From patchwork Wed Sep 26 17:47:54 2018 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Dennis Dalessandro X-Patchwork-Id: 10616465 Return-Path: Received: from mail.wl.linuxfoundation.org (pdx-wl-mail.web.codeaurora.org [172.30.200.125]) by pdx-korg-patchwork-2.web.codeaurora.org (Postfix) with ESMTP id 761803E9D for ; Wed, 26 Sep 2018 17:48:00 +0000 (UTC) Received: from mail.wl.linuxfoundation.org (localhost [127.0.0.1]) by mail.wl.linuxfoundation.org (Postfix) with ESMTP id 646672B402 for ; Wed, 26 Sep 2018 17:48:00 +0000 (UTC) Received: by mail.wl.linuxfoundation.org (Postfix, from userid 486) id 54BDA2B43F; Wed, 26 Sep 2018 17:48:00 +0000 (UTC) X-Spam-Checker-Version: SpamAssassin 3.3.1 (2010-03-16) on pdx-wl-mail.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-7.9 required=2.0 tests=BAYES_00,MAILING_LIST_MULTI, RCVD_IN_DNSWL_HI autolearn=ham version=3.3.1 Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by mail.wl.linuxfoundation.org (Postfix) with ESMTP id E730F2B402 for ; Wed, 26 Sep 2018 17:47:59 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1727823AbeI0ACC (ORCPT ); Wed, 26 Sep 2018 20:02:02 -0400 Received: from mga07.intel.com ([134.134.136.100]:48661 "EHLO mga07.intel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1727649AbeI0ACC (ORCPT ); Wed, 26 Sep 2018 20:02:02 -0400 X-Amp-Result: SKIPPED(no attachment in message) X-Amp-File-Uploaded: False Received: from fmsmga005.fm.intel.com ([10.253.24.32]) by orsmga105.jf.intel.com with ESMTP/TLS/DHE-RSA-AES256-GCM-SHA384; 26 Sep 2018 10:47:58 -0700 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.54,307,1534834800"; d="scan'208";a="265954057" Received: from scymds02.sc.intel.com ([10.82.195.37]) by fmsmga005.fm.intel.com with ESMTP; 26 Sep 2018 10:47:55 -0700 Received: from scvm10.sc.intel.com (scvm10.sc.intel.com [10.82.195.27]) by scymds02.sc.intel.com with ESMTP id w8QHlsvE010631; Wed, 26 Sep 2018 10:47:54 -0700 Received: from scvm10.sc.intel.com (localhost [127.0.0.1]) by scvm10.sc.intel.com with ESMTP id w8QHlsLl011198; Wed, 26 Sep 2018 10:47:54 -0700 Subject: [PATCH for-next 1/2] IB/hfi1: Add mtu check for operational data VLs From: Dennis Dalessandro To: jgg@ziepe.ca, dledford@redhat.com Cc: linux-rdma@vger.kernel.org, "Michael J. Ruhl" , Mike Marciniszyn , Alex Estrin Date: Wed, 26 Sep 2018 10:47:54 -0700 Message-ID: <20180926174747.4570.21640.stgit@scvm10.sc.intel.com> In-Reply-To: <20180926174525.4570.83126.stgit@scvm10.sc.intel.com> References: <20180926174525.4570.83126.stgit@scvm10.sc.intel.com> User-Agent: StGit/0.17.1-18-g2e886-dirty MIME-Version: 1.0 Sender: linux-rdma-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: linux-rdma@vger.kernel.org X-Virus-Scanned: ClamAV using ClamSMTP From: Alex Estrin Since Virtual Lanes BCT credits and MTU are set through separate MADs, we have to ensure both are valid, and data VLs are ready for transmission before we allow port transition to Armed state. Fixes: 5e2d6764a729 ("IB/hfi1: Verify port data VLs credits on transition to Armed") Reviewed-by: Mike Marciniszyn Reviewed-by: Michael J. Ruhl Signed-off-by: Alex Estrin Signed-off-by: Dennis Dalessandro --- drivers/infiniband/hw/hfi1/chip.c | 26 ++++++++++++++++++++++---- 1 files changed, 22 insertions(+), 4 deletions(-) diff --git a/drivers/infiniband/hw/hfi1/chip.c b/drivers/infiniband/hw/hfi1/chip.c index bdcc4f1..9b20479 100644 --- a/drivers/infiniband/hw/hfi1/chip.c +++ b/drivers/infiniband/hw/hfi1/chip.c @@ -10561,12 +10561,29 @@ void set_link_down_reason(struct hfi1_pportdata *ppd, u8 lcl_reason, } } -/* - * Verify if BCT for data VLs is non-zero. +/** + * data_vls_operational() - Verify if data VL BCT credits and MTU + * are both set. + * @ppd: pointer to hfi1_pportdata structure + * + * Return: true - Ok, false -otherwise. */ static inline bool data_vls_operational(struct hfi1_pportdata *ppd) { - return !!ppd->actual_vls_operational; + int i; + u64 reg; + + if (!ppd->actual_vls_operational) + return false; + + for (i = 0; i < ppd->vls_supported; i++) { + reg = read_csr(ppd->dd, SEND_CM_CREDIT_VL + (8 * i)); + if ((reg && !ppd->dd->vld[i].mtu) || + (!reg && ppd->dd->vld[i].mtu)) + return false; + } + + return true; } /* @@ -10679,7 +10696,8 @@ int set_link_state(struct hfi1_pportdata *ppd, u32 state) if (!data_vls_operational(ppd)) { dd_dev_err(dd, - "%s: data VLs not operational\n", __func__); + "%s: Invalid data VL credits or mtu\n", + __func__); ret = -EINVAL; break; } From patchwork Wed Sep 26 17:48:04 2018 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Dennis Dalessandro X-Patchwork-Id: 10616467 Return-Path: Received: from mail.wl.linuxfoundation.org (pdx-wl-mail.web.codeaurora.org [172.30.200.125]) by pdx-korg-patchwork-2.web.codeaurora.org (Postfix) with ESMTP id 92EBD913 for ; Wed, 26 Sep 2018 17:48:06 +0000 (UTC) Received: from mail.wl.linuxfoundation.org (localhost [127.0.0.1]) by mail.wl.linuxfoundation.org (Postfix) with ESMTP id 81DFC2B016 for ; Wed, 26 Sep 2018 17:48:06 +0000 (UTC) Received: by mail.wl.linuxfoundation.org (Postfix, from userid 486) id 75CDE2B040; Wed, 26 Sep 2018 17:48:06 +0000 (UTC) X-Spam-Checker-Version: SpamAssassin 3.3.1 (2010-03-16) on pdx-wl-mail.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-7.9 required=2.0 tests=BAYES_00,MAILING_LIST_MULTI, RCVD_IN_DNSWL_HI autolearn=ham version=3.3.1 Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by mail.wl.linuxfoundation.org (Postfix) with ESMTP id 1C2AF2B016 for ; Wed, 26 Sep 2018 17:48:06 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1727649AbeI0ACI (ORCPT ); Wed, 26 Sep 2018 20:02:08 -0400 Received: from mga04.intel.com ([192.55.52.120]:54306 "EHLO mga04.intel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1727280AbeI0ACI (ORCPT ); Wed, 26 Sep 2018 20:02:08 -0400 X-Amp-Result: SKIPPED(no attachment in message) X-Amp-File-Uploaded: False Received: from fmsmga005.fm.intel.com ([10.253.24.32]) by fmsmga104.fm.intel.com with ESMTP/TLS/DHE-RSA-AES256-GCM-SHA384; 26 Sep 2018 10:48:05 -0700 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.54,307,1534834800"; d="scan'208";a="265954119" Received: from scymds02.sc.intel.com ([10.82.195.37]) by fmsmga005.fm.intel.com with ESMTP; 26 Sep 2018 10:48:05 -0700 Received: from scvm10.sc.intel.com (scvm10.sc.intel.com [10.82.195.27]) by scymds02.sc.intel.com with ESMTP id w8QHm4np010728; Wed, 26 Sep 2018 10:48:04 -0700 Received: from scvm10.sc.intel.com (localhost [127.0.0.1]) by scvm10.sc.intel.com with ESMTP id w8QHm48Y011309; Wed, 26 Sep 2018 10:48:04 -0700 Subject: [PATCH for-next 2/2] IB/hfi1: Use VL15 for SM packets From: Dennis Dalessandro To: jgg@ziepe.ca, dledford@redhat.com Cc: linux-rdma@vger.kernel.org, Mike Marciniszyn , Kaike Wan Date: Wed, 26 Sep 2018 10:48:04 -0700 Message-ID: <20180926174759.4570.70010.stgit@scvm10.sc.intel.com> In-Reply-To: <20180926174525.4570.83126.stgit@scvm10.sc.intel.com> References: <20180926174525.4570.83126.stgit@scvm10.sc.intel.com> User-Agent: StGit/0.17.1-18-g2e886-dirty MIME-Version: 1.0 Sender: linux-rdma-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: linux-rdma@vger.kernel.org X-Virus-Scanned: ClamAV using ClamSMTP From: Kaike Wan Subnet Management Packets (SMP) should exclusively use VL15 and their SL is ignored (IBTA v1.3, Section 3.5.8.2). Therefore, when an SMP is posted, the SL in the address handle can be set to 0 by a user application. Consequently, when an address handle is created by the IB core, some fields in struct rvt_ah may not be set correctly by using the SL2SC and SC2VL tables at the time. Subsequently, when the request is post sent, the incoming swqe may fail the validation check, resulting in the rejection of the send request. This patch fixes the problem by using VL15 for any validation, ignoring the SL in the address handle. Reviewed-by: Mike Marciniszyn Signed-off-by: Kaike Wan Signed-off-by: Dennis Dalessandro --- drivers/infiniband/hw/hfi1/qp.c | 14 ++++++++++++-- 1 files changed, 12 insertions(+), 2 deletions(-) diff --git a/drivers/infiniband/hw/hfi1/qp.c b/drivers/infiniband/hw/hfi1/qp.c index c9fe0d9..d48377a 100644 --- a/drivers/infiniband/hw/hfi1/qp.c +++ b/drivers/infiniband/hw/hfi1/qp.c @@ -306,6 +306,8 @@ int hfi1_setup_wqe(struct rvt_qp *qp, struct rvt_swqe *wqe, bool *call_send) { struct hfi1_ibport *ibp = to_iport(qp->ibqp.device, qp->port_num); struct rvt_ah *ah; + struct hfi1_pportdata *ppd; + struct hfi1_devdata *dd; switch (qp->ibqp.qp_type) { case IB_QPT_RC: @@ -316,8 +318,16 @@ int hfi1_setup_wqe(struct rvt_qp *qp, struct rvt_swqe *wqe, bool *call_send) *call_send = false; break; case IB_QPT_SMI: - ah = ibah_to_rvtah(wqe->ud_wr.ah); - if (wqe->length > (1 << ah->log_pmtu)) + /* + * SM packets should exclusively use VL15 and their SL is + * ignored (IBTA v1.3, Section 3.5.8.2). Therefore, when ah + * is created, SL is 0 in most cases and as a result some + * fields (vl and pmtu) in ah may not be set correctly, + * depending on the SL2SC and SC2VL tables at the time. + */ + ppd = ppd_from_ibp(ibp); + dd = dd_from_ppd(ppd); + if (wqe->length > dd->vld[15].mtu) return -EINVAL; break; case IB_QPT_GSI: