cpufreq: powernv: Define per_cpu chip pointer to optimize hot-path

Commit 96c4726f01cd "cpufreq: powernv: Remove cpu_to_chip_id() from
hot-path" introduced a 'core_to_chip_map' array to cache the chip-ids
of all cores.

Replace this with a per-CPU variable that stores the pointer to the
chip-array. This removes the linear lookup and provides a neater and
simpler solution.

Signed-off-by: Michael Neuling <mikey@neuling.org>
Signed-off-by: Shilpasri G Bhat <shilpa.bhat@linux.vnet.ibm.com>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>

1 files changed, 17 insertions, 33 deletions

diff --git a/drivers/cpufreq/powernv-cpufreq.c b/drivers/cpufreq/powernv-cpufreq.c
index 50bf12033bbc..a00bcc2cef09 100644
--- a/drivers/cpufreq/powernv-cpufreq.c
+++ b/drivers/cpufreq/powernv-cpufreq.c
@@ -44,7 +44,6 @@
 
 static struct cpufreq_frequency_table powernv_freqs[POWERNV_MAX_PSTATES+1];
 static bool rebooting, throttled, occ_reset;
-static unsigned int *core_to_chip_map;
 
 static const char * const throttle_reason[] = {
         "No throttling",
@@ -65,6 +64,7 @@ static struct chip {
 } *chips;
 
 static int nr_chips;
+static DEFINE_PER_CPU(struct chip *, chip_info);
 
 /*
  * Note: The set of pstates consists of contiguous integers, the
@@ -324,34 +324,31 @@ static inline unsigned int get_nominal_index(void)
 
 static void powernv_cpufreq_throttle_check(void *data)
 {
+        struct chip *chip;
         unsigned int cpu = smp_processor_id();
-        unsigned int chip_id = core_to_chip_map[cpu_core_index_of_thread(cpu)];
         unsigned long pmsr;
-        int pmsr_pmax, i;
+        int pmsr_pmax;
 
         pmsr = get_pmspr(SPRN_PMSR);
-
-        for (i = 0; i < nr_chips; i++)
-                if (chips[i].id == chip_id)
-                        break;
+        chip = this_cpu_read(chip_info);
 
         /* Check for Pmax Capping */
         pmsr_pmax = (s8)PMSR_MAX(pmsr);
         if (pmsr_pmax != powernv_pstate_info.max) {
-                if (chips[i].throttled)
+                if (chip->throttled)
                         goto next;
-                chips[i].throttled = true;
+                chip->throttled = true;
                 if (pmsr_pmax < powernv_pstate_info.nominal)
                         pr_warn_once("CPU %d on Chip %u has Pmax reduced below nominal frequency (%d < %d)\n",
-                                     cpu, chips[i].id, pmsr_pmax,
+                                     cpu, chip->id, pmsr_pmax,
                                      powernv_pstate_info.nominal);
-                trace_powernv_throttle(chips[i].id,
-                                      throttle_reason[chips[i].throttle_reason],
+                trace_powernv_throttle(chip->id,
+                                      throttle_reason[chip->throttle_reason],
                                       pmsr_pmax);
-        } else if (chips[i].throttled) {
-                chips[i].throttled = false;
-                trace_powernv_throttle(chips[i].id,
-                                      throttle_reason[chips[i].throttle_reason],
+        } else if (chip->throttled) {
+                chip->throttled = false;
+                trace_powernv_throttle(chip->id,
+                                      throttle_reason[chip->throttle_reason],
                                       pmsr_pmax);
         }
 
@@ -558,47 +555,34 @@ static int init_chip_info(void)
         unsigned int chip[256];
         unsigned int cpu, i;
         unsigned int prev_chip_id = UINT_MAX;
-        cpumask_t cpu_mask;
-        int ret = -ENOMEM;
-
-        core_to_chip_map = kcalloc(cpu_nr_cores(), sizeof(unsigned int),
-                                   GFP_KERNEL);
-        if (!core_to_chip_map)
-                goto out;
 
-        cpumask_copy(&cpu_mask, cpu_possible_mask);
-        for_each_cpu(cpu, &cpu_mask) {
+        for_each_possible_cpu(cpu) {
                 unsigned int id = cpu_to_chip_id(cpu);
 
                 if (prev_chip_id != id) {
                         prev_chip_id = id;
                         chip[nr_chips++] = id;
                 }
-                core_to_chip_map[cpu_core_index_of_thread(cpu)] = id;
-                cpumask_andnot(&cpu_mask, &cpu_mask, cpu_sibling_mask(cpu));
         }
 
         chips = kcalloc(nr_chips, sizeof(struct chip), GFP_KERNEL);
         if (!chips)
-                goto free_chip_map;
+                return -ENOMEM;
 
         for (i = 0; i < nr_chips; i++) {
                 chips[i].id = chip[i];
                 cpumask_copy(&chips[i].mask, cpumask_of_node(chip[i]));
                 INIT_WORK(&chips[i].throttle, powernv_cpufreq_work_fn);
+                for_each_cpu(cpu, &chips[i].mask)
+                        per_cpu(chip_info, cpu) =  &chips[i];
         }
 
         return 0;
-free_chip_map:
-        kfree(core_to_chip_map);
-out:
-        return ret;
 }
 
 static inline void clean_chip_info(void)
 {
         kfree(chips);
-        kfree(core_to_chip_map);
 }
 
 static inline void unregister_all_notifiers(void)