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

Pull rdma updates from Jason Gunthorpe:
 "Usual wide collection of unrelated items in drivers:

   - Driver bug fixes and treewide cleanups in hfi1, siw, qib, mlx5,
     rxe, usnic, usnic, bnxt_re, ocrdma, iser:
       - remove unnecessary NULL checks
       - kmap obsolescence
       - pci_enable_pcie_error_reporting() obsolescence
       - unused variables and macros
       - trace event related warnings
       - casting warnings

   - Code cleanups for irdm and erdma

   - EFA reporting of 128 byte PCIe TLP support

   - mlx5 more agressively uses the out of order HW feature

   - Big rework of how state machines and tasks work in rxe

   - Fix a syzkaller found crash netdev refcount leak in siw

   - bnxt_re revises their HW description header

   - Congestion control for bnxt_re

   - Use mmu_notifiers more safely in hfi1

   - mlx5 gets better support for PCIe relaxed ordering inside VMs"

* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma: (81 commits)
  RDMA/efa: Add rdma write capability to device caps
  RDMA/mlx5: Use correct device num_ports when modify DC
  RDMA/irdma: Drop spurious WQ_UNBOUND from alloc_ordered_workqueue() call
  RDMA/rxe: Fix spinlock recursion deadlock on requester
  RDMA/mlx5: Fix flow counter query via DEVX
  RDMA/rxe: Protect QP state with qp->state_lock
  RDMA/rxe: Move code to check if drained to subroutine
  RDMA/rxe: Remove qp->req.state
  RDMA/rxe: Remove qp->comp.state
  RDMA/rxe: Remove qp->resp.state
  RDMA/mlx5: Allow relaxed ordering read in VFs and VMs
  net/mlx5: Update relaxed ordering read HCA capabilities
  RDMA/mlx5: Check pcie_relaxed_ordering_enabled() in UMR
  RDMA/mlx5: Remove pcie_relaxed_ordering_enabled() check for RO write
  RDMA: Add ib_virt_dma_to_page()
  RDMA/rxe: Fix the error "trying to register non-static key in rxe_cleanup_task"
  RDMA/irdma: Slightly optimize irdma_form_ah_cm_frame()
  RDMA/rxe: Fix incorrect TASKLET_STATE_SCHED check in rxe_task.c
  IB/hfi1: Place struct mmu_rb_handler on cache line start
  IB/hfi1: Fix bugs with non-PAGE_SIZE-end multi-iovec user SDMA requests
  ...

4 files changed, 54 insertions, 10 deletions

diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index b42696d74c9f..dc5e2cb302a5 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -1100,7 +1100,9 @@ struct mlx5_ifc_roce_cap_bits {
 	u8         sw_r_roce_src_udp_port[0x1];
 	u8         fl_rc_qp_when_roce_disabled[0x1];
 	u8         fl_rc_qp_when_roce_enabled[0x1];
-	u8         reserved_at_7[0x17];
+	u8         reserved_at_7[0x1];
+	u8	   qp_ooo_transmit_default[0x1];
+	u8         reserved_at_9[0x15];
 	u8	   qp_ts_format[0x2];
 
 	u8         reserved_at_20[0x60];
@@ -1516,7 +1518,8 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 	u8         reserved_at_b0[0x1];
 	u8         uplink_follow[0x1];
 	u8         ts_cqe_to_dest_cqn[0x1];
-	u8         reserved_at_b3[0x7];
+	u8         reserved_at_b3[0x6];
+	u8         go_back_n[0x1];
 	u8         shampo[0x1];
 	u8         reserved_at_bb[0x5];
 
@@ -1531,7 +1534,7 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 
 	u8         log_max_eq_sz[0x8];
 	u8         relaxed_ordering_write[0x1];
-	u8         relaxed_ordering_read[0x1];
+	u8         relaxed_ordering_read_pci_enabled[0x1];
 	u8         log_max_mkey[0x6];
 	u8         reserved_at_f0[0x6];
 	u8	   terminate_scatter_list_mkey[0x1];
@@ -1747,9 +1750,12 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 
 	u8         reserved_at_320[0x3];
 	u8         log_max_transport_domain[0x5];
-	u8         reserved_at_328[0x3];
+	u8         reserved_at_328[0x2];
+	u8	   relaxed_ordering_read[0x1];
 	u8         log_max_pd[0x5];
-	u8         reserved_at_330[0xb];
+	u8         reserved_at_330[0x9];
+	u8         q_counter_aggregation[0x1];
+	u8         q_counter_other_vport[0x1];
 	u8         log_max_xrcd[0x5];
 
 	u8         nic_receive_steering_discard[0x1];
@@ -3291,7 +3297,8 @@ struct mlx5_ifc_qpc_bits {
 	u8         log_rq_stride[0x3];
 	u8         no_sq[0x1];
 	u8         log_sq_size[0x4];
-	u8         reserved_at_55[0x3];
+	u8         reserved_at_55[0x1];
+	u8	   retry_mode[0x2];
 	u8	   ts_format[0x2];
 	u8         reserved_at_5a[0x1];
 	u8         rlky[0x1];
@@ -5629,10 +5636,15 @@ struct mlx5_ifc_query_q_counter_in_bits {
 	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_at_40[0x80];
+	u8         other_vport[0x1];
+	u8         reserved_at_41[0xf];
+	u8         vport_number[0x10];
+
+	u8         reserved_at_60[0x60];
 
 	u8         clear[0x1];
-	u8         reserved_at_c1[0x1f];
+	u8         aggregate[0x1];
+	u8         reserved_at_c2[0x1e];
 
 	u8         reserved_at_e0[0x18];
 	u8         counter_set_id[0x8];
@@ -9315,7 +9327,8 @@ struct mlx5_ifc_alloc_flow_counter_in_bits {
 	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_at_40[0x38];
+	u8         reserved_at_40[0x33];
+	u8         flow_counter_bulk_log_size[0x5];
 	u8         flow_counter_bulk[0x8];
 };
 
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index 949cf4ffc536..1e7774ac808f 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -4036,6 +4036,31 @@ static inline bool ib_dma_pci_p2p_dma_supported(struct ib_device *dev)
 }
 
 /**
+ * ib_virt_dma_to_ptr - Convert a dma_addr to a kernel pointer
+ * @dma_addr: The DMA address
+ *
+ * Used by ib_uses_virt_dma() devices to get back to the kernel pointer after
+ * going through the dma_addr marshalling.
+ */
+static inline void *ib_virt_dma_to_ptr(u64 dma_addr)
+{
+	/* virt_dma mode maps the kvs's directly into the dma addr */
+	return (void *)(uintptr_t)dma_addr;
+}
+
+/**
+ * ib_virt_dma_to_page - Convert a dma_addr to a struct page
+ * @dma_addr: The DMA address
+ *
+ * Used by ib_uses_virt_dma() device to get back to the struct page after going
+ * through the dma_addr marshalling.
+ */
+static inline struct page *ib_virt_dma_to_page(u64 dma_addr)
+{
+	return virt_to_page(ib_virt_dma_to_ptr(dma_addr));
+}
+
+/**
  * ib_dma_mapping_error - check a DMA addr for error
  * @dev: The device for which the dma_addr was created
  * @dma_addr: The DMA address to check
diff --git a/include/uapi/rdma/bnxt_re-abi.h b/include/uapi/rdma/bnxt_re-abi.h
index b1de99bf56ce..c4e90775da0c 100644
--- a/include/uapi/rdma/bnxt_re-abi.h
+++ b/include/uapi/rdma/bnxt_re-abi.h
@@ -96,6 +96,10 @@ struct bnxt_re_cq_resp {
 	__u32 rsvd;
 };
 
+struct bnxt_re_resize_cq_req {
+	__aligned_u64 cq_va;
+};
+
 struct bnxt_re_qp_req {
 	__aligned_u64 qpsva;
 	__aligned_u64 qprva;
diff --git a/include/uapi/rdma/efa-abi.h b/include/uapi/rdma/efa-abi.h
index 163ac79556d6..d94c32f28804 100644
--- a/include/uapi/rdma/efa-abi.h
+++ b/include/uapi/rdma/efa-abi.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) */
 /*
- * Copyright 2018-2022 Amazon.com, Inc. or its affiliates. All rights reserved.
+ * Copyright 2018-2023 Amazon.com, Inc. or its affiliates. All rights reserved.
  */
 
 #ifndef EFA_ABI_USER_H
@@ -120,6 +120,8 @@ enum {
 	EFA_QUERY_DEVICE_CAPS_RNR_RETRY = 1 << 1,
 	EFA_QUERY_DEVICE_CAPS_CQ_NOTIFICATIONS = 1 << 2,
 	EFA_QUERY_DEVICE_CAPS_CQ_WITH_SGID     = 1 << 3,
+	EFA_QUERY_DEVICE_CAPS_DATA_POLLING_128 = 1 << 4,
+	EFA_QUERY_DEVICE_CAPS_RDMA_WRITE = 1 << 5,
 };
 
 struct efa_ibv_ex_query_device_resp {