RDMA/verbs: Add a DMA iterator to return aligned contiguous memory blocks

driver inclusion
category: bugfix
bugzilla: NA
CVE: NA

This helper iterates over a DMA-mapped SGL and returns contiguous memory
blocks aligned to a HW supported page size.
Suggested-by: NJason Gunthorpe <jgg@ziepe.ca>
Signed-off-by: NShiraz Saleem <shiraz.saleem@intel.com>
Signed-off-by: NJason Gunthorpe <jgg@mellanox.com>
Signed-off-by: NXi Wang <wangxi11@huawei.com>
Signed-off-by: NShunfeng Yang <yangshunfeng2@huawei.com>
Reviewed-by: Nchunzhi hu <huchunzhi@huawei.com>
Signed-off-by: NYang Yingliang <yangyingliang@huawei.com>

drivers/infiniband/core/verbs.c

@@ -2628,3 +2628,37 @@ void ib_drain_qp(struct ib_qp *qp)
 		ib_drain_rq(qp);
 }
 EXPORT_SYMBOL(ib_drain_qp);
+
+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;
+
+	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);
+	biter->__sg_advance += BIT_ULL(biter->__pg_bit) - block_offset;
+
+	if (biter->__sg_advance >= sg_dma_len(biter->__sg)) {
+		biter->__sg_advance = 0;
+		biter->__sg = sg_next(biter->__sg);
+		biter->__sg_nents--;
+	}
+
+	return true;
+}
+EXPORT_SYMBOL(__rdma_block_iter_next);

include/rdma/ib_verbs.h

@@ -2629,6 +2629,21 @@ struct ib_client {
 	struct list_head list;
 };
 
+/*
+ * 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);
 void ib_dealloc_device(struct ib_device *device);
 
@@ -2642,6 +2657,38 @@ void ib_unregister_device(struct ib_device *device);
 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);)
+
 void *ib_get_client_data(struct ib_device *device, struct ib_client *client);
 void  ib_set_client_data(struct ib_device *device, struct ib_client *client,
 			 void *data);