From nobody Mon Sep 29 22:49:04 2025 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id B2CB7C25B0D for ; Tue, 16 Aug 2022 00:52:33 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S239227AbiHPAw2 (ORCPT ); Mon, 15 Aug 2022 20:52:28 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:36186 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1349786AbiHPAqp (ORCPT ); Mon, 15 Aug 2022 20:46:45 -0400 Received: from dfw.source.kernel.org (dfw.source.kernel.org [IPv6:2604:1380:4641:c500::1]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 8033C196868; Mon, 15 Aug 2022 13:45:22 -0700 (PDT) Received: from smtp.kernel.org (relay.kernel.org [52.25.139.140]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by dfw.source.kernel.org (Postfix) with ESMTPS id A6C5561241; Mon, 15 Aug 2022 20:45:21 +0000 (UTC) Received: by smtp.kernel.org (Postfix) with ESMTPSA id AE35CC433C1; Mon, 15 Aug 2022 20:45:20 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=linuxfoundation.org; s=korg; t=1660596321; bh=Tr2M4nayNpPSq3PjjPGO+MGyVIhL9QGHlDEJcNCeS/8=; h=From:To:Cc:Subject:Date:In-Reply-To:References:From; b=arMA1MurgJkuSj+4lFAuTFpeerDxOgMbe3uZTC2Hy+nfB3EKTIdfT2h20nWtyqQKH /BVeqPtXcHrYOWHegWIwuNfrHqWgltexJHoOszNWarZZLXe9P0LFXegYbBpk9/2gQ3 Mhz9RR6uTXbcvp2w8ClSPYHKT6zkO8dyQZq2xQI4= From: Greg Kroah-Hartman To: linux-kernel@vger.kernel.org Cc: Greg Kroah-Hartman , stable@vger.kernel.org, Quinn Tran , Nilesh Javali , "Martin K. Petersen" Subject: [PATCH 5.19 1041/1157] scsi: qla2xxx: Wind down adapter after PCIe error Date: Mon, 15 Aug 2022 20:06:37 +0200 Message-Id: <20220815180521.643619758@linuxfoundation.org> X-Mailer: git-send-email 2.37.2 In-Reply-To: <20220815180439.416659447@linuxfoundation.org> References: <20220815180439.416659447@linuxfoundation.org> User-Agent: quilt/0.67 MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Type: text/plain; charset="utf-8" From: Quinn Tran commit d3117c83ba316b3200d9f2fe900f2b9a5525a25c upstream. Put adapter into a wind down state if OS does not make any attempt to recover the adapter after PCIe error. Link: https://lore.kernel.org/r/20220616053508.27186-4-njavali@marvell.com Cc: stable@vger.kernel.org Signed-off-by: Quinn Tran Signed-off-by: Nilesh Javali Signed-off-by: Martin K. Petersen Signed-off-by: Greg Kroah-Hartman --- drivers/scsi/qla2xxx/qla_bsg.c | 10 +++++++- drivers/scsi/qla2xxx/qla_def.h | 4 +++ drivers/scsi/qla2xxx/qla_init.c | 20 ++++++++++++++++ drivers/scsi/qla2xxx/qla_os.c | 48 +++++++++++++++++++++++++++++++++++= +++++ 4 files changed, 81 insertions(+), 1 deletion(-) --- a/drivers/scsi/qla2xxx/qla_bsg.c +++ b/drivers/scsi/qla2xxx/qla_bsg.c @@ -2975,6 +2975,13 @@ qla24xx_bsg_timeout(struct bsg_job *bsg_ =20 ql_log(ql_log_info, vha, 0x708b, "%s CMD timeout. bsg ptr %p.\n", __func__, bsg_job); + + if (qla2x00_isp_reg_stat(ha)) { + ql_log(ql_log_info, vha, 0x9007, + "PCI/Register disconnect.\n"); + qla_pci_set_eeh_busy(vha); + } + /* find the bsg job from the active list of commands */ spin_lock_irqsave(&ha->hardware_lock, flags); for (que =3D 0; que < ha->max_req_queues; que++) { @@ -2992,7 +2999,8 @@ qla24xx_bsg_timeout(struct bsg_job *bsg_ sp->u.bsg_job =3D=3D bsg_job) { req->outstanding_cmds[cnt] =3D NULL; spin_unlock_irqrestore(&ha->hardware_lock, flags); - if (ha->isp_ops->abort_command(sp)) { + + if (!ha->flags.eeh_busy && ha->isp_ops->abort_command(sp)) { ql_log(ql_log_warn, vha, 0x7089, "mbx abort_command failed.\n"); bsg_reply->result =3D -EIO; --- a/drivers/scsi/qla2xxx/qla_def.h +++ b/drivers/scsi/qla2xxx/qla_def.h @@ -4048,6 +4048,9 @@ struct qla_hw_data { uint32_t n2n_fw_acc_sec:1; uint32_t plogi_template_valid:1; uint32_t port_isolated:1; + uint32_t eeh_flush:2; +#define EEH_FLUSH_RDY 1 +#define EEH_FLUSH_DONE 2 } flags; =20 uint16_t max_exchg; @@ -4082,6 +4085,7 @@ struct qla_hw_data { uint32_t rsp_que_len; uint32_t req_que_off; uint32_t rsp_que_off; + unsigned long eeh_jif; =20 /* Multi queue data structs */ device_reg_t *mqiobase; --- a/drivers/scsi/qla2xxx/qla_init.c +++ b/drivers/scsi/qla2xxx/qla_init.c @@ -47,6 +47,7 @@ qla2x00_sp_timeout(struct timer_list *t) { srb_t *sp =3D from_timer(sp, t, u.iocb_cmd.timer); struct srb_iocb *iocb; + scsi_qla_host_t *vha =3D sp->vha; =20 WARN_ON(irqs_disabled()); iocb =3D &sp->u.iocb_cmd; @@ -54,6 +55,12 @@ qla2x00_sp_timeout(struct timer_list *t) =20 /* ref: TMR */ kref_put(&sp->cmd_kref, qla2x00_sp_release); + + if (vha && qla2x00_isp_reg_stat(vha->hw)) { + ql_log(ql_log_info, vha, 0x9008, + "PCI/Register disconnect.\n"); + qla_pci_set_eeh_busy(vha); + } } =20 void qla2x00_sp_free(srb_t *sp) @@ -9702,6 +9709,12 @@ int qla2xxx_disable_port(struct Scsi_Hos =20 vha->hw->flags.port_isolated =3D 1; =20 + if (qla2x00_isp_reg_stat(vha->hw)) { + ql_log(ql_log_info, vha, 0x9006, + "PCI/Register disconnect, exiting.\n"); + qla_pci_set_eeh_busy(vha); + return FAILED; + } if (qla2x00_chip_is_down(vha)) return 0; =20 @@ -9717,6 +9730,13 @@ int qla2xxx_enable_port(struct Scsi_Host { scsi_qla_host_t *vha =3D shost_priv(host); =20 + if (qla2x00_isp_reg_stat(vha->hw)) { + ql_log(ql_log_info, vha, 0x9001, + "PCI/Register disconnect, exiting.\n"); + qla_pci_set_eeh_busy(vha); + return FAILED; + } + vha->hw->flags.port_isolated =3D 0; /* Set the flag to 1, so that isp_abort can proceed */ vha->flags.online =3D 1; --- a/drivers/scsi/qla2xxx/qla_os.c +++ b/drivers/scsi/qla2xxx/qla_os.c @@ -333,6 +333,11 @@ MODULE_PARM_DESC(ql2xabts_wait_nvme, "To wait for ABTS response on I/O timeouts for NVMe. (default: 1)"); =20 =20 +u32 ql2xdelay_before_pci_error_handling =3D 5; +module_param(ql2xdelay_before_pci_error_handling, uint, 0644); +MODULE_PARM_DESC(ql2xdelay_before_pci_error_handling, + "Number of seconds delayed before qla begin PCI error self-handling (defa= ult: 5).\n"); + static void qla2x00_clear_drv_active(struct qla_hw_data *); static void qla2x00_free_device(scsi_qla_host_t *); static int qla2xxx_map_queues(struct Scsi_Host *shost); @@ -7257,6 +7262,44 @@ static void qla_heart_beat(struct scsi_q } } =20 +static void qla_wind_down_chip(scsi_qla_host_t *vha) +{ + struct qla_hw_data *ha =3D vha->hw; + + if (!ha->flags.eeh_busy) + return; + if (ha->pci_error_state) + /* system is trying to recover */ + return; + + /* + * Current system is not handling PCIE error. At this point, this is + * best effort to wind down the adapter. + */ + if (time_after_eq(jiffies, ha->eeh_jif + ql2xdelay_before_pci_error_handl= ing * HZ) && + !ha->flags.eeh_flush) { + ql_log(ql_log_info, vha, 0x9009, + "PCI Error detected, attempting to reset hardware.\n"); + + ha->isp_ops->reset_chip(vha); + ha->isp_ops->disable_intrs(ha); + + ha->flags.eeh_flush =3D EEH_FLUSH_RDY; + ha->eeh_jif =3D jiffies; + + } else if (ha->flags.eeh_flush =3D=3D EEH_FLUSH_RDY && + time_after_eq(jiffies, ha->eeh_jif + 5 * HZ)) { + pci_clear_master(ha->pdev); + + /* flush all command */ + qla2x00_abort_isp_cleanup(vha); + ha->flags.eeh_flush =3D EEH_FLUSH_DONE; + + ql_log(ql_log_info, vha, 0x900a, + "PCI Error handling complete, all IOs aborted.\n"); + } +} + /************************************************************************** * qla2x00_timer * @@ -7280,6 +7323,8 @@ qla2x00_timer(struct timer_list *t) fc_port_t *fcport =3D NULL; =20 if (ha->flags.eeh_busy) { + qla_wind_down_chip(vha); + ql_dbg(ql_dbg_timer, vha, 0x6000, "EEH =3D %d, restarting timer.\n", ha->flags.eeh_busy); @@ -7860,6 +7905,9 @@ void qla_pci_set_eeh_busy(struct scsi_ql =20 spin_lock_irqsave(&base_vha->work_lock, flags); if (!ha->flags.eeh_busy) { + ha->eeh_jif =3D jiffies; + ha->flags.eeh_flush =3D 0; + ha->flags.eeh_busy =3D 1; do_cleanup =3D true; }