public inbox for linux-rdma@vger.kernel.org
 help / color / mirror / Atom feed
From: Michael Margolin <mrgolin@amazon.com>
To: <jgg@nvidia.com>, <leon@kernel.org>, <linux-rdma@vger.kernel.org>
Cc: <sleybo@amazon.com>, <matua@amazon.com>, <gal.pressman@linux.dev>,
	"Daniel Kranzdorf" <dkkranzd@amazon.com>,
	Yonatan Nachum <ynachum@amazon.com>
Subject: [PATCH for-next] RDMA/efa: Add CQ with external memory support
Date: Thu, 15 May 2025 14:50:40 +0000	[thread overview]
Message-ID: <20250515145040.6862-1-mrgolin@amazon.com> (raw)

Add an option to create CQ using external memory instead of allocating
in the driver. The memory can be passed from userspace by dmabuf fd and
an offset. Add a capability bit to reflect on the feature support.

Reviewed-by: Daniel Kranzdorf <dkkranzd@amazon.com>
Reviewed-by: Yonatan Nachum <ynachum@amazon.com>
Signed-off-by: Michael Margolin <mrgolin@amazon.com>
---
 drivers/infiniband/hw/efa/efa.h       |  1 +
 drivers/infiniband/hw/efa/efa_verbs.c | 60 ++++++++++++++++++++++-----
 include/uapi/rdma/efa-abi.h           |  8 +++-
 3 files changed, 58 insertions(+), 11 deletions(-)

diff --git a/drivers/infiniband/hw/efa/efa.h b/drivers/infiniband/hw/efa/efa.h
index 838182d0409c..fd609a50cea0 100644
--- a/drivers/infiniband/hw/efa/efa.h
+++ b/drivers/infiniband/hw/efa/efa.h
@@ -107,6 +107,7 @@ struct efa_cq {
 	u16 cq_idx;
 	/* NULL when no interrupts requested */
 	struct efa_eq *eq;
+	struct ib_umem *umem;
 };
 
 struct efa_qp {
diff --git a/drivers/infiniband/hw/efa/efa_verbs.c b/drivers/infiniband/hw/efa/efa_verbs.c
index a8645a40730f..ecebc47ff249 100644
--- a/drivers/infiniband/hw/efa/efa_verbs.c
+++ b/drivers/infiniband/hw/efa/efa_verbs.c
@@ -249,6 +249,7 @@ int efa_query_device(struct ib_device *ibdev,
 		resp.max_rdma_size = dev_attr->max_rdma_size;
 
 		resp.device_caps |= EFA_QUERY_DEVICE_CAPS_CQ_WITH_SGID;
+		resp.device_caps |= EFA_QUERY_DEVICE_CAPS_CQ_WITH_EXT_MEM_DMABUF;
 		if (EFA_DEV_CAP(dev, RDMA_READ))
 			resp.device_caps |= EFA_QUERY_DEVICE_CAPS_RDMA_READ;
 
@@ -1082,8 +1083,11 @@ int efa_destroy_cq(struct ib_cq *ibcq, struct ib_udata *udata)
 		xa_erase(&dev->cqs_xa, cq->cq_idx);
 		synchronize_irq(cq->eq->irq.irqn);
 	}
-	efa_free_mapped(dev, cq->cpu_addr, cq->dma_addr, cq->size,
-			DMA_FROM_DEVICE);
+
+	if (cq->umem)
+		ib_umem_release(cq->umem);
+	else
+		efa_free_mapped(dev, cq->cpu_addr, cq->dma_addr, cq->size, DMA_FROM_DEVICE);
 	return 0;
 }
 
@@ -1133,8 +1137,10 @@ int efa_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr,
 	struct efa_com_create_cq_result result;
 	struct ib_device *ibdev = ibcq->device;
 	struct efa_dev *dev = to_edev(ibdev);
+	struct ib_umem_dmabuf *umem_dmabuf;
 	struct efa_ibv_create_cq cmd = {};
 	struct efa_cq *cq = to_ecq(ibcq);
+	struct scatterlist *umem_sgl;
 	int entries = attr->cqe;
 	bool set_src_addr;
 	int err;
@@ -1202,11 +1208,40 @@ int efa_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr,
 
 	cq->ucontext = ucontext;
 	cq->size = PAGE_ALIGN(cmd.cq_entry_size * entries * cmd.num_sub_cqs);
-	cq->cpu_addr = efa_zalloc_mapped(dev, &cq->dma_addr, cq->size,
-					 DMA_FROM_DEVICE);
-	if (!cq->cpu_addr) {
-		err = -ENOMEM;
-		goto err_out;
+
+	if (cmd.flags & EFA_CREATE_CQ_WITH_EXT_MEM_DMABUF) {
+		if (cmd.ext_mem_length < cq->size) {
+			ibdev_dbg(&dev->ibdev, "External memory too small\n");
+			err = -EINVAL;
+			goto err_out;
+		}
+
+		umem_dmabuf = ib_umem_dmabuf_get_pinned(ibdev, cmd.ext_mem_offset,
+							cq->size, cmd.ext_mem_fd,
+							IB_ACCESS_LOCAL_WRITE);
+		if (IS_ERR(umem_dmabuf)) {
+			err = PTR_ERR(umem_dmabuf);
+			ibdev_dbg(&dev->ibdev, "Failed to get dmabuf umem[%d]\n", err);
+			goto err_out;
+		}
+		cq->umem = &umem_dmabuf->umem;
+		umem_sgl = cq->umem->sgt_append.sgt.sgl;
+
+		if (sg_dma_len(umem_sgl) < ib_umem_offset(cq->umem) + cq->size) {
+			ibdev_dbg(&dev->ibdev, "Non contiguous CQ unsupported\n");
+			err = -EINVAL;
+			goto err_free_mapped;
+		}
+
+		cq->cpu_addr = NULL;
+		cq->dma_addr = sg_dma_address(umem_sgl) + ib_umem_offset(cq->umem);
+	} else {
+		cq->cpu_addr = efa_zalloc_mapped(dev, &cq->dma_addr, cq->size,
+						 DMA_FROM_DEVICE);
+		if (!cq->cpu_addr) {
+			err = -ENOMEM;
+			goto err_out;
+		}
 	}
 
 	params.uarn = cq->ucontext->uarn;
@@ -1231,7 +1266,9 @@ int efa_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr,
 	cq->ibcq.cqe = result.actual_depth;
 	WARN_ON_ONCE(entries != result.actual_depth);
 
-	err = cq_mmap_entries_setup(dev, cq, &resp, result.db_valid);
+	if (!(cmd.flags & EFA_CREATE_CQ_WITH_EXT_MEM_DMABUF))
+		err = cq_mmap_entries_setup(dev, cq, &resp, result.db_valid);
+
 	if (err) {
 		ibdev_dbg(ibdev, "Could not setup cq[%u] mmap entries\n",
 			  cq->cq_idx);
@@ -1270,8 +1307,11 @@ int efa_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr,
 err_destroy_cq:
 	efa_destroy_cq_idx(dev, cq->cq_idx);
 err_free_mapped:
-	efa_free_mapped(dev, cq->cpu_addr, cq->dma_addr, cq->size,
-			DMA_FROM_DEVICE);
+	if (cq->umem)
+		ib_umem_release(cq->umem);
+	else
+		efa_free_mapped(dev, cq->cpu_addr, cq->dma_addr, cq->size,
+				DMA_FROM_DEVICE);
 
 err_out:
 	atomic64_inc(&dev->stats.create_cq_err);
diff --git a/include/uapi/rdma/efa-abi.h b/include/uapi/rdma/efa-abi.h
index 11b94b0b035b..f2bcef789571 100644
--- a/include/uapi/rdma/efa-abi.h
+++ b/include/uapi/rdma/efa-abi.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) */
 /*
- * Copyright 2018-2024 Amazon.com, Inc. or its affiliates. All rights reserved.
+ * Copyright 2018-2025 Amazon.com, Inc. or its affiliates. All rights reserved.
  */
 
 #ifndef EFA_ABI_USER_H
@@ -56,6 +56,7 @@ struct efa_ibv_alloc_pd_resp {
 enum {
 	EFA_CREATE_CQ_WITH_COMPLETION_CHANNEL = 1 << 0,
 	EFA_CREATE_CQ_WITH_SGID               = 1 << 1,
+	EFA_CREATE_CQ_WITH_EXT_MEM_DMABUF     = 1 << 2,
 };
 
 struct efa_ibv_create_cq {
@@ -64,6 +65,10 @@ struct efa_ibv_create_cq {
 	__u16 num_sub_cqs;
 	__u8 flags;
 	__u8 reserved_58[5];
+	__aligned_u64 ext_mem_offset;
+	__aligned_u64 ext_mem_length;
+	__u32 ext_mem_fd;
+	__u8 reserved_120[4];
 };
 
 enum {
@@ -131,6 +136,7 @@ enum {
 	EFA_QUERY_DEVICE_CAPS_DATA_POLLING_128 = 1 << 4,
 	EFA_QUERY_DEVICE_CAPS_RDMA_WRITE = 1 << 5,
 	EFA_QUERY_DEVICE_CAPS_UNSOLICITED_WRITE_RECV = 1 << 6,
+	EFA_QUERY_DEVICE_CAPS_CQ_WITH_EXT_MEM_DMABUF = 1 << 7,
 };
 
 struct efa_ibv_ex_query_device_resp {
-- 
2.47.1


             reply	other threads:[~2025-05-15 14:50 UTC|newest]

Thread overview: 12+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-05-15 14:50 Michael Margolin [this message]
2025-05-18  6:42 ` [PATCH for-next] RDMA/efa: Add CQ with external memory support Leon Romanovsky
2025-05-18  8:56   ` Margolin, Michael
2025-05-20  9:16     ` Leon Romanovsky
2025-05-21 15:19       ` Margolin, Michael
2025-05-25 17:52         ` Jason Gunthorpe
2025-05-26 15:45           ` Margolin, Michael
2025-05-26 16:08             ` Jason Gunthorpe
2025-05-26 16:17               ` Margolin, Michael
2025-06-09 15:03                 ` Margolin, Michael
2025-06-11 19:47                   ` Jason Gunthorpe
2025-06-24 16:39                     ` Margolin, Michael

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20250515145040.6862-1-mrgolin@amazon.com \
    --to=mrgolin@amazon.com \
    --cc=dkkranzd@amazon.com \
    --cc=gal.pressman@linux.dev \
    --cc=jgg@nvidia.com \
    --cc=leon@kernel.org \
    --cc=linux-rdma@vger.kernel.org \
    --cc=matua@amazon.com \
    --cc=sleybo@amazon.com \
    --cc=ynachum@amazon.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox