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

Pull rdma updates from Jason Gunthorpe:
 "Usual collection of small improvements and fixes, nothing especially
  stands out to me here.

  The new multipath PCI feature is a sign of things to come, I think we
  will see more of this in the next 10 years. Broadcom and HNS continue
  to update their drivers for their new HW generations.

  Summary:

   - Bug fixes and minor improvments in cxgb4, siw, mlx5, rxe, efa, rts,
     hfi, erdma, hns, irdma

   - Code cleanups/typos/etc. Tidy alloc_ordered_workqueue() calls

   - Multipath PCI for mlx5

   - Variable size work queue, SRQ changes, and relaxed ordering for new
     bnxt HW

   - New ODP fault resolution FW protocol in mlx5

   - New 'rdma monitor' netlink mechanism"

* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma: (99 commits)
  RDMA/bnxt_re: Remove the unused variable en_dev
  RDMA/nldev: Add missing break in rdma_nl_notify_err_msg()
  RDMA/irdma: fix error message in irdma_modify_qp_roce()
  RDMA/cxgb4: Added NULL check for lookup_atid
  RDMA/hns: Fix ah error counter in sw stat not increasing
  RDMA/bnxt_re: Recover the device when FW error is detected
  RDMA/bnxt_re: Group all operations under add_device and remove_device
  RDMA/bnxt_re: Use the aux device for L2 ULP callbacks
  RDMA/bnxt_re: Change aux driver data to en_info to hold more information
  RDMA/nldev: Expose whether RDMA monitoring is supported
  RDMA/nldev: Add support for RDMA monitoring
  RDMA/mlx5: Use IB set_netdev and get_netdev functions
  RDMA/device: Remove optimization in ib_device_get_netdev()
  RDMA/mlx5: Initialize phys_port_cnt earlier in RDMA device creation
  RDMA/mlx5: Obtain upper net device only when needed
  RDMA/mlx5: Check RoCE LAG status before getting netdev
  RDMA/mlx5: Consider the query_vuid cap for data_direct
  net/mlx5: Handle memory scheme ODP capabilities
  RDMA/mlx5: Add implicit MR handling to ODP memory scheme
  RDMA/mlx5: Add handling for memory scheme page fault events
  ...

1 files changed, 30 insertions, 1 deletions

diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h
index d0f7d1f36c5e..cc647992f3d1 100644
--- a/include/linux/mlx5/device.h
+++ b/include/linux/mlx5/device.h
@@ -211,6 +211,7 @@ enum {
 enum {
 	MLX5_PFAULT_SUBTYPE_WQE = 0,
 	MLX5_PFAULT_SUBTYPE_RDMA = 1,
+	MLX5_PFAULT_SUBTYPE_MEMORY = 2,
 };
 
 enum wqe_page_fault_type {
@@ -370,6 +371,7 @@ enum mlx5_driver_event {
 	MLX5_DRIVER_EVENT_SF_PEER_DEVLINK,
 	MLX5_DRIVER_EVENT_AFFILIATION_DONE,
 	MLX5_DRIVER_EVENT_AFFILIATION_REMOVED,
+	MLX5_DRIVER_EVENT_ACTIVE_BACKUP_LAG_CHANGE_LOWERSTATE,
 };
 
 enum {
@@ -646,10 +648,11 @@ struct mlx5_eqe_page_req {
 	__be32		rsvd1[5];
 };
 
+#define MEMORY_SCHEME_PAGE_FAULT_GRANULARITY 4096
 struct mlx5_eqe_page_fault {
-	__be32 bytes_committed;
 	union {
 		struct {
+			__be32  bytes_committed;
 			u16     reserved1;
 			__be16  wqe_index;
 			u16	reserved2;
@@ -659,6 +662,7 @@ struct mlx5_eqe_page_fault {
 			__be32  pftype_wq;
 		} __packed wqe;
 		struct {
+			__be32  bytes_committed;
 			__be32  r_key;
 			u16	reserved1;
 			__be16  packet_length;
@@ -666,6 +670,23 @@ struct mlx5_eqe_page_fault {
 			__be64  rdma_va;
 			__be32  pftype_token;
 		} __packed rdma;
+		struct {
+			u8      flags;
+			u8      reserved1;
+			__be16  post_demand_fault_pages;
+			__be16  pre_demand_fault_pages;
+			__be16  token47_32;
+			__be32  token31_0;
+			/*
+			 * FW changed from specifying the fault size in byte
+			 * count to 4k pages granularity. The size specified
+			 * in pages uses bits 31:12, to keep backward
+			 * compatibility.
+			 */
+			__be32 demand_fault_pages;
+			__be32  mkey;
+			__be64  va;
+		} __packed memory;
 	} __packed;
 } __packed;
 
@@ -1370,6 +1391,14 @@ enum mlx5_qcam_feature_groups {
 #define MLX5_CAP_ODP(mdev, cap)\
 	MLX5_GET(odp_cap, mdev->caps.hca[MLX5_CAP_ODP]->cur, cap)
 
+#define MLX5_CAP_ODP_SCHEME(mdev, cap)                                \
+	(MLX5_GET(odp_cap, mdev->caps.hca[MLX5_CAP_ODP]->cur,         \
+		  mem_page_fault) ?                                   \
+		 MLX5_GET(odp_cap, mdev->caps.hca[MLX5_CAP_ODP]->cur, \
+			  memory_page_fault_scheme_cap.cap) :         \
+		 MLX5_GET(odp_cap, mdev->caps.hca[MLX5_CAP_ODP]->cur, \
+			  transport_page_fault_scheme_cap.cap))
+
 #define MLX5_CAP_ODP_MAX(mdev, cap)\
 	MLX5_GET(odp_cap, mdev->caps.hca[MLX5_CAP_ODP]->max, cap)