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

Pull rdma updates from Jason Gunthorpe:
 "A smaller cycle this time. Notably we see another new driver, 'Soft
  iWarp', and the deletion of an ancient unused driver for nes.

   - Revise and simplify the signature offload RDMA MR APIs

   - More progress on hoisting object allocation boiler plate code out
     of the drivers

   - Driver bug fixes and revisions for hns, hfi1, efa, cxgb4, qib,
     i40iw

   - Tree wide cleanups: struct_size, put_user_page, xarray, rst doc
     conversion

   - Removal of obsolete ib_ucm chardev and nes driver

   - netlink based discovery of chardevs and autoloading of the modules
     providing them

   - Move more of the rdamvt/hfi1 uapi to include/uapi/rdma

   - New driver 'siw' for software based iWarp running on top of netdev,
     much like rxe's software RoCE.

   - mlx5 feature to report events in their raw devx format to userspace

   - Expose per-object counters through rdma tool

   - Adaptive interrupt moderation for RDMA (DIM), sharing the DIM core
     from netdev"

* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma: (194 commits)
  RMDA/siw: Require a 64 bit arch
  RDMA/siw: Mark expected switch fall-throughs
  RDMA/core: Fix -Wunused-const-variable warnings
  rdma/siw: Remove set but not used variable 's'
  rdma/siw: Add missing dependencies on LIBCRC32C and DMA_VIRT_OPS
  RDMA/siw: Add missing rtnl_lock around access to ifa
  rdma/siw: Use proper enumerated type in map_cqe_status
  RDMA/siw: Remove unnecessary kthread create/destroy printouts
  IB/rdmavt: Fix variable shadowing issue in rvt_create_cq
  RDMA/core: Fix race when resolving IP address
  RDMA/core: Make rdma_counter.h compile stand alone
  IB/core: Work on the caller socket net namespace in nldev_newlink()
  RDMA/rxe: Fill in wc byte_len with IB_WC_RECV_RDMA_WITH_IMM
  RDMA/mlx5: Set RDMA DIM to be enabled by default
  RDMA/nldev: Added configuration of RDMA dynamic interrupt moderation to netlink
  RDMA/core: Provide RDMA DIM support for ULPs
  linux/dim: Implement RDMA adaptive moderation (DIM)
  IB/mlx5: Report correctly tag matching rendezvous capability
  docs: infiniband: add it to the driver-api bookset
  IB/mlx5: Implement VHCA tunnel mechanism in DEVX
  ...

include/linux/dim.h

@@ -82,6 +82,7 @@ struct dim_stats {
  * @prev_stats: Measured rates from previous iteration (for comparison)
  * @start_sample: Sampled data at start of current iteration
  * @work: Work to perform on action required
+ * @priv: A pointer to the struct that points to dim
  * @profile_ix: Current moderation profile
  * @mode: CQ period count mode
  * @tune_state: Algorithm tuning state (see below)
@@ -95,6 +96,7 @@ struct dim {
 	struct dim_sample start_sample;
 	struct dim_sample measuring_sample;
 	struct work_struct work;
+	void *priv;
 	u8 profile_ix;
 	u8 mode;
 	u8 tune_state;
@@ -363,4 +365,25 @@ struct dim_cq_moder net_dim_get_def_tx_moderation(u8 cq_period_mode);
  */
 void net_dim(struct dim *dim, struct dim_sample end_sample);
 
+/* RDMA DIM */
+
+/*
+ * RDMA DIM profile:
+ * profile size must be of RDMA_DIM_PARAMS_NUM_PROFILES.
+ */
+#define RDMA_DIM_PARAMS_NUM_PROFILES 9
+#define RDMA_DIM_START_PROFILE 0
+
+/**
+ * rdma_dim - Runs the adaptive moderation.
+ * @dim: The moderation struct.
+ * @completions: The number of completions collected in this round.
+ *
+ * Each call to rdma_dim takes the latest amount of completions that
+ * have been collected and counts them as a new event.
+ * Once enough events have been collected the algorithm decides a new
+ * moderation level.
+ */
+void rdma_dim(struct dim *dim, u64 completions);
+
 #endif /* DIM_H */

include/linux/mlx5/mlx5_ifc.h

@@ -1391,7 +1391,9 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 	u8	   reserved_at_6c8[0x28];
 	u8	   sf_base_id[0x10];
 
-	u8	   reserved_at_700[0x100];
+	u8	   reserved_at_700[0x80];
+	u8	   vhca_tunnel_commands[0x40];
+	u8	   reserved_at_7c0[0x40];
 };
 
 enum mlx5_flow_destination_type {
@@ -9695,7 +9697,7 @@ struct mlx5_ifc_general_obj_in_cmd_hdr_bits {
 	u8         opcode[0x10];
 	u8         uid[0x10];
 
-	u8         reserved_at_20[0x10];
+	u8         vhca_tunnel_id[0x10];
 	u8         obj_type[0x10];
 
 	u8         obj_id[0x20];

include/linux/mlx5/qp.h

@@ -37,7 +37,8 @@
 #include <linux/mlx5/driver.h>
 
 #define MLX5_INVALID_LKEY	0x100
-#define MLX5_SIG_WQE_SIZE	(MLX5_SEND_WQE_BB * 5)
+/* UMR (3 WQE_BB's) + SIG (3 WQE_BB's) + PSV (mem) + PSV (wire) */
+#define MLX5_SIG_WQE_SIZE	(MLX5_SEND_WQE_BB * 8)
 #define MLX5_DIF_SIZE		8
 #define MLX5_STRIDE_BLOCK_OP	0x400
 #define MLX5_CPY_GRD_MASK	0xc0
@@ -70,6 +71,7 @@ enum mlx5_qp_optpar {
 	MLX5_QP_OPTPAR_CQN_RCV			= 1 << 19,
 	MLX5_QP_OPTPAR_DC_HS			= 1 << 20,
 	MLX5_QP_OPTPAR_DC_KEY			= 1 << 21,
+	MLX5_QP_OPTPAR_COUNTER_SET_ID		= 1 << 25,
 };
 
 enum mlx5_qp_state {