diff options
Diffstat (limited to 'drivers/misc/habanalabs/hw_queue.c')
-rw-r--r-- | drivers/misc/habanalabs/hw_queue.c | 32 |
1 files changed, 17 insertions, 15 deletions
diff --git a/drivers/misc/habanalabs/hw_queue.c b/drivers/misc/habanalabs/hw_queue.c index e3b5517897ea..55b383b2a116 100644 --- a/drivers/misc/habanalabs/hw_queue.c +++ b/drivers/misc/habanalabs/hw_queue.c @@ -80,9 +80,9 @@ static void ext_queue_submit_bd(struct hl_device *hdev, struct hl_hw_queue *q, bd = (struct hl_bd *) (uintptr_t) q->kernel_address; bd += hl_pi_2_offset(q->pi); - bd->ctl = __cpu_to_le32(ctl); - bd->len = __cpu_to_le32(len); - bd->ptr = __cpu_to_le64(ptr); + bd->ctl = cpu_to_le32(ctl); + bd->len = cpu_to_le32(len); + bd->ptr = cpu_to_le64(ptr); q->pi = hl_queue_inc_ptr(q->pi); hdev->asic_funcs->ring_doorbell(hdev, q->hw_queue_id, q->pi); @@ -249,7 +249,7 @@ static void ext_hw_queue_schedule_job(struct hl_cs_job *job) len = job->job_cb_size; ptr = cb->bus_address; - cq_pkt.data = __cpu_to_le32( + cq_pkt.data = cpu_to_le32( ((q->pi << CQ_ENTRY_SHADOW_INDEX_SHIFT) & CQ_ENTRY_SHADOW_INDEX_MASK) | (1 << CQ_ENTRY_SHADOW_INDEX_VALID_SHIFT) | @@ -267,7 +267,7 @@ static void ext_hw_queue_schedule_job(struct hl_cs_job *job) hdev->asic_funcs->add_end_of_cb_packets(hdev, cb->kernel_address, len, cq_addr, - __le32_to_cpu(cq_pkt.data), + le32_to_cpu(cq_pkt.data), q->hw_queue_id); q->shadow_queue[hl_pi_2_offset(q->pi)] = job; @@ -290,23 +290,19 @@ static void int_hw_queue_schedule_job(struct hl_cs_job *job) struct hl_device *hdev = job->cs->ctx->hdev; struct hl_hw_queue *q = &hdev->kernel_queues[job->hw_queue_id]; struct hl_bd bd; - u64 *pi, *pbd = (u64 *) &bd; + __le64 *pi; bd.ctl = 0; - bd.len = __cpu_to_le32(job->job_cb_size); - bd.ptr = __cpu_to_le64((u64) (uintptr_t) job->user_cb); + bd.len = cpu_to_le32(job->job_cb_size); + bd.ptr = cpu_to_le64((u64) (uintptr_t) job->user_cb); - pi = (u64 *) (uintptr_t) (q->kernel_address + + pi = (__le64 *) (uintptr_t) (q->kernel_address + ((q->pi & (q->int_queue_len - 1)) * sizeof(bd))); - pi[0] = pbd[0]; - pi[1] = pbd[1]; - q->pi++; q->pi &= ((q->int_queue_len << 1) - 1); - /* Flush PQ entry write. Relevant only for specific ASICs */ - hdev->asic_funcs->flush_pq_write(hdev, pi, pbd[0]); + hdev->asic_funcs->pqe_write(hdev, pi, &bd); hdev->asic_funcs->ring_doorbell(hdev, q->hw_queue_id, q->pi); } @@ -368,7 +364,13 @@ int hl_hw_queue_schedule_cs(struct hl_cs *cs) spin_unlock(&hdev->hw_queues_mirror_lock); } - atomic_inc(&hdev->cs_active_cnt); + if (!hdev->cs_active_cnt++) { + struct hl_device_idle_busy_ts *ts; + + ts = &hdev->idle_busy_ts_arr[hdev->idle_busy_ts_idx]; + ts->busy_to_idle_ts = ktime_set(0, 0); + ts->idle_to_busy_ts = ktime_get(); + } list_for_each_entry_safe(job, tmp, &cs->job_list, cs_node) if (job->ext_queue) |