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

pc, acpi, pci, virtio: fixes, cleanups, features, tests

Some fixes and cleanups. New tests.
Configurable tx queue size for virtio-net.
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>

# gpg: Signature made Mon 03 Jul 2017 20:43:17 BST
# gpg:                using RSA key 0x281F0DB8D28D5469
# gpg: Good signature from "Michael S. Tsirkin <mst@kernel.org>"
# gpg:                 aka "Michael S. Tsirkin <mst@redhat.com>"
# gpg: WARNING: This key is not certified with a trusted signature!
# gpg:          There is no indication that the signature belongs to the owner.
# 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: (21 commits)
  i386/acpi: update expected acpi files
  virtio-net: fix tx queue size for !vhost-user
  tests: Add unit tests for the VM Generation ID feature
  vhost-user: unregister slave req handler at cleanup time
  vhost: ensure vhost_ops are set before calling iotlb callback
  intel_iommu: fix migration breakage on mr switch
  hw/acpi: remove dead acpi code
  fw_cfg: move setting of FW_CFG_VERSION_DMA bit to fw_cfg_init1()
  fw_cfg: don't map the fw_cfg IO ports in fw_cfg_io_realize()
  i386/kvm/pci-assign: Use errp directly rather than local_err
  i386/kvm/pci-assign: Fix return type of verify_irqchip_kernel()
  pci: Convert shpc_init() to Error
  pci: Convert to realize
  pci: Replace pci_add_capability2() with pci_add_capability()
  pci: Make errp the last parameter of pci_add_capability()
  pci: Fix the wrong assertion.
  pci: Add comment for pci_add_capability2()
  pci: Clean up error checking in pci_add_capability()
  intel_iommu: relax iq tail check on VTD_GCMD_QIE enable
  hw/pci-bridge/dec: Classify the DEC PCI bridge as bridge device
  ...
Signed-off-by: NPeter Maydell <peter.maydell@linaro.org>

hw/i386/acpi-build.c

@@ -1912,16 +1912,6 @@ build_dsdt(GArray *table_data, BIOSLinker *linker,
         build_piix4_pci_hotplug(dsdt);
         build_piix4_pci0_int(dsdt);
     } else {
-        sb_scope = aml_scope("_SB");
-        aml_append(sb_scope,
-            aml_operation_region("PCST", AML_SYSTEM_IO, aml_int(0xae00), 0x0c));
-        aml_append(sb_scope,
-            aml_operation_region("PCSB", AML_SYSTEM_IO, aml_int(0xae0c), 0x01));
-        field = aml_field("PCSB", AML_ANY_ACC, AML_NOLOCK, AML_WRITE_AS_ZEROS);
-        aml_append(field, aml_named_field("PCIB", 8));
-        aml_append(sb_scope, field);
-        aml_append(dsdt, sb_scope);
-
         sb_scope = aml_scope("_SB");
         dev = aml_device("PCI0");
         aml_append(dev, aml_name_decl("_HID", aml_eisaid("PNP0A08")));

hw/i386/amd_iommu.c

@@ -1158,13 +1158,23 @@ static void amdvi_realize(DeviceState *dev, Error **err)
     x86_iommu->type = TYPE_AMD;
     qdev_set_parent_bus(DEVICE(&s->pci), &bus->qbus);
     object_property_set_bool(OBJECT(&s->pci), true, "realized", err);
-    s->capab_offset = pci_add_capability(&s->pci.dev, AMDVI_CAPAB_ID_SEC, 0,
-                                         AMDVI_CAPAB_SIZE);
-    assert(s->capab_offset > 0);
-    ret = pci_add_capability(&s->pci.dev, PCI_CAP_ID_MSI, 0, AMDVI_CAPAB_REG_SIZE);
-    assert(ret > 0);
-    ret = pci_add_capability(&s->pci.dev, PCI_CAP_ID_HT, 0, AMDVI_CAPAB_REG_SIZE);
-    assert(ret > 0);
+    ret = pci_add_capability(&s->pci.dev, AMDVI_CAPAB_ID_SEC, 0,
+                                         AMDVI_CAPAB_SIZE, err);
+    if (ret < 0) {
+        return;
+    }
+    s->capab_offset = ret;
+
+    ret = pci_add_capability(&s->pci.dev, PCI_CAP_ID_MSI, 0,
+                             AMDVI_CAPAB_REG_SIZE, err);
+    if (ret < 0) {
+        return;
+    }
+    ret = pci_add_capability(&s->pci.dev, PCI_CAP_ID_HT, 0,
+                             AMDVI_CAPAB_REG_SIZE, err);
+    if (ret < 0) {
+        return;
+    }
 
     /* set up MMIO */
     memory_region_init_io(&s->mmio, OBJECT(s), &mmio_mem_ops, s, "amdvi-mmio",

hw/i386/intel_iommu.c

@@ -1450,10 +1450,7 @@ static uint64_t vtd_iotlb_flush(IntelIOMMUState *s, uint64_t val)
     return iaig;
 }
 
-static inline bool vtd_queued_inv_enable_check(IntelIOMMUState *s)
-{
-    return s->iq_tail == 0;
-}
+static void vtd_fetch_inv_desc(IntelIOMMUState *s);
 
 static inline bool vtd_queued_inv_disable_check(IntelIOMMUState *s)
 {
@@ -1468,16 +1465,24 @@ static void vtd_handle_gcmd_qie(IntelIOMMUState *s, bool en)
     trace_vtd_inv_qi_enable(en);
 
     if (en) {
-        if (vtd_queued_inv_enable_check(s)) {
-            s->iq = iqa_val & VTD_IQA_IQA_MASK;
-            /* 2^(x+8) entries */
-            s->iq_size = 1UL << ((iqa_val & VTD_IQA_QS) + 8);
-            s->qi_enabled = true;
-            trace_vtd_inv_qi_setup(s->iq, s->iq_size);
-            /* Ok - report back to driver */
-            vtd_set_clear_mask_long(s, DMAR_GSTS_REG, 0, VTD_GSTS_QIES);
-        } else {
-            trace_vtd_err_qi_enable(s->iq_tail);
+        s->iq = iqa_val & VTD_IQA_IQA_MASK;
+        /* 2^(x+8) entries */
+        s->iq_size = 1UL << ((iqa_val & VTD_IQA_QS) + 8);
+        s->qi_enabled = true;
+        trace_vtd_inv_qi_setup(s->iq, s->iq_size);
+        /* Ok - report back to driver */
+        vtd_set_clear_mask_long(s, DMAR_GSTS_REG, 0, VTD_GSTS_QIES);
+
+        if (s->iq_tail != 0) {
+            /*
+             * This is a spec violation but Windows guests are known to set up
+             * Queued Invalidation this way so we allow the write and process
+             * Invalidation Descriptors right away.
+             */
+            trace_vtd_warn_invalid_qi_tail(s->iq_tail);
+            if (!(vtd_get_long_raw(s, DMAR_FSTS_REG) & VTD_FSTS_IQE)) {
+                vtd_fetch_inv_desc(s);
+            }
         }
     } else {
         if (vtd_queued_inv_disable_check(s)) {
@@ -2332,11 +2337,26 @@ static void vtd_iommu_notify_flag_changed(MemoryRegion *iommu,
     }
 }
 
+static int vtd_post_load(void *opaque, int version_id)
+{
+    IntelIOMMUState *iommu = opaque;
+
+    /*
+     * Memory regions are dynamically turned on/off depending on
+     * context entry configurations from the guest. After migration,
+     * we need to make sure the memory regions are still correct.
+     */
+    vtd_switch_address_space_all(iommu);
+
+    return 0;
+}
+
 static const VMStateDescription vtd_vmstate = {
     .name = "iommu-intel",
     .version_id = 1,
     .minimum_version_id = 1,
     .priority = MIG_PRI_IOMMU,
+    .post_load = vtd_post_load,
     .fields = (VMStateField[]) {
         VMSTATE_UINT64(root, IntelIOMMUState),
         VMSTATE_UINT64(intr_root, IntelIOMMUState),

hw/i386/kvm/pci-assign.c

@@ -824,12 +824,13 @@ static void assign_device(AssignedDevice *dev, Error **errp)
     }
 }
 
-static void verify_irqchip_in_kernel(Error **errp)
+static int verify_irqchip_in_kernel(Error **errp)
 {
     if (kvm_irqchip_in_kernel()) {
-        return;
+        return -1;
     }
     error_setg(errp, "pci-assign requires KVM with in-kernel irqchip enabled");
+    return 0;
 }
 
 static int assign_intx(AssignedDevice *dev, Error **errp)
@@ -838,7 +839,6 @@ static int assign_intx(AssignedDevice *dev, Error **errp)
     PCIINTxRoute intx_route;
     bool intx_host_msi;
     int r;
-    Error *local_err = NULL;
 
     /* Interrupt PIN 0 means don't use INTx */
     if (assigned_dev_pci_read_byte(&dev->dev, PCI_INTERRUPT_PIN) == 0) {
@@ -846,9 +846,7 @@ static int assign_intx(AssignedDevice *dev, Error **errp)
         return 0;
     }
 
-    verify_irqchip_in_kernel(&local_err);
-    if (local_err) {
-        error_propagate(errp, local_err);
+    if (verify_irqchip_in_kernel(errp) < 0) {
         return -ENOTSUP;
     }
 
@@ -1234,7 +1232,6 @@ static int assigned_device_pci_cap_init(PCIDevice *pci_dev, Error **errp)
     AssignedDevice *dev = PCI_ASSIGN(pci_dev);
     PCIRegion *pci_region = dev->real_device.regions;
     int ret, pos;
-    Error *local_err = NULL;
 
     /* Clear initial capabilities pointer and status copied from hw */
     pci_set_byte(pci_dev->config + PCI_CAPABILITY_LIST, 0);
@@ -1246,18 +1243,15 @@ static int assigned_device_pci_cap_init(PCIDevice *pci_dev, Error **errp)
      * MSI capability is the 1st capability in capability config */
     pos = pci_find_cap_offset(pci_dev, PCI_CAP_ID_MSI, 0);
     if (pos != 0 && kvm_check_extension(kvm_state, KVM_CAP_ASSIGN_DEV_IRQ)) {
-        verify_irqchip_in_kernel(&local_err);
-        if (local_err) {
-            error_propagate(errp, local_err);
+        if (verify_irqchip_in_kernel(errp) < 0) {
             return -ENOTSUP;
         }
         dev->dev.cap_present |= QEMU_PCI_CAP_MSI;
         dev->cap.available |= ASSIGNED_DEVICE_CAP_MSI;
         /* Only 32-bit/no-mask currently supported */
-        ret = pci_add_capability2(pci_dev, PCI_CAP_ID_MSI, pos, 10,
-                                  &local_err);
+        ret = pci_add_capability(pci_dev, PCI_CAP_ID_MSI, pos, 10,
+                                  errp);
         if (ret < 0) {
-            error_propagate(errp, local_err);
             return ret;
         }
         pci_dev->msi_cap = pos;
@@ -1281,17 +1275,14 @@ static int assigned_device_pci_cap_init(PCIDevice *pci_dev, Error **errp)
         uint32_t msix_table_entry;
         uint16_t msix_max;
 
-        verify_irqchip_in_kernel(&local_err);
-        if (local_err) {
-            error_propagate(errp, local_err);
+        if (verify_irqchip_in_kernel(errp) < 0) {
             return -ENOTSUP;
         }
         dev->dev.cap_present |= QEMU_PCI_CAP_MSIX;
         dev->cap.available |= ASSIGNED_DEVICE_CAP_MSIX;
-        ret = pci_add_capability2(pci_dev, PCI_CAP_ID_MSIX, pos, 12,
-                                  &local_err);
+        ret = pci_add_capability(pci_dev, PCI_CAP_ID_MSIX, pos, 12,
+                                  errp);
         if (ret < 0) {
-            error_propagate(errp, local_err);
             return ret;
         }
         pci_dev->msix_cap = pos;
@@ -1318,10 +1309,9 @@ static int assigned_device_pci_cap_init(PCIDevice *pci_dev, Error **errp)
     if (pos) {
         uint16_t pmc;
 
-        ret = pci_add_capability2(pci_dev, PCI_CAP_ID_PM, pos, PCI_PM_SIZEOF,
-                                  &local_err);
+        ret = pci_add_capability(pci_dev, PCI_CAP_ID_PM, pos, PCI_PM_SIZEOF,
+                                  errp);
         if (ret < 0) {
-            error_propagate(errp, local_err);
             return ret;
         }
 
@@ -1386,10 +1376,9 @@ static int assigned_device_pci_cap_init(PCIDevice *pci_dev, Error **errp)
             return -EINVAL;
         }
 
-        ret = pci_add_capability2(pci_dev, PCI_CAP_ID_EXP, pos, size,
-                                  &local_err);
+        ret = pci_add_capability(pci_dev, PCI_CAP_ID_EXP, pos, size,
+                                  errp);
         if (ret < 0) {
-            error_propagate(errp, local_err);
             return ret;
         }
 
@@ -1462,10 +1451,9 @@ static int assigned_device_pci_cap_init(PCIDevice *pci_dev, Error **errp)
         uint32_t status;
 
         /* Only expose the minimum, 8 byte capability */
-        ret = pci_add_capability2(pci_dev, PCI_CAP_ID_PCIX, pos, 8,
-                                  &local_err);
+        ret = pci_add_capability(pci_dev, PCI_CAP_ID_PCIX, pos, 8,
+                                  errp);
         if (ret < 0) {
-            error_propagate(errp, local_err);
             return ret;
         }
 
@@ -1490,10 +1478,9 @@ static int assigned_device_pci_cap_init(PCIDevice *pci_dev, Error **errp)
     pos = pci_find_cap_offset(pci_dev, PCI_CAP_ID_VPD, 0);
     if (pos) {
         /* Direct R/W passthrough */
-        ret = pci_add_capability2(pci_dev, PCI_CAP_ID_VPD, pos, 8,
-                                  &local_err);
+        ret = pci_add_capability(pci_dev, PCI_CAP_ID_VPD, pos, 8,
+                                  errp);
         if (ret < 0) {
-            error_propagate(errp, local_err);
             return ret;
         }
 
@@ -1508,10 +1495,9 @@ static int assigned_device_pci_cap_init(PCIDevice *pci_dev, Error **errp)
         pos += PCI_CAP_LIST_NEXT) {
         uint8_t len = pci_get_byte(pci_dev->config + pos + PCI_CAP_FLAGS);
         /* Direct R/W passthrough */
-        ret = pci_add_capability2(pci_dev, PCI_CAP_ID_VNDR, pos, len,
-                                  &local_err);
+        ret = pci_add_capability(pci_dev, PCI_CAP_ID_VNDR, pos, len,
+                                  errp);
         if (ret < 0) {
-            error_propagate(errp, local_err);
             return ret;
         }
 

hw/i386/trace-events

@@ -74,7 +74,7 @@ vtd_err_dmar_slpte_read_error(uint64_t iova, int level) "iova 0x%"PRIx64" level
 vtd_err_dmar_slpte_perm_error(uint64_t iova, int level, uint64_t slpte, bool is_write) "iova 0x%"PRIx64" level %d slpte 0x%"PRIx64" write %d"
 vtd_err_dmar_slpte_resv_error(uint64_t iova, int level, uint64_t slpte) "iova 0x%"PRIx64" level %d slpte 0x%"PRIx64
 vtd_err_dmar_translate(uint8_t bus, uint8_t slot, uint8_t func, uint64_t iova) "dev %02x:%02x.%02x iova 0x%"PRIx64
-vtd_err_qi_enable(uint16_t tail) "tail 0x%"PRIx16
+vtd_warn_invalid_qi_tail(uint16_t tail) "tail 0x%"PRIx16
 vtd_err_qi_disable(uint16_t head, uint16_t tail, int type) "head 0x%"PRIx16" tail 0x%"PRIx16" last_desc_type %d"
 vtd_err_qi_tail(uint16_t tail, uint16_t size) "tail 0x%"PRIx16" size 0x%"PRIx16
 vtd_err_irte(int index, uint64_t lo, uint64_t hi) "index %d low 0x%"PRIx64" high 0x%"PRIx64

hw/ide/ich.c

@@ -130,7 +130,7 @@ static void pci_ich9_ahci_realize(PCIDevice *dev, Error **errp)
     pci_register_bar(dev, ICH9_MEM_BAR, PCI_BASE_ADDRESS_SPACE_MEMORY,
                      &d->ahci.mem);
 
-    sata_cap_offset = pci_add_capability2(dev, PCI_CAP_ID_SATA,
+    sata_cap_offset = pci_add_capability(dev, PCI_CAP_ID_SATA,
                                           ICH9_SATA_CAP_OFFSET, SATA_CAP_SIZE,
                                           errp);
     if (sata_cap_offset < 0) {

hw/net/e1000e.c

@@ -47,6 +47,7 @@
 #include "e1000e_core.h"
 
 #include "trace.h"
+#include "qapi/error.h"
 
 #define TYPE_E1000E "e1000e"
 #define E1000E(obj) OBJECT_CHECK(E1000EState, (obj), TYPE_E1000E)
@@ -372,21 +373,26 @@ e1000e_gen_dsn(uint8_t *mac)
 static int
 e1000e_add_pm_capability(PCIDevice *pdev, uint8_t offset, uint16_t pmc)
 {
-    int ret = pci_add_capability(pdev, PCI_CAP_ID_PM, offset, PCI_PM_SIZEOF);
+    Error *local_err = NULL;
+    int ret = pci_add_capability(pdev, PCI_CAP_ID_PM, offset,
+                                 PCI_PM_SIZEOF, &local_err);
 
-    if (ret >= 0) {
-        pci_set_word(pdev->config + offset + PCI_PM_PMC,
-                     PCI_PM_CAP_VER_1_1 |
-                     pmc);
+    if (local_err) {
+        error_report_err(local_err);
+        return ret;
+    }
 
-        pci_set_word(pdev->wmask + offset + PCI_PM_CTRL,
-                     PCI_PM_CTRL_STATE_MASK |
-                     PCI_PM_CTRL_PME_ENABLE |
-                     PCI_PM_CTRL_DATA_SEL_MASK);
+    pci_set_word(pdev->config + offset + PCI_PM_PMC,
+                 PCI_PM_CAP_VER_1_1 |
+                 pmc);
 
-        pci_set_word(pdev->w1cmask + offset + PCI_PM_CTRL,
-                     PCI_PM_CTRL_PME_STATUS);
-    }
+    pci_set_word(pdev->wmask + offset + PCI_PM_CTRL,
+                 PCI_PM_CTRL_STATE_MASK |
+                 PCI_PM_CTRL_PME_ENABLE |
+                 PCI_PM_CTRL_DATA_SEL_MASK);
+
+    pci_set_word(pdev->w1cmask + offset + PCI_PM_CTRL,
+                 PCI_PM_CTRL_PME_STATUS);
 
     return ret;
 }

hw/net/eepro100.c

@@ -48,6 +48,7 @@
 #include "sysemu/sysemu.h"
 #include "sysemu/dma.h"
 #include "qemu/bitops.h"
+#include "qapi/error.h"
 
 /* QEMU sends frames smaller than 60 bytes to ethernet nics.
  * Such frames are rejected by real nics and their emulations.
@@ -494,7 +495,7 @@ static void eepro100_fcp_interrupt(EEPRO100State * s)
 }
 #endif
 
-static void e100_pci_reset(EEPRO100State * s)
+static void e100_pci_reset(EEPRO100State *s, Error **errp)
 {
     E100PCIDeviceInfo *info = eepro100_get_class(s);
     uint32_t device = s->device;
@@ -570,8 +571,12 @@ static void e100_pci_reset(EEPRO100State * s)
         /* Power Management Capabilities */
         int cfg_offset = 0xdc;
         int r = pci_add_capability(&s->dev, PCI_CAP_ID_PM,
-                                   cfg_offset, PCI_PM_SIZEOF);
-        assert(r >= 0);
+                                   cfg_offset, PCI_PM_SIZEOF,
+                                   errp);
+        if (r < 0) {
+            return;
+        }
+
         pci_set_word(pci_conf + cfg_offset + PCI_PM_PMC, 0x7e21);
 #if 0 /* TODO: replace dummy code for power management emulation. */
         /* TODO: Power Management Control / Status. */
@@ -1858,12 +1863,17 @@ static void e100_nic_realize(PCIDevice *pci_dev, Error **errp)
 {
     EEPRO100State *s = DO_UPCAST(EEPRO100State, dev, pci_dev);
     E100PCIDeviceInfo *info = eepro100_get_class(s);
+    Error *local_err = NULL;
 
     TRACE(OTHER, logout("\n"));
 
     s->device = info->device;
 
-    e100_pci_reset(s);
+    e100_pci_reset(s, &local_err);
+    if (local_err) {
+        error_propagate(errp, local_err);
+        return;
+    }
 
     /* Add 64 * 2 EEPROM. i82557 and i82558 support a 64 word EEPROM,
      * i82559 and later support 64 or 256 word EEPROM. */

hw/net/virtio-net.c

@@ -34,8 +34,11 @@
 
 /* previously fixed value */
 #define VIRTIO_NET_RX_QUEUE_DEFAULT_SIZE 256
+#define VIRTIO_NET_TX_QUEUE_DEFAULT_SIZE 256
+
 /* for now, only allow larger queues; with virtio-1, guest can downsize */
 #define VIRTIO_NET_RX_QUEUE_MIN_SIZE VIRTIO_NET_RX_QUEUE_DEFAULT_SIZE
+#define VIRTIO_NET_TX_QUEUE_MIN_SIZE VIRTIO_NET_TX_QUEUE_DEFAULT_SIZE
 
 /*
  * Calculate the number of bytes up to and including the given 'field' of
@@ -495,6 +498,24 @@ static void virtio_net_set_mrg_rx_bufs(VirtIONet *n, int mergeable_rx_bufs,
     }
 }
 
+static int virtio_net_max_tx_queue_size(VirtIONet *n)
+{
+    NetClientState *peer = n->nic_conf.peers.ncs[0];
+
+    /*
+     * Backends other than vhost-user don't support max queue size.
+     */
+    if (!peer) {
+        return VIRTIO_NET_TX_QUEUE_DEFAULT_SIZE;
+    }
+
+    if (peer->info->type != NET_CLIENT_DRIVER_VHOST_USER) {
+        return VIRTIO_NET_TX_QUEUE_DEFAULT_SIZE;
+    }
+
+    return VIRTQUEUE_MAX_SIZE;
+}
+
 static int peer_attach(VirtIONet *n, int index)
 {
     NetClientState *nc = qemu_get_subqueue(n->nic, index);
@@ -1508,15 +1529,18 @@ static void virtio_net_add_queue(VirtIONet *n, int index)
 
     n->vqs[index].rx_vq = virtio_add_queue(vdev, n->net_conf.rx_queue_size,
                                            virtio_net_handle_rx);
+
     if (n->net_conf.tx && !strcmp(n->net_conf.tx, "timer")) {
         n->vqs[index].tx_vq =
-            virtio_add_queue(vdev, 256, virtio_net_handle_tx_timer);
+            virtio_add_queue(vdev, n->net_conf.tx_queue_size,
+                             virtio_net_handle_tx_timer);
         n->vqs[index].tx_timer = timer_new_ns(QEMU_CLOCK_VIRTUAL,
                                               virtio_net_tx_timer,
                                               &n->vqs[index]);
     } else {
         n->vqs[index].tx_vq =
-            virtio_add_queue(vdev, 256, virtio_net_handle_tx_bh);
+            virtio_add_queue(vdev, n->net_conf.tx_queue_size,
+                             virtio_net_handle_tx_bh);
         n->vqs[index].tx_bh = qemu_bh_new(virtio_net_tx_bh, &n->vqs[index]);
     }
 
@@ -1927,6 +1951,17 @@ static void virtio_net_device_realize(DeviceState *dev, Error **errp)
         return;
     }
 
+    if (n->net_conf.tx_queue_size < VIRTIO_NET_TX_QUEUE_MIN_SIZE ||
+        n->net_conf.tx_queue_size > VIRTQUEUE_MAX_SIZE ||
+        !is_power_of_2(n->net_conf.tx_queue_size)) {
+        error_setg(errp, "Invalid tx_queue_size (= %" PRIu16 "), "
+                   "must be a power of 2 between %d and %d",
+                   n->net_conf.tx_queue_size, VIRTIO_NET_TX_QUEUE_MIN_SIZE,
+                   VIRTQUEUE_MAX_SIZE);
+        virtio_cleanup(vdev);
+        return;
+    }
+
     n->max_queues = MAX(n->nic_conf.peers.queues, 1);
     if (n->max_queues * 2 + 1 > VIRTIO_QUEUE_MAX) {
         error_setg(errp, "Invalid number of queues (= %" PRIu32 "), "
@@ -1947,6 +1982,9 @@ static void virtio_net_device_realize(DeviceState *dev, Error **errp)
         error_report("Defaulting to \"bh\"");
     }
 
+    n->net_conf.tx_queue_size = MIN(virtio_net_max_tx_queue_size(n),
+                                    n->net_conf.tx_queue_size);
+
     for (i = 0; i < n->max_queues; i++) {
         virtio_net_add_queue(n, i);
     }
@@ -2106,6 +2144,8 @@ static Property virtio_net_properties[] = {
     DEFINE_PROP_STRING("tx", VirtIONet, net_conf.tx),
     DEFINE_PROP_UINT16("rx_queue_size", VirtIONet, net_conf.rx_queue_size,
                        VIRTIO_NET_RX_QUEUE_DEFAULT_SIZE),
+    DEFINE_PROP_UINT16("tx_queue_size", VirtIONet, net_conf.tx_queue_size,
+                       VIRTIO_NET_TX_QUEUE_DEFAULT_SIZE),
     DEFINE_PROP_UINT16("host_mtu", VirtIONet, net_conf.mtu, 0),
     DEFINE_PROP_BOOL("x-mtu-bypass-backend", VirtIONet, mtu_bypass_backend,
                      true),

hw/nvram/fw_cfg.c

@@ -96,7 +96,6 @@ struct FWCfgIoState {
     /*< public >*/
 
     MemoryRegion comb_iomem;
-    uint32_t iobase, dma_iobase;
 };
 
 struct FWCfgMemState {
@@ -914,6 +913,7 @@ static void fw_cfg_init1(DeviceState *dev)
 {
     FWCfgState *s = FW_CFG(dev);
     MachineState *machine = MACHINE(qdev_get_machine());
+    uint32_t version = FW_CFG_VERSION;
 
     assert(!object_resolve_path(FW_CFG_PATH, NULL));
 
@@ -928,6 +928,12 @@ static void fw_cfg_init1(DeviceState *dev)
     fw_cfg_bootsplash(s);
     fw_cfg_reboot(s);
 
+    if (s->dma_enabled) {
+        version |= FW_CFG_VERSION_DMA;
+    }
+
+    fw_cfg_add_i32(s, FW_CFG_ID, version);
+
     s->machine_ready.notify = fw_cfg_machine_ready;
     qemu_add_machine_init_done_notifier(&s->machine_ready);
 }
@@ -936,30 +942,31 @@ FWCfgState *fw_cfg_init_io_dma(uint32_t iobase, uint32_t dma_iobase,
                                 AddressSpace *dma_as)
 {
     DeviceState *dev;
+    SysBusDevice *sbd;
+    FWCfgIoState *ios;
     FWCfgState *s;
-    uint32_t version = FW_CFG_VERSION;
     bool dma_requested = dma_iobase && dma_as;
 
     dev = qdev_create(NULL, TYPE_FW_CFG_IO);
-    qdev_prop_set_uint32(dev, "iobase", iobase);
-    qdev_prop_set_uint32(dev, "dma_iobase", dma_iobase);
     if (!dma_requested) {
         qdev_prop_set_bit(dev, "dma_enabled", false);
     }
 
     fw_cfg_init1(dev);
+
+    sbd = SYS_BUS_DEVICE(dev);
+    ios = FW_CFG_IO(dev);
+    sysbus_add_io(sbd, iobase, &ios->comb_iomem);
+
     s = FW_CFG(dev);
 
     if (s->dma_enabled) {
         /* 64 bits for the address field */
         s->dma_as = dma_as;
         s->dma_addr = 0;
-
-        version |= FW_CFG_VERSION_DMA;
+        sysbus_add_io(sbd, dma_iobase, &s->dma_iomem);
     }
 
-    fw_cfg_add_i32(s, FW_CFG_ID, version);
-
     return s;
 }
 
@@ -975,7 +982,6 @@ FWCfgState *fw_cfg_init_mem_wide(hwaddr ctl_addr,
     DeviceState *dev;
     SysBusDevice *sbd;
     FWCfgState *s;
-    uint32_t version = FW_CFG_VERSION;
     bool dma_requested = dma_addr && dma_as;
 
     dev = qdev_create(NULL, TYPE_FW_CFG_MEM);
@@ -996,11 +1002,8 @@ FWCfgState *fw_cfg_init_mem_wide(hwaddr ctl_addr,
         s->dma_as = dma_as;
         s->dma_addr = 0;
         sysbus_mmio_map(sbd, 2, dma_addr);
-        version |= FW_CFG_VERSION_DMA;
     }
 
-    fw_cfg_add_i32(s, FW_CFG_ID, version);
-
     return s;
 }
 
@@ -1059,8 +1062,6 @@ static void fw_cfg_file_slots_allocate(FWCfgState *s, Error **errp)
 }
 
 static Property fw_cfg_io_properties[] = {
-    DEFINE_PROP_UINT32("iobase", FWCfgIoState, iobase, -1),
-    DEFINE_PROP_UINT32("dma_iobase", FWCfgIoState, dma_iobase, -1),
     DEFINE_PROP_BOOL("dma_enabled", FWCfgIoState, parent_obj.dma_enabled,
                      true),
     DEFINE_PROP_UINT16("x-file-slots", FWCfgIoState, parent_obj.file_slots,
@@ -1071,7 +1072,6 @@ static Property fw_cfg_io_properties[] = {
 static void fw_cfg_io_realize(DeviceState *dev, Error **errp)
 {
     FWCfgIoState *s = FW_CFG_IO(dev);
-    SysBusDevice *sbd = SYS_BUS_DEVICE(dev);
     Error *local_err = NULL;
 
     fw_cfg_file_slots_allocate(FW_CFG(s), &local_err);
@@ -1085,13 +1085,11 @@ static void fw_cfg_io_realize(DeviceState *dev, Error **errp)
      * of the i/o region used is FW_CFG_CTL_SIZE */
     memory_region_init_io(&s->comb_iomem, OBJECT(s), &fw_cfg_comb_mem_ops,
                           FW_CFG(s), "fwcfg", FW_CFG_CTL_SIZE);
-    sysbus_add_io(sbd, s->iobase, &s->comb_iomem);
 
     if (FW_CFG(s)->dma_enabled) {
         memory_region_init_io(&FW_CFG(s)->dma_iomem, OBJECT(s),
                               &fw_cfg_dma_mem_ops, FW_CFG(s), "fwcfg.dma",
                               sizeof(dma_addr_t));
-        sysbus_add_io(sbd, s->dma_iobase, &FW_CFG(s)->dma_iomem);
     }
 }
 

hw/pci-bridge/dec.c

@@ -62,6 +62,7 @@ static void dec_21154_pci_bridge_class_init(ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS(klass);
     PCIDeviceClass *k = PCI_DEVICE_CLASS(klass);
 
+    set_bit(DEVICE_CATEGORY_BRIDGE, dc->categories);
     k->realize = dec_pci_bridge_realize;
     k->exit = pci_bridge_exitfn;
     k->vendor_id = PCI_VENDOR_ID_DEC;
@@ -118,6 +119,7 @@ static void dec_21154_pci_host_class_init(ObjectClass *klass, void *data)
     PCIDeviceClass *k = PCI_DEVICE_CLASS(klass);
     DeviceClass *dc = DEVICE_CLASS(klass);
 
+    set_bit(DEVICE_CATEGORY_BRIDGE, dc->categories);
     k->realize = dec_21154_pci_host_realize;
     k->vendor_id = PCI_VENDOR_ID_DEC;
     k->device_id = PCI_DEVICE_ID_DEC_21154;

hw/pci-bridge/i82801b11.c

@@ -44,6 +44,7 @@
 #include "qemu/osdep.h"
 #include "hw/pci/pci.h"
 #include "hw/i386/ich9.h"
+#include "qapi/error.h"
 
 
 /*****************************************************************************/
@@ -58,24 +59,23 @@ typedef struct I82801b11Bridge {
     /*< public >*/
 } I82801b11Bridge;
 
-static int i82801b11_bridge_initfn(PCIDevice *d)
+static void i82801b11_bridge_realize(PCIDevice *d, Error **errp)
 {
     int rc;
 
     pci_bridge_initfn(d, TYPE_PCI_BUS);
 
     rc = pci_bridge_ssvid_init(d, I82801ba_SSVID_OFFSET,
-                               I82801ba_SSVID_SVID, I82801ba_SSVID_SSID);
+                               I82801ba_SSVID_SVID, I82801ba_SSVID_SSID,
+                               errp);
     if (rc < 0) {
         goto err_bridge;
     }
     pci_config_set_prog_interface(d->config, PCI_CLASS_BRIDGE_PCI_INF_SUB);
-    return 0;
+    return;
 
 err_bridge:
     pci_bridge_exitfn(d);
-
-    return rc;
 }
 
 static const VMStateDescription i82801b11_bridge_dev_vmstate = {
@@ -95,7 +95,7 @@ static void i82801b11_bridge_class_init(ObjectClass *klass, void *data)
     k->vendor_id = PCI_VENDOR_ID_INTEL;
     k->device_id = PCI_DEVICE_ID_INTEL_82801BA_11;
     k->revision = ICH9_D2P_A2_REVISION;
-    k->init = i82801b11_bridge_initfn;
+    k->realize = i82801b11_bridge_realize;
     k->config_write = pci_bridge_write_config;
     dc->vmsd = &i82801b11_bridge_dev_vmstate;
     set_bit(DEVICE_CATEGORY_BRIDGE, dc->categories);

hw/pci-bridge/pci_bridge_dev.c

@@ -49,7 +49,7 @@ struct PCIBridgeDev {
 };
 typedef struct PCIBridgeDev PCIBridgeDev;
 
-static int pci_bridge_dev_initfn(PCIDevice *dev)
+static void pci_bridge_dev_realize(PCIDevice *dev, Error **errp)
 {
     PCIBridge *br = PCI_BRIDGE(dev);
     PCIBridgeDev *bridge_dev = PCI_BRIDGE_DEV(dev);
@@ -62,7 +62,7 @@ static int pci_bridge_dev_initfn(PCIDevice *dev)
         dev->config[PCI_INTERRUPT_PIN] = 0x1;
         memory_region_init(&bridge_dev->bar, OBJECT(dev), "shpc-bar",
                            shpc_bar_size(dev));
-        err = shpc_init(dev, &br->sec_bus, &bridge_dev->bar, 0);
+        err = shpc_init(dev, &br->sec_bus, &bridge_dev->bar, 0, errp);
         if (err) {
             goto shpc_error;
         }
@@ -71,7 +71,7 @@ static int pci_bridge_dev_initfn(PCIDevice *dev)
         bridge_dev->msi = ON_OFF_AUTO_OFF;
     }
 
-    err = slotid_cap_init(dev, 0, bridge_dev->chassis_nr, 0);
+    err = slotid_cap_init(dev, 0, bridge_dev->chassis_nr, 0, errp);
     if (err) {
         goto slotid_error;
     }
@@ -87,7 +87,7 @@ static int pci_bridge_dev_initfn(PCIDevice *dev)
             /* Can't satisfy user's explicit msi=on request, fail */
             error_append_hint(&local_err, "You have to use msi=auto (default) "
                     "or msi=off with this machine type.\n");
-            error_report_err(local_err);
+            error_propagate(errp, local_err);
             goto msi_error;
         }
         assert(!local_err || bridge_dev->msi == ON_OFF_AUTO_AUTO);
@@ -101,7 +101,7 @@ static int pci_bridge_dev_initfn(PCIDevice *dev)
         pci_register_bar(dev, 0, PCI_BASE_ADDRESS_SPACE_MEMORY |
                          PCI_BASE_ADDRESS_MEM_TYPE_64, &bridge_dev->bar);
     }
-    return 0;
+    return;
 
 msi_error:
     slotid_cap_cleanup(dev);
@@ -111,8 +111,6 @@ slotid_error:
     }
 shpc_error:
     pci_bridge_exitfn(dev);
-
-    return err;
 }
 
 static void pci_bridge_dev_exitfn(PCIDevice *dev)
@@ -216,7 +214,7 @@ static void pci_bridge_dev_class_init(ObjectClass *klass, void *data)
     PCIDeviceClass *k = PCI_DEVICE_CLASS(klass);
     HotplugHandlerClass *hc = HOTPLUG_HANDLER_CLASS(klass);
 
-    k->init = pci_bridge_dev_initfn;
+    k->realize = pci_bridge_dev_realize;
     k->exit = pci_bridge_dev_exitfn;
     k->config_write = pci_bridge_dev_write_config;
     k->vendor_id = PCI_VENDOR_ID_REDHAT;

hw/pci-bridge/pcie_root_port.c

@@ -59,29 +59,30 @@ static void rp_realize(PCIDevice *d, Error **errp)
     PCIDeviceClass *dc = PCI_DEVICE_GET_CLASS(d);
     PCIERootPortClass *rpc = PCIE_ROOT_PORT_GET_CLASS(d);
     int rc;
-    Error *local_err = NULL;
 
     pci_config_set_interrupt_pin(d->config, 1);
     pci_bridge_initfn(d, TYPE_PCIE_BUS);
     pcie_port_init_reg(d);
 
-    rc = pci_bridge_ssvid_init(d, rpc->ssvid_offset, dc->vendor_id, rpc->ssid);
+    rc = pci_bridge_ssvid_init(d, rpc->ssvid_offset, dc->vendor_id,
+                               rpc->ssid, errp);
     if (rc < 0) {
-        error_setg(errp, "Can't init SSV ID, error %d", rc);
+        error_append_hint(errp, "Can't init SSV ID, error %d\n", rc);
         goto err_bridge;
     }
 
     if (rpc->interrupts_init) {
-        rc = rpc->interrupts_init(d, &local_err);
+        rc = rpc->interrupts_init(d, errp);
         if (rc < 0) {
-            error_propagate(errp, local_err);
             goto err_bridge;
         }
     }
 
-    rc = pcie_cap_init(d, rpc->exp_offset, PCI_EXP_TYPE_ROOT_PORT, p->port);
+    rc = pcie_cap_init(d, rpc->exp_offset, PCI_EXP_TYPE_ROOT_PORT,
+                       p->port, errp);
     if (rc < 0) {
-        error_setg(errp, "Can't add Root Port capability, error %d", rc);
+        error_append_hint(errp, "Can't add Root Port capability, "
+                          "error %d\n", rc);
         goto err_int;
     }
 
@@ -98,9 +99,8 @@ static void rp_realize(PCIDevice *d, Error **errp)
     }
 
     rc = pcie_aer_init(d, PCI_ERR_VER, rpc->aer_offset,
-                       PCI_ERR_SIZEOF, &local_err);
+                       PCI_ERR_SIZEOF, errp);
     if (rc < 0) {
-        error_propagate(errp, local_err);
         goto err;
     }
     pcie_aer_root_init(d);

hw/pci-bridge/xio3130_downstream.c

@@ -56,33 +56,33 @@ static void xio3130_downstream_reset(DeviceState *qdev)
     pci_bridge_reset(qdev);
 }
 
-static int xio3130_downstream_initfn(PCIDevice *d)
+static void xio3130_downstream_realize(PCIDevice *d, Error **errp)
 {
     PCIEPort *p = PCIE_PORT(d);
     PCIESlot *s = PCIE_SLOT(d);
     int rc;
-    Error *err = NULL;
 
     pci_bridge_initfn(d, TYPE_PCIE_BUS);
     pcie_port_init_reg(d);
 
     rc = msi_init(d, XIO3130_MSI_OFFSET, XIO3130_MSI_NR_VECTOR,
                   XIO3130_MSI_SUPPORTED_FLAGS & PCI_MSI_FLAGS_64BIT,
-                  XIO3130_MSI_SUPPORTED_FLAGS & PCI_MSI_FLAGS_MASKBIT, &err);
+                  XIO3130_MSI_SUPPORTED_FLAGS & PCI_MSI_FLAGS_MASKBIT,
+                  errp);
     if (rc < 0) {
         assert(rc == -ENOTSUP);
-        error_report_err(err);
         goto err_bridge;
     }
 
     rc = pci_bridge_ssvid_init(d, XIO3130_SSVID_OFFSET,
-                               XIO3130_SSVID_SVID, XIO3130_SSVID_SSID);
+                               XIO3130_SSVID_SVID, XIO3130_SSVID_SSID,
+                               errp);
     if (rc < 0) {
         goto err_bridge;
     }
 
     rc = pcie_cap_init(d, XIO3130_EXP_OFFSET, PCI_EXP_TYPE_DOWNSTREAM,
-                       p->port);
+                       p->port, errp);
     if (rc < 0) {
         goto err_msi;
     }
@@ -98,13 +98,12 @@ static int xio3130_downstream_initfn(PCIDevice *d)
     }
 
     rc = pcie_aer_init(d, PCI_ERR_VER, XIO3130_AER_OFFSET,
-                       PCI_ERR_SIZEOF, &err);
+                       PCI_ERR_SIZEOF, errp);
     if (rc < 0) {
-        error_report_err(err);
         goto err;
     }
 
-    return 0;
+    return;
 
 err:
     pcie_chassis_del_slot(s);
@@ -114,7 +113,6 @@ err_msi:
     msi_uninit(d);
 err_bridge:
     pci_bridge_exitfn(d);
-    return rc;
 }
 
 static void xio3130_downstream_exitfn(PCIDevice *d)
@@ -181,7 +179,7 @@ static void xio3130_downstream_class_init(ObjectClass *klass, void *data)
     k->is_express = 1;
     k->is_bridge = 1;
     k->config_write = xio3130_downstream_write_config;
-    k->init = xio3130_downstream_initfn;
+    k->realize = xio3130_downstream_realize;
     k->exit = xio3130_downstream_exitfn;
     k->vendor_id = PCI_VENDOR_ID_TI;
     k->device_id = PCI_DEVICE_ID_TI_XIO3130D;

hw/pci-bridge/xio3130_upstream.c

@@ -53,32 +53,32 @@ static void xio3130_upstream_reset(DeviceState *qdev)
     pcie_cap_deverr_reset(d);
 }
 
-static int xio3130_upstream_initfn(PCIDevice *d)
+static void xio3130_upstream_realize(PCIDevice *d, Error **errp)
 {
     PCIEPort *p = PCIE_PORT(d);
     int rc;
-    Error *err = NULL;
 
     pci_bridge_initfn(d, TYPE_PCIE_BUS);
     pcie_port_init_reg(d);
 
     rc = msi_init(d, XIO3130_MSI_OFFSET, XIO3130_MSI_NR_VECTOR,
                   XIO3130_MSI_SUPPORTED_FLAGS & PCI_MSI_FLAGS_64BIT,
-                  XIO3130_MSI_SUPPORTED_FLAGS & PCI_MSI_FLAGS_MASKBIT, &err);
+                  XIO3130_MSI_SUPPORTED_FLAGS & PCI_MSI_FLAGS_MASKBIT,
+                  errp);
     if (rc < 0) {
         assert(rc == -ENOTSUP);
-        error_report_err(err);
         goto err_bridge;
     }
 
     rc = pci_bridge_ssvid_init(d, XIO3130_SSVID_OFFSET,
-                               XIO3130_SSVID_SVID, XIO3130_SSVID_SSID);
+                               XIO3130_SSVID_SVID, XIO3130_SSVID_SSID,
+                               errp);
     if (rc < 0) {
         goto err_bridge;
     }
 
     rc = pcie_cap_init(d, XIO3130_EXP_OFFSET, PCI_EXP_TYPE_UPSTREAM,
-                       p->port);
+                       p->port, errp);
     if (rc < 0) {
         goto err_msi;
     }
@@ -86,13 +86,12 @@ static int xio3130_upstream_initfn(PCIDevice *d)
     pcie_cap_deverr_init(d);
 
     rc = pcie_aer_init(d, PCI_ERR_VER, XIO3130_AER_OFFSET,
-                       PCI_ERR_SIZEOF, &err);
+                       PCI_ERR_SIZEOF, errp);
     if (rc < 0) {
-        error_report_err(err);
         goto err;
     }
 
-    return 0;
+    return;
 
 err:
     pcie_cap_exit(d);
@@ -100,7 +99,6 @@ err_msi:
     msi_uninit(d);
 err_bridge:
     pci_bridge_exitfn(d);
-    return rc;
 }
 
 static void xio3130_upstream_exitfn(PCIDevice *d)
@@ -153,7 +151,7 @@ static void xio3130_upstream_class_init(ObjectClass *klass, void *data)
     k->is_express = 1;
     k->is_bridge = 1;
     k->config_write = xio3130_upstream_write_config;
-    k->init = xio3130_upstream_initfn;
+    k->realize = xio3130_upstream_realize;
     k->exit = xio3130_upstream_exitfn;
     k->vendor_id = PCI_VENDOR_ID_TI;
     k->device_id = PCI_DEVICE_ID_TI_XIO3130U;

hw/pci/msi.c

@@ -216,7 +216,7 @@ int msi_init(struct PCIDevice *dev, uint8_t offset,
     }
 
     cap_size = msi_cap_sizeof(flags);
-    config_offset = pci_add_capability2(dev, PCI_CAP_ID_MSI, offset,
+    config_offset = pci_add_capability(dev, PCI_CAP_ID_MSI, offset,
                                         cap_size, errp);
     if (config_offset < 0) {
         return config_offset;

hw/pci/msix.c

@@ -301,7 +301,7 @@ int msix_init(struct PCIDevice *dev, unsigned short nentries,
         return -EINVAL;
     }
 
-    cap = pci_add_capability2(dev, PCI_CAP_ID_MSIX,
+    cap = pci_add_capability(dev, PCI_CAP_ID_MSIX,
                               cap_pos, MSIX_CAP_LENGTH, errp);
     if (cap < 0) {
         return cap;

hw/pci/pci.c

@@ -2259,28 +2259,12 @@ static void pci_del_option_rom(PCIDevice *pdev)
 }
 
 /*
- * if offset = 0,
- * Find and reserve space and add capability to the linked list
- * in pci config space
+ * On success, pci_add_capability() returns a positive value
+ * that the offset of the pci capability.
+ * On failure, it sets an error and returns a negative error
+ * code.
  */
 int pci_add_capability(PCIDevice *pdev, uint8_t cap_id,
-                       uint8_t offset, uint8_t size)
-{
-    int ret;
-    Error *local_err = NULL;
-
-    ret = pci_add_capability2(pdev, cap_id, offset, size, &local_err);
-    if (local_err) {
-        assert(ret < 0);
-        error_report_err(local_err);
-    } else {
-        /* success implies a positive offset in config space */
-        assert(ret > 0);
-    }
-    return ret;
-}
-
-int pci_add_capability2(PCIDevice *pdev, uint8_t cap_id,
                        uint8_t offset, uint8_t size,
                        Error **errp)
 {

hw/pci/pci_bridge.c

@@ -33,6 +33,7 @@
 #include "hw/pci/pci_bridge.h"
 #include "hw/pci/pci_bus.h"
 #include "qemu/range.h"
+#include "qapi/error.h"
 
 /* PCI bridge subsystem vendor ID helper functions */
 #define PCI_SSVID_SIZEOF        8
@@ -40,10 +41,13 @@
 #define PCI_SSVID_SSID          6
 
 int pci_bridge_ssvid_init(PCIDevice *dev, uint8_t offset,
-                          uint16_t svid, uint16_t ssid)
+                          uint16_t svid, uint16_t ssid,
+                          Error **errp)
 {
     int pos;
-    pos = pci_add_capability(dev, PCI_CAP_ID_SSVID, offset, PCI_SSVID_SIZEOF);
+
+    pos = pci_add_capability(dev, PCI_CAP_ID_SSVID, offset,
+                             PCI_SSVID_SIZEOF, errp);
     if (pos < 0) {
         return pos;
     }

hw/pci/pcie.c

@@ -86,7 +86,9 @@ pcie_cap_v1_fill(PCIDevice *dev, uint8_t port, uint8_t type, uint8_t version)
     pci_set_word(cmask + PCI_EXP_LNKSTA, 0);
 }
 
-int pcie_cap_init(PCIDevice *dev, uint8_t offset, uint8_t type, uint8_t port)
+int pcie_cap_init(PCIDevice *dev, uint8_t offset,
+                  uint8_t type, uint8_t port,
+                  Error **errp)
 {
     /* PCIe cap v2 init */
     int pos;
@@ -94,7 +96,8 @@ int pcie_cap_init(PCIDevice *dev, uint8_t offset, uint8_t type, uint8_t port)
 
     assert(pci_is_express(dev));
 
-    pos = pci_add_capability(dev, PCI_CAP_ID_EXP, offset, PCI_EXP_VER2_SIZEOF);
+    pos = pci_add_capability(dev, PCI_CAP_ID_EXP, offset,
+                             PCI_EXP_VER2_SIZEOF, errp);
     if (pos < 0) {
         return pos;
     }
@@ -123,11 +126,14 @@ int pcie_cap_v1_init(PCIDevice *dev, uint8_t offset, uint8_t type,
 {
     /* PCIe cap v1 init */
     int pos;
+    Error *local_err = NULL;
 
     assert(pci_is_express(dev));
 
-    pos = pci_add_capability(dev, PCI_CAP_ID_EXP, offset, PCI_EXP_VER1_SIZEOF);
+    pos = pci_add_capability(dev, PCI_CAP_ID_EXP, offset,
+                             PCI_EXP_VER1_SIZEOF, &local_err);
     if (pos < 0) {
+        error_report_err(local_err);
         return pos;
     }
     dev->exp.exp_cap = pos;
@@ -141,6 +147,8 @@ static int
 pcie_endpoint_cap_common_init(PCIDevice *dev, uint8_t offset, uint8_t cap_size)
 {
     uint8_t type = PCI_EXP_TYPE_ENDPOINT;
+    Error *local_err = NULL;
+    int ret;
 
     /*
      * Windows guests will report Code 10, device cannot start, if
@@ -151,9 +159,17 @@ pcie_endpoint_cap_common_init(PCIDevice *dev, uint8_t offset, uint8_t cap_size)
         type = PCI_EXP_TYPE_RC_END;
     }
 
-    return (cap_size == PCI_EXP_VER1_SIZEOF)
-        ? pcie_cap_v1_init(dev, offset, type, 0)
-        : pcie_cap_init(dev, offset, type, 0);
+    if (cap_size == PCI_EXP_VER1_SIZEOF) {
+        return pcie_cap_v1_init(dev, offset, type, 0);
+    } else {
+        ret = pcie_cap_init(dev, offset, type, 0, &local_err);
+
+        if (ret < 0) {
+            error_report_err(local_err);
+        }
+
+        return ret;
+    }
 }
 
 int pcie_endpoint_cap_init(PCIDevice *dev, uint8_t offset)

hw/pci/shpc.c

@@ -446,12 +446,13 @@ static void shpc_cap_update_dword(PCIDevice *d)
 }
 
 /* Add SHPC capability to the config space for the device. */
-static int shpc_cap_add_config(PCIDevice *d)
+static int shpc_cap_add_config(PCIDevice *d, Error **errp)
 {
     uint8_t *config;
     int config_offset;
     config_offset = pci_add_capability(d, PCI_CAP_ID_SHPC,
-                                       0, SHPC_CAP_LENGTH);
+                                       0, SHPC_CAP_LENGTH,
+                                       errp);
     if (config_offset < 0) {
         return config_offset;
     }
@@ -581,13 +582,14 @@ void shpc_device_hot_unplug_request_cb(HotplugHandler *hotplug_dev,
 }
 
 /* Initialize the SHPC structure in bridge's BAR. */
-int shpc_init(PCIDevice *d, PCIBus *sec_bus, MemoryRegion *bar, unsigned offset)
+int shpc_init(PCIDevice *d, PCIBus *sec_bus, MemoryRegion *bar,
+              unsigned offset, Error **errp)
 {
     int i, ret;
     int nslots = SHPC_MAX_SLOTS; /* TODO: qdev property? */
     SHPCDevice *shpc = d->shpc = g_malloc0(sizeof(*d->shpc));
     shpc->sec_bus = sec_bus;
-    ret = shpc_cap_add_config(d);
+    ret = shpc_cap_add_config(d, errp);
     if (ret) {
         g_free(d->shpc);
         return ret;

hw/pci/slotid_cap.c

@@ -2,18 +2,21 @@
 #include "hw/pci/slotid_cap.h"
 #include "hw/pci/pci.h"
 #include "qemu/error-report.h"
+#include "qapi/error.h"
 
 #define SLOTID_CAP_LENGTH 4
 #define SLOTID_NSLOTS_SHIFT ctz32(PCI_SID_ESR_NSLOTS)
 
 int slotid_cap_init(PCIDevice *d, int nslots,
                     uint8_t chassis,
-                    unsigned offset)
+                    unsigned offset,
+                    Error **errp)
 {
     int cap;
+
     if (!chassis) {
-        error_report("Bridge chassis not specified. Each bridge is required "
-                     "to be assigned a unique chassis id > 0.");
+        error_setg(errp, "Bridge chassis not specified. Each bridge is required"
+                   " to be assigned a unique chassis id > 0.");
         return -EINVAL;
     }
     if (nslots < 0 || nslots > (PCI_SID_ESR_NSLOTS >> SLOTID_NSLOTS_SHIFT)) {
@@ -21,7 +24,8 @@ int slotid_cap_init(PCIDevice *d, int nslots,
         return -EINVAL;
     }
 
-    cap = pci_add_capability(d, PCI_CAP_ID_SLOTID, offset, SLOTID_CAP_LENGTH);
+    cap = pci_add_capability(d, PCI_CAP_ID_SLOTID, offset,
+                             SLOTID_CAP_LENGTH, errp);
     if (cap < 0) {
         return cap;
     }

hw/usb/hcd-xhci.c

@@ -3419,7 +3419,7 @@ static void usb_xhci_realize(struct PCIDevice *dev, Error **errp)
     if (pci_bus_is_express(dev->bus) ||
         xhci_get_flag(xhci, XHCI_FLAG_FORCE_PCIE_ENDCAP)) {
         ret = pcie_endpoint_cap_init(dev, 0xa0);
-        assert(ret >= 0);
+        assert(ret > 0);
     }
 
     if (xhci->msix != ON_OFF_AUTO_OFF) {

hw/vfio/pci.c

@@ -1743,11 +1743,14 @@ static int vfio_setup_pcie_cap(VFIOPCIDevice *vdev, int pos, uint8_t size,
                                PCI_EXP_LNKCAP_MLW | PCI_EXP_LNKCAP_SLS);
     }
 
-    pos = pci_add_capability(&vdev->pdev, PCI_CAP_ID_EXP, pos, size);
-    if (pos >= 0) {
-        vdev->pdev.exp.exp_cap = pos;
+    pos = pci_add_capability(&vdev->pdev, PCI_CAP_ID_EXP, pos, size,
+                             errp);
+    if (pos < 0) {
+        return pos;
     }
 
+    vdev->pdev.exp.exp_cap = pos;
+
     return pos;
 }
 
@@ -1834,14 +1837,14 @@ static int vfio_add_std_cap(VFIOPCIDevice *vdev, uint8_t pos, Error **errp)
     case PCI_CAP_ID_PM:
         vfio_check_pm_reset(vdev, pos);
         vdev->pm_cap = pos;
-        ret = pci_add_capability2(pdev, cap_id, pos, size, errp);
+        ret = pci_add_capability(pdev, cap_id, pos, size, errp);
         break;
     case PCI_CAP_ID_AF:
         vfio_check_af_flr(vdev, pos);
-        ret = pci_add_capability2(pdev, cap_id, pos, size, errp);
+        ret = pci_add_capability(pdev, cap_id, pos, size, errp);
         break;
     default:
-        ret = pci_add_capability2(pdev, cap_id, pos, size, errp);
+        ret = pci_add_capability(pdev, cap_id, pos, size, errp);
         break;
     }
 out:

hw/virtio/vhost-backend.c

@@ -309,7 +309,10 @@ int vhost_backend_update_device_iotlb(struct vhost_dev *dev,
         return -EINVAL;
     }
 
-    return dev->vhost_ops->vhost_send_device_iotlb_msg(dev, &imsg);
+    if (dev->vhost_ops && dev->vhost_ops->vhost_send_device_iotlb_msg)
+        return dev->vhost_ops->vhost_send_device_iotlb_msg(dev, &imsg);
+
+    return -ENODEV;
 }
 
 int vhost_backend_invalidate_device_iotlb(struct vhost_dev *dev,
@@ -321,7 +324,10 @@ int vhost_backend_invalidate_device_iotlb(struct vhost_dev *dev,
     imsg.size = len;
     imsg.type = VHOST_IOTLB_INVALIDATE;
 
-    return dev->vhost_ops->vhost_send_device_iotlb_msg(dev, &imsg);
+    if (dev->vhost_ops && dev->vhost_ops->vhost_send_device_iotlb_msg)
+        return dev->vhost_ops->vhost_send_device_iotlb_msg(dev, &imsg);
+
+    return -ENODEV;
 }
 
 int vhost_backend_handle_iotlb_msg(struct vhost_dev *dev,

hw/virtio/vhost-user.c

@@ -779,6 +779,7 @@ static int vhost_user_cleanup(struct vhost_dev *dev)
 
     u = dev->opaque;
     if (u->slave_fd >= 0) {
+        qemu_set_fd_handler(u->slave_fd, NULL, NULL, NULL);
         close(u->slave_fd);
         u->slave_fd = -1;
     }

hw/virtio/virtio-pci.c

@@ -1162,8 +1162,8 @@ static int virtio_pci_add_mem_cap(VirtIOPCIProxy *proxy,
     PCIDevice *dev = &proxy->pci_dev;
     int offset;
 
-    offset = pci_add_capability(dev, PCI_CAP_ID_VNDR, 0, cap->cap_len);
-    assert(offset > 0);
+    offset = pci_add_capability(dev, PCI_CAP_ID_VNDR, 0,
+                                cap->cap_len, &error_abort);
 
     assert(cap->cap_len >= sizeof *cap);
     memcpy(dev->config + offset + PCI_CAP_FLAGS, &cap->cap_len,
@@ -1810,8 +1810,12 @@ static void virtio_pci_realize(PCIDevice *pci_dev, Error **errp)
         pos = pcie_endpoint_cap_init(pci_dev, 0);
         assert(pos > 0);
 
-        pos = pci_add_capability(pci_dev, PCI_CAP_ID_PM, 0, PCI_PM_SIZEOF);
-        assert(pos > 0);
+        pos = pci_add_capability(pci_dev, PCI_CAP_ID_PM, 0,
+                                 PCI_PM_SIZEOF, errp);
+        if (pos < 0) {
+            return;
+        }
+
         pci_dev->exp.pm_cap = pos;
 
         /*

include/hw/pci/pci.h

@@ -356,8 +356,6 @@ void pci_unregister_vga(PCIDevice *pci_dev);
 pcibus_t pci_get_bar_addr(PCIDevice *pci_dev, int region_num);
 
 int pci_add_capability(PCIDevice *pdev, uint8_t cap_id,
-                       uint8_t offset, uint8_t size);
-int pci_add_capability2(PCIDevice *pdev, uint8_t cap_id,
                        uint8_t offset, uint8_t size,
                        Error **errp);
 

include/hw/pci/pci_bridge.h

@@ -33,7 +33,8 @@
 #define PCI_BRIDGE_DEV_PROP_SHPC       "shpc"
 
 int pci_bridge_ssvid_init(PCIDevice *dev, uint8_t offset,
-                          uint16_t svid, uint16_t ssid);
+                          uint16_t svid, uint16_t ssid,
+                          Error **errp);
 
 PCIDevice *pci_bridge_get_device(PCIBus *bus);
 PCIBus *pci_bridge_get_sec_bus(PCIBridge *br);

include/hw/pci/pcie.h

@@ -84,7 +84,8 @@ struct PCIExpressDevice {
 #define COMPAT_PROP_PCP "power_controller_present"
 
 /* PCI express capability helper functions */
-int pcie_cap_init(PCIDevice *dev, uint8_t offset, uint8_t type, uint8_t port);
+int pcie_cap_init(PCIDevice *dev, uint8_t offset, uint8_t type,
+                  uint8_t port, Error **errp);
 int pcie_cap_v1_init(PCIDevice *dev, uint8_t offset,
                      uint8_t type, uint8_t port);
 int pcie_endpoint_cap_init(PCIDevice *dev, uint8_t offset);

include/hw/pci/shpc.h

@@ -38,7 +38,8 @@ struct SHPCDevice {
 
 void shpc_reset(PCIDevice *d);
 int shpc_bar_size(PCIDevice *dev);
-int shpc_init(PCIDevice *dev, PCIBus *sec_bus, MemoryRegion *bar, unsigned off);
+int shpc_init(PCIDevice *dev, PCIBus *sec_bus, MemoryRegion *bar,
+              unsigned off, Error **errp);
 void shpc_cleanup(PCIDevice *dev, MemoryRegion *bar);
 void shpc_free(PCIDevice *dev);
 void shpc_cap_write_config(PCIDevice *d, uint32_t addr, uint32_t val, int len);

include/hw/pci/slotid_cap.h

@@ -5,7 +5,8 @@
 
 int slotid_cap_init(PCIDevice *dev, int nslots,
                     uint8_t chassis,
-                    unsigned offset);
+                    unsigned offset,
+                    Error **errp);
 void slotid_cap_cleanup(PCIDevice *dev);
 
 #endif

include/hw/virtio/virtio-net.h

@@ -36,6 +36,7 @@ typedef struct virtio_net_conf
     int32_t txburst;
     char *tx;
     uint16_t rx_queue_size;
+    uint16_t tx_queue_size;
     uint16_t mtu;
 } virtio_net_conf;
 

tests/Makefile.include

@@ -250,6 +250,7 @@ check-qtest-i386-y += tests/usb-hcd-xhci-test$(EXESUF)
 gcov-files-i386-y += hw/usb/hcd-xhci.c
 check-qtest-i386-y += tests/pc-cpu-test$(EXESUF)
 check-qtest-i386-y += tests/q35-test$(EXESUF)
+check-qtest-i386-y += tests/vmgenid-test$(EXESUF)
 gcov-files-i386-y += hw/pci-host/q35.c
 check-qtest-i386-$(CONFIG_VHOST_NET_TEST_i386) += tests/vhost-user-test$(EXESUF)
 ifeq ($(CONFIG_VHOST_NET_TEST_i386),)
@@ -760,6 +761,7 @@ tests/test-uuid$(EXESUF): tests/test-uuid.o $(test-util-obj-y)
 tests/test-arm-mptimer$(EXESUF): tests/test-arm-mptimer.o
 tests/test-qapi-util$(EXESUF): tests/test-qapi-util.o $(test-util-obj-y)
 tests/numa-test$(EXESUF): tests/numa-test.o
+tests/vmgenid-test$(EXESUF): tests/vmgenid-test.o tests/acpi-utils.o
 
 tests/migration/stress$(EXESUF): tests/migration/stress.o
 	$(call quiet-command, $(LINKPROG) -static -O3 $(PTHREAD_LIB) -o $@ $< ,"LINK","$(TARGET_DIR)$@")

tests/vmgenid-test.c

+/*
+ * QTest testcase for VM Generation ID
+ *
+ * Copyright (c) 2016 Red Hat, Inc.
+ * Copyright (c) 2017 Skyport Systems
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ */
+
+#include <glib.h>
+#include <string.h>
+#include <unistd.h>
+#include "qemu/osdep.h"
+#include "qemu/bitmap.h"
+#include "qemu/uuid.h"
+#include "hw/acpi/acpi-defs.h"
+#include "acpi-utils.h"
+#include "libqtest.h"
+
+#define VGID_GUID "324e6eaf-d1d1-4bf6-bf41-b9bb6c91fb87"
+#define VMGENID_GUID_OFFSET 40   /* allow space for
+                                  * OVMF SDT Header Probe Supressor
+                                  */
+#define RSDP_ADDR_INVALID 0x100000 /* RSDP must be below this address */
+#define RSDP_SLEEP_US     100000   /* Sleep for 100ms between tries */
+#define RSDP_TRIES_MAX    100      /* Max total time is 10 seconds */
+
+typedef struct {
+    AcpiTableHeader header;
+    gchar name_op;
+    gchar vgia[4];
+    gchar val_op;
+    uint32_t vgia_val;
+} QEMU_PACKED VgidTable;
+
+static uint32_t acpi_find_vgia(void)
+{
+    uint32_t rsdp_offset;
+    uint32_t guid_offset = 0;
+    AcpiRsdpDescriptor rsdp_table;
+    uint32_t rsdt;
+    AcpiRsdtDescriptorRev1 rsdt_table;
+    int tables_nr;
+    uint32_t *tables;
+    AcpiTableHeader ssdt_table;
+    VgidTable vgid_table;
+    int i;
+
+    /* Tables may take a short time to be set up by the guest */
+    for (i = 0; i < RSDP_TRIES_MAX; i++) {
+        rsdp_offset = acpi_find_rsdp_address();
+        if (rsdp_offset < RSDP_ADDR_INVALID) {
+            break;
+        }
+        g_usleep(RSDP_SLEEP_US);
+    }
+    g_assert_cmphex(rsdp_offset, <, RSDP_ADDR_INVALID);
+
+    acpi_parse_rsdp_table(rsdp_offset, &rsdp_table);
+
+    rsdt = rsdp_table.rsdt_physical_address;
+    /* read the header */
+    ACPI_READ_TABLE_HEADER(&rsdt_table, rsdt);
+    ACPI_ASSERT_CMP(rsdt_table.signature, "RSDT");
+
+    /* compute the table entries in rsdt */
+    tables_nr = (rsdt_table.length - sizeof(AcpiRsdtDescriptorRev1)) /
+                sizeof(uint32_t);
+    g_assert_cmpint(tables_nr, >, 0);
+
+    /* get the addresses of the tables pointed by rsdt */
+    tables = g_new0(uint32_t, tables_nr);
+    ACPI_READ_ARRAY_PTR(tables, tables_nr, rsdt);
+
+    for (i = 0; i < tables_nr; i++) {
+        ACPI_READ_TABLE_HEADER(&ssdt_table, tables[i]);
+        if (!strncmp((char *)ssdt_table.oem_table_id, "VMGENID", 7)) {
+            /* the first entry in the table should be VGIA
+             * That's all we need
+             */
+            ACPI_READ_FIELD(vgid_table.name_op, tables[i]);
+            g_assert(vgid_table.name_op == 0x08);  /* name */
+            ACPI_READ_ARRAY(vgid_table.vgia, tables[i]);
+            g_assert(memcmp(vgid_table.vgia, "VGIA", 4) == 0);
+            ACPI_READ_FIELD(vgid_table.val_op, tables[i]);
+            g_assert(vgid_table.val_op == 0x0C);  /* dword */
+            ACPI_READ_FIELD(vgid_table.vgia_val, tables[i]);
+            /* The GUID is written at a fixed offset into the fw_cfg file
+             * in order to implement the "OVMF SDT Header probe suppressor"
+             * see docs/specs/vmgenid.txt for more details
+             */
+            guid_offset = vgid_table.vgia_val + VMGENID_GUID_OFFSET;
+            break;
+        }
+    }
+    g_free(tables);
+    return guid_offset;
+}
+
+static void read_guid_from_memory(QemuUUID *guid)
+{
+    uint32_t vmgenid_addr;
+    int i;
+
+    vmgenid_addr = acpi_find_vgia();
+    g_assert(vmgenid_addr);
+
+    /* Read the GUID directly from guest memory */
+    for (i = 0; i < 16; i++) {
+        guid->data[i] = readb(vmgenid_addr + i);
+    }
+    /* The GUID is in little-endian format in the guest, while QEMU
+     * uses big-endian.  Swap after reading.
+     */
+    qemu_uuid_bswap(guid);
+}
+
+static void read_guid_from_monitor(QemuUUID *guid)
+{
+    QDict *rsp, *rsp_ret;
+    const char *guid_str;
+
+    rsp = qmp("{ 'execute': 'query-vm-generation-id' }");
+    if (qdict_haskey(rsp, "return")) {
+        rsp_ret = qdict_get_qdict(rsp, "return");
+        g_assert(qdict_haskey(rsp_ret, "guid"));
+        guid_str = qdict_get_str(rsp_ret, "guid");
+        g_assert(qemu_uuid_parse(guid_str, guid) == 0);
+    }
+    QDECREF(rsp);
+}
+
+static void vmgenid_set_guid_test(void)
+{
+    QemuUUID expected, measured;
+    gchar *cmd;
+
+    g_assert(qemu_uuid_parse(VGID_GUID, &expected) == 0);
+
+    cmd = g_strdup_printf("-machine accel=tcg -device vmgenid,id=testvgid,"
+                          "guid=%s", VGID_GUID);
+    qtest_start(cmd);
+
+    /* Read the GUID from accessing guest memory */
+    read_guid_from_memory(&measured);
+    g_assert(memcmp(measured.data, expected.data, sizeof(measured.data)) == 0);
+
+    qtest_quit(global_qtest);
+    g_free(cmd);
+}
+
+static void vmgenid_set_guid_auto_test(void)
+{
+    const char *cmd;
+    QemuUUID measured;
+
+    cmd = "-machine accel=tcg -device vmgenid,id=testvgid," "guid=auto";
+    qtest_start(cmd);
+
+    read_guid_from_memory(&measured);
+
+    /* Just check that the GUID is non-null */
+    g_assert(!qemu_uuid_is_null(&measured));
+
+    qtest_quit(global_qtest);
+}
+
+static void vmgenid_query_monitor_test(void)
+{
+    QemuUUID expected, measured;
+    gchar *cmd;
+
+    g_assert(qemu_uuid_parse(VGID_GUID, &expected) == 0);
+
+    cmd = g_strdup_printf("-machine accel=tcg -device vmgenid,id=testvgid,"
+                          "guid=%s", VGID_GUID);
+    qtest_start(cmd);
+
+    /* Read the GUID via the monitor */
+    read_guid_from_monitor(&measured);
+    g_assert(memcmp(measured.data, expected.data, sizeof(measured.data)) == 0);
+
+    qtest_quit(global_qtest);
+    g_free(cmd);
+}
+
+int main(int argc, char **argv)
+{
+    int ret;
+
+    g_test_init(&argc, &argv, NULL);
+
+    qtest_add_func("/vmgenid/vmgenid/set-guid",
+                   vmgenid_set_guid_test);
+    qtest_add_func("/vmgenid/vmgenid/set-guid-auto",
+                   vmgenid_set_guid_auto_test);
+    qtest_add_func("/vmgenid/vmgenid/query-monitor",
+                   vmgenid_query_monitor_test);
+    ret = g_test_run();
+
+    return ret;
+}