From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: X-Google-Smtp-Source: AB8JxZojBScwdUexXaKScxXcvRYexMTeYzAc9huNcWd7Ju7sIu8YcSwRMLB+iqv58769cqotzCpR ARC-Seal: i=1; a=rsa-sha256; t=1525323846; cv=none; d=google.com; s=arc-20160816; b=VH4NKv3i1Vpe+9w1ftcbLXddOGoGzKXuvZW+wjOpMRWgUwrEl3jwBFtr+0wrh9QMQt sEikhqpHWYMI1dNoi2JTCf3zDeTjeqwQmg2+/4Bi8RDqyPEFPN1MSjJNg3jNAzq1LwRO OGeHOx1U7JZV2kSS2JYV6qCOVK+hVexnOYpD2jw4xPLSI3WxuDelINEmcO/IPGs4Kx9+ GN30/RS2WlJXIQGQeGUQWMeNKu61+8gnmWlD0z2dV1BxoEMyjlCFI3CKbirPAiZ2/mcV f65lP39Wv8o2VbtdAxwgAYz4GebujopRp/WfTUPXb+HdOxv3rajwB9xCdBr5pp01pqPL V95A== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=arc-20160816; h=references:in-reply-to:message-id:date:subject:cc:to:from :arc-authentication-results; bh=rbDJPF8reTwDuA6mqr3Qn8HMsERKz+JaMXLkz+6cP50=; b=Xc+5J1v5QNRN0QI1Z7v1wyzkW8WqVlMD1jYjCNrNxbgLyFPRmz9oKWIh0oKrOYwG2m PxhY2Lnu8ZixSBBw75dp3y9wLTLwEAKn5iv+4r8eNrcZ8hBBVafO3hQrSzslbbOwj4gh gaRrGmOrpbsUq50KrI1P7weSx2oYLek4i4JkTFbH2/WMwgp4motuChYzbDXYkuMcCi3f QhWtdgdqIVqUZ25BtXby5SJIddxzOJk7o7iO0upowrCCj1fQkH+sRxJGJf4Ag550+WWK 8+O4/qPHtA0BT95B4vEqZPgv3W712rCW8ZNZPYQ+7DnzhSUsG0p2gsm5U0IVSiihNl/z EpfQ== ARC-Authentication-Results: i=1; mx.google.com; spf=pass (google.com: domain of poza@qualcomm.com designates 65.197.215.72 as permitted sender) smtp.mailfrom=poza@qualcomm.com Authentication-Results: mx.google.com; spf=pass (google.com: domain of poza@qualcomm.com designates 65.197.215.72 as permitted sender) smtp.mailfrom=poza@qualcomm.com X-IronPort-AV: E=Sophos;i="5.49,356,1520924400"; d="scan'208";a="126361294" X-IronPort-AV: E=McAfee;i="5900,7806,8881"; a="152473228" From: Oza Pawandeep To: Bjorn Helgaas , Philippe Ombredanne , Thomas Gleixner , Greg Kroah-Hartman , Kate Stewart , linux-pci@vger.kernel.org, linux-kernel@vger.kernel.org, Dongdong Liu , Keith Busch , Wei Zhang , Sinan Kaya , Timur Tabi Cc: Oza Pawandeep Subject: [PATCH v15 3/9] PCI/AER: Handle ERR_FATAL with removal and re-enumeration of devices Date: Thu, 3 May 2018 01:03:52 -0400 Message-Id: <1525323838-1735-4-git-send-email-poza@codeaurora.org> X-Mailer: git-send-email 2.7.4 In-Reply-To: <1525323838-1735-1-git-send-email-poza@codeaurora.org> References: <1525323838-1735-1-git-send-email-poza@codeaurora.org> X-getmail-retrieved-from-mailbox: INBOX X-GMAIL-THRID: =?utf-8?q?1599417977501212020?= X-GMAIL-MSGID: =?utf-8?q?1599417977501212020?= X-Mailing-List: linux-kernel@vger.kernel.org List-ID: This patch alters the behavior of handling of ERR_FATAL, where removal of devices is initiated, followed by reset link, followed by re-enumeration. So the errors are handled in a different way as follows: ERR_NONFATAL => call driver recovery entry points ERR_FATAL => remove and re-enumerate please refer to Documentation/PCI/pci-error-recovery.txt for more details. Signed-off-by: Oza Pawandeep diff --git a/drivers/pci/pcie/aer/aerdrv.c b/drivers/pci/pcie/aer/aerdrv.c index 779b387..206f590 100644 --- a/drivers/pci/pcie/aer/aerdrv.c +++ b/drivers/pci/pcie/aer/aerdrv.c @@ -330,6 +330,13 @@ static pci_ers_result_t aer_root_reset(struct pci_dev *dev) reg32 |= ROOT_PORT_INTR_ON_MESG_MASK; pci_write_config_dword(dev, pos + PCI_ERR_ROOT_COMMAND, reg32); + /* + * This function is called only on ERR_FATAL now, and since + * the pci_report_resume is called only in ERR_NONFATAL case, + * the clearing part has to be taken care here. + */ + aer_error_resume(dev); + return PCI_ERS_RESULT_RECOVERED; } diff --git a/drivers/pci/pcie/aer/aerdrv_core.c b/drivers/pci/pcie/aer/aerdrv_core.c index 0ea5acc..655d4e8 100644 --- a/drivers/pci/pcie/aer/aerdrv_core.c +++ b/drivers/pci/pcie/aer/aerdrv_core.c @@ -20,6 +20,7 @@ #include #include #include "aerdrv.h" +#include "../../pci.h" #define PCI_EXP_AER_FLAGS (PCI_EXP_DEVCTL_CERE | PCI_EXP_DEVCTL_NFERE | \ PCI_EXP_DEVCTL_FERE | PCI_EXP_DEVCTL_URRE) @@ -474,6 +475,44 @@ static pci_ers_result_t reset_link(struct pci_dev *dev) return status; } +static pci_ers_result_t do_fatal_recovery(struct pci_dev *dev, int severity) +{ + struct pci_dev *udev; + struct pci_bus *parent; + struct pci_dev *pdev, *temp; + pci_ers_result_t result = PCI_ERS_RESULT_RECOVERED; + + if (severity == AER_FATAL) + pci_cleanup_aer_uncorrect_error_status(dev); + + if (dev->hdr_type == PCI_HEADER_TYPE_BRIDGE) + udev = dev; + else + udev = dev->bus->self; + + parent = udev->subordinate; + pci_lock_rescan_remove(); + list_for_each_entry_safe_reverse(pdev, temp, &parent->devices, + bus_list) { + pci_dev_get(pdev); + pci_dev_set_disconnected(pdev, NULL); + if (pci_has_subordinate(pdev)) + pci_walk_bus(pdev->subordinate, + pci_dev_set_disconnected, NULL); + pci_stop_and_remove_bus_device(pdev); + pci_dev_put(pdev); + } + + result = reset_link(udev); + if (result == PCI_ERS_RESULT_RECOVERED) + if (pcie_wait_for_link(udev, true)) + pci_rescan_bus(udev->bus); + + pci_unlock_rescan_remove(); + + return result; +} + /** * do_recovery - handle nonfatal/fatal error recovery process * @dev: pointer to a pci_dev data structure of agent detecting an error @@ -485,11 +524,15 @@ static pci_ers_result_t reset_link(struct pci_dev *dev) */ static void do_recovery(struct pci_dev *dev, int severity) { - pci_ers_result_t status, result = PCI_ERS_RESULT_RECOVERED; + pci_ers_result_t status; enum pci_channel_state state; - if (severity == AER_FATAL) - state = pci_channel_io_frozen; + if (severity == AER_FATAL) { + status = do_fatal_recovery(dev, severity); + if (status != PCI_ERS_RESULT_RECOVERED) + goto failed; + return; + } else state = pci_channel_io_normal; @@ -498,12 +541,6 @@ static void do_recovery(struct pci_dev *dev, int severity) "error_detected", report_error_detected); - if (severity == AER_FATAL) { - result = reset_link(dev); - if (result != PCI_ERS_RESULT_RECOVERED) - goto failed; - } - if (status == PCI_ERS_RESULT_CAN_RECOVER) status = broadcast_error_message(dev, state, -- 2.7.4