Linux RDMA and InfiniBand development
 help / color / mirror / Atom feed
From: Yishai Hadas <yishaih@nvidia.com>
To: <jgg@ziepe.ca>, <leon@kernel.org>
Cc: <linux-rdma@vger.kernel.org>, <selvin.xavier@broadcom.com>,
	<kalesh-anakkur.purayil@broadcom.com>,
	<chengyou@linux.alibaba.com>, <kaishen@linux.alibaba.com>,
	<tangchengchang@huawei.com>, <huangjunxian6@hisilicon.com>,
	<abhijit.gangurde@amd.com>, <allen.hubbe@amd.com>,
	<longli@microsoft.com>, <kotaranov@microsoft.com>,
	<mkalderon@marvell.com>, <bryan-bt.tan@broadcom.com>,
	<vishnu.dasa@broadcom.com>, <yishaih@nvidia.com>,
	<maorg@nvidia.com>
Subject: [PATCH V1 rdma-next 05/15] RDMA/umem: Support an explicit DMA direction other than DMA_BIDIRECTIONAL
Date: Tue, 15 Sep 2026 17:09:23 +0300	[thread overview]
Message-ID: <20260915140933.40580-6-yishaih@nvidia.com> (raw)
In-Reply-To: <20260915140933.40580-1-yishaih@nvidia.com>

Add a dma_dir field to struct ib_umem to record the direction chosen at
map time and reuse it at unmap. Thread an explicit dma_data_direction
parameter through the internal pinning helpers so each caller can supply
the direction that matches the device's actual access pattern.

All existing callers still pass DMA_BIDIRECTIONAL, so this is a pure
mechanism addition with no behavioural change.

Signed-off-by: Yishai Hadas <yishaih@nvidia.com>
---
 drivers/infiniband/core/umem.c | 64 ++++++++++++++++++++++------------
 include/rdma/ib_umem.h         |  2 ++
 2 files changed, 43 insertions(+), 23 deletions(-)

diff --git a/drivers/infiniband/core/umem.c b/drivers/infiniband/core/umem.c
index 88110b9661f5..c2f277ada042 100644
--- a/drivers/infiniband/core/umem.c
+++ b/drivers/infiniband/core/umem.c
@@ -55,7 +55,7 @@ static void __ib_umem_release(struct ib_device *dev, struct ib_umem *umem, int d
 
 	if (dirty)
 		ib_dma_unmap_sgtable_attrs(dev, &umem->sgt_append.sgt,
-					   DMA_BIDIRECTIONAL, umem->dma_attrs);
+					   umem->dma_dir, umem->dma_attrs);
 
 	for_each_sgtable_sg(&umem->sgt_append.sgt, sg, i) {
 		unpin_user_page_range_dirty_lock(sg_page(sg),
@@ -161,7 +161,8 @@ EXPORT_SYMBOL(ib_umem_find_best_pgsz);
 
 static struct ib_umem *__ib_umem_get_va(struct ib_device *device,
 					unsigned long addr, size_t size,
-					int access)
+					int access,
+					enum dma_data_direction dir)
 {
 	struct ib_umem *umem;
 	struct page **page_list;
@@ -202,6 +203,7 @@ static struct ib_umem *__ib_umem_get_va(struct ib_device *device,
 	 */
 	umem->iova = addr;
 	umem->writable   = ib_access_writable(access);
+	umem->dma_dir    = dir;
 	umem->owning_mm = mm = current->mm;
 	umem->dma_attrs = DMA_ATTR_REQUIRE_COHERENT;
 	if (access & IB_ACCESS_RELAXED_ORDERING)
@@ -261,7 +263,7 @@ static struct ib_umem *__ib_umem_get_va(struct ib_device *device,
 	}
 
 	ret = ib_dma_map_sgtable_attrs(device, &umem->sgt_append.sgt,
-				       DMA_BIDIRECTIONAL, umem->dma_attrs);
+				       dir, umem->dma_attrs);
 	if (ret)
 		goto umem_release;
 	goto out;
@@ -279,17 +281,16 @@ static struct ib_umem *__ib_umem_get_va(struct ib_device *device,
 	return ret ? ERR_PTR(ret) : umem;
 }
 
-/**
- * ib_umem_get_desc - Pin a umem from a buffer descriptor.
- * @device: IB device.
- * @desc:   buffer descriptor (VA or DMABUF).
- * @access: IB access flags.
+/*
+ * __ib_umem_get_desc_dir - core implementation for ib_umem_get_desc().
  *
- * Return: caller-owned umem on success, ERR_PTR(...) on error.
+ * @dir applies to VA buffers only; dmabuf direction is managed by the
+ * dmabuf subsystem and this argument is ignored for that type.
  */
-struct ib_umem *ib_umem_get_desc(struct ib_device *device,
-				 const struct ib_uverbs_buffer_desc *desc,
-				 int access)
+static struct ib_umem *
+__ib_umem_get_desc_dir(struct ib_device *device,
+		       const struct ib_uverbs_buffer_desc *desc,
+		       int access, enum dma_data_direction dir)
 {
 	struct ib_umem_dmabuf *umem_dmabuf;
 
@@ -310,11 +311,26 @@ struct ib_umem *ib_umem_get_desc(struct ib_device *device,
 		return &umem_dmabuf->umem;
 	case IB_UVERBS_BUFFER_TYPE_VA:
 		return __ib_umem_get_va(device, desc->addr, desc->length,
-					access);
+					access, dir);
 	default:
 		return ERR_PTR(-EINVAL);
 	}
 }
+
+/**
+ * ib_umem_get_desc - Pin a umem from a buffer descriptor.
+ * @device: IB device.
+ * @desc:   buffer descriptor (VA or DMABUF).
+ * @access: IB access flags.
+ *
+ * Return: caller-owned umem on success, ERR_PTR(...) on error.
+ */
+struct ib_umem *ib_umem_get_desc(struct ib_device *device,
+				 const struct ib_uverbs_buffer_desc *desc,
+				 int access)
+{
+	return __ib_umem_get_desc_dir(device, desc, access, DMA_BIDIRECTIONAL);
+}
 EXPORT_SYMBOL(ib_umem_get_desc);
 
 /*
@@ -376,11 +392,12 @@ static int ib_umem_resolve_desc(const struct uverbs_attr_bundle *attrs,
 static struct ib_umem *
 ib_umem_get_desc_check(struct ib_device *device,
 		       const struct ib_uverbs_buffer_desc *desc,
-		       size_t min_size, int access)
+		       size_t min_size, int access,
+		       enum dma_data_direction dir)
 {
 	struct ib_umem *umem;
 
-	umem = ib_umem_get_desc(device, desc, access);
+	umem = __ib_umem_get_desc_dir(device, desc, access, dir);
 	if (IS_ERR(umem))
 		return umem;
 	if (umem->length < min_size) {
@@ -401,7 +418,7 @@ static struct ib_umem *
 ib_umem_get_from_attrs(struct ib_device *device,
 		       const struct uverbs_attr_bundle *attrs,
 		       u16 attr_id, ib_umem_buf_desc_filler_t legacy_filler,
-		       size_t size, int access)
+		       size_t size, int access, enum dma_data_direction dir)
 {
 	struct ib_uverbs_buffer_desc desc = {};
 	int ret;
@@ -411,7 +428,7 @@ ib_umem_get_from_attrs(struct ib_device *device,
 		return NULL;
 	if (ret)
 		return ERR_PTR(ret);
-	return ib_umem_get_desc_check(device, &desc, size, access);
+	return ib_umem_get_desc_check(device, &desc, size, access, dir);
 }
 
 /*
@@ -431,7 +448,8 @@ ib_umem_get_from_attrs_or_va(struct ib_device *device,
 			     const struct uverbs_attr_bundle *attrs,
 			     u16 attr_id,
 			     ib_umem_buf_desc_filler_t legacy_filler,
-			     u64 addr, size_t size, int access)
+			     u64 addr, size_t size, int access,
+			     enum dma_data_direction dir)
 {
 	struct ib_uverbs_buffer_desc desc = {};
 	int ret;
@@ -445,7 +463,7 @@ ib_umem_get_from_attrs_or_va(struct ib_device *device,
 		};
 	else if (ret)
 		return ERR_PTR(ret);
-	return ib_umem_get_desc_check(device, &desc, size, access);
+	return ib_umem_get_desc_check(device, &desc, size, access, dir);
 }
 
 /**
@@ -464,7 +482,7 @@ struct ib_umem *ib_umem_get_attr(struct ib_device *device,
 				 u16 attr_id, size_t size, int access)
 {
 	return ib_umem_get_from_attrs(device, attrs, attr_id, NULL, size,
-				      access);
+				      access, DMA_BIDIRECTIONAL);
 }
 EXPORT_SYMBOL(ib_umem_get_attr);
 
@@ -503,7 +521,7 @@ struct ib_umem *ib_umem_get_attr_or_va(struct ib_device *device,
 				       int access)
 {
 	return ib_umem_get_from_attrs_or_va(device, attrs, attr_id, NULL, addr,
-					    size, access);
+					    size, access, DMA_BIDIRECTIONAL);
 }
 EXPORT_SYMBOL(ib_umem_get_attr_or_va);
 
@@ -579,7 +597,7 @@ struct ib_umem *ib_umem_get_cq_buf(struct ib_device *device,
 	return ib_umem_get_from_attrs(device, attrs,
 				      UVERBS_ATTR_CREATE_CQ_BUF_UMEM,
 				      uverbs_create_cq_get_buffer_desc,
-				      size, access);
+				      size, access, DMA_BIDIRECTIONAL);
 }
 EXPORT_SYMBOL(ib_umem_get_cq_buf);
 
@@ -608,7 +626,7 @@ struct ib_umem *ib_umem_get_cq_buf_or_va(struct ib_device *device,
 	return ib_umem_get_from_attrs_or_va(device, attrs,
 					    UVERBS_ATTR_CREATE_CQ_BUF_UMEM,
 					    uverbs_create_cq_get_buffer_desc,
-					    addr, size, access);
+					    addr, size, access, DMA_BIDIRECTIONAL);
 }
 EXPORT_SYMBOL(ib_umem_get_cq_buf_or_va);
 
diff --git a/include/rdma/ib_umem.h b/include/rdma/ib_umem.h
index 1fe87fd1d769..dcb645419692 100644
--- a/include/rdma/ib_umem.h
+++ b/include/rdma/ib_umem.h
@@ -7,6 +7,7 @@
 #ifndef IB_UMEM_H
 #define IB_UMEM_H
 
+#include <linux/dma-direction.h>
 #include <linux/scatterlist.h>
 
 struct ib_device;
@@ -19,6 +20,7 @@ struct ib_umem {
 	size_t			length;
 	unsigned long		address;
 	unsigned long		dma_attrs;
+	enum dma_data_direction dma_dir;
 	u32 writable : 1;
 	u32 is_odp : 1;
 	u32 is_dmabuf : 1;
-- 
2.18.1


  parent reply	other threads:[~2026-09-15 14:11 UTC|newest]

Thread overview: 35+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-09-15 14:09 [PATCH V1 rdma-next 00/15] DMA direction and mlx5 driver correctness fixes Yishai Hadas
2026-09-15 14:09 ` [PATCH V1 rdma-next 01/15] RDMA/erdma: Pin CQ buffer writable to match device DMA write access Yishai Hadas
2026-09-15 14:22   ` sashiko-bot
2026-09-15 14:09 ` [PATCH V1 rdma-next 02/15] RDMA/hns: " Yishai Hadas
2026-09-15 14:20   ` sashiko-bot
2026-09-15 14:09 ` [PATCH V1 rdma-next 03/15] RDMA/vmw_pvrdma: Pin QP and SRQ rings " Yishai Hadas
2026-09-15 14:21   ` sashiko-bot
2026-09-15 14:09 ` [PATCH V1 rdma-next 04/15] RDMA/umem: Reuse ib_umem_get_cq_buf_or_va() for VA-only CQ pinning Yishai Hadas
2026-09-15 14:21   ` sashiko-bot
2026-09-20 12:24   ` Leon Romanovsky
2026-09-22  7:25     ` Yishai Hadas
2026-09-15 14:09 ` Yishai Hadas [this message]
2026-09-15 14:21   ` [PATCH V1 rdma-next 05/15] RDMA/umem: Support an explicit DMA direction other than DMA_BIDIRECTIONAL sashiko-bot
2026-09-15 14:09 ` [PATCH V1 rdma-next 06/15] RDMA/umem: Map CQ buffers DMA_FROM_DEVICE Yishai Hadas
2026-09-15 14:25   ` sashiko-bot
2026-09-15 14:09 ` [PATCH V1 rdma-next 07/15] RDMA/umem: Derive DMA direction from IB access flags Yishai Hadas
2026-09-15 14:28   ` sashiko-bot
2026-09-15 14:09 ` [PATCH V1 rdma-next 08/15] RDMA/mlx5: Fix mlx5_ib_dev_res_init() failure when XRC cap is absent Yishai Hadas
2026-09-15 14:24   ` sashiko-bot
2026-09-15 14:09 ` [PATCH V1 rdma-next 09/15] RDMA/mlx5: Put resource reference in mlx5_ib_wq_event() Yishai Hadas
2026-09-15 14:25   ` sashiko-bot
2026-09-15 14:09 ` [PATCH V1 rdma-next 10/15] RDMA/mlx5: Set WQ event handler before firmware RQ insertion Yishai Hadas
2026-09-15 14:30   ` sashiko-bot
2026-09-15 14:09 ` [PATCH V1 rdma-next 11/15] RDMA/mlx5: Set SRQ event handler before xarray insertion Yishai Hadas
2026-09-15 14:36   ` sashiko-bot
2026-09-15 14:09 ` [PATCH V1 rdma-next 12/15] RDMA/mlx5: Set RQ event handler for raw-packet QP Yishai Hadas
2026-09-15 14:32   ` sashiko-bot
2026-09-15 14:09 ` [PATCH V1 rdma-next 13/15] RDMA/mlx5: Set QP event handler before firmware QPC insertion Yishai Hadas
2026-09-15 14:35   ` sashiko-bot
2026-09-15 14:09 ` [PATCH V1 rdma-next 14/15] RDMA/mlx5: Initialize QP/RQ/SQ resource refcount before publishing it Yishai Hadas
2026-09-15 14:29   ` sashiko-bot
2026-09-15 14:09 ` [PATCH V1 rdma-next 15/15] RDMA/mlx5: Fix signed integer overflow in EQE qp_srq type shift Yishai Hadas
2026-09-15 14:31   ` sashiko-bot
2026-09-28 12:17 ` [PATCH V1 rdma-next 00/15] DMA direction and mlx5 driver correctness fixes Leon Romanovsky
2026-09-28 12:19 ` Leon Romanovsky

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=20260915140933.40580-6-yishaih@nvidia.com \
    --to=yishaih@nvidia.com \
    --cc=abhijit.gangurde@amd.com \
    --cc=allen.hubbe@amd.com \
    --cc=bryan-bt.tan@broadcom.com \
    --cc=chengyou@linux.alibaba.com \
    --cc=huangjunxian6@hisilicon.com \
    --cc=jgg@ziepe.ca \
    --cc=kaishen@linux.alibaba.com \
    --cc=kalesh-anakkur.purayil@broadcom.com \
    --cc=kotaranov@microsoft.com \
    --cc=leon@kernel.org \
    --cc=linux-rdma@vger.kernel.org \
    --cc=longli@microsoft.com \
    --cc=maorg@nvidia.com \
    --cc=mkalderon@marvell.com \
    --cc=selvin.xavier@broadcom.com \
    --cc=tangchengchang@huawei.com \
    --cc=vishnu.dasa@broadcom.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