ARM: sched: Use device-tree to provide fast/slow CPU list for HMP

We can't rely on Kconfig options to set the fast and slow CPU lists for
HMP scheduling if we want a single kernel binary to support multiple
devices with different CPU topology. E.g. TC2 (ARM's Test-Chip-2
big.LITTLE system), Fast Models, or even non big.LITTLE devices.

This patch adds the function arch_get_fast_and_slow_cpus() to generate
the lists at run-time by parsing the CPU nodes in device-tree; it
assumes slow cores are A7s and everything else is fast. The function
still supports the old Kconfig options as this is useful for testing the
HMP scheduler on devices without big.LITTLE.

This patch is reuse of a patch by Jon Medhurst <tixy@linaro.org> with a
few bits left out.

Signed-off-by: Morten Rasmussen <Morten.Rasmussen@arm.com>

diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 99d41f9633bbe839e1c32c0d1f6b6113b4c978dc..bc19fa61b907bac5ebef95a0ec91375450be94d2 100644 (file)
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -1528,13 +1528,15 @@ config HMP_FAST_CPU_MASK
        string "HMP scheduler fast CPU mask"
        depends on SCHED_HMP
        help
-          Specify the cpuids of the fast CPUs in the system as a list string,
+          Leave empty to use device tree information.
+         Specify the cpuids of the fast CPUs in the system as a list string,
          e.g. cpuid 0+1 should be specified as 0-1.
 
 config HMP_SLOW_CPU_MASK
        string "HMP scheduler slow CPU mask"
        depends on SCHED_HMP
        help
+         Leave empty to use device tree information.
          Specify the cpuids of the slow CPUs in the system as a list string,
          e.g. cpuid 0+1 should be specified as 0-1.
 

diff --git a/arch/arm/kernel/topology.c b/arch/arm/kernel/topology.c
index c5a59546a256c9b3720022265eb08fcde0dc4f68..e6e430a567c08516d09638127c432ebc2a2c4b50 100644 (file)
--- a/arch/arm/kernel/topology.c
+++ b/arch/arm/kernel/topology.c
@@ -289,6 +289,75 @@ void store_cpu_topology(unsigned int cpuid)
                cpu_topology[cpuid].socket_id, mpidr);
 }
 
+
+#ifdef CONFIG_SCHED_HMP
+
+static const char * const little_cores[] = {
+       "arm,cortex-a7",
+       NULL,
+};
+
+static bool is_little_cpu(struct device_node *cn)
+{
+       const char * const *lc;
+       for (lc = little_cores; *lc; lc++)
+               if (of_device_is_compatible(cn, *lc))
+                       return true;
+       return false;
+}
+
+void __init arch_get_fast_and_slow_cpus(struct cpumask *fast,
+                                       struct cpumask *slow)
+{
+       struct device_node *cn = NULL;
+       int cpu = 0;
+
+       cpumask_clear(fast);
+       cpumask_clear(slow);
+
+       /*
+        * Use the config options if they are given. This helps testing
+        * HMP scheduling on systems without a big.LITTLE architecture.
+        */
+       if (strlen(CONFIG_HMP_FAST_CPU_MASK) && strlen(CONFIG_HMP_SLOW_CPU_MASK)) {
+               if (cpulist_parse(CONFIG_HMP_FAST_CPU_MASK, fast))
+                       WARN(1, "Failed to parse HMP fast cpu mask!\n");
+               if (cpulist_parse(CONFIG_HMP_SLOW_CPU_MASK, slow))
+                       WARN(1, "Failed to parse HMP slow cpu mask!\n");
+               return;
+       }
+
+       /*
+        * Else, parse device tree for little cores.
+        */
+       while ((cn = of_find_node_by_type(cn, "cpu"))) {
+
+               if (cpu >= num_possible_cpus())
+                       break;
+
+               if (is_little_cpu(cn))
+                       cpumask_set_cpu(cpu, slow);
+               else
+                       cpumask_set_cpu(cpu, fast);
+
+               cpu++;
+       }
+
+       if (!cpumask_empty(fast) && !cpumask_empty(slow))
+               return;
+
+       /*
+        * We didn't find both big and little cores so let's call all cores
+        * fast as this will keep the system running, with all cores being
+        * treated equal.
+        */
+       cpumask_setall(fast);
+       cpumask_clear(slow);
+}
+
+#endif /* CONFIG_SCHED_HMP */
+
+
 /*
  * init_cpu_topology is called at boot when only one cpu is running
  * which prevent simultaneous write access to cpu_topology array