pci, pc, virtio: fixes, features

pci resource capability + misc fixes everywhere.
 
 Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
 -----BEGIN PGP SIGNATURE-----
 
 iQEcBAABAgAGBQJbkvKuAAoJECgfDbjSjVRpJ5MIALC60skYR6gyu8NCqma1NNod
 F1xEtlA2lkWOS6C5ohoHLm9EJ6pBT/dIqhZxzhw2eVKYLqJpXQbshkXTZFshFmUt
 RQy7rNlI4N5yzxU6RyYn2zXtSI1HN3YxKrpeB+WEUETi6eqor8ZHijWNJIDwIq+9
 By44CFaEisoqhFDSQp+PAUhzLnRretn6CyRLTKSfYQull2ZAJk1SVYc9FOQkq/M6
 +QlOtTsADVyu7veZabaj+/Noqndc4yCtV3uvyAfmO6j+DNxDo1sN/9DwWq7GROIs
 Y4R/ena+yOsmWDUh5f7Xkhgc1BqIJc0UjEx8Q4lIRBe1AI4VV9kjvvPXwMRlWWw=
 =a+iV
 -----END PGP SIGNATURE-----

Merge remote-tracking branch 'remotes/mst/tags/for_upstream' into staging

pci, pc, virtio: fixes, features

pci resource capability + misc fixes everywhere.

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>

# gpg: Signature made Fri 07 Sep 2018 22:50:38 BST
# gpg:                using RSA key 281F0DB8D28D5469
# gpg: Good signature from "Michael S. Tsirkin <mst@kernel.org>"
# gpg:                 aka "Michael S. Tsirkin <mst@redhat.com>"
# Primary key fingerprint: 0270 606B 6F3C DF3D 0B17  0970 C350 3912 AFBE 8E67
#      Subkey fingerprint: 5D09 FD08 71C8 F85B 94CA  8A0D 281F 0DB8 D28D 5469

* remotes/mst/tags/for_upstream:
  tests: update acpi expected files
  vhost: fix invalid downcast
  pc: make sure that guest isn't able to unplug the first cpu
  hw/pci: add PCI resource reserve capability to legacy PCI bridge
  hw/pci: factor PCI reserve resources to a separate structure
  virtio: update MemoryRegionCaches when guest negotiates features
  pc: acpi: revert back to 1 SRAT entry for hotpluggable area

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

hw/acpi/cpu.c

@@ -117,7 +117,7 @@ static void cpu_hotplug_wr(void *opaque, hwaddr addr, uint64_t data,
             DeviceState *dev = NULL;
             HotplugHandler *hotplug_ctrl = NULL;
 
-            if (!cdev->cpu) {
+            if (!cdev->cpu || cdev->cpu == first_cpu) {
                 trace_cpuhp_acpi_ejecting_invalid_cpu(cpu_st->selector);
                 break;
             }
@@ -541,9 +541,11 @@ void build_cpus_aml(Aml *table, MachineState *machine, CPUHotplugFeatures opts,
                 aml_buffer(madt_buf->len, (uint8_t *)madt_buf->data)));
             g_array_free(madt_buf, true);
 
-            method = aml_method("_EJ0", 1, AML_NOTSERIALIZED);
+            if (CPU(arch_ids->cpus[i].cpu) != first_cpu) {
-            aml_append(method, aml_call1(CPU_EJECT_METHOD, uid));
+                method = aml_method("_EJ0", 1, AML_NOTSERIALIZED);
-            aml_append(dev, method);
+                aml_append(method, aml_call1(CPU_EJECT_METHOD, uid));
+                aml_append(dev, method);
+            }
 
             method = aml_method("_OST", 3, AML_SERIALIZED);
             aml_append(method,

hw/i386/acpi-build.c

@@ -2251,64 +2251,6 @@ build_tpm2(GArray *table_data, BIOSLinker *linker, GArray *tcpalog)
 #define HOLE_640K_START  (640 * KiB)
 #define HOLE_640K_END   (1 * MiB)
 
-static void build_srat_hotpluggable_memory(GArray *table_data, uint64_t base,
-                                           uint64_t len, int default_node)
-{
-    MemoryDeviceInfoList *info_list = qmp_memory_device_list();
-    MemoryDeviceInfoList *info;
-    MemoryDeviceInfo *mi;
-    PCDIMMDeviceInfo *di;
-    uint64_t end = base + len, cur, size;
-    bool is_nvdimm;
-    AcpiSratMemoryAffinity *numamem;
-    MemoryAffinityFlags flags;
-
-    for (cur = base, info = info_list;
-         cur < end;
-         cur += size, info = info->next) {
-        numamem = acpi_data_push(table_data, sizeof *numamem);
-
-        if (!info) {
-            /*
-             * Entry is required for Windows to enable memory hotplug in OS
-             * and for Linux to enable SWIOTLB when booted with less than
-             * 4G of RAM. Windows works better if the entry sets proximity
-             * to the highest NUMA node in the machine at the end of the
-             * reserved space.
-             * Memory devices may override proximity set by this entry,
-             * providing _PXM method if necessary.
-             */
-            build_srat_memory(numamem, end - 1, 1, default_node,
-                              MEM_AFFINITY_HOTPLUGGABLE | MEM_AFFINITY_ENABLED);
-            break;
-        }
-
-        mi = info->value;
-        is_nvdimm = (mi->type == MEMORY_DEVICE_INFO_KIND_NVDIMM);
-        di = !is_nvdimm ? mi->u.dimm.data : mi->u.nvdimm.data;
-
-        if (cur < di->addr) {
-            build_srat_memory(numamem, cur, di->addr - cur, default_node,
-                              MEM_AFFINITY_HOTPLUGGABLE | MEM_AFFINITY_ENABLED);
-            numamem = acpi_data_push(table_data, sizeof *numamem);
-        }
-
-        size = di->size;
-
-        flags = MEM_AFFINITY_ENABLED;
-        if (di->hotpluggable) {
-            flags |= MEM_AFFINITY_HOTPLUGGABLE;
-        }
-        if (is_nvdimm) {
-            flags |= MEM_AFFINITY_NON_VOLATILE;
-        }
-
-        build_srat_memory(numamem, di->addr, size, di->node, flags);
-    }
-
-    qapi_free_MemoryDeviceInfoList(info_list);
-}
-
 static void
 build_srat(GArray *table_data, BIOSLinker *linker, MachineState *machine)
 {
@@ -2414,10 +2356,19 @@ build_srat(GArray *table_data, BIOSLinker *linker, MachineState *machine)
         build_srat_memory(numamem, 0, 0, 0, MEM_AFFINITY_NOFLAGS);
     }
 
+    /*
+     * Entry is required for Windows to enable memory hotplug in OS
+     * and for Linux to enable SWIOTLB when booted with less than
+     * 4G of RAM. Windows works better if the entry sets proximity
+     * to the highest NUMA node in the machine.
+     * Memory devices may override proximity set by this entry,
+     * providing _PXM method if necessary.
+     */
     if (hotplugabble_address_space_size) {
-        build_srat_hotpluggable_memory(table_data, machine->device_memory->base,
+        numamem = acpi_data_push(table_data, sizeof *numamem);
-                                       hotplugabble_address_space_size,
+        build_srat_memory(numamem, machine->device_memory->base,
-                                       pcms->numa_nodes - 1);
+                          hotplugabble_address_space_size, pcms->numa_nodes - 1,
+                          MEM_AFFINITY_HOTPLUGGABLE | MEM_AFFINITY_ENABLED);
     }
 
     build_header(linker, table_data,

hw/pci-bridge/gen_pcie_root_port.c

@@ -29,12 +29,8 @@ typedef struct GenPCIERootPort {
 
     bool migrate_msix;
 
-    /* additional resources to reserve on firmware init */
+    /* additional resources to reserve */
-    uint32_t bus_reserve;
+    PCIResReserve res_reserve;
-    uint64_t io_reserve;
-    uint64_t mem_reserve;
-    uint64_t pref32_reserve;
-    uint64_t pref64_reserve;
 } GenPCIERootPort;
 
 static uint8_t gen_rp_aer_vector(const PCIDevice *d)
@@ -82,16 +78,15 @@ static void gen_rp_realize(DeviceState *dev, Error **errp)
         return;
     }
 
-    int rc = pci_bridge_qemu_reserve_cap_init(d, 0, grp->bus_reserve,
+    int rc = pci_bridge_qemu_reserve_cap_init(d, 0,
-            grp->io_reserve, grp->mem_reserve, grp->pref32_reserve,
+                                              grp->res_reserve, errp);
-            grp->pref64_reserve, errp);
 
     if (rc < 0) {
         rpc->parent_class.exit(d);
         return;
     }
 
-    if (!grp->io_reserve) {
+    if (!grp->res_reserve.io) {
         pci_word_test_and_clear_mask(d->wmask + PCI_COMMAND,
                                      PCI_COMMAND_IO);
         d->wmask[PCI_IO_BASE] = 0;
@@ -117,12 +112,18 @@ static const VMStateDescription vmstate_rp_dev = {
 };
 
 static Property gen_rp_props[] = {
-    DEFINE_PROP_BOOL("x-migrate-msix", GenPCIERootPort, migrate_msix, true),
+    DEFINE_PROP_BOOL("x-migrate-msix", GenPCIERootPort,
-    DEFINE_PROP_UINT32("bus-reserve", GenPCIERootPort, bus_reserve, -1),
+                     migrate_msix, true),
-    DEFINE_PROP_SIZE("io-reserve", GenPCIERootPort, io_reserve, -1),
+    DEFINE_PROP_UINT32("bus-reserve", GenPCIERootPort,
-    DEFINE_PROP_SIZE("mem-reserve", GenPCIERootPort, mem_reserve, -1),
+                       res_reserve.bus, -1),
-    DEFINE_PROP_SIZE("pref32-reserve", GenPCIERootPort, pref32_reserve, -1),
+    DEFINE_PROP_SIZE("io-reserve", GenPCIERootPort,
-    DEFINE_PROP_SIZE("pref64-reserve", GenPCIERootPort, pref64_reserve, -1),
+                     res_reserve.io, -1),
+    DEFINE_PROP_SIZE("mem-reserve", GenPCIERootPort,
+                     res_reserve.mem_non_pref, -1),
+    DEFINE_PROP_SIZE("pref32-reserve", GenPCIERootPort,
+                     res_reserve.mem_pref_32, -1),
+    DEFINE_PROP_SIZE("pref64-reserve", GenPCIERootPort,
+                     res_reserve.mem_pref_64, -1),
     DEFINE_PROP_END_OF_LIST()
 };
 

hw/pci-bridge/pci_bridge_dev.c

@@ -46,6 +46,9 @@ struct PCIBridgeDev {
     uint32_t flags;
 
     OnOffAuto msi;
+
+    /* additional resources to reserve */
+    PCIResReserve res_reserve;
 };
 typedef struct PCIBridgeDev PCIBridgeDev;
 
@@ -95,6 +98,12 @@ static void pci_bridge_dev_realize(PCIDevice *dev, Error **errp)
         error_free(local_err);
     }
 
+    err = pci_bridge_qemu_reserve_cap_init(dev, 0,
+                                         bridge_dev->res_reserve, errp);
+    if (err) {
+        goto cap_error;
+    }
+
     if (shpc_present(dev)) {
         /* TODO: spec recommends using 64 bit prefetcheable BAR.
          * Check whether that works well. */
@@ -103,6 +112,8 @@ static void pci_bridge_dev_realize(PCIDevice *dev, Error **errp)
     }
     return;
 
+cap_error:
+    msi_uninit(dev);
 msi_error:
     slotid_cap_cleanup(dev);
 slotid_error:
@@ -116,6 +127,8 @@ shpc_error:
 static void pci_bridge_dev_exitfn(PCIDevice *dev)
 {
     PCIBridgeDev *bridge_dev = PCI_BRIDGE_DEV(dev);
+
+    pci_del_capability(dev, PCI_CAP_ID_VNDR, sizeof(PCIBridgeQemuCap));
     if (msi_present(dev)) {
         msi_uninit(dev);
     }
@@ -162,6 +175,17 @@ static Property pci_bridge_dev_properties[] = {
                             ON_OFF_AUTO_AUTO),
     DEFINE_PROP_BIT(PCI_BRIDGE_DEV_PROP_SHPC, PCIBridgeDev, flags,
                     PCI_BRIDGE_DEV_F_SHPC_REQ, true),
+    DEFINE_PROP_UINT32("bus-reserve", PCIBridgeDev,
+                       res_reserve.bus, -1),
+    DEFINE_PROP_SIZE("io-reserve", PCIBridgeDev,
+                     res_reserve.io, -1),
+    DEFINE_PROP_SIZE("mem-reserve", PCIBridgeDev,
+                     res_reserve.mem_non_pref, -1),
+    DEFINE_PROP_SIZE("pref32-reserve", PCIBridgeDev,
+                     res_reserve.mem_pref_32, -1),
+    DEFINE_PROP_SIZE("pref64-reserve", PCIBridgeDev,
+                     res_reserve.mem_pref_64, -1),
+
     DEFINE_PROP_END_OF_LIST(),
 };
 

hw/pci/pci_bridge.c

@@ -411,38 +411,34 @@ void pci_bridge_map_irq(PCIBridge *br, const char* bus_name,
 
 
 int pci_bridge_qemu_reserve_cap_init(PCIDevice *dev, int cap_offset,
-                                     uint32_t bus_reserve, uint64_t io_reserve,
+                                     PCIResReserve res_reserve, Error **errp)
-                                     uint64_t mem_non_pref_reserve,
-                                     uint64_t mem_pref_32_reserve,
-                                     uint64_t mem_pref_64_reserve,
-                                     Error **errp)
 {
-    if (mem_pref_32_reserve != (uint64_t)-1 &&
+    if (res_reserve.mem_pref_32 != (uint64_t)-1 &&
-        mem_pref_64_reserve != (uint64_t)-1) {
+        res_reserve.mem_pref_64 != (uint64_t)-1) {
         error_setg(errp,
                    "PCI resource reserve cap: PREF32 and PREF64 conflict");
         return -EINVAL;
     }
 
-    if (mem_non_pref_reserve != (uint64_t)-1 &&
+    if (res_reserve.mem_non_pref != (uint64_t)-1 &&
-        mem_non_pref_reserve >= (1ULL << 32)) {
+        res_reserve.mem_non_pref >= (1ULL << 32)) {
         error_setg(errp,
                    "PCI resource reserve cap: mem-reserve must be less than 4G");
         return -EINVAL;
     }
 
-    if (mem_pref_32_reserve != (uint64_t)-1 &&
+    if (res_reserve.mem_pref_32 != (uint64_t)-1 &&
-        mem_pref_32_reserve >= (1ULL << 32)) {
+        res_reserve.mem_pref_32 >= (1ULL << 32)) {
         error_setg(errp,
                    "PCI resource reserve cap: pref32-reserve  must be less than 4G");
         return -EINVAL;
     }
 
-    if (bus_reserve == (uint32_t)-1 &&
+    if (res_reserve.bus == (uint32_t)-1 &&
-        io_reserve == (uint64_t)-1 &&
+        res_reserve.io == (uint64_t)-1 &&
-        mem_non_pref_reserve == (uint64_t)-1 &&
+        res_reserve.mem_non_pref == (uint64_t)-1 &&
-        mem_pref_32_reserve == (uint64_t)-1 &&
+        res_reserve.mem_pref_32 == (uint64_t)-1 &&
-        mem_pref_64_reserve == (uint64_t)-1) {
+        res_reserve.mem_pref_64 == (uint64_t)-1) {
         return 0;
     }
 
@@ -450,11 +446,11 @@ int pci_bridge_qemu_reserve_cap_init(PCIDevice *dev, int cap_offset,
     PCIBridgeQemuCap cap = {
             .len = cap_len,
             .type = REDHAT_PCI_CAP_RESOURCE_RESERVE,
-            .bus_res = bus_reserve,
+            .bus_res = res_reserve.bus,
-            .io = io_reserve,
+            .io = res_reserve.io,
-            .mem = mem_non_pref_reserve,
+            .mem = res_reserve.mem_non_pref,
-            .mem_pref_32 = mem_pref_32_reserve,
+            .mem_pref_32 = res_reserve.mem_pref_32,
-            .mem_pref_64 = mem_pref_64_reserve
+            .mem_pref_64 = res_reserve.mem_pref_64
     };
 
     int offset = pci_add_capability(dev, PCI_CAP_ID_VNDR,

hw/virtio/vhost.c

@@ -1073,10 +1073,8 @@ static void vhost_virtqueue_stop(struct vhost_dev *dev,
         .index = vhost_vq_index,
     };
     int r;
-    int a;
 
-    a = virtio_queue_get_desc_addr(vdev, idx);
+    if (virtio_queue_get_desc_addr(vdev, idx) == 0) {
-    if (a == 0) {
         /* Don't stop the virtqueue which might have not been started */
         return;
     }

hw/virtio/virtio.c

@@ -2006,14 +2006,25 @@ static int virtio_set_features_nocheck(VirtIODevice *vdev, uint64_t val)
 
 int virtio_set_features(VirtIODevice *vdev, uint64_t val)
 {
-   /*
+    int ret;
+    /*
      * The driver must not attempt to set features after feature negotiation
      * has finished.
      */
     if (vdev->status & VIRTIO_CONFIG_S_FEATURES_OK) {
         return -EINVAL;
     }
-    return virtio_set_features_nocheck(vdev, val);
+    ret = virtio_set_features_nocheck(vdev, val);
+    if (!ret && virtio_vdev_has_feature(vdev, VIRTIO_RING_F_EVENT_IDX)) {
+        /* VIRTIO_RING_F_EVENT_IDX changes the size of the caches.  */
+        int i;
+        for (i = 0; i < VIRTIO_QUEUE_MAX; i++) {
+            if (vdev->vq[i].vring.num != 0) {
+                virtio_init_region_cache(vdev, i);
+            }
+        }
+    }
+    return ret;
 }
 
 int virtio_load(VirtIODevice *vdev, QEMUFile *f, int version_id)

include/hw/pci/pci_bridge.h

@@ -133,11 +133,19 @@ typedef struct PCIBridgeQemuCap {
 
 #define REDHAT_PCI_CAP_RESOURCE_RESERVE 1
 
+/*
+ * PCI BUS/IO/MEM/PREFMEM additional resources recorded as a
+ * capability in PCI configuration space to reserve on firmware init.
+ */
+typedef struct PCIResReserve {
+    uint32_t bus;
+    uint64_t io;
+    uint64_t mem_non_pref;
+    uint64_t mem_pref_32;
+    uint64_t mem_pref_64;
+} PCIResReserve;
+
 int pci_bridge_qemu_reserve_cap_init(PCIDevice *dev, int cap_offset,
-                              uint32_t bus_reserve, uint64_t io_reserve,
+                               PCIResReserve res_reserve, Error **errp);
-                              uint64_t mem_non_pref_reserve,
-                              uint64_t mem_pref_32_reserve,
-                              uint64_t mem_pref_64_reserve,
-                              Error **errp);
 
 #endif /* QEMU_PCI_BRIDGE_H */