Merge tag 'pull-target-arm-20220509' of https://git.linaro.org/people/pmaydell/qemu-arm into staging

target-arm queue:
 * MAINTAINERS/.mailmap: update email for Leif Lindholm
 * hw/arm: add version information to sbsa-ref machine DT
 * Enable new features for -cpu max:
   FEAT_Debugv8p2, FEAT_Debugv8p4, FEAT_RAS (minimal version only),
   FEAT_IESB, FEAT_CSV2, FEAT_CSV2_2, FEAT_CSV3, FEAT_DGH
 * Emulate Cortex-A76
 * Emulate Neoverse-N1
 * Fix the virt board default NUMA topology

# -----BEGIN PGP SIGNATURE-----
#
# iQJNBAABCAA3FiEE4aXFk81BneKOgxXPPCUl7RQ2DN4FAmJ5AbsZHHBldGVyLm1h
# eWRlbGxAbGluYXJvLm9yZwAKCRA8JSXtFDYM3vyFEACZZ6tRVJYB6YpIzI7rho9x
# hVQIMTc4D5lmVetJnbLdLazifIy60oIOtSKV3Y3oj5DLMcsf6NITrPaFPWNRX3Nm
# mcbTCT5FGj8i7b1CkpEylLwvRQbIaoz2GnJPckdYelxxAq1uJNog3fmoG8nVtJ1F
# HfXVCVkZGQyiyr6Y2/zn3vpdp9n6/4RymN8ugizkcgIRII87DKV+DNDalw613JG4
# 5xxBOGkYzo5DZM8TgL8Ylmb5Jy9XY0EN1xpkyHFOg6gi0B3UZTxHq5SvK6NFoZLJ
# ogyhmMh6IjEfhUIDCtWG9VCoPyWpOXAFoh7D7akFVB4g2SIvBvcuGzFxCAsh5q3K
# s+9CgNX1SZpJQkT1jLjQlNzoUhh8lNc7QvhPWVrbAj3scc+1xVnS5MJsokEV21Cx
# /bp3mFwCL+Q4gjsMKx1nKSvxLv8xlxRtIilmlfj+wvpkenIfIwHYjbvItJTlAy1L
# +arx8fqImNQorxO6oMjOuAlSbNnDKup5qvwGghyu/qz/YEnGQVzN6gI324Km081L
# 1u31H/B3C2rj3qMsYMp5yOqgprXi1D5c6wfYIpLD/C4UfHgIlRiprawZPDM7fAhX
# vxhUhhj3e9OgkbC9yqd6SUR2Uk3YaQlp319LyoZa3VKSvjBTciFsMXXnIV1UitYp
# BGtz8+FypPVkYH7zQB9c7Q==
# =ey1m
# -----END PGP SIGNATURE-----
# gpg: Signature made Mon 09 May 2022 04:57:47 AM PDT
# gpg:                using RSA key E1A5C593CD419DE28E8315CF3C2525ED14360CDE
# gpg:                issuer "peter.maydell@linaro.org"
# gpg: Good signature from "Peter Maydell <peter.maydell@linaro.org>" [full]
# gpg:                 aka "Peter Maydell <pmaydell@gmail.com>" [full]
# gpg:                 aka "Peter Maydell <pmaydell@chiark.greenend.org.uk>" [full]

* tag 'pull-target-arm-20220509' of https://git.linaro.org/people/pmaydell/qemu-arm: (32 commits)
  hw/acpi/aml-build: Use existing CPU topology to build PPTT table
  hw/arm/virt: Fix CPU's default NUMA node ID
  qtest/numa-test: Correct CPU and NUMA association in aarch64_numa_cpu()
  hw/arm/virt: Consider SMP configuration in CPU topology
  qtest/numa-test: Specify CPU topology in aarch64_numa_cpu()
  qapi/machine.json: Add cluster-id
  hw/arm: add versioning to sbsa-ref machine DT
  target/arm: Define neoverse-n1
  target/arm: Define cortex-a76
  target/arm: Enable FEAT_DGH for -cpu max
  target/arm: Enable FEAT_CSV3 for -cpu max
  target/arm: Enable FEAT_CSV2_2 for -cpu max
  target/arm: Enable FEAT_CSV2 for -cpu max
  target/arm: Enable FEAT_IESB for -cpu max
  target/arm: Enable FEAT_RAS for -cpu max
  target/arm: Implement ESB instruction
  target/arm: Implement virtual SError exceptions
  target/arm: Enable SCR and HCR bits for RAS
  target/arm: Add minimal RAS registers
  target/arm: Enable FEAT_Debugv8p4 for -cpu max
  ...

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

5 files changed, 103 insertions, 65 deletions

diff --git a/hw/acpi/aml-build.c b/hw/acpi/aml-build.c
index 4086879..e6bfac9 100644
--- a/hw/acpi/aml-build.c
+++ b/hw/acpi/aml-build.c
@@ -2002,86 +2002,71 @@ void build_pptt(GArray *table_data, BIOSLinker *linker, MachineState *ms,
                 const char *oem_id, const char *oem_table_id)
 {
     MachineClass *mc = MACHINE_GET_CLASS(ms);
-    GQueue *list = g_queue_new();
-    guint pptt_start = table_data->len;
-    guint parent_offset;
-    guint length, i;
-    int uid = 0;
-    int socket;
+    CPUArchIdList *cpus = ms->possible_cpus;
+    int64_t socket_id = -1, cluster_id = -1, core_id = -1;
+    uint32_t socket_offset = 0, cluster_offset = 0, core_offset = 0;
+    uint32_t pptt_start = table_data->len;
+    int n;
     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++) {
-        g_queue_push_tail(list,
-            GUINT_TO_POINTER(table_data->len - pptt_start));
-        build_processor_hierarchy_node(
-            table_data,
-            /*
-             * Physical package - represents the boundary
-             * of a physical package
-             */
-            (1 << 0),
-            0, socket, NULL, 0);
-    }
-
-    if (mc->smp_props.clusters_supported) {
-        length = g_queue_get_length(list);
-        for (i = 0; i < length; i++) {
-            int cluster;
-
-            parent_offset = GPOINTER_TO_UINT(g_queue_pop_head(list));
-            for (cluster = 0; cluster < ms->smp.clusters; cluster++) {
-                g_queue_push_tail(list,
-                    GUINT_TO_POINTER(table_data->len - pptt_start));
-                build_processor_hierarchy_node(
-                    table_data,
-                    (0 << 0), /* not a physical package */
-                    parent_offset, cluster, NULL, 0);
-            }
+    /*
+     * This works with the assumption that cpus[n].props.*_id has been
+     * sorted from top to down levels in mc->possible_cpu_arch_ids().
+     * Otherwise, the unexpected and duplicated containers will be
+     * created.
+     */
+    for (n = 0; n < cpus->len; n++) {
+        if (cpus->cpus[n].props.socket_id != socket_id) {
+            assert(cpus->cpus[n].props.socket_id > socket_id);
+            socket_id = cpus->cpus[n].props.socket_id;
+            cluster_id = -1;
+            core_id = -1;
+            socket_offset = table_data->len - pptt_start;
+            build_processor_hierarchy_node(table_data,
+                (1 << 0), /* Physical package */
+                0, socket_id, NULL, 0);
         }
-    }
 
-    length = g_queue_get_length(list);
-    for (i = 0; i < length; i++) {
-        int core;
-
-        parent_offset = GPOINTER_TO_UINT(g_queue_pop_head(list));
-        for (core = 0; core < ms->smp.cores; core++) {
-            if (ms->smp.threads > 1) {
-                g_queue_push_tail(list,
-                    GUINT_TO_POINTER(table_data->len - pptt_start));
-                build_processor_hierarchy_node(
-                    table_data,
-                    (0 << 0), /* not a physical package */
-                    parent_offset, core, NULL, 0);
-            } else {
-                build_processor_hierarchy_node(
-                    table_data,
-                    (1 << 1) | /* ACPI Processor ID valid */
-                    (1 << 3),  /* Node is a Leaf */
-                    parent_offset, uid++, NULL, 0);
+        if (mc->smp_props.clusters_supported) {
+            if (cpus->cpus[n].props.cluster_id != cluster_id) {
+                assert(cpus->cpus[n].props.cluster_id > cluster_id);
+                cluster_id = cpus->cpus[n].props.cluster_id;
+                core_id = -1;
+                cluster_offset = table_data->len - pptt_start;
+                build_processor_hierarchy_node(table_data,
+                    (0 << 0), /* Not a physical package */
+                    socket_offset, cluster_id, NULL, 0);
             }
+        } else {
+            cluster_offset = socket_offset;
         }
-    }
 
-    length = g_queue_get_length(list);
-    for (i = 0; i < length; i++) {
-        int thread;
+        if (ms->smp.threads == 1) {
+            build_processor_hierarchy_node(table_data,
+                (1 << 1) | /* ACPI Processor ID valid */
+                (1 << 3),  /* Node is a Leaf */
+                cluster_offset, n, NULL, 0);
+        } else {
+            if (cpus->cpus[n].props.core_id != core_id) {
+                assert(cpus->cpus[n].props.core_id > core_id);
+                core_id = cpus->cpus[n].props.core_id;
+                core_offset = table_data->len - pptt_start;
+                build_processor_hierarchy_node(table_data,
+                    (0 << 0), /* Not a physical package */
+                    cluster_offset, core_id, NULL, 0);
+            }
 
-        parent_offset = GPOINTER_TO_UINT(g_queue_pop_head(list));
-        for (thread = 0; thread < ms->smp.threads; thread++) {
-            build_processor_hierarchy_node(
-                table_data,
+            build_processor_hierarchy_node(table_data,
                 (1 << 1) | /* ACPI Processor ID valid */
                 (1 << 2) | /* Processor is a Thread */
                 (1 << 3),  /* Node is a Leaf */
-                parent_offset, uid++, NULL, 0);
+                core_offset, n, NULL, 0);
         }
     }
 
-    g_queue_free(list);
     acpi_table_end(linker, &table);
 }
 
diff --git a/hw/arm/sbsa-ref.c b/hw/arm/sbsa-ref.c
index 2387401..4bb4446 100644
--- a/hw/arm/sbsa-ref.c
+++ b/hw/arm/sbsa-ref.c
@@ -145,6 +145,8 @@ static const int sbsa_ref_irqmap[] = {
 static const char * const valid_cpus[] = {
     ARM_CPU_TYPE_NAME("cortex-a57"),
     ARM_CPU_TYPE_NAME("cortex-a72"),
+    ARM_CPU_TYPE_NAME("cortex-a76"),
+    ARM_CPU_TYPE_NAME("neoverse-n1"),
     ARM_CPU_TYPE_NAME("max"),
 };
 
@@ -190,6 +192,20 @@ static void create_fdt(SBSAMachineState *sms)
     qemu_fdt_setprop_cell(fdt, "/", "#address-cells", 0x2);
     qemu_fdt_setprop_cell(fdt, "/", "#size-cells", 0x2);
 
+    /*
+     * This versioning scheme is for informing platform fw only. It is neither:
+     * - A QEMU versioned machine type; a given version of QEMU will emulate
+     *   a given version of the platform.
+     * - A reflection of level of SBSA (now SystemReady SR) support provided.
+     *
+     * machine-version-major: updated when changes breaking fw compatibility
+     *                        are introduced.
+     * machine-version-minor: updated when features are added that don't break
+     *                        fw compatibility.
+     */
+    qemu_fdt_setprop_cell(fdt, "/", "machine-version-major", 0);
+    qemu_fdt_setprop_cell(fdt, "/", "machine-version-minor", 0);
+
     if (ms->numa_state->have_numa_distance) {
         int size = nb_numa_nodes * nb_numa_nodes * 3 * sizeof(uint32_t);
         uint32_t *matrix = g_malloc0(size);
diff --git a/hw/arm/virt.c b/hw/arm/virt.c
index f942789..1a45f44 100644
--- a/hw/arm/virt.c
+++ b/hw/arm/virt.c
@@ -202,7 +202,9 @@ static const char *valid_cpus[] = {
     ARM_CPU_TYPE_NAME("cortex-a53"),
     ARM_CPU_TYPE_NAME("cortex-a57"),
     ARM_CPU_TYPE_NAME("cortex-a72"),
+    ARM_CPU_TYPE_NAME("cortex-a76"),
     ARM_CPU_TYPE_NAME("a64fx"),
+    ARM_CPU_TYPE_NAME("neoverse-n1"),
     ARM_CPU_TYPE_NAME("host"),
     ARM_CPU_TYPE_NAME("max"),
 };
@@ -2552,7 +2554,9 @@ virt_cpu_index_to_props(MachineState *ms, unsigned cpu_index)
 
 static int64_t virt_get_default_cpu_node_id(const MachineState *ms, int idx)
 {
-    return idx % ms->numa_state->num_nodes;
+    int64_t socket_id = ms->possible_cpus->cpus[idx].props.socket_id;
+
+    return socket_id % ms->numa_state->num_nodes;
 }
 
 static const CPUArchIdList *virt_possible_cpu_arch_ids(MachineState *ms)
@@ -2560,6 +2564,7 @@ static const CPUArchIdList *virt_possible_cpu_arch_ids(MachineState *ms)
     int n;
     unsigned int max_cpus = ms->smp.max_cpus;
     VirtMachineState *vms = VIRT_MACHINE(ms);
+    MachineClass *mc = MACHINE_GET_CLASS(vms);
 
     if (ms->possible_cpus) {
         assert(ms->possible_cpus->len == max_cpus);
@@ -2573,8 +2578,20 @@ static const CPUArchIdList *virt_possible_cpu_arch_ids(MachineState *ms)
         ms->possible_cpus->cpus[n].type = ms->cpu_type;
         ms->possible_cpus->cpus[n].arch_id =
             virt_cpu_mp_affinity(vms, n);
+
+        assert(!mc->smp_props.dies_supported);
+        ms->possible_cpus->cpus[n].props.has_socket_id = true;
+        ms->possible_cpus->cpus[n].props.socket_id =
+            n / (ms->smp.clusters * ms->smp.cores * ms->smp.threads);
+        ms->possible_cpus->cpus[n].props.has_cluster_id = true;
+        ms->possible_cpus->cpus[n].props.cluster_id =
+            (n / (ms->smp.cores * ms->smp.threads)) % ms->smp.clusters;
+        ms->possible_cpus->cpus[n].props.has_core_id = true;
+        ms->possible_cpus->cpus[n].props.core_id =
+            (n / ms->smp.threads) % ms->smp.cores;
         ms->possible_cpus->cpus[n].props.has_thread_id = true;
-        ms->possible_cpus->cpus[n].props.thread_id = n;
+        ms->possible_cpus->cpus[n].props.thread_id =
+            n % ms->smp.threads;
     }
     return ms->possible_cpus;
 }
diff --git a/hw/core/machine-hmp-cmds.c b/hw/core/machine-hmp-cmds.c
index 4e2f319..5cb5eec 100644
--- a/hw/core/machine-hmp-cmds.c
+++ b/hw/core/machine-hmp-cmds.c
@@ -77,6 +77,10 @@ void hmp_hotpluggable_cpus(Monitor *mon, const QDict *qdict)
         if (c->has_die_id) {
             monitor_printf(mon, "    die-id: \"%" PRIu64 "\"\n", c->die_id);
         }
+        if (c->has_cluster_id) {
+            monitor_printf(mon, "    cluster-id: \"%" PRIu64 "\"\n",
+                           c->cluster_id);
+        }
         if (c->has_core_id) {
             monitor_printf(mon, "    core-id: \"%" PRIu64 "\"\n", c->core_id);
         }
diff --git a/hw/core/machine.c b/hw/core/machine.c
index cb9bbc8..700c1e7 100644
--- a/hw/core/machine.c
+++ b/hw/core/machine.c
@@ -682,6 +682,11 @@ void machine_set_cpu_numa_node(MachineState *machine,
             return;
         }
 
+        if (props->has_cluster_id && !slot->props.has_cluster_id) {
+            error_setg(errp, "cluster-id is not supported");
+            return;
+        }
+
         if (props->has_socket_id && !slot->props.has_socket_id) {
             error_setg(errp, "socket-id is not supported");
             return;
@@ -701,6 +706,11 @@ void machine_set_cpu_numa_node(MachineState *machine,
                 continue;
         }
 
+        if (props->has_cluster_id &&
+            props->cluster_id != slot->props.cluster_id) {
+                continue;
+        }
+
         if (props->has_die_id && props->die_id != slot->props.die_id) {
                 continue;
         }
@@ -995,6 +1005,12 @@ static char *cpu_slot_to_string(const CPUArchId *cpu)
         }
         g_string_append_printf(s, "die-id: %"PRId64, cpu->props.die_id);
     }
+    if (cpu->props.has_cluster_id) {
+        if (s->len) {
+            g_string_append_printf(s, ", ");
+        }
+        g_string_append_printf(s, "cluster-id: %"PRId64, cpu->props.cluster_id);
+    }
     if (cpu->props.has_core_id) {
         if (s->len) {
             g_string_append_printf(s, ", ");