Merge tag 'for-linus-timers-conversion-final-v4.15-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux into timers/urgent

Pull the last batch of manual timer conversions from Kees Cook:

 - final batch of "non trivial" timer conversions (multi-tree dependencies,
   things Coccinelle couldn't handle, etc).

 - treewide conversions via Coccinelle, in 4 steps:
   - DEFINE_TIMER() functions converted to struct timer_list * argument
   - init_timer() -> setup_timer()
   - setup_timer() -> timer_setup()
   - setup_timer() -> timer_setup() (with a single embedded structure)

 - deprecated timer API removals (init_timer(), setup_*timer())

 - finalization of new API (remove global casts)

7 files changed, 241 insertions, 41 deletions

diff --git a/drivers/infiniband/hw/mlx5/ah.c b/drivers/infiniband/hw/mlx5/ah.c
index 3363e29157f6..fe269f680103 100644
--- a/drivers/infiniband/hw/mlx5/ah.c
+++ b/drivers/infiniband/hw/mlx5/ah.c
@@ -89,10 +89,6 @@ struct ib_ah *mlx5_ib_create_ah(struct ib_pd *pd, struct rdma_ah_attr *ah_attr,
 
 		resp.response_length = min_resp_len;
 
-		err = ib_resolve_eth_dmac(pd->device, ah_attr);
-		if (err)
-			return ERR_PTR(err);
-
 		memcpy(resp.dmac, ah_attr->roce.dmac, ETH_ALEN);
 		err = ib_copy_to_udata(udata, &resp, resp.response_length);
 		if (err)
diff --git a/drivers/infiniband/hw/mlx5/cq.c b/drivers/infiniband/hw/mlx5/cq.c
index 2aa53f427685..18705cbcdc8c 100644
--- a/drivers/infiniband/hw/mlx5/cq.c
+++ b/drivers/infiniband/hw/mlx5/cq.c
@@ -124,11 +124,13 @@ static void handle_good_req(struct ib_wc *wc, struct mlx5_cqe64 *cqe,
 	switch (be32_to_cpu(cqe->sop_drop_qpn) >> 24) {
 	case MLX5_OPCODE_RDMA_WRITE_IMM:
 		wc->wc_flags |= IB_WC_WITH_IMM;
+		/* fall through */
 	case MLX5_OPCODE_RDMA_WRITE:
 		wc->opcode    = IB_WC_RDMA_WRITE;
 		break;
 	case MLX5_OPCODE_SEND_IMM:
 		wc->wc_flags |= IB_WC_WITH_IMM;
+		/* fall through */
 	case MLX5_OPCODE_SEND:
 	case MLX5_OPCODE_SEND_INVAL:
 		wc->opcode    = IB_WC_SEND;
@@ -752,13 +754,13 @@ static int create_cq_user(struct mlx5_ib_dev *dev, struct ib_udata *udata,
 	int err;
 
 	ucmdlen = udata->inlen < sizeof(ucmd) ?
-		  (sizeof(ucmd) - sizeof(ucmd.reserved)) : sizeof(ucmd);
+		  (sizeof(ucmd) - sizeof(ucmd.flags)) : sizeof(ucmd);
 
 	if (ib_copy_from_udata(&ucmd, udata, ucmdlen))
 		return -EFAULT;
 
 	if (ucmdlen == sizeof(ucmd) &&
-	    ucmd.reserved != 0)
+	    (ucmd.flags & ~(MLX5_IB_CREATE_CQ_FLAGS_CQE_128B_PAD)))
 		return -EINVAL;
 
 	if (ucmd.cqe_size != 64 && ucmd.cqe_size != 128)
@@ -802,8 +804,10 @@ static int create_cq_user(struct mlx5_ib_dev *dev, struct ib_udata *udata,
 	*index = to_mucontext(context)->bfregi.sys_pages[0];
 
 	if (ucmd.cqe_comp_en == 1) {
-		if (unlikely((*cqe_size != 64) ||
-			     !MLX5_CAP_GEN(dev->mdev, cqe_compression))) {
+		if (!((*cqe_size == 128 &&
+		       MLX5_CAP_GEN(dev->mdev, cqe_compression_128)) ||
+		      (*cqe_size == 64  &&
+		       MLX5_CAP_GEN(dev->mdev, cqe_compression)))) {
 			err = -EOPNOTSUPP;
 			mlx5_ib_warn(dev, "CQE compression is not supported for size %d!\n",
 				     *cqe_size);
@@ -826,6 +830,19 @@ static int create_cq_user(struct mlx5_ib_dev *dev, struct ib_udata *udata,
 			 ilog2(ucmd.cqe_comp_res_format));
 	}
 
+	if (ucmd.flags & MLX5_IB_CREATE_CQ_FLAGS_CQE_128B_PAD) {
+		if (*cqe_size != 128 ||
+		    !MLX5_CAP_GEN(dev->mdev, cqe_128_always)) {
+			err = -EOPNOTSUPP;
+			mlx5_ib_warn(dev,
+				     "CQE padding is not supported for CQE size of %dB!\n",
+				     *cqe_size);
+			goto err_cqb;
+		}
+
+		cq->private_flags |= MLX5_IB_CQ_PR_FLAGS_CQE_128_PAD;
+	}
+
 	return 0;
 
 err_cqb:
@@ -985,7 +1002,10 @@ struct ib_cq *mlx5_ib_create_cq(struct ib_device *ibdev,
 	cq->cqe_size = cqe_size;
 
 	cqc = MLX5_ADDR_OF(create_cq_in, cqb, cq_context);
-	MLX5_SET(cqc, cqc, cqe_sz, cqe_sz_to_mlx_sz(cqe_size));
+	MLX5_SET(cqc, cqc, cqe_sz,
+		 cqe_sz_to_mlx_sz(cqe_size,
+				  cq->private_flags &
+				  MLX5_IB_CQ_PR_FLAGS_CQE_128_PAD));
 	MLX5_SET(cqc, cqc, log_cq_size, ilog2(entries));
 	MLX5_SET(cqc, cqc, uar_page, index);
 	MLX5_SET(cqc, cqc, c_eqn, eqn);
@@ -1129,6 +1149,9 @@ int mlx5_ib_modify_cq(struct ib_cq *cq, u16 cq_count, u16 cq_period)
 	if (!MLX5_CAP_GEN(dev->mdev, cq_moderation))
 		return -ENOSYS;
 
+	if (cq_period > MLX5_MAX_CQ_PERIOD)
+		return -EINVAL;
+
 	err = mlx5_core_modify_cq_moderation(dev->mdev, &mcq->mcq,
 					     cq_period, cq_count);
 	if (err)
@@ -1335,7 +1358,10 @@ int mlx5_ib_resize_cq(struct ib_cq *ibcq, int entries, struct ib_udata *udata)
 
 	MLX5_SET(cqc, cqc, log_page_size,
 		 page_shift - MLX5_ADAPTER_PAGE_SHIFT);
-	MLX5_SET(cqc, cqc, cqe_sz, cqe_sz_to_mlx_sz(cqe_size));
+	MLX5_SET(cqc, cqc, cqe_sz,
+		 cqe_sz_to_mlx_sz(cqe_size,
+				  cq->private_flags &
+				  MLX5_IB_CQ_PR_FLAGS_CQE_128_PAD));
 	MLX5_SET(cqc, cqc, log_cq_size, ilog2(entries));
 
 	MLX5_SET(modify_cq_in, in, op_mod, MLX5_CQ_OPMOD_RESIZE);
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index 552f7bd4ecc3..543d0a4c8bf3 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -715,6 +715,9 @@ static int mlx5_ib_query_device(struct ib_device *ibdev,
 	if (mlx5_get_flow_namespace(dev->mdev, MLX5_FLOW_NAMESPACE_BYPASS))
 		props->device_cap_flags |= IB_DEVICE_MANAGED_FLOW_STEERING;
 
+	if (MLX5_CAP_GEN(mdev, end_pad))
+		props->device_cap_flags |= IB_DEVICE_PCI_WRITE_END_PADDING;
+
 	props->vendor_part_id	   = mdev->pdev->device;
 	props->hw_ver		   = mdev->pdev->revision;
 
@@ -787,6 +790,13 @@ static int mlx5_ib_query_device(struct ib_device *ibdev,
 		props->tm_caps.max_sge = MLX5_TM_MAX_SGE;
 	}
 
+	if (MLX5_CAP_GEN(dev->mdev, cq_moderation)) {
+		props->cq_caps.max_cq_moderation_count =
+						MLX5_MAX_CQ_COUNT;
+		props->cq_caps.max_cq_moderation_period =
+						MLX5_MAX_CQ_PERIOD;
+	}
+
 	if (field_avail(typeof(resp), cqe_comp_caps, uhw->outlen)) {
 		resp.cqe_comp_caps.max_num =
 			MLX5_CAP_GEN(dev->mdev, cqe_compression) ?
@@ -824,8 +834,16 @@ static int mlx5_ib_query_device(struct ib_device *ibdev,
 			sizeof(resp.mlx5_ib_support_multi_pkt_send_wqes);
 	}
 
-	if (field_avail(typeof(resp), reserved, uhw->outlen))
-		resp.response_length += sizeof(resp.reserved);
+	if (field_avail(typeof(resp), flags, uhw->outlen)) {
+		resp.response_length += sizeof(resp.flags);
+
+		if (MLX5_CAP_GEN(mdev, cqe_compression_128))
+			resp.flags |=
+				MLX5_IB_QUERY_DEV_RESP_FLAGS_CQE_128B_COMP;
+
+		if (MLX5_CAP_GEN(mdev, cqe_128_always))
+			resp.flags |= MLX5_IB_QUERY_DEV_RESP_FLAGS_CQE_128B_PAD;
+	}
 
 	if (field_avail(typeof(resp), sw_parsing_caps,
 			uhw->outlen)) {
@@ -848,6 +866,36 @@ static int mlx5_ib_query_device(struct ib_device *ibdev,
 		}
 	}
 
+	if (field_avail(typeof(resp), striding_rq_caps, uhw->outlen)) {
+		resp.response_length += sizeof(resp.striding_rq_caps);
+		if (MLX5_CAP_GEN(mdev, striding_rq)) {
+			resp.striding_rq_caps.min_single_stride_log_num_of_bytes =
+				MLX5_MIN_SINGLE_STRIDE_LOG_NUM_BYTES;
+			resp.striding_rq_caps.max_single_stride_log_num_of_bytes =
+				MLX5_MAX_SINGLE_STRIDE_LOG_NUM_BYTES;
+			resp.striding_rq_caps.min_single_wqe_log_num_of_strides =
+				MLX5_MIN_SINGLE_WQE_LOG_NUM_STRIDES;
+			resp.striding_rq_caps.max_single_wqe_log_num_of_strides =
+				MLX5_MAX_SINGLE_WQE_LOG_NUM_STRIDES;
+			resp.striding_rq_caps.supported_qpts =
+				BIT(IB_QPT_RAW_PACKET);
+		}
+	}
+
+	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 |=
+				MLX5_IB_TUNNELED_OFFLOADS_VXLAN;
+		if (MLX5_CAP_ETH(mdev, tunnel_stateless_geneve_rx))
+			resp.tunnel_offloads_caps |=
+				MLX5_IB_TUNNELED_OFFLOADS_GENEVE;
+		if (MLX5_CAP_ETH(mdev, tunnel_stateless_gre))
+			resp.tunnel_offloads_caps |=
+				MLX5_IB_TUNNELED_OFFLOADS_GRE;
+	}
+
 	if (uhw->outlen) {
 		err = ib_copy_to_udata(uhw, &resp, resp.response_length);
 
@@ -3097,6 +3145,8 @@ static int create_umr_res(struct mlx5_ib_dev *dev)
 	qp->real_qp    = qp;
 	qp->uobject    = NULL;
 	qp->qp_type    = MLX5_IB_QPT_REG_UMR;
+	qp->send_cq    = init_attr->send_cq;
+	qp->recv_cq    = init_attr->recv_cq;
 
 	attr->qp_state = IB_QPS_INIT;
 	attr->port_num = 1;
@@ -3979,7 +4029,8 @@ static void *mlx5_ib_add(struct mlx5_core_dev *mdev)
 		(1ull << IB_USER_VERBS_EX_CMD_QUERY_DEVICE)	|
 		(1ull << IB_USER_VERBS_EX_CMD_CREATE_CQ)	|
 		(1ull << IB_USER_VERBS_EX_CMD_CREATE_QP)	|
-		(1ull << IB_USER_VERBS_EX_CMD_MODIFY_QP);
+		(1ull << IB_USER_VERBS_EX_CMD_MODIFY_QP)	|
+		(1ull << IB_USER_VERBS_EX_CMD_MODIFY_CQ);
 
 	dev->ib_dev.query_device	= mlx5_ib_query_device;
 	dev->ib_dev.query_port		= mlx5_ib_query_port;
diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h
index 189e80cd6b2f..6dd8cac78de2 100644
--- a/drivers/infiniband/hw/mlx5/mlx5_ib.h
+++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h
@@ -228,6 +228,7 @@ struct wr_list {
 
 enum mlx5_ib_rq_flags {
 	MLX5_IB_RQ_CVLAN_STRIPPING	= 1 << 0,
+	MLX5_IB_RQ_PCI_WRITE_END_PADDING	= 1 << 1,
 };
 
 struct mlx5_ib_wq {
@@ -254,8 +255,14 @@ struct mlx5_ib_wq {
 
 enum mlx5_ib_wq_flags {
 	MLX5_IB_WQ_FLAGS_DELAY_DROP = 0x1,
+	MLX5_IB_WQ_FLAGS_STRIDING_RQ = 0x2,
 };
 
+#define MLX5_MIN_SINGLE_WQE_LOG_NUM_STRIDES 9
+#define MLX5_MAX_SINGLE_WQE_LOG_NUM_STRIDES 16
+#define MLX5_MIN_SINGLE_STRIDE_LOG_NUM_BYTES 6
+#define MLX5_MAX_SINGLE_STRIDE_LOG_NUM_BYTES 13
+
 struct mlx5_ib_rwq {
 	struct ib_wq		ibwq;
 	struct mlx5_core_qp	core_qp;
@@ -264,6 +271,9 @@ struct mlx5_ib_rwq {
 	u32			log_rq_size;
 	u32			rq_page_offset;
 	u32			log_page_size;
+	u32			log_num_strides;
+	u32			two_byte_shift_en;
+	u32			single_stride_log_num_of_bytes;
 	struct ib_umem		*umem;
 	size_t			buf_size;
 	unsigned int		page_shift;
@@ -389,6 +399,7 @@ struct mlx5_ib_qp {
 	struct list_head	cq_send_list;
 	u32			rate_limit;
 	u32                     underlay_qpn;
+	bool			tunnel_offload_en;
 };
 
 struct mlx5_ib_cq_buf {
@@ -411,6 +422,8 @@ enum mlx5_ib_qp_flags {
 	MLX5_IB_QP_RSS				= 1 << 8,
 	MLX5_IB_QP_CVLAN_STRIPPING		= 1 << 9,
 	MLX5_IB_QP_UNDERLAY			= 1 << 10,
+	MLX5_IB_QP_PCI_WRITE_END_PADDING	= 1 << 11,
+	MLX5_IB_QP_TUNNEL_OFFLOAD		= 1 << 12,
 };
 
 struct mlx5_umr_wr {
@@ -435,6 +448,10 @@ struct mlx5_shared_mr_info {
 	struct ib_umem		*umem;
 };
 
+enum mlx5_ib_cq_pr_flags {
+	MLX5_IB_CQ_PR_FLAGS_CQE_128_PAD	= 1 << 0,
+};
+
 struct mlx5_ib_cq {
 	struct ib_cq		ibcq;
 	struct mlx5_core_cq	mcq;
@@ -457,6 +474,7 @@ struct mlx5_ib_cq {
 	struct list_head	wc_list;
 	enum ib_cq_notify_flags notify_flags;
 	struct work_struct	notify_work;
+	u16			private_flags; /* Use mlx5_ib_cq_pr_flags */
 };
 
 struct mlx5_ib_wc {
diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c
index 37bbc543847a..ee0ee1f9994b 100644
--- a/drivers/infiniband/hw/mlx5/mr.c
+++ b/drivers/infiniband/hw/mlx5/mr.c
@@ -642,9 +642,9 @@ err:
 	return -ENOMEM;
 }
 
-static void delay_time_func(unsigned long ctx)
+static void delay_time_func(struct timer_list *t)
 {
-	struct mlx5_ib_dev *dev = (struct mlx5_ib_dev *)ctx;
+	struct mlx5_ib_dev *dev = from_timer(dev, t, delay_timer);
 
 	dev->fill_delay = 0;
 }
@@ -663,7 +663,7 @@ int mlx5_mr_cache_init(struct mlx5_ib_dev *dev)
 		return -ENOMEM;
 	}
 
-	setup_timer(&dev->delay_timer, delay_time_func, (unsigned long)dev);
+	timer_setup(&dev->delay_timer, delay_time_func, 0);
 	for (i = 0; i < MAX_MR_CACHE_ENTRIES; i++) {
 		ent = &cache->ent[i];
 		INIT_LIST_HEAD(&ent->head);
@@ -1230,13 +1230,13 @@ struct ib_mr *mlx5_ib_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
 		mr = alloc_mr_from_cache(pd, umem, virt_addr, length, ncont,
 					 page_shift, order, access_flags);
 		if (PTR_ERR(mr) == -EAGAIN) {
-			mlx5_ib_dbg(dev, "cache empty for order %d", order);
+			mlx5_ib_dbg(dev, "cache empty for order %d\n", order);
 			mr = NULL;
 		}
 	} else if (!MLX5_CAP_GEN(dev->mdev, umr_extended_translation_offset)) {
 		if (access_flags & IB_ACCESS_ON_DEMAND) {
 			err = -EINVAL;
-			pr_err("Got MR registration for ODP MR > 512MB, not supported for Connect-IB");
+			pr_err("Got MR registration for ODP MR > 512MB, not supported for Connect-IB\n");
 			goto error;
 		}
 		use_umr = false;
diff --git a/drivers/infiniband/hw/mlx5/odp.c b/drivers/infiniband/hw/mlx5/odp.c
index 3d701c7a4c91..e2197bdda89c 100644
--- a/drivers/infiniband/hw/mlx5/odp.c
+++ b/drivers/infiniband/hw/mlx5/odp.c
@@ -32,6 +32,7 @@
 
 #include <rdma/ib_umem.h>
 #include <rdma/ib_umem_odp.h>
+#include <linux/kernel.h>
 
 #include "mlx5_ib.h"
 #include "cmd.h"
@@ -929,9 +930,8 @@ static int mlx5_ib_mr_initiator_pfault_handler(
 		return -EFAULT;
 	}
 
-	if (unlikely(opcode >= sizeof(mlx5_ib_odp_opcode_cap) /
-	    sizeof(mlx5_ib_odp_opcode_cap[0]) ||
-	    !(transport_caps & mlx5_ib_odp_opcode_cap[opcode]))) {
+	if (unlikely(opcode >= ARRAY_SIZE(mlx5_ib_odp_opcode_cap) ||
+		     !(transport_caps & mlx5_ib_odp_opcode_cap[opcode]))) {
 		mlx5_ib_err(dev, "ODP fault on QP of an unsupported opcode 0x%x\n",
 			    opcode);
 		return -EFAULT;
diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c
index acb79d3a4f1d..31ad28853efa 100644
--- a/drivers/infiniband/hw/mlx5/qp.c
+++ b/drivers/infiniband/hw/mlx5/qp.c
@@ -1178,8 +1178,8 @@ static int create_raw_packet_qp_rq(struct mlx5_ib_dev *dev,
 
 	wq = MLX5_ADDR_OF(rqc, rqc, wq);
 	MLX5_SET(wq, wq, wq_type, MLX5_WQ_TYPE_CYCLIC);
-	MLX5_SET(wq, wq, end_padding_mode,
-		 MLX5_GET(qpc, qpc, end_padding_mode));
+	if (rq->flags & MLX5_IB_RQ_PCI_WRITE_END_PADDING)
+		MLX5_SET(wq, wq, end_padding_mode, MLX5_WQ_END_PAD_MODE_ALIGN);
 	MLX5_SET(wq, wq, page_offset, MLX5_GET(qpc, qpc, page_offset));
 	MLX5_SET(wq, wq, pd, MLX5_GET(qpc, qpc, pd));
 	MLX5_SET64(wq, wq, dbr_addr, MLX5_GET64(qpc, qpc, dbr_addr));
@@ -1204,8 +1204,16 @@ static void destroy_raw_packet_qp_rq(struct mlx5_ib_dev *dev,
 	mlx5_core_destroy_rq_tracked(dev->mdev, &rq->base.mqp);
 }
 
+static bool tunnel_offload_supported(struct mlx5_core_dev *dev)
+{
+	return  (MLX5_CAP_ETH(dev, tunnel_stateless_vxlan) ||
+		 MLX5_CAP_ETH(dev, tunnel_stateless_gre) ||
+		 MLX5_CAP_ETH(dev, tunnel_stateless_geneve_rx));
+}
+
 static int create_raw_packet_qp_tir(struct mlx5_ib_dev *dev,
-				    struct mlx5_ib_rq *rq, u32 tdn)
+				    struct mlx5_ib_rq *rq, u32 tdn,
+				    bool tunnel_offload_en)
 {
 	u32 *in;
 	void *tirc;
@@ -1221,6 +1229,8 @@ static int create_raw_packet_qp_tir(struct mlx5_ib_dev *dev,
 	MLX5_SET(tirc, tirc, disp_type, MLX5_TIRC_DISP_TYPE_DIRECT);
 	MLX5_SET(tirc, tirc, inline_rqn, rq->base.mqp.qpn);
 	MLX5_SET(tirc, tirc, transport_domain, tdn);
+	if (tunnel_offload_en)
+		MLX5_SET(tirc, tirc, tunneled_offload_en, 1);
 
 	err = mlx5_core_create_tir(dev->mdev, in, inlen, &rq->tirn);
 
@@ -1266,12 +1276,15 @@ static int create_raw_packet_qp(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp,
 
 		if (qp->flags & MLX5_IB_QP_CVLAN_STRIPPING)
 			rq->flags |= MLX5_IB_RQ_CVLAN_STRIPPING;
+		if (qp->flags & MLX5_IB_QP_PCI_WRITE_END_PADDING)
+			rq->flags |= MLX5_IB_RQ_PCI_WRITE_END_PADDING;
 		err = create_raw_packet_qp_rq(dev, rq, in);
 		if (err)
 			goto err_destroy_sq;
 
 
-		err = create_raw_packet_qp_tir(dev, rq, tdn);
+		err = create_raw_packet_qp_tir(dev, rq, tdn,
+					       qp->tunnel_offload_en);
 		if (err)
 			goto err_destroy_rq;
 	}
@@ -1358,7 +1371,7 @@ static int create_rss_raw_qp_tir(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp,
 	if (udata->outlen < min_resp_len)
 		return -EINVAL;
 
-	required_cmd_sz = offsetof(typeof(ucmd), reserved1) + sizeof(ucmd.reserved1);
+	required_cmd_sz = offsetof(typeof(ucmd), flags) + sizeof(ucmd.flags);
 	if (udata->inlen < required_cmd_sz) {
 		mlx5_ib_dbg(dev, "invalid inlen\n");
 		return -EINVAL;
@@ -1381,8 +1394,20 @@ static int create_rss_raw_qp_tir(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp,
 		return -EOPNOTSUPP;
 	}
 
-	if (memchr_inv(ucmd.reserved, 0, sizeof(ucmd.reserved)) || ucmd.reserved1) {
-		mlx5_ib_dbg(dev, "invalid reserved\n");
+	if (ucmd.flags & ~MLX5_QP_FLAG_TUNNEL_OFFLOADS) {
+		mlx5_ib_dbg(dev, "invalid flags\n");
+		return -EOPNOTSUPP;
+	}
+
+	if (ucmd.flags & MLX5_QP_FLAG_TUNNEL_OFFLOADS &&
+	    !tunnel_offload_supported(dev->mdev)) {
+		mlx5_ib_dbg(dev, "tunnel offloads isn't supported\n");
+		return -EOPNOTSUPP;
+	}
+
+	if (ucmd.rx_hash_fields_mask & MLX5_RX_HASH_INNER &&
+	    !(ucmd.flags & MLX5_QP_FLAG_TUNNEL_OFFLOADS)) {
+		mlx5_ib_dbg(dev, "Tunnel offloads must be set for inner RSS\n");
 		return -EOPNOTSUPP;
 	}
 
@@ -1405,6 +1430,15 @@ static int create_rss_raw_qp_tir(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp,
 	MLX5_SET(tirc, tirc, transport_domain, tdn);
 
 	hfso = MLX5_ADDR_OF(tirc, tirc, rx_hash_field_selector_outer);
+
+	if (ucmd.flags & MLX5_QP_FLAG_TUNNEL_OFFLOADS)
+		MLX5_SET(tirc, tirc, tunneled_offload_en, 1);
+
+	if (ucmd.rx_hash_fields_mask & MLX5_RX_HASH_INNER)
+		hfso = MLX5_ADDR_OF(tirc, tirc, rx_hash_field_selector_inner);
+	else
+		hfso = MLX5_ADDR_OF(tirc, tirc, rx_hash_field_selector_outer);
+
 	switch (ucmd.rx_hash_function) {
 	case MLX5_RX_HASH_FUNC_TOEPLITZ:
 	{
@@ -1604,6 +1638,14 @@ static int create_qp_common(struct mlx5_ib_dev *dev, struct ib_pd *pd,
 
 		qp->wq_sig = !!(ucmd.flags & MLX5_QP_FLAG_SIGNATURE);
 		qp->scat_cqe = !!(ucmd.flags & MLX5_QP_FLAG_SCATTER_CQE);
+		if (ucmd.flags & MLX5_QP_FLAG_TUNNEL_OFFLOADS) {
+			if (init_attr->qp_type != IB_QPT_RAW_PACKET ||
+			    !tunnel_offload_supported(mdev)) {
+				mlx5_ib_dbg(dev, "Tunnel offload isn't supported\n");
+				return -EOPNOTSUPP;
+			}
+			qp->tunnel_offload_en = true;
+		}
 
 		if (init_attr->create_flags & IB_QP_CREATE_SOURCE_QPN) {
 			if (init_attr->qp_type != IB_QPT_UD ||
@@ -1781,6 +1823,19 @@ static int create_qp_common(struct mlx5_ib_dev *dev, struct ib_pd *pd,
 		qp->flags |= MLX5_IB_QP_LSO;
 	}
 
+	if (init_attr->create_flags & IB_QP_CREATE_PCI_WRITE_END_PADDING) {
+		if (!MLX5_CAP_GEN(dev->mdev, end_pad)) {
+			mlx5_ib_dbg(dev, "scatter end padding is not supported\n");
+			err = -EOPNOTSUPP;
+			goto err;
+		} else if (init_attr->qp_type != IB_QPT_RAW_PACKET) {
+			MLX5_SET(qpc, qpc, end_padding_mode,
+				 MLX5_WQ_END_PAD_MODE_ALIGN);
+		} else {
+			qp->flags |= MLX5_IB_QP_PCI_WRITE_END_PADDING;
+		}
+	}
+
 	if (init_attr->qp_type == IB_QPT_RAW_PACKET ||
 	    qp->flags & MLX5_IB_QP_UNDERLAY) {
 		qp->raw_packet_qp.sq.ubuffer.buf_addr = ucmd.sq_buf_addr;
@@ -1825,6 +1880,7 @@ err_create:
 	else if (qp->create_type == MLX5_QP_KERNEL)
 		destroy_qp_kernel(dev, qp);
 
+err:
 	kvfree(in);
 	return err;
 }
@@ -2283,8 +2339,12 @@ static int mlx5_set_path(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp,
 		if (err)
 			return err;
 		memcpy(path->rmac, ah->roce.dmac, sizeof(ah->roce.dmac));
-		path->udp_sport = mlx5_get_roce_udp_sport(dev, port,
-							  grh->sgid_index);
+		if (qp->ibqp.qp_type == IB_QPT_RC ||
+		    qp->ibqp.qp_type == IB_QPT_UC ||
+		    qp->ibqp.qp_type == IB_QPT_XRC_INI ||
+		    qp->ibqp.qp_type == IB_QPT_XRC_TGT)
+			path->udp_sport = mlx5_get_roce_udp_sport(dev, port,
+								  grh->sgid_index);
 		path->dci_cfi_prio_sl = (sl & 0x7) << 4;
 		if (gid_type == IB_GID_TYPE_ROCE_UDP_ENCAP)
 			path->ecn_dscp = (grh->traffic_class >> 2) & 0x3f;
@@ -3858,7 +3918,6 @@ int mlx5_ib_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
 	unsigned long flags;
 	unsigned idx;
 	int err = 0;
-	int inl = 0;
 	int num_sge;
 	void *seg;
 	int nreq;
@@ -4053,6 +4112,7 @@ int mlx5_ib_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
 				*bad_wr = wr;
 				goto out;
 			}
+			/* fall through */
 		case MLX5_IB_QPT_HW_GSI:
 			set_datagram_seg(seg, wr);
 			seg += sizeof(struct mlx5_wqe_datagram_seg);
@@ -4116,7 +4176,6 @@ int mlx5_ib_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
 				*bad_wr = wr;
 				goto out;
 			}
-			inl = 1;
 			size += sz;
 		} else {
 			dpseg = seg;
@@ -4707,9 +4766,27 @@ static int  create_rq(struct mlx5_ib_rwq *rwq, struct ib_pd *pd,
 	MLX5_SET(rqc,  rqc, state, MLX5_RQC_STATE_RST);
 	MLX5_SET(rqc,  rqc, flush_in_error_en, 1);
 	wq = MLX5_ADDR_OF(rqc, rqc, wq);
-	MLX5_SET(wq, wq, wq_type, MLX5_WQ_TYPE_CYCLIC);
-	MLX5_SET(wq, wq, end_padding_mode, MLX5_WQ_END_PAD_MODE_ALIGN);
+	MLX5_SET(wq, wq, wq_type,
+		 rwq->create_flags & MLX5_IB_WQ_FLAGS_STRIDING_RQ ?
+		 MLX5_WQ_TYPE_CYCLIC_STRIDING_RQ : MLX5_WQ_TYPE_CYCLIC);
+	if (init_attr->create_flags & IB_WQ_FLAGS_PCI_WRITE_END_PADDING) {
+		if (!MLX5_CAP_GEN(dev->mdev, end_pad)) {
+			mlx5_ib_dbg(dev, "Scatter end padding is not supported\n");
+			err = -EOPNOTSUPP;
+			goto out;
+		} else {
+			MLX5_SET(wq, wq, end_padding_mode, MLX5_WQ_END_PAD_MODE_ALIGN);
+		}
+	}
 	MLX5_SET(wq, wq, log_wq_stride, rwq->log_rq_stride);
+	if (rwq->create_flags & MLX5_IB_WQ_FLAGS_STRIDING_RQ) {
+		MLX5_SET(wq, wq, two_byte_shift_en, rwq->two_byte_shift_en);
+		MLX5_SET(wq, wq, log_wqe_stride_size,
+			 rwq->single_stride_log_num_of_bytes -
+			 MLX5_MIN_SINGLE_STRIDE_LOG_NUM_BYTES);
+		MLX5_SET(wq, wq, log_wqe_num_of_strides, rwq->log_num_strides -
+			 MLX5_MIN_SINGLE_WQE_LOG_NUM_STRIDES);
+	}
 	MLX5_SET(wq, wq, log_wq_sz, rwq->log_rq_size);
 	MLX5_SET(wq, wq, pd, to_mpd(pd)->pdn);
 	MLX5_SET(wq, wq, page_offset, rwq->rq_page_offset);
@@ -4791,7 +4868,8 @@ static int prepare_user_rq(struct ib_pd *pd,
 	int err;
 	size_t required_cmd_sz;
 
-	required_cmd_sz = offsetof(typeof(ucmd), reserved) + sizeof(ucmd.reserved);
+	required_cmd_sz = offsetof(typeof(ucmd), single_stride_log_num_of_bytes)
+		+ sizeof(ucmd.single_stride_log_num_of_bytes);
 	if (udata->inlen < required_cmd_sz) {
 		mlx5_ib_dbg(dev, "invalid inlen\n");
 		return -EINVAL;
@@ -4809,14 +4887,39 @@ static int prepare_user_rq(struct ib_pd *pd,
 		return -EFAULT;
 	}
 
-	if (ucmd.comp_mask) {
+	if (ucmd.comp_mask & (~MLX5_IB_CREATE_WQ_STRIDING_RQ)) {
 		mlx5_ib_dbg(dev, "invalid comp mask\n");
 		return -EOPNOTSUPP;
-	}
-
-	if (ucmd.reserved) {
-		mlx5_ib_dbg(dev, "invalid reserved\n");
-		return -EOPNOTSUPP;
+	} else if (ucmd.comp_mask & MLX5_IB_CREATE_WQ_STRIDING_RQ) {
+		if (!MLX5_CAP_GEN(dev->mdev, striding_rq)) {
+			mlx5_ib_dbg(dev, "Striding RQ is not supported\n");
+			return -EOPNOTSUPP;
+		}
+		if ((ucmd.single_stride_log_num_of_bytes <
+		    MLX5_MIN_SINGLE_STRIDE_LOG_NUM_BYTES) ||
+		    (ucmd.single_stride_log_num_of_bytes >
+		     MLX5_MAX_SINGLE_STRIDE_LOG_NUM_BYTES)) {
+			mlx5_ib_dbg(dev, "Invalid log stride size (%u. Range is %u - %u)\n",
+				    ucmd.single_stride_log_num_of_bytes,
+				    MLX5_MIN_SINGLE_STRIDE_LOG_NUM_BYTES,
+				    MLX5_MAX_SINGLE_STRIDE_LOG_NUM_BYTES);
+			return -EINVAL;
+		}
+		if ((ucmd.single_wqe_log_num_of_strides >
+		    MLX5_MAX_SINGLE_WQE_LOG_NUM_STRIDES) ||
+		     (ucmd.single_wqe_log_num_of_strides <
+			MLX5_MIN_SINGLE_WQE_LOG_NUM_STRIDES)) {
+			mlx5_ib_dbg(dev, "Invalid log num strides (%u. Range is %u - %u)\n",
+				    ucmd.single_wqe_log_num_of_strides,
+				    MLX5_MIN_SINGLE_WQE_LOG_NUM_STRIDES,
+				    MLX5_MAX_SINGLE_WQE_LOG_NUM_STRIDES);
+			return -EINVAL;
+		}
+		rwq->single_stride_log_num_of_bytes =
+			ucmd.single_stride_log_num_of_bytes;
+		rwq->log_num_strides = ucmd.single_wqe_log_num_of_strides;
+		rwq->two_byte_shift_en = !!ucmd.two_byte_shift_en;
+		rwq->create_flags |= MLX5_IB_WQ_FLAGS_STRIDING_RQ;
 	}
 
 	err = set_user_rq_size(dev, init_attr, &ucmd, rwq);
@@ -5054,6 +5157,12 @@ int mlx5_ib_modify_wq(struct ib_wq *wq, struct ib_wq_attr *wq_attr,
 			MLX5_SET(rqc, rqc, vsd,
 				 (wq_attr->flags & IB_WQ_FLAGS_CVLAN_STRIPPING) ? 0 : 1);
 		}
+
+		if (wq_attr->flags_mask & IB_WQ_FLAGS_PCI_WRITE_END_PADDING) {
+			mlx5_ib_dbg(dev, "Modifying scatter end padding is not supported\n");
+			err = -EOPNOTSUPP;
+			goto out;
+		}
 	}
 
 	if (curr_wq_state == IB_WQS_RESET && wq_state == IB_WQS_RDY) {