topology: Represent clusters of CPUs within a die

Both ACPI and DT provide the ability to describe additional layers of
topology between that of individual cores and higher level constructs
such as the level at which the last level cache is shared.
In ACPI this can be represented in PPTT as a Processor Hierarchy
Node Structure [1] that is the parent of the CPU cores and in turn
has a parent Processor Hierarchy Nodes Structure representing
a higher level of topology.

For example Kunpeng 920 has 6 or 8 clusters in each NUMA node, and each
cluster has 4 cpus. All clusters share L3 cache data, but each cluster
has local L3 tag. On the other hand, each clusters will share some
internal system bus.

+-----------------------------------+                          +---------+
|  +------+    +------+             +--------------------------+         |
|  | CPU0 |    | cpu1 |             |    +-----------+         |         |
|  +------+    +------+             |    |           |         |         |
|                                   +----+    L3     |         |         |
|  +------+    +------+   cluster   |    |    tag    |         |         |
|  | CPU2 |    | CPU3 |             |    |           |         |         |
|  +------+    +------+             |    +-----------+         |         |
|                                   |                          |         |
+-----------------------------------+                          |         |
+-----------------------------------+                          |         |
|  +------+    +------+             +--------------------------+         |
|  |      |    |      |             |    +-----------+         |         |
|  +------+    +------+             |    |           |         |         |
|                                   |    |    L3     |         |         |
|  +------+    +------+             +----+    tag    |         |         |
|  |      |    |      |             |    |           |         |         |
|  +------+    +------+             |    +-----------+         |         |
|                                   |                          |         |
+-----------------------------------+                          |   L3    |
                                                               |   data  |
+-----------------------------------+                          |         |
|  +------+    +------+             |    +-----------+         |         |
|  |      |    |      |             |    |           |         |         |
|  +------+    +------+             +----+    L3     |         |         |
|                                   |    |    tag    |         |         |
|  +------+    +------+             |    |           |         |         |
|  |      |    |      |             |    +-----------+         |         |
|  +------+    +------+             +--------------------------+         |
+-----------------------------------|                          |         |
+-----------------------------------|                          |         |
|  +------+    +------+             +--------------------------+         |
|  |      |    |      |             |    +-----------+         |         |
|  +------+    +------+             |    |           |         |         |
|                                   +----+    L3     |         |         |
|  +------+    +------+             |    |    tag    |         |         |
|  |      |    |      |             |    |           |         |         |
|  +------+    +------+             |    +-----------+         |         |
|                                   |                          |         |
+-----------------------------------+                          |         |
+-----------------------------------+                          |         |
|  +------+    +------+             +--------------------------+         |
|  |      |    |      |             |   +-----------+          |         |
|  +------+    +------+             |   |           |          |         |
|                                   |   |    L3     |          |         |
|  +------+    +------+             +---+    tag    |          |         |
|  |      |    |      |             |   |           |          |         |
|  +------+    +------+             |   +-----------+          |         |
|                                   |                          |         |
+-----------------------------------+                          |         |
+-----------------------------------+                          |         |
|  +------+    +------+             +--------------------------+         |
|  |      |    |      |             |  +-----------+           |         |
|  +------+    +------+             |  |           |           |         |
|                                   |  |    L3     |           |         |
|  +------+    +------+             +--+    tag    |           |         |
|  |      |    |      |             |  |           |           |         |
|  +------+    +------+             |  +-----------+           |         |
|                                   |                          +---------+
+-----------------------------------+

That means spreading tasks among clusters will bring more bandwidth
while packing tasks within one cluster will lead to smaller cache
synchronization latency. So both kernel and userspace will have
a chance to leverage this topology to deploy tasks accordingly to
achieve either smaller cache latency within one cluster or an even
distribution of load among clusters for higher throughput.

This patch exposes cluster topology to both kernel and userspace.
Libraried like hwloc will know cluster by cluster_cpus and related
sysfs attributes. PoC of HWLOC support at [2].

Note this patch only handle the ACPI case.

Special consideration is needed for SMT processors, where it is
necessary to move 2 levels up the hierarchy from the leaf nodes
(thus skipping the processor core level).

Note that arm64 / ACPI does not provide any means of identifying
a die level in the topology but that may be unrelate to the cluster
level.

[1] ACPI Specification 6.3 - section 5.2.29.1 processor hierarchy node
    structure (Type 0)
[2] https://github.com/hisilicon/hwloc/tree/linux-cluster

Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Signed-off-by: Tian Tao <tiantao6@hisilicon.com>
Signed-off-by: Barry Song <song.bao.hua@hisilicon.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20210924085104.44806-2-21cnbao@gmail.com

3 files changed, 16 insertions, 0 deletions

diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index 974d497a897d..fbc2146050a4 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -1353,6 +1353,7 @@ static inline int lpit_read_residency_count_address(u64 *address)
 #ifdef CONFIG_ACPI_PPTT
 int acpi_pptt_cpu_is_thread(unsigned int cpu);
 int find_acpi_cpu_topology(unsigned int cpu, int level);
+int find_acpi_cpu_topology_cluster(unsigned int cpu);
 int find_acpi_cpu_topology_package(unsigned int cpu);
 int find_acpi_cpu_topology_hetero_id(unsigned int cpu);
 int find_acpi_cpu_cache_topology(unsigned int cpu, int level);
@@ -1365,6 +1366,10 @@ static inline int find_acpi_cpu_topology(unsigned int cpu, int level)
 {
 	return -EINVAL;
 }
+static inline int find_acpi_cpu_topology_cluster(unsigned int cpu)
+{
+	return -EINVAL;
+}
 static inline int find_acpi_cpu_topology_package(unsigned int cpu)
 {
 	return -EINVAL;
diff --git a/include/linux/arch_topology.h b/include/linux/arch_topology.h
index f180240dc95f..b97cea83b25e 100644
--- a/include/linux/arch_topology.h
+++ b/include/linux/arch_topology.h
@@ -62,10 +62,12 @@ void topology_set_thermal_pressure(const struct cpumask *cpus,
 struct cpu_topology {
 	int thread_id;
 	int core_id;
+	int cluster_id;
 	int package_id;
 	int llc_id;
 	cpumask_t thread_sibling;
 	cpumask_t core_sibling;
+	cpumask_t cluster_sibling;
 	cpumask_t llc_sibling;
 };
 
@@ -73,13 +75,16 @@ struct cpu_topology {
 extern struct cpu_topology cpu_topology[NR_CPUS];
 
 #define topology_physical_package_id(cpu)	(cpu_topology[cpu].package_id)
+#define topology_cluster_id(cpu)	(cpu_topology[cpu].cluster_id)
 #define topology_core_id(cpu)		(cpu_topology[cpu].core_id)
 #define topology_core_cpumask(cpu)	(&cpu_topology[cpu].core_sibling)
 #define topology_sibling_cpumask(cpu)	(&cpu_topology[cpu].thread_sibling)
+#define topology_cluster_cpumask(cpu)	(&cpu_topology[cpu].cluster_sibling)
 #define topology_llc_cpumask(cpu)	(&cpu_topology[cpu].llc_sibling)
 void init_cpu_topology(void);
 void store_cpu_topology(unsigned int cpuid);
 const struct cpumask *cpu_coregroup_mask(int cpu);
+const struct cpumask *cpu_clustergroup_mask(int cpu);
 void update_siblings_masks(unsigned int cpu);
 void remove_cpu_topology(unsigned int cpuid);
 void reset_cpu_topology(void);
diff --git a/include/linux/topology.h b/include/linux/topology.h
index 7634cd737061..80d27d717631 100644
--- a/include/linux/topology.h
+++ b/include/linux/topology.h
@@ -186,6 +186,9 @@ static inline int cpu_to_mem(int cpu)
 #ifndef topology_die_id
 #define topology_die_id(cpu)			((void)(cpu), -1)
 #endif
+#ifndef topology_cluster_id
+#define topology_cluster_id(cpu)		((void)(cpu), -1)
+#endif
 #ifndef topology_core_id
 #define topology_core_id(cpu)			((void)(cpu), 0)
 #endif
@@ -195,6 +198,9 @@ static inline int cpu_to_mem(int cpu)
 #ifndef topology_core_cpumask
 #define topology_core_cpumask(cpu)		cpumask_of(cpu)
 #endif
+#ifndef topology_cluster_cpumask
+#define topology_cluster_cpumask(cpu)		cpumask_of(cpu)
+#endif
 #ifndef topology_die_cpumask
 #define topology_die_cpumask(cpu)		cpumask_of(cpu)
 #endif