[PATCH 3/5] habanalabs: fail reset if device is not idle

[Oded Gabbay]

After any reset (soft or hard) the device (the engines/QMANs) should
be idle. If they are not idle, fail the reset. If it is soft-reset,
the driver will try to do hard-reset automatically. If it is hard-reset,
the driver will make the device non-operational.

Signed-off-by: Oded Gabbay <ogabbay@xxxxxxxxxx>
---
 drivers/misc/habanalabs/common/device.c | 25 +++++++++++--------------
 1 file changed, 11 insertions(+), 14 deletions(-)

diff --git a/drivers/misc/habanalabs/common/device.c b/drivers/misc/habanalabs/common/device.c
index 8cc3264ae378..48d301a03d62 100644
--- a/drivers/misc/habanalabs/common/device.c
+++ b/drivers/misc/habanalabs/common/device.c
@@ -71,21 +71,8 @@ static void hpriv_release(struct kref *ref)
 
 	kfree(hpriv);
 
-	if (hdev->reset_upon_device_release) {
-		u64 idle_mask[HL_BUSY_ENGINES_MASK_EXT_SIZE] = {0};
-
-		/* We try soft reset first */
+	if (hdev->reset_upon_device_release)
 		hl_device_reset(hdev, false, false);
-
-		/* If device is not idle perform hard reset */
-		if (!hdev->asic_funcs->is_device_idle(hdev, idle_mask,
-				HL_BUSY_ENGINES_MASK_EXT_SIZE, NULL)) {
-			dev_info(hdev->dev,
-				"device is not idle (mask %#llx %#llx) after soft reset, performing hard reset",
-				idle_mask[0], idle_mask[1]);
-			hl_device_reset(hdev, true, false);
-		}
-	}
 }
 
 void hl_hpriv_get(struct hl_fpriv *hpriv)
@@ -921,6 +908,7 @@ static int device_kill_open_processes(struct hl_device *hdev, u32 timeout)
 int hl_device_reset(struct hl_device *hdev, bool hard_reset,
 			bool from_hard_reset_thread)
 {
+	u64 idle_mask[HL_BUSY_ENGINES_MASK_EXT_SIZE] = {0};
 	int i, rc;
 
 	if (!hdev->init_done) {
@@ -1140,6 +1128,15 @@ int hl_device_reset(struct hl_device *hdev, bool hard_reset,
 		goto out_err;
 	}
 
+	/* If device is not idle fail the reset process */
+	if (!hdev->asic_funcs->is_device_idle(hdev, idle_mask,
+			HL_BUSY_ENGINES_MASK_EXT_SIZE, NULL)) {
+		dev_err(hdev->dev,
+			"device is not idle (mask %#llx %#llx) after reset\n",
+			idle_mask[0], idle_mask[1]);
+		goto out_err;
+	}
+
 	/* Check that the communication with the device is working */
 	rc = hdev->asic_funcs->test_queues(hdev);
 	if (rc) {
-- 
2.25.1