Merge tag 'rds-odp-for-5.5' of https://git.kernel.org/pub/scm/linux/kernel/git/leon/linux-rdma

Leon Romanovsky says:

====================
Use ODP MRs for kernel ULPs

The following series extends MR creation routines to allow creation of
user MRs through kernel ULPs as a proxy. The immediate use case is to
allow RDS to work over FS-DAX, which requires ODP (on-demand-paging)
MRs to be created and such MRs were not possible to create prior this
series.

The first part of this patchset extends RDMA to have special verb
ib_reg_user_mr(). The common use case that uses this function is a
userspace application that allocates memory for HCA access but the
responsibility to register the memory at the HCA is on an kernel ULP.
This ULP acts as an agent for the userspace application.

The second part provides advise MR functionality for ULPs. This is
integral part of ODP flows and used to trigger pagefaults in advance
to prepare memory before running working set.

The third part is actual user of those in-kernel APIs.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 33 insertions, 18 deletions

diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index 90489c5f0c6f..904d508cc823 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -815,6 +815,7 @@ static int mlx5_ib_query_device(struct ib_device *ibdev,
 				struct ib_device_attr *props,
 				struct ib_udata *uhw)
 {
+	size_t uhw_outlen = (uhw) ? uhw->outlen : 0;
 	struct mlx5_ib_dev *dev = to_mdev(ibdev);
 	struct mlx5_core_dev *mdev = dev->mdev;
 	int err = -ENOMEM;
@@ -828,12 +829,12 @@ static int mlx5_ib_query_device(struct ib_device *ibdev,
 	u64 max_tso;
 
 	resp_len = sizeof(resp.comp_mask) + sizeof(resp.response_length);
-	if (uhw->outlen && uhw->outlen < resp_len)
+	if (uhw_outlen && uhw_outlen < resp_len)
 		return -EINVAL;
 
 	resp.response_length = resp_len;
 
-	if (uhw->inlen && !ib_is_udata_cleared(uhw, 0, uhw->inlen))
+	if (uhw && uhw->inlen && !ib_is_udata_cleared(uhw, 0, uhw->inlen))
 		return -EINVAL;
 
 	memset(props, 0, sizeof(*props));
@@ -897,7 +898,7 @@ static int mlx5_ib_query_device(struct ib_device *ibdev,
 			props->raw_packet_caps |=
 				IB_RAW_PACKET_CAP_CVLAN_STRIPPING;
 
-		if (field_avail(typeof(resp), tso_caps, uhw->outlen)) {
+		if (field_avail(typeof(resp), tso_caps, uhw_outlen)) {
 			max_tso = MLX5_CAP_ETH(mdev, max_lso_cap);
 			if (max_tso) {
 				resp.tso_caps.max_tso = 1 << max_tso;
@@ -907,7 +908,7 @@ static int mlx5_ib_query_device(struct ib_device *ibdev,
 			}
 		}
 
-		if (field_avail(typeof(resp), rss_caps, uhw->outlen)) {
+		if (field_avail(typeof(resp), rss_caps, uhw_outlen)) {
 			resp.rss_caps.rx_hash_function =
 						MLX5_RX_HASH_FUNC_TOEPLITZ;
 			resp.rss_caps.rx_hash_fields_mask =
@@ -927,9 +928,9 @@ static int mlx5_ib_query_device(struct ib_device *ibdev,
 			resp.response_length += sizeof(resp.rss_caps);
 		}
 	} else {
-		if (field_avail(typeof(resp), tso_caps, uhw->outlen))
+		if (field_avail(typeof(resp), tso_caps, uhw_outlen))
 			resp.response_length += sizeof(resp.tso_caps);
-		if (field_avail(typeof(resp), rss_caps, uhw->outlen))
+		if (field_avail(typeof(resp), rss_caps, uhw_outlen))
 			resp.response_length += sizeof(resp.rss_caps);
 	}
 
@@ -1014,6 +1015,23 @@ static int mlx5_ib_query_device(struct ib_device *ibdev,
 		if (dev->odp_caps.general_caps & IB_ODP_SUPPORT)
 			props->device_cap_flags |= IB_DEVICE_ON_DEMAND_PAGING;
 		props->odp_caps = dev->odp_caps;
+		if (!uhw) {
+			/* ODP for kernel QPs is not implemented for receive
+			 * WQEs and SRQ WQEs
+			 */
+			props->odp_caps.per_transport_caps.rc_odp_caps &=
+				~(IB_ODP_SUPPORT_READ |
+				  IB_ODP_SUPPORT_SRQ_RECV);
+			props->odp_caps.per_transport_caps.uc_odp_caps &=
+				~(IB_ODP_SUPPORT_READ |
+				  IB_ODP_SUPPORT_SRQ_RECV);
+			props->odp_caps.per_transport_caps.ud_odp_caps &=
+				~(IB_ODP_SUPPORT_READ |
+				  IB_ODP_SUPPORT_SRQ_RECV);
+			props->odp_caps.per_transport_caps.xrc_odp_caps &=
+				~(IB_ODP_SUPPORT_READ |
+				  IB_ODP_SUPPORT_SRQ_RECV);
+		}
 	}
 
 	if (MLX5_CAP_GEN(mdev, cd))
@@ -1054,7 +1072,7 @@ static int mlx5_ib_query_device(struct ib_device *ibdev,
 						MLX5_MAX_CQ_PERIOD;
 	}
 
-	if (field_avail(typeof(resp), cqe_comp_caps, uhw->outlen)) {
+	if (field_avail(typeof(resp), cqe_comp_caps, uhw_outlen)) {
 		resp.response_length += sizeof(resp.cqe_comp_caps);
 
 		if (MLX5_CAP_GEN(dev->mdev, cqe_compression)) {
@@ -1072,7 +1090,7 @@ static int mlx5_ib_query_device(struct ib_device *ibdev,
 		}
 	}
 
-	if (field_avail(typeof(resp), packet_pacing_caps, uhw->outlen) &&
+	if (field_avail(typeof(resp), packet_pacing_caps, uhw_outlen) &&
 	    raw_support) {
 		if (MLX5_CAP_QOS(mdev, packet_pacing) &&
 		    MLX5_CAP_GEN(mdev, qos)) {
@@ -1091,7 +1109,7 @@ static int mlx5_ib_query_device(struct ib_device *ibdev,
 	}
 
 	if (field_avail(typeof(resp), mlx5_ib_support_multi_pkt_send_wqes,
-			uhw->outlen)) {
+			uhw_outlen)) {
 		if (MLX5_CAP_ETH(mdev, multi_pkt_send_wqe))
 			resp.mlx5_ib_support_multi_pkt_send_wqes =
 				MLX5_IB_ALLOW_MPW;
@@ -1104,7 +1122,7 @@ static int mlx5_ib_query_device(struct ib_device *ibdev,
 			sizeof(resp.mlx5_ib_support_multi_pkt_send_wqes);
 	}
 
-	if (field_avail(typeof(resp), flags, uhw->outlen)) {
+	if (field_avail(typeof(resp), flags, uhw_outlen)) {
 		resp.response_length += sizeof(resp.flags);
 
 		if (MLX5_CAP_GEN(mdev, cqe_compression_128))
@@ -1120,8 +1138,7 @@ static int mlx5_ib_query_device(struct ib_device *ibdev,
 		resp.flags |= MLX5_IB_QUERY_DEV_RESP_FLAGS_SCAT2CQE_DCT;
 	}
 
-	if (field_avail(typeof(resp), sw_parsing_caps,
-			uhw->outlen)) {
+	if (field_avail(typeof(resp), sw_parsing_caps, uhw_outlen)) {
 		resp.response_length += sizeof(resp.sw_parsing_caps);
 		if (MLX5_CAP_ETH(mdev, swp)) {
 			resp.sw_parsing_caps.sw_parsing_offloads |=
@@ -1141,7 +1158,7 @@ static int mlx5_ib_query_device(struct ib_device *ibdev,
 		}
 	}
 
-	if (field_avail(typeof(resp), striding_rq_caps, uhw->outlen) &&
+	if (field_avail(typeof(resp), striding_rq_caps, uhw_outlen) &&
 	    raw_support) {
 		resp.response_length += sizeof(resp.striding_rq_caps);
 		if (MLX5_CAP_GEN(mdev, striding_rq)) {
@@ -1164,8 +1181,7 @@ static int mlx5_ib_query_device(struct ib_device *ibdev,
 		}
 	}
 
-	if (field_avail(typeof(resp), tunnel_offloads_caps,
-			uhw->outlen)) {
+	if (field_avail(typeof(resp), tunnel_offloads_caps, uhw_outlen)) {
 		resp.response_length += sizeof(resp.tunnel_offloads_caps);
 		if (MLX5_CAP_ETH(mdev, tunnel_stateless_vxlan))
 			resp.tunnel_offloads_caps |=
@@ -1186,7 +1202,7 @@ static int mlx5_ib_query_device(struct ib_device *ibdev,
 				MLX5_IB_TUNNELED_OFFLOADS_MPLS_UDP;
 	}
 
-	if (uhw->outlen) {
+	if (uhw_outlen) {
 		err = ib_copy_to_udata(uhw, &resp, resp.response_length);
 
 		if (err)
@@ -4773,7 +4789,6 @@ static int __get_port_caps(struct mlx5_ib_dev *dev, u8 port)
 	struct ib_device_attr *dprops = NULL;
 	struct ib_port_attr *pprops = NULL;
 	int err = -ENOMEM;
-	struct ib_udata uhw = {.inlen = 0, .outlen = 0};
 
 	pprops = kzalloc(sizeof(*pprops), GFP_KERNEL);
 	if (!pprops)
@@ -4783,7 +4798,7 @@ static int __get_port_caps(struct mlx5_ib_dev *dev, u8 port)
 	if (!dprops)
 		goto out;
 
-	err = mlx5_ib_query_device(&dev->ib_dev, dprops, &uhw);
+	err = mlx5_ib_query_device(&dev->ib_dev, dprops, NULL);
 	if (err) {
 		mlx5_ib_warn(dev, "query_device failed %d\n", err);
 		goto out;