All of lore.kernel.org
 help / color / mirror / Atom feed
From: Sasha Levin <sashal@kernel.org>
To: stable@vger.kernel.org
Cc: Leon Romanovsky <leonro@nvidia.com>, Sasha Levin <sashal@kernel.org>
Subject: [PATCH 5.10.y 2/3] RDMA: Move DMA block iterator logic into dedicated files
Date: Mon, 15 Jun 2026 23:17:36 -0400	[thread overview]
Message-ID: <20260616031737.2781524-2-sashal@kernel.org> (raw)
In-Reply-To: <20260616031737.2781524-1-sashal@kernel.org>

From: Leon Romanovsky <leonro@nvidia.com>

[ Upstream commit 6094ea64c69520ed1e770e7c79c43412de202bfa ]

The DMA iterator logic was mixed into verbs and umem-specific code,
forcing all users to include rdma/ib_umem.h. Move the block iterator
logic into iter.c and rdma/iter.h so that rdma/ib_umem.h and
rdma/ib_verbs.h can be separated in a follow-up patch.

Link: https://patch.msgid.link/20260213-refactor-umem-v1-1-f3be85847922@nvidia.com
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Stable-dep-of: 15fe76e23615 ("RDMA/umem: Fix truncation for block sizes >= 4G")
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/infiniband/core/Makefile             |  2 +-
 drivers/infiniband/core/iter.c               | 43 +++++++++++
 drivers/infiniband/core/verbs.c              | 37 ---------
 drivers/infiniband/hw/bnxt_re/qplib_res.c    |  2 +-
 drivers/infiniband/hw/cxgb4/mem.c            |  2 +-
 drivers/infiniband/hw/efa/efa_verbs.c        |  2 +-
 drivers/infiniband/hw/hns/hns_roce_alloc.c   |  2 +-
 drivers/infiniband/hw/i40iw/i40iw_verbs.c    |  1 +
 drivers/infiniband/hw/mlx4/mr.c              |  1 +
 drivers/infiniband/hw/mlx5/mem.c             |  1 +
 drivers/infiniband/hw/mthca/mthca_provider.c |  2 +-
 drivers/infiniband/hw/ocrdma/ocrdma_verbs.c  |  2 +-
 drivers/infiniband/hw/qedr/verbs.c           |  2 +-
 drivers/infiniband/hw/vmw_pvrdma/pvrdma.h    |  2 +-
 include/rdma/ib_umem.h                       | 24 ------
 include/rdma/ib_verbs.h                      | 47 ------------
 include/rdma/iter.h                          | 80 ++++++++++++++++++++
 17 files changed, 135 insertions(+), 117 deletions(-)
 create mode 100644 drivers/infiniband/core/iter.c
 create mode 100644 include/rdma/iter.h

diff --git a/drivers/infiniband/core/Makefile b/drivers/infiniband/core/Makefile
index ccf2670ef45efe..b19200130fb440 100644
--- a/drivers/infiniband/core/Makefile
+++ b/drivers/infiniband/core/Makefile
@@ -12,7 +12,7 @@ ib_core-y :=			packer.o ud_header.o verbs.o cq.o rw.o sysfs.o \
 				roce_gid_mgmt.o mr_pool.o addr.o sa_query.o \
 				multicast.o mad.o smi.o agent.o mad_rmpp.o \
 				nldev.o restrack.o counters.o ib_core_uverbs.o \
-				trace.o lag.o
+				trace.o lag.o iter.o
 
 ib_core-$(CONFIG_SECURITY_INFINIBAND) += security.o
 ib_core-$(CONFIG_CGROUP_RDMA) += cgroup.o
diff --git a/drivers/infiniband/core/iter.c b/drivers/infiniband/core/iter.c
new file mode 100644
index 00000000000000..8e543d100657ee
--- /dev/null
+++ b/drivers/infiniband/core/iter.c
@@ -0,0 +1,43 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2026, NVIDIA CORPORATION & AFFILIATES. */
+
+#include <linux/export.h>
+#include <rdma/iter.h>
+
+void __rdma_block_iter_start(struct ib_block_iter *biter,
+			     struct scatterlist *sglist, unsigned int nents,
+			     unsigned long pgsz)
+{
+	memset(biter, 0, sizeof(struct ib_block_iter));
+	biter->__sg = sglist;
+	biter->__sg_nents = nents;
+
+	/* Driver provides best block size to use */
+	biter->__pg_bit = __fls(pgsz);
+}
+EXPORT_SYMBOL(__rdma_block_iter_start);
+
+bool __rdma_block_iter_next(struct ib_block_iter *biter)
+{
+	unsigned int block_offset;
+	unsigned int delta;
+
+	if (!biter->__sg_nents || !biter->__sg)
+		return false;
+
+	biter->__dma_addr = sg_dma_address(biter->__sg) + biter->__sg_advance;
+	block_offset = biter->__dma_addr & (BIT_ULL(biter->__pg_bit) - 1);
+	delta = BIT_ULL(biter->__pg_bit) - block_offset;
+
+	while (biter->__sg_nents && biter->__sg &&
+	       sg_dma_len(biter->__sg) - biter->__sg_advance <= delta) {
+		delta -= sg_dma_len(biter->__sg) - biter->__sg_advance;
+		biter->__sg_advance = 0;
+		biter->__sg = sg_next(biter->__sg);
+		biter->__sg_nents--;
+	}
+	biter->__sg_advance += delta;
+
+	return true;
+}
+EXPORT_SYMBOL(__rdma_block_iter_next);
diff --git a/drivers/infiniband/core/verbs.c b/drivers/infiniband/core/verbs.c
index 4a28f30c39f104..1fdaffd0b9880e 100644
--- a/drivers/infiniband/core/verbs.c
+++ b/drivers/infiniband/core/verbs.c
@@ -2896,40 +2896,3 @@ int rdma_init_netdev(struct ib_device *device, u8 port_num,
 					     netdev, params.param);
 }
 EXPORT_SYMBOL(rdma_init_netdev);
-
-void __rdma_block_iter_start(struct ib_block_iter *biter,
-			     struct scatterlist *sglist, unsigned int nents,
-			     unsigned long pgsz)
-{
-	memset(biter, 0, sizeof(struct ib_block_iter));
-	biter->__sg = sglist;
-	biter->__sg_nents = nents;
-
-	/* Driver provides best block size to use */
-	biter->__pg_bit = __fls(pgsz);
-}
-EXPORT_SYMBOL(__rdma_block_iter_start);
-
-bool __rdma_block_iter_next(struct ib_block_iter *biter)
-{
-	unsigned int block_offset;
-	unsigned int sg_delta;
-
-	if (!biter->__sg_nents || !biter->__sg)
-		return false;
-
-	biter->__dma_addr = sg_dma_address(biter->__sg) + biter->__sg_advance;
-	block_offset = biter->__dma_addr & (BIT_ULL(biter->__pg_bit) - 1);
-	sg_delta = BIT_ULL(biter->__pg_bit) - block_offset;
-
-	if (sg_dma_len(biter->__sg) - biter->__sg_advance > sg_delta) {
-		biter->__sg_advance += sg_delta;
-	} else {
-		biter->__sg_advance = 0;
-		biter->__sg = sg_next(biter->__sg);
-		biter->__sg_nents--;
-	}
-
-	return true;
-}
-EXPORT_SYMBOL(__rdma_block_iter_next);
diff --git a/drivers/infiniband/hw/bnxt_re/qplib_res.c b/drivers/infiniband/hw/bnxt_re/qplib_res.c
index 8547a8512541ce..49e6b9fae36e7d 100644
--- a/drivers/infiniband/hw/bnxt_re/qplib_res.c
+++ b/drivers/infiniband/hw/bnxt_re/qplib_res.c
@@ -46,7 +46,7 @@
 #include <linux/if_vlan.h>
 #include <linux/vmalloc.h>
 #include <rdma/ib_verbs.h>
-#include <rdma/ib_umem.h>
+#include <rdma/iter.h>
 
 #include "roce_hsi.h"
 #include "qplib_res.h"
diff --git a/drivers/infiniband/hw/cxgb4/mem.c b/drivers/infiniband/hw/cxgb4/mem.c
index 42234df896fb2c..02fb7c314ab46f 100644
--- a/drivers/infiniband/hw/cxgb4/mem.c
+++ b/drivers/infiniband/hw/cxgb4/mem.c
@@ -32,9 +32,9 @@
 
 #include <linux/module.h>
 #include <linux/moduleparam.h>
-#include <rdma/ib_umem.h>
 #include <linux/atomic.h>
 #include <rdma/ib_user_verbs.h>
+#include <rdma/iter.h>
 
 #include "iw_cxgb4.h"
 
diff --git a/drivers/infiniband/hw/efa/efa_verbs.c b/drivers/infiniband/hw/efa/efa_verbs.c
index be6c5d48448784..15086856581f70 100644
--- a/drivers/infiniband/hw/efa/efa_verbs.c
+++ b/drivers/infiniband/hw/efa/efa_verbs.c
@@ -7,9 +7,9 @@
 #include <linux/log2.h>
 
 #include <rdma/ib_addr.h>
-#include <rdma/ib_umem.h>
 #include <rdma/ib_user_verbs.h>
 #include <rdma/ib_verbs.h>
+#include <rdma/iter.h>
 #include <rdma/uverbs_ioctl.h>
 
 #include "efa.h"
diff --git a/drivers/infiniband/hw/hns/hns_roce_alloc.c b/drivers/infiniband/hw/hns/hns_roce_alloc.c
index 4bcaaa0524b127..37cdcd6ba17bce 100644
--- a/drivers/infiniband/hw/hns/hns_roce_alloc.c
+++ b/drivers/infiniband/hw/hns/hns_roce_alloc.c
@@ -34,7 +34,7 @@
 #include <linux/platform_device.h>
 #include <linux/vmalloc.h>
 #include "hns_roce_device.h"
-#include <rdma/ib_umem.h>
+#include <rdma/iter.h>
 
 int hns_roce_bitmap_alloc(struct hns_roce_bitmap *bitmap, unsigned long *obj)
 {
diff --git a/drivers/infiniband/hw/i40iw/i40iw_verbs.c b/drivers/infiniband/hw/i40iw/i40iw_verbs.c
index 89654dc91d81a7..ac37914a1ee21c 100644
--- a/drivers/infiniband/hw/i40iw/i40iw_verbs.c
+++ b/drivers/infiniband/hw/i40iw/i40iw_verbs.c
@@ -45,6 +45,7 @@
 #include <rdma/iw_cm.h>
 #include <rdma/ib_user_verbs.h>
 #include <rdma/ib_umem.h>
+#include <rdma/iter.h>
 #include <rdma/uverbs_ioctl.h>
 #include "i40iw.h"
 
diff --git a/drivers/infiniband/hw/mlx4/mr.c b/drivers/infiniband/hw/mlx4/mr.c
index 811b4bb345247d..0f303e8aa13776 100644
--- a/drivers/infiniband/hw/mlx4/mr.c
+++ b/drivers/infiniband/hw/mlx4/mr.c
@@ -33,6 +33,7 @@
 
 #include <linux/slab.h>
 #include <rdma/ib_user_verbs.h>
+#include <rdma/iter.h>
 
 #include "mlx4_ib.h"
 
diff --git a/drivers/infiniband/hw/mlx5/mem.c b/drivers/infiniband/hw/mlx5/mem.c
index 13de3d2edd34e3..47aca791cbf956 100644
--- a/drivers/infiniband/hw/mlx5/mem.c
+++ b/drivers/infiniband/hw/mlx5/mem.c
@@ -33,6 +33,7 @@
 #include <linux/module.h>
 #include <rdma/ib_umem.h>
 #include <rdma/ib_umem_odp.h>
+#include <rdma/iter.h>
 #include "mlx5_ib.h"
 #include <linux/jiffies.h>
 
diff --git a/drivers/infiniband/hw/mthca/mthca_provider.c b/drivers/infiniband/hw/mthca/mthca_provider.c
index c48e3be6754066..d4d7e34f173b2a 100644
--- a/drivers/infiniband/hw/mthca/mthca_provider.c
+++ b/drivers/infiniband/hw/mthca/mthca_provider.c
@@ -35,8 +35,8 @@
  */
 
 #include <rdma/ib_smi.h>
-#include <rdma/ib_umem.h>
 #include <rdma/ib_user_verbs.h>
+#include <rdma/iter.h>
 #include <rdma/uverbs_ioctl.h>
 
 #include <linux/sched.h>
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c
index 2a691dc30a1299..700bd4b968aed8 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c
@@ -44,9 +44,9 @@
 #include <rdma/ib_verbs.h>
 #include <rdma/ib_user_verbs.h>
 #include <rdma/iw_cm.h>
-#include <rdma/ib_umem.h>
 #include <rdma/ib_addr.h>
 #include <rdma/ib_cache.h>
+#include <rdma/iter.h>
 #include <rdma/uverbs_ioctl.h>
 
 #include "ocrdma.h"
diff --git a/drivers/infiniband/hw/qedr/verbs.c b/drivers/infiniband/hw/qedr/verbs.c
index d382ac21159c28..ee215fa7168da7 100644
--- a/drivers/infiniband/hw/qedr/verbs.c
+++ b/drivers/infiniband/hw/qedr/verbs.c
@@ -39,9 +39,9 @@
 #include <rdma/ib_verbs.h>
 #include <rdma/ib_user_verbs.h>
 #include <rdma/iw_cm.h>
-#include <rdma/ib_umem.h>
 #include <rdma/ib_addr.h>
 #include <rdma/ib_cache.h>
+#include <rdma/iter.h>
 #include <rdma/uverbs_ioctl.h>
 
 #include <linux/qed/common_hsi.h>
diff --git a/drivers/infiniband/hw/vmw_pvrdma/pvrdma.h b/drivers/infiniband/hw/vmw_pvrdma/pvrdma.h
index de57f2fed74375..bd85a4380bf1a4 100644
--- a/drivers/infiniband/hw/vmw_pvrdma/pvrdma.h
+++ b/drivers/infiniband/hw/vmw_pvrdma/pvrdma.h
@@ -53,8 +53,8 @@
 #include <linux/pci.h>
 #include <linux/semaphore.h>
 #include <linux/workqueue.h>
-#include <rdma/ib_umem.h>
 #include <rdma/ib_verbs.h>
+#include <rdma/iter.h>
 #include <rdma/vmw_pvrdma-abi.h>
 
 #include "pvrdma_ring.h"
diff --git a/include/rdma/ib_umem.h b/include/rdma/ib_umem.h
index 161c80e1d71957..a68ba94fe799c8 100644
--- a/include/rdma/ib_umem.h
+++ b/include/rdma/ib_umem.h
@@ -46,30 +46,6 @@ static inline size_t ib_umem_num_pages(struct ib_umem *umem)
 {
 	return ib_umem_num_dma_blocks(umem, PAGE_SIZE);
 }
-
-static inline void __rdma_umem_block_iter_start(struct ib_block_iter *biter,
-						struct ib_umem *umem,
-						unsigned long pgsz)
-{
-	__rdma_block_iter_start(biter, umem->sg_head.sgl, umem->nmap, pgsz);
-}
-
-/**
- * rdma_umem_for_each_dma_block - iterate over contiguous DMA blocks of the umem
- * @umem: umem to iterate over
- * @biter: block iterator variable
- * @pgsz: Page size to split the list into
- *
- * pgsz must be <= PAGE_SIZE or computed by ib_umem_find_best_pgsz(). The
- * returned DMA blocks will be aligned to pgsz and span the range:
- * ALIGN_DOWN(umem->address, pgsz) to ALIGN(umem->address + umem->length, pgsz)
- *
- * Performs exactly ib_umem_num_dma_blocks() iterations.
- */
-#define rdma_umem_for_each_dma_block(umem, biter, pgsz)                        \
-	for (__rdma_umem_block_iter_start(biter, umem, pgsz);                  \
-	     __rdma_block_iter_next(biter);)
-
 #ifdef CONFIG_INFINIBAND_USER_MEM
 
 struct ib_umem *ib_umem_get(struct ib_device *device, unsigned long addr,
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index 495bf66620a6fc..bd04ec8c506822 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -2756,21 +2756,6 @@ struct ib_client {
 	u8 no_kverbs_req:1;
 };
 
-/*
- * IB block DMA iterator
- *
- * Iterates the DMA-mapped SGL in contiguous memory blocks aligned
- * to a HW supported page size.
- */
-struct ib_block_iter {
-	/* internal states */
-	struct scatterlist *__sg;	/* sg holding the current aligned block */
-	dma_addr_t __dma_addr;		/* unaligned DMA address of this block */
-	unsigned int __sg_nents;	/* number of SG entries */
-	unsigned int __sg_advance;	/* number of bytes to advance in sg in next step */
-	unsigned int __pg_bit;		/* alignment of current block */
-};
-
 struct ib_device *_ib_alloc_device(size_t size);
 #define ib_alloc_device(drv_struct, member)                                    \
 	container_of(_ib_alloc_device(sizeof(struct drv_struct) +              \
@@ -2792,38 +2777,6 @@ void ib_unregister_device_queued(struct ib_device *ib_dev);
 int ib_register_client   (struct ib_client *client);
 void ib_unregister_client(struct ib_client *client);
 
-void __rdma_block_iter_start(struct ib_block_iter *biter,
-			     struct scatterlist *sglist,
-			     unsigned int nents,
-			     unsigned long pgsz);
-bool __rdma_block_iter_next(struct ib_block_iter *biter);
-
-/**
- * rdma_block_iter_dma_address - get the aligned dma address of the current
- * block held by the block iterator.
- * @biter: block iterator holding the memory block
- */
-static inline dma_addr_t
-rdma_block_iter_dma_address(struct ib_block_iter *biter)
-{
-	return biter->__dma_addr & ~(BIT_ULL(biter->__pg_bit) - 1);
-}
-
-/**
- * rdma_for_each_block - iterate over contiguous memory blocks of the sg list
- * @sglist: sglist to iterate over
- * @biter: block iterator holding the memory block
- * @nents: maximum number of sg entries to iterate over
- * @pgsz: best HW supported page size to use
- *
- * Callers may use rdma_block_iter_dma_address() to get each
- * blocks aligned DMA address.
- */
-#define rdma_for_each_block(sglist, biter, nents, pgsz)		\
-	for (__rdma_block_iter_start(biter, sglist, nents,	\
-				     pgsz);			\
-	     __rdma_block_iter_next(biter);)
-
 /**
  * ib_get_client_data - Get IB client context
  * @device:Device to get context for
diff --git a/include/rdma/iter.h b/include/rdma/iter.h
new file mode 100644
index 00000000000000..3c85ea3eab78ee
--- /dev/null
+++ b/include/rdma/iter.h
@@ -0,0 +1,80 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2026, NVIDIA CORPORATION & AFFILIATES. */
+
+#ifndef _RDMA_ITER_H_
+#define _RDMA_ITER_H_
+
+#include <linux/scatterlist.h>
+#include <rdma/ib_umem.h>
+
+/**
+ * IB block DMA iterator
+ *
+ * Iterates the DMA-mapped SGL in contiguous memory blocks aligned
+ * to a HW supported page size.
+ */
+struct ib_block_iter {
+	/* internal states */
+	struct scatterlist *__sg;	/* sg holding the current aligned block */
+	dma_addr_t __dma_addr;		/* unaligned DMA address of this block */
+	unsigned int __sg_nents;	/* number of SG entries */
+	unsigned int __sg_advance;	/* number of bytes to advance in sg in next step */
+	unsigned int __pg_bit;		/* alignment of current block */
+};
+
+void __rdma_block_iter_start(struct ib_block_iter *biter,
+			     struct scatterlist *sglist,
+			     unsigned int nents,
+			     unsigned long pgsz);
+bool __rdma_block_iter_next(struct ib_block_iter *biter);
+
+/**
+ * rdma_block_iter_dma_address - get the aligned dma address of the current
+ * block held by the block iterator.
+ * @biter: block iterator holding the memory block
+ */
+static inline dma_addr_t
+rdma_block_iter_dma_address(struct ib_block_iter *biter)
+{
+	return biter->__dma_addr & ~(BIT_ULL(biter->__pg_bit) - 1);
+}
+
+/**
+ * rdma_for_each_block - iterate over contiguous memory blocks of the sg list
+ * @sglist: sglist to iterate over
+ * @biter: block iterator holding the memory block
+ * @nents: maximum number of sg entries to iterate over
+ * @pgsz: best HW supported page size to use
+ *
+ * Callers may use rdma_block_iter_dma_address() to get each
+ * blocks aligned DMA address.
+ */
+#define rdma_for_each_block(sglist, biter, nents, pgsz)		\
+	for (__rdma_block_iter_start(biter, sglist, nents,	\
+				     pgsz);			\
+	     __rdma_block_iter_next(biter);)
+
+static inline void __rdma_umem_block_iter_start(struct ib_block_iter *biter,
+						struct ib_umem *umem,
+						unsigned long pgsz)
+{
+	__rdma_block_iter_start(biter, umem->sg_head.sgl, umem->nmap, pgsz);
+}
+
+/**
+ * rdma_umem_for_each_dma_block - iterate over contiguous DMA blocks of the umem
+ * @umem: umem to iterate over
+ * @biter: block iterator variable
+ * @pgsz: Page size to split the list into
+ *
+ * pgsz must be <= PAGE_SIZE or computed by ib_umem_find_best_pgsz(). The
+ * returned DMA blocks will be aligned to pgsz and span the range:
+ * ALIGN_DOWN(umem->address, pgsz) to ALIGN(umem->address + umem->length, pgsz)
+ *
+ * Performs exactly ib_umem_num_dma_blocks() iterations.
+ */
+#define rdma_umem_for_each_dma_block(umem, biter, pgsz)                        \
+	for (__rdma_umem_block_iter_start(biter, umem, pgsz);                  \
+	     __rdma_block_iter_next(biter);)
+
+#endif /* _RDMA_ITER_H_ */
-- 
2.53.0


  reply	other threads:[~2026-06-16  3:17 UTC|newest]

Thread overview: 4+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-06-15 14:21 FAILED: patch "[PATCH] RDMA/umem: Fix truncation for block sizes >= 4G" failed to apply to 5.10-stable tree gregkh
2026-06-16  3:17 ` [PATCH 5.10.y 1/3] RDMA/umem: fix kernel-doc warnings Sasha Levin
2026-06-16  3:17   ` Sasha Levin [this message]
2026-06-16  3:17   ` [PATCH 5.10.y 3/3] RDMA/umem: Fix truncation for block sizes >= 4G Sasha Levin

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=20260616031737.2781524-2-sashal@kernel.org \
    --to=sashal@kernel.org \
    --cc=leonro@nvidia.com \
    --cc=stable@vger.kernel.org \
    /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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.