[PATCH v3 01/11] PCI/P2PDMA: Support peer-to-peer memory

[Logan Gunthorpe]

Some PCI devices may have memory mapped in a BAR space that's
intended for use in peer-to-peer transactions. In order to enable
such transactions the memory must be registered with ZONE_DEVICE pages
so it can be used by DMA interfaces in existing drivers.

Add an interface for other subsystems to find and allocate chunks of P2P
memory as necessary to facilitate transfers between two PCI peers:

int pci_p2pdma_add_client();
struct pci_dev *pci_p2pmem_find();
void *pci_alloc_p2pmem();

The new interface requires a driver to collect a list of client devices
involved in the transaction with the pci_p2pmem_add_client*() functions
then call pci_p2pmem_find() to obtain any suitable P2P memory. Once
this is done the list is bound to the memory and the calling driver is
free to add and remove clients as necessary (adding incompatible clients
will fail). With a suitable p2pmem device, memory can then be
allocated with pci_alloc_p2pmem() for use in DMA transactions.

Depending on hardware, using peer-to-peer memory may reduce the bandwidth
of the transfer but would significantly reduce pressure on system memory.
This may be desirable in many cases: for example a system could be designed
with a small CPU connected to a PCI switch by a small number of lanes
which would maximize the number of lanes available to connect to NVME
devices.

The code is designed to only utilize the p2pmem device if all the devices
involved in a transfer are behind the same PCI switch. This is because
we have no way of knowing whether peer-to-peer routing between PCIe
Root Ports is supported (PCIe r4.0, sec 1.3.1). Additionally, the
benefits of P2P transfers that go through the RC is limited to only
reducing DRAM usage and, in some cases, coding convienence.

This commit includes significant rework and feedback from Christoph
Hellwig.

Signed-off-by: Christoph Hellwig <hch@xxxxxx>
Signed-off-by: Logan Gunthorpe <logang@xxxxxxxxxxxx>
---
 drivers/pci/Kconfig        |  16 ++
 drivers/pci/Makefile       |   1 +
 drivers/pci/p2pdma.c       | 679 +++++++++++++++++++++++++++++++++++++++++++++
 include/linux/memremap.h   |  18 ++
 include/linux/pci-p2pdma.h | 101 +++++++
 include/linux/pci.h        |   4 +
 6 files changed, 819 insertions(+)
 create mode 100644 drivers/pci/p2pdma.c
 create mode 100644 include/linux/pci-p2pdma.h

diff --git a/drivers/pci/Kconfig b/drivers/pci/Kconfig
index 34b56a8f8480..d59f6f5ddfcd 100644
--- a/drivers/pci/Kconfig
+++ b/drivers/pci/Kconfig
@@ -124,6 +124,22 @@ config PCI_PASID
 
 	  If unsure, say N.
 
+config PCI_P2PDMA
+	bool "PCI peer-to-peer transfer support"
+	depends on ZONE_DEVICE
+	select GENERIC_ALLOCATOR
+	help
+	  EnableÑ 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 you
+	  will need a PCIe switch.
+
+	  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 941970936840..45e0ff6f3213 100644
--- a/drivers/pci/Makefile
+++ b/drivers/pci/Makefile
@@ -26,6 +26,7 @@ obj-$(CONFIG_PCI_MSI) += msi.o
 
 obj-$(CONFIG_PCI_ATS) += ats.o
 obj-$(CONFIG_PCI_IOV) += iov.o
+obj-$(CONFIG_PCI_P2PDMA) += p2pdma.o
 
 #
 # ACPI Related PCI FW Functions
diff --git a/drivers/pci/p2pdma.c b/drivers/pci/p2pdma.c
new file mode 100644
index 000000000000..0ee917381dce
--- /dev/null
+++ b/drivers/pci/p2pdma.c
@@ -0,0 +1,679 @@
+// 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.
+ *
+ */
+
+#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>
+
+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;
+}
+
+/*
+ * If a device is behind a switch, we try to find the upstream bridge
+ * port of the switch. This requires two calls to pci_upstream_bridge():
+ * one for the upstream port on the switch, one on the upstream port
+ * for the next level in the hierarchy. Because of this, devices connected
+ * to the root port will be rejected.
+ */
+static struct pci_dev *get_upstream_bridge_port(struct pci_dev *pdev)
+{
+	struct pci_dev *up1, *up2;
+
+	if (!pdev)
+		return NULL;
+
+	up1 = pci_dev_get(pci_upstream_bridge(pdev));
+	if (!up1)
+		return NULL;
+
+	up2 = pci_dev_get(pci_upstream_bridge(up1));
+	pci_dev_put(up1);
+
+	return up2;
+}
+
+/*
+ * This function checks if two PCI devices are behind the same switch.
+ * (ie. they share the same second upstream port as returned by
+ *  get_upstream_bridge_port().)
+ *
+ * Future work could expand this to handle hierarchies of switches
+ * so any devices whose traffic can be routed without going through
+ * the root complex could be used. For now, we limit it to just one
+ * level of switch.
+ *
+ * This function returns the "distance" between the devices. 0 meaning
+ * they are the same device, 1 meaning they are behind the same switch.
+ * If they are not behind the same switch, -1 is returned.
+ */
+static int __upstream_bridges_match(struct pci_dev *upstream,
+				    struct pci_dev *client)
+{
+	struct pci_dev *dma_up;
+	int ret = 1;
+
+	dma_up = get_upstream_bridge_port(client);
+
+	if (!dma_up) {
+		dev_dbg(&client->dev, "not a PCI device behind a bridge\n");
+		ret = -1;
+		goto out;
+	}
+
+	if (upstream != dma_up) {
+		dev_dbg(&client->dev,
+			"does not reside on the same upstream bridge\n");
+		ret = -1;
+		goto out;
+	}
+
+out:
+	pci_dev_put(dma_up);
+	return ret;
+}
+
+static int upstream_bridges_match(struct pci_dev *provider,
+				  struct pci_dev *client)
+{
+	struct pci_dev *upstream;
+	int ret;
+
+	if (provider == client)
+		return 0;
+
+	upstream = get_upstream_bridge_port(provider);
+	if (!upstream) {
+		pci_warn(provider, "not behind a PCI bridge\n");
+		return -1;
+	}
+
+	ret = __upstream_bridges_match(upstream, client);
+
+	pci_dev_put(upstream);
+
+	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;
+
+		if (upstream_bridges_match(provider, client) < 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 new 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)
+ *
+ * Returns -1 if any of the clients are not compatible (behind the same
+ * switch 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 switch. This cuts out cases that may work but is safest for the
+ * user. Future work can expand this to cases with nested switches.
+ */
+int pci_p2pdma_distance(struct pci_dev *provider, struct list_head *clients)
+{
+	struct pci_p2pdma_client *pos;
+	struct pci_dev *upstream;
+	int ret;
+	int distance = 0;
+
+	upstream = get_upstream_bridge_port(provider);
+	if (!upstream) {
+		pci_warn(provider, "not behind a PCI bridge\n");
+		return false;
+	}
+
+	list_for_each_entry(pos, clients, list) {
+		if (pos->client == provider)
+			continue;
+
+		ret = __upstream_bridges_match(upstream, pos->client);
+		if (ret < 0)
+			goto no_match;
+
+		distance += ret;
+	}
+
+	ret = distance;
+
+no_match:
+	pci_dev_put(upstream);
+	return ret;
+}
+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) < 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 ties = 0;
+	const int max_ties = 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);
+		if (distance < 0 || distance > closest_distance)
+			continue;
+
+		if (distance == closest_distance && ties >= max_ties)
+			continue;
+
+		if (distance < closest_distance) {
+			for (i = 0; i < ties; i++)
+				pci_dev_put(closest_pdevs[i]);
+
+			ties = 0;
+			closest_distance = distance;
+		}
+
+		closest_pdevs[ties++] = pci_dev_get(pdev);
+	}
+
+	if (ties)
+		pdev = pci_dev_get(closest_pdevs[prandom_u32_max(ties)]);
+
+	for (i = 0; i < ties; 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
+ */
+int pci_p2pmem_alloc_sgl(struct pci_dev *pdev, struct scatterlist **sgl,
+			 unsigned int *nents, u32 length)
+{
+	struct scatterlist *sg;
+	void *addr;
+
+	sg = kzalloc(sizeof(*sg), GFP_KERNEL);
+	if (!sg)
+		return -ENOMEM;
+
+	sg_init_table(sg, 1);
+
+	addr = pci_alloc_p2pmem(pdev, length);
+	if (!addr)
+		goto out_free_sg;
+
+	sg_set_buf(sg, addr, length);
+	*sgl = sg;
+	*nents = 1;
+	return 0;
+
+out_free_sg:
+	kfree(sg);
+	return -ENOMEM;
+}
+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,
+			 unsigned int nents)
+{
+	struct scatterlist *sg;
+	int count;
+
+	if (!sgl || !nents)
+		return;
+
+	for_each_sg(sgl, sg, nents, count)
+		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
+ */
+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);
diff --git a/include/linux/memremap.h b/include/linux/memremap.h
index 7b4899c06f49..9e907c338a44 100644
--- a/include/linux/memremap.h
+++ b/include/linux/memremap.h
@@ -53,11 +53,16 @@ struct vmem_altmap {
  * driver can hotplug the device memory using ZONE_DEVICE and with that memory
  * type. Any page of a process can be migrated to such memory. However no one
  * should be allow to pin such memory so that it can always be evicted.
+ *
+ * MEMORY_DEVICE_PCI_P2PDMA:
+ * Device memory residing in a PCI BAR intended for use with Peer-to-Peer
+ * transactions.
  */
 enum memory_type {
 	MEMORY_DEVICE_HOST = 0,
 	MEMORY_DEVICE_PRIVATE,
 	MEMORY_DEVICE_PUBLIC,
+	MEMORY_DEVICE_PCI_P2PDMA,
 };
 
 /*
@@ -161,6 +166,19 @@ static inline void vmem_altmap_free(struct vmem_altmap *altmap,
 }
 #endif /* CONFIG_ZONE_DEVICE */
 
+#ifdef CONFIG_PCI_P2PDMA
+static inline bool is_pci_p2pdma_page(const struct page *page)
+{
+	return is_zone_device_page(page) &&
+		page->pgmap->type == MEMORY_DEVICE_PCI_P2PDMA;
+}
+#else /* CONFIG_PCI_P2PDMA */
+static inline bool is_pci_p2pdma_page(const struct page *page)
+{
+	return false;
+}
+#endif /* CONFIG_PCI_P2PDMA */
+
 #if defined(CONFIG_DEVICE_PRIVATE) || defined(CONFIG_DEVICE_PUBLIC)
 static inline bool is_device_private_page(const struct page *page)
 {
diff --git a/include/linux/pci-p2pdma.h b/include/linux/pci-p2pdma.h
new file mode 100644
index 000000000000..1f7856ff098b
--- /dev/null
+++ b/include/linux/pci-p2pdma.h
@@ -0,0 +1,101 @@
+/* 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.
+ *
+ */
+
+#ifndef _LINUX_PCI_P2PDMA_H
+#define _LINUX_PCI_P2PDMA_H
+
+#include <linux/pci.h>
+
+struct block_device;
+struct scatterlist;
+
+#ifdef CONFIG_PCI_P2PDMA
+int pci_p2pdma_add_resource(struct pci_dev *pdev, int bar, size_t size,
+		u64 offset);
+int pci_p2pdma_add_client(struct list_head *head, struct device *dev);
+void pci_p2pdma_remove_client(struct list_head *head, struct device *dev);
+void pci_p2pdma_client_list_free(struct list_head *head);
+int pci_p2pdma_distance(struct pci_dev *provider, struct list_head *clients);
+bool pci_p2pdma_assign_provider(struct pci_dev *provider,
+				struct list_head *clients);
+bool pci_has_p2pmem(struct pci_dev *pdev);
+struct pci_dev *pci_p2pmem_find(struct list_head *clients);
+void *pci_alloc_p2pmem(struct pci_dev *pdev, size_t size);
+void pci_free_p2pmem(struct pci_dev *pdev, void *addr, size_t size);
+pci_bus_addr_t pci_p2pmem_virt_to_bus(struct pci_dev *pdev, void *addr);
+int pci_p2pmem_alloc_sgl(struct pci_dev *pdev, struct scatterlist **sgl,
+		unsigned int *nents, u32 length);
+void pci_p2pmem_free_sgl(struct pci_dev *pdev, struct scatterlist *sgl,
+		unsigned int nents);
+void pci_p2pmem_publish(struct pci_dev *pdev, bool publish);
+#else /* CONFIG_PCI_P2PDMA */
+static inline int pci_p2pdma_add_resource(struct pci_dev *pdev, int bar,
+		size_t size, u64 offset)
+{
+	return 0;
+}
+static inline int pci_p2pdma_add_client(struct list_head *head,
+		struct device *dev)
+{
+	return 0;
+}
+static inline void pci_p2pdma_remove_client(struct list_head *head,
+		struct device *dev)
+{
+}
+static inline void pci_p2pdma_client_list_free(struct list_head *head)
+{
+}
+static inline int pci_p2pdma_distance(struct pci_dev *provider,
+				      struct list_head *clients)
+{
+	return -1;
+}
+static inline bool pci_p2pdma_assign_provider(struct pci_dev *provider,
+					      struct list_head *clients)
+{
+	return false;
+}
+static inline bool pci_has_p2pmem(struct pci_dev *pdev)
+{
+	return false;
+}
+static inline struct pci_dev *pci_p2pmem_find(struct list_head *clients)
+{
+	return NULL;
+}
+static inline void *pci_alloc_p2pmem(struct pci_dev *pdev, size_t size)
+{
+	return NULL;
+}
+static inline void pci_free_p2pmem(struct pci_dev *pdev, void *addr,
+		size_t size)
+{
+}
+static inline pci_bus_addr_t pci_p2pmem_virt_to_bus(struct pci_dev *pdev,
+						    void *addr)
+{
+	return 0;
+}
+static inline int pci_p2pmem_alloc_sgl(struct pci_dev *pdev,
+		struct scatterlist **sgl, unsigned int *nents, u32 length)
+{
+	return -ENODEV;
+}
+static inline void pci_p2pmem_free_sgl(struct pci_dev *pdev,
+		struct scatterlist *sgl, unsigned int nents)
+{
+}
+static inline void pci_p2pmem_publish(struct pci_dev *pdev, bool publish)
+{
+}
+#endif /* CONFIG_PCI_P2PDMA */
+#endif /* _LINUX_PCI_P2P_H */
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 024a1beda008..437e42615896 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -276,6 +276,7 @@ struct pcie_link_state;
 struct pci_vpd;
 struct pci_sriov;
 struct pci_ats;
+struct pci_p2pdma;
 
 /* The pci_dev structure describes PCI devices */
 struct pci_dev {
@@ -429,6 +430,9 @@ struct pci_dev {
 #ifdef CONFIG_PCI_PASID
 	u16		pasid_features;
 #endif
+#ifdef CONFIG_PCI_P2PDMA
+	struct pci_p2pdma *p2pdma;
+#endif
 	phys_addr_t	rom;		/* Physical address if not from BAR */
 	size_t		romlen;		/* Length if not from BAR */
 	char		*driver_override; /* Driver name to force a match */
-- 
2.11.0