From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-9.0 required=3.0 tests=HEADER_FROM_DIFFERENT_DOMAINS, INCLUDES_PATCH,MAILING_LIST_MULTI,SIGNED_OFF_BY,SPF_PASS,URIBL_BLOCKED, USER_AGENT_GIT autolearn=ham autolearn_force=no version=3.4.0 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id 00C9AC5AE5E for ; Sat, 19 Jan 2019 03:01:32 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by mail.kernel.org (Postfix) with ESMTP id B74E12086D for ; Sat, 19 Jan 2019 03:01:31 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1730458AbfASDB3 (ORCPT ); Fri, 18 Jan 2019 22:01:29 -0500 Received: from szxga06-in.huawei.com ([45.249.212.32]:60146 "EHLO huawei.com" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1729963AbfASDBK (ORCPT ); Fri, 18 Jan 2019 22:01:10 -0500 Received: from DGGEMS408-HUB.china.huawei.com (unknown [172.30.72.59]) by Forcepoint Email with ESMTP id 03A227699DF673D88534; Sat, 19 Jan 2019 11:01:08 +0800 (CST) Received: from linux-ioko.site (10.71.200.31) by DGGEMS408-HUB.china.huawei.com (10.3.19.208) with Microsoft SMTP Server id 14.3.408.0; Sat, 19 Jan 2019 11:01:00 +0800 From: "Wei Hu (Xavier)" To: , CC: , , , , , , , Subject: [PATCH V2 rdma-next 2/3] RDMA/hns: Fix the chip hanging caused by sending mailbox&CMQ during reset Date: Sat, 19 Jan 2019 11:36:06 +0800 Message-ID: <1547868967-115951-3-git-send-email-xavier.huwei@huawei.com> X-Mailer: git-send-email 1.9.1 In-Reply-To: <1547868967-115951-1-git-send-email-xavier.huwei@huawei.com> References: <1547868967-115951-1-git-send-email-xavier.huwei@huawei.com> MIME-Version: 1.0 Content-Type: text/plain X-Originating-IP: [10.71.200.31] X-CFilter-Loop: Reflected Sender: linux-kernel-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On hi08 chip, There is a possibility of chip hanging and some errors when sending mailbox & doorbell during reset. We can fix it by prohibiting mailbox and doorbell during reset and reset occurred to ensure that hardware can work normally. Fixes: a04ff739f2a9 ("RDMA/hns: Add command queue support for hip08 RoCE driver") Signed-off-by: Wei Hu (Xavier) --- drivers/infiniband/hw/hns/hns_roce_cmd.c | 32 ++++-- drivers/infiniband/hw/hns/hns_roce_device.h | 7 ++ drivers/infiniband/hw/hns/hns_roce_hw_v2.c | 154 +++++++++++++++++++++++++++- drivers/infiniband/hw/hns/hns_roce_hw_v2.h | 2 + 4 files changed, 182 insertions(+), 13 deletions(-) diff --git a/drivers/infiniband/hw/hns/hns_roce_cmd.c b/drivers/infiniband/hw/hns/hns_roce_cmd.c index a0ba19d..2acf946 100644 --- a/drivers/infiniband/hw/hns/hns_roce_cmd.c +++ b/drivers/infiniband/hw/hns/hns_roce_cmd.c @@ -176,17 +176,33 @@ int hns_roce_cmd_mbox(struct hns_roce_dev *hr_dev, u64 in_param, u64 out_param, unsigned long in_modifier, u8 op_modifier, u16 op, unsigned long timeout) { - if (hr_dev->is_reset) - return 0; + int ret; + + if (hr_dev->hw->rst_prc_mbox) { + ret = hr_dev->hw->rst_prc_mbox(hr_dev); + if (ret == CMD_RST_PRC_SUCCESS) + return 0; + else if (ret == CMD_RST_PRC_EBUSY) + return -EBUSY; + } if (hr_dev->cmd.use_events) - return hns_roce_cmd_mbox_wait(hr_dev, in_param, out_param, - in_modifier, op_modifier, op, - timeout); + ret = hns_roce_cmd_mbox_wait(hr_dev, in_param, out_param, + in_modifier, op_modifier, op, + timeout); else - return hns_roce_cmd_mbox_poll(hr_dev, in_param, out_param, - in_modifier, op_modifier, op, - timeout); + ret = hns_roce_cmd_mbox_poll(hr_dev, in_param, out_param, + in_modifier, op_modifier, op, + timeout); + + if (ret == CMD_RST_PRC_EBUSY) + return -EBUSY; + + if (ret && (hr_dev->hw->rst_prc_mbox && + hr_dev->hw->rst_prc_mbox(hr_dev) == CMD_RST_PRC_SUCCESS)) + return 0; + + return ret; } EXPORT_SYMBOL_GPL(hns_roce_cmd_mbox); diff --git a/drivers/infiniband/hw/hns/hns_roce_device.h b/drivers/infiniband/hw/hns/hns_roce_device.h index 0f3fe90..65eb4bc 100644 --- a/drivers/infiniband/hw/hns/hns_roce_device.h +++ b/drivers/infiniband/hw/hns/hns_roce_device.h @@ -237,6 +237,12 @@ enum { HNS_ROCE_RST_DIRECT_RETURN = 0, }; +enum { + CMD_RST_PRC_OTHERS, + CMD_RST_PRC_SUCCESS, + CMD_RST_PRC_EBUSY, +}; + #define HNS_ROCE_CMD_SUCCESS 1 #define HNS_ROCE_PORT_DOWN 0 @@ -874,6 +880,7 @@ struct hns_roce_hw { u64 out_param, u32 in_modifier, u8 op_modifier, u16 op, u16 token, int event); int (*chk_mbox)(struct hns_roce_dev *hr_dev, unsigned long timeout); + int (*rst_prc_mbox)(struct hns_roce_dev *hr_dev); int (*set_gid)(struct hns_roce_dev *hr_dev, u8 port, int gid_index, const union ib_gid *gid, const struct ib_gid_attr *attr); int (*set_mac)(struct hns_roce_dev *hr_dev, u8 phy_port, u8 *addr); diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c index 575a233..811e186 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c @@ -712,6 +712,125 @@ static int hns_roce_v2_post_recv(struct ib_qp *ibqp, return ret; } +static int hns_roce_v2_cmd_hw_reseted(struct hns_roce_dev *hr_dev, + unsigned long instance_stage, + unsigned long reset_stage) +{ + /* When hardware reset has been completed once or more, we should stop + * sending mailbox&cmq to hardware. If now in .init_instance() + * function, we should exit with error. If now at HNAE3_INIT_CLIENT + * stage of soft reset process, we should exit with error, and then + * HNAE3_INIT_CLIENT related process can rollback the operation like + * notifing hardware to free resources, HNAE3_INIT_CLIENT related + * process will exit with error to notify NIC driver to reschedule soft + * reset process once again. + */ + hr_dev->is_reset = true; + + if (reset_stage == HNS_ROCE_STATE_RST_INIT || + instance_stage == HNS_ROCE_STATE_INIT) + return CMD_RST_PRC_EBUSY; + + return CMD_RST_PRC_SUCCESS; +} + +static int hns_roce_v2_cmd_hw_resetting(struct hns_roce_dev *hr_dev, + unsigned long instance_stage, + unsigned long reset_stage) +{ + struct hns_roce_v2_priv *priv = (struct hns_roce_v2_priv *)hr_dev->priv; + struct hnae3_handle *handle = priv->handle; + const struct hnae3_ae_ops *ops = handle->ae_algo->ops; + unsigned long end; + + /* When hardware reset is detected, we should stop sending mailbox&cmq + * to hardware, and wait until hardware reset finished. If now + * in .init_instance() function, we should exit with error. If now at + * HNAE3_INIT_CLIENT stage of soft reset process, we should exit with + * error, and then HNAE3_INIT_CLIENT related process can rollback the + * operation like notifing hardware to free resources, HNAE3_INIT_CLIENT + * related process will exit with error to notify NIC driver to + * reschedule soft reset process once again. + */ + end = msecs_to_jiffies(HNS_ROCE_V2_HW_RST_TIMEOUT) + jiffies; + while (ops->get_hw_reset_stat(handle) && time_before(jiffies, end)) + udelay(1); + + if (!ops->get_hw_reset_stat(handle)) + hr_dev->is_reset = true; + else + dev_warn(hr_dev->dev, "hw_resetting!\n"); + + if (!hr_dev->is_reset || reset_stage == HNS_ROCE_STATE_RST_INIT || + instance_stage == HNS_ROCE_STATE_INIT) + return CMD_RST_PRC_EBUSY; + + return CMD_RST_PRC_SUCCESS; +} + +static int hns_roce_v2_cmd_sw_resetting(struct hns_roce_dev *hr_dev) +{ + struct hns_roce_v2_priv *priv = (struct hns_roce_v2_priv *)hr_dev->priv; + struct hnae3_handle *handle = priv->handle; + const struct hnae3_ae_ops *ops = handle->ae_algo->ops; + unsigned long end; + + /* When software reset is detected at .init_instance() function, we + * should stop sending mailbox&cmq to hardware, and + * wait until hardware reset finished, we should exit with error. + */ + end = msecs_to_jiffies(HNS_ROCE_V2_HW_RST_TIMEOUT) + jiffies; + while (ops->ae_dev_reset_cnt(handle) == hr_dev->reset_cnt && + time_before(jiffies, end)) + udelay(1); + + if (ops->ae_dev_reset_cnt(handle) != hr_dev->reset_cnt) + hr_dev->is_reset = true; + else + dev_warn(hr_dev->dev, "reset_cnt no change!\n"); + + return CMD_RST_PRC_EBUSY; +} + +static int hns_roce_v2_rst_process_cmd(struct hns_roce_dev *hr_dev) +{ + struct hns_roce_v2_priv *priv = (struct hns_roce_v2_priv *)hr_dev->priv; + struct hnae3_handle *handle = priv->handle; + const struct hnae3_ae_ops *ops = handle->ae_algo->ops; + unsigned long instance_stage; /* the current instance stage */ + unsigned long reset_stage; /* the current reset stage */ + unsigned long reset_cnt; + bool sw_resetting; + bool hw_resetting; + + if (hr_dev->is_reset) + return CMD_RST_PRC_SUCCESS; + + /* Get information about reset from NIC driver or RoCE driver itself, + * the meaning of the following variables from NIC driver are described + * as below: + * reset_cnt -- The count value of completed hardware reset. + * hw_resetting -- Whether hardware device is resetting now. + * sw_resetting -- Whether NIC's software reset process is running now. + */ + instance_stage = handle->rinfo.instance_state; + reset_stage = handle->rinfo.reset_state; + reset_cnt = ops->ae_dev_reset_cnt(handle); + hw_resetting = ops->get_hw_reset_stat(handle); + sw_resetting = ops->ae_dev_resetting(handle); + + if (reset_cnt != hr_dev->reset_cnt) + return hns_roce_v2_cmd_hw_reseted(hr_dev, instance_stage, + reset_stage); + else if (hw_resetting) + return hns_roce_v2_cmd_hw_resetting(hr_dev, instance_stage, + reset_stage); + else if (sw_resetting && instance_stage == HNS_ROCE_STATE_INIT) + return hns_roce_v2_cmd_sw_resetting(hr_dev); + + return 0; +} + static int hns_roce_cmq_space(struct hns_roce_v2_cmq_ring *ring) { int ntu = ring->next_to_use; @@ -892,8 +1011,8 @@ static int hns_roce_cmq_csq_clean(struct hns_roce_dev *hr_dev) return clean; } -static int hns_roce_cmq_send(struct hns_roce_dev *hr_dev, - struct hns_roce_cmq_desc *desc, int num) +static int __hns_roce_cmq_send(struct hns_roce_dev *hr_dev, + struct hns_roce_cmq_desc *desc, int num) { struct hns_roce_v2_priv *priv = (struct hns_roce_v2_priv *)hr_dev->priv; struct hns_roce_v2_cmq_ring *csq = &priv->cmq.csq; @@ -905,9 +1024,6 @@ static int hns_roce_cmq_send(struct hns_roce_dev *hr_dev, int ret = 0; int ntc; - if (hr_dev->is_reset) - return 0; - spin_lock_bh(&csq->lock); if (num > hns_roce_cmq_space(csq)) { @@ -982,6 +1098,30 @@ static int hns_roce_cmq_send(struct hns_roce_dev *hr_dev, return ret; } +int hns_roce_cmq_send(struct hns_roce_dev *hr_dev, + struct hns_roce_cmq_desc *desc, int num) +{ + int retval; + int ret; + + ret = hns_roce_v2_rst_process_cmd(hr_dev); + if (ret == CMD_RST_PRC_SUCCESS) + return 0; + if (ret == CMD_RST_PRC_EBUSY) + return ret; + + ret = __hns_roce_cmq_send(hr_dev, desc, num); + if (ret) { + retval = hns_roce_v2_rst_process_cmd(hr_dev); + if (retval == CMD_RST_PRC_SUCCESS) + return 0; + else if (retval == CMD_RST_PRC_EBUSY) + return retval; + } + + return ret; +} + static int hns_roce_cmq_query_hw_info(struct hns_roce_dev *hr_dev) { struct hns_roce_query_version *resp; @@ -1857,6 +1997,9 @@ static int hns_roce_v2_chk_mbox(struct hns_roce_dev *hr_dev, status = hns_roce_v2_cmd_complete(hr_dev); if (status != 0x1) { + if (status == CMD_RST_PRC_EBUSY) + return status; + dev_err(dev, "mailbox status 0x%x!\n", status); return -EBUSY; } @@ -5978,6 +6121,7 @@ static int hns_roce_v2_post_srq_recv(struct ib_srq *ibsrq, .hw_exit = hns_roce_v2_exit, .post_mbox = hns_roce_v2_post_mbox, .chk_mbox = hns_roce_v2_chk_mbox, + .rst_prc_mbox = hns_roce_v2_rst_process_cmd, .set_gid = hns_roce_v2_set_gid, .set_mac = hns_roce_v2_set_mac, .write_mtpt = hns_roce_v2_write_mtpt, diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.h b/drivers/infiniband/hw/hns/hns_roce_hw_v2.h index 938d36a..f22094e 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.h +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.h @@ -96,6 +96,8 @@ #define HNS_ROCE_V2_UC_RC_SGE_NUM_IN_WQE 2 #define HNS_ROCE_V2_RSV_QPS 8 +#define HNS_ROCE_V2_HW_RST_TIMEOUT 1000 + #define HNS_ROCE_CONTEXT_HOP_NUM 1 #define HNS_ROCE_SCCC_HOP_NUM 1 #define HNS_ROCE_MTT_HOP_NUM 1 -- 1.9.1