From: Zhu Yanjun <yanjun.zhu@xxxxxxxxx> This is a followup to the EFA dmabuf[1]. Irdma driver currently does not support on-demand-paging(ODP). So it uses habanalabs as the dmabuf exporter, and irdma as the importer to allow for peer2peer access through libibverbs. In this commit, the function ib_umem_dmabuf_get_pinned() is used. This function is introduced in EFA dmabuf[1] which allows the driver to get a dmabuf umem which is pinned and does not require move_notify callback implementation. The returned umem is pinned and DMA mapped like standard cpu umems, and is released through ib_umem_release(). [1]https://lore.kernel.org/lkml/20211007114018.GD2688930@xxxxxxxx/t/ Signed-off-by: Zhu Yanjun <yanjun.zhu@xxxxxxxxx> --- drivers/infiniband/hw/irdma/verbs.c | 158 ++++++++++++++++++++++++++++ 1 file changed, 158 insertions(+) diff --git a/drivers/infiniband/hw/irdma/verbs.c b/drivers/infiniband/hw/irdma/verbs.c index f6973ea55eda..76dc6e65930a 100644 --- a/drivers/infiniband/hw/irdma/verbs.c +++ b/drivers/infiniband/hw/irdma/verbs.c @@ -2912,6 +2912,163 @@ static struct ib_mr *irdma_reg_user_mr(struct ib_pd *pd, u64 start, u64 len, return ERR_PTR(err); } +struct ib_mr *irdma_reg_user_mr_dmabuf(struct ib_pd *pd, u64 start, + u64 len, u64 virt, + int fd, int access, + struct ib_udata *udata) +{ + struct irdma_device *iwdev = to_iwdev(pd->device); + struct irdma_ucontext *ucontext; + struct irdma_pble_alloc *palloc; + struct irdma_pbl *iwpbl; + struct irdma_mr *iwmr; + struct irdma_mem_reg_req req; + u32 total, stag = 0; + u8 shadow_pgcnt = 1; + bool use_pbles = false; + unsigned long flags; + int err = -EINVAL; + struct ib_umem_dmabuf *umem_dmabuf; + + if (len > iwdev->rf->sc_dev.hw_attrs.max_mr_size) + return ERR_PTR(-EINVAL); + + if (udata->inlen < IRDMA_MEM_REG_MIN_REQ_LEN) + return ERR_PTR(-EINVAL); + + umem_dmabuf = ib_umem_dmabuf_get_pinned(pd->device, start, len, fd, + access); + if (IS_ERR(umem_dmabuf)) { + err = PTR_ERR(umem_dmabuf); + ibdev_dbg(&iwdev->ibdev, "Failed to get dmabuf umem[%d]\n", err); + return ERR_PTR(err); + } + + if (ib_copy_from_udata(&req, udata, min(sizeof(req), udata->inlen))) { + ib_umem_release(&umem_dmabuf->umem); + return ERR_PTR(-EFAULT); + } + + iwmr = kzalloc(sizeof(*iwmr), GFP_KERNEL); + if (!iwmr) { + ib_umem_release(&umem_dmabuf->umem); + return ERR_PTR(-ENOMEM); + } + + iwpbl = &iwmr->iwpbl; + iwpbl->iwmr = iwmr; + iwmr->region = &umem_dmabuf->umem; + iwmr->ibmr.pd = pd; + iwmr->ibmr.device = pd->device; + iwmr->ibmr.iova = virt; + iwmr->page_size = PAGE_SIZE; + + if (req.reg_type == IRDMA_MEMREG_TYPE_MEM) { + iwmr->page_size = ib_umem_find_best_pgsz(iwmr->region, + iwdev->rf->sc_dev.hw_attrs.page_size_cap, + virt); + if (unlikely(!iwmr->page_size)) { + kfree(iwmr); + ib_umem_release(iwmr->region); + return ERR_PTR(-EOPNOTSUPP); + } + } + iwmr->len = iwmr->region->length; + iwpbl->user_base = virt; + palloc = &iwpbl->pble_alloc; + iwmr->type = req.reg_type; + iwmr->page_cnt = ib_umem_num_dma_blocks(iwmr->region, iwmr->page_size); + + switch (req.reg_type) { + case IRDMA_MEMREG_TYPE_QP: + total = req.sq_pages + req.rq_pages + shadow_pgcnt; + if (total > iwmr->page_cnt) { + err = -EINVAL; + goto error; + } + total = req.sq_pages + req.rq_pages; + use_pbles = (total > 2); + err = irdma_handle_q_mem(iwdev, &req, iwpbl, use_pbles); + if (err) + goto error; + + ucontext = rdma_udata_to_drv_context(udata, struct irdma_ucontext, + ibucontext); + spin_lock_irqsave(&ucontext->qp_reg_mem_list_lock, flags); + list_add_tail(&iwpbl->list, &ucontext->qp_reg_mem_list); + iwpbl->on_list = true; + spin_unlock_irqrestore(&ucontext->qp_reg_mem_list_lock, flags); + break; + case IRDMA_MEMREG_TYPE_CQ: + if (iwdev->rf->sc_dev.hw_attrs.uk_attrs.feature_flags & IRDMA_FEATURE_CQ_RESIZE) + shadow_pgcnt = 0; + total = req.cq_pages + shadow_pgcnt; + if (total > iwmr->page_cnt) { + err = -EINVAL; + goto error; + } + + use_pbles = (req.cq_pages > 1); + err = irdma_handle_q_mem(iwdev, &req, iwpbl, use_pbles); + if (err) + goto error; + + ucontext = rdma_udata_to_drv_context(udata, struct irdma_ucontext, + ibucontext); + spin_lock_irqsave(&ucontext->cq_reg_mem_list_lock, flags); + list_add_tail(&iwpbl->list, &ucontext->cq_reg_mem_list); + iwpbl->on_list = true; + spin_unlock_irqrestore(&ucontext->cq_reg_mem_list_lock, flags); + break; + case IRDMA_MEMREG_TYPE_MEM: + use_pbles = (iwmr->page_cnt != 1); + + err = irdma_setup_pbles(iwdev->rf, iwmr, use_pbles, false); + if (err) + goto error; + + if (use_pbles) { + err = irdma_check_mr_contiguous(palloc, + iwmr->page_size); + if (err) { + irdma_free_pble(iwdev->rf->pble_rsrc, palloc); + iwpbl->pbl_allocated = false; + } + } + + stag = irdma_create_stag(iwdev); + if (!stag) { + err = -ENOMEM; + goto error; + } + + iwmr->stag = stag; + iwmr->ibmr.rkey = stag; + iwmr->ibmr.lkey = stag; + err = irdma_hwreg_mr(iwdev, iwmr, access); + if (err) { + irdma_free_stag(iwdev, stag); + goto error; + } + + break; + default: + goto error; + } + + iwmr->type = req.reg_type; + + return &iwmr->ibmr; + +error: + if (palloc->level != PBLE_LEVEL_0 && iwpbl->pbl_allocated) + irdma_free_pble(iwdev->rf->pble_rsrc, palloc); + ib_umem_release(iwmr->region); + kfree(iwmr); + + return ERR_PTR(err); +} + /** * irdma_reg_phys_mr - register kernel physical memory * @pd: ibpd pointer @@ -4418,6 +4575,7 @@ static const struct ib_device_ops irdma_dev_ops = { .query_port = irdma_query_port, .query_qp = irdma_query_qp, .reg_user_mr = irdma_reg_user_mr, + .reg_user_mr_dmabuf = irdma_reg_user_mr_dmabuf, .req_notify_cq = irdma_req_notify_cq, .resize_cq = irdma_resize_cq, INIT_RDMA_OBJ_SIZE(ib_pd, irdma_pd, ibpd), -- 2.34.1
