Merge branch kvm/kvm-hw-enable-refactor into kvmarm/next

Merge the kvm_init() + hardware enable rework to avoid conflicts
with kvmarm.

Signed-off-by: Oliver Upton <oliver.upton@linux.dev>

10 files changed, 90 insertions, 103 deletions

diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 35a159d131b5..113e20fdbb56 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -66,8 +66,8 @@ enum kvm_mode kvm_get_mode(void);
 
 DECLARE_STATIC_KEY_FALSE(userspace_irqchip_in_use);
 
-extern unsigned int kvm_sve_max_vl;
-int kvm_arm_init_sve(void);
+extern unsigned int __ro_after_init kvm_sve_max_vl;
+int __init kvm_arm_init_sve(void);
 
 u32 __attribute_const__ kvm_target_cpu(void);
 int kvm_reset_vcpu(struct kvm_vcpu *vcpu);
@@ -877,7 +877,7 @@ int kvm_handle_cp10_id(struct kvm_vcpu *vcpu);
 
 void kvm_reset_sys_regs(struct kvm_vcpu *vcpu);
 
-int kvm_sys_reg_table_init(void);
+int __init kvm_sys_reg_table_init(void);
 
 /* MMIO helpers */
 void kvm_mmio_write_buf(void *buf, unsigned int len, unsigned long data);
@@ -908,9 +908,9 @@ 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);
+extern unsigned int __ro_after_init kvm_arm_vmid_bits;
+int __init kvm_arm_vmid_alloc_init(void);
+void __init kvm_arm_vmid_alloc_free(void);
 void kvm_arm_vmid_update(struct kvm_vmid *kvm_vmid);
 void kvm_arm_vmid_clear_active(void);
 
@@ -943,7 +943,6 @@ static inline bool kvm_system_needs_idmapped_vectors(void)
 
 void kvm_arm_vcpu_ptrauth_trap(struct kvm_vcpu *vcpu);
 
-static inline void kvm_arch_hardware_unsetup(void) {}
 static inline void kvm_arch_sync_events(struct kvm *kvm) {}
 static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) {}
 
@@ -994,7 +993,7 @@ static inline void kvm_clr_pmu_events(u32 clr) {}
 void kvm_vcpu_load_sysregs_vhe(struct kvm_vcpu *vcpu);
 void kvm_vcpu_put_sysregs_vhe(struct kvm_vcpu *vcpu);
 
-int kvm_set_ipa_limit(void);
+int __init kvm_set_ipa_limit(void);
 
 #define __KVM_HAVE_ARCH_VM_ALLOC
 struct kvm *kvm_arch_alloc_vm(void);
diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h
index e4a7e6369499..7f7c1231679e 100644
--- a/arch/arm64/include/asm/kvm_mmu.h
+++ b/arch/arm64/include/asm/kvm_mmu.h
@@ -163,7 +163,7 @@ int create_hyp_io_mappings(phys_addr_t phys_addr, size_t size,
 			   void __iomem **haddr);
 int create_hyp_exec_mappings(phys_addr_t phys_addr, size_t size,
 			     void **haddr);
-void free_hyp_pgds(void);
+void __init free_hyp_pgds(void);
 
 void stage2_unmap_vm(struct kvm *kvm);
 int kvm_init_stage2_mmu(struct kvm *kvm, struct kvm_s2_mmu *mmu, unsigned long type);
@@ -175,7 +175,7 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu);
 
 phys_addr_t kvm_mmu_get_httbr(void);
 phys_addr_t kvm_get_idmap_vector(void);
-int kvm_mmu_init(u32 *hyp_va_bits);
+int __init kvm_mmu_init(u32 *hyp_va_bits);
 
 static inline void *__kvm_vector_slot2addr(void *base,
 					   enum arm64_hyp_spectre_vector slot)
diff --git a/arch/arm64/kvm/Kconfig b/arch/arm64/kvm/Kconfig
index 05da3c8f7e88..ca6eadeb7d1a 100644
--- a/arch/arm64/kvm/Kconfig
+++ b/arch/arm64/kvm/Kconfig
@@ -21,6 +21,7 @@ if VIRTUALIZATION
 menuconfig KVM
 	bool "Kernel-based Virtual Machine (KVM) support"
 	depends on HAVE_KVM
+	select KVM_GENERIC_HARDWARE_ENABLING
 	select MMU_NOTIFIER
 	select PREEMPT_NOTIFIERS
 	select HAVE_KVM_CPU_RELAX_INTERCEPT
diff --git a/arch/arm64/kvm/arch_timer.c b/arch/arm64/kvm/arch_timer.c
index bb24a76b4224..23346585a294 100644
--- a/arch/arm64/kvm/arch_timer.c
+++ b/arch/arm64/kvm/arch_timer.c
@@ -811,10 +811,18 @@ void kvm_timer_vcpu_init(struct kvm_vcpu *vcpu)
 	ptimer->host_timer_irq_flags = host_ptimer_irq_flags;
 }
 
-static void kvm_timer_init_interrupt(void *info)
+void kvm_timer_cpu_up(void)
 {
 	enable_percpu_irq(host_vtimer_irq, host_vtimer_irq_flags);
-	enable_percpu_irq(host_ptimer_irq, host_ptimer_irq_flags);
+	if (host_ptimer_irq)
+		enable_percpu_irq(host_ptimer_irq, host_ptimer_irq_flags);
+}
+
+void kvm_timer_cpu_down(void)
+{
+	disable_percpu_irq(host_vtimer_irq);
+	if (host_ptimer_irq)
+		disable_percpu_irq(host_ptimer_irq);
 }
 
 int kvm_arm_timer_set_reg(struct kvm_vcpu *vcpu, u64 regid, u64 value)
@@ -976,18 +984,6 @@ void kvm_arm_timer_write_sysreg(struct kvm_vcpu *vcpu,
 	preempt_enable();
 }
 
-static int kvm_timer_starting_cpu(unsigned int cpu)
-{
-	kvm_timer_init_interrupt(NULL);
-	return 0;
-}
-
-static int kvm_timer_dying_cpu(unsigned int cpu)
-{
-	disable_percpu_irq(host_vtimer_irq);
-	return 0;
-}
-
 static int timer_irq_set_vcpu_affinity(struct irq_data *d, void *vcpu)
 {
 	if (vcpu)
@@ -1117,7 +1113,7 @@ static int kvm_irq_init(struct arch_timer_kvm_info *info)
 	return 0;
 }
 
-int kvm_timer_hyp_init(bool has_gic)
+int __init kvm_timer_hyp_init(bool has_gic)
 {
 	struct arch_timer_kvm_info *info;
 	int err;
@@ -1185,9 +1181,6 @@ int kvm_timer_hyp_init(bool has_gic)
 		goto out_free_irq;
 	}
 
-	cpuhp_setup_state(CPUHP_AP_KVM_ARM_TIMER_STARTING,
-			  "kvm/arm/timer:starting", kvm_timer_starting_cpu,
-			  kvm_timer_dying_cpu);
 	return 0;
 out_free_irq:
 	free_percpu_irq(host_vtimer_irq, kvm_get_running_vcpus());
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index 9c5573bc4614..698787ed87e9 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -63,16 +63,6 @@ int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu)
 	return kvm_vcpu_exiting_guest_mode(vcpu) == IN_GUEST_MODE;
 }
 
-int kvm_arch_hardware_setup(void *opaque)
-{
-	return 0;
-}
-
-int kvm_arch_check_processor_compat(void *opaque)
-{
-	return 0;
-}
-
 int kvm_vm_ioctl_enable_cap(struct kvm *kvm,
 			    struct kvm_enable_cap *cap)
 {
@@ -1539,7 +1529,7 @@ static int kvm_init_vector_slots(void)
 	return 0;
 }
 
-static void cpu_prepare_hyp_mode(int cpu, u32 hyp_va_bits)
+static void __init cpu_prepare_hyp_mode(int cpu, u32 hyp_va_bits)
 {
 	struct kvm_nvhe_init_params *params = per_cpu_ptr_nvhe_sym(kvm_init_params, cpu);
 	unsigned long tcr;
@@ -1682,7 +1672,15 @@ static void _kvm_arch_hardware_enable(void *discard)
 
 int kvm_arch_hardware_enable(void)
 {
+	int was_enabled = __this_cpu_read(kvm_arm_hardware_enabled);
+
 	_kvm_arch_hardware_enable(NULL);
+
+	if (!was_enabled) {
+		kvm_vgic_cpu_up();
+		kvm_timer_cpu_up();
+	}
+
 	return 0;
 }
 
@@ -1696,6 +1694,11 @@ static void _kvm_arch_hardware_disable(void *discard)
 
 void kvm_arch_hardware_disable(void)
 {
+	if (__this_cpu_read(kvm_arm_hardware_enabled)) {
+		kvm_timer_cpu_down();
+		kvm_vgic_cpu_down();
+	}
+
 	if (!is_protected_kvm_enabled())
 		_kvm_arch_hardware_disable(NULL);
 }
@@ -1738,26 +1741,26 @@ static struct notifier_block hyp_init_cpu_pm_nb = {
 	.notifier_call = hyp_init_cpu_pm_notifier,
 };
 
-static void hyp_cpu_pm_init(void)
+static void __init hyp_cpu_pm_init(void)
 {
 	if (!is_protected_kvm_enabled())
 		cpu_pm_register_notifier(&hyp_init_cpu_pm_nb);
 }
-static void hyp_cpu_pm_exit(void)
+static void __init hyp_cpu_pm_exit(void)
 {
 	if (!is_protected_kvm_enabled())
 		cpu_pm_unregister_notifier(&hyp_init_cpu_pm_nb);
 }
 #else
-static inline void hyp_cpu_pm_init(void)
+static inline void __init hyp_cpu_pm_init(void)
 {
 }
-static inline void hyp_cpu_pm_exit(void)
+static inline void __init hyp_cpu_pm_exit(void)
 {
 }
 #endif
 
-static void init_cpu_logical_map(void)
+static void __init init_cpu_logical_map(void)
 {
 	unsigned int cpu;
 
@@ -1774,7 +1777,7 @@ static void init_cpu_logical_map(void)
 #define init_psci_0_1_impl_state(config, what)	\
 	config.psci_0_1_ ## what ## _implemented = psci_ops.what
 
-static bool init_psci_relay(void)
+static bool __init init_psci_relay(void)
 {
 	/*
 	 * If PSCI has not been initialized, protected KVM cannot install
@@ -1797,7 +1800,7 @@ static bool init_psci_relay(void)
 	return true;
 }
 
-static int init_subsystems(void)
+static int __init init_subsystems(void)
 {
 	int err = 0;
 
@@ -1838,13 +1841,22 @@ static int init_subsystems(void)
 	kvm_register_perf_callbacks(NULL);
 
 out:
+	if (err)
+		hyp_cpu_pm_exit();
+
 	if (err || !is_protected_kvm_enabled())
 		on_each_cpu(_kvm_arch_hardware_disable, NULL, 1);
 
 	return err;
 }
 
-static void teardown_hyp_mode(void)
+static void __init teardown_subsystems(void)
+{
+	kvm_unregister_perf_callbacks();
+	hyp_cpu_pm_exit();
+}
+
+static void __init teardown_hyp_mode(void)
 {
 	int cpu;
 
@@ -1855,7 +1867,7 @@ static void teardown_hyp_mode(void)
 	}
 }
 
-static int do_pkvm_init(u32 hyp_va_bits)
+static int __init do_pkvm_init(u32 hyp_va_bits)
 {
 	void *per_cpu_base = kvm_ksym_ref(kvm_nvhe_sym(kvm_arm_hyp_percpu_base));
 	int ret;
@@ -1891,7 +1903,7 @@ static void kvm_hyp_init_symbols(void)
 	kvm_nvhe_sym(kvm_arm_vmid_bits) = kvm_arm_vmid_bits;
 }
 
-static int kvm_hyp_init_protection(u32 hyp_va_bits)
+static int __init kvm_hyp_init_protection(u32 hyp_va_bits)
 {
 	void *addr = phys_to_virt(hyp_mem_base);
 	int ret;
@@ -1912,7 +1924,7 @@ static int kvm_hyp_init_protection(u32 hyp_va_bits)
 /**
  * Inits Hyp-mode on all online CPUs
  */
-static int init_hyp_mode(void)
+static int __init init_hyp_mode(void)
 {
 	u32 hyp_va_bits;
 	int cpu;
@@ -2094,7 +2106,7 @@ out_err:
 	return err;
 }
 
-static void _kvm_host_prot_finalize(void *arg)
+static void __init _kvm_host_prot_finalize(void *arg)
 {
 	int *err = arg;
 
@@ -2102,7 +2114,7 @@ static void _kvm_host_prot_finalize(void *arg)
 		WRITE_ONCE(*err, -EINVAL);
 }
 
-static int pkvm_drop_host_privileges(void)
+static int __init pkvm_drop_host_privileges(void)
 {
 	int ret = 0;
 
@@ -2115,7 +2127,7 @@ static int pkvm_drop_host_privileges(void)
 	return ret;
 }
 
-static int finalize_hyp_mode(void)
+static int __init finalize_hyp_mode(void)
 {
 	if (!is_protected_kvm_enabled())
 		return 0;
@@ -2190,7 +2202,7 @@ void kvm_arch_irq_bypass_start(struct irq_bypass_consumer *cons)
 /**
  * Initialize Hyp-mode and memory mappings on all CPUs.
  */
-int kvm_arch_init(void *opaque)
+static __init int kvm_arm_init(void)
 {
 	int err;
 	bool in_hyp_mode;
@@ -2241,7 +2253,7 @@ int kvm_arch_init(void *opaque)
 	err = kvm_init_vector_slots();
 	if (err) {
 		kvm_err("Cannot initialise vector slots\n");
-		goto out_err;
+		goto out_hyp;
 	}
 
 	err = init_subsystems();
@@ -2252,7 +2264,7 @@ int kvm_arch_init(void *opaque)
 		err = finalize_hyp_mode();
 		if (err) {
 			kvm_err("Failed to finalize Hyp protection\n");
-			goto out_hyp;
+			goto out_subs;
 		}
 	}
 
@@ -2264,10 +2276,19 @@ int kvm_arch_init(void *opaque)
 		kvm_info("Hyp mode initialized successfully\n");
 	}
 
+	/*
+	 * FIXME: Do something reasonable if kvm_init() fails after pKVM
+	 * hypervisor protection is finalized.
+	 */
+	err = kvm_init(sizeof(struct kvm_vcpu), 0, THIS_MODULE);
+	if (err)
+		goto out_subs;
+
 	return 0;
 
+out_subs:
+	teardown_subsystems();
 out_hyp:
-	hyp_cpu_pm_exit();
 	if (!in_hyp_mode)
 		teardown_hyp_mode();
 out_err:
@@ -2275,12 +2296,6 @@ out_err:
 	return err;
 }
 
-/* NOP: Compiling as a module not supported */
-void kvm_arch_exit(void)
-{
-	kvm_unregister_perf_callbacks();
-}
-
 static int __init early_kvm_mode_cfg(char *arg)
 {
 	if (!arg)
@@ -2319,10 +2334,4 @@ enum kvm_mode kvm_get_mode(void)
 	return kvm_mode;
 }
 
-static int arm_init(void)
-{
-	int rc = kvm_init(NULL, sizeof(struct kvm_vcpu), 0, THIS_MODULE);
-	return rc;
-}
-
-module_init(arm_init);
+module_init(kvm_arm_init);
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index a3ee3b605c9b..01352f5838a0 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -25,11 +25,11 @@
 static struct kvm_pgtable *hyp_pgtable;
 static DEFINE_MUTEX(kvm_hyp_pgd_mutex);
 
-static unsigned long hyp_idmap_start;
-static unsigned long hyp_idmap_end;
-static phys_addr_t hyp_idmap_vector;
+static unsigned long __ro_after_init hyp_idmap_start;
+static unsigned long __ro_after_init hyp_idmap_end;
+static phys_addr_t __ro_after_init hyp_idmap_vector;
 
-static unsigned long io_map_base;
+static unsigned long __ro_after_init io_map_base;
 
 static phys_addr_t stage2_range_addr_end(phys_addr_t addr, phys_addr_t end)
 {
@@ -280,7 +280,7 @@ static void stage2_flush_vm(struct kvm *kvm)
 /**
  * free_hyp_pgds - free Hyp-mode page tables
  */
-void free_hyp_pgds(void)
+void __init free_hyp_pgds(void)
 {
 	mutex_lock(&kvm_hyp_pgd_mutex);
 	if (hyp_pgtable) {
@@ -1668,7 +1668,7 @@ static struct kvm_pgtable_mm_ops kvm_hyp_mm_ops = {
 	.virt_to_phys		= kvm_host_pa,
 };
 
-int kvm_mmu_init(u32 *hyp_va_bits)
+int __init kvm_mmu_init(u32 *hyp_va_bits)
 {
 	int err;
 	u32 idmap_bits;
diff --git a/arch/arm64/kvm/reset.c b/arch/arm64/kvm/reset.c
index e0267f672b8a..2bc74739a6df 100644
--- a/arch/arm64/kvm/reset.c
+++ b/arch/arm64/kvm/reset.c
@@ -30,7 +30,7 @@
 #include <asm/virt.h>
 
 /* Maximum phys_shift supported for any VM on this host */
-static u32 kvm_ipa_limit;
+static u32 __ro_after_init kvm_ipa_limit;
 
 /*
  * ARMv8 Reset Values
@@ -41,9 +41,9 @@ static u32 kvm_ipa_limit;
 #define VCPU_RESET_PSTATE_SVC	(PSR_AA32_MODE_SVC | PSR_AA32_A_BIT | \
 				 PSR_AA32_I_BIT | PSR_AA32_F_BIT)
 
-unsigned int kvm_sve_max_vl;
+unsigned int __ro_after_init kvm_sve_max_vl;
 
-int kvm_arm_init_sve(void)
+int __init kvm_arm_init_sve(void)
 {
 	if (system_supports_sve()) {
 		kvm_sve_max_vl = sve_max_virtualisable_vl();
@@ -352,7 +352,7 @@ u32 get_kvm_ipa_limit(void)
 	return kvm_ipa_limit;
 }
 
-int kvm_set_ipa_limit(void)
+int __init kvm_set_ipa_limit(void)
 {
 	unsigned int parange;
 	u64 mmfr0;
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index c6cbfe6b854b..46d161fe08d3 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -82,7 +82,7 @@ void vcpu_write_sys_reg(struct kvm_vcpu *vcpu, u64 val, int reg)
 }
 
 /* 3 bits per cache level, as per CLIDR, but non-existent caches always 0 */
-static u32 cache_levels;
+static u32 __ro_after_init cache_levels;
 
 /* CSSELR values; used to index KVM_REG_ARM_DEMUX_ID_CCSIDR */
 #define CSSELR_MAX 14
@@ -2733,7 +2733,7 @@ static void get_ctr_el0(struct kvm_vcpu *v, const struct sys_reg_desc *r)
 }
 
 /* ->val is filled in by kvm_sys_reg_table_init() */
-static struct sys_reg_desc invariant_sys_regs[] = {
+static struct sys_reg_desc invariant_sys_regs[] __ro_after_init = {
 	{ SYS_DESC(SYS_MIDR_EL1), NULL, get_midr_el1 },
 	{ SYS_DESC(SYS_REVIDR_EL1), NULL, get_revidr_el1 },
 	{ SYS_DESC(SYS_CLIDR_EL1), NULL, get_clidr_el1 },
@@ -3057,7 +3057,7 @@ int kvm_arm_copy_sys_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices)
 	return write_demux_regids(uindices);
 }
 
-int kvm_sys_reg_table_init(void)
+int __init kvm_sys_reg_table_init(void)
 {
 	bool valid = true;
 	unsigned int i;
diff --git a/arch/arm64/kvm/vgic/vgic-init.c b/arch/arm64/kvm/vgic/vgic-init.c
index f6d4f4052555..6c7f6ae21ec0 100644
--- a/arch/arm64/kvm/vgic/vgic-init.c
+++ b/arch/arm64/kvm/vgic/vgic-init.c
@@ -465,17 +465,15 @@ out:
 
 /* GENERIC PROBE */
 
-static int vgic_init_cpu_starting(unsigned int cpu)
+void kvm_vgic_cpu_up(void)
 {
 	enable_percpu_irq(kvm_vgic_global_state.maint_irq, 0);
-	return 0;
 }
 
 
-static int vgic_init_cpu_dying(unsigned int cpu)
+void kvm_vgic_cpu_down(void)
 {
 	disable_percpu_irq(kvm_vgic_global_state.maint_irq);
-	return 0;
 }
 
 static irqreturn_t vgic_maintenance_handler(int irq, void *data)
@@ -584,19 +582,6 @@ int kvm_vgic_hyp_init(void)
 		return ret;
 	}
 
-	ret = cpuhp_setup_state(CPUHP_AP_KVM_ARM_VGIC_INIT_STARTING,
-				"kvm/arm/vgic:starting",
-				vgic_init_cpu_starting, vgic_init_cpu_dying);
-	if (ret) {
-		kvm_err("Cannot register vgic CPU notifier\n");
-		goto out_free_irq;
-	}
-
 	kvm_info("vgic interrupt IRQ%d\n", kvm_vgic_global_state.maint_irq);
 	return 0;
-
-out_free_irq:
-	free_percpu_irq(kvm_vgic_global_state.maint_irq,
-			kvm_get_running_vcpus());
-	return ret;
 }
diff --git a/arch/arm64/kvm/vmid.c b/arch/arm64/kvm/vmid.c
index d78ae63d7c15..08978d0672e7 100644
--- a/arch/arm64/kvm/vmid.c
+++ b/arch/arm64/kvm/vmid.c
@@ -16,7 +16,7 @@
 #include <asm/kvm_asm.h>
 #include <asm/kvm_mmu.h>
 
-unsigned int kvm_arm_vmid_bits;
+unsigned int __ro_after_init kvm_arm_vmid_bits;
 static DEFINE_RAW_SPINLOCK(cpu_vmid_lock);
 
 static atomic64_t vmid_generation;
@@ -172,7 +172,7 @@ void kvm_arm_vmid_update(struct kvm_vmid *kvm_vmid)
 /*
  * Initialize the VMID allocator
  */
-int kvm_arm_vmid_alloc_init(void)
+int __init kvm_arm_vmid_alloc_init(void)
 {
 	kvm_arm_vmid_bits = kvm_get_vmid_bits();
 
@@ -190,7 +190,7 @@ int kvm_arm_vmid_alloc_init(void)
 	return 0;
 }
 
-void kvm_arm_vmid_alloc_free(void)
+void __init kvm_arm_vmid_alloc_free(void)
 {
 	kfree(vmid_map);
 }