--- /dev/null
+From stable+bounces-263456-greg=kroah.com@vger.kernel.org Tue Jun 16 02:43:46 2026
+From: Sasha Levin <sashal@kernel.org>
+Date: Mon, 15 Jun 2026 17:13:35 -0400
+Subject: RDMA: Move DMA block iterator logic into dedicated files
+To: stable@vger.kernel.org
+Cc: Leon Romanovsky <leonro@nvidia.com>, Sasha Levin <sashal@kernel.org>
+Message-ID: <20260615211336.2459359-2-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>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ drivers/infiniband/core/Makefile | 2
+ drivers/infiniband/core/iter.c | 43 +++++++++++++
+ drivers/infiniband/core/verbs.c | 38 -----------
+ 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/erdma/erdma_verbs.c | 2
+ drivers/infiniband/hw/hns/hns_roce_alloc.c | 2
+ drivers/infiniband/hw/ionic/ionic_ibdev.h | 2
+ drivers/infiniband/hw/irdma/main.h | 2
+ drivers/infiniband/hw/mana/mana_ib.h | 2
+ drivers/infiniband/hw/mlx4/mr.c | 1
+ drivers/infiniband/hw/mlx5/mem.c | 1
+ drivers/infiniband/hw/mlx5/umr.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 | 32 ---------
+ include/rdma/ib_verbs.h | 48 --------------
+ include/rdma/iter.h | 88 +++++++++++++++++++++++++++
+ 21 files changed, 147 insertions(+), 131 deletions(-)
+ create mode 100644 drivers/infiniband/core/iter.c
+ create mode 100644 include/rdma/iter.h
+
+--- a/drivers/infiniband/core/Makefile
++++ b/drivers/infiniband/core/Makefile
+@@ -12,7 +12,7 @@ ib_core-y := packer.o ud_header.o verb
+ 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
+--- /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);
+--- a/drivers/infiniband/core/verbs.c
++++ b/drivers/infiniband/core/verbs.c
+@@ -3154,44 +3154,6 @@ int rdma_init_netdev(struct ib_device *d
+ }
+ 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 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);
+-
+ /**
+ * rdma_alloc_hw_stats_struct - Helper function to allocate dynamic struct
+ * for the drivers.
+--- 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"
+--- 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"
+
+--- a/drivers/infiniband/hw/efa/efa_verbs.c
++++ b/drivers/infiniband/hw/efa/efa_verbs.c
+@@ -9,9 +9,9 @@
+ #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>
+ #define UVERBS_MODULE_NAME efa_ib
+ #include <rdma/uverbs_named_ioctl.h>
+--- a/drivers/infiniband/hw/erdma/erdma_verbs.c
++++ b/drivers/infiniband/hw/erdma/erdma_verbs.c
+@@ -12,7 +12,7 @@
+ #include <linux/vmalloc.h>
+ #include <net/addrconf.h>
+ #include <rdma/erdma-abi.h>
+-#include <rdma/ib_umem.h>
++#include <rdma/iter.h>
+ #include <rdma/uverbs_ioctl.h>
+
+ #include "erdma.h"
+--- a/drivers/infiniband/hw/hns/hns_roce_alloc.c
++++ b/drivers/infiniband/hw/hns/hns_roce_alloc.c
+@@ -32,7 +32,7 @@
+ */
+
+ #include <linux/vmalloc.h>
+-#include <rdma/ib_umem.h>
++#include <rdma/iter.h>
+ #include "hns_roce_device.h"
+
+ void hns_roce_buf_free(struct hns_roce_dev *hr_dev, struct hns_roce_buf *buf)
+--- a/drivers/infiniband/hw/ionic/ionic_ibdev.h
++++ b/drivers/infiniband/hw/ionic/ionic_ibdev.h
+@@ -4,9 +4,9 @@
+ #ifndef _IONIC_IBDEV_H_
+ #define _IONIC_IBDEV_H_
+
+-#include <rdma/ib_umem.h>
+ #include <rdma/ib_verbs.h>
+ #include <rdma/ib_pack.h>
++#include <rdma/iter.h>
+ #include <rdma/uverbs_ioctl.h>
+
+ #include <rdma/ionic-abi.h>
+--- a/drivers/infiniband/hw/irdma/main.h
++++ b/drivers/infiniband/hw/irdma/main.h
+@@ -37,8 +37,8 @@
+ #include <rdma/rdma_cm.h>
+ #include <rdma/iw_cm.h>
+ #include <rdma/ib_user_verbs.h>
+-#include <rdma/ib_umem.h>
+ #include <rdma/ib_cache.h>
++#include <rdma/iter.h>
+ #include <rdma/uverbs_ioctl.h>
+ #include "osdep.h"
+ #include "defs.h"
+--- a/drivers/infiniband/hw/mana/mana_ib.h
++++ b/drivers/infiniband/hw/mana/mana_ib.h
+@@ -8,7 +8,7 @@
+
+ #include <rdma/ib_verbs.h>
+ #include <rdma/ib_mad.h>
+-#include <rdma/ib_umem.h>
++#include <rdma/iter.h>
+ #include <rdma/mana-abi.h>
+ #include <rdma/uverbs_ioctl.h>
+ #include <linux/dmapool.h>
+--- 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"
+
+--- a/drivers/infiniband/hw/mlx5/mem.c
++++ b/drivers/infiniband/hw/mlx5/mem.c
+@@ -31,6 +31,7 @@
+ */
+
+ #include <rdma/ib_umem_odp.h>
++#include <rdma/iter.h>
+ #include "mlx5_ib.h"
+
+ /*
+--- a/drivers/infiniband/hw/mlx5/umr.c
++++ b/drivers/infiniband/hw/mlx5/umr.c
+@@ -2,6 +2,7 @@
+ /* Copyright (c) 2022, NVIDIA CORPORATION & AFFILIATES. */
+
+ #include <rdma/ib_umem_odp.h>
++#include <rdma/iter.h>
+ #include "mlx5_ib.h"
+ #include "umr.h"
+ #include "wr.h"
+--- 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>
+--- a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c
++++ b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c
+@@ -45,9 +45,9 @@
+ #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"
+--- 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>
+--- 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"
+--- a/include/rdma/ib_umem.h
++++ b/include/rdma/ib_umem.h
+@@ -76,38 +76,6 @@ static inline size_t ib_umem_num_pages(s
+ {
+ 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->sgt_append.sgt.sgl,
+- umem->sgt_append.sgt.nents, pgsz);
+- biter->__sg_advance = ib_umem_offset(umem) & ~(pgsz - 1);
+- biter->__sg_numblocks = ib_umem_num_dma_blocks(umem, pgsz);
+-}
+-
+-static inline bool __rdma_umem_block_iter_next(struct ib_block_iter *biter)
+-{
+- return __rdma_block_iter_next(biter) && biter->__sg_numblocks--;
+-}
+-
+-/**
+- * 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_umem_block_iter_next(biter);)
+-
+ #ifdef CONFIG_INFINIBAND_USER_MEM
+
+ struct ib_umem *ib_umem_get(struct ib_device *device, unsigned long addr,
+--- a/include/rdma/ib_verbs.h
++++ b/include/rdma/ib_verbs.h
+@@ -2959,22 +2959,6 @@ 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 */
+- size_t __sg_numblocks; /* ib_umem_num_dma_blocks() */
+- 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, struct net *net);
+ #define ib_alloc_device(drv_struct, member) \
+ container_of(_ib_alloc_device(sizeof(struct drv_struct) + \
+@@ -3003,38 +2987,6 @@ void ib_unregister_device_queued(struct
+ 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
+--- /dev/null
++++ b/include/rdma/iter.h
+@@ -0,0 +1,88 @@
++/* 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 */
++ size_t __sg_numblocks; /* ib_umem_num_dma_blocks() */
++ 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->sgt_append.sgt.sgl,
++ umem->sgt_append.sgt.nents, pgsz);
++ biter->__sg_advance = ib_umem_offset(umem) & ~(pgsz - 1);
++ biter->__sg_numblocks = ib_umem_num_dma_blocks(umem, pgsz);
++}
++
++static inline bool __rdma_umem_block_iter_next(struct ib_block_iter *biter)
++{
++ return __rdma_block_iter_next(biter) && biter->__sg_numblocks--;
++}
++
++/**
++ * rdma_umem_for_each_dma_block - iterate over contiguous DMA blocks of the umem
++ * @umem: umem to iterate over
++ * @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_umem_block_iter_next(biter);)
++
++#endif /* _RDMA_ITER_H_ */
projects / thirdparty / kernel / stable-queue.git / commitdiff
