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

virtio,pc,pci: features, cleanups, fixes

more memslots support in libvhost-user
support PCIe Gen5/Gen6 link speeds in pcie
more traces in vdpa
network simulation devices support in vdpa
SMBIOS type 9 descriptor implementation
Bump max_cpus to 4096 vcpus in q35
aw-bits and granule options in VIRTIO-IOMMU
Support report NUMA nodes for device memory using GI in acpi
Beginning of shutdown event support in pvpanic

fixes, cleanups all over the place.

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

# -----BEGIN PGP SIGNATURE-----
#
# iQFDBAABCAAtFiEEXQn9CHHI+FuUyooNKB8NuNKNVGkFAmXw0TMPHG1zdEByZWRo
# YXQuY29tAAoJECgfDbjSjVRp8x4H+gLMoGwaGAX7gDGPgn2Ix4j/3kO77ZJ9X9k/
# 1KqZu/9eMS1j2Ei+vZqf05w7qRjxxhwDq3ilEXF/+UFqgAehLqpRRB8j5inqvzYt
# +jv0DbL11PBp/oFjWcytm5CbiVsvq8KlqCF29VNzc162XdtcduUOWagL96y8lJfZ
# uPrOoyeR7SMH9lp3LLLHWgu+9W4nOS03RroZ6Umj40y5B7yR0Rrppz8lMw5AoQtr
# 0gMRnFhYXeiW6CXdz+Tzcr7XfvkkYDi/j7ibiNSURLBfOpZa6Y8+kJGKxz5H1K1G
# 6ZY4PBcOpQzl+NMrktPHogczgJgOK10t+1i/R3bGZYw2Qn/93Eg=
# =C0UU
# -----END PGP SIGNATURE-----
# gpg: Signature made Tue 12 Mar 2024 22:03:31 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: (68 commits)
  docs/specs/pvpanic: document shutdown event
  hw/cxl: Fix missing reserved data in CXL Device DVSEC
  hmat acpi: Fix out of bounds access due to missing use of indirection
  hmat acpi: Do not add Memory Proximity Domain Attributes Structure targetting non existent memory.
  qemu-options.hx: Document the virtio-iommu-pci aw-bits option
  hw/arm/virt: Set virtio-iommu aw-bits default value to 48
  hw/i386/q35: Set virtio-iommu aw-bits default value to 39
  virtio-iommu: Add an option to define the input range width
  virtio-iommu: Trace domain range limits as unsigned int
  qemu-options.hx: Document the virtio-iommu-pci granule option
  virtio-iommu: Change the default granule to the host page size
  virtio-iommu: Add a granule property
  hw/i386/acpi-build: Add support for SRAT Generic Initiator structures
  hw/acpi: Implement the SRAT GI affinity structure
  qom: new object to associate device to NUMA node
  hw/i386/pc: Inline pc_cmos_init() into pc_cmos_init_late() and remove it
  hw/i386/pc: Set "normal" boot device order in pc_basic_device_init()
  hw/i386/pc: Avoid one use of the current_machine global
  hw/i386/pc: Remove "rtc_state" link again
  Revert "hw/i386/pc: Confine system flash handling to pc_sysfw"
  ...

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

# Conflicts:
#	hw/core/machine.c

3 files changed, 162 insertions, 2 deletions

diff --git a/hw/acpi/acpi_generic_initiator.c b/hw/acpi/acpi_generic_initiator.c
new file mode 100644
index 0000000000..17b9a052f5
--- /dev/null
+++ b/hw/acpi/acpi_generic_initiator.c
@@ -0,0 +1,148 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2024, NVIDIA CORPORATION & AFFILIATES. All rights reserved
+ */
+
+#include "qemu/osdep.h"
+#include "hw/acpi/acpi_generic_initiator.h"
+#include "hw/acpi/aml-build.h"
+#include "hw/boards.h"
+#include "hw/pci/pci_device.h"
+#include "qemu/error-report.h"
+
+typedef struct AcpiGenericInitiatorClass {
+    ObjectClass parent_class;
+} AcpiGenericInitiatorClass;
+
+OBJECT_DEFINE_TYPE_WITH_INTERFACES(AcpiGenericInitiator, acpi_generic_initiator,
+                   ACPI_GENERIC_INITIATOR, OBJECT,
+                   { TYPE_USER_CREATABLE },
+                   { NULL })
+
+OBJECT_DECLARE_SIMPLE_TYPE(AcpiGenericInitiator, ACPI_GENERIC_INITIATOR)
+
+static void acpi_generic_initiator_init(Object *obj)
+{
+    AcpiGenericInitiator *gi = ACPI_GENERIC_INITIATOR(obj);
+
+    gi->node = MAX_NODES;
+    gi->pci_dev = NULL;
+}
+
+static void acpi_generic_initiator_finalize(Object *obj)
+{
+    AcpiGenericInitiator *gi = ACPI_GENERIC_INITIATOR(obj);
+
+    g_free(gi->pci_dev);
+}
+
+static void acpi_generic_initiator_set_pci_device(Object *obj, const char *val,
+                                                  Error **errp)
+{
+    AcpiGenericInitiator *gi = ACPI_GENERIC_INITIATOR(obj);
+
+    gi->pci_dev = g_strdup(val);
+}
+
+static void acpi_generic_initiator_set_node(Object *obj, Visitor *v,
+                                            const char *name, void *opaque,
+                                            Error **errp)
+{
+    AcpiGenericInitiator *gi = ACPI_GENERIC_INITIATOR(obj);
+    MachineState *ms = MACHINE(qdev_get_machine());
+    uint32_t value;
+
+    if (!visit_type_uint32(v, name, &value, errp)) {
+        return;
+    }
+
+    if (value >= MAX_NODES) {
+        error_printf("%s: Invalid NUMA node specified\n",
+                     TYPE_ACPI_GENERIC_INITIATOR);
+        exit(1);
+    }
+
+    gi->node = value;
+    ms->numa_state->nodes[gi->node].has_gi = true;
+}
+
+static void acpi_generic_initiator_class_init(ObjectClass *oc, void *data)
+{
+    object_class_property_add_str(oc, "pci-dev", NULL,
+        acpi_generic_initiator_set_pci_device);
+    object_class_property_add(oc, "node", "int", NULL,
+        acpi_generic_initiator_set_node, NULL, NULL);
+}
+
+/*
+ * ACPI 6.3:
+ * Table 5-78 Generic Initiator Affinity Structure
+ */
+static void
+build_srat_generic_pci_initiator_affinity(GArray *table_data, int node,
+                                          PCIDeviceHandle *handle)
+{
+    uint8_t index;
+
+    build_append_int_noprefix(table_data, 5, 1);  /* Type */
+    build_append_int_noprefix(table_data, 32, 1); /* Length */
+    build_append_int_noprefix(table_data, 0, 1);  /* Reserved */
+    build_append_int_noprefix(table_data, 1, 1);  /* Device Handle Type: PCI */
+    build_append_int_noprefix(table_data, node, 4);  /* Proximity Domain */
+
+    /* Device Handle - PCI */
+    build_append_int_noprefix(table_data, handle->segment, 2);
+    build_append_int_noprefix(table_data, handle->bdf, 2);
+    for (index = 0; index < 12; index++) {
+        build_append_int_noprefix(table_data, 0, 1);
+    }
+
+    build_append_int_noprefix(table_data, GEN_AFFINITY_ENABLED, 4); /* Flags */
+    build_append_int_noprefix(table_data, 0, 4);     /* Reserved */
+}
+
+static int build_all_acpi_generic_initiators(Object *obj, void *opaque)
+{
+    MachineState *ms = MACHINE(qdev_get_machine());
+    AcpiGenericInitiator *gi;
+    GArray *table_data = opaque;
+    PCIDeviceHandle dev_handle;
+    PCIDevice *pci_dev;
+    Object *o;
+
+    if (!object_dynamic_cast(obj, TYPE_ACPI_GENERIC_INITIATOR)) {
+        return 0;
+    }
+
+    gi = ACPI_GENERIC_INITIATOR(obj);
+    if (gi->node >= ms->numa_state->num_nodes) {
+        error_printf("%s: Specified node %d is invalid.\n",
+                     TYPE_ACPI_GENERIC_INITIATOR, gi->node);
+        exit(1);
+    }
+
+    o = object_resolve_path_type(gi->pci_dev, TYPE_PCI_DEVICE, NULL);
+    if (!o) {
+        error_printf("%s: Specified device must be a PCI device.\n",
+                     TYPE_ACPI_GENERIC_INITIATOR);
+        exit(1);
+    }
+
+    pci_dev = PCI_DEVICE(o);
+
+    dev_handle.segment = 0;
+    dev_handle.bdf = PCI_BUILD_BDF(pci_bus_num(pci_get_bus(pci_dev)),
+                                               pci_dev->devfn);
+
+    build_srat_generic_pci_initiator_affinity(table_data,
+                                              gi->node, &dev_handle);
+
+    return 0;
+}
+
+void build_srat_generic_pci_initiator(GArray *table_data)
+{
+    object_child_foreach_recursive(object_get_root(),
+                                   build_all_acpi_generic_initiators,
+                                   table_data);
+}
diff --git a/hw/acpi/hmat.c b/hw/acpi/hmat.c
index 3042d223c8..9b1662b6b8 100644
--- a/hw/acpi/hmat.c
+++ b/hw/acpi/hmat.c
@@ -78,6 +78,7 @@ static void build_hmat_lb(GArray *table_data, HMAT_LB_Info *hmat_lb,
                           uint32_t *initiator_list)
 {
     int i, index;
+    uint32_t initiator_to_index[MAX_NODES] = {};
     HMAT_LB_Data *lb_data;
     uint16_t *entry_list;
     uint32_t base;
@@ -121,6 +122,8 @@ static void build_hmat_lb(GArray *table_data, HMAT_LB_Info *hmat_lb,
     /* Initiator Proximity Domain List */
     for (i = 0; i < num_initiator; i++) {
         build_append_int_noprefix(table_data, initiator_list[i], 4);
+        /* Reverse mapping for array possitions */
+        initiator_to_index[initiator_list[i]] = i;
     }
 
     /* Target Proximity Domain List */
@@ -132,7 +135,8 @@ static void build_hmat_lb(GArray *table_data, HMAT_LB_Info *hmat_lb,
     entry_list = g_new0(uint16_t, num_initiator * num_target);
     for (i = 0; i < hmat_lb->list->len; i++) {
         lb_data = &g_array_index(hmat_lb->list, HMAT_LB_Data, i);
-        index = lb_data->initiator * num_target + lb_data->target;
+        index = initiator_to_index[lb_data->initiator] * num_target +
+            lb_data->target;
 
         entry_list[index] = (uint16_t)(lb_data->data / hmat_lb->base);
     }
@@ -204,6 +208,13 @@ static void hmat_build_table_structs(GArray *table_data, NumaState *numa_state)
     build_append_int_noprefix(table_data, 0, 4); /* Reserved */
 
     for (i = 0; i < numa_state->num_nodes; i++) {
+        /*
+         * Linux rejects whole HMAT table if a node with no memory
+         * has one of these structures listing it as a target.
+         */
+        if (!numa_state->nodes[i].node_mem) {
+            continue;
+        }
         flags = 0;
 
         if (numa_state->nodes[i].initiator < MAX_NODES) {
@@ -214,7 +225,7 @@ static void hmat_build_table_structs(GArray *table_data, NumaState *numa_state)
     }
 
     for (i = 0; i < numa_state->num_nodes; i++) {
-        if (numa_state->nodes[i].has_cpu) {
+        if (numa_state->nodes[i].has_cpu || numa_state->nodes[i].has_gi) {
             initiator_list[num_initiator++] = i;
         }
     }
diff --git a/hw/acpi/meson.build b/hw/acpi/meson.build
index 5441c9b1e4..fa5c07db90 100644
--- a/hw/acpi/meson.build
+++ b/hw/acpi/meson.build
@@ -1,5 +1,6 @@
 acpi_ss = ss.source_set()
 acpi_ss.add(files(
+  'acpi_generic_initiator.c',
   'acpi_interface.c',
   'aml-build.c',
   'bios-linker-loader.c',