korg/linux
0
0
Fork 0
mirror of https://mirrors.bfsu.edu.cn/git/linux.git synced 2024-12-05 01:54:09 +08:00
Code Issues Packages Projects Releases Wiki Activity

habanalabs: print context refcount value if hard reset fails

Browse Source 
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>
This commit is contained in:
Tomer Tayar 2022-11-14 13:26:21 +02:00 committed by Oded Gabbay
parent 0abcae8b48
commit 408c46bd6e
1 changed files with 15 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

18
drivers/misc/habanalabs/common/device.c
View File

@ -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));