[Qemu-ppc] [PATCH v4 09/14] spapr: introduce routines to delete the KVM IRQ device

[Cédric Le Goater]

If a new interrupt mode is chosen by CAS, the machine generates a
reset to reconfigure. At this point, the connection with the previous
KVM device needs to be closed and a new connection needs to opened
with the KVM device operating the chosen interrupt mode.

New routines are introduced to destroy the XICS and the XIVE KVM
devices. They make use of a new KVM device ioctl which destroys the
device and also disconnects the IRQ presenters from the vCPUs.

Signed-off-by: Cédric Le Goater <address@hidden>
Reviewed-by: David Gibson <address@hidden>
---

 Changes since v3:

 - removed KVM_DESTROY_DEVICE control. KVM device is destroyed when
   the fd is closed.

 include/hw/ppc/spapr_xive.h |  1 +
 include/hw/ppc/xics_spapr.h |  1 +
 hw/intc/spapr_xive_kvm.c    | 56 +++++++++++++++++++++++++++++++++++++
 hw/intc/xics_kvm.c          | 51 +++++++++++++++++++++++++++++++++
 4 files changed, 109 insertions(+)

diff --git a/include/hw/ppc/spapr_xive.h b/include/hw/ppc/spapr_xive.h
index 04294b0ca266..0b5e972d52c8 100644
--- a/include/hw/ppc/spapr_xive.h
+++ b/include/hw/ppc/spapr_xive.h
@@ -71,6 +71,7 @@ int spapr_xive_end_to_target(uint8_t end_blk, uint32_t 
end_idx,
  * KVM XIVE device helpers
  */
 void kvmppc_xive_connect(SpaprXive *xive, Error **errp);
+void kvmppc_xive_disconnect(SpaprXive *xive, Error **errp);
 void kvmppc_xive_reset(SpaprXive *xive, Error **errp);
 void kvmppc_xive_set_source_config(SpaprXive *xive, uint32_t lisn, XiveEAS 
*eas,
                                    Error **errp);
diff --git a/include/hw/ppc/xics_spapr.h b/include/hw/ppc/xics_spapr.h
index 15a8dcff66fc..2476b540edfa 100644
--- a/include/hw/ppc/xics_spapr.h
+++ b/include/hw/ppc/xics_spapr.h
@@ -34,6 +34,7 @@
 void spapr_dt_xics(SpaprMachineState *spapr, uint32_t nr_servers, void *fdt,
                    uint32_t phandle);
 int xics_kvm_init(SpaprMachineState *spapr, Error **errp);
+void xics_kvm_disconnect(SpaprMachineState *spapr, Error **errp);
 void xics_spapr_init(SpaprMachineState *spapr);
 
 #endif /* XICS_SPAPR_H */
diff --git a/hw/intc/spapr_xive_kvm.c b/hw/intc/spapr_xive_kvm.c
index 3999e4b7edfb..259cd1db9582 100644
--- a/hw/intc/spapr_xive_kvm.c
+++ b/hw/intc/spapr_xive_kvm.c
@@ -58,6 +58,16 @@ static void kvm_cpu_enable(CPUState *cs)
     QLIST_INSERT_HEAD(&kvm_enabled_cpus, enabled_cpu, node);
 }
 
+static void kvm_cpu_disable_all(void)
+{
+    KVMEnabledCPU *enabled_cpu, *next;
+
+    QLIST_FOREACH_SAFE(enabled_cpu, &kvm_enabled_cpus, node, next) {
+        QLIST_REMOVE(enabled_cpu, node);
+        g_free(enabled_cpu);
+    }
+}
+
 /*
  * XIVE Thread Interrupt Management context (KVM)
  */
@@ -709,3 +719,49 @@ void kvmppc_xive_connect(SpaprXive *xive, Error **errp)
     /* Map all regions */
     spapr_xive_map_mmio(xive);
 }
+
+void kvmppc_xive_disconnect(SpaprXive *xive, Error **errp)
+{
+    XiveSource *xsrc;
+    size_t esb_len;
+
+    /* The KVM XIVE device is not in use */
+    if (!xive || xive->fd == -1) {
+        return;
+    }
+
+    if (!kvmppc_has_cap_xive()) {
+        error_setg(errp, "IRQ_XIVE capability must be present for KVM");
+        return;
+    }
+
+    /* Clear the KVM mapping */
+    xsrc = &xive->source;
+    esb_len = (1ull << xsrc->esb_shift) * xsrc->nr_irqs;
+
+    sysbus_mmio_unmap(SYS_BUS_DEVICE(xive), 0);
+    munmap(xsrc->esb_mmap, esb_len);
+
+    sysbus_mmio_unmap(SYS_BUS_DEVICE(xive), 1);
+
+    sysbus_mmio_unmap(SYS_BUS_DEVICE(xive), 2);
+    munmap(xive->tm_mmap, 4ull << TM_SHIFT);
+
+    /*
+     * When the KVM device fd is closed, the KVM device is destroyed
+     * and removed from the list of devices of the VM. The VCPU
+     * presenters are also detached from the device.
+     */
+    close(xive->fd);
+    xive->fd = -1;
+
+    kvm_kernel_irqchip = false;
+    kvm_msi_via_irqfd_allowed = false;
+    kvm_gsi_direct_mapping = false;
+
+    /* Clear the local list of presenter (hotplug) */
+    kvm_cpu_disable_all();
+
+    /* VM Change state handler is not needed anymore */
+    qemu_del_vm_change_state_handler(xive->change);
+}
diff --git a/hw/intc/xics_kvm.c b/hw/intc/xics_kvm.c
index 78a252e6dfd4..1185846ff183 100644
--- a/hw/intc/xics_kvm.c
+++ b/hw/intc/xics_kvm.c
@@ -51,6 +51,16 @@ typedef struct KVMEnabledICP {
 static QLIST_HEAD(, KVMEnabledICP)
     kvm_enabled_icps = QLIST_HEAD_INITIALIZER(&kvm_enabled_icps);
 
+static void kvm_disable_icps(void)
+{
+    KVMEnabledICP *enabled_icp, *next;
+
+    QLIST_FOREACH_SAFE(enabled_icp, &kvm_enabled_icps, node, next) {
+        QLIST_REMOVE(enabled_icp, node);
+        g_free(enabled_icp);
+    }
+}
+
 /*
  * ICP-KVM
  */
@@ -360,3 +370,44 @@ fail:
     kvmppc_define_rtas_kernel_token(0, "ibm,int-off");
     return -1;
 }
+
+void xics_kvm_disconnect(SpaprMachineState *spapr, Error **errp)
+{
+    /* The KVM XICS device is not in use */
+    if (kernel_xics_fd == -1) {
+        return;
+    }
+
+    if (!kvm_enabled() || !kvm_check_extension(kvm_state, KVM_CAP_IRQ_XICS)) {
+        error_setg(errp,
+                   "KVM and IRQ_XICS capability must be present for KVM XICS 
device");
+        return;
+    }
+
+    /*
+     * Only on P9 using the XICS-on XIVE KVM device:
+     *
+     * When the KVM device fd is closed, the device is destroyed and
+     * removed from the list of devices of the VM. The VCPU presenters
+     * are also detached from the device.
+     */
+    close(kernel_xics_fd);
+    kernel_xics_fd = -1;
+
+    spapr_rtas_unregister(RTAS_IBM_SET_XIVE);
+    spapr_rtas_unregister(RTAS_IBM_GET_XIVE);
+    spapr_rtas_unregister(RTAS_IBM_INT_OFF);
+    spapr_rtas_unregister(RTAS_IBM_INT_ON);
+
+    kvmppc_define_rtas_kernel_token(0, "ibm,set-xive");
+    kvmppc_define_rtas_kernel_token(0, "ibm,get-xive");
+    kvmppc_define_rtas_kernel_token(0, "ibm,int-on");
+    kvmppc_define_rtas_kernel_token(0, "ibm,int-off");
+
+    kvm_kernel_irqchip = false;
+    kvm_msi_via_irqfd_allowed = false;
+    kvm_gsi_direct_mapping = false;
+
+    /* Clear the presenter from the VCPUs */
+    kvm_disable_icps();
+}
-- 
2.20.1