Merge tag 'for_upstream' of https://git.kernel.org/pub/scm/virt/kvm/mst/qemu into staging

virtio,pc,pci: features, fixes

Several features that landed at the last possible moment:

Passthrough HDM decoder emulation
Refactor cryptodev
RAS error emulation and injection
acpi-index support on non-hotpluggable slots
Dynamically switch to vhost shadow virtqueues at vdpa net migration

Plus a couple of bugfixes that look important to have in the release.

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

# -----BEGIN PGP SIGNATURE-----
#
# iQFDBAABCAAtFiEEXQn9CHHI+FuUyooNKB8NuNKNVGkFAmQJ8TYPHG1zdEByZWRo
# YXQuY29tAAoJECgfDbjSjVRp37YIAMpQA5/ddmKKz/ABtBMHB5JX/SVYcG+1xkBR
# j9IFYusOfmmDfmgAhv0Qxi9+Wik95lszVZUnphvocSGd0PXH47pK7yv9RZ1ttaYX
# oAbXrGqXo8rUhl1ksQsJ8Iasj2di1BLP0byPuozbRkg1Kkz5TqRd9+hBqSBGEx21
# tsP5708UVCDAriwYYO78Cx0ZasmB9bqqeom5FdEsg9sYJ5aElOOvitp9YO1p2xhU
# gRvhD+k/aqNi+mfOUF7qGDBanxKgx75VV/KU1cjjS9R1vNtwRhfc/26PBrROY00a
# wkZWnAxmzDFKRS6cEfeb+eDGEVjC3IqLAjcFeuAIT/78CwdvIiY=
# =e1yv
# -----END PGP SIGNATURE-----
# gpg: Signature made Thu 09 Mar 2023 14:46:14 GMT
# gpg:                using RSA key 5D09FD0871C8F85B94CA8A0D281F0DB8D28D5469
# gpg:                issuer "mst@redhat.com"
# gpg: Good signature from "Michael S. Tsirkin <mst@kernel.org>" [full]
# gpg:                 aka "Michael S. Tsirkin <mst@redhat.com>" [full]
# 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

* tag 'for_upstream' of https://git.kernel.org/pub/scm/virt/kvm/mst/qemu: (72 commits)
  virtio: fix reachable assertion due to stale value of cached region size
  hw/virtio/vhost-user: avoid using unitialized errp
  hw/pxb-cxl: Support passthrough HDM Decoders unless overridden
  hw/pci: Add pcie_count_ds_port() and pcie_find_port_first() helpers
  hw/mem/cxl_type3: Add CXL RAS Error Injection Support.
  hw/pci/aer: Make PCIE AER error injection facility available for other emulation to use.
  hw/cxl: Fix endian issues in CXL RAS capability defaults / masks
  hw/mem/cxl-type3: Add AER extended capability
  hw/pci-bridge/cxl_root_port: Wire up MSI
  hw/pci-bridge/cxl_root_port: Wire up AER
  hw/pci/aer: Add missing routing for AER errors
  hw/pci/aer: Implement PCI_ERR_UNCOR_MASK register
  pcihp: add ACPI PCI hotplug specific is_hotpluggable_bus() callback
  pcihp: move fields enabling hotplug into AcpiPciHpState
  acpi: pci: move out ACPI PCI hotplug generator from generic slot generator build_append_pci_bus_devices()
  acpi: pci: move BSEL into build_append_pcihp_slots()
  acpi: pci: drop BSEL usage when deciding that device isn't hotpluggable
  pci: move acpi-index uniqueness check to generic PCI device code
  tests: acpi: update expected blobs
  tests: acpi: add non zero function device with acpi-index on non-hotpluggble bus
  ...

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

4 files changed, 116 insertions, 2 deletions

diff --git a/hw/pci/pci-internal.h b/hw/pci/pci-internal.h
index 2ea356b..a7d6d8a 100644
--- a/hw/pci/pci-internal.h
+++ b/hw/pci/pci-internal.h
@@ -20,6 +20,5 @@ void pcibus_dev_print(Monitor *mon, DeviceState *dev, int indent);
 
 int pcie_aer_parse_error_string(const char *error_name,
                                 uint32_t *status, bool *correctable);
-int pcie_aer_inject_error(PCIDevice *dev, const PCIEAERErr *err);
 
 #endif
diff --git a/hw/pci/pci.c b/hw/pci/pci.c
index 034fe49..def5000 100644
--- a/hw/pci/pci.c
+++ b/hw/pci/pci.c
@@ -95,6 +95,21 @@ static const VMStateDescription vmstate_pcibus = {
     }
 };
 
+static gint g_cmp_uint32(gconstpointer a, gconstpointer b, gpointer user_data)
+{
+    return a - b;
+}
+
+static GSequence *pci_acpi_index_list(void)
+{
+    static GSequence *used_acpi_index_list;
+
+    if (!used_acpi_index_list) {
+        used_acpi_index_list = g_sequence_new(NULL);
+    }
+    return used_acpi_index_list;
+}
+
 static void pci_init_bus_master(PCIDevice *pci_dev)
 {
     AddressSpace *dma_as = pci_device_iommu_address_space(pci_dev);
@@ -1246,6 +1261,17 @@ static void pci_qdev_unrealize(DeviceState *dev)
     do_pci_unregister_device(pci_dev);
 
     pci_dev->msi_trigger = NULL;
+
+    /*
+     * clean up acpi-index so it could reused by another device
+     */
+    if (pci_dev->acpi_index) {
+        GSequence *used_indexes = pci_acpi_index_list();
+
+        g_sequence_remove(g_sequence_lookup(used_indexes,
+                          GINT_TO_POINTER(pci_dev->acpi_index),
+                          g_cmp_uint32, NULL));
+    }
 }
 
 void pci_register_bar(PCIDevice *pci_dev, int region_num,
@@ -2005,6 +2031,8 @@ PCIDevice *pci_find_device(PCIBus *bus, int bus_num, uint8_t devfn)
     return bus->devices[devfn];
 }
 
+#define ONBOARD_INDEX_MAX (16 * 1024 - 1)
+
 static void pci_qdev_realize(DeviceState *qdev, Error **errp)
 {
     PCIDevice *pci_dev = (PCIDevice *)qdev;
@@ -2014,6 +2042,35 @@ static void pci_qdev_realize(DeviceState *qdev, Error **errp)
     bool is_default_rom;
     uint16_t class_id;
 
+    /*
+     * capped by systemd (see: udev-builtin-net_id.c)
+     * as it's the only known user honor it to avoid users
+     * misconfigure QEMU and then wonder why acpi-index doesn't work
+     */
+    if (pci_dev->acpi_index > ONBOARD_INDEX_MAX) {
+        error_setg(errp, "acpi-index should be less or equal to %u",
+                   ONBOARD_INDEX_MAX);
+        return;
+    }
+
+    /*
+     * make sure that acpi-index is unique across all present PCI devices
+     */
+    if (pci_dev->acpi_index) {
+        GSequence *used_indexes = pci_acpi_index_list();
+
+        if (g_sequence_lookup(used_indexes,
+                              GINT_TO_POINTER(pci_dev->acpi_index),
+                              g_cmp_uint32, NULL)) {
+            error_setg(errp, "a PCI device with acpi-index = %" PRIu32
+                       " already exist", pci_dev->acpi_index);
+            return;
+        }
+        g_sequence_insert_sorted(used_indexes,
+                                 GINT_TO_POINTER(pci_dev->acpi_index),
+                                 g_cmp_uint32, NULL);
+    }
+
     if (pci_dev->romsize != -1 && !is_power_of_2(pci_dev->romsize)) {
         error_setg(errp, "ROM size %u is not a power of two", pci_dev->romsize);
         return;
diff --git a/hw/pci/pcie_aer.c b/hw/pci/pcie_aer.c
index 9a19be4..103667c 100644
--- a/hw/pci/pcie_aer.c
+++ b/hw/pci/pcie_aer.c
@@ -112,6 +112,10 @@ int pcie_aer_init(PCIDevice *dev, uint8_t cap_ver, uint16_t offset,
 
     pci_set_long(dev->w1cmask + offset + PCI_ERR_UNCOR_STATUS,
                  PCI_ERR_UNC_SUPPORTED);
+    pci_set_long(dev->config + offset + PCI_ERR_UNCOR_MASK,
+                 PCI_ERR_UNC_MASK_DEFAULT);
+    pci_set_long(dev->wmask + offset + PCI_ERR_UNCOR_MASK,
+                 PCI_ERR_UNC_SUPPORTED);
 
     pci_set_long(dev->config + offset + PCI_ERR_UNCOR_SEVER,
                  PCI_ERR_UNC_SEVERITY_DEFAULT);
@@ -188,8 +192,16 @@ static void pcie_aer_update_uncor_status(PCIDevice *dev)
 static bool
 pcie_aer_msg_alldev(PCIDevice *dev, const PCIEAERMsg *msg)
 {
+    uint16_t devctl = pci_get_word(dev->config + dev->exp.exp_cap +
+                                   PCI_EXP_DEVCTL);
     if (!(pcie_aer_msg_is_uncor(msg) &&
-          (pci_get_word(dev->config + PCI_COMMAND) & PCI_COMMAND_SERR))) {
+          (pci_get_word(dev->config + PCI_COMMAND) & PCI_COMMAND_SERR)) &&
+        !((msg->severity == PCI_ERR_ROOT_CMD_NONFATAL_EN) &&
+          (devctl & PCI_EXP_DEVCTL_NFERE)) &&
+        !((msg->severity == PCI_ERR_ROOT_CMD_COR_EN) &&
+          (devctl & PCI_EXP_DEVCTL_CERE)) &&
+        !((msg->severity == PCI_ERR_ROOT_CMD_FATAL_EN) &&
+          (devctl & PCI_EXP_DEVCTL_FERE))) {
         return false;
     }
 
diff --git a/hw/pci/pcie_port.c b/hw/pci/pcie_port.c
index 65a397a..20ff2b3 100644
--- a/hw/pci/pcie_port.c
+++ b/hw/pci/pcie_port.c
@@ -161,6 +161,51 @@ PCIDevice *pcie_find_port_by_pn(PCIBus *bus, uint8_t pn)
     return NULL;
 }
 
+/* Find first port in devfn number order */
+PCIDevice *pcie_find_port_first(PCIBus *bus)
+{
+    int devfn;
+
+    for (devfn = 0; devfn < ARRAY_SIZE(bus->devices); devfn++) {
+        PCIDevice *d = bus->devices[devfn];
+
+        if (!d || !pci_is_express(d) || !d->exp.exp_cap) {
+            continue;
+        }
+
+        if (object_dynamic_cast(OBJECT(d), TYPE_PCIE_PORT)) {
+            return d;
+        }
+    }
+
+    return NULL;
+}
+
+int pcie_count_ds_ports(PCIBus *bus)
+{
+    int dsp_count = 0;
+    int devfn;
+
+    for (devfn = 0; devfn < ARRAY_SIZE(bus->devices); devfn++) {
+        PCIDevice *d = bus->devices[devfn];
+
+        if (!d || !pci_is_express(d) || !d->exp.exp_cap) {
+            continue;
+        }
+        if (object_dynamic_cast(OBJECT(d), TYPE_PCIE_PORT)) {
+            dsp_count++;
+        }
+    }
+    return dsp_count;
+}
+
+static bool pcie_slot_is_hotpluggbale_bus(HotplugHandler *plug_handler,
+                                          BusState *bus)
+{
+    PCIESlot *s = PCIE_SLOT(bus->parent);
+    return s->hotplug;
+}
+
 static const TypeInfo pcie_port_type_info = {
     .name = TYPE_PCIE_PORT,
     .parent = TYPE_PCI_BRIDGE,
@@ -188,6 +233,7 @@ static void pcie_slot_class_init(ObjectClass *oc, void *data)
     hc->plug = pcie_cap_slot_plug_cb;
     hc->unplug = pcie_cap_slot_unplug_cb;
     hc->unplug_request = pcie_cap_slot_unplug_request_cb;
+    hc->is_hotpluggable_bus = pcie_slot_is_hotpluggbale_bus;
 }
 
 static const TypeInfo pcie_slot_type_info = {