From patchwork Fri May 15 05:46:22 2015 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Wei Yang X-Patchwork-Id: 6411321 X-Patchwork-Delegate: bhelgaas@google.com Return-Path: X-Original-To: patchwork-linux-pci@patchwork.kernel.org Delivered-To: patchwork-parsemail@patchwork1.web.kernel.org Received: from mail.kernel.org (mail.kernel.org [198.145.29.136]) by patchwork1.web.kernel.org (Postfix) with ESMTP id 8BA4F9F1CC for ; Fri, 15 May 2015 05:51:56 +0000 (UTC) Received: from mail.kernel.org (localhost [127.0.0.1]) by mail.kernel.org (Postfix) with ESMTP id 780E420452 for ; Fri, 15 May 2015 05:51:55 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by mail.kernel.org (Postfix) with ESMTP id 94E5520451 for ; Fri, 15 May 2015 05:51:50 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753399AbbEOFvt (ORCPT ); Fri, 15 May 2015 01:51:49 -0400 Received: from e23smtp04.au.ibm.com ([202.81.31.146]:54108 "EHLO e23smtp04.au.ibm.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753087AbbEOFvt (ORCPT ); Fri, 15 May 2015 01:51:49 -0400 Received: from /spool/local by e23smtp04.au.ibm.com with IBM ESMTP SMTP Gateway: Authorized Use Only! Violators will be prosecuted for from ; Fri, 15 May 2015 15:51:47 +1000 Received: from d23dlp02.au.ibm.com (202.81.31.213) by e23smtp04.au.ibm.com (202.81.31.210) with IBM ESMTP SMTP Gateway: Authorized Use Only! Violators will be prosecuted; Fri, 15 May 2015 15:51:44 +1000 Received: from d23relay10.au.ibm.com (d23relay10.au.ibm.com [9.190.26.77]) by d23dlp02.au.ibm.com (Postfix) with ESMTP id CCF5B2BB0052 for ; Fri, 15 May 2015 15:51:43 +1000 (EST) Received: from d23av01.au.ibm.com (d23av01.au.ibm.com [9.190.234.96]) by d23relay10.au.ibm.com (8.14.9/8.14.9/NCO v10.0) with ESMTP id t4F5pZRe36962456 for ; Fri, 15 May 2015 15:51:43 +1000 Received: from d23av01.au.ibm.com (localhost [127.0.0.1]) by d23av01.au.ibm.com (8.14.4/8.14.4/NCO v10.0 AVout) with ESMTP id t4F5pATa003522 for ; Fri, 15 May 2015 15:51:11 +1000 Received: from localhost ([9.123.251.150]) by d23av01.au.ibm.com (8.14.4/8.14.4/NCO v10.0 AVin) with ESMTP id t4F5pASe003229; Fri, 15 May 2015 15:51:10 +1000 From: Wei Yang To: gwshan@linux.vnet.ibm.com, bhelgaas@google.com Cc: linuxppc-dev@lists.ozlabs.org, linux-pci@vger.kernel.org, Wei Yang Subject: [PATCH V4 07/11] powerpc/powernv: Support EEH reset for VFs Date: Fri, 15 May 2015 13:46:22 +0800 Message-Id: <1431668786-30371-8-git-send-email-weiyang@linux.vnet.ibm.com> X-Mailer: git-send-email 1.7.9.5 In-Reply-To: <1431668786-30371-1-git-send-email-weiyang@linux.vnet.ibm.com> References: <1431668786-30371-1-git-send-email-weiyang@linux.vnet.ibm.com> X-TM-AS-MML: disable X-Content-Scanned: Fidelis XPS MAILER x-cbid: 15051505-0013-0000-0000-00000141FF8B Sender: linux-pci-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: linux-pci@vger.kernel.org X-Spam-Status: No, score=-6.9 required=5.0 tests=BAYES_00, RCVD_IN_DNSWL_HI, T_RP_MATCHES_RCVD, UNPARSEABLE_RELAY autolearn=unavailable version=3.3.1 X-Spam-Checker-Version: SpamAssassin 3.3.1 (2010-03-16) on mail.kernel.org X-Virus-Scanned: ClamAV using ClamSMTP Before VF PE is introduced, there isn't a method to reset an individual PCI function. And since skiboot firmware is not aware of the VF, the VF's reset should be done in kernel. This patch introduces a function pnv_eeh_vf_pe_reset() to do the FLR or AF FLR to a VF. Signed-off-by: Wei Yang --- arch/powerpc/include/asm/eeh.h | 1 + arch/powerpc/platforms/powernv/eeh-powernv.c | 123 +++++++++++++++++++++++++- 2 files changed, 123 insertions(+), 1 deletion(-) diff --git a/arch/powerpc/include/asm/eeh.h b/arch/powerpc/include/asm/eeh.h index c1fde48..3d64cf3 100644 --- a/arch/powerpc/include/asm/eeh.h +++ b/arch/powerpc/include/asm/eeh.h @@ -134,6 +134,7 @@ struct eeh_dev { int pcix_cap; /* Saved PCIx capability */ int pcie_cap; /* Saved PCIe capability */ int aer_cap; /* Saved AER capability */ + int af_cap; /* Saved AF capability */ struct eeh_pe *pe; /* Associated PE */ struct list_head list; /* Form link list in the PE */ struct pci_controller *phb; /* Associated PHB */ diff --git a/arch/powerpc/platforms/powernv/eeh-powernv.c b/arch/powerpc/platforms/powernv/eeh-powernv.c index 31344a4..61f1a55 100644 --- a/arch/powerpc/platforms/powernv/eeh-powernv.c +++ b/arch/powerpc/platforms/powernv/eeh-powernv.c @@ -402,6 +402,7 @@ static void *pnv_eeh_probe(struct pci_dn *pdn, void *data) edev->pcix_cap = pnv_eeh_find_cap(pdn, PCI_CAP_ID_PCIX); edev->pcie_cap = pnv_eeh_find_cap(pdn, PCI_CAP_ID_EXP); edev->aer_cap = pnv_eeh_find_ecap(pdn, PCI_EXT_CAP_ID_ERR); + edev->af_cap = pnv_eeh_find_cap(pdn, PCI_CAP_ID_AF); if ((edev->class_code >> 8) == PCI_CLASS_BRIDGE_PCI) { edev->mode |= EEH_DEV_BRIDGE; if (edev->pcie_cap) { @@ -891,6 +892,117 @@ static int pnv_eeh_bridge_reset(struct pci_dev *dev, int option) return 0; } +static int pnv_pci_wait_for_pending(struct pci_dn *pdn, int pos, u16 mask) +{ + int i; + + /* Wait for Transaction Pending bit clean */ + for (i = 0; i < 4; i++) { + u32 status; + if (i) + msleep((1 << (i - 1)) * 100); + + eeh_ops->read_config(pdn, pos, 2, &status); + if (!(status & mask)) + return 1; + } + + return 0; +} + +static int pnv_eeh_do_flr(struct pci_dn *pdn, int option) +{ + u32 cap; + struct eeh_dev *edev = pdn_to_eeh_dev(pdn); + + eeh_ops->read_config(pdn, edev->pcie_cap + PCI_EXP_DEVCAP, 4, &cap); + if (!(cap & PCI_EXP_DEVCAP_FLR)) + return -ENOTTY; + + if (!pnv_pci_wait_for_pending(pdn, edev->pcie_cap + PCI_EXP_DEVSTA, + PCI_EXP_DEVSTA_TRPND)) + pr_err("%04x:%02x:%02x:%01x timed out waiting for pending " + "transaction; performing function level reset anyway\n", + edev->phb->global_number, pdn->busno, + PCI_SLOT(pdn->devfn), PCI_FUNC(pdn->devfn)); + + eeh_ops->read_config(pdn, edev->pcie_cap + PCI_EXP_DEVCTL, 4, &cap); + if (option == EEH_RESET_DEACTIVATE) + cap &= ~PCI_EXP_DEVCTL_BCR_FLR; + else + cap |= PCI_EXP_DEVCTL_BCR_FLR; + eeh_ops->write_config(pdn, edev->pcie_cap + PCI_EXP_DEVCTL, 4, cap); + msleep(100); + return 0; +} + +static int pnv_eeh_do_af_flr(struct pci_dn *pdn, int option) +{ + u32 cap; + struct eeh_dev *edev = pdn_to_eeh_dev(pdn); + + if (!edev->af_cap) + return -ENOTTY; + + eeh_ops->read_config(pdn, edev->af_cap + PCI_AF_CAP, 1, &cap); + if (!(cap & PCI_AF_CAP_TP) || !(cap & PCI_AF_CAP_FLR)) + return -ENOTTY; + + /* + * Wait for Transaction Pending bit to clear. A word-aligned test + * is used, so we use the conrol offset rather than status and shift + * the test bit to match. + */ + if (!pnv_pci_wait_for_pending(pdn, edev->af_cap + PCI_AF_CTRL, + PCI_AF_STATUS_TP << 8)) + pr_err("%04x:%02x:%02x:%01x timed out waiting for pending " + "transaction; performing AF function level reset anyway\n", + edev->phb->global_number, pdn->busno, + PCI_SLOT(pdn->devfn), PCI_FUNC(pdn->devfn)); + + if (option == EEH_RESET_DEACTIVATE) + eeh_ops->write_config(pdn, edev->af_cap + PCI_AF_CTRL, 1, 0); + else + eeh_ops->write_config(pdn, edev->af_cap + PCI_AF_CTRL, 1, + PCI_AF_CTRL_FLR); + msleep(100); + return 0; +} + +static int pnv_eeh_reset_vf(struct pci_dn *pdn, int option) +{ + int rc; + + might_sleep(); + + rc = pnv_eeh_do_flr(pdn, option); + if (rc != -ENOTTY) + goto done; + + rc = pnv_eeh_do_af_flr(pdn, option); + if (rc != -ENOTTY) + goto done; + +done: + return rc; +} + +static int pnv_eeh_vf_pe_reset(struct eeh_pe *pe, int option) +{ + struct eeh_dev *edev, *tmp; + struct pci_dn *pdn; + int ret = 0; + + eeh_pe_for_each_dev(pe, edev, tmp) { + pdn = eeh_dev_to_pdn(edev); + ret |= pnv_eeh_reset_vf(pdn, option); + if (ret) + return ret; + } + + return ret; +} + void pnv_pci_reset_secondary_bus(struct pci_dev *dev) { struct pci_controller *hose; @@ -966,7 +1078,9 @@ static int pnv_eeh_reset(struct eeh_pe *pe, int option) } bus = eeh_pe_bus_get(pe); - if (pci_is_root_bus(bus) || + if (pe->type & EEH_PE_VF) + ret = pnv_eeh_vf_pe_reset(pe, option); + else if (pci_is_root_bus(bus) || pci_is_root_bus(bus->parent)) ret = pnv_eeh_root_reset(hose, option); else @@ -1106,6 +1220,13 @@ static inline bool pnv_eeh_cfg_blocked(struct pci_dn *pdn) if (!edev || !edev->pe) return false; + /* + * For VF's reset operation, we need to rely on the kernel to + * do those PCI config operations since firmware isn't aware of VFs. + */ + if ((edev->physfn) && (edev->pe->state & EEH_PE_RESET)) + return false; + if (edev->pe->state & EEH_PE_CFG_BLOCKED) return true;