struct kvm *kvm)
 	case ID_AA64DFR0_PMUVER_8_7:
 		return GENMASK(15, 0);
 	default:		/* Shouldn't be here, just for sanity */
-		WARN_ONCE(1, "Unknown PMU version %d\n", kvm->arch.pmuver);
+		WARN_ONCE(1, "Unknown PMU version %d\n", pmuver);
 		return 0;
 	}
 }
@@ -600,6 +608,7 @@ static bool kvm_pmu_counter_is_enabled(struct kvm_vcpu *vcpu, u64 select_idx)
  */
 static void kvm_pmu_create_perf_event(struct kvm_vcpu *vcpu, u64 select_idx)
 {
+	struct arm_pmu *arm_pmu = vcpu->kvm->arch.arm_pmu;
 	struct kvm_pmu *pmu = &vcpu->arch.pmu;
 	struct kvm_pmc *pmc;
 	struct perf_event *event;
@@ -636,7 +645,7 @@ static void kvm_pmu_create_perf_event(struct kvm_vcpu *vcpu, u64 select_idx)
 		return;
 
 	memset(&attr, 0, sizeof(struct perf_event_attr));
-	attr.type = PERF_TYPE_RAW;
+	attr.type = arm_pmu->pmu.type;
 	attr.size = sizeof(attr);
 	attr.pinned = 1;
 	attr.disabled = !kvm_pmu_counter_is_enabled(vcpu, pmc->idx);
@@ -745,17 +754,33 @@ void kvm_pmu_set_counter_event_type(struct kvm_vcpu *vcpu, u64 data,
 
 void kvm_host_pmu_init(struct arm_pmu *pmu)
 {
-	if (pmu->pmuver != 0 && pmu->pmuver != ID_AA64DFR0_PMUVER_IMP_DEF &&
-	    !kvm_arm_support_pmu_v3() && !is_protected_kvm_enabled())
+	struct arm_pmu_entry *entry;
+
+	if (pmu->pmuver == 0 || pmu->pmuver == ID_AA64DFR0_PMUVER_IMP_DEF ||
+	    is_protected_kvm_enabled())
+		return;
+
+	mutex_lock(&arm_pmus_lock);
+
+	entry = kmalloc(sizeof(*entry), GFP_KERNEL);
+	if (!entry)
+		goto out_unlock;
+
+	entry->arm_pmu = pmu;
+	list_add_tail(&entry->entry, &arm_pmus);
+
+	if (list_is_singular(&arm_pmus))
 		static_branch_enable(&kvm_arm_pmu_available);
+
+out_unlock:
+	mutex_unlock(&arm_pmus_lock);
 }
 
-static int kvm_pmu_probe_pmuver(void)
+static struct arm_pmu *kvm_pmu_probe_armpmu(void)
 {
 	struct perf_event_attr attr = { };
 	struct perf_event *event;
-	struct arm_pmu *pmu;
-	int pmuver = ID_AA64DFR0_PMUVER_IMP_DEF;
+	struct arm_pmu *pmu = NULL;
 
 	/*
 	 * Create a dummy event that only counts user cycles. As we'll never
@@ -780,19 +805,20 @@ static int kvm_pmu_probe_pmuver(void)
 	if (IS_ERR(event)) {
 		pr_err_once("kvm: pmu event creation failed %ld\n",
 			    PTR_ERR(event));
-		return ID_AA64DFR0_PMUVER_IMP_DEF;
+		return NULL;
 	}
 
 	if (event->pmu) {
 		pmu = to_arm_pmu(event->pmu);
-		if (pmu->pmuver)
-			pmuver = pmu->pmuver;
+		if (pmu->pmuver == 0 ||
+		    pmu->pmuver == ID_AA64DFR0_PMUVER_IMP_DEF)
+			pmu = NULL;
 	}
 
 	perf_event_disable(event);
 	perf_event_release_kernel(event);
 
-	return pmuver;
+	return pmu;
 }
 
 u64 kvm_pmu_get_pmceid(struct kvm_vcpu *vcpu, bool pmceid1)
@@ -810,7 +836,7 @@ u64 kvm_pmu_get_pmceid(struct kvm_vcpu *vcpu, bool pmceid1)
 		 * Don't advertise STALL_SLOT, as PMMIR_EL0 is handled
 		 * as RAZ
 		 */
-		if (vcpu->kvm->arch.pmuver >= ID_AA64DFR0_PMUVER_8_4)
+		if (vcpu->kvm->arch.arm_pmu->pmuver >= ID_AA64DFR0_PMUVER_8_4)
 			val &= ~BIT_ULL(ARMV8_PMUV3_PERFCTR_STALL_SLOT - 32);
 		base = 32;
 	}
@@ -922,26 +948,64 @@ static bool pmu_irq_is_valid(struct kvm *kvm, int irq)
 	return true;
 }
 
+static int kvm_arm_pmu_v3_set_pmu(struct kvm_vcpu *vcpu, int pmu_id)
+{
+	struct kvm *kvm = vcpu->kvm;
+	struct arm_pmu_entry *entry;
+	struct arm_pmu *arm_pmu;
+	int ret = -ENXIO;
+
+	mutex_lock(&kvm->lock);
+	mutex_lock(&arm_pmus_lock);
+
+	list_for_each_entry(entry, &arm_pmus, entry) {
+		arm_pmu = entry->arm_pmu;
+		if (arm_pmu->pmu.type == pmu_id) {
+			if (test_bit(KVM_ARCH_FLAG_HAS_RAN_ONCE, &kvm->arch.flags) ||
+			    (kvm->arch.pmu_filter && kvm->arch.arm_pmu != arm_pmu)) {
+				ret = -EBUSY;
+				break;
+			}
+
+			kvm->arch.arm_pmu = arm_pmu;
+			cpumask_copy(kvm->arch.supported_cpus, &arm_pmu->supported_cpus);
+			ret = 0;
+			break;
+		}
+	}
+
+	mutex_unlock(&arm_pmus_lock);
+	mutex_unlock(&kvm->lock);
+	return ret;
+}
+
 int kvm_arm_pmu_v3_set_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr)
 {
+	struct kvm *kvm = vcpu->kvm;
+
 	if (!kvm_vcpu_has_pmu(vcpu))
 		return -ENODEV;
 
 	if (vcpu->arch.pmu.created)
 		return -EBUSY;
 
-	if (!vcpu->kvm->arch.pmuver)
-		vcpu->kvm->arch.pmuver = kvm_pmu_probe_pmuver();
-
-	if (vcpu->kvm->arch.pmuver == ID_AA64DFR0_PMUVER_IMP_DEF)
-		return -ENODEV;
+	mutex_lock(&kvm->lock);
+	if (!kvm->arch.arm_pmu) {
+		/* No PMU set, get the default one */
+		kvm->arch.arm_pmu = kvm_pmu_probe_armpmu();
+		if (!kvm->arch.arm_pmu) {
+			mutex_unlock(&kvm->lock);
+			return -ENODEV;
+		}
+	}
+	mutex_unlock(&kvm->lock);
 
 	switch (attr->attr) {
 	case KVM_ARM_VCPU_PMU_V3_IRQ: {
 		int __user *uaddr = (int __user *)(long)attr->addr;
 		int irq;
 
-		if (!irqchip_in_kernel(vcpu->kvm))
+		if (!irqchip_in_kernel(kvm))
 			return -EINVAL;
 
 		if (get_user(irq, uaddr))
@@ -951,7 +1015,7 @@ int kvm_arm_pmu_v3_set_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr)
 		if (!(irq_is_ppi(irq) || irq_is_spi(irq)))
 			return -EINVAL;
 
-		if (!pmu_irq_is_valid(vcpu->kvm, irq))
+		if (!pmu_irq_is_valid(kvm, irq))
 			return -EINVAL;
 
 		if (kvm_arm_pmu_irq_initialized(vcpu))
@@ -966,7 +1030,7 @@ int kvm_arm_pmu_v3_set_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr)
 		struct kvm_pmu_event_filter filter;
 		int nr_events;
 
-		nr_events = kvm_pmu_event_mask(vcpu->kvm) + 1;
+		nr_events = kvm_pmu_event_mask(kvm) + 1;
 
 		uaddr = (struct kvm_pmu_event_filter __user *)(long)attr->addr;
 
@@ -978,12 +1042,17 @@ int kvm_arm_pmu_v3_set_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr)
 		     filter.action != KVM_PMU_EVENT_DENY))
 			return -EINVAL;
 
-		mutex_lock(&vcpu->kvm->lock);
+		mutex_lock(&kvm->lock);
 
-		if (!vcpu->kvm->arch.pmu_filter) {
-			vcpu->kvm->arch.pmu_filter = bitmap_alloc(nr_events, GFP_KERNEL_ACCOUNT);
-			if (!vcpu->kvm->arch.pmu_filter) {
-				mutex_unlock(&vcpu->kvm->lock);
+		if (test_bit(KVM_ARCH_FLAG_HAS_RAN_ONCE, &kvm->arch.flags)) {
+			mutex_unlock(&kvm->lock);
+			return -EBUSY;
+		}
+
+		if (!kvm->arch.pmu_filter) {
+			kvm->arch.pmu_filter = bitmap_alloc(nr_events, GFP_KERNEL_ACCOUNT);
+			if (!kvm->arch.pmu_filter) {
+				mutex_unlock(&kvm->lock);
 				return -ENOMEM;
 			}
 
@@ -994,20 +1063,29 @@ int kvm_arm_pmu_v3_set_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr)
 			 * events, the default is to allow.
 			 */
 			if (filter.action == KVM_PMU_EVENT_ALLOW)
-				bitmap_zero(vcpu->kvm->arch.pmu_filter, nr_events);
+				bitmap_zero(kvm->arch.pmu_filter, nr_events);
 			else
-				bitmap_fill(vcpu->kvm->arch.pmu_filter, nr_events);
+				bitmap_fill(kvm->arch.pmu_filter, nr_events);
 		}
 
 		if (filter.action == KVM_PMU_EVENT_ALLOW)
-			bitmap_set(vcpu->kvm->arch.pmu_filter, filter.base_event, filter.nevents);
+			bitmap_set(kvm->arch.pmu_filter, filter.base_event, filter.nevents);
 		else
-			bitmap_clear(vcpu->kvm->arch.pmu_filter, filter.base_event, filter.nevents);
+			bitmap_clear(kvm->arch.pmu_filter, filter.base_event, filter.nevents);
 
-		mutex_unlock(&vcpu->kvm->lock);
+		mutex_unlock(&kvm->lock);
 
 		return 0;
 	}
+	case KVM_ARM_VCPU_PMU_V3_SET_PMU: {
+		int __user *uaddr = (int __user *)(long)attr->addr;
+		int pmu_id;
+
+		if (get_user(pmu_id, uaddr))
+			return -EFAULT;
+
+		return kvm_arm_pmu_v3_set_pmu(vcpu, pmu_id);
+	}
 	case KVM_ARM_VCPU_PMU_V3_INIT:
 		return kvm_arm_pmu_v3_init(vcpu);
 	}
@@ -1045,6 +1123,7 @@ int kvm_arm_pmu_v3_has_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr)
 	case KVM_ARM_VCPU_PMU_V3_IRQ:
 	case KVM_ARM_VCPU_PMU_V3_INIT:
 	case KVM_ARM_VCPU_PMU_V3_FILTER:
+	case KVM_ARM_VCPU_PMU_V3_SET_PMU:
 		if (kvm_vcpu_has_pmu(vcpu))
 			return 0;
 	}

arch/arm64/kvm/psci.c

@@ -84,7 +84,7 @@ static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu)
 	if (!vcpu)
 		return PSCI_RET_INVALID_PARAMS;
 	if (!vcpu->arch.power_off) {
-		if (kvm_psci_version(source_vcpu, kvm) != KVM_ARM_PSCI_0_1)
+		if (kvm_psci_version(source_vcpu) != KVM_ARM_PSCI_0_1)
 			return PSCI_RET_ALREADY_ON;
 		else
 			return PSCI_RET_INVALID_PARAMS;
@@ -161,7 +161,7 @@ static unsigned long kvm_psci_vcpu_affinity_info(struct kvm_vcpu *vcpu)
 	return PSCI_0_2_AFFINITY_LEVEL_OFF;
 }
 
-static void kvm_prepare_system_event(struct kvm_vcpu *vcpu, u32 type)
+static void kvm_prepare_system_event(struct kvm_vcpu *vcpu, u32 type, u64 flags)
 {
 	unsigned long i;
 	struct kvm_vcpu *tmp;
@@ -181,17 +181,24 @@ static void kvm_prepare_system_event(struct kvm_vcpu *vcpu, u32 type)
 
 	memset(&vcpu->run->system_event, 0, sizeof(vcpu->run->system_event));
 	vcpu->run->system_event.type = type;
+	vcpu->run->system_event.flags = flags;
 	vcpu->run->exit_reason = KVM_EXIT_SYSTEM_EVENT;
 }
 
 static void kvm_psci_system_off(struct kvm_vcpu *vcpu)
 {
-	kvm_prepare_system_event(vcpu, KVM_SYSTEM_EVENT_SHUTDOWN);
+	kvm_prepare_system_event(vcpu, KVM_SYSTEM_EVENT_SHUTDOWN, 0);
 }
 
 static void kvm_psci_system_reset(struct kvm_vcpu *vcpu)
 {
-	kvm_prepare_system_event(vcpu, KVM_SYSTEM_EVENT_RESET);
+	kvm_prepare_system_event(vcpu, KVM_SYSTEM_EVENT_RESET, 0);
+}
+
+static void kvm_psci_system_reset2(struct kvm_vcpu *vcpu)
+{
+	kvm_prepare_system_event(vcpu, KVM_SYSTEM_EVENT_RESET,
+				 KVM_SYSTEM_EVENT_RESET_FLAG_PSCI_RESET2);
 }
 
 static void kvm_psci_narrow_to_32bit(struct kvm_vcpu *vcpu)
@@ -304,24 +311,27 @@ static int kvm_psci_0_2_call(struct kvm_vcpu *vcpu)
 	return ret;
 }
 
-static int kvm_psci_1_0_call(struct kvm_vcpu *vcpu)
+static int kvm_psci_1_x_call(struct kvm_vcpu *vcpu, u32 minor)
 {
 	u32 psci_fn = smccc_get_function(vcpu);
-	u32 feature;
+	u32 arg;
 	unsigned long val;
 	int ret = 1;
 
+	if (minor > 1)
+		return -EINVAL;
+
 	switch(psci_fn) {
 	case PSCI_0_2_FN_PSCI_VERSION:
-		val = KVM_ARM_PSCI_1_0;
+		val = minor == 0 ? KVM_ARM_PSCI_1_0 : KVM_ARM_PSCI_1_1;
 		break;
 	case PSCI_1_0_FN_PSCI_FEATURES:
-		feature = smccc_get_arg1(vcpu);
-		val = kvm_psci_check_allowed_function(vcpu, feature);
+		arg = smccc_get_arg1(vcpu);
+		val = kvm_psci_check_allowed_function(vcpu, arg);
 		if (val)
 			break;
 
-		switch(feature) {
+		switch(arg) {
 		case PSCI_0_2_FN_PSCI_VERSION:
 		case PSCI_0_2_FN_CPU_SUSPEND:
 		case PSCI_0_2_FN64_CPU_SUSPEND:
@@ -337,11 +347,36 @@ static int kvm_psci_1_0_call(struct kvm_vcpu *vcpu)
 		case ARM_SMCCC_VERSION_FUNC_ID:
 			val = 0;
 			break;
+		case PSCI_1_1_FN_SYSTEM_RESET2:
+		case PSCI_1_1_FN64_SYSTEM_RESET2:
+			if (minor >= 1) {
+				val = 0;
+				break;
+			}
+			fallthrough;
 		default:
 			val = PSCI_RET_NOT_SUPPORTED;
 			break;
 		}
 		break;
+	case PSCI_1_1_FN_SYSTEM_RESET2:
+		kvm_psci_narrow_to_32bit(vcpu);
+		fallthrough;
+	case PSCI_1_1_FN64_SYSTEM_RESET2:
+		if (minor >= 1) {
+			arg = smccc_get_arg1(vcpu);
+
+			if (arg <= PSCI_1_1_RESET_TYPE_SYSTEM_WARM_RESET ||
+			    arg >= PSCI_1_1_RESET_TYPE_VENDOR_START) {
+				kvm_psci_system_reset2(vcpu);
+				vcpu_set_reg(vcpu, 0, PSCI_RET_INTERNAL_FAILURE);
+				return 0;
+			}
+
+			val = PSCI_RET_INVALID_PARAMS;
+			break;
+		}
+		fallthrough;
 	default:
 		return kvm_psci_0_2_call(vcpu);
 	}
@@ -391,16 +426,18 @@ static int kvm_psci_0_1_call(struct kvm_vcpu *vcpu)
  */
 int kvm_psci_call(struct kvm_vcpu *vcpu)
 {
-	switch (kvm_psci_version(vcpu, vcpu->kvm)) {
+	switch (kvm_psci_version(vcpu)) {
+	case KVM_ARM_PSCI_1_1:
+		return kvm_psci_1_x_call(vcpu, 1);
 	case KVM_ARM_PSCI_1_0:
-		return kvm_psci_1_0_call(vcpu);
+		return kvm_psci_1_x_call(vcpu, 0);
 	case KVM_ARM_PSCI_0_2:
 		return kvm_psci_0_2_call(vcpu);
 	case KVM_ARM_PSCI_0_1:
 		return kvm_psci_0_1_call(vcpu);
 	default:
 		return -EINVAL;
-	};
+	}
 }
 
 int kvm_arm_get_fw_num_regs(struct kvm_vcpu *vcpu)
@@ -470,7 +507,7 @@ int kvm_arm_get_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 
 	switch (reg->id) {
 	case KVM_REG_ARM_PSCI_VERSION:
-		val = kvm_psci_version(vcpu, vcpu->kvm);
+		val = kvm_psci_version(vcpu);
 		break;
 	case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1:
 	case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2:
@@ -510,6 +547,7 @@ int kvm_arm_set_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 			return 0;
 		case KVM_ARM_PSCI_0_2:
 		case KVM_ARM_PSCI_1_0:
+		case KVM_ARM_PSCI_1_1:
 			if (!wants_02)
 				return -EINVAL;
 			vcpu->kvm->arch.psci_version = val;

arch/arm64/kvm/sys_regs.c

@@ -44,6 +44,10 @@
  * 64bit interface.
  */
 
+static int reg_from_user(u64 *val, const void __user *uaddr, u64 id);
+static int reg_to_user(void __user *uaddr, const u64 *val, u64 id);
+static u64 sys_reg_to_index(const struct sys_reg_desc *reg);
+
 static bool read_from_write_only(struct kvm_vcpu *vcpu,
 				 struct sys_reg_params *params,
 				 const struct sys_reg_desc *r)
@@ -287,16 +291,55 @@ static bool trap_loregion(struct kvm_vcpu *vcpu,
 	return trap_raz_wi(vcpu, p, r);
 }
 
+static bool trap_oslar_el1(struct kvm_vcpu *vcpu,
+			   struct sys_reg_params *p,
+			   const struct sys_reg_desc *r)
+{
+	u64 oslsr;
+
+	if (!p->is_write)
+		return read_from_write_only(vcpu, p, r);
+
+	/* Forward the OSLK bit to OSLSR */
+	oslsr = __vcpu_sys_reg(vcpu, OSLSR_EL1) & ~SYS_OSLSR_OSLK;
+	if (p->regval & SYS_OSLAR_OSLK)
+		oslsr |= SYS_OSLSR_OSLK;
+
+	__vcpu_sys_reg(vcpu, OSLSR_EL1) = oslsr;
+	return true;
+}
+
 static bool trap_oslsr_el1(struct kvm_vcpu *vcpu,
 			   struct sys_reg_params *p,
 			   const struct sys_reg_desc *r)
 {
-	if (p->is_write) {
-		return ignore_write(vcpu, p);
-	} else {
-		p->regval = (1 << 3);
-		return true;
-	}
+	if (p->is_write)
+		return write_to_read_only(vcpu, p, r);
+
+	p->regval = __vcpu_sys_reg(vcpu, r->reg);
+	return true;
+}
+
+static int set_oslsr_el1(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd,
+			 const struct kvm_one_reg *reg, void __user *uaddr)
+{
+	u64 id = sys_reg_to_index(rd);
+	u64 val;
+	int err;
+
+	err = reg_from_user(&val, uaddr, id);
+	if (err)
+		return err;
+
+	/*
+	 * The only modifiable bit is the OSLK bit. Refuse the write if
+	 * userspace attempts to change any other bit in the register.
+	 */
+	if ((val ^ rd->val) & ~SYS_OSLSR_OSLK)
+		return -EINVAL;
+
+	__vcpu_sys_reg(vcpu, rd->reg) = val;
+	return 0;
 }
 
 static bool trap_dbgauthstatus_el1(struct kvm_vcpu *vcpu,
@@ -1164,10 +1207,6 @@ static bool access_raz_id_reg(struct kvm_vcpu *vcpu,
 	return __access_id_reg(vcpu, p, r, true);
 }
 
-static int reg_from_user(u64 *val, const void __user *uaddr, u64 id);
-static int reg_to_user(void __user *uaddr, const u64 *val, u64 id);
-static u64 sys_reg_to_index(const struct sys_reg_desc *reg);
-
 /* Visibility overrides for SVE-specific control registers */
 static unsigned int sve_visibility(const struct kvm_vcpu *vcpu,
 				   const struct sys_reg_desc *rd)
@@ -1418,9 +1457,9 @@ static unsigned int mte_visibility(const struct kvm_vcpu *vcpu,
  * Debug handling: We do trap most, if not all debug related system
  * registers. The implementation is good enough to ensure that a guest
  * can use these with minimal performance degradation. The drawback is
- * that we don't implement any of the external debug, none of the
- * OSlock protocol. This should be revisited if we ever encounter a
- * more demanding guest...
+ * that we don't implement any of the external debug architecture.
+ * This should be revisited if we ever encounter a more demanding
+ * guest...
  */
 static const struct sys_reg_desc sys_reg_descs[] = {
 	{ SYS_DESC(SYS_DC_ISW), access_dcsw },
@@ -1447,8 +1486,9 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	DBG_BCR_BVR_WCR_WVR_EL1(15),
 
 	{ SYS_DESC(SYS_MDRAR_EL1), trap_raz_wi },
-	{ SYS_DESC(SYS_OSLAR_EL1), trap_raz_wi },
-	{ SYS_DESC(SYS_OSLSR_EL1), trap_oslsr_el1 },
+	{ SYS_DESC(SYS_OSLAR_EL1), trap_oslar_el1 },
+	{ SYS_DESC(SYS_OSLSR_EL1), trap_oslsr_el1, reset_val, OSLSR_EL1,
+		SYS_OSLSR_OSLM_IMPLEMENTED, .set_user = set_oslsr_el1, },
 	{ SYS_DESC(SYS_OSDLR_EL1), trap_raz_wi },
 	{ SYS_DESC(SYS_DBGPRCR_EL1), trap_raz_wi },
 	{ SYS_DESC(SYS_DBGCLAIMSET_EL1), trap_raz_wi },
@@ -1920,10 +1960,10 @@ static const struct sys_reg_desc cp14_regs[] = {
 
 	DBGBXVR(0),
 	/* DBGOSLAR */
-	{ Op1( 0), CRn( 1), CRm( 0), Op2( 4), trap_raz_wi },
+	{ Op1( 0), CRn( 1), CRm( 0), Op2( 4), trap_oslar_el1 },
 	DBGBXVR(1),
 	/* DBGOSLSR */
-	{ Op1( 0), CRn( 1), CRm( 1), Op2( 4), trap_oslsr_el1 },
+	{ Op1( 0), CRn( 1), CRm( 1), Op2( 4), trap_oslsr_el1, NULL, OSLSR_EL1 },
 	DBGBXVR(2),
 	DBGBXVR(3),
 	/* DBGOSDLR */

arch/arm64/kvm/vgic/vgic.c

@@ -37,7 +37,7 @@ struct vgic_global kvm_vgic_global_state __ro_after_init = {
  * If you need to take multiple locks, always take the upper lock first,
  * then the lower ones, e.g. first take the its_lock, then the irq_lock.
  * If you are already holding a lock and need to take a higher one, you
- * have to drop the lower ranking lock first and re-aquire it after having
+ * have to drop the lower ranking lock first and re-acquire it after having
  * taken the upper one.
  *
  * When taking more than one ap_list_lock at the same time, always take the

arch/arm64/kvm/vmid.c

+// SPDX-License-Identifier: GPL-2.0
+/*
+ * VMID allocator.
+ *
+ * Based on Arm64 ASID allocator algorithm.
+ * Please refer arch/arm64/mm/context.c for detailed
+ * comments on algorithm.
+ *
+ * Copyright (C) 2002-2003 Deep Blue Solutions Ltd, all rights reserved.
+ * Copyright (C) 2012 ARM Ltd.
+ */
+
+#include <linux/bitfield.h>
+#include <linux/bitops.h>
+
+#include <asm/kvm_asm.h>
+#include <asm/kvm_mmu.h>
+
+unsigned int kvm_arm_vmid_bits;
+static DEFINE_RAW_SPINLOCK(cpu_vmid_lock);
+
+static atomic64_t vmid_generation;
+static unsigned long *vmid_map;
+
+static DEFINE_PER_CPU(atomic64_t, active_vmids);
+static DEFINE_PER_CPU(u64, reserved_vmids);
+
+#define VMID_MASK		(~GENMASK(kvm_arm_vmid_bits - 1, 0))
+#define VMID_FIRST_VERSION	(1UL << kvm_arm_vmid_bits)
+
+#define NUM_USER_VMIDS		VMID_FIRST_VERSION
+#define vmid2idx(vmid)		((vmid) & ~VMID_MASK)
+#define idx2vmid(idx)		vmid2idx(idx)
+
+/*
+ * As vmid #0 is always reserved, we will never allocate one
+ * as below and can be treated as invalid. This is used to
+ * set the active_vmids on vCPU schedule out.
+ */
+#define VMID_ACTIVE_INVALID		VMID_FIRST_VERSION
+
+#define vmid_gen_match(vmid) \
+	(!(((vmid) ^ atomic64_read(&vmid_generation)) >> kvm_arm_vmid_bits))
+
+static void flush_context(void)
+{
+	int cpu;
+	u64 vmid;
+
+	bitmap_clear(vmid_map, 0, NUM_USER_VMIDS);
+
+	for_each_possible_cpu(cpu) {
+		vmid = atomic64_xchg_relaxed(&per_cpu(active_vmids, cpu), 0);
+
+		/* Preserve reserved VMID */
+		if (vmid == 0)
+			vmid = per_cpu(reserved_vmids, cpu);
+		__set_bit(vmid2idx(vmid), vmid_map);
+		per_cpu(reserved_vmids, cpu) = vmid;
+	}
+
+	/*
+	 * Unlike ASID allocator, we expect less frequent rollover in
+	 * case of VMIDs. Hence, instead of marking the CPU as
+	 * flush_pending and issuing a local context invalidation on
+	 * the next context-switch, we broadcast TLB flush + I-cache
+	 * invalidation over the inner shareable domain on rollover.
+	 */
+	 kvm_call_hyp(__kvm_flush_vm_context);
+}
+
+static bool check_update_reserved_vmid(u64 vmid, u64 newvmid)
+{
+	int cpu;
+	bool hit = false;
+
+	/*
+	 * Iterate over the set of reserved VMIDs looking for a match
+	 * and update to use newvmid (i.e. the same VMID in the current
+	 * generation).
+	 */
+	for_each_possible_cpu(cpu) {
+		if (per_cpu(reserved_vmids, cpu) == vmid) {
+			hit = true;
+			per_cpu(reserved_vmids, cpu) = newvmid;
+		}
+	}
+
+	return hit;
+}
+
+static u64 new_vmid(struct kvm_vmid *kvm_vmid)
+{
+	static u32 cur_idx = 1;
+	u64 vmid = atomic64_read(&kvm_vmid->id);
+	u64 generation = atomic64_read(&vmid_generation);
+
+	if (vmid != 0) {
+		u64 newvmid = generation | (vmid & ~VMID_MASK);
+
+		if (check_update_reserved_vmid(vmid, newvmid)) {
+			atomic64_set(&kvm_vmid->id, newvmid);
+			return newvmid;
+		}
+
+		if (!__test_and_set_bit(vmid2idx(vmid), vmid_map)) {
+			atomic64_set(&kvm_vmid->id, newvmid);
+			return newvmid;
+		}
+	}
+
+	vmid = find_next_zero_bit(vmid_map, NUM_USER_VMIDS, cur_idx);
+	if (vmid != NUM_USER_VMIDS)
+		goto set_vmid;
+
+	/* We're out of VMIDs, so increment the global generation count */
+	generation = atomic64_add_return_relaxed(VMID_FIRST_VERSION,
+						 &vmid_generation);
+	flush_context();
+
+	/* We have more VMIDs than CPUs, so this will always succeed */
+	vmid = find_next_zero_bit(vmid_map, NUM_USER_VMIDS, 1);
+
+set_vmid:
+	__set_bit(vmid, vmid_map);
+	cur_idx = vmid;
+	vmid = idx2vmid(vmid) | generation;
+	atomic64_set(&kvm_vmid->id, vmid);
+	return vmid;
+}
+
+/* Called from vCPU sched out with preemption disabled */
+void kvm_arm_vmid_clear_active(void)
+{
+	atomic64_set(this_cpu_ptr(&active_vmids), VMID_ACTIVE_INVALID);
+}
+
+void kvm_arm_vmid_update(struct kvm_vmid *kvm_vmid)
+{
+	unsigned long flags;
+	u64 vmid, old_active_vmid;
+
+	vmid = atomic64_read(&kvm_vmid->id);
+
+	/*
+	 * Please refer comments in check_and_switch_context() in
+	 * arch/arm64/mm/context.c.
+	 *
+	 * Unlike ASID allocator, we set the active_vmids to
+	 * VMID_ACTIVE_INVALID on vCPU schedule out to avoid
+	 * reserving the VMID space needlessly on rollover.
+	 * Hence explicitly check here for a "!= 0" to
+	 * handle the sync with a concurrent rollover.
+	 */
+	old_active_vmid = atomic64_read(this_cpu_ptr(&active_vmids));
+	if (old_active_vmid != 0 && vmid_gen_match(vmid) &&
+	    0 != atomic64_cmpxchg_relaxed(this_cpu_ptr(&active_vmids),
+					  old_active_vmid, vmid))
+		return;
+
+	raw_spin_lock_irqsave(&cpu_vmid_lock, flags);
+
+	/* Check that our VMID belongs to the current generation. */
+	vmid = atomic64_read(&kvm_vmid->id);
+	if (!vmid_gen_match(vmid))
+		vmid = new_vmid(kvm_vmid);
+
+	atomic64_set(this_cpu_ptr(&active_vmids), vmid);
+	raw_spin_unlock_irqrestore(&cpu_vmid_lock, flags);
+}
+
+/*
+ * Initialize the VMID allocator
+ */
+int kvm_arm_vmid_alloc_init(void)
+{
+	kvm_arm_vmid_bits = kvm_get_vmid_bits();
+
+	/*
+	 * Expect allocation after rollover to fail if we don't have
+	 * at least one more VMID than CPUs. VMID #0 is always reserved.
+	 */
+	WARN_ON(NUM_USER_VMIDS - 1 <= num_possible_cpus());
+	atomic64_set(&vmid_generation, VMID_FIRST_VERSION);
+	vmid_map = kcalloc(BITS_TO_LONGS(NUM_USER_VMIDS),
+			   sizeof(*vmid_map), GFP_KERNEL);
+	if (!vmid_map)
+		return -ENOMEM;
+
+	return 0;
+}
+
+void kvm_arm_vmid_alloc_free(void)
+{
+	kfree(vmid_map);
+}

include/kvm/arm_pmu.h

@@ -29,6 +29,11 @@ struct kvm_pmu {
 	struct irq_work overflow_work;
 };
 
+struct arm_pmu_entry {
+	struct list_head entry;
+	struct arm_pmu *arm_pmu;
+};
+
 DECLARE_STATIC_KEY_FALSE(kvm_arm_pmu_available);
 
 static __always_inline bool kvm_arm_support_pmu_v3(void)

include/kvm/arm_psci.h

@@ -13,14 +13,11 @@
 #define KVM_ARM_PSCI_0_1	PSCI_VERSION(0, 1)
 #define KVM_ARM_PSCI_0_2	PSCI_VERSION(0, 2)
 #define KVM_ARM_PSCI_1_0	PSCI_VERSION(1, 0)
+#define KVM_ARM_PSCI_1_1	PSCI_VERSION(1, 1)
 
-#define KVM_ARM_PSCI_LATEST	KVM_ARM_PSCI_1_0
+#define KVM_ARM_PSCI_LATEST	KVM_ARM_PSCI_1_1
 
-/*
- * We need the KVM pointer independently from the vcpu as we can call
- * this from HYP, and need to apply kern_hyp_va on it...
- */
-static inline int kvm_psci_version(struct kvm_vcpu *vcpu, struct kvm *kvm)
+static inline int kvm_psci_version(struct kvm_vcpu *vcpu)
 {
 	/*
 	 * Our PSCI implementation stays the same across versions from

include/linux/perf_event.h

@@ -864,7 +864,7 @@ struct perf_event_context {
 #define PERF_NR_CONTEXTS	4
 
 /**
- * struct perf_event_cpu_context - per cpu event context structure
+ * struct perf_cpu_context - per cpu event context structure
  */
 struct perf_cpu_context {
 	struct perf_event_context	ctx;

include/uapi/linux/psci.h

@@ -82,6 +82,10 @@
 #define PSCI_0_2_TOS_UP_NO_MIGRATE		1
 #define PSCI_0_2_TOS_MP				2
 
+/* PSCI v1.1 reset type encoding for SYSTEM_RESET2 */
+#define PSCI_1_1_RESET_TYPE_SYSTEM_WARM_RESET	0
+#define PSCI_1_1_RESET_TYPE_VENDOR_START	0x80000000U
+
 /* PSCI version decoding (independent of PSCI version) */
 #define PSCI_VERSION_MAJOR_SHIFT		16
 #define PSCI_VERSION_MINOR_MASK			\

tools/arch/arm64/include/uapi/asm/kvm.h

@@ -362,6 +362,7 @@ struct kvm_arm_copy_mte_tags {
 #define   KVM_ARM_VCPU_PMU_V3_IRQ	0
 #define   KVM_ARM_VCPU_PMU_V3_INIT	1
 #define   KVM_ARM_VCPU_PMU_V3_FILTER	2
+#define   KVM_ARM_VCPU_PMU_V3_SET_PMU	3
 #define KVM_ARM_VCPU_TIMER_CTRL		1
 #define   KVM_ARM_VCPU_TIMER_IRQ_VTIMER		0
 #define   KVM_ARM_VCPU_TIMER_IRQ_PTIMER		1

tools/testing/selftests/kvm/aarch64/debug-exceptions.c

@@ -23,7 +23,7 @@
 #define SPSR_D		(1 << 9)
 #define SPSR_SS		(1 << 21)
 
-extern unsigned char sw_bp, hw_bp, bp_svc, bp_brk, hw_wp, ss_start;
+extern unsigned char sw_bp, sw_bp2, hw_bp, hw_bp2, bp_svc, bp_brk, hw_wp, ss_start;
 static volatile uint64_t sw_bp_addr, hw_bp_addr;
 static volatile uint64_t wp_addr, wp_data_addr;
 static volatile uint64_t svc_addr;
@@ -47,6 +47,14 @@ static void reset_debug_state(void)
 	isb();
 }
 
+static void enable_os_lock(void)
+{
+	write_sysreg(1, oslar_el1);
+	isb();
+
+	GUEST_ASSERT(read_sysreg(oslsr_el1) & 2);
+}
+
 static void install_wp(uint64_t addr)
 {
 	uint32_t wcr;
@@ -99,6 +107,7 @@ static void guest_code(void)
 	GUEST_SYNC(0);
 
 	/* Software-breakpoint */
+	reset_debug_state();
 	asm volatile("sw_bp: brk #0");
 	GUEST_ASSERT_EQ(sw_bp_addr, PC(sw_bp));
 
@@ -152,6 +161,51 @@ static void guest_code(void)
 	GUEST_ASSERT_EQ(ss_addr[1], PC(ss_start) + 4);
 	GUEST_ASSERT_EQ(ss_addr[2], PC(ss_start) + 8);
 
+	GUEST_SYNC(6);
+
+	/* OS Lock does not block software-breakpoint */
+	reset_debug_state();
+	enable_os_lock();
+	sw_bp_addr = 0;
+	asm volatile("sw_bp2: brk #0");
+	GUEST_ASSERT_EQ(sw_bp_addr, PC(sw_bp2));
+
+	GUEST_SYNC(7);
+
+	/* OS Lock blocking hardware-breakpoint */
+	reset_debug_state();
+	enable_os_lock();
+	install_hw_bp(PC(hw_bp2));
+	hw_bp_addr = 0;
+	asm volatile("hw_bp2: nop");
+	GUEST_ASSERT_EQ(hw_bp_addr, 0);
+
+	GUEST_SYNC(8);
+
+	/* OS Lock blocking watchpoint */
+	reset_debug_state();
+	enable_os_lock();
+	write_data = '\0';
+	wp_data_addr = 0;
+	install_wp(PC(write_data));
+	write_data = 'x';
+	GUEST_ASSERT_EQ(write_data, 'x');
+	GUEST_ASSERT_EQ(wp_data_addr, 0);
+
+	GUEST_SYNC(9);
+
+	/* OS Lock blocking single-step */
+	reset_debug_state();
+	enable_os_lock();
+	ss_addr[0] = 0;
+	install_ss();
+	ss_idx = 0;
+	asm volatile("mrs x0, esr_el1\n\t"
+		     "add x0, x0, #1\n\t"
+		     "msr daifset, #8\n\t"
+		     : : : "x0");
+	GUEST_ASSERT_EQ(ss_addr[0], 0);
+
 	GUEST_DONE();
 }
 
@@ -223,7 +277,7 @@ int main(int argc, char *argv[])
 	vm_install_sync_handler(vm, VECTOR_SYNC_CURRENT,
 				ESR_EC_SVC64, guest_svc_handler);
 
-	for (stage = 0; stage < 7; stage++) {
+	for (stage = 0; stage < 11; stage++) {
 		vcpu_run(vm, VCPU_ID);
 
 		switch (get_ucall(vm, VCPU_ID, &uc)) {

tools/testing/selftests/kvm/aarch64/get-reg-list.c

@@ -760,6 +760,7 @@ static __u64 base_regs[] = {
 	ARM64_SYS_REG(2, 0, 0, 15, 5),
 	ARM64_SYS_REG(2, 0, 0, 15, 6),
 	ARM64_SYS_REG(2, 0, 0, 15, 7),
+	ARM64_SYS_REG(2, 0, 1, 1, 4),	/* OSLSR_EL1 */
 	ARM64_SYS_REG(2, 4, 0, 7, 0),	/* DBGVCR32_EL2 */
 	ARM64_SYS_REG(3, 0, 0, 0, 5),	/* MPIDR_EL1 */
 	ARM64_SYS_REG(3, 0, 0, 1, 0),	/* ID_PFR0_EL1 */

tools/testing/selftests/kvm/aarch64/vgic_irq.c

@@ -306,7 +306,8 @@ static void guest_restore_active(struct test_args *args,
 	uint32_t prio, intid, ap1r;
 	int i;
 
-	/* Set the priorities of the first (KVM_NUM_PRIOS - 1) IRQs
+	/*
+	 * Set the priorities of the first (KVM_NUM_PRIOS - 1) IRQs
 	 * in descending order, so intid+1 can preempt intid.
 	 */
 	for (i = 0, prio = (num - 1) * 8; i < num; i++, prio -= 8) {
@@ -315,7 +316,8 @@ static void guest_restore_active(struct test_args *args,
 		gic_set_priority(intid, prio);
 	}
 
-	/* In a real migration, KVM would restore all GIC state before running
+	/*
+	 * In a real migration, KVM would restore all GIC state before running
 	 * guest code.
 	 */
 	for (i = 0; i < num; i++) {
@@ -472,10 +474,10 @@ static void test_restore_active(struct test_args *args, struct kvm_inject_desc *
 		guest_restore_active(args, MIN_SPI, 4, f->cmd);
 }
 
-static void guest_code(struct test_args args)
+static void guest_code(struct test_args *args)
 {
-	uint32_t i, nr_irqs = args.nr_irqs;
-	bool level_sensitive = args.level_sensitive;
+	uint32_t i, nr_irqs = args->nr_irqs;
+	bool level_sensitive = args->level_sensitive;
 	struct kvm_inject_desc *f, *inject_fns;
 
 	gic_init(GIC_V3, 1, dist, redist);
@@ -484,11 +486,11 @@ static void guest_code(struct test_args args)
 		gic_irq_enable(i);
 
 	for (i = MIN_SPI; i < nr_irqs; i++)
-		gic_irq_set_config(i, !args.level_sensitive);
+		gic_irq_set_config(i, !level_sensitive);
 
-	gic_set_eoi_split(args.eoi_split);
+	gic_set_eoi_split(args->eoi_split);
 
-	reset_priorities(&args);
+	reset_priorities(args);
 	gic_set_priority_mask(CPU_PRIO_MASK);
 
 	inject_fns  = level_sensitive ? inject_level_fns
@@ -497,17 +499,18 @@ static void guest_code(struct test_args args)
 	local_irq_enable();
 
 	/* Start the tests. */
-	for_each_supported_inject_fn(&args, inject_fns, f) {
-		test_injection(&args, f);
-		test_preemption(&args, f);
-		test_injection_failure(&args, f);
+	for_each_supported_inject_fn(args, inject_fns, f) {
+		test_injection(args, f);
+		test_preemption(args, f);
+		test_injection_failure(args, f);
 	}
 
-	/* Restore the active state of IRQs. This would happen when live
+	/*
+	 * Restore the active state of IRQs. This would happen when live
 	 * migrating IRQs in the middle of being handled.
 	 */
-	for_each_supported_activate_fn(&args, set_active_fns, f)
-		test_restore_active(&args, f);
+	for_each_supported_activate_fn(args, set_active_fns, f)
+		test_restore_active(args, f);
 
 	GUEST_DONE();
 }
@@ -573,8 +576,8 @@ static void kvm_set_gsi_routing_irqchip_check(struct kvm_vm *vm,
 		kvm_gsi_routing_write(vm, routing);
 	} else {
 		ret = _kvm_gsi_routing_write(vm, routing);
-		/* The kernel only checks for KVM_IRQCHIP_NUM_PINS. */
-		if (intid >= KVM_IRQCHIP_NUM_PINS)
+		/* The kernel only checks e->irqchip.pin >= KVM_IRQCHIP_NUM_PINS */
+		if (((uint64_t)intid + num - 1 - MIN_SPI) >= KVM_IRQCHIP_NUM_PINS)
 			TEST_ASSERT(ret != 0 && errno == EINVAL,
 				"Bad intid %u did not cause KVM_SET_GSI_ROUTING "
 				"error: rc: %i errno: %i", intid, ret, errno);
@@ -739,6 +742,7 @@ static void test_vgic(uint32_t nr_irqs, bool level_sensitive, bool eoi_split)
 	int gic_fd;
 	struct kvm_vm *vm;
 	struct kvm_inject_args inject_args;
+	vm_vaddr_t args_gva;
 
 	struct test_args args = {
 		.nr_irqs = nr_irqs,
@@ -757,7 +761,9 @@ static void test_vgic(uint32_t nr_irqs, bool level_sensitive, bool eoi_split)
 	vcpu_init_descriptor_tables(vm, VCPU_ID);
 
 	/* Setup the guest args page (so it gets the args). */
-	vcpu_args_set(vm, 0, 1, args);
+	args_gva = vm_vaddr_alloc_page(vm);
+	memcpy(addr_gva2hva(vm, args_gva), &args, sizeof(args));
+	vcpu_args_set(vm, 0, 1, args_gva);
 
 	gic_fd = vgic_v3_setup(vm, 1, nr_irqs,
 			GICD_BASE_GPA, GICR_BASE_GPA);
@@ -841,7 +847,8 @@ int main(int argc, char **argv)
 		}
 	}
 
-	/* If the user just specified nr_irqs and/or gic_version, then run all
+	/*
+	 * If the user just specified nr_irqs and/or gic_version, then run all
 	 * combinations.
 	 */
 	if (default_args) {

tools/testing/selftests/kvm/dirty_log_perf_test.c

@@ -18,6 +18,12 @@
 #include "test_util.h"
 #include "perf_test_util.h"
 #include "guest_modes.h"
+#ifdef __aarch64__
+#include "aarch64/vgic.h"
+
+#define GICD_BASE_GPA			0x8000000ULL
+#define GICR_BASE_GPA			0x80A0000ULL
+#endif
 
 /* How many host loops to run by default (one KVM_GET_DIRTY_LOG for each loop)*/
 #define TEST_HOST_LOOP_N		2UL
@@ -200,6 +206,10 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 		vm_enable_cap(vm, &cap);
 	}
 
+#ifdef __aarch64__
+	vgic_v3_setup(vm, nr_vcpus, 64, GICD_BASE_GPA, GICR_BASE_GPA);
+#endif
+
 	/* Start the iterations */
 	iteration = 0;
 	host_quit = false;

tools/testing/selftests/kvm/lib/aarch64/gic_v3.c

@@ -19,7 +19,7 @@ struct gicv3_data {
 	unsigned int nr_spis;
 };
 
-#define sgi_base_from_redist(redist_base) 	(redist_base + SZ_64K)
+#define sgi_base_from_redist(redist_base)	(redist_base + SZ_64K)
 #define DIST_BIT				(1U << 31)
 
 enum gicv3_intid_range {
@@ -105,7 +105,8 @@ static void gicv3_set_eoi_split(bool split)
 {
 	uint32_t val;
 
-	/* All other fields are read-only, so no need to read CTLR first. In
+	/*
+	 * All other fields are read-only, so no need to read CTLR first. In
 	 * fact, the kernel does the same.
 	 */
 	val = split ? (1U << 1) : 0;
@@ -159,9 +160,10 @@ static void gicv3_access_reg(uint32_t intid, uint64_t offset,
 	uint32_t cpu_or_dist;
 
 	GUEST_ASSERT(bits_per_field <= reg_bits);
-	GUEST_ASSERT(*val < (1U << bits_per_field));
-	/* Some registers like IROUTER are 64 bit long. Those are currently not
-	 * supported by readl nor writel, so just asserting here until then.
+	GUEST_ASSERT(!write || *val < (1U << bits_per_field));
+	/*
+	 * This function does not support 64 bit accesses. Just asserting here
+	 * until we implement readq/writeq.
 	 */
 	GUEST_ASSERT(reg_bits == 32);
 

tools/testing/selftests/kvm/lib/aarch64/vgic.c

@@ -140,9 +140,6 @@ static void vgic_poke_irq(int gic_fd, uint32_t intid,
 	uint64_t val;
 	bool intid_is_private = INTID_IS_SGI(intid) || INTID_IS_PPI(intid);
 
-	/* Check that the addr part of the attr is within 32 bits. */
-	assert(attr <= KVM_DEV_ARM_VGIC_OFFSET_MASK);
-
 	uint32_t group = intid_is_private ? KVM_DEV_ARM_VGIC_GRP_REDIST_REGS
 					  : KVM_DEV_ARM_VGIC_GRP_DIST_REGS;
 
@@ -152,7 +149,11 @@ static void vgic_poke_irq(int gic_fd, uint32_t intid,
 		attr += SZ_64K;
 	}
 
-	/* All calls will succeed, even with invalid intid's, as long as the
+	/* Check that the addr part of the attr is within 32 bits. */
+	assert((attr & ~KVM_DEV_ARM_VGIC_OFFSET_MASK) == 0);
+
+	/*
+	 * All calls will succeed, even with invalid intid's, as long as the
 	 * addr part of the attr is within 32 bits (checked above). An invalid
 	 * intid will just make the read/writes point to above the intended
 	 * register space (i.e., ICPENDR after ISPENDR).