[Qemu-devel] [PATCH v5 33/36] spapr: introduce routines to delete the KVM IRQ device

["Cédric Le Goater" <clg@kaod.org>]

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 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 <clg@kaod.org>
---
 include/hw/ppc/spapr_xive.h |  1 +
 include/hw/ppc/xics.h       |  1 +
 linux-headers/linux/kvm.h   |  2 ++
 hw/intc/spapr_xive_kvm.c    | 54 +++++++++++++++++++++++++++++++++++
 hw/intc/xics_kvm.c          | 57 +++++++++++++++++++++++++++++++++++++
 5 files changed, 115 insertions(+)

diff --git a/include/hw/ppc/spapr_xive.h b/include/hw/ppc/spapr_xive.h
index 1d134a681326..c913c0aed08a 100644
--- a/include/hw/ppc/spapr_xive.h
+++ b/include/hw/ppc/spapr_xive.h
@@ -108,5 +108,6 @@ void spapr_xive_mmio_map(sPAPRXive *xive);
 #define XIVE_TCTX_KVM(obj)   OBJECT_CHECK(XiveTCTX, (obj), TYPE_XIVE_TCTX_KVM)
 
 void spapr_xive_kvm_init(sPAPRXive *xive, Error **errp);
+void spapr_xive_kvm_fini(sPAPRXive *xive, Error **errp);
 
 #endif /* PPC_SPAPR_XIVE_H */
diff --git a/include/hw/ppc/xics.h b/include/hw/ppc/xics.h
index 9958443d1984..a5468c6eb6e3 100644
--- a/include/hw/ppc/xics.h
+++ b/include/hw/ppc/xics.h
@@ -205,6 +205,7 @@ void icp_resend(ICPState *ss);
 typedef struct sPAPRMachineState sPAPRMachineState;
 
 int xics_kvm_init(sPAPRMachineState *spapr, Error **errp);
+int xics_kvm_fini(sPAPRMachineState *spapr, Error **errp);
 void xics_spapr_init(sPAPRMachineState *spapr);
 
 Object *icp_create(Object *cpu, const char *type, XICSFabric *xi,
diff --git a/linux-headers/linux/kvm.h b/linux-headers/linux/kvm.h
index 59fa8d8d7f39..b7a74c58d0db 100644
--- a/linux-headers/linux/kvm.h
+++ b/linux-headers/linux/kvm.h
@@ -1309,6 +1309,8 @@ struct kvm_s390_ucas_mapping {
 #define KVM_GET_DEVICE_ATTR	  _IOW(KVMIO,  0xe2, struct kvm_device_attr)
 #define KVM_HAS_DEVICE_ATTR	  _IOW(KVMIO,  0xe3, struct kvm_device_attr)
 
+#define KVM_DESTROY_DEVICE	  _IOWR(KVMIO,  0xf0, struct kvm_create_device)
+
 /*
  * ioctls for vcpu fds
  */
diff --git a/hw/intc/spapr_xive_kvm.c b/hw/intc/spapr_xive_kvm.c
index cb2aa6e81274..0672d8bcbc6b 100644
--- a/hw/intc/spapr_xive_kvm.c
+++ b/hw/intc/spapr_xive_kvm.c
@@ -55,6 +55,16 @@ 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)
  */
@@ -864,6 +874,50 @@ void spapr_xive_kvm_init(sPAPRXive *xive, Error **errp)
     kvm_gsi_direct_mapping = true;
 }
 
+void spapr_xive_kvm_fini(sPAPRXive *xive, Error **errp)
+{
+    XiveSource *xsrc = &xive->source;
+    struct kvm_create_device xive_destroy_device = {
+        .fd = xive->fd,
+        .type = KVM_DEV_TYPE_XIVE,
+        .flags = 0,
+    };
+    size_t esb_len = (1ull << xsrc->esb_shift) * xsrc->nr_irqs;
+    int rc;
+
+    /* The KVM XIVE device is not in use */
+    if (xive->fd == -1) {
+        return;
+    }
+
+    if (!kvm_enabled() || !kvmppc_has_cap_xive()) {
+        error_setg(errp,
+                   "IRQ_XIVE capability must be present for KVM XIVE device");
+        return;
+    }
+
+    /* Clear the KVM mapping */
+    sysbus_mmio_unmap(SYS_BUS_DEVICE(xsrc), 0);
+    munmap(xsrc->esb_mmap, esb_len);
+    sysbus_mmio_unmap(SYS_BUS_DEVICE(xive), 0);
+    munmap(xive->tm_mmap, 4ull << TM_SHIFT);
+
+    /* Destroy the KVM device. This also clears the VCPU presenters */
+    rc = kvm_vm_ioctl(kvm_state, KVM_DESTROY_DEVICE, &xive_destroy_device);
+    if (rc < 0) {
+        error_setg_errno(errp, -rc, "Error on KVM_DESTROY_DEVICE for XIVE");
+    }
+    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();
+}
+
 static void spapr_xive_kvm_realize(DeviceState *dev, Error **errp)
 {
     sPAPRXive *xive = SPAPR_XIVE_KVM(dev);
diff --git a/hw/intc/xics_kvm.c b/hw/intc/xics_kvm.c
index eabc901a4556..a7e3ec32a761 100644
--- a/hw/intc/xics_kvm.c
+++ b/hw/intc/xics_kvm.c
@@ -50,6 +50,16 @@ 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
  */
@@ -475,6 +485,53 @@ fail:
     return -1;
 }
 
+int xics_kvm_fini(sPAPRMachineState *spapr, Error **errp)
+{
+    int rc;
+    struct kvm_create_device xics_create_device = {
+        .fd = kernel_xics_fd,
+        .type = KVM_DEV_TYPE_XICS,
+        .flags = 0,
+    };
+
+    /* The KVM XICS device is not in use */
+    if (kernel_xics_fd == -1) {
+        return 0;
+    }
+
+    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 -1;
+    }
+
+    rc = kvm_vm_ioctl(kvm_state, KVM_DESTROY_DEVICE, &xics_create_device);
+    if (rc < 0) {
+        error_setg_errno(errp, -rc, "Error on KVM_DESTROY_DEVICE for XICS");
+    }
+    close(kernel_xics_fd);
+    kernel_xics_fd = -1;
+
+    spapr_rtas_register(RTAS_IBM_SET_XIVE, NULL, 0);
+    spapr_rtas_register(RTAS_IBM_GET_XIVE, NULL, 0);
+    spapr_rtas_register(RTAS_IBM_INT_OFF, NULL, 0);
+    spapr_rtas_register(RTAS_IBM_INT_ON, NULL, 0);
+
+    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();
+
+    return rc;
+}
+
 static void xics_kvm_register_types(void)
 {
     type_register_static(&ics_kvm_info);
-- 
2.17.2