From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-15.3 required=3.0 tests=BAYES_00, HEADER_FROM_DIFFERENT_DOMAINS,INCLUDES_CR_TRAILER,INCLUDES_PATCH, MAILING_LIST_MULTI,NICE_REPLY_A,SPF_HELO_NONE,SPF_PASS,USER_AGENT_SANE_1 autolearn=ham autolearn_force=no version=3.4.0 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id 29A78C433B4 for ; Sun, 2 May 2021 11:53:46 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id DE4DF61106 for ; Sun, 2 May 2021 11:53:45 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S230354AbhEBLtn (ORCPT ); Sun, 2 May 2021 07:49:43 -0400 Received: from mx2.suse.de ([195.135.220.15]:44296 "EHLO mx2.suse.de" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S230222AbhEBLtm (ORCPT ); Sun, 2 May 2021 07:49:42 -0400 X-Virus-Scanned: by amavisd-new at test-mx.suse.de Received: from relay2.suse.de (unknown [195.135.221.27]) by mx2.suse.de (Postfix) with ESMTP id 0CE55B199; Sun, 2 May 2021 11:48:50 +0000 (UTC) Subject: Re: [RFC PATCH v4 23/27] qedn: Add support of Task and SGL To: Shai Malin , netdev@vger.kernel.org, linux-nvme@lists.infradead.org, sagi@grimberg.me, hch@lst.de, axboe@fb.com, kbusch@kernel.org Cc: "David S . Miller davem @ davemloft . net --cc=Jakub Kicinski" , aelior@marvell.com, mkalderon@marvell.com, okulkarni@marvell.com, pkushwaha@marvell.com, malin1024@gmail.com References: <20210429190926.5086-1-smalin@marvell.com> <20210429190926.5086-24-smalin@marvell.com> From: Hannes Reinecke Message-ID: <3b9b048f-94e3-9bef-6d32-fc683636b649@suse.de> Date: Sun, 2 May 2021 13:48:49 +0200 User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:78.0) Gecko/20100101 Thunderbird/78.8.0 MIME-Version: 1.0 In-Reply-To: <20210429190926.5086-24-smalin@marvell.com> Content-Type: text/plain; charset=utf-8; format=flowed Content-Language: en-US Content-Transfer-Encoding: 8bit Precedence: bulk List-ID: X-Mailing-List: netdev@vger.kernel.org On 4/29/21 9:09 PM, Shai Malin wrote: > From: Prabhakar Kushwaha > > This patch will add support of Task and SGL which is used > for slowpath and fast path IO. here Task is IO granule used > by firmware to perform tasks > > The internal implementation: > - Create task/sgl resources used by all connection > - Provide APIs to allocate and free task. > - Add task support during connection establishment i.e. slowpath > > Acked-by: Igor Russkikh > Signed-off-by: Prabhakar Kushwaha > Signed-off-by: Omkar Kulkarni > Signed-off-by: Michal Kalderon > Signed-off-by: Ariel Elior > Signed-off-by: Shai Malin > --- > drivers/nvme/hw/qedn/qedn.h | 66 +++++ > drivers/nvme/hw/qedn/qedn_conn.c | 43 +++- > drivers/nvme/hw/qedn/qedn_main.c | 34 ++- > drivers/nvme/hw/qedn/qedn_task.c | 411 +++++++++++++++++++++++++++++++ > 4 files changed, 550 insertions(+), 4 deletions(-) > > diff --git a/drivers/nvme/hw/qedn/qedn.h b/drivers/nvme/hw/qedn/qedn.h > index bd9a250cb2f5..880ca245b02c 100644 > --- a/drivers/nvme/hw/qedn/qedn.h > +++ b/drivers/nvme/hw/qedn/qedn.h > @@ -50,6 +50,21 @@ > #define QEDN_FW_CQ_FP_WQ_WORKQUEUE "qedn_fw_cq_fp_wq" > #define QEDN_NVME_REQ_FP_WQ_WORKQUEUE "qedn_nvme_req_fp_wq" > > +/* Protocol defines */ > +#define QEDN_MAX_IO_SIZE QED_NVMETCP_MAX_IO_SIZE > + > +#define QEDN_SGE_BUFF_SIZE 4096 > +#define QEDN_MAX_SGES_PER_TASK DIV_ROUND_UP(QEDN_MAX_IO_SIZE, QEDN_SGE_BUFF_SIZE) > +#define QEDN_FW_SGE_SIZE sizeof(struct nvmetcp_sge) > +#define QEDN_MAX_FW_SGL_SIZE ((QEDN_MAX_SGES_PER_TASK) * QEDN_FW_SGE_SIZE) > +#define QEDN_FW_SLOW_IO_MIN_SGE_LIMIT (9700 / 6) > + > +#define QEDN_MAX_HW_SECTORS (QEDN_MAX_IO_SIZE / 512) > +#define QEDN_MAX_SEGMENTS QEDN_MAX_SGES_PER_TASK > + > +#define QEDN_TASK_INSIST_TMO 1000 /* 1 sec */ > +#define QEDN_INVALID_ITID 0xFFFF > + > /* > * TCP offload stack default configurations and defines. > * Future enhancements will allow controlling the configurable > @@ -95,6 +110,15 @@ enum qedn_state { > QEDN_STATE_MODULE_REMOVE_ONGOING, > }; > > +struct qedn_io_resources { > + /* Lock for IO resources */ > + spinlock_t resources_lock; > + struct list_head task_free_list; > + u32 num_alloc_tasks; > + u32 num_free_tasks; > + u32 no_avail_resrc_cnt; > +}; > + > /* Per CPU core params */ > struct qedn_fp_queue { > struct qed_chain cq_chain; > @@ -104,6 +128,10 @@ struct qedn_fp_queue { > struct qed_sb_info *sb_info; > unsigned int cpu; > struct work_struct fw_cq_fp_wq_entry; > + > + /* IO related resources for host */ > + struct qedn_io_resources host_resrc; > + > u16 sb_id; > char irqname[QEDN_IRQ_NAME_LEN]; > }; > @@ -130,6 +158,8 @@ struct qedn_ctx { > /* Connections */ > DECLARE_HASHTABLE(conn_ctx_hash, 16); > > + u32 num_tasks_per_pool; > + > /* Fast path queues */ > u8 num_fw_cqs; > struct qedn_fp_queue *fp_q_arr; > @@ -137,6 +167,27 @@ struct qedn_ctx { > dma_addr_t fw_cq_array_phy; /* Physical address of fw_cq_array_virt */ > struct workqueue_struct *nvme_req_fp_wq; > struct workqueue_struct *fw_cq_fp_wq; > + > + /* Fast Path Tasks */ > + struct qed_nvmetcp_tid tasks; > +}; > + > +struct qedn_task_ctx { > + struct qedn_conn_ctx *qedn_conn; > + struct qedn_ctx *qedn; > + void *fw_task_ctx; > + struct qedn_fp_queue *fp_q; > + struct scatterlist *nvme_sg; > + struct nvme_tcp_ofld_req *req; /* currently proccessed request */ > + struct list_head entry; > + spinlock_t lock; /* To protect task resources */ > + bool valid; > + unsigned long flags; /* Used by qedn_task_flags */ > + u32 task_size; > + u16 itid; > + u16 cccid; > + int req_direction; > + struct storage_sgl_task_params sgl_task_params; > }; > > struct qedn_endpoint { > @@ -243,6 +294,7 @@ struct qedn_conn_ctx { > struct nvme_tcp_ofld_ctrl *ctrl; > u32 conn_handle; > u32 fw_cid; > + u8 default_cq; > > atomic_t est_conn_indicator; > atomic_t destroy_conn_indicator; > @@ -260,6 +312,11 @@ struct qedn_conn_ctx { > dma_addr_t host_cccid_itid_phy_addr; > struct qedn_endpoint ep; > int abrt_flag; > + /* Spinlock for accessing active_task_list */ > + spinlock_t task_list_lock; > + struct list_head active_task_list; > + atomic_t num_active_tasks; > + atomic_t num_active_fw_tasks; > > /* Connection resources - turned on to indicate what resource was > * allocated, to that it can later be released. > @@ -279,6 +336,7 @@ struct qedn_conn_ctx { > enum qedn_conn_resources_state { > QEDN_CONN_RESRC_FW_SQ, > QEDN_CONN_RESRC_ACQUIRE_CONN, > + QEDN_CONN_RESRC_TASKS, > QEDN_CONN_RESRC_CCCID_ITID_MAP, > QEDN_CONN_RESRC_TCP_PORT, > QEDN_CONN_RESRC_MAX = 64 > @@ -309,5 +367,13 @@ inline int qedn_validate_cccid_in_range(struct qedn_conn_ctx *conn_ctx, u16 ccci > void qedn_queue_request(struct qedn_conn_ctx *qedn_conn, struct nvme_tcp_ofld_req *req); > void qedn_nvme_req_fp_wq_handler(struct work_struct *work); > void qedn_io_work_cq(struct qedn_ctx *qedn, struct nvmetcp_fw_cqe *cqe); > +int qedn_alloc_tasks(struct qedn_conn_ctx *conn_ctx); > +inline int qedn_qid(struct nvme_tcp_ofld_queue *queue); > +struct qedn_task_ctx * > + qedn_get_task_from_pool_insist(struct qedn_conn_ctx *conn_ctx, u16 cccid); > +void qedn_common_clear_fw_sgl(struct storage_sgl_task_params *sgl_task_params); > +void qedn_return_active_tasks(struct qedn_conn_ctx *conn_ctx); > +void qedn_destroy_free_tasks(struct qedn_fp_queue *fp_q, > + struct qedn_io_resources *io_resrc); > > #endif /* _QEDN_H_ */ > diff --git a/drivers/nvme/hw/qedn/qedn_conn.c b/drivers/nvme/hw/qedn/qedn_conn.c > index 90d8aa36d219..10a80fbeac43 100644 > --- a/drivers/nvme/hw/qedn/qedn_conn.c > +++ b/drivers/nvme/hw/qedn/qedn_conn.c > @@ -29,6 +29,11 @@ static const char * const qedn_conn_state_str[] = { > NULL > }; > > +inline int qedn_qid(struct nvme_tcp_ofld_queue *queue) > +{ > + return queue - queue->ctrl->queues; > +} > + > int qedn_set_con_state(struct qedn_conn_ctx *conn_ctx, enum qedn_conn_state new_state) > { > spin_lock_bh(&conn_ctx->conn_state_lock); > @@ -146,6 +151,11 @@ static void qedn_release_conn_ctx(struct qedn_conn_ctx *conn_ctx) > clear_bit(QEDN_CONN_RESRC_ACQUIRE_CONN, &conn_ctx->resrc_state); > } > > + if (test_bit(QEDN_CONN_RESRC_TASKS, &conn_ctx->resrc_state)) { > + clear_bit(QEDN_CONN_RESRC_TASKS, &conn_ctx->resrc_state); > + qedn_return_active_tasks(conn_ctx); > + } > + > if (test_bit(QEDN_CONN_RESRC_CCCID_ITID_MAP, &conn_ctx->resrc_state)) { > dma_free_coherent(&qedn->pdev->dev, > conn_ctx->sq_depth * > @@ -247,6 +257,7 @@ static int qedn_nvmetcp_offload_conn(struct qedn_conn_ctx *conn_ctx) > offld_prms.max_rt_time = QEDN_TCP_MAX_RT_TIME; > offld_prms.sq_pbl_addr = > (u64)qed_chain_get_pbl_phys(&qedn_ep->fw_sq_chain); > + offld_prms.default_cq = conn_ctx->default_cq; > > rc = qed_ops->offload_conn(qedn->cdev, > conn_ctx->conn_handle, > @@ -375,6 +386,9 @@ int qedn_event_cb(void *context, u8 fw_event_code, void *event_ring_data) > static int qedn_prep_and_offload_queue(struct qedn_conn_ctx *conn_ctx) > { > struct qedn_ctx *qedn = conn_ctx->qedn; > + struct qedn_io_resources *io_resrc; > + struct qedn_fp_queue *fp_q; > + u8 default_cq_idx, qid; > size_t dma_size; > int rc; > > @@ -387,6 +401,8 @@ static int qedn_prep_and_offload_queue(struct qedn_conn_ctx *conn_ctx) > set_bit(QEDN_CONN_RESRC_FW_SQ, &conn_ctx->resrc_state); > INIT_LIST_HEAD(&conn_ctx->host_pend_req_list); > spin_lock_init(&conn_ctx->nvme_req_lock); > + atomic_set(&conn_ctx->num_active_tasks, 0); > + atomic_set(&conn_ctx->num_active_fw_tasks, 0); > > rc = qed_ops->acquire_conn(qedn->cdev, > &conn_ctx->conn_handle, > @@ -401,7 +417,32 @@ static int qedn_prep_and_offload_queue(struct qedn_conn_ctx *conn_ctx) > conn_ctx->conn_handle); > set_bit(QEDN_CONN_RESRC_ACQUIRE_CONN, &conn_ctx->resrc_state); > > - /* Placeholder - Allocate task resources and initialize fields */ > + qid = qedn_qid(conn_ctx->queue); > + default_cq_idx = qid ? qid - 1 : 0; /* Offset adminq */ > + > + conn_ctx->default_cq = (default_cq_idx % qedn->num_fw_cqs); > + fp_q = &qedn->fp_q_arr[conn_ctx->default_cq]; > + conn_ctx->fp_q = fp_q; > + io_resrc = &fp_q->host_resrc; > + > + /* The first connection on each fp_q will fill task > + * resources > + */ > + spin_lock(&io_resrc->resources_lock); > + if (io_resrc->num_alloc_tasks == 0) { > + rc = qedn_alloc_tasks(conn_ctx); > + if (rc) { > + pr_err("Failed allocating tasks: CID=0x%x\n", > + conn_ctx->fw_cid); > + spin_unlock(&io_resrc->resources_lock); > + goto rel_conn; > + } > + } > + spin_unlock(&io_resrc->resources_lock); > + > + spin_lock_init(&conn_ctx->task_list_lock); > + INIT_LIST_HEAD(&conn_ctx->active_task_list); > + set_bit(QEDN_CONN_RESRC_TASKS, &conn_ctx->resrc_state); > > rc = qedn_fetch_tcp_port(conn_ctx); > if (rc) > diff --git a/drivers/nvme/hw/qedn/qedn_main.c b/drivers/nvme/hw/qedn/qedn_main.c > index 38f23dbb03a5..8d9c19d63480 100644 > --- a/drivers/nvme/hw/qedn/qedn_main.c > +++ b/drivers/nvme/hw/qedn/qedn_main.c > @@ -30,6 +30,12 @@ __be16 qedn_get_in_port(struct sockaddr_storage *sa) > : ((struct sockaddr_in6 *)sa)->sin6_port; > } > > +static void qedn_init_io_resc(struct qedn_io_resources *io_resrc) > +{ > + spin_lock_init(&io_resrc->resources_lock); > + INIT_LIST_HEAD(&io_resrc->task_free_list); > +} > + > struct qedn_llh_filter *qedn_add_llh_filter(struct qedn_ctx *qedn, u16 tcp_port) > { > struct qedn_llh_filter *llh_filter = NULL; > @@ -436,6 +442,8 @@ static struct nvme_tcp_ofld_ops qedn_ofld_ops = { > * NVMF_OPT_HDR_DIGEST | NVMF_OPT_DATA_DIGEST | > * NVMF_OPT_NR_POLL_QUEUES | NVMF_OPT_TOS > */ > + .max_hw_sectors = QEDN_MAX_HW_SECTORS, > + .max_segments = QEDN_MAX_SEGMENTS, > .claim_dev = qedn_claim_dev, > .setup_ctrl = qedn_setup_ctrl, > .release_ctrl = qedn_release_ctrl, > @@ -657,8 +665,24 @@ static void qedn_remove_pf_from_gl_list(struct qedn_ctx *qedn) > mutex_unlock(&qedn_glb.glb_mutex); > } > > +static void qedn_call_destroy_free_tasks(struct qedn_fp_queue *fp_q, > + struct qedn_io_resources *io_resrc) > +{ > + if (list_empty(&io_resrc->task_free_list)) > + return; > + > + if (io_resrc->num_alloc_tasks != io_resrc->num_free_tasks) > + pr_err("Task Pool:Not all returned allocated=0x%x, free=0x%x\n", > + io_resrc->num_alloc_tasks, io_resrc->num_free_tasks); > + > + qedn_destroy_free_tasks(fp_q, io_resrc); > + if (io_resrc->num_free_tasks) > + pr_err("Expected num_free_tasks to be 0\n"); > +} > + > static void qedn_free_function_queues(struct qedn_ctx *qedn) > { > + struct qedn_io_resources *host_resrc; > struct qed_sb_info *sb_info = NULL; > struct qedn_fp_queue *fp_q; > int i; > @@ -673,6 +697,9 @@ static void qedn_free_function_queues(struct qedn_ctx *qedn) > /* Free the fast path queues*/ > for (i = 0; i < qedn->num_fw_cqs; i++) { > fp_q = &qedn->fp_q_arr[i]; > + host_resrc = &fp_q->host_resrc; > + > + qedn_call_destroy_free_tasks(fp_q, host_resrc); > > /* Free SB */ > sb_info = fp_q->sb_info; > @@ -769,7 +796,8 @@ static int qedn_alloc_function_queues(struct qedn_ctx *qedn) > goto mem_alloc_failure; > } > > - /* placeholder - create task pools */ > + qedn->num_tasks_per_pool = > + qedn->pf_params.nvmetcp_pf_params.num_tasks / qedn->num_fw_cqs; > > for (i = 0; i < qedn->num_fw_cqs; i++) { > fp_q = &qedn->fp_q_arr[i]; > @@ -811,7 +839,7 @@ static int qedn_alloc_function_queues(struct qedn_ctx *qedn) > fp_q->qedn = qedn; > INIT_WORK(&fp_q->fw_cq_fp_wq_entry, qedn_fw_cq_fq_wq_handler); > > - /* Placeholder - Init IO-path resources */ > + qedn_init_io_resc(&fp_q->host_resrc); > } > > return 0; > @@ -1005,7 +1033,7 @@ static int __qedn_probe(struct pci_dev *pdev) > > /* NVMeTCP start HW PF */ > rc = qed_ops->start(qedn->cdev, > - NULL /* Placeholder for FW IO-path resources */, > + &qedn->tasks, > qedn, > qedn_event_cb); > if (rc) { > diff --git a/drivers/nvme/hw/qedn/qedn_task.c b/drivers/nvme/hw/qedn/qedn_task.c > index d3474188efdc..54f2f4cba6ea 100644 > --- a/drivers/nvme/hw/qedn/qedn_task.c > +++ b/drivers/nvme/hw/qedn/qedn_task.c > @@ -11,6 +11,263 @@ > /* Driver includes */ > #include "qedn.h" > > +static bool qedn_sgl_has_small_mid_sge(struct nvmetcp_sge *sgl, u16 sge_count) > +{ > + u16 sge_num; > + > + if (sge_count > 8) { > + for (sge_num = 0; sge_num < sge_count; sge_num++) { > + if (le32_to_cpu(sgl[sge_num].sge_len) < > + QEDN_FW_SLOW_IO_MIN_SGE_LIMIT) > + return true; /* small middle SGE found */ > + } > + } > + > + return false; /* no small middle SGEs */ > +} > + > +static int qedn_init_sgl(struct qedn_ctx *qedn, struct qedn_task_ctx *qedn_task) > +{ > + struct storage_sgl_task_params *sgl_task_params; > + enum dma_data_direction dma_dir; > + struct scatterlist *sg; > + struct request *rq; > + u16 num_sges; > + int index; > + int rc; > + > + sgl_task_params = &qedn_task->sgl_task_params; > + rq = blk_mq_rq_from_pdu(qedn_task->req); > + if (qedn_task->task_size == 0) { > + sgl_task_params->num_sges = 0; > + > + return 0; > + } > + > + /* Convert BIO to scatterlist */ > + num_sges = blk_rq_map_sg(rq->q, rq, qedn_task->nvme_sg); > + if (qedn_task->req_direction == WRITE) > + dma_dir = DMA_TO_DEVICE; > + else > + dma_dir = DMA_FROM_DEVICE; > + > + /* DMA map the scatterlist */ > + if (dma_map_sg(&qedn->pdev->dev, qedn_task->nvme_sg, num_sges, dma_dir) != num_sges) { > + pr_err("Couldn't map sgl\n"); > + rc = -EPERM; > + > + return rc; > + } > + > + sgl_task_params->total_buffer_size = qedn_task->task_size; > + sgl_task_params->num_sges = num_sges; > + > + for_each_sg(qedn_task->nvme_sg, sg, num_sges, index) { > + DMA_REGPAIR_LE(sgl_task_params->sgl[index].sge_addr, sg_dma_address(sg)); > + sgl_task_params->sgl[index].sge_len = cpu_to_le32(sg_dma_len(sg)); > + } > + > + /* Relevant for Host Write Only */ > + sgl_task_params->small_mid_sge = (qedn_task->req_direction == READ) ? > + false : > + qedn_sgl_has_small_mid_sge(sgl_task_params->sgl, > + sgl_task_params->num_sges); > + > + return 0; > +} > + > +static void qedn_free_nvme_sg(struct qedn_task_ctx *qedn_task) > +{ > + kfree(qedn_task->nvme_sg); > + qedn_task->nvme_sg = NULL; > +} > + > +static void qedn_free_fw_sgl(struct qedn_task_ctx *qedn_task) > +{ > + struct qedn_ctx *qedn = qedn_task->qedn; > + dma_addr_t sgl_pa; > + > + sgl_pa = HILO_DMA_REGPAIR(qedn_task->sgl_task_params.sgl_phys_addr); > + dma_free_coherent(&qedn->pdev->dev, > + QEDN_MAX_FW_SGL_SIZE, > + qedn_task->sgl_task_params.sgl, > + sgl_pa); > + qedn_task->sgl_task_params.sgl = NULL; > +} > + > +static void qedn_destroy_single_task(struct qedn_task_ctx *qedn_task) > +{ > + u16 itid; > + > + itid = qedn_task->itid; > + list_del(&qedn_task->entry); > + qedn_free_nvme_sg(qedn_task); > + qedn_free_fw_sgl(qedn_task); > + kfree(qedn_task); > + qedn_task = NULL; > +} > + > +void qedn_destroy_free_tasks(struct qedn_fp_queue *fp_q, > + struct qedn_io_resources *io_resrc) > +{ > + struct qedn_task_ctx *qedn_task, *task_tmp; > + > + /* Destroy tasks from the free task list */ > + list_for_each_entry_safe(qedn_task, task_tmp, > + &io_resrc->task_free_list, entry) { > + qedn_destroy_single_task(qedn_task); > + io_resrc->num_free_tasks -= 1; > + } > +} > + > +static int qedn_alloc_nvme_sg(struct qedn_task_ctx *qedn_task) > +{ > + int rc; > + > + qedn_task->nvme_sg = kcalloc(QEDN_MAX_SGES_PER_TASK, > + sizeof(*qedn_task->nvme_sg), GFP_KERNEL); > + if (!qedn_task->nvme_sg) { > + rc = -ENOMEM; > + > + return rc; > + } > + > + return 0; > +} > + > +static int qedn_alloc_fw_sgl(struct qedn_task_ctx *qedn_task) > +{ > + struct qedn_ctx *qedn = qedn_task->qedn_conn->qedn; > + dma_addr_t fw_sgl_phys; > + > + qedn_task->sgl_task_params.sgl = > + dma_alloc_coherent(&qedn->pdev->dev, QEDN_MAX_FW_SGL_SIZE, > + &fw_sgl_phys, GFP_KERNEL); > + if (!qedn_task->sgl_task_params.sgl) { > + pr_err("Couldn't allocate FW sgl\n"); > + > + return -ENOMEM; > + } > + > + DMA_REGPAIR_LE(qedn_task->sgl_task_params.sgl_phys_addr, fw_sgl_phys); > + > + return 0; > +} > + > +static inline void *qedn_get_fw_task(struct qed_nvmetcp_tid *info, u16 itid) > +{ > + return (void *)(info->blocks[itid / info->num_tids_per_block] + > + (itid % info->num_tids_per_block) * info->size); > +} > + > +static struct qedn_task_ctx *qedn_alloc_task(struct qedn_conn_ctx *conn_ctx, u16 itid) > +{ > + struct qedn_ctx *qedn = conn_ctx->qedn; > + struct qedn_task_ctx *qedn_task; > + void *fw_task_ctx; > + int rc = 0; > + > + qedn_task = kzalloc(sizeof(*qedn_task), GFP_KERNEL); > + if (!qedn_task) > + return NULL; > + As this is a pool, why don't you use mempools here? > + spin_lock_init(&qedn_task->lock); > + fw_task_ctx = qedn_get_fw_task(&qedn->tasks, itid); > + if (!fw_task_ctx) { > + pr_err("iTID: 0x%x; Failed getting fw_task_ctx memory\n", itid); > + goto release_task; > + } > + > + /* No need to memset fw_task_ctx - its done in the HSI func */ > + qedn_task->qedn_conn = conn_ctx; > + qedn_task->qedn = qedn; > + qedn_task->fw_task_ctx = fw_task_ctx; > + qedn_task->valid = 0; > + qedn_task->flags = 0; > + qedn_task->itid = itid; > + rc = qedn_alloc_fw_sgl(qedn_task); > + if (rc) { > + pr_err("iTID: 0x%x; Failed allocating FW sgl\n", itid); > + goto release_task; > + } > + > + rc = qedn_alloc_nvme_sg(qedn_task); > + if (rc) { > + pr_err("iTID: 0x%x; Failed allocating FW sgl\n", itid); > + goto release_fw_sgl; > + } > + > + return qedn_task; > + > +release_fw_sgl: > + qedn_free_fw_sgl(qedn_task); > +release_task: > + kfree(qedn_task); > + > + return NULL; > +} > + > +int qedn_alloc_tasks(struct qedn_conn_ctx *conn_ctx) > +{ > + struct qedn_ctx *qedn = conn_ctx->qedn; > + struct qedn_task_ctx *qedn_task = NULL; > + struct qedn_io_resources *io_resrc; > + u16 itid, start_itid, offset; > + struct qedn_fp_queue *fp_q; > + int i, rc; > + > + fp_q = conn_ctx->fp_q; > + > + offset = fp_q->sb_id; > + io_resrc = &fp_q->host_resrc; > + > + start_itid = qedn->num_tasks_per_pool * offset; > + for (i = 0; i < qedn->num_tasks_per_pool; ++i) { > + itid = start_itid + i; > + qedn_task = qedn_alloc_task(conn_ctx, itid); > + if (!qedn_task) { > + pr_err("Failed allocating task\n"); > + rc = -ENOMEM; > + goto release_tasks; > + } > + > + qedn_task->fp_q = fp_q; > + io_resrc->num_free_tasks += 1; > + list_add_tail(&qedn_task->entry, &io_resrc->task_free_list); > + } > + > + io_resrc->num_alloc_tasks = io_resrc->num_free_tasks; > + > + return 0; > + > +release_tasks: > + qedn_destroy_free_tasks(fp_q, io_resrc); > + > + return rc; > +} > + > +void qedn_common_clear_fw_sgl(struct storage_sgl_task_params *sgl_task_params) > +{ > + u16 sge_cnt = sgl_task_params->num_sges; > + > + memset(&sgl_task_params->sgl[(sge_cnt - 1)], 0, > + sizeof(struct nvmetcp_sge)); > + sgl_task_params->total_buffer_size = 0; > + sgl_task_params->small_mid_sge = false; > + sgl_task_params->num_sges = 0; > +} > + > +inline void qedn_host_reset_cccid_itid_entry(struct qedn_conn_ctx *conn_ctx, > + u16 cccid) > +{ > + conn_ctx->host_cccid_itid[cccid].itid = cpu_to_le16(QEDN_INVALID_ITID); > +} > + > +inline void qedn_host_set_cccid_itid_entry(struct qedn_conn_ctx *conn_ctx, u16 cccid, u16 itid) > +{ > + conn_ctx->host_cccid_itid[cccid].itid = cpu_to_le16(itid); > +} > + > inline int qedn_validate_cccid_in_range(struct qedn_conn_ctx *conn_ctx, u16 cccid) > { > int rc = 0; > @@ -23,6 +280,160 @@ inline int qedn_validate_cccid_in_range(struct qedn_conn_ctx *conn_ctx, u16 ccci > return rc; > } > > +static void qedn_clear_sgl(struct qedn_ctx *qedn, > + struct qedn_task_ctx *qedn_task) > +{ > + struct storage_sgl_task_params *sgl_task_params; > + enum dma_data_direction dma_dir; > + u32 sge_cnt; > + > + sgl_task_params = &qedn_task->sgl_task_params; > + sge_cnt = sgl_task_params->num_sges; > + > + /* Nothing to do if no SGEs were used */ > + if (!qedn_task->task_size || !sge_cnt) > + return; > + > + dma_dir = (qedn_task->req_direction == WRITE ? DMA_TO_DEVICE : DMA_FROM_DEVICE); > + dma_unmap_sg(&qedn->pdev->dev, qedn_task->nvme_sg, sge_cnt, dma_dir); > + memset(&qedn_task->nvme_sg[(sge_cnt - 1)], 0, sizeof(struct scatterlist)); > + qedn_common_clear_fw_sgl(sgl_task_params); > + qedn_task->task_size = 0; > +} > + > +static void qedn_clear_task(struct qedn_conn_ctx *conn_ctx, > + struct qedn_task_ctx *qedn_task) > +{ > + /* Task lock isn't needed since it is no longer in use */ > + qedn_clear_sgl(conn_ctx->qedn, qedn_task); > + qedn_task->valid = 0; > + qedn_task->flags = 0; > + > + atomic_dec(&conn_ctx->num_active_tasks); > +} > + > +void qedn_return_active_tasks(struct qedn_conn_ctx *conn_ctx) > +{ > + struct qedn_fp_queue *fp_q = conn_ctx->fp_q; > + struct qedn_task_ctx *qedn_task, *task_tmp; > + struct qedn_io_resources *io_resrc; > + int num_returned_tasks = 0; > + int num_active_tasks; > + > + io_resrc = &fp_q->host_resrc; > + > + /* Return tasks that aren't "Used by FW" to the pool */ > + list_for_each_entry_safe(qedn_task, task_tmp, > + &conn_ctx->active_task_list, entry) { > + qedn_clear_task(conn_ctx, qedn_task); > + num_returned_tasks++; > + } > + > + if (num_returned_tasks) { > + spin_lock(&io_resrc->resources_lock); > + /* Return tasks to FP_Q pool in one shot */ > + > + list_splice_tail_init(&conn_ctx->active_task_list, > + &io_resrc->task_free_list); > + io_resrc->num_free_tasks += num_returned_tasks; > + spin_unlock(&io_resrc->resources_lock); > + } > + > + num_active_tasks = atomic_read(&conn_ctx->num_active_tasks); > + if (num_active_tasks) > + pr_err("num_active_tasks is %u after cleanup.\n", num_active_tasks); > +} > + > +void qedn_return_task_to_pool(struct qedn_conn_ctx *conn_ctx, > + struct qedn_task_ctx *qedn_task) > +{ > + struct qedn_fp_queue *fp_q = conn_ctx->fp_q; > + struct qedn_io_resources *io_resrc; > + unsigned long lock_flags; > + > + io_resrc = &fp_q->host_resrc; > + > + spin_lock_irqsave(&qedn_task->lock, lock_flags); > + qedn_task->valid = 0; > + qedn_task->flags = 0; > + qedn_clear_sgl(conn_ctx->qedn, qedn_task); > + spin_unlock_irqrestore(&qedn_task->lock, lock_flags); > + > + spin_lock(&conn_ctx->task_list_lock); > + list_del(&qedn_task->entry); > + qedn_host_reset_cccid_itid_entry(conn_ctx, qedn_task->cccid); > + spin_unlock(&conn_ctx->task_list_lock); > + > + atomic_dec(&conn_ctx->num_active_tasks); > + atomic_dec(&conn_ctx->num_active_fw_tasks); > + > + spin_lock(&io_resrc->resources_lock); > + list_add_tail(&qedn_task->entry, &io_resrc->task_free_list); > + io_resrc->num_free_tasks += 1; > + spin_unlock(&io_resrc->resources_lock); > +} > + > +struct qedn_task_ctx * > +qedn_get_free_task_from_pool(struct qedn_conn_ctx *conn_ctx, u16 cccid) > +{ > + struct qedn_task_ctx *qedn_task = NULL; > + struct qedn_io_resources *io_resrc; > + struct qedn_fp_queue *fp_q; > + > + fp_q = conn_ctx->fp_q; > + io_resrc = &fp_q->host_resrc; > + > + spin_lock(&io_resrc->resources_lock); > + qedn_task = list_first_entry_or_null(&io_resrc->task_free_list, > + struct qedn_task_ctx, entry); > + if (unlikely(!qedn_task)) { > + spin_unlock(&io_resrc->resources_lock); > + > + return NULL; > + } > + list_del(&qedn_task->entry); > + io_resrc->num_free_tasks -= 1; > + spin_unlock(&io_resrc->resources_lock); > + > + spin_lock(&conn_ctx->task_list_lock); > + list_add_tail(&qedn_task->entry, &conn_ctx->active_task_list); > + qedn_host_set_cccid_itid_entry(conn_ctx, cccid, qedn_task->itid); > + spin_unlock(&conn_ctx->task_list_lock); > + > + atomic_inc(&conn_ctx->num_active_tasks); > + qedn_task->cccid = cccid; > + qedn_task->qedn_conn = conn_ctx; > + qedn_task->valid = 1; > + > + return qedn_task; > +} > + > +struct qedn_task_ctx * > +qedn_get_task_from_pool_insist(struct qedn_conn_ctx *conn_ctx, u16 cccid) > +{ > + struct qedn_task_ctx *qedn_task = NULL; > + unsigned long timeout; > + > + qedn_task = qedn_get_free_task_from_pool(conn_ctx, cccid); > + if (unlikely(!qedn_task)) { > + timeout = msecs_to_jiffies(QEDN_TASK_INSIST_TMO) + jiffies; > + while (1) { > + qedn_task = qedn_get_free_task_from_pool(conn_ctx, cccid); > + if (likely(qedn_task)) > + break; > + > + msleep(100); > + if (time_after(jiffies, timeout)) { > + pr_err("Failed on timeout of fetching task\n"); > + > + return NULL; > + } > + } > + } > + > + return qedn_task; > +} > + > static bool qedn_process_req(struct qedn_conn_ctx *qedn_conn) > { > return true; > Cheers, Hannes -- Dr. Hannes Reinecke Kernel Storage Architect hare@suse.de +49 911 74053 688 SUSE Software Solutions GmbH, Maxfeldstr. 5, 90409 Nürnberg HRB 36809 (AG Nürnberg), Geschäftsführer: Felix Imendörffer