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

Pull rdma updates from Doug Ledford:
 "This is a big pull request.

  Of note is that I'm sending you the new ioctl API for the rdma
  subsystem. We put it up on linux-api@, but didn't get much response.
  The API is complex, but it solves two different problems in one go:

   1) The bi-directional nature of the RDMA file write calls, which
      created the security hole we had to handle (and for which the fix
      is now causing problems for systems in production, we were a bit
      over zealous in the fix and the ability to open a device, then
      fork, then create new queue pairs on the device and use them is
      broken).

   2) The bloat caused by different vendors implementing extensions to
      the base verbs API. Each vendor's hardware is slightly different,
      and the hardware might be suitable for one extension but not
      another.

      By the time we add generic extensions for all the different ways
      that the different hardware can offload things, the API becomes
      bloated. Things like our completion structs have started to exceed
      a cache line in size because of all the elements needed to support
      this. That in turn shows up heavily in the performance graphs with
      a noticable drop in performance on 100Gigabit links as our
      completion structs go from occupying one cache line to 1+.

      This API makes things like the completion structs modular in a
      very similar way to netlink so that your structs can only include
      the items needed for the offloads/features you are actually using
      on a given queue pair. In that way we support everything, but only
      use what we need, and our structs stay smaller.

  The ioctl API is better explained by the posting on linux-api@ than I
  can explain it here, so I'll just leave it at that.

  The rest of the pull request is typical stuff.

  Updates for 4.14 kernel merge window

   - Lots of hfi1 driver updates (mixed with a few qib and core updates
     as well)

   - rxe updates

   - various mlx updates

   - Set default roce type to RoCEv2

   - Several larger fixes for bnxt_re that were too big for -rc

   - Several larger fixes for qedr that, likewise, were too big for -rc

   - Misc core changes

   - Make the hns_roce driver compilable on arches other than aarch64 so
     we can more easily debug build issues related to it

   - Add rdma-netlink infrastructure updates

   - Add automatic IRQ affinity infrastructure

   - Add 32bit lid support

   - Lots of misc fixes across the subsystem from random people

   - Autoloading of RDMA netlink modules

   - PCI pool cleanups from Romain Perier

   - mlx5 driver feature additions and fixes

   - Hardware tag matchine feature

   - Fix sleeping in atomic when resolving roce ah

   - Add experimental ioctl interface as posted to linux-api@"

* tag 'for-linus-ioctl' of git://git.kernel.org/pub/scm/linux/kernel/git/dledford/rdma: (328 commits)
  IB/core: Expose ioctl interface through experimental Kconfig
  IB/core: Assign root to all drivers
  IB/core: Add completion queue (cq) object actions
  IB/core: Add legacy driver's user-data
  IB/core: Export ioctl enum types to user-space
  IB/core: Explicitly destroy an object while keeping uobject
  IB/core: Add macros for declaring methods and attributes
  IB/core: Add uverbs merge trees functionality
  IB/core: Add DEVICE object and root tree structure
  IB/core: Declare an object instead of declaring only type attributes
  IB/core: Add new ioctl interface
  RDMA/vmw_pvrdma: Fix a signedness
  RDMA/vmw_pvrdma: Report network header type in WC
  IB/core: Add might_sleep() annotation to ib_init_ah_from_wc()
  IB/cm: Fix sleeping in atomic when RoCE is used
  IB/core: Add support to finalize objects in one transaction
  IB/core: Add a generic way to execute an operation on a uobject
  Documentation: Hardware tag matching
  IB/mlx5: Support IB_SRQT_TM
  net/mlx5: Add XRQ support
  ...

23 files changed, 395 insertions, 165 deletions

diff --git a/drivers/net/ethernet/mellanox/mlx4/cmd.c b/drivers/net/ethernet/mellanox/mlx4/cmd.c
index 674773b28b2e..78b89ceb4f46 100644
--- a/drivers/net/ethernet/mellanox/mlx4/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx4/cmd.c
@@ -2535,8 +2535,8 @@ int mlx4_cmd_init(struct mlx4_dev *dev)
 	}
 
 	if (!priv->cmd.pool) {
-		priv->cmd.pool = pci_pool_create("mlx4_cmd",
-						 dev->persist->pdev,
+		priv->cmd.pool = dma_pool_create("mlx4_cmd",
+						 &dev->persist->pdev->dev,
 						 MLX4_MAILBOX_SIZE,
 						 MLX4_MAILBOX_SIZE, 0);
 		if (!priv->cmd.pool)
@@ -2607,7 +2607,7 @@ void mlx4_cmd_cleanup(struct mlx4_dev *dev, int cleanup_mask)
 	struct mlx4_priv *priv = mlx4_priv(dev);
 
 	if (priv->cmd.pool && (cleanup_mask & MLX4_CMD_CLEANUP_POOL)) {
-		pci_pool_destroy(priv->cmd.pool);
+		dma_pool_destroy(priv->cmd.pool);
 		priv->cmd.pool = NULL;
 	}
 
@@ -2699,7 +2699,7 @@ struct mlx4_cmd_mailbox *mlx4_alloc_cmd_mailbox(struct mlx4_dev *dev)
 	if (!mailbox)
 		return ERR_PTR(-ENOMEM);
 
-	mailbox->buf = pci_pool_zalloc(mlx4_priv(dev)->cmd.pool, GFP_KERNEL,
+	mailbox->buf = dma_pool_zalloc(mlx4_priv(dev)->cmd.pool, GFP_KERNEL,
 				       &mailbox->dma);
 	if (!mailbox->buf) {
 		kfree(mailbox);
@@ -2716,7 +2716,7 @@ void mlx4_free_cmd_mailbox(struct mlx4_dev *dev,
 	if (!mailbox)
 		return;
 
-	pci_pool_free(mlx4_priv(dev)->cmd.pool, mailbox->buf, mailbox->dma);
+	dma_pool_free(mlx4_priv(dev)->cmd.pool, mailbox->buf, mailbox->dma);
 	kfree(mailbox);
 }
 EXPORT_SYMBOL_GPL(mlx4_free_cmd_mailbox);
diff --git a/drivers/net/ethernet/mellanox/mlx4/cq.c b/drivers/net/ethernet/mellanox/mlx4/cq.c
index c56a511b918e..72eb50cd5ecd 100644
--- a/drivers/net/ethernet/mellanox/mlx4/cq.c
+++ b/drivers/net/ethernet/mellanox/mlx4/cq.c
@@ -241,13 +241,14 @@ err_out:
 	return err;
 }
 
-static int mlx4_cq_alloc_icm(struct mlx4_dev *dev, int *cqn)
+static int mlx4_cq_alloc_icm(struct mlx4_dev *dev, int *cqn, u8 usage)
 {
+	u32 in_modifier = RES_CQ | (((u32)usage & 3) << 30);
 	u64 out_param;
 	int err;
 
 	if (mlx4_is_mfunc(dev)) {
-		err = mlx4_cmd_imm(dev, 0, &out_param, RES_CQ,
+		err = mlx4_cmd_imm(dev, 0, &out_param, in_modifier,
 				   RES_OP_RESERVE_AND_MAP, MLX4_CMD_ALLOC_RES,
 				   MLX4_CMD_TIME_CLASS_A, MLX4_CMD_WRAPPED);
 		if (err)
@@ -303,7 +304,7 @@ int mlx4_cq_alloc(struct mlx4_dev *dev, int nent,
 
 	cq->vector = vector;
 
-	err = mlx4_cq_alloc_icm(dev, &cq->cqn);
+	err = mlx4_cq_alloc_icm(dev, &cq->cqn, cq->usage);
 	if (err)
 		return err;
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_cq.c b/drivers/net/ethernet/mellanox/mlx4/en_cq.c
index 85fe17e4dcfb..f849eec21824 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_cq.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_cq.c
@@ -140,6 +140,7 @@ int mlx4_en_activate_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq,
 	    (cq->type == RX && priv->hwtstamp_config.rx_filter))
 		timestamp_en = 1;
 
+	cq->mcq.usage = MLX4_RES_USAGE_DRIVER;
 	err = mlx4_cq_alloc(mdev->dev, cq->size, &cq->wqres.mtt,
 			    &mdev->priv_uar, cq->wqres.db.dma, &cq->mcq,
 			    cq->vector, 0, timestamp_en);
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index 3a291fc1780a..e3e6d9fa69fd 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -651,7 +651,8 @@ static int mlx4_en_get_qp(struct mlx4_en_priv *priv)
 		return 0;
 	}
 
-	err = mlx4_qp_reserve_range(dev, 1, 1, qpn, MLX4_RESERVE_A0_QP);
+	err = mlx4_qp_reserve_range(dev, 1, 1, qpn, MLX4_RESERVE_A0_QP,
+				    MLX4_RES_USAGE_DRIVER);
 	en_dbg(DRV, priv, "Reserved qp %d\n", *qpn);
 	if (err) {
 		en_err(priv, "Failed to reserve qp for mac registration\n");
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
index bf1638044a7a..ec24c4057be6 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
@@ -1088,7 +1088,8 @@ int mlx4_en_create_drop_qp(struct mlx4_en_priv *priv)
 	u32 qpn;
 
 	err = mlx4_qp_reserve_range(priv->mdev->dev, 1, 1, &qpn,
-				    MLX4_RESERVE_A0_QP);
+				    MLX4_RESERVE_A0_QP,
+				    MLX4_RES_USAGE_DRIVER);
 	if (err) {
 		en_err(priv, "Failed reserving drop qpn\n");
 		return err;
@@ -1134,7 +1135,8 @@ int mlx4_en_config_rss_steer(struct mlx4_en_priv *priv)
 	flags = priv->rx_ring_num == 1 ? MLX4_RESERVE_A0_QP : 0;
 	err = mlx4_qp_reserve_range(mdev->dev, priv->rx_ring_num,
 				    priv->rx_ring_num,
-				    &rss_map->base_qpn, flags);
+				    &rss_map->base_qpn, flags,
+				    MLX4_RES_USAGE_DRIVER);
 	if (err) {
 		en_err(priv, "Failed reserving %d qps\n", priv->rx_ring_num);
 		return err;
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
index 73faa3d77921..a81db2582555 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
@@ -105,7 +105,8 @@ int mlx4_en_create_tx_ring(struct mlx4_en_priv *priv,
 	       (unsigned long long) ring->sp_wqres.buf.direct.map);
 
 	err = mlx4_qp_reserve_range(mdev->dev, 1, 1, &ring->qpn,
-				    MLX4_RESERVE_ETH_BF_QP);
+				    MLX4_RESERVE_ETH_BF_QP,
+				    MLX4_RES_USAGE_DRIVER);
 	if (err) {
 		en_err(priv, "failed reserving qp for TX ring\n");
 		goto err_hwq_res;
diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index 5fe5cdc51357..a594bfd9e095 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -2477,7 +2477,7 @@ static int mlx4_allocate_default_counters(struct mlx4_dev *dev)
 		priv->def_counter[port] = -1;
 
 	for (port = 0; port < dev->caps.num_ports; port++) {
-		err = mlx4_counter_alloc(dev, &idx);
+		err = mlx4_counter_alloc(dev, &idx, MLX4_RES_USAGE_DRIVER);
 
 		if (!err || err == -ENOSPC) {
 			priv->def_counter[port] = idx;
@@ -2519,13 +2519,14 @@ int __mlx4_counter_alloc(struct mlx4_dev *dev, u32 *idx)
 	return 0;
 }
 
-int mlx4_counter_alloc(struct mlx4_dev *dev, u32 *idx)
+int mlx4_counter_alloc(struct mlx4_dev *dev, u32 *idx, u8 usage)
 {
+	u32 in_modifier = RES_COUNTER | (((u32)usage & 3) << 30);
 	u64 out_param;
 	int err;
 
 	if (mlx4_is_mfunc(dev)) {
-		err = mlx4_cmd_imm(dev, 0, &out_param, RES_COUNTER,
+		err = mlx4_cmd_imm(dev, 0, &out_param, in_modifier,
 				   RES_OP_RESERVE, MLX4_CMD_ALLOC_RES,
 				   MLX4_CMD_TIME_CLASS_A, MLX4_CMD_WRAPPED);
 		if (!err)
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
index 706d7f21ac5c..852d00a5b016 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
@@ -626,7 +626,7 @@ struct mlx4_mgm {
 };
 
 struct mlx4_cmd {
-	struct pci_pool	       *pool;
+	struct dma_pool	       *pool;
 	void __iomem	       *hcr;
 	struct mutex		slave_cmd_mutex;
 	struct semaphore	poll_sem;
diff --git a/drivers/net/ethernet/mellanox/mlx4/qp.c b/drivers/net/ethernet/mellanox/mlx4/qp.c
index 26747212526b..5e5b4475b85e 100644
--- a/drivers/net/ethernet/mellanox/mlx4/qp.c
+++ b/drivers/net/ethernet/mellanox/mlx4/qp.c
@@ -245,8 +245,9 @@ int __mlx4_qp_reserve_range(struct mlx4_dev *dev, int cnt, int align,
 }
 
 int mlx4_qp_reserve_range(struct mlx4_dev *dev, int cnt, int align,
-			  int *base, u8 flags)
+			  int *base, u8 flags, u8 usage)
 {
+	u32 in_modifier = RES_QP | (((u32)usage & 3) << 30);
 	u64 in_param = 0;
 	u64 out_param;
 	int err;
@@ -258,7 +259,7 @@ int mlx4_qp_reserve_range(struct mlx4_dev *dev, int cnt, int align,
 		set_param_l(&in_param, (((u32)flags) << 24) | (u32)cnt);
 		set_param_h(&in_param, align);
 		err = mlx4_cmd_imm(dev, in_param, &out_param,
-				   RES_QP, RES_OP_RESERVE,
+				   in_modifier, RES_OP_RESERVE,
 				   MLX4_CMD_ALLOC_RES,
 				   MLX4_CMD_TIME_CLASS_A, MLX4_CMD_WRAPPED);
 		if (err)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index 31cbe5e86a01..1acbb721f38d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -1110,7 +1110,7 @@ static struct mlx5_cmd_mailbox *alloc_cmd_box(struct mlx5_core_dev *dev,
 	if (!mailbox)
 		return ERR_PTR(-ENOMEM);
 
-	mailbox->buf = pci_pool_zalloc(dev->cmd.pool, flags,
+	mailbox->buf = dma_pool_zalloc(dev->cmd.pool, flags,
 				       &mailbox->dma);
 	if (!mailbox->buf) {
 		mlx5_core_dbg(dev, "failed allocation\n");
@@ -1125,7 +1125,7 @@ static struct mlx5_cmd_mailbox *alloc_cmd_box(struct mlx5_core_dev *dev,
 static void free_cmd_box(struct mlx5_core_dev *dev,
 			 struct mlx5_cmd_mailbox *mailbox)
 {
-	pci_pool_free(dev->cmd.pool, mailbox->buf, mailbox->dma);
+	dma_pool_free(dev->cmd.pool, mailbox->buf, mailbox->dma);
 	kfree(mailbox);
 }
 
@@ -1776,7 +1776,8 @@ int mlx5_cmd_init(struct mlx5_core_dev *dev)
 		return -EINVAL;
 	}
 
-	cmd->pool = pci_pool_create("mlx5_cmd", dev->pdev, size, align, 0);
+	cmd->pool = dma_pool_create("mlx5_cmd", &dev->pdev->dev, size, align,
+				    0);
 	if (!cmd->pool)
 		return -ENOMEM;
 
@@ -1866,7 +1867,7 @@ err_free_page:
 	free_cmd_page(dev, cmd);
 
 err_free_pool:
-	pci_pool_destroy(cmd->pool);
+	dma_pool_destroy(cmd->pool);
 
 	return err;
 }
@@ -1880,6 +1881,6 @@ void mlx5_cmd_cleanup(struct mlx5_core_dev *dev)
 	destroy_workqueue(cmd->wq);
 	destroy_msg_cache(dev);
 	free_cmd_page(dev, cmd);
-	pci_pool_destroy(cmd->pool);
+	dma_pool_destroy(cmd->pool);
 }
 EXPORT_SYMBOL(mlx5_cmd_cleanup);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 2f26fb34d741..040d1af310b4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -596,7 +596,6 @@ struct mlx5e_channel {
 	struct mlx5_core_dev      *mdev;
 	struct mlx5e_tstamp       *tstamp;
 	int                        ix;
-	int                        cpu;
 };
 
 struct mlx5e_channels {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 6ad7f07e7861..d75f3099d164 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -71,6 +71,11 @@ struct mlx5e_channel_param {
 	struct mlx5e_cq_param      icosq_cq;
 };
 
+static int mlx5e_get_node(struct mlx5e_priv *priv, int ix)
+{
+	return pci_irq_get_node(priv->mdev->pdev, MLX5_EQ_VEC_COMP_BASE + ix);
+}
+
 static bool mlx5e_check_fragmented_striding_rq_cap(struct mlx5_core_dev *mdev)
 {
 	return MLX5_CAP_GEN(mdev, striding_rq) &&
@@ -396,7 +401,7 @@ static void mlx5e_enable_async_events(struct mlx5e_priv *priv)
 static void mlx5e_disable_async_events(struct mlx5e_priv *priv)
 {
 	clear_bit(MLX5E_STATE_ASYNC_EVENTS_ENABLED, &priv->state);
-	synchronize_irq(mlx5_get_msix_vec(priv->mdev, MLX5_EQ_VEC_ASYNC));
+	synchronize_irq(pci_irq_vector(priv->mdev->pdev, MLX5_EQ_VEC_ASYNC));
 }
 
 static inline int mlx5e_get_wqe_mtt_sz(void)
@@ -443,16 +448,17 @@ static int mlx5e_rq_alloc_mpwqe_info(struct mlx5e_rq *rq,
 	int wq_sz = mlx5_wq_ll_get_size(&rq->wq);
 	int mtt_sz = mlx5e_get_wqe_mtt_sz();
 	int mtt_alloc = mtt_sz + MLX5_UMR_ALIGN - 1;
+	int node = mlx5e_get_node(c->priv, c->ix);
 	int i;
 
 	rq->mpwqe.info = kzalloc_node(wq_sz * sizeof(*rq->mpwqe.info),
-				      GFP_KERNEL, cpu_to_node(c->cpu));
+					GFP_KERNEL, node);
 	if (!rq->mpwqe.info)
 		goto err_out;
 
 	/* We allocate more than mtt_sz as we will align the pointer */
-	rq->mpwqe.mtt_no_align = kzalloc_node(mtt_alloc * wq_sz, GFP_KERNEL,
-					cpu_to_node(c->cpu));
+	rq->mpwqe.mtt_no_align = kzalloc_node(mtt_alloc * wq_sz,
+					GFP_KERNEL, node);
 	if (unlikely(!rq->mpwqe.mtt_no_align))
 		goto err_free_wqe_info;
 
@@ -560,7 +566,7 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c,
 	int err;
 	int i;
 
-	rqp->wq.db_numa_node = cpu_to_node(c->cpu);
+	rqp->wq.db_numa_node = mlx5e_get_node(c->priv, c->ix);
 
 	err = mlx5_wq_ll_create(mdev, &rqp->wq, rqc_wq, &rq->wq,
 				&rq->wq_ctrl);
@@ -627,7 +633,8 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c,
 	default: /* MLX5_WQ_TYPE_LINKED_LIST */
 		rq->wqe.frag_info =
 			kzalloc_node(wq_sz * sizeof(*rq->wqe.frag_info),
-				     GFP_KERNEL, cpu_to_node(c->cpu));
+				     GFP_KERNEL,
+				     mlx5e_get_node(c->priv, c->ix));
 		if (!rq->wqe.frag_info) {
 			err = -ENOMEM;
 			goto err_rq_wq_destroy;
@@ -992,13 +999,13 @@ static int mlx5e_alloc_xdpsq(struct mlx5e_channel *c,
 	sq->uar_map   = mdev->mlx5e_res.bfreg.map;
 	sq->min_inline_mode = params->tx_min_inline_mode;
 
-	param->wq.db_numa_node = cpu_to_node(c->cpu);
+	param->wq.db_numa_node = mlx5e_get_node(c->priv, c->ix);
 	err = mlx5_wq_cyc_create(mdev, &param->wq, sqc_wq, &sq->wq, &sq->wq_ctrl);
 	if (err)
 		return err;
 	sq->wq.db = &sq->wq.db[MLX5_SND_DBR];
 
-	err = mlx5e_alloc_xdpsq_db(sq, cpu_to_node(c->cpu));
+	err = mlx5e_alloc_xdpsq_db(sq, mlx5e_get_node(c->priv, c->ix));
 	if (err)
 		goto err_sq_wq_destroy;
 
@@ -1046,13 +1053,13 @@ static int mlx5e_alloc_icosq(struct mlx5e_channel *c,
 	sq->channel   = c;
 	sq->uar_map   = mdev->mlx5e_res.bfreg.map;
 
-	param->wq.db_numa_node = cpu_to_node(c->cpu);
+	param->wq.db_numa_node = mlx5e_get_node(c->priv, c->ix);
 	err = mlx5_wq_cyc_create(mdev, &param->wq, sqc_wq, &sq->wq, &sq->wq_ctrl);
 	if (err)
 		return err;
 	sq->wq.db = &sq->wq.db[MLX5_SND_DBR];
 
-	err = mlx5e_alloc_icosq_db(sq, cpu_to_node(c->cpu));
+	err = mlx5e_alloc_icosq_db(sq, mlx5e_get_node(c->priv, c->ix));
 	if (err)
 		goto err_sq_wq_destroy;
 
@@ -1118,13 +1125,13 @@ static int mlx5e_alloc_txqsq(struct mlx5e_channel *c,
 	if (MLX5_IPSEC_DEV(c->priv->mdev))
 		set_bit(MLX5E_SQ_STATE_IPSEC, &sq->state);
 
-	param->wq.db_numa_node = cpu_to_node(c->cpu);
+	param->wq.db_numa_node = mlx5e_get_node(c->priv, c->ix);
 	err = mlx5_wq_cyc_create(mdev, &param->wq, sqc_wq, &sq->wq, &sq->wq_ctrl);
 	if (err)
 		return err;
 	sq->wq.db    = &sq->wq.db[MLX5_SND_DBR];
 
-	err = mlx5e_alloc_txqsq_db(sq, cpu_to_node(c->cpu));
+	err = mlx5e_alloc_txqsq_db(sq, mlx5e_get_node(c->priv, c->ix));
 	if (err)
 		goto err_sq_wq_destroy;
 
@@ -1496,8 +1503,8 @@ static int mlx5e_alloc_cq(struct mlx5e_channel *c,
 	struct mlx5_core_dev *mdev = c->priv->mdev;
 	int err;
 
-	param->wq.buf_numa_node = cpu_to_node(c->cpu);
-	param->wq.db_numa_node  = cpu_to_node(c->cpu);
+	param->wq.buf_numa_node = mlx5e_get_node(c->priv, c->ix);
+	param->wq.db_numa_node  = mlx5e_get_node(c->priv, c->ix);
 	param->eq_ix   = c->ix;
 
 	err = mlx5e_alloc_cq_common(mdev, param, cq);
@@ -1596,11 +1603,6 @@ static void mlx5e_close_cq(struct mlx5e_cq *cq)
 	mlx5e_free_cq(cq);
 }
 
-static int mlx5e_get_cpu(struct mlx5e_priv *priv, int ix)
-{
-	return cpumask_first(priv->mdev->priv.irq_info[ix].mask);
-}
-
 static int mlx5e_open_tx_cqs(struct mlx5e_channel *c,
 			     struct mlx5e_params *params,
 			     struct mlx5e_channel_param *cparam)
@@ -1749,11 +1751,10 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix,
 {
 	struct mlx5e_cq_moder icocq_moder = {0, 0};
 	struct net_device *netdev = priv->netdev;
-	int cpu = mlx5e_get_cpu(priv, ix);
 	struct mlx5e_channel *c;
 	int err;
 
-	c = kzalloc_node(sizeof(*c), GFP_KERNEL, cpu_to_node(cpu));
+	c = kzalloc_node(sizeof(*c), GFP_KERNEL, mlx5e_get_node(priv, ix));
 	if (!c)
 		return -ENOMEM;
 
@@ -1761,7 +1762,6 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix,
 	c->mdev     = priv->mdev;
 	c->tstamp   = &priv->tstamp;
 	c->ix       = ix;
-	c->cpu      = cpu;
 	c->pdev     = &priv->mdev->pdev->dev;
 	c->netdev   = priv->netdev;
 	c->mkey_be  = cpu_to_be32(priv->mdev->mlx5e_res.mkey.key);
@@ -1847,7 +1847,8 @@ static void mlx5e_activate_channel(struct mlx5e_channel *c)
 	for (tc = 0; tc < c->num_tc; tc++)
 		mlx5e_activate_txqsq(&c->sq[tc]);
 	mlx5e_activate_rq(&c->rq);
-	netif_set_xps_queue(c->netdev, get_cpu_mask(c->cpu), c->ix);
+	netif_set_xps_queue(c->netdev,
+		mlx5_get_vector_affinity(c->priv->mdev, c->ix), c->ix);
 }
 
 static void mlx5e_deactivate_channel(struct mlx5e_channel *c)
@@ -3793,18 +3794,8 @@ void mlx5e_build_default_indir_rqt(struct mlx5_core_dev *mdev,
 				   u32 *indirection_rqt, int len,
 				   int num_channels)
 {
-	int node = mdev->priv.numa_node;
-	int node_num_of_cores;
 	int i;
 
-	if (node == -1)
-		node = first_online_node;
-
-	node_num_of_cores = cpumask_weight(cpumask_of_node(node));
-
-	if (node_num_of_cores)
-		num_channels = min_t(int, num_channels, node_num_of_cores);
-
 	for (i = 0; i < len; i++)
 		indirection_rqt[i] = i % num_channels;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c b/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c
index 898759fcf9ec..1f1f8af87d4d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c
@@ -189,6 +189,7 @@ struct mlx5e_lbt_priv {
 	struct packet_type pt;
 	struct completion comp;
 	bool loopback_ok;
+	bool local_lb;
 };
 
 static int
@@ -236,6 +237,13 @@ static int mlx5e_test_loopback_setup(struct mlx5e_priv *priv,
 {
 	int err = 0;
 
+	/* Temporarily enable local_lb */
+	if (MLX5_CAP_GEN(priv->mdev, disable_local_lb)) {
+		mlx5_nic_vport_query_local_lb(priv->mdev, &lbtp->local_lb);
+		if (!lbtp->local_lb)
+			mlx5_nic_vport_update_local_lb(priv->mdev, true);
+	}
+
 	err = mlx5e_refresh_tirs(priv, true);
 	if (err)
 		return err;
@@ -254,6 +262,11 @@ static int mlx5e_test_loopback_setup(struct mlx5e_priv *priv,
 static void mlx5e_test_loopback_cleanup(struct mlx5e_priv *priv,
 					struct mlx5e_lbt_priv *lbtp)
 {
+	if (MLX5_CAP_GEN(priv->mdev, disable_local_lb)) {
+		if (!lbtp->local_lb)
+			mlx5_nic_vport_update_local_lb(priv->mdev, false);
+	}
+
 	dev_remove_pack(&lbtp->pt);
 	mlx5e_refresh_tirs(priv, false);
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
index 52b9a64cd3a2..edd11ebd392e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
@@ -161,6 +161,8 @@ static const char *eqe_type_str(u8 type)
 		return "MLX5_EVENT_TYPE_NIC_VPORT_CHANGE";
 	case MLX5_EVENT_TYPE_FPGA_ERROR:
 		return "MLX5_EVENT_TYPE_FPGA_ERROR";
+	case MLX5_EVENT_TYPE_GENERAL_EVENT:
+		return "MLX5_EVENT_TYPE_GENERAL_EVENT";
 	default:
 		return "Unrecognized event";
 	}
@@ -378,6 +380,20 @@ int mlx5_core_page_fault_resume(struct mlx5_core_dev *dev, u32 token,
 EXPORT_SYMBOL_GPL(mlx5_core_page_fault_resume);
 #endif
 
+static void general_event_handler(struct mlx5_core_dev *dev,
+				  struct mlx5_eqe *eqe)
+{
+	switch (eqe->sub_type) {
+	case MLX5_GENERAL_SUBTYPE_DELAY_DROP_TIMEOUT:
+		if (dev->event)
+			dev->event(dev, MLX5_DEV_EVENT_DELAY_DROP_TIMEOUT, 0);
+		break;
+	default:
+		mlx5_core_dbg(dev, "General event with unrecognized subtype: sub_type %d\n",
+			      eqe->sub_type);
+	}
+}
+
 static irqreturn_t mlx5_eq_int(int irq, void *eq_ptr)
 {
 	struct mlx5_eq *eq = eq_ptr;
@@ -486,6 +502,9 @@ static irqreturn_t mlx5_eq_int(int irq, void *eq_ptr)
 			mlx5_fpga_event(dev, eqe->type, &eqe->data.raw);
 			break;
 
+		case MLX5_EVENT_TYPE_GENERAL_EVENT:
+			general_event_handler(dev, eqe);
+			break;
 		default:
 			mlx5_core_warn(dev, "Unhandled event 0x%x on EQ 0x%x\n",
 				       eqe->type, eq->eqn);
@@ -585,7 +604,7 @@ int mlx5_create_map_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq, u8 vecidx,
 		 name, pci_name(dev->pdev));
 
 	eq->eqn = MLX5_GET(create_eq_out, out, eq_number);
-	eq->irqn = priv->msix_arr[vecidx].vector;
+	eq->irqn = pci_irq_vector(dev->pdev, vecidx);
 	eq->dev = dev;
 	eq->doorbell = priv->uar->map + MLX5_EQ_DOORBEL_OFFSET;
 	err = request_irq(eq->irqn, handler, 0,
@@ -620,7 +639,7 @@ int mlx5_create_map_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq, u8 vecidx,
 	return 0;
 
 err_irq:
-	free_irq(priv->msix_arr[vecidx].vector, eq);
+	free_irq(eq->irqn, eq);
 
 err_eq:
 	mlx5_cmd_destroy_eq(dev, eq->eqn);
@@ -661,11 +680,6 @@ int mlx5_destroy_unmap_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq)
 }
 EXPORT_SYMBOL_GPL(mlx5_destroy_unmap_eq);
 
-u32 mlx5_get_msix_vec(struct mlx5_core_dev *dev, int vecidx)
-{
-	return dev->priv.msix_arr[MLX5_EQ_VEC_ASYNC].vector;
-}
-
 int mlx5_eq_init(struct mlx5_core_dev *dev)
 {
 	int err;
@@ -693,6 +707,10 @@ int mlx5_start_eqs(struct mlx5_core_dev *dev)
 	    mlx5_core_is_pf(dev))
 		async_event_mask |= (1ull << MLX5_EVENT_TYPE_NIC_VPORT_CHANGE);
 
+	if (MLX5_CAP_GEN(dev, port_type) == MLX5_CAP_PORT_TYPE_ETH &&
+	    MLX5_CAP_GEN(dev, general_notification_event))
+		async_event_mask |= (1ull << MLX5_EVENT_TYPE_GENERAL_EVENT);
+
 	if (MLX5_CAP_GEN(dev, port_module_event))
 		async_event_mask |= (1ull << MLX5_EVENT_TYPE_PORT_MODULE_EVENT);
 	else
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index 8b18cc9ec026..5b41f692acad 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -1585,7 +1585,7 @@ static void esw_disable_vport(struct mlx5_eswitch *esw, int vport_num)
 	/* Mark this vport as disabled to discard new events */
 	vport->enabled = false;
 
-	synchronize_irq(mlx5_get_msix_vec(esw->dev, MLX5_EQ_VEC_ASYNC));
+	synchronize_irq(pci_irq_vector(esw->dev->pdev, MLX5_EQ_VEC_ASYNC));
 	/* Wait for current already scheduled events to complete */
 	flush_workqueue(esw->work_queue);
 	/* Disable events from this vport */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw.c b/drivers/net/ethernet/mellanox/mlx5/core/fw.c
index fa33d59ab485..2c71557d1cee 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fw.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fw.c
@@ -120,6 +120,12 @@ int mlx5_query_hca_caps(struct mlx5_core_dev *dev)
 			return err;
 	}
 
+	if (MLX5_CAP_GEN(dev, ipoib_enhanced_offloads)) {
+		err = mlx5_core_get_caps(dev, MLX5_CAP_IPOIB_ENHANCED_OFFLOADS);
+		if (err)
+			return err;
+	}
+
 	if (MLX5_CAP_GEN(dev, pg)) {
 		err = mlx5_core_get_caps(dev, MLX5_CAP_ODP);
 		if (err)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c
index 4b6b03d6297f..8aea0a065e56 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/health.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c
@@ -81,7 +81,7 @@ static void trigger_cmd_completions(struct mlx5_core_dev *dev)
 	u64 vector;
 
 	/* wait for pending handlers to complete */
-	synchronize_irq(dev->priv.msix_arr[MLX5_EQ_VEC_CMD].vector);
+	synchronize_irq(pci_irq_vector(dev->pdev, MLX5_EQ_VEC_CMD));
 	spin_lock_irqsave(&dev->cmd.alloc_lock, flags);
 	vector = ~dev->cmd.bitmask & ((1ul << (1 << dev->cmd.log_sz)) - 1);
 	if (!vector)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 16885827367b..8c4b45ef539c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -47,6 +47,7 @@
 #include <linux/debugfs.h>
 #include <linux/kmod.h>
 #include <linux/mlx5/mlx5_ifc.h>
+#include <linux/mlx5/vport.h>
 #ifdef CONFIG_RFS_ACCEL
 #include <linux/cpu_rmap.h>
 #endif
@@ -312,13 +313,15 @@ static void release_bar(struct pci_dev *pdev)
 	pci_release_regions(pdev);
 }
 
-static int mlx5_enable_msix(struct mlx5_core_dev *dev)
+static int mlx5_alloc_irq_vectors(struct mlx5_core_dev *dev)
 {
 	struct mlx5_priv *priv = &dev->priv;
 	struct mlx5_eq_table *table = &priv->eq_table;
+	struct irq_affinity irqdesc = {
+		.pre_vectors = MLX5_EQ_VEC_COMP_BASE,
+	};
 	int num_eqs = 1 << MLX5_CAP_GEN(dev, log_max_eq);
 	int nvec;
-	int i;
 
 	nvec = MLX5_CAP_GEN(dev, num_ports) * num_online_cpus() +
 	       MLX5_EQ_VEC_COMP_BASE;
@@ -326,17 +329,14 @@ static int mlx5_enable_msix(struct mlx5_core_dev *dev)
 	if (nvec <= MLX5_EQ_VEC_COMP_BASE)
 		return -ENOMEM;
 
-	priv->msix_arr = kcalloc(nvec, sizeof(*priv->msix_arr), GFP_KERNEL);
-
 	priv->irq_info = kcalloc(nvec, sizeof(*priv->irq_info), GFP_KERNEL);
-	if (!priv->msix_arr || !priv->irq_info)
+	if (!priv->irq_info)
 		goto err_free_msix;
 
-	for (i = 0; i < nvec; i++)
-		priv->msix_arr[i].entry = i;
-
-	nvec = pci_enable_msix_range(dev->pdev, priv->msix_arr,
-				     MLX5_EQ_VEC_COMP_BASE + 1, nvec);
+	nvec = pci_alloc_irq_vectors_affinity(dev->pdev,
+			MLX5_EQ_VEC_COMP_BASE + 1, nvec,
+			PCI_IRQ_MSIX | PCI_IRQ_AFFINITY,
+			&irqdesc);
 	if (nvec < 0)
 		return nvec;
 
@@ -346,17 +346,15 @@ static int mlx5_enable_msix(struct mlx5_core_dev *dev)
 
 err_free_msix:
 	kfree(priv->irq_info);
-	kfree(priv->msix_arr);
 	return -ENOMEM;
 }
 
-static void mlx5_disable_msix(struct mlx5_core_dev *dev)
+static void mlx5_free_irq_vectors(struct mlx5_core_dev *dev)
 {
 	struct mlx5_priv *priv = &dev->priv;
 
-	pci_disable_msix(dev->pdev);
+	pci_free_irq_vectors(dev->pdev);
 	kfree(priv->irq_info);
-	kfree(priv->msix_arr);
 }
 
 struct mlx5_reg_host_endianness {
@@ -579,6 +577,18 @@ static int set_hca_ctrl(struct mlx5_core_dev *dev)
 	return err;
 }
 
+static int mlx5_core_set_hca_defaults(struct mlx5_core_dev *dev)
+{
+	int ret = 0;
+
+	/* Disable local_lb by default */
+	if ((MLX5_CAP_GEN(dev, port_type) == MLX5_CAP_PORT_TYPE_ETH) &&
+	    MLX5_CAP_GEN(dev, disable_local_lb))
+		ret = mlx5_nic_vport_update_local_lb(dev, false);
+
+	return ret;
+}
+
 int mlx5_core_enable_hca(struct mlx5_core_dev *dev, u16 func_id)
 {
 	u32 out[MLX5_ST_SZ_DW(enable_hca_out)] = {0};
@@ -612,65 +622,6 @@ u64 mlx5_read_internal_timer(struct mlx5_core_dev *dev)
 	return (u64)timer_l | (u64)timer_h1 << 32;
 }
 
-static int mlx5_irq_set_affinity_hint(struct mlx5_core_dev *mdev, int i)
-{
-	struct mlx5_priv *priv  = &mdev->priv;
-	struct msix_entry *msix = priv->msix_arr;
-	int irq                 = msix[i + MLX5_EQ_VEC_COMP_BASE].vector;
-
-	if (!zalloc_cpumask_var(&priv->irq_info[i].mask, GFP_KERNEL)) {
-		mlx5_core_warn(mdev, "zalloc_cpumask_var failed");
-		return -ENOMEM;
-	}
-
-	cpumask_set_cpu(cpumask_local_spread(i, priv->numa_node),
-			priv->irq_info[i].mask);
-
-	if (IS_ENABLED(CONFIG_SMP) &&
-	    irq_set_affinity_hint(irq, priv->irq_info[i].mask))
-		mlx5_core_warn(mdev, "irq_set_affinity_hint failed, irq 0x%.4x", irq);
-
-	return 0;
-}
-
-static void mlx5_irq_clear_affinity_hint(struct mlx5_core_dev *mdev, int i)
-{
-	struct mlx5_priv *priv  = &mdev->priv;
-	struct msix_entry *msix = priv->msix_arr;
-	int irq                 = msix[i + MLX5_EQ_VEC_COMP_BASE].vector;
-
-	irq_set_affinity_hint(irq, NULL);
-	free_cpumask_var(priv->irq_info[i].mask);
-}
-
-static int mlx5_irq_set_affinity_hints(struct mlx5_core_dev *mdev)
-{
-	int err;
-	int i;
-
-	for (i = 0; i < mdev->priv.eq_table.num_comp_vectors; i++) {
-		err = mlx5_irq_set_affinity_hint(mdev, i);
-		if (err)
-			goto err_out;
-	}
-
-	return 0;
-
-err_out:
-	for (i--; i >= 0; i--)
-		mlx5_irq_clear_affinity_hint(mdev, i);
-
-	return err;
-}
-
-static void mlx5_irq_clear_affinity_hints(struct mlx5_core_dev *mdev)
-{
-	int i;
-
-	for (i = 0; i < mdev->priv.eq_table.num_comp_vectors; i++)
-		mlx5_irq_clear_affinity_hint(mdev, i);
-}
-
 int mlx5_vector2eqn(struct mlx5_core_dev *dev, int vector, int *eqn,
 		    unsigned int *irqn)
 {
@@ -760,8 +711,8 @@ static int alloc_comp_eqs(struct mlx5_core_dev *dev)
 		}
 
 #ifdef CONFIG_RFS_ACCEL
-		irq_cpu_rmap_add(dev->rmap,
-				 dev->priv.msix_arr[i + MLX5_EQ_VEC_COMP_BASE].vector);
+		irq_cpu_rmap_add(dev->rmap, pci_irq_vector(dev->pdev,
+				 MLX5_EQ_VEC_COMP_BASE + i));
 #endif
 		snprintf(name, MLX5_MAX_IRQ_NAME, "mlx5_comp%d", i);
 		err = mlx5_create_map_eq(dev, eq,
@@ -1119,9 +1070,9 @@ static int mlx5_load_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv,
 		goto err_stop_poll;
 	}
 
-	err = mlx5_enable_msix(dev);
+	err = mlx5_alloc_irq_vectors(dev);
 	if (err) {
-		dev_err(&pdev->dev, "enable msix failed\n");
+		dev_err(&pdev->dev, "alloc irq vectors failed\n");
 		goto err_cleanup_once;
 	}
 
@@ -1143,15 +1094,15 @@ static int mlx5_load_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv,
 		goto err_stop_eqs;
 	}
 
-	err = mlx5_irq_set_affinity_hints(dev);
+	err = mlx5_init_fs(dev);
 	if (err) {
-		dev_err(&pdev->dev, "Failed to alloc affinity hint cpumask\n");
-		goto err_affinity_hints;
+		dev_err(&pdev->dev, "Failed to init flow steering\n");
+		goto err_fs;
 	}
 
-	err = mlx5_init_fs(dev);
+	err = mlx5_core_set_hca_defaults(dev);
 	if (err) {
-		dev_err(&pdev->dev, "Failed to init flow steering\n");
+		dev_err(&pdev->dev, "Failed to set hca defaults\n");
 		goto err_fs;
 	}
 
@@ -1207,9 +1158,6 @@ err_sriov:
 	mlx5_cleanup_fs(dev);
 
 err_fs:
-	mlx5_irq_clear_affinity_hints(dev);
-
-err_affinity_hints:
 	free_comp_eqs(dev);
 
 err_stop_eqs:
@@ -1219,7 +1167,7 @@ err_put_uars:
 	mlx5_put_uars_page(dev, priv->uar);
 
 err_disable_msix:
-	mlx5_disable_msix(dev);
+	mlx5_free_irq_vectors(dev);
 
 err_cleanup_once:
 	if (boot)
@@ -1281,11 +1229,10 @@ static int mlx5_unload_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv,
 	mlx5_eswitch_detach(dev->priv.eswitch);
 #endif
 	mlx5_cleanup_fs(dev);
-	mlx5_irq_clear_affinity_hints(dev);
 	free_comp_eqs(dev);
 	mlx5_stop_eqs(dev);
 	mlx5_put_uars_page(dev, priv->uar);
-	mlx5_disable_msix(dev);
+	mlx5_free_irq_vectors(dev);
 	if (cleanup)
 		mlx5_cleanup_once(dev);
 	mlx5_stop_health_poll(dev);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
index 6a263e8d883a..01d637dac533 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
@@ -110,7 +110,6 @@ int mlx5_destroy_scheduling_element_cmd(struct mlx5_core_dev *dev, u8 hierarchy,
 					u32 element_id);
 int mlx5_wait_for_vf_pages(struct mlx5_core_dev *dev);
 u64 mlx5_read_internal_timer(struct mlx5_core_dev *dev);
-u32 mlx5_get_msix_vec(struct mlx5_core_dev *dev, int vecidx);
 struct mlx5_eq *mlx5_eqn2eq(struct mlx5_core_dev *dev, int eqn);
 void mlx5_cq_tasklet_cb(unsigned long data);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/qp.c b/drivers/net/ethernet/mellanox/mlx5/core/qp.c
index 340f281c9801..db9e665ab104 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/qp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/qp.c
@@ -242,6 +242,20 @@ int mlx5_core_destroy_qp(struct mlx5_core_dev *dev,
 }
 EXPORT_SYMBOL_GPL(mlx5_core_destroy_qp);
 
+int mlx5_core_set_delay_drop(struct mlx5_core_dev *dev,
+			     u32 timeout_usec)
+{
+	u32 out[MLX5_ST_SZ_DW(set_delay_drop_params_out)] = {0};
+	u32 in[MLX5_ST_SZ_DW(set_delay_drop_params_in)]   = {0};
+
+	MLX5_SET(set_delay_drop_params_in, in, opcode,
+		 MLX5_CMD_OP_SET_DELAY_DROP_PARAMS);
+	MLX5_SET(set_delay_drop_params_in, in, delay_drop_timeout,
+		 timeout_usec / 100);
+	return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
+}
+EXPORT_SYMBOL_GPL(mlx5_core_set_delay_drop);
+
 struct mbox_info {
 	u32 *in;
 	u32 *out;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sriov.c b/drivers/net/ethernet/mellanox/mlx5/core/sriov.c
index bf99d40e30b4..28d8472b36f1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/sriov.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sriov.c
@@ -32,6 +32,7 @@
 
 #include <linux/pci.h>
 #include <linux/mlx5/driver.h>
+#include <linux/mlx5/vport.h>
 #include "mlx5_core.h"
 #ifdef CONFIG_MLX5_CORE_EN
 #include "eswitch.h"
@@ -44,6 +45,38 @@ bool mlx5_sriov_is_enabled(struct mlx5_core_dev *dev)
 	return !!sriov->num_vfs;
 }
 
+static int sriov_restore_guids(struct mlx5_core_dev *dev, int vf)
+{
+	struct mlx5_core_sriov *sriov = &dev->priv.sriov;
+	struct mlx5_hca_vport_context *in;
+	int err = 0;
+
+	/* Restore sriov guid and policy settings */
+	if (sriov->vfs_ctx[vf].node_guid ||
+	    sriov->vfs_ctx[vf].port_guid ||
+	    sriov->vfs_ctx[vf].policy != MLX5_POLICY_INVALID) {
+		in = kzalloc(sizeof(*in), GFP_KERNEL);
+		if (!in)
+			return -ENOMEM;
+
+		in->node_guid = sriov->vfs_ctx[vf].node_guid;
+		in->port_guid = sriov->vfs_ctx[vf].port_guid;
+		in->policy = sriov->vfs_ctx[vf].policy;
+		in->field_select =
+			!!(in->port_guid) * MLX5_HCA_VPORT_SEL_PORT_GUID |
+			!!(in->node_guid) * MLX5_HCA_VPORT_SEL_NODE_GUID |
+			!!(in->policy) * MLX5_HCA_VPORT_SEL_STATE_POLICY;
+
+		err = mlx5_core_modify_hca_vport_context(dev, 1, 1, vf + 1, in);
+		if (err)
+			mlx5_core_warn(dev, "modify vport context failed, unable to restore VF %d settings\n", vf);
+
+		kfree(in);
+	}
+
+	return err;
+}
+
 static int mlx5_device_enable_sriov(struct mlx5_core_dev *dev, int num_vfs)
 {
 	struct mlx5_core_sriov *sriov = &dev->priv.sriov;
@@ -74,6 +107,15 @@ static int mlx5_device_enable_sriov(struct mlx5_core_dev *dev, int num_vfs)
 		}
 		sriov->vfs_ctx[vf].enabled = 1;
 		sriov->enabled_vfs++;
+		if (MLX5_CAP_GEN(dev, port_type) == MLX5_CAP_PORT_TYPE_IB) {
+			err = sriov_restore_guids(dev, vf);
+			if (err) {
+				mlx5_core_warn(dev,
+					       "failed to restore VF %d settings, err %d\n",
+					       vf, err);
+			continue;
+			}
+		}
 		mlx5_core_dbg(dev, "successfully enabled VF* %d\n", vf);
 
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/srq.c b/drivers/net/ethernet/mellanox/mlx5/core/srq.c
index 520f6382dfde..23cc337a96c9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/srq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/srq.c
@@ -435,16 +435,128 @@ out:
 	return err;
 }
 
+static int create_xrq_cmd(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq,
+			  struct mlx5_srq_attr *in)
+{
+	u32 create_out[MLX5_ST_SZ_DW(create_xrq_out)] = {0};
+	void *create_in;
+	void *xrqc;
+	void *wq;
+	int pas_size;
+	int inlen;
+	int err;
+
+	pas_size = get_pas_size(in);
+	inlen = MLX5_ST_SZ_BYTES(create_xrq_in) + pas_size;
+	create_in = kvzalloc(inlen, GFP_KERNEL);
+	if (!create_in)
+		return -ENOMEM;
+
+	xrqc = MLX5_ADDR_OF(create_xrq_in, create_in, xrq_context);
+	wq = MLX5_ADDR_OF(xrqc, xrqc, wq);
+
+	set_wq(wq, in);
+	memcpy(MLX5_ADDR_OF(xrqc, xrqc, wq.pas), in->pas, pas_size);
+
+	if (in->type == IB_SRQT_TM) {
+		MLX5_SET(xrqc, xrqc, topology, MLX5_XRQC_TOPOLOGY_TAG_MATCHING);
+		if (in->flags & MLX5_SRQ_FLAG_RNDV)
+			MLX5_SET(xrqc, xrqc, offload, MLX5_XRQC_OFFLOAD_RNDV);
+		MLX5_SET(xrqc, xrqc,
+			 tag_matching_topology_context.log_matching_list_sz,
+			 in->tm_log_list_size);
+	}
+	MLX5_SET(xrqc, xrqc, user_index, in->user_index);
+	MLX5_SET(xrqc, xrqc, cqn, in->cqn);
+	MLX5_SET(create_xrq_in, create_in, opcode, MLX5_CMD_OP_CREATE_XRQ);
+	err = mlx5_cmd_exec(dev, create_in, inlen, create_out,
+			    sizeof(create_out));
+	kvfree(create_in);
+	if (!err)
+		srq->srqn = MLX5_GET(create_xrq_out, create_out, xrqn);
+
+	return err;
+}
+
+static int destroy_xrq_cmd(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq)
+{
+	u32 in[MLX5_ST_SZ_DW(destroy_xrq_in)] = {0};
+	u32 out[MLX5_ST_SZ_DW(destroy_xrq_out)] = {0};
+
+	MLX5_SET(destroy_xrq_in, in, opcode, MLX5_CMD_OP_DESTROY_XRQ);
+	MLX5_SET(destroy_xrq_in, in, xrqn,   srq->srqn);
+
+	return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
+}
+
+static int arm_xrq_cmd(struct mlx5_core_dev *dev,
+		       struct mlx5_core_srq *srq,
+		       u16 lwm)
+{
+	u32 out[MLX5_ST_SZ_DW(arm_rq_out)] = {0};
+	u32 in[MLX5_ST_SZ_DW(arm_rq_in)] = {0};
+
+	MLX5_SET(arm_rq_in, in, opcode,     MLX5_CMD_OP_ARM_RQ);
+	MLX5_SET(arm_rq_in, in, op_mod,     MLX5_ARM_RQ_IN_OP_MOD_XRQ);
+	MLX5_SET(arm_rq_in, in, srq_number, srq->srqn);
+	MLX5_SET(arm_rq_in, in, lwm,	    lwm);
+
+	return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
+}
+
+static int query_xrq_cmd(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq,
+			 struct mlx5_srq_attr *out)
+{
+	u32 in[MLX5_ST_SZ_DW(query_xrq_in)] = {0};
+	u32 *xrq_out;
+	int outlen = MLX5_ST_SZ_BYTES(query_xrq_out);
+	void *xrqc;
+	int err;
+
+	xrq_out = kvzalloc(outlen, GFP_KERNEL);
+	if (!xrq_out)
+		return -ENOMEM;
+
+	MLX5_SET(query_xrq_in, in, opcode, MLX5_CMD_OP_QUERY_XRQ);
+	MLX5_SET(query_xrq_in, in, xrqn, srq->srqn);
+
+	err = mlx5_cmd_exec(dev, in, sizeof(in), xrq_out, outlen);
+	if (err)
+		goto out;
+
+	xrqc = MLX5_ADDR_OF(query_xrq_out, xrq_out, xrq_context);
+	get_wq(MLX5_ADDR_OF(xrqc, xrqc, wq), out);
+	if (MLX5_GET(xrqc, xrqc, state) != MLX5_XRQC_STATE_GOOD)
+		out->flags |= MLX5_SRQ_FLAG_ERR;
+	out->tm_next_tag =
+		MLX5_GET(xrqc, xrqc,
+			 tag_matching_topology_context.append_next_index);
+	out->tm_hw_phase_cnt =
+		MLX5_GET(xrqc, xrqc,
+			 tag_matching_topology_context.hw_phase_cnt);
+	out->tm_sw_phase_cnt =
+		MLX5_GET(xrqc, xrqc,
+			 tag_matching_topology_context.sw_phase_cnt);
+
+out:
+	kvfree(xrq_out);
+	return err;
+}
+
 static int create_srq_split(struct mlx5_core_dev *dev,
 			    struct mlx5_core_srq *srq,
 			    struct mlx5_srq_attr *in)
 {
 	if (!dev->issi)
 		return create_srq_cmd(dev, srq, in);
-	else if (srq->common.res == MLX5_RES_XSRQ)
+	switch (srq->common.res) {
+	case MLX5_RES_XSRQ:
 		return create_xrc_srq_cmd(dev, srq, in);
-	else
+	case MLX5_RES_XRQ:
+		return create_xrq_cmd(dev, srq, in);
+	default:
 		return create_rmp_cmd(dev, srq, in);
+	}
 }
 
 static int destroy_srq_split(struct mlx5_core_dev *dev,
@@ -452,10 +564,14 @@ static int destroy_srq_split(struct mlx5_core_dev *dev,
 {
 	if (!dev->issi)
 		return destroy_srq_cmd(dev, srq);
-	else if (srq->common.res == MLX5_RES_XSRQ)
+	switch (srq->common.res) {
+	case MLX5_RES_XSRQ:
 		return destroy_xrc_srq_cmd(dev, srq);
-	else
+	case MLX5_RES_XRQ:
+		return destroy_xrq_cmd(dev, srq);
+	default:
 		return destroy_rmp_cmd(dev, srq);
+	}
 }
 
 int mlx5_core_create_srq(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq,
@@ -464,10 +580,16 @@ int mlx5_core_create_srq(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq,
 	int err;
 	struct mlx5_srq_table *table = &dev->priv.srq_table;
 
-	if (in->type == IB_SRQT_XRC)
+	switch (in->type) {
+	case IB_SRQT_XRC:
 		srq->common.res = MLX5_RES_XSRQ;
-	else
+		break;
+	case IB_SRQT_TM:
+		srq->common.res = MLX5_RES_XRQ;
+		break;
+	default:
 		srq->common.res = MLX5_RES_SRQ;
+	}
 
 	err = create_srq_split(dev, srq, in);
 	if (err)
@@ -528,10 +650,14 @@ int mlx5_core_query_srq(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq,
 {
 	if (!dev->issi)
 		return query_srq_cmd(dev, srq, out);
-	else if (srq->common.res == MLX5_RES_XSRQ)
+	switch (srq->common.res) {
+	case MLX5_RES_XSRQ:
 		return query_xrc_srq_cmd(dev, srq, out);
-	else
+	case MLX5_RES_XRQ:
+		return query_xrq_cmd(dev, srq, out);
+	default:
 		return query_rmp_cmd(dev, srq, out);
+	}
 }
 EXPORT_SYMBOL(mlx5_core_query_srq);
 
@@ -540,10 +666,14 @@ int mlx5_core_arm_srq(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq,
 {
 	if (!dev->issi)
 		return arm_srq_cmd(dev, srq, lwm, is_srq);
-	else if (srq->common.res == MLX5_RES_XSRQ)
+	switch (srq->common.res) {
+	case MLX5_RES_XSRQ:
 		return arm_xrc_srq_cmd(dev, srq, lwm);
-	else
+	case MLX5_RES_XRQ:
+		return arm_xrq_cmd(dev, srq, lwm);
+	default:
 		return arm_rmp_cmd(dev, srq, lwm);
+	}
 }
 EXPORT_SYMBOL(mlx5_core_arm_srq);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vport.c b/drivers/net/ethernet/mellanox/mlx5/core/vport.c
index 5abfec1c3399..d653b0025b13 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/vport.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/vport.c
@@ -897,6 +897,68 @@ int mlx5_modify_nic_vport_promisc(struct mlx5_core_dev *mdev,
 }
 EXPORT_SYMBOL_GPL(mlx5_modify_nic_vport_promisc);
 
+enum {
+	UC_LOCAL_LB,
+	MC_LOCAL_LB
+};
+
+int mlx5_nic_vport_update_local_lb(struct mlx5_core_dev *mdev, bool enable)
+{
+	int inlen = MLX5_ST_SZ_BYTES(modify_nic_vport_context_in);
+	void *in;
+	int err;
+
+	mlx5_core_dbg(mdev, "%s local_lb\n", enable ? "enable" : "disable");
+	in = kvzalloc(inlen, GFP_KERNEL);
+	if (!in)
+		return -ENOMEM;
+
+	MLX5_SET(modify_nic_vport_context_in, in,
+		 field_select.disable_mc_local_lb, 1);
+	MLX5_SET(modify_nic_vport_context_in, in,
+		 nic_vport_context.disable_mc_local_lb, !enable);
+
+	MLX5_SET(modify_nic_vport_context_in, in,
+		 field_select.disable_uc_local_lb, 1);
+	MLX5_SET(modify_nic_vport_context_in, in,
+		 nic_vport_context.disable_uc_local_lb, !enable);
+
+	err = mlx5_modify_nic_vport_context(mdev, in, inlen);
+
+	kvfree(in);
+	return err;
+}
+EXPORT_SYMBOL_GPL(mlx5_nic_vport_update_local_lb);
+
+int mlx5_nic_vport_query_local_lb(struct mlx5_core_dev *mdev, bool *status)
+{
+	int outlen = MLX5_ST_SZ_BYTES(query_nic_vport_context_out);
+	u32 *out;
+	int value;
+	int err;
+
+	out = kzalloc(outlen, GFP_KERNEL);
+	if (!out)
+		return -ENOMEM;
+
+	err = mlx5_query_nic_vport_context(mdev, 0, out, outlen);
+	if (err)
+		goto out;
+
+	value = MLX5_GET(query_nic_vport_context_out, out,
+			 nic_vport_context.disable_mc_local_lb) << MC_LOCAL_LB;
+
+	value |= MLX5_GET(query_nic_vport_context_out, out,
+			  nic_vport_context.disable_uc_local_lb) << UC_LOCAL_LB;
+
+	*status = !value;
+
+out:
+	kfree(out);
+	return err;
+}
+EXPORT_SYMBOL_GPL(mlx5_nic_vport_query_local_lb);
+
 enum mlx5_vport_roce_state {
 	MLX5_VPORT_ROCE_DISABLED = 0,
 	MLX5_VPORT_ROCE_ENABLED  = 1,