[PATCH v1 04/28] accel/kvm: add changes required to support KVM VM file descriptor change

[Ani Sinha <anisinha@redhat.com>]

This change adds common kvm specific support to handle KVM VM file descriptor
change. KVM VM file descriptor can change as a part of confidential guest reset
mechanism. A new function api kvm_arch_vmfd_change_ops() per
architecture platform is added in order to implement architecture specific
changes required to support it. A subsequent patch will add x86 specific
implementation for kvm_arch_vmfd_change_ops as currently only x86 supports
confidential guest reset.

Signed-off-by: Ani Sinha <anisinha@redhat.com>
---
 accel/kvm/kvm-all.c        | 70 ++++++++++++++++++++++++++++++++++++--
 include/system/kvm.h       |  1 +
 target/arm/kvm.c           |  5 +++
 target/i386/kvm/kvm.c      |  5 +++
 target/loongarch/kvm/kvm.c |  5 +++
 target/mips/kvm.c          |  5 +++
 target/ppc/kvm.c           |  5 +++
 target/riscv/kvm/kvm-cpu.c |  5 +++
 target/s390x/kvm/kvm.c     |  5 +++
 9 files changed, 103 insertions(+), 3 deletions(-)

diff --git a/accel/kvm/kvm-all.c b/accel/kvm/kvm-all.c
index 28006d73c5..c9564bf681 100644
--- a/accel/kvm/kvm-all.c
+++ b/accel/kvm/kvm-all.c
@@ -2415,11 +2415,9 @@ void kvm_irqchip_set_qemuirq_gsi(KVMState *s, qemu_irq irq, int gsi)
     g_hash_table_insert(s->gsimap, irq, GINT_TO_POINTER(gsi));
 }
 
-static void kvm_irqchip_create(KVMState *s)
+static void do_kvm_irqchip_create(KVMState *s)
 {
     int ret;
-
-    assert(s->kernel_irqchip_split != ON_OFF_AUTO_AUTO);
     if (kvm_check_extension(s, KVM_CAP_IRQCHIP)) {
         ;
     } else if (kvm_check_extension(s, KVM_CAP_S390_IRQCHIP)) {
@@ -2452,7 +2450,13 @@ static void kvm_irqchip_create(KVMState *s)
         fprintf(stderr, "Create kernel irqchip failed: %s\n", strerror(-ret));
         exit(1);
     }
+}
 
+static void kvm_irqchip_create(KVMState *s)
+{
+    assert(s->kernel_irqchip_split != ON_OFF_AUTO_AUTO);
+
+    do_kvm_irqchip_create(s);
     kvm_kernel_irqchip = true;
     /* If we have an in-kernel IRQ chip then we must have asynchronous
      * interrupt delivery (though the reverse is not necessarily true)
@@ -2607,6 +2611,65 @@ static int kvm_setup_dirty_ring(KVMState *s)
     return 0;
 }
 
+static int kvm_reset_vmfd(MachineState *ms)
+{
+    KVMState *s;
+    KVMMemoryListener *kml;
+    int ret, type;
+    Error *err = NULL;
+
+    s = KVM_STATE(ms->accelerator);
+    kml = &s->memory_listener;
+
+    memory_listener_unregister(&kml->listener);
+    memory_listener_unregister(&kvm_io_listener);
+
+    if (s->vmfd >= 0) {
+        close(s->vmfd);
+    }
+
+    type = find_kvm_machine_type(ms);
+    if (type < 0) {
+        return -EINVAL;
+    }
+
+    ret = do_kvm_create_vm(s, type);
+    if (ret < 0) {
+        return ret;
+    }
+
+    s->vmfd = ret;
+
+    kvm_setup_dirty_ring(s);
+
+    /* rebind memory to new vm fd */
+    ret = ram_block_rebind(&err);
+    if (ret < 0) {
+        return ret;
+    }
+    assert(!err);
+
+    ret = kvm_arch_vmfd_change_ops(ms, s);
+    if (ret < 0) {
+        return ret;
+    }
+
+    if (s->kernel_irqchip_allowed) {
+        do_kvm_irqchip_create(s);
+    }
+
+    /* these can be only called after ram_block_rebind() */
+    memory_listener_register(&kml->listener, &address_space_memory);
+    memory_listener_register(&kvm_io_listener, &address_space_io);
+
+    /*
+     * kvm fd has changed. Commit the irq routes to KVM once more.
+     */
+    kvm_irqchip_commit_routes(s);
+
+    return ret;
+}
+
 static int kvm_init(AccelState *as, MachineState *ms)
 {
     MachineClass *mc = MACHINE_GET_CLASS(ms);
@@ -4014,6 +4077,7 @@ static void kvm_accel_class_init(ObjectClass *oc, const void *data)
     AccelClass *ac = ACCEL_CLASS(oc);
     ac->name = "KVM";
     ac->init_machine = kvm_init;
+    ac->reset_vmfd = kvm_reset_vmfd;
     ac->has_memory = kvm_accel_has_memory;
     ac->allowed = &kvm_allowed;
     ac->gdbstub_supported_sstep_flags = kvm_gdbstub_sstep_flags;
diff --git a/include/system/kvm.h b/include/system/kvm.h
index 8f9eecf044..ade13dd8cc 100644
--- a/include/system/kvm.h
+++ b/include/system/kvm.h
@@ -358,6 +358,7 @@ int kvm_arch_init(MachineState *ms, KVMState *s);
 int kvm_arch_pre_create_vcpu(CPUState *cpu, Error **errp);
 int kvm_arch_init_vcpu(CPUState *cpu);
 int kvm_arch_destroy_vcpu(CPUState *cpu);
+int kvm_arch_vmfd_change_ops(MachineState *ms, KVMState *s);
 
 #ifdef TARGET_KVM_HAVE_RESET_PARKED_VCPU
 void kvm_arch_reset_parked_vcpu(unsigned long vcpu_id, int kvm_fd);
diff --git a/target/arm/kvm.c b/target/arm/kvm.c
index 0d57081e69..919bf95ae1 100644
--- a/target/arm/kvm.c
+++ b/target/arm/kvm.c
@@ -1568,6 +1568,11 @@ void kvm_arch_init_irq_routing(KVMState *s)
 {
 }
 
+int kvm_arch_vmfd_change_ops(MachineState *ms, KVMState *s)
+{
+    abort();
+}
+
 int kvm_arch_irqchip_create(KVMState *s)
 {
     if (kvm_kernel_irqchip_split()) {
diff --git a/target/i386/kvm/kvm.c b/target/i386/kvm/kvm.c
index 02819de625..cdfcb70f40 100644
--- a/target/i386/kvm/kvm.c
+++ b/target/i386/kvm/kvm.c
@@ -3252,6 +3252,11 @@ static int kvm_vm_enable_energy_msrs(KVMState *s)
     return 0;
 }
 
+int kvm_arch_vmfd_change_ops(MachineState *ms, KVMState *s)
+{
+    abort();
+}
+
 int kvm_arch_init(MachineState *ms, KVMState *s)
 {
     int ret;
diff --git a/target/loongarch/kvm/kvm.c b/target/loongarch/kvm/kvm.c
index 26e40c9bdc..4171781346 100644
--- a/target/loongarch/kvm/kvm.c
+++ b/target/loongarch/kvm/kvm.c
@@ -1312,6 +1312,11 @@ int kvm_arch_irqchip_create(KVMState *s)
     return kvm_check_extension(s, KVM_CAP_DEVICE_CTRL);
 }
 
+int kvm_arch_vmfd_change_ops(MachineState *ms, KVMState *s)
+{
+    return 0;
+}
+
 void kvm_arch_pre_run(CPUState *cs, struct kvm_run *run)
 {
 }
diff --git a/target/mips/kvm.c b/target/mips/kvm.c
index 912cd5dfa0..28730da06b 100644
--- a/target/mips/kvm.c
+++ b/target/mips/kvm.c
@@ -44,6 +44,11 @@ unsigned long kvm_arch_vcpu_id(CPUState *cs)
     return cs->cpu_index;
 }
 
+int kvm_arch_vmfd_change_ops(MachineState *ms, KVMState *s)
+{
+    return 0;
+}
+
 int kvm_arch_init(MachineState *ms, KVMState *s)
 {
     /* MIPS has 128 signals */
diff --git a/target/ppc/kvm.c b/target/ppc/kvm.c
index 43124bf1c7..a48dc7670b 100644
--- a/target/ppc/kvm.c
+++ b/target/ppc/kvm.c
@@ -180,6 +180,11 @@ int kvm_arch_irqchip_create(KVMState *s)
     return 0;
 }
 
+int kvm_arch_vmfd_change_ops(MachineState *ms, KVMState *s)
+{
+    return 0;
+}
+
 static int kvm_arch_sync_sregs(PowerPCCPU *cpu)
 {
     CPUPPCState *cenv = &cpu->env;
diff --git a/target/riscv/kvm/kvm-cpu.c b/target/riscv/kvm/kvm-cpu.c
index 47e672c7aa..ca384a8b85 100644
--- a/target/riscv/kvm/kvm-cpu.c
+++ b/target/riscv/kvm/kvm-cpu.c
@@ -1545,6 +1545,11 @@ int kvm_arch_irqchip_create(KVMState *s)
     return kvm_check_extension(s, KVM_CAP_DEVICE_CTRL);
 }
 
+int kvm_arch_vmfd_change_ops(MachineState *ms, KVMState *s)
+{
+    return 0;
+}
+
 int kvm_arch_process_async_events(CPUState *cs)
 {
     return 0;
diff --git a/target/s390x/kvm/kvm.c b/target/s390x/kvm/kvm.c
index 916dac1f14..671c854634 100644
--- a/target/s390x/kvm/kvm.c
+++ b/target/s390x/kvm/kvm.c
@@ -393,6 +393,11 @@ int kvm_arch_irqchip_create(KVMState *s)
     return 0;
 }
 
+int kvm_arch_vmfd_change_ops(MachineState *ms, KVMState *s)
+{
+    return 0;
+}
+
 unsigned long kvm_arch_vcpu_id(CPUState *cpu)
 {
     return cpu->cpu_index;
-- 
2.42.0