From cfc1a89e449c02207952c72a4c0394691fdedf43 Mon Sep 17 00:00:00 2001
From: Maor Gottlieb <maorg@mellanox.com>
Date: Thu, 30 Apr 2020 22:21:46 +0300
Subject: RDMA/mlx5: Set lag tx affinity according to slave

The patch sets the lag tx affinity of the data QPs and the GSI QPs
according to the LAG xmit slave.

For GSI QPs, in case the link layer is Ethenet (RoCE) we create two GSI
QPs, one for each physical port. When the driver selects the GSI QP, it
will consider the port affinity result.  For connected QPs, the driver
sets the affinity of the xmit slave.

The above, ensures that RC QP and it's corresponding GSI QP will transmit
from the same physical port.

Link: https://lore.kernel.org/r/20200430192146.12863-17-maorg@mellanox.com
Signed-off-by: Maor Gottlieb <maorg@mellanox.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
---
 include/linux/mlx5/mlx5_ifc.h | 4 +++-
 include/linux/mlx5/qp.h       | 2 ++
 2 files changed, 5 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index fb243848132d..c1ba89198335 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -1321,7 +1321,9 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 	u8         stat_rate_support[0x10];
 	u8         reserved_at_1f0[0x1];
 	u8         pci_sync_for_fw_update_event[0x1];
-	u8         reserved_at_1f2[0xa];
+	u8         reserved_at_1f2[0x6];
+	u8         init2_lag_tx_port_affinity[0x1];
+	u8         reserved_at_1fa[0x3];
 	u8         cqe_version[0x4];
 
 	u8         compact_address_vector[0x1];
diff --git a/include/linux/mlx5/qp.h b/include/linux/mlx5/qp.h
index f23eb18526fe..b9facdb9b9bd 100644
--- a/include/linux/mlx5/qp.h
+++ b/include/linux/mlx5/qp.h
@@ -66,6 +66,7 @@ enum mlx5_qp_optpar {
 	MLX5_QP_OPTPAR_RETRY_COUNT		= 1 << 12,
 	MLX5_QP_OPTPAR_RNR_RETRY		= 1 << 13,
 	MLX5_QP_OPTPAR_ACK_TIMEOUT		= 1 << 14,
+	MLX5_QP_OPTPAR_LAG_TX_AFF		= 1 << 15,
 	MLX5_QP_OPTPAR_PRI_PORT			= 1 << 16,
 	MLX5_QP_OPTPAR_SRQN			= 1 << 18,
 	MLX5_QP_OPTPAR_CQN_RCV			= 1 << 19,
@@ -321,6 +322,7 @@ struct mlx5_av {
 struct mlx5_ib_ah {
 	struct ib_ah		ibah;
 	struct mlx5_av		av;
+	u8			xmit_port;
 };
 
 static inline struct mlx5_ib_ah *to_mah(struct ib_ah *ibah)
-- 
cgit v1.2.3-71-gd317


From f18e26af6aba778b888044859d9c69bb9bbc7bc1 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Tue, 26 May 2020 14:54:38 +0300
Subject: RDMA/mlx5: Convert modify QP to use MLX5_SET macros

Instead of hand crafted mlx5_qp_context and mlx5_qp_path use common
MLX5_SET() macros.

Link: https://lore.kernel.org/r/20200526115440.205922-7-leon@kernel.org
Reviewed-by: Maor Gottlieb <maorg@mellanox.com>
Reviewed-by: Mark Zhang <markz@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
---
 drivers/infiniband/hw/mlx5/qp.c | 203 +++++++++++++++++++---------------------
 include/linux/mlx5/qp.h         |  66 -------------
 2 files changed, 97 insertions(+), 172 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c
index 5099866533dd..a24176a8ec83 100644
--- a/drivers/infiniband/hw/mlx5/qp.c
+++ b/drivers/infiniband/hw/mlx5/qp.c
@@ -3028,14 +3028,13 @@ int mlx5_ib_destroy_qp(struct ib_qp *qp, struct ib_udata *udata)
 	return 0;
 }
 
-static int to_mlx5_access_flags(struct mlx5_ib_qp *qp,
-				const struct ib_qp_attr *attr,
-				int attr_mask, __be32 *hw_access_flags_be)
+static int set_qpc_atomic_flags(struct mlx5_ib_qp *qp,
+				const struct ib_qp_attr *attr, int attr_mask,
+				void *qpc)
 {
-	u8 dest_rd_atomic;
-	u32 access_flags, hw_access_flags = 0;
-
 	struct mlx5_ib_dev *dev = to_mdev(qp->ibqp.device);
+	u8 dest_rd_atomic;
+	u32 access_flags;
 
 	if (attr_mask & IB_QP_MAX_DEST_RD_ATOMIC)
 		dest_rd_atomic = attr->max_dest_rd_atomic;
@@ -3050,8 +3049,8 @@ static int to_mlx5_access_flags(struct mlx5_ib_qp *qp,
 	if (!dest_rd_atomic)
 		access_flags &= IB_ACCESS_REMOTE_WRITE;
 
-	if (access_flags & IB_ACCESS_REMOTE_READ)
-		hw_access_flags |= MLX5_QP_BIT_RRE;
+	MLX5_SET(qpc, qpc, rre, !!(access_flags & IB_ACCESS_REMOTE_READ));
+
 	if (access_flags & IB_ACCESS_REMOTE_ATOMIC) {
 		int atomic_mode;
 
@@ -3059,15 +3058,11 @@ static int to_mlx5_access_flags(struct mlx5_ib_qp *qp,
 		if (atomic_mode < 0)
 			return -EOPNOTSUPP;
 
-		hw_access_flags |= MLX5_QP_BIT_RAE;
-		hw_access_flags |= atomic_mode << MLX5_ATOMIC_MODE_OFFSET;
+		MLX5_SET(qpc, qpc, rae, 1);
+		MLX5_SET(qpc, qpc, atomic_mode, atomic_mode);
 	}
 
-	if (access_flags & IB_ACCESS_REMOTE_WRITE)
-		hw_access_flags |= MLX5_QP_BIT_RWE;
-
-	*hw_access_flags_be = cpu_to_be32(hw_access_flags);
-
+	MLX5_SET(qpc, qpc, rwe, !!(access_flags & IB_ACCESS_REMOTE_WRITE));
 	return 0;
 }
 
@@ -3147,26 +3142,22 @@ static int modify_raw_packet_tx_affinity(struct mlx5_core_dev *dev,
 	return err;
 }
 
-static void mlx5_set_path_udp_sport(struct mlx5_qp_path *path,
-				    const struct rdma_ah_attr *ah,
+static void mlx5_set_path_udp_sport(void *path, const struct rdma_ah_attr *ah,
 				    u32 lqpn, u32 rqpn)
 
 {
 	u32 fl = ah->grh.flow_label;
-	u16 sport;
 
 	if (!fl)
 		fl = rdma_calc_flow_label(lqpn, rqpn);
 
-	sport = rdma_flow_label_to_udp_sport(fl);
-	path->udp_sport = cpu_to_be16(sport);
+	MLX5_SET(ads, path, udp_sport, rdma_flow_label_to_udp_sport(fl));
 }
 
 static int mlx5_set_path(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp,
-			 const struct rdma_ah_attr *ah,
-			 struct mlx5_qp_path *path, u8 port, int attr_mask,
-			 u32 path_flags, const struct ib_qp_attr *attr,
-			 bool alt)
+			 const struct rdma_ah_attr *ah, void *path, u8 port,
+			 int attr_mask, u32 path_flags,
+			 const struct ib_qp_attr *attr, bool alt)
 {
 	const struct ib_global_route *grh = rdma_ah_read_grh(ah);
 	int err;
@@ -3175,8 +3166,8 @@ static int mlx5_set_path(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp,
 	u8 sl = rdma_ah_get_sl(ah);
 
 	if (attr_mask & IB_QP_PKEY_INDEX)
-		path->pkey_index = cpu_to_be16(alt ? attr->alt_pkey_index :
-						     attr->pkey_index);
+		MLX5_SET(ads, path, pkey_index,
+			 alt ? attr->alt_pkey_index : attr->pkey_index);
 
 	if (ah_flags & IB_AH_GRH) {
 		if (grh->sgid_index >=
@@ -3192,7 +3183,8 @@ static int mlx5_set_path(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp,
 		if (!(ah_flags & IB_AH_GRH))
 			return -EINVAL;
 
-		memcpy(path->rmac, ah->roce.dmac, sizeof(ah->roce.dmac));
+		ether_addr_copy(MLX5_ADDR_OF(ads, path, rmac_47_32),
+				ah->roce.dmac);
 		if ((qp->ibqp.qp_type == IB_QPT_RC ||
 		     qp->ibqp.qp_type == IB_QPT_UC ||
 		     qp->ibqp.qp_type == IB_QPT_XRC_INI ||
@@ -3202,38 +3194,38 @@ static int mlx5_set_path(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp,
 			mlx5_set_path_udp_sport(path, ah,
 						qp->ibqp.qp_num,
 						attr->dest_qp_num);
-		path->dci_cfi_prio_sl = (sl & 0x7) << 4;
+		MLX5_SET(ads, path, eth_prio, sl & 0x7);
 		gid_type = ah->grh.sgid_attr->gid_type;
 		if (gid_type == IB_GID_TYPE_ROCE_UDP_ENCAP)
-			path->ecn_dscp = (grh->traffic_class >> 2) & 0x3f;
+			MLX5_SET(ads, path, dscp, grh->traffic_class >> 2);
 	} else {
-		path->fl_free_ar = (path_flags & MLX5_PATH_FLAG_FL) ? 0x80 : 0;
-		path->fl_free_ar |=
-			(path_flags & MLX5_PATH_FLAG_FREE_AR) ? 0x40 : 0;
-		path->rlid = cpu_to_be16(rdma_ah_get_dlid(ah));
-		path->grh_mlid = rdma_ah_get_path_bits(ah) & 0x7f;
-		if (ah_flags & IB_AH_GRH)
-			path->grh_mlid	|= 1 << 7;
-		path->dci_cfi_prio_sl = sl & 0xf;
+		MLX5_SET(ads, path, fl, !!(path_flags & MLX5_PATH_FLAG_FL));
+		MLX5_SET(ads, path, free_ar,
+			 !!(path_flags & MLX5_PATH_FLAG_FREE_AR));
+		MLX5_SET(ads, path, rlid, rdma_ah_get_dlid(ah));
+		MLX5_SET(ads, path, mlid, rdma_ah_get_path_bits(ah));
+		MLX5_SET(ads, path, grh, !!(ah_flags & IB_AH_GRH));
+		MLX5_SET(ads, path, sl, sl);
 	}
 
 	if (ah_flags & IB_AH_GRH) {
-		path->mgid_index = grh->sgid_index;
-		path->hop_limit  = grh->hop_limit;
-		path->tclass_flowlabel =
-			cpu_to_be32((grh->traffic_class << 20) |
-				    (grh->flow_label));
-		memcpy(path->rgid, grh->dgid.raw, 16);
+		MLX5_SET(ads, path, src_addr_index, grh->sgid_index);
+		MLX5_SET(ads, path, hop_limit, grh->hop_limit);
+		MLX5_SET(ads, path, tclass, grh->traffic_class);
+		MLX5_SET(ads, path, flow_label, grh->flow_label);
+		memcpy(MLX5_ADDR_OF(ads, path, rgid_rip), grh->dgid.raw,
+		       sizeof(grh->dgid.raw));
 	}
 
 	err = ib_rate_to_mlx5(dev, rdma_ah_get_static_rate(ah));
 	if (err < 0)
 		return err;
-	path->static_rate = err;
-	path->port = port;
+	MLX5_SET(ads, path, stat_rate, err);
+	MLX5_SET(ads, path, vhca_port_num, port);
 
 	if (attr_mask & IB_QP_TIMEOUT)
-		path->ackto_lt = (alt ? attr->alt_timeout : attr->timeout) << 3;
+		MLX5_SET(ads, path, ack_timeout,
+			 alt ? attr->alt_timeout : attr->timeout);
 
 	if ((qp->ibqp.qp_type == IB_QPT_RAW_PACKET) && qp->sq.wqe_cnt)
 		return modify_raw_packet_eth_prio(dev->mdev,
@@ -3759,9 +3751,9 @@ static int __mlx5_ib_modify_qp(struct ib_qp *ibqp,
 	struct mlx5_ib_qp *qp = to_mqp(ibqp);
 	struct mlx5_ib_qp_base *base = &qp->trans_qp.base;
 	struct mlx5_ib_cq *send_cq, *recv_cq;
-	struct mlx5_qp_context *context;
 	struct mlx5_ib_pd *pd;
 	enum mlx5_qp_state mlx5_cur, mlx5_new;
+	void *qpc, *pri_path, *alt_path;
 	enum mlx5_qp_optpar optpar = 0;
 	u32 set_id = 0;
 	int mlx5_st;
@@ -3773,25 +3765,25 @@ static int __mlx5_ib_modify_qp(struct ib_qp *ibqp,
 	if (mlx5_st < 0)
 		return -EINVAL;
 
-	context = kzalloc(sizeof(*context), GFP_KERNEL);
-	if (!context)
+	qpc = kzalloc(MLX5_ST_SZ_BYTES(qpc), GFP_KERNEL);
+	if (!qpc)
 		return -ENOMEM;
 
 	pd = to_mpd(qp->ibqp.pd);
-	context->flags = cpu_to_be32(mlx5_st << 16);
+	MLX5_SET(qpc, qpc, st, mlx5_st);
 
 	if (!(attr_mask & IB_QP_PATH_MIG_STATE)) {
-		context->flags |= cpu_to_be32(MLX5_QP_PM_MIGRATED << 11);
+		MLX5_SET(qpc, qpc, pm_state, MLX5_QP_PM_MIGRATED);
 	} else {
 		switch (attr->path_mig_state) {
 		case IB_MIG_MIGRATED:
-			context->flags |= cpu_to_be32(MLX5_QP_PM_MIGRATED << 11);
+			MLX5_SET(qpc, qpc, pm_state, MLX5_QP_PM_MIGRATED);
 			break;
 		case IB_MIG_REARM:
-			context->flags |= cpu_to_be32(MLX5_QP_PM_REARM << 11);
+			MLX5_SET(qpc, qpc, pm_state, MLX5_QP_PM_REARM);
 			break;
 		case IB_MIG_ARMED:
-			context->flags |= cpu_to_be32(MLX5_QP_PM_ARMED << 11);
+			MLX5_SET(qpc, qpc, pm_state, MLX5_QP_PM_ARMED);
 			break;
 		}
 	}
@@ -3799,19 +3791,20 @@ static int __mlx5_ib_modify_qp(struct ib_qp *ibqp,
 	tx_affinity = get_tx_affinity(ibqp, attr, attr_mask,
 				      cur_state == IB_QPS_RESET &&
 				      new_state == IB_QPS_INIT, udata);
-	if (tx_affinity) {
-		context->flags |= cpu_to_be32(tx_affinity << 24);
-		if (new_state == IB_QPS_RTR &&
-		    MLX5_CAP_GEN(dev->mdev, init2_lag_tx_port_affinity))
-			optpar |= MLX5_QP_OPTPAR_LAG_TX_AFF;
-	}
+
+	MLX5_SET(qpc, qpc, lag_tx_port_affinity, tx_affinity);
+	if (tx_affinity && new_state == IB_QPS_RTR &&
+	    MLX5_CAP_GEN(dev->mdev, init2_lag_tx_port_affinity))
+		optpar |= MLX5_QP_OPTPAR_LAG_TX_AFF;
 
 	if (is_sqp(ibqp->qp_type)) {
-		context->mtu_msgmax = (IB_MTU_256 << 5) | 8;
+		MLX5_SET(qpc, qpc, mtu, IB_MTU_256);
+		MLX5_SET(qpc, qpc, log_msg_max, 8);
 	} else if ((ibqp->qp_type == IB_QPT_UD &&
 		    !(qp->flags & IB_QP_CREATE_SOURCE_QPN)) ||
 		   ibqp->qp_type == MLX5_IB_QPT_REG_UMR) {
-		context->mtu_msgmax = (IB_MTU_4096 << 5) | 12;
+		MLX5_SET(qpc, qpc, mtu, IB_MTU_4096);
+		MLX5_SET(qpc, qpc, log_msg_max, 12);
 	} else if (attr_mask & IB_QP_PATH_MTU) {
 		if (attr->path_mtu < IB_MTU_256 ||
 		    attr->path_mtu > IB_MTU_4096) {
@@ -3819,40 +3812,45 @@ static int __mlx5_ib_modify_qp(struct ib_qp *ibqp,
 			err = -EINVAL;
 			goto out;
 		}
-		context->mtu_msgmax = (attr->path_mtu << 5) |
-				      (u8)MLX5_CAP_GEN(dev->mdev, log_max_msg);
+		MLX5_SET(qpc, qpc, mtu, attr->path_mtu);
+		MLX5_SET(qpc, qpc, log_msg_max,
+			 MLX5_CAP_GEN(dev->mdev, log_max_msg));
 	}
 
 	if (attr_mask & IB_QP_DEST_QPN)
-		context->log_pg_sz_remote_qpn = cpu_to_be32(attr->dest_qp_num);
+		MLX5_SET(qpc, qpc, remote_qpn, attr->dest_qp_num);
+
+	pri_path = MLX5_ADDR_OF(qpc, qpc, primary_address_path);
+	alt_path = MLX5_ADDR_OF(qpc, qpc, secondary_address_path);
 
 	if (attr_mask & IB_QP_PKEY_INDEX)
-		context->pri_path.pkey_index = cpu_to_be16(attr->pkey_index);
+		MLX5_SET(ads, pri_path, pkey_index, attr->pkey_index);
 
 	/* todo implement counter_index functionality */
 
 	if (is_sqp(ibqp->qp_type))
-		context->pri_path.port = qp->port;
+		MLX5_SET(ads, pri_path, vhca_port_num, qp->port);
 
 	if (attr_mask & IB_QP_PORT)
-		context->pri_path.port = attr->port_num;
+		MLX5_SET(ads, pri_path, vhca_port_num, attr->port_num);
 
 	if (attr_mask & IB_QP_AV) {
-		err = mlx5_set_path(dev, qp, &attr->ah_attr, &context->pri_path,
-				    attr_mask & IB_QP_PORT ? attr->port_num : qp->port,
+		err = mlx5_set_path(dev, qp, &attr->ah_attr, pri_path,
+				    attr_mask & IB_QP_PORT ? attr->port_num :
+							     qp->port,
 				    attr_mask, 0, attr, false);
 		if (err)
 			goto out;
 	}
 
 	if (attr_mask & IB_QP_TIMEOUT)
-		context->pri_path.ackto_lt |= attr->timeout << 3;
+		MLX5_SET(ads, pri_path, ack_timeout, attr->timeout);
 
 	if (attr_mask & IB_QP_ALT_PATH) {
-		err = mlx5_set_path(dev, qp, &attr->alt_ah_attr,
-				    &context->alt_path,
+		err = mlx5_set_path(dev, qp, &attr->alt_ah_attr, alt_path,
 				    attr->alt_port_num,
-				    attr_mask | IB_QP_PKEY_INDEX | IB_QP_TIMEOUT,
+				    attr_mask | IB_QP_PKEY_INDEX |
+					    IB_QP_TIMEOUT,
 				    0, attr, true);
 		if (err)
 			goto out;
@@ -3861,53 +3859,47 @@ static int __mlx5_ib_modify_qp(struct ib_qp *ibqp,
 	get_cqs(qp->ibqp.qp_type, qp->ibqp.send_cq, qp->ibqp.recv_cq,
 		&send_cq, &recv_cq);
 
-	context->flags_pd = cpu_to_be32(pd ? pd->pdn : to_mpd(dev->devr.p0)->pdn);
-	context->cqn_send = send_cq ? cpu_to_be32(send_cq->mcq.cqn) : 0;
-	context->cqn_recv = recv_cq ? cpu_to_be32(recv_cq->mcq.cqn) : 0;
-	context->params1  = cpu_to_be32(MLX5_IB_ACK_REQ_FREQ << 28);
+	MLX5_SET(qpc, qpc, pd, pd ? pd->pdn : to_mpd(dev->devr.p0)->pdn);
+	if (send_cq)
+		MLX5_SET(qpc, qpc, cqn_snd, send_cq->mcq.cqn);
+	if (recv_cq)
+		MLX5_SET(qpc, qpc, cqn_rcv, recv_cq->mcq.cqn);
+
+	MLX5_SET(qpc, qpc, log_ack_req_freq, MLX5_IB_ACK_REQ_FREQ);
 
 	if (attr_mask & IB_QP_RNR_RETRY)
-		context->params1 |= cpu_to_be32(attr->rnr_retry << 13);
+		MLX5_SET(qpc, qpc, rnr_retry, attr->rnr_retry);
 
 	if (attr_mask & IB_QP_RETRY_CNT)
-		context->params1 |= cpu_to_be32(attr->retry_cnt << 16);
+		MLX5_SET(qpc, qpc, retry_count, attr->retry_cnt);
 
-	if (attr_mask & IB_QP_MAX_QP_RD_ATOMIC) {
-		if (attr->max_rd_atomic)
-			context->params1 |=
-				cpu_to_be32(fls(attr->max_rd_atomic - 1) << 21);
-	}
+	if (attr_mask & IB_QP_MAX_QP_RD_ATOMIC && attr->max_rd_atomic)
+		MLX5_SET(qpc, qpc, log_sra_max, ilog2(attr->max_rd_atomic));
 
 	if (attr_mask & IB_QP_SQ_PSN)
-		context->next_send_psn = cpu_to_be32(attr->sq_psn);
+		MLX5_SET(qpc, qpc, next_send_psn, attr->sq_psn);
 
-	if (attr_mask & IB_QP_MAX_DEST_RD_ATOMIC) {
-		if (attr->max_dest_rd_atomic)
-			context->params2 |=
-				cpu_to_be32(fls(attr->max_dest_rd_atomic - 1) << 21);
-	}
+	if (attr_mask & IB_QP_MAX_DEST_RD_ATOMIC && attr->max_dest_rd_atomic)
+		MLX5_SET(qpc, qpc, log_rra_max,
+			 ilog2(attr->max_dest_rd_atomic));
 
 	if (attr_mask & (IB_QP_ACCESS_FLAGS | IB_QP_MAX_DEST_RD_ATOMIC)) {
-		__be32 access_flags;
-
-		err = to_mlx5_access_flags(qp, attr, attr_mask, &access_flags);
+		err = set_qpc_atomic_flags(qp, attr, attr_mask, qpc);
 		if (err)
 			goto out;
-
-		context->params2 |= access_flags;
 	}
 
 	if (attr_mask & IB_QP_MIN_RNR_TIMER)
-		context->rnr_nextrecvpsn |= cpu_to_be32(attr->min_rnr_timer << 24);
+		MLX5_SET(qpc, qpc, min_rnr_nak, attr->min_rnr_timer);
 
 	if (attr_mask & IB_QP_RQ_PSN)
-		context->rnr_nextrecvpsn |= cpu_to_be32(attr->rq_psn);
+		MLX5_SET(qpc, qpc, next_rcv_psn, attr->rq_psn);
 
 	if (attr_mask & IB_QP_QKEY)
-		context->qkey = cpu_to_be32(attr->qkey);
+		MLX5_SET(qpc, qpc, q_key, attr->qkey);
 
 	if (qp->rq.wqe_cnt && cur_state == IB_QPS_RESET && new_state == IB_QPS_INIT)
-		context->db_rec_addr = cpu_to_be64(qp->db.dma);
+		MLX5_SET64(qpc, qpc, dbr_addr, qp->db.dma);
 
 	if (cur_state == IB_QPS_RESET && new_state == IB_QPS_INIT) {
 		u8 port_num = (attr_mask & IB_QP_PORT ? attr->port_num :
@@ -3921,15 +3913,14 @@ static int __mlx5_ib_modify_qp(struct ib_qp *ibqp,
 			set_id = ibqp->counter->id;
 		else
 			set_id = mlx5_ib_get_counters_id(dev, port_num);
-		context->qp_counter_set_usr_page |=
-			cpu_to_be32(set_id << 24);
+		MLX5_SET(qpc, qpc, counter_set_id, set_id);
 	}
 
 	if (!ibqp->uobject && cur_state == IB_QPS_RESET && new_state == IB_QPS_INIT)
-		context->sq_crq_size |= cpu_to_be16(1 << 4);
+		MLX5_SET(qpc, qpc, rlky, 1);
 
 	if (qp->flags & MLX5_IB_QP_CREATE_SQPN_QP1)
-		context->deth_sqpn = cpu_to_be32(1);
+		MLX5_SET(qpc, qpc, deth_sqpn, 1);
 
 	mlx5_cur = to_mlx5_state(cur_state);
 	mlx5_new = to_mlx5_state(new_state);
@@ -3987,7 +3978,7 @@ static int __mlx5_ib_modify_qp(struct ib_qp *ibqp,
 
 		err = modify_raw_packet_qp(dev, qp, &raw_qp_param, tx_affinity);
 	} else {
-		err = mlx5_core_qp_modify(dev, op, optpar, context, &base->mqp);
+		err = mlx5_core_qp_modify(dev, op, optpar, qpc, &base->mqp);
 	}
 
 	if (err)
@@ -4034,7 +4025,7 @@ static int __mlx5_ib_modify_qp(struct ib_qp *ibqp,
 	}
 
 out:
-	kfree(context);
+	kfree(qpc);
 	return err;
 }
 
diff --git a/include/linux/mlx5/qp.h b/include/linux/mlx5/qp.h
index def601199a1a..b8992b861ae6 100644
--- a/include/linux/mlx5/qp.h
+++ b/include/linux/mlx5/qp.h
@@ -495,72 +495,6 @@ struct mlx5_core_dct {
 	struct completion	drained;
 };
 
-struct mlx5_qp_path {
-	u8			fl_free_ar;
-	u8			rsvd3;
-	__be16			pkey_index;
-	u8			rsvd0;
-	u8			grh_mlid;
-	__be16			rlid;
-	u8			ackto_lt;
-	u8			mgid_index;
-	u8			static_rate;
-	u8			hop_limit;
-	__be32			tclass_flowlabel;
-	union {
-		u8		rgid[16];
-		u8		rip[16];
-	};
-	u8			f_dscp_ecn_prio;
-	u8			ecn_dscp;
-	__be16			udp_sport;
-	u8			dci_cfi_prio_sl;
-	u8			port;
-	u8			rmac[6];
-};
-
-/* FIXME: use mlx5_ifc.h qpc */
-struct mlx5_qp_context {
-	__be32			flags;
-	__be32			flags_pd;
-	u8			mtu_msgmax;
-	u8			rq_size_stride;
-	__be16			sq_crq_size;
-	__be32			qp_counter_set_usr_page;
-	__be32			wire_qpn;
-	__be32			log_pg_sz_remote_qpn;
-	struct			mlx5_qp_path pri_path;
-	struct			mlx5_qp_path alt_path;
-	__be32			params1;
-	u8			reserved2[4];
-	__be32			next_send_psn;
-	__be32			cqn_send;
-	__be32			deth_sqpn;
-	u8			reserved3[4];
-	__be32			last_acked_psn;
-	__be32			ssn;
-	__be32			params2;
-	__be32			rnr_nextrecvpsn;
-	__be32			xrcd;
-	__be32			cqn_recv;
-	__be64			db_rec_addr;
-	__be32			qkey;
-	__be32			rq_type_srqn;
-	__be32			rmsn;
-	__be16			hw_sq_wqe_counter;
-	__be16			sw_sq_wqe_counter;
-	__be16			hw_rcyclic_byte_counter;
-	__be16			hw_rq_counter;
-	__be16			sw_rcyclic_byte_counter;
-	__be16			sw_rq_counter;
-	u8			rsvd0[5];
-	u8			cgs;
-	u8			cs_req;
-	u8			cs_res;
-	__be64			dc_access_key;
-	u8			rsvd1[24];
-};
-
 int mlx5_debug_qp_add(struct mlx5_core_dev *dev, struct mlx5_core_qp *qp);
 void mlx5_debug_qp_remove(struct mlx5_core_dev *dev, struct mlx5_core_qp *qp);
 
-- 
cgit v1.2.3-71-gd317


From 1f55b7ab907d373581e9abf3fc4b24ed19cf831f Mon Sep 17 00:00:00 2001
From: Max Gurtovoy <maxg@mellanox.com>
Date: Thu, 28 May 2020 16:45:50 -0300
Subject: RDMA/mlx4: Remove FMR support for memory registration

HCA's that are driven by mlx4 driver support FRWR method to register
memory. Remove the ancient and unsafe FMR method.

Link: https://lore.kernel.org/r/8-v3-f58e6669d5d3+2cf-fmr_removal_jgg@mellanox.com
Reviewed-by: Max Gurtovoy <maxg@mellanox.com>
Signed-off-by: Max Gurtovoy <maxg@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
---
 drivers/infiniband/hw/mlx4/main.c         |  11 --
 drivers/infiniband/hw/mlx4/mlx4_ib.h      |  16 ---
 drivers/infiniband/hw/mlx4/mr.c           |  93 ---------------
 drivers/net/ethernet/mellanox/mlx4/main.c |   2 -
 drivers/net/ethernet/mellanox/mlx4/mr.c   | 183 ------------------------------
 include/linux/mlx4/device.h               |  22 +---
 6 files changed, 2 insertions(+), 325 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c
index 275722cec8c6..816d28854a8e 100644
--- a/drivers/infiniband/hw/mlx4/main.c
+++ b/drivers/infiniband/hw/mlx4/main.c
@@ -558,7 +558,6 @@ static int mlx4_ib_query_device(struct ib_device *ibdev,
 	props->max_mcast_qp_attach = dev->dev->caps.num_qp_per_mgm;
 	props->max_total_mcast_qp_attach = props->max_mcast_qp_attach *
 					   props->max_mcast_grp;
-	props->max_map_per_fmr = dev->dev->caps.max_fmr_maps;
 	props->hca_core_clock = dev->dev->caps.hca_core_clock * 1000UL;
 	props->timestamp_mask = 0xFFFFFFFFFFFFULL;
 	props->max_ah = INT_MAX;
@@ -2600,13 +2599,6 @@ static const struct ib_device_ops mlx4_ib_dev_wq_ops = {
 	.modify_wq = mlx4_ib_modify_wq,
 };
 
-static const struct ib_device_ops mlx4_ib_dev_fmr_ops = {
-	.alloc_fmr = mlx4_ib_fmr_alloc,
-	.dealloc_fmr = mlx4_ib_fmr_dealloc,
-	.map_phys_fmr = mlx4_ib_map_phys_fmr,
-	.unmap_fmr = mlx4_ib_unmap_fmr,
-};
-
 static const struct ib_device_ops mlx4_ib_dev_mw_ops = {
 	.alloc_mw = mlx4_ib_alloc_mw,
 	.dealloc_mw = mlx4_ib_dealloc_mw,
@@ -2724,9 +2716,6 @@ static void *mlx4_ib_add(struct mlx4_dev *dev)
 		ib_set_device_ops(&ibdev->ib_dev, &mlx4_ib_dev_wq_ops);
 	}
 
-	if (!mlx4_is_slave(ibdev->dev))
-		ib_set_device_ops(&ibdev->ib_dev, &mlx4_ib_dev_fmr_ops);
-
 	if (dev->caps.flags & MLX4_DEV_CAP_FLAG_MEM_WINDOW ||
 	    dev->caps.bmme_flags & MLX4_BMME_FLAG_TYPE_2_WIN) {
 		ibdev->ib_dev.uverbs_cmd_mask |=
diff --git a/drivers/infiniband/hw/mlx4/mlx4_ib.h b/drivers/infiniband/hw/mlx4/mlx4_ib.h
index 182a237b87f7..6f4ea1067095 100644
--- a/drivers/infiniband/hw/mlx4/mlx4_ib.h
+++ b/drivers/infiniband/hw/mlx4/mlx4_ib.h
@@ -146,11 +146,6 @@ struct mlx4_ib_mw {
 	struct mlx4_mw		mmw;
 };
 
-struct mlx4_ib_fmr {
-	struct ib_fmr           ibfmr;
-	struct mlx4_fmr         mfmr;
-};
-
 #define MAX_REGS_PER_FLOW 2
 
 struct mlx4_flow_reg_id {
@@ -679,11 +674,6 @@ static inline struct mlx4_ib_mw *to_mmw(struct ib_mw *ibmw)
 	return container_of(ibmw, struct mlx4_ib_mw, ibmw);
 }
 
-static inline struct mlx4_ib_fmr *to_mfmr(struct ib_fmr *ibfmr)
-{
-	return container_of(ibfmr, struct mlx4_ib_fmr, ibfmr);
-}
-
 static inline struct mlx4_ib_flow *to_mflow(struct ib_flow *ibflow)
 {
 	return container_of(ibflow, struct mlx4_ib_flow, ibflow);
@@ -794,12 +784,6 @@ int mlx4_ib_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num,
 int mlx4_ib_mad_init(struct mlx4_ib_dev *dev);
 void mlx4_ib_mad_cleanup(struct mlx4_ib_dev *dev);
 
-struct ib_fmr *mlx4_ib_fmr_alloc(struct ib_pd *pd, int mr_access_flags,
-				  struct ib_fmr_attr *fmr_attr);
-int mlx4_ib_map_phys_fmr(struct ib_fmr *ibfmr, u64 *page_list, int npages,
-			 u64 iova);
-int mlx4_ib_unmap_fmr(struct list_head *fmr_list);
-int mlx4_ib_fmr_dealloc(struct ib_fmr *fmr);
 int __mlx4_ib_query_port(struct ib_device *ibdev, u8 port,
 			 struct ib_port_attr *props, int netw_view);
 int __mlx4_ib_query_pkey(struct ib_device *ibdev, u8 port, u16 index,
diff --git a/drivers/infiniband/hw/mlx4/mr.c b/drivers/infiniband/hw/mlx4/mr.c
index b0121c90c561..e2fb71b23c80 100644
--- a/drivers/infiniband/hw/mlx4/mr.c
+++ b/drivers/infiniband/hw/mlx4/mr.c
@@ -698,99 +698,6 @@ err_free:
 	return ERR_PTR(err);
 }
 
-struct ib_fmr *mlx4_ib_fmr_alloc(struct ib_pd *pd, int acc,
-				 struct ib_fmr_attr *fmr_attr)
-{
-	struct mlx4_ib_dev *dev = to_mdev(pd->device);
-	struct mlx4_ib_fmr *fmr;
-	int err = -ENOMEM;
-
-	fmr = kmalloc(sizeof *fmr, GFP_KERNEL);
-	if (!fmr)
-		return ERR_PTR(-ENOMEM);
-
-	err = mlx4_fmr_alloc(dev->dev, to_mpd(pd)->pdn, convert_access(acc),
-			     fmr_attr->max_pages, fmr_attr->max_maps,
-			     fmr_attr->page_shift, &fmr->mfmr);
-	if (err)
-		goto err_free;
-
-	err = mlx4_fmr_enable(to_mdev(pd->device)->dev, &fmr->mfmr);
-	if (err)
-		goto err_mr;
-
-	fmr->ibfmr.rkey = fmr->ibfmr.lkey = fmr->mfmr.mr.key;
-
-	return &fmr->ibfmr;
-
-err_mr:
-	(void) mlx4_mr_free(to_mdev(pd->device)->dev, &fmr->mfmr.mr);
-
-err_free:
-	kfree(fmr);
-
-	return ERR_PTR(err);
-}
-
-int mlx4_ib_map_phys_fmr(struct ib_fmr *ibfmr, u64 *page_list,
-		      int npages, u64 iova)
-{
-	struct mlx4_ib_fmr *ifmr = to_mfmr(ibfmr);
-	struct mlx4_ib_dev *dev = to_mdev(ifmr->ibfmr.device);
-
-	return mlx4_map_phys_fmr(dev->dev, &ifmr->mfmr, page_list, npages, iova,
-				 &ifmr->ibfmr.lkey, &ifmr->ibfmr.rkey);
-}
-
-int mlx4_ib_unmap_fmr(struct list_head *fmr_list)
-{
-	struct ib_fmr *ibfmr;
-	int err;
-	struct mlx4_dev *mdev = NULL;
-
-	list_for_each_entry(ibfmr, fmr_list, list) {
-		if (mdev && to_mdev(ibfmr->device)->dev != mdev)
-			return -EINVAL;
-		mdev = to_mdev(ibfmr->device)->dev;
-	}
-
-	if (!mdev)
-		return 0;
-
-	list_for_each_entry(ibfmr, fmr_list, list) {
-		struct mlx4_ib_fmr *ifmr = to_mfmr(ibfmr);
-
-		mlx4_fmr_unmap(mdev, &ifmr->mfmr, &ifmr->ibfmr.lkey, &ifmr->ibfmr.rkey);
-	}
-
-	/*
-	 * Make sure all MPT status updates are visible before issuing
-	 * SYNC_TPT firmware command.
-	 */
-	wmb();
-
-	err = mlx4_SYNC_TPT(mdev);
-	if (err)
-		pr_warn("SYNC_TPT error %d when "
-		       "unmapping FMRs\n", err);
-
-	return 0;
-}
-
-int mlx4_ib_fmr_dealloc(struct ib_fmr *ibfmr)
-{
-	struct mlx4_ib_fmr *ifmr = to_mfmr(ibfmr);
-	struct mlx4_ib_dev *dev = to_mdev(ibfmr->device);
-	int err;
-
-	err = mlx4_fmr_free(dev->dev, &ifmr->mfmr);
-
-	if (!err)
-		kfree(ifmr);
-
-	return err;
-}
-
 static int mlx4_set_page(struct ib_mr *ibmr, u64 addr)
 {
 	struct mlx4_ib_mr *mr = to_mmr(ibmr);
diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index c72c4e1ea383..3d9aa7da95e9 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -2345,8 +2345,6 @@ static int mlx4_init_hca(struct mlx4_dev *dev)
 			goto out_free;
 		}
 
-		dev->caps.max_fmr_maps = (1 << (32 - ilog2(dev->caps.num_mpts))) - 1;
-
 		if (enable_4k_uar || !dev->persist->num_vfs) {
 			init_hca->log_uar_sz = ilog2(dev->caps.num_uars) +
 						    PAGE_SHIFT - DEFAULT_UAR_PAGE_SHIFT;
diff --git a/drivers/net/ethernet/mellanox/mlx4/mr.c b/drivers/net/ethernet/mellanox/mlx4/mr.c
index 1a11bc0e1612..d2986f1f2db0 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mr.c
+++ b/drivers/net/ethernet/mellanox/mlx4/mr.c
@@ -966,189 +966,6 @@ void mlx4_cleanup_mr_table(struct mlx4_dev *dev)
 	mlx4_bitmap_cleanup(&mr_table->mpt_bitmap);
 }
 
-static inline int mlx4_check_fmr(struct mlx4_fmr *fmr, u64 *page_list,
-				  int npages, u64 iova)
-{
-	int i, page_mask;
-
-	if (npages > fmr->max_pages)
-		return -EINVAL;
-
-	page_mask = (1 << fmr->page_shift) - 1;
-
-	/* We are getting page lists, so va must be page aligned. */
-	if (iova & page_mask)
-		return -EINVAL;
-
-	/* Trust the user not to pass misaligned data in page_list */
-	if (0)
-		for (i = 0; i < npages; ++i) {
-			if (page_list[i] & ~page_mask)
-				return -EINVAL;
-		}
-
-	if (fmr->maps >= fmr->max_maps)
-		return -EINVAL;
-
-	return 0;
-}
-
-int mlx4_map_phys_fmr(struct mlx4_dev *dev, struct mlx4_fmr *fmr, u64 *page_list,
-		      int npages, u64 iova, u32 *lkey, u32 *rkey)
-{
-	u32 key;
-	int i, err;
-
-	err = mlx4_check_fmr(fmr, page_list, npages, iova);
-	if (err)
-		return err;
-
-	++fmr->maps;
-
-	key = key_to_hw_index(fmr->mr.key);
-	key += dev->caps.num_mpts;
-	*lkey = *rkey = fmr->mr.key = hw_index_to_key(key);
-
-	*(u8 *) fmr->mpt = MLX4_MPT_STATUS_SW;
-
-	/* Make sure MPT status is visible before writing MTT entries */
-	wmb();
-
-	dma_sync_single_for_cpu(&dev->persist->pdev->dev, fmr->dma_handle,
-				npages * sizeof(u64), DMA_TO_DEVICE);
-
-	for (i = 0; i < npages; ++i)
-		fmr->mtts[i] = cpu_to_be64(page_list[i] | MLX4_MTT_FLAG_PRESENT);
-
-	dma_sync_single_for_device(&dev->persist->pdev->dev, fmr->dma_handle,
-				   npages * sizeof(u64), DMA_TO_DEVICE);
-
-	fmr->mpt->key    = cpu_to_be32(key);
-	fmr->mpt->lkey   = cpu_to_be32(key);
-	fmr->mpt->length = cpu_to_be64(npages * (1ull << fmr->page_shift));
-	fmr->mpt->start  = cpu_to_be64(iova);
-
-	/* Make MTT entries are visible before setting MPT status */
-	wmb();
-
-	*(u8 *) fmr->mpt = MLX4_MPT_STATUS_HW;
-
-	/* Make sure MPT status is visible before consumer can use FMR */
-	wmb();
-
-	return 0;
-}
-EXPORT_SYMBOL_GPL(mlx4_map_phys_fmr);
-
-int mlx4_fmr_alloc(struct mlx4_dev *dev, u32 pd, u32 access, int max_pages,
-		   int max_maps, u8 page_shift, struct mlx4_fmr *fmr)
-{
-	struct mlx4_priv *priv = mlx4_priv(dev);
-	int err = -ENOMEM;
-
-	if (max_maps > dev->caps.max_fmr_maps)
-		return -EINVAL;
-
-	if (page_shift < (ffs(dev->caps.page_size_cap) - 1) || page_shift >= 32)
-		return -EINVAL;
-
-	/* All MTTs must fit in the same page */
-	if (max_pages * sizeof(*fmr->mtts) > PAGE_SIZE)
-		return -EINVAL;
-
-	fmr->page_shift = page_shift;
-	fmr->max_pages  = max_pages;
-	fmr->max_maps   = max_maps;
-	fmr->maps = 0;
-
-	err = mlx4_mr_alloc(dev, pd, 0, 0, access, max_pages,
-			    page_shift, &fmr->mr);
-	if (err)
-		return err;
-
-	fmr->mtts = mlx4_table_find(&priv->mr_table.mtt_table,
-				    fmr->mr.mtt.offset,
-				    &fmr->dma_handle);
-
-	if (!fmr->mtts) {
-		err = -ENOMEM;
-		goto err_free;
-	}
-
-	return 0;
-
-err_free:
-	(void) mlx4_mr_free(dev, &fmr->mr);
-	return err;
-}
-EXPORT_SYMBOL_GPL(mlx4_fmr_alloc);
-
-int mlx4_fmr_enable(struct mlx4_dev *dev, struct mlx4_fmr *fmr)
-{
-	struct mlx4_priv *priv = mlx4_priv(dev);
-	int err;
-
-	err = mlx4_mr_enable(dev, &fmr->mr);
-	if (err)
-		return err;
-
-	fmr->mpt = mlx4_table_find(&priv->mr_table.dmpt_table,
-				    key_to_hw_index(fmr->mr.key), NULL);
-	if (!fmr->mpt)
-		return -ENOMEM;
-
-	return 0;
-}
-EXPORT_SYMBOL_GPL(mlx4_fmr_enable);
-
-void mlx4_fmr_unmap(struct mlx4_dev *dev, struct mlx4_fmr *fmr,
-		    u32 *lkey, u32 *rkey)
-{
-	if (!fmr->maps)
-		return;
-
-	/* To unmap: it is sufficient to take back ownership from HW */
-	*(u8 *)fmr->mpt = MLX4_MPT_STATUS_SW;
-
-	/* Make sure MPT status is visible */
-	wmb();
-
-	fmr->maps = 0;
-}
-EXPORT_SYMBOL_GPL(mlx4_fmr_unmap);
-
-int mlx4_fmr_free(struct mlx4_dev *dev, struct mlx4_fmr *fmr)
-{
-	int ret;
-
-	if (fmr->maps)
-		return -EBUSY;
-	if (fmr->mr.enabled == MLX4_MPT_EN_HW) {
-		/* In case of FMR was enabled and unmapped
-		 * make sure to give ownership of MPT back to HW
-		 * so HW2SW_MPT command will success.
-		 */
-		*(u8 *)fmr->mpt = MLX4_MPT_STATUS_SW;
-		/* Make sure MPT status is visible before changing MPT fields */
-		wmb();
-		fmr->mpt->length = 0;
-		fmr->mpt->start  = 0;
-		/* Make sure MPT data is visible after changing MPT status */
-		wmb();
-		*(u8 *)fmr->mpt = MLX4_MPT_STATUS_HW;
-		/* make sure MPT status is visible */
-		wmb();
-	}
-
-	ret = mlx4_mr_free(dev, &fmr->mr);
-	if (ret)
-		return ret;
-	fmr->mr.enabled = MLX4_MPT_DISABLED;
-
-	return 0;
-}
-EXPORT_SYMBOL_GPL(mlx4_fmr_free);
-
 int mlx4_SYNC_TPT(struct mlx4_dev *dev)
 {
 	return mlx4_cmd(dev, 0, 0, 0, MLX4_CMD_SYNC_TPT,
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index 20372de0b587..06e066e04a4b 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -573,7 +573,6 @@ struct mlx4_caps {
 	int			reserved_eqs;
 	int			num_comp_vectors;
 	int			num_mpts;
-	int			max_fmr_maps;
 	int			num_mtts;
 	int			fmr_reserved_mtts;
 	int			reserved_mtts;
@@ -707,17 +706,6 @@ struct mlx4_mw {
 	int			enabled;
 };
 
-struct mlx4_fmr {
-	struct mlx4_mr		mr;
-	struct mlx4_mpt_entry  *mpt;
-	__be64		       *mtts;
-	dma_addr_t		dma_handle;
-	int			max_pages;
-	int			max_maps;
-	int			maps;
-	u8			page_shift;
-};
-
 struct mlx4_uar {
 	unsigned long		pfn;
 	int			index;
@@ -1412,14 +1400,6 @@ int mlx4_find_cached_vlan(struct mlx4_dev *dev, u8 port, u16 vid, int *idx);
 int mlx4_register_vlan(struct mlx4_dev *dev, u8 port, u16 vlan, int *index);
 void mlx4_unregister_vlan(struct mlx4_dev *dev, u8 port, u16 vlan);
 
-int mlx4_map_phys_fmr(struct mlx4_dev *dev, struct mlx4_fmr *fmr, u64 *page_list,
-		      int npages, u64 iova, u32 *lkey, u32 *rkey);
-int mlx4_fmr_alloc(struct mlx4_dev *dev, u32 pd, u32 access, int max_pages,
-		   int max_maps, u8 page_shift, struct mlx4_fmr *fmr);
-int mlx4_fmr_enable(struct mlx4_dev *dev, struct mlx4_fmr *fmr);
-void mlx4_fmr_unmap(struct mlx4_dev *dev, struct mlx4_fmr *fmr,
-		    u32 *lkey, u32 *rkey);
-int mlx4_fmr_free(struct mlx4_dev *dev, struct mlx4_fmr *fmr);
 int mlx4_SYNC_TPT(struct mlx4_dev *dev);
 int mlx4_test_interrupt(struct mlx4_dev *dev, int vector);
 int mlx4_test_async(struct mlx4_dev *dev);
@@ -1522,6 +1502,8 @@ int mlx4_vf_smi_enabled(struct mlx4_dev *dev, int slave, int port);
 int mlx4_vf_get_enable_smi_admin(struct mlx4_dev *dev, int slave, int port);
 int mlx4_vf_set_enable_smi_admin(struct mlx4_dev *dev, int slave, int port,
 				 int enable);
+
+struct mlx4_mpt_entry;
 int mlx4_mr_hw_get_mpt(struct mlx4_dev *dev, struct mlx4_mr *mmr,
 		       struct mlx4_mpt_entry ***mpt_entry);
 int mlx4_mr_hw_write_mpt(struct mlx4_dev *dev, struct mlx4_mr *mmr,
-- 
cgit v1.2.3-71-gd317


From 649392bf75a423287a9c4936b341677f12e8cf0b Mon Sep 17 00:00:00 2001
From: Jason Gunthorpe <jgg@mellanox.com>
Date: Thu, 28 May 2020 16:45:54 -0300
Subject: RDMA: Remove 'max_fmr'

Now that FMR support is gone, this attribute can be deleted from all
places.

Link: https://lore.kernel.org/r/12-v3-f58e6669d5d3+2cf-fmr_removal_jgg@mellanox.com
Reviewed-by: Max Gurtovoy <maxg@mellanox.com>
Reviewed-by: Bernard Metzler <bmt@zurich.ibm.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
---
 drivers/infiniband/core/uverbs_cmd.c        | 1 -
 drivers/infiniband/hw/ocrdma/ocrdma.h       | 1 -
 drivers/infiniband/hw/ocrdma/ocrdma_hw.c    | 1 -
 drivers/infiniband/hw/ocrdma/ocrdma_verbs.c | 1 -
 drivers/infiniband/hw/qedr/main.c           | 1 -
 drivers/infiniband/hw/qedr/qedr.h           | 1 -
 drivers/infiniband/hw/qedr/verbs.c          | 1 -
 drivers/infiniband/sw/rdmavt/mr.c           | 1 -
 drivers/infiniband/sw/siw/siw.h             | 2 --
 drivers/infiniband/sw/siw/siw_main.c        | 1 -
 drivers/infiniband/sw/siw/siw_verbs.c       | 1 -
 drivers/net/ethernet/qlogic/qed/qed_rdma.c  | 1 -
 drivers/net/ethernet/qlogic/qed/qed_rdma.h  | 1 -
 include/linux/qed/qed_rdma_if.h             | 1 -
 include/rdma/ib_verbs.h                     | 1 -
 net/rds/ib.c                                | 2 +-
 16 files changed, 1 insertion(+), 17 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c
index 2067a939788b..56d207405dbd 100644
--- a/drivers/infiniband/core/uverbs_cmd.c
+++ b/drivers/infiniband/core/uverbs_cmd.c
@@ -356,7 +356,6 @@ static void copy_query_dev_fields(struct ib_ucontext *ucontext,
 	resp->max_mcast_qp_attach	= attr->max_mcast_qp_attach;
 	resp->max_total_mcast_qp_attach	= attr->max_total_mcast_qp_attach;
 	resp->max_ah			= attr->max_ah;
-	resp->max_fmr			= attr->max_fmr;
 	resp->max_map_per_fmr		= attr->max_map_per_fmr;
 	resp->max_srq			= attr->max_srq;
 	resp->max_srq_wr		= attr->max_srq_wr;
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma.h b/drivers/infiniband/hw/ocrdma/ocrdma.h
index 7baedc74e39d..fcfe0e82197a 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma.h
+++ b/drivers/infiniband/hw/ocrdma/ocrdma.h
@@ -98,7 +98,6 @@ struct ocrdma_dev_attr {
 	u64 max_mr_size;
 	u32 max_num_mr_pbl;
 	int max_mw;
-	int max_fmr;
 	int max_map_per_fmr;
 	int max_pages_per_frmr;
 	u16 max_ord_per_qp;
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_hw.c b/drivers/infiniband/hw/ocrdma/ocrdma_hw.c
index d82d3ec3649e..e07bf0b2209a 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_hw.c
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_hw.c
@@ -1190,7 +1190,6 @@ static void ocrdma_get_attr(struct ocrdma_dev *dev,
 	attr->max_mr = rsp->max_mr;
 	attr->max_mr_size = ((u64)rsp->max_mr_size_hi << 32) |
 			      rsp->max_mr_size_lo;
-	attr->max_fmr = 0;
 	attr->max_pages_per_frmr = rsp->max_pages_per_frmr;
 	attr->max_num_mr_pbl = rsp->max_num_mr_pbl;
 	attr->max_cqe = rsp->max_cq_cqes_per_cq &
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c
index 10e343894595..890e3fd41d21 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c
@@ -99,7 +99,6 @@ int ocrdma_query_device(struct ib_device *ibdev, struct ib_device_attr *attr,
 	attr->max_mw = dev->attr.max_mw;
 	attr->max_pd = dev->attr.max_pd;
 	attr->atomic_cap = 0;
-	attr->max_fmr = 0;
 	attr->max_map_per_fmr = 0;
 	attr->max_qp_rd_atom =
 	    min(dev->attr.max_ord_per_qp, dev->attr.max_ird_per_qp);
diff --git a/drivers/infiniband/hw/qedr/main.c b/drivers/infiniband/hw/qedr/main.c
index dcdc85a1ab25..ccaedfd53e49 100644
--- a/drivers/infiniband/hw/qedr/main.c
+++ b/drivers/infiniband/hw/qedr/main.c
@@ -632,7 +632,6 @@ static int qedr_set_device_attr(struct qedr_dev *dev)
 	attr->max_mr_size = qed_attr->max_mr_size;
 	attr->max_cqe = min_t(u64, qed_attr->max_cqe, QEDR_MAX_CQES);
 	attr->max_mw = qed_attr->max_mw;
-	attr->max_fmr = qed_attr->max_fmr;
 	attr->max_mr_mw_fmr_pbl = qed_attr->max_mr_mw_fmr_pbl;
 	attr->max_mr_mw_fmr_size = qed_attr->max_mr_mw_fmr_size;
 	attr->max_pd = qed_attr->max_pd;
diff --git a/drivers/infiniband/hw/qedr/qedr.h b/drivers/infiniband/hw/qedr/qedr.h
index 5488dbd59d3c..fdf90ecb2699 100644
--- a/drivers/infiniband/hw/qedr/qedr.h
+++ b/drivers/infiniband/hw/qedr/qedr.h
@@ -103,7 +103,6 @@ struct qedr_device_attr {
 	u64	max_mr_size;
 	u32	max_cqe;
 	u32	max_mw;
-	u32	max_fmr;
 	u32	max_mr_mw_fmr_pbl;
 	u64	max_mr_mw_fmr_size;
 	u32	max_pd;
diff --git a/drivers/infiniband/hw/qedr/verbs.c b/drivers/infiniband/hw/qedr/verbs.c
index d6b94a713573..ca88006eaa66 100644
--- a/drivers/infiniband/hw/qedr/verbs.c
+++ b/drivers/infiniband/hw/qedr/verbs.c
@@ -145,7 +145,6 @@ int qedr_query_device(struct ib_device *ibdev,
 	attr->max_mw = qattr->max_mw;
 	attr->max_pd = qattr->max_pd;
 	attr->atomic_cap = dev->atomic_cap;
-	attr->max_fmr = qattr->max_fmr;
 	attr->max_map_per_fmr = 16;
 	attr->max_qp_init_rd_atom =
 	    1 << (fls(qattr->max_qp_req_rd_atomic_resc) - 1);
diff --git a/drivers/infiniband/sw/rdmavt/mr.c b/drivers/infiniband/sw/rdmavt/mr.c
index ddb0c0d771c2..60864e5ca7cb 100644
--- a/drivers/infiniband/sw/rdmavt/mr.c
+++ b/drivers/infiniband/sw/rdmavt/mr.c
@@ -97,7 +97,6 @@ int rvt_driver_mr_init(struct rvt_dev_info *rdi)
 		RCU_INIT_POINTER(rdi->lkey_table.table[i], NULL);
 
 	rdi->dparms.props.max_mr = rdi->lkey_table.max;
-	rdi->dparms.props.max_fmr = rdi->lkey_table.max;
 	return 0;
 }
 
diff --git a/drivers/infiniband/sw/siw/siw.h b/drivers/infiniband/sw/siw/siw.h
index 5a58a1cc7a7e..e9753831ac3f 100644
--- a/drivers/infiniband/sw/siw/siw.h
+++ b/drivers/infiniband/sw/siw/siw.h
@@ -30,7 +30,6 @@
 #define SIW_MAX_MR (SIW_MAX_QP * 10)
 #define SIW_MAX_PD SIW_MAX_QP
 #define SIW_MAX_MW 0 /* to be set if MW's are supported */
-#define SIW_MAX_FMR SIW_MAX_MR
 #define SIW_MAX_SRQ SIW_MAX_QP
 #define SIW_MAX_SRQ_WR (SIW_MAX_QP_WR * 10)
 #define SIW_MAX_CONTEXT SIW_MAX_PD
@@ -59,7 +58,6 @@ struct siw_dev_cap {
 	int max_mr;
 	int max_pd;
 	int max_mw;
-	int max_fmr;
 	int max_srq;
 	int max_srq_wr;
 	int max_srq_sge;
diff --git a/drivers/infiniband/sw/siw/siw_main.c b/drivers/infiniband/sw/siw/siw_main.c
index 5cd40fb9e20c..a0b8cc643c5c 100644
--- a/drivers/infiniband/sw/siw/siw_main.c
+++ b/drivers/infiniband/sw/siw/siw_main.c
@@ -413,7 +413,6 @@ static struct siw_device *siw_device_create(struct net_device *netdev)
 	sdev->attrs.max_mr = SIW_MAX_MR;
 	sdev->attrs.max_pd = SIW_MAX_PD;
 	sdev->attrs.max_mw = SIW_MAX_MW;
-	sdev->attrs.max_fmr = SIW_MAX_FMR;
 	sdev->attrs.max_srq = SIW_MAX_SRQ;
 	sdev->attrs.max_srq_wr = SIW_MAX_SRQ_WR;
 	sdev->attrs.max_srq_sge = SIW_MAX_SGE;
diff --git a/drivers/infiniband/sw/siw/siw_verbs.c b/drivers/infiniband/sw/siw/siw_verbs.c
index aeb842bc7a1e..987e2ba05dbc 100644
--- a/drivers/infiniband/sw/siw/siw_verbs.c
+++ b/drivers/infiniband/sw/siw/siw_verbs.c
@@ -136,7 +136,6 @@ int siw_query_device(struct ib_device *base_dev, struct ib_device_attr *attr,
 	attr->max_cq = sdev->attrs.max_cq;
 	attr->max_cqe = sdev->attrs.max_cqe;
 	attr->max_fast_reg_page_list_len = SIW_MAX_SGE_PBL;
-	attr->max_fmr = sdev->attrs.max_fmr;
 	attr->max_mr = sdev->attrs.max_mr;
 	attr->max_mw = sdev->attrs.max_mw;
 	attr->max_mr_size = ~0ull;
diff --git a/drivers/net/ethernet/qlogic/qed/qed_rdma.c b/drivers/net/ethernet/qlogic/qed/qed_rdma.c
index 38b1f402f7ed..5dc18a4bdda4 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_rdma.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_rdma.c
@@ -499,7 +499,6 @@ static void qed_rdma_init_devinfo(struct qed_hwfn *p_hwfn,
 		dev->max_cqe = QED_RDMA_MAX_CQE_16_BIT;
 
 	dev->max_mw = 0;
-	dev->max_fmr = QED_RDMA_MAX_FMR;
 	dev->max_mr_mw_fmr_pbl = (PAGE_SIZE / 8) * (PAGE_SIZE / 8);
 	dev->max_mr_mw_fmr_size = dev->max_mr_mw_fmr_pbl * PAGE_SIZE;
 	dev->max_pkey = QED_RDMA_MAX_P_KEY;
diff --git a/drivers/net/ethernet/qlogic/qed/qed_rdma.h b/drivers/net/ethernet/qlogic/qed/qed_rdma.h
index 3689fe3e5935..dfaa2f552627 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_rdma.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_rdma.h
@@ -45,7 +45,6 @@
 #include "qed_iwarp.h"
 #include "qed_roce.h"
 
-#define QED_RDMA_MAX_FMR                    (RDMA_MAX_TIDS)
 #define QED_RDMA_MAX_P_KEY                  (1)
 #define QED_RDMA_MAX_WQE                    (0x7FFF)
 #define QED_RDMA_MAX_SRQ_WQE_ELEM           (0x7FFF)
diff --git a/include/linux/qed/qed_rdma_if.h b/include/linux/qed/qed_rdma_if.h
index 74efca15fde7..c90276cda5c1 100644
--- a/include/linux/qed/qed_rdma_if.h
+++ b/include/linux/qed/qed_rdma_if.h
@@ -91,7 +91,6 @@ struct qed_rdma_device {
 	u64 max_mr_size;
 	u32 max_cqe;
 	u32 max_mw;
-	u32 max_fmr;
 	u32 max_mr_mw_fmr_pbl;
 	u64 max_mr_mw_fmr_size;
 	u32 max_pd;
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index ff6a8053ec52..c4708b3243f9 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -430,7 +430,6 @@ struct ib_device_attr {
 	int			max_mcast_qp_attach;
 	int			max_total_mcast_qp_attach;
 	int			max_ah;
-	int			max_fmr;
 	int			max_map_per_fmr;
 	int			max_srq;
 	int			max_srq_wr;
diff --git a/net/rds/ib.c b/net/rds/ib.c
index 6c43b3e4c736..deecbdcdae84 100644
--- a/net/rds/ib.c
+++ b/net/rds/ib.c
@@ -217,7 +217,7 @@ static int rds_ib_add_one(struct ib_device *device)
 	}
 
 	rdsdebug("RDS/IB: max_mr = %d, max_wrs = %d, max_sge = %d, max_1m_mrs = %d, max_8k_mrs = %d\n",
-		 device->attrs.max_fmr, rds_ibdev->max_wrs, rds_ibdev->max_sge,
+		 device->attrs.max_mr, rds_ibdev->max_wrs, rds_ibdev->max_sge,
 		 rds_ibdev->max_1m_mrs, rds_ibdev->max_8k_mrs);
 
 	pr_info("RDS/IB: %s: added\n", device->name);
-- 
cgit v1.2.3-71-gd317


From a645a89d9a780a8fbb6e283f84fc91ad538c2edc Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Tue, 2 Jun 2020 15:55:48 +0300
Subject: RDMA/mlx5: Return ECE DC support

The DC QPs are many-to-one QP types that means that first connection will
establish ECE options that coming connections should follow.  Due to this
property, the ECE code was removed between first [1] and second [2] ECE
submissions.

This patch returns the dropped code, because ECE is a property of a
connection and like any other connection users are needed to manage this
data. Allow them to set ECE parameter for DC too and avoid need of having
compatibility flag for the DC ECE.

[1]
https://lore.kernel.org/linux-rdma/20200523132243.817936-1-leon@kernel.org/
[2]
https://lore.kernel.org/linux-rdma/20200525174401.71152-1-leon@kernel.org/

Link: https://lore.kernel.org/r/20200602125548.172654-4-leon@kernel.org
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
---
 drivers/infiniband/hw/mlx5/qp.c | 45 ++++++++++++++++++++++++++++-------------
 include/linux/mlx5/mlx5_ifc.h   |  5 +++--
 2 files changed, 34 insertions(+), 16 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c
index 18135f908971..81bf6b975e0e 100644
--- a/drivers/infiniband/hw/mlx5/qp.c
+++ b/drivers/infiniband/hw/mlx5/qp.c
@@ -2404,7 +2404,8 @@ static void destroy_qp_common(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp,
 	destroy_qp(dev, qp, base, udata);
 }
 
-static int create_dct(struct ib_pd *pd, struct mlx5_ib_qp *qp,
+static int create_dct(struct mlx5_ib_dev *dev, struct ib_pd *pd,
+		      struct mlx5_ib_qp *qp,
 		      struct mlx5_create_qp_params *params)
 {
 	struct ib_qp_init_attr *attr = params->attr;
@@ -2423,6 +2424,8 @@ static int create_dct(struct ib_pd *pd, struct mlx5_ib_qp *qp,
 	MLX5_SET(dctc, dctc, cqn, to_mcq(attr->recv_cq)->mcq.cqn);
 	MLX5_SET64(dctc, dctc, dc_access_key, ucmd->access_key);
 	MLX5_SET(dctc, dctc, user_index, uidx);
+	if (MLX5_CAP_GEN(dev->mdev, ece_support))
+		MLX5_SET(dctc, dctc, ece, ucmd->ece_options);
 
 	if (qp->flags_en & MLX5_QP_FLAG_SCATTER_CQE) {
 		int rcqe_sz = mlx5_ib_get_cqe_size(attr->recv_cq);
@@ -2768,7 +2771,7 @@ static int create_qp(struct mlx5_ib_dev *dev, struct ib_pd *pd,
 	}
 
 	if (qp->type == MLX5_IB_QPT_DCT) {
-		err = create_dct(pd, qp, params);
+		err = create_dct(dev, pd, qp, params);
 		goto out;
 	}
 
@@ -2882,9 +2885,8 @@ static int check_ucmd_data(struct mlx5_ib_dev *dev,
 		 */
 		last = sizeof(struct mlx5_ib_create_qp_rss);
 	else
-		/* IB_QPT_RAW_PACKET and IB_QPT_DRIVER don't have ECE data */
+		/* IB_QPT_RAW_PACKET doesn't have ECE data */
 		switch (attr->qp_type) {
-		case IB_QPT_DRIVER:
 		case IB_QPT_RAW_PACKET:
 			last = offsetof(struct mlx5_ib_create_qp, ece_options);
 			break;
@@ -4095,7 +4097,8 @@ static bool modify_dci_qp_is_ok(enum ib_qp_state cur_state, enum ib_qp_state new
  * Other transitions and attributes are illegal
  */
 static int mlx5_ib_modify_dct(struct ib_qp *ibqp, struct ib_qp_attr *attr,
-			      int attr_mask, struct ib_udata *udata)
+			      int attr_mask, struct mlx5_ib_modify_qp *ucmd,
+			      struct ib_udata *udata)
 {
 	struct mlx5_ib_qp *qp = to_mqp(ibqp);
 	struct mlx5_ib_dev *dev = to_mdev(ibqp->device);
@@ -4111,6 +4114,15 @@ static int mlx5_ib_modify_dct(struct ib_qp *ibqp, struct ib_qp_attr *attr,
 	new_state = attr->qp_state;
 
 	dctc = MLX5_ADDR_OF(create_dct_in, qp->dct.in, dct_context_entry);
+	if (MLX5_CAP_GEN(dev->mdev, ece_support) && ucmd->ece_options)
+		/*
+		 * DCT doesn't initialize QP till modify command is executed,
+		 * so we need to overwrite previously set ECE field if user
+		 * provided any value except zero, which means not set/not
+		 * valid.
+		 */
+		MLX5_SET(dctc, dctc, ece, ucmd->ece_options);
+
 	if (cur_state == IB_QPS_RESET && new_state == IB_QPS_INIT) {
 		u16 set_id;
 
@@ -4145,14 +4157,21 @@ static int mlx5_ib_modify_dct(struct ib_qp *ibqp, struct ib_qp_attr *attr,
 		MLX5_SET(dctc, dctc, counter_set_id, set_id);
 	} else if (cur_state == IB_QPS_INIT && new_state == IB_QPS_RTR) {
 		struct mlx5_ib_modify_qp_resp resp = {};
-		u32 out[MLX5_ST_SZ_DW(create_dct_out)] = {0};
-		u32 min_resp_len = offsetof(typeof(resp), dctn) +
-				   sizeof(resp.dctn);
+		u32 out[MLX5_ST_SZ_DW(create_dct_out)] = {};
+		u32 min_resp_len = offsetofend(typeof(resp), dctn);
 
 		if (udata->outlen < min_resp_len)
 			return -EINVAL;
 		resp.response_length = min_resp_len;
 
+		/*
+		 * If we don't have enough space for the ECE options,
+		 * simply indicate it with resp.response_length.
+		 */
+		resp.response_length = (udata->outlen < sizeof(resp)) ?
+					       min_resp_len :
+					       sizeof(resp);
+
 		required |= IB_QP_MIN_RNR_TIMER | IB_QP_AV | IB_QP_PATH_MTU;
 		if (!is_valid_mask(attr_mask, required, 0))
 			return -EINVAL;
@@ -4169,6 +4188,8 @@ static int mlx5_ib_modify_dct(struct ib_qp *ibqp, struct ib_qp_attr *attr,
 		if (err)
 			return err;
 		resp.dctn = qp->dct.mdct.mqp.qpn;
+		if (MLX5_CAP_GEN(dev->mdev, ece_support))
+			resp.ece_options = MLX5_GET(create_dct_out, out, ece);
 		err = ib_copy_to_udata(udata, &resp, resp.response_length);
 		if (err) {
 			mlx5_core_destroy_dct(dev, &qp->dct.mdct);
@@ -4226,12 +4247,8 @@ int mlx5_ib_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr,
 	qp_type = (unlikely(ibqp->qp_type == MLX5_IB_QPT_HW_GSI)) ? IB_QPT_GSI :
 								    qp->type;
 
-	if (qp_type == MLX5_IB_QPT_DCT) {
-		if (memchr_inv(&ucmd.ece_options, 0, sizeof(ucmd.ece_options)))
-			return -EOPNOTSUPP;
-
-		return mlx5_ib_modify_dct(ibqp, attr, attr_mask, udata);
-	}
+	if (qp_type == MLX5_IB_QPT_DCT)
+		return mlx5_ib_modify_dct(ibqp, attr, attr_mask, &ucmd, udata);
 
 	mutex_lock(&qp->mutex);
 
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 4d2e36dd2c6b..116bd9bb347f 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -3690,7 +3690,8 @@ struct mlx5_ifc_dctc_bits {
 	u8         ecn[0x2];
 	u8         dscp[0x6];
 
-	u8         reserved_at_1c0[0x40];
+	u8         reserved_at_1c0[0x20];
+	u8         ece[0x20];
 };
 
 enum {
@@ -7940,7 +7941,7 @@ struct mlx5_ifc_create_dct_out_bits {
 	u8         reserved_at_40[0x8];
 	u8         dctn[0x18];
 
-	u8         reserved_at_60[0x20];
+	u8         ece[0x20];
 };
 
 struct mlx5_ifc_create_dct_in_bits {
-- 
cgit v1.2.3-71-gd317