From a35c99760146137bbcfafe82ed5dc9c7a00b640a Mon Sep 17 00:00:00 2001 From: Tomer Tayar Date: Wed, 10 May 2023 18:18:05 +0300 Subject: [PATCH] accel/habanalabs: update pending reset flags with new reset requests If hl_device_cond_reset() is called while a reset is already pending but hasn't started, the reset request will be dropped. If the flags of the new request are more severe, e.g. a hard reset while the pending reset is a compute reset, the eventual reset won't be suitable for the device status. To prevent such cases, update the pending reset flags with the new requests flags before the requests are dropped. Signed-off-by: Tomer Tayar Reviewed-by: Oded Gabbay Signed-off-by: Oded Gabbay --- drivers/accel/habanalabs/common/device.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/accel/habanalabs/common/device.c b/drivers/accel/habanalabs/common/device.c index 1e61e79c42e52..9933058712920 100644 --- a/drivers/accel/habanalabs/common/device.c +++ b/drivers/accel/habanalabs/common/device.c @@ -1937,8 +1937,10 @@ int hl_device_cond_reset(struct hl_device *hdev, u32 flags, u64 event_mask) goto device_reset; } - if (hdev->reset_info.watchdog_active) + if (hdev->reset_info.watchdog_active) { + hdev->device_release_watchdog_work.flags |= flags; goto out; + } hdev->device_release_watchdog_work.flags = flags; dev_dbg(hdev->dev, "Device is going to be hard-reset in %u sec unless being released\n", -- 2.30.2