Merge tag 'dma-mapping-5.20-2022-08-06' of git://git.infradead.org/users/hch/dma-mapping

Pull dma-mapping updates from Christoph Hellwig:

 - convert arm32 to the common dma-direct code (Arnd Bergmann, Robin
   Murphy, Christoph Hellwig)

 - restructure the PCIe peer to peer mapping support (Logan Gunthorpe)

 - allow the IOMMU code to communicate an optional DMA mapping length
   and use that in scsi and libata (John Garry)

 - split the global swiotlb lock (Tianyu Lan)

 - various fixes and cleanup (Chao Gao, Dan Carpenter, Dongli Zhang,
   Lukas Bulwahn, Robin Murphy)

* tag 'dma-mapping-5.20-2022-08-06' of git://git.infradead.org/users/hch/dma-mapping: (45 commits)
  swiotlb: fix passing local variable to debugfs_create_ulong()
  dma-mapping: reformat comment to suppress htmldoc warning
  PCI/P2PDMA: Remove pci_p2pdma_[un]map_sg()
  RDMA/rw: drop pci_p2pdma_[un]map_sg()
  RDMA/core: introduce ib_dma_pci_p2p_dma_supported()
  nvme-pci: convert to using dma_map_sgtable()
  nvme-pci: check DMA ops when indicating support for PCI P2PDMA
  iommu/dma: support PCI P2PDMA pages in dma-iommu map_sg
  iommu: Explicitly skip bus address marked segments in __iommu_map_sg()
  dma-mapping: add flags to dma_map_ops to indicate PCI P2PDMA support
  dma-direct: support PCI P2PDMA pages in dma-direct map_sg
  dma-mapping: allow EREMOTEIO return code for P2PDMA transfers
  PCI/P2PDMA: Introduce helpers for dma_map_sg implementations
  PCI/P2PDMA: Attempt to set map_type if it has not been set
  lib/scatterlist: add flag for indicating P2PDMA segments in an SGL
  swiotlb: clean up some coding style and minor issues
  dma-mapping: update comment after dmabounce removal
  scsi: sd: Add a comment about limiting max_sectors to shost optimal limit
  ata: libata-scsi: cap ata_device->max_sectors according to shost->max_sectors
  scsi: scsi_transport_sas: cap shost opt_sectors according to DMA optimal limit
  ...

17 files changed, 245 insertions, 165 deletions

diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c
index 9b999c0e8c37..29e2f55c6faa 100644
--- a/drivers/ata/libata-scsi.c
+++ b/drivers/ata/libata-scsi.c
@@ -1060,6 +1060,7 @@ int ata_scsi_dev_config(struct scsi_device *sdev, struct ata_device *dev)
 		dev->flags |= ATA_DFLAG_NO_UNLOAD;
 
 	/* configure max sectors */
+	dev->max_sectors = min(dev->max_sectors, sdev->host->max_sectors);
 	blk_queue_max_hw_sectors(q, dev->max_sectors);
 
 	if (dev->class == ATA_DEV_ATAPI) {
diff --git a/drivers/infiniband/core/rw.c b/drivers/infiniband/core/rw.c
index 4d98f931a13d..8367974b7998 100644
--- a/drivers/infiniband/core/rw.c
+++ b/drivers/infiniband/core/rw.c
@@ -274,33 +274,6 @@ static int rdma_rw_init_single_wr(struct rdma_rw_ctx *ctx, struct ib_qp *qp,
 	return 1;
 }
 
-static void rdma_rw_unmap_sg(struct ib_device *dev, struct scatterlist *sg,
-			     u32 sg_cnt, enum dma_data_direction dir)
-{
-	if (is_pci_p2pdma_page(sg_page(sg)))
-		pci_p2pdma_unmap_sg(dev->dma_device, sg, sg_cnt, dir);
-	else
-		ib_dma_unmap_sg(dev, sg, sg_cnt, dir);
-}
-
-static int rdma_rw_map_sgtable(struct ib_device *dev, struct sg_table *sgt,
-			       enum dma_data_direction dir)
-{
-	int nents;
-
-	if (is_pci_p2pdma_page(sg_page(sgt->sgl))) {
-		if (WARN_ON_ONCE(ib_uses_virt_dma(dev)))
-			return 0;
-		nents = pci_p2pdma_map_sg(dev->dma_device, sgt->sgl,
-					  sgt->orig_nents, dir);
-		if (!nents)
-			return -EIO;
-		sgt->nents = nents;
-		return 0;
-	}
-	return ib_dma_map_sgtable_attrs(dev, sgt, dir, 0);
-}
-
 /**
  * rdma_rw_ctx_init - initialize a RDMA READ/WRITE context
  * @ctx:	context to initialize
@@ -327,7 +300,7 @@ int rdma_rw_ctx_init(struct rdma_rw_ctx *ctx, struct ib_qp *qp, u32 port_num,
 	};
 	int ret;
 
-	ret = rdma_rw_map_sgtable(dev, &sgt, dir);
+	ret = ib_dma_map_sgtable_attrs(dev, &sgt, dir, 0);
 	if (ret)
 		return ret;
 	sg_cnt = sgt.nents;
@@ -366,7 +339,7 @@ int rdma_rw_ctx_init(struct rdma_rw_ctx *ctx, struct ib_qp *qp, u32 port_num,
 	return ret;
 
 out_unmap_sg:
-	rdma_rw_unmap_sg(dev, sgt.sgl, sgt.orig_nents, dir);
+	ib_dma_unmap_sgtable_attrs(dev, &sgt, dir, 0);
 	return ret;
 }
 EXPORT_SYMBOL(rdma_rw_ctx_init);
@@ -414,12 +387,12 @@ int rdma_rw_ctx_signature_init(struct rdma_rw_ctx *ctx, struct ib_qp *qp,
 		return -EINVAL;
 	}
 
-	ret = rdma_rw_map_sgtable(dev, &sgt, dir);
+	ret = ib_dma_map_sgtable_attrs(dev, &sgt, dir, 0);
 	if (ret)
 		return ret;
 
 	if (prot_sg_cnt) {
-		ret = rdma_rw_map_sgtable(dev, &prot_sgt, dir);
+		ret = ib_dma_map_sgtable_attrs(dev, &prot_sgt, dir, 0);
 		if (ret)
 			goto out_unmap_sg;
 	}
@@ -486,9 +459,9 @@ out_free_ctx:
 	kfree(ctx->reg);
 out_unmap_prot_sg:
 	if (prot_sgt.nents)
-		rdma_rw_unmap_sg(dev, prot_sgt.sgl, prot_sgt.orig_nents, dir);
+		ib_dma_unmap_sgtable_attrs(dev, &prot_sgt, dir, 0);
 out_unmap_sg:
-	rdma_rw_unmap_sg(dev, sgt.sgl, sgt.orig_nents, dir);
+	ib_dma_unmap_sgtable_attrs(dev, &sgt, dir, 0);
 	return ret;
 }
 EXPORT_SYMBOL(rdma_rw_ctx_signature_init);
@@ -621,7 +594,7 @@ void rdma_rw_ctx_destroy(struct rdma_rw_ctx *ctx, struct ib_qp *qp,
 		break;
 	}
 
-	rdma_rw_unmap_sg(qp->pd->device, sg, sg_cnt, dir);
+	ib_dma_unmap_sg(qp->pd->device, sg, sg_cnt, dir);
 }
 EXPORT_SYMBOL(rdma_rw_ctx_destroy);
 
@@ -649,8 +622,8 @@ void rdma_rw_ctx_destroy_signature(struct rdma_rw_ctx *ctx, struct ib_qp *qp,
 	kfree(ctx->reg);
 
 	if (prot_sg_cnt)
-		rdma_rw_unmap_sg(qp->pd->device, prot_sg, prot_sg_cnt, dir);
-	rdma_rw_unmap_sg(qp->pd->device, sg, sg_cnt, dir);
+		ib_dma_unmap_sg(qp->pd->device, prot_sg, prot_sg_cnt, dir);
+	ib_dma_unmap_sg(qp->pd->device, sg, sg_cnt, dir);
 }
 EXPORT_SYMBOL(rdma_rw_ctx_destroy_signature);
 
diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index 458fb6738223..376c4e3ae0e6 100644
--- a/drivers/iommu/dma-iommu.c
+++ b/drivers/iommu/dma-iommu.c
@@ -21,6 +21,7 @@
 #include <linux/iova.h>
 #include <linux/irq.h>
 #include <linux/list_sort.h>
+#include <linux/memremap.h>
 #include <linux/mm.h>
 #include <linux/mutex.h>
 #include <linux/pci.h>
@@ -1062,15 +1063,30 @@ static int __finalise_sg(struct device *dev, struct scatterlist *sg, int nents,
 
 	for_each_sg(sg, s, nents, i) {
 		/* Restore this segment's original unaligned fields first */
+		dma_addr_t s_dma_addr = sg_dma_address(s);
 		unsigned int s_iova_off = sg_dma_address(s);
 		unsigned int s_length = sg_dma_len(s);
 		unsigned int s_iova_len = s->length;
 
-		s->offset += s_iova_off;
-		s->length = s_length;
 		sg_dma_address(s) = DMA_MAPPING_ERROR;
 		sg_dma_len(s) = 0;
 
+		if (sg_is_dma_bus_address(s)) {
+			if (i > 0)
+				cur = sg_next(cur);
+
+			sg_dma_unmark_bus_address(s);
+			sg_dma_address(cur) = s_dma_addr;
+			sg_dma_len(cur) = s_length;
+			sg_dma_mark_bus_address(cur);
+			count++;
+			cur_len = 0;
+			continue;
+		}
+
+		s->offset += s_iova_off;
+		s->length = s_length;
+
 		/*
 		 * Now fill in the real DMA data. If...
 		 * - there is a valid output segment to append to
@@ -1111,10 +1127,14 @@ static void __invalidate_sg(struct scatterlist *sg, int nents)
 	int i;
 
 	for_each_sg(sg, s, nents, i) {
-		if (sg_dma_address(s) != DMA_MAPPING_ERROR)
-			s->offset += sg_dma_address(s);
-		if (sg_dma_len(s))
-			s->length = sg_dma_len(s);
+		if (sg_is_dma_bus_address(s)) {
+			sg_dma_unmark_bus_address(s);
+		} else {
+			if (sg_dma_address(s) != DMA_MAPPING_ERROR)
+				s->offset += sg_dma_address(s);
+			if (sg_dma_len(s))
+				s->length = sg_dma_len(s);
+		}
 		sg_dma_address(s) = DMA_MAPPING_ERROR;
 		sg_dma_len(s) = 0;
 	}
@@ -1167,6 +1187,8 @@ static int iommu_dma_map_sg(struct device *dev, struct scatterlist *sg,
 	struct iova_domain *iovad = &cookie->iovad;
 	struct scatterlist *s, *prev = NULL;
 	int prot = dma_info_to_prot(dir, dev_is_dma_coherent(dev), attrs);
+	struct pci_p2pdma_map_state p2pdma_state = {};
+	enum pci_p2pdma_map_type map;
 	dma_addr_t iova;
 	size_t iova_len = 0;
 	unsigned long mask = dma_get_seg_boundary(dev);
@@ -1196,6 +1218,30 @@ static int iommu_dma_map_sg(struct device *dev, struct scatterlist *sg,
 		size_t s_length = s->length;
 		size_t pad_len = (mask - iova_len + 1) & mask;
 
+		if (is_pci_p2pdma_page(sg_page(s))) {
+			map = pci_p2pdma_map_segment(&p2pdma_state, dev, s);
+			switch (map) {
+			case PCI_P2PDMA_MAP_BUS_ADDR:
+				/*
+				 * iommu_map_sg() will skip this segment as
+				 * it is marked as a bus address,
+				 * __finalise_sg() will copy the dma address
+				 * into the output segment.
+				 */
+				continue;
+			case PCI_P2PDMA_MAP_THRU_HOST_BRIDGE:
+				/*
+				 * Mapping through host bridge should be
+				 * mapped with regular IOVAs, thus we
+				 * do nothing here and continue below.
+				 */
+				break;
+			default:
+				ret = -EREMOTEIO;
+				goto out_restore_sg;
+			}
+		}
+
 		sg_dma_address(s) = s_iova_off;
 		sg_dma_len(s) = s_length;
 		s->offset -= s_iova_off;
@@ -1224,6 +1270,9 @@ static int iommu_dma_map_sg(struct device *dev, struct scatterlist *sg,
 		prev = s;
 	}
 
+	if (!iova_len)
+		return __finalise_sg(dev, sg, nents, 0);
+
 	iova = iommu_dma_alloc_iova(domain, iova_len, dma_get_mask(dev), dev);
 	if (!iova) {
 		ret = -ENOMEM;
@@ -1245,7 +1294,7 @@ out_free_iova:
 out_restore_sg:
 	__invalidate_sg(sg, nents);
 out:
-	if (ret != -ENOMEM)
+	if (ret != -ENOMEM && ret != -EREMOTEIO)
 		return -EINVAL;
 	return ret;
 }
@@ -1253,7 +1302,7 @@ out:
 static void iommu_dma_unmap_sg(struct device *dev, struct scatterlist *sg,
 		int nents, enum dma_data_direction dir, unsigned long attrs)
 {
-	dma_addr_t start, end;
+	dma_addr_t end = 0, start;
 	struct scatterlist *tmp;
 	int i;
 
@@ -1267,16 +1316,37 @@ static void iommu_dma_unmap_sg(struct device *dev, struct scatterlist *sg,
 
 	/*
 	 * The scatterlist segments are mapped into a single
-	 * contiguous IOVA allocation, so this is incredibly easy.
+	 * contiguous IOVA allocation, the start and end points
+	 * just have to be determined.
 	 */
-	start = sg_dma_address(sg);
-	for_each_sg(sg_next(sg), tmp, nents - 1, i) {
+	for_each_sg(sg, tmp, nents, i) {
+		if (sg_is_dma_bus_address(tmp)) {
+			sg_dma_unmark_bus_address(tmp);
+			continue;
+		}
+
 		if (sg_dma_len(tmp) == 0)
 			break;
-		sg = tmp;
+
+		start = sg_dma_address(tmp);
+		break;
 	}
-	end = sg_dma_address(sg) + sg_dma_len(sg);
-	__iommu_dma_unmap(dev, start, end - start);
+
+	nents -= i;
+	for_each_sg(tmp, tmp, nents, i) {
+		if (sg_is_dma_bus_address(tmp)) {
+			sg_dma_unmark_bus_address(tmp);
+			continue;
+		}
+
+		if (sg_dma_len(tmp) == 0)
+			break;
+
+		end = sg_dma_address(tmp) + sg_dma_len(tmp);
+	}
+
+	if (end)
+		__iommu_dma_unmap(dev, start, end - start);
 }
 
 static dma_addr_t iommu_dma_map_resource(struct device *dev, phys_addr_t phys,
@@ -1468,7 +1538,13 @@ static unsigned long iommu_dma_get_merge_boundary(struct device *dev)
 	return (1UL << __ffs(domain->pgsize_bitmap)) - 1;
 }
 
+static size_t iommu_dma_opt_mapping_size(void)
+{
+	return iova_rcache_range();
+}
+
 static const struct dma_map_ops iommu_dma_ops = {
+	.flags			= DMA_F_PCI_P2PDMA_SUPPORTED,
 	.alloc			= iommu_dma_alloc,
 	.free			= iommu_dma_free,
 	.alloc_pages		= dma_common_alloc_pages,
@@ -1488,6 +1564,7 @@ static const struct dma_map_ops iommu_dma_ops = {
 	.map_resource		= iommu_dma_map_resource,
 	.unmap_resource		= iommu_dma_unmap_resource,
 	.get_merge_boundary	= iommu_dma_get_merge_boundary,
+	.opt_mapping_size	= iommu_dma_opt_mapping_size,
 };
 
 /*
diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index f53f8b2d27a5..780fb7071577 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -2460,6 +2460,9 @@ static ssize_t __iommu_map_sg(struct iommu_domain *domain, unsigned long iova,
 			len = 0;
 		}
 
+		if (sg_is_dma_bus_address(sg))
+			goto next;
+
 		if (len) {
 			len += sg->length;
 		} else {
@@ -2467,6 +2470,7 @@ static ssize_t __iommu_map_sg(struct iommu_domain *domain, unsigned long iova,
 			start = s_phys;
 		}
 
+next:
 		if (++i < nents)
 			sg = sg_next(sg);
 	}
diff --git a/drivers/iommu/iova.c b/drivers/iommu/iova.c
index e44f565c5319..47d1983dfa2a 100644
--- a/drivers/iommu/iova.c
+++ b/drivers/iommu/iova.c
@@ -26,6 +26,11 @@ static unsigned long iova_rcache_get(struct iova_domain *iovad,
 static void free_cpu_cached_iovas(unsigned int cpu, struct iova_domain *iovad);
 static void free_iova_rcaches(struct iova_domain *iovad);
 
+unsigned long iova_rcache_range(void)
+{
+	return PAGE_SIZE << (IOVA_RANGE_CACHE_MAX_SIZE - 1);
+}
+
 static int iova_cpuhp_dead(unsigned int cpu, struct hlist_node *node)
 {
 	struct iova_domain *iovad;
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 2429b11eb9a8..af367b22871b 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -4198,7 +4198,8 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, struct nvme_ns_info *info)
 		blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES, ns->queue);
 
 	blk_queue_flag_set(QUEUE_FLAG_NONROT, ns->queue);
-	if (ctrl->ops->flags & NVME_F_PCI_P2PDMA)
+	if (ctrl->ops->supports_pci_p2pdma &&
+	    ctrl->ops->supports_pci_p2pdma(ctrl))
 		blk_queue_flag_set(QUEUE_FLAG_PCI_P2PDMA, ns->queue);
 
 	ns->ctrl = ctrl;
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index bdc0ff7ed9ab..1bdf714dcd9e 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -504,7 +504,6 @@ struct nvme_ctrl_ops {
 	unsigned int flags;
 #define NVME_F_FABRICS			(1 << 0)
 #define NVME_F_METADATA_SUPPORTED	(1 << 1)
-#define NVME_F_PCI_P2PDMA		(1 << 2)
 	int (*reg_read32)(struct nvme_ctrl *ctrl, u32 off, u32 *val);
 	int (*reg_write32)(struct nvme_ctrl *ctrl, u32 off, u32 val);
 	int (*reg_read64)(struct nvme_ctrl *ctrl, u32 off, u64 *val);
@@ -514,6 +513,7 @@ struct nvme_ctrl_ops {
 	void (*stop_ctrl)(struct nvme_ctrl *ctrl);
 	int (*get_address)(struct nvme_ctrl *ctrl, char *buf, int size);
 	void (*print_device_info)(struct nvme_ctrl *ctrl);
+	bool (*supports_pci_p2pdma)(struct nvme_ctrl *ctrl);
 };
 
 /*
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 71a4f26ba476..de1b4463142d 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -230,11 +230,10 @@ struct nvme_iod {
 	bool use_sgl;
 	int aborted;
 	int npages;		/* In the PRP list. 0 means small pool in use */
-	int nents;		/* Used in scatterlist */
 	dma_addr_t first_dma;
 	unsigned int dma_len;	/* length of single DMA segment mapping */
 	dma_addr_t meta_dma;
-	struct scatterlist *sg;
+	struct sg_table sgt;
 };
 
 static inline unsigned int nvme_dbbuf_size(struct nvme_dev *dev)
@@ -524,7 +523,7 @@ static void nvme_commit_rqs(struct blk_mq_hw_ctx *hctx)
 static void **nvme_pci_iod_list(struct request *req)
 {
 	struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
-	return (void **)(iod->sg + blk_rq_nr_phys_segments(req));
+	return (void **)(iod->sgt.sgl + blk_rq_nr_phys_segments(req));
 }
 
 static inline bool nvme_pci_use_sgls(struct nvme_dev *dev, struct request *req)
@@ -576,17 +575,6 @@ static void nvme_free_sgls(struct nvme_dev *dev, struct request *req)
 	}
 }
 
-static void nvme_unmap_sg(struct nvme_dev *dev, struct request *req)
-{
-	struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
-
-	if (is_pci_p2pdma_page(sg_page(iod->sg)))
-		pci_p2pdma_unmap_sg(dev->dev, iod->sg, iod->nents,
-				    rq_dma_dir(req));
-	else
-		dma_unmap_sg(dev->dev, iod->sg, iod->nents, rq_dma_dir(req));
-}
-
 static void nvme_unmap_data(struct nvme_dev *dev, struct request *req)
 {
 	struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
@@ -597,9 +585,10 @@ static void nvme_unmap_data(struct nvme_dev *dev, struct request *req)
 		return;
 	}
 
-	WARN_ON_ONCE(!iod->nents);
+	WARN_ON_ONCE(!iod->sgt.nents);
+
+	dma_unmap_sgtable(dev->dev, &iod->sgt, rq_dma_dir(req), 0);
 
-	nvme_unmap_sg(dev, req);
 	if (iod->npages == 0)
 		dma_pool_free(dev->prp_small_pool, nvme_pci_iod_list(req)[0],
 			      iod->first_dma);
@@ -607,7 +596,7 @@ static void nvme_unmap_data(struct nvme_dev *dev, struct request *req)
 		nvme_free_sgls(dev, req);
 	else
 		nvme_free_prps(dev, req);
-	mempool_free(iod->sg, dev->iod_mempool);
+	mempool_free(iod->sgt.sgl, dev->iod_mempool);
 }
 
 static void nvme_print_sgl(struct scatterlist *sgl, int nents)
@@ -630,7 +619,7 @@ static blk_status_t nvme_pci_setup_prps(struct nvme_dev *dev,
 	struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
 	struct dma_pool *pool;
 	int length = blk_rq_payload_bytes(req);
-	struct scatterlist *sg = iod->sg;
+	struct scatterlist *sg = iod->sgt.sgl;
 	int dma_len = sg_dma_len(sg);
 	u64 dma_addr = sg_dma_address(sg);
 	int offset = dma_addr & (NVME_CTRL_PAGE_SIZE - 1);
@@ -702,16 +691,16 @@ static blk_status_t nvme_pci_setup_prps(struct nvme_dev *dev,
 		dma_len = sg_dma_len(sg);
 	}
 done:
-	cmnd->dptr.prp1 = cpu_to_le64(sg_dma_address(iod->sg));
+	cmnd->dptr.prp1 = cpu_to_le64(sg_dma_address(iod->sgt.sgl));
 	cmnd->dptr.prp2 = cpu_to_le64(iod->first_dma);
 	return BLK_STS_OK;
 free_prps:
 	nvme_free_prps(dev, req);
 	return BLK_STS_RESOURCE;
 bad_sgl:
-	WARN(DO_ONCE(nvme_print_sgl, iod->sg, iod->nents),
+	WARN(DO_ONCE(nvme_print_sgl, iod->sgt.sgl, iod->sgt.nents),
 			"Invalid SGL for payload:%d nents:%d\n",
-			blk_rq_payload_bytes(req), iod->nents);
+			blk_rq_payload_bytes(req), iod->sgt.nents);
 	return BLK_STS_IOERR;
 }
 
@@ -737,12 +726,13 @@ static void nvme_pci_sgl_set_seg(struct nvme_sgl_desc *sge,
 }
 
 static blk_status_t nvme_pci_setup_sgls(struct nvme_dev *dev,
-		struct request *req, struct nvme_rw_command *cmd, int entries)
+		struct request *req, struct nvme_rw_command *cmd)
 {
 	struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
 	struct dma_pool *pool;
 	struct nvme_sgl_desc *sg_list;
-	struct scatterlist *sg = iod->sg;
+	struct scatterlist *sg = iod->sgt.sgl;
+	unsigned int entries = iod->sgt.nents;
 	dma_addr_t sgl_dma;
 	int i = 0;
 
@@ -840,7 +830,7 @@ static blk_status_t nvme_map_data(struct nvme_dev *dev, struct request *req,
 {
 	struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
 	blk_status_t ret = BLK_STS_RESOURCE;
-	int nr_mapped;
+	int rc;
 
 	if (blk_rq_nr_phys_segments(req) == 1) {
 		struct bio_vec bv = req_bvec(req);
@@ -858,26 +848,25 @@ static blk_status_t nvme_map_data(struct nvme_dev *dev, struct request *req,
 	}
 
 	iod->dma_len = 0;
-	iod->sg = mempool_alloc(dev->iod_mempool, GFP_ATOMIC);
-	if (!iod->sg)
+	iod->sgt.sgl = mempool_alloc(dev->iod_mempool, GFP_ATOMIC);
+	if (!iod->sgt.sgl)
 		return BLK_STS_RESOURCE;
-	sg_init_table(iod->sg, blk_rq_nr_phys_segments(req));
-	iod->nents = blk_rq_map_sg(req->q, req, iod->sg);
-	if (!iod->nents)
+	sg_init_table(iod->sgt.sgl, blk_rq_nr_phys_segments(req));
+	iod->sgt.orig_nents = blk_rq_map_sg(req->q, req, iod->sgt.sgl);
+	if (!iod->sgt.orig_nents)
 		goto out_free_sg;
 
-	if (is_pci_p2pdma_page(sg_page(iod->sg)))
-		nr_mapped = pci_p2pdma_map_sg_attrs(dev->dev, iod->sg,
-				iod->nents, rq_dma_dir(req), DMA_ATTR_NO_WARN);
-	else
-		nr_mapped = dma_map_sg_attrs(dev->dev, iod->sg, iod->nents,
-					     rq_dma_dir(req), DMA_ATTR_NO_WARN);
-	if (!nr_mapped)
+	rc = dma_map_sgtable(dev->dev, &iod->sgt, rq_dma_dir(req),
+			     DMA_ATTR_NO_WARN);
+	if (rc) {
+		if (rc == -EREMOTEIO)
+			ret = BLK_STS_TARGET;
 		goto out_free_sg;
+	}
 
 	iod->use_sgl = nvme_pci_use_sgls(dev, req);
 	if (iod->use_sgl)
-		ret = nvme_pci_setup_sgls(dev, req, &cmnd->rw, nr_mapped);
+		ret = nvme_pci_setup_sgls(dev, req, &cmnd->rw);
 	else
 		ret = nvme_pci_setup_prps(dev, req, &cmnd->rw);
 	if (ret != BLK_STS_OK)
@@ -885,9 +874,9 @@ static blk_status_t nvme_map_data(struct nvme_dev *dev, struct request *req,
 	return BLK_STS_OK;
 
 out_unmap_sg:
-	nvme_unmap_sg(dev, req);
+	dma_unmap_sgtable(dev->dev, &iod->sgt, rq_dma_dir(req), 0);
 out_free_sg:
-	mempool_free(iod->sg, dev->iod_mempool);
+	mempool_free(iod->sgt.sgl, dev->iod_mempool);
 	return ret;
 }
 
@@ -911,7 +900,7 @@ static blk_status_t nvme_prep_rq(struct nvme_dev *dev, struct request *req)
 
 	iod->aborted = 0;
 	iod->npages = -1;
-	iod->nents = 0;
+	iod->sgt.nents = 0;
 
 	ret = nvme_setup_cmd(req->q->queuedata, req);
 	if (ret)
@@ -2992,7 +2981,6 @@ static int nvme_pci_get_address(struct nvme_ctrl *ctrl, char *buf, int size)
 	return snprintf(buf, size, "%s\n", dev_name(&pdev->dev));
 }
 
-
 static void nvme_pci_print_device_info(struct nvme_ctrl *ctrl)
 {
 	struct pci_dev *pdev = to_pci_dev(to_nvme_dev(ctrl)->dev);
@@ -3007,11 +2995,17 @@ static void nvme_pci_print_device_info(struct nvme_ctrl *ctrl)
 		subsys->firmware_rev);
 }
 
+static bool nvme_pci_supports_pci_p2pdma(struct nvme_ctrl *ctrl)
+{
+	struct nvme_dev *dev = to_nvme_dev(ctrl);
+
+	return dma_pci_p2pdma_supported(dev->dev);
+}
+
 static const struct nvme_ctrl_ops nvme_pci_ctrl_ops = {
 	.name			= "pcie",
 	.module			= THIS_MODULE,
-	.flags			= NVME_F_METADATA_SUPPORTED |
-				  NVME_F_PCI_P2PDMA,
+	.flags			= NVME_F_METADATA_SUPPORTED,
 	.reg_read32		= nvme_pci_reg_read32,
 	.reg_write32		= nvme_pci_reg_write32,
 	.reg_read64		= nvme_pci_reg_read64,
@@ -3019,6 +3013,7 @@ static const struct nvme_ctrl_ops nvme_pci_ctrl_ops = {
 	.submit_async_event	= nvme_pci_submit_async_event,
 	.get_address		= nvme_pci_get_address,
 	.print_device_info	= nvme_pci_print_device_info,
+	.supports_pci_p2pdma	= nvme_pci_supports_pci_p2pdma,
 };
 
 static int nvme_dev_map(struct nvme_dev *dev)
diff --git a/drivers/nvme/target/rdma.c b/drivers/nvme/target/rdma.c
index 09fdcac87d17..4597bca43a6d 100644
--- a/drivers/nvme/target/rdma.c
+++ b/drivers/nvme/target/rdma.c
@@ -415,7 +415,7 @@ static int nvmet_rdma_alloc_rsp(struct nvmet_rdma_device *ndev,
 	if (ib_dma_mapping_error(ndev->device, r->send_sge.addr))
 		goto out_free_rsp;
 
-	if (!ib_uses_virt_dma(ndev->device))
+	if (ib_dma_pci_p2p_dma_supported(ndev->device))
 		r->req.p2p_client = &ndev->device->dev;
 	r->send_sge.length = sizeof(*r->req.cqe);
 	r->send_sge.lkey = ndev->pd->local_dma_lkey;
diff --git a/drivers/pci/Kconfig b/drivers/pci/Kconfig
index 133c73207782..5cc7cba1941f 100644
--- a/drivers/pci/Kconfig
+++ b/drivers/pci/Kconfig
@@ -164,6 +164,11 @@ config PCI_PASID
 config PCI_P2PDMA
 	bool "PCI peer-to-peer transfer support"
 	depends on ZONE_DEVICE
+	#
+	# The need for the scatterlist DMA bus address flag means PCI P2PDMA
+	# requires 64bit
+	#
+	depends on 64BIT
 	select GENERIC_ALLOCATOR
 	help
 	  Enableѕ drivers to do PCI peer-to-peer transactions to and from
diff --git a/drivers/pci/p2pdma.c b/drivers/pci/p2pdma.c
index 462b429ad243..4496a7c5c478 100644
--- a/drivers/pci/p2pdma.c
+++ b/drivers/pci/p2pdma.c
@@ -10,6 +10,7 @@
 
 #define pr_fmt(fmt) "pci-p2pdma: " fmt
 #include <linux/ctype.h>
+#include <linux/dma-map-ops.h>
 #include <linux/pci-p2pdma.h>
 #include <linux/module.h>
 #include <linux/slab.h>
@@ -20,13 +21,6 @@
 #include <linux/seq_buf.h>
 #include <linux/xarray.h>
 
-enum pci_p2pdma_map_type {
-	PCI_P2PDMA_MAP_UNKNOWN = 0,
-	PCI_P2PDMA_MAP_NOT_SUPPORTED,
-	PCI_P2PDMA_MAP_BUS_ADDR,
-	PCI_P2PDMA_MAP_THRU_HOST_BRIDGE,
-};
-
 struct pci_p2pdma {
 	struct gen_pool *pool;
 	bool p2pmem_published;
@@ -854,6 +848,7 @@ static enum pci_p2pdma_map_type pci_p2pdma_map_type(struct dev_pagemap *pgmap,
 	struct pci_dev *provider = to_p2p_pgmap(pgmap)->provider;
 	struct pci_dev *client;
 	struct pci_p2pdma *p2pdma;
+	int dist;
 
 	if (!provider->p2pdma)
 		return PCI_P2PDMA_MAP_NOT_SUPPORTED;
@@ -870,74 +865,48 @@ static enum pci_p2pdma_map_type pci_p2pdma_map_type(struct dev_pagemap *pgmap,
 		type = xa_to_value(xa_load(&p2pdma->map_types,
 					   map_types_idx(client)));
 	rcu_read_unlock();
-	return type;
-}
 
-static int __pci_p2pdma_map_sg(struct pci_p2pdma_pagemap *p2p_pgmap,
-		struct device *dev, struct scatterlist *sg, int nents)
-{
-	struct scatterlist *s;
-	int i;
-
-	for_each_sg(sg, s, nents, i) {
-		s->dma_address = sg_phys(s) + p2p_pgmap->bus_offset;
-		sg_dma_len(s) = s->length;
-	}
+	if (type == PCI_P2PDMA_MAP_UNKNOWN)
+		return calc_map_type_and_dist(provider, client, &dist, true);
 
-	return nents;
+	return type;
 }
 
 /**
- * pci_p2pdma_map_sg_attrs - map a PCI peer-to-peer scatterlist for DMA
- * @dev: device doing the DMA request
- * @sg: scatter list to map
- * @nents: elements in the scatterlist
- * @dir: DMA direction
- * @attrs: DMA attributes passed to dma_map_sg() (if called)
+ * pci_p2pdma_map_segment - map an sg segment determining the mapping type
+ * @state: State structure that should be declared outside of the for_each_sg()
+ *	loop and initialized to zero.
+ * @dev: DMA device that's doing the mapping operation
+ * @sg: scatterlist segment to map
  *
- * Scatterlists mapped with this function should be unmapped using
- * pci_p2pdma_unmap_sg_attrs().
+ * This is a helper to be used by non-IOMMU dma_map_sg() implementations where
+ * the sg segment is the same for the page_link and the dma_address.
  *
- * Returns the number of SG entries mapped or 0 on error.
+ * Attempt to map a single segment in an SGL with the PCI bus address.
+ * The segment must point to a PCI P2PDMA page and thus must be
+ * wrapped in a is_pci_p2pdma_page(sg_page(sg)) check.
+ *
+ * Returns the type of mapping used and maps the page if the type is
+ * PCI_P2PDMA_MAP_BUS_ADDR.
  */
-int pci_p2pdma_map_sg_attrs(struct device *dev, struct scatterlist *sg,
-		int nents, enum dma_data_direction dir, unsigned long attrs)
+enum pci_p2pdma_map_type
+pci_p2pdma_map_segment(struct pci_p2pdma_map_state *state, struct device *dev,
+		       struct scatterlist *sg)
 {
-	struct pci_p2pdma_pagemap *p2p_pgmap =
-		to_p2p_pgmap(sg_page(sg)->pgmap);
-
-	switch (pci_p2pdma_map_type(sg_page(sg)->pgmap, dev)) {
-	case PCI_P2PDMA_MAP_THRU_HOST_BRIDGE:
-		return dma_map_sg_attrs(dev, sg, nents, dir, attrs);
-	case PCI_P2PDMA_MAP_BUS_ADDR:
-		return __pci_p2pdma_map_sg(p2p_pgmap, dev, sg, nents);
-	default:
-		WARN_ON_ONCE(1);
-		return 0;
+	if (state->pgmap != sg_page(sg)->pgmap) {
+		state->pgmap = sg_page(sg)->pgmap;
+		state->map = pci_p2pdma_map_type(state->pgmap, dev);
+		state->bus_off = to_p2p_pgmap(state->pgmap)->bus_offset;
 	}
-}
-EXPORT_SYMBOL_GPL(pci_p2pdma_map_sg_attrs);
 
-/**
- * pci_p2pdma_unmap_sg_attrs - unmap a PCI peer-to-peer scatterlist that was
- *	mapped with pci_p2pdma_map_sg()
- * @dev: device doing the DMA request
- * @sg: scatter list to map
- * @nents: number of elements returned by pci_p2pdma_map_sg()
- * @dir: DMA direction
- * @attrs: DMA attributes passed to dma_unmap_sg() (if called)
- */
-void pci_p2pdma_unmap_sg_attrs(struct device *dev, struct scatterlist *sg,
-		int nents, enum dma_data_direction dir, unsigned long attrs)
-{
-	enum pci_p2pdma_map_type map_type;
-
-	map_type = pci_p2pdma_map_type(sg_page(sg)->pgmap, dev);
+	if (state->map == PCI_P2PDMA_MAP_BUS_ADDR) {
+		sg->dma_address = sg_phys(sg) + state->bus_off;
+		sg_dma_len(sg) = sg->length;
+		sg_dma_mark_bus_address(sg);
+	}
 
-	if (map_type == PCI_P2PDMA_MAP_THRU_HOST_BRIDGE)
-		dma_unmap_sg_attrs(dev, sg, nents, dir, attrs);
+	return state->map;
 }
-EXPORT_SYMBOL_GPL(pci_p2pdma_unmap_sg_attrs);
 
 /**
  * pci_p2pdma_enable_store - parse a configfs/sysfs attribute store
diff --git a/drivers/scsi/hosts.c b/drivers/scsi/hosts.c
index bbcb901f6926..26bf3b153595 100644
--- a/drivers/scsi/hosts.c
+++ b/drivers/scsi/hosts.c
@@ -236,6 +236,11 @@ int scsi_add_host_with_dma(struct Scsi_Host *shost, struct device *dev,
 
 	shost->dma_dev = dma_dev;
 
+	if (dma_dev->dma_mask) {
+		shost->max_sectors = min_t(unsigned int, shost->max_sectors,
+				dma_max_mapping_size(dma_dev) >> SECTOR_SHIFT);
+	}
+
 	error = scsi_mq_setup_tags(shost);
 	if (error)
 		goto fail;
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index b59a71aedcd7..4dbd29ab1dcc 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -1876,10 +1876,6 @@ void __scsi_init_queue(struct Scsi_Host *shost, struct request_queue *q)
 		blk_queue_max_integrity_segments(q, shost->sg_prot_tablesize);
 	}
 
-	if (dev->dma_mask) {
-		shost->max_sectors = min_t(unsigned int, shost->max_sectors,
-				dma_max_mapping_size(dev) >> SECTOR_SHIFT);
-	}
 	blk_queue_max_hw_sectors(q, shost->max_sectors);
 	blk_queue_segment_boundary(q, shost->dma_boundary);
 	dma_set_seg_boundary(dev, shost->dma_boundary);
diff --git a/drivers/scsi/scsi_transport_sas.c b/drivers/scsi/scsi_transport_sas.c
index 12bff64dade6..2f88c61216ee 100644
--- a/drivers/scsi/scsi_transport_sas.c
+++ b/drivers/scsi/scsi_transport_sas.c
@@ -225,6 +225,7 @@ static int sas_host_setup(struct transport_container *tc, struct device *dev,
 {
 	struct Scsi_Host *shost = dev_to_shost(dev);
 	struct sas_host_attrs *sas_host = to_sas_host_attrs(shost);
+	struct device *dma_dev = shost->dma_dev;
 
 	INIT_LIST_HEAD(&sas_host->rphy_list);
 	mutex_init(&sas_host->lock);
@@ -236,6 +237,11 @@ static int sas_host_setup(struct transport_container *tc, struct device *dev,
 		dev_printk(KERN_ERR, dev, "fail to a bsg device %d\n",
 			   shost->host_no);
 
+	if (dma_dev->dma_mask) {
+		shost->opt_sectors = min_t(unsigned int, shost->max_sectors,
+				dma_opt_mapping_size(dma_dev) >> SECTOR_SHIFT);
+	}
+
 	return 0;
 }
 
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index 6f7a39b96750..8f79fa6318fe 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -3297,6 +3297,13 @@ static int sd_revalidate_disk(struct gendisk *disk)
 				      (sector_t)BLK_DEF_MAX_SECTORS);
 	}
 
+	/*
+	 * Limit default to SCSI host optimal sector limit if set. There may be
+	 * an impact on performance for when the size of a request exceeds this
+	 * host limit.
+	 */
+	rw_max = min_not_zero(rw_max, sdp->host->opt_sectors);
+
 	/* Do not exceed controller limit */
 	rw_max = min(rw_max, queue_max_hw_sectors(q));
 
diff --git a/drivers/usb/core/hcd.c b/drivers/usb/core/hcd.c
index a6a87c5d1b05..94b305bbd621 100644
--- a/drivers/usb/core/hcd.c
+++ b/drivers/usb/core/hcd.c
@@ -1251,7 +1251,8 @@ void usb_hcd_unlink_urb_from_ep(struct usb_hcd *hcd, struct urb *urb)
 EXPORT_SYMBOL_GPL(usb_hcd_unlink_urb_from_ep);
 
 /*
- * Some usb host controllers can only perform dma using a small SRAM area.
+ * Some usb host controllers can only perform dma using a small SRAM area,
+ * or have restrictions on addressable DRAM.
  * The usb core itself is however optimized for host controllers that can dma
  * using regular system memory - like pci devices doing bus mastering.
  *
@@ -3127,8 +3128,18 @@ int usb_hcd_setup_local_mem(struct usb_hcd *hcd, phys_addr_t phys_addr,
 	if (IS_ERR(hcd->localmem_pool))
 		return PTR_ERR(hcd->localmem_pool);
 
-	local_mem = devm_memremap(hcd->self.sysdev, phys_addr,
-				  size, MEMREMAP_WC);
+	/*
+	 * if a physical SRAM address was passed, map it, otherwise
+	 * allocate system memory as a buffer.
+	 */
+	if (phys_addr)
+		local_mem = devm_memremap(hcd->self.sysdev, phys_addr,
+					  size, MEMREMAP_WC);
+	else
+		local_mem = dmam_alloc_attrs(hcd->self.sysdev, size, &dma,
+					     GFP_KERNEL,
+					     DMA_ATTR_WRITE_COMBINE);
+
 	if (IS_ERR(local_mem))
 		return PTR_ERR(local_mem);
 
diff --git a/drivers/usb/host/ohci-sa1111.c b/drivers/usb/host/ohci-sa1111.c
index feca826d3f6a..75c2b28b3379 100644
--- a/drivers/usb/host/ohci-sa1111.c
+++ b/drivers/usb/host/ohci-sa1111.c
@@ -203,6 +203,31 @@ static int ohci_hcd_sa1111_probe(struct sa1111_dev *dev)
 		goto err1;
 	}
 
+	/*
+	 * According to the "Intel StrongARM SA-1111 Microprocessor Companion
+	 * Chip Specification Update" (June 2000), erratum #7, there is a
+	 * significant bug in the SA1111 SDRAM shared memory controller.  If
+	 * an access to a region of memory above 1MB relative to the bank base,
+	 * it is important that address bit 10 _NOT_ be asserted. Depending
+	 * on the configuration of the RAM, bit 10 may correspond to one
+	 * of several different (processor-relative) address bits.
+	 *
+	 * Section 4.6 of the "Intel StrongARM SA-1111 Development Module
+	 * User's Guide" mentions that jumpers R51 and R52 control the
+	 * target of SA-1111 DMA (either SDRAM bank 0 on Assabet, or
+	 * SDRAM bank 1 on Neponset). The default configuration selects
+	 * Assabet, so any address in bank 1 is necessarily invalid.
+	 *
+	 * As a workaround, use a bounce buffer in addressable memory
+	 * as local_mem, relying on ZONE_DMA to provide an area that
+	 * fits within the above constraints.
+	 *
+	 * SZ_64K is an estimate for what size this might need.
+	 */
+	ret = usb_hcd_setup_local_mem(hcd, 0, 0, SZ_64K);
+	if (ret)
+		goto err1;
+
 	if (!request_mem_region(hcd->rsrc_start, hcd->rsrc_len, hcd_name)) {
 		dev_dbg(&dev->dev, "request_mem_region failed\n");
 		ret = -EBUSY;