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

Pull rdma updates from Jason Gunthorpe:
 "A quiet cycle after the larger 5.8 effort. Substantially cleanup and
  driver work with a few smaller features this time.

   - Driver updates for hfi1, rxe, mlx5, hns, qedr, usnic, bnxt_re

   - Removal of dead or redundant code across the drivers

   - RAW resource tracker dumps to include a device specific data blob
     for device objects to aide device debugging

   - Further advance the IOCTL interface, remove the ability to turn it
     off. Add QUERY_CONTEXT, QUERY_MR, and QUERY_PD commands

   - Remove stubs related to devices with no pkey table

   - A shared CQ scheme to allow multiple ULPs to share the CQ rings of
     a device to give higher performance

   - Several more static checker, syzkaller and rare crashers fixed"

* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma: (121 commits)
  RDMA/mlx5: Fix flow destination setting for RDMA TX flow table
  RDMA/rxe: Remove pkey table
  RDMA/umem: Add a schedule point in ib_umem_get()
  RDMA/hns: Fix the unneeded process when getting a general type of CQE error
  RDMA/hns: Fix error during modify qp RTS2RTS
  RDMA/hns: Delete unnecessary memset when allocating VF resource
  RDMA/hns: Remove redundant parameters in set_rc_wqe()
  RDMA/hns: Remove support for HIP08_A
  RDMA/hns: Refactor hns_roce_v2_set_hem()
  RDMA/hns: Remove redundant hardware opcode definitions
  RDMA/netlink: Remove CAP_NET_RAW check when dump a raw QP
  RDMA/include: Replace license text with SPDX tags
  RDMA/rtrs: remove WQ_MEM_RECLAIM for rtrs_wq
  RDMA/rtrs-clt: add an additional random 8 seconds before reconnecting
  RDMA/cma: Execute rdma_cm destruction from a handler properly
  RDMA/cma: Remove unneeded locking for req paths
  RDMA/cma: Using the standard locking pattern when delivering the removal event
  RDMA/cma: Simplify DEVICE_REMOVAL for internal_id
  RDMA/efa: Add EFA 0xefa1 PCI ID
  RDMA/efa: User/kernel compatibility handshake mechanism
  ...

drivers/infiniband/hw/mlx5/odp.c

@@ -816,6 +816,7 @@ static int pagefault_mr(struct mlx5_ib_mr *mr, u64 io_virt, size_t bcnt,
 {
 	struct ib_umem_odp *odp = to_ib_umem_odp(mr->umem);
 
+	lockdep_assert_held(&mr->dev->odp_srcu);
 	if (unlikely(io_virt < mr->mmkey.iova))
 		return -EFAULT;
 
@@ -929,11 +930,6 @@ next_mr:
 		if (ret < 0)
 			goto srcu_unlock;
 
-		/*
-		 * When prefetching a page, page fault is generated
-		 * in order to bring the page to the main memory.
-		 * In the current flow, page faults are being counted.
-		 */
 		mlx5_update_odp_stats(mr, faults, ret);
 
 		npages += ret;
@@ -1770,13 +1766,26 @@ static void mlx5_ib_prefetch_mr_work(struct work_struct *w)
 {
 	struct prefetch_mr_work *work =
 		container_of(w, struct prefetch_mr_work, work);
+	struct mlx5_ib_dev *dev;
 	u32 bytes_mapped = 0;
+	int srcu_key;
+	int ret;
 	u32 i;
 
-	for (i = 0; i < work->num_sge; ++i)
-		pagefault_mr(work->frags[i].mr, work->frags[i].io_virt,
-			     work->frags[i].length, &bytes_mapped,
-			     work->pf_flags);
+	/* We rely on IB/core that work is executed if we have num_sge != 0 only. */
+	WARN_ON(!work->num_sge);
+	dev = work->frags[0].mr->dev;
+	/* SRCU should be held when calling to mlx5_odp_populate_xlt() */
+	srcu_key = srcu_read_lock(&dev->odp_srcu);
+	for (i = 0; i < work->num_sge; ++i) {
+		ret = pagefault_mr(work->frags[i].mr, work->frags[i].io_virt,
+				   work->frags[i].length, &bytes_mapped,
+				   work->pf_flags);
+		if (ret <= 0)
+			continue;
+		mlx5_update_odp_stats(work->frags[i].mr, prefetch, ret);
+	}
+	srcu_read_unlock(&dev->odp_srcu, srcu_key);
 
 	destroy_prefetch_work(work);
 }
@@ -1832,6 +1841,7 @@ static int mlx5_ib_prefetch_sg_list(struct ib_pd *pd,
 				   &bytes_mapped, pf_flags);
 		if (ret < 0)
 			goto out;
+		mlx5_update_odp_stats(mr, prefetch, ret);
 	}
 	ret = 0;