From patchwork Thu Dec 13 11:22:09 2018 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Zhou Wang X-Patchwork-Id: 153632 Delivered-To: patch@linaro.org Received: by 2002:a2e:299d:0:0:0:0:0 with SMTP id p29-v6csp680722ljp; Thu, 13 Dec 2018 03:22:23 -0800 (PST) X-Google-Smtp-Source: AFSGD/WVRyCoVUhaxpKSNC0N246tg2+2P0itgRqguHq4vGafCdNTI0UzbverO+ndCZKjlin+3esf X-Received: by 2002:a62:520b:: with SMTP id g11mr24036294pfb.53.1544700142940; Thu, 13 Dec 2018 03:22:22 -0800 (PST) ARC-Seal: i=1; a=rsa-sha256; t=1544700142; cv=none; d=google.com; s=arc-20160816; b=WLI/KK0rOvKZ9SMVzgIyLQ8qw3NbxHO07crD+ZFgvJvG9ctsGw9SbOiUqgnRhUYvmw AoRTdu3hUknBxwFT52kr8gk5ra4R42cbo1EgX5MpFvBBwPAIHNSDUXEa0QIc9/2Sw/B0 nl1YJgvAviLwpfQ2hErWjB+CwOsQsL2jxU8xkIXkRjcuKdZLFNBeQep/eEL+6Cl6H9Rg TbvI4NXEJuqsz2wtY8aW2vP2MjVoHPlLIvlO0bCFwUY5DMEc+CugG0PqWYfNLE4PHSMx fXpsbX4Q+F6QicUjaAqG7xRXFna9p7tBH3XsRcRCTcrK59CxnNwifNYLGt9CX9bBlnKR 2Xkw== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=arc-20160816; h=list-id:precedence:sender:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from; bh=gHauXux8Va9Upin7mCkULD5Pymys9nhX2gqRTYhaCQs=; b=dXgwzgo53TVddECQ2xiOwr7VJYm47LocJ7+vDep/Iz1sQFJ+8kSU4RRi8V5KXgWaSr QYchoU6vuvbk1ASmuuzwCtquEfU6cfXk7vnrERR2bbcl8y+PSWukW1XBDWp79xQXgsqg lG2U43Bgi7DQSu31Oggd2SODew2AKlO6lHKXNNnPJRpiEsAG2pPsVi0U8PVNDJo8sVXK OjKPeRMW7A8EVA9GcA7siFAhVskhm4J781YcDrQjwvFB5BkZU3JfJFdgooxlONCwkV1s MFf4wmcF+8HWLOAUEDdHRroOLJzTWIynG7XcbOaXoqrM9ibc+FejaFEbOTzaLPqCwDVv qDSw== ARC-Authentication-Results: i=1; mx.google.com; spf=pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) smtp.mailfrom=linux-kernel-owner@vger.kernel.org Return-Path: Received: from vger.kernel.org (vger.kernel.org. [209.132.180.67]) by mx.google.com with ESMTP id s36si1345657pld.46.2018.12.13.03.22.22; Thu, 13 Dec 2018 03:22:22 -0800 (PST) Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67; Authentication-Results: mx.google.com; spf=pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) smtp.mailfrom=linux-kernel-owner@vger.kernel.org Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1728828AbeLMLWU (ORCPT + 31 others); Thu, 13 Dec 2018 06:22:20 -0500 Received: from szxga06-in.huawei.com ([45.249.212.32]:50942 "EHLO huawei.com" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1728791AbeLMLWT (ORCPT ); Thu, 13 Dec 2018 06:22:19 -0500 Received: from DGGEMS413-HUB.china.huawei.com (unknown [172.30.72.60]) by Forcepoint Email with ESMTP id 35BE8E9113A0A; Thu, 13 Dec 2018 19:22:11 +0800 (CST) Received: from localhost.localdomain (10.67.212.75) by DGGEMS413-HUB.china.huawei.com (10.3.19.213) with Microsoft SMTP Server id 14.3.408.0; Thu, 13 Dec 2018 19:22:05 +0800 From: Zhou Wang To: Herbert Xu , "David S . Miller" , CC: , , Zhou Wang , Kenneth Lee , Shiju Jose , Hao Fang Subject: [PATCH RFC 2/4] crypto: hisilicon: Add queue management driver for HiSilicon QM module Date: Thu, 13 Dec 2018 19:22:09 +0800 Message-ID: <1544700131-196846-3-git-send-email-wangzhou1@hisilicon.com> X-Mailer: git-send-email 2.8.1 In-Reply-To: <1544700131-196846-1-git-send-email-wangzhou1@hisilicon.com> References: <1544700131-196846-1-git-send-email-wangzhou1@hisilicon.com> MIME-Version: 1.0 X-Originating-IP: [10.67.212.75] X-CFilter-Loop: Reflected Sender: linux-kernel-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org QM is a general IP used by HiSilicon accelerators. It provides a general PCIe interface for the CPU and the accelerator to share a group of queues. A QM integrated in an accelerator provides queue management service. Queues can be assigned to PF and VFs, and queues can be controlled by unified mailboxes and doorbells. Specific task request are descripted by specific description buffer, which will be controlled and pass to related accelerator IP by QM. This patch adds a QM driver used by the accelerator driver to access the QM hardware. Signed-off-by: Zhou Wang Signed-off-by: Kenneth Lee Signed-off-by: Shiju Jose Signed-off-by: Hao Fang reviewed-by: Jonathan Cameron reviewed-by: John Garry --- drivers/crypto/hisilicon/Kconfig | 4 + drivers/crypto/hisilicon/Makefile | 1 + drivers/crypto/hisilicon/qm.c | 1815 +++++++++++++++++++++++++++++++++++++ drivers/crypto/hisilicon/qm.h | 176 ++++ 4 files changed, 1996 insertions(+) create mode 100644 drivers/crypto/hisilicon/qm.c create mode 100644 drivers/crypto/hisilicon/qm.h -- 2.8.1 diff --git a/drivers/crypto/hisilicon/Kconfig b/drivers/crypto/hisilicon/Kconfig index 8ca9c50..993a98d 100644 --- a/drivers/crypto/hisilicon/Kconfig +++ b/drivers/crypto/hisilicon/Kconfig @@ -12,3 +12,7 @@ config CRYPTO_DEV_HISI_SEC To compile this as a module, choose M here: the module will be called hisi_sec. + +config CRYPTO_DEV_HISI_QM + tristate + depends on ARM64 && PCI && PCI_MSI diff --git a/drivers/crypto/hisilicon/Makefile b/drivers/crypto/hisilicon/Makefile index 463f46a..05e9052 100644 --- a/drivers/crypto/hisilicon/Makefile +++ b/drivers/crypto/hisilicon/Makefile @@ -1,2 +1,3 @@ # SPDX-License-Identifier: GPL-2.0 obj-$(CONFIG_CRYPTO_DEV_HISI_SEC) += sec/ +obj-$(CONFIG_CRYPTO_DEV_HISI_QM) += qm.o diff --git a/drivers/crypto/hisilicon/qm.c b/drivers/crypto/hisilicon/qm.c new file mode 100644 index 0000000..4d14b72 --- /dev/null +++ b/drivers/crypto/hisilicon/qm.c @@ -0,0 +1,1815 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2018 Hisilicon Limited. */ +#include +#include +#include +#include +#include +#include +#include +#include +#include "qm.h" + +/* eq/aeq irq enable */ +#define QM_VF_EQ_INT_SOURCE 0x8 +#define QM_VF_EQ_INT_MASK 0xc + +/* mailbox */ +#define QM_MB_CMD_SQC 0x0 +#define QM_MB_CMD_CQC 0x1 +#define QM_MB_CMD_EQC 0x2 +#define QM_MB_CMD_AEQC 0x3 +#define QM_MB_CMD_SQC_BT 0x4 +#define QM_MB_CMD_CQC_BT 0x5 +#define QM_MB_CMD_SQC_VFT_V2 0x6 + +#define QM_MB_CMD_SEND_BASE 0x300 +#define QM_MB_EVENT_SHIFT 8 +#define QM_MB_BUSY_SHIFT 13 +#define QM_MB_OP_SHIFT 14 +#define QM_MB_CMD_DATA_ADDR_L 0x304 +#define QM_MB_CMD_DATA_ADDR_H 0x308 + +/* sqc shift */ +#define QM_SQ_HOP_NUM_SHIFT 0 +#define QM_SQ_PAGE_SIZE_SHIFT 4 +#define QM_SQ_BUF_SIZE_SHIFT 8 +#define QM_SQ_SQE_SIZE_SHIFT 12 +#define QM_SQ_PRIORITY_SHIFT 0 +#define QM_SQ_ORDERS_SHIFT 4 +#define QM_SQ_TYPE_SHIFT 8 + +#define QM_SQ_TYPE_MASK 0xf + +/* cqc shift */ +#define QM_CQ_HOP_NUM_SHIFT 0 +#define QM_CQ_PAGE_SIZE_SHIFT 4 +#define QM_CQ_BUF_SIZE_SHIFT 8 +#define QM_CQ_SQE_SIZE_SHIFT 12 +#define QM_CQ_PHASE_SHIFT 0 +#define QM_CQ_FLAG_SHIFT 1 + +#define QM_CQC_PHASE_BIT 0x1 +#define QM_CQE_PHASE(cqe) ((cqe)->w7 & 0x1) + +/* eqc shift */ +#define QM_EQC_EQE_SHIFT 12 +#define QM_EQC_PHASE_SHIFT 16 +#define QM_EQC_PHASE(eqc) ((((eqc)->dw6) >> 16) & 0x1) +#define QM_EQC_PHASE_BIT 0x00010000 + +#define QM_EQE_PHASE(eqe) (((eqe)->dw0 >> 16) & 0x1) +#define QM_EQE_CQN_MASK 0xffff + +#define QM_AEQC_PHASE(aeqc) ((((aeqc)->dw6) >> 16) & 0x1) +#define QM_AEQC_PHASE_BIT 0x00010000 +#define QM_AEQE_PHASE(aeqe) (((aeqe)->dw0 >> 16) & 0x1) + +#define QM_DOORBELL_CMD_SQ 0 +#define QM_DOORBELL_CMD_CQ 1 +#define QM_DOORBELL_CMD_EQ 2 +#define QM_DOORBELL_CMD_AEQ 3 + +#define QM_DOORBELL_BASE_V1 0x340 +#define QM_DOORBELL_SQ_CQ_BASE_V2 0x1000 +#define QM_DOORBELL_EQ_AEQ_BASE_V2 0x2000 + +#define QM_MEM_START_INIT 0x100040 +#define QM_MEM_INIT_DONE 0x100044 +#define QM_VFT_CFG_RDY 0x10006c +#define QM_VFT_CFG_OP_WR 0x100058 +#define QM_VFT_CFG_TYPE 0x10005c +#define QM_SQC_VFT 0x0 +#define QM_CQC_VFT 0x1 +#define QM_VFT_CFG_ADDRESS 0x100060 +#define QM_VFT_CFG_OP_ENABLE 0x100054 + +#define QM_VFT_CFG_DATA_L 0x100064 +#define QM_VFT_CFG_DATA_H 0x100068 +#define QM_SQC_VFT_BUF_SIZE (7ULL << 8) +#define QM_SQC_VFT_SQC_SIZE (5ULL << 12) +#define QM_SQC_VFT_INDEX_NUMBER (1ULL << 16) +#define QM_SQC_VFT_START_SQN_SHIFT 28 +#define QM_SQC_VFT_VALID (1ULL << 44) +#define QM_SQC_VFT_SQN_SHIFT 45 +#define QM_CQC_VFT_BUF_SIZE (7ULL << 8) +#define QM_CQC_VFT_SQC_SIZE (5ULL << 12) +#define QM_CQC_VFT_INDEX_NUMBER (1ULL << 16) +#define QM_CQC_VFT_VALID (1ULL << 28) + +#define QM_SQC_VFT_BASE_SHIFT_V2 28 +#define QM_SQC_VFT_BASE_MASK_V2 0x3f +#define QM_SQC_VFT_NUM_SHIFT_V2 45 +#define QM_SQC_VFT_NUM_MASK_v2 0x3ff + +#define QM_DFX_SQE_CNT_VF_SQN 0x104030 +#define QM_DFX_CQE_CNT_VF_CQN 0x104040 +#define QM_DFX_CNT_CLR_CE 0x100118 + +#define QM_ABNORMAL_INT_SOURCE 0x100000 +#define QM_ABNORMAL_INT_MASK 0x100004 +#define QM_ABNORMAL_INT_STATUS 0x100008 +#define QM_ABNORMAL_INF00 0x100010 +#define QM_FIFO_OVERFLOW_TYPE 0xc0 +#define QM_FIFO_OVERFLOW_VF 0x3f +#define QM_ABNORMAL_INF01 0x100014 +#define QM_DB_TIMEOUT_TYPE 0xc0 +#define QM_DB_TIMEOUT_VF 0x3f +#define QM_RAS_CE_ENABLE 0x1000ec +#define QM_RAS_FE_ENABLE 0x1000f0 +#define QM_RAS_NFE_ENABLE 0x1000f4 +#define QM_RAS_CE_THRESHOLD 0x1000f8 +#define QM_RAS_MSI_INT_SEL 0x1040f4 + +struct qm_cqe { + __le32 rsvd0; + __le16 cmd_id; + __le16 rsvd1; + __le16 sq_head; + __le16 sq_num; + __le16 rsvd2; + __le16 w7; +}; + +struct qm_eqe { + __le32 dw0; +}; + +struct qm_aeqe { + __le32 dw0; +}; + +struct qm_sqc { + __le16 head; + __le16 tail; + __le32 base_l; + __le32 base_h; + __le32 dw3; + __le16 w8; + __le16 rsvd0; + __le16 pasid; + __le16 w11; + __le16 cq_num; + __le16 w13; + __le32 rsvd1; +}; + +struct qm_cqc { + __le16 head; + __le16 tail; + __le32 base_l; + __le32 base_h; + __le32 dw3; + __le16 w8; + __le16 rsvd0; + __le16 pasid; + __le16 w11; + __le32 dw6; + __le32 rsvd1; +}; + +#define INIT_QC_COMMON(qc, base) do { \ + (qc)->head = 0; \ + (qc)->tail = 0; \ + (qc)->base_l = lower_32_bits(base); \ + (qc)->base_h = upper_32_bits(base); \ + (qc)->pasid = 0; \ + (qc)->w11 = 0; \ + (qc)->rsvd1 = 0; \ +} while (0) + +struct qm_eqc { + __le16 head; + __le16 tail; + __le32 base_l; + __le32 base_h; + __le32 dw3; + __le32 rsvd[2]; + __le32 dw6; +}; + +struct qm_aeqc { + __le16 head; + __le16 tail; + __le32 base_l; + __le32 base_h; + __le32 dw3; + __le32 rsvd[2]; + __le32 dw6; +}; + +struct qm_mailbox { + __le16 w0; + __le16 queue_num; + __le32 base_l; + __le32 base_h; + __le32 rsvd; +}; + +struct qm_doorbell { + __le16 queue_num; + __le16 cmd; + __le16 index; + __le16 priority; +}; + +enum vft_type { + SQC_VFT = 0, + CQC_VFT, +}; + +struct hisi_qm_hw_ops { + int (*set_vft)(struct hisi_qm *qm, u32 fun_num, u32 base, u32 number); + int (*get_vft)(struct hisi_qm *qm, u32 *base, u32 *number); + int (*qm_start_qp)(struct hisi_qp *qp, unsigned long arg); + void (*qm_db)(struct hisi_qm *qm, u16 qn, + u8 cmd, u16 index, u8 priority); + u32 (*get_irq_num)(struct hisi_qm *qm); + int (*debug_init)(struct hisi_qm *qm); + void (*hw_error_init)(struct hisi_qm *qm, u32 ce, u32 nfe, u32 fe, + u32 msi); + pci_ers_result_t (*hw_error_handle)(struct hisi_qm *qm); +}; + +static const char * const qm_debug_file_name[] = { + [CURRENT_Q] = "current_q", + [CLEAR_ENABLE] = "clear_enable", +}; + +struct hisi_qm_hw_error { + u32 int_msk; + const char *msg; +}; + +static const struct hisi_qm_hw_error qm_hw_error[] = { + { .int_msk = BIT(0), .msg = "qm_axi_rresp" }, + { .int_msk = BIT(1), .msg = "qm_axi_bresp" }, + { .int_msk = BIT(2), .msg = "qm_ecc_mbit" }, + { .int_msk = BIT(3), .msg = "qm_ecc_1bit" }, + { .int_msk = BIT(4), .msg = "qm_acc_get_task_timeout" }, + { .int_msk = BIT(5), .msg = "qm_acc_do_task_timeout" }, + { .int_msk = BIT(6), .msg = "qm_acc_wb_not_ready_timeout" }, + { .int_msk = BIT(7), .msg = "qm_sq_cq_vf_invalid" }, + { .int_msk = BIT(8), .msg = "qm_cq_vf_invalid" }, + { .int_msk = BIT(9), .msg = "qm_sq_vf_invalid" }, + { .int_msk = BIT(10), .msg = "qm_db_timeout" }, + { .int_msk = BIT(11), .msg = "qm_of_fifo_of" }, + { .int_msk = BIT(12), .msg = "qm_db_random_invalid" }, + { /* sentinel */ } +}; + +static const char * const qm_db_timeout[] = { + "sq", "cq", "eq", "aeq", +}; + +static const char * const qm_fifo_overflow[] = { + "cq", "eq", "aeq", +}; + +/* return 0 mailbox ready, -ETIMEDOUT hardware timeout */ +static int qm_wait_mb_ready(struct hisi_qm *qm) +{ + u32 val; + + return readl_relaxed_poll_timeout(qm->io_base + QM_MB_CMD_SEND_BASE, + val, !((val >> QM_MB_BUSY_SHIFT) & 0x1), 10, 1000); +} + +/* 128 bit should be wrote to hardware at one time to trigger a mailbox */ +static void qm_mb_write(struct hisi_qm *qm, void *src) +{ + void __iomem *fun_base = qm->io_base + QM_MB_CMD_SEND_BASE; + unsigned long tmp0 = 0, tmp1 = 0; + + asm volatile("ldp %0, %1, %3\n" + "stp %0, %1, %2\n" + "dsb sy\n" + : "=&r" (tmp0), + "=&r" (tmp1), + "+Q" (*((char *)fun_base)) + : "Q" (*((char *)src)) + : "memory"); +} + +static int qm_mb(struct hisi_qm *qm, u8 cmd, dma_addr_t dma_addr, u16 queue, + bool op, bool event) +{ + struct qm_mailbox mailbox; + int ret = 0; + + dev_dbg(&qm->pdev->dev, "QM mailbox request to q%u: %u-%llx\n", queue, + cmd, dma_addr); + + mailbox.w0 = cmd | + (event ? 0x1 << QM_MB_EVENT_SHIFT : 0) | + (op ? 0x1 << QM_MB_OP_SHIFT : 0) | + (0x1 << QM_MB_BUSY_SHIFT); + mailbox.queue_num = queue; + mailbox.base_l = lower_32_bits(dma_addr); + mailbox.base_h = upper_32_bits(dma_addr); + mailbox.rsvd = 0; + + mutex_lock(&qm->mailbox_lock); + + if (unlikely(qm_wait_mb_ready(qm))) { + ret = -EBUSY; + dev_err(&qm->pdev->dev, "QM mailbox is busy to start!\n"); + goto busy_unlock; + } + + qm_mb_write(qm, &mailbox); + + if (unlikely(qm_wait_mb_ready(qm))) { + ret = -EBUSY; + dev_err(&qm->pdev->dev, "QM mailbox operation timeout!\n"); + goto busy_unlock; + } + +busy_unlock: + mutex_unlock(&qm->mailbox_lock); + + return ret; +} + +static void qm_db_v1(struct hisi_qm *qm, u16 qn, u8 cmd, u16 index, u8 priority) +{ + u64 doorbell = 0; + + doorbell = qn | ((u64)cmd << 16) | ((u64)index << 32) | + ((u64)priority << 48); + + writeq(doorbell, qm->io_base + QM_DOORBELL_BASE_V1); +} + +static void qm_db_v2(struct hisi_qm *qm, u16 qn, u8 cmd, u16 index, u8 priority) +{ + u64 doorbell = 0; + u16 randate = 0; + u64 dbase; + + if (cmd == QM_DOORBELL_CMD_SQ || cmd == QM_DOORBELL_CMD_CQ) + dbase = QM_DOORBELL_SQ_CQ_BASE_V2; + else + dbase = QM_DOORBELL_EQ_AEQ_BASE_V2; + + doorbell = qn | ((u64)cmd << 12) | ((u64)randate << 16) | + ((u64)index << 32) | ((u64)priority << 48); + + writeq(doorbell, qm->io_base + dbase); +} + +static void qm_db(struct hisi_qm *qm, u16 qn, u8 cmd, u16 index, u8 priority) +{ + dev_dbg(&qm->pdev->dev, "QM doorbell request: qn=%u, cmd=%u, index=%u\n", + qn, cmd, index); + + qm->ops->qm_db(qm, qn, cmd, index, priority); +} + +static u32 qm_get_irq_num_v1(struct hisi_qm *qm) +{ + return 1; +} + +static u32 qm_get_irq_num_v2(struct hisi_qm *qm) +{ + if (qm->fun_type == QM_HW_PF) + return 4; + else + return 2; +} + +static struct hisi_qp *qm_to_hisi_qp(struct hisi_qm *qm, struct qm_eqe *eqe) +{ + u16 cqn = eqe->dw0 & QM_EQE_CQN_MASK; + struct hisi_qp *qp; + + read_lock(&qm->qps_lock); + qp = qm->qp_array[cqn]; + read_unlock(&qm->qps_lock); + + return qp; +} + +static void qm_cq_head_update(struct hisi_qp *qp) +{ + struct qm_cqc *cqc = qp->cqc.addr; + + if (qp->qp_status.cq_head == QM_Q_DEPTH - 1) { + cqc->dw6 = cqc->dw6 ^ QM_CQC_PHASE_BIT; + qp->qp_status.cq_head = 0; + } else { + qp->qp_status.cq_head++; + } +} + +static void qm_poll_qp(struct hisi_qp *qp, struct hisi_qm *qm) +{ + struct qm_cqe *cq_base = qp->scqe.addr + qp->qm->sqe_size * QM_Q_DEPTH; + struct qm_cqc *cqc = qp->cqc.addr; + struct qm_cqe *cqe; + + cqe = cq_base + qp->qp_status.cq_head; + + if (qp->req_cb) { + while (QM_CQE_PHASE(cqe) == (cqc->dw6 & 0x1)) { + dma_rmb(); + qp->req_cb(qp, qp->scqe.addr + qm->sqe_size * + cqe->sq_head); + qm_cq_head_update(qp); + cqe = cq_base + qp->qp_status.cq_head; + atomic_dec(&qp->qp_status.used); + } + } else { + dma_rmb(); + complete(&qp->completion); + qm_cq_head_update(qp); + cqe = cq_base + qp->qp_status.cq_head; + atomic_dec(&qp->qp_status.used); + } + + qm_db(qm, qp->qp_id, QM_DOORBELL_CMD_CQ, qp->qp_status.cq_head, 0); + + /* set c_flag */ + qm_db(qm, qp->qp_id, QM_DOORBELL_CMD_CQ, qp->qp_status.cq_head, 1); +} + +static irqreturn_t qm_irq_thread(int irq, void *data) +{ + struct hisi_qm *qm = data; + struct qm_eqe *eqe = qm->eqe.addr + qm->eq_head * sizeof(struct qm_eqe); + struct qm_eqc *eqc = qm->eqc.addr; + struct hisi_qp *qp; + + while (QM_EQE_PHASE(eqe) == QM_EQC_PHASE(eqc)) { + qp = qm_to_hisi_qp(qm, eqe); + if (qp) + qm_poll_qp(qp, qm); + + if (qm->eq_head == QM_Q_DEPTH - 1) { + eqc->dw6 = eqc->dw6 ^ QM_EQC_PHASE_BIT; + eqe = qm->eqe.addr; + qm->eq_head = 0; + } else { + eqe++; + qm->eq_head++; + } + + qm_db(qm, 0, QM_DOORBELL_CMD_EQ, qm->eq_head, 0); + } + + return IRQ_HANDLED; +} + +static irqreturn_t qm_irq(int irq, void *data) +{ + struct hisi_qm *qm = data; + + if (readl(qm->io_base + QM_VF_EQ_INT_SOURCE)) + return IRQ_WAKE_THREAD; + + dev_err(&qm->pdev->dev, "invalid int source\n"); + + return IRQ_NONE; +} + +static irqreturn_t qm_aeq_irq(int irq, void *data) +{ + struct hisi_qm *qm = data; + struct qm_aeqe *aeqe = qm->aeqe.addr + + qm->aeq_head * sizeof(struct qm_aeqe); + struct qm_aeqc *aeqc = qm->aeqc.addr; + u32 type; + + while (QM_AEQE_PHASE(aeqe) == QM_AEQC_PHASE(aeqc)) { + type = aeqe->dw0 >> 16; + if (type < ARRAY_SIZE(qm_fifo_overflow)) + dev_err(&qm->pdev->dev, "%s overflow\n", + qm_fifo_overflow[type]); + else + dev_err(&qm->pdev->dev, "unknown error type\n"); + + if (qm->aeq_head == QM_Q_DEPTH - 1) { + aeqc->dw6 = aeqc->dw6 ^ QM_AEQC_PHASE_BIT; + aeqe = qm->aeqe.addr; + qm->aeq_head = 0; + } else { + aeqe++; + qm->aeq_head++; + } + + qm_db(qm, 0, QM_DOORBELL_CMD_AEQ, qm->aeq_head, 0); + } + + return IRQ_HANDLED; +} + +static irqreturn_t qm_abnormal_irq(int irq, void *data) +{ + const struct hisi_qm_hw_error *err = qm_hw_error; + struct hisi_qm *qm = data; + struct device *dev = &qm->pdev->dev; + u32 error_status, tmp; + + /* read err sts */ + tmp = readl(qm->io_base + QM_ABNORMAL_INT_STATUS); + error_status = qm->msi_mask & tmp; + + while (err->msg) { + if (err->int_msk & error_status) + dev_warn(dev, "%s [error status=0x%x] found\n", + err->msg, err->int_msk); + + err++; + } + + /* clear err sts */ + writel(error_status, qm->io_base + QM_ABNORMAL_INT_SOURCE); + + return IRQ_HANDLED; +} + +static int qm_irq_register(struct hisi_qm *qm) +{ + struct pci_dev *pdev = qm->pdev; + int ret; + + ret = request_threaded_irq(pci_irq_vector(pdev, 0), qm_irq, + qm_irq_thread, IRQF_SHARED, qm->dev_name, + qm); + if (ret) + return ret; + + if (qm->ver == QM_HW_V2) { + ret = request_irq(pci_irq_vector(pdev, 1), qm_aeq_irq, + IRQF_SHARED, qm->dev_name, qm); + if (ret) + goto err_aeq_irq; + + if (qm->fun_type == QM_HW_PF) { + ret = request_irq(pci_irq_vector(pdev, 3), + qm_abnormal_irq, IRQF_SHARED, + qm->dev_name, qm); + if (ret) + goto err_abonormal_irq; + } + } + + return 0; + +err_abonormal_irq: + free_irq(pci_irq_vector(pdev, 1), qm); +err_aeq_irq: + free_irq(pci_irq_vector(pdev, 0), qm); + return ret; +} + +static void qm_irq_unregister(struct hisi_qm *qm) +{ + struct pci_dev *pdev = qm->pdev; + + free_irq(pci_irq_vector(pdev, 0), qm); + + if (qm->ver == QM_HW_V2) { + free_irq(pci_irq_vector(pdev, 1), qm); + + if (qm->fun_type == QM_HW_PF) + free_irq(pci_irq_vector(pdev, 3), qm); + } +} + +static void qm_init_qp_status(struct hisi_qp *qp) +{ + struct hisi_qp_status *qp_status = &qp->qp_status; + + qp_status->sq_tail = 0; + qp_status->sq_head = 0; + qp_status->cq_head = 0; + qp_status->cqc_phase = 1; + qp_status->flags = 0; +} + +/* + * Allocate sq,cq,eq,aeq,sqc,cqc,eqc,aeqc buffer. + * + * Note: sq should 128 bypte alignment, 32 byte alignment for other queues and + * queue contexts. + */ +static int qm_init_q_buffer(struct device *dev, size_t size, + struct qm_dma_buffer *db) +{ + db->addr = dma_zalloc_coherent(dev, size, &db->dma, GFP_KERNEL); + if (!db->addr) + return -ENOMEM; + + db->size = size; + + return 0; +} + +static void qm_uninit_q_buffer(struct device *dev, struct qm_dma_buffer *db) +{ + dma_free_coherent(dev, db->size, db->addr, db->dma); + + db->size = 0; + db->addr = NULL; + db->dma = 0; +} + +static void qm_vft_data_cfg(struct hisi_qm *qm, enum vft_type type, u32 base, + u32 number) +{ + u64 tmp = 0; + + switch (type) { + case SQC_VFT: + switch (qm->ver) { + case QM_HW_V1: + tmp = QM_SQC_VFT_BUF_SIZE | + QM_SQC_VFT_SQC_SIZE | + QM_SQC_VFT_INDEX_NUMBER | + QM_SQC_VFT_VALID | + (u64)base << QM_SQC_VFT_START_SQN_SHIFT; + break; + case QM_HW_V2: + tmp = (u64)number << QM_SQC_VFT_SQN_SHIFT | + QM_SQC_VFT_VALID | + (u64)base << QM_SQC_VFT_START_SQN_SHIFT; + break; + } + break; + case CQC_VFT: + switch (qm->ver) { + case QM_HW_V1: + tmp = QM_CQC_VFT_BUF_SIZE | + QM_CQC_VFT_SQC_SIZE | + QM_CQC_VFT_INDEX_NUMBER | + QM_CQC_VFT_VALID; + break; + case QM_HW_V2: + tmp = QM_CQC_VFT_VALID; + break; + } + break; + } + + writel(lower_32_bits(tmp), qm->io_base + QM_VFT_CFG_DATA_L); + writel(upper_32_bits(tmp), qm->io_base + QM_VFT_CFG_DATA_H); +} + +static int qm_set_vft_common(struct hisi_qm *qm, enum vft_type type, + u32 fun_num, u32 base, u32 number) +{ + int val, ret; + + ret = readl_relaxed_poll_timeout(qm->io_base + QM_VFT_CFG_RDY, val, + val & BIT(0), 10, 1000); + if (ret) + return ret; + + writel(0x0, qm->io_base + QM_VFT_CFG_OP_WR); + writel(type, qm->io_base + QM_VFT_CFG_TYPE); + writel(fun_num, qm->io_base + QM_VFT_CFG_ADDRESS); + + qm_vft_data_cfg(qm, type, base, number); + + writel(0x0, qm->io_base + QM_VFT_CFG_RDY); + writel(0x1, qm->io_base + QM_VFT_CFG_OP_ENABLE); + + return readl_relaxed_poll_timeout(qm->io_base + QM_VFT_CFG_RDY, val, + val & BIT(0), 10, 1000); +} + +/* The config should be conducted after hisi_qm_mem_start() */ +static int qm_set_sqc_cqc_vft(struct hisi_qm *qm, u32 fun_num, u32 base, + u32 number) +{ + int ret, i; + + for (i = SQC_VFT; i <= CQC_VFT; i++) { + ret = qm_set_vft_common(qm, i, fun_num, base, number); + if (ret) + return ret; + } + + return 0; +} + +static int qm_get_vft_v2(struct hisi_qm *qm, u32 *base, u32 *number) +{ + u64 sqc_vft; + int ret; + + ret = qm_mb(qm, QM_MB_CMD_SQC_VFT_V2, 0, 0, 1, 0); + if (ret) + return ret; + + sqc_vft = readl(qm->io_base + QM_MB_CMD_DATA_ADDR_L) | + ((u64)readl(qm->io_base + QM_MB_CMD_DATA_ADDR_H) << 32); + *base = QM_SQC_VFT_BASE_MASK_V2 & (sqc_vft >> QM_SQC_VFT_BASE_SHIFT_V2); + *number = QM_SQC_VFT_NUM_MASK_v2 & (sqc_vft >> QM_SQC_VFT_NUM_SHIFT_V2); + + return 0; +} + +static int qm_init_qp_mem(struct hisi_qp *qp) +{ + struct hisi_qm *qm = qp->qm; + struct device *dev = &qm->pdev->dev; + + /* allocate sq and cq */ + return qm_init_q_buffer(dev, (qm->sqe_size + sizeof(struct qm_cqe)) * + QM_Q_DEPTH, &qp->scqe); +} + +static void qm_init_qp_sqc_cqc_mem(struct hisi_qp *qp) +{ + struct hisi_qm *qm = qp->qm; + int qp_id = qp->qp_id; + + qp->sqc.addr = qm->sqc.addr + qp_id * sizeof(struct qm_sqc); + qp->sqc.dma = qm->sqc.dma + qp_id * sizeof(struct qm_sqc); + qp->cqc.addr = qm->cqc.addr + qp_id * sizeof(struct qm_cqc); + qp->cqc.dma = qm->cqc.dma + qp_id * sizeof(struct qm_cqc); +} + +static void qm_uninit_qp_mem(struct hisi_qp *qp) +{ + struct device *dev = &qp->qm->pdev->dev; + + qm_uninit_q_buffer(dev, &qp->scqe); +} + +static void qm_uninit_qp_sqc_cqc_mem(struct hisi_qp *qp) +{ + qp->sqc.addr = NULL; + qp->sqc.dma = 0; + qp->cqc.addr = NULL; + qp->cqc.dma = 0; +} + +static int qm_start_qp(struct hisi_qp *qp, unsigned long arg) +{ + struct hisi_qm *qm = qp->qm; + int qp_id = qp->qp_id; + struct device *dev = &qm->pdev->dev; + enum qm_hw_ver ver = qm->ver; + struct qm_sqc *sqc; + struct qm_cqc *cqc; + int pasid = arg; + int ret; + + sqc = qp->sqc.addr; + INIT_QC_COMMON(sqc, qp->scqe.dma); + sqc->pasid = pasid; + if (ver == QM_HW_V1) { + sqc->dw3 = (0 << QM_SQ_HOP_NUM_SHIFT) | + (0 << QM_SQ_PAGE_SIZE_SHIFT) | + (0 << QM_SQ_BUF_SIZE_SHIFT) | + (ilog2(qm->sqe_size) << QM_SQ_SQE_SIZE_SHIFT); + sqc->w8 = QM_Q_DEPTH - 1; + } else if (ver == QM_HW_V2) { + sqc->dw3 = (QM_Q_DEPTH - 1) | + (ilog2(qm->sqe_size) << QM_SQ_SQE_SIZE_SHIFT); + sqc->w8 = 0; /* rand_qc */ + } + sqc->cq_num = qp_id; + sqc->w13 = 0 << QM_SQ_PRIORITY_SHIFT | + 1 << QM_SQ_ORDERS_SHIFT | + (qp->alg_type & QM_SQ_TYPE_MASK) << QM_SQ_TYPE_SHIFT; + + ret = qm_mb(qm, QM_MB_CMD_SQC, qp->sqc.dma, qp_id, 0, 0); + if (ret) + return ret; + + cqc = qp->cqc.addr; + INIT_QC_COMMON(cqc, qp->scqe.dma + qm->sqe_size * QM_Q_DEPTH); + if (ver == QM_HW_V1) { + cqc->dw3 = (0 << QM_CQ_HOP_NUM_SHIFT) | + (0 << QM_CQ_PAGE_SIZE_SHIFT) | + (0 << QM_CQ_BUF_SIZE_SHIFT) | + (4 << QM_CQ_SQE_SIZE_SHIFT); + cqc->w8 = QM_Q_DEPTH - 1; + } else if (ver == QM_HW_V2) { + cqc->pasid = pasid; + cqc->dw3 = (QM_Q_DEPTH - 1) | + (4 << QM_CQ_SQE_SIZE_SHIFT); + cqc->w8 = 0; /* rand_qc */ + } + cqc->dw6 = 1 << QM_CQ_PHASE_SHIFT | 1 << QM_CQ_FLAG_SHIFT; + + ret = qm_mb(qm, QM_MB_CMD_CQC, qp->cqc.dma, qp_id, 0, 0); + if (ret) + return ret; + + dev_dbg(dev, "QM qn=%u, sq_va=%p, sq_dma=%pad, sq_size=%lx, cq_va=%p, cq_dma=%pad, cq_size=%lx\n", + qp_id, qp->sqc.addr, &qp->sqc.dma, qm->sqe_size * QM_Q_DEPTH, + qp->cqc.addr, &qp->cqc.dma, sizeof(struct qm_cqe) * QM_Q_DEPTH); + + return qp_id; +} + +static struct hisi_qm *file_to_qm(struct debugfs_file *file) +{ + struct qm_debug *debug = file->debug; + + return container_of(debug, struct hisi_qm, debug); +} + +static u32 current_q_read(struct debugfs_file *file) +{ + struct hisi_qm *qm = file_to_qm(file); + + return readl(qm->io_base + QM_DFX_SQE_CNT_VF_SQN); +} + +static int current_q_write(struct debugfs_file *file, u32 val) +{ + struct hisi_qm *qm = file_to_qm(file); + + if (val >= qm->qp_num) + return -EINVAL; + + writel(val, qm->io_base + QM_DFX_SQE_CNT_VF_SQN); + writel(val, qm->io_base + QM_DFX_CQE_CNT_VF_CQN); + + return 0; +} + +static u32 clear_enable_read(struct debugfs_file *file) +{ + struct hisi_qm *qm = file_to_qm(file); + + return readl(qm->io_base + QM_DFX_CNT_CLR_CE); +} + +/* rd_clr_ctrl 1 enable read clear, otherwise 0 disable it */ +static int clear_enable_write(struct debugfs_file *file, u32 rd_clr_ctrl) +{ + struct hisi_qm *qm = file_to_qm(file); + + if (rd_clr_ctrl > 1) + return -EINVAL; + + writel(rd_clr_ctrl, qm->io_base + QM_DFX_CNT_CLR_CE); + + return 0; +} + +static ssize_t qm_debug_read(struct file *filp, char __user *buf, + size_t count, loff_t *pos) +{ + struct debugfs_file *file = filp->private_data; + enum qm_debug_file index = file->index; + char tbuf[20]; + u32 val; + int ret; + + mutex_lock(&file->lock); + switch (index) { + case CURRENT_Q: + val = current_q_read(file); + break; + case CLEAR_ENABLE: + val = clear_enable_read(file); + break; + default: + mutex_unlock(&file->lock); + return -EINVAL; + } + mutex_unlock(&file->lock); + ret = sprintf(tbuf, "%u\n", val); + return simple_read_from_buffer(buf, count, pos, tbuf, ret); +} + +static ssize_t qm_debug_write(struct file *filp, const char __user *buf, + size_t count, loff_t *pos) +{ + struct debugfs_file *file = filp->private_data; + enum qm_debug_file index = file->index; + unsigned long val; + char tbuf[20]; + int len, ret; + + if (*pos != 0) + return 0; + + if (count >= 20) + return -ENOSPC; + + len = simple_write_to_buffer(tbuf, 20 - 1, pos, buf, count); + if (len < 0) + return len; + + tbuf[len] = '\0'; + if (kstrtoul(tbuf, 0, &val)) + return -EFAULT; + + mutex_lock(&file->lock); + switch (index) { + case CURRENT_Q: + ret = current_q_write(file, val); + if (ret) + goto err_input; + break; + case CLEAR_ENABLE: + ret = clear_enable_write(file, val); + if (ret) + goto err_input; + break; + default: + ret = -EINVAL; + goto err_input; + } + mutex_unlock(&file->lock); + + return count; + +err_input: + mutex_unlock(&file->lock); + return ret; +} + +static const struct file_operations qm_debug_fops = { + .owner = THIS_MODULE, + .open = simple_open, + .read = qm_debug_read, + .write = qm_debug_write, +}; + +struct qm_dfx_registers { + char *reg_name; + u64 reg_offset; +}; + +static struct qm_dfx_registers qm_dfx_regs[] = { + {"QM_DFX_FUNS_ACTIVE_ST ", 0x200ull}, + {"QM_ECC_1BIT_CNT ", 0x104000ull}, + {"QM_ECC_1BIT_INF ", 0x104004ull}, + {"QM_ECC_MBIT_CNT ", 0x104008ull}, + {"QM_ECC_MBIT_INF ", 0x10400cull}, + {"QM_DFX_MB_CNT ", 0x104018ull}, + {"QM_DFX_DB_CNT ", 0x104028ull}, + {"QM_DFX_SQE_CNT ", 0x104038ull}, + {"QM_DFX_CQE_CNT ", 0x104048ull}, + {"QM_DFX_SEND_SQE_TO_ACC_CNT ", 0x104050ull}, + {"QM_DFX_WB_SQE_FROM_ACC_CNT ", 0x104058ull}, + {"QM_DFX_ACC_FINISH_CNT ", 0x104060ull}, + {"QM_DFX_ACC_RDY_VLD0 ", 0x1040a0ull}, + {"QM_DFX_ACC_RDY_VLD1 ", 0x1040a4ull}, + {"QM_DFX_AXI_RDY_VLD ", 0x1040a8ull}, + {"QM_DFX_CQE_ERR_CNT ", 0x1040b4ull}, + {"QM_DFX_FF_ST0 ", 0x1040c8ull}, + {"QM_DFX_FF_ST1 ", 0x1040ccull}, + {"QM_DFX_FF_ST2 ", 0x1040d0ull}, + {"QM_DFX_FF_ST3 ", 0x1040d4ull}, + {"QM_DFX_FF_ST4 ", 0x1040d8ull}, + {"QM_DFX_FF_ST5 ", 0x1040dcull}, + {"QM_DFX_FF_ST6 ", 0x1040e0ull}, + {"QM_IN_IDLE_ST ", 0x1040e4ull}, + { NULL, 0} +}; + +static struct qm_dfx_registers qm_vf_dfx_regs[] = { + {"QM_DFX_FUNS_ACTIVE_ST ", 0x200ull}, + { NULL, 0} +}; + +static int qm_regs_show(struct seq_file *s, void *unused) +{ + struct hisi_qm *qm = s->private; + struct qm_dfx_registers *regs; + u32 val; + + if (qm->fun_type == QM_HW_PF) + regs = qm_dfx_regs; + else + regs = qm_vf_dfx_regs; + + while (regs->reg_name) { + val = readl(qm->io_base + regs->reg_offset); + seq_printf(s, "%s: %16x\n", regs->reg_name, val); + regs++; + } + + return 0; +} + +static int qm_regs_open(struct inode *inode, struct file *file) +{ + return single_open(file, qm_regs_show, inode->i_private); +} + +static const struct file_operations qm_regs_fops = { + .owner = THIS_MODULE, + .open = qm_regs_open, + .read = seq_read, +}; + +static int qm_create_debugfs_file(struct hisi_qm *qm, enum qm_debug_file index) +{ + struct dentry *qm_d = qm->debug.qm_d, *tmp; + struct debugfs_file *file = qm->debug.files + index; + + tmp = debugfs_create_file(qm_debug_file_name[index], 0600, qm_d, file, + &qm_debug_fops); + if (!tmp) + return -ENOENT; + + file->index = index; + mutex_init(&file->lock); + file->debug = &qm->debug; + + return 0; +} + +static void qm_hw_error_init_v1(struct hisi_qm *qm, u32 ce, u32 nfe, u32 fe, + u32 msi) +{ + dev_info(&qm->pdev->dev, + "QM v%d does not support hw error handle\n", qm->ver); + + writel(0x1fff, qm->io_base + QM_ABNORMAL_INT_MASK); +} + +static void qm_hw_error_init_v2(struct hisi_qm *qm, u32 ce, u32 nfe, u32 fe, + u32 msi) +{ + u32 irq_enable = ce | nfe | fe | msi; + u32 irq_unmask = ~irq_enable; + + qm->error_mask = ce | nfe | fe; + qm->msi_mask = msi; + + /* configure error type */ + writel(ce, qm->io_base + QM_RAS_CE_ENABLE); + writel(0x1, qm->io_base + QM_RAS_CE_THRESHOLD); + writel(nfe, qm->io_base + QM_RAS_NFE_ENABLE); + writel(fe, qm->io_base + QM_RAS_FE_ENABLE); + + /* use RAS irq default, so only set QM_RAS_MSI_INT_SEL for MSI */ + writel(msi, qm->io_base + QM_RAS_MSI_INT_SEL); + + irq_unmask &= readl(qm->io_base + QM_ABNORMAL_INT_MASK); + writel(irq_unmask, qm->io_base + QM_ABNORMAL_INT_MASK); +} + +static void qm_log_hw_error(struct hisi_qm *qm, u32 error_status) +{ + const struct hisi_qm_hw_error *err = qm_hw_error; + struct device *dev = &qm->pdev->dev; + u32 reg_val, type, vf_num; + + while (err->msg) { + if (err->int_msk & error_status) + dev_warn(dev, "%s [error status=0x%x] found\n", + err->msg, err->int_msk); + + if (error_status & QM_DB_TIMEOUT) { + reg_val = readl(qm->io_base + QM_ABNORMAL_INF01); + type = (reg_val & QM_DB_TIMEOUT_TYPE) >> 6; + vf_num = reg_val & QM_DB_TIMEOUT_VF; + dev_warn(dev, "qm %s doorbell timeout in function %u\n", + qm_db_timeout[type], vf_num); + } + + if (error_status & QM_OF_FIFO_OF) { + reg_val = readl(qm->io_base + QM_ABNORMAL_INF00); + type = (reg_val & QM_FIFO_OVERFLOW_TYPE) >> 6; + vf_num = reg_val & QM_FIFO_OVERFLOW_VF; + dev_warn(dev, "qm %s fifo overflow in function %u\n", + qm_fifo_overflow[type], vf_num); + } + + err++; + } +} + +static pci_ers_result_t qm_hw_error_handle_v2(struct hisi_qm *qm) +{ + u32 error_status, tmp; + + /* read err sts */ + tmp = readl(qm->io_base + QM_ABNORMAL_INT_STATUS); + error_status = qm->error_mask & tmp; + + if (error_status) { + qm_log_hw_error(qm, error_status); + + /* clear err sts */ + writel(error_status, qm->io_base + QM_ABNORMAL_INT_SOURCE); + + return PCI_ERS_RESULT_NEED_RESET; + } + + return PCI_ERS_RESULT_NONE; +} + +static const struct hisi_qm_hw_ops qm_hw_ops_v1 = { + .set_vft = qm_set_sqc_cqc_vft, + .qm_start_qp = qm_start_qp, + .qm_db = qm_db_v1, + .get_irq_num = qm_get_irq_num_v1, + .hw_error_init = qm_hw_error_init_v1, +}; + +static const struct hisi_qm_hw_ops qm_hw_ops_v2 = { + .set_vft = qm_set_sqc_cqc_vft, + .get_vft = qm_get_vft_v2, + .qm_start_qp = qm_start_qp, + .qm_db = qm_db_v2, + .get_irq_num = qm_get_irq_num_v2, + .hw_error_init = qm_hw_error_init_v2, + .hw_error_handle = qm_hw_error_handle_v2, +}; + +static void *qm_get_avail_sqe(struct hisi_qp *qp) +{ + struct hisi_qp_status *qp_status = &qp->qp_status; + void *sq_base = qp->scqe.addr; + u16 sq_tail = qp_status->sq_tail; + + if (unlikely(test_bit(QP_FULL, &qp->qp_status.flags))) + return NULL; + + return sq_base + sq_tail * qp->qm->sqe_size; +} + +/** + * hisi_qm_create_qp() - Create a queue pair from qm. + * @qm: The qm we create a qp from. + * @alg_type: Accelerator specific algorithm type in sqc. + * + * return created qp, -EBUSY if all qps in qm allocated, -ENOMEM if allocating + * qp memory fails. + */ +struct hisi_qp *hisi_qm_create_qp(struct hisi_qm *qm, u8 alg_type) +{ + struct hisi_qp *qp; + struct hisi_qp *ret; + int qp_id, r_qp_mem; + + qp = kzalloc(sizeof(*qp), GFP_KERNEL); + if (!qp) + return ERR_PTR(-ENOMEM); + + write_lock(&qm->qps_lock); + + qp_id = find_first_zero_bit(qm->qp_bitmap, qm->qp_num); + if (qp_id >= qm->qp_num) { + write_unlock(&qm->qps_lock); + dev_info(&qm->pdev->dev, "QM all queues are busy!\n"); + ret = ERR_PTR(-EBUSY); + goto err_free_qp; + } + set_bit(qp_id, qm->qp_bitmap); + qm->qp_array[qp_id] = qp; + + write_unlock(&qm->qps_lock); + + qp->qm = qm; + r_qp_mem = qm_init_qp_mem(qp); + if (r_qp_mem) { + ret = ERR_PTR(r_qp_mem); + goto err_clear_bit; + } + + qp->qp_id = qp_id; + qp->alg_type = alg_type; + qm_init_qp_status(qp); + qm_init_qp_sqc_cqc_mem(qp); + init_completion(&qp->completion); + + return qp; + +err_clear_bit: + write_lock(&qm->qps_lock); + qm->qp_array[qp_id] = NULL; + clear_bit(qp_id, qm->qp_bitmap); + write_unlock(&qm->qps_lock); +err_free_qp: + kfree(qp); + return ret; +} +EXPORT_SYMBOL_GPL(hisi_qm_create_qp); + +/** + * hisi_qm_release_qp() - Release a qp back to its qm. + * @qp: The qp we want to release. + * + * This function releases the resource of a qp. + */ +void hisi_qm_release_qp(struct hisi_qp *qp) +{ + struct hisi_qm *qm = qp->qm; + + qm_uninit_qp_sqc_cqc_mem(qp); + qm_uninit_qp_mem(qp); + + write_lock(&qm->qps_lock); + qm->qp_array[qp->qp_id] = NULL; + clear_bit(qp->qp_id, qm->qp_bitmap); + write_unlock(&qm->qps_lock); + + kfree(qp); +} +EXPORT_SYMBOL_GPL(hisi_qm_release_qp); + +/** + * hisi_qm_start_qp() - Start a qp into running. + * @qp: The qp we want to start to run. + * @arg: Accelerator specific argument. + * + * After this function, qp can receive request from user. Return qp_id if + * successful, Return -EBUSY if failed. + */ +int hisi_qm_start_qp(struct hisi_qp *qp, unsigned long arg) +{ + struct hisi_qm *qm = qp->qm; + + return qm->ops->qm_start_qp(qp, arg); +} +EXPORT_SYMBOL_GPL(hisi_qm_start_qp); + +/** + * hisi_qm_stop_qp() - Stop a qp in qm. + * @qp: The qp we want to stop. + * + * This function is reverse of hisi_qm_start_qp. Return 0 if successful, + * return -EBUSY if stopping failed as there are tasks remaining in hardware. + */ +int hisi_qm_stop_qp(struct hisi_qp *qp) +{ + struct device *dev = &qp->qm->pdev->dev; + int i = 0; + + while (atomic_read(&qp->qp_status.used)) { + i++; + msleep(5); + if (i == 10) { + dev_err(dev, "Hardware unknown error!\n"); + return -EBUSY; + } + } + + if (test_and_set_bit(QP_STOP, &qp->qp_status.flags)) { + dev_warn(dev, "Failed to stop qp%u!", qp->qp_id); + return -EPERM; + } + + return 0; +} +EXPORT_SYMBOL_GPL(hisi_qm_stop_qp); + +/** + * hisi_qp_send() - Queue up a task in the hardware queue. + * @qp: The qp in which to put the message. + * @msg: The message. + * + * This function will return -EBUSY if qp is currently full, and -EAGAIN + * if qp related qm is resetting. + */ +int hisi_qp_send(struct hisi_qp *qp, void *msg) +{ + struct hisi_qp_status *qp_status = &qp->qp_status; + u16 sq_tail = qp_status->sq_tail; + u16 sq_tail_next = (sq_tail + 1) % QM_Q_DEPTH; + void *sqe = qm_get_avail_sqe(qp); + + if (unlikely(test_bit(QP_STOP, &qp->qp_status.flags) || + test_bit(QM_RESET, &qp->qm->flags))) { + dev_info(&qp->qm->pdev->dev, "QM resetting...\n"); + return -EAGAIN; + } + + if (!sqe) + return -EBUSY; + + memcpy(sqe, msg, qp->qm->sqe_size); + + qm_db(qp->qm, qp->qp_id, QM_DOORBELL_CMD_SQ, sq_tail_next, 0); + atomic_inc(&qp->qp_status.used); + + qp_status->sq_tail = sq_tail_next; + if (qp_status->sq_tail == qp_status->sq_head) + set_bit(QP_FULL, &qp->qp_status.flags); + + return 0; +} +EXPORT_SYMBOL_GPL(hisi_qp_send); + +/** + * hisi_qp_wait() - Wait a task in qp to finish. + * @qp: The qp which will wait. + * + * This function will block and wait task finish in qp, or return -ETIME for + * timeout. + * + * This function should be called after hisi_qp_send. + */ +int hisi_qp_wait(struct hisi_qp *qp) +{ + if (wait_for_completion_timeout(&qp->completion, + msecs_to_jiffies(10)) == 0) { + atomic_dec(&qp->qp_status.used); + dev_err(&qp->qm->pdev->dev, "QM task timeout\n"); + return -ETIME; + } + + return 0; +} +EXPORT_SYMBOL_GPL(hisi_qp_wait); + +/** + * hisi_qm_mem_init() - Allocate qm related memory. + * @qm: The qm which we allocate memory for. + * + * Return 0 if successful, return -ENOMEM if allocating failed. + */ +int hisi_qm_mem_init(struct hisi_qm *qm) +{ + struct device *dev = &qm->pdev->dev; + int ret; + + ret = qm_init_q_buffer(dev, sizeof(struct qm_eqc), &qm->eqc); + if (ret) + return ret; + + ret = qm_init_q_buffer(dev, sizeof(struct qm_eqe) * QM_Q_DEPTH, + &qm->eqe); + if (ret) + goto err_free_eqc; + + ret = qm_init_q_buffer(dev, sizeof(struct qm_aeqc), &qm->aeqc); + if (ret) + goto err_free_eqe; + + ret = qm_init_q_buffer(dev, sizeof(struct qm_aeqe) * QM_Q_DEPTH, + &qm->aeqe); + if (ret) + goto err_free_aeqc; + + qm->qp_bitmap = bitmap_zalloc(qm->qp_num, GFP_KERNEL); + if (!qm->qp_bitmap) { + ret = -ENOMEM; + goto err_free_aeqe; + } + + qm->qp_array = kcalloc(qm->qp_num, sizeof(struct hisi_qp *), + GFP_KERNEL); + if (!qm->qp_array) { + ret = -ENOMEM; + goto err_free_bitmap; + } + + ret = qm_init_q_buffer(dev, sizeof(struct qm_sqc) * qm->qp_num, + &qm->sqc); + if (ret) + goto err_free_qp_array; + + ret = qm_init_q_buffer(dev, sizeof(struct qm_cqc) * qm->qp_num, + &qm->cqc); + if (ret) + goto err_free_sqc; + + return 0; + +err_free_sqc: + qm_uninit_q_buffer(dev, &qm->sqc); +err_free_qp_array: + kfree(qm->qp_array); +err_free_bitmap: + bitmap_free(qm->qp_bitmap); +err_free_aeqe: + qm_uninit_q_buffer(dev, &qm->aeqe); +err_free_aeqc: + qm_uninit_q_buffer(dev, &qm->aeqc); +err_free_eqe: + qm_uninit_q_buffer(dev, &qm->eqe); +err_free_eqc: + qm_uninit_q_buffer(dev, &qm->eqc); + return ret; +} +EXPORT_SYMBOL_GPL(hisi_qm_mem_init); + +/** + * hisi_qm_mem_uninit() - Uninit qm related memory. + * @qm: The qm which we uninit memory for. + * + * This function is reverse of hisi_qm_mem_init. + */ +void hisi_qm_mem_uninit(struct hisi_qm *qm) +{ + struct device *dev = &qm->pdev->dev; + + qm_uninit_q_buffer(dev, &qm->cqc); + qm_uninit_q_buffer(dev, &qm->sqc); + kfree(qm->qp_array); + bitmap_free(qm->qp_bitmap); + qm_uninit_q_buffer(dev, &qm->aeqe); + qm_uninit_q_buffer(dev, &qm->aeqc); + qm_uninit_q_buffer(dev, &qm->eqe); + qm_uninit_q_buffer(dev, &qm->eqc); +} +EXPORT_SYMBOL_GPL(hisi_qm_mem_uninit); + +/** + * hisi_qm_init() - Initialize configures about qm. + * @qm: The qm needed init. + * + * This function init qm, then we can call hisi_qm_mem_init and hisi_qm_start + * to put qm into work. + */ +int hisi_qm_init(struct hisi_qm *qm) +{ + struct pci_dev *pdev = qm->pdev; + struct device *dev = &pdev->dev; + unsigned int num_vec = 0; + int ret; + + switch (qm->ver) { + case QM_HW_V1: + qm->ops = &qm_hw_ops_v1; + break; + case QM_HW_V2: + qm->ops = &qm_hw_ops_v2; + break; + default: + return -EINVAL; + } + + ret = pci_enable_device_mem(pdev); + if (ret < 0) { + dev_err(&pdev->dev, "Failed to enable device mem!\n"); + return ret; + } + + ret = pci_request_mem_regions(pdev, qm->dev_name); + if (ret < 0) { + dev_err(&pdev->dev, "Failed to request mem regions!\n"); + goto err_disable_pcidev; + } + + qm->io_base = ioremap(pci_resource_start(pdev, 2), + pci_resource_len(qm->pdev, 2)); + if (!qm->io_base) { + ret = -EIO; + goto err_release_mem_regions; + } + + ret = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(64)); + if (ret < 0) + goto err_iounmap; + pci_set_master(pdev); + + num_vec = qm->ops->get_irq_num(qm); + ret = pci_alloc_irq_vectors(pdev, num_vec, num_vec, PCI_IRQ_MSI); + if (ret < 0) { + dev_err(dev, "Failed to enable MSI vectors!\n"); + goto err_iounmap; + } + + ret = qm_irq_register(qm); + if (ret) + goto err_free_irq_vectors; + + qm->eq_head = 0; + mutex_init(&qm->mailbox_lock); + rwlock_init(&qm->qps_lock); + + return 0; + +err_free_irq_vectors: + pci_free_irq_vectors(pdev); +err_iounmap: + iounmap(qm->io_base); +err_release_mem_regions: + pci_release_mem_regions(pdev); +err_disable_pcidev: + pci_disable_device(pdev); + + return ret; +} +EXPORT_SYMBOL_GPL(hisi_qm_init); + +/** + * hisi_qm_uninit() - Uninitialize qm. + * @qm: The qm needed uninit. + * + * This function uninits qm related device resources. + */ +void hisi_qm_uninit(struct hisi_qm *qm) +{ + struct pci_dev *pdev = qm->pdev; + + qm_irq_unregister(qm); + pci_free_irq_vectors(pdev); + iounmap(qm->io_base); + pci_release_mem_regions(pdev); + pci_disable_device(pdev); +} +EXPORT_SYMBOL_GPL(hisi_qm_uninit); + +/** + * hisi_qm_start() - Let qm start to work. + * @qm: The qm which will be started. + * + * This function starts a qm, then we can allocate qp from this qm. + */ +int hisi_qm_start(struct hisi_qm *qm) +{ + struct pci_dev *pdev = qm->pdev; + struct device *dev = &pdev->dev; + struct qm_eqc *eqc; + struct qm_aeqc *aeqc; + int ret; + + if (qm->qp_num == 0) { + dev_info(dev, "Allocated zero qp for this qm!\n"); + return 0; + } + + if (qm->fun_type == QM_HW_PF) { + ret = qm->ops->set_vft(qm, 0, qm->qp_base, qm->qp_num); + if (ret) + return ret; + } + + eqc = qm->eqc.addr; + eqc->base_l = lower_32_bits(qm->eqe.dma); + eqc->base_h = upper_32_bits(qm->eqe.dma); + eqc->dw3 = 2 << QM_EQC_EQE_SHIFT; + eqc->dw6 = (QM_Q_DEPTH - 1) | (1 << QM_EQC_PHASE_SHIFT); + ret = qm_mb(qm, QM_MB_CMD_EQC, qm->eqc.dma, 0, 0, 0); + if (ret) + return ret; + + aeqc = qm->aeqc.addr; + aeqc->base_l = lower_32_bits(qm->aeqe.dma); + aeqc->base_h = upper_32_bits(qm->aeqe.dma); + aeqc->dw3 = 2 << QM_EQC_EQE_SHIFT; + aeqc->dw6 = (QM_Q_DEPTH - 1) | (1 << QM_EQC_PHASE_SHIFT); + ret = qm_mb(qm, QM_MB_CMD_AEQC, qm->aeqc.dma, 0, 0, 0); + if (ret) + return ret; + + ret = qm_mb(qm, QM_MB_CMD_SQC_BT, qm->sqc.dma, 0, 0, 0); + if (ret) + return ret; + + ret = qm_mb(qm, QM_MB_CMD_CQC_BT, qm->cqc.dma, 0, 0, 0); + if (ret) + return ret; + + /* Unmask eq irq */ + writel(0x0, qm->io_base + QM_VF_EQ_INT_MASK); + + return 0; +} +EXPORT_SYMBOL_GPL(hisi_qm_start); + +/** + * hisi_qm_stop() - Stop a qm. + * @qm: The qm which will be stopped. + * + * This function stops qm and its qps, then qm can not accept request. + * Related resources are not released at this state, we can use hisi_qm_start + * to let qm start again. + */ +int hisi_qm_stop(struct hisi_qm *qm) +{ + struct device *dev = &qm->pdev->dev; + struct hisi_qp *qp; + int ret, i; + + /* Mask eq irq */ + writel(0x1, qm->io_base + QM_VF_EQ_INT_MASK); + + /* Stop all qps belong to this qm */ + for (i = 0; i < qm->qp_num; i++) { + qp = qm->qp_array[i]; + if (qp) { + ret = hisi_qm_stop_qp(qp); + if (ret < 0) { + dev_err(dev, "Failed to stop qp%d!\n", i); + return -EBUSY; + } + } + } + + if (qm->fun_type == QM_HW_PF) { + ret = qm->ops->set_vft(qm, 0, 0, 0); + if (ret) { + dev_err(dev, "Failed to set vft!\n"); + return -EBUSY; + } + } + + return 0; +} +EXPORT_SYMBOL_GPL(hisi_qm_stop); + +/** + * hisi_qm_mem_start() - Start qm's internal memory. + * @qm: The qm which memory will be started. + * + * Put qm memory into active, so that other configs become available + */ +int hisi_qm_mem_start(struct hisi_qm *qm) +{ + u32 val; + + writel(0x1, qm->io_base + QM_MEM_START_INIT); + return readl_relaxed_poll_timeout(qm->io_base + QM_MEM_INIT_DONE, val, + val & BIT(0), 10, 1000); +} +EXPORT_SYMBOL_GPL(hisi_qm_mem_start); + +/** + * hisi_qm_get_vft() - Get vft from a qm. + * @qm: The qm we want to get its vft. + * @base: The base number of queue in vft. + * @number: The number of queues in vft. + * + * We can allocate multiple queues to a qm by configuring virtual function + * table. We get related configures by this function. Normally, we call this + * function in VF driver to get the queue information. + * + * qm hw v1 does not support this interface. + */ +int hisi_qm_get_vft(struct hisi_qm *qm, u32 *base, u32 *number) +{ + if (!base || !number) + return -EINVAL; + + if (!qm->ops->get_vft) { + dev_err(&qm->pdev->dev, "Don't support vft read!\n"); + return -EINVAL; + } + + return qm->ops->get_vft(qm, base, number); +} +EXPORT_SYMBOL_GPL(hisi_qm_get_vft); + +/** + * hisi_qm_set_vft() - Set "virtual function table" for a qm. + * @fun_num: Number of operated function. + * @qm: The qm in which to set vft, alway in a PF. + * @base: The base number of queue in vft. + * @number: The number of queues in vft. + * + * This function is alway called in PF driver, it is used to assign queues + * among PF and VFs. + * + * Assign queues A~B to PF: hisi_qm_set_vft(qm, 0, A, B - A + 1) + * Assign queues A~B to VF: hisi_qm_set_vft(qm, 2, A, B - A + 1) + * (VF function number 0x2) + */ +int hisi_qm_set_vft(struct hisi_qm *qm, u32 fun_num, u32 base, + u32 number) +{ + return qm->ops->set_vft(qm, fun_num, base, number); +} +EXPORT_SYMBOL_GPL(hisi_qm_set_vft); + +/** + * hisi_qm_debug_init() - Initialize qm related debugfs files. + * @qm: The qm for which we want to add debugfs files. + * + * Create qm related debugfs files. + */ +int hisi_qm_debug_init(struct hisi_qm *qm) +{ + struct dentry *qm_d, *qm_regs; + int i, ret; + + qm_d = debugfs_create_dir("qm", qm->debug.debug_root); + if (!qm_d) + return -ENOENT; + qm->debug.qm_d = qm_d; + + /* only show this in PF */ + if (qm->fun_type == QM_HW_PF) + for (i = CURRENT_Q; i < DEBUG_FILE_NUM; i++) + if (qm_create_debugfs_file(qm, i)) { + ret = -ENOENT; + goto failed_to_create; + } + + qm_regs = debugfs_create_file("qm_regs", 0444, qm->debug.qm_d, qm, + &qm_regs_fops); + if (!qm_regs) { + ret = -ENOENT; + goto failed_to_create; + } + + return 0; + +failed_to_create: + debugfs_remove_recursive(qm_d); + return ret; +} +EXPORT_SYMBOL_GPL(hisi_qm_debug_init); + +/** + * hisi_qm_hw_error_init() - Configure qm hardware error report method. + * @qm: The qm which we want to configure. + * @ce: Correctable error configure. + * @nfe: Non-fatal error configure. + * @fe: Fatal error configure. + * @msi: Error reported by message signal interrupt. + * + * Hardware errors of qm can be reported either by RAS interrupts which will + * be handled by UEFI and then PCIe AER or by device MSI. User can configure + * each error to use either of above two methods. For RAS interrupts, we can + * configure an error as one of correctable error, non-fatal error or + * fatal error. + * + * Bits indicating errors can be configured to ce, nfe, fe and msi to enable + * related report methods. Error report will be masked if related error bit + * does not configure. + */ +void hisi_qm_hw_error_init(struct hisi_qm *qm, u32 ce, u32 nfe, u32 fe, + u32 msi) +{ + if (!qm->ops->hw_error_init) { + dev_err(&qm->pdev->dev, "QM version %d doesn't support hw error handling!\n", + qm->ver); + return; + } + + return qm->ops->hw_error_init(qm, ce, nfe, fe, msi); +} +EXPORT_SYMBOL_GPL(hisi_qm_hw_error_init); + +/** + * hisi_qm_hw_error_handle() - Handle qm non-fatal hardware errors. + * @qm: The qm which has non-fatal hardware errors. + * + * Accelerators use this function to handle qm non-fatal hardware errors. + */ +int hisi_qm_hw_error_handle(struct hisi_qm *qm) +{ + if (!qm->ops->hw_error_handle) { + dev_err(&qm->pdev->dev, "QM version %d doesn't support hw error report!\n", + qm->ver); + return PCI_ERS_RESULT_NONE; + } + + return qm->ops->hw_error_handle(qm); +} +EXPORT_SYMBOL_GPL(hisi_qm_hw_error_handle); + +/** + * hisi_qm_clear_queues() - Clear memory of queues in a qm. + * @qm: The qm which memory needs clear. + * + * This function clears all queues memory in a qm. Reset of accelerator can + * use this to clear queues. + */ +void hisi_qm_clear_queues(struct hisi_qm *qm) +{ + struct hisi_qp **qp = qm->qp_array; + struct hisi_qp *tmp; + int i; + + for (i = 0; i < qm->qp_num; i++, qp++) { + tmp = *qp; + if (!tmp) + continue; + + memset(tmp->scqe.addr, 0, tmp->scqe.size); + memset(&tmp->qp_status, 0, sizeof(tmp->qp_status)); + } + memset(qm->eqe.addr, 0, qm->eqe.size); + memset(qm->aeqe.addr, 0, qm->aeqe.size); + + qm->flags = 0; + qm->eq_head = 0; + qm->aeq_head = 0; +} +EXPORT_SYMBOL_GPL(hisi_qm_clear_queues); + +/** + * hisi_qm_get_hw_version() - Get hardware version of a qm. + * @qm: The qm which hardware version we want to get. + * + * This function gets the hardware version of a qm. Return -EINVAL if the + * hardware version is not supported. + */ +enum qm_hw_ver hisi_qm_get_hw_version(struct hisi_qm *qm) +{ + switch (qm->pdev->revision) { + case 0x20: + return QM_HW_V1; + case 0x21: + return QM_HW_V2; + default: + return -EINVAL; + } +} +EXPORT_SYMBOL_GPL(hisi_qm_get_hw_version); + +MODULE_LICENSE("GPL v2"); +MODULE_AUTHOR("Zhou Wang "); +MODULE_DESCRIPTION("HiSilicon Accelerator queue manager driver"); diff --git a/drivers/crypto/hisilicon/qm.h b/drivers/crypto/hisilicon/qm.h new file mode 100644 index 0000000..1e63ff3 --- /dev/null +++ b/drivers/crypto/hisilicon/qm.h @@ -0,0 +1,176 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2018 Hisilicon Limited. */ +#ifndef HISI_ACC_QM_H +#define HISI_ACC_QM_H + +#include +#include +#include +#include +#include + +/* default queue depth for sq/cq/eq */ +#define QM_Q_DEPTH 1024UL + +/* qm user domain */ +#define QM_ARUSER_M_CFG_1 0x100088 +#define QM_ARUSER_M_CFG_ENABLE 0x100090 +#define QM_AWUSER_M_CFG_1 0x100098 +#define QM_AWUSER_M_CFG_ENABLE 0x1000a0 +#define QM_WUSER_M_CFG_ENABLE 0x1000a8 + +/* qm cache */ +#define QM_CACHE_CTL 0x100050 +#define QM_AXI_M_CFG 0x1000ac +#define QM_AXI_M_CFG_ENABLE 0x1000b0 +#define QM_PEH_AXUSER_CFG 0x1000cc +#define QM_PEH_AXUSER_CFG_ENABLE 0x1000d0 + +#define QM_DFX_MB_CNT_VF 0x104010 +#define QM_DFX_DB_CNT_VF 0x104020 + +#define QM_AXI_RRESP BIT(0) +#define QM_AXI_BRESP BIT(1) +#define QM_ECC_MBIT BIT(2) +#define QM_ECC_1BIT BIT(3) +#define QM_ACC_GET_TASK_TIMEOUT BIT(4) +#define QM_ACC_DO_TASK_TIMEOUT BIT(5) +#define QM_ACC_WB_NOT_READY_TIMEOUT BIT(6) +#define QM_SQ_CQ_VF_INVALID BIT(7) +#define QM_CQ_VF_INVALID BIT(8) +#define QM_SQ_VF_INVALID BIT(9) +#define QM_DB_TIMEOUT BIT(10) +#define QM_OF_FIFO_OF BIT(11) +#define QM_DB_RANDOM_INVALID BIT(12) + +#define QM_BASE_NFE (QM_AXI_RRESP | QM_AXI_BRESP | QM_ECC_MBIT | \ + QM_ACC_GET_TASK_TIMEOUT | QM_ACC_DO_TASK_TIMEOUT | \ + QM_DB_TIMEOUT | QM_OF_FIFO_OF) +#define QM_BASE_CE QM_ECC_1BIT + +enum qm_state { + QM_RESET, +}; + +enum qp_state { + QP_STOP, + QP_FULL, +}; + +enum qm_hw_ver { + QM_HW_V1 = 1, + QM_HW_V2, +}; + +enum qm_fun_type { + QM_HW_PF, + QM_HW_VF, +}; + +enum qm_debug_file { + CURRENT_Q, + CLEAR_ENABLE, + DEBUG_FILE_NUM, +}; + +struct qm_dma_buffer { + int size; + void *addr; + dma_addr_t dma; +}; + +struct debugfs_file { + enum qm_debug_file index; + struct mutex lock; + struct qm_debug *debug; +}; + +struct qm_debug { + struct dentry *debug_root; + struct dentry *qm_d; + struct debugfs_file files[DEBUG_FILE_NUM]; +}; + +struct hisi_qm { + enum qm_hw_ver ver; + enum qm_fun_type fun_type; + const char *dev_name; + struct pci_dev *pdev; + void __iomem *io_base; + u32 sqe_size; + u32 qp_base; + u32 qp_num; + unsigned long flags; + + struct qm_dma_buffer sqc, cqc, eqc, eqe, aeqc, aeqe; + + u32 eq_head; + u32 aeq_head; + + rwlock_t qps_lock; + unsigned long *qp_bitmap; + struct hisi_qp **qp_array; + + struct mutex mailbox_lock; + + const struct hisi_qm_hw_ops *ops; + + struct qm_debug debug; + + u32 error_mask; + u32 msi_mask; +}; + +struct hisi_qp_status { + atomic_t used; + u16 sq_tail; + u16 sq_head; + u16 cq_head; + bool cqc_phase; + unsigned long flags; +}; + +struct hisi_qp_ops { + int (*fill_sqe)(void *sqe, void *q_parm, void *d_parm); +}; + +struct hisi_qp { + u32 qp_id; + u8 alg_type; + u8 req_type; + + struct qm_dma_buffer sqc; + struct qm_dma_buffer cqc; + struct qm_dma_buffer scqe; + + struct hisi_qp_status qp_status; + struct completion completion; + struct hisi_qp_ops *hw_ops; + void *qp_ctx; + void (*req_cb)(struct hisi_qp *qp, void *data); + + struct hisi_qm *qm; +}; + +int hisi_qm_init(struct hisi_qm *qm); +void hisi_qm_uninit(struct hisi_qm *qm); +int hisi_qm_mem_init(struct hisi_qm *qm); +void hisi_qm_mem_uninit(struct hisi_qm *qm); +int hisi_qm_start(struct hisi_qm *qm); +int hisi_qm_stop(struct hisi_qm *qm); +int hisi_qm_mem_start(struct hisi_qm *qm); +struct hisi_qp *hisi_qm_create_qp(struct hisi_qm *qm, u8 alg_type); +int hisi_qm_start_qp(struct hisi_qp *qp, unsigned long arg); +int hisi_qm_stop_qp(struct hisi_qp *qp); +void hisi_qm_release_qp(struct hisi_qp *qp); +int hisi_qp_send(struct hisi_qp *qp, void *msg); +int hisi_qp_wait(struct hisi_qp *qp); +int hisi_qm_get_vft(struct hisi_qm *qm, u32 *base, u32 *number); +int hisi_qm_set_vft(struct hisi_qm *qm, u32 fun_num, u32 base, u32 number); +int hisi_qm_debug_init(struct hisi_qm *qm); +void hisi_qm_hw_error_init(struct hisi_qm *qm, u32 ce, u32 nfe, u32 fe, + u32 msi); +int hisi_qm_hw_error_handle(struct hisi_qm *qm); +void hisi_qm_clear_queues(struct hisi_qm *qm); +enum qm_hw_ver hisi_qm_get_hw_version(struct hisi_qm *qm); +#endif From patchwork Thu Dec 13 11:22:10 2018 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Zhou Wang X-Patchwork-Id: 153631 Delivered-To: patch@linaro.org Received: by 2002:a2e:299d:0:0:0:0:0 with SMTP id p29-v6csp680637ljp; Thu, 13 Dec 2018 03:22:18 -0800 (PST) X-Google-Smtp-Source: AFSGD/VRn0sG3C1SlhLA1z8igpcRSvA6Ak8YHB5vjAcEhv/v4ol9eMhtUBpzQy0maKGcWoYlPK1l X-Received: by 2002:a63:2406:: with SMTP id k6mr20856512pgk.229.1544700138527; Thu, 13 Dec 2018 03:22:18 -0800 (PST) ARC-Seal: i=1; a=rsa-sha256; t=1544700138; cv=none; d=google.com; s=arc-20160816; b=EgmJ6ObPyN4vJV8SjzCC8VxMY7UkSQw2TqiIvEAAFmYXFBdtQPtH6RnYo/mMVSjjXs YhUHW+KEZ2Xd038WGDLM3JUh6rzFrQAhiDFlj7VD/el5VyLR2xfOrurJiMVQGIX8ZSXW aQ40pvTz/4MKpxyS77Gcy1VTMWBMZlSGpzNAeSQI/zH3b8I4egNK+AxK2xonis7INeNV thtD7Ze2CgdD3YuRk/uD+/7vq87gtJvbJ46antqFATLVArhL7qTiiyI/9L9qYKznUdoy gtNJaD+sgWkEcC5ikio9BO24gnvUNe9/mDeEhPm04auaQ9pXYLpbubkfPdudDudgJlF9 OZXA== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=arc-20160816; h=list-id:precedence:sender:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from; bh=Les6ozK+j1BtH3B+r8JvdIA17U3vPf/7Dbjc2t5CWkQ=; b=SXahpQnf7ph1JHfGFnnp2QWKDJCD+O0tevqZqnZ0unFMht8q+HyEfbdEdaWw1/7+2Q bxy6ckhOoYNeo93+iLvdXoQsg02GBDStm2z+bPvMictyYOcRQa4LSMeXTlkgfqKVBJ4f m3POW8VziLhq+ySN9a5S/edRX177U5xa4+vwWEO+ePVaqubtdKXgmWycut1+vvTyPtIc qukd2E0/oyum66vX9M+dyGVUxPSCu9b32PqlV+T8n0Lg0kYptWfE2b9/nuT0svCcrpoL W+vh6xlzIpt4sIpJXRlCK2aLstBAppYL+3UC1q93UAQr4Z6BRFKCLwRds3leQ/sEBKON pvzg== ARC-Authentication-Results: i=1; mx.google.com; spf=pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) smtp.mailfrom=linux-kernel-owner@vger.kernel.org Return-Path: Received: from vger.kernel.org (vger.kernel.org. [209.132.180.67]) by mx.google.com with ESMTP id z4si1332478pgl.16.2018.12.13.03.22.18; Thu, 13 Dec 2018 03:22:18 -0800 (PST) Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67; Authentication-Results: mx.google.com; spf=pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) smtp.mailfrom=linux-kernel-owner@vger.kernel.org Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1728810AbeLMLWR (ORCPT + 31 others); Thu, 13 Dec 2018 06:22:17 -0500 Received: from szxga06-in.huawei.com ([45.249.212.32]:50928 "EHLO huawei.com" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1728674AbeLMLWQ (ORCPT ); Thu, 13 Dec 2018 06:22:16 -0500 Received: from DGGEMS413-HUB.china.huawei.com (unknown [172.30.72.60]) by Forcepoint Email with ESMTP id 2E8E88D107A14; Thu, 13 Dec 2018 19:22:11 +0800 (CST) Received: from localhost.localdomain (10.67.212.75) by DGGEMS413-HUB.china.huawei.com (10.3.19.213) with Microsoft SMTP Server id 14.3.408.0; Thu, 13 Dec 2018 19:22:05 +0800 From: Zhou Wang To: Herbert Xu , "David S . Miller" , CC: , , Zhou Wang , Shiju Jose , Kenneth Lee , Hao Fang Subject: [PATCH RFC 3/4] crypto: hisilicon: Add HiSilicon ZIP accelerator support Date: Thu, 13 Dec 2018 19:22:10 +0800 Message-ID: <1544700131-196846-4-git-send-email-wangzhou1@hisilicon.com> X-Mailer: git-send-email 2.8.1 In-Reply-To: <1544700131-196846-1-git-send-email-wangzhou1@hisilicon.com> References: <1544700131-196846-1-git-send-email-wangzhou1@hisilicon.com> MIME-Version: 1.0 X-Originating-IP: [10.67.212.75] X-CFilter-Loop: Reflected Sender: linux-kernel-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org The HiSilicon ZIP accelerator implements the zlib and gzip algorithm. It uses Hisilicon QM as the interface to the CPU. This patch provides PCIe driver to the accelerator and register it to the crypto subsystem. Signed-off-by: Zhou Wang Signed-off-by: Shiju Jose Signed-off-by: Kenneth Lee Signed-off-by: Hao Fang reviewed-by: Jonathan Cameron reviewed-by: John Garry --- drivers/crypto/hisilicon/Kconfig | 7 + drivers/crypto/hisilicon/Makefile | 1 + drivers/crypto/hisilicon/zip/Makefile | 2 + drivers/crypto/hisilicon/zip/zip.h | 55 ++ drivers/crypto/hisilicon/zip/zip_crypto.c | 404 ++++++++++ drivers/crypto/hisilicon/zip/zip_main.c | 1162 +++++++++++++++++++++++++++++ 6 files changed, 1631 insertions(+) create mode 100644 drivers/crypto/hisilicon/zip/Makefile create mode 100644 drivers/crypto/hisilicon/zip/zip.h create mode 100644 drivers/crypto/hisilicon/zip/zip_crypto.c create mode 100644 drivers/crypto/hisilicon/zip/zip_main.c -- 2.8.1 diff --git a/drivers/crypto/hisilicon/Kconfig b/drivers/crypto/hisilicon/Kconfig index 993a98d..338a70a 100644 --- a/drivers/crypto/hisilicon/Kconfig +++ b/drivers/crypto/hisilicon/Kconfig @@ -16,3 +16,10 @@ config CRYPTO_DEV_HISI_SEC config CRYPTO_DEV_HISI_QM tristate depends on ARM64 && PCI && PCI_MSI + +config CRYPTO_DEV_HISI_ZIP + tristate "Support for HiSilicon ZIP accelerator" + depends on ARM64 + select CRYPTO_DEV_HISI_QM + help + Support for HiSilicon ZIP Driver diff --git a/drivers/crypto/hisilicon/Makefile b/drivers/crypto/hisilicon/Makefile index 05e9052..c97c5b2 100644 --- a/drivers/crypto/hisilicon/Makefile +++ b/drivers/crypto/hisilicon/Makefile @@ -1,3 +1,4 @@ # SPDX-License-Identifier: GPL-2.0 obj-$(CONFIG_CRYPTO_DEV_HISI_SEC) += sec/ obj-$(CONFIG_CRYPTO_DEV_HISI_QM) += qm.o +obj-$(CONFIG_CRYPTO_DEV_HISI_ZIP) += zip/ diff --git a/drivers/crypto/hisilicon/zip/Makefile b/drivers/crypto/hisilicon/zip/Makefile new file mode 100644 index 0000000..a936f09 --- /dev/null +++ b/drivers/crypto/hisilicon/zip/Makefile @@ -0,0 +1,2 @@ +obj-$(CONFIG_CRYPTO_DEV_HISI_ZIP) += hisi_zip.o +hisi_zip-objs = zip_main.o zip_crypto.o diff --git a/drivers/crypto/hisilicon/zip/zip.h b/drivers/crypto/hisilicon/zip/zip.h new file mode 100644 index 0000000..7eb1180 --- /dev/null +++ b/drivers/crypto/hisilicon/zip/zip.h @@ -0,0 +1,55 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2018 Hisilicon Limited. */ +#ifndef HISI_ZIP_H +#define HISI_ZIP_H + +#include +#include "../qm.h" + +#undef pr_fmt +#define pr_fmt(fmt) "hisi_zip: " fmt + +struct hisi_zip_ctrl; + +struct hisi_zip { + struct hisi_qm qm; + struct list_head list; + struct hisi_zip_ctrl *ctrl; +}; + +struct hisi_zip_sqe { + __u32 consumed; + __u32 produced; + __u32 comp_data_length; + __u32 dw3; + __u32 input_data_length; + __u32 lba_l; + __u32 lba_h; + __u32 dw7; + __u32 dw8; + __u32 dw9; + __u32 dw10; + __u32 priv_info; + __u32 dw12; + __u32 tag; + __u32 dest_avail_out; + __u32 rsvd0; + __u32 comp_head_addr_l; + __u32 comp_head_addr_h; + __u32 source_addr_l; + __u32 source_addr_h; + __u32 dest_addr_l; + __u32 dest_addr_h; + __u32 stream_ctx_addr_l; + __u32 stream_ctx_addr_h; + __u32 cipher_key1_addr_l; + __u32 cipher_key1_addr_h; + __u32 cipher_key2_addr_l; + __u32 cipher_key2_addr_h; + __u32 rsvd1[4]; +}; + +struct hisi_zip *find_zip_device(int node); +int hisi_zip_register_to_crypto(void); +void hisi_zip_unregister_from_crypto(void); +#endif diff --git a/drivers/crypto/hisilicon/zip/zip_crypto.c b/drivers/crypto/hisilicon/zip/zip_crypto.c new file mode 100644 index 0000000..f22c009 --- /dev/null +++ b/drivers/crypto/hisilicon/zip/zip_crypto.c @@ -0,0 +1,404 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2018 Hisilicon Limited. */ +#include +#include +#include "zip.h" + +#define HZIP_INPUT_BUFFER_SIZE SZ_4M +#define HZIP_OUTPUT_BUFFER_SIZE SZ_4M + +#define HZIP_ALG_TYPE_ZLIB 0x02 +#define HZIP_ALG_TYPE_GZIP 0x03 + +const u8 zlib_head[2] = {0x78, 0x9c}; +const u8 gzip_head[10] = {0x1f, 0x8b, 0x08, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x03}; + +#define COMP_NAME_TO_TYPE(alg_name) \ + (!strcmp((alg_name), "zlib-deflate") ? HZIP_ALG_TYPE_ZLIB : \ + !strcmp((alg_name), "gzip") ? HZIP_ALG_TYPE_GZIP : 0) \ + +#define TO_HEAD_SIZE(req_type) \ + (((req_type) == HZIP_ALG_TYPE_ZLIB) ? sizeof(zlib_head) : \ + ((req_type) == HZIP_ALG_TYPE_GZIP) ? sizeof(gzip_head) : 0) \ + +#define TO_HEAD(req_type) \ + (((req_type) == HZIP_ALG_TYPE_ZLIB) ? zlib_head : \ + ((req_type) == HZIP_ALG_TYPE_GZIP) ? gzip_head : 0) \ + +struct hisi_zip_buffer { + u8 *input; + dma_addr_t input_dma; + u8 *output; + dma_addr_t output_dma; +}; + +struct hisi_zip_qp_ctx { + struct hisi_zip_buffer buffer; + struct hisi_qp *qp; + struct hisi_zip_sqe zip_sqe; +}; + +struct hisi_zip_ctx { +#define QPC_COMP 0 +#define QPC_DECOMP 1 + struct hisi_zip_qp_ctx qp_ctx[2]; +}; + +static void hisi_zip_fill_sqe(void *sqe, void *q_parm, u32 len) +{ + struct hisi_zip_sqe *zip_sqe = sqe; + struct hisi_zip_qp_ctx *qp_ctx = q_parm; + struct hisi_zip_buffer *buffer = &qp_ctx->buffer; + + memset(zip_sqe, 0, sizeof(struct hisi_zip_sqe)); + + zip_sqe->input_data_length = len; + zip_sqe->dw9 = qp_ctx->qp->req_type; + zip_sqe->dest_avail_out = HZIP_OUTPUT_BUFFER_SIZE; + zip_sqe->source_addr_l = lower_32_bits(buffer->input_dma); + zip_sqe->source_addr_h = upper_32_bits(buffer->input_dma); + zip_sqe->dest_addr_l = lower_32_bits(buffer->output_dma); + zip_sqe->dest_addr_h = upper_32_bits(buffer->output_dma); +} + +/* let's allocate one buffer now, may have problem in async case */ +static int hisi_zip_alloc_qp_buffer(struct hisi_zip_qp_ctx *hisi_zip_qp_ctx) +{ + struct hisi_zip_buffer *buffer = &hisi_zip_qp_ctx->buffer; + struct hisi_qp *qp = hisi_zip_qp_ctx->qp; + struct device *dev = &qp->qm->pdev->dev; + int ret; + + buffer->input = dma_alloc_coherent(dev, HZIP_INPUT_BUFFER_SIZE, + &buffer->input_dma, GFP_KERNEL); + if (!buffer->input) + return -ENOMEM; + + buffer->output = dma_alloc_coherent(dev, HZIP_OUTPUT_BUFFER_SIZE, + &buffer->output_dma, GFP_KERNEL); + if (!buffer->output) { + ret = -ENOMEM; + goto err_alloc_output_buffer; + } + + return 0; + +err_alloc_output_buffer: + dma_free_coherent(dev, HZIP_INPUT_BUFFER_SIZE, buffer->input, + buffer->input_dma); + return ret; +} + +static void hisi_zip_free_qp_buffer(struct hisi_zip_qp_ctx *hisi_zip_qp_ctx) +{ + struct hisi_zip_buffer *buffer = &hisi_zip_qp_ctx->buffer; + struct hisi_qp *qp = hisi_zip_qp_ctx->qp; + struct device *dev = &qp->qm->pdev->dev; + + dma_free_coherent(dev, HZIP_INPUT_BUFFER_SIZE, buffer->input, + buffer->input_dma); + dma_free_coherent(dev, HZIP_OUTPUT_BUFFER_SIZE, buffer->output, + buffer->output_dma); +} + +static int hisi_zip_create_qp(struct hisi_qm *qm, struct hisi_zip_qp_ctx *ctx, + int alg_type, int req_type) +{ + struct hisi_qp *qp; + int ret; + + qp = hisi_qm_create_qp(qm, alg_type); + if (IS_ERR(qp)) + return PTR_ERR(qp); + + qp->req_type = req_type; + qp->qp_ctx = ctx; + ctx->qp = qp; + + ret = hisi_zip_alloc_qp_buffer(ctx); + if (ret) + goto err_release_qp; + + ret = hisi_qm_start_qp(qp, 0); + if (ret < 0) + goto err_free_qp_buffer; + + return 0; + +err_free_qp_buffer: + hisi_zip_free_qp_buffer(ctx); +err_release_qp: + hisi_qm_release_qp(qp); + return ret; +} + +static void hisi_zip_release_qp(struct hisi_zip_qp_ctx *ctx) +{ + hisi_qm_stop_qp(ctx->qp); + hisi_zip_free_qp_buffer(ctx); + hisi_qm_release_qp(ctx->qp); +} + +static int hisi_zip_alloc_comp_ctx(struct crypto_tfm *tfm) +{ + struct hisi_zip_ctx *hisi_zip_ctx = crypto_tfm_ctx(tfm); + const char *alg_name = crypto_tfm_alg_name(tfm); + struct hisi_zip *hisi_zip; + struct hisi_qm *qm; + int ret, i, j; + + u8 req_type = COMP_NAME_TO_TYPE(alg_name); + + /* find the proper zip device */ + hisi_zip = find_zip_device(cpu_to_node(smp_processor_id())); + if (!hisi_zip) { + pr_err("Failed to find a proper ZIP device!\n"); + return -ENODEV; + } + qm = &hisi_zip->qm; + + for (i = 0; i < 2; i++) { + /* it is just happen that 0 is compress, 1 is decompress on alg_type */ + ret = hisi_zip_create_qp(qm, &hisi_zip_ctx->qp_ctx[i], i, + req_type); + if (ret) + goto err; + } + + return 0; +err: + for (j = i - 1; j >= 0; j--) + hisi_zip_release_qp(&hisi_zip_ctx->qp_ctx[j]); + + return ret; +} + +static void hisi_zip_free_comp_ctx(struct crypto_tfm *tfm) +{ + struct hisi_zip_ctx *hisi_zip_ctx = crypto_tfm_ctx(tfm); + int i; + + /* release the qp */ + for (i = 1; i >= 0; i--) + hisi_zip_release_qp(&hisi_zip_ctx->qp_ctx[i]); +} + +static int hisi_zip_copy_data_to_buffer(struct hisi_zip_qp_ctx *qp_ctx, + const u8 *src, unsigned int slen) +{ + struct hisi_zip_buffer *buffer = &qp_ctx->buffer; + + if (slen > HZIP_INPUT_BUFFER_SIZE) + return -ENOSPC; + + memcpy(buffer->input, src, slen); + + return 0; +} + +static struct hisi_zip_sqe *hisi_zip_get_writeback_sqe(struct hisi_qp *qp) +{ + struct hisi_qp_status *qp_status = &qp->qp_status; + struct hisi_zip_sqe *sq_base = qp->scqe.addr; + u16 sq_head = qp_status->sq_head; + + return sq_base + sq_head; +} + +static void hisi_zip_add_comp_head(struct hisi_qp *qp, u8 *dst) +{ + u8 head_size = TO_HEAD_SIZE(qp->req_type); + const u8 *head = TO_HEAD(qp->req_type); + + memcpy(dst, head, head_size); +} + +static void hisi_zip_copy_data_from_buffer(struct hisi_zip_qp_ctx *qp_ctx, + u8 *dst) +{ + struct hisi_zip_buffer *buffer = &qp_ctx->buffer; + struct hisi_qp *qp = qp_ctx->qp; + struct hisi_zip_sqe *zip_sqe = hisi_zip_get_writeback_sqe(qp); + u16 sq_head; + + memcpy(dst, buffer->output, zip_sqe->produced); + + sq_head = qp->qp_status.sq_head; + if (sq_head == QM_Q_DEPTH - 1) + qp->qp_status.sq_head = 0; + else + qp->qp_status.sq_head++; + + if (unlikely(test_bit(QP_FULL, &qp->qp_status.flags))) + clear_bit(QP_FULL, &qp->qp_status.flags); +} + +static int hisi_zip_compress_data_output(struct hisi_zip_qp_ctx *qp_ctx, + u8 *dst, unsigned int *dlen) +{ + struct hisi_qp *qp = qp_ctx->qp; + struct hisi_zip_sqe *zip_sqe = hisi_zip_get_writeback_sqe(qp); + u32 status = zip_sqe->dw3 & 0xff; + u8 head_size = TO_HEAD_SIZE(qp->req_type); + + if (status != 0) { + dev_err(&qp->qm->pdev->dev, "Compression failed in qp%d!\n", + qp->qp_id); + return status; + } + + if (zip_sqe->produced + head_size > *dlen) + return -ENOMEM; + + hisi_zip_add_comp_head(qp, dst); + hisi_zip_copy_data_from_buffer(qp_ctx, dst + head_size); + + *dlen = zip_sqe->produced + head_size; + + return 0; +} + +static int hisi_zip_compress(struct crypto_tfm *tfm, const u8 *src, + unsigned int slen, u8 *dst, unsigned int *dlen) +{ + struct hisi_zip_ctx *hisi_zip_ctx = crypto_tfm_ctx(tfm); + struct hisi_zip_qp_ctx *qp_ctx = &hisi_zip_ctx->qp_ctx[QPC_COMP]; + struct hisi_qp *qp = qp_ctx->qp; + struct hisi_zip_sqe *zip_sqe = &qp_ctx->zip_sqe; + int ret; + + ret = hisi_zip_copy_data_to_buffer(qp_ctx, src, slen); + if (ret < 0) + return ret; + + hisi_zip_fill_sqe(zip_sqe, qp_ctx, slen); + + /* send command to start the compress job */ + ret = hisi_qp_send(qp, zip_sqe); + if (ret < 0) + return ret; + + ret = hisi_qp_wait(qp); + if (ret < 0) + return ret; + + return hisi_zip_compress_data_output(qp_ctx, dst, dlen); +} + +static int hisi_zip_get_comp_head_size(struct hisi_qp *qp) +{ + return TO_HEAD_SIZE(qp->req_type); +} + +static int hisi_zip_decompress_data_output(struct hisi_zip_qp_ctx *qp_ctx, + u8 *dst, unsigned int *dlen) +{ + struct hisi_qp *qp = qp_ctx->qp; + struct hisi_zip_sqe *zip_sqe = hisi_zip_get_writeback_sqe(qp); + u32 status = zip_sqe->dw3 & 0xff; + + if (status != 0) { + dev_err(&qp->qm->pdev->dev, "Decompression fail in qp%u!\n", + qp->qp_id); + return status; + } + + if (zip_sqe->produced > *dlen) + return -ENOMEM; + + hisi_zip_copy_data_from_buffer(qp_ctx, dst); + + *dlen = zip_sqe->produced; + + return 0; +} + +static int hisi_zip_decompress(struct crypto_tfm *tfm, const u8 *src, + unsigned int slen, u8 *dst, unsigned int *dlen) +{ + struct hisi_zip_ctx *hisi_zip_ctx = crypto_tfm_ctx(tfm); + struct hisi_zip_qp_ctx *qp_ctx = &hisi_zip_ctx->qp_ctx[QPC_DECOMP]; + struct hisi_qp *qp = qp_ctx->qp; + struct hisi_zip_sqe *zip_sqe = &qp_ctx->zip_sqe; + u16 size = hisi_zip_get_comp_head_size(qp); + int ret; + + ret = hisi_zip_copy_data_to_buffer(qp_ctx, src + size, slen - size); + if (ret < 0) + return ret; + + hisi_zip_fill_sqe(zip_sqe, qp_ctx, slen - size); + + /* send command to start the decompress job */ + ret = hisi_qp_send(qp, zip_sqe); + if (ret < 0) + return ret; + + ret = hisi_qp_wait(qp); + if (ret < 0) + return ret; + + return hisi_zip_decompress_data_output(qp_ctx, dst, dlen); +} + +static struct crypto_alg hisi_zip_zlib = { + .cra_name = "zlib-deflate", + .cra_flags = CRYPTO_ALG_TYPE_COMPRESS, + .cra_ctxsize = sizeof(struct hisi_zip_ctx), + .cra_priority = 300, + .cra_module = THIS_MODULE, + .cra_init = hisi_zip_alloc_comp_ctx, + .cra_exit = hisi_zip_free_comp_ctx, + .cra_u = { + .compress = { + .coa_compress = hisi_zip_compress, + .coa_decompress = hisi_zip_decompress + } + } +}; + +static struct crypto_alg hisi_zip_gzip = { + .cra_name = "gzip", + .cra_flags = CRYPTO_ALG_TYPE_COMPRESS, + .cra_ctxsize = sizeof(struct hisi_zip_ctx), + .cra_priority = 300, + .cra_module = THIS_MODULE, + .cra_init = hisi_zip_alloc_comp_ctx, + .cra_exit = hisi_zip_free_comp_ctx, + .cra_u = { + .compress = { + .coa_compress = hisi_zip_compress, + .coa_decompress = hisi_zip_decompress + } + } +}; + +int hisi_zip_register_to_crypto(void) +{ + int ret; + + ret = crypto_register_alg(&hisi_zip_zlib); + if (ret < 0) { + pr_err("Zlib algorithm registration failed\n"); + return ret; + } + + ret = crypto_register_alg(&hisi_zip_gzip); + if (ret < 0) { + pr_err("Gzip algorithm registration failed\n"); + goto err_unregister_zlib; + } + + return 0; + +err_unregister_zlib: + crypto_unregister_alg(&hisi_zip_zlib); + + return ret; +} + +void hisi_zip_unregister_from_crypto(void) +{ + crypto_unregister_alg(&hisi_zip_gzip); + crypto_unregister_alg(&hisi_zip_zlib); +} diff --git a/drivers/crypto/hisilicon/zip/zip_main.c b/drivers/crypto/hisilicon/zip/zip_main.c new file mode 100644 index 0000000..b5684ea --- /dev/null +++ b/drivers/crypto/hisilicon/zip/zip_main.c @@ -0,0 +1,1162 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2018 Hisilicon Limited. */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include "zip.h" + +#define HZIP_VF_NUM 63 +#define HZIP_QUEUE_NUM_V1 4096 +#define HZIP_QUEUE_NUM_V2 1024 + +#define HZIP_FSM_MAX_CNT 0x301008 + +#define HZIP_PORT_ARCA_CHE_0 0x301040 +#define HZIP_PORT_ARCA_CHE_1 0x301044 +#define HZIP_PORT_AWCA_CHE_0 0x301060 +#define HZIP_PORT_AWCA_CHE_1 0x301064 + +#define HZIP_BD_RUSER_32_63 0x301110 +#define HZIP_SGL_RUSER_32_63 0x30111c +#define HZIP_DATA_RUSER_32_63 0x301128 +#define HZIP_DATA_WUSER_32_63 0x301134 +#define HZIP_BD_WUSER_32_63 0x301140 + +#define HZIP_QM_IDEL_STATUS 0x3040e4 +#define HZIP_MASTER_GLOBAL_CTRL 0x300000 +#define MASTER_GLOBAL_CTRL_SHUTDOWN 0x1 +#define HZIP_MASTER_TRANS_RETURN 0x300150 +#define MASTER_TRANS_RETURN_RW 0x3 + +#define HZIP_CORE_DEBUG_COMP_0 0x302000 +#define HZIP_CORE_DEBUG_COMP_1 0x303000 +#define HZIP_CORE_DEBUG_DECOMP_0 0x304000 +#define HZIP_CORE_DEBUG_DECOMP_1 0x305000 +#define HZIP_CORE_DEBUG_DECOMP_2 0x306000 +#define HZIP_CORE_DEBUG_DECOMP_3 0x307000 +#define HZIP_CORE_DEBUG_DECOMP_4 0x308000 +#define HZIP_CORE_DEBUG_DECOMP_5 0x309000 + +#define HZIP_CORE_INT_SOURCE 0x3010A0 +#define HZIP_CORE_INT_MASK 0x3010A4 +#define HZIP_CORE_INT_STATUS 0x3010AC +#define HZIP_CORE_INT_STATUS_M_ECC BIT(1) +#define HZIP_CORE_SRAM_ECC_ERR_INFO 0x301148 +#define HZIP_CORE_INT_DISABLE 0x000007FF +#define HZIP_COMP_CORE_NUM 2 +#define HZIP_DECOMP_CORE_NUM 6 +#define HZIP_CORE_NUM (HZIP_COMP_CORE_NUM + \ + HZIP_DECOMP_CORE_NUM) +#define HZIP_SQE_SIZE 128 +#define HZIP_SQ_SIZE (HZIP_SQE_SIZE * QM_Q_DEPTH) +#define HZIP_PF_DEF_Q_NUM 64 +#define HZIP_PF_DEF_Q_BASE 0 + +#define HZIP_SOFT_CTRL_CNT_CLR_CE 0x301000 +#define SOFT_CTRL_CNT_CLR_CE_BIT BIT(0) + +static const char hisi_zip_name[] = "hisi_zip"; +static struct dentry *hzip_debugfs_root; +LIST_HEAD(hisi_zip_list); +DEFINE_MUTEX(hisi_zip_list_lock); + +struct hisi_zip *find_zip_device(int node) +{ + struct hisi_zip *ret = NULL; +#ifdef CONFIG_NUMA + struct hisi_zip *hisi_zip; + int min_distance = 100; + struct device *dev; + + mutex_lock(&hisi_zip_list_lock); + + list_for_each_entry(hisi_zip, &hisi_zip_list, list) { + dev = &hisi_zip->qm.pdev->dev; + if (node_distance(dev->numa_node, node) < min_distance) { + ret = hisi_zip; + min_distance = node_distance(dev->numa_node, node); + } + } +#else + mutex_lock(&hisi_zip_list_lock); + + ret = list_first_entry(&hisi_zip_list, struct hisi_zip, list); +#endif + mutex_unlock(&hisi_zip_list_lock); + + return ret; +} + +struct hisi_zip_hw_error { + u32 int_msk; + const char *msg; +}; + +static const struct hisi_zip_hw_error zip_hw_error[] = { + { .int_msk = BIT(0), .msg = "zip_ecc_1bitt_err" }, + { .int_msk = BIT(1), .msg = "zip_ecc_2bit_err" }, + { .int_msk = BIT(2), .msg = "zip_axi_rresp_err" }, + { .int_msk = BIT(3), .msg = "zip_axi_bresp_err" }, + { .int_msk = BIT(4), .msg = "zip_src_addr_parse_err" }, + { .int_msk = BIT(5), .msg = "zip_dst_addr_parse_err" }, + { .int_msk = BIT(6), .msg = "zip_pre_in_addr_err" }, + { .int_msk = BIT(7), .msg = "zip_pre_in_data_err" }, + { .int_msk = BIT(8), .msg = "zip_com_inf_err" }, + { .int_msk = BIT(9), .msg = "zip_enc_inf_err" }, + { .int_msk = BIT(10), .msg = "zip_pre_out_err" }, + { /* sentinel */ } +}; + +enum ctrl_debug_file_index { + HZIP_CURRENT_QM, + HZIP_CLEAR_ENABLE, + HZIP_DEBUG_FILE_NUM, +}; + +static const char * const ctrl_debug_file_name[] = { + [HZIP_CURRENT_QM] = "current_qm", + [HZIP_CLEAR_ENABLE] = "clear_enable", +}; + +struct ctrl_debug_file { + enum ctrl_debug_file_index index; + spinlock_t lock; + struct hisi_zip_ctrl *ctrl; +}; + +/* + * One ZIP controller has one PF and multiple VFs, some global configurations + * which PF has need this structure. + * + * Just relevant for PF. + */ +struct hisi_zip_ctrl { + u32 ctrl_q_num; + u32 num_vfs; + struct hisi_zip *hisi_zip; + struct dentry *debug_root; + struct ctrl_debug_file files[HZIP_DEBUG_FILE_NUM]; +}; + +enum { + HZIP_COMP_CORE0, + HZIP_COMP_CORE1, + HZIP_DECOMP_CORE0, + HZIP_DECOMP_CORE1, + HZIP_DECOMP_CORE2, + HZIP_DECOMP_CORE3, + HZIP_DECOMP_CORE4, + HZIP_DECOMP_CORE5, +}; + +static const u64 core_offsets[] = { + [HZIP_COMP_CORE0] = 0x302000, + [HZIP_COMP_CORE1] = 0x303000, + [HZIP_DECOMP_CORE0] = 0x304000, + [HZIP_DECOMP_CORE1] = 0x305000, + [HZIP_DECOMP_CORE2] = 0x306000, + [HZIP_DECOMP_CORE3] = 0x307000, + [HZIP_DECOMP_CORE4] = 0x308000, + [HZIP_DECOMP_CORE5] = 0x309000, +}; + +static struct debugfs_reg32 hzip_dfx_regs[] = { + {"HZIP_GET_BD_NUM ", 0x00ull}, + {"HZIP_GET_RIGHT_BD ", 0x04ull}, + {"HZIP_GET_ERROR_BD ", 0x08ull}, + {"HZIP_DONE_BD_NUM ", 0x0cull}, + {"HZIP_WORK_CYCLE ", 0x10ull}, + {"HZIP_IDLE_CYCLE ", 0x18ull}, + {"HZIP_MAX_DELAY ", 0x20ull}, + {"HZIP_MIN_DELAY ", 0x24ull}, + {"HZIP_AVG_DELAY ", 0x28ull}, + {"HZIP_MEM_VISIBLE_DATA ", 0x30ull}, + {"HZIP_MEM_VISIBLE_ADDR ", 0x34ull}, + {"HZIP_COMSUMED_BYTE ", 0x38ull}, + {"HZIP_PRODUCED_BYTE ", 0x40ull}, + {"HZIP_COMP_INF ", 0x70ull}, + {"HZIP_PRE_OUT ", 0x78ull}, + {"HZIP_BD_RD ", 0x7cull}, + {"HZIP_BD_WR ", 0x80ull}, + {"HZIP_GET_BD_AXI_ERR_NUM ", 0x84ull}, + {"HZIP_GET_BD_PARSE_ERR_NUM ", 0x88ull}, + {"HZIP_ADD_BD_AXI_ERR_NUM ", 0x8cull}, + {"HZIP_DECOMP_STF_RELOAD_CURR_ST ", 0x94ull}, + {"HZIP_DECOMP_LZ77_CURR_ST ", 0x9cull}, +}; + +static int pf_q_num_set(const char *val, const struct kernel_param *kp) +{ + struct pci_dev *pdev = pci_get_device(PCI_VENDOR_ID_HUAWEI, 0xa250, + NULL); + u32 n, q_num; + u8 rev_id; + int ret; + + if (unlikely(!pdev)) { + q_num = min_t(u32, HZIP_QUEUE_NUM_V1, HZIP_QUEUE_NUM_V2); + pr_info("No device found currently, suppose queue number is %d\n", + q_num); + } else { + rev_id = pdev->revision; + switch (rev_id) { + case 0x20: + q_num = HZIP_QUEUE_NUM_V1; + break; + case 0x21: + q_num = HZIP_QUEUE_NUM_V2; + break; + default: + return -EINVAL; + } + } + + ret = kstrtou32(val, 10, &n); + if (ret != 0 || n > q_num) + return -EINVAL; + + return param_set_int(val, kp); +} + +static const struct kernel_param_ops pf_q_num_ops = { + .set = pf_q_num_set, + .get = param_get_int, +}; + +static u32 pf_q_num = HZIP_PF_DEF_Q_NUM; +module_param_cb(pf_q_num, &pf_q_num_ops, &pf_q_num, 0444); +MODULE_PARM_DESC(pf_q_num, "Number of queues in PF(v1 0-4096, v2 0-1024)"); + +static const struct pci_device_id hisi_zip_dev_ids[] = { + { PCI_DEVICE(PCI_VENDOR_ID_HUAWEI, 0xa250) }, + { PCI_DEVICE(PCI_VENDOR_ID_HUAWEI, 0xa251) }, + { 0, } +}; +MODULE_DEVICE_TABLE(pci, hisi_zip_dev_ids); + +static inline void hisi_zip_add_to_list(struct hisi_zip *hisi_zip) +{ + mutex_lock(&hisi_zip_list_lock); + list_add_tail(&hisi_zip->list, &hisi_zip_list); + mutex_unlock(&hisi_zip_list_lock); +} + +static inline void hisi_zip_remove_from_list(struct hisi_zip *hisi_zip) +{ + mutex_lock(&hisi_zip_list_lock); + list_del(&hisi_zip->list); + mutex_unlock(&hisi_zip_list_lock); +} + +static void hisi_zip_set_user_domain_and_cache(struct hisi_zip *hisi_zip) +{ + u32 val; + + /* qm user domain */ + writel(0x40001070, hisi_zip->qm.io_base + QM_ARUSER_M_CFG_1); + writel(0xfffffffe, hisi_zip->qm.io_base + QM_ARUSER_M_CFG_ENABLE); + writel(0x40001070, hisi_zip->qm.io_base + QM_AWUSER_M_CFG_1); + writel(0xfffffffe, hisi_zip->qm.io_base + QM_AWUSER_M_CFG_ENABLE); + writel(0xffffffff, hisi_zip->qm.io_base + QM_WUSER_M_CFG_ENABLE); + + val = readl(hisi_zip->qm.io_base + QM_PEH_AXUSER_CFG); + val |= (1 << 11); + writel(val, hisi_zip->qm.io_base + QM_PEH_AXUSER_CFG); + + /* qm cache */ + writel(0xffff, hisi_zip->qm.io_base + QM_AXI_M_CFG); + writel(0xffffffff, hisi_zip->qm.io_base + QM_AXI_M_CFG_ENABLE); + writel(0xffffffff, hisi_zip->qm.io_base + QM_PEH_AXUSER_CFG_ENABLE); + + /* cache */ + writel(0xffffffff, hisi_zip->qm.io_base + HZIP_PORT_ARCA_CHE_0); + writel(0xffffffff, hisi_zip->qm.io_base + HZIP_PORT_ARCA_CHE_1); + writel(0xffffffff, hisi_zip->qm.io_base + HZIP_PORT_AWCA_CHE_0); + writel(0xffffffff, hisi_zip->qm.io_base + HZIP_PORT_AWCA_CHE_1); + /* user domain configurations */ + writel(0x40001070, hisi_zip->qm.io_base + HZIP_BD_RUSER_32_63); + writel(0x40001070, hisi_zip->qm.io_base + HZIP_SGL_RUSER_32_63); + writel(0x40001070, hisi_zip->qm.io_base + HZIP_DATA_RUSER_32_63); + writel(0x40001070, hisi_zip->qm.io_base + HZIP_DATA_WUSER_32_63); + writel(0x40001070, hisi_zip->qm.io_base + HZIP_BD_WUSER_32_63); + + /* fsm count */ + writel(0xfffffff, hisi_zip->qm.io_base + HZIP_FSM_MAX_CNT); + + /* let's open all compression/decompression cores */ + writel(0x100ff, hisi_zip->qm.io_base + 0x301004); +} + +static void hisi_zip_hw_error_set_state(struct hisi_zip *hisi_zip, bool state) +{ + struct hisi_qm *qm = &hisi_zip->qm; + + if (qm->ver == QM_HW_V1) { + writel(HZIP_CORE_INT_DISABLE, qm->io_base + HZIP_CORE_INT_MASK); + dev_info(&qm->pdev->dev, "ZIP v%d does not support hw error handle\n", + qm->ver); + return; + } + + if (state) + /* enable ZIP hw error interrupts */ + writel(0, hisi_zip->qm.io_base + HZIP_CORE_INT_MASK); + else + /* disable ZIP hw error interrupts */ + writel(HZIP_CORE_INT_DISABLE, + hisi_zip->qm.io_base + HZIP_CORE_INT_MASK); +} + +static inline struct hisi_qm *file_to_qm(struct ctrl_debug_file *file) +{ + struct hisi_zip *hisi_zip = file->ctrl->hisi_zip; + + return &hisi_zip->qm; +} + +static u32 current_qm_read(struct ctrl_debug_file *file) +{ + struct hisi_qm *qm = file_to_qm(file); + + return readl(qm->io_base + QM_DFX_MB_CNT_VF); +} + +static int current_qm_write(struct ctrl_debug_file *file, u32 val) +{ + struct hisi_qm *qm = file_to_qm(file); + struct hisi_zip_ctrl *ctrl = file->ctrl; + + if (val > ctrl->num_vfs) + return -EINVAL; + + writel(val, qm->io_base + QM_DFX_MB_CNT_VF); + writel(val, qm->io_base + QM_DFX_DB_CNT_VF); + + return 0; +} + +static u32 clear_enable_read(struct ctrl_debug_file *file) +{ + struct hisi_qm *qm = file_to_qm(file); + + return readl(qm->io_base + HZIP_SOFT_CTRL_CNT_CLR_CE) && + SOFT_CTRL_CNT_CLR_CE_BIT; +} + +static int clear_enable_write(struct ctrl_debug_file *file, u32 val) +{ + struct hisi_qm *qm = file_to_qm(file); + + if (val != 1 && val != 0) + return -EINVAL; + + val |= readl(qm->io_base + HZIP_SOFT_CTRL_CNT_CLR_CE) & + ~SOFT_CTRL_CNT_CLR_CE_BIT; + writel(val, qm->io_base + HZIP_SOFT_CTRL_CNT_CLR_CE); + + return 0; +} + +static ssize_t ctrl_debug_read(struct file *filp, char __user *buf, + size_t count, loff_t *pos) +{ + struct ctrl_debug_file *file = filp->private_data; + char tbuf[20]; + u32 val; + int ret; + + spin_lock_irq(&file->lock); + switch (file->index) { + case HZIP_CURRENT_QM: + val = current_qm_read(file); + break; + case HZIP_CLEAR_ENABLE: + val = clear_enable_read(file); + break; + default: + spin_unlock_irq(&file->lock); + return -EINVAL; + } + spin_unlock_irq(&file->lock); + ret = sprintf(tbuf, "%u\n", val); + return simple_read_from_buffer(buf, count, pos, tbuf, ret); +} + +static ssize_t ctrl_debug_write(struct file *filp, const char __user *buf, + size_t count, loff_t *pos) +{ + struct ctrl_debug_file *file = filp->private_data; + char tbuf[20]; + unsigned long val; + int len, ret; + + if (*pos != 0) + return 0; + + if (count >= 20) + return -ENOSPC; + + len = simple_write_to_buffer(tbuf, 20 - 1, pos, buf, count); + if (len < 0) + return len; + + tbuf[len] = '\0'; + if (kstrtoul(tbuf, 0, &val)) + return -EFAULT; + + spin_lock_irq(&file->lock); + switch (file->index) { + case HZIP_CURRENT_QM: + ret = current_qm_write(file, val); + if (ret) + goto err_input; + break; + case HZIP_CLEAR_ENABLE: + ret = clear_enable_write(file, val); + if (ret) + goto err_input; + break; + default: + ret = -EINVAL; + goto err_input; + } + spin_unlock_irq(&file->lock); + + return count; + +err_input: + spin_unlock_irq(&file->lock); + return ret; +} + +static const struct file_operations ctrl_debug_fops = { + .owner = THIS_MODULE, + .open = simple_open, + .read = ctrl_debug_read, + .write = ctrl_debug_write, +}; + +static int hisi_zip_core_debug_init(struct hisi_zip_ctrl *ctrl) +{ + struct hisi_zip *hisi_zip = ctrl->hisi_zip; + struct hisi_qm *qm = &hisi_zip->qm; + struct device *dev = &qm->pdev->dev; + struct debugfs_regset32 *regset; + struct dentry *tmp_d, *tmp; + char buf[20]; + int i; + + if (!ctrl) + return -EINVAL; + + for (i = 0; i < HZIP_CORE_NUM; i++) { + if (i < HZIP_COMP_CORE_NUM) + sprintf(buf, "comp_core%d", i); + else + sprintf(buf, "decomp_core%d", i - HZIP_COMP_CORE_NUM); + + tmp_d = debugfs_create_dir(buf, ctrl->debug_root); + if (!tmp_d) + return -ENOENT; + + regset = devm_kzalloc(dev, sizeof(*regset), GFP_KERNEL); + if (!regset) + return -ENOENT; + + regset->regs = hzip_dfx_regs; + regset->nregs = ARRAY_SIZE(hzip_dfx_regs); + regset->base = qm->io_base + core_offsets[i]; + + tmp = debugfs_create_regset32("regs", 0444, tmp_d, regset); + if (!tmp) + return -ENOENT; + } + + return 0; +} + +static int hisi_zip_ctrl_debug_init(struct hisi_zip_ctrl *ctrl) +{ + struct dentry *tmp; + int i; + + for (i = HZIP_CURRENT_QM; i < HZIP_DEBUG_FILE_NUM; i++) { + spin_lock_init(&ctrl->files[i].lock); + ctrl->files[i].ctrl = ctrl; + ctrl->files[i].index = i; + + tmp = debugfs_create_file(ctrl_debug_file_name[i], 0600, + ctrl->debug_root, ctrl->files + i, + &ctrl_debug_fops); + if (!tmp) + return -ENOENT; + } + + return hisi_zip_core_debug_init(ctrl); +} + +static int hisi_zip_debugfs_init(struct hisi_zip *hisi_zip) +{ + struct hisi_qm *qm = &hisi_zip->qm; + struct device *dev = &qm->pdev->dev; + struct dentry *dev_d; + int ret; + + dev_d = debugfs_create_dir(dev_name(dev), hzip_debugfs_root); + if (!dev_d) + return -ENOENT; + + qm->debug.debug_root = dev_d; + ret = hisi_qm_debug_init(qm); + if (ret) + goto failed_to_create; + + if (qm->pdev->device == 0xa250) { + hisi_zip->ctrl->debug_root = dev_d; + ret = hisi_zip_ctrl_debug_init(hisi_zip->ctrl); + if (ret) + goto failed_to_create; + } + + return 0; + +failed_to_create: + debugfs_remove_recursive(hzip_debugfs_root); + return ret; +} + +static int hisi_zip_probe(struct pci_dev *pdev, const struct pci_device_id *id) +{ + struct hisi_zip_ctrl *ctrl; + struct hisi_zip *hisi_zip; + enum qm_hw_ver rev_id; + struct hisi_qm *qm; + u32 nfe_flag; + int ret; + + hisi_zip = devm_kzalloc(&pdev->dev, sizeof(*hisi_zip), GFP_KERNEL); + if (!hisi_zip) + return -ENOMEM; + + ctrl = devm_kzalloc(&pdev->dev, sizeof(*ctrl), GFP_KERNEL); + if (!ctrl) + return -ENOMEM; + + hisi_zip->ctrl = ctrl; + ctrl->hisi_zip = hisi_zip; + pci_set_drvdata(pdev, hisi_zip); + + hisi_zip_add_to_list(hisi_zip); + + qm = &hisi_zip->qm; + qm->pdev = pdev; + + rev_id = hisi_qm_get_hw_version(qm); + if (rev_id < 0) + return rev_id; + qm->ver = rev_id; + + switch (rev_id) { + case QM_HW_V1: + ctrl->ctrl_q_num = HZIP_QUEUE_NUM_V1; + break; + case QM_HW_V2: + ctrl->ctrl_q_num = HZIP_QUEUE_NUM_V2; + break; + } + + qm->sqe_size = HZIP_SQE_SIZE; + qm->dev_name = hisi_zip_name; + qm->fun_type = (pdev->device == 0xa250) ? QM_HW_PF : QM_HW_VF; + + ret = hisi_qm_init(qm); + if (ret) { + dev_err(&pdev->dev, "Failed to init qm!\n"); + goto err_remove_from_list; + } + + if (qm->fun_type == QM_HW_PF) { + ret = hisi_qm_mem_start(qm); + if (ret) + goto err_qm_uninit; + + hisi_zip_set_user_domain_and_cache(hisi_zip); + + nfe_flag = QM_BASE_NFE | QM_ACC_WB_NOT_READY_TIMEOUT; + hisi_qm_hw_error_init(qm, QM_BASE_CE, nfe_flag, 0, + QM_DB_RANDOM_INVALID); + hisi_zip_hw_error_set_state(hisi_zip, true); + + qm->qp_base = HZIP_PF_DEF_Q_BASE; + qm->qp_num = pf_q_num; + } else if (qm->fun_type == QM_HW_VF) { + /* + * have no way to get qm configure in VM in v1 hardware, + * so currently force PF to uses HZIP_PF_DEF_Q_NUM, and force + * to trigger only one VF in v1 hardware. + * + * v2 hardware has no such bug. + */ + if (qm->ver == QM_HW_V1) { + qm->qp_base = HZIP_PF_DEF_Q_NUM; + qm->qp_num = HZIP_QUEUE_NUM_V1 - HZIP_PF_DEF_Q_NUM; + } else if (qm->ver == QM_HW_V2) + /* v2 starts to support get vft by mailbox */ + hisi_qm_get_vft(qm, &qm->qp_base, &qm->qp_num); + } + + ret = hisi_qm_mem_init(qm); + if (ret) + goto err_qm_uninit; + + ret = hisi_qm_start(qm); + if (ret) + goto err_qm_mem_uninit; + + hisi_zip_debugfs_init(hisi_zip); + + return 0; + +err_qm_mem_uninit: + hisi_qm_mem_uninit(qm); +err_qm_uninit: + hisi_qm_uninit(qm); +err_remove_from_list: + hisi_zip_remove_from_list(hisi_zip); + return ret; +} + +static void hisi_zip_debugfs_exit(struct hisi_zip *hisi_zip) +{ + struct hisi_qm *qm = &hisi_zip->qm; + + debugfs_remove_recursive(qm->debug.debug_root); +} + +static void hisi_zip_remove(struct pci_dev *pdev) +{ + struct hisi_zip *hisi_zip = pci_get_drvdata(pdev); + struct hisi_qm *qm = &hisi_zip->qm; + + hisi_zip_debugfs_exit(hisi_zip); + hisi_qm_stop(qm); + hisi_qm_mem_uninit(qm); + + if (pdev->device == 0xa250) + hisi_zip_hw_error_set_state(hisi_zip, false); + + hisi_qm_uninit(qm); + hisi_zip_remove_from_list(hisi_zip); +} + +/* now we only support equal assignment */ +static int hisi_zip_vf_q_assign(struct hisi_zip *hisi_zip, int num_vfs) +{ + struct hisi_zip_ctrl *ctrl = hisi_zip->ctrl; + struct hisi_qm *qm = &hisi_zip->qm; + u32 qp_num = qm->qp_num; + u32 q_base = qp_num; + u32 q_num, remain_q_num, i; + int ret; + + remain_q_num = ctrl->ctrl_q_num - qp_num; + q_num = remain_q_num / num_vfs; + + for (i = 1; i <= num_vfs; i++) { + if (i == num_vfs) + q_num += remain_q_num % num_vfs; + ret = hisi_qm_set_vft(qm, i, q_base, q_num); + if (ret) + return ret; + q_base += q_num; + } + + return 0; +} + +static int hisi_zip_clear_vft_config(struct hisi_zip *hisi_zip) +{ + struct hisi_zip_ctrl *ctrl = hisi_zip->ctrl; + struct hisi_qm *qm = &hisi_zip->qm; + u32 i, num_vfs = ctrl->num_vfs; + int ret; + + for (i = 1; i <= num_vfs; i++) { + ret = hisi_qm_set_vft(qm, i, 0, 0); + if (ret) + return ret; + } + + ctrl->num_vfs = 0; + + return 0; +} + +static int hisi_zip_sriov_enable(struct pci_dev *pdev, int max_vfs) +{ +#ifdef CONFIG_PCI_IOV + struct hisi_zip *hisi_zip = pci_get_drvdata(pdev); + int pre_existing_vfs, num_vfs, ret; + + pre_existing_vfs = pci_num_vf(pdev); + + if (pre_existing_vfs) { + dev_err(&pdev->dev, + "Can't enable VF. Please disable pre-enabled VFs!\n"); + return 0; + } + + num_vfs = min_t(int, max_vfs, HZIP_VF_NUM); + + ret = hisi_zip_vf_q_assign(hisi_zip, num_vfs); + if (ret) { + dev_err(&pdev->dev, "Can't assign queues for VF!\n"); + return ret; + } + + hisi_zip->ctrl->num_vfs = num_vfs; + + ret = pci_enable_sriov(pdev, num_vfs); + if (ret) { + dev_err(&pdev->dev, "Can't enable VF!\n"); + hisi_zip_clear_vft_config(hisi_zip); + return ret; + } + + return num_vfs; +#else + return 0; +#endif +} + +static int hisi_zip_sriov_disable(struct pci_dev *pdev) +{ + struct hisi_zip *hisi_zip = pci_get_drvdata(pdev); + + if (pci_vfs_assigned(pdev)) { + dev_err(&pdev->dev, + "Can't disable VFs while VFs are assigned!\n"); + return -EPERM; + } + + /* remove in hisi_zip_pci_driver will be called to free VF resources */ + pci_disable_sriov(pdev); + + return hisi_zip_clear_vft_config(hisi_zip); +} + +static int hisi_zip_sriov_configure(struct pci_dev *pdev, int num_vfs) +{ + if (num_vfs == 0) + return hisi_zip_sriov_disable(pdev); + else + return hisi_zip_sriov_enable(pdev, num_vfs); +} + +static void hisi_zip_log_hw_error(struct hisi_zip *hisi_zip, u32 err_sts) +{ + const struct hisi_zip_hw_error *err = zip_hw_error; + struct device *dev = &hisi_zip->qm.pdev->dev; + u32 err_val; + + while (err->msg) { + if (err->int_msk & err_sts) { + dev_warn(dev, "%s [error status=0x%x] found\n", + err->msg, err->int_msk); + + if (HZIP_CORE_INT_STATUS_M_ECC & err_sts) { + err_val = readl(hisi_zip->qm.io_base + + HZIP_CORE_SRAM_ECC_ERR_INFO); + dev_warn(dev, "hisi-zip multi ecc sram num=0x%x\n", + ((err_val >> 16) & 0xFF)); + dev_warn(dev, "hisi-zip multi ecc sram addr=0x%x\n", + (err_val >> 24)); + } + } + err++; + } +} + +static pci_ers_result_t hisi_zip_hw_error_handle(struct hisi_zip *hisi_zip) +{ + u32 err_sts; + + /* read err sts */ + err_sts = readl(hisi_zip->qm.io_base + HZIP_CORE_INT_STATUS); + + if (err_sts) { + hisi_zip_log_hw_error(hisi_zip, err_sts); + /* clear error interrupts */ + writel(err_sts, hisi_zip->qm.io_base + HZIP_CORE_INT_SOURCE); + + return PCI_ERS_RESULT_NEED_RESET; + } + + return PCI_ERS_RESULT_NONE; +} + +static pci_ers_result_t hisi_zip_process_hw_error(struct pci_dev *pdev) +{ + struct hisi_zip *hisi_zip = pci_get_drvdata(pdev); + struct device *dev = &pdev->dev; + pci_ers_result_t qm_ret, zip_ret; + + if (!hisi_zip) { + dev_err(dev, + "Can't recover ZIP-error occurred during device init\n"); + return PCI_ERS_RESULT_NONE; + } + + /* log qm error */ + qm_ret = hisi_qm_hw_error_handle(&hisi_zip->qm); + + /* log zip error */ + zip_ret = hisi_zip_hw_error_handle(hisi_zip); + + return (qm_ret == PCI_ERS_RESULT_NEED_RESET || + zip_ret == PCI_ERS_RESULT_NEED_RESET) ? + PCI_ERS_RESULT_NEED_RESET : PCI_ERS_RESULT_NONE; +} + +static pci_ers_result_t hisi_zip_error_detected(struct pci_dev *pdev, + pci_channel_state_t state) +{ + dev_info(&pdev->dev, "PCI error detected, state(=%d)!!\n", state); + if (state == pci_channel_io_perm_failure) + return PCI_ERS_RESULT_DISCONNECT; + + return hisi_zip_process_hw_error(pdev); +} + +static int hisi_zip_controller_reset_prepare(struct hisi_zip *hisi_zip) +{ + struct hisi_qm *qm = &hisi_zip->qm; + struct pci_dev *pdev = qm->pdev; + int ret; + + ret = hisi_qm_stop(qm); + if (ret) { + dev_err(&pdev->dev, "Fails to stop QM!\n"); + return ret; + } + + if (test_and_set_bit(QM_RESET, &qm->flags)) { + dev_warn(&pdev->dev, "Failed to set reset flag!"); + return -EPERM; + } + + /* If having VFs enable, let's disable them firstly */ + if (hisi_zip->ctrl->num_vfs) { + ret = hisi_zip_sriov_disable(pdev); + if (ret) { + dev_err(&pdev->dev, "Fails to disable VFs!\n"); + return ret; + } + } + + return 0; +} + +static void hisi_zip_set_mse(struct hisi_zip *hisi_zip, bool set) +{ + struct pci_dev *pdev = hisi_zip->qm.pdev; + u16 sriov_ctrl; + int pos; + + pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_SRIOV); + pci_read_config_word(pdev, pos + PCI_SRIOV_CTRL, &sriov_ctrl); + if (set) + sriov_ctrl |= PCI_SRIOV_CTRL_MSE; + else + sriov_ctrl &= ~PCI_SRIOV_CTRL_MSE; + pci_write_config_word(pdev, pos + PCI_SRIOV_CTRL, sriov_ctrl); +} + +static int hisi_zip_soft_reset(struct hisi_zip *hisi_zip) +{ + struct hisi_qm *qm = &hisi_zip->qm; + struct device *dev = &qm->pdev->dev; + int ret; + u32 val; + + /* Set VF MSE bit */ + hisi_zip_set_mse(hisi_zip, 1); + + /* OOO register set and check */ + writel(MASTER_GLOBAL_CTRL_SHUTDOWN, + hisi_zip->qm.io_base + HZIP_MASTER_GLOBAL_CTRL); + + /* If bus lock, reset chip */ + ret = readl_relaxed_poll_timeout(hisi_zip->qm.io_base + + HZIP_MASTER_TRANS_RETURN, val, + (val == MASTER_TRANS_RETURN_RW), 10, + 1000); + if (ret) { + dev_emerg(dev, "Bus lock! Please reset system.\n"); + return ret; + } + + /* The reset related sub-control registers are not in PCI BAR */ + if (ACPI_HANDLE(dev)) { + acpi_status s; + + s = acpi_evaluate_object(ACPI_HANDLE(dev), "_RST", NULL, NULL); + if (ACPI_FAILURE(s)) { + dev_err(dev, "Controller reset fails\n"); + return -EIO; + } + } else { + dev_err(dev, "No reset method!\n"); + return -EINVAL; + } + + return 0; +} + +static int hisi_zip_controller_reset_done(struct hisi_zip *hisi_zip) +{ + struct hisi_qm *qm = &hisi_zip->qm; + struct pci_dev *pdev = qm->pdev; + struct hisi_qp *qp; + int i, ret; + + hisi_qm_clear_queues(qm); + + ret = hisi_qm_mem_start(qm); + if (ret) + return ret; + + hisi_zip_set_user_domain_and_cache(hisi_zip); + + ret = hisi_qm_start(qm); + if (ret) { + dev_err(&pdev->dev, "Failed to start QM!\n"); + return -EPERM; + } + + for (i = 0; i < qm->qp_num; i++) { + qp = qm->qp_array[i]; + if (qp) { + ret = hisi_qm_start_qp(qp, 0); + if (ret < 0) { + dev_err(&pdev->dev, "Start qp%d failed\n", i); + return -EPERM; + } + } + } + + ret = hisi_zip_sriov_enable(pdev, pci_num_vf(pdev)); + if (ret) { + dev_err(&pdev->dev, "Can't enable VFs!\n"); + return ret; + } + + /* Clear VF MSE bit */ + hisi_zip_set_mse(hisi_zip, 0); + + return 0; +} + +static int hisi_zip_controller_reset(struct hisi_zip *hisi_zip) +{ + struct device *dev = &hisi_zip->qm.pdev->dev; + int ret; + + dev_info(dev, "Controller resetting...\n"); + + ret = hisi_zip_controller_reset_prepare(hisi_zip); + if (ret) + return ret; + + ret = hisi_zip_soft_reset(hisi_zip); + if (ret) { + dev_err(dev, "Controller reset failed (%d)\n", ret); + return ret; + } + + ret = hisi_zip_controller_reset_done(hisi_zip); + if (ret) + return ret; + + dev_info(dev, "Controller reset complete\n"); + clear_bit(QM_RESET, &hisi_zip->qm.flags); + + return 0; +} + +static pci_ers_result_t hisi_zip_slot_reset(struct pci_dev *pdev) +{ + struct hisi_zip *hisi_zip = pci_get_drvdata(pdev); + int ret; + + dev_info(&pdev->dev, "Requesting reset due to PCI error\n"); + + pci_cleanup_aer_uncorrect_error_status(pdev); + + /* reset zip controller */ + ret = hisi_zip_controller_reset(hisi_zip); + if (ret) { + dev_warn(&pdev->dev, "hisi_zip controller reset failed (%d)\n", + ret); + return PCI_ERS_RESULT_DISCONNECT; + } + + return PCI_ERS_RESULT_RECOVERED; +} + +static void hisi_zip_reset_prepare(struct pci_dev *pdev) +{ + struct hisi_zip *hisi_zip = pci_get_drvdata(pdev); + struct hisi_qm *qm = &hisi_zip->qm; + struct device *dev = &pdev->dev; + int ret; + + ret = hisi_qm_stop(qm); + if (ret) { + dev_err(&pdev->dev, "Fails to stop QM!\n"); + return; + } + + if (test_and_set_bit(QM_RESET, &qm->flags)) { + dev_warn(dev, "Failed to set reset flag!"); + return; + } + + /* If having VFs in PF, disable VFs before PF FLR */ + if (pdev->is_physfn && hisi_zip->ctrl->num_vfs) { + ret = hisi_zip_sriov_disable(pdev); + if (ret) { + dev_err(dev, "Fails to disable VFs\n"); + return; + } + } + + dev_info(dev, "FLR resetting...\n"); +} + +static void hisi_zip_reset_done(struct pci_dev *pdev) +{ + struct hisi_zip *hisi_zip = pci_get_drvdata(pdev); + struct hisi_qm *qm = &hisi_zip->qm; + struct device *dev = &pdev->dev; + struct hisi_qp *qp; + int i, ret; + + if (pdev->is_physfn) { + hisi_qm_clear_queues(qm); + + ret = hisi_qm_mem_start(qm); + if (ret) { + dev_err(dev, "QM can't init memory\n"); + return; + } + + hisi_zip_set_user_domain_and_cache(hisi_zip); + + ret = hisi_qm_start(qm); + if (ret) { + dev_err(dev, "Failed to start QM!\n"); + return; + } + + for (i = 0; i < qm->qp_num; i++) { + qp = qm->qp_array[i]; + if (qp) { + ret = hisi_qm_start_qp(qp, 0); + if (ret < 0) { + dev_err(dev, "Start qp%d failed\n", i); + return; + } + } + } + + ret = hisi_zip_sriov_enable(pdev, pci_num_vf(pdev)); + if (ret) { + dev_err(dev, "Can't enable VFs!\n"); + return; + } + + dev_info(dev, "FLR reset complete\n"); + } +} + +static const struct pci_error_handlers hisi_zip_err_handler = { + .error_detected = hisi_zip_error_detected, + .slot_reset = hisi_zip_slot_reset, + .reset_prepare = hisi_zip_reset_prepare, + .reset_done = hisi_zip_reset_done, +}; + +static struct pci_driver hisi_zip_pci_driver = { + .name = "hisi_zip", + .id_table = hisi_zip_dev_ids, + .probe = hisi_zip_probe, + .remove = hisi_zip_remove, + .sriov_configure = hisi_zip_sriov_configure, + .err_handler = &hisi_zip_err_handler, +}; + +static void hisi_zip_register_debugfs(void) +{ + if (!debugfs_initialized()) + return; + + hzip_debugfs_root = debugfs_create_dir("hisi_zip", NULL); + if (IS_ERR_OR_NULL(hzip_debugfs_root)) + hzip_debugfs_root = NULL; +} + +static void hisi_zip_unregister_debugfs(void) +{ + debugfs_remove_recursive(hzip_debugfs_root); +} + +static int __init hisi_zip_init(void) +{ + int ret; + + hisi_zip_register_debugfs(); + + ret = pci_register_driver(&hisi_zip_pci_driver); + if (ret < 0) { + pr_err("Failed to register pci driver.\n"); + goto err_pci; + } + + ret = hisi_zip_register_to_crypto(); + if (ret < 0) { + pr_err("Failed to register driver to crypto.\n"); + goto err_crypto; + } + + return 0; + +err_crypto: + pci_unregister_driver(&hisi_zip_pci_driver); +err_pci: + hisi_zip_unregister_debugfs(); + + return ret; +} + +static void __exit hisi_zip_exit(void) +{ + hisi_zip_unregister_from_crypto(); + pci_unregister_driver(&hisi_zip_pci_driver); + hisi_zip_unregister_debugfs(); +} + +module_init(hisi_zip_init); +module_exit(hisi_zip_exit); + +MODULE_LICENSE("GPL v2"); +MODULE_AUTHOR("Zhou Wang "); +MODULE_DESCRIPTION("Driver for HiSilicon ZIP accelerator"); From patchwork Thu Dec 13 11:22:11 2018 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 8bit X-Patchwork-Submitter: Zhou Wang X-Patchwork-Id: 153634 Delivered-To: patch@linaro.org Received: by 2002:a2e:299d:0:0:0:0:0 with SMTP id p29-v6csp680813ljp; Thu, 13 Dec 2018 03:22:30 -0800 (PST) X-Google-Smtp-Source: AFSGD/XwXyG3a6PqEk2m+cuqgqCLDt3DjciDMLQVzrYhPstcaUojmixdqBYARwmtunMicswKf6dD X-Received: by 2002:a63:c848:: with SMTP id l8mr838024pgi.78.1544700150515; Thu, 13 Dec 2018 03:22:30 -0800 (PST) ARC-Seal: i=1; a=rsa-sha256; t=1544700150; cv=none; d=google.com; s=arc-20160816; b=yFss4YbkKOcCNEKjgOcRls5pK5CnMFHCx3Dw9rjCAa9dAsGVkAdhUqIJmI4KfwCML+ WiKELNcejH+D1aVfwZjEV+utS1pdAnqxyO1wlnfsBy79LrCwuSfFr1aI7Nf54jlSwXW4 L6VBq0x43/olkhJTGwKb2s9X55jLrV6t+R17V3HDkcyD/8s0tkpzCDmzm5mDxq4K44fr 7mUDO2lCKk5ZkVZnry2+Ii8h4zeuiVqMDPHmoH4yvllN4MgxJn4XisS1+63ugW9HcGWf 1MOf+5/NYgiOJRTwQlw3a7th4jkiiSaYIWpAjivSDmuiXWbTcbJrylhNXUpUEn38x/Hg 5bxA== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=arc-20160816; h=list-id:precedence:sender:content-transfer-encoding:mime-version :references:in-reply-to:message-id:date:subject:cc:to:from; bh=PF6PknHZWTfLEmXbOpSyx0eze3SV6zO1SnOEXjXJdXE=; b=Vt9OQC7GTuWT0hjILmG31YXRQrfiQIzsEfTNDPwpqGzow+Ag3yIsQk3H+qRyQXEE9v p3uFybx2aAhKQ3xWFO2Et621MotBcZBF2eyT2/SRKZPXlPniGuMGqpnAUW28TYbkZmSC d16FKs4AeD3vTa1oPAbbvzhVABHS6uu89jtUG0UOBikl8hlsQZhjdCqXKXz8euzmBaN/ gwY6Z1pMBmbkc0ubDRLVZT+1e4mck9kRzPrvlgNNIyLQWzhr9A6nm+so2BRvt08KEi6a +XKrE5F9uDFUi8YIqsB5guyV0bDLL4vrWLYqy4Ut++MgYpkDJ4XXlHe6k2Xe6/VwHEPe cW6Q== ARC-Authentication-Results: i=1; mx.google.com; spf=pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) smtp.mailfrom=linux-kernel-owner@vger.kernel.org Return-Path: Received: from vger.kernel.org (vger.kernel.org. [209.132.180.67]) by mx.google.com with ESMTP id u188si1396175pfb.232.2018.12.13.03.22.30; Thu, 13 Dec 2018 03:22:30 -0800 (PST) Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67; Authentication-Results: mx.google.com; spf=pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) smtp.mailfrom=linux-kernel-owner@vger.kernel.org Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1728838AbeLMLW2 (ORCPT + 31 others); Thu, 13 Dec 2018 06:22:28 -0500 Received: from szxga06-in.huawei.com ([45.249.212.32]:50927 "EHLO huawei.com" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1728746AbeLMLWP (ORCPT ); Thu, 13 Dec 2018 06:22:15 -0500 Received: from DGGEMS413-HUB.china.huawei.com (unknown [172.30.72.60]) by Forcepoint Email with ESMTP id 2A867737A65E2; Thu, 13 Dec 2018 19:22:11 +0800 (CST) Received: from localhost.localdomain (10.67.212.75) by DGGEMS413-HUB.china.huawei.com (10.3.19.213) with Microsoft SMTP Server id 14.3.408.0; Thu, 13 Dec 2018 19:22:05 +0800 From: Zhou Wang To: Herbert Xu , "David S . Miller" , CC: , , Zhou Wang Subject: [PATCH RFC 4/4] MAINTAINERS: add maintainer for HiSilicon QM and ZIP controller driver Date: Thu, 13 Dec 2018 19:22:11 +0800 Message-ID: <1544700131-196846-5-git-send-email-wangzhou1@hisilicon.com> X-Mailer: git-send-email 2.8.1 In-Reply-To: <1544700131-196846-1-git-send-email-wangzhou1@hisilicon.com> References: <1544700131-196846-1-git-send-email-wangzhou1@hisilicon.com> MIME-Version: 1.0 X-Originating-IP: [10.67.212.75] X-CFilter-Loop: Reflected Sender: linux-kernel-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Add Zhou Wang as a maintainer for HiSilicon QM and ZIP controller driver. Signed-off-by: Zhou Wang reviewed-by: John Garry --- MAINTAINERS | 8 ++++++++ 1 file changed, 8 insertions(+) -- 2.8.1 diff --git a/MAINTAINERS b/MAINTAINERS index 0767f1d..5be84e2 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -6785,6 +6785,14 @@ S: Supported F: drivers/scsi/hisi_sas/ F: Documentation/devicetree/bindings/scsi/hisilicon-sas.txt +HISILICON QM AND ZIP Controller DRIVER +M: Zhou Wang +L: linux-crypto@vger.kernel.org +S: Maintained +F: drivers/crypto/hisilicon/qm.c +F: drivers/crypto/hisilicon/qm.h +F: drivers/crypto/hisilicon/zip/ + HMM - Heterogeneous Memory Management M: Jérôme Glisse L: linux-mm@kvack.org