The SDMA queue counter read was dispatched by GC version: anything newer
than gfx 9.4.2 was routed to the kfd2kgd->hqd_sdma_get_counter hook.
However that hook is only implemented for gfx 9.4.3, so gfx 10.3, gfx 11
and gfx 12 fell into the else branch with a NULL hook and got
-EOPNOTSUPP. This spammed "Failed to read SDMA queue counter" on every
SDMA queue teardown and left sdma_val at 0, so the per-process SDMA
activity accounting stopped working on those ASICs.
Dispatch based on whether the hook is implemented instead of the GC
version, so ASICs without the hook keep using read_sdma_queue_counter()
as before.
Fixes: 0ee24cad5b35 ("drm/amdkfd: add sdma queue counter for gfxv9.4.3")
Signed-off-by: Jesse Zhang <[email protected]>
---
.../drm/amd/amdkfd/kfd_device_queue_manager.c | 28 ++++++++-----------
drivers/gpu/drm/amd/amdkfd/kfd_process.c | 12 ++++----
2 files changed, 17 insertions(+), 23 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
index 53415317ad63..7ee10fb0a8fd 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
@@ -1027,17 +1027,15 @@ static int destroy_queue_nocpsch(struct
device_queue_manager *dqm,
/* Get the SDMA queue stats */
if ((q->properties.type == KFD_QUEUE_TYPE_SDMA) ||
(q->properties.type == KFD_QUEUE_TYPE_SDMA_XGMI)) {
- if (KFD_GC_VERSION(dqm->dev) <= IP_VERSION(9, 4, 2))
+ if (dqm->dev->kfd2kgd->hqd_sdma_get_counter)
+ retval = dqm->dev->kfd2kgd->hqd_sdma_get_counter(
+ dqm->dev->adev, q->mqd,
+
dqm->dev->kfd->device_info.num_sdma_queues_per_engine,
+ &sdma_val);
+ else
retval = read_sdma_queue_counter(
(uint64_t __user
*)q->properties.read_ptr,
&sdma_val);
- else
- retval = dqm->dev->kfd2kgd->hqd_sdma_get_counter ?
- dqm->dev->kfd2kgd->hqd_sdma_get_counter(
- dqm->dev->adev, q->mqd,
-
dqm->dev->kfd->device_info.num_sdma_queues_per_engine,
- &sdma_val) :
- -EOPNOTSUPP;
if (retval)
dev_err(dev, "Failed to read SDMA queue counter for
queue: %d\n",
q->properties.queue_id);
@@ -2675,17 +2673,15 @@ static int destroy_queue_cpsch(struct
device_queue_manager *dqm,
/* Get the SDMA queue stats */
if ((q->properties.type == KFD_QUEUE_TYPE_SDMA) ||
(q->properties.type == KFD_QUEUE_TYPE_SDMA_XGMI)) {
- if (KFD_GC_VERSION(dqm->dev) <= IP_VERSION(9, 4, 2))
+ if (dqm->dev->kfd2kgd->hqd_sdma_get_counter)
+ retval = dqm->dev->kfd2kgd->hqd_sdma_get_counter(
+ dqm->dev->adev, q->mqd,
+
dqm->dev->kfd->device_info.num_sdma_queues_per_engine,
+ &sdma_val);
+ else
retval = read_sdma_queue_counter(
(uint64_t __user
*)q->properties.read_ptr,
&sdma_val);
- else
- retval = dqm->dev->kfd2kgd->hqd_sdma_get_counter ?
- dqm->dev->kfd2kgd->hqd_sdma_get_counter(
- dqm->dev->adev, q->mqd,
-
dqm->dev->kfd->device_info.num_sdma_queues_per_engine,
- &sdma_val) :
- -EOPNOTSUPP;
if (retval)
dev_err(dev, "Failed to read SDMA queue counter for
queue: %d\n",
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c
b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
index e0b885b2395a..f280c3e41ea6 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
@@ -192,15 +192,13 @@ static void kfd_sdma_activity_worker(struct work_struct
*work)
list_for_each_entry(sdma_q, &sdma_q_list.list, list) {
val = 0;
- if (KFD_GC_VERSION(dqm->dev) <= IP_VERSION(9, 4, 2))
- ret = read_sdma_queue_counter(sdma_q->rptr, &val);
- else
- ret = dqm->dev->kfd2kgd->hqd_sdma_get_counter ?
- dqm->dev->kfd2kgd->hqd_sdma_get_counter(
+ if (dqm->dev->kfd2kgd->hqd_sdma_get_counter)
+ ret = dqm->dev->kfd2kgd->hqd_sdma_get_counter(
dqm->dev->adev, sdma_q->mqd,
dqm->dev->kfd->device_info.num_sdma_queues_per_engine,
- &val) :
- -EOPNOTSUPP;
+ &val);
+ else
+ ret = read_sdma_queue_counter(sdma_q->rptr, &val);
if (ret) {
pr_debug("Failed to read SDMA queue active counter for
queue id: %d",
--
2.49.0
