Merge remote-tracking branch 'remotes/dgibson/tags/ppc-for-4.2-20191126' into staging

ppc patch queue for 2019-11-26

Here's the first 4.2 hard freeze pull request from me.  This has:

  * A fix for some testcases that cause errors on older host kernels
    (e.g. RHEL7), with our new default configuration of VSMT mode
  * Changes to make VFIO devices interact properly with change of irq
    chip caused by PAPR feature negotiation.  This is more involved
    than I would like, but it's a problem in real use cases and I
    can't see an easier way to handle it.
  * Fix an error with ms6522 counters for the g3beige machine
  * Fix a coverity warning

# gpg: Signature made Tue 26 Nov 2019 05:52:16 GMT
# gpg:                using RSA key 75F46586AE61A66CC44E87DC6C38CACA20D9B392
# gpg: Good signature from "David Gibson <david@gibson.dropbear.id.au>" [full]
# gpg:                 aka "David Gibson (Red Hat) <dgibson@redhat.com>" [full]
# gpg:                 aka "David Gibson (ozlabs.org) <dgibson@ozlabs.org>" [full]
# gpg:                 aka "David Gibson (kernel.org) <dwg@kernel.org>" [unknown]
# Primary key fingerprint: 75F4 6586 AE61 A66C C44E  87DC 6C38 CACA 20D9 B392

* remotes/dgibson/tags/ppc-for-4.2-20191126:
  ppc/spapr_events: fix potential NULL pointer dereference in rtas_event_log_dequeue
  mos6522: update counters when timer interrupts are off
  spapr: Work around spurious warnings from vfio INTx initialization
  spapr: Handle irq backend changes with VFIO PCI devices
  vfio/pci: Respond to KVM irqchip change notifier
  vfio/pci: Split vfio_intx_update()
  kvm: Introduce KVM irqchip change notifier
  pseries: fix migration-test and pxe-test

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

10 files changed, 105 insertions, 31 deletions

diff --git a/accel/kvm/kvm-all.c b/accel/kvm/kvm-all.c
index 140b0bd..ca00daa 100644
--- a/accel/kvm/kvm-all.c
+++ b/accel/kvm/kvm-all.c
@@ -149,6 +149,9 @@ static const KVMCapabilityInfo kvm_required_capabilites[] = {
     KVM_CAP_LAST_INFO
 };
 
+static NotifierList kvm_irqchip_change_notifiers =
+    NOTIFIER_LIST_INITIALIZER(kvm_irqchip_change_notifiers);
+
 #define kvm_slots_lock(kml)      qemu_mutex_lock(&(kml)->slots_lock)
 #define kvm_slots_unlock(kml)    qemu_mutex_unlock(&(kml)->slots_lock)
 
@@ -1396,6 +1399,21 @@ void kvm_irqchip_release_virq(KVMState *s, int virq)
     trace_kvm_irqchip_release_virq(virq);
 }
 
+void kvm_irqchip_add_change_notifier(Notifier *n)
+{
+    notifier_list_add(&kvm_irqchip_change_notifiers, n);
+}
+
+void kvm_irqchip_remove_change_notifier(Notifier *n)
+{
+    notifier_remove(n);
+}
+
+void kvm_irqchip_change_notify(void)
+{
+    notifier_list_notify(&kvm_irqchip_change_notifiers, NULL);
+}
+
 static unsigned int kvm_hash_msi(uint32_t data)
 {
     /* This is optimized for IA32 MSI layout. However, no other arch shall
diff --git a/accel/stubs/kvm-stub.c b/accel/stubs/kvm-stub.c
index 6feb66e..82f118d 100644
--- a/accel/stubs/kvm-stub.c
+++ b/accel/stubs/kvm-stub.c
@@ -138,6 +138,18 @@ void kvm_irqchip_commit_routes(KVMState *s)
 {
 }
 
+void kvm_irqchip_add_change_notifier(Notifier *n)
+{
+}
+
+void kvm_irqchip_remove_change_notifier(Notifier *n)
+{
+}
+
+void kvm_irqchip_change_notify(void)
+{
+}
+
 int kvm_irqchip_add_adapter_route(KVMState *s, AdapterInfo *adapter)
 {
     return -ENOSYS;
diff --git a/hw/misc/mos6522.c b/hw/misc/mos6522.c
index aa3bfe1..cecf0be 100644
--- a/hw/misc/mos6522.c
+++ b/hw/misc/mos6522.c
@@ -113,6 +113,10 @@ static int64_t get_next_irq_time(MOS6522State *s, MOS6522Timer *ti,
     int64_t d, next_time;
     unsigned int counter;
 
+    if (ti->frequency == 0) {
+        return INT64_MAX;
+    }
+
     /* current counter value */
     d = muldiv64(qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) - ti->load_time,
                  ti->frequency, NANOSECONDS_PER_SECOND);
@@ -149,10 +153,10 @@ static void mos6522_timer1_update(MOS6522State *s, MOS6522Timer *ti,
     if (!ti->timer) {
         return;
     }
+    ti->next_irq_time = get_next_irq_time(s, ti, current_time);
     if ((s->ier & T1_INT) == 0 || (s->acr & T1MODE) != T1MODE_CONT) {
         timer_del(ti->timer);
     } else {
-        ti->next_irq_time = get_next_irq_time(s, ti, current_time);
         timer_mod(ti->timer, ti->next_irq_time);
     }
 }
@@ -163,10 +167,10 @@ static void mos6522_timer2_update(MOS6522State *s, MOS6522Timer *ti,
     if (!ti->timer) {
         return;
     }
+    ti->next_irq_time = get_next_irq_time(s, ti, current_time);
     if ((s->ier & T2_INT) == 0) {
         timer_del(ti->timer);
     } else {
-        ti->next_irq_time = get_next_irq_time(s, ti, current_time);
         timer_mod(ti->timer, ti->next_irq_time);
     }
 }
diff --git a/hw/ppc/spapr_events.c b/hw/ppc/spapr_events.c
index 0e4c195..e355e00 100644
--- a/hw/ppc/spapr_events.c
+++ b/hw/ppc/spapr_events.c
@@ -358,6 +358,7 @@ static SpaprEventLogEntry *rtas_event_log_dequeue(SpaprMachineState *spapr,
             rtas_event_log_to_source(spapr,
                                      spapr_event_log_entry_type(entry));
 
+        g_assert(source);
         if (source->mask & event_mask) {
             break;
         }
diff --git a/hw/ppc/spapr_irq.c b/hw/ppc/spapr_irq.c
index 168044b..d6bb7fd 100644
--- a/hw/ppc/spapr_irq.c
+++ b/hw/ppc/spapr_irq.c
@@ -373,6 +373,14 @@ void spapr_irq_init(SpaprMachineState *spapr, Error **errp)
 
     spapr->qirqs = qemu_allocate_irqs(spapr_set_irq, spapr,
                                       smc->nr_xirqs + SPAPR_XIRQ_BASE);
+
+    /*
+     * Mostly we don't actually need this until reset, except that not
+     * having this set up can cause VFIO devices to issue a
+     * false-positive warning during realize(), because they don't yet
+     * have an in-kernel irq chip.
+     */
+    spapr_irq_update_active_intc(spapr);
 }
 
 int spapr_irq_claim(SpaprMachineState *spapr, int irq, bool lsi, Error **errp)
@@ -508,6 +516,12 @@ static void set_active_intc(SpaprMachineState *spapr,
     }
 
     spapr->active_intc = new_intc;
+
+    /*
+     * We've changed the kernel irqchip, let VFIO devices know they
+     * need to readjust.
+     */
+    kvm_irqchip_change_notify();
 }
 
 void spapr_irq_update_active_intc(SpaprMachineState *spapr)
@@ -522,7 +536,8 @@ void spapr_irq_update_active_intc(SpaprMachineState *spapr)
          * this.
          */
         new_intc = SPAPR_INTC(spapr->xive);
-    } else if (spapr_ovec_test(spapr->ov5_cas, OV5_XIVE_EXPLOIT)) {
+    } else if (spapr->ov5_cas
+               && spapr_ovec_test(spapr->ov5_cas, OV5_XIVE_EXPLOIT)) {
         new_intc = SPAPR_INTC(spapr->xive);
     } else {
         new_intc = SPAPR_INTC(spapr->ics);
diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c
index 0c55883..2d40b39 100644
--- a/hw/vfio/pci.c
+++ b/hw/vfio/pci.c
@@ -216,30 +216,18 @@ static void vfio_intx_disable_kvm(VFIOPCIDevice *vdev)
 #endif
 }
 
-static void vfio_intx_update(PCIDevice *pdev)
+static void vfio_intx_update(VFIOPCIDevice *vdev, PCIINTxRoute *route)
 {
-    VFIOPCIDevice *vdev = PCI_VFIO(pdev);
-    PCIINTxRoute route;
     Error *err = NULL;
 
-    if (vdev->interrupt != VFIO_INT_INTx) {
-        return;
-    }
-
-    route = pci_device_route_intx_to_irq(&vdev->pdev, vdev->intx.pin);
-
-    if (!pci_intx_route_changed(&vdev->intx.route, &route)) {
-        return; /* Nothing changed */
-    }
-
     trace_vfio_intx_update(vdev->vbasedev.name,
-                           vdev->intx.route.irq, route.irq);
+                           vdev->intx.route.irq, route->irq);
 
     vfio_intx_disable_kvm(vdev);
 
-    vdev->intx.route = route;
+    vdev->intx.route = *route;
 
-    if (route.mode != PCI_INTX_ENABLED) {
+    if (route->mode != PCI_INTX_ENABLED) {
         return;
     }
 
@@ -252,6 +240,30 @@ static void vfio_intx_update(PCIDevice *pdev)
     vfio_intx_eoi(&vdev->vbasedev);
 }
 
+static void vfio_intx_routing_notifier(PCIDevice *pdev)
+{
+    VFIOPCIDevice *vdev = PCI_VFIO(pdev);
+    PCIINTxRoute route;
+
+    if (vdev->interrupt != VFIO_INT_INTx) {
+        return;
+    }
+
+    route = pci_device_route_intx_to_irq(&vdev->pdev, vdev->intx.pin);
+
+    if (pci_intx_route_changed(&vdev->intx.route, &route)) {
+        vfio_intx_update(vdev, &route);
+    }
+}
+
+static void vfio_irqchip_change(Notifier *notify, void *data)
+{
+    VFIOPCIDevice *vdev = container_of(notify, VFIOPCIDevice,
+                                       irqchip_change_notifier);
+
+    vfio_intx_update(vdev, &vdev->intx.route);
+}
+
 static int vfio_intx_enable(VFIOPCIDevice *vdev, Error **errp)
 {
     uint8_t pin = vfio_pci_read_config(&vdev->pdev, PCI_INTERRUPT_PIN, 1);
@@ -2967,31 +2979,34 @@ static void vfio_realize(PCIDevice *pdev, Error **errp)
     if (vfio_pci_read_config(&vdev->pdev, PCI_INTERRUPT_PIN, 1)) {
         vdev->intx.mmap_timer = timer_new_ms(QEMU_CLOCK_VIRTUAL,
                                                   vfio_intx_mmap_enable, vdev);
-        pci_device_set_intx_routing_notifier(&vdev->pdev, vfio_intx_update);
+        pci_device_set_intx_routing_notifier(&vdev->pdev,
+                                             vfio_intx_routing_notifier);
+        vdev->irqchip_change_notifier.notify = vfio_irqchip_change;
+        kvm_irqchip_add_change_notifier(&vdev->irqchip_change_notifier);
         ret = vfio_intx_enable(vdev, errp);
         if (ret) {
-            goto out_teardown;
+            goto out_deregister;
         }
     }
 
     if (vdev->display != ON_OFF_AUTO_OFF) {
         ret = vfio_display_probe(vdev, errp);
         if (ret) {
-            goto out_teardown;
+            goto out_deregister;
         }
     }
     if (vdev->enable_ramfb && vdev->dpy == NULL) {
         error_setg(errp, "ramfb=on requires display=on");
-        goto out_teardown;
+        goto out_deregister;
     }
     if (vdev->display_xres || vdev->display_yres) {
         if (vdev->dpy == NULL) {
             error_setg(errp, "xres and yres properties require display=on");
-            goto out_teardown;
+            goto out_deregister;
         }
         if (vdev->dpy->edid_regs == NULL) {
             error_setg(errp, "xres and yres properties need edid support");
-            goto out_teardown;
+            goto out_deregister;
         }
     }
 
@@ -3015,8 +3030,10 @@ static void vfio_realize(PCIDevice *pdev, Error **errp)
 
     return;
 
-out_teardown:
+out_deregister:
     pci_device_set_intx_routing_notifier(&vdev->pdev, NULL);
+    kvm_irqchip_remove_change_notifier(&vdev->irqchip_change_notifier);
+out_teardown:
     vfio_teardown_msi(vdev);
     vfio_bars_exit(vdev);
 error:
@@ -3059,6 +3076,7 @@ static void vfio_exitfn(PCIDevice *pdev)
     vfio_unregister_req_notifier(vdev);
     vfio_unregister_err_notifier(vdev);
     pci_device_set_intx_routing_notifier(&vdev->pdev, NULL);
+    kvm_irqchip_remove_change_notifier(&vdev->irqchip_change_notifier);
     vfio_disable_interrupts(vdev);
     if (vdev->intx.mmap_timer) {
         timer_free(vdev->intx.mmap_timer);
diff --git a/hw/vfio/pci.h b/hw/vfio/pci.h
index b329d50..35626cd 100644
--- a/hw/vfio/pci.h
+++ b/hw/vfio/pci.h
@@ -169,6 +169,7 @@ typedef struct VFIOPCIDevice {
     bool enable_ramfb;
     VFIODisplay *dpy;
     Error *migration_blocker;
+    Notifier irqchip_change_notifier;
 } VFIOPCIDevice;
 
 uint32_t vfio_pci_read_config(PCIDevice *pdev, uint32_t addr, int len);
diff --git a/include/sysemu/kvm.h b/include/sysemu/kvm.h
index 9d14328..9fe233b 100644
--- a/include/sysemu/kvm.h
+++ b/include/sysemu/kvm.h
@@ -201,6 +201,7 @@ typedef struct KVMCapabilityInfo {
 struct KVMState;
 typedef struct KVMState KVMState;
 extern KVMState *kvm_state;
+typedef struct Notifier Notifier;
 
 /* external API */
 
@@ -401,6 +402,10 @@ int kvm_irqchip_send_msi(KVMState *s, MSIMessage msg);
 
 void kvm_irqchip_add_irq_route(KVMState *s, int gsi, int irqchip, int pin);
 
+void kvm_irqchip_add_change_notifier(Notifier *n);
+void kvm_irqchip_remove_change_notifier(Notifier *n);
+void kvm_irqchip_change_notify(void);
+
 void kvm_get_apic_state(DeviceState *d, struct kvm_lapic_state *kapic);
 
 struct kvm_guest_debug;
diff --git a/tests/migration-test.c b/tests/migration-test.c
index ac780df..ebd77a5 100644
--- a/tests/migration-test.c
+++ b/tests/migration-test.c
@@ -614,7 +614,7 @@ static int test_migrate_start(QTestState **from, QTestState **to,
         end_address = S390_TEST_MEM_END;
     } else if (strcmp(arch, "ppc64") == 0) {
         extra_opts = use_shmem ? get_shmem_opts("256M", shmem_path) : NULL;
-        cmd_src = g_strdup_printf("-machine accel=%s -m 256M -nodefaults"
+        cmd_src = g_strdup_printf("-machine accel=%s,vsmt=8 -m 256M -nodefaults"
                                   " -name source,debug-threads=on"
                                   " -serial file:%s/src_serial"
                                   " -prom-env 'use-nvramrc?=true' -prom-env "
@@ -623,7 +623,7 @@ static int test_migrate_start(QTestState **from, QTestState **to,
                                   "until' %s %s",  accel, tmpfs, end_address,
                                   start_address, extra_opts ? extra_opts : "",
                                   opts_src);
-        cmd_dst = g_strdup_printf("-machine accel=%s -m 256M"
+        cmd_dst = g_strdup_printf("-machine accel=%s,vsmt=8 -m 256M"
                                   " -name target,debug-threads=on"
                                   " -serial file:%s/dest_serial"
                                   " -incoming %s %s %s",
diff --git a/tests/pxe-test.c b/tests/pxe-test.c
index 948b0fb..aaae54f 100644
--- a/tests/pxe-test.c
+++ b/tests/pxe-test.c
@@ -46,15 +46,15 @@ static testdef_t x86_tests_slow[] = {
 
 static testdef_t ppc64_tests[] = {
     { "pseries", "spapr-vlan",
-      "-machine cap-cfpc=broken,cap-sbbc=broken,cap-ibs=broken" },
+      "-machine cap-cfpc=broken,cap-sbbc=broken,cap-ibs=broken,vsmt=8" },
     { "pseries", "virtio-net-pci",
-      "-machine cap-cfpc=broken,cap-sbbc=broken,cap-ibs=broken" },
+      "-machine cap-cfpc=broken,cap-sbbc=broken,cap-ibs=broken,vsmt=8" },
     { NULL },
 };
 
 static testdef_t ppc64_tests_slow[] = {
     { "pseries", "e1000",
-      "-machine cap-cfpc=broken,cap-sbbc=broken,cap-ibs=broken" },
+      "-machine cap-cfpc=broken,cap-sbbc=broken,cap-ibs=broken,vsmt=8" },
     { NULL },
 };