[PATCH 2/4] arm64: topology: Add support for topology DT bindings

[lorenzo.pieralisi@arm.com (Lorenzo Pieralisi)]

On Tue, Apr 22, 2014 at 09:21:16PM +0100, Mark Brown wrote:
> From: Mark Brown <broonie@linaro.org>
> 
> Add support for parsing the explicit topology bindings to discover the
> topology of the system.
> 
> Since it is not currently clear how to map multi-level clusters for the
> scheduler all leaf clusters are presented to the scheduler at the same
> level. This should be enough to provide good support for current systems.
> 
> Signed-off-by: Mark Brown <broonie@linaro.org>
> ---
>  arch/arm64/kernel/topology.c | 203 +++++++++++++++++++++++++++++++++++++++++--
>  1 file changed, 195 insertions(+), 8 deletions(-)
> 
> diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c
> index ff662b23af5f..a326f5b37546 100644
> --- a/arch/arm64/kernel/topology.c
> +++ b/arch/arm64/kernel/topology.c
> @@ -17,10 +17,191 @@
>  #include <linux/percpu.h>
>  #include <linux/node.h>
>  #include <linux/nodemask.h>
> +#include <linux/of.h>
>  #include <linux/sched.h>
>  
>  #include <asm/topology.h>
>  
> +static int __init get_cpu_for_node(struct device_node *node)
> +{
> +	struct device_node *cpu_node;
> +	int cpu;
> +
> +	cpu_node = of_parse_phandle(node, "cpu", 0);
> +	if (!cpu_node)
> +		return -1;
> +
> +	for_each_possible_cpu(cpu)
> +		if (of_get_cpu_node(cpu, NULL) == cpu_node) {
> +			of_node_put(cpu_node);
> +			return cpu;
> +		}
> +
> +	pr_crit("Unable to find CPU node for %s\n", cpu_node->full_name);
> +
> +	of_node_put(cpu_node);
> +	return -1;
> +}
> +
> +static int __init parse_core(struct device_node *core, int cluster_id,
> +			     int core_id)
> +{
> +	char name[10];
> +	bool leaf = true;
> +	int i = 0;
> +	int cpu;
> +	struct device_node *t;
> +
> +	do {
> +		snprintf(name, sizeof(name), "thread%d", i);
> +		t = of_get_child_by_name(core, name);
> +		if (t) {
> +			leaf = false;
> +			cpu = get_cpu_for_node(t);
> +			if (cpu >= 0) {
> +				cpu_topology[cpu].cluster_id = cluster_id;
> +				cpu_topology[cpu].core_id = core_id;
> +				cpu_topology[cpu].thread_id = i;
> +			} else {
> +				pr_err("%s: Can't get CPU for thread\n",
> +				       t->full_name);
> +				of_node_put(t);
> +				return -EINVAL;
> +			}
> +			of_node_put(t);
> +		}
> +		i++;
> +	} while (t);
> +
> +	cpu = get_cpu_for_node(core);
> +	if (cpu >= 0) {
> +		if (!leaf) {
> +			pr_err("%s: Core has both threads and CPU\n",
> +			       core->full_name);
> +			return -EINVAL;
> +		}
> +
> +		cpu_topology[cpu].cluster_id = cluster_id;
> +		cpu_topology[cpu].core_id = core_id;
> +	} else if (leaf) {
> +		pr_err("%s: Can't get CPU for leaf core\n", core->full_name);
> +		return -EINVAL;
> +	}
> +
> +	return 0;
> +}
> +
> +static int __init parse_cluster(struct device_node *cluster, int depth)
> +{
> +	char name[10];
> +	bool leaf = true;
> +	bool has_cores = false;
> +	struct device_node *c;
> +	static int cluster_id __initdata;
> +	int core_id = 0;
> +	int i, ret;
> +
> +	/*
> +	 * 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.
> +	 */
> +	i = 0;
> +	do {
> +		snprintf(name, sizeof(name), "cluster%d", i);
> +		c = of_get_child_by_name(cluster, name);
> +		if (c) {
> +			leaf = false;
> +			ret = parse_cluster(c, depth + 1);
> +			of_node_put(c);
> +			if (ret != 0)
> +				return ret;
> +		}
> +		i++;
> +	} while (c);
> +
> +	/* Now check for cores */
> +	i = 0;
> +	do {
> +		snprintf(name, sizeof(name), "core%d", i);
> +		c = of_get_child_by_name(cluster, name);
> +		if (c) {
> +			has_cores = true;
> +
> +			if (depth == 0) {
> +				pr_err("%s: cpu-map children should be clusters\n",
> +				       c->full_name);
> +				of_node_put(c);
> +				return -EINVAL;
> +			}
> +
> +			if (leaf) {
> +				ret = parse_core(c, cluster_id, core_id++);
> +			} else {
> +				pr_err("%s: Non-leaf cluster with core %s\n",
> +				       cluster->full_name, name);
> +				ret = -EINVAL;
> +			}
> +
> +			of_node_put(c);
> +			if (ret != 0)
> +				return ret;
> +		}
> +		i++;
> +	} while (c);
> +
> +	if (leaf && !has_cores)
> +		pr_warn("%s: empty cluster\n", cluster->full_name);
> +
> +	if (leaf)
> +		cluster_id++;
> +
> +	return 0;
> +}
> +
> +static int __init parse_dt_topology(void)
> +{
> +	struct device_node *cn, *map;
> +	int ret = 0;
> +	int cpu;
> +
> +	cn = of_find_node_by_path("/cpus");
> +	if (!cn) {
> +		pr_err("No CPU information found in DT\n");
> +		return 0;
> +	}
> +
> +	/*
> +	 * When topology is provided cpu-map is essentially a root
> +	 * cluster with restricted subnodes.
> +	 */
> +	map = of_get_child_by_name(cn, "cpu-map");
> +	if (!map)
> +		goto out;
> +
> +	ret = parse_cluster(map, 0);
> +	if (ret != 0)
> +		goto out_map;
> +
> +	/*
> +	 * Check that all cores are in the topology; the SMP code will
> +	 * only mark cores described in the DT as possible.
> +	 */
> +	for_each_possible_cpu(cpu) {
> +		if (cpu_topology[cpu].cluster_id == -1) {
> +			pr_err("CPU%d: No topology information specified\n",
> +			       cpu);
> +			ret = -EINVAL;
> +		}
> +	}
> +
> +out_map:
> +	of_node_put(map);
> +out:
> +	of_node_put(cn);
> +	return ret;
> +}
> +
>  /*
>   * cpu topology table
>   */
> @@ -39,8 +220,7 @@ static void update_siblings_masks(unsigned int cpuid)
>  
>  	if (cpuid_topo->cluster_id == -1) {
>  		/*
> -		 * DT does not contain topology information for this cpu
> -		 * reset it to default behaviour
> +		 * DT does not contain topology information for this cpu.
>  		 */
>  		pr_debug("CPU%u: No topology information configured\n", cpuid);
>  		return;
> @@ -71,15 +251,10 @@ void store_cpu_topology(unsigned int cpuid)
>  	update_siblings_masks(cpuid);
>  }
>  
> -/*
> - * init_cpu_topology is called at boot when only one cpu is running
> - * which prevent simultaneous write access to cpu_topology array
> - */
> -void __init init_cpu_topology(void)
> +static void __init reset_cpu_topology(void)
>  {
>  	unsigned int cpu;
>  
> -	/* init core mask and power*/
>  	for_each_possible_cpu(cpu) {
>  		struct cpu_topology *cpu_topo = &cpu_topology[cpu];
>  
> @@ -93,3 +268,15 @@ void __init init_cpu_topology(void)
>  		cpumask_set_cpu(cpu, &cpu_topo->thread_sibling);
>  	}
>  }
> +
> +void __init init_cpu_topology(void)
> +{
> +	reset_cpu_topology();
> +
> +	/*
> +	 * Discard anything that was parsed if we hit an error so we
> +	 * don't use partial information.
> +	 */
> +	if (parse_dt_topology())
> +		reset_cpu_topology();
> +}

I tested it and tried to clobber it a bit with some DT changes, it seems
fine.

Apart from an ultra-minor decoration change (attached):

Reviewed-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: 0001-arm64-kernel-topology-minor-cosmetic-changes.patch
Type: text/x-diff
Size: 1008 bytes
Desc: not available
URL: <http://lists.infradead.org/pipermail/linux-arm-kernel/attachments/20140424/75fec107/attachment.bin>