[PATCH v5 00/13] Copy Offload in NVMe Fabrics with P2P PCI Memory

@@ -725,6 +725,24 @@ void nvmet_req_execute(struct nvmet_req *req)
 }
 EXPORT_SYMBOL_GPL(nvmet_req_execute);
 
+int nvmet_req_alloc_sgl(struct nvmet_req *req, struct nvmet_sq *sq)
+{
+	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)
+{
+	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;

@@ -336,6 +336,8 @@ 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, struct nvmet_sq *sq);
+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);

@@ -489,7 +489,7 @@ 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);

@@ -638,24 +638,24 @@ 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, &rsp->queue->nvme_sq);
+	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) {

@@ -664,6 +664,10 @@ 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)

@@ -191,6 +191,8 @@ int pci_p2pdma_add_resource(struct pci_dev *pdev, int bar, size_t size,
 	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)) {

@@ -813,3 +815,44 @@ void pci_p2pmem_publish(struct pci_dev *pdev, bool publish)
 	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);

@@ -125,6 +125,7 @@ struct dev_pagemap {
 	struct device *dev;
 	void *data;
 	enum memory_type type;
+	u64 pci_p2pdma_bus_offset;
 };
 
 #ifdef CONFIG_ZONE_DEVICE

@@ -36,6 +36,8 @@ struct scatterlist *pci_p2pmem_alloc_sgl(struct pci_dev *pdev,
 					 unsigned int *nents, u32 length);
 void pci_p2pmem_free_sgl(struct pci_dev *pdev, struct scatterlist *sgl);
 void pci_p2pmem_publish(struct pci_dev *pdev, bool publish);
+int pci_p2pdma_map_sg(struct device *dev, struct scatterlist *sg, int nents,
+		      enum dma_data_direction dir);
 #else /* CONFIG_PCI_P2PDMA */
 static inline int pci_p2pdma_add_resource(struct pci_dev *pdev, int bar,
 		size_t size, u64 offset)

@@ -98,5 +100,10 @@ static inline void pci_p2pmem_free_sgl(struct pci_dev *pdev,
 static inline void pci_p2pmem_publish(struct pci_dev *pdev, bool publish)
 {
 }
+static inline int pci_p2pdma_map_sg(struct device *dev,
+		struct scatterlist *sg, int nents, enum dma_data_direction dir)
+{
+	return 0;
+}
 #endif /* CONFIG_PCI_P2PDMA */
 #endif /* _LINUX_PCI_P2P_H */

@@ -90,6 +90,13 @@ enum nvme_quirks {
 	 * Set MEDIUM priority on SQ creation
 	 */
 	NVME_QUIRK_MEDIUM_PRIO_SQ		= (1 << 7),
+
+	/*
+	 * Pseudo CMB Support on BAR 4. For adapters like the Microsemi
+	 * NVRAM that have CMB-like memory on a BAR but does not set
+	 * CMBLOC or CMBSZ.
+	 */
+	NVME_QUIRK_PSEUDO_CMB_BAR4		= (1 << 8),
 };
 
 /*

@@ -1636,6 +1636,13 @@ static ssize_t nvme_cmb_show(struct device *dev,
 }
 static DEVICE_ATTR(cmb, S_IRUGO, nvme_cmb_show, NULL);
 
+static u32 nvme_pseudo_cmbsz(struct pci_dev *pdev, int bar)
+{
+	return NVME_CMBSZ_WDS | NVME_CMBSZ_RDS |
+		(((ilog2(SZ_16M) - 12) / 4) << NVME_CMBSZ_SZU_SHIFT) |
+		((pci_resource_len(pdev, bar) / SZ_16M) << NVME_CMBSZ_SZ_SHIFT);
+}
+
 static u64 nvme_cmb_size_unit(struct nvme_dev *dev)
 {
 	u8 szu = (dev->cmbsz >> NVME_CMBSZ_SZU_SHIFT) & NVME_CMBSZ_SZU_MASK;

@@ -1655,10 +1662,15 @@ static void nvme_map_cmb(struct nvme_dev *dev)
 	struct pci_dev *pdev = to_pci_dev(dev->dev);
 	int bar;
 
-	dev->cmbsz = readl(dev->bar + NVME_REG_CMBSZ);
-	if (!dev->cmbsz)
-		return;
-	dev->cmbloc = readl(dev->bar + NVME_REG_CMBLOC);
+	if (dev->ctrl.quirks & NVME_QUIRK_PSEUDO_CMB_BAR4) {
+		dev->cmbsz = nvme_pseudo_cmbsz(pdev, 4);
+		dev->cmbloc = 4;
+	} else {
+		dev->cmbsz = readl(dev->bar + NVME_REG_CMBSZ);
+		if (!dev->cmbsz)
+			return;
+		dev->cmbloc = readl(dev->bar + NVME_REG_CMBLOC);
+	}
 
 	size = nvme_cmb_size_unit(dev) * nvme_cmb_size(dev);
 	offset = nvme_cmb_size_unit(dev) * NVME_CMB_OFST(dev->cmbloc);

@@ -2707,6 +2719,10 @@ static const struct pci_device_id nvme_id_table[] = {
 		.driver_data = NVME_QUIRK_LIGHTNVM, },
 	{ PCI_DEVICE(0x1d1d, 0x2601),	/* CNEX Granby */
 		.driver_data = NVME_QUIRK_LIGHTNVM, },
+	{ PCI_DEVICE(0x11f8, 0xf117),	/* Microsemi NVRAM adaptor */
+		.driver_data = NVME_QUIRK_PSEUDO_CMB_BAR4, },
+	{ PCI_DEVICE(0x1db1, 0x0002),	/* Everspin nvNitro adaptor */
+		.driver_data = NVME_QUIRK_PSEUDO_CMB_BAR4,  },
 	{ PCI_DEVICE_CLASS(PCI_CLASS_STORAGE_EXPRESS, 0xffffff) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_APPLE, 0x2001) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_APPLE, 0x2003) },

@@ -9,6 +9,7 @@
  */
 
 #define pr_fmt(fmt) "pci-p2pdma: " fmt
+#include <linux/ctype.h>
 #include <linux/pci-p2pdma.h>
 #include <linux/module.h>
 #include <linux/slab.h>

@@ -856,3 +857,85 @@ int pci_p2pdma_map_sg(struct device *dev, struct scatterlist *sg, int nents,
 	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 'auto', 'none or a boolean isn't the store 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), a boolean, or 'auto'. 'auto' and a true boolean value
+ * have the same meaning. A false value disables p2pdma and
+ * a PCI device enables it to use a specific device as the
+ * backing 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)) {
+			pr_err("PCI device has no peer-to-peer memory: %s\n",
+			       page);
+			pci_dev_put(*p2p_dev);
+			return -ENODEV;
+		}
+
+		return 0;
+	} else if (sysfs_streq(page, "auto")) {
+		*use_p2pdma = true;
+		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, "none\n");
+
+	if (!p2p_dev)
+		return sprintf(page, "auto\n");
+
+	return sprintf(page, "%s\n", pci_name(p2p_dev));
+}
+EXPORT_SYMBOL_GPL(pci_p2pdma_enable_show);

@@ -38,6 +38,10 @@ void pci_p2pmem_free_sgl(struct pci_dev *pdev, struct scatterlist *sgl);
 void pci_p2pmem_publish(struct pci_dev *pdev, bool publish);
 int pci_p2pdma_map_sg(struct device *dev, struct scatterlist *sg, int nents,
 		      enum dma_data_direction dir);
+int pci_p2pdma_enable_store(const char *page, struct pci_dev **p2p_dev,
+			    bool *use_p2pdma);
+ssize_t pci_p2pdma_enable_show(char *page, struct pci_dev *p2p_dev,
+			       bool use_p2pdma);
 #else /* CONFIG_PCI_P2PDMA */
 static inline int pci_p2pdma_add_resource(struct pci_dev *pdev, int bar,
 		size_t size, u64 offset)

@@ -105,5 +109,16 @@ static inline int pci_p2pdma_map_sg(struct device *dev,
 {
 	return 0;
 }
+static inline int pci_p2pdma_enable_store(const char *page,
+		struct pci_dev **p2p_dev, bool *use_p2pdma)
+{
+	*use_p2pdma = false;
+	return 0;
+}
+static inline ssize_t pci_p2pdma_enable_show(char *page,
+		struct pci_dev *p2p_dev, bool use_p2pdma)
+{
+	return sprintf(page, "none\n");
+}
 #endif /* CONFIG_PCI_P2PDMA */
 #endif /* _LINUX_PCI_P2P_H */

@@ -29,7 +29,7 @@ available subsections can be seen below.
    iio/index
    input
    usb/index
-   pci
+   pci/index
    spi
    i2c
    hsi

@@ -0,0 +1,20 @@
+.. SPDX-License-Identifier: GPL-2.0
+============================================
+The Linux PCI driver implementer's API guide
+============================================
+
+.. class:: toc-title
+
+	   Table of contents
+
+.. toctree::
+   :maxdepth: 2
+
+   pci
+
+.. only::  subproject and html
+
+   Indices
+   =======
+
+   * :ref:`genindex`

@@ -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"
 

@@ -1094,6 +1096,37 @@ static void nvmet_port_release(struct config_item *item)
 	kfree(port);
 }
 
+#ifdef CONFIG_PCI_P2PDMA
+static ssize_t nvmet_p2pmem_show(struct config_item *item, char *page)
+{
+	struct nvmet_port *port = to_nvmet_port(item);
+
+	return pci_p2pdma_enable_show(page, port->p2p_dev, port->use_p2pmem);
+}
+
+static ssize_t nvmet_p2pmem_store(struct config_item *item,
+		const char *page, size_t count)
+{
+	struct nvmet_port *port = to_nvmet_port(item);
+	struct pci_dev *p2p_dev = NULL;
+	bool use_p2pmem;
+	int error;
+
+	error = pci_p2pdma_enable_store(page, &p2p_dev, &use_p2pmem);
+	if (error)
+		return error;
+
+	down_write(&nvmet_config_sem);
+	port->use_p2pmem = use_p2pmem;
+	pci_dev_put(port->p2p_dev);
+	port->p2p_dev = p2p_dev;
+	up_write(&nvmet_config_sem);
+
+	return count;
+}
+CONFIGFS_ATTR(nvmet_, p2pmem);
+#endif /* CONFIG_PCI_P2PDMA */
+
 static struct configfs_attribute *nvmet_port_attrs[] = {
 	&nvmet_attr_addr_adrfam,
 	&nvmet_attr_addr_treq,

@@ -1101,6 +1134,9 @@ static struct configfs_attribute *nvmet_port_attrs[] = {
 	&nvmet_attr_addr_trsvcid,
 	&nvmet_attr_addr_trtype,
 	&nvmet_attr_param_inline_data_size,
+#ifdef CONFIG_PCI_P2PDMA
+	&nvmet_attr_p2pmem,
+#endif
 	NULL,
 };
 

@@ -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 +366,29 @@ static void nvmet_ns_dev_disable(struct nvmet_ns *ns)
 	nvmet_file_ns_disable(ns);
 }
 
+static int nvmet_p2pdma_add_client(struct nvmet_ctrl *ctrl,
+		struct nvmet_ns *ns)
+{
+	int ret;
+
+	if (!blk_queue_pci_p2pdma(ns->bdev->bd_queue)) {
+		pr_err("peer-to-peer DMA is not supported by %s\n",
+		       ns->device_path);
+		return -EINVAL;
+	}
+
+	ret = pci_p2pdma_add_client(&ctrl->p2p_clients, nvmet_ns_dev(ns));
+	if (ret)
+		pr_err("failed to add peer-to-peer DMA client %s: %d\n",
+		       ns->device_path, ret);
+
+	return ret;
+}
+
 int nvmet_ns_enable(struct nvmet_ns *ns)
 {
 	struct nvmet_subsys *subsys = ns->subsys;
+	struct nvmet_ctrl *ctrl;
 	int ret;
 
 	mutex_lock(&subsys->lock);

@@ -389,6 +410,14 @@ int nvmet_ns_enable(struct nvmet_ns *ns)
 	if (ret)
 		goto out_dev_put;
 
+	list_for_each_entry(ctrl, &subsys->ctrls, subsys_entry) {
+		if (ctrl->p2p_dev) {
+			ret = nvmet_p2pdma_add_client(ctrl, ns);
+			if (ret)
+				goto out_remove_clients;
+		}
+	}
+
 	if (ns->nsid > subsys->max_nsid)
 		subsys->max_nsid = ns->nsid;
 

@@ -417,6 +446,9 @@ int nvmet_ns_enable(struct nvmet_ns *ns)
 out_unlock:
 	mutex_unlock(&subsys->lock);
 	return ret;
+out_remove_clients:
+	list_for_each_entry(ctrl, &subsys->ctrls, subsys_entry)
+		pci_p2pdma_remove_client(&ctrl->p2p_clients, nvmet_ns_dev(ns));
 out_dev_put:
 	nvmet_ns_dev_disable(ns);
 	goto out_unlock;

@@ -425,6 +457,7 @@ int nvmet_ns_enable(struct nvmet_ns *ns)
 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)

@@ -450,6 +483,12 @@ void nvmet_ns_disable(struct nvmet_ns *ns)
 	percpu_ref_exit(&ns->ref);
 
 	mutex_lock(&subsys->lock);
+
+	list_for_each_entry(ctrl, &subsys->ctrls, subsys_entry) {
+		pci_p2pdma_remove_client(&ctrl->p2p_clients, nvmet_ns_dev(ns));
+		nvmet_add_async_event(ctrl, NVME_AER_TYPE_NOTICE, 0, 0);
+	}
+
 	subsys->nr_namespaces--;
 	nvmet_ns_changed(subsys, ns->nsid);
 	nvmet_ns_dev_disable(ns);

@@ -727,6 +766,23 @@ EXPORT_SYMBOL_GPL(nvmet_req_execute);
 
 int nvmet_req_alloc_sgl(struct nvmet_req *req, struct nvmet_sq *sq)
 {
+	struct pci_dev *p2p_dev = NULL;
+
+	if (IS_ENABLED(CONFIG_PCI_P2PDMA)) {
+		if (sq->ctrl)
+			p2p_dev = sq->ctrl->p2p_dev;
+
+		req->p2p_dev = NULL;
+		if (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;
+			}
+		}
+	}
+
 	req->sg = sgl_alloc(req->transfer_len, GFP_KERNEL, &req->sg_cnt);
 	if (!req->sg)
 		return -ENOMEM;

@@ -737,7 +793,11 @@ EXPORT_SYMBOL_GPL(nvmet_req_alloc_sgl);
 
 void nvmet_req_free_sgl(struct nvmet_req *req)
 {
-	sgl_free(req->sg);
+	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;
 }

@@ -939,6 +999,74 @@ bool nvmet_host_allowed(struct nvmet_req *req, struct nvmet_subsys *subsys,
 		return __nvmet_host_allowed(subsys, hostnqn);
 }
 
+/*
+ * If allow_p2pmem is set, we will try to use P2P memory for the SGL lists for
+ * Ι/O commands. This requires the PCI p2p device to be compatible with the
+ * backing device for every namespace on this controller.
+ */
+static void nvmet_setup_p2pmem(struct nvmet_ctrl *ctrl, struct nvmet_req *req)
+{
+	struct nvmet_ns *ns;
+	int ret;
+
+	if (!req->port->use_p2pmem || !req->p2p_client)
+		return;
+
+	mutex_lock(&ctrl->subsys->lock);
+
+	ret = pci_p2pdma_add_client(&ctrl->p2p_clients, req->p2p_client);
+	if (ret) {
+		pr_err("failed adding peer-to-peer DMA client %s: %d\n",
+		       dev_name(req->p2p_client), ret);
+		goto free_devices;
+	}
+
+	list_for_each_entry_rcu(ns, &ctrl->subsys->namespaces, dev_link) {
+		ret = nvmet_p2pdma_add_client(ctrl, ns);
+		if (ret)
+			goto free_devices;
+	}
+
+	if (req->port->p2p_dev) {
+		if (!pci_p2pdma_assign_provider(req->port->p2p_dev,
+						&ctrl->p2p_clients)) {
+			pr_info("peer-to-peer memory on %s is not supported\n",
+				pci_name(req->port->p2p_dev));
+			goto free_devices;
+		}
+		ctrl->p2p_dev = pci_dev_get(req->port->p2p_dev);
+	} else {
+		ctrl->p2p_dev = pci_p2pmem_find(&ctrl->p2p_clients);
+		if (!ctrl->p2p_dev) {
+			pr_info("no supported peer-to-peer memory devices found\n");
+			goto free_devices;
+		}
+	}
+
+	mutex_unlock(&ctrl->subsys->lock);
+
+	pr_info("using peer-to-peer memory on %s\n", pci_name(ctrl->p2p_dev));
+	return;
+
+free_devices:
+	pci_p2pdma_client_list_free(&ctrl->p2p_clients);
+	mutex_unlock(&ctrl->subsys->lock);
+}
+
+static void nvmet_release_p2pmem(struct nvmet_ctrl *ctrl)
+{
+	if (!ctrl->p2p_dev)
+		return;
+
+	mutex_lock(&ctrl->subsys->lock);
+
+	pci_p2pdma_client_list_free(&ctrl->p2p_clients);
+	pci_dev_put(ctrl->p2p_dev);
+	ctrl->p2p_dev = NULL;
+
+	mutex_unlock(&ctrl->subsys->lock);
+}
+
 u16 nvmet_alloc_ctrl(const char *subsysnqn, const char *hostnqn,
 		struct nvmet_req *req, u32 kato, struct nvmet_ctrl **ctrlp)
 {

@@ -980,6 +1108,7 @@ 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_LIST_HEAD(&ctrl->p2p_clients);
 
 	memcpy(ctrl->subsysnqn, subsysnqn, NVMF_NQN_SIZE);
 	memcpy(ctrl->hostnqn, hostnqn, NVMF_NQN_SIZE);

@@ -1041,6 +1170,7 @@ u16 nvmet_alloc_ctrl(const char *subsysnqn, const char *hostnqn,
 		ctrl->kato = DIV_ROUND_UP(kato, 1000);
 	}
 	nvmet_start_keep_alive_timer(ctrl);
+	nvmet_setup_p2pmem(ctrl, req);
 
 	mutex_lock(&subsys->lock);
 	list_add_tail(&ctrl->subsys_entry, &subsys->ctrls);

@@ -1079,6 +1209,7 @@ static void nvmet_ctrl_free(struct kref *ref)
 	flush_work(&ctrl->async_event_work);
 	cancel_work_sync(&ctrl->fatal_err_work);
 
+	nvmet_release_p2pmem(ctrl);
 	ida_simple_remove(&cntlid_ida, ctrl->cntlid);
 
 	kfree(ctrl->sqs);

@@ -84,6 +84,11 @@ 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 disk_to_dev(ns->bdev->bd_disk);
+}
+
 struct nvmet_cq {
 	u16			qid;
 	u16			size;

@@ -134,6 +139,8 @@ struct nvmet_port {
 	void				*priv;
 	bool				enabled;
 	int				inline_data_size;
+	bool				use_p2pmem;
+	struct pci_dev			*p2p_dev;
 };
 
 static inline struct nvmet_port *to_nvmet_port(struct config_item *item)

@@ -182,6 +189,9 @@ struct nvmet_ctrl {
 	__le32			*changed_ns_list;
 	u32			nr_changed_ns;
 
+	struct pci_dev		*p2p_dev;
+	struct list_head	p2p_clients;
+
 	char			subsysnqn[NVMF_NQN_FIELD_LEN];
 	char			hostnqn[NVMF_NQN_FIELD_LEN];
 };

@@ -294,6 +304,9 @@ 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;

@@ -735,6 +735,8 @@ 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;

@@ -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

@@ -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

@@ -0,0 +1,761 @@
+// 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/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 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;
+
+	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);
+	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;
+
+	percpu_ref_switch_to_atomic_sync(&p2p->devmap_ref);
+
+	error = devm_add_action_or_reset(&pdev->dev, pci_p2pdma_release, pdev);
+	if (error)
+		goto out_pool_destroy;
+
+	pdev->p2pdma = p2p;
+
+	return 0;
+
+out_pool_destroy:
+	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;
+
+	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:
+	devres_free(pgmap);
+	return error;
+}
+EXPORT_SYMBOL_GPL(pci_p2pdma_add_resource);
+
+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 it's 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 *dev)
+{
+	int pos;
+	u16 ctrl;
+
+	pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ACS);
+	if (!pos)
+		return 0;
+
+	pci_read_config_word(dev, 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 *dev)
+{
+	if (!buf)
+		return;
+
+	seq_buf_printf(buf, "%04x:%02x:%02x.%x;", pci_domain_nr(dev->bus),
+		       dev->bus->number, PCI_SLOT(dev->devfn),
+		       PCI_FUNC(dev->devfn));
+}
+
+/*
+ * 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 evenutally 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);
+
+	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\n");
+		/* 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 do not share an upstream bridge\n");
+	}
+
+	kfree(acs_list.buffer);
+
+	return ret;
+}
+
+struct pci_p2pdma_client {
+	struct list_head list;
+	struct pci_dev *client;
+	struct pci_dev *provider;
+};
+
+/**
+ * pci_p2pdma_add_client - allocate a new element in a client device list
+ * @head: list head of p2pdma clients
+ * @dev: device to add to the list
+ *
+ * This adds @dev to a list of clients used by a p2pdma device.
+ * This list should be passed to pci_p2pmem_find(). Once pci_p2pmem_find() has
+ * been called successfully, the list will be bound to a specific p2pdma
+ * device and new clients can only be added to the list if they are
+ * supported by that p2pdma device.
+ *
+ * The caller is expected to have a lock which protects @head as necessary
+ * so that none of the pci_p2p functions can be called concurrently
+ * on that list.
+ *
+ * Returns 0 if the client was successfully added.
+ */
+int pci_p2pdma_add_client(struct list_head *head, struct device *dev)
+{
+	struct pci_p2pdma_client *item, *new_item;
+	struct pci_dev *provider = NULL;
+	struct pci_dev *client;
+	int ret;
+
+	if (IS_ENABLED(CONFIG_DMA_VIRT_OPS) && dev->dma_ops == &dma_virt_ops) {
+		dev_warn(dev, "cannot be used for peer-to-peer DMA because the driver makes use of dma_virt_ops\n");
+		return -ENODEV;
+	}
+
+	client = find_parent_pci_dev(dev);
+	if (!client) {
+		dev_warn(dev, "cannot be used for peer-to-peer DMA as it is not a PCI device\n");
+		return -ENODEV;
+	}
+
+	item = list_first_entry_or_null(head, struct pci_p2pdma_client, list);
+	if (item && item->provider) {
+		provider = item->provider;
+
+		ret = upstream_bridge_distance_warn(provider, client);
+		if (ret < 0) {
+			ret = -EXDEV;
+			goto put_client;
+		}
+	}
+
+	new_item = kzalloc(sizeof(*new_item), GFP_KERNEL);
+	if (!new_item) {
+		ret = -ENOMEM;
+		goto put_client;
+	}
+
+	new_item->client = client;
+	new_item->provider = pci_dev_get(provider);
+
+	list_add_tail(&new_item->list, head);
+
+	return 0;
+
+put_client:
+	pci_dev_put(client);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(pci_p2pdma_add_client);
+
+static void pci_p2pdma_client_free(struct pci_p2pdma_client *item)
+{
+	list_del(&item->list);
+	pci_dev_put(item->client);
+	pci_dev_put(item->provider);
+	kfree(item);
+}
+
+/**
+ * pci_p2pdma_remove_client - remove and free a p2pdma client
+ * @head: list head of p2pdma clients
+ * @dev: device to remove from the list
+ *
+ * This removes @dev from a list of clients used by a p2pdma device.
+ * The caller is expected to have a lock which protects @head as necessary
+ * so that none of the pci_p2p functions can be called concurrently
+ * on that list.
+ */
+void pci_p2pdma_remove_client(struct list_head *head, struct device *dev)
+{
+	struct pci_p2pdma_client *pos, *tmp;
+	struct pci_dev *pdev;
+
+	pdev = find_parent_pci_dev(dev);
+	if (!pdev)
+		return;
+
+	list_for_each_entry_safe(pos, tmp, head, list) {
+		if (pos->client != pdev)
+			continue;
+
+		pci_p2pdma_client_free(pos);
+	}
+
+	pci_dev_put(pdev);
+}
+EXPORT_SYMBOL_GPL(pci_p2pdma_remove_client);
+
+/**
+ * pci_p2pdma_client_list_free - free an entire list of p2pdma clients
+ * @head: list head of p2pdma clients
+ *
+ * This removes all devices in a list of clients used by a p2pdma device.
+ * The caller is expected to have a lock which protects @head as necessary
+ * so that none of the pci_p2pdma functions can be called concurrently
+ * on that list.
+ */
+void pci_p2pdma_client_list_free(struct list_head *head)
+{
+	struct pci_p2pdma_client *pos, *tmp;
+
+	list_for_each_entry_safe(pos, tmp, head, list)
+		pci_p2pdma_client_free(pos);
+}
+EXPORT_SYMBOL_GPL(pci_p2pdma_client_list_free);
+
+/**
+ * pci_p2pdma_distance - Determive the cumulative distance between
+ *	a p2pdma provider and the clients in use.
+ * @provider: p2pdma provider to check against the client list
+ * @clients: list of devices to check (NULL-terminated)
+ * @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
+ * the 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(struct pci_dev *provider, struct list_head *clients,
+			bool verbose)
+{
+	struct pci_p2pdma_client *pos;
+	int ret;
+	int distance = 0;
+	bool not_supported = false;
+
+	if (list_empty(clients))
+		return -1;
+
+	list_for_each_entry(pos, clients, list) {
+		if (verbose)
+			ret = upstream_bridge_distance_warn(provider,
+							    pos->client);
+		else
+			ret = upstream_bridge_distance(provider, pos->client,
+						       NULL);
+
+		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);
+
+/**
+ * pci_p2pdma_assign_provider - Check compatibily (as per pci_p2pdma_distance)
+ *	and assign a provider to a list of clients
+ * @provider: p2pdma provider to assign to the client list
+ * @clients: list of devices to check (NULL-terminated)
+ *
+ * Returns false if any of the clients are not compatible, true if the
+ * provider was successfully assigned to the clients.
+ */
+bool pci_p2pdma_assign_provider(struct pci_dev *provider,
+				struct list_head *clients)
+{
+	struct pci_p2pdma_client *pos;
+
+	if (pci_p2pdma_distance(provider, clients, true) < 0)
+		return false;
+
+	list_for_each_entry(pos, clients, list)
+		pos->provider = provider;
+
+	return true;
+}
+EXPORT_SYMBOL_GPL(pci_p2pdma_assign_provider);
+
+/**
+ * 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: list of devices to check (NULL-terminated)
+ *
+ * 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(struct list_head *clients)
+{
+	struct pci_dev *pdev = NULL;
+	struct pci_p2pdma_client *pos;
+	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);
+
+	while ((pdev = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, pdev))) {
+		if (!pci_has_p2pmem(pdev))
+			continue;
+
+		distance = pci_p2pdma_distance(pdev, 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]);
+
+	if (pdev)
+		list_for_each_entry(pos, clients, list)
+			pos->provider = pdev;
+
+	kfree(closest_pdevs);
+	return pdev;
+}
+EXPORT_SYMBOL_GPL(pci_p2pmem_find);
+
+/**
+ * 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 - allocate 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
+ * @sgl: the allocated scatterlist
+ * @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
+ * @nents: the number of SG entries in the list
+ */
+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 (publish && !pdev->p2pdma)
+		return;
+
+	pdev->p2pdma->p2pmem_published = publish;
+}
+EXPORT_SYMBOL_GPL(pci_p2pmem_publish);