* [PATCHv4 for-next 1/1] RDMA/irdma: Add support for dmabuf pin memory regions
@ 2023-02-17 1:14 Zhu Yanjun
2023-02-17 20:37 ` Jason Gunthorpe
0 siblings, 1 reply; 2+ messages in thread
From: Zhu Yanjun @ 2023-02-17 1:14 UTC (permalink / raw)
To: mustafa.ismail, shiraz.saleem, jgg, leon, linux-rdma; +Cc: Zhu Yanjun
From: Zhu Yanjun <yanjun.zhu@linux.dev>
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@ziepe.ca/t/
Reviewed-by: Shiraz Saleem <shiraz.saleem@intel.com>
Signed-off-by: Zhu Yanjun <yanjun.zhu@linux.dev>
---
V3->V4: Remove inlen test
V2->V3: Remove unnecessary variable initialization;
Use error handler;
V1->V2: Thanks Shiraz Saleem, he gave me a lot of good suggestions.
This commit is based on the shared functions from refactored
irdma_reg_user_mr.
---
drivers/infiniband/hw/irdma/verbs.c | 42 +++++++++++++++++++++++++++++
1 file changed, 42 insertions(+)
diff --git a/drivers/infiniband/hw/irdma/verbs.c b/drivers/infiniband/hw/irdma/verbs.c
index 6982f38596c8..1b2e3e800c9a 100644
--- a/drivers/infiniband/hw/irdma/verbs.c
+++ b/drivers/infiniband/hw/irdma/verbs.c
@@ -2977,6 +2977,47 @@ static struct ib_mr *irdma_reg_user_mr(struct ib_pd *pd, u64 start, u64 len,
return ERR_PTR(err);
}
+static 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 ib_umem_dmabuf *umem_dmabuf;
+ struct irdma_mr *iwmr;
+ int err;
+
+ if (len > iwdev->rf->sc_dev.hw_attrs.max_mr_size)
+ 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);
+ }
+
+ iwmr = irdma_alloc_iwmr(&umem_dmabuf->umem, pd, virt, IRDMA_MEMREG_TYPE_MEM);
+ if (IS_ERR(iwmr)) {
+ err = PTR_ERR(iwmr);
+ goto err_release;
+ }
+
+ err = irdma_reg_user_mr_type_mem(iwmr, access);
+ if (err)
+ goto err_iwmr;
+
+ return &iwmr->ibmr;
+
+err_iwmr:
+ irdma_free_iwmr(iwmr);
+
+err_release:
+ ib_umem_release(&umem_dmabuf->umem);
+
+ return ERR_PTR(err);
+}
+
/**
* irdma_reg_phys_mr - register kernel physical memory
* @pd: ibpd pointer
@@ -4483,6 +4524,7 @@ 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),
--
2.27.0
^ permalink raw reply related [flat|nested] 2+ messages in thread
* Re: [PATCHv4 for-next 1/1] RDMA/irdma: Add support for dmabuf pin memory regions
2023-02-17 1:14 [PATCHv4 for-next 1/1] RDMA/irdma: Add support for dmabuf pin memory regions Zhu Yanjun
@ 2023-02-17 20:37 ` Jason Gunthorpe
0 siblings, 0 replies; 2+ messages in thread
From: Jason Gunthorpe @ 2023-02-17 20:37 UTC (permalink / raw)
To: Zhu Yanjun; +Cc: mustafa.ismail, shiraz.saleem, leon, linux-rdma, Zhu Yanjun
On Fri, Feb 17, 2023 at 09:14:25AM +0800, Zhu Yanjun wrote:
> From: Zhu Yanjun <yanjun.zhu@linux.dev>
>
> 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@ziepe.ca/t/
>
> Reviewed-by: Shiraz Saleem <shiraz.saleem@intel.com>
> Signed-off-by: Zhu Yanjun <yanjun.zhu@linux.dev>
> ---
> V3->V4: Remove inlen test
> V2->V3: Remove unnecessary variable initialization;
> Use error handler;
> V1->V2: Thanks Shiraz Saleem, he gave me a lot of good suggestions.
> This commit is based on the shared functions from refactored
> irdma_reg_user_mr.
> ---
> drivers/infiniband/hw/irdma/verbs.c | 42 +++++++++++++++++++++++++++++
> 1 file changed, 42 insertions(+)
Applied to for-next, thanks
Jason
^ permalink raw reply [flat|nested] 2+ messages in thread
end of thread, other threads:[~2023-02-17 20:37 UTC | newest]
Thread overview: 2+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2023-02-17 1:14 [PATCHv4 for-next 1/1] RDMA/irdma: Add support for dmabuf pin memory regions Zhu Yanjun
2023-02-17 20:37 ` Jason Gunthorpe
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).