[PATCH v5 1/4] xen/device-tree: Parse 'cpu-map' node for CPU topology exploration

[Hirokazu Takahashi <taka@xxxxxxxxxxxxx>]

Parse the 'cpu-map' node in the Device Tree to extract CPU topology
information. If the 'cpu-map' node is absent, fall back to
generating the topology data from the NUMA information. This
generation assumes exactly one socket per NUMA node and that SMT
is unsupported.

Signed-off-by: Hirokazu Takahashi <taka@xxxxxxxxxxxxx>
---
 xen/arch/arm/Kconfig                  |   1 +
 xen/arch/arm/smpboot.c                |   7 +
 xen/common/Kconfig                    |  15 ++
 xen/common/Makefile                   |   1 +
 xen/common/cpu-topology.c             |  62 +++++
 xen/common/device-tree/Makefile       |   1 +
 xen/common/device-tree/cpu-topology.c | 355 ++++++++++++++++++++++++++
 xen/drivers/acpi/Kconfig              |   3 +
 xen/drivers/acpi/Makefile             |   1 +
 xen/drivers/acpi/topology.c           |  38 +++
 xen/include/xen/acpi.h                |  10 +
 xen/include/xen/cpu-topology.h        |  35 +++
 xen/include/xen/dt-cpu-topology.h     |  29 +++
 13 files changed, 558 insertions(+)
 create mode 100644 xen/common/cpu-topology.c
 create mode 100644 xen/common/device-tree/cpu-topology.c
 create mode 100644 xen/drivers/acpi/topology.c
 create mode 100644 xen/include/xen/cpu-topology.h
 create mode 100644 xen/include/xen/dt-cpu-topology.h

diff --git a/xen/arch/arm/Kconfig b/xen/arch/arm/Kconfig
index 843a43897e..26296c12c8 100644
--- a/xen/arch/arm/Kconfig
+++ b/xen/arch/arm/Kconfig
@@ -23,6 +23,7 @@ config ARM
        select HAS_STACK_PROTECTOR
        select HAS_STATIC_MEMORY
        select HAS_UBSAN
+       select HAS_GENERIC_CPU_TOPOLOGY
 
 config ARCH_DEFCONFIG
        string
diff --git a/xen/arch/arm/smpboot.c b/xen/arch/arm/smpboot.c
index ba5fd2dd52..d957553a44 100644
--- a/xen/arch/arm/smpboot.c
+++ b/xen/arch/arm/smpboot.c
@@ -9,10 +9,12 @@
 
 #include <xen/acpi.h>
 #include <xen/cpu.h>
+#include <xen/cpu-topology.h>
 #include <xen/cpumask.h>
 #include <xen/delay.h>
 #include <xen/device_tree.h>
 #include <xen/domain_page.h>
+#include <xen/dt-cpu-topology.h>
 #include <xen/errno.h>
 #include <xen/init.h>
 #include <xen/mm.h>
@@ -244,6 +246,9 @@ static void __init dt_smp_init_cpus(void)
         }
         else
             tmp_map[i] = hwid;
+
+        /* Pass the info to dt_init_cpu_topology() */
+        map_cpu_to_dt_node(i, cpu);
     }
 
     if ( !bootcpu_valid )
@@ -280,6 +285,8 @@ void __init smp_init_cpus(void)
     else
         acpi_smp_init_cpus();
 
+    init_cpu_topology();
+
     if ( opt_hmp_unsafe )
         warning_add("WARNING: HMP COMPUTING HAS BEEN ENABLED.\n"
                     "It has implications on the security and stability of the 
system,\n"
diff --git a/xen/common/Kconfig b/xen/common/Kconfig
index da80fdba84..c4bddfd098 100644
--- a/xen/common/Kconfig
+++ b/xen/common/Kconfig
@@ -191,6 +191,21 @@ config VM_EVENT
 config NEEDS_LIBELF
        bool
 
+config HAS_GENERIC_CPU_TOPOLOGY
+       bool
+
+config DT_CPU_TOPOLOGY
+       bool
+
+config GENERIC_CPU_TOPOLOGY
+       bool "CPU topology support (UNSUPPORTED)" if UNSUPPORTED
+       depends on HAS_GENERIC_CPU_TOPOLOGY
+       select DT_CPU_TOPOLOGY if DEVICE_TREE_PARSE
+       select ACPI_CPU_TOPOLOGY if ACPI
+       help
+         Retrieve CPU topology information from the device tree or the
+         ACPI PPTT to optimize virtual CPU scheduling.
+
 config NUMA
        bool
 
diff --git a/xen/common/Makefile b/xen/common/Makefile
index 6018e25614..34b333cdb3 100644
--- a/xen/common/Makefile
+++ b/xen/common/Makefile
@@ -5,6 +5,7 @@ obj-$(CONFIG_GENERIC_BUG_FRAME) += bug.o
 obj-$(CONFIG_HYPFS_CONFIG) += config_data.o
 obj-$(CONFIG_CORE_PARKING) += core_parking.o
 obj-y += cpu.o
+obj-$(CONFIG_GENERIC_CPU_TOPOLOGY) += cpu-topology.o
 obj-$(CONFIG_DEBUG_TRACE) += debugtrace.o
 obj-$(CONFIG_HAS_DEVICE_TREE_DISCOVERY) += device.o
 obj-$(filter-out $(CONFIG_X86),$(CONFIG_ACPI)) += device.o
diff --git a/xen/common/cpu-topology.c b/xen/common/cpu-topology.c
new file mode 100644
index 0000000000..94cb9ba312
--- /dev/null
+++ b/xen/common/cpu-topology.c
@@ -0,0 +1,62 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+
+#include <xen/acpi.h>
+#include <xen/cpu-topology.h>
+#include <xen/cpumask.h>
+#include <xen/dt-cpu-topology.h>
+#include <xen/init.h>
+
+struct cpu_topology *__ro_after_init cpu_topology;
+
+static void __init free_topology_table(void)
+{
+    unsigned int cpu;
+
+    for ( cpu = 0; cpu < nr_cpu_ids; cpu++ )
+    {
+        free_cpumask_var(cpu_topology[cpu].thread_sibling);
+        free_cpumask_var(cpu_topology[cpu].core_sibling);
+        free_cpumask_var(cpu_topology[cpu].cluster_sibling);
+    }
+
+    XFREE(cpu_topology);
+}
+
+void __init init_cpu_topology(void)
+{
+    unsigned int cpu;
+
+    cpu_topology = xzalloc_array(struct cpu_topology, nr_cpu_ids);
+    if ( !cpu_topology )
+    {
+        printk(XENLOG_ERR "Failed to allocate memory for cpu_topology 
table\n");
+        return;
+    }
+
+    for ( cpu = 0; cpu < nr_cpu_ids; cpu++ )
+    {
+        if ( !zalloc_cpumask_var(&cpu_topology[cpu].thread_sibling) ||
+             !zalloc_cpumask_var(&cpu_topology[cpu].core_sibling) ||
+             !zalloc_cpumask_var(&cpu_topology[cpu].cluster_sibling) )
+        {
+            free_topology_table();
+            printk(XENLOG_ERR "Failed to allocate memory for cpu_topology 
table\n");
+            return;
+        }
+    }
+
+    if ( acpi_disabled )
+        dt_init_cpu_topology();
+    else
+        acpi_init_cpu_topology();
+}
+
+/*
+ * Local variables:
+ * mode: C
+ * c-file-style: "BSD"
+ * c-basic-offset: 4
+ * tab-width: 4
+ * indent-tabs-mode: nil
+ * End:
+ */
diff --git a/xen/common/device-tree/Makefile b/xen/common/device-tree/Makefile
index 9036e455d6..6ee670b5f4 100644
--- a/xen/common/device-tree/Makefile
+++ b/xen/common/device-tree/Makefile
@@ -1,6 +1,7 @@
 obj-y += bootfdt.init.o
 obj-$(CONFIG_HAS_DEVICE_TREE_DISCOVERY) += bootinfo-fdt.init.o
 obj-$(CONFIG_HAS_DEVICE_TREE_DISCOVERY) += bootinfo.init.o
+obj-$(CONFIG_DT_CPU_TOPOLOGY) += cpu-topology.init.o
 obj-y += device-tree.o
 obj-$(CONFIG_DOMAIN_BUILD_HELPERS) += domain-build.init.o
 obj-$(filter $(CONFIG_DOM0LESS_BOOT),$(CONFIG_HAS_DEVICE_TREE_DISCOVERY)) += 
dom0less-build.init.o
diff --git a/xen/common/device-tree/cpu-topology.c 
b/xen/common/device-tree/cpu-topology.c
new file mode 100644
index 0000000000..b653227ef4
--- /dev/null
+++ b/xen/common/device-tree/cpu-topology.c
@@ -0,0 +1,355 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Derived from Linux kernel 7.0's $drivers/base/arch_topology.c
+ * Parse cpu topology information.
+ */
+
+#include <xen/acpi.h>
+#include <xen/cpu-topology.h>
+#include <xen/cpumask.h>
+#include <xen/device_tree.h>
+#include <xen/errno.h>
+#include <xen/init.h>
+#include <xen/numa.h>
+
+struct cpu_map {
+    unsigned int thread_id;
+    unsigned int core_id;
+    unsigned int cluster_id;
+    unsigned int package_id;
+};
+
+static const unsigned int __initdata invalid_topo_id = ~0U;
+static struct cpu_map __initdata cpu_map[NR_CPUS] = {
+    [0 ... NR_CPUS - 1] = {invalid_topo_id, invalid_topo_id, invalid_topo_id, 
0}
+};
+static struct dt_device_node *__initdata dt_cpu_table[NR_CPUS];
+
+static void __init setup_siblings_masks(unsigned int target_cpu)
+{
+    const struct cpu_topology *target_topo = &cpu_topology[target_cpu];
+    const struct cpu_map *target_map = &cpu_map[target_cpu];
+    unsigned int cpu;
+
+    /* Update core and thread sibling masks */
+    for_each_possible_cpu(cpu)
+    {
+        const struct cpu_topology *cpu_topo = &cpu_topology[cpu];
+        const struct cpu_map *map = &cpu_map[cpu];
+
+        if ( target_map->package_id != map->package_id )
+            continue;
+
+        cpumask_set_cpu(target_cpu, cpu_topo->core_sibling);
+        cpumask_set_cpu(cpu, target_topo->core_sibling);
+
+        if ( target_map->cluster_id != map->cluster_id )
+            continue;
+
+        if ( target_map->cluster_id != invalid_topo_id )
+        {
+            cpumask_set_cpu(target_cpu, cpu_topo->cluster_sibling);
+            cpumask_set_cpu(cpu, target_topo->cluster_sibling);
+        }
+
+        if ( target_map->core_id != map->core_id )
+            continue;
+
+        cpumask_set_cpu(target_cpu, cpu_topo->thread_sibling);
+        cpumask_set_cpu(cpu, target_topo->thread_sibling);
+    }
+}
+
+static struct dt_device_node *__init
+       dt_find_child_node_by_name(const struct dt_device_node *dt,
+                                  const char *name)
+{
+    struct dt_device_node *np;
+
+    dt_for_each_child_node(dt, np)
+        if ( np->name && (dt_node_cmp(np->name, name) == 0) )
+            break;
+
+    return np;
+}
+
+void __init map_cpu_to_dt_node(unsigned int cpu,
+                               struct dt_device_node *cpu_node)
+{
+    if ( cpu < ARRAY_SIZE(dt_cpu_table) )
+        dt_cpu_table[cpu] = cpu_node;
+    else
+        printk(XENLOG_WARNING
+               "cpu id %u exceeds the max cores %lu\n",
+               cpu, ARRAY_SIZE(dt_cpu_table));
+}
+
+static unsigned int __init cpu_node_to_id(const struct dt_device_node 
*cpu_node)
+{
+    unsigned int cpu;
+
+    for_each_possible_cpu(cpu)
+        if ( cpu_node == dt_cpu_table[cpu] )
+            return cpu;
+
+    return invalid_topo_id;
+}
+
+/*
+ * This function returns the logical cpu number of the DT node.
+ */
+static unsigned int __init
+       get_cpu_for_node(const struct dt_device_node *dt_node)
+{
+    const struct dt_device_node *cpu_node = dt_parse_phandle(dt_node, "cpu", 
0);
+
+    if ( !cpu_node )
+        return invalid_topo_id;
+
+    return cpu_node_to_id(cpu_node);
+}
+
+static int __init parse_core(const struct dt_device_node *core,
+                             unsigned int package_id,
+                             unsigned int cluster_id,
+                             unsigned int core_id)
+{
+    bool leaf = true;
+    unsigned int i = 0;
+    unsigned int cpu;
+
+    do {
+        const struct dt_device_node *t;
+        char name[20];
+
+        snprintf(name, sizeof(name), "thread%u", i);
+        t = dt_find_child_node_by_name(core, name);
+
+        if ( !t )
+            break;
+
+        leaf = false;
+        cpu = get_cpu_for_node(t);
+        if ( cpu != invalid_topo_id )
+        {
+            cpu_map[cpu].package_id = package_id;
+            cpu_map[cpu].cluster_id = cluster_id;
+            cpu_map[cpu].core_id = core_id;
+            cpu_map[cpu].thread_id = i;
+        }
+        else
+        {
+            printk(XENLOG_ERR
+                   "ERROR: %s: Can't get CPU for thread\n", dt_node_name(t));
+            return -EINVAL;
+        }
+        i++;
+    } while ( true );
+
+    cpu = get_cpu_for_node(core);
+
+    if ( cpu != invalid_topo_id )
+    {
+        if ( !leaf )
+        {
+            printk(XENLOG_ERR "ERROR: %s: Core has both threads and CPU\n",
+                   dt_node_name(core));
+            return -EINVAL;
+        }
+
+        cpu_map[cpu].package_id = package_id;
+        cpu_map[cpu].cluster_id = cluster_id;
+        cpu_map[cpu].core_id = core_id;
+        cpu_map[cpu].thread_id = 0;
+    }
+    else if ( leaf )
+    {
+        printk(XENLOG_ERR
+               "ERROR: %s: Can't get CPU for leaf core\n", dt_node_name(core));
+        return -EINVAL;
+    }
+
+    return 0;
+}
+
+static int __init parse_cluster(const struct dt_device_node *cluster,
+                                unsigned int package_id,
+                                unsigned int cluster_id,
+                                unsigned int depth)
+{
+    bool leaf = true;
+    bool has_cores = false;
+    unsigned int core_id = 0;
+    unsigned int i = 0;
+
+    /*
+     * First check for child clusters; we currently ignore any
+     * information about the nesting of clusters and present the
+     * scheduler with a flat list of them.
+     */
+    do {
+        const struct dt_device_node *c;
+        char name[20];
+        int ret;
+
+        snprintf(name, sizeof(name), "cluster%u", i);
+        c = dt_find_child_node_by_name(cluster, name);
+
+        if ( !c )
+            break;
+
+        leaf = false;
+        ret = parse_cluster(c, package_id, i, depth + 1);
+        if ( depth > 0 )
+            printk(XENLOG_WARNING
+                   "WARNING: Topology for clusters of clusters not yet 
supported\n");
+        if ( ret != 0 )
+            return ret;
+        i++;
+    } while ( true );
+
+    /* Now check for cores */
+    i = 0;
+    do {
+        const struct dt_device_node *c;
+        char name[20];
+        int ret;
+
+        snprintf(name, sizeof(name), "core%u", i);
+        c = dt_find_child_node_by_name(cluster, name);
+
+        if ( !c )
+            break;
+
+        has_cores = true;
+
+        if ( depth == 0 )
+        {
+            printk(XENLOG_ERR
+                   "ERROR: %s: cpu-map children should be clusters\n",
+                   dt_node_name(c));
+            return -EINVAL;
+        }
+
+        if ( leaf )
+        {
+            ret = parse_core(c, package_id, cluster_id, core_id++);
+            if ( ret != 0 )
+                return ret;
+        }
+        else
+        {
+            printk(XENLOG_ERR "ERROR: %s: Non-leaf cluster with core %s\n",
+                   dt_node_name(cluster), name);
+            return -EINVAL;
+        }
+
+        i++;
+    } while ( true );
+
+    if ( leaf && !has_cores )
+        printk(XENLOG_WARNING "WARNING: %s: empty cluster\n",
+               dt_node_name(cluster));
+
+    return 0;
+}
+
+static int __init parse_socket(const struct dt_device_node *socket)
+{
+    bool has_socket = false;
+    unsigned int package_id = 0;
+    int ret;
+
+    do {
+        const struct dt_device_node *c;
+        char name[20];
+
+        snprintf(name, sizeof(name), "socket%u", package_id);
+        c = dt_find_child_node_by_name(socket, name);
+
+        if ( !c )
+            break;
+
+        has_socket = true;
+        ret = parse_cluster(c, package_id, invalid_topo_id, 0);
+        if ( ret != 0 )
+            return ret;
+
+        package_id++;
+    } while ( true );
+
+    if ( !has_socket )
+        ret = parse_cluster(socket, 0, invalid_topo_id, 0);
+
+    return ret;
+}
+
+/*
+ * Generate cpu topology information when cpu-map node doesn't exist.
+ * It assumes that the cpu doesn't have SMT and all CPUs on a NUMA
+ * node belong to the same socket.
+ */
+static void __init fixup_topology(void)
+{
+    unsigned int cpu;
+    unsigned int clid = 0;
+    unsigned int pkgid = 0;
+
+    for_each_possible_cpu(cpu)
+    {
+        struct cpu_map *map = &cpu_map[cpu];
+
+        map->package_id = cpu_to_node(cpu);
+        if ( map->package_id != pkgid )
+        {
+            pkgid = map->package_id;
+            clid = 0;
+        }
+        map->cluster_id = clid++;
+        map->core_id = 0;
+        map->thread_id = 0;
+    }
+}
+
+int __init parse_dt_topology(void)
+{
+    const struct dt_device_node *cpus;
+    const struct dt_device_node *map;
+
+    cpus = dt_find_node_by_path("/cpus");
+    if ( !cpus )
+    {
+        printk(XENLOG_ERR "ERROR: No CPU information found in DT\n");
+        return -EINVAL;
+    }
+
+    map = dt_find_child_node_by_name(cpus, "cpu-map");
+    if ( !map )
+        return -ENOENT;
+
+    return parse_socket(map);
+}
+
+void __init dt_init_cpu_topology(void)
+{
+    unsigned int cpu;
+
+    BUG_ON(!acpi_disabled);
+    BUG_ON(!cpu_topology);
+
+    if ( parse_dt_topology() )
+        fixup_topology();
+
+    for_each_possible_cpu(cpu)
+        setup_siblings_masks(cpu);
+}
+
+/*
+ * Local variables:
+ * mode: C
+ * c-file-style: "BSD"
+ * c-basic-offset: 4
+ * tab-width: 4
+ * indent-tabs-mode: nil
+ * End:
+ */
diff --git a/xen/drivers/acpi/Kconfig b/xen/drivers/acpi/Kconfig
index e3f3d8f4b1..5277b7bf83 100644
--- a/xen/drivers/acpi/Kconfig
+++ b/xen/drivers/acpi/Kconfig
@@ -8,3 +8,6 @@ config ACPI_LEGACY_TABLES_LOOKUP
 config ACPI_NUMA
        bool
        select NUMA
+
+config ACPI_CPU_TOPOLOGY
+       bool
diff --git a/xen/drivers/acpi/Makefile b/xen/drivers/acpi/Makefile
index 477408afbe..bcdb1b5e1b 100644
--- a/xen/drivers/acpi/Makefile
+++ b/xen/drivers/acpi/Makefile
@@ -10,3 +10,4 @@ obj-$(CONFIG_PM_OP) += pm-op.o
 
 obj-$(CONFIG_X86) += hwregs.o
 obj-$(CONFIG_X86) += reboot.o
+obj-$(CONFIG_ACPI_CPU_TOPOLOGY) += topology.init.o
diff --git a/xen/drivers/acpi/topology.c b/xen/drivers/acpi/topology.c
new file mode 100644
index 0000000000..6bd2d96ebb
--- /dev/null
+++ b/xen/drivers/acpi/topology.c
@@ -0,0 +1,38 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+
+#include <xen/acpi.h>
+#include <xen/cpu-topology.h>
+#include <xen/cpumask.h>
+#include <xen/init.h>
+
+/*
+ * TODO: Populate the topology information by scanning the ACPI
+ *       PPTT (Processor Properties Topology Table).
+ */
+void __init acpi_init_cpu_topology(void)
+{
+    unsigned int cpu;
+
+    /*
+     * Generate temporary cpu topology information for now.
+     * It assumes that the cpu doesn't have SMT and all CPUs
+     * belong to the same socket.
+     */
+    for_each_possible_cpu(cpu)
+    {
+        struct cpu_topology *topo = &cpu_topology[cpu];
+
+        cpumask_set_cpu(cpu, topo->thread_sibling);
+        cpumask_copy(topo->core_sibling, &cpu_possible_map);
+    }
+}
+
+/*
+ * Local variables:
+ * mode: C
+ * c-file-style: "BSD"
+ * c-basic-offset: 4
+ * tab-width: 4
+ * indent-tabs-mode: nil
+ * End:
+ */
diff --git a/xen/include/xen/acpi.h b/xen/include/xen/acpi.h
index 2fdf38cf74..bd982ee836 100644
--- a/xen/include/xen/acpi.h
+++ b/xen/include/xen/acpi.h
@@ -135,6 +135,16 @@ static inline int acpi_boot_table_init(void)
 
 #endif         /*!CONFIG_ACPI*/
 
+#ifdef CONFIG_ACPI_CPU_TOPOLOGY
+
+void acpi_init_cpu_topology(void);
+
+#else /* CONFIG_ACPI_CPU_TOPOLOGY */
+
+static inline void acpi_init_cpu_topology(void) {}
+
+#endif /* CONFIG_ACPI_CPU_TOPOLOGY */
+
 int get_cpu_id(u32 acpi_id);
 
 unsigned int acpi_register_gsi (u32 gsi, int edge_level, int active_high_low);
diff --git a/xen/include/xen/cpu-topology.h b/xen/include/xen/cpu-topology.h
new file mode 100644
index 0000000000..f64820febf
--- /dev/null
+++ b/xen/include/xen/cpu-topology.h
@@ -0,0 +1,35 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+
+#ifndef XEN_CPU_TOPOLOGY_H
+#define XEN_CPU_TOPOLOGY_H
+
+#include <xen/cpumask.h>
+
+#ifdef CONFIG_GENERIC_CPU_TOPOLOGY
+
+struct cpu_topology {
+    cpumask_var_t thread_sibling;
+    cpumask_var_t core_sibling;
+    cpumask_var_t cluster_sibling;
+};
+
+extern struct cpu_topology *cpu_topology;
+void init_cpu_topology(void);
+
+#else /* CONFIG_GENERIC_CPU_TOPOLOGY */
+
+#define cpu_topology ((struct cpu_topology *)NULL)
+static inline void init_cpu_topology(void) {}
+
+#endif /* CONFIG_GENERIC_CPU_TOPOLOGY */
+
+#endif /* XEN_CPU_TOPOLOGY_H */
+
+/*
+ * Local variables:
+ * mode: C
+ * c-file-style: "BSD"
+ * c-basic-offset: 4
+ * indent-tabs-mode: nil
+ * End:
+ */
diff --git a/xen/include/xen/dt-cpu-topology.h 
b/xen/include/xen/dt-cpu-topology.h
new file mode 100644
index 0000000000..cb8a266479
--- /dev/null
+++ b/xen/include/xen/dt-cpu-topology.h
@@ -0,0 +1,29 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+
+#ifndef XEN_DT_CPU_TOPOLOGY_H
+#define XEN_DT_CPU_TOPOLOGY_H
+
+struct dt_device_node;
+
+#ifdef CONFIG_DT_CPU_TOPOLOGY
+
+void map_cpu_to_dt_node(unsigned int cpu, struct dt_device_node *cpu_node);
+void dt_init_cpu_topology(void);
+
+#else /* CONFIG_DT_CPU_TOPOLOGY */
+
+static inline void map_cpu_to_dt_node(unsigned int cpu,
+                                      struct dt_device_node *cpu_node) {}
+
+#endif /* CONFIG_DT_CPU_TOPOLOGY */
+
+#endif /* XEN_DT_CPU_TOPOLOGY_H */
+
+/*
+ * Local variables:
+ * mode: C
+ * c-file-style: "BSD"
+ * c-basic-offset: 4
+ * indent-tabs-mode: nil
+ * End:
+ */
-- 
2.43.0