From patchwork Wed Jul 27 01:49:20 2022 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Cheng Xu X-Patchwork-Id: 12929955 X-Patchwork-Delegate: jgg@ziepe.ca Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 11AC8C19F21 for ; Wed, 27 Jul 2022 01:49:43 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S240188AbiG0Btl (ORCPT ); Tue, 26 Jul 2022 21:49:41 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:54636 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S233245AbiG0Btj (ORCPT ); Tue, 26 Jul 2022 21:49:39 -0400 Received: from out199-6.us.a.mail.aliyun.com (out199-6.us.a.mail.aliyun.com [47.90.199.6]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id E64EB39B85 for ; Tue, 26 Jul 2022 18:49:36 -0700 (PDT) X-Alimail-AntiSpam: AC=PASS;BC=-1|-1;BR=01201311R981e4;CH=green;DM=||false|;DS=||;FP=0|-1|-1|-1|0|-1|-1|-1;HT=ay29a033018046050;MF=chengyou@linux.alibaba.com;NM=1;PH=DS;RN=6;SR=0;TI=SMTPD_---0VKYVUU4_1658886572; Received: from localhost(mailfrom:chengyou@linux.alibaba.com fp:SMTPD_---0VKYVUU4_1658886572) by smtp.aliyun-inc.com; Wed, 27 Jul 2022 09:49:33 +0800 From: Cheng Xu To: jgg@ziepe.ca, leon@kernel.org Cc: linux-rdma@vger.kernel.org, KaiShen@linux.alibaba.com, chengyou@linux.alibaba.com, tonylu@linux.alibaba.com Subject: [PATCH for-next v14 04/11] RDMA/erdma: Add cmdq implementation Date: Wed, 27 Jul 2022 09:49:20 +0800 Message-Id: <20220727014927.76564-5-chengyou@linux.alibaba.com> X-Mailer: git-send-email 2.37.0 In-Reply-To: <20220727014927.76564-1-chengyou@linux.alibaba.com> References: <20220727014927.76564-1-chengyou@linux.alibaba.com> MIME-Version: 1.0 Precedence: bulk List-ID: X-Mailing-List: linux-rdma@vger.kernel.org Cmdq is the main control plane channel between erdma driver and hardware. After erdma device is initialized, the cmdq channel will be active in the whole lifecycle of this driver. This commit also includes two modifications from Christophe, one is using the bitmap API to allocate bitmaps instead of hand-writing, and another is using the non-atomic bitmap API when applicable. Signed-off-by: Christophe JAILLET Signed-off-by: Cheng Xu --- drivers/infiniband/hw/erdma/erdma_cmdq.c | 493 +++++++++++++++++++++++ 1 file changed, 493 insertions(+) create mode 100644 drivers/infiniband/hw/erdma/erdma_cmdq.c diff --git a/drivers/infiniband/hw/erdma/erdma_cmdq.c b/drivers/infiniband/hw/erdma/erdma_cmdq.c new file mode 100644 index 000000000000..57da0c670472 --- /dev/null +++ b/drivers/infiniband/hw/erdma/erdma_cmdq.c @@ -0,0 +1,493 @@ +// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause + +/* Authors: Cheng Xu */ +/* Kai Shen */ +/* Copyright (c) 2020-2022, Alibaba Group. */ + +#include +#include +#include + +#include "erdma.h" +#include "erdma_hw.h" +#include "erdma_verbs.h" + +static void arm_cmdq_cq(struct erdma_cmdq *cmdq) +{ + struct erdma_dev *dev = container_of(cmdq, struct erdma_dev, cmdq); + u64 db_data = FIELD_PREP(ERDMA_CQDB_CI_MASK, cmdq->cq.ci) | + FIELD_PREP(ERDMA_CQDB_ARM_MASK, 1) | + FIELD_PREP(ERDMA_CQDB_CMDSN_MASK, cmdq->cq.cmdsn) | + FIELD_PREP(ERDMA_CQDB_IDX_MASK, cmdq->cq.cmdsn); + + *cmdq->cq.db_record = db_data; + writeq(db_data, dev->func_bar + ERDMA_CMDQ_CQDB_REG); + + atomic64_inc(&cmdq->cq.armed_num); +} + +static void kick_cmdq_db(struct erdma_cmdq *cmdq) +{ + struct erdma_dev *dev = container_of(cmdq, struct erdma_dev, cmdq); + u64 db_data = FIELD_PREP(ERDMA_CMD_HDR_WQEBB_INDEX_MASK, cmdq->sq.pi); + + *cmdq->sq.db_record = db_data; + writeq(db_data, dev->func_bar + ERDMA_CMDQ_SQDB_REG); +} + +static struct erdma_comp_wait *get_comp_wait(struct erdma_cmdq *cmdq) +{ + int comp_idx; + + spin_lock(&cmdq->lock); + comp_idx = find_first_zero_bit(cmdq->comp_wait_bitmap, + cmdq->max_outstandings); + if (comp_idx == cmdq->max_outstandings) { + spin_unlock(&cmdq->lock); + return ERR_PTR(-ENOMEM); + } + + __set_bit(comp_idx, cmdq->comp_wait_bitmap); + spin_unlock(&cmdq->lock); + + return &cmdq->wait_pool[comp_idx]; +} + +static void put_comp_wait(struct erdma_cmdq *cmdq, + struct erdma_comp_wait *comp_wait) +{ + int used; + + cmdq->wait_pool[comp_wait->ctx_id].cmd_status = ERDMA_CMD_STATUS_INIT; + spin_lock(&cmdq->lock); + used = __test_and_clear_bit(comp_wait->ctx_id, cmdq->comp_wait_bitmap); + spin_unlock(&cmdq->lock); + + WARN_ON(!used); +} + +static int erdma_cmdq_wait_res_init(struct erdma_dev *dev, + struct erdma_cmdq *cmdq) +{ + int i; + + cmdq->wait_pool = + devm_kcalloc(&dev->pdev->dev, cmdq->max_outstandings, + sizeof(struct erdma_comp_wait), GFP_KERNEL); + if (!cmdq->wait_pool) + return -ENOMEM; + + spin_lock_init(&cmdq->lock); + cmdq->comp_wait_bitmap = devm_bitmap_zalloc( + &dev->pdev->dev, cmdq->max_outstandings, GFP_KERNEL); + if (!cmdq->comp_wait_bitmap) + return -ENOMEM; + + for (i = 0; i < cmdq->max_outstandings; i++) { + init_completion(&cmdq->wait_pool[i].wait_event); + cmdq->wait_pool[i].ctx_id = i; + } + + return 0; +} + +static int erdma_cmdq_sq_init(struct erdma_dev *dev) +{ + struct erdma_cmdq *cmdq = &dev->cmdq; + struct erdma_cmdq_sq *sq = &cmdq->sq; + u32 buf_size; + + sq->wqebb_cnt = SQEBB_COUNT(ERDMA_CMDQ_SQE_SIZE); + sq->depth = cmdq->max_outstandings * sq->wqebb_cnt; + + buf_size = sq->depth << SQEBB_SHIFT; + + sq->qbuf = + dma_alloc_coherent(&dev->pdev->dev, WARPPED_BUFSIZE(buf_size), + &sq->qbuf_dma_addr, GFP_KERNEL); + if (!sq->qbuf) + return -ENOMEM; + + sq->db_record = (u64 *)(sq->qbuf + buf_size); + + spin_lock_init(&sq->lock); + + erdma_reg_write32(dev, ERDMA_REGS_CMDQ_SQ_ADDR_H_REG, + upper_32_bits(sq->qbuf_dma_addr)); + erdma_reg_write32(dev, ERDMA_REGS_CMDQ_SQ_ADDR_L_REG, + lower_32_bits(sq->qbuf_dma_addr)); + erdma_reg_write32(dev, ERDMA_REGS_CMDQ_DEPTH_REG, sq->depth); + erdma_reg_write64(dev, ERDMA_CMDQ_SQ_DB_HOST_ADDR_REG, + sq->qbuf_dma_addr + buf_size); + + return 0; +} + +static int erdma_cmdq_cq_init(struct erdma_dev *dev) +{ + struct erdma_cmdq *cmdq = &dev->cmdq; + struct erdma_cmdq_cq *cq = &cmdq->cq; + u32 buf_size; + + cq->depth = cmdq->sq.depth; + buf_size = cq->depth << CQE_SHIFT; + + cq->qbuf = + dma_alloc_coherent(&dev->pdev->dev, WARPPED_BUFSIZE(buf_size), + &cq->qbuf_dma_addr, GFP_KERNEL | __GFP_ZERO); + if (!cq->qbuf) + return -ENOMEM; + + spin_lock_init(&cq->lock); + + cq->db_record = (u64 *)(cq->qbuf + buf_size); + + atomic64_set(&cq->armed_num, 0); + + erdma_reg_write32(dev, ERDMA_REGS_CMDQ_CQ_ADDR_H_REG, + upper_32_bits(cq->qbuf_dma_addr)); + erdma_reg_write32(dev, ERDMA_REGS_CMDQ_CQ_ADDR_L_REG, + lower_32_bits(cq->qbuf_dma_addr)); + erdma_reg_write64(dev, ERDMA_CMDQ_CQ_DB_HOST_ADDR_REG, + cq->qbuf_dma_addr + buf_size); + + return 0; +} + +static int erdma_cmdq_eq_init(struct erdma_dev *dev) +{ + struct erdma_cmdq *cmdq = &dev->cmdq; + struct erdma_eq *eq = &cmdq->eq; + u32 buf_size; + + eq->depth = cmdq->max_outstandings; + buf_size = eq->depth << EQE_SHIFT; + + eq->qbuf = + dma_alloc_coherent(&dev->pdev->dev, WARPPED_BUFSIZE(buf_size), + &eq->qbuf_dma_addr, GFP_KERNEL | __GFP_ZERO); + if (!eq->qbuf) + return -ENOMEM; + + spin_lock_init(&eq->lock); + atomic64_set(&eq->event_num, 0); + + eq->db_addr = + (u64 __iomem *)(dev->func_bar + ERDMA_REGS_CEQ_DB_BASE_REG); + eq->db_record = (u64 *)(eq->qbuf + buf_size); + + erdma_reg_write32(dev, ERDMA_REGS_CMDQ_EQ_ADDR_H_REG, + upper_32_bits(eq->qbuf_dma_addr)); + erdma_reg_write32(dev, ERDMA_REGS_CMDQ_EQ_ADDR_L_REG, + lower_32_bits(eq->qbuf_dma_addr)); + erdma_reg_write32(dev, ERDMA_REGS_CMDQ_EQ_DEPTH_REG, eq->depth); + erdma_reg_write64(dev, ERDMA_CMDQ_EQ_DB_HOST_ADDR_REG, + eq->qbuf_dma_addr + buf_size); + + return 0; +} + +int erdma_cmdq_init(struct erdma_dev *dev) +{ + int err, i; + struct erdma_cmdq *cmdq = &dev->cmdq; + u32 sts, ctrl; + + cmdq->max_outstandings = ERDMA_CMDQ_MAX_OUTSTANDING; + cmdq->use_event = false; + + sema_init(&cmdq->credits, cmdq->max_outstandings); + + err = erdma_cmdq_wait_res_init(dev, cmdq); + if (err) + return err; + + err = erdma_cmdq_sq_init(dev); + if (err) + return err; + + err = erdma_cmdq_cq_init(dev); + if (err) + goto err_destroy_sq; + + err = erdma_cmdq_eq_init(dev); + if (err) + goto err_destroy_cq; + + ctrl = FIELD_PREP(ERDMA_REG_DEV_CTRL_INIT_MASK, 1); + erdma_reg_write32(dev, ERDMA_REGS_DEV_CTRL_REG, ctrl); + + for (i = 0; i < ERDMA_WAIT_DEV_DONE_CNT; i++) { + sts = erdma_reg_read32_filed(dev, ERDMA_REGS_DEV_ST_REG, + ERDMA_REG_DEV_ST_INIT_DONE_MASK); + if (sts) + break; + + msleep(ERDMA_REG_ACCESS_WAIT_MS); + } + + if (i == ERDMA_WAIT_DEV_DONE_CNT) { + dev_err(&dev->pdev->dev, "wait init done failed.\n"); + err = -ETIMEDOUT; + goto err_destroy_eq; + } + + set_bit(ERDMA_CMDQ_STATE_OK_BIT, &cmdq->state); + + return 0; + +err_destroy_eq: + dma_free_coherent(&dev->pdev->dev, + (cmdq->eq.depth << EQE_SHIFT) + + ERDMA_EXTRA_BUFFER_SIZE, + cmdq->eq.qbuf, cmdq->eq.qbuf_dma_addr); + +err_destroy_cq: + dma_free_coherent(&dev->pdev->dev, + (cmdq->cq.depth << CQE_SHIFT) + + ERDMA_EXTRA_BUFFER_SIZE, + cmdq->cq.qbuf, cmdq->cq.qbuf_dma_addr); + +err_destroy_sq: + dma_free_coherent(&dev->pdev->dev, + (cmdq->sq.depth << SQEBB_SHIFT) + + ERDMA_EXTRA_BUFFER_SIZE, + cmdq->sq.qbuf, cmdq->sq.qbuf_dma_addr); + + return err; +} + +void erdma_finish_cmdq_init(struct erdma_dev *dev) +{ + /* after device init successfully, change cmdq to event mode. */ + dev->cmdq.use_event = true; + arm_cmdq_cq(&dev->cmdq); +} + +void erdma_cmdq_destroy(struct erdma_dev *dev) +{ + struct erdma_cmdq *cmdq = &dev->cmdq; + + clear_bit(ERDMA_CMDQ_STATE_OK_BIT, &cmdq->state); + + dma_free_coherent(&dev->pdev->dev, + (cmdq->eq.depth << EQE_SHIFT) + + ERDMA_EXTRA_BUFFER_SIZE, + cmdq->eq.qbuf, cmdq->eq.qbuf_dma_addr); + dma_free_coherent(&dev->pdev->dev, + (cmdq->sq.depth << SQEBB_SHIFT) + + ERDMA_EXTRA_BUFFER_SIZE, + cmdq->sq.qbuf, cmdq->sq.qbuf_dma_addr); + dma_free_coherent(&dev->pdev->dev, + (cmdq->cq.depth << CQE_SHIFT) + + ERDMA_EXTRA_BUFFER_SIZE, + cmdq->cq.qbuf, cmdq->cq.qbuf_dma_addr); +} + +static void *get_next_valid_cmdq_cqe(struct erdma_cmdq *cmdq) +{ + __be32 *cqe = get_queue_entry(cmdq->cq.qbuf, cmdq->cq.ci, + cmdq->cq.depth, CQE_SHIFT); + u32 owner = FIELD_GET(ERDMA_CQE_HDR_OWNER_MASK, + __be32_to_cpu(READ_ONCE(*cqe))); + + return owner ^ !!(cmdq->cq.ci & cmdq->cq.depth) ? cqe : NULL; +} + +static void push_cmdq_sqe(struct erdma_cmdq *cmdq, u64 *req, size_t req_len, + struct erdma_comp_wait *comp_wait) +{ + __le64 *wqe; + u64 hdr = *req; + + comp_wait->cmd_status = ERDMA_CMD_STATUS_ISSUED; + reinit_completion(&comp_wait->wait_event); + comp_wait->sq_pi = cmdq->sq.pi; + + wqe = get_queue_entry(cmdq->sq.qbuf, cmdq->sq.pi, cmdq->sq.depth, + SQEBB_SHIFT); + memcpy(wqe, req, req_len); + + cmdq->sq.pi += cmdq->sq.wqebb_cnt; + hdr |= FIELD_PREP(ERDMA_CMD_HDR_WQEBB_INDEX_MASK, cmdq->sq.pi) | + FIELD_PREP(ERDMA_CMD_HDR_CONTEXT_COOKIE_MASK, + comp_wait->ctx_id) | + FIELD_PREP(ERDMA_CMD_HDR_WQEBB_CNT_MASK, cmdq->sq.wqebb_cnt - 1); + *wqe = cpu_to_le64(hdr); + + kick_cmdq_db(cmdq); +} + +static int erdma_poll_single_cmd_completion(struct erdma_cmdq *cmdq) +{ + struct erdma_comp_wait *comp_wait; + u32 hdr0, sqe_idx; + __be32 *cqe; + u16 ctx_id; + u64 *sqe; + int i; + + cqe = get_next_valid_cmdq_cqe(cmdq); + if (!cqe) + return -EAGAIN; + + cmdq->cq.ci++; + + dma_rmb(); + hdr0 = __be32_to_cpu(*cqe); + sqe_idx = __be32_to_cpu(*(cqe + 1)); + + sqe = get_queue_entry(cmdq->sq.qbuf, sqe_idx, cmdq->sq.depth, + SQEBB_SHIFT); + ctx_id = FIELD_GET(ERDMA_CMD_HDR_CONTEXT_COOKIE_MASK, *sqe); + comp_wait = &cmdq->wait_pool[ctx_id]; + if (comp_wait->cmd_status != ERDMA_CMD_STATUS_ISSUED) + return -EIO; + + comp_wait->cmd_status = ERDMA_CMD_STATUS_FINISHED; + comp_wait->comp_status = FIELD_GET(ERDMA_CQE_HDR_SYNDROME_MASK, hdr0); + cmdq->sq.ci += cmdq->sq.wqebb_cnt; + + for (i = 0; i < 4; i++) + comp_wait->comp_data[i] = __be32_to_cpu(*(cqe + 2 + i)); + + if (cmdq->use_event) + complete(&comp_wait->wait_event); + + return 0; +} + +static void erdma_polling_cmd_completions(struct erdma_cmdq *cmdq) +{ + unsigned long flags; + u16 comp_num; + + spin_lock_irqsave(&cmdq->cq.lock, flags); + + /* We must have less than # of max_outstandings + * completions at one time. + */ + for (comp_num = 0; comp_num < cmdq->max_outstandings; comp_num++) + if (erdma_poll_single_cmd_completion(cmdq)) + break; + + if (comp_num && cmdq->use_event) + arm_cmdq_cq(cmdq); + + spin_unlock_irqrestore(&cmdq->cq.lock, flags); +} + +void erdma_cmdq_completion_handler(struct erdma_cmdq *cmdq) +{ + int got_event = 0; + + if (!test_bit(ERDMA_CMDQ_STATE_OK_BIT, &cmdq->state) || + !cmdq->use_event) + return; + + while (get_next_valid_eqe(&cmdq->eq)) { + cmdq->eq.ci++; + got_event++; + } + + if (got_event) { + cmdq->cq.cmdsn++; + erdma_polling_cmd_completions(cmdq); + } + + notify_eq(&cmdq->eq); +} + +static int erdma_poll_cmd_completion(struct erdma_comp_wait *comp_ctx, + struct erdma_cmdq *cmdq, u32 timeout) +{ + unsigned long comp_timeout = jiffies + msecs_to_jiffies(timeout); + + while (1) { + erdma_polling_cmd_completions(cmdq); + if (comp_ctx->cmd_status != ERDMA_CMD_STATUS_ISSUED) + break; + + if (time_is_before_jiffies(comp_timeout)) + return -ETIME; + + msleep(20); + } + + return 0; +} + +static int erdma_wait_cmd_completion(struct erdma_comp_wait *comp_ctx, + struct erdma_cmdq *cmdq, u32 timeout) +{ + unsigned long flags = 0; + + wait_for_completion_timeout(&comp_ctx->wait_event, + msecs_to_jiffies(timeout)); + + if (unlikely(comp_ctx->cmd_status != ERDMA_CMD_STATUS_FINISHED)) { + spin_lock_irqsave(&cmdq->cq.lock, flags); + comp_ctx->cmd_status = ERDMA_CMD_STATUS_TIMEOUT; + spin_unlock_irqrestore(&cmdq->cq.lock, flags); + return -ETIME; + } + + return 0; +} + +void erdma_cmdq_build_reqhdr(u64 *hdr, u32 mod, u32 op) +{ + *hdr = FIELD_PREP(ERDMA_CMD_HDR_SUB_MOD_MASK, mod) | + FIELD_PREP(ERDMA_CMD_HDR_OPCODE_MASK, op); +} + +int erdma_post_cmd_wait(struct erdma_cmdq *cmdq, u64 *req, u32 req_size, + u64 *resp0, u64 *resp1) +{ + struct erdma_comp_wait *comp_wait; + int ret; + + if (!test_bit(ERDMA_CMDQ_STATE_OK_BIT, &cmdq->state)) + return -ENODEV; + + down(&cmdq->credits); + + comp_wait = get_comp_wait(cmdq); + if (IS_ERR(comp_wait)) { + clear_bit(ERDMA_CMDQ_STATE_OK_BIT, &cmdq->state); + set_bit(ERDMA_CMDQ_STATE_CTX_ERR_BIT, &cmdq->state); + up(&cmdq->credits); + return PTR_ERR(comp_wait); + } + + spin_lock(&cmdq->sq.lock); + push_cmdq_sqe(cmdq, req, req_size, comp_wait); + spin_unlock(&cmdq->sq.lock); + + if (cmdq->use_event) + ret = erdma_wait_cmd_completion(comp_wait, cmdq, + ERDMA_CMDQ_TIMEOUT_MS); + else + ret = erdma_poll_cmd_completion(comp_wait, cmdq, + ERDMA_CMDQ_TIMEOUT_MS); + + if (ret) { + set_bit(ERDMA_CMDQ_STATE_TIMEOUT_BIT, &cmdq->state); + clear_bit(ERDMA_CMDQ_STATE_OK_BIT, &cmdq->state); + goto out; + } + + if (comp_wait->comp_status) + ret = -EIO; + + if (resp0 && resp1) { + *resp0 = *((u64 *)&comp_wait->comp_data[0]); + *resp1 = *((u64 *)&comp_wait->comp_data[2]); + } + put_comp_wait(cmdq, comp_wait); + +out: + up(&cmdq->credits); + + return ret; +}