}
/*
- * ext_and_hw_queue_submit_bd() - Submit a buffer descriptor to an external or a
+ * hl_hw_queue_submit_bd() - Submit a buffer descriptor to an external or a
* H/W queue.
* @hdev: pointer to habanalabs device structure
* @q: pointer to habanalabs queue structure
* This function must be called when the scheduler mutex is taken
*
*/
-static void ext_and_hw_queue_submit_bd(struct hl_device *hdev,
- struct hl_hw_queue *q, u32 ctl, u32 len, u64 ptr)
+void hl_hw_queue_submit_bd(struct hl_device *hdev, struct hl_hw_queue *q,
+ u32 ctl, u32 len, u64 ptr)
{
struct hl_bd *bd;
* @cb_size: size of CB
* @cb_ptr: pointer to CB location
*
- * This function sends a single CB, that must NOT generate a completion entry
- *
+ * This function sends a single CB, that must NOT generate a completion entry.
+ * Sending CPU messages can be done instead via 'hl_hw_queue_submit_bd()'
*/
int hl_hw_queue_send_cb_no_cmpl(struct hl_device *hdev, u32 hw_queue_id,
u32 cb_size, u64 cb_ptr)
struct hl_hw_queue *q = &hdev->kernel_queues[hw_queue_id];
int rc = 0;
- /*
- * The CPU queue is a synchronous queue with an effective depth of
- * a single entry (although it is allocated with room for multiple
- * entries). Therefore, there is a different lock, called
- * send_cpu_message_lock, that serializes accesses to the CPU queue.
- * As a result, we don't need to lock the access to the entire H/W
- * queues module when submitting a JOB to the CPU queue
- */
- if (q->queue_type != QUEUE_TYPE_CPU)
- hdev->asic_funcs->hw_queues_lock(hdev);
+ hdev->asic_funcs->hw_queues_lock(hdev);
if (hdev->disabled) {
rc = -EPERM;
goto out;
}
- ext_and_hw_queue_submit_bd(hdev, q, 0, cb_size, cb_ptr);
+ hl_hw_queue_submit_bd(hdev, q, 0, cb_size, cb_ptr);
out:
- if (q->queue_type != QUEUE_TYPE_CPU)
- hdev->asic_funcs->hw_queues_unlock(hdev);
+ hdev->asic_funcs->hw_queues_unlock(hdev);
return rc;
}
cq->pi = hl_cq_inc_ptr(cq->pi);
submit_bd:
- ext_and_hw_queue_submit_bd(hdev, q, ctl, len, ptr);
+ hl_hw_queue_submit_bd(hdev, q, ctl, len, ptr);
}
/*
else
ptr = (u64) (uintptr_t) job->user_cb;
- ext_and_hw_queue_submit_bd(hdev, q, ctl, len, ptr);
+ hl_hw_queue_submit_bd(hdev, q, ctl, len, ptr);
}
static int init_signal_cs(struct hl_device *hdev,
cs_cmpl->sob_val = prop->next_sob_val;
dev_dbg(hdev->dev,
- "generate signal CB, sob_id: %d, sob val: 0x%x, q_idx: %d\n",
- cs_cmpl->hw_sob->sob_id, cs_cmpl->sob_val, q_idx);
+ "generate signal CB, sob_id: %d, sob val: %u, q_idx: %d, seq: %llu\n",
+ cs_cmpl->hw_sob->sob_id, cs_cmpl->sob_val, q_idx,
+ cs_cmpl->cs_seq);
/* we set an EB since we must make sure all oeprations are done
* when sending the signal
hdev->asic_funcs->gen_signal_cb(hdev, job->patched_cb,
cs_cmpl->hw_sob->sob_id, 0, true);
- rc = hl_cs_signal_sob_wraparound_handler(hdev, q_idx, &hw_sob, 1);
+ rc = hl_cs_signal_sob_wraparound_handler(hdev, q_idx, &hw_sob, 1,
+ false);
return rc;
}
-static void init_wait_cs(struct hl_device *hdev, struct hl_cs *cs,
+void hl_hw_queue_encaps_sig_set_sob_info(struct hl_device *hdev,
+ struct hl_cs *cs, struct hl_cs_job *job,
+ struct hl_cs_compl *cs_cmpl)
+{
+ struct hl_cs_encaps_sig_handle *handle = cs->encaps_sig_hdl;
+
+ cs_cmpl->hw_sob = handle->hw_sob;
+
+ /* Note that encaps_sig_wait_offset was validated earlier in the flow
+ * for offset value which exceeds the max reserved signal count.
+ * always decrement 1 of the offset since when the user
+ * set offset 1 for example he mean to wait only for the first
+ * signal only, which will be pre_sob_val, and if he set offset 2
+ * then the value required is (pre_sob_val + 1) and so on...
+ */
+ cs_cmpl->sob_val = handle->pre_sob_val +
+ (job->encaps_sig_wait_offset - 1);
+}
+
+static int init_wait_cs(struct hl_device *hdev, struct hl_cs *cs,
struct hl_cs_job *job, struct hl_cs_compl *cs_cmpl)
{
- struct hl_cs_compl *signal_cs_cmpl;
- struct hl_sync_stream_properties *prop;
struct hl_gen_wait_properties wait_prop;
+ struct hl_sync_stream_properties *prop;
+ struct hl_cs_compl *signal_cs_cmpl;
u32 q_idx;
q_idx = job->hw_queue_id;
struct hl_cs_compl,
base_fence);
- /* copy the SOB id and value of the signal CS */
- cs_cmpl->hw_sob = signal_cs_cmpl->hw_sob;
- cs_cmpl->sob_val = signal_cs_cmpl->sob_val;
+ if (cs->encaps_signals) {
+ /* use the encaps signal handle stored earlier in the flow
+ * and set the SOB information from the encaps
+ * signals handle
+ */
+ hl_hw_queue_encaps_sig_set_sob_info(hdev, cs, job, cs_cmpl);
+
+ dev_dbg(hdev->dev, "Wait for encaps signals handle, qidx(%u), CS sequence(%llu), sob val: 0x%x, offset: %u\n",
+ cs->encaps_sig_hdl->q_idx,
+ cs->encaps_sig_hdl->cs_seq,
+ cs_cmpl->sob_val,
+ job->encaps_sig_wait_offset);
+ } else {
+ /* Copy the SOB id and value of the signal CS */
+ cs_cmpl->hw_sob = signal_cs_cmpl->hw_sob;
+ cs_cmpl->sob_val = signal_cs_cmpl->sob_val;
+ }
+
+ /* check again if the signal cs already completed.
+ * if yes then don't send any wait cs since the hw_sob
+ * could be in reset already. if signal is not completed
+ * then get refcount to hw_sob to prevent resetting the sob
+ * while wait cs is not submitted.
+ * note that this check is protected by two locks,
+ * hw queue lock and completion object lock,
+ * and the same completion object lock also protects
+ * the hw_sob reset handler function.
+ * The hw_queue lock prevent out of sync of hw_sob
+ * refcount value, changed by signal/wait flows.
+ */
+ spin_lock(&signal_cs_cmpl->lock);
+
+ if (completion_done(&cs->signal_fence->completion)) {
+ spin_unlock(&signal_cs_cmpl->lock);
+ return -EINVAL;
+ }
+
+ kref_get(&cs_cmpl->hw_sob->kref);
+
+ spin_unlock(&signal_cs_cmpl->lock);
dev_dbg(hdev->dev,
- "generate wait CB, sob_id: %d, sob_val: 0x%x, mon_id: %d, q_idx: %d\n",
+ "generate wait CB, sob_id: %d, sob_val: 0x%x, mon_id: %d, q_idx: %d, seq: %llu\n",
cs_cmpl->hw_sob->sob_id, cs_cmpl->sob_val,
- prop->base_mon_id, q_idx);
+ prop->base_mon_id, q_idx, cs->sequence);
wait_prop.data = (void *) job->patched_cb;
wait_prop.sob_base = cs_cmpl->hw_sob->sob_id;
wait_prop.mon_id = prop->base_mon_id;
wait_prop.q_idx = q_idx;
wait_prop.size = 0;
+
hdev->asic_funcs->gen_wait_cb(hdev, &wait_prop);
- kref_get(&cs_cmpl->hw_sob->kref);
- /*
- * Must put the signal fence after the SOB refcnt increment so
- * the SOB refcnt won't turn 0 and reset the SOB before the
- * wait CS was submitted.
- */
mb();
hl_fence_put(cs->signal_fence);
cs->signal_fence = NULL;
+
+ return 0;
}
/*
if (cs->type & CS_TYPE_SIGNAL)
rc = init_signal_cs(hdev, job, cs_cmpl);
else if (cs->type & CS_TYPE_WAIT)
- init_wait_cs(hdev, cs, job, cs_cmpl);
+ rc = init_wait_cs(hdev, cs, job, cs_cmpl);
+
+ return rc;
+}
+
+static int encaps_sig_first_staged_cs_handler
+ (struct hl_device *hdev, struct hl_cs *cs)
+{
+ struct hl_cs_compl *cs_cmpl =
+ container_of(cs->fence,
+ struct hl_cs_compl, base_fence);
+ struct hl_cs_encaps_sig_handle *encaps_sig_hdl;
+ struct hl_encaps_signals_mgr *mgr;
+ int rc = 0;
+
+ mgr = &hdev->compute_ctx->sig_mgr;
+
+ spin_lock(&mgr->lock);
+ encaps_sig_hdl = idr_find(&mgr->handles, cs->encaps_sig_hdl_id);
+ if (encaps_sig_hdl) {
+ /*
+ * Set handler CS sequence,
+ * the CS which contains the encapsulated signals.
+ */
+ encaps_sig_hdl->cs_seq = cs->sequence;
+ /* store the handle and set encaps signal indication,
+ * to be used later in cs_do_release to put the last
+ * reference to encaps signals handlers.
+ */
+ cs_cmpl->encaps_signals = true;
+ cs_cmpl->encaps_sig_hdl = encaps_sig_hdl;
+
+ /* set hw_sob pointer in completion object
+ * since it's used in cs_do_release flow to put
+ * refcount to sob
+ */
+ cs_cmpl->hw_sob = encaps_sig_hdl->hw_sob;
+ cs_cmpl->sob_val = encaps_sig_hdl->pre_sob_val +
+ encaps_sig_hdl->count;
+
+ dev_dbg(hdev->dev, "CS seq (%llu) added to encaps signal handler id (%u), count(%u), qidx(%u), sob(%u), val(%u)\n",
+ cs->sequence, encaps_sig_hdl->id,
+ encaps_sig_hdl->count,
+ encaps_sig_hdl->q_idx,
+ cs_cmpl->hw_sob->sob_id,
+ cs_cmpl->sob_val);
+
+ } else {
+ dev_err(hdev->dev, "encaps handle id(%u) wasn't found!\n",
+ cs->encaps_sig_hdl_id);
+ rc = -EINVAL;
+ }
+
+ spin_unlock(&mgr->lock);
return rc;
}
if ((cs->type == CS_TYPE_SIGNAL) || (cs->type == CS_TYPE_WAIT)) {
rc = init_signal_wait_cs(cs);
- if (rc) {
- dev_err(hdev->dev, "Failed to submit signal cs\n");
+ if (rc)
goto unroll_cq_resv;
- }
- } else if (cs->type == CS_TYPE_COLLECTIVE_WAIT)
- hdev->asic_funcs->collective_wait_init_cs(cs);
+ } else if (cs->type == CS_TYPE_COLLECTIVE_WAIT) {
+ rc = hdev->asic_funcs->collective_wait_init_cs(cs);
+ if (rc)
+ goto unroll_cq_resv;
+ }
+ if (cs->encaps_signals && cs->staged_first) {
+ rc = encaps_sig_first_staged_cs_handler(hdev, cs);
+ if (rc)
+ goto unroll_cq_resv;
+ }
+
spin_lock(&hdev->cs_mirror_lock);
/* Verify staged CS exists and add to the staged list */
}
list_add_tail(&cs->staged_cs_node, &staged_cs->staged_cs_node);
+
+ /* update stream map of the first CS */
+ if (hdev->supports_wait_for_multi_cs)
+ staged_cs->fence->stream_master_qid_map |=
+ cs->fence->stream_master_qid_map;
}
list_add_tail(&cs->mirror_node, &hdev->cs_mirror_list);
hw_sob = &sync_stream_prop->hw_sob[sob];
hw_sob->hdev = hdev;
hw_sob->sob_id = sync_stream_prop->base_sob_id + sob;
+ hw_sob->sob_addr =
+ hdev->asic_funcs->get_sob_addr(hdev, hw_sob->sob_id);
hw_sob->q_idx = q_idx;
kref_init(&hw_sob->kref);
}
projects / linux-2.6-microblaze.git / blobdiff