From: Oded Gabbay <ogabbay@kernel.org>
To: linux-kernel@vger.kernel.org
Cc: SW_Drivers@habana.ai, Ofir Bitton <obitton@habana.ai>
Subject: [PATCH] habanalabs: release signal if collective wait was dropped
Date: Wed, 4 Nov 2020 16:09:02 +0200 [thread overview]
Message-ID: <20201104140908.10178-6-ogabbay@kernel.org> (raw)
In-Reply-To: <20201104140908.10178-1-ogabbay@kernel.org>
From: Ofir Bitton <obitton@habana.ai>
As in standard wait cs, we must release a signal fence once
a collective wait cs was dropped and not submitted.
Signed-off-by: Ofir Bitton <obitton@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
---
drivers/misc/habanalabs/common/command_submission.c | 6 ++++--
1 file changed, 4 insertions(+), 2 deletions(-)
diff --git a/drivers/misc/habanalabs/common/command_submission.c b/drivers/misc/habanalabs/common/command_submission.c
index 18cd20eec4c5..6de4b161856c 100644
--- a/drivers/misc/habanalabs/common/command_submission.c
+++ b/drivers/misc/habanalabs/common/command_submission.c
@@ -300,9 +300,11 @@ static void cs_do_release(struct kref *ref)
if (!cs->submitted) {
/* In case the wait for signal CS was submitted, the put occurs
- * in init_signal_wait_cs() right before hanging on the PQ.
+ * in init_signal_wait_cs() or collective_wait_init_cs()
+ * right before hanging on the PQ.
*/
- if (cs->type == CS_TYPE_WAIT)
+ if (cs->type == CS_TYPE_WAIT ||
+ cs->type == CS_TYPE_COLLECTIVE_WAIT)
hl_fence_put(cs->signal_fence);
goto out;
--
2.17.1
next prev parent reply other threads:[~2020-11-04 14:09 UTC|newest]
Thread overview: 12+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-11-04 14:08 [PATCH] habanalabs: add 'needs reset' state in driver Oded Gabbay
2020-11-04 14:08 ` [PATCH] habanalabs: fix hard reset print and comment Oded Gabbay
2020-11-04 14:08 ` [PATCH] habanalabs/gaudi: increase MAX CS to 16K Oded Gabbay
2020-11-04 14:09 ` [PATCH] habanalabs/gaudi: remove pcie_en strap toggle Oded Gabbay
2020-11-04 14:09 ` [PATCH] habanalabs: Move repeatedly included headers to habanalabs.h Oded Gabbay
2020-11-04 14:09 ` Oded Gabbay [this message]
2020-11-04 14:09 ` [PATCH] habanalabs: remove duplicate print Oded Gabbay
2020-11-04 14:09 ` [PATCH] habanalabs: reset device upon fw read failure Oded Gabbay
2020-11-04 14:09 ` [PATCH] habanalabs: restore vm_pgoff after mmap Oded Gabbay
2020-11-04 14:09 ` [PATCH] habanalabs: Separate CS job completion from its deallocation Oded Gabbay
2020-11-04 14:09 ` [PATCH] habanalabs: Skip updating CI of internal queues if not in use Oded Gabbay
2020-11-04 14:09 ` [PATCH] habanalabs: Small refactoring of cs_do_release() Oded Gabbay
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20201104140908.10178-6-ogabbay@kernel.org \
--to=ogabbay@kernel.org \
--cc=SW_Drivers@habana.ai \
--cc=linux-kernel@vger.kernel.org \
--cc=obitton@habana.ai \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox