habanalabs: reset after device is actually released

The device is actually released only after the refcnt of the hpriv
structure is 0, which means all its contexts were closed.

If we reset the device while a context is still open, there are
possibilities for unexpected behavior and crashes. For example, if the
process has a mapping of a register block that is now currently being
reset, and the process writes/reads to that block during the reset,
the device can get stuck.
Signed-off-by: NOded Gabbay <ogabbay@kernel.org>

drivers/misc/habanalabs/common/device.c

@@ -70,6 +70,22 @@ static void hpriv_release(struct kref *ref)
 	mutex_unlock(&hdev->fpriv_list_lock);
 
 	kfree(hpriv);
+
+	if (hdev->reset_upon_device_release) {
+		u64 idle_mask[HL_BUSY_ENGINES_MASK_EXT_SIZE] = {0};
+
+		/* We try soft reset first */
+		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)
@@ -106,22 +122,6 @@ static int hl_device_release(struct inode *inode, struct file *filp)
 	hl_cb_mgr_fini(hdev, &hpriv->cb_mgr);
 	hl_ctx_mgr_fini(hdev, &hpriv->ctx_mgr);
 
-	if (hdev->reset_upon_device_release) {
-		u64 idle_mask[HL_BUSY_ENGINES_MASK_EXT_SIZE] = {0};
-
-		/* We try soft reset first */
-		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);
-		}
-	}
-
 	hl_hpriv_put(hpriv);
 
 	return 0;