Merge branch 'pci/peer-to-peer'

  - Add PCI support for peer-to-peer DMA (Logan Gunthorpe)

  - Add sysfs group for PCI peer-to-peer memory statistics (Logan
    Gunthorpe)

  - Add PCI peer-to-peer DMA scatterlist mapping interface (Logan
    Gunthorpe)

  - Add PCI configfs/sysfs helpers for use by peer-to-peer users (Logan
    Gunthorpe)

  - Add PCI peer-to-peer DMA driver writer's documentation (Logan
    Gunthorpe)

  - Add block layer flag to indicate driver support for PCI peer-to-peer
    DMA (Logan Gunthorpe)

  - Map Infiniband scatterlists for peer-to-peer DMA if they contain P2P
    memory (Logan Gunthorpe)

  - Register nvme-pci CMB buffer as PCI peer-to-peer memory (Logan
    Gunthorpe)

  - Add nvme-pci support for PCI peer-to-peer memory in requests (Logan
    Gunthorpe)

  - Use PCI peer-to-peer memory in nvme (Stephen Bates, Steve Wise,
    Christoph Hellwig, Logan Gunthorpe)

* pci/peer-to-peer:
  nvmet: Optionally use PCI P2P memory
  nvmet: Introduce helper functions to allocate and free request SGLs
  nvme-pci: Add support for P2P memory in requests
  nvme-pci: Use PCI p2pmem subsystem to manage the CMB
  IB/core: Ensure we map P2P memory correctly in rdma_rw_ctx_[init|destroy]()
  block: Add PCI P2P flag for request queue
  PCI/P2PDMA: Add P2P DMA driver writer's documentation
  docs-rst: Add a new directory for PCI documentation
  PCI/P2PDMA: Introduce configfs/sysfs enable attribute helpers
  PCI/P2PDMA: Add PCI p2pmem DMA mappings to adjust the bus offset
  PCI/P2PDMA: Add sysfs group to display p2pmem stats
  PCI/P2PDMA: Support peer-to-peer memory

12 files changed, 1156 insertions, 49 deletions

diff --git a/drivers/infiniband/core/rw.c b/drivers/infiniband/core/rw.c
index 683e6d11a564..d22c4a2ebac6 100644
--- a/drivers/infiniband/core/rw.c
+++ b/drivers/infiniband/core/rw.c
@@ -12,6 +12,7 @@
  */
 #include <linux/moduleparam.h>
 #include <linux/slab.h>
+#include <linux/pci-p2pdma.h>
 #include <rdma/mr_pool.h>
 #include <rdma/rw.h>
 
@@ -280,7 +281,11 @@ int rdma_rw_ctx_init(struct rdma_rw_ctx *ctx, struct ib_qp *qp, u8 port_num,
 	struct ib_device *dev = qp->pd->device;
 	int ret;
 
-	ret = ib_dma_map_sg(dev, sg, sg_cnt, dir);
+	if (is_pci_p2pdma_page(sg_page(sg)))
+		ret = pci_p2pdma_map_sg(dev->dma_device, sg, sg_cnt, dir);
+	else
+		ret = ib_dma_map_sg(dev, sg, sg_cnt, dir);
+
 	if (!ret)
 		return -ENOMEM;
 	sg_cnt = ret;
@@ -602,7 +607,9 @@ void rdma_rw_ctx_destroy(struct rdma_rw_ctx *ctx, struct ib_qp *qp, u8 port_num,
 		break;
 	}
 
-	ib_dma_unmap_sg(qp->pd->device, sg, sg_cnt, dir);
+	/* P2PDMA contexts do not need to be unmapped */
+	if (!is_pci_p2pdma_page(sg_page(sg)))
+		ib_dma_unmap_sg(qp->pd->device, sg, sg_cnt, dir);
 }
 EXPORT_SYMBOL(rdma_rw_ctx_destroy);
 
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index dd8ec1dd9219..6033ce2fd3e9 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -3051,7 +3051,11 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid)
 	ns->queue = blk_mq_init_queue(ctrl->tagset);
 	if (IS_ERR(ns->queue))
 		goto out_free_ns;
+
 	blk_queue_flag_set(QUEUE_FLAG_NONROT, ns->queue);
+	if (ctrl->ops->flags & NVME_F_PCI_P2PDMA)
+		blk_queue_flag_set(QUEUE_FLAG_PCI_P2PDMA, ns->queue);
+
 	ns->queue->queuedata = ns;
 	ns->ctrl = ctrl;
 
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index bb4a2003c097..4030743c90aa 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -343,6 +343,7 @@ 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);
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 8991e79b2b87..7e09e45b0b28 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -30,6 +30,7 @@
 #include <linux/types.h>
 #include <linux/io-64-nonatomic-lo-hi.h>
 #include <linux/sed-opal.h>
+#include <linux/pci-p2pdma.h>
 
 #include "nvme.h"
 
@@ -99,9 +100,8 @@ struct nvme_dev {
 	struct work_struct remove_work;
 	struct mutex shutdown_lock;
 	bool subsystem;
-	void __iomem *cmb;
-	pci_bus_addr_t cmb_bus_addr;
 	u64 cmb_size;
+	bool cmb_use_sqes;
 	u32 cmbsz;
 	u32 cmbloc;
 	struct nvme_ctrl ctrl;
@@ -158,7 +158,7 @@ struct nvme_queue {
 	struct nvme_dev *dev;
 	spinlock_t sq_lock;
 	struct nvme_command *sq_cmds;
-	struct nvme_command __iomem *sq_cmds_io;
+	bool sq_cmds_is_io;
 	spinlock_t cq_lock ____cacheline_aligned_in_smp;
 	volatile struct nvme_completion *cqes;
 	struct blk_mq_tags **tags;
@@ -447,11 +447,8 @@ static int nvme_pci_map_queues(struct blk_mq_tag_set *set)
 static void nvme_submit_cmd(struct nvme_queue *nvmeq, struct nvme_command *cmd)
 {
 	spin_lock(&nvmeq->sq_lock);
-	if (nvmeq->sq_cmds_io)
-		memcpy_toio(&nvmeq->sq_cmds_io[nvmeq->sq_tail], cmd,
-				sizeof(*cmd));
-	else
-		memcpy(&nvmeq->sq_cmds[nvmeq->sq_tail], cmd, sizeof(*cmd));
+
+	memcpy(&nvmeq->sq_cmds[nvmeq->sq_tail], cmd, sizeof(*cmd));
 
 	if (++nvmeq->sq_tail == nvmeq->q_depth)
 		nvmeq->sq_tail = 0;
@@ -748,8 +745,13 @@ static blk_status_t nvme_map_data(struct nvme_dev *dev, struct request *req,
 		goto out;
 
 	ret = BLK_STS_RESOURCE;
-	nr_mapped = dma_map_sg_attrs(dev->dev, iod->sg, iod->nents, dma_dir,
-			DMA_ATTR_NO_WARN);
+
+	if (is_pci_p2pdma_page(sg_page(iod->sg)))
+		nr_mapped = pci_p2pdma_map_sg(dev->dev, iod->sg, iod->nents,
+					  dma_dir);
+	else
+		nr_mapped = dma_map_sg_attrs(dev->dev, iod->sg, iod->nents,
+					     dma_dir,  DMA_ATTR_NO_WARN);
 	if (!nr_mapped)
 		goto out;
 
@@ -791,7 +793,10 @@ static void nvme_unmap_data(struct nvme_dev *dev, struct request *req)
 			DMA_TO_DEVICE : DMA_FROM_DEVICE;
 
 	if (iod->nents) {
-		dma_unmap_sg(dev->dev, iod->sg, iod->nents, dma_dir);
+		/* P2PDMA requests do not need to be unmapped */
+		if (!is_pci_p2pdma_page(sg_page(iod->sg)))
+			dma_unmap_sg(dev->dev, iod->sg, iod->nents, dma_dir);
+
 		if (blk_integrity_rq(req))
 			dma_unmap_sg(dev->dev, &iod->meta_sg, 1, dma_dir);
 	}
@@ -1232,9 +1237,18 @@ static void nvme_free_queue(struct nvme_queue *nvmeq)
 {
 	dma_free_coherent(nvmeq->q_dmadev, CQ_SIZE(nvmeq->q_depth),
 				(void *)nvmeq->cqes, nvmeq->cq_dma_addr);
-	if (nvmeq->sq_cmds)
-		dma_free_coherent(nvmeq->q_dmadev, SQ_SIZE(nvmeq->q_depth),
-					nvmeq->sq_cmds, nvmeq->sq_dma_addr);
+
+	if (nvmeq->sq_cmds) {
+		if (nvmeq->sq_cmds_is_io)
+			pci_free_p2pmem(to_pci_dev(nvmeq->q_dmadev),
+					nvmeq->sq_cmds,
+					SQ_SIZE(nvmeq->q_depth));
+		else
+			dma_free_coherent(nvmeq->q_dmadev,
+					  SQ_SIZE(nvmeq->q_depth),
+					  nvmeq->sq_cmds,
+					  nvmeq->sq_dma_addr);
+	}
 }
 
 static void nvme_free_queues(struct nvme_dev *dev, int lowest)
@@ -1323,12 +1337,21 @@ static int nvme_cmb_qdepth(struct nvme_dev *dev, int nr_io_queues,
 static int nvme_alloc_sq_cmds(struct nvme_dev *dev, struct nvme_queue *nvmeq,
 				int qid, int depth)
 {
-	/* CMB SQEs will be mapped before creation */
-	if (qid && dev->cmb && use_cmb_sqes && (dev->cmbsz & NVME_CMBSZ_SQS))
-		return 0;
+	struct pci_dev *pdev = to_pci_dev(dev->dev);
+
+	if (qid && dev->cmb_use_sqes && (dev->cmbsz & NVME_CMBSZ_SQS)) {
+		nvmeq->sq_cmds = pci_alloc_p2pmem(pdev, SQ_SIZE(depth));
+		nvmeq->sq_dma_addr = pci_p2pmem_virt_to_bus(pdev,
+						nvmeq->sq_cmds);
+		nvmeq->sq_cmds_is_io = true;
+	}
+
+	if (!nvmeq->sq_cmds) {
+		nvmeq->sq_cmds = dma_alloc_coherent(dev->dev, SQ_SIZE(depth),
+					&nvmeq->sq_dma_addr, GFP_KERNEL);
+		nvmeq->sq_cmds_is_io = false;
+	}
 
-	nvmeq->sq_cmds = dma_alloc_coherent(dev->dev, SQ_SIZE(depth),
-					    &nvmeq->sq_dma_addr, GFP_KERNEL);
 	if (!nvmeq->sq_cmds)
 		return -ENOMEM;
 	return 0;
@@ -1405,13 +1428,6 @@ static int nvme_create_queue(struct nvme_queue *nvmeq, int qid)
 	int result;
 	s16 vector;
 
-	if (dev->cmb && use_cmb_sqes && (dev->cmbsz & NVME_CMBSZ_SQS)) {
-		unsigned offset = (qid - 1) * roundup(SQ_SIZE(nvmeq->q_depth),
-						      dev->ctrl.page_size);
-		nvmeq->sq_dma_addr = dev->cmb_bus_addr + offset;
-		nvmeq->sq_cmds_io = dev->cmb + offset;
-	}
-
 	/*
 	 * A queue's vector matches the queue identifier unless the controller
 	 * has only one vector available.
@@ -1652,9 +1668,6 @@ static void nvme_map_cmb(struct nvme_dev *dev)
 		return;
 	dev->cmbloc = readl(dev->bar + NVME_REG_CMBLOC);
 
-	if (!use_cmb_sqes)
-		return;
-
 	size = nvme_cmb_size_unit(dev) * nvme_cmb_size(dev);
 	offset = nvme_cmb_size_unit(dev) * NVME_CMB_OFST(dev->cmbloc);
 	bar = NVME_CMB_BIR(dev->cmbloc);
@@ -1671,11 +1684,18 @@ static void nvme_map_cmb(struct nvme_dev *dev)
 	if (size > bar_size - offset)
 		size = bar_size - offset;
 
-	dev->cmb = ioremap_wc(pci_resource_start(pdev, bar) + offset, size);
-	if (!dev->cmb)
+	if (pci_p2pdma_add_resource(pdev, bar, size, offset)) {
+		dev_warn(dev->ctrl.device,
+			 "failed to register the CMB\n");
 		return;
-	dev->cmb_bus_addr = pci_bus_address(pdev, bar) + offset;
+	}
+
 	dev->cmb_size = size;
+	dev->cmb_use_sqes = use_cmb_sqes && (dev->cmbsz & NVME_CMBSZ_SQS);
+
+	if ((dev->cmbsz & (NVME_CMBSZ_WDS | NVME_CMBSZ_RDS)) ==
+			(NVME_CMBSZ_WDS | NVME_CMBSZ_RDS))
+		pci_p2pmem_publish(pdev, true);
 
 	if (sysfs_add_file_to_group(&dev->ctrl.device->kobj,
 				    &dev_attr_cmb.attr, NULL))
@@ -1685,12 +1705,10 @@ static void nvme_map_cmb(struct nvme_dev *dev)
 
 static inline void nvme_release_cmb(struct nvme_dev *dev)
 {
-	if (dev->cmb) {
-		iounmap(dev->cmb);
-		dev->cmb = NULL;
+	if (dev->cmb_size) {
 		sysfs_remove_file_from_group(&dev->ctrl.device->kobj,
 					     &dev_attr_cmb.attr, NULL);
-		dev->cmbsz = 0;
+		dev->cmb_size = 0;
 	}
 }
 
@@ -1889,13 +1907,13 @@ static int nvme_setup_io_queues(struct nvme_dev *dev)
 	if (nr_io_queues == 0)
 		return 0;
 
-	if (dev->cmb && (dev->cmbsz & NVME_CMBSZ_SQS)) {
+	if (dev->cmb_use_sqes) {
 		result = nvme_cmb_qdepth(dev, nr_io_queues,
 				sizeof(struct nvme_command));
 		if (result > 0)
 			dev->q_depth = result;
 		else
-			nvme_release_cmb(dev);
+			dev->cmb_use_sqes = false;
 	}
 
 	do {
@@ -2390,7 +2408,8 @@ static int nvme_pci_get_address(struct nvme_ctrl *ctrl, char *buf, int size)
 static const struct nvme_ctrl_ops nvme_pci_ctrl_ops = {
 	.name			= "pcie",
 	.module			= THIS_MODULE,
-	.flags			= NVME_F_METADATA_SUPPORTED,
+	.flags			= NVME_F_METADATA_SUPPORTED |
+				  NVME_F_PCI_P2PDMA,
 	.reg_read32		= nvme_pci_reg_read32,
 	.reg_write32		= nvme_pci_reg_write32,
 	.reg_read64		= nvme_pci_reg_read64,
diff --git a/drivers/nvme/target/configfs.c b/drivers/nvme/target/configfs.c
index b37a8e3e3f80..d895579b6c5d 100644
--- a/drivers/nvme/target/configfs.c
+++ b/drivers/nvme/target/configfs.c
@@ -17,6 +17,8 @@
 #include <linux/slab.h>
 #include <linux/stat.h>
 #include <linux/ctype.h>
+#include <linux/pci.h>
+#include <linux/pci-p2pdma.h>
 
 #include "nvmet.h"
 
@@ -340,6 +342,48 @@ out_unlock:
 
 CONFIGFS_ATTR(nvmet_ns_, device_path);
 
+#ifdef CONFIG_PCI_P2PDMA
+static ssize_t nvmet_ns_p2pmem_show(struct config_item *item, char *page)
+{
+	struct nvmet_ns *ns = to_nvmet_ns(item);
+
+	return pci_p2pdma_enable_show(page, ns->p2p_dev, ns->use_p2pmem);
+}
+
+static ssize_t nvmet_ns_p2pmem_store(struct config_item *item,
+		const char *page, size_t count)
+{
+	struct nvmet_ns *ns = to_nvmet_ns(item);
+	struct pci_dev *p2p_dev = NULL;
+	bool use_p2pmem;
+	int ret = count;
+	int error;
+
+	mutex_lock(&ns->subsys->lock);
+	if (ns->enabled) {
+		ret = -EBUSY;
+		goto out_unlock;
+	}
+
+	error = pci_p2pdma_enable_store(page, &p2p_dev, &use_p2pmem);
+	if (error) {
+		ret = error;
+		goto out_unlock;
+	}
+
+	ns->use_p2pmem = use_p2pmem;
+	pci_dev_put(ns->p2p_dev);
+	ns->p2p_dev = p2p_dev;
+
+out_unlock:
+	mutex_unlock(&ns->subsys->lock);
+
+	return ret;
+}
+
+CONFIGFS_ATTR(nvmet_ns_, p2pmem);
+#endif /* CONFIG_PCI_P2PDMA */
+
 static ssize_t nvmet_ns_device_uuid_show(struct config_item *item, char *page)
 {
 	return sprintf(page, "%pUb\n", &to_nvmet_ns(item)->uuid);
@@ -509,6 +553,9 @@ static struct configfs_attribute *nvmet_ns_attrs[] = {
 	&nvmet_ns_attr_ana_grpid,
 	&nvmet_ns_attr_enable,
 	&nvmet_ns_attr_buffered_io,
+#ifdef CONFIG_PCI_P2PDMA
+	&nvmet_ns_attr_p2pmem,
+#endif
 	NULL,
 };
 
diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c
index b5ec96abd048..9b4d84cfc224 100644
--- a/drivers/nvme/target/core.c
+++ b/drivers/nvme/target/core.c
@@ -15,6 +15,7 @@
 #include <linux/module.h>
 #include <linux/random.h>
 #include <linux/rculist.h>
+#include <linux/pci-p2pdma.h>
 
 #include "nvmet.h"
 
@@ -365,9 +366,93 @@ static void nvmet_ns_dev_disable(struct nvmet_ns *ns)
 	nvmet_file_ns_disable(ns);
 }
 
+static int nvmet_p2pmem_ns_enable(struct nvmet_ns *ns)
+{
+	int ret;
+	struct pci_dev *p2p_dev;
+
+	if (!ns->use_p2pmem)
+		return 0;
+
+	if (!ns->bdev) {
+		pr_err("peer-to-peer DMA is not supported by non-block device namespaces\n");
+		return -EINVAL;
+	}
+
+	if (!blk_queue_pci_p2pdma(ns->bdev->bd_queue)) {
+		pr_err("peer-to-peer DMA is not supported by the driver of %s\n",
+		       ns->device_path);
+		return -EINVAL;
+	}
+
+	if (ns->p2p_dev) {
+		ret = pci_p2pdma_distance(ns->p2p_dev, nvmet_ns_dev(ns), true);
+		if (ret < 0)
+			return -EINVAL;
+	} else {
+		/*
+		 * Right now we just check that there is p2pmem available so
+		 * we can report an error to the user right away if there
+		 * is not. We'll find the actual device to use once we
+		 * setup the controller when the port's device is available.
+		 */
+
+		p2p_dev = pci_p2pmem_find(nvmet_ns_dev(ns));
+		if (!p2p_dev) {
+			pr_err("no peer-to-peer memory is available for %s\n",
+			       ns->device_path);
+			return -EINVAL;
+		}
+
+		pci_dev_put(p2p_dev);
+	}
+
+	return 0;
+}
+
+/*
+ * Note: ctrl->subsys->lock should be held when calling this function
+ */
+static void nvmet_p2pmem_ns_add_p2p(struct nvmet_ctrl *ctrl,
+				    struct nvmet_ns *ns)
+{
+	struct device *clients[2];
+	struct pci_dev *p2p_dev;
+	int ret;
+
+	if (!ctrl->p2p_client)
+		return;
+
+	if (ns->p2p_dev) {
+		ret = pci_p2pdma_distance(ns->p2p_dev, ctrl->p2p_client, true);
+		if (ret < 0)
+			return;
+
+		p2p_dev = pci_dev_get(ns->p2p_dev);
+	} else {
+		clients[0] = ctrl->p2p_client;
+		clients[1] = nvmet_ns_dev(ns);
+
+		p2p_dev = pci_p2pmem_find_many(clients, ARRAY_SIZE(clients));
+		if (!p2p_dev) {
+			pr_err("no peer-to-peer memory is available that's supported by %s and %s\n",
+			       dev_name(ctrl->p2p_client), ns->device_path);
+			return;
+		}
+	}
+
+	ret = radix_tree_insert(&ctrl->p2p_ns_map, ns->nsid, p2p_dev);
+	if (ret < 0)
+		pci_dev_put(p2p_dev);
+
+	pr_info("using p2pmem on %s for nsid %d\n", pci_name(p2p_dev),
+		ns->nsid);
+}
+
 int nvmet_ns_enable(struct nvmet_ns *ns)
 {
 	struct nvmet_subsys *subsys = ns->subsys;
+	struct nvmet_ctrl *ctrl;
 	int ret;
 
 	mutex_lock(&subsys->lock);
@@ -384,6 +469,13 @@ int nvmet_ns_enable(struct nvmet_ns *ns)
 	if (ret)
 		goto out_unlock;
 
+	ret = nvmet_p2pmem_ns_enable(ns);
+	if (ret)
+		goto out_unlock;
+
+	list_for_each_entry(ctrl, &subsys->ctrls, subsys_entry)
+		nvmet_p2pmem_ns_add_p2p(ctrl, ns);
+
 	ret = percpu_ref_init(&ns->ref, nvmet_destroy_namespace,
 				0, GFP_KERNEL);
 	if (ret)
@@ -418,6 +510,9 @@ out_unlock:
 	mutex_unlock(&subsys->lock);
 	return ret;
 out_dev_put:
+	list_for_each_entry(ctrl, &subsys->ctrls, subsys_entry)
+		pci_dev_put(radix_tree_delete(&ctrl->p2p_ns_map, ns->nsid));
+
 	nvmet_ns_dev_disable(ns);
 	goto out_unlock;
 }
@@ -425,6 +520,7 @@ out_dev_put:
 void nvmet_ns_disable(struct nvmet_ns *ns)
 {
 	struct nvmet_subsys *subsys = ns->subsys;
+	struct nvmet_ctrl *ctrl;
 
 	mutex_lock(&subsys->lock);
 	if (!ns->enabled)
@@ -434,6 +530,10 @@ void nvmet_ns_disable(struct nvmet_ns *ns)
 	list_del_rcu(&ns->dev_link);
 	if (ns->nsid == subsys->max_nsid)
 		subsys->max_nsid = nvmet_max_nsid(subsys);
+
+	list_for_each_entry(ctrl, &subsys->ctrls, subsys_entry)
+		pci_dev_put(radix_tree_delete(&ctrl->p2p_ns_map, ns->nsid));
+
 	mutex_unlock(&subsys->lock);
 
 	/*
@@ -450,6 +550,7 @@ void nvmet_ns_disable(struct nvmet_ns *ns)
 	percpu_ref_exit(&ns->ref);
 
 	mutex_lock(&subsys->lock);
+
 	subsys->nr_namespaces--;
 	nvmet_ns_changed(subsys, ns->nsid);
 	nvmet_ns_dev_disable(ns);
@@ -725,6 +826,51 @@ void nvmet_req_execute(struct nvmet_req *req)
 }
 EXPORT_SYMBOL_GPL(nvmet_req_execute);
 
+int nvmet_req_alloc_sgl(struct nvmet_req *req)
+{
+	struct pci_dev *p2p_dev = NULL;
+
+	if (IS_ENABLED(CONFIG_PCI_P2PDMA)) {
+		if (req->sq->ctrl && req->ns)
+			p2p_dev = radix_tree_lookup(&req->sq->ctrl->p2p_ns_map,
+						    req->ns->nsid);
+
+		req->p2p_dev = NULL;
+		if (req->sq->qid && p2p_dev) {
+			req->sg = pci_p2pmem_alloc_sgl(p2p_dev, &req->sg_cnt,
+						       req->transfer_len);
+			if (req->sg) {
+				req->p2p_dev = p2p_dev;
+				return 0;
+			}
+		}
+
+		/*
+		 * If no P2P memory was available we fallback to using
+		 * regular memory
+		 */
+	}
+
+	req->sg = sgl_alloc(req->transfer_len, GFP_KERNEL, &req->sg_cnt);
+	if (!req->sg)
+		return -ENOMEM;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(nvmet_req_alloc_sgl);
+
+void nvmet_req_free_sgl(struct nvmet_req *req)
+{
+	if (req->p2p_dev)
+		pci_p2pmem_free_sgl(req->p2p_dev, req->sg);
+	else
+		sgl_free(req->sg);
+
+	req->sg = NULL;
+	req->sg_cnt = 0;
+}
+EXPORT_SYMBOL_GPL(nvmet_req_free_sgl);
+
 static inline bool nvmet_cc_en(u32 cc)
 {
 	return (cc >> NVME_CC_EN_SHIFT) & 0x1;
@@ -921,6 +1067,37 @@ bool nvmet_host_allowed(struct nvmet_req *req, struct nvmet_subsys *subsys,
 		return __nvmet_host_allowed(subsys, hostnqn);
 }
 
+/*
+ * Note: ctrl->subsys->lock should be held when calling this function
+ */
+static void nvmet_setup_p2p_ns_map(struct nvmet_ctrl *ctrl,
+		struct nvmet_req *req)
+{
+	struct nvmet_ns *ns;
+
+	if (!req->p2p_client)
+		return;
+
+	ctrl->p2p_client = get_device(req->p2p_client);
+
+	list_for_each_entry_rcu(ns, &ctrl->subsys->namespaces, dev_link)
+		nvmet_p2pmem_ns_add_p2p(ctrl, ns);
+}
+
+/*
+ * Note: ctrl->subsys->lock should be held when calling this function
+ */
+static void nvmet_release_p2p_ns_map(struct nvmet_ctrl *ctrl)
+{
+	struct radix_tree_iter iter;
+	void __rcu **slot;
+
+	radix_tree_for_each_slot(slot, &ctrl->p2p_ns_map, &iter, 0)
+		pci_dev_put(radix_tree_deref_slot(slot));
+
+	put_device(ctrl->p2p_client);
+}
+
 u16 nvmet_alloc_ctrl(const char *subsysnqn, const char *hostnqn,
 		struct nvmet_req *req, u32 kato, struct nvmet_ctrl **ctrlp)
 {
@@ -962,6 +1139,7 @@ u16 nvmet_alloc_ctrl(const char *subsysnqn, const char *hostnqn,
 
 	INIT_WORK(&ctrl->async_event_work, nvmet_async_event_work);
 	INIT_LIST_HEAD(&ctrl->async_events);
+	INIT_RADIX_TREE(&ctrl->p2p_ns_map, GFP_KERNEL);
 
 	memcpy(ctrl->subsysnqn, subsysnqn, NVMF_NQN_SIZE);
 	memcpy(ctrl->hostnqn, hostnqn, NVMF_NQN_SIZE);
@@ -1026,6 +1204,7 @@ u16 nvmet_alloc_ctrl(const char *subsysnqn, const char *hostnqn,
 
 	mutex_lock(&subsys->lock);
 	list_add_tail(&ctrl->subsys_entry, &subsys->ctrls);
+	nvmet_setup_p2p_ns_map(ctrl, req);
 	mutex_unlock(&subsys->lock);
 
 	*ctrlp = ctrl;
@@ -1053,6 +1232,7 @@ static void nvmet_ctrl_free(struct kref *ref)
 	struct nvmet_subsys *subsys = ctrl->subsys;
 
 	mutex_lock(&subsys->lock);
+	nvmet_release_p2p_ns_map(ctrl);
 	list_del(&ctrl->subsys_entry);
 	mutex_unlock(&subsys->lock);
 
diff --git a/drivers/nvme/target/io-cmd-bdev.c b/drivers/nvme/target/io-cmd-bdev.c
index 7bc9f6240432..5660dd7ca755 100644
--- a/drivers/nvme/target/io-cmd-bdev.c
+++ b/drivers/nvme/target/io-cmd-bdev.c
@@ -78,6 +78,9 @@ static void nvmet_bdev_execute_rw(struct nvmet_req *req)
 		op = REQ_OP_READ;
 	}
 
+	if (is_pci_p2pdma_page(sg_page(req->sg)))
+		op_flags |= REQ_NOMERGE;
+
 	sector = le64_to_cpu(req->cmd->rw.slba);
 	sector <<= (req->ns->blksize_shift - 9);
 
diff --git a/drivers/nvme/target/nvmet.h b/drivers/nvme/target/nvmet.h
index ec9af4ee03b6..d6be098f342b 100644
--- a/drivers/nvme/target/nvmet.h
+++ b/drivers/nvme/target/nvmet.h
@@ -26,6 +26,7 @@
 #include <linux/configfs.h>
 #include <linux/rcupdate.h>
 #include <linux/blkdev.h>
+#include <linux/radix-tree.h>
 
 #define NVMET_ASYNC_EVENTS		4
 #define NVMET_ERROR_LOG_SLOTS		128
@@ -77,6 +78,9 @@ struct nvmet_ns {
 	struct completion	disable_done;
 	mempool_t		*bvec_pool;
 	struct kmem_cache	*bvec_cache;
+
+	int			use_p2pmem;
+	struct pci_dev		*p2p_dev;
 };
 
 static inline struct nvmet_ns *to_nvmet_ns(struct config_item *item)
@@ -84,6 +88,11 @@ static inline struct nvmet_ns *to_nvmet_ns(struct config_item *item)
 	return container_of(to_config_group(item), struct nvmet_ns, group);
 }
 
+static inline struct device *nvmet_ns_dev(struct nvmet_ns *ns)
+{
+	return ns->bdev ? disk_to_dev(ns->bdev->bd_disk) : NULL;
+}
+
 struct nvmet_cq {
 	u16			qid;
 	u16			size;
@@ -184,6 +193,9 @@ struct nvmet_ctrl {
 
 	char			subsysnqn[NVMF_NQN_FIELD_LEN];
 	char			hostnqn[NVMF_NQN_FIELD_LEN];
+
+	struct device *p2p_client;
+	struct radix_tree_root p2p_ns_map;
 };
 
 struct nvmet_subsys {
@@ -294,6 +306,9 @@ struct nvmet_req {
 
 	void (*execute)(struct nvmet_req *req);
 	const struct nvmet_fabrics_ops *ops;
+
+	struct pci_dev *p2p_dev;
+	struct device *p2p_client;
 };
 
 extern struct workqueue_struct *buffered_io_wq;
@@ -336,6 +351,8 @@ bool nvmet_req_init(struct nvmet_req *req, struct nvmet_cq *cq,
 void nvmet_req_uninit(struct nvmet_req *req);
 void nvmet_req_execute(struct nvmet_req *req);
 void nvmet_req_complete(struct nvmet_req *req, u16 status);
+int nvmet_req_alloc_sgl(struct nvmet_req *req);
+void nvmet_req_free_sgl(struct nvmet_req *req);
 
 void nvmet_cq_setup(struct nvmet_ctrl *ctrl, struct nvmet_cq *cq, u16 qid,
 		u16 size);
diff --git a/drivers/nvme/target/rdma.c b/drivers/nvme/target/rdma.c
index bfc4da660bb4..3f7971d3706d 100644
--- a/drivers/nvme/target/rdma.c
+++ b/drivers/nvme/target/rdma.c
@@ -503,7 +503,7 @@ static void nvmet_rdma_release_rsp(struct nvmet_rdma_rsp *rsp)
 	}
 
 	if (rsp->req.sg != rsp->cmd->inline_sg)
-		sgl_free(rsp->req.sg);
+		nvmet_req_free_sgl(&rsp->req);
 
 	if (unlikely(!list_empty_careful(&queue->rsp_wr_wait_list)))
 		nvmet_rdma_process_wr_wait_list(queue);
@@ -652,24 +652,24 @@ static u16 nvmet_rdma_map_sgl_keyed(struct nvmet_rdma_rsp *rsp,
 {
 	struct rdma_cm_id *cm_id = rsp->queue->cm_id;
 	u64 addr = le64_to_cpu(sgl->addr);
-	u32 len = get_unaligned_le24(sgl->length);
 	u32 key = get_unaligned_le32(sgl->key);
 	int ret;
 
+	rsp->req.transfer_len = get_unaligned_le24(sgl->length);
+
 	/* no data command? */
-	if (!len)
+	if (!rsp->req.transfer_len)
 		return 0;
 
-	rsp->req.sg = sgl_alloc(len, GFP_KERNEL, &rsp->req.sg_cnt);
-	if (!rsp->req.sg)
-		return NVME_SC_INTERNAL;
+	ret = nvmet_req_alloc_sgl(&rsp->req);
+	if (ret < 0)
+		goto error_out;
 
 	ret = rdma_rw_ctx_init(&rsp->rw, cm_id->qp, cm_id->port_num,
 			rsp->req.sg, rsp->req.sg_cnt, 0, addr, key,
 			nvmet_data_dir(&rsp->req));
 	if (ret < 0)
-		return NVME_SC_INTERNAL;
-	rsp->req.transfer_len += len;
+		goto error_out;
 	rsp->n_rdma += ret;
 
 	if (invalidate) {
@@ -678,6 +678,10 @@ static u16 nvmet_rdma_map_sgl_keyed(struct nvmet_rdma_rsp *rsp,
 	}
 
 	return 0;
+
+error_out:
+	rsp->req.transfer_len = 0;
+	return NVME_SC_INTERNAL;
 }
 
 static u16 nvmet_rdma_map_sgl(struct nvmet_rdma_rsp *rsp)
@@ -745,6 +749,8 @@ static void nvmet_rdma_handle_command(struct nvmet_rdma_queue *queue,
 		cmd->send_sge.addr, cmd->send_sge.length,
 		DMA_TO_DEVICE);
 
+	cmd->req.p2p_client = &queue->dev->device->dev;
+
 	if (!nvmet_req_init(&cmd->req, &queue->nvme_cq,
 			&queue->nvme_sq, &nvmet_rdma_ops))
 		return;
diff --git a/drivers/pci/Kconfig b/drivers/pci/Kconfig
index 56ff8f6d31fc..deb68be4fdac 100644
--- a/drivers/pci/Kconfig
+++ b/drivers/pci/Kconfig
@@ -132,6 +132,23 @@ config PCI_PASID
 
 	  If unsure, say N.
 
+config PCI_P2PDMA
+	bool "PCI peer-to-peer transfer support"
+	depends on PCI && ZONE_DEVICE
+	select GENERIC_ALLOCATOR
+	help
+	  Enableѕ drivers to do PCI peer-to-peer transactions to and from
+	  BARs that are exposed in other devices that are the part of
+	  the hierarchy where peer-to-peer DMA is guaranteed by the PCI
+	  specification to work (ie. anything below a single PCI bridge).
+
+	  Many PCIe root complexes do not support P2P transactions and
+	  it's hard to tell which support it at all, so at this time,
+	  P2P DMA transations must be between devices behind the same root
+	  port.
+
+	  If unsure, say N.
+
 config PCI_LABEL
 	def_bool y if (DMI || ACPI)
 	depends on PCI
diff --git a/drivers/pci/Makefile b/drivers/pci/Makefile
index 1b2cfe51e8d7..85f4a703b2be 100644
--- a/drivers/pci/Makefile
+++ b/drivers/pci/Makefile
@@ -26,6 +26,7 @@ obj-$(CONFIG_PCI_SYSCALL)	+= syscall.o
 obj-$(CONFIG_PCI_STUB)		+= pci-stub.o
 obj-$(CONFIG_PCI_PF_STUB)	+= pci-pf-stub.o
 obj-$(CONFIG_PCI_ECAM)		+= ecam.o
+obj-$(CONFIG_PCI_P2PDMA)	+= p2pdma.o
 obj-$(CONFIG_XEN_PCIDEV_FRONTEND) += xen-pcifront.o
 
 # Endpoint library must be initialized before its users
diff --git a/drivers/pci/p2pdma.c b/drivers/pci/p2pdma.c
new file mode 100644
index 000000000000..ae3c5b25dcc7
--- /dev/null
+++ b/drivers/pci/p2pdma.c
@@ -0,0 +1,805 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * PCI Peer 2 Peer DMA support.
+ *
+ * Copyright (c) 2016-2018, Logan Gunthorpe
+ * Copyright (c) 2016-2017, Microsemi Corporation
+ * Copyright (c) 2017, Christoph Hellwig
+ * Copyright (c) 2018, Eideticom Inc.
+ */
+
+#define pr_fmt(fmt) "pci-p2pdma: " fmt
+#include <linux/ctype.h>
+#include <linux/pci-p2pdma.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/genalloc.h>
+#include <linux/memremap.h>
+#include <linux/percpu-refcount.h>
+#include <linux/random.h>
+#include <linux/seq_buf.h>
+
+struct pci_p2pdma {
+	struct percpu_ref devmap_ref;
+	struct completion devmap_ref_done;
+	struct gen_pool *pool;
+	bool p2pmem_published;
+};
+
+static ssize_t size_show(struct device *dev, struct device_attribute *attr,
+			 char *buf)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+	size_t size = 0;
+
+	if (pdev->p2pdma->pool)
+		size = gen_pool_size(pdev->p2pdma->pool);
+
+	return snprintf(buf, PAGE_SIZE, "%zd\n", size);
+}
+static DEVICE_ATTR_RO(size);
+
+static ssize_t available_show(struct device *dev, struct device_attribute *attr,
+			      char *buf)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+	size_t avail = 0;
+
+	if (pdev->p2pdma->pool)
+		avail = gen_pool_avail(pdev->p2pdma->pool);
+
+	return snprintf(buf, PAGE_SIZE, "%zd\n", avail);
+}
+static DEVICE_ATTR_RO(available);
+
+static ssize_t published_show(struct device *dev, struct device_attribute *attr,
+			      char *buf)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+
+	return snprintf(buf, PAGE_SIZE, "%d\n",
+			pdev->p2pdma->p2pmem_published);
+}
+static DEVICE_ATTR_RO(published);
+
+static struct attribute *p2pmem_attrs[] = {
+	&dev_attr_size.attr,
+	&dev_attr_available.attr,
+	&dev_attr_published.attr,
+	NULL,
+};
+
+static const struct attribute_group p2pmem_group = {
+	.attrs = p2pmem_attrs,
+	.name = "p2pmem",
+};
+
+static void pci_p2pdma_percpu_release(struct percpu_ref *ref)
+{
+	struct pci_p2pdma *p2p =
+		container_of(ref, struct pci_p2pdma, devmap_ref);
+
+	complete_all(&p2p->devmap_ref_done);
+}
+
+static void pci_p2pdma_percpu_kill(void *data)
+{
+	struct percpu_ref *ref = data;
+
+	/*
+	 * pci_p2pdma_add_resource() may be called multiple times
+	 * by a driver and may register the percpu_kill devm action multiple
+	 * times. We only want the first action to actually kill the
+	 * percpu_ref.
+	 */
+	if (percpu_ref_is_dying(ref))
+		return;
+
+	percpu_ref_kill(ref);
+}
+
+static void pci_p2pdma_release(void *data)
+{
+	struct pci_dev *pdev = data;
+
+	if (!pdev->p2pdma)
+		return;
+
+	wait_for_completion(&pdev->p2pdma->devmap_ref_done);
+	percpu_ref_exit(&pdev->p2pdma->devmap_ref);
+
+	gen_pool_destroy(pdev->p2pdma->pool);
+	sysfs_remove_group(&pdev->dev.kobj, &p2pmem_group);
+	pdev->p2pdma = NULL;
+}
+
+static int pci_p2pdma_setup(struct pci_dev *pdev)
+{
+	int error = -ENOMEM;
+	struct pci_p2pdma *p2p;
+
+	p2p = devm_kzalloc(&pdev->dev, sizeof(*p2p), GFP_KERNEL);
+	if (!p2p)
+		return -ENOMEM;
+
+	p2p->pool = gen_pool_create(PAGE_SHIFT, dev_to_node(&pdev->dev));
+	if (!p2p->pool)
+		goto out;
+
+	init_completion(&p2p->devmap_ref_done);
+	error = percpu_ref_init(&p2p->devmap_ref,
+			pci_p2pdma_percpu_release, 0, GFP_KERNEL);
+	if (error)
+		goto out_pool_destroy;
+
+	error = devm_add_action_or_reset(&pdev->dev, pci_p2pdma_release, pdev);
+	if (error)
+		goto out_pool_destroy;
+
+	pdev->p2pdma = p2p;
+
+	error = sysfs_create_group(&pdev->dev.kobj, &p2pmem_group);
+	if (error)
+		goto out_pool_destroy;
+
+	return 0;
+
+out_pool_destroy:
+	pdev->p2pdma = NULL;
+	gen_pool_destroy(p2p->pool);
+out:
+	devm_kfree(&pdev->dev, p2p);
+	return error;
+}
+
+/**
+ * pci_p2pdma_add_resource - add memory for use as p2p memory
+ * @pdev: the device to add the memory to
+ * @bar: PCI BAR to add
+ * @size: size of the memory to add, may be zero to use the whole BAR
+ * @offset: offset into the PCI BAR
+ *
+ * The memory will be given ZONE_DEVICE struct pages so that it may
+ * be used with any DMA request.
+ */
+int pci_p2pdma_add_resource(struct pci_dev *pdev, int bar, size_t size,
+			    u64 offset)
+{
+	struct dev_pagemap *pgmap;
+	void *addr;
+	int error;
+
+	if (!(pci_resource_flags(pdev, bar) & IORESOURCE_MEM))
+		return -EINVAL;
+
+	if (offset >= pci_resource_len(pdev, bar))
+		return -EINVAL;
+
+	if (!size)
+		size = pci_resource_len(pdev, bar) - offset;
+
+	if (size + offset > pci_resource_len(pdev, bar))
+		return -EINVAL;
+
+	if (!pdev->p2pdma) {
+		error = pci_p2pdma_setup(pdev);
+		if (error)
+			return error;
+	}
+
+	pgmap = devm_kzalloc(&pdev->dev, sizeof(*pgmap), GFP_KERNEL);
+	if (!pgmap)
+		return -ENOMEM;
+
+	pgmap->res.start = pci_resource_start(pdev, bar) + offset;
+	pgmap->res.end = pgmap->res.start + size - 1;
+	pgmap->res.flags = pci_resource_flags(pdev, bar);
+	pgmap->ref = &pdev->p2pdma->devmap_ref;
+	pgmap->type = MEMORY_DEVICE_PCI_P2PDMA;
+	pgmap->pci_p2pdma_bus_offset = pci_bus_address(pdev, bar) -
+		pci_resource_start(pdev, bar);
+
+	addr = devm_memremap_pages(&pdev->dev, pgmap);
+	if (IS_ERR(addr)) {
+		error = PTR_ERR(addr);
+		goto pgmap_free;
+	}
+
+	error = gen_pool_add_virt(pdev->p2pdma->pool, (unsigned long)addr,
+			pci_bus_address(pdev, bar) + offset,
+			resource_size(&pgmap->res), dev_to_node(&pdev->dev));
+	if (error)
+		goto pgmap_free;
+
+	error = devm_add_action_or_reset(&pdev->dev, pci_p2pdma_percpu_kill,
+					  &pdev->p2pdma->devmap_ref);
+	if (error)
+		goto pgmap_free;
+
+	pci_info(pdev, "added peer-to-peer DMA memory %pR\n",
+		 &pgmap->res);
+
+	return 0;
+
+pgmap_free:
+	devm_kfree(&pdev->dev, pgmap);
+	return error;
+}
+EXPORT_SYMBOL_GPL(pci_p2pdma_add_resource);
+
+/*
+ * Note this function returns the parent PCI device with a
+ * reference taken. It is the caller's responsibily to drop
+ * the reference.
+ */
+static struct pci_dev *find_parent_pci_dev(struct device *dev)
+{
+	struct device *parent;
+
+	dev = get_device(dev);
+
+	while (dev) {
+		if (dev_is_pci(dev))
+			return to_pci_dev(dev);
+
+		parent = get_device(dev->parent);
+		put_device(dev);
+		dev = parent;
+	}
+
+	return NULL;
+}
+
+/*
+ * Check if a PCI bridge has its ACS redirection bits set to redirect P2P
+ * TLPs upstream via ACS. Returns 1 if the packets will be redirected
+ * upstream, 0 otherwise.
+ */
+static int pci_bridge_has_acs_redir(struct pci_dev *pdev)
+{
+	int pos;
+	u16 ctrl;
+
+	pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_ACS);
+	if (!pos)
+		return 0;
+
+	pci_read_config_word(pdev, pos + PCI_ACS_CTRL, &ctrl);
+
+	if (ctrl & (PCI_ACS_RR | PCI_ACS_CR | PCI_ACS_EC))
+		return 1;
+
+	return 0;
+}
+
+static void seq_buf_print_bus_devfn(struct seq_buf *buf, struct pci_dev *pdev)
+{
+	if (!buf)
+		return;
+
+	seq_buf_printf(buf, "%s;", pci_name(pdev));
+}
+
+/*
+ * Find the distance through the nearest common upstream bridge between
+ * two PCI devices.
+ *
+ * If the two devices are the same device then 0 will be returned.
+ *
+ * If there are two virtual functions of the same device behind the same
+ * bridge port then 2 will be returned (one step down to the PCIe switch,
+ * then one step back to the same device).
+ *
+ * In the case where two devices are connected to the same PCIe switch, the
+ * value 4 will be returned. This corresponds to the following PCI tree:
+ *
+ *     -+  Root Port
+ *      \+ Switch Upstream Port
+ *       +-+ Switch Downstream Port
+ *       + \- Device A
+ *       \-+ Switch Downstream Port
+ *         \- Device B
+ *
+ * The distance is 4 because we traverse from Device A through the downstream
+ * port of the switch, to the common upstream port, back up to the second
+ * downstream port and then to Device B.
+ *
+ * Any two devices that don't have a common upstream bridge will return -1.
+ * In this way devices on separate PCIe root ports will be rejected, which
+ * is what we want for peer-to-peer seeing each PCIe root port defines a
+ * separate hierarchy domain and there's no way to determine whether the root
+ * complex supports forwarding between them.
+ *
+ * In the case where two devices are connected to different PCIe switches,
+ * this function will still return a positive distance as long as both
+ * switches eventually have a common upstream bridge. Note this covers
+ * the case of using multiple PCIe switches to achieve a desired level of
+ * fan-out from a root port. The exact distance will be a function of the
+ * number of switches between Device A and Device B.
+ *
+ * If a bridge which has any ACS redirection bits set is in the path
+ * then this functions will return -2. This is so we reject any
+ * cases where the TLPs are forwarded up into the root complex.
+ * In this case, a list of all infringing bridge addresses will be
+ * populated in acs_list (assuming it's non-null) for printk purposes.
+ */
+static int upstream_bridge_distance(struct pci_dev *a,
+				    struct pci_dev *b,
+				    struct seq_buf *acs_list)
+{
+	int dist_a = 0;
+	int dist_b = 0;
+	struct pci_dev *bb = NULL;
+	int acs_cnt = 0;
+
+	/*
+	 * Note, we don't need to take references to devices returned by
+	 * pci_upstream_bridge() seeing we hold a reference to a child
+	 * device which will already hold a reference to the upstream bridge.
+	 */
+
+	while (a) {
+		dist_b = 0;
+
+		if (pci_bridge_has_acs_redir(a)) {
+			seq_buf_print_bus_devfn(acs_list, a);
+			acs_cnt++;
+		}
+
+		bb = b;
+
+		while (bb) {
+			if (a == bb)
+				goto check_b_path_acs;
+
+			bb = pci_upstream_bridge(bb);
+			dist_b++;
+		}
+
+		a = pci_upstream_bridge(a);
+		dist_a++;
+	}
+
+	return -1;
+
+check_b_path_acs:
+	bb = b;
+
+	while (bb) {
+		if (a == bb)
+			break;
+
+		if (pci_bridge_has_acs_redir(bb)) {
+			seq_buf_print_bus_devfn(acs_list, bb);
+			acs_cnt++;
+		}
+
+		bb = pci_upstream_bridge(bb);
+	}
+
+	if (acs_cnt)
+		return -2;
+
+	return dist_a + dist_b;
+}
+
+static int upstream_bridge_distance_warn(struct pci_dev *provider,
+					 struct pci_dev *client)
+{
+	struct seq_buf acs_list;
+	int ret;
+
+	seq_buf_init(&acs_list, kmalloc(PAGE_SIZE, GFP_KERNEL), PAGE_SIZE);
+	if (!acs_list.buffer)
+		return -ENOMEM;
+
+	ret = upstream_bridge_distance(provider, client, &acs_list);
+	if (ret == -2) {
+		pci_warn(client, "cannot be used for peer-to-peer DMA as ACS redirect is set between the client and provider (%s)\n",
+			 pci_name(provider));
+		/* Drop final semicolon */
+		acs_list.buffer[acs_list.len-1] = 0;
+		pci_warn(client, "to disable ACS redirect for this path, add the kernel parameter: pci=disable_acs_redir=%s\n",
+			 acs_list.buffer);
+
+	} else if (ret < 0) {
+		pci_warn(client, "cannot be used for peer-to-peer DMA as the client and provider (%s) do not share an upstream bridge\n",
+			 pci_name(provider));
+	}
+
+	kfree(acs_list.buffer);
+
+	return ret;
+}
+
+/**
+ * pci_p2pdma_distance_many - Determive the cumulative distance between
+ *	a p2pdma provider and the clients in use.
+ * @provider: p2pdma provider to check against the client list
+ * @clients: array of devices to check (NULL-terminated)
+ * @num_clients: number of clients in the array
+ * @verbose: if true, print warnings for devices when we return -1
+ *
+ * Returns -1 if any of the clients are not compatible (behind the same
+ * root port as the provider), otherwise returns a positive number where
+ * a lower number is the preferrable choice. (If there's one client
+ * that's the same as the provider it will return 0, which is best choice).
+ *
+ * For now, "compatible" means the provider and the clients are all behind
+ * the same PCI root port. This cuts out cases that may work but is safest
+ * for the user. Future work can expand this to white-list root complexes that
+ * can safely forward between each ports.
+ */
+int pci_p2pdma_distance_many(struct pci_dev *provider, struct device **clients,
+			     int num_clients, bool verbose)
+{
+	bool not_supported = false;
+	struct pci_dev *pci_client;
+	int distance = 0;
+	int i, ret;
+
+	if (num_clients == 0)
+		return -1;
+
+	for (i = 0; i < num_clients; i++) {
+		pci_client = find_parent_pci_dev(clients[i]);
+		if (!pci_client) {
+			if (verbose)
+				dev_warn(clients[i],
+					 "cannot be used for peer-to-peer DMA as it is not a PCI device\n");
+			return -1;
+		}
+
+		if (verbose)
+			ret = upstream_bridge_distance_warn(provider,
+							    pci_client);
+		else
+			ret = upstream_bridge_distance(provider, pci_client,
+						       NULL);
+
+		pci_dev_put(pci_client);
+
+		if (ret < 0)
+			not_supported = true;
+
+		if (not_supported && !verbose)
+			break;
+
+		distance += ret;
+	}
+
+	if (not_supported)
+		return -1;
+
+	return distance;
+}
+EXPORT_SYMBOL_GPL(pci_p2pdma_distance_many);
+
+/**
+ * pci_has_p2pmem - check if a given PCI device has published any p2pmem
+ * @pdev: PCI device to check
+ */
+bool pci_has_p2pmem(struct pci_dev *pdev)
+{
+	return pdev->p2pdma && pdev->p2pdma->p2pmem_published;
+}
+EXPORT_SYMBOL_GPL(pci_has_p2pmem);
+
+/**
+ * pci_p2pmem_find - find a peer-to-peer DMA memory device compatible with
+ *	the specified list of clients and shortest distance (as determined
+ *	by pci_p2pmem_dma())
+ * @clients: array of devices to check (NULL-terminated)
+ * @num_clients: number of client devices in the list
+ *
+ * If multiple devices are behind the same switch, the one "closest" to the
+ * client devices in use will be chosen first. (So if one of the providers are
+ * the same as one of the clients, that provider will be used ahead of any
+ * other providers that are unrelated). If multiple providers are an equal
+ * distance away, one will be chosen at random.
+ *
+ * Returns a pointer to the PCI device with a reference taken (use pci_dev_put
+ * to return the reference) or NULL if no compatible device is found. The
+ * found provider will also be assigned to the client list.
+ */
+struct pci_dev *pci_p2pmem_find_many(struct device **clients, int num_clients)
+{
+	struct pci_dev *pdev = NULL;
+	int distance;
+	int closest_distance = INT_MAX;
+	struct pci_dev **closest_pdevs;
+	int dev_cnt = 0;
+	const int max_devs = PAGE_SIZE / sizeof(*closest_pdevs);
+	int i;
+
+	closest_pdevs = kmalloc(PAGE_SIZE, GFP_KERNEL);
+	if (!closest_pdevs)
+		return NULL;
+
+	while ((pdev = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, pdev))) {
+		if (!pci_has_p2pmem(pdev))
+			continue;
+
+		distance = pci_p2pdma_distance_many(pdev, clients,
+						    num_clients, false);
+		if (distance < 0 || distance > closest_distance)
+			continue;
+
+		if (distance == closest_distance && dev_cnt >= max_devs)
+			continue;
+
+		if (distance < closest_distance) {
+			for (i = 0; i < dev_cnt; i++)
+				pci_dev_put(closest_pdevs[i]);
+
+			dev_cnt = 0;
+			closest_distance = distance;
+		}
+
+		closest_pdevs[dev_cnt++] = pci_dev_get(pdev);
+	}
+
+	if (dev_cnt)
+		pdev = pci_dev_get(closest_pdevs[prandom_u32_max(dev_cnt)]);
+
+	for (i = 0; i < dev_cnt; i++)
+		pci_dev_put(closest_pdevs[i]);
+
+	kfree(closest_pdevs);
+	return pdev;
+}
+EXPORT_SYMBOL_GPL(pci_p2pmem_find_many);
+
+/**
+ * pci_alloc_p2p_mem - allocate peer-to-peer DMA memory
+ * @pdev: the device to allocate memory from
+ * @size: number of bytes to allocate
+ *
+ * Returns the allocated memory or NULL on error.
+ */
+void *pci_alloc_p2pmem(struct pci_dev *pdev, size_t size)
+{
+	void *ret;
+
+	if (unlikely(!pdev->p2pdma))
+		return NULL;
+
+	if (unlikely(!percpu_ref_tryget_live(&pdev->p2pdma->devmap_ref)))
+		return NULL;
+
+	ret = (void *)gen_pool_alloc(pdev->p2pdma->pool, size);
+
+	if (unlikely(!ret))
+		percpu_ref_put(&pdev->p2pdma->devmap_ref);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(pci_alloc_p2pmem);
+
+/**
+ * pci_free_p2pmem - free peer-to-peer DMA memory
+ * @pdev: the device the memory was allocated from
+ * @addr: address of the memory that was allocated
+ * @size: number of bytes that was allocated
+ */
+void pci_free_p2pmem(struct pci_dev *pdev, void *addr, size_t size)
+{
+	gen_pool_free(pdev->p2pdma->pool, (uintptr_t)addr, size);
+	percpu_ref_put(&pdev->p2pdma->devmap_ref);
+}
+EXPORT_SYMBOL_GPL(pci_free_p2pmem);
+
+/**
+ * pci_virt_to_bus - return the PCI bus address for a given virtual
+ *	address obtained with pci_alloc_p2pmem()
+ * @pdev: the device the memory was allocated from
+ * @addr: address of the memory that was allocated
+ */
+pci_bus_addr_t pci_p2pmem_virt_to_bus(struct pci_dev *pdev, void *addr)
+{
+	if (!addr)
+		return 0;
+	if (!pdev->p2pdma)
+		return 0;
+
+	/*
+	 * Note: when we added the memory to the pool we used the PCI
+	 * bus address as the physical address. So gen_pool_virt_to_phys()
+	 * actually returns the bus address despite the misleading name.
+	 */
+	return gen_pool_virt_to_phys(pdev->p2pdma->pool, (unsigned long)addr);
+}
+EXPORT_SYMBOL_GPL(pci_p2pmem_virt_to_bus);
+
+/**
+ * pci_p2pmem_alloc_sgl - allocate peer-to-peer DMA memory in a scatterlist
+ * @pdev: the device to allocate memory from
+ * @nents: the number of SG entries in the list
+ * @length: number of bytes to allocate
+ *
+ * Returns 0 on success
+ */
+struct scatterlist *pci_p2pmem_alloc_sgl(struct pci_dev *pdev,
+					 unsigned int *nents, u32 length)
+{
+	struct scatterlist *sg;
+	void *addr;
+
+	sg = kzalloc(sizeof(*sg), GFP_KERNEL);
+	if (!sg)
+		return NULL;
+
+	sg_init_table(sg, 1);
+
+	addr = pci_alloc_p2pmem(pdev, length);
+	if (!addr)
+		goto out_free_sg;
+
+	sg_set_buf(sg, addr, length);
+	*nents = 1;
+	return sg;
+
+out_free_sg:
+	kfree(sg);
+	return NULL;
+}
+EXPORT_SYMBOL_GPL(pci_p2pmem_alloc_sgl);
+
+/**
+ * pci_p2pmem_free_sgl - free a scatterlist allocated by pci_p2pmem_alloc_sgl()
+ * @pdev: the device to allocate memory from
+ * @sgl: the allocated scatterlist
+ */
+void pci_p2pmem_free_sgl(struct pci_dev *pdev, struct scatterlist *sgl)
+{
+	struct scatterlist *sg;
+	int count;
+
+	for_each_sg(sgl, sg, INT_MAX, count) {
+		if (!sg)
+			break;
+
+		pci_free_p2pmem(pdev, sg_virt(sg), sg->length);
+	}
+	kfree(sgl);
+}
+EXPORT_SYMBOL_GPL(pci_p2pmem_free_sgl);
+
+/**
+ * pci_p2pmem_publish - publish the peer-to-peer DMA memory for use by
+ *	other devices with pci_p2pmem_find()
+ * @pdev: the device with peer-to-peer DMA memory to publish
+ * @publish: set to true to publish the memory, false to unpublish it
+ *
+ * Published memory can be used by other PCI device drivers for
+ * peer-2-peer DMA operations. Non-published memory is reserved for
+ * exlusive use of the device driver that registers the peer-to-peer
+ * memory.
+ */
+void pci_p2pmem_publish(struct pci_dev *pdev, bool publish)
+{
+	if (pdev->p2pdma)
+		pdev->p2pdma->p2pmem_published = publish;
+}
+EXPORT_SYMBOL_GPL(pci_p2pmem_publish);
+
+/**
+ * pci_p2pdma_map_sg - 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
+ *
+ * Scatterlists mapped with this function should not be unmapped in any way.
+ *
+ * Returns the number of SG entries mapped or 0 on error.
+ */
+int pci_p2pdma_map_sg(struct device *dev, struct scatterlist *sg, int nents,
+		      enum dma_data_direction dir)
+{
+	struct dev_pagemap *pgmap;
+	struct scatterlist *s;
+	phys_addr_t paddr;
+	int i;
+
+	/*
+	 * p2pdma mappings are not compatible with devices that use
+	 * dma_virt_ops. If the upper layers do the right thing
+	 * this should never happen because it will be prevented
+	 * by the check in pci_p2pdma_add_client()
+	 */
+	if (WARN_ON_ONCE(IS_ENABLED(CONFIG_DMA_VIRT_OPS) &&
+			 dev->dma_ops == &dma_virt_ops))
+		return 0;
+
+	for_each_sg(sg, s, nents, i) {
+		pgmap = sg_page(s)->pgmap;
+		paddr = sg_phys(s);
+
+		s->dma_address = paddr - pgmap->pci_p2pdma_bus_offset;
+		sg_dma_len(s) = s->length;
+	}
+
+	return nents;
+}
+EXPORT_SYMBOL_GPL(pci_p2pdma_map_sg);
+
+/**
+ * pci_p2pdma_enable_store - parse a configfs/sysfs attribute store
+ *		to enable p2pdma
+ * @page: contents of the value to be stored
+ * @p2p_dev: returns the PCI device that was selected to be used
+ *		(if one was specified in the stored value)
+ * @use_p2pdma: returns whether to enable p2pdma or not
+ *
+ * Parses an attribute value to decide whether to enable p2pdma.
+ * The value can select a PCI device (using it's full BDF device
+ * name) or a boolean (in any format strtobool() accepts). A false
+ * value disables p2pdma, a true value expects the caller
+ * to automatically find a compatible device and specifying a PCI device
+ * expects the caller to use the specific provider.
+ *
+ * pci_p2pdma_enable_show() should be used as the show operation for
+ * the attribute.
+ *
+ * Returns 0 on success
+ */
+int pci_p2pdma_enable_store(const char *page, struct pci_dev **p2p_dev,
+			    bool *use_p2pdma)
+{
+	struct device *dev;
+
+	dev = bus_find_device_by_name(&pci_bus_type, NULL, page);
+	if (dev) {
+		*use_p2pdma = true;
+		*p2p_dev = to_pci_dev(dev);
+
+		if (!pci_has_p2pmem(*p2p_dev)) {
+			pci_err(*p2p_dev,
+				"PCI device has no peer-to-peer memory: %s\n",
+				page);
+			pci_dev_put(*p2p_dev);
+			return -ENODEV;
+		}
+
+		return 0;
+	} else if ((page[0] == '0' || page[0] == '1') && !iscntrl(page[1])) {
+		/*
+		 * If the user enters a PCI device that  doesn't exist
+		 * like "0000:01:00.1", we don't want strtobool to think
+		 * it's a '0' when it's clearly not what the user wanted.
+		 * So we require 0's and 1's to be exactly one character.
+		 */
+	} else if (!strtobool(page, use_p2pdma)) {
+		return 0;
+	}
+
+	pr_err("No such PCI device: %.*s\n", (int)strcspn(page, "\n"), page);
+	return -ENODEV;
+}
+EXPORT_SYMBOL_GPL(pci_p2pdma_enable_store);
+
+/**
+ * pci_p2pdma_enable_show - show a configfs/sysfs attribute indicating
+ *		whether p2pdma is enabled
+ * @page: contents of the stored value
+ * @p2p_dev: the selected p2p device (NULL if no device is selected)
+ * @use_p2pdma: whether p2pdme has been enabled
+ *
+ * Attributes that use pci_p2pdma_enable_store() should use this function
+ * to show the value of the attribute.
+ *
+ * Returns 0 on success
+ */
+ssize_t pci_p2pdma_enable_show(char *page, struct pci_dev *p2p_dev,
+			       bool use_p2pdma)
+{
+	if (!use_p2pdma)
+		return sprintf(page, "0\n");
+
+	if (!p2p_dev)
+		return sprintf(page, "1\n");
+
+	return sprintf(page, "%s\n", pci_name(p2p_dev));
+}
+EXPORT_SYMBOL_GPL(pci_p2pdma_enable_show);