Merge branch kvm-arm64/misc-6.10 into kvmarm-master/next

* kvm-arm64/misc-6.10:
  : .
  : Misc fixes and updates targeting 6.10
  :
  : - Improve boot-time diagnostics when the sysreg tables
  :   are not correctly sorted
  :
  : - Allow FFA_MSG_SEND_DIRECT_REQ in the FFA proxy
  :
  : - Fix duplicate XNX field in the ID_AA64MMFR1_EL1
  :   writeable mask
  :
  : - Allocate PPIs and SGIs outside of the vcpu structure, allowing
  :   for smaller EL2 mapping and some flexibility in implementing
  :   more or less than 32 private IRQs.
  :
  : - Use bitmap_gather() instead of its open-coded equivalent
  :
  : - Make protected mode use hVHE if available
  :
  : - Purge stale mpidr_data if a vcpu is created after the MPIDR
  :   map has been created
  : .
  KVM: arm64: Destroy mpidr_data for 'late' vCPU creation
  KVM: arm64: Use hVHE in pKVM by default on CPUs with VHE support
  KVM: arm64: Fix hvhe/nvhe early alias parsing
  KVM: arm64: Convert kvm_mpidr_index() to bitmap_gather()
  KVM: arm64: vgic: Allocate private interrupts on demand
  KVM: arm64: Remove duplicated AA64MMFR1_EL1 XNX
  KVM: arm64: Remove FFA_MSG_SEND_DIRECT_REQ from the denylist
  KVM: arm64: Improve out-of-order sysreg table diagnostics

Signed-off-by: Marc Zyngier <maz@kernel.org>

arch/arm64/include/asm/kvm_host.h

@@ -221,20 +221,10 @@ struct kvm_mpidr_data {
 
 static inline u16 kvm_mpidr_index(struct kvm_mpidr_data *data, u64 mpidr)
 {
-	unsigned long mask = data->mpidr_mask;
+	unsigned long index = 0, mask = data->mpidr_mask;
-	u64 aff = mpidr & MPIDR_HWID_BITMASK;
+	unsigned long aff = mpidr & MPIDR_HWID_BITMASK;
-	int nbits, bit, bit_idx = 0;
-	u16 index = 0;
 
-	/*
+	bitmap_gather(&index, &aff, &mask, fls(mask));
-	 * If this looks like RISC-V's BEXT or x86's PEXT
-	 * instructions, it isn't by accident.
-	 */
-	nbits = fls(mask);
-	for_each_set_bit(bit, &mask, nbits) {
-		index |= (aff & BIT(bit)) >> (bit - bit_idx);
-		bit_idx++;
-	}
 
 	return index;
 }

arch/arm64/kernel/pi/idreg-override.c

@@ -209,8 +209,8 @@ static const struct {
 	char	alias[FTR_ALIAS_NAME_LEN];
 	char	feature[FTR_ALIAS_OPTION_LEN];
 } aliases[] __initconst = {
-	{ "kvm_arm.mode=nvhe",		"id_aa64mmfr1.vh=0" },
+	{ "kvm_arm.mode=nvhe",		"arm64_sw.hvhe=0 id_aa64mmfr1.vh=0" },
-	{ "kvm_arm.mode=protected",	"id_aa64mmfr1.vh=0" },
+	{ "kvm_arm.mode=protected",	"arm64_sw.hvhe=1" },
 	{ "arm64.nosve",		"id_aa64pfr0.sve=0" },
 	{ "arm64.nosme",		"id_aa64pfr1.sme=0" },
 	{ "arm64.nobti",		"id_aa64pfr1.bt=0" },

arch/arm64/kvm/arm.c

@@ -218,6 +218,23 @@ void kvm_arch_create_vm_debugfs(struct kvm *kvm)
 	kvm_sys_regs_create_debugfs(kvm);
 }
 
+static void kvm_destroy_mpidr_data(struct kvm *kvm)
+{
+	struct kvm_mpidr_data *data;
+
+	mutex_lock(&kvm->arch.config_lock);
+
+	data = rcu_dereference_protected(kvm->arch.mpidr_data,
+					 lockdep_is_held(&kvm->arch.config_lock));
+	if (data) {
+		rcu_assign_pointer(kvm->arch.mpidr_data, NULL);
+		synchronize_rcu();
+		kfree(data);
+	}
+
+	mutex_unlock(&kvm->arch.config_lock);
+}
+
 /**
  * kvm_arch_destroy_vm - destroy the VM data structure
  * @kvm:	pointer to the KVM struct
@@ -232,7 +249,8 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
 	if (is_protected_kvm_enabled())
 		pkvm_destroy_hyp_vm(kvm);
 
-	kfree(kvm->arch.mpidr_data);
+	kvm_destroy_mpidr_data(kvm);
+
 	kfree(kvm->arch.sysreg_masks);
 	kvm_destroy_vcpus(kvm);
 
@@ -450,6 +468,13 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
 
 	vcpu->arch.hw_mmu = &vcpu->kvm->arch.mmu;
 
+	/*
+	 * This vCPU may have been created after mpidr_data was initialized.
+	 * Throw out the pre-computed mappings if that is the case which forces
+	 * KVM to fall back to iteratively searching the vCPUs.
+	 */
+	kvm_destroy_mpidr_data(vcpu->kvm);
+
 	err = kvm_vgic_vcpu_init(vcpu);
 	if (err)
 		return err;
@@ -687,7 +712,8 @@ static void kvm_init_mpidr_data(struct kvm *kvm)
 
 	mutex_lock(&kvm->arch.config_lock);
 
-	if (kvm->arch.mpidr_data || atomic_read(&kvm->online_vcpus) == 1)
+	if (rcu_access_pointer(kvm->arch.mpidr_data) ||
+	    atomic_read(&kvm->online_vcpus) == 1)
 		goto out;
 
 	kvm_for_each_vcpu(c, vcpu, kvm) {
@@ -724,7 +750,7 @@ static void kvm_init_mpidr_data(struct kvm *kvm)
 		data->cmpidr_to_idx[index] = c;
 	}
 
-	kvm->arch.mpidr_data = data;
+	rcu_assign_pointer(kvm->arch.mpidr_data, data);
 out:
 	mutex_unlock(&kvm->arch.config_lock);
 }
@@ -2562,22 +2588,28 @@ out_err:
 
 struct kvm_vcpu *kvm_mpidr_to_vcpu(struct kvm *kvm, unsigned long mpidr)
 {
-	struct kvm_vcpu *vcpu;
+	struct kvm_vcpu *vcpu = NULL;
+	struct kvm_mpidr_data *data;
 	unsigned long i;
 
 	mpidr &= MPIDR_HWID_BITMASK;
 
-	if (kvm->arch.mpidr_data) {
+	rcu_read_lock();
-		u16 idx = kvm_mpidr_index(kvm->arch.mpidr_data, mpidr);
+	data = rcu_dereference(kvm->arch.mpidr_data);
 
-		vcpu = kvm_get_vcpu(kvm,
+	if (data) {
-				    kvm->arch.mpidr_data->cmpidr_to_idx[idx]);
+		u16 idx = kvm_mpidr_index(data, mpidr);
+
+		vcpu = kvm_get_vcpu(kvm, data->cmpidr_to_idx[idx]);
 		if (mpidr != kvm_vcpu_get_mpidr_aff(vcpu))
 			vcpu = NULL;
-
-		return vcpu;
 	}
 
+	rcu_read_unlock();
+
+	if (vcpu)
+		return vcpu;
+
 	kvm_for_each_vcpu(i, vcpu, kvm) {
 		if (mpidr == kvm_vcpu_get_mpidr_aff(vcpu))
 			return vcpu;

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

@@ -600,7 +600,6 @@ static bool ffa_call_supported(u64 func_id)
 	case FFA_MSG_POLL:
 	case FFA_MSG_WAIT:
 	/* 32-bit variants of 64-bit calls */
-	case FFA_MSG_SEND_DIRECT_REQ:
 	case FFA_MSG_SEND_DIRECT_RESP:
 	case FFA_RXTX_MAP:
 	case FFA_MEM_DONATE:

arch/arm64/kvm/sys_regs.c

@@ -2338,7 +2338,6 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 					ID_AA64MMFR0_EL1_TGRAN16_2)),
 	ID_WRITABLE(ID_AA64MMFR1_EL1, ~(ID_AA64MMFR1_EL1_RES0 |
 					ID_AA64MMFR1_EL1_HCX |
-					ID_AA64MMFR1_EL1_XNX |
 					ID_AA64MMFR1_EL1_TWED |
 					ID_AA64MMFR1_EL1_XNX |
 					ID_AA64MMFR1_EL1_VH |
@@ -3069,12 +3068,14 @@ static bool check_sysreg_table(const struct sys_reg_desc *table, unsigned int n,
 
 	for (i = 0; i < n; i++) {
 		if (!is_32 && table[i].reg && !table[i].reset) {
-			kvm_err("sys_reg table %pS entry %d lacks reset\n", &table[i], i);
+			kvm_err("sys_reg table %pS entry %d (%s) lacks reset\n",
+				&table[i], i, table[i].name);
 			return false;
 		}
 
 		if (i && cmp_sys_reg(&table[i-1], &table[i]) >= 0) {
-			kvm_err("sys_reg table %pS entry %d out of order\n", &table[i - 1], i - 1);
+			kvm_err("sys_reg table %pS entry %d (%s -> %s) out of order\n",
+				&table[i], i, table[i - 1].name, table[i].name);
 			return false;
 		}
 	}

arch/arm64/kvm/vgic/vgic-init.c

@@ -180,27 +180,22 @@ static int kvm_vgic_dist_init(struct kvm *kvm, unsigned int nr_spis)
 	return 0;
 }
 
-/**
+static int vgic_allocate_private_irqs_locked(struct kvm_vcpu *vcpu)
- * kvm_vgic_vcpu_init() - Initialize static VGIC VCPU data
- * structures and register VCPU-specific KVM iodevs
- *
- * @vcpu: pointer to the VCPU being created and initialized
- *
- * Only do initialization, but do not actually enable the
- * VGIC CPU interface
- */
-int kvm_vgic_vcpu_init(struct kvm_vcpu *vcpu)
 {
 	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
-	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
-	int ret = 0;
 	int i;
 
-	vgic_cpu->rd_iodev.base_addr = VGIC_ADDR_UNDEF;
+	lockdep_assert_held(&vcpu->kvm->arch.config_lock);
 
-	INIT_LIST_HEAD(&vgic_cpu->ap_list_head);
+	if (vgic_cpu->private_irqs)
-	raw_spin_lock_init(&vgic_cpu->ap_list_lock);
+		return 0;
-	atomic_set(&vgic_cpu->vgic_v3.its_vpe.vlpi_count, 0);
+
+	vgic_cpu->private_irqs = kcalloc(VGIC_NR_PRIVATE_IRQS,
+					 sizeof(struct vgic_irq),
+					 GFP_KERNEL_ACCOUNT);
+
+	if (!vgic_cpu->private_irqs)
+		return -ENOMEM;
 
 	/*
 	 * Enable and configure all SGIs to be edge-triggered and
@@ -225,9 +220,48 @@ int kvm_vgic_vcpu_init(struct kvm_vcpu *vcpu)
 		}
 	}
 
+	return 0;
+}
+
+static int vgic_allocate_private_irqs(struct kvm_vcpu *vcpu)
+{
+	int ret;
+
+	mutex_lock(&vcpu->kvm->arch.config_lock);
+	ret = vgic_allocate_private_irqs_locked(vcpu);
+	mutex_unlock(&vcpu->kvm->arch.config_lock);
+
+	return ret;
+}
+
+/**
+ * kvm_vgic_vcpu_init() - Initialize static VGIC VCPU data
+ * structures and register VCPU-specific KVM iodevs
+ *
+ * @vcpu: pointer to the VCPU being created and initialized
+ *
+ * Only do initialization, but do not actually enable the
+ * VGIC CPU interface
+ */
+int kvm_vgic_vcpu_init(struct kvm_vcpu *vcpu)
+{
+	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
+	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
+	int ret = 0;
+
+	vgic_cpu->rd_iodev.base_addr = VGIC_ADDR_UNDEF;
+
+	INIT_LIST_HEAD(&vgic_cpu->ap_list_head);
+	raw_spin_lock_init(&vgic_cpu->ap_list_lock);
+	atomic_set(&vgic_cpu->vgic_v3.its_vpe.vlpi_count, 0);
+
 	if (!irqchip_in_kernel(vcpu->kvm))
 		return 0;
 
+	ret = vgic_allocate_private_irqs(vcpu);
+	if (ret)
+		return ret;
+
 	/*
 	 * If we are creating a VCPU with a GICv3 we must also register the
 	 * KVM io device for the redistributor that belongs to this VCPU.
@@ -283,10 +317,13 @@ int vgic_init(struct kvm *kvm)
 
 	/* 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;
+		ret = vgic_allocate_private_irqs_locked(vcpu);
+		if (ret)
+			goto out;
 
 		for (i = 0; i < VGIC_NR_PRIVATE_IRQS; i++) {
-			struct vgic_irq *irq = &vgic_cpu->private_irqs[i];
+			struct vgic_irq *irq = vgic_get_irq(kvm, vcpu, i);
+
 			switch (dist->vgic_model) {
 			case KVM_DEV_TYPE_ARM_VGIC_V3:
 				irq->group = 1;
@@ -298,8 +335,12 @@ int vgic_init(struct kvm *kvm)
 				break;
 			default:
 				ret = -EINVAL;
-				goto out;
 			}
+
+			vgic_put_irq(kvm, irq);
+
+			if (ret)
+				goto out;
 		}
 	}
 
@@ -373,6 +414,9 @@ static void __kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu)
 	vgic_flush_pending_lpis(vcpu);
 
 	INIT_LIST_HEAD(&vgic_cpu->ap_list_head);
+	kfree(vgic_cpu->private_irqs);
+	vgic_cpu->private_irqs = NULL;
+
 	if (vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3) {
 		vgic_unregister_redist_iodev(vcpu);
 		vgic_cpu->rd_iodev.base_addr = VGIC_ADDR_UNDEF;

include/kvm/arm_vgic.h

@@ -331,7 +331,7 @@ struct vgic_cpu {
 		struct vgic_v3_cpu_if	vgic_v3;
 	};
 
-	struct vgic_irq private_irqs[VGIC_NR_PRIVATE_IRQS];
+	struct vgic_irq *private_irqs;
 
 	raw_spinlock_t ap_list_lock;	/* Protects the ap_list */