Setup empty IRQ routing during VM creation so that x86 and s390 don't need
to set empty/dummy IRQ routing during KVM_CREATE_IRQCHIP (in future
patches). Initializing IRQ routing before there are any potential readers
allows KVM to avoid the synchronize_srcu() in kvm_set_irq_routing(), which
can introduces 20+ milliseconds of latency in the VM creation path.
Ensuring that all VMs have non-NULL IRQ routing also hardens KVM against
misbehaving userspace VMMs, e.g. RISC-V dynamically instantiates its
interrupt controller, but doesn't override kvm_arch_intc_initialized() or
kvm_arch_irqfd_allowed(), and so can likely reach kvm_irq_map_gsi()
without fully initialized IRQ routing.
Signed-off-by: Yi Wang <foxywang@tencent.com>
Acked-by: Christian Borntraeger <borntraeger@linux.ibm.com>
Link: https://lore.kernel.org/r/20240506101751.3145407-2-foxywang@tencent.com
[sean: init refcount after IRQ routing, fix stub, massage changelog]
Signed-off-by: Sean Christopherson <seanjc@google.com>
const struct kvm_irq_routing_entry *entries,
unsigned nr,
unsigned flags);
+int kvm_init_irq_routing(struct kvm *kvm);
int kvm_set_routing_entry(struct kvm *kvm,
struct kvm_kernel_irq_routing_entry *e,
const struct kvm_irq_routing_entry *ue);
static inline void kvm_free_irq_routing(struct kvm *kvm) {}
+static inline int kvm_init_irq_routing(struct kvm *kvm)
+{
+ return 0;
+}
+
#endif
int kvm_send_userspace_msi(struct kvm *kvm, struct kvm_msi *msi);
return r;
}
+
+/*
+ * Allocate empty IRQ routing by default so that additional setup isn't needed
+ * when userspace-driven IRQ routing is activated, and so that kvm->irq_routing
+ * is guaranteed to be non-NULL.
+ */
+int kvm_init_irq_routing(struct kvm *kvm)
+{
+ struct kvm_irq_routing_table *new;
+ int chip_size;
+
+ new = kzalloc(struct_size(new, map, 1), GFP_KERNEL_ACCOUNT);
+ if (!new)
+ return -ENOMEM;
+
+ new->nr_rt_entries = 1;
+
+ chip_size = sizeof(int) * KVM_NR_IRQCHIPS * KVM_IRQCHIP_NUM_PINS;
+ memset(new->chip, -1, chip_size);
+
+ RCU_INIT_POINTER(kvm->irq_routing, new);
+
+ return 0;
+}
if (init_srcu_struct(&kvm->irq_srcu))
goto out_err_no_irq_srcu;
+ r = kvm_init_irq_routing(kvm);
+ if (r)
+ goto out_err_no_irq_routing;
+
refcount_set(&kvm->users_count, 1);
+
for (i = 0; i < kvm_arch_nr_memslot_as_ids(kvm); i++) {
for (j = 0; j < 2; j++) {
slots = &kvm->__memslots[i][j];
WARN_ON_ONCE(!refcount_dec_and_test(&kvm->users_count));
for (i = 0; i < KVM_NR_BUSES; i++)
kfree(kvm_get_bus(kvm, i));
+ kvm_free_irq_routing(kvm);
+out_err_no_irq_routing:
cleanup_srcu_struct(&kvm->irq_srcu);
out_err_no_irq_srcu:
cleanup_srcu_struct(&kvm->srcu);