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

5 files changed, 145 insertions, 0 deletions

diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 6980014357d4..c32f7171899b 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -699,6 +699,7 @@ struct request_queue {
 #define QUEUE_FLAG_SCSI_PASSTHROUGH 27	/* queue supports SCSI commands */
 #define QUEUE_FLAG_QUIESCED    28	/* queue has been quiesced */
 #define QUEUE_FLAG_PREEMPT_ONLY	29	/* only process REQ_PREEMPT requests */
+#define QUEUE_FLAG_PCI_P2PDMA  30	/* device supports PCI p2p requests */
 
 #define QUEUE_FLAG_DEFAULT	((1 << QUEUE_FLAG_IO_STAT) |		\
 				 (1 << QUEUE_FLAG_SAME_COMP)	|	\
@@ -731,6 +732,8 @@ bool blk_queue_flag_test_and_clear(unsigned int flag, struct request_queue *q);
 #define blk_queue_dax(q)	test_bit(QUEUE_FLAG_DAX, &(q)->queue_flags)
 #define blk_queue_scsi_passthrough(q)	\
 	test_bit(QUEUE_FLAG_SCSI_PASSTHROUGH, &(q)->queue_flags)
+#define blk_queue_pci_p2pdma(q)	\
+	test_bit(QUEUE_FLAG_PCI_P2PDMA, &(q)->queue_flags)
 
 #define blk_noretry_request(rq) \
 	((rq)->cmd_flags & (REQ_FAILFAST_DEV|REQ_FAILFAST_TRANSPORT| \
diff --git a/include/linux/memremap.h b/include/linux/memremap.h
index f91f9e763557..0ac69ddf5fc4 100644
--- a/include/linux/memremap.h
+++ b/include/linux/memremap.h
@@ -53,11 +53,16 @@ struct vmem_altmap {
  * wakeup event whenever a page is unpinned and becomes idle. This
  * wakeup is used to coordinate physical address space management (ex:
  * fs truncate/hole punch) vs pinned pages (ex: device dma).
+ *
+ * MEMORY_DEVICE_PCI_P2PDMA:
+ * Device memory residing in a PCI BAR intended for use with Peer-to-Peer
+ * transactions.
  */
 enum memory_type {
 	MEMORY_DEVICE_PRIVATE = 1,
 	MEMORY_DEVICE_PUBLIC,
 	MEMORY_DEVICE_FS_DAX,
+	MEMORY_DEVICE_PCI_P2PDMA,
 };
 
 /*
@@ -120,6 +125,7 @@ struct dev_pagemap {
 	struct device *dev;
 	void *data;
 	enum memory_type type;
+	u64 pci_p2pdma_bus_offset;
 };
 
 #ifdef CONFIG_ZONE_DEVICE
diff --git a/include/linux/mm.h b/include/linux/mm.h
index a61ebe8ad4ca..2055df412a77 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -890,6 +890,19 @@ static inline bool is_device_public_page(const struct page *page)
 		page->pgmap->type == MEMORY_DEVICE_PUBLIC;
 }
 
+#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 */
+
 #else /* CONFIG_DEV_PAGEMAP_OPS */
 static inline void dev_pagemap_get_ops(void)
 {
@@ -913,6 +926,11 @@ static inline bool is_device_public_page(const struct page *page)
 {
 	return false;
 }
+
+static inline bool is_pci_p2pdma_page(const struct page *page)
+{
+	return false;
+}
 #endif /* CONFIG_DEV_PAGEMAP_OPS */
 
 static inline void get_page(struct page *page)
diff --git a/include/linux/pci-p2pdma.h b/include/linux/pci-p2pdma.h
new file mode 100644
index 000000000000..bca9bc3e5be7
--- /dev/null
+++ b/include/linux/pci-p2pdma.h
@@ -0,0 +1,114 @@
+/* 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_distance_many(struct pci_dev *provider, struct device **clients,
+			     int num_clients, bool verbose);
+bool pci_has_p2pmem(struct pci_dev *pdev);
+struct pci_dev *pci_p2pmem_find_many(struct device **clients, int num_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);
+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);
+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)
+{
+	return -EOPNOTSUPP;
+}
+static inline int pci_p2pdma_distance_many(struct pci_dev *provider,
+	struct device **clients, int num_clients, bool verbose)
+{
+	return -1;
+}
+static inline bool pci_has_p2pmem(struct pci_dev *pdev)
+{
+	return false;
+}
+static inline struct pci_dev *pci_p2pmem_find_many(struct device **clients,
+						   int num_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 struct scatterlist *pci_p2pmem_alloc_sgl(struct pci_dev *pdev,
+		unsigned int *nents, u32 length)
+{
+	return NULL;
+}
+static inline void pci_p2pmem_free_sgl(struct pci_dev *pdev,
+		struct scatterlist *sgl)
+{
+}
+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;
+}
+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 */
+
+
+static inline int pci_p2pdma_distance(struct pci_dev *provider,
+	struct device *client, bool verbose)
+{
+	return pci_p2pdma_distance_many(provider, &client, 1, verbose);
+}
+
+static inline struct pci_dev *pci_p2pmem_find(struct device *client)
+{
+	return pci_p2pmem_find_many(&client, 1);
+}
+
+#endif /* _LINUX_PCI_P2P_H */
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 7c4802de1e3a..f9e04c170301 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -281,6 +281,7 @@ 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 {
@@ -441,6 +442,9 @@ 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 */