'doorbell_bitmap' and 'queue_slot_bitmap' are bitmaps. So use 'bitmap_zalloc()' to simplify code, improve the semantic and avoid some open-coded arithmetic in allocator arguments.
Also change the corresponding 'kfree()' into 'bitmap_free()' to keep consistency.
Reviewed-by: Felix Kuehling Felix.Kuehling@amd.com Signed-off-by: Christophe JAILLET christophe.jaillet@wanadoo.fr --- v1 --> v2: Compile tested :) Add a missing ',' (kernel test robot) Add kfd_process_queue_manager.c (Felix Kuehling) --- drivers/gpu/drm/amd/amdkfd/kfd_process.c | 7 +++---- drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c | 7 +++---- 2 files changed, 6 insertions(+), 8 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c index d4c8a6948a9f..67bb1654becc 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c @@ -1011,7 +1011,7 @@ static void kfd_process_destroy_pdds(struct kfd_process *p) free_pages((unsigned long)pdd->qpd.cwsr_kaddr, get_order(KFD_CWSR_TBA_TMA_SIZE));
- kfree(pdd->qpd.doorbell_bitmap); + bitmap_free(pdd->qpd.doorbell_bitmap); idr_destroy(&pdd->alloc_idr);
kfd_free_process_doorbells(pdd->dev, pdd->doorbell_index); @@ -1433,9 +1433,8 @@ static int init_doorbell_bitmap(struct qcm_process_device *qpd, if (!KFD_IS_SOC15(dev)) return 0;
- qpd->doorbell_bitmap = - kzalloc(DIV_ROUND_UP(KFD_MAX_NUM_OF_QUEUES_PER_PROCESS, - BITS_PER_BYTE), GFP_KERNEL); + qpd->doorbell_bitmap = bitmap_zalloc(KFD_MAX_NUM_OF_QUEUES_PER_PROCESS, + GFP_KERNEL); if (!qpd->doorbell_bitmap) return -ENOMEM;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c index 4f8464658daf..c5f5a25c6dcc 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c @@ -135,9 +135,8 @@ void kfd_process_dequeue_from_all_devices(struct kfd_process *p) int pqm_init(struct process_queue_manager *pqm, struct kfd_process *p) { INIT_LIST_HEAD(&pqm->queues); - pqm->queue_slot_bitmap = - kzalloc(DIV_ROUND_UP(KFD_MAX_NUM_OF_QUEUES_PER_PROCESS, - BITS_PER_BYTE), GFP_KERNEL); + pqm->queue_slot_bitmap = bitmap_zalloc(KFD_MAX_NUM_OF_QUEUES_PER_PROCESS, + GFP_KERNEL); if (!pqm->queue_slot_bitmap) return -ENOMEM; pqm->process = p; @@ -159,7 +158,7 @@ void pqm_uninit(struct process_queue_manager *pqm) kfree(pqn); }
- kfree(pqm->queue_slot_bitmap); + bitmap_free(pqm->queue_slot_bitmap); pqm->queue_slot_bitmap = NULL; }
The 'doorbell_bitmap' bitmap has just been allocated. So we can use the non-atomic '__set_bit()' function to save a few cycles as no concurrent access can happen.
Reviewed-by: Felix Kuehling Felix.Kuehling@amd.com Signed-off-by: Christophe JAILLET christophe.jaillet@wanadoo.fr --- bitmap_set() could certainly also be use, but range checking would be tricky.
v1 --> v2: No change --- drivers/gpu/drm/amd/amdkfd/kfd_process.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c index 67bb1654becc..9158f9754a24 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c @@ -1446,9 +1446,9 @@ static int init_doorbell_bitmap(struct qcm_process_device *qpd,
for (i = 0; i < KFD_MAX_NUM_OF_QUEUES_PER_PROCESS / 2; i++) { if (i >= range_start && i <= range_end) { - set_bit(i, qpd->doorbell_bitmap); - set_bit(i + KFD_QUEUE_DOORBELL_MIRROR_OFFSET, - qpd->doorbell_bitmap); + __set_bit(i, qpd->doorbell_bitmap); + __set_bit(i + KFD_QUEUE_DOORBELL_MIRROR_OFFSET, + qpd->doorbell_bitmap); } }
Am 2021-11-23 um 3:46 p.m. schrieb Christophe JAILLET:
The 'doorbell_bitmap' bitmap has just been allocated. So we can use the non-atomic '__set_bit()' function to save a few cycles as no concurrent access can happen.
Reviewed-by: Felix Kuehling Felix.Kuehling@amd.com Signed-off-by: Christophe JAILLET christophe.jaillet@wanadoo.fr
Thank you! I applied the series to amd-staging-drm-next.
Regards, Felix
bitmap_set() could certainly also be use, but range checking would be tricky.
v1 --> v2: No change
drivers/gpu/drm/amd/amdkfd/kfd_process.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c index 67bb1654becc..9158f9754a24 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c @@ -1446,9 +1446,9 @@ static int init_doorbell_bitmap(struct qcm_process_device *qpd,
for (i = 0; i < KFD_MAX_NUM_OF_QUEUES_PER_PROCESS / 2; i++) { if (i >= range_start && i <= range_end) {
set_bit(i, qpd->doorbell_bitmap);
set_bit(i + KFD_QUEUE_DOORBELL_MIRROR_OFFSET,
qpd->doorbell_bitmap);
__set_bit(i, qpd->doorbell_bitmap);
__set_bit(i + KFD_QUEUE_DOORBELL_MIRROR_OFFSET,
} }qpd->doorbell_bitmap);
dri-devel@lists.freedesktop.org