[PATCH v2] drm/amdkfd: Try to schedule bottom half on same core

[Felix Kuehling]

On systems that support SMT (hyperthreading) schedule the bottom half of
the KFD interrupt handler on the same core. This makes it possible to
reserve a core for interrupt handling and have the bottom half run on
that same core.

On systems without SMT, pick another core in the same NUMA node, as
before.

Use for_each_cpu_wrap instead of open-coding it.

Signed-off-by: Felix Kuehling <felix.kuehl...@amd.com>
---
 drivers/gpu/drm/amd/amdkfd/kfd_device.c | 20 ++++++++++++++++----
 1 file changed, 16 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c 
b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
index f5853835f03a..4d1284714e7a 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
@@ -24,6 +24,7 @@
 #include <linux/bsearch.h>
 #include <linux/pci.h>
 #include <linux/slab.h>
+#include <linux/topology.h>
 #include "kfd_priv.h"
 #include "kfd_device_queue_manager.h"
 #include "kfd_pm4_headers_vi.h"
@@ -801,13 +802,24 @@ static inline void kfd_queue_work(struct workqueue_struct 
*wq,
                                  struct work_struct *work)
 {
        int cpu, new_cpu;
+       const struct cpumask *mask = NULL;
 
        cpu = new_cpu = smp_processor_id();
-       do {
-               new_cpu = cpumask_next(new_cpu, cpu_online_mask) % nr_cpu_ids;
-               if (cpu_to_node(new_cpu) == numa_node_id())
+
+#if defined(CONFIG_SCHED_SMT)
+       /* CPU threads in the same core */
+       mask = cpu_smt_mask(cpu);
+#endif
+       if (!mask || cpumask_weight(mask) <= 1)
+               /* CPU threads in the same NUMA node */
+               mask = cpu_cpu_mask(cpu);
+       /* Pick the next online CPU thread in the same core or NUMA node */
+       for_each_cpu_wrap(cpu, mask, cpu+1) {
+               if (cpu != new_cpu && cpu_online(cpu)) {
+                       new_cpu = cpu;
                        break;
-       } while (cpu != new_cpu);
+               }
+       }
 
        queue_work_on(new_cpu, wq, work);
 }
-- 
2.32.0