mirrors/linux
1
0
Fork 0
mirror of https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git synced 2026-04-29 15:15:28 -04:00
Code Issues Packages Projects Releases Wiki Activity

habanalabs/gaudi: Fix collective wait bug

Browse Source 
In Signaling-From-Graph case, the driver didn't set the hw_sob pointer
at the right place, which is needed for the cs completion
check prior to start sending all the master/slaves jobs to device.

Signed-off-by: farah kassabri <fkassabri@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
This commit is contained in:
farah kassabri
2021-11-03 13:15:55 +02:00
committed by Oded Gabbay
parent 1679c7ee58
commit 792512459f
1 changed files with 11 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

15
drivers/misc/habanalabs/gaudi/gaudi.c
View File

@@ -1276,6 +1276,7 @@ static int gaudi_collective_wait_init_cs(struct hl_cs *cs)
container_of(cs->signal_fence, struct hl_cs_compl, base_fence);
struct hl_cs_compl *cs_cmpl =
container_of(cs->fence, struct hl_cs_compl, base_fence);
struct hl_cs_encaps_sig_handle *handle = cs->encaps_sig_hdl;
struct gaudi_collective_properties *cprop;
u32 stream, queue_id, sob_group_offset;
struct gaudi_device *gaudi;
@@ -1288,10 +1289,16 @@ static int gaudi_collective_wait_init_cs(struct hl_cs *cs)
gaudi = hdev->asic_specific;
cprop = &gaudi->collective_props;
/* In encaps signals case the SOB info will be retrieved from
* the handle in gaudi_collective_slave_init_job.
*/
if (!cs->encaps_signals) {
if (cs->encaps_signals) {
cs_cmpl->hw_sob = handle->hw_sob;
/* at this checkpoint we only need the hw_sob pointer
* for the completion check before start going over the jobs
* of the master/slaves, the sob_value will be taken later on
* in gaudi_collective_slave_init_job depends on each
* job wait offset value.
*/
cs_cmpl->sob_val = 0;
} 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;