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

Pull main rdma updates from Doug Ledford:
 "This is the main pull request for the rdma stack this release.  The
  code has been through 0day and I had it tagged for linux-next testing
  for a couple days.

  Summary:

   - updates to mlx5

   - updates to mlx4 (two conflicts, both minor and easily resolved)

   - updates to iw_cxgb4 (one conflict, not so obvious to resolve,
     proper resolution is to keep the code in cxgb4_main.c as it is in
     Linus' tree as attach_uld was refactored and moved into
     cxgb4_uld.c)

   - improvements to uAPI (moved vendor specific API elements to uAPI
     area)

   - add hns-roce driver and hns and hns-roce ACPI reset support

   - conversion of all rdma code away from deprecated
     create_singlethread_workqueue

   - security improvement: remove unsafe ib_get_dma_mr (breaks lustre in
     staging)"

* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/dledford/rdma: (75 commits)
  staging/lustre: Disable InfiniBand support
  iw_cxgb4: add fast-path for small REG_MR operations
  cxgb4: advertise support for FR_NSMR_TPTE_WR
  IB/core: correctly handle rdma_rw_init_mrs() failure
  IB/srp: Fix infinite loop when FMR sg[0].offset != 0
  IB/srp: Remove an unused argument
  IB/core: Improve ib_map_mr_sg() documentation
  IB/mlx4: Fix possible vl/sl field mismatch in LRH header in QP1 packets
  IB/mthca: Move user vendor structures
  IB/nes: Move user vendor structures
  IB/ocrdma: Move user vendor structures
  IB/mlx4: Move user vendor structures
  IB/cxgb4: Move user vendor structures
  IB/cxgb3: Move user vendor structures
  IB/mlx5: Move and decouple user vendor structures
  IB/{core,hw}: Add constant for node_desc
  ipoib: Make ipoib_warn ratelimited
  IB/mlx4/alias_GUID: Remove deprecated create_singlethread_workqueue
  IB/ipoib_verbs: Remove deprecated create_singlethread_workqueue
  IB/ipoib: Remove deprecated create_singlethread_workqueue
  ...

drivers/infiniband/hw/cxgb4/t4.h

@@ -95,6 +95,7 @@ union t4_wr {
 	struct fw_ri_rdma_read_wr read;
 	struct fw_ri_bind_mw_wr bind;
 	struct fw_ri_fr_nsmr_wr fr;
+	struct fw_ri_fr_nsmr_tpte_wr fr_tpte;
 	struct fw_ri_inv_lstag_wr inv;
 	struct t4_status_page status;
 	__be64 flits[T4_EQ_ENTRY_SIZE / sizeof(__be64) * T4_SQ_NUM_SLOTS];
@@ -170,7 +171,7 @@ struct t4_cqe {
 			__be32 msn;
 		} rcqe;
 		struct {
-			u32 nada1;
+			u32 stag;
 			u16 nada2;
 			u16 cidx;
 		} scqe;
@@ -232,6 +233,7 @@ struct t4_cqe {
 
 /* used for SQ completion processing */
 #define CQE_WRID_SQ_IDX(x)	((x)->u.scqe.cidx)
+#define CQE_WRID_FR_STAG(x)     (be32_to_cpu((x)->u.scqe.stag))
 
 /* generic accessor macros */
 #define CQE_WRID_HI(x)		(be32_to_cpu((x)->u.gen.wrid_hi))