From 37988216de8e8df46e72fb4a76f437f7c49d7b79 Mon Sep 17 00:00:00 2001 From: Jiaran Zhang Date: Mon, 7 Jun 2021 19:18:10 +0800 Subject: [PATCH] net: hns3: add a separate error handling task Error handling and recovery logic are intertwined. Error handling (i.e. error identification, clearing error sources and initiation of recovery) is done in context of reset task. If certain hardware errors get delivered during driver init time, which can cause driver init/loading to fail. Introduce a separate error handling task to ensure below: 1. Reset logic remains independent of the error handling logic. 2. Add the hclge_errhand_task_schedule to schedule error recovery tasks, This will ensure that common misellaneous MSI-X interrupt are re-enabled quickly. Signed-off-by: Jiaran Zhang Signed-off-by: Salil Mehta Signed-off-by: Yufeng Mo Signed-off-by: Guangbin Huang Signed-off-by: David S. Miller --- .../hisilicon/hns3/hns3pf/hclge_err.c | 4 +- .../hisilicon/hns3/hns3pf/hclge_main.c | 38 +++++++++++++++++++ .../hisilicon/hns3/hns3pf/hclge_main.h | 1 + 3 files changed, 41 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c index 8223d699cd940..f125aa4258729 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c @@ -1940,8 +1940,8 @@ int hclge_handle_hw_msix_error(struct hclge_dev *hdev, if (!test_bit(HCLGE_STATE_SERVICE_INITED, &hdev->state)) { dev_err(dev, - "Can't handle - MSIx error reported during dev init\n"); - return 0; + "failed to handle msix error during dev init\n"); + return -EAGAIN; } return hclge_handle_all_hw_msix_error(hdev, reset_requests); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index 6ecc106af334f..8a431e124adb6 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -2843,6 +2843,14 @@ static void hclge_reset_task_schedule(struct hclge_dev *hdev) hclge_wq, &hdev->service_task, 0); } +static void hclge_errhand_task_schedule(struct hclge_dev *hdev) +{ + if (!test_bit(HCLGE_STATE_REMOVING, &hdev->state) && + !test_and_set_bit(HCLGE_STATE_ERR_SERVICE_SCHED, &hdev->state)) + mod_delayed_work_on(cpumask_first(&hdev->affinity_mask), + hclge_wq, &hdev->service_task, 0); +} + void hclge_task_schedule(struct hclge_dev *hdev, unsigned long delay_time) { if (!test_bit(HCLGE_STATE_REMOVING, &hdev->state) && @@ -4264,6 +4272,36 @@ static void hclge_reset_subtask(struct hclge_dev *hdev) hdev->reset_type = HNAE3_NONE_RESET; } +static void hclge_misc_err_recovery(struct hclge_dev *hdev) +{ + struct hnae3_ae_dev *ae_dev = pci_get_drvdata(hdev->pdev); + struct device *dev = &hdev->pdev->dev; + u32 msix_sts_reg; + + msix_sts_reg = hclge_read_dev(&hdev->hw, HCLGE_MISC_VECTOR_INT_STS); + + if (msix_sts_reg & HCLGE_VECTOR0_REG_MSIX_MASK) { + if (hclge_handle_hw_msix_error(hdev, + &hdev->default_reset_request)) + dev_info(dev, "received msix interrupt 0x%x\n", + msix_sts_reg); + + if (hdev->default_reset_request) + if (ae_dev->ops->reset_event) + ae_dev->ops->reset_event(hdev->pdev, NULL); + } + + hclge_enable_vector(&hdev->misc_vector, true); +} + +static void hclge_errhand_service_task(struct hclge_dev *hdev) +{ + if (!test_and_clear_bit(HCLGE_STATE_ERR_SERVICE_SCHED, &hdev->state)) + return; + + hclge_misc_err_recovery(hdev); +} + static void hclge_reset_service_task(struct hclge_dev *hdev) { if (!test_and_clear_bit(HCLGE_STATE_RST_SERVICE_SCHED, &hdev->state)) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h index 7595f841aaacc..9b8abb5d7a8ee 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h @@ -221,6 +221,7 @@ enum HCLGE_DEV_STATE { HCLGE_STATE_RST_HANDLING, HCLGE_STATE_MBX_SERVICE_SCHED, HCLGE_STATE_MBX_HANDLING, + HCLGE_STATE_ERR_SERVICE_SCHED, HCLGE_STATE_STATISTICS_UPDATING, HCLGE_STATE_CMD_DISABLE, HCLGE_STATE_LINK_UPDATING, -- 2.39.5