Merge tag 'mlx5-net-next-5.15-rc7' of git://git.kernel.org/pub/scm/linux/kernel/git/saeed/linux

Saeed Mahameed says:

====================
Merge mlx5-next into net-next
====================

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

34 files changed, 292 insertions, 248 deletions

diff --git a/drivers/infiniband/hw/mlx5/cmd.c b/drivers/infiniband/hw/mlx5/cmd.c
index a8db8a051170..ff3742b0460a 100644
--- a/drivers/infiniband/hw/mlx5/cmd.c
+++ b/drivers/infiniband/hw/mlx5/cmd.c
@@ -206,3 +206,29 @@ out:
 	kfree(in);
 	return err;
 }
+
+int mlx5_cmd_uar_alloc(struct mlx5_core_dev *dev, u32 *uarn, u16 uid)
+{
+	u32 out[MLX5_ST_SZ_DW(alloc_uar_out)] = {};
+	u32 in[MLX5_ST_SZ_DW(alloc_uar_in)] = {};
+	int err;
+
+	MLX5_SET(alloc_uar_in, in, opcode, MLX5_CMD_OP_ALLOC_UAR);
+	MLX5_SET(alloc_uar_in, in, uid, uid);
+	err = mlx5_cmd_exec_inout(dev, alloc_uar, in, out);
+	if (err)
+		return err;
+
+	*uarn = MLX5_GET(alloc_uar_out, out, uar);
+	return 0;
+}
+
+int mlx5_cmd_uar_dealloc(struct mlx5_core_dev *dev, u32 uarn, u16 uid)
+{
+	u32 in[MLX5_ST_SZ_DW(dealloc_uar_in)] = {};
+
+	MLX5_SET(dealloc_uar_in, in, opcode, MLX5_CMD_OP_DEALLOC_UAR);
+	MLX5_SET(dealloc_uar_in, in, uar, uarn);
+	MLX5_SET(dealloc_uar_in, in, uid, uid);
+	return mlx5_cmd_exec_in(dev, dealloc_uar, in);
+}
diff --git a/drivers/infiniband/hw/mlx5/cmd.h b/drivers/infiniband/hw/mlx5/cmd.h
index 66c96292ed43..ee46638db5de 100644
--- a/drivers/infiniband/hw/mlx5/cmd.h
+++ b/drivers/infiniband/hw/mlx5/cmd.h
@@ -57,4 +57,6 @@ int mlx5_cmd_xrcd_alloc(struct mlx5_core_dev *dev, u32 *xrcdn, u16 uid);
 int mlx5_cmd_xrcd_dealloc(struct mlx5_core_dev *dev, u32 xrcdn, u16 uid);
 int mlx5_cmd_mad_ifc(struct mlx5_core_dev *dev, const void *inb, void *outb,
 		     u16 opmod, u8 port);
+int mlx5_cmd_uar_alloc(struct mlx5_core_dev *dev, u32 *uarn, u16 uid);
+int mlx5_cmd_uar_dealloc(struct mlx5_core_dev *dev, u32 uarn, u16 uid);
 #endif /* MLX5_IB_CMD_H */
diff --git a/drivers/infiniband/hw/mlx5/devx.c b/drivers/infiniband/hw/mlx5/devx.c
index e95967aefe78..08b7f6bc56c3 100644
--- a/drivers/infiniband/hw/mlx5/devx.c
+++ b/drivers/infiniband/hw/mlx5/devx.c
@@ -1292,21 +1292,16 @@ static int devx_handle_mkey_indirect(struct devx_obj *obj,
 				     struct mlx5_ib_dev *dev,
 				     void *in, void *out)
 {
-	struct mlx5_ib_devx_mr *devx_mr = &obj->devx_mr;
-	struct mlx5_core_mkey *mkey;
+	struct mlx5_ib_mkey *mkey = &obj->mkey;
 	void *mkc;
 	u8 key;
 
-	mkey = &devx_mr->mmkey;
 	mkc = MLX5_ADDR_OF(create_mkey_in, in, memory_key_mkey_entry);
 	key = MLX5_GET(mkc, mkc, mkey_7_0);
 	mkey->key = mlx5_idx_to_mkey(
 			MLX5_GET(create_mkey_out, out, mkey_index)) | key;
 	mkey->type = MLX5_MKEY_INDIRECT_DEVX;
-	mkey->iova = MLX5_GET64(mkc, mkc, start_addr);
-	mkey->size = MLX5_GET64(mkc, mkc, len);
-	mkey->pd = MLX5_GET(mkc, mkc, pd);
-	devx_mr->ndescs = MLX5_GET(mkc, mkc, translations_octword_size);
+	mkey->ndescs = MLX5_GET(mkc, mkc, translations_octword_size);
 	init_waitqueue_head(&mkey->wait);
 
 	return mlx5r_store_odp_mkey(dev, mkey);
@@ -1384,13 +1379,13 @@ static int devx_obj_cleanup(struct ib_uobject *uobject,
 	dev = mlx5_udata_to_mdev(&attrs->driver_udata);
 	if (obj->flags & DEVX_OBJ_FLAGS_INDIRECT_MKEY &&
 	    xa_erase(&obj->ib_dev->odp_mkeys,
-		     mlx5_base_mkey(obj->devx_mr.mmkey.key)))
+		     mlx5_base_mkey(obj->mkey.key)))
 		/*
 		 * The pagefault_single_data_segment() does commands against
 		 * the mmkey, we must wait for that to stop before freeing the
 		 * mkey, as another allocation could get the same mkey #.
 		 */
-		mlx5r_deref_wait_odp_mkey(&obj->devx_mr.mmkey);
+		mlx5r_deref_wait_odp_mkey(&obj->mkey);
 
 	if (obj->flags & DEVX_OBJ_FLAGS_DCT)
 		ret = mlx5_core_destroy_dct(obj->ib_dev, &obj->core_dct);
diff --git a/drivers/infiniband/hw/mlx5/devx.h b/drivers/infiniband/hw/mlx5/devx.h
index 1f69866aed16..ee2213275fd6 100644
--- a/drivers/infiniband/hw/mlx5/devx.h
+++ b/drivers/infiniband/hw/mlx5/devx.h
@@ -16,7 +16,7 @@ struct devx_obj {
 	u32			dinbox[MLX5_MAX_DESTROY_INBOX_SIZE_DW];
 	u32			flags;
 	union {
-		struct mlx5_ib_devx_mr	devx_mr;
+		struct mlx5_ib_mkey	mkey;
 		struct mlx5_core_dct	core_dct;
 		struct mlx5_core_cq	core_cq;
 		u32			flow_counter_bulk_size;
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index 8664bcf6d3f5..5ec8bd2f0b2f 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -1643,7 +1643,8 @@ static int allocate_uars(struct mlx5_ib_dev *dev, struct mlx5_ib_ucontext *conte
 
 	bfregi = &context->bfregi;
 	for (i = 0; i < bfregi->num_static_sys_pages; i++) {
-		err = mlx5_cmd_alloc_uar(dev->mdev, &bfregi->sys_pages[i]);
+		err = mlx5_cmd_uar_alloc(dev->mdev, &bfregi->sys_pages[i],
+					 context->devx_uid);
 		if (err)
 			goto error;
 
@@ -1657,7 +1658,8 @@ static int allocate_uars(struct mlx5_ib_dev *dev, struct mlx5_ib_ucontext *conte
 
 error:
 	for (--i; i >= 0; i--)
-		if (mlx5_cmd_free_uar(dev->mdev, bfregi->sys_pages[i]))
+		if (mlx5_cmd_uar_dealloc(dev->mdev, bfregi->sys_pages[i],
+					 context->devx_uid))
 			mlx5_ib_warn(dev, "failed to free uar %d\n", i);
 
 	return err;
@@ -1673,7 +1675,8 @@ static void deallocate_uars(struct mlx5_ib_dev *dev,
 	for (i = 0; i < bfregi->num_sys_pages; i++)
 		if (i < bfregi->num_static_sys_pages ||
 		    bfregi->sys_pages[i] != MLX5_IB_INVALID_UAR_INDEX)
-			mlx5_cmd_free_uar(dev->mdev, bfregi->sys_pages[i]);
+			mlx5_cmd_uar_dealloc(dev->mdev, bfregi->sys_pages[i],
+					     context->devx_uid);
 }
 
 int mlx5_ib_enable_lb(struct mlx5_ib_dev *dev, bool td, bool qp)
@@ -1891,6 +1894,13 @@ static int mlx5_ib_alloc_ucontext(struct ib_ucontext *uctx,
 	if (req.num_low_latency_bfregs > req.total_num_bfregs - 1)
 		return -EINVAL;
 
+	if (req.flags & MLX5_IB_ALLOC_UCTX_DEVX) {
+		err = mlx5_ib_devx_create(dev, true);
+		if (err < 0)
+			goto out_ctx;
+		context->devx_uid = err;
+	}
+
 	lib_uar_4k = req.lib_caps & MLX5_LIB_CAP_4K_UAR;
 	lib_uar_dyn = req.lib_caps & MLX5_LIB_CAP_DYN_UAR;
 	bfregi = &context->bfregi;
@@ -1903,7 +1913,7 @@ static int mlx5_ib_alloc_ucontext(struct ib_ucontext *uctx,
 	/* updates req->total_num_bfregs */
 	err = calc_total_bfregs(dev, lib_uar_4k, &req, bfregi);
 	if (err)
-		goto out_ctx;
+		goto out_devx;
 
 	mutex_init(&bfregi->lock);
 	bfregi->lib_uar_4k = lib_uar_4k;
@@ -1911,7 +1921,7 @@ static int mlx5_ib_alloc_ucontext(struct ib_ucontext *uctx,
 				GFP_KERNEL);
 	if (!bfregi->count) {
 		err = -ENOMEM;
-		goto out_ctx;
+		goto out_devx;
 	}
 
 	bfregi->sys_pages = kcalloc(bfregi->num_sys_pages,
@@ -1927,17 +1937,10 @@ static int mlx5_ib_alloc_ucontext(struct ib_ucontext *uctx,
 		goto out_sys_pages;
 
 uar_done:
-	if (req.flags & MLX5_IB_ALLOC_UCTX_DEVX) {
-		err = mlx5_ib_devx_create(dev, true);
-		if (err < 0)
-			goto out_uars;
-		context->devx_uid = err;
-	}
-
 	err = mlx5_ib_alloc_transport_domain(dev, &context->tdn,
 					     context->devx_uid);
 	if (err)
-		goto out_devx;
+		goto out_uars;
 
 	INIT_LIST_HEAD(&context->db_page_list);
 	mutex_init(&context->db_page_mutex);
@@ -1972,9 +1975,6 @@ uar_done:
 
 out_mdev:
 	mlx5_ib_dealloc_transport_domain(dev, context->tdn, context->devx_uid);
-out_devx:
-	if (req.flags & MLX5_IB_ALLOC_UCTX_DEVX)
-		mlx5_ib_devx_destroy(dev, context->devx_uid);
 
 out_uars:
 	deallocate_uars(dev, context);
@@ -1985,6 +1985,10 @@ out_sys_pages:
 out_count:
 	kfree(bfregi->count);
 
+out_devx:
+	if (req.flags & MLX5_IB_ALLOC_UCTX_DEVX)
+		mlx5_ib_devx_destroy(dev, context->devx_uid);
+
 out_ctx:
 	return err;
 }
@@ -2021,12 +2025,12 @@ static void mlx5_ib_dealloc_ucontext(struct ib_ucontext *ibcontext)
 	bfregi = &context->bfregi;
 	mlx5_ib_dealloc_transport_domain(dev, context->tdn, context->devx_uid);
 
-	if (context->devx_uid)
-		mlx5_ib_devx_destroy(dev, context->devx_uid);
-
 	deallocate_uars(dev, context);
 	kfree(bfregi->sys_pages);
 	kfree(bfregi->count);
+
+	if (context->devx_uid)
+		mlx5_ib_devx_destroy(dev, context->devx_uid);
 }
 
 static phys_addr_t uar_index2pfn(struct mlx5_ib_dev *dev,
@@ -2119,6 +2123,7 @@ static void mlx5_ib_mmap_free(struct rdma_user_mmap_entry *entry)
 	struct mlx5_user_mmap_entry *mentry = to_mmmap(entry);
 	struct mlx5_ib_dev *dev = to_mdev(entry->ucontext->device);
 	struct mlx5_var_table *var_table = &dev->var_table;
+	struct mlx5_ib_ucontext *context = to_mucontext(entry->ucontext);
 
 	switch (mentry->mmap_flag) {
 	case MLX5_IB_MMAP_TYPE_MEMIC:
@@ -2133,7 +2138,8 @@ static void mlx5_ib_mmap_free(struct rdma_user_mmap_entry *entry)
 		break;
 	case MLX5_IB_MMAP_TYPE_UAR_WC:
 	case MLX5_IB_MMAP_TYPE_UAR_NC:
-		mlx5_cmd_free_uar(dev->mdev, mentry->page_idx);
+		mlx5_cmd_uar_dealloc(dev->mdev, mentry->page_idx,
+				     context->devx_uid);
 		kfree(mentry);
 		break;
 	default:
@@ -2211,7 +2217,8 @@ static int uar_mmap(struct mlx5_ib_dev *dev, enum mlx5_ib_mmap_cmd cmd,
 		bfregi->count[bfreg_dyn_idx]++;
 		mutex_unlock(&bfregi->lock);
 
-		err = mlx5_cmd_alloc_uar(dev->mdev, &uar_index);
+		err = mlx5_cmd_uar_alloc(dev->mdev, &uar_index,
+					 context->devx_uid);
 		if (err) {
 			mlx5_ib_warn(dev, "UAR alloc failed\n");
 			goto free_bfreg;
@@ -2240,7 +2247,7 @@ err:
 	if (!dyn_uar)
 		return err;
 
-	mlx5_cmd_free_uar(dev->mdev, idx);
+	mlx5_cmd_uar_dealloc(dev->mdev, idx, context->devx_uid);
 
 free_bfreg:
 	mlx5_ib_free_bfreg(dev, bfregi, bfreg_dyn_idx);
@@ -3489,7 +3496,7 @@ alloc_uar_entry(struct mlx5_ib_ucontext *c,
 		return ERR_PTR(-ENOMEM);
 
 	dev = to_mdev(c->ibucontext.device);
-	err = mlx5_cmd_alloc_uar(dev->mdev, &uar_index);
+	err = mlx5_cmd_uar_alloc(dev->mdev, &uar_index, c->devx_uid);
 	if (err)
 		goto end;
 
@@ -3507,7 +3514,7 @@ alloc_uar_entry(struct mlx5_ib_ucontext *c,
 	return entry;
 
 err_insert:
-	mlx5_cmd_free_uar(dev->mdev, uar_index);
+	mlx5_cmd_uar_dealloc(dev->mdev, uar_index, c->devx_uid);
 end:
 	kfree(entry);
 	return ERR_PTR(err);
diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h
index bf20a388eabe..e462e368c353 100644
--- a/drivers/infiniband/hw/mlx5/mlx5_ib.h
+++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h
@@ -619,6 +619,20 @@ struct mlx5_user_mmap_entry {
 	u32 page_idx;
 };
 
+enum mlx5_mkey_type {
+	MLX5_MKEY_MR = 1,
+	MLX5_MKEY_MW,
+	MLX5_MKEY_INDIRECT_DEVX,
+};
+
+struct mlx5_ib_mkey {
+	u32 key;
+	enum mlx5_mkey_type type;
+	unsigned int ndescs;
+	struct wait_queue_head wait;
+	refcount_t usecount;
+};
+
 #define MLX5_IB_MTT_PRESENT (MLX5_IB_MTT_READ | MLX5_IB_MTT_WRITE)
 
 #define MLX5_IB_DM_MEMIC_ALLOWED_ACCESS (IB_ACCESS_LOCAL_WRITE   |\
@@ -637,7 +651,7 @@ struct mlx5_user_mmap_entry {
 
 struct mlx5_ib_mr {
 	struct ib_mr ibmr;
-	struct mlx5_core_mkey mmkey;
+	struct mlx5_ib_mkey mmkey;
 
 	/* User MR data */
 	struct mlx5_cache_ent *cache_ent;
@@ -659,7 +673,6 @@ struct mlx5_ib_mr {
 			void *descs_alloc;
 			dma_addr_t desc_map;
 			int max_descs;
-			int ndescs;
 			int desc_size;
 			int access_mode;
 
@@ -713,13 +726,7 @@ static inline bool is_dmabuf_mr(struct mlx5_ib_mr *mr)
 
 struct mlx5_ib_mw {
 	struct ib_mw		ibmw;
-	struct mlx5_core_mkey	mmkey;
-	int			ndescs;
-};
-
-struct mlx5_ib_devx_mr {
-	struct mlx5_core_mkey	mmkey;
-	int			ndescs;
+	struct mlx5_ib_mkey	mmkey;
 };
 
 struct mlx5_ib_umr_context {
@@ -1579,7 +1586,7 @@ static inline bool mlx5_ib_can_reconfig_with_umr(struct mlx5_ib_dev *dev,
 }
 
 static inline int mlx5r_store_odp_mkey(struct mlx5_ib_dev *dev,
-				       struct mlx5_core_mkey *mmkey)
+				       struct mlx5_ib_mkey *mmkey)
 {
 	refcount_set(&mmkey->usecount, 1);
 
@@ -1588,14 +1595,14 @@ static inline int mlx5r_store_odp_mkey(struct mlx5_ib_dev *dev,
 }
 
 /* deref an mkey that can participate in ODP flow */
-static inline void mlx5r_deref_odp_mkey(struct mlx5_core_mkey *mmkey)
+static inline void mlx5r_deref_odp_mkey(struct mlx5_ib_mkey *mmkey)
 {
 	if (refcount_dec_and_test(&mmkey->usecount))
 		wake_up(&mmkey->wait);
 }
 
 /* deref an mkey that can participate in ODP flow and wait for relese */
-static inline void mlx5r_deref_wait_odp_mkey(struct mlx5_core_mkey *mmkey)
+static inline void mlx5r_deref_wait_odp_mkey(struct mlx5_ib_mkey *mmkey)
 {
 	mlx5r_deref_odp_mkey(mmkey);
 	wait_event(mmkey->wait, refcount_read(&mmkey->usecount) == 0);
diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c
index 3be36ebbf67a..14c5564428ab 100644
--- a/drivers/infiniband/hw/mlx5/mr.c
+++ b/drivers/infiniband/hw/mlx5/mr.c
@@ -88,9 +88,8 @@ static void set_mkc_access_pd_addr_fields(void *mkc, int acc, u64 start_addr,
 	MLX5_SET64(mkc, mkc, start_addr, start_addr);
 }
 
-static void
-assign_mkey_variant(struct mlx5_ib_dev *dev, struct mlx5_core_mkey *mkey,
-		    u32 *in)
+static void assign_mkey_variant(struct mlx5_ib_dev *dev,
+				struct mlx5_ib_mkey *mkey, u32 *in)
 {
 	u8 key = atomic_inc_return(&dev->mkey_var);
 	void *mkc;
@@ -100,17 +99,22 @@ assign_mkey_variant(struct mlx5_ib_dev *dev, struct mlx5_core_mkey *mkey,
 	mkey->key = key;
 }
 
-static int
-mlx5_ib_create_mkey(struct mlx5_ib_dev *dev, struct mlx5_core_mkey *mkey,
-		    u32 *in, int inlen)
+static int mlx5_ib_create_mkey(struct mlx5_ib_dev *dev,
+			       struct mlx5_ib_mkey *mkey, u32 *in, int inlen)
 {
+	int ret;
+
 	assign_mkey_variant(dev, mkey, in);
-	return mlx5_core_create_mkey(dev->mdev, mkey, in, inlen);
+	ret = mlx5_core_create_mkey(dev->mdev, &mkey->key, in, inlen);
+	if (!ret)
+		init_waitqueue_head(&mkey->wait);
+
+	return ret;
 }
 
 static int
 mlx5_ib_create_mkey_cb(struct mlx5_ib_dev *dev,
-		       struct mlx5_core_mkey *mkey,
+		       struct mlx5_ib_mkey *mkey,
 		       struct mlx5_async_ctx *async_ctx,
 		       u32 *in, int inlen, u32 *out, int outlen,
 		       struct mlx5_async_work *context)
@@ -133,7 +137,7 @@ static int destroy_mkey(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr)
 {
 	WARN_ON(xa_load(&dev->odp_mkeys, mlx5_base_mkey(mr->mmkey.key)));
 
-	return mlx5_core_destroy_mkey(dev->mdev, &mr->mmkey);
+	return mlx5_core_destroy_mkey(dev->mdev, mr->mmkey.key);
 }
 
 static void create_mkey_callback(int status, struct mlx5_async_work *context)
@@ -260,10 +264,11 @@ static struct mlx5_ib_mr *create_cache_mr(struct mlx5_cache_ent *ent)
 		goto free_in;
 	}
 
-	err = mlx5_core_create_mkey(ent->dev->mdev, &mr->mmkey, in, inlen);
+	err = mlx5_core_create_mkey(ent->dev->mdev, &mr->mmkey.key, in, inlen);
 	if (err)
 		goto free_mr;
 
+	init_waitqueue_head(&mr->mmkey.wait);
 	mr->mmkey.type = MLX5_MKEY_MR;
 	WRITE_ONCE(ent->dev->cache.last_add, jiffies);
 	spin_lock_irq(&ent->lock);
@@ -290,7 +295,7 @@ static void remove_cache_mr_locked(struct mlx5_cache_ent *ent)
 	ent->available_mrs--;
 	ent->total_mrs--;
 	spin_unlock_irq(&ent->lock);
-	mlx5_core_destroy_mkey(ent->dev->mdev, &mr->mmkey);
+	mlx5_core_destroy_mkey(ent->dev->mdev, mr->mmkey.key);
 	kfree(mr);
 	spin_lock_irq(&ent->lock);
 }
@@ -658,7 +663,7 @@ static void clean_keys(struct mlx5_ib_dev *dev, int c)
 		ent->available_mrs--;
 		ent->total_mrs--;
 		spin_unlock_irq(&ent->lock);
-		mlx5_core_destroy_mkey(dev->mdev, &mr->mmkey);
+		mlx5_core_destroy_mkey(dev->mdev, mr->mmkey.key);
 	}
 
 	list_for_each_entry_safe(mr, tmp_mr, &del_list, list) {
@@ -911,12 +916,13 @@ static struct mlx5_cache_ent *mr_cache_ent_from_order(struct mlx5_ib_dev *dev,
 }
 
 static void set_mr_fields(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr,
-			  u64 length, int access_flags)
+			  u64 length, int access_flags, u64 iova)
 {
 	mr->ibmr.lkey = mr->mmkey.key;
 	mr->ibmr.rkey = mr->mmkey.key;
 	mr->ibmr.length = length;
 	mr->ibmr.device = &dev->ib_dev;
+	mr->ibmr.iova = iova;
 	mr->access_flags = access_flags;
 }
 
@@ -974,11 +980,8 @@ static struct mlx5_ib_mr *alloc_cacheable_mr(struct ib_pd *pd,
 
 	mr->ibmr.pd = pd;
 	mr->umem = umem;
-	mr->mmkey.iova = iova;
-	mr->mmkey.size = umem->length;
-	mr->mmkey.pd = to_mpd(pd)->pdn;
 	mr->page_shift = order_base_2(page_size);
-	set_mr_fields(dev, mr, umem->length, access_flags);
+	set_mr_fields(dev, mr, umem->length, access_flags, iova);
 
 	return mr;
 }
@@ -1087,8 +1090,8 @@ static void *mlx5_ib_create_xlt_wr(struct mlx5_ib_mr *mr,
 	wr->wr.opcode = MLX5_IB_WR_UMR;
 	wr->pd = mr->ibmr.pd;
 	wr->mkey = mr->mmkey.key;
-	wr->length = mr->mmkey.size;
-	wr->virt_addr = mr->mmkey.iova;
+	wr->length = mr->ibmr.length;
+	wr->virt_addr = mr->ibmr.iova;
 	wr->access_flags = mr->access_flags;
 	wr->page_shift = mr->page_shift;
 	wr->xlt_size = sg->length;
@@ -1341,7 +1344,7 @@ static struct mlx5_ib_mr *reg_create(struct ib_pd *pd, struct ib_umem *umem,
 	mr->mmkey.type = MLX5_MKEY_MR;
 	mr->desc_size = sizeof(struct mlx5_mtt);
 	mr->umem = umem;
-	set_mr_fields(dev, mr, umem->length, access_flags);
+	set_mr_fields(dev, mr, umem->length, access_flags, iova);
 	kvfree(in);
 
 	mlx5_ib_dbg(dev, "mkey = 0x%x\n", mr->mmkey.key);
@@ -1388,7 +1391,7 @@ static struct ib_mr *mlx5_ib_get_dm_mr(struct ib_pd *pd, u64 start_addr,
 
 	kfree(in);
 
-	set_mr_fields(dev, mr, length, acc);
+	set_mr_fields(dev, mr, length, acc, start_addr);
 
 	return &mr->ibmr;
 
@@ -1709,7 +1712,6 @@ static int umr_rereg_pd_access(struct mlx5_ib_mr *mr, struct ib_pd *pd,
 		return err;
 
 	mr->access_flags = access_flags;
-	mr->mmkey.pd = to_mpd(pd)->pdn;
 	return 0;
 }
 
@@ -1754,7 +1756,6 @@ static int umr_rereg_pas(struct mlx5_ib_mr *mr, struct ib_pd *pd,
 
 	if (flags & IB_MR_REREG_PD) {
 		mr->ibmr.pd = pd;
-		mr->mmkey.pd = to_mpd(pd)->pdn;
 		upd_flags |= MLX5_IB_UPD_XLT_PD;
 	}
 	if (flags & IB_MR_REREG_ACCESS) {
@@ -1763,8 +1764,8 @@ static int umr_rereg_pas(struct mlx5_ib_mr *mr, struct ib_pd *pd,
 	}
 
 	mr->ibmr.length = new_umem->length;
-	mr->mmkey.iova = iova;
-	mr->mmkey.size = new_umem->length;
+	mr->ibmr.iova = iova;
+	mr->ibmr.length = new_umem->length;
 	mr->page_shift = order_base_2(page_size);
 	mr->umem = new_umem;
 	err = mlx5_ib_update_mr_pas(mr, upd_flags);
@@ -1834,7 +1835,7 @@ struct ib_mr *mlx5_ib_rereg_user_mr(struct ib_mr *ib_mr, int flags, u64 start,
 		mr->umem = NULL;
 		atomic_sub(ib_umem_num_pages(umem), &dev->mdev->priv.reg_pages);
 
-		return create_real_mr(new_pd, umem, mr->mmkey.iova,
+		return create_real_mr(new_pd, umem, mr->ibmr.iova,
 				      new_access_flags);
 	}
 
@@ -2263,9 +2264,9 @@ int mlx5_ib_alloc_mw(struct ib_mw *ibmw, struct ib_udata *udata)
 	struct mlx5_ib_dev *dev = to_mdev(ibmw->device);
 	int inlen = MLX5_ST_SZ_BYTES(create_mkey_in);
 	struct mlx5_ib_mw *mw = to_mmw(ibmw);
+	unsigned int ndescs;
 	u32 *in = NULL;
 	void *mkc;
-	int ndescs;
 	int err;
 	struct mlx5_ib_alloc_mw req = {};
 	struct {
@@ -2310,7 +2311,7 @@ int mlx5_ib_alloc_mw(struct ib_mw *ibmw, struct ib_udata *udata)
 
 	mw->mmkey.type = MLX5_MKEY_MW;
 	ibmw->rkey = mw->mmkey.key;
-	mw->ndescs = ndescs;
+	mw->mmkey.ndescs = ndescs;
 
 	resp.response_length =
 		min(offsetofend(typeof(resp), response_length), udata->outlen);
@@ -2330,7 +2331,7 @@ int mlx5_ib_alloc_mw(struct ib_mw *ibmw, struct ib_udata *udata)
 	return 0;
 
 free_mkey:
-	mlx5_core_destroy_mkey(dev->mdev, &mw->mmkey);
+	mlx5_core_destroy_mkey(dev->mdev, mw->mmkey.key);
 free:
 	kfree(in);
 	return err;
@@ -2349,7 +2350,7 @@ int mlx5_ib_dealloc_mw(struct ib_mw *mw)
 		 */
 		mlx5r_deref_wait_odp_mkey(&mmw->mmkey);
 
-	return mlx5_core_destroy_mkey(dev->mdev, &mmw->mmkey);
+	return mlx5_core_destroy_mkey(dev->mdev, mmw->mmkey.key);
 }
 
 int mlx5_ib_check_mr_status(struct ib_mr *ibmr, u32 check_mask,
@@ -2406,7 +2407,7 @@ mlx5_ib_map_pa_mr_sg_pi(struct ib_mr *ibmr, struct scatterlist *data_sg,
 	mr->meta_length = 0;
 	if (data_sg_nents == 1) {
 		n++;
-		mr->ndescs = 1;
+		mr->mmkey.ndescs = 1;
 		if (data_sg_offset)
 			sg_offset = *data_sg_offset;
 		mr->data_length = sg_dma_len(data_sg) - sg_offset;
@@ -2459,7 +2460,7 @@ mlx5_ib_sg_to_klms(struct mlx5_ib_mr *mr,
 	if (sg_offset_p)
 		*sg_offset_p = sg_offset;
 
-	mr->ndescs = i;
+	mr->mmkey.ndescs = i;
 	mr->data_length = mr->ibmr.length;
 
 	if (meta_sg_nents) {
@@ -2492,11 +2493,11 @@ static int mlx5_set_page(struct ib_mr *ibmr, u64 addr)
 	struct mlx5_ib_mr *mr = to_mmr(ibmr);
 	__be64 *descs;
 
-	if (unlikely(mr->ndescs == mr->max_descs))
+	if (unlikely(mr->mmkey.ndescs == mr->max_descs))
 		return -ENOMEM;
 
 	descs = mr->descs;
-	descs[mr->ndescs++] = cpu_to_be64(addr | MLX5_EN_RD | MLX5_EN_WR);
+	descs[mr->mmkey.ndescs++] = cpu_to_be64(addr | MLX5_EN_RD | MLX5_EN_WR);
 
 	return 0;
 }
@@ -2506,11 +2507,11 @@ static int mlx5_set_page_pi(struct ib_mr *ibmr, u64 addr)
 	struct mlx5_ib_mr *mr = to_mmr(ibmr);
 	__be64 *descs;
 
-	if (unlikely(mr->ndescs + mr->meta_ndescs == mr->max_descs))
+	if (unlikely(mr->mmkey.ndescs + mr->meta_ndescs == mr->max_descs))
 		return -ENOMEM;
 
 	descs = mr->descs;
-	descs[mr->ndescs + mr->meta_ndescs++] =
+	descs[mr->mmkey.ndescs + mr->meta_ndescs++] =
 		cpu_to_be64(addr | MLX5_EN_RD | MLX5_EN_WR);
 
 	return 0;
@@ -2526,7 +2527,7 @@ mlx5_ib_map_mtt_mr_sg_pi(struct ib_mr *ibmr, struct scatterlist *data_sg,
 	struct mlx5_ib_mr *pi_mr = mr->mtt_mr;
 	int n;
 
-	pi_mr->ndescs = 0;
+	pi_mr->mmkey.ndescs = 0;
 	pi_mr->meta_ndescs = 0;
 	pi_mr->meta_length = 0;
 
@@ -2560,7 +2561,7 @@ mlx5_ib_map_mtt_mr_sg_pi(struct ib_mr *ibmr, struct scatterlist *data_sg,
 		 * metadata offset at the first metadata page
 		 */
 		pi_mr->pi_iova = (iova & page_mask) +
-				 pi_mr->ndescs * ibmr->page_size +
+				 pi_mr->mmkey.ndescs * ibmr->page_size +
 				 (pi_mr->ibmr.iova & ~page_mask);
 		/*
 		 * In order to use one MTT MR for data and metadata, we register
@@ -2591,7 +2592,7 @@ mlx5_ib_map_klm_mr_sg_pi(struct ib_mr *ibmr, struct scatterlist *data_sg,
 	struct mlx5_ib_mr *pi_mr = mr->klm_mr;
 	int n;
 
-	pi_mr->ndescs = 0;
+	pi_mr->mmkey.ndescs = 0;
 	pi_mr->meta_ndescs = 0;
 	pi_mr->meta_length = 0;
 
@@ -2626,7 +2627,7 @@ int mlx5_ib_map_mr_sg_pi(struct ib_mr *ibmr, struct scatterlist *data_sg,
 
 	WARN_ON(ibmr->type != IB_MR_TYPE_INTEGRITY);
 
-	mr->ndescs = 0;
+	mr->mmkey.ndescs = 0;
 	mr->data_length = 0;
 	mr->data_iova = 0;
 	mr->meta_ndescs = 0;
@@ -2682,7 +2683,7 @@ int mlx5_ib_map_mr_sg(struct ib_mr *ibmr, struct scatterlist *sg, int sg_nents,
 	struct mlx5_ib_mr *mr = to_mmr(ibmr);
 	int n;
 
-	mr->ndescs = 0;
+	mr->mmkey.ndescs = 0;
 
 	ib_dma_sync_single_for_cpu(ibmr->device, mr->desc_map,
 				   mr->desc_size * mr->max_descs,
diff --git a/drivers/infiniband/hw/mlx5/odp.c b/drivers/infiniband/hw/mlx5/odp.c
index 81147d774dd2..b1e2725f4586 100644
--- a/drivers/infiniband/hw/mlx5/odp.c
+++ b/drivers/infiniband/hw/mlx5/odp.c
@@ -430,7 +430,7 @@ static struct mlx5_ib_mr *implicit_get_child_mr(struct mlx5_ib_mr *imr,
 	mr->umem = &odp->umem;
 	mr->ibmr.lkey = mr->mmkey.key;
 	mr->ibmr.rkey = mr->mmkey.key;
-	mr->mmkey.iova = idx * MLX5_IMR_MTT_SIZE;
+	mr->ibmr.iova = idx * MLX5_IMR_MTT_SIZE;
 	mr->parent = imr;
 	odp->private = mr;
 
@@ -500,7 +500,7 @@ struct mlx5_ib_mr *mlx5_ib_alloc_implicit_mr(struct mlx5_ib_pd *pd,
 	}
 
 	imr->ibmr.pd = &pd->ibpd;
-	imr->mmkey.iova = 0;
+	imr->ibmr.iova = 0;
 	imr->umem = &umem_odp->umem;
 	imr->ibmr.lkey = imr->mmkey.key;
 	imr->ibmr.rkey = imr->mmkey.key;
@@ -738,7 +738,7 @@ static int pagefault_mr(struct mlx5_ib_mr *mr, u64 io_virt, size_t bcnt,
 {
 	struct ib_umem_odp *odp = to_ib_umem_odp(mr->umem);
 
-	if (unlikely(io_virt < mr->mmkey.iova))
+	if (unlikely(io_virt < mr->ibmr.iova))
 		return -EFAULT;
 
 	if (mr->umem->is_dmabuf)
@@ -747,7 +747,7 @@ static int pagefault_mr(struct mlx5_ib_mr *mr, u64 io_virt, size_t bcnt,
 	if (!odp->is_implicit_odp) {
 		u64 user_va;
 
-		if (check_add_overflow(io_virt - mr->mmkey.iova,
+		if (check_add_overflow(io_virt - mr->ibmr.iova,
 				       (u64)odp->umem.address, &user_va))
 			return -EFAULT;
 		if (unlikely(user_va >= ib_umem_end(odp) ||
@@ -788,7 +788,7 @@ struct pf_frame {
 	int depth;
 };
 
-static bool mkey_is_eq(struct mlx5_core_mkey *mmkey, u32 key)
+static bool mkey_is_eq(struct mlx5_ib_mkey *mmkey, u32 key)
 {
 	if (!mmkey)
 		return false;
@@ -797,21 +797,6 @@ static bool mkey_is_eq(struct mlx5_core_mkey *mmkey, u32 key)
 	return mmkey->key == key;
 }
 
-static int get_indirect_num_descs(struct mlx5_core_mkey *mmkey)
-{
-	struct mlx5_ib_mw *mw;
-	struct mlx5_ib_devx_mr *devx_mr;
-
-	if (mmkey->type == MLX5_MKEY_MW) {
-		mw = container_of(mmkey, struct mlx5_ib_mw, mmkey);
-		return mw->ndescs;
-	}
-
-	devx_mr = container_of(mmkey, struct mlx5_ib_devx_mr,
-			       mmkey);
-	return devx_mr->ndescs;
-}
-
 /*
  * Handle a single data segment in a page-fault WQE or RDMA region.
  *
@@ -831,12 +816,11 @@ static int pagefault_single_data_segment(struct mlx5_ib_dev *dev,
 {
 	int npages = 0, ret, i, outlen, cur_outlen = 0, depth = 0;
 	struct pf_frame *head = NULL, *frame;
-	struct mlx5_core_mkey *mmkey;
+	struct mlx5_ib_mkey *mmkey;
 	struct mlx5_ib_mr *mr;
 	struct mlx5_klm *pklm;
 	u32 *out = NULL;
 	size_t offset;
-	int ndescs;
 
 	io_virt += *bytes_committed;
 	bcnt -= *bytes_committed;
@@ -885,8 +869,6 @@ next_mr:
 
 	case MLX5_MKEY_MW:
 	case MLX5_MKEY_INDIRECT_DEVX:
-		ndescs = get_indirect_num_descs(mmkey);
-
 		if (depth >= MLX5_CAP_GEN(dev->mdev, max_indirection)) {
 			mlx5_ib_dbg(dev, "indirection level exceeded\n");
 			ret = -EFAULT;
@@ -894,7 +876,7 @@ next_mr:
 		}
 
 		outlen = MLX5_ST_SZ_BYTES(query_mkey_out) +
-			sizeof(*pklm) * (ndescs - 2);
+			sizeof(*pklm) * (mmkey->ndescs - 2);
 
 		if (outlen > cur_outlen) {
 			kfree(out);
@@ -909,14 +891,14 @@ next_mr:
 		pklm = (struct mlx5_klm *)MLX5_ADDR_OF(query_mkey_out, out,
 						       bsf0_klm0_pas_mtt0_1);
 
-		ret = mlx5_core_query_mkey(dev->mdev, mmkey, out, outlen);
+		ret = mlx5_core_query_mkey(dev->mdev, mmkey->key, out, outlen);
 		if (ret)
 			goto end;
 
 		offset = io_virt - MLX5_GET64(query_mkey_out, out,
 					      memory_key_mkey_entry.start_addr);
 
-		for (i = 0; bcnt && i < ndescs; i++, pklm++) {
+		for (i = 0; bcnt && i < mmkey->ndescs; i++, pklm++) {
 			if (offset >= be32_to_cpu(pklm->bcount)) {
 				offset -= be32_to_cpu(pklm->bcount);
 				continue;
@@ -1704,8 +1686,8 @@ get_prefetchable_mr(struct ib_pd *pd, enum ib_uverbs_advise_mr_advice advice,
 		    u32 lkey)
 {
 	struct mlx5_ib_dev *dev = to_mdev(pd->device);
-	struct mlx5_core_mkey *mmkey;
 	struct mlx5_ib_mr *mr = NULL;
+	struct mlx5_ib_mkey *mmkey;
 
 	xa_lock(&dev->odp_mkeys);
 	mmkey = xa_load(&dev->odp_mkeys, mlx5_base_mkey(lkey));
diff --git a/drivers/infiniband/hw/mlx5/wr.c b/drivers/infiniband/hw/mlx5/wr.c
index 8841620af82f..51e48ca9016e 100644
--- a/drivers/infiniband/hw/mlx5/wr.c
+++ b/drivers/infiniband/hw/mlx5/wr.c
@@ -217,7 +217,7 @@ static __be64 sig_mkey_mask(void)
 static void set_reg_umr_seg(struct mlx5_wqe_umr_ctrl_seg *umr,
 			    struct mlx5_ib_mr *mr, u8 flags, bool atomic)
 {
-	int size = (mr->ndescs + mr->meta_ndescs) * mr->desc_size;
+	int size = (mr->mmkey.ndescs + mr->meta_ndescs) * mr->desc_size;
 
 	memset(umr, 0, sizeof(*umr));
 
@@ -374,7 +374,7 @@ static void set_reg_mkey_seg(struct mlx5_mkey_seg *seg,
 			     struct mlx5_ib_mr *mr,
 			     u32 key, int access)
 {
-	int ndescs = ALIGN(mr->ndescs + mr->meta_ndescs, 8) >> 1;
+	int ndescs = ALIGN(mr->mmkey.ndescs + mr->meta_ndescs, 8) >> 1;
 
 	memset(seg, 0, sizeof(*seg));
 
@@ -439,7 +439,7 @@ static void set_reg_data_seg(struct mlx5_wqe_data_seg *dseg,
 			     struct mlx5_ib_mr *mr,
 			     struct mlx5_ib_pd *pd)
 {
-	int bcount = mr->desc_size * (mr->ndescs + mr->meta_ndescs);
+	int bcount = mr->desc_size * (mr->mmkey.ndescs + mr->meta_ndescs);
 
 	dseg->addr = cpu_to_be64(mr->desc_map);
 	dseg->byte_count = cpu_to_be32(ALIGN(bcount, 64));
@@ -861,7 +861,7 @@ static int set_reg_wr(struct mlx5_ib_qp *qp,
 	struct mlx5_ib_mr *mr = to_mmr(wr->mr);
 	struct mlx5_ib_pd *pd = to_mpd(qp->ibqp.pd);
 	struct mlx5_ib_dev *dev = to_mdev(pd->ibpd.device);
-	int mr_list_size = (mr->ndescs + mr->meta_ndescs) * mr->desc_size;
+	int mr_list_size = (mr->mmkey.ndescs + mr->meta_ndescs) * mr->desc_size;
 	bool umr_inline = mr_list_size <= MLX5_IB_SQ_UMR_INLINE_THRESHOLD;
 	bool atomic = wr->access & IB_ACCESS_REMOTE_ATOMIC;
 	u8 flags = 0;
@@ -1111,7 +1111,7 @@ static int handle_reg_mr_integrity(struct mlx5_ib_dev *dev,
 		memset(&pa_pi_mr, 0, sizeof(struct mlx5_ib_mr));
 		/* No UMR, use local_dma_lkey */
 		pa_pi_mr.ibmr.lkey = mr->ibmr.pd->local_dma_lkey;
-		pa_pi_mr.ndescs = mr->ndescs;
+		pa_pi_mr.mmkey.ndescs = mr->mmkey.ndescs;
 		pa_pi_mr.data_length = mr->data_length;
 		pa_pi_mr.data_iova = mr->data_iova;
 		if (mr->meta_ndescs) {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c
index da1bec04efff..eae9aa9c0811 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c
@@ -745,7 +745,7 @@ static int mlx5_fw_tracer_set_mtrc_conf(struct mlx5_fw_tracer *tracer)
 	MLX5_SET(mtrc_conf, in, trace_mode, TRACE_TO_MEMORY);
 	MLX5_SET(mtrc_conf, in, log_trace_buffer_size,
 		 ilog2(TRACER_BUFFER_PAGE_NUM));
-	MLX5_SET(mtrc_conf, in, trace_mkey, tracer->buff.mkey.key);
+	MLX5_SET(mtrc_conf, in, trace_mkey, tracer->buff.mkey);
 
 	err = mlx5_core_access_reg(dev, in, sizeof(in), out, sizeof(out),
 				   MLX5_REG_MTRC_CONF, 0, 1);
@@ -1028,7 +1028,7 @@ int mlx5_fw_tracer_init(struct mlx5_fw_tracer *tracer)
 
 err_notifier_unregister:
 	mlx5_eq_notifier_unregister(dev, &tracer->nb);
-	mlx5_core_destroy_mkey(dev, &tracer->buff.mkey);
+	mlx5_core_destroy_mkey(dev, tracer->buff.mkey);
 err_dealloc_pd:
 	mlx5_core_dealloc_pd(dev, tracer->buff.pdn);
 err_cancel_work:
@@ -1051,7 +1051,7 @@ void mlx5_fw_tracer_cleanup(struct mlx5_fw_tracer *tracer)
 	if (tracer->owner)
 		mlx5_fw_tracer_ownership_release(tracer);
 
-	mlx5_core_destroy_mkey(tracer->dev, &tracer->buff.mkey);
+	mlx5_core_destroy_mkey(tracer->dev, tracer->buff.mkey);
 	mlx5_core_dealloc_pd(tracer->dev, tracer->buff.pdn);
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.h b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.h
index 97252a85d65e..4762b55b0b0e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.h
@@ -89,7 +89,7 @@ struct mlx5_fw_tracer {
 		void *log_buf;
 		dma_addr_t dma;
 		u32 size;
-		struct mlx5_core_mkey mkey;
+		u32 mkey;
 		u32 consumer_index;
 	} buff;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/rsc_dump.c b/drivers/net/ethernet/mellanox/mlx5/core/diag/rsc_dump.c
index ed4fb79b4db7..538adab6878b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/diag/rsc_dump.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/rsc_dump.c
@@ -30,7 +30,7 @@ static const char *const mlx5_rsc_sgmt_name[] = {
 
 struct mlx5_rsc_dump {
 	u32 pdn;
-	struct mlx5_core_mkey mkey;
+	u32 mkey;
 	u16 fw_segment_type[MLX5_SGMT_TYPE_NUM];
 };
 
@@ -89,7 +89,7 @@ static int mlx5_rsc_dump_trigger(struct mlx5_core_dev *dev, struct mlx5_rsc_dump
 		return -ENOMEM;
 
 	in_seq_num = MLX5_GET(resource_dump, cmd->cmd, seq_num);
-	MLX5_SET(resource_dump, cmd->cmd, mkey, rsc_dump->mkey.key);
+	MLX5_SET(resource_dump, cmd->cmd, mkey, rsc_dump->mkey);
 	MLX5_SET64(resource_dump, cmd->cmd, address, dma);
 
 	err = mlx5_core_access_reg(dev, cmd->cmd, sizeof(cmd->cmd), cmd->cmd,
@@ -202,7 +202,7 @@ free_page:
 }
 
 static int mlx5_rsc_dump_create_mkey(struct mlx5_core_dev *mdev, u32 pdn,
-				     struct mlx5_core_mkey *mkey)
+				     u32 *mkey)
 {
 	int inlen = MLX5_ST_SZ_BYTES(create_mkey_in);
 	void *mkc;
@@ -276,7 +276,7 @@ int mlx5_rsc_dump_init(struct mlx5_core_dev *dev)
 	return err;
 
 destroy_mkey:
-	mlx5_core_destroy_mkey(dev, &rsc_dump->mkey);
+	mlx5_core_destroy_mkey(dev, rsc_dump->mkey);
 free_pd:
 	mlx5_core_dealloc_pd(dev, rsc_dump->pdn);
 	return err;
@@ -287,6 +287,6 @@ void mlx5_rsc_dump_cleanup(struct mlx5_core_dev *dev)
 	if (IS_ERR_OR_NULL(dev->rsc_dump))
 		return;
 
-	mlx5_core_destroy_mkey(dev, &dev->rsc_dump->mkey);
+	mlx5_core_destroy_mkey(dev, dev->rsc_dump->mkey);
 	mlx5_core_dealloc_pd(dev, dev->rsc_dump->pdn);
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 67453dd75b93..f0ac6b0d9653 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -643,7 +643,7 @@ struct mlx5e_rq_frags_info {
 };
 
 struct mlx5e_shampo_hd {
-	struct mlx5_core_mkey mkey;
+	u32 mkey;
 	struct mlx5e_dma_info *info;
 	struct page *last_page;
 	u16 hd_per_wq;
@@ -731,7 +731,7 @@ struct mlx5e_rq {
 	u8                     wq_type;
 	u32                    rqn;
 	struct mlx5_core_dev  *mdev;
-	struct mlx5_core_mkey  umr_mkey;
+	u32  umr_mkey;
 	struct mlx5e_dma_info  wqe_overflow;
 
 	/* XDP read-mostly */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c
index 3a86f66d1295..18d542b1c5cb 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c
@@ -682,7 +682,7 @@ int mlx5e_ptp_open(struct mlx5e_priv *priv, struct mlx5e_params *params,
 	c->tstamp   = &priv->tstamp;
 	c->pdev     = mlx5_core_dma_dev(priv->mdev);
 	c->netdev   = priv->netdev;
-	c->mkey_be  = cpu_to_be32(priv->mdev->mlx5e_res.hw_objs.mkey.key);
+	c->mkey_be  = cpu_to_be32(priv->mdev->mlx5e_res.hw_objs.mkey);
 	c->num_tc   = mlx5e_get_dcb_num_tc(params);
 	c->stats    = &priv->ptp_stats.ch;
 	c->lag_port = lag_port;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/trap.c b/drivers/net/ethernet/mellanox/mlx5/core/en/trap.c
index d54607a42740..a55b066746cb 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/trap.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/trap.c
@@ -137,7 +137,7 @@ static struct mlx5e_trap *mlx5e_open_trap(struct mlx5e_priv *priv)
 	t->tstamp   = &priv->tstamp;
 	t->pdev     = mlx5_core_dma_dev(priv->mdev);
 	t->netdev   = priv->netdev;
-	t->mkey_be  = cpu_to_be32(priv->mdev->mlx5e_res.hw_objs.mkey.key);
+	t->mkey_be  = cpu_to_be32(priv->mdev->mlx5e_res.hw_objs.mkey);
 	t->stats    = &priv->trap_stats.ch;
 
 	netif_napi_add(netdev, &t->napi, mlx5e_trap_napi_poll, 64);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c
index 84eb7201c142..c0f409c195bf 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c
@@ -47,7 +47,7 @@ void mlx5e_mkey_set_relaxed_ordering(struct mlx5_core_dev *mdev, void *mkc)
 }
 
 static int mlx5e_create_mkey(struct mlx5_core_dev *mdev, u32 pdn,
-			     struct mlx5_core_mkey *mkey)
+			     u32 *mkey)
 {
 	int inlen = MLX5_ST_SZ_BYTES(create_mkey_in);
 	void *mkc;
@@ -108,7 +108,7 @@ int mlx5e_create_mdev_resources(struct mlx5_core_dev *mdev)
 	return 0;
 
 err_destroy_mkey:
-	mlx5_core_destroy_mkey(mdev, &res->mkey);
+	mlx5_core_destroy_mkey(mdev, res->mkey);
 err_dealloc_transport_domain:
 	mlx5_core_dealloc_transport_domain(mdev, res->td.tdn);
 err_dealloc_pd:
@@ -121,7 +121,7 @@ void mlx5e_destroy_mdev_resources(struct mlx5_core_dev *mdev)
 	struct mlx5e_hw_objs *res = &mdev->mlx5e_res.hw_objs;
 
 	mlx5_free_bfreg(mdev, &res->bfreg);
-	mlx5_core_destroy_mkey(mdev, &res->mkey);
+	mlx5_core_destroy_mkey(mdev, res->mkey);
 	mlx5_core_dealloc_transport_domain(mdev, res->td.tdn);
 	mlx5_core_dealloc_pd(mdev, res->pdn);
 	memset(res, 0, sizeof(*res));
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 6f398f636f01..65571593ec5c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -273,8 +273,7 @@ static int mlx5e_rq_alloc_mpwqe_info(struct mlx5e_rq *rq, int node)
 }
 
 static int mlx5e_create_umr_mtt_mkey(struct mlx5_core_dev *mdev,
-				     u64 npages, u8 page_shift,
-				     struct mlx5_core_mkey *umr_mkey,
+				     u64 npages, u8 page_shift, u32 *umr_mkey,
 				     dma_addr_t filler_addr)
 {
 	struct mlx5_mtt *mtt;
@@ -325,7 +324,7 @@ static int mlx5e_create_umr_mtt_mkey(struct mlx5_core_dev *mdev,
 
 static int mlx5e_create_umr_klm_mkey(struct mlx5_core_dev *mdev,
 				     u64 nentries,
-				     struct mlx5_core_mkey *umr_mkey)
+				     u32 *umr_mkey)
 {
 	int inlen;
 	void *mkc;
@@ -519,7 +518,7 @@ static int mlx5_rq_shampo_alloc(struct mlx5_core_dev *mdev,
 		goto err_hw_gro_data;
 	}
 	rq->mpwqe.shampo->key =
-		cpu_to_be32(rq->mpwqe.shampo->mkey.key);
+		cpu_to_be32(rq->mpwqe.shampo->mkey);
 	rq->mpwqe.shampo->hd_per_wqe =
 		mlx5e_shampo_hd_per_wqe(mdev, params, rqp);
 	wq_size = BIT(MLX5_GET(wq, wqc, log_wq_sz));
@@ -530,7 +529,7 @@ static int mlx5_rq_shampo_alloc(struct mlx5_core_dev *mdev,
 err_hw_gro_data:
 	mlx5e_rq_shampo_hd_info_free(rq);
 err_shampo_info:
-	mlx5_core_destroy_mkey(mdev, &rq->mpwqe.shampo->mkey);
+	mlx5_core_destroy_mkey(mdev, rq->mpwqe.shampo->mkey);
 err_shampo_hd:
 	mlx5e_rq_shampo_hd_free(rq);
 out:
@@ -544,7 +543,7 @@ static void mlx5e_rq_free_shampo(struct mlx5e_rq *rq)
 
 	kvfree(rq->hw_gro_data);
 	mlx5e_rq_shampo_hd_info_free(rq);
-	mlx5_core_destroy_mkey(rq->mdev, &rq->mpwqe.shampo->mkey);
+	mlx5_core_destroy_mkey(rq->mdev, rq->mpwqe.shampo->mkey);
 	mlx5e_rq_shampo_hd_free(rq);
 }
 
@@ -600,7 +599,7 @@ static int mlx5e_alloc_rq(struct mlx5e_params *params,
 		err = mlx5e_create_rq_umr_mkey(mdev, rq);
 		if (err)
 			goto err_rq_drop_page;
-		rq->mkey_be = cpu_to_be32(rq->umr_mkey.key);
+		rq->mkey_be = cpu_to_be32(rq->umr_mkey);
 
 		err = mlx5e_rq_alloc_mpwqe_info(rq, node);
 		if (err)
@@ -637,7 +636,7 @@ static int mlx5e_alloc_rq(struct mlx5e_params *params,
 		if (err)
 			goto err_rq_frags;
 
-		rq->mkey_be = cpu_to_be32(mdev->mlx5e_res.hw_objs.mkey.key);
+		rq->mkey_be = cpu_to_be32(mdev->mlx5e_res.hw_objs.mkey);
 	}
 
 	if (xsk) {
@@ -728,7 +727,7 @@ err_free_by_rq_type:
 	case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ:
 		kvfree(rq->mpwqe.info);
 err_rq_mkey:
-		mlx5_core_destroy_mkey(mdev, &rq->umr_mkey);
+		mlx5_core_destroy_mkey(mdev, rq->umr_mkey);
 err_rq_drop_page:
 		mlx5e_free_mpwqe_rq_drop_page(rq);
 		break;
@@ -761,7 +760,7 @@ static void mlx5e_free_rq(struct mlx5e_rq *rq)
 	switch (rq->wq_type) {
 	case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ:
 		kvfree(rq->mpwqe.info);
-		mlx5_core_destroy_mkey(rq->mdev, &rq->umr_mkey);
+		mlx5_core_destroy_mkey(rq->mdev, rq->umr_mkey);
 		mlx5e_free_mpwqe_rq_drop_page(rq);
 		mlx5e_rq_free_shampo(rq);
 		break;
@@ -820,7 +819,7 @@ int mlx5e_create_rq(struct mlx5e_rq *rq, struct mlx5e_rq_param *param)
 	if (test_bit(MLX5E_RQ_STATE_SHAMPO, &rq->state)) {
 		MLX5_SET(wq, wq, log_headers_buffer_entry_num,
 			 order_base_2(rq->mpwqe.shampo->hd_per_wq));
-		MLX5_SET(wq, wq, headers_mkey, rq->mpwqe.shampo->mkey.key);
+		MLX5_SET(wq, wq, headers_mkey, rq->mpwqe.shampo->mkey);
 	}
 
 	mlx5_fill_page_frag_array(&rq->wq_ctrl.buf,
@@ -2205,7 +2204,7 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix,
 	c->cpu      = cpu;
 	c->pdev     = mlx5_core_dma_dev(priv->mdev);
 	c->netdev   = priv->netdev;
-	c->mkey_be  = cpu_to_be32(priv->mdev->mlx5e_res.hw_objs.mkey.key);
+	c->mkey_be  = cpu_to_be32(priv->mdev->mlx5e_res.hw_objs.mkey);
 	c->num_tc   = mlx5e_get_dcb_num_tc(params);
 	c->xdp      = !!params->xdp_prog;
 	c->stats    = &priv->channel_stats[ix].ch;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index fe979edd96dc..f63c8ff3ef3f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -544,7 +544,7 @@ static int mlx5e_build_shampo_hd_umr(struct mlx5e_rq *rq,
 {
 	struct mlx5e_shampo_hd *shampo = rq->mpwqe.shampo;
 	u16 entries, pi, i, header_offset, err, wqe_bbs, new_entries;
-	u32 lkey = rq->mdev->mlx5e_res.hw_objs.mkey.key;
+	u32 lkey = rq->mdev->mlx5e_res.hw_objs.mkey;
 	struct page *page = shampo->last_page;
 	u64 addr = shampo->last_addr;
 	struct mlx5e_dma_info *dma_info;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c b/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c
index 306279b7f9e7..12abe991583a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c
@@ -115,7 +115,7 @@ static int mlx5_fpga_conn_post_recv(struct mlx5_fpga_conn *conn,
 	ix = conn->qp.rq.pc & (conn->qp.rq.size - 1);
 	data = mlx5_wq_cyc_get_wqe(&conn->qp.wq.rq, ix);
 	data->byte_count = cpu_to_be32(buf->sg[0].size);
-	data->lkey = cpu_to_be32(conn->fdev->conn_res.mkey.key);
+	data->lkey = cpu_to_be32(conn->fdev->conn_res.mkey);
 	data->addr = cpu_to_be64(buf->sg[0].dma_addr);
 
 	conn->qp.rq.pc++;
@@ -155,7 +155,7 @@ static void mlx5_fpga_conn_post_send(struct mlx5_fpga_conn *conn,
 		if (!buf->sg[sgi].data)
 			break;
 		data->byte_count = cpu_to_be32(buf->sg[sgi].size);
-		data->lkey = cpu_to_be32(conn->fdev->conn_res.mkey.key);
+		data->lkey = cpu_to_be32(conn->fdev->conn_res.mkey);
 		data->addr = cpu_to_be64(buf->sg[sgi].dma_addr);
 		data++;
 		size++;
@@ -221,7 +221,7 @@ static int mlx5_fpga_conn_post_recv_buf(struct mlx5_fpga_conn *conn)
 }
 
 static int mlx5_fpga_conn_create_mkey(struct mlx5_core_dev *mdev, u32 pdn,
-				      struct mlx5_core_mkey *mkey)
+				      u32 *mkey)
 {
 	int inlen = MLX5_ST_SZ_BYTES(create_mkey_in);
 	void *mkc;
@@ -978,7 +978,7 @@ int mlx5_fpga_conn_device_init(struct mlx5_fpga_device *fdev)
 		mlx5_fpga_err(fdev, "create mkey failed, %d\n", err);
 		goto err_dealloc_pd;
 	}
-	mlx5_fpga_dbg(fdev, "Created mkey 0x%x\n", fdev->conn_res.mkey.key);
+	mlx5_fpga_dbg(fdev, "Created mkey 0x%x\n", fdev->conn_res.mkey);
 
 	return 0;
 
@@ -994,7 +994,7 @@ out:
 
 void mlx5_fpga_conn_device_cleanup(struct mlx5_fpga_device *fdev)
 {
-	mlx5_core_destroy_mkey(fdev->mdev, &fdev->conn_res.mkey);
+	mlx5_core_destroy_mkey(fdev->mdev, fdev->conn_res.mkey);
 	mlx5_core_dealloc_pd(fdev->mdev, fdev->conn_res.pdn);
 	mlx5_put_uars_page(fdev->mdev, fdev->conn_res.uar);
 	mlx5_nic_vport_disable_roce(fdev->mdev);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/core.h b/drivers/net/ethernet/mellanox/mlx5/core/fpga/core.h
index 52c9dee91ea4..2a984e82ae16 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/core.h
@@ -54,7 +54,7 @@ struct mlx5_fpga_device {
 	/* QP Connection resources */
 	struct {
 		u32 pdn;
-		struct mlx5_core_mkey mkey;
+		u32 mkey;
 		struct mlx5_uars_page *uar;
 	} conn_res;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
index 873efde0d458..386ab9a2d490 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
@@ -99,6 +99,9 @@
 #define LEFTOVERS_NUM_LEVELS 1
 #define LEFTOVERS_NUM_PRIOS 1
 
+#define RDMA_RX_COUNTERS_PRIO_NUM_LEVELS 1
+#define RDMA_TX_COUNTERS_PRIO_NUM_LEVELS 1
+
 #define BY_PASS_PRIO_NUM_LEVELS 1
 #define BY_PASS_MIN_LEVEL (ETHTOOL_MIN_LEVEL + MLX5_BY_PASS_NUM_PRIOS +\
 			   LEFTOVERS_NUM_PRIOS)
@@ -206,34 +209,63 @@ static struct init_tree_node egress_root_fs = {
 	}
 };
 
-#define RDMA_RX_BYPASS_PRIO 0
-#define RDMA_RX_KERNEL_PRIO 1
+enum {
+	RDMA_RX_COUNTERS_PRIO,
+	RDMA_RX_BYPASS_PRIO,
+	RDMA_RX_KERNEL_PRIO,
+};
+
+#define RDMA_RX_BYPASS_MIN_LEVEL MLX5_BY_PASS_NUM_REGULAR_PRIOS
+#define RDMA_RX_KERNEL_MIN_LEVEL (RDMA_RX_BYPASS_MIN_LEVEL + 1)
+#define RDMA_RX_COUNTERS_MIN_LEVEL (RDMA_RX_KERNEL_MIN_LEVEL + 2)
+
 static struct init_tree_node rdma_rx_root_fs = {
 	.type = FS_TYPE_NAMESPACE,
-	.ar_size = 2,
+	.ar_size = 3,
 	.children = (struct init_tree_node[]) {
+		[RDMA_RX_COUNTERS_PRIO] =
+		ADD_PRIO(0, RDMA_RX_COUNTERS_MIN_LEVEL, 0,
+			 FS_CHAINING_CAPS,
+			 ADD_NS(MLX5_FLOW_TABLE_MISS_ACTION_DEF,
+				ADD_MULTIPLE_PRIO(MLX5_RDMA_RX_NUM_COUNTERS_PRIOS,
+						  RDMA_RX_COUNTERS_PRIO_NUM_LEVELS))),
 		[RDMA_RX_BYPASS_PRIO] =
-		ADD_PRIO(0, MLX5_BY_PASS_NUM_REGULAR_PRIOS, 0,
+		ADD_PRIO(0, RDMA_RX_BYPASS_MIN_LEVEL, 0,
 			 FS_CHAINING_CAPS,
 			 ADD_NS(MLX5_FLOW_TABLE_MISS_ACTION_DEF,
 				ADD_MULTIPLE_PRIO(MLX5_BY_PASS_NUM_REGULAR_PRIOS,
 						  BY_PASS_PRIO_NUM_LEVELS))),
 		[RDMA_RX_KERNEL_PRIO] =
-		ADD_PRIO(0, MLX5_BY_PASS_NUM_REGULAR_PRIOS + 1, 0,
+		ADD_PRIO(0, RDMA_RX_KERNEL_MIN_LEVEL, 0,
 			 FS_CHAINING_CAPS,
 			 ADD_NS(MLX5_FLOW_TABLE_MISS_ACTION_SWITCH_DOMAIN,
 				ADD_MULTIPLE_PRIO(1, 1))),
 	}
 };
 
+enum {
+	RDMA_TX_COUNTERS_PRIO,
+	RDMA_TX_BYPASS_PRIO,
+};
+
+#define RDMA_TX_BYPASS_MIN_LEVEL MLX5_BY_PASS_NUM_PRIOS
+#define RDMA_TX_COUNTERS_MIN_LEVEL (RDMA_TX_BYPASS_MIN_LEVEL + 1)
+
 static struct init_tree_node rdma_tx_root_fs = {
 	.type = FS_TYPE_NAMESPACE,
-	.ar_size = 1,
+	.ar_size = 2,
 	.children = (struct init_tree_node[]) {
-		ADD_PRIO(0, MLX5_BY_PASS_NUM_PRIOS, 0,
+		[RDMA_TX_COUNTERS_PRIO] =
+		ADD_PRIO(0, RDMA_TX_COUNTERS_MIN_LEVEL, 0,
+			 FS_CHAINING_CAPS,
+			 ADD_NS(MLX5_FLOW_TABLE_MISS_ACTION_DEF,
+				ADD_MULTIPLE_PRIO(MLX5_RDMA_TX_NUM_COUNTERS_PRIOS,
+						  RDMA_TX_COUNTERS_PRIO_NUM_LEVELS))),
+		[RDMA_TX_BYPASS_PRIO] =
+		ADD_PRIO(0, RDMA_TX_BYPASS_MIN_LEVEL, 0,
 			 FS_CHAINING_CAPS_RDMA_TX,
 			 ADD_NS(MLX5_FLOW_TABLE_MISS_ACTION_DEF,
-				ADD_MULTIPLE_PRIO(MLX5_BY_PASS_NUM_PRIOS,
+				ADD_MULTIPLE_PRIO(RDMA_TX_BYPASS_MIN_LEVEL,
 						  BY_PASS_PRIO_NUM_LEVELS))),
 	}
 };
@@ -2219,6 +2251,12 @@ struct mlx5_flow_namespace *mlx5_get_flow_namespace(struct mlx5_core_dev *dev,
 		prio = RDMA_RX_KERNEL_PRIO;
 	} else if (type == MLX5_FLOW_NAMESPACE_RDMA_TX) {
 		root_ns = steering->rdma_tx_root_ns;
+	} else if (type == MLX5_FLOW_NAMESPACE_RDMA_RX_COUNTERS) {
+		root_ns = steering->rdma_rx_root_ns;
+		prio = RDMA_RX_COUNTERS_PRIO;
+	} else if (type == MLX5_FLOW_NAMESPACE_RDMA_TX_COUNTERS) {
+		root_ns = steering->rdma_tx_root_ns;
+		prio = RDMA_TX_COUNTERS_PRIO;
 	} else { /* Must be NIC RX */
 		root_ns = steering->root_ns;
 		prio = type;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mr.c b/drivers/net/ethernet/mellanox/mlx5/core/mr.c
index 174f71ed5280..f099a087400e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/mr.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/mr.c
@@ -35,13 +35,11 @@
 #include <linux/mlx5/driver.h>
 #include "mlx5_core.h"
 
-int mlx5_core_create_mkey(struct mlx5_core_dev *dev,
-			  struct mlx5_core_mkey *mkey,
-			  u32 *in, int inlen)
+int mlx5_core_create_mkey(struct mlx5_core_dev *dev, u32 *mkey, u32 *in,
+			  int inlen)
 {
 	u32 lout[MLX5_ST_SZ_DW(create_mkey_out)] = {};
 	u32 mkey_index;
-	void *mkc;
 	int err;
 
 	MLX5_SET(create_mkey_in, in, opcode, MLX5_CMD_OP_CREATE_MKEY);
@@ -50,38 +48,33 @@ int mlx5_core_create_mkey(struct mlx5_core_dev *dev,
 	if (err)
 		return err;
 
-	mkc = MLX5_ADDR_OF(create_mkey_in, in, memory_key_mkey_entry);
 	mkey_index = MLX5_GET(create_mkey_out, lout, mkey_index);
-	mkey->iova = MLX5_GET64(mkc, mkc, start_addr);
-	mkey->size = MLX5_GET64(mkc, mkc, len);
-	mkey->key = (u32)mlx5_mkey_variant(mkey->key) | mlx5_idx_to_mkey(mkey_index);
-	mkey->pd = MLX5_GET(mkc, mkc, pd);
-	init_waitqueue_head(&mkey->wait);
+	*mkey = MLX5_GET(create_mkey_in, in, memory_key_mkey_entry.mkey_7_0) |
+		mlx5_idx_to_mkey(mkey_index);
 
-	mlx5_core_dbg(dev, "out 0x%x, mkey 0x%x\n", mkey_index, mkey->key);
+	mlx5_core_dbg(dev, "out 0x%x, mkey 0x%x\n", mkey_index, *mkey);
 	return 0;
 }
 EXPORT_SYMBOL(mlx5_core_create_mkey);
 
-int mlx5_core_destroy_mkey(struct mlx5_core_dev *dev,
-			   struct mlx5_core_mkey *mkey)
+int mlx5_core_destroy_mkey(struct mlx5_core_dev *dev, u32 mkey)
 {
 	u32 in[MLX5_ST_SZ_DW(destroy_mkey_in)] = {};
 
 	MLX5_SET(destroy_mkey_in, in, opcode, MLX5_CMD_OP_DESTROY_MKEY);
-	MLX5_SET(destroy_mkey_in, in, mkey_index, mlx5_mkey_to_idx(mkey->key));
+	MLX5_SET(destroy_mkey_in, in, mkey_index, mlx5_mkey_to_idx(mkey));
 	return mlx5_cmd_exec_in(dev, destroy_mkey, in);
 }
 EXPORT_SYMBOL(mlx5_core_destroy_mkey);
 
-int mlx5_core_query_mkey(struct mlx5_core_dev *dev, struct mlx5_core_mkey *mkey,
-			 u32 *out, int outlen)
+int mlx5_core_query_mkey(struct mlx5_core_dev *dev, u32 mkey, u32 *out,
+			 int outlen)
 {
 	u32 in[MLX5_ST_SZ_DW(query_mkey_in)] = {};
 
 	memset(out, 0, outlen);
 	MLX5_SET(query_mkey_in, in, opcode, MLX5_CMD_OP_QUERY_MKEY);
-	MLX5_SET(query_mkey_in, in, mkey_index, mlx5_mkey_to_idx(mkey->key));
+	MLX5_SET(query_mkey_in, in, mkey_index, mlx5_mkey_to_idx(mkey));
 	return mlx5_cmd_exec(dev, in, sizeof(in), out, outlen);
 }
 EXPORT_SYMBOL(mlx5_core_query_mkey);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_icm_pool.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_icm_pool.c
index 66c24767e3b0..7f6fd9c5e371 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_icm_pool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_icm_pool.c
@@ -24,7 +24,7 @@ struct mlx5dr_icm_dm {
 };
 
 struct mlx5dr_icm_mr {
-	struct mlx5_core_mkey mkey;
+	u32 mkey;
 	struct mlx5dr_icm_dm dm;
 	struct mlx5dr_domain *dmn;
 	size_t length;
@@ -33,7 +33,7 @@ struct mlx5dr_icm_mr {
 
 static int dr_icm_create_dm_mkey(struct mlx5_core_dev *mdev,
 				 u32 pd, u64 length, u64 start_addr, int mode,
-				 struct mlx5_core_mkey *mkey)
+				 u32 *mkey)
 {
 	u32 inlen = MLX5_ST_SZ_BYTES(create_mkey_in);
 	u32 in[MLX5_ST_SZ_DW(create_mkey_in)] = {};
@@ -116,7 +116,7 @@ dr_icm_pool_mr_create(struct mlx5dr_icm_pool *pool)
 	return icm_mr;
 
 free_mkey:
-	mlx5_core_destroy_mkey(mdev, &icm_mr->mkey);
+	mlx5_core_destroy_mkey(mdev, icm_mr->mkey);
 free_dm:
 	mlx5_dm_sw_icm_dealloc(mdev, icm_mr->dm.type, icm_mr->dm.length, 0,
 			       icm_mr->dm.addr, icm_mr->dm.obj_id);
@@ -130,7 +130,7 @@ static void dr_icm_pool_mr_destroy(struct mlx5dr_icm_mr *icm_mr)
 	struct mlx5_core_dev *mdev = icm_mr->dmn->mdev;
 	struct mlx5dr_icm_dm *dm = &icm_mr->dm;
 
-	mlx5_core_destroy_mkey(mdev, &icm_mr->mkey);
+	mlx5_core_destroy_mkey(mdev, icm_mr->mkey);
 	mlx5_dm_sw_icm_dealloc(mdev, dm->type, dm->length, 0,
 			       dm->addr, dm->obj_id);
 	kvfree(icm_mr);
@@ -252,7 +252,7 @@ dr_icm_chunk_create(struct mlx5dr_icm_pool *pool,
 
 	offset = mlx5dr_icm_pool_dm_type_to_entry_size(pool->icm_type) * seg;
 
-	chunk->rkey = buddy_mem_pool->icm_mr->mkey.key;
+	chunk->rkey = buddy_mem_pool->icm_mr->mkey;
 	chunk->mr_addr = offset;
 	chunk->icm_addr =
 		(uintptr_t)buddy_mem_pool->icm_mr->icm_start_addr + offset;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c
index bfb14b4b1906..00aef47d7682 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c
@@ -350,7 +350,7 @@ static void dr_fill_data_segs(struct mlx5dr_send_ring *send_ring,
 	send_info->read.length = send_info->write.length;
 	/* Read into the same write area */
 	send_info->read.addr = (uintptr_t)send_info->write.addr;
-	send_info->read.lkey = send_ring->mr->mkey.key;
+	send_info->read.lkey = send_ring->mr->mkey;
 
 	if (send_ring->pending_wqe % send_ring->signal_th == 0)
 		send_info->read.send_flags = IB_SEND_SIGNALED;
@@ -388,7 +388,7 @@ static int dr_postsend_icm_data(struct mlx5dr_domain *dmn,
 		       (void *)(uintptr_t)send_info->write.addr,
 		       send_info->write.length);
 		send_info->write.addr = (uintptr_t)send_ring->mr->dma_addr + buff_offset;
-		send_info->write.lkey = send_ring->mr->mkey.key;
+		send_info->write.lkey = send_ring->mr->mkey;
 	}
 
 	send_ring->tx_head++;
@@ -848,8 +848,7 @@ static void dr_destroy_cq(struct mlx5_core_dev *mdev, struct mlx5dr_cq *cq)
 	kfree(cq);
 }
 
-static int
-dr_create_mkey(struct mlx5_core_dev *mdev, u32 pdn, struct mlx5_core_mkey *mkey)
+static int dr_create_mkey(struct mlx5_core_dev *mdev, u32 pdn, u32 *mkey)
 {
 	u32 in[MLX5_ST_SZ_DW(create_mkey_in)] = {};
 	void *mkc;
@@ -908,7 +907,7 @@ static struct mlx5dr_mr *dr_reg_mr(struct mlx5_core_dev *mdev,
 
 static void dr_dereg_mr(struct mlx5_core_dev *mdev, struct mlx5dr_mr *mr)
 {
-	mlx5_core_destroy_mkey(mdev, &mr->mkey);
+	mlx5_core_destroy_mkey(mdev, mr->mkey);
 	dma_unmap_single(mlx5_core_dma_dev(mdev), mr->dma_addr, mr->size,
 			 DMA_BIDIRECTIONAL);
 	kfree(mr);
@@ -1039,7 +1038,7 @@ int mlx5dr_send_ring_force_drain(struct mlx5dr_domain *dmn)
 	send_info.write.lkey = 0;
 	/* Using the sync_mr in order to write/read */
 	send_info.remote_addr = (uintptr_t)send_ring->sync_mr->addr;
-	send_info.rkey = send_ring->sync_mr->mkey.key;
+	send_info.rkey = send_ring->sync_mr->mkey;
 
 	for (i = 0; i < num_of_sends_req; i++) {
 		ret = dr_postsend_icm_data(dmn, &send_info);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h
index 73fed94af09a..3f47d2b3b6e6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h
@@ -1264,7 +1264,7 @@ struct mlx5dr_cq {
 
 struct mlx5dr_mr {
 	struct mlx5_core_dev *mdev;
-	struct mlx5_core_mkey mkey;
+	u32 mkey;
 	dma_addr_t dma_addr;
 	void *addr;
 	size_t size;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/uar.c b/drivers/net/ethernet/mellanox/mlx5/core/uar.c
index da481a7c12f4..01e9c412977c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/uar.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/uar.c
@@ -36,7 +36,7 @@
 #include <linux/mlx5/driver.h>
 #include "mlx5_core.h"
 
-int mlx5_cmd_alloc_uar(struct mlx5_core_dev *dev, u32 *uarn)
+static int mlx5_cmd_alloc_uar(struct mlx5_core_dev *dev, u32 *uarn)
 {
 	u32 out[MLX5_ST_SZ_DW(alloc_uar_out)] = {};
 	u32 in[MLX5_ST_SZ_DW(alloc_uar_in)] = {};
@@ -44,13 +44,14 @@ int mlx5_cmd_alloc_uar(struct mlx5_core_dev *dev, u32 *uarn)
 
 	MLX5_SET(alloc_uar_in, in, opcode, MLX5_CMD_OP_ALLOC_UAR);
 	err = mlx5_cmd_exec_inout(dev, alloc_uar, in, out);
-	if (!err)
-		*uarn = MLX5_GET(alloc_uar_out, out, uar);
-	return err;
+	if (err)
+		return err;
+
+	*uarn = MLX5_GET(alloc_uar_out, out, uar);
+	return 0;
 }
-EXPORT_SYMBOL(mlx5_cmd_alloc_uar);
 
-int mlx5_cmd_free_uar(struct mlx5_core_dev *dev, u32 uarn)
+static int mlx5_cmd_free_uar(struct mlx5_core_dev *dev, u32 uarn)
 {
 	u32 in[MLX5_ST_SZ_DW(dealloc_uar_in)] = {};
 
@@ -58,7 +59,6 @@ int mlx5_cmd_free_uar(struct mlx5_core_dev *dev, u32 uarn)
 	MLX5_SET(dealloc_uar_in, in, uar, uarn);
 	return mlx5_cmd_exec_in(dev, dealloc_uar, in);
 }
-EXPORT_SYMBOL(mlx5_cmd_free_uar);
 
 static int uars_per_sys_page(struct mlx5_core_dev *mdev)
 {
diff --git a/drivers/vdpa/mlx5/core/mlx5_vdpa.h b/drivers/vdpa/mlx5/core/mlx5_vdpa.h
index 01a848adf590..3163b313a470 100644
--- a/drivers/vdpa/mlx5/core/mlx5_vdpa.h
+++ b/drivers/vdpa/mlx5/core/mlx5_vdpa.h
@@ -15,7 +15,7 @@ struct mlx5_vdpa_direct_mr {
 	u64 start;
 	u64 end;
 	u32 perm;
-	struct mlx5_core_mkey mr;
+	u32 mr;
 	struct sg_table sg_head;
 	int log_size;
 	int nsg;
@@ -25,7 +25,7 @@ struct mlx5_vdpa_direct_mr {
 };
 
 struct mlx5_vdpa_mr {
-	struct mlx5_core_mkey mkey;
+	u32 mkey;
 
 	/* list of direct MRs descendants of this indirect mr */
 	struct list_head head;
@@ -99,9 +99,9 @@ int mlx5_vdpa_alloc_transport_domain(struct mlx5_vdpa_dev *mvdev, u32 *tdn);
 void mlx5_vdpa_dealloc_transport_domain(struct mlx5_vdpa_dev *mvdev, u32 tdn);
 int mlx5_vdpa_alloc_resources(struct mlx5_vdpa_dev *mvdev);
 void mlx5_vdpa_free_resources(struct mlx5_vdpa_dev *mvdev);
-int mlx5_vdpa_create_mkey(struct mlx5_vdpa_dev *mvdev, struct mlx5_core_mkey *mkey, u32 *in,
+int mlx5_vdpa_create_mkey(struct mlx5_vdpa_dev *mvdev, u32 *mkey, u32 *in,
 			  int inlen);
-int mlx5_vdpa_destroy_mkey(struct mlx5_vdpa_dev *mvdev, struct mlx5_core_mkey *mkey);
+int mlx5_vdpa_destroy_mkey(struct mlx5_vdpa_dev *mvdev, u32 mkey);
 int mlx5_vdpa_handle_set_map(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *iotlb,
 			     bool *change_map);
 int mlx5_vdpa_create_mr(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *iotlb);
diff --git a/drivers/vdpa/mlx5/core/mr.c b/drivers/vdpa/mlx5/core/mr.c
index ff010c6d0cd3..a639b9208d41 100644
--- a/drivers/vdpa/mlx5/core/mr.c
+++ b/drivers/vdpa/mlx5/core/mr.c
@@ -88,7 +88,7 @@ static int create_direct_mr(struct mlx5_vdpa_dev *mvdev, struct mlx5_vdpa_direct
 
 static void destroy_direct_mr(struct mlx5_vdpa_dev *mvdev, struct mlx5_vdpa_direct_mr *mr)
 {
-	mlx5_vdpa_destroy_mkey(mvdev, &mr->mr);
+	mlx5_vdpa_destroy_mkey(mvdev, mr->mr);
 }
 
 static u64 map_start(struct vhost_iotlb_map *map, struct mlx5_vdpa_direct_mr *mr)
@@ -162,7 +162,7 @@ again:
 		}
 
 		if (preve == dmr->start) {
-			klm->key = cpu_to_be32(dmr->mr.key);
+			klm->key = cpu_to_be32(dmr->mr);
 			klm->bcount = cpu_to_be32(klm_bcount(dmr->end - dmr->start));
 			preve = dmr->end;
 		} else {
@@ -217,7 +217,7 @@ static int create_indirect_key(struct mlx5_vdpa_dev *mvdev, struct mlx5_vdpa_mr
 
 static void destroy_indirect_key(struct mlx5_vdpa_dev *mvdev, struct mlx5_vdpa_mr *mkey)
 {
-	mlx5_vdpa_destroy_mkey(mvdev, &mkey->mkey);
+	mlx5_vdpa_destroy_mkey(mvdev, mkey->mkey);
 }
 
 static int map_direct_mr(struct mlx5_vdpa_dev *mvdev, struct mlx5_vdpa_direct_mr *mr,
@@ -449,7 +449,7 @@ static int create_dma_mr(struct mlx5_vdpa_dev *mvdev, struct mlx5_vdpa_mr *mr)
 
 static void destroy_dma_mr(struct mlx5_vdpa_dev *mvdev, struct mlx5_vdpa_mr *mr)
 {
-	mlx5_vdpa_destroy_mkey(mvdev, &mr->mkey);
+	mlx5_vdpa_destroy_mkey(mvdev, mr->mkey);
 }
 
 static int dup_iotlb(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *src)
diff --git a/drivers/vdpa/mlx5/core/resources.c b/drivers/vdpa/mlx5/core/resources.c
index 15e266d0e27a..9800f9bec225 100644
--- a/drivers/vdpa/mlx5/core/resources.c
+++ b/drivers/vdpa/mlx5/core/resources.c
@@ -198,12 +198,11 @@ void mlx5_vdpa_dealloc_transport_domain(struct mlx5_vdpa_dev *mvdev, u32 tdn)
 	mlx5_cmd_exec_in(mvdev->mdev, dealloc_transport_domain, in);
 }
 
-int mlx5_vdpa_create_mkey(struct mlx5_vdpa_dev *mvdev, struct mlx5_core_mkey *mkey, u32 *in,
+int mlx5_vdpa_create_mkey(struct mlx5_vdpa_dev *mvdev, u32 *mkey, u32 *in,
 			  int inlen)
 {
 	u32 lout[MLX5_ST_SZ_DW(create_mkey_out)] = {};
 	u32 mkey_index;
-	void *mkc;
 	int err;
 
 	MLX5_SET(create_mkey_in, in, opcode, MLX5_CMD_OP_CREATE_MKEY);
@@ -213,22 +212,18 @@ int mlx5_vdpa_create_mkey(struct mlx5_vdpa_dev *mvdev, struct mlx5_core_mkey *mk
 	if (err)
 		return err;
 
-	mkc = MLX5_ADDR_OF(create_mkey_in, in, memory_key_mkey_entry);
 	mkey_index = MLX5_GET(create_mkey_out, lout, mkey_index);
-	mkey->iova = MLX5_GET64(mkc, mkc, start_addr);
-	mkey->size = MLX5_GET64(mkc, mkc, len);
-	mkey->key |= mlx5_idx_to_mkey(mkey_index);
-	mkey->pd = MLX5_GET(mkc, mkc, pd);
+	*mkey |= mlx5_idx_to_mkey(mkey_index);
 	return 0;
 }
 
-int mlx5_vdpa_destroy_mkey(struct mlx5_vdpa_dev *mvdev, struct mlx5_core_mkey *mkey)
+int mlx5_vdpa_destroy_mkey(struct mlx5_vdpa_dev *mvdev, u32 mkey)
 {
 	u32 in[MLX5_ST_SZ_DW(destroy_mkey_in)] = {};
 
 	MLX5_SET(destroy_mkey_in, in, uid, mvdev->res.uid);
 	MLX5_SET(destroy_mkey_in, in, opcode, MLX5_CMD_OP_DESTROY_MKEY);
-	MLX5_SET(destroy_mkey_in, in, mkey_index, mlx5_mkey_to_idx(mkey->key));
+	MLX5_SET(destroy_mkey_in, in, mkey_index, mlx5_mkey_to_idx(mkey));
 	return mlx5_cmd_exec_in(mvdev->mdev, destroy_mkey, in);
 }
 
diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c
index bd56de7484dc..5c7d2a953dbd 100644
--- a/drivers/vdpa/mlx5/net/mlx5_vnet.c
+++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c
@@ -865,7 +865,7 @@ static int create_virtqueue(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtque
 	MLX5_SET64(virtio_q, vq_ctx, desc_addr, mvq->desc_addr);
 	MLX5_SET64(virtio_q, vq_ctx, used_addr, mvq->device_addr);
 	MLX5_SET64(virtio_q, vq_ctx, available_addr, mvq->driver_addr);
-	MLX5_SET(virtio_q, vq_ctx, virtio_q_mkey, ndev->mvdev.mr.mkey.key);
+	MLX5_SET(virtio_q, vq_ctx, virtio_q_mkey, ndev->mvdev.mr.mkey);
 	MLX5_SET(virtio_q, vq_ctx, umem_1_id, mvq->umem1.id);
 	MLX5_SET(virtio_q, vq_ctx, umem_1_size, mvq->umem1.size);
 	MLX5_SET(virtio_q, vq_ctx, umem_2_id, mvq->umem2.id);
diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h
index 56bcf95d4ab7..9c25edfd59a6 100644
--- a/include/linux/mlx5/device.h
+++ b/include/linux/mlx5/device.h
@@ -1493,6 +1493,8 @@ static inline u16 mlx5_to_sw_pkey_sz(int pkey_sz)
 	return MLX5_MIN_PKEY_TABLE_SIZE << pkey_sz;
 }
 
+#define MLX5_RDMA_RX_NUM_COUNTERS_PRIOS 2
+#define MLX5_RDMA_TX_NUM_COUNTERS_PRIOS 1
 #define MLX5_BY_PASS_NUM_REGULAR_PRIOS 16
 #define MLX5_BY_PASS_NUM_DONT_TRAP_PRIOS 16
 #define MLX5_BY_PASS_NUM_MULTICAST_PRIOS 1
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index f617dfbcd9fd..a623ec635947 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -357,22 +357,6 @@ struct mlx5_core_sig_ctx {
 	u32			sigerr_count;
 };
 
-enum {
-	MLX5_MKEY_MR = 1,
-	MLX5_MKEY_MW,
-	MLX5_MKEY_INDIRECT_DEVX,
-};
-
-struct mlx5_core_mkey {
-	u64			iova;
-	u64			size;
-	u32			key;
-	u32			pd;
-	u32			type;
-	struct wait_queue_head wait;
-	refcount_t usecount;
-};
-
 #define MLX5_24BIT_MASK		((1 << 24) - 1)
 
 enum mlx5_res_type {
@@ -654,7 +638,7 @@ struct mlx5e_resources {
 	struct mlx5e_hw_objs {
 		u32                        pdn;
 		struct mlx5_td             td;
-		struct mlx5_core_mkey      mkey;
+		u32			   mkey;
 		struct mlx5_sq_bfreg       bfreg;
 	} hw_objs;
 	struct devlink_port dl_port;
@@ -1007,8 +991,6 @@ void mlx5_cmd_mbox_status(void *out, u8 *status, u32 *syndrome);
 bool mlx5_cmd_is_down(struct mlx5_core_dev *dev);
 
 int mlx5_core_get_caps(struct mlx5_core_dev *dev, enum mlx5_cap_type cap_type);
-int mlx5_cmd_alloc_uar(struct mlx5_core_dev *dev, u32 *uarn);
-int mlx5_cmd_free_uar(struct mlx5_core_dev *dev, u32 uarn);
 void mlx5_health_flush(struct mlx5_core_dev *dev);
 void mlx5_health_cleanup(struct mlx5_core_dev *dev);
 int mlx5_health_init(struct mlx5_core_dev *dev);
@@ -1026,13 +1008,11 @@ struct mlx5_cmd_mailbox *mlx5_alloc_cmd_mailbox_chain(struct mlx5_core_dev *dev,
 						      gfp_t flags, int npages);
 void mlx5_free_cmd_mailbox_chain(struct mlx5_core_dev *dev,
 				 struct mlx5_cmd_mailbox *head);
-int mlx5_core_create_mkey(struct mlx5_core_dev *dev,
-			  struct mlx5_core_mkey *mkey,
-			  u32 *in, int inlen);
-int mlx5_core_destroy_mkey(struct mlx5_core_dev *dev,
-			   struct mlx5_core_mkey *mkey);
-int mlx5_core_query_mkey(struct mlx5_core_dev *dev, struct mlx5_core_mkey *mkey,
-			 u32 *out, int outlen);
+int mlx5_core_create_mkey(struct mlx5_core_dev *dev, u32 *mkey, u32 *in,
+			  int inlen);
+int mlx5_core_destroy_mkey(struct mlx5_core_dev *dev, u32 mkey);
+int mlx5_core_query_mkey(struct mlx5_core_dev *dev, u32 mkey, u32 *out,
+			 int outlen);
 int mlx5_core_alloc_pd(struct mlx5_core_dev *dev, u32 *pdn);
 int mlx5_core_dealloc_pd(struct mlx5_core_dev *dev, u32 pdn);
 int mlx5_pagealloc_init(struct mlx5_core_dev *dev);
diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h
index 7a43fec63a35..a7e1155bc4da 100644
--- a/include/linux/mlx5/fs.h
+++ b/include/linux/mlx5/fs.h
@@ -84,6 +84,8 @@ enum mlx5_flow_namespace_type {
 	MLX5_FLOW_NAMESPACE_RDMA_RX_KERNEL,
 	MLX5_FLOW_NAMESPACE_RDMA_TX,
 	MLX5_FLOW_NAMESPACE_PORT_SEL,
+	MLX5_FLOW_NAMESPACE_RDMA_RX_COUNTERS,
+	MLX5_FLOW_NAMESPACE_RDMA_TX_COUNTERS,
 };
 
 enum {
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 0bb78c04336c..3636df90899a 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -343,7 +343,7 @@ struct mlx5_ifc_flow_table_fields_supported_bits {
 	u8         outer_geneve_oam[0x1];
 	u8         outer_geneve_protocol_type[0x1];
 	u8         outer_geneve_opt_len[0x1];
-	u8         reserved_at_1e[0x1];
+	u8         source_vhca_port[0x1];
 	u8         source_eswitch_port[0x1];
 
 	u8         inner_dmac[0x1];
@@ -394,6 +394,14 @@ struct mlx5_ifc_flow_table_fields_supported_bits {
 	u8         metadata_reg_c_0[0x1];
 };
 
+struct mlx5_ifc_flow_table_fields_supported_2_bits {
+	u8         reserved_at_0[0xe];
+	u8         bth_opcode[0x1];
+	u8         reserved_at_f[0x11];
+
+	u8         reserved_at_20[0x60];
+};
+
 struct mlx5_ifc_flow_table_prop_layout_bits {
 	u8         ft_support[0x1];
 	u8         reserved_at_1[0x1];
@@ -540,7 +548,7 @@ struct mlx5_ifc_fte_match_set_misc_bits {
 	union mlx5_ifc_gre_key_bits gre_key;
 
 	u8         vxlan_vni[0x18];
-	u8         reserved_at_b8[0x8];
+	u8         bth_opcode[0x8];
 
 	u8         geneve_vni[0x18];
 	u8         reserved_at_d8[0x7];
@@ -757,7 +765,15 @@ struct mlx5_ifc_flow_table_nic_cap_bits {
 
 	struct mlx5_ifc_flow_table_prop_layout_bits flow_table_properties_nic_transmit_sniffer;
 
-	u8         reserved_at_e00[0x1200];
+	u8         reserved_at_e00[0x700];
+
+	struct mlx5_ifc_flow_table_fields_supported_2_bits ft_field_support_2_nic_receive_rdma;
+
+	u8         reserved_at_1580[0x280];
+
+	struct mlx5_ifc_flow_table_fields_supported_2_bits ft_field_support_2_nic_transmit_rdma;
+
+	u8         reserved_at_1880[0x780];
 
 	u8         sw_steering_nic_rx_action_drop_icm_address[0x40];
 
@@ -7907,7 +7923,7 @@ struct mlx5_ifc_dealloc_uar_out_bits {
 
 struct mlx5_ifc_dealloc_uar_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_at_10[0x10];
+	u8         uid[0x10];
 
 	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
@@ -8764,7 +8780,7 @@ struct mlx5_ifc_alloc_uar_out_bits {
 
 struct mlx5_ifc_alloc_uar_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_at_10[0x10];
+	u8         uid[0x10];
 
 	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];