Merge remote-tracking branch 'remotes/rth/tags/pull-arm-20211021' into staging

Introduce cpu topology support
Generate DBG2 table
Switch to ssize_t for elf loader return type
Fixed sbsa cpu type error message typo
Only initialize required submodules for edk2
Dont create device-tree node for empty NUMA node

# gpg: Signature made Thu 21 Oct 2021 08:22:32 AM PDT
# gpg:                using RSA key 7A481E78868B4DB6A85A05C064DF38E8AF7E215F
# gpg:                issuer "richard.henderson@linaro.org"
# gpg: Good signature from "Richard Henderson <richard.henderson@linaro.org>" [ultimate]

* remotes/rth/tags/pull-arm-20211021:
  tests/data/acpi/virt: Update the empty expected file for PPTT
  hw/arm/virt-acpi-build: Generate PPTT table
  tests/data/acpi/virt: Add an empty expected file for PPTT
  hw/acpi/aml-build: Add PPTT table
  hw/acpi/aml-build: Add Processor hierarchy node structure
  hw/arm/virt: Add cpu-map to device tree
  device_tree: Add qemu_fdt_add_path
  hw/arm/virt: Only describe cpu topology since virt-6.2
  bios-tables-test: Generate reference table for virt/DBG2
  hw/arm/virt_acpi_build: Generate DBG2 table
  tests/acpi: Add void table for virt/DBG2 bios-tables-test
  hw/elf_ops.h: switch to ssize_t for elf loader return type
  hw/arm/sbsa-ref: Fixed cpu type error message typo.
  roms/edk2: Only initialize required submodules
  roms/edk2: Only init brotli submodule to build BaseTools
  hw/arm/virt: Don't create device-tree node for empty NUMA node
  tests/acpi: Generate reference blob for IORT rev E.b
  hw/arm/virt-acpi-build: IORT upgrade up to revision E.b
  tests/acpi: Get prepared for IORT E.b revision upgrade

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>

22 files changed, 403 insertions, 109 deletions

diff --git a/.gitlab-ci.d/edk2.yml b/.gitlab-ci.d/edk2.yml
index 62497ba47f..13d0f8b019 100644
--- a/.gitlab-ci.d/edk2.yml
+++ b/.gitlab-ci.d/edk2.yml
@@ -50,7 +50,11 @@ build-edk2:
    GIT_DEPTH: 3
  script: # Clone the required submodules and build EDK2
  - git submodule update --init roms/edk2
- - git -C roms/edk2 submodule update --init
+ - git -C roms/edk2 submodule update --init --
+     ArmPkg/Library/ArmSoftFloatLib/berkeley-softfloat-3
+     BaseTools/Source/C/BrotliCompress/brotli
+     CryptoPkg/Library/OpensslLib/openssl
+     MdeModulePkg/Library/BrotliCustomDecompressLib/brotli
  - export JOBS=$(($(getconf _NPROCESSORS_ONLN) + 1))
  - echo "=== Using ${JOBS} simultaneous jobs ==="
  - make -j${JOBS} -C roms efi 2>&1 1>edk2-stdout.log | tee -a edk2-stderr.log >&2
diff --git a/hw/acpi/aml-build.c b/hw/acpi/aml-build.c
index 76af0ebaf9..b3b3310df3 100644
--- a/hw/acpi/aml-build.c
+++ b/hw/acpi/aml-build.c
@@ -1964,6 +1964,95 @@ void build_slit(GArray *table_data, BIOSLinker *linker, MachineState *ms,
     acpi_table_end(linker, &table);
 }
 
+/*
+ * ACPI spec, Revision 6.3
+ * 5.2.29.1 Processor hierarchy node structure (Type 0)
+ */
+static void build_processor_hierarchy_node(GArray *tbl, uint32_t flags,
+                                           uint32_t parent, uint32_t id,
+                                           uint32_t *priv_rsrc,
+                                           uint32_t priv_num)
+{
+    int i;
+
+    build_append_byte(tbl, 0);                 /* Type 0 - processor */
+    build_append_byte(tbl, 20 + priv_num * 4); /* Length */
+    build_append_int_noprefix(tbl, 0, 2);      /* Reserved */
+    build_append_int_noprefix(tbl, flags, 4);  /* Flags */
+    build_append_int_noprefix(tbl, parent, 4); /* Parent */
+    build_append_int_noprefix(tbl, id, 4);     /* ACPI Processor ID */
+
+    /* Number of private resources */
+    build_append_int_noprefix(tbl, priv_num, 4);
+
+    /* Private resources[N] */
+    if (priv_num > 0) {
+        assert(priv_rsrc);
+        for (i = 0; i < priv_num; i++) {
+            build_append_int_noprefix(tbl, priv_rsrc[i], 4);
+        }
+    }
+}
+
+/*
+ * ACPI spec, Revision 6.3
+ * 5.2.29 Processor Properties Topology Table (PPTT)
+ */
+void build_pptt(GArray *table_data, BIOSLinker *linker, MachineState *ms,
+                const char *oem_id, const char *oem_table_id)
+{
+    int pptt_start = table_data->len;
+    int uid = 0;
+    int socket;
+    AcpiTable table = { .sig = "PPTT", .rev = 2,
+                        .oem_id = oem_id, .oem_table_id = oem_table_id };
+
+    acpi_table_begin(&table, table_data);
+
+    for (socket = 0; socket < ms->smp.sockets; socket++) {
+        uint32_t socket_offset = table_data->len - pptt_start;
+        int core;
+
+        build_processor_hierarchy_node(
+            table_data,
+            /*
+             * Physical package - represents the boundary
+             * of a physical package
+             */
+            (1 << 0),
+            0, socket, NULL, 0);
+
+        for (core = 0; core < ms->smp.cores; core++) {
+            uint32_t core_offset = table_data->len - pptt_start;
+            int thread;
+
+            if (ms->smp.threads > 1) {
+                build_processor_hierarchy_node(
+                    table_data,
+                    (0 << 0), /* not a physical package */
+                    socket_offset, core, NULL, 0);
+
+                for (thread = 0; thread < ms->smp.threads; thread++) {
+                    build_processor_hierarchy_node(
+                        table_data,
+                        (1 << 1) | /* ACPI Processor ID valid */
+                        (1 << 2) | /* Processor is a Thread */
+                        (1 << 3),  /* Node is a Leaf */
+                        core_offset, uid++, NULL, 0);
+                }
+            } else {
+                build_processor_hierarchy_node(
+                    table_data,
+                    (1 << 1) | /* ACPI Processor ID valid */
+                    (1 << 3),  /* Node is a Leaf */
+                    socket_offset, uid++, NULL, 0);
+            }
+        }
+    }
+
+    acpi_table_end(linker, &table);
+}
+
 /* build rev1/rev3/rev5.1 FADT */
 void build_fadt(GArray *tbl, BIOSLinker *linker, const AcpiFadtData *f,
                 const char *oem_id, const char *oem_table_id)
diff --git a/hw/arm/boot.c b/hw/arm/boot.c
index 57efb61ee4..74ad397b1f 100644
--- a/hw/arm/boot.c
+++ b/hw/arm/boot.c
@@ -599,10 +599,23 @@ int arm_load_dtb(hwaddr addr, const struct arm_boot_info *binfo,
     }
     g_strfreev(node_path);
 
+    /*
+     * We drop all the memory nodes which correspond to empty NUMA nodes
+     * from the device tree, because the Linux NUMA binding document
+     * states they should not be generated. Linux will get the NUMA node
+     * IDs of the empty NUMA nodes from the distance map if they are needed.
+     * This means QEMU users may be obliged to provide command lines which
+     * configure distance maps when the empty NUMA node IDs are needed and
+     * Linux's default distance map isn't sufficient.
+     */
     if (ms->numa_state != NULL && ms->numa_state->num_nodes > 0) {
         mem_base = binfo->loader_start;
         for (i = 0; i < ms->numa_state->num_nodes; i++) {
             mem_len = ms->numa_state->nodes[i].node_mem;
+            if (!mem_len) {
+                continue;
+            }
+
             rc = fdt_add_memory_node(fdt, acells, mem_base,
                                      scells, mem_len, i);
             if (rc < 0) {
diff --git a/hw/arm/sbsa-ref.c b/hw/arm/sbsa-ref.c
index 509c5f09b4..358714bd3e 100644
--- a/hw/arm/sbsa-ref.c
+++ b/hw/arm/sbsa-ref.c
@@ -670,7 +670,7 @@ static void sbsa_ref_init(MachineState *machine)
     int n, sbsa_max_cpus;
 
     if (!cpu_type_valid(machine->cpu_type)) {
-        error_report("mach-virt: CPU type %s not supported", machine->cpu_type);
+        error_report("sbsa-ref: CPU type %s not supported", machine->cpu_type);
         exit(1);
     }
 
diff --git a/hw/arm/virt-acpi-build.c b/hw/arm/virt-acpi-build.c
index 6cec97352b..674f902652 100644
--- a/hw/arm/virt-acpi-build.c
+++ b/hw/arm/virt-acpi-build.c
@@ -241,19 +241,20 @@ static void acpi_dsdt_add_tpm(Aml *scope, VirtMachineState *vms)
 #endif
 
 #define ID_MAPPING_ENTRY_SIZE 20
-#define SMMU_V3_ENTRY_SIZE 60
-#define ROOT_COMPLEX_ENTRY_SIZE 32
+#define SMMU_V3_ENTRY_SIZE 68
+#define ROOT_COMPLEX_ENTRY_SIZE 36
 #define IORT_NODE_OFFSET 48
 
 static void build_iort_id_mapping(GArray *table_data, uint32_t input_base,
                                   uint32_t id_count, uint32_t out_ref)
 {
-    /* Identity RID mapping covering the whole input RID range */
+    /* Table 4 ID mapping format */
     build_append_int_noprefix(table_data, input_base, 4); /* Input base */
     build_append_int_noprefix(table_data, id_count, 4); /* Number of IDs */
     build_append_int_noprefix(table_data, input_base, 4); /* Output base */
     build_append_int_noprefix(table_data, out_ref, 4); /* Output Reference */
-    build_append_int_noprefix(table_data, 0, 4); /* Flags */
+    /* Flags */
+    build_append_int_noprefix(table_data, 0 /* Single mapping (disabled) */, 4);
 }
 
 struct AcpiIortIdMapping {
@@ -298,7 +299,7 @@ static int iort_idmap_compare(gconstpointer a, gconstpointer b)
 /*
  * Input Output Remapping Table (IORT)
  * Conforms to "IO Remapping Table System Software on ARM Platforms",
- * Document number: ARM DEN 0049B, October 2015
+ * Document number: ARM DEN 0049E.b, Feb 2021
  */
 static void
 build_iort(GArray *table_data, BIOSLinker *linker, VirtMachineState *vms)
@@ -307,10 +308,11 @@ build_iort(GArray *table_data, BIOSLinker *linker, VirtMachineState *vms)
     const uint32_t iort_node_offset = IORT_NODE_OFFSET;
     size_t node_size, smmu_offset = 0;
     AcpiIortIdMapping *idmap;
+    uint32_t id = 0;
     GArray *smmu_idmaps = g_array_new(false, true, sizeof(AcpiIortIdMapping));
     GArray *its_idmaps = g_array_new(false, true, sizeof(AcpiIortIdMapping));
 
-    AcpiTable table = { .sig = "IORT", .rev = 0, .oem_id = vms->oem_id,
+    AcpiTable table = { .sig = "IORT", .rev = 3, .oem_id = vms->oem_id,
                         .oem_table_id = vms->oem_table_id };
     /* Table 2 The IORT */
     acpi_table_begin(&table, table_data);
@@ -358,12 +360,12 @@ build_iort(GArray *table_data, BIOSLinker *linker, VirtMachineState *vms)
     build_append_int_noprefix(table_data, IORT_NODE_OFFSET, 4);
     build_append_int_noprefix(table_data, 0, 4); /* Reserved */
 
-    /* 3.1.1.3 ITS group node */
+    /* Table 12 ITS Group Format */
     build_append_int_noprefix(table_data, 0 /* ITS Group */, 1); /* Type */
     node_size =  20 /* fixed header size */ + 4 /* 1 GIC ITS Identifier */;
     build_append_int_noprefix(table_data, node_size, 2); /* Length */
-    build_append_int_noprefix(table_data, 0, 1); /* Revision */
-    build_append_int_noprefix(table_data, 0, 4); /* Reserved */
+    build_append_int_noprefix(table_data, 1, 1); /* Revision */
+    build_append_int_noprefix(table_data, id++, 4); /* Identifier */
     build_append_int_noprefix(table_data, 0, 4); /* Number of ID mappings */
     build_append_int_noprefix(table_data, 0, 4); /* Reference to ID Array */
     build_append_int_noprefix(table_data, 1, 4); /* Number of ITSs */
@@ -374,19 +376,19 @@ build_iort(GArray *table_data, BIOSLinker *linker, VirtMachineState *vms)
         int irq =  vms->irqmap[VIRT_SMMU] + ARM_SPI_BASE;
 
         smmu_offset = table_data->len - table.table_offset;
-        /* 3.1.1.2 SMMUv3 */
+        /* Table 9 SMMUv3 Format */
         build_append_int_noprefix(table_data, 4 /* SMMUv3 */, 1); /* Type */
         node_size =  SMMU_V3_ENTRY_SIZE + ID_MAPPING_ENTRY_SIZE;
         build_append_int_noprefix(table_data, node_size, 2); /* Length */
-        build_append_int_noprefix(table_data, 0, 1); /* Revision */
-        build_append_int_noprefix(table_data, 0, 4); /* Reserved */
+        build_append_int_noprefix(table_data, 4, 1); /* Revision */
+        build_append_int_noprefix(table_data, id++, 4); /* Identifier */
         build_append_int_noprefix(table_data, 1, 4); /* Number of ID mappings */
         /* Reference to ID Array */
         build_append_int_noprefix(table_data, SMMU_V3_ENTRY_SIZE, 4);
         /* Base address */
         build_append_int_noprefix(table_data, vms->memmap[VIRT_SMMU].base, 8);
         /* Flags */
-        build_append_int_noprefix(table_data, 1 /* COHACC OverrideNote */, 4);
+        build_append_int_noprefix(table_data, 1 /* COHACC Override */, 4);
         build_append_int_noprefix(table_data, 0, 4); /* Reserved */
         build_append_int_noprefix(table_data, 0, 8); /* VATOS address */
         /* Model */
@@ -395,35 +397,43 @@ build_iort(GArray *table_data, BIOSLinker *linker, VirtMachineState *vms)
         build_append_int_noprefix(table_data, irq + 1, 4); /* PRI */
         build_append_int_noprefix(table_data, irq + 3, 4); /* GERR */
         build_append_int_noprefix(table_data, irq + 2, 4); /* Sync */
+        build_append_int_noprefix(table_data, 0, 4); /* Proximity domain */
+        /* DeviceID mapping index (ignored since interrupts are GSIV based) */
+        build_append_int_noprefix(table_data, 0, 4);
 
         /* output IORT node is the ITS group node (the first node) */
         build_iort_id_mapping(table_data, 0, 0xFFFF, IORT_NODE_OFFSET);
     }
 
-    /* Table 16 Root Complex Node */
+    /* Table 17 Root Complex Node */
     build_append_int_noprefix(table_data, 2 /* Root complex */, 1); /* Type */
     node_size =  ROOT_COMPLEX_ENTRY_SIZE +
                  ID_MAPPING_ENTRY_SIZE * rc_mapping_count;
     build_append_int_noprefix(table_data, node_size, 2); /* Length */
-    build_append_int_noprefix(table_data, 0, 1); /* Revision */
-    build_append_int_noprefix(table_data, 0, 4); /* Reserved */
+    build_append_int_noprefix(table_data, 3, 1); /* Revision */
+    build_append_int_noprefix(table_data, id++, 4); /* Identifier */
     /* Number of ID mappings */
     build_append_int_noprefix(table_data, rc_mapping_count, 4);
     /* Reference to ID Array */
     build_append_int_noprefix(table_data, ROOT_COMPLEX_ENTRY_SIZE, 4);
 
-    /* Table 13 Memory access properties */
+    /* Table 14 Memory access properties */
     /* CCA: Cache Coherent Attribute */
     build_append_int_noprefix(table_data, 1 /* fully coherent */, 4);
     build_append_int_noprefix(table_data, 0, 1); /* AH: Note Allocation Hints */
     build_append_int_noprefix(table_data, 0, 2); /* Reserved */
-    /* MAF: Note Memory Access Flags */
-    build_append_int_noprefix(table_data, 0x3 /* CCA = CPM = DCAS = 1 */, 1);
+    /* Table 15 Memory Access Flags */
+    build_append_int_noprefix(table_data, 0x3 /* CCA = CPM = DACS = 1 */, 1);
 
     build_append_int_noprefix(table_data, 0, 4); /* ATS Attribute */
     /* MCFG pci_segment */
     build_append_int_noprefix(table_data, 0, 4); /* PCI Segment number */
 
+    /* Memory address size limit */
+    build_append_int_noprefix(table_data, 64, 1);
+
+    build_append_int_noprefix(table_data, 0, 3); /* Reserved */
+
     /* Output Reference */
     if (vms->iommu == VIRT_IOMMU_SMMUV3) {
         AcpiIortIdMapping *range;
@@ -616,6 +626,64 @@ build_gtdt(GArray *table_data, BIOSLinker *linker, VirtMachineState *vms)
     acpi_table_end(linker, &table);
 }
 
+/* Debug Port Table 2 (DBG2) */
+static void
+build_dbg2(GArray *table_data, BIOSLinker *linker, VirtMachineState *vms)
+{
+    AcpiTable table = { .sig = "DBG2", .rev = 0, .oem_id = vms->oem_id,
+                        .oem_table_id = vms->oem_table_id };
+    int dbg2devicelength;
+    const char name[] = "COM0";
+    const int namespace_length = sizeof(name);
+
+    acpi_table_begin(&table, table_data);
+
+    dbg2devicelength = 22 + /* BaseAddressRegister[] offset */
+                       12 + /* BaseAddressRegister[] */
+                       4 + /* AddressSize[] */
+                       namespace_length /* NamespaceString[] */;
+
+    /* OffsetDbgDeviceInfo */
+    build_append_int_noprefix(table_data, 44, 4);
+    /* NumberDbgDeviceInfo */
+    build_append_int_noprefix(table_data, 1, 4);
+
+    /* Table 2. Debug Device Information structure format */
+    build_append_int_noprefix(table_data, 0, 1); /* Revision */
+    build_append_int_noprefix(table_data, dbg2devicelength, 2); /* Length */
+    /* NumberofGenericAddressRegisters */
+    build_append_int_noprefix(table_data, 1, 1);
+    /* NameSpaceStringLength */
+    build_append_int_noprefix(table_data, namespace_length, 2);
+    build_append_int_noprefix(table_data, 38, 2); /* NameSpaceStringOffset */
+    build_append_int_noprefix(table_data, 0, 2); /* OemDataLength */
+    /* OemDataOffset (0 means no OEM data) */
+    build_append_int_noprefix(table_data, 0, 2);
+
+    /* Port Type */
+    build_append_int_noprefix(table_data, 0x8000 /* Serial */, 2);
+    /* Port Subtype */
+    build_append_int_noprefix(table_data, 0x3 /* ARM PL011 UART */, 2);
+    build_append_int_noprefix(table_data, 0, 2); /* Reserved */
+    /* BaseAddressRegisterOffset */
+    build_append_int_noprefix(table_data, 22, 2);
+    /* AddressSizeOffset */
+    build_append_int_noprefix(table_data, 34, 2);
+
+    /* BaseAddressRegister[] */
+    build_append_gas(table_data, AML_AS_SYSTEM_MEMORY, 8, 0, 1,
+                     vms->memmap[VIRT_UART].base);
+
+    /* AddressSize[] */
+    build_append_int_noprefix(table_data,
+                              vms->memmap[VIRT_UART].size, 4);
+
+    /* NamespaceString[] */
+    g_array_append_vals(table_data, name, namespace_length);
+
+    acpi_table_end(linker, &table);
+};
+
 /*
  * ACPI spec, Revision 5.1 Errata A
  * 5.2.12 Multiple APIC Description Table (MADT)
@@ -875,13 +943,19 @@ void virt_acpi_build(VirtMachineState *vms, AcpiBuildTables *tables)
     dsdt = tables_blob->len;
     build_dsdt(tables_blob, tables->linker, vms);
 
-    /* FADT MADT GTDT MCFG SPCR pointed to by RSDT */
+    /* FADT MADT PPTT GTDT MCFG SPCR DBG2 pointed to by RSDT */
     acpi_add_table(table_offsets, tables_blob);
     build_fadt_rev5(tables_blob, tables->linker, vms, dsdt);
 
     acpi_add_table(table_offsets, tables_blob);
     build_madt(tables_blob, tables->linker, vms);
 
+    if (!vmc->no_cpu_topology) {
+        acpi_add_table(table_offsets, tables_blob);
+        build_pptt(tables_blob, tables->linker, ms,
+                   vms->oem_id, vms->oem_table_id);
+    }
+
     acpi_add_table(table_offsets, tables_blob);
     build_gtdt(tables_blob, tables->linker, vms);
 
@@ -898,6 +972,9 @@ void virt_acpi_build(VirtMachineState *vms, AcpiBuildTables *tables)
     acpi_add_table(table_offsets, tables_blob);
     build_spcr(tables_blob, tables->linker, vms);
 
+    acpi_add_table(table_offsets, tables_blob);
+    build_dbg2(tables_blob, tables->linker, vms);
+
     if (vms->ras) {
         build_ghes_error_table(tables->hardware_errors, tables->linker);
         acpi_add_table(table_offsets, tables_blob);
diff --git a/hw/arm/virt.c b/hw/arm/virt.c
index 4160d49688..ca433adb5b 100644
--- a/hw/arm/virt.c
+++ b/hw/arm/virt.c
@@ -351,20 +351,21 @@ static void fdt_add_cpu_nodes(const VirtMachineState *vms)
     int cpu;
     int addr_cells = 1;
     const MachineState *ms = MACHINE(vms);
+    const VirtMachineClass *vmc = VIRT_MACHINE_GET_CLASS(vms);
     int smp_cpus = ms->smp.cpus;
 
     /*
-     * From Documentation/devicetree/bindings/arm/cpus.txt
-     *  On ARM v8 64-bit systems value should be set to 2,
-     *  that corresponds to the MPIDR_EL1 register size.
-     *  If MPIDR_EL1[63:32] value is equal to 0 on all CPUs
-     *  in the system, #address-cells can be set to 1, since
-     *  MPIDR_EL1[63:32] bits are not used for CPUs
-     *  identification.
+     * See Linux Documentation/devicetree/bindings/arm/cpus.yaml
+     * On ARM v8 64-bit systems value should be set to 2,
+     * that corresponds to the MPIDR_EL1 register size.
+     * If MPIDR_EL1[63:32] value is equal to 0 on all CPUs
+     * in the system, #address-cells can be set to 1, since
+     * MPIDR_EL1[63:32] bits are not used for CPUs
+     * identification.
      *
-     *  Here we actually don't know whether our system is 32- or 64-bit one.
-     *  The simplest way to go is to examine affinity IDs of all our CPUs. If
-     *  at least one of them has Aff3 populated, we set #address-cells to 2.
+     * Here we actually don't know whether our system is 32- or 64-bit one.
+     * The simplest way to go is to examine affinity IDs of all our CPUs. If
+     * at least one of them has Aff3 populated, we set #address-cells to 2.
      */
     for (cpu = 0; cpu < smp_cpus; cpu++) {
         ARMCPU *armcpu = ARM_CPU(qemu_get_cpu(cpu));
@@ -407,8 +408,57 @@ static void fdt_add_cpu_nodes(const VirtMachineState *vms)
                 ms->possible_cpus->cpus[cs->cpu_index].props.node_id);
         }
 
+        if (!vmc->no_cpu_topology) {
+            qemu_fdt_setprop_cell(ms->fdt, nodename, "phandle",
+                                  qemu_fdt_alloc_phandle(ms->fdt));
+        }
+
         g_free(nodename);
     }
+
+    if (!vmc->no_cpu_topology) {
+        /*
+         * Add vCPU topology description through fdt node cpu-map.
+         *
+         * See Linux Documentation/devicetree/bindings/cpu/cpu-topology.txt
+         * In a SMP system, the hierarchy of CPUs can be defined through
+         * four entities that are used to describe the layout of CPUs in
+         * the system: socket/cluster/core/thread.
+         *
+         * A socket node represents the boundary of system physical package
+         * and its child nodes must be one or more cluster nodes. A system
+         * can contain several layers of clustering within a single physical
+         * package and cluster nodes can be contained in parent cluster nodes.
+         *
+         * Given that cluster is not yet supported in the vCPU topology,
+         * we currently generate one cluster node within each socket node
+         * by default.
+         */
+        qemu_fdt_add_subnode(ms->fdt, "/cpus/cpu-map");
+
+        for (cpu = smp_cpus - 1; cpu >= 0; cpu--) {
+            char *cpu_path = g_strdup_printf("/cpus/cpu@%d", cpu);
+            char *map_path;
+
+            if (ms->smp.threads > 1) {
+                map_path = g_strdup_printf(
+                    "/cpus/cpu-map/socket%d/cluster0/core%d/thread%d",
+                    cpu / (ms->smp.cores * ms->smp.threads),
+                    (cpu / ms->smp.threads) % ms->smp.cores,
+                    cpu % ms->smp.threads);
+            } else {
+                map_path = g_strdup_printf(
+                    "/cpus/cpu-map/socket%d/cluster0/core%d",
+                    cpu / ms->smp.cores,
+                    cpu % ms->smp.cores);
+            }
+            qemu_fdt_add_path(ms->fdt, map_path);
+            qemu_fdt_setprop_phandle(ms->fdt, map_path, "cpu", cpu_path);
+
+            g_free(map_path);
+            g_free(cpu_path);
+        }
+    }
 }
 
 static void fdt_add_its_gic_node(VirtMachineState *vms)
@@ -2816,6 +2866,7 @@ static void virt_machine_6_1_options(MachineClass *mc)
     virt_machine_6_2_options(mc);
     compat_props_add(mc->compat_props, hw_compat_6_1, hw_compat_6_1_len);
     mc->smp_props.prefer_sockets = true;
+    vmc->no_cpu_topology = true;
 
     /* qemu ITS was introduced with 6.2 */
     vmc->no_tcg_its = true;
diff --git a/hw/core/loader.c b/hw/core/loader.c
index c623318b73..c7f97fdce8 100644
--- a/hw/core/loader.c
+++ b/hw/core/loader.c
@@ -326,7 +326,7 @@ static void *load_at(int fd, off_t offset, size_t size)
 #define SZ		64
 #include "hw/elf_ops.h"
 
-const char *load_elf_strerror(int error)
+const char *load_elf_strerror(ssize_t error)
 {
     switch (error) {
     case 0:
@@ -402,12 +402,12 @@ fail:
 }
 
 /* return < 0 if error, otherwise the number of bytes loaded in memory */
-int load_elf(const char *filename,
-             uint64_t (*elf_note_fn)(void *, void *, bool),
-             uint64_t (*translate_fn)(void *, uint64_t),
-             void *translate_opaque, uint64_t *pentry, uint64_t *lowaddr,
-             uint64_t *highaddr, uint32_t *pflags, int big_endian,
-             int elf_machine, int clear_lsb, int data_swab)
+ssize_t load_elf(const char *filename,
+                 uint64_t (*elf_note_fn)(void *, void *, bool),
+                 uint64_t (*translate_fn)(void *, uint64_t),
+                 void *translate_opaque, uint64_t *pentry, uint64_t *lowaddr,
+                 uint64_t *highaddr, uint32_t *pflags, int big_endian,
+                 int elf_machine, int clear_lsb, int data_swab)
 {
     return load_elf_as(filename, elf_note_fn, translate_fn, translate_opaque,
                        pentry, lowaddr, highaddr, pflags, big_endian,
@@ -415,12 +415,13 @@ int load_elf(const char *filename,
 }
 
 /* return < 0 if error, otherwise the number of bytes loaded in memory */
-int load_elf_as(const char *filename,
-                uint64_t (*elf_note_fn)(void *, void *, bool),
-                uint64_t (*translate_fn)(void *, uint64_t),
-                void *translate_opaque, uint64_t *pentry, uint64_t *lowaddr,
-                uint64_t *highaddr, uint32_t *pflags, int big_endian,
-                int elf_machine, int clear_lsb, int data_swab, AddressSpace *as)
+ssize_t load_elf_as(const char *filename,
+                    uint64_t (*elf_note_fn)(void *, void *, bool),
+                    uint64_t (*translate_fn)(void *, uint64_t),
+                    void *translate_opaque, uint64_t *pentry, uint64_t *lowaddr,
+                    uint64_t *highaddr, uint32_t *pflags, int big_endian,
+                    int elf_machine, int clear_lsb, int data_swab,
+                    AddressSpace *as)
 {
     return load_elf_ram(filename, elf_note_fn, translate_fn, translate_opaque,
                         pentry, lowaddr, highaddr, pflags, big_endian,
@@ -428,13 +429,13 @@ int load_elf_as(const char *filename,
 }
 
 /* return < 0 if error, otherwise the number of bytes loaded in memory */
-int load_elf_ram(const char *filename,
-                 uint64_t (*elf_note_fn)(void *, void *, bool),
-                 uint64_t (*translate_fn)(void *, uint64_t),
-                 void *translate_opaque, uint64_t *pentry, uint64_t *lowaddr,
-                 uint64_t *highaddr, uint32_t *pflags, int big_endian,
-                 int elf_machine, int clear_lsb, int data_swab,
-                 AddressSpace *as, bool load_rom)
+ssize_t load_elf_ram(const char *filename,
+                     uint64_t (*elf_note_fn)(void *, void *, bool),
+                     uint64_t (*translate_fn)(void *, uint64_t),
+                     void *translate_opaque, uint64_t *pentry,
+                     uint64_t *lowaddr, uint64_t *highaddr, uint32_t *pflags,
+                     int big_endian, int elf_machine, int clear_lsb,
+                     int data_swab, AddressSpace *as, bool load_rom)
 {
     return load_elf_ram_sym(filename, elf_note_fn,
                             translate_fn, translate_opaque,
@@ -444,16 +445,17 @@ int load_elf_ram(const char *filename,
 }
 
 /* return < 0 if error, otherwise the number of bytes loaded in memory */
-int load_elf_ram_sym(const char *filename,
-                     uint64_t (*elf_note_fn)(void *, void *, bool),
-                     uint64_t (*translate_fn)(void *, uint64_t),
-                     void *translate_opaque, uint64_t *pentry,
-                     uint64_t *lowaddr, uint64_t *highaddr, uint32_t *pflags,
-                     int big_endian, int elf_machine,
-                     int clear_lsb, int data_swab,
-                     AddressSpace *as, bool load_rom, symbol_fn_t sym_cb)
+ssize_t load_elf_ram_sym(const char *filename,
+                         uint64_t (*elf_note_fn)(void *, void *, bool),
+                         uint64_t (*translate_fn)(void *, uint64_t),
+                         void *translate_opaque, uint64_t *pentry,
+                         uint64_t *lowaddr, uint64_t *highaddr,
+                         uint32_t *pflags, int big_endian, int elf_machine,
+                         int clear_lsb, int data_swab,
+                         AddressSpace *as, bool load_rom, symbol_fn_t sym_cb)
 {
-    int fd, data_order, target_data_order, must_swab, ret = ELF_LOAD_FAILED;
+    int fd, data_order, target_data_order, must_swab;
+    ssize_t ret = ELF_LOAD_FAILED;
     uint8_t e_ident[EI_NIDENT];
 
     fd = open(filename, O_RDONLY | O_BINARY);
diff --git a/include/hw/acpi/aml-build.h b/include/hw/acpi/aml-build.h
index 3cf6f2c1b9..8346003a22 100644
--- a/include/hw/acpi/aml-build.h
+++ b/include/hw/acpi/aml-build.h
@@ -489,6 +489,9 @@ void build_srat_memory(GArray *table_data, uint64_t base,
 void build_slit(GArray *table_data, BIOSLinker *linker, MachineState *ms,
                 const char *oem_id, const char *oem_table_id);
 
+void build_pptt(GArray *table_data, BIOSLinker *linker, MachineState *ms,
+                const char *oem_id, const char *oem_table_id);
+
 void build_fadt(GArray *tbl, BIOSLinker *linker, const AcpiFadtData *f,
                 const char *oem_id, const char *oem_table_id);
 
diff --git a/include/hw/arm/virt.h b/include/hw/arm/virt.h
index b461b8d261..dc6b66ffc8 100644
--- a/include/hw/arm/virt.h
+++ b/include/hw/arm/virt.h
@@ -125,11 +125,13 @@ struct VirtMachineClass {
     bool claim_edge_triggered_timers;
     bool smbios_old_sys_ver;
     bool no_highmem_ecam;
-    bool no_ged;   /* Machines < 4.2 has no support for ACPI GED device */
+    bool no_ged;   /* Machines < 4.2 have no support for ACPI GED device */
     bool kvm_no_adjvtime;
     bool no_kvm_steal_time;
     bool acpi_expose_flash;
     bool no_secure_gpio;
+    /* Machines < 6.2 have no support for describing cpu topology to guest */
+    bool no_cpu_topology;
 };
 
 struct VirtMachineState {
diff --git a/include/hw/elf_ops.h b/include/hw/elf_ops.h
index 1c37cec4ae..995de8495c 100644
--- a/include/hw/elf_ops.h
+++ b/include/hw/elf_ops.h
@@ -312,25 +312,26 @@ static struct elf_note *glue(get_elf_note_type, SZ)(struct elf_note *nhdr,
     return nhdr;
 }
 
-static int glue(load_elf, SZ)(const char *name, int fd,
-                              uint64_t (*elf_note_fn)(void *, void *, bool),
-                              uint64_t (*translate_fn)(void *, uint64_t),
-                              void *translate_opaque,
-                              int must_swab, uint64_t *pentry,
-                              uint64_t *lowaddr, uint64_t *highaddr,
-                              uint32_t *pflags, int elf_machine,
-                              int clear_lsb, int data_swab,
-                              AddressSpace *as, bool load_rom,
-                              symbol_fn_t sym_cb)
+static ssize_t glue(load_elf, SZ)(const char *name, int fd,
+                                  uint64_t (*elf_note_fn)(void *, void *, bool),
+                                  uint64_t (*translate_fn)(void *, uint64_t),
+                                  void *translate_opaque,
+                                  int must_swab, uint64_t *pentry,
+                                  uint64_t *lowaddr, uint64_t *highaddr,
+                                  uint32_t *pflags, int elf_machine,
+                                  int clear_lsb, int data_swab,
+                                  AddressSpace *as, bool load_rom,
+                                  symbol_fn_t sym_cb)
 {
     struct elfhdr ehdr;
     struct elf_phdr *phdr = NULL, *ph;
-    int size, i, total_size;
+    int size, i;
+    ssize_t total_size;
     elf_word mem_size, file_size, data_offset;
     uint64_t addr, low = (uint64_t)-1, high = 0;
     GMappedFile *mapped_file = NULL;
     uint8_t *data = NULL;
-    int ret = ELF_LOAD_FAILED;
+    ssize_t ret = ELF_LOAD_FAILED;
 
     if (read(fd, &ehdr, sizeof(ehdr)) != sizeof(ehdr))
         goto fail;
@@ -482,7 +483,7 @@ static int glue(load_elf, SZ)(const char *name, int fd,
                 }
             }
 
-            if (mem_size > INT_MAX - total_size) {
+            if (mem_size > SSIZE_MAX - total_size) {
                 ret = ELF_LOAD_TOO_BIG;
                 goto fail;
             }
diff --git a/include/hw/loader.h b/include/hw/loader.h
index 81104cb02f..4fa485bd61 100644
--- a/include/hw/loader.h
+++ b/include/hw/loader.h
@@ -90,7 +90,7 @@ int load_image_gzipped(const char *filename, hwaddr addr, uint64_t max_sz);
 #define ELF_LOAD_WRONG_ARCH   -3
 #define ELF_LOAD_WRONG_ENDIAN -4
 #define ELF_LOAD_TOO_BIG      -5
-const char *load_elf_strerror(int error);
+const char *load_elf_strerror(ssize_t error);
 
 /** load_elf_ram_sym:
  * @filename: Path of ELF file
@@ -128,48 +128,48 @@ const char *load_elf_strerror(int error);
 typedef void (*symbol_fn_t)(const char *st_name, int st_info,
                             uint64_t st_value, uint64_t st_size);
 
-int load_elf_ram_sym(const char *filename,
-                     uint64_t (*elf_note_fn)(void *, void *, bool),
-                     uint64_t (*translate_fn)(void *, uint64_t),
-                     void *translate_opaque, uint64_t *pentry,
-                     uint64_t *lowaddr, uint64_t *highaddr, uint32_t *pflags,
-                     int big_endian, int elf_machine,
-                     int clear_lsb, int data_swab,
-                     AddressSpace *as, bool load_rom, symbol_fn_t sym_cb);
+ssize_t load_elf_ram_sym(const char *filename,
+                         uint64_t (*elf_note_fn)(void *, void *, bool),
+                         uint64_t (*translate_fn)(void *, uint64_t),
+                         void *translate_opaque, uint64_t *pentry,
+                         uint64_t *lowaddr, uint64_t *highaddr,
+                         uint32_t *pflags, int big_endian, int elf_machine,
+                         int clear_lsb, int data_swab,
+                         AddressSpace *as, bool load_rom, symbol_fn_t sym_cb);
 
 /** load_elf_ram:
  * Same as load_elf_ram_sym(), but doesn't allow the caller to specify a
  * symbol callback function
  */
-int load_elf_ram(const char *filename,
-                 uint64_t (*elf_note_fn)(void *, void *, bool),
-                 uint64_t (*translate_fn)(void *, uint64_t),
-                 void *translate_opaque, uint64_t *pentry, uint64_t *lowaddr,
-                 uint64_t *highaddr, uint32_t *pflags, int big_endian,
-                 int elf_machine, int clear_lsb, int data_swab,
-                 AddressSpace *as, bool load_rom);
+ssize_t load_elf_ram(const char *filename,
+                     uint64_t (*elf_note_fn)(void *, void *, bool),
+                     uint64_t (*translate_fn)(void *, uint64_t),
+                     void *translate_opaque, uint64_t *pentry,
+                     uint64_t *lowaddr, uint64_t *highaddr, uint32_t *pflags,
+                     int big_endian, int elf_machine, int clear_lsb,
+                     int data_swab, AddressSpace *as, bool load_rom);
 
 /** load_elf_as:
  * Same as load_elf_ram(), but always loads the elf as ROM
  */
-int load_elf_as(const char *filename,
-                uint64_t (*elf_note_fn)(void *, void *, bool),
-                uint64_t (*translate_fn)(void *, uint64_t),
-                void *translate_opaque, uint64_t *pentry, uint64_t *lowaddr,
-                uint64_t *highaddr, uint32_t *pflags, int big_endian,
-                int elf_machine, int clear_lsb, int data_swab,
-                AddressSpace *as);
+ssize_t load_elf_as(const char *filename,
+                    uint64_t (*elf_note_fn)(void *, void *, bool),
+                    uint64_t (*translate_fn)(void *, uint64_t),
+                    void *translate_opaque, uint64_t *pentry, uint64_t *lowaddr,
+                    uint64_t *highaddr, uint32_t *pflags, int big_endian,
+                    int elf_machine, int clear_lsb, int data_swab,
+                    AddressSpace *as);
 
 /** load_elf:
  * Same as load_elf_as(), but doesn't allow the caller to specify an
  * AddressSpace.
  */
-int load_elf(const char *filename,
-             uint64_t (*elf_note_fn)(void *, void *, bool),
-             uint64_t (*translate_fn)(void *, uint64_t),
-             void *translate_opaque, uint64_t *pentry, uint64_t *lowaddr,
-             uint64_t *highaddr, uint32_t *pflags, int big_endian,
-             int elf_machine, int clear_lsb, int data_swab);
+ssize_t load_elf(const char *filename,
+                 uint64_t (*elf_note_fn)(void *, void *, bool),
+                 uint64_t (*translate_fn)(void *, uint64_t),
+                 void *translate_opaque, uint64_t *pentry, uint64_t *lowaddr,
+                 uint64_t *highaddr, uint32_t *pflags, int big_endian,
+                 int elf_machine, int clear_lsb, int data_swab);
 
 /** load_elf_hdr:
  * @filename: Path of ELF file
diff --git a/include/sysemu/device_tree.h b/include/sysemu/device_tree.h
index 8a2fe55622..ef060a9759 100644
--- a/include/sysemu/device_tree.h
+++ b/include/sysemu/device_tree.h
@@ -121,6 +121,7 @@ uint32_t qemu_fdt_get_phandle(void *fdt, const char *path);
 uint32_t qemu_fdt_alloc_phandle(void *fdt);
 int qemu_fdt_nop_node(void *fdt, const char *node_path);
 int qemu_fdt_add_subnode(void *fdt, const char *name);
+int qemu_fdt_add_path(void *fdt, const char *path);
 
 #define qemu_fdt_setprop_cells(fdt, node_path, property, ...)                 \
     do {                                                                      \
diff --git a/roms/Makefile b/roms/Makefile
index eeb5970348..b967b53bb7 100644
--- a/roms/Makefile
+++ b/roms/Makefile
@@ -143,7 +143,8 @@ build-efi-roms: build-pxe-roms
 #    efirom
 #
 edk2-basetools:
-	cd edk2/BaseTools && git submodule update --init --force
+	cd edk2/BaseTools && git submodule update --init --force \
+		Source/C/BrotliCompress/brotli
 	$(MAKE) -C edk2/BaseTools \
 		PYTHON_COMMAND=$${EDK2_PYTHON_COMMAND:-python3} \
 		EXTRA_OPTFLAGS='$(EDK2_BASETOOLS_OPTFLAGS)' \
diff --git a/roms/Makefile.edk2 b/roms/Makefile.edk2
index a8ed325575..fdae0b511f 100644
--- a/roms/Makefile.edk2
+++ b/roms/Makefile.edk2
@@ -51,7 +51,12 @@ all: $(foreach flashdev,$(flashdevs),../pc-bios/edk2-$(flashdev).fd.bz2) \
 # make-release/tarball scripts.
 submodules:
 	if test -d edk2/.git; then \
-		cd edk2 && git submodule update --init --force; \
+		cd edk2 && git submodule update --init --force -- \
+			ArmPkg/Library/ArmSoftFloatLib/berkeley-softfloat-3 \
+			BaseTools/Source/C/BrotliCompress/brotli \
+			CryptoPkg/Library/OpensslLib/openssl \
+			MdeModulePkg/Library/BrotliCustomDecompressLib/brotli \
+		; \
 	fi
 
 # See notes on the ".NOTPARALLEL" target and the "+" indicator in
diff --git a/scripts/make-release b/scripts/make-release
index a2a8cda33c..05b14ecc95 100755
--- a/scripts/make-release
+++ b/scripts/make-release
@@ -27,7 +27,12 @@ git submodule update --init
 # don't necessarily have much control over how a submodule handles its
 # submodule dependencies, so we continue to handle these on a case-by-case
 # basis for now.
-(cd roms/edk2 && git submodule update --init)
+(cd roms/edk2 && \
+    git submodule update --init -- \
+        ArmPkg/Library/ArmSoftFloatLib/berkeley-softfloat-3 \
+        BaseTools/Source/C/BrotliCompress/brotli \
+        CryptoPkg/Library/OpensslLib/openssl \
+        MdeModulePkg/Library/BrotliCustomDecompressLib/brotli)
 popd
 tar --exclude=.git -cjf ${destination}.tar.bz2 ${destination}
 rm -rf ${destination}
diff --git a/softmmu/device_tree.c b/softmmu/device_tree.c
index b621f63fba..3965c834ca 100644
--- a/softmmu/device_tree.c
+++ b/softmmu/device_tree.c
@@ -540,8 +540,8 @@ int qemu_fdt_add_subnode(void *fdt, const char *name)
 
     retval = fdt_add_subnode(fdt, parent, basename);
     if (retval < 0) {
-        error_report("FDT: Failed to create subnode %s: %s", name,
-                     fdt_strerror(retval));
+        error_report("%s: Failed to create subnode %s: %s",
+                     __func__, name, fdt_strerror(retval));
         exit(1);
     }
 
@@ -549,6 +549,46 @@ int qemu_fdt_add_subnode(void *fdt, const char *name)
     return retval;
 }
 
+/*
+ * qemu_fdt_add_path: Like qemu_fdt_add_subnode(), but will add
+ * all missing subnodes from the given path.
+ */
+int qemu_fdt_add_path(void *fdt, const char *path)
+{
+    const char *name;
+    const char *p = path;
+    int namelen, retval;
+    int parent = 0;
+
+    if (path[0] != '/') {
+        return -1;
+    }
+
+    while (p) {
+        name = p + 1;
+        p = strchr(name, '/');
+        namelen = p != NULL ? p - name : strlen(name);
+
+        retval = fdt_subnode_offset_namelen(fdt, parent, name, namelen);
+        if (retval < 0 && retval != -FDT_ERR_NOTFOUND) {
+            error_report("%s: Unexpected error in finding subnode %.*s: %s",
+                         __func__, namelen, name, fdt_strerror(retval));
+            exit(1);
+        } else if (retval == -FDT_ERR_NOTFOUND) {
+            retval = fdt_add_subnode_namelen(fdt, parent, name, namelen);
+            if (retval < 0) {
+                error_report("%s: Failed to create subnode %.*s: %s",
+                             __func__, namelen, name, fdt_strerror(retval));
+                exit(1);
+            }
+        }
+
+        parent = retval;
+    }
+
+    return retval;
+}
+
 void qemu_fdt_dumpdtb(void *fdt, int size)
 {
     const char *dumpdtb = current_machine->dumpdtb;
diff --git a/tests/data/acpi/virt/DBG2 b/tests/data/acpi/virt/DBG2
new file mode 100644
index 0000000000..86e6314f7b
--- /dev/null
+++ b/tests/data/acpi/virt/DBG2
diff --git a/tests/data/acpi/virt/IORT b/tests/data/acpi/virt/IORT
index 521acefe9b..7efd0ce8a6 100644
--- a/tests/data/acpi/virt/IORT
+++ b/tests/data/acpi/virt/IORT
diff --git a/tests/data/acpi/virt/IORT.memhp b/tests/data/acpi/virt/IORT.memhp
index 521acefe9b..7efd0ce8a6 100644
--- a/tests/data/acpi/virt/IORT.memhp
+++ b/tests/data/acpi/virt/IORT.memhp
diff --git a/tests/data/acpi/virt/IORT.numamem b/tests/data/acpi/virt/IORT.numamem
index 521acefe9b..7efd0ce8a6 100644
--- a/tests/data/acpi/virt/IORT.numamem
+++ b/tests/data/acpi/virt/IORT.numamem
diff --git a/tests/data/acpi/virt/IORT.pxb b/tests/data/acpi/virt/IORT.pxb
index 521acefe9b..7efd0ce8a6 100644
--- a/tests/data/acpi/virt/IORT.pxb
+++ b/tests/data/acpi/virt/IORT.pxb
diff --git a/tests/data/acpi/virt/PPTT b/tests/data/acpi/virt/PPTT
new file mode 100644
index 0000000000..7a1258ecf1
--- /dev/null
+++ b/tests/data/acpi/virt/PPTT