summaryrefslogtreecommitdiff
path: root/drivers/misc
diff options
context:
space:
mode:
authorTomer Tayar <ttayar@habana.ai>2022-11-14 13:26:21 +0200
committerOded Gabbay <ogabbay@kernel.org>2022-11-23 16:45:23 +0200
commit408c46bd6eb7a4e2fb9fd686218e4a13b9de844c (patch)
treea91cd60f8b1c19bf95e3edcbb17301a18f7bca40 /drivers/misc
parent0abcae8b48850e0f488d0eb7232323d93bdc4b13 (diff)
habanalabs: print context refcount value if hard reset fails
Failing to kill a user process during a hard reset can be due to a reference to the user context which isn't released. To make it easier to understand if this the reason for the failure and not something else, add a print of the context refcount value. Signed-off-by: Tomer Tayar <ttayar@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
Diffstat (limited to 'drivers/misc')
-rw-r--r--drivers/misc/habanalabs/common/device.c18
1 files changed, 15 insertions, 3 deletions
diff --git a/drivers/misc/habanalabs/common/device.c b/drivers/misc/habanalabs/common/device.c
index f5864893237c..926f230def56 100644
--- a/drivers/misc/habanalabs/common/device.c
+++ b/drivers/misc/habanalabs/common/device.c
@@ -696,10 +696,22 @@ static void device_hard_reset_pending(struct work_struct *work)
flags = device_reset_work->flags | HL_DRV_RESET_FROM_RESET_THR;
rc = hl_device_reset(hdev, flags);
+
if ((rc == -EBUSY) && !hdev->device_fini_pending) {
- dev_info(hdev->dev,
- "Could not reset device. will try again in %u seconds",
- HL_PENDING_RESET_PER_SEC);
+ struct hl_ctx *ctx = hl_get_compute_ctx(hdev);
+
+ if (ctx) {
+ /* The read refcount value should subtracted by one, because the read is
+ * protected with hl_get_compute_ctx().
+ */
+ dev_info(hdev->dev,
+ "Could not reset device (compute_ctx refcount %u). will try again in %u seconds",
+ kref_read(&ctx->refcount) - 1, HL_PENDING_RESET_PER_SEC);
+ hl_ctx_put(ctx);
+ } else {
+ dev_info(hdev->dev, "Could not reset device. will try again in %u seconds",
+ HL_PENDING_RESET_PER_SEC);
+ }
queue_delayed_work(hdev->reset_wq, &device_reset_work->reset_work,
msecs_to_jiffies(HL_PENDING_RESET_PER_SEC * 1000));