Merge tag 'kvmarm-6.18' of git://git.kernel.org/pub/scm/linux/kernel/git/kvmarm/kvmarm into HEAD

KVM/arm64 updates for 6.18

- Add support for FF-A 1.2 as the secure memory conduit for pKVM,
  allowing more registers to be used as part of the message payload.

- Change the way pKVM allocates its VM handles, making sure that the
  privileged hypervisor is never tricked into using uninitialised
  data.

- Speed up MMIO range registration by avoiding unnecessary RCU
  synchronisation, which results in VMs starting much quicker.

- Add the dump of the instruction stream when panic-ing in the EL2
  payload, just like the rest of the kernel has always done. This will
  hopefully help debugging non-VHE setups.

- Add 52bit PA support to the stage-1 page-table walker, and make use
  of it to populate the fault level reported to the guest on failing
  to translate a stage-1 walk.

- Add NV support to the GICv3-on-GICv5 emulation code, ensuring
  feature parity for guests, irrespective of the host platform.

- Fix some really ugly architecture problems when dealing with debug
  in a nested VM. This has some bad performance impacts, but is at
  least correct.

- Add enough infrastructure to be able to disable EL2 features and
  give effective values to the EL2 control registers. This then allows
  a bunch of features to be turned off, which helps cross-host
  migration.

- Large rework of the selftest infrastructure to allow most tests to
  transparently run at EL2. This is the first step towards enabling
  NV testing.

- Various fixes and improvements all over the map, including one BE
  fix, just in time for the removal of the feature.

1 files changed, 35 insertions, 8 deletions

diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 18f29ef93543..f2e77ebee0ff 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -1103,6 +1103,14 @@ void __weak kvm_arch_create_vm_debugfs(struct kvm *kvm)
 {
 }
 
+/* Called only on cleanup and destruction paths when there are no users. */
+static inline struct kvm_io_bus *kvm_get_bus_for_destruction(struct kvm *kvm,
+							     enum kvm_bus idx)
+{
+	return rcu_dereference_protected(kvm->buses[idx],
+					 !refcount_read(&kvm->users_count));
+}
+
 static struct kvm *kvm_create_vm(unsigned long type, const char *fdname)
 {
 	struct kvm *kvm = kvm_arch_alloc_vm();
@@ -1228,7 +1236,7 @@ out_err_no_disable:
 out_err_no_arch_destroy_vm:
 	WARN_ON_ONCE(!refcount_dec_and_test(&kvm->users_count));
 	for (i = 0; i < KVM_NR_BUSES; i++)
-		kfree(kvm_get_bus(kvm, i));
+		kfree(kvm_get_bus_for_destruction(kvm, i));
 	kvm_free_irq_routing(kvm);
 out_err_no_irq_routing:
 	cleanup_srcu_struct(&kvm->irq_srcu);
@@ -1276,7 +1284,7 @@ static void kvm_destroy_vm(struct kvm *kvm)
 
 	kvm_free_irq_routing(kvm);
 	for (i = 0; i < KVM_NR_BUSES; i++) {
-		struct kvm_io_bus *bus = kvm_get_bus(kvm, i);
+		struct kvm_io_bus *bus = kvm_get_bus_for_destruction(kvm, i);
 
 		if (bus)
 			kvm_io_bus_destroy(bus);
@@ -1312,6 +1320,7 @@ static void kvm_destroy_vm(struct kvm *kvm)
 		kvm_free_memslots(kvm, &kvm->__memslots[i][1]);
 	}
 	cleanup_srcu_struct(&kvm->irq_srcu);
+	srcu_barrier(&kvm->srcu);
 	cleanup_srcu_struct(&kvm->srcu);
 #ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES
 	xa_destroy(&kvm->mem_attr_array);
@@ -5845,6 +5854,18 @@ static int __kvm_io_bus_write(struct kvm_vcpu *vcpu, struct kvm_io_bus *bus,
 	return -EOPNOTSUPP;
 }
 
+static struct kvm_io_bus *kvm_get_bus_srcu(struct kvm *kvm, enum kvm_bus idx)
+{
+	/*
+	 * Ensure that any updates to kvm_buses[] observed by the previous vCPU
+	 * machine instruction are also visible to the vCPU machine instruction
+	 * that triggered this call.
+	 */
+	smp_mb__after_srcu_read_lock();
+
+	return srcu_dereference(kvm->buses[idx], &kvm->srcu);
+}
+
 int kvm_io_bus_write(struct kvm_vcpu *vcpu, enum kvm_bus bus_idx, gpa_t addr,
 		     int len, const void *val)
 {
@@ -5857,7 +5878,7 @@ int kvm_io_bus_write(struct kvm_vcpu *vcpu, enum kvm_bus bus_idx, gpa_t addr,
 		.len = len,
 	};
 
-	bus = srcu_dereference(vcpu->kvm->buses[bus_idx], &vcpu->kvm->srcu);
+	bus = kvm_get_bus_srcu(vcpu->kvm, bus_idx);
 	if (!bus)
 		return -ENOMEM;
 	r = __kvm_io_bus_write(vcpu, bus, &range, val);
@@ -5876,7 +5897,7 @@ int kvm_io_bus_write_cookie(struct kvm_vcpu *vcpu, enum kvm_bus bus_idx,
 		.len = len,
 	};
 
-	bus = srcu_dereference(vcpu->kvm->buses[bus_idx], &vcpu->kvm->srcu);
+	bus = kvm_get_bus_srcu(vcpu->kvm, bus_idx);
 	if (!bus)
 		return -ENOMEM;
 
@@ -5926,7 +5947,7 @@ int kvm_io_bus_read(struct kvm_vcpu *vcpu, enum kvm_bus bus_idx, gpa_t addr,
 		.len = len,
 	};
 
-	bus = srcu_dereference(vcpu->kvm->buses[bus_idx], &vcpu->kvm->srcu);
+	bus = kvm_get_bus_srcu(vcpu->kvm, bus_idx);
 	if (!bus)
 		return -ENOMEM;
 	r = __kvm_io_bus_read(vcpu, bus, &range, val);
@@ -5934,6 +5955,13 @@ int kvm_io_bus_read(struct kvm_vcpu *vcpu, enum kvm_bus bus_idx, gpa_t addr,
 }
 EXPORT_SYMBOL_GPL(kvm_io_bus_read);
 
+static void __free_bus(struct rcu_head *rcu)
+{
+	struct kvm_io_bus *bus = container_of(rcu, struct kvm_io_bus, rcu);
+
+	kfree(bus);
+}
+
 int kvm_io_bus_register_dev(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr,
 			    int len, struct kvm_io_device *dev)
 {
@@ -5972,8 +6000,7 @@ int kvm_io_bus_register_dev(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr,
 	memcpy(new_bus->range + i + 1, bus->range + i,
 		(bus->dev_count - i) * sizeof(struct kvm_io_range));
 	rcu_assign_pointer(kvm->buses[bus_idx], new_bus);
-	synchronize_srcu_expedited(&kvm->srcu);
-	kfree(bus);
+	call_srcu(&kvm->srcu, &bus->rcu, __free_bus);
 
 	return 0;
 }
@@ -6035,7 +6062,7 @@ struct kvm_io_device *kvm_io_bus_get_dev(struct kvm *kvm, enum kvm_bus bus_idx,
 
 	srcu_idx = srcu_read_lock(&kvm->srcu);
 
-	bus = srcu_dereference(kvm->buses[bus_idx], &kvm->srcu);
+	bus = kvm_get_bus_srcu(kvm, bus_idx);
 	if (!bus)
 		goto out_unlock;