From patchwork Wed Jan 6 10:42:17 2021 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Srujana Challa X-Patchwork-Id: 357658 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=-18.8 required=3.0 tests=BAYES_00,DKIM_SIGNED, DKIM_VALID, DKIM_VALID_AU, HEADER_FROM_DIFFERENT_DOMAINS, INCLUDES_CR_TRAILER, INCLUDES_PATCH, MAILING_LIST_MULTI, SPF_HELO_NONE, 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 76781C4332B for ; Wed, 6 Jan 2021 10:44:01 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id 48DA82311C for ; Wed, 6 Jan 2021 10:44:01 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1726311AbhAFKn7 (ORCPT ); Wed, 6 Jan 2021 05:43:59 -0500 Received: from mx0b-0016f401.pphosted.com ([67.231.156.173]:23184 "EHLO mx0b-0016f401.pphosted.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1726366AbhAFKn6 (ORCPT ); Wed, 6 Jan 2021 05:43:58 -0500 Received: from pps.filterd (m0045851.ppops.net [127.0.0.1]) by mx0b-0016f401.pphosted.com (8.16.0.43/8.16.0.43) with SMTP id 106Aag8v026064; Wed, 6 Jan 2021 02:43:13 -0800 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=marvell.com; h=from : to : cc : subject : date : message-id : in-reply-to : references : mime-version : content-transfer-encoding : content-type; s=pfpt0220; bh=V7UPpgXX/PJ5G7MFuXxpL2cANATlrFJGwSlXQ7I05sw=; b=LSHam9XKH8dhQH7cDYKf4ZN2qlQGWcAuGx3OKh+DpplKnVTYyGkeIW3QY8Lnn5mHqvpV QSZScwXpspb0NGyOz4h+TPdytn8PCndUs+IAwz3k9sepLWH+xm8Bx2mtOFpSH2I/Y+3D Lua0RrB/RT00gvHaKndVTrgHL2HsPsmRSpDZGMZaqypBGz3n1KCzzy/swnWUlHoF/bmB lQq22PqrS4LTPH1YcMwBd4tRlrLWAwYUt4riBYXBSyVjASMXqgXWpxz4FpZG8mMUvuZR weOUDCOHSU/XJ2ApR8S0Qu0A21Cq6zavbsWkXFZKC207yzT/fp5Ra2a0jzWxw/BB5dM9 0A== Received: from dc5-exch01.marvell.com ([199.233.59.181]) by mx0b-0016f401.pphosted.com with ESMTP id 35ts7rs15v-1 (version=TLSv1.2 cipher=ECDHE-RSA-AES256-SHA384 bits=256 verify=NOT); Wed, 06 Jan 2021 02:43:12 -0800 Received: from SC-EXCH03.marvell.com (10.93.176.83) by DC5-EXCH01.marvell.com (10.69.176.38) with Microsoft SMTP Server (TLS) id 15.0.1497.2; Wed, 6 Jan 2021 02:43:10 -0800 Received: from DC5-EXCH01.marvell.com (10.69.176.38) by SC-EXCH03.marvell.com (10.93.176.83) with Microsoft SMTP Server (TLS) id 15.0.1497.2; Wed, 6 Jan 2021 02:43:09 -0800 Received: from maili.marvell.com (10.69.176.80) by DC5-EXCH01.marvell.com (10.69.176.38) with Microsoft SMTP Server id 15.0.1497.2 via Frontend Transport; Wed, 6 Jan 2021 02:43:10 -0800 Received: from hyd1schalla-dt.caveonetworks.com.com (unknown [10.29.8.39]) by maili.marvell.com (Postfix) with ESMTP id 97FFF3F7043; Wed, 6 Jan 2021 02:43:07 -0800 (PST) From: Srujana Challa To: CC: , , , , Srujana Challa , Suheil Chandran , "Lukasz Bartosik" Subject: [PATCH 3/9] crypto: octeontx2: enable SR-IOV and mailbox communication with VF Date: Wed, 6 Jan 2021 16:12:17 +0530 Message-ID: <20210106104223.6182-4-schalla@marvell.com> X-Mailer: git-send-email 2.29.0 In-Reply-To: <20210106104223.6182-1-schalla@marvell.com> References: <20210106104223.6182-1-schalla@marvell.com> MIME-Version: 1.0 X-Proofpoint-Virus-Version: vendor=fsecure engine=2.50.10434:6.0.343, 18.0.737 definitions=2021-01-06_05:2021-01-06,2021-01-06 signatures=0 Precedence: bulk List-ID: X-Mailing-List: linux-crypto@vger.kernel.org Adds 'sriov_configure' to enable/disable virtual functions (VFs). Also Initializes VF<=>PF mailbox IRQs, register handlers for processing these mailbox messages. Admin function (AF) handles resource allocation and configuration for PFs and their VFs. PFs request the AF directly, via mailboxes. Unlike PFs, VFs cannot send a mailbox request directly. A VF sends mailbox messages to its parent PF, with which it shares a mailbox region. The PF then forwards these messages to the AF. After handling the request, the AF sends a response back to the VF, through the PF. This patch adds support for this 'VF <=> PF <=> AF' mailbox communication. Signed-off-by: Suheil Chandran Signed-off-by: Lukasz Bartosik Signed-off-by: Srujana Challa --- .../marvell/octeontx2/otx2_cpt_common.h | 1 + drivers/crypto/marvell/octeontx2/otx2_cptpf.h | 27 ++ .../marvell/octeontx2/otx2_cptpf_main.c | 382 ++++++++++++++++++ .../marvell/octeontx2/otx2_cptpf_mbox.c | 175 +++++++- 4 files changed, 583 insertions(+), 2 deletions(-) diff --git a/drivers/crypto/marvell/octeontx2/otx2_cpt_common.h b/drivers/crypto/marvell/octeontx2/otx2_cpt_common.h index b677f8c7e724..277c7c7f95cf 100644 --- a/drivers/crypto/marvell/octeontx2/otx2_cpt_common.h +++ b/drivers/crypto/marvell/octeontx2/otx2_cpt_common.h @@ -14,6 +14,7 @@ #include "rvu.h" #include "mbox.h" +#define OTX2_CPT_MAX_VFS_NUM 128 #define OTX2_CPT_RVU_FUNC_ADDR_S(blk, slot, offs) \ (((blk) << 20) | ((slot) << 12) | (offs)) diff --git a/drivers/crypto/marvell/octeontx2/otx2_cptpf.h b/drivers/crypto/marvell/octeontx2/otx2_cptpf.h index 87fe4c6838e5..8a9805f89fee 100644 --- a/drivers/crypto/marvell/octeontx2/otx2_cptpf.h +++ b/drivers/crypto/marvell/octeontx2/otx2_cptpf.h @@ -7,19 +7,46 @@ #include "otx2_cpt_common.h" +struct otx2_cptpf_dev; +struct otx2_cptvf_info { + struct otx2_cptpf_dev *cptpf; /* PF pointer this VF belongs to */ + struct work_struct vfpf_mbox_work; + struct pci_dev *vf_dev; + int vf_id; + int intr_idx; +}; + +struct cptpf_flr_work { + struct work_struct work; + struct otx2_cptpf_dev *pf; +}; + struct otx2_cptpf_dev { void __iomem *reg_base; /* CPT PF registers start address */ void __iomem *afpf_mbox_base; /* PF-AF mbox start address */ + void __iomem *vfpf_mbox_base; /* VF-PF mbox start address */ struct pci_dev *pdev; /* PCI device handle */ + struct otx2_cptvf_info vf[OTX2_CPT_MAX_VFS_NUM]; /* AF <=> PF mbox */ struct otx2_mbox afpf_mbox; struct work_struct afpf_mbox_work; struct workqueue_struct *afpf_mbox_wq; + /* VF <=> PF mbox */ + struct otx2_mbox vfpf_mbox; + struct workqueue_struct *vfpf_mbox_wq; + + struct workqueue_struct *flr_wq; + struct cptpf_flr_work *flr_work; + u8 pf_id; /* RVU PF number */ + u8 max_vfs; /* Maximum number of VFs supported by CPT */ + u8 enabled_vfs; /* Number of enabled VFs */ }; irqreturn_t otx2_cptpf_afpf_mbox_intr(int irq, void *arg); void otx2_cptpf_afpf_mbox_handler(struct work_struct *work); +irqreturn_t otx2_cptpf_vfpf_mbox_intr(int irq, void *arg); +void otx2_cptpf_vfpf_mbox_handler(struct work_struct *work); #endif /* __OTX2_CPTPF_H */ diff --git a/drivers/crypto/marvell/octeontx2/otx2_cptpf_main.c b/drivers/crypto/marvell/octeontx2/otx2_cptpf_main.c index 2f5bf02436da..224882454c2f 100644 --- a/drivers/crypto/marvell/octeontx2/otx2_cptpf_main.c +++ b/drivers/crypto/marvell/octeontx2/otx2_cptpf_main.c @@ -10,6 +10,318 @@ #define OTX2_CPT_DRV_NAME "octeontx2-cpt" #define OTX2_CPT_DRV_STRING "Marvell OcteonTX2 CPT Physical Function Driver" +static void cptpf_enable_vfpf_mbox_intr(struct otx2_cptpf_dev *cptpf, + int num_vfs) +{ + int ena_bits; + + /* Clear any pending interrupts */ + otx2_cpt_write64(cptpf->reg_base, BLKADDR_RVUM, 0, + RVU_PF_VFPF_MBOX_INTX(0), ~0x0ULL); + otx2_cpt_write64(cptpf->reg_base, BLKADDR_RVUM, 0, + RVU_PF_VFPF_MBOX_INTX(1), ~0x0ULL); + + /* Enable VF interrupts for VFs from 0 to 63 */ + ena_bits = ((num_vfs - 1) % 64); + otx2_cpt_write64(cptpf->reg_base, BLKADDR_RVUM, 0, + RVU_PF_VFPF_MBOX_INT_ENA_W1SX(0), + GENMASK_ULL(ena_bits, 0)); + + if (num_vfs > 64) { + /* Enable VF interrupts for VFs from 64 to 127 */ + ena_bits = num_vfs - 64 - 1; + otx2_cpt_write64(cptpf->reg_base, BLKADDR_RVUM, 0, + RVU_PF_VFPF_MBOX_INT_ENA_W1SX(1), + GENMASK_ULL(ena_bits, 0)); + } +} + +static void cptpf_disable_vfpf_mbox_intr(struct otx2_cptpf_dev *cptpf, + int num_vfs) +{ + int vector; + + /* Disable VF-PF interrupts */ + otx2_cpt_write64(cptpf->reg_base, BLKADDR_RVUM, 0, + RVU_PF_VFPF_MBOX_INT_ENA_W1CX(0), ~0ULL); + otx2_cpt_write64(cptpf->reg_base, BLKADDR_RVUM, 0, + RVU_PF_VFPF_MBOX_INT_ENA_W1CX(1), ~0ULL); + /* Clear any pending interrupts */ + otx2_cpt_write64(cptpf->reg_base, BLKADDR_RVUM, 0, + RVU_PF_VFPF_MBOX_INTX(0), ~0ULL); + + vector = pci_irq_vector(cptpf->pdev, RVU_PF_INT_VEC_VFPF_MBOX0); + free_irq(vector, cptpf); + + if (num_vfs > 64) { + otx2_cpt_write64(cptpf->reg_base, BLKADDR_RVUM, 0, + RVU_PF_VFPF_MBOX_INTX(1), ~0ULL); + vector = pci_irq_vector(cptpf->pdev, RVU_PF_INT_VEC_VFPF_MBOX1); + free_irq(vector, cptpf); + } +} + +static void cptpf_enable_vf_flr_intrs(struct otx2_cptpf_dev *cptpf) +{ + /* Clear interrupt if any */ + otx2_cpt_write64(cptpf->reg_base, BLKADDR_RVUM, 0, RVU_PF_VFFLR_INTX(0), + ~0x0ULL); + otx2_cpt_write64(cptpf->reg_base, BLKADDR_RVUM, 0, RVU_PF_VFFLR_INTX(1), + ~0x0ULL); + + /* Enable VF FLR interrupts */ + otx2_cpt_write64(cptpf->reg_base, BLKADDR_RVUM, 0, + RVU_PF_VFFLR_INT_ENA_W1SX(0), ~0x0ULL); + otx2_cpt_write64(cptpf->reg_base, BLKADDR_RVUM, 0, + RVU_PF_VFFLR_INT_ENA_W1SX(1), ~0x0ULL); +} + +static void cptpf_disable_vf_flr_intrs(struct otx2_cptpf_dev *cptpf, + int num_vfs) +{ + int vector; + + /* Disable VF FLR interrupts */ + otx2_cpt_write64(cptpf->reg_base, BLKADDR_RVUM, 0, + RVU_PF_VFFLR_INT_ENA_W1CX(0), ~0x0ULL); + otx2_cpt_write64(cptpf->reg_base, BLKADDR_RVUM, 0, + RVU_PF_VFFLR_INT_ENA_W1CX(1), ~0x0ULL); + + /* Clear interrupt if any */ + otx2_cpt_write64(cptpf->reg_base, BLKADDR_RVUM, 0, RVU_PF_VFFLR_INTX(0), + ~0x0ULL); + otx2_cpt_write64(cptpf->reg_base, BLKADDR_RVUM, 0, RVU_PF_VFFLR_INTX(1), + ~0x0ULL); + + vector = pci_irq_vector(cptpf->pdev, RVU_PF_INT_VEC_VFFLR0); + free_irq(vector, cptpf); + + if (num_vfs > 64) { + vector = pci_irq_vector(cptpf->pdev, RVU_PF_INT_VEC_VFFLR1); + free_irq(vector, cptpf); + } +} + +static void cptpf_flr_wq_handler(struct work_struct *work) +{ + struct cptpf_flr_work *flr_work; + struct otx2_cptpf_dev *pf; + struct mbox_msghdr *req; + struct otx2_mbox *mbox; + int vf, reg = 0; + + flr_work = container_of(work, struct cptpf_flr_work, work); + pf = flr_work->pf; + mbox = &pf->afpf_mbox; + + vf = flr_work - pf->flr_work; + + req = otx2_mbox_alloc_msg_rsp(mbox, 0, sizeof(*req), + sizeof(struct msg_rsp)); + if (!req) + return; + + req->sig = OTX2_MBOX_REQ_SIG; + req->id = MBOX_MSG_VF_FLR; + req->pcifunc &= RVU_PFVF_FUNC_MASK; + req->pcifunc |= (vf + 1) & RVU_PFVF_FUNC_MASK; + + otx2_cpt_send_mbox_msg(mbox, pf->pdev); + + if (vf >= 64) { + reg = 1; + vf = vf - 64; + } + /* Clear transaction pending register */ + otx2_cpt_write64(pf->reg_base, BLKADDR_RVUM, 0, + RVU_PF_VFTRPENDX(reg), BIT_ULL(vf)); + otx2_cpt_write64(pf->reg_base, BLKADDR_RVUM, 0, + RVU_PF_VFFLR_INT_ENA_W1SX(reg), BIT_ULL(vf)); +} + +static irqreturn_t cptpf_vf_flr_intr(int __always_unused irq, void *arg) +{ + int reg, dev, vf, start_vf, num_reg = 1; + struct otx2_cptpf_dev *cptpf = arg; + u64 intr; + + if (cptpf->max_vfs > 64) + num_reg = 2; + + for (reg = 0; reg < num_reg; reg++) { + intr = otx2_cpt_read64(cptpf->reg_base, BLKADDR_RVUM, 0, + RVU_PF_VFFLR_INTX(reg)); + if (!intr) + continue; + start_vf = 64 * reg; + for (vf = 0; vf < 64; vf++) { + if (!(intr & BIT_ULL(vf))) + continue; + dev = vf + start_vf; + queue_work(cptpf->flr_wq, &cptpf->flr_work[dev].work); + /* Clear interrupt */ + otx2_cpt_write64(cptpf->reg_base, BLKADDR_RVUM, 0, + RVU_PF_VFFLR_INTX(reg), BIT_ULL(vf)); + /* Disable the interrupt */ + otx2_cpt_write64(cptpf->reg_base, BLKADDR_RVUM, 0, + RVU_PF_VFFLR_INT_ENA_W1CX(reg), + BIT_ULL(vf)); + } + } + return IRQ_HANDLED; +} + +static void cptpf_unregister_vfpf_intr(struct otx2_cptpf_dev *cptpf, + int num_vfs) +{ + cptpf_disable_vfpf_mbox_intr(cptpf, num_vfs); + cptpf_disable_vf_flr_intrs(cptpf, num_vfs); +} + +static int cptpf_register_vfpf_intr(struct otx2_cptpf_dev *cptpf, int num_vfs) +{ + struct pci_dev *pdev = cptpf->pdev; + struct device *dev = &pdev->dev; + int ret, vector; + + vector = pci_irq_vector(pdev, RVU_PF_INT_VEC_VFPF_MBOX0); + /* Register VF-PF mailbox interrupt handler */ + ret = request_irq(vector, otx2_cptpf_vfpf_mbox_intr, 0, "CPTVFPF Mbox0", + cptpf); + if (ret) { + dev_err(dev, + "IRQ registration failed for PFVF mbox0 irq\n"); + return ret; + } + vector = pci_irq_vector(pdev, RVU_PF_INT_VEC_VFFLR0); + /* Register VF FLR interrupt handler */ + ret = request_irq(vector, cptpf_vf_flr_intr, 0, "CPTPF FLR0", cptpf); + if (ret) { + dev_err(dev, + "IRQ registration failed for VFFLR0 irq\n"); + goto free_mbox0_irq; + } + if (num_vfs > 64) { + vector = pci_irq_vector(pdev, RVU_PF_INT_VEC_VFPF_MBOX1); + ret = request_irq(vector, otx2_cptpf_vfpf_mbox_intr, 0, + "CPTVFPF Mbox1", cptpf); + if (ret) { + dev_err(dev, + "IRQ registration failed for PFVF mbox1 irq\n"); + goto free_flr0_irq; + } + vector = pci_irq_vector(pdev, RVU_PF_INT_VEC_VFFLR1); + /* Register VF FLR interrupt handler */ + ret = request_irq(vector, cptpf_vf_flr_intr, 0, "CPTPF FLR1", + cptpf); + if (ret) { + dev_err(dev, + "IRQ registration failed for VFFLR1 irq\n"); + goto free_mbox1_irq; + } + } + cptpf_enable_vfpf_mbox_intr(cptpf, num_vfs); + cptpf_enable_vf_flr_intrs(cptpf); + + return 0; + +free_mbox1_irq: + vector = pci_irq_vector(pdev, RVU_PF_INT_VEC_VFPF_MBOX1); + free_irq(vector, cptpf); +free_flr0_irq: + vector = pci_irq_vector(pdev, RVU_PF_INT_VEC_VFFLR0); + free_irq(vector, cptpf); +free_mbox0_irq: + vector = pci_irq_vector(pdev, RVU_PF_INT_VEC_VFPF_MBOX0); + free_irq(vector, cptpf); + return ret; +} + +static void cptpf_flr_wq_destroy(struct otx2_cptpf_dev *pf) +{ + if (!pf->flr_wq) + return; + destroy_workqueue(pf->flr_wq); + pf->flr_wq = NULL; + kfree(pf->flr_work); +} + +static int cptpf_flr_wq_init(struct otx2_cptpf_dev *cptpf, int num_vfs) +{ + int vf; + + cptpf->flr_wq = alloc_ordered_workqueue("cptpf_flr_wq", 0); + if (!cptpf->flr_wq) + return -ENOMEM; + + cptpf->flr_work = kcalloc(num_vfs, sizeof(struct cptpf_flr_work), + GFP_KERNEL); + if (!cptpf->flr_work) + goto destroy_wq; + + for (vf = 0; vf < num_vfs; vf++) { + cptpf->flr_work[vf].pf = cptpf; + INIT_WORK(&cptpf->flr_work[vf].work, cptpf_flr_wq_handler); + } + return 0; + +destroy_wq: + destroy_workqueue(cptpf->flr_wq); + return -ENOMEM; +} + +static int cptpf_vfpf_mbox_init(struct otx2_cptpf_dev *cptpf, int num_vfs) +{ + struct device *dev = &cptpf->pdev->dev; + u64 vfpf_mbox_base; + int err, i; + + cptpf->vfpf_mbox_wq = alloc_workqueue("cpt_vfpf_mailbox", + WQ_UNBOUND | WQ_HIGHPRI | + WQ_MEM_RECLAIM, 1); + if (!cptpf->vfpf_mbox_wq) + return -ENOMEM; + + /* Map VF-PF mailbox memory */ + vfpf_mbox_base = readq(cptpf->reg_base + RVU_PF_VF_BAR4_ADDR); + if (!vfpf_mbox_base) { + dev_err(dev, "VF-PF mailbox address not configured\n"); + err = -ENOMEM; + goto free_wqe; + } + cptpf->vfpf_mbox_base = devm_ioremap_wc(dev, vfpf_mbox_base, + MBOX_SIZE * cptpf->max_vfs); + if (!cptpf->vfpf_mbox_base) { + dev_err(dev, "Mapping of VF-PF mailbox address failed\n"); + err = -ENOMEM; + goto free_wqe; + } + err = otx2_mbox_init(&cptpf->vfpf_mbox, cptpf->vfpf_mbox_base, + cptpf->pdev, cptpf->reg_base, MBOX_DIR_PFVF, + num_vfs); + if (err) + goto free_wqe; + + for (i = 0; i < num_vfs; i++) { + cptpf->vf[i].vf_id = i; + cptpf->vf[i].cptpf = cptpf; + cptpf->vf[i].intr_idx = i % 64; + INIT_WORK(&cptpf->vf[i].vfpf_mbox_work, + otx2_cptpf_vfpf_mbox_handler); + } + return 0; + +free_wqe: + destroy_workqueue(cptpf->vfpf_mbox_wq); + return err; +} + +static void cptpf_vfpf_mbox_destroy(struct otx2_cptpf_dev *cptpf) +{ + destroy_workqueue(cptpf->vfpf_mbox_wq); + otx2_mbox_destroy(&cptpf->vfpf_mbox); +} + static void cptpf_disable_afpf_mbox_intr(struct otx2_cptpf_dev *cptpf) { /* Disable AF-PF interrupt */ @@ -98,6 +410,71 @@ static int cpt_is_pf_usable(struct otx2_cptpf_dev *cptpf) return 0; } +static int cptpf_sriov_disable(struct pci_dev *pdev) +{ + struct otx2_cptpf_dev *cptpf = pci_get_drvdata(pdev); + int num_vfs = pci_num_vf(pdev); + + if (!num_vfs) + return 0; + + pci_disable_sriov(pdev); + cptpf_unregister_vfpf_intr(cptpf, num_vfs); + cptpf_flr_wq_destroy(cptpf); + cptpf_vfpf_mbox_destroy(cptpf); + module_put(THIS_MODULE); + cptpf->enabled_vfs = 0; + + return 0; +} + +static int cptpf_sriov_enable(struct pci_dev *pdev, int num_vfs) +{ + struct otx2_cptpf_dev *cptpf = pci_get_drvdata(pdev); + int ret; + + /* Initialize VF<=>PF mailbox */ + ret = cptpf_vfpf_mbox_init(cptpf, num_vfs); + if (ret) + return ret; + + ret = cptpf_flr_wq_init(cptpf, num_vfs); + if (ret) + goto destroy_mbox; + /* Register VF<=>PF mailbox interrupt */ + ret = cptpf_register_vfpf_intr(cptpf, num_vfs); + if (ret) + goto destroy_flr; + + cptpf->enabled_vfs = num_vfs; + ret = pci_enable_sriov(pdev, num_vfs); + if (ret) + goto disable_intr; + + dev_notice(&cptpf->pdev->dev, "VFs enabled: %d\n", num_vfs); + + try_module_get(THIS_MODULE); + return num_vfs; + +disable_intr: + cptpf_unregister_vfpf_intr(cptpf, num_vfs); + cptpf->enabled_vfs = 0; +destroy_flr: + cptpf_flr_wq_destroy(cptpf); +destroy_mbox: + cptpf_vfpf_mbox_destroy(cptpf); + return ret; +} + +static int otx2_cptpf_sriov_configure(struct pci_dev *pdev, int num_vfs) +{ + if (num_vfs > 0) { + return cptpf_sriov_enable(pdev, num_vfs); + } else { + return cptpf_sriov_disable(pdev); + } +} + static int otx2_cptpf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) { @@ -164,6 +541,8 @@ static int otx2_cptpf_probe(struct pci_dev *pdev, if (err) goto destroy_afpf_mbox; + cptpf->max_vfs = pci_sriov_get_totalvfs(pdev); + return 0; destroy_afpf_mbox: @@ -179,6 +558,8 @@ static void otx2_cptpf_remove(struct pci_dev *pdev) if (!cptpf) return; + + cptpf_sriov_disable(pdev); /* Disable AF-PF mailbox interrupt */ cptpf_disable_afpf_mbox_intr(cptpf); /* Destroy AF-PF mbox */ @@ -197,6 +578,7 @@ static struct pci_driver otx2_cpt_pci_driver = { .id_table = otx2_cpt_id_table, .probe = otx2_cptpf_probe, .remove = otx2_cptpf_remove, + .sriov_configure = otx2_cptpf_sriov_configure }; module_pci_driver(otx2_cpt_pci_driver); diff --git a/drivers/crypto/marvell/octeontx2/otx2_cptpf_mbox.c b/drivers/crypto/marvell/octeontx2/otx2_cptpf_mbox.c index 0a8bd46b5686..1d97f7202130 100644 --- a/drivers/crypto/marvell/octeontx2/otx2_cptpf_mbox.c +++ b/drivers/crypto/marvell/octeontx2/otx2_cptpf_mbox.c @@ -5,6 +5,127 @@ #include "otx2_cptpf.h" #include "rvu_reg.h" +static int forward_to_af(struct otx2_cptpf_dev *cptpf, + struct otx2_cptvf_info *vf, + struct mbox_msghdr *req, int size) +{ + struct mbox_msghdr *msg; + int ret; + + msg = otx2_mbox_alloc_msg(&cptpf->afpf_mbox, 0, size); + if (msg == NULL) + return -ENOMEM; + + memcpy((uint8_t *)msg + sizeof(struct mbox_msghdr), + (uint8_t *)req + sizeof(struct mbox_msghdr), size); + msg->id = req->id; + msg->pcifunc = req->pcifunc; + msg->sig = req->sig; + msg->ver = req->ver; + + otx2_mbox_msg_send(&cptpf->afpf_mbox, 0); + ret = otx2_mbox_wait_for_rsp(&cptpf->afpf_mbox, 0); + if (ret == -EIO) { + dev_err(&cptpf->pdev->dev, "RVU MBOX timeout.\n"); + return ret; + } else if (ret) { + dev_err(&cptpf->pdev->dev, "RVU MBOX error: %d.\n", ret); + return -EFAULT; + } + return 0; +} + +static int cptpf_handle_vf_req(struct otx2_cptpf_dev *cptpf, + struct otx2_cptvf_info *vf, + struct mbox_msghdr *req, int size) +{ + int err = 0; + + /* Check if msg is valid, if not reply with an invalid msg */ + if (req->sig != OTX2_MBOX_REQ_SIG) + goto inval_msg; + + return forward_to_af(cptpf, vf, req, size); + +inval_msg: + otx2_reply_invalid_msg(&cptpf->vfpf_mbox, vf->vf_id, 0, req->id); + otx2_mbox_msg_send(&cptpf->vfpf_mbox, vf->vf_id); + return err; +} + +irqreturn_t otx2_cptpf_vfpf_mbox_intr(int __always_unused irq, void *arg) +{ + struct otx2_cptpf_dev *cptpf = arg; + struct otx2_cptvf_info *vf; + int i, vf_idx; + u64 intr; + + /* + * Check which VF has raised an interrupt and schedule + * corresponding work queue to process the messages + */ + for (i = 0; i < 2; i++) { + /* Read the interrupt bits */ + intr = otx2_cpt_read64(cptpf->reg_base, BLKADDR_RVUM, 0, + RVU_PF_VFPF_MBOX_INTX(i)); + + for (vf_idx = i * 64; vf_idx < cptpf->enabled_vfs; vf_idx++) { + vf = &cptpf->vf[vf_idx]; + if (intr & (1ULL << vf->intr_idx)) { + queue_work(cptpf->vfpf_mbox_wq, + &vf->vfpf_mbox_work); + /* Clear the interrupt */ + otx2_cpt_write64(cptpf->reg_base, BLKADDR_RVUM, + 0, RVU_PF_VFPF_MBOX_INTX(i), + BIT_ULL(vf->intr_idx)); + } + } + } + return IRQ_HANDLED; +} + +void otx2_cptpf_vfpf_mbox_handler(struct work_struct *work) +{ + struct otx2_cptpf_dev *cptpf; + struct otx2_cptvf_info *vf; + struct otx2_mbox_dev *mdev; + struct mbox_hdr *req_hdr; + struct mbox_msghdr *msg; + struct otx2_mbox *mbox; + int offset, i, err; + + vf = container_of(work, struct otx2_cptvf_info, vfpf_mbox_work); + cptpf = vf->cptpf; + mbox = &cptpf->vfpf_mbox; + /* sync with mbox memory region */ + smp_rmb(); + mdev = &mbox->dev[vf->vf_id]; + /* Process received mbox messages */ + req_hdr = (struct mbox_hdr *)(mdev->mbase + mbox->rx_start); + offset = mbox->rx_start + ALIGN(sizeof(*req_hdr), MBOX_MSG_ALIGN); + + for (i = 0; i < req_hdr->num_msgs; i++) { + msg = (struct mbox_msghdr *)(mdev->mbase + offset); + + /* Set which VF sent this message based on mbox IRQ */ + msg->pcifunc = ((u16)cptpf->pf_id << RVU_PFVF_PF_SHIFT) | + ((vf->vf_id + 1) & RVU_PFVF_FUNC_MASK); + + err = cptpf_handle_vf_req(cptpf, vf, msg, + msg->next_msgoff - offset); + /* + * Behave as the AF, drop the msg if there is + * no memory, timeout handling also goes here + */ + if (err == -ENOMEM || err == -EIO) + break; + offset = msg->next_msgoff; + } + /* Send mbox responses to VF */ + if (mdev->num_msgs) + otx2_mbox_msg_send(mbox, vf->vf_id); +} + irqreturn_t otx2_cptpf_afpf_mbox_intr(int __always_unused irq, void *arg) { struct otx2_cptpf_dev *cptpf = arg; @@ -50,6 +171,49 @@ static void process_afpf_mbox_msg(struct otx2_cptpf_dev *cptpf, } } +static void forward_to_vf(struct otx2_cptpf_dev *cptpf, struct mbox_msghdr *msg, + int vf_id, int size) +{ + struct otx2_mbox *vfpf_mbox; + struct mbox_msghdr *fwd; + + if (msg->id >= MBOX_MSG_MAX) { + dev_err(&cptpf->pdev->dev, + "MBOX msg with unknown ID %d\n", msg->id); + return; + } + if (msg->sig != OTX2_MBOX_RSP_SIG) { + dev_err(&cptpf->pdev->dev, + "MBOX msg with wrong signature %x, ID %d\n", + msg->sig, msg->id); + return; + } + vfpf_mbox = &cptpf->vfpf_mbox; + vf_id--; + if (vf_id >= cptpf->enabled_vfs) { + dev_err(&cptpf->pdev->dev, + "MBOX msg to unknown VF: %d >= %d\n", + vf_id, cptpf->enabled_vfs); + return; + } + if (msg->id == MBOX_MSG_VF_FLR) + return; + + fwd = otx2_mbox_alloc_msg(vfpf_mbox, vf_id, size); + if (!fwd) { + dev_err(&cptpf->pdev->dev, + "Forwarding to VF%d failed.\n", vf_id); + return; + } + memcpy((uint8_t *)fwd + sizeof(struct mbox_msghdr), + (uint8_t *)msg + sizeof(struct mbox_msghdr), size); + fwd->id = msg->id; + fwd->pcifunc = msg->pcifunc; + fwd->sig = msg->sig; + fwd->ver = msg->ver; + fwd->rc = msg->rc; +} + /* Handle mailbox messages received from AF */ void otx2_cptpf_afpf_mbox_handler(struct work_struct *work) { @@ -58,7 +222,7 @@ void otx2_cptpf_afpf_mbox_handler(struct work_struct *work) struct otx2_mbox_dev *mdev; struct mbox_hdr *rsp_hdr; struct mbox_msghdr *msg; - int offset, i; + int offset, vf_id, i; cptpf = container_of(work, struct otx2_cptpf_dev, afpf_mbox_work); afpf_mbox = &cptpf->afpf_mbox; @@ -72,7 +236,14 @@ void otx2_cptpf_afpf_mbox_handler(struct work_struct *work) for (i = 0; i < rsp_hdr->num_msgs; i++) { msg = (struct mbox_msghdr *)(mdev->mbase + afpf_mbox->rx_start + offset); - process_afpf_mbox_msg(cptpf, msg); + vf_id = (msg->pcifunc >> RVU_PFVF_FUNC_SHIFT) & + RVU_PFVF_FUNC_MASK; + if (vf_id > 0) + forward_to_vf(cptpf, msg, vf_id, + msg->next_msgoff - offset); + else + process_afpf_mbox_msg(cptpf, msg); + offset = msg->next_msgoff; mdev->msgs_acked++; } From patchwork Wed Jan 6 10:42:18 2021 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Srujana Challa X-Patchwork-Id: 357657 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=-18.8 required=3.0 tests=BAYES_00,DKIM_SIGNED, DKIM_VALID, DKIM_VALID_AU, HEADER_FROM_DIFFERENT_DOMAINS, INCLUDES_CR_TRAILER, INCLUDES_PATCH, MAILING_LIST_MULTI, SPF_HELO_NONE, 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 61312C433DB for ; Wed, 6 Jan 2021 10:44:21 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id D43FB23102 for ; Wed, 6 Jan 2021 10:44:20 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1726618AbhAFKoE (ORCPT ); Wed, 6 Jan 2021 05:44:04 -0500 Received: from mx0a-0016f401.pphosted.com ([67.231.148.174]:9950 "EHLO mx0b-0016f401.pphosted.com" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1726366AbhAFKoD (ORCPT ); Wed, 6 Jan 2021 05:44:03 -0500 Received: from pps.filterd (m0045849.ppops.net [127.0.0.1]) by mx0a-0016f401.pphosted.com (8.16.0.43/8.16.0.43) with SMTP id 106AYhiN027880; Wed, 6 Jan 2021 02:43:16 -0800 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=marvell.com; h=from : to : cc : subject : date : message-id : in-reply-to : references : mime-version : content-transfer-encoding : content-type; s=pfpt0220; bh=SA1mXH2gbZjt5LiyE5Xk2fdqcfwJQlEX596jg2MLKxo=; b=FzMZGpnnrzEWKymUzfdusG2KGugqH+h+WduLlpuM+tQVqfs2fybz+T5JMkKe3Vh7lQey CCqR7o9pwL+o8Os7nsdaDvfZUPOgfgondxPx9dzqPkBOjw+NFv5LSdLB4dwmKC7MOIBE 2JNkFqBm3KdUHAcO6h2NzwGGMUpvx4XytCXzceAEZzW3UawMDhTZWhRGeqSSlFA9Ae/q xNfD7Nx3TE5c3djyw1KvUUNfeKx2z25LA8DyHY23wdwWBx+MycvE2O9t4rnxQqn3v1SD kc49EQvcX79V2hUrlYKk5/r3dloUDigBSLhTJhmrp0rv1Ry5I/4nzcmjzIGaYBtr2r2z Ew== Received: from dc5-exch02.marvell.com ([199.233.59.182]) by mx0a-0016f401.pphosted.com with ESMTP id 35tq2uhc5g-1 (version=TLSv1.2 cipher=ECDHE-RSA-AES256-SHA384 bits=256 verify=NOT); Wed, 06 Jan 2021 02:43:16 -0800 Received: from DC5-EXCH01.marvell.com (10.69.176.38) by DC5-EXCH02.marvell.com (10.69.176.39) with Microsoft SMTP Server (TLS) id 15.0.1497.2; Wed, 6 Jan 2021 02:43:15 -0800 Received: from maili.marvell.com (10.69.176.80) by DC5-EXCH01.marvell.com (10.69.176.38) with Microsoft SMTP Server id 15.0.1497.2 via Frontend Transport; Wed, 6 Jan 2021 02:43:14 -0800 Received: from hyd1schalla-dt.caveonetworks.com.com (unknown [10.29.8.39]) by maili.marvell.com (Postfix) with ESMTP id CE6523F703F; Wed, 6 Jan 2021 02:43:11 -0800 (PST) From: Srujana Challa To: CC: , , , , Srujana Challa , Suheil Chandran , "Lukasz Bartosik" Subject: [PATCH 4/9] crypto: octeontx2: load microcode and create engine groups Date: Wed, 6 Jan 2021 16:12:18 +0530 Message-ID: <20210106104223.6182-5-schalla@marvell.com> X-Mailer: git-send-email 2.29.0 In-Reply-To: <20210106104223.6182-1-schalla@marvell.com> References: <20210106104223.6182-1-schalla@marvell.com> MIME-Version: 1.0 X-Proofpoint-Virus-Version: vendor=fsecure engine=2.50.10434:6.0.343, 18.0.737 definitions=2021-01-06_05:2021-01-06,2021-01-06 signatures=0 Precedence: bulk List-ID: X-Mailing-List: linux-crypto@vger.kernel.org CPT includes microcoded GigaCypher symmetric engines(SEs), IPsec symmetric engines(IEs), and asymmetric engines (AEs). Each engine receives CPT instructions from the engine groups it has subscribed to. This patch loads microcode, configures three engine groups(one for SEs, one for IEs and one for AEs), and configures all engines. Signed-off-by: Suheil Chandran Signed-off-by: Lukasz Bartosik Signed-off-by: Srujana Challa --- drivers/crypto/marvell/octeontx2/Makefile | 2 +- .../marvell/octeontx2/otx2_cpt_common.h | 42 + .../marvell/octeontx2/otx2_cpt_mbox_common.c | 77 + drivers/crypto/marvell/octeontx2/otx2_cptpf.h | 3 + .../marvell/octeontx2/otx2_cptpf_main.c | 72 + .../marvell/octeontx2/otx2_cptpf_mbox.c | 46 +- .../marvell/octeontx2/otx2_cptpf_ucode.c | 1254 +++++++++++++++++ .../marvell/octeontx2/otx2_cptpf_ucode.h | 161 +++ 8 files changed, 1655 insertions(+), 2 deletions(-) create mode 100644 drivers/crypto/marvell/octeontx2/otx2_cptpf_ucode.c create mode 100644 drivers/crypto/marvell/octeontx2/otx2_cptpf_ucode.h diff --git a/drivers/crypto/marvell/octeontx2/Makefile b/drivers/crypto/marvell/octeontx2/Makefile index 8c8262e94f78..3c4155446296 100644 --- a/drivers/crypto/marvell/octeontx2/Makefile +++ b/drivers/crypto/marvell/octeontx2/Makefile @@ -2,6 +2,6 @@ obj-$(CONFIG_CRYPTO_DEV_OCTEONTX2_CPT) += octeontx2-cpt.o octeontx2-cpt-objs := otx2_cptpf_main.o otx2_cptpf_mbox.o \ - otx2_cpt_mbox_common.o + otx2_cpt_mbox_common.o otx2_cptpf_ucode.o ccflags-y += -I$(srctree)/drivers/net/ethernet/marvell/octeontx2/af diff --git a/drivers/crypto/marvell/octeontx2/otx2_cpt_common.h b/drivers/crypto/marvell/octeontx2/otx2_cpt_common.h index 277c7c7f95cf..ae16dc102459 100644 --- a/drivers/crypto/marvell/octeontx2/otx2_cpt_common.h +++ b/drivers/crypto/marvell/octeontx2/otx2_cpt_common.h @@ -18,6 +18,37 @@ #define OTX2_CPT_RVU_FUNC_ADDR_S(blk, slot, offs) \ (((blk) << 20) | ((slot) << 12) | (offs)) +#define OTX2_CPT_INVALID_CRYPTO_ENG_GRP 0xFF +#define OTX2_CPT_NAME_LENGTH 64 + +#define BAD_OTX2_CPT_ENG_TYPE OTX2_CPT_MAX_ENG_TYPES + +enum otx2_cpt_eng_type { + OTX2_CPT_AE_TYPES = 1, + OTX2_CPT_SE_TYPES = 2, + OTX2_CPT_IE_TYPES = 3, + OTX2_CPT_MAX_ENG_TYPES, +}; + +/* Take mbox id from end of CPT mbox range in AF (range 0xA00 - 0xBFF) */ +#define MBOX_MSG_GET_ENG_GRP_NUM 0xBFF + +/* + * Message request and response to get engine group number + * which has attached a given type of engines (SE, AE, IE) + * This messages are only used between CPT PF <=> CPT VF + */ +struct otx2_cpt_egrp_num_msg { + struct mbox_msghdr hdr; + u8 eng_type; +}; + +struct otx2_cpt_egrp_num_rsp { + struct mbox_msghdr hdr; + u8 eng_type; + u8 eng_grp_num; +}; + static inline void otx2_cpt_write64(void __iomem *reg_base, u64 blk, u64 slot, u64 offs, u64 val) { @@ -34,4 +65,15 @@ static inline u64 otx2_cpt_read64(void __iomem *reg_base, u64 blk, u64 slot, int otx2_cpt_send_ready_msg(struct otx2_mbox *mbox, struct pci_dev *pdev); int otx2_cpt_send_mbox_msg(struct otx2_mbox *mbox, struct pci_dev *pdev); + +int otx2_cpt_send_af_reg_requests(struct otx2_mbox *mbox, + struct pci_dev *pdev); +int otx2_cpt_add_read_af_reg(struct otx2_mbox *mbox, + struct pci_dev *pdev, u64 reg, u64 *val); +int otx2_cpt_add_write_af_reg(struct otx2_mbox *mbox, struct pci_dev *pdev, + u64 reg, u64 val); +int otx2_cpt_read_af_reg(struct otx2_mbox *mbox, struct pci_dev *pdev, + u64 reg, u64 *val); +int otx2_cpt_write_af_reg(struct otx2_mbox *mbox, struct pci_dev *pdev, + u64 reg, u64 val); #endif /* __OTX2_CPT_COMMON_H */ diff --git a/drivers/crypto/marvell/octeontx2/otx2_cpt_mbox_common.c b/drivers/crypto/marvell/octeontx2/otx2_cpt_mbox_common.c index a122483b5976..ef1291c4881b 100644 --- a/drivers/crypto/marvell/octeontx2/otx2_cpt_mbox_common.c +++ b/drivers/crypto/marvell/octeontx2/otx2_cpt_mbox_common.c @@ -35,3 +35,80 @@ int otx2_cpt_send_ready_msg(struct otx2_mbox *mbox, struct pci_dev *pdev) return otx2_cpt_send_mbox_msg(mbox, pdev); } + +int otx2_cpt_send_af_reg_requests(struct otx2_mbox *mbox, struct pci_dev *pdev) +{ + return otx2_cpt_send_mbox_msg(mbox, pdev); +} + +int otx2_cpt_add_read_af_reg(struct otx2_mbox *mbox, struct pci_dev *pdev, + u64 reg, u64 *val) +{ + struct cpt_rd_wr_reg_msg *reg_msg; + + reg_msg = (struct cpt_rd_wr_reg_msg *) + otx2_mbox_alloc_msg_rsp(mbox, 0, sizeof(*reg_msg), + sizeof(*reg_msg)); + if (reg_msg == NULL) { + dev_err(&pdev->dev, "RVU MBOX failed to get message.\n"); + return -EFAULT; + } + + reg_msg->hdr.id = MBOX_MSG_CPT_RD_WR_REGISTER; + reg_msg->hdr.sig = OTX2_MBOX_REQ_SIG; + reg_msg->hdr.pcifunc = 0; + + reg_msg->is_write = 0; + reg_msg->reg_offset = reg; + reg_msg->ret_val = val; + + return 0; +} + +int otx2_cpt_add_write_af_reg(struct otx2_mbox *mbox, struct pci_dev *pdev, + u64 reg, u64 val) +{ + struct cpt_rd_wr_reg_msg *reg_msg; + + reg_msg = (struct cpt_rd_wr_reg_msg *) + otx2_mbox_alloc_msg_rsp(mbox, 0, sizeof(*reg_msg), + sizeof(*reg_msg)); + if (reg_msg == NULL) { + dev_err(&pdev->dev, "RVU MBOX failed to get message.\n"); + return -EFAULT; + } + + reg_msg->hdr.id = MBOX_MSG_CPT_RD_WR_REGISTER; + reg_msg->hdr.sig = OTX2_MBOX_REQ_SIG; + reg_msg->hdr.pcifunc = 0; + + reg_msg->is_write = 1; + reg_msg->reg_offset = reg; + reg_msg->val = val; + + return 0; +} + +int otx2_cpt_read_af_reg(struct otx2_mbox *mbox, struct pci_dev *pdev, + u64 reg, u64 *val) +{ + int ret; + + ret = otx2_cpt_add_read_af_reg(mbox, pdev, reg, val); + if (ret) + return ret; + + return otx2_cpt_send_mbox_msg(mbox, pdev); +} + +int otx2_cpt_write_af_reg(struct otx2_mbox *mbox, struct pci_dev *pdev, + u64 reg, u64 val) +{ + int ret; + + ret = otx2_cpt_add_write_af_reg(mbox, pdev, reg, val); + if (ret) + return ret; + + return otx2_cpt_send_mbox_msg(mbox, pdev); +} diff --git a/drivers/crypto/marvell/octeontx2/otx2_cptpf.h b/drivers/crypto/marvell/octeontx2/otx2_cptpf.h index 8a9805f89fee..ac9795978286 100644 --- a/drivers/crypto/marvell/octeontx2/otx2_cptpf.h +++ b/drivers/crypto/marvell/octeontx2/otx2_cptpf.h @@ -6,6 +6,7 @@ #define __OTX2_CPTPF_H #include "otx2_cpt_common.h" +#include "otx2_cptpf_ucode.h" struct otx2_cptpf_dev; struct otx2_cptvf_info { @@ -27,6 +28,8 @@ struct otx2_cptpf_dev { void __iomem *vfpf_mbox_base; /* VF-PF mbox start address */ struct pci_dev *pdev; /* PCI device handle */ struct otx2_cptvf_info vf[OTX2_CPT_MAX_VFS_NUM]; + struct otx2_cpt_eng_grps eng_grps;/* Engine groups information */ + /* AF <=> PF mbox */ struct otx2_mbox afpf_mbox; struct work_struct afpf_mbox_work; diff --git a/drivers/crypto/marvell/octeontx2/otx2_cptpf_main.c b/drivers/crypto/marvell/octeontx2/otx2_cptpf_main.c index 224882454c2f..f0ad45c04df7 100644 --- a/drivers/crypto/marvell/octeontx2/otx2_cptpf_main.c +++ b/drivers/crypto/marvell/octeontx2/otx2_cptpf_main.c @@ -4,6 +4,7 @@ #include #include "otx2_cpt_hw_types.h" #include "otx2_cpt_common.h" +#include "otx2_cptpf_ucode.h" #include "otx2_cptpf.h" #include "rvu_reg.h" @@ -410,6 +411,59 @@ static int cpt_is_pf_usable(struct otx2_cptpf_dev *cptpf) return 0; } +static int cptpf_device_reset(struct otx2_cptpf_dev *cptpf) +{ + int timeout = 10, ret; + u64 reg = 0; + + ret = otx2_cpt_write_af_reg(&cptpf->afpf_mbox, cptpf->pdev, + CPT_AF_BLK_RST, 0x1); + if (ret) + return ret; + + do { + ret = otx2_cpt_read_af_reg(&cptpf->afpf_mbox, cptpf->pdev, + CPT_AF_BLK_RST, ®); + if (ret) + return ret; + + if (!((reg >> 63) & 0x1)) + break; + + usleep_range(10000, 20000); + if (timeout-- < 0) + return -EBUSY; + } while (1); + + return ret; +} + +static int cptpf_device_init(struct otx2_cptpf_dev *cptpf) +{ + union otx2_cptx_af_constants1 af_cnsts1 = {0}; + int ret = 0; + + /* Reset the CPT PF device */ + ret = cptpf_device_reset(cptpf); + if (ret) + return ret; + + /* Get number of SE, IE and AE engines */ + ret = otx2_cpt_read_af_reg(&cptpf->afpf_mbox, cptpf->pdev, + CPT_AF_CONSTANTS1, &af_cnsts1.u); + if (ret) + return ret; + + cptpf->eng_grps.avail.max_se_cnt = af_cnsts1.s.se; + cptpf->eng_grps.avail.max_ie_cnt = af_cnsts1.s.ie; + cptpf->eng_grps.avail.max_ae_cnt = af_cnsts1.s.ae; + + /* Disable all cores */ + ret = otx2_cpt_disable_all_cores(cptpf); + + return ret; +} + static int cptpf_sriov_disable(struct pci_dev *pdev) { struct otx2_cptpf_dev *cptpf = pci_get_drvdata(pdev); @@ -446,6 +500,10 @@ static int cptpf_sriov_enable(struct pci_dev *pdev, int num_vfs) if (ret) goto destroy_flr; + ret = otx2_cpt_create_eng_grps(cptpf->pdev, &cptpf->eng_grps); + if (ret) + goto disable_intr; + cptpf->enabled_vfs = num_vfs; ret = pci_enable_sriov(pdev, num_vfs); if (ret) @@ -543,8 +601,20 @@ static int otx2_cptpf_probe(struct pci_dev *pdev, cptpf->max_vfs = pci_sriov_get_totalvfs(pdev); + /* Initialize CPT PF device */ + err = cptpf_device_init(cptpf); + if (err) + goto unregister_intr; + + /* Initialize engine groups */ + err = otx2_cpt_init_eng_grps(pdev, &cptpf->eng_grps); + if (err) + goto unregister_intr; + return 0; +unregister_intr: + cptpf_disable_afpf_mbox_intr(cptpf); destroy_afpf_mbox: cptpf_afpf_mbox_destroy(cptpf); clear_drvdata: @@ -560,6 +630,8 @@ static void otx2_cptpf_remove(struct pci_dev *pdev) return; cptpf_sriov_disable(pdev); + /* Cleanup engine groups */ + otx2_cpt_cleanup_eng_grps(pdev, &cptpf->eng_grps); /* Disable AF-PF mailbox interrupt */ cptpf_disable_afpf_mbox_intr(cptpf); /* Destroy AF-PF mbox */ diff --git a/drivers/crypto/marvell/octeontx2/otx2_cptpf_mbox.c b/drivers/crypto/marvell/octeontx2/otx2_cptpf_mbox.c index 1d97f7202130..08e18fe6817b 100644 --- a/drivers/crypto/marvell/octeontx2/otx2_cptpf_mbox.c +++ b/drivers/crypto/marvell/octeontx2/otx2_cptpf_mbox.c @@ -35,6 +35,29 @@ static int forward_to_af(struct otx2_cptpf_dev *cptpf, return 0; } +static int handle_msg_get_eng_grp_num(struct otx2_cptpf_dev *cptpf, + struct otx2_cptvf_info *vf, + struct mbox_msghdr *req) +{ + struct otx2_cpt_egrp_num_msg *grp_req; + struct otx2_cpt_egrp_num_rsp *rsp; + + grp_req = (struct otx2_cpt_egrp_num_msg *)req; + rsp = (struct otx2_cpt_egrp_num_rsp *) + otx2_mbox_alloc_msg(&cptpf->vfpf_mbox, vf->vf_id, sizeof(*rsp)); + if (!rsp) + return -ENOMEM; + + rsp->hdr.id = MBOX_MSG_GET_ENG_GRP_NUM; + rsp->hdr.sig = OTX2_MBOX_RSP_SIG; + rsp->hdr.pcifunc = req->pcifunc; + rsp->eng_type = grp_req->eng_type; + rsp->eng_grp_num = otx2_cpt_get_eng_grp(&cptpf->eng_grps, + grp_req->eng_type); + + return 0; +} + static int cptpf_handle_vf_req(struct otx2_cptpf_dev *cptpf, struct otx2_cptvf_info *vf, struct mbox_msghdr *req, int size) @@ -45,7 +68,15 @@ static int cptpf_handle_vf_req(struct otx2_cptpf_dev *cptpf, if (req->sig != OTX2_MBOX_REQ_SIG) goto inval_msg; - return forward_to_af(cptpf, vf, req, size); + switch (req->id) { + case MBOX_MSG_GET_ENG_GRP_NUM: + err = handle_msg_get_eng_grp_num(cptpf, vf, req); + break; + default: + err = forward_to_af(cptpf, vf, req, size); + break; + } + return err; inval_msg: otx2_reply_invalid_msg(&cptpf->vfpf_mbox, vf->vf_id, 0, req->id); @@ -148,6 +179,7 @@ static void process_afpf_mbox_msg(struct otx2_cptpf_dev *cptpf, struct mbox_msghdr *msg) { struct device *dev = &cptpf->pdev->dev; + struct cpt_rd_wr_reg_msg *rsp_rd_wr; if (msg->id >= MBOX_MSG_MAX) { dev_err(dev, "MBOX msg with unknown ID %d\n", msg->id); @@ -164,6 +196,18 @@ static void process_afpf_mbox_msg(struct otx2_cptpf_dev *cptpf, cptpf->pf_id = (msg->pcifunc >> RVU_PFVF_PF_SHIFT) & RVU_PFVF_PF_MASK; break; + case MBOX_MSG_CPT_RD_WR_REGISTER: + rsp_rd_wr = (struct cpt_rd_wr_reg_msg *)msg; + if (msg->rc) { + dev_err(dev, "Reg %llx rd/wr(%d) failed %d\n", + rsp_rd_wr->reg_offset, rsp_rd_wr->is_write, + msg->rc); + return; + } + if (!rsp_rd_wr->is_write) + *rsp_rd_wr->ret_val = rsp_rd_wr->val; + break; + default: dev_err(dev, "Unsupported msg %d received.\n", msg->id); diff --git a/drivers/crypto/marvell/octeontx2/otx2_cptpf_ucode.c b/drivers/crypto/marvell/octeontx2/otx2_cptpf_ucode.c new file mode 100644 index 000000000000..d28182a789c6 --- /dev/null +++ b/drivers/crypto/marvell/octeontx2/otx2_cptpf_ucode.c @@ -0,0 +1,1254 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (C) 2020 Marvell. */ + +#include +#include +#include "otx2_cptpf_ucode.h" +#include "otx2_cpt_common.h" +#include "otx2_cptpf.h" +#include "rvu_reg.h" + +#define CSR_DELAY 30 + +#define LOADFVC_RLEN 8 +#define LOADFVC_MAJOR_OP 0x01 +#define LOADFVC_MINOR_OP 0x08 + +struct fw_info_t { + struct list_head ucodes; +}; + +static struct otx2_cpt_bitmap get_cores_bmap(struct device *dev, + struct otx2_cpt_eng_grp_info *eng_grp) +{ + struct otx2_cpt_bitmap bmap = { {0} }; + bool found = false; + int i; + + if (eng_grp->g->engs_num > OTX2_CPT_MAX_ENGINES) { + dev_err(dev, "unsupported number of engines %d on octeontx2\n", + eng_grp->g->engs_num); + return bmap; + } + + for (i = 0; i < OTX2_CPT_MAX_ETYPES_PER_GRP; i++) { + if (eng_grp->engs[i].type) { + bitmap_or(bmap.bits, bmap.bits, + eng_grp->engs[i].bmap, + eng_grp->g->engs_num); + bmap.size = eng_grp->g->engs_num; + found = true; + } + } + + if (!found) + dev_err(dev, "No engines reserved for engine group %d\n", + eng_grp->idx); + return bmap; +} + +static int is_eng_type(int val, int eng_type) +{ + return val & (1 << eng_type); +} + +static int is_2nd_ucode_used(struct otx2_cpt_eng_grp_info *eng_grp) +{ + if (eng_grp->ucode[1].type) + return true; + else + return false; +} + +static void set_ucode_filename(struct otx2_cpt_ucode *ucode, + const char *filename) +{ + strlcpy(ucode->filename, filename, OTX2_CPT_NAME_LENGTH); +} + +static char *get_eng_type_str(int eng_type) +{ + char *str = "unknown"; + + switch (eng_type) { + case OTX2_CPT_SE_TYPES: + str = "SE"; + break; + + case OTX2_CPT_IE_TYPES: + str = "IE"; + break; + + case OTX2_CPT_AE_TYPES: + str = "AE"; + break; + } + return str; +} + +static char *get_ucode_type_str(int ucode_type) +{ + char *str = "unknown"; + + switch (ucode_type) { + case (1 << OTX2_CPT_SE_TYPES): + str = "SE"; + break; + + case (1 << OTX2_CPT_IE_TYPES): + str = "IE"; + break; + + case (1 << OTX2_CPT_AE_TYPES): + str = "AE"; + break; + + case (1 << OTX2_CPT_SE_TYPES | 1 << OTX2_CPT_IE_TYPES): + str = "SE+IPSEC"; + break; + } + return str; +} + +static int get_ucode_type(struct device *dev, + struct otx2_cpt_ucode_hdr *ucode_hdr, + int *ucode_type) +{ + struct otx2_cptpf_dev *cptpf = dev_get_drvdata(dev); + char ver_str_prefix[OTX2_CPT_UCODE_VER_STR_SZ]; + char tmp_ver_str[OTX2_CPT_UCODE_VER_STR_SZ]; + struct pci_dev *pdev = cptpf->pdev; + int i, val = 0; + u8 nn; + + strlcpy(tmp_ver_str, ucode_hdr->ver_str, OTX2_CPT_UCODE_VER_STR_SZ); + for (i = 0; i < strlen(tmp_ver_str); i++) + tmp_ver_str[i] = tolower(tmp_ver_str[i]); + + sprintf(ver_str_prefix, "ocpt-%02d", pdev->revision); + if (!strnstr(tmp_ver_str, ver_str_prefix, OTX2_CPT_UCODE_VER_STR_SZ)) + return -EINVAL; + + nn = ucode_hdr->ver_num.nn; + if (strnstr(tmp_ver_str, "se-", OTX2_CPT_UCODE_VER_STR_SZ) && + (nn == OTX2_CPT_SE_UC_TYPE1 || nn == OTX2_CPT_SE_UC_TYPE2 || + nn == OTX2_CPT_SE_UC_TYPE3)) + val |= 1 << OTX2_CPT_SE_TYPES; + if (strnstr(tmp_ver_str, "ie-", OTX2_CPT_UCODE_VER_STR_SZ) && + (nn == OTX2_CPT_IE_UC_TYPE1 || nn == OTX2_CPT_IE_UC_TYPE2 || + nn == OTX2_CPT_IE_UC_TYPE3)) + val |= 1 << OTX2_CPT_IE_TYPES; + if (strnstr(tmp_ver_str, "ae", OTX2_CPT_UCODE_VER_STR_SZ) && + nn == OTX2_CPT_AE_UC_TYPE) + val |= 1 << OTX2_CPT_AE_TYPES; + + *ucode_type = val; + + if (!val) + return -EINVAL; + + return 0; +} + +static int __write_ucode_base(struct otx2_cptpf_dev *cptpf, int eng, + dma_addr_t dma_addr) +{ + return otx2_cpt_write_af_reg(&cptpf->afpf_mbox, cptpf->pdev, + CPT_AF_EXEX_UCODE_BASE(eng), + (u64)dma_addr); +} + +static int cpt_set_ucode_base(struct otx2_cpt_eng_grp_info *eng_grp, void *obj) +{ + struct otx2_cptpf_dev *cptpf = obj; + struct otx2_cpt_engs_rsvd *engs; + dma_addr_t dma_addr; + int i, bit, ret; + + /* Set PF number for microcode fetches */ + ret = otx2_cpt_write_af_reg(&cptpf->afpf_mbox, cptpf->pdev, + CPT_AF_PF_FUNC, + cptpf->pf_id << RVU_PFVF_PF_SHIFT); + if (ret) + return ret; + + for (i = 0; i < OTX2_CPT_MAX_ETYPES_PER_GRP; i++) { + engs = &eng_grp->engs[i]; + if (!engs->type) + continue; + + dma_addr = engs->ucode->dma; + + /* + * Set UCODE_BASE only for the cores which are not used, + * other cores should have already valid UCODE_BASE set + */ + for_each_set_bit(bit, engs->bmap, eng_grp->g->engs_num) + if (!eng_grp->g->eng_ref_cnt[bit]) { + ret = __write_ucode_base(cptpf, bit, dma_addr); + if (ret) + return ret; + } + } + return 0; +} + +static int cpt_detach_and_disable_cores(struct otx2_cpt_eng_grp_info *eng_grp, + void *obj) +{ + struct otx2_cptpf_dev *cptpf = obj; + struct otx2_cpt_bitmap bmap; + int i, timeout = 10; + int busy, ret; + u64 reg = 0; + + bmap = get_cores_bmap(&cptpf->pdev->dev, eng_grp); + if (!bmap.size) + return -EINVAL; + + /* Detach the cores from group */ + for_each_set_bit(i, bmap.bits, bmap.size) { + ret = otx2_cpt_read_af_reg(&cptpf->afpf_mbox, cptpf->pdev, + CPT_AF_EXEX_CTL2(i), ®); + if (ret) + return ret; + + if (reg & (1ull << eng_grp->idx)) { + eng_grp->g->eng_ref_cnt[i]--; + reg &= ~(1ull << eng_grp->idx); + + ret = otx2_cpt_write_af_reg(&cptpf->afpf_mbox, + cptpf->pdev, + CPT_AF_EXEX_CTL2(i), reg); + if (ret) + return ret; + } + } + + /* Wait for cores to become idle */ + do { + busy = 0; + usleep_range(10000, 20000); + if (timeout-- < 0) + return -EBUSY; + + for_each_set_bit(i, bmap.bits, bmap.size) { + ret = otx2_cpt_read_af_reg(&cptpf->afpf_mbox, + cptpf->pdev, + CPT_AF_EXEX_STS(i), ®); + if (ret) + return ret; + + if (reg & 0x1) { + busy = 1; + break; + } + } + } while (busy); + + /* Disable the cores only if they are not used anymore */ + for_each_set_bit(i, bmap.bits, bmap.size) { + if (!eng_grp->g->eng_ref_cnt[i]) { + ret = otx2_cpt_write_af_reg(&cptpf->afpf_mbox, + cptpf->pdev, + CPT_AF_EXEX_CTL(i), 0x0); + if (ret) + return ret; + } + } + + return 0; +} + +static int cpt_attach_and_enable_cores(struct otx2_cpt_eng_grp_info *eng_grp, + void *obj) +{ + struct otx2_cptpf_dev *cptpf = obj; + struct otx2_cpt_bitmap bmap; + u64 reg = 0; + int i, ret; + + bmap = get_cores_bmap(&cptpf->pdev->dev, eng_grp); + if (!bmap.size) + return -EINVAL; + + /* Attach the cores to the group */ + for_each_set_bit(i, bmap.bits, bmap.size) { + ret = otx2_cpt_read_af_reg(&cptpf->afpf_mbox, cptpf->pdev, + CPT_AF_EXEX_CTL2(i), ®); + if (ret) + return ret; + + if (!(reg & (1ull << eng_grp->idx))) { + eng_grp->g->eng_ref_cnt[i]++; + reg |= 1ull << eng_grp->idx; + + ret = otx2_cpt_write_af_reg(&cptpf->afpf_mbox, + cptpf->pdev, + CPT_AF_EXEX_CTL2(i), reg); + if (ret) + return ret; + } + } + + /* Enable the cores */ + for_each_set_bit(i, bmap.bits, bmap.size) { + ret = otx2_cpt_add_write_af_reg(&cptpf->afpf_mbox, + cptpf->pdev, + CPT_AF_EXEX_CTL(i), 0x1); + if (ret) + return ret; + } + ret = otx2_cpt_send_af_reg_requests(&cptpf->afpf_mbox, cptpf->pdev); + + return ret; +} + +static int load_fw(struct device *dev, struct fw_info_t *fw_info, + char *filename) +{ + struct otx2_cpt_ucode_hdr *ucode_hdr; + struct otx2_cpt_uc_info_t *uc_info; + int ucode_type, ucode_size; + int ret; + + uc_info = kzalloc(sizeof(*uc_info), GFP_KERNEL); + if (!uc_info) + return -ENOMEM; + + ret = request_firmware(&uc_info->fw, filename, dev); + if (ret) + goto free_uc_info; + + ucode_hdr = (struct otx2_cpt_ucode_hdr *)uc_info->fw->data; + ret = get_ucode_type(dev, ucode_hdr, &ucode_type); + if (ret) + goto release_fw; + + ucode_size = ntohl(ucode_hdr->code_length) * 2; + if (!ucode_size) { + dev_err(dev, "Ucode %s invalid size\n", filename); + ret = -EINVAL; + goto release_fw; + } + + set_ucode_filename(&uc_info->ucode, filename); + memcpy(uc_info->ucode.ver_str, ucode_hdr->ver_str, + OTX2_CPT_UCODE_VER_STR_SZ); + uc_info->ucode.ver_num = ucode_hdr->ver_num; + uc_info->ucode.type = ucode_type; + uc_info->ucode.size = ucode_size; + list_add_tail(&uc_info->list, &fw_info->ucodes); + + return 0; + +release_fw: + release_firmware(uc_info->fw); +free_uc_info: + kfree(uc_info); + return ret; +} + +static void cpt_ucode_release_fw(struct fw_info_t *fw_info) +{ + struct otx2_cpt_uc_info_t *curr, *temp; + + if (!fw_info) + return; + + list_for_each_entry_safe(curr, temp, &fw_info->ucodes, list) { + list_del(&curr->list); + release_firmware(curr->fw); + kfree(curr); + } +} + +static struct otx2_cpt_uc_info_t *get_ucode(struct fw_info_t *fw_info, + int ucode_type) +{ + struct otx2_cpt_uc_info_t *curr; + + list_for_each_entry(curr, &fw_info->ucodes, list) { + if (!is_eng_type(curr->ucode.type, ucode_type)) + continue; + + return curr; + } + return NULL; +} + +static void print_uc_info(struct fw_info_t *fw_info) +{ + struct otx2_cpt_uc_info_t *curr; + + list_for_each_entry(curr, &fw_info->ucodes, list) { + pr_debug("Ucode filename %s\n", curr->ucode.filename); + pr_debug("Ucode version string %s\n", curr->ucode.ver_str); + pr_debug("Ucode version %d.%d.%d.%d\n", + curr->ucode.ver_num.nn, curr->ucode.ver_num.xx, + curr->ucode.ver_num.yy, curr->ucode.ver_num.zz); + pr_debug("Ucode type (%d) %s\n", curr->ucode.type, + get_ucode_type_str(curr->ucode.type)); + pr_debug("Ucode size %d\n", curr->ucode.size); + pr_debug("Ucode ptr %p\n", curr->fw->data); + } +} + +static int cpt_ucode_load_fw(struct pci_dev *pdev, struct fw_info_t *fw_info) +{ + char filename[OTX2_CPT_NAME_LENGTH]; + char eng_type[8] = {0}; + int ret, e, i; + + INIT_LIST_HEAD(&fw_info->ucodes); + + for (e = 1; e < OTX2_CPT_MAX_ENG_TYPES; e++) { + strncpy(eng_type, get_eng_type_str(e), 2); + for (i = 0; i < strlen(eng_type); i++) + eng_type[i] = tolower(eng_type[i]); + + snprintf(filename, sizeof(filename), "mrvl/cpt%02d/%s.out", + pdev->revision, eng_type); + /* Request firmware for each engine type */ + ret = load_fw(&pdev->dev, fw_info, filename); + if (ret) + goto release_fw; + } + print_uc_info(fw_info); + return 0; + +release_fw: + cpt_ucode_release_fw(fw_info); + return ret; +} + +static struct otx2_cpt_engs_rsvd *find_engines_by_type( + struct otx2_cpt_eng_grp_info *eng_grp, + int eng_type) +{ + int i; + + for (i = 0; i < OTX2_CPT_MAX_ETYPES_PER_GRP; i++) { + if (!eng_grp->engs[i].type) + continue; + + if (eng_grp->engs[i].type == eng_type) + return &eng_grp->engs[i]; + } + return NULL; +} + +static int eng_grp_has_eng_type(struct otx2_cpt_eng_grp_info *eng_grp, + int eng_type) +{ + struct otx2_cpt_engs_rsvd *engs; + + engs = find_engines_by_type(eng_grp, eng_type); + + return (engs != NULL ? 1 : 0); +} + +static int update_engines_avail_count(struct device *dev, + struct otx2_cpt_engs_available *avail, + struct otx2_cpt_engs_rsvd *engs, int val) +{ + switch (engs->type) { + case OTX2_CPT_SE_TYPES: + avail->se_cnt += val; + break; + + case OTX2_CPT_IE_TYPES: + avail->ie_cnt += val; + break; + + case OTX2_CPT_AE_TYPES: + avail->ae_cnt += val; + break; + + default: + dev_err(dev, "Invalid engine type %d\n", engs->type); + return -EINVAL; + } + return 0; +} + +static int update_engines_offset(struct device *dev, + struct otx2_cpt_engs_available *avail, + struct otx2_cpt_engs_rsvd *engs) +{ + switch (engs->type) { + case OTX2_CPT_SE_TYPES: + engs->offset = 0; + break; + + case OTX2_CPT_IE_TYPES: + engs->offset = avail->max_se_cnt; + break; + + case OTX2_CPT_AE_TYPES: + engs->offset = avail->max_se_cnt + avail->max_ie_cnt; + break; + + default: + dev_err(dev, "Invalid engine type %d\n", engs->type); + return -EINVAL; + } + return 0; +} + +static int release_engines(struct device *dev, + struct otx2_cpt_eng_grp_info *grp) +{ + int i, ret = 0; + + for (i = 0; i < OTX2_CPT_MAX_ETYPES_PER_GRP; i++) { + if (!grp->engs[i].type) + continue; + + if (grp->engs[i].count > 0) { + ret = update_engines_avail_count(dev, &grp->g->avail, + &grp->engs[i], + grp->engs[i].count); + if (ret) + return ret; + } + + grp->engs[i].type = 0; + grp->engs[i].count = 0; + grp->engs[i].offset = 0; + grp->engs[i].ucode = NULL; + bitmap_zero(grp->engs[i].bmap, grp->g->engs_num); + } + return 0; +} + +static int do_reserve_engines(struct device *dev, + struct otx2_cpt_eng_grp_info *grp, + struct otx2_cpt_engines *req_engs) +{ + struct otx2_cpt_engs_rsvd *engs = NULL; + int i, ret; + + for (i = 0; i < OTX2_CPT_MAX_ETYPES_PER_GRP; i++) { + if (!grp->engs[i].type) { + engs = &grp->engs[i]; + break; + } + } + + if (!engs) + return -ENOMEM; + + engs->type = req_engs->type; + engs->count = req_engs->count; + + ret = update_engines_offset(dev, &grp->g->avail, engs); + if (ret) + return ret; + + if (engs->count > 0) { + ret = update_engines_avail_count(dev, &grp->g->avail, engs, + -engs->count); + if (ret) + return ret; + } + + return 0; +} + +static int check_engines_availability(struct device *dev, + struct otx2_cpt_eng_grp_info *grp, + struct otx2_cpt_engines *req_eng) +{ + int avail_cnt = 0; + + switch (req_eng->type) { + case OTX2_CPT_SE_TYPES: + avail_cnt = grp->g->avail.se_cnt; + break; + + case OTX2_CPT_IE_TYPES: + avail_cnt = grp->g->avail.ie_cnt; + break; + + case OTX2_CPT_AE_TYPES: + avail_cnt = grp->g->avail.ae_cnt; + break; + + default: + dev_err(dev, "Invalid engine type %d\n", req_eng->type); + return -EINVAL; + } + + if (avail_cnt < req_eng->count) { + dev_err(dev, + "Error available %s engines %d < than requested %d\n", + get_eng_type_str(req_eng->type), + avail_cnt, req_eng->count); + return -EBUSY; + } + return 0; +} + +static int reserve_engines(struct device *dev, + struct otx2_cpt_eng_grp_info *grp, + struct otx2_cpt_engines *req_engs, int ucodes_cnt) +{ + int i, ret = 0; + + /* Validate if a number of requested engines are available */ + for (i = 0; i < ucodes_cnt; i++) { + ret = check_engines_availability(dev, grp, &req_engs[i]); + if (ret) + return ret; + } + + /* Reserve requested engines for this engine group */ + for (i = 0; i < ucodes_cnt; i++) { + ret = do_reserve_engines(dev, grp, &req_engs[i]); + if (ret) + return ret; + } + return 0; +} + +static void ucode_unload(struct device *dev, struct otx2_cpt_ucode *ucode) +{ + if (ucode->va) { + dma_free_coherent(dev, ucode->size, ucode->va, ucode->dma); + ucode->va = NULL; + ucode->dma = 0; + ucode->size = 0; + } + + memset(&ucode->ver_str, 0, OTX2_CPT_UCODE_VER_STR_SZ); + memset(&ucode->ver_num, 0, sizeof(struct otx2_cpt_ucode_ver_num)); + set_ucode_filename(ucode, ""); + ucode->type = 0; +} + +static int copy_ucode_to_dma_mem(struct device *dev, + struct otx2_cpt_ucode *ucode, + const u8 *ucode_data) +{ + u32 i; + + /* Allocate DMAable space */ + ucode->va = dma_alloc_coherent(dev, ucode->size, &ucode->dma, + GFP_KERNEL); + if (!ucode->va) + return -ENOMEM; + + memcpy(ucode->va, ucode_data + sizeof(struct otx2_cpt_ucode_hdr), + ucode->size); + + /* Byte swap 64-bit */ + for (i = 0; i < (ucode->size / 8); i++) + cpu_to_be64s(&((u64 *)ucode->va)[i]); + /* Ucode needs 16-bit swap */ + for (i = 0; i < (ucode->size / 2); i++) + cpu_to_be16s(&((u16 *)ucode->va)[i]); + return 0; +} + +static int enable_eng_grp(struct otx2_cpt_eng_grp_info *eng_grp, + void *obj) +{ + int ret; + + /* Point microcode to each core of the group */ + ret = cpt_set_ucode_base(eng_grp, obj); + if (ret) + return ret; + + /* Attach the cores to the group and enable them */ + ret = cpt_attach_and_enable_cores(eng_grp, obj); + + return ret; +} + +static int disable_eng_grp(struct device *dev, + struct otx2_cpt_eng_grp_info *eng_grp, + void *obj) +{ + int i, ret; + + /* Disable all engines used by this group */ + ret = cpt_detach_and_disable_cores(eng_grp, obj); + if (ret) + return ret; + + /* Unload ucode used by this engine group */ + ucode_unload(dev, &eng_grp->ucode[0]); + ucode_unload(dev, &eng_grp->ucode[1]); + + for (i = 0; i < OTX2_CPT_MAX_ETYPES_PER_GRP; i++) { + if (!eng_grp->engs[i].type) + continue; + + eng_grp->engs[i].ucode = &eng_grp->ucode[0]; + } + + /* Clear UCODE_BASE register for each engine used by this group */ + ret = cpt_set_ucode_base(eng_grp, obj); + + return ret; +} + +static void setup_eng_grp_mirroring(struct otx2_cpt_eng_grp_info *dst_grp, + struct otx2_cpt_eng_grp_info *src_grp) +{ + /* Setup fields for engine group which is mirrored */ + src_grp->mirror.is_ena = false; + src_grp->mirror.idx = 0; + src_grp->mirror.ref_count++; + + /* Setup fields for mirroring engine group */ + dst_grp->mirror.is_ena = true; + dst_grp->mirror.idx = src_grp->idx; + dst_grp->mirror.ref_count = 0; +} + +static void remove_eng_grp_mirroring(struct otx2_cpt_eng_grp_info *dst_grp) +{ + struct otx2_cpt_eng_grp_info *src_grp; + + if (!dst_grp->mirror.is_ena) + return; + + src_grp = &dst_grp->g->grp[dst_grp->mirror.idx]; + + src_grp->mirror.ref_count--; + dst_grp->mirror.is_ena = false; + dst_grp->mirror.idx = 0; + dst_grp->mirror.ref_count = 0; +} + +static void update_requested_engs(struct otx2_cpt_eng_grp_info *mirror_eng_grp, + struct otx2_cpt_engines *engs, int engs_cnt) +{ + struct otx2_cpt_engs_rsvd *mirrored_engs; + int i; + + for (i = 0; i < engs_cnt; i++) { + mirrored_engs = find_engines_by_type(mirror_eng_grp, + engs[i].type); + if (!mirrored_engs) + continue; + + /* + * If mirrored group has this type of engines attached then + * there are 3 scenarios possible: + * 1) mirrored_engs.count == engs[i].count then all engines + * from mirrored engine group will be shared with this engine + * group + * 2) mirrored_engs.count > engs[i].count then only a subset of + * engines from mirrored engine group will be shared with this + * engine group + * 3) mirrored_engs.count < engs[i].count then all engines + * from mirrored engine group will be shared with this group + * and additional engines will be reserved for exclusively use + * by this engine group + */ + engs[i].count -= mirrored_engs->count; + } +} + +static struct otx2_cpt_eng_grp_info *find_mirrored_eng_grp( + struct otx2_cpt_eng_grp_info *grp) +{ + struct otx2_cpt_eng_grps *eng_grps = grp->g; + int i; + + for (i = 0; i < OTX2_CPT_MAX_ENGINE_GROUPS; i++) { + if (!eng_grps->grp[i].is_enabled) + continue; + if (eng_grps->grp[i].ucode[0].type && + eng_grps->grp[i].ucode[1].type) + continue; + if (grp->idx == i) + continue; + if (!strncasecmp(eng_grps->grp[i].ucode[0].ver_str, + grp->ucode[0].ver_str, + OTX2_CPT_UCODE_VER_STR_SZ)) + return &eng_grps->grp[i]; + } + + return NULL; +} + +static struct otx2_cpt_eng_grp_info *find_unused_eng_grp( + struct otx2_cpt_eng_grps *eng_grps) +{ + int i; + + for (i = 0; i < OTX2_CPT_MAX_ENGINE_GROUPS; i++) { + if (!eng_grps->grp[i].is_enabled) + return &eng_grps->grp[i]; + } + return NULL; +} + +static int eng_grp_update_masks(struct device *dev, + struct otx2_cpt_eng_grp_info *eng_grp) +{ + struct otx2_cpt_engs_rsvd *engs, *mirrored_engs; + struct otx2_cpt_bitmap tmp_bmap = { {0} }; + int i, j, cnt, max_cnt; + int bit; + + for (i = 0; i < OTX2_CPT_MAX_ETYPES_PER_GRP; i++) { + engs = &eng_grp->engs[i]; + if (!engs->type) + continue; + if (engs->count <= 0) + continue; + + switch (engs->type) { + case OTX2_CPT_SE_TYPES: + max_cnt = eng_grp->g->avail.max_se_cnt; + break; + + case OTX2_CPT_IE_TYPES: + max_cnt = eng_grp->g->avail.max_ie_cnt; + break; + + case OTX2_CPT_AE_TYPES: + max_cnt = eng_grp->g->avail.max_ae_cnt; + break; + + default: + dev_err(dev, "Invalid engine type %d\n", engs->type); + return -EINVAL; + } + + cnt = engs->count; + WARN_ON(engs->offset + max_cnt > OTX2_CPT_MAX_ENGINES); + bitmap_zero(tmp_bmap.bits, eng_grp->g->engs_num); + for (j = engs->offset; j < engs->offset + max_cnt; j++) { + if (!eng_grp->g->eng_ref_cnt[j]) { + bitmap_set(tmp_bmap.bits, j, 1); + cnt--; + if (!cnt) + break; + } + } + + if (cnt) + return -ENOSPC; + + bitmap_copy(engs->bmap, tmp_bmap.bits, eng_grp->g->engs_num); + } + + if (!eng_grp->mirror.is_ena) + return 0; + + for (i = 0; i < OTX2_CPT_MAX_ETYPES_PER_GRP; i++) { + engs = &eng_grp->engs[i]; + if (!engs->type) + continue; + + mirrored_engs = find_engines_by_type( + &eng_grp->g->grp[eng_grp->mirror.idx], + engs->type); + WARN_ON(!mirrored_engs && engs->count <= 0); + if (!mirrored_engs) + continue; + + bitmap_copy(tmp_bmap.bits, mirrored_engs->bmap, + eng_grp->g->engs_num); + if (engs->count < 0) { + bit = find_first_bit(mirrored_engs->bmap, + eng_grp->g->engs_num); + bitmap_clear(tmp_bmap.bits, bit, -engs->count); + } + bitmap_or(engs->bmap, engs->bmap, tmp_bmap.bits, + eng_grp->g->engs_num); + } + return 0; +} + +static int delete_engine_group(struct device *dev, + struct otx2_cpt_eng_grp_info *eng_grp) +{ + int ret; + + if (!eng_grp->is_enabled) + return 0; + + if (eng_grp->mirror.ref_count) + return -EINVAL; + + /* Removing engine group mirroring if enabled */ + remove_eng_grp_mirroring(eng_grp); + + /* Disable engine group */ + ret = disable_eng_grp(dev, eng_grp, eng_grp->g->obj); + if (ret) + return ret; + + /* Release all engines held by this engine group */ + ret = release_engines(dev, eng_grp); + if (ret) + return ret; + + eng_grp->is_enabled = false; + + return 0; +} + +static void update_ucode_ptrs(struct otx2_cpt_eng_grp_info *eng_grp) +{ + struct otx2_cpt_ucode *ucode; + + if (eng_grp->mirror.is_ena) + ucode = &eng_grp->g->grp[eng_grp->mirror.idx].ucode[0]; + else + ucode = &eng_grp->ucode[0]; + WARN_ON(!eng_grp->engs[0].type); + eng_grp->engs[0].ucode = ucode; + + if (eng_grp->engs[1].type) { + if (is_2nd_ucode_used(eng_grp)) + eng_grp->engs[1].ucode = &eng_grp->ucode[1]; + else + eng_grp->engs[1].ucode = ucode; + } +} + +static int create_engine_group(struct device *dev, + struct otx2_cpt_eng_grps *eng_grps, + struct otx2_cpt_engines *engs, int ucodes_cnt, + void *ucode_data[], int is_print) +{ + struct otx2_cpt_eng_grp_info *mirrored_eng_grp; + struct otx2_cpt_eng_grp_info *eng_grp; + struct otx2_cpt_uc_info_t *uc_info; + int i, ret = 0; + + /* Find engine group which is not used */ + eng_grp = find_unused_eng_grp(eng_grps); + if (!eng_grp) { + dev_err(dev, "Error all engine groups are being used\n"); + return -ENOSPC; + } + /* Load ucode */ + for (i = 0; i < ucodes_cnt; i++) { + uc_info = (struct otx2_cpt_uc_info_t *) ucode_data[i]; + eng_grp->ucode[i] = uc_info->ucode; + ret = copy_ucode_to_dma_mem(dev, &eng_grp->ucode[i], + uc_info->fw->data); + if (ret) + goto unload_ucode; + } + + /* Check if this group mirrors another existing engine group */ + mirrored_eng_grp = find_mirrored_eng_grp(eng_grp); + if (mirrored_eng_grp) { + /* Setup mirroring */ + setup_eng_grp_mirroring(eng_grp, mirrored_eng_grp); + + /* + * Update count of requested engines because some + * of them might be shared with mirrored group + */ + update_requested_engs(mirrored_eng_grp, engs, ucodes_cnt); + } + ret = reserve_engines(dev, eng_grp, engs, ucodes_cnt); + if (ret) + goto unload_ucode; + + /* Update ucode pointers used by engines */ + update_ucode_ptrs(eng_grp); + + /* Update engine masks used by this group */ + ret = eng_grp_update_masks(dev, eng_grp); + if (ret) + goto release_engs; + + /* Enable engine group */ + ret = enable_eng_grp(eng_grp, eng_grps->obj); + if (ret) + goto release_engs; + + /* + * If this engine group mirrors another engine group + * then we need to unload ucode as we will use ucode + * from mirrored engine group + */ + if (eng_grp->mirror.is_ena) + ucode_unload(dev, &eng_grp->ucode[0]); + + eng_grp->is_enabled = true; + + if (!is_print) + return 0; + + if (mirrored_eng_grp) + dev_info(dev, + "Engine_group%d: reuse microcode %s from group %d\n", + eng_grp->idx, mirrored_eng_grp->ucode[0].ver_str, + mirrored_eng_grp->idx); + else + dev_info(dev, "Engine_group%d: microcode loaded %s\n", + eng_grp->idx, eng_grp->ucode[0].ver_str); + if (is_2nd_ucode_used(eng_grp)) + dev_info(dev, "Engine_group%d: microcode loaded %s\n", + eng_grp->idx, eng_grp->ucode[1].ver_str); + + return 0; + +release_engs: + release_engines(dev, eng_grp); +unload_ucode: + ucode_unload(dev, &eng_grp->ucode[0]); + ucode_unload(dev, &eng_grp->ucode[1]); + return ret; +} + +static void delete_engine_grps(struct pci_dev *pdev, + struct otx2_cpt_eng_grps *eng_grps) +{ + int i; + + /* First delete all mirroring engine groups */ + for (i = 0; i < OTX2_CPT_MAX_ENGINE_GROUPS; i++) + if (eng_grps->grp[i].mirror.is_ena) + delete_engine_group(&pdev->dev, &eng_grps->grp[i]); + + /* Delete remaining engine groups */ + for (i = 0; i < OTX2_CPT_MAX_ENGINE_GROUPS; i++) + delete_engine_group(&pdev->dev, &eng_grps->grp[i]); +} + +int otx2_cpt_get_eng_grp(struct otx2_cpt_eng_grps *eng_grps, int eng_type) +{ + + int eng_grp_num = OTX2_CPT_INVALID_CRYPTO_ENG_GRP; + struct otx2_cpt_eng_grp_info *grp; + int i; + + for (i = 0; i < OTX2_CPT_MAX_ENGINE_GROUPS; i++) { + grp = &eng_grps->grp[i]; + if (!grp->is_enabled) + continue; + + if (eng_type == OTX2_CPT_SE_TYPES) { + if (eng_grp_has_eng_type(grp, eng_type) && + !eng_grp_has_eng_type(grp, OTX2_CPT_IE_TYPES)) { + eng_grp_num = i; + break; + } + } else { + if (eng_grp_has_eng_type(grp, eng_type)) { + eng_grp_num = i; + break; + } + } + } + return eng_grp_num; +} + +int otx2_cpt_create_eng_grps(struct pci_dev *pdev, + struct otx2_cpt_eng_grps *eng_grps) +{ + struct otx2_cpt_uc_info_t *uc_info[OTX2_CPT_MAX_ETYPES_PER_GRP] = { }; + struct otx2_cpt_engines engs[OTX2_CPT_MAX_ETYPES_PER_GRP] = { {0} }; + struct fw_info_t fw_info; + int ret; + + /* + * We don't create engine groups if it was already + * made (when user enabled VFs for the first time) + */ + if (eng_grps->is_grps_created) + return 0; + + ret = cpt_ucode_load_fw(pdev, &fw_info); + if (ret) + return ret; + + /* + * Create engine group with SE engines for kernel + * crypto functionality (symmetric crypto) + */ + uc_info[0] = get_ucode(&fw_info, OTX2_CPT_SE_TYPES); + if (uc_info[0] == NULL) { + dev_err(&pdev->dev, "Unable to find firmware for SE\n"); + ret = -EINVAL; + goto release_fw; + } + engs[0].type = OTX2_CPT_SE_TYPES; + engs[0].count = eng_grps->avail.max_se_cnt; + + ret = create_engine_group(&pdev->dev, eng_grps, engs, 1, + (void **) uc_info, 1); + if (ret) + goto release_fw; + + /* + * Create engine group with SE+IE engines for IPSec. + * All SE engines will be shared with engine group 0. + */ + uc_info[0] = get_ucode(&fw_info, OTX2_CPT_SE_TYPES); + uc_info[1] = get_ucode(&fw_info, OTX2_CPT_IE_TYPES); + + if (uc_info[1] == NULL) { + dev_err(&pdev->dev, "Unable to find firmware for IE"); + ret = -EINVAL; + goto delete_eng_grp; + } + engs[0].type = OTX2_CPT_SE_TYPES; + engs[0].count = eng_grps->avail.max_se_cnt; + engs[1].type = OTX2_CPT_IE_TYPES; + engs[1].count = eng_grps->avail.max_ie_cnt; + + ret = create_engine_group(&pdev->dev, eng_grps, engs, 2, + (void **) uc_info, 1); + if (ret) + goto delete_eng_grp; + + /* + * Create engine group with AE engines for asymmetric + * crypto functionality. + */ + uc_info[0] = get_ucode(&fw_info, OTX2_CPT_AE_TYPES); + if (uc_info[0] == NULL) { + dev_err(&pdev->dev, "Unable to find firmware for AE"); + ret = -EINVAL; + goto delete_eng_grp; + } + engs[0].type = OTX2_CPT_AE_TYPES; + engs[0].count = eng_grps->avail.max_ae_cnt; + + ret = create_engine_group(&pdev->dev, eng_grps, engs, 1, + (void **) uc_info, 1); + if (ret) + goto delete_eng_grp; + + eng_grps->is_grps_created = true; + + cpt_ucode_release_fw(&fw_info); + return 0; + +delete_eng_grp: + delete_engine_grps(pdev, eng_grps); +release_fw: + cpt_ucode_release_fw(&fw_info); + return ret; +} + +int otx2_cpt_disable_all_cores(struct otx2_cptpf_dev *cptpf) +{ + int i, ret, busy, total_cores; + int timeout = 10; + u64 reg = 0; + + total_cores = cptpf->eng_grps.avail.max_se_cnt + + cptpf->eng_grps.avail.max_ie_cnt + + cptpf->eng_grps.avail.max_ae_cnt; + + /* Disengage the cores from groups */ + for (i = 0; i < total_cores; i++) { + ret = otx2_cpt_add_write_af_reg(&cptpf->afpf_mbox, cptpf->pdev, + CPT_AF_EXEX_CTL2(i), 0x0); + if (ret) + return ret; + + cptpf->eng_grps.eng_ref_cnt[i] = 0; + } + ret = otx2_cpt_send_af_reg_requests(&cptpf->afpf_mbox, cptpf->pdev); + if (ret) + return ret; + + /* Wait for cores to become idle */ + do { + busy = 0; + usleep_range(10000, 20000); + if (timeout-- < 0) + return -EBUSY; + + for (i = 0; i < total_cores; i++) { + ret = otx2_cpt_read_af_reg(&cptpf->afpf_mbox, + cptpf->pdev, + CPT_AF_EXEX_STS(i), ®); + if (ret) + return ret; + + if (reg & 0x1) { + busy = 1; + break; + } + } + } while (busy); + + /* Disable the cores */ + for (i = 0; i < total_cores; i++) { + ret = otx2_cpt_add_write_af_reg(&cptpf->afpf_mbox, cptpf->pdev, + CPT_AF_EXEX_CTL(i), 0x0); + if (ret) + return ret; + } + return otx2_cpt_send_af_reg_requests(&cptpf->afpf_mbox, cptpf->pdev); +} + +void otx2_cpt_cleanup_eng_grps(struct pci_dev *pdev, + struct otx2_cpt_eng_grps *eng_grps) +{ + struct otx2_cpt_eng_grp_info *grp; + int i, j; + + delete_engine_grps(pdev, eng_grps); + /* Release memory */ + for (i = 0; i < OTX2_CPT_MAX_ENGINE_GROUPS; i++) { + grp = &eng_grps->grp[i]; + for (j = 0; j < OTX2_CPT_MAX_ETYPES_PER_GRP; j++) { + kfree(grp->engs[j].bmap); + grp->engs[j].bmap = NULL; + } + } +} + +int otx2_cpt_init_eng_grps(struct pci_dev *pdev, + struct otx2_cpt_eng_grps *eng_grps) +{ + struct otx2_cpt_eng_grp_info *grp; + int i, j, ret; + + eng_grps->obj = pci_get_drvdata(pdev); + eng_grps->avail.se_cnt = eng_grps->avail.max_se_cnt; + eng_grps->avail.ie_cnt = eng_grps->avail.max_ie_cnt; + eng_grps->avail.ae_cnt = eng_grps->avail.max_ae_cnt; + + eng_grps->engs_num = eng_grps->avail.max_se_cnt + + eng_grps->avail.max_ie_cnt + + eng_grps->avail.max_ae_cnt; + if (eng_grps->engs_num > OTX2_CPT_MAX_ENGINES) { + dev_err(&pdev->dev, + "Number of engines %d > than max supported %d\n", + eng_grps->engs_num, OTX2_CPT_MAX_ENGINES); + ret = -EINVAL; + goto cleanup_eng_grps; + } + + for (i = 0; i < OTX2_CPT_MAX_ENGINE_GROUPS; i++) { + grp = &eng_grps->grp[i]; + grp->g = eng_grps; + grp->idx = i; + + for (j = 0; j < OTX2_CPT_MAX_ETYPES_PER_GRP; j++) { + grp->engs[j].bmap = + kcalloc(BITS_TO_LONGS(eng_grps->engs_num), + sizeof(long), GFP_KERNEL); + if (!grp->engs[j].bmap) { + ret = -ENOMEM; + goto cleanup_eng_grps; + } + } + } + return 0; + +cleanup_eng_grps: + otx2_cpt_cleanup_eng_grps(pdev, eng_grps); + return ret; +} diff --git a/drivers/crypto/marvell/octeontx2/otx2_cptpf_ucode.h b/drivers/crypto/marvell/octeontx2/otx2_cptpf_ucode.h new file mode 100644 index 000000000000..96556399a58c --- /dev/null +++ b/drivers/crypto/marvell/octeontx2/otx2_cptpf_ucode.h @@ -0,0 +1,161 @@ +/* SPDX-License-Identifier: GPL-2.0-only + * Copyright (C) 2020 Marvell. + */ + +#ifndef __OTX2_CPTPF_UCODE_H +#define __OTX2_CPTPF_UCODE_H + +#include +#include +#include +#include "otx2_cpt_hw_types.h" +#include "otx2_cpt_common.h" + +/* + * On OcteonTX2 platform IPSec ucode can use both IE and SE engines therefore + * IE and SE engines can be attached to the same engine group. + */ +#define OTX2_CPT_MAX_ETYPES_PER_GRP 2 + +/* CPT ucode signature size */ +#define OTX2_CPT_UCODE_SIGN_LEN 256 + +/* Microcode version string length */ +#define OTX2_CPT_UCODE_VER_STR_SZ 44 + +/* Maximum number of supported engines/cores on OcteonTX2 platform */ +#define OTX2_CPT_MAX_ENGINES 128 + +#define OTX2_CPT_ENGS_BITMASK_LEN BITS_TO_LONGS(OTX2_CPT_MAX_ENGINES) + +/* Microcode types */ +enum otx2_cpt_ucode_type { + OTX2_CPT_AE_UC_TYPE = 1, /* AE-MAIN */ + OTX2_CPT_SE_UC_TYPE1 = 20,/* SE-MAIN - combination of 21 and 22 */ + OTX2_CPT_SE_UC_TYPE2 = 21,/* Fast Path IPSec + AirCrypto */ + OTX2_CPT_SE_UC_TYPE3 = 22,/* + * Hash + HMAC + FlexiCrypto + RNG + + * Full Feature IPSec + AirCrypto + Kasumi + */ + OTX2_CPT_IE_UC_TYPE1 = 30, /* IE-MAIN - combination of 31 and 32 */ + OTX2_CPT_IE_UC_TYPE2 = 31, /* Fast Path IPSec */ + OTX2_CPT_IE_UC_TYPE3 = 32, /* + * Hash + HMAC + FlexiCrypto + RNG + + * Full Future IPSec + */ +}; + +struct otx2_cpt_bitmap { + unsigned long bits[OTX2_CPT_ENGS_BITMASK_LEN]; + int size; +}; + +struct otx2_cpt_engines { + int type; + int count; +}; + +/* Microcode version number */ +struct otx2_cpt_ucode_ver_num { + u8 nn; + u8 xx; + u8 yy; + u8 zz; +}; + +struct otx2_cpt_ucode_hdr { + struct otx2_cpt_ucode_ver_num ver_num; + u8 ver_str[OTX2_CPT_UCODE_VER_STR_SZ]; + __be32 code_length; + u32 padding[3]; +}; + +struct otx2_cpt_ucode { + u8 ver_str[OTX2_CPT_UCODE_VER_STR_SZ];/* + * ucode version in readable + * format + */ + struct otx2_cpt_ucode_ver_num ver_num;/* ucode version number */ + char filename[OTX2_CPT_NAME_LENGTH];/* ucode filename */ + dma_addr_t dma; /* phys address of ucode image */ + void *va; /* virt address of ucode image */ + u32 size; /* ucode image size */ + int type; /* ucode image type SE, IE, AE or SE+IE */ +}; + +struct otx2_cpt_uc_info_t { + struct list_head list; + struct otx2_cpt_ucode ucode;/* microcode information */ + const struct firmware *fw; +}; + +/* Maximum and current number of engines available for all engine groups */ +struct otx2_cpt_engs_available { + int max_se_cnt; + int max_ie_cnt; + int max_ae_cnt; + int se_cnt; + int ie_cnt; + int ae_cnt; +}; + +/* Engines reserved to an engine group */ +struct otx2_cpt_engs_rsvd { + int type; /* engine type */ + int count; /* number of engines attached */ + int offset; /* constant offset of engine type in the bitmap */ + unsigned long *bmap; /* attached engines bitmap */ + struct otx2_cpt_ucode *ucode; /* ucode used by these engines */ +}; + +struct otx2_cpt_mirror_info { + int is_ena; /* + * is mirroring enabled, it is set only for engine + * group which mirrors another engine group + */ + int idx; /* + * index of engine group which is mirrored by this + * group, set only for engine group which mirrors + * another group + */ + int ref_count; /* + * number of times this engine group is mirrored by + * other groups, this is set only for engine group + * which is mirrored by other group(s) + */ +}; + +struct otx2_cpt_eng_grp_info { + struct otx2_cpt_eng_grps *g; /* pointer to engine_groups structure */ + /* engines attached */ + struct otx2_cpt_engs_rsvd engs[OTX2_CPT_MAX_ETYPES_PER_GRP]; + /* ucodes information */ + struct otx2_cpt_ucode ucode[OTX2_CPT_MAX_ETYPES_PER_GRP]; + /* engine group mirroring information */ + struct otx2_cpt_mirror_info mirror; + int idx; /* engine group index */ + bool is_enabled; /* + * is engine group enabled, engine group is enabled + * when it has engines attached and ucode loaded + */ +}; + +struct otx2_cpt_eng_grps { + struct otx2_cpt_eng_grp_info grp[OTX2_CPT_MAX_ENGINE_GROUPS]; + struct otx2_cpt_engs_available avail; + void *obj; /* device specific data */ + int engs_num; /* total number of engines supported */ + u8 eng_ref_cnt[OTX2_CPT_MAX_ENGINES];/* engines reference count */ + bool is_grps_created; /* Is the engine groups are already created */ +}; +struct otx2_cptpf_dev; +int otx2_cpt_init_eng_grps(struct pci_dev *pdev, + struct otx2_cpt_eng_grps *eng_grps); +void otx2_cpt_cleanup_eng_grps(struct pci_dev *pdev, + struct otx2_cpt_eng_grps *eng_grps); +int otx2_cpt_create_eng_grps(struct pci_dev *pdev, + struct otx2_cpt_eng_grps *eng_grps); +int otx2_cpt_disable_all_cores(struct otx2_cptpf_dev *cptpf); +int otx2_cpt_get_eng_grp(struct otx2_cpt_eng_grps *eng_grps, int eng_type); + +#endif /* __OTX2_CPTPF_UCODE_H */ From patchwork Wed Jan 6 10:42:19 2021 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Srujana Challa X-Patchwork-Id: 357656 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=-18.8 required=3.0 tests=BAYES_00,DKIM_SIGNED, DKIM_VALID, DKIM_VALID_AU, HEADER_FROM_DIFFERENT_DOMAINS, INCLUDES_CR_TRAILER, INCLUDES_PATCH, MAILING_LIST_MULTI, SPF_HELO_NONE, 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 AAA5AC433E9 for ; Wed, 6 Jan 2021 10:44:21 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id 662C623118 for ; Wed, 6 Jan 2021 10:44:21 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1726294AbhAFKoG (ORCPT ); Wed, 6 Jan 2021 05:44:06 -0500 Received: from mx0a-0016f401.pphosted.com ([67.231.148.174]:53994 "EHLO mx0b-0016f401.pphosted.com" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1726580AbhAFKoE (ORCPT ); Wed, 6 Jan 2021 05:44:04 -0500 Received: from pps.filterd (m0045849.ppops.net [127.0.0.1]) by mx0a-0016f401.pphosted.com (8.16.0.43/8.16.0.43) with SMTP id 106AZ8sP027983; Wed, 6 Jan 2021 02:43:20 -0800 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=marvell.com; h=from : to : cc : subject : date : message-id : in-reply-to : references : mime-version : content-transfer-encoding : content-type; s=pfpt0220; bh=c1ZaEb5KAOfQaqBX30rkw7p3FNdECXFKPWR5siRwI6Q=; b=JdUPDNRzGWztiCgkBxN3BSFbVBwcbHpF56bo3tru2iLsHmCI40ZS2pNVAaRE8f6Z+4bx 2oZhWWW2rpDNuiFEqf7+FVgZFznKykexunZ2nZbiPrRtCXUR+byYQYiOgrs7xgaZs8Rq Ty02GOaSg+tcR/T/bHz+3d0Zhk5X92LZDOm6NbeFvvrX6HGSyGHBc2Mhxr9i5SABIccG SRBvoF551ZmH2o9mt9XneZ57fvCF3v6KMQiVWHJ8rvGj+BtPMFt91wEz0/976OkWRoTD DhOpT68ADm5pSH7P9Mh8AqvB3iVa7hQKmlYpTr0L91J+xP25zM0gAeanTalhUY1Nnzcs vA== Received: from dc5-exch02.marvell.com ([199.233.59.182]) by mx0a-0016f401.pphosted.com with ESMTP id 35tq2uhc5t-2 (version=TLSv1.2 cipher=ECDHE-RSA-AES256-SHA384 bits=256 verify=NOT); Wed, 06 Jan 2021 02:43:20 -0800 Received: from DC5-EXCH01.marvell.com (10.69.176.38) by DC5-EXCH02.marvell.com (10.69.176.39) with Microsoft SMTP Server (TLS) id 15.0.1497.2; Wed, 6 Jan 2021 02:43:19 -0800 Received: from maili.marvell.com (10.69.176.80) by DC5-EXCH01.marvell.com (10.69.176.38) with Microsoft SMTP Server id 15.0.1497.2 via Frontend Transport; Wed, 6 Jan 2021 02:43:18 -0800 Received: from hyd1schalla-dt.caveonetworks.com.com (unknown [10.29.8.39]) by maili.marvell.com (Postfix) with ESMTP id 512053F7040; Wed, 6 Jan 2021 02:43:16 -0800 (PST) From: Srujana Challa To: CC: , , , , Srujana Challa , Suheil Chandran , "Lukasz Bartosik" Subject: [PATCH 5/9] crypto: octeontx2: add LF framework Date: Wed, 6 Jan 2021 16:12:19 +0530 Message-ID: <20210106104223.6182-6-schalla@marvell.com> X-Mailer: git-send-email 2.29.0 In-Reply-To: <20210106104223.6182-1-schalla@marvell.com> References: <20210106104223.6182-1-schalla@marvell.com> MIME-Version: 1.0 X-Proofpoint-Virus-Version: vendor=fsecure engine=2.50.10434:6.0.343, 18.0.737 definitions=2021-01-06_05:2021-01-06,2021-01-06 signatures=0 Precedence: bulk List-ID: X-Mailing-List: linux-crypto@vger.kernel.org CPT RVU Local Functions(LFs) needs to be attached to the PF/VF to submit the instructions to CPT. This patch adds the interface to initialize and attach the LFs. It also adds interface to register the LF's interrupts. Signed-off-by: Suheil Chandran Signed-off-by: Lukasz Bartosik Signed-off-by: Srujana Challa --- drivers/crypto/marvell/octeontx2/Makefile | 2 +- .../marvell/octeontx2/otx2_cpt_common.h | 4 + .../marvell/octeontx2/otx2_cpt_mbox_common.c | 56 +++ drivers/crypto/marvell/octeontx2/otx2_cptlf.c | 429 ++++++++++++++++++ drivers/crypto/marvell/octeontx2/otx2_cptlf.h | 283 ++++++++++++ drivers/crypto/marvell/octeontx2/otx2_cptpf.h | 2 + .../marvell/octeontx2/otx2_cptpf_mbox.c | 8 + 7 files changed, 783 insertions(+), 1 deletion(-) create mode 100644 drivers/crypto/marvell/octeontx2/otx2_cptlf.c create mode 100644 drivers/crypto/marvell/octeontx2/otx2_cptlf.h diff --git a/drivers/crypto/marvell/octeontx2/Makefile b/drivers/crypto/marvell/octeontx2/Makefile index 3c4155446296..e47a55961bb8 100644 --- a/drivers/crypto/marvell/octeontx2/Makefile +++ b/drivers/crypto/marvell/octeontx2/Makefile @@ -2,6 +2,6 @@ obj-$(CONFIG_CRYPTO_DEV_OCTEONTX2_CPT) += octeontx2-cpt.o octeontx2-cpt-objs := otx2_cptpf_main.o otx2_cptpf_mbox.o \ - otx2_cpt_mbox_common.o otx2_cptpf_ucode.o + otx2_cpt_mbox_common.o otx2_cptpf_ucode.o otx2_cptlf.o ccflags-y += -I$(srctree)/drivers/net/ethernet/marvell/octeontx2/af diff --git a/drivers/crypto/marvell/octeontx2/otx2_cpt_common.h b/drivers/crypto/marvell/octeontx2/otx2_cpt_common.h index ae16dc102459..d5576f5d3b90 100644 --- a/drivers/crypto/marvell/octeontx2/otx2_cpt_common.h +++ b/drivers/crypto/marvell/octeontx2/otx2_cpt_common.h @@ -76,4 +76,8 @@ int otx2_cpt_read_af_reg(struct otx2_mbox *mbox, struct pci_dev *pdev, u64 reg, u64 *val); int otx2_cpt_write_af_reg(struct otx2_mbox *mbox, struct pci_dev *pdev, u64 reg, u64 val); +struct otx2_cptlfs_info; +int otx2_cpt_attach_rscrs_msg(struct otx2_cptlfs_info *lfs); +int otx2_cpt_detach_rsrcs_msg(struct otx2_cptlfs_info *lfs); + #endif /* __OTX2_CPT_COMMON_H */ diff --git a/drivers/crypto/marvell/octeontx2/otx2_cpt_mbox_common.c b/drivers/crypto/marvell/octeontx2/otx2_cpt_mbox_common.c index ef1291c4881b..0933031ac827 100644 --- a/drivers/crypto/marvell/octeontx2/otx2_cpt_mbox_common.c +++ b/drivers/crypto/marvell/octeontx2/otx2_cpt_mbox_common.c @@ -2,6 +2,7 @@ /* Copyright (C) 2020 Marvell. */ #include "otx2_cpt_common.h" +#include "otx2_cptlf.h" int otx2_cpt_send_mbox_msg(struct otx2_mbox *mbox, struct pci_dev *pdev) { @@ -112,3 +113,58 @@ int otx2_cpt_write_af_reg(struct otx2_mbox *mbox, struct pci_dev *pdev, return otx2_cpt_send_mbox_msg(mbox, pdev); } + +int otx2_cpt_attach_rscrs_msg(struct otx2_cptlfs_info *lfs) +{ + struct otx2_mbox *mbox = lfs->mbox; + struct rsrc_attach *req; + int ret; + + req = (struct rsrc_attach *) + otx2_mbox_alloc_msg_rsp(mbox, 0, sizeof(*req), + sizeof(struct msg_rsp)); + if (req == NULL) { + dev_err(&lfs->pdev->dev, "RVU MBOX failed to get message.\n"); + return -EFAULT; + } + + req->hdr.id = MBOX_MSG_ATTACH_RESOURCES; + req->hdr.sig = OTX2_MBOX_REQ_SIG; + req->hdr.pcifunc = 0; + req->cptlfs = lfs->lfs_num; + ret = otx2_cpt_send_mbox_msg(mbox, lfs->pdev); + if (ret) + return ret; + + if (!lfs->are_lfs_attached) + ret = -EINVAL; + + return ret; +} + +int otx2_cpt_detach_rsrcs_msg(struct otx2_cptlfs_info *lfs) +{ + struct otx2_mbox *mbox = lfs->mbox; + struct rsrc_detach *req; + int ret; + + req = (struct rsrc_detach *) + otx2_mbox_alloc_msg_rsp(mbox, 0, sizeof(*req), + sizeof(struct msg_rsp)); + if (req == NULL) { + dev_err(&lfs->pdev->dev, "RVU MBOX failed to get message.\n"); + return -EFAULT; + } + + req->hdr.id = MBOX_MSG_DETACH_RESOURCES; + req->hdr.sig = OTX2_MBOX_REQ_SIG; + req->hdr.pcifunc = 0; + ret = otx2_cpt_send_mbox_msg(mbox, lfs->pdev); + if (ret) + return ret; + + if (lfs->are_lfs_attached) + ret = -EINVAL; + + return ret; +} diff --git a/drivers/crypto/marvell/octeontx2/otx2_cptlf.c b/drivers/crypto/marvell/octeontx2/otx2_cptlf.c new file mode 100644 index 000000000000..e27ea8909368 --- /dev/null +++ b/drivers/crypto/marvell/octeontx2/otx2_cptlf.c @@ -0,0 +1,429 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (C) 2020 Marvell. */ + +#include "otx2_cpt_common.h" +#include "otx2_cptlf.h" +#include "rvu_reg.h" + +#define CPT_TIMER_HOLD 0x03F +#define CPT_COUNT_HOLD 32 + +static void cptlf_do_set_done_time_wait(struct otx2_cptlf_info *lf, + int time_wait) +{ + union otx2_cptx_lf_done_wait done_wait; + + done_wait.u = otx2_cpt_read64(lf->lfs->reg_base, BLKADDR_CPT0, lf->slot, + OTX2_CPT_LF_DONE_WAIT); + done_wait.s.time_wait = time_wait; + otx2_cpt_write64(lf->lfs->reg_base, BLKADDR_CPT0, lf->slot, + OTX2_CPT_LF_DONE_WAIT, done_wait.u); +} + +static void cptlf_do_set_done_num_wait(struct otx2_cptlf_info *lf, int num_wait) +{ + union otx2_cptx_lf_done_wait done_wait; + + done_wait.u = otx2_cpt_read64(lf->lfs->reg_base, BLKADDR_CPT0, lf->slot, + OTX2_CPT_LF_DONE_WAIT); + done_wait.s.num_wait = num_wait; + otx2_cpt_write64(lf->lfs->reg_base, BLKADDR_CPT0, lf->slot, + OTX2_CPT_LF_DONE_WAIT, done_wait.u); +} + +static void cptlf_set_done_time_wait(struct otx2_cptlfs_info *lfs, + int time_wait) +{ + int slot; + + for (slot = 0; slot < lfs->lfs_num; slot++) + cptlf_do_set_done_time_wait(&lfs->lf[slot], time_wait); +} + +static void cptlf_set_done_num_wait(struct otx2_cptlfs_info *lfs, int num_wait) +{ + int slot; + + for (slot = 0; slot < lfs->lfs_num; slot++) + cptlf_do_set_done_num_wait(&lfs->lf[slot], num_wait); +} + +static int cptlf_set_pri(struct otx2_cptlf_info *lf, int pri) +{ + struct otx2_cptlfs_info *lfs = lf->lfs; + union otx2_cptx_af_lf_ctrl lf_ctrl; + int ret; + + ret = otx2_cpt_read_af_reg(lfs->mbox, lfs->pdev, + CPT_AF_LFX_CTL(lf->slot), + &lf_ctrl.u); + if (ret) + return ret; + + lf_ctrl.s.pri = pri ? 1 : 0; + + ret = otx2_cpt_write_af_reg(lfs->mbox, lfs->pdev, + CPT_AF_LFX_CTL(lf->slot), + lf_ctrl.u); + return ret; +} + +static int cptlf_set_eng_grps_mask(struct otx2_cptlf_info *lf, + int eng_grps_mask) +{ + struct otx2_cptlfs_info *lfs = lf->lfs; + union otx2_cptx_af_lf_ctrl lf_ctrl; + int ret; + + ret = otx2_cpt_read_af_reg(lfs->mbox, lfs->pdev, + CPT_AF_LFX_CTL(lf->slot), + &lf_ctrl.u); + if (ret) + return ret; + + lf_ctrl.s.grp = eng_grps_mask; + + ret = otx2_cpt_write_af_reg(lfs->mbox, lfs->pdev, + CPT_AF_LFX_CTL(lf->slot), + lf_ctrl.u); + return ret; +} + +static int cptlf_set_grp_and_pri(struct otx2_cptlfs_info *lfs, + int eng_grp_mask, int pri) +{ + int slot, ret = 0; + + for (slot = 0; slot < lfs->lfs_num; slot++) { + ret = cptlf_set_pri(&lfs->lf[slot], pri); + if (ret) + return ret; + + ret = cptlf_set_eng_grps_mask(&lfs->lf[slot], eng_grp_mask); + if (ret) + return ret; + } + return ret; +} + +static void cptlf_hw_init(struct otx2_cptlfs_info *lfs) +{ + /* Disable instruction queues */ + otx2_cptlf_disable_iqueues(lfs); + + /* Set instruction queues base addresses */ + otx2_cptlf_set_iqueues_base_addr(lfs); + + /* Set instruction queues sizes */ + otx2_cptlf_set_iqueues_size(lfs); + + /* Set done interrupts time wait */ + cptlf_set_done_time_wait(lfs, CPT_TIMER_HOLD); + + /* Set done interrupts num wait */ + cptlf_set_done_num_wait(lfs, CPT_COUNT_HOLD); + + /* Enable instruction queues */ + otx2_cptlf_enable_iqueues(lfs); +} + +static void cptlf_hw_cleanup(struct otx2_cptlfs_info *lfs) +{ + /* Disable instruction queues */ + otx2_cptlf_disable_iqueues(lfs); +} + +static void cptlf_set_misc_intrs(struct otx2_cptlfs_info *lfs, u8 enable) +{ + union otx2_cptx_lf_misc_int_ena_w1s irq_misc = { .u = 0x0 }; + u64 reg = enable ? OTX2_CPT_LF_MISC_INT_ENA_W1S : + OTX2_CPT_LF_MISC_INT_ENA_W1C; + int slot; + + irq_misc.s.fault = 0x1; + irq_misc.s.hwerr = 0x1; + irq_misc.s.irde = 0x1; + irq_misc.s.nqerr = 0x1; + irq_misc.s.nwrp = 0x1; + + for (slot = 0; slot < lfs->lfs_num; slot++) + otx2_cpt_write64(lfs->reg_base, BLKADDR_CPT0, slot, reg, + irq_misc.u); +} + +static void cptlf_enable_intrs(struct otx2_cptlfs_info *lfs) +{ + int slot; + + /* Enable done interrupts */ + for (slot = 0; slot < lfs->lfs_num; slot++) + otx2_cpt_write64(lfs->reg_base, BLKADDR_CPT0, slot, + OTX2_CPT_LF_DONE_INT_ENA_W1S, 0x1); + /* Enable Misc interrupts */ + cptlf_set_misc_intrs(lfs, true); +} + +static void cptlf_disable_intrs(struct otx2_cptlfs_info *lfs) +{ + int slot; + + for (slot = 0; slot < lfs->lfs_num; slot++) + otx2_cpt_write64(lfs->reg_base, BLKADDR_CPT0, slot, + OTX2_CPT_LF_DONE_INT_ENA_W1C, 0x1); + cptlf_set_misc_intrs(lfs, false); +} + +static inline int cptlf_read_done_cnt(struct otx2_cptlf_info *lf) +{ + union otx2_cptx_lf_done irq_cnt; + + irq_cnt.u = otx2_cpt_read64(lf->lfs->reg_base, BLKADDR_CPT0, lf->slot, + OTX2_CPT_LF_DONE); + return irq_cnt.s.done; +} + +static irqreturn_t cptlf_misc_intr_handler(int __always_unused irq, void *arg) +{ + union otx2_cptx_lf_misc_int irq_misc, irq_misc_ack; + struct otx2_cptlf_info *lf = arg; + struct device *dev; + + dev = &lf->lfs->pdev->dev; + irq_misc.u = otx2_cpt_read64(lf->lfs->reg_base, BLKADDR_CPT0, lf->slot, + OTX2_CPT_LF_MISC_INT); + irq_misc_ack.u = 0x0; + + if (irq_misc.s.fault) { + dev_err(dev, "Memory error detected while executing CPT_INST_S, LF %d.\n", + lf->slot); + irq_misc_ack.s.fault = 0x1; + + } else if (irq_misc.s.hwerr) { + dev_err(dev, "HW error from an engine executing CPT_INST_S, LF %d.", + lf->slot); + irq_misc_ack.s.hwerr = 0x1; + + } else if (irq_misc.s.nwrp) { + dev_err(dev, "SMMU fault while writing CPT_RES_S to CPT_INST_S[RES_ADDR], LF %d.\n", + lf->slot); + irq_misc_ack.s.nwrp = 0x1; + + } else if (irq_misc.s.irde) { + dev_err(dev, "Memory error when accessing instruction memory queue CPT_LF_Q_BASE[ADDR].\n"); + irq_misc_ack.s.irde = 0x1; + + } else if (irq_misc.s.nqerr) { + dev_err(dev, "Error enqueuing an instruction received at CPT_LF_NQ.\n"); + irq_misc_ack.s.nqerr = 0x1; + + } else { + dev_err(dev, "Unhandled interrupt in CPT LF %d\n", lf->slot); + return IRQ_NONE; + } + + /* Acknowledge interrupts */ + otx2_cpt_write64(lf->lfs->reg_base, BLKADDR_CPT0, lf->slot, + OTX2_CPT_LF_MISC_INT, irq_misc_ack.u); + + return IRQ_HANDLED; +} + +static irqreturn_t cptlf_done_intr_handler(int irq, void *arg) +{ + union otx2_cptx_lf_done_wait done_wait; + struct otx2_cptlf_info *lf = arg; + int irq_cnt; + + /* Read the number of completed requests */ + irq_cnt = cptlf_read_done_cnt(lf); + if (irq_cnt) { + done_wait.u = otx2_cpt_read64(lf->lfs->reg_base, BLKADDR_CPT0, + lf->slot, OTX2_CPT_LF_DONE_WAIT); + /* Acknowledge the number of completed requests */ + otx2_cpt_write64(lf->lfs->reg_base, BLKADDR_CPT0, lf->slot, + OTX2_CPT_LF_DONE_ACK, irq_cnt); + + otx2_cpt_write64(lf->lfs->reg_base, BLKADDR_CPT0, lf->slot, + OTX2_CPT_LF_DONE_WAIT, done_wait.u); + if (unlikely(!lf->wqe)) { + dev_err(&lf->lfs->pdev->dev, "No work for LF %d\n", + lf->slot); + return IRQ_NONE; + } + + /* Schedule processing of completed requests */ + tasklet_hi_schedule(&lf->wqe->work); + } + return IRQ_HANDLED; +} + +void otx2_cptlf_unregister_interrupts(struct otx2_cptlfs_info *lfs) +{ + int i, offs, vector; + + for (i = 0; i < lfs->lfs_num; i++) { + for (offs = 0; offs < OTX2_CPT_LF_MSIX_VECTORS; offs++) { + if (!lfs->lf[i].is_irq_reg[offs]) + continue; + + vector = pci_irq_vector(lfs->pdev, + lfs->lf[i].msix_offset + offs); + free_irq(vector, &lfs->lf[i]); + lfs->lf[i].is_irq_reg[offs] = false; + } + } + cptlf_disable_intrs(lfs); +} + +static int cptlf_do_register_interrrupts(struct otx2_cptlfs_info *lfs, + int lf_num, int irq_offset, + irq_handler_t handler) +{ + int ret, vector; + + vector = pci_irq_vector(lfs->pdev, lfs->lf[lf_num].msix_offset + + irq_offset); + ret = request_irq(vector, handler, 0, + lfs->lf[lf_num].irq_name[irq_offset], + &lfs->lf[lf_num]); + if (ret) + return ret; + + lfs->lf[lf_num].is_irq_reg[irq_offset] = true; + + return ret; +} + +int otx2_cptlf_register_interrupts(struct otx2_cptlfs_info *lfs) +{ + int irq_offs, ret, i; + + for (i = 0; i < lfs->lfs_num; i++) { + irq_offs = OTX2_CPT_LF_INT_VEC_E_MISC; + snprintf(lfs->lf[i].irq_name[irq_offs], 32, "CPTLF Misc%d", i); + ret = cptlf_do_register_interrrupts(lfs, i, irq_offs, + cptlf_misc_intr_handler); + if (ret) + goto free_irq; + + irq_offs = OTX2_CPT_LF_INT_VEC_E_DONE; + snprintf(lfs->lf[i].irq_name[irq_offs], 32, "OTX2_CPTLF Done%d", + i); + ret = cptlf_do_register_interrrupts(lfs, i, irq_offs, + cptlf_done_intr_handler); + if (ret) + goto free_irq; + } + cptlf_enable_intrs(lfs); + return 0; + +free_irq: + otx2_cptlf_unregister_interrupts(lfs); + return ret; +} + +void otx2_cptlf_free_irqs_affinity(struct otx2_cptlfs_info *lfs) +{ + int slot, offs; + + for (slot = 0; slot < lfs->lfs_num; slot++) { + for (offs = 0; offs < OTX2_CPT_LF_MSIX_VECTORS; offs++) + irq_set_affinity_hint(pci_irq_vector(lfs->pdev, + lfs->lf[slot].msix_offset + + offs), NULL); + if (lfs->lf[slot].affinity_mask) + free_cpumask_var(lfs->lf[slot].affinity_mask); + } +} + +int otx2_cptlf_set_irqs_affinity(struct otx2_cptlfs_info *lfs) +{ + struct otx2_cptlf_info *lf = lfs->lf; + int slot, offs, ret; + + for (slot = 0; slot < lfs->lfs_num; slot++) { + if (!zalloc_cpumask_var(&lf[slot].affinity_mask, GFP_KERNEL)) { + dev_err(&lfs->pdev->dev, + "cpumask allocation failed for LF %d", slot); + ret = -ENOMEM; + goto free_affinity_mask; + } + + cpumask_set_cpu(cpumask_local_spread(slot, + dev_to_node(&lfs->pdev->dev)), + lf[slot].affinity_mask); + + for (offs = 0; offs < OTX2_CPT_LF_MSIX_VECTORS; offs++) { + ret = irq_set_affinity_hint(pci_irq_vector(lfs->pdev, + lf[slot].msix_offset + offs), + lf[slot].affinity_mask); + if (ret) + goto free_affinity_mask; + } + } + return 0; + +free_affinity_mask: + otx2_cptlf_free_irqs_affinity(lfs); + return ret; +} + +int otx2_cptlf_init(struct otx2_cptlfs_info *lfs, u8 eng_grp_mask, int pri, + int lfs_num) +{ + int slot, ret; + + if (!lfs->pdev || !lfs->reg_base) + return -EINVAL; + + lfs->lfs_num = lfs_num; + for (slot = 0; slot < lfs->lfs_num; slot++) { + lfs->lf[slot].lfs = lfs; + lfs->lf[slot].slot = slot; + lfs->lf[slot].lmtline = lfs->reg_base + + OTX2_CPT_RVU_FUNC_ADDR_S(BLKADDR_LMT, slot, + OTX2_CPT_LMT_LF_LMTLINEX(0)); + lfs->lf[slot].ioreg = lfs->reg_base + + OTX2_CPT_RVU_FUNC_ADDR_S(BLKADDR_CPT0, slot, + OTX2_CPT_LF_NQX(0)); + } + /* Send request to attach LFs */ + ret = otx2_cpt_attach_rscrs_msg(lfs); + if (ret) + goto clear_lfs_num; + + ret = otx2_cpt_alloc_instruction_queues(lfs); + if (ret) { + dev_err(&lfs->pdev->dev, + "Allocating instruction queues failed\n"); + goto detach_rsrcs; + } + cptlf_hw_init(lfs); + /* + * Allow each LF to execute requests destined to any of 8 engine + * groups and set queue priority of each LF to high + */ + ret = cptlf_set_grp_and_pri(lfs, eng_grp_mask, pri); + if (ret) + goto free_iq; + + return 0; + +free_iq: + otx2_cpt_free_instruction_queues(lfs); + cptlf_hw_cleanup(lfs); +detach_rsrcs: + otx2_cpt_detach_rsrcs_msg(lfs); +clear_lfs_num: + lfs->lfs_num = 0; + return ret; +} + +void otx2_cptlf_shutdown(struct otx2_cptlfs_info *lfs) +{ + lfs->lfs_num = 0; + /* Cleanup LFs hardware side */ + cptlf_hw_cleanup(lfs); + /* Send request to detach LFs */ + otx2_cpt_detach_rsrcs_msg(lfs); +} diff --git a/drivers/crypto/marvell/octeontx2/otx2_cptlf.h b/drivers/crypto/marvell/octeontx2/otx2_cptlf.h new file mode 100644 index 000000000000..37ae0d2dcf55 --- /dev/null +++ b/drivers/crypto/marvell/octeontx2/otx2_cptlf.h @@ -0,0 +1,283 @@ +/* SPDX-License-Identifier: GPL-2.0-only + * Copyright (C) 2020 Marvell. + */ +#ifndef __OTX2_CPTLF_H +#define __OTX2_CPTLF_H + +#include +#include +#include "otx2_cpt_common.h" + +/* + * CPT instruction and pending queues user requested length in CPT_INST_S msgs + */ +#define OTX2_CPT_USER_REQUESTED_QLEN_MSGS 8200 + +/* + * CPT instruction queue size passed to HW is in units of 40*CPT_INST_S + * messages. + */ +#define OTX2_CPT_SIZE_DIV40 (OTX2_CPT_USER_REQUESTED_QLEN_MSGS/40) + +/* + * CPT instruction and pending queues length in CPT_INST_S messages + */ +#define OTX2_CPT_INST_QLEN_MSGS ((OTX2_CPT_SIZE_DIV40 - 1) * 40) + +/* CPT instruction queue length in bytes */ +#define OTX2_CPT_INST_QLEN_BYTES (OTX2_CPT_SIZE_DIV40 * 40 * \ + OTX2_CPT_INST_SIZE) + +/* CPT instruction group queue length in bytes */ +#define OTX2_CPT_INST_GRP_QLEN_BYTES (OTX2_CPT_SIZE_DIV40 * 16) + +/* CPT FC length in bytes */ +#define OTX2_CPT_Q_FC_LEN 128 + +/* CPT instruction queue alignment */ +#define OTX2_CPT_INST_Q_ALIGNMENT 128 + +/* Mask which selects all engine groups */ +#define OTX2_CPT_ALL_ENG_GRPS_MASK 0xFF + +/* Maximum LFs supported in OcteonTX2 for CPT */ +#define OTX2_CPT_MAX_LFS_NUM 64 + +/* Queue priority */ +#define OTX2_CPT_QUEUE_HI_PRIO 0x1 +#define OTX2_CPT_QUEUE_LOW_PRIO 0x0 + +enum otx2_cptlf_state { + OTX2_CPTLF_IN_RESET, + OTX2_CPTLF_STARTED, +}; + +struct otx2_cpt_inst_queue { + u8 *vaddr; + u8 *real_vaddr; + dma_addr_t dma_addr; + dma_addr_t real_dma_addr; + u32 size; +}; + +struct otx2_cptlfs_info; +struct otx2_cptlf_wqe { + struct tasklet_struct work; + struct otx2_cptlfs_info *lfs; + u8 lf_num; +}; + +struct otx2_cptlf_info { + struct otx2_cptlfs_info *lfs; /* Ptr to cptlfs_info struct */ + void __iomem *lmtline; /* Address of LMTLINE */ + void __iomem *ioreg; /* LMTLINE send register */ + int msix_offset; /* MSI-X interrupts offset */ + cpumask_var_t affinity_mask; /* IRQs affinity mask */ + u8 irq_name[OTX2_CPT_LF_MSIX_VECTORS][32];/* Interrupts name */ + u8 is_irq_reg[OTX2_CPT_LF_MSIX_VECTORS]; /* Is interrupt registered */ + u8 slot; /* Slot number of this LF */ + + struct otx2_cpt_inst_queue iqueue;/* Instruction queue */ + struct otx2_cptlf_wqe *wqe; /* Tasklet work info */ +}; + +struct otx2_cptlfs_info { + /* Registers start address of VF/PF LFs are attached to */ + void __iomem *reg_base; + struct pci_dev *pdev; /* Device LFs are attached to */ + struct otx2_cptlf_info lf[OTX2_CPT_MAX_LFS_NUM]; + struct otx2_mbox *mbox; + u8 are_lfs_attached; /* Whether CPT LFs are attached */ + u8 lfs_num; /* Number of CPT LFs */ + atomic_t state; /* LF's state. started/reset */ +}; + +static inline void otx2_cpt_free_instruction_queues( + struct otx2_cptlfs_info *lfs) +{ + struct otx2_cpt_inst_queue *iq; + int i; + + for (i = 0; i < lfs->lfs_num; i++) { + iq = &lfs->lf[i].iqueue; + if (iq->real_vaddr) + dma_free_coherent(&lfs->pdev->dev, + iq->size, + iq->real_vaddr, + iq->real_dma_addr); + iq->real_vaddr = NULL; + iq->vaddr = NULL; + } +} + +static inline int otx2_cpt_alloc_instruction_queues( + struct otx2_cptlfs_info *lfs) +{ + struct otx2_cpt_inst_queue *iq; + int ret = 0, i; + + if (!lfs->lfs_num) + return -EINVAL; + + for (i = 0; i < lfs->lfs_num; i++) { + iq = &lfs->lf[i].iqueue; + iq->size = OTX2_CPT_INST_QLEN_BYTES + + OTX2_CPT_Q_FC_LEN + + OTX2_CPT_INST_GRP_QLEN_BYTES + + OTX2_CPT_INST_Q_ALIGNMENT; + iq->real_vaddr = dma_alloc_coherent(&lfs->pdev->dev, iq->size, + &iq->real_dma_addr, GFP_KERNEL); + if (!iq->real_vaddr) { + ret = -ENOMEM; + goto error; + } + iq->vaddr = iq->real_vaddr + OTX2_CPT_INST_GRP_QLEN_BYTES; + iq->dma_addr = iq->real_dma_addr + OTX2_CPT_INST_GRP_QLEN_BYTES; + + /* Align pointers */ + iq->vaddr = PTR_ALIGN(iq->vaddr, OTX2_CPT_INST_Q_ALIGNMENT); + iq->dma_addr = PTR_ALIGN(iq->dma_addr, + OTX2_CPT_INST_Q_ALIGNMENT); + } + return 0; + +error: + otx2_cpt_free_instruction_queues(lfs); + return ret; +} + +static inline void otx2_cptlf_set_iqueues_base_addr( + struct otx2_cptlfs_info *lfs) +{ + union otx2_cptx_lf_q_base lf_q_base; + int slot; + + for (slot = 0; slot < lfs->lfs_num; slot++) { + lf_q_base.u = lfs->lf[slot].iqueue.dma_addr; + otx2_cpt_write64(lfs->reg_base, BLKADDR_CPT0, slot, + OTX2_CPT_LF_Q_BASE, lf_q_base.u); + } +} + +static inline void otx2_cptlf_do_set_iqueue_size(struct otx2_cptlf_info *lf) +{ + union otx2_cptx_lf_q_size lf_q_size = { .u = 0x0 }; + + lf_q_size.s.size_div40 = OTX2_CPT_SIZE_DIV40; + otx2_cpt_write64(lf->lfs->reg_base, BLKADDR_CPT0, lf->slot, + OTX2_CPT_LF_Q_SIZE, lf_q_size.u); +} + +static inline void otx2_cptlf_set_iqueues_size(struct otx2_cptlfs_info *lfs) +{ + int slot; + + for (slot = 0; slot < lfs->lfs_num; slot++) + otx2_cptlf_do_set_iqueue_size(&lfs->lf[slot]); +} + +static inline void otx2_cptlf_do_disable_iqueue(struct otx2_cptlf_info *lf) +{ + union otx2_cptx_lf_ctl lf_ctl = { .u = 0x0 }; + union otx2_cptx_lf_inprog lf_inprog; + int timeout = 20; + + /* Disable instructions enqueuing */ + otx2_cpt_write64(lf->lfs->reg_base, BLKADDR_CPT0, lf->slot, + OTX2_CPT_LF_CTL, lf_ctl.u); + + /* Wait for instruction queue to become empty */ + do { + lf_inprog.u = otx2_cpt_read64(lf->lfs->reg_base, BLKADDR_CPT0, + lf->slot, OTX2_CPT_LF_INPROG); + if (!lf_inprog.s.inflight) + break; + + usleep_range(10000, 20000); + if (timeout-- < 0) { + dev_err(&lf->lfs->pdev->dev, + "Error LF %d is still busy.\n", lf->slot); + break; + } + + } while (1); + + /* + * Disable executions in the LF's queue, + * the queue should be empty at this point + */ + lf_inprog.s.eena = 0x0; + otx2_cpt_write64(lf->lfs->reg_base, BLKADDR_CPT0, lf->slot, + OTX2_CPT_LF_INPROG, lf_inprog.u); +} + +static inline void otx2_cptlf_disable_iqueues(struct otx2_cptlfs_info *lfs) +{ + int slot; + + for (slot = 0; slot < lfs->lfs_num; slot++) + otx2_cptlf_do_disable_iqueue(&lfs->lf[slot]); +} + +static inline void otx2_cptlf_set_iqueue_enq(struct otx2_cptlf_info *lf, + bool enable) +{ + union otx2_cptx_lf_ctl lf_ctl; + + lf_ctl.u = otx2_cpt_read64(lf->lfs->reg_base, BLKADDR_CPT0, lf->slot, + OTX2_CPT_LF_CTL); + + /* Set iqueue's enqueuing */ + lf_ctl.s.ena = enable ? 0x1 : 0x0; + otx2_cpt_write64(lf->lfs->reg_base, BLKADDR_CPT0, lf->slot, + OTX2_CPT_LF_CTL, lf_ctl.u); +} + +static inline void otx2_cptlf_enable_iqueue_enq(struct otx2_cptlf_info *lf) +{ + otx2_cptlf_set_iqueue_enq(lf, true); +} + +static inline void otx2_cptlf_set_iqueue_exec(struct otx2_cptlf_info *lf, + bool enable) +{ + union otx2_cptx_lf_inprog lf_inprog; + + lf_inprog.u = otx2_cpt_read64(lf->lfs->reg_base, BLKADDR_CPT0, lf->slot, + OTX2_CPT_LF_INPROG); + + /* Set iqueue's execution */ + lf_inprog.s.eena = enable ? 0x1 : 0x0; + otx2_cpt_write64(lf->lfs->reg_base, BLKADDR_CPT0, lf->slot, + OTX2_CPT_LF_INPROG, lf_inprog.u); +} + +static inline void otx2_cptlf_enable_iqueue_exec(struct otx2_cptlf_info *lf) +{ + otx2_cptlf_set_iqueue_exec(lf, true); +} + +static inline void otx2_cptlf_disable_iqueue_exec(struct otx2_cptlf_info *lf) +{ + otx2_cptlf_set_iqueue_exec(lf, false); +} + +static inline void otx2_cptlf_enable_iqueues(struct otx2_cptlfs_info *lfs) +{ + int slot; + + for (slot = 0; slot < lfs->lfs_num; slot++) { + otx2_cptlf_enable_iqueue_exec(&lfs->lf[slot]); + otx2_cptlf_enable_iqueue_enq(&lfs->lf[slot]); + } +} + +int otx2_cptlf_init(struct otx2_cptlfs_info *lfs, u8 eng_grp_msk, int pri, + int lfs_num); +void otx2_cptlf_shutdown(struct otx2_cptlfs_info *lfs); +int otx2_cptlf_register_interrupts(struct otx2_cptlfs_info *lfs); +void otx2_cptlf_unregister_interrupts(struct otx2_cptlfs_info *lfs); +void otx2_cptlf_free_irqs_affinity(struct otx2_cptlfs_info *lfs); +int otx2_cptlf_set_irqs_affinity(struct otx2_cptlfs_info *lfs); + +#endif /* __OTX2_CPTLF_H */ diff --git a/drivers/crypto/marvell/octeontx2/otx2_cptpf.h b/drivers/crypto/marvell/octeontx2/otx2_cptpf.h index ac9795978286..f441c2dbe7bf 100644 --- a/drivers/crypto/marvell/octeontx2/otx2_cptpf.h +++ b/drivers/crypto/marvell/octeontx2/otx2_cptpf.h @@ -7,6 +7,7 @@ #include "otx2_cpt_common.h" #include "otx2_cptpf_ucode.h" +#include "otx2_cptlf.h" struct otx2_cptpf_dev; struct otx2_cptvf_info { @@ -29,6 +30,7 @@ struct otx2_cptpf_dev { struct pci_dev *pdev; /* PCI device handle */ struct otx2_cptvf_info vf[OTX2_CPT_MAX_VFS_NUM]; struct otx2_cpt_eng_grps eng_grps;/* Engine groups information */ + struct otx2_cptlfs_info lfs; /* CPT LFs attached to this PF */ /* AF <=> PF mbox */ struct otx2_mbox afpf_mbox; diff --git a/drivers/crypto/marvell/octeontx2/otx2_cptpf_mbox.c b/drivers/crypto/marvell/octeontx2/otx2_cptpf_mbox.c index 08e18fe6817b..2270967eaf65 100644 --- a/drivers/crypto/marvell/octeontx2/otx2_cptpf_mbox.c +++ b/drivers/crypto/marvell/octeontx2/otx2_cptpf_mbox.c @@ -207,6 +207,14 @@ static void process_afpf_mbox_msg(struct otx2_cptpf_dev *cptpf, if (!rsp_rd_wr->is_write) *rsp_rd_wr->ret_val = rsp_rd_wr->val; break; + case MBOX_MSG_ATTACH_RESOURCES: + if (!msg->rc) + cptpf->lfs.are_lfs_attached = 1; + break; + case MBOX_MSG_DETACH_RESOURCES: + if (!msg->rc) + cptpf->lfs.are_lfs_attached = 0; + break; default: dev_err(dev, From patchwork Wed Jan 6 10:42:22 2021 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Srujana Challa X-Patchwork-Id: 357655 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=-18.8 required=3.0 tests=BAYES_00,DKIM_SIGNED, DKIM_VALID, DKIM_VALID_AU, HEADER_FROM_DIFFERENT_DOMAINS, INCLUDES_CR_TRAILER, INCLUDES_PATCH, MAILING_LIST_MULTI, SPF_HELO_NONE, 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 E892CC4332B for ; Wed, 6 Jan 2021 10:44:21 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id C2E7E23118 for ; Wed, 6 Jan 2021 10:44:21 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1726612AbhAFKoT (ORCPT ); Wed, 6 Jan 2021 05:44:19 -0500 Received: from mx0a-0016f401.pphosted.com ([67.231.148.174]:13710 "EHLO mx0b-0016f401.pphosted.com" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1726076AbhAFKoT (ORCPT ); Wed, 6 Jan 2021 05:44:19 -0500 Received: from pps.filterd (m0045849.ppops.net [127.0.0.1]) by mx0a-0016f401.pphosted.com (8.16.0.43/8.16.0.43) with SMTP id 106AaNPg029204; Wed, 6 Jan 2021 02:43:33 -0800 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=marvell.com; h=from : to : cc : subject : date : message-id : in-reply-to : references : mime-version : content-transfer-encoding : content-type; s=pfpt0220; bh=LxVmxeMemH94Q8Z0wrh6FnsvsfUrYDw5n9KGLPwRT9A=; b=a6TQbeqfXoFttRbwajVASjgBQnAUe7amX72EQ8J6zmIFXoV4jqbQ2V4ey2XT4UHdvnY7 vMch9EQN+b8siiXzEK5+qjHMRM80ZbzF5VY8PIwDvfUJrzmrImnNUr0QTT1ULHjxSPvK hCbvwlhsCi3AD1xv8l5AhvpzHhk70H6aWyVlfXrB0/B88n/WFq6Ak3CGNtyeOlTw5YEF MucYsS8kB9RPDl94TPzJfX23r6z9GVA6V+A7pQPC2ccLbS11/IQ6jnMz2ZR0alW515bB RxqtuS63Z4X7iFApSyLZQQFDkxs+3TsarW4KFnOjlA9iLkwBcSaY4mZDIgnvsW0tsWee Tw== Received: from dc5-exch02.marvell.com ([199.233.59.182]) by mx0a-0016f401.pphosted.com with ESMTP id 35tq2uhc62-1 (version=TLSv1.2 cipher=ECDHE-RSA-AES256-SHA384 bits=256 verify=NOT); Wed, 06 Jan 2021 02:43:33 -0800 Received: from SC-EXCH02.marvell.com (10.93.176.82) by DC5-EXCH02.marvell.com (10.69.176.39) with Microsoft SMTP Server (TLS) id 15.0.1497.2; Wed, 6 Jan 2021 02:43:32 -0800 Received: from DC5-EXCH02.marvell.com (10.69.176.39) by SC-EXCH02.marvell.com (10.93.176.82) with Microsoft SMTP Server (TLS) id 15.0.1497.2; Wed, 6 Jan 2021 02:43:31 -0800 Received: from maili.marvell.com (10.69.176.80) by DC5-EXCH02.marvell.com (10.69.176.39) with Microsoft SMTP Server id 15.0.1497.2 via Frontend Transport; Wed, 6 Jan 2021 02:43:31 -0800 Received: from hyd1schalla-dt.caveonetworks.com.com (unknown [10.29.8.39]) by maili.marvell.com (Postfix) with ESMTP id C20973F7041; Wed, 6 Jan 2021 02:43:28 -0800 (PST) From: Srujana Challa To: CC: , , , , Srujana Challa , Suheil Chandran , "Lukasz Bartosik" Subject: [PATCH 8/9] crypto: octeontx2: add support to process the crypto request Date: Wed, 6 Jan 2021 16:12:22 +0530 Message-ID: <20210106104223.6182-9-schalla@marvell.com> X-Mailer: git-send-email 2.29.0 In-Reply-To: <20210106104223.6182-1-schalla@marvell.com> References: <20210106104223.6182-1-schalla@marvell.com> MIME-Version: 1.0 X-Proofpoint-Virus-Version: vendor=fsecure engine=2.50.10434:6.0.343, 18.0.737 definitions=2021-01-06_05:2021-01-06,2021-01-06 signatures=0 Precedence: bulk List-ID: X-Mailing-List: linux-crypto@vger.kernel.org Attach LFs to CPT VF to process the crypto requests and register LF interrupts. Signed-off-by: Suheil Chandran Signed-off-by: Lukasz Bartosik Signed-off-by: Srujana Challa --- drivers/crypto/marvell/octeontx2/Makefile | 2 +- .../marvell/octeontx2/otx2_cpt_common.h | 17 + .../marvell/octeontx2/otx2_cpt_reqmgr.h | 145 +++++ drivers/crypto/marvell/octeontx2/otx2_cptlf.h | 8 + drivers/crypto/marvell/octeontx2/otx2_cptpf.h | 1 + .../marvell/octeontx2/otx2_cptpf_main.c | 47 ++ .../marvell/octeontx2/otx2_cptpf_mbox.c | 22 + drivers/crypto/marvell/octeontx2/otx2_cptvf.h | 1 + .../marvell/octeontx2/otx2_cptvf_main.c | 204 +++++++ .../marvell/octeontx2/otx2_cptvf_mbox.c | 54 ++ .../marvell/octeontx2/otx2_cptvf_reqmgr.c | 534 ++++++++++++++++++ 11 files changed, 1034 insertions(+), 1 deletion(-) create mode 100644 drivers/crypto/marvell/octeontx2/otx2_cptvf_reqmgr.c diff --git a/drivers/crypto/marvell/octeontx2/Makefile b/drivers/crypto/marvell/octeontx2/Makefile index ef6fb2ab3571..41c0a5832b3f 100644 --- a/drivers/crypto/marvell/octeontx2/Makefile +++ b/drivers/crypto/marvell/octeontx2/Makefile @@ -4,6 +4,6 @@ obj-$(CONFIG_CRYPTO_DEV_OCTEONTX2_CPT) += octeontx2-cpt.o octeontx2-cptvf.o octeontx2-cpt-objs := otx2_cptpf_main.o otx2_cptpf_mbox.o \ otx2_cpt_mbox_common.o otx2_cptpf_ucode.o otx2_cptlf.o octeontx2-cptvf-objs := otx2_cptvf_main.o otx2_cptvf_mbox.o otx2_cptlf.o \ - otx2_cpt_mbox_common.o + otx2_cpt_mbox_common.o otx2_cptvf_reqmgr.o ccflags-y += -I$(srctree)/drivers/net/ethernet/marvell/octeontx2/af diff --git a/drivers/crypto/marvell/octeontx2/otx2_cpt_common.h b/drivers/crypto/marvell/octeontx2/otx2_cpt_common.h index ca220178e518..3518fac29834 100644 --- a/drivers/crypto/marvell/octeontx2/otx2_cpt_common.h +++ b/drivers/crypto/marvell/octeontx2/otx2_cpt_common.h @@ -17,6 +17,9 @@ #define OTX2_CPT_MAX_VFS_NUM 128 #define OTX2_CPT_RVU_FUNC_ADDR_S(blk, slot, offs) \ (((blk) << 20) | ((slot) << 12) | (offs)) +#define OTX2_CPT_RVU_PFFUNC(pf, func) \ + ((((pf) & RVU_PFVF_PF_MASK) << RVU_PFVF_PF_SHIFT) | \ + (((func) & RVU_PFVF_FUNC_MASK) << RVU_PFVF_FUNC_SHIFT)) #define OTX2_CPT_INVALID_CRYPTO_ENG_GRP 0xFF #define OTX2_CPT_NAME_LENGTH 64 @@ -34,6 +37,7 @@ enum otx2_cpt_eng_type { /* Take mbox id from end of CPT mbox range in AF (range 0xA00 - 0xBFF) */ #define MBOX_MSG_GET_ENG_GRP_NUM 0xBFF #define MBOX_MSG_GET_CAPS 0xBFD +#define MBOX_MSG_GET_KVF_LIMITS 0xBFC /* * Message request and response to get engine group number @@ -51,6 +55,19 @@ struct otx2_cpt_egrp_num_rsp { u8 eng_grp_num; }; +/* + * Message request and response to get kernel crypto limits + * This messages are only used between CPT PF <-> CPT VF + */ +struct otx2_cpt_kvf_limits_msg { + struct mbox_msghdr hdr; +}; + +struct otx2_cpt_kvf_limits_rsp { + struct mbox_msghdr hdr; + u8 kvf_limits; +}; + /* CPT HW capabilities */ union otx2_cpt_eng_caps { u64 u; diff --git a/drivers/crypto/marvell/octeontx2/otx2_cpt_reqmgr.h b/drivers/crypto/marvell/octeontx2/otx2_cpt_reqmgr.h index 9184f91c68c1..597a998c6df6 100644 --- a/drivers/crypto/marvell/octeontx2/otx2_cpt_reqmgr.h +++ b/drivers/crypto/marvell/octeontx2/otx2_cpt_reqmgr.h @@ -10,6 +10,22 @@ /* Completion code size and initial value */ #define OTX2_CPT_COMPLETION_CODE_SIZE 8 #define OTX2_CPT_COMPLETION_CODE_INIT OTX2_CPT_COMP_E_NOTDONE +/* + * Maximum total number of SG buffers is 100, we divide it equally + * between input and output + */ +#define OTX2_CPT_MAX_SG_IN_CNT 50 +#define OTX2_CPT_MAX_SG_OUT_CNT 50 + +/* DMA mode direct or SG */ +#define OTX2_CPT_DMA_MODE_DIRECT 0 +#define OTX2_CPT_DMA_MODE_SG 1 + +/* Context source CPTR or DPTR */ +#define OTX2_CPT_FROM_CPTR 0 +#define OTX2_CPT_FROM_DPTR 1 + +#define OTX2_CPT_MAX_REQ_SIZE 65535 union otx2_cpt_opcode { u16 flags; @@ -19,6 +35,13 @@ union otx2_cpt_opcode { } s; }; +struct otx2_cptvf_request { + u32 param1; + u32 param2; + u16 dlen; + union otx2_cpt_opcode opcode; +}; + /* * CPT_INST_S software command definitions * Words EI (0-3) @@ -48,4 +71,126 @@ struct otx2_cpt_iq_command { union otx2_cpt_iq_cmd_word3 cptr; }; +struct otx2_cpt_pending_entry { + void *completion_addr; /* Completion address */ + void *info; + /* Kernel async request callback */ + void (*callback)(int status, void *arg1, void *arg2); + struct crypto_async_request *areq; /* Async request callback arg */ + u8 resume_sender; /* Notify sender to resume sending requests */ + u8 busy; /* Entry status (free/busy) */ +}; + +struct otx2_cpt_pending_queue { + struct otx2_cpt_pending_entry *head; /* Head of the queue */ + u32 front; /* Process work from here */ + u32 rear; /* Append new work here */ + u32 pending_count; /* Pending requests count */ + u32 qlen; /* Queue length */ + spinlock_t lock; /* Queue lock */ +}; + +struct otx2_cpt_buf_ptr { + u8 *vptr; + dma_addr_t dma_addr; + u16 size; +}; + +union otx2_cpt_ctrl_info { + u32 flags; + struct { +#if defined(__BIG_ENDIAN_BITFIELD) + u32 reserved_6_31:26; + u32 grp:3; /* Group bits */ + u32 dma_mode:2; /* DMA mode */ + u32 se_req:1; /* To SE core */ +#else + u32 se_req:1; /* To SE core */ + u32 dma_mode:2; /* DMA mode */ + u32 grp:3; /* Group bits */ + u32 reserved_6_31:26; +#endif + } s; +}; + +struct otx2_cpt_req_info { + /* Kernel async request callback */ + void (*callback)(int status, void *arg1, void *arg2); + struct crypto_async_request *areq; /* Async request callback arg */ + struct otx2_cptvf_request req;/* Request information (core specific) */ + union otx2_cpt_ctrl_info ctrl;/* User control information */ + struct otx2_cpt_buf_ptr in[OTX2_CPT_MAX_SG_IN_CNT]; + struct otx2_cpt_buf_ptr out[OTX2_CPT_MAX_SG_OUT_CNT]; + u8 *iv_out; /* IV to send back */ + u16 rlen; /* Output length */ + u8 in_cnt; /* Number of input buffers */ + u8 out_cnt; /* Number of output buffers */ + u8 req_type; /* Type of request */ + u8 is_enc; /* Is a request an encryption request */ + u8 is_trunc_hmac;/* Is truncated hmac used */ +}; + +struct otx2_cpt_inst_info { + struct otx2_cpt_pending_entry *pentry; + struct otx2_cpt_req_info *req; + struct pci_dev *pdev; + void *completion_addr; + u8 *out_buffer; + u8 *in_buffer; + dma_addr_t dptr_baddr; + dma_addr_t rptr_baddr; + dma_addr_t comp_baddr; + unsigned long time_in; + u32 dlen; + u32 dma_len; + u8 extra_time; +}; + +struct otx2_cpt_sglist_component { + __be16 len0; + __be16 len1; + __be16 len2; + __be16 len3; + __be64 ptr0; + __be64 ptr1; + __be64 ptr2; + __be64 ptr3; +}; + +static inline void otx2_cpt_info_destroy(struct pci_dev *pdev, + struct otx2_cpt_inst_info *info) +{ + struct otx2_cpt_req_info *req; + int i; + + if (info->dptr_baddr) + dma_unmap_single(&pdev->dev, info->dptr_baddr, + info->dma_len, DMA_BIDIRECTIONAL); + + if (info->req) { + req = info->req; + for (i = 0; i < req->out_cnt; i++) { + if (req->out[i].dma_addr) + dma_unmap_single(&pdev->dev, + req->out[i].dma_addr, + req->out[i].size, + DMA_BIDIRECTIONAL); + } + + for (i = 0; i < req->in_cnt; i++) { + if (req->in[i].dma_addr) + dma_unmap_single(&pdev->dev, + req->in[i].dma_addr, + req->in[i].size, + DMA_BIDIRECTIONAL); + } + } + kfree(info); +} + +struct otx2_cptlf_wqe; +int otx2_cpt_do_request(struct pci_dev *pdev, struct otx2_cpt_req_info *req, + int cpu_num); +void otx2_cpt_post_process(struct otx2_cptlf_wqe *wqe); + #endif /* __OTX2_CPT_REQMGR_H */ diff --git a/drivers/crypto/marvell/octeontx2/otx2_cptlf.h b/drivers/crypto/marvell/octeontx2/otx2_cptlf.h index efb4f395a54a..314e97354100 100644 --- a/drivers/crypto/marvell/octeontx2/otx2_cptlf.h +++ b/drivers/crypto/marvell/octeontx2/otx2_cptlf.h @@ -80,6 +80,7 @@ struct otx2_cptlf_info { u8 slot; /* Slot number of this LF */ struct otx2_cpt_inst_queue iqueue;/* Instruction queue */ + struct otx2_cpt_pending_queue pqueue; /* Pending queue */ struct otx2_cptlf_wqe *wqe; /* Tasklet work info */ }; @@ -91,6 +92,8 @@ struct otx2_cptlfs_info { struct otx2_mbox *mbox; u8 are_lfs_attached; /* Whether CPT LFs are attached */ u8 lfs_num; /* Number of CPT LFs */ + u8 kcrypto_eng_grp_num; /* Kernel crypto engine group number */ + u8 kvf_limits; /* Kernel crypto limits */ atomic_t state; /* LF's state. started/reset */ }; @@ -334,6 +337,11 @@ static inline void otx2_cpt_send_cmd(union otx2_cpt_inst_s *cptinst, } while (!ret); } +static inline bool otx2_cptlf_started(struct otx2_cptlfs_info *lfs) +{ + return atomic_read(&lfs->state) == OTX2_CPTLF_STARTED; +} + int otx2_cptlf_init(struct otx2_cptlfs_info *lfs, u8 eng_grp_msk, int pri, int lfs_num); void otx2_cptlf_shutdown(struct otx2_cptlfs_info *lfs); diff --git a/drivers/crypto/marvell/octeontx2/otx2_cptpf.h b/drivers/crypto/marvell/octeontx2/otx2_cptpf.h index ede230dc205f..8c899ad531a5 100644 --- a/drivers/crypto/marvell/octeontx2/otx2_cptpf.h +++ b/drivers/crypto/marvell/octeontx2/otx2_cptpf.h @@ -50,6 +50,7 @@ struct otx2_cptpf_dev { u8 pf_id; /* RVU PF number */ u8 max_vfs; /* Maximum number of VFs supported by CPT */ u8 enabled_vfs; /* Number of enabled VFs */ + u8 kvf_limits; /* Kernel crypto limits */ }; irqreturn_t otx2_cptpf_afpf_mbox_intr(int irq, void *arg); diff --git a/drivers/crypto/marvell/octeontx2/otx2_cptpf_main.c b/drivers/crypto/marvell/octeontx2/otx2_cptpf_main.c index 502bcf21ea89..5277e04badd9 100644 --- a/drivers/crypto/marvell/octeontx2/otx2_cptpf_main.c +++ b/drivers/crypto/marvell/octeontx2/otx2_cptpf_main.c @@ -392,6 +392,46 @@ static void cptpf_afpf_mbox_destroy(struct otx2_cptpf_dev *cptpf) otx2_mbox_destroy(&cptpf->afpf_mbox); } +static ssize_t kvf_limits_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct otx2_cptpf_dev *cptpf = dev_get_drvdata(dev); + + return sprintf(buf, "%d\n", cptpf->kvf_limits); +} + +static ssize_t kvf_limits_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct otx2_cptpf_dev *cptpf = dev_get_drvdata(dev); + int lfs_num; + + if (kstrtoint(buf, 0, &lfs_num)) { + dev_err(dev, "lfs count %d must be in range [1 - %d]\n", + lfs_num, num_online_cpus()); + return -EINVAL; + } + if (lfs_num < 1 || lfs_num > num_online_cpus()) { + dev_err(dev, "lfs count %d must be in range [1 - %d]\n", + lfs_num, num_online_cpus()); + return -EINVAL; + } + cptpf->kvf_limits = lfs_num; + + return count; +} + +static DEVICE_ATTR_RW(kvf_limits); +static struct attribute *cptpf_attrs[] = { + &dev_attr_kvf_limits.attr, + NULL +}; + +static const struct attribute_group cptpf_sysfs_group = { + .attrs = cptpf_attrs, +}; + static int cpt_is_pf_usable(struct otx2_cptpf_dev *cptpf) { u64 rev; @@ -616,8 +656,13 @@ static int otx2_cptpf_probe(struct pci_dev *pdev, if (err) goto unregister_intr; + err = sysfs_create_group(&dev->kobj, &cptpf_sysfs_group); + if (err) + goto cleanup_eng_grps; return 0; +cleanup_eng_grps: + otx2_cpt_cleanup_eng_grps(pdev, &cptpf->eng_grps); unregister_intr: cptpf_disable_afpf_mbox_intr(cptpf); destroy_afpf_mbox: @@ -635,6 +680,8 @@ static void otx2_cptpf_remove(struct pci_dev *pdev) return; cptpf_sriov_disable(pdev); + /* Delete sysfs entry created for kernel VF limits */ + sysfs_remove_group(&pdev->dev.kobj, &cptpf_sysfs_group); /* Cleanup engine groups */ otx2_cpt_cleanup_eng_grps(pdev, &cptpf->eng_grps); /* Disable AF-PF mailbox interrupt */ diff --git a/drivers/crypto/marvell/octeontx2/otx2_cptpf_mbox.c b/drivers/crypto/marvell/octeontx2/otx2_cptpf_mbox.c index 0834dc3b3e59..186f1c1190c1 100644 --- a/drivers/crypto/marvell/octeontx2/otx2_cptpf_mbox.c +++ b/drivers/crypto/marvell/octeontx2/otx2_cptpf_mbox.c @@ -86,6 +86,25 @@ static int handle_msg_get_eng_grp_num(struct otx2_cptpf_dev *cptpf, return 0; } +static int handle_msg_kvf_limits(struct otx2_cptpf_dev *cptpf, + struct otx2_cptvf_info *vf, + struct mbox_msghdr *req) +{ + struct otx2_cpt_kvf_limits_rsp *rsp; + + rsp = (struct otx2_cpt_kvf_limits_rsp *) + otx2_mbox_alloc_msg(&cptpf->vfpf_mbox, vf->vf_id, sizeof(*rsp)); + if (!rsp) + return -ENOMEM; + + rsp->hdr.id = MBOX_MSG_GET_KVF_LIMITS; + rsp->hdr.sig = OTX2_MBOX_RSP_SIG; + rsp->hdr.pcifunc = req->pcifunc; + rsp->kvf_limits = cptpf->kvf_limits; + + return 0; +} + static int cptpf_handle_vf_req(struct otx2_cptpf_dev *cptpf, struct otx2_cptvf_info *vf, struct mbox_msghdr *req, int size) @@ -103,6 +122,9 @@ static int cptpf_handle_vf_req(struct otx2_cptpf_dev *cptpf, case MBOX_MSG_GET_CAPS: err = handle_msg_get_caps(cptpf, vf, req); break; + case MBOX_MSG_GET_KVF_LIMITS: + err = handle_msg_kvf_limits(cptpf, vf, req); + break; default: err = forward_to_af(cptpf, vf, req, size); break; diff --git a/drivers/crypto/marvell/octeontx2/otx2_cptvf.h b/drivers/crypto/marvell/octeontx2/otx2_cptvf.h index 4b01eb9d9f70..4f0a169fddbd 100644 --- a/drivers/crypto/marvell/octeontx2/otx2_cptvf.h +++ b/drivers/crypto/marvell/octeontx2/otx2_cptvf.h @@ -24,5 +24,6 @@ struct otx2_cptvf_dev { irqreturn_t otx2_cptvf_pfvf_mbox_intr(int irq, void *arg); void otx2_cptvf_pfvf_mbox_handler(struct work_struct *work); int otx2_cptvf_send_eng_grp_num_msg(struct otx2_cptvf_dev *cptvf, int eng_type); +int otx2_cptvf_send_kvf_limits_msg(struct otx2_cptvf_dev *cptvf); #endif /* __OTX2_CPTVF_H */ diff --git a/drivers/crypto/marvell/octeontx2/otx2_cptvf_main.c b/drivers/crypto/marvell/octeontx2/otx2_cptvf_main.c index 6d84fafa2915..97d57bcb2b94 100644 --- a/drivers/crypto/marvell/octeontx2/otx2_cptvf_main.c +++ b/drivers/crypto/marvell/octeontx2/otx2_cptvf_main.c @@ -3,6 +3,7 @@ #include "otx2_cpt_common.h" #include "otx2_cptvf.h" +#include "otx2_cptlf.h" #include #define OTX2_CPTVF_DRV_NAME "octeontx2-cptvf" @@ -95,6 +96,201 @@ static void cptvf_pfvf_mbox_destroy(struct otx2_cptvf_dev *cptvf) otx2_mbox_destroy(&cptvf->pfvf_mbox); } +static void cptlf_work_handler(unsigned long data) +{ + otx2_cpt_post_process((struct otx2_cptlf_wqe *) data); +} + +static void cleanup_tasklet_work(struct otx2_cptlfs_info *lfs) +{ + int i; + + for (i = 0; i < lfs->lfs_num; i++) { + if (!lfs->lf[i].wqe) + continue; + + tasklet_kill(&lfs->lf[i].wqe->work); + kfree(lfs->lf[i].wqe); + lfs->lf[i].wqe = NULL; + } +} + +static int init_tasklet_work(struct otx2_cptlfs_info *lfs) +{ + struct otx2_cptlf_wqe *wqe; + int i, ret = 0; + + for (i = 0; i < lfs->lfs_num; i++) { + wqe = kzalloc(sizeof(struct otx2_cptlf_wqe), GFP_KERNEL); + if (!wqe) { + ret = -ENOMEM; + goto cleanup_tasklet; + } + + tasklet_init(&wqe->work, cptlf_work_handler, (u64) wqe); + wqe->lfs = lfs; + wqe->lf_num = i; + lfs->lf[i].wqe = wqe; + } + return 0; + +cleanup_tasklet: + cleanup_tasklet_work(lfs); + return ret; +} + +static void free_pending_queues(struct otx2_cptlfs_info *lfs) +{ + int i; + + for (i = 0; i < lfs->lfs_num; i++) { + kfree(lfs->lf[i].pqueue.head); + lfs->lf[i].pqueue.head = NULL; + } +} + +static int alloc_pending_queues(struct otx2_cptlfs_info *lfs) +{ + int size, ret, i; + + if (!lfs->lfs_num) + return -EINVAL; + + for (i = 0; i < lfs->lfs_num; i++) { + lfs->lf[i].pqueue.qlen = OTX2_CPT_INST_QLEN_MSGS; + size = lfs->lf[i].pqueue.qlen * + sizeof(struct otx2_cpt_pending_entry); + + lfs->lf[i].pqueue.head = kzalloc(size, GFP_KERNEL); + if (!lfs->lf[i].pqueue.head) { + ret = -ENOMEM; + goto error; + } + + /* Initialize spin lock */ + spin_lock_init(&lfs->lf[i].pqueue.lock); + } + return 0; + +error: + free_pending_queues(lfs); + return ret; +} + +static void lf_sw_cleanup(struct otx2_cptlfs_info *lfs) +{ + cleanup_tasklet_work(lfs); + free_pending_queues(lfs); +} + +static int lf_sw_init(struct otx2_cptlfs_info *lfs) +{ + int ret; + + ret = alloc_pending_queues(lfs); + if (ret) { + dev_err(&lfs->pdev->dev, + "Allocating pending queues failed\n"); + return ret; + } + ret = init_tasklet_work(lfs); + if (ret) { + dev_err(&lfs->pdev->dev, + "Tasklet work init failed\n"); + goto pending_queues_free; + } + return 0; + +pending_queues_free: + free_pending_queues(lfs); + return ret; +} + +static void cptvf_lf_shutdown(struct otx2_cptlfs_info *lfs) +{ + atomic_set(&lfs->state, OTX2_CPTLF_IN_RESET); + + /* Remove interrupts affinity */ + otx2_cptlf_free_irqs_affinity(lfs); + /* Disable instruction queue */ + otx2_cptlf_disable_iqueues(lfs); + /* Unregister LFs interrupts */ + otx2_cptlf_unregister_interrupts(lfs); + /* Cleanup LFs software side */ + lf_sw_cleanup(lfs); + /* Send request to detach LFs */ + otx2_cpt_detach_rsrcs_msg(lfs); +} + +static int cptvf_lf_init(struct otx2_cptvf_dev *cptvf) +{ + struct otx2_cptlfs_info *lfs = &cptvf->lfs; + struct device *dev = &cptvf->pdev->dev; + int ret, lfs_num; + u8 eng_grp_msk; + + /* Get engine group number for symmetric crypto */ + cptvf->lfs.kcrypto_eng_grp_num = OTX2_CPT_INVALID_CRYPTO_ENG_GRP; + ret = otx2_cptvf_send_eng_grp_num_msg(cptvf, OTX2_CPT_SE_TYPES); + if (ret) + return ret; + + if (cptvf->lfs.kcrypto_eng_grp_num == OTX2_CPT_INVALID_CRYPTO_ENG_GRP) { + dev_err(dev, "Engine group for kernel crypto not available\n"); + ret = -ENOENT; + return ret; + } + eng_grp_msk = 1 << cptvf->lfs.kcrypto_eng_grp_num; + + ret = otx2_cptvf_send_kvf_limits_msg(cptvf); + if (ret) + return ret; + + lfs->reg_base = cptvf->reg_base; + lfs->pdev = cptvf->pdev; + lfs->mbox = &cptvf->pfvf_mbox; + + lfs_num = cptvf->lfs.kvf_limits ? cptvf->lfs.kvf_limits : + num_online_cpus(); + ret = otx2_cptlf_init(lfs, eng_grp_msk, OTX2_CPT_QUEUE_HI_PRIO, + lfs_num); + if (ret) + return ret; + + /* Get msix offsets for attached LFs */ + ret = otx2_cpt_msix_offset_msg(lfs); + if (ret) + goto cleanup_lf; + + /* Initialize LFs software side */ + ret = lf_sw_init(lfs); + if (ret) + goto cleanup_lf; + + /* Register LFs interrupts */ + ret = otx2_cptlf_register_interrupts(lfs); + if (ret) + goto cleanup_lf_sw; + + /* Set interrupts affinity */ + ret = otx2_cptlf_set_irqs_affinity(lfs); + if (ret) + goto unregister_intr; + + atomic_set(&lfs->state, OTX2_CPTLF_STARTED); + + return 0; + +unregister_intr: + otx2_cptlf_unregister_interrupts(lfs); +cleanup_lf_sw: + lf_sw_cleanup(lfs); +cleanup_lf: + otx2_cptlf_shutdown(lfs); + + return ret; +} + static int otx2_cptvf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) { @@ -150,8 +346,15 @@ static int otx2_cptvf_probe(struct pci_dev *pdev, if (ret) goto destroy_pfvf_mbox; + /* Initialize CPT LFs */ + ret = cptvf_lf_init(cptvf); + if (ret) + goto unregister_interrupts; + return 0; +unregister_interrupts: + cptvf_disable_pfvf_mbox_intrs(cptvf); destroy_pfvf_mbox: cptvf_pfvf_mbox_destroy(cptvf); clear_drvdata: @@ -168,6 +371,7 @@ static void otx2_cptvf_remove(struct pci_dev *pdev) dev_err(&pdev->dev, "Invalid CPT VF device.\n"); return; } + cptvf_lf_shutdown(&cptvf->lfs); /* Disable PF-VF mailbox interrupt */ cptvf_disable_pfvf_mbox_intrs(cptvf); /* Destroy PF-VF mbox */ diff --git a/drivers/crypto/marvell/octeontx2/otx2_cptvf_mbox.c b/drivers/crypto/marvell/octeontx2/otx2_cptvf_mbox.c index 417099a86742..5d73b711cba6 100644 --- a/drivers/crypto/marvell/octeontx2/otx2_cptvf_mbox.c +++ b/drivers/crypto/marvell/octeontx2/otx2_cptvf_mbox.c @@ -28,6 +28,8 @@ static void process_pfvf_mbox_mbox_msg(struct otx2_cptvf_dev *cptvf, struct mbox_msghdr *msg) { struct otx2_cptlfs_info *lfs = &cptvf->lfs; + struct otx2_cpt_kvf_limits_rsp *rsp_limits; + struct otx2_cpt_egrp_num_rsp *rsp_grp; struct cpt_rd_wr_reg_msg *rsp_reg; struct msix_offset_rsp *rsp_msix; int i; @@ -75,6 +77,14 @@ static void process_pfvf_mbox_mbox_msg(struct otx2_cptvf_dev *cptvf, if (!rsp_reg->is_write) *rsp_reg->ret_val = rsp_reg->val; break; + case MBOX_MSG_GET_ENG_GRP_NUM: + rsp_grp = (struct otx2_cpt_egrp_num_rsp *) msg; + cptvf->lfs.kcrypto_eng_grp_num = rsp_grp->eng_grp_num; + break; + case MBOX_MSG_GET_KVF_LIMITS: + rsp_limits = (struct otx2_cpt_kvf_limits_rsp *) msg; + cptvf->lfs.kvf_limits = rsp_limits->kvf_limits; + break; default: dev_err(&cptvf->pdev->dev, "Unsupported msg %d received.\n", msg->id); @@ -111,3 +121,47 @@ void otx2_cptvf_pfvf_mbox_handler(struct work_struct *work) } otx2_mbox_reset(pfvf_mbox, 0); } + +int otx2_cptvf_send_eng_grp_num_msg(struct otx2_cptvf_dev *cptvf, int eng_type) +{ + struct otx2_mbox *mbox = &cptvf->pfvf_mbox; + struct pci_dev *pdev = cptvf->pdev; + struct otx2_cpt_egrp_num_msg *req; + + req = (struct otx2_cpt_egrp_num_msg *) + otx2_mbox_alloc_msg_rsp(mbox, 0, sizeof(*req), + sizeof(struct otx2_cpt_egrp_num_rsp)); + if (req == NULL) { + dev_err(&pdev->dev, "RVU MBOX failed to get message.\n"); + return -EFAULT; + } + req->hdr.id = MBOX_MSG_GET_ENG_GRP_NUM; + req->hdr.sig = OTX2_MBOX_REQ_SIG; + req->hdr.pcifunc = OTX2_CPT_RVU_PFFUNC(cptvf->vf_id, 0); + req->eng_type = eng_type; + + return otx2_cpt_send_mbox_msg(mbox, pdev); +} + +int otx2_cptvf_send_kvf_limits_msg(struct otx2_cptvf_dev *cptvf) +{ + struct otx2_mbox *mbox = &cptvf->pfvf_mbox; + struct pci_dev *pdev = cptvf->pdev; + struct mbox_msghdr *req; + int ret; + + req = (struct mbox_msghdr *) + otx2_mbox_alloc_msg_rsp(mbox, 0, sizeof(*req), + sizeof(struct otx2_cpt_kvf_limits_rsp)); + if (req == NULL) { + dev_err(&pdev->dev, "RVU MBOX failed to get message.\n"); + return -EFAULT; + } + req->id = MBOX_MSG_GET_KVF_LIMITS; + req->sig = OTX2_MBOX_REQ_SIG; + req->pcifunc = OTX2_CPT_RVU_PFFUNC(cptvf->vf_id, 0); + + ret = otx2_cpt_send_mbox_msg(mbox, pdev); + + return ret; +} diff --git a/drivers/crypto/marvell/octeontx2/otx2_cptvf_reqmgr.c b/drivers/crypto/marvell/octeontx2/otx2_cptvf_reqmgr.c new file mode 100644 index 000000000000..b3b371ce06f9 --- /dev/null +++ b/drivers/crypto/marvell/octeontx2/otx2_cptvf_reqmgr.c @@ -0,0 +1,534 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (C) 2020 Marvell. */ + +#include "otx2_cptvf.h" +#include "otx2_cpt_common.h" + +/* SG list header size in bytes */ +#define SG_LIST_HDR_SIZE 8 + +/* Default timeout when waiting for free pending entry in us */ +#define CPT_PENTRY_TIMEOUT 1000 +#define CPT_PENTRY_STEP 50 + +/* Default threshold for stopping and resuming sender requests */ +#define CPT_IQ_STOP_MARGIN 128 +#define CPT_IQ_RESUME_MARGIN 512 + +/* Default command timeout in seconds */ +#define CPT_COMMAND_TIMEOUT 4 +#define CPT_TIME_IN_RESET_COUNT 5 + +static void otx2_cpt_dump_sg_list(struct pci_dev *pdev, + struct otx2_cpt_req_info *req) +{ + int i; + + pr_debug("Gather list size %d\n", req->in_cnt); + for (i = 0; i < req->in_cnt; i++) { + pr_debug("Buffer %d size %d, vptr 0x%p, dmaptr 0x%p\n", i, + req->in[i].size, req->in[i].vptr, + (void *) req->in[i].dma_addr); + pr_debug("Buffer hexdump (%d bytes)\n", + req->in[i].size); + print_hex_dump_debug("", DUMP_PREFIX_NONE, 16, 1, + req->in[i].vptr, req->in[i].size, false); + } + pr_debug("Scatter list size %d\n", req->out_cnt); + for (i = 0; i < req->out_cnt; i++) { + pr_debug("Buffer %d size %d, vptr 0x%p, dmaptr 0x%p\n", i, + req->out[i].size, req->out[i].vptr, + (void *) req->out[i].dma_addr); + pr_debug("Buffer hexdump (%d bytes)\n", req->out[i].size); + print_hex_dump_debug("", DUMP_PREFIX_NONE, 16, 1, + req->out[i].vptr, req->out[i].size, false); + } +} + +static inline struct otx2_cpt_pending_entry *get_free_pending_entry( + struct otx2_cpt_pending_queue *q, + int qlen) +{ + struct otx2_cpt_pending_entry *ent = NULL; + + ent = &q->head[q->rear]; + if (unlikely(ent->busy)) + return NULL; + + q->rear++; + if (unlikely(q->rear == qlen)) + q->rear = 0; + + return ent; +} + +static inline u32 modulo_inc(u32 index, u32 length, u32 inc) +{ + if (WARN_ON(inc > length)) + inc = length; + + index += inc; + if (unlikely(index >= length)) + index -= length; + + return index; +} + +static inline void free_pentry(struct otx2_cpt_pending_entry *pentry) +{ + pentry->completion_addr = NULL; + pentry->info = NULL; + pentry->callback = NULL; + pentry->areq = NULL; + pentry->resume_sender = false; + pentry->busy = false; +} + +static inline int setup_sgio_components(struct pci_dev *pdev, + struct otx2_cpt_buf_ptr *list, + int buf_count, u8 *buffer) +{ + struct otx2_cpt_sglist_component *sg_ptr = NULL; + int ret = 0, i, j; + int components; + + if (unlikely(!list)) { + dev_err(&pdev->dev, "Input list pointer is NULL\n"); + return -EFAULT; + } + + for (i = 0; i < buf_count; i++) { + if (unlikely(!list[i].vptr)) + continue; + list[i].dma_addr = dma_map_single(&pdev->dev, list[i].vptr, + list[i].size, + DMA_BIDIRECTIONAL); + if (unlikely(dma_mapping_error(&pdev->dev, list[i].dma_addr))) { + dev_err(&pdev->dev, "Dma mapping failed\n"); + ret = -EIO; + goto sg_cleanup; + } + } + components = buf_count / 4; + sg_ptr = (struct otx2_cpt_sglist_component *)buffer; + for (i = 0; i < components; i++) { + sg_ptr->len0 = cpu_to_be16(list[i * 4 + 0].size); + sg_ptr->len1 = cpu_to_be16(list[i * 4 + 1].size); + sg_ptr->len2 = cpu_to_be16(list[i * 4 + 2].size); + sg_ptr->len3 = cpu_to_be16(list[i * 4 + 3].size); + sg_ptr->ptr0 = cpu_to_be64(list[i * 4 + 0].dma_addr); + sg_ptr->ptr1 = cpu_to_be64(list[i * 4 + 1].dma_addr); + sg_ptr->ptr2 = cpu_to_be64(list[i * 4 + 2].dma_addr); + sg_ptr->ptr3 = cpu_to_be64(list[i * 4 + 3].dma_addr); + sg_ptr++; + } + components = buf_count % 4; + + switch (components) { + case 3: + sg_ptr->len2 = cpu_to_be16(list[i * 4 + 2].size); + sg_ptr->ptr2 = cpu_to_be64(list[i * 4 + 2].dma_addr); + fallthrough; + case 2: + sg_ptr->len1 = cpu_to_be16(list[i * 4 + 1].size); + sg_ptr->ptr1 = cpu_to_be64(list[i * 4 + 1].dma_addr); + fallthrough; + case 1: + sg_ptr->len0 = cpu_to_be16(list[i * 4 + 0].size); + sg_ptr->ptr0 = cpu_to_be64(list[i * 4 + 0].dma_addr); + break; + default: + break; + } + return ret; + +sg_cleanup: + for (j = 0; j < i; j++) { + if (list[j].dma_addr) { + dma_unmap_single(&pdev->dev, list[j].dma_addr, + list[j].size, DMA_BIDIRECTIONAL); + } + + list[j].dma_addr = 0; + } + return ret; +} + +static inline struct otx2_cpt_inst_info *info_create(struct pci_dev *pdev, + struct otx2_cpt_req_info *req, + gfp_t gfp) +{ + int align = OTX2_CPT_DMA_MINALIGN; + struct otx2_cpt_inst_info *info; + u32 dlen, align_dlen, info_len; + u16 g_sz_bytes, s_sz_bytes; + u32 total_mem_len; + + if (unlikely(req->in_cnt > OTX2_CPT_MAX_SG_IN_CNT || + req->out_cnt > OTX2_CPT_MAX_SG_OUT_CNT)) { + dev_err(&pdev->dev, "Error too many sg components\n"); + return NULL; + } + + g_sz_bytes = ((req->in_cnt + 3) / 4) * + sizeof(struct otx2_cpt_sglist_component); + s_sz_bytes = ((req->out_cnt + 3) / 4) * + sizeof(struct otx2_cpt_sglist_component); + + dlen = g_sz_bytes + s_sz_bytes + SG_LIST_HDR_SIZE; + align_dlen = ALIGN(dlen, align); + info_len = ALIGN(sizeof(*info), align); + total_mem_len = align_dlen + info_len + sizeof(union otx2_cpt_res_s); + + info = kzalloc(total_mem_len, gfp); + if (unlikely(!info)) + return NULL; + + info->dlen = dlen; + info->in_buffer = (u8 *)info + info_len; + + ((u16 *)info->in_buffer)[0] = req->out_cnt; + ((u16 *)info->in_buffer)[1] = req->in_cnt; + ((u16 *)info->in_buffer)[2] = 0; + ((u16 *)info->in_buffer)[3] = 0; + cpu_to_be64s((u64 *)info->in_buffer); + + /* Setup gather (input) components */ + if (setup_sgio_components(pdev, req->in, req->in_cnt, + &info->in_buffer[8])) { + dev_err(&pdev->dev, "Failed to setup gather list\n"); + goto destroy_info; + } + + if (setup_sgio_components(pdev, req->out, req->out_cnt, + &info->in_buffer[8 + g_sz_bytes])) { + dev_err(&pdev->dev, "Failed to setup scatter list\n"); + goto destroy_info; + } + + info->dma_len = total_mem_len - info_len; + info->dptr_baddr = dma_map_single(&pdev->dev, info->in_buffer, + info->dma_len, DMA_BIDIRECTIONAL); + if (unlikely(dma_mapping_error(&pdev->dev, info->dptr_baddr))) { + dev_err(&pdev->dev, "DMA Mapping failed for cpt req\n"); + goto destroy_info; + } + /* + * Get buffer for union otx2_cpt_res_s response + * structure and its physical address + */ + info->completion_addr = info->in_buffer + align_dlen; + info->comp_baddr = info->dptr_baddr + align_dlen; + + return info; + +destroy_info: + otx2_cpt_info_destroy(pdev, info); + return NULL; +} + +static int process_request(struct pci_dev *pdev, struct otx2_cpt_req_info *req, + struct otx2_cpt_pending_queue *pqueue, + struct otx2_cptlf_info *lf) +{ + struct otx2_cptvf_request *cpt_req = &req->req; + struct otx2_cpt_pending_entry *pentry = NULL; + union otx2_cpt_ctrl_info *ctrl = &req->ctrl; + struct otx2_cpt_inst_info *info = NULL; + union otx2_cpt_res_s *result = NULL; + struct otx2_cpt_iq_command iq_cmd; + union otx2_cpt_inst_s cptinst; + int retry, ret = 0; + u8 resume_sender; + gfp_t gfp; + + gfp = (req->areq->flags & CRYPTO_TFM_REQ_MAY_SLEEP) ? GFP_KERNEL : + GFP_ATOMIC; + if (unlikely(!otx2_cptlf_started(lf->lfs))) + return -ENODEV; + + info = info_create(pdev, req, gfp); + if (unlikely(!info)) { + dev_err(&pdev->dev, "Setting up cpt inst info failed"); + return -ENOMEM; + } + cpt_req->dlen = info->dlen; + + result = info->completion_addr; + result->s.compcode = OTX2_CPT_COMPLETION_CODE_INIT; + + spin_lock_bh(&pqueue->lock); + pentry = get_free_pending_entry(pqueue, pqueue->qlen); + retry = CPT_PENTRY_TIMEOUT / CPT_PENTRY_STEP; + while (unlikely(!pentry) && retry--) { + spin_unlock_bh(&pqueue->lock); + udelay(CPT_PENTRY_STEP); + spin_lock_bh(&pqueue->lock); + pentry = get_free_pending_entry(pqueue, pqueue->qlen); + } + + if (unlikely(!pentry)) { + ret = -ENOSPC; + goto destroy_info; + } + + /* + * Check if we are close to filling in entire pending queue, + * if so then tell the sender to stop/sleep by returning -EBUSY + * We do it only for context which can sleep (GFP_KERNEL) + */ + if (gfp == GFP_KERNEL && + pqueue->pending_count > (pqueue->qlen - CPT_IQ_STOP_MARGIN)) { + pentry->resume_sender = true; + } else + pentry->resume_sender = false; + resume_sender = pentry->resume_sender; + pqueue->pending_count++; + + pentry->completion_addr = info->completion_addr; + pentry->info = info; + pentry->callback = req->callback; + pentry->areq = req->areq; + pentry->busy = true; + info->pentry = pentry; + info->time_in = jiffies; + info->req = req; + + /* Fill in the command */ + iq_cmd.cmd.u = 0; + iq_cmd.cmd.s.opcode = cpu_to_be16(cpt_req->opcode.flags); + iq_cmd.cmd.s.param1 = cpu_to_be16(cpt_req->param1); + iq_cmd.cmd.s.param2 = cpu_to_be16(cpt_req->param2); + iq_cmd.cmd.s.dlen = cpu_to_be16(cpt_req->dlen); + + /* 64-bit swap for microcode data reads, not needed for addresses*/ + cpu_to_be64s(&iq_cmd.cmd.u); + iq_cmd.dptr = info->dptr_baddr; + iq_cmd.rptr = 0; + iq_cmd.cptr.u = 0; + iq_cmd.cptr.s.grp = ctrl->s.grp; + + /* Fill in the CPT_INST_S type command for HW interpretation */ + otx2_cpt_fill_inst(&cptinst, &iq_cmd, info->comp_baddr); + + /* Print debug info if enabled */ + otx2_cpt_dump_sg_list(pdev, req); + pr_debug("Cpt_inst_s hexdump (%d bytes)\n", OTX2_CPT_INST_SIZE); + print_hex_dump_debug("", 0, 16, 1, &cptinst, OTX2_CPT_INST_SIZE, false); + pr_debug("Dptr hexdump (%d bytes)\n", cpt_req->dlen); + print_hex_dump_debug("", 0, 16, 1, info->in_buffer, + cpt_req->dlen, false); + + /* Send CPT command */ + otx2_cpt_send_cmd(&cptinst, 1, lf); + + /* + * We allocate and prepare pending queue entry in critical section + * together with submitting CPT instruction to CPT instruction queue + * to make sure that order of CPT requests is the same in both + * pending and instruction queues + */ + spin_unlock_bh(&pqueue->lock); + + ret = resume_sender ? -EBUSY : -EINPROGRESS; + return ret; + +destroy_info: + spin_unlock_bh(&pqueue->lock); + otx2_cpt_info_destroy(pdev, info); + return ret; +} + +int otx2_cpt_do_request(struct pci_dev *pdev, struct otx2_cpt_req_info *req, + int cpu_num) +{ + struct otx2_cptvf_dev *cptvf = pci_get_drvdata(pdev); + struct otx2_cptlfs_info *lfs = &cptvf->lfs; + + return process_request(lfs->pdev, req, &lfs->lf[cpu_num].pqueue, + &lfs->lf[cpu_num]); +} + +static int cpt_process_ccode(struct pci_dev *pdev, + union otx2_cpt_res_s *cpt_status, + struct otx2_cpt_inst_info *info, + u32 *res_code) +{ + u8 uc_ccode = cpt_status->s.uc_compcode; + u8 ccode = cpt_status->s.compcode; + + switch (ccode) { + case OTX2_CPT_COMP_E_FAULT: + dev_err(&pdev->dev, + "Request failed with DMA fault\n"); + otx2_cpt_dump_sg_list(pdev, info->req); + break; + + case OTX2_CPT_COMP_E_HWERR: + dev_err(&pdev->dev, + "Request failed with hardware error\n"); + otx2_cpt_dump_sg_list(pdev, info->req); + break; + + case OTX2_CPT_COMP_E_INSTERR: + dev_err(&pdev->dev, + "Request failed with instruction error\n"); + otx2_cpt_dump_sg_list(pdev, info->req); + break; + + case OTX2_CPT_COMP_E_NOTDONE: + /* check for timeout */ + if (time_after_eq(jiffies, info->time_in + + CPT_COMMAND_TIMEOUT * HZ)) + dev_warn(&pdev->dev, + "Request timed out 0x%p", info->req); + else if (info->extra_time < CPT_TIME_IN_RESET_COUNT) { + info->time_in = jiffies; + info->extra_time++; + } + return 1; + + case OTX2_CPT_COMP_E_GOOD: + /* + * Check microcode completion code, it is only valid + * when completion code is CPT_COMP_E::GOOD + */ + if (uc_ccode != OTX2_CPT_UCC_SUCCESS) { + /* + * If requested hmac is truncated and ucode returns + * s/g write length error then we report success + * because ucode writes as many bytes of calculated + * hmac as available in gather buffer and reports + * s/g write length error if number of bytes in gather + * buffer is less than full hmac size. + */ + if (info->req->is_trunc_hmac && + uc_ccode == OTX2_CPT_UCC_SG_WRITE_LENGTH) { + *res_code = 0; + break; + } + + dev_err(&pdev->dev, + "Request failed with software error code 0x%x\n", + cpt_status->s.uc_compcode); + otx2_cpt_dump_sg_list(pdev, info->req); + break; + } + /* Request has been processed with success */ + *res_code = 0; + break; + + default: + dev_err(&pdev->dev, + "Request returned invalid status %d\n", ccode); + break; + } + return 0; +} + +static inline void process_pending_queue(struct pci_dev *pdev, + struct otx2_cpt_pending_queue *pqueue) +{ + struct otx2_cpt_pending_entry *resume_pentry = NULL; + void (*callback)(int status, void *arg, void *req); + struct otx2_cpt_pending_entry *pentry = NULL; + union otx2_cpt_res_s *cpt_status = NULL; + struct otx2_cpt_inst_info *info = NULL; + struct otx2_cpt_req_info *req = NULL; + struct crypto_async_request *areq; + u32 res_code, resume_index; + + while (1) { + spin_lock_bh(&pqueue->lock); + pentry = &pqueue->head[pqueue->front]; + + if (WARN_ON(!pentry)) { + spin_unlock_bh(&pqueue->lock); + break; + } + + res_code = -EINVAL; + if (unlikely(!pentry->busy)) { + spin_unlock_bh(&pqueue->lock); + break; + } + + if (unlikely(!pentry->callback)) { + dev_err(&pdev->dev, "Callback NULL\n"); + goto process_pentry; + } + + info = pentry->info; + if (unlikely(!info)) { + dev_err(&pdev->dev, "Pending entry post arg NULL\n"); + goto process_pentry; + } + + req = info->req; + if (unlikely(!req)) { + dev_err(&pdev->dev, "Request NULL\n"); + goto process_pentry; + } + + cpt_status = pentry->completion_addr; + if (unlikely(!cpt_status)) { + dev_err(&pdev->dev, "Completion address NULL\n"); + goto process_pentry; + } + + if (cpt_process_ccode(pdev, cpt_status, info, &res_code)) { + spin_unlock_bh(&pqueue->lock); + return; + } + info->pdev = pdev; + +process_pentry: + /* + * Check if we should inform sending side to resume + * We do it CPT_IQ_RESUME_MARGIN elements in advance before + * pending queue becomes empty + */ + resume_index = modulo_inc(pqueue->front, pqueue->qlen, + CPT_IQ_RESUME_MARGIN); + resume_pentry = &pqueue->head[resume_index]; + if (resume_pentry && + resume_pentry->resume_sender) { + resume_pentry->resume_sender = false; + callback = resume_pentry->callback; + areq = resume_pentry->areq; + + if (callback) { + spin_unlock_bh(&pqueue->lock); + + /* + * EINPROGRESS is an indication for sending + * side that it can resume sending requests + */ + callback(-EINPROGRESS, areq, info); + spin_lock_bh(&pqueue->lock); + } + } + + callback = pentry->callback; + areq = pentry->areq; + free_pentry(pentry); + + pqueue->pending_count--; + pqueue->front = modulo_inc(pqueue->front, pqueue->qlen, 1); + spin_unlock_bh(&pqueue->lock); + + /* + * Call callback after current pending entry has been + * processed, we don't do it if the callback pointer is + * invalid. + */ + if (callback) + callback(res_code, areq, info); + } +} + +void otx2_cpt_post_process(struct otx2_cptlf_wqe *wqe) +{ + process_pending_queue(wqe->lfs->pdev, + &wqe->lfs->lf[wqe->lf_num].pqueue); +}