Merge tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma

Pull rdma updates from Jason Gunthorpe:
 "Usual smallish cycle. The NFS biovec work to push it down into RDMA
  instead of indirecting through a scatterlist is pretty nice to see,
  been talked about for a long time now.

   - Various code improvements in irdma, rtrs, qedr, ocrdma, irdma, rxe

   - Small driver improvements and minor bug fixes to hns, mlx5, rxe,
     mana, mlx5, irdma

   - Robusness improvements in completion processing for EFA

   - New query_port_speed() verb to move past limited IBA defined speed
     steps

   - Support for SG_GAPS in rts and many other small improvements

   - Rare list corruption fix in iwcm

   - Better support different page sizes in rxe

   - Device memory support for mana

   - Direct bio vec to kernel MR for use by NFS-RDMA

   - QP rate limiting for bnxt_re

   - Remote triggerable NULL pointer crash in siw

   - DMA-buf exporter support for RDMA mmaps like doorbells"

* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma: (66 commits)
  RDMA/mlx5: Implement DMABUF export ops
  RDMA/uverbs: Add DMABUF object type and operations
  RDMA/uverbs: Support external FD uobjects
  RDMA/siw: Fix potential NULL pointer dereference in header processing
  RDMA/umad: Reject negative data_len in ib_umad_write
  IB/core: Extend rate limit support for RC QPs
  RDMA/mlx5: Support rate limit only for Raw Packet QP
  RDMA/bnxt_re: Report QP rate limit in debugfs
  RDMA/bnxt_re: Report packet pacing capabilities when querying device
  RDMA/bnxt_re: Add support for QP rate limiting
  MAINTAINERS: Drop RDMA files from Hyper-V section
  RDMA/uverbs: Add __GFP_NOWARN to ib_uverbs_unmarshall_recv() kmalloc
  svcrdma: use bvec-based RDMA read/write API
  RDMA/core: add rdma_rw_max_sge() helper for SQ sizing
  RDMA/core: add MR support for bvec-based RDMA operations
  RDMA/core: use IOVA-based DMA mapping for bvec RDMA operations
  RDMA/core: add bio_vec based RDMA read/write API
  RDMA/irdma: Use kvzalloc for paged memory DMA address array
  RDMA/rxe: Fix race condition in QP timer handlers
  RDMA/mana_ib: Add device‑memory support
  ...

include/rdma/ib_verbs.h

@@ -15,6 +15,7 @@
 #include <linux/ethtool.h>
 #include <linux/types.h>
 #include <linux/device.h>
+#include <linux/bvec.h>
 #include <linux/dma-mapping.h>
 #include <linux/kref.h>
 #include <linux/list.h>
@@ -43,6 +44,7 @@
 #include <uapi/rdma/rdma_user_ioctl.h>
 #include <uapi/rdma/ib_user_ioctl_verbs.h>
 #include <linux/pci-tph.h>
+#include <linux/dma-buf.h>
 
 #define IB_FW_VERSION_NAME_MAX	ETHTOOL_FWVERS_LEN
 
@@ -764,6 +766,7 @@ enum ib_event_type {
 	IB_EVENT_CLIENT_REREGISTER,
 	IB_EVENT_GID_CHANGE,
 	IB_EVENT_WQ_FATAL,
+	IB_EVENT_DEVICE_SPEED_CHANGE,
 };
 
 const char *__attribute_const__ ib_event_msg(enum ib_event_type event);
@@ -877,6 +880,20 @@ __attribute_const__ int ib_rate_to_mult(enum ib_rate rate);
  */
 __attribute_const__ int ib_rate_to_mbps(enum ib_rate rate);
 
+struct ib_port_speed_info {
+	const char *str;
+	int rate;	/* in deci-Gb/sec (100 MBps units) */
+};
+
+/**
+ * ib_port_attr_to_speed_info - Convert port attributes to speed information
+ * @attr: Port attributes containing active_speed and active_width
+ * @speed_info: Speed information to return
+ *
+ * Returns 0 on success, -EINVAL on error.
+ */
+int ib_port_attr_to_speed_info(struct ib_port_attr *attr,
+			       struct ib_port_speed_info *speed_info);
 
 /**
  * enum ib_mr_type - memory region type
@@ -2348,6 +2365,9 @@ struct rdma_user_mmap_entry {
 	unsigned long start_pgoff;
 	size_t npages;
 	bool driver_removed;
+	/* protects access to dmabufs */
+	struct mutex dmabufs_lock;
+	struct list_head dmabufs;
 };
 
 /* Return the offset (in bytes) the user should pass to libc's mmap() */
@@ -2403,6 +2423,8 @@ struct ib_device_ops {
 						     int comp_vector);
 	int (*query_port)(struct ib_device *device, u32 port_num,
 			  struct ib_port_attr *port_attr);
+	int (*query_port_speed)(struct ib_device *device, u32 port_num,
+				u64 *speed);
 	int (*modify_port)(struct ib_device *device, u32 port_num,
 			   int port_modify_mask,
 			   struct ib_port_modify *port_modify);
@@ -2483,6 +2505,11 @@ struct ib_device_ops {
 	 * Therefore needs to be implemented by the driver in mmap_free.
 	 */
 	void (*mmap_free)(struct rdma_user_mmap_entry *entry);
+	int (*mmap_get_pfns)(struct rdma_user_mmap_entry *entry,
+			     struct phys_vec *phys_vec,
+			     struct p2pdma_provider **provider);
+	struct rdma_user_mmap_entry *(*pgoff_to_mmap_entry)(struct ib_ucontext *ucontext,
+							    off_t pg_off);
 	void (*disassociate_ucontext)(struct ib_ucontext *ibcontext);
 	int (*alloc_pd)(struct ib_pd *pd, struct ib_udata *udata);
 	int (*dealloc_pd)(struct ib_pd *pd, struct ib_udata *udata);
@@ -4249,6 +4276,47 @@ static inline void ib_dma_unmap_page(struct ib_device *dev,
 		dma_unmap_page(dev->dma_device, addr, size, direction);
 }
 
+/**
+ * ib_dma_map_bvec - Map a bio_vec to DMA address
+ * @dev: The device for which the dma_addr is to be created
+ * @bvec: The bio_vec to map
+ * @direction: The direction of the DMA
+ *
+ * Returns a DMA address for the bio_vec. The caller must check the
+ * result with ib_dma_mapping_error() before use; a failed mapping
+ * must not be passed to ib_dma_unmap_bvec().
+ *
+ * For software RDMA devices (rxe, siw), returns a virtual address
+ * and no actual DMA mapping occurs.
+ */
+static inline u64 ib_dma_map_bvec(struct ib_device *dev,
+				  struct bio_vec *bvec,
+				  enum dma_data_direction direction)
+{
+	if (ib_uses_virt_dma(dev))
+		return (uintptr_t)bvec_virt(bvec);
+	return dma_map_phys(dev->dma_device, bvec_phys(bvec),
+			    bvec->bv_len, direction, 0);
+}
+
+/**
+ * ib_dma_unmap_bvec - Unmap a bio_vec DMA mapping
+ * @dev: The device for which the DMA address was created
+ * @addr: The DMA address returned by ib_dma_map_bvec()
+ * @size: The size of the region in bytes
+ * @direction: The direction of the DMA
+ *
+ * Releases a DMA mapping created by ib_dma_map_bvec(). For software
+ * RDMA devices this is a no-op since no actual mapping occurred.
+ */
+static inline void ib_dma_unmap_bvec(struct ib_device *dev,
+				     u64 addr, size_t size,
+				     enum dma_data_direction direction)
+{
+	if (!ib_uses_virt_dma(dev))
+		dma_unmap_phys(dev->dma_device, addr, size, direction, 0);
+}
+
 int ib_dma_virt_map_sg(struct ib_device *dev, struct scatterlist *sg, int nents);
 static inline int ib_dma_map_sg_attrs(struct ib_device *dev,
 				      struct scatterlist *sg, int nents,
@@ -4545,8 +4613,6 @@ static inline bool ib_device_try_get(struct ib_device *dev)
 void ib_device_put(struct ib_device *device);
 struct ib_device *ib_device_get_by_netdev(struct net_device *ndev,
 					  enum rdma_driver_id driver_id);
-struct ib_device *ib_device_get_by_name(const char *name,
-					enum rdma_driver_id driver_id);
 struct net_device *ib_get_net_dev_by_params(struct ib_device *dev, u32 port,
 					    u16 pkey, const union ib_gid *gid,
 					    const struct sockaddr *addr);

include/rdma/rw.h

@@ -5,6 +5,7 @@
 #ifndef _RDMA_RW_H
 #define _RDMA_RW_H
 
+#include <linux/bvec.h>
 #include <linux/dma-mapping.h>
 #include <linux/scatterlist.h>
 #include <rdma/ib_verbs.h>
@@ -31,6 +32,14 @@ struct rdma_rw_ctx {
 			struct ib_rdma_wr	*wrs;
 		} map;
 
+		/* for IOVA-based mapping of bvecs into contiguous DMA range: */
+		struct {
+			struct dma_iova_state	state;
+			struct ib_sge		sge;
+			struct ib_rdma_wr	wr;
+			size_t			mapped_len;
+		} iova;
+
 		/* for registering multiple WRs: */
 		struct rdma_rw_reg_ctx {
 			struct ib_sge		sge;
@@ -38,6 +47,7 @@ struct rdma_rw_ctx {
 			struct ib_reg_wr	reg_wr;
 			struct ib_send_wr	inv_wr;
 			struct ib_mr		*mr;
+			struct sg_table		sgt;
 		} *reg;
 	};
 };
@@ -49,6 +59,16 @@ void rdma_rw_ctx_destroy(struct rdma_rw_ctx *ctx, struct ib_qp *qp,
 			 u32 port_num, struct scatterlist *sg, u32 sg_cnt,
 			 enum dma_data_direction dir);
 
+struct bio_vec;
+
+int rdma_rw_ctx_init_bvec(struct rdma_rw_ctx *ctx, struct ib_qp *qp,
+		u32 port_num, const struct bio_vec *bvecs, u32 nr_bvec,
+		struct bvec_iter iter, u64 remote_addr, u32 rkey,
+		enum dma_data_direction dir);
+void rdma_rw_ctx_destroy_bvec(struct rdma_rw_ctx *ctx, struct ib_qp *qp,
+		u32 port_num, const struct bio_vec *bvecs, u32 nr_bvec,
+		enum dma_data_direction dir);
+
 int rdma_rw_ctx_signature_init(struct rdma_rw_ctx *ctx, struct ib_qp *qp,
 		u32 port_num, struct scatterlist *sg, u32 sg_cnt,
 		struct scatterlist *prot_sg, u32 prot_sg_cnt,
@@ -66,6 +86,8 @@ int rdma_rw_ctx_post(struct rdma_rw_ctx *ctx, struct ib_qp *qp, u32 port_num,
 
 unsigned int rdma_rw_mr_factor(struct ib_device *device, u32 port_num,
 		unsigned int maxpages);
+unsigned int rdma_rw_max_send_wr(struct ib_device *dev, u32 port_num,
+		unsigned int max_rdma_ctxs, u32 create_flags);
 void rdma_rw_init_qp(struct ib_device *dev, struct ib_qp_init_attr *attr);
 int rdma_rw_init_mrs(struct ib_qp *qp, struct ib_qp_init_attr *attr);
 void rdma_rw_cleanup_mrs(struct ib_qp *qp);

include/rdma/uverbs_types.h

@@ -186,6 +186,7 @@ struct ib_uverbs_file {
 extern const struct uverbs_obj_type_class uverbs_idr_class;
 extern const struct uverbs_obj_type_class uverbs_fd_class;
 int uverbs_uobject_fd_release(struct inode *inode, struct file *filp);
+int uverbs_uobject_release(struct ib_uobject *uobj);
 
 #define UVERBS_BUILD_BUG_ON(cond) (sizeof(char[1 - 2 * !!(cond)]) -	\
 				   sizeof(char))