Merge tag 'arch-cache-topo-5.20' of git://git.kernel.org/pub/scm/linux/kernel/git/sudeep.holla/linux into driver-core-next

Sudeep writes:

cacheinfo and arch_topology updates for v5.20

These are updates to fix some discrepancies we have in the CPU topology
parsing from the device tree /cpu-map node and the divergence from the
behaviour on a ACPI enabled platform. The expectation is that both DT
and ACPI enabled systems must present consistent view of the CPU topology.

The current assignment of generated cluster count as the physical package
identifier for each CPU is wrong. The device tree bindings for CPU
topology supports sockets to infer the socket or physical package
identifier for a given CPU. It is now being made use of you address the
issue. These updates also assigns the cluster identifier as parsed from
the device tree cluster nodes within /cpu-map without support for
nesting of the clusters as there are no such reported/known platforms.

In order to be on par with ACPI PPTT physical package/socket support,
these updates also include support for socket nodes in /cpu-map.

The only exception is that the last level cache id information can be
inferred from the same ACPI PPTT while we need to parse CPU cache nodes
in the device tree. The cacheinfo changes here is to enable the re-use
of the cacheinfo to detect the cache attributes for all the CPU quite
early even before the scondardaries are booted so that the information
can be used to build the schedular domains especially the last level
cache(LLC).

* tag 'arch-cache-topo-5.20' of git://git.kernel.org/pub/scm/linux/kernel/git/sudeep.holla/linux: (21 commits)
  ACPI: Remove the unused find_acpi_cpu_cache_topology()
  arch_topology: Warn that topology for nested clusters is not supported
  arch_topology: Add support for parsing sockets in /cpu-map
  arch_topology: Set cluster identifier in each core/thread from /cpu-map
  arch_topology: Limit span of cpu_clustergroup_mask()
  arch_topology: Don't set cluster identifier as physical package identifier
  arch_topology: Avoid parsing through all the CPUs once a outlier CPU is found
  arch_topology: Check for non-negative value rather than -1 for IDs validity
  arch_topology: Set thread sibling cpumask only within the cluster
  arch_topology: Drop LLC identifier stash from the CPU topology
  arm64: topology: Remove redundant setting of llc_id in CPU topology
  arch_topology: Use the last level cache information from the cacheinfo
  arch_topology: Add support to parse and detect cache attributes
  cacheinfo: Align checks in cache_shared_cpu_map_{setup,remove} for readability
  cacheinfo: Use cache identifiers to check if the caches are shared if available
  cacheinfo: Allow early detection and population of cache attributes
  cacheinfo: Add support to check if last level cache(LLC) is valid or shared
  cacheinfo: Move cache_leaves_are_shared out of CONFIG_OF
  cacheinfo: Add helper to access any cache index for a given CPU
  cacheinfo: Use of_cpu_device_node_get instead cpu_dev->of_node
  ...

Author: gregkh

arch/arm64/kernel/topology.c

@@ -89,8 +89,6 @@ int __init parse_acpi_topology(void)
 		return 0;
 
 	for_each_possible_cpu(cpu) {
-		int i, cache_id;
-
 		topology_id = find_acpi_cpu_topology(cpu, 0);
 		if (topology_id < 0)
 			return topology_id;
@@ -107,18 +105,6 @@ int __init parse_acpi_topology(void)
 		cpu_topology[cpu].cluster_id = topology_id;
 		topology_id = find_acpi_cpu_topology_package(cpu);
 		cpu_topology[cpu].package_id = topology_id;
-
-		i = acpi_find_last_cache_level(cpu);
-
-		if (i > 0) {
-			/*
-			 * this is the only part of cpu_topology that has
-			 * a direct relationship with the cache topology
-			 */
-			cache_id = find_acpi_cpu_cache_topology(cpu, i);
-			if (cache_id > 0)
-				cpu_topology[cpu].llc_id = cache_id;
-		}
 	}
 
 	return 0;

drivers/acpi/pptt.c

@@ -437,7 +437,8 @@ static void cache_setup_acpi_cpu(struct acpi_table_header *table,
 		pr_debug("found = %p %p\n", found_cache, cpu_node);
 		if (found_cache)
 			update_cache_properties(this_leaf, found_cache,
-			                        cpu_node, table->revision);
+						ACPI_TO_POINTER(ACPI_PTR_DIFF(cpu_node, table)),
+						table->revision);
 
 		index++;
 	}
@@ -690,43 +691,6 @@ int find_acpi_cpu_topology(unsigned int cpu, int level)
 	return find_acpi_cpu_topology_tag(cpu, level, 0);
 }
 
-/**
- * find_acpi_cpu_cache_topology() - Determine a unique cache topology value
- * @cpu: Kernel logical CPU number
- * @level: The cache level for which we would like a unique ID
- *
- * Determine a unique ID for each unified cache in the system
- *
- * Return: -ENOENT if the PPTT doesn't exist, or the CPU cannot be found.
- * Otherwise returns a value which represents a unique topological feature.
- */
-int find_acpi_cpu_cache_topology(unsigned int cpu, int level)
-{
-	struct acpi_table_header *table;
-	struct acpi_pptt_cache *found_cache;
-	acpi_status status;
-	u32 acpi_cpu_id = get_acpi_id_for_cpu(cpu);
-	struct acpi_pptt_processor *cpu_node = NULL;
-	int ret = -1;
-
-	status = acpi_get_table(ACPI_SIG_PPTT, 0, &table);
-	if (ACPI_FAILURE(status)) {
-		acpi_pptt_warn_missing();
-		return -ENOENT;
-	}
-
-	found_cache = acpi_find_cache_node(table, acpi_cpu_id,
-					   CACHE_TYPE_UNIFIED,
-					   level,
-					   &cpu_node);
-	if (found_cache)
-		ret = ACPI_PTR_DIFF(cpu_node, table);
-
-	acpi_put_table(table);
-
-	return ret;
-}
-
 /**
  * find_acpi_cpu_topology_package() - Determine a unique CPU package value
  * @cpu: Kernel logical CPU number

drivers/base/arch_topology.c

@@ -7,6 +7,7 @@
  */
 
 #include <linux/acpi.h>
+#include <linux/cacheinfo.h>
 #include <linux/cpu.h>
 #include <linux/cpufreq.h>
 #include <linux/device.h>
@@ -496,7 +497,7 @@ static int __init get_cpu_for_node(struct device_node *node)
 }
 
 static int __init parse_core(struct device_node *core, int package_id,
-			     int core_id)
+			     int cluster_id, int core_id)
 {
 	char name[20];
 	bool leaf = true;
@@ -512,6 +513,7 @@ static int __init parse_core(struct device_node *core, int package_id,
 			cpu = get_cpu_for_node(t);
 			if (cpu >= 0) {
 				cpu_topology[cpu].package_id = package_id;
+				cpu_topology[cpu].cluster_id = cluster_id;
 				cpu_topology[cpu].core_id = core_id;
 				cpu_topology[cpu].thread_id = i;
 			} else if (cpu != -ENODEV) {
@@ -533,6 +535,7 @@ static int __init parse_core(struct device_node *core, int package_id,
 		}
 
 		cpu_topology[cpu].package_id = package_id;
+		cpu_topology[cpu].cluster_id = cluster_id;
 		cpu_topology[cpu].core_id = core_id;
 	} else if (leaf && cpu != -ENODEV) {
 		pr_err("%pOF: Can't get CPU for leaf core\n", core);
@@ -542,13 +545,13 @@ static int __init parse_core(struct device_node *core, int package_id,
 	return 0;
 }
 
-static int __init parse_cluster(struct device_node *cluster, int depth)
+static int __init parse_cluster(struct device_node *cluster, int package_id,
+				int cluster_id, int depth)
 {
 	char name[20];
 	bool leaf = true;
 	bool has_cores = false;
 	struct device_node *c;
-	static int package_id __initdata;
 	int core_id = 0;
 	int i, ret;
 
@@ -563,7 +566,9 @@ static int __init parse_cluster(struct device_node *cluster, int depth)
 		c = of_get_child_by_name(cluster, name);
 		if (c) {
 			leaf = false;
-			ret = parse_cluster(c, depth + 1);
+			ret = parse_cluster(c, package_id, i, depth + 1);
+			if (depth > 0)
+				pr_warn("Topology for clusters of clusters not yet supported\n");
 			of_node_put(c);
 			if (ret != 0)
 				return ret;
@@ -587,7 +592,8 @@ static int __init parse_cluster(struct device_node *cluster, int depth)
 			}
 
 			if (leaf) {
-				ret = parse_core(c, package_id, core_id++);
+				ret = parse_core(c, package_id, cluster_id,
+						 core_id++);
 			} else {
 				pr_err("%pOF: Non-leaf cluster with core %s\n",
 				       cluster, name);
@@ -604,10 +610,33 @@ static int __init parse_cluster(struct device_node *cluster, int depth)
 	if (leaf && !has_cores)
 		pr_warn("%pOF: empty cluster\n", cluster);
 
-	if (leaf)
+	return 0;
+}
+
+static int __init parse_socket(struct device_node *socket)
+{
+	char name[20];
+	struct device_node *c;
+	bool has_socket = false;
+	int package_id = 0, ret;
+
+	do {
+		snprintf(name, sizeof(name), "socket%d", package_id);
+		c = of_get_child_by_name(socket, name);
+		if (c) {
+			has_socket = true;
+			ret = parse_cluster(c, package_id, -1, 0);
+			of_node_put(c);
+			if (ret != 0)
+				return ret;
+		}
 		package_id++;
+	} while (c);
 
-	return 0;
+	if (!has_socket)
+		ret = parse_cluster(socket, 0, -1, 0);
+
+	return ret;
 }
 
 static int __init parse_dt_topology(void)
@@ -630,7 +659,7 @@ static int __init parse_dt_topology(void)
 	if (!map)
 		goto out;
 
-	ret = parse_cluster(map, 0);
+	ret = parse_socket(map);
 	if (ret != 0)
 		goto out_map;
 
@@ -641,8 +670,10 @@ static int __init parse_dt_topology(void)
 	 * only mark cores described in the DT as possible.
 	 */
 	for_each_possible_cpu(cpu)
-		if (cpu_topology[cpu].package_id == -1)
+		if (cpu_topology[cpu].package_id < 0) {
 			ret = -EINVAL;
+			break;
+		}
 
 out_map:
 	of_node_put(map);
@@ -667,7 +698,8 @@ const struct cpumask *cpu_coregroup_mask(int cpu)
 		/* not numa in package, lets use the package siblings */
 		core_mask = &cpu_topology[cpu].core_sibling;
 	}
-	if (cpu_topology[cpu].llc_id != -1) {
+
+	if (last_level_cache_is_valid(cpu)) {
 		if (cpumask_subset(&cpu_topology[cpu].llc_sibling, core_mask))
 			core_mask = &cpu_topology[cpu].llc_sibling;
 	}
@@ -686,6 +718,14 @@ const struct cpumask *cpu_coregroup_mask(int cpu)
 
 const struct cpumask *cpu_clustergroup_mask(int cpu)
 {
+	/*
+	 * Forbid cpu_clustergroup_mask() to span more or the same CPUs as
+	 * cpu_coregroup_mask().
+	 */
+	if (cpumask_subset(cpu_coregroup_mask(cpu),
+			   &cpu_topology[cpu].cluster_sibling))
+		return get_cpu_mask(cpu);
+
 	return &cpu_topology[cpu].cluster_sibling;
 }
 
@@ -698,23 +738,25 @@ void update_siblings_masks(unsigned int cpuid)
 	for_each_online_cpu(cpu) {
 		cpu_topo = &cpu_topology[cpu];
 
-		if (cpu_topo->llc_id != -1 && cpuid_topo->llc_id == cpu_topo->llc_id) {
+		if (last_level_cache_is_shared(cpu, cpuid)) {
 			cpumask_set_cpu(cpu, &cpuid_topo->llc_sibling);
 			cpumask_set_cpu(cpuid, &cpu_topo->llc_sibling);
 		}
 
 		if (cpuid_topo->package_id != cpu_topo->package_id)
 			continue;
 
-		if (cpuid_topo->cluster_id == cpu_topo->cluster_id &&
-		    cpuid_topo->cluster_id != -1) {
+		cpumask_set_cpu(cpuid, &cpu_topo->core_sibling);
+		cpumask_set_cpu(cpu, &cpuid_topo->core_sibling);
+
+		if (cpuid_topo->cluster_id != cpu_topo->cluster_id)
+			continue;
+
+		if (cpuid_topo->cluster_id >= 0) {
 			cpumask_set_cpu(cpu, &cpuid_topo->cluster_sibling);
 			cpumask_set_cpu(cpuid, &cpu_topo->cluster_sibling);
 		}
 
-		cpumask_set_cpu(cpuid, &cpu_topo->core_sibling);
-		cpumask_set_cpu(cpu, &cpuid_topo->core_sibling);
-
 		if (cpuid_topo->core_id != cpu_topo->core_id)
 			continue;
 
@@ -750,7 +792,6 @@ void __init reset_cpu_topology(void)
 		cpu_topo->core_id = -1;
 		cpu_topo->cluster_id = -1;
 		cpu_topo->package_id = -1;
-		cpu_topo->llc_id = -1;
 
 		clear_cpu_topology(cpu);
 	}
@@ -780,15 +821,28 @@ __weak int __init parse_acpi_topology(void)
 #if defined(CONFIG_ARM64) || defined(CONFIG_RISCV)
 void __init init_cpu_topology(void)
 {
+	int ret, cpu;
+
 	reset_cpu_topology();
+	ret = parse_acpi_topology();
+	if (!ret)
+		ret = of_have_populated_dt() && parse_dt_topology();
 
-	/*
-	 * Discard anything that was parsed if we hit an error so we
-	 * don't use partial information.
-	 */
-	if (parse_acpi_topology())
-		reset_cpu_topology();
-	else if (of_have_populated_dt() && parse_dt_topology())
+	if (ret) {
+		/*
+		 * Discard anything that was parsed if we hit an error so we
+		 * don't use partial information.
+		 */
 		reset_cpu_topology();
+		return;
+	}
+
+	for_each_possible_cpu(cpu) {
+		ret = detect_cache_attributes(cpu);
+		if (ret) {
+			pr_info("Early cacheinfo failed, ret = %d\n", ret);
+			break;
+		}
+	}
 }
 #endif