Merge remote-tracking branch 'remotes/cohuck/tags/s390x-20181212' into staging

s390x patches for 4.0:
- add 4.0 machine type
- various fixes and small changes

# gpg: Signature made Wed 12 Dec 2018 09:52:04 GMT
# gpg:                using RSA key DECF6B93C6F02FAF
# gpg: Good signature from "Cornelia Huck <conny@cornelia-huck.de>"
# gpg:                 aka "Cornelia Huck <huckc@linux.vnet.ibm.com>"
# gpg:                 aka "Cornelia Huck <cornelia.huck@de.ibm.com>"
# gpg:                 aka "Cornelia Huck <cohuck@kernel.org>"
# gpg:                 aka "Cornelia Huck <cohuck@redhat.com>"
# Primary key fingerprint: C3D0 D66D C362 4FF6 A8C0  18CE DECF 6B93 C6F0 2FAF

* remotes/cohuck/tags/s390x-20181212:
  hw/s390x/virtio-ccw.c: Don't take address of fields in packed structs
  vfio-ap: flag as compatible with balloon
  s390x/tod: Properly stop the KVM TOD while the guest is not running
  s390/MAINTAINERS: Add Halil as kvm and machine maintainer
  s390x: introduce 4.0 compat machine
  s390x/zpci: drop msix.available

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

6 files changed, 146 insertions, 26 deletions

diff --git a/hw/s390x/s390-pci-bus.c b/hw/s390x/s390-pci-bus.c
index 060ff062bc..99d0368868 100644
--- a/hw/s390x/s390-pci-bus.c
+++ b/hw/s390x/s390-pci-bus.c
@@ -745,7 +745,6 @@ static int s390_pci_msix_init(S390PCIBusDevice *pbdev)
 
     pos = pci_find_capability(pbdev->pdev, PCI_CAP_ID_MSIX);
     if (!pos) {
-        pbdev->msix.available = false;
         return -1;
     }
 
@@ -761,7 +760,6 @@ static int s390_pci_msix_init(S390PCIBusDevice *pbdev)
     pbdev->msix.pba_bar = pba & PCI_MSIX_FLAGS_BIRMASK;
     pbdev->msix.pba_offset = pba & ~PCI_MSIX_FLAGS_BIRMASK;
     pbdev->msix.entries = (ctrl & PCI_MSIX_FLAGS_QSIZE) + 1;
-    pbdev->msix.available = true;
 
     name = g_strdup_printf("msix-s390-%04x", pbdev->uid);
     memory_region_init_io(&pbdev->msix_notify_mr, OBJECT(pbdev),
diff --git a/hw/s390x/s390-pci-bus.h b/hw/s390x/s390-pci-bus.h
index 1f7f9b5814..f47a0f2da5 100644
--- a/hw/s390x/s390-pci-bus.h
+++ b/hw/s390x/s390-pci-bus.h
@@ -252,7 +252,6 @@ typedef struct ChscSeiNt2Res {
 } QEMU_PACKED ChscSeiNt2Res;
 
 typedef struct S390MsixInfo {
-    bool available;
     uint8_t table_bar;
     uint8_t pba_bar;
     uint16_t entries;
diff --git a/hw/s390x/s390-virtio-ccw.c b/hw/s390x/s390-virtio-ccw.c
index a0615a8b35..fd9d0b0542 100644
--- a/hw/s390x/s390-virtio-ccw.c
+++ b/hw/s390x/s390-virtio-ccw.c
@@ -651,6 +651,9 @@ bool css_migration_enabled(void)
     }                                                                         \
     type_init(ccw_machine_register_##suffix)
 
+#define CCW_COMPAT_3_1 \
+        HW_COMPAT_3_1
+
 #define CCW_COMPAT_3_0 \
         HW_COMPAT_3_0
 
@@ -742,14 +745,26 @@ bool css_migration_enabled(void)
             .value    = "0",\
         },
 
+static void ccw_machine_4_0_instance_options(MachineState *machine)
+{
+}
+
+static void ccw_machine_4_0_class_options(MachineClass *mc)
+{
+}
+DEFINE_CCW_MACHINE(4_0, "4.0", true);
+
 static void ccw_machine_3_1_instance_options(MachineState *machine)
 {
+    ccw_machine_4_0_instance_options(machine);
 }
 
 static void ccw_machine_3_1_class_options(MachineClass *mc)
 {
+    ccw_machine_4_0_class_options(mc);
+    SET_MACHINE_COMPAT(mc, CCW_COMPAT_3_1);
 }
-DEFINE_CCW_MACHINE(3_1, "3.1", true);
+DEFINE_CCW_MACHINE(3_1, "3.1", false);
 
 static void ccw_machine_3_0_instance_options(MachineState *machine)
 {
diff --git a/hw/s390x/tod-kvm.c b/hw/s390x/tod-kvm.c
index df564ab89c..2456bf7b24 100644
--- a/hw/s390x/tod-kvm.c
+++ b/hw/s390x/tod-kvm.c
@@ -10,10 +10,11 @@
 
 #include "qemu/osdep.h"
 #include "qapi/error.h"
+#include "sysemu/sysemu.h"
 #include "hw/s390x/tod.h"
 #include "kvm_s390x.h"
 
-static void kvm_s390_tod_get(const S390TODState *td, S390TOD *tod, Error **errp)
+static void kvm_s390_get_tod_raw(S390TOD *tod, Error **errp)
 {
     int r;
 
@@ -27,7 +28,17 @@ static void kvm_s390_tod_get(const S390TODState *td, S390TOD *tod, Error **errp)
     }
 }
 
-static void kvm_s390_tod_set(S390TODState *td, const S390TOD *tod, Error **errp)
+static void kvm_s390_tod_get(const S390TODState *td, S390TOD *tod, Error **errp)
+{
+    if (td->stopped) {
+        *tod = td->base;
+        return;
+    }
+
+    kvm_s390_get_tod_raw(tod, errp);
+}
+
+static void kvm_s390_set_tod_raw(const S390TOD *tod, Error **errp)
 {
     int r;
 
@@ -41,18 +52,105 @@ static void kvm_s390_tod_set(S390TODState *td, const S390TOD *tod, Error **errp)
     }
 }
 
+static void kvm_s390_tod_set(S390TODState *td, const S390TOD *tod, Error **errp)
+{
+    Error *local_err = NULL;
+
+    /*
+     * Somebody (e.g. migration) set the TOD. We'll store it into KVM to
+     * properly detect errors now but take a look at the runstate to decide
+     * whether really to keep the tod running. E.g. during migration, this
+     * is the point where we want to stop the initially running TOD to fire
+     * it back up when actually starting the migrated guest.
+     */
+    kvm_s390_set_tod_raw(tod, &local_err);
+    if (local_err) {
+        error_propagate(errp, local_err);
+        return;
+    }
+
+    if (runstate_is_running()) {
+        td->stopped = false;
+    } else {
+        td->stopped = true;
+        td->base = *tod;
+    }
+}
+
+static void kvm_s390_tod_vm_state_change(void *opaque, int running,
+                                         RunState state)
+{
+    S390TODState *td = opaque;
+    Error *local_err = NULL;
+
+    if (running && td->stopped) {
+        /* Set the old TOD when running the VM - start the TOD clock. */
+        kvm_s390_set_tod_raw(&td->base, &local_err);
+        if (local_err) {
+            warn_report_err(local_err);
+        }
+        /* Treat errors like the TOD was running all the time. */
+        td->stopped = false;
+    } else if (!running && !td->stopped) {
+        /* Store the TOD when stopping the VM - stop the TOD clock. */
+        kvm_s390_get_tod_raw(&td->base, &local_err);
+        if (local_err) {
+            /* Keep the TOD running in case we could not back it up. */
+            warn_report_err(local_err);
+        } else {
+            td->stopped = true;
+        }
+    }
+}
+
+static void kvm_s390_tod_realize(DeviceState *dev, Error **errp)
+{
+    S390TODState *td = S390_TOD(dev);
+    S390TODClass *tdc = S390_TOD_GET_CLASS(td);
+    Error *local_err = NULL;
+
+    tdc->parent_realize(dev, &local_err);
+    if (local_err) {
+        error_propagate(errp, local_err);
+        return;
+    }
+
+    /*
+     * We need to know when the VM gets started/stopped to start/stop the TOD.
+     * As we can never have more than one TOD instance (and that will never be
+     * removed), registering here and never unregistering is good enough.
+     */
+    qemu_add_vm_change_state_handler(kvm_s390_tod_vm_state_change, td);
+}
+
 static void kvm_s390_tod_class_init(ObjectClass *oc, void *data)
 {
     S390TODClass *tdc = S390_TOD_CLASS(oc);
 
+    device_class_set_parent_realize(DEVICE_CLASS(oc), kvm_s390_tod_realize,
+                                    &tdc->parent_realize);
     tdc->get = kvm_s390_tod_get;
     tdc->set = kvm_s390_tod_set;
 }
 
+static void kvm_s390_tod_init(Object *obj)
+{
+    S390TODState *td = S390_TOD(obj);
+
+    /*
+     * The TOD is initially running (value stored in KVM). Avoid needless
+     * loading/storing of the TOD when starting a simple VM, so let it
+     * run although the (never started) VM is stopped. For migration, we
+     * will properly set the TOD later.
+     */
+    td->stopped = false;
+}
+
 static TypeInfo kvm_s390_tod_info = {
     .name = TYPE_KVM_S390_TOD,
     .parent = TYPE_S390_TOD,
     .instance_size = sizeof(S390TODState),
+    .instance_init = kvm_s390_tod_init,
     .class_init = kvm_s390_tod_class_init,
     .class_size = sizeof(S390TODClass),
 };
diff --git a/hw/s390x/virtio-ccw.c b/hw/s390x/virtio-ccw.c
index 212b3d3dea..c2b78c8e9b 100644
--- a/hw/s390x/virtio-ccw.c
+++ b/hw/s390x/virtio-ccw.c
@@ -287,18 +287,18 @@ static int virtio_ccw_handle_set_vq(SubchDev *sch, CCW1 ccw, bool check_len,
     }
     if (is_legacy) {
         ccw_dstream_read(&sch->cds, linfo);
-        be64_to_cpus(&linfo.queue);
-        be32_to_cpus(&linfo.align);
-        be16_to_cpus(&linfo.index);
-        be16_to_cpus(&linfo.num);
+        linfo.queue = be64_to_cpu(linfo.queue);
+        linfo.align = be32_to_cpu(linfo.align);
+        linfo.index = be16_to_cpu(linfo.index);
+        linfo.num = be16_to_cpu(linfo.num);
         ret = virtio_ccw_set_vqs(sch, NULL, &linfo);
     } else {
         ccw_dstream_read(&sch->cds, info);
-        be64_to_cpus(&info.desc);
-        be16_to_cpus(&info.index);
-        be16_to_cpus(&info.num);
-        be64_to_cpus(&info.avail);
-        be64_to_cpus(&info.used);
+        info.desc = be64_to_cpu(info.desc);
+        info.index = be16_to_cpu(info.index);
+        info.num = be16_to_cpu(info.num);
+        info.avail = be64_to_cpu(info.avail);
+        info.used = be64_to_cpu(info.used);
         ret = virtio_ccw_set_vqs(sch, &info, NULL);
     }
     sch->curr_status.scsw.count = 0;
@@ -382,7 +382,7 @@ static int virtio_ccw_cb(SubchDev *sch, CCW1 ccw)
                 features.features = 0;
             }
             ccw_dstream_rewind(&sch->cds);
-            cpu_to_le32s(&features.features);
+            features.features = cpu_to_le32(features.features);
             ccw_dstream_write(&sch->cds, features.features);
             sch->curr_status.scsw.count = ccw.count - sizeof(features);
             ret = 0;
@@ -403,7 +403,7 @@ static int virtio_ccw_cb(SubchDev *sch, CCW1 ccw)
             ret = -EFAULT;
         } else {
             ccw_dstream_read(&sch->cds, features);
-            le32_to_cpus(&features.features);
+            features.features = le32_to_cpu(features.features);
             if (features.index == 0) {
                 virtio_set_features(vdev,
                                     (vdev->guest_features & 0xffffffff00000000ULL) |
@@ -546,7 +546,7 @@ static int virtio_ccw_cb(SubchDev *sch, CCW1 ccw)
             ret = -EFAULT;
         } else {
             ccw_dstream_read(&sch->cds, indicators);
-            be64_to_cpus(&indicators);
+            indicators = be64_to_cpu(indicators);
             dev->indicators = get_indicator(indicators, sizeof(uint64_t));
             sch->curr_status.scsw.count = ccw.count - sizeof(indicators);
             ret = 0;
@@ -567,7 +567,7 @@ static int virtio_ccw_cb(SubchDev *sch, CCW1 ccw)
             ret = -EFAULT;
         } else {
             ccw_dstream_read(&sch->cds, indicators);
-            be64_to_cpus(&indicators);
+            indicators = be64_to_cpu(indicators);
             dev->indicators2 = get_indicator(indicators, sizeof(uint64_t));
             sch->curr_status.scsw.count = ccw.count - sizeof(indicators);
             ret = 0;
@@ -588,14 +588,14 @@ static int virtio_ccw_cb(SubchDev *sch, CCW1 ccw)
             ret = -EFAULT;
         } else {
             ccw_dstream_read(&sch->cds, vq_config.index);
-            be16_to_cpus(&vq_config.index);
+            vq_config.index = be16_to_cpu(vq_config.index);
             if (vq_config.index >= VIRTIO_QUEUE_MAX) {
                 ret = -EINVAL;
                 break;
             }
             vq_config.num_max = virtio_queue_get_num(vdev,
                                                      vq_config.index);
-            cpu_to_be16s(&vq_config.num_max);
+            vq_config.num_max = cpu_to_be16(vq_config.num_max);
             ccw_dstream_write(&sch->cds, vq_config.num_max);
             sch->curr_status.scsw.count = ccw.count - sizeof(vq_config);
             ret = 0;
@@ -621,9 +621,11 @@ static int virtio_ccw_cb(SubchDev *sch, CCW1 ccw)
             if (ccw_dstream_read(&sch->cds, thinint)) {
                 ret = -EFAULT;
             } else {
-                be64_to_cpus(&thinint.ind_bit);
-                be64_to_cpus(&thinint.summary_indicator);
-                be64_to_cpus(&thinint.device_indicator);
+                thinint.ind_bit = be64_to_cpu(thinint.ind_bit);
+                thinint.summary_indicator =
+                    be64_to_cpu(thinint.summary_indicator);
+                thinint.device_indicator =
+                    be64_to_cpu(thinint.device_indicator);
 
                 dev->summary_indicator =
                     get_indicator(thinint.summary_indicator, sizeof(uint8_t));
@@ -654,8 +656,8 @@ static int virtio_ccw_cb(SubchDev *sch, CCW1 ccw)
             break;
         }
         ccw_dstream_read_buf(&sch->cds, &revinfo, 4);
-        be16_to_cpus(&revinfo.revision);
-        be16_to_cpus(&revinfo.length);
+        revinfo.revision = be16_to_cpu(revinfo.revision);
+        revinfo.length = be16_to_cpu(revinfo.length);
         if (ccw.count < len + revinfo.length ||
             (check_len && ccw.count > len + revinfo.length)) {
             ret = -EINVAL;
diff --git a/hw/vfio/ap.c b/hw/vfio/ap.c
index 65de952f44..0a25f5e096 100644
--- a/hw/vfio/ap.c
+++ b/hw/vfio/ap.c
@@ -104,6 +104,14 @@ static void vfio_ap_realize(DeviceState *dev, Error **errp)
     vapdev->vdev.name = g_strdup_printf("%s", mdevid);
     vapdev->vdev.dev = dev;
 
+    /*
+     * vfio-ap devices operate in a way compatible with
+     * memory ballooning, as no pages are pinned in the host.
+     * This needs to be set before vfio_get_device() for vfio common to
+     * handle the balloon inhibitor.
+     */
+    vapdev->vdev.balloon_allowed = true;
+
     ret = vfio_get_device(vfio_group, mdevid, &vapdev->vdev, &local_err);
     if (ret) {
         goto out_get_dev_err;