[PULL 55/68] hw/acpi: Implement the SRAT GI affinity structure

[Michael S. Tsirkin]

From: Ankit Agrawal <ankita@nvidia.com>

ACPI spec provides a scheme to associate "Generic Initiators" [1]
(e.g. heterogeneous processors and accelerators, GPUs, and I/O devices with
integrated compute or DMA engines GPUs) with Proximity Domains. This is
achieved using Generic Initiator Affinity Structure in SRAT. During bootup,
Linux kernel parse the ACPI SRAT to determine the PXM ids and create a NUMA
node for each unique PXM ID encountered. Qemu currently do not implement
these structures while building SRAT.

Add GI structures while building VM ACPI SRAT. The association between
device and node are stored using acpi-generic-initiator object. Lookup
presence of all such objects and use them to build these structures.

The structure needs a PCI device handle [2] that consists of the device BDF.
The vfio-pci device corresponding to the acpi-generic-initiator object is
located to determine the BDF.

[1] ACPI Spec 6.3, Section 5.2.16.6
[2] ACPI Spec 6.3, Table 5.80

Cc: Jonathan Cameron <qemu-devel@nongnu.org>
Cc: Alex Williamson <alex.williamson@redhat.com>
Cc: Cedric Le Goater <clg@redhat.com>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Signed-off-by: Ankit Agrawal <ankita@nvidia.com>
Message-Id: <20240308145525.10886-3-ankita@nvidia.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 include/hw/acpi/acpi_generic_initiator.h | 25 ++++++++
 include/sysemu/numa.h                    |  1 +
 hw/acpi/acpi_generic_initiator.c         | 77 ++++++++++++++++++++++++
 hw/acpi/hmat.c                           |  2 +-
 hw/arm/virt-acpi-build.c                 |  3 +
 hw/core/numa.c                           |  3 +-
 6 files changed, 109 insertions(+), 2 deletions(-)

diff --git a/include/hw/acpi/acpi_generic_initiator.h 
b/include/hw/acpi/acpi_generic_initiator.h
index 16de1d3d80..a304bad73e 100644
--- a/include/hw/acpi/acpi_generic_initiator.h
+++ b/include/hw/acpi/acpi_generic_initiator.h
@@ -19,4 +19,29 @@ typedef struct AcpiGenericInitiator {
     uint16_t node;
 } AcpiGenericInitiator;
 
+/*
+ * ACPI 6.3:
+ * Table 5-81 Flags – Generic Initiator Affinity Structure
+ */
+typedef enum {
+    /*
+     * If clear, the OSPM ignores the contents of the Generic
+     * Initiator/Port Affinity Structure. This allows system firmware
+     * to populate the SRAT with a static number of structures, but only
+     * enable them as necessary.
+     */
+    GEN_AFFINITY_ENABLED = (1 << 0),
+} GenericAffinityFlags;
+
+/*
+ * ACPI 6.3:
+ * Table 5-80 Device Handle - PCI
+ */
+typedef struct PCIDeviceHandle {
+    uint16_t segment;
+    uint16_t bdf;
+} PCIDeviceHandle;
+
+void build_srat_generic_pci_initiator(GArray *table_data);
+
 #endif
diff --git a/include/sysemu/numa.h b/include/sysemu/numa.h
index 4173ef2afa..825cfe86bc 100644
--- a/include/sysemu/numa.h
+++ b/include/sysemu/numa.h
@@ -41,6 +41,7 @@ struct NodeInfo {
     struct HostMemoryBackend *node_memdev;
     bool present;
     bool has_cpu;
+    bool has_gi;
     uint8_t lb_info_provided;
     uint16_t initiator;
     uint8_t distance[MAX_NODES];
diff --git a/hw/acpi/acpi_generic_initiator.c b/hw/acpi/acpi_generic_initiator.c
index 130d6ae8c1..17b9a052f5 100644
--- a/hw/acpi/acpi_generic_initiator.c
+++ b/hw/acpi/acpi_generic_initiator.c
@@ -5,7 +5,9 @@
 
 #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 {
@@ -47,6 +49,7 @@ static void acpi_generic_initiator_set_node(Object *obj, 
Visitor *v,
                                             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)) {
@@ -60,6 +63,7 @@ static void acpi_generic_initiator_set_node(Object *obj, 
Visitor *v,
     }
 
     gi->node = value;
+    ms->numa_state->nodes[gi->node].has_gi = true;
 }
 
 static void acpi_generic_initiator_class_init(ObjectClass *oc, void *data)
@@ -69,3 +73,76 @@ static void acpi_generic_initiator_class_init(ObjectClass 
*oc, void *data)
     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..2242981e18 100644
--- a/hw/acpi/hmat.c
+++ b/hw/acpi/hmat.c
@@ -214,7 +214,7 @@ 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/arm/virt-acpi-build.c b/hw/arm/virt-acpi-build.c
index 6a1bde61ce..c3ccfef026 100644
--- a/hw/arm/virt-acpi-build.c
+++ b/hw/arm/virt-acpi-build.c
@@ -57,6 +57,7 @@
 #include "migration/vmstate.h"
 #include "hw/acpi/ghes.h"
 #include "hw/acpi/viot.h"
+#include "hw/acpi/acpi_generic_initiator.h"
 #include "hw/virtio/virtio-acpi.h"
 #include "target/arm/multiprocessing.h"
 
@@ -504,6 +505,8 @@ build_srat(GArray *table_data, BIOSLinker *linker, 
VirtMachineState *vms)
         }
     }
 
+    build_srat_generic_pci_initiator(table_data);
+
     if (ms->nvdimms_state->is_enabled) {
         nvdimm_build_srat(table_data);
     }
diff --git a/hw/core/numa.c b/hw/core/numa.c
index f08956ddb0..58a32f1564 100644
--- a/hw/core/numa.c
+++ b/hw/core/numa.c
@@ -229,7 +229,8 @@ void parse_numa_hmat_lb(NumaState *numa_state, 
NumaHmatLBOptions *node,
                    node->target, numa_state->num_nodes);
         return;
     }
-    if (!numa_info[node->initiator].has_cpu) {
+    if (!numa_info[node->initiator].has_cpu &&
+        !numa_info[node->initiator].has_gi) {
         error_setg(errp, "Invalid initiator=%d, it isn't an "
                    "initiator proximity domain", node->initiator);
         return;
-- 
MST