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

Pull rdma updates from Jason Gunthorpe:
 "This has been a slightly more active cycle than normal with ongoing
  core changes and quite a lot of collected driver updates.

   - Various driver fixes for bnxt_re, cxgb4, hns, mlx5, pvrdma, rxe

   - A new data transfer mode for HFI1 giving higher performance

   - Significant functional and bug fix update to the mlx5
     On-Demand-Paging MR feature

   - A chip hang reset recovery system for hns

   - Change mm->pinned_vm to an atomic64

   - Update bnxt_re to support a new 57500 chip

   - A sane netlink 'rdma link add' method for creating rxe devices and
     fixing the various unregistration race conditions in rxe's
     unregister flow

   - Allow lookup up objects by an ID over netlink

   - Various reworking of the core to driver interface:
       - drivers should not assume umem SGLs are in PAGE_SIZE chunks
       - ucontext is accessed via udata not other means
       - start to make the core code responsible for object memory
         allocation
       - drivers should convert struct device to struct ib_device via a
         helper
       - drivers have more tools to avoid use after unregister problems"

* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma: (280 commits)
  net/mlx5: ODP support for XRC transport is not enabled by default in FW
  IB/hfi1: Close race condition on user context disable and close
  RDMA/umem: Revert broken 'off by one' fix
  RDMA/umem: minor bug fix in error handling path
  RDMA/hns: Use GFP_ATOMIC in hns_roce_v2_modify_qp
  cxgb4: kfree mhp after the debug print
  IB/rdmavt: Fix concurrency panics in QP post_send and modify to error
  IB/rdmavt: Fix loopback send with invalidate ordering
  IB/iser: Fix dma_nents type definition
  IB/mlx5: Set correct write permissions for implicit ODP MR
  bnxt_re: Clean cq for kernel consumers only
  RDMA/uverbs: Don't do double free of allocated PD
  RDMA: Handle ucontext allocations by IB/core
  RDMA/core: Fix a WARN() message
  bnxt_re: fix the regression due to changes in alloc_pbl
  IB/mlx4: Increase the timeout for CM cache
  IB/core: Abort page fault handler silently during owning process exit
  IB/mlx5: Validate correct PD before prefetch MR
  IB/mlx5: Protect against prefetch of invalid MR
  RDMA/uverbs: Store PR pointer before it is overwritten
  ...

1 files changed, 27 insertions, 14 deletions

diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h
index eedba0d2ec4b..4a617d78eae1 100644
--- a/drivers/infiniband/hw/mlx5/mlx5_ib.h
+++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h
@@ -36,6 +36,7 @@
 #include <linux/kernel.h>
 #include <linux/sched.h>
 #include <rdma/ib_verbs.h>
+#include <rdma/ib_umem.h>
 #include <rdma/ib_smi.h>
 #include <linux/mlx5/driver.h>
 #include <linux/mlx5/cq.h>
@@ -588,14 +589,27 @@ struct mlx5_ib_mr {
 	atomic_t		num_leaf_free;
 	wait_queue_head_t       q_leaf_free;
 	struct mlx5_async_work  cb_work;
+	atomic_t		num_pending_prefetch;
 };
 
+static inline bool is_odp_mr(struct mlx5_ib_mr *mr)
+{
+	return IS_ENABLED(CONFIG_INFINIBAND_ON_DEMAND_PAGING) && mr->umem &&
+	       mr->umem->is_odp;
+}
+
 struct mlx5_ib_mw {
 	struct ib_mw		ibmw;
 	struct mlx5_core_mkey	mmkey;
 	int			ndescs;
 };
 
+struct mlx5_ib_devx_mr {
+	struct mlx5_core_mkey	mmkey;
+	int			ndescs;
+	struct rcu_head		rcu;
+};
+
 struct mlx5_ib_umr_context {
 	struct ib_cqe		cqe;
 	enum ib_wc_status	status;
@@ -624,7 +638,6 @@ struct mlx5_cache_ent {
 	spinlock_t		lock;
 
 
-	struct dentry	       *dir;
 	char                    name[4];
 	u32                     order;
 	u32			xlt;
@@ -636,11 +649,6 @@ struct mlx5_cache_ent {
 	u32                     miss;
 	u32			limit;
 
-	struct dentry          *fsize;
-	struct dentry          *fcur;
-	struct dentry          *fmiss;
-	struct dentry          *flimit;
-
 	struct mlx5_ib_dev     *dev;
 	struct work_struct	work;
 	struct delayed_work	dwork;
@@ -912,7 +920,6 @@ struct mlx5_ib_dev {
 	/* Prevents soft lock on massive reg MRs */
 	struct mutex			slow_path_mutex;
 	int				fill_delay;
-#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
 	struct ib_odp_caps	odp_caps;
 	u64			odp_max_size;
 	struct mlx5_ib_pf_eq	odp_pf_eq;
@@ -923,8 +930,6 @@ struct mlx5_ib_dev {
 	 */
 	struct srcu_struct      mr_srcu;
 	u32			null_mkey;
-	struct workqueue_struct *advise_mr_wq;
-#endif
 	struct mlx5_ib_flow_db	*flow_db;
 	/* protect resources needed as part of reset flow */
 	spinlock_t		reset_flow_resource_lock;
@@ -1034,7 +1039,8 @@ to_mflow_act(struct ib_flow_action *ibact)
 	return container_of(ibact, struct mlx5_ib_flow_action, ib_action);
 }
 
-int mlx5_ib_db_map_user(struct mlx5_ib_ucontext *context, unsigned long virt,
+int mlx5_ib_db_map_user(struct mlx5_ib_ucontext *context,
+			struct ib_udata *udata, unsigned long virt,
 			struct mlx5_db *db);
 void mlx5_ib_db_unmap_user(struct mlx5_ib_ucontext *context, struct mlx5_db *db);
 void __mlx5_ib_cq_clean(struct mlx5_ib_cq *cq, u32 qpn, struct mlx5_ib_srq *srq);
@@ -1069,9 +1075,12 @@ int mlx5_ib_post_send(struct ib_qp *ibqp, const struct ib_send_wr *wr,
 		      const struct ib_send_wr **bad_wr);
 int mlx5_ib_post_recv(struct ib_qp *ibqp, const struct ib_recv_wr *wr,
 		      const struct ib_recv_wr **bad_wr);
-int mlx5_ib_read_user_wqe(struct mlx5_ib_qp *qp, int send, int wqe_index,
-			  void *buffer, u32 length,
-			  struct mlx5_ib_qp_base *base);
+int mlx5_ib_read_user_wqe_sq(struct mlx5_ib_qp *qp, int wqe_index, void *buffer,
+			     int buflen, size_t *bc);
+int mlx5_ib_read_user_wqe_rq(struct mlx5_ib_qp *qp, int wqe_index, void *buffer,
+			     int buflen, size_t *bc);
+int mlx5_ib_read_user_wqe_srq(struct mlx5_ib_srq *srq, int wqe_index,
+			      void *buffer, int buflen, size_t *bc);
 struct ib_cq *mlx5_ib_create_cq(struct ib_device *ibdev,
 				const struct ib_cq_init_attr *attr,
 				struct ib_ucontext *context,
@@ -1097,6 +1106,7 @@ int mlx5_ib_dealloc_mw(struct ib_mw *mw);
 int mlx5_ib_update_xlt(struct mlx5_ib_mr *mr, u64 idx, int npages,
 		       int page_shift, int flags);
 struct mlx5_ib_mr *mlx5_ib_alloc_implicit_mr(struct mlx5_ib_pd *pd,
+					     struct ib_udata *udata,
 					     int access_flags);
 void mlx5_ib_free_implicit_mr(struct mlx5_ib_mr *mr);
 int mlx5_ib_rereg_user_mr(struct ib_mr *ib_mr, int flags, u64 start,
@@ -1214,6 +1224,9 @@ mlx5_ib_advise_mr_prefetch(struct ib_pd *pd,
 {
 	return -EOPNOTSUPP;
 }
+static inline void mlx5_ib_invalidate_range(struct ib_umem_odp *umem_odp,
+					    unsigned long start,
+					    unsigned long end){};
 #endif /* CONFIG_INFINIBAND_ON_DEMAND_PAGING */
 
 /* Needed for rep profile */
@@ -1253,7 +1266,7 @@ __be16 mlx5_get_roce_udp_sport(struct mlx5_ib_dev *dev,
 			       const struct ib_gid_attr *attr);
 
 void mlx5_ib_cleanup_cong_debugfs(struct mlx5_ib_dev *dev, u8 port_num);
-int mlx5_ib_init_cong_debugfs(struct mlx5_ib_dev *dev, u8 port_num);
+void mlx5_ib_init_cong_debugfs(struct mlx5_ib_dev *dev, u8 port_num);
 
 /* GSI QP helper functions */
 struct ib_qp *mlx5_ib_gsi_create_qp(struct ib_pd *pd,