Merge tag 'kvm-arm-fixes-for-5.0' of...

Merge tag 'kvm-arm-fixes-for-5.0' of git://git.kernel.org/pub/scm/linux/kernel/git/kvmarm/kvmarm into kvm-master

KVM/ARM fixes for 5.0:

- Fix the way we reset vcpus, plugging the race that could happen on VHE
- Fix potentially inconsistent group setting for private interrupts
- Don't generate UNDEF when LORegion feature is present
- Relax the restriction on using stage2 PUD huge mapping
- Turn some spinlocks into raw_spinlocks to help RT compliance

arch/arm/include/asm/kvm_host.h

@@ -48,6 +48,7 @@
 #define KVM_REQ_SLEEP \
 	KVM_ARCH_REQ_FLAGS(0, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
 #define KVM_REQ_IRQ_PENDING	KVM_ARCH_REQ(1)
+#define KVM_REQ_VCPU_RESET	KVM_ARCH_REQ(2)
 
 DECLARE_STATIC_KEY_FALSE(userspace_irqchip_in_use);
 
@@ -147,6 +148,13 @@ struct kvm_cpu_context {
 
 typedef struct kvm_cpu_context kvm_cpu_context_t;
 
+struct vcpu_reset_state {
+	unsigned long	pc;
+	unsigned long	r0;
+	bool		be;
+	bool		reset;
+};
+
 struct kvm_vcpu_arch {
 	struct kvm_cpu_context ctxt;
 
@@ -186,6 +194,8 @@ struct kvm_vcpu_arch {
 	/* Cache some mmu pages needed inside spinlock regions */
 	struct kvm_mmu_memory_cache mmu_page_cache;
 
+	struct vcpu_reset_state reset_state;
+
 	/* Detect first run of a vcpu */
 	bool has_run_once;
 };

arch/arm/include/asm/stage2_pgtable.h

@@ -76,4 +76,9 @@ static inline bool kvm_stage2_has_pud(struct kvm *kvm)
 #define S2_PMD_MASK				PMD_MASK
 #define S2_PMD_SIZE				PMD_SIZE
 
+static inline bool kvm_stage2_has_pmd(struct kvm *kvm)
+{
+	return true;
+}
+
 #endif	/* __ARM_S2_PGTABLE_H_ */

arch/arm/kvm/coproc.c

@@ -1450,6 +1450,6 @@ void kvm_reset_coprocs(struct kvm_vcpu *vcpu)
 	reset_coproc_regs(vcpu, table, num);
 
 	for (num = 1; num < NR_CP15_REGS; num++)
-		if (vcpu_cp15(vcpu, num) == 0x42424242)
-			panic("Didn't reset vcpu_cp15(vcpu, %zi)", num);
+		WARN(vcpu_cp15(vcpu, num) == 0x42424242,
+		     "Didn't reset vcpu_cp15(vcpu, %zi)", num);
 }

arch/arm/kvm/reset.c

@@ -26,6 +26,7 @@
 #include <asm/cputype.h>
 #include <asm/kvm_arm.h>
 #include <asm/kvm_coproc.h>
+#include <asm/kvm_emulate.h>
 
 #include <kvm/arm_arch_timer.h>
 
@@ -69,6 +70,29 @@ int kvm_reset_vcpu(struct kvm_vcpu *vcpu)
 	/* Reset CP15 registers */
 	kvm_reset_coprocs(vcpu);
 
+	/*
+	 * Additional reset state handling that PSCI may have imposed on us.
+	 * Must be done after all the sys_reg reset.
+	 */
+	if (READ_ONCE(vcpu->arch.reset_state.reset)) {
+		unsigned long target_pc = vcpu->arch.reset_state.pc;
+
+		/* Gracefully handle Thumb2 entry point */
+		if (target_pc & 1) {
+			target_pc &= ~1UL;
+			vcpu_set_thumb(vcpu);
+		}
+
+		/* Propagate caller endianness */
+		if (vcpu->arch.reset_state.be)
+			kvm_vcpu_set_be(vcpu);
+
+		*vcpu_pc(vcpu) = target_pc;
+		vcpu_set_reg(vcpu, 0, vcpu->arch.reset_state.r0);
+
+		vcpu->arch.reset_state.reset = false;
+	}
+
 	/* Reset arch_timer context */
 	return kvm_timer_vcpu_reset(vcpu);
 }

arch/arm64/include/asm/kvm_host.h

@@ -48,6 +48,7 @@
 #define KVM_REQ_SLEEP \
 	KVM_ARCH_REQ_FLAGS(0, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
 #define KVM_REQ_IRQ_PENDING	KVM_ARCH_REQ(1)
+#define KVM_REQ_VCPU_RESET	KVM_ARCH_REQ(2)
 
 DECLARE_STATIC_KEY_FALSE(userspace_irqchip_in_use);
 
@@ -208,6 +209,13 @@ struct kvm_cpu_context {
 
 typedef struct kvm_cpu_context kvm_cpu_context_t;
 
+struct vcpu_reset_state {
+	unsigned long	pc;
+	unsigned long	r0;
+	bool		be;
+	bool		reset;
+};
+
 struct kvm_vcpu_arch {
 	struct kvm_cpu_context ctxt;
 
@@ -297,6 +305,9 @@ struct kvm_vcpu_arch {
 	/* Virtual SError ESR to restore when HCR_EL2.VSE is set */
 	u64 vsesr_el2;
 
+	/* Additional reset state */
+	struct vcpu_reset_state	reset_state;
+
 	/* True when deferrable sysregs are loaded on the physical CPU,
 	 * see kvm_vcpu_load_sysregs and kvm_vcpu_put_sysregs. */
 	bool sysregs_loaded_on_cpu;

arch/arm64/kvm/hyp/switch.c

@@ -23,6 +23,7 @@
 #include <kvm/arm_psci.h>
 
 #include <asm/cpufeature.h>
+#include <asm/kprobes.h>
 #include <asm/kvm_asm.h>
 #include <asm/kvm_emulate.h>
 #include <asm/kvm_host.h>
@@ -107,6 +108,7 @@ static void activate_traps_vhe(struct kvm_vcpu *vcpu)
 
 	write_sysreg(kvm_get_hyp_vector(), vbar_el1);
 }
+NOKPROBE_SYMBOL(activate_traps_vhe);
 
 static void __hyp_text __activate_traps_nvhe(struct kvm_vcpu *vcpu)
 {
@@ -154,6 +156,7 @@ static void deactivate_traps_vhe(void)
 	write_sysreg(CPACR_EL1_DEFAULT, cpacr_el1);
 	write_sysreg(vectors, vbar_el1);
 }
+NOKPROBE_SYMBOL(deactivate_traps_vhe);
 
 static void __hyp_text __deactivate_traps_nvhe(void)
 {
@@ -513,6 +516,7 @@ int kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu)
 
 	return exit_code;
 }
+NOKPROBE_SYMBOL(kvm_vcpu_run_vhe);
 
 /* Switch to the guest for legacy non-VHE systems */
 int __hyp_text __kvm_vcpu_run_nvhe(struct kvm_vcpu *vcpu)
@@ -620,6 +624,7 @@ static void __hyp_call_panic_vhe(u64 spsr, u64 elr, u64 par,
 	      read_sysreg_el2(esr),   read_sysreg_el2(far),
 	      read_sysreg(hpfar_el2), par, vcpu);
 }
+NOKPROBE_SYMBOL(__hyp_call_panic_vhe);
 
 void __hyp_text __noreturn hyp_panic(struct kvm_cpu_context *host_ctxt)
 {

arch/arm64/kvm/hyp/sysreg-sr.c

@@ -18,6 +18,7 @@
 #include <linux/compiler.h>
 #include <linux/kvm_host.h>
 
+#include <asm/kprobes.h>
 #include <asm/kvm_asm.h>
 #include <asm/kvm_emulate.h>
 #include <asm/kvm_hyp.h>
@@ -98,12 +99,14 @@ void sysreg_save_host_state_vhe(struct kvm_cpu_context *ctxt)
 {
 	__sysreg_save_common_state(ctxt);
 }
+NOKPROBE_SYMBOL(sysreg_save_host_state_vhe);
 
 void sysreg_save_guest_state_vhe(struct kvm_cpu_context *ctxt)
 {
 	__sysreg_save_common_state(ctxt);
 	__sysreg_save_el2_return_state(ctxt);
 }
+NOKPROBE_SYMBOL(sysreg_save_guest_state_vhe);
 
 static void __hyp_text __sysreg_restore_common_state(struct kvm_cpu_context *ctxt)
 {
@@ -188,12 +191,14 @@ void sysreg_restore_host_state_vhe(struct kvm_cpu_context *ctxt)
 {
 	__sysreg_restore_common_state(ctxt);
 }
+NOKPROBE_SYMBOL(sysreg_restore_host_state_vhe);
 
 void sysreg_restore_guest_state_vhe(struct kvm_cpu_context *ctxt)
 {
 	__sysreg_restore_common_state(ctxt);
 	__sysreg_restore_el2_return_state(ctxt);
 }
+NOKPROBE_SYMBOL(sysreg_restore_guest_state_vhe);
 
 void __hyp_text __sysreg32_save_state(struct kvm_vcpu *vcpu)
 {

arch/arm64/kvm/reset.c

@@ -32,6 +32,7 @@
 #include <asm/kvm_arm.h>
 #include <asm/kvm_asm.h>
 #include <asm/kvm_coproc.h>
+#include <asm/kvm_emulate.h>
 #include <asm/kvm_mmu.h>
 
 /* Maximum phys_shift supported for any VM on this host */
@@ -105,16 +106,33 @@ int kvm_arch_vm_ioctl_check_extension(struct kvm *kvm, long ext)
  * This function finds the right table above and sets the registers on
  * the virtual CPU struct to their architecturally defined reset
  * values.
+ *
+ * Note: This function can be called from two paths: The KVM_ARM_VCPU_INIT
+ * ioctl or as part of handling a request issued by another VCPU in the PSCI
+ * handling code.  In the first case, the VCPU will not be loaded, and in the
+ * second case the VCPU will be loaded.  Because this function operates purely
+ * on the memory-backed valus of system registers, we want to do a full put if
+ * we were loaded (handling a request) and load the values back at the end of
+ * the function.  Otherwise we leave the state alone.  In both cases, we
+ * disable preemption around the vcpu reset as we would otherwise race with
+ * preempt notifiers which also call put/load.
  */
 int kvm_reset_vcpu(struct kvm_vcpu *vcpu)
 {
 	const struct kvm_regs *cpu_reset;
+	int ret = -EINVAL;
+	bool loaded;
+
+	preempt_disable();
+	loaded = (vcpu->cpu != -1);
+	if (loaded)
+		kvm_arch_vcpu_put(vcpu);
 
 	switch (vcpu->arch.target) {
 	default:
 		if (test_bit(KVM_ARM_VCPU_EL1_32BIT, vcpu->arch.features)) {
 			if (!cpu_has_32bit_el1())
-				return -EINVAL;
+				goto out;
 			cpu_reset = &default_regs_reset32;
 		} else {
 			cpu_reset = &default_regs_reset;
@@ -129,6 +147,29 @@ int kvm_reset_vcpu(struct kvm_vcpu *vcpu)
 	/* Reset system registers */
 	kvm_reset_sys_regs(vcpu);
 
+	/*
+	 * Additional reset state handling that PSCI may have imposed on us.
+	 * Must be done after all the sys_reg reset.
+	 */
+	if (vcpu->arch.reset_state.reset) {
+		unsigned long target_pc = vcpu->arch.reset_state.pc;
+
+		/* Gracefully handle Thumb2 entry point */
+		if (vcpu_mode_is_32bit(vcpu) && (target_pc & 1)) {
+			target_pc &= ~1UL;
+			vcpu_set_thumb(vcpu);
+		}
+
+		/* Propagate caller endianness */
+		if (vcpu->arch.reset_state.be)
+			kvm_vcpu_set_be(vcpu);
+
+		*vcpu_pc(vcpu) = target_pc;
+		vcpu_set_reg(vcpu, 0, vcpu->arch.reset_state.r0);
+
+		vcpu->arch.reset_state.reset = false;
+	}
+
 	/* Reset PMU */
 	kvm_pmu_vcpu_reset(vcpu);
 
@@ -137,7 +178,12 @@ int kvm_reset_vcpu(struct kvm_vcpu *vcpu)
 		vcpu->arch.workaround_flags |= VCPU_WORKAROUND_2_FLAG;
 
 	/* Reset timer */
-	return kvm_timer_vcpu_reset(vcpu);
+	ret = kvm_timer_vcpu_reset(vcpu);
+out:
+	if (loaded)
+		kvm_arch_vcpu_load(vcpu, smp_processor_id());
+	preempt_enable();
+	return ret;
 }
 
 void kvm_set_ipa_limit(void)

arch/arm64/kvm/sys_regs.c

@@ -314,12 +314,29 @@ static bool trap_raz_wi(struct kvm_vcpu *vcpu,
 		return read_zero(vcpu, p);
 }
 
-static bool trap_undef(struct kvm_vcpu *vcpu,
+/*
+ * ARMv8.1 mandates at least a trivial LORegion implementation, where all the
+ * RW registers are RES0 (which we can implement as RAZ/WI). On an ARMv8.0
+ * system, these registers should UNDEF. LORID_EL1 being a RO register, we
+ * treat it separately.
+ */
+static bool trap_loregion(struct kvm_vcpu *vcpu,
 			  struct sys_reg_params *p,
 			  const struct sys_reg_desc *r)
 {
+	u64 val = read_sanitised_ftr_reg(SYS_ID_AA64MMFR1_EL1);
+	u32 sr = sys_reg((u32)r->Op0, (u32)r->Op1,
+			 (u32)r->CRn, (u32)r->CRm, (u32)r->Op2);
+
+	if (!(val & (0xfUL << ID_AA64MMFR1_LOR_SHIFT))) {
 		kvm_inject_undefined(vcpu);
 		return false;
+	}
+
+	if (p->is_write && sr == SYS_LORID_EL1)
+		return write_to_read_only(vcpu, p, r);
+
+	return trap_raz_wi(vcpu, p, r);
 }
 
 static bool trap_oslsr_el1(struct kvm_vcpu *vcpu,
@@ -1048,11 +1065,6 @@ static u64 read_id_reg(struct sys_reg_desc const *r, bool raz)
 		if (val & ptrauth_mask)
 			kvm_debug("ptrauth unsupported for guests, suppressing\n");
 		val &= ~ptrauth_mask;
-	} else if (id == SYS_ID_AA64MMFR1_EL1) {
-		if (val & (0xfUL << ID_AA64MMFR1_LOR_SHIFT))
-			kvm_debug("LORegions unsupported for guests, suppressing\n");
-
-		val &= ~(0xfUL << ID_AA64MMFR1_LOR_SHIFT);
 	}
 
 	return val;
@@ -1338,11 +1350,11 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	{ SYS_DESC(SYS_MAIR_EL1), access_vm_reg, reset_unknown, MAIR_EL1 },
 	{ SYS_DESC(SYS_AMAIR_EL1), access_vm_reg, reset_amair_el1, AMAIR_EL1 },
 
-	{ SYS_DESC(SYS_LORSA_EL1), trap_undef },
-	{ SYS_DESC(SYS_LOREA_EL1), trap_undef },
-	{ SYS_DESC(SYS_LORN_EL1), trap_undef },
-	{ SYS_DESC(SYS_LORC_EL1), trap_undef },
-	{ SYS_DESC(SYS_LORID_EL1), trap_undef },
+	{ SYS_DESC(SYS_LORSA_EL1), trap_loregion },
+	{ SYS_DESC(SYS_LOREA_EL1), trap_loregion },
+	{ SYS_DESC(SYS_LORN_EL1), trap_loregion },
+	{ SYS_DESC(SYS_LORC_EL1), trap_loregion },
+	{ SYS_DESC(SYS_LORID_EL1), trap_loregion },
 
 	{ SYS_DESC(SYS_VBAR_EL1), NULL, reset_val, VBAR_EL1, 0 },
 	{ SYS_DESC(SYS_DISR_EL1), NULL, reset_val, DISR_EL1, 0 },
@@ -2596,7 +2608,9 @@ void kvm_reset_sys_regs(struct kvm_vcpu *vcpu)
 	table = get_target_table(vcpu->arch.target, true, &num);
 	reset_sys_reg_descs(vcpu, table, num);
 
-	for (num = 1; num < NR_SYS_REGS; num++)
-		if (__vcpu_sys_reg(vcpu, num) == 0x4242424242424242)
-			panic("Didn't reset __vcpu_sys_reg(%zi)", num);
+	for (num = 1; num < NR_SYS_REGS; num++) {
+		if (WARN(__vcpu_sys_reg(vcpu, num) == 0x4242424242424242,
+			 "Didn't reset __vcpu_sys_reg(%zi)\n", num))
+			break;
+	}
 }

include/kvm/arm_vgic.h

@@ -100,7 +100,7 @@ enum vgic_irq_config {
 };
 
 struct vgic_irq {
-	spinlock_t irq_lock;		/* Protects the content of the struct */
+	raw_spinlock_t irq_lock;	/* Protects the content of the struct */
 	struct list_head lpi_list;	/* Used to link all LPIs together */
 	struct list_head ap_list;
 
@@ -256,7 +256,7 @@ struct vgic_dist {
 	u64			propbaser;
 
 	/* Protects the lpi_list and the count value below. */
-	spinlock_t		lpi_list_lock;
+	raw_spinlock_t		lpi_list_lock;
 	struct list_head	lpi_list_head;
 	int			lpi_list_count;
 
@@ -307,7 +307,7 @@ struct vgic_cpu {
 	unsigned int used_lrs;
 	struct vgic_irq private_irqs[VGIC_NR_PRIVATE_IRQS];
 
-	spinlock_t ap_list_lock;	/* Protects the ap_list */
+	raw_spinlock_t ap_list_lock;	/* Protects the ap_list */
 
 	/*
 	 * List of IRQs that this VCPU should consider because they are either

virt/kvm/arm/arm.c

@@ -626,6 +626,13 @@ static void vcpu_req_sleep(struct kvm_vcpu *vcpu)
 		/* Awaken to handle a signal, request we sleep again later. */
 		kvm_make_request(KVM_REQ_SLEEP, vcpu);
 	}
+
+	/*
+	 * Make sure we will observe a potential reset request if we've
+	 * observed a change to the power state. Pairs with the smp_wmb() in
+	 * kvm_psci_vcpu_on().
+	 */
+	smp_rmb();
 }
 
 static int kvm_vcpu_initialized(struct kvm_vcpu *vcpu)
@@ -639,6 +646,9 @@ static void check_vcpu_requests(struct kvm_vcpu *vcpu)
 		if (kvm_check_request(KVM_REQ_SLEEP, vcpu))
 			vcpu_req_sleep(vcpu);
 
+		if (kvm_check_request(KVM_REQ_VCPU_RESET, vcpu))
+			kvm_reset_vcpu(vcpu);
+
 		/*
 		 * Clear IRQ_PENDING requests that were made to guarantee
 		 * that a VCPU sees new virtual interrupts.

virt/kvm/arm/mmu.c

@@ -1695,11 +1695,14 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 
 	vma_pagesize = vma_kernel_pagesize(vma);
 	/*
-	 * PUD level may not exist for a VM but PMD is guaranteed to
-	 * exist.
+	 * The stage2 has a minimum of 2 level table (For arm64 see
+	 * kvm_arm_setup_stage2()). Hence, we are guaranteed that we can
+	 * use PMD_SIZE huge mappings (even when the PMD is folded into PGD).
+	 * As for PUD huge maps, we must make sure that we have at least
+	 * 3 levels, i.e, PMD is not folded.
 	 */
 	if ((vma_pagesize == PMD_SIZE ||
-	     (vma_pagesize == PUD_SIZE && kvm_stage2_has_pud(kvm))) &&
+	     (vma_pagesize == PUD_SIZE && kvm_stage2_has_pmd(kvm))) &&
 	    !force_pte) {
 		gfn = (fault_ipa & huge_page_mask(hstate_vma(vma))) >> PAGE_SHIFT;
 	}

virt/kvm/arm/psci.c

@@ -104,12 +104,10 @@ static void kvm_psci_vcpu_off(struct kvm_vcpu *vcpu)
 
 static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu)
 {
+	struct vcpu_reset_state *reset_state;
 	struct kvm *kvm = source_vcpu->kvm;
 	struct kvm_vcpu *vcpu = NULL;
-	struct swait_queue_head *wq;
 	unsigned long cpu_id;
-	unsigned long context_id;
-	phys_addr_t target_pc;
 
 	cpu_id = smccc_get_arg1(source_vcpu) & MPIDR_HWID_BITMASK;
 	if (vcpu_mode_is_32bit(source_vcpu))
@@ -130,32 +128,30 @@ static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu)
 			return PSCI_RET_INVALID_PARAMS;
 	}
 
-	target_pc = smccc_get_arg2(source_vcpu);
-	context_id = smccc_get_arg3(source_vcpu);
+	reset_state = &vcpu->arch.reset_state;
 
-	kvm_reset_vcpu(vcpu);
-
-	/* Gracefully handle Thumb2 entry point */
-	if (vcpu_mode_is_32bit(vcpu) && (target_pc & 1)) {
-		target_pc &= ~((phys_addr_t) 1);
-		vcpu_set_thumb(vcpu);
-	}
+	reset_state->pc = smccc_get_arg2(source_vcpu);
 
 	/* Propagate caller endianness */
-	if (kvm_vcpu_is_be(source_vcpu))
-		kvm_vcpu_set_be(vcpu);
+	reset_state->be = kvm_vcpu_is_be(source_vcpu);
 
-	*vcpu_pc(vcpu) = target_pc;
 	/*
 	 * NOTE: We always update r0 (or x0) because for PSCI v0.1
 	 * the general puspose registers are undefined upon CPU_ON.
 	 */
-	smccc_set_retval(vcpu, context_id, 0, 0, 0);
-	vcpu->arch.power_off = false;
-	smp_mb();		/* Make sure the above is visible */
+	reset_state->r0 = smccc_get_arg3(source_vcpu);
+
+	WRITE_ONCE(reset_state->reset, true);
+	kvm_make_request(KVM_REQ_VCPU_RESET, vcpu);
 
-	wq = kvm_arch_vcpu_wq(vcpu);
-	swake_up_one(wq);
+	/*
+	 * Make sure the reset request is observed if the change to
+	 * power_state is observed.
+	 */
+	smp_wmb();
+
+	vcpu->arch.power_off = false;
+	kvm_vcpu_wake_up(vcpu);
 
 	return PSCI_RET_SUCCESS;
 }

virt/kvm/arm/vgic/vgic-debug.c

@@ -251,9 +251,9 @@ static int vgic_debug_show(struct seq_file *s, void *v)
 		return 0;
 	}
 
-	spin_lock_irqsave(&irq->irq_lock, flags);
+	raw_spin_lock_irqsave(&irq->irq_lock, flags);
 	print_irq_state(s, irq, vcpu);
-	spin_unlock_irqrestore(&irq->irq_lock, flags);
+	raw_spin_unlock_irqrestore(&irq->irq_lock, flags);
 
 	vgic_put_irq(kvm, irq);
 	return 0;

virt/kvm/arm/vgic/vgic-init.c

@@ -64,7 +64,7 @@ void kvm_vgic_early_init(struct kvm *kvm)
 	struct vgic_dist *dist = &kvm->arch.vgic;
 
 	INIT_LIST_HEAD(&dist->lpi_list_head);
-	spin_lock_init(&dist->lpi_list_lock);
+	raw_spin_lock_init(&dist->lpi_list_lock);
 }
 
 /* CREATION */
@@ -171,7 +171,7 @@ static int kvm_vgic_dist_init(struct kvm *kvm, unsigned int nr_spis)
 
 		irq->intid = i + VGIC_NR_PRIVATE_IRQS;
 		INIT_LIST_HEAD(&irq->ap_list);
-		spin_lock_init(&irq->irq_lock);
+		raw_spin_lock_init(&irq->irq_lock);
 		irq->vcpu = NULL;
 		irq->target_vcpu = vcpu0;
 		kref_init(&irq->refcount);
@@ -206,7 +206,7 @@ int kvm_vgic_vcpu_init(struct kvm_vcpu *vcpu)
 	vgic_cpu->sgi_iodev.base_addr = VGIC_ADDR_UNDEF;
 
 	INIT_LIST_HEAD(&vgic_cpu->ap_list_head);
-	spin_lock_init(&vgic_cpu->ap_list_lock);
+	raw_spin_lock_init(&vgic_cpu->ap_list_lock);
 
 	/*
 	 * Enable and configure all SGIs to be edge-triggered and
@@ -216,7 +216,7 @@ int kvm_vgic_vcpu_init(struct kvm_vcpu *vcpu)
 		struct vgic_irq *irq = &vgic_cpu->private_irqs[i];
 
 		INIT_LIST_HEAD(&irq->ap_list);
-		spin_lock_init(&irq->irq_lock);
+		raw_spin_lock_init(&irq->irq_lock);
 		irq->intid = i;
 		irq->vcpu = NULL;
 		irq->target_vcpu = vcpu;
@@ -231,13 +231,6 @@ int kvm_vgic_vcpu_init(struct kvm_vcpu *vcpu)
 			irq->config = VGIC_CONFIG_LEVEL;
 		}
 
-		/*
-		 * GICv3 can only be created via the KVM_DEVICE_CREATE API and
-		 * so we always know the emulation type at this point as it's
-		 * either explicitly configured as GICv3, or explicitly
-		 * configured as GICv2, or not configured yet which also
-		 * implies GICv2.
-		 */
 		if (dist->vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3)
 			irq->group = 1;
 		else
@@ -281,7 +274,7 @@ int vgic_init(struct kvm *kvm)
 {
 	struct vgic_dist *dist = &kvm->arch.vgic;
 	struct kvm_vcpu *vcpu;
-	int ret = 0, i;
+	int ret = 0, i, idx;
 
 	if (vgic_initialized(kvm))
 		return 0;
@@ -298,6 +291,19 @@ int vgic_init(struct kvm *kvm)
 	if (ret)
 		goto out;
 
+	/* Initialize groups on CPUs created before the VGIC type was known */
+	kvm_for_each_vcpu(idx, vcpu, kvm) {
+		struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
+
+		for (i = 0; i < VGIC_NR_PRIVATE_IRQS; i++) {
+			struct vgic_irq *irq = &vgic_cpu->private_irqs[i];
+			if (dist->vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3)
+				irq->group = 1;
+			else
+				irq->group = 0;
+		}
+	}
+
 	if (vgic_has_its(kvm)) {
 		ret = vgic_v4_init(kvm);
 		if (ret)

virt/kvm/arm/vgic/vgic-its.c

@@ -65,7 +65,7 @@ static struct vgic_irq *vgic_add_lpi(struct kvm *kvm, u32 intid,
 
 	INIT_LIST_HEAD(&irq->lpi_list);
 	INIT_LIST_HEAD(&irq->ap_list);
-	spin_lock_init(&irq->irq_lock);
+	raw_spin_lock_init(&irq->irq_lock);
 
 	irq->config = VGIC_CONFIG_EDGE;
 	kref_init(&irq->refcount);
@@ -73,7 +73,7 @@ static struct vgic_irq *vgic_add_lpi(struct kvm *kvm, u32 intid,
 	irq->target_vcpu = vcpu;
 	irq->group = 1;
 
-	spin_lock_irqsave(&dist->lpi_list_lock, flags);
+	raw_spin_lock_irqsave(&dist->lpi_list_lock, flags);
 
 	/*
 	 * There could be a race with another vgic_add_lpi(), so we need to
@@ -101,7 +101,7 @@ static struct vgic_irq *vgic_add_lpi(struct kvm *kvm, u32 intid,
 	dist->lpi_list_count++;
 
 out_unlock:
-	spin_unlock_irqrestore(&dist->lpi_list_lock, flags);
+	raw_spin_unlock_irqrestore(&dist->lpi_list_lock, flags);
 
 	/*
 	 * We "cache" the configuration table entries in our struct vgic_irq's.
@@ -287,7 +287,7 @@ static int update_lpi_config(struct kvm *kvm, struct vgic_irq *irq,
 	if (ret)
 		return ret;
 
-	spin_lock_irqsave(&irq->irq_lock, flags);
+	raw_spin_lock_irqsave(&irq->irq_lock, flags);
 
 	if (!filter_vcpu || filter_vcpu == irq->target_vcpu) {
 		irq->priority = LPI_PROP_PRIORITY(prop);
@@ -299,7 +299,7 @@ static int update_lpi_config(struct kvm *kvm, struct vgic_irq *irq,
 		}
 	}
 
-	spin_unlock_irqrestore(&irq->irq_lock, flags);
+	raw_spin_unlock_irqrestore(&irq->irq_lock, flags);
 
 	if (irq->hw)
 		return its_prop_update_vlpi(irq->host_irq, prop, needs_inv);
@@ -332,7 +332,7 @@ int vgic_copy_lpi_list(struct kvm *kvm, struct kvm_vcpu *vcpu, u32 **intid_ptr)
 	if (!intids)
 		return -ENOMEM;
 
-	spin_lock_irqsave(&dist->lpi_list_lock, flags);
+	raw_spin_lock_irqsave(&dist->lpi_list_lock, flags);
 	list_for_each_entry(irq, &dist->lpi_list_head, lpi_list) {
 		if (i == irq_count)
 			break;
@@ -341,7 +341,7 @@ int vgic_copy_lpi_list(struct kvm *kvm, struct kvm_vcpu *vcpu, u32 **intid_ptr)
 			continue;
 		intids[i++] = irq->intid;
 	}
-	spin_unlock_irqrestore(&dist->lpi_list_lock, flags);
+	raw_spin_unlock_irqrestore(&dist->lpi_list_lock, flags);
 
 	*intid_ptr = intids;
 	return i;
@@ -352,9 +352,9 @@ static int update_affinity(struct vgic_irq *irq, struct kvm_vcpu *vcpu)
 	int ret = 0;
 	unsigned long flags;
 
-	spin_lock_irqsave(&irq->irq_lock, flags);
+	raw_spin_lock_irqsave(&irq->irq_lock, flags);
 	irq->target_vcpu = vcpu;
-	spin_unlock_irqrestore(&irq->irq_lock, flags);
+	raw_spin_unlock_irqrestore(&irq->irq_lock, flags);
 
 	if (irq->hw) {
 		struct its_vlpi_map map;
@@ -455,7 +455,7 @@ static int its_sync_lpi_pending_table(struct kvm_vcpu *vcpu)
 		}
 
 		irq = vgic_get_irq(vcpu->kvm, NULL, intids[i]);
-		spin_lock_irqsave(&irq->irq_lock, flags);
+		raw_spin_lock_irqsave(&irq->irq_lock, flags);
 		irq->pending_latch = pendmask & (1U << bit_nr);
 		vgic_queue_irq_unlock(vcpu->kvm, irq, flags);
 		vgic_put_irq(vcpu->kvm, irq);
@@ -612,7 +612,7 @@ static int vgic_its_trigger_msi(struct kvm *kvm, struct vgic_its *its,
 		return irq_set_irqchip_state(irq->host_irq,
 					     IRQCHIP_STATE_PENDING, true);
 
-	spin_lock_irqsave(&irq->irq_lock, flags);
+	raw_spin_lock_irqsave(&irq->irq_lock, flags);
 	irq->pending_latch = true;
 	vgic_queue_irq_unlock(kvm, irq, flags);
 

virt/kvm/arm/vgic/vgic-mmio-v2.c

@@ -147,7 +147,7 @@ static void vgic_mmio_write_sgir(struct kvm_vcpu *source_vcpu,
 
 		irq = vgic_get_irq(source_vcpu->kvm, vcpu, intid);
 
-		spin_lock_irqsave(&irq->irq_lock, flags);
+		raw_spin_lock_irqsave(&irq->irq_lock, flags);
 		irq->pending_latch = true;
 		irq->source |= 1U << source_vcpu->vcpu_id;
 
@@ -191,13 +191,13 @@ static void vgic_mmio_write_target(struct kvm_vcpu *vcpu,
 		struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, NULL, intid + i);
 		int target;
 
-		spin_lock_irqsave(&irq->irq_lock, flags);
+		raw_spin_lock_irqsave(&irq->irq_lock, flags);
 
 		irq->targets = (val >> (i * 8)) & cpu_mask;
 		target = irq->targets ? __ffs(irq->targets) : 0;
 		irq->target_vcpu = kvm_get_vcpu(vcpu->kvm, target);
 
-		spin_unlock_irqrestore(&irq->irq_lock, flags);
+		raw_spin_unlock_irqrestore(&irq->irq_lock, flags);
 		vgic_put_irq(vcpu->kvm, irq);
 	}
 }
@@ -230,13 +230,13 @@ static void vgic_mmio_write_sgipendc(struct kvm_vcpu *vcpu,
 	for (i = 0; i < len; i++) {
 		struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i);
 
-		spin_lock_irqsave(&irq->irq_lock, flags);
+		raw_spin_lock_irqsave(&irq->irq_lock, flags);
 
 		irq->source &= ~((val >> (i * 8)) & 0xff);
 		if (!irq->source)
 			irq->pending_latch = false;
 
-		spin_unlock_irqrestore(&irq->irq_lock, flags);
+		raw_spin_unlock_irqrestore(&irq->irq_lock, flags);
 		vgic_put_irq(vcpu->kvm, irq);
 	}
 }
@@ -252,7 +252,7 @@ static void vgic_mmio_write_sgipends(struct kvm_vcpu *vcpu,
 	for (i = 0; i < len; i++) {
 		struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i);
 
-		spin_lock_irqsave(&irq->irq_lock, flags);
+		raw_spin_lock_irqsave(&irq->irq_lock, flags);
 
 		irq->source |= (val >> (i * 8)) & 0xff;
 
@@ -260,7 +260,7 @@ static void vgic_mmio_write_sgipends(struct kvm_vcpu *vcpu,
 			irq->pending_latch = true;
 			vgic_queue_irq_unlock(vcpu->kvm, irq, flags);
 		} else {
-			spin_unlock_irqrestore(&irq->irq_lock, flags);
+			raw_spin_unlock_irqrestore(&irq->irq_lock, flags);
 		}
 		vgic_put_irq(vcpu->kvm, irq);
 	}

virt/kvm/arm/vgic/vgic-mmio-v3.c

@@ -169,13 +169,13 @@ static void vgic_mmio_write_irouter(struct kvm_vcpu *vcpu,
 	if (!irq)
 		return;
 
-	spin_lock_irqsave(&irq->irq_lock, flags);
+	raw_spin_lock_irqsave(&irq->irq_lock, flags);
 
 	/* We only care about and preserve Aff0, Aff1 and Aff2. */
 	irq->mpidr = val & GENMASK(23, 0);
 	irq->target_vcpu = kvm_mpidr_to_vcpu(vcpu->kvm, irq->mpidr);
 
-	spin_unlock_irqrestore(&irq->irq_lock, flags);
+	raw_spin_unlock_irqrestore(&irq->irq_lock, flags);
 	vgic_put_irq(vcpu->kvm, irq);
 }
 
@@ -281,7 +281,7 @@ static int vgic_v3_uaccess_write_pending(struct kvm_vcpu *vcpu,
 	for (i = 0; i < len * 8; i++) {
 		struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i);
 
-		spin_lock_irqsave(&irq->irq_lock, flags);
+		raw_spin_lock_irqsave(&irq->irq_lock, flags);
 		if (test_bit(i, &val)) {
 			/*
 			 * pending_latch is set irrespective of irq type
@@ -292,7 +292,7 @@ static int vgic_v3_uaccess_write_pending(struct kvm_vcpu *vcpu,
 			vgic_queue_irq_unlock(vcpu->kvm, irq, flags);
 		} else {
 			irq->pending_latch = false;
-			spin_unlock_irqrestore(&irq->irq_lock, flags);
+			raw_spin_unlock_irqrestore(&irq->irq_lock, flags);
 		}
 
 		vgic_put_irq(vcpu->kvm, irq);
@@ -957,7 +957,7 @@ void vgic_v3_dispatch_sgi(struct kvm_vcpu *vcpu, u64 reg, bool allow_group1)
 
 		irq = vgic_get_irq(vcpu->kvm, c_vcpu, sgi);
 
-		spin_lock_irqsave(&irq->irq_lock, flags);
+		raw_spin_lock_irqsave(&irq->irq_lock, flags);
 
 		/*
 		 * An access targetting Group0 SGIs can only generate
@@ -968,7 +968,7 @@ void vgic_v3_dispatch_sgi(struct kvm_vcpu *vcpu, u64 reg, bool allow_group1)
 			irq->pending_latch = true;
 			vgic_queue_irq_unlock(vcpu->kvm, irq, flags);
 		} else {
-			spin_unlock_irqrestore(&irq->irq_lock, flags);
+			raw_spin_unlock_irqrestore(&irq->irq_lock, flags);
 		}
 
 		vgic_put_irq(vcpu->kvm, irq);

virt/kvm/arm/vgic/vgic-mmio.c

@@ -77,7 +77,7 @@ void vgic_mmio_write_group(struct kvm_vcpu *vcpu, gpa_t addr,
 	for (i = 0; i < len * 8; i++) {
 		struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i);
 
-		spin_lock_irqsave(&irq->irq_lock, flags);
+		raw_spin_lock_irqsave(&irq->irq_lock, flags);
 		irq->group = !!(val & BIT(i));
 		vgic_queue_irq_unlock(vcpu->kvm, irq, flags);
 
@@ -120,7 +120,7 @@ void vgic_mmio_write_senable(struct kvm_vcpu *vcpu,
 	for_each_set_bit(i, &val, len * 8) {
 		struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i);
 
-		spin_lock_irqsave(&irq->irq_lock, flags);
+		raw_spin_lock_irqsave(&irq->irq_lock, flags);
 		irq->enabled = true;
 		vgic_queue_irq_unlock(vcpu->kvm, irq, flags);
 
@@ -139,11 +139,11 @@ void vgic_mmio_write_cenable(struct kvm_vcpu *vcpu,
 	for_each_set_bit(i, &val, len * 8) {
 		struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i);
 
-		spin_lock_irqsave(&irq->irq_lock, flags);
+		raw_spin_lock_irqsave(&irq->irq_lock, flags);
 
 		irq->enabled = false;
 
-		spin_unlock_irqrestore(&irq->irq_lock, flags);
+		raw_spin_unlock_irqrestore(&irq->irq_lock, flags);
 		vgic_put_irq(vcpu->kvm, irq);
 	}
 }
@@ -160,10 +160,10 @@ unsigned long vgic_mmio_read_pending(struct kvm_vcpu *vcpu,
 		struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i);
 		unsigned long flags;
 
-		spin_lock_irqsave(&irq->irq_lock, flags);
+		raw_spin_lock_irqsave(&irq->irq_lock, flags);
 		if (irq_is_pending(irq))
 			value |= (1U << i);
-		spin_unlock_irqrestore(&irq->irq_lock, flags);
+		raw_spin_unlock_irqrestore(&irq->irq_lock, flags);
 
 		vgic_put_irq(vcpu->kvm, irq);
 	}
@@ -215,7 +215,7 @@ void vgic_mmio_write_spending(struct kvm_vcpu *vcpu,
 	for_each_set_bit(i, &val, len * 8) {
 		struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i);
 
-		spin_lock_irqsave(&irq->irq_lock, flags);
+		raw_spin_lock_irqsave(&irq->irq_lock, flags);
 		if (irq->hw)
 			vgic_hw_irq_spending(vcpu, irq, is_uaccess);
 		else
@@ -262,14 +262,14 @@ void vgic_mmio_write_cpending(struct kvm_vcpu *vcpu,
 	for_each_set_bit(i, &val, len * 8) {
 		struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i);
 
-		spin_lock_irqsave(&irq->irq_lock, flags);
+		raw_spin_lock_irqsave(&irq->irq_lock, flags);
 
 		if (irq->hw)
 			vgic_hw_irq_cpending(vcpu, irq, is_uaccess);
 		else
 			irq->pending_latch = false;
 
-		spin_unlock_irqrestore(&irq->irq_lock, flags);
+		raw_spin_unlock_irqrestore(&irq->irq_lock, flags);
 		vgic_put_irq(vcpu->kvm, irq);
 	}
 }
@@ -311,7 +311,7 @@ static void vgic_mmio_change_active(struct kvm_vcpu *vcpu, struct vgic_irq *irq,
 	unsigned long flags;
 	struct kvm_vcpu *requester_vcpu = vgic_get_mmio_requester_vcpu();
 
-	spin_lock_irqsave(&irq->irq_lock, flags);
+	raw_spin_lock_irqsave(&irq->irq_lock, flags);
 
 	if (irq->hw) {
 		vgic_hw_irq_change_active(vcpu, irq, active, !requester_vcpu);
@@ -342,7 +342,7 @@ static void vgic_mmio_change_active(struct kvm_vcpu *vcpu, struct vgic_irq *irq,
 	if (irq->active)
 		vgic_queue_irq_unlock(vcpu->kvm, irq, flags);
 	else
-		spin_unlock_irqrestore(&irq->irq_lock, flags);
+		raw_spin_unlock_irqrestore(&irq->irq_lock, flags);
 }
 
 /*
@@ -485,10 +485,10 @@ void vgic_mmio_write_priority(struct kvm_vcpu *vcpu,
 	for (i = 0; i < len; i++) {
 		struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i);
 
-		spin_lock_irqsave(&irq->irq_lock, flags);
+		raw_spin_lock_irqsave(&irq->irq_lock, flags);
 		/* Narrow the priority range to what we actually support */
 		irq->priority = (val >> (i * 8)) & GENMASK(7, 8 - VGIC_PRI_BITS);
-		spin_unlock_irqrestore(&irq->irq_lock, flags);
+		raw_spin_unlock_irqrestore(&irq->irq_lock, flags);
 
 		vgic_put_irq(vcpu->kvm, irq);
 	}
@@ -534,14 +534,14 @@ void vgic_mmio_write_config(struct kvm_vcpu *vcpu,
 			continue;
 
 		irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i);
-		spin_lock_irqsave(&irq->irq_lock, flags);
+		raw_spin_lock_irqsave(&irq->irq_lock, flags);
 
 		if (test_bit(i * 2 + 1, &val))
 			irq->config = VGIC_CONFIG_EDGE;
 		else
 			irq->config = VGIC_CONFIG_LEVEL;
 
-		spin_unlock_irqrestore(&irq->irq_lock, flags);
+		raw_spin_unlock_irqrestore(&irq->irq_lock, flags);
 		vgic_put_irq(vcpu->kvm, irq);
 	}
 }
@@ -590,12 +590,12 @@ void vgic_write_irq_line_level_info(struct kvm_vcpu *vcpu, u32 intid,
 		 * restore irq config before line level.
 		 */
 		new_level = !!(val & (1U << i));
-		spin_lock_irqsave(&irq->irq_lock, flags);
+		raw_spin_lock_irqsave(&irq->irq_lock, flags);
 		irq->line_level = new_level;
 		if (new_level)
 			vgic_queue_irq_unlock(vcpu->kvm, irq, flags);
 		else
-			spin_unlock_irqrestore(&irq->irq_lock, flags);
+			raw_spin_unlock_irqrestore(&irq->irq_lock, flags);
 
 		vgic_put_irq(vcpu->kvm, irq);
 	}

virt/kvm/arm/vgic/vgic-v2.c

@@ -84,7 +84,7 @@ void vgic_v2_fold_lr_state(struct kvm_vcpu *vcpu)
 
 		irq = vgic_get_irq(vcpu->kvm, vcpu, intid);
 
-		spin_lock(&irq->irq_lock);
+		raw_spin_lock(&irq->irq_lock);
 
 		/* Always preserve the active bit */
 		irq->active = !!(val & GICH_LR_ACTIVE_BIT);
@@ -127,7 +127,7 @@ void vgic_v2_fold_lr_state(struct kvm_vcpu *vcpu)
 				vgic_irq_set_phys_active(irq, false);
 		}
 
-		spin_unlock(&irq->irq_lock);
+		raw_spin_unlock(&irq->irq_lock);
 		vgic_put_irq(vcpu->kvm, irq);
 	}
 

virt/kvm/arm/vgic/vgic-v3.c

@@ -76,7 +76,7 @@ void vgic_v3_fold_lr_state(struct kvm_vcpu *vcpu)
 		if (!irq)	/* An LPI could have been unmapped. */
 			continue;
 
-		spin_lock(&irq->irq_lock);
+		raw_spin_lock(&irq->irq_lock);
 
 		/* Always preserve the active bit */
 		irq->active = !!(val & ICH_LR_ACTIVE_BIT);
@@ -119,7 +119,7 @@ void vgic_v3_fold_lr_state(struct kvm_vcpu *vcpu)
 				vgic_irq_set_phys_active(irq, false);
 		}
 
-		spin_unlock(&irq->irq_lock);
+		raw_spin_unlock(&irq->irq_lock);
 		vgic_put_irq(vcpu->kvm, irq);
 	}
 
@@ -347,9 +347,9 @@ int vgic_v3_lpi_sync_pending_status(struct kvm *kvm, struct vgic_irq *irq)
 
 	status = val & (1 << bit_nr);
 
-	spin_lock_irqsave(&irq->irq_lock, flags);
+	raw_spin_lock_irqsave(&irq->irq_lock, flags);
 	if (irq->target_vcpu != vcpu) {
-		spin_unlock_irqrestore(&irq->irq_lock, flags);
+		raw_spin_unlock_irqrestore(&irq->irq_lock, flags);
 		goto retry;
 	}
 	irq->pending_latch = status;